Skip to content

C
cpython
Commit 90a07913 authored by Fredrik Lundh's avatar Fredrik Lundh
Browse files
Options

- pedantic: make sure "python -t" doesn't complain...

parent df02d0b3
Hide whitespace changes
Inline Side-by-side
Showing with 587 additions and 587 deletions
Lib/sre.py
View file @ 90a07913
......@@ -98,7 +98,7 @@ def _subn(pattern, template, string, count=0):
if callable(template):
filter = template
else:
template = sre_parse.parse_template(template, pattern)
template = sre_parse.parse_template(template, pattern)
def filter(match, template=template):
return sre_parse.expand_template(template, match)
n = i = 0
......@@ -109,11 +109,11 @@ def _subn(pattern, template, string, count=0):
m = c.search()
if not m:
break
b, e = m.span()
b, e = m.span()
if i < b:
append(string[i:b])
append(filter(m))
i = e
i = e
n = n + 1
append(string[i:])
return string[:0].join(s), n
......@@ -130,15 +130,15 @@ def _split(pattern, string, maxsplit=0):
m = c.search()
if not m:
break
b, e = m.span()
if b == e:
if i >= len(string):
break
continue
b, e = m.span()
if b == e:
if i >= len(string):
break
continue
append(string[i:b])
if g and b != e:
extend(m.groups())
i = e
if g and b != e:
extend(m.groups())
i = e
n = n + 1
append(string[i:])
return s
Lib/sre_compile.py
View file @ 90a07913
......@@ -18,7 +18,7 @@ from sre_constants import *
# find an array type code that matches the engine's code size
for WORDSIZE in "BHil":
if len(array.array(WORDSIZE, [0]).tostring()) == _sre.getcodesize():
break
break
else:
raise RuntimeError, "cannot find a useable array type"
......@@ -26,132 +26,132 @@ def _compile(code, pattern, flags):
# internal: compile a (sub)pattern
emit = code.append
for op, av in pattern:
if op is ANY:
if flags & SRE_FLAG_DOTALL:
emit(OPCODES[op])
else:
emit(OPCODES[CATEGORY])
emit(CHCODES[CATEGORY_NOT_LINEBREAK])
elif op in (SUCCESS, FAILURE):
emit(OPCODES[op])
elif op is AT:
emit(OPCODES[op])
if flags & SRE_FLAG_MULTILINE:
emit(ATCODES[AT_MULTILINE[av]])
else:
emit(ATCODES[av])
elif op is BRANCH:
emit(OPCODES[op])
tail = []
for av in av[1]:
skip = len(code); emit(0)
_compile(code, av, flags)
emit(OPCODES[JUMP])
tail.append(len(code)); emit(0)
code[skip] = len(code) - skip
emit(0) # end of branch
for tail in tail:
code[tail] = len(code) - tail
elif op is CALL:
emit(OPCODES[op])
skip = len(code); emit(0)
_compile(code, av, flags)
emit(OPCODES[SUCCESS])
code[skip] = len(code) - skip
elif op is CATEGORY:
emit(OPCODES[op])
if flags & SRE_FLAG_LOCALE:
emit(CHCODES[CH_LOCALE[av]])
elif flags & SRE_FLAG_UNICODE:
emit(CHCODES[CH_UNICODE[av]])
else:
emit(CHCODES[av])
elif op is GROUP:
if flags & SRE_FLAG_IGNORECASE:
emit(OPCODES[OP_IGNORE[op]])
else:
emit(OPCODES[op])
emit(av-1)
elif op is IN:
if flags & SRE_FLAG_IGNORECASE:
emit(OPCODES[OP_IGNORE[op]])
def fixup(literal, flags=flags):
return _sre.getlower(ord(literal), flags)
else:
emit(OPCODES[op])
fixup = ord
