diff options
| -rw-r--r-- | src/mbyte.c | 597 | ||||
| -rw-r--r-- | src/proto/mbyte.pro | 1 | ||||
| -rw-r--r-- | src/screen.c | 4 | ||||
| -rw-r--r-- | src/version.c | 2 |
4 files changed, 308 insertions, 296 deletions
diff --git a/src/mbyte.c b/src/mbyte.c index f38e63e77..6d419b2e4 100644 --- a/src/mbyte.c +++ b/src/mbyte.c @@ -1210,6 +1210,185 @@ intable(struct interval *table, size_t size, int c) return FALSE; } +/* Sorted list of non-overlapping intervals of East Asian Ambiguous + * characters, generated with ../runtime/tools/unicode.vim. */ +static struct interval ambiguous[] = +{ + {0x00a1, 0x00a1}, + {0x00a4, 0x00a4}, + {0x00a7, 0x00a8}, + {0x00aa, 0x00aa}, + {0x00ad, 0x00ae}, + {0x00b0, 0x00b4}, + {0x00b6, 0x00ba}, + {0x00bc, 0x00bf}, + {0x00c6, 0x00c6}, + {0x00d0, 0x00d0}, + {0x00d7, 0x00d8}, + {0x00de, 0x00e1}, + {0x00e6, 0x00e6}, + {0x00e8, 0x00ea}, + {0x00ec, 0x00ed}, + {0x00f0, 0x00f0}, + {0x00f2, 0x00f3}, + {0x00f7, 0x00fa}, + {0x00fc, 0x00fc}, + {0x00fe, 0x00fe}, + {0x0101, 0x0101}, + {0x0111, 0x0111}, + {0x0113, 0x0113}, + {0x011b, 0x011b}, + {0x0126, 0x0127}, + {0x012b, 0x012b}, + {0x0131, 0x0133}, + {0x0138, 0x0138}, + {0x013f, 0x0142}, + {0x0144, 0x0144}, + {0x0148, 0x014b}, + {0x014d, 0x014d}, + {0x0152, 0x0153}, + {0x0166, 0x0167}, + {0x016b, 0x016b}, + {0x01ce, 0x01ce}, + {0x01d0, 0x01d0}, + {0x01d2, 0x01d2}, + {0x01d4, 0x01d4}, + {0x01d6, 0x01d6}, + {0x01d8, 0x01d8}, + {0x01da, 0x01da}, + {0x01dc, 0x01dc}, + {0x0251, 0x0251}, + {0x0261, 0x0261}, + {0x02c4, 0x02c4}, + {0x02c7, 0x02c7}, + {0x02c9, 0x02cb}, + {0x02cd, 0x02cd}, + {0x02d0, 0x02d0}, + {0x02d8, 0x02db}, + {0x02dd, 0x02dd}, + {0x02df, 0x02df}, + {0x0300, 0x036f}, + {0x0391, 0x03a1}, + {0x03a3, 0x03a9}, + {0x03b1, 0x03c1}, + {0x03c3, 0x03c9}, + {0x0401, 0x0401}, + {0x0410, 0x044f}, + {0x0451, 0x0451}, + {0x2010, 0x2010}, + {0x2013, 0x2016}, + {0x2018, 0x2019}, + {0x201c, 0x201d}, + {0x2020, 0x2022}, + {0x2024, 0x2027}, + {0x2030, 0x2030}, + {0x2032, 0x2033}, + {0x2035, 0x2035}, + {0x203b, 0x203b}, + {0x203e, 0x203e}, + {0x2074, 0x2074}, + {0x207f, 0x207f}, + {0x2081, 0x2084}, + {0x20ac, 0x20ac}, + {0x2103, 0x2103}, + {0x2105, 0x2105}, + {0x2109, 0x2109}, + {0x2113, 0x2113}, + {0x2116, 0x2116}, + {0x2121, 0x2122}, + {0x2126, 0x2126}, + {0x212b, 0x212b}, + {0x2153, 0x2154}, + {0x215b, 0x215e}, + {0x2160, 0x216b}, + {0x2170, 0x2179}, + {0x2189, 0x2189}, + {0x2190, 0x2199}, + {0x21b8, 0x21b9}, + {0x21d2, 0x21d2}, + {0x21d4, 0x21d4}, + {0x21e7, 0x21e7}, + {0x2200, 0x2200}, + {0x2202, 0x2203}, + {0x2207, 0x2208}, + {0x220b, 0x220b}, + {0x220f, 0x220f}, + {0x2211, 0x2211}, + {0x2215, 0x2215}, + {0x221a, 0x221a}, + {0x221d, 0x2220}, + {0x2223, 0x2223}, + {0x2225, 0x2225}, + {0x2227, 0x222c}, + {0x222e, 0x222e}, + {0x2234, 0x2237}, + {0x223c, 0x223d}, + {0x2248, 0x2248}, + {0x224c, 0x224c}, + {0x2252, 0x2252}, + {0x2260, 0x2261}, + {0x2264, 0x2267}, + {0x226a, 0x226b}, + {0x226e, 0x226f}, + {0x2282, 0x2283}, + {0x2286, 0x2287}, + {0x2295, 0x2295}, + {0x2299, 0x2299}, + {0x22a5, 0x22a5}, + {0x22bf, 0x22bf}, + {0x2312, 0x2312}, + {0x2460, 0x24e9}, + {0x24eb, 0x254b}, + {0x2550, 0x2573}, + {0x2580, 0x258f}, + {0x2592, 0x2595}, + {0x25a0, 0x25a1}, + {0x25a3, 0x25a9}, + {0x25b2, 0x25b3}, + {0x25b6, 0x25b7}, + {0x25bc, 0x25bd}, + {0x25c0, 0x25c1}, + {0x25c6, 0x25c8}, + {0x25cb, 0x25cb}, + {0x25ce, 0x25d1}, + {0x25e2, 0x25e5}, + {0x25ef, 0x25ef}, + {0x2605, 0x2606}, + {0x2609, 0x2609}, + {0x260e, 0x260f}, + {0x2614, 0x2615}, + {0x261c, 0x261c}, + {0x261e, 0x261e}, + {0x2640, 0x2640}, + {0x2642, 0x2642}, + {0x2660, 0x2661}, + {0x2663, 0x2665}, + {0x2667, 0x266a}, + {0x266c, 0x266d}, + {0x266f, 0x266f}, + {0x269e, 0x269f}, + {0x26be, 0x26bf}, + {0x26c4, 0x26cd}, + {0x26cf, 0x26e1}, + {0x26e3, 0x26e3}, + {0x26e8, 0x26ff}, + {0x273d, 0x273d}, + {0x2757, 0x2757}, + {0x2776, 0x277f}, + {0x2b55, 0x2b59}, + {0x3248, 0x324f}, + {0xe000, 0xf8ff}, + {0xfe00, 0xfe0f}, + {0xfffd, 0xfffd}, + {0x1f100, 0x1f10a}, + {0x1f110, 0x1f12d}, + {0x1f130, 0x1f169}, + {0x1f170, 0x1f19a}, + {0xe0100, 0xe01ef}, + {0xf0000, 0xffffd}, + {0x100000, 0x10fffd} +}; + /* * For UTF-8 character "c" return 2 for a double-width character, 1 for others. * Returns 4 or 6 for an unprintable character. @@ -1261,185 +1440,6 @@ utf_char2cells(int c) {0x30000, 0x3fffd} }; - /* Sorted list of non-overlapping intervals of East Asian Ambiguous - * characters, generated with ../runtime/tools/unicode.vim. */ - static struct interval ambiguous[] = - { - {0x00a1, 0x00a1}, - {0x00a4, 0x00a4}, - {0x00a7, 0x00a8}, - {0x00aa, 0x00aa}, - {0x00ad, 0x00ae}, - {0x00b0, 0x00b4}, - {0x00b6, 0x00ba}, - {0x00bc, 0x00bf}, - {0x00c6, 0x00c6}, - {0x00d0, 0x00d0}, - {0x00d7, 0x00d8}, - {0x00de, 0x00e1}, - {0x00e6, 0x00e6}, - {0x00e8, 0x00ea}, - {0x00ec, 0x00ed}, - {0x00f0, 0x00f0}, - {0x00f2, 0x00f3}, - {0x00f7, 0x00fa}, - {0x00fc, 0x00fc}, - {0x00fe, 0x00fe}, - {0x0101, 0x0101}, - {0x0111, 0x0111}, - {0x0113, 0x0113}, - {0x011b, 0x011b}, - {0x0126, 0x0127}, - {0x012b, 0x012b}, - {0x0131, 0x0133}, - {0x0138, 0x0138}, - {0x013f, 0x0142}, - {0x0144, 0x0144}, - {0x0148, 0x014b}, - {0x014d, 0x014d}, - {0x0152, 0x0153}, - {0x0166, 0x0167}, - {0x016b, 0x016b}, - {0x01ce, 0x01ce}, - {0x01d0, 0x01d0}, - {0x01d2, 0x01d2}, - {0x01d4, 0x01d4}, - {0x01d6, 0x01d6}, - {0x01d8, 0x01d8}, - {0x01da, 0x01da}, - {0x01dc, 0x01dc}, - {0x0251, 0x0251}, - {0x0261, 0x0261}, - {0x02c4, 0x02c4}, - {0x02c7, 0x02c7}, - {0x02c9, 0x02cb}, - {0x02cd, 0x02cd}, - {0x02d0, 0x02d0}, - {0x02d8, 0x02db}, - {0x02dd, 0x02dd}, - {0x02df, 0x02df}, - {0x0300, 0x036f}, - {0x0391, 0x03a1}, - {0x03a3, 0x03a9}, - {0x03b1, 0x03c1}, - {0x03c3, 0x03c9}, - {0x0401, 0x0401}, - {0x0410, 0x044f}, - {0x0451, 0x0451}, - {0x2010, 0x2010}, - {0x2013, 0x2016}, - {0x2018, 0x2019}, - {0x201c, 0x201d}, - {0x2020, 0x2022}, - {0x2024, 0x2027}, - {0x2030, 0x2030}, - {0x2032, 0x2033}, - {0x2035, 0x2035}, - {0x203b, 0x203b}, - {0x203e, 0x203e}, - {0x2074, 0x2074}, - {0x207f, 0x207f}, - {0x2081, 0x2084}, - {0x20ac, 0x20ac}, - {0x2103, 0x2103}, - {0x2105, 0x2105}, - {0x2109, 0x2109}, - {0x2113, 0x2113}, - {0x2116, 0x2116}, - {0x2121, 0x2122}, - {0x2126, 0x2126}, - {0x212b, 0x212b}, - {0x2153, 0x2154}, - {0x215b, 0x215e}, - {0x2160, 0x216b}, - {0x2170, 0x2179}, - {0x2189, 0x2189}, - {0x2190, 0x2199}, - {0x21b8, 0x21b9}, - {0x21d2, 0x21d2}, - {0x21d4, 0x21d4}, - {0x21e7, 0x21e7}, - {0x2200, 0x2200}, - {0x2202, 0x2203}, - {0x2207, 0x2208}, - {0x220b, 0x220b}, - {0x220f, 0x220f}, - {0x2211, 0x2211}, - {0x2215, 0x2215}, - {0x221a, 0x221a}, - {0x221d, 0x2220}, - {0x2223, 0x2223}, - {0x2225, 0x2225}, - {0x2227, 0x222c}, - {0x222e, 0x222e}, - {0x2234, 0x2237}, - {0x223c, 0x223d}, - {0x2248, 0x2248}, - {0x224c, 0x224c}, - {0x2252, 0x2252}, - {0x2260, 0x2261}, - {0x2264, 0x2267}, - {0x226a, 0x226b}, - {0x226e, 0x226f}, - {0x2282, 0x2283}, - {0x2286, 0x2287}, - {0x2295, 0x2295}, - {0x2299, 0x2299}, - {0x22a5, 0x22a5}, - {0x22bf, 0x22bf}, - {0x2312, 0x2312}, - {0x2460, 0x24e9}, - {0x24eb, 0x254b}, - {0x2550, 0x2573}, - {0x2580, 0x258f}, - {0x2592, 0x2595}, - {0x25a0, 0x25a1}, - {0x25a3, 0x25a9}, - {0x25b2, 0x25b3}, - {0x25b6, 0x25b7}, - {0x25bc, 0x25bd}, - {0x25c0, 0x25c1}, - {0x25c6, 0x25c8}, - {0x25cb, 0x25cb}, - {0x25ce, 0x25d1}, - {0x25e2, 0x25e5}, - {0x25ef, 0x25ef}, - {0x2605, 0x2606}, - {0x2609, 0x2609}, - {0x260e, 0x260f}, - {0x2614, 0x2615}, - {0x261c, 0x261c}, - {0x261e, 0x261e}, - {0x2640, 