diff options
author | bptato <nincsnevem662@gmail.com> | 2023-02-05 16:24:56 +0100 |
---|---|---|
committer | bptato <nincsnevem662@gmail.com> | 2023-02-05 16:24:56 +0100 |
commit | 6190ae1071c8d07a9a2d10037801838718363e1f (patch) | |
tree | 68581290381ecebb011750908f21b6a0c3d45633 /src/utils | |
parent | c5a318c85da3ae3cee30c839a40068e7f5fd514b (diff) | |
download | chawan-6190ae1071c8d07a9a2d10037801838718363e1f.tar.gz |
Update character width ranges
Use the Unicode 15 EastAsianWidth.txt file instead of an ancient wcwidth implementation's ranges.
Diffstat (limited to 'src/utils')
-rw-r--r-- | src/utils/twtstr.nim | 270 |
1 files changed, 102 insertions, 168 deletions
diff --git a/src/utils/twtstr.nim b/src/utils/twtstr.nim index 09422d0f..aea8bea5 100644 --- a/src/utils/twtstr.nim +++ b/src/utils/twtstr.nim @@ -1,5 +1,4 @@ import algorithm -import terminal import strutils import unicode import os @@ -11,22 +10,11 @@ import punycode import bindings/libunicode import data/idna +import data/charwidth when defined(posix): import posix -func ansiStyle*(str: string, style: Style): string = - result &= ansiStyleCode(style) - result &= str - -func ansiFgColor*(str: string, color: ForegroundColor): string = - result &= ansiForegroundColorCode(color) - result &= str - -func ansiReset*(str: string): string = - result &= str - result &= ansiResetCode - const C0Controls* = {chr(0x00)..chr(0x1F)} const Controls* = (C0Controls + {chr(0x7F)}) const Ascii* = {chr(0x00)..chr(0x7F)} @@ -790,7 +778,7 @@ iterator split*(s: seq[Rune], sep: Rune): seq[Rune] = if prev < i: yield s.substr(prev, i) -# Measure length of runes. From https://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c +# Combining chars from https://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c # # The following two functions define the column width of an ISO 10646 # character as follows: @@ -821,182 +809,129 @@ iterator split*(s: seq[Rune], sep: Rune): seq[Rune] = # sorted list of non-overlapping intervals of non-spacing characters generated # by "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c" const Combining = [ - ( 0x0300, 0x036F ), ( 0x0483, 0x0486 ), ( 0x0488, 0x0489 ), - ( 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 ), - ( 0x09E2, 0x09E3 ), ( 0x0A01, 0x0A02 ), ( 0x0A3C, 0x0A3C ), - ( 0x0A41, 0x0A42 ), ( 0x0A47, 0x0A48 ), ( 0x0A4B, 0x0A4D ), - ( 0x0A70, 0x0A71 ), ( 0x0A81, 0x0A82 ), ( 0x0ABC, 0x0ABC ), - ( 0x0AC1, 0x0AC5 ), ( 0x0AC7, 0x0AC8 ), ( 0x0ACD, 0x0ACD ), - ( 0x0AE2, 0x0AE3 ), ( 0x0B01, 0x0B01 ), ( 0x0B3C, 0x0B3C ), - ( 0x0B3F, 0x0B3F ), ( 0x0B41, 0x0B43 ), ( 0x0B4D, 0x0B4D ), - ( 0x0B56, 0x0B56 ), ( 0x0B82, 0x0B82 ), ( 0x0BC0, 0x0BC0 ), - ( 0x0BCD, 0x0BCD ), ( 0x0C3E, 0x0C40 ), ( 0x0C46, 0x0C48 ), - ( 0x0C4A, 0x0C4D ), ( 0x0C55, 0x0C56 ), ( 0x0CBC, 0x0CBC ), - ( 0x0CBF, 0x0CBF ), ( 0x0CC6, 0x0CC6 ), ( 0x0CCC, 0x0CCD ), - ( 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 ) + (0x0300u32, 0x036Fu32), (0x0483u32, 0x0486u32), (0x0488u32, 