[Python-checkins] CVS: python/dist/src/Lib sre.py,1.6,1.7 sre_compile.py,1.4,1.5 sre_constants.py,1.4,1.5 sre_parse.py,1.4,1.5
Fredrik Lundh
python-dev@python.org
Thu, 29 Jun 2000 01:58:47 -0700
- Previous message: [Python-checkins] CVS: python/dist/src/Modules _sre.c,2.4,2.5
- Next message: [Python-checkins] CVS: python/dist/src/Lib sre.py,1.7,1.8 sre_compile.py,1.5,1.6 sre_constants.py,1.5,1.6 sre_parse.py,1.5,1.6
- Messages sorted by:
[ date ]
[ thread ]
[ subject ]
[ author ]
Update of /cvsroot/python/python/dist/src/Lib
In directory slayer.i.sourceforge.net:/tmp/cvs-serv11309
Modified Files:
sre.py sre_compile.py sre_constants.py sre_parse.py
Log Message:
towards 1.6b1
Index: sre.py
===================================================================
RCS file: /cvsroot/python/python/dist/src/Lib/sre.py,v
retrieving revision 1.6
retrieving revision 1.7
diff -C2 -r1.6 -r1.7
*** sre.py 2000/06/18 20:27:10 1.6
--- sre.py 2000/06/29 08:58:44 1.7
***************
*** 13,16 ****
--- 13,17 ----
import sre_compile
+ import sre_parse
# flags
***************
*** 21,24 ****
--- 22,32 ----
X = VERBOSE = sre_compile.SRE_FLAG_VERBOSE
+ # sre extensions (may or may not be in 1.6 final)
+ T = TEMPLATE = sre_compile.SRE_FLAG_TEMPLATE
+ U = UNICODE = sre_compile.SRE_FLAG_UNICODE
+
+ # sre exception
+ error = sre_parse.error
+
# --------------------------------------------------------------------
# public interface
***************
*** 47,50 ****
--- 55,61 ----
return _compile(pattern, flags)
+ def template(pattern, flags=0):
+ return _compile(pattern, flags|T)
+
def escape(pattern):
s = list(pattern)
***************
*** 84,91 ****
return _subn(pattern, template, string, count)[0]
- def _expand(match, template):
- # internal: expand template
- return template # FIXME
-
def _subn(pattern, template, string, count=0):
# internal: pattern.subn implementation hook
--- 95,98 ----
***************
*** 93,99 ****
filter = template
else:
! # FIXME: prepare template
def filter(match, template=template):
! return _expand(match, template)
n = i = 0
s = []
--- 100,106 ----
filter = template
else:
! template = sre_parse.parse_template(template, pattern)
def filter(match, template=template):
! return sre_parse.expand_template(template, match)
n = i = 0
s = []
***************
*** 109,112 ****
--- 116,121 ----
append(filter(m))
i = m.end()
+ if i <= j:
+ break
n = n + 1
if i < len(string):
***************
*** 127,130 ****
--- 136,141 ----
append(string[i:j])
i = m.end()
+ if i <= j:
+ break
n = n + 1
if i < len(string):
Index: sre_compile.py
===================================================================
RCS file: /cvsroot/python/python/dist/src/Lib/sre_compile.py,v
retrieving revision 1.4
retrieving revision 1.5
diff -C2 -r1.4 -r1.5
*** sre_compile.py 2000/06/01 17:39:12 1.4
--- sre_compile.py 2000/06/29 08:58:44 1.5
