[Python-3000-checkins] r46754 - in python/branches/p3yk: Demo/README Demo/classes/Dates.py Demo/curses/README Demo/curses/life.py Demo/curses/rain.py Demo/curses/repeat.py Demo/curses/tclock.py Demo/curses/xmas.py Demo/sockets/README Demo/sockets/unixclient.py Demo/sockets/unixserver.py Demo/threads/fcmp.py Demo/xmlrpc Demo/zlib/minigzip.py Demo/zlib/zlibdemo.py Doc/api/newtypes.tex Doc/dist/dist.tex Doc/lib/libdoctest.tex Doc/lib/libfunctools.tex Doc/lib/libsgmllib.tex Doc/lib/libsocket.tex Doc/lib/libsqlite3.tex Doc/lib/liburllib2.tex Doc/mac/undoc.tex Doc/whatsnew/whatsnew25.tex Include/symtable.h Include/unicodeobject.h Lib/bsddb/__init__.py Lib/bsddb/dbobj.py Lib/bsddb/dbtables.py Lib/bsddb/test/test_all.py Lib/bsddb/test/test_basics.py Lib/bsddb/test/test_cursor_pget_bug.py Lib/bsddb/test/test_dbtables.py Lib/bsddb/test/test_sequence.py Lib/ctypes/test/test_cfuncs.py Lib/ctypes/test/test_pointers.py Lib/ctypes/test/test_structures.py Lib/doctest.py Lib/encodings/cp037.py Lib/encodings/cp1006.py Lib/encodings/cp1026.py Lib/encodings/cp1140.py Lib/encodings/cp1250.py Lib/encodings/cp1251.py Lib/encodings/cp1252.py Lib/encodings/cp1253.py Lib/encodings/cp1254.py Lib/encodings/cp1255.py Lib/encodings/cp1256.py Lib/encodings/cp1257.py Lib/encodings/cp1258.py Lib/encodings/cp424.py Lib/encodings/cp500.py Lib/encodings/cp856.py Lib/encodings/cp874.py Lib/encodings/cp875.py Lib/encodings/iso8859_1.py Lib/encodings/iso8859_10.py Lib/encodings/iso8859_11.py Lib/encodings/iso8859_13.py Lib/encodings/iso8859_14.py Lib/encodings/iso8859_15.py Lib/encodings/iso8859_16.py Lib/encodings/iso8859_2.py Lib/encodings/iso8859_3.py Lib/encodings/iso8859_4.py Lib/encodings/iso8859_5.py Lib/encodings/iso8859_6.py Lib/encodings/iso8859_7.py Lib/encodings/iso8859_8.py Lib/encodings/iso8859_9.py Lib/encodings/koi8_r.py Lib/encodings/koi8_u.py Lib/encodings/mac_centeuro.py Lib/encodings/mac_croatian.py Lib/encodings/mac_cyrillic.py Lib/encodings/mac_farsi.py Lib/encodings/mac_greek.py Lib/encodings/mac_iceland.py Lib/encodings/mac_roman.py Lib/encodings/mac_romanian.py Lib/encodings/mac_turkish.py Lib/encodings/tis_620.py Lib/functools.py Lib/lib-tk/Tix.py Lib/markupbase.py Lib/plat-mac/Carbon/WASTEconst.py Lib/plat-mac/EasyDialogs.py Lib/plat-mac/WASTEconst.py Lib/plat-mac/argvemulator.py Lib/smtplib.py Lib/socket.py Lib/struct.py Lib/subprocess.py Lib/test/regrtest.py Lib/test/test_bsddb3.py Lib/test/test_builtin.py Lib/test/test_class.py Lib/test/test_descr.py Lib/test/test_doctest.py Lib/test/test_exceptions.py Lib/test/test_file.py Lib/test/test_functools.py Lib/test/test_generators.py Lib/test/test_socket.py Lib/test/test_struct.py Lib/test/test_tempfile.py Mac/BuildScript Mac/Demo/index.html Mac/Demo/textedit.html Mac/Demo/waste Mac/Demo/waste.html Mac/Extras.ReadMe.txt Mac/Extras.install.py Mac/IDLE Mac/Icons Mac/Makefile.in Mac/Modules/waste Mac/OSX Mac/OSXResources Mac/PythonLauncher Mac/README Mac/Resources Mac/Tools Mac/scripts/BuildApplet.py Makefile.pre.in Misc/SpecialBuilds.txt Modules/_bsddb.c Modules/_codecsmodule.c Modules/_ctypes/callbacks.c Modules/_ctypes/callproc.c Modules/_ctypes/cfield.c Modules/_elementtree.c Modules/_struct.c Modules/_tkinter.c Modules/cjkcodecs/_codecs_jp.c Modules/socketmodule.c Objects/abstract.c Objects/classobject.c Objects/descrobject.c Objects/exceptions.c Objects/fileobject.c Objects/obmalloc.c Objects/unicodeobject.c PC/_subprocess.c PC/py.ico PC/pyc.ico PC/pycon.ico Parser/node.c Python/compile.c Python/symtable.c Python/sysmodule.c Python/thread.c Python/thread_nt.h Python/thread_os2.h Tools/unicode/Makefile Tools/unicode/gencodec.py Tools/webchecker/webchecker.py configure configure.in setup.py
thomas.wouters
python-3000-checkins at python.org
Thu Jun 8 17:36:29 CEST 2006
Author: thomas.wouters
Date: Thu Jun 8 17:35:45 2006
New Revision: 46754
Added:
python/branches/p3yk/Lib/bsddb/test/test_cursor_pget_bug.py
- copied unchanged from r46752, python/trunk/Lib/bsddb/test/test_cursor_pget_bug.py
python/branches/p3yk/Lib/bsddb/test/test_sequence.py
- copied unchanged from r46752, python/trunk/Lib/bsddb/test/test_sequence.py
python/branches/p3yk/Mac/BuildScript/
- copied from r46752, python/trunk/Mac/BuildScript/
python/branches/p3yk/Mac/Extras.ReadMe.txt
- copied unchanged from r46752, python/trunk/Mac/Extras.ReadMe.txt
python/branches/p3yk/Mac/Extras.install.py
- copied unchanged from r46752, python/trunk/Mac/Extras.install.py
python/branches/p3yk/Mac/IDLE/
- copied from r46752, python/trunk/Mac/IDLE/
python/branches/p3yk/Mac/Icons/
- copied from r46752, python/trunk/Mac/Icons/
python/branches/p3yk/Mac/Makefile.in
- copied unchanged from r46752, python/trunk/Mac/Makefile.in
python/branches/p3yk/Mac/PythonLauncher/ (props changed)
- copied from r46752, python/trunk/Mac/PythonLauncher/
python/branches/p3yk/Mac/README
- copied unchanged from r46752, python/trunk/Mac/README
python/branches/p3yk/Mac/Resources/
- copied from r46752, python/trunk/Mac/Resources/
python/branches/p3yk/Mac/Tools/
- copied from r46752, python/trunk/Mac/Tools/
Removed:
python/branches/p3yk/Demo/xmlrpc/
python/branches/p3yk/Lib/plat-mac/Carbon/WASTEconst.py
python/branches/p3yk/Lib/plat-mac/WASTEconst.py
python/branches/p3yk/Mac/Demo/waste/
python/branches/p3yk/Mac/Demo/waste.html
python/branches/p3yk/Mac/Modules/waste/
python/branches/p3yk/Mac/OSX/
python/branches/p3yk/Mac/OSXResources/
Modified:
python/branches/p3yk/ (props changed)
python/branches/p3yk/Demo/README
python/branches/p3yk/Demo/classes/Dates.py
python/branches/p3yk/Demo/curses/README
python/branches/p3yk/Demo/curses/life.py
python/branches/p3yk/Demo/curses/rain.py
python/branches/p3yk/Demo/curses/repeat.py
python/branches/p3yk/Demo/curses/tclock.py
python/branches/p3yk/Demo/curses/xmas.py
python/branches/p3yk/Demo/sockets/README
python/branches/p3yk/Demo/sockets/unixclient.py
python/branches/p3yk/Demo/sockets/unixserver.py
python/branches/p3yk/Demo/threads/fcmp.py
python/branches/p3yk/Demo/zlib/minigzip.py
python/branches/p3yk/Demo/zlib/zlibdemo.py
python/branches/p3yk/Doc/api/newtypes.tex
python/branches/p3yk/Doc/dist/dist.tex
python/branches/p3yk/Doc/lib/libdoctest.tex
python/branches/p3yk/Doc/lib/libfunctools.tex
python/branches/p3yk/Doc/lib/libsgmllib.tex
python/branches/p3yk/Doc/lib/libsocket.tex
python/branches/p3yk/Doc/lib/libsqlite3.tex
python/branches/p3yk/Doc/lib/liburllib2.tex
python/branches/p3yk/Doc/mac/undoc.tex
python/branches/p3yk/Doc/whatsnew/whatsnew25.tex
python/branches/p3yk/Include/symtable.h
python/branches/p3yk/Include/unicodeobject.h
python/branches/p3yk/Lib/bsddb/__init__.py
python/branches/p3yk/Lib/bsddb/dbobj.py
python/branches/p3yk/Lib/bsddb/dbtables.py
python/branches/p3yk/Lib/bsddb/test/test_all.py
python/branches/p3yk/Lib/bsddb/test/test_basics.py
python/branches/p3yk/Lib/bsddb/test/test_dbtables.py
python/branches/p3yk/Lib/ctypes/test/test_cfuncs.py
python/branches/p3yk/Lib/ctypes/test/test_pointers.py
python/branches/p3yk/Lib/ctypes/test/test_structures.py
python/branches/p3yk/Lib/doctest.py
python/branches/p3yk/Lib/encodings/cp037.py
python/branches/p3yk/Lib/encodings/cp1006.py
python/branches/p3yk/Lib/encodings/cp1026.py
python/branches/p3yk/Lib/encodings/cp1140.py
python/branches/p3yk/Lib/encodings/cp1250.py
python/branches/p3yk/Lib/encodings/cp1251.py
python/branches/p3yk/Lib/encodings/cp1252.py
python/branches/p3yk/Lib/encodings/cp1253.py
python/branches/p3yk/Lib/encodings/cp1254.py
python/branches/p3yk/Lib/encodings/cp1255.py
python/branches/p3yk/Lib/encodings/cp1256.py
python/branches/p3yk/Lib/encodings/cp1257.py
python/branches/p3yk/Lib/encodings/cp1258.py
python/branches/p3yk/Lib/encodings/cp424.py
python/branches/p3yk/Lib/encodings/cp500.py
python/branches/p3yk/Lib/encodings/cp856.py
python/branches/p3yk/Lib/encodings/cp874.py
python/branches/p3yk/Lib/encodings/cp875.py
python/branches/p3yk/Lib/encodings/iso8859_1.py
python/branches/p3yk/Lib/encodings/iso8859_10.py
python/branches/p3yk/Lib/encodings/iso8859_11.py
python/branches/p3yk/Lib/encodings/iso8859_13.py
python/branches/p3yk/Lib/encodings/iso8859_14.py
python/branches/p3yk/Lib/encodings/iso8859_15.py
python/branches/p3yk/Lib/encodings/iso8859_16.py
python/branches/p3yk/Lib/encodings/iso8859_2.py
python/branches/p3yk/Lib/encodings/iso8859_3.py
python/branches/p3yk/Lib/encodings/iso8859_4.py
python/branches/p3yk/Lib/encodings/iso8859_5.py
python/branches/p3yk/Lib/encodings/iso8859_6.py
python/branches/p3yk/Lib/encodings/iso8859_7.py
python/branches/p3yk/Lib/encodings/iso8859_8.py
python/branches/p3yk/Lib/encodings/iso8859_9.py
python/branches/p3yk/Lib/encodings/koi8_r.py
python/branches/p3yk/Lib/encodings/koi8_u.py
python/branches/p3yk/Lib/encodings/mac_centeuro.py
python/branches/p3yk/Lib/encodings/mac_croatian.py
python/branches/p3yk/Lib/encodings/mac_cyrillic.py
python/branches/p3yk/Lib/encodings/mac_farsi.py
python/branches/p3yk/Lib/encodings/mac_greek.py
python/branches/p3yk/Lib/encodings/mac_iceland.py
python/branches/p3yk/Lib/encodings/mac_roman.py
python/branches/p3yk/Lib/encodings/mac_romanian.py
python/branches/p3yk/Lib/encodings/mac_turkish.py
python/branches/p3yk/Lib/encodings/tis_620.py
python/branches/p3yk/Lib/functools.py
python/branches/p3yk/Lib/lib-tk/Tix.py
python/branches/p3yk/Lib/markupbase.py
python/branches/p3yk/Lib/plat-mac/EasyDialogs.py
python/branches/p3yk/Lib/plat-mac/argvemulator.py
python/branches/p3yk/Lib/smtplib.py
python/branches/p3yk/Lib/socket.py
python/branches/p3yk/Lib/struct.py
python/branches/p3yk/Lib/subprocess.py
python/branches/p3yk/Lib/test/regrtest.py
python/branches/p3yk/Lib/test/test_bsddb3.py
python/branches/p3yk/Lib/test/test_builtin.py
python/branches/p3yk/Lib/test/test_class.py
python/branches/p3yk/Lib/test/test_descr.py
python/branches/p3yk/Lib/test/test_doctest.py
python/branches/p3yk/Lib/test/test_exceptions.py
python/branches/p3yk/Lib/test/test_file.py
python/branches/p3yk/Lib/test/test_functools.py
python/branches/p3yk/Lib/test/test_generators.py
python/branches/p3yk/Lib/test/test_socket.py
python/branches/p3yk/Lib/test/test_struct.py
python/branches/p3yk/Lib/test/test_tempfile.py
python/branches/p3yk/Mac/Demo/index.html
python/branches/p3yk/Mac/Demo/textedit.html
python/branches/p3yk/Mac/scripts/BuildApplet.py
python/branches/p3yk/Makefile.pre.in
python/branches/p3yk/Misc/SpecialBuilds.txt
python/branches/p3yk/Modules/_bsddb.c
python/branches/p3yk/Modules/_codecsmodule.c
python/branches/p3yk/Modules/_ctypes/callbacks.c
python/branches/p3yk/Modules/_ctypes/callproc.c
python/branches/p3yk/Modules/_ctypes/cfield.c
python/branches/p3yk/Modules/_elementtree.c
python/branches/p3yk/Modules/_struct.c
python/branches/p3yk/Modules/_tkinter.c
python/branches/p3yk/Modules/cjkcodecs/_codecs_jp.c
python/branches/p3yk/Modules/socketmodule.c
python/branches/p3yk/Objects/abstract.c
python/branches/p3yk/Objects/classobject.c
python/branches/p3yk/Objects/descrobject.c
python/branches/p3yk/Objects/exceptions.c
python/branches/p3yk/Objects/fileobject.c
python/branches/p3yk/Objects/obmalloc.c
python/branches/p3yk/Objects/unicodeobject.c
python/branches/p3yk/PC/_subprocess.c
python/branches/p3yk/PC/py.ico
python/branches/p3yk/PC/pyc.ico
python/branches/p3yk/PC/pycon.ico
python/branches/p3yk/Parser/node.c
python/branches/p3yk/Python/compile.c
python/branches/p3yk/Python/symtable.c
python/branches/p3yk/Python/sysmodule.c
python/branches/p3yk/Python/thread.c
python/branches/p3yk/Python/thread_nt.h
python/branches/p3yk/Python/thread_os2.h
python/branches/p3yk/Tools/unicode/Makefile
python/branches/p3yk/Tools/unicode/gencodec.py
python/branches/p3yk/Tools/webchecker/webchecker.py
python/branches/p3yk/configure
python/branches/p3yk/configure.in
python/branches/p3yk/setup.py
Log:
Merge the rest of the trunk.
Merged revisions 46490-46494,46496,46498,46500,46506,46521,46538,46558,46563-46567,46570-46571,46583,46593,46595-46598,46604,46606,46609-46753 via svnmerge from
svn+ssh://pythondev@svn.python.org/python/trunk
........
r46610 | martin.v.loewis | 2006-06-03 09:42:26 +0200 (Sat, 03 Jun 2006) | 2 lines
Updated version (win32-icons2.zip) from #1490384.
........
r46612 | andrew.kuchling | 2006-06-03 20:09:41 +0200 (Sat, 03 Jun 2006) | 1 line
[Bug #1472084] Fix description of do_tag
........
r46614 | andrew.kuchling | 2006-06-03 20:33:35 +0200 (Sat, 03 Jun 2006) | 1 line
[Bug #1475554] Strengthen text to say 'must' instead of 'should'
........
r46616 | andrew.kuchling | 2006-06-03 20:41:28 +0200 (Sat, 03 Jun 2006) | 1 line
[Bug #1441864] Clarify description of 'data' argument
........
r46617 | andrew.kuchling | 2006-06-03 20:43:24 +0200 (Sat, 03 Jun 2006) | 1 line
Minor rewording
........
r46619 | andrew.kuchling | 2006-06-03 21:02:35 +0200 (Sat, 03 Jun 2006) | 9 lines
[Bug #1497414] _self is a reserved word in the WATCOM 10.6 C compiler.
Fix by renaming the variable.
In a different module, Neal fixed it by renaming _self to self. There's
already a variable named 'self' here, so I used selfptr.
(I'm committing this on a Mac without Tk, but it's a simple search-and-replace.
<crosses fingers>, so I'll watch the buildbots and see what happens.)
........
r46621 | fredrik.lundh | 2006-06-03 23:56:05 +0200 (Sat, 03 Jun 2006) | 5 lines
"_self" is a said to be a reserved word in Watcom C 10.6. I'm
not sure that's really standard compliant behaviour, but I guess
we have to fix that anyway...
........
r46622 | andrew.kuchling | 2006-06-04 00:44:42 +0200 (Sun, 04 Jun 2006) | 1 line
Update readme
........
r46623 | andrew.kuchling | 2006-06-04 00:59:23 +0200 (Sun, 04 Jun 2006) | 1 line
Drop 0 parameter
........
r46624 | andrew.kuchling | 2006-06-04 00:59:59 +0200 (Sun, 04 Jun 2006) | 1 line
Some code tidying; use curses.wrapper
........
r46625 | andrew.kuchling | 2006-06-04 01:02:15 +0200 (Sun, 04 Jun 2006) | 1 line
Use True; value returned from main is unused
........
r46626 | andrew.kuchling | 2006-06-04 01:07:21 +0200 (Sun, 04 Jun 2006) | 1 line
Use true division, and the True value
........
r46627 | andrew.kuchling | 2006-06-04 01:09:58 +0200 (Sun, 04 Jun 2006) | 1 line
Docstring fix; use True
........
r46628 | andrew.kuchling | 2006-06-04 01:15:56 +0200 (Sun, 04 Jun 2006) | 1 line
Put code in a main() function; loosen up the spacing to match current code style
........
r46629 | andrew.kuchling | 2006-06-04 01:39:07 +0200 (Sun, 04 Jun 2006) | 1 line
Use functions; modernize code
........
r46630 | andrew.kuchling | 2006-06-04 01:43:22 +0200 (Sun, 04 Jun 2006) | 1 line
This demo requires Medusa (not just asyncore); remove it
........
r46631 | andrew.kuchling | 2006-06-04 01:46:36 +0200 (Sun, 04 Jun 2006) | 2 lines
Remove xmlrpc demo -- it duplicates the SimpleXMLRPCServer module.
........
r46632 | andrew.kuchling | 2006-06-04 01:47:22 +0200 (Sun, 04 Jun 2006) | 1 line
Remove xmlrpc/ directory
........
r46633 | andrew.kuchling | 2006-06-04 01:51:21 +0200 (Sun, 04 Jun 2006) | 1 line
Remove dangling reference
........
r46634 | andrew.kuchling | 2006-06-04 01:59:36 +0200 (Sun, 04 Jun 2006) | 1 line
Add more whitespace; use a better socket name
........
r46635 | tim.peters | 2006-06-04 03:22:53 +0200 (Sun, 04 Jun 2006) | 2 lines
Whitespace normalization.
........
r46637 | tim.peters | 2006-06-04 05:26:02 +0200 (Sun, 04 Jun 2006) | 16 lines
In a PYMALLOC_DEBUG build obmalloc adds extra debugging info
to each allocated block. This was using 4 bytes for each such
piece of info regardless of platform. This didn't really matter
before (proof: no bug reports, and the debug-build obmalloc would
have assert-failed if it was ever asked for a chunk of memory
>= 2**32 bytes), since container indices were plain ints. But after
the Py_ssize_t changes, it's at least theoretically possible to
allocate a list or string whose guts exceed 2**32 bytes, and the
PYMALLOC_DEBUG routines would fail then (having only 4 bytes
to record the originally requested size).
Now we use sizeof(size_t) bytes for each of a PYMALLOC_DEBUG
build's extra debugging fields. This won't make any difference
on 32-bit boxes, but will add 16 bytes to each allocation in
a debug build on a 64-bit box.
........
r46638 | tim.peters | 2006-06-04 05:38:04 +0200 (Sun, 04 Jun 2006) | 4 lines
_PyObject_DebugMalloc(): The return value should add
2*sizeof(size_t) now, not 8. This probably accounts for
current disasters on the 64-bit buildbot slaves.
........
r46639 | neal.norwitz | 2006-06-04 08:19:31 +0200 (Sun, 04 Jun 2006) | 1 line
SF #1499797, Fix for memory leak in WindowsError_str
........
r46640 | andrew.macintyre | 2006-06-04 14:31:09 +0200 (Sun, 04 Jun 2006) | 2 lines
Patch #1454481: Make thread stack size runtime tunable.
........
r46641 | andrew.macintyre | 2006-06-04 14:59:59 +0200 (Sun, 04 Jun 2006) | 2 lines
clean up function declarations to conform to PEP-7 style.
........
r46642 | martin.blais | 2006-06-04 15:49:49 +0200 (Sun, 04 Jun 2006) | 15 lines
Fixes in struct and socket from merge reviews.
- Following Guido's comments, renamed
* pack_to -> pack_into
* recv_buf -> recv_into
* recvfrom_buf -> recvfrom_into
- Made fixes to _struct.c according to Neal Norwitz comments on the checkins
list.
- Converted some ints into the appropriate -- I hope -- ssize_t and size_t.
........
r46643 | ronald.oussoren | 2006-06-04 16:05:28 +0200 (Sun, 04 Jun 2006) | 3 lines
"Import" LDFLAGS in Mac/OSX/Makefile.in to ensure pythonw gets build with
the right compiler flags.
........
r46644 | ronald.oussoren | 2006-06-04 16:24:59 +0200 (Sun, 04 Jun 2006) | 2 lines
Drop Mac wrappers for the WASTE library.
........
r46645 | tim.peters | 2006-06-04 17:49:07 +0200 (Sun, 04 Jun 2006) | 3 lines
s_methods[]: Stop compiler warnings by casting
s_unpack_from to PyCFunction.
........
r46646 | george.yoshida | 2006-06-04 19:04:12 +0200 (Sun, 04 Jun 2006) | 2 lines
Remove a redundant word
........
r46647 | george.yoshida | 2006-06-04 19:17:25 +0200 (Sun, 04 Jun 2006) | 2 lines
Markup fix
........
r46648 | martin.v.loewis | 2006-06-04 21:36:28 +0200 (Sun, 04 Jun 2006) | 2 lines
Patch #1359618: Speed-up charmap encoder.
........
r46649 | georg.brandl | 2006-06-04 23:46:16 +0200 (Sun, 04 Jun 2006) | 3 lines
Repair refleaks in unicodeobject.
........
r46650 | georg.brandl | 2006-06-04 23:56:52 +0200 (Sun, 04 Jun 2006) | 4 lines
Patch #1346214: correctly optimize away "if 0"-style stmts
(thanks to Neal for review)
........
r46651 | georg.brandl | 2006-06-05 00:15:37 +0200 (Mon, 05 Jun 2006) | 2 lines
Bug #1500293: fix memory leaks in _subprocess module.
........
r46654 | tim.peters | 2006-06-05 01:43:53 +0200 (Mon, 05 Jun 2006) | 2 lines
Whitespace normalization.
........
r46655 | tim.peters | 2006-06-05 01:52:47 +0200 (Mon, 05 Jun 2006) | 16 lines
Revert revisions:
46640 Patch #1454481: Make thread stack size runtime tunable.
46647 Markup fix
The first is causing many buildbots to fail test runs, and there
are multiple causes with seemingly no immediate prospects for
repairing them. See python-dev discussion.
Note that a branch can (and should) be created for resolving these
problems, like
svn copy svn+ssh://svn.python.org/python/trunk -r46640 svn+ssh://svn.python.org/python/branches/NEW_BRANCH
followed by merging rev 46647 to the new branch.
........
r46656 | andrew.kuchling | 2006-06-05 02:08:09 +0200 (Mon, 05 Jun 2006) | 1 line
Mention second encoding speedup
........
r46657 | gregory.p.smith | 2006-06-05 02:31:01 +0200 (Mon, 05 Jun 2006) | 7 lines
bugfix: when log_archive was called with the DB_ARCH_REMOVE flag present
in BerkeleyDB >= 4.2 it tried to construct a list out of an uninitialized
char **log_list.
feature: export the DB_ARCH_REMOVE flag by name in the module on BerkeleyDB >= 4.2.
........
r46658 | gregory.p.smith | 2006-06-05 02:33:35 +0200 (Mon, 05 Jun 2006) | 5 lines
fix a bug in the previous commit. don't leak empty list on error return and
fix the additional rare (out of memory only) bug that it was supposed to fix
of not freeing log_list when the python allocator failed.
........
r46660 | tim.peters | 2006-06-05 02:55:26 +0200 (Mon, 05 Jun 2006) | 9 lines
"Flat is better than nested."
Move the long-winded, multiply-nested -R support out
of runtest() and into some module-level helper functions.
This makes runtest() and the -R code easier to follow.
That in turn allowed seeing some opportunities for code
simplification, and made it obvious that reglog.txt
never got closed.
........
r46661 | hyeshik.chang | 2006-06-05 02:59:54 +0200 (Mon, 05 Jun 2006) | 3 lines
Fix a potentially invalid memory access of CJKCodecs' shift-jis
decoder. (found by Neal Norwitz)
........
r46663 | gregory.p.smith | 2006-06-05 03:39:52 +0200 (Mon, 05 Jun 2006) | 3 lines
* support DBEnv.log_stat() method on BerkeleyDB >= 4.0 [patch #1494885]
........
r46664 | tim.peters | 2006-06-05 03:43:03 +0200 (Mon, 05 Jun 2006) | 3 lines
Remove doctest.testmod's deprecated (in 2.4) `isprivate`
argument. A lot of hair went into supporting that!
........
r46665 | tim.peters | 2006-06-05 03:47:24 +0200 (Mon, 05 Jun 2006) | 2 lines
Whitespace normalization.
........
r46666 | tim.peters | 2006-06-05 03:48:21 +0200 (Mon, 05 Jun 2006) | 2 lines
Make doctest news more accurate.
........
r46667 | gregory.p.smith | 2006-06-05 03:56:15 +0200 (Mon, 05 Jun 2006) | 3 lines
* support DBEnv.lsn_reset() method on BerkeleyDB >= 4.4 [patch #1494902]
........
r46668 | gregory.p.smith | 2006-06-05 04:02:25 +0200 (Mon, 05 Jun 2006) | 3 lines
mention the just committed bsddb changes
........
r46671 | gregory.p.smith | 2006-06-05 19:38:04 +0200 (Mon, 05 Jun 2006) | 3 lines
* add support for DBSequence objects [patch #1466734]
........
r46672 | gregory.p.smith | 2006-06-05 20:20:07 +0200 (Mon, 05 Jun 2006) | 3 lines
forgot to add this file in previous commit
........
r46673 | tim.peters | 2006-06-05 20:36:12 +0200 (Mon, 05 Jun 2006) | 2 lines
Whitespace normalization.
........
r46674 | tim.peters | 2006-06-05 20:36:54 +0200 (Mon, 05 Jun 2006) | 2 lines
Add missing svn:eol-style property to text files.
........
r46675 | gregory.p.smith | 2006-06-05 20:48:21 +0200 (Mon, 05 Jun 2006) | 4 lines
* fix DBCursor.pget() bug with keyword argument names when no data= is
supplied [SF pybsddb bug #1477863]
........
r46676 | andrew.kuchling | 2006-06-05 21:05:32 +0200 (Mon, 05 Jun 2006) | 1 line
Remove use of Trove name, which isn't very helpful to users
........
r46677 | andrew.kuchling | 2006-06-05 21:08:25 +0200 (Mon, 05 Jun 2006) | 1 line
[Bug #1470026] Include link to list of classifiers
........
r46679 | tim.peters | 2006-06-05 22:48:49 +0200 (Mon, 05 Jun 2006) | 10 lines
Access _struct attributes directly instead of mucking with getattr.
string_reverse(): Simplify.
assertRaises(): Raise TestFailed on failure.
test_unpack_from(), test_pack_into(), test_pack_into_fn(): never
use `assert` to test for an expected result (it doesn't test anything
when Python is run with -O).
........
r46680 | tim.peters | 2006-06-05 22:49:27 +0200 (Mon, 05 Jun 2006) | 2 lines
Add missing svn:eol-style property to text files.
........
r46681 | gregory.p.smith | 2006-06-06 01:38:06 +0200 (Tue, 06 Jun 2006) | 3 lines
add depends = ['md5.h'] to the _md5 module extension for correctness sake.
........
r46682 | brett.cannon | 2006-06-06 01:51:55 +0200 (Tue, 06 Jun 2006) | 4 lines
Add 3 more bytes to a buffer to cover constants in string and null byte on top of 10 possible digits for an int.
Closes bug #1501223.
........
r46684 | gregory.p.smith | 2006-06-06 01:59:37 +0200 (Tue, 06 Jun 2006) | 5 lines
- bsddb: the __len__ method of a DB object has been fixed to return correct
results. It could previously incorrectly return 0 in some cases.
Fixes SF bug 1493322 (pybsddb bug 1184012).
........
r46686 | tim.peters | 2006-06-06 02:25:07 +0200 (Tue, 06 Jun 2006) | 7 lines
_PySys_Init(): It's rarely a good idea to size a buffer to the
exact maximum size someone guesses is needed. In this case, if
we're really worried about extreme integers, then "cp%d" can
actually need 14 bytes (2 for "cp" + 1 for \0 at the end +
11 for -(2**31-1)). So reserve 128 bytes instead -- nothing is
actually saved by making a stack-local buffer tiny.
........
r46687 | neal.norwitz | 2006-06-06 09:22:08 +0200 (Tue, 06 Jun 2006) | 1 line
Remove unused variable (and stop compiler warning)
........
r46688 | neal.norwitz | 2006-06-06 09:23:01 +0200 (Tue, 06 Jun 2006) | 1 line
Fix a bunch of parameter strings
........
r46689 | thomas.heller | 2006-06-06 13:34:33 +0200 (Tue, 06 Jun 2006) | 6 lines
Convert CFieldObject tp_members to tp_getset, since there is no
structmember typecode for Py_ssize_t fields. This should fix some of
the errors on the PPC64 debian machine (64-bit, big endian).
Assigning to readonly fields now raises AttributeError instead of
TypeError, so the testcase has to be changed as well.
........
r46690 | thomas.heller | 2006-06-06 13:54:32 +0200 (Tue, 06 Jun 2006) | 1 line
Damn - the sentinel was missing. And fix another silly mistake.
........
r46691 | martin.blais | 2006-06-06 14:46:55 +0200 (Tue, 06 Jun 2006) | 13 lines
Normalized a few cases of whitespace in function declarations.
Found them using::
find . -name '*.py' | while read i ; do grep 'def[^(]*( ' $i /dev/null ; done
find . -name '*.py' | while read i ; do grep ' ):' $i /dev/null ; done
(I was doing this all over my own code anyway, because I'd been using spaces in
all defs, so I thought I'd make a run on the Python code as well. If you need
to do such fixes in your own code, you can use xx-rename or parenregu.el within
emacs.)
........
r46693 | thomas.heller | 2006-06-06 17:34:18 +0200 (Tue, 06 Jun 2006) | 1 line
Specify argtypes for all test functions. Maybe that helps on strange ;-) architectures
........
r46694 | tim.peters | 2006-06-06 17:50:17 +0200 (Tue, 06 Jun 2006) | 5 lines
BSequence_set_range(): Rev 46688 ("Fix a bunch of
parameter strings") changed this function's signature
seemingly by mistake, which is causing buildbots to fail
test_bsddb3. Restored the pre-46688 signature.
........
r46695 | tim.peters | 2006-06-06 17:52:35 +0200 (Tue, 06 Jun 2006) | 4 lines
On python-dev Thomas Heller said these were committed
by mistake in rev 46693, so reverting this part of
rev 46693.
........
r46696 | andrew.kuchling | 2006-06-06 19:10:41 +0200 (Tue, 06 Jun 2006) | 1 line
Fix comment typo
........
r46697 | brett.cannon | 2006-06-06 20:08:16 +0200 (Tue, 06 Jun 2006) | 2 lines
Fix coding style guide bug.
........
r46698 | thomas.heller | 2006-06-06 20:50:46 +0200 (Tue, 06 Jun 2006) | 2 lines
Add a hack so that foreign functions returning float now do work on 64-bit
big endian platforms.
........
r46699 | thomas.heller | 2006-06-06 21:25:13 +0200 (Tue, 06 Jun 2006) | 3 lines
Use the same big-endian hack as in _ctypes/callproc.c for callback functions.
This fixes the callback function tests that return float.
........
r46700 | ronald.oussoren | 2006-06-06 21:50:24 +0200 (Tue, 06 Jun 2006) | 5 lines
* Ensure that "make altinstall" works when the tree was configured
with --enable-framework
* Also for --enable-framework: allow users to use --prefix to specify
the location of the compatibility symlinks (such as /usr/local/bin/python)
........
r46701 | ronald.oussoren | 2006-06-06 21:56:00 +0200 (Tue, 06 Jun 2006) | 3 lines
A quick hack to ensure the right key-bindings for IDLE on osx: install patched
configuration files during a framework install.
........
r46702 | tim.peters | 2006-06-07 03:04:59 +0200 (Wed, 07 Jun 2006) | 4 lines
dash_R_cleanup(): Clear filecmp._cache. This accounts for
different results across -R runs (at least on Windows) of
test_filecmp.
........
r46705 | tim.peters | 2006-06-07 08:57:51 +0200 (Wed, 07 Jun 2006) | 17 lines
SF patch 1501987: Remove randomness from test_exceptions,
from ?iga Seilnacht (sorry about the name, but Firefox
on my box can't display the first character of the name --
the SF "Unix name" is zseil).
This appears to cure the oddball intermittent leaks across
runs when running test_exceptions under -R. I'm not sure
why, but I'm too sleepy to care ;-)
The thrust of the SF patch was to remove randomness in the
pickle protocol used. I changed the patch to use
range(pickle.HIGHEST_PROTOCOL + 1), to try both pickle and
cPickle, and randomly mucked with other test lines to put
statements on their own lines.
Not a bugfix candidate (this is fiddling new-in-2.5 code).
........
r46706 | andrew.kuchling | 2006-06-07 15:55:33 +0200 (Wed, 07 Jun 2006) | 1 line
Add an SQLite introduction, taken from the 'What's New' text
........
r46708 | andrew.kuchling | 2006-06-07 19:02:52 +0200 (Wed, 07 Jun 2006) | 1 line
Mention other placeholders
........
r46709 | andrew.kuchling | 2006-06-07 19:03:46 +0200 (Wed, 07 Jun 2006) | 1 line
Add an item; also, escape %
........
r46710 | andrew.kuchling | 2006-06-07 19:04:01 +0200 (Wed, 07 Jun 2006) | 1 line
Mention other placeholders
........
r46716 | ronald.oussoren | 2006-06-07 20:57:44 +0200 (Wed, 07 Jun 2006) | 2 lines
Move Mac/OSX/Tools one level up
........
r46717 | ronald.oussoren | 2006-06-07 20:58:01 +0200 (Wed, 07 Jun 2006) | 2 lines
Move Mac/OSX/PythonLauncher one level up
........
r46718 | ronald.oussoren | 2006-06-07 20:58:42 +0200 (Wed, 07 Jun 2006) | 2 lines
mv Mac/OSX/BuildScript one level up
........
r46719 | ronald.oussoren | 2006-06-07 21:02:03 +0200 (Wed, 07 Jun 2006) | 2 lines
Move Mac/OSX/* one level up
........
r46720 | ronald.oussoren | 2006-06-07 21:06:01 +0200 (Wed, 07 Jun 2006) | 2 lines
And the last bit: move IDLE one level up and adjust makefiles
........
r46723 | ronald.oussoren | 2006-06-07 21:38:53 +0200 (Wed, 07 Jun 2006) | 4 lines
- Patch the correct version of python in the Info.plists at build time, instead
of relying on a maintainer to update them before releases.
- Remove the now empty Mac/OSX directory
........
r46727 | ronald.oussoren | 2006-06-07 22:18:44 +0200 (Wed, 07 Jun 2006) | 7 lines
* If BuildApplet.py is used as an applet it starts with a version of
sys.exutable that isn't usuable on an #!-line. That results in generated
applets that don't actually work. Work around this problem by resetting
sys.executable.
* argvemulator.py didn't work on intel macs. This patch fixes this
(bug #1491468)
........
r46728 | tim.peters | 2006-06-07 22:40:06 +0200 (Wed, 07 Jun 2006) | 2 lines
Whitespace normalization.
........
r46729 | tim.peters | 2006-06-07 22:40:54 +0200 (Wed, 07 Jun 2006) | 2 lines
Add missing svn:eol-style property to text files.
........
r46730 | thomas.heller | 2006-06-07 22:43:06 +0200 (Wed, 07 Jun 2006) | 7 lines
Fix for foreign functions returning small structures on 64-bit big
endian machines. Should fix the remaininf failure in the PPC64
Debian buildbot.
Thanks to Matthias Klose for providing access to a machine to debug
and test this.
........
r46731 | brett.cannon | 2006-06-07 23:48:17 +0200 (Wed, 07 Jun 2006) | 2 lines
Clarify documentation for bf_getcharbuffer.
........
r46735 | neal.norwitz | 2006-06-08 07:12:45 +0200 (Thu, 08 Jun 2006) | 1 line
Fix a refleak in recvfrom_into
........
r46736 | gregory.p.smith | 2006-06-08 07:17:08 +0200 (Thu, 08 Jun 2006) | 9 lines
- bsddb: the bsddb.dbtables Modify method now raises the proper error and
aborts the db transaction safely when a modifier callback fails.
Fixes SF python patch/bug #1408584.
Also cleans up the bsddb.dbtables docstrings since thats the only
documentation that exists for that unadvertised module. (people
really should really just use sqlite3)
........
r46737 | gregory.p.smith | 2006-06-08 07:38:11 +0200 (Thu, 08 Jun 2006) | 4 lines
* Turn the deadlock situation described in SF bug #775414 into a
DBDeadLockError exception.
* add the test case for my previous dbtables commit.
........
r46738 | gregory.p.smith | 2006-06-08 07:39:54 +0200 (Thu, 08 Jun 2006) | 2 lines
pasted set_lk_detect line in wrong spot in previous commit. fixed. passes tests this time.
........
r46739 | armin.rigo | 2006-06-08 12:56:24 +0200 (Thu, 08 Jun 2006) | 6 lines
(arre, arigo) SF bug #1350060
Give a consistent behavior for comparison and hashing of method objects
(both user- and built-in methods). Now compares the 'self' recursively.
The hash was already asking for the hash of 'self'.
........
r46740 | andrew.kuchling | 2006-06-08 13:56:44 +0200 (Thu, 08 Jun 2006) | 1 line
Typo fix
........
r46741 | georg.brandl | 2006-06-08 14:45:01 +0200 (Thu, 08 Jun 2006) | 2 lines
Bug #1502750: Fix getargs "i" format to use LONG_MIN and LONG_MAX for bounds checking.
........
r46743 | georg.brandl | 2006-06-08 14:54:13 +0200 (Thu, 08 Jun 2006) | 2 lines
Bug #1502728: Correctly link against librt library on HP-UX.
........
r46745 | georg.brandl | 2006-06-08 14:55:47 +0200 (Thu, 08 Jun 2006) | 3 lines
Add news for recent bugfix.
........
r46746 | georg.brandl | 2006-06-08 15:31:07 +0200 (Thu, 08 Jun 2006) | 4 lines
Argh. "integer" is a very confusing word ;)
Actually, checking for INT_MAX and INT_MIN is correct since
the format code explicitly handles a C "int".
........
r46748 | nick.coghlan | 2006-06-08 15:54:49 +0200 (Thu, 08 Jun 2006) | 1 line
Add functools.update_wrapper() and functools.wraps() as described in PEP 356
........
r46751 | georg.brandl | 2006-06-08 16:50:21 +0200 (Thu, 08 Jun 2006) | 4 lines
Bug #1502805: don't alias file.__exit__ to file.close since the
latter can return something that's true.
........
r46752 | georg.brandl | 2006-06-08 16:50:53 +0200 (Thu, 08 Jun 2006) | 3 lines
Convert test_file to unittest.
........
Modified: python/branches/p3yk/Demo/README
==============================================================================
--- python/branches/p3yk/Demo/README (original)
+++ python/branches/p3yk/Demo/README Thu Jun 8 17:35:45 2006
@@ -57,8 +57,5 @@
xml Some XML demos.
-xmlrpc XML-RPC server framework (but see the standard library
- module SimpleXMLRPCServer.py for a replacement).
-
zlib Some demos for the zlib module (see also the standard
library module gzip.py).
Modified: python/branches/p3yk/Demo/classes/Dates.py
==============================================================================
--- python/branches/p3yk/Demo/classes/Dates.py (original)
+++ python/branches/p3yk/Demo/classes/Dates.py Thu Jun 8 17:35:45 2006
@@ -59,32 +59,32 @@
_INT_TYPES = type(1), type(1L)
-def _is_leap( year ): # 1 if leap year, else 0
+def _is_leap(year): # 1 if leap year, else 0
if year % 4 != 0: return 0
if year % 400 == 0: return 1
return year % 100 != 0
-def _days_in_year( year ): # number of days in year
+def _days_in_year(year): # number of days in year
return 365 + _is_leap(year)
-def _days_before_year( year ): # number of days before year
+def _days_before_year(year): # number of days before year
return year*365L + (year+3)/4 - (year+99)/100 + (year+399)/400
-def _days_in_month( month, year ): # number of days in month of year
+def _days_in_month(month, year): # number of days in month of year
if month == 2 and _is_leap(year): return 29
return _DAYS_IN_MONTH[month-1]
-def _days_before_month( month, year ): # number of days in year before month
+def _days_before_month(month, year): # number of days in year before month
return _DAYS_BEFORE_MONTH[month-1] + (month > 2 and _is_leap(year))
-def _date2num( date ): # compute ordinal of date.month,day,year
- return _days_before_year( date.year ) + \
- _days_before_month( date.month, date.year ) + \
+def _date2num(date): # compute ordinal of date.month,day,year
+ return _days_before_year(date.year) + \
+ _days_before_month(date.month, date.year) + \
date.day
-_DI400Y = _days_before_year( 400 ) # number of days in 400 years
+_DI400Y = _days_before_year(400) # number of days in 400 years
-def _num2date( n ): # return date with ordinal n
+def _num2date(n): # return date with ordinal n
if type(n) not in _INT_TYPES:
raise TypeError, 'argument must be integer: %r' % type(n)
@@ -95,53 +95,53 @@
n400 = (n-1)/_DI400Y # # of 400-year blocks preceding
year, n = 400 * n400, n - _DI400Y * n400
more = n / 365
- dby = _days_before_year( more )
+ dby = _days_before_year(more)
if dby >= n:
more = more - 1
- dby = dby - _days_in_year( more )
+ dby = dby - _days_in_year(more)
year, n = year + more, int(n - dby)
try: year = int(year) # chop to int, if it fits
except (ValueError, OverflowError): pass
- month = min( n/29 + 1, 12 )
- dbm = _days_before_month( month, year )
+ month = min(n/29 + 1, 12)
+ dbm = _days_before_month(month, year)
if dbm >= n:
month = month - 1
- dbm = dbm - _days_in_month( month, year )
+ dbm = dbm - _days_in_month(month, year)
ans.month, ans.day, ans.year = month, n-dbm, year
return ans
-def _num2day( n ): # return weekday name of day with ordinal n
+def _num2day(n): # return weekday name of day with ordinal n
return _DAY_NAMES[ int(n % 7) ]
class Date:
- def __init__( self, month, day, year ):
+ def __init__(self, month, day, year):
if not 1 <= month <= 12:
raise ValueError, 'month must be in 1..12: %r' % (month,)
- dim = _days_in_month( month, year )
+ dim = _days_in_month(month, year)
if not 1 <= day <= dim:
raise ValueError, 'day must be in 1..%r: %r' % (dim, day)
self.month, self.day, self.year = month, day, year
- self.ord = _date2num( self )
+ self.ord = _date2num(self)
# don't allow setting existing attributes
- def __setattr__( self, name, value ):
+ def __setattr__(self, name, value):
if self.__dict__.has_key(name):
raise AttributeError, 'read-only attribute ' + name
self.__dict__[name] = value
- def __cmp__( self, other ):
- return cmp( self.ord, other.ord )
+ def __cmp__(self, other):
+ return cmp(self.ord, other.ord)
# define a hash function so dates can be used as dictionary keys
- def __hash__( self ):
- return hash( self.ord )
+ def __hash__(self):
+ return hash(self.ord)
# print as, e.g., Mon 16 Aug 1993
- def __repr__( self ):
+ def __repr__(self):
return '%.3s %2d %.3s %r' % (
self.weekday(),
self.day,
@@ -149,33 +149,33 @@
self.year)
# Python 1.1 coerces neither int+date nor date+int
- def __add__( self, n ):
+ def __add__(self, n):
if type(n) not in _INT_TYPES:
raise TypeError, 'can\'t add %r to date' % type(n)
- return _num2date( self.ord + n )
+ return _num2date(self.ord + n)
__radd__ = __add__ # handle int+date
# Python 1.1 coerces neither date-int nor date-date
- def __sub__( self, other ):
+ def __sub__(self, other):
if type(other) in _INT_TYPES: # date-int
- return _num2date( self.ord - other )
+ return _num2date(self.ord - other)
else:
return self.ord - other.ord # date-date
# complain about int-date
- def __rsub__( self, other ):
+ def __rsub__(self, other):
raise TypeError, 'Can\'t subtract date from integer'
- def weekday( self ):
- return _num2day( self.ord )
+ def weekday(self):
+ return _num2day(self.ord)
def today():
import time
local = time.localtime(time.time())
- return Date( local[1], local[2], local[0] )
+ return Date(local[1], local[2], local[0])
DateTestError = 'DateTestError'
-def test( firstyear, lastyear ):
+def test(firstyear, lastyear):
a = Date(9,30,1913)
b = Date(9,30,1914)
if repr(a) != 'Tue 30 Sep 1913':
@@ -207,7 +207,7 @@
# verify date<->number conversions for first and last days for
# all years in firstyear .. lastyear
- lord = _days_before_year( firstyear )
+ lord = _days_before_year(firstyear)
y = firstyear
while y <= lastyear:
ford = lord + 1
Modified: python/branches/p3yk/Demo/curses/README
==============================================================================
--- python/branches/p3yk/Demo/curses/README (original)
+++ python/branches/p3yk/Demo/curses/README Thu Jun 8 17:35:45 2006
@@ -11,14 +11,11 @@
course.
ncurses.py -- currently only a panels demo
- XXX this won't work until panel support is checked in
rain.py -- raindrops keep falling on my desktop
tclock.py -- ASCII clock, by Howard Jones
xmas.py -- I'm dreaming of an ASCII christmas
-Please send bugfixes and new contributions to me or, even better,
-submit them to the Python Bug Tracker on SourceForge
-(<URL:http://sourceforge.net/bugs/?group_id=5470>).
+Please submit bugfixes and new contributions to the Python bug tracker.
Other demos
Modified: python/branches/p3yk/Demo/curses/life.py
==============================================================================
--- python/branches/p3yk/Demo/curses/life.py (original)
+++ python/branches/p3yk/Demo/curses/life.py Thu Jun 8 17:35:45 2006
@@ -44,14 +44,15 @@
scr -- curses screen object to use for display
char -- character used to render live cells (default: '*')
"""
- self.state={} ; self.scr=scr
+ self.state = {}
+ self.scr = scr
Y, X = self.scr.getmaxyx()
self.X, self.Y = X-2, Y-2-1
self.char = char
self.scr.clear()
# Draw a border around the board
- border_line='+'+(self.X*'-')+'+'
+ border_line = '+'+(self.X*'-')+'+'
self.scr.addstr(0, 0, border_line)
self.scr.addstr(self.Y+1,0, border_line)
for y in range(0, self.Y):
@@ -73,16 +74,16 @@
del self.state[x,y]
self.scr.addch(y+1, x+1, ' ')
else:
- self.state[x,y]=1
+ self.state[x,y] = 1
self.scr.addch(y+1, x+1, self.char)
self.scr.refresh()
def erase(self):
"""Clear the entire board and update the board display"""
- self.state={}
- self.display(update_board=0)
+ self.state = {}
+ self.display(update_board=False)
- def display(self, update_board=1):
+ def display(self, update_board=True):
"""Display the whole board, optionally computing one generation"""
M,N = self.X, self.Y
if not update_board:
@@ -95,42 +96,46 @@
self.scr.refresh()
return
- d={} ; self.boring=1
+ d = {}
+ self.boring = 1
for i in range(0, M):
- L=range( max(0, i-1), min(M, i+2) )
+ L = range( max(0, i-1), min(M, i+2) )
for j in range(0, N):
- s=0
- live=self.state.has_key( (i,j) )
+ s = 0
+ live = self.state.has_key( (i,j) )
for k in range( max(0, j-1), min(N, j+2) ):
for l in L:
if self.state.has_key( (l,k) ):
- s=s+1
- s=s-live
- if s==3:
+ s += 1
+ s -= live
+ if s == 3:
# Birth
- d[i,j]=1
+ d[i,j] = 1
self.scr.addch(j+1, i+1, self.char)
- if not live: self.boring=0
- elif s==2 and live: d[i,j]=1 # Survival
+ if not live: self.boring = 0
+ elif s == 2 and live: d[i,j] = 1 # Survival
elif live:
# Death
self.scr.addch(j+1, i+1, ' ')
- self.boring=0
- self.state=d
+ self.boring = 0
+ self.state = d
self.scr.refresh()
def makeRandom(self):
"Fill the board with a random pattern"
- self.state={}
+ self.state = {}
for i in range(0, self.X):
for j in range(0, self.Y):
- if random.random() > 0.5: self.set(j,i)
+ if random.random() > 0.5:
+ self.set(j,i)
def erase_menu(stdscr, menu_y):
"Clear the space where the menu resides"
- stdscr.move(menu_y, 0) ; stdscr.clrtoeol()
- stdscr.move(menu_y+1, 0) ; stdscr.clrtoeol()
+ stdscr.move(menu_y, 0)
+ stdscr.clrtoeol()
+ stdscr.move(menu_y+1, 0)
+ stdscr.clrtoeol()
def display_menu(stdscr, menu_y):
"Display the menu of possible keystroke commands"
@@ -140,18 +145,17 @@
stdscr.addstr(menu_y+1, 4,
'E)rase the board, R)andom fill, S)tep once or C)ontinuously, Q)uit')
-def main(stdscr):
-
+def keyloop(stdscr):
# Clear the screen and display the menu of keys
stdscr.clear()
stdscr_y, stdscr_x = stdscr.getmaxyx()
- menu_y=(stdscr_y-3)-1
+ menu_y = (stdscr_y-3)-1
display_menu(stdscr, menu_y)
# Allocate a subwindow for the Life board and create the board object
- subwin=stdscr.subwin(stdscr_y-3, stdscr_x, 0, 0)
- board=LifeBoard(subwin, char=ord('*'))
- board.display(update_board=0)
+ subwin = stdscr.subwin(stdscr_y-3, stdscr_x, 0, 0)
+ board = LifeBoard(subwin, char=ord('*'))
+ board.display(update_board=False)
# xpos, ypos are the cursor's position
xpos, ypos = board.X/2, board.Y/2
@@ -159,9 +163,9 @@
# Main loop:
while (1):
stdscr.move(1+ypos, 1+xpos) # Move the cursor
- c=stdscr.getch() # Get a keystroke
+ c = stdscr.getch() # Get a keystroke
if 0<c<256:
- c=chr(c)
+ c = chr(c)
if c in ' \n':
board.toggle(ypos, xpos)
elif c in 'Cc':
@@ -173,50 +177,40 @@
# if no keystroke is available, instead of waiting.
stdscr.nodelay(1)
while (1):
- c=stdscr.getch()
- if c!=-1: break
- stdscr.addstr(0,0, '/'); stdscr.refresh()
+ c = stdscr.getch()
+ if c != -1:
+ break
+ stdscr.addstr(0,0, '/')
+ stdscr.refresh()
board.display()
- stdscr.addstr(0,0, '+'); stdscr.refresh()
+ stdscr.addstr(0,0, '+')
+ stdscr.refresh()
stdscr.nodelay(0) # Disable nodelay mode
display_menu(stdscr, menu_y)
- elif c in 'Ee': board.erase()
- elif c in 'Qq': break
+ elif c in 'Ee':
+ board.erase()
+ elif c in 'Qq':
+ break
elif c in 'Rr':
board.makeRandom()
- board.display(update_board=0)
+ board.display(update_board=False)
elif c in 'Ss':
board.display()
else: pass # Ignore incorrect keys
- elif c==curses.KEY_UP and ypos>0: ypos=ypos-1
- elif c==curses.KEY_DOWN and ypos<board.Y-1: ypos=ypos+1
- elif c==curses.KEY_LEFT and xpos>0: xpos=xpos-1
- elif c==curses.KEY_RIGHT and xpos<board.X-1: xpos=xpos+1
- else: pass # Ignore incorrect keys
-
-if __name__=='__main__':
- try:
- # Initialize curses
- stdscr=curses.initscr()
- # Turn off echoing of keys, and enter cbreak mode,
- # where no buffering is performed on keyboard input
- curses.noecho() ; curses.cbreak()
-
- # In keypad mode, escape sequences for special keys
- # (like the cursor keys) will be interpreted and
- # a special value like curses.KEY_LEFT will be returned
- stdscr.keypad(1)
- main(stdscr) # Enter the main loop
- # Set everything back to normal
- stdscr.keypad(0)
- curses.echo() ; curses.nocbreak()
- curses.endwin() # Terminate curses
- except:
- # In the event of an error, restore the terminal
- # to a sane state.
- stdscr.keypad(0)
- curses.echo() ; curses.nocbreak()
- curses.endwin()
- traceback.print_exc() # Print the exception
+ elif c == curses.KEY_UP and ypos>0: ypos -= 1
+ elif c == curses.KEY_DOWN and ypos<board.Y-1: ypos += 1
+ elif c == curses.KEY_LEFT and xpos>0: xpos -= 1
+ elif c == curses.KEY_RIGHT and xpos<board.X-1: xpos += 1
+ else:
+ # Ignore incorrect keys
+ pass
+
+
+def main(stdscr):
+ keyloop(stdscr) # Enter the main loop
+
+
+if __name__ == '__main__':
+ curses.wrapper(main)
Modified: python/branches/p3yk/Demo/curses/rain.py
==============================================================================
--- python/branches/p3yk/Demo/curses/rain.py (original)
+++ python/branches/p3yk/Demo/curses/rain.py Thu Jun 8 17:35:45 2006
@@ -48,7 +48,7 @@
ypos[j] = randrange(0, r) + 2
j = 0
- while 1:
+ while True:
x = randrange(0, c) + 2
y = randrange(0, r) + 2
@@ -83,7 +83,7 @@
ch = stdscr.getch()
if ch == ord('q') or ch == ord('Q'):
- return 0
+ return
elif ch == ord('s'):
stdscr.nodelay(0)
elif ch == ord(' '):
Modified: python/branches/p3yk/Demo/curses/repeat.py
==============================================================================
--- python/branches/p3yk/Demo/curses/repeat.py (original)
+++ python/branches/p3yk/Demo/curses/repeat.py Thu Jun 8 17:35:45 2006
@@ -2,7 +2,7 @@
"""repeat <shell-command>
-This simple program repeatedly (with 1-second intervals) executes the
+This simple program repeatedly (at 1-second intervals) executes the
shell command given on the command line and displays the output (or as
much of it as fits on the screen). It uses curses to paint each new
output on top of the old output, so that if nothing changes, the
@@ -38,7 +38,7 @@
sys.exit(sts)
w = curses.initscr()
try:
- while 1:
+ while True:
w.erase()
try:
w.addstr(text)
Modified: python/branches/p3yk/Demo/curses/tclock.py
==============================================================================
--- python/branches/p3yk/Demo/curses/tclock.py (original)
+++ python/branches/p3yk/Demo/curses/tclock.py Thu Jun 8 17:35:45 2006
@@ -14,7 +14,8 @@
return 1
def A2XY(angle, radius):
- return int(round(ASPECT * radius * sin(angle))), int(round(radius * cos(angle)))
+ return (int(round(ASPECT * radius * sin(angle))),
+ int(round(radius * cos(angle))))
def plot(x, y, col):
stdscr.addch(y, x, col)
@@ -37,9 +38,9 @@
y = from_y
if ax > ay:
- d = ay - ax / 2
+ d = ay - ax // 2
- while 1:
+ while True:
plot(x, y, ch)
if x == x2:
return
@@ -50,9 +51,9 @@
x += sx
d += ay
else:
- d = ax - ay / 2
+ d = ax - ay // 2
- while 1:
+ while True:
plot(x, y, ch)
if y == y2:
return
@@ -78,12 +79,12 @@
curses.init_pair(2, curses.COLOR_MAGENTA, my_bg)
curses.init_pair(3, curses.COLOR_GREEN, my_bg)
- cx = (curses.COLS - 1) / 2
- cy = curses.LINES / 2
- ch = min( cy-1, int(cx / ASPECT) - 1)
- mradius = (3 * ch) / 4
- hradius = ch / 2
- sradius = 5 * ch / 6
+ cx = (curses.COLS - 1) // 2
+ cy = curses.LINES // 2
+ ch = min( cy-1, int(cx // ASPECT) - 1)
+ mradius = (3 * ch) // 4
+ hradius = ch // 2
+ sradius = 5 * ch // 6
for i in range(0, 12):
sangle = (i + 1) * 2.0 * pi / 12.0
@@ -96,7 +97,7 @@
sradius = max(sradius-4, 8)
- while 1:
+ while True:
curses.napms(1000)
tim = time.time()
Modified: python/branches/p3yk/Demo/curses/xmas.py
==============================================================================
--- python/branches/p3yk/Demo/curses/xmas.py (original)
+++ python/branches/p3yk/Demo/curses/xmas.py Thu Jun 8 17:35:45 2006
@@ -4,7 +4,7 @@
# $Id$
#
# I'm dreaming of an ascii character-based monochrome Christmas,
-# Just like the one's I used to know!
+# Just like the ones I used to know!
# Via a full duplex communications channel,
# At 9600 bits per second,
# Even though it's kinda slow.
@@ -272,7 +272,7 @@
def blinkit():
treescrn8.touchwin()
- for cycle in range(0, 5):
+ for cycle in range(5):
if cycle == 0:
treescrn3.overlay(treescrn8)
treescrn8.refresh()
@@ -380,7 +380,7 @@
middeer0.refresh()
w_del_msg.refresh()
- for looper in range(0, 2):
+ for looper in range(2):
deer_step(middeer3, y_pos, x_pos)
deer_step(middeer2, y_pos, x_pos)
deer_step(middeer1, y_pos, x_pos)
Modified: python/branches/p3yk/Demo/sockets/README
==============================================================================
--- python/branches/p3yk/Demo/sockets/README (original)
+++ python/branches/p3yk/Demo/sockets/README Thu Jun 8 17:35:45 2006
@@ -19,4 +19,3 @@
/usr/people/4Dgifts/examples/network/mcast.c
(Note that IN.py is in ../../lib/sgi.)
-See also ../../lib/nntp.py for another example of socket code.
Modified: python/branches/p3yk/Demo/sockets/unixclient.py
==============================================================================
--- python/branches/p3yk/Demo/sockets/unixclient.py (original)
+++ python/branches/p3yk/Demo/sockets/unixclient.py Thu Jun 8 17:35:45 2006
@@ -1,7 +1,9 @@
# Echo client demo using Unix sockets
# Piet van Oostrum
+
from socket import *
-FILE = 'blabla'
+
+FILE = 'unix-socket'
s = socket(AF_UNIX, SOCK_STREAM)
s.connect(FILE)
s.send('Hello, world')
Modified: python/branches/p3yk/Demo/sockets/unixserver.py
==============================================================================
--- python/branches/p3yk/Demo/sockets/unixserver.py (original)
+++ python/branches/p3yk/Demo/sockets/unixserver.py Thu Jun 8 17:35:45 2006
@@ -1,17 +1,24 @@
# Echo server demo using Unix sockets (handles one connection only)
# Piet van Oostrum
+
import os
from socket import *
-FILE = 'blabla'
+
+FILE = 'unix-socket'
s = socket(AF_UNIX, SOCK_STREAM)
s.bind(FILE)
+
print 'Sock name is: ['+s.getsockname()+']'
+
+# Wait for a connection
s.listen(1)
conn, addr = s.accept()
-print 'Connected by', addr
-while 1:
+
+while True:
data = conn.recv(1024)
- if not data: break
+ if not data:
+ break
conn.send(data)
+
conn.close()
os.unlink(FILE)
Modified: python/branches/p3yk/Demo/threads/fcmp.py
==============================================================================
--- python/branches/p3yk/Demo/threads/fcmp.py (original)
+++ python/branches/p3yk/Demo/threads/fcmp.py Thu Jun 8 17:35:45 2006
@@ -4,14 +4,14 @@
# fringe visits a nested list in inorder, and detaches for each non-list
# element; raises EarlyExit after the list is exhausted
-def fringe( co, list ):
+def fringe(co, list):
for x in list:
if type(x) is type([]):
fringe(co, x)
else:
co.back(x)
-def printinorder( list ):
+def printinorder(list):
co = Coroutine()
f = co.create(fringe, co, list)
try:
@@ -27,7 +27,7 @@
printinorder(x) # 0 1 2 3 4 5 6
# fcmp lexicographically compares the fringes of two nested lists
-def fcmp( l1, l2 ):
+def fcmp(l1, l2):
co1 = Coroutine(); f1 = co1.create(fringe, co1, l1)
co2 = Coroutine(); f2 = co2.create(fringe, co2, l2)
while 1:
Modified: python/branches/p3yk/Demo/zlib/minigzip.py
==============================================================================
--- python/branches/p3yk/Demo/zlib/minigzip.py (original)
+++ python/branches/p3yk/Demo/zlib/minigzip.py Thu Jun 8 17:35:45 2006
@@ -1,106 +1,133 @@
#!/usr/bin/env python
# Demo program for zlib; it compresses or decompresses files, but *doesn't*
# delete the original. This doesn't support all of gzip's options.
+#
+# The 'gzip' module in the standard library provides a more complete
+# implementation of gzip-format files.
+
+import zlib, sys, os
FTEXT, FHCRC, FEXTRA, FNAME, FCOMMENT = 1, 2, 4, 8, 16
def write32(output, value):
- output.write(chr(value & 255)) ; value=value / 256
- output.write(chr(value & 255)) ; value=value / 256
- output.write(chr(value & 255)) ; value=value / 256
+ output.write(chr(value & 255)) ; value=value // 256
+ output.write(chr(value & 255)) ; value=value // 256
+ output.write(chr(value & 255)) ; value=value // 256
output.write(chr(value & 255))
def read32(input):
- v=ord(input.read(1))
- v=v+ (ord(input.read(1))<<8 )
- v=v+ (ord(input.read(1))<<16)
- v=v+ (ord(input.read(1))<<24)
+ v = ord(input.read(1))
+ v += (ord(input.read(1)) << 8 )
+ v += (ord(input.read(1)) << 16)
+ v += (ord(input.read(1)) << 24)
return v
-import zlib, sys
-if len(sys.argv)!=2:
- print 'Usage: minigzip.py <filename>'
- print ' The file will be compressed or decompressed.'
- sys.exit(0)
-
-filename=sys.argv[1]
-compressing=1 ; outputname=filename+'.gz'
-if filename[-3:]=='.gz':
- compressing=0 ; outputname=filename[:-3]
-input=open(filename) ; output=open(outputname, 'w')
-
-if compressing:
+def compress (filename, input, output):
output.write('\037\213\010') # Write the header, ...
output.write(chr(FNAME)) # ... flag byte ...
- import os # ... modification time ...
- statval=os.stat(filename)
- mtime=statval[8]
+ statval = os.stat(filename) # ... modification time ...
+ mtime = statval[8]
write32(output, mtime)
output.write('\002') # ... slowest compression alg. ...
output.write('\377') # ... OS (=unknown) ...
output.write(filename+'\000') # ... original filename ...
- crcval=zlib.crc32("")
- compobj=zlib.compressobj(9, zlib.DEFLATED, -zlib.MAX_WBITS,
+ crcval = zlib.crc32("")
+ compobj = zlib.compressobj(9, zlib.DEFLATED, -zlib.MAX_WBITS,
zlib.DEF_MEM_LEVEL, 0)
- while (1):
- data=input.read(1024)
- if data=="": break
- crcval=zlib.crc32(data, crcval)
+ while True:
+ data = input.read(1024)
+ if data == "":
+ break
+ crcval = zlib.crc32(data, crcval)
output.write(compobj.compress(data))
output.write(compobj.flush())
write32(output, crcval) # ... the CRC ...
write32(output, statval[6]) # and the file size.
-else:
- magic=input.read(2)
- if magic!='\037\213':
- print 'Not a gzipped file' ; sys.exit(0)
- if ord(input.read(1))!=8:
- print 'Unknown compression method' ; sys.exit(0)
- flag=ord(input.read(1))
+def decompress (input, output):
+ magic = input.read(2)
+ if magic != '\037\213':
+ print 'Not a gzipped file'
+ sys.exit(0)
+ if ord(input.read(1)) != 8:
+ print 'Unknown compression method'
+ sys.exit(0)
+ flag = ord(input.read(1))
input.read(4+1+1) # Discard modification time,
# extra flags, and OS byte.
if flag & FEXTRA:
# Read & discard the extra field, if present
- xlen=ord(input.read(1))
- xlen=xlen+256*ord(input.read(1))
+ xlen = ord(input.read(1))
+ xlen += 256*ord(input.read(1))
input.read(xlen)
if flag & FNAME:
# Read and discard a null-terminated string containing the filename
- while (1):
- s=input.read(1)
- if s=='\000': break
+ while True:
+ s = input.read(1)
+ if s == '\0': break
if flag & FCOMMENT:
# Read and discard a null-terminated string containing a comment
- while (1):
+ while True:
s=input.read(1)
- if s=='\000': break
+ if s=='\0': break
if flag & FHCRC:
input.read(2) # Read & discard the 16-bit header CRC
- decompobj=zlib.decompressobj(-zlib.MAX_WBITS)
- crcval=zlib.crc32("")
- length=0
- while (1):
+
+ decompobj = zlib.decompressobj(-zlib.MAX_WBITS)
+ crcval = zlib.crc32("")
+ length = 0
+ while True:
data=input.read(1024)
- if data=="": break
- decompdata=decompobj.decompress(data)
- print len(decompdata)
- output.write(decompdata) ; length=length+len(decompdata)
- crcval=zlib.crc32(decompdata, crcval)
- decompdata=decompobj.flush()
- output.write(decompdata) ; length=length+len(decompdata)
- crcval=zlib.crc32(decompdata, crcval)
+ if data == "":
+ break
+ decompdata = decompobj.decompress(data)
+ output.write(decompdata)
+ length += len(decompdata)
+ crcval = zlib.crc32(decompdata, crcval)
+
+ decompdata = decompobj.flush()
+ output.write(decompdata)
+ length += len(decompdata)
+ crcval = zlib.crc32(decompdata, crcval)
# We've read to the end of the file, so we have to rewind in order
# to reread the 8 bytes containing the CRC and the file size. The
# decompressor is smart and knows when to stop, so feeding it
# extra data is harmless.
input.seek(-8, 2)
- crc32=read32(input)
- isize=read32(input)
- if crc32!=crcval: print 'CRC check failed.'
- if isize!=length: print 'Incorrect length of data produced'
+ crc32 = read32(input)
+ isize = read32(input)
+ if crc32 != crcval:
+ print 'CRC check failed.'
+ if isize != length:
+ print 'Incorrect length of data produced'
+
+def main():
+ if len(sys.argv)!=2:
+ print 'Usage: minigzip.py <filename>'
+ print ' The file will be compressed or decompressed.'
+ sys.exit(0)
+
+ filename = sys.argv[1]
+ if filename.endswith('.gz'):
+ compressing = False
+ outputname = filename[:-3]
+ else:
+ compressing = True
+ outputname = filename + '.gz'
+
+ input = open(filename, 'rb')
+ output = open(outputname, 'wb')
+
+ if compressing:
+ compress(filename, input, output)
+ else:
+ decompress(input, output)
+
+ input.close()
+ output.close()
-input.close() ; output.close()
+if __name__ == '__main__':
+ main()
Modified: python/branches/p3yk/Demo/zlib/zlibdemo.py
==============================================================================
--- python/branches/p3yk/Demo/zlib/zlibdemo.py (original)
+++ python/branches/p3yk/Demo/zlib/zlibdemo.py Thu Jun 8 17:35:45 2006
@@ -1,35 +1,48 @@
#!/usr/bin/env python
+# Takes an optional filename, defaulting to this file itself.
+# Reads the file and compresses the content using level 1 and level 9
+# compression, printing a summary of the results.
+
import zlib, sys
-if len(sys.argv)>1: filename=sys.argv[1]
-else: filename='zlibdemo.py'
-print 'Reading', filename
-f=open(filename, 'r') # Get the data to compress
-s=f.read()
-f.close()
-
-# First, we'll compress the string in one step
-comptext=zlib.compress(s, 1)
-decomp=zlib.decompress(comptext)
-
-print '1-step compression: (level 1)'
-print ' Original:', len(s), 'Compressed:', len(comptext),
-print 'Uncompressed:', len(decomp)
-
-# Now, let's compress the string in stages; set chunk to work in smaller steps
-
-chunk=256
-compressor=zlib.compressobj(9)
-decompressor=zlib.decompressobj()
-comptext=decomp=''
-for i in range(0, len(s), chunk):
- comptext=comptext+compressor.compress(s[i:i+chunk])
-comptext=comptext+compressor.flush() # Don't forget to call flush()!!
-
-for i in range(0, len(comptext), chunk):
- decomp=decomp+decompressor.decompress(comptext[i:i+chunk])
-decomp=decomp+decompressor.flush()
-
-print 'Progressive compression (level 9):'
-print ' Original:', len(s), 'Compressed:', len(comptext),
-print 'Uncompressed:', len(decomp)
+
+def main():
+ if len(sys.argv) > 1:
+ filename = sys.argv[1]
+ else:
+ filename = sys.argv[0]
+ print 'Reading', filename
+
+ f = open(filename, 'rb') # Get the data to compress
+ s = f.read()
+ f.close()
+
+ # First, we'll compress the string in one step
+ comptext = zlib.compress(s, 1)
+ decomp = zlib.decompress(comptext)
+
+ print '1-step compression: (level 1)'
+ print ' Original:', len(s), 'Compressed:', len(comptext),
+ print 'Uncompressed:', len(decomp)
+
+ # Now, let's compress the string in stages; set chunk to work in smaller steps
+
+ chunk = 256
+ compressor = zlib.compressobj(9)
+ decompressor = zlib.decompressobj()
+ comptext = decomp = ''
+ for i in range(0, len(s), chunk):
+ comptext = comptext+compressor.compress(s[i:i+chunk])
+ # Don't forget to call flush()!!
+ comptext = comptext + compressor.flush()
+
+ for i in range(0, len(comptext), chunk):
+ decomp = decomp + decompressor.decompress(comptext[i:i+chunk])
+ decomp=decomp+decompressor.flush()
+
+ print 'Progressive compression (level 9):'
+ print ' Original:', len(s), 'Compressed:', len(comptext),
+ print 'Uncompressed:', len(decomp)
+
+if __name__ == '__main__':
+ main()
Modified: python/branches/p3yk/Doc/api/newtypes.tex
==============================================================================
--- python/branches/p3yk/Doc/api/newtypes.tex (original)
+++ python/branches/p3yk/Doc/api/newtypes.tex Thu Jun 8 17:35:45 2006
@@ -1549,7 +1549,9 @@
Before using this slot, the caller should test whether it is present
by using the
\cfunction{PyType_HasFeature()}\ttindex{PyType_HasFeature()}
- function. If present, it may be \NULL, indicating that the object's
+ function. If the flag is present, \member{bf_getcharbuffer} may be
+ \NULL,
+ indicating that the object's
contents cannot be used as \emph{8-bit characters}.
The slot function may also raise an error if the object's contents
cannot be interpreted as 8-bit characters. For example, if the
@@ -1574,12 +1576,13 @@
\begin{ctypedesc}[getreadbufferproc]{Py_ssize_t (*readbufferproc)
(PyObject *self, Py_ssize_t segment, void **ptrptr)}
- Return a pointer to a readable segment of the buffer. This function
+ Return a pointer to a readable segment of the buffer in
+ \code{*\var{ptrptr}}. This function
is allowed to raise an exception, in which case it must return
- \code{-1}. The \var{segment} which is passed must be zero or
+ \code{-1}. The \var{segment} which is specified must be zero or
positive, and strictly less than the number of segments returned by
the \member{bf_getsegcount} slot function. On success, it returns
- the length of the buffer memory, and sets \code{*\var{ptrptr}} to a
+ the length of the segment, and sets \code{*\var{ptrptr}} to a
pointer to that memory.
\end{ctypedesc}
@@ -1608,8 +1611,9 @@
\begin{ctypedesc}[getcharbufferproc]{Py_ssize_t (*charbufferproc)
(PyObject *self, Py_ssize_t segment, const char **ptrptr)}
- Return the size of the memory buffer in \var{ptrptr} for segment
- \var{segment}. \code{*\var{ptrptr}} is set to the memory buffer.
+ Return the size of the segment \var{segment} that \var{ptrptr}
+ is set to. \code{*\var{ptrptr}} is set to the memory buffer.
+ Returns \code{-1} on error.
\end{ctypedesc}
Modified: python/branches/p3yk/Doc/dist/dist.tex
==============================================================================
--- python/branches/p3yk/Doc/dist/dist.tex (original)
+++ python/branches/p3yk/Doc/dist/dist.tex Thu Jun 8 17:35:45 2006
@@ -849,7 +849,7 @@
{long string}{}
\lineiv{download_url}{location where the package may be downloaded}
{URL}{(4)}
- \lineiv{classifiers}{a list of Trove classifiers}
+ \lineiv{classifiers}{a list of classifiers}
{list of strings}{(4)}
\end{tableiv}
@@ -2251,7 +2251,7 @@
\lineiii{scripts}{A list of standalone script files to be built and installed}{a list of strings}
\lineiii{ext_modules}{A list of Python extensions to be built}{A list of
instances of \class{distutils.core.Extension}}
-\lineiii{classifiers}{A list of Trove categories for the package}{XXX link to better definition}
+\lineiii{classifiers}{A list of categories for the package}{The list of available categorizations is at \url{http://cheeseshop.python.org/pypi?:action=list_classifiers}.}
\lineiii{distclass}{the \class{Distribution} class to use}{A subclass of \class{distutils.core.Distribution}}
% What on earth is the use case for script_name?
\lineiii{script_name}{The name of the setup.py script - defaults to \code{sys.argv[0]}}{a string}
Modified: python/branches/p3yk/Doc/lib/libdoctest.tex
==============================================================================
--- python/branches/p3yk/Doc/lib/libdoctest.tex (original)
+++ python/branches/p3yk/Doc/lib/libdoctest.tex Thu Jun 8 17:35:45 2006
@@ -952,7 +952,7 @@
\begin{funcdesc}{testmod}{\optional{m}\optional{, name}\optional{,
globs}\optional{, verbose}\optional{,
- isprivate}\optional{, report}\optional{,
+ report}\optional{,
optionflags}\optional{, extraglobs}\optional{,
raise_on_error}\optional{, exclude_empty}}
@@ -990,19 +990,14 @@
for function \function{testfile()} above, except that \var{globs}
defaults to \code{\var{m}.__dict__}.
- Optional argument \var{isprivate} specifies a function used to
- determine whether a name is private. The default function treats
- all names as public. \var{isprivate} can be set to
- \code{doctest.is_private} to skip over names that are
- private according to Python's underscore naming convention.
- \deprecated{2.4}{\var{isprivate} was a stupid idea -- don't use it.
- If you need to skip tests based on name, filter the list returned by
- \code{DocTestFinder.find()} instead.}
-
\versionchanged[The parameter \var{optionflags} was added]{2.3}
\versionchanged[The parameters \var{extraglobs}, \var{raise_on_error}
and \var{exclude_empty} were added]{2.4}
+
+ \versionchanged[The optional argument \var{isprivate}, deprecated
+ in 2.4, was removed]{2.5}
+
\end{funcdesc}
There's also a function to run the doctests associated with a single object.
Modified: python/branches/p3yk/Doc/lib/libfunctools.tex
==============================================================================
--- python/branches/p3yk/Doc/lib/libfunctools.tex (original)
+++ python/branches/p3yk/Doc/lib/libfunctools.tex Thu Jun 8 17:35:45 2006
@@ -5,6 +5,7 @@
\moduleauthor{Peter Harris}{scav at blueyonder.co.uk}
\moduleauthor{Raymond Hettinger}{python at rcn.com}
+\moduleauthor{Nick Coghlan}{ncoghlan at gmail.com}
\sectionauthor{Peter Harris}{scav at blueyonder.co.uk}
\modulesynopsis{Higher-order functions and operations on callable objects.}
@@ -50,6 +51,51 @@
\end{verbatim}
\end{funcdesc}
+\begin{funcdesc}{update_wrapper}
+{wrapper, wrapped\optional{, assigned}\optional{, updated}}
+Update a wrapper function to look like the wrapped function. The optional
+arguments are tuples to specify which attributes of the original
+function are assigned directly to the matching attributes on the wrapper
+function and which attributes of the wrapper function are updated with
+the corresponding attributes from the original function. The default
+values for these arguments are the module level constants
+\var{WRAPPER_ASSIGNMENTS} (which assigns to the wrapper function's name,
+module and documentation string) and \var{WRAPPER_UPDATES} (which
+updates the wrapper function's instance dictionary).
+
+The main intended use for this function is in decorator functions
+which wrap the decorated function and return the wrapper. If the
+wrapper function is not updated, the metadata of the returned function
+will reflect the wrapper definition rather than the original function
+definition, which is typically less than helpful.
+\end{funcdesc}
+
+\begin{funcdesc}{wraps}
+{wrapped\optional{, assigned}\optional{, updated}}
+This is a convenience function for invoking
+\code{partial(update_wrapper, wrapped=wrapped, assigned=assigned, updated=updated)}
+as a function decorator when defining a wrapper function. For example:
+ \begin{verbatim}
+ >>> def my_decorator(f):
+ ... @wraps(f)
+ ... def wrapper(*args, **kwds):
+ ... print 'Calling decorated function'
+ ... return f(*args, **kwds)
+ ... return wrapper
+ ...
+ >>> @my_decorator
+ ... def example():
+ ... print 'Called example function'
+ ...
+ >>> example()
+ Calling decorated function
+ Called example function
+ >>> example.__name__
+ 'example'
+ \end{verbatim}
+Without the use of this decorator factory, the name of the example
+function would have been \code{'wrapper'}.
+\end{funcdesc}
\subsection{\class{partial} Objects \label{partial-objects}}
Modified: python/branches/p3yk/Doc/lib/libsgmllib.tex
==============================================================================
--- python/branches/p3yk/Doc/lib/libsgmllib.tex (original)
+++ python/branches/p3yk/Doc/lib/libsgmllib.tex Thu Jun 8 17:35:45 2006
@@ -218,8 +218,9 @@
\end{methoddescni}
\begin{methoddescni}{do_\var{tag}}{attributes}
-This method is called to process an opening tag \var{tag} that does
-not come with a matching closing tag. The \var{attributes} argument
+This method is called to process an opening tag \var{tag}
+for which no \method{start_\var{tag}} method is defined.
+The \var{attributes} argument
has the same meaning as described for \method{handle_starttag()} above.
\end{methoddescni}
Modified: python/branches/p3yk/Doc/lib/libsocket.tex
==============================================================================
--- python/branches/p3yk/Doc/lib/libsocket.tex (original)
+++ python/branches/p3yk/Doc/lib/libsocket.tex Thu Jun 8 17:35:45 2006
@@ -548,7 +548,7 @@
The file object references a \cfunction{dup()}ped version of the
socket file descriptor, so the file object and socket object may be
closed or garbage-collected independently.
-The socket should be in blocking mode.
+The socket must be in blocking mode.
\index{I/O control!buffering}The optional \var{mode}
and \var{bufsize} arguments are interpreted the same way as by the
built-in \function{file()} function; see ``Built-in Functions''
@@ -647,7 +647,7 @@
blocking and timeout modes are shared between file descriptors and
socket objects that refer to the same network endpoint. A consequence
of this is that file objects returned by the \method{makefile()}
-method should only be used when the socket is in blocking mode; in
+method must only be used when the socket is in blocking mode; in
timeout or non-blocking mode file operations that cannot be completed
immediately will fail.
Modified: python/branches/p3yk/Doc/lib/libsqlite3.tex
==============================================================================
--- python/branches/p3yk/Doc/lib/libsqlite3.tex (original)
+++ python/branches/p3yk/Doc/lib/libsqlite3.tex Thu Jun 8 17:35:45 2006
@@ -6,6 +6,105 @@
\sectionauthor{Gerhard Häring}{gh at ghaering.de}
\versionadded{2.5}
+SQLite is a C library that provides a SQL-language database that
+stores data in disk files without requiring a separate server process.
+pysqlite was written by Gerhard H\"aring and provides a SQL interface
+compliant with the DB-API 2.0 specification described by
+\pep{249}. This means that it should be possible to write the first
+version of your applications using SQLite for data storage. If
+switching to a larger database such as PostgreSQL or Oracle is
+later necessary, the switch should be relatively easy.
+
+To use the module, you must first create a \class{Connection} object
+that represents the database. Here the data will be stored in the
+\file{/tmp/example} file:
+
+\begin{verbatim}
+conn = sqlite3.connect('/tmp/example')
+\end{verbatim}
+
+You can also supply the special name \samp{:memory:} to create
+a database in RAM.
+
+Once you have a \class{Connection}, you can create a \class{Cursor}
+object and call its \method{execute()} method to perform SQL commands:
+
+\begin{verbatim}
+c = conn.cursor()
+
+# Create table
+c.execute('''create table stocks
+(date timestamp, trans varchar, symbol varchar,
+ qty decimal, price decimal)''')
+
+# Insert a row of data
+c.execute("""insert into stocks
+ values ('2006-01-05','BUY','RHAT',100,35.14)""")
+\end{verbatim}
+
+Usually your SQL operations will need to use values from Python
+variables. You shouldn't assemble your query using Python's string
+operations because doing so is insecure; it makes your program
+vulnerable to an SQL injection attack.
+
+Instead, use the DB-API's parameter substitution. Put \samp{?} as a
+placeholder wherever you want to use a value, and then provide a tuple
+of values as the second argument to the cursor's \method{execute()}
+method. (Other database modules may use a different placeholder,
+such as \samp{\%s} or \samp{:1}.) For example:
+
+\begin{verbatim}
+# Never do this -- insecure!
+symbol = 'IBM'
+c.execute("... where symbol = '%s'" % symbol)
+
+# Do this instead
+t = (symbol,)
+c.execute('select * from stocks where symbol=?', t)
+
+# Larger example
+for t in (('2006-03-28', 'BUY', 'IBM', 1000, 45.00),
+ ('2006-04-05', 'BUY', 'MSOFT', 1000, 72.00),
+ ('2006-04-06', 'SELL', 'IBM', 500, 53.00),
+ ):
+ c.execute('insert into stocks values (?,?,?,?,?)', t)
+\end{verbatim}
+
+To retrieve data after executing a SELECT statement, you can either
+treat the cursor as an iterator, call the cursor's \method{fetchone()}
+method to retrieve a single matching row,
+or call \method{fetchall()} to get a list of the matching rows.
+
+This example uses the iterator form:
+
+\begin{verbatim}
+>>> c = conn.cursor()
+>>> c.execute('select * from stocks order by price')
+>>> for row in c:
+... print row
+...
+(u'2006-01-05', u'BUY', u'RHAT', 100, 35.140000000000001)
+(u'2006-03-28', u'BUY', u'IBM', 1000, 45.0)
+(u'2006-04-06', u'SELL', u'IBM', 500, 53.0)
+(u'2006-04-05', u'BUY', u'MSOFT', 1000, 72.0)
+>>>
+\end{verbatim}
+
+\begin{seealso}
+
+\seeurl{http://www.pysqlite.org}
+{The pysqlite web page.}
+
+\seeurl{http://www.sqlite.org}
+{The SQLite web page; the documentation describes the syntax and the
+available data types for the supported SQL dialect.}
+
+\seepep{249}{Database API Specification 2.0}{PEP written by
+Marc-Andr\'e Lemburg.}
+
+\end{seealso}
+
+
\subsection{Module functions and constants\label{sqlite3-Module-Contents}}
\begin{datadesc}{PARSE_DECLTYPES}
@@ -467,7 +566,7 @@
If you want \strong{autocommit mode}, then set \member{isolation_level} to None.
-Otherwise leave it at it's default, which will result in a plain "BEGIN"
+Otherwise leave it at its default, which will result in a plain "BEGIN"
statement, or set it to one of SQLite's supported isolation levels: DEFERRED,
IMMEDIATE or EXCLUSIVE.
Modified: python/branches/p3yk/Doc/lib/liburllib2.tex
==============================================================================
--- python/branches/p3yk/Doc/lib/liburllib2.tex (original)
+++ python/branches/p3yk/Doc/lib/liburllib2.tex Thu Jun 8 17:35:45 2006
@@ -18,11 +18,13 @@
Open the URL \var{url}, which can be either a string or a \class{Request}
object.
-\var{data} should be a string, which specifies additional data to
-send to the server. In HTTP requests, which are the only ones that
-support \var{data}, it should be a buffer in the format of
-\mimetype{application/x-www-form-urlencoded}, for example one returned
-from \function{urllib.urlencode()}.
+\var{data} may be a string specifying additional data to send to the
+server. Currently HTTP requests are the only ones that use \var{data};
+the HTTP request will be a POST instead of a GET when the \var{data}
+parameter is provided. \var{data} should be a buffer in the standard
+\mimetype{application/x-www-form-urlencoded} format. The
+\function{urllib.urlencode()} function takes a mapping or sequence of
+2-tuples and returns a string in this format.
This function returns a file-like object with two additional methods:
Modified: python/branches/p3yk/Doc/mac/undoc.tex
==============================================================================
--- python/branches/p3yk/Doc/mac/undoc.tex (original)
+++ python/branches/p3yk/Doc/mac/undoc.tex Thu Jun 8 17:35:45 2006
@@ -95,14 +95,3 @@
The \module{W} widgets are used extensively in the \program{IDE}.
-\section{\module{waste} --- non-Apple \program{TextEdit} replacement}
-\declaremodule{standard}{waste}
- \platform{Mac}
-\modulesynopsis{Interface to the ``WorldScript-Aware Styled Text Engine.''}
-
-\begin{seealso}
- \seetitle[http://www.merzwaren.com/waste/]{About WASTE}{Information
- about the WASTE widget and library, including
- documentation and downloads.}
-\end{seealso}
-
Modified: python/branches/p3yk/Doc/whatsnew/whatsnew25.tex
==============================================================================
--- python/branches/p3yk/Doc/whatsnew/whatsnew25.tex (original)
+++ python/branches/p3yk/Doc/whatsnew/whatsnew25.tex Thu Jun 8 17:35:45 2006
@@ -1166,12 +1166,13 @@
and as a result sets will use a third less memory and are somewhat faster.
(Implemented by Raymond Hettinger.)
-\item The speed of some Unicode operations, such as
-finding substrings, string splitting, and character map decoding, has
-been improved. (Substring search and splitting improvements were
+\item The speed of some Unicode operations, such as finding
+substrings, string splitting, and character map encoding and decoding,
+has been improved. (Substring search and splitting improvements were
added by Fredrik Lundh and Andrew Dalke at the NeedForSpeed
-sprint. Character map decoding was improved by Walter D\"orwald.)
-% Patch 1313939
+sprint. Character maps were improved by Walter D\"orwald and
+Martin von~L\"owis.)
+% Patch 1313939, 1359618
\item The \function{long(\var{str}, \var{base})} function is now
faster on long digit strings because fewer intermediate results are
@@ -1185,6 +1186,11 @@
representation, yielding a 20\% speedup. (Contributed by Bob Ippolito
at the NeedForSpeed sprint.)
+\item The \module{re} module got a 1 or 2\% speedup by switching to
+Python's allocator functions instead of the system's
+\cfunction{malloc()} and \cfunction{free()}.
+(Contributed by Jack Diederich at the NeedForSpeed sprint.)
+
\item The code generator's peephole optimizer now performs
simple constant folding in expressions. If you write something like
\code{a = 2+3}, the code generator will do the arithmetic and produce
@@ -1358,7 +1364,6 @@
now support a \code{key} keyword parameter similar to the one
provided by the \function{min()}/\function{max()} functions
and the \method{sort()} methods. For example:
-Example:
\begin{verbatim}
>>> import heapq
@@ -1923,10 +1928,11 @@
operations because doing so is insecure; it makes your program
vulnerable to an SQL injection attack.
-Instead, use SQLite's parameter substitution. Put \samp{?} as a
+Instead, use the DB-API's parameter substitution. Put \samp{?} as a
placeholder wherever you want to use a value, and then provide a tuple
of values as the second argument to the cursor's \method{execute()}
-method. For example:
+method. (Other database modules may use a different placeholder,
+such as \samp{\%s} or \samp{:1}.) For example:
\begin{verbatim}
# Never do this -- insecure!
Modified: python/branches/p3yk/Include/symtable.h
==============================================================================
--- python/branches/p3yk/Include/symtable.h (original)
+++ python/branches/p3yk/Include/symtable.h Thu Jun 8 17:35:45 2006
@@ -39,6 +39,8 @@
unsigned ste_generator : 1; /* true if namespace is a generator */
unsigned ste_varargs : 1; /* true if block has varargs */
unsigned ste_varkeywords : 1; /* true if block has varkeywords */
+ unsigned ste_returns_value : 1; /* true if namespace uses return with
+ an argument */
int ste_lineno; /* first line of block */
int ste_opt_lineno; /* lineno of last exec or import * */
int ste_tmpname; /* counter for listcomp temp vars */
Modified: python/branches/p3yk/Include/unicodeobject.h
==============================================================================
--- python/branches/p3yk/Include/unicodeobject.h (original)
+++ python/branches/p3yk/Include/unicodeobject.h Thu Jun 8 17:35:45 2006
@@ -650,6 +650,11 @@
const char *errors /* error handling */
);
+PyAPI_FUNC(PyObject*) PyUnicode_BuildEncodingMap(
+ PyObject* string /* 256 character map */
+ );
+
+
/* --- UTF-7 Codecs ------------------------------------------------------- */
PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF7(
Modified: python/branches/p3yk/Lib/bsddb/__init__.py
==============================================================================
--- python/branches/p3yk/Lib/bsddb/__init__.py (original)
+++ python/branches/p3yk/Lib/bsddb/__init__.py Thu Jun 8 17:35:45 2006
@@ -343,6 +343,7 @@
e.set_cachesize(0, cachesize)
else:
raise error, "cachesize must be >= 20480"
+ e.set_lk_detect(db.DB_LOCK_DEFAULT)
e.open('.', db.DB_PRIVATE | db.DB_CREATE | db.DB_THREAD | db.DB_INIT_LOCK | db.DB_INIT_MPOOL)
return e
Modified: python/branches/p3yk/Lib/bsddb/dbobj.py
==============================================================================
--- python/branches/p3yk/Lib/bsddb/dbobj.py (original)
+++ python/branches/p3yk/Lib/bsddb/dbobj.py Thu Jun 8 17:35:45 2006
@@ -91,9 +91,14 @@
return self._cobj.lock_stat(*args, **kwargs)
def log_archive(self, *args, **kwargs):
return self._cobj.log_archive(*args, **kwargs)
+
def set_get_returns_none(self, *args, **kwargs):
return self._cobj.set_get_returns_none(*args, **kwargs)
+ if db.version() >= (4,0):
+ def log_stat(self, *args, **kwargs):
+ return apply(self._cobj.log_stat, args, kwargs)
+
if db.version() >= (4,1):
def dbremove(self, *args, **kwargs):
return self._cobj.dbremove(*args, **kwargs)
@@ -102,6 +107,10 @@
def set_encrypt(self, *args, **kwargs):
return self._cobj.set_encrypt(*args, **kwargs)
+ if db.version() >= (4,4):
+ def lsn_reset(self, *args, **kwargs):
+ return apply(self._cobj.lsn_reset, args, kwargs)
+
class DB(DictMixin):
def __init__(self, dbenv, *args, **kwargs):
@@ -208,3 +217,38 @@
if db.version() >= (4,1):
def set_encrypt(self, *args, **kwargs):
return self._cobj.set_encrypt(*args, **kwargs)
+
+
+class DBSequence:
+ def __init__(self, *args, **kwargs):
+ self._cobj = apply(db.DBSequence, args, kwargs)
+
+ def close(self, *args, **kwargs):
+ return apply(self._cobj.close, args, kwargs)
+ def get(self, *args, **kwargs):
+ return apply(self._cobj.get, args, kwargs)
+ def get_dbp(self, *args, **kwargs):
+ return apply(self._cobj.get_dbp, args, kwargs)
+ def get_key(self, *args, **kwargs):
+ return apply(self._cobj.get_key, args, kwargs)
+ def init_value(self, *args, **kwargs):
+ return apply(self._cobj.init_value, args, kwargs)
+ def open(self, *args, **kwargs):
+ return apply(self._cobj.open, args, kwargs)
+ def remove(self, *args, **kwargs):
+ return apply(self._cobj.remove, args, kwargs)
+ def stat(self, *args, **kwargs):
+ return apply(self._cobj.stat, args, kwargs)
+ def set_cachesize(self, *args, **kwargs):
+ return apply(self._cobj.set_cachesize, args, kwargs)
+ def set_flags(self, *args, **kwargs):
+ return apply(self._cobj.set_flags, args, kwargs)
+ def set_range(self, *args, **kwargs):
+ return apply(self._cobj.set_range, args, kwargs)
+ def get_cachesize(self, *args, **kwargs):
+ return apply(self._cobj.get_cachesize, args, kwargs)
+ def get_flags(self, *args, **kwargs):
+ return apply(self._cobj.get_flags, args, kwargs)
+ def get_range(self, *args, **kwargs):
+ return apply(self._cobj.get_range, args, kwargs)
+>>>>>>> .merge-right.r46752
Modified: python/branches/p3yk/Lib/bsddb/dbtables.py
==============================================================================
--- python/branches/p3yk/Lib/bsddb/dbtables.py (original)
+++ python/branches/p3yk/Lib/bsddb/dbtables.py Thu Jun 8 17:35:45 2006
@@ -131,7 +131,8 @@
class bsdTableDB :
def __init__(self, filename, dbhome, create=0, truncate=0, mode=0600,
recover=0, dbflags=0):
- """bsdTableDB.open(filename, dbhome, create=0, truncate=0, mode=0600)
+ """bsdTableDB(filename, dbhome, create=0, truncate=0, mode=0600)
+
Open database name in the dbhome BerkeleyDB directory.
Use keyword arguments when calling this constructor.
"""
@@ -218,7 +219,8 @@
def CreateTable(self, table, columns):
- """CreateTable(table, columns) - Create a new table in the database
+ """CreateTable(table, columns) - Create a new table in the database.
+
raises TableDBError if it already exists or for other DB errors.
"""
assert isinstance(columns, ListType)
@@ -286,7 +288,8 @@
def CreateOrExtendTable(self, table, columns):
"""CreateOrExtendTable(table, columns)
- - Create a new table in the database.
+ Create a new table in the database.
+
If a table of this name already exists, extend it to have any
additional columns present in the given list as well as
all of its current columns.
@@ -411,14 +414,15 @@
def Modify(self, table, conditions={}, mappings={}):
- """Modify(table, conditions) - Modify in rows matching 'conditions'
- using mapping functions in 'mappings'
- * conditions is a dictionary keyed on column names
- containing condition functions expecting the data string as an
- argument and returning a boolean.
- * mappings is a dictionary keyed on column names containint condition
- functions expecting the data string as an argument and returning the
- new string for that column.
+ """Modify(table, conditions={}, mappings={}) - Modify items in rows matching 'conditions' using mapping functions in 'mappings'
+
+ * table - the table name
+ * conditions - a dictionary keyed on column names containing
+ a condition callable expecting the data string as an
+ argument and returning a boolean.
+ * mappings - a dictionary keyed on column names containing a
+ condition callable expecting the data string as an argument and
+ returning the new string for that column.
"""
try:
matching_rowids = self.__Select(table, [], conditions)
@@ -450,7 +454,8 @@
txn.commit()
txn = None
- except DBError, dberror:
+ # catch all exceptions here since we call unknown callables
+ except:
if txn:
txn.abort()
raise
@@ -461,9 +466,10 @@
def Delete(self, table, conditions={}):
"""Delete(table, conditions) - Delete items matching the given
conditions from the table.
- * conditions is a dictionary keyed on column names
- containing condition functions expecting the data string as an
- argument and returning a boolean.
+
+ * conditions - a dictionary keyed on column names containing
+ condition functions expecting the data string as an
+ argument and returning a boolean.
"""
try:
matching_rowids = self.__Select(table, [], conditions)
@@ -499,11 +505,12 @@
def Select(self, table, columns, conditions={}):
- """Select(table, conditions) - retrieve specific row data
+ """Select(table, columns, conditions) - retrieve specific row data
Returns a list of row column->value mapping dictionaries.
- * columns is a list of which column data to return. If
+
+ * columns - a list of which column data to return. If
columns is None, all columns will be returned.
- * conditions is a dictionary keyed on column names
+ * conditions - a dictionary keyed on column names
containing callable conditions expecting the data string as an
argument and returning a boolean.
"""
Modified: python/branches/p3yk/Lib/bsddb/test/test_all.py
==============================================================================
--- python/branches/p3yk/Lib/bsddb/test/test_all.py (original)
+++ python/branches/p3yk/Lib/bsddb/test/test_all.py Thu Jun 8 17:35:45 2006
@@ -4,6 +4,12 @@
import sys
import os
import unittest
+try:
+ # For Pythons w/distutils pybsddb
+ from bsddb3 import db
+except ImportError:
+ # For Python 2.3
+ from bsddb import db
verbose = 0
if 'verbose' in sys.argv:
@@ -16,12 +22,6 @@
def print_versions():
- try:
- # For Pythons w/distutils pybsddb
- from bsddb3 import db
- except ImportError:
- # For Python 2.3
- from bsddb import db
print
print '-=' * 38
print db.DB_VERSION_STRING
@@ -69,6 +69,8 @@
'test_queue',
'test_recno',
'test_thread',
+ 'test_sequence',
+ 'test_cursor_pget_bug',
]
alltests = unittest.TestSuite()
Modified: python/branches/p3yk/Lib/bsddb/test/test_basics.py
==============================================================================
--- python/branches/p3yk/Lib/bsddb/test/test_basics.py (original)
+++ python/branches/p3yk/Lib/bsddb/test/test_basics.py Thu Jun 8 17:35:45 2006
@@ -659,12 +659,22 @@
except db.DBIncompleteError:
pass
+ if db.version() >= (4,0):
+ statDict = self.env.log_stat(0);
+ assert statDict.has_key('magic')
+ assert statDict.has_key('version')
+ assert statDict.has_key('cur_file')
+ assert statDict.has_key('region_nowait')
+
# must have at least one log file present:
logs = self.env.log_archive(db.DB_ARCH_ABS | db.DB_ARCH_LOG)
assert logs != None
for log in logs:
if verbose:
print 'log file: ' + log
+ if db.version >= (4,2):
+ logs = self.env.log_archive(db.DB_ARCH_REMOVE)
+ assert not logs
self.txn = self.env.txn_begin()
Modified: python/branches/p3yk/Lib/bsddb/test/test_dbtables.py
==============================================================================
--- python/branches/p3yk/Lib/bsddb/test/test_dbtables.py (original)
+++ python/branches/p3yk/Lib/bsddb/test/test_dbtables.py Thu Jun 8 17:35:45 2006
@@ -339,6 +339,16 @@
conditions={'Name': dbtables.LikeCond('%')},
mappings={'Access': increment_access})
+ try:
+ self.tdb.Modify(tabname,
+ conditions={'Name': dbtables.LikeCond('%')},
+ mappings={'Access': 'What is your quest?'})
+ except TypeError:
+ # success, the string value in mappings isn't callable
+ pass
+ else:
+ raise RuntimeError, "why was TypeError not raised for bad callable?"
+
# Delete key in select conditions
values = self.tdb.Select(
tabname, None,
Modified: python/branches/p3yk/Lib/ctypes/test/test_cfuncs.py
==============================================================================
--- python/branches/p3yk/Lib/ctypes/test/test_cfuncs.py (original)
+++ python/branches/p3yk/Lib/ctypes/test/test_cfuncs.py Thu Jun 8 17:35:45 2006
@@ -40,41 +40,49 @@
def test_short(self):
self._dll.tf_h.restype = c_short
+ self._dll.tf_h.argtypes = (c_short,)
self.failUnlessEqual(self._dll.tf_h(-32766), -10922)
self.failUnlessEqual(self.S(), -32766)
def test_short_plus(self):
self._dll.tf_bh.restype = c_short
+ self._dll.tf_bh.argtypes = (c_byte, c_short)
self.failUnlessEqual(self._dll.tf_bh(0, -32766), -10922)
self.failUnlessEqual(self.S(), -32766)
def test_ushort(self):
self._dll.tf_H.restype = c_ushort
+ self._dll.tf_H.argtypes = (c_ushort,)
self.failUnlessEqual(self._dll.tf_H(65535), 21845)
self.failUnlessEqual(self.U(), 65535)
def test_ushort_plus(self):
self._dll.tf_bH.restype = c_ushort
+ self._dll.tf_bH.argtypes = (c_byte, c_ushort)
self.failUnlessEqual(self._dll.tf_bH(0, 65535), 21845)
self.failUnlessEqual(self.U(), 65535)
def test_int(self):
self._dll.tf_i.restype = c_int
+ self._dll.tf_i.argtypes = (c_int,)
self.failUnlessEqual(self._dll.tf_i(-2147483646), -715827882)
self.failUnlessEqual(self.S(), -2147483646)
def test_int_plus(self):
self._dll.tf_bi.restype = c_int
+ self._dll.tf_bi.argtypes = (c_byte, c_int)
self.failUnlessEqual(self._dll.tf_bi(0, -2147483646), -715827882)
self.failUnlessEqual(self.S(), -2147483646)
def test_uint(self):
self._dll.tf_I.restype = c_uint
+ self._dll.tf_I.argtypes = (c_uint,)
self.failUnlessEqual(self._dll.tf_I(4294967295), 1431655765)
self.failUnlessEqual(self.U(), 4294967295)
def test_uint_plus(self):
self._dll.tf_bI.restype = c_uint
+ self._dll.tf_bI.argtypes = (c_byte, c_uint)
self.failUnlessEqual(self._dll.tf_bI(0, 4294967295), 1431655765)
self.failUnlessEqual(self.U(), 4294967295)
Modified: python/branches/p3yk/Lib/ctypes/test/test_pointers.py
==============================================================================
--- python/branches/p3yk/Lib/ctypes/test/test_pointers.py (original)
+++ python/branches/p3yk/Lib/ctypes/test/test_pointers.py Thu Jun 8 17:35:45 2006
@@ -133,7 +133,7 @@
self.failUnlessEqual(p[0], 42)
self.failUnlessEqual(p.contents.value, 42)
- def test_charpp( self ):
+ def test_charpp(self):
"""Test that a character pointer-to-pointer is correctly passed"""
dll = CDLL(_ctypes_test.__file__)
func = dll._testfunc_c_p_p
Modified: python/branches/p3yk/Lib/ctypes/test/test_structures.py
==============================================================================
--- python/branches/p3yk/Lib/ctypes/test/test_structures.py (original)
+++ python/branches/p3yk/Lib/ctypes/test/test_structures.py Thu Jun 8 17:35:45 2006
@@ -138,8 +138,8 @@
self.failUnlessEqual(X.y.size, sizeof(c_char))
# readonly
- self.assertRaises(TypeError, setattr, X.x, "offset", 92)
- self.assertRaises(TypeError, setattr, X.x, "size", 92)
+ self.assertRaises(AttributeError, setattr, X.x, "offset", 92)
+ self.assertRaises(AttributeError, setattr, X.x, "size", 92)
class X(Union):
_fields_ = [("x", c_int),
@@ -152,8 +152,8 @@
self.failUnlessEqual(X.y.size, sizeof(c_char))
# readonly
- self.assertRaises(TypeError, setattr, X.x, "offset", 92)
- self.assertRaises(TypeError, setattr, X.x, "size", 92)
+ self.assertRaises(AttributeError, setattr, X.x, "offset", 92)
+ self.assertRaises(AttributeError, setattr, X.x, "size", 92)
# XXX Should we check nested data types also?
# offset is always relative to the class...
Modified: python/branches/p3yk/Lib/doctest.py
==============================================================================
--- python/branches/p3yk/Lib/doctest.py (original)
+++ python/branches/p3yk/Lib/doctest.py Thu Jun 8 17:35:45 2006
@@ -63,7 +63,6 @@
'REPORT_ONLY_FIRST_FAILURE',
'REPORTING_FLAGS',
# 1. Utility Functions
- 'is_private',
# 2. Example & DocTest
'Example',
'DocTest',
@@ -101,11 +100,6 @@
import warnings
from StringIO import StringIO
-# Don't whine about the deprecated is_private function in this
-# module's tests.
-warnings.filterwarnings("ignore", "is_private", DeprecationWarning,
- __name__, 0)
-
# There are 4 basic classes:
# - Example: a <source, want> pair, plus an intra-docstring line number.
# - DocTest: a collection of examples, parsed from a docstring, plus
@@ -178,35 +172,6 @@
## 1. Utility Functions
######################################################################
-def is_private(prefix, base):
- """prefix, base -> true iff name prefix + "." + base is "private".
-
- Prefix may be an empty string, and base does not contain a period.
- Prefix is ignored (although functions you write conforming to this
- protocol may make use of it).
- Return true iff base begins with an (at least one) underscore, but
- does not both begin and end with (at least) two underscores.
-
- >>> is_private("a.b", "my_func")
- False
- >>> is_private("____", "_my_func")
- True
- >>> is_private("someclass", "__init__")
- False
- >>> is_private("sometypo", "__init_")
- True
- >>> is_private("x.y.z", "_")
- True
- >>> is_private("_x.y.z", "__")
- False
- >>> is_private("", "") # senseless but consistent
- False
- """
- warnings.warn("is_private is deprecated; it wasn't useful; "
- "examine DocTestFinder.find() lists instead",
- DeprecationWarning, stacklevel=2)
- return base[:1] == "_" and not base[:2] == "__" == base[-2:]
-
def _extract_future_flags(globs):
"""
Return the compiler-flags associated with the future features that
@@ -759,7 +724,7 @@
"""
def __init__(self, verbose=False, parser=DocTestParser(),
- recurse=True, _namefilter=None, exclude_empty=True):
+ recurse=True, exclude_empty=True):
"""
Create a new doctest finder.
@@ -779,12 +744,8 @@
self._verbose = verbose
self._recurse = recurse
self._exclude_empty = exclude_empty
- # _namefilter is undocumented, and exists only for temporary backward-
- # compatibility support of testmod's deprecated isprivate mess.
- self._namefilter = _namefilter
- def find(self, obj, name=None, module=None, globs=None,
- extraglobs=None):
+ def find(self, obj, name=None, module=None, globs=None, extraglobs=None):
"""
Return a list of the DocTests that are defined by the given
object's docstring, or by any of its contained objects'
@@ -862,13 +823,6 @@
self._find(tests, obj, name, module, source_lines, globs, {})
return tests
- def _filter(self, obj, prefix, base):
- """
- Return true if the given object should not be examined.
- """
- return (self._namefilter is not None and
- self._namefilter(prefix, base))
-
def _from_module(self, module, object):
"""
Return true if the given object is defined in the given
@@ -910,9 +864,6 @@
# Look for tests in a module's contained objects.
if inspect.ismodule(obj) and self._recurse:
for valname, val in obj.__dict__.items():
- # Check if this contained object should be ignored.
- if self._filter(val, name, valname):
- continue
valname = '%s.%s' % (name, valname)
# Recurse to functions & classes.
if ((inspect.isfunction(val) or inspect.isclass(val)) and
@@ -941,9 +892,6 @@
# Look for tests in a class's contained objects.
if inspect.isclass(obj) and self._recurse:
for valname, val in obj.__dict__.items():
- # Check if this contained object should be ignored.
- if self._filter(val, name, valname):
- continue
# Special handling for staticmethod/classmethod.
if isinstance(val, staticmethod):
val = getattr(obj, valname)
@@ -1751,17 +1699,16 @@
# class, updated by testmod.
master = None
-def testmod(m=None, name=None, globs=None, verbose=None, isprivate=None,
+def testmod(m=None, name=None, globs=None, verbose=None,
report=True, optionflags=0, extraglobs=None,
raise_on_error=False, exclude_empty=False):
- """m=None, name=None, globs=None, verbose=None, isprivate=None,
- report=True, optionflags=0, extraglobs=None, raise_on_error=False,
+ """m=None, name=None, globs=None, verbose=None, report=True,
+ optionflags=0, extraglobs=None, raise_on_error=False,
exclude_empty=False
Test examples in docstrings in functions and classes reachable
from module m (or the current module if m is not supplied), starting
- with m.__doc__. Unless isprivate is specified, private names
- are not skipped.
+ with m.__doc__.
Also test examples reachable from dict m.__test__ if it exists and is
not None. m.__test__ maps names to functions, classes and strings;
@@ -1810,13 +1757,6 @@
first unexpected exception or failure. This allows failures to be
post-mortem debugged.
- Deprecated in Python 2.4:
- Optional keyword arg "isprivate" specifies a function used to
- determine whether a name is private. The default function is
- treat all functions as public. Optionally, "isprivate" can be
- set to doctest.is_private to skip over functions marked as private
- using the underscore naming convention; see its docs for details.
-
Advanced tomfoolery: testmod runs methods of a local instance of
class doctest.Tester, then merges the results into (or creates)
global Tester instance doctest.master. Methods of doctest.master
@@ -1827,11 +1767,6 @@
"""
global master
- if isprivate is not None:
- warnings.warn("the isprivate argument is deprecated; "
- "examine DocTestFinder.find() lists instead",
- DeprecationWarning)
-
# If no module was given, then use __main__.
if m is None:
# DWA - m will still be None if this wasn't invoked from the command
@@ -1848,7 +1783,7 @@
name = m.__name__
# Find, parse, and run all tests in the given module.
- finder = DocTestFinder(_namefilter=isprivate, exclude_empty=exclude_empty)
+ finder = DocTestFinder(exclude_empty=exclude_empty)
if raise_on_error:
runner = DebugRunner(verbose=verbose, optionflags=optionflags)
@@ -2021,8 +1956,7 @@
# actually used in any way.
class Tester:
- def __init__(self, mod=None, globs=None, verbose=None,
- isprivate=None, optionflags=0):
+ def __init__(self, mod=None, globs=None, verbose=None, optionflags=0):
warnings.warn("class Tester is deprecated; "
"use class doctest.DocTestRunner instead",
@@ -2037,9 +1971,8 @@
self.globs = globs
self.verbose = verbose
- self.isprivate = isprivate
self.optionflags = optionflags
- self.testfinder = DocTestFinder(_namefilter=isprivate)
+ self.testfinder = DocTestFinder()
self.testrunner = DocTestRunner(verbose=verbose,
optionflags=optionflags)
Modified: python/branches/p3yk/Lib/encodings/cp037.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/cp037.py (original)
+++ python/branches/p3yk/Lib/encodings/cp037.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\x9f' # 0xFF -> CONTROL
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x37, # END OF TRANSMISSION
- 0x0005: 0x2D, # ENQUIRY
- 0x0006: 0x2E, # ACKNOWLEDGE
- 0x0007: 0x2F, # BELL
- 0x0008: 0x16, # BACKSPACE
- 0x0009: 0x05, # HORIZONTAL TABULATION
- 0x000A: 0x25, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x3C, # DEVICE CONTROL FOUR
- 0x0015: 0x3D, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x32, # SYNCHRONOUS IDLE
- 0x0017: 0x26, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x3F, # SUBSTITUTE
- 0x001B: 0x27, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x40, # SPACE
- 0x0021: 0x5A, # EXCLAMATION MARK
- 0x0022: 0x7F, # QUOTATION MARK
- 0x0023: 0x7B, # NUMBER SIGN
- 0x0024: 0x5B, # DOLLAR SIGN
- 0x0025: 0x6C, # PERCENT SIGN
- 0x0026: 0x50, # AMPERSAND
- 0x0027: 0x7D, # APOSTROPHE
- 0x0028: 0x4D, # LEFT PARENTHESIS
- 0x0029: 0x5D, # RIGHT PARENTHESIS
- 0x002A: 0x5C, # ASTERISK
- 0x002B: 0x4E, # PLUS SIGN
- 0x002C: 0x6B, # COMMA
- 0x002D: 0x60, # HYPHEN-MINUS
- 0x002E: 0x4B, # FULL STOP
- 0x002F: 0x61, # SOLIDUS
- 0x0030: 0xF0, # DIGIT ZERO
- 0x0031: 0xF1, # DIGIT ONE
- 0x0032: 0xF2, # DIGIT TWO
- 0x0033: 0xF3, # DIGIT THREE
- 0x0034: 0xF4, # DIGIT FOUR
- 0x0035: 0xF5, # DIGIT FIVE
- 0x0036: 0xF6, # DIGIT SIX
- 0x0037: 0xF7, # DIGIT SEVEN
- 0x0038: 0xF8, # DIGIT EIGHT
- 0x0039: 0xF9, # DIGIT NINE
- 0x003A: 0x7A, # COLON
- 0x003B: 0x5E, # SEMICOLON
- 0x003C: 0x4C, # LESS-THAN SIGN
- 0x003D: 0x7E, # EQUALS SIGN
- 0x003E: 0x6E, # GREATER-THAN SIGN
- 0x003F: 0x6F, # QUESTION MARK
- 0x0040: 0x7C, # COMMERCIAL AT
- 0x0041: 0xC1, # LATIN CAPITAL LETTER A
- 0x0042: 0xC2, # LATIN CAPITAL LETTER B
- 0x0043: 0xC3, # LATIN CAPITAL LETTER C
- 0x0044: 0xC4, # LATIN CAPITAL LETTER D
- 0x0045: 0xC5, # LATIN CAPITAL LETTER E
- 0x0046: 0xC6, # LATIN CAPITAL LETTER F
- 0x0047: 0xC7, # LATIN CAPITAL LETTER G
- 0x0048: 0xC8, # LATIN CAPITAL LETTER H
- 0x0049: 0xC9, # LATIN CAPITAL LETTER I
- 0x004A: 0xD1, # LATIN CAPITAL LETTER J
- 0x004B: 0xD2, # LATIN CAPITAL LETTER K
- 0x004C: 0xD3, # LATIN CAPITAL LETTER L
- 0x004D: 0xD4, # LATIN CAPITAL LETTER M
- 0x004E: 0xD5, # LATIN CAPITAL LETTER N
- 0x004F: 0xD6, # LATIN CAPITAL LETTER O
- 0x0050: 0xD7, # LATIN CAPITAL LETTER P
- 0x0051: 0xD8, # LATIN CAPITAL LETTER Q
- 0x0052: 0xD9, # LATIN CAPITAL LETTER R
- 0x0053: 0xE2, # LATIN CAPITAL LETTER S
- 0x0054: 0xE3, # LATIN CAPITAL LETTER T
- 0x0055: 0xE4, # LATIN CAPITAL LETTER U
- 0x0056: 0xE5, # LATIN CAPITAL LETTER V
- 0x0057: 0xE6, # LATIN CAPITAL LETTER W
- 0x0058: 0xE7, # LATIN CAPITAL LETTER X
- 0x0059: 0xE8, # LATIN CAPITAL LETTER Y
- 0x005A: 0xE9, # LATIN CAPITAL LETTER Z
- 0x005B: 0xBA, # LEFT SQUARE BRACKET
- 0x005C: 0xE0, # REVERSE SOLIDUS
- 0x005D: 0xBB, # RIGHT SQUARE BRACKET
- 0x005E: 0xB0, # CIRCUMFLEX ACCENT
- 0x005F: 0x6D, # LOW LINE
- 0x0060: 0x79, # GRAVE ACCENT
- 0x0061: 0x81, # LATIN SMALL LETTER A
- 0x0062: 0x82, # LATIN SMALL LETTER B
- 0x0063: 0x83, # LATIN SMALL LETTER C
- 0x0064: 0x84, # LATIN SMALL LETTER D
- 0x0065: 0x85, # LATIN SMALL LETTER E
- 0x0066: 0x86, # LATIN SMALL LETTER F
- 0x0067: 0x87, # LATIN SMALL LETTER G
- 0x0068: 0x88, # LATIN SMALL LETTER H
- 0x0069: 0x89, # LATIN SMALL LETTER I
- 0x006A: 0x91, # LATIN SMALL LETTER J
- 0x006B: 0x92, # LATIN SMALL LETTER K
- 0x006C: 0x93, # LATIN SMALL LETTER L
- 0x006D: 0x94, # LATIN SMALL LETTER M
- 0x006E: 0x95, # LATIN SMALL LETTER N
- 0x006F: 0x96, # LATIN SMALL LETTER O
- 0x0070: 0x97, # LATIN SMALL LETTER P
- 0x0071: 0x98, # LATIN SMALL LETTER Q
- 0x0072: 0x99, # LATIN SMALL LETTER R
- 0x0073: 0xA2, # LATIN SMALL LETTER S
- 0x0074: 0xA3, # LATIN SMALL LETTER T
- 0x0075: 0xA4, # LATIN SMALL LETTER U
- 0x0076: 0xA5, # LATIN SMALL LETTER V
- 0x0077: 0xA6, # LATIN SMALL LETTER W
- 0x0078: 0xA7, # LATIN SMALL LETTER X
- 0x0079: 0xA8, # LATIN SMALL LETTER Y
- 0x007A: 0xA9, # LATIN SMALL LETTER Z
- 0x007B: 0xC0, # LEFT CURLY BRACKET
- 0x007C: 0x4F, # VERTICAL LINE
- 0x007D: 0xD0, # RIGHT CURLY BRACKET
- 0x007E: 0xA1, # TILDE
- 0x007F: 0x07, # DELETE
- 0x0080: 0x20, # CONTROL
- 0x0081: 0x21, # CONTROL
- 0x0082: 0x22, # CONTROL
- 0x0083: 0x23, # CONTROL
- 0x0084: 0x24, # CONTROL
- 0x0085: 0x15, # CONTROL
- 0x0086: 0x06, # CONTROL
- 0x0087: 0x17, # CONTROL
- 0x0088: 0x28, # CONTROL
- 0x0089: 0x29, # CONTROL
- 0x008A: 0x2A, # CONTROL
- 0x008B: 0x2B, # CONTROL
- 0x008C: 0x2C, # CONTROL
- 0x008D: 0x09, # CONTROL
- 0x008E: 0x0A, # CONTROL
- 0x008F: 0x1B, # CONTROL
- 0x0090: 0x30, # CONTROL
- 0x0091: 0x31, # CONTROL
- 0x0092: 0x1A, # CONTROL
- 0x0093: 0x33, # CONTROL
- 0x0094: 0x34, # CONTROL
- 0x0095: 0x35, # CONTROL
- 0x0096: 0x36, # CONTROL
- 0x0097: 0x08, # CONTROL
- 0x0098: 0x38, # CONTROL
- 0x0099: 0x39, # CONTROL
- 0x009A: 0x3A, # CONTROL
- 0x009B: 0x3B, # CONTROL
- 0x009C: 0x04, # CONTROL
- 0x009D: 0x14, # CONTROL
- 0x009E: 0x3E, # CONTROL
- 0x009F: 0xFF, # CONTROL
- 0x00A0: 0x41, # NO-BREAK SPACE
- 0x00A1: 0xAA, # INVERTED EXCLAMATION MARK
- 0x00A2: 0x4A, # CENT SIGN
- 0x00A3: 0xB1, # POUND SIGN
- 0x00A4: 0x9F, # CURRENCY SIGN
- 0x00A5: 0xB2, # YEN SIGN
- 0x00A6: 0x6A, # BROKEN BAR
- 0x00A7: 0xB5, # SECTION SIGN
- 0x00A8: 0xBD, # DIAERESIS
- 0x00A9: 0xB4, # COPYRIGHT SIGN
- 0x00AA: 0x9A, # FEMININE ORDINAL INDICATOR
- 0x00AB: 0x8A, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0x5F, # NOT SIGN
- 0x00AD: 0xCA, # SOFT HYPHEN
- 0x00AE: 0xAF, # REGISTERED SIGN
- 0x00AF: 0xBC, # MACRON
- 0x00B0: 0x90, # DEGREE SIGN
- 0x00B1: 0x8F, # PLUS-MINUS SIGN
- 0x00B2: 0xEA, # SUPERSCRIPT TWO
- 0x00B3: 0xFA, # SUPERSCRIPT THREE
- 0x00B4: 0xBE, # ACUTE ACCENT
- 0x00B5: 0xA0, # MICRO SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00B7: 0xB3, # MIDDLE DOT
- 0x00B8: 0x9D, # CEDILLA
- 0x00B9: 0xDA, # SUPERSCRIPT ONE
- 0x00BA: 0x9B, # MASCULINE ORDINAL INDICATOR
- 0x00BB: 0x8B, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BC: 0xB7, # VULGAR FRACTION ONE QUARTER
- 0x00BD: 0xB8, # VULGAR FRACTION ONE HALF
- 0x00BE: 0xB9, # VULGAR FRACTION THREE QUARTERS
- 0x00BF: 0xAB, # INVERTED QUESTION MARK
- 0x00C0: 0x64, # LATIN CAPITAL LETTER A WITH GRAVE
- 0x00C1: 0x65, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0x62, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C3: 0x66, # LATIN CAPITAL LETTER A WITH TILDE
- 0x00C4: 0x63, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C5: 0x67, # LATIN CAPITAL LETTER A WITH RING ABOVE
- 0x00C6: 0x9E, # LATIN CAPITAL LIGATURE AE
- 0x00C7: 0x68, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C8: 0x74, # LATIN CAPITAL LETTER E WITH GRAVE
- 0x00C9: 0x71, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CA: 0x72, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
- 0x00CB: 0x73, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CC: 0x78, # LATIN CAPITAL LETTER I WITH GRAVE
- 0x00CD: 0x75, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0x76, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00CF: 0x77, # LATIN CAPITAL LETTER I WITH DIAERESIS
- 0x00D0: 0xAC, # LATIN CAPITAL LETTER ETH (ICELANDIC)
- 0x00D1: 0x69, # LATIN CAPITAL LETTER N WITH TILDE
- 0x00D2: 0xED, # LATIN CAPITAL LETTER O WITH GRAVE
- 0x00D3: 0xEE, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xEB, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D5: 0xEF, # LATIN CAPITAL LETTER O WITH TILDE
- 0x00D6: 0xEC, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D7: 0xBF, # MULTIPLICATION SIGN
- 0x00D8: 0x80, # LATIN CAPITAL LETTER O WITH STROKE
- 0x00D9: 0xFD, # LATIN CAPITAL LETTER U WITH GRAVE
- 0x00DA: 0xFE, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DB: 0xFB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
- 0x00DC: 0xFC, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DD: 0xAD, # LATIN CAPITAL LETTER Y WITH ACUTE
- 0x00DE: 0xAE, # LATIN CAPITAL LETTER THORN (ICELANDIC)
- 0x00DF: 0x59, # LATIN SMALL LETTER SHARP S (GERMAN)
- 0x00E0: 0x44, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E1: 0x45, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0x42, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E3: 0x46, # LATIN SMALL LETTER A WITH TILDE
- 0x00E4: 0x43, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E5: 0x47, # LATIN SMALL LETTER A WITH RING ABOVE
- 0x00E6: 0x9C, # LATIN SMALL LIGATURE AE
- 0x00E7: 0x48, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0x54, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0x51, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0x52, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0x53, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00EC: 0x58, # LATIN SMALL LETTER I WITH GRAVE
- 0x00ED: 0x55, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0x56, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0x57, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F0: 0x8C, # LATIN SMALL LETTER ETH (ICELANDIC)
- 0x00F1: 0x49, # LATIN SMALL LETTER N WITH TILDE
- 0x00F2: 0xCD, # LATIN SMALL LETTER O WITH GRAVE
- 0x00F3: 0xCE, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0xCB, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F5: 0xCF, # LATIN SMALL LETTER O WITH TILDE
- 0x00F6: 0xCC, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xE1, # DIVISION SIGN
- 0x00F8: 0x70, # LATIN SMALL LETTER O WITH STROKE
- 0x00F9: 0xDD, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FA: 0xDE, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0xDB, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0xDC, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x00FD: 0x8D, # LATIN SMALL LETTER Y WITH ACUTE
- 0x00FE: 0x8E, # LATIN SMALL LETTER THORN (ICELANDIC)
- 0x00FF: 0xDF, # LATIN SMALL LETTER Y WITH DIAERESIS
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/cp1006.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/cp1006.py (original)
+++ python/branches/p3yk/Lib/encodings/cp1006.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,262 +303,5 @@
u'\ufe7d' # 0xFF -> ARABIC SHADDA MEDIAL FORM
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x0080: 0x80, # <control>
- 0x0081: 0x81, # <control>
- 0x0082: 0x82, # <control>
- 0x0083: 0x83, # <control>
- 0x0084: 0x84, # <control>
- 0x0085: 0x85, # <control>
- 0x0086: 0x86, # <control>
- 0x0087: 0x87, # <control>
- 0x0088: 0x88, # <control>
- 0x0089: 0x89, # <control>
- 0x008A: 0x8A, # <control>
- 0x008B: 0x8B, # <control>
- 0x008C: 0x8C, # <control>
- 0x008D: 0x8D, # <control>
- 0x008E: 0x8E, # <control>
- 0x008F: 0x8F, # <control>
- 0x0090: 0x90, # <control>
- 0x0091: 0x91, # <control>
- 0x0092: 0x92, # <control>
- 0x0093: 0x93, # <control>
- 0x0094: 0x94, # <control>
- 0x0095: 0x95, # <control>
- 0x0096: 0x96, # <control>
- 0x0097: 0x97, # <control>
- 0x0098: 0x98, # <control>
- 0x0099: 0x99, # <control>
- 0x009A: 0x9A, # <control>
- 0x009B: 0x9B, # <control>
- 0x009C: 0x9C, # <control>
- 0x009D: 0x9D, # <control>
- 0x009E: 0x9E, # <control>
- 0x009F: 0x9F, # <control>
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x060C: 0xAB, # ARABIC COMMA
- 0x061B: 0xAC, # ARABIC SEMICOLON
- 0x061F: 0xAE, # ARABIC QUESTION MARK
- 0x06F0: 0xA1, # EXTENDED ARABIC-INDIC DIGIT ZERO
- 0x06F1: 0xA2, # EXTENDED ARABIC-INDIC DIGIT ONE
- 0x06F2: 0xA3, # EXTENDED ARABIC-INDIC DIGIT TWO
- 0x06F3: 0xA4, # EXTENDED ARABIC-INDIC DIGIT THREE
- 0x06F4: 0xA5, # EXTENDED ARABIC-INDIC DIGIT FOUR
- 0x06F5: 0xA6, # EXTENDED ARABIC-INDIC DIGIT FIVE
- 0x06F6: 0xA7, # EXTENDED ARABIC-INDIC DIGIT SIX
- 0x06F7: 0xA8, # EXTENDED ARABIC-INDIC DIGIT SEVEN
- 0x06F8: 0xA9, # EXTENDED ARABIC-INDIC DIGIT EIGHT
- 0x06F9: 0xAA, # EXTENDED ARABIC-INDIC DIGIT NINE
- 0xFB56: 0xB5, # ARABIC LETTER PEH ISOLATED FORM
- 0xFB58: 0xB6, # ARABIC LETTER PEH INITIAL FORM
- 0xFB66: 0xBA, # ARABIC LETTER TTEH ISOLATED FORM
- 0xFB68: 0xBB, # ARABIC LETTER TTEH INITIAL FORM
- 0xFB7A: 0xC0, # ARABIC LETTER TCHEH ISOLATED FORM
- 0xFB7C: 0xC1, # ARABIC LETTER TCHEH INITIAL FORM
- 0xFB84: 0xC7, # ARABIC LETTER DAHAL ISOLATED FORMN
- 0xFB8A: 0xCC, # ARABIC LETTER JEH ISOLATED FORM
- 0xFB8C: 0xCA, # ARABIC LETTER RREH ISOLATED FORM
- 0xFB92: 0xE5, # ARABIC LETTER GAF ISOLATED FORM
- 0xFB94: 0xE6, # ARABIC LETTER GAF INITIAL FORM
- 0xFB9E: 0xEC, # ARABIC LETTER NOON GHUNNA ISOLATED FORM
- 0xFBA6: 0xF1, # ARABIC LETTER HEH GOAL ISOLATED FORM
- 0xFBA8: 0xF2, # ARABIC LETTER HEH GOAL INITIAL FORM
- 0xFBA9: 0xF3, # ARABIC LETTER HEH GOAL MEDIAL FORM
- 0xFBAA: 0xF4, # ARABIC LETTER HEH DOACHASHMEE ISOLATED FORM
- 0xFBAE: 0xFD, # ARABIC LETTER YEH BARREE ISOLATED FORM
- 0xFBB0: 0xFC, # ARABIC LETTER YEH BARREE WITH HAMZA ABOVE ISOLATED FORM
- 0xFE7C: 0xFE, # ARABIC SHADDA ISOLATED FORM
- 0xFE7D: 0xFF, # ARABIC SHADDA MEDIAL FORM
- 0xFE80: 0xF5, # ARABIC LETTER HAMZA ISOLATED FORM
- 0xFE81: 0xAF, # ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM
- 0xFE85: 0xEF, # ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM
- 0xFE89: 0xF6, # ARABIC LETTER YEH WITH HAMZA ABOVE ISOLATED FORM
- 0xFE8A: 0xF7, # ARABIC LETTER YEH WITH HAMZA ABOVE FINAL FORM
- 0xFE8B: 0xF8, # ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM
- 0xFE8D: 0xB0, # ARABIC LETTER ALEF ISOLATED FORM
- 0xFE8E: None, # ARABIC LETTER ALEF FINAL FORM
- 0xFE8F: 0xB3, # ARABIC LETTER BEH ISOLATED FORM
- 0xFE91: 0xB4, # ARABIC LETTER BEH INITIAL FORM
- 0xFE93: 0xB7, # ARABIC LETTER TEH MARBUTA ISOLATED FORM
- 0xFE95: 0xB8, # ARABIC LETTER TEH ISOLATED FORM
- 0xFE97: 0xB9, # ARABIC LETTER TEH INITIAL FORM
- 0xFE99: 0xBC, # ARABIC LETTER THEH ISOLATED FORM
- 0xFE9B: 0xBD, # ARABIC LETTER THEH INITIAL FORM
- 0xFE9D: 0xBE, # ARABIC LETTER JEEM ISOLATED FORM
- 0xFE9F: 0xBF, # ARABIC LETTER JEEM INITIAL FORM
- 0xFEA1: 0xC2, # ARABIC LETTER HAH ISOLATED FORM
- 0xFEA3: 0xC3, # ARABIC LETTER HAH INITIAL FORM
- 0xFEA5: 0xC4, # ARABIC LETTER KHAH ISOLATED FORM
- 0xFEA7: 0xC5, # ARABIC LETTER KHAH INITIAL FORM
- 0xFEA9: 0xC6, # ARABIC LETTER DAL ISOLATED FORM
- 0xFEAB: 0xC8, # ARABIC LETTER THAL ISOLATED FORM
- 0xFEAD: 0xC9, # ARABIC LETTER REH ISOLATED FORM
- 0xFEAF: 0xCB, # ARABIC LETTER ZAIN ISOLATED FORM
- 0xFEB1: 0xCD, # ARABIC LETTER SEEN ISOLATED FORM
- 0xFEB3: 0xCE, # ARABIC LETTER SEEN INITIAL FORM
- 0xFEB5: 0xCF, # ARABIC LETTER SHEEN ISOLATED FORM
- 0xFEB7: 0xD0, # ARABIC LETTER SHEEN INITIAL FORM
- 0xFEB9: 0xD1, # ARABIC LETTER SAD ISOLATED FORM
- 0xFEBB: 0xD2, # ARABIC LETTER SAD INITIAL FORM
- 0xFEBD: 0xD3, # ARABIC LETTER DAD ISOLATED FORM
- 0xFEBF: 0xD4, # ARABIC LETTER DAD INITIAL FORM
- 0xFEC1: 0xD5, # ARABIC LETTER TAH ISOLATED FORM
- 0xFEC5: 0xD6, # ARABIC LETTER ZAH ISOLATED FORM
- 0xFEC9: 0xD7, # ARABIC LETTER AIN ISOLATED FORM
- 0xFECA: 0xD8, # ARABIC LETTER AIN FINAL FORM
- 0xFECB: 0xD9, # ARABIC LETTER AIN INITIAL FORM
- 0xFECC: 0xDA, # ARABIC LETTER AIN MEDIAL FORM
- 0xFECD: 0xDB, # ARABIC LETTER GHAIN ISOLATED FORM
- 0xFECE: 0xDC, # ARABIC LETTER GHAIN FINAL FORM
- 0xFECF: 0xDD, # ARABIC LETTER GHAIN INITIAL FORM
- 0xFED0: 0xDE, # ARABIC LETTER GHAIN MEDIAL FORM
- 0xFED1: 0xDF, # ARABIC LETTER FEH ISOLATED FORM
- 0xFED3: 0xE0, # ARABIC LETTER FEH INITIAL FORM
- 0xFED5: 0xE1, # ARABIC LETTER QAF ISOLATED FORM
- 0xFED7: 0xE2, # ARABIC LETTER QAF INITIAL FORM
- 0xFED9: 0xE3, # ARABIC LETTER KAF ISOLATED FORM
- 0xFEDB: 0xE4, # ARABIC LETTER KAF INITIAL FORM
- 0xFEDD: 0xE7, # ARABIC LETTER LAM ISOLATED FORM
- 0xFEDF: 0xE8, # ARABIC LETTER LAM INITIAL FORM
- 0xFEE0: 0xE9, # ARABIC LETTER LAM MEDIAL FORM
- 0xFEE1: 0xEA, # ARABIC LETTER MEEM ISOLATED FORM
- 0xFEE3: 0xEB, # ARABIC LETTER MEEM INITIAL FORM
- 0xFEE5: 0xED, # ARABIC LETTER NOON ISOLATED FORM
- 0xFEE7: 0xEE, # ARABIC LETTER NOON INITIAL FORM
- 0xFEED: 0xF0, # ARABIC LETTER WAW ISOLATED FORM
- 0xFEF1: 0xF9, # ARABIC LETTER YEH ISOLATED FORM
- 0xFEF2: 0xFA, # ARABIC LETTER YEH FINAL FORM
- 0xFEF3: 0xFB, # ARABIC LETTER YEH INITIAL FORM
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/cp1026.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/cp1026.py (original)
+++ python/branches/p3yk/Lib/encodings/cp1026.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\x9f' # 0xFF -> CONTROL
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x37, # END OF TRANSMISSION
- 0x0005: 0x2D, # ENQUIRY
- 0x0006: 0x2E, # ACKNOWLEDGE
- 0x0007: 0x2F, # BELL
- 0x0008: 0x16, # BACKSPACE
- 0x0009: 0x05, # HORIZONTAL TABULATION
- 0x000A: 0x25, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x3C, # DEVICE CONTROL FOUR
- 0x0015: 0x3D, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x32, # SYNCHRONOUS IDLE
- 0x0017: 0x26, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x3F, # SUBSTITUTE
- 0x001B: 0x27, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x40, # SPACE
- 0x0021: 0x4F, # EXCLAMATION MARK
- 0x0022: 0xFC, # QUOTATION MARK
- 0x0023: 0xEC, # NUMBER SIGN
- 0x0024: 0xAD, # DOLLAR SIGN
- 0x0025: 0x6C, # PERCENT SIGN
- 0x0026: 0x50, # AMPERSAND
- 0x0027: 0x7D, # APOSTROPHE
- 0x0028: 0x4D, # LEFT PARENTHESIS
- 0x0029: 0x5D, # RIGHT PARENTHESIS
- 0x002A: 0x5C, # ASTERISK
- 0x002B: 0x4E, # PLUS SIGN
- 0x002C: 0x6B, # COMMA
- 0x002D: 0x60, # HYPHEN-MINUS
- 0x002E: 0x4B, # FULL STOP
- 0x002F: 0x61, # SOLIDUS
- 0x0030: 0xF0, # DIGIT ZERO
- 0x0031: 0xF1, # DIGIT ONE
- 0x0032: 0xF2, # DIGIT TWO
- 0x0033: 0xF3, # DIGIT THREE
- 0x0034: 0xF4, # DIGIT FOUR
- 0x0035: 0xF5, # DIGIT FIVE
- 0x0036: 0xF6, # DIGIT SIX
- 0x0037: 0xF7, # DIGIT SEVEN
- 0x0038: 0xF8, # DIGIT EIGHT
- 0x0039: 0xF9, # DIGIT NINE
- 0x003A: 0x7A, # COLON
- 0x003B: 0x5E, # SEMICOLON
- 0x003C: 0x4C, # LESS-THAN SIGN
- 0x003D: 0x7E, # EQUALS SIGN
- 0x003E: 0x6E, # GREATER-THAN SIGN
- 0x003F: 0x6F, # QUESTION MARK
- 0x0040: 0xAE, # COMMERCIAL AT
- 0x0041: 0xC1, # LATIN CAPITAL LETTER A
- 0x0042: 0xC2, # LATIN CAPITAL LETTER B
- 0x0043: 0xC3, # LATIN CAPITAL LETTER C
- 0x0044: 0xC4, # LATIN CAPITAL LETTER D
- 0x0045: 0xC5, # LATIN CAPITAL LETTER E
- 0x0046: 0xC6, # LATIN CAPITAL LETTER F
- 0x0047: 0xC7, # LATIN CAPITAL LETTER G
- 0x0048: 0xC8, # LATIN CAPITAL LETTER H
- 0x0049: 0xC9, # LATIN CAPITAL LETTER I
- 0x004A: 0xD1, # LATIN CAPITAL LETTER J
- 0x004B: 0xD2, # LATIN CAPITAL LETTER K
- 0x004C: 0xD3, # LATIN CAPITAL LETTER L
- 0x004D: 0xD4, # LATIN CAPITAL LETTER M
- 0x004E: 0xD5, # LATIN CAPITAL LETTER N
- 0x004F: 0xD6, # LATIN CAPITAL LETTER O
- 0x0050: 0xD7, # LATIN CAPITAL LETTER P
- 0x0051: 0xD8, # LATIN CAPITAL LETTER Q
- 0x0052: 0xD9, # LATIN CAPITAL LETTER R
- 0x0053: 0xE2, # LATIN CAPITAL LETTER S
- 0x0054: 0xE3, # LATIN CAPITAL LETTER T
- 0x0055: 0xE4, # LATIN CAPITAL LETTER U
- 0x0056: 0xE5, # LATIN CAPITAL LETTER V
- 0x0057: 0xE6, # LATIN CAPITAL LETTER W
- 0x0058: 0xE7, # LATIN CAPITAL LETTER X
- 0x0059: 0xE8, # LATIN CAPITAL LETTER Y
- 0x005A: 0xE9, # LATIN CAPITAL LETTER Z
- 0x005B: 0x68, # LEFT SQUARE BRACKET
- 0x005C: 0xDC, # REVERSE SOLIDUS
- 0x005D: 0xAC, # RIGHT SQUARE BRACKET
- 0x005E: 0x5F, # CIRCUMFLEX ACCENT
- 0x005F: 0x6D, # LOW LINE
- 0x0060: 0x8D, # GRAVE ACCENT
- 0x0061: 0x81, # LATIN SMALL LETTER A
- 0x0062: 0x82, # LATIN SMALL LETTER B
- 0x0063: 0x83, # LATIN SMALL LETTER C
- 0x0064: 0x84, # LATIN SMALL LETTER D
- 0x0065: 0x85, # LATIN SMALL LETTER E
- 0x0066: 0x86, # LATIN SMALL LETTER F
- 0x0067: 0x87, # LATIN SMALL LETTER G
- 0x0068: 0x88, # LATIN SMALL LETTER H
- 0x0069: 0x89, # LATIN SMALL LETTER I
- 0x006A: 0x91, # LATIN SMALL LETTER J
- 0x006B: 0x92, # LATIN SMALL LETTER K
- 0x006C: 0x93, # LATIN SMALL LETTER L
- 0x006D: 0x94, # LATIN SMALL LETTER M
- 0x006E: 0x95, # LATIN SMALL LETTER N
- 0x006F: 0x96, # LATIN SMALL LETTER O
- 0x0070: 0x97, # LATIN SMALL LETTER P
- 0x0071: 0x98, # LATIN SMALL LETTER Q
- 0x0072: 0x99, # LATIN SMALL LETTER R
- 0x0073: 0xA2, # LATIN SMALL LETTER S
- 0x0074: 0xA3, # LATIN SMALL LETTER T
- 0x0075: 0xA4, # LATIN SMALL LETTER U
- 0x0076: 0xA5, # LATIN SMALL LETTER V
- 0x0077: 0xA6, # LATIN SMALL LETTER W
- 0x0078: 0xA7, # LATIN SMALL LETTER X
- 0x0079: 0xA8, # LATIN SMALL LETTER Y
- 0x007A: 0xA9, # LATIN SMALL LETTER Z
- 0x007B: 0x48, # LEFT CURLY BRACKET
- 0x007C: 0xBB, # VERTICAL LINE
- 0x007D: 0x8C, # RIGHT CURLY BRACKET
- 0x007E: 0xCC, # TILDE
- 0x007F: 0x07, # DELETE
- 0x0080: 0x20, # CONTROL
- 0x0081: 0x21, # CONTROL
- 0x0082: 0x22, # CONTROL
- 0x0083: 0x23, # CONTROL
- 0x0084: 0x24, # CONTROL
- 0x0085: 0x15, # CONTROL
- 0x0086: 0x06, # CONTROL
- 0x0087: 0x17, # CONTROL
- 0x0088: 0x28, # CONTROL
- 0x0089: 0x29, # CONTROL
- 0x008A: 0x2A, # CONTROL
- 0x008B: 0x2B, # CONTROL
- 0x008C: 0x2C, # CONTROL
- 0x008D: 0x09, # CONTROL
- 0x008E: 0x0A, # CONTROL
- 0x008F: 0x1B, # CONTROL
- 0x0090: 0x30, # CONTROL
- 0x0091: 0x31, # CONTROL
- 0x0092: 0x1A, # CONTROL
- 0x0093: 0x33, # CONTROL
- 0x0094: 0x34, # CONTROL
- 0x0095: 0x35, # CONTROL
- 0x0096: 0x36, # CONTROL
- 0x0097: 0x08, # CONTROL
- 0x0098: 0x38, # CONTROL
- 0x0099: 0x39, # CONTROL
- 0x009A: 0x3A, # CONTROL
- 0x009B: 0x3B, # CONTROL
- 0x009C: 0x04, # CONTROL
- 0x009D: 0x14, # CONTROL
- 0x009E: 0x3E, # CONTROL
- 0x009F: 0xFF, # CONTROL
- 0x00A0: 0x41, # NO-BREAK SPACE
- 0x00A1: 0xAA, # INVERTED EXCLAMATION MARK
- 0x00A2: 0xB0, # CENT SIGN
- 0x00A3: 0xB1, # POUND SIGN
- 0x00A4: 0x9F, # CURRENCY SIGN
- 0x00A5: 0xB2, # YEN SIGN
- 0x00A6: 0x8E, # BROKEN BAR
- 0x00A7: 0xB5, # SECTION SIGN
- 0x00A8: 0xBD, # DIAERESIS
- 0x00A9: 0xB4, # COPYRIGHT SIGN
- 0x00AA: 0x9A, # FEMININE ORDINAL INDICATOR
- 0x00AB: 0x8A, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xBA, # NOT SIGN
- 0x00AD: 0xCA, # SOFT HYPHEN
- 0x00AE: 0xAF, # REGISTERED SIGN
- 0x00AF: 0xBC, # MACRON
- 0x00B0: 0x90, # DEGREE SIGN
- 0x00B1: 0x8F, # PLUS-MINUS SIGN
- 0x00B2: 0xEA, # SUPERSCRIPT TWO
- 0x00B3: 0xFA, # SUPERSCRIPT THREE
- 0x00B4: 0xBE, # ACUTE ACCENT
- 0x00B5: 0xA0, # MICRO SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00B7: 0xB3, # MIDDLE DOT
- 0x00B8: 0x9D, # CEDILLA
- 0x00B9: 0xDA, # SUPERSCRIPT ONE
- 0x00BA: 0x9B, # MASCULINE ORDINAL INDICATOR
- 0x00BB: 0x8B, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BC: 0xB7, # VULGAR FRACTION ONE QUARTER
- 0x00BD: 0xB8, # VULGAR FRACTION ONE HALF
- 0x00BE: 0xB9, # VULGAR FRACTION THREE QUARTERS
- 0x00BF: 0xAB, # INVERTED QUESTION MARK
- 0x00C0: 0x64, # LATIN CAPITAL LETTER A WITH GRAVE
- 0x00C1: 0x65, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0x62, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C3: 0x66, # LATIN CAPITAL LETTER A WITH TILDE
- 0x00C4: 0x63, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C5: 0x67, # LATIN CAPITAL LETTER A WITH RING ABOVE
- 0x00C6: 0x9E, # LATIN CAPITAL LIGATURE AE
- 0x00C7: 0x4A, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C8: 0x74, # LATIN CAPITAL LETTER E WITH GRAVE
- 0x00C9: 0x71, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CA: 0x72, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
- 0x00CB: 0x73, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CC: 0x78, # LATIN CAPITAL LETTER I WITH GRAVE
- 0x00CD: 0x75, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0x76, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00CF: 0x77, # LATIN CAPITAL LETTER I WITH DIAERESIS
- 0x00D1: 0x69, # LATIN CAPITAL LETTER N WITH TILDE
- 0x00D2: 0xED, # LATIN CAPITAL LETTER O WITH GRAVE
- 0x00D3: 0xEE, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xEB, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D5: 0xEF, # LATIN CAPITAL LETTER O WITH TILDE
- 0x00D6: 0x7B, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D7: 0xBF, # MULTIPLICATION SIGN
- 0x00D8: 0x80, # LATIN CAPITAL LETTER O WITH STROKE
- 0x00D9: 0xFD, # LATIN CAPITAL LETTER U WITH GRAVE
- 0x00DA: 0xFE, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DB: 0xFB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
- 0x00DC: 0x7F, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DF: 0x59, # LATIN SMALL LETTER SHARP S (GERMAN)
- 0x00E0: 0x44, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E1: 0x45, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0x42, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E3: 0x46, # LATIN SMALL LETTER A WITH TILDE
- 0x00E4: 0x43, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E5: 0x47, # LATIN SMALL LETTER A WITH RING ABOVE
- 0x00E6: 0x9C, # LATIN SMALL LIGATURE AE
- 0x00E7: 0xC0, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0x54, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0x51, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0x52, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0x53, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00EC: 0x58, # LATIN SMALL LETTER I WITH GRAVE
- 0x00ED: 0x55, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0x56, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0x57, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F1: 0x49, # LATIN SMALL LETTER N WITH TILDE
- 0x00F2: 0xCD, # LATIN SMALL LETTER O WITH GRAVE
- 0x00F3: 0xCE, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0xCB, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F5: 0xCF, # LATIN SMALL LETTER O WITH TILDE
- 0x00F6: 0xA1, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xE1, # DIVISION SIGN
- 0x00F8: 0x70, # LATIN SMALL LETTER O WITH STROKE
- 0x00F9: 0xDD, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FA: 0xDE, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0xDB, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0xE0, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x00FF: 0xDF, # LATIN SMALL LETTER Y WITH DIAERESIS
- 0x011E: 0x5A, # LATIN CAPITAL LETTER G WITH BREVE
- 0x011F: 0xD0, # LATIN SMALL LETTER G WITH BREVE
- 0x0130: 0x5B, # LATIN CAPITAL LETTER I WITH DOT ABOVE
- 0x0131: 0x79, # LATIN SMALL LETTER DOTLESS I
- 0x015E: 0x7C, # LATIN CAPITAL LETTER S WITH CEDILLA
- 0x015F: 0x6A, # LATIN SMALL LETTER S WITH CEDILLA
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/cp1140.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/cp1140.py (original)
+++ python/branches/p3yk/Lib/encodings/cp1140.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\x9f' # 0xFF -> CONTROL
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x37, # END OF TRANSMISSION
- 0x0005: 0x2D, # ENQUIRY
- 0x0006: 0x2E, # ACKNOWLEDGE
- 0x0007: 0x2F, # BELL
- 0x0008: 0x16, # BACKSPACE
- 0x0009: 0x05, # HORIZONTAL TABULATION
- 0x000A: 0x25, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x3C, # DEVICE CONTROL FOUR
- 0x0015: 0x3D, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x32, # SYNCHRONOUS IDLE
- 0x0017: 0x26, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x3F, # SUBSTITUTE
- 0x001B: 0x27, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x40, # SPACE
- 0x0021: 0x5A, # EXCLAMATION MARK
- 0x0022: 0x7F, # QUOTATION MARK
- 0x0023: 0x7B, # NUMBER SIGN
- 0x0024: 0x5B, # DOLLAR SIGN
- 0x0025: 0x6C, # PERCENT SIGN
- 0x0026: 0x50, # AMPERSAND
- 0x0027: 0x7D, # APOSTROPHE
- 0x0028: 0x4D, # LEFT PARENTHESIS
- 0x0029: 0x5D, # RIGHT PARENTHESIS
- 0x002A: 0x5C, # ASTERISK
- 0x002B: 0x4E, # PLUS SIGN
- 0x002C: 0x6B, # COMMA
- 0x002D: 0x60, # HYPHEN-MINUS
- 0x002E: 0x4B, # FULL STOP
- 0x002F: 0x61, # SOLIDUS
- 0x0030: 0xF0, # DIGIT ZERO
- 0x0031: 0xF1, # DIGIT ONE
- 0x0032: 0xF2, # DIGIT TWO
- 0x0033: 0xF3, # DIGIT THREE
- 0x0034: 0xF4, # DIGIT FOUR
- 0x0035: 0xF5, # DIGIT FIVE
- 0x0036: 0xF6, # DIGIT SIX
- 0x0037: 0xF7, # DIGIT SEVEN
- 0x0038: 0xF8, # DIGIT EIGHT
- 0x0039: 0xF9, # DIGIT NINE
- 0x003A: 0x7A, # COLON
- 0x003B: 0x5E, # SEMICOLON
- 0x003C: 0x4C, # LESS-THAN SIGN
- 0x003D: 0x7E, # EQUALS SIGN
- 0x003E: 0x6E, # GREATER-THAN SIGN
- 0x003F: 0x6F, # QUESTION MARK
- 0x0040: 0x7C, # COMMERCIAL AT
- 0x0041: 0xC1, # LATIN CAPITAL LETTER A
- 0x0042: 0xC2, # LATIN CAPITAL LETTER B
- 0x0043: 0xC3, # LATIN CAPITAL LETTER C
- 0x0044: 0xC4, # LATIN CAPITAL LETTER D
- 0x0045: 0xC5, # LATIN CAPITAL LETTER E
- 0x0046: 0xC6, # LATIN CAPITAL LETTER F
- 0x0047: 0xC7, # LATIN CAPITAL LETTER G
- 0x0048: 0xC8, # LATIN CAPITAL LETTER H
- 0x0049: 0xC9, # LATIN CAPITAL LETTER I
- 0x004A: 0xD1, # LATIN CAPITAL LETTER J
- 0x004B: 0xD2, # LATIN CAPITAL LETTER K
- 0x004C: 0xD3, # LATIN CAPITAL LETTER L
- 0x004D: 0xD4, # LATIN CAPITAL LETTER M
- 0x004E: 0xD5, # LATIN CAPITAL LETTER N
- 0x004F: 0xD6, # LATIN CAPITAL LETTER O
- 0x0050: 0xD7, # LATIN CAPITAL LETTER P
- 0x0051: 0xD8, # LATIN CAPITAL LETTER Q
- 0x0052: 0xD9, # LATIN CAPITAL LETTER R
- 0x0053: 0xE2, # LATIN CAPITAL LETTER S
- 0x0054: 0xE3, # LATIN CAPITAL LETTER T
- 0x0055: 0xE4, # LATIN CAPITAL LETTER U
- 0x0056: 0xE5, # LATIN CAPITAL LETTER V
- 0x0057: 0xE6, # LATIN CAPITAL LETTER W
- 0x0058: 0xE7, # LATIN CAPITAL LETTER X
- 0x0059: 0xE8, # LATIN CAPITAL LETTER Y
- 0x005A: 0xE9, # LATIN CAPITAL LETTER Z
- 0x005B: 0xBA, # LEFT SQUARE BRACKET
- 0x005C: 0xE0, # REVERSE SOLIDUS
- 0x005D: 0xBB, # RIGHT SQUARE BRACKET
- 0x005E: 0xB0, # CIRCUMFLEX ACCENT
- 0x005F: 0x6D, # LOW LINE
- 0x0060: 0x79, # GRAVE ACCENT
- 0x0061: 0x81, # LATIN SMALL LETTER A
- 0x0062: 0x82, # LATIN SMALL LETTER B
- 0x0063: 0x83, # LATIN SMALL LETTER C
- 0x0064: 0x84, # LATIN SMALL LETTER D
- 0x0065: 0x85, # LATIN SMALL LETTER E
- 0x0066: 0x86, # LATIN SMALL LETTER F
- 0x0067: 0x87, # LATIN SMALL LETTER G
- 0x0068: 0x88, # LATIN SMALL LETTER H
- 0x0069: 0x89, # LATIN SMALL LETTER I
- 0x006A: 0x91, # LATIN SMALL LETTER J
- 0x006B: 0x92, # LATIN SMALL LETTER K
- 0x006C: 0x93, # LATIN SMALL LETTER L
- 0x006D: 0x94, # LATIN SMALL LETTER M
- 0x006E: 0x95, # LATIN SMALL LETTER N
- 0x006F: 0x96, # LATIN SMALL LETTER O
- 0x0070: 0x97, # LATIN SMALL LETTER P
- 0x0071: 0x98, # LATIN SMALL LETTER Q
- 0x0072: 0x99, # LATIN SMALL LETTER R
- 0x0073: 0xA2, # LATIN SMALL LETTER S
- 0x0074: 0xA3, # LATIN SMALL LETTER T
- 0x0075: 0xA4, # LATIN SMALL LETTER U
- 0x0076: 0xA5, # LATIN SMALL LETTER V
- 0x0077: 0xA6, # LATIN SMALL LETTER W
- 0x0078: 0xA7, # LATIN SMALL LETTER X
- 0x0079: 0xA8, # LATIN SMALL LETTER Y
- 0x007A: 0xA9, # LATIN SMALL LETTER Z
- 0x007B: 0xC0, # LEFT CURLY BRACKET
- 0x007C: 0x4F, # VERTICAL LINE
- 0x007D: 0xD0, # RIGHT CURLY BRACKET
- 0x007E: 0xA1, # TILDE
- 0x007F: 0x07, # DELETE
- 0x0080: 0x20, # CONTROL
- 0x0081: 0x21, # CONTROL
- 0x0082: 0x22, # CONTROL
- 0x0083: 0x23, # CONTROL
- 0x0084: 0x24, # CONTROL
- 0x0085: 0x15, # CONTROL
- 0x0086: 0x06, # CONTROL
- 0x0087: 0x17, # CONTROL
- 0x0088: 0x28, # CONTROL
- 0x0089: 0x29, # CONTROL
- 0x008A: 0x2A, # CONTROL
- 0x008B: 0x2B, # CONTROL
- 0x008C: 0x2C, # CONTROL
- 0x008D: 0x09, # CONTROL
- 0x008E: 0x0A, # CONTROL
- 0x008F: 0x1B, # CONTROL
- 0x0090: 0x30, # CONTROL
- 0x0091: 0x31, # CONTROL
- 0x0092: 0x1A, # CONTROL
- 0x0093: 0x33, # CONTROL
- 0x0094: 0x34, # CONTROL
- 0x0095: 0x35, # CONTROL
- 0x0096: 0x36, # CONTROL
- 0x0097: 0x08, # CONTROL
- 0x0098: 0x38, # CONTROL
- 0x0099: 0x39, # CONTROL
- 0x009A: 0x3A, # CONTROL
- 0x009B: 0x3B, # CONTROL
- 0x009C: 0x04, # CONTROL
- 0x009D: 0x14, # CONTROL
- 0x009E: 0x3E, # CONTROL
- 0x009F: 0xFF, # CONTROL
- 0x00A0: 0x41, # NO-BREAK SPACE
- 0x00A1: 0xAA, # INVERTED EXCLAMATION MARK
- 0x00A2: 0x4A, # CENT SIGN
- 0x00A3: 0xB1, # POUND SIGN
- 0x00A5: 0xB2, # YEN SIGN
- 0x00A6: 0x6A, # BROKEN BAR
- 0x00A7: 0xB5, # SECTION SIGN
- 0x00A8: 0xBD, # DIAERESIS
- 0x00A9: 0xB4, # COPYRIGHT SIGN
- 0x00AA: 0x9A, # FEMININE ORDINAL INDICATOR
- 0x00AB: 0x8A, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0x5F, # NOT SIGN
- 0x00AD: 0xCA, # SOFT HYPHEN
- 0x00AE: 0xAF, # REGISTERED SIGN
- 0x00AF: 0xBC, # MACRON
- 0x00B0: 0x90, # DEGREE SIGN
- 0x00B1: 0x8F, # PLUS-MINUS SIGN
- 0x00B2: 0xEA, # SUPERSCRIPT TWO
- 0x00B3: 0xFA, # SUPERSCRIPT THREE
- 0x00B4: 0xBE, # ACUTE ACCENT
- 0x00B5: 0xA0, # MICRO SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00B7: 0xB3, # MIDDLE DOT
- 0x00B8: 0x9D, # CEDILLA
- 0x00B9: 0xDA, # SUPERSCRIPT ONE
- 0x00BA: 0x9B, # MASCULINE ORDINAL INDICATOR
- 0x00BB: 0x8B, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BC: 0xB7, # VULGAR FRACTION ONE QUARTER
- 0x00BD: 0xB8, # VULGAR FRACTION ONE HALF
- 0x00BE: 0xB9, # VULGAR FRACTION THREE QUARTERS
- 0x00BF: 0xAB, # INVERTED QUESTION MARK
- 0x00C0: 0x64, # LATIN CAPITAL LETTER A WITH GRAVE
- 0x00C1: 0x65, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0x62, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C3: 0x66, # LATIN CAPITAL LETTER A WITH TILDE
- 0x00C4: 0x63, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C5: 0x67, # LATIN CAPITAL LETTER A WITH RING ABOVE
- 0x00C6: 0x9E, # LATIN CAPITAL LIGATURE AE
- 0x00C7: 0x68, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C8: 0x74, # LATIN CAPITAL LETTER E WITH GRAVE
- 0x00C9: 0x71, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CA: 0x72, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
- 0x00CB: 0x73, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CC: 0x78, # LATIN CAPITAL LETTER I WITH GRAVE
- 0x00CD: 0x75, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0x76, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00CF: 0x77, # LATIN CAPITAL LETTER I WITH DIAERESIS
- 0x00D0: 0xAC, # LATIN CAPITAL LETTER ETH (ICELANDIC)
- 0x00D1: 0x69, # LATIN CAPITAL LETTER N WITH TILDE
- 0x00D2: 0xED, # LATIN CAPITAL LETTER O WITH GRAVE
- 0x00D3: 0xEE, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xEB, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D5: 0xEF, # LATIN CAPITAL LETTER O WITH TILDE
- 0x00D6: 0xEC, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D7: 0xBF, # MULTIPLICATION SIGN
- 0x00D8: 0x80, # LATIN CAPITAL LETTER O WITH STROKE
- 0x00D9: 0xFD, # LATIN CAPITAL LETTER U WITH GRAVE
- 0x00DA: 0xFE, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DB: 0xFB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
- 0x00DC: 0xFC, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DD: 0xAD, # LATIN CAPITAL LETTER Y WITH ACUTE
- 0x00DE: 0xAE, # LATIN CAPITAL LETTER THORN (ICELANDIC)
- 0x00DF: 0x59, # LATIN SMALL LETTER SHARP S (GERMAN)
- 0x00E0: 0x44, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E1: 0x45, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0x42, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E3: 0x46, # LATIN SMALL LETTER A WITH TILDE
- 0x00E4: 0x43, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E5: 0x47, # LATIN SMALL LETTER A WITH RING ABOVE
- 0x00E6: 0x9C, # LATIN SMALL LIGATURE AE
- 0x00E7: 0x48, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0x54, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0x51, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0x52, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0x53, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00EC: 0x58, # LATIN SMALL LETTER I WITH GRAVE
- 0x00ED: 0x55, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0x56, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0x57, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F0: 0x8C, # LATIN SMALL LETTER ETH (ICELANDIC)
- 0x00F1: 0x49, # LATIN SMALL LETTER N WITH TILDE
- 0x00F2: 0xCD, # LATIN SMALL LETTER O WITH GRAVE
- 0x00F3: 0xCE, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0xCB, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F5: 0xCF, # LATIN SMALL LETTER O WITH TILDE
- 0x00F6: 0xCC, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xE1, # DIVISION SIGN
- 0x00F8: 0x70, # LATIN SMALL LETTER O WITH STROKE
- 0x00F9: 0xDD, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FA: 0xDE, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0xDB, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0xDC, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x00FD: 0x8D, # LATIN SMALL LETTER Y WITH ACUTE
- 0x00FE: 0x8E, # LATIN SMALL LETTER THORN (ICELANDIC)
- 0x00FF: 0xDF, # LATIN SMALL LETTER Y WITH DIAERESIS
- 0x20AC: 0x9F, # EURO SIGN
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/cp1250.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/cp1250.py (original)
+++ python/branches/p3yk/Lib/encodings/cp1250.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,258 +303,5 @@
u'\u02d9' # 0xFF -> DOT ABOVE
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A4: 0xA4, # CURRENCY SIGN
- 0x00A6: 0xA6, # BROKEN BAR
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00A8: 0xA8, # DIAERESIS
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xAC, # NOT SIGN
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00AE: 0xAE, # REGISTERED SIGN
- 0x00B0: 0xB0, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B4: 0xB4, # ACUTE ACCENT
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00B7: 0xB7, # MIDDLE DOT
- 0x00B8: 0xB8, # CEDILLA
- 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D7: 0xD7, # MULTIPLICATION SIGN
- 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DD: 0xDD, # LATIN CAPITAL LETTER Y WITH ACUTE
- 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S
- 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xF7, # DIVISION SIGN
- 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x00FD: 0xFD, # LATIN SMALL LETTER Y WITH ACUTE
- 0x0102: 0xC3, # LATIN CAPITAL LETTER A WITH BREVE
- 0x0103: 0xE3, # LATIN SMALL LETTER A WITH BREVE
- 0x0104: 0xA5, # LATIN CAPITAL LETTER A WITH OGONEK
- 0x0105: 0xB9, # LATIN SMALL LETTER A WITH OGONEK
- 0x0106: 0xC6, # LATIN CAPITAL LETTER C WITH ACUTE
- 0x0107: 0xE6, # LATIN SMALL LETTER C WITH ACUTE
- 0x010C: 0xC8, # LATIN CAPITAL LETTER C WITH CARON
- 0x010D: 0xE8, # LATIN SMALL LETTER C WITH CARON
- 0x010E: 0xCF, # LATIN CAPITAL LETTER D WITH CARON
- 0x010F: 0xEF, # LATIN SMALL LETTER D WITH CARON
- 0x0110: 0xD0, # LATIN CAPITAL LETTER D WITH STROKE
- 0x0111: 0xF0, # LATIN SMALL LETTER D WITH STROKE
- 0x0118: 0xCA, # LATIN CAPITAL LETTER E WITH OGONEK
- 0x0119: 0xEA, # LATIN SMALL LETTER E WITH OGONEK
- 0x011A: 0xCC, # LATIN CAPITAL LETTER E WITH CARON
- 0x011B: 0xEC, # LATIN SMALL LETTER E WITH CARON
- 0x0139: 0xC5, # LATIN CAPITAL LETTER L WITH ACUTE
- 0x013A: 0xE5, # LATIN SMALL LETTER L WITH ACUTE
- 0x013D: 0xBC, # LATIN CAPITAL LETTER L WITH CARON
- 0x013E: 0xBE, # LATIN SMALL LETTER L WITH CARON
- 0x0141: 0xA3, # LATIN CAPITAL LETTER L WITH STROKE
- 0x0142: 0xB3, # LATIN SMALL LETTER L WITH STROKE
- 0x0143: 0xD1, # LATIN CAPITAL LETTER N WITH ACUTE
- 0x0144: 0xF1, # LATIN SMALL LETTER N WITH ACUTE
- 0x0147: 0xD2, # LATIN CAPITAL LETTER N WITH CARON
- 0x0148: 0xF2, # LATIN SMALL LETTER N WITH CARON
- 0x0150: 0xD5, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
- 0x0151: 0xF5, # LATIN SMALL LETTER O WITH DOUBLE ACUTE
- 0x0154: 0xC0, # LATIN CAPITAL LETTER R WITH ACUTE
- 0x0155: 0xE0, # LATIN SMALL LETTER R WITH ACUTE
- 0x0158: 0xD8, # LATIN CAPITAL LETTER R WITH CARON
- 0x0159: 0xF8, # LATIN SMALL LETTER R WITH CARON
- 0x015A: 0x8C, # LATIN CAPITAL LETTER S WITH ACUTE
- 0x015B: 0x9C, # LATIN SMALL LETTER S WITH ACUTE
- 0x015E: 0xAA, # LATIN CAPITAL LETTER S WITH CEDILLA
- 0x015F: 0xBA, # LATIN SMALL LETTER S WITH CEDILLA
- 0x0160: 0x8A, # LATIN CAPITAL LETTER S WITH CARON
- 0x0161: 0x9A, # LATIN SMALL LETTER S WITH CARON
- 0x0162: 0xDE, # LATIN CAPITAL LETTER T WITH CEDILLA
- 0x0163: 0xFE, # LATIN SMALL LETTER T WITH CEDILLA
- 0x0164: 0x8D, # LATIN CAPITAL LETTER T WITH CARON
- 0x0165: 0x9D, # LATIN SMALL LETTER T WITH CARON
- 0x016E: 0xD9, # LATIN CAPITAL LETTER U WITH RING ABOVE
- 0x016F: 0xF9, # LATIN SMALL LETTER U WITH RING ABOVE
- 0x0170: 0xDB, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
- 0x0171: 0xFB, # LATIN SMALL LETTER U WITH DOUBLE ACUTE
- 0x0179: 0x8F, # LATIN CAPITAL LETTER Z WITH ACUTE
- 0x017A: 0x9F, # LATIN SMALL LETTER Z WITH ACUTE
- 0x017B: 0xAF, # LATIN CAPITAL LETTER Z WITH DOT ABOVE
- 0x017C: 0xBF, # LATIN SMALL LETTER Z WITH DOT ABOVE
- 0x017D: 0x8E, # LATIN CAPITAL LETTER Z WITH CARON
- 0x017E: 0x9E, # LATIN SMALL LETTER Z WITH CARON
- 0x02C7: 0xA1, # CARON
- 0x02D8: 0xA2, # BREVE
- 0x02D9: 0xFF, # DOT ABOVE
- 0x02DB: 0xB2, # OGONEK
- 0x02DD: 0xBD, # DOUBLE ACUTE ACCENT
- 0x2013: 0x96, # EN DASH
- 0x2014: 0x97, # EM DASH
- 0x2018: 0x91, # LEFT SINGLE QUOTATION MARK
- 0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK
- 0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK
- 0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK
- 0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK
- 0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK
- 0x2020: 0x86, # DAGGER
- 0x2021: 0x87, # DOUBLE DAGGER
- 0x2022: 0x95, # BULLET
- 0x2026: 0x85, # HORIZONTAL ELLIPSIS
- 0x2030: 0x89, # PER MILLE SIGN
- 0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
- 0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
- 0x20AC: 0x80, # EURO SIGN
- 0x2122: 0x99, # TRADE MARK SIGN
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/cp1251.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/cp1251.py (original)
+++ python/branches/p3yk/Lib/encodings/cp1251.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,262 +303,5 @@
u'\u044f' # 0xFF -> CYRILLIC SMALL LETTER YA
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A4: 0xA4, # CURRENCY SIGN
- 0x00A6: 0xA6, # BROKEN BAR
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xAC, # NOT SIGN
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00AE: 0xAE, # REGISTERED SIGN
- 0x00B0: 0xB0, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00B7: 0xB7, # MIDDLE DOT
- 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x0401: 0xA8, # CYRILLIC CAPITAL LETTER IO
- 0x0402: 0x80, # CYRILLIC CAPITAL LETTER DJE
- 0x0403: 0x81, # CYRILLIC CAPITAL LETTER GJE
- 0x0404: 0xAA, # CYRILLIC CAPITAL LETTER UKRAINIAN IE
- 0x0405: 0xBD, # CYRILLIC CAPITAL LETTER DZE
- 0x0406: 0xB2, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
- 0x0407: 0xAF, # CYRILLIC CAPITAL LETTER YI
- 0x0408: 0xA3, # CYRILLIC CAPITAL LETTER JE
- 0x0409: 0x8A, # CYRILLIC CAPITAL LETTER LJE
- 0x040A: 0x8C, # CYRILLIC CAPITAL LETTER NJE
- 0x040B: 0x8E, # CYRILLIC CAPITAL LETTER TSHE
- 0x040C: 0x8D, # CYRILLIC CAPITAL LETTER KJE
- 0x040E: 0xA1, # CYRILLIC CAPITAL LETTER SHORT U
- 0x040F: 0x8F, # CYRILLIC CAPITAL LETTER DZHE
- 0x0410: 0xC0, # CYRILLIC CAPITAL LETTER A
- 0x0411: 0xC1, # CYRILLIC CAPITAL LETTER BE
- 0x0412: 0xC2, # CYRILLIC CAPITAL LETTER VE
- 0x0413: 0xC3, # CYRILLIC CAPITAL LETTER GHE
- 0x0414: 0xC4, # CYRILLIC CAPITAL LETTER DE
- 0x0415: 0xC5, # CYRILLIC CAPITAL LETTER IE
- 0x0416: 0xC6, # CYRILLIC CAPITAL LETTER ZHE
- 0x0417: 0xC7, # CYRILLIC CAPITAL LETTER ZE
- 0x0418: 0xC8, # CYRILLIC CAPITAL LETTER I
- 0x0419: 0xC9, # CYRILLIC CAPITAL LETTER SHORT I
- 0x041A: 0xCA, # CYRILLIC CAPITAL LETTER KA
- 0x041B: 0xCB, # CYRILLIC CAPITAL LETTER EL
- 0x041C: 0xCC, # CYRILLIC CAPITAL LETTER EM
- 0x041D: 0xCD, # CYRILLIC CAPITAL LETTER EN
- 0x041E: 0xCE, # CYRILLIC CAPITAL LETTER O
- 0x041F: 0xCF, # CYRILLIC CAPITAL LETTER PE
- 0x0420: 0xD0, # CYRILLIC CAPITAL LETTER ER
- 0x0421: 0xD1, # CYRILLIC CAPITAL LETTER ES
- 0x0422: 0xD2, # CYRILLIC CAPITAL LETTER TE
- 0x0423: 0xD3, # CYRILLIC CAPITAL LETTER U
- 0x0424: 0xD4, # CYRILLIC CAPITAL LETTER EF
- 0x0425: 0xD5, # CYRILLIC CAPITAL LETTER HA
- 0x0426: 0xD6, # CYRILLIC CAPITAL LETTER TSE
- 0x0427: 0xD7, # CYRILLIC CAPITAL LETTER CHE
- 0x0428: 0xD8, # CYRILLIC CAPITAL LETTER SHA
- 0x0429: 0xD9, # CYRILLIC CAPITAL LETTER SHCHA
- 0x042A: 0xDA, # CYRILLIC CAPITAL LETTER HARD SIGN
- 0x042B: 0xDB, # CYRILLIC CAPITAL LETTER YERU
- 0x042C: 0xDC, # CYRILLIC CAPITAL LETTER SOFT SIGN
- 0x042D: 0xDD, # CYRILLIC CAPITAL LETTER E
- 0x042E: 0xDE, # CYRILLIC CAPITAL LETTER YU
- 0x042F: 0xDF, # CYRILLIC CAPITAL LETTER YA
- 0x0430: 0xE0, # CYRILLIC SMALL LETTER A
- 0x0431: 0xE1, # CYRILLIC SMALL LETTER BE
- 0x0432: 0xE2, # CYRILLIC SMALL LETTER VE
- 0x0433: 0xE3, # CYRILLIC SMALL LETTER GHE
- 0x0434: 0xE4, # CYRILLIC SMALL LETTER DE
- 0x0435: 0xE5, # CYRILLIC SMALL LETTER IE
- 0x0436: 0xE6, # CYRILLIC SMALL LETTER ZHE
