[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
2000年6月29日 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年06月18日 20:27:10	1.6
--- sre.py	2000年06月29日 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年06月01日 17:39:12	1.4
--- sre_compile.py	2000年06月29日 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年06月01日 17:39:12	1.4
--- sre_constants.py	2000年06月29日 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年06月09日 14:08:07	1.4
--- sre_parse.py	2000年06月29日 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 ]