Skip to content

C
cpython
Commit 8f417748 authored by Andrew M. Kuchling's avatar Andrew M. Kuchling
Browse files
Options

This patch looks large, but it just deletes the ^M characters and 

   untabifies the files.  No actual code changes were made.
parent bd83b7ee
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 482 additions and 482 deletions
Lib/sre_compile.py
View file @ 8f417748
...@@ -26,7 +26,7 @@ from sre_constants import * ...@@ -26,7 +26,7 @@ from sre_constants import *
# find an array type code that matches the engine's code size # find an array type code that matches the engine's code size
for WORDSIZE in "BHil": for WORDSIZE in "BHil":
if len(array.array(WORDSIZE, [0]).tostring()) == _sre.getcodesize(): if len(array.array(WORDSIZE, [0]).tostring()) == _sre.getcodesize():
break break
else: else:
raise RuntimeError, "cannot find a useable array type" raise RuntimeError, "cannot find a useable array type"
...@@ -34,18 +34,18 @@ else: ...@@ -34,18 +34,18 @@ else:
class Code: class Code:
def __init__(self): def __init__(self):
self.data = [] self.data = []
def __len__(self): def __len__(self):
return len(self.data) return len(self.data)
def __getitem__(self, index): def __getitem__(self, index):
return self.data[index] return self.data[index]
def __setitem__(self, index, code): def __setitem__(self, index, code):
self.data[index] = code self.data[index] = code
def append(self, code): def append(self, code):
self.data.append(code) self.data.append(code)
def todata(self): def todata(self):
# print self.data # print self.data
return array.array(WORDSIZE, self.data).tostring() return array.array(WORDSIZE, self.data).tostring()
def _lower(literal): def _lower(literal):
# return _sre._lower(literal) # FIXME # return _sre._lower(literal) # FIXME
...@@ -54,122 +54,122 @@ def _lower(literal): ...@@ -54,122 +54,122 @@ def _lower(literal):
def _compile(code, pattern, flags): def _compile(code, pattern, flags):
append = code.append append = code.append
for op, av in pattern: for op, av in pattern:
if op is ANY: if op is ANY:
if "s" in flags: if "s" in flags:
append(CODES[op]) # any character at all! append(CODES[op]) # any character at all!
else: else:
append(CODES[NOT_LITERAL]) append(CODES[NOT_LITERAL])
append(10) append(10)
elif op in (SUCCESS, FAILURE): elif op in (SUCCESS, FAILURE):
append(CODES[op]) append(CODES[op])
elif op is AT: elif op is AT:
append(CODES[op]) append(CODES[op])
append(POSITIONS[av]) append(POSITIONS[av])
elif op is BRANCH: elif op is BRANCH:
append(CODES[op]) append(CODES[op])
tail = [] tail = []
for av in av[1]: for av in av[1]:
skip = len(code); append(0) skip = len(code); append(0)
_compile(code, av, flags) _compile(code, av, flags)
append(CODES[JUMP]) append(CODES[JUMP])
tail.append(len(code)); append(0) tail.append(len(code)); append(0)
code[skip] = len(code) - skip code[skip] = len(code) - skip
append(0) # end of branch append(0) # end of branch
for tail in tail: for tail in tail:
code[tail] = len(code) - tail code[tail] = len(code) - tail
elif op is CALL: elif op is CALL:
append(CODES[op]) append(CODES[op])
skip = len(code); append(0) skip = len(code); append(0)
_compile(code, av, flags) _compile(code, av, flags)
append(CODES[SUCCESS]) append(CODES[SUCCESS])
code[skip] = len(code) - skip code[skip] = len(code) - skip
elif op is CATEGORY: # not used by current parser elif op is CATEGORY: # not used by current parser
append(CODES[op]) append(CODES[op])
append(CATEGORIES[av]) append(CATEGORIES[av])
elif op is GROUP: elif op is GROUP:
if "i" in flags: if "i" in flags:
append(CODES[MAP_IGNORE[op]]) append(CODES[MAP_IGNORE[op]])
else: else:
append(CODES[op]) append(CODES[op])
append(av) append(av)
elif op is IN: elif op is IN:
if "i" in flags: if "i" in flags:
append(CODES[MAP_IGNORE[op]]) append(CODES[MAP_IGNORE[op]])
def fixup(literal): def fixup(literal):
return ord(_lower(literal)) return ord(_lower(literal))
else: else:
append(CODES[op]) append(CODES[op])
fixup = ord fixup = ord
skip = len(code); append(0) skip = len(code); append(0)
for op, av in av: for op, av in av:
append(CODES[op]) append(CODES[op])
if op is NEGATE: if op is NEGATE:
pass pass
elif op is LITERAL: elif op is LITERAL:
append(fixup(av)) append(fixup(av))
