2000-03-31 22:58:54 +08:00
|
|
|
#
|
|
|
|
# Secret Labs' Regular Expression Engine
|
|
|
|
#
|
|
|
|
# re-compatible interface for the sre matching engine
|
|
|
|
#
|
|
|
|
# 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 1.6 integration and
|
|
|
|
# other compatibility work.
|
|
|
|
#
|
|
|
|
|
|
|
|
import sre_compile
|
2000-06-29 16:58:44 +08:00
|
|
|
import sre_parse
|
2000-03-31 22:58:54 +08:00
|
|
|
|
2000-06-02 01:39:12 +08:00
|
|
|
# flags
|
|
|
|
I = IGNORECASE = sre_compile.SRE_FLAG_IGNORECASE
|
|
|
|
L = LOCALE = sre_compile.SRE_FLAG_LOCALE
|
|
|
|
M = MULTILINE = sre_compile.SRE_FLAG_MULTILINE
|
|
|
|
S = DOTALL = sre_compile.SRE_FLAG_DOTALL
|
|
|
|
X = VERBOSE = sre_compile.SRE_FLAG_VERBOSE
|
|
|
|
|
2000-06-29 16:58:44 +08:00
|
|
|
# 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
|
2000-06-30 00:57:40 +08:00
|
|
|
error = sre_compile.error
|
2000-06-29 16:58:44 +08:00
|
|
|
|
2000-03-31 22:58:54 +08:00
|
|
|
# --------------------------------------------------------------------
|
|
|
|
# public interface
|
|
|
|
|
2000-06-02 01:39:12 +08:00
|
|
|
# FIXME: add docstrings
|
2000-03-31 22:58:54 +08:00
|
|
|
|
|
|
|
def match(pattern, string, flags=0):
|
2000-06-02 01:39:12 +08:00
|
|
|
return _compile(pattern, flags).match(string)
|
2000-03-31 22:58:54 +08:00
|
|
|
|
|
|
|
def search(pattern, string, flags=0):
|
2000-06-02 01:39:12 +08:00
|
|
|
return _compile(pattern, flags).search(string)
|
|
|
|
|
|
|
|
def sub(pattern, repl, string, count=0):
|
|
|
|
return _compile(pattern).sub(repl, string, count)
|
|
|
|
|
|
|
|
def subn(pattern, repl, string, count=0):
|
|
|
|
return _compile(pattern).subn(repl, string, count)
|
|
|
|
|
|
|
|
def split(pattern, string, maxsplit=0):
|
|
|
|
return _compile(pattern).split(string, maxsplit)
|
2000-03-31 22:58:54 +08:00
|
|
|
|
2000-06-02 01:39:12 +08:00
|
|
|
def findall(pattern, string, maxsplit=0):
|
|
|
|
return _compile(pattern).findall(string, maxsplit)
|
|
|
|
|
|
|
|
def compile(pattern, flags=0):
|
|
|
|
return _compile(pattern, flags)
|
|
|
|
|
2000-06-29 16:58:44 +08:00
|
|
|
def template(pattern, flags=0):
|
|
|
|
return _compile(pattern, flags|T)
|
|
|
|
|
2000-06-02 01:39:12 +08:00
|
|
|
def escape(pattern):
|
|
|
|
s = list(pattern)
|
|
|
|
for i in range(len(pattern)):
|
|
|
|
c = pattern[i]
|
|
|
|
if not ("a" <= c <= "z" or "A" <= c <= "Z" or "0" <= c <= "9"):
|
|
|
|
if c == "\000":
|
|
|
|
s[i] = "\\000"
|
|
|
|
else:
|
|
|
|
s[i] = "\\" + c
|
|
|
|
return pattern[:0].join(s)
|
2000-03-31 22:58:54 +08:00
|
|
|
|
|
|
|
# --------------------------------------------------------------------
|
2000-06-02 01:39:12 +08:00
|
|
|
# internals
|
|
|
|
|
|
|
|
_cache = {}
|
|
|
|
_MAXCACHE = 100
|
|
|
|
|
|
|
|
def _compile(pattern, flags=0):
|
|
|
|
# internal: compile pattern
|
|
|
|
tp = type(pattern)
|
|
|
|
if tp not in (type(""), type(u"")):
|
|
|
|
return pattern
|
|
|
|
key = (tp, pattern, flags)
|
|
|
|
try:
|
|
|
|
return _cache[key]
|
|
|
|
except KeyError:
|
|
|
|
pass
|
|
|
|
p = sre_compile.compile(pattern, flags)
|
|
|
|
if len(_cache) >= _MAXCACHE:
|
|
|
|
_cache.clear()
|
|
|
|
_cache[key] = p
|
|
|
|
return p
|
|
|
|
|
|
|
|
def _sub(pattern, template, string, count=0):
|
|
|
|
# internal: pattern.sub implementation hook
|
|
|
|
return _subn(pattern, template, string, count)[0]
|
|
|
|
|
|
|
|
def _subn(pattern, template, string, count=0):
|
|
|
|
# internal: pattern.subn implementation hook
|
|
|
|
if callable(template):
|
2000-06-19 04:27:10 +08:00
|
|
|
filter = template
|
2000-06-02 01:39:12 +08:00
|
|
|
else:
|
2000-06-29 16:58:44 +08:00
|
|
|
template = sre_parse.parse_template(template, pattern)
|
2000-06-02 01:39:12 +08:00
|
|
|
def filter(match, template=template):
|
2000-06-29 16:58:44 +08:00
|
|
|
return sre_parse.expand_template(template, match)
|
2000-06-02 01:39:12 +08:00
|
|
|
n = i = 0
|
|
|
|
s = []
|
|
|
|
append = s.append
|
2000-06-30 00:57:40 +08:00
|
|
|
c = pattern.scanner(string)
|
2000-06-02 01:39:12 +08:00
|
|
|
while not count or n < count:
|
|
|
|
m = c.search()
|
|
|
|
if not m:
|
|
|
|
break
|
|
|
|
j = m.start()
|
|
|
|
if j > i:
|
|
|
|
append(string[i:j])
|
|
|
|
append(filter(m))
|
|
|
|
i = m.end()
|
2000-06-29 16:58:44 +08:00
|
|
|
if i <= j:
|
|
|
|
break
|
2000-06-02 01:39:12 +08:00
|
|
|
n = n + 1
|
|
|
|
if i < len(string):
|
|
|
|
append(string[i:])
|
|
|
|
return string[:0].join(s), n
|
2000-03-31 22:58:54 +08:00
|
|
|
|
2000-06-02 01:39:12 +08:00
|
|
|
def _split(pattern, string, maxsplit=0):
|
|
|
|
# internal: pattern.split implementation hook
|
|
|
|
n = i = 0
|
|
|
|
s = []
|
|
|
|
append = s.append
|
2000-06-30 00:57:40 +08:00
|
|
|
extend = s.extend
|
|
|
|
c = pattern.scanner(string)
|
|
|
|
g = c.groups
|
2000-06-02 01:39:12 +08:00
|
|
|
while not maxsplit or n < maxsplit:
|
|
|
|
m = c.search()
|
|
|
|
if not m:
|
|
|
|
break
|
2000-06-30 00:57:40 +08:00
|
|
|
b, e = m.span()
|
2000-06-30 02:03:25 +08:00
|
|
|
if b == e:
|
|
|
|
if i >= len(string):
|
|
|
|
break
|
2000-06-30 00:57:40 +08:00
|
|
|
continue
|
|
|
|
append(string[i:b])
|
|
|
|
if g and b != e:
|
|
|
|
extend(m.groups())
|
|
|
|
i = e
|
2000-06-02 01:39:12 +08:00
|
|
|
n = n + 1
|
2000-06-30 02:03:25 +08:00
|
|
|
append(string[i:])
|
2000-06-02 01:39:12 +08:00
|
|
|
return s
|