diff options
author | Serhiy Storchaka <storchaka@gmail.com> | 2013-08-19 22:53:46 +0300 |
---|---|---|
committer | Serhiy Storchaka <storchaka@gmail.com> | 2013-08-19 22:53:46 +0300 |
commit | 34ecb118f116d4564a82bd16650d643f26ee989b (patch) | |
tree | d25921ff4d94572de0adc57ffca4c21f9fdb0f2d /Lib/sre_parse.py | |
parent | 10107813acc9a9c5895f4e00e264bc605443c538 (diff) | |
download | cpython-git-34ecb118f116d4564a82bd16650d643f26ee989b.tar.gz |
Issue #18647: Correctly bound calculated min/max width of a subexpression.
Now max width is MAXREPEAT on 32- and 64-bit platforms when one of
subexpressions is unbounded repetition.
Diffstat (limited to 'Lib/sre_parse.py')
-rw-r--r-- | Lib/sre_parse.py | 10 |
1 files changed, 5 insertions, 5 deletions
diff --git a/Lib/sre_parse.py b/Lib/sre_parse.py index 75f8c9601d..e8d35a6d41 100644 --- a/Lib/sre_parse.py +++ b/Lib/sre_parse.py @@ -142,12 +142,12 @@ class SubPattern: # determine the width (min, max) for this subpattern if self.width: return self.width - lo = hi = 0L + lo = hi = 0 UNITCODES = (ANY, RANGE, IN, LITERAL, NOT_LITERAL, CATEGORY) REPEATCODES = (MIN_REPEAT, MAX_REPEAT) for op, av in self.data: if op is BRANCH: - i = sys.maxint + i = MAXREPEAT - 1 j = 0 for av in av[1]: l, h = av.getwidth() @@ -165,14 +165,14 @@ class SubPattern: hi = hi + j elif op in REPEATCODES: i, j = av[2].getwidth() - lo = lo + long(i) * av[0] - hi = hi + long(j) * av[1] + lo = lo + i * av[0] + hi = hi + j * av[1] elif op in UNITCODES: lo = lo + 1 hi = hi + 1 elif op == SUCCESS: break - self.width = int(min(lo, sys.maxint)), int(min(hi, sys.maxint)) + self.width = min(lo, MAXREPEAT - 1), min(hi, MAXREPEAT) return self.width class Tokenizer: |