elif op is RANGE: elif op is RANGE:
append(fixup(av[0])) append(fixup(av[0]))
append(fixup(av[1])) append(fixup(av[1]))
elif op is CATEGORY: elif op is CATEGORY:
append(CATEGORIES[av]) append(CATEGORIES[av])
else: else:
raise ValueError, "unsupported set operator" raise ValueError, "unsupported set operator"
append(CODES[FAILURE]) append(CODES[FAILURE])
code[skip] = len(code) - skip code[skip] = len(code) - skip
elif op in (LITERAL, NOT_LITERAL): elif op in (LITERAL, NOT_LITERAL):
if "i" in flags: if "i" in flags:
append(CODES[MAP_IGNORE[op]]) append(CODES[MAP_IGNORE[op]])
append(ord(_lower(av))) append(ord(_lower(av)))
else: else:
append(CODES[op]) append(CODES[op])
append(ord(av)) append(ord(av))
elif op is MARK: elif op is MARK:
append(CODES[op]) append(CODES[op])
append(av) append(av)
elif op in (REPEAT, MIN_REPEAT, MAX_REPEAT): elif op in (REPEAT, MIN_REPEAT, MAX_REPEAT):
lo, hi = av[2].getwidth() lo, hi = av[2].getwidth()
if lo == 0: if lo == 0:
raise SyntaxError, "cannot repeat zero-width items" raise SyntaxError, "cannot repeat zero-width items"
if lo == hi == 1 and op is MAX_REPEAT: if lo == hi == 1 and op is MAX_REPEAT:
append(CODES[MAX_REPEAT_ONE]) append(CODES[MAX_REPEAT_ONE])
skip = len(code); append(0) skip = len(code); append(0)
append(av[0]) append(av[0])
append(av[1]) append(av[1])
_compile(code, av[2], flags) _compile(code, av[2], flags)
append(CODES[SUCCESS]) append(CODES[SUCCESS])
code[skip] = len(code) - skip code[skip] = len(code) - skip
else: else:
append(CODES[op]) append(CODES[op])
skip = len(code); append(0) skip = len(code); append(0)
append(av[0]) append(av[0])
append(av[1]) append(av[1])
_compile(code, av[2], flags) _compile(code, av[2], flags)
if op is MIN_REPEAT: if op is MIN_REPEAT:
append(CODES[MIN_UNTIL]) append(CODES[MIN_UNTIL])
else: else:
# FIXME: MAX_REPEAT PROBABLY DOESN'T WORK (?) # FIXME: MAX_REPEAT PROBABLY DOESN'T WORK (?)
append(CODES[MAX_UNTIL]) append(CODES[MAX_UNTIL])
code[skip] = len(code) - skip code[skip] = len(code) - skip
elif op is SUBPATTERN: elif op is SUBPATTERN:
## group = av[0] ## group = av[0]
## if group: ## if group:
## append(CODES[MARK]) ## append(CODES[MARK])
## append((group-1)*2) ## append((group-1)*2)
_compile(code, av[1], flags) _compile(code, av[1], flags)
## if group: ## if group:
## append(CODES[MARK]) ## append(CODES[MARK])
## append((group-1)*2+1) ## append((group-1)*2+1)
else: else:
raise ValueError, ("unsupported operand type", op) raise ValueError, ("unsupported operand type", op)
def compile(p, flags=()): def compile(p, flags=()):
# convert pattern list to internal format # convert pattern list to internal format
if type(p) is type(""): if type(p) is type(""):
import sre_parse import sre_parse
pattern = p pattern = p
p = sre_parse.parse(p) p = sre_parse.parse(p)
else: else:
pattern = None pattern = None
# print p.getwidth() # print p.getwidth()
# print p # print p
code = Code() code = Code()
...@@ -178,10 +178,10 @@ def compile(p, flags=()): ...@@ -178,10 +178,10 @@ def compile(p, flags=()):
# print list(code.data) # print list(code.data)
data = code.todata() data = code.todata()
if 0: # debugging if 0: # debugging
print print
print "-" * 68 print "-" * 68
import sre_disasm import sre_disasm
sre_disasm.disasm(data) sre_disasm.disasm(data)
print "-" * 68 print "-" * 68
# print len(data), p.pattern.groups, len(p.pattern.groupdict) # print len(data), p.pattern.groups, len(p.pattern.groupdict)
return _sre.compile(pattern, data, p.pattern.groups-1, p.pattern.groupdict) return _sre.compile(pattern, data, p.pattern.groups-1, p.pattern.groupdict)
Lib/sre_constants.py
View file @ 8f417748
...@@ -126,6 +126,6 @@ if __name__ == "__main__": ...@@ -126,6 +126,6 @@ if __name__ == "__main__":
f = open("sre_constants.h", "w") f = open("sre_constants.h", "w")
f.write("/* generated by sre_constants.py */\n") f.write("/* generated by sre_constants.py */\n")
for k, v in items: for k, v in items:
f.write("#define SRE_OP_" + string.upper(k) + " " + str(v) + "\n") f.write("#define SRE_OP_" + string.upper(k) + " " + str(v) + "\n")
f.close() f.close()
print "done" print "done"
Lib/sre_parse.py
View file @ 8f417748
This diff is collapsed.
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7