- 0x0437: 0xE7, # CYRILLIC SMALL LETTER ZE
- 0x0438: 0xE8, # CYRILLIC SMALL LETTER I
- 0x0439: 0xE9, # CYRILLIC SMALL LETTER SHORT I
- 0x043A: 0xEA, # CYRILLIC SMALL LETTER KA
- 0x043B: 0xEB, # CYRILLIC SMALL LETTER EL
- 0x043C: 0xEC, # CYRILLIC SMALL LETTER EM
- 0x043D: 0xED, # CYRILLIC SMALL LETTER EN
- 0x043E: 0xEE, # CYRILLIC SMALL LETTER O
- 0x043F: 0xEF, # CYRILLIC SMALL LETTER PE
- 0x0440: 0xF0, # CYRILLIC SMALL LETTER ER
- 0x0441: 0xF1, # CYRILLIC SMALL LETTER ES
- 0x0442: 0xF2, # CYRILLIC SMALL LETTER TE
- 0x0443: 0xF3, # CYRILLIC SMALL LETTER U
- 0x0444: 0xF4, # CYRILLIC SMALL LETTER EF
- 0x0445: 0xF5, # CYRILLIC SMALL LETTER HA
- 0x0446: 0xF6, # CYRILLIC SMALL LETTER TSE
- 0x0447: 0xF7, # CYRILLIC SMALL LETTER CHE
- 0x0448: 0xF8, # CYRILLIC SMALL LETTER SHA
- 0x0449: 0xF9, # CYRILLIC SMALL LETTER SHCHA
- 0x044A: 0xFA, # CYRILLIC SMALL LETTER HARD SIGN
- 0x044B: 0xFB, # CYRILLIC SMALL LETTER YERU
- 0x044C: 0xFC, # CYRILLIC SMALL LETTER SOFT SIGN
- 0x044D: 0xFD, # CYRILLIC SMALL LETTER E
- 0x044E: 0xFE, # CYRILLIC SMALL LETTER YU
- 0x044F: 0xFF, # CYRILLIC SMALL LETTER YA
- 0x0451: 0xB8, # CYRILLIC SMALL LETTER IO
- 0x0452: 0x90, # CYRILLIC SMALL LETTER DJE
- 0x0453: 0x83, # CYRILLIC SMALL LETTER GJE
- 0x0454: 0xBA, # CYRILLIC SMALL LETTER UKRAINIAN IE
- 0x0455: 0xBE, # CYRILLIC SMALL LETTER DZE
- 0x0456: 0xB3, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
- 0x0457: 0xBF, # CYRILLIC SMALL LETTER YI
- 0x0458: 0xBC, # CYRILLIC SMALL LETTER JE
- 0x0459: 0x9A, # CYRILLIC SMALL LETTER LJE
- 0x045A: 0x9C, # CYRILLIC SMALL LETTER NJE
- 0x045B: 0x9E, # CYRILLIC SMALL LETTER TSHE
- 0x045C: 0x9D, # CYRILLIC SMALL LETTER KJE
- 0x045E: 0xA2, # CYRILLIC SMALL LETTER SHORT U
- 0x045F: 0x9F, # CYRILLIC SMALL LETTER DZHE
- 0x0490: 0xA5, # CYRILLIC CAPITAL LETTER GHE WITH UPTURN
- 0x0491: 0xB4, # CYRILLIC SMALL LETTER GHE WITH UPTURN
- 0x2013: 0x96, # EN DASH
- 0x2014: 0x97, # EM DASH
- 0x2018: 0x91, # LEFT SINGLE QUOTATION MARK
- 0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK
- 0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK
- 0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK
- 0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK
- 0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK
- 0x2020: 0x86, # DAGGER
- 0x2021: 0x87, # DOUBLE DAGGER
- 0x2022: 0x95, # BULLET
- 0x2026: 0x85, # HORIZONTAL ELLIPSIS
- 0x2030: 0x89, # PER MILLE SIGN
- 0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
- 0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
- 0x20AC: 0x88, # EURO SIGN
- 0x2116: 0xB9, # NUMERO SIGN
- 0x2122: 0x99, # TRADE MARK SIGN
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/cp1252.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/cp1252.py (original)
+++ python/branches/p3yk/Lib/encodings/cp1252.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,258 +303,5 @@
u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A1: 0xA1, # INVERTED EXCLAMATION MARK
- 0x00A2: 0xA2, # CENT SIGN
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A4: 0xA4, # CURRENCY SIGN
- 0x00A5: 0xA5, # YEN SIGN
- 0x00A6: 0xA6, # BROKEN BAR
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00A8: 0xA8, # DIAERESIS
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AA: 0xAA, # FEMININE ORDINAL INDICATOR
- 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xAC, # NOT SIGN
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00AE: 0xAE, # REGISTERED SIGN
- 0x00AF: 0xAF, # MACRON
- 0x00B0: 0xB0, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B2: 0xB2, # SUPERSCRIPT TWO
- 0x00B3: 0xB3, # SUPERSCRIPT THREE
- 0x00B4: 0xB4, # ACUTE ACCENT
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00B7: 0xB7, # MIDDLE DOT
- 0x00B8: 0xB8, # CEDILLA
- 0x00B9: 0xB9, # SUPERSCRIPT ONE
- 0x00BA: 0xBA, # MASCULINE ORDINAL INDICATOR
- 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER
- 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF
- 0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS
- 0x00BF: 0xBF, # INVERTED QUESTION MARK
- 0x00C0: 0xC0, # LATIN CAPITAL LETTER A WITH GRAVE
- 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C3: 0xC3, # LATIN CAPITAL LETTER A WITH TILDE
- 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE
- 0x00C6: 0xC6, # LATIN CAPITAL LETTER AE
- 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C8: 0xC8, # LATIN CAPITAL LETTER E WITH GRAVE
- 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CA: 0xCA, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
- 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CC: 0xCC, # LATIN CAPITAL LETTER I WITH GRAVE
- 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS
- 0x00D0: 0xD0, # LATIN CAPITAL LETTER ETH
- 0x00D1: 0xD1, # LATIN CAPITAL LETTER N WITH TILDE
- 0x00D2: 0xD2, # LATIN CAPITAL LETTER O WITH GRAVE
- 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE
- 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D7: 0xD7, # MULTIPLICATION SIGN
- 0x00D8: 0xD8, # LATIN CAPITAL LETTER O WITH STROKE
- 0x00D9: 0xD9, # LATIN CAPITAL LETTER U WITH GRAVE
- 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
- 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DD: 0xDD, # LATIN CAPITAL LETTER Y WITH ACUTE
- 0x00DE: 0xDE, # LATIN CAPITAL LETTER THORN
- 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S
- 0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E3: 0xE3, # LATIN SMALL LETTER A WITH TILDE
- 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE
- 0x00E6: 0xE6, # LATIN SMALL LETTER AE
- 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00EC: 0xEC, # LATIN SMALL LETTER I WITH GRAVE
- 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F0: 0xF0, # LATIN SMALL LETTER ETH
- 0x00F1: 0xF1, # LATIN SMALL LETTER N WITH TILDE
- 0x00F2: 0xF2, # LATIN SMALL LETTER O WITH GRAVE
- 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE
- 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xF7, # DIVISION SIGN
- 0x00F8: 0xF8, # LATIN SMALL LETTER O WITH STROKE
- 0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x00FD: 0xFD, # LATIN SMALL LETTER Y WITH ACUTE
- 0x00FE: 0xFE, # LATIN SMALL LETTER THORN
- 0x00FF: 0xFF, # LATIN SMALL LETTER Y WITH DIAERESIS
- 0x0152: 0x8C, # LATIN CAPITAL LIGATURE OE
- 0x0153: 0x9C, # LATIN SMALL LIGATURE OE
- 0x0160: 0x8A, # LATIN CAPITAL LETTER S WITH CARON
- 0x0161: 0x9A, # LATIN SMALL LETTER S WITH CARON
- 0x0178: 0x9F, # LATIN CAPITAL LETTER Y WITH DIAERESIS
- 0x017D: 0x8E, # LATIN CAPITAL LETTER Z WITH CARON
- 0x017E: 0x9E, # LATIN SMALL LETTER Z WITH CARON
- 0x0192: 0x83, # LATIN SMALL LETTER F WITH HOOK
- 0x02C6: 0x88, # MODIFIER LETTER CIRCUMFLEX ACCENT
- 0x02DC: 0x98, # SMALL TILDE
- 0x2013: 0x96, # EN DASH
- 0x2014: 0x97, # EM DASH
- 0x2018: 0x91, # LEFT SINGLE QUOTATION MARK
- 0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK
- 0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK
- 0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK
- 0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK
- 0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK
- 0x2020: 0x86, # DAGGER
- 0x2021: 0x87, # DOUBLE DAGGER
- 0x2022: 0x95, # BULLET
- 0x2026: 0x85, # HORIZONTAL ELLIPSIS
- 0x2030: 0x89, # PER MILLE SIGN
- 0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
- 0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
- 0x20AC: 0x80, # EURO SIGN
- 0x2122: 0x99, # TRADE MARK SIGN
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/cp1253.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/cp1253.py (original)
+++ python/branches/p3yk/Lib/encodings/cp1253.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,246 +303,5 @@
u'\ufffe' # 0xFF -> UNDEFINED
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A4: 0xA4, # CURRENCY SIGN
- 0x00A5: 0xA5, # YEN SIGN
- 0x00A6: 0xA6, # BROKEN BAR
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00A8: 0xA8, # DIAERESIS
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xAC, # NOT SIGN
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00AE: 0xAE, # REGISTERED SIGN
- 0x00B0: 0xB0, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B2: 0xB2, # SUPERSCRIPT TWO
- 0x00B3: 0xB3, # SUPERSCRIPT THREE
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00B7: 0xB7, # MIDDLE DOT
- 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF
- 0x0192: 0x83, # LATIN SMALL LETTER F WITH HOOK
- 0x0384: 0xB4, # GREEK TONOS
- 0x0385: 0xA1, # GREEK DIALYTIKA TONOS
- 0x0386: 0xA2, # GREEK CAPITAL LETTER ALPHA WITH TONOS
- 0x0388: 0xB8, # GREEK CAPITAL LETTER EPSILON WITH TONOS
- 0x0389: 0xB9, # GREEK CAPITAL LETTER ETA WITH TONOS
- 0x038A: 0xBA, # GREEK CAPITAL LETTER IOTA WITH TONOS
- 0x038C: 0xBC, # GREEK CAPITAL LETTER OMICRON WITH TONOS
- 0x038E: 0xBE, # GREEK CAPITAL LETTER UPSILON WITH TONOS
- 0x038F: 0xBF, # GREEK CAPITAL LETTER OMEGA WITH TONOS
- 0x0390: 0xC0, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
- 0x0391: 0xC1, # GREEK CAPITAL LETTER ALPHA
- 0x0392: 0xC2, # GREEK CAPITAL LETTER BETA
- 0x0393: 0xC3, # GREEK CAPITAL LETTER GAMMA
- 0x0394: 0xC4, # GREEK CAPITAL LETTER DELTA
- 0x0395: 0xC5, # GREEK CAPITAL LETTER EPSILON
- 0x0396: 0xC6, # GREEK CAPITAL LETTER ZETA
- 0x0397: 0xC7, # GREEK CAPITAL LETTER ETA
- 0x0398: 0xC8, # GREEK CAPITAL LETTER THETA
- 0x0399: 0xC9, # GREEK CAPITAL LETTER IOTA
- 0x039A: 0xCA, # GREEK CAPITAL LETTER KAPPA
- 0x039B: 0xCB, # GREEK CAPITAL LETTER LAMDA
- 0x039C: 0xCC, # GREEK CAPITAL LETTER MU
- 0x039D: 0xCD, # GREEK CAPITAL LETTER NU
- 0x039E: 0xCE, # GREEK CAPITAL LETTER XI
- 0x039F: 0xCF, # GREEK CAPITAL LETTER OMICRON
- 0x03A0: 0xD0, # GREEK CAPITAL LETTER PI
- 0x03A1: 0xD1, # GREEK CAPITAL LETTER RHO
- 0x03A3: 0xD3, # GREEK CAPITAL LETTER SIGMA
- 0x03A4: 0xD4, # GREEK CAPITAL LETTER TAU
- 0x03A5: 0xD5, # GREEK CAPITAL LETTER UPSILON
- 0x03A6: 0xD6, # GREEK CAPITAL LETTER PHI
- 0x03A7: 0xD7, # GREEK CAPITAL LETTER CHI
- 0x03A8: 0xD8, # GREEK CAPITAL LETTER PSI
- 0x03A9: 0xD9, # GREEK CAPITAL LETTER OMEGA
- 0x03AA: 0xDA, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
- 0x03AB: 0xDB, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
- 0x03AC: 0xDC, # GREEK SMALL LETTER ALPHA WITH TONOS
- 0x03AD: 0xDD, # GREEK SMALL LETTER EPSILON WITH TONOS
- 0x03AE: 0xDE, # GREEK SMALL LETTER ETA WITH TONOS
- 0x03AF: 0xDF, # GREEK SMALL LETTER IOTA WITH TONOS
- 0x03B0: 0xE0, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
- 0x03B1: 0xE1, # GREEK SMALL LETTER ALPHA
- 0x03B2: 0xE2, # GREEK SMALL LETTER BETA
- 0x03B3: 0xE3, # GREEK SMALL LETTER GAMMA
- 0x03B4: 0xE4, # GREEK SMALL LETTER DELTA
- 0x03B5: 0xE5, # GREEK SMALL LETTER EPSILON
- 0x03B6: 0xE6, # GREEK SMALL LETTER ZETA
- 0x03B7: 0xE7, # GREEK SMALL LETTER ETA
- 0x03B8: 0xE8, # GREEK SMALL LETTER THETA
- 0x03B9: 0xE9, # GREEK SMALL LETTER IOTA
- 0x03BA: 0xEA, # GREEK SMALL LETTER KAPPA
- 0x03BB: 0xEB, # GREEK SMALL LETTER LAMDA
- 0x03BC: 0xEC, # GREEK SMALL LETTER MU
- 0x03BD: 0xED, # GREEK SMALL LETTER NU
- 0x03BE: 0xEE, # GREEK SMALL LETTER XI
- 0x03BF: 0xEF, # GREEK SMALL LETTER OMICRON
- 0x03C0: 0xF0, # GREEK SMALL LETTER PI
- 0x03C1: 0xF1, # GREEK SMALL LETTER RHO
- 0x03C2: 0xF2, # GREEK SMALL LETTER FINAL SIGMA
- 0x03C3: 0xF3, # GREEK SMALL LETTER SIGMA
- 0x03C4: 0xF4, # GREEK SMALL LETTER TAU
- 0x03C5: 0xF5, # GREEK SMALL LETTER UPSILON
- 0x03C6: 0xF6, # GREEK SMALL LETTER PHI
- 0x03C7: 0xF7, # GREEK SMALL LETTER CHI
- 0x03C8: 0xF8, # GREEK SMALL LETTER PSI
- 0x03C9: 0xF9, # GREEK SMALL LETTER OMEGA
- 0x03CA: 0xFA, # GREEK SMALL LETTER IOTA WITH DIALYTIKA
- 0x03CB: 0xFB, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
- 0x03CC: 0xFC, # GREEK SMALL LETTER OMICRON WITH TONOS
- 0x03CD: 0xFD, # GREEK SMALL LETTER UPSILON WITH TONOS
- 0x03CE: 0xFE, # GREEK SMALL LETTER OMEGA WITH TONOS
- 0x2013: 0x96, # EN DASH
- 0x2014: 0x97, # EM DASH
- 0x2015: 0xAF, # HORIZONTAL BAR
- 0x2018: 0x91, # LEFT SINGLE QUOTATION MARK
- 0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK
- 0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK
- 0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK
- 0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK
- 0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK
- 0x2020: 0x86, # DAGGER
- 0x2021: 0x87, # DOUBLE DAGGER
- 0x2022: 0x95, # BULLET
- 0x2026: 0x85, # HORIZONTAL ELLIPSIS
- 0x2030: 0x89, # PER MILLE SIGN
- 0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
- 0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
- 0x20AC: 0x80, # EURO SIGN
- 0x2122: 0x99, # TRADE MARK SIGN
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/cp1254.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/cp1254.py (original)
+++ python/branches/p3yk/Lib/encodings/cp1254.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,256 +303,5 @@
u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A1: 0xA1, # INVERTED EXCLAMATION MARK
- 0x00A2: 0xA2, # CENT SIGN
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A4: 0xA4, # CURRENCY SIGN
- 0x00A5: 0xA5, # YEN SIGN
- 0x00A6: 0xA6, # BROKEN BAR
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00A8: 0xA8, # DIAERESIS
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AA: 0xAA, # FEMININE ORDINAL INDICATOR
- 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xAC, # NOT SIGN
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00AE: 0xAE, # REGISTERED SIGN
- 0x00AF: 0xAF, # MACRON
- 0x00B0: 0xB0, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B2: 0xB2, # SUPERSCRIPT TWO
- 0x00B3: 0xB3, # SUPERSCRIPT THREE
- 0x00B4: 0xB4, # ACUTE ACCENT
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00B7: 0xB7, # MIDDLE DOT
- 0x00B8: 0xB8, # CEDILLA
- 0x00B9: 0xB9, # SUPERSCRIPT ONE
- 0x00BA: 0xBA, # MASCULINE ORDINAL INDICATOR
- 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER
- 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF
- 0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS
- 0x00BF: 0xBF, # INVERTED QUESTION MARK
- 0x00C0: 0xC0, # LATIN CAPITAL LETTER A WITH GRAVE
- 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C3: 0xC3, # LATIN CAPITAL LETTER A WITH TILDE
- 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE
- 0x00C6: 0xC6, # LATIN CAPITAL LETTER AE
- 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C8: 0xC8, # LATIN CAPITAL LETTER E WITH GRAVE
- 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CA: 0xCA, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
- 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CC: 0xCC, # LATIN CAPITAL LETTER I WITH GRAVE
- 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS
- 0x00D1: 0xD1, # LATIN CAPITAL LETTER N WITH TILDE
- 0x00D2: 0xD2, # LATIN CAPITAL LETTER O WITH GRAVE
- 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE
- 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D7: 0xD7, # MULTIPLICATION SIGN
- 0x00D8: 0xD8, # LATIN CAPITAL LETTER O WITH STROKE
- 0x00D9: 0xD9, # LATIN CAPITAL LETTER U WITH GRAVE
- 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
- 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S
- 0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E3: 0xE3, # LATIN SMALL LETTER A WITH TILDE
- 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE
- 0x00E6: 0xE6, # LATIN SMALL LETTER AE
- 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00EC: 0xEC, # LATIN SMALL LETTER I WITH GRAVE
- 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F1: 0xF1, # LATIN SMALL LETTER N WITH TILDE
- 0x00F2: 0xF2, # LATIN SMALL LETTER O WITH GRAVE
- 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE
- 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xF7, # DIVISION SIGN
- 0x00F8: 0xF8, # LATIN SMALL LETTER O WITH STROKE
- 0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x00FF: 0xFF, # LATIN SMALL LETTER Y WITH DIAERESIS
- 0x011E: 0xD0, # LATIN CAPITAL LETTER G WITH BREVE
- 0x011F: 0xF0, # LATIN SMALL LETTER G WITH BREVE
- 0x0130: 0xDD, # LATIN CAPITAL LETTER I WITH DOT ABOVE
- 0x0131: 0xFD, # LATIN SMALL LETTER DOTLESS I
- 0x0152: 0x8C, # LATIN CAPITAL LIGATURE OE
- 0x0153: 0x9C, # LATIN SMALL LIGATURE OE
- 0x015E: 0xDE, # LATIN CAPITAL LETTER S WITH CEDILLA
- 0x015F: 0xFE, # LATIN SMALL LETTER S WITH CEDILLA
- 0x0160: 0x8A, # LATIN CAPITAL LETTER S WITH CARON
- 0x0161: 0x9A, # LATIN SMALL LETTER S WITH CARON
- 0x0178: 0x9F, # LATIN CAPITAL LETTER Y WITH DIAERESIS
- 0x0192: 0x83, # LATIN SMALL LETTER F WITH HOOK
- 0x02C6: 0x88, # MODIFIER LETTER CIRCUMFLEX ACCENT
- 0x02DC: 0x98, # SMALL TILDE
- 0x2013: 0x96, # EN DASH
- 0x2014: 0x97, # EM DASH
- 0x2018: 0x91, # LEFT SINGLE QUOTATION MARK
- 0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK
- 0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK
- 0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK
- 0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK
- 0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK
- 0x2020: 0x86, # DAGGER
- 0x2021: 0x87, # DOUBLE DAGGER
- 0x2022: 0x95, # BULLET
- 0x2026: 0x85, # HORIZONTAL ELLIPSIS
- 0x2030: 0x89, # PER MILLE SIGN
- 0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
- 0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
- 0x20AC: 0x80, # EURO SIGN
- 0x2122: 0x99, # TRADE MARK SIGN
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/cp1255.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/cp1255.py (original)
+++ python/branches/p3yk/Lib/encodings/cp1255.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,240 +303,5 @@
u'\ufffe' # 0xFF -> UNDEFINED
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A1: 0xA1, # INVERTED EXCLAMATION MARK
- 0x00A2: 0xA2, # CENT SIGN
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A5: 0xA5, # YEN SIGN
- 0x00A6: 0xA6, # BROKEN BAR
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00A8: 0xA8, # DIAERESIS
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xAC, # NOT SIGN
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00AE: 0xAE, # REGISTERED SIGN
- 0x00AF: 0xAF, # MACRON
- 0x00B0: 0xB0, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B2: 0xB2, # SUPERSCRIPT TWO
- 0x00B3: 0xB3, # SUPERSCRIPT THREE
- 0x00B4: 0xB4, # ACUTE ACCENT
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00B7: 0xB7, # MIDDLE DOT
- 0x00B8: 0xB8, # CEDILLA
- 0x00B9: 0xB9, # SUPERSCRIPT ONE
- 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER
- 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF
- 0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS
- 0x00BF: 0xBF, # INVERTED QUESTION MARK
- 0x00D7: 0xAA, # MULTIPLICATION SIGN
- 0x00F7: 0xBA, # DIVISION SIGN
- 0x0192: 0x83, # LATIN SMALL LETTER F WITH HOOK
- 0x02C6: 0x88, # MODIFIER LETTER CIRCUMFLEX ACCENT
- 0x02DC: 0x98, # SMALL TILDE
- 0x05B0: 0xC0, # HEBREW POINT SHEVA
- 0x05B1: 0xC1, # HEBREW POINT HATAF SEGOL
- 0x05B2: 0xC2, # HEBREW POINT HATAF PATAH
- 0x05B3: 0xC3, # HEBREW POINT HATAF QAMATS
- 0x05B4: 0xC4, # HEBREW POINT HIRIQ
- 0x05B5: 0xC5, # HEBREW POINT TSERE
- 0x05B6: 0xC6, # HEBREW POINT SEGOL
- 0x05B7: 0xC7, # HEBREW POINT PATAH
- 0x05B8: 0xC8, # HEBREW POINT QAMATS
- 0x05B9: 0xC9, # HEBREW POINT HOLAM
- 0x05BB: 0xCB, # HEBREW POINT QUBUTS
- 0x05BC: 0xCC, # HEBREW POINT DAGESH OR MAPIQ
- 0x05BD: 0xCD, # HEBREW POINT METEG
- 0x05BE: 0xCE, # HEBREW PUNCTUATION MAQAF
- 0x05BF: 0xCF, # HEBREW POINT RAFE
- 0x05C0: 0xD0, # HEBREW PUNCTUATION PASEQ
- 0x05C1: 0xD1, # HEBREW POINT SHIN DOT
- 0x05C2: 0xD2, # HEBREW POINT SIN DOT
- 0x05C3: 0xD3, # HEBREW PUNCTUATION SOF PASUQ
- 0x05D0: 0xE0, # HEBREW LETTER ALEF
- 0x05D1: 0xE1, # HEBREW LETTER BET
- 0x05D2: 0xE2, # HEBREW LETTER GIMEL
- 0x05D3: 0xE3, # HEBREW LETTER DALET
- 0x05D4: 0xE4, # HEBREW LETTER HE
- 0x05D5: 0xE5, # HEBREW LETTER VAV
- 0x05D6: 0xE6, # HEBREW LETTER ZAYIN
- 0x05D7: 0xE7, # HEBREW LETTER HET
- 0x05D8: 0xE8, # HEBREW LETTER TET
- 0x05D9: 0xE9, # HEBREW LETTER YOD
- 0x05DA: 0xEA, # HEBREW LETTER FINAL KAF
- 0x05DB: 0xEB, # HEBREW LETTER KAF
- 0x05DC: 0xEC, # HEBREW LETTER LAMED
- 0x05DD: 0xED, # HEBREW LETTER FINAL MEM
- 0x05DE: 0xEE, # HEBREW LETTER MEM
- 0x05DF: 0xEF, # HEBREW LETTER FINAL NUN
- 0x05E0: 0xF0, # HEBREW LETTER NUN
- 0x05E1: 0xF1, # HEBREW LETTER SAMEKH
- 0x05E2: 0xF2, # HEBREW LETTER AYIN
- 0x05E3: 0xF3, # HEBREW LETTER FINAL PE
- 0x05E4: 0xF4, # HEBREW LETTER PE
- 0x05E5: 0xF5, # HEBREW LETTER FINAL TSADI
- 0x05E6: 0xF6, # HEBREW LETTER TSADI
- 0x05E7: 0xF7, # HEBREW LETTER QOF
- 0x05E8: 0xF8, # HEBREW LETTER RESH
- 0x05E9: 0xF9, # HEBREW LETTER SHIN
- 0x05EA: 0xFA, # HEBREW LETTER TAV
- 0x05F0: 0xD4, # HEBREW LIGATURE YIDDISH DOUBLE VAV
- 0x05F1: 0xD5, # HEBREW LIGATURE YIDDISH VAV YOD
- 0x05F2: 0xD6, # HEBREW LIGATURE YIDDISH DOUBLE YOD
- 0x05F3: 0xD7, # HEBREW PUNCTUATION GERESH
- 0x05F4: 0xD8, # HEBREW PUNCTUATION GERSHAYIM
- 0x200E: 0xFD, # LEFT-TO-RIGHT MARK
- 0x200F: 0xFE, # RIGHT-TO-LEFT MARK
- 0x2013: 0x96, # EN DASH
- 0x2014: 0x97, # EM DASH
- 0x2018: 0x91, # LEFT SINGLE QUOTATION MARK
- 0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK
- 0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK
- 0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK
- 0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK
- 0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK
- 0x2020: 0x86, # DAGGER
- 0x2021: 0x87, # DOUBLE DAGGER
- 0x2022: 0x95, # BULLET
- 0x2026: 0x85, # HORIZONTAL ELLIPSIS
- 0x2030: 0x89, # PER MILLE SIGN
- 0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
- 0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
- 0x20AA: 0xA4, # NEW SHEQEL SIGN
- 0x20AC: 0x80, # EURO SIGN
- 0x2122: 0x99, # TRADE MARK SIGN
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/cp1256.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/cp1256.py (original)
+++ python/branches/p3yk/Lib/encodings/cp1256.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\u06d2' # 0xFF -> ARABIC LETTER YEH BARREE
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A2: 0xA2, # CENT SIGN
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A4: 0xA4, # CURRENCY SIGN
- 0x00A5: 0xA5, # YEN SIGN
- 0x00A6: 0xA6, # BROKEN BAR
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00A8: 0xA8, # DIAERESIS
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xAC, # NOT SIGN
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00AE: 0xAE, # REGISTERED SIGN
- 0x00AF: 0xAF, # MACRON
- 0x00B0: 0xB0, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B2: 0xB2, # SUPERSCRIPT TWO
- 0x00B3: 0xB3, # SUPERSCRIPT THREE
- 0x00B4: 0xB4, # ACUTE ACCENT
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00B7: 0xB7, # MIDDLE DOT
- 0x00B8: 0xB8, # CEDILLA
- 0x00B9: 0xB9, # SUPERSCRIPT ONE
- 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER
- 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF
- 0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS
- 0x00D7: 0xD7, # MULTIPLICATION SIGN
- 0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F7: 0xF7, # DIVISION SIGN
- 0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x0152: 0x8C, # LATIN CAPITAL LIGATURE OE
- 0x0153: 0x9C, # LATIN SMALL LIGATURE OE
- 0x0192: 0x83, # LATIN SMALL LETTER F WITH HOOK
- 0x02C6: 0x88, # MODIFIER LETTER CIRCUMFLEX ACCENT
- 0x060C: 0xA1, # ARABIC COMMA
- 0x061B: 0xBA, # ARABIC SEMICOLON
- 0x061F: 0xBF, # ARABIC QUESTION MARK
- 0x0621: 0xC1, # ARABIC LETTER HAMZA
- 0x0622: 0xC2, # ARABIC LETTER ALEF WITH MADDA ABOVE
- 0x0623: 0xC3, # ARABIC LETTER ALEF WITH HAMZA ABOVE
- 0x0624: 0xC4, # ARABIC LETTER WAW WITH HAMZA ABOVE
- 0x0625: 0xC5, # ARABIC LETTER ALEF WITH HAMZA BELOW
- 0x0626: 0xC6, # ARABIC LETTER YEH WITH HAMZA ABOVE
- 0x0627: 0xC7, # ARABIC LETTER ALEF
- 0x0628: 0xC8, # ARABIC LETTER BEH
- 0x0629: 0xC9, # ARABIC LETTER TEH MARBUTA
- 0x062A: 0xCA, # ARABIC LETTER TEH
- 0x062B: 0xCB, # ARABIC LETTER THEH
- 0x062C: 0xCC, # ARABIC LETTER JEEM
- 0x062D: 0xCD, # ARABIC LETTER HAH
- 0x062E: 0xCE, # ARABIC LETTER KHAH
- 0x062F: 0xCF, # ARABIC LETTER DAL
- 0x0630: 0xD0, # ARABIC LETTER THAL
- 0x0631: 0xD1, # ARABIC LETTER REH
- 0x0632: 0xD2, # ARABIC LETTER ZAIN
- 0x0633: 0xD3, # ARABIC LETTER SEEN
- 0x0634: 0xD4, # ARABIC LETTER SHEEN
- 0x0635: 0xD5, # ARABIC LETTER SAD
- 0x0636: 0xD6, # ARABIC LETTER DAD
- 0x0637: 0xD8, # ARABIC LETTER TAH
- 0x0638: 0xD9, # ARABIC LETTER ZAH
- 0x0639: 0xDA, # ARABIC LETTER AIN
- 0x063A: 0xDB, # ARABIC LETTER GHAIN
- 0x0640: 0xDC, # ARABIC TATWEEL
- 0x0641: 0xDD, # ARABIC LETTER FEH
- 0x0642: 0xDE, # ARABIC LETTER QAF
- 0x0643: 0xDF, # ARABIC LETTER KAF
- 0x0644: 0xE1, # ARABIC LETTER LAM
- 0x0645: 0xE3, # ARABIC LETTER MEEM
- 0x0646: 0xE4, # ARABIC LETTER NOON
- 0x0647: 0xE5, # ARABIC LETTER HEH
- 0x0648: 0xE6, # ARABIC LETTER WAW
- 0x0649: 0xEC, # ARABIC LETTER ALEF MAKSURA
- 0x064A: 0xED, # ARABIC LETTER YEH
- 0x064B: 0xF0, # ARABIC FATHATAN
- 0x064C: 0xF1, # ARABIC DAMMATAN
- 0x064D: 0xF2, # ARABIC KASRATAN
- 0x064E: 0xF3, # ARABIC FATHA
- 0x064F: 0xF5, # ARABIC DAMMA
- 0x0650: 0xF6, # ARABIC KASRA
- 0x0651: 0xF8, # ARABIC SHADDA
- 0x0652: 0xFA, # ARABIC SUKUN
- 0x0679: 0x8A, # ARABIC LETTER TTEH
- 0x067E: 0x81, # ARABIC LETTER PEH
- 0x0686: 0x8D, # ARABIC LETTER TCHEH
- 0x0688: 0x8F, # ARABIC LETTER DDAL
- 0x0691: 0x9A, # ARABIC LETTER RREH
- 0x0698: 0x8E, # ARABIC LETTER JEH
- 0x06A9: 0x98, # ARABIC LETTER KEHEH
- 0x06AF: 0x90, # ARABIC LETTER GAF
- 0x06BA: 0x9F, # ARABIC LETTER NOON GHUNNA
- 0x06BE: 0xAA, # ARABIC LETTER HEH DOACHASHMEE
- 0x06C1: 0xC0, # ARABIC LETTER HEH GOAL
- 0x06D2: 0xFF, # ARABIC LETTER YEH BARREE
- 0x200C: 0x9D, # ZERO WIDTH NON-JOINER
- 0x200D: 0x9E, # ZERO WIDTH JOINER
- 0x200E: 0xFD, # LEFT-TO-RIGHT MARK
- 0x200F: 0xFE, # RIGHT-TO-LEFT MARK
- 0x2013: 0x96, # EN DASH
- 0x2014: 0x97, # EM DASH
- 0x2018: 0x91, # LEFT SINGLE QUOTATION MARK
- 0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK
- 0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK
- 0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK
- 0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK
- 0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK
- 0x2020: 0x86, # DAGGER
- 0x2021: 0x87, # DOUBLE DAGGER
- 0x2022: 0x95, # BULLET
- 0x2026: 0x85, # HORIZONTAL ELLIPSIS
- 0x2030: 0x89, # PER MILLE SIGN
- 0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
- 0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
- 0x20AC: 0x80, # EURO SIGN
- 0x2122: 0x99, # TRADE MARK SIGN
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/cp1257.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/cp1257.py (original)
+++ python/branches/p3yk/Lib/encodings/cp1257.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,251 +303,5 @@
u'\u02d9' # 0xFF -> DOT ABOVE
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A2: 0xA2, # CENT SIGN
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A4: 0xA4, # CURRENCY SIGN
- 0x00A6: 0xA6, # BROKEN BAR
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00A8: 0x8D, # DIAERESIS
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xAC, # NOT SIGN
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00AE: 0xAE, # REGISTERED SIGN
- 0x00AF: 0x9D, # MACRON
- 0x00B0: 0xB0, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B2: 0xB2, # SUPERSCRIPT TWO
- 0x00B3: 0xB3, # SUPERSCRIPT THREE
- 0x00B4: 0xB4, # ACUTE ACCENT
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00B7: 0xB7, # MIDDLE DOT
- 0x00B8: 0x8F, # CEDILLA
- 0x00B9: 0xB9, # SUPERSCRIPT ONE
- 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER
- 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF
- 0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS
- 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE
- 0x00C6: 0xAF, # LATIN CAPITAL LETTER AE
- 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE
- 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D7: 0xD7, # MULTIPLICATION SIGN
- 0x00D8: 0xA8, # LATIN CAPITAL LETTER O WITH STROKE
- 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S
- 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE
- 0x00E6: 0xBF, # LATIN SMALL LETTER AE
- 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE
- 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE
- 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xF7, # DIVISION SIGN
- 0x00F8: 0xB8, # LATIN SMALL LETTER O WITH STROKE
- 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x0100: 0xC2, # LATIN CAPITAL LETTER A WITH MACRON
- 0x0101: 0xE2, # LATIN SMALL LETTER A WITH MACRON
- 0x0104: 0xC0, # LATIN CAPITAL LETTER A WITH OGONEK
- 0x0105: 0xE0, # LATIN SMALL LETTER A WITH OGONEK
- 0x0106: 0xC3, # LATIN CAPITAL LETTER C WITH ACUTE
- 0x0107: 0xE3, # LATIN SMALL LETTER C WITH ACUTE
- 0x010C: 0xC8, # LATIN CAPITAL LETTER C WITH CARON
- 0x010D: 0xE8, # LATIN SMALL LETTER C WITH CARON
- 0x0112: 0xC7, # LATIN CAPITAL LETTER E WITH MACRON
- 0x0113: 0xE7, # LATIN SMALL LETTER E WITH MACRON
- 0x0116: 0xCB, # LATIN CAPITAL LETTER E WITH DOT ABOVE
- 0x0117: 0xEB, # LATIN SMALL LETTER E WITH DOT ABOVE
- 0x0118: 0xC6, # LATIN CAPITAL LETTER E WITH OGONEK
- 0x0119: 0xE6, # LATIN SMALL LETTER E WITH OGONEK
- 0x0122: 0xCC, # LATIN CAPITAL LETTER G WITH CEDILLA
- 0x0123: 0xEC, # LATIN SMALL LETTER G WITH CEDILLA
- 0x012A: 0xCE, # LATIN CAPITAL LETTER I WITH MACRON
- 0x012B: 0xEE, # LATIN SMALL LETTER I WITH MACRON
- 0x012E: 0xC1, # LATIN CAPITAL LETTER I WITH OGONEK
- 0x012F: 0xE1, # LATIN SMALL LETTER I WITH OGONEK
- 0x0136: 0xCD, # LATIN CAPITAL LETTER K WITH CEDILLA
- 0x0137: 0xED, # LATIN SMALL LETTER K WITH CEDILLA
- 0x013B: 0xCF, # LATIN CAPITAL LETTER L WITH CEDILLA
- 0x013C: 0xEF, # LATIN SMALL LETTER L WITH CEDILLA
- 0x0141: 0xD9, # LATIN CAPITAL LETTER L WITH STROKE
- 0x0142: 0xF9, # LATIN SMALL LETTER L WITH STROKE
- 0x0143: 0xD1, # LATIN CAPITAL LETTER N WITH ACUTE
- 0x0144: 0xF1, # LATIN SMALL LETTER N WITH ACUTE
- 0x0145: 0xD2, # LATIN CAPITAL LETTER N WITH CEDILLA
- 0x0146: 0xF2, # LATIN SMALL LETTER N WITH CEDILLA
- 0x014C: 0xD4, # LATIN CAPITAL LETTER O WITH MACRON
- 0x014D: 0xF4, # LATIN SMALL LETTER O WITH MACRON
- 0x0156: 0xAA, # LATIN CAPITAL LETTER R WITH CEDILLA
- 0x0157: 0xBA, # LATIN SMALL LETTER R WITH CEDILLA
- 0x015A: 0xDA, # LATIN CAPITAL LETTER S WITH ACUTE
- 0x015B: 0xFA, # LATIN SMALL LETTER S WITH ACUTE
- 0x0160: 0xD0, # LATIN CAPITAL LETTER S WITH CARON
- 0x0161: 0xF0, # LATIN SMALL LETTER S WITH CARON
- 0x016A: 0xDB, # LATIN CAPITAL LETTER U WITH MACRON
- 0x016B: 0xFB, # LATIN SMALL LETTER U WITH MACRON
- 0x0172: 0xD8, # LATIN CAPITAL LETTER U WITH OGONEK
- 0x0173: 0xF8, # LATIN SMALL LETTER U WITH OGONEK
- 0x0179: 0xCA, # LATIN CAPITAL LETTER Z WITH ACUTE
- 0x017A: 0xEA, # LATIN SMALL LETTER Z WITH ACUTE
- 0x017B: 0xDD, # LATIN CAPITAL LETTER Z WITH DOT ABOVE
- 0x017C: 0xFD, # LATIN SMALL LETTER Z WITH DOT ABOVE
- 0x017D: 0xDE, # LATIN CAPITAL LETTER Z WITH CARON
- 0x017E: 0xFE, # LATIN SMALL LETTER Z WITH CARON
- 0x02C7: 0x8E, # CARON
- 0x02D9: 0xFF, # DOT ABOVE
- 0x02DB: 0x9E, # OGONEK
- 0x2013: 0x96, # EN DASH
- 0x2014: 0x97, # EM DASH
- 0x2018: 0x91, # LEFT SINGLE QUOTATION MARK
- 0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK
- 0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK
- 0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK
- 0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK
- 0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK
- 0x2020: 0x86, # DAGGER
- 0x2021: 0x87, # DOUBLE DAGGER
- 0x2022: 0x95, # BULLET
- 0x2026: 0x85, # HORIZONTAL ELLIPSIS
- 0x2030: 0x89, # PER MILLE SIGN
- 0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
- 0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
- 0x20AC: 0x80, # EURO SIGN
- 0x2122: 0x99, # TRADE MARK SIGN
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/cp1258.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/cp1258.py (original)
+++ python/branches/p3yk/Lib/encodings/cp1258.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,254 +303,5 @@
u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A1: 0xA1, # INVERTED EXCLAMATION MARK
- 0x00A2: 0xA2, # CENT SIGN
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A4: 0xA4, # CURRENCY SIGN
- 0x00A5: 0xA5, # YEN SIGN
- 0x00A6: 0xA6, # BROKEN BAR
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00A8: 0xA8, # DIAERESIS
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AA: 0xAA, # FEMININE ORDINAL INDICATOR
- 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xAC, # NOT SIGN
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00AE: 0xAE, # REGISTERED SIGN
- 0x00AF: 0xAF, # MACRON
- 0x00B0: 0xB0, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B2: 0xB2, # SUPERSCRIPT TWO
- 0x00B3: 0xB3, # SUPERSCRIPT THREE
- 0x00B4: 0xB4, # ACUTE ACCENT
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00B7: 0xB7, # MIDDLE DOT
- 0x00B8: 0xB8, # CEDILLA
- 0x00B9: 0xB9, # SUPERSCRIPT ONE
- 0x00BA: 0xBA, # MASCULINE ORDINAL INDICATOR
- 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER
- 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF
- 0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS
- 0x00BF: 0xBF, # INVERTED QUESTION MARK
- 0x00C0: 0xC0, # LATIN CAPITAL LETTER A WITH GRAVE
- 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE
- 0x00C6: 0xC6, # LATIN CAPITAL LETTER AE
- 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C8: 0xC8, # LATIN CAPITAL LETTER E WITH GRAVE
- 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CA: 0xCA, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
- 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS
- 0x00D1: 0xD1, # LATIN CAPITAL LETTER N WITH TILDE
- 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D7: 0xD7, # MULTIPLICATION SIGN
- 0x00D8: 0xD8, # LATIN CAPITAL LETTER O WITH STROKE
- 0x00D9: 0xD9, # LATIN CAPITAL LETTER U WITH GRAVE
- 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
- 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S
- 0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE
- 0x00E6: 0xE6, # LATIN SMALL LETTER AE
- 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F1: 0xF1, # LATIN SMALL LETTER N WITH TILDE
- 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xF7, # DIVISION SIGN
- 0x00F8: 0xF8, # LATIN SMALL LETTER O WITH STROKE
- 0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x00FF: 0xFF, # LATIN SMALL LETTER Y WITH DIAERESIS
- 0x0102: 0xC3, # LATIN CAPITAL LETTER A WITH BREVE
- 0x0103: 0xE3, # LATIN SMALL LETTER A WITH BREVE
- 0x0110: 0xD0, # LATIN CAPITAL LETTER D WITH STROKE
- 0x0111: 0xF0, # LATIN SMALL LETTER D WITH STROKE
- 0x0152: 0x8C, # LATIN CAPITAL LIGATURE OE
- 0x0153: 0x9C, # LATIN SMALL LIGATURE OE
- 0x0178: 0x9F, # LATIN CAPITAL LETTER Y WITH DIAERESIS
- 0x0192: 0x83, # LATIN SMALL LETTER F WITH HOOK
- 0x01A0: 0xD5, # LATIN CAPITAL LETTER O WITH HORN
- 0x01A1: 0xF5, # LATIN SMALL LETTER O WITH HORN
- 0x01AF: 0xDD, # LATIN CAPITAL LETTER U WITH HORN
- 0x01B0: 0xFD, # LATIN SMALL LETTER U WITH HORN
- 0x02C6: 0x88, # MODIFIER LETTER CIRCUMFLEX ACCENT
- 0x02DC: 0x98, # SMALL TILDE
- 0x0300: 0xCC, # COMBINING GRAVE ACCENT
- 0x0301: 0xEC, # COMBINING ACUTE ACCENT
- 0x0303: 0xDE, # COMBINING TILDE
- 0x0309: 0xD2, # COMBINING HOOK ABOVE
- 0x0323: 0xF2, # COMBINING DOT BELOW
- 0x2013: 0x96, # EN DASH
- 0x2014: 0x97, # EM DASH
- 0x2018: 0x91, # LEFT SINGLE QUOTATION MARK
- 0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK
- 0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK
- 0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK
- 0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK
- 0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK
- 0x2020: 0x86, # DAGGER
- 0x2021: 0x87, # DOUBLE DAGGER
- 0x2022: 0x95, # BULLET
- 0x2026: 0x85, # HORIZONTAL ELLIPSIS
- 0x2030: 0x89, # PER MILLE SIGN
- 0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
- 0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
- 0x20AB: 0xFE, # DONG SIGN
- 0x20AC: 0x80, # EURO SIGN
- 0x2122: 0x99, # TRADE MARK SIGN
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/cp424.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/cp424.py (original)
+++ python/branches/p3yk/Lib/encodings/cp424.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,225 +303,5 @@
u'\x9f' # 0xFF -> EIGHT ONES
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x37, # END OF TRANSMISSION
- 0x0005: 0x2D, # ENQUIRY
- 0x0006: 0x2E, # ACKNOWLEDGE
- 0x0007: 0x2F, # BELL
- 0x0008: 0x16, # BACKSPACE
- 0x0009: 0x05, # HORIZONTAL TABULATION
- 0x000A: 0x25, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x3C, # DEVICE CONTROL FOUR
- 0x0015: 0x3D, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x32, # SYNCHRONOUS IDLE
- 0x0017: 0x26, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x3F, # SUBSTITUTE
- 0x001B: 0x27, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x40, # SPACE
- 0x0021: 0x5A, # EXCLAMATION MARK
- 0x0022: 0x7F, # QUOTATION MARK
- 0x0023: 0x7B, # NUMBER SIGN
- 0x0024: 0x5B, # DOLLAR SIGN
- 0x0025: 0x6C, # PERCENT SIGN
- 0x0026: 0x50, # AMPERSAND
- 0x0027: 0x7D, # APOSTROPHE
- 0x0028: 0x4D, # LEFT PARENTHESIS
- 0x0029: 0x5D, # RIGHT PARENTHESIS
- 0x002A: 0x5C, # ASTERISK
- 0x002B: 0x4E, # PLUS SIGN
- 0x002C: 0x6B, # COMMA
- 0x002D: 0x60, # HYPHEN-MINUS
- 0x002E: 0x4B, # FULL STOP
- 0x002F: 0x61, # SOLIDUS
- 0x0030: 0xF0, # DIGIT ZERO
- 0x0031: 0xF1, # DIGIT ONE
- 0x0032: 0xF2, # DIGIT TWO
- 0x0033: 0xF3, # DIGIT THREE
- 0x0034: 0xF4, # DIGIT FOUR
- 0x0035: 0xF5, # DIGIT FIVE
- 0x0036: 0xF6, # DIGIT SIX
- 0x0037: 0xF7, # DIGIT SEVEN
- 0x0038: 0xF8, # DIGIT EIGHT
- 0x0039: 0xF9, # DIGIT NINE
- 0x003A: 0x7A, # COLON
- 0x003B: 0x5E, # SEMICOLON
- 0x003C: 0x4C, # LESS-THAN SIGN
- 0x003D: 0x7E, # EQUALS SIGN
- 0x003E: 0x6E, # GREATER-THAN SIGN
- 0x003F: 0x6F, # QUESTION MARK
- 0x0040: 0x7C, # COMMERCIAL AT
- 0x0041: 0xC1, # LATIN CAPITAL LETTER A
- 0x0042: 0xC2, # LATIN CAPITAL LETTER B
- 0x0043: 0xC3, # LATIN CAPITAL LETTER C
- 0x0044: 0xC4, # LATIN CAPITAL LETTER D
- 0x0045: 0xC5, # LATIN CAPITAL LETTER E
- 0x0046: 0xC6, # LATIN CAPITAL LETTER F
- 0x0047: 0xC7, # LATIN CAPITAL LETTER G
- 0x0048: 0xC8, # LATIN CAPITAL LETTER H
- 0x0049: 0xC9, # LATIN CAPITAL LETTER I
- 0x004A: 0xD1, # LATIN CAPITAL LETTER J
- 0x004B: 0xD2, # LATIN CAPITAL LETTER K
- 0x004C: 0xD3, # LATIN CAPITAL LETTER L
- 0x004D: 0xD4, # LATIN CAPITAL LETTER M
- 0x004E: 0xD5, # LATIN CAPITAL LETTER N
- 0x004F: 0xD6, # LATIN CAPITAL LETTER O
- 0x0050: 0xD7, # LATIN CAPITAL LETTER P
- 0x0051: 0xD8, # LATIN CAPITAL LETTER Q
- 0x0052: 0xD9, # LATIN CAPITAL LETTER R
- 0x0053: 0xE2, # LATIN CAPITAL LETTER S
- 0x0054: 0xE3, # LATIN CAPITAL LETTER T
- 0x0055: 0xE4, # LATIN CAPITAL LETTER U
- 0x0056: 0xE5, # LATIN CAPITAL LETTER V
- 0x0057: 0xE6, # LATIN CAPITAL LETTER W
- 0x0058: 0xE7, # LATIN CAPITAL LETTER X
- 0x0059: 0xE8, # LATIN CAPITAL LETTER Y
- 0x005A: 0xE9, # LATIN CAPITAL LETTER Z
- 0x005B: 0xBA, # LEFT SQUARE BRACKET
- 0x005C: 0xE0, # REVERSE SOLIDUS
- 0x005D: 0xBB, # RIGHT SQUARE BRACKET
- 0x005E: 0xB0, # CIRCUMFLEX ACCENT
- 0x005F: 0x6D, # LOW LINE
- 0x0060: 0x79, # GRAVE ACCENT
- 0x0061: 0x81, # LATIN SMALL LETTER A
- 0x0062: 0x82, # LATIN SMALL LETTER B
- 0x0063: 0x83, # LATIN SMALL LETTER C
- 0x0064: 0x84, # LATIN SMALL LETTER D
- 0x0065: 0x85, # LATIN SMALL LETTER E
- 0x0066: 0x86, # LATIN SMALL LETTER F
- 0x0067: 0x87, # LATIN SMALL LETTER G
- 0x0068: 0x88, # LATIN SMALL LETTER H
- 0x0069: 0x89, # LATIN SMALL LETTER I
- 0x006A: 0x91, # LATIN SMALL LETTER J
- 0x006B: 0x92, # LATIN SMALL LETTER K
- 0x006C: 0x93, # LATIN SMALL LETTER L
- 0x006D: 0x94, # LATIN SMALL LETTER M
- 0x006E: 0x95, # LATIN SMALL LETTER N
- 0x006F: 0x96, # LATIN SMALL LETTER O
- 0x0070: 0x97, # LATIN SMALL LETTER P
- 0x0071: 0x98, # LATIN SMALL LETTER Q
- 0x0072: 0x99, # LATIN SMALL LETTER R
- 0x0073: 0xA2, # LATIN SMALL LETTER S
- 0x0074: 0xA3, # LATIN SMALL LETTER T
- 0x0075: 0xA4, # LATIN SMALL LETTER U
- 0x0076: 0xA5, # LATIN SMALL LETTER V
- 0x0077: 0xA6, # LATIN SMALL LETTER W
- 0x0078: 0xA7, # LATIN SMALL LETTER X
- 0x0079: 0xA8, # LATIN SMALL LETTER Y
- 0x007A: 0xA9, # LATIN SMALL LETTER Z
- 0x007B: 0xC0, # LEFT CURLY BRACKET
- 0x007C: 0x4F, # VERTICAL LINE
- 0x007D: 0xD0, # RIGHT CURLY BRACKET
- 0x007E: 0xA1, # TILDE
- 0x007F: 0x07, # DELETE
- 0x0080: 0x20, # DIGIT SELECT
- 0x0081: 0x21, # START OF SIGNIFICANCE
- 0x0082: 0x22, # FIELD SEPARATOR
- 0x0083: 0x23, # WORD UNDERSCORE
- 0x0084: 0x24, # BYPASS OR INHIBIT PRESENTATION
- 0x0085: 0x15, # NEW LINE
- 0x0086: 0x06, # REQUIRED NEW LINE
- 0x0087: 0x17, # PROGRAM OPERATOR COMMUNICATION
- 0x0088: 0x28, # SET ATTRIBUTE
- 0x0089: 0x29, # START FIELD EXTENDED
- 0x008A: 0x2A, # SET MODE OR SWITCH
- 0x008B: 0x2B, # CONTROL SEQUENCE PREFIX
- 0x008C: 0x2C, # MODIFY FIELD ATTRIBUTE
- 0x008D: 0x09, # SUPERSCRIPT
- 0x008E: 0x0A, # REPEAT
- 0x008F: 0x1B, # CUSTOMER USE ONE
- 0x0090: 0x30, # <reserved>
- 0x0091: 0x31, # <reserved>
- 0x0092: 0x1A, # UNIT BACK SPACE
- 0x0093: 0x33, # INDEX RETURN
- 0x0094: 0x34, # PRESENTATION POSITION
- 0x0095: 0x35, # TRANSPARENT
- 0x0096: 0x36, # NUMERIC BACKSPACE
- 0x0097: 0x08, # GRAPHIC ESCAPE
- 0x0098: 0x38, # SUBSCRIPT
- 0x0099: 0x39, # INDENT TABULATION
- 0x009A: 0x3A, # REVERSE FORM FEED
- 0x009B: 0x3B, # CUSTOMER USE THREE
- 0x009C: 0x04, # SELECT
- 0x009D: 0x14, # RESTORE/ENABLE PRESENTATION
- 0x009E: 0x3E, # <reserved>
- 0x009F: 0xFF, # EIGHT ONES
- 0x00A0: 0x74, # NO-BREAK SPACE
- 0x00A2: 0x4A, # CENT SIGN
- 0x00A3: 0xB1, # POUND SIGN
- 0x00A4: 0x9F, # CURRENCY SIGN
- 0x00A5: 0xB2, # YEN SIGN
- 0x00A6: 0x6A, # BROKEN BAR
- 0x00A7: 0xB5, # SECTION SIGN
- 0x00A8: 0xBD, # DIAERESIS
- 0x00A9: 0xB4, # COPYRIGHT SIGN
- 0x00AB: 0x8A, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0x5F, # NOT SIGN
- 0x00AD: 0xCA, # SOFT HYPHEN
- 0x00AE: 0xAF, # REGISTERED SIGN
- 0x00AF: 0xBC, # MACRON
- 0x00B0: 0x90, # DEGREE SIGN
- 0x00B1: 0x8F, # PLUS-MINUS SIGN
- 0x00B2: 0xEA, # SUPERSCRIPT TWO
- 0x00B3: 0xFA, # SUPERSCRIPT THREE
- 0x00B4: 0xBE, # ACUTE ACCENT
- 0x00B5: 0xA0, # MICRO SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00B7: 0xB3, # MIDDLE DOT
- 0x00B8: 0x9D, # CEDILLA
- 0x00B9: 0xDA, # SUPERSCRIPT ONE
- 0x00BB: 0x8B, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BC: 0xB7, # VULGAR FRACTION ONE QUARTER
- 0x00BD: 0xB8, # VULGAR FRACTION ONE HALF
- 0x00BE: 0xB9, # VULGAR FRACTION THREE QUARTERS
- 0x00D7: 0xBF, # MULTIPLICATION SIGN
- 0x00F7: 0xE1, # DIVISION SIGN
- 0x05D0: 0x41, # HEBREW LETTER ALEF
- 0x05D1: 0x42, # HEBREW LETTER BET
- 0x05D2: 0x43, # HEBREW LETTER GIMEL
- 0x05D3: 0x44, # HEBREW LETTER DALET
- 0x05D4: 0x45, # HEBREW LETTER HE
- 0x05D5: 0x46, # HEBREW LETTER VAV
- 0x05D6: 0x47, # HEBREW LETTER ZAYIN
- 0x05D7: 0x48, # HEBREW LETTER HET
- 0x05D8: 0x49, # HEBREW LETTER TET
- 0x05D9: 0x51, # HEBREW LETTER YOD
- 0x05DA: 0x52, # HEBREW LETTER FINAL KAF
- 0x05DB: 0x53, # HEBREW LETTER KAF
- 0x05DC: 0x54, # HEBREW LETTER LAMED
- 0x05DD: 0x55, # HEBREW LETTER FINAL MEM
- 0x05DE: 0x56, # HEBREW LETTER MEM
- 0x05DF: 0x57, # HEBREW LETTER FINAL NUN
- 0x05E0: 0x58, # HEBREW LETTER NUN
- 0x05E1: 0x59, # HEBREW LETTER SAMEKH
- 0x05E2: 0x62, # HEBREW LETTER AYIN
- 0x05E3: 0x63, # HEBREW LETTER FINAL PE
- 0x05E4: 0x64, # HEBREW LETTER PE
- 0x05E5: 0x65, # HEBREW LETTER FINAL TSADI
- 0x05E6: 0x66, # HEBREW LETTER TSADI
- 0x05E7: 0x67, # HEBREW LETTER QOF
- 0x05E8: 0x68, # HEBREW LETTER RESH
- 0x05E9: 0x69, # HEBREW LETTER SHIN
- 0x05EA: 0x71, # HEBREW LETTER TAV
- 0x2017: 0x78, # DOUBLE LOW LINE
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/cp500.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/cp500.py (original)
+++ python/branches/p3yk/Lib/encodings/cp500.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\x9f' # 0xFF -> CONTROL
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x37, # END OF TRANSMISSION
- 0x0005: 0x2D, # ENQUIRY
- 0x0006: 0x2E, # ACKNOWLEDGE
- 0x0007: 0x2F, # BELL
- 0x0008: 0x16, # BACKSPACE
- 0x0009: 0x05, # HORIZONTAL TABULATION
- 0x000A: 0x25, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x3C, # DEVICE CONTROL FOUR
- 0x0015: 0x3D, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x32, # SYNCHRONOUS IDLE
- 0x0017: 0x26, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x3F, # SUBSTITUTE
- 0x001B: 0x27, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x40, # SPACE
- 0x0021: 0x4F, # EXCLAMATION MARK
- 0x0022: 0x7F, # QUOTATION MARK
- 0x0023: 0x7B, # NUMBER SIGN
- 0x0024: 0x5B, # DOLLAR SIGN
- 0x0025: 0x6C, # PERCENT SIGN
- 0x0026: 0x50, # AMPERSAND
- 0x0027: 0x7D, # APOSTROPHE
- 0x0028: 0x4D, # LEFT PARENTHESIS
- 0x0029: 0x5D, # RIGHT PARENTHESIS
- 0x002A: 0x5C, # ASTERISK
- 0x002B: 0x4E, # PLUS SIGN
- 0x002C: 0x6B, # COMMA
- 0x002D: 0x60, # HYPHEN-MINUS
- 0x002E: 0x4B, # FULL STOP
- 0x002F: 0x61, # SOLIDUS
- 0x0030: 0xF0, # DIGIT ZERO
- 0x0031: 0xF1, # DIGIT ONE
- 0x0032: 0xF2, # DIGIT TWO
- 0x0033: 0xF3, # DIGIT THREE
- 0x0034: 0xF4, # DIGIT FOUR
- 0x0035: 0xF5, # DIGIT FIVE
- 0x0036: 0xF6, # DIGIT SIX
- 0x0037: 0xF7, # DIGIT SEVEN
- 0x0038: 0xF8, # DIGIT EIGHT
- 0x0039: 0xF9, # DIGIT NINE
- 0x003A: 0x7A, # COLON
- 0x003B: 0x5E, # SEMICOLON
- 0x003C: 0x4C, # LESS-THAN SIGN
- 0x003D: 0x7E, # EQUALS SIGN
- 0x003E: 0x6E, # GREATER-THAN SIGN
- 0x003F: 0x6F, # QUESTION MARK
- 0x0040: 0x7C, # COMMERCIAL AT
- 0x0041: 0xC1, # LATIN CAPITAL LETTER A
- 0x0042: 0xC2, # LATIN CAPITAL LETTER B
- 0x0043: 0xC3, # LATIN CAPITAL LETTER C
- 0x0044: 0xC4, # LATIN CAPITAL LETTER D
- 0x0045: 0xC5, # LATIN CAPITAL LETTER E
- 0x0046: 0xC6, # LATIN CAPITAL LETTER F
- 0x0047: 0xC7, # LATIN CAPITAL LETTER G
- 0x0048: 0xC8, # LATIN CAPITAL LETTER H
- 0x0049: 0xC9, # LATIN CAPITAL LETTER I
- 0x004A: 0xD1, # LATIN CAPITAL LETTER J
- 0x004B: 0xD2, # LATIN CAPITAL LETTER K
- 0x004C: 0xD3, # LATIN CAPITAL LETTER L
- 0x004D: 0xD4, # LATIN CAPITAL LETTER M
- 0x004E: 0xD5, # LATIN CAPITAL LETTER N
- 0x004F: 0xD6, # LATIN CAPITAL LETTER O
- 0x0050: 0xD7, # LATIN CAPITAL LETTER P
- 0x0051: 0xD8, # LATIN CAPITAL LETTER Q
- 0x0052: 0xD9, # LATIN CAPITAL LETTER R
- 0x0053: 0xE2, # LATIN CAPITAL LETTER S
- 0x0054: 0xE3, # LATIN CAPITAL LETTER T
- 0x0055: 0xE4, # LATIN CAPITAL LETTER U
- 0x0056: 0xE5, # LATIN CAPITAL LETTER V
- 0x0057: 0xE6, # LATIN CAPITAL LETTER W
- 0x0058: 0xE7, # LATIN CAPITAL LETTER X
- 0x0059: 0xE8, # LATIN CAPITAL LETTER Y
- 0x005A: 0xE9, # LATIN CAPITAL LETTER Z
- 0x005B: 0x4A, # LEFT SQUARE BRACKET
- 0x005C: 0xE0, # REVERSE SOLIDUS
- 0x005D: 0x5A, # RIGHT SQUARE BRACKET
- 0x005E: 0x5F, # CIRCUMFLEX ACCENT
- 0x005F: 0x6D, # LOW LINE
- 0x0060: 0x79, # GRAVE ACCENT
- 0x0061: 0x81, # LATIN SMALL LETTER A
- 0x0062: 0x82, # LATIN SMALL LETTER B
- 0x0063: 0x83, # LATIN SMALL LETTER C
- 0x0064: 0x84, # LATIN SMALL LETTER D
- 0x0065: 0x85, # LATIN SMALL LETTER E
- 0x0066: 0x86, # LATIN SMALL LETTER F
- 0x0067: 0x87, # LATIN SMALL LETTER G
- 0x0068: 0x88, # LATIN SMALL LETTER H
- 0x0069: 0x89, # LATIN SMALL LETTER I
- 0x006A: 0x91, # LATIN SMALL LETTER J
- 0x006B: 0x92, # LATIN SMALL LETTER K
- 0x006C: 0x93, # LATIN SMALL LETTER L
- 0x006D: 0x94, # LATIN SMALL LETTER M
- 0x006E: 0x95, # LATIN SMALL LETTER N
- 0x006F: 0x96, # LATIN SMALL LETTER O
- 0x0070: 0x97, # LATIN SMALL LETTER P
- 0x0071: 0x98, # LATIN SMALL LETTER Q
- 0x0072: 0x99, # LATIN SMALL LETTER R
- 0x0073: 0xA2, # LATIN SMALL LETTER S
- 0x0074: 0xA3, # LATIN SMALL LETTER T
- 0x0075: 0xA4, # LATIN SMALL LETTER U
- 0x0076: 0xA5, # LATIN SMALL LETTER V
- 0x0077: 0xA6, # LATIN SMALL LETTER W
- 0x0078: 0xA7, # LATIN SMALL LETTER X
- 0x0079: 0xA8, # LATIN SMALL LETTER Y
- 0x007A: 0xA9, # LATIN SMALL LETTER Z
- 0x007B: 0xC0, # LEFT CURLY BRACKET
- 0x007C: 0xBB, # VERTICAL LINE
- 0x007D: 0xD0, # RIGHT CURLY BRACKET
- 0x007E: 0xA1, # TILDE
- 0x007F: 0x07, # DELETE
- 0x0080: 0x20, # CONTROL
- 0x0081: 0x21, # CONTROL
- 0x0082: 0x22, # CONTROL
- 0x0083: 0x23, # CONTROL
- 0x0084: 0x24, # CONTROL
- 0x0085: 0x15, # CONTROL
- 0x0086: 0x06, # CONTROL
- 0x0087: 0x17, # CONTROL
- 0x0088: 0x28, # CONTROL
- 0x0089: 0x29, # CONTROL
- 0x008A: 0x2A, # CONTROL
- 0x008B: 0x2B, # CONTROL
- 0x008C: 0x2C, # CONTROL
- 0x008D: 0x09, # CONTROL
- 0x008E: 0x0A, # CONTROL
- 0x008F: 0x1B, # CONTROL
- 0x0090: 0x30, # CONTROL
- 0x0091: 0x31, # CONTROL
- 0x0092: 0x1A, # CONTROL
- 0x0093: 0x33, # CONTROL
- 0x0094: 0x34, # CONTROL
- 0x0095: 0x35, # CONTROL
- 0x0096: 0x36, # CONTROL
- 0x0097: 0x08, # CONTROL
- 0x0098: 0x38, # CONTROL
- 0x0099: 0x39, # CONTROL
- 0x009A: 0x3A, # CONTROL
- 0x009B: 0x3B, # CONTROL
- 0x009C: 0x04, # CONTROL
- 0x009D: 0x14, # CONTROL
- 0x009E: 0x3E, # CONTROL
- 0x009F: 0xFF, # CONTROL
- 0x00A0: 0x41, # NO-BREAK SPACE
- 0x00A1: 0xAA, # INVERTED EXCLAMATION MARK
- 0x00A2: 0xB0, # CENT SIGN
- 0x00A3: 0xB1, # POUND SIGN
- 0x00A4: 0x9F, # CURRENCY SIGN
- 0x00A5: 0xB2, # YEN SIGN
- 0x00A6: 0x6A, # BROKEN BAR
- 0x00A7: 0xB5, # SECTION SIGN
- 0x00A8: 0xBD, # DIAERESIS
- 0x00A9: 0xB4, # COPYRIGHT SIGN
- 0x00AA: 0x9A, # FEMININE ORDINAL INDICATOR
- 0x00AB: 0x8A, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xBA, # NOT SIGN
- 0x00AD: 0xCA, # SOFT HYPHEN
- 0x00AE: 0xAF, # REGISTERED SIGN
- 0x00AF: 0xBC, # MACRON
- 0x00B0: 0x90, # DEGREE SIGN
- 0x00B1: 0x8F, # PLUS-MINUS SIGN
- 0x00B2: 0xEA, # SUPERSCRIPT TWO
- 0x00B3: 0xFA, # SUPERSCRIPT THREE
- 0x00B4: 0xBE, # ACUTE ACCENT
- 0x00B5: 0xA0, # MICRO SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00B7: 0xB3, # MIDDLE DOT
- 0x00B8: 0x9D, # CEDILLA
- 0x00B9: 0xDA, # SUPERSCRIPT ONE
- 0x00BA: 0x9B, # MASCULINE ORDINAL INDICATOR
- 0x00BB: 0x8B, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BC: 0xB7, # VULGAR FRACTION ONE QUARTER
- 0x00BD: 0xB8, # VULGAR FRACTION ONE HALF
- 0x00BE: 0xB9, # VULGAR FRACTION THREE QUARTERS
- 0x00BF: 0xAB, # INVERTED QUESTION MARK
- 0x00C0: 0x64, # LATIN CAPITAL LETTER A WITH GRAVE
- 0x00C1: 0x65, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0x62, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C3: 0x66, # LATIN CAPITAL LETTER A WITH TILDE
- 0x00C4: 0x63, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C5: 0x67, # LATIN CAPITAL LETTER A WITH RING ABOVE
- 0x00C6: 0x9E, # LATIN CAPITAL LIGATURE AE
- 0x00C7: 0x68, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C8: 0x74, # LATIN CAPITAL LETTER E WITH GRAVE
- 0x00C9: 0x71, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CA: 0x72, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
- 0x00CB: 0x73, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CC: 0x78, # LATIN CAPITAL LETTER I WITH GRAVE
- 0x00CD: 0x75, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0x76, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00CF: 0x77, # LATIN CAPITAL LETTER I WITH DIAERESIS
- 0x00D0: 0xAC, # LATIN CAPITAL LETTER ETH (ICELANDIC)
- 0x00D1: 0x69, # LATIN CAPITAL LETTER N WITH TILDE
- 0x00D2: 0xED, # LATIN CAPITAL LETTER O WITH GRAVE
- 0x00D3: 0xEE, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xEB, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D5: 0xEF, # LATIN CAPITAL LETTER O WITH TILDE
- 0x00D6: 0xEC, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D7: 0xBF, # MULTIPLICATION SIGN
- 0x00D8: 0x80, # LATIN CAPITAL LETTER O WITH STROKE
- 0x00D9: 0xFD, # LATIN CAPITAL LETTER U WITH GRAVE
- 0x00DA: 0xFE, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DB: 0xFB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
- 0x00DC: 0xFC, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DD: 0xAD, # LATIN CAPITAL LETTER Y WITH ACUTE
- 0x00DE: 0xAE, # LATIN CAPITAL LETTER THORN (ICELANDIC)
- 0x00DF: 0x59, # LATIN SMALL LETTER SHARP S (GERMAN)
- 0x00E0: 0x44, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E1: 0x45, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0x42, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E3: 0x46, # LATIN SMALL LETTER A WITH TILDE
- 0x00E4: 0x43, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E5: 0x47, # LATIN SMALL LETTER A WITH RING ABOVE
- 0x00E6: 0x9C, # LATIN SMALL LIGATURE AE
- 0x00E7: 0x48, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0x54, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0x51, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0x52, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0x53, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00EC: 0x58, # LATIN SMALL LETTER I WITH GRAVE
- 0x00ED: 0x55, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0x56, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0x57, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F0: 0x8C, # LATIN SMALL LETTER ETH (ICELANDIC)
- 0x00F1: 0x49, # LATIN SMALL LETTER N WITH TILDE
- 0x00F2: 0xCD, # LATIN SMALL LETTER O WITH GRAVE
- 0x00F3: 0xCE, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0xCB, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F5: 0xCF, # LATIN SMALL LETTER O WITH TILDE
- 0x00F6: 0xCC, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xE1, # DIVISION SIGN
- 0x00F8: 0x70, # LATIN SMALL LETTER O WITH STROKE
- 0x00F9: 0xDD, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FA: 0xDE, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0xDB, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0xDC, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x00FD: 0x8D, # LATIN SMALL LETTER Y WITH ACUTE
- 0x00FE: 0x8E, # LATIN SMALL LETTER THORN (ICELANDIC)
- 0x00FF: 0xDF, # LATIN SMALL LETTER Y WITH DIAERESIS
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/cp856.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/cp856.py (original)
+++ python/branches/p3yk/Lib/encodings/cp856.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,222 +303,5 @@
u'\xa0' # 0xFF -> NO-BREAK SPACE
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x00A0: 0xFF, # NO-BREAK SPACE
- 0x00A2: 0xBD, # CENT SIGN
- 0x00A3: 0x9C, # POUND SIGN
- 0x00A4: 0xCF, # CURRENCY SIGN
- 0x00A5: 0xBE, # YEN SIGN
- 0x00A6: 0xDD, # BROKEN BAR
- 0x00A7: 0xF5, # SECTION SIGN
- 0x00A8: 0xF9, # DIAERESIS
- 0x00A9: 0xB8, # COPYRIGHT SIGN
- 0x00AB: 0xAE, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xAA, # NOT SIGN
- 0x00AD: 0xF0, # SOFT HYPHEN
- 0x00AE: 0xA9, # REGISTERED SIGN
- 0x00AF: 0xEE, # MACRON
- 0x00B0: 0xF8, # DEGREE SIGN
- 0x00B1: 0xF1, # PLUS-MINUS SIGN
- 0x00B2: 0xFD, # SUPERSCRIPT TWO
- 0x00B3: 0xFC, # SUPERSCRIPT THREE
- 0x00B4: 0xEF, # ACUTE ACCENT
- 0x00B5: 0xE6, # MICRO SIGN
- 0x00B6: 0xF4, # PILCROW SIGN
- 0x00B7: 0xFA, # MIDDLE DOT
- 0x00B8: 0xF7, # CEDILLA
- 0x00B9: 0xFB, # SUPERSCRIPT ONE
- 0x00BB: 0xAF, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BC: 0xAC, # VULGAR FRACTION ONE QUARTER
- 0x00BD: 0xAB, # VULGAR FRACTION ONE HALF
- 0x00BE: 0xF3, # VULGAR FRACTION THREE QUARTERS
- 0x00D7: 0x9E, # MULTIPLICATION SIGN
- 0x00F7: 0xF6, # DIVISION SIGN
- 0x05D0: 0x80, # HEBREW LETTER ALEF
- 0x05D1: 0x81, # HEBREW LETTER BET
- 0x05D2: 0x82, # HEBREW LETTER GIMEL
- 0x05D3: 0x83, # HEBREW LETTER DALET
- 0x05D4: 0x84, # HEBREW LETTER HE
- 0x05D5: 0x85, # HEBREW LETTER VAV
- 0x05D6: 0x86, # HEBREW LETTER ZAYIN
- 0x05D7: 0x87, # HEBREW LETTER HET
- 0x05D8: 0x88, # HEBREW LETTER TET
- 0x05D9: 0x89, # HEBREW LETTER YOD
- 0x05DA: 0x8A, # HEBREW LETTER FINAL KAF
- 0x05DB: 0x8B, # HEBREW LETTER KAF
- 0x05DC: 0x8C, # HEBREW LETTER LAMED
- 0x05DD: 0x8D, # HEBREW LETTER FINAL MEM
- 0x05DE: 0x8E, # HEBREW LETTER MEM
- 0x05DF: 0x8F, # HEBREW LETTER FINAL NUN
- 0x05E0: 0x90, # HEBREW LETTER NUN
- 0x05E1: 0x91, # HEBREW LETTER SAMEKH
- 0x05E2: 0x92, # HEBREW LETTER AYIN
- 0x05E3: 0x93, # HEBREW LETTER FINAL PE
- 0x05E4: 0x94, # HEBREW LETTER PE
- 0x05E5: 0x95, # HEBREW LETTER FINAL TSADI
- 0x05E6: 0x96, # HEBREW LETTER TSADI
- 0x05E7: 0x97, # HEBREW LETTER QOF
- 0x05E8: 0x98, # HEBREW LETTER RESH
- 0x05E9: 0x99, # HEBREW LETTER SHIN
- 0x05EA: 0x9A, # HEBREW LETTER TAV
- 0x2017: 0xF2, # DOUBLE LOW LINE
- 0x2500: 0xC4, # BOX DRAWINGS LIGHT HORIZONTAL
- 0x2502: 0xB3, # BOX DRAWINGS LIGHT VERTICAL
- 0x250C: 0xDA, # BOX DRAWINGS LIGHT DOWN AND RIGHT
- 0x2510: 0xBF, # BOX DRAWINGS LIGHT DOWN AND LEFT
- 0x2514: 0xC0, # BOX DRAWINGS LIGHT UP AND RIGHT
- 0x2518: 0xD9, # BOX DRAWINGS LIGHT UP AND LEFT
- 0x251C: 0xC3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
- 0x2524: 0xB4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
- 0x252C: 0xC2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
- 0x2534: 0xC1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
- 0x253C: 0xC5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
- 0x2550: 0xCD, # BOX DRAWINGS DOUBLE HORIZONTAL
- 0x2551: 0xBA, # BOX DRAWINGS DOUBLE VERTICAL
- 0x2554: 0xC9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
- 0x2557: 0xBB, # BOX DRAWINGS DOUBLE DOWN AND LEFT
- 0x255A: 0xC8, # BOX DRAWINGS DOUBLE UP AND RIGHT
- 0x255D: 0xBC, # BOX DRAWINGS DOUBLE UP AND LEFT
- 0x2560: 0xCC, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
- 0x2563: 0xB9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
- 0x2566: 0xCB, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
- 0x2569: 0xCA, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
- 0x256C: 0xCE, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
- 0x2580: 0xDF, # UPPER HALF BLOCK
- 0x2584: 0xDC, # LOWER HALF BLOCK
- 0x2588: 0xDB, # FULL BLOCK
- 0x2591: 0xB0, # LIGHT SHADE
- 0x2592: 0xB1, # MEDIUM SHADE
- 0x2593: 0xB2, # DARK SHADE
- 0x25A0: 0xFE, # BLACK SQUARE
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/cp874.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/cp874.py (original)
+++ python/branches/p3yk/Lib/encodings/cp874.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,232 +303,5 @@
u'\ufffe' # 0xFF -> UNDEFINED
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x0E01: 0xA1, # THAI CHARACTER KO KAI
- 0x0E02: 0xA2, # THAI CHARACTER KHO KHAI
- 0x0E03: 0xA3, # THAI CHARACTER KHO KHUAT
- 0x0E04: 0xA4, # THAI CHARACTER KHO KHWAI
- 0x0E05: 0xA5, # THAI CHARACTER KHO KHON
- 0x0E06: 0xA6, # THAI CHARACTER KHO RAKHANG
- 0x0E07: 0xA7, # THAI CHARACTER NGO NGU
- 0x0E08: 0xA8, # THAI CHARACTER CHO CHAN
- 0x0E09: 0xA9, # THAI CHARACTER CHO CHING
- 0x0E0A: 0xAA, # THAI CHARACTER CHO CHANG
- 0x0E0B: 0xAB, # THAI CHARACTER SO SO
- 0x0E0C: 0xAC, # THAI CHARACTER CHO CHOE
- 0x0E0D: 0xAD, # THAI CHARACTER YO YING
- 0x0E0E: 0xAE, # THAI CHARACTER DO CHADA
- 0x0E0F: 0xAF, # THAI CHARACTER TO PATAK
- 0x0E10: 0xB0, # THAI CHARACTER THO THAN
- 0x0E11: 0xB1, # THAI CHARACTER THO NANGMONTHO
- 0x0E12: 0xB2, # THAI CHARACTER THO PHUTHAO
- 0x0E13: 0xB3, # THAI CHARACTER NO NEN
- 0x0E14: 0xB4, # THAI CHARACTER DO DEK
- 0x0E15: 0xB5, # THAI CHARACTER TO TAO
- 0x0E16: 0xB6, # THAI CHARACTER THO THUNG
- 0x0E17: 0xB7, # THAI CHARACTER THO THAHAN
- 0x0E18: 0xB8, # THAI CHARACTER THO THONG
- 0x0E19: 0xB9, # THAI CHARACTER NO NU
- 0x0E1A: 0xBA, # THAI CHARACTER BO BAIMAI
- 0x0E1B: 0xBB, # THAI CHARACTER PO PLA
- 0x0E1C: 0xBC, # THAI CHARACTER PHO PHUNG
- 0x0E1D: 0xBD, # THAI CHARACTER FO FA
- 0x0E1E: 0xBE, # THAI CHARACTER PHO PHAN
- 0x0E1F: 0xBF, # THAI CHARACTER FO FAN
- 0x0E20: 0xC0, # THAI CHARACTER PHO SAMPHAO
- 0x0E21: 0xC1, # THAI CHARACTER MO MA
- 0x0E22: 0xC2, # THAI CHARACTER YO YAK
- 0x0E23: 0xC3, # THAI CHARACTER RO RUA
- 0x0E24: 0xC4, # THAI CHARACTER RU
- 0x0E25: 0xC5, # THAI CHARACTER LO LING
- 0x0E26: 0xC6, # THAI CHARACTER LU
- 0x0E27: 0xC7, # THAI CHARACTER WO WAEN
- 0x0E28: 0xC8, # THAI CHARACTER SO SALA
- 0x0E29: 0xC9, # THAI CHARACTER SO RUSI
- 0x0E2A: 0xCA, # THAI CHARACTER SO SUA
- 0x0E2B: 0xCB, # THAI CHARACTER HO HIP
- 0x0E2C: 0xCC, # THAI CHARACTER LO CHULA
- 0x0E2D: 0xCD, # THAI CHARACTER O ANG
- 0x0E2E: 0xCE, # THAI CHARACTER HO NOKHUK
- 0x0E2F: 0xCF, # THAI CHARACTER PAIYANNOI
- 0x0E30: 0xD0, # THAI CHARACTER SARA A
- 0x0E31: 0xD1, # THAI CHARACTER MAI HAN-AKAT
- 0x0E32: 0xD2, # THAI CHARACTER SARA AA
- 0x0E33: 0xD3, # THAI CHARACTER SARA AM
- 0x0E34: 0xD4, # THAI CHARACTER SARA I
- 0x0E35: 0xD5, # THAI CHARACTER SARA II
- 0x0E36: 0xD6, # THAI CHARACTER SARA UE
- 0x0E37: 0xD7, # THAI CHARACTER SARA UEE
- 0x0E38: 0xD8, # THAI CHARACTER SARA U
- 0x0E39: 0xD9, # THAI CHARACTER SARA UU
- 0x0E3A: 0xDA, # THAI CHARACTER PHINTHU
- 0x0E3F: 0xDF, # THAI CURRENCY SYMBOL BAHT
- 0x0E40: 0xE0, # THAI CHARACTER SARA E
- 0x0E41: 0xE1, # THAI CHARACTER SARA AE
- 0x0E42: 0xE2, # THAI CHARACTER SARA O
- 0x0E43: 0xE3, # THAI CHARACTER SARA AI MAIMUAN
- 0x0E44: 0xE4, # THAI CHARACTER SARA AI MAIMALAI
- 0x0E45: 0xE5, # THAI CHARACTER LAKKHANGYAO
- 0x0E46: 0xE6, # THAI CHARACTER MAIYAMOK
- 0x0E47: 0xE7, # THAI CHARACTER MAITAIKHU
- 0x0E48: 0xE8, # THAI CHARACTER MAI EK
- 0x0E49: 0xE9, # THAI CHARACTER MAI THO
- 0x0E4A: 0xEA, # THAI CHARACTER MAI TRI
- 0x0E4B: 0xEB, # THAI CHARACTER MAI CHATTAWA
- 0x0E4C: 0xEC, # THAI CHARACTER THANTHAKHAT
- 0x0E4D: 0xED, # THAI CHARACTER NIKHAHIT
- 0x0E4E: 0xEE, # THAI CHARACTER YAMAKKAN
- 0x0E4F: 0xEF, # THAI CHARACTER FONGMAN
- 0x0E50: 0xF0, # THAI DIGIT ZERO
- 0x0E51: 0xF1, # THAI DIGIT ONE
- 0x0E52: 0xF2, # THAI DIGIT TWO
- 0x0E53: 0xF3, # THAI DIGIT THREE
- 0x0E54: 0xF4, # THAI DIGIT FOUR
- 0x0E55: 0xF5, # THAI DIGIT FIVE
- 0x0E56: 0xF6, # THAI DIGIT SIX
- 0x0E57: 0xF7, # THAI DIGIT SEVEN
- 0x0E58: 0xF8, # THAI DIGIT EIGHT
- 0x0E59: 0xF9, # THAI DIGIT NINE
- 0x0E5A: 0xFA, # THAI CHARACTER ANGKHANKHU
- 0x0E5B: 0xFB, # THAI CHARACTER KHOMUT
- 0x2013: 0x96, # EN DASH
- 0x2014: 0x97, # EM DASH
- 0x2018: 0x91, # LEFT SINGLE QUOTATION MARK
- 0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK
- 0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK
- 0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK
- 0x2022: 0x95, # BULLET
- 0x2026: 0x85, # HORIZONTAL ELLIPSIS
- 0x20AC: 0x80, # EURO SIGN
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/cp875.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/cp875.py (original)
+++ python/branches/p3yk/Lib/encodings/cp875.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,257 +303,5 @@
u'\x9f' # 0xFF -> CONTROL
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x37, # END OF TRANSMISSION
- 0x0005: 0x2D, # ENQUIRY
- 0x0006: 0x2E, # ACKNOWLEDGE
- 0x0007: 0x2F, # BELL
- 0x0008: 0x16, # BACKSPACE
- 0x0009: 0x05, # HORIZONTAL TABULATION
- 0x000A: 0x25, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x3C, # DEVICE CONTROL FOUR
- 0x0015: 0x3D, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x32, # SYNCHRONOUS IDLE
- 0x0017: 0x26, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: None, # SUBSTITUTE
- 0x001B: 0x27, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x40, # SPACE
- 0x0021: 0x4F, # EXCLAMATION MARK
- 0x0022: 0x7F, # QUOTATION MARK
- 0x0023: 0x7B, # NUMBER SIGN
- 0x0024: 0x5B, # DOLLAR SIGN
- 0x0025: 0x6C, # PERCENT SIGN
- 0x0026: 0x50, # AMPERSAND
- 0x0027: 0x7D, # APOSTROPHE
- 0x0028: 0x4D, # LEFT PARENTHESIS
- 0x0029: 0x5D, # RIGHT PARENTHESIS
- 0x002A: 0x5C, # ASTERISK
- 0x002B: 0x4E, # PLUS SIGN
- 0x002C: 0x6B, # COMMA
- 0x002D: 0x60, # HYPHEN-MINUS
- 0x002E: 0x4B, # FULL STOP
- 0x002F: 0x61, # SOLIDUS
- 0x0030: 0xF0, # DIGIT ZERO
- 0x0031: 0xF1, # DIGIT ONE
- 0x0032: 0xF2, # DIGIT TWO
- 0x0033: 0xF3, # DIGIT THREE
- 0x0034: 0xF4, # DIGIT FOUR
- 0x0035: 0xF5, # DIGIT FIVE
- 0x0036: 0xF6, # DIGIT SIX
- 0x0037: 0xF7, # DIGIT SEVEN
- 0x0038: 0xF8, # DIGIT EIGHT
- 0x0039: 0xF9, # DIGIT NINE
- 0x003A: 0x7A, # COLON
- 0x003B: 0x5E, # SEMICOLON
- 0x003C: 0x4C, # LESS-THAN SIGN
- 0x003D: 0x7E, # EQUALS SIGN
- 0x003E: 0x6E, # GREATER-THAN SIGN
- 0x003F: 0x6F, # QUESTION MARK
- 0x0040: 0x7C, # COMMERCIAL AT
- 0x0041: 0xC1, # LATIN CAPITAL LETTER A
- 0x0042: 0xC2, # LATIN CAPITAL LETTER B
- 0x0043: 0xC3, # LATIN CAPITAL LETTER C
- 0x0044: 0xC4, # LATIN CAPITAL LETTER D
- 0x0045: 0xC5, # LATIN CAPITAL LETTER E
- 0x0046: 0xC6, # LATIN CAPITAL LETTER F
- 0x0047: 0xC7, # LATIN CAPITAL LETTER G
- 0x0048: 0xC8, # LATIN CAPITAL LETTER H
- 0x0049: 0xC9, # LATIN CAPITAL LETTER I
- 0x004A: 0xD1, # LATIN CAPITAL LETTER J
- 0x004B: 0xD2, # LATIN CAPITAL LETTER K
- 0x004C: 0xD3, # LATIN CAPITAL LETTER L
- 0x004D: 0xD4, # LATIN CAPITAL LETTER M
- 0x004E: 0xD5, # LATIN CAPITAL LETTER N
- 0x004F: 0xD6, # LATIN CAPITAL LETTER O
- 0x0050: 0xD7, # LATIN CAPITAL LETTER P
- 0x0051: 0xD8, # LATIN CAPITAL LETTER Q
- 0x0052: 0xD9, # LATIN CAPITAL LETTER R
- 0x0053: 0xE2, # LATIN CAPITAL LETTER S
- 0x0054: 0xE3, # LATIN CAPITAL LETTER T
- 0x0055: 0xE4, # LATIN CAPITAL LETTER U
- 0x0056: 0xE5, # LATIN CAPITAL LETTER V
- 0x0057: 0xE6, # LATIN CAPITAL LETTER W
- 0x0058: 0xE7, # LATIN CAPITAL LETTER X
- 0x0059: 0xE8, # LATIN CAPITAL LETTER Y
- 0x005A: 0xE9, # LATIN CAPITAL LETTER Z
- 0x005B: 0x4A, # LEFT SQUARE BRACKET
- 0x005C: 0xE0, # REVERSE SOLIDUS
- 0x005D: 0x5A, # RIGHT SQUARE BRACKET
- 0x005E: 0x5F, # CIRCUMFLEX ACCENT
- 0x005F: 0x6D, # LOW LINE
- 0x0060: 0x79, # GRAVE ACCENT
- 0x0061: 0x81, # LATIN SMALL LETTER A
- 0x0062: 0x82, # LATIN SMALL LETTER B
- 0x0063: 0x83, # LATIN SMALL LETTER C
- 0x0064: 0x84, # LATIN SMALL LETTER D
- 0x0065: 0x85, # LATIN SMALL LETTER E
- 0x0066: 0x86, # LATIN SMALL LETTER F
- 0x0067: 0x87, # LATIN SMALL LETTER G
- 0x0068: 0x88, # LATIN SMALL LETTER H
- 0x0069: 0x89, # LATIN SMALL LETTER I
- 0x006A: 0x91, # LATIN SMALL LETTER J
- 0x006B: 0x92, # LATIN SMALL LETTER K
- 0x006C: 0x93, # LATIN SMALL LETTER L
- 0x006D: 0x94, # LATIN SMALL LETTER M
- 0x006E: 0x95, # LATIN SMALL LETTER N
- 0x006F: 0x96, # LATIN SMALL LETTER O
- 0x0070: 0x97, # LATIN SMALL LETTER P
- 0x0071: 0x98, # LATIN SMALL LETTER Q
- 0x0072: 0x99, # LATIN SMALL LETTER R
- 0x0073: 0xA2, # LATIN SMALL LETTER S
- 0x0074: 0xA3, # LATIN SMALL LETTER T
- 0x0075: 0xA4, # LATIN SMALL LETTER U
- 0x0076: 0xA5, # LATIN SMALL LETTER V
- 0x0077: 0xA6, # LATIN SMALL LETTER W
- 0x0078: 0xA7, # LATIN SMALL LETTER X
- 0x0079: 0xA8, # LATIN SMALL LETTER Y
- 0x007A: 0xA9, # LATIN SMALL LETTER Z
- 0x007B: 0xC0, # LEFT CURLY BRACKET