skip = len(code); emit(0)
for op, av in av:
emit(OPCODES[op])
if op is NEGATE:
pass
elif op is LITERAL:
emit(fixup(av))
elif op is RANGE:
emit(fixup(av[0]))
emit(fixup(av[1]))
elif op is CATEGORY:
if flags & SRE_FLAG_LOCALE:
emit(CHCODES[CH_LOCALE[av]])
elif flags & SRE_FLAG_UNICODE:
emit(CHCODES[CH_UNICODE[av]])
else:
emit(CHCODES[av])
else:
raise error, "internal: unsupported set operator"
emit(OPCODES[FAILURE])
code[skip] = len(code) - skip
elif op in (LITERAL, NOT_LITERAL):
if flags & SRE_FLAG_IGNORECASE:
emit(OPCODES[OP_IGNORE[op]])
else:
emit(OPCODES[op])
emit(ord(av))
elif op is MARK:
emit(OPCODES[op])
emit(av)
elif op in (REPEAT, MIN_REPEAT, MAX_REPEAT):
if flags & SRE_FLAG_TEMPLATE:
emit(OPCODES[REPEAT])
skip = len(code); emit(0)
emit(av[0])
emit(av[1])
_compile(code, av[2], flags)
emit(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)
emit(OPCODES[MAX_REPEAT_ONE])
skip = len(code); emit(0)
emit(av[0])
emit(av[1])
_compile(code, av[2], flags)
emit(OPCODES[SUCCESS])
code[skip] = len(code) - skip
else:
emit(OPCODES[op])
skip = len(code); emit(0)
emit(av[0])
emit(av[1])
_compile(code, av[2], flags)
emit(OPCODES[SUCCESS])
code[skip] = len(code) - skip
elif op is SUBPATTERN:
group = av[0]
if group:
emit(OPCODES[MARK])
emit((group-1)*2)
_compile(code, av[1], flags)
if group:
emit(OPCODES[MARK])
emit((group-1)*2+1)
else:
raise ValueError, ("unsupported operand type", op)
if op is ANY:
if flags & SRE_FLAG_DOTALL:
emit(OPCODES[op])
else:
emit(OPCODES[CATEGORY])
emit(CHCODES[CATEGORY_NOT_LINEBREAK])
elif op in (SUCCESS, FAILURE):
emit(OPCODES[op])
elif op is AT:
emit(OPCODES[op])
if flags & SRE_FLAG_MULTILINE:
emit(ATCODES[AT_MULTILINE[av]])
else:
emit(ATCODES[av])
elif op is BRANCH:
emit(OPCODES[op])
tail = []
for av in av[1]:
skip = len(code); emit(0)
_compile(code, av, flags)
emit(OPCODES[JUMP])
tail.append(len(code)); emit(0)
code[skip] = len(code) - skip
emit(0) # end of branch
for tail in tail:
code[tail] = len(code) - tail
elif op is CALL:
emit(OPCODES[op])
skip = len(code); emit(0)
_compile(code, av, flags)
emit(OPCODES[SUCCESS])
code[skip] = len(code) - skip
elif op is CATEGORY:
emit(OPCODES[op])
if flags & SRE_FLAG_LOCALE:
emit(CHCODES[CH_LOCALE[av]])
elif flags & SRE_FLAG_UNICODE:
emit(CHCODES[CH_UNICODE[av]])
else:
emit(CHCODES[av])
elif op is GROUP:
if flags & SRE_FLAG_IGNORECASE:
emit(OPCODES[OP_IGNORE[op]])
else:
emit(OPCODES[op])
emit(av-1)
elif op is IN:
if flags & SRE_FLAG_IGNORECASE:
emit(OPCODES[OP_IGNORE[op]])
def fixup(literal, flags=flags):
return _sre.getlower(ord(literal), flags)
else:
emit(OPCODES[op])
fixup = ord
skip = len(code); emit(0)
for op, av in av:
emit(OPCODES[op])
if op is NEGATE:
pass
elif op is LITERAL:
emit(fixup(av))
elif op is RANGE:
emit(fixup(av[0]))
emit(fixup(av[1]))
elif op is CATEGORY:
if flags & SRE_FLAG_LOCALE:
emit(CHCODES[CH_LOCALE[av]])
elif flags & SRE_FLAG_UNICODE:
emit(CHCODES[CH_UNICODE[av]])
