# HG changeset patch # User FUJIWARA Katsunori # Date 1404583001 -32400 # Node ID 86c2d792a4b782a379ebf4f71d2267af1df681a1 # Parent d24969ee272fa62e936bb1e93f08306a97470b20 util: replace 'ellipsis' implementation by 'encoding.trim' Before this patch, 'util.ellipsis' tried to avoid splitting at intermediate multi-byte sequence, but its implementation was incorrect. Internal function '_ellipsis' trims specified unicode sequence not at most maxlength 'columns in display', but at most maxlength number of 'unicode characters'. def _ellipsis(text, maxlength): if len(text) <= maxlength: return text, False else: return "%s..." % (text[:maxlength - 3]), True In many encodings, number of unicode characters can be different from columns in display. This patch replaces 'ellipsis' implementation by 'encoding.trim', which can trim string at most maxlength columns in display correctly, even though specified string contains multi-byte characters. '_ellipsis' is removed in this patch, because it is referred only from 'ellipsis'. diff -r d24969ee272f -r 86c2d792a4b7 mercurial/util.py --- a/mercurial/util.py Sun Jul 06 02:56:41 2014 +0900 +++ b/mercurial/util.py Sun Jul 06 02:56:41 2014 +0900 @@ -1318,23 +1318,9 @@ r = None return author[author.find('<') + 1:r] -def _ellipsis(text, maxlength): - if len(text) <= maxlength: - return text, False - else: - return "%s..." % (text[:maxlength - 3]), True - def ellipsis(text, maxlength=400): - """Trim string to at most maxlength (default: 400) characters.""" - try: - # use unicode not to split at intermediate multi-byte sequence - utext, truncated = _ellipsis(text.decode(encoding.encoding), - maxlength) - if not truncated: - return text - return utext.encode(encoding.encoding) - except (UnicodeDecodeError, UnicodeEncodeError): - return _ellipsis(text, maxlength)[0] + """Trim string to at most maxlength (default: 400) columns in display.""" + return encoding.trim(text, maxlength, ellipsis='...') def unitcountfn(*unittable): '''return a function that renders a readable count of some quantity'''