diff: do not split function name if character encoding is unknown

Only ASCII characters can be split reliably at any byte positions, so let's
just leave long multi-byte sequence long. It's probably less bad than putting
an invalid byte sequence into a diff.

This doesn't try to split the first ASCII slice from multi-byte sequence
because a combining character may follow.

mercurial/mdiff.py

@@ -1,512 +1,517 b''
 # mdiff.py - diff and patch routines for mercurial
 #
 # Copyright 2005, 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import re
 import struct
 import zlib
 
 from .i18n import _
 from . import (
+    encoding,
     error,
     policy,
     pycompat,
     util,
 )
 
 _missing_newline_marker = "\\ No newline at end of file\n"
 
 bdiff = policy.importmod(r'bdiff')
 mpatch = policy.importmod(r'mpatch')
 
 blocks = bdiff.blocks
 fixws = bdiff.fixws
 patches = mpatch.patches
 patchedsize = mpatch.patchedsize
 textdiff = bdiff.bdiff
 splitnewlines = bdiff.splitnewlines
 
 class diffopts(object):
     '''context is the number of context lines
     text treats all files as text
     showfunc enables diff -p output
     git enables the git extended patch format
     nodates removes dates from diff headers
     nobinary ignores binary files
     noprefix disables the 'a/' and 'b/' prefixes (ignored in plain mode)
     ignorews ignores all whitespace changes in the diff
     ignorewsamount ignores changes in the amount of whitespace
     ignoreblanklines ignores changes whose lines are all blank
     upgrade generates git diffs to avoid data loss
     '''
 
     defaults = {
         'context': 3,
         'text': False,
         'showfunc': False,
         'git': False,
         'nodates': False,
         'nobinary': False,
         'noprefix': False,
         'index': 0,
         'ignorews': False,
         'ignorewsamount': False,
         'ignorewseol': False,
         'ignoreblanklines': False,
         'upgrade': False,
         'showsimilarity': False,
         'worddiff': False,
         }
 
     def __init__(self, **opts):
         opts = pycompat.byteskwargs(opts)
         for k in self.defaults.keys():
             v = opts.get(k)
             if v is None:
                 v = self.defaults[k]
             setattr(self, k, v)
 
         try:
             self.context = int(self.context)
         except ValueError:
             raise error.Abort(_('diff context lines count must be '
                                'an integer, not %r') % self.context)
 
     def copy(self, **kwargs):
         opts = dict((k, getattr(self, k)) for k in self.defaults)
         opts = pycompat.strkwargs(opts)
         opts.update(kwargs)
         return diffopts(**opts)
 
 defaultopts = diffopts()
 
 def wsclean(opts, text, blank=True):
     if opts.ignorews:
         text = bdiff.fixws(text, 1)
     elif opts.ignorewsamount:
         text = bdiff.fixws(text, 0)
     if blank and opts.ignoreblanklines:
         text = re.sub('\n+', '\n', text).strip('\n')
     if opts.ignorewseol:
         text = re.sub(br'[ \t\r\f]+\n', r'\n', text)
     return text
 
 def splitblock(base1, lines1, base2, lines2, opts):
     # The input lines matches except for interwoven blank lines. We
     # transform it into a sequence of matching blocks and blank blocks.
     lines1 = [(wsclean(opts, l) and 1 or 0) for l in lines1]
     lines2 = [(wsclean(opts, l) and 1 or 0) for l in lines2]
     s1, e1 = 0, len(lines1)
     s2, e2 = 0, len(lines2)
     while s1 < e1 or s2 < e2:
         i1, i2, btype = s1, s2, '='
         if (i1 >= e1 or lines1[i1] == 0
             or i2 >= e2 or lines2[i2] == 0):
             # Consume the block of blank lines
             btype = '~'
             while i1 < e1 and lines1[i1] == 0:
                 i1 += 1
             while i2 < e2 and lines2[i2] == 0:
                 i2 += 1
         else:
             # Consume the matching lines
             while i1 < e1 and lines1[i1] == 1 and lines2[i2] == 1:
                 i1 += 1
                 i2 += 1
         yield [base1 + s1, base1 + i1, base2 + s2, base2 + i2], btype
         s1 = i1
         s2 = i2
 
 def hunkinrange(hunk, linerange):
     """Return True if `hunk` defined as (start, length) is in `linerange`
     defined as (lowerbound, upperbound).
 
