Subject: Fix incorrect generation of ucs_ambwidth_map Author: Tatsuya Kinoshita diff --git a/libwc/ambwidth_map.awk b/libwc/ambwidth_map.awk index 8544f58..1d9d25f 100644 --- a/libwc/ambwidth_map.awk +++ b/libwc/ambwidth_map.awk @@ -3,9 +3,15 @@ BEGIN { i = 0; } $2 == "A" { - code = sprintf("0x%s", $1); - if (strtonum(code) < 0x10000) { - map[i] = code + code = code2 = strtonum(sprintf("0x%s", $1)) + if (match($1, /[.]+[0-9A-Fa-f]+/)) { + s = substr($1, RSTART, RLENGTH) + sub(/[.]+/, "0x", s) + code2 = strtonum(s) + } + for (; code <= code2; code++) { + if (code >= 0x10000) { break } + map[i] = sprintf("0x%04X", code) i++; } } @@ -15,28 +21,14 @@ END { prev = strtonum(map[0]); for (j = 1; j < i; j++) { cur = strtonum(map[j]); - if (match(map[j], "[.]+")) { + if (cur - prev > 1) { map2[n] = sprintf("%s, %s", start, map[j - 1]); n++; - gsub("[.]+", ", 0x", map[j]) - map2[n] = map[j]; - n++; - start = map[j + 1]; - cur = strtonum(start); - } else { - if (cur - prev > 2) { - map2[n] = sprintf("%s, %s", start, map[j - 1]); - start = map[j]; - n++; - } - - if (j == i - 1) { - map2[n] = sprintf("%s, %s", start, map[j]); - n++; - } + start = map[j]; } prev = cur; } + if (i > 0) { map2[n] = sprintf("%s, %s", start, map[i - 1]); n++ } printf("static wc_map ucs_ambwidth_map[] = {\n"); for (j = 0; j < n; j++) { diff --git a/libwc/map/ucs_ambwidth.map b/libwc/map/ucs_ambwidth.map index 6f03ba8..35ceedb 100644 --- a/libwc/map/ucs_ambwidth.map +++ b/libwc/map/ucs_ambwidth.map @@ -1,50 +1,82 @@ static wc_map ucs_ambwidth_map[] = { { 0x00A1, 0x00A1 }, { 0x00A4, 0x00A4 }, - { 0x00A7, 0x00AA }, - { 0x00AD, 0x00BF }, + { 0x00A7, 0x00A8 }, + { 0x00AA, 0x00AA }, + { 0x00AD, 0x00AE }, + { 0x00B0, 0x00B4 }, + { 0x00B6, 0x00BA }, + { 0x00BC, 0x00BF }, { 0x00C6, 0x00C6 }, { 0x00D0, 0x00D0 }, { 0x00D7, 0x00D8 }, { 0x00DE, 0x00E1 }, - { 0x00E6, 0x00ED }, - { 0x00F0, 0x00F3 }, - { 0x00F7, 0x00FE }, + { 0x00E6, 0x00E6 }, + { 0x00E8, 0x00EA }, + { 0x00EC, 0x00ED }, + { 0x00F0, 0x00F0 }, + { 0x00F2, 0x00F3 }, + { 0x00F7, 0x00FA }, + { 0x00FC, 0x00FC }, + { 0x00FE, 0x00FE }, { 0x0101, 0x0101 }, - { 0x0111, 0x0113 }, + { 0x0111, 0x0111 }, + { 0x0113, 0x0113 }, { 0x011B, 0x011B }, { 0x0126, 0x0127 }, { 0x012B, 0x012B }, { 0x0131, 0x0133 }, { 0x0138, 0x0138 }, - { 0x013F, 0x0144 }, - { 0x0148, 0x014D }, + { 0x013F, 0x0142 }, + { 0x0144, 0x0144 }, + { 0x0148, 0x014B }, + { 0x014D, 0x014D }, { 0x0152, 0x0153 }, { 0x0166, 0x0167 }, { 0x016B, 0x016B }, - { 0x01CE, 0x01DC }, + { 0x01CE, 0x01CE }, + { 0x01D0, 0x01D0 }, + { 0x01D2, 0x01D2 }, + { 0x01D4, 0x01D4 }, + { 0x01D6, 0x01D6 }, + { 0x01D8, 0x01D8 }, + { 0x01DA, 0x01DA }, + { 0x01DC, 0x01DC }, { 0x0251, 0x0251 }, { 0x0261, 