0x2640}, - {0x2642, 0x2642}, - {0x2660, 0x2661}, - {0x2663, 0x2665}, - {0x2667, 0x266a}, - {0x266c, 0x266d}, - {0x266f, 0x266f}, - {0x269e, 0x269f}, - {0x26be, 0x26bf}, - {0x26c4, 0x26cd}, - {0x26cf, 0x26e1}, - {0x26e3, 0x26e3}, - {0x26e8, 0x26ff}, - {0x273d, 0x273d}, - {0x2757, 0x2757}, - {0x2776, 0x277f}, - {0x2b55, 0x2b59}, - {0x3248, 0x324f}, - {0xe000, 0xf8ff}, - {0xfe00, 0xfe0f}, - {0xfffd, 0xfffd}, - {0x1f100, 0x1f10a}, - {0x1f110, 0x1f12d}, - {0x1f130, 0x1f169}, - {0x1f170, 0x1f19a}, - {0xe0100, 0xe01ef}, - {0xf0000, 0xffffd}, - {0x100000, 0x10fffd} - }; - /* Sorted list of non-overlapping intervals of Emoji characters that don't * have ambiguous or double width, * based on http://unicode.org/emoji/charts/emoji-list.html */ @@ -2478,6 +2478,122 @@ utf_printable(int c) #endif } +/* Sorted list of non-overlapping intervals of all Emoji characters, + * based on http://unicode.org/emoji/charts/emoji-list.html */ +static struct interval emoji_all[] = +{ + {0x203c, 0x203c}, + {0x2049, 0x2049}, + {0x2122, 0x2122}, + {0x2139, 0x2139}, + {0x2194, 0x2199}, + {0x21a9, 0x21aa}, + {0x231a, 0x231b}, + {0x2328, 0x2328}, + {0x23cf, 0x23cf}, + {0x23e9, 0x23f3}, + {0x24c2, 0x24c2}, + {0x25aa, 0x25ab}, + {0x25b6, 0x25b6}, + {0x25c0, 0x25c0}, + {0x25fb, 0x25fe}, + {0x2600, 0x2604}, + {0x260e, 0x260e}, + {0x2611, 0x2611}, + {0x2614, 0x2615}, + {0x2618, 0x2618}, + {0x261d, 0x261d}, + {0x2620, 0x2620}, + {0x2622, 0x2623}, + {0x2626, 0x2626}, + {0x262a, 0x262a}, + {0x262e, 0x262f}, + {0x2638, 0x263a}, + {0x2648, 0x2653}, + {0x2660, 0x2660}, + {0x2663, 0x2663}, + {0x2665, 0x2666}, + {0x2668, 0x2668}, + {0x267b, 0x267b}, + {0x267f, 0x267f}, + {0x2692, 0x2694}, + {0x2696, 0x2697}, + {0x2699, 0x2699}, + {0x269b, 0x269c}, + {0x26a0, 0x26a1}, + {0x26aa, 0x26ab}, + {0x26b0, 0x26b1}, + {0x26bd, 0x26be}, + {0x26c4, 0x26c5}, + {0x26c8, 0x26c8}, + {0x26ce, 0x26cf}, + {0x26d1, 0x26d1}, + {0x26d3, 0x26d4}, + {0x26e9, 0x26ea}, + {0x26f0, 0x26f5}, + {0x26f7, 0x26fa}, + {0x26fd, 0x26fd}, + {0x2702, 0x2702}, + {0x2705, 0x2705}, + {0x2708, 0x270d}, + {0x270f, 0x270f}, + {0x2712, 0x2712}, + {0x2714, 0x2714}, + {0x2716, 0x2716}, + {0x271d, 0x271d}, + {0x2721, 0x2721}, + {0x2728, 0x2728}, + {0x2733, 0x2734}, + {0x2744, 0x2744}, + {0x2747, 0x2747}, + {0x274c, 0x274c}, + {0x274e, 0x274e}, + {0x2753, 0x2755}, + {0x2757, 0x2757}, + {0x2763, 0x2764}, + {0x2795, 0x2797}, + {0x27a1, 0x27a1}, + {0x27b0, 0x27b0}, + {0x27bf, 0x27bf}, + {0x2934, 0x2935}, + {0x2b05, 