mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-01 15:43:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

Issue #5828 (Invalid behavior of unicode.lower): Fixed bogus logic in

Browse source 
makeunicodedata.py and regenerated the Unicode database (This fixes
u'\u1d79'.lower() == '\x00').
This commit is contained in:
Walter Dörwald 2009-04-25 14:03:16 +00:00
parent 140d9d673e
commit 5d98ec76bb
4 changed files with 41 additions and 25 deletions
Download patch file Download diff file Expand all files Collapse all files

43
Tools/unicode/makeunicodedata.py
View file

@ -371,33 +371,32 @@ def makeunicodetype(unicode, trace):
flags |= UPPER_MASK
# use delta predictor for upper/lower/title if it fits
if record[12]:
upper = int(record[12], 16) - char
if -32768 <= upper <= 32767 and delta:
upper = upper & 0xffff
else:
upper += char
delta = False
upper = int(record[12], 16)
else:
upper = 0
upper = char
if record[13]:
lower = int(record[13], 16) - char
if -32768 <= lower <= 32767 and delta:
lower = lower & 0xffff
else:
lower += char
delta = False
lower = int(record[13], 16)
else:
lower = 0
lower = char
if record[14]:
title = int(record[14], 16) - char
if -32768 <= lower <= 32767 and delta:
title = title & 0xffff
else:
title += char
delta = False
title = int(record[14], 16)
else:
# UCD.html says that a missing title char means that
# it defaults to the uppercase character, not to the
# character itself. Apparently, in the current UCD (5.x)
# this feature is never used
title = upper
upper_d = upper - char
lower_d = lower - char
title_d = title - char
if -32768 <= upper_d <= 32767 and \
-32768 <= lower_d <= 32767 and \
-32768 <= title_d <= 32767:
# use deltas
upper = upper_d & 0xffff
lower = lower_d & 0xffff
title = title_d & 0xffff
else:
title = 0
if not delta:
flags |= NODELTA_MASK
# decimal digit, integer digit
decimal = 0