else:
emit(CHCODES[av])
else:
raise error, "internal: unsupported set operator"
emit(OPCODES[FAILURE])
code[skip] = len(code) - skip
elif op in (LITERAL, NOT_LITERAL):
if flags & SRE_FLAG_IGNORECASE:
emit(OPCODES[OP_IGNORE[op]])
else:
emit(OPCODES[op])
emit(ord(av))
elif op is MARK:
emit(OPCODES[op])
emit(av)
elif op in (REPEAT, MIN_REPEAT, MAX_REPEAT):
if flags & SRE_FLAG_TEMPLATE:
emit(OPCODES[REPEAT])
skip = len(code); emit(0)
emit(av[0])
emit(av[1])
_compile(code, av[2], flags)
emit(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)
emit(OPCODES[MAX_REPEAT_ONE])
skip = len(code); emit(0)
emit(av[0])
emit(av[1])
_compile(code, av[2], flags)
emit(OPCODES[SUCCESS])
code[skip] = len(code) - skip
else:
emit(OPCODES[op])
skip = len(code); emit(0)
emit(av[0])
emit(av[1])
_compile(code, av[2], flags)
emit(OPCODES[SUCCESS])
code[skip] = len(code) - skip
elif op is SUBPATTERN:
group = av[0]
if group:
emit(OPCODES[MARK])
emit((group-1)*2)
_compile(code, av[1], flags)
if group:
emit(OPCODES[MARK])
emit((group-1)*2+1)
else:
raise ValueError, ("unsupported operand type", op)
def _compile_info(code, pattern, flags):
# internal: compile an info block. in the current version,
......@@ -159,15 +159,15 @@ def _compile_info(code, pattern, flags):
# if any
lo, hi = pattern.getwidth()
if lo == 0:
return # not worth it
return # not worth it
# look for a literal prefix
prefix = []
if not (flags & SRE_FLAG_IGNORECASE):
for op, av in pattern.data:
if op is LITERAL:
prefix.append(ord(av))
else:
break
for op, av in pattern.data:
if op is LITERAL:
prefix.append(ord(av))
else:
break
# add an info block
emit = code.append
emit(OPCODES[INFO])
......@@ -175,25 +175,25 @@ def _compile_info(code, pattern, flags):
# literal flag
mask = 0
if len(prefix) == len(pattern.data):
mask = 1
mask = 1
emit(mask)
# pattern length
emit(lo)
if hi < 32768:
emit(hi)
emit(hi)
else:
emit(0)
emit(0)
# add literal prefix
emit(len(prefix))
if prefix:
code.extend(prefix)
# generate overlap table
table = [-1] + ([0]*len(prefix))
for i in range(len(prefix)):
table[i+1] = table[i]+1
while table[i+1] > 0 and prefix[i] != prefix[table[i+1]-1]:
table[i+1] = table[table[i+1]-1]+1
code.extend(table[1:]) # don't store first entry
code.extend(prefix)
# generate overlap table
table = [-1] + ([0]*len(prefix))
for i in range(len(prefix)):
table[i+1] = table[i]+1
while table[i+1] > 0 and prefix[i] != prefix[table[i+1]-1]:
table[i+1] = table[table[i+1]-1]+1
code.extend(table[1:]) # don't store first entry
code[skip] = len(code) - skip
def compile(p, flags=0):
......@@ -201,11 +201,11 @@ def compile(p, flags=0):
# compile, as necessary
if type(p) in (type(""), type(u"")):
import sre_parse
pattern = p
p = sre_parse.parse(p)
import sre_parse
pattern = p
p = sre_parse.parse(p)
else:
pattern = None
pattern = None
flags = p.pattern.flags | flags
code = []
......@@ -220,10 +220,10 @@ def compile(p, flags=0):