     >>> hunkinrange((5, 10), (2, 7))
     True
     >>> hunkinrange((5, 10), (6, 12))
     True
     >>> hunkinrange((5, 10), (13, 17))
     True
     >>> hunkinrange((5, 10), (3, 17))
     True
     >>> hunkinrange((5, 10), (1, 3))
     False
     >>> hunkinrange((5, 10), (18, 20))
     False
     >>> hunkinrange((5, 10), (1, 5))
     False
     >>> hunkinrange((5, 10), (15, 27))
     False
     """
     start, length = hunk
     lowerbound, upperbound = linerange
     return lowerbound < start + length and start < upperbound
 
 def blocksinrange(blocks, rangeb):
     """filter `blocks` like (a1, a2, b1, b2) from items outside line range
     `rangeb` from ``(b1, b2)`` point of view.
 
     Return `filteredblocks, rangea` where:
 
     * `filteredblocks` is list of ``block = (a1, a2, b1, b2), stype`` items of
       `blocks` that are inside `rangeb` from ``(b1, b2)`` point of view; a
       block ``(b1, b2)`` being inside `rangeb` if
       ``rangeb[0] < b2 and b1 < rangeb[1]``;
     * `rangea` is the line range w.r.t. to ``(a1, a2)`` parts of `blocks`.
     """
     lbb, ubb = rangeb
     lba, uba = None, None
     filteredblocks = []
     for block in blocks:
         (a1, a2, b1, b2), stype = block
         if lbb >= b1 and ubb <= b2 and stype == '=':
             # rangeb is within a single "=" hunk, restrict back linerange1
             # by offsetting rangeb
             lba = lbb - b1 + a1
             uba = ubb - b1 + a1
         else:
             if b1 <= lbb < b2:
                 if stype == '=':
                     lba = a2 - (b2 - lbb)
                 else:
                     lba = a1
             if b1 < ubb <= b2:
                 if stype == '=':
                     uba = a1 + (ubb - b1)
                 else:
                     uba = a2
         if hunkinrange((b1, (b2 - b1)), rangeb):
             filteredblocks.append(block)
     if lba is None or uba is None or uba < lba:
         raise error.Abort(_('line range exceeds file size'))
     return filteredblocks, (lba, uba)
 
 def allblocks(text1, text2, opts=None, lines1=None, lines2=None):
     """Return (block, type) tuples, where block is an mdiff.blocks
     line entry. type is '=' for blocks matching exactly one another
     (bdiff blocks), '!' for non-matching blocks and '~' for blocks
     matching only after having filtered blank lines.
     line1 and line2 are text1 and text2 split with splitnewlines() if
     they are already available.
     """
     if opts is None:
         opts = defaultopts
     if opts.ignorews or opts.ignorewsamount or opts.ignorewseol:
         text1 = wsclean(opts, text1, False)
         text2 = wsclean(opts, text2, False)
     diff = bdiff.blocks(text1, text2)
     for i, s1 in enumerate(diff):
         # The first match is special.
         # we've either found a match starting at line 0 or a match later
         # in the file.  If it starts later, old and new below will both be
         # empty and we'll continue to the next match.
         if i > 0:
             s = diff[i - 1]
         else:
             s = [0, 0, 0, 0]
         s = [s[1], s1[0], s[3], s1[2]]
 
         # bdiff sometimes gives huge matches past eof, this check eats them,
         # and deals with the special first match case described above
         if s[0] != s[1] or s[2] != s[3]:
             type = '!'
             if opts.ignoreblanklines:
                 if lines1 is None:
                     lines1 = splitnewlines(text1)
                 if lines2 is None:
                     lines2 = splitnewlines(text2)
                 old = wsclean(opts, "".join(lines1[s[0]:s[1]]))
                 new = wsclean(opts, "".join(lines2[s[2]:s[3]]))
                 if old == new:
                     type = '~'
             yield s, type
         yield s1, '='
 
 def unidiff(a, ad, b, bd, fn1, fn2, binary, opts=defaultopts):
     """Return a unified diff as a (headers, hunks) tuple.
 
