From d813ab970db8b57b70bdd1b7e5feddec1c3fd84e Mon Sep 17 00:00:00 2001 From: =?utf8?q?Torsten=20B=C3=B6gershausen?= Date: Mon, 7 Apr 2014 21:39:41 +0200 Subject: [PATCH] utf8.c: partially update to version 6.3 MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Unicode 6.3 defines more code points as combining or accents. For example, the character "ö" could be expressed as an "o" followed by U+0308 COMBINING DIARESIS (aka umlaut, double-dot-above). We should consider that such a sequence of two codepoints occupies one display column for the alignment purposes, and for that, git_wcwidth() should return 0 for them. Affected codepoints are: U+0358..U+035C U+0487 U+05A2, U+05BA, U+05C5, U+05C7 U+0604, U+0616..U+061A, U+0659..U+065F Earlier unicode standards had defined these as "reserved". Only the range 0..U+07FF has been checked to see which codepoints need to be marked as 0-width while preparing for this commit; more updates may be needed. Signed-off-by: Torsten Bögershausen Signed-off-by: Junio C Hamano --- utf8.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/utf8.c b/utf8.c index 0d20e0acb2..536a9c83e1 100644 --- a/utf8.c +++ b/utf8.c @@ -84,11 +84,10 @@ static int git_wcwidth(ucs_char_t ch) * "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c". */ static const struct interval combining[] = { - { 0x0300, 0x0357 }, { 0x035D, 0x036F }, { 0x0483, 0x0486 }, - { 0x0488, 0x0489 }, { 0x0591, 0x05A1 }, { 0x05A3, 0x05B9 }, - { 0x05BB, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 }, - { 0x05C4, 0x05C4 }, { 0x0600, 0x0603 }, { 0x0610, 0x0615 }, - { 0x064B, 0x0658 }, { 0x0670, 0x0670 }, { 0x06D6, 0x06E4 }, + { 0x0300, 0x036F }, { 0x0483, 0x0489 }, { 0x0591, 0x05BD }, + { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 }, { 0x05C4, 0x05C5 }, + { 0x05C7, 0x05C7 }, { 0x0600, 0x0604 }, { 0x0610, 0x061A }, + { 0x064B, 0x065F }, { 0x0670, 0x0670 }, { 0x06D6, 0x06E4 }, { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED }, { 0x070F, 0x070F }, { 0x0711, 0x0711 }, { 0x0730, 0x074A }, { 0x07A6, 0x07B0 }, { 0x0901, 0x0902 }, { 0x093C, 0x093C }, { 0x0941, 0x0948 }, -- 2.11.4.GIT