[Clang] Update Unicode version to 15.1 (#77147)
This update all of our Unicode tables to Unicode 15.1. This is a minor version so only a relatively small numbers of characters are added, mainly ideographs https://www.unicode.org/versions/Unicode15.1.0/#Appendices_nb
This commit is contained in:
parent
b26bfcc1ec
commit
03e43cf1c7
@ -281,6 +281,8 @@ Non-comprehensive list of changes in this release
|
||||
|
||||
* Added ``#pragma clang fp reciprocal``.
|
||||
|
||||
* The version of Unicode used by Clang (primarily to parse identifiers) has been updated to 15.1.
|
||||
|
||||
New Compiler Flags
|
||||
------------------
|
||||
|
||||
|
@ -10,7 +10,7 @@
|
||||
|
||||
#include "llvm/Support/UnicodeCharRanges.h"
|
||||
|
||||
// Unicode 15.0 XID_Start
|
||||
// Unicode 15.1 XID_Start
|
||||
static const llvm::sys::UnicodeCharRange XIDStartRanges[] = {
|
||||
{0x0041, 0x005A}, {0x0061, 0x007A}, {0x00AA, 0x00AA},
|
||||
{0x00B5, 0x00B5}, {0x00BA, 0x00BA}, {0x00C0, 0x00D6},
|
||||
@ -233,9 +233,10 @@ static const llvm::sys::UnicodeCharRange XIDStartRanges[] = {
|
||||
{0x1EE8B, 0x1EE9B}, {0x1EEA1, 0x1EEA3}, {0x1EEA5, 0x1EEA9},
|
||||
{0x1EEAB, 0x1EEBB}, {0x20000, 0x2A6DF}, {0x2A700, 0x2B739},
|
||||
{0x2B740, 0x2B81D}, {0x2B820, 0x2CEA1}, {0x2CEB0, 0x2EBE0},
|
||||
{0x2F800, 0x2FA1D}, {0x30000, 0x3134A}, {0x31350, 0x323AF}};
|
||||
{0x2EBF0, 0x2EE5D}, {0x2F800, 0x2FA1D}, {0x30000, 0x3134A},
|
||||
{0x31350, 0x323AF}};
|
||||
|
||||
// Unicode 15.0 XID_Continue, excluding XID_Start
|
||||
// Unicode 15.1 XID_Continue, excluding XID_Start
|
||||
// The Unicode Property XID_Continue is a super set of XID_Start.
|
||||
// To save Space, the table below only contains the codepoints
|
||||
// that are not also in XID_Start.
|
||||
@ -299,24 +300,25 @@ static const llvm::sys::UnicodeCharRange XIDContinueRanges[] = {
|
||||
{0x1C24, 0x1C37}, {0x1C40, 0x1C49}, {0x1C50, 0x1C59},
|
||||
{0x1CD0, 0x1CD2}, {0x1CD4, 0x1CE8}, {0x1CED, 0x1CED},
|
||||
{0x1CF4, 0x1CF4}, {0x1CF7, 0x1CF9}, {0x1DC0, 0x1DFF},
|
||||
{0x203F, 0x2040}, {0x2054, 0x2054}, {0x20D0, 0x20DC},
|
||||
{0x20E1, 0x20E1}, {0x20E5, 0x20F0}, {0x2CEF, 0x2CF1},
|
||||
{0x2D7F, 0x2D7F}, {0x2DE0, 0x2DFF}, {0x302A, 0x302F},
|
||||
{0x3099, 0x309A}, {0xA620, 0xA629}, {0xA66F, 0xA66F},
|
||||
{0xA674, 0xA67D}, {0xA69E, 0xA69F}, {0xA6F0, 0xA6F1},
|
||||
{0xA802, 0xA802}, {0xA806, 0xA806}, {0xA80B, 0xA80B},
|
||||
{0xA823, 0xA827}, {0xA82C, 0xA82C}, {0xA880, 0xA881},
|
||||
{0xA8B4, 0xA8C5}, {0xA8D0, 0xA8D9}, {0xA8E0, 0xA8F1},
|
||||
{0xA8FF, 0xA909}, {0xA926, 0xA92D}, {0xA947, 0xA953},
|
||||
{0xA980, 0xA983}, {0xA9B3, 0xA9C0}, {0xA9D0, 0xA9D9},
|
||||
{0xA9E5, 0xA9E5}, {0xA9F0, 0xA9F9}, {0xAA29, 0xAA36},
|
||||
{0xAA43, 0xAA43}, {0xAA4C, 0xAA4D}, {0xAA50, 0xAA59},
|
||||
{0xAA7B, 0xAA7D}, {0xAAB0, 0xAAB0}, {0xAAB2, 0xAAB4},
|
||||
{0xAAB7, 0xAAB8}, {0xAABE, 0xAABF}, {0xAAC1, 0xAAC1},
|
||||
{0xAAEB, 0xAAEF}, {0xAAF5, 0xAAF6}, {0xABE3, 0xABEA},
|
||||
{0xABEC, 0xABED}, {0xABF0, 0xABF9}, {0xFB1E, 0xFB1E},
|
||||
{0xFE00, 0xFE0F}, {0xFE20, 0xFE2F}, {0xFE33, 0xFE34},
|
||||
{0xFE4D, 0xFE4F}, {0xFF10, 0xFF19}, {0xFF3F, 0xFF3F},
|
||||
{0x200C, 0x200D}, {0x203F, 0x2040}, {0x2054, 0x2054},
|
||||
{0x20D0, 0x20DC}, {0x20E1, 0x20E1}, {0x20E5, 0x20F0},
|
||||
{0x2CEF, 0x2CF1}, {0x2D7F, 0x2D7F}, {0x2DE0, 0x2DFF},
|
||||
{0x302A, 0x302F}, {0x3099, 0x309A}, {0x30FB, 0x30FB},
|
||||
{0xA620, 0xA629}, {0xA66F, 0xA66F}, {0xA674, 0xA67D},
|
||||
{0xA69E, 0xA69F}, {0xA6F0, 0xA6F1}, {0xA802, 0xA802},
|
||||
{0xA806, 0xA806}, {0xA80B, 0xA80B}, {0xA823, 0xA827},
|
||||
{0xA82C, 0xA82C}, {0xA880, 0xA881}, {0xA8B4, 0xA8C5},
|
||||
{0xA8D0, 0xA8D9}, {0xA8E0, 0xA8F1}, {0xA8FF, 0xA909},
|
||||
{0xA926, 0xA92D}, {0xA947, 0xA953}, {0xA980, 0xA983},
|
||||
{0xA9B3, 0xA9C0}, {0xA9D0, 0xA9D9}, {0xA9E5, 0xA9E5},
|
||||
{0xA9F0, 0xA9F9}, {0xAA29, 0xAA36}, {0xAA43, 0xAA43},
|
||||
{0xAA4C, 0xAA4D}, {0xAA50, 0xAA59}, {0xAA7B, 0xAA7D},
|
||||
{0xAAB0, 0xAAB0}, {0xAAB2, 0xAAB4}, {0xAAB7, 0xAAB8},
|
||||
{0xAABE, 0xAABF}, {0xAAC1, 0xAAC1}, {0xAAEB, 0xAAEF},
|
||||
{0xAAF5, 0xAAF6}, {0xABE3, 0xABEA}, {0xABEC, 0xABED},
|
||||
{0xABF0, 0xABF9}, {0xFB1E, 0xFB1E}, {0xFE00, 0xFE0F},
|
||||
{0xFE20, 0xFE2F}, {0xFE33, 0xFE34}, {0xFE4D, 0xFE4F},
|
||||
{0xFF10, 0xFF19}, {0xFF3F, 0xFF3F}, {0xFF65, 0xFF65},
|
||||
{0xFF9E, 0xFF9F}, {0x101FD, 0x101FD}, {0x102E0, 0x102E0},
|
||||
{0x10376, 0x1037A}, {0x104A0, 0x104A9}, {0x10A01, 0x10A03},
|
||||
{0x10A05, 0x10A06}, {0x10A0C, 0x10A0F}, {0x10A38, 0x10A3A},
|
||||
@ -364,7 +366,8 @@ static const llvm::sys::UnicodeCharRange XIDContinueRanges[] = {
|
||||
{0x1E026, 0x1E02A}, {0x1E08F, 0x1E08F}, {0x1E130, 0x1E136},
|
||||
{0x1E140, 0x1E149}, {0x1E2AE, 0x1E2AE}, {0x1E2EC, 0x1E2F9},
|
||||
{0x1E4EC, 0x1E4F9}, {0x1E8D0, 0x1E8D6}, {0x1E944, 0x1E94A},
|
||||
{0x1E950, 0x1E959}, {0x1FBF0, 0x1FBF9}, {0xE0100, 0xE01EF}};
|
||||
{0x1E950, 0x1E959}, {0x1FBF0, 0x1FBF9}, {0xE0100, 0xE01EF},
|
||||
};
|
||||
|
||||
// Clang supports the "Mathematical notation profile" as an extension,
|
||||
// as described in https://www.unicode.org/L2/L2022/22230-math-profile.pdf
|
||||
|
@ -38,9 +38,10 @@ extern int ༀ;
|
||||
extern int 𑩐;
|
||||
extern int 𐠈;
|
||||
extern int ꙮ;
|
||||
extern int \u1B4C; // BALINESE LETTER ARCHAIC JNYA - Added in Unicode 14
|
||||
extern int \U00016AA2; // TANGSA LETTER GA - Added in Unicode 14
|
||||
extern int \U0001E4D0; // 𞓐 NAG MUNDARI LETTER O - Added in Unicode 15
|
||||
extern int \u1B4C; // BALINESE LETTER ARCHAIC JNYA - Added in Unicode 14
|
||||
extern int \U00016AA2; // TANGSA LETTER GA - Added in Unicode 14
|
||||
extern int \U0001E4D0; // 𞓐 NAG MUNDARI LETTER O - Added in Unicode 15
|
||||
extern int \u{2EBF0}; // CJK UNIFIED IDEOGRAPH-2EBF0 - Added in Unicode 15.1
|
||||
extern int a\N{TANGSA LETTER GA};
|
||||
extern int a\N{TANGSALETTERGA}; // expected-error {{'TANGSALETTERGA' is not a valid Unicode character name}} \
|
||||
// expected-error {{expected ';' after top level declarator}} \
|
||||
@ -74,7 +75,7 @@ extern int 👷; // expected-error {{unexpected character <U+1F477>}} \
|
||||
|
||||
extern int 👷♀; // expected-warning {{declaration does not declare anything}} \
|
||||
expected-error {{unexpected character <U+1F477>}} \
|
||||
expected-error {{unexpected character <U+200D>}} \
|
||||
expected-error {{character <U+200D> not allowed at the start of an identifier}} \
|
||||
expected-error {{unexpected character <U+2640>}}
|
||||
#else
|
||||
|
||||
|
@ -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/15.0.0/ucdxml/
|
||||
// https://unicode.org/Public/15.1.0/ucdxml/
|
||||
static const UnicodeCharRange PrintableRanges[] = {
|
||||
{0x0020, 0x007E}, {0x00A0, 0x00AC}, {0x00AE, 0x0377},
|
||||
{0x037A, 0x037F}, {0x0384, 0x038A}, {0x038C, 0x038C},
|
||||
@ -119,151 +119,152 @@ bool isPrintable(int UCS) {
|
||||
{0x2DB8, 0x2DBE}, {0x2DC0, 0x2DC6}, {0x2DC8, 0x2DCE},
|
||||
{0x2DD0, 0x2DD6}, {0x2DD8, 0x2DDE}, {0x2DE0, 0x2E5D},
|
||||
{0x2E80, 0x2E99}, {0x2E9B, 0x2EF3}, {0x2F00, 0x2FD5},
|
||||
{0x2FF0, 0x2FFB}, {0x3000, 0x303F}, {0x3041, 0x3096},
|
||||
{0x3099, 0x30FF}, {0x3105, 0x312F}, {0x3131, 0x318E},
|
||||
{0x3190, 0x31E3}, {0x31F0, 0x321E}, {0x3220, 0xA48C},
|
||||
{0xA490, 0xA4C6}, {0xA4D0, 0xA62B}, {0xA640, 0xA6F7},
|
||||
{0xA700, 0xA7CA}, {0xA7D0, 0xA7D1}, {0xA7D3, 0xA7D3},
|
||||
{0xA7D5, 0xA7D9}, {0xA7F2, 0xA82C}, {0xA830, 0xA839},
|
||||
{0xA840, 0xA877}, {0xA880, 0xA8C5}, {0xA8CE, 0xA8D9},
|
||||
{0xA8E0, 0xA953}, {0xA95F, 0xA97C}, {0xA980, 0xA9CD},
|
||||
{0xA9CF, 0xA9D9}, {0xA9DE, 0xA9FE}, {0xAA00, 0xAA36},
|
||||
{0xAA40, 0xAA4D}, {0xAA50, 0xAA59}, {0xAA5C, 0xAAC2},
|
||||
{0xAADB, 0xAAF6}, {0xAB01, 0xAB06}, {0xAB09, 0xAB0E},
|
||||
{0xAB11, 0xAB16}, {0xAB20, 0xAB26}, {0xAB28, 0xAB2E},
|
||||
{0xAB30, 0xAB6B}, {0xAB70, 0xABED}, {0xABF0, 0xABF9},
|
||||
{0xAC00, 0xD7A3}, {0xD7B0, 0xD7C6}, {0xD7CB, 0xD7FB},
|
||||
{0xF900, 0xFA6D}, {0xFA70, 0xFAD9}, {0xFB00, 0xFB06},
|
||||
{0xFB13, 0xFB17}, {0xFB1D, 0xFB36}, {0xFB38, 0xFB3C},
|
||||
{0xFB3E, 0xFB3E}, {0xFB40, 0xFB41}, {0xFB43, 0xFB44},
|
||||
{0xFB46, 0xFBC2}, {0xFBD3, 0xFD8F}, {0xFD92, 0xFDC7},
|
||||
{0xFDCF, 0xFDCF}, {0xFDF0, 0xFE19}, {0xFE20, 0xFE52},
|
||||
{0xFE54, 0xFE66}, {0xFE68, 0xFE6B}, {0xFE70, 0xFE74},
|
||||
{0xFE76, 0xFEFC}, {0xFF01, 0xFFBE}, {0xFFC2, 0xFFC7},
|
||||
{0xFFCA, 0xFFCF}, {0xFFD2, 0xFFD7}, {0xFFDA, 0xFFDC},
|
||||
{0xFFE0, 0xFFE6}, {0xFFE8, 0xFFEE}, {0xFFFC, 0xFFFD},
|
||||
{0x10000, 0x1000B}, {0x1000D, 0x10026}, {0x10028, 0x1003A},
|
||||
{0x1003C, 0x1003D}, {0x1003F, 0x1004D}, {0x10050, 0x1005D},
|
||||
{0x10080, 0x100FA}, {0x10100, 0x10102}, {0x10107, 0x10133},
|
||||
{0x10137, 0x1018E}, {0x10190, 0x1019C}, {0x101A0, 0x101A0},
|
||||
{0x101D0, 0x101FD}, {0x10280, 0x1029C}, {0x102A0, 0x102D0},
|
||||
{0x102E0, 0x102FB}, {0x10300, 0x10323}, {0x1032D, 0x1034A},
|
||||
{0x10350, 0x1037A}, {0x10380, 0x1039D}, {0x1039F, 0x103C3},
|
||||
{0x103C8, 0x103D5}, {0x10400, 0x1049D}, {0x104A0, 0x104A9},
|
||||
{0x104B0, 0x104D3}, {0x104D8, 0x104FB}, {0x10500, 0x10527},
|
||||
{0x10530, 0x10563}, {0x1056F, 0x1057A}, {0x1057C, 0x1058A},
|
||||
{0x1058C, 0x10592}, {0x10594, 0x10595}, {0x10597, 0x105A1},
|
||||
{0x105A3, 0x105B1}, {0x105B3, 0x105B9}, {0x105BB, 0x105BC},
|
||||
{0x10600, 0x10736}, {0x10740, 0x10755}, {0x10760, 0x10767},
|
||||
{0x10780, 0x10785}, {0x10787, 0x107B0}, {0x107B2, 0x107BA},
|
||||
{0x10800, 0x10805}, {0x10808, 0x10808}, {0x1080A, 0x10835},
|
||||
{0x10837, 0x10838}, {0x1083C, 0x1083C}, {0x1083F, 0x10855},
|
||||
{0x10857, 0x1089E}, {0x108A7, 0x108AF}, {0x108E0, 0x108F2},
|
||||
{0x108F4, 0x108F5}, {0x108FB, 0x1091B}, {0x1091F, 0x10939},
|
||||
{0x1093F, 0x1093F}, {0x10980, 0x109B7}, {0x109BC, 0x109CF},
|
||||
{0x109D2, 0x10A03}, {0x10A05, 0x10A06}, {0x10A0C, 0x10A13},
|
||||
{0x10A15, 0x10A17}, {0x10A19, 0x10A35}, {0x10A38, 0x10A3A},
|
||||
{0x10A3F, 0x10A48}, {0x10A50, 0x10A58}, {0x10A60, 0x10A9F},
|
||||
{0x10AC0, 0x10AE6}, {0x10AEB, 0x10AF6}, {0x10B00, 0x10B35},
|
||||
{0x10B39, 0x10B55}, {0x10B58, 0x10B72}, {0x10B78, 0x10B91},
|
||||
{0x10B99, 0x10B9C}, {0x10BA9, 0x10BAF}, {0x10C00, 0x10C48},
|
||||
{0x10C80, 0x10CB2}, {0x10CC0, 0x10CF2}, {0x10CFA, 0x10D27},
|
||||
{0x10D30, 0x10D39}, {0x10E60, 0x10E7E}, {0x10E80, 0x10EA9},
|
||||
{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, 0x11241}, {0x11280, 0x11286},
|
||||
{0x11288, 0x11288}, {0x1128A, 0x1128D}, {0x1128F, 0x1129D},
|
||||
{0x1129F, 0x112A9}, {0x112B0, 0x112EA}, {0x112F0, 0x112F9},
|
||||
{0x11300, 0x11303}, {0x11305, 0x1130C}, {0x1130F, 0x11310},
|
||||
{0x11313, 0x11328}, {0x1132A, 0x11330}, {0x11332, 0x11333},
|
||||
{0x11335, 0x11339}, {0x1133B, 0x11344}, {0x11347, 0x11348},
|
||||
{0x1134B, 0x1134D}, {0x11350, 0x11350}, {0x11357, 0x11357},
|
||||
{0x1135D, 0x11363}, {0x11366, 0x1136C}, {0x11370, 0x11374},
|
||||
{0x11400, 0x1145B}, {0x1145D, 0x11461}, {0x11480, 0x114C7},
|
||||
{0x114D0, 0x114D9}, {0x11580, 0x115B5}, {0x115B8, 0x115DD},
|
||||
{0x11600, 0x11644}, {0x11650, 0x11659}, {0x11660, 0x1166C},
|
||||
{0x11680, 0x116B9}, {0x116C0, 0x116C9}, {0x11700, 0x1171A},
|
||||
{0x1171D, 0x1172B}, {0x11730, 0x11746}, {0x11800, 0x1183B},
|
||||
{0x118A0, 0x118F2}, {0x118FF, 0x11906}, {0x11909, 0x11909},
|
||||
{0x1190C, 0x11913}, {0x11915, 0x11916}, {0x11918, 0x11935},
|
||||
{0x11937, 0x11938}, {0x1193B, 0x11946}, {0x11950, 0x11959},
|
||||
{0x119A0, 0x119A7}, {0x119AA, 0x119D7}, {0x119DA, 0x119E4},
|
||||
{0x11A00, 0x11A47}, {0x11A50, 0x11AA2}, {0x11AB0, 0x11AF8},
|
||||
{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}, {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},
|
||||
{0x1ED01, 0x1ED3D}, {0x1EE00, 0x1EE03}, {0x1EE05, 0x1EE1F},
|
||||
{0x1EE21, 0x1EE22}, {0x1EE24, 0x1EE24}, {0x1EE27, 0x1EE27},
|
||||
{0x1EE29, 0x1EE32}, {0x1EE34, 0x1EE37}, {0x1EE39, 0x1EE39},
|
||||
{0x1EE3B, 0x1EE3B}, {0x1EE42, 0x1EE42}, {0x1EE47, 0x1EE47},
|
||||
{0x1EE49, 0x1EE49}, {0x1EE4B, 0x1EE4B}, {0x1EE4D, 0x1EE4F},
|
||||
{0x1EE51, 0x1EE52}, {0x1EE54, 0x1EE54}, {0x1EE57, 0x1EE57},
|
||||
{0x1EE59, 0x1EE59}, {0x1EE5B, 0x1EE5B}, {0x1EE5D, 0x1EE5D},
|
||||
{0x1EE5F, 0x1EE5F}, {0x1EE61, 0x1EE62}, {0x1EE64, 0x1EE64},
|
||||
{0x1EE67, 0x1EE6A}, {0x1EE6C, 0x1EE72}, {0x1EE74, 0x1EE77},
|
||||
{0x1EE79, 0x1EE7C}, {0x1EE7E, 0x1EE7E}, {0x1EE80, 0x1EE89},
|
||||
{0x1EE8B, 0x1EE9B}, {0x1EEA1, 0x1EEA3}, {0x1EEA5, 0x1EEA9},
|
||||
{0x1EEAB, 0x1EEBB}, {0x1EEF0, 0x1EEF1}, {0x1F000, 0x1F02B},
|
||||
{0x1F030, 0x1F093}, {0x1F0A0, 0x1F0AE}, {0x1F0B1, 0x1F0BF},
|
||||
{0x1F0C1, 0x1F0CF}, {0x1F0D1, 0x1F0F5}, {0x1F100, 0x1F1AD},
|
||||
{0x1F1E6, 0x1F202}, {0x1F210, 0x1F23B}, {0x1F240, 0x1F248},
|
||||
{0x1F250, 0x1F251}, {0x1F260, 0x1F265}, {0x1F300, 0x1F6D7},
|
||||
{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, 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}};
|
||||
{0x2FF0, 0x303F}, {0x3041, 0x3096}, {0x3099, 0x30FF},
|
||||
{0x3105, 0x312F}, {0x3131, 0x318E}, {0x3190, 0x31E3},
|
||||
{0x31EF, 0x321E}, {0x3220, 0xA48C}, {0xA490, 0xA4C6},
|
||||
{0xA4D0, 0xA62B}, {0xA640, 0xA6F7}, {0xA700, 0xA7CA},
|
||||
{0xA7D0, 0xA7D1}, {0xA7D3, 0xA7D3}, {0xA7D5, 0xA7D9},
|
||||
{0xA7F2, 0xA82C}, {0xA830, 0xA839}, {0xA840, 0xA877},
|
||||
{0xA880, 0xA8C5}, {0xA8CE, 0xA8D9}, {0xA8E0, 0xA953},
|
||||
{0xA95F, 0xA97C}, {0xA980, 0xA9CD}, {0xA9CF, 0xA9D9},
|
||||
{0xA9DE, 0xA9FE}, {0xAA00, 0xAA36}, {0xAA40, 0xAA4D},
|
||||
{0xAA50, 0xAA59}, {0xAA5C, 0xAAC2}, {0xAADB, 0xAAF6},
|
||||
{0xAB01, 0xAB06}, {0xAB09, 0xAB0E}, {0xAB11, 0xAB16},
|
||||
{0xAB20, 0xAB26}, {0xAB28, 0xAB2E}, {0xAB30, 0xAB6B},
|
||||
{0xAB70, 0xABED}, {0xABF0, 0xABF9}, {0xAC00, 0xD7A3},
|
||||
{0xD7B0, 0xD7C6}, {0xD7CB, 0xD7FB}, {0xF900, 0xFA6D},
|
||||
{0xFA70, 0xFAD9}, {0xFB00, 0xFB06}, {0xFB13, 0xFB17},
|
||||
{0xFB1D, 0xFB36}, {0xFB38, 0xFB3C}, {0xFB3E, 0xFB3E},
|
||||
{0xFB40, 0xFB41}, {0xFB43, 0xFB44}, {0xFB46, 0xFBC2},
|
||||
{0xFBD3, 0xFD8F}, {0xFD92, 0xFDC7}, {0xFDCF, 0xFDCF},
|
||||
{0xFDF0, 0xFE19}, {0xFE20, 0xFE52}, {0xFE54, 0xFE66},
|
||||
{0xFE68, 0xFE6B}, {0xFE70, 0xFE74}, {0xFE76, 0xFEFC},
|
||||
{0xFF01, 0xFFBE}, {0xFFC2, 0xFFC7}, {0xFFCA, 0xFFCF},
|
||||
{0xFFD2, 0xFFD7}, {0xFFDA, 0xFFDC}, {0xFFE0, 0xFFE6},
|
||||
{0xFFE8, 0xFFEE}, {0xFFFC, 0xFFFD}, {0x10000, 0x1000B},
|
||||
{0x1000D, 0x10026}, {0x10028, 0x1003A}, {0x1003C, 0x1003D},
|
||||
{0x1003F, 0x1004D}, {0x10050, 0x1005D}, {0x10080, 0x100FA},
|
||||
{0x10100, 0x10102}, {0x10107, 0x10133}, {0x10137, 0x1018E},
|
||||
{0x10190, 0x1019C}, {0x101A0, 0x101A0}, {0x101D0, 0x101FD},
|
||||
{0x10280, 0x1029C}, {0x102A0, 0x102D0}, {0x102E0, 0x102FB},
|
||||
{0x10300, 0x10323}, {0x1032D, 0x1034A}, {0x10350, 0x1037A},
|
||||
{0x10380, 0x1039D}, {0x1039F, 0x103C3}, {0x103C8, 0x103D5},
|
||||
{0x10400, 0x1049D}, {0x104A0, 0x104A9}, {0x104B0, 0x104D3},
|
||||
{0x104D8, 0x104FB}, {0x10500, 0x10527}, {0x10530, 0x10563},
|
||||
{0x1056F, 0x1057A}, {0x1057C, 0x1058A}, {0x1058C, 0x10592},
|
||||
{0x10594, 0x10595}, {0x10597, 0x105A1}, {0x105A3, 0x105B1},
|
||||
{0x105B3, 0x105B9}, {0x105BB, 0x105BC}, {0x10600, 0x10736},
|
||||
{0x10740, 0x10755}, {0x10760, 0x10767}, {0x10780, 0x10785},
|
||||
{0x10787, 0x107B0}, {0x107B2, 0x107BA}, {0x10800, 0x10805},
|
||||
{0x10808, 0x10808}, {0x1080A, 0x10835}, {0x10837, 0x10838},
|
||||
{0x1083C, 0x1083C}, {0x1083F, 0x10855}, {0x10857, 0x1089E},
|
||||
{0x108A7, 0x108AF}, {0x108E0, 0x108F2}, {0x108F4, 0x108F5},
|
||||
{0x108FB, 0x1091B}, {0x1091F, 0x10939}, {0x1093F, 0x1093F},
|
||||
{0x10980, 0x109B7}, {0x109BC, 0x109CF}, {0x109D2, 0x10A03},
|
||||
{0x10A05, 0x10A06}, {0x10A0C, 0x10A13}, {0x10A15, 0x10A17},
|
||||
{0x10A19, 0x10A35}, {0x10A38, 0x10A3A}, {0x10A3F, 0x10A48},
|
||||
{0x10A50, 0x10A58}, {0x10A60, 0x10A9F}, {0x10AC0, 0x10AE6},
|
||||
{0x10AEB, 0x10AF6}, {0x10B00, 0x10B35}, {0x10B39, 0x10B55},
|
||||
{0x10B58, 0x10B72}, {0x10B78, 0x10B91}, {0x10B99, 0x10B9C},
|
||||
{0x10BA9, 0x10BAF}, {0x10C00, 0x10C48}, {0x10C80, 0x10CB2},
|
||||
{0x10CC0, 0x10CF2}, {0x10CFA, 0x10D27}, {0x10D30, 0x10D39},
|
||||
{0x10E60, 0x10E7E}, {0x10E80, 0x10EA9}, {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, 0x11241}, {0x11280, 0x11286}, {0x11288, 0x11288},
|
||||
{0x1128A, 0x1128D}, {0x1128F, 0x1129D}, {0x1129F, 0x112A9},
|
||||
{0x112B0, 0x112EA}, {0x112F0, 0x112F9}, {0x11300, 0x11303},
|
||||
{0x11305, 0x1130C}, {0x1130F, 0x11310}, {0x11313, 0x11328},
|
||||
{0x1132A, 0x11330}, {0x11332, 0x11333}, {0x11335, 0x11339},
|
||||
{0x1133B, 0x11344}, {0x11347, 0x11348}, {0x1134B, 0x1134D},
|
||||
{0x11350, 0x11350}, {0x11357, 0x11357}, {0x1135D, 0x11363},
|
||||
{0x11366, 0x1136C}, {0x11370, 0x11374}, {0x11400, 0x1145B},
|
||||
{0x1145D, 0x11461}, {0x11480, 0x114C7}, {0x114D0, 0x114D9},
|
||||
{0x11580, 0x115B5}, {0x115B8, 0x115DD}, {0x11600, 0x11644},
|
||||
{0x11650, 0x11659}, {0x11660, 0x1166C}, {0x11680, 0x116B9},
|
||||
{0x116C0, 0x116C9}, {0x11700, 0x1171A}, {0x1171D, 0x1172B},
|
||||
{0x11730, 0x11746}, {0x11800, 0x1183B}, {0x118A0, 0x118F2},
|
||||
{0x118FF, 0x11906}, {0x11909, 0x11909}, {0x1190C, 0x11913},
|
||||
{0x11915, 0x11916}, {0x11918, 0x11935}, {0x11937, 0x11938},
|
||||
{0x1193B, 0x11946}, {0x11950, 0x11959}, {0x119A0, 0x119A7},
|
||||
{0x119AA, 0x119D7}, {0x119DA, 0x119E4}, {0x11A00, 0x11A47},
|
||||
{0x11A50, 0x11AA2}, {0x11AB0, 0x11AF8}, {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},
|
||||
{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}, {0x1ED01, 0x1ED3D},
|
||||
{0x1EE00, 0x1EE03}, {0x1EE05, 0x1EE1F}, {0x1EE21, 0x1EE22},
|
||||
{0x1EE24, 0x1EE24}, {0x1EE27, 0x1EE27}, {0x1EE29, 0x1EE32},
|
||||
{0x1EE34, 0x1EE37}, {0x1EE39, 0x1EE39}, {0x1EE3B, 0x1EE3B},
|
||||
{0x1EE42, 0x1EE42}, {0x1EE47, 0x1EE47}, {0x1EE49, 0x1EE49},
|
||||
{0x1EE4B, 0x1EE4B}, {0x1EE4D, 0x1EE4F}, {0x1EE51, 0x1EE52},
|
||||
{0x1EE54, 0x1EE54}, {0x1EE57, 0x1EE57}, {0x1EE59, 0x1EE59},
|
||||
{0x1EE5B, 0x1EE5B}, {0x1EE5D, 0x1EE5D}, {0x1EE5F, 0x1EE5F},
|
||||
{0x1EE61, 0x1EE62}, {0x1EE64, 0x1EE64}, {0x1EE67, 0x1EE6A},
|
||||
{0x1EE6C, 0x1EE72}, {0x1EE74, 0x1EE77}, {0x1EE79, 0x1EE7C},
|
||||
{0x1EE7E, 0x1EE7E}, {0x1EE80, 0x1EE89}, {0x1EE8B, 0x1EE9B},
|
||||
{0x1EEA1, 0x1EEA3}, {0x1EEA5, 0x1EEA9}, {0x1EEAB, 0x1EEBB},
|
||||
{0x1EEF0, 0x1EEF1}, {0x1F000, 0x1F02B}, {0x1F030, 0x1F093},
|
||||
{0x1F0A0, 0x1F0AE}, {0x1F0B1, 0x1F0BF}, {0x1F0C1, 0x1F0CF},
|
||||
{0x1F0D1, 0x1F0F5}, {0x1F100, 0x1F1AD}, {0x1F1E6, 0x1F202},
|
||||
{0x1F210, 0x1F23B}, {0x1F240, 0x1F248}, {0x1F250, 0x1F251},
|
||||
{0x1F260, 0x1F265}, {0x1F300, 0x1F6D7}, {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, 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}, {0x2EBF0, 0x2EE5D}, {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
|
||||
@ -275,14 +276,14 @@ bool isPrintable(int UCS) {
|
||||
/// formatting characters.
|
||||
bool isFormatting(int UCS) {
|
||||
|
||||
// https://unicode.org/Public/15.0.0/ucdxml/
|
||||
// https://unicode.org/Public/15.1.0/ucdxml/
|
||||
static const UnicodeCharRange Cf[] = {
|
||||
{0x00AD, 0x00AD}, {0x0600, 0x0605}, {0x061C, 0x061C},
|
||||
{0x06DD, 0x06DD}, {0x070F, 0x070F}, {0x0890, 0x0891},
|
||||
{0x08E2, 0x08E2}, {0x180E, 0x180E}, {0x200B, 0x200F},
|
||||
{0x202A, 0x202E}, {0x2060, 0x2064}, {0x2066, 0x206F},
|
||||
{0xFEFF, 0xFEFF}, {0xFFF9, 0xFFFB}, {0x110BD, 0x110BD},
|
||||
{0x110CD, 0x110CD}, {0x13430, 0x13438}, {0x1BCA0, 0x1BCA3},
|
||||
{0x110CD, 0x110CD}, {0x13430, 0x1343F}, {0x1BCA0, 0x1BCA3},
|
||||
{0x1D173, 0x1D17A}, {0xE0001, 0xE0001}, {0xE0020, 0xE007F}};
|
||||
|
||||
static const UnicodeCharSet Format(Cf);
|
||||
@ -446,29 +447,28 @@ static inline int charWidth(int UCS) {
|
||||
{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}
|
||||
};
|
||||
{0x2E9B, 0x2EF3}, {0x2F00, 0x2FD5}, {0x2FF0, 0x303E},
|
||||
{0x3041, 0x3096}, {0x3099, 0x30FF}, {0x3105, 0x312F},
|
||||
{0x3131, 0x318E}, {0x3190, 0x31E3}, {0x31EF, 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);
|
||||
|
||||
if (DoubleWidthCharacters.contains(UCS))
|
||||
|
@ -2,11 +2,11 @@
|
||||
//
|
||||
// This file was generated by utils/unicode-case-fold.py from the Unicode
|
||||
// case folding database at
|
||||
// http://www.unicode.org/Public/15.0.0/ucd/CaseFolding.txt
|
||||
// http://www.unicode.org/Public/15.1.0/ucd/CaseFolding.txt
|
||||
//
|
||||
// To regenerate this file, run:
|
||||
// utils/unicode-case-fold.py \
|
||||
// "http://www.unicode.org/Public/15.0.0/ucd/CaseFolding.txt" \
|
||||
// "http://www.unicode.org/Public/15.1.0/ucd/CaseFolding.txt" \
|
||||
// > lib/Support/UnicodeCaseFold.cpp
|
||||
//
|
||||
//===----------------------------------------------------------------------===//
|
||||
@ -511,6 +511,9 @@ int llvm::sys::unicode::foldCharSimple(int C) {
|
||||
// GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI
|
||||
if (C == 0x1fcc)
|
||||
return 0x1fc3;
|
||||
// GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
|
||||
if (C == 0x1fd3)
|
||||
return 0x0390;
|
||||
if (C < 0x1fd8)
|
||||
return C;
|
||||
// 2 characters
|
||||
@ -521,6 +524,9 @@ int llvm::sys::unicode::foldCharSimple(int C) {
|
||||
// 2 characters
|
||||
if (C <= 0x1fdb)
|
||||
return C + -100;
|
||||
// GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
|
||||
if (C == 0x1fe3)
|
||||
return 0x03b0;
|
||||
if (C < 0x1fe8)
|
||||
return C;
|
||||
// 2 characters
|
||||
@ -741,6 +747,9 @@ int llvm::sys::unicode::foldCharSimple(int C) {
|
||||
// 80 characters
|
||||
if (C <= 0xabbf)
|
||||
return C + -38864;
|
||||
// LATIN SMALL LIGATURE LONG S T
|
||||
if (C == 0xfb05)
|
||||
return 0xfb06;
|
||||
if (C < 0xff21)
|
||||
return C;
|
||||
// 26 characters
|
||||
|
@ -320,7 +320,7 @@ struct GeneratedNamesData {
|
||||
uint32_t End;
|
||||
};
|
||||
|
||||
// Unicode 15.0 Table 4-8. Name Derivation Rule Prefix Strings
|
||||
// Unicode 15.1 Table 4-8. Name Derivation Rule Prefix Strings
|
||||
static const GeneratedNamesData GeneratedNamesDataTable[] = {
|
||||
{"CJK UNIFIED IDEOGRAPH-", 0x3400, 0x4DBF},
|
||||
{"CJK UNIFIED IDEOGRAPH-", 0x4E00, 0x9FFF},
|
||||
@ -329,6 +329,7 @@ static const GeneratedNamesData GeneratedNamesDataTable[] = {
|
||||
{"CJK UNIFIED IDEOGRAPH-", 0x2B740, 0x2B81D},
|
||||
{"CJK UNIFIED IDEOGRAPH-", 0x2B820, 0x2CEA1},
|
||||
{"CJK UNIFIED IDEOGRAPH-", 0x2CEB0, 0x2EBE0},
|
||||
{"CJK UNIFIED IDEOGRAPH-", 0x2EBF0, 0x2EE5D},
|
||||
{"CJK UNIFIED IDEOGRAPH-", 0x30000, 0x3134A},
|
||||
{"CJK UNIFIED IDEOGRAPH-", 0x31350, 0x323AF},
|
||||
{"TANGUT IDEOGRAPH-", 0x17000, 0x187F7},
|
||||
|
File diff suppressed because it is too large
Load Diff
@ -145,6 +145,7 @@ TEST(Unicode, nameToCodepointStrict) {
|
||||
EXPECT_EQ(0x2F800u, map("CJK COMPATIBILITY IDEOGRAPH-2F800"));
|
||||
EXPECT_EQ(0x2FA1Du, map("CJK COMPATIBILITY IDEOGRAPH-2FA1D"));
|
||||
EXPECT_EQ(0x31350u, map("CJK UNIFIED IDEOGRAPH-31350")); // Unicode 15.0
|
||||
EXPECT_EQ(0x2EBF0u, map("CJK UNIFIED IDEOGRAPH-2EBF0")); // Unicode 15.1
|
||||
|
||||
EXPECT_EQ(0xAC00u, map("HANGUL SYLLABLE GA"));
|
||||
EXPECT_EQ(0xAC14u, map("HANGUL SYLLABLE GASS"));
|
||||
@ -168,6 +169,8 @@ TEST(Unicode, nameToCodepointStrict) {
|
||||
"ABOVE WITH ALEF MAKSURA ISOLATED FORM"));
|
||||
EXPECT_EQ(0x11F04u, map("KAWI LETTER A")); // Unicode 15.0
|
||||
EXPECT_EQ(0x1FA77u, map("PINK HEART")); // Unicode 15.0
|
||||
EXPECT_EQ(0x2FFFu,
|
||||
map("IDEOGRAPHIC DESCRIPTION CHARACTER ROTATION")); // Unicode 15.1
|
||||
|
||||
// Aliases
|
||||
EXPECT_EQ(0x0000u, map("NULL"));
|
||||
|
@ -8,7 +8,7 @@
|
||||
//
|
||||
// This file is used to generate lib/Support/UnicodeNameToCodepointGenerated.cpp
|
||||
// using UnicodeData.txt and NameAliases.txt available at
|
||||
// https://unicode.org/Public/15.0.0/ucd/
|
||||
// https://unicode.org/Public/15.1.0/ucd/
|
||||
//===----------------------------------------------------------------------===//
|
||||
|
||||
#include "llvm/ADT/STLExtras.h"
|
||||
@ -355,9 +355,9 @@ int main(int argc, char **argv) {
|
||||
"Usage: %s UnicodeData.txt NameAliases.txt output\n\n",
|
||||
argv[0]);
|
||||
printf("NameAliases.txt can be found at "
|
||||
"https://unicode.org/Public/15.0.0/ucd/NameAliases.txt\n"
|
||||
"https://unicode.org/Public/15.1.0/ucd/NameAliases.txt\n"
|
||||
"UnicodeData.txt can be found at "
|
||||
"https://unicode.org/Public/15.0.0/ucd/UnicodeData.txt\n\n");
|
||||
"https://unicode.org/Public/15.1.0/ucd/UnicodeData.txt\n\n");
|
||||
|
||||
if (argc != 4)
|
||||
return EXIT_FAILURE;
|
||||
|
Loading…
x
Reference in New Issue
Block a user