lib-python.2.5.re.py Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of jython Show documentation
Show all versions of jython Show documentation
Jython is an implementation of the high-level, dynamic, object-oriented
language Python written in 100% Pure Java, and seamlessly integrated with
the Java platform. It thus allows you to run Python on any Java platform.
#
# Secret Labs' Regular Expression Engine
#
# re-compatible interface for the sre matching engine
#
# Copyright (c) 1998-2001 by Secret Labs AB. All rights reserved.
#
# This version of the SRE library can be redistributed under CNRI's
# Python 1.6 license. For any other use, please contact Secret Labs
# AB ([email protected]).
#
# Portions of this engine have been developed in cooperation with
# CNRI. Hewlett-Packard provided funding for 1.6 integration and
# other compatibility work.
#
r"""Support for regular expressions (RE).
This module provides regular expression matching operations similar to
those found in Perl. It supports both 8-bit and Unicode strings; both
the pattern and the strings being processed can contain null bytes and
characters outside the US ASCII range.
Regular expressions can contain both special and ordinary characters.
Most ordinary characters, like "A", "a", or "0", are the simplest
regular expressions; they simply match themselves. You can
concatenate ordinary characters, so last matches the string 'last'.
The special characters are:
"." Matches any character except a newline.
"^" Matches the start of the string.
"$" Matches the end of the string or just before the newline at
the end of the string.
"*" Matches 0 or more (greedy) repetitions of the preceding RE.
Greedy means that it will match as many repetitions as possible.
"+" Matches 1 or more (greedy) repetitions of the preceding RE.
"?" Matches 0 or 1 (greedy) of the preceding RE.
*?,+?,?? Non-greedy versions of the previous three special characters.
{m,n} Matches from m to n repetitions of the preceding RE.
{m,n}? Non-greedy version of the above.
"\\" Either escapes special characters or signals a special sequence.
[] Indicates a set of characters.
A "^" as the first character indicates a complementing set.
"|" A|B, creates an RE that will match either A or B.
(...) Matches the RE inside the parentheses.
The contents can be retrieved or matched later in the string.
(?iLmsux) Set the I, L, M, S, U, or X flag for the RE (see below).
(?:...) Non-grouping version of regular parentheses.
(?P...) The substring matched by the group is accessible by name.
(?P=name) Matches the text matched earlier by the group named name.
(?#...) A comment; ignored.
(?=...) Matches if ... matches next, but doesn't consume the string.
(?!...) Matches if ... doesn't match next.
(?<=...) Matches if preceded by ... (must be fixed length).
(?= 0x02020000:
__all__.append("finditer")
def finditer(pattern, string, flags=0):
"""Return an iterator over all non-overlapping matches in the
string. For each match, the iterator returns a match object.
Empty matches are included in the result."""
return _compile(pattern, flags).finditer(string)
def compile(pattern, flags=0):
"Compile a regular expression pattern, returning a pattern object."
return _compile(pattern, flags)
def purge():
"Clear the regular expression cache"
_cache.clear()
_cache_repl.clear()
def template(pattern, flags=0):
"Compile a template pattern, returning a pattern object"
return _compile(pattern, flags|T)
_alphanum = {}
for c in 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01234567890':
_alphanum[c] = 1
del c
def escape(pattern):
"Escape all non-alphanumeric characters in pattern."
s = list(pattern)
alphanum = _alphanum
for i in range(len(pattern)):
c = pattern[i]
if c not in alphanum:
if c == "\000":
s[i] = "\\000"
else:
s[i] = "\\" + c
return pattern[:0].join(s)
# --------------------------------------------------------------------
# internals
_cache = {}
_cache_repl = {}
_pattern_type = type(sre_compile.compile("", 0))
_MAXCACHE = 100
def _compile(*key):
# internal: compile pattern
cachekey = (type(key[0]),) + key
p = _cache.get(cachekey)
if p is not None:
return p
pattern, flags = key
if isinstance(pattern, _pattern_type):
return pattern
if not sre_compile.isstring(pattern):
raise TypeError, "first argument must be string or compiled pattern"
try:
p = sre_compile.compile(pattern, flags)
except error, v:
raise error, v # invalid expression
if len(_cache) >= _MAXCACHE:
_cache.clear()
_cache[cachekey] = p
return p
def _compile_repl(*key):
# internal: compile replacement pattern
p = _cache_repl.get(key)
if p is not None:
return p
repl, pattern = key
try:
p = sre_parse.parse_template(repl, pattern)
except error, v:
raise error, v # invalid expression
if len(_cache_repl) >= _MAXCACHE:
_cache_repl.clear()
_cache_repl[key] = p
return p
def _expand(pattern, match, template):
# internal: match.expand implementation hook
template = sre_parse.parse_template(template, pattern)
return sre_parse.expand_template(template, match)
def _subx(pattern, template):
# internal: pattern.sub/subn implementation helper
template = _compile_repl(template, pattern)
if not template[0] and len(template[1]) == 1:
# literal replacement
return template[1][0]
def filter(match, template=template):
return sre_parse.expand_template(template, match)
return filter
# register myself for pickling
import copy_reg
def _pickle(p):
return _compile, (p.pattern, p.flags)
copy_reg.pickle(_pattern_type, _pickle, _compile)
# --------------------------------------------------------------------
# experimental stuff (see python-dev discussions for details)
class Scanner:
def __init__(self, lexicon, flags=0):
from sre_constants import BRANCH, SUBPATTERN
self.lexicon = lexicon
# combine phrases into a compound pattern
p = []
s = sre_parse.Pattern()
s.flags = flags
for phrase, action in lexicon:
p.append(sre_parse.SubPattern(s, [
(SUBPATTERN, (len(p)+1, sre_parse.parse(phrase, flags))),
]))
s.groups = len(p)+1
p = sre_parse.SubPattern(s, [(BRANCH, (None, p))])
self.scanner = sre_compile.compile(p)
def scan(self, string):
result = []
append = result.append
match = self.scanner.scanner(string).match
i = 0
while 1:
m = match()
if not m:
break
j = m.end()
if i == j:
break
action = self.lexicon[m.lastindex-1][1]
if callable(action):
self.match = m
action = action(self, m.group())
if action is not None:
append(action)
i = j
return result, string[i:]