# FIXME: <fl> get rid of this limitation!
assert p.pattern.groups <= 100,\
"sorry, but this version only supports 100 named groups"
"sorry, but this version only supports 100 named groups"
return _sre.compile(
pattern, flags,
array.array(WORDSIZE, code).tostring(),
p.pattern.groups-1, p.pattern.groupdict
)
pattern, flags,
array.array(WORDSIZE, code).tostring(),
p.pattern.groups-1, p.pattern.groupdict
)
Lib/sre_parse.py
View file @ 90a07913
......@@ -67,106 +67,106 @@ FLAGS = {
class State:
def __init__(self):
self.flags = 0
self.groups = 1
self.groupdict = {}
self.flags = 0
self.groups = 1
self.groupdict = {}
def getgroup(self, name=None):
gid = self.groups
self.groups = gid + 1
if name:
self.groupdict[name] = gid
return gid
gid = self.groups
self.groups = gid + 1
if name:
self.groupdict[name] = gid
return gid
class SubPattern:
# a subpattern, in intermediate form
def __init__(self, pattern, data=None):
self.pattern = pattern
if not data:
data = []
self.data = data
self.width = None
self.pattern = pattern
if not data:
data = []
self.data = data
self.width = None
def __repr__(self):
return repr(self.data)
return repr(self.data)
def __len__(self):
return len(self.data)
return len(self.data)
def __delitem__(self, index):
del self.data[index]
del self.data[index]
def __getitem__(self, index):
return self.data[index]
return self.data[index]
def __setitem__(self, index, code):
self.data[index] = code
self.data[index] = code
def __getslice__(self, start, stop):
return SubPattern(self.pattern, self.data[start:stop])
return SubPattern(self.pattern, self.data[start:stop])
def insert(self, index, code):
self.data.insert(index, code)
self.data.insert(index, code)
def append(self, code):
self.data.append(code)
self.data.append(code)
def getwidth(self):
# determine the width (min, max) for this subpattern
if self.width:
return self.width
lo = hi = 0L
for op, av in self.data:
if op is BRANCH:
l = sys.maxint
h = 0
for av in av[1]:
i, j = av.getwidth()
l = min(l, i)
h = min(h, j)
lo = lo + i
hi = hi + j
elif op is CALL:
i, j = av.getwidth()
lo = lo + i
hi = hi + j
elif op is SUBPATTERN:
i, j = av[1].getwidth()
lo = lo + i
hi = hi + j
elif op in (MIN_REPEAT, MAX_REPEAT):
i, j = av[2].getwidth()
lo = lo + long(i) * av[0]
hi = hi + long(j) * av[1]
elif op in (ANY, RANGE, IN, LITERAL, NOT_LITERAL, CATEGORY):
lo = lo + 1
hi = hi + 1
elif op == SUCCESS:
break
self.width = int(min(lo, sys.maxint)), int(min(hi, sys.maxint))
return self.width
# determine the width (min, max) for this subpattern
if self.width:
return self.width
lo = hi = 0L
for op, av in self.data:
if op is BRANCH:
l = sys.maxint
h = 0
for av in av[1]:
i, j = av.getwidth()
l = min(l, i)
h = min(h, j)
lo = lo + i
hi = hi + j
elif op is CALL:
i, j = av.getwidth()
lo = lo + i
hi = hi + j
elif op is SUBPATTERN:
i, j = av[1].getwidth()
lo = lo + i
hi = hi + j
elif op in (MIN_REPEAT, MAX_REPEAT):
i, j = av[2].getwidth()
lo = lo + long(i) * av[0]
hi = hi + long(j) * av[1]
elif op in (ANY, RANGE, IN, LITERAL, NOT_LITERAL, CATEGORY):
lo = lo + 1
hi = hi + 1
elif op == SUCCESS:
break
self.width = int(min(lo, sys.maxint)), int(min(hi, sys.maxint))
return self.width
class Tokenizer:
def __init__(self, string):
self.index = 0
self.string = string
self.next = self.__next()
self.index = 0
self.string = string
self.next = self.__next()
def __next(self):
if self.index >= len(self.string):
return None
char = self.string[self.index]
if char[0] == "\\":
try:
c = self.string[self.index + 1]
except IndexError:
raise error, "bogus escape"
char = char + c
self.index = self.index + len(char)
return char
if self.index >= len(self.string):
return None
char = self.string[self.index]
if char[0] == "\\":
try:
c = self.string[self.index + 1]
except IndexError:
raise error, "bogus escape"
char = char + c
self.index = self.index + len(char)
return char
def match(self, char):
if char == self.next:
self.next = self.__next()
return 1
return 0
if char == self.next:
self.next = self.__next()
return 1
return 0
def match_set(self, set):
if self.next and self.next in set:
self.next = self.__next()
return 1
return 0
if self.next and self.next in set:
self.next = self.__next()
return 1
return 0
def get(self):
this = self.next
self.next = self.__next()
return this
this = self.next
self.next = self.__next()
return this
def isident(char):
return "a" <= char <= "z" or "A" <= char <= "Z" or char == "_"
......@@ -180,83 +180,83 @@ def isname(name):
# expression instead, but I seem to have certain bootstrapping
# problems here ;-)
if not isident(name[0]):
return 0
return 0
for char in name:
if not isident(char) and not isdigit(char):
return 0
if not isident(char) and not isdigit(char):
return 0
return 1
def _group(escape, groups):
# check if the escape string represents a valid group
try:
group = int(escape[1:])
if group and group < groups:
return group
group = int(escape[1:])
if group and group < groups:
return group
except ValueError:
pass
pass
return None # not a valid group
def _class_escape(source, escape):
# handle escape code inside character class
code = ESCAPES.get(escape)
if code:
return code
return code
code = CATEGORIES.get(escape)
if code:
return code
return code
try:
if escape[1:2] == "x":
while source.next in HEXDIGITS:
escape = escape + source.get()
escape = escape[2:]
