Divec has uploaded a new change for review. https://gerrit.wikimedia.org/r/185103
Change subject: WIP: Word character detection ...................................................................... WIP: Word character detection unicodejs-properties.py: * Extract alphabetic ranges from DerivedCoreProperties.txt database unicodejs.alphabetic.js: * Resulting extraction Change-Id: I1b785a369a2c80f6afc27f792787f6590948241e --- A src/unicodejs.alphabetic.js M tools/unicodejs-properties.py 2 files changed, 938 insertions(+), 0 deletions(-) git pull ssh://gerrit.wikimedia.org:29418/unicodejs refs/changes/03/185103/1 diff --git a/src/unicodejs.alphabetic.js b/src/unicodejs.alphabetic.js new file mode 100644 index 0000000..368e734 --- /dev/null +++ b/src/unicodejs.alphabetic.js @@ -0,0 +1,912 @@ +// This file is GENERATED by tools/unicodejs-properties.py +// DO NOT EDIT +unicodeJS.alphabetic = [ + [0x0041, 0x005A], + [0x0061, 0x007A], + 0x00AA, + 0x00B5, + 0x00BA, + [0x00C0, 0x00D6], + [0x00D8, 0x00F6], + [0x00F8, 0x01BA], + 0x01BB, + [0x01BC, 0x01BF], + [0x01C0, 0x01C3], + [0x01C4, 0x0293], + 0x0294, + [0x0295, 0x02AF], + [0x02B0, 0x02C1], + [0x02C6, 0x02D1], + [0x02E0, 0x02E4], + 0x02EC, + 0x02EE, + 0x0345, + [0x0370, 0x0373], + 0x0374, + [0x0376, 0x0377], + 0x037A, + [0x037B, 0x037D], + 0x037F, + 0x0386, + [0x0388, 0x038A], + 0x038C, + [0x038E, 0x03A1], + [0x03A3, 0x03F5], + [0x03F7, 0x0481], + [0x048A, 0x052F], + [0x0531, 0x0556], + 0x0559, + [0x0561, 0x0587], + [0x05B0, 0x05BD], + 0x05BF, + [0x05C1, 0x05C2], + [0x05C4, 0x05C5], + 0x05C7, + [0x05D0, 0x05EA], + [0x05F0, 0x05F2], + [0x0610, 0x061A], + [0x0620, 0x063F], + 0x0640, + [0x0641, 0x064A], + [0x064B, 0x0657], + [0x0659, 0x065F], + [0x066E, 0x066F], + 0x0670, + [0x0671, 0x06D3], + 0x06D5, + [0x06D6, 0x06DC], + [0x06E1, 0x06E4], + [0x06E5, 0x06E6], + [0x06E7, 0x06E8], + 0x06ED, + [0x06EE, 0x06EF], + [0x06FA, 0x06FC], + 0x06FF, + 0x0710, + 0x0711, + [0x0712, 0x072F], + [0x0730, 0x073F], + [0x074D, 0x07A5], + [0x07A6, 0x07B0], + 0x07B1, + [0x07CA, 0x07EA], + [0x07F4, 0x07F5], + 0x07FA, + [0x0800, 0x0815], + [0x0816, 0x0817], + 0x081A, + [0x081B, 0x0823], + 0x0824, + [0x0825, 0x0827], + 0x0828, + [0x0829, 0x082C], + [0x0840, 0x0858], + [0x08A0, 0x08B2], + [0x08E4, 0x08E9], + [0x08F0, 0x0902], + 0x0903, + [0x0904, 0x0939], + 0x093A, + 0x093B, + 0x093D, + [0x093E, 0x0940], + [0x0941, 0x0948], + [0x0949, 