***************
*** 49,53 ****
raise
! def _compile(code, pattern, flags, level=0):
append = code.append
for op, av in pattern:
--- 49,53 ----
raise
! def _compile(code, pattern, flags):
append = code.append
for op, av in pattern:
***************
*** 71,91 ****
for av in av[1]:
skip = len(code); append(0)
! _compile(code, av, flags, level)
! append(OPCODES[JUMP])
! tail.append(len(code)); append(0)
code[skip] = len(code) - skip
append(0) # end of branch
! for tail in tail:
code[tail] = len(code) - tail
elif op is CALL:
append(OPCODES[op])
skip = len(code); append(0)
! _compile(code, av, flags, level+1)
append(OPCODES[SUCCESS])
code[skip] = len(code) - skip
! elif op is CATEGORY: # not used by current parser
append(OPCODES[op])
if flags & SRE_FLAG_LOCALE:
append(CH_LOCALE[CHCODES[av]])
else:
append(CHCODES[av])
--- 71,94 ----
for av in av[1]:
skip = len(code); append(0)
! _compile(code, av, flags)
! ## append(OPCODES[SUCCESS])
! append(OPCODES[JUMP])
! tail.append(len(code)); append(0)
code[skip] = len(code) - skip
append(0) # end of branch
! for tail in tail:
code[tail] = len(code) - tail
elif op is CALL:
append(OPCODES[op])
skip = len(code); append(0)
! _compile(code, av, flags)
append(OPCODES[SUCCESS])
code[skip] = len(code) - skip
! elif op is CATEGORY:
append(OPCODES[op])
if flags & SRE_FLAG_LOCALE:
append(CH_LOCALE[CHCODES[av]])
+ elif flags & SRE_FLAG_UNICODE:
+ append(CH_UNICODE[CHCODES[av]])
else:
append(CHCODES[av])
***************
*** 99,104 ****
if flags & SRE_FLAG_IGNORECASE:
append(OPCODES[OP_IGNORE[op]])
! def fixup(literal):
! return ord(literal.lower())
else:
append(OPCODES[op])
--- 102,107 ----
if flags & SRE_FLAG_IGNORECASE:
append(OPCODES[OP_IGNORE[op]])
! def fixup(literal, flags=flags):
! return _sre.getlower(ord(literal), flags)
else:
append(OPCODES[op])
***************
*** 117,120 ****
--- 120,125 ----
if flags & SRE_FLAG_LOCALE:
append(CH_LOCALE[CHCODES[av]])
+ elif flags & SRE_FLAG_UNICODE:
+ append(CH_UNICODE[CHCODES[av]])
else:
append(CHCODES[av])
***************
*** 126,159 ****
if flags & SRE_FLAG_IGNORECASE:
append(OPCODES[OP_IGNORE[op]])
- append(ord(av.lower()))
else:
append(OPCODES[op])
! append(ord(av))
elif op is MARK:
append(OPCODES[op])
append(av)
elif op in (REPEAT, MIN_REPEAT, MAX_REPEAT):
! lo, hi = av[2].getwidth()
! if lo == 0:
! raise SyntaxError, "cannot repeat zero-width items"
! if lo == hi == 1 and op is MAX_REPEAT:
! append(OPCODES[MAX_REPEAT_ONE])
skip = len(code); append(0)
append(av[0])
append(av[1])
! _compile(code, av[2], flags, level+1)
append(OPCODES[SUCCESS])
code[skip] = len(code) - skip
else:
! append(OPCODES[op])
! skip = len(code); append(0)
! append(av[0])
! append(av[1])
! _compile(code, av[2], flags, level+1)
! if op is MIN_REPEAT:
! append(OPCODES[MIN_UNTIL])
