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

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.

--- a/mercurial/mdiff.py	Sun Feb 25 11:20:35 2018 +0900
+++ b/mercurial/mdiff.py	Fri Feb 23 23:09:58 2018 +0900
@@ -13,6 +13,7 @@
 
 from .i18n import _
 from . import (
+    encoding,
     error,
     policy,
     pycompat,
@@ -348,7 +349,11 @@
             # 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

--- a/tests/test-diff-unified.t	Sun Feb 25 11:20:35 2018 +0900
+++ b/tests/test-diff-unified.t	Fri Feb 23 23:09:58 2018 +0900
@@ -386,3 +386,73 @@
    }
 
   $ 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 ..