Applied patch #725106, by Greg Chapman, fixing capturing groups
within repeats of alternatives. The only change to the original
patch was to convert the tests to the new test_re.py file.
This patch fixes cases like:
>>> re.match('((a)|b)*', 'abc').groups()
('b', '')
Which is wrong (it's impossible to match the empty string),
and incompatible with other regex systems, like the following
examples show:
% perl -e '"abc" =~ /^((a)|b)*/; print "$1 $2\n";'
b a
% echo "abc" | sed -r -e "s/^((a)|b)*/\1 \2|/"
b a|c
diff --git a/Modules/_sre.c b/Modules/_sre.c
index 3f17d13..b9e1827 100644
--- a/Modules/_sre.c
+++ b/Modules/_sre.c
@@ -947,10 +947,20 @@
if (pattern[1] == SRE_OP_IN &&
(ptr >= end || !SRE_CHARSET(pattern + 3, (SRE_CODE) *ptr)))
continue;
+ if (state->repeat) {
+ i = mark_save(state, 0, lastmark);
+ if (i < 0)
+ return i;
+ }
state->ptr = ptr;
i = SRE_MATCH(state, pattern + 1, level + 1);
if (i)
return i;
+ if (state->repeat) {
+ i = mark_restore(state, 0, lastmark);
+ if (i < 0)
+ return i;
+ }
LASTMARK_RESTORE();
}
return 0;