summaryrefslogtreecommitdiffstats
path: root/Lib
diff options
context:
space:
mode:
Diffstat (limited to 'Lib')
-rw-r--r--Lib/sre.py13
-rw-r--r--Lib/sre_compile.py8
-rw-r--r--Lib/sre_parse.py66
-rw-r--r--Lib/test/output/test_sre3
4 files changed, 49 insertions, 41 deletions
diff --git a/Lib/sre.py b/Lib/sre.py
index 97a5140..5e6aeeb 100644
--- a/Lib/sre.py
+++ b/Lib/sre.py
@@ -89,6 +89,10 @@ def _compile(pattern, flags=0):
_cache[key] = p
return p
+def purge():
+ # clear pattern cache
+ _cache.clear()
+
def _sub(pattern, template, string, count=0):
# internal: pattern.sub implementation hook
return _subn(pattern, template, string, count)[0]
@@ -142,3 +146,12 @@ def _split(pattern, string, maxsplit=0):
n = n + 1
append(string[i:])
return s
+
+# register myself for pickling
+
+import copy_reg
+
+def _pickle(p):
+ return _compile, (p.pattern, p.flags)
+
+copy_reg.pickle(type(_compile("")), _pickle, _compile)
diff --git a/Lib/sre_compile.py b/Lib/sre_compile.py
index 0829c00..e48a7eb 100644
--- a/Lib/sre_compile.py
+++ b/Lib/sre_compile.py
@@ -31,15 +31,15 @@ def _compile(code, pattern, flags):
emit(OPCODES[OP_IGNORE[op]])
else:
emit(OPCODES[op])
- emit(ord(av))
+ emit(av)
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)
+ return _sre.getlower(literal, flags)
else:
emit(OPCODES[op])
- fixup = ord
+ fixup = lambda x: x
skip = len(code); emit(0)
for op, av in av:
emit(OPCODES[op])
@@ -165,7 +165,7 @@ def _compile_info(code, pattern, flags):
if not (flags & SRE_FLAG_IGNORECASE):
for op, av in pattern.data:
if op is LITERAL:
- prefix.append(ord(av))
+ prefix.append(av)
else:
break
# add an info block
diff --git a/Lib/sre_parse.py b/Lib/sre_parse.py
index d3dbe00..fb954e9 100644
--- a/Lib/sre_parse.py
+++ b/Lib/sre_parse.py
@@ -19,6 +19,9 @@ from sre_constants import *
# FIXME: should be 65535, but the arraymodule is still broken
MAXREPEAT = 32767
+# FIXME: same here
+CHARMASK = 0x7fff
+
SPECIAL_CHARS = ".\\[{()*+?^$|"
REPEAT_CHARS = "*+?{"
@@ -30,14 +33,14 @@ HEXDIGITS = tuple("0123456789abcdefABCDEF")
WHITESPACE = string.whitespace
ESCAPES = {
- r"\a": (LITERAL, chr(7)),
- r"\b": (LITERAL, chr(8)),
- r"\f": (LITERAL, chr(12)),
- r"\n": (LITERAL, chr(10)),
- r"\r": (LITERAL, chr(13)),
- r"\t": (LITERAL, chr(9)),
- r"\v": (LITERAL, chr(11)),
- r"\\": (LITERAL, "\\")
+ 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 = {
@@ -176,9 +179,6 @@ def isdigit(char):
def isname(name):
# check that group name is a valid string
- # FIXME: <fl> this code is really lame. should use a regular
- # expression instead, but I seem to have certain bootstrapping
- # problems here ;-)
if not isident(name[0]):
return 0
for char in name:
@@ -209,16 +209,14 @@ def _class_escape(source, escape):
while source.next in HEXDIGITS:
escape = escape + source.get()
escape = escape[2:]
- # FIXME: support unicode characters!
- return LITERAL, chr(int(escape[-4:], 16) & 0xff)
+ 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:]
- # FIXME: support unicode characters!
- return LITERAL, chr(int(escape[-6:], 8) & 0xff)
+ return LITERAL, int(escape[-6:], 8) & CHARMASK
if len(escape) == 2:
- return LITERAL, escape[1]
+ return LITERAL, ord(escape[1])
except ValueError:
pass
raise error, "bogus escape: %s" % repr(escape)
@@ -236,8 +234,7 @@ def _escape(source, escape, state):
while source.next in HEXDIGITS:
escape = escape + source.get()
escape = escape[2:]
- # FIXME: support unicode characters!
- return LITERAL, chr(int(escape[-4:], 16) & 0xff)
+ return LITERAL, int(escape[-4:], 16) & CHARMASK
elif escape[1:2] in DIGITS:
while 1:
group = _group(escape, state.groups)
@@ -251,17 +248,14 @@ def _escape(source, escape, state):
else:
break
escape = escape[1:]
- # FIXME: support unicode characters!
- return LITERAL, chr(int(escape[-6:], 8) & 0xff)
+ return LITERAL, int(escape[-6:], 8) & CHARMASK
if len(escape) == 2:
- return LITERAL, escape[1]
+ 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)
@@ -327,7 +321,7 @@ def _parse(source, state, flags=0):
continue
if this and this[0] not in SPECIAL_CHARS:
- subpattern.append((LITERAL, this))
+ subpattern.append((LITERAL, ord(this)))
elif this == "[":
# character set
@@ -345,7 +339,7 @@ def _parse(source, state, flags=0):
elif this and this[0] == "\\":
code1 = _class_escape(source, this)
elif this:
- code1 = LITERAL, this
+ code1 = LITERAL, ord(this)
else:
raise error, "unexpected end of regular expression"
if source.match("-"):
@@ -353,17 +347,15 @@ def _parse(source, state, flags=0):
this = source.get()
if this == "]":
set.append(code1)
- set.append((LITERAL, "-"))
+ set.append((LITERAL, ord("-")))
break
else:
if this[0] == "\\":
code2 = _class_escape(source, this)
else:
- code2 = LITERAL, this
+ code2 = LITERAL, ord(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:
@@ -605,17 +597,16 @@ def parse_template(source, pattern):
break
if not code:
this = this[1:]
- # FIXME: support unicode characters!
- code = LITERAL, chr(int(this[-6:], 8) & 0xff)
+ code = LITERAL, int(this[-6:], 8) & CHARMASK
a(code)
else:
try:
a(ESCAPES[this])
except KeyError:
for c in this:
- a((LITERAL, c))
+ a((LITERAL, ord(c)))
else:
- a((LITERAL, this))
+ a((LITERAL, ord(this)))
return p
def expand_template(template, match):
@@ -623,12 +614,17 @@ def expand_template(template, match):
# 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(s)
+ a(char(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)
+ return sep.join(p)
diff --git a/Lib/test/output/test_sre b/Lib/test/output/test_sre
index d3732b5..10de93d 100644
--- a/Lib/test/output/test_sre
+++ b/Lib/test/output/test_sre
@@ -1,6 +1,5 @@
test_sre
-test_support -- test failed re module pickle
-test_support -- test failed re module cPickle
+=== Failed incorrectly ('\\x00ffffffffffffff', '\377', 0, 'found', '\377')
=== Failed incorrectly ('^(.+)?B', 'AB', 0, 'g1', 'A')
=== Failed incorrectly ('(a+)+\\1', 'aa', 0, 'found+"-"+g1', 'aa-a')
=== grouping error ('([^/]*/)*sub1/', 'd:msgs/tdir/sub1/trial/away.cpp', 0, 'found+"-"+g1', 'd:msgs/tdir/sub1/-tdir/') 'd:msgs/tdir/sub1/-trial/' should be 'd:msgs/tdir/sub1/-tdir/'
generated by cgit v0.12 at 2024-11-22 16:08:49 (GMT)