diff options
Diffstat (limited to 'app/xterm/wcwidth.c')
| -rw-r--r-- | app/xterm/wcwidth.c | 94 |
1 files changed, 57 insertions, 37 deletions
diff --git a/app/xterm/wcwidth.c b/app/xterm/wcwidth.c index 5d0a4913d..77e101556 100644 --- a/app/xterm/wcwidth.c +++ b/app/xterm/wcwidth.c @@ -1,4 +1,4 @@ -/* $XTermId: wcwidth.c,v 1.19 2006/06/19 00:36:52 tom Exp $ */ +/* $XTermId: wcwidth.c,v 1.22 2009/02/13 19:53:12 tom Exp $ */ /* $XFree86: xc/programs/xterm/wcwidth.c,v 1.9 2006/06/19 00:36:52 dickey Exp $ */ @@ -54,7 +54,7 @@ * * http://www.unicode.org/unicode/reports/tr11/ * - * Markus Kuhn -- 2003-05-20 (Unicode 4.0) + * Markus Kuhn -- 2007-05-25 (Unicode 5.0) * * Permission to use, copy, modify, and distribute this software * for any purpose and without fee is hereby granted. The author @@ -128,15 +128,17 @@ int mk_wcwidth(wchar_t ucs) unsigned long cmp = (unsigned long) ucs; /* sorted list of non-overlapping intervals of non-spacing characters */ - /* generated by "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c" */ + /* generated by + * uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c + */ static const struct interval combining[] = { { 0x0300, 0x036F }, { 0x0483, 0x0486 }, { 0x0488, 0x0489 }, - { 0x0591, 0x05B9 }, { 0x05BB, 0x05BD }, { 0x05BF, 0x05BF }, - { 0x05C1, 0x05C2 }, { 0x05C4, 0x05C5 }, { 0x05C7, 0x05C7 }, - { 0x0600, 0x0603 }, { 0x0610, 0x0615 }, { 0x064B, 0x065E }, - { 0x0670, 0x0670 }, { 0x06D6, 0x06E4 }, { 0x06E7, 0x06E8 }, - { 0x06EA, 0x06ED }, { 0x070F, 0x070F }, { 0x0711, 0x0711 }, - { 0x0730, 0x074A }, { 0x07A6, 0x07B0 }, { 0x0901, 0x0902 }, + { 0x0591, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 }, + { 0x05C4, 0x05C5 }, { 0x05C7, 0x05C7 }, { 0x0600, 0x0603 }, + { 0x0610, 0x0615 }, { 0x064B, 0x065E }, { 0x0670, 0x0670 }, + { 0x06D6, 0x06E4 }, { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED }, + { 0x070F, 0x070F }, { 0x0711, 0x0711 }, { 0x0730, 0x074A }, + { 0x07A6, 0x07B0 }, { 0x07EB, 0x07F3 }, { 0x0901, 0x0902 }, { 0x093C, 0x093C }, { 0x0941, 0x0948 }, { 0x094D, 0x094D }, { 0x0951, 0x0954 }, { 0x0962, 0x0963 }, { 0x0981, 0x0981 }, { 0x09BC, 0x09BC }, { 0x09C1, 0x09C4 }, { 0x09CD, 0x09CD }, @@ -150,31 +152,34 @@ int mk_wcwidth(wchar_t ucs) { 0x0BCD, 0x0BCD }, { 0x0C3E, 0x0C40 }, { 0x0C46, 0x0C48 }, { 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 }, { 0x0CBC, 0x0CBC }, { 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 }, { 0x0CCC, 0x0CCD }, - { 0x0D41, 0x0D43 }, { 0x0D4D, 0x0D4D }, { 0x0DCA, 0x0DCA }, - { 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 }, { 0x0E31, 0x0E31 }, - { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E }, { 0x0EB1, 0x0EB1 }, - { 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC }, { 0x0EC8, 0x0ECD }, - { 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 }, { 0x0F37, 0x0F37 }, - { 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E }, { 0x0F80, 0x0F84 }, - { 0x0F86, 0x0F87 }, { 0x0F90, 0x0F97 }, { 0x0F99, 0x0FBC }, - { 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 }, { 0x1032, 0x1032 }, - { 0x1036, 0x1037 }, { 0x1039, 0x1039 }, { 0x1058, 0x1059 }, - { 0x1160, 0x11FF }, { 0x135F, 0x135F }, { 0x1712, 0x1714 }, - { 0x1732, 0x1734 }, { 0x1752, 0x1753 }, { 0x1772, 0x1773 }, - { 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD }, { 0x17C6, 0x17C6 }, - { 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD }, { 0x180B, 0x180D }, - { 0x18A9, 0x18A9 }, { 0x1920, 0x1922 }, { 0x1927, 0x1928 }, - { 0x1932, 0x1932 }, { 0x1939, 0x193B }, { 0x1A17, 0x1A18 }, - { 0x1DC0, 0x1DC3 }, { 0x200B, 0x200F }, { 0x202A, 0x202E }, - { 0x2060, 0x2063 }, { 0x206A, 0x206F }, { 0x20D0, 0x20EB }, - { 0x302A, 0x302F }, { 0x3099, 0x309A }, { 0xA806, 0xA806 }, - { 0xA80B, 0xA80B }, { 0xA825, 0xA826 }, { 0xFB1E, 0xFB1E }, - { 0xFE00, 0xFE0F }, { 0xFE20, 0xFE23 }, { 0xFEFF, 0xFEFF }, - { 0xFFF9, 0xFFFB }, { 0x10A01, 0x10A03 }, { 0x10A05, 0x10A06 }, - { 0x10A0C, 0x10A0F }, { 0x10A38, 0x10A3A }, { 0x10A3F, 0x10A3F }, - { 0x1D167, 0x1D169 }, { 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B }, - { 0x1D1AA, 0x1D1AD }, { 0x1D242, 0x1D244 }, { 0xE0001, 0xE0001 }, - { 0xE0020, 0xE007F }, { 0xE0100, 0xE01EF } + { 0x0CE2, 0x0CE3 }, { 0x0D41, 0x0D43 }, { 0x0D4D, 0x0D4D }, + { 0x0DCA, 0x0DCA }, { 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 }, + { 0x0E31, 0x0E31 }, { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E }, + { 0x0EB1, 0x0EB1 }, { 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC }, + { 0x0EC8, 0x0ECD }, { 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 }, + { 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E }, + { 0x0F80, 0x0F84 }, { 0x0F86, 0x0F87 }, { 0x0F90, 0x0F97 }, + { 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 }, + { 0x1032, 0x1032 }, { 0x1036, 0x1037 }, { 0x1039, 0x1039 }, + { 0x1058, 0x1059 }, { 0x1160, 0x11FF }, { 0x135F, 0x135F }, + { 0x1712, 0x1714 }, { 0x1732, 0x1734 }, { 0x1752, 0x1753 }, + { 0x1772, 0x1773 }, { 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD }, + { 0x17C6, 0x17C6 }, { 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD }, + { 0x180B, 0x180D }, { 0x18A9, 0x18A9 }, { 0x1920, 0x1922 }, + { 0x1927, 0x1928 }, { 0x1932, 0x1932 }, { 0x1939, 0x193B }, + { 0x1A17, 0x1A18 }, { 0x1B00, 0x1B03 }, { 0x1B34, 0x1B34 }, + { 0x1B36, 0x1B3A }, { 0x1B3C, 0x1B3C }, { 0x1B42, 0x1B42 }, + { 0x1B6B, 0x1B73 }, { 0x1DC0, 0x1DCA }, { 0x1DFE, 0x1DFF }, + { 0x200B, 0x200F }, { 0x202A, 0x202E }, { 0x2060, 0x2063 }, + { 0x206A, 0x206F }, { 0x20D0, 0x20EF }, { 0x302A, 0x302F }, + { 0x3099, 0x309A }, { 0xA806, 0xA806 }, { 0xA80B, 0xA80B }, + { 0xA825, 0xA826 }, { 0xFB1E, 0xFB1E }, { 0xFE00, 0xFE0F }, + { 0xFE20, 0xFE23 }, { 0xFEFF, 0xFEFF }, { 0xFFF9, 0xFFFB }, + { 0x10A01, 0x10A03 }, { 0x10A05, 0x10A06 }, { 0x10A0C, 0x10A0F }, + { 0x10A38, 0x10A3A }, { 0x10A3F, 0x10A3F }, { 0x1D167, 0x1D169 }, + { 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B }, { 0x1D1AA, 0x1D1AD }, + { 0x1D242, 0x1D244 }, { 0xE0001, 0xE0001 }, { 0xE0020, 0xE007F }, + { 0xE0100, 0xE01EF } }; /* test for 8-bit control characters */ @@ -185,7 +190,7 @@ int mk_wcwidth(wchar_t ucs) /* binary search in table of non-spacing characters */ if (bisearch(cmp, combining, - sizeof(combining) / sizeof(struct interval) - 1)) + (int) (sizeof(combining) / sizeof(struct interval) - 1))) return 0; /* if we arrive here, cmp is not a combining or C0/C1 control character */ @@ -198,6 +203,7 @@ int mk_wcwidth(wchar_t ucs) cmp != 0x303f) || /* CJK ... Yi */ (cmp >= 0xac00 && cmp <= 0xd7a3) || /* Hangul Syllables */ (cmp >= 0xf900 && cmp <= 0xfaff) || /* CJK Compatibility Ideographs */ + (cmp >= 0xfe10 && cmp <= 0xfe19) || /* Vertical forms */ (cmp >= 0xfe30 && cmp <= 0xfe6f) || /* CJK Compatibility Forms */ (cmp >= 0xff00 && cmp <= 0xff60) || /* Fullwidth Forms */ (cmp >= 0xffe0 && cmp <= 0xffe6) || @@ -232,7 +238,21 @@ int mk_wcswidth(const wchar_t *pwcs, size_t n) int mk_wcwidth_cjk(wchar_t ucs) { /* sorted list of non-overlapping intervals of East Asian Ambiguous - * characters, generated by "uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c" */ + * characters, generated by + * + * uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf \ + * +E000..F8FF \ + * +F0000..FFFFD \ + * +100000..10FFFD c + * + * "WIDTH-A" is a file extracted from EastAsianWidth.txt by selecting + * only those with width "A", and omitting: + * + * 0xAD + * all lines with "COMBINING" + * + * (uniset does not recognize the range expressions in WIDTH-A). + */ static const struct interval ambiguous[] = { { 0x00A1, 0x00A1 }, { 0x00A4, 0x00A4 }, { 0x00A7, 0x00A8 }, { 0x00AA, 0x00AA }, { 0x00AE, 0x00AE }, { 0x00B0, 0x00B4 }, @@ -290,7 +310,7 @@ int mk_wcwidth_cjk(wchar_t ucs) /* binary search in table of non-spacing characters */ if (bisearch((unsigned long) ucs, ambiguous, - sizeof(ambiguous) / sizeof(struct interval) - 1)) + (int) (sizeof(ambiguous) / sizeof(struct interval) - 1))) return 2; return mk_wcwidth(ucs); |