0x094C], + [0x094E, 0x094F], + 0x0950, + [0x0955, 0x0957], + [0x0958, 0x0961], + [0x0962, 0x0963], + 0x0971, + [0x0972, 0x0980], + 0x0981, + [0x0982, 0x0983], + [0x0985, 0x098C], + [0x098F, 0x0990], + [0x0993, 0x09A8], + [0x09AA, 0x09B0], + 0x09B2, + [0x09B6, 0x09B9], + 0x09BD, + [0x09BE, 0x09C0], + [0x09C1, 0x09C4], + [0x09C7, 0x09C8], + [0x09CB, 0x09CC], + 0x09CE, + 0x09D7, + [0x09DC, 0x09DD], + [0x09DF, 0x09E1], + [0x09E2, 0x09E3], + [0x09F0, 0x09F1], + [0x0A01, 0x0A02], + 0x0A03, + [0x0A05, 0x0A0A], + [0x0A0F, 0x0A10], + [0x0A13, 0x0A28], + [0x0A2A, 0x0A30], + [0x0A32, 0x0A33], + [0x0A35, 0x0A36], + [0x0A38, 0x0A39], + [0x0A3E, 0x0A40], + [0x0A41, 0x0A42], + [0x0A47, 0x0A48], + [0x0A4B, 0x0A4C], + 0x0A51, + [0x0A59, 0x0A5C], + 0x0A5E, + [0x0A70, 0x0A71], + [0x0A72, 0x0A74], + 0x0A75, + [0x0A81, 0x0A82], + 0x0A83, + [0x0A85, 0x0A8D], + [0x0A8F, 0x0A91], + [0x0A93, 0x0AA8], + [0x0AAA, 0x0AB0], + [0x0AB2, 0x0AB3], + [0x0AB5, 0x0AB9], + 0x0ABD, + [0x0ABE, 0x0AC0], + [0x0AC1, 0x0AC5], + [0x0AC7, 0x0AC8], + 0x0AC9, + [0x0ACB, 0x0ACC], + 0x0AD0, + [0x0AE0, 0x0AE1], + [0x0AE2, 0x0AE3], + 0x0B01, + [0x0B02, 0x0B03], + [0x0B05, 0x0B0C], + [0x0B0F, 0x0B10], + [0x0B13, 0x0B28], + [0x0B2A, 0x0B30], + [0x0B32, 0x0B33], + [0x0B35, 0x0B39], + 0x0B3D, + 0x0B3E, + 0x0B3F, + 0x0B40, + [0x0B41, 0x0B44], + [0x0B47, 0x0B48], + [0x0B4B, 0x0B4C], + 0x0B56, + 0x0B57, + [0x0B5C, 0x0B5D], + [0x0B5F, 0x0B61], + [0x0B62, 0x0B63], + 0x0B71, + 0x0B82, + 0x0B83, + [0x0B85, 0x0B8A], + [0x0B8E, 0x0B90], + [0x0B92, 0x0B95], + [0x0B99, 0x0B9A], + 0x0B9C, + [0x0B9E, 0x0B9F], + [0x0BA3, 0x0BA4], + [0x0BA8, 0x0BAA], + [0x0BAE, 0x0BB9], + [0x0BBE, 0x0BBF], + 0x0BC0, + [0x0BC1, 0x0BC2], + [0x0BC6, 0x0BC8], + [0x0BCA, 0x0BCC], + 0x0BD0, + 0x0BD7, + 0x0C00, + [0x0C01, 0x0C03], + [0x0C05, 0x0C0C], + [0x0C0E, 0x0C10], + [0x0C12, 0x0C28], + [0x0C2A, 0x0C39], + 0x0C3D, + [0x0C3E, 0x0C40], + [0x0C41, 0x0C44], + [0x0C46, 0x0C48], + [0x0C4A, 0x0C4C], + [0x0C55, 0x0C56], + [0x0C58, 0x0C59], + [0x0C60, 0x0C61], + [0x0C62, 0x0C63], + 0x0C81, + [0x0C82, 0x0C83], + [0x0C85, 0x0C8C], + [0x0C8E, 0x0C90], + [0x0C92, 0x0CA8], + [0x0CAA, 0x0CB3], + [0x0CB5, 0x0CB9], + 0x0CBD, + 0x0CBE, + 0x0CBF, + [0x0CC0, 0x0CC4], + 0x0CC6, + [0x0CC7, 0x0CC8], + [0x0CCA, 0x0CCB], + 0x0CCC, + [0x0CD5, 0x0CD6], + 0x0CDE, + [0x0CE0, 0x0CE1], + [0x0CE2, 0x0CE3], + [0x0CF1, 0x0CF2], + 0x0D01, + [0x0D02, 0x0D03], + [0x0D05, 0x0D0C], + [0x0D0E, 0x0D10], + [0x0D12, 0x0D3A], + 0x0D3D, + [0x0D3E, 0x0D40], + [0x0D41, 0x0D44], + [0x0D46, 0x0D48], + [0x0D4A, 0x0D4C], + 0x0D4E, + 0x0D57, + [0x0D60, 0x0D61], + [0x0D62, 0x0D63], + [0x0D7A, 0x0D7F], + [0x0D82, 0x0D83], + [0x0D85, 0x0D96], + [0x0D9A, 0x0DB1], + [0x0DB3, 0x0DBB], + 0x0DBD, + [0x0DC0, 0x0DC6], + [0x0DCF, 0x0DD1], + [0x0DD2, 0x0DD4], + 0x0DD6, + [0x0DD8, 0x0DDF], + [0x0DF2, 0x0DF3], + [0x0E01, 0x0E30], + 0x0E31, + [0x0E32, 0x0E33], + [0x0E34, 0x0E3A], + [0x0E40, 0x0E45], + 0x0E46, + 0x0E4D, + [0x0E81, 0x0E82], + 0x0E84, + [0x0E87, 0x0E88], + 0x0E8A, + 0x0E8D, + [0x0E94, 0x0E97], + [0x0E99, 0x0E9F], + [0x0EA1, 0x0EA3], + 0x0EA5, + 0x0EA7, + [0x0EAA, 0x0EAB], + [0x0EAD, 0x0EB0], + 0x0EB1, + [0x0EB2, 0x0EB3], + [0x0EB4, 0x0EB9], + [0x0EBB, 0x0EBC], + 0x0EBD, + [0x0EC0, 0x0EC4], + 0x0EC6, + 0x0ECD, + [0x0EDC, 0x0EDF], + 0x0F00, + [0x0F40, 0x0F47], + [0x0F49, 0x0F6C], + [0x0F71, 0x0F7E], + 0x0F7F, + [0x0F80, 0x0F81], + [0x0F88, 0x0F8C], + [0x0F8D, 0x0F97], + [0x0F99, 0x0FBC], + [0x1000, 0x102A], + [0x102B, 0x102C], + [0x102D, 0x1030], + 0x1031, + [0x1032, 0x1036], + 0x1038, + [0x103B, 0x103C], + [0x103D, 0x103E], + 0x103F, + [0x1050, 0x1055], + [0x1056, 0x1057], + [0x1058, 0x1059], + [0x105A, 0x105D], + [0x105E, 0x1060], + 0x1061, + 0x1062, + [0x1065, 0x1066], + [0x1067, 0x1068], + [0x106E, 0x1070], + [0x1071, 0x1074], + [0x1075, 0x1081], + 0x1082, + [0x1083, 0x1084], + [0x1085, 0x1086], + 0x108E, + 0x109C, + 0x109D, + [0x10A0, 0x10C5], + 0x10C7, + 0x10CD, + [0x10D0, 0x10FA], + 0x10FC, + [0x10FD, 0x1248], + [0x124A, 0x124D], + [0x1250, 0x1256], + 0x1258, + [0x125A, 0x125D], + [0x1260, 0x1288], + [0x128A, 0x128D], + [0x1290, 0x12B0], + [0x12B2, 0x12B5], + [0x12B8, 0x12BE], + 0x12C0, + [0x12C2, 0x12C5], + [0x12C8, 0x12D6], + [0x12D8, 0x1310], + [0x1312, 0x1315], + [0x1318, 0x135A], + 0x135F, + [0x1380, 0x138F], + [0x13A0, 0x13F4], + [0x1401, 0x166C], + [0x166F, 0x167F], + [0x1681, 0x169A], + [0x16A0, 0x16EA], + [0x16EE, 0x16F0], + [0x16F1, 0x16F8], + [0x1700, 0x170C], + [0x170E, 0x1711], + [0x1712, 0x1713], + [0x1720, 0x1731], + [0x1732, 0x1733], + [0x1740, 0x1751], + [0x1752, 0x1753], + [0x1760, 0x176C], + [0x176E, 0x1770], + [0x1772, 0x1773], + [0x1780, 0x17B3], + 0x17B6, + [0x17B7, 0x17BD], + [0x17BE, 0x17C5], + 0x17C6, + [0x17C7, 0x17C8], + 0x17D7, + 0x17DC, + [0x1820, 0x1842], + 0x1843, + [0x1844, 0x1877], + [0x1880, 0x18A8], + 0x18A9, + 0x18AA, + [0x18B0, 0x18F5], + [0x1900, 0x191E], + [0x1920, 0x1922], + [0x1923, 0x1926], + [0x1927, 0x1928], + [0x1929, 0x192B], + [0x1930, 0x1931], + 0x1932, + [0x1933, 0x1938], + [0x1950, 0x196D], + [0x1970, 0x1974], + [0x1980, 0x19AB], + [0x19B0, 0x19C0], + [0x19C1, 0x19C7], + [0x19C8, 0x19C9], + [0x1A00, 0x1A16], + [0x1A17, 0x1A18], + [0x1A19, 0x1A1A], + 0x1A1B, + [0x1A20, 0x1A54], + 0x1A55, + 0x1A56, + 0x1A57, + [0x1A58, 0x1A5E], + 0x1A61, + 0x1A62, + [0x1A63, 0x1A64], + [0x1A65, 0x1A6C], + [0x1A6D, 0x1A72], + [0x1A73, 0x1A74], + 0x1AA7, + [0x1B00, 0x1B03], + 0x1B04, + [0x1B05, 0x1B33], + 0x1B35, + [0x1B36, 0x1B3A], + 0x1B3B, + 0x1B3C, + [0x1B3D, 0x1B41], + 0x1B42, + 0x1B43, + [0x1B45, 0x1B4B], + [0x1B80, 0x1B81], + 0x1B82, + [0x1B83, 0x1BA0], + 0x1BA1, + [0x1BA2, 0x1BA5], + [0x1BA6, 0x1BA7], + [0x1BA8, 0x1BA9], + [0x1BAC, 0x1BAD], + [0x1BAE, 0x1BAF], + [0x1BBA, 0x1BE5], + 0x1BE7, + [0x1BE8, 0x1BE9], + [0x1BEA, 0x1BEC], + 0x1BED, + 0x1BEE, + [0x1BEF, 0x1BF1], + [0x1C00, 0x1C23], + [0x1C24, 0x1C2B], + [0x1C2C, 0x1C33], + [0x1C34, 0x1C35], + [0x1C4D, 0x1C4F], + [0x1C5A, 0x1C77], + [0x1C78, 0x1C7D], + [0x1CE9, 0x1CEC], + [0x1CEE, 0x1CF1], + [0x1CF2, 0x1CF3], + [0x1CF5, 0x1CF6], + [0x1D00, 0x1D2B], + [0x1D2C, 0x1D6A], + [0x1D6B, 0x1D77], + 0x1D78, + [0x1D79, 0x1D9A], + [0x1D9B, 0x1DBF], + [0x1DE7, 0x1DF4], + [0x1E00, 0x1F15], + [0x1F18, 0x1F1D], + [0x1F20, 0x1F45], + [0x1F48, 0x1F4D], + [0x1F50, 0x1F57], + 0x1F59, + 0x1F5B, + 0x1F5D, + [0x1F5F, 0x1F7D], + [0x1F80, 0x1FB4], + [0x1FB6, 0x1FBC], + 0x1FBE, + [0x1FC2, 0x1FC4], + [0x1FC6, 0x1FCC], + [0x1FD0, 0x1FD3], + [0x1FD6, 0x1FDB], + [0x1FE0, 0x1FEC], + [0x1FF2, 0x1FF4], + [0x1FF6, 0x1FFC], + 0x2071, + 0x207F, + [0x2090, 0x209C], + 0x2102, + 0x2107, + [0x210A, 0x2113], + 0x2115, + [0x2119, 0x211D], + 0x2124, + 0x2126, + 0x2128, + [0x212A, 0x212D], + [0x212F, 0x2134], + [0x2135, 0x2138], + 0x2139, + [0x213C, 0x213F], + [0x2145, 0x2149], + 0x214E, + [0x2160, 0x2182], + [0x2183, 0x2184], + [0x2185, 0x2188], + [0x24B6, 0x24E9], + [0x2C00, 0x2C2E], + [0x2C30, 0x2C5E], + [0x2C60, 0x2C7B], + [0x2C7C, 0x2C7D], + [0x2C7E, 0x2CE4], + [0x2CEB, 0x2CEE], + [0x2CF2, 0x2CF3], + [0x2D00, 0x2D25], + 0x2D27, + 0x2D2D, + [0x2D30, 0x2D67], + 0x2D6F, + [0x2D80, 0x2D96], + [0x2DA0, 0x2DA6], + [0x2DA8, 0x2DAE], + [0x2DB0, 0x2DB6], + [0x2DB8, 0x2DBE], + [0x2DC0, 0x2DC6], + [0x2DC8, 0x2DCE], + [0x2DD0, 0x2DD6], + [0x2DD8, 0x2DDE], + [0x2DE0, 0x2DFF], + 0x2E2F, + 0x3005, + 0x3006, + 0x3007, + [0x3021, 0x3029], + [0x3031, 0x3035], + [0x3038, 0x303A], + 0x303B, + 0x303C, + [0x3041, 0x3096], + [0x309D, 0x309E], + 0x309F, + [0x30A1, 0x30FA], + [0x30FC, 0x30FE], + 0x30FF, + [0x3105, 0x312D], + [0x3131, 0x318E], + [0x31A0, 0x31BA], + [0x31F0, 0x31FF], + [0x3400, 0x4DB5], + [0x4E00, 0x9FCC], + [0xA000, 0xA014], + 0xA015, + [0xA016, 0xA48C], + [0xA4D0, 0xA4F7], + [0xA4F8, 0xA4FD], + [0xA500, 0xA60B], + 0xA60C, + [0xA610, 0xA61F], + [0xA62A, 0xA62B], + [0xA640, 0xA66D], + 0xA66E, + [0xA674, 0xA67B], + 0xA67F, + [0xA680, 0xA69B], + [0xA69C, 0xA69D], + 0xA69F, + [0xA6A0, 0xA6E5], + [0xA6E6, 0xA6EF], + [0xA717, 0xA71F], + [0xA722, 0xA76F], + 0xA770, + [0xA771, 0xA787], + 0xA788, + [0xA78B, 0xA78E], + [0xA790, 0xA7AD], + [0xA7B0, 0xA7B1], + 0xA7F7, + [0xA7F8, 0xA7F9], + 0xA7FA, + [0xA7FB, 0xA801], + [0xA803, 0xA805], + [0xA807, 0xA80A], + [0xA80C, 0xA822], + [0xA823, 0xA824], + [0xA825, 0xA826], + 0xA827, + [0xA840, 0xA873], + [0xA880, 0xA881], + [0xA882, 0xA8B3], + [0xA8B4, 0xA8C3], + [0xA8F2, 0xA8F7], + 0xA8FB, + [0xA90A, 0xA925], + [0xA926, 0xA92A], + [0xA930, 0xA946], + [0xA947, 0xA951], + 0xA952, + [0xA960, 0xA97C], + [0xA980, 0xA982], + 0xA983, + [0xA984, 0xA9B2], + [0xA9B4, 0xA9B5], + [0xA9B6, 0xA9B9], + [0xA9BA, 0xA9BB], + 0xA9BC, + [0xA9BD, 0xA9BF], + 0xA9CF, + [0xA9E0, 0xA9E4], + 0xA9E6, + [0xA9E7, 0xA9EF], + [0xA9FA, 0xA9FE], + [0xAA00, 0xAA28], + [0xAA29, 0xAA2E], + [0xAA2F, 0xAA30], + [0xAA31, 0xAA32], + [0xAA33, 0xAA34], + [0xAA35, 0xAA36], + [0xAA40, 0xAA42], + 0xAA43, + [0xAA44, 0xAA4B], + 0xAA4C, + 0xAA4D, + [0xAA60, 0xAA6F], + 0xAA70, + [0xAA71, 0xAA76], + 0xAA7A, + [0xAA7E, 0xAAAF], + 0xAAB0, + 0xAAB1, + [0xAAB2, 0xAAB4], + [0xAAB5, 0xAAB6], + [0xAAB7, 0xAAB8], + [0xAAB9, 0xAABD], + 0xAABE, + 0xAAC0, + 0xAAC2, + [0xAADB, 0xAADC], + 0xAADD, + [0xAAE0, 0xAAEA], + 0xAAEB, + [0xAAEC, 0xAAED], + [0xAAEE, 0xAAEF], + 0xAAF2, + [0xAAF3, 0xAAF4], + 0xAAF5, + [0xAB01, 0xAB06], + [0xAB09, 0xAB0E], + [0xAB11, 0xAB16], + [0xAB20, 0xAB26], + [0xAB28, 0xAB2E], + [0xAB30, 0xAB5A], + [0xAB5C, 0xAB5F], + [0xAB64, 0xAB65], + [0xABC0, 0xABE2], + [0xABE3, 0xABE4], + 0xABE5, + [0xABE6, 0xABE7], + 0xABE8, + [0xABE9, 0xABEA], + [0xAC00, 0xD7A3], + [0xD7B0, 0xD7C6], + [0xD7CB, 0xD7FB], + [0xF900, 0xFA6D], + [0xFA70, 0xFAD9], + [0xFB00, 0xFB06], + [0xFB13, 0xFB17], + 0xFB1D, + 0xFB1E, + [0xFB1F, 0xFB28], + [0xFB2A, 0xFB36], + [0xFB38, 0xFB3C], + 0xFB3E, + [0xFB40, 0xFB41], + [0xFB43, 0xFB44], + [0xFB46, 0xFBB1], + [0xFBD3, 0xFD3D], + [0xFD50, 0xFD8F], + [0xFD92, 0xFDC7], + [0xFDF0, 0xFDFB], + [0xFE70, 0xFE74], + [0xFE76, 0xFEFC], + [0xFF21, 0xFF3A], + [0xFF41, 0xFF5A], + [0xFF66, 0xFF6F], + 0xFF70, + [0xFF71, 0xFF9D], + [0xFF9E, 0xFF9F], + [0xFFA0, 0xFFBE], + [0xFFC2, 0xFFC7], + [0xFFCA, 0xFFCF], + [0xFFD2, 0xFFD7], + [0xFFDA, 0xFFDC], + [0x10000, 0x1000B], + [0x1000D, 0x10026], + [0x10028, 0x1003A], + [0x1003C, 0x1003D], + [0x1003F, 0x1004D], + [0x10050, 0x1005D], + [0x10080, 0x100FA], + [0x10140, 0x10174], + [0x10280, 0x1029C], + [0x102A0, 0x102D0], + [0x10300, 0x1031F], + [0x10330, 0x10340], + 0x10341, + [0x10342, 0x10349], + 0x1034A, + [0x10350, 0x10375], + [0x10376, 0x1037A], + [0x10380, 0x1039D], + [0x103A0, 0x103C3], + [0x103C8, 0x103CF], + [0x103D1, 0x103D5], + [0x10400, 0x1044F], + [0x10450, 0x1049D], + [0x10500, 0x10527], + [0x10530, 0x10563], + [0x10600, 0x10736], + [0x10740, 0x10755], + [0x10760, 0x10767], + [0x10800, 0x10805], + 0x10808, + [0x1080A, 0x10835], + [0x10837, 0x10838], + 0x1083C, + [0x1083F, 0x10855], + [0x10860, 0x10876], + [0x10880, 0x1089E], + [0x10900, 0x10915], + [0x10920, 0x10939], + [0x10980, 0x109B7], + [0x109BE, 0x109BF], + 0x10A00, + [0x10A01, 0x10A03], + [0x10A05, 0x10A06], + [0x10A0C, 0x10A0F], + [0x10A10, 0x10A13], + [0x10A15, 0x10A17], + [0x10A19, 0x10A33], + [0x10A60, 0x10A7C], + [0x10A80, 0x10A9C], + [0x10AC0, 0x10AC7], + [0x10AC9, 0x10AE4], + [0x10B00, 0x10B35], + [0x10B40, 0x10B55], + [0x10B60, 0x10B72], + [0x10B80, 0x10B91], + [0x10C00, 0x10C48], + 0x11000, + 0x11001, + 0x11002, + [0x11003, 0x11037], + [0x11038, 0x11045], + 0x11082, + [0x11083, 0x110AF], + [0x110B0, 0x110B2], + [0x110B3, 0x110B6], + [0x110B7, 0x110B8], + [0x110D0, 0x110E8], + [0x11100, 0x11102], + [0x11103, 0x11126], + [0x11127, 0x1112B], + 0x1112C, + [0x1112D, 0x11132], + [0x11150, 0x11172], + 0x11176, + [0x11180, 0x11181], + 0x11182, + [0x11183, 0x111B2], + [0x111B3, 0x111B5], + [0x111B6, 0x111BE], + 0x111BF, + [0x111C1, 0x111C4], + 0x111DA, + [0x11200, 0x11211], + [0x11213, 0x1122B], + [0x1122C, 0x1122E], + [0x1122F, 0x11231], + [0x11232, 0x11233], + 0x11234, + 0x11237, + [0x112B0, 0x112DE], + 0x112DF, + [0x112E0, 0x112E2], + [0x112E3, 0x112E8], + 0x11301, + [0x11302, 0x11303], + [0x11305, 0x1130C], + [0x1130F, 0x11310], + [0x11313, 0x11328], + [0x1132A, 0x11330], + [0x11332, 0x11333], + [0x11335, 0x11339], + 0x1133D, + [0x1133E, 0x1133F], + 0x11340, + [0x11341, 0x11344], + [0x11347, 0x11348], + [0x1134B, 0x1134C], + 0x11357, + [0x1135D, 0x11361], + [0x11362, 0x11363], + [0x11480, 0x114AF], + [0x114B0, 0x114B2], + [0x114B3, 0x114B8], + 0x114B9, + 0x114BA, + [0x114BB, 0x114BE], + [0x114BF, 0x114C0], + 0x114C1, + [0x114C4, 0x114C5], + 0x114C7, + [0x11580, 0x115AE], + [0x115AF, 0x115B1], + [0x115B2, 0x115B5], + [0x115B8, 0x115BB], + [0x115BC, 0x115BD], + 0x115BE, + [0x11600, 0x1162F], + [0x11630, 0x11632], + [0x11633, 0x1163A], + [0x1163B, 0x1163C], + 0x1163D, + 0x1163E, + 0x11640, + 0x11644, + [0x11680, 0x116AA], + 0x116AB, + 0x116AC, + 0x116AD, + [0x116AE, 0x116AF], + [0x116B0, 0x116B5], + [0x118A0, 0x118DF], + 0x118FF, + [0x11AC0, 0x11AF8], + [0x12000, 0x12398], + [0x12400, 0x1246E], + [0x13000, 0x1342E], + [0x16800, 0x16A38], + [0x16A40, 0x16A5E], + [0x16AD0, 0x16AED], + [0x16B00, 0x16B2F], + [0x16B30, 0x16B36], + [0x16B40, 0x16B43], + [0x16B63, 0x16B77], + [0x16B7D, 0x16B8F], + [0x16F00, 0x16F44], + 0x16F50, + [0x16F51, 0x16F7E], + [0x16F93, 0x16F9F], + [0x1B000, 0x1B001], + [0x1BC00, 0x1BC6A], + [0x1BC70, 0x1BC7C], + [0x1BC80, 0x1BC88], + [0x1BC90, 0x1BC99], + 0x1BC9E, + [0x1D400, 0x1D454], + [0x1D456, 0x1D49C], + [0x1D49E, 0x1D49F], + 0x1D4A2, + [0x1D4A5, 0x1D4A6], + [0x1D4A9, 0x1D4AC], + [0x1D4AE, 0x1D4B9], + 0x1D4BB, + [0x1D4BD, 0x1D4C3], + [0x1D4C5, 0x1D505], + [0x1D507, 0x1D50A], + [0x1D50D, 0x1D514], + [0x1D516, 0x1D51C], + [0x1D51E, 0x1D539], + [0x1D53B, 0x1D53E], + [0x1D540, 0x1D544], + 0x1D546, + [0x1D54A, 0x1D550], + [0x1D552, 0x1D6A5], + [0x1D6A8, 0x1D6C0], + [0x1D6C2, 0x1D6DA], + [0x1D6DC, 0x1D6FA], + [0x1D6FC, 0x1D714], + [0x1D716, 0x1D734], + [0x1D736, 0x1D74E], + [0x1D750, 0x1D76E], + [0x1D770, 0x1D788], + [0x1D78A, 0x1D7A8], + [0x1D7AA, 0x1D7C2], + [0x1D7C4, 0x1D7CB], + [0x1E800, 0x1E8C4], + [0x1EE00, 0x1EE03], + [0x1EE05, 0x1EE1F], + [0x1EE21, 0x1EE22], + 0x1EE24, + 0x1EE27, + [0x1EE29, 0x1EE32], + [0x1EE34, 0x1EE37], + 0x1EE39, + 0x1EE3B, + 0x1EE42, + 0x1EE47, + 0x1EE49, + 0x1EE4B, + [0x1EE4D, 0x1EE4F], + [0x1EE51, 0x1EE52], + 0x1EE54, + 0x1EE57, + 0x1EE59, + 0x1EE5B, + 0x1EE5D, + 0x1EE5F, + [0x1EE61, 0x1EE62], + 0x1EE64, + [0x1EE67, 0x1EE6A], + [0x1EE6C, 0x1EE72], + [0x1EE74, 0x1EE77], + [0x1EE79, 0x1EE7C], + 0x1EE7E, + [0x1EE80, 0x1EE89], + [0x1EE8B