0x0489u32), + (0x0591u32, 0x05BDu32), (0x05BFu32, 0x05BFu32), (0x05C1u32, 0x05C2u32), + (0x05C4u32, 0x05C5u32), (0x05C7u32, 0x05C7u32), (0x0600u32, 0x0603u32), + (0x0610u32, 0x0615u32), (0x064Bu32, 0x065Eu32), (0x0670u32, 0x0670u32), + (0x06D6u32, 0x06E4u32), (0x06E7u32, 0x06E8u32), (0x06EAu32, 0x06EDu32), + (0x070Fu32, 0x070Fu32), (0x0711u32, 0x0711u32), (0x0730u32, 0x074Au32), + (0x07A6u32, 0x07B0u32), (0x07EBu32, 0x07F3u32), (0x0901u32, 0x0902u32), + (0x093Cu32, 0x093Cu32), (0x0941u32, 0x0948u32), (0x094Du32, 0x094Du32), + (0x0951u32, 0x0954u32), (0x0962u32, 0x0963u32), (0x0981u32, 0x0981u32), + (0x09BCu32, 0x09BCu32), (0x09C1u32, 0x09C4u32), (0x09CDu32, 0x09CDu32), + (0x09E2u32, 0x09E3u32), (0x0A01u32, 0x0A02u32), (0x0A3Cu32, 0x0A3Cu32), + (0x0A41u32, 0x0A42u32), (0x0A47u32, 0x0A48u32), (0x0A4Bu32, 0x0A4Du32), + (0x0A70u32, 0x0A71u32), (0x0A81u32, 0x0A82u32), (0x0ABCu32, 0x0ABCu32), + (0x0AC1u32, 0x0AC5u32), (0x0AC7u32, 0x0AC8u32), (0x0ACDu32, 0x0ACDu32), + (0x0AE2u32, 0x0AE3u32), (0x0B01u32, 0x0B01u32), (0x0B3Cu32, 0x0B3Cu32), + (0x0B3Fu32, 0x0B3Fu32), (0x0B41u32, 0x0B43u32), (0x0B4Du32, 0x0B4Du32), + (0x0B56u32, 0x0B56u32), (0x0B82u32, 0x0B82u32), (0x0BC0u32, 0x0BC0u32), + (0x0BCDu32, 0x0BCDu32), (0x0C3Eu32, 0x0C40u32), (0x0C46u32, 0x0C48u32), + (0x0C4Au32, 0x0C4Du32), (0x0C55u32, 0x0C56u32), (0x0CBCu32, 0x0CBCu32), + (0x0CBFu32, 0x0CBFu32), (0x0CC6u32, 0x0CC6u32), (0x0CCCu32, 0x0CCDu32), + (0x0CE2u32, 0x0CE3u32), (0x0D41u32, 0x0D43u32), (0x0D4Du32, 0x0D4Du32), + (0x0DCAu32, 0x0DCAu32), (0x0DD2u32, 0x0DD4u32), (0x0DD6u32, 0x0DD6u32), + (0x0E31u32, 0x0E31u32), (0x0E34u32, 0x0E3Au32), (0x0E47u32, 0x0E4Eu32), + (0x0EB1u32, 0x0EB1u32), (0x0EB4u32, 0x0EB9u32), (0x0EBBu32, 0x0EBCu32), + (0x0EC8u32, 0x0ECDu32), (0x0F18u32, 0x0F19u32), (0x0F35u32, 0x0F35u32), + (0x0F37u32, 0x0F37u32), (0x0F39u32, 0x0F39u32), (0x0F71u32, 0x0F7Eu32), + (0x0F80u32, 0x0F84u32), (0x0F86u32, 0x0F87u32), (0x0F90u32, 0x0F97u32), + (0x0F99u32, 0x0FBCu32), (0x0FC6u32, 0x0FC6u32), (0x102Du32, 0x1030u32), + (0x1032u32, 0x1032u32), (0x1036u32, 0x1037u32), (0x1039u32, 0x1039u32), + (0x1058u32, 0x1059u32), (0x1160u32, 0x11FFu32), (0x135Fu32, 0x135Fu32), + (0x1712u32, 0x1714u32), (0x1732u32, 0x1734u32), (0x1752u32, 0x1753u32), + (0x1772u32, 0x1773u32), (0x17B4u32, 0x17B5u32), (0x17B7u32, 0x17BDu32), + (0x17C6u32, 0x17C6u32), (0x17C9u32, 0x17D3u32), (0x17DDu32, 0x17DDu32), + (0x180Bu32, 0x180Du32), (0x18A9u32, 0x18A9u32), (0x1920u32, 0x1922u32), + (0x1927u32, 0x1928u32), (0x1932u32, 0x1932u32), (0x1939u32, 0x193Bu32), + (0x1A17u32, 0x1A18u32), (0x1B00u32, 0x1B03u32), (0x1B34u32, 0x1B34u32), + (0x1B36u32, 0x1B3Au32), (0x1B3Cu32, 0x1B3Cu32), (0x1B42u32, 0x1B42u32), + (0x1B6Bu32, 0x1B73u32), (0x1DC0u32, 0x1DCAu32), (0x1DFEu32, 0x1DFFu32), + (0x200Bu32, 0x200Fu32), (0x202Au32, 0x202Eu32), (0x2060u32, 0x2063u32), + (0x206Au32, 0x206Fu32), (0x20D0u32, 0x20EFu32), (0x302Au32, 0x302Fu32), + (0x3099u32, 0x309Au32), (0xA806u32, 0xA806u32), (0xA80Bu32, 0xA80Bu32), + (0xA825u32, 0xA826u32), (0xFB1Eu32, 0xFB1Eu32), (0xFE00u32, 0xFE0Fu32), + (0xFE20u32, 0xFE23u32), (0xFEFFu32, 0xFEFFu32), (0xFFF9u32, 0xFFFBu32), + (0x10A01u32, 0x10A03u32), (0x10A05u32, 0x10A06u32), (0x10A0Cu32, 0x10A0Fu32), + (0x10A38u32, 0x10A3Au32), (0x10A3Fu32, 0x10A3Fu32), (0x1D167u32, 0x1D169u32), + (0x1D173u32, 0x1D182u32), (0x1D185u32, 0x1D18Bu32), (0x1D1AAu32, 0x1D1ADu32), + (0x1D242u32, 0x1D244u32), (0xE0001u32, 0xE0001u32), (0xE0020u32, 0xE007Fu32), + (0xE0100u32, 0xE01EFu32) ] -func isDoubleWidthLow(r: Rune): bool = - let ucs = cast[uint32](r) - return ucs in 0x1100u32..0x115Fu32 or # Hangul Jamo init. consonants - ucs == 0x2329 or ucs == 0x232A or - ucs in 0x2E80u32..0xA4CFu32 and ucs != 0x303F or # CJK ... Yi - ucs in 0xAC00u32..0xD7A3u32 or # Hangul Syllables - ucs in 0xF900u32..0xFAFFu32 or # CJK Compatibility Ideographs - ucs in 0xFE10u32..0xFE19u32 or # Vertical forms - ucs in 0xFE30u32..0xFE6Fu32 or # CJK Compatibility Forms - ucs in 0xFF00u32..0xFF60u32 or # Fullwidth Forms - ucs in 0xFFE0u32..0xFFE6u32 +func cmp(range: (uint32, uint32), r: Rune): int = + if range[0] < cast[uint32](r): + return -1 + elif range[1] > cast[uint32](r): + return 1 + return 0 func isDoubleWidthHigh(r: Rune): bool = - let ucs = cast[uint32](r) - return (ucs in 0x20000u32..0x2FFFDu32) or - (ucs in 0x30000u32..0x3FFFDu32) - -# sorted list of non-overlapping intervals of East Asian Ambiguous characters, -# generated by "uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c" - -const Ambiguous = [ - ( 0x00A1, 0x00A1 ), ( 0x00A4, 0x00A4 ), ( 0x00A7, 0x00A8 ), - ( 0x00AA, 0x00AA ), ( 0x00AE, 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 ), ( 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 ), - ( 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 ), - ( 0x273D, 0x273D ), ( 0x2776, 0x277F ), ( 0xE000, 0xF8FF ), - ( 0xFFFD, 0xFFFD ), ( 0xF0000, 0xFFFFD ), ( 0x100000, 0x10FFFD ) -] - -# -# The following functions are the same as mk_wcwidth() and mk_wcswidth(), -# except that spacing characters in the East Asian Ambiguous (A) category as -# defined in Unicode Technical Report #11 have a column width of 2. This -# variant might be useful for users of CJK legacy encodings who want to migrate -# to UCS without changing the traditional terminal character-width behaviour. -# It is not otherwise recommended for general use. + return binarySearch(DoubleWidthRanges, r, twtstr.cmp) != -1 func isDoubleWidthAmbiguousHigh(r: Rune): bool = # binary search in table of non-spacing characters - if binarySearch(Ambiguous, int32(r), (x, y) => (if x[0] < y: -1 elif x[1] > y: 1 else: 0)) != -1: + if binarySearch(DoubleWidthAmbiguousRanges, r, twtstr.cmp) != -1: return true return r.isDoubleWidthHigh() func isCombining(r: Rune): bool = - return binarySearch(Combining, int32(r), (x, y) => (if x[0] < y: -1 elif x[1] > y: 1 else: 0)) != -1 + return binarySearch(Combining, r, twtstr.cmp) != -1 # Lookup tables for characters on the BMP. This "only" takes up 8k of space # per table, as opposed to the 135k that storing all characters would require. # The downside is obviously that we need a binary search fallback for non-bmp. +# We do not store a lookup table of ambiguous ranges, either. type PropertyTable = array[0..