     If the diff is not null, `headers` is a list with unified diff header
     lines "--- <original>" and "+++ <new>" and `hunks` is a generator yielding
     (hunkrange, hunklines) coming from _unidiff().
     Otherwise, `headers` and `hunks` are empty.
 
     Set binary=True if either a or b should be taken as a binary file.
     """
     def datetag(date, fn=None):
         if not opts.git and not opts.nodates:
             return '\t%s' % date
         if fn and ' ' in fn:
             return '\t'
         return ''
 
     sentinel = [], ()
     if not a and not b:
         return sentinel
 
     if opts.noprefix:
         aprefix = bprefix = ''
     else:
         aprefix = 'a/'
         bprefix = 'b/'
 
     epoch = util.datestr((0, 0))
 
     fn1 = util.pconvert(fn1)
     fn2 = util.pconvert(fn2)
 
     if binary:
         if a and b and len(a) == len(b) and a == b:
             return sentinel
         headerlines = []
         hunks = (None, ['Binary file %s has changed\n' % fn1]),
     elif not a:
         without_newline = not b.endswith('\n')
         b = splitnewlines(b)
         if a is None:
             l1 = '--- /dev/null%s' % datetag(epoch)
         else:
             l1 = "--- %s%s%s" % (aprefix, fn1, datetag(ad, fn1))
         l2 = "+++ %s%s" % (bprefix + fn2, datetag(bd, fn2))
         headerlines = [l1, l2]
         size = len(b)
         hunkrange = (0, 0, 1, size)
         hunklines = ["@@ -0,0 +1,%d @@\n" % size] + ["+" + e for e in b]
         if without_newline:
             hunklines[-1] += '\n'
             hunklines.append(_missing_newline_marker)
         hunks = (hunkrange, hunklines),
     elif not b:
         without_newline = not a.endswith('\n')
         a = splitnewlines(a)
         l1 = "--- %s%s%s" % (aprefix, fn1, datetag(ad, fn1))
         if b is None:
             l2 = '+++ /dev/null%s' % datetag(epoch)
         else:
             l2 = "+++ %s%s%s" % (bprefix, fn2, datetag(bd, fn2))
         headerlines = [l1, l2]
         size = len(a)
         hunkrange = (1, size, 0, 0)
         hunklines = ["@@ -1,%d +0,0 @@\n" % size] + ["-" + e for e in a]
         if without_newline:
             hunklines[-1] += '\n'
             hunklines.append(_missing_newline_marker)
         hunks = (hunkrange, hunklines),
     else:
         hunks = _unidiff(a, b, opts=opts)
         if not next(hunks):
             return sentinel
 
         headerlines = [
             "--- %s%s%s" % (aprefix, fn1, datetag(ad, fn1)),
             "+++ %s%s%s" % (bprefix, fn2, datetag(bd, fn2)),
         ]
 
     return headerlines, hunks
 
 def _unidiff(t1, t2, opts=defaultopts):
     """Yield hunks of a headerless unified diff from t1 and t2 texts.
 
     Each hunk consists of a (hunkrange, hunklines) tuple where `hunkrange` is a
     tuple (s1, l1, s2, l2) representing the range information of the hunk to
     form the '@@ -s1,l1 +s2,l2 @@' header and `hunklines` is a list of lines
     of the hunk combining said header followed by line additions and
     deletions.
 
     The hunks are prefixed with a bool.
     """
     l1 = splitnewlines(t1)
     l2 = splitnewlines(t2)
     def contextend(l, len):
         ret = l + opts.context
         if ret > len:
             ret = len
         return ret
 
     def contextstart(l):
         ret = l - opts.context
         if ret < 0:
             return 0
         return ret
 
     lastfunc = [0, '']
     def yieldhunk(hunk):
         (astart, a2, bstart, b2, delta) = hunk
         aend = contextend(a2, len(l1))
         alen = aend - astart
         blen = b2 - bstart + aend - a2
 
         func = ""
         if opts.showfunc:
             lastpos, func = lastfunc
             # walk backwards from the start of the context up to the start of
             # the previous hunk context until we find a line starting with an
             # alphanumeric char.
             for i in xrange(astart - 1, lastpos - 1, -1):
                 if l1[i][0:1].isalnum():
-                    func = ' ' + l1[i].rstrip()[:40]
+                    func = b' ' + l1[i].rstrip()
+                    # split long function name if ASCII. otherwise we have no
+                    # idea where the multi-byte boundary is, so just leave it.
+                    if encoding.isasciistr(func):
+                        func = func[:41]
                     lastfunc[1] = func
                     break
             # by recording this hunk's starting point as the next place to
             # start looking for function lines, we avoid reading any line in
             # the file more than once.
             lastfunc[0] = astart
 