- 0x007C: 0x6A, # VERTICAL LINE
- 0x007D: 0xD0, # RIGHT CURLY BRACKET
- 0x007E: 0xA1, # TILDE
- 0x007F: 0x07, # DELETE
- 0x0080: 0x20, # CONTROL
- 0x0081: 0x21, # CONTROL
- 0x0082: 0x22, # CONTROL
- 0x0083: 0x23, # CONTROL
- 0x0084: 0x24, # CONTROL
- 0x0085: 0x15, # CONTROL
- 0x0086: 0x06, # CONTROL
- 0x0087: 0x17, # CONTROL
- 0x0088: 0x28, # CONTROL
- 0x0089: 0x29, # CONTROL
- 0x008A: 0x2A, # CONTROL
- 0x008B: 0x2B, # CONTROL
- 0x008C: 0x2C, # CONTROL
- 0x008D: 0x09, # CONTROL
- 0x008E: 0x0A, # CONTROL
- 0x008F: 0x1B, # CONTROL
- 0x0090: 0x30, # CONTROL
- 0x0091: 0x31, # CONTROL
- 0x0092: 0x1A, # CONTROL
- 0x0093: 0x33, # CONTROL
- 0x0094: 0x34, # CONTROL
- 0x0095: 0x35, # CONTROL
- 0x0096: 0x36, # CONTROL
- 0x0097: 0x08, # CONTROL
- 0x0098: 0x38, # CONTROL
- 0x0099: 0x39, # CONTROL
- 0x009A: 0x3A, # CONTROL
- 0x009B: 0x3B, # CONTROL
- 0x009C: 0x04, # CONTROL
- 0x009D: 0x14, # CONTROL
- 0x009E: 0x3E, # CONTROL
- 0x009F: 0xFF, # CONTROL
- 0x00A0: 0x74, # NO-BREAK SPACE
- 0x00A3: 0xB0, # POUND SIGN
- 0x00A6: 0xDF, # BROKEN BAR
- 0x00A7: 0xEB, # SECTION SIGN
- 0x00A8: 0x70, # DIAERESIS
- 0x00A9: 0xFB, # COPYRIGHT SIGN
- 0x00AB: 0xEE, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xEF, # NOT SIGN
- 0x00AD: 0xCA, # SOFT HYPHEN
- 0x00B0: 0x90, # DEGREE SIGN
- 0x00B1: 0xDA, # PLUS-MINUS SIGN
- 0x00B2: 0xEA, # SUPERSCRIPT TWO
- 0x00B3: 0xFA, # SUPERSCRIPT THREE
- 0x00B4: 0xA0, # ACUTE ACCENT
- 0x00BB: 0xFE, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BD: 0xDB, # VULGAR FRACTION ONE HALF
- 0x0385: 0x80, # GREEK DIALYTIKA TONOS
- 0x0386: 0x71, # GREEK CAPITAL LETTER ALPHA WITH TONOS
- 0x0387: 0xDD, # GREEK ANO TELEIA
- 0x0388: 0x72, # GREEK CAPITAL LETTER EPSILON WITH TONOS
- 0x0389: 0x73, # GREEK CAPITAL LETTER ETA WITH TONOS
- 0x038A: 0x75, # GREEK CAPITAL LETTER IOTA WITH TONOS
- 0x038C: 0x76, # GREEK CAPITAL LETTER OMICRON WITH TONOS
- 0x038E: 0x77, # GREEK CAPITAL LETTER UPSILON WITH TONOS
- 0x038F: 0x78, # GREEK CAPITAL LETTER OMEGA WITH TONOS
- 0x0390: 0xCC, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
- 0x0391: 0x41, # GREEK CAPITAL LETTER ALPHA
- 0x0392: 0x42, # GREEK CAPITAL LETTER BETA
- 0x0393: 0x43, # GREEK CAPITAL LETTER GAMMA
- 0x0394: 0x44, # GREEK CAPITAL LETTER DELTA
- 0x0395: 0x45, # GREEK CAPITAL LETTER EPSILON
- 0x0396: 0x46, # GREEK CAPITAL LETTER ZETA
- 0x0397: 0x47, # GREEK CAPITAL LETTER ETA
- 0x0398: 0x48, # GREEK CAPITAL LETTER THETA
- 0x0399: 0x49, # GREEK CAPITAL LETTER IOTA
- 0x039A: 0x51, # GREEK CAPITAL LETTER KAPPA
- 0x039B: 0x52, # GREEK CAPITAL LETTER LAMDA
- 0x039C: 0x53, # GREEK CAPITAL LETTER MU
- 0x039D: 0x54, # GREEK CAPITAL LETTER NU
- 0x039E: 0x55, # GREEK CAPITAL LETTER XI
- 0x039F: 0x56, # GREEK CAPITAL LETTER OMICRON
- 0x03A0: 0x57, # GREEK CAPITAL LETTER PI
- 0x03A1: 0x58, # GREEK CAPITAL LETTER RHO
- 0x03A3: 0x59, # GREEK CAPITAL LETTER SIGMA
- 0x03A4: 0x62, # GREEK CAPITAL LETTER TAU
- 0x03A5: 0x63, # GREEK CAPITAL LETTER UPSILON
- 0x03A6: 0x64, # GREEK CAPITAL LETTER PHI
- 0x03A7: 0x65, # GREEK CAPITAL LETTER CHI
- 0x03A8: 0x66, # GREEK CAPITAL LETTER PSI
- 0x03A9: 0x67, # GREEK CAPITAL LETTER OMEGA
- 0x03AA: 0x68, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
- 0x03AB: 0x69, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
- 0x03AC: 0xB1, # GREEK SMALL LETTER ALPHA WITH TONOS
- 0x03AD: 0xB2, # GREEK SMALL LETTER EPSILON WITH TONOS
- 0x03AE: 0xB3, # GREEK SMALL LETTER ETA WITH TONOS
- 0x03AF: 0xB5, # GREEK SMALL LETTER IOTA WITH TONOS
- 0x03B0: 0xCD, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
- 0x03B1: 0x8A, # GREEK SMALL LETTER ALPHA
- 0x03B2: 0x8B, # GREEK SMALL LETTER BETA
- 0x03B3: 0x8C, # GREEK SMALL LETTER GAMMA
- 0x03B4: 0x8D, # GREEK SMALL LETTER DELTA
- 0x03B5: 0x8E, # GREEK SMALL LETTER EPSILON
- 0x03B6: 0x8F, # GREEK SMALL LETTER ZETA
- 0x03B7: 0x9A, # GREEK SMALL LETTER ETA
- 0x03B8: 0x9B, # GREEK SMALL LETTER THETA
- 0x03B9: 0x9C, # GREEK SMALL LETTER IOTA
- 0x03BA: 0x9D, # GREEK SMALL LETTER KAPPA
- 0x03BB: 0x9E, # GREEK SMALL LETTER LAMDA
- 0x03BC: 0x9F, # GREEK SMALL LETTER MU
- 0x03BD: 0xAA, # GREEK SMALL LETTER NU
- 0x03BE: 0xAB, # GREEK SMALL LETTER XI
- 0x03BF: 0xAC, # GREEK SMALL LETTER OMICRON
- 0x03C0: 0xAD, # GREEK SMALL LETTER PI
- 0x03C1: 0xAE, # GREEK SMALL LETTER RHO
- 0x03C2: 0xBA, # GREEK SMALL LETTER FINAL SIGMA
- 0x03C3: 0xAF, # GREEK SMALL LETTER SIGMA
- 0x03C4: 0xBB, # GREEK SMALL LETTER TAU
- 0x03C5: 0xBC, # GREEK SMALL LETTER UPSILON
- 0x03C6: 0xBD, # GREEK SMALL LETTER PHI
- 0x03C7: 0xBE, # GREEK SMALL LETTER CHI
- 0x03C8: 0xBF, # GREEK SMALL LETTER PSI
- 0x03C9: 0xCB, # GREEK SMALL LETTER OMEGA
- 0x03CA: 0xB4, # GREEK SMALL LETTER IOTA WITH DIALYTIKA
- 0x03CB: 0xB8, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
- 0x03CC: 0xB6, # GREEK SMALL LETTER OMICRON WITH TONOS
- 0x03CD: 0xB7, # GREEK SMALL LETTER UPSILON WITH TONOS
- 0x03CE: 0xB9, # GREEK SMALL LETTER OMEGA WITH TONOS
- 0x2015: 0xCF, # HORIZONTAL BAR
- 0x2018: 0xCE, # LEFT SINGLE QUOTATION MARK
- 0x2019: 0xDE, # RIGHT SINGLE QUOTATION MARK
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/iso8859_1.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/iso8859_1.py (original)
+++ python/branches/p3yk/Lib/encodings/iso8859_1.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x0080: 0x80, # <control>
- 0x0081: 0x81, # <control>
- 0x0082: 0x82, # <control>
- 0x0083: 0x83, # <control>
- 0x0084: 0x84, # <control>
- 0x0085: 0x85, # <control>
- 0x0086: 0x86, # <control>
- 0x0087: 0x87, # <control>
- 0x0088: 0x88, # <control>
- 0x0089: 0x89, # <control>
- 0x008A: 0x8A, # <control>
- 0x008B: 0x8B, # <control>
- 0x008C: 0x8C, # <control>
- 0x008D: 0x8D, # <control>
- 0x008E: 0x8E, # <control>
- 0x008F: 0x8F, # <control>
- 0x0090: 0x90, # <control>
- 0x0091: 0x91, # <control>
- 0x0092: 0x92, # <control>
- 0x0093: 0x93, # <control>
- 0x0094: 0x94, # <control>
- 0x0095: 0x95, # <control>
- 0x0096: 0x96, # <control>
- 0x0097: 0x97, # <control>
- 0x0098: 0x98, # <control>
- 0x0099: 0x99, # <control>
- 0x009A: 0x9A, # <control>
- 0x009B: 0x9B, # <control>
- 0x009C: 0x9C, # <control>
- 0x009D: 0x9D, # <control>
- 0x009E: 0x9E, # <control>
- 0x009F: 0x9F, # <control>
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A1: 0xA1, # INVERTED EXCLAMATION MARK
- 0x00A2: 0xA2, # CENT SIGN
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A4: 0xA4, # CURRENCY SIGN
- 0x00A5: 0xA5, # YEN SIGN
- 0x00A6: 0xA6, # BROKEN BAR
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00A8: 0xA8, # DIAERESIS
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AA: 0xAA, # FEMININE ORDINAL INDICATOR
- 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xAC, # NOT SIGN
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00AE: 0xAE, # REGISTERED SIGN
- 0x00AF: 0xAF, # MACRON
- 0x00B0: 0xB0, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B2: 0xB2, # SUPERSCRIPT TWO
- 0x00B3: 0xB3, # SUPERSCRIPT THREE
- 0x00B4: 0xB4, # ACUTE ACCENT
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00B7: 0xB7, # MIDDLE DOT
- 0x00B8: 0xB8, # CEDILLA
- 0x00B9: 0xB9, # SUPERSCRIPT ONE
- 0x00BA: 0xBA, # MASCULINE ORDINAL INDICATOR
- 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER
- 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF
- 0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS
- 0x00BF: 0xBF, # INVERTED QUESTION MARK
- 0x00C0: 0xC0, # LATIN CAPITAL LETTER A WITH GRAVE
- 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C3: 0xC3, # LATIN CAPITAL LETTER A WITH TILDE
- 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE
- 0x00C6: 0xC6, # LATIN CAPITAL LETTER AE
- 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C8: 0xC8, # LATIN CAPITAL LETTER E WITH GRAVE
- 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CA: 0xCA, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
- 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CC: 0xCC, # LATIN CAPITAL LETTER I WITH GRAVE
- 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS
- 0x00D0: 0xD0, # LATIN CAPITAL LETTER ETH (Icelandic)
- 0x00D1: 0xD1, # LATIN CAPITAL LETTER N WITH TILDE
- 0x00D2: 0xD2, # LATIN CAPITAL LETTER O WITH GRAVE
- 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE
- 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D7: 0xD7, # MULTIPLICATION SIGN
- 0x00D8: 0xD8, # LATIN CAPITAL LETTER O WITH STROKE
- 0x00D9: 0xD9, # LATIN CAPITAL LETTER U WITH GRAVE
- 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
- 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DD: 0xDD, # LATIN CAPITAL LETTER Y WITH ACUTE
- 0x00DE: 0xDE, # LATIN CAPITAL LETTER THORN (Icelandic)
- 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S (German)
- 0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E3: 0xE3, # LATIN SMALL LETTER A WITH TILDE
- 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE
- 0x00E6: 0xE6, # LATIN SMALL LETTER AE
- 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00EC: 0xEC, # LATIN SMALL LETTER I WITH GRAVE
- 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F0: 0xF0, # LATIN SMALL LETTER ETH (Icelandic)
- 0x00F1: 0xF1, # LATIN SMALL LETTER N WITH TILDE
- 0x00F2: 0xF2, # LATIN SMALL LETTER O WITH GRAVE
- 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE
- 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xF7, # DIVISION SIGN
- 0x00F8: 0xF8, # LATIN SMALL LETTER O WITH STROKE
- 0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x00FD: 0xFD, # LATIN SMALL LETTER Y WITH ACUTE
- 0x00FE: 0xFE, # LATIN SMALL LETTER THORN (Icelandic)
- 0x00FF: 0xFF, # LATIN SMALL LETTER Y WITH DIAERESIS
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/iso8859_10.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/iso8859_10.py (original)
+++ python/branches/p3yk/Lib/encodings/iso8859_10.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\u0138' # 0xFF -> LATIN SMALL LETTER KRA
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x0080: 0x80, # <control>
- 0x0081: 0x81, # <control>
- 0x0082: 0x82, # <control>
- 0x0083: 0x83, # <control>
- 0x0084: 0x84, # <control>
- 0x0085: 0x85, # <control>
- 0x0086: 0x86, # <control>
- 0x0087: 0x87, # <control>
- 0x0088: 0x88, # <control>
- 0x0089: 0x89, # <control>
- 0x008A: 0x8A, # <control>
- 0x008B: 0x8B, # <control>
- 0x008C: 0x8C, # <control>
- 0x008D: 0x8D, # <control>
- 0x008E: 0x8E, # <control>
- 0x008F: 0x8F, # <control>
- 0x0090: 0x90, # <control>
- 0x0091: 0x91, # <control>
- 0x0092: 0x92, # <control>
- 0x0093: 0x93, # <control>
- 0x0094: 0x94, # <control>
- 0x0095: 0x95, # <control>
- 0x0096: 0x96, # <control>
- 0x0097: 0x97, # <control>
- 0x0098: 0x98, # <control>
- 0x0099: 0x99, # <control>
- 0x009A: 0x9A, # <control>
- 0x009B: 0x9B, # <control>
- 0x009C: 0x9C, # <control>
- 0x009D: 0x9D, # <control>
- 0x009E: 0x9E, # <control>
- 0x009F: 0x9F, # <control>
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00B0: 0xB0, # DEGREE SIGN
- 0x00B7: 0xB7, # MIDDLE DOT
- 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C3: 0xC3, # LATIN CAPITAL LETTER A WITH TILDE
- 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE
- 0x00C6: 0xC6, # LATIN CAPITAL LETTER AE
- 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS
- 0x00D0: 0xD0, # LATIN CAPITAL LETTER ETH (Icelandic)
- 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE
- 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D8: 0xD8, # LATIN CAPITAL LETTER O WITH STROKE
- 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
- 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DD: 0xDD, # LATIN CAPITAL LETTER Y WITH ACUTE
- 0x00DE: 0xDE, # LATIN CAPITAL LETTER THORN (Icelandic)
- 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S (German)
- 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E3: 0xE3, # LATIN SMALL LETTER A WITH TILDE
- 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE
- 0x00E6: 0xE6, # LATIN SMALL LETTER AE
- 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F0: 0xF0, # LATIN SMALL LETTER ETH (Icelandic)
- 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE
- 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F8: 0xF8, # LATIN SMALL LETTER O WITH STROKE
- 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x00FD: 0xFD, # LATIN SMALL LETTER Y WITH ACUTE
- 0x00FE: 0xFE, # LATIN SMALL LETTER THORN (Icelandic)
- 0x0100: 0xC0, # LATIN CAPITAL LETTER A WITH MACRON
- 0x0101: 0xE0, # LATIN SMALL LETTER A WITH MACRON
- 0x0104: 0xA1, # LATIN CAPITAL LETTER A WITH OGONEK
- 0x0105: 0xB1, # LATIN SMALL LETTER A WITH OGONEK
- 0x010C: 0xC8, # LATIN CAPITAL LETTER C WITH CARON
- 0x010D: 0xE8, # LATIN SMALL LETTER C WITH CARON
- 0x0110: 0xA9, # LATIN CAPITAL LETTER D WITH STROKE
- 0x0111: 0xB9, # LATIN SMALL LETTER D WITH STROKE
- 0x0112: 0xA2, # LATIN CAPITAL LETTER E WITH MACRON
- 0x0113: 0xB2, # LATIN SMALL LETTER E WITH MACRON
- 0x0116: 0xCC, # LATIN CAPITAL LETTER E WITH DOT ABOVE
- 0x0117: 0xEC, # LATIN SMALL LETTER E WITH DOT ABOVE
- 0x0118: 0xCA, # LATIN CAPITAL LETTER E WITH OGONEK
- 0x0119: 0xEA, # LATIN SMALL LETTER E WITH OGONEK
- 0x0122: 0xA3, # LATIN CAPITAL LETTER G WITH CEDILLA
- 0x0123: 0xB3, # LATIN SMALL LETTER G WITH CEDILLA
- 0x0128: 0xA5, # LATIN CAPITAL LETTER I WITH TILDE
- 0x0129: 0xB5, # LATIN SMALL LETTER I WITH TILDE
- 0x012A: 0xA4, # LATIN CAPITAL LETTER I WITH MACRON
- 0x012B: 0xB4, # LATIN SMALL LETTER I WITH MACRON
- 0x012E: 0xC7, # LATIN CAPITAL LETTER I WITH OGONEK
- 0x012F: 0xE7, # LATIN SMALL LETTER I WITH OGONEK
- 0x0136: 0xA6, # LATIN CAPITAL LETTER K WITH CEDILLA
- 0x0137: 0xB6, # LATIN SMALL LETTER K WITH CEDILLA
- 0x0138: 0xFF, # LATIN SMALL LETTER KRA
- 0x013B: 0xA8, # LATIN CAPITAL LETTER L WITH CEDILLA
- 0x013C: 0xB8, # LATIN SMALL LETTER L WITH CEDILLA
- 0x0145: 0xD1, # LATIN CAPITAL LETTER N WITH CEDILLA
- 0x0146: 0xF1, # LATIN SMALL LETTER N WITH CEDILLA
- 0x014A: 0xAF, # LATIN CAPITAL LETTER ENG
- 0x014B: 0xBF, # LATIN SMALL LETTER ENG
- 0x014C: 0xD2, # LATIN CAPITAL LETTER O WITH MACRON
- 0x014D: 0xF2, # LATIN SMALL LETTER O WITH MACRON
- 0x0160: 0xAA, # LATIN CAPITAL LETTER S WITH CARON
- 0x0161: 0xBA, # LATIN SMALL LETTER S WITH CARON
- 0x0166: 0xAB, # LATIN CAPITAL LETTER T WITH STROKE
- 0x0167: 0xBB, # LATIN SMALL LETTER T WITH STROKE
- 0x0168: 0xD7, # LATIN CAPITAL LETTER U WITH TILDE
- 0x0169: 0xF7, # LATIN SMALL LETTER U WITH TILDE
- 0x016A: 0xAE, # LATIN CAPITAL LETTER U WITH MACRON
- 0x016B: 0xBE, # LATIN SMALL LETTER U WITH MACRON
- 0x0172: 0xD9, # LATIN CAPITAL LETTER U WITH OGONEK
- 0x0173: 0xF9, # LATIN SMALL LETTER U WITH OGONEK
- 0x017D: 0xAC, # LATIN CAPITAL LETTER Z WITH CARON
- 0x017E: 0xBC, # LATIN SMALL LETTER Z WITH CARON
- 0x2015: 0xBD, # HORIZONTAL BAR
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/iso8859_11.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/iso8859_11.py (original)
+++ python/branches/p3yk/Lib/encodings/iso8859_11.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,255 +303,5 @@
u'\ufffe'
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x0080: 0x80, # <control>
- 0x0081: 0x81, # <control>
- 0x0082: 0x82, # <control>
- 0x0083: 0x83, # <control>
- 0x0084: 0x84, # <control>
- 0x0085: 0x85, # <control>
- 0x0086: 0x86, # <control>
- 0x0087: 0x87, # <control>
- 0x0088: 0x88, # <control>
- 0x0089: 0x89, # <control>
- 0x008A: 0x8A, # <control>
- 0x008B: 0x8B, # <control>
- 0x008C: 0x8C, # <control>
- 0x008D: 0x8D, # <control>
- 0x008E: 0x8E, # <control>
- 0x008F: 0x8F, # <control>
- 0x0090: 0x90, # <control>
- 0x0091: 0x91, # <control>
- 0x0092: 0x92, # <control>
- 0x0093: 0x93, # <control>
- 0x0094: 0x94, # <control>
- 0x0095: 0x95, # <control>
- 0x0096: 0x96, # <control>
- 0x0097: 0x97, # <control>
- 0x0098: 0x98, # <control>
- 0x0099: 0x99, # <control>
- 0x009A: 0x9A, # <control>
- 0x009B: 0x9B, # <control>
- 0x009C: 0x9C, # <control>
- 0x009D: 0x9D, # <control>
- 0x009E: 0x9E, # <control>
- 0x009F: 0x9F, # <control>
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x0E01: 0xA1, # THAI CHARACTER KO KAI
- 0x0E02: 0xA2, # THAI CHARACTER KHO KHAI
- 0x0E03: 0xA3, # THAI CHARACTER KHO KHUAT
- 0x0E04: 0xA4, # THAI CHARACTER KHO KHWAI
- 0x0E05: 0xA5, # THAI CHARACTER KHO KHON
- 0x0E06: 0xA6, # THAI CHARACTER KHO RAKHANG
- 0x0E07: 0xA7, # THAI CHARACTER NGO NGU
- 0x0E08: 0xA8, # THAI CHARACTER CHO CHAN
- 0x0E09: 0xA9, # THAI CHARACTER CHO CHING
- 0x0E0A: 0xAA, # THAI CHARACTER CHO CHANG
- 0x0E0B: 0xAB, # THAI CHARACTER SO SO
- 0x0E0C: 0xAC, # THAI CHARACTER CHO CHOE
- 0x0E0D: 0xAD, # THAI CHARACTER YO YING
- 0x0E0E: 0xAE, # THAI CHARACTER DO CHADA
- 0x0E0F: 0xAF, # THAI CHARACTER TO PATAK
- 0x0E10: 0xB0, # THAI CHARACTER THO THAN
- 0x0E11: 0xB1, # THAI CHARACTER THO NANGMONTHO
- 0x0E12: 0xB2, # THAI CHARACTER THO PHUTHAO
- 0x0E13: 0xB3, # THAI CHARACTER NO NEN
- 0x0E14: 0xB4, # THAI CHARACTER DO DEK
- 0x0E15: 0xB5, # THAI CHARACTER TO TAO
- 0x0E16: 0xB6, # THAI CHARACTER THO THUNG
- 0x0E17: 0xB7, # THAI CHARACTER THO THAHAN
- 0x0E18: 0xB8, # THAI CHARACTER THO THONG
- 0x0E19: 0xB9, # THAI CHARACTER NO NU
- 0x0E1A: 0xBA, # THAI CHARACTER BO BAIMAI
- 0x0E1B: 0xBB, # THAI CHARACTER PO PLA
- 0x0E1C: 0xBC, # THAI CHARACTER PHO PHUNG
- 0x0E1D: 0xBD, # THAI CHARACTER FO FA
- 0x0E1E: 0xBE, # THAI CHARACTER PHO PHAN
- 0x0E1F: 0xBF, # THAI CHARACTER FO FAN
- 0x0E20: 0xC0, # THAI CHARACTER PHO SAMPHAO
- 0x0E21: 0xC1, # THAI CHARACTER MO MA
- 0x0E22: 0xC2, # THAI CHARACTER YO YAK
- 0x0E23: 0xC3, # THAI CHARACTER RO RUA
- 0x0E24: 0xC4, # THAI CHARACTER RU
- 0x0E25: 0xC5, # THAI CHARACTER LO LING
- 0x0E26: 0xC6, # THAI CHARACTER LU
- 0x0E27: 0xC7, # THAI CHARACTER WO WAEN
- 0x0E28: 0xC8, # THAI CHARACTER SO SALA
- 0x0E29: 0xC9, # THAI CHARACTER SO RUSI
- 0x0E2A: 0xCA, # THAI CHARACTER SO SUA
- 0x0E2B: 0xCB, # THAI CHARACTER HO HIP
- 0x0E2C: 0xCC, # THAI CHARACTER LO CHULA
- 0x0E2D: 0xCD, # THAI CHARACTER O ANG
- 0x0E2E: 0xCE, # THAI CHARACTER HO NOKHUK
- 0x0E2F: 0xCF, # THAI CHARACTER PAIYANNOI
- 0x0E30: 0xD0, # THAI CHARACTER SARA A
- 0x0E31: 0xD1, # THAI CHARACTER MAI HAN-AKAT
- 0x0E32: 0xD2, # THAI CHARACTER SARA AA
- 0x0E33: 0xD3, # THAI CHARACTER SARA AM
- 0x0E34: 0xD4, # THAI CHARACTER SARA I
- 0x0E35: 0xD5, # THAI CHARACTER SARA II
- 0x0E36: 0xD6, # THAI CHARACTER SARA UE
- 0x0E37: 0xD7, # THAI CHARACTER SARA UEE
- 0x0E38: 0xD8, # THAI CHARACTER SARA U
- 0x0E39: 0xD9, # THAI CHARACTER SARA UU
- 0x0E3A: 0xDA, # THAI CHARACTER PHINTHU
- 0x0E3F: 0xDF, # THAI CURRENCY SYMBOL BAHT
- 0x0E40: 0xE0, # THAI CHARACTER SARA E
- 0x0E41: 0xE1, # THAI CHARACTER SARA AE
- 0x0E42: 0xE2, # THAI CHARACTER SARA O
- 0x0E43: 0xE3, # THAI CHARACTER SARA AI MAIMUAN
- 0x0E44: 0xE4, # THAI CHARACTER SARA AI MAIMALAI
- 0x0E45: 0xE5, # THAI CHARACTER LAKKHANGYAO
- 0x0E46: 0xE6, # THAI CHARACTER MAIYAMOK
- 0x0E47: 0xE7, # THAI CHARACTER MAITAIKHU
- 0x0E48: 0xE8, # THAI CHARACTER MAI EK
- 0x0E49: 0xE9, # THAI CHARACTER MAI THO
- 0x0E4A: 0xEA, # THAI CHARACTER MAI TRI
- 0x0E4B: 0xEB, # THAI CHARACTER MAI CHATTAWA
- 0x0E4C: 0xEC, # THAI CHARACTER THANTHAKHAT
- 0x0E4D: 0xED, # THAI CHARACTER NIKHAHIT
- 0x0E4E: 0xEE, # THAI CHARACTER YAMAKKAN
- 0x0E4F: 0xEF, # THAI CHARACTER FONGMAN
- 0x0E50: 0xF0, # THAI DIGIT ZERO
- 0x0E51: 0xF1, # THAI DIGIT ONE
- 0x0E52: 0xF2, # THAI DIGIT TWO
- 0x0E53: 0xF3, # THAI DIGIT THREE
- 0x0E54: 0xF4, # THAI DIGIT FOUR
- 0x0E55: 0xF5, # THAI DIGIT FIVE
- 0x0E56: 0xF6, # THAI DIGIT SIX
- 0x0E57: 0xF7, # THAI DIGIT SEVEN
- 0x0E58: 0xF8, # THAI DIGIT EIGHT
- 0x0E59: 0xF9, # THAI DIGIT NINE
- 0x0E5A: 0xFA, # THAI CHARACTER ANGKHANKHU
- 0x0E5B: 0xFB, # THAI CHARACTER KHOMUT
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/iso8859_13.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/iso8859_13.py (original)
+++ python/branches/p3yk/Lib/encodings/iso8859_13.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\u2019' # 0xFF -> RIGHT SINGLE QUOTATION MARK
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x0080: 0x80, # <control>
- 0x0081: 0x81, # <control>
- 0x0082: 0x82, # <control>
- 0x0083: 0x83, # <control>
- 0x0084: 0x84, # <control>
- 0x0085: 0x85, # <control>
- 0x0086: 0x86, # <control>
- 0x0087: 0x87, # <control>
- 0x0088: 0x88, # <control>
- 0x0089: 0x89, # <control>
- 0x008A: 0x8A, # <control>
- 0x008B: 0x8B, # <control>
- 0x008C: 0x8C, # <control>
- 0x008D: 0x8D, # <control>
- 0x008E: 0x8E, # <control>
- 0x008F: 0x8F, # <control>
- 0x0090: 0x90, # <control>
- 0x0091: 0x91, # <control>
- 0x0092: 0x92, # <control>
- 0x0093: 0x93, # <control>
- 0x0094: 0x94, # <control>
- 0x0095: 0x95, # <control>
- 0x0096: 0x96, # <control>
- 0x0097: 0x97, # <control>
- 0x0098: 0x98, # <control>
- 0x0099: 0x99, # <control>
- 0x009A: 0x9A, # <control>
- 0x009B: 0x9B, # <control>
- 0x009C: 0x9C, # <control>
- 0x009D: 0x9D, # <control>
- 0x009E: 0x9E, # <control>
- 0x009F: 0x9F, # <control>
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A2: 0xA2, # CENT SIGN
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A4: 0xA4, # CURRENCY SIGN
- 0x00A6: 0xA6, # BROKEN BAR
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xAC, # NOT SIGN
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00AE: 0xAE, # REGISTERED SIGN
- 0x00B0: 0xB0, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B2: 0xB2, # SUPERSCRIPT TWO
- 0x00B3: 0xB3, # SUPERSCRIPT THREE
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00B7: 0xB7, # MIDDLE DOT
- 0x00B9: 0xB9, # SUPERSCRIPT ONE
- 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER
- 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF
- 0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS
- 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE
- 0x00C6: 0xAF, # LATIN CAPITAL LETTER AE
- 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE
- 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D7: 0xD7, # MULTIPLICATION SIGN
- 0x00D8: 0xA8, # LATIN CAPITAL LETTER O WITH STROKE
- 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S (German)
- 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE
- 0x00E6: 0xBF, # LATIN SMALL LETTER AE
- 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE
- 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE
- 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xF7, # DIVISION SIGN
- 0x00F8: 0xB8, # LATIN SMALL LETTER O WITH STROKE
- 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x0100: 0xC2, # LATIN CAPITAL LETTER A WITH MACRON
- 0x0101: 0xE2, # LATIN SMALL LETTER A WITH MACRON
- 0x0104: 0xC0, # LATIN CAPITAL LETTER A WITH OGONEK
- 0x0105: 0xE0, # LATIN SMALL LETTER A WITH OGONEK
- 0x0106: 0xC3, # LATIN CAPITAL LETTER C WITH ACUTE
- 0x0107: 0xE3, # LATIN SMALL LETTER C WITH ACUTE
- 0x010C: 0xC8, # LATIN CAPITAL LETTER C WITH CARON
- 0x010D: 0xE8, # LATIN SMALL LETTER C WITH CARON
- 0x0112: 0xC7, # LATIN CAPITAL LETTER E WITH MACRON
- 0x0113: 0xE7, # LATIN SMALL LETTER E WITH MACRON
- 0x0116: 0xCB, # LATIN CAPITAL LETTER E WITH DOT ABOVE
- 0x0117: 0xEB, # LATIN SMALL LETTER E WITH DOT ABOVE
- 0x0118: 0xC6, # LATIN CAPITAL LETTER E WITH OGONEK
- 0x0119: 0xE6, # LATIN SMALL LETTER E WITH OGONEK
- 0x0122: 0xCC, # LATIN CAPITAL LETTER G WITH CEDILLA
- 0x0123: 0xEC, # LATIN SMALL LETTER G WITH CEDILLA
- 0x012A: 0xCE, # LATIN CAPITAL LETTER I WITH MACRON
- 0x012B: 0xEE, # LATIN SMALL LETTER I WITH MACRON
- 0x012E: 0xC1, # LATIN CAPITAL LETTER I WITH OGONEK
- 0x012F: 0xE1, # LATIN SMALL LETTER I WITH OGONEK
- 0x0136: 0xCD, # LATIN CAPITAL LETTER K WITH CEDILLA
- 0x0137: 0xED, # LATIN SMALL LETTER K WITH CEDILLA
- 0x013B: 0xCF, # LATIN CAPITAL LETTER L WITH CEDILLA
- 0x013C: 0xEF, # LATIN SMALL LETTER L WITH CEDILLA
- 0x0141: 0xD9, # LATIN CAPITAL LETTER L WITH STROKE
- 0x0142: 0xF9, # LATIN SMALL LETTER L WITH STROKE
- 0x0143: 0xD1, # LATIN CAPITAL LETTER N WITH ACUTE
- 0x0144: 0xF1, # LATIN SMALL LETTER N WITH ACUTE
- 0x0145: 0xD2, # LATIN CAPITAL LETTER N WITH CEDILLA
- 0x0146: 0xF2, # LATIN SMALL LETTER N WITH CEDILLA
- 0x014C: 0xD4, # LATIN CAPITAL LETTER O WITH MACRON
- 0x014D: 0xF4, # LATIN SMALL LETTER O WITH MACRON
- 0x0156: 0xAA, # LATIN CAPITAL LETTER R WITH CEDILLA
- 0x0157: 0xBA, # LATIN SMALL LETTER R WITH CEDILLA
- 0x015A: 0xDA, # LATIN CAPITAL LETTER S WITH ACUTE
- 0x015B: 0xFA, # LATIN SMALL LETTER S WITH ACUTE
- 0x0160: 0xD0, # LATIN CAPITAL LETTER S WITH CARON
- 0x0161: 0xF0, # LATIN SMALL LETTER S WITH CARON
- 0x016A: 0xDB, # LATIN CAPITAL LETTER U WITH MACRON
- 0x016B: 0xFB, # LATIN SMALL LETTER U WITH MACRON
- 0x0172: 0xD8, # LATIN CAPITAL LETTER U WITH OGONEK
- 0x0173: 0xF8, # LATIN SMALL LETTER U WITH OGONEK
- 0x0179: 0xCA, # LATIN CAPITAL LETTER Z WITH ACUTE
- 0x017A: 0xEA, # LATIN SMALL LETTER Z WITH ACUTE
- 0x017B: 0xDD, # LATIN CAPITAL LETTER Z WITH DOT ABOVE
- 0x017C: 0xFD, # LATIN SMALL LETTER Z WITH DOT ABOVE
- 0x017D: 0xDE, # LATIN CAPITAL LETTER Z WITH CARON
- 0x017E: 0xFE, # LATIN SMALL LETTER Z WITH CARON
- 0x2019: 0xFF, # RIGHT SINGLE QUOTATION MARK
- 0x201C: 0xB4, # LEFT DOUBLE QUOTATION MARK
- 0x201D: 0xA1, # RIGHT DOUBLE QUOTATION MARK
- 0x201E: 0xA5, # DOUBLE LOW-9 QUOTATION MARK
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/iso8859_14.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/iso8859_14.py (original)
+++ python/branches/p3yk/Lib/encodings/iso8859_14.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x0080: 0x80, # <control>
- 0x0081: 0x81, # <control>
- 0x0082: 0x82, # <control>
- 0x0083: 0x83, # <control>
- 0x0084: 0x84, # <control>
- 0x0085: 0x85, # <control>
- 0x0086: 0x86, # <control>
- 0x0087: 0x87, # <control>
- 0x0088: 0x88, # <control>
- 0x0089: 0x89, # <control>
- 0x008A: 0x8A, # <control>
- 0x008B: 0x8B, # <control>
- 0x008C: 0x8C, # <control>
- 0x008D: 0x8D, # <control>
- 0x008E: 0x8E, # <control>
- 0x008F: 0x8F, # <control>
- 0x0090: 0x90, # <control>
- 0x0091: 0x91, # <control>
- 0x0092: 0x92, # <control>
- 0x0093: 0x93, # <control>
- 0x0094: 0x94, # <control>
- 0x0095: 0x95, # <control>
- 0x0096: 0x96, # <control>
- 0x0097: 0x97, # <control>
- 0x0098: 0x98, # <control>
- 0x0099: 0x99, # <control>
- 0x009A: 0x9A, # <control>
- 0x009B: 0x9B, # <control>
- 0x009C: 0x9C, # <control>
- 0x009D: 0x9D, # <control>
- 0x009E: 0x9E, # <control>
- 0x009F: 0x9F, # <control>
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00AE: 0xAE, # REGISTERED SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00C0: 0xC0, # LATIN CAPITAL LETTER A WITH GRAVE
- 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C3: 0xC3, # LATIN CAPITAL LETTER A WITH TILDE
- 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE
- 0x00C6: 0xC6, # LATIN CAPITAL LETTER AE
- 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C8: 0xC8, # LATIN CAPITAL LETTER E WITH GRAVE
- 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CA: 0xCA, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
- 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CC: 0xCC, # LATIN CAPITAL LETTER I WITH GRAVE
- 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS
- 0x00D1: 0xD1, # LATIN CAPITAL LETTER N WITH TILDE
- 0x00D2: 0xD2, # LATIN CAPITAL LETTER O WITH GRAVE
- 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE
- 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D8: 0xD8, # LATIN CAPITAL LETTER O WITH STROKE
- 0x00D9: 0xD9, # LATIN CAPITAL LETTER U WITH GRAVE
- 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
- 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DD: 0xDD, # LATIN CAPITAL LETTER Y WITH ACUTE
- 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S
- 0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E3: 0xE3, # LATIN SMALL LETTER A WITH TILDE
- 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE
- 0x00E6: 0xE6, # LATIN SMALL LETTER AE
- 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00EC: 0xEC, # LATIN SMALL LETTER I WITH GRAVE
- 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F1: 0xF1, # LATIN SMALL LETTER N WITH TILDE
- 0x00F2: 0xF2, # LATIN SMALL LETTER O WITH GRAVE
- 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE
- 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F8: 0xF8, # LATIN SMALL LETTER O WITH STROKE
- 0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x00FD: 0xFD, # LATIN SMALL LETTER Y WITH ACUTE
- 0x00FF: 0xFF, # LATIN SMALL LETTER Y WITH DIAERESIS
- 0x010A: 0xA4, # LATIN CAPITAL LETTER C WITH DOT ABOVE
- 0x010B: 0xA5, # LATIN SMALL LETTER C WITH DOT ABOVE
- 0x0120: 0xB2, # LATIN CAPITAL LETTER G WITH DOT ABOVE
- 0x0121: 0xB3, # LATIN SMALL LETTER G WITH DOT ABOVE
- 0x0174: 0xD0, # LATIN CAPITAL LETTER W WITH CIRCUMFLEX
- 0x0175: 0xF0, # LATIN SMALL LETTER W WITH CIRCUMFLEX
- 0x0176: 0xDE, # LATIN CAPITAL LETTER Y WITH CIRCUMFLEX
- 0x0177: 0xFE, # LATIN SMALL LETTER Y WITH CIRCUMFLEX
- 0x0178: 0xAF, # LATIN CAPITAL LETTER Y WITH DIAERESIS
- 0x1E02: 0xA1, # LATIN CAPITAL LETTER B WITH DOT ABOVE
- 0x1E03: 0xA2, # LATIN SMALL LETTER B WITH DOT ABOVE
- 0x1E0A: 0xA6, # LATIN CAPITAL LETTER D WITH DOT ABOVE
- 0x1E0B: 0xAB, # LATIN SMALL LETTER D WITH DOT ABOVE
- 0x1E1E: 0xB0, # LATIN CAPITAL LETTER F WITH DOT ABOVE
- 0x1E1F: 0xB1, # LATIN SMALL LETTER F WITH DOT ABOVE
- 0x1E40: 0xB4, # LATIN CAPITAL LETTER M WITH DOT ABOVE
- 0x1E41: 0xB5, # LATIN SMALL LETTER M WITH DOT ABOVE
- 0x1E56: 0xB7, # LATIN CAPITAL LETTER P WITH DOT ABOVE
- 0x1E57: 0xB9, # LATIN SMALL LETTER P WITH DOT ABOVE
- 0x1E60: 0xBB, # LATIN CAPITAL LETTER S WITH DOT ABOVE
- 0x1E61: 0xBF, # LATIN SMALL LETTER S WITH DOT ABOVE
- 0x1E6A: 0xD7, # LATIN CAPITAL LETTER T WITH DOT ABOVE
- 0x1E6B: 0xF7, # LATIN SMALL LETTER T WITH DOT ABOVE
- 0x1E80: 0xA8, # LATIN CAPITAL LETTER W WITH GRAVE
- 0x1E81: 0xB8, # LATIN SMALL LETTER W WITH GRAVE
- 0x1E82: 0xAA, # LATIN CAPITAL LETTER W WITH ACUTE
- 0x1E83: 0xBA, # LATIN SMALL LETTER W WITH ACUTE
- 0x1E84: 0xBD, # LATIN CAPITAL LETTER W WITH DIAERESIS
- 0x1E85: 0xBE, # LATIN SMALL LETTER W WITH DIAERESIS
- 0x1EF2: 0xAC, # LATIN CAPITAL LETTER Y WITH GRAVE
- 0x1EF3: 0xBC, # LATIN SMALL LETTER Y WITH GRAVE
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/iso8859_15.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/iso8859_15.py (original)
+++ python/branches/p3yk/Lib/encodings/iso8859_15.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x0080: 0x80, # <control>
- 0x0081: 0x81, # <control>
- 0x0082: 0x82, # <control>
- 0x0083: 0x83, # <control>
- 0x0084: 0x84, # <control>
- 0x0085: 0x85, # <control>
- 0x0086: 0x86, # <control>
- 0x0087: 0x87, # <control>
- 0x0088: 0x88, # <control>
- 0x0089: 0x89, # <control>
- 0x008A: 0x8A, # <control>
- 0x008B: 0x8B, # <control>
- 0x008C: 0x8C, # <control>
- 0x008D: 0x8D, # <control>
- 0x008E: 0x8E, # <control>
- 0x008F: 0x8F, # <control>
- 0x0090: 0x90, # <control>
- 0x0091: 0x91, # <control>
- 0x0092: 0x92, # <control>
- 0x0093: 0x93, # <control>
- 0x0094: 0x94, # <control>
- 0x0095: 0x95, # <control>
- 0x0096: 0x96, # <control>
- 0x0097: 0x97, # <control>
- 0x0098: 0x98, # <control>
- 0x0099: 0x99, # <control>
- 0x009A: 0x9A, # <control>
- 0x009B: 0x9B, # <control>
- 0x009C: 0x9C, # <control>
- 0x009D: 0x9D, # <control>
- 0x009E: 0x9E, # <control>
- 0x009F: 0x9F, # <control>
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A1: 0xA1, # INVERTED EXCLAMATION MARK
- 0x00A2: 0xA2, # CENT SIGN
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A5: 0xA5, # YEN SIGN
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AA: 0xAA, # FEMININE ORDINAL INDICATOR
- 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xAC, # NOT SIGN
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00AE: 0xAE, # REGISTERED SIGN
- 0x00AF: 0xAF, # MACRON
- 0x00B0: 0xB0, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B2: 0xB2, # SUPERSCRIPT TWO
- 0x00B3: 0xB3, # SUPERSCRIPT THREE
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00B7: 0xB7, # MIDDLE DOT
- 0x00B9: 0xB9, # SUPERSCRIPT ONE
- 0x00BA: 0xBA, # MASCULINE ORDINAL INDICATOR
- 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BF: 0xBF, # INVERTED QUESTION MARK
- 0x00C0: 0xC0, # LATIN CAPITAL LETTER A WITH GRAVE
- 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C3: 0xC3, # LATIN CAPITAL LETTER A WITH TILDE
- 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE
- 0x00C6: 0xC6, # LATIN CAPITAL LETTER AE
- 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C8: 0xC8, # LATIN CAPITAL LETTER E WITH GRAVE
- 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CA: 0xCA, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
- 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CC: 0xCC, # LATIN CAPITAL LETTER I WITH GRAVE
- 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS
- 0x00D0: 0xD0, # LATIN CAPITAL LETTER ETH
- 0x00D1: 0xD1, # LATIN CAPITAL LETTER N WITH TILDE
- 0x00D2: 0xD2, # LATIN CAPITAL LETTER O WITH GRAVE
- 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE
- 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D7: 0xD7, # MULTIPLICATION SIGN
- 0x00D8: 0xD8, # LATIN CAPITAL LETTER O WITH STROKE
- 0x00D9: 0xD9, # LATIN CAPITAL LETTER U WITH GRAVE
- 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
- 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DD: 0xDD, # LATIN CAPITAL LETTER Y WITH ACUTE
- 0x00DE: 0xDE, # LATIN CAPITAL LETTER THORN
- 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S
- 0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E3: 0xE3, # LATIN SMALL LETTER A WITH TILDE
- 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE
- 0x00E6: 0xE6, # LATIN SMALL LETTER AE
- 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00EC: 0xEC, # LATIN SMALL LETTER I WITH GRAVE
- 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F0: 0xF0, # LATIN SMALL LETTER ETH
- 0x00F1: 0xF1, # LATIN SMALL LETTER N WITH TILDE
- 0x00F2: 0xF2, # LATIN SMALL LETTER O WITH GRAVE
- 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE
- 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xF7, # DIVISION SIGN
- 0x00F8: 0xF8, # LATIN SMALL LETTER O WITH STROKE
- 0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x00FD: 0xFD, # LATIN SMALL LETTER Y WITH ACUTE
- 0x00FE: 0xFE, # LATIN SMALL LETTER THORN
- 0x00FF: 0xFF, # LATIN SMALL LETTER Y WITH DIAERESIS
- 0x0152: 0xBC, # LATIN CAPITAL LIGATURE OE
- 0x0153: 0xBD, # LATIN SMALL LIGATURE OE
- 0x0160: 0xA6, # LATIN CAPITAL LETTER S WITH CARON
- 0x0161: 0xA8, # LATIN SMALL LETTER S WITH CARON
- 0x0178: 0xBE, # LATIN CAPITAL LETTER Y WITH DIAERESIS
- 0x017D: 0xB4, # LATIN CAPITAL LETTER Z WITH CARON
- 0x017E: 0xB8, # LATIN SMALL LETTER Z WITH CARON
- 0x20AC: 0xA4, # EURO SIGN
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/iso8859_16.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/iso8859_16.py (original)
+++ python/branches/p3yk/Lib/encodings/iso8859_16.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x0080: 0x80, # <control>
- 0x0081: 0x81, # <control>
- 0x0082: 0x82, # <control>
- 0x0083: 0x83, # <control>
- 0x0084: 0x84, # <control>
- 0x0085: 0x85, # <control>
- 0x0086: 0x86, # <control>
- 0x0087: 0x87, # <control>
- 0x0088: 0x88, # <control>
- 0x0089: 0x89, # <control>
- 0x008A: 0x8A, # <control>
- 0x008B: 0x8B, # <control>
- 0x008C: 0x8C, # <control>
- 0x008D: 0x8D, # <control>
- 0x008E: 0x8E, # <control>
- 0x008F: 0x8F, # <control>
- 0x0090: 0x90, # <control>
- 0x0091: 0x91, # <control>
- 0x0092: 0x92, # <control>
- 0x0093: 0x93, # <control>
- 0x0094: 0x94, # <control>
- 0x0095: 0x95, # <control>
- 0x0096: 0x96, # <control>
- 0x0097: 0x97, # <control>
- 0x0098: 0x98, # <control>
- 0x0099: 0x99, # <control>
- 0x009A: 0x9A, # <control>
- 0x009B: 0x9B, # <control>
- 0x009C: 0x9C, # <control>
- 0x009D: 0x9D, # <control>
- 0x009E: 0x9E, # <control>
- 0x009F: 0x9F, # <control>
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00B0: 0xB0, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00B7: 0xB7, # MIDDLE DOT
- 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00C0: 0xC0, # LATIN CAPITAL LETTER A WITH GRAVE
- 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C6: 0xC6, # LATIN CAPITAL LETTER AE
- 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C8: 0xC8, # LATIN CAPITAL LETTER E WITH GRAVE
- 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CA: 0xCA, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
- 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CC: 0xCC, # LATIN CAPITAL LETTER I WITH GRAVE
- 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS
- 0x00D2: 0xD2, # LATIN CAPITAL LETTER O WITH GRAVE
- 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D9: 0xD9, # LATIN CAPITAL LETTER U WITH GRAVE
- 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
- 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S
- 0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E6: 0xE6, # LATIN SMALL LETTER AE
- 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00EC: 0xEC, # LATIN SMALL LETTER I WITH GRAVE
- 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F2: 0xF2, # LATIN SMALL LETTER O WITH GRAVE
- 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x00FF: 0xFF, # LATIN SMALL LETTER Y WITH DIAERESIS
- 0x0102: 0xC3, # LATIN CAPITAL LETTER A WITH BREVE
- 0x0103: 0xE3, # LATIN SMALL LETTER A WITH BREVE
- 0x0104: 0xA1, # LATIN CAPITAL LETTER A WITH OGONEK
- 0x0105: 0xA2, # LATIN SMALL LETTER A WITH OGONEK
- 0x0106: 0xC5, # LATIN CAPITAL LETTER C WITH ACUTE
- 0x0107: 0xE5, # LATIN SMALL LETTER C WITH ACUTE
- 0x010C: 0xB2, # LATIN CAPITAL LETTER C WITH CARON
- 0x010D: 0xB9, # LATIN SMALL LETTER C WITH CARON
- 0x0110: 0xD0, # LATIN CAPITAL LETTER D WITH STROKE
- 0x0111: 0xF0, # LATIN SMALL LETTER D WITH STROKE
- 0x0118: 0xDD, # LATIN CAPITAL LETTER E WITH OGONEK
- 0x0119: 0xFD, # LATIN SMALL LETTER E WITH OGONEK
- 0x0141: 0xA3, # LATIN CAPITAL LETTER L WITH STROKE
- 0x0142: 0xB3, # LATIN SMALL LETTER L WITH STROKE
- 0x0143: 0xD1, # LATIN CAPITAL LETTER N WITH ACUTE
- 0x0144: 0xF1, # LATIN SMALL LETTER N WITH ACUTE
- 0x0150: 0xD5, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
- 0x0151: 0xF5, # LATIN SMALL LETTER O WITH DOUBLE ACUTE
- 0x0152: 0xBC, # LATIN CAPITAL LIGATURE OE
- 0x0153: 0xBD, # LATIN SMALL LIGATURE OE
- 0x015A: 0xD7, # LATIN CAPITAL LETTER S WITH ACUTE
- 0x015B: 0xF7, # LATIN SMALL LETTER S WITH ACUTE
- 0x0160: 0xA6, # LATIN CAPITAL LETTER S WITH CARON
- 0x0161: 0xA8, # LATIN SMALL LETTER S WITH CARON
- 0x0170: 0xD8, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
- 0x0171: 0xF8, # LATIN SMALL LETTER U WITH DOUBLE ACUTE
- 0x0178: 0xBE, # LATIN CAPITAL LETTER Y WITH DIAERESIS
- 0x0179: 0xAC, # LATIN CAPITAL LETTER Z WITH ACUTE
- 0x017A: 0xAE, # LATIN SMALL LETTER Z WITH ACUTE
- 0x017B: 0xAF, # LATIN CAPITAL LETTER Z WITH DOT ABOVE
- 0x017C: 0xBF, # LATIN SMALL LETTER Z WITH DOT ABOVE
- 0x017D: 0xB4, # LATIN CAPITAL LETTER Z WITH CARON
- 0x017E: 0xB8, # LATIN SMALL LETTER Z WITH CARON
- 0x0218: 0xAA, # LATIN CAPITAL LETTER S WITH COMMA BELOW
- 0x0219: 0xBA, # LATIN SMALL LETTER S WITH COMMA BELOW
- 0x021A: 0xDE, # LATIN CAPITAL LETTER T WITH COMMA BELOW
- 0x021B: 0xFE, # LATIN SMALL LETTER T WITH COMMA BELOW
- 0x201D: 0xB5, # RIGHT DOUBLE QUOTATION MARK
- 0x201E: 0xA5, # DOUBLE LOW-9 QUOTATION MARK
- 0x20AC: 0xA4, # EURO SIGN
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/iso8859_2.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/iso8859_2.py (original)
+++ python/branches/p3yk/Lib/encodings/iso8859_2.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\u02d9' # 0xFF -> DOT ABOVE
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x0080: 0x80, # <control>
- 0x0081: 0x81, # <control>
- 0x0082: 0x82, # <control>
- 0x0083: 0x83, # <control>
- 0x0084: 0x84, # <control>
- 0x0085: 0x85, # <control>
- 0x0086: 0x86, # <control>
- 0x0087: 0x87, # <control>
- 0x0088: 0x88, # <control>
- 0x0089: 0x89, # <control>
- 0x008A: 0x8A, # <control>
- 0x008B: 0x8B, # <control>
- 0x008C: 0x8C, # <control>
- 0x008D: 0x8D, # <control>
- 0x008E: 0x8E, # <control>
- 0x008F: 0x8F, # <control>
- 0x0090: 0x90, # <control>
- 0x0091: 0x91, # <control>
- 0x0092: 0x92, # <control>
- 0x0093: 0x93, # <control>
- 0x0094: 0x94, # <control>
- 0x0095: 0x95, # <control>
- 0x0096: 0x96, # <control>
- 0x0097: 0x97, # <control>
- 0x0098: 0x98, # <control>
- 0x0099: 0x99, # <control>
- 0x009A: 0x9A, # <control>
- 0x009B: 0x9B, # <control>
- 0x009C: 0x9C, # <control>
- 0x009D: 0x9D, # <control>
- 0x009E: 0x9E, # <control>
- 0x009F: 0x9F, # <control>
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A4: 0xA4, # CURRENCY SIGN
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00A8: 0xA8, # DIAERESIS
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00B0: 0xB0, # DEGREE SIGN
- 0x00B4: 0xB4, # ACUTE ACCENT
- 0x00B8: 0xB8, # CEDILLA
- 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D7: 0xD7, # MULTIPLICATION SIGN
- 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DD: 0xDD, # LATIN CAPITAL LETTER Y WITH ACUTE
- 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S
- 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xF7, # DIVISION SIGN
- 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x00FD: 0xFD, # LATIN SMALL LETTER Y WITH ACUTE
- 0x0102: 0xC3, # LATIN CAPITAL LETTER A WITH BREVE
- 0x0103: 0xE3, # LATIN SMALL LETTER A WITH BREVE
- 0x0104: 0xA1, # LATIN CAPITAL LETTER A WITH OGONEK
- 0x0105: 0xB1, # LATIN SMALL LETTER A WITH OGONEK
- 0x0106: 0xC6, # LATIN CAPITAL LETTER C WITH ACUTE
- 0x0107: 0xE6, # LATIN SMALL LETTER C WITH ACUTE
- 0x010C: 0xC8, # LATIN CAPITAL LETTER C WITH CARON
- 0x010D: 0xE8, # LATIN SMALL LETTER C WITH CARON
- 0x010E: 0xCF, # LATIN CAPITAL LETTER D WITH CARON
- 0x010F: 0xEF, # LATIN SMALL LETTER D WITH CARON
- 0x0110: 0xD0, # LATIN CAPITAL LETTER D WITH STROKE
- 0x0111: 0xF0, # LATIN SMALL LETTER D WITH STROKE
- 0x0118: 0xCA, # LATIN CAPITAL LETTER E WITH OGONEK
- 0x0119: 0xEA, # LATIN SMALL LETTER E WITH OGONEK
- 0x011A: 0xCC, # LATIN CAPITAL LETTER E WITH CARON
- 0x011B: 0xEC, # LATIN SMALL LETTER E WITH CARON
- 0x0139: 0xC5, # LATIN CAPITAL LETTER L WITH ACUTE
- 0x013A: 0xE5, # LATIN SMALL LETTER L WITH ACUTE
- 0x013D: 0xA5, # LATIN CAPITAL LETTER L WITH CARON
- 0x013E: 0xB5, # LATIN SMALL LETTER L WITH CARON
- 0x0141: 0xA3, # LATIN CAPITAL LETTER L WITH STROKE
- 0x0142: 0xB3, # LATIN SMALL LETTER L WITH STROKE
- 0x0143: 0xD1, # LATIN CAPITAL LETTER N WITH ACUTE
- 0x0144: 0xF1, # LATIN SMALL LETTER N WITH ACUTE
- 0x0147: 0xD2, # LATIN CAPITAL LETTER N WITH CARON
- 0x0148: 0xF2, # LATIN SMALL LETTER N WITH CARON
- 0x0150: 0xD5, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
- 0x0151: 0xF5, # LATIN SMALL LETTER O WITH DOUBLE ACUTE
- 0x0154: 0xC0, # LATIN CAPITAL LETTER R WITH ACUTE
- 0x0155: 0xE0, # LATIN SMALL LETTER R WITH ACUTE
- 0x0158: 0xD8, # LATIN CAPITAL LETTER R WITH CARON
- 0x0159: 0xF8, # LATIN SMALL LETTER R WITH CARON
- 0x015A: 0xA6, # LATIN CAPITAL LETTER S WITH ACUTE
- 0x015B: 0xB6, # LATIN SMALL LETTER S WITH ACUTE
- 0x015E: 0xAA, # LATIN CAPITAL LETTER S WITH CEDILLA
- 0x015F: 0xBA, # LATIN SMALL LETTER S WITH CEDILLA
- 0x0160: 0xA9, # LATIN CAPITAL LETTER S WITH CARON
- 0x0161: 0xB9, # LATIN SMALL LETTER S WITH CARON
- 0x0162: 0xDE, # LATIN CAPITAL LETTER T WITH CEDILLA
- 0x0163: 0xFE, # LATIN SMALL LETTER T WITH CEDILLA
- 0x0164: 0xAB, # LATIN CAPITAL LETTER T WITH CARON
- 0x0165: 0xBB, # LATIN SMALL LETTER T WITH CARON
- 0x016E: 0xD9, # LATIN CAPITAL LETTER U WITH RING ABOVE
- 0x016F: 0xF9, # LATIN SMALL LETTER U WITH RING ABOVE
- 0x0170: 0xDB, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
- 0x0171: 0xFB, # LATIN SMALL LETTER U WITH DOUBLE ACUTE
- 0x0179: 0xAC, # LATIN CAPITAL LETTER Z WITH ACUTE
- 0x017A: 0xBC, # LATIN SMALL LETTER Z WITH ACUTE
- 0x017B: 0xAF, # LATIN CAPITAL LETTER Z WITH DOT ABOVE
- 0x017C: 0xBF, # LATIN SMALL LETTER Z WITH DOT ABOVE
- 0x017D: 0xAE, # LATIN CAPITAL LETTER Z WITH CARON
- 0x017E: 0xBE, # LATIN SMALL LETTER Z WITH CARON
- 0x02C7: 0xB7, # CARON
- 0x02D8: 0xA2, # BREVE
- 0x02D9: 0xFF, # DOT ABOVE
- 0x02DB: 0xB2, # OGONEK
- 0x02DD: 0xBD, # DOUBLE ACUTE ACCENT
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/iso8859_3.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/iso8859_3.py (original)
+++ python/branches/p3yk/Lib/encodings/iso8859_3.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,256 +303,5 @@
u'\u02d9' # 0xFF -> DOT ABOVE
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x0080: 0x80, # <control>
- 0x0081: 0x81, # <control>
- 0x0082: 0x82, # <control>
- 0x0083: 0x83, # <control>
- 0x0084: 0x84, # <control>
- 0x0085: 0x85, # <control>
- 0x0086: 0x86, # <control>
- 0x0087: 0x87, # <control>
- 0x0088: 0x88, # <control>
- 0x0089: 0x89, # <control>
- 0x008A: 0x8A, # <control>
- 0x008B: 0x8B, # <control>
- 0x008C: 0x8C, # <control>
- 0x008D: 0x8D, # <control>
- 0x008E: 0x8E, # <control>
- 0x008F: 0x8F, # <control>
- 0x0090: 0x90, # <control>
- 0x0091: 0x91, # <control>
- 0x0092: 0x92, # <control>
- 0x0093: 0x93, # <control>
- 0x0094: 0x94, # <control>
- 0x0095: 0x95, # <control>
- 0x0096: 0x96, # <control>
- 0x0097: 0x97, # <control>
- 0x0098: 0x98, # <control>
- 0x0099: 0x99, # <control>
- 0x009A: 0x9A, # <control>
- 0x009B: 0x9B, # <control>
- 0x009C: 0x9C, # <control>
- 0x009D: 0x9D, # <control>
- 0x009E: 0x9E, # <control>
- 0x009F: 0x9F, # <control>
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A4: 0xA4, # CURRENCY SIGN
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00A8: 0xA8, # DIAERESIS
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00B0: 0xB0, # DEGREE SIGN
- 0x00B2: 0xB2, # SUPERSCRIPT TWO
- 0x00B3: 0xB3, # SUPERSCRIPT THREE
- 0x00B4: 0xB4, # ACUTE ACCENT
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B7: 0xB7, # MIDDLE DOT
- 0x00B8: 0xB8, # CEDILLA
- 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF
- 0x00C0: 0xC0, # LATIN CAPITAL LETTER A WITH GRAVE
- 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C8: 0xC8, # LATIN CAPITAL LETTER E WITH GRAVE
- 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CA: 0xCA, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
- 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CC: 0xCC, # LATIN CAPITAL LETTER I WITH GRAVE
- 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS
- 0x00D1: 0xD1, # LATIN CAPITAL LETTER N WITH TILDE
- 0x00D2: 0xD2, # LATIN CAPITAL LETTER O WITH GRAVE
- 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D7: 0xD7, # MULTIPLICATION SIGN
- 0x00D9: 0xD9, # LATIN CAPITAL LETTER U WITH GRAVE
- 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
- 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S
- 0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00EC: 0xEC, # LATIN SMALL LETTER I WITH GRAVE
- 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F1: 0xF1, # LATIN SMALL LETTER N WITH TILDE
- 0x00F2: 0xF2, # LATIN SMALL LETTER O WITH GRAVE
- 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xF7, # DIVISION SIGN
- 0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x0108: 0xC6, # LATIN CAPITAL LETTER C WITH CIRCUMFLEX
- 0x0109: 0xE6, # LATIN SMALL LETTER C WITH CIRCUMFLEX
- 0x010A: 0xC5, # LATIN CAPITAL LETTER C WITH DOT ABOVE
- 0x010B: 0xE5, # LATIN SMALL LETTER C WITH DOT ABOVE
- 0x011C: 0xD8, # LATIN CAPITAL LETTER G WITH CIRCUMFLEX
- 0x011D: 0xF8, # LATIN SMALL LETTER G WITH CIRCUMFLEX
- 0x011E: 0xAB, # LATIN CAPITAL LETTER G WITH BREVE
- 0x011F: 0xBB, # LATIN SMALL LETTER G WITH BREVE
- 0x0120: 0xD5, # LATIN CAPITAL LETTER G WITH DOT ABOVE
- 0x0121: 0xF5, # LATIN SMALL LETTER G WITH DOT ABOVE
- 0x0124: 0xA6, # LATIN CAPITAL LETTER H WITH CIRCUMFLEX
- 0x0125: 0xB6, # LATIN SMALL LETTER H WITH CIRCUMFLEX
- 0x0126: 0xA1, # LATIN CAPITAL LETTER H WITH STROKE
- 0x0127: 0xB1, # LATIN SMALL LETTER H WITH STROKE
- 0x0130: 0xA9, # LATIN CAPITAL LETTER I WITH DOT ABOVE
- 0x0131: 0xB9, # LATIN SMALL LETTER DOTLESS I
- 0x0134: 0xAC, # LATIN CAPITAL LETTER J WITH CIRCUMFLEX
- 0x0135: 0xBC, # LATIN SMALL LETTER J WITH CIRCUMFLEX
- 0x015C: 0xDE, # LATIN CAPITAL LETTER S WITH CIRCUMFLEX
- 0x015D: 0xFE, # LATIN SMALL LETTER S WITH CIRCUMFLEX
- 0x015E: 0xAA, # LATIN CAPITAL LETTER S WITH CEDILLA
- 0x015F: 0xBA, # LATIN SMALL LETTER S WITH CEDILLA
- 0x016C: 0xDD, # LATIN CAPITAL LETTER U WITH BREVE
- 0x016D: 0xFD, # LATIN SMALL LETTER U WITH BREVE
- 0x017B: 0xAF, # LATIN CAPITAL LETTER Z WITH DOT ABOVE
- 0x017C: 0xBF, # LATIN SMALL LETTER Z WITH DOT ABOVE
- 0x02D8: 0xA2, # BREVE
- 0x02D9: 0xFF, # DOT ABOVE
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/iso8859_4.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/iso8859_4.py (original)
+++ python/branches/p3yk/Lib/encodings/iso8859_4.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\u02d9' # 0xFF -> DOT ABOVE
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x0080: 0x80, # <control>
- 0x0081: 0x81, # <control>
- 0x0082: 0x82, # <control>
- 0x0083: 0x83, # <control>
- 0x0084: 0x84, # <control>
- 0x0085: 0x85, # <control>
- 0x0086: 0x86, # <control>
- 0x0087: 0x87, # <control>
- 0x0088: 0x88, # <control>
- 0x0089: 0x89, # <control>
- 0x008A: 0x8A, # <control>
- 0x008B: 0x8B, # <control>
- 0x008C: 0x8C, # <control>
- 0x008D: 0x8D, # <control>
- 0x008E: 0x8E, # <control>
- 0x008F: 0x8F, # <control>
- 0x0090: 0x90, # <control>
- 0x0091: 0x91, # <control>
- 0x0092: 0x92, # <control>
- 0x0093: 0x93, # <control>
- 0x0094: 0x94, # <control>
- 0x0095: 0x95, # <control>
- 0x0096: 0x96, # <control>
- 0x0097: 0x97, # <control>
- 0x0098: 0x98, # <control>
- 0x0099: 0x99, # <control>
- 0x009A: 0x9A, # <control>
- 0x009B: 0x9B, # <control>
- 0x009C: 0x9C, # <control>
- 0x009D: 0x9D, # <control>
- 0x009E: 0x9E, # <control>
- 0x009F: 0x9F, # <control>
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A4: 0xA4, # CURRENCY SIGN
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00A8: 0xA8, # DIAERESIS
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00AF: 0xAF, # MACRON
- 0x00B0: 0xB0, # DEGREE SIGN
- 0x00B4: 0xB4, # ACUTE ACCENT
- 0x00B8: 0xB8, # CEDILLA
- 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C3: 0xC3, # LATIN CAPITAL LETTER A WITH TILDE
- 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE
- 0x00C6: 0xC6, # LATIN CAPITAL LETTER AE
- 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE
- 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D7: 0xD7, # MULTIPLICATION SIGN
- 0x00D8: 0xD8, # LATIN CAPITAL LETTER O WITH STROKE
- 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
- 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S
- 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E3: 0xE3, # LATIN SMALL LETTER A WITH TILDE
- 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE
- 0x00E6: 0xE6, # LATIN SMALL LETTER AE
- 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE
- 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xF7, # DIVISION SIGN
- 0x00F8: 0xF8, # LATIN SMALL LETTER O WITH STROKE
- 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x0100: 0xC0, # LATIN CAPITAL LETTER A WITH MACRON
- 0x0101: 0xE0, # LATIN SMALL LETTER A WITH MACRON
- 0x0104: 0xA1, # LATIN CAPITAL LETTER A WITH OGONEK
- 0x0105: 0xB1, # LATIN SMALL LETTER A WITH OGONEK
- 0x010C: 0xC8, # LATIN CAPITAL LETTER C WITH CARON
- 0x010D: 0xE8, # LATIN SMALL LETTER C WITH CARON
- 0x0110: 0xD0, # LATIN CAPITAL LETTER D WITH STROKE
- 0x0111: 0xF0, # LATIN SMALL LETTER D WITH STROKE
- 0x0112: 0xAA, # LATIN CAPITAL LETTER E WITH MACRON
- 0x0113: 0xBA, # LATIN SMALL LETTER E WITH MACRON
- 0x0116: 0xCC, # LATIN CAPITAL LETTER E WITH DOT ABOVE
- 0x0117: 0xEC, # LATIN SMALL LETTER E WITH DOT ABOVE
- 0x0118: 0xCA, # LATIN CAPITAL LETTER E WITH OGONEK
- 0x0119: 0xEA, # LATIN SMALL LETTER E WITH OGONEK
- 0x0122: 0xAB, # LATIN CAPITAL LETTER G WITH CEDILLA
- 0x0123: 0xBB, # LATIN SMALL LETTER G WITH CEDILLA
- 0x0128: 0xA5, # LATIN CAPITAL LETTER I WITH TILDE
- 0x0129: 0xB5, # LATIN SMALL LETTER I WITH TILDE
- 0x012A: 0xCF, # LATIN CAPITAL LETTER I WITH MACRON
- 0x012B: 0xEF, # LATIN SMALL LETTER I WITH MACRON
- 0x012E: 0xC7, # LATIN CAPITAL LETTER I WITH OGONEK
- 0x012F: 0xE7, # LATIN SMALL LETTER I WITH OGONEK
- 0x0136: 0xD3, # LATIN CAPITAL LETTER K WITH CEDILLA
- 0x0137: 0xF3, # LATIN SMALL LETTER K WITH CEDILLA
- 0x0138: 0xA2, # LATIN SMALL LETTER KRA
- 0x013B: 0xA6, # LATIN CAPITAL LETTER L WITH CEDILLA
- 0x013C: 0xB6, # LATIN SMALL LETTER L WITH CEDILLA
- 0x0145: 0xD1, # LATIN CAPITAL LETTER N WITH CEDILLA
- 0x0146: 0xF1, # LATIN SMALL LETTER N WITH CEDILLA
- 0x014A: 0xBD, # LATIN CAPITAL LETTER ENG
- 0x014B: 0xBF, # LATIN SMALL LETTER ENG
- 0x014C: 0xD2, # LATIN CAPITAL LETTER O WITH MACRON
- 0x014D: 0xF2, # LATIN SMALL LETTER O WITH MACRON
- 0x0156: 0xA3, # LATIN CAPITAL LETTER R WITH CEDILLA
- 0x0157: 0xB3, # LATIN SMALL LETTER R WITH CEDILLA
- 0x0160: 0xA9, # LATIN CAPITAL LETTER S WITH CARON
- 0x0161: 0xB9, # LATIN SMALL LETTER S WITH CARON
- 0x0166: 0xAC, # LATIN CAPITAL LETTER T WITH STROKE
- 0x0167: 0xBC, # LATIN SMALL LETTER T WITH STROKE
- 0x0168: 0xDD, # LATIN CAPITAL LETTER U WITH TILDE
- 0x0169: 0xFD, # LATIN SMALL LETTER U WITH TILDE
- 0x016A: 0xDE, # LATIN CAPITAL LETTER U WITH MACRON
- 0x016B: 0xFE, # LATIN SMALL LETTER U WITH MACRON
- 0x0172: 0xD9, # LATIN CAPITAL LETTER U WITH OGONEK
- 0x0173: 0xF9, # LATIN SMALL LETTER U WITH OGONEK
- 0x017D: 0xAE, # LATIN CAPITAL LETTER Z WITH CARON
- 0x017E: 0xBE, # LATIN SMALL LETTER Z WITH CARON
- 0x02C7: 0xB7, # CARON
- 0x02D9: 0xFF, # DOT ABOVE
- 0x02DB: 0xB2, # OGONEK
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/iso8859_5.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/iso8859_5.py (original)
+++ python/branches/p3yk/Lib/encodings/iso8859_5.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\u045f' # 0xFF -> CYRILLIC SMALL LETTER DZHE
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x0080: 0x80, # <control>
- 0x0081: 0x81, # <control>
- 0x0082: 0x82, # <control>
- 0x0083: 0x83, # <control>
- 0x0084: 0x84, # <control>
- 0x0085: 0x85, # <control>
- 0x0086: 0x86, # <control>
- 0x0087: 0x87, # <control>
- 0x0088: 0x88, # <control>
- 0x0089: 0x89, # <control>
- 0x008A: 0x8A, # <control>
- 0x008B: 0x8B, # <control>
- 0x008C: 0x8C, # <control>
- 0x008D: 0x8D, # <control>
- 0x008E: 0x8E, # <control>
- 0x008F: 0x8F, # <control>
- 0x0090: 0x90, # <control>
- 0x0091: 0x91, # <control>
- 0x0092: 0x92, # <control>
- 0x0093: 0x93, # <control>
- 0x0094: 0x94, # <control>
- 0x0095: 0x95, # <control>
- 0x0096: 0x96, # <control>
- 0x0097: 0x97, # <control>
- 0x0098: 0x98, # <control>
- 0x0099: 0x99, # <control>
- 0x009A: 0x9A, # <control>
- 0x009B: 0x9B, # <control>
- 0x009C: 0x9C, # <control>
- 0x009D: 0x9D, # <control>
- 0x009E: 0x9E, # <control>
- 0x009F: 0x9F, # <control>
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A7: 0xFD, # SECTION SIGN
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x0401: 0xA1, # CYRILLIC CAPITAL LETTER IO
- 0x0402: 0xA2, # CYRILLIC CAPITAL LETTER DJE
- 0x0403: 0xA3, # CYRILLIC CAPITAL LETTER GJE
- 0x0404: 0xA4, # CYRILLIC CAPITAL LETTER UKRAINIAN IE
- 0x0405: 0xA5, # CYRILLIC CAPITAL LETTER DZE
- 0x0406: 0xA6, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
- 0x0407: 0xA7, # CYRILLIC CAPITAL LETTER YI
- 0x0408: 0xA8, # CYRILLIC CAPITAL LETTER JE
- 0x0409: 0xA9, # CYRILLIC CAPITAL LETTER LJE
- 0x040A: 0xAA, # CYRILLIC CAPITAL LETTER NJE
- 0x040B: 0xAB, # CYRILLIC CAPITAL LETTER TSHE
- 0x040C: 0xAC, # CYRILLIC CAPITAL LETTER KJE
- 0x040E: 0xAE, # CYRILLIC CAPITAL LETTER SHORT U
- 0x040F: 0xAF, # CYRILLIC CAPITAL LETTER DZHE
- 0x0410: 0xB0, # CYRILLIC CAPITAL LETTER A
- 0x0411: 0xB1, # CYRILLIC CAPITAL LETTER BE
- 0x0412: 0xB2, # CYRILLIC CAPITAL LETTER VE
- 0x0413: 0xB3, # CYRILLIC CAPITAL LETTER GHE
- 0x0414: 0xB4, # CYRILLIC CAPITAL LETTER DE
- 0x0415: 0xB5, # CYRILLIC CAPITAL LETTER IE
- 0x0416: 0xB6, # CYRILLIC CAPITAL LETTER ZHE
- 0x0417: 0xB7, # CYRILLIC CAPITAL LETTER ZE
- 0x0418: 0xB8, # CYRILLIC CAPITAL LETTER I
- 0x0419: 0xB9, # CYRILLIC CAPITAL LETTER SHORT I
- 0x041A: 0xBA, # CYRILLIC CAPITAL LETTER KA
- 0x041B: 0xBB, # CYRILLIC CAPITAL LETTER EL
- 0x041C: 0xBC, # CYRILLIC CAPITAL LETTER EM
- 0x041D: 0xBD, # CYRILLIC CAPITAL LETTER EN
- 0x041E: 0xBE, # CYRILLIC CAPITAL LETTER O
- 0x041F: 0xBF, # CYRILLIC CAPITAL LETTER PE
- 0x0420: 0xC0, # CYRILLIC CAPITAL LETTER ER
- 0x0421: 0xC1, # CYRILLIC CAPITAL LETTER ES
- 0x0422: 0xC2, # CYRILLIC CAPITAL LETTER TE
- 0x0423: 0xC3, # CYRILLIC CAPITAL LETTER U
- 0x0424: 0xC4, # CYRILLIC CAPITAL LETTER EF
- 0x0425: 0xC5, # CYRILLIC CAPITAL LETTER HA
- 0x0426: 0xC6, # CYRILLIC CAPITAL LETTER TSE
- 0x0427: 0xC7, # CYRILLIC CAPITAL LETTER CHE
- 0x0428: 0xC8, # CYRILLIC CAPITAL LETTER SHA
- 0x0429: 0xC9, # CYRILLIC CAPITAL LETTER SHCHA
- 0x042A: 0xCA, # CYRILLIC CAPITAL LETTER HARD SIGN
- 0x042B: 0xCB, # CYRILLIC CAPITAL LETTER YERU
- 0x042C: 0xCC, # CYRILLIC CAPITAL LETTER SOFT SIGN
- 0x042D: 0xCD, # CYRILLIC CAPITAL LETTER E
- 0x042E: 0xCE, # CYRILLIC CAPITAL LETTER YU
- 0x042F: 0xCF, # CYRILLIC CAPITAL LETTER YA
- 0x0430: 0xD0, # CYRILLIC SMALL LETTER A
- 0x0431: 0xD1, # CYRILLIC SMALL LETTER BE
- 0x0432: 0xD2, # CYRILLIC SMALL LETTER VE
- 0x0433: 0xD3, # CYRILLIC SMALL LETTER GHE
- 0x0434: 0xD4, # CYRILLIC SMALL LETTER DE
- 0x0435: 0xD5, # CYRILLIC SMALL LETTER IE
- 0x0436: 0xD6, # CYRILLIC SMALL LETTER ZHE
- 0x0437: 0xD7, # CYRILLIC SMALL LETTER ZE
- 0x0438: 0xD8, # CYRILLIC SMALL LETTER I
- 0x0439: 0xD9, # CYRILLIC SMALL LETTER SHORT I
- 0x043A: 0xDA, # CYRILLIC SMALL LETTER KA
- 0x043B: 0xDB, # CYRILLIC SMALL LETTER EL
- 0x043C: 0xDC, # CYRILLIC SMALL LETTER EM
- 0x043D: 0xDD, # CYRILLIC SMALL LETTER EN
- 0x043E: 0xDE, # CYRILLIC SMALL LETTER O
- 0x043F: 0xDF, # CYRILLIC SMALL LETTER PE
- 0x0440: 0xE0, # CYRILLIC SMALL LETTER ER
- 0x0441: 0xE1, # CYRILLIC SMALL LETTER ES
- 0x0442: 0xE2, # CYRILLIC SMALL LETTER TE
- 0x0443: 0xE3, # CYRILLIC SMALL LETTER U
- 0x0444: 0xE4, # CYRILLIC SMALL LETTER EF
- 0x0445: 0xE5, # CYRILLIC SMALL LETTER HA
- 0x0446: 0xE6, # CYRILLIC SMALL LETTER TSE
- 0x0447: 0xE7, # CYRILLIC SMALL LETTER CHE
- 0x0448: 0xE8, # CYRILLIC SMALL LETTER SHA
- 0x0449: 0xE9, # CYRILLIC SMALL LETTER SHCHA
- 0x044A: 0xEA, # CYRILLIC SMALL LETTER HARD SIGN
- 0x044B: 0xEB, # CYRILLIC SMALL LETTER YERU
- 0x044C: 0xEC, # CYRILLIC SMALL LETTER SOFT SIGN
- 0x044D: 0xED, # CYRILLIC SMALL LETTER E
- 0x044E: 0xEE, # CYRILLIC SMALL LETTER YU
- 0x044F: 0xEF, # CYRILLIC SMALL LETTER YA
- 0x0451: 0xF1, # CYRILLIC SMALL LETTER IO
- 0x0452: 0xF2, # CYRILLIC SMALL LETTER DJE
- 0x0453: 0xF3, # CYRILLIC SMALL LETTER GJE
- 0x0454: 0xF4, # CYRILLIC SMALL LETTER UKRAINIAN IE
- 0x0455: 0xF5, # CYRILLIC SMALL LETTER DZE
- 0x0456: 0xF6, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
- 0x0457: 0xF7, # CYRILLIC SMALL LETTER YI
- 0x0458: 0xF8, # CYRILLIC SMALL LETTER JE
- 0x0459: 0xF9, # CYRILLIC SMALL LETTER LJE
- 0x045A: 0xFA, # CYRILLIC SMALL LETTER NJE
- 0x045B: 0xFB, # CYRILLIC SMALL LETTER TSHE
- 0x045C: 0xFC, # CYRILLIC SMALL LETTER KJE
- 0x045E: 0xFE, # CYRILLIC SMALL LETTER SHORT U
- 0x045F: 0xFF, # CYRILLIC SMALL LETTER DZHE
- 0x2116: 0xF0, # NUMERO SIGN
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/iso8859_6.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/iso8859_6.py (original)
+++ python/branches/p3yk/Lib/encodings/iso8859_6.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,218 +303,5 @@
u'\ufffe'
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x0080: 0x80, # <control>
- 0x0081: 0x81, # <control>
- 0x0082: 0x82, # <control>
- 0x0083: 0x83, # <control>
- 0x0084: 0x84, # <control>
- 0x0085: 0x85, # <control>
- 0x0086: 0x86, # <control>
- 0x0087: 0x87, # <control>
- 0x0088: 0x88, # <control>
- 0x0089: 0x89, # <control>
- 0x008A: 0x8A, # <control>
- 0x008B: 0x8B, # <control>
- 0x008C: 0x8C, # <control>
- 0x008D: 0x8D, # <control>
- 0x008E: 0x8E, # <control>
- 0x008F: 0x8F, # <control>
- 0x0090: 0x90, # <control>
- 0x0091: 0x91, # <control>
- 0x0092: 0x92, # <control>
- 0x0093: 0x93, # <control>
- 0x0094: 0x94, # <control>
- 0x0095: 0x95, # <control>
- 0x0096: 0x96, # <control>
- 0x0097: 0x97, # <control>
- 0x0098: 0x98, # <control>
- 0x0099: 0x99, # <control>
- 0x009A: 0x9A, # <control>
- 0x009B: 0x9B, # <control>
- 0x009C: 0x9C, # <control>
- 0x009D: 0x9D, # <control>
- 0x009E: 0x9E, # <control>
- 0x009F: 0x9F, # <control>
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A4: 0xA4, # CURRENCY SIGN
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x060C: 0xAC, # ARABIC COMMA
- 0x061B: 0xBB, # ARABIC SEMICOLON
- 0x061F: 0xBF, # ARABIC QUESTION MARK
- 0x0621: 0xC1, # ARABIC LETTER HAMZA
- 0x0622: 0xC2, # ARABIC LETTER ALEF WITH MADDA ABOVE
- 0x0623: 0xC3, # ARABIC LETTER ALEF WITH HAMZA ABOVE
- 0x0624: 0xC4, # ARABIC LETTER WAW WITH HAMZA ABOVE
- 0x0625: 0xC5, # ARABIC LETTER ALEF WITH HAMZA BELOW
- 0x0626: 0xC6, # ARABIC LETTER YEH WITH HAMZA ABOVE
- 0x0627: 0xC7, # ARABIC LETTER ALEF
- 0x0628: 0xC8, # ARABIC LETTER BEH
- 0x0629: 0xC9, # ARABIC LETTER TEH MARBUTA
- 0x062A: 0xCA, # ARABIC LETTER TEH
- 0x062B: 0xCB, # ARABIC LETTER THEH
- 0x062C: 0xCC, # ARABIC LETTER JEEM
- 0x062D: 0xCD, # ARABIC LETTER HAH
- 0x062E: 0xCE, # ARABIC LETTER KHAH
- 0x062F: 0xCF, # ARABIC LETTER DAL
- 0x0630: 0xD0, # ARABIC LETTER THAL
- 0x0631: 0xD1, # ARABIC LETTER REH
- 0x0632: 0xD2, # ARABIC LETTER ZAIN
- 0x0633: 0xD3, # ARABIC LETTER SEEN
- 0x0634: 0xD4, # ARABIC LETTER SHEEN
- 0x0635: 0xD5, # ARABIC LETTER SAD
- 0x0636: 0xD6, # ARABIC LETTER DAD
- 0x0637: 0xD7, # ARABIC LETTER TAH
- 0x0638: 0xD8, # ARABIC LETTER ZAH
- 0x0639: 0xD9, # ARABIC LETTER AIN
- 0x063A: 0xDA, # ARABIC LETTER GHAIN
- 0x0640: 0xE0, # ARABIC TATWEEL
- 0x0641: 0xE1, # ARABIC LETTER FEH
- 0x0642: 0xE2, # ARABIC LETTER QAF
- 0x0643: 0xE3, # ARABIC LETTER KAF
- 0x0644: 0xE4, # ARABIC LETTER LAM
- 0x0645: 0xE5, # ARABIC LETTER MEEM
- 0x0646: 0xE6, # ARABIC LETTER NOON
- 0x0647: 0xE7, # ARABIC LETTER HEH
- 0x0648: 0xE8, # ARABIC LETTER WAW
- 0x0649: 0xE9, # ARABIC LETTER ALEF MAKSURA
- 0x064A: 0xEA, # ARABIC LETTER YEH
- 0x064B: 0xEB, # ARABIC FATHATAN
- 0x064C: 0xEC, # ARABIC DAMMATAN
- 0x064D: 0xED, # ARABIC KASRATAN
- 0x064E: 0xEE, # ARABIC FATHA
- 0x064F: 0xEF, # ARABIC DAMMA
- 0x0650: 0xF0, # ARABIC KASRA
- 0x0651: 0xF1, # ARABIC SHADDA
- 0x0652: 0xF2, # ARABIC SUKUN
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/iso8859_7.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/iso8859_7.py (original)
+++ python/branches/p3yk/Lib/encodings/iso8859_7.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,260 +303,5 @@
u'\ufffe'
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x0080: 0x80, # <control>
- 0x0081: 0x81, # <control>
- 0x0082: 0x82, # <control>
- 0x0083: 0x83, # <control>
- 0x0084: 0x84, # <control>
- 0x0085: 0x85, # <control>
- 0x0086: 0x86, # <control>
- 0x0087: 0x87, # <control>
- 0x0088: 0x88, # <control>
- 0x0089: 0x89, # <control>
- 0x008A: 0x8A, # <control>
- 0x008B: 0x8B, # <control>
- 0x008C: 0x8C, # <control>
- 0x008D: 0x8D, # <control>
- 0x008E: 0x8E, # <control>
- 0x008F: 0x8F, # <control>
- 0x0090: 0x90, # <control>
- 0x0091: 0x91, # <control>
- 0x0092: 0x92, # <control>
- 0x0093: 0x93, # <control>
- 0x0094: 0x94, # <control>
- 0x0095: 0x95, # <control>
- 0x0096: 0x96, # <control>
- 0x0097: 0x97, # <control>
- 0x0098: 0x98, # <control>
- 0x0099: 0x99, # <control>
- 0x009A: 0x9A, # <control>
- 0x009B: 0x9B, # <control>
- 0x009C: 0x9C, # <control>
- 0x009D: 0x9D, # <control>
- 0x009E: 0x9E, # <control>
- 0x009F: 0x9F, # <control>
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A6: 0xA6, # BROKEN BAR
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00A8: 0xA8, # DIAERESIS
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xAC, # NOT SIGN
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00B0: 0xB0, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B2: 0xB2, # SUPERSCRIPT TWO
- 0x00B3: 0xB3, # SUPERSCRIPT THREE
- 0x00B7: 0xB7, # MIDDLE DOT
- 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF
- 0x037A: 0xAA, # GREEK YPOGEGRAMMENI
- 0x0384: 0xB4, # GREEK TONOS
- 0x0385: 0xB5, # GREEK DIALYTIKA TONOS
- 0x0386: 0xB6, # GREEK CAPITAL LETTER ALPHA WITH TONOS
- 0x0388: 0xB8, # GREEK CAPITAL LETTER EPSILON WITH TONOS
- 0x0389: 0xB9, # GREEK CAPITAL LETTER ETA WITH TONOS
- 0x038A: 0xBA, # GREEK CAPITAL LETTER IOTA WITH TONOS
- 0x038C: 0xBC, # GREEK CAPITAL LETTER OMICRON WITH TONOS
- 0x038E: 0xBE, # GREEK CAPITAL LETTER UPSILON WITH TONOS
- 0x038F: 0xBF, # GREEK CAPITAL LETTER OMEGA WITH TONOS
- 0x0390: 0xC0, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
- 0x0391: 0xC1, # GREEK CAPITAL LETTER ALPHA
- 0x0392: 0xC2, # GREEK CAPITAL LETTER BETA
- 0x0393: 0xC3, # GREEK CAPITAL LETTER GAMMA
- 0x0394: 0xC4, # GREEK CAPITAL LETTER DELTA
- 0x0395: 0xC5, # GREEK CAPITAL LETTER EPSILON
- 0x0396: 0xC6, # GREEK CAPITAL LETTER ZETA
- 0x0397: 0xC7, # GREEK CAPITAL LETTER ETA
- 0x0398: 0xC8, # GREEK CAPITAL LETTER THETA
- 0x0399: 0xC9, # GREEK CAPITAL LETTER IOTA
- 0x039A: 0xCA, # GREEK CAPITAL LETTER KAPPA
- 0x039B: 0xCB, # GREEK CAPITAL LETTER LAMDA
- 0x039C: 0xCC, # GREEK CAPITAL LETTER MU
- 0x039D: 0xCD, # GREEK CAPITAL LETTER NU
- 0x039E: 0xCE, # GREEK CAPITAL LETTER XI
- 0x039F: 0xCF, # GREEK CAPITAL LETTER OMICRON
- 0x03A0: 0xD0, # GREEK CAPITAL LETTER PI
- 0x03A1: 0xD1, # GREEK CAPITAL LETTER RHO
- 0x03A3: 0xD3, # GREEK CAPITAL LETTER SIGMA
- 0x03A4: 0xD4, # GREEK CAPITAL LETTER TAU
- 0x03A5: 0xD5, # GREEK CAPITAL LETTER UPSILON
- 0x03A6: 0xD6, # GREEK CAPITAL LETTER PHI
- 0x03A7: 0xD7, # GREEK CAPITAL LETTER CHI
- 0x03A8: 0xD8, # GREEK CAPITAL LETTER PSI
- 0x03A9: 0xD9, # GREEK CAPITAL LETTER OMEGA
- 0x03AA: 0xDA, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
- 0x03AB: 0xDB, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
