i18n: use "encoding.lower()" to normalize string in hgweb search query
some problematic encoding (e.g.: cp932) uses ASCII alphabet characters
in byte sequence of multi byte characters.
"str.lower()" on such byte sequence may treat distinct characters as
same one, and cause unexpected log matching.
this patch uses "encoding.lower()" instead of "str.lower()" to
normalize strings for compare.
--- a/mercurial/hgweb/webcommands.py Sun Dec 25 20:35:16 2011 +0900
+++ b/mercurial/hgweb/webcommands.py Sun Dec 25 20:35:16 2011 +0900
@@ -124,7 +124,8 @@
def changelist(**map):
count = 0
- qw = query.lower().split()
+ lower = encoding.lower
+ qw = lower(query).split()
def revgen():
for i in xrange(len(web.repo) - 1, 0, -100):
@@ -139,9 +140,9 @@
for ctx in revgen():
miss = 0
for q in qw:
- if not (q in ctx.user().lower() or
- q in ctx.description().lower() or
- q in " ".join(ctx.files()).lower()):
+ if not (q in lower(ctx.user()) or
+ q in lower(ctx.description()) or
+ q in lower(" ".join(ctx.files()))):
miss = 1
break
if miss: