diff options
Diffstat (limited to 'contrib/llvm-project/llvm/lib/Support/Unicode.cpp')
-rw-r--r-- | contrib/llvm-project/llvm/lib/Support/Unicode.cpp | 358 |
1 files changed, 210 insertions, 148 deletions
diff --git a/contrib/llvm-project/llvm/lib/Support/Unicode.cpp b/contrib/llvm-project/llvm/lib/Support/Unicode.cpp index d4d7e75b739d..621ffc712187 100644 --- a/contrib/llvm-project/llvm/lib/Support/Unicode.cpp +++ b/contrib/llvm-project/llvm/lib/Support/Unicode.cpp @@ -25,7 +25,7 @@ namespace unicode { /// it's actually displayed on most terminals. \return true if the character is /// considered printable. bool isPrintable(int UCS) { - // https://unicode.org/Public/14.0.0/ucdxml/ + // https://unicode.org/Public/15.0.0/ucdxml/ static const UnicodeCharRange PrintableRanges[] = { {0x0020, 0x007E}, {0x00A0, 0x00AC}, {0x00AE, 0x0377}, {0x037A, 0x037F}, {0x0384, 0x038A}, {0x038C, 0x038C}, @@ -68,7 +68,7 @@ bool isPrintable(int UCS) { {0x0C8E, 0x0C90}, {0x0C92, 0x0CA8}, {0x0CAA, 0x0CB3}, {0x0CB5, 0x0CB9}, {0x0CBC, 0x0CC4}, {0x0CC6, 0x0CC8}, {0x0CCA, 0x0CCD}, {0x0CD5, 0x0CD6}, {0x0CDD, 0x0CDE}, - {0x0CE0, 0x0CE3}, {0x0CE6, 0x0CEF}, {0x0CF1, 0x0CF2}, + {0x0CE0, 0x0CE3}, {0x0CE6, 0x0CEF}, {0x0CF1, 0x0CF3}, {0x0D00, 0x0D0C}, {0x0D0E, 0x0D10}, {0x0D12, 0x0D44}, {0x0D46, 0x0D48}, {0x0D4A, 0x0D4F}, {0x0D54, 0x0D63}, {0x0D66, 0x0D7F}, {0x0D81, 0x0D83}, {0x0D85, 0x0D96}, @@ -78,7 +78,7 @@ bool isPrintable(int UCS) { {0x0DF2, 0x0DF4}, {0x0E01, 0x0E3A}, {0x0E3F, 0x0E5B}, {0x0E81, 0x0E82}, {0x0E84, 0x0E84}, {0x0E86, 0x0E8A}, {0x0E8C, 0x0EA3}, {0x0EA5, 0x0EA5}, {0x0EA7, 0x0EBD}, - {0x0EC0, 0x0EC4}, {0x0EC6, 0x0EC6}, {0x0EC8, 0x0ECD}, + {0x0EC0, 0x0EC4}, {0x0EC6, 0x0EC6}, {0x0EC8, 0x0ECE}, {0x0ED0, 0x0ED9}, {0x0EDC, 0x0EDF}, {0x0F00, 0x0F47}, {0x0F49, 0x0F6C}, {0x0F71, 0x0F97}, {0x0F99, 0x0FBC}, {0x0FBE, 0x0FCC}, {0x0FCE, 0x0FDA}, {0x1000, 0x10C5}, @@ -169,13 +169,13 @@ bool isPrintable(int UCS) { {0x10B99, 0x10B9C}, {0x10BA9, 0x10BAF}, {0x10C00, 0x10C48}, {0x10C80, 0x10CB2}, {0x10CC0, 0x10CF2}, {0x10CFA, 0x10D27}, {0x10D30, 0x10D39}, {0x10E60, 0x10E7E}, {0x10E80, 0x10EA9}, - {0x10EAB, 0x10EAD}, {0x10EB0, 0x10EB1}, {0x10F00, 0x10F27}, + {0x10EAB, 0x10EAD}, {0x10EB0, 0x10EB1}, {0x10EFD, 0x10F27}, {0x10F30, 0x10F59}, {0x10F70, 0x10F89}, {0x10FB0, 0x10FCB}, {0x10FE0, 0x10FF6}, {0x11000, 0x1104D}, {0x11052, 0x11075}, {0x1107F, 0x110BC}, {0x110BE, 0x110C2}, {0x110D0, 0x110E8}, {0x110F0, 0x110F9}, {0x11100, 0x11134}, {0x11136, 0x11147}, {0x11150, 0x11176}, {0x11180, 0x111DF}, {0x111E1, 0x111F4}, - {0x11200, 0x11211}, {0x11213, 0x1123E}, {0x11280, 0x11286}, + {0x11200, 0x11211}, {0x11213, 0x11241}, {0x11280, 0x11286}, {0x11288, 0x11288}, {0x1128A, 0x1128D}, {0x1128F, 0x1129D}, {0x1129F, 0x112A9}, {0x112B0, 0x112EA}, {0x112F0, 0x112F9}, {0x11300, 0x11303}, {0x11305, 0x1130C}, {0x1130F, 0x11310}, @@ -193,43 +193,47 @@ bool isPrintable(int UCS) { {0x11937, 0x11938}, {0x1193B, 0x11946}, {0x11950, 0x11959}, {0x119A0, 0x119A7}, {0x119AA, 0x119D7}, {0x119DA, 0x119E4}, {0x11A00, 0x11A47}, {0x11A50, 0x11AA2}, {0x11AB0, 0x11AF8}, - {0x11C00, 0x11C08}, {0x11C0A, 0x11C36}, {0x11C38, 0x11C45}, - {0x11C50, 0x11C6C}, {0x11C70, 0x11C8F}, {0x11C92, 0x11CA7}, - {0x11CA9, 0x11CB6}, {0x11D00, 0x11D06}, {0x11D08, 0x11D09}, - {0x11D0B, 0x11D36}, {0x11D3A, 0x11D3A}, {0x11D3C, 0x11D3D}, - {0x11D3F, 0x11D47}, {0x11D50, 0x11D59}, {0x11D60, 0x11D65}, - {0x11D67, 0x11D68}, {0x11D6A, 0x11D8E}, {0x11D90, 0x11D91}, - {0x11D93, 0x11D98}, {0x11DA0, 0x11DA9}, {0x11EE0, 0x11EF8}, - {0x11FB0, 0x11FB0}, {0x11FC0, 0x11FF1}, {0x11FFF, 0x12399}, - {0x12400, 0x1246E}, {0x12470, 0x12474}, {0x12480, 0x12543}, - {0x12F90, 0x12FF2}, {0x13000, 0x1342E}, {0x14400, 0x14646}, - {0x16800, 0x16A38}, {0x16A40, 0x16A5E}, {0x16A60, 0x16A69}, - {0x16A6E, 0x16ABE}, {0x16AC0, 0x16AC9}, {0x16AD0, 0x16AED}, - {0x16AF0, 0x16AF5}, {0x16B00, 0x16B45}, {0x16B50, 0x16B59}, - {0x16B5B, 0x16B61}, {0x16B63, 0x16B77}, {0x16B7D, 0x16B8F}, - {0x16E40, 0x16E9A}, {0x16F00, 0x16F4A}, {0x16F4F, 0x16F87}, - {0x16F8F, 0x16F9F}, {0x16FE0, 0x16FE4}, {0x16FF0, 0x16FF1}, - {0x17000, 0x187F7}, {0x18800, 0x18CD5}, {0x18D00, 0x18D08}, - {0x1AFF0, 0x1AFF3}, {0x1AFF5, 0x1AFFB}, {0x1AFFD, 0x1AFFE}, - {0x1B000, 0x1B122}, {0x1B150, 0x1B152}, {0x1B164, 0x1B167}, - {0x1B170, 0x1B2FB}, {0x1BC00, 0x1BC6A}, {0x1BC70, 0x1BC7C}, - {0x1BC80, 0x1BC88}, {0x1BC90, 0x1BC99}, {0x1BC9C, 0x1BC9F}, - {0x1CF00, 0x1CF2D}, {0x1CF30, 0x1CF46}, {0x1CF50, 0x1CFC3}, - {0x1D000, 0x1D0F5}, {0x1D100, 0x1D126}, {0x1D129, 0x1D172}, - {0x1D17B, 0x1D1EA}, {0x1D200, 0x1D245}, {0x1D2E0, 0x1D2F3}, - {0x1D300, 0x1D356}, {0x1D360, 0x1D378}, {0x1D400, 0x1D454}, - {0x1D456, 0x1D49C}, {0x1D49E, 0x1D49F}, {0x1D4A2, 0x1D4A2}, - {0x1D4A5, 0x1D4A6}, {0x1D4A9, 0x1D4AC}, {0x1D4AE, 0x1D4B9}, - {0x1D4BB, 0x1D4BB}, {0x1D4BD, 0x1D4C3}, {0x1D4C5, 0x1D505}, - {0x1D507, 0x1D50A}, {0x1D50D, 0x1D514}, {0x1D516, 0x1D51C}, - {0x1D51E, 0x1D539}, {0x1D53B, 0x1D53E}, {0x1D540, 0x1D544}, - {0x1D546, 0x1D546}, {0x1D54A, 0x1D550}, {0x1D552, 0x1D6A5}, - {0x1D6A8, 0x1D7CB}, {0x1D7CE, 0x1DA8B}, {0x1DA9B, 0x1DA9F}, - {0x1DAA1, 0x1DAAF}, {0x1DF00, 0x1DF1E}, {0x1E000, 0x1E006}, + {0x11B00, 0x11B09}, {0x11C00, 0x11C08}, {0x11C0A, 0x11C36}, + {0x11C38, 0x11C45}, {0x11C50, 0x11C6C}, {0x11C70, 0x11C8F}, + {0x11C92, 0x11CA7}, {0x11CA9, 0x11CB6}, {0x11D00, 0x11D06}, + {0x11D08, 0x11D09}, {0x11D0B, 0x11D36}, {0x11D3A, 0x11D3A}, + {0x11D3C, 0x11D3D}, {0x11D3F, 0x11D47}, {0x11D50, 0x11D59}, + {0x11D60, 0x11D65}, {0x11D67, 0x11D68}, {0x11D6A, 0x11D8E}, + {0x11D90, 0x11D91}, {0x11D93, 0x11D98}, {0x11DA0, 0x11DA9}, + {0x11EE0, 0x11EF8}, {0x11F00, 0x11F10}, {0x11F12, 0x11F3A}, + {0x11F3E, 0x11F59}, {0x11FB0, 0x11FB0}, {0x11FC0, 0x11FF1}, + {0x11FFF, 0x12399}, {0x12400, 0x1246E}, {0x12470, 0x12474}, + {0x12480, 0x12543}, {0x12F90, 0x12FF2}, {0x13000, 0x1342F}, + {0x13440, 0x13455}, {0x14400, 0x14646}, {0x16800, 0x16A38}, + {0x16A40, 0x16A5E}, {0x16A60, 0x16A69}, {0x16A6E, 0x16ABE}, + {0x16AC0, 0x16AC9}, {0x16AD0, 0x16AED}, {0x16AF0, 0x16AF5}, + {0x16B00, 0x16B45}, {0x16B50, 0x16B59}, {0x16B5B, 0x16B61}, + {0x16B63, 0x16B77}, {0x16B7D, 0x16B8F}, {0x16E40, 0x16E9A}, + {0x16F00, 0x16F4A}, {0x16F4F, 0x16F87}, {0x16F8F, 0x16F9F}, + {0x16FE0, 0x16FE4}, {0x16FF0, 0x16FF1}, {0x17000, 0x187F7}, + {0x18800, 0x18CD5}, {0x18D00, 0x18D08}, {0x1AFF0, 0x1AFF3}, + {0x1AFF5, 0x1AFFB}, {0x1AFFD, 0x1AFFE}, {0x1B000, 0x1B122}, + {0x1B132, 0x1B132}, {0x1B150, 0x1B152}, {0x1B155, 0x1B155}, + {0x1B164, 0x1B167}, {0x1B170, 0x1B2FB}, {0x1BC00, 0x1BC6A}, + {0x1BC70, 0x1BC7C}, {0x1BC80, 0x1BC88}, {0x1BC90, 0x1BC99}, + {0x1BC9C, 0x1BC9F}, {0x1CF00, 0x1CF2D}, {0x1CF30, 0x1CF46}, + {0x1CF50, 0x1CFC3}, {0x1D000, 0x1D0F5}, {0x1D100, 0x1D126}, + {0x1D129, 0x1D172}, {0x1D17B, 0x1D1EA}, {0x1D200, 0x1D245}, + {0x1D2C0, 0x1D2D3}, {0x1D2E0, 0x1D2F3}, {0x1D300, 0x1D356}, + {0x1D360, 0x1D378}, {0x1D400, 0x1D454}, {0x1D456, 0x1D49C}, + {0x1D49E, 0x1D49F}, {0x1D4A2, 0x1D4A2}, {0x1D4A5, 0x1D4A6}, + {0x1D4A9, 0x1D4AC}, {0x1D4AE, 0x1D4B9}, {0x1D4BB, 0x1D4BB}, + {0x1D4BD, 0x1D4C3}, {0x1D4C5, 0x1D505}, {0x1D507, 0x1D50A}, + {0x1D50D, 0x1D514}, {0x1D516, 0x1D51C}, {0x1D51E, 0x1D539}, + {0x1D53B, 0x1D53E}, {0x1D540, 0x1D544}, {0x1D546, 0x1D546}, + {0x1D54A, 0x1D550}, {0x1D552, 0x1D6A5}, {0x1D6A8, 0x1D7CB}, + {0x1D7CE, 0x1DA8B}, {0x1DA9B, 0x1DA9F}, {0x1DAA1, 0x1DAAF}, + {0x1DF00, 0x1DF1E}, {0x1DF25, 0x1DF2A}, {0x1E000, 0x1E006}, {0x1E008, 0x1E018}, {0x1E01B, 0x1E021}, {0x1E023, 0x1E024}, - {0x1E026, 0x1E02A}, {0x1E100, 0x1E12C}, {0x1E130, 0x1E13D}, - {0x1E140, 0x1E149}, {0x1E14E, 0x1E14F}, {0x1E290, 0x1E2AE}, - {0x1E2C0, 0x1E2F9}, {0x1E2FF, 0x1E2FF}, {0x1E7E0, 0x1E7E6}, + {0x1E026, 0x1E02A}, {0x1E030, 0x1E06D}, {0x1E08F, 0x1E08F}, + {0x1E100, 0x1E12C}, {0x1E130, 0x1E13D}, {0x1E140, 0x1E149}, + {0x1E14E, 0x1E14F}, {0x1E290, 0x1E2AE}, {0x1E2C0, 0x1E2F9}, + {0x1E2FF, 0x1E2FF}, {0x1E4D0, 0x1E4F9}, {0x1E7E0, 0x1E7E6}, {0x1E7E8, 0x1E7EB}, {0x1E7ED, 0x1E7EE}, {0x1E7F0, 0x1E7FE}, {0x1E800, 0x1E8C4}, {0x1E8C7, 0x1E8D6}, {0x1E900, 0x1E94B}, {0x1E950, 0x1E959}, {0x1E95E, 0x1E95F}, {0x1EC71, 0x1ECB4}, @@ -249,18 +253,17 @@ bool isPrintable(int UCS) { {0x1F0C1, 0x1F0CF}, {0x1F0D1, 0x1F0F5}, {0x1F100, 0x1F1AD}, {0x1F1E6, 0x1F202}, {0x1F210, 0x1F23B}, {0x1F240, 0x1F248}, {0x1F250, 0x1F251}, {0x1F260, 0x1F265}, {0x1F300, 0x1F6D7}, - {0x1F6DD, 0x1F6EC}, {0x1F6F0, 0x1F6FC}, {0x1F700, 0x1F773}, - {0x1F780, 0x1F7D8}, {0x1F7E0, 0x1F7EB}, {0x1F7F0, 0x1F7F0}, + {0x1F6DC, 0x1F6EC}, {0x1F6F0, 0x1F6FC}, {0x1F700, 0x1F776}, + {0x1F77B, 0x1F7D9}, {0x1F7E0, 0x1F7EB}, {0x1F7F0, 0x1F7F0}, {0x1F800, 0x1F80B}, {0x1F810, 0x1F847}, {0x1F850, 0x1F859}, {0x1F860, 0x1F887}, {0x1F890, 0x1F8AD}, {0x1F8B0, 0x1F8B1}, - {0x1F900, 0x1FA53}, {0x1FA60, 0x1FA6D}, {0x1FA70, 0x1FA74}, - {0x1FA78, 0x1FA7C}, {0x1FA80, 0x1FA86}, {0x1FA90, 0x1FAAC}, - {0x1FAB0, 0x1FABA}, {0x1FAC0, 0x1FAC5}, {0x1FAD0, 0x1FAD9}, - {0x1FAE0, 0x1FAE7}, {0x1FAF0, 0x1FAF6}, {0x1FB00, 0x1FB92}, - {0x1FB94, 0x1FBCA}, {0x1FBF0, 0x1FBF9}, {0x20000, 0x2A6DF}, - {0x2A700, 0x2B738}, {0x2B740, 0x2B81D}, {0x2B820, 0x2CEA1}, - {0x2CEB0, 0x2EBE0}, {0x2F800, 0x2FA1D}, {0x30000, 0x3134A}, - {0xE0100, 0xE01EF}}; + {0x1F900, 0x1FA53}, {0x1FA60, 0x1FA6D}, {0x1FA70, 0x1FA7C}, + {0x1FA80, 0x1FA88}, {0x1FA90, 0x1FABD}, {0x1FABF, 0x1FAC5}, + {0x1FACE, 0x1FADB}, {0x1FAE0, 0x1FAE8}, {0x1FAF0, 0x1FAF8}, + {0x1FB00, 0x1FB92}, {0x1FB94, 0x1FBCA}, {0x1FBF0, 0x1FBF9}, + {0x20000, 0x2A6DF}, {0x2A700, 0x2B739}, {0x2B740, 0x2B81D}, + {0x2B820, 0x2CEA1}, {0x2CEB0, 0x2EBE0}, {0x2F800, 0x2FA1D}, + {0x30000, 0x3134A}, {0x31350, 0x323AF}, {0xE0100, 0xE01EF}}; static const UnicodeCharSet Printables(PrintableRanges); // Clang special cases 0x00AD (SOFT HYPHEN) which is rendered as an actual @@ -272,7 +275,7 @@ bool isPrintable(int UCS) { /// formatting characters. bool isFormatting(int UCS) { - // https://unicode.org/Public/14.0.0/ucdxml/ + // https://unicode.org/Public/15.0.0/ucdxml/ static const UnicodeCharRange Cf[] = { {0x00AD, 0x00AD}, {0x0600, 0x0605}, {0x061C, 0x061C}, {0x06DD, 0x06DD}, {0x070F, 0x070F}, {0x0890, 0x0891}, @@ -297,114 +300,174 @@ bool isFormatting(int UCS) { /// * 0 for non-spacing and enclosing combining marks; /// * 2 for CJK characters excluding halfwidth forms; /// * 1 for all remaining characters. -static inline int charWidth(int UCS) -{ +static inline int charWidth(int UCS) { if (!isPrintable(UCS)) return ErrorNonPrintableCharacter; // Sorted list of non-spacing and enclosing combining mark intervals as // defined in "3.6 Combination" of - // http://www.unicode.org/versions/Unicode6.2.0/UnicodeStandard-6.2.pdf + // https://www.unicode.org/versions/Unicode15.0.0/UnicodeStandard-15.0.pdf static const UnicodeCharRange CombiningCharacterRanges[] = { - { 0x0300, 0x036F }, { 0x0483, 0x0489 }, { 0x0591, 0x05BD }, - { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 }, { 0x05C4, 0x05C5 }, - { 0x05C7, 0x05C7 }, { 0x0610, 0x061A }, { 0x064B, 0x065F }, - { 0x0670, 0x0670 }, { 0x06D6, 0x06DC }, { 0x06DF, 0x06E4 }, - { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED }, { 0x0711, 0x0711 }, - { 0x0730, 0x074A }, { 0x07A6, 0x07B0 }, { 0x07EB, 0x07F3 }, - { 0x0816, 0x0819 }, { 0x081B, 0x0823 }, { 0x0825, 0x0827 }, - { 0x0829, 0x082D }, { 0x0859, 0x085B }, { 0x08E4, 0x08FE }, - { 0x0900, 0x0902 }, { 0x093A, 0x093A }, { 0x093C, 0x093C }, - { 0x0941, 0x0948 }, { 0x094D, 0x094D }, { 0x0951, 0x0957 }, - { 0x0962, 0x0963 }, { 0x0981, 0x0981 }, { 0x09BC, 0x09BC }, - { 0x09C1, 0x09C4 }, { 0x09CD, 0x09CD }, { 0x09E2, 0x09E3 }, - { 0x0A01, 0x0A02 }, { 0x0A3C, 0x0A3C }, { 0x0A41, 0x0A42 }, - { 0x0A47, 0x0A48 }, { 0x0A4B, 0x0A4D }, { 0x0A51, 0x0A51 }, - { 0x0A70, 0x0A71 }, { 0x0A75, 0x0A75 }, { 0x0A81, 0x0A82 }, - { 0x0ABC, 0x0ABC }, { 0x0AC1, 0x0AC5 }, { 0x0AC7, 0x0AC8 }, - { 0x0ACD, 0x0ACD }, { 0x0AE2, 0x0AE3 }, { 0x0B01, 0x0B01 }, - { 0x0B3C, 0x0B3C }, { 0x0B3F, 0x0B3F }, { 0x0B41, 0x0B44 }, - { 0x0B4D, 0x0B4D }, { 0x0B56, 0x0B56 }, { 0x0B62, 0x0B63 }, - { 0x0B82, 0x0B82 }, { 0x0BC0, 0x0BC0 }, { 0x0BCD, 0x0BCD }, - { 0x0C3E, 0x0C40 }, { 0x0C46, 0x0C48 }, { 0x0C4A, 0x0C4D }, - { 0x0C55, 0x0C56 }, { 0x0C62, 0x0C63 }, { 0x0CBC, 0x0CBC }, - { 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 }, { 0x0CCC, 0x0CCD }, - { 0x0CE2, 0x0CE3 }, { 0x0D41, 0x0D44 }, { 0x0D4D, 0x0D4D }, - { 0x0D62, 0x0D63 }, { 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 }, - { 0x0F8D, 0x0F97 }, { 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 }, - { 0x102D, 0x1030 }, { 0x1032, 0x1037 }, { 0x1039, 0x103A }, - { 0x103D, 0x103E }, { 0x1058, 0x1059 }, { 0x105E, 0x1060 }, - { 0x1071, 0x1074 }, { 0x1082, 0x1082 }, { 0x1085, 0x1086 }, - { 0x108D, 0x108D }, { 0x109D, 0x109D }, { 0x135D, 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 }, { 0x1A56, 0x1A56 }, { 0x1A58, 0x1A5E }, - { 0x1A60, 0x1A60 }, { 0x1A62, 0x1A62 }, { 0x1A65, 0x1A6C }, - { 0x1A73, 0x1A7C }, { 0x1A7F, 0x1A7F }, { 0x1B00, 0x1B03 }, - { 0x1B34, 0x1B34 }, { 0x1B36, 0x1B3A }, { 0x1B3C, 0x1B3C }, - { 0x1B42, 0x1B42 }, { 0x1B6B, 0x1B73 }, { 0x1B80, 0x1B81 }, - { 0x1BA2, 0x1BA5 }, { 0x1BA8, 0x1BA9 }, { 0x1BAB, 0x1BAB }, - { 0x1BE6, 0x1BE6 }, { 0x1BE8, 0x1BE9 }, { 0x1BED, 0x1BED }, - { 0x1BEF, 0x1BF1 }, { 0x1C2C, 0x1C33 }, { 0x1C36, 0x1C37 }, - { 0x1CD0, 0x1CD2 }, { 0x1CD4, 0x1CE0 }, { 0x1CE2, 0x1CE8 }, - { 0x1CED, 0x1CED }, { 0x1CF4, 0x1CF4 }, { 0x1DC0, 0x1DE6 }, - { 0x1DFC, 0x1DFF }, { 0x20D0, 0x20F0 }, { 0x2CEF, 0x2CF1 }, - { 0x2D7F, 0x2D7F }, { 0x2DE0, 0x2DFF }, { 0x302A, 0x302D }, - { 0x3099, 0x309A }, { 0xA66F, 0xA672 }, { 0xA674, 0xA67D }, - { 0xA69F, 0xA69F }, { 0xA6F0, 0xA6F1 }, { 0xA802, 0xA802 }, - { 0xA806, 0xA806 }, { 0xA80B, 0xA80B }, { 0xA825, 0xA826 }, - { 0xA8C4, 0xA8C4 }, { 0xA8E0, 0xA8F1 }, { 0xA926, 0xA92D }, - { 0xA947, 0xA951 }, { 0xA980, 0xA982 }, { 0xA9B3, 0xA9B3 }, - { 0xA9B6, 0xA9B9 }, { 0xA9BC, 0xA9BC }, { 0xAA29, 0xAA2E }, - { 0xAA31, 0xAA32 }, { 0xAA35, 0xAA36 }, { 0xAA43, 0xAA43 }, - { 0xAA4C, 0xAA4C }, { 0xAAB0, 0xAAB0 }, { 0xAAB2, 0xAAB4 }, - { 0xAAB7, 0xAAB8 }, { 0xAABE, 0xAABF }, { 0xAAC1, 0xAAC1 }, - { 0xAAEC, 0xAAED }, { 0xAAF6, 0xAAF6 }, { 0xABE5, 0xABE5 }, - { 0xABE8, 0xABE8 }, { 0xABED, 0xABED }, { 0xFB1E, 0xFB1E }, - { 0xFE00, 0xFE0F }, { 0xFE20, 0xFE26 }, { 0x101FD, 0x101FD }, - { 0x10A01, 0x10A03 }, { 0x10A05, 0x10A06 }, { 0x10A0C, 0x10A0F }, - { 0x10A38, 0x10A3A }, { 0x10A3F, 0x10A3F }, { 0x11001, 0x11001 }, - { 0x11038, 0x11046 }, { 0x11080, 0x11081 }, { 0x110B3, 0x110B6 }, - { 0x110B9, 0x110BA }, { 0x11100, 0x11102 }, { 0x11127, 0x1112B }, - { 0x1112D, 0x11134 }, { 0x11180, 0x11181 }, { 0x111B6, 0x111BE }, - { 0x116AB, 0x116AB }, { 0x116AD, 0x116AD }, { 0x116B0, 0x116B5 }, - { 0x116B7, 0x116B7 }, { 0x16F8F, 0x16F92 }, { 0x1D167, 0x1D169 }, - { 0x1D17B, 0x1D182 }, { 0x1D185, 0x1D18B }, { 0x1D1AA, 0x1D1AD }, - { 0x1D242, 0x1D244 }, { 0xE0100, 0xE01EF }, + {0x0300, 0x036F}, {0x0483, 0x0489}, {0x0591, 0x05BD}, + {0x05BF, 0x05BF}, {0x05C1, 0x05C2}, {0x05C4, 0x05C5}, + {0x05C7, 0x05C7}, {0x0610, 0x061A}, {0x064B, 0x065F}, + {0x0670, 0x0670}, {0x06D6, 0x06DC}, {0x06DF, 0x06E4}, + {0x06E7, 0x06E8}, {0x06EA, 0x06ED}, {0x0711, 0x0711}, + {0x0730, 0x074A}, {0x07A6, 0x07B0}, {0x07EB, 0x07F3}, + {0x07FD, 0x07FD}, {0x0816, 0x0819}, {0x081B, 0x0823}, + {0x0825, 0x0827}, {0x0829, 0x082D}, {0x0859, 0x085B}, + {0x0898, 0x089F}, {0x08CA, 0x08E1}, {0x08E3, 0x0902}, + {0x093A, 0x093A}, {0x093C, 0x093C}, {0x0941, 0x0948}, + {0x094D, 0x094D}, {0x0951, 0x0957}, {0x0962, 0x0963}, + {0x0981, 0x0981}, {0x09BC, 0x09BC}, {0x09C1, 0x09C4}, + {0x09CD, 0x09CD}, {0x09E2, 0x09E3}, {0x09FE, 0x09FE}, + {0x0A01, 0x0A02}, {0x0A3C, 0x0A3C}, {0x0A41, 0x0A42}, + {0x0A47, 0x0A48}, {0x0A4B, 0x0A4D}, {0x0A51, 0x0A51}, + {0x0A70, 0x0A71}, {0x0A75, 0x0A75}, {0x0A81, 0x0A82}, + {0x0ABC, 0x0ABC}, {0x0AC1, 0x0AC5}, {0x0AC7, 0x0AC8}, + {0x0ACD, 0x0ACD}, {0x0AE2, 0x0AE3}, {0x0AFA, 0x0AFF}, + {0x0B01, 0x0B01}, {0x0B3C, 0x0B3C}, {0x0B3F, 0x0B3F}, + {0x0B41, 0x0B44}, {0x0B4D, 0x0B4D}, {0x0B55, 0x0B56}, + {0x0B62, 0x0B63}, {0x0B82, 0x0B82}, {0x0BC0, 0x0BC0}, + {0x0BCD, 0x0BCD}, {0x0C00, 0x0C00}, {0x0C04, 0x0C04}, + {0x0C3C, 0x0C3C}, {0x0C3E, 0x0C40}, {0x0C46, 0x0C48}, + {0x0C4A, 0x0C4D}, {0x0C55, 0x0C56}, {0x0C62, 0x0C63}, + {0x0C81, 0x0C81}, {0x0CBC, 0x0CBC}, {0x0CBF, 0x0CBF}, + {0x0CC6, 0x0CC6}, {0x0CCC, 0x0CCD}, {0x0CE2, 0x0CE3}, + {0x0D00, 0x0D01}, {0x0D3B, 0x0D3C}, {0x0D41, 0x0D44}, + {0x0D4D, 0x0D4D}, {0x0D62, 0x0D63}, {0x0D81, 0x0D81}, + {0x0DCA, 0x0DCA}, {0x0DD2, 0x0DD4}, {0x0DD6, 0x0DD6}, + {0x0E31, 0x0E31}, {0x0E34, 0x0E3A}, {0x0E47, 0x0E4E}, + {0x0EB1, 0x0EB1}, {0x0EB4, 0x0EBC}, {0x0EC8, 0x0ECE}, + {0x0F18, 0x0F19}, {0x0F35, 0x0F35}, {0x0F37, 0x0F37}, + {0x0F39, 0x0F39}, {0x0F71, 0x0F7E}, {0x0F80, 0x0F84}, + {0x0F86, 0x0F87}, {0x0F8D, 0x0F97}, {0x0F99, 0x0FBC}, + {0x0FC6, 0x0FC6}, {0x102D, 0x1030}, {0x1032, 0x1037}, + {0x1039, 0x103A}, {0x103D, 0x103E}, {0x1058, 0x1059}, + {0x105E, 0x1060}, {0x1071, 0x1074}, {0x1082, 0x1082}, + {0x1085, 0x1086}, {0x108D, 0x108D}, {0x109D, 0x109D}, + {0x135D, 0x135F}, {0x1712, 0x1714}, {0x1732, 0x1733}, + {0x1752, 0x1753}, {0x1772, 0x1773}, {0x17B4, 0x17B5}, + {0x17B7, 0x17BD}, {0x17C6, 0x17C6}, {0x17C9, 0x17D3}, + {0x17DD, 0x17DD}, {0x180B, 0x180D}, {0x180F, 0x180F}, + {0x1885, 0x1886}, {0x18A9, 0x18A9}, {0x1920, 0x1922}, + {0x1927, 0x1928}, {0x1932, 0x1932}, {0x1939, 0x193B}, + {0x1A17, 0x1A18}, {0x1A1B, 0x1A1B}, {0x1A56, 0x1A56}, + {0x1A58, 0x1A5E}, {0x1A60, 0x1A60}, {0x1A62, 0x1A62}, + {0x1A65, 0x1A6C}, {0x1A73, 0x1A7C}, {0x1A7F, 0x1A7F}, + {0x1AB0, 0x1ACE}, {0x1B00, 0x1B03}, {0x1B34, 0x1B34}, + {0x1B36, 0x1B3A}, {0x1B3C, 0x1B3C}, {0x1B42, 0x1B42}, + {0x1B6B, 0x1B73}, {0x1B80, 0x1B81}, {0x1BA2, 0x1BA5}, + {0x1BA8, 0x1BA9}, {0x1BAB, 0x1BAD}, {0x1BE6, 0x1BE6}, + {0x1BE8, 0x1BE9}, {0x1BED, 0x1BED}, {0x1BEF, 0x1BF1}, + {0x1C2C, 0x1C33}, {0x1C36, 0x1C37}, {0x1CD0, 0x1CD2}, + {0x1CD4, 0x1CE0}, {0x1CE2, 0x1CE8}, {0x1CED, 0x1CED}, + {0x1CF4, 0x1CF4}, {0x1CF8, 0x1CF9}, {0x1DC0, 0x1DFF}, + {0x20D0, 0x20F0}, {0x2CEF, 0x2CF1}, {0x2D7F, 0x2D7F}, + {0x2DE0, 0x2DFF}, {0x302A, 0x302D}, {0x3099, 0x309A}, + {0xA66F, 0xA672}, {0xA674, 0xA67D}, {0xA69E, 0xA69F}, + {0xA6F0, 0xA6F1}, {0xA802, 0xA802}, {0xA806, 0xA806}, + {0xA80B, 0xA80B}, {0xA825, 0xA826}, {0xA82C, 0xA82C}, + {0xA8C4, 0xA8C5}, {0xA8E0, 0xA8F1}, {0xA8FF, 0xA8FF}, + {0xA926, 0xA92D}, {0xA947, 0xA951}, {0xA980, 0xA982}, + {0xA9B3, 0xA9B3}, {0xA9B6, 0xA9B9}, {0xA9BC, 0xA9BD}, + {0xA9E5, 0xA9E5}, {0xAA29, 0xAA2E}, {0xAA31, 0xAA32}, + {0xAA35, 0xAA36}, {0xAA43, 0xAA43}, {0xAA4C, 0xAA4C}, + {0xAA7C, 0xAA7C}, {0xAAB0, 0xAAB0}, {0xAAB2, 0xAAB4}, + {0xAAB7, 0xAAB8}, {0xAABE, 0xAABF}, {0xAAC1, 0xAAC1}, + {0xAAEC, 0xAAED}, {0xAAF6, 0xAAF6}, {0xABE5, 0xABE5}, + {0xABE8, 0xABE8}, {0xABED, 0xABED}, {0xFB1E, 0xFB1E}, + {0xFE00, 0xFE0F}, {0xFE20, 0xFE2F}, {0x101FD, 0x101FD}, + {0x102E0, 0x102E0}, {0x10376, 0x1037A}, {0x10A01, 0x10A03}, + {0x10A05, 0x10A06}, {0x10A0C, 0x10A0F}, {0x10A38, 0x10A3A}, + {0x10A3F, 0x10A3F}, {0x10AE5, 0x10AE6}, {0x10D24, 0x10D27}, + {0x10EAB, 0x10EAC}, {0x10EFD, 0x10EFF}, {0x10F46, 0x10F50}, + {0x10F82, 0x10F85}, {0x11001, 0x11001}, {0x11038, 0x11046}, + {0x11070, 0x11070}, {0x11073, 0x11074}, {0x1107F, 0x11081}, + {0x110B3, 0x110B6}, {0x110B9, 0x110BA}, {0x110C2, 0x110C2}, + {0x11100, 0x11102}, {0x11127, 0x1112B}, {0x1112D, 0x11134}, + {0x11173, 0x11173}, {0x11180, 0x11181}, {0x111B6, 0x111BE}, + {0x111C9, 0x111CC}, {0x111CF, 0x111CF}, {0x1122F, 0x11231}, + {0x11234, 0x11234}, {0x11236, 0x11237}, {0x1123E, 0x1123E}, + {0x11241, 0x11241}, {0x112DF, 0x112DF}, {0x112E3, 0x112EA}, + {0x11300, 0x11301}, {0x1133B, 0x1133C}, {0x11340, 0x11340}, + {0x11366, 0x1136C}, {0x11370, 0x11374}, {0x11438, 0x1143F}, + {0x11442, 0x11444}, {0x11446, 0x11446}, {0x1145E, 0x1145E}, + {0x114B3, 0x114B8}, {0x114BA, 0x114BA}, {0x114BF, 0x114C0}, + {0x114C2, 0x114C3}, {0x115B2, 0x115B5}, {0x115BC, 0x115BD}, + {0x115BF, 0x115C0}, {0x115DC, 0x115DD}, {0x11633, 0x1163A}, + {0x1163D, 0x1163D}, {0x1163F, 0x11640}, {0x116AB, 0x116AB}, + {0x116AD, 0x116AD}, {0x116B0, 0x116B5}, {0x116B7, 0x116B7}, + {0x1171D, 0x1171F}, {0x11722, 0x11725}, {0x11727, 0x1172B}, + {0x1182F, 0x11837}, {0x11839, 0x1183A}, {0x1193B, 0x1193C}, + {0x1193E, 0x1193E}, {0x11943, 0x11943}, {0x119D4, 0x119D7}, + {0x119DA, 0x119DB}, {0x119E0, 0x119E0}, {0x11A01, 0x11A0A}, + {0x11A33, 0x11A38}, {0x11A3B, 0x11A3E}, {0x11A47, 0x11A47}, + {0x11A51, 0x11A56}, {0x11A59, 0x11A5B}, {0x11A8A, 0x11A96}, + {0x11A98, 0x11A99}, {0x11C30, 0x11C36}, {0x11C38, 0x11C3D}, + {0x11C3F, 0x11C3F}, {0x11C92, 0x11CA7}, {0x11CAA, 0x11CB0}, + {0x11CB2, 0x11CB3}, {0x11CB5, 0x11CB6}, {0x11D31, 0x11D36}, + {0x11D3A, 0x11D3A}, {0x11D3C, 0x11D3D}, {0x11D3F, 0x11D45}, + {0x11D47, 0x11D47}, {0x11D90, 0x11D91}, {0x11D95, 0x11D95}, + {0x11D97, 0x11D97}, {0x11EF3, 0x11EF4}, {0x11F00, 0x11F01}, + {0x11F36, 0x11F3A}, {0x11F40, 0x11F40}, {0x11F42, 0x11F42}, + {0x13440, 0x13440}, {0x13447, 0x13455}, {0x16AF0, 0x16AF4}, + {0x16B30, 0x16B36}, {0x16F4F, 0x16F4F}, {0x16F8F, 0x16F92}, + {0x16FE4, 0x16FE4}, {0x1BC9D, 0x1BC9E}, {0x1CF00, 0x1CF2D}, + {0x1CF30, 0x1CF46}, {0x1D167, 0x1D169}, {0x1D17B, 0x1D182}, + {0x1D185, 0x1D18B}, {0x1D1AA, 0x1D1AD}, {0x1D242, 0x1D244}, + {0x1DA00, 0x1DA36}, {0x1DA3B, 0x1DA6C}, {0x1DA75, 0x1DA75}, + {0x1DA84, 0x1DA84}, {0x1DA9B, 0x1DA9F}, {0x1DAA1, 0x1DAAF}, + {0x1E000, 0x1E006}, {0x1E008, 0x1E018}, {0x1E01B, 0x1E021}, + {0x1E023, 0x1E024}, {0x1E026, 0x1E02A}, {0x1E08F, 0x1E08F}, + {0x1E130, 0x1E136}, {0x1E2AE, 0x1E2AE}, {0x1E2EC, 0x1E2EF}, + {0x1E4EC, 0x1E4EF}, {0x1E8D0, 0x1E8D6}, {0x1E944, 0x1E94A}, + {0xE0100, 0xE01EF}, }; static const UnicodeCharSet CombiningCharacters(CombiningCharacterRanges); if (CombiningCharacters.contains(UCS)) return 0; + // We consider double width codepoints any codepoint with + // the property East_Asian_Width=F|W + // + Misc Symbols and Pictographs (U+1F300...U+1F5FF) + // + Supplemental Symbols and Pictographs (U+1F900...U+1F9FF) static const UnicodeCharRange DoubleWidthCharacterRanges[] = { - // Hangul Jamo - { 0x1100, 0x11FF }, - // Deprecated fullwidth angle brackets - { 0x2329, 0x232A }, - // CJK Misc, CJK Unified Ideographs, Yijing Hexagrams, Yi - // excluding U+303F (IDEOGRAPHIC HALF FILL SPACE) - { 0x2E80, 0x303E }, { 0x3040, 0xA4CF }, - // Hangul - { 0xAC00, 0xD7A3 }, { 0xD7B0, 0xD7C6 }, { 0xD7CB, 0xD7FB }, - // CJK Unified Ideographs - { 0xF900, 0xFAFF }, - // Vertical forms - { 0xFE10, 0xFE19 }, - // CJK Compatibility Forms + Small Form Variants - { 0xFE30, 0xFE6F }, - // Fullwidth forms - { 0xFF01, 0xFF60 }, { 0xFFE0, 0xFFE6 }, - // CJK Unified Ideographs - { 0x20000, 0x2A6DF }, { 0x2A700, 0x2B81F }, { 0x2F800, 0x2FA1F } + {0x1100, 0x115F}, {0x231A, 0x231B}, {0x2329, 0x232A}, + {0x23E9, 0x23EC}, {0x23F0, 0x23F0}, {0x23F3, 0x23F3}, + {0x25FD, 0x25FE}, {0x2614, 0x2615}, {0x2648, 0x2653}, + {0x267F, 0x267F}, {0x2693, 0x2693}, {0x26A1, 0x26A1}, + {0x26AA, 0x26AB}, {0x26BD, 0x26BE}, {0x26C4, 0x26C5}, + {0x26CE, 0x26CE}, {0x26D4, 0x26D4}, {0x26EA, 0x26EA}, + {0x26F2, 0x26F3}, {0x26F5, 0x26F5}, {0x26FA, 0x26FA}, + {0x26FD, 0x26FD}, {0x2705, 0x2705}, {0x270A, 0x270B}, + {0x2728, 0x2728}, {0x274C, 0x274C}, {0x274E, 0x274E}, + {0x2753, 0x2755}, {0x2757, 0x2757}, {0x2795, 0x2797}, + {0x27B0, 0x27B0}, {0x27BF, 0x27BF}, {0x2B1B, 0x2B1C}, + {0x2B50, 0x2B50}, {0x2B55, 0x2B55}, {0x2E80, 0x2E99}, + {0x2E9B, 0x2EF3}, {0x2F00, 0x2FD5}, {0x2FF0, 0x2FFB}, + {0x3000, 0x303E}, {0x3041, 0x3096}, {0x3099, 0x30FF}, + {0x3105, 0x312F}, {0x3131, 0x318E}, {0x3190, 0x31E3}, + {0x31F0, 0x321E}, {0x3220, 0x3247}, {0x3250, 0xA48C}, + {0xA490, 0xA4C6}, {0xA960, 0xA97C}, {0xAC00, 0xD7A3}, + {0xF900, 0xFAFF}, {0xFE10, 0xFE19}, {0xFE30, 0xFE52}, + {0xFE54, 0xFE66}, {0xFE68, 0xFE6B}, {0xFF01, 0xFF60}, + {0xFFE0, 0xFFE6}, {0x16FE0, 0x16FE4}, {0x16FF0, 0x16FF1}, + {0x17000, 0x187F7}, {0x18800, 0x18CD5}, {0x18D00, 0x18D08}, + {0x1AFF0, 0x1AFF3}, {0x1AFF5, 0x1AFFB}, {0x1AFFD, 0x1AFFE}, + {0x1B000, 0x1B122}, {0x1B132, 0x1B132}, {0x1B150, 0x1B152}, + {0x1B155, 0x1B155}, {0x1B164, 0x1B167}, {0x1B170, 0x1B2FB}, + {0x1F004, 0x1F004}, {0x1F0CF, 0x1F0CF}, {0x1F18E, 0x1F18E}, + {0x1F191, 0x1F19A}, {0x1F200, 0x1F202}, {0x1F210, 0x1F23B}, + {0x1F240, 0x1F248}, {0x1F250, 0x1F251}, {0x1F260, 0x1F265}, + {0x1F300, 0x1F64F}, {0x1F680, 0x1F6C5}, {0x1F6CC, 0x1F6CC}, + {0x1F6D0, 0x1F6D2}, {0x1F6D5, 0x1F6D7}, {0x1F6DC, 0x1F6DF}, + {0x1F6EB, 0x1F6EC}, {0x1F6F4, 0x1F6FC}, {0x1F7E0, 0x1F7EB}, + {0x1F7F0, 0x1F7F0}, {0x1F900, 0x1F9FF}, {0x1FA70, 0x1FA7C}, + {0x1FA80, 0x1FA88}, {0x1FA90, 0x1FABD}, {0x1FABF, 0x1FAC5}, + {0x1FACE, 0x1FADB}, {0x1FAE0, 0x1FAE8}, {0x1FAF0, 0x1FAF8}, + {0x20000, 0x2FFFD}, {0x30000, 0x3FFFD} }; static const UnicodeCharSet DoubleWidthCharacters(DoubleWidthCharacterRanges); @@ -448,4 +511,3 @@ int columnWidthUTF8(StringRef Text) { } // namespace unicode } // namespace sys } // namespace llvm - |