- 0x03AC: 0xDC, # GREEK SMALL LETTER ALPHA WITH TONOS
- 0x03AD: 0xDD, # GREEK SMALL LETTER EPSILON WITH TONOS
- 0x03AE: 0xDE, # GREEK SMALL LETTER ETA WITH TONOS
- 0x03AF: 0xDF, # GREEK SMALL LETTER IOTA WITH TONOS
- 0x03B0: 0xE0, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
- 0x03B1: 0xE1, # GREEK SMALL LETTER ALPHA
- 0x03B2: 0xE2, # GREEK SMALL LETTER BETA
- 0x03B3: 0xE3, # GREEK SMALL LETTER GAMMA
- 0x03B4: 0xE4, # GREEK SMALL LETTER DELTA
- 0x03B5: 0xE5, # GREEK SMALL LETTER EPSILON
- 0x03B6: 0xE6, # GREEK SMALL LETTER ZETA
- 0x03B7: 0xE7, # GREEK SMALL LETTER ETA
- 0x03B8: 0xE8, # GREEK SMALL LETTER THETA
- 0x03B9: 0xE9, # GREEK SMALL LETTER IOTA
- 0x03BA: 0xEA, # GREEK SMALL LETTER KAPPA
- 0x03BB: 0xEB, # GREEK SMALL LETTER LAMDA
- 0x03BC: 0xEC, # GREEK SMALL LETTER MU
- 0x03BD: 0xED, # GREEK SMALL LETTER NU
- 0x03BE: 0xEE, # GREEK SMALL LETTER XI
- 0x03BF: 0xEF, # GREEK SMALL LETTER OMICRON
- 0x03C0: 0xF0, # GREEK SMALL LETTER PI
- 0x03C1: 0xF1, # GREEK SMALL LETTER RHO
- 0x03C2: 0xF2, # GREEK SMALL LETTER FINAL SIGMA
- 0x03C3: 0xF3, # GREEK SMALL LETTER SIGMA
- 0x03C4: 0xF4, # GREEK SMALL LETTER TAU
- 0x03C5: 0xF5, # GREEK SMALL LETTER UPSILON
- 0x03C6: 0xF6, # GREEK SMALL LETTER PHI
- 0x03C7: 0xF7, # GREEK SMALL LETTER CHI
- 0x03C8: 0xF8, # GREEK SMALL LETTER PSI
- 0x03C9: 0xF9, # GREEK SMALL LETTER OMEGA
- 0x03CA: 0xFA, # GREEK SMALL LETTER IOTA WITH DIALYTIKA
- 0x03CB: 0xFB, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
- 0x03CC: 0xFC, # GREEK SMALL LETTER OMICRON WITH TONOS
- 0x03CD: 0xFD, # GREEK SMALL LETTER UPSILON WITH TONOS
- 0x03CE: 0xFE, # GREEK SMALL LETTER OMEGA WITH TONOS
- 0x2015: 0xAF, # HORIZONTAL BAR
- 0x2018: 0xA1, # LEFT SINGLE QUOTATION MARK
- 0x2019: 0xA2, # RIGHT SINGLE QUOTATION MARK
- 0x20AC: 0xA4, # EURO SIGN
- 0x20AF: 0xA5, # DRACHMA SIGN
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/iso8859_8.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/iso8859_8.py (original)
+++ python/branches/p3yk/Lib/encodings/iso8859_8.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,227 +303,5 @@
u'\ufffe'
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x0080: 0x80, # <control>
- 0x0081: 0x81, # <control>
- 0x0082: 0x82, # <control>
- 0x0083: 0x83, # <control>
- 0x0084: 0x84, # <control>
- 0x0085: 0x85, # <control>
- 0x0086: 0x86, # <control>
- 0x0087: 0x87, # <control>
- 0x0088: 0x88, # <control>
- 0x0089: 0x89, # <control>
- 0x008A: 0x8A, # <control>
- 0x008B: 0x8B, # <control>
- 0x008C: 0x8C, # <control>
- 0x008D: 0x8D, # <control>
- 0x008E: 0x8E, # <control>
- 0x008F: 0x8F, # <control>
- 0x0090: 0x90, # <control>
- 0x0091: 0x91, # <control>
- 0x0092: 0x92, # <control>
- 0x0093: 0x93, # <control>
- 0x0094: 0x94, # <control>
- 0x0095: 0x95, # <control>
- 0x0096: 0x96, # <control>
- 0x0097: 0x97, # <control>
- 0x0098: 0x98, # <control>
- 0x0099: 0x99, # <control>
- 0x009A: 0x9A, # <control>
- 0x009B: 0x9B, # <control>
- 0x009C: 0x9C, # <control>
- 0x009D: 0x9D, # <control>
- 0x009E: 0x9E, # <control>
- 0x009F: 0x9F, # <control>
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A2: 0xA2, # CENT SIGN
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A4: 0xA4, # CURRENCY SIGN
- 0x00A5: 0xA5, # YEN SIGN
- 0x00A6: 0xA6, # BROKEN BAR
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00A8: 0xA8, # DIAERESIS
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xAC, # NOT SIGN
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00AE: 0xAE, # REGISTERED SIGN
- 0x00AF: 0xAF, # MACRON
- 0x00B0: 0xB0, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B2: 0xB2, # SUPERSCRIPT TWO
- 0x00B3: 0xB3, # SUPERSCRIPT THREE
- 0x00B4: 0xB4, # ACUTE ACCENT
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00B7: 0xB7, # MIDDLE DOT
- 0x00B8: 0xB8, # CEDILLA
- 0x00B9: 0xB9, # SUPERSCRIPT ONE
- 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER
- 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF
- 0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS
- 0x00D7: 0xAA, # MULTIPLICATION SIGN
- 0x00F7: 0xBA, # DIVISION SIGN
- 0x05D0: 0xE0, # HEBREW LETTER ALEF
- 0x05D1: 0xE1, # HEBREW LETTER BET
- 0x05D2: 0xE2, # HEBREW LETTER GIMEL
- 0x05D3: 0xE3, # HEBREW LETTER DALET
- 0x05D4: 0xE4, # HEBREW LETTER HE
- 0x05D5: 0xE5, # HEBREW LETTER VAV
- 0x05D6: 0xE6, # HEBREW LETTER ZAYIN
- 0x05D7: 0xE7, # HEBREW LETTER HET
- 0x05D8: 0xE8, # HEBREW LETTER TET
- 0x05D9: 0xE9, # HEBREW LETTER YOD
- 0x05DA: 0xEA, # HEBREW LETTER FINAL KAF
- 0x05DB: 0xEB, # HEBREW LETTER KAF
- 0x05DC: 0xEC, # HEBREW LETTER LAMED
- 0x05DD: 0xED, # HEBREW LETTER FINAL MEM
- 0x05DE: 0xEE, # HEBREW LETTER MEM
- 0x05DF: 0xEF, # HEBREW LETTER FINAL NUN
- 0x05E0: 0xF0, # HEBREW LETTER NUN
- 0x05E1: 0xF1, # HEBREW LETTER SAMEKH
- 0x05E2: 0xF2, # HEBREW LETTER AYIN
- 0x05E3: 0xF3, # HEBREW LETTER FINAL PE
- 0x05E4: 0xF4, # HEBREW LETTER PE
- 0x05E5: 0xF5, # HEBREW LETTER FINAL TSADI
- 0x05E6: 0xF6, # HEBREW LETTER TSADI
- 0x05E7: 0xF7, # HEBREW LETTER QOF
- 0x05E8: 0xF8, # HEBREW LETTER RESH
- 0x05E9: 0xF9, # HEBREW LETTER SHIN
- 0x05EA: 0xFA, # HEBREW LETTER TAV
- 0x200E: 0xFD, # LEFT-TO-RIGHT MARK
- 0x200F: 0xFE, # RIGHT-TO-LEFT MARK
- 0x2017: 0xDF, # DOUBLE LOW LINE
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/iso8859_9.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/iso8859_9.py (original)
+++ python/branches/p3yk/Lib/encodings/iso8859_9.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x0080: 0x80, # <control>
- 0x0081: 0x81, # <control>
- 0x0082: 0x82, # <control>
- 0x0083: 0x83, # <control>
- 0x0084: 0x84, # <control>
- 0x0085: 0x85, # <control>
- 0x0086: 0x86, # <control>
- 0x0087: 0x87, # <control>
- 0x0088: 0x88, # <control>
- 0x0089: 0x89, # <control>
- 0x008A: 0x8A, # <control>
- 0x008B: 0x8B, # <control>
- 0x008C: 0x8C, # <control>
- 0x008D: 0x8D, # <control>
- 0x008E: 0x8E, # <control>
- 0x008F: 0x8F, # <control>
- 0x0090: 0x90, # <control>
- 0x0091: 0x91, # <control>
- 0x0092: 0x92, # <control>
- 0x0093: 0x93, # <control>
- 0x0094: 0x94, # <control>
- 0x0095: 0x95, # <control>
- 0x0096: 0x96, # <control>
- 0x0097: 0x97, # <control>
- 0x0098: 0x98, # <control>
- 0x0099: 0x99, # <control>
- 0x009A: 0x9A, # <control>
- 0x009B: 0x9B, # <control>
- 0x009C: 0x9C, # <control>
- 0x009D: 0x9D, # <control>
- 0x009E: 0x9E, # <control>
- 0x009F: 0x9F, # <control>
- 0x00A0: 0xA0, # NO-BREAK SPACE
- 0x00A1: 0xA1, # INVERTED EXCLAMATION MARK
- 0x00A2: 0xA2, # CENT SIGN
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A4: 0xA4, # CURRENCY SIGN
- 0x00A5: 0xA5, # YEN SIGN
- 0x00A6: 0xA6, # BROKEN BAR
- 0x00A7: 0xA7, # SECTION SIGN
- 0x00A8: 0xA8, # DIAERESIS
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AA: 0xAA, # FEMININE ORDINAL INDICATOR
- 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xAC, # NOT SIGN
- 0x00AD: 0xAD, # SOFT HYPHEN
- 0x00AE: 0xAE, # REGISTERED SIGN
- 0x00AF: 0xAF, # MACRON
- 0x00B0: 0xB0, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B2: 0xB2, # SUPERSCRIPT TWO
- 0x00B3: 0xB3, # SUPERSCRIPT THREE
- 0x00B4: 0xB4, # ACUTE ACCENT
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B6: 0xB6, # PILCROW SIGN
- 0x00B7: 0xB7, # MIDDLE DOT
- 0x00B8: 0xB8, # CEDILLA
- 0x00B9: 0xB9, # SUPERSCRIPT ONE
- 0x00BA: 0xBA, # MASCULINE ORDINAL INDICATOR
- 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER
- 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF
- 0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS
- 0x00BF: 0xBF, # INVERTED QUESTION MARK
- 0x00C0: 0xC0, # LATIN CAPITAL LETTER A WITH GRAVE
- 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C3: 0xC3, # LATIN CAPITAL LETTER A WITH TILDE
- 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE
- 0x00C6: 0xC6, # LATIN CAPITAL LETTER AE
- 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C8: 0xC8, # LATIN CAPITAL LETTER E WITH GRAVE
- 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CA: 0xCA, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
- 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CC: 0xCC, # LATIN CAPITAL LETTER I WITH GRAVE
- 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS
- 0x00D1: 0xD1, # LATIN CAPITAL LETTER N WITH TILDE
- 0x00D2: 0xD2, # LATIN CAPITAL LETTER O WITH GRAVE
- 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE
- 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D7: 0xD7, # MULTIPLICATION SIGN
- 0x00D8: 0xD8, # LATIN CAPITAL LETTER O WITH STROKE
- 0x00D9: 0xD9, # LATIN CAPITAL LETTER U WITH GRAVE
- 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
- 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S
- 0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E3: 0xE3, # LATIN SMALL LETTER A WITH TILDE
- 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE
- 0x00E6: 0xE6, # LATIN SMALL LETTER AE
- 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00EC: 0xEC, # LATIN SMALL LETTER I WITH GRAVE
- 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F1: 0xF1, # LATIN SMALL LETTER N WITH TILDE
- 0x00F2: 0xF2, # LATIN SMALL LETTER O WITH GRAVE
- 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE
- 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xF7, # DIVISION SIGN
- 0x00F8: 0xF8, # LATIN SMALL LETTER O WITH STROKE
- 0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x00FF: 0xFF, # LATIN SMALL LETTER Y WITH DIAERESIS
- 0x011E: 0xD0, # LATIN CAPITAL LETTER G WITH BREVE
- 0x011F: 0xF0, # LATIN SMALL LETTER G WITH BREVE
- 0x0130: 0xDD, # LATIN CAPITAL LETTER I WITH DOT ABOVE
- 0x0131: 0xFD, # LATIN SMALL LETTER DOTLESS I
- 0x015E: 0xDE, # LATIN CAPITAL LETTER S WITH CEDILLA
- 0x015F: 0xFE, # LATIN SMALL LETTER S WITH CEDILLA
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/koi8_r.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/koi8_r.py (original)
+++ python/branches/p3yk/Lib/encodings/koi8_r.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\u042a' # 0xFF -> CYRILLIC CAPITAL LETTER HARD SIGN
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x00A0: 0x9A, # NO-BREAK SPACE
- 0x00A9: 0xBF, # COPYRIGHT SIGN
- 0x00B0: 0x9C, # DEGREE SIGN
- 0x00B2: 0x9D, # SUPERSCRIPT TWO
- 0x00B7: 0x9E, # MIDDLE DOT
- 0x00F7: 0x9F, # DIVISION SIGN
- 0x0401: 0xB3, # CYRILLIC CAPITAL LETTER IO
- 0x0410: 0xE1, # CYRILLIC CAPITAL LETTER A
- 0x0411: 0xE2, # CYRILLIC CAPITAL LETTER BE
- 0x0412: 0xF7, # CYRILLIC CAPITAL LETTER VE
- 0x0413: 0xE7, # CYRILLIC CAPITAL LETTER GHE
- 0x0414: 0xE4, # CYRILLIC CAPITAL LETTER DE
- 0x0415: 0xE5, # CYRILLIC CAPITAL LETTER IE
- 0x0416: 0xF6, # CYRILLIC CAPITAL LETTER ZHE
- 0x0417: 0xFA, # CYRILLIC CAPITAL LETTER ZE
- 0x0418: 0xE9, # CYRILLIC CAPITAL LETTER I
- 0x0419: 0xEA, # CYRILLIC CAPITAL LETTER SHORT I
- 0x041A: 0xEB, # CYRILLIC CAPITAL LETTER KA
- 0x041B: 0xEC, # CYRILLIC CAPITAL LETTER EL
- 0x041C: 0xED, # CYRILLIC CAPITAL LETTER EM
- 0x041D: 0xEE, # CYRILLIC CAPITAL LETTER EN
- 0x041E: 0xEF, # CYRILLIC CAPITAL LETTER O
- 0x041F: 0xF0, # CYRILLIC CAPITAL LETTER PE
- 0x0420: 0xF2, # CYRILLIC CAPITAL LETTER ER
- 0x0421: 0xF3, # CYRILLIC CAPITAL LETTER ES
- 0x0422: 0xF4, # CYRILLIC CAPITAL LETTER TE
- 0x0423: 0xF5, # CYRILLIC CAPITAL LETTER U
- 0x0424: 0xE6, # CYRILLIC CAPITAL LETTER EF
- 0x0425: 0xE8, # CYRILLIC CAPITAL LETTER HA
- 0x0426: 0xE3, # CYRILLIC CAPITAL LETTER TSE
- 0x0427: 0xFE, # CYRILLIC CAPITAL LETTER CHE
- 0x0428: 0xFB, # CYRILLIC CAPITAL LETTER SHA
- 0x0429: 0xFD, # CYRILLIC CAPITAL LETTER SHCHA
- 0x042A: 0xFF, # CYRILLIC CAPITAL LETTER HARD SIGN
- 0x042B: 0xF9, # CYRILLIC CAPITAL LETTER YERU
- 0x042C: 0xF8, # CYRILLIC CAPITAL LETTER SOFT SIGN
- 0x042D: 0xFC, # CYRILLIC CAPITAL LETTER E
- 0x042E: 0xE0, # CYRILLIC CAPITAL LETTER YU
- 0x042F: 0xF1, # CYRILLIC CAPITAL LETTER YA
- 0x0430: 0xC1, # CYRILLIC SMALL LETTER A
- 0x0431: 0xC2, # CYRILLIC SMALL LETTER BE
- 0x0432: 0xD7, # CYRILLIC SMALL LETTER VE
- 0x0433: 0xC7, # CYRILLIC SMALL LETTER GHE
- 0x0434: 0xC4, # CYRILLIC SMALL LETTER DE
- 0x0435: 0xC5, # CYRILLIC SMALL LETTER IE
- 0x0436: 0xD6, # CYRILLIC SMALL LETTER ZHE
- 0x0437: 0xDA, # CYRILLIC SMALL LETTER ZE
- 0x0438: 0xC9, # CYRILLIC SMALL LETTER I
- 0x0439: 0xCA, # CYRILLIC SMALL LETTER SHORT I
- 0x043A: 0xCB, # CYRILLIC SMALL LETTER KA
- 0x043B: 0xCC, # CYRILLIC SMALL LETTER EL
- 0x043C: 0xCD, # CYRILLIC SMALL LETTER EM
- 0x043D: 0xCE, # CYRILLIC SMALL LETTER EN
- 0x043E: 0xCF, # CYRILLIC SMALL LETTER O
- 0x043F: 0xD0, # CYRILLIC SMALL LETTER PE
- 0x0440: 0xD2, # CYRILLIC SMALL LETTER ER
- 0x0441: 0xD3, # CYRILLIC SMALL LETTER ES
- 0x0442: 0xD4, # CYRILLIC SMALL LETTER TE
- 0x0443: 0xD5, # CYRILLIC SMALL LETTER U
- 0x0444: 0xC6, # CYRILLIC SMALL LETTER EF
- 0x0445: 0xC8, # CYRILLIC SMALL LETTER HA
- 0x0446: 0xC3, # CYRILLIC SMALL LETTER TSE
- 0x0447: 0xDE, # CYRILLIC SMALL LETTER CHE
- 0x0448: 0xDB, # CYRILLIC SMALL LETTER SHA
- 0x0449: 0xDD, # CYRILLIC SMALL LETTER SHCHA
- 0x044A: 0xDF, # CYRILLIC SMALL LETTER HARD SIGN
- 0x044B: 0xD9, # CYRILLIC SMALL LETTER YERU
- 0x044C: 0xD8, # CYRILLIC SMALL LETTER SOFT SIGN
- 0x044D: 0xDC, # CYRILLIC SMALL LETTER E
- 0x044E: 0xC0, # CYRILLIC SMALL LETTER YU
- 0x044F: 0xD1, # CYRILLIC SMALL LETTER YA
- 0x0451: 0xA3, # CYRILLIC SMALL LETTER IO
- 0x2219: 0x95, # BULLET OPERATOR
- 0x221A: 0x96, # SQUARE ROOT
- 0x2248: 0x97, # ALMOST EQUAL TO
- 0x2264: 0x98, # LESS-THAN OR EQUAL TO
- 0x2265: 0x99, # GREATER-THAN OR EQUAL TO
- 0x2320: 0x93, # TOP HALF INTEGRAL
- 0x2321: 0x9B, # BOTTOM HALF INTEGRAL
- 0x2500: 0x80, # BOX DRAWINGS LIGHT HORIZONTAL
- 0x2502: 0x81, # BOX DRAWINGS LIGHT VERTICAL
- 0x250C: 0x82, # BOX DRAWINGS LIGHT DOWN AND RIGHT
- 0x2510: 0x83, # BOX DRAWINGS LIGHT DOWN AND LEFT
- 0x2514: 0x84, # BOX DRAWINGS LIGHT UP AND RIGHT
- 0x2518: 0x85, # BOX DRAWINGS LIGHT UP AND LEFT
- 0x251C: 0x86, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
- 0x2524: 0x87, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
- 0x252C: 0x88, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
- 0x2534: 0x89, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
- 0x253C: 0x8A, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
- 0x2550: 0xA0, # BOX DRAWINGS DOUBLE HORIZONTAL
- 0x2551: 0xA1, # BOX DRAWINGS DOUBLE VERTICAL
- 0x2552: 0xA2, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
- 0x2553: 0xA4, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
- 0x2554: 0xA5, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
- 0x2555: 0xA6, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
- 0x2556: 0xA7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
- 0x2557: 0xA8, # BOX DRAWINGS DOUBLE DOWN AND LEFT
- 0x2558: 0xA9, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
- 0x2559: 0xAA, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
- 0x255A: 0xAB, # BOX DRAWINGS DOUBLE UP AND RIGHT
- 0x255B: 0xAC, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
- 0x255C: 0xAD, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
- 0x255D: 0xAE, # BOX DRAWINGS DOUBLE UP AND LEFT
- 0x255E: 0xAF, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
- 0x255F: 0xB0, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
- 0x2560: 0xB1, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
- 0x2561: 0xB2, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
- 0x2562: 0xB4, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
- 0x2563: 0xB5, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
- 0x2564: 0xB6, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
- 0x2565: 0xB7, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
- 0x2566: 0xB8, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
- 0x2567: 0xB9, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
- 0x2568: 0xBA, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
- 0x2569: 0xBB, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
- 0x256A: 0xBC, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
- 0x256B: 0xBD, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
- 0x256C: 0xBE, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
- 0x2580: 0x8B, # UPPER HALF BLOCK
- 0x2584: 0x8C, # LOWER HALF BLOCK
- 0x2588: 0x8D, # FULL BLOCK
- 0x258C: 0x8E, # LEFT HALF BLOCK
- 0x2590: 0x8F, # RIGHT HALF BLOCK
- 0x2591: 0x90, # LIGHT SHADE
- 0x2592: 0x91, # MEDIUM SHADE
- 0x2593: 0x92, # DARK SHADE
- 0x25A0: 0x94, # BLACK SQUARE
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/koi8_u.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/koi8_u.py (original)
+++ python/branches/p3yk/Lib/encodings/koi8_u.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\u042a' # 0xFF -> CYRILLIC CAPITAL LETTER HARD SIGN
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x00A0: 0x9A, # NO-BREAK SPACE
- 0x00A9: 0xBF, # COPYRIGHT SIGN
- 0x00B0: 0x9C, # DEGREE SIGN
- 0x00B2: 0x9D, # SUPERSCRIPT TWO
- 0x00B7: 0x9E, # MIDDLE DOT
- 0x00F7: 0x9F, # DIVISION SIGN
- 0x0401: 0xB3, # CYRILLIC CAPITAL LETTER IO
- 0x0404: 0xB4, # CYRILLIC CAPITAL LETTER UKRAINIAN IE
- 0x0406: 0xB6, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
- 0x0407: 0xB7, # CYRILLIC CAPITAL LETTER YI (UKRAINIAN)
- 0x0410: 0xE1, # CYRILLIC CAPITAL LETTER A
- 0x0411: 0xE2, # CYRILLIC CAPITAL LETTER BE
- 0x0412: 0xF7, # CYRILLIC CAPITAL LETTER VE
- 0x0413: 0xE7, # CYRILLIC CAPITAL LETTER GHE
- 0x0414: 0xE4, # CYRILLIC CAPITAL LETTER DE
- 0x0415: 0xE5, # CYRILLIC CAPITAL LETTER IE
- 0x0416: 0xF6, # CYRILLIC CAPITAL LETTER ZHE
- 0x0417: 0xFA, # CYRILLIC CAPITAL LETTER ZE
- 0x0418: 0xE9, # CYRILLIC CAPITAL LETTER I
- 0x0419: 0xEA, # CYRILLIC CAPITAL LETTER SHORT I
- 0x041A: 0xEB, # CYRILLIC CAPITAL LETTER KA
- 0x041B: 0xEC, # CYRILLIC CAPITAL LETTER EL
- 0x041C: 0xED, # CYRILLIC CAPITAL LETTER EM
- 0x041D: 0xEE, # CYRILLIC CAPITAL LETTER EN
- 0x041E: 0xEF, # CYRILLIC CAPITAL LETTER O
- 0x041F: 0xF0, # CYRILLIC CAPITAL LETTER PE
- 0x0420: 0xF2, # CYRILLIC CAPITAL LETTER ER
- 0x0421: 0xF3, # CYRILLIC CAPITAL LETTER ES
- 0x0422: 0xF4, # CYRILLIC CAPITAL LETTER TE
- 0x0423: 0xF5, # CYRILLIC CAPITAL LETTER U
- 0x0424: 0xE6, # CYRILLIC CAPITAL LETTER EF
- 0x0425: 0xE8, # CYRILLIC CAPITAL LETTER HA
- 0x0426: 0xE3, # CYRILLIC CAPITAL LETTER TSE
- 0x0427: 0xFE, # CYRILLIC CAPITAL LETTER CHE
- 0x0428: 0xFB, # CYRILLIC CAPITAL LETTER SHA
- 0x0429: 0xFD, # CYRILLIC CAPITAL LETTER SHCHA
- 0x042A: 0xFF, # CYRILLIC CAPITAL LETTER HARD SIGN
- 0x042B: 0xF9, # CYRILLIC CAPITAL LETTER YERU
- 0x042C: 0xF8, # CYRILLIC CAPITAL LETTER SOFT SIGN
- 0x042D: 0xFC, # CYRILLIC CAPITAL LETTER E
- 0x042E: 0xE0, # CYRILLIC CAPITAL LETTER YU
- 0x042F: 0xF1, # CYRILLIC CAPITAL LETTER YA
- 0x0430: 0xC1, # CYRILLIC SMALL LETTER A
- 0x0431: 0xC2, # CYRILLIC SMALL LETTER BE
- 0x0432: 0xD7, # CYRILLIC SMALL LETTER VE
- 0x0433: 0xC7, # CYRILLIC SMALL LETTER GHE
- 0x0434: 0xC4, # CYRILLIC SMALL LETTER DE
- 0x0435: 0xC5, # CYRILLIC SMALL LETTER IE
- 0x0436: 0xD6, # CYRILLIC SMALL LETTER ZHE
- 0x0437: 0xDA, # CYRILLIC SMALL LETTER ZE
- 0x0438: 0xC9, # CYRILLIC SMALL LETTER I
- 0x0439: 0xCA, # CYRILLIC SMALL LETTER SHORT I
- 0x043A: 0xCB, # CYRILLIC SMALL LETTER KA
- 0x043B: 0xCC, # CYRILLIC SMALL LETTER EL
- 0x043C: 0xCD, # CYRILLIC SMALL LETTER EM
- 0x043D: 0xCE, # CYRILLIC SMALL LETTER EN
- 0x043E: 0xCF, # CYRILLIC SMALL LETTER O
- 0x043F: 0xD0, # CYRILLIC SMALL LETTER PE
- 0x0440: 0xD2, # CYRILLIC SMALL LETTER ER
- 0x0441: 0xD3, # CYRILLIC SMALL LETTER ES
- 0x0442: 0xD4, # CYRILLIC SMALL LETTER TE
- 0x0443: 0xD5, # CYRILLIC SMALL LETTER U
- 0x0444: 0xC6, # CYRILLIC SMALL LETTER EF
- 0x0445: 0xC8, # CYRILLIC SMALL LETTER HA
- 0x0446: 0xC3, # CYRILLIC SMALL LETTER TSE
- 0x0447: 0xDE, # CYRILLIC SMALL LETTER CHE
- 0x0448: 0xDB, # CYRILLIC SMALL LETTER SHA
- 0x0449: 0xDD, # CYRILLIC SMALL LETTER SHCHA
- 0x044A: 0xDF, # CYRILLIC SMALL LETTER HARD SIGN
- 0x044B: 0xD9, # CYRILLIC SMALL LETTER YERU
- 0x044C: 0xD8, # CYRILLIC SMALL LETTER SOFT SIGN
- 0x044D: 0xDC, # CYRILLIC SMALL LETTER E
- 0x044E: 0xC0, # CYRILLIC SMALL LETTER YU
- 0x044F: 0xD1, # CYRILLIC SMALL LETTER YA
- 0x0451: 0xA3, # CYRILLIC SMALL LETTER IO
- 0x0454: 0xA4, # CYRILLIC SMALL LETTER UKRAINIAN IE
- 0x0456: 0xA6, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
- 0x0457: 0xA7, # CYRILLIC SMALL LETTER YI (UKRAINIAN)
- 0x0490: 0xBD, # CYRILLIC CAPITAL LETTER UKRAINIAN GHE WITH UPTURN
- 0x0491: 0xAD, # CYRILLIC SMALL LETTER UKRAINIAN GHE WITH UPTURN
- 0x2219: 0x95, # BULLET OPERATOR
- 0x221A: 0x96, # SQUARE ROOT
- 0x2248: 0x97, # ALMOST EQUAL TO
- 0x2264: 0x98, # LESS-THAN OR EQUAL TO
- 0x2265: 0x99, # GREATER-THAN OR EQUAL TO
- 0x2320: 0x93, # TOP HALF INTEGRAL
- 0x2321: 0x9B, # BOTTOM HALF INTEGRAL
- 0x2500: 0x80, # BOX DRAWINGS LIGHT HORIZONTAL
- 0x2502: 0x81, # BOX DRAWINGS LIGHT VERTICAL
- 0x250C: 0x82, # BOX DRAWINGS LIGHT DOWN AND RIGHT
- 0x2510: 0x83, # BOX DRAWINGS LIGHT DOWN AND LEFT
- 0x2514: 0x84, # BOX DRAWINGS LIGHT UP AND RIGHT
- 0x2518: 0x85, # BOX DRAWINGS LIGHT UP AND LEFT
- 0x251C: 0x86, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
- 0x2524: 0x87, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
- 0x252C: 0x88, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
- 0x2534: 0x89, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
- 0x253C: 0x8A, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
- 0x2550: 0xA0, # BOX DRAWINGS DOUBLE HORIZONTAL
- 0x2551: 0xA1, # BOX DRAWINGS DOUBLE VERTICAL
- 0x2552: 0xA2, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
- 0x2554: 0xA5, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
- 0x2557: 0xA8, # BOX DRAWINGS DOUBLE DOWN AND LEFT
- 0x2558: 0xA9, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
- 0x2559: 0xAA, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
- 0x255A: 0xAB, # BOX DRAWINGS DOUBLE UP AND RIGHT
- 0x255B: 0xAC, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
- 0x255D: 0xAE, # BOX DRAWINGS DOUBLE UP AND LEFT
- 0x255E: 0xAF, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
- 0x255F: 0xB0, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
- 0x2560: 0xB1, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
- 0x2561: 0xB2, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
- 0x2563: 0xB5, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
- 0x2566: 0xB8, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
- 0x2567: 0xB9, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
- 0x2568: 0xBA, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
- 0x2569: 0xBB, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
- 0x256A: 0xBC, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
- 0x256C: 0xBE, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
- 0x2580: 0x8B, # UPPER HALF BLOCK
- 0x2584: 0x8C, # LOWER HALF BLOCK
- 0x2588: 0x8D, # FULL BLOCK
- 0x258C: 0x8E, # LEFT HALF BLOCK
- 0x2590: 0x8F, # RIGHT HALF BLOCK
- 0x2591: 0x90, # LIGHT SHADE
- 0x2592: 0x91, # MEDIUM SHADE
- 0x2593: 0x92, # DARK SHADE
- 0x25A0: 0x94, # BLACK SQUARE
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/mac_centeuro.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/mac_centeuro.py (original)
+++ python/branches/p3yk/Lib/encodings/mac_centeuro.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\u02c7' # 0xFF -> CARON
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # CONTROL CHARACTER
- 0x0001: 0x01, # CONTROL CHARACTER
- 0x0002: 0x02, # CONTROL CHARACTER
- 0x0003: 0x03, # CONTROL CHARACTER
- 0x0004: 0x04, # CONTROL CHARACTER
- 0x0005: 0x05, # CONTROL CHARACTER
- 0x0006: 0x06, # CONTROL CHARACTER
- 0x0007: 0x07, # CONTROL CHARACTER
- 0x0008: 0x08, # CONTROL CHARACTER
- 0x0009: 0x09, # CONTROL CHARACTER
- 0x000A: 0x0A, # CONTROL CHARACTER
- 0x000B: 0x0B, # CONTROL CHARACTER
- 0x000C: 0x0C, # CONTROL CHARACTER
- 0x000D: 0x0D, # CONTROL CHARACTER
- 0x000E: 0x0E, # CONTROL CHARACTER
- 0x000F: 0x0F, # CONTROL CHARACTER
- 0x0010: 0x10, # CONTROL CHARACTER
- 0x0011: 0x11, # CONTROL CHARACTER
- 0x0012: 0x12, # CONTROL CHARACTER
- 0x0013: 0x13, # CONTROL CHARACTER
- 0x0014: 0x14, # CONTROL CHARACTER
- 0x0015: 0x15, # CONTROL CHARACTER
- 0x0016: 0x16, # CONTROL CHARACTER
- 0x0017: 0x17, # CONTROL CHARACTER
- 0x0018: 0x18, # CONTROL CHARACTER
- 0x0019: 0x19, # CONTROL CHARACTER
- 0x001A: 0x1A, # CONTROL CHARACTER
- 0x001B: 0x1B, # CONTROL CHARACTER
- 0x001C: 0x1C, # CONTROL CHARACTER
- 0x001D: 0x1D, # CONTROL CHARACTER
- 0x001E: 0x1E, # CONTROL CHARACTER
- 0x001F: 0x1F, # CONTROL CHARACTER
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # CONTROL CHARACTER
- 0x00A0: 0xCA, # NO-BREAK SPACE
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A7: 0xA4, # SECTION SIGN
- 0x00A8: 0xAC, # DIAERESIS
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AB: 0xC7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xC2, # NOT SIGN
- 0x00AE: 0xA8, # REGISTERED SIGN
- 0x00B0: 0xA1, # DEGREE SIGN
- 0x00B6: 0xA6, # PILCROW SIGN
- 0x00BB: 0xC8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00C1: 0xE7, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CD: 0xEA, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00D3: 0xEE, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xEF, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D5: 0xCD, # LATIN CAPITAL LETTER O WITH TILDE
- 0x00D6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00DA: 0xF2, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DC: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DD: 0xF8, # LATIN CAPITAL LETTER Y WITH ACUTE
- 0x00DF: 0xA7, # LATIN SMALL LETTER SHARP S
- 0x00E1: 0x87, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E4: 0x8A, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E9: 0x8E, # LATIN SMALL LETTER E WITH ACUTE
- 0x00ED: 0x92, # LATIN SMALL LETTER I WITH ACUTE
- 0x00F3: 0x97, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F5: 0x9B, # LATIN SMALL LETTER O WITH TILDE
- 0x00F6: 0x9A, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xD6, # DIVISION SIGN
- 0x00FA: 0x9C, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FC: 0x9F, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x00FD: 0xF9, # LATIN SMALL LETTER Y WITH ACUTE
- 0x0100: 0x81, # LATIN CAPITAL LETTER A WITH MACRON
- 0x0101: 0x82, # LATIN SMALL LETTER A WITH MACRON
- 0x0104: 0x84, # LATIN CAPITAL LETTER A WITH OGONEK
- 0x0105: 0x88, # LATIN SMALL LETTER A WITH OGONEK
- 0x0106: 0x8C, # LATIN CAPITAL LETTER C WITH ACUTE
- 0x0107: 0x8D, # LATIN SMALL LETTER C WITH ACUTE
- 0x010C: 0x89, # LATIN CAPITAL LETTER C WITH CARON
- 0x010D: 0x8B, # LATIN SMALL LETTER C WITH CARON
- 0x010E: 0x91, # LATIN CAPITAL LETTER D WITH CARON
- 0x010F: 0x93, # LATIN SMALL LETTER D WITH CARON
- 0x0112: 0x94, # LATIN CAPITAL LETTER E WITH MACRON
- 0x0113: 0x95, # LATIN SMALL LETTER E WITH MACRON
- 0x0116: 0x96, # LATIN CAPITAL LETTER E WITH DOT ABOVE
- 0x0117: 0x98, # LATIN SMALL LETTER E WITH DOT ABOVE
- 0x0118: 0xA2, # LATIN CAPITAL LETTER E WITH OGONEK
- 0x0119: 0xAB, # LATIN SMALL LETTER E WITH OGONEK
- 0x011A: 0x9D, # LATIN CAPITAL LETTER E WITH CARON
- 0x011B: 0x9E, # LATIN SMALL LETTER E WITH CARON
- 0x0122: 0xFE, # LATIN CAPITAL LETTER G WITH CEDILLA
- 0x0123: 0xAE, # LATIN SMALL LETTER G WITH CEDILLA
- 0x012A: 0xB1, # LATIN CAPITAL LETTER I WITH MACRON
- 0x012B: 0xB4, # LATIN SMALL LETTER I WITH MACRON
- 0x012E: 0xAF, # LATIN CAPITAL LETTER I WITH OGONEK
- 0x012F: 0xB0, # LATIN SMALL LETTER I WITH OGONEK
- 0x0136: 0xB5, # LATIN CAPITAL LETTER K WITH CEDILLA
- 0x0137: 0xFA, # LATIN SMALL LETTER K WITH CEDILLA
- 0x0139: 0xBD, # LATIN CAPITAL LETTER L WITH ACUTE
- 0x013A: 0xBE, # LATIN SMALL LETTER L WITH ACUTE
- 0x013B: 0xB9, # LATIN CAPITAL LETTER L WITH CEDILLA
- 0x013C: 0xBA, # LATIN SMALL LETTER L WITH CEDILLA
- 0x013D: 0xBB, # LATIN CAPITAL LETTER L WITH CARON
- 0x013E: 0xBC, # LATIN SMALL LETTER L WITH CARON
- 0x0141: 0xFC, # LATIN CAPITAL LETTER L WITH STROKE
- 0x0142: 0xB8, # LATIN SMALL LETTER L WITH STROKE
- 0x0143: 0xC1, # LATIN CAPITAL LETTER N WITH ACUTE
- 0x0144: 0xC4, # LATIN SMALL LETTER N WITH ACUTE
- 0x0145: 0xBF, # LATIN CAPITAL LETTER N WITH CEDILLA
- 0x0146: 0xC0, # LATIN SMALL LETTER N WITH CEDILLA
- 0x0147: 0xC5, # LATIN CAPITAL LETTER N WITH CARON
- 0x0148: 0xCB, # LATIN SMALL LETTER N WITH CARON
- 0x014C: 0xCF, # LATIN CAPITAL LETTER O WITH MACRON
- 0x014D: 0xD8, # LATIN SMALL LETTER O WITH MACRON
- 0x0150: 0xCC, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
- 0x0151: 0xCE, # LATIN SMALL LETTER O WITH DOUBLE ACUTE
- 0x0154: 0xD9, # LATIN CAPITAL LETTER R WITH ACUTE
- 0x0155: 0xDA, # LATIN SMALL LETTER R WITH ACUTE
- 0x0156: 0xDF, # LATIN CAPITAL LETTER R WITH CEDILLA
- 0x0157: 0xE0, # LATIN SMALL LETTER R WITH CEDILLA
- 0x0158: 0xDB, # LATIN CAPITAL LETTER R WITH CARON
- 0x0159: 0xDE, # LATIN SMALL LETTER R WITH CARON
- 0x015A: 0xE5, # LATIN CAPITAL LETTER S WITH ACUTE
- 0x015B: 0xE6, # LATIN SMALL LETTER S WITH ACUTE
- 0x0160: 0xE1, # LATIN CAPITAL LETTER S WITH CARON
- 0x0161: 0xE4, # LATIN SMALL LETTER S WITH CARON
- 0x0164: 0xE8, # LATIN CAPITAL LETTER T WITH CARON
- 0x0165: 0xE9, # LATIN SMALL LETTER T WITH CARON
- 0x016A: 0xED, # LATIN CAPITAL LETTER U WITH MACRON
- 0x016B: 0xF0, # LATIN SMALL LETTER U WITH MACRON
- 0x016E: 0xF1, # LATIN CAPITAL LETTER U WITH RING ABOVE
- 0x016F: 0xF3, # LATIN SMALL LETTER U WITH RING ABOVE
- 0x0170: 0xF4, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
- 0x0171: 0xF5, # LATIN SMALL LETTER U WITH DOUBLE ACUTE
- 0x0172: 0xF6, # LATIN CAPITAL LETTER U WITH OGONEK
- 0x0173: 0xF7, # LATIN SMALL LETTER U WITH OGONEK
- 0x0179: 0x8F, # LATIN CAPITAL LETTER Z WITH ACUTE
- 0x017A: 0x90, # LATIN SMALL LETTER Z WITH ACUTE
- 0x017B: 0xFB, # LATIN CAPITAL LETTER Z WITH DOT ABOVE
- 0x017C: 0xFD, # LATIN SMALL LETTER Z WITH DOT ABOVE
- 0x017D: 0xEB, # LATIN CAPITAL LETTER Z WITH CARON
- 0x017E: 0xEC, # LATIN SMALL LETTER Z WITH CARON
- 0x02C7: 0xFF, # CARON
- 0x2013: 0xD0, # EN DASH
- 0x2014: 0xD1, # EM DASH
- 0x2018: 0xD4, # LEFT SINGLE QUOTATION MARK
- 0x2019: 0xD5, # RIGHT SINGLE QUOTATION MARK
- 0x201A: 0xE2, # SINGLE LOW-9 QUOTATION MARK
- 0x201C: 0xD2, # LEFT DOUBLE QUOTATION MARK
- 0x201D: 0xD3, # RIGHT DOUBLE QUOTATION MARK
- 0x201E: 0xE3, # DOUBLE LOW-9 QUOTATION MARK
- 0x2020: 0xA0, # DAGGER
- 0x2022: 0xA5, # BULLET
- 0x2026: 0xC9, # HORIZONTAL ELLIPSIS
- 0x2039: 0xDC, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
- 0x203A: 0xDD, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
- 0x2122: 0xAA, # TRADE MARK SIGN
- 0x2202: 0xB6, # PARTIAL DIFFERENTIAL
- 0x2206: 0xC6, # INCREMENT
- 0x2211: 0xB7, # N-ARY SUMMATION
- 0x221A: 0xC3, # SQUARE ROOT
- 0x2260: 0xAD, # NOT EQUAL TO
- 0x2264: 0xB2, # LESS-THAN OR EQUAL TO
- 0x2265: 0xB3, # GREATER-THAN OR EQUAL TO
- 0x25CA: 0xD7, # LOZENGE
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/mac_croatian.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/mac_croatian.py (original)
+++ python/branches/p3yk/Lib/encodings/mac_croatian.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\u02c7' # 0xFF -> CARON
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # CONTROL CHARACTER
- 0x0001: 0x01, # CONTROL CHARACTER
- 0x0002: 0x02, # CONTROL CHARACTER
- 0x0003: 0x03, # CONTROL CHARACTER
- 0x0004: 0x04, # CONTROL CHARACTER
- 0x0005: 0x05, # CONTROL CHARACTER
- 0x0006: 0x06, # CONTROL CHARACTER
- 0x0007: 0x07, # CONTROL CHARACTER
- 0x0008: 0x08, # CONTROL CHARACTER
- 0x0009: 0x09, # CONTROL CHARACTER
- 0x000A: 0x0A, # CONTROL CHARACTER
- 0x000B: 0x0B, # CONTROL CHARACTER
- 0x000C: 0x0C, # CONTROL CHARACTER
- 0x000D: 0x0D, # CONTROL CHARACTER
- 0x000E: 0x0E, # CONTROL CHARACTER
- 0x000F: 0x0F, # CONTROL CHARACTER
- 0x0010: 0x10, # CONTROL CHARACTER
- 0x0011: 0x11, # CONTROL CHARACTER
- 0x0012: 0x12, # CONTROL CHARACTER
- 0x0013: 0x13, # CONTROL CHARACTER
- 0x0014: 0x14, # CONTROL CHARACTER
- 0x0015: 0x15, # CONTROL CHARACTER
- 0x0016: 0x16, # CONTROL CHARACTER
- 0x0017: 0x17, # CONTROL CHARACTER
- 0x0018: 0x18, # CONTROL CHARACTER
- 0x0019: 0x19, # CONTROL CHARACTER
- 0x001A: 0x1A, # CONTROL CHARACTER
- 0x001B: 0x1B, # CONTROL CHARACTER
- 0x001C: 0x1C, # CONTROL CHARACTER
- 0x001D: 0x1D, # CONTROL CHARACTER
- 0x001E: 0x1E, # CONTROL CHARACTER
- 0x001F: 0x1F, # CONTROL CHARACTER
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # CONTROL CHARACTER
- 0x00A0: 0xCA, # NO-BREAK SPACE
- 0x00A1: 0xC1, # INVERTED EXCLAMATION MARK
- 0x00A2: 0xA2, # CENT SIGN
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A7: 0xA4, # SECTION SIGN
- 0x00A8: 0xAC, # DIAERESIS
- 0x00A9: 0xD9, # COPYRIGHT SIGN
- 0x00AA: 0xBB, # FEMININE ORDINAL INDICATOR
- 0x00AB: 0xC7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xC2, # NOT SIGN
- 0x00AE: 0xA8, # REGISTERED SIGN
- 0x00AF: 0xF8, # MACRON
- 0x00B0: 0xA1, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B4: 0xAB, # ACUTE ACCENT
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B6: 0xA6, # PILCROW SIGN
- 0x00B7: 0xE1, # MIDDLE DOT
- 0x00B8: 0xFC, # CEDILLA
- 0x00BA: 0xBC, # MASCULINE ORDINAL INDICATOR
- 0x00BB: 0xDF, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BF: 0xC0, # INVERTED QUESTION MARK
- 0x00C0: 0xCB, # LATIN CAPITAL LETTER A WITH GRAVE
- 0x00C1: 0xE7, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0xE5, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C3: 0xCC, # LATIN CAPITAL LETTER A WITH TILDE
- 0x00C4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C5: 0x81, # LATIN CAPITAL LETTER A WITH RING ABOVE
- 0x00C6: 0xDE, # LATIN CAPITAL LETTER AE
- 0x00C7: 0x82, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C8: 0xE9, # LATIN CAPITAL LETTER E WITH GRAVE
- 0x00C9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CA: 0xFD, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
- 0x00CB: 0xFA, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CC: 0xED, # LATIN CAPITAL LETTER I WITH GRAVE
- 0x00CD: 0xEA, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0xEB, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00CF: 0xEC, # LATIN CAPITAL LETTER I WITH DIAERESIS
- 0x00D1: 0x84, # LATIN CAPITAL LETTER N WITH TILDE
- 0x00D2: 0xF1, # LATIN CAPITAL LETTER O WITH GRAVE
- 0x00D3: 0xEE, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xEF, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D5: 0xCD, # LATIN CAPITAL LETTER O WITH TILDE
- 0x00D6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D8: 0xAF, # LATIN CAPITAL LETTER O WITH STROKE
- 0x00D9: 0xF4, # LATIN CAPITAL LETTER U WITH GRAVE
- 0x00DA: 0xF2, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DB: 0xF3, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
- 0x00DC: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DF: 0xA7, # LATIN SMALL LETTER SHARP S
- 0x00E0: 0x88, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E1: 0x87, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E3: 0x8B, # LATIN SMALL LETTER A WITH TILDE
- 0x00E4: 0x8A, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E5: 0x8C, # LATIN SMALL LETTER A WITH RING ABOVE
- 0x00E6: 0xFE, # LATIN SMALL LETTER AE
- 0x00E7: 0x8D, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0x8F, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0x8E, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00EC: 0x93, # LATIN SMALL LETTER I WITH GRAVE
- 0x00ED: 0x92, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F1: 0x96, # LATIN SMALL LETTER N WITH TILDE
- 0x00F2: 0x98, # LATIN SMALL LETTER O WITH GRAVE
- 0x00F3: 0x97, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F5: 0x9B, # LATIN SMALL LETTER O WITH TILDE
- 0x00F6: 0x9A, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xD6, # DIVISION SIGN
- 0x00F8: 0xBF, # LATIN SMALL LETTER O WITH STROKE
- 0x00F9: 0x9D, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FA: 0x9C, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0x9E, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0x9F, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x0106: 0xC6, # LATIN CAPITAL LETTER C WITH ACUTE
- 0x0107: 0xE6, # LATIN SMALL LETTER C WITH ACUTE
- 0x010C: 0xC8, # LATIN CAPITAL LETTER C WITH CARON
- 0x010D: 0xE8, # LATIN SMALL LETTER C WITH CARON
- 0x0110: 0xD0, # LATIN CAPITAL LETTER D WITH STROKE
- 0x0111: 0xF0, # LATIN SMALL LETTER D WITH STROKE
- 0x0131: 0xF5, # LATIN SMALL LETTER DOTLESS I
- 0x0152: 0xCE, # LATIN CAPITAL LIGATURE OE
- 0x0153: 0xCF, # LATIN SMALL LIGATURE OE
- 0x0160: 0xA9, # LATIN CAPITAL LETTER S WITH CARON
- 0x0161: 0xB9, # LATIN SMALL LETTER S WITH CARON
- 0x017D: 0xAE, # LATIN CAPITAL LETTER Z WITH CARON
- 0x017E: 0xBE, # LATIN SMALL LETTER Z WITH CARON
- 0x0192: 0xC4, # LATIN SMALL LETTER F WITH HOOK
- 0x02C6: 0xF6, # MODIFIER LETTER CIRCUMFLEX ACCENT
- 0x02C7: 0xFF, # CARON
- 0x02DA: 0xFB, # RING ABOVE
- 0x02DC: 0xF7, # SMALL TILDE
- 0x03A9: 0xBD, # GREEK CAPITAL LETTER OMEGA
- 0x03C0: 0xF9, # GREEK SMALL LETTER PI
- 0x2013: 0xE0, # EN DASH
- 0x2014: 0xD1, # EM DASH
- 0x2018: 0xD4, # LEFT SINGLE QUOTATION MARK
- 0x2019: 0xD5, # RIGHT SINGLE QUOTATION MARK
- 0x201A: 0xE2, # SINGLE LOW-9 QUOTATION MARK
- 0x201C: 0xD2, # LEFT DOUBLE QUOTATION MARK
- 0x201D: 0xD3, # RIGHT DOUBLE QUOTATION MARK
- 0x201E: 0xE3, # DOUBLE LOW-9 QUOTATION MARK
- 0x2020: 0xA0, # DAGGER
- 0x2022: 0xA5, # BULLET
- 0x2026: 0xC9, # HORIZONTAL ELLIPSIS
- 0x2030: 0xE4, # PER MILLE SIGN
- 0x2039: 0xDC, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
- 0x203A: 0xDD, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
- 0x2044: 0xDA, # FRACTION SLASH
- 0x20AC: 0xDB, # EURO SIGN
- 0x2122: 0xAA, # TRADE MARK SIGN
- 0x2202: 0xB6, # PARTIAL DIFFERENTIAL
- 0x2206: 0xB4, # INCREMENT
- 0x220F: 0xB8, # N-ARY PRODUCT
- 0x2211: 0xB7, # N-ARY SUMMATION
- 0x221A: 0xC3, # SQUARE ROOT
- 0x221E: 0xB0, # INFINITY
- 0x222B: 0xBA, # INTEGRAL
- 0x2248: 0xC5, # ALMOST EQUAL TO
- 0x2260: 0xAD, # NOT EQUAL TO
- 0x2264: 0xB2, # LESS-THAN OR EQUAL TO
- 0x2265: 0xB3, # GREATER-THAN OR EQUAL TO
- 0x25CA: 0xD7, # LOZENGE
- 0xF8FF: 0xD8, # Apple logo
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/mac_cyrillic.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/mac_cyrillic.py (original)
+++ python/branches/p3yk/Lib/encodings/mac_cyrillic.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\u20ac' # 0xFF -> EURO SIGN
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # CONTROL CHARACTER
- 0x0001: 0x01, # CONTROL CHARACTER
- 0x0002: 0x02, # CONTROL CHARACTER
- 0x0003: 0x03, # CONTROL CHARACTER
- 0x0004: 0x04, # CONTROL CHARACTER
- 0x0005: 0x05, # CONTROL CHARACTER
- 0x0006: 0x06, # CONTROL CHARACTER
- 0x0007: 0x07, # CONTROL CHARACTER
- 0x0008: 0x08, # CONTROL CHARACTER
- 0x0009: 0x09, # CONTROL CHARACTER
- 0x000A: 0x0A, # CONTROL CHARACTER
- 0x000B: 0x0B, # CONTROL CHARACTER
- 0x000C: 0x0C, # CONTROL CHARACTER
- 0x000D: 0x0D, # CONTROL CHARACTER
- 0x000E: 0x0E, # CONTROL CHARACTER
- 0x000F: 0x0F, # CONTROL CHARACTER
- 0x0010: 0x10, # CONTROL CHARACTER
- 0x0011: 0x11, # CONTROL CHARACTER
- 0x0012: 0x12, # CONTROL CHARACTER
- 0x0013: 0x13, # CONTROL CHARACTER
- 0x0014: 0x14, # CONTROL CHARACTER
- 0x0015: 0x15, # CONTROL CHARACTER
- 0x0016: 0x16, # CONTROL CHARACTER
- 0x0017: 0x17, # CONTROL CHARACTER
- 0x0018: 0x18, # CONTROL CHARACTER
- 0x0019: 0x19, # CONTROL CHARACTER
- 0x001A: 0x1A, # CONTROL CHARACTER
- 0x001B: 0x1B, # CONTROL CHARACTER
- 0x001C: 0x1C, # CONTROL CHARACTER
- 0x001D: 0x1D, # CONTROL CHARACTER
- 0x001E: 0x1E, # CONTROL CHARACTER
- 0x001F: 0x1F, # CONTROL CHARACTER
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # CONTROL CHARACTER
- 0x00A0: 0xCA, # NO-BREAK SPACE
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A7: 0xA4, # SECTION SIGN
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AB: 0xC7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xC2, # NOT SIGN
- 0x00AE: 0xA8, # REGISTERED SIGN
- 0x00B0: 0xA1, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B6: 0xA6, # PILCROW SIGN
- 0x00BB: 0xC8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00F7: 0xD6, # DIVISION SIGN
- 0x0192: 0xC4, # LATIN SMALL LETTER F WITH HOOK
- 0x0401: 0xDD, # CYRILLIC CAPITAL LETTER IO
- 0x0402: 0xAB, # CYRILLIC CAPITAL LETTER DJE
- 0x0403: 0xAE, # CYRILLIC CAPITAL LETTER GJE
- 0x0404: 0xB8, # CYRILLIC CAPITAL LETTER UKRAINIAN IE
- 0x0405: 0xC1, # CYRILLIC CAPITAL LETTER DZE
- 0x0406: 0xA7, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
- 0x0407: 0xBA, # CYRILLIC CAPITAL LETTER YI
- 0x0408: 0xB7, # CYRILLIC CAPITAL LETTER JE
- 0x0409: 0xBC, # CYRILLIC CAPITAL LETTER LJE
- 0x040A: 0xBE, # CYRILLIC CAPITAL LETTER NJE
- 0x040B: 0xCB, # CYRILLIC CAPITAL LETTER TSHE
- 0x040C: 0xCD, # CYRILLIC CAPITAL LETTER KJE
- 0x040E: 0xD8, # CYRILLIC CAPITAL LETTER SHORT U
- 0x040F: 0xDA, # CYRILLIC CAPITAL LETTER DZHE
- 0x0410: 0x80, # CYRILLIC CAPITAL LETTER A
- 0x0411: 0x81, # CYRILLIC CAPITAL LETTER BE
- 0x0412: 0x82, # CYRILLIC CAPITAL LETTER VE
- 0x0413: 0x83, # CYRILLIC CAPITAL LETTER GHE
- 0x0414: 0x84, # CYRILLIC CAPITAL LETTER DE
- 0x0415: 0x85, # CYRILLIC CAPITAL LETTER IE
- 0x0416: 0x86, # CYRILLIC CAPITAL LETTER ZHE
- 0x0417: 0x87, # CYRILLIC CAPITAL LETTER ZE
- 0x0418: 0x88, # CYRILLIC CAPITAL LETTER I
- 0x0419: 0x89, # CYRILLIC CAPITAL LETTER SHORT I
- 0x041A: 0x8A, # CYRILLIC CAPITAL LETTER KA
- 0x041B: 0x8B, # CYRILLIC CAPITAL LETTER EL
- 0x041C: 0x8C, # CYRILLIC CAPITAL LETTER EM
- 0x041D: 0x8D, # CYRILLIC CAPITAL LETTER EN
- 0x041E: 0x8E, # CYRILLIC CAPITAL LETTER O
- 0x041F: 0x8F, # CYRILLIC CAPITAL LETTER PE
- 0x0420: 0x90, # CYRILLIC CAPITAL LETTER ER
- 0x0421: 0x91, # CYRILLIC CAPITAL LETTER ES
- 0x0422: 0x92, # CYRILLIC CAPITAL LETTER TE
- 0x0423: 0x93, # CYRILLIC CAPITAL LETTER U
- 0x0424: 0x94, # CYRILLIC CAPITAL LETTER EF
- 0x0425: 0x95, # CYRILLIC CAPITAL LETTER HA
- 0x0426: 0x96, # CYRILLIC CAPITAL LETTER TSE
- 0x0427: 0x97, # CYRILLIC CAPITAL LETTER CHE
- 0x0428: 0x98, # CYRILLIC CAPITAL LETTER SHA
- 0x0429: 0x99, # CYRILLIC CAPITAL LETTER SHCHA
- 0x042A: 0x9A, # CYRILLIC CAPITAL LETTER HARD SIGN
- 0x042B: 0x9B, # CYRILLIC CAPITAL LETTER YERU
- 0x042C: 0x9C, # CYRILLIC CAPITAL LETTER SOFT SIGN
- 0x042D: 0x9D, # CYRILLIC CAPITAL LETTER E
- 0x042E: 0x9E, # CYRILLIC CAPITAL LETTER YU
- 0x042F: 0x9F, # CYRILLIC CAPITAL LETTER YA
- 0x0430: 0xE0, # CYRILLIC SMALL LETTER A
- 0x0431: 0xE1, # CYRILLIC SMALL LETTER BE
- 0x0432: 0xE2, # CYRILLIC SMALL LETTER VE
- 0x0433: 0xE3, # CYRILLIC SMALL LETTER GHE
- 0x0434: 0xE4, # CYRILLIC SMALL LETTER DE
- 0x0435: 0xE5, # CYRILLIC SMALL LETTER IE
- 0x0436: 0xE6, # CYRILLIC SMALL LETTER ZHE
- 0x0437: 0xE7, # CYRILLIC SMALL LETTER ZE
- 0x0438: 0xE8, # CYRILLIC SMALL LETTER I
- 0x0439: 0xE9, # CYRILLIC SMALL LETTER SHORT I
- 0x043A: 0xEA, # CYRILLIC SMALL LETTER KA
- 0x043B: 0xEB, # CYRILLIC SMALL LETTER EL
- 0x043C: 0xEC, # CYRILLIC SMALL LETTER EM
- 0x043D: 0xED, # CYRILLIC SMALL LETTER EN
- 0x043E: 0xEE, # CYRILLIC SMALL LETTER O
- 0x043F: 0xEF, # CYRILLIC SMALL LETTER PE
- 0x0440: 0xF0, # CYRILLIC SMALL LETTER ER
- 0x0441: 0xF1, # CYRILLIC SMALL LETTER ES
- 0x0442: 0xF2, # CYRILLIC SMALL LETTER TE
- 0x0443: 0xF3, # CYRILLIC SMALL LETTER U
- 0x0444: 0xF4, # CYRILLIC SMALL LETTER EF
- 0x0445: 0xF5, # CYRILLIC SMALL LETTER HA
- 0x0446: 0xF6, # CYRILLIC SMALL LETTER TSE
- 0x0447: 0xF7, # CYRILLIC SMALL LETTER CHE
- 0x0448: 0xF8, # CYRILLIC SMALL LETTER SHA
- 0x0449: 0xF9, # CYRILLIC SMALL LETTER SHCHA
- 0x044A: 0xFA, # CYRILLIC SMALL LETTER HARD SIGN
- 0x044B: 0xFB, # CYRILLIC SMALL LETTER YERU
- 0x044C: 0xFC, # CYRILLIC SMALL LETTER SOFT SIGN
- 0x044D: 0xFD, # CYRILLIC SMALL LETTER E
- 0x044E: 0xFE, # CYRILLIC SMALL LETTER YU
- 0x044F: 0xDF, # CYRILLIC SMALL LETTER YA
- 0x0451: 0xDE, # CYRILLIC SMALL LETTER IO
- 0x0452: 0xAC, # CYRILLIC SMALL LETTER DJE
- 0x0453: 0xAF, # CYRILLIC SMALL LETTER GJE
- 0x0454: 0xB9, # CYRILLIC SMALL LETTER UKRAINIAN IE
- 0x0455: 0xCF, # CYRILLIC SMALL LETTER DZE
- 0x0456: 0xB4, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
- 0x0457: 0xBB, # CYRILLIC SMALL LETTER YI
- 0x0458: 0xC0, # CYRILLIC SMALL LETTER JE
- 0x0459: 0xBD, # CYRILLIC SMALL LETTER LJE
- 0x045A: 0xBF, # CYRILLIC SMALL LETTER NJE
- 0x045B: 0xCC, # CYRILLIC SMALL LETTER TSHE
- 0x045C: 0xCE, # CYRILLIC SMALL LETTER KJE
- 0x045E: 0xD9, # CYRILLIC SMALL LETTER SHORT U
- 0x045F: 0xDB, # CYRILLIC SMALL LETTER DZHE
- 0x0490: 0xA2, # CYRILLIC CAPITAL LETTER GHE WITH UPTURN
- 0x0491: 0xB6, # CYRILLIC SMALL LETTER GHE WITH UPTURN
- 0x2013: 0xD0, # EN DASH
- 0x2014: 0xD1, # EM DASH
- 0x2018: 0xD4, # LEFT SINGLE QUOTATION MARK
- 0x2019: 0xD5, # RIGHT SINGLE QUOTATION MARK
- 0x201C: 0xD2, # LEFT DOUBLE QUOTATION MARK
- 0x201D: 0xD3, # RIGHT DOUBLE QUOTATION MARK
- 0x201E: 0xD7, # DOUBLE LOW-9 QUOTATION MARK
- 0x2020: 0xA0, # DAGGER
- 0x2022: 0xA5, # BULLET
- 0x2026: 0xC9, # HORIZONTAL ELLIPSIS
- 0x20AC: 0xFF, # EURO SIGN
- 0x2116: 0xDC, # NUMERO SIGN
- 0x2122: 0xAA, # TRADE MARK SIGN
- 0x2206: 0xC6, # INCREMENT
- 0x221A: 0xC3, # SQUARE ROOT
- 0x221E: 0xB0, # INFINITY
- 0x2248: 0xC5, # ALMOST EQUAL TO
- 0x2260: 0xAD, # NOT EQUAL TO
- 0x2264: 0xB2, # LESS-THAN OR EQUAL TO
- 0x2265: 0xB3, # GREATER-THAN OR EQUAL TO
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/mac_farsi.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/mac_farsi.py (original)
+++ python/branches/p3yk/Lib/encodings/mac_farsi.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\u06d2' # 0xFF -> ARABIC LETTER YEH BARREE
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # CONTROL CHARACTER
- 0x0001: 0x01, # CONTROL CHARACTER
- 0x0002: 0x02, # CONTROL CHARACTER
- 0x0003: 0x03, # CONTROL CHARACTER
- 0x0004: 0x04, # CONTROL CHARACTER
- 0x0005: 0x05, # CONTROL CHARACTER
- 0x0006: 0x06, # CONTROL CHARACTER
- 0x0007: 0x07, # CONTROL CHARACTER
- 0x0008: 0x08, # CONTROL CHARACTER
- 0x0009: 0x09, # CONTROL CHARACTER
- 0x000A: 0x0A, # CONTROL CHARACTER
- 0x000B: 0x0B, # CONTROL CHARACTER
- 0x000C: 0x0C, # CONTROL CHARACTER
- 0x000D: 0x0D, # CONTROL CHARACTER
- 0x000E: 0x0E, # CONTROL CHARACTER
- 0x000F: 0x0F, # CONTROL CHARACTER
- 0x0010: 0x10, # CONTROL CHARACTER
- 0x0011: 0x11, # CONTROL CHARACTER
- 0x0012: 0x12, # CONTROL CHARACTER
- 0x0013: 0x13, # CONTROL CHARACTER
- 0x0014: 0x14, # CONTROL CHARACTER
- 0x0015: 0x15, # CONTROL CHARACTER
- 0x0016: 0x16, # CONTROL CHARACTER
- 0x0017: 0x17, # CONTROL CHARACTER
- 0x0018: 0x18, # CONTROL CHARACTER
- 0x0019: 0x19, # CONTROL CHARACTER
- 0x001A: 0x1A, # CONTROL CHARACTER
- 0x001B: 0x1B, # CONTROL CHARACTER
- 0x001C: 0x1C, # CONTROL CHARACTER
- 0x001D: 0x1D, # CONTROL CHARACTER
- 0x001E: 0x1E, # CONTROL CHARACTER
- 0x001F: 0x1F, # CONTROL CHARACTER
- 0x0020: 0x20, # SPACE, left-right
- 0x0020: 0xA0, # SPACE, right-left
- 0x0021: 0x21, # EXCLAMATION MARK, left-right
- 0x0021: 0xA1, # EXCLAMATION MARK, right-left
- 0x0022: 0x22, # QUOTATION MARK, left-right
- 0x0022: 0xA2, # QUOTATION MARK, right-left
- 0x0023: 0x23, # NUMBER SIGN, left-right
- 0x0023: 0xA3, # NUMBER SIGN, right-left
- 0x0024: 0x24, # DOLLAR SIGN, left-right
- 0x0024: 0xA4, # DOLLAR SIGN, right-left
- 0x0025: 0x25, # PERCENT SIGN, left-right
- 0x0026: 0x26, # AMPERSAND, left-right
- 0x0026: 0xA6, # AMPERSAND, right-left
- 0x0027: 0x27, # APOSTROPHE, left-right
- 0x0027: 0xA7, # APOSTROPHE, right-left
- 0x0028: 0x28, # LEFT PARENTHESIS, left-right
- 0x0028: 0xA8, # LEFT PARENTHESIS, right-left
- 0x0029: 0x29, # RIGHT PARENTHESIS, left-right
- 0x0029: 0xA9, # RIGHT PARENTHESIS, right-left
- 0x002A: 0x2A, # ASTERISK, left-right
- 0x002A: 0xAA, # ASTERISK, right-left
- 0x002B: 0x2B, # PLUS SIGN, left-right
- 0x002B: 0xAB, # PLUS SIGN, right-left
- 0x002C: 0x2C, # COMMA, left-right; in Arabic-script context, displayed as 0x066C ARABIC THOUSANDS SEPARATOR
- 0x002D: 0x2D, # HYPHEN-MINUS, left-right
- 0x002D: 0xAD, # HYPHEN-MINUS, right-left
- 0x002E: 0x2E, # FULL STOP, left-right; in Arabic-script context, displayed as 0x066B ARABIC DECIMAL SEPARATOR
- 0x002E: 0xAE, # FULL STOP, right-left
- 0x002F: 0x2F, # SOLIDUS, left-right
- 0x002F: 0xAF, # SOLIDUS, right-left
- 0x0030: 0x30, # DIGIT ZERO; in Arabic-script context, displayed as 0x06F0 EXTENDED ARABIC-INDIC DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE; in Arabic-script context, displayed as 0x06F1 EXTENDED ARABIC-INDIC DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO; in Arabic-script context, displayed as 0x06F2 EXTENDED ARABIC-INDIC DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE; in Arabic-script context, displayed as 0x06F3 EXTENDED ARABIC-INDIC DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR; in Arabic-script context, displayed as 0x06F4 EXTENDED ARABIC-INDIC DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE; in Arabic-script context, displayed as 0x06F5 EXTENDED ARABIC-INDIC DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX; in Arabic-script context, displayed as 0x06F6 EXTENDED ARABIC-INDIC DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN; in Arabic-script context, displayed as 0x06F7 EXTENDED ARABIC-INDIC DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT; in Arabic-script context, displayed as 0x06F8 EXTENDED ARABIC-INDIC DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE; in Arabic-script context, displayed as 0x06F9 EXTENDED ARABIC-INDIC DIGIT NINE
- 0x003A: 0x3A, # COLON, left-right
- 0x003A: 0xBA, # COLON, right-left
- 0x003B: 0x3B, # SEMICOLON, left-right
- 0x003C: 0x3C, # LESS-THAN SIGN, left-right
- 0x003C: 0xBC, # LESS-THAN SIGN, right-left
- 0x003D: 0x3D, # EQUALS SIGN, left-right
- 0x003D: 0xBD, # EQUALS SIGN, right-left
- 0x003E: 0x3E, # GREATER-THAN SIGN, left-right
- 0x003E: 0xBE, # GREATER-THAN SIGN, right-left
- 0x003F: 0x3F, # QUESTION MARK, left-right
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET, left-right
- 0x005B: 0xDB, # LEFT SQUARE BRACKET, right-left
- 0x005C: 0x5C, # REVERSE SOLIDUS, left-right
- 0x005C: 0xDC, # REVERSE SOLIDUS, right-left
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET, left-right
- 0x005D: 0xDD, # RIGHT SQUARE BRACKET, right-left
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT, left-right
- 0x005E: 0xDE, # CIRCUMFLEX ACCENT, right-left
- 0x005F: 0x5F, # LOW LINE, left-right
- 0x005F: 0xDF, # LOW LINE, right-left
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET, left-right
- 0x007B: 0xFB, # LEFT CURLY BRACKET, right-left
- 0x007C: 0x7C, # VERTICAL LINE, left-right
- 0x007C: 0xFC, # VERTICAL LINE, right-left
- 0x007D: 0x7D, # RIGHT CURLY BRACKET, left-right
- 0x007D: 0xFD, # RIGHT CURLY BRACKET, right-left
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # CONTROL CHARACTER
- 0x00A0: 0x81, # NO-BREAK SPACE, right-left
- 0x00AB: 0x8C, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left
- 0x00BB: 0x98, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left
- 0x00C4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C7: 0x82, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00D1: 0x84, # LATIN CAPITAL LETTER N WITH TILDE
- 0x00D6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00DC: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00E0: 0x88, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E1: 0x87, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E4: 0x8A, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E7: 0x8D, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0x8F, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0x8E, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00ED: 0x92, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F1: 0x96, # LATIN SMALL LETTER N WITH TILDE
- 0x00F3: 0x97, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F6: 0x9A, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0x9B, # DIVISION SIGN, right-left
- 0x00F9: 0x9D, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FA: 0x9C, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0x9E, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0x9F, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x060C: 0xAC, # ARABIC COMMA
- 0x061B: 0xBB, # ARABIC SEMICOLON
- 0x061F: 0xBF, # ARABIC QUESTION MARK
- 0x0621: 0xC1, # ARABIC LETTER HAMZA
- 0x0622: 0xC2, # ARABIC LETTER ALEF WITH MADDA ABOVE
- 0x0623: 0xC3, # ARABIC LETTER ALEF WITH HAMZA ABOVE
- 0x0624: 0xC4, # ARABIC LETTER WAW WITH HAMZA ABOVE
- 0x0625: 0xC5, # ARABIC LETTER ALEF WITH HAMZA BELOW
- 0x0626: 0xC6, # ARABIC LETTER YEH WITH HAMZA ABOVE
- 0x0627: 0xC7, # ARABIC LETTER ALEF
- 0x0628: 0xC8, # ARABIC LETTER BEH
- 0x0629: 0xC9, # ARABIC LETTER TEH MARBUTA
- 0x062A: 0xCA, # ARABIC LETTER TEH
- 0x062B: 0xCB, # ARABIC LETTER THEH
- 0x062C: 0xCC, # ARABIC LETTER JEEM
- 0x062D: 0xCD, # ARABIC LETTER HAH
- 0x062E: 0xCE, # ARABIC LETTER KHAH
- 0x062F: 0xCF, # ARABIC LETTER DAL
- 0x0630: 0xD0, # ARABIC LETTER THAL
- 0x0631: 0xD1, # ARABIC LETTER REH
- 0x0632: 0xD2, # ARABIC LETTER ZAIN
- 0x0633: 0xD3, # ARABIC LETTER SEEN
- 0x0634: 0xD4, # ARABIC LETTER SHEEN
- 0x0635: 0xD5, # ARABIC LETTER SAD
- 0x0636: 0xD6, # ARABIC LETTER DAD
- 0x0637: 0xD7, # ARABIC LETTER TAH
- 0x0638: 0xD8, # ARABIC LETTER ZAH
- 0x0639: 0xD9, # ARABIC LETTER AIN
- 0x063A: 0xDA, # ARABIC LETTER GHAIN
- 0x0640: 0xE0, # ARABIC TATWEEL
- 0x0641: 0xE1, # ARABIC LETTER FEH
- 0x0642: 0xE2, # ARABIC LETTER QAF
- 0x0643: 0xE3, # ARABIC LETTER KAF
- 0x0644: 0xE4, # ARABIC LETTER LAM
- 0x0645: 0xE5, # ARABIC LETTER MEEM
- 0x0646: 0xE6, # ARABIC LETTER NOON
- 0x0647: 0xE7, # ARABIC LETTER HEH
- 0x0648: 0xE8, # ARABIC LETTER WAW
- 0x0649: 0xE9, # ARABIC LETTER ALEF MAKSURA
- 0x064A: 0xEA, # ARABIC LETTER YEH
- 0x064B: 0xEB, # ARABIC FATHATAN
- 0x064C: 0xEC, # ARABIC DAMMATAN
- 0x064D: 0xED, # ARABIC KASRATAN
- 0x064E: 0xEE, # ARABIC FATHA
- 0x064F: 0xEF, # ARABIC DAMMA
- 0x0650: 0xF0, # ARABIC KASRA
- 0x0651: 0xF1, # ARABIC SHADDA
- 0x0652: 0xF2, # ARABIC SUKUN
- 0x066A: 0xA5, # ARABIC PERCENT SIGN
- 0x0679: 0xF4, # ARABIC LETTER TTEH
- 0x067E: 0xF3, # ARABIC LETTER PEH
- 0x0686: 0xF5, # ARABIC LETTER TCHEH
- 0x0688: 0xF9, # ARABIC LETTER DDAL
- 0x0691: 0xFA, # ARABIC LETTER RREH
- 0x0698: 0xFE, # ARABIC LETTER JEH
- 0x06A4: 0xF7, # ARABIC LETTER VEH
- 0x06AF: 0xF8, # ARABIC LETTER GAF
- 0x06BA: 0x8B, # ARABIC LETTER NOON GHUNNA
- 0x06D2: 0xFF, # ARABIC LETTER YEH BARREE
- 0x06D5: 0xF6, # ARABIC LETTER AE
- 0x06F0: 0xB0, # EXTENDED ARABIC-INDIC DIGIT ZERO, right-left (need override)
- 0x06F1: 0xB1, # EXTENDED ARABIC-INDIC DIGIT ONE, right-left (need override)
- 0x06F2: 0xB2, # EXTENDED ARABIC-INDIC DIGIT TWO, right-left (need override)
- 0x06F3: 0xB3, # EXTENDED ARABIC-INDIC DIGIT THREE, right-left (need override)
- 0x06F4: 0xB4, # EXTENDED ARABIC-INDIC DIGIT FOUR, right-left (need override)
- 0x06F5: 0xB5, # EXTENDED ARABIC-INDIC DIGIT FIVE, right-left (need override)
- 0x06F6: 0xB6, # EXTENDED ARABIC-INDIC DIGIT SIX, right-left (need override)
- 0x06F7: 0xB7, # EXTENDED ARABIC-INDIC DIGIT SEVEN, right-left (need override)
- 0x06F8: 0xB8, # EXTENDED ARABIC-INDIC DIGIT EIGHT, right-left (need override)
- 0x06F9: 0xB9, # EXTENDED ARABIC-INDIC DIGIT NINE, right-left (need override)
- 0x2026: 0x93, # HORIZONTAL ELLIPSIS, right-left
- 0x274A: 0xC0, # EIGHT TEARDROP-SPOKED PROPELLER ASTERISK, right-left
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/mac_greek.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/mac_greek.py (original)
+++ python/branches/p3yk/Lib/encodings/mac_greek.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\xad' # 0xFF -> SOFT HYPHEN # before Mac OS 9.2.2, was undefined
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # CONTROL CHARACTER
- 0x0001: 0x01, # CONTROL CHARACTER
- 0x0002: 0x02, # CONTROL CHARACTER
- 0x0003: 0x03, # CONTROL CHARACTER
- 0x0004: 0x04, # CONTROL CHARACTER
- 0x0005: 0x05, # CONTROL CHARACTER
- 0x0006: 0x06, # CONTROL CHARACTER
- 0x0007: 0x07, # CONTROL CHARACTER
- 0x0008: 0x08, # CONTROL CHARACTER
- 0x0009: 0x09, # CONTROL CHARACTER
- 0x000A: 0x0A, # CONTROL CHARACTER
- 0x000B: 0x0B, # CONTROL CHARACTER
- 0x000C: 0x0C, # CONTROL CHARACTER
- 0x000D: 0x0D, # CONTROL CHARACTER
- 0x000E: 0x0E, # CONTROL CHARACTER
- 0x000F: 0x0F, # CONTROL CHARACTER
- 0x0010: 0x10, # CONTROL CHARACTER
- 0x0011: 0x11, # CONTROL CHARACTER
- 0x0012: 0x12, # CONTROL CHARACTER
- 0x0013: 0x13, # CONTROL CHARACTER
- 0x0014: 0x14, # CONTROL CHARACTER
- 0x0015: 0x15, # CONTROL CHARACTER
- 0x0016: 0x16, # CONTROL CHARACTER
- 0x0017: 0x17, # CONTROL CHARACTER
- 0x0018: 0x18, # CONTROL CHARACTER
- 0x0019: 0x19, # CONTROL CHARACTER
- 0x001A: 0x1A, # CONTROL CHARACTER
- 0x001B: 0x1B, # CONTROL CHARACTER
- 0x001C: 0x1C, # CONTROL CHARACTER
- 0x001D: 0x1D, # CONTROL CHARACTER
- 0x001E: 0x1E, # CONTROL CHARACTER
- 0x001F: 0x1F, # CONTROL CHARACTER
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # CONTROL CHARACTER
- 0x00A0: 0xCA, # NO-BREAK SPACE
- 0x00A3: 0x92, # POUND SIGN
- 0x00A5: 0xB4, # YEN SIGN
- 0x00A6: 0x9B, # BROKEN BAR
- 0x00A7: 0xAC, # SECTION SIGN
- 0x00A8: 0x8C, # DIAERESIS
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AB: 0xC7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xC2, # NOT SIGN
- 0x00AD: 0xFF, # SOFT HYPHEN # before Mac OS 9.2.2, was undefined
- 0x00AE: 0xA8, # REGISTERED SIGN
- 0x00B0: 0xAE, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B2: 0x82, # SUPERSCRIPT TWO
- 0x00B3: 0x84, # SUPERSCRIPT THREE
- 0x00B7: 0xAF, # MIDDLE DOT
- 0x00B9: 0x81, # SUPERSCRIPT ONE
- 0x00BB: 0xC8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BD: 0x97, # VULGAR FRACTION ONE HALF
- 0x00C4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00D6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00DC: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DF: 0xA7, # LATIN SMALL LETTER SHARP S
- 0x00E0: 0x88, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E4: 0x8A, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E7: 0x8D, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0x8F, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0x8E, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00EE: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F6: 0x9A, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xD6, # DIVISION SIGN
- 0x00F9: 0x9D, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FB: 0x9E, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0x9F, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x0153: 0xCF, # LATIN SMALL LIGATURE OE
- 0x0384: 0x8B, # GREEK TONOS
- 0x0385: 0x87, # GREEK DIALYTIKA TONOS
- 0x0386: 0xCD, # GREEK CAPITAL LETTER ALPHA WITH TONOS
- 0x0388: 0xCE, # GREEK CAPITAL LETTER EPSILON WITH TONOS
- 0x0389: 0xD7, # GREEK CAPITAL LETTER ETA WITH TONOS
- 0x038A: 0xD8, # GREEK CAPITAL LETTER IOTA WITH TONOS
- 0x038C: 0xD9, # GREEK CAPITAL LETTER OMICRON WITH TONOS
- 0x038E: 0xDA, # GREEK CAPITAL LETTER UPSILON WITH TONOS
- 0x038F: 0xDF, # GREEK CAPITAL LETTER OMEGA WITH TONOS
- 0x0390: 0xFD, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
- 0x0391: 0xB0, # GREEK CAPITAL LETTER ALPHA
- 0x0392: 0xB5, # GREEK CAPITAL LETTER BETA
- 0x0393: 0xA1, # GREEK CAPITAL LETTER GAMMA
- 0x0394: 0xA2, # GREEK CAPITAL LETTER DELTA
- 0x0395: 0xB6, # GREEK CAPITAL LETTER EPSILON
- 0x0396: 0xB7, # GREEK CAPITAL LETTER ZETA
- 0x0397: 0xB8, # GREEK CAPITAL LETTER ETA
- 0x0398: 0xA3, # GREEK CAPITAL LETTER THETA
- 0x0399: 0xB9, # GREEK CAPITAL LETTER IOTA
- 0x039A: 0xBA, # GREEK CAPITAL LETTER KAPPA
- 0x039B: 0xA4, # GREEK CAPITAL LETTER LAMDA
- 0x039C: 0xBB, # GREEK CAPITAL LETTER MU
- 0x039D: 0xC1, # GREEK CAPITAL LETTER NU
- 0x039E: 0xA5, # GREEK CAPITAL LETTER XI
- 0x039F: 0xC3, # GREEK CAPITAL LETTER OMICRON
- 0x03A0: 0xA6, # GREEK CAPITAL LETTER PI
- 0x03A1: 0xC4, # GREEK CAPITAL LETTER RHO
- 0x03A3: 0xAA, # GREEK CAPITAL LETTER SIGMA
- 0x03A4: 0xC6, # GREEK CAPITAL LETTER TAU
- 0x03A5: 0xCB, # GREEK CAPITAL LETTER UPSILON
- 0x03A6: 0xBC, # GREEK CAPITAL LETTER PHI
- 0x03A7: 0xCC, # GREEK CAPITAL LETTER CHI
- 0x03A8: 0xBE, # GREEK CAPITAL LETTER PSI
- 0x03A9: 0xBF, # GREEK CAPITAL LETTER OMEGA
- 0x03AA: 0xAB, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
- 0x03AB: 0xBD, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
- 0x03AC: 0xC0, # GREEK SMALL LETTER ALPHA WITH TONOS
- 0x03AD: 0xDB, # GREEK SMALL LETTER EPSILON WITH TONOS
- 0x03AE: 0xDC, # GREEK SMALL LETTER ETA WITH TONOS
- 0x03AF: 0xDD, # GREEK SMALL LETTER IOTA WITH TONOS
- 0x03B0: 0xFE, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
- 0x03B1: 0xE1, # GREEK SMALL LETTER ALPHA
- 0x03B2: 0xE2, # GREEK SMALL LETTER BETA
- 0x03B3: 0xE7, # GREEK SMALL LETTER GAMMA
- 0x03B4: 0xE4, # GREEK SMALL LETTER DELTA
- 0x03B5: 0xE5, # GREEK SMALL LETTER EPSILON
- 0x03B6: 0xFA, # GREEK SMALL LETTER ZETA
- 0x03B7: 0xE8, # GREEK SMALL LETTER ETA
- 0x03B8: 0xF5, # GREEK SMALL LETTER THETA
- 0x03B9: 0xE9, # GREEK SMALL LETTER IOTA
- 0x03BA: 0xEB, # GREEK SMALL LETTER KAPPA
- 0x03BB: 0xEC, # GREEK SMALL LETTER LAMDA
- 0x03BC: 0xED, # GREEK SMALL LETTER MU
- 0x03BD: 0xEE, # GREEK SMALL LETTER NU
- 0x03BE: 0xEA, # GREEK SMALL LETTER XI
- 0x03BF: 0xEF, # GREEK SMALL LETTER OMICRON
- 0x03C0: 0xF0, # GREEK SMALL LETTER PI
- 0x03C1: 0xF2, # GREEK SMALL LETTER RHO
- 0x03C2: 0xF7, # GREEK SMALL LETTER FINAL SIGMA
- 0x03C3: 0xF3, # GREEK SMALL LETTER SIGMA
- 0x03C4: 0xF4, # GREEK SMALL LETTER TAU
- 0x03C5: 0xF9, # GREEK SMALL LETTER UPSILON
- 0x03C6: 0xE6, # GREEK SMALL LETTER PHI
- 0x03C7: 0xF8, # GREEK SMALL LETTER CHI
- 0x03C8: 0xE3, # GREEK SMALL LETTER PSI
- 0x03C9: 0xF6, # GREEK SMALL LETTER OMEGA
- 0x03CA: 0xFB, # GREEK SMALL LETTER IOTA WITH DIALYTIKA
- 0x03CB: 0xFC, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
- 0x03CC: 0xDE, # GREEK SMALL LETTER OMICRON WITH TONOS
- 0x03CD: 0xE0, # GREEK SMALL LETTER UPSILON WITH TONOS
- 0x03CE: 0xF1, # GREEK SMALL LETTER OMEGA WITH TONOS
- 0x2013: 0xD0, # EN DASH
- 0x2015: 0xD1, # HORIZONTAL BAR
- 0x2018: 0xD4, # LEFT SINGLE QUOTATION MARK
- 0x2019: 0xD5, # RIGHT SINGLE QUOTATION MARK
- 0x201C: 0xD2, # LEFT DOUBLE QUOTATION MARK
- 0x201D: 0xD3, # RIGHT DOUBLE QUOTATION MARK
- 0x2020: 0xA0, # DAGGER
- 0x2022: 0x96, # BULLET
- 0x2026: 0xC9, # HORIZONTAL ELLIPSIS
- 0x2030: 0x98, # PER MILLE SIGN
- 0x20AC: 0x9C, # EURO SIGN # before Mac OS 9.2.2, was SOFT HYPHEN
- 0x2122: 0x93, # TRADE MARK SIGN
- 0x2248: 0xC5, # ALMOST EQUAL TO
- 0x2260: 0xAD, # NOT EQUAL TO
- 0x2264: 0xB2, # LESS-THAN OR EQUAL TO
- 0x2265: 0xB3, # GREATER-THAN OR EQUAL TO
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/mac_iceland.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/mac_iceland.py (original)
+++ python/branches/p3yk/Lib/encodings/mac_iceland.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\u02c7' # 0xFF -> CARON
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # CONTROL CHARACTER
- 0x0001: 0x01, # CONTROL CHARACTER
- 0x0002: 0x02, # CONTROL CHARACTER
- 0x0003: 0x03, # CONTROL CHARACTER
- 0x0004: 0x04, # CONTROL CHARACTER
- 0x0005: 0x05, # CONTROL CHARACTER
- 0x0006: 0x06, # CONTROL CHARACTER
- 0x0007: 0x07, # CONTROL CHARACTER
- 0x0008: 0x08, # CONTROL CHARACTER
- 0x0009: 0x09, # CONTROL CHARACTER
- 0x000A: 0x0A, # CONTROL CHARACTER
- 0x000B: 0x0B, # CONTROL CHARACTER
- 0x000C: 0x0C, # CONTROL CHARACTER
- 0x000D: 0x0D, # CONTROL CHARACTER
- 0x000E: 0x0E, # CONTROL CHARACTER
- 0x000F: 0x0F, # CONTROL CHARACTER
- 0x0010: 0x10, # CONTROL CHARACTER
- 0x0011: 0x11, # CONTROL CHARACTER
- 0x0012: 0x12, # CONTROL CHARACTER
- 0x0013: 0x13, # CONTROL CHARACTER
- 0x0014: 0x14, # CONTROL CHARACTER
- 0x0015: 0x15, # CONTROL CHARACTER
- 0x0016: 0x16, # CONTROL CHARACTER
- 0x0017: 0x17, # CONTROL CHARACTER
- 0x0018: 0x18, # CONTROL CHARACTER
- 0x0019: 0x19, # CONTROL CHARACTER
- 0x001A: 0x1A, # CONTROL CHARACTER
- 0x001B: 0x1B, # CONTROL CHARACTER
- 0x001C: 0x1C, # CONTROL CHARACTER
- 0x001D: 0x1D, # CONTROL CHARACTER
- 0x001E: 0x1E, # CONTROL CHARACTER
- 0x001F: 0x1F, # CONTROL CHARACTER
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # CONTROL CHARACTER
- 0x00A0: 0xCA, # NO-BREAK SPACE
- 0x00A1: 0xC1, # INVERTED EXCLAMATION MARK
- 0x00A2: 0xA2, # CENT SIGN
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A5: 0xB4, # YEN SIGN
- 0x00A7: 0xA4, # SECTION SIGN
- 0x00A8: 0xAC, # DIAERESIS
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AA: 0xBB, # FEMININE ORDINAL INDICATOR
- 0x00AB: 0xC7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xC2, # NOT SIGN
- 0x00AE: 0xA8, # REGISTERED SIGN
- 0x00AF: 0xF8, # MACRON
- 0x00B0: 0xA1, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B4: 0xAB, # ACUTE ACCENT
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B6: 0xA6, # PILCROW SIGN
- 0x00B7: 0xE1, # MIDDLE DOT
- 0x00B8: 0xFC, # CEDILLA
- 0x00BA: 0xBC, # MASCULINE ORDINAL INDICATOR
- 0x00BB: 0xC8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BF: 0xC0, # INVERTED QUESTION MARK
- 0x00C0: 0xCB, # LATIN CAPITAL LETTER A WITH GRAVE
- 0x00C1: 0xE7, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0xE5, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C3: 0xCC, # LATIN CAPITAL LETTER A WITH TILDE
- 0x00C4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C5: 0x81, # LATIN CAPITAL LETTER A WITH RING ABOVE
- 0x00C6: 0xAE, # LATIN CAPITAL LETTER AE
- 0x00C7: 0x82, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C8: 0xE9, # LATIN CAPITAL LETTER E WITH GRAVE
- 0x00C9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CA: 0xE6, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
- 0x00CB: 0xE8, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CC: 0xED, # LATIN CAPITAL LETTER I WITH GRAVE
- 0x00CD: 0xEA, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0xEB, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00CF: 0xEC, # LATIN CAPITAL LETTER I WITH DIAERESIS
- 0x00D0: 0xDC, # LATIN CAPITAL LETTER ETH
- 0x00D1: 0x84, # LATIN CAPITAL LETTER N WITH TILDE
- 0x00D2: 0xF1, # LATIN CAPITAL LETTER O WITH GRAVE
- 0x00D3: 0xEE, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xEF, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D5: 0xCD, # LATIN CAPITAL LETTER O WITH TILDE
- 0x00D6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D8: 0xAF, # LATIN CAPITAL LETTER O WITH STROKE
- 0x00D9: 0xF4, # LATIN CAPITAL LETTER U WITH GRAVE
- 0x00DA: 0xF2, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DB: 0xF3, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
- 0x00DC: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DD: 0xA0, # LATIN CAPITAL LETTER Y WITH ACUTE
- 0x00DE: 0xDE, # LATIN CAPITAL LETTER THORN
- 0x00DF: 0xA7, # LATIN SMALL LETTER SHARP S
- 0x00E0: 0x88, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E1: 0x87, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E3: 0x8B, # LATIN SMALL LETTER A WITH TILDE
- 0x00E4: 0x8A, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E5: 0x8C, # LATIN SMALL LETTER A WITH RING ABOVE
- 0x00E6: 0xBE, # LATIN SMALL LETTER AE
- 0x00E7: 0x8D, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0x8F, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0x8E, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00EC: 0x93, # LATIN SMALL LETTER I WITH GRAVE
- 0x00ED: 0x92, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F0: 0xDD, # LATIN SMALL LETTER ETH
- 0x00F1: 0x96, # LATIN SMALL LETTER N WITH TILDE
- 0x00F2: 0x98, # LATIN SMALL LETTER O WITH GRAVE
- 0x00F3: 0x97, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F5: 0x9B, # LATIN SMALL LETTER O WITH TILDE
- 0x00F6: 0x9A, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xD6, # DIVISION SIGN
- 0x00F8: 0xBF, # LATIN SMALL LETTER O WITH STROKE
- 0x00F9: 0x9D, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FA: 0x9C, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0x9E, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0x9F, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x00FD: 0xE0, # LATIN SMALL LETTER Y WITH ACUTE
- 0x00FE: 0xDF, # LATIN SMALL LETTER THORN
- 0x00FF: 0xD8, # LATIN SMALL LETTER Y WITH DIAERESIS
- 0x0131: 0xF5, # LATIN SMALL LETTER DOTLESS I
- 0x0152: 0xCE, # LATIN CAPITAL LIGATURE OE
- 0x0153: 0xCF, # LATIN SMALL LIGATURE OE
- 0x0178: 0xD9, # LATIN CAPITAL LETTER Y WITH DIAERESIS
- 0x0192: 0xC4, # LATIN SMALL LETTER F WITH HOOK
- 0x02C6: 0xF6, # MODIFIER LETTER CIRCUMFLEX ACCENT
- 0x02C7: 0xFF, # CARON
- 0x02D8: 0xF9, # BREVE
- 0x02D9: 0xFA, # DOT ABOVE
- 0x02DA: 0xFB, # RING ABOVE
- 0x02DB: 0xFE, # OGONEK
- 0x02DC: 0xF7, # SMALL TILDE
- 0x02DD: 0xFD, # DOUBLE ACUTE ACCENT
- 0x03A9: 0xBD, # GREEK CAPITAL LETTER OMEGA
- 0x03C0: 0xB9, # GREEK SMALL LETTER PI
- 0x2013: 0xD0, # EN DASH
- 0x2014: 0xD1, # EM DASH
- 0x2018: 0xD4, # LEFT SINGLE QUOTATION MARK
- 0x2019: 0xD5, # RIGHT SINGLE QUOTATION MARK
- 0x201A: 0xE2, # SINGLE LOW-9 QUOTATION MARK
- 0x201C: 0xD2, # LEFT DOUBLE QUOTATION MARK
- 0x201D: 0xD3, # RIGHT DOUBLE QUOTATION MARK
- 0x201E: 0xE3, # DOUBLE LOW-9 QUOTATION MARK
- 0x2022: 0xA5, # BULLET
- 0x2026: 0xC9, # HORIZONTAL ELLIPSIS
- 0x2030: 0xE4, # PER MILLE SIGN
- 0x2044: 0xDA, # FRACTION SLASH
- 0x20AC: 0xDB, # EURO SIGN
- 0x2122: 0xAA, # TRADE MARK SIGN
- 0x2202: 0xB6, # PARTIAL DIFFERENTIAL
- 0x2206: 0xC6, # INCREMENT
- 0x220F: 0xB8, # N-ARY PRODUCT
- 0x2211: 0xB7, # N-ARY SUMMATION
- 0x221A: 0xC3, # SQUARE ROOT
- 0x221E: 0xB0, # INFINITY
- 0x222B: 0xBA, # INTEGRAL
- 0x2248: 0xC5, # ALMOST EQUAL TO
- 0x2260: 0xAD, # NOT EQUAL TO
- 0x2264: 0xB2, # LESS-THAN OR EQUAL TO
- 0x2265: 0xB3, # GREATER-THAN OR EQUAL TO
- 0x25CA: 0xD7, # LOZENGE
- 0xF8FF: 0xF0, # Apple logo
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/mac_roman.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/mac_roman.py (original)
+++ python/branches/p3yk/Lib/encodings/mac_roman.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\u02c7' # 0xFF -> CARON
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # CONTROL CHARACTER
- 0x0001: 0x01, # CONTROL CHARACTER
- 0x0002: 0x02, # CONTROL CHARACTER
- 0x0003: 0x03, # CONTROL CHARACTER
- 0x0004: 0x04, # CONTROL CHARACTER
- 0x0005: 0x05, # CONTROL CHARACTER
- 0x0006: 0x06, # CONTROL CHARACTER
- 0x0007: 0x07, # CONTROL CHARACTER
- 0x0008: 0x08, # CONTROL CHARACTER
- 0x0009: 0x09, # CONTROL CHARACTER
- 0x000A: 0x0A, # CONTROL CHARACTER
- 0x000B: 0x0B, # CONTROL CHARACTER
- 0x000C: 0x0C, # CONTROL CHARACTER
- 0x000D: 0x0D, # CONTROL CHARACTER
- 0x000E: 0x0E, # CONTROL CHARACTER
- 0x000F: 0x0F, # CONTROL CHARACTER
- 0x0010: 0x10, # CONTROL CHARACTER
- 0x0011: 0x11, # CONTROL CHARACTER
- 0x0012: 0x12, # CONTROL CHARACTER
- 0x0013: 0x13, # CONTROL CHARACTER
- 0x0014: 0x14, # CONTROL CHARACTER
- 0x0015: 0x15, # CONTROL CHARACTER
- 0x0016: 0x16, # CONTROL CHARACTER
- 0x0017: 0x17, # CONTROL CHARACTER
- 0x0018: 0x18, # CONTROL CHARACTER
- 0x0019: 0x19, # CONTROL CHARACTER
- 0x001A: 0x1A, # CONTROL CHARACTER
- 0x001B: 0x1B, # CONTROL CHARACTER
- 0x001C: 0x1C, # CONTROL CHARACTER
- 0x001D: 0x1D, # CONTROL CHARACTER
- 0x001E: 0x1E, # CONTROL CHARACTER
- 0x001F: 0x1F, # CONTROL CHARACTER
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # CONTROL CHARACTER
- 0x00A0: 0xCA, # NO-BREAK SPACE
- 0x00A1: 0xC1, # INVERTED EXCLAMATION MARK
- 0x00A2: 0xA2, # CENT SIGN
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A5: 0xB4, # YEN SIGN
- 0x00A7: 0xA4, # SECTION SIGN
- 0x00A8: 0xAC, # DIAERESIS
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AA: 0xBB, # FEMININE ORDINAL INDICATOR
- 0x00AB: 0xC7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xC2, # NOT SIGN
- 0x00AE: 0xA8, # REGISTERED SIGN
- 0x00AF: 0xF8, # MACRON
- 0x00B0: 0xA1, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B4: 0xAB, # ACUTE ACCENT
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B6: 0xA6, # PILCROW SIGN
- 0x00B7: 0xE1, # MIDDLE DOT
- 0x00B8: 0xFC, # CEDILLA
- 0x00BA: 0xBC, # MASCULINE ORDINAL INDICATOR
- 0x00BB: 0xC8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BF: 0xC0, # INVERTED QUESTION MARK
- 0x00C0: 0xCB, # LATIN CAPITAL LETTER A WITH GRAVE
- 0x00C1: 0xE7, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0xE5, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C3: 0xCC, # LATIN CAPITAL LETTER A WITH TILDE
- 0x00C4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C5: 0x81, # LATIN CAPITAL LETTER A WITH RING ABOVE
- 0x00C6: 0xAE, # LATIN CAPITAL LETTER AE
- 0x00C7: 0x82, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C8: 0xE9, # LATIN CAPITAL LETTER E WITH GRAVE
- 0x00C9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CA: 0xE6, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
- 0x00CB: 0xE8, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CC: 0xED, # LATIN CAPITAL LETTER I WITH GRAVE
- 0x00CD: 0xEA, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0xEB, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00CF: 0xEC, # LATIN CAPITAL LETTER I WITH DIAERESIS
- 0x00D1: 0x84, # LATIN CAPITAL LETTER N WITH TILDE
- 0x00D2: 0xF1, # LATIN CAPITAL LETTER O WITH GRAVE
- 0x00D3: 0xEE, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xEF, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D5: 0xCD, # LATIN CAPITAL LETTER O WITH TILDE
- 0x00D6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D8: 0xAF, # LATIN CAPITAL LETTER O WITH STROKE
- 0x00D9: 0xF4, # LATIN CAPITAL LETTER U WITH GRAVE
- 0x00DA: 0xF2, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DB: 0xF3, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
- 0x00DC: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DF: 0xA7, # LATIN SMALL LETTER SHARP S
- 0x00E0: 0x88, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E1: 0x87, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E3: 0x8B, # LATIN SMALL LETTER A WITH TILDE
- 0x00E4: 0x8A, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E5: 0x8C, # LATIN SMALL LETTER A WITH RING ABOVE
- 0x00E6: 0xBE, # LATIN SMALL LETTER AE
- 0x00E7: 0x8D, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0x8F, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0x8E, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00EC: 0x93, # LATIN SMALL LETTER I WITH GRAVE
- 0x00ED: 0x92, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F1: 0x96, # LATIN SMALL LETTER N WITH TILDE
- 0x00F2: 0x98, # LATIN SMALL LETTER O WITH GRAVE
- 0x00F3: 0x97, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F5: 0x9B, # LATIN SMALL LETTER O WITH TILDE
- 0x00F6: 0x9A, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xD6, # DIVISION SIGN
- 0x00F8: 0xBF, # LATIN SMALL LETTER O WITH STROKE
- 0x00F9: 0x9D, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FA: 0x9C, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0x9E, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0x9F, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x00FF: 0xD8, # LATIN SMALL LETTER Y WITH DIAERESIS
- 0x0131: 0xF5, # LATIN SMALL LETTER DOTLESS I
- 0x0152: 0xCE, # LATIN CAPITAL LIGATURE OE
- 0x0153: 0xCF, # LATIN SMALL LIGATURE OE
- 0x0178: 0xD9, # LATIN CAPITAL LETTER Y WITH DIAERESIS
- 0x0192: 0xC4, # LATIN SMALL LETTER F WITH HOOK
- 0x02C6: 0xF6, # MODIFIER LETTER CIRCUMFLEX ACCENT
- 0x02C7: 0xFF, # CARON
- 0x02D8: 0xF9, # BREVE
- 0x02D9: 0xFA, # DOT ABOVE
- 0x02DA: 0xFB, # RING ABOVE
- 0x02DB: 0xFE, # OGONEK
- 0x02DC: 0xF7, # SMALL TILDE
- 0x02DD: 0xFD, # DOUBLE ACUTE ACCENT
- 0x03A9: 0xBD, # GREEK CAPITAL LETTER OMEGA
- 0x03C0: 0xB9, # GREEK SMALL LETTER PI
- 0x2013: 0xD0, # EN DASH
- 0x2014: 0xD1, # EM DASH
- 0x2018: 0xD4, # LEFT SINGLE QUOTATION MARK
- 0x2019: 0xD5, # RIGHT SINGLE QUOTATION MARK
- 0x201A: 0xE2, # SINGLE LOW-9 QUOTATION MARK
- 0x201C: 0xD2, # LEFT DOUBLE QUOTATION MARK
- 0x201D: 0xD3, # RIGHT DOUBLE QUOTATION MARK
- 0x201E: 0xE3, # DOUBLE LOW-9 QUOTATION MARK
- 0x2020: 0xA0, # DAGGER
- 0x2021: 0xE0, # DOUBLE DAGGER
- 0x2022: 0xA5, # BULLET
- 0x2026: 0xC9, # HORIZONTAL ELLIPSIS
- 0x2030: 0xE4, # PER MILLE SIGN
- 0x2039: 0xDC, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
- 0x203A: 0xDD, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
- 0x2044: 0xDA, # FRACTION SLASH
- 0x20AC: 0xDB, # EURO SIGN
- 0x2122: 0xAA, # TRADE MARK SIGN
- 0x2202: 0xB6, # PARTIAL DIFFERENTIAL
- 0x2206: 0xC6, # INCREMENT
- 0x220F: 0xB8, # N-ARY PRODUCT
- 0x2211: 0xB7, # N-ARY SUMMATION
- 0x221A: 0xC3, # SQUARE ROOT
- 0x221E: 0xB0, # INFINITY
- 0x222B: 0xBA, # INTEGRAL
- 0x2248: 0xC5, # ALMOST EQUAL TO
- 0x2260: 0xAD, # NOT EQUAL TO
- 0x2264: 0xB2, # LESS-THAN OR EQUAL TO
- 0x2265: 0xB3, # GREATER-THAN OR EQUAL TO
- 0x25CA: 0xD7, # LOZENGE
- 0xF8FF: 0xF0, # Apple logo
- 0xFB01: 0xDE, # LATIN SMALL LIGATURE FI
- 0xFB02: 0xDF, # LATIN SMALL LIGATURE FL
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/mac_romanian.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/mac_romanian.py (original)
+++ python/branches/p3yk/Lib/encodings/mac_romanian.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\u02c7' # 0xFF -> CARON
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # CONTROL CHARACTER
- 0x0001: 0x01, # CONTROL CHARACTER
- 0x0002: 0x02, # CONTROL CHARACTER
- 0x0003: 0x03, # CONTROL CHARACTER
- 0x0004: 0x04, # CONTROL CHARACTER
- 0x0005: 0x05, # CONTROL CHARACTER
- 0x0006: 0x06, # CONTROL CHARACTER
- 0x0007: 0x07, # CONTROL CHARACTER
- 0x0008: 0x08, # CONTROL CHARACTER
- 0x0009: 0x09, # CONTROL CHARACTER
- 0x000A: 0x0A, # CONTROL CHARACTER
- 0x000B: 0x0B, # CONTROL CHARACTER
- 0x000C: 0x0C, # CONTROL CHARACTER
- 0x000D: 0x0D, # CONTROL CHARACTER
- 0x000E: 0x0E, # CONTROL CHARACTER
- 0x000F: 0x0F, # CONTROL CHARACTER
- 0x0010: 0x10, # CONTROL CHARACTER
- 0x0011: 0x11, # CONTROL CHARACTER
- 0x0012: 0x12, # CONTROL CHARACTER
- 0x0013: 0x13, # CONTROL CHARACTER
- 0x0014: 0x14, # CONTROL CHARACTER
- 0x0015: 0x15, # CONTROL CHARACTER
- 0x0016: 0x16, # CONTROL CHARACTER
- 0x0017: 0x17, # CONTROL CHARACTER
- 0x0018: 0x18, # CONTROL CHARACTER
- 0x0019: 0x19, # CONTROL CHARACTER
- 0x001A: 0x1A, # CONTROL CHARACTER
- 0x001B: 0x1B, # CONTROL CHARACTER
- 0x001C: 0x1C, # CONTROL CHARACTER
- 0x001D: 0x1D, # CONTROL CHARACTER
- 0x001E: 0x1E, # CONTROL CHARACTER
- 0x001F: 0x1F, # CONTROL CHARACTER
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # CONTROL CHARACTER
- 0x00A0: 0xCA, # NO-BREAK SPACE
- 0x00A1: 0xC1, # INVERTED EXCLAMATION MARK
- 0x00A2: 0xA2, # CENT SIGN
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A5: 0xB4, # YEN SIGN
- 0x00A7: 0xA4, # SECTION SIGN
- 0x00A8: 0xAC, # DIAERESIS
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AA: 0xBB, # FEMININE ORDINAL INDICATOR
- 0x00AB: 0xC7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xC2, # NOT SIGN
- 0x00AE: 0xA8, # REGISTERED SIGN
- 0x00AF: 0xF8, # MACRON
- 0x00B0: 0xA1, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B4: 0xAB, # ACUTE ACCENT
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B6: 0xA6, # PILCROW SIGN
- 0x00B7: 0xE1, # MIDDLE DOT
- 0x00B8: 0xFC, # CEDILLA
- 0x00BA: 0xBC, # MASCULINE ORDINAL INDICATOR
- 0x00BB: 0xC8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BF: 0xC0, # INVERTED QUESTION MARK
- 0x00C0: 0xCB, # LATIN CAPITAL LETTER A WITH GRAVE
- 0x00C1: 0xE7, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0xE5, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C3: 0xCC, # LATIN CAPITAL LETTER A WITH TILDE
- 0x00C4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C5: 0x81, # LATIN CAPITAL LETTER A WITH RING ABOVE
- 0x00C7: 0x82, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C8: 0xE9, # LATIN CAPITAL LETTER E WITH GRAVE
- 0x00C9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CA: 0xE6, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
- 0x00CB: 0xE8, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CC: 0xED, # LATIN CAPITAL LETTER I WITH GRAVE
- 0x00CD: 0xEA, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0xEB, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00CF: 0xEC, # LATIN CAPITAL LETTER I WITH DIAERESIS
- 0x00D1: 0x84, # LATIN CAPITAL LETTER N WITH TILDE
- 0x00D2: 0xF1, # LATIN CAPITAL LETTER O WITH GRAVE
- 0x00D3: 0xEE, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xEF, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D5: 0xCD, # LATIN CAPITAL LETTER O WITH TILDE
- 0x00D6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D9: 0xF4, # LATIN CAPITAL LETTER U WITH GRAVE
- 0x00DA: 0xF2, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DB: 0xF3, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
- 0x00DC: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DF: 0xA7, # LATIN SMALL LETTER SHARP S
- 0x00E0: 0x88, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E1: 0x87, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E3: 0x8B, # LATIN SMALL LETTER A WITH TILDE
- 0x00E4: 0x8A, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E5: 0x8C, # LATIN SMALL LETTER A WITH RING ABOVE
- 0x00E7: 0x8D, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0x8F, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0x8E, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00EC: 0x93, # LATIN SMALL LETTER I WITH GRAVE
- 0x00ED: 0x92, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F1: 0x96, # LATIN SMALL LETTER N WITH TILDE
- 0x00F2: 0x98, # LATIN SMALL LETTER O WITH GRAVE
- 0x00F3: 0x97, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F5: 0x9B, # LATIN SMALL LETTER O WITH TILDE
- 0x00F6: 0x9A, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xD6, # DIVISION SIGN
- 0x00F9: 0x9D, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FA: 0x9C, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0x9E, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0x9F, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x00FF: 0xD8, # LATIN SMALL LETTER Y WITH DIAERESIS
- 0x0102: 0xAE, # LATIN CAPITAL LETTER A WITH BREVE
- 0x0103: 0xBE, # LATIN SMALL LETTER A WITH BREVE
- 0x0131: 0xF5, # LATIN SMALL LETTER DOTLESS I
- 0x0152: 0xCE, # LATIN CAPITAL LIGATURE OE
- 0x0153: 0xCF, # LATIN SMALL LIGATURE OE
- 0x0178: 0xD9, # LATIN CAPITAL LETTER Y WITH DIAERESIS
- 0x0192: 0xC4, # LATIN SMALL LETTER F WITH HOOK
- 0x0218: 0xAF, # LATIN CAPITAL LETTER S WITH COMMA BELOW # for Unicode 3.0 and later
- 0x0219: 0xBF, # LATIN SMALL LETTER S WITH COMMA BELOW # for Unicode 3.0 and later
- 0x021A: 0xDE, # LATIN CAPITAL LETTER T WITH COMMA BELOW # for Unicode 3.0 and later
- 0x021B: 0xDF, # LATIN SMALL LETTER T WITH COMMA BELOW # for Unicode 3.0 and later
- 0x02C6: 0xF6, # MODIFIER LETTER CIRCUMFLEX ACCENT
- 0x02C7: 0xFF, # CARON
- 0x02D8: 0xF9, # BREVE
- 0x02D9: 0xFA, # DOT ABOVE
- 0x02DA: 0xFB, # RING ABOVE
- 0x02DB: 0xFE, # OGONEK
- 0x02DC: 0xF7, # SMALL TILDE
- 0x02DD: 0xFD, # DOUBLE ACUTE ACCENT
- 0x03A9: 0xBD, # GREEK CAPITAL LETTER OMEGA
- 0x03C0: 0xB9, # GREEK SMALL LETTER PI
- 0x2013: 0xD0, # EN DASH
- 0x2014: 0xD1, # EM DASH
- 0x2018: 0xD4, # LEFT SINGLE QUOTATION MARK
- 0x2019: 0xD5, # RIGHT SINGLE QUOTATION MARK
- 0x201A: 0xE2, # SINGLE LOW-9 QUOTATION MARK
- 0x201C: 0xD2, # LEFT DOUBLE QUOTATION MARK
- 0x201D: 0xD3, # RIGHT DOUBLE QUOTATION MARK
- 0x201E: 0xE3, # DOUBLE LOW-9 QUOTATION MARK
- 0x2020: 0xA0, # DAGGER
- 0x2021: 0xE0, # DOUBLE DAGGER
- 0x2022: 0xA5, # BULLET
- 0x2026: 0xC9, # HORIZONTAL ELLIPSIS
- 0x2030: 0xE4, # PER MILLE SIGN
- 0x2039: 0xDC, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
- 0x203A: 0xDD, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
- 0x2044: 0xDA, # FRACTION SLASH
- 0x20AC: 0xDB, # EURO SIGN
- 0x2122: 0xAA, # TRADE MARK SIGN
- 0x2202: 0xB6, # PARTIAL DIFFERENTIAL
- 0x2206: 0xC6, # INCREMENT
- 0x220F: 0xB8, # N-ARY PRODUCT
- 0x2211: 0xB7, # N-ARY SUMMATION
- 0x221A: 0xC3, # SQUARE ROOT
- 0x221E: 0xB0, # INFINITY
- 0x222B: 0xBA, # INTEGRAL
- 0x2248: 0xC5, # ALMOST EQUAL TO
- 0x2260: 0xAD, # NOT EQUAL TO
- 0x2264: 0xB2, # LESS-THAN OR EQUAL TO
- 0x2265: 0xB3, # GREATER-THAN OR EQUAL TO
- 0x25CA: 0xD7, # LOZENGE
- 0xF8FF: 0xF0, # Apple logo
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/mac_turkish.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/mac_turkish.py (original)
+++ python/branches/p3yk/Lib/encodings/mac_turkish.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,263 +303,5 @@
u'\u02c7' # 0xFF -> CARON
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # CONTROL CHARACTER
- 0x0001: 0x01, # CONTROL CHARACTER
- 0x0002: 0x02, # CONTROL CHARACTER
- 0x0003: 0x03, # CONTROL CHARACTER
- 0x0004: 0x04, # CONTROL CHARACTER
- 0x0005: 0x05, # CONTROL CHARACTER
- 0x0006: 0x06, # CONTROL CHARACTER
- 0x0007: 0x07, # CONTROL CHARACTER
- 0x0008: 0x08, # CONTROL CHARACTER
- 0x0009: 0x09, # CONTROL CHARACTER
- 0x000A: 0x0A, # CONTROL CHARACTER
- 0x000B: 0x0B, # CONTROL CHARACTER
- 0x000C: 0x0C, # CONTROL CHARACTER
- 0x000D: 0x0D, # CONTROL CHARACTER
- 0x000E: 0x0E, # CONTROL CHARACTER
- 0x000F: 0x0F, # CONTROL CHARACTER
- 0x0010: 0x10, # CONTROL CHARACTER
- 0x0011: 0x11, # CONTROL CHARACTER
- 0x0012: 0x12, # CONTROL CHARACTER
- 0x0013: 0x13, # CONTROL CHARACTER
- 0x0014: 0x14, # CONTROL CHARACTER
- 0x0015: 0x15, # CONTROL CHARACTER
- 0x0016: 0x16, # CONTROL CHARACTER
- 0x0017: 0x17, # CONTROL CHARACTER
- 0x0018: 0x18, # CONTROL CHARACTER
- 0x0019: 0x19, # CONTROL CHARACTER
- 0x001A: 0x1A, # CONTROL CHARACTER
- 0x001B: 0x1B, # CONTROL CHARACTER
- 0x001C: 0x1C, # CONTROL CHARACTER
- 0x001D: 0x1D, # CONTROL CHARACTER
- 0x001E: 0x1E, # CONTROL CHARACTER
- 0x001F: 0x1F, # CONTROL CHARACTER
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # CONTROL CHARACTER
- 0x00A0: 0xCA, # NO-BREAK SPACE
- 0x00A1: 0xC1, # INVERTED EXCLAMATION MARK
- 0x00A2: 0xA2, # CENT SIGN
- 0x00A3: 0xA3, # POUND SIGN
- 0x00A5: 0xB4, # YEN SIGN
- 0x00A7: 0xA4, # SECTION SIGN
- 0x00A8: 0xAC, # DIAERESIS
- 0x00A9: 0xA9, # COPYRIGHT SIGN
- 0x00AA: 0xBB, # FEMININE ORDINAL INDICATOR
- 0x00AB: 0xC7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00AC: 0xC2, # NOT SIGN
- 0x00AE: 0xA8, # REGISTERED SIGN
- 0x00AF: 0xF8, # MACRON
- 0x00B0: 0xA1, # DEGREE SIGN
- 0x00B1: 0xB1, # PLUS-MINUS SIGN
- 0x00B4: 0xAB, # ACUTE ACCENT
- 0x00B5: 0xB5, # MICRO SIGN
- 0x00B6: 0xA6, # PILCROW SIGN
- 0x00B7: 0xE1, # MIDDLE DOT
- 0x00B8: 0xFC, # CEDILLA
- 0x00BA: 0xBC, # MASCULINE ORDINAL INDICATOR
- 0x00BB: 0xC8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x00BF: 0xC0, # INVERTED QUESTION MARK
- 0x00C0: 0xCB, # LATIN CAPITAL LETTER A WITH GRAVE
- 0x00C1: 0xE7, # LATIN CAPITAL LETTER A WITH ACUTE
- 0x00C2: 0xE5, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- 0x00C3: 0xCC, # LATIN CAPITAL LETTER A WITH TILDE
- 0x00C4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS
- 0x00C5: 0x81, # LATIN CAPITAL LETTER A WITH RING ABOVE
- 0x00C6: 0xAE, # LATIN CAPITAL LETTER AE
- 0x00C7: 0x82, # LATIN CAPITAL LETTER C WITH CEDILLA
- 0x00C8: 0xE9, # LATIN CAPITAL LETTER E WITH GRAVE
- 0x00C9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE
- 0x00CA: 0xE6, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
- 0x00CB: 0xE8, # LATIN CAPITAL LETTER E WITH DIAERESIS
- 0x00CC: 0xED, # LATIN CAPITAL LETTER I WITH GRAVE
- 0x00CD: 0xEA, # LATIN CAPITAL LETTER I WITH ACUTE
- 0x00CE: 0xEB, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- 0x00CF: 0xEC, # LATIN CAPITAL LETTER I WITH DIAERESIS
- 0x00D1: 0x84, # LATIN CAPITAL LETTER N WITH TILDE
- 0x00D2: 0xF1, # LATIN CAPITAL LETTER O WITH GRAVE
- 0x00D3: 0xEE, # LATIN CAPITAL LETTER O WITH ACUTE
- 0x00D4: 0xEF, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- 0x00D5: 0xCD, # LATIN CAPITAL LETTER O WITH TILDE
- 0x00D6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS
- 0x00D8: 0xAF, # LATIN CAPITAL LETTER O WITH STROKE
- 0x00D9: 0xF4, # LATIN CAPITAL LETTER U WITH GRAVE
- 0x00DA: 0xF2, # LATIN CAPITAL LETTER U WITH ACUTE
- 0x00DB: 0xF3, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
- 0x00DC: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS
- 0x00DF: 0xA7, # LATIN SMALL LETTER SHARP S
- 0x00E0: 0x88, # LATIN SMALL LETTER A WITH GRAVE
- 0x00E1: 0x87, # LATIN SMALL LETTER A WITH ACUTE
- 0x00E2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX
- 0x00E3: 0x8B, # LATIN SMALL LETTER A WITH TILDE
- 0x00E4: 0x8A, # LATIN SMALL LETTER A WITH DIAERESIS
- 0x00E5: 0x8C, # LATIN SMALL LETTER A WITH RING ABOVE
- 0x00E6: 0xBE, # LATIN SMALL LETTER AE
- 0x00E7: 0x8D, # LATIN SMALL LETTER C WITH CEDILLA
- 0x00E8: 0x8F, # LATIN SMALL LETTER E WITH GRAVE
- 0x00E9: 0x8E, # LATIN SMALL LETTER E WITH ACUTE
- 0x00EA: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX
- 0x00EB: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS
- 0x00EC: 0x93, # LATIN SMALL LETTER I WITH GRAVE
- 0x00ED: 0x92, # LATIN SMALL LETTER I WITH ACUTE
- 0x00EE: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX
- 0x00EF: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS
- 0x00F1: 0x96, # LATIN SMALL LETTER N WITH TILDE
- 0x00F2: 0x98, # LATIN SMALL LETTER O WITH GRAVE
- 0x00F3: 0x97, # LATIN SMALL LETTER O WITH ACUTE
- 0x00F4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX
- 0x00F5: 0x9B, # LATIN SMALL LETTER O WITH TILDE
- 0x00F6: 0x9A, # LATIN SMALL LETTER O WITH DIAERESIS
- 0x00F7: 0xD6, # DIVISION SIGN
- 0x00F8: 0xBF, # LATIN SMALL LETTER O WITH STROKE
- 0x00F9: 0x9D, # LATIN SMALL LETTER U WITH GRAVE
- 0x00FA: 0x9C, # LATIN SMALL LETTER U WITH ACUTE
- 0x00FB: 0x9E, # LATIN SMALL LETTER U WITH CIRCUMFLEX
- 0x00FC: 0x9F, # LATIN SMALL LETTER U WITH DIAERESIS
- 0x00FF: 0xD8, # LATIN SMALL LETTER Y WITH DIAERESIS
- 0x011E: 0xDA, # LATIN CAPITAL LETTER G WITH BREVE
- 0x011F: 0xDB, # LATIN SMALL LETTER G WITH BREVE
- 0x0130: 0xDC, # LATIN CAPITAL LETTER I WITH DOT ABOVE
- 0x0131: 0xDD, # LATIN SMALL LETTER DOTLESS I
- 0x0152: 0xCE, # LATIN CAPITAL LIGATURE OE
- 0x0153: 0xCF, # LATIN SMALL LIGATURE OE
- 0x015E: 0xDE, # LATIN CAPITAL LETTER S WITH CEDILLA
- 0x015F: 0xDF, # LATIN SMALL LETTER S WITH CEDILLA
- 0x0178: 0xD9, # LATIN CAPITAL LETTER Y WITH DIAERESIS
- 0x0192: 0xC4, # LATIN SMALL LETTER F WITH HOOK
- 0x02C6: 0xF6, # MODIFIER LETTER CIRCUMFLEX ACCENT
- 0x02C7: 0xFF, # CARON
- 0x02D8: 0xF9, # BREVE
- 0x02D9: 0xFA, # DOT ABOVE
- 0x02DA: 0xFB, # RING ABOVE
- 0x02DB: 0xFE, # OGONEK
- 0x02DC: 0xF7, # SMALL TILDE
- 0x02DD: 0xFD, # DOUBLE ACUTE ACCENT
- 0x03A9: 0xBD, # GREEK CAPITAL LETTER OMEGA
- 0x03C0: 0xB9, # GREEK SMALL LETTER PI
- 0x2013: 0xD0, # EN DASH
- 0x2014: 0xD1, # EM DASH
- 0x2018: 0xD4, # LEFT SINGLE QUOTATION MARK
- 0x2019: 0xD5, # RIGHT SINGLE QUOTATION MARK
- 0x201A: 0xE2, # SINGLE LOW-9 QUOTATION MARK
- 0x201C: 0xD2, # LEFT DOUBLE QUOTATION MARK
- 0x201D: 0xD3, # RIGHT DOUBLE QUOTATION MARK
- 0x201E: 0xE3, # DOUBLE LOW-9 QUOTATION MARK
- 0x2020: 0xA0, # DAGGER
- 0x2021: 0xE0, # DOUBLE DAGGER
- 0x2022: 0xA5, # BULLET
- 0x2026: 0xC9, # HORIZONTAL ELLIPSIS
- 0x2030: 0xE4, # PER MILLE SIGN
- 0x2122: 0xAA, # TRADE MARK SIGN
- 0x2202: 0xB6, # PARTIAL DIFFERENTIAL
- 0x2206: 0xC6, # INCREMENT
- 0x220F: 0xB8, # N-ARY PRODUCT
- 0x2211: 0xB7, # N-ARY SUMMATION
- 0x221A: 0xC3, # SQUARE ROOT
- 0x221E: 0xB0, # INFINITY
- 0x222B: 0xBA, # INTEGRAL
- 0x2248: 0xC5, # ALMOST EQUAL TO
- 0x2260: 0xAD, # NOT EQUAL TO
- 0x2264: 0xB2, # LESS-THAN OR EQUAL TO
- 0x2265: 0xB3, # GREATER-THAN OR EQUAL TO
- 0x25CA: 0xD7, # LOZENGE
- 0xF8A0: 0xF5, # undefined1
- 0xF8FF: 0xF0, # Apple logo
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/encodings/tis_620.py
==============================================================================
--- python/branches/p3yk/Lib/encodings/tis_620.py (original)
+++ python/branches/p3yk/Lib/encodings/tis_620.py Thu Jun 8 17:35:45 2006
@@ -9,14 +9,14 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,254 +303,5 @@
u'\ufffe'
)
-### Encoding Map
-
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x04, # END OF TRANSMISSION
- 0x0005: 0x05, # ENQUIRY
- 0x0006: 0x06, # ACKNOWLEDGE
- 0x0007: 0x07, # BELL
- 0x0008: 0x08, # BACKSPACE
- 0x0009: 0x09, # HORIZONTAL TABULATION
- 0x000A: 0x0A, # LINE FEED
- 0x000B: 0x0B, # VERTICAL TABULATION
- 0x000C: 0x0C, # FORM FEED
- 0x000D: 0x0D, # CARRIAGE RETURN
- 0x000E: 0x0E, # SHIFT OUT
- 0x000F: 0x0F, # SHIFT IN
- 0x0010: 0x10, # DATA LINK ESCAPE
- 0x0011: 0x11, # DEVICE CONTROL ONE
- 0x0012: 0x12, # DEVICE CONTROL TWO
- 0x0013: 0x13, # DEVICE CONTROL THREE
- 0x0014: 0x14, # DEVICE CONTROL FOUR
- 0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
- 0x0016: 0x16, # SYNCHRONOUS IDLE
- 0x0017: 0x17, # END OF TRANSMISSION BLOCK
- 0x0018: 0x18, # CANCEL
- 0x0019: 0x19, # END OF MEDIUM
- 0x001A: 0x1A, # SUBSTITUTE
- 0x001B: 0x1B, # ESCAPE
- 0x001C: 0x1C, # FILE SEPARATOR
- 0x001D: 0x1D, # GROUP SEPARATOR
- 0x001E: 0x1E, # RECORD SEPARATOR
- 0x001F: 0x1F, # UNIT SEPARATOR
- 0x0020: 0x20, # SPACE
- 0x0021: 0x21, # EXCLAMATION MARK
- 0x0022: 0x22, # QUOTATION MARK
- 0x0023: 0x23, # NUMBER SIGN
- 0x0024: 0x24, # DOLLAR SIGN
- 0x0025: 0x25, # PERCENT SIGN
- 0x0026: 0x26, # AMPERSAND
- 0x0027: 0x27, # APOSTROPHE
- 0x0028: 0x28, # LEFT PARENTHESIS
- 0x0029: 0x29, # RIGHT PARENTHESIS
- 0x002A: 0x2A, # ASTERISK
- 0x002B: 0x2B, # PLUS SIGN
- 0x002C: 0x2C, # COMMA
- 0x002D: 0x2D, # HYPHEN-MINUS
- 0x002E: 0x2E, # FULL STOP
- 0x002F: 0x2F, # SOLIDUS
- 0x0030: 0x30, # DIGIT ZERO
- 0x0031: 0x31, # DIGIT ONE
- 0x0032: 0x32, # DIGIT TWO
- 0x0033: 0x33, # DIGIT THREE
- 0x0034: 0x34, # DIGIT FOUR
- 0x0035: 0x35, # DIGIT FIVE
- 0x0036: 0x36, # DIGIT SIX
- 0x0037: 0x37, # DIGIT SEVEN
- 0x0038: 0x38, # DIGIT EIGHT
- 0x0039: 0x39, # DIGIT NINE
- 0x003A: 0x3A, # COLON
- 0x003B: 0x3B, # SEMICOLON
- 0x003C: 0x3C, # LESS-THAN SIGN
- 0x003D: 0x3D, # EQUALS SIGN
- 0x003E: 0x3E, # GREATER-THAN SIGN
- 0x003F: 0x3F, # QUESTION MARK
- 0x0040: 0x40, # COMMERCIAL AT
- 0x0041: 0x41, # LATIN CAPITAL LETTER A
- 0x0042: 0x42, # LATIN CAPITAL LETTER B
- 0x0043: 0x43, # LATIN CAPITAL LETTER C
- 0x0044: 0x44, # LATIN CAPITAL LETTER D
- 0x0045: 0x45, # LATIN CAPITAL LETTER E
- 0x0046: 0x46, # LATIN CAPITAL LETTER F
- 0x0047: 0x47, # LATIN CAPITAL LETTER G
- 0x0048: 0x48, # LATIN CAPITAL LETTER H
- 0x0049: 0x49, # LATIN CAPITAL LETTER I
- 0x004A: 0x4A, # LATIN CAPITAL LETTER J
- 0x004B: 0x4B, # LATIN CAPITAL LETTER K
- 0x004C: 0x4C, # LATIN CAPITAL LETTER L
- 0x004D: 0x4D, # LATIN CAPITAL LETTER M
- 0x004E: 0x4E, # LATIN CAPITAL LETTER N
- 0x004F: 0x4F, # LATIN CAPITAL LETTER O
- 0x0050: 0x50, # LATIN CAPITAL LETTER P
- 0x0051: 0x51, # LATIN CAPITAL LETTER Q
- 0x0052: 0x52, # LATIN CAPITAL LETTER R
- 0x0053: 0x53, # LATIN CAPITAL LETTER S
- 0x0054: 0x54, # LATIN CAPITAL LETTER T
- 0x0055: 0x55, # LATIN CAPITAL LETTER U
- 0x0056: 0x56, # LATIN CAPITAL LETTER V
- 0x0057: 0x57, # LATIN CAPITAL LETTER W
- 0x0058: 0x58, # LATIN CAPITAL LETTER X
- 0x0059: 0x59, # LATIN CAPITAL LETTER Y
- 0x005A: 0x5A, # LATIN CAPITAL LETTER Z
- 0x005B: 0x5B, # LEFT SQUARE BRACKET
- 0x005C: 0x5C, # REVERSE SOLIDUS
- 0x005D: 0x5D, # RIGHT SQUARE BRACKET
- 0x005E: 0x5E, # CIRCUMFLEX ACCENT
- 0x005F: 0x5F, # LOW LINE
- 0x0060: 0x60, # GRAVE ACCENT
- 0x0061: 0x61, # LATIN SMALL LETTER A
- 0x0062: 0x62, # LATIN SMALL LETTER B
- 0x0063: 0x63, # LATIN SMALL LETTER C
- 0x0064: 0x64, # LATIN SMALL LETTER D
- 0x0065: 0x65, # LATIN SMALL LETTER E
- 0x0066: 0x66, # LATIN SMALL LETTER F
- 0x0067: 0x67, # LATIN SMALL LETTER G
- 0x0068: 0x68, # LATIN SMALL LETTER H
- 0x0069: 0x69, # LATIN SMALL LETTER I
- 0x006A: 0x6A, # LATIN SMALL LETTER J
- 0x006B: 0x6B, # LATIN SMALL LETTER K
- 0x006C: 0x6C, # LATIN SMALL LETTER L
- 0x006D: 0x6D, # LATIN SMALL LETTER M
- 0x006E: 0x6E, # LATIN SMALL LETTER N
- 0x006F: 0x6F, # LATIN SMALL LETTER O
- 0x0070: 0x70, # LATIN SMALL LETTER P
- 0x0071: 0x71, # LATIN SMALL LETTER Q
- 0x0072: 0x72, # LATIN SMALL LETTER R
- 0x0073: 0x73, # LATIN SMALL LETTER S
- 0x0074: 0x74, # LATIN SMALL LETTER T
- 0x0075: 0x75, # LATIN SMALL LETTER U
- 0x0076: 0x76, # LATIN SMALL LETTER V
- 0x0077: 0x77, # LATIN SMALL LETTER W
- 0x0078: 0x78, # LATIN SMALL LETTER X
- 0x0079: 0x79, # LATIN SMALL LETTER Y
- 0x007A: 0x7A, # LATIN SMALL LETTER Z
- 0x007B: 0x7B, # LEFT CURLY BRACKET
- 0x007C: 0x7C, # VERTICAL LINE
- 0x007D: 0x7D, # RIGHT CURLY BRACKET
- 0x007E: 0x7E, # TILDE
- 0x007F: 0x7F, # DELETE
- 0x0080: 0x80, # <control>
- 0x0081: 0x81, # <control>
- 0x0082: 0x82, # <control>
- 0x0083: 0x83, # <control>
- 0x0084: 0x84, # <control>
- 0x0085: 0x85, # <control>
- 0x0086: 0x86, # <control>
- 0x0087: 0x87, # <control>
- 0x0088: 0x88, # <control>
- 0x0089: 0x89, # <control>
- 0x008A: 0x8A, # <control>
- 0x008B: 0x8B, # <control>
- 0x008C: 0x8C, # <control>
- 0x008D: 0x8D, # <control>
- 0x008E: 0x8E, # <control>
- 0x008F: 0x8F, # <control>
- 0x0090: 0x90, # <control>
- 0x0091: 0x91, # <control>
- 0x0092: 0x92, # <control>
- 0x0093: 0x93, # <control>
- 0x0094: 0x94, # <control>
- 0x0095: 0x95, # <control>
- 0x0096: 0x96, # <control>
- 0x0097: 0x97, # <control>
- 0x0098: 0x98, # <control>
- 0x0099: 0x99, # <control>
- 0x009A: 0x9A, # <control>
- 0x009B: 0x9B, # <control>
- 0x009C: 0x9C, # <control>
- 0x009D: 0x9D, # <control>
- 0x009E: 0x9E, # <control>
- 0x009F: 0x9F, # <control>
- 0x0E01: 0xA1, # THAI CHARACTER KO KAI
- 0x0E02: 0xA2, # THAI CHARACTER KHO KHAI
- 0x0E03: 0xA3, # THAI CHARACTER KHO KHUAT
- 0x0E04: 0xA4, # THAI CHARACTER KHO KHWAI
- 0x0E05: 0xA5, # THAI CHARACTER KHO KHON
- 0x0E06: 0xA6, # THAI CHARACTER KHO RAKHANG
- 0x0E07: 0xA7, # THAI CHARACTER NGO NGU
- 0x0E08: 0xA8, # THAI CHARACTER CHO CHAN
- 0x0E09: 0xA9, # THAI CHARACTER CHO CHING
- 0x0E0A: 0xAA, # THAI CHARACTER CHO CHANG
- 0x0E0B: 0xAB, # THAI CHARACTER SO SO
- 0x0E0C: 0xAC, # THAI CHARACTER CHO CHOE
- 0x0E0D: 0xAD, # THAI CHARACTER YO YING
- 0x0E0E: 0xAE, # THAI CHARACTER DO CHADA
- 0x0E0F: 0xAF, # THAI CHARACTER TO PATAK
- 0x0E10: 0xB0, # THAI CHARACTER THO THAN
- 0x0E11: 0xB1, # THAI CHARACTER THO NANGMONTHO
- 0x0E12: 0xB2, # THAI CHARACTER THO PHUTHAO
- 0x0E13: 0xB3, # THAI CHARACTER NO NEN
- 0x0E14: 0xB4, # THAI CHARACTER DO DEK
- 0x0E15: 0xB5, # THAI CHARACTER TO TAO
- 0x0E16: 0xB6, # THAI CHARACTER THO THUNG
- 0x0E17: 0xB7, # THAI CHARACTER THO THAHAN
- 0x0E18: 0xB8, # THAI CHARACTER THO THONG
- 0x0E19: 0xB9, # THAI CHARACTER NO NU
- 0x0E1A: 0xBA, # THAI CHARACTER BO BAIMAI
- 0x0E1B: 0xBB, # THAI CHARACTER PO PLA
- 0x0E1C: 0xBC, # THAI CHARACTER PHO PHUNG
- 0x0E1D: 0xBD, # THAI CHARACTER FO FA
- 0x0E1E: 0xBE, # THAI CHARACTER PHO PHAN
- 0x0E1F: 0xBF, # THAI CHARACTER FO FAN
- 0x0E20: 0xC0, # THAI CHARACTER PHO SAMPHAO
- 0x0E21: 0xC1, # THAI CHARACTER MO MA
- 0x0E22: 0xC2, # THAI CHARACTER YO YAK
- 0x0E23: 0xC3, # THAI CHARACTER RO RUA
- 0x0E24: 0xC4, # THAI CHARACTER RU
- 0x0E25: 0xC5, # THAI CHARACTER LO LING
- 0x0E26: 0xC6, # THAI CHARACTER LU
- 0x0E27: 0xC7, # THAI CHARACTER WO WAEN
- 0x0E28: 0xC8, # THAI CHARACTER SO SALA
- 0x0E29: 0xC9, # THAI CHARACTER SO RUSI
- 0x0E2A: 0xCA, # THAI CHARACTER SO SUA
- 0x0E2B: 0xCB, # THAI CHARACTER HO HIP
- 0x0E2C: 0xCC, # THAI CHARACTER LO CHULA
- 0x0E2D: 0xCD, # THAI CHARACTER O ANG
- 0x0E2E: 0xCE, # THAI CHARACTER HO NOKHUK
- 0x0E2F: 0xCF, # THAI CHARACTER PAIYANNOI
- 0x0E30: 0xD0, # THAI CHARACTER SARA A
- 0x0E31: 0xD1, # THAI CHARACTER MAI HAN-AKAT
- 0x0E32: 0xD2, # THAI CHARACTER SARA AA
- 0x0E33: 0xD3, # THAI CHARACTER SARA AM
- 0x0E34: 0xD4, # THAI CHARACTER SARA I
- 0x0E35: 0xD5, # THAI CHARACTER SARA II
- 0x0E36: 0xD6, # THAI CHARACTER SARA UE
- 0x0E37: 0xD7, # THAI CHARACTER SARA UEE
- 0x0E38: 0xD8, # THAI CHARACTER SARA U
- 0x0E39: 0xD9, # THAI CHARACTER SARA UU
- 0x0E3A: 0xDA, # THAI CHARACTER PHINTHU
- 0x0E3F: 0xDF, # THAI CURRENCY SYMBOL BAHT
- 0x0E40: 0xE0, # THAI CHARACTER SARA E
- 0x0E41: 0xE1, # THAI CHARACTER SARA AE
- 0x0E42: 0xE2, # THAI CHARACTER SARA O
- 0x0E43: 0xE3, # THAI CHARACTER SARA AI MAIMUAN
- 0x0E44: 0xE4, # THAI CHARACTER SARA AI MAIMALAI
- 0x0E45: 0xE5, # THAI CHARACTER LAKKHANGYAO
- 0x0E46: 0xE6, # THAI CHARACTER MAIYAMOK
- 0x0E47: 0xE7, # THAI CHARACTER MAITAIKHU
- 0x0E48: 0xE8, # THAI CHARACTER MAI EK
- 0x0E49: 0xE9, # THAI CHARACTER MAI THO
- 0x0E4A: 0xEA, # THAI CHARACTER MAI TRI
- 0x0E4B: 0xEB, # THAI CHARACTER MAI CHATTAWA
- 0x0E4C: 0xEC, # THAI CHARACTER THANTHAKHAT
- 0x0E4D: 0xED, # THAI CHARACTER NIKHAHIT
- 0x0E4E: 0xEE, # THAI CHARACTER YAMAKKAN
- 0x0E4F: 0xEF, # THAI CHARACTER FONGMAN
- 0x0E50: 0xF0, # THAI DIGIT ZERO
- 0x0E51: 0xF1, # THAI DIGIT ONE
- 0x0E52: 0xF2, # THAI DIGIT TWO
- 0x0E53: 0xF3, # THAI DIGIT THREE
- 0x0E54: 0xF4, # THAI DIGIT FOUR
- 0x0E55: 0xF5, # THAI DIGIT FIVE
- 0x0E56: 0xF6, # THAI DIGIT SIX
- 0x0E57: 0xF7, # THAI DIGIT SEVEN
- 0x0E58: 0xF8, # THAI DIGIT EIGHT
- 0x0E59: 0xF9, # THAI DIGIT NINE
- 0x0E5A: 0xFA, # THAI CHARACTER ANGKHANKHU
- 0x0E5B: 0xFB, # THAI CHARACTER KHOMUT
-}
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
Modified: python/branches/p3yk/Lib/functools.py
==============================================================================
--- python/branches/p3yk/Lib/functools.py (original)
+++ python/branches/p3yk/Lib/functools.py Thu Jun 8 17:35:45 2006
@@ -1,26 +1,51 @@
-"""functools.py - Tools for working with functions
+"""functools.py - Tools for working with functions and callable objects
"""
# Python module wrapper for _functools C module
# to allow utilities written in Python to be added
# to the functools module.
# Written by Nick Coghlan <ncoghlan at gmail.com>
-# Copyright (c) 2006 Python Software Foundation.
+# Copyright (C) 2006 Python Software Foundation.
+# See C source code for _functools credits/copyright
from _functools import partial
-__all__ = [
- "partial",
-]
-
-# Still to come here (need to write tests and docs):
-# update_wrapper - utility function to transfer basic function
-# metadata to wrapper functions
-# WRAPPER_ASSIGNMENTS & WRAPPER_UPDATES - defaults args to above
-# (update_wrapper has been approved by BDFL)
-# wraps - decorator factory equivalent to:
-# def wraps(f):
-# return partial(update_wrapper, wrapped=f)
-#
-# The wraps function makes it easy to avoid the bug that afflicts the
-# decorator example in the python-dev email proposing the
-# update_wrapper function:
-# http://mail.python.org/pipermail/python-dev/2006-May/064775.html
+
+# update_wrapper() and wraps() are tools to help write
+# wrapper functions that can handle naive introspection
+
+WRAPPER_ASSIGNMENTS = ('__module__', '__name__', '__doc__')
+WRAPPER_UPDATES = ('__dict__',)
+def update_wrapper(wrapper,
+ wrapped,
+ assigned = WRAPPER_ASSIGNMENTS,
+ updated = WRAPPER_UPDATES):
+ """Update a wrapper function to look like the wrapped function
+
+ wrapper is the function to be updated
+ wrapped is the original function
+ assigned is a tuple naming the attributes assigned directly
+ from the wrapped function to the wrapper function (defaults to
+ functools.WRAPPER_ASSIGNMENTS)
+ updated is a tuple naming the attributes off the wrapper that
+ are updated with the corresponding attribute from the wrapped
+ function (defaults to functools.WRAPPER_UPDATES)
+ """
+ for attr in assigned:
+ setattr(wrapper, attr, getattr(wrapped, attr))
+ for attr in updated:
+ getattr(wrapper, attr).update(getattr(wrapped, attr))
+ # Return the wrapper so this can be used as a decorator via partial()
+ return wrapper
+
+def wraps(wrapped,
+ assigned = WRAPPER_ASSIGNMENTS,
+ updated = WRAPPER_UPDATES):
+ """Decorator factory to apply update_wrapper() to a wrapper function
+
+ Returns a decorator that invokes update_wrapper() with the decorated
+ function as the wrapper argument and the arguments to wraps() as the
+ remaining arguments. Default arguments are as for update_wrapper().
+ This is a convenience function to simplify applying partial() to
+ update_wrapper().
+ """
+ return partial(update_wrapper, wrapped=wrapped,
+ assigned=assigned, updated=updated)
Modified: python/branches/p3yk/Lib/lib-tk/Tix.py
==============================================================================
--- python/branches/p3yk/Lib/lib-tk/Tix.py (original)
+++ python/branches/p3yk/Lib/lib-tk/Tix.py Thu Jun 8 17:35:45 2006
@@ -468,7 +468,7 @@
"""DisplayStyle - handle configuration options shared by
(multiple) Display Items"""
- def __init__(self, itemtype, cnf={}, **kw ):
+ def __init__(self, itemtype, cnf={}, **kw):
master = _default_root # global from Tkinter
if not master and cnf.has_key('refwindow'): master=cnf['refwindow']
elif not master and kw.has_key('refwindow'): master= kw['refwindow']
@@ -480,7 +480,7 @@
def __str__(self):
return self.stylename
- def _options(self, cnf, kw ):
+ def _options(self, cnf, kw):
if kw and cnf:
cnf = _cnfmerge((cnf, kw))
elif kw:
Modified: python/branches/p3yk/Lib/markupbase.py
==============================================================================
--- python/branches/p3yk/Lib/markupbase.py (original)
+++ python/branches/p3yk/Lib/markupbase.py Thu Jun 8 17:35:45 2006
@@ -140,7 +140,7 @@
# Internal -- parse a marked section
# Override this to handle MS-word extension syntax <![if word]>content<![endif]>
- def parse_marked_section( self, i, report=1 ):
+ def parse_marked_section(self, i, report=1):
rawdata= self.rawdata
assert rawdata[i:i+3] == '<![', "unexpected call to parse_marked_section()"
sectName, j = self._scan_name( i+3, i )
Deleted: /python/branches/p3yk/Lib/plat-mac/Carbon/WASTEconst.py
==============================================================================
--- /python/branches/p3yk/Lib/plat-mac/Carbon/WASTEconst.py Thu Jun 8 17:35:45 2006
+++ (empty file)
@@ -1,207 +0,0 @@
-# Generated from 'WASTE.h'
-
-kPascalStackBased = None # workaround for header parsing
-def FOUR_CHAR_CODE(x): return x
-weCantUndoErr = -10015
-weEmptySelectionErr = -10013
-weUnknownObjectTypeErr = -9478
-weObjectNotFoundErr = -9477
-weReadOnlyErr = -9476
-weTextNotFoundErr = -9474
-weInvalidTextEncodingErr = -9473
-weDuplicateAttributeErr = -9472
-weInvalidAttributeSizeErr = -9471
-weReadOnlyAttributeErr = -9470
-weOddByteCountErr = -9469
-weHandlerNotFoundErr = -1717
-weNotHandledErr = -1708
-weNewerVersionErr = -1706
-weCorruptDataErr = -1702
-weProtocolErr = -603
-weUndefinedSelectorErr = -50
-weFlushLeft = -2
-weFlushRight = -1
-weFlushDefault = 0
-weCenter = 1
-weJustify = 2
-weDirDefault = 1
-weDirRightToLeft = -1
-weDirLeftToRight = 0
-weDoFont = 0x0001
-weDoFace = 0x0002
-weDoSize = 0x0004
-weDoColor = 0x0008
-weDoAll = weDoFont | weDoFace | weDoSize | weDoColor
-weDoAddSize = 0x0010
-weDoToggleFace = 0x0020
-weDoReplaceFace = 0x0040
-weDoPreserveScript = 0x0080
-weDoExtractSubscript = 0x0100
-weDoFaceMask = 0x0200
-weDoDirection = 0x00000001
-weDoAlignment = 0x00000002
-weDoLeftIndent = 0x00000004
-weDoRightIndent = 0x00000008
-weDoFirstLineIndent = 0x00000010
-weDoLineSpacing = 0x00000020
-weDoSpaceBefore = 0x00000040
-weDoSpaceAfter = 0x00000080
-weDoBottomBorderStyle = 0x00000400
-kLeadingEdge = -1
-kTrailingEdge = 0
-kObjectEdge = 2
-weFAutoScroll = 0
-weFOutlineHilite = 2
-weFReadOnly = 5
-weFUndo = 6
-weFIntCutAndPaste = 7
-weFDragAndDrop = 8
-weFInhibitRecal = 9
-weFUseTempMem = 10
-weFDrawOffscreen = 11
-weFInhibitRedraw = 12
-weFMonoStyled = 13
-weFMultipleUndo = 14
-weFNoKeyboardSync = 29
-weFInhibitICSupport = 30
-weFInhibitColor = 31
-# weDoAutoScroll = 1UL << weFAutoScroll
-# weDoOutlineHilite = 1UL << weFOutlineHilite
-# weDoReadOnly = 1UL << weFReadOnly
-# weDoUndo = 1UL << weFUndo
-# weDoIntCutAndPaste = 1UL << weFIntCutAndPaste
-# weDoDragAndDrop = 1UL << weFDragAndDrop
-# weDoInhibitRecal = 1UL << weFInhibitRecal
-# weDoUseTempMem = 1UL << weFUseTempMem
-# weDoDrawOffscreen = 1UL << weFDrawOffscreen
-# weDoInhibitRedraw = 1UL << weFInhibitRedraw
-# weDoMonoStyled = 1UL << weFMonoStyled
-# weDoMultipleUndo = 1UL << weFMultipleUndo
-# weDoNoKeyboardSync = 1UL << weFNoKeyboardSync
-# weDoInhibitICSupport = 1UL << weFInhibitICSupport
-# weDoInhibitColor = 1UL << weFInhibitColor
-weBitToggle = -2
-weBitTest = -1
-weBitClear = 0
-weBitSet = 1
-weLowerCase = 0
-weUpperCase = 1
-weFindWholeWords = 0x00000001
-weFindCaseInsensitive = 0x00000002
-weFindDiacriticalInsensitive = 0x00000004
-wePutIntCutAndPaste = 0x00000001
-wePutAddToTypingSequence = 0x00000002
-wePutDetectUnicodeBOM = 0x00000200
-weStreamDestinationKindMask = 0x000000FF
-weStreamIncludeObjects = 0x00000100
-weGetAddUnicodeBOM = 0x00000200
-weGetLittleEndian = 0x00000400
-weTagFontFamily = FOUR_CHAR_CODE('font')
-weTagFontSize = FOUR_CHAR_CODE('ptsz')
-weTagPlain = FOUR_CHAR_CODE('plan')
-weTagBold = FOUR_CHAR_CODE('bold')
-weTagItalic = FOUR_CHAR_CODE('ital')
-weTagUnderline = FOUR_CHAR_CODE('undl')
-weTagOutline = FOUR_CHAR_CODE('outl')
-weTagShadow = FOUR_CHAR_CODE('shad')
-weTagCondensed = FOUR_CHAR_CODE('cond')
-weTagExtended = FOUR_CHAR_CODE('pexp')
-weTagStrikethrough = FOUR_CHAR_CODE('strk')
-weTagTextColor = FOUR_CHAR_CODE('colr')
-weTagBackgroundColor = FOUR_CHAR_CODE('pbcl')
-weTagTransferMode = FOUR_CHAR_CODE('pptm')
-weTagVerticalShift = FOUR_CHAR_CODE('xshf')
-weTagAlignment = FOUR_CHAR_CODE('pjst')
-weTagDirection = FOUR_CHAR_CODE('LDIR')
-weTagLineSpacing = FOUR_CHAR_CODE('ledg')
-weTagLeftIndent = FOUR_CHAR_CODE('lein')
-weTagRightIndent = FOUR_CHAR_CODE('riin')
-weTagFirstLineIndent = FOUR_CHAR_CODE('fidt')
-weTagSpaceBefore = FOUR_CHAR_CODE('spbe')
-weTagSpaceAfter = FOUR_CHAR_CODE('spaf')
-weTagBottomBorderStyle = FOUR_CHAR_CODE('BBRD')
-weTagForceFontFamily = FOUR_CHAR_CODE('ffnt')
-weTagAddFontSize = FOUR_CHAR_CODE('+siz')
-weTagAddVerticalShift = FOUR_CHAR_CODE('+shf')
-weTagTextEncoding = FOUR_CHAR_CODE('ptxe')
-weTagQDStyles = FOUR_CHAR_CODE('qdst')
-weTagTETextStyle = FOUR_CHAR_CODE('tets')
-weTagAlignmentDefault = FOUR_CHAR_CODE('deft')
-weTagAlignmentLeft = FOUR_CHAR_CODE('left')
-weTagAlignmentCenter = FOUR_CHAR_CODE('cent')
-weTagAlignmentRight = FOUR_CHAR_CODE('rght')
-weTagAlignmentFull = FOUR_CHAR_CODE('full')
-weTagDirectionDefault = FOUR_CHAR_CODE('deft')
-weTagDirectionLeftToRight = FOUR_CHAR_CODE('L->R')
-weTagDirectionRightToLeft = FOUR_CHAR_CODE('R->L')
-weTagBorderStyleNone = FOUR_CHAR_CODE('NONE')
-weTagBorderStyleThin = FOUR_CHAR_CODE('SLDL')
-weTagBorderStyleDotted = FOUR_CHAR_CODE('DTDL')
-weTagBorderStyleThick = FOUR_CHAR_CODE('THKL')
-weLineSpacingSingle = 0x00000000
-weLineSpacingOneAndHalf = 0x00008000
-weLineSpacingDouble = 0x00010000
-weCharByteHook = FOUR_CHAR_CODE('cbyt')
-weCharToPixelHook = FOUR_CHAR_CODE('c2p ')
-weCharTypeHook = FOUR_CHAR_CODE('ctyp')
-weClickLoop = FOUR_CHAR_CODE('clik')
-weCurrentDrag = FOUR_CHAR_CODE('drag')
-weDrawTextHook = FOUR_CHAR_CODE('draw')
-weDrawTSMHiliteHook = FOUR_CHAR_CODE('dtsm')
-weEraseHook = FOUR_CHAR_CODE('eras')
-weFontFamilyToNameHook = FOUR_CHAR_CODE('ff2n')
-weFontNameToFamilyHook = FOUR_CHAR_CODE('fn2f')
-weFluxProc = FOUR_CHAR_CODE('flux')
-weHiliteDropAreaHook = FOUR_CHAR_CODE('hidr')
-weLineBreakHook = FOUR_CHAR_CODE('lbrk')
-wePixelToCharHook = FOUR_CHAR_CODE('p2c ')
-wePort = FOUR_CHAR_CODE('port')
-wePreTrackDragHook = FOUR_CHAR_CODE('ptrk')
-weRefCon = FOUR_CHAR_CODE('refc')
-weScrollProc = FOUR_CHAR_CODE('scrl')
-weText = FOUR_CHAR_CODE('text')
-weTranslateDragHook = FOUR_CHAR_CODE('xdrg')
-weTranslucencyThreshold = FOUR_CHAR_CODE('tluc')
-weTSMDocumentID = FOUR_CHAR_CODE('tsmd')
-weTSMPreUpdate = FOUR_CHAR_CODE('pre ')
-weTSMPostUpdate = FOUR_CHAR_CODE('post')
-weURLHint = FOUR_CHAR_CODE('urlh')
-weWordBreakHook = FOUR_CHAR_CODE('wbrk')
-weNewHandler = FOUR_CHAR_CODE('new ')
-weDisposeHandler = FOUR_CHAR_CODE('free')
-weDrawHandler = FOUR_CHAR_CODE('draw')
-weClickHandler = FOUR_CHAR_CODE('clik')
-weStreamHandler = FOUR_CHAR_CODE('strm')
-weHoverHandler = FOUR_CHAR_CODE('hovr')
-kTypeText = FOUR_CHAR_CODE('TEXT')
-kTypeStyles = FOUR_CHAR_CODE('styl')
-kTypeSoup = FOUR_CHAR_CODE('SOUP')
-kTypeFontTable = FOUR_CHAR_CODE('FISH')
-kTypeParaFormat = FOUR_CHAR_CODE('WEpf')
-kTypeRulerScrap = FOUR_CHAR_CODE('WEru')
-kTypeCharFormat = FOUR_CHAR_CODE('WEcf')
-kTypeStyleScrap = FOUR_CHAR_CODE('WEst')
-kTypeUnicodeText = FOUR_CHAR_CODE('utxt')
-kTypeUTF8Text = FOUR_CHAR_CODE('UTF8')
-kTypeStyledText = FOUR_CHAR_CODE('STXT')
-weAKNone = 0
-weAKUnspecified = 1
-weAKTyping = 2
-weAKCut = 3
-weAKPaste = 4
-weAKClear = 5
-weAKDrag = 6
-weAKSetStyle = 7
-weAKSetRuler = 8
-weAKBackspace = 9
-weAKFwdDelete = 10
-weAKCaseChange = 11
-weAKObjectChange = 12
-weToScrap = 0
-weToDrag = 1
-weToSoup = 2
-weMouseEnter = 0
-weMouseWithin = 1
-weMouseLeave = 2
-kCurrentSelection = -1
-kNullStyle = -2
Modified: python/branches/p3yk/Lib/plat-mac/EasyDialogs.py
==============================================================================
--- python/branches/p3yk/Lib/plat-mac/EasyDialogs.py (original)
+++ python/branches/p3yk/Lib/plat-mac/EasyDialogs.py Thu Jun 8 17:35:45 2006
@@ -262,7 +262,7 @@
self.w.ShowWindow()
self.d.DrawDialog()
- def __del__( self ):
+ def __del__(self):
if self.w:
self.w.BringToFront()
self.w.HideWindow()
@@ -274,7 +274,7 @@
self.w.BringToFront()
self.w.SetWTitle(newstr)
- def label( self, *newstr ):
+ def label(self, *newstr):
"""label(text) - Set text in progress box"""
self.w.BringToFront()
if newstr:
Deleted: /python/branches/p3yk/Lib/plat-mac/WASTEconst.py
==============================================================================
--- /python/branches/p3yk/Lib/plat-mac/WASTEconst.py Thu Jun 8 17:35:45 2006
+++ (empty file)
@@ -1,207 +0,0 @@
-# Generated from 'WASTE.h'
-
-kPascalStackBased = None # workaround for header parsing
-def FOUR_CHAR_CODE(x): return x
-weCantUndoErr = -10015
-weEmptySelectionErr = -10013
-weUnknownObjectTypeErr = -9478
-weObjectNotFoundErr = -9477
-weReadOnlyErr = -9476
-weTextNotFoundErr = -9474
-weInvalidTextEncodingErr = -9473
-weDuplicateAttributeErr = -9472
-weInvalidAttributeSizeErr = -9471
-weReadOnlyAttributeErr = -9470
-weOddByteCountErr = -9469
-weHandlerNotFoundErr = -1717
-weNotHandledErr = -1708
-weNewerVersionErr = -1706
-weCorruptDataErr = -1702
-weProtocolErr = -603
-weUndefinedSelectorErr = -50
-weFlushLeft = -2
-weFlushRight = -1
-weFlushDefault = 0
-weCenter = 1
-weJustify = 2
-weDirDefault = 1
-weDirRightToLeft = -1
-weDirLeftToRight = 0
-weDoFont = 0x0001
-weDoFace = 0x0002
-weDoSize = 0x0004
-weDoColor = 0x0008
-weDoAll = weDoFont | weDoFace | weDoSize | weDoColor
-weDoAddSize = 0x0010
-weDoToggleFace = 0x0020
-weDoReplaceFace = 0x0040
-weDoPreserveScript = 0x0080
-weDoExtractSubscript = 0x0100
-weDoFaceMask = 0x0200
-weDoDirection = 0x00000001
-weDoAlignment = 0x00000002
-weDoLeftIndent = 0x00000004
-weDoRightIndent = 0x00000008
-weDoFirstLineIndent = 0x00000010
-weDoLineSpacing = 0x00000020
-weDoSpaceBefore = 0x00000040
-weDoSpaceAfter = 0x00000080
-weDoBottomBorderStyle = 0x00000400
-kLeadingEdge = -1
-kTrailingEdge = 0
-kObjectEdge = 2
-weFAutoScroll = 0
-weFOutlineHilite = 2
-weFReadOnly = 5
-weFUndo = 6
-weFIntCutAndPaste = 7
-weFDragAndDrop = 8
-weFInhibitRecal = 9
-weFUseTempMem = 10
-weFDrawOffscreen = 11
-weFInhibitRedraw = 12
-weFMonoStyled = 13
-weFMultipleUndo = 14
-weFNoKeyboardSync = 29
-weFInhibitICSupport = 30
-weFInhibitColor = 31
-weDoAutoScroll = 1 << weFAutoScroll
-weDoOutlineHilite = 1 << weFOutlineHilite
-weDoReadOnly = 1 << weFReadOnly
-weDoUndo = 1 << weFUndo
-weDoIntCutAndPaste = 1 << weFIntCutAndPaste
-weDoDragAndDrop = 1 << weFDragAndDrop
-weDoInhibitRecal = 1 << weFInhibitRecal
-weDoUseTempMem = 1 << weFUseTempMem
-weDoDrawOffscreen = 1 << weFDrawOffscreen
-weDoInhibitRedraw = 1 << weFInhibitRedraw
-weDoMonoStyled = 1 << weFMonoStyled
-weDoMultipleUndo = 1 << weFMultipleUndo
-weDoNoKeyboardSync = 1 << weFNoKeyboardSync
-weDoInhibitICSupport = 1 << weFInhibitICSupport
-# weDoInhibitColor = 1 << weFInhibitColor
-weBitToggle = -2
-weBitTest = -1
-weBitClear = 0
-weBitSet = 1
-weLowerCase = 0
-weUpperCase = 1
-weFindWholeWords = 0x00000001
-weFindCaseInsensitive = 0x00000002
-weFindDiacriticalInsensitive = 0x00000004
-wePutIntCutAndPaste = 0x00000001
-wePutAddToTypingSequence = 0x00000002
-wePutDetectUnicodeBOM = 0x00000200
-weStreamDestinationKindMask = 0x000000FF
-weStreamIncludeObjects = 0x00000100
-weGetAddUnicodeBOM = 0x00000200
-weGetLittleEndian = 0x00000400
-weTagFontFamily = FOUR_CHAR_CODE('font')
-weTagFontSize = FOUR_CHAR_CODE('ptsz')
-weTagPlain = FOUR_CHAR_CODE('plan')
-weTagBold = FOUR_CHAR_CODE('bold')
-weTagItalic = FOUR_CHAR_CODE('ital')
-weTagUnderline = FOUR_CHAR_CODE('undl')
-weTagOutline = FOUR_CHAR_CODE('outl')
-weTagShadow = FOUR_CHAR_CODE('shad')
-weTagCondensed = FOUR_CHAR_CODE('cond')
-weTagExtended = FOUR_CHAR_CODE('pexp')
-weTagStrikethrough = FOUR_CHAR_CODE('strk')
-weTagTextColor = FOUR_CHAR_CODE('colr')
-weTagBackgroundColor = FOUR_CHAR_CODE('pbcl')
-weTagTransferMode = FOUR_CHAR_CODE('pptm')
-weTagVerticalShift = FOUR_CHAR_CODE('xshf')
-weTagAlignment = FOUR_CHAR_CODE('pjst')
-weTagDirection = FOUR_CHAR_CODE('LDIR')
-weTagLineSpacing = FOUR_CHAR_CODE('ledg')
-weTagLeftIndent = FOUR_CHAR_CODE('lein')
-weTagRightIndent = FOUR_CHAR_CODE('riin')
-weTagFirstLineIndent = FOUR_CHAR_CODE('fidt')
-weTagSpaceBefore = FOUR_CHAR_CODE('spbe')
-weTagSpaceAfter = FOUR_CHAR_CODE('spaf')
-weTagBottomBorderStyle = FOUR_CHAR_CODE('BBRD')
-weTagForceFontFamily = FOUR_CHAR_CODE('ffnt')
-weTagAddFontSize = FOUR_CHAR_CODE('+siz')
-weTagAddVerticalShift = FOUR_CHAR_CODE('+shf')
-weTagTextEncoding = FOUR_CHAR_CODE('ptxe')
-weTagQDStyles = FOUR_CHAR_CODE('qdst')
-weTagTETextStyle = FOUR_CHAR_CODE('tets')
-weTagAlignmentDefault = FOUR_CHAR_CODE('deft')
-weTagAlignmentLeft = FOUR_CHAR_CODE('left')
-weTagAlignmentCenter = FOUR_CHAR_CODE('cent')
-weTagAlignmentRight = FOUR_CHAR_CODE('rght')
-weTagAlignmentFull = FOUR_CHAR_CODE('full')
-weTagDirectionDefault = FOUR_CHAR_CODE('deft')
-weTagDirectionLeftToRight = FOUR_CHAR_CODE('L->R')
-weTagDirectionRightToLeft = FOUR_CHAR_CODE('R->L')
-weTagBorderStyleNone = FOUR_CHAR_CODE('NONE')
-weTagBorderStyleThin = FOUR_CHAR_CODE('SLDL')
-weTagBorderStyleDotted = FOUR_CHAR_CODE('DTDL')
-weTagBorderStyleThick = FOUR_CHAR_CODE('THKL')
-weLineSpacingSingle = 0x00000000
-weLineSpacingOneAndHalf = 0x00008000
-weLineSpacingDouble = 0x00010000
-weCharByteHook = FOUR_CHAR_CODE('cbyt')
-weCharToPixelHook = FOUR_CHAR_CODE('c2p ')
-weCharTypeHook = FOUR_CHAR_CODE('ctyp')
-weClickLoop = FOUR_CHAR_CODE('clik')
-weCurrentDrag = FOUR_CHAR_CODE('drag')
-weDrawTextHook = FOUR_CHAR_CODE('draw')
-weDrawTSMHiliteHook = FOUR_CHAR_CODE('dtsm')
-weEraseHook = FOUR_CHAR_CODE('eras')
-weFontFamilyToNameHook = FOUR_CHAR_CODE('ff2n')
-weFontNameToFamilyHook = FOUR_CHAR_CODE('fn2f')
-weFluxProc = FOUR_CHAR_CODE('flux')
-weHiliteDropAreaHook = FOUR_CHAR_CODE('hidr')
-weLineBreakHook = FOUR_CHAR_CODE('lbrk')
-wePixelToCharHook = FOUR_CHAR_CODE('p2c ')
-wePort = FOUR_CHAR_CODE('port')
-wePreTrackDragHook = FOUR_CHAR_CODE('ptrk')
-weRefCon = FOUR_CHAR_CODE('refc')
-weScrollProc = FOUR_CHAR_CODE('scrl')
-weText = FOUR_CHAR_CODE('text')
-weTranslateDragHook = FOUR_CHAR_CODE('xdrg')
-weTranslucencyThreshold = FOUR_CHAR_CODE('tluc')
-weTSMDocumentID = FOUR_CHAR_CODE('tsmd')
-weTSMPreUpdate = FOUR_CHAR_CODE('pre ')
-weTSMPostUpdate = FOUR_CHAR_CODE('post')
-weURLHint = FOUR_CHAR_CODE('urlh')
-weWordBreakHook = FOUR_CHAR_CODE('wbrk')
-weNewHandler = FOUR_CHAR_CODE('new ')
-weDisposeHandler = FOUR_CHAR_CODE('free')
-weDrawHandler = FOUR_CHAR_CODE('draw')
-weClickHandler = FOUR_CHAR_CODE('clik')
-weStreamHandler = FOUR_CHAR_CODE('strm')
-weHoverHandler = FOUR_CHAR_CODE('hovr')
-kTypeText = FOUR_CHAR_CODE('TEXT')
-kTypeStyles = FOUR_CHAR_CODE('styl')
-kTypeSoup = FOUR_CHAR_CODE('SOUP')
-kTypeFontTable = FOUR_CHAR_CODE('FISH')
-kTypeParaFormat = FOUR_CHAR_CODE('WEpf')
-kTypeRulerScrap = FOUR_CHAR_CODE('WEru')
-kTypeCharFormat = FOUR_CHAR_CODE('WEcf')
-kTypeStyleScrap = FOUR_CHAR_CODE('WEst')
-kTypeUnicodeText = FOUR_CHAR_CODE('utxt')
-kTypeUTF8Text = FOUR_CHAR_CODE('UTF8')
-kTypeStyledText = FOUR_CHAR_CODE('STXT')
-weAKNone = 0
-weAKUnspecified = 1
-weAKTyping = 2
-weAKCut = 3
-weAKPaste = 4
-weAKClear = 5
-weAKDrag = 6
-weAKSetStyle = 7
-weAKSetRuler = 8
-weAKBackspace = 9
-weAKFwdDelete = 10
-weAKCaseChange = 11
-weAKObjectChange = 12
-weToScrap = 0
-weToDrag = 1
-weToSoup = 2
-weMouseEnter = 0
-weMouseWithin = 1
-weMouseLeave = 2
-kCurrentSelection = -1
-kNullStyle = -2
Modified: python/branches/p3yk/Lib/plat-mac/argvemulator.py
==============================================================================
--- python/branches/p3yk/Lib/plat-mac/argvemulator.py (original)
+++ python/branches/p3yk/Lib/plat-mac/argvemulator.py Thu Jun 8 17:35:45 2006
@@ -7,6 +7,7 @@
from Carbon import AE
from Carbon.AppleEvents import *
from Carbon import Evt
+from Carbon import File
from Carbon.Events import *
import aetools
@@ -16,36 +17,36 @@
def __init__(self):
self.quitting = 0
- self.ae_handlers = {}
# Remove the funny -psn_xxx_xxx argument
if len(sys.argv) > 1 and sys.argv[1][:4] == '-psn':
del sys.argv[1]
- self.installaehandler('aevt', 'oapp', self.open_app)
- self.installaehandler('aevt', 'odoc', self.open_file)
- def installaehandler(self, classe, type, callback):
- AE.AEInstallEventHandler(classe, type, self.callback_wrapper)
- self.ae_handlers[(classe, type)] = callback
+ AE.AEInstallEventHandler(kCoreEventClass, kAEOpenApplication, self.__runapp)
+ AE.AEInstallEventHandler(kCoreEventClass, kAEOpenDocuments, self.__openfiles)
def close(self):
- for classe, type in self.ae_handlers.keys():
- AE.AERemoveEventHandler(classe, type)
+ AE.AERemoveEventHandler(kCoreEventClass, kAEOpenApplication)
+ AE.AERemoveEventHandler(kCoreEventClass, kAEOpenDocuments)
def mainloop(self, mask = highLevelEventMask, timeout = 1*60):
+ # Note: this is not the right way to run an event loop in OSX or even
+ # "recent" versions of MacOS9. This is however code that has proven
+ # itself.
stoptime = Evt.TickCount() + timeout
while not self.quitting and Evt.TickCount() < stoptime:
- self.dooneevent(mask, timeout)
- self.close()
+ self._dooneevent(mask, timeout)
- def _quit(self):
- self.quitting = 1
+ if not self.quitting:
+ print "argvemulator: timeout waiting for arguments"
- def dooneevent(self, mask = highLevelEventMask, timeout = 1*60):
+ self.close()
+
+ def _dooneevent(self, mask = highLevelEventMask, timeout = 1*60):
got, event = Evt.WaitNextEvent(mask, timeout)
if got:
- self.lowlevelhandler(event)
+ self._lowlevelhandler(event)
- def lowlevelhandler(self, event):
+ def _lowlevelhandler(self, event):
what, message, when, where, modifiers = event
h, v = where
if what == kHighLevelEvent:
@@ -60,53 +61,28 @@
else:
print "Unhandled event:", event
- def callback_wrapper(self, _request, _reply):
- _parameters, _attributes = aetools.unpackevent(_request)
- _class = _attributes['evcl'].type
- _type = _attributes['evid'].type
-
- if self.ae_handlers.has_key((_class, _type)):
- _function = self.ae_handlers[(_class, _type)]
- elif self.ae_handlers.has_key((_class, '****')):
- _function = self.ae_handlers[(_class, '****')]
- elif self.ae_handlers.has_key(('****', '****')):
- _function = self.ae_handlers[('****', '****')]
- else:
- raise 'Cannot happen: AE callback without handler', (_class, _type)
-
- # XXXX Do key-to-name mapping here
- _parameters['_attributes'] = _attributes
- _parameters['_class'] = _class
- _parameters['_type'] = _type
- if _parameters.has_key('----'):
- _object = _parameters['----']
- del _parameters['----']
- # The try/except that used to be here can mask programmer errors.
- # Let the program crash, the programmer can always add a **args
- # to the formal parameter list.
- rv = _function(_object, **_parameters)
- else:
- #Same try/except comment as above
- rv = _function(**_parameters)
-
- if rv == None:
- aetools.packevent(_reply, {})
- else:
- aetools.packevent(_reply, {'----':rv})
+ def _quit(self):
+ self.quitting = 1
- def open_app(self, **args):
+ def __runapp(self, requestevent, replyevent):
self._quit()
- def open_file(self, _object=None, **args):
- for alias in _object:
- fsr = alias.FSResolveAlias(None)[0]
- pathname = fsr.as_pathname()
- sys.argv.append(pathname)
- self._quit()
+ def __openfiles(self, requestevent, replyevent):
+ try:
+ listdesc = requestevent.AEGetParamDesc(keyDirectObject, typeAEList)
+ for i in range(listdesc.AECountItems()):
+ aliasdesc = listdesc.AEGetNthDesc(i+1, typeAlias)[1]
+ alias = File.Alias(rawdata=aliasdesc.data)
+ fsref = alias.FSResolveAlias(None)[0]
+ pathname = fsref.as_pathname()
+ sys.argv.append(pathname)
+ except Exception, e:
+ print "argvemulator.py warning: can't unpack an open document event"
+ import traceback
+ traceback.print_exc()
- def other(self, _object=None, _class=None, _type=None, **args):
- print 'Ignore AppleEvent', (_class, _type), 'for', _object, 'Other args:', args
+ self._quit()
if __name__ == '__main__':
ArgvCollector().mainloop()
Modified: python/branches/p3yk/Lib/smtplib.py
==============================================================================
--- python/branches/p3yk/Lib/smtplib.py (original)
+++ python/branches/p3yk/Lib/smtplib.py Thu Jun 8 17:35:45 2006
@@ -150,7 +150,7 @@
It only supports what is needed in smtplib.
"""
- def __init__( self, sslobj):
+ def __init__(self, sslobj):
self.sslobj = sslobj
def readline(self):
Modified: python/branches/p3yk/Lib/socket.py
==============================================================================
--- python/branches/p3yk/Lib/socket.py (original)
+++ python/branches/p3yk/Lib/socket.py Thu Jun 8 17:35:45 2006
@@ -141,7 +141,7 @@
__doc__ = _realsocket.__doc__
__slots__ = ["_sock",
- "recv", "recv_buf", "recvfrom_buf",
+ "recv", "recv_into", "recvfrom_into",
"send", "sendto", "recvfrom",
"__weakref__"]
@@ -151,10 +151,10 @@
self._sock = _sock
self.send = self._sock.send
self.recv = self._sock.recv
- self.recv_buf = self._sock.recv_buf
+ self.recv_into = self._sock.recv_into
self.sendto = self._sock.sendto
self.recvfrom = self._sock.recvfrom
- self.recvfrom_buf = self._sock.recvfrom_buf
+ self.recvfrom_into = self._sock.recvfrom_into
def close(self):
self._sock = _closedsocket()
Modified: python/branches/p3yk/Lib/struct.py
==============================================================================
--- python/branches/p3yk/Lib/struct.py (original)
+++ python/branches/p3yk/Lib/struct.py Thu Jun 8 17:35:45 2006
@@ -62,7 +62,7 @@
o = _compile(fmt)
return o.pack(*args)
-def pack_to(fmt, buf, offset, *args):
+def pack_into(fmt, buf, offset, *args):
"""
Pack the values v2, v2, ... according to fmt, write
the packed bytes into the writable buffer buf starting at offset.
@@ -72,7 +72,7 @@
o = _cache[fmt]
except KeyError:
o = _compile(fmt)
- return o.pack_to(buf, offset, *args)
+ return o.pack_into(buf, offset, *args)
def unpack(fmt, s):
"""
Modified: python/branches/p3yk/Lib/subprocess.py
==============================================================================
--- python/branches/p3yk/Lib/subprocess.py (original)
+++ python/branches/p3yk/Lib/subprocess.py Thu Jun 8 17:35:45 2006
@@ -388,6 +388,7 @@
hStdInput = None
hStdOutput = None
hStdError = None
+ wShowWindow = 0
class pywintypes:
error = IOError
else:
@@ -744,18 +745,17 @@
args = list2cmdline(args)
# Process startup details
- default_startupinfo = STARTUPINFO()
if startupinfo is None:
- startupinfo = default_startupinfo
- if not None in (p2cread, c2pwrite, errwrite):
+ startupinfo = STARTUPINFO()
+ if None not in (p2cread, c2pwrite, errwrite):
startupinfo.dwFlags |= STARTF_USESTDHANDLES
startupinfo.hStdInput = p2cread
startupinfo.hStdOutput = c2pwrite
startupinfo.hStdError = errwrite
if shell:
- default_startupinfo.dwFlags |= STARTF_USESHOWWINDOW
- default_startupinfo.wShowWindow = SW_HIDE
+ startupinfo.dwFlags |= STARTF_USESHOWWINDOW
+ startupinfo.wShowWindow = SW_HIDE
comspec = os.environ.get("COMSPEC", "cmd.exe")
args = comspec + " /c " + args
if (GetVersion() >= 0x80000000L or
Modified: python/branches/p3yk/Lib/test/regrtest.py
==============================================================================
--- python/branches/p3yk/Lib/test/regrtest.py (original)
+++ python/branches/p3yk/Lib/test/regrtest.py Thu Jun 8 17:35:45 2006
@@ -503,6 +503,7 @@
quiet -- if true, don't print 'skipped' messages (probably redundant)
testdir -- test directory
"""
+
test_support.unload(test)
if not testdir:
testdir = findtestdir()
@@ -512,11 +513,7 @@
cfp = None
else:
cfp = cStringIO.StringIO()
- if huntrleaks:
- if not hasattr(sys, 'gettotalrefcount'):
- raise Exception("Tracking reference leaks requires a debug build "
- "of Python")
- refrep = open(huntrleaks[2], "a")
+
try:
save_stdout = sys.stdout
try:
@@ -538,60 +535,7 @@
if indirect_test is not None:
indirect_test()
if huntrleaks:
- # This code *is* hackish and inelegant, yes.
- # But it seems to do the job.
- import copy_reg
- fs = warnings.filters[:]
- ps = copy_reg.dispatch_table.copy()
- pic = sys.path_importer_cache.copy()
- import gc
- def cleanup():
- import _strptime, linecache, warnings, dircache
- import urlparse, urllib, urllib2, mimetypes, doctest
- import struct
- from distutils.dir_util import _path_created
- _path_created.clear()
- warnings.filters[:] = fs
- gc.collect()
- re.purge()
- _strptime._regex_cache.clear()
- urlparse.clear_cache()
- urllib.urlcleanup()
- urllib2.install_opener(None)
- copy_reg.dispatch_table.clear()
- copy_reg.dispatch_table.update(ps)
- sys.path_importer_cache.clear()
- sys.path_importer_cache.update(pic)
- dircache.reset()
- linecache.clearcache()
- mimetypes._default_mime_types()
- struct._cache.clear()
- doctest.master = None
- if indirect_test:
- def run_the_test():
- indirect_test()
- else:
- def run_the_test():
- reload(the_module)
- deltas = []
- repcount = huntrleaks[0] + huntrleaks[1]
- print >> sys.stderr, "beginning", repcount, "repetitions"
- print >> sys.stderr, \
- ("1234567890"*(repcount//10 + 1))[:repcount]
- cleanup()
- for i in range(repcount):
- rc = sys.gettotalrefcount()
- run_the_test()
- sys.stderr.write('.')
- cleanup()
- deltas.append(sys.gettotalrefcount() - rc - 2)
- print >>sys.stderr
- if max(map(abs, deltas[-huntrleaks[1]:])) > 0:
- print >>sys.stderr, test, 'leaked', \
- deltas[-huntrleaks[1]:], 'references'
- print >>refrep, test, 'leaked', \
- deltas[-huntrleaks[1]:], 'references'
- # The end of the huntrleaks hackishness.
+ dash_R(the_module, test, indirect_test, huntrleaks)
finally:
sys.stdout = save_stdout
except test_support.ResourceDenied, msg:
@@ -651,6 +595,77 @@
sys.stdout.flush()
return 0
+def dash_R(the_module, test, indirect_test, huntrleaks):
+ # This code is hackish and inelegant, but it seems to do the job.
+ import copy_reg
+
+ if not hasattr(sys, 'gettotalrefcount'):
+ raise Exception("Tracking reference leaks requires a debug build "
+ "of Python")
+
+ # Save current values for dash_R_cleanup() to restore.
+ fs = warnings.filters[:]
+ ps = copy_reg.dispatch_table.copy()
+ pic = sys.path_importer_cache.copy()
+
+ if indirect_test:
+ def run_the_test():
+ indirect_test()
+ else:
+ def run_the_test():
+ reload(the_module)
+
+ deltas = []
+ nwarmup, ntracked, fname = huntrleaks
+ repcount = nwarmup + ntracked
+ print >> sys.stderr, "beginning", repcount, "repetitions"
+ print >> sys.stderr, ("1234567890"*(repcount//10 + 1))[:repcount]
+ dash_R_cleanup(fs, ps, pic)
+ for i in range(repcount):
+ rc = sys.gettotalrefcount()
+ run_the_test()
+ sys.stderr.write('.')
+ dash_R_cleanup(fs, ps, pic)
+ if i >= nwarmup:
+ deltas.append(sys.gettotalrefcount() - rc - 2)
+ print >> sys.stderr
+ if any(deltas):
+ print >> sys.stderr, test, 'leaked', deltas, 'references'
+ refrep = open(fname, "a")
+ print >> refrep, test, 'leaked', deltas, 'references'
+ refrep.close()
+
+def dash_R_cleanup(fs, ps, pic):
+ import gc, copy_reg
+ import _strptime, linecache, warnings, dircache
+ import urlparse, urllib, urllib2, mimetypes, doctest
+ import struct, filecmp
+ from distutils.dir_util import _path_created
+
+ # Restore some original values.