         # zero-length hunk ranges report their start line as one less
         if alen:
             astart += 1
         if blen:
             bstart += 1
 
         hunkrange = astart, alen, bstart, blen
         hunklines = (
             ["@@ -%d,%d +%d,%d @@%s\n" % (hunkrange + (func,))]
             + delta
             + [' ' + l1[x] for x in xrange(a2, aend)]
         )
         # If either file ends without a newline and the last line of
         # that file is part of a hunk, a marker is printed. If the
         # last line of both files is identical and neither ends in
         # a newline, print only one marker. That's the only case in
         # which the hunk can end in a shared line without a newline.
         skip = False
         if not t1.endswith('\n') and astart + alen == len(l1) + 1:
             for i in xrange(len(hunklines) - 1, -1, -1):
                 if hunklines[i].startswith(('-', ' ')):
                     if hunklines[i].startswith(' '):
                         skip = True
                     hunklines[i] += '\n'
                     hunklines.insert(i + 1, _missing_newline_marker)
                     break
         if not skip and not t2.endswith('\n') and bstart + blen == len(l2) + 1:
             for i in xrange(len(hunklines) - 1, -1, -1):
                 if hunklines[i].startswith('+'):
                     hunklines[i] += '\n'
                     hunklines.insert(i + 1, _missing_newline_marker)
                     break
         yield hunkrange, hunklines
 
     # bdiff.blocks gives us the matching sequences in the files.  The loop
     # below finds the spaces between those matching sequences and translates
     # them into diff output.
     #
     hunk = None
     ignoredlines = 0
     has_hunks = False
     for s, stype in allblocks(t1, t2, opts, l1, l2):
         a1, a2, b1, b2 = s
         if stype != '!':
             if stype == '~':
                 # The diff context lines are based on t1 content. When
                 # blank lines are ignored, the new lines offsets must
                 # be adjusted as if equivalent blocks ('~') had the
                 # same sizes on both sides.
                 ignoredlines += (b2 - b1) - (a2 - a1)
             continue
         delta = []
         old = l1[a1:a2]
         new = l2[b1:b2]
 
         b1 -= ignoredlines
         b2 -= ignoredlines
         astart = contextstart(a1)
         bstart = contextstart(b1)
         prev = None
         if hunk:
             # join with the previous hunk if it falls inside the context
             if astart < hunk[1] + opts.context + 1:
                 prev = hunk
                 astart = hunk[1]
                 bstart = hunk[3]
             else:
                 if not has_hunks:
                     has_hunks = True
                     yield True
                 for x in yieldhunk(hunk):
                     yield x
         if prev:
             # we've joined the previous hunk, record the new ending points.
             hunk[1] = a2
             hunk[3] = b2
             delta = hunk[4]
         else:
             # create a new hunk
             hunk = [astart, a2, bstart, b2, delta]
 
         delta[len(delta):] = [' ' + x for x in l1[astart:a1]]
         delta[len(delta):] = ['-' + x for x in old]
         delta[len(delta):] = ['+' + x for x in new]
 
     if hunk:
         if not has_hunks:
             has_hunks = True
             yield True
         for x in yieldhunk(hunk):
             yield x
     elif not has_hunks:
         yield False
 
 def b85diff(to, tn):
     '''print base85-encoded binary diff'''
     def fmtline(line):
         l = len(line)
         if l <= 26:
             l = pycompat.bytechr(ord('A') + l - 1)
         else:
             l = pycompat.bytechr(l - 26 + ord('a') - 1)
         return '%c%s\n' % (l, util.b85encode(line, True))
 
     def chunk(text, csize=52):
         l = len(text)
         i = 0
         while i < l:
             yield text[i:i + csize]
             i += csize
 
     if to is None:
         to = ''
     if tn is None:
         tn = ''
 
     if to == tn:
         return ''
 