(0xFFFF div 8), uint8] -func makePropertyTable(crit: proc(r: Rune): bool {.noSideEffect.}, - skip: openarray[(int, int)] = @[]): PropertyTable {.noInit.} = - var ucs = 0 +func makePropertyTable(ranges, skip: openarray[(uint32, uint32)] = @[]): PropertyTable = + var ucs: uint32 = 0 var j = 0 + var k = 0 while ucs <= 0xFFFF: + if k > ranges.len: + break + if ranges[k][0] > ucs: + ucs = ranges[k][0] + continue + if ranges[k][1] < ucs: + inc k + continue if j != skip.len and ucs == skip[j][0]: ucs = skip[j][1] + 1 continue - if crit(cast[Rune](ucs)): - let i = ucs div 8 - case ucs mod 8 - of 0: result[i] = result[i] or 0x01 - of 1: result[i] = result[i] or 0x02 - of 2: result[i] = result[i] or 0x04 - of 3: result[i] = result[i] or 0x08 - of 4: result[i] = result[i] or 0x10 - of 5: result[i] = result[i] or 0x20 - of 6: result[i] = result[i] or 0x40 - of 7: result[i] = result[i] or 0x80 - else: discard + let i = ucs div 8 + case ucs mod 8 + of 0: result[i] = result[i] or 0x01 + of 1: result[i] = result[i] or 0x02 + of 2: result[i] = result[i] or 0x04 + of 3: result[i] = result[i] or 0x08 + of 4: result[i] = result[i] or 0x10 + of 5: result[i] = result[i] or 0x20 + of 6: result[i] = result[i] or 0x40 + of 7: result[i] = result[i] or 0x80 + else: discard inc ucs -# Control chars return a width of 2, and are displayed as ^{letter}. -const DoubleWidthTable = makePropertyTable((func(r: Rune): bool = - r.isAscii() and cast[char](r) in Controls or r.isDoubleWidthLow() -), Combining) -const CombiningTable = makePropertyTable(func(r: Rune): bool = - return binarySearch(Combining, int32(r), (x, y) => (if x[0] < y: -1 elif x[1] > y: 1 else: 0)) != -1 -) +const DoubleWidthTable = (func(): PropertyTable = + var ptab = makePropertyTable(DoubleWidthRanges, Combining) + # Control chars return a width of 2, and are displayed as ^{letter}. + for c in Controls: + let i = cast[uint16](c) div 8 + case cast[uint16](c) mod 8 + of 0: ptab[i] = ptab[i] or 0x01 + of 1: ptab[i] = ptab[i] or 0x02 + of 2: ptab[i] = ptab[i] or 0x04 + of 3: ptab[i] = ptab[i] or 0x08 + of 4: ptab[i] = ptab[i] or 0x10 + of 5: ptab[i] = ptab[i] or 0x20 + of 6: ptab[i] = ptab[i] or 0x40 + of 7: ptab[i] = ptab[i] or 0x80 + else: discard + return ptab +)() + +const CombiningTable = makePropertyTable(Combining) # One of the few global variables in the code. Honestly, it should not exist. var is_cjk_ambiguous = false @@ -1031,8 +966,7 @@ func width*(r: Rune): int = return 2 else: if r in DoubleWidthTable or - binarySearch(Ambiguous, int32(r), - (x, y) => (if x[0] < y: -1 elif x[1] > y: 1 else: 0)) != -1: + binarySearch(DoubleWidthAmbiguousRanges, r, twtstr.cmp) != -1: return 2 else: if r.isCombining(): |