mirror of
https://github.com/python/cpython.git
synced 2024-11-26 03:14:27 +08:00
660 lines
21 KiB
Python
660 lines
21 KiB
Python
#
|
|
# Secret Labs' Regular Expression Engine
|
|
#
|
|
# convert re-style regular expression to sre pattern
|
|
#
|
|
# Copyright (c) 1998-2000 by Secret Labs AB. All rights reserved.
|
|
#
|
|
# Portions of this engine have been developed in cooperation with
|
|
# CNRI. Hewlett-Packard provided funding for 2.0 integration and
|
|
# other compatibility work.
|
|
#
|
|
|
|
import string, sys
|
|
|
|
import _sre
|
|
|
|
from sre_constants import *
|
|
|
|
MAXREPEAT = 65535
|
|
|
|
# FIXME: the following might change in 2.0 final. but for now, this
|
|
# seems to be the best way to be compatible with 1.5.2
|
|
CHARMASK = 0xff
|
|
|
|
SPECIAL_CHARS = ".\\[{()*+?^$|"
|
|
REPEAT_CHARS = "*+?{"
|
|
|
|
DIGITS = tuple(string.digits)
|
|
|
|
OCTDIGITS = tuple("01234567")
|
|
HEXDIGITS = tuple("0123456789abcdefABCDEF")
|
|
|
|
WHITESPACE = tuple(string.whitespace)
|
|
|
|
ESCAPES = {
|
|
r"\a": (LITERAL, 7),
|
|
r"\b": (LITERAL, 8),
|
|
r"\f": (LITERAL, 12),
|
|
r"\n": (LITERAL, 10),
|
|
r"\r": (LITERAL, 13),
|
|
r"\t": (LITERAL, 9),
|
|
r"\v": (LITERAL, 11),
|
|
r"\\": (LITERAL, ord("\\"))
|
|
}
|
|
|
|
CATEGORIES = {
|
|
r"\A": (AT, AT_BEGINNING), # start of string
|
|
r"\b": (AT, AT_BOUNDARY),
|
|
r"\B": (AT, AT_NON_BOUNDARY),
|
|
r"\d": (IN, [(CATEGORY, CATEGORY_DIGIT)]),
|
|
r"\D": (IN, [(CATEGORY, CATEGORY_NOT_DIGIT)]),
|
|
r"\s": (IN, [(CATEGORY, CATEGORY_SPACE)]),
|
|
r"\S": (IN, [(CATEGORY, CATEGORY_NOT_SPACE)]),
|
|
r"\w": (IN, [(CATEGORY, CATEGORY_WORD)]),
|
|
r"\W": (IN, [(CATEGORY, CATEGORY_NOT_WORD)]),
|
|
r"\Z": (AT, AT_END), # end of string
|
|
}
|
|
|
|
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,
|
|
}
|
|
|
|
class State:
|
|
def __init__(self):
|
|
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
|
|
|
|
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
|
|
def __repr__(self):
|
|
return repr(self.data)
|
|
def __len__(self):
|
|
return len(self.data)
|
|
def __delitem__(self, index):
|
|
del self.data[index]
|
|
def __getitem__(self, index):
|
|
return self.data[index]
|
|
def __setitem__(self, index, code):
|
|
self.data[index] = code
|
|
def __getslice__(self, start, stop):
|
|
return SubPattern(self.pattern, self.data[start:stop])
|
|
def insert(self, index, code):
|
|
self.data.insert(index, code)
|
|
def append(self, 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
|
|
|
|
class Tokenizer:
|
|
def __init__(self, string):
|
|
self.string = string
|
|
self.index = 0
|
|
self.__next()
|
|
def __next(self):
|
|
if self.index >= len(self.string):
|
|
self.next = None
|
|
return
|
|
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)
|
|
self.next = char
|
|
def match(self, char):
|
|
if char == self.next:
|
|
self.__next()
|
|
return 1
|
|
return 0
|
|
def get(self):
|
|
this = self.next
|
|
self.__next()
|
|
return this
|
|
def tell(self):
|
|
return self.index, self.next
|
|
def seek(self, index):
|
|
self.index, self.next = index
|
|
|
|
def isident(char):
|
|
return "a" <= char <= "z" or "A" <= char <= "Z" or char == "_"
|
|
|
|
def isdigit(char):
|
|
return "0" <= char <= "9"
|
|
|
|
def isname(name):
|
|
# check that group name is a valid string
|
|
if not isident(name[0]):
|
|
return 0
|
|
for char in name:
|
|
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:
|
|
gid = int(escape[1:])
|
|
if gid and gid < groups:
|
|
return gid
|
|
except ValueError:
|
|
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
|
|
code = CATEGORIES.get(escape)
|
|
if code:
|
|
return code
|
|
try:
|
|
if escape[1:2] == "x":
|
|
while source.next in HEXDIGITS:
|
|
escape = escape + source.get()
|
|
escape = escape[2:]
|
|
return LITERAL, int(escape[-4:], 16) & CHARMASK
|
|
elif str(escape[1:2]) in OCTDIGITS:
|
|
while source.next in OCTDIGITS:
|
|
escape = escape + source.get()
|
|
escape = escape[1:]
|
|
return LITERAL, int(escape[-6:], 8) & CHARMASK
|
|
if len(escape) == 2:
|
|
return LITERAL, ord(escape[1])
|
|
except ValueError:
|
|
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
|
|
code = ESCAPES.get(escape)
|
|
if code:
|
|
return code
|
|
try:
|
|
if escape[1:2] == "x":
|
|
while source.next in HEXDIGITS:
|
|
escape = escape + source.get()
|
|
escape = escape[2:]
|
|
return LITERAL, int(escape[-4:], 16) & CHARMASK
|
|
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 GROUPREF, group
|
|
escape = escape + source.get()
|
|
elif source.next in OCTDIGITS:
|
|
escape = escape + source.get()
|
|
else:
|
|
break
|
|
escape = escape[1:]
|
|
return LITERAL, int(escape[-6:], 8) & CHARMASK
|
|
if len(escape) == 2:
|
|
return LITERAL, ord(escape[1])
|
|
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)
|
|
|
|
# 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
|
|
|
|
# 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
|
|
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
|
|
|
|
subpattern.append((BRANCH, (None, items)))
|
|
return subpattern
|
|
|
|
def _parse(source, state):