0x0261 }, { 0x02C4, 0x02C4 }, - { 0x02C7, 0x02CD }, + { 0x02C7, 0x02C7 }, + { 0x02C9, 0x02CB }, + { 0x02CD, 0x02CD }, { 0x02D0, 0x02D0 }, - { 0x02D8, 0x02DF }, + { 0x02D8, 0x02DB }, + { 0x02DD, 0x02DD }, + { 0x02DF, 0x02DF }, { 0x0300, 0x036F }, - { 0x0391, 0x03A9 }, - { 0x03B1, 0x03C9 }, + { 0x0391, 0x03A1 }, + { 0x03A3, 0x03A9 }, + { 0x03B1, 0x03C1 }, + { 0x03C3, 0x03C9 }, { 0x0401, 0x0401 }, - { 0x0410, 0x0451 }, + { 0x0410, 0x044F }, + { 0x0451, 0x0451 }, { 0x2010, 0x2010 }, - { 0x2013, 0x2019 }, + { 0x2013, 0x2016 }, + { 0x2018, 0x2019 }, { 0x201C, 0x201D }, - { 0x2020, 0x2027 }, - { 0x2030, 0x2035 }, + { 0x2020, 0x2022 }, + { 0x2024, 0x2027 }, + { 0x2030, 0x2030 }, + { 0x2032, 0x2033 }, + { 0x2035, 0x2035 }, { 0x203B, 0x203B }, { 0x203E, 0x203E }, { 0x2074, 0x2074 }, - { 0x207F, 0x2084 }, + { 0x207F, 0x207F }, + { 0x2081, 0x2084 }, { 0x20AC, 0x20AC }, - { 0x2103, 0x2105 }, + { 0x2103, 0x2103 }, + { 0x2105, 0x2105 }, { 0x2109, 0x2109 }, { 0x2113, 0x2113 }, { 0x2116, 0x2116 }, @@ -52,21 +84,28 @@ static wc_map ucs_ambwidth_map[] = { { 0x2126, 0x2126 }, { 0x212B, 0x212B }, { 0x2153, 0x2154 }, - { 0x215B, 0x216B }, + { 0x215B, 0x215E }, + { 0x2160, 0x216B }, { 0x2170, 0x2179 }, { 0x2189, 0x2189 }, { 0x2190, 0x2199 }, { 0x21B8, 0x21B9 }, - { 0x21D2, 0x21D4 }, + { 0x21D2, 0x21D2 }, + { 0x21D4, 0x21D4 }, { 0x21E7, 0x21E7 }, - { 0x2200, 0x2203 }, + { 0x2200, 0x2200 }, + { 0x2202, 0x2203 }, { 0x2207, 0x2208 }, { 0x220B, 0x220B }, - { 0x220F, 0x2211 }, + { 0x220F, 0x220F }, + { 0x2211, 0x2211 }, { 0x2215, 0x2215 }, { 0x221A, 0x221A }, { 0x221D, 0x2220 }, - { 0x2223, 0x222E }, + { 0x2223, 0x2223 }, + { 0x2225, 0x2225 }, + { 0x2227, 0x222C }, + { 0x222E, 0x222E }, { 0x2234, 0x2237 }, { 0x223C, 0x223D }, { 0x2248, 0x2248 }, @@ -83,11 +122,13 @@ static wc_map ucs_ambwidth_map[] = { { 0x22A5, 0x22A5 }, { 0x22BF, 0x22BF }, { 0x2312, 0x2312 }, - { 0x2460, 0x254B }, + { 0x2460, 0x24E9 }, + { 0x24EB, 0x254B }, { 0x2550, 0x2573 }, { 0x2580, 0x258F }, { 0x2592, 0x2595 }, - { 0x25A0, 0x25A9 }, + { 0x25A0, 0x25A1 }, + { 0x25A3, 0x25A9 }, { 0x25B2, 0x25B3 }, { 0x25B6, 0x25B7 }, { 0x25BC, 0x25BD }, @@ -101,12 +142,20 @@ static wc_map ucs_ambwidth_map[] = { { 0x2609, 0x2609 }, { 0x260E, 0x260F }, { 0x2614, 0x2615 }, - { 0x261C, 0x261E }, - { 0x2640, 0x2642 }, - { 0x2660, 0x266F }, + { 0x261C, 0x261C }, + { 0x261E, 0x261E }, + { 0x2640, 0x2640 }, + { 0x2642, 0x2642 }, + { 0x2660, 0x2661 }, + { 0x2663, 0x2665 }, + { 0x2667, 0x266A }, + { 0x266C, 0x266D }, + { 0x266F, 0x266F }, { 0x269E, 0x269F }, { 0x26BE, 0x26BF }, - { 0x26C4, 0x26E3 }, + { 0x26C4, 0x26CD }, + { 0x26CF, 0x26E1 }, + { 0x26E3, 0x26E3 }, { 0x26E8, 0x26FF }, { 0x273D, 0x273D }, { 0x2757, 0x2757 },