0x2b07}, + {0x2b1b, 0x2b1c}, + {0x2b50, 0x2b50}, + {0x2b55, 0x2b55}, + {0x3030, 0x3030}, + {0x303d, 0x303d}, + {0x3297, 0x3297}, + {0x3299, 0x3299}, + {0x1f004, 0x1f004}, + {0x1f0cf, 0x1f0cf}, + {0x1f170, 0x1f171}, + {0x1f17e, 0x1f17f}, + {0x1f18e, 0x1f18e}, + {0x1f191, 0x1f19a}, + {0x1f1e6, 0x1f1ff}, + {0x1f201, 0x1f202}, + {0x1f21a, 0x1f21a}, + {0x1f22f, 0x1f22f}, + {0x1f232, 0x1f23a}, + {0x1f250, 0x1f251}, + {0x1f300, 0x1f320}, + {0x1f330, 0x1f335}, + {0x1f337, 0x1f37c}, + {0x1f380, 0x1f393}, + {0x1f3a0, 0x1f3c4}, + {0x1f3c6, 0x1f3ca}, + {0x1f3e0, 0x1f3f0}, + {0x1f400, 0x1f43e}, + {0x1f440, 0x1f440}, + {0x1f442, 0x1f4f7}, + {0x1f4f9, 0x1f4fc}, + {0x1f500, 0x1f53d}, + {0x1f550, 0x1f567}, + {0x1f5fb, 0x1f640}, + {0x1f645, 0x1f64f}, + {0x1f680, 0x1f6c5} +}; + /* * Get class of a Unicode character. * 0: white space @@ -2564,122 +2680,6 @@ utf_class(int c) {0x2f800, 0x2fa1f, 0x4e00}, /* CJK Ideographs */ }; - /* Sorted list of non-overlapping intervals of all Emoji characters, - * based on http://unicode.org/emoji/charts/emoji-list.html */ - static struct interval emoji_all[] = - { - {0x203c, 0x203c}, - {0x2049, 0x2049}, - {0x2122, 0x2122}, - {0x2139, 0x2139}, - {0x2194, 0x2199}, - {0x21a9, 0x21aa}, - {0x231a, 0x231b}, - {0x2328, 0x2328}, - {0x23cf, 0x23cf}, - {0x23e9, 0x23f3}, - {0x24c2, 0x24c2}, - {0x25aa, 0x25ab}, - {0x25b6, 0x25b6}, - {0x25c0, 0x25c0}, - {0x25fb, 0x25fe}, - {0x2600, 0x2604}, - {0x260e, 0x260e}, - {0x2611, 0x2611}, - {0x2614, 0x2615}, - {0x2618, 0x2618}, - {0x261d, 0x261d}, - {0x2620, 0x2620}, - {0x2622, 0x2623}, - {0x2626, 0x2626}, - {0x262a, 0x262a}, - {0x262e, 0x262f}, - {0x2638, 0x263a}, - {0x2648, 0x2653}, - {0x2660, 0x2660}, - {0x2663, 0x2663}, - {0x2665, 0x2666}, - {0x2668, 0x2668}, - {0x267b, 0x267b}, - {0x267f, 0x267f}, - {0x2692, 0x2694}, - {0x2696, 0x2697}, - {0x2699, 0x2699}, - {0x269b, 0x269c}, - {0x26a0, 0x26a1}, - {0x26aa, 0x26ab}, - {0x26b0, 0x26b1}, - {0x26bd, 0x26be}, - {0x26c4, 0x26c5}, - {0x26c8, 0x26c8}, - {0x26ce, 0x26cf}, - {0x26d1, 0x26d1}, - {0x26d3, 0x26d4}, - {0x26e9, 0x26ea}, - {0x26f0, 0x26f5}, - {0x26f7, 0x26fa}, - {0x26fd, 0x26fd}, - {0x2702, 0x2702}, - {0x2705, 0x2705}, - {0x2708, 0x270d}, - {0x270f, 0x270f}, - {0x2712, 0x2712}, - {0x2714, 0x2714}, - {0x2716, 0x2716}, - {0x271d, 0x271d}, - {0x2721, 0x2721}, - {0x2728, 0x2728}, - {0x2733, 0x2734}, - {0x2744, 0x2744}, - {0x2747, 0x2747}, - {0x274c, 0x274c}, - {0x274e, 0x274e}, - {0x2753, 0x2755}, - {0x2757, 