# FIXME: support unicode characters!
return LITERAL, chr(int(escape[-4:], 16) & 0xff)
elif str(escape[1:2]) in OCTDIGITS:
while source.next in OCTDIGITS:
escape = escape + source.get()
escape = escape[1:]
# FIXME: support unicode characters!
return LITERAL, chr(int(escape[-6:], 8) & 0xff)
if len(escape) == 2:
return LITERAL, escape[1]
if escape[1:2] == "x":
while source.next in HEXDIGITS:
escape = escape + source.get()
escape = escape[2:]
# FIXME: support unicode characters!
return LITERAL, chr(int(escape[-4:], 16) & 0xff)
elif str(escape[1:2]) in OCTDIGITS:
while source.next in OCTDIGITS:
escape = escape + source.get()
escape = escape[1:]
# FIXME: support unicode characters!
return LITERAL, chr(int(escape[-6:], 8) & 0xff)
if len(escape) == 2:
return LITERAL, escape[1]
except ValueError:
pass
pass
raise error, "bogus escape: %s" % repr(escape)
def _escape(source, escape, state):
# handle escape code in expression
code = CATEGORIES.get(escape)
if code:
return code
return code
code = ESCAPES.get(escape)
if code:
return code
return code
try:
if escape[1:2] == "x":
while source.next in HEXDIGITS:
escape = escape + source.get()
escape = escape[2:]
# FIXME: support unicode characters!
return LITERAL, chr(int(escape[-4:], 16) & 0xff)
elif escape[1:2] in DIGITS:
while 1:
group = _group(escape, state.groups)
if group:
if (not source.next or
not _group(escape + source.next, state.groups)):
return GROUP, group
escape = escape + source.get()
elif source.next in OCTDIGITS:
escape = escape + source.get()
else:
break
escape = escape[1:]
# FIXME: support unicode characters!
return LITERAL, chr(int(escape[-6:], 8) & 0xff)
if len(escape) == 2:
return LITERAL, escape[1]
if escape[1:2] == "x":
while source.next in HEXDIGITS:
escape = escape + source.get()
escape = escape[2:]
# FIXME: support unicode characters!
return LITERAL, chr(int(escape[-4:], 16) & 0xff)
elif escape[1:2] in DIGITS:
while 1:
group = _group(escape, state.groups)
if group:
if (not source.next or
not _group(escape + source.next, state.groups)):
return GROUP, group
escape = escape + source.get()
elif source.next in OCTDIGITS:
escape = escape + source.get()
else:
break
escape = escape[1:]
# FIXME: support unicode characters!
return LITERAL, chr(int(escape[-6:], 8) & 0xff)
if len(escape) == 2:
return LITERAL, escape[1]
except ValueError:
pass
pass
raise error, "bogus escape: %s" % repr(escape)
......@@ -268,35 +268,35 @@ def _branch(pattern, items):
# check if all items share a common prefix
while 1:
prefix = None
for item in items:
if not item:
break
if prefix is None:
prefix = item[0]
elif item[0] != prefix:
break
else:
# all subitems start with a common "prefix".
# move it out of the branch
for item in items:
del item[0]
subpattern.append(prefix)
continue # check next one
break
prefix = None
for item in items:
if not item:
break
if prefix is None:
prefix = item[0]
elif item[0] != prefix:
break
else:
# all subitems start with a common "prefix".
# move it out of the branch
for item in items:
del item[0]
subpattern.append(prefix)
continue # check next one
break
# check if the branch can be replaced by a character set
for item in items:
if len(item) != 1 or item[0][0] != LITERAL:
break
if len(item) != 1 or item[0][0] != LITERAL:
break
else:
# we can store this as a character set instead of a
# branch (FIXME: use a range if possible)
set = []
for item in items:
set.append(item[0])
subpattern.append((IN, set))
return subpattern
# we can store this as a character set instead of a
# branch (FIXME: use a range if possible)
set = []
for item in items:
set.append(item[0])
subpattern.append((IN, set))
return subpattern
subpattern.append((BRANCH, (None, items)))
return subpattern
......@@ -309,197 +309,197 @@ def _parse(source, state, flags=0):
while 1:
if source.next in ("|", ")"):
break # end of subpattern
this = source.get()
if this is None:
break # end of pattern
if state.flags & SRE_FLAG_VERBOSE:
# skip whitespace and comments
if this in WHITESPACE:
continue
if this == "#":
while 1:
this = source.get()
if this in (None, "\n"):
break
continue
if this and this[0] not in SPECIAL_CHARS:
subpattern.append((LITERAL, this))
elif this == "[":
# character set
set = []
## if source.match(":"):
## pass # handle character classes
if source.match("^"):
set.append((NEGATE, None))
# check remaining characters
start = set[:]
while 1:
this = source.get()
if this == "]" and set != start:
break
elif this and this[0] == "\\":
code1 = _class_escape(source, this)
elif this:
code1 = LITERAL, this
else:
raise error, "unexpected end of regular expression"
if source.match("-"):
# potential range
this = source.get()
if this == "]":
set.append(code1)
set.append((LITERAL, "-"))
break
else:
if this[0] == "\\":
code2 = _class_escape(source, this)
else:
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:
if code1[0] is IN:
code1 = code1[1][0]
set.append(code1)
# FIXME: <fl> move set optimization to compiler!
if len(set)==1 and set[0][0] is LITERAL:
subpattern.append(set[0]) # optimization
elif len(set)==2 and set[0][0] is NEGATE and set[1][0] is LITERAL:
subpattern.append((NOT_LITERAL, set[1][1])) # optimization
else:
# FIXME: <fl> add charmap optimization
subpattern.append((IN, set))
elif this and this[0] in REPEAT_CHARS:
# repeat previous item
if this == "?":
min, max = 0, 1
elif this == "*":
min, max = 0, MAXREPEAT
elif this == "+":
min, max = 1, MAXREPEAT
elif this == "{":
min, max = 0, MAXREPEAT
lo = hi = ""
while source.next in DIGITS:
lo = lo + source.get()
if source.match(","):
while source.next in DIGITS:
hi = hi + source.get()
else:
hi = lo
if not source.match("}"):
raise error, "bogus range"
if lo:
min = int(lo)
if hi:
max = int(hi)
# 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))
else:
subpattern[-1] = (MAX_REPEAT, (min, max, item))
elif this == ".":
subpattern.append((ANY, None))
elif this == "(":
group = 1
name = None
if source.match("?"):
group = 0
# options
if source.match("P"):
# python extensions
if source.match("<"):
# named group: skip forward to end of name
name = ""
while 1:
char = source.get()
if char is None:
raise error, "unterminated name"
if char == ">":
break
name = name + char
group = 1
if not isname(name):
raise error, "illegal character in group name"
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
group = 2
elif source.match("#"):
# comment
while 1:
if source.next is None or source.next == ")":
break
source.get()
else:
# flags
while FLAGS.has_key(source.next):
state.flags = state.flags | FLAGS[source.get()]
if group:
# parse group contents
b = []
if group == 2:
# anonymous group
group = None
else:
group = state.getgroup(name)
while 1:
p = _parse(source, state, flags)
if source.match(")"):
if b:
b.append(p)
p = _branch(state, b)
subpattern.append((SUBPATTERN, (group, p)))
break
elif source.match("|"):
b.append(p)
else:
raise error, "group not properly closed"
else:
while 1:
char = source.get()
if char is None or char == ")":
break
raise error, "unknown extension"
elif this == "^":
subpattern.append((AT, AT_BEGINNING))
elif this == "$":
subpattern.append((AT, AT_END))
elif this and this[0] == "\\":
code = _escape(source, this, state)
subpattern.append(code)
else:
raise error, "parser error"
if source.next in ("|", ")"):
break # end of subpattern
this = source.get()
if this is None:
break # end of pattern
if state.flags & SRE_FLAG_VERBOSE:
# skip whitespace and comments
if this in WHITESPACE:
continue
if this == "#":
while 1:
this = source.get()
if this in (None, "\n"):
break
continue
if this and this[0] not in SPECIAL_CHARS:
subpattern.append((LITERAL, this))
elif this == "[":
# character set
set = []
## if source.match(":"):
## pass # handle character classes
if source.match("^"):
set.append((NEGATE, None))
# check remaining characters
start = set[:]
while 1:
this = source.get()
if this == "]" and set != start:
break
elif this and this[0] == "\\":
code1 = _class_escape(source, this)
elif this:
code1 = LITERAL, this
else:
raise error, "unexpected end of regular expression"
if source.match("-"):
# potential range
this = source.get()
if this == "]":
set.append(code1)
set.append((LITERAL, "-"))
break
else:
if this[0] == "\\":
code2 = _class_escape(source, this)
else:
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:
if code1[0] is IN:
code1 = code1[1][0]
set.append(code1)
# FIXME: <fl> move set optimization to compiler!
if len(set)==1 and set[0][0] is LITERAL:
subpattern.append(set[0]) # optimization
elif len(set)==2 and set[0][0] is NEGATE and set[1][0] is LITERAL:
subpattern.append((NOT_LITERAL, set[1][1])) # optimization
else:
# FIXME: <fl> add charmap optimization
subpattern.append((IN, set))
elif this and this[0] in REPEAT_CHARS:
# repeat previous item
if this == "?":
min, max = 0, 1
elif this == "*":
min, max = 0, MAXREPEAT
elif this == "+":
min, max = 1, MAXREPEAT
elif this == "{":
min, max = 0, MAXREPEAT
lo = hi = ""
while source.next in DIGITS:
lo = lo + source.get()
if source.match(","):
while source.next in DIGITS:
hi = hi + source.get()
else:
hi = lo
if not source.match("}"):
raise error, "bogus range"
if lo:
min = int(lo)
if hi:
max = int(hi)
# 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))
else:
subpattern[-1] = (MAX_REPEAT, (min, max, item))
elif this == ".":
subpattern.append((ANY, None))
elif this == "(":
group = 1
name = None
if source.match("?"):
group = 0
# options
if source.match("P"):
# python extensions
if source.match("<"):
# named group: skip forward to end of name
name = ""
while 1:
char = source.get()
if char is None:
raise error, "unterminated name"
if char == ">":
break
name = name + char
group = 1
if not isname(name):
raise error, "illegal character in group name"
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
group = 2
elif source.match("#"):
# comment
while 1:
if source.next is None or source.next == ")":
break
source.get()
else:
# flags
while FLAGS.has_key(source.next):
state.flags = state.flags | FLAGS[source.get()]
if group:
# parse group contents
b = []
if group == 2:
# anonymous group
group = None
else:
group = state.getgroup(name)
while 1:
p = _parse(source, state, flags)
if source.match(")"):
if b:
b.append(p)
p = _branch(state, b)
subpattern.append((SUBPATTERN, (group, p)))
break
elif source.match("|"):
b.append(p)
else:
raise error, "group not properly closed"
else:
while 1:
char = source.get()
if char is None or char == ")":
break
raise error, "unknown extension"
elif this == "^":
subpattern.append((AT, AT_BEGINNING))
elif this == "$":
subpattern.append((AT, AT_END))
elif this and this[0] == "\\":
code = _escape(source, this, state)
subpattern.append(code)
else:
raise error, "parser error"
return subpattern
......@@ -509,19 +509,19 @@ def parse(pattern, flags=0):
state = State()
b = []
while 1:
p = _parse(source, state, flags)
tail = source.get()
if tail == "|":
b.append(p)
elif tail == ")":
raise error, "unbalanced parenthesis"
elif tail is None:
if b:
b.append(p)
p = _branch(state, b)
break
else:
raise error, "bogus characters at end of regular expression"
p = _parse(source, state, flags)
tail = source.get()
if tail == "|":
b.append(p)
elif tail == ")":
raise error, "unbalanced parenthesis"
elif tail is None:
if b:
b.append(p)
p = _branch(state, b)
break
else:
raise error, "bogus characters at end of regular expression"
return p
def parse_template(source, pattern):
......@@ -531,59 +531,59 @@ def parse_template(source, pattern):
p = []
a = p.append
while 1:
this = s.get()
if this is None:
break # end of replacement string
if this and this[0] == "\\":
# group
if this == "\\g":
name = ""
if s.match("<"):
while 1:
char = s.get()
if char is None:
raise error, "unterminated group name"
if char == ">":
break
name = name + char
if not name:
raise error, "bad group name"
try:
index = int(name)
except ValueError:
if not isname(name):
raise error, "illegal character in group name"
try:
index = pattern.groupindex[name]
except KeyError:
raise IndexError, "unknown group name"
a((MARK, index))
elif len(this) > 1 and this[1] in DIGITS:
code = None
while 1:
group = _group(this, pattern.groups+1)
if group:
if (not s.next or
not _group(this + s.next, pattern.groups+1)):
code = MARK, int(group)
break
elif s.next in OCTDIGITS:
this = this + s.get()
else:
break
if not code:
this = this[1:]
# FIXME: support unicode characters!
code = LITERAL, chr(int(this[-6:], 8) & 0xff)
a(code)
else:
try:
a(ESCAPES[this])
except KeyError:
for c in this:
a((LITERAL, c))
else:
a((LITERAL, this))
this = s.get()
if this is None:
break # end of replacement string
if this and this[0] == "\\":
# group
if this == "\\g":
name = ""
if s.match("<"):
while 1:
char = s.get()
if char is None:
raise error, "unterminated group name"
if char == ">":
break
name = name + char
if not name:
raise error, "bad group name"
try:
index = int(name)
except ValueError:
if not isname(name):
raise error, "illegal character in group name"
try:
index = pattern.groupindex[name]
except KeyError:
raise IndexError, "unknown group name"
a((MARK, index))
elif len(this) > 1 and this[1] in DIGITS:
code = None
while 1:
group = _group(this, pattern.groups+1)
if group:
if (not s.next or
not _group(this + s.next, pattern.groups+1)):
code = MARK, int(group)
break
elif s.next in OCTDIGITS:
this = this + s.get()
else:
break
if not code:
this = this[1:]
# FIXME: support unicode characters!
code = LITERAL, chr(int(this[-6:], 8) & 0xff)
a(code)
else:
try:
a(ESCAPES[this])
except KeyError:
for c in this:
a((LITERAL, c))
else:
a((LITERAL, this))
return p
def expand_template(template, match):
......@@ -592,11 +592,11 @@ def expand_template(template, match):
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)
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)
Lib/test/test_sre.py
View file @ 90a07913
# FIXME: this is basically test_re.py, with a few
# FIXME: this is basically test_re.py, with a few minor changes
import sys
sys.path=['.']+sys.path
......@@ -337,7 +337,7 @@ for t in tests:
print repr(repl)+' should be '+repr(expected)
else:
print '=== Failed incorrectly', t
continue
continue
# Try the match on a unicode string, and check that it
# still succeeds.
......@@ -359,9 +359,9 @@ for t in tests:
if pattern[:2]!='\\B' and pattern[-2:]!='\\B':
obj=sre.compile(pattern)
result=obj.search(s, result.start(0), result.end(0)+1)
if result==None:
print '=== Failed on range-limited match', t
result=obj.search(s, result.start(0), result.end(0)+1)
if result==None:
print '=== Failed on range-limited match', t
# Try the match with IGNORECASE enabled, and check that it
# still succeeds.
......
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