|
|
|
|
# parse regular expression pattern into an operator list.
|
|
|
|
subpattern = SubPattern(state)
|
|
|
|
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, ord(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, ord(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, ord("-")))
|
|
break
|
|
else:
|
|
if this[0] == "\\":
|
|
code2 = _class_escape(source, this)
|
|
else:
|
|
code2 = LITERAL, ord(this)
|
|
if code1[0] != LITERAL or code2[0] != LITERAL:
|
|
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 == "{":
|
|
here = source.tell()
|
|
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("}"):
|
|
subpattern.append((LITERAL, ord(this)))
|
|
source.seek(here)
|
|
continue
|
|
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
|
|
name = ""
|
|
while 1:
|
|
char = source.get()
|
|
if char is None:
|
|
raise error, "unterminated name"
|
|
if char == ")":
|
|
break
|
|
name = name + char
|
|
if not isname(name):
|
|
raise error, "illegal character in group name"
|
|
gid = state.groupdict.get(name)
|
|
if gid is None:
|
|
raise error, "unknown group name"
|
|
subpattern.append((GROUPREF, gid))
|
|
elif source.match("#"):
|
|
index = ""
|
|
while 1:
|
|
char = source.get()
|
|
if char is None:
|
|
raise error, "unterminated index"
|
|
if char == ")":
|
|
break
|
|
index = index + char
|
|
try:
|
|
index = int(index)
|
|
if index < 0 or index > MAXREPEAT:
|
|
raise ValueError
|
|
except ValueError:
|
|
raise error, "illegal index"
|
|
subpattern.append((INDEX, index))
|
|
continue
|
|
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()
|
|
elif source.next in ("=", "!", "<"):
|
|
# lookahead assertions
|
|
char = source.get()
|
|
dir = 1
|
|
if char == "<":
|
|
if source.next not in ("=", "!"):
|
|
raise error, "syntax error"
|
|
dir = -1 # lookbehind
|
|
char = source.get()
|
|
b = []
|
|
while 1:
|
|
p = _parse(source, state)
|
|
if source.next == ")":
|
|
if b:
|
|
b.append(p)
|
|
p = _branch(state, b)
|
|
if char == "=":
|
|
subpattern.append((ASSERT, (dir, p)))
|
|
else:
|
|
subpattern.append((ASSERT_NOT, (dir, p)))
|
|
break
|
|
elif source.match("|"):
|
|
b.append(p)
|
|
else:
|
|
raise error, "pattern not properly closed"
|
|
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)
|
|
if group is not None:
|
|
p.append((INDEX, group))
|
|
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
|
|
|
|
def parse(pattern, flags=0):
|
|
# parse 're' pattern into list of (opcode, argument) tuples
|
|
source = Tokenizer(pattern)
|
|
state = State()
|
|
state.flags = flags
|
|
b = []
|
|
while 1:
|
|
p = _parse(source, state)
|
|
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):
|
|
# parse 're' replacement string into list of literals and
|
|
# group references
|
|
s = Tokenizer(source)
|
|
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:]
|
|
code = LITERAL, int(this[-6:], 8) & CHARMASK
|
|
a(code)
|
|
else:
|
|
try:
|
|
a(ESCAPES[this])
|
|
except KeyError:
|
|
for c in this:
|
|
a((LITERAL, ord(c)))
|
|
else:
|
|
a((LITERAL, ord(this)))
|
|
return p
|
|
|
|
def expand_template(template, match):
|
|
# FIXME: <fl> this is sooooo slow. drop in the slicelist
|
|
# code instead
|
|
p = []
|
|
a = p.append
|
|
sep = match.string[:0]
|
|
if type(sep) is type(""):
|
|
char = chr
|
|
else:
|
|
char = unichr
|
|
for c, s in template:
|
|
if c is LITERAL:
|
|
a(char(s))
|
|
elif c is MARK:
|
|
s = match.group(s)
|
|
if s is None:
|
|
raise error, "empty group"
|
|
a(s)
|
|
return sep.join(p)
|