     # TODO: deltas
     ret = []
     ret.append('GIT binary patch\n')
     ret.append('literal %d\n' % len(tn))
     for l in chunk(zlib.compress(tn)):
         ret.append(fmtline(l))
     ret.append('\n')
 
     return ''.join(ret)
 
 def patchtext(bin):
     pos = 0
     t = []
     while pos < len(bin):
         p1, p2, l = struct.unpack(">lll", bin[pos:pos + 12])
         pos += 12
         t.append(bin[pos:pos + l])
         pos += l
     return "".join(t)
 
 def patch(a, bin):
     if len(a) == 0:
         # skip over trivial delta header
         return util.buffer(bin, 12)
     return mpatch.patches(a, [bin])
 
 # similar to difflib.SequenceMatcher.get_matching_blocks
 def get_matching_blocks(a, b):
     return [(d[0], d[2], d[1] - d[0]) for d in bdiff.blocks(a, b)]
 
 def trivialdiffheader(length):
     return struct.pack(">lll", 0, 0, length) if length else ''
 
 def replacediffheader(oldlen, newlen):
     return struct.pack(">lll", 0, oldlen, newlen)

tests/test-diff-unified.t

@@ -1,388 +1,458 b''
   $ hg init repo
   $ cd repo
   $ cat > a <<EOF
   > c
   > c
   > a
   > a
   > b
   > a
   > a
   > c
   > c
   > EOF
   $ hg ci -Am adda
   adding a
 
   $ cat > a <<EOF
   > c
   > c
   > a
   > a
   > dd
   > a
   > a
   > c
   > c
   > EOF
 
 default context
 
   $ hg diff --nodates
   diff -r cf9f4ba66af2 a
   --- a/a
   +++ b/a
   @@ -2,7 +2,7 @@
    c
    a
    a
   -b
   +dd
    a
    a
    c
 
 invalid --unified
 
   $ hg diff --nodates -U foo
   abort: diff context lines count must be an integer, not 'foo'
   [255]
 
 
   $ hg diff --nodates -U 2
   diff -r cf9f4ba66af2 a
   --- a/a
   +++ b/a
   @@ -3,5 +3,5 @@
    a
    a
   -b
   +dd
    a
    a
 
   $ hg --config diff.unified=2 diff --nodates
   diff -r cf9f4ba66af2 a
   --- a/a
   +++ b/a
   @@ -3,5 +3,5 @@
    a
    a
   -b
   +dd
    a
    a
 
   $ hg diff --nodates -U 1
   diff -r cf9f4ba66af2 a
   --- a/a
   +++ b/a
   @@ -4,3 +4,3 @@
    a
   -b
   +dd
    a
 
 invalid diff.unified
 
   $ hg --config diff.unified=foo diff --nodates
   abort: diff context lines count must be an integer, not 'foo'
   [255]
 
 noprefix config and option
 
   $ hg --config diff.noprefix=True diff --nodates
   diff -r cf9f4ba66af2 a
   --- a
   +++ a
   @@ -2,7 +2,7 @@
    c
    a
    a
   -b
   +dd
    a
    a
    c
   $ hg diff --noprefix --nodates
   diff -r cf9f4ba66af2 a
   --- a
   +++ a
   @@ -2,7 +2,7 @@
    c
    a
    a
   -b
   +dd
    a
    a
    c
 
 noprefix config disabled in plain mode, but option still enabled
 
   $ HGPLAIN=1 hg --config diff.noprefix=True diff --nodates
   diff -r cf9f4ba66af2 a
   --- a/a
   +++ b/a
   @@ -2,7 +2,7 @@
    c
    a
    a
   -b
   +dd
    a
    a
    c
   $ HGPLAIN=1 hg diff --noprefix --nodates
   diff -r cf9f4ba66af2 a
   --- a
   +++ a
   @@ -2,7 +2,7 @@
    c
    a
    a
   -b
   +dd
    a
    a
    c
 
   $ cd ..
 
 
 0 lines of context hunk header matches gnu diff hunk header
 
   $ hg init diffzero
   $ cd diffzero
   $ cat > f1 << EOF
   > c2
   > c4
   > c5
   > EOF
   $ hg commit -Am0
   adding f1
 
   $ cat > f2 << EOF
   > c1
   > c2
   > c3
   > c4
   > EOF
   $ mv f2 f1
   $ hg diff -U0 --nodates
   diff -r 55d8ff78db23 f1
   --- a/f1
   +++ b/f1
   @@ -0,0 +1,1 @@
   +c1
   @@ -1,0 +3,1 @@
   +c3
   @@ -3,1 +4,0 @@
   -c5
 
   $ hg diff -U0 --nodates --git
   diff --git a/f1 b/f1
   --- a/f1
   +++ b/f1
   @@ -0,0 +1,1 @@
   +c1
   @@ -1,0 +3,1 @@
   +c3
   @@ -3,1 +4,0 @@
   -c5
 
   $ hg diff -U0 --nodates -p
   diff -r 55d8ff78db23 f1
   --- a/f1
   +++ b/f1
   @@ -0,0 +1,1 @@
   +c1
   @@ -1,0 +3,1 @@ c2
   +c3
   @@ -3,1 +4,0 @@ c4
   -c5
 
   $ echo a > f1
   $ hg ci -m movef2
 
 Test diff headers terminating with TAB when necessary (issue3357)
 Regular diff --nodates, file creation
 
   $ hg mv f1 'f 1'
   $ echo b > 'f 1'
   $ hg diff --nodates 'f 1'
   diff -r 7574207d0d15 f 1
   --- /dev/null
   +++ b/f 1	
   @@ -0,0 +1,1 @@
   +b
 
 Git diff, adding space
 
   $ hg diff --git
   diff --git a/f1 b/f 1
   rename from f1
   rename to f 1
   --- a/f1
   +++ b/f 1	
   @@ -1,1 +1,1 @@
   -a
   +b
 
 Git diff, adding extended headers
 
   $ hg diff --git --config experimental.extendedheader.index=7 --config experimental.extendedheader.similarity=True
   diff --git a/f1 b/f 1
   similarity index 0%
   rename from f1
   rename to f 1
   index 7898192..6178079 100644
   --- a/f1
   +++ b/f 1	
   @@ -1,1 +1,1 @@
   -a
   +b
 
   $ hg diff --git --config experimental.extendedheader.index=-1
   invalid length for extendedheader.index: '-1'
   diff --git a/f1 b/f 1
   rename from f1
   rename to f 1
   --- a/f1
   +++ b/f 1	
   @@ -1,1 +1,1 @@
   -a
   +b
 
   $ hg diff --git --config experimental.extendedheader.index=whatever
   invalid value for extendedheader.index: 'whatever'
   diff --git a/f1 b/f 1
   rename from f1
   rename to f 1
   --- a/f1
   +++ b/f 1	
   @@ -1,1 +1,1 @@
   -a
   +b
 
 Git diff with noprefix
 
   $ hg --config diff.noprefix=True diff --git --nodates
   diff --git f1 f 1
   rename from f1
   rename to f 1
   --- f1
   +++ f 1	
   @@ -1,1 +1,1 @@
   -a
   +b
 
 noprefix config disabled in plain mode, but option still enabled
 
   $ HGPLAIN=1 hg --config diff.noprefix=True diff --git --nodates
   diff --git a/f1 b/f 1
   rename from f1
   rename to f 1
   --- a/f1
   +++ b/f 1	
   @@ -1,1 +1,1 @@
   -a
   +b
   $ HGPLAIN=1 hg diff --git --noprefix --nodates
   diff --git f1 f 1
   rename from f1
   rename to f 1
   --- f1
   +++ f 1	
   @@ -1,1 +1,1 @@
   -a
   +b
 
 Regular diff --nodates, file deletion
 
   $ hg ci -m addspace
   $ hg mv 'f 1' f1
   $ echo a > f1
   $ hg diff --nodates 'f 1'
   diff -r ca50fe67c9c7 f 1
   --- a/f 1	
   +++ /dev/null
   @@ -1,1 +0,0 @@
   -b
 
 Git diff, removing space
 
   $ hg diff --git
   diff --git a/f 1 b/f1
   rename from f 1
   rename to f1
   --- a/f 1	
   +++ b/f1
   @@ -1,1 +1,1 @@
   -b
   +a
 
 showfunc diff
   $ cat > f1 << EOF
   > int main() {
   >     int a = 0;
   >     int b = 1;
   >     int c = 2;
   >     int d = 3;
   >     return a + b + c + d;
   > }
   > EOF
   $ hg commit -m addfunction
   $ cat > f1 << EOF
   > int main() {
   >     int a = 0;
   >     int b = 1;
   >     int c = 2;
   >     int e = 3;
   >     return a + b + c + e;
   > }
   > EOF
   $ hg diff --git
   diff --git a/f1 b/f1
   --- a/f1
   +++ b/f1
   @@ -2,6 +2,6 @@
        int a = 0;
        int b = 1;
        int c = 2;
   -    int d = 3;
   -    return a + b + c + d;
   +    int e = 3;
   +    return a + b + c + e;
    }
   $ hg diff --config diff.showfunc=True --git
   diff --git a/f1 b/f1
   --- a/f1
   +++ b/f1
   @@ -2,6 +2,6 @@ int main() {
        int a = 0;
        int b = 1;
        int c = 2;
   -    int d = 3;
   -    return a + b + c + d;
   +    int e = 3;
   +    return a + b + c + e;
    }
 
 If [diff] git is set to true, but the user says --no-git, we should
 *not* get git diffs
   $ hg diff --nodates --config diff.git=1 --no-git
   diff -r f2c7c817fa55 f1
   --- a/f1
   +++ b/f1
   @@ -2,6 +2,6 @@
        int a = 0;
        int b = 1;
        int c = 2;
   -    int d = 3;
   -    return a + b + c + d;
   +    int e = 3;
   +    return a + b + c + e;
    }
 
   $ cd ..
+
+Long function names should be abbreviated, but multi-byte character shouldn't
+be broken up
+
+  $ hg init longfunc
+  $ cd longfunc
+
+  >>> with open('a', 'wb') as f:
+  ...     f.write(b'a' * 39 + b'bb' + b'\n')
+  ...     f.write(b' .\n' * 3)
+  ...     f.write(b' 0 b\n')
+  ...     f.write(b' .\n' * 3)
+  ...     f.write(b'a' * 39 + b'\xc3\xa0' + b'\n')
+  ...     f.write(b' .\n' * 3)
+  ...     f.write(b' 0 a with grave (single code point)\n')
+  ...     f.write(b' .\n' * 3)
+  ...     f.write(b'a' * 39 + b'a\xcc\x80' + b'\n')
+  ...     f.write(b' .\n' * 3)
+  ...     f.write(b' 0 a with grave (composition)\n')
+  ...     f.write(b' .\n' * 3)
+  $ hg ci -qAm0
+
+  >>> with open('a', 'wb') as f:
+  ...     f.write(b'a' * 39 + b'bb' + b'\n')
+  ...     f.write(b' .\n' * 3)
+  ...     f.write(b' 1 b\n')
+  ...     f.write(b' .\n' * 3)
+  ...     f.write(b'a' * 39 + b'\xc3\xa0' + b'\n')
+  ...     f.write(b' .\n' * 3)
+  ...     f.write(b' 1 a with grave (single code point)\n')
+  ...     f.write(b' .\n' * 3)
+  ...     f.write(b'a' * 39 + b'a\xcc\x80' + b'\n')
+  ...     f.write(b' .\n' * 3)
+  ...     f.write(b' 1 a with grave (composition)\n')
+  ...     f.write(b' .\n' * 3)
+  $ hg ci -m1
+
+  $ hg diff -c1 --nodates --show-function
+  diff -r 3e92dd6fa812 -r a256341606cb a
+  --- a/a
+  +++ b/a
+  @@ -2,7 +2,7 @@ aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaab
+    .
+    .
+    .
+  - 0 b
+  + 1 b
+    .
+    .
+    .
+  @@ -10,7 +10,7 @@ aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\xc3\xa0 (esc)
+    .
+    .
+    .
+  - 0 a with grave (single code point)
+  + 1 a with grave (single code point)
+    .
+    .
+    .
+  @@ -18,7 +18,7 @@ aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\xcc\x80 (esc)
+    .
+    .
+    .
+  - 0 a with grave (composition)
+  + 1 a with grave (composition)
+    .
+    .
+    .
+
+  $ cd ..