Mercurial > public > mercurial-scm > hg

comparison mercurial/util.py @ 15065:24a6c3f903bb stable

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
util: wrap lines with multi-byte characters correctly (issue2943) This re-introduces the unicode conversion what was lost in d320e70442a5 5 years ago and had the comment: To avoid corrupting multi-byte characters in line, we must wrap a Unicode string instead of a bytestring.
author Mads Kiilerich <mads@kiilerich.com>
date Sat, 06 Aug 2011 23:52:20 +0200
parents 0f1311e829c9
children 24efa83d81cb
comparison
equal deleted inserted replaced
15064:1f581a8b1948 15065:24a6c3f903bb
1146 representation, or encoding of the underlying string) 1146 representation, or encoding of the underlying string)
1147 """ 1147 """
1148 def __init__(self, **kwargs): 1148 def __init__(self, **kwargs):
1149 textwrap.TextWrapper.__init__(self, **kwargs) 1149 textwrap.TextWrapper.__init__(self, **kwargs)
1150 1150
1151 def _cutdown(self, str, space_left): 1151 def _cutdown(self, ucstr, space_left):
1152 l = 0 1152 l = 0
1153 ucstr = unicode(str, encoding.encoding)
1154 colwidth = unicodedata.east_asian_width 1153 colwidth = unicodedata.east_asian_width
1155 for i in xrange(len(ucstr)): 1154 for i in xrange(len(ucstr)):
1156 l += colwidth(ucstr[i]) in 'WFA' and 2 or 1 1155 l += colwidth(ucstr[i]) in 'WFA' and 2 or 1
1157 if space_left < l: 1156 if space_left < l:
1158 return (ucstr[:i].encode(encoding.encoding), 1157 return (ucstr[:i], ucstr[i:])
1159 ucstr[i:].encode(encoding.encoding)) 1158 return ucstr, ''
1160 return str, ''
1161 1159
1162 # overriding of base class 1160 # overriding of base class
1163 def _handle_long_word(self, reversed_chunks, cur_line, cur_len, width): 1161 def _handle_long_word(self, reversed_chunks, cur_line, cur_len, width):
1164 space_left = max(width - cur_len, 1) 1162 space_left = max(width - cur_len, 1)
1165 1163
1177 def wrap(line, width, initindent='', hangindent=''): 1175 def wrap(line, width, initindent='', hangindent=''):
1178 maxindent = max(len(hangindent), len(initindent)) 1176 maxindent = max(len(hangindent), len(initindent))
1179 if width <= maxindent: 1177 if width <= maxindent:
1180 # adjust for weird terminal size 1178 # adjust for weird terminal size
1181 width = max(78, maxindent + 1) 1179 width = max(78, maxindent + 1)
1180 line = line.decode(encoding.encoding, encoding.encodingmode)
1181 initindent = initindent.decode(encoding.encoding, encoding.encodingmode)
1182 hangindent = hangindent.decode(encoding.encoding, encoding.encodingmode)
1182 wrapper = MBTextWrapper(width=width, 1183 wrapper = MBTextWrapper(width=width,
1183 initial_indent=initindent, 1184 initial_indent=initindent,
1184 subsequent_indent=hangindent) 1185 subsequent_indent=hangindent)
1185 return wrapper.fill(line) 1186 return wrapper.fill(line).encode(encoding.encoding)
1186 1187
1187 def iterlines(iterator): 1188 def iterlines(iterator):
1188 for chunk in iterator: 1189 for chunk in iterator:
1189 for line in chunk.splitlines(): 1190 for line in chunk.splitlines():
1190 yield line 1191 yield line