From: <go...@us...> - 2006-06-30 01:05:26
|
Author: goodger Date: 2006-06-30 03:04:10 +0200 (Fri, 30 Jun 2006) New Revision: 4646 Modified: trunk/sandbox/davidg/unispace.py Log: removed zero-width non-joiner Modified: trunk/sandbox/davidg/unispace.py =================================================================== --- trunk/sandbox/davidg/unispace.py 2006-06-29 21:02:41 UTC (rev 4645) +++ trunk/sandbox/davidg/unispace.py 2006-06-30 01:04:10 UTC (rev 4646) @@ -10,7 +10,7 @@ 1. '\\s' 2. '\\s', re.UNICODE -3. u'(?![\xa0\u202f])[\\s\u200c]', re.UNICODE +3. u'(?![\xa0\u202f])\\s', re.UNICODE === ========= ======= ========================= ======= Cat Codepoint Decimal Name/Description Regexps @@ -40,7 +40,6 @@ Zs U+2009 8201 THIN SPACE 2 3 Zs U+200a 8202 HAIR SPACE 2 3 Zs U+200b 8203 ZERO WIDTH SPACE 2 3 -Cf U+200c 8204 ZERO WIDTH NON-JOINER 3 Zl U+2028 8232 LINE SEPARATOR 2 3 Zp U+2029 8233 PARAGRAPH SEPARATOR 2 3 Zs U+202f 8239 NARROW NO-BREAK SPACE 2 @@ -79,7 +78,7 @@ pats = [re.compile(r'\s'), re.compile(r'\s', re.UNICODE), - re.compile(u'(?![\u00a0\u202f])[\\s\u200c]', re.UNICODE),] + re.compile(u'(?![\u00a0\u202f])\\s', re.UNICODE),] border = '=== ========= ======= ========================= =======' header = 'Cat Codepoint Decimal Name/Description Regexps' |