[Python-checkins] r72086 - in python/branches/py3k: Doc/library/tokenize.rst Lib/tokenize.py
raymond.hettinger
python-checkins at python.org
Wed Apr 29 02:34:27 CEST 2009
Author: raymond.hettinger
Date: Wed Apr 29 02:34:27 2009
New Revision: 72086
Log:
Issue #5857: tokenize.tokenize() now returns named tuples.
Modified:
python/branches/py3k/Doc/library/tokenize.rst
python/branches/py3k/Lib/tokenize.py
Modified: python/branches/py3k/Doc/library/tokenize.rst
==============================================================================
--- python/branches/py3k/Doc/library/tokenize.rst (original)
+++ python/branches/py3k/Doc/library/tokenize.rst Wed Apr 29 02:34:27 2009
@@ -27,7 +27,12 @@
column where the token begins in the source; a 2-tuple ``(erow, ecol)`` of
ints specifying the row and column where the token ends in the source; and
the line on which the token was found. The line passed (the last tuple item)
- is the *logical* line; continuation lines are included.
+ is the *logical* line; continuation lines are included. The 5 tuple is
+ returned as a :term:`named tuple` with the field names:
+ ``type string start end line``.
+
+ .. versionchanged:: 3.1
+ Added support for named tuples.
:func:`tokenize` determines the source encoding of the file by looking for a
UTF-8 BOM or encoding cookie, according to :pep:`263`.
Modified: python/branches/py3k/Lib/tokenize.py
==============================================================================
--- python/branches/py3k/Lib/tokenize.py (original)
+++ python/branches/py3k/Lib/tokenize.py Wed Apr 29 02:34:27 2009
@@ -24,6 +24,7 @@
'Skip Montanaro, Raymond Hettinger, Trent Nelson, '
'Michael Foord')
+import collections
import re, string, sys
from token import *
from codecs import lookup, BOM_UTF8
@@ -31,7 +32,7 @@
import token
__all__ = [x for x in dir(token) if x[0] != '_'] + ["COMMENT", "tokenize",
- "detect_encoding", "NL", "untokenize", "ENCODING"]
+ "detect_encoding", "NL", "untokenize", "ENCODING", "Tokenize"]
del token
COMMENT = N_TOKENS
@@ -42,6 +43,8 @@
tok_name[ENCODING] = 'ENCODING'
N_TOKENS += 3
+TokenInfo = collections.namedtuple('TokenInfo', 'type string start end line')
+
def group(*choices): return '(' + '|'.join(choices) + ')'
def any(*choices): return group(*choices) + '*'
def maybe(*choices): return group(*choices) + '?'
@@ -346,7 +349,7 @@
indents = [0]
if encoding is not None:
- yield (ENCODING, encoding, (0, 0), (0, 0), '')
+ yield TokenInfo(ENCODING, encoding, (0, 0), (0, 0), '')
while True: # loop over lines in stream
try:
line = readline()
@@ -364,12 +367,12 @@
endmatch = endprog.match(line)
if endmatch:
pos = end = endmatch.end(0)
- yield (STRING, contstr + line[:end],
+ yield TokenInfo(STRING, contstr + line[:end],
strstart, (lnum, end), contline + line)
contstr, needcont = '', 0
contline = None
elif needcont and line[-2:] != '\\\n' and line[-3:] != '\\\r\n':
- yield (ERRORTOKEN, contstr + line,
+ yield TokenInfo(ERRORTOKEN, contstr + line,
strstart, (lnum, len(line)), contline)
contstr = ''
contline = None
@@ -394,25 +397,25 @@
if line[pos] == '#':
comment_token = line[pos:].rstrip('\r\n')
nl_pos = pos + len(comment_token)
- yield (COMMENT, comment_token,
+ yield TokenInfo(COMMENT, comment_token,
(lnum, pos), (lnum, pos + len(comment_token)), line)
- yield (NL, line[nl_pos:],
+ yield TokenInfo(NL, line[nl_pos:],
(lnum, nl_pos), (lnum, len(line)), line)
else:
- yield ((NL, COMMENT)[line[pos] == '#'], line[pos:],
+ yield TokenInfo((NL, COMMENT)[line[pos] == '#'], line[pos:],
(lnum, pos), (lnum, len(line)), line)
continue
if column > indents[-1]: # count indents or dedents
indents.append(column)
- yield (INDENT, line[:pos], (lnum, 0), (lnum, pos), line)
+ yield TokenInfo(INDENT, line[:pos], (lnum, 0), (lnum, pos), line)
while column < indents[-1]:
if column not in indents:
raise IndentationError(
"unindent does not match any outer indentation level",
("<tokenize>", lnum, pos, line))
indents = indents[:-1]
- yield (DEDENT, '', (lnum, pos), (lnum, pos), line)
+ yield TokenInfo(DEDENT, '', (lnum, pos), (lnum, pos), line)
else: # continued statement
if not line:
@@ -428,20 +431,20 @@
if (initial in numchars or # ordinary number
(initial == '.' and token != '.' and token != '...')):
- yield (NUMBER, token, spos, epos, line)
+ yield TokenInfo(NUMBER, token, spos, epos, line)
elif initial in '\r\n':
- yield (NL if parenlev > 0 else NEWLINE,
+ yield TokenInfo(NL if parenlev > 0 else NEWLINE,
token, spos, epos, line)
elif initial == '#':
assert not token.endswith("\n")
- yield (COMMENT, token, spos, epos, line)
+ yield TokenInfo(COMMENT, token, spos, epos, line)
elif token in triple_quoted:
endprog = endprogs[token]
endmatch = endprog.match(line, pos)
if endmatch: # all on one line
pos = endmatch.end(0)
token = line[start:pos]
- yield (STRING, token, spos, (lnum, pos), line)
+ yield TokenInfo(STRING, token, spos, (lnum, pos), line)
else:
strstart = (lnum, start) # multiple lines
contstr = line[start:]
@@ -458,23 +461,23 @@
contline = line
break
else: # ordinary string
- yield (STRING, token, spos, epos, line)
+ yield TokenInfo(STRING, token, spos, epos, line)
elif initial in namechars: # ordinary name
- yield (NAME, token, spos, epos, line)
+ yield TokenInfo(NAME, token, spos, epos, line)
elif initial == '\\': # continued stmt
continued = 1
else:
if initial in '([{': parenlev = parenlev + 1
elif initial in ')]}': parenlev = parenlev - 1
- yield (OP, token, spos, epos, line)
+ yield TokenInfo(OP, token, spos, epos, line)
else:
- yield (ERRORTOKEN, line[pos],
+ yield TokenInfo(ERRORTOKEN, line[pos],
(lnum, pos), (lnum, pos+1), line)
pos = pos + 1
for indent in indents[1:]: # pop remaining indent levels
- yield (DEDENT, '', (lnum, 0), (lnum, 0), '')
- yield (ENDMARKER, '', (lnum, 0), (lnum, 0), '')
+ yield TokenInfo(DEDENT, '', (lnum, 0), (lnum, 0), '')
+ yield TokenInfo(ENDMARKER, '', (lnum, 0), (lnum, 0), '')
# An undocumented, backwards compatible, API for all the places in the standard
More information about the Python-checkins
mailing list