0x2757}, - {0x2763, 0x2764}, - {0x2795, 0x2797}, - {0x27a1, 0x27a1}, - {0x27b0, 0x27b0}, - {0x27bf, 0x27bf}, - {0x2934, 0x2935}, - {0x2b05, 0x2b07}, - {0x2b1b, 0x2b1c}, - {0x2b50, 0x2b50}, - {0x2b55, 0x2b55}, - {0x3030, 0x3030}, - {0x303d, 0x303d}, - {0x3297, 0x3297}, - {0x3299, 0x3299}, - {0x1f004, 0x1f004}, - {0x1f0cf, 0x1f0cf}, - {0x1f170, 0x1f171}, - {0x1f17e, 0x1f17f}, - {0x1f18e, 0x1f18e}, - {0x1f191, 0x1f19a}, - {0x1f1e6, 0x1f1ff}, - {0x1f201, 0x1f202}, - {0x1f21a, 0x1f21a}, - {0x1f22f, 0x1f22f}, - {0x1f232, 0x1f23a}, - {0x1f250, 0x1f251}, - {0x1f300, 0x1f320}, - {0x1f330, 0x1f335}, - {0x1f337, 0x1f37c}, - {0x1f380, 0x1f393}, - {0x1f3a0, 0x1f3c4}, - {0x1f3c6, 0x1f3ca}, - {0x1f3e0, 0x1f3f0}, - {0x1f400, 0x1f43e}, - {0x1f440, 0x1f440}, - {0x1f442, 0x1f4f7}, - {0x1f4f9, 0x1f4fc}, - {0x1f500, 0x1f53d}, - {0x1f550, 0x1f567}, - {0x1f5fb, 0x1f640}, - {0x1f645, 0x1f64f}, - {0x1f680, 0x1f6c5} - }; - int bot = 0; int top = sizeof(classes) / sizeof(struct clinterval) - 1; int mid; @@ -2714,6 +2714,13 @@ utf_class(int c) return 2; } + int +utf_ambiguous_width(int c) +{ + return c >= 0x80 && (intable(ambiguous, sizeof(ambiguous), c) + || intable(emoji_all, sizeof(emoji_all), c)); +} + /* * Code for Unicode case-dependent operations. Based on notes in * http://www.unicode.org/Public/UNIDATA/CaseFolding.txt diff --git a/src/proto/mbyte.pro b/src/proto/mbyte.pro index bb00a5035..0e41a4125 100644 --- a/src/proto/mbyte.pro +++ b/src/proto/mbyte.pro @@ -10,6 +10,7 @@ int latin_char2len(int c); int latin_char2bytes(int c, char_u *buf); int latin_ptr2len(char_u *p); int latin_ptr2len_len(char_u *p, int size); +int utf_ambiguous_width(int c); int utf_char2cells(int c); int latin_ptr2cells(char_u *p); int utf_ptr2cells(char_u *p); diff --git a/src/screen.c b/src/screen.c index 77fb3b94c..4c2b70c31 100644 --- a/src/screen.c +++ b/src/screen.c @@ -8052,7 +8052,9 @@ screen_char(unsigned off, int row, int col) buf[utfc_char2bytes(off, buf)] = NUL; out_str(buf); - if (utf_char2cells(ScreenLinesUC[off]) > 1) + if (utf_ambiguous_width(ScreenLinesUC[off])) + screen_cur_col = 9999; + else if (utf_char2cells(ScreenLinesUC[off]) > 1) ++screen_cur_col; } else diff --git a/src/version.c b/src/version.c index ab2cc39a4..cfca22ed6 100644 --- a/src/version.c +++ b/src/version.c @@ -749,6 +749,8 @@ static char *(features[]) = static int included_patches[] = { /* Add new patch number below this line */ /**/ + 1697, +/**/ 1696, /**/ 1695, |