else:
! append(OPCODES[MAX_UNTIL])
! code[skip] = len(code) - skip
elif op is SUBPATTERN:
group = av[0]
--- 131,171 ----
if flags & SRE_FLAG_IGNORECASE:
append(OPCODES[OP_IGNORE[op]])
else:
append(OPCODES[op])
! append(ord(av))
elif op is MARK:
append(OPCODES[op])
append(av)
elif op in (REPEAT, MIN_REPEAT, MAX_REPEAT):
! if flags & SRE_FLAG_TEMPLATE:
! append(OPCODES[REPEAT])
skip = len(code); append(0)
append(av[0])
append(av[1])
! _compile(code, av[2], flags)
append(OPCODES[SUCCESS])
code[skip] = len(code) - skip
else:
! lo, hi = av[2].getwidth()
! if lo == 0:
! raise error, "nothing to repeat"
! if 0 and lo == hi == 1 and op is MAX_REPEAT:
! # FIXME: <fl> need a better way to figure out when
! # it's safe to use this one (in the parser, probably)
! append(OPCODES[MAX_REPEAT_ONE])
! skip = len(code); append(0)
! append(av[0])
! append(av[1])
! _compile(code, av[2], flags)
! append(OPCODES[SUCCESS])
! code[skip] = len(code) - skip
else:
! append(OPCODES[op])
! skip = len(code); append(0)
! append(av[0])
! append(av[1])
! _compile(code, av[2], flags)
! append(OPCODES[SUCCESS])
! code[skip] = len(code) - skip
elif op is SUBPATTERN:
group = av[0]
***************
*** 161,165 ****
append(OPCODES[MARK])
append((group-1)*2)
! _compile(code, av[1], flags, level+1)
if group:
append(OPCODES[MARK])
--- 173,177 ----
append(OPCODES[MARK])
append((group-1)*2)
! _compile(code, av[1], flags)
if group:
append(OPCODES[MARK])
Index: sre_constants.py
===================================================================
RCS file: /cvsroot/python/python/dist/src/Lib/sre_constants.py,v
retrieving revision 1.4
retrieving revision 1.5
diff -C2 -r1.4 -r1.5
*** sre_constants.py 2000/06/01 17:39:12 1.4
--- sre_constants.py 2000/06/29 08:58:44 1.5
***************
*** 16,19 ****
--- 16,24 ----
#
+ # should this really be here?
+
+ class error(Exception):
+ pass
+
# operators
***************
*** 31,34 ****
--- 36,40 ----
IN = "in"
IN_IGNORE = "in_ignore"
+ INFO = "info"
JUMP = "jump"
LITERAL = "literal"
***************
*** 37,43 ****
MAX_REPEAT = "max_repeat"
MAX_REPEAT_ONE = "max_repeat_one"
- MAX_UNTIL = "max_until"
MIN_REPEAT = "min_repeat"
- MIN_UNTIL = "min_until"
NEGATE = "negate"
NOT_LITERAL = "not_literal"
--- 43,47 ----
***************
*** 45,48 ****
--- 49,53 ----
RANGE = "range"
REPEAT = "repeat"
+ REPEAT_ONE = "repeat_one"
SUBPATTERN = "subpattern"
***************
*** 64,75 ****
CATEGORY_LINEBREAK = "category_linebreak"
CATEGORY_NOT_LINEBREAK = "category_not_linebreak"
- CATEGORY_LOC_DIGIT = "category_loc_digit"
- CATEGORY_LOC_NOT_DIGIT = "category_loc_not_digit"
- CATEGORY_LOC_SPACE = "category_loc_space"
- CATEGORY_LOC_NOT_SPACE = "category_loc_not_space"
CATEGORY_LOC_WORD = "category_loc_word"
CATEGORY_LOC_NOT_WORD = "category_loc_not_word"
! CATEGORY_LOC_LINEBREAK = "category_loc_linebreak"
! CATEGORY_LOC_NOT_LINEBREAK = "category_loc_not_linebreak"
OPCODES = [
--- 69,82 ----
CATEGORY_LINEBREAK = "category_linebreak"
CATEGORY_NOT_LINEBREAK = "category_not_linebreak"
CATEGORY_LOC_WORD = "category_loc_word"
CATEGORY_LOC_NOT_WORD = "category_loc_not_word"
! CATEGORY_UNI_DIGIT = "category_uni_digit"
! CATEGORY_UNI_NOT_DIGIT = "category_uni_not_digit"
! CATEGORY_UNI_SPACE = "category_uni_space"
! CATEGORY_UNI_NOT_SPACE = "category_uni_not_space"
! CATEGORY_UNI_WORD = "category_uni_word"
! CATEGORY_UNI_NOT_WORD = "category_uni_not_word"
! CATEGORY_UNI_LINEBREAK = "category_uni_linebreak"
! CATEGORY_UNI_NOT_LINEBREAK = "category_uni_not_linebreak"
OPCODES = [
***************
*** 86,95 ****
GROUP, GROUP_IGNORE,
IN, IN_IGNORE,
JUMP,
LITERAL, LITERAL_IGNORE,
MARK,
! MAX_REPEAT, MAX_UNTIL,
MAX_REPEAT_ONE,
! MIN_REPEAT, MIN_UNTIL,
NOT_LITERAL, NOT_LITERAL_IGNORE,
NEGATE,
--- 93,103 ----
GROUP, GROUP_IGNORE,
IN, IN_IGNORE,
+ INFO,
JUMP,
LITERAL, LITERAL_IGNORE,
MARK,
! MAX_REPEAT,
MAX_REPEAT_ONE,
! MIN_REPEAT,
NOT_LITERAL, NOT_LITERAL_IGNORE,
NEGATE,
***************
*** 107,114 ****
CATEGORY_DIGIT, CATEGORY_NOT_DIGIT, CATEGORY_SPACE,
CATEGORY_NOT_SPACE, CATEGORY_WORD, CATEGORY_NOT_WORD,
! CATEGORY_LINEBREAK, CATEGORY_NOT_LINEBREAK, CATEGORY_LOC_DIGIT,
! CATEGORY_LOC_NOT_DIGIT, CATEGORY_LOC_SPACE,
! CATEGORY_LOC_NOT_SPACE, CATEGORY_LOC_WORD, CATEGORY_LOC_NOT_WORD,
! CATEGORY_LOC_LINEBREAK, CATEGORY_LOC_NOT_LINEBREAK
]
--- 115,123 ----
CATEGORY_DIGIT, CATEGORY_NOT_DIGIT, CATEGORY_SPACE,
CATEGORY_NOT_SPACE, CATEGORY_WORD, CATEGORY_NOT_WORD,
! CATEGORY_LINEBREAK, CATEGORY_NOT_LINEBREAK, CATEGORY_LOC_WORD,
! CATEGORY_LOC_NOT_WORD, CATEGORY_UNI_DIGIT, CATEGORY_UNI_NOT_DIGIT,
! CATEGORY_UNI_SPACE, CATEGORY_UNI_NOT_SPACE, CATEGORY_UNI_WORD,
! CATEGORY_UNI_NOT_WORD, CATEGORY_UNI_LINEBREAK,
! CATEGORY_UNI_NOT_LINEBREAK
]
***************
*** 139,159 ****
CH_LOCALE = {
! CATEGORY_DIGIT: CATEGORY_LOC_DIGIT,
! CATEGORY_NOT_DIGIT: CATEGORY_LOC_NOT_DIGIT,
! CATEGORY_SPACE: CATEGORY_LOC_SPACE,
! CATEGORY_NOT_SPACE: CATEGORY_LOC_NOT_SPACE,
CATEGORY_WORD: CATEGORY_LOC_WORD,
CATEGORY_NOT_WORD: CATEGORY_LOC_NOT_WORD,
! CATEGORY_LINEBREAK: CATEGORY_LOC_LINEBREAK,
! CATEGORY_NOT_LINEBREAK: CATEGORY_LOC_NOT_LINEBREAK
}
# flags
! SRE_FLAG_TEMPLATE = 1 # NYI
SRE_FLAG_IGNORECASE = 2
SRE_FLAG_LOCALE = 4
SRE_FLAG_MULTILINE = 8
SRE_FLAG_DOTALL = 16
! SRE_FLAG_VERBOSE = 32
if __name__ == "__main__":
--- 148,180 ----
CH_LOCALE = {
! CATEGORY_DIGIT: CATEGORY_DIGIT,
! CATEGORY_NOT_DIGIT: CATEGORY_NOT_DIGIT,
! CATEGORY_SPACE: CATEGORY_SPACE,
! CATEGORY_NOT_SPACE: CATEGORY_NOT_SPACE,
CATEGORY_WORD: CATEGORY_LOC_WORD,
CATEGORY_NOT_WORD: CATEGORY_LOC_NOT_WORD,
! CATEGORY_LINEBREAK: CATEGORY_LINEBREAK,
! CATEGORY_NOT_LINEBREAK: CATEGORY_NOT_LINEBREAK
! }
!
! CH_UNICODE = {
! CATEGORY_DIGIT: CATEGORY_UNI_DIGIT,
! CATEGORY_NOT_DIGIT: CATEGORY_UNI_NOT_DIGIT,
! CATEGORY_SPACE: CATEGORY_UNI_SPACE,
! CATEGORY_NOT_SPACE: CATEGORY_UNI_NOT_SPACE,
! CATEGORY_WORD: CATEGORY_UNI_WORD,
! CATEGORY_NOT_WORD: CATEGORY_UNI_NOT_WORD,
! CATEGORY_LINEBREAK: CATEGORY_UNI_LINEBREAK,
! CATEGORY_NOT_LINEBREAK: CATEGORY_UNI_NOT_LINEBREAK
}
# flags
! SRE_FLAG_TEMPLATE = 1
SRE_FLAG_IGNORECASE = 2
SRE_FLAG_LOCALE = 4
SRE_FLAG_MULTILINE = 8
SRE_FLAG_DOTALL = 16
! SRE_FLAG_UNICODE = 32
! SRE_FLAG_VERBOSE = 64
if __name__ == "__main__":
***************
*** 169,172 ****
--- 190,200 ----
dump(f, ATCODES, "SRE")
dump(f, CHCODES, "SRE")
+ f.write("#define SRE_FLAG_TEMPLATE %d\n" % SRE_FLAG_TEMPLATE)
+ f.write("#define SRE_FLAG_IGNORECASE %d\n" % SRE_FLAG_IGNORECASE)
+ f.write("#define SRE_FLAG_LOCALE %d\n" % SRE_FLAG_LOCALE)
+ f.write("#define SRE_FLAG_MULTILINE %d\n" % SRE_FLAG_MULTILINE)
+ f.write("#define SRE_FLAG_DOTALL %d\n" % SRE_FLAG_DOTALL)
+ f.write("#define SRE_FLAG_UNICODE %d\n" % SRE_FLAG_UNICODE)
+ f.write("#define SRE_FLAG_VERBOSE %d\n" % SRE_FLAG_VERBOSE)
f.close()
print "done"
Index: sre_parse.py
===================================================================
RCS file: /cvsroot/python/python/dist/src/Lib/sre_parse.py,v
retrieving revision 1.4
retrieving revision 1.5
diff -C2 -r1.4 -r1.5
*** sre_parse.py 2000/06/09 14:08:07 1.4
--- sre_parse.py 2000/06/29 08:58:44 1.5
***************
*** 21,26 ****
from sre_constants import *
! # FIXME: should be 65535, but the array module currently chokes on
! # unsigned integers larger than 32767...
MAXREPEAT = int(2L**(_sre.getcodesize()*8-1))-1
--- 21,26 ----
from sre_constants import *
! # FIXME: <fl> should be 65535, but the array module currently chokes
! # on unsigned integers larger than 32767 [fixed in 1.6b1?]
MAXREPEAT = int(2L**(_sre.getcodesize()*8-1))-1
***************
*** 28,32 ****
REPEAT_CHARS = "*+?{"
! # FIXME: string in tuple tests may explode with if char is unicode :-(
DIGITS = tuple(string.digits)
--- 28,33 ----
REPEAT_CHARS = "*+?{"
! # FIXME: <fl> string in tuple tests may explode with if char is
! # unicode [fixed in 1.6b1?]
DIGITS = tuple(string.digits)
***************
*** 60,69 ****
FLAGS = {
"i": SRE_FLAG_IGNORECASE,
"L": SRE_FLAG_LOCALE,
"m": SRE_FLAG_MULTILINE,
"s": SRE_FLAG_DOTALL,
- "t": SRE_FLAG_TEMPLATE,
"x": SRE_FLAG_VERBOSE,
}
--- 61,73 ----
FLAGS = {
+ # standard flags
"i": SRE_FLAG_IGNORECASE,
"L": SRE_FLAG_LOCALE,
"m": SRE_FLAG_MULTILINE,
"s": SRE_FLAG_DOTALL,
"x": SRE_FLAG_VERBOSE,
+ # extensions
+ "t": SRE_FLAG_TEMPLATE,
+ "u": SRE_FLAG_UNICODE,
}
***************
*** 152,156 ****
c = self.string[self.index + 1]
except IndexError:
! raise SyntaxError, "bogus escape"
char = char + c
self.index = self.index + len(char)
--- 156,160 ----
c = self.string[self.index + 1]
except IndexError:
! raise error, "bogus escape"
char = char + c
self.index = self.index + len(char)
***************
*** 206,210 ****
except ValueError:
pass
! raise SyntaxError, "bogus escape: %s" % repr(escape)
def _escape(source, escape, state):
--- 210,214 ----
except ValueError:
pass
! raise error, "bogus escape: %s" % repr(escape)
def _escape(source, escape, state):
***************
*** 242,252 ****
except ValueError:
pass
! raise SyntaxError, "bogus escape: %s" % repr(escape)
def _branch(pattern, items):
! # form a branch operator from a set of items (FIXME: move this
! # optimization to the compiler module!)
subpattern = SubPattern(pattern)
--- 246,255 ----
except ValueError:
pass
! raise error, "bogus escape: %s" % repr(escape)
def _branch(pattern, items):
! # form a branch operator from a set of items
subpattern = SubPattern(pattern)
***************
*** 333,337 ****
code1 = LITERAL, this
else:
! raise SyntaxError, "unexpected end of regular expression"
if source.match("-"):
# potential range
--- 336,340 ----
code1 = LITERAL, this
else:
! raise error, "unexpected end of regular expression"
if source.match("-"):
# potential range
***************
*** 347,353 ****
code2 = LITERAL, this
if code1[0] != LITERAL or code2[0] != LITERAL:
! raise SyntaxError, "illegal range"
if len(code1[1]) != 1 or len(code2[1]) != 1:
! raise SyntaxError, "illegal range"
set.append((RANGE, (code1[1], code2[1])))
else:
--- 350,356 ----
code2 = LITERAL, this
if code1[0] != LITERAL or code2[0] != LITERAL:
! raise error, "illegal range"
if len(code1[1]) != 1 or len(code2[1]) != 1:
! raise error, "illegal range"
set.append((RANGE, (code1[1], code2[1])))
else:
***************
*** 384,388 ****
hi = lo
if not source.match("}"):
! raise SyntaxError, "bogus range"
if lo:
min = int(lo)
--- 387,391 ----
hi = lo
if not source.match("}"):
! raise error, "bogus range"
if lo:
min = int(lo)
***************
*** 391,400 ****
# FIXME: <fl> check that hi >= lo!
else:
! raise SyntaxError, "not supported"
# figure out which item to repeat
if subpattern:
item = subpattern[-1:]
else:
! raise SyntaxError, "nothing to repeat"
if source.match("?"):
subpattern[-1] = (MIN_REPEAT, (min, max, item))
--- 394,403 ----
# FIXME: <fl> check that hi >= lo!
else:
! raise error, "not supported"
# figure out which item to repeat
if subpattern:
item = subpattern[-1:]
else:
! raise error, "nothing to repeat"
if source.match("?"):
subpattern[-1] = (MIN_REPEAT, (min, max, item))
***************
*** 419,423 ****
char = source.get()
if char is None:
! raise SyntaxError, "unterminated name"
if char == ">":
break
--- 422,426 ----
char = source.get()
if char is None:
! raise error, "unterminated name"
if char == ">":
break
***************
*** 427,437 ****
elif source.match("="):
# named backreference
! raise SyntaxError, "not yet implemented"
!
else:
char = source.get()
if char is None:
! raise SyntaxError, "unexpected end of pattern"
! raise SyntaxError, "unknown specifier: ?P%s" % char
elif source.match(":"):
# non-capturing group
--- 430,439 ----
elif source.match("="):
# named backreference
! raise error, "not yet implemented"
else:
char = source.get()
if char is None:
! raise error, "unexpected end of pattern"
! raise error, "unknown specifier: ?P%s" % char
elif source.match(":"):
# non-capturing group
***************
*** 440,446 ****
# comment
while 1:
! char = source.get()
! if char is None or char == ")":
break
else:
# flags
--- 442,448 ----
# comment
while 1:
! if source.next is None or source.next == ")":
break
+ source.get()
else:
# flags
***************
*** 466,470 ****
b.append(p)
else:
! raise SyntaxError, "group not properly closed"
else:
while 1:
--- 468,472 ----
b.append(p)
else:
! raise error, "group not properly closed"
else:
while 1:
***************
*** 472,476 ****
if char is None or char == ")":
break
! # FIXME: skip characters?
elif this == "^":
--- 474,478 ----
if char is None or char == ")":
break
! raise error, "unknown extension"
elif this == "^":
***************
*** 485,489 ****
else:
! raise SyntaxError, "parser error"
return subpattern
--- 487,491 ----
else:
! raise error, "parser error"
return subpattern
***************
*** 500,504 ****
b.append(p)
elif tail == ")":
! raise SyntaxError, "unbalanced parenthesis"
elif tail is None:
if b:
--- 502,506 ----
b.append(p)
elif tail == ")":
! raise error, "unbalanced parenthesis"
elif tail is None:
if b:
***************
*** 507,514 ****
break
else:
! raise SyntaxError, "bogus characters at end of regular expression"
return p
! def parse_replacement(source, pattern):
# parse 're' replacement string into list of literals and
# group references
--- 509,516 ----
break
else:
! raise error, "bogus characters at end of regular expression"
return p
! def parse_template(source, pattern):
# parse 're' replacement string into list of literals and
# group references
***************
*** 521,533 ****
break # end of replacement string
if this and this[0] == "\\":
! try:
! a(LITERAL, ESCAPES[this])
! except KeyError:
! for char in this:
! a(LITERAL, char)
else:
! a(LITERAL, this)
return p
if __name__ == "__main__":
from pprint import pprint
--- 523,576 ----
break # end of replacement string
if this and this[0] == "\\":
! if this == "\\g":
! name = ""
! if s.match("<"):
! while 1:
! char = s.get()
! if char is None:
! raise error, "unterminated index"
! if char == ">":
! break
! # FIXME: check for valid character
! name = name + char
! if not name:
! raise error, "bad index"
! try:
! index = int(name)
! except ValueError:
! try:
! index = pattern.groupindex[name]
! except KeyError:
! raise IndexError, "unknown index"
! a((MARK, index))
! elif len(this) > 1 and this[1] in DIGITS:
! while s.next in DIGITS:
! this = this + s.get()
! a((MARK, int(this[1:])))
! else:
! try:
! a(ESCAPES[this])
! except KeyError:
! for char in this:
! a((LITERAL, char))
else:
! a((LITERAL, this))
return p
+ def expand_template(template, match):
+ # FIXME: <fl> this is sooooo slow. drop in the slicelist
+ # code instead
+ p = []
+ a = p.append
+ for c, s in template:
+ if c is LITERAL:
+ a(s)
+ elif c is MARK:
+ s = match.group(s)
+ if s is None:
+ raise error, "empty group"
+ a(s)
+ return match.string[:0].join(p)
+
if __name__ == "__main__":
from pprint import pprint
***************
*** 549,553 ****
pass
a = a + 1
! except SyntaxError, v:
print "**", repr(pattern), v
b = b + 1
--- 592,596 ----
pass
a = a + 1
! except error, v:
print "**", repr(pattern), v
b = b + 1
- Previous message: [Python-checkins] CVS: python/dist/src/Modules _sre.c,2.4,2.5
- Next message: [Python-checkins] CVS: python/dist/src/Lib sre.py,1.7,1.8 sre_compile.py,1.5,1.6 sre_constants.py,1.5,1.6 sre_parse.py,1.5,1.6
- Messages sorted by:
[ date ]
[ thread ]
[ subject ]
[ author ]