-- reset marks if repeat_one tail doesn't match

   (this should fix Sjoerd's xmllib problem)
-- added skip field to INFO header
-- changed compiler to generate charset INFO header
-- changed trace messages to support post-mortem analysis

Lib/sre.py

@@ -47,16 +47,16 @@ def search(pattern, string, flags=0):
     return _compile(pattern, flags).search(string)
 
 def sub(pattern, repl, string, count=0):
-    return _compile(pattern).sub(repl, string, count)
+    return _compile(pattern, 0).sub(repl, string, count)
 
 def subn(pattern, repl, string, count=0):
-    return _compile(pattern).subn(repl, string, count)
+    return _compile(pattern, 0).subn(repl, string, count)
 
 def split(pattern, string, maxsplit=0):
-    return _compile(pattern).split(string, maxsplit)
+    return _compile(pattern, 0).split(string, maxsplit)
 
 def findall(pattern, string, maxsplit=0):
-    return _compile(pattern).findall(string, maxsplit)
+    return _compile(pattern, 0).findall(string, maxsplit)
 
 def compile(pattern, flags=0):
     return _compile(pattern, flags)
@@ -88,16 +88,14 @@ def _join(seq, sep):
     # internal: join into string having the same type as sep
     return string.join(seq, sep[:0])
 
-def _compile(pattern, flags=0):
+def _compile(*key):
     # internal: compile pattern
-    tp = type(pattern)
-    if tp not in sre_compile.STRING_TYPES:
+    p = _cache.get(key)
+    if p is not None:
+        return p
+    pattern, flags = key
+    if type(pattern) not in sre_compile.STRING_TYPES:
         return pattern
-    key = (tp, pattern, flags)
-    try:
-        return _cache[key]
-    except KeyError:
-        pass
     try:
         p = sre_compile.compile(pattern, flags)
     except error, v:
@@ -168,7 +166,7 @@ import copy_reg
 def _pickle(p):
     return _compile, (p.pattern, p.flags)
 
-copy_reg.pickle(type(_compile("")), _pickle, _compile)
+copy_reg.pickle(type(_compile("", 0)), _pickle, _compile)
 
 # --------------------------------------------------------------------
 # experimental stuff (see python-dev discussions for details)

Lib/sre_parse.py

@@ -10,8 +10,6 @@
 
 import string, sys
 
-import _sre
-
 from sre_constants import *
 
 MAXREPEAT = 65535
@@ -232,6 +230,7 @@ def _class_escape(source, escape):
         return code
     try:
         if escape[1:2] == "x":
+            # FIXME: in 2.0, \xNN must have exactly two digits
             while source.next in HEXDIGITS:
                 escape = escape + source.get()
             escape = escape[2:]
@@ -556,12 +555,13 @@ def _parse(source, state):
 
     return subpattern
 
-def parse(str, flags=0):
+def parse(str, flags=0, pattern=None):
     # parse 're' pattern into list of (opcode, argument) tuples
 
     source = Tokenizer(str)
 
-    pattern = Pattern()
+    if pattern is None:
+        pattern = Pattern()
     pattern.flags = flags
 
     p = _parse_sub(source, pattern, 0)