+ warnings.filters[:] = fs
+ copy_reg.dispatch_table.clear()
+ copy_reg.dispatch_table.update(ps)
+ sys.path_importer_cache.clear()
+ sys.path_importer_cache.update(pic)
+
+ # Clear assorted module caches.
+ _path_created.clear()
+ re.purge()
+ _strptime._regex_cache.clear()
+ urlparse.clear_cache()
+ urllib.urlcleanup()
+ urllib2.install_opener(None)
+ dircache.reset()
+ linecache.clearcache()
+ mimetypes._default_mime_types()
+ struct._cache.clear()
+ filecmp._cache.clear()
+ doctest.master = None
+
+ # Collect cyclic trash.
+ gc.collect()
+
def reportdiff(expected, output):
import difflib
print "*" * 70
Modified: python/branches/p3yk/Lib/test/test_bsddb3.py
==============================================================================
--- python/branches/p3yk/Lib/test/test_bsddb3.py (original)
+++ python/branches/p3yk/Lib/test/test_bsddb3.py Thu Jun 8 17:35:45 2006
@@ -44,6 +44,8 @@
'test_queue',
'test_recno',
'test_thread',
+ 'test_sequence',
+ 'test_cursor_pget_bug',
]
alltests = unittest.TestSuite()
Modified: python/branches/p3yk/Lib/test/test_builtin.py
==============================================================================
--- python/branches/p3yk/Lib/test/test_builtin.py (original)
+++ python/branches/p3yk/Lib/test/test_builtin.py Thu Jun 8 17:35:45 2006
@@ -336,7 +336,7 @@
_cells = {}
def __setitem__(self, key, formula):
self._cells[key] = formula
- def __getitem__(self, key ):
+ def __getitem__(self, key):
return eval(self._cells[key], globals(), self)
ss = SpreadSheet()
Modified: python/branches/p3yk/Lib/test/test_class.py
==============================================================================
--- python/branches/p3yk/Lib/test/test_class.py (original)
+++ python/branches/p3yk/Lib/test/test_class.py Thu Jun 8 17:35:45 2006
@@ -363,3 +363,37 @@
pass
else:
print "attribute error for I.__init__ got masked"
+
+
+# Test comparison and hash of methods
+class A:
+ def __init__(self, x):
+ self.x = x
+ def f(self):
+ pass
+ def g(self):
+ pass
+ def __eq__(self, other):
+ return self.x == other.x
+ def __hash__(self):
+ return self.x
+class B(A):
+ pass
+
+a1 = A(1)
+a2 = A(2)
+assert a1.f == a1.f
+assert a1.f != a2.f
+assert a1.f != a1.g
+assert a1.f == A(1).f
+assert hash(a1.f) == hash(a1.f)
+assert hash(a1.f) == hash(A(1).f)
+
+assert A.f != a1.f
+assert A.f != A.g
+assert B.f == A.f
+assert hash(B.f) == hash(A.f)
+
+# the following triggers a SystemError in 2.4
+a = A(hash(A.f.im_func)^(-1))
+hash(a.f)
Modified: python/branches/p3yk/Lib/test/test_descr.py
==============================================================================
--- python/branches/p3yk/Lib/test/test_descr.py (original)
+++ python/branches/p3yk/Lib/test/test_descr.py Thu Jun 8 17:35:45 2006
@@ -3866,11 +3866,24 @@
l = []
vereq(l.__add__, l.__add__)
- verify(l.__add__ != [].__add__)
+ vereq(l.__add__, [].__add__)
+ verify(l.__add__ != [5].__add__)
+ verify(l.__add__ != l.__mul__)
verify(l.__add__.__name__ == '__add__')
verify(l.__add__.__self__ is l)
verify(l.__add__.__objclass__ is list)
vereq(l.__add__.__doc__, list.__add__.__doc__)
+ try:
+ hash(l.__add__)
+ except TypeError:
+ pass
+ else:
+ raise TestFailed("no TypeError from hash([].__add__)")
+
+ t = ()
+ t += (7,)
+ vereq(t.__add__, (7,).__add__)
+ vereq(hash(t.__add__), hash((7,).__add__))
def notimplemented():
# all binary methods should be able to return a NotImplemented
Modified: python/branches/p3yk/Lib/test/test_doctest.py
==============================================================================
--- python/branches/p3yk/Lib/test/test_doctest.py (original)
+++ python/branches/p3yk/Lib/test/test_doctest.py Thu Jun 8 17:35:45 2006
@@ -512,15 +512,11 @@
>>> tests[1].name.split('.')[-1] in ['f', 'g']
True
-Filter Functions
-~~~~~~~~~~~~~~~~
-A filter function can be used to restrict which objects get examined,
-but this is temporary, undocumented internal support for testmod's
-deprecated isprivate gimmick.
-
- >>> def namefilter(prefix, base):
- ... return base.startswith('a_')
- >>> tests = doctest.DocTestFinder(_namefilter=namefilter).find(SampleClass)
+Empty Tests
+~~~~~~~~~~~
+By default, an object with no doctests doesn't create any tests:
+
+ >>> tests = doctest.DocTestFinder().find(SampleClass)
>>> tests.sort()
>>> for t in tests:
... print '%2s %s' % (len(t.examples), t.name)
@@ -528,6 +524,9 @@
3 SampleClass.NestedClass
1 SampleClass.NestedClass.__init__
1 SampleClass.__init__
+ 2 SampleClass.a_classmethod
+ 1 SampleClass.a_property
+ 1 SampleClass.a_staticmethod
1 SampleClass.double
1 SampleClass.get
@@ -536,8 +535,7 @@
is really to support backward compatibility in what doctest.master.summarize()
displays.
- >>> tests = doctest.DocTestFinder(_namefilter=namefilter,
- ... exclude_empty=False).find(SampleClass)
+ >>> tests = doctest.DocTestFinder(exclude_empty=False).find(SampleClass)
>>> tests.sort()
>>> for t in tests:
... print '%2s %s' % (len(t.examples), t.name)
@@ -547,35 +545,12 @@
0 SampleClass.NestedClass.get
0 SampleClass.NestedClass.square
1 SampleClass.__init__
- 1 SampleClass.double
- 1 SampleClass.get
-
-If a given object is filtered out, then none of the objects that it
-contains will be added either:
-
- >>> def namefilter(prefix, base):
- ... return base == 'NestedClass'
- >>> tests = doctest.DocTestFinder(_namefilter=namefilter).find(SampleClass)
- >>> tests.sort()
- >>> for t in tests:
- ... print '%2s %s' % (len(t.examples), t.name)
- 3 SampleClass
- 1 SampleClass.__init__
2 SampleClass.a_classmethod
1 SampleClass.a_property
1 SampleClass.a_staticmethod
1 SampleClass.double
1 SampleClass.get
-The filter function apply to contained objects, and *not* to the
-object explicitly passed to DocTestFinder:
-
- >>> def namefilter(prefix, base):
- ... return base == 'SampleClass'
- >>> tests = doctest.DocTestFinder(_namefilter=namefilter).find(SampleClass)
- >>> len(tests)
- 9
-
Turning off Recursion
~~~~~~~~~~~~~~~~~~~~~
DocTestFinder can be told not to look for tests in contained objects
@@ -1913,20 +1888,6 @@
modified the test globals, which are a copy of the
sample_doctest module dictionary. The test globals are
automatically cleared for us after a test.
-
- Finally, you can provide an alternate test finder. Here we'll
- use a custom test_finder to to run just the test named bar.
- However, the test in the module docstring, and the two tests
- in the module __test__ dict, aren't filtered, so we actually
- run three tests besides bar's. The filtering mechanisms are
- poorly conceived, and will go away someday.
-
- >>> finder = doctest.DocTestFinder(
- ... _namefilter=lambda prefix, base: base!='bar')
- >>> suite = doctest.DocTestSuite('test.sample_doctest',
- ... test_finder=finder)
- >>> suite.run(unittest.TestResult())
- <unittest.TestResult run=4 errors=0 failures=1>
"""
def test_DocFileSuite():
Modified: python/branches/p3yk/Lib/test/test_exceptions.py
==============================================================================
--- python/branches/p3yk/Lib/test/test_exceptions.py (original)
+++ python/branches/p3yk/Lib/test/test_exceptions.py Thu Jun 8 17:35:45 2006
@@ -1,9 +1,12 @@
# Python test set -- part 5, built-in exceptions
-from test.test_support import TESTFN, unlink, run_unittest
-import warnings
-import sys, traceback, os
+import os
+import sys
import unittest
+import warnings
+import pickle, cPickle
+
+from test.test_support import TESTFN, unlink, run_unittest
# XXX This is not really enough, each *operation* should be tested!
@@ -191,11 +194,15 @@
def testAttributes(self):
# test that exception attributes are happy
- try: str(u'Hello \u00E1')
- except Exception, e: sampleUnicodeEncodeError = e
+ try:
+ str(u'Hello \u00E1')
+ except Exception, e:
+ sampleUnicodeEncodeError = e
- try: unicode('\xff')
- except Exception, e: sampleUnicodeDecodeError = e
+ try:
+ unicode('\xff')
+ except Exception, e:
+ sampleUnicodeDecodeError = e
exceptionList = [
(BaseException, (), {'message' : '', 'args' : ()}),
@@ -260,19 +267,20 @@
'strerror' : 'strErrorStr', 'winerror' : 1,
'errno' : 22, 'filename' : 'filenameStr'})
)
- except NameError: pass
-
- import pickle, random
+ except NameError:
+ pass
for args in exceptionList:
expected = args[-1]
try:
exc = args[0]
- if len(args) == 2: raise exc
- else: raise exc(*args[1])
+ if len(args) == 2:
+ raise exc
+ else:
+ raise exc(*args[1])
except BaseException, e:
if (e is not exc and # needed for sampleUnicode errors
- type(e) is not exc):
+ type(e) is not exc):
raise
# Verify no ref leaks in Exc_str()
s = str(e)
@@ -283,12 +291,15 @@
(repr(e), checkArgName))
# test for pickling support
- new = pickle.loads(pickle.dumps(e, random.randint(0, 2)))
- for checkArgName in expected:
- self.assertEquals(repr(getattr(e, checkArgName)),
- repr(expected[checkArgName]),
- 'pickled exception "%s", attribute "%s' %
- (repr(e), checkArgName))
+ for p in pickle, cPickle:
+ for protocol in range(p.HIGHEST_PROTOCOL + 1):
+ new = p.loads(p.dumps(e, protocol))
+ for checkArgName in expected:
+ got = repr(getattr(new, checkArgName))
+ want = repr(expected[checkArgName])
+ self.assertEquals(got, want,
+ 'pickled "%r", attribute "%s' %
+ (e, checkArgName))
def testKeywordArgs(self):
# test that builtin exception don't take keyword args,
Modified: python/branches/p3yk/Lib/test/test_file.py
==============================================================================
--- python/branches/p3yk/Lib/test/test_file.py (original)
+++ python/branches/p3yk/Lib/test/test_file.py Thu Jun 8 17:35:45 2006
@@ -1,356 +1,325 @@
import sys
import os
+import unittest
from array import array
from weakref import proxy
-from test.test_support import verify, TESTFN, TestFailed, findfile
+from test.test_support import TESTFN, findfile, run_unittest
from UserList import UserList
-# verify weak references
-f = file(TESTFN, 'w')
-p = proxy(f)
-p.write('teststring')
-verify(f.tell(), p.tell())
-f.close()
-f = None
-try:
- p.tell()
-except ReferenceError:
- pass
-else:
- raise TestFailed('file proxy still exists when the file is gone')
-
-# verify expected attributes exist
-f = file(TESTFN, 'w')
-softspace = f.softspace
-f.name # merely shouldn't blow up
-f.mode # ditto
-f.closed # ditto
-
-# verify softspace is writable
-f.softspace = softspace # merely shouldn't blow up
-
-# verify the others aren't
-for attr in 'name', 'mode', 'closed':
- try:
- setattr(f, attr, 'oops')
- except (AttributeError, TypeError):
- pass
- else:
- raise TestFailed('expected exception setting file attr %r' % attr)
-f.close()
-
-# check invalid mode strings
-for mode in ("", "aU", "wU+"):
- try:
- f = file(TESTFN, mode)
- except ValueError:
- pass
- else:
- f.close()
- raise TestFailed('%r is an invalid file mode' % mode)
+class AutoFileTests(unittest.TestCase):
+ # file tests for which a test file is automatically set up
-# verify writelines with instance sequence
-l = UserList(['1', '2'])
-f = open(TESTFN, 'wb')
-f.writelines(l)
-f.close()
-f = open(TESTFN, 'rb')
-buf = f.read()
-f.close()
-verify(buf == '12')
-
-# verify readinto
-a = array('c', 'x'*10)
-f = open(TESTFN, 'rb')
-n = f.readinto(a)
-f.close()
-verify(buf == a.tostring()[:n])
-
-# verify readinto refuses text files
-a = array('c', 'x'*10)
-f = open(TESTFN, 'r')
-try:
- f.readinto(a)
- raise TestFailed("readinto shouldn't work in text mode")
-except TypeError:
- pass
-finally:
- f.close()
-
-# verify writelines with integers
-f = open(TESTFN, 'wb')
-try:
- f.writelines([1, 2, 3])
-except TypeError:
- pass
-else:
- print "writelines accepted sequence of integers"
-f.close()
-
-# verify writelines with integers in UserList
-f = open(TESTFN, 'wb')
-l = UserList([1,2,3])
-try:
- f.writelines(l)
-except TypeError:
- pass
-else:
- print "writelines accepted sequence of integers"
-f.close()
-
-# verify writelines with non-string object
-class NonString: pass
-
-f = open(TESTFN, 'wb')
-try:
- f.writelines([NonString(), NonString()])
-except TypeError:
- pass
-else:
- print "writelines accepted sequence of non-string objects"
-f.close()
-
-# This causes the interpreter to exit on OSF1 v5.1.
-if sys.platform != 'osf1V5':
- try:
- sys.stdin.seek(-1)
- except IOError:
- pass
- else:
- print "should not be able to seek on sys.stdin"
-else:
- print >>sys.__stdout__, (
- ' Skipping sys.stdin.seek(-1), it may crash the interpreter.'
- ' Test manually.')
-
-try:
- sys.stdin.truncate()
-except IOError:
- pass
-else:
- print "should not be able to truncate on sys.stdin"
-
-# verify repr works
-f = open(TESTFN)
-if not repr(f).startswith("<open file '" + TESTFN):
- print "repr(file) failed"
-f.close()
-
-# verify repr works for unicode too
-f = open(unicode(TESTFN))
-if not repr(f).startswith("<open file u'" + TESTFN):
- print "repr(file with unicode name) failed"
-f.close()
-
-# verify that we get a sensible error message for bad mode argument
-bad_mode = "qwerty"
-try:
- open(TESTFN, bad_mode)
-except ValueError, msg:
- if msg[0] != 0:
- s = str(msg)
- if s.find(TESTFN) != -1 or s.find(bad_mode) == -1:
- print "bad error message for invalid mode: %s" % s
- # if msg[0] == 0, we're probably on Windows where there may be
- # no obvious way to discover why open() failed.
-else:
- print "no error for invalid mode: %s" % bad_mode
-
-f = open(TESTFN)
-if f.name != TESTFN:
- raise TestFailed, 'file.name should be "%s"' % TESTFN
-if f.isatty():
- raise TestFailed, 'file.isatty() should be false'
-
-if f.closed:
- raise TestFailed, 'file.closed should be false'
-
-try:
- f.readinto("")
-except TypeError:
- pass
-else:
- raise TestFailed, 'file.readinto("") should raise a TypeError'
-
-f.close()
-if not f.closed:
- raise TestFailed, 'file.closed should be true'
-
-# make sure that explicitly setting the buffer size doesn't cause
-# misbehaviour especially with repeated close() calls
-for s in (-1, 0, 1, 512):
- try:
- f = open(TESTFN, 'w', s)
- f.write(str(s))
- f.close()
- f.close()
- f = open(TESTFN, 'r', s)
- d = int(f.read())
- f.close()
- f.close()
- except IOError, msg:
- raise TestFailed, 'error setting buffer size %d: %s' % (s, str(msg))
- if d != s:
- raise TestFailed, 'readback failure using buffer size %d'
-
-methods = ['fileno', 'flush', 'isatty', 'next', 'read', 'readinto',
- 'readline', 'readlines', 'seek', 'tell', 'truncate', 'write',
- '__iter__']
-if sys.platform.startswith('atheos'):
- methods.remove('truncate')
-
-for methodname in methods:
- method = getattr(f, methodname)
- try:
- method()
- except ValueError:
- pass
- else:
- raise TestFailed, 'file.%s() on a closed file should raise a ValueError' % methodname
-
-try:
- f.writelines([])
-except ValueError:
- pass
-else:
- raise TestFailed, 'file.writelines([]) on a closed file should raise a ValueError'
-
-os.unlink(TESTFN)
-
-def bug801631():
- # SF bug <http://www.python.org/sf/801631>
- # "file.truncate fault on windows"
- f = file(TESTFN, 'wb')
- f.write('12345678901') # 11 bytes
- f.close()
-
- f = file(TESTFN,'rb+')
- data = f.read(5)
- if data != '12345':
- raise TestFailed("Read on file opened for update failed %r" % data)
- if f.tell() != 5:
- raise TestFailed("File pos after read wrong %d" % f.tell())
-
- f.truncate()
- if f.tell() != 5:
- raise TestFailed("File pos after ftruncate wrong %d" % f.tell())
-
- f.close()
- size = os.path.getsize(TESTFN)
- if size != 5:
- raise TestFailed("File size after ftruncate wrong %d" % size)
-
-try:
- bug801631()
-finally:
- os.unlink(TESTFN)
-
-# Test the complex interaction when mixing file-iteration and the various
-# read* methods. Ostensibly, the mixture could just be tested to work
-# when it should work according to the Python language, instead of fail
-# when it should fail according to the current CPython implementation.
-# People don't always program Python the way they should, though, and the
-# implemenation might change in subtle ways, so we explicitly test for
-# errors, too; the test will just have to be updated when the
-# implementation changes.
-dataoffset = 16384
-filler = "ham\n"
-assert not dataoffset % len(filler), \
- "dataoffset must be multiple of len(filler)"
-nchunks = dataoffset // len(filler)
-testlines = [
- "spam, spam and eggs\n",
- "eggs, spam, ham and spam\n",
- "saussages, spam, spam and eggs\n",
- "spam, ham, spam and eggs\n",
- "spam, spam, spam, spam, spam, ham, spam\n",
- "wonderful spaaaaaam.\n"
-]
-methods = [("readline", ()), ("read", ()), ("readlines", ()),
- ("readinto", (array("c", " "*100),))]
-
-try:
- # Prepare the testfile
- bag = open(TESTFN, "wb")
- bag.write(filler * nchunks)
- bag.writelines(testlines)
- bag.close()
- # Test for appropriate errors mixing read* and iteration
- for methodname, args in methods:
- f = open(TESTFN, 'rb')
- if f.next() != filler:
- raise TestFailed, "Broken testfile"
- meth = getattr(f, methodname)
+ def setUp(self):
+ self.f = file(TESTFN, 'wb')
+
+ def tearDown(self):
try:
- meth(*args)
- except ValueError:
+ if self.f:
+ self.f.close()
+ except IOError:
pass
+
+ def testWeakRefs(self):
+ # verify weak references
+ p = proxy(self.f)
+ p.write('teststring')
+ self.assertEquals(self.f.tell(), p.tell())
+ self.f.close()
+ self.f = None
+ self.assertRaises(ReferenceError, getattr, p, 'tell')
+
+ def testAttributes(self):
+ # verify expected attributes exist
+ f = self.f
+ softspace = f.softspace
+ f.name # merely shouldn't blow up
+ f.mode # ditto
+ f.closed # ditto
+
+ # verify softspace is writable
+ f.softspace = softspace # merely shouldn't blow up
+
+ # verify the others aren't
+ for attr in 'name', 'mode', 'closed':
+ self.assertRaises((AttributeError, TypeError), setattr, f, attr, 'oops')
+
+ def testReadinto(self):
+ # verify readinto
+ self.f.write('12')
+ self.f.close()
+ a = array('c', 'x'*10)
+ self.f = open(TESTFN, 'rb')
+ n = self.f.readinto(a)
+ self.assertEquals('12', a.tostring()[:n])
+
+ def testReadinto_text(self):
+ # verify readinto refuses text files
+ a = array('c', 'x'*10)
+ self.f.close()
+ self.f = open(TESTFN, 'r')
+ self.assertRaises(TypeError, self.f.readinto, a)
+
+ def testWritelinesUserList(self):
+ # verify writelines with instance sequence
+ l = UserList(['1', '2'])
+ self.f.writelines(l)
+ self.f.close()
+ self.f = open(TESTFN, 'rb')
+ buf = self.f.read()
+ self.assertEquals(buf, '12')
+
+ def testWritelinesIntegers(self):
+ # verify writelines with integers
+ self.assertRaises(TypeError, self.f.writelines, [1, 2, 3])
+
+ def testWritelinesIntegersUserList(self):
+ # verify writelines with integers in UserList
+ l = UserList([1,2,3])
+ self.assertRaises(TypeError, self.f.writelines, l)
+
+ def testWritelinesNonString(self):
+ # verify writelines with non-string object
+ class NonString: pass
+
+ self.assertRaises(TypeError, self.f.writelines, [NonString(), NonString()])
+
+ def testRepr(self):
+ # verify repr works
+ self.assert_(repr(self.f).startswith("<open file '" + TESTFN))
+
+ def testErrors(self):
+ f = self.f
+ self.assertEquals(f.name, TESTFN)
+ self.assert_(not f.isatty())
+ self.assert_(not f.closed)
+
+ self.assertRaises(TypeError, f.readinto, "")
+ f.close()
+ self.assert_(f.closed)
+
+ def testMethods(self):
+ methods = ['fileno', 'flush', 'isatty', 'next', 'read', 'readinto',
+ 'readline', 'readlines', 'seek', 'tell', 'truncate', 'write',
+ '__iter__']
+ if sys.platform.startswith('atheos'):
+ methods.remove('truncate')
+
+ self.f.close()
+
+ for methodname in methods:
+ method = getattr(self.f, methodname)
+ # should raise on closed file
+ self.assertRaises(ValueError, method)
+ self.assertRaises(ValueError, self.f.writelines, [])
+
+
+class OtherFileTests(unittest.TestCase):
+
+ def testModeStrings(self):
+ # check invalid mode strings
+ for mode in ("", "aU", "wU+"):
+ try:
+ f = file(TESTFN, mode)
+ except ValueError:
+ pass
+ else:
+ f.close()
+ self.fail('%r is an invalid file mode' % mode)
+
+ def testStdin(self):
+ # This causes the interpreter to exit on OSF1 v5.1.
+ if sys.platform != 'osf1V5':
+ self.assertRaises(IOError, sys.stdin.seek, -1)
else:
- raise TestFailed("%s%r after next() didn't raise ValueError" %
- (methodname, args))
+ print >>sys.__stdout__, (
+ ' Skipping sys.stdin.seek(-1), it may crash the interpreter.'
+ ' Test manually.')
+ self.assertRaises(IOError, sys.stdin.truncate)
+
+ def testUnicodeOpen(self):
+ # verify repr works for unicode too
+ f = open(unicode(TESTFN), "w")
+ self.assert_(repr(f).startswith("<open file u'" + TESTFN))
f.close()
- # Test to see if harmless (by accident) mixing of read* and iteration
- # still works. This depends on the size of the internal iteration
- # buffer (currently 8192,) but we can test it in a flexible manner.
- # Each line in the bag o' ham is 4 bytes ("h", "a", "m", "\n"), so
- # 4096 lines of that should get us exactly on the buffer boundary for
- # any power-of-2 buffersize between 4 and 16384 (inclusive).
- f = open(TESTFN, 'rb')
- for i in range(nchunks):
- f.next()
- testline = testlines.pop(0)
- try:
- line = f.readline()
- except ValueError:
- raise TestFailed("readline() after next() with supposedly empty "
- "iteration-buffer failed anyway")
- if line != testline:
- raise TestFailed("readline() after next() with empty buffer "
- "failed. Got %r, expected %r" % (line, testline))
- testline = testlines.pop(0)
- buf = array("c", "\x00" * len(testline))
- try:
- f.readinto(buf)
- except ValueError:
- raise TestFailed("readinto() after next() with supposedly empty "
- "iteration-buffer failed anyway")
- line = buf.tostring()
- if line != testline:
- raise TestFailed("readinto() after next() with empty buffer "
- "failed. Got %r, expected %r" % (line, testline))
-
- testline = testlines.pop(0)
- try:
- line = f.read(len(testline))
- except ValueError:
- raise TestFailed("read() after next() with supposedly empty "
- "iteration-buffer failed anyway")
- if line != testline:
- raise TestFailed("read() after next() with empty buffer "
- "failed. Got %r, expected %r" % (line, testline))
- try:
- lines = f.readlines()
- except ValueError:
- raise TestFailed("readlines() after next() with supposedly empty "
- "iteration-buffer failed anyway")
- if lines != testlines:
- raise TestFailed("readlines() after next() with empty buffer "
- "failed. Got %r, expected %r" % (line, testline))
- # Reading after iteration hit EOF shouldn't hurt either
- f = open(TESTFN, 'rb')
- try:
- for line in f:
- pass
+ def testBadModeArgument(self):
+ # verify that we get a sensible error message for bad mode argument
+ bad_mode = "qwerty"
try:
- f.readline()
- f.readinto(buf)
- f.read()
- f.readlines()
- except ValueError:
- raise TestFailed("read* failed after next() consumed file")
- finally:
- f.close()
-finally:
- os.unlink(TESTFN)
+ f = open(TESTFN, bad_mode)
+ except ValueError, msg:
+ if msg[0] != 0:
+ s = str(msg)
+ if s.find(TESTFN) != -1 or s.find(bad_mode) == -1:
+ self.fail("bad error message for invalid mode: %s" % s)
+ # if msg[0] == 0, we're probably on Windows where there may be
+ # no obvious way to discover why open() failed.
+ else:
+ f.close()
+ self.fail("no error for invalid mode: %s" % bad_mode)
+
+ def testSetBufferSize(self):
+ # make sure that explicitly setting the buffer size doesn't cause
+ # misbehaviour especially with repeated close() calls
+ for s in (-1, 0, 1, 512):
+ try:
+ f = open(TESTFN, 'w', s)
+ f.write(str(s))
+ f.close()
+ f.close()
+ f = open(TESTFN, 'r', s)
+ d = int(f.read())
+ f.close()
+ f.close()
+ except IOError, msg:
+ self.fail('error setting buffer size %d: %s' % (s, str(msg)))
+ self.assertEquals(d, s)
+
+ def testTruncateOnWindows(self):
+ os.unlink(TESTFN)
+
+ def bug801631():
+ # SF bug <http://www.python.org/sf/801631>
+ # "file.truncate fault on windows"
+ f = file(TESTFN, 'wb')
+ f.write('12345678901') # 11 bytes
+ f.close()
+
+ f = file(TESTFN,'rb+')
+ data = f.read(5)
+ if data != '12345':
+ self.fail("Read on file opened for update failed %r" % data)
+ if f.tell() != 5:
+ self.fail("File pos after read wrong %d" % f.tell())
+
+ f.truncate()
+ if f.tell() != 5:
+ self.fail("File pos after ftruncate wrong %d" % f.tell())
+
+ f.close()
+ size = os.path.getsize(TESTFN)
+ if size != 5:
+ self.fail("File size after ftruncate wrong %d" % size)
+
+ try:
+ bug801631()
+ finally:
+ os.unlink(TESTFN)
+
+ def testIteration(self):
+ # Test the complex interaction when mixing file-iteration and the various
+ # read* methods. Ostensibly, the mixture could just be tested to work
+ # when it should work according to the Python language, instead of fail
+ # when it should fail according to the current CPython implementation.
+ # People don't always program Python the way they should, though, and the
+ # implemenation might change in subtle ways, so we explicitly test for
+ # errors, too; the test will just have to be updated when the
+ # implementation changes.
+ dataoffset = 16384
+ filler = "ham\n"
+ assert not dataoffset % len(filler), \
+ "dataoffset must be multiple of len(filler)"
+ nchunks = dataoffset // len(filler)
+ testlines = [
+ "spam, spam and eggs\n",
+ "eggs, spam, ham and spam\n",
+ "saussages, spam, spam and eggs\n",
+ "spam, ham, spam and eggs\n",
+ "spam, spam, spam, spam, spam, ham, spam\n",
+ "wonderful spaaaaaam.\n"
+ ]
+ methods = [("readline", ()), ("read", ()), ("readlines", ()),
+ ("readinto", (array("c", " "*100),))]
+
+ try:
+ # Prepare the testfile
+ bag = open(TESTFN, "wb")
+ bag.write(filler * nchunks)
+ bag.writelines(testlines)
+ bag.close()
+ # Test for appropriate errors mixing read* and iteration
+ for methodname, args in methods:
+ f = open(TESTFN, 'rb')
+ if f.next() != filler:
+ self.fail, "Broken testfile"
+ meth = getattr(f, methodname)
+ try:
+ meth(*args)
+ except ValueError:
+ pass
+ else:
+ self.fail("%s%r after next() didn't raise ValueError" %
+ (methodname, args))
+ f.close()
+
+ # Test to see if harmless (by accident) mixing of read* and iteration
+ # still works. This depends on the size of the internal iteration
+ # buffer (currently 8192,) but we can test it in a flexible manner.
+ # Each line in the bag o' ham is 4 bytes ("h", "a", "m", "\n"), so
+ # 4096 lines of that should get us exactly on the buffer boundary for
+ # any power-of-2 buffersize between 4 and 16384 (inclusive).
+ f = open(TESTFN, 'rb')
+ for i in range(nchunks):
+ f.next()
+ testline = testlines.pop(0)
+ try:
+ line = f.readline()
+ except ValueError:
+ self.fail("readline() after next() with supposedly empty "
+ "iteration-buffer failed anyway")
+ if line != testline:
+ self.fail("readline() after next() with empty buffer "
+ "failed. Got %r, expected %r" % (line, testline))
+ testline = testlines.pop(0)
+ buf = array("c", "\x00" * len(testline))
+ try:
+ f.readinto(buf)
+ except ValueError:
+ self.fail("readinto() after next() with supposedly empty "
+ "iteration-buffer failed anyway")
+ line = buf.tostring()
+ if line != testline:
+ self.fail("readinto() after next() with empty buffer "
+ "failed. Got %r, expected %r" % (line, testline))
+
+ testline = testlines.pop(0)
+ try:
+ line = f.read(len(testline))
+ except ValueError:
+ self.fail("read() after next() with supposedly empty "
+ "iteration-buffer failed anyway")
+ if line != testline:
+ self.fail("read() after next() with empty buffer "
+ "failed. Got %r, expected %r" % (line, testline))
+ try:
+ lines = f.readlines()
+ except ValueError:
+ self.fail("readlines() after next() with supposedly empty "
+ "iteration-buffer failed anyway")
+ if lines != testlines:
+ self.fail("readlines() after next() with empty buffer "
+ "failed. Got %r, expected %r" % (line, testline))
+ # Reading after iteration hit EOF shouldn't hurt either
+ f = open(TESTFN, 'rb')
+ try:
+ for line in f:
+ pass
+ try:
+ f.readline()
+ f.readinto(buf)
+ f.read()
+ f.readlines()
+ except ValueError:
+ self.fail("read* failed after next() consumed file")
+ finally:
+ f.close()
+ finally:
+ os.unlink(TESTFN)
+
+
+def test_main():
+ run_unittest(AutoFileTests, OtherFileTests)
+
+if __name__ == '__main__':
+ test_main()
Modified: python/branches/p3yk/Lib/test/test_functools.py
==============================================================================
--- python/branches/p3yk/Lib/test/test_functools.py (original)
+++ python/branches/p3yk/Lib/test/test_functools.py Thu Jun 8 17:35:45 2006
@@ -152,6 +152,113 @@
thetype = PythonPartial
+class TestUpdateWrapper(unittest.TestCase):
+
+ def check_wrapper(self, wrapper, wrapped,
+ assigned=functools.WRAPPER_ASSIGNMENTS,
+ updated=functools.WRAPPER_UPDATES):
+ # Check attributes were assigned
+ for name in assigned:
+ self.failUnless(getattr(wrapper, name) is getattr(wrapped, name))
+ # Check attributes were updated
+ for name in updated:
+ wrapper_attr = getattr(wrapper, name)
+ wrapped_attr = getattr(wrapped, name)
+ for key in wrapped_attr:
+ self.failUnless(wrapped_attr[key] is wrapper_attr[key])
+
+ def test_default_update(self):
+ def f():
+ """This is a test"""
+ pass
+ f.attr = 'This is also a test'
+ def wrapper():
+ pass
+ functools.update_wrapper(wrapper, f)
+ self.check_wrapper(wrapper, f)
+ self.assertEqual(wrapper.__name__, 'f')
+ self.assertEqual(wrapper.__doc__, 'This is a test')
+ self.assertEqual(wrapper.attr, 'This is also a test')
+
+ def test_no_update(self):
+ def f():
+ """This is a test"""
+ pass
+ f.attr = 'This is also a test'
+ def wrapper():
+ pass
+ functools.update_wrapper(wrapper, f, (), ())
+ self.check_wrapper(wrapper, f, (), ())
+ self.assertEqual(wrapper.__name__, 'wrapper')
+ self.assertEqual(wrapper.__doc__, None)
+ self.failIf(hasattr(wrapper, 'attr'))
+
+ def test_selective_update(self):
+ def f():
+ pass
+ f.attr = 'This is a different test'
+ f.dict_attr = dict(a=1, b=2, c=3)
+ def wrapper():
+ pass
+ wrapper.dict_attr = {}
+ assign = ('attr',)
+ update = ('dict_attr',)
+ functools.update_wrapper(wrapper, f, assign, update)
+ self.check_wrapper(wrapper, f, assign, update)
+ self.assertEqual(wrapper.__name__, 'wrapper')
+ self.assertEqual(wrapper.__doc__, None)
+ self.assertEqual(wrapper.attr, 'This is a different test')
+ self.assertEqual(wrapper.dict_attr, f.dict_attr)
+
+
+class TestWraps(TestUpdateWrapper):
+
+ def test_default_update(self):
+ def f():
+ """This is a test"""
+ pass
+ f.attr = 'This is also a test'
+ @functools.wraps(f)
+ def wrapper():
+ pass
+ self.check_wrapper(wrapper, f)
+ self.assertEqual(wrapper.__name__, 'f')
+ self.assertEqual(wrapper.__doc__, 'This is a test')
+ self.assertEqual(wrapper.attr, 'This is also a test')
+
+ def test_no_update(self):
+ def f():
+ """This is a test"""
+ pass
+ f.attr = 'This is also a test'
+ @functools.wraps(f, (), ())
+ def wrapper():
+ pass
+ self.check_wrapper(wrapper, f, (), ())
+ self.assertEqual(wrapper.__name__, 'wrapper')
+ self.assertEqual(wrapper.__doc__, None)
+ self.failIf(hasattr(wrapper, 'attr'))
+
+ def test_selective_update(self):
+ def f():
+ pass
+ f.attr = 'This is a different test'
+ f.dict_attr = dict(a=1, b=2, c=3)
+ def add_dict_attr(f):
+ f.dict_attr = {}
+ return f
+ assign = ('attr',)
+ update = ('dict_attr',)
+ @functools.wraps(f, assign, update)
+ @add_dict_attr
+ def wrapper():
+ pass
+ self.check_wrapper(wrapper, f, assign, update)
+ self.assertEqual(wrapper.__name__, 'wrapper')
+ self.assertEqual(wrapper.__doc__, None)
+ self.assertEqual(wrapper.attr, 'This is a different test')
+ self.assertEqual(wrapper.dict_attr, f.dict_attr)
+
def test_main(verbose=None):
@@ -160,6 +267,8 @@
TestPartial,
TestPartialSubclass,
TestPythonPartial,
+ TestUpdateWrapper,
+ TestWraps
)
test_support.run_unittest(*test_classes)
Modified: python/branches/p3yk/Lib/test/test_generators.py
==============================================================================
--- python/branches/p3yk/Lib/test/test_generators.py (original)
+++ python/branches/p3yk/Lib/test/test_generators.py Thu Jun 8 17:35:45 2006
@@ -733,7 +733,7 @@
... yield 1
Traceback (most recent call last):
..
-SyntaxError: 'return' with argument inside generator (<doctest test.test_generators.__test__.syntax[0]>, line 2)
+SyntaxError: 'return' with argument inside generator (<doctest test.test_generators.__test__.syntax[0]>, line 3)
>>> def f():
... yield 1
@@ -876,9 +876,9 @@
... if 0:
... return 3 # but *this* sucks (line 8)
... if 0:
-... yield 2 # because it's a generator
+... yield 2 # because it's a generator (line 10)
Traceback (most recent call last):
-SyntaxError: 'return' with argument inside generator (<doctest test.test_generators.__test__.syntax[24]>, line 8)
+SyntaxError: 'return' with argument inside generator (<doctest test.test_generators.__test__.syntax[24]>, line 10)
This one caused a crash (see SF bug 567538):
Modified: python/branches/p3yk/Lib/test/test_socket.py
==============================================================================
--- python/branches/p3yk/Lib/test/test_socket.py (original)
+++ python/branches/p3yk/Lib/test/test_socket.py Thu Jun 8 17:35:45 2006
@@ -860,25 +860,25 @@
def __init__(self, methodName='runTest'):
SocketConnectedTest.__init__(self, methodName=methodName)
- def testRecvBuf(self):
+ def testRecvInto(self):
buf = array.array('c', ' '*1024)
- nbytes = self.cli_conn.recv_buf(buf)
+ nbytes = self.cli_conn.recv_into(buf)
self.assertEqual(nbytes, len(MSG))
msg = buf.tostring()[:len(MSG)]
self.assertEqual(msg, MSG)
- def _testRecvBuf(self):
+ def _testRecvInto(self):
buf = buffer(MSG)
self.serv_conn.send(buf)
- def testRecvFromBuf(self):
+ def testRecvFromInto(self):
buf = array.array('c', ' '*1024)
- nbytes, addr = self.cli_conn.recvfrom_buf(buf)
+ nbytes, addr = self.cli_conn.recvfrom_into(buf)
self.assertEqual(nbytes, len(MSG))
msg = buf.tostring()[:len(MSG)]
self.assertEqual(msg, MSG)
- def _testRecvFromBuf(self):
+ def _testRecvFromInto(self):
buf = buffer(MSG)
self.serv_conn.send(buf)
Modified: python/branches/p3yk/Lib/test/test_struct.py
==============================================================================
--- python/branches/p3yk/Lib/test/test_struct.py (original)
+++ python/branches/p3yk/Lib/test/test_struct.py Thu Jun 8 17:35:45 2006
@@ -1,4 +1,4 @@
-from test.test_support import TestFailed, verbose, verify
+from test.test_support import TestFailed, verbose, verify, vereq
import test.test_support
import struct
import array
@@ -16,13 +16,11 @@
PY_STRUCT_RANGE_CHECKING = 0
PY_STRUCT_OVERFLOW_MASKING = 1
else:
- PY_STRUCT_RANGE_CHECKING = getattr(_struct, '_PY_STRUCT_RANGE_CHECKING', 0)
- PY_STRUCT_OVERFLOW_MASKING = getattr(_struct, '_PY_STRUCT_OVERFLOW_MASKING', 0)
+ PY_STRUCT_RANGE_CHECKING = _struct._PY_STRUCT_RANGE_CHECKING
+ PY_STRUCT_OVERFLOW_MASKING = _struct._PY_STRUCT_OVERFLOW_MASKING
def string_reverse(s):
- chars = list(s)
- chars.reverse()
- return "".join(chars)
+ return "".join(reversed(s))
def bigendian_to_native(value):
if ISBIGENDIAN:
@@ -504,7 +502,7 @@
except excClass:
return
else:
- raise RuntimeError("%s not raised." % excClass)
+ raise TestFailed("%s not raised." % excClass)
def test_unpack_from():
test_string = 'abcd01234'
@@ -512,68 +510,67 @@
s = struct.Struct(fmt)
for cls in (str, buffer):
data = cls(test_string)
- assert s.unpack_from(data) == ('abcd',)
- assert s.unpack_from(data, 2) == ('cd01',)
- assert s.unpack_from(data, 4) == ('0123',)
+ vereq(s.unpack_from(data), ('abcd',))
+ vereq(s.unpack_from(data, 2), ('cd01',))
+ vereq(s.unpack_from(data, 4), ('0123',))
for i in xrange(6):
- assert s.unpack_from(data, i) == (data[i:i+4],)
+ vereq(s.unpack_from(data, i), (data[i:i+4],))
for i in xrange(6, len(test_string) + 1):
simple_err(s.unpack_from, data, i)
for cls in (str, buffer):
data = cls(test_string)
- assert struct.unpack_from(fmt, data) == ('abcd',)
- assert struct.unpack_from(fmt, data, 2) == ('cd01',)
- assert struct.unpack_from(fmt, data, 4) == ('0123',)
+ vereq(struct.unpack_from(fmt, data), ('abcd',))
+ vereq(struct.unpack_from(fmt, data, 2), ('cd01',))
+ vereq(struct.unpack_from(fmt, data, 4), ('0123',))
for i in xrange(6):
- assert (struct.unpack_from(fmt, data, i) == (data[i:i+4],))
+ vereq(struct.unpack_from(fmt, data, i), (data[i:i+4],))
for i in xrange(6, len(test_string) + 1):
simple_err(struct.unpack_from, fmt, data, i)
-def test_pack_to():
+def test_pack_into():
test_string = 'Reykjavik rocks, eow!'
writable_buf = array.array('c', ' '*100)
fmt = '21s'
s = struct.Struct(fmt)
# Test without offset
- s.pack_to(writable_buf, 0, test_string)
+ s.pack_into(writable_buf, 0, test_string)
from_buf = writable_buf.tostring()[:len(test_string)]
- assert from_buf == test_string
+ vereq(from_buf, test_string)
# Test with offset.
- s.pack_to(writable_buf, 10, test_string)
+ s.pack_into(writable_buf, 10, test_string)
from_buf = writable_buf.tostring()[:len(test_string)+10]
- assert from_buf == (test_string[:10] + test_string)
+ vereq(from_buf, test_string[:10] + test_string)
# Go beyond boundaries.
small_buf = array.array('c', ' '*10)
- assertRaises(struct.error, s.pack_to, small_buf, 0, test_string)
- assertRaises(struct.error, s.pack_to, small_buf, 2, test_string)
+ assertRaises(struct.error, s.pack_into, small_buf, 0, test_string)
+ assertRaises(struct.error, s.pack_into, small_buf, 2, test_string)
-def test_pack_to_fn():
+def test_pack_into_fn():
test_string = 'Reykjavik rocks, eow!'
writable_buf = array.array('c', ' '*100)
fmt = '21s'
- pack_to = lambda *args: struct.pack_to(fmt, *args)
+ pack_into = lambda *args: struct.pack_into(fmt, *args)
- # Test without offset
- pack_to(writable_buf, 0, test_string)
+ # Test without offset.
+ pack_into(writable_buf, 0, test_string)
from_buf = writable_buf.tostring()[:len(test_string)]
- assert from_buf == test_string
+ vereq(from_buf, test_string)
# Test with offset.
- pack_to(writable_buf, 10, test_string)
+ pack_into(writable_buf, 10, test_string)
from_buf = writable_buf.tostring()[:len(test_string)+10]
- assert from_buf == (test_string[:10] + test_string)
+ vereq(from_buf, test_string[:10] + test_string)
# Go beyond boundaries.
small_buf = array.array('c', ' '*10)
- assertRaises(struct.error, pack_to, small_buf, 0, test_string)
- assertRaises(struct.error, pack_to, small_buf, 2, test_string)
+ assertRaises(struct.error, pack_into, small_buf, 0, test_string)
+ assertRaises(struct.error, pack_into, small_buf, 2, test_string)
+
-
# Test methods to pack and unpack from buffers rather than strings.
test_unpack_from()
-test_pack_to()
-test_pack_to_fn()
-
+test_pack_into()
+test_pack_into_fn()
Modified: python/branches/p3yk/Lib/test/test_tempfile.py
==============================================================================
--- python/branches/p3yk/Lib/test/test_tempfile.py (original)
+++ python/branches/p3yk/Lib/test/test_tempfile.py Thu Jun 8 17:35:45 2006
@@ -390,7 +390,7 @@
class test_mkstemp(TC):
"""Test mkstemp()."""
- def do_create(self, dir=None, pre="", suf="", ):
+ def do_create(self, dir=None, pre="", suf=""):
if dir is None:
dir = tempfile.gettempdir()
try:
Modified: python/branches/p3yk/Mac/Demo/index.html
==============================================================================
--- python/branches/p3yk/Mac/Demo/index.html (original)
+++ python/branches/p3yk/Mac/Demo/index.html Thu Jun 8 17:35:45 2006
@@ -74,10 +74,6 @@
<code>TextEdit</code> toolbox to build a text editor.
<LI>
-<A HREF="waste.html">Using WASTE</A> expands on this editor by using
-WASTE, an extended TextEdit replacement.
-
-<LI>
<A HREF="plugins.html">Creating a C extension module on the Macintosh</A>
is meant for the hardcore programmer, and shows how to create an
extension module in C. It also handles using Modulator to create the
Modified: python/branches/p3yk/Mac/Demo/textedit.html
==============================================================================
--- python/branches/p3yk/Mac/Demo/textedit.html (original)
+++ python/branches/p3yk/Mac/Demo/textedit.html Thu Jun 8 17:35:45 2006
@@ -80,8 +80,7 @@
Let us have a look at <A HREF="textedit/ped.py">ped.py</A> (in the Demo:textedit folder), the Pathetic
EDitor. It has multiple windows, cut/copy/paste and keyboard input, but that is about all. It looks
-as if you can resize the window but it does not work. Still, it serves as an example. We will improve
-on ped later, in a <A HREF="waste.html">waste-based example</A>. <p>
+as if you can resize the window but it does not work. Still, it serves as an example.
Ped creates two classes, <code>TEWindow</code> and <code>Ped</code>. Let us start with the latter one,
which is a subclass of <code>FrameWork.Application</code> and our main application. The init function
Deleted: /python/branches/p3yk/Mac/Demo/waste.html
==============================================================================
--- /python/branches/p3yk/Mac/Demo/waste.html Thu Jun 8 17:35:45 2006
+++ (empty file)
@@ -1,72 +0,0 @@
-<HTML><HEAD><TITLE>Using WASTE</TITLE></HEAD>
-<BODY>
-<H1>Using WASTE</H1>
-<HR>
-
-WASTE is an almost-compatible TextEdit replacement which overcomes
-some of the limitations of it (like the 32K limit) and provides some extensions
-(drag and drop, images, undo support). Moreover, it has a much cleaner interface
-and is therefore easier integrated in Python. <p>
-
-WASTE is written by Marco Piovanelli, <A HREF="mailto:piovanel at kagi.com"><piovanel at kagi.com></A>,
-and copyrighted by him. You can always obtain the latest version (for use in C
-or Pascal programs) and the documentation from
-<A HREF="http://www.boingo.com/waste/"><http://www.boingo.com/waste/></A>.
-
-We explain the useage of waste here by showing how to modify the TextEdit based
-<A HREF="textedit/ped.py">ped.py</A> of the
-<A HREF="textedit.html">previous example</A> into the waste-based <A HREF="waste/wed.py">wed.py</A>,
-so you should have both sources handy. <p>
-
-Functionally, <code>wed.py</code> provides three new things: resizable windows, a horizontal
-scroll bar and undo. <p>
-
-Let us look at the code, first at the application class <code>Wed</code>. The only real change is that
-we now handle <code>undo</code>. Aside from enabling it in the creation routine and the addition of
-a callback routine there is a bit of new code in <code>updatemenubar</code>: Waste not only handles
-the full details of implementing undo, it will also tell us what the next undo operation will undo
-(or redo). We use this to our advantage by changing the undo menu label to tell the user. <p>
-
-The <code>WasteWindow</code> has seen a bit more change. Initialization of the waste data structure is
-a bit different, in that we can specify some options at creation time. Also, waste has no <code>SetText</code>
-method but a <code>UseText</code> which expects a handle as parameter. We have to be <EM>very</EM> careful
-that we keep this handle around, because Python will happily free the handle if we have no more references
-to it (and I doubt that Waste would like this:-). A final difference in <code>open</code>
-is that we use a large number for the destination rectangle width, because we will use a horizontal scroll
-bar. <p>
-
-The <code>idle</code> method is a bit more involved, since we also call <code>WEAdjustCursor</code> to
-provide the correct cursor based on mouse-position. Users like this. <p>
-
-<code>Getscrollbarvalues</code> is simpler than its' TextEdit counterpart because Waste correctly
-updates the destination rectangle when the document changes. Also note that waste uses accessor functions
-to get at internal values, as opposed to direct struct access for TextEdit. <p>
-
-<code>Scrollbar_callback</code> on the other hand is more elaborate (but also provides more functionality).
-It also handles horizontal scrolls (scrolling one-tenth and half a screenful with the buttons). This
-function is also "multi-font-ready" in that scrolling one line will do the expected thing in case of multiple
-fonts. We will implement a multi-font editor later. A minor annoyance of Waste is that is does not provide
-a pinned scroll, so at the end of our callback routine we have to check that we have not scrolled past the
-beginning or end of the document, and adjust when needed. <p>
-
-<code>do_update</code> is also changed, because Waste is completely region-based (as opposed to rect-based).
-Hence, we erase regions here and we can also return immedeately if there is nothing to update. <p>
-
-<code>Do_postresize</code> is new: because Waste uses accessor functions we can now modify the viewRect from
-Python, which is impossible in the Python TextEdit interface, and hence we can implement resize. The
-<code>do_key</code> and <code>do_contentclick</code> methods have also seen minor changes, because the
-corresponding waste routines need a bit more information than their TextEdit counterparts. The Cut/copy/paste
-code is simplified, because Waste uses the normal desktop scrap. <p>
-
-Implementing undo is a wonder of simplicity: Waste handles all the details for us. Also, the new
-<code>can_paste</code> method (which controls greying out of the paste menu entry) is an improvement
-over what <code>ped</code> did: in ped it was possible that paste was enabled but that the data on the
-scrap was incompatible with TextEdit. No more such problems here. <p>
-
-That is all for now. There is an undocumented extended version of wed, <a href="waste/swed.py">swed.py</a>,
-which supports multiple fonts, sizes and faces, and uses Waste's tab-calculation to do tab characters "right".
-There is also an even more elaborate example, <a href="waste/htmled.py">htmled.py</a> which extends swed with
-the ability to import html files, showing the use of color and how to use embedded object (rulers, in this case).
-These two programs have not been documented yet, though, so you will have to look at them without guidance. <p>
-<hr>
-Back to the <A HREF="index.html">index</A> to pick another example.
Modified: python/branches/p3yk/Mac/scripts/BuildApplet.py
==============================================================================
--- python/branches/p3yk/Mac/scripts/BuildApplet.py (original)
+++ python/branches/p3yk/Mac/scripts/BuildApplet.py Thu Jun 8 17:35:45 2006
@@ -16,6 +16,18 @@
import buildtools
import getopt
+if not sys.executable.startswith(sys.exec_prefix):
+ # Oh, the joys of using a python script to bootstrap applicatin bundles
+ # sys.executable points inside the current application bundle. Because this
+ # path contains blanks (two of them actually) this path isn't usable on
+ # #! lines. Reset sys.executable to point to the embedded python interpreter
+ sys.executable = os.path.join(sys.prefix,
+ 'Resources/Python.app/Contents/MacOS/Python')
+
+ # Just in case we're not in a framework:
+ if not os.path.exists(sys.executable):
+ sys.executable = os.path.join(sys.exec_prefix, 'bin/python')
+
def main():
try:
buildapplet()
Modified: python/branches/p3yk/Makefile.pre.in
==============================================================================
--- python/branches/p3yk/Makefile.pre.in (original)
+++ python/branches/p3yk/Makefile.pre.in Thu Jun 8 17:35:45 2006
@@ -370,12 +370,12 @@
fi
libpython$(VERSION).sl: $(LIBRARY_OBJS)
- $(LDSHARED) -o $@ $(LIBRARY_OBJS) $(LIBC) $(LIBM)
+ $(LDSHARED) -o $@ $(LIBRARY_OBJS) $(SHLIBS) $(LIBC) $(LIBM)
# This rule is here for OPENSTEP/Rhapsody/MacOSX. It builds a temporary
# minimal framework (not including the Lib directory and such) in the current
# directory.
-RESSRCDIR=$(srcdir)/Mac/OSXResources/framework
+RESSRCDIR=$(srcdir)/Mac/Resources/framework
$(PYTHONFRAMEWORKDIR)/Versions/$(VERSION)/$(PYTHONFRAMEWORK): \
$(LIBRARY) \
$(RESSRCDIR)/Info.plist \
@@ -619,8 +619,8 @@
install: @FRAMEWORKINSTALLFIRST@ altinstall bininstall maninstall @FRAMEWORKINSTALLLAST@
# Install almost everything without disturbing previous versions
-altinstall: altbininstall libinstall inclinstall libainstall \
- sharedinstall oldsharedinstall
+altinstall: @FRAMEWORKALTINSTALLFIRST@ altbininstall libinstall inclinstall libainstall \
+ sharedinstall oldsharedinstall @FRAMEWORKALTINSTALLLAST@
# Install shared libraries enabled by Setup
DESTDIRS= $(exec_prefix) $(LIBDIR) $(BINLIBDEST) $(DESTSHARED)
@@ -899,7 +899,7 @@
# Here are a couple of targets for MacOSX again, to install a full
# framework-based Python. frameworkinstall installs everything, the
# subtargets install specific parts. Much of the actual work is offloaded to
-# the Makefile in Mac/OSX
+# the Makefile in Mac
#
#
# This target is here for backward compatiblity, previous versions of Python
@@ -940,22 +940,23 @@
# This installs Mac/Lib into the framework
frameworkinstallmaclib:
- cd Mac/OSX && $(MAKE) installmacsubtree DESTDIR="$(DESTDIR)"
+ cd Mac && $(MAKE) installmacsubtree DESTDIR="$(DESTDIR)"
# This installs the IDE, the Launcher and other apps into /Applications
frameworkinstallapps:
- cd Mac/OSX && $(MAKE) installapps DESTDIR="$(DESTDIR)"
+ cd Mac && $(MAKE) installapps DESTDIR="$(DESTDIR)"
# This install the unix python and pythonw tools in /usr/local/bin
frameworkinstallunixtools:
- cd Mac/OSX && $(MAKE) installunixtools DESTDIR="$(DESTDIR)"
+ cd Mac && $(MAKE) installunixtools DESTDIR="$(DESTDIR)"
+
+frameworkaltinstallunixtools:
+ cd Mac && $(MAKE) altinstallunixtools DESTDIR="$(DESTDIR)"
# This installs the Demos and Tools into the applications directory.
# It is not part of a normal frameworkinstall
frameworkinstallextras:
- $(MAKE) -f Mac/OSX/Makefile installextras \
- $(RUNSHARED) BUILDPYTHON=./$(BUILDPYTHON) DIRMODE=$(DIRMODE) FILEMODE=$(FILEMODE) \
- srcdir=$(srcdir) builddir=. DESTDIR=$(DESTDIR)
+ cd Mac && Make installextras DESTDIR="$(DESTDIR)"
# This installs a few of the useful scripts in Tools/scripts
scriptsinstall:
@@ -1083,6 +1084,7 @@
.PHONY: maninstall libinstall inclinstall libainstall sharedinstall
.PHONY: frameworkinstall frameworkinstallframework frameworkinstallstructure
.PHONY: frameworkinstallmaclib frameworkinstallapps frameworkinstallunixtools
-.PHONY: recheck autoconf clean clobber distclean smelly funny
+.PHONY: frameworkaltinstallunixtools recheck autoconf clean clobber distclean
+.PHONY: smelly funny
# IF YOU PUT ANYTHING HERE IT WILL GO AWAY
Modified: python/branches/p3yk/Misc/SpecialBuilds.txt
==============================================================================
--- python/branches/p3yk/Misc/SpecialBuilds.txt (original)
+++ python/branches/p3yk/Misc/SpecialBuilds.txt Thu Jun 8 17:35:45 2006
@@ -96,16 +96,16 @@
Strings of these bytes are unlikely to be valid addresses, floats, or 7-bit
ASCII strings.
-8 bytes are added at each end of each block of N bytes requested. The
-memory layout is like so, where p represents the address returned by a
-malloc-like or realloc-like function (p[i:j] means the slice of bytes
-from *(p+i) inclusive up to *(p+j) exclusive; note that the treatment
-of negative indices differs from a Python slice):
-
-p[-8:-4]
- Number of bytes originally asked for. 4-byte unsigned integer,
- big-endian (easier to read in a memory dump).
-p[-4:0]
+Let S = sizeof(size_t). 2*S bytes are added at each end of each block of N
+bytes requested. The memory layout is like so, where p represents the
+address returned by a malloc-like or realloc-like function (p[i:j] means
+the slice of bytes from *(p+i) inclusive up to *(p+j) exclusive; note that
+the treatment of negative indices differs from a Python slice):
+
+p[-2*S:-S]
+ Number of bytes originally asked for. This is a size_t, big-endian
+ (easier to read in a memory dump).
+p[-S:0]
Copies of FORBIDDENBYTE. Used to catch under- writes and reads.
p[0:N]
The requested memory, filled with copies of CLEANBYTE, used to catch
@@ -116,12 +116,12 @@
DEADBYTE, to catch reference to freed memory. When a realloc-
like function is called requesting a smaller memory block, the excess
old bytes are also filled with DEADBYTE.
-p[N:N+4]
+p[N:N+S]
Copies of FORBIDDENBYTE. Used to catch over- writes and reads.
-p[N+4:N+8]
+p[N+S:N+2*S]
A serial number, incremented by 1 on each call to a malloc-like or
realloc-like function.
- 4-byte unsigned integer, big-endian.
+ Big-endian size_t.
If "bad memory" is detected later, the serial number gives an
excellent way to set a breakpoint on the next run, to capture the
instant at which this block was passed out. The static function
@@ -145,6 +145,10 @@
If this envar exists, a report of pymalloc summary statistics is
printed to stderr whenever a new arena is allocated, and also
by Py_Finalize().
+
+Changed in 2.5: The number of extra bytes allocated is 4*sizeof(size_t).
+Before it was 16 on all boxes, reflecting that Python couldn't make use of
+allocations >= 2**32 bytes even on 64-bit boxes before 2.5.
---------------------------------------------------------------------------
Py_DEBUG introduced in 1.5
named DEBUG before 1.5
@@ -251,7 +255,7 @@
find the manual for your specific processor. For the 750CX, 750CXe
and 750FX (all sold as the G3) we find:
- The time base counter is clocked at a frequency that is
+ The time base counter is clocked at a frequency that is
one-fourth that of the bus clock.
This build is enabled by the --with-tsc flag to configure.
Modified: python/branches/p3yk/Modules/_bsddb.c
==============================================================================
--- python/branches/p3yk/Modules/_bsddb.c (original)
+++ python/branches/p3yk/Modules/_bsddb.c Thu Jun 8 17:35:45 2006
@@ -61,13 +61,14 @@
*
* http://www.python.org/peps/pep-0291.html
*
- * This module contains 5 types:
+ * This module contains 6 types:
*
* DB (Database)
* DBCursor (Database Cursor)
* DBEnv (database environment)
* DBTxn (An explicit database transaction)
* DBLock (A lock handle)
+ * DBSequence (Sequence)
*
*/
@@ -97,7 +98,7 @@
#error "eek! DBVER can't handle minor versions > 9"
#endif
-#define PY_BSDDB_VERSION "4.4.2"
+#define PY_BSDDB_VERSION "4.4.4"
static char *rcs_id = "$Id$";
@@ -285,7 +286,17 @@
#endif
} DBLockObject;
-
+#if (DBVER >= 43)
+typedef struct {
+ PyObject_HEAD
+ DB_SEQUENCE* sequence;
+ DBObject* mydb;
+#ifdef HAVE_WEAKREF
+ PyObject *in_weakreflist; /* List of weak references */
+#endif
+} DBSequenceObject;
+static PyTypeObject DBSequence_Type;
+#endif
static PyTypeObject DB_Type, DBCursor_Type, DBEnv_Type, DBTxn_Type, DBLock_Type;
@@ -294,6 +305,9 @@
#define DBEnvObject_Check(v) ((v)->ob_type == &DBEnv_Type)
#define DBTxnObject_Check(v) ((v)->ob_type == &DBTxn_Type)
#define DBLockObject_Check(v) ((v)->ob_type == &DBLock_Type)
+#if (DBVER >= 43)
+#define DBSequenceObject_Check(v) ((v)->ob_type == &DBSequence_Type)
+#endif
/* --------------------------------------------------------------------- */
@@ -324,6 +338,10 @@
#define CHECK_CURSOR_NOT_CLOSED(curs) \
_CHECK_OBJECT_NOT_CLOSED(curs->dbc, DBCursorClosedError, DBCursor)
+#if (DBVER >= 43)
+#define CHECK_SEQUENCE_NOT_CLOSED(curs) \
+ _CHECK_OBJECT_NOT_CLOSED(curs->sequence, DBError, DBSequence)
+#endif
#define CHECK_DBFLAG(mydb, flag) (((mydb)->flags & (flag)) || \
(((mydb)->myenvobj != NULL) && ((mydb)->myenvobj->flags & (flag))))
@@ -724,7 +742,17 @@
Py_XDECREF(v);
}
+#if (DBVER >= 43)
+/* add an db_seq_t to a dictionary using the given name as a key */
+static void _addDb_seq_tToDict(PyObject* dict, char *name, db_seq_t value)
+{
+ PyObject* v = PyLong_FromLongLong(value);
+ if (!v || PyDict_SetItemString(dict, name, v))
+ PyErr_Clear();
+ Py_XDECREF(v);
+}
+#endif
@@ -777,7 +805,7 @@
MYDB_END_ALLOW_THREADS;
/* TODO add a weakref(self) to the self->myenvobj->open_child_weakrefs
* list so that a DBEnv can refuse to close without aborting any open
- * open DBTxns and closing any open DBs first. */
+ * DBTxns and closing any open DBs first. */
if (makeDBError(err)) {
if (self->myenvobj) {
Py_DECREF(self->myenvobj);
@@ -1029,6 +1057,48 @@
}
+#if (DBVER >= 43)
+static DBSequenceObject*
+newDBSequenceObject(DBObject* mydb, int flags)
+{
+ int err;
+ DBSequenceObject* self = PyObject_New(DBSequenceObject, &DBSequence_Type);
+ if (self == NULL)
+ return NULL;
+ Py_INCREF(mydb);
+ self->mydb = mydb;
+#ifdef HAVE_WEAKREF
+ self->in_weakreflist = NULL;
+#endif
+
+
+ MYDB_BEGIN_ALLOW_THREADS;
+ err = db_sequence_create(&self->sequence, self->mydb->db, flags);
+ MYDB_END_ALLOW_THREADS;
+ if (makeDBError(err)) {
+ Py_DECREF(self->mydb);
+ PyObject_Del(self);
+ self = NULL;
+ }
+
+ return self;
+}
+
+
+static void
+DBSequence_dealloc(DBSequenceObject* self)
+{
+#ifdef HAVE_WEAKREF
+ if (self->in_weakreflist != NULL) {
+ PyObject_ClearWeakRefs((PyObject *) self);
+ }
+#endif
+
+ Py_DECREF(self->mydb);
+ PyObject_Del(self);
+}
+#endif
+
/* --------------------------------------------------------------------- */
/* DB methods */
@@ -2614,7 +2684,7 @@
Py_ssize_t DB_length(DBObject* self)
{
int err;
- long size = 0;
+ Py_ssize_t size = 0;
int flags = 0;
void* sp;
@@ -2627,10 +2697,11 @@
if (self->haveStat) { /* Has the stat function been called recently? If
so, we can use the cached value. */
- flags = DB_CACHED_COUNTS;
+ flags = DB_FAST_STAT;
}
MYDB_BEGIN_ALLOW_THREADS;
+redo_stat_for_length:
#if (DBVER >= 43)
err = self->db->stat(self->db, /*txnid*/ NULL, &sp, flags);
#elif (DBVER >= 33)
@@ -2638,6 +2709,20 @@
#else
err = self->db->stat(self->db, &sp, NULL, flags);
#endif
+
+ /* All the stat structures have matching fields upto the ndata field,
+ so we can use any of them for the type cast */
+ size = ((DB_BTREE_STAT*)sp)->bt_ndata;
+
+ /* A size of 0 could mean that BerkeleyDB no longer had the stat values cached.
+ * redo a full stat to make sure.
+ * Fixes SF python bug 1493322, pybsddb bug 1184012
+ */
+ if (size == 0 && (flags & DB_FAST_STAT)) {
+ flags = 0;
+ goto redo_stat_for_length;
+ }
+
MYDB_END_ALLOW_THREADS;
if (err)
@@ -2645,9 +2730,6 @@
self->haveStat = 1;
- /* All the stat structures have matching fields upto the ndata field,
- so we can use any of them for the type cast */
- size = ((DB_BTREE_STAT*)sp)->bt_ndata;
free(sp);
return size;
}
@@ -3124,8 +3206,8 @@
int dlen = -1;
int doff = -1;
DBT key, pkey, data;
- static char* kwnames[] = { "key","data", "flags", "dlen", "doff",
- NULL };
+ static char* kwnames_keyOnly[] = { "key", "flags", "dlen", "doff", NULL };
+ static char* kwnames[] = { "key", "data", "flags", "dlen", "doff", NULL };
CLEAR_DBT(key);
CLEAR_DBT(data);
@@ -3134,7 +3216,7 @@
{
PyErr_Clear();
if (!PyArg_ParseTupleAndKeywords(args, kwargs, "Oi|ii:pget",
- &kwnames[1],
+ kwnames_keyOnly,
&keyobj, &flags, &dlen, &doff))
{
PyErr_Clear();
@@ -4294,6 +4376,93 @@
RETURN_NONE();
}
+#if (DBVER >= 44)
+static PyObject*
+DBEnv_lsn_reset(DBEnvObject* self, PyObject* args, PyObject* kwargs)
+{
+ int err;
+ char *file;
+ u_int32_t flags = 0;
+ static char* kwnames[] = { "file", "flags", NULL};
+
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "z|i:lsn_reset", kwnames,
+ &file, &flags))
+ return NULL;
+ CHECK_ENV_NOT_CLOSED(self);
+
+ MYDB_BEGIN_ALLOW_THREADS;
+ err = self->db_env->lsn_reset(self->db_env, file, flags);
+ MYDB_END_ALLOW_THREADS;
+ RETURN_IF_ERR();
+ RETURN_NONE();
+}
+#endif /* DBVER >= 4.4 */
+
+#if (DBVER >= 40)
+static PyObject*
+DBEnv_log_stat(DBEnvObject* self, PyObject* args)
+{
+ int err;
+ DB_LOG_STAT* statp = NULL;
+ PyObject* d = NULL;
+ u_int32_t flags = 0;
+
+ if (!PyArg_ParseTuple(args, "|i:log_stat", &flags))
+ return NULL;
+ CHECK_ENV_NOT_CLOSED(self);
+
+ MYDB_BEGIN_ALLOW_THREADS;
+ err = self->db_env->log_stat(self->db_env, &statp, flags);
+ MYDB_END_ALLOW_THREADS;
+ RETURN_IF_ERR();
+
+ /* Turn the stat structure into a dictionary */
+ d = PyDict_New();
+ if (d == NULL) {
+ if (statp)
+ free(statp);
+ return NULL;
+ }
+
+#define MAKE_ENTRY(name) _addIntToDict(d, #name, statp->st_##name)
+
+ MAKE_ENTRY(magic);
+ MAKE_ENTRY(version);
+ MAKE_ENTRY(mode);
+ MAKE_ENTRY(lg_bsize);
+#if (DBVER >= 44)
+ MAKE_ENTRY(lg_size);
+ MAKE_ENTRY(record);
+#endif
+#if (DBVER <= 40)
+ MAKE_ENTRY(lg_max);
+#endif
+ MAKE_ENTRY(w_mbytes);
+ MAKE_ENTRY(w_bytes);
+ MAKE_ENTRY(wc_mbytes);
+ MAKE_ENTRY(wc_bytes);
+ MAKE_ENTRY(wcount);
+ MAKE_ENTRY(wcount_fill);
+#if (DBVER >= 44)
+ MAKE_ENTRY(rcount);
+#endif
+ MAKE_ENTRY(scount);
+ MAKE_ENTRY(cur_file);
+ MAKE_ENTRY(cur_offset);
+ MAKE_ENTRY(disk_file);
+ MAKE_ENTRY(disk_offset);
+ MAKE_ENTRY(maxcommitperflush);
+ MAKE_ENTRY(mincommitperflush);
+ MAKE_ENTRY(regsize);
+ MAKE_ENTRY(region_wait);
+ MAKE_ENTRY(region_nowait);
+
+#undef MAKE_ENTRY
+ free(statp);
+ return d;
+} /* DBEnv_log_stat */
+#endif /* DBVER >= 4.0 for log_stat method */
+
static PyObject*
DBEnv_lock_stat(DBEnvObject* self, PyObject* args)
@@ -4371,7 +4540,7 @@
{
int flags=0;
int err;
- char **log_list_start, **log_list;
+ char **log_list = NULL;
PyObject* list;
PyObject* item = NULL;
@@ -4391,10 +4560,14 @@
RETURN_IF_ERR();
list = PyList_New(0);
- if (list == NULL)
+ if (list == NULL) {
+ if (log_list)
+ free(log_list);
return NULL;
+ }
if (log_list) {
+ char **log_list_start;
for (log_list_start = log_list; *log_list != NULL; ++log_list) {
item = PyString_FromString (*log_list);
if (item == NULL) {
@@ -4624,6 +4797,294 @@
return PyInt_FromLong(id);
}
+#if (DBVER >= 43)
+/* --------------------------------------------------------------------- */
+/* DBSequence methods */
+
+
+static PyObject*
+DBSequence_close(DBSequenceObject* self, PyObject* args)
+{
+ int err, flags=0;
+ if (!PyArg_ParseTuple(args,"|i:close", &flags))
+ return NULL;
+ CHECK_SEQUENCE_NOT_CLOSED(self)
+
+ MYDB_BEGIN_ALLOW_THREADS
+ err = self->sequence->close(self->sequence, flags);
+ self->sequence = NULL;
+ MYDB_END_ALLOW_THREADS
+
+ RETURN_IF_ERR();
+
+ RETURN_NONE();
+}
+
+static PyObject*
+DBSequence_get(DBSequenceObject* self, PyObject* args, PyObject* kwargs)
+{
+ int err, flags = 0;
+ int delta = 1;
+ db_seq_t value;
+ PyObject *txnobj = NULL;
+ DB_TXN *txn = NULL;
+ static char* kwnames[] = {"delta", "txn", "flags", NULL };
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|iOi:get", kwnames, &delta, &txnobj, &flags))
+ return NULL;
+ CHECK_SEQUENCE_NOT_CLOSED(self)
+
+ if (!checkTxnObj(txnobj, &txn))
+ return NULL;
+
+ MYDB_BEGIN_ALLOW_THREADS
+ err = self->sequence->get(self->sequence, txn, delta, &value, flags);
+ MYDB_END_ALLOW_THREADS
+
+ RETURN_IF_ERR();
+ return PyLong_FromLongLong(value);
+
+}
+
+static PyObject*
+DBSequence_get_dbp(DBSequenceObject* self, PyObject* args)
+{
+ if (!PyArg_ParseTuple(args,":get_dbp"))
+ return NULL;
+ CHECK_SEQUENCE_NOT_CLOSED(self)
+ Py_INCREF(self->mydb);
+ return (PyObject* )self->mydb;
+}
+
+static PyObject*
+DBSequence_get_key(DBSequenceObject* self, PyObject* args)
+{
+ int err;
+ DBT key;
+ CHECK_SEQUENCE_NOT_CLOSED(self)
+ MYDB_BEGIN_ALLOW_THREADS
+ err = self->sequence->get_key(self->sequence, &key);
+ MYDB_END_ALLOW_THREADS
+
+ RETURN_IF_ERR();
+
+ return PyString_FromStringAndSize(key.data, key.size);
+}
+
+static PyObject*
+DBSequence_init_value(DBSequenceObject* self, PyObject* args)
+{
+ int err;
+ db_seq_t value;
+ if (!PyArg_ParseTuple(args,"L:init_value", &value))
+ return NULL;
+ CHECK_SEQUENCE_NOT_CLOSED(self)
+
+ MYDB_BEGIN_ALLOW_THREADS
+ err = self->sequence->initial_value(self->sequence, value);
+ MYDB_END_ALLOW_THREADS
+
+ RETURN_IF_ERR();
+
+ RETURN_NONE();
+}
+
+static PyObject*
+DBSequence_open(DBSequenceObject* self, PyObject* args, PyObject* kwargs)
+{
+ int err, flags = 0;
+ PyObject* keyobj;
+ PyObject *txnobj = NULL;
+ DB_TXN *txn = NULL;
+ DBT key;
+
+ static char* kwnames[] = {"key", "txn", "flags", NULL };
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O|Oi:open", kwnames, &keyobj, &txnobj, &flags))
+ return NULL;
+
+ if (!checkTxnObj(txnobj, &txn))
+ return NULL;
+
+ if (!make_key_dbt(self->mydb, keyobj, &key, NULL))
+ return NULL;
+
+ MYDB_BEGIN_ALLOW_THREADS
+ err = self->sequence->open(self->sequence, txn, &key, flags);
+ MYDB_END_ALLOW_THREADS
+
+ CLEAR_DBT(key);
+ RETURN_IF_ERR();
+
+ RETURN_NONE();
+}
+
+static PyObject*
+DBSequence_remove(DBSequenceObject* self, PyObject* args, PyObject* kwargs)
+{
+ int err, flags = 0;
+ PyObject *txnobj = NULL;
+ DB_TXN *txn = NULL;
+
+ static char* kwnames[] = {"txn", "flags", NULL };
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|Oi:remove", kwnames, &txnobj, &flags))
+ return NULL;
+
+ if (!checkTxnObj(txnobj, &txn))
+ return NULL;
+
+ CHECK_SEQUENCE_NOT_CLOSED(self)
+
+ MYDB_BEGIN_ALLOW_THREADS
+ err = self->sequence->remove(self->sequence, txn, flags);
+ MYDB_END_ALLOW_THREADS
+
+ RETURN_IF_ERR();
+ RETURN_NONE();
+}
+
+static PyObject*
+DBSequence_set_cachesize(DBSequenceObject* self, PyObject* args)
+{
+ int err, size;
+ if (!PyArg_ParseTuple(args,"i:set_cachesize", &size))
+ return NULL;
+ CHECK_SEQUENCE_NOT_CLOSED(self)
+
+ MYDB_BEGIN_ALLOW_THREADS
+ err = self->sequence->set_cachesize(self->sequence, size);
+ MYDB_END_ALLOW_THREADS
+
+ RETURN_IF_ERR();
+ RETURN_NONE();
+}
+
+static PyObject*
+DBSequence_get_cachesize(DBSequenceObject* self, PyObject* args)
+{
+ int err, size;
+ if (!PyArg_ParseTuple(args,":get_cachesize"))
+ return NULL;
+ CHECK_SEQUENCE_NOT_CLOSED(self)
+
+ MYDB_BEGIN_ALLOW_THREADS
+ err = self->sequence->get_cachesize(self->sequence, &size);
+ MYDB_END_ALLOW_THREADS
+
+ RETURN_IF_ERR();
+ return PyInt_FromLong(size);
+}
+
+static PyObject*
+DBSequence_set_flags(DBSequenceObject* self, PyObject* args)
+{
+ int err, flags = 0;
+ if (!PyArg_ParseTuple(args,"i:set_flags", &flags))
+ return NULL;
+ CHECK_SEQUENCE_NOT_CLOSED(self)
+
+ MYDB_BEGIN_ALLOW_THREADS
+ err = self->sequence->set_flags(self->sequence, flags);
+ MYDB_END_ALLOW_THREADS
+
+ RETURN_IF_ERR();
+ RETURN_NONE();
+
+}
+
+static PyObject*
+DBSequence_get_flags(DBSequenceObject* self, PyObject* args)
+{
+ unsigned int flags;
+ int err;
+ if (!PyArg_ParseTuple(args,":get_flags"))
+ return NULL;
+ CHECK_SEQUENCE_NOT_CLOSED(self)
+
+ MYDB_BEGIN_ALLOW_THREADS
+ err = self->sequence->get_flags(self->sequence, &flags);
+ MYDB_END_ALLOW_THREADS
+
+ RETURN_IF_ERR();
+ return PyInt_FromLong((int)flags);
+}
+
+static PyObject*
+DBSequence_set_range(DBSequenceObject* self, PyObject* args)
+{
+ int err;
+ db_seq_t min, max;
+ if (!PyArg_ParseTuple(args,"(LL):set_range", &min, &max))
+ return NULL;
+ CHECK_SEQUENCE_NOT_CLOSED(self)
+
+ MYDB_BEGIN_ALLOW_THREADS
+ err = self->sequence->set_range(self->sequence, min, max);
+ MYDB_END_ALLOW_THREADS
+
+ RETURN_IF_ERR();
+ RETURN_NONE();
+}
+
+static PyObject*
+DBSequence_get_range(DBSequenceObject* self, PyObject* args)
+{
+ int err;
+ db_seq_t min, max;
+ if (!PyArg_ParseTuple(args,":get_range"))
+ return NULL;
+ CHECK_SEQUENCE_NOT_CLOSED(self)
+
+ MYDB_BEGIN_ALLOW_THREADS
+ err = self->sequence->get_range(self->sequence, &min, &max);
+ MYDB_END_ALLOW_THREADS
+
+ RETURN_IF_ERR();
+ return Py_BuildValue("(LL)", min, max);
+}
+
+static PyObject*
+DBSequence_stat(DBSequenceObject* self, PyObject* args, PyObject* kwargs)
+{
+ int err, flags = 0;
+ DB_SEQUENCE_STAT* sp = NULL;
+ PyObject* dict_stat;
+ static char* kwnames[] = {"flags", NULL };
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|i:stat", kwnames, &flags))
+ return NULL;
+ CHECK_SEQUENCE_NOT_CLOSED(self);
+
+ MYDB_BEGIN_ALLOW_THREADS;
+ err = self->sequence->stat(self->sequence, &sp, flags);
+ MYDB_END_ALLOW_THREADS;
+ RETURN_IF_ERR();
+
+ if ((dict_stat = PyDict_New()) == NULL) {
+ free(sp);
+ return NULL;
+ }
+
+
+#define MAKE_INT_ENTRY(name) _addIntToDict(dict_stat, #name, sp->st_##name)
+#define MAKE_LONG_LONG_ENTRY(name) _addDb_seq_tToDict(dict_stat, #name, sp->st_##name)
+
+ MAKE_INT_ENTRY(wait);
+ MAKE_INT_ENTRY(nowait);
+ MAKE_LONG_LONG_ENTRY(current);
+ MAKE_LONG_LONG_ENTRY(value);
+ MAKE_LONG_LONG_ENTRY(last_value);
+ MAKE_LONG_LONG_ENTRY(min);
+ MAKE_LONG_LONG_ENTRY(max);
+ MAKE_INT_ENTRY(cache_size);
+ MAKE_INT_ENTRY(flags);
+
+#undef MAKE_INT_ENTRY
+#undef MAKE_LONG_LONG_ENTRY
+
+ free(sp);
+ return dict_stat;
+}
+#endif
+
+
/* --------------------------------------------------------------------- */
/* Method definition tables and type objects */
@@ -4777,6 +5238,12 @@
{"lock_put", (PyCFunction)DBEnv_lock_put, METH_VARARGS},
{"lock_stat", (PyCFunction)DBEnv_lock_stat, METH_VARARGS},
{"log_archive", (PyCFunction)DBEnv_log_archive, METH_VARARGS},
+#if (DBVER >= 40)
+ {"log_stat", (PyCFunction)DBEnv_log_stat, METH_VARARGS},
+#endif
+#if (DBVER >= 44)
+ {"lsn_reset", (PyCFunction)DBEnv_lsn_reset, METH_VARARGS|METH_KEYWORDS},
+#endif
{"set_get_returns_none",(PyCFunction)DBEnv_set_get_returns_none, METH_VARARGS},
{NULL, NULL} /* sentinel */
};
@@ -4791,6 +5258,27 @@
};
+#if (DBVER >= 43)
+static PyMethodDef DBSequence_methods[] = {
+ {"close", (PyCFunction)DBSequence_close, METH_VARARGS},
+ {"get", (PyCFunction)DBSequence_get, METH_VARARGS|METH_KEYWORDS},
+ {"get_dbp", (PyCFunction)DBSequence_get_dbp, METH_VARARGS},
+ {"get_key", (PyCFunction)DBSequence_get_key, METH_VARARGS},
+ {"init_value", (PyCFunction)DBSequence_init_value, METH_VARARGS},
+ {"open", (PyCFunction)DBSequence_open, METH_VARARGS|METH_KEYWORDS},
+ {"remove", (PyCFunction)DBSequence_remove, METH_VARARGS|METH_KEYWORDS},
+ {"set_cachesize", (PyCFunction)DBSequence_set_cachesize, METH_VARARGS},
+ {"get_cachesize", (PyCFunction)DBSequence_get_cachesize, METH_VARARGS},
+ {"set_flags", (PyCFunction)DBSequence_set_flags, METH_VARARGS},
+ {"get_flags", (PyCFunction)DBSequence_get_flags, METH_VARARGS},
+ {"set_range", (PyCFunction)DBSequence_set_range, METH_VARARGS},
+ {"get_range", (PyCFunction)DBSequence_get_range, METH_VARARGS},
+ {"stat", (PyCFunction)DBSequence_stat, METH_VARARGS|METH_KEYWORDS},
+ {NULL, NULL} /* sentinel */
+};
+#endif
+
+
static PyObject*
DB_getattr(DBObject* self, char *name)
{
@@ -4831,6 +5319,14 @@
return NULL;
}
+#if (DBVER >= 43)
+static PyObject*
+DBSequence_getattr(DBSequenceObject* self, char *name)
+{
+ return Py_FindMethod(DBSequence_methods, (PyObject* )self, name);
+}
+#endif
+
static PyTypeObject DB_Type = {
PyObject_HEAD_INIT(NULL)
0, /*ob_size*/
@@ -4994,6 +5490,39 @@
#endif
};
+#if (DBVER >= 43)
+static PyTypeObject DBSequence_Type = {
+ PyObject_HEAD_INIT(NULL)
+ 0, /*ob_size*/
+ "DBSequence", /*tp_name*/
+ sizeof(DBSequenceObject), /*tp_basicsize*/
+ 0, /*tp_itemsize*/
+ /* methods */
+ (destructor)DBSequence_dealloc, /*tp_dealloc*/
+ 0, /*tp_print*/
+ (getattrfunc)DBSequence_getattr,/*tp_getattr*/
+ 0, /*tp_setattr*/
+ 0, /*tp_compare*/
+ 0, /*tp_repr*/
+ 0, /*tp_as_number*/
+ 0, /*tp_as_sequence*/
+ 0, /*tp_as_mapping*/
+ 0, /*tp_hash*/
+#ifdef HAVE_WEAKREF
+ 0, /* tp_call */
+ 0, /* tp_str */
+ 0, /* tp_getattro */
+ 0, /* tp_setattro */
+ 0, /* tp_as_buffer */
+ Py_TPFLAGS_DEFAULT | Py_TPFLAGS_HAVE_WEAKREFS, /* tp_flags */
+ 0, /* tp_doc */
+ 0, /* tp_traverse */
+ 0, /* tp_clear */
+ 0, /* tp_richcompare */
+ offsetof(DBSequenceObject, in_weakreflist), /* tp_weaklistoffset */
+#endif
+};
+#endif
/* --------------------------------------------------------------------- */
/* Module-level functions */
@@ -5027,6 +5556,25 @@
return (PyObject* )newDBEnvObject(flags);
}
+#if (DBVER >= 43)
+static PyObject*
+DBSequence_construct(PyObject* self, PyObject* args, PyObject* kwargs)
+{
+ PyObject* dbobj = NULL;
+ int flags = 0;
+ static char* kwnames[] = { "db", "flags", NULL};
+
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O|i:DBSequence", kwnames, &dbobj, &flags))
+ return NULL;
+ if (dbobj == Py_None)
+ dbobj = NULL;
+ else if (dbobj && !DBObject_Check(dbobj)) {
+ makeTypeError("DB", dbobj);
+ return NULL;
+ }
+ return (PyObject* )newDBSequenceObject((DBObject*)dbobj, flags);
+}
+#endif
static char bsddb_version_doc[] =
"Returns a tuple of major, minor, and patch release numbers of the\n\
@@ -5047,9 +5595,12 @@
/* List of functions defined in the module */
static PyMethodDef bsddb_methods[] = {
- {"DB", (PyCFunction)DB_construct, METH_VARARGS | METH_KEYWORDS },
- {"DBEnv", (PyCFunction)DBEnv_construct, METH_VARARGS},
- {"version", (PyCFunction)bsddb_version, METH_VARARGS, bsddb_version_doc},
+ {"DB", (PyCFunction)DB_construct, METH_VARARGS | METH_KEYWORDS },
+ {"DBEnv", (PyCFunction)DBEnv_construct, METH_VARARGS},
+#if (DBVER >= 43)
+ {"DBSequence", (PyCFunction)DBSequence_construct, METH_VARARGS | METH_KEYWORDS },
+#endif
+ {"version", (PyCFunction)bsddb_version, METH_VARARGS, bsddb_version_doc},
{NULL, NULL} /* sentinel */
};
@@ -5081,6 +5632,9 @@
DBEnv_Type.ob_type = &PyType_Type;
DBTxn_Type.ob_type = &PyType_Type;
DBLock_Type.ob_type = &PyType_Type;
+#if (DBVER >= 43)
+ DBSequence_Type.ob_type = &PyType_Type;
+#endif
#if defined(WITH_THREAD) && !defined(MYDB_USE_GILSTATE)
@@ -5247,6 +5801,9 @@
ADD_INT(d, DB_ARCH_ABS);
ADD_INT(d, DB_ARCH_DATA);
ADD_INT(d, DB_ARCH_LOG);
+#if (DBVER >= 42)
+ ADD_INT(d, DB_ARCH_REMOVE);
+#endif
ADD_INT(d, DB_BTREE);
ADD_INT(d, DB_HASH);
@@ -5368,6 +5925,9 @@
#if (DBVER >= 43)
ADD_INT(d, DB_LOG_INMEMORY);
ADD_INT(d, DB_BUFFER_SMALL);
+ ADD_INT(d, DB_SEQ_DEC);
+ ADD_INT(d, DB_SEQ_INC);
+ ADD_INT(d, DB_SEQ_WRAP);
#endif
#if (DBVER >= 41)
Modified: python/branches/p3yk/Modules/_codecsmodule.c
==============================================================================
--- python/branches/p3yk/Modules/_codecsmodule.c (original)
+++ python/branches/p3yk/Modules/_codecsmodule.c Thu Jun 8 17:35:45 2006
@@ -792,6 +792,15 @@
return v;
}
+static PyObject*
+charmap_build(PyObject *self, PyObject *args)
+{
+ PyObject *map;
+ if (!PyArg_ParseTuple(args, "U:charmap_build", &map))
+ return NULL;
+ return PyUnicode_BuildEncodingMap(map);
+}
+
#if defined(MS_WINDOWS) && defined(HAVE_USABLE_WCHAR_T)
static PyObject *
@@ -897,6 +906,7 @@
{"ascii_decode", ascii_decode, METH_VARARGS},
{"charmap_encode", charmap_encode, METH_VARARGS},
{"charmap_decode", charmap_decode, METH_VARARGS},
+ {"charmap_build", charmap_build, METH_VARARGS},
{"readbuffer_encode", readbuffer_encode, METH_VARARGS},
{"charbuffer_encode", charbuffer_encode, METH_VARARGS},
#if defined(MS_WINDOWS) && defined(HAVE_USABLE_WCHAR_T)
Modified: python/branches/p3yk/Modules/_ctypes/callbacks.c
==============================================================================
--- python/branches/p3yk/Modules/_ctypes/callbacks.c (original)
+++ python/branches/p3yk/Modules/_ctypes/callbacks.c Thu Jun 8 17:35:45 2006
@@ -199,45 +199,16 @@
result = PyObject_CallObject(callable, arglist);
CHECK("'calling callback function'", result);
- if ((restype != &ffi_type_void)
- && result && result != Py_None) { /* XXX What is returned for Py_None ? */
- /* another big endian hack */
- union {
- char c;
- short s;
- int i;
- long l;
- } r;
+ if ((restype != &ffi_type_void) && result && result != Py_None) {
PyObject *keep;
assert(setfunc);
- switch (restype->size) {
- case 1:
- keep = setfunc(&r, result, 0);
- CHECK("'converting callback result'", keep);
- *(ffi_arg *)mem = r.c;
- break;
- case SIZEOF_SHORT:
- keep = setfunc(&r, result, 0);
- CHECK("'converting callback result'", keep);
- *(ffi_arg *)mem = r.s;
- break;
- case SIZEOF_INT:
- keep = setfunc(&r, result, 0);
- CHECK("'converting callback result'", keep);
- *(ffi_arg *)mem = r.i;
- break;
-#if (SIZEOF_LONG != SIZEOF_INT)
- case SIZEOF_LONG:
- keep = setfunc(&r, result, 0);
- CHECK("'converting callback result'", keep);
- *(ffi_arg *)mem = r.l;
- break;
+#ifdef WORDS_BIGENDIAN
+ /* See the corresponding code in callproc.c, around line 961 */
+ if (restype->type != FFI_TYPE_FLOAT && restype->size < sizeof(ffi_arg))
+ mem = (char *)mem + sizeof(ffi_arg) - restype->size;
#endif
- default:
- keep = setfunc(mem, result, 0);
- CHECK("'converting callback result'", keep);
- break;
- }
+ keep = setfunc(mem, result, 0);
+ CHECK("'converting callback result'", keep);
/* keep is an object we have to keep alive so that the result
stays valid. If there is no such object, the setfunc will
have returned Py_None.
Modified: python/branches/p3yk/Modules/_ctypes/callproc.c
==============================================================================
--- python/branches/p3yk/Modules/_ctypes/callproc.c (original)
+++ python/branches/p3yk/Modules/_ctypes/callproc.c Thu Jun 8 17:35:45 2006
@@ -964,7 +964,14 @@
address cannot simply be used as result pointer, instead we must
adjust the pointer value:
*/
- if (rtype->size < sizeof(ffi_arg))
+ /*
+ XXX I should find out and clarify why this is needed at all,
+ especially why adjusting for ffi_type_float must be avoided on
+ 64-bit platforms.
+ */
+ if (rtype->type != FFI_TYPE_FLOAT
+ && rtype->type != FFI_TYPE_STRUCT
+ && rtype->size < sizeof(ffi_arg))
resbuf = (char *)resbuf + sizeof(ffi_arg) - rtype->size;
#endif
Modified: python/branches/p3yk/Modules/_ctypes/cfield.c
==============================================================================
--- python/branches/p3yk/Modules/_ctypes/cfield.c (original)
+++ python/branches/p3yk/Modules/_ctypes/cfield.c Thu Jun 8 17:35:45 2006
@@ -1,5 +1,4 @@
#include "Python.h"
-#include "structmember.h"
#include <ffi.h>
#ifdef MS_WIN32
@@ -208,14 +207,30 @@
self->index, self->size, src->b_ptr + self->offset);
}
-static PyMemberDef CField_members[] = {
- { "offset", T_UINT,
- offsetof(CFieldObject, offset), READONLY,
- "offset in bytes of this field"},
- { "size", T_UINT,
- offsetof(CFieldObject, size), READONLY,
- "size in bytes of this field"},
- { NULL },
+static PyObject *
+CField_get_offset(PyObject *self, void *data)
+{
+#if (PY_VERSION_HEX < 0x02050000)
+ return PyInt_FromLong(((CFieldObject *)self)->offset);
+#else
+ return PyInt_FromSsize_t(((CFieldObject *)self)->offset);
+#endif
+}
+
+static PyObject *
+CField_get_size(PyObject *self, void *data)
+{
+#if (PY_VERSION_HEX < 0x02050000)
+ return PyInt_FromLong(((CFieldObject *)self)->size);
+#else
+ return PyInt_FromSsize_t(((CFieldObject *)self)->size);
+#endif
+}
+
+static PyGetSetDef CField_getset[] = {
+ { "offset", CField_get_offset, NULL, "offset in bytes of this field" },
+ { "size", CField_get_size, NULL, "size in bytes of this field" },
+ { NULL, NULL, NULL, NULL },
};
static int
@@ -298,8 +313,8 @@
0, /* tp_iter */
0, /* tp_iternext */
0, /* tp_methods */
- CField_members, /* tp_members */
- 0, /* tp_getset */
+ 0, /* tp_members */
+ CField_getset, /* tp_getset */
0, /* tp_base */
0, /* tp_dict */
(descrgetfunc)CField_get, /* tp_descr_get */
Modified: python/branches/p3yk/Modules/_elementtree.c
==============================================================================
--- python/branches/p3yk/Modules/_elementtree.c (original)
+++ python/branches/p3yk/Modules/_elementtree.c Thu Jun 8 17:35:45 2006
@@ -1476,7 +1476,7 @@
}
static PyObject*
-treebuilder(PyObject* _self, PyObject* args)
+treebuilder(PyObject* self_, PyObject* args)
{
if (!PyArg_ParseTuple(args, ":TreeBuilder"))
return NULL;
@@ -2201,7 +2201,7 @@
/* constructor and destructor */
static PyObject*
-xmlparser(PyObject* _self, PyObject* args, PyObject* kw)
+xmlparser(PyObject* self_, PyObject* args, PyObject* kw)
{
XMLParserObject* self;
/* FIXME: does this need to be static? */
Modified: python/branches/p3yk/Modules/_struct.c
==============================================================================
--- python/branches/p3yk/Modules/_struct.c (original)
+++ python/branches/p3yk/Modules/_struct.c Thu Jun 8 17:35:45 2006
@@ -1572,8 +1572,7 @@
soself = (PyStructObject *)self;
assert(PyStruct_Check(self));
assert(soself->s_codes != NULL);
- if (args == NULL || !PyTuple_Check(args) ||
- PyTuple_GET_SIZE(args) != soself->s_len)
+ if (PyTuple_GET_SIZE(args) != soself->s_len)
{
PyErr_Format(StructError,
"pack requires exactly %zd arguments", soself->s_len);
@@ -1594,16 +1593,16 @@
return result;
}
-PyDoc_STRVAR(s_pack_to__doc__,
-"S.pack_to(buffer, offset, v1, v2, ...)\n\
+PyDoc_STRVAR(s_pack_into__doc__,
+"S.pack_into(buffer, offset, v1, v2, ...)\n\
\n\
-Pack the values v2, v2, ... according to this Struct's format, write \n\
+Pack the values v1, v2, ... according to this Struct's format, write \n\
the packed bytes into the writable buffer buf starting at offset. Note\n\
that the offset is not an optional argument. See struct.__doc__ for \n\
more on format strings.");
static PyObject *
-s_pack_to(PyObject *self, PyObject *args)
+s_pack_into(PyObject *self, PyObject *args)
{
PyStructObject *soself;
char *buffer;
@@ -1613,11 +1612,10 @@
soself = (PyStructObject *)self;
assert(PyStruct_Check(self));
assert(soself->s_codes != NULL);
- if (args == NULL || !PyTuple_Check(args) ||
- PyTuple_GET_SIZE(args) != (soself->s_len + 2))
+ if (PyTuple_GET_SIZE(args) != (soself->s_len + 2))
{
PyErr_Format(StructError,
- "pack_to requires exactly %zd arguments",
+ "pack_into requires exactly %zd arguments",
(soself->s_len + 2));
return NULL;
}
@@ -1630,7 +1628,7 @@
assert( buffer_len >= 0 );
/* Extract the offset from the first argument */
- offset = PyInt_AsLong(PyTuple_GET_ITEM(args, 1));
+ offset = PyInt_AsSsize_t(PyTuple_GET_ITEM(args, 1));
/* Support negative offsets. */
if (offset < 0)
@@ -1639,7 +1637,7 @@
/* Check boundaries */
if (offset < 0 || (buffer_len - offset) < soself->s_size) {
PyErr_Format(StructError,
- "pack_to requires a buffer of at least %zd bytes",
+ "pack_into requires a buffer of at least %zd bytes",
soself->s_size);
return NULL;
}
@@ -1668,10 +1666,11 @@
/* List of functions */
static struct PyMethodDef s_methods[] = {
- {"pack", (PyCFunction)s_pack, METH_VARARGS, s_pack__doc__},
- {"pack_to", (PyCFunction)s_pack_to, METH_VARARGS, s_pack_to__doc__},
- {"unpack", (PyCFunction)s_unpack, METH_O, s_unpack__doc__},
- {"unpack_from", (PyCFunction)s_unpack_from, METH_KEYWORDS, s_unpack_from__doc__},
+ {"pack", s_pack, METH_VARARGS, s_pack__doc__},
+ {"pack_into", s_pack_into, METH_VARARGS, s_pack_into__doc__},
+ {"unpack", s_unpack, METH_O, s_unpack__doc__},
+ {"unpack_from", (PyCFunction)s_unpack_from, METH_KEYWORDS,
+ s_unpack_from__doc__},
{NULL, NULL} /* sentinel */
};
Modified: python/branches/p3yk/Modules/_tkinter.c
==============================================================================
--- python/branches/p3yk/Modules/_tkinter.c (original)
+++ python/branches/p3yk/Modules/_tkinter.c Thu Jun 8 17:35:45 2006
@@ -1274,13 +1274,13 @@
and perform processing there. */
static PyObject *
-Tkapp_Call(PyObject *_self, PyObject *args)
+Tkapp_Call(PyObject *selfptr, PyObject *args)
{
Tcl_Obj *objStore[ARGSZ];
Tcl_Obj **objv = NULL;
int objc, i;
PyObject *res = NULL;
- TkappObject *self = (TkappObject*)_self;
+ TkappObject *self = (TkappObject*)selfptr;
/* Could add TCL_EVAL_GLOBAL if wrapped by GlobalCall... */
int flags = TCL_EVAL_DIRECT;
@@ -1326,7 +1326,7 @@
ENTER_OVERLAP
if (i == TCL_ERROR)
- Tkinter_Error(_self);
+ Tkinter_Error(selfptr);
else
res = Tkapp_CallResult(self);
@@ -1542,12 +1542,12 @@
}
static PyObject*
-var_invoke(EventFunc func, PyObject *_self, PyObject *args, int flags)
+var_invoke(EventFunc func, PyObject *selfptr, PyObject *args, int flags)
{
- TkappObject *self = (TkappObject*)_self;
+ TkappObject *self = (TkappObject*)selfptr;
#ifdef WITH_THREAD
if (self->threaded && self->thread_id != Tcl_GetCurrentThread()) {
- TkappObject *self = (TkappObject*)_self;
+ TkappObject *self = (TkappObject*)selfptr;
VarEvent *ev;
PyObject *res, *exc_type, *exc_val;
@@ -1559,7 +1559,7 @@
ev = (VarEvent*)ckalloc(sizeof(VarEvent));
- ev->self = _self;
+ ev->self = selfptr;
ev->args = args;
ev->flags = flags;
ev->func = func;
@@ -1579,7 +1579,7 @@
}
#endif
/* Tcl is not threaded, or this is the interpreter thread. */
- return func(_self, args, flags);
+ return func(selfptr, args, flags);
}
static PyObject *
@@ -2079,9 +2079,9 @@
}
static PyObject *
-Tkapp_CreateCommand(PyObject *_self, PyObject *args)
+Tkapp_CreateCommand(PyObject *selfptr, PyObject *args)
{
- TkappObject *self = (TkappObject*)_self;
+ TkappObject *self = (TkappObject*)selfptr;
PythonCmd_ClientData *data;
char *cmdName;
PyObject *func;
@@ -2105,7 +2105,7 @@
return PyErr_NoMemory();
Py_XINCREF(self);
Py_XINCREF(func);
- data->self = _self;
+ data->self = selfptr;
data->func = func;
if (self->threaded && self->thread_id != Tcl_GetCurrentThread()) {
@@ -2139,9 +2139,9 @@
static PyObject *
-Tkapp_DeleteCommand(PyObject *_self, PyObject *args)
+Tkapp_DeleteCommand(PyObject *selfptr, PyObject *args)
{
- TkappObject *self = (TkappObject*)_self;
+ TkappObject *self = (TkappObject*)selfptr;
char *cmdName;
int err;
@@ -2502,10 +2502,10 @@
/** Event Loop **/
static PyObject *
-Tkapp_MainLoop(PyObject *_self, PyObject *args)
+Tkapp_MainLoop(PyObject *selfptr, PyObject *args)
{
int threshold = 0;
- TkappObject *self = (TkappObject*)_self;
+ TkappObject *self = (TkappObject*)selfptr;
#ifdef WITH_THREAD
PyThreadState *tstate = PyThreadState_Get();
#endif
Modified: python/branches/p3yk/Modules/cjkcodecs/_codecs_jp.c
==============================================================================
--- python/branches/p3yk/Modules/cjkcodecs/_codecs_jp.c (original)
+++ python/branches/p3yk/Modules/cjkcodecs/_codecs_jp.c Thu Jun 8 17:35:45 2006
@@ -639,10 +639,11 @@
REQUIRE_OUTBUF(1)
JISX0201_DECODE(c, **outbuf)
else if ((c >= 0x81 && c <= 0x9f) || (c >= 0xe0 && c <= 0xfc)){
- unsigned char c1, c2 = IN2;
+ unsigned char c1, c2;
ucs4_t code;
REQUIRE_INBUF(2)
+ c2 = IN2;
if (c2 < 0x40 || (c2 > 0x7e && c2 < 0x80) || c2 > 0xfc)
return 2;
Modified: python/branches/p3yk/Modules/socketmodule.c
==============================================================================
--- python/branches/p3yk/Modules/socketmodule.c (original)
+++ python/branches/p3yk/Modules/socketmodule.c Thu Jun 8 17:35:45 2006
@@ -104,9 +104,9 @@
listen(n) -- start listening for incoming connections\n\
makefile([mode, [bufsize]]) -- return a file object for the socket [*]\n\
recv(buflen[, flags]) -- receive data\n\
-recv_buf(buffer[, nbytes[, flags]]) -- receive data (into a buffer)\n\
+recv_into(buffer[, nbytes[, flags]]) -- receive data (into a buffer)\n\
recvfrom(buflen[, flags]) -- receive data and sender\'s address\n\
-recvfrom_buf(buffer[, nbytes, [, flags])\n\
+recvfrom_into(buffer[, nbytes, [, flags])\n\
-- receive data and sender\'s address (into a buffer)\n\
sendall(data[, flags]) -- send all data\n\
send(data[, flags]) -- send data, may not send all of it\n\
@@ -2139,17 +2139,18 @@
#endif /* NO_DUP */
/*
- * This is the guts of the recv() and recv_buf() methods, which reads into a
+ * This is the guts of the recv() and recv_into() methods, which reads into a
* char buffer. If you have any inc/def ref to do to the objects that contain
* the buffer, do it in the caller. This function returns the number of bytes
* succesfully read. If there was an error, it returns -1. Note that it is
* also possible that we return a number of bytes smaller than the request
* bytes.
*/
-static int
+static ssize_t
sock_recv_guts(PySocketSockObject *s, char* cbuf, int len, int flags)
{
- int timeout, outlen = 0;
+ ssize_t outlen = 0;
+ int timeout;
#ifdef __VMS
int remaining, nread;
char *read_buf;
@@ -2225,7 +2226,8 @@
static PyObject *
sock_recv(PySocketSockObject *s, PyObject *args)
{
- int recvlen, flags = 0, outlen;
+ int recvlen, flags = 0;
+ ssize_t outlen;
PyObject *buf;
if (!PyArg_ParseTuple(args, "i|i:recv", &recvlen, &flags))
@@ -2243,7 +2245,7 @@
return NULL;
/* Call the guts */
- outlen = sock_recv_guts(s, PyString_AsString(buf), recvlen, flags);
+ outlen = sock_recv_guts(s, PyString_AS_STRING(buf), recvlen, flags);
if (outlen < 0) {
/* An error occured, release the string and return an
error. */
@@ -2270,19 +2272,20 @@
the remote end is closed and all data is read, return the empty string.");
-/* s.recv_buf(buffer, [nbytes [,flags]]) method */
+/* s.recv_into(buffer, [nbytes [,flags]]) method */
static PyObject*
-sock_recv_buf(PySocketSockObject *s, PyObject *args, PyObject *kwds)
+sock_recv_into(PySocketSockObject *s, PyObject *args, PyObject *kwds)
{
static char *kwlist[] = {"buffer", "nbytes", "flags", 0};
- int recvlen = 0, flags = 0, readlen;
+ int recvlen = 0, flags = 0;
+ ssize_t readlen;
char *buf;
int buflen;
/* Get the buffer's memory */
- if (!PyArg_ParseTupleAndKeywords(args, kwds, "s#|ii:recv", kwlist,
+ if (!PyArg_ParseTupleAndKeywords(args, kwds, "w#|ii:recv", kwlist,
&buf, &buflen, &recvlen, &flags))
return NULL;
assert(buf != 0 && buflen > 0);
@@ -2313,11 +2316,11 @@
/* Return the number of bytes read. Note that we do not do anything
special here in the case that readlen < recvlen. */
- return PyInt_FromLong(readlen);
+ return PyInt_FromSsize_t(readlen);
}
-PyDoc_STRVAR(recv_buf_doc,
-"recv_buf(buffer, [nbytes[, flags]]) -> nbytes_read\n\
+PyDoc_STRVAR(recv_into_doc,
+"recv_into(buffer, [nbytes[, flags]]) -> nbytes_read\n\
\n\
A version of recv() that stores its data into a buffer rather than creating \n\
a new string. Receive up to buffersize bytes from the socket. If buffersize \n\
@@ -2327,7 +2330,7 @@
/*
- * This is the guts of the recv() and recv_buf() methods, which reads into a
+ * This is the guts of the recv() and recv_into() methods, which reads into a
* char buffer. If you have any inc/def ref to do to the objects that contain
* the buffer, do it in the caller. This function returns the number of bytes
* succesfully read. If there was an error, it returns -1. Note that it is
@@ -2337,12 +2340,13 @@
* 'addr' is a return value for the address object. Note that you must decref
* it yourself.
*/
-static int
+static ssize_t
sock_recvfrom_guts(PySocketSockObject *s, char* cbuf, int len, int flags,
PyObject** addr)
{
sock_addr_t addrbuf;
- int n = 0, timeout;
+ int timeout;
+ ssize_t n = 0;
socklen_t addrlen;
*addr = NULL;
@@ -2398,7 +2402,8 @@
PyObject *buf = NULL;
PyObject *addr = NULL;
PyObject *ret = NULL;
- int recvlen, outlen, flags = 0;
+ int recvlen, flags = 0;
+ ssize_t outlen;
if (!PyArg_ParseTuple(args, "i|i:recvfrom", &recvlen, &flags))
return NULL;
@@ -2435,21 +2440,21 @@
Like recv(buffersize, flags) but also return the sender's address info.");
-/* s.recvfrom_buf(buffer[, nbytes [,flags]]) method */
+/* s.recvfrom_into(buffer[, nbytes [,flags]]) method */
static PyObject *
-sock_recvfrom_buf(PySocketSockObject *s, PyObject *args, PyObject* kwds)
+sock_recvfrom_into(PySocketSockObject *s, PyObject *args, PyObject* kwds)
{
static char *kwlist[] = {"buffer", "nbytes", "flags", 0};
- int recvlen = 0, flags = 0, readlen;
+ int recvlen = 0, flags = 0;
+ ssize_t readlen;
char *buf;
int buflen;
PyObject *addr = NULL;
- PyObject *ret = NULL;
- if (!PyArg_ParseTupleAndKeywords(args, kwds, "s#|ii:recvfrom", kwlist,
+ if (!PyArg_ParseTupleAndKeywords(args, kwds, "w#|ii:recvfrom", kwlist,
&buf, &buflen, &recvlen, &flags))
return NULL;
assert(buf != 0 && buflen > 0);
@@ -2467,22 +2472,19 @@
readlen = sock_recvfrom_guts(s, buf, recvlen, flags, &addr);
if (readlen < 0) {
/* Return an error */
- goto finally;
+ Py_XDECREF(addr);
+ return NULL;
}
/* Return the number of bytes read and the address. Note that we do
not do anything special here in the case that readlen < recvlen. */
- ret = Py_BuildValue("lO", readlen, addr);
-
-finally:
- Py_XDECREF(addr);
- return ret;
+ return Py_BuildValue("lN", readlen, addr);
}
-PyDoc_STRVAR(recvfrom_buf_doc,
-"recvfrom_buf(buffer[, nbytes[, flags]]) -> (nbytes, address info)\n\
+PyDoc_STRVAR(recvfrom_into_doc,
+"recvfrom_into(buffer[, nbytes[, flags]]) -> (nbytes, address info)\n\
\n\
-Like recv_buf(buffer[, nbytes[, flags]]) but also return the sender's address info.");
+Like recv_into(buffer[, nbytes[, flags]]) but also return the sender's address info.");
/* s.send(data [,flags]) method */
@@ -2711,12 +2713,12 @@
#endif
{"recv", (PyCFunction)sock_recv, METH_VARARGS,
recv_doc},
- {"recv_buf", (PyCFunction)sock_recv_buf, METH_VARARGS | METH_KEYWORDS,
- recv_buf_doc},
+ {"recv_into", (PyCFunction)sock_recv_into, METH_VARARGS | METH_KEYWORDS,
+ recv_into_doc},
{"recvfrom", (PyCFunction)sock_recvfrom, METH_VARARGS,
recvfrom_doc},
- {"recvfrom_buf", (PyCFunction)sock_recvfrom_buf, METH_VARARGS | METH_KEYWORDS,
- recvfrom_buf_doc},
+ {"recvfrom_into", (PyCFunction)sock_recvfrom_into, METH_VARARGS | METH_KEYWORDS,
+ recvfrom_into_doc},
{"send", (PyCFunction)sock_send, METH_VARARGS,
send_doc},
{"sendall", (PyCFunction)sock_sendall, METH_VARARGS,
Modified: python/branches/p3yk/Objects/abstract.c
==============================================================================
--- python/branches/p3yk/Objects/abstract.c (original)
+++ python/branches/p3yk/Objects/abstract.c Thu Jun 8 17:35:45 2006
@@ -216,7 +216,8 @@
return ret;
}
-int PyObject_AsCharBuffer(PyObject *obj,
+int
+PyObject_AsCharBuffer(PyObject *obj,
const char **buffer,
Py_ssize_t *buffer_len)
{
Modified: python/branches/p3yk/Objects/classobject.c
==============================================================================
--- python/branches/p3yk/Objects/classobject.c (original)
+++ python/branches/p3yk/Objects/classobject.c Thu Jun 8 17:35:45 2006
@@ -2217,9 +2217,17 @@
static int
instancemethod_compare(PyMethodObject *a, PyMethodObject *b)
{
- if (a->im_self != b->im_self)
+ int cmp;
+ cmp = PyObject_Compare(a->im_func, b->im_func);
+ if (cmp)
+ return cmp;
+
+ if (a->im_self == b->im_self)
+ return 0;
+ if (a->im_self == NULL || b->im_self == NULL)
return (a->im_self < b->im_self) ? -1 : 1;
- return PyObject_Compare(a->im_func, b->im_func);
+ else
+ return PyObject_Compare(a->im_self, b->im_self);
}
static PyObject *
@@ -2295,7 +2303,10 @@
y = PyObject_Hash(a->im_func);
if (y == -1)
return -1;
- return x ^ y;
+ x = x ^ y;
+ if (x == -1)
+ x = -2;
+ return x;
}
static int
Modified: python/branches/p3yk/Objects/descrobject.c
==============================================================================
--- python/branches/p3yk/Objects/descrobject.c (original)
+++ python/branches/p3yk/Objects/descrobject.c Thu Jun 8 17:35:45 2006
@@ -901,16 +901,28 @@
static int
wrapper_compare(wrapperobject *a, wrapperobject *b)
{
- if (a->descr == b->descr) {
- if (a->self == b->self)
- return 0;
- else
- return (a->self < b->self) ? -1 : 1;
- }
+ if (a->descr == b->descr)
+ return PyObject_Compare(a->self, b->self);
else
return (a->descr < b->descr) ? -1 : 1;
}
+static long
+wrapper_hash(wrapperobject *wp)
+{
+ int x, y;
+ x = _Py_HashPointer(wp->descr);
+ if (x == -1)
+ return -1;
+ y = PyObject_Hash(wp->self);
+ if (y == -1)
+ return -1;
+ x = x ^ y;
+ if (x == -1)
+ x = -2;
+ return x;
+}
+
static PyObject *
wrapper_repr(wrapperobject *wp)
{
@@ -1008,7 +1020,7 @@
0, /* tp_as_number */
0, /* tp_as_sequence */
0, /* tp_as_mapping */
- 0, /* tp_hash */
+ (hashfunc)wrapper_hash, /* tp_hash */
(ternaryfunc)wrapper_call, /* tp_call */
0, /* tp_str */
PyObject_GenericGetAttr, /* tp_getattro */
Modified: python/branches/p3yk/Objects/exceptions.c
==============================================================================
--- python/branches/p3yk/Objects/exceptions.c (original)
+++ python/branches/p3yk/Objects/exceptions.c Thu Jun 8 17:35:45 2006
@@ -851,7 +851,6 @@
PyTuple_SET_ITEM(tuple, 1, Py_None);
}
- Py_INCREF(repr);
PyTuple_SET_ITEM(tuple, 2, repr);
rtnval = PyString_Format(fmt, tuple);
Modified: python/branches/p3yk/Objects/fileobject.c
==============================================================================
--- python/branches/p3yk/Objects/fileobject.c (original)
+++ python/branches/p3yk/Objects/fileobject.c Thu Jun 8 17:35:45 2006
@@ -1640,6 +1640,20 @@
return (PyObject *)f;
}
+static PyObject *
+file_exit(PyFileObject *f, PyObject *args)
+{
+ PyObject *ret = file_close(f);
+ if (!ret)
+ /* If error occurred, pass through */
+ return NULL;
+ Py_DECREF(ret);
+ /* We cannot return the result of close since a true
+ * value will be interpreted as "yes, swallow the
+ * exception if one was raised inside the with block". */
+ Py_RETURN_NONE;
+}
+
PyDoc_STRVAR(readline_doc,
"readline([size]) -> next line from the file, as a string.\n"
"\n"
@@ -1721,6 +1735,9 @@
PyDoc_STRVAR(enter_doc,
"__enter__() -> self.");
+PyDoc_STRVAR(exit_doc,
+ "__exit__(*excinfo) -> None. Closes the file.");
+
static PyMethodDef file_methods[] = {
{"readline", (PyCFunction)file_readline, METH_VARARGS, readline_doc},
{"read", (PyCFunction)file_read, METH_VARARGS, read_doc},
@@ -1738,7 +1755,7 @@
{"close", (PyCFunction)file_close, METH_NOARGS, close_doc},
{"isatty", (PyCFunction)file_isatty, METH_NOARGS, isatty_doc},
{"__enter__", (PyCFunction)file_self, METH_NOARGS, enter_doc},
- {"__exit__", (PyCFunction)file_close, METH_VARARGS, close_doc},
+ {"__exit__", (PyCFunction)file_exit, METH_VARARGS, exit_doc},
{NULL, NULL} /* sentinel */
};
Modified: python/branches/p3yk/Objects/obmalloc.c
==============================================================================
--- python/branches/p3yk/Objects/obmalloc.c (original)
+++ python/branches/p3yk/Objects/obmalloc.c Thu Jun 8 17:35:45 2006
@@ -491,13 +491,13 @@
#define INITIAL_ARENA_OBJECTS 16
/* Number of arenas allocated that haven't been free()'d. */
-static ulong narenas_currently_allocated = 0;
+static size_t narenas_currently_allocated = 0;
#ifdef PYMALLOC_DEBUG
/* Total number of times malloc() called to allocate an arena. */
-static ulong ntimes_arena_allocated = 0;
+static size_t ntimes_arena_allocated = 0;
/* High water mark (max value ever seen) for narenas_currently_allocated. */
-static ulong narenas_highwater = 0;
+static size_t narenas_highwater = 0;
#endif
/* Allocate a new arena. If we run out of memory, return NULL. Else
@@ -1220,39 +1220,45 @@
#define DEADBYTE 0xDB /* dead (newly freed) memory */
#define FORBIDDENBYTE 0xFB /* untouchable bytes at each end of a block */
-static ulong serialno = 0; /* incremented on each debug {m,re}alloc */
+static size_t serialno = 0; /* incremented on each debug {m,re}alloc */
/* serialno is always incremented via calling this routine. The point is
- to supply a single place to set a breakpoint.
-*/
+ * to supply a single place to set a breakpoint.
+ */
static void
bumpserialno(void)
{
++serialno;
}
+#define SST SIZEOF_SIZE_T
-/* Read 4 bytes at p as a big-endian ulong. */
-static ulong
-read4(const void *p)
+/* Read sizeof(size_t) bytes at p as a big-endian size_t. */
+static size_t
+read_size_t(const void *p)
{
const uchar *q = (const uchar *)p;
- return ((ulong)q[0] << 24) |
- ((ulong)q[1] << 16) |
- ((ulong)q[2] << 8) |
- (ulong)q[3];
+ size_t result = *q++;
+ int i;
+
+ for (i = SST; --i > 0; ++q)
+ result = (result << 8) | *q;
+ return result;
}
-/* Write the 4 least-significant bytes of n as a big-endian unsigned int,
- MSB at address p, LSB at p+3. */
+/* Write n as a big-endian size_t, MSB at address p, LSB at
+ * p + sizeof(size_t) - 1.
+ */
static void
-write4(void *p, ulong n)
+write_size_t(void *p, size_t n)
{
- uchar *q = (uchar *)p;
- q[0] = (uchar)((n >> 24) & 0xff);
- q[1] = (uchar)((n >> 16) & 0xff);
- q[2] = (uchar)((n >> 8) & 0xff);
- q[3] = (uchar)( n & 0xff);
+ uchar *q = (uchar *)p + SST - 1;
+ int i;
+
+ for (i = SST; --i >= 0; --q) {
+ *q = (uchar)(n & 0xff);
+ n >>= 8;
+ }
}
#ifdef Py_DEBUG
@@ -1280,25 +1286,25 @@
#endif /* Py_DEBUG */
-/* The debug malloc asks for 16 extra bytes and fills them with useful stuff,
- here calling the underlying malloc's result p:
+/* Let S = sizeof(size_t). The debug malloc asks for 4*S extra bytes and
+ fills them with useful stuff, here calling the underlying malloc's result p:
-p[0:4]
- Number of bytes originally asked for. 4-byte unsigned integer,
- big-endian (easier to read in a memory dump).
-p[4:8]
+p[0: S]
+ Number of bytes originally asked for. This is a size_t, big-endian (easier
+ to read in a memory dump).
+p[S: 2*S]
Copies of FORBIDDENBYTE. Used to catch under- writes and reads.
-p[8:8+n]
+p[2*S: 2*S+n]
The requested memory, filled with copies of CLEANBYTE.
Used to catch reference to uninitialized memory.
- &p[8] is returned. Note that this is 8-byte aligned if pymalloc
+ &p[2*S] is returned. Note that this is 8-byte aligned if pymalloc
handled the request itself.
-p[8+n:8+n+4]
+p[2*S+n: 2*S+n+S]
Copies of FORBIDDENBYTE. Used to catch over- writes and reads.
-p[8+n+4:8+n+8]
+p[2*S+n+S: 2*S+n+2*S]
A serial number, incremented by 1 on each call to _PyObject_DebugMalloc
and _PyObject_DebugRealloc.
- 4-byte unsigned integer, big-endian.
+ This is a big-endian size_t.
If "bad memory" is detected later, the serial number gives an
excellent way to set a breakpoint on the next run, to capture the
instant at which this block was passed out.
@@ -1308,41 +1314,33 @@
_PyObject_DebugMalloc(size_t nbytes)
{
uchar *p; /* base address of malloc'ed block */
- uchar *tail; /* p + 8 + nbytes == pointer to tail pad bytes */
- size_t total; /* nbytes + 16 */
+ uchar *tail; /* p + 2*SST + nbytes == pointer to tail pad bytes */
+ size_t total; /* nbytes + 4*SST */
bumpserialno();
- total = nbytes + 16;
-#if SIZEOF_SIZE_T < 8
- /* XXX do this check only on 32-bit machines */
- if (total < nbytes || (total >> 31) > 1) {
- /* overflow, or we can't represent it in 4 bytes */
- /* Obscure: can't do (total >> 32) != 0 instead, because
- C doesn't define what happens for a right-shift of 32
- when size_t is a 32-bit type. At least C guarantees
- size_t is an unsigned type. */
+ total = nbytes + 4*SST;
+ if (total < nbytes)
+ /* overflow: can't represent total as a size_t */
return NULL;
- }
-#endif
p = (uchar *)PyObject_Malloc(total);
if (p == NULL)
return NULL;
- write4(p, (ulong)nbytes);
- p[4] = p[5] = p[6] = p[7] = FORBIDDENBYTE;
+ write_size_t(p, nbytes);
+ memset(p + SST, FORBIDDENBYTE, SST);
if (nbytes > 0)
- memset(p+8, CLEANBYTE, nbytes);
+ memset(p + 2*SST, CLEANBYTE, nbytes);
- tail = p + 8 + nbytes;
- tail[0] = tail[1] = tail[2] = tail[3] = FORBIDDENBYTE;
- write4(tail + 4, serialno);
+ tail = p + 2*SST + nbytes;
+ memset(tail, FORBIDDENBYTE, SST);
+ write_size_t(tail + SST, serialno);
- return p+8;
+ return p + 2*SST;
}
-/* The debug free first checks the 8 bytes on each end for sanity (in
+/* The debug free first checks the 2*SST bytes on each end for sanity (in
particular, that the FORBIDDENBYTEs are still intact).
Then fills the original bytes with DEADBYTE.
Then calls the underlying free.
@@ -1350,16 +1348,16 @@
void
_PyObject_DebugFree(void *p)
{
- uchar *q = (uchar *)p;
+ uchar *q = (uchar *)p - 2*SST; /* address returned from malloc */
size_t nbytes;
if (p == NULL)
return;
_PyObject_DebugCheckAddress(p);
- nbytes = read4(q-8);
+ nbytes = read_size_t(q);
if (nbytes > 0)
memset(q, DEADBYTE, nbytes);
- PyObject_Free(q-8);
+ PyObject_Free(q);
}
void *
@@ -1367,20 +1365,20 @@
{
uchar *q = (uchar *)p;
uchar *tail;
- size_t total; /* nbytes + 16 */
+ size_t total; /* nbytes + 4*SST */
size_t original_nbytes;
+ int i;
if (p == NULL)
return _PyObject_DebugMalloc(nbytes);
_PyObject_DebugCheckAddress(p);
bumpserialno();
- original_nbytes = read4(q-8);
- total = nbytes + 16;
- if (total < nbytes || (total >> 31) > 1) {
- /* overflow, or we can't represent it in 4 bytes */
+ original_nbytes = read_size_t(q - 2*SST);
+ total = nbytes + 4*SST;
+ if (total < nbytes)
+ /* overflow: can't represent total as a size_t */
return NULL;
- }
if (nbytes < original_nbytes) {
/* shrinking: mark old extra memory dead */
@@ -1388,19 +1386,17 @@
}
/* Resize and add decorations. */
- q = (uchar *)PyObject_Realloc(q-8, total);
+ q = (uchar *)PyObject_Realloc(q - 2*SST, total);
if (q == NULL)
return NULL;
- write4(q, (ulong)nbytes);
- assert(q[4] == FORBIDDENBYTE &&
- q[5] == FORBIDDENBYTE &&
- q[6] == FORBIDDENBYTE &&
- q[7] == FORBIDDENBYTE);
- q += 8;
+ write_size_t(q, nbytes);
+ for (i = 0; i < SST; ++i)
+ assert(q[SST + i] == FORBIDDENBYTE);
+ q += 2*SST;
tail = q + nbytes;
- tail[0] = tail[1] = tail[2] = tail[3] = FORBIDDENBYTE;
- write4(tail + 4, serialno);
+ memset(tail, FORBIDDENBYTE, SST);
+ write_size_t(tail + SST, serialno);
if (nbytes > original_nbytes) {
/* growing: mark new extra memory clean */
@@ -1420,7 +1416,7 @@
{
const uchar *q = (const uchar *)p;
char *msg;
- ulong nbytes;
+ size_t nbytes;
const uchar *tail;
int i;
@@ -1433,16 +1429,16 @@
* corruption, the number-of-bytes field may be nuts, and checking
* the tail could lead to a segfault then.
*/
- for (i = 4; i >= 1; --i) {
+ for (i = SST; i >= 1; --i) {
if (*(q-i) != FORBIDDENBYTE) {
msg = "bad leading pad byte";
goto error;
}
}
- nbytes = read4(q-8);
+ nbytes = read_size_t(q - 2*SST);
tail = q + nbytes;
- for (i = 0; i < 4; ++i) {
+ for (i = 0; i < SST; ++i) {
if (tail[i] != FORBIDDENBYTE) {
msg = "bad trailing pad byte";
goto error;
@@ -1462,28 +1458,33 @@
{
const uchar *q = (const uchar *)p;
const uchar *tail;
- ulong nbytes, serial;
+ size_t nbytes, serial;
int i;
+ int ok;
fprintf(stderr, "Debug memory block at address p=%p:\n", p);
if (p == NULL)
return;
- nbytes = read4(q-8);
- fprintf(stderr, " %lu bytes originally requested\n", nbytes);
+ nbytes = read_size_t(q - 2*SST);
+ fprintf(stderr, " %" PY_FORMAT_SIZE_T "u bytes originally "
+ "requested\n", nbytes);
/* In case this is nuts, check the leading pad bytes first. */
- fputs(" The 4 pad bytes at p-4 are ", stderr);
- if (*(q-4) == FORBIDDENBYTE &&
- *(q-3) == FORBIDDENBYTE &&
- *(q-2) == FORBIDDENBYTE &&
- *(q-1) == FORBIDDENBYTE) {
- fputs("FORBIDDENBYTE, as expected.\n", stderr);
+ fprintf(stderr, " The %d pad bytes at p-%d are ", SST, SST);
+ ok = 1;
+ for (i = 1; i <= SST; ++i) {
+ if (*(q-i) != FORBIDDENBYTE) {
+ ok = 0;
+ break;
+ }
}
+ if (ok)
+ fputs("FORBIDDENBYTE, as expected.\n", stderr);
else {
fprintf(stderr, "not all FORBIDDENBYTE (0x%02x):\n",
FORBIDDENBYTE);
- for (i = 4; i >= 1; --i) {
+ for (i = SST; i >= 1; --i) {
const uchar byte = *(q-i);
fprintf(stderr, " at p-%d: 0x%02x", i, byte);
if (byte != FORBIDDENBYTE)
@@ -1498,17 +1499,20 @@
}
tail = q + nbytes;
- fprintf(stderr, " The 4 pad bytes at tail=%p are ", tail);
- if (tail[0] == FORBIDDENBYTE &&
- tail[1] == FORBIDDENBYTE &&
- tail[2] == FORBIDDENBYTE &&
- tail[3] == FORBIDDENBYTE) {
- fputs("FORBIDDENBYTE, as expected.\n", stderr);
+ fprintf(stderr, " The %d pad bytes at tail=%p are ", SST, tail);
+ ok = 1;
+ for (i = 0; i < SST; ++i) {
+ if (tail[i] != FORBIDDENBYTE) {
+ ok = 0;
+ break;
+ }
}
+ if (ok)
+ fputs("FORBIDDENBYTE, as expected.\n", stderr);
else {
fprintf(stderr, "not all FORBIDDENBYTE (0x%02x):\n",
FORBIDDENBYTE);
- for (i = 0; i < 4; ++i) {
+ for (i = 0; i < SST; ++i) {
const uchar byte = tail[i];
fprintf(stderr, " at tail+%d: 0x%02x",
i, byte);
@@ -1518,12 +1522,12 @@
}
}
- serial = read4(tail+4);
- fprintf(stderr, " The block was made by call #%lu to "
- "debug malloc/realloc.\n", serial);
+ serial = read_size_t(tail + SST);
+ fprintf(stderr, " The block was made by call #%" PY_FORMAT_SIZE_T
+ "u to debug malloc/realloc.\n", serial);
if (nbytes > 0) {
- int i = 0;
+ i = 0;
fputs(" Data at p:", stderr);
/* print up to 8 bytes at the start */
while (q < tail && i < 8) {
@@ -1546,12 +1550,12 @@
}
}
-static ulong
-printone(const char* msg, ulong value)
+static size_t
+printone(const char* msg, size_t value)
{
int i, k;
char buf[100];
- ulong origvalue = value;
+ size_t origvalue = value;
fputs(msg, stderr);
for (i = (int)strlen(msg); i < 35; ++i)
@@ -1564,8 +1568,8 @@
buf[i--] = '\n';
k = 3;
do {
- ulong nextvalue = value / 10UL;
- uint digit = value - nextvalue * 10UL;
+ size_t nextvalue = value / 10;
+ uint digit = (uint)(value - nextvalue * 10);
value = nextvalue;
buf[i--] = (char)(digit + '0');
--k;
@@ -1592,28 +1596,28 @@
uint i;
const uint numclasses = SMALL_REQUEST_THRESHOLD >> ALIGNMENT_SHIFT;
/* # of pools, allocated blocks, and free blocks per class index */
- ulong numpools[SMALL_REQUEST_THRESHOLD >> ALIGNMENT_SHIFT];
- ulong numblocks[SMALL_REQUEST_THRESHOLD >> ALIGNMENT_SHIFT];
- ulong numfreeblocks[SMALL_REQUEST_THRESHOLD >> ALIGNMENT_SHIFT];
+ size_t numpools[SMALL_REQUEST_THRESHOLD >> ALIGNMENT_SHIFT];
+ size_t numblocks[SMALL_REQUEST_THRESHOLD >> ALIGNMENT_SHIFT];
+ size_t numfreeblocks[SMALL_REQUEST_THRESHOLD >> ALIGNMENT_SHIFT];
/* total # of allocated bytes in used and full pools */
- ulong allocated_bytes = 0;
+ size_t allocated_bytes = 0;
/* total # of available bytes in used pools */
- ulong available_bytes = 0;
+ size_t available_bytes = 0;
/* # of free pools + pools not yet carved out of current arena */
uint numfreepools = 0;
/* # of bytes for arena alignment padding */
- ulong arena_alignment = 0;
+ size_t arena_alignment = 0;
/* # of bytes in used and full pools used for pool_headers */
- ulong pool_header_bytes = 0;
+ size_t pool_header_bytes = 0;
/* # of bytes in used and full pools wasted due to quantization,
* i.e. the necessarily leftover space at the ends of used and
* full pools.
*/
- ulong quantization = 0;
+ size_t quantization = 0;
/* # of arenas actually allocated. */
- ulong narenas = 0;
+ size_t narenas = 0;
/* running total -- should equal narenas * ARENA_SIZE */
- ulong total;
+ size_t total;
char buf[128];
fprintf(stderr, "Small block threshold = %d, in %u size classes.\n",
@@ -1678,15 +1682,18 @@
stderr);
for (i = 0; i < numclasses; ++i) {
- ulong p = numpools[i];
- ulong b = numblocks[i];
- ulong f = numfreeblocks[i];
+ size_t p = numpools[i];
+ size_t b = numblocks[i];
+ size_t f = numfreeblocks[i];
uint size = INDEX2SIZE(i);
if (p == 0) {
assert(b == 0 && f == 0);
continue;
}
- fprintf(stderr, "%5u %6u %11lu %15lu %13lu\n",
+ fprintf(stderr, "%5u %6u "
+ "%11" PY_FORMAT_SIZE_T "u "
+ "%15" PY_FORMAT_SIZE_T "u "
+ "%13" PY_FORMAT_SIZE_T "u\n",
i, size, p, b, f);
allocated_bytes += b * size;
available_bytes += f * size;
@@ -1702,7 +1709,8 @@
(void)printone("# arenas allocated current", narenas);
PyOS_snprintf(buf, sizeof(buf),
- "%lu arenas * %d bytes/arena", narenas, ARENA_SIZE);
+ "%" PY_FORMAT_SIZE_T "u arenas * %d bytes/arena",
+ narenas, ARENA_SIZE);
(void)printone(buf, narenas * ARENA_SIZE);
fputc('\n', stderr);
@@ -1712,7 +1720,7 @@
PyOS_snprintf(buf, sizeof(buf),
"%u unused pools * %d bytes", numfreepools, POOL_SIZE);
- total += printone(buf, (ulong)numfreepools * POOL_SIZE);
+ total += printone(buf, (size_t)numfreepools * POOL_SIZE);
total += printone("# bytes lost to pool headers", pool_header_bytes);
total += printone("# bytes lost to quantization", quantization);
Modified: python/branches/p3yk/Objects/unicodeobject.c
==============================================================================
--- python/branches/p3yk/Objects/unicodeobject.c (original)
+++ python/branches/p3yk/Objects/unicodeobject.c Thu Jun 8 17:35:45 2006
@@ -3057,6 +3057,221 @@
return NULL;
}
+/* Charmap encoding: the lookup table */
+
+struct encoding_map{
+ PyObject_HEAD
+ unsigned char level1[32];
+ int count2, count3;
+ unsigned char level23[1];
+};
+
+static PyObject*
+encoding_map_size(PyObject *obj, PyObject* args)
+{
+ struct encoding_map *map = (struct encoding_map*)obj;
+ return PyInt_FromLong(sizeof(*map) - 1 + 16*map->count2 +
+ 128*map->count3);
+}
+
+static PyMethodDef encoding_map_methods[] = {
+ {"size", encoding_map_size, METH_NOARGS,
+ PyDoc_STR("Return the size (in bytes) of this object") },
+ { 0 }
+};
+
+static void
+encoding_map_dealloc(PyObject* o)
+{
+ PyObject_FREE(o);
+}
+
+static PyTypeObject EncodingMapType = {
+ PyObject_HEAD_INIT(NULL)
+ 0, /*ob_size*/
+ "EncodingMap", /*tp_name*/
+ sizeof(struct encoding_map), /*tp_basicsize*/
+ 0, /*tp_itemsize*/
+ /* methods */
+ encoding_map_dealloc, /*tp_dealloc*/
+ 0, /*tp_print*/
+ 0, /*tp_getattr*/
+ 0, /*tp_setattr*/
+ 0, /*tp_compare*/
+ 0, /*tp_repr*/
+ 0, /*tp_as_number*/
+ 0, /*tp_as_sequence*/
+ 0, /*tp_as_mapping*/
+ 0, /*tp_hash*/
+ 0, /*tp_call*/
+ 0, /*tp_str*/
+ 0, /*tp_getattro*/
+ 0, /*tp_setattro*/
+ 0, /*tp_as_buffer*/
+ Py_TPFLAGS_DEFAULT, /*tp_flags*/
+ 0, /*tp_doc*/
+ 0, /*tp_traverse*/
+ 0, /*tp_clear*/
+ 0, /*tp_richcompare*/
+ 0, /*tp_weaklistoffset*/
+ 0, /*tp_iter*/
+ 0, /*tp_iternext*/
+ encoding_map_methods, /*tp_methods*/
+ 0, /*tp_members*/
+ 0, /*tp_getset*/
+ 0, /*tp_base*/
+ 0, /*tp_dict*/
+ 0, /*tp_descr_get*/
+ 0, /*tp_descr_set*/
+ 0, /*tp_dictoffset*/
+ 0, /*tp_init*/
+ 0, /*tp_alloc*/
+ 0, /*tp_new*/
+ 0, /*tp_free*/
+ 0, /*tp_is_gc*/
+};
+
+PyObject*
+PyUnicode_BuildEncodingMap(PyObject* string)
+{
+ Py_UNICODE *decode;
+ PyObject *result;
+ struct encoding_map *mresult;
+ int i;
+ int need_dict = 0;
+ unsigned char level1[32];
+ unsigned char level2[512];
+ unsigned char *mlevel1, *mlevel2, *mlevel3;
+ int count2 = 0, count3 = 0;
+
+ if (!PyUnicode_Check(string) || PyUnicode_GetSize(string) != 256) {
+ PyErr_BadArgument();
+ return NULL;
+ }
+ decode = PyUnicode_AS_UNICODE(string);
+ memset(level1, 0xFF, sizeof level1);
+ memset(level2, 0xFF, sizeof level2);
+
+ /* If there isn't a one-to-one mapping of NULL to \0,
+ or if there are non-BMP characters, we need to use
+ a mapping dictionary. */
+ if (decode[0] != 0)
+ need_dict = 1;
+ for (i = 1; i < 256; i++) {
+ int l1, l2;
+ if (decode[i] == 0
+ #ifdef Py_UNICODE_WIDE
+ || decode[i] > 0xFFFF
+ #endif
+ ) {
+ need_dict = 1;
+ break;
+ }
+ if (decode[i] == 0xFFFE)
+ /* unmapped character */
+ continue;
+ l1 = decode[i] >> 11;
+ l2 = decode[i] >> 7;
+ if (level1[l1] == 0xFF)
+ level1[l1] = count2++;
+ if (level2[l2] == 0xFF)
+ level2[l2] = count3++;
+ }
+
+ if (count2 >= 0xFF || count3 >= 0xFF)
+ need_dict = 1;
+
+ if (need_dict) {
+ PyObject *result = PyDict_New();
+ PyObject *key, *value;
+ if (!result)
+ return NULL;
+ for (i = 0; i < 256; i++) {
+ key = value = NULL;
+ key = PyInt_FromLong(decode[i]);
+ value = PyInt_FromLong(i);
+ if (!key || !value)
+ goto failed1;
+ if (PyDict_SetItem(result, key, value) == -1)
+ goto failed1;
+ Py_DECREF(key);
+ Py_DECREF(value);
+ }
+ return result;
+ failed1:
+ Py_XDECREF(key);
+ Py_XDECREF(value);
+ Py_DECREF(result);
+ return NULL;
+ }
+
+ /* Create a three-level trie */
+ result = PyObject_MALLOC(sizeof(struct encoding_map) +
+ 16*count2 + 128*count3 - 1);
+ if (!result)
+ return PyErr_NoMemory();
+ PyObject_Init(result, &EncodingMapType);
+ mresult = (struct encoding_map*)result;
+ mresult->count2 = count2;
+ mresult->count3 = count3;
+ mlevel1 = mresult->level1;
+ mlevel2 = mresult->level23;
+ mlevel3 = mresult->level23 + 16*count2;
+ memcpy(mlevel1, level1, 32);
+ memset(mlevel2, 0xFF, 16*count2);
+ memset(mlevel3, 0, 128*count3);
+ count3 = 0;
+ for (i = 1; i < 256; i++) {
+ int o1, o2, o3, i2, i3;
+ if (decode[i] == 0xFFFE)
+ /* unmapped character */
+ continue;
+ o1 = decode[i]>>11;
+ o2 = (decode[i]>>7) & 0xF;
+ i2 = 16*mlevel1[o1] + o2;
+ if (mlevel2[i2] == 0xFF)
+ mlevel2[i2] = count3++;
+ o3 = decode[i] & 0x7F;
+ i3 = 128*mlevel2[i2] + o3;
+ mlevel3[i3] = i;
+ }
+ return result;
+}
+
+static int
+encoding_map_lookup(Py_UNICODE c, PyObject *mapping)
+{
+ struct encoding_map *map = (struct encoding_map*)mapping;
+ int l1 = c>>11;
+ int l2 = (c>>7) & 0xF;
+ int l3 = c & 0x7F;
+ int i;
+
+#ifdef Py_UNICODE_WIDE
+ if (c > 0xFFFF) {
+ return -1;
+ }
+#endif
+ if (c == 0)
+ return 0;
+ /* level 1*/
+ i = map->level1[l1];
+ if (i == 0xFF) {
+ return -1;
+ }
+ /* level 2*/
+ i = map->level23[16*i+l2];
+ if (i == 0xFF) {
+ return -1;
+ }
+ /* level 3 */
+ i = map->level23[16*map->count2 + 128*i + l3];
+ if (i == 0) {
+ return -1;
+ }
+ return i;
+}
+
/* Lookup the character ch in the mapping. If the character
can't be found, Py_None is returned (or NULL, if another
error occurred). */
@@ -3102,6 +3317,22 @@
}
}
+static int
+charmapencode_resize(PyObject **outobj, Py_ssize_t *outpos, Py_ssize_t requiredsize)
+{
+ Py_ssize_t outsize = PyString_GET_SIZE(*outobj);
+ /* exponentially overallocate to minimize reallocations */
+ if (requiredsize < 2*outsize)
+ requiredsize = 2*outsize;
+ if (_PyString_Resize(outobj, requiredsize)) {
+ return 0;
+ }
+ return 1;
+}
+
+typedef enum charmapencode_result {
+ enc_SUCCESS, enc_FAILED, enc_EXCEPTION
+}charmapencode_result;
/* lookup the character, put the result in the output string and adjust
various state variables. Reallocate the output string if not enough
space is available. Return a new reference to the object that
@@ -3109,51 +3340,59 @@
(in which case no character was written) or NULL, if a
reallocation error occurred. The caller must decref the result */
static
-PyObject *charmapencode_output(Py_UNICODE c, PyObject *mapping,
+charmapencode_result charmapencode_output(Py_UNICODE c, PyObject *mapping,
PyObject **outobj, Py_ssize_t *outpos)
{
- PyObject *rep = charmapencode_lookup(c, mapping);
+ PyObject *rep;
+ char *outstart;
+ Py_ssize_t outsize = PyString_GET_SIZE(*outobj);
+
+ if (mapping->ob_type == &EncodingMapType) {
+ int res = encoding_map_lookup(c, mapping);
+ Py_ssize_t requiredsize = *outpos+1;
+ if (res == -1)
+ return enc_FAILED;
+ if (outsize<requiredsize)
+ if (!charmapencode_resize(outobj, outpos, requiredsize))
+ return enc_EXCEPTION;
+ outstart = PyString_AS_STRING(*outobj);
+ outstart[(*outpos)++] = (char)res;
+ return enc_SUCCESS;
+ }
+ rep = charmapencode_lookup(c, mapping);
if (rep==NULL)
- return NULL;
- else if (rep==Py_None)
- return rep;
- else {
- char *outstart = PyString_AS_STRING(*outobj);
- Py_ssize_t outsize = PyString_GET_SIZE(*outobj);
+ return enc_EXCEPTION;
+ else if (rep==Py_None) {
+ Py_DECREF(rep);
+ return enc_FAILED;
+ } else {
if (PyInt_Check(rep)) {
Py_ssize_t requiredsize = *outpos+1;
- if (outsize<requiredsize) {
- /* exponentially overallocate to minimize reallocations */
- if (requiredsize < 2*outsize)
- requiredsize = 2*outsize;
- if (_PyString_Resize(outobj, requiredsize)) {
+ if (outsize<requiredsize)
+ if (!charmapencode_resize(outobj, outpos, requiredsize)) {
Py_DECREF(rep);
- return NULL;
+ return enc_EXCEPTION;
}
- outstart = PyString_AS_STRING(*outobj);
- }
+ outstart = PyString_AS_STRING(*outobj);
outstart[(*outpos)++] = (char)PyInt_AS_LONG(rep);
}
else {
const char *repchars = PyString_AS_STRING(rep);
Py_ssize_t repsize = PyString_GET_SIZE(rep);
Py_ssize_t requiredsize = *outpos+repsize;
- if (outsize<requiredsize) {
- /* exponentially overallocate to minimize reallocations */
- if (requiredsize < 2*outsize)
- requiredsize = 2*outsize;
- if (_PyString_Resize(outobj, requiredsize)) {
+ if (outsize<requiredsize)
+ if (!charmapencode_resize(outobj, outpos, requiredsize)) {
Py_DECREF(rep);
- return NULL;
+ return enc_EXCEPTION;
}
- outstart = PyString_AS_STRING(*outobj);
- }
+ outstart = PyString_AS_STRING(*outobj);
memcpy(outstart + *outpos, repchars, repsize);
*outpos += repsize;
}
}
- return rep;
+ Py_DECREF(rep);
+ return enc_SUCCESS;
}
/* handle an error in PyUnicode_EncodeCharmap
@@ -3175,18 +3414,27 @@
Py_ssize_t collpos;
char *encoding = "charmap";
char *reason = "character maps to <undefined>";
+ charmapencode_result x;
- PyObject *x;
/* find all unencodable characters */
while (collendpos < size) {
- x = charmapencode_lookup(p[collendpos], mapping);
- if (x==NULL)
+ PyObject *rep;
+ if (mapping->ob_type == &EncodingMapType) {
+ int res = encoding_map_lookup(p[collendpos], mapping);
+ if (res != -1)
+ break;
+ ++collendpos;
+ continue;
+ }
+
+ rep = charmapencode_lookup(p[collendpos], mapping);
+ if (rep==NULL)
return -1;
- else if (x!=Py_None) {
- Py_DECREF(x);
+ else if (rep!=Py_None) {
+ Py_DECREF(rep);
break;
}
- Py_DECREF(x);
+ Py_DECREF(rep);
++collendpos;
}
/* cache callback name lookup
@@ -3210,15 +3458,13 @@
case 2: /* replace */
for (collpos = collstartpos; collpos<collendpos; ++collpos) {
x = charmapencode_output('?', mapping, res, respos);
- if (x==NULL) {
+ if (x==enc_EXCEPTION) {
return -1;
}
- else if (x==Py_None) {
- Py_DECREF(x);
+ else if (x==enc_FAILED) {
raise_encode_exception(exceptionObject, encoding, p, size, collstartpos, collendpos, reason);
return -1;
}
- Py_DECREF(x);
}
/* fall through */
case 3: /* ignore */
@@ -3232,14 +3478,12 @@
sprintf(buffer, "&#%d;", (int)p[collpos]);
for (cp = buffer; *cp; ++cp) {
x = charmapencode_output(*cp, mapping, res, respos);
- if (x==NULL)
+ if (x==enc_EXCEPTION)
return -1;
- else if (x==Py_None) {
- Py_DECREF(x);
+ else if (x==enc_FAILED) {
raise_encode_exception(exceptionObject, encoding, p, size, collstartpos, collendpos, reason);
return -1;
}
- Py_DECREF(x);
}
}
*inpos = collendpos;
@@ -3254,17 +3498,14 @@
repsize = PyUnicode_GET_SIZE(repunicode);
for (uni2 = PyUnicode_AS_UNICODE(repunicode); repsize-->0; ++uni2) {
x = charmapencode_output(*uni2, mapping, res, respos);
- if (x==NULL) {
- Py_DECREF(repunicode);
+ if (x==enc_EXCEPTION) {
return -1;
}
- else if (x==Py_None) {
+ else if (x==enc_FAILED) {
Py_DECREF(repunicode);
- Py_DECREF(x);
raise_encode_exception(exceptionObject, encoding, p, size, collstartpos, collendpos, reason);
return -1;
}
- Py_DECREF(x);
}
*inpos = newpos;
Py_DECREF(repunicode);
@@ -3304,22 +3545,20 @@
while (inpos<size) {
/* try to encode it */
- PyObject *x = charmapencode_output(p[inpos], mapping, &res, &respos);
- if (x==NULL) /* error */
+ charmapencode_result x = charmapencode_output(p[inpos], mapping, &res, &respos);
+ if (x==enc_EXCEPTION) /* error */
goto onError;
- if (x==Py_None) { /* unencodable character */
+ if (x==enc_FAILED) { /* unencodable character */
if (charmap_encoding_error(p, size, &inpos, mapping,
&exc,
&known_errorHandler, &errorHandler, errors,
&res, &respos)) {
- Py_DECREF(x);
goto onError;
}
}
else
/* done with this character => adjust input position */
++inpos;
- Py_DECREF(x);
}
/* Resize if we allocated to much */
Modified: python/branches/p3yk/PC/_subprocess.c
==============================================================================
--- python/branches/p3yk/PC/_subprocess.c (original)
+++ python/branches/p3yk/PC/_subprocess.c Thu Jun 8 17:35:45 2006
@@ -250,19 +250,23 @@
getint(PyObject* obj, char* name)
{
PyObject* value;
+ int ret;
value = PyObject_GetAttrString(obj, name);
if (! value) {
PyErr_Clear(); /* FIXME: propagate error? */
return 0;
}
- return (int) PyInt_AsLong(value);
+ ret = (int) PyInt_AsLong(value);
+ Py_DECREF(value);
+ return ret;
}
static HANDLE
gethandle(PyObject* obj, char* name)
{
sp_handle_object* value;
+ HANDLE ret;
value = (sp_handle_object*) PyObject_GetAttrString(obj, name);
if (! value) {
@@ -270,8 +274,11 @@
return NULL;
}
if (value->ob_type != &sp_handle_type)
- return NULL;
- return value->handle;
+ ret = NULL;
+ else
+ ret = value->handle;
+ Py_DECREF(value);
+ return ret;
}
static PyObject*
Modified: python/branches/p3yk/PC/py.ico
==============================================================================
Binary files. No diff available.
Modified: python/branches/p3yk/PC/pyc.ico
==============================================================================
Binary files. No diff available.
Modified: python/branches/p3yk/PC/pycon.ico
==============================================================================
Binary files. No diff available.
Modified: python/branches/p3yk/Parser/node.c
==============================================================================
--- python/branches/p3yk/Parser/node.c (original)
+++ python/branches/p3yk/Parser/node.c Thu Jun 8 17:35:45 2006
@@ -65,7 +65,7 @@
* reported that, with this scheme, 89% of PyObject_REALLOC calls in
* PyNode_AddChild passed 1 for the size, and 9% passed 4. So this usually
* wastes very little memory, but is very effective at sidestepping
- * platform-realloc disasters on vulnernable platforms.
+ * platform-realloc disasters on vulnerable platforms.
*
* Note that this would be straightforward if a node stored its current
* capacity. The code is tricky to avoid that.
Modified: python/branches/p3yk/Python/compile.c
==============================================================================
--- python/branches/p3yk/Python/compile.c (original)
+++ python/branches/p3yk/Python/compile.c Thu Jun 8 17:35:45 2006
@@ -2141,7 +2141,7 @@
compiler_if(struct compiler *c, stmt_ty s)
{
basicblock *end, *next;
-
+ int constant;
assert(s->kind == If_kind);
end = compiler_new_block(c);
if (end == NULL)
@@ -2149,15 +2149,27 @@
next = compiler_new_block(c);
if (next == NULL)
return 0;
- VISIT(c, expr, s->v.If.test);
- ADDOP_JREL(c, JUMP_IF_FALSE, next);
- ADDOP(c, POP_TOP);
- VISIT_SEQ(c, stmt, s->v.If.body);
- ADDOP_JREL(c, JUMP_FORWARD, end);
- compiler_use_next_block(c, next);
- ADDOP(c, POP_TOP);
- if (s->v.If.orelse)
- VISIT_SEQ(c, stmt, s->v.If.orelse);
+
+ constant = expr_constant(s->v.If.test);
+ /* constant = 0: "if 0"
+ * constant = 1: "if 1", "if 2", ...
+ * constant = -1: rest */
+ if (constant == 0) {
+ if (s->v.If.orelse)
+ VISIT_SEQ(c, stmt, s->v.If.orelse);
+ } else if (constant == 1) {
+ VISIT_SEQ(c, stmt, s->v.If.body);
+ } else {
+ VISIT(c, expr, s->v.If.test);
+ ADDOP_JREL(c, JUMP_IF_FALSE, next);
+ ADDOP(c, POP_TOP);
+ VISIT_SEQ(c, stmt, s->v.If.body);
+ ADDOP_JREL(c, JUMP_FORWARD, end);
+ compiler_use_next_block(c, next);
+ ADDOP(c, POP_TOP);
+ if (s->v.If.orelse)
+ VISIT_SEQ(c, stmt, s->v.If.orelse);
+ }
compiler_use_next_block(c, end);
return 1;
}
@@ -2623,10 +2635,6 @@
if (c->u->u_ste->ste_type != FunctionBlock)
return compiler_error(c, "'return' outside function");
if (s->v.Return.value) {
- if (c->u->u_ste->ste_generator) {
- return compiler_error(c,
- "'return' with argument inside generator");
- }
VISIT(c, expr, s->v.Return.value);
}
else
@@ -3334,6 +3342,13 @@
return PyObject_IsTrue(e->v.Num.n);
case Str_kind:
return PyObject_IsTrue(e->v.Str.s);
+ case Name_kind:
+ /* __debug__ is not assignable, so we can optimize
+ * it away in if and while statements */
+ if (strcmp(PyString_AS_STRING(e->v.Name.id),
+ "__debug__") == 0)
+ return ! Py_OptimizeFlag;
+ /* fall through */
default:
return -1;
}
Modified: python/branches/p3yk/Python/symtable.c
==============================================================================
--- python/branches/p3yk/Python/symtable.c (original)
+++ python/branches/p3yk/Python/symtable.c Thu Jun 8 17:35:45 2006
@@ -13,6 +13,8 @@
#define IMPORT_STAR_WARNING "import * only allowed at module level"
+#define RETURN_VAL_IN_GENERATOR \
+ "'return' with argument inside generator"
/* XXX(nnorwitz): change name since static? */
static PySTEntryObject *
@@ -66,6 +68,7 @@
ste->ste_nested = 1;
ste->ste_child_free = 0;
ste->ste_generator = 0;
+ ste->ste_returns_value = 0;
if (PyDict_SetItem(st->st_symbols, ste->ste_id, (PyObject *)ste) < 0)
goto fail;
@@ -944,8 +947,17 @@
break;
}
case Return_kind:
- if (s->v.Return.value)
+ if (s->v.Return.value) {
VISIT(st, expr, s->v.Return.value);
+ st->st_cur->ste_returns_value = 1;
+ if (st->st_cur->ste_generator) {
+ PyErr_SetString(PyExc_SyntaxError,
+ RETURN_VAL_IN_GENERATOR);
+ PyErr_SyntaxLocation(st->st_filename,
+ s->lineno);
+ return 0;
+ }
+ }
break;
case Delete_kind:
VISIT_SEQ(st, expr, s->v.Delete.targets);
@@ -1136,6 +1148,13 @@
if (e->v.Yield.value)
VISIT(st, expr, e->v.Yield.value);
st->st_cur->ste_generator = 1;
+ if (st->st_cur->ste_returns_value) {
+ PyErr_SetString(PyExc_SyntaxError,
+ RETURN_VAL_IN_GENERATOR);
+ PyErr_SyntaxLocation(st->st_filename,
+ e->lineno);
+ return 0;
+ }
break;
case Compare_kind:
VISIT(st, expr, e->v.Compare.left);
Modified: python/branches/p3yk/Python/sysmodule.c
==============================================================================
--- python/branches/p3yk/Python/sysmodule.c (original)
+++ python/branches/p3yk/Python/sysmodule.c Thu Jun 8 17:35:45 2006
@@ -1027,7 +1027,7 @@
PyObject *sysin, *sysout, *syserr;
char *s;
#ifdef MS_WINDOWS
- char buf[10];
+ char buf[128];
#endif
m = Py_InitModule3("sys", sys_methods, sys_doc);
Modified: python/branches/p3yk/Python/thread.c
==============================================================================
--- python/branches/p3yk/Python/thread.c (original)
+++ python/branches/p3yk/Python/thread.c Thu Jun 8 17:35:45 2006
@@ -75,7 +75,8 @@
static void PyThread__init_thread(void); /* Forward */
-void PyThread_init_thread(void)
+void
+PyThread_init_thread(void)
{
#ifdef Py_DEBUG
char *p = getenv("THREADDEBUG");
Modified: python/branches/p3yk/Python/thread_nt.h
==============================================================================
--- python/branches/p3yk/Python/thread_nt.h (original)
+++ python/branches/p3yk/Python/thread_nt.h Thu Jun 8 17:35:45 2006
@@ -16,7 +16,8 @@
typedef PVOID WINAPI interlocked_cmp_xchg_t(PVOID *dest, PVOID exc, PVOID comperand) ;
/* Sorry mate, but we haven't got InterlockedCompareExchange in Win95! */
-static PVOID WINAPI interlocked_cmp_xchg(PVOID *dest, PVOID exc, PVOID comperand)
+static PVOID WINAPI
+interlocked_cmp_xchg(PVOID *dest, PVOID exc, PVOID comperand)
{
static LONG spinlock = 0 ;
PVOID result ;
@@ -54,8 +55,10 @@
return result ;
} ;
-static interlocked_cmp_xchg_t *ixchg ;
-BOOL InitializeNonRecursiveMutex(PNRMUTEX mutex)
+static interlocked_cmp_xchg_t *ixchg;
+
+BOOL
+InitializeNonRecursiveMutex(PNRMUTEX mutex)
{
if (!ixchg)
{
@@ -76,14 +79,16 @@
#endif
#define InterlockedCompareExchange(dest,exchange,comperand) (ixchg((dest), (exchange), (comperand)))
-VOID DeleteNonRecursiveMutex(PNRMUTEX mutex)
+VOID
+DeleteNonRecursiveMutex(PNRMUTEX mutex)
{
/* No in-use check */
CloseHandle(mutex->hevent) ;
mutex->hevent = NULL ; /* Just in case */
}
-DWORD EnterNonRecursiveMutex(PNRMUTEX mutex, BOOL wait)
+DWORD
+EnterNonRecursiveMutex(PNRMUTEX mutex, BOOL wait)
{
/* Assume that the thread waits successfully */
DWORD ret ;
@@ -104,7 +109,8 @@
return ret ;
}
-BOOL LeaveNonRecursiveMutex(PNRMUTEX mutex)
+BOOL
+LeaveNonRecursiveMutex(PNRMUTEX mutex)
{
/* We don't own the mutex */
mutex->thread_id = 0 ;
@@ -113,7 +119,8 @@
SetEvent(mutex->hevent) ; /* Other threads are waiting, wake one on them up */
}
-PNRMUTEX AllocNonRecursiveMutex(void)
+PNRMUTEX
+AllocNonRecursiveMutex(void)
{
PNRMUTEX mutex = (PNRMUTEX)malloc(sizeof(NRMUTEX)) ;
if (mutex && !InitializeNonRecursiveMutex(mutex))
@@ -124,7 +131,8 @@
return mutex ;
}
-void FreeNonRecursiveMutex(PNRMUTEX mutex)
+void
+FreeNonRecursiveMutex(PNRMUTEX mutex)
{
if (mutex)
{
@@ -138,7 +146,8 @@
/*
* Initialization of the C package, should not be needed.
*/
-static void PyThread__init_thread(void)
+static void
+PyThread__init_thread(void)
{
}
@@ -209,7 +218,8 @@
* Return the thread Id instead of an handle. The Id is said to uniquely identify the
* thread in the system
*/
-long PyThread_get_thread_ident(void)
+long
+PyThread_get_thread_ident(void)
{
if (!initialized)
PyThread_init_thread();
@@ -217,7 +227,8 @@
return GetCurrentThreadId();
}
-static void do_PyThread_exit_thread(int no_cleanup)
+static void
+do_PyThread_exit_thread(int no_cleanup)
{
dprintf(("%ld: PyThread_exit_thread called\n", PyThread_get_thread_ident()));
if (!initialized)
@@ -228,18 +239,21 @@
_endthread();
}
-void PyThread_exit_thread(void)
+void
+PyThread_exit_thread(void)
{
do_PyThread_exit_thread(0);
}
-void PyThread__exit_thread(void)
+void
+PyThread__exit_thread(void)
{
do_PyThread_exit_thread(1);
}
#ifndef NO_EXIT_PROG
-static void do_PyThread_exit_prog(int status, int no_cleanup)
+static void
+do_PyThread_exit_prog(int status, int no_cleanup)
{
dprintf(("PyThread_exit_prog(%d) called\n", status));
if (!initialized)
@@ -249,12 +263,14 @@
exit(status);
}
-void PyThread_exit_prog(int status)
+void
+PyThread_exit_prog(int status)
{
do_PyThread_exit_prog(status, 0);
}
-void PyThread__exit_prog(int status)
+void
+PyThread__exit_prog(int status)
{
do_PyThread_exit_prog(status, 1);
}
@@ -265,7 +281,8 @@
* I [Dag] tried to implement it with mutex but I could find a way to
* tell whether a thread already own the lock or not.
*/
-PyThread_type_lock PyThread_allocate_lock(void)
+PyThread_type_lock
+PyThread_allocate_lock(void)
{
PNRMUTEX aLock;
@@ -280,7 +297,8 @@
return (PyThread_type_lock) aLock;
}
-void PyThread_free_lock(PyThread_type_lock aLock)
+void
+PyThread_free_lock(PyThread_type_lock aLock)
{
dprintf(("%ld: PyThread_free_lock(%p) called\n", PyThread_get_thread_ident(),aLock));
@@ -293,7 +311,8 @@
* and 0 if the lock was not acquired. This means a 0 is returned
* if the lock has already been acquired by this thread!
*/
-int PyThread_acquire_lock(PyThread_type_lock aLock, int waitflag)
+int
+PyThread_acquire_lock(PyThread_type_lock aLock, int waitflag)
{
int success ;
@@ -306,7 +325,8 @@
return success;
}
-void PyThread_release_lock(PyThread_type_lock aLock)
+void
+PyThread_release_lock(PyThread_type_lock aLock)
{
dprintf(("%ld: PyThread_release_lock(%p) called\n", PyThread_get_thread_ident(),aLock));
Modified: python/branches/p3yk/Python/thread_os2.h
==============================================================================
--- python/branches/p3yk/Python/thread_os2.h (original)
+++ python/branches/p3yk/Python/thread_os2.h Thu Jun 8 17:35:45 2006
@@ -238,7 +238,8 @@
return 1;
}
-void PyThread_release_lock(PyThread_type_lock aLock)
+void
+PyThread_release_lock(PyThread_type_lock aLock)
{
#if !defined(PYCC_GCC)
type_os2_lock lock = (type_os2_lock)aLock;
Modified: python/branches/p3yk/Tools/unicode/Makefile
==============================================================================
--- python/branches/p3yk/Tools/unicode/Makefile (original)
+++ python/branches/p3yk/Tools/unicode/Makefile Thu Jun 8 17:35:45 2006
@@ -78,7 +78,7 @@
### Cleanup
clean:
- $(RM) build/*
+ $(RM) -f build/*
distclean: clean
$(RM) -rf MAPPINGS/
Modified: python/branches/p3yk/Tools/unicode/gencodec.py
==============================================================================
--- python/branches/p3yk/Tools/unicode/gencodec.py (original)
+++ python/branches/p3yk/Tools/unicode/gencodec.py Thu Jun 8 17:35:45 2006
@@ -270,6 +270,11 @@
comments=comments,
precisions=(4, 2))
+ if decoding_table_code:
+ suffix = 'table'
+ else:
+ suffix = 'map'
+
l = [
'''\
""" Python Character Mapping Codec %s generated from '%s' with gencodec.py.
@@ -283,30 +288,20 @@
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
-
- def decode(self,input,errors='strict'):''' % (encodingname, name)
- ]
- if decoding_table_code:
- l.append('''\
- return codecs.charmap_decode(input,errors,decoding_table)''')
- else:
- l.append('''\
- return codecs.charmap_decode(input,errors,decoding_map)''')
+ return codecs.charmap_encode(input,errors,encoding_%s)
- l.append('''
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_%s)
+''' % (encodingname, name, suffix, suffix)]
+ l.append('''\
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_%s)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
- def decode(self, input, final=False):''')
- if decoding_table_code:
- l.append('''\
- return codecs.charmap_decode(input,self.errors,decoding_table)[0]''')
- else:
- l.append('''\
- return codecs.charmap_decode(input,self.errors,decoding_map)[0]''')
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_%s)[0]''' %
+ (suffix, suffix))
l.append('''
class StreamWriter(Codec,codecs.StreamWriter):
@@ -319,13 +314,13 @@
def getregentry():
return codecs.CodecInfo(
- Codec().encode,
- Codec().decode,
name=%r,
- streamwriter=StreamWriter,
- streamreader=StreamReader,
+ encode=Codec().encode,
+ decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
)
''' % encodingname.replace('_', '-'))
@@ -342,10 +337,16 @@
l.extend(decoding_table_code)
# Add encoding map
- l.append('''
+ if decoding_table_code:
+ l.append('''
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
+''')
+ else:
+ l.append('''
### Encoding Map
''')
- l.extend(encoding_map_code)
+ l.extend(encoding_map_code)
# Final new-line
l.append('')
Modified: python/branches/p3yk/Tools/webchecker/webchecker.py
==============================================================================
--- python/branches/p3yk/Tools/webchecker/webchecker.py (original)
+++ python/branches/p3yk/Tools/webchecker/webchecker.py Thu Jun 8 17:35:45 2006
@@ -784,7 +784,7 @@
self.url = url
sgmllib.SGMLParser.__init__(self)
- def check_name_id( self, attributes ):
+ def check_name_id(self, attributes):
""" Check the name or id attributes on an element.
"""
# We must rescue the NAME or id (name is deprecated in XHTML)
@@ -799,7 +799,7 @@
else: self.names.append(value)
break
- def unknown_starttag( self, tag, attributes ):
+ def unknown_starttag(self, tag, attributes):
""" In XHTML, you can have id attributes on any element.
"""
self.check_name_id(attributes)
Modified: python/branches/p3yk/configure
==============================================================================
--- python/branches/p3yk/configure (original)
+++ python/branches/p3yk/configure Thu Jun 8 17:35:45 2006
@@ -1,5 +1,5 @@
#! /bin/sh
-# From configure.in Revision: 46491 .
+# From configure.in Revision: 46753 .
# Guess values for system-dependent variables and create Makefiles.
# Generated by GNU Autoconf 2.59e for python 3.0.
#
@@ -648,6 +648,9 @@
PYTHONFRAMEWORKINSTALLDIR
FRAMEWORKINSTALLFIRST
FRAMEWORKINSTALLLAST
+FRAMEWORKALTINSTALLFIRST
+FRAMEWORKALTINSTALLLAST
+FRAMEWORKUNIXTOOLSPREFIX
MACHDEP
SGI_ABI
EXTRAPLATDIR
@@ -1874,6 +1877,13 @@
PYTHONFRAMEWORKINSTALLDIR=
FRAMEWORKINSTALLFIRST=
FRAMEWORKINSTALLLAST=
+ FRAMEWORKALTINSTALLFIRST=
+ FRAMEWORKALTINSTALLLAST=
+ if test "x${prefix}" = "xNONE"; then
+ FRAMEWORKUNIXTOOLSPREFIX="${ac_default_prefix}"
+ else
+ FRAMEWORKUNIXTOOLSPREFIX="${prefix}"
+ fi
enable_framework=
;;
*)
@@ -1883,15 +1893,22 @@
PYTHONFRAMEWORKINSTALLDIR=$PYTHONFRAMEWORKPREFIX/$PYTHONFRAMEWORKDIR
FRAMEWORKINSTALLFIRST="frameworkinstallstructure"
FRAMEWORKINSTALLLAST="frameworkinstallmaclib frameworkinstallapps frameworkinstallunixtools"
+ FRAMEWORKALTINSTALLFIRST="${FRAMEWORKINSTALLFIRST} bininstall maninstall"
+ FRAMEWORKALTINSTALLLAST="frameworkinstallmaclib frameworkinstallapps frameworkaltinstallunixtools"
+ if test "x${prefix}" = "xNONE" ; then
+ FRAMEWORKUNIXTOOLSPREFIX="${ac_default_prefix}"
+ else
+ FRAMEWORKUNIXTOOLSPREFIX="${prefix}"
+ fi
prefix=$PYTHONFRAMEWORKINSTALLDIR/Versions/$VERSION
# Add makefiles for Mac specific code to the list of output
# files:
- ac_config_files="$ac_config_files Mac/OSX/Makefile"
+ ac_config_files="$ac_config_files Mac/Makefile"
- ac_config_files="$ac_config_files Mac/OSX/PythonLauncher/Makefile"
+ ac_config_files="$ac_config_files Mac/PythonLauncher/Makefile"
- ac_config_files="$ac_config_files Mac/OSX/IDLE/Makefile"
+ ac_config_files="$ac_config_files Mac/IDLE/Makefile"
esac
@@ -1903,6 +1920,13 @@
PYTHONFRAMEWORKINSTALLDIR=
FRAMEWORKINSTALLFIRST=
FRAMEWORKINSTALLLAST=
+ FRAMEWORKALTINSTALLFIRST=
+ FRAMEWORKALTINSTALLLAST=
+ if test "x${prefix}" = "xNONE" ; then
+ FRAMEWORKUNIXTOOLSPREFIX="${ac_default_prefix}"
+ else
+ FRAMEWORKUNIXTOOLSPREFIX="${prefix}"
+ fi
enable_framework=
fi
@@ -1914,6 +1938,9 @@
+
+
+
##AC_ARG_WITH(dyld,
## AC_HELP_STRING(--with-dyld,
## Use (OpenStep|Rhapsody) dynamic linker))
@@ -26168,9 +26195,9 @@
do
case $ac_config_target in
"pyconfig.h") CONFIG_HEADERS="$CONFIG_HEADERS pyconfig.h" ;;
- "Mac/OSX/Makefile") CONFIG_FILES="$CONFIG_FILES Mac/OSX/Makefile" ;;
- "Mac/OSX/PythonLauncher/Makefile") CONFIG_FILES="$CONFIG_FILES Mac/OSX/PythonLauncher/Makefile" ;;
- "Mac/OSX/IDLE/Makefile") CONFIG_FILES="$CONFIG_FILES Mac/OSX/IDLE/Makefile" ;;
+ "Mac/Makefile") CONFIG_FILES="$CONFIG_FILES Mac/Makefile" ;;
+ "Mac/PythonLauncher/Makefile") CONFIG_FILES="$CONFIG_FILES Mac/PythonLauncher/Makefile" ;;
+ "Mac/IDLE/Makefile") CONFIG_FILES="$CONFIG_FILES Mac/IDLE/Makefile" ;;
"Makefile.pre") CONFIG_FILES="$CONFIG_FILES Makefile.pre" ;;
"Modules/Setup.config") CONFIG_FILES="$CONFIG_FILES Modules/Setup.config" ;;
@@ -26281,6 +26308,9 @@
PYTHONFRAMEWORKINSTALLDIR!$PYTHONFRAMEWORKINSTALLDIR$ac_delim
FRAMEWORKINSTALLFIRST!$FRAMEWORKINSTALLFIRST$ac_delim
FRAMEWORKINSTALLLAST!$FRAMEWORKINSTALLLAST$ac_delim
+FRAMEWORKALTINSTALLFIRST!$FRAMEWORKALTINSTALLFIRST$ac_delim
+FRAMEWORKALTINSTALLLAST!$FRAMEWORKALTINSTALLLAST$ac_delim
+FRAMEWORKUNIXTOOLSPREFIX!$FRAMEWORKUNIXTOOLSPREFIX$ac_delim
MACHDEP!$MACHDEP$ac_delim
SGI_ABI!$SGI_ABI$ac_delim
EXTRAPLATDIR!$EXTRAPLATDIR$ac_delim
@@ -26328,9 +26358,6 @@
SHLIBS!$SHLIBS$ac_delim
USE_SIGNAL_MODULE!$USE_SIGNAL_MODULE$ac_delim
SIGNAL_OBJS!$SIGNAL_OBJS$ac_delim
-USE_THREAD_MODULE!$USE_THREAD_MODULE$ac_delim
-LDLAST!$LDLAST$ac_delim
-THREADOBJ!$THREADOBJ$ac_delim
_ACEOF
if test `sed -n "s/.*$ac_delim\$/X/p" conf$$subs.sed | grep -c X` = 97; then
@@ -26372,6 +26399,9 @@
ac_delim='%!_!# '
for ac_last_try in false false false false false :; do
cat >conf$$subs.sed <<_ACEOF
+USE_THREAD_MODULE!$USE_THREAD_MODULE$ac_delim
+LDLAST!$LDLAST$ac_delim
+THREADOBJ!$THREADOBJ$ac_delim
DLINCLDIR!$DLINCLDIR$ac_delim
DYNLOADFILE!$DYNLOADFILE$ac_delim
MACHDEP_OBJS!$MACHDEP_OBJS$ac_delim
@@ -26390,7 +26420,7 @@
LTLIBOBJS!$LTLIBOBJS$ac_delim
_ACEOF
- if test `sed -n "s/.*$ac_delim\$/X/p" conf$$subs.sed | grep -c X` = 16; then
+ if test `sed -n "s/.*$ac_delim\$/X/p" conf$$subs.sed | grep -c X` = 19; then
break
elif $ac_last_try; then
{ { echo "$as_me:$LINENO: error: could not make $CONFIG_STATUS" >&5
Modified: python/branches/p3yk/configure.in
==============================================================================
--- python/branches/p3yk/configure.in (original)
+++ python/branches/p3yk/configure.in Thu Jun 8 17:35:45 2006
@@ -99,6 +99,13 @@
PYTHONFRAMEWORKINSTALLDIR=
FRAMEWORKINSTALLFIRST=
FRAMEWORKINSTALLLAST=
+ FRAMEWORKALTINSTALLFIRST=
+ FRAMEWORKALTINSTALLLAST=
+ if test "x${prefix}" = "xNONE"; then
+ FRAMEWORKUNIXTOOLSPREFIX="${ac_default_prefix}"
+ else
+ FRAMEWORKUNIXTOOLSPREFIX="${prefix}"
+ fi
enable_framework=
;;
*)
@@ -108,13 +115,20 @@
PYTHONFRAMEWORKINSTALLDIR=$PYTHONFRAMEWORKPREFIX/$PYTHONFRAMEWORKDIR
FRAMEWORKINSTALLFIRST="frameworkinstallstructure"
FRAMEWORKINSTALLLAST="frameworkinstallmaclib frameworkinstallapps frameworkinstallunixtools"
+ FRAMEWORKALTINSTALLFIRST="${FRAMEWORKINSTALLFIRST} bininstall maninstall"
+ FRAMEWORKALTINSTALLLAST="frameworkinstallmaclib frameworkinstallapps frameworkaltinstallunixtools"
+ if test "x${prefix}" = "xNONE" ; then
+ FRAMEWORKUNIXTOOLSPREFIX="${ac_default_prefix}"
+ else
+ FRAMEWORKUNIXTOOLSPREFIX="${prefix}"
+ fi
prefix=$PYTHONFRAMEWORKINSTALLDIR/Versions/$VERSION
# Add makefiles for Mac specific code to the list of output
# files:
- AC_CONFIG_FILES(Mac/OSX/Makefile)
- AC_CONFIG_FILES(Mac/OSX/PythonLauncher/Makefile)
- AC_CONFIG_FILES(Mac/OSX/IDLE/Makefile)
+ AC_CONFIG_FILES(Mac/Makefile)
+ AC_CONFIG_FILES(Mac/PythonLauncher/Makefile)
+ AC_CONFIG_FILES(Mac/IDLE/Makefile)
esac
],[
PYTHONFRAMEWORK=
@@ -123,6 +137,13 @@
PYTHONFRAMEWORKINSTALLDIR=
FRAMEWORKINSTALLFIRST=
FRAMEWORKINSTALLLAST=
+ FRAMEWORKALTINSTALLFIRST=
+ FRAMEWORKALTINSTALLLAST=
+ if test "x${prefix}" = "xNONE" ; then
+ FRAMEWORKUNIXTOOLSPREFIX="${ac_default_prefix}"
+ else
+ FRAMEWORKUNIXTOOLSPREFIX="${prefix}"
+ fi
enable_framework=
])
AC_SUBST(PYTHONFRAMEWORK)
@@ -131,6 +152,9 @@
AC_SUBST(PYTHONFRAMEWORKINSTALLDIR)
AC_SUBST(FRAMEWORKINSTALLFIRST)
AC_SUBST(FRAMEWORKINSTALLLAST)
+AC_SUBST(FRAMEWORKALTINSTALLFIRST)
+AC_SUBST(FRAMEWORKALTINSTALLLAST)
+AC_SUBST(FRAMEWORKUNIXTOOLSPREFIX)
##AC_ARG_WITH(dyld,
## AC_HELP_STRING(--with-dyld,
Modified: python/branches/p3yk/setup.py
==============================================================================
--- python/branches/p3yk/setup.py (original)
+++ python/branches/p3yk/setup.py Thu Jun 8 17:35:45 2006
@@ -582,7 +582,9 @@
# The _md5 module implements the RSA Data Security, Inc. MD5
# Message-Digest Algorithm, described in RFC 1321. The
# necessary files md5.c and md5.h are included here.
- exts.append( Extension('_md5', ['md5module.c', 'md5.c']) )
+ exts.append( Extension('_md5',
+ sources = ['md5module.c', 'md5.c'],
+ depends = ['md5.h']) )
if (openssl_ver < 0x00908000):
# OpenSSL doesn't do these until 0.9.8 so we'll bring our own hash
@@ -1095,29 +1097,6 @@
extra_link_args=['-framework', 'QuickTime',
'-framework', 'Carbon']) )
- # As there is no standardized place (yet) to put
- # user-installed Mac libraries on OSX, we search for "waste"
- # in parent directories of the Python source tree. You
- # should put a symlink to your Waste installation in the
- # same folder as your python source tree. Or modify the
- # next few lines:-)
- waste_incs = find_file("WASTE.h", [],
- ['../'*n + 'waste/C_C++ Headers' for n in (0,1,2,3,4)])
- waste_libs = find_library_file(self.compiler, "WASTE", [],
- ["../"*n + "waste/Static Libraries" for n in (0,1,2,3,4)])
- if waste_incs != None and waste_libs != None:
- exts.append( Extension('waste',
- ['waste/wastemodule.c'] + [
- os.path.join(srcdir, d) for d in
- 'Mac/Wastemods/WEObjectHandlers.c',
- 'Mac/Wastemods/WETabHooks.c',
- 'Mac/Wastemods/WETabs.c'
- ],
- include_dirs = waste_incs + [os.path.join(srcdir, 'Mac/Wastemods')],
- library_dirs = waste_libs,
- libraries = ['WASTE'],
- extra_link_args = ['-framework', 'Carbon'],
- ) )
self.extensions.extend(exts)
More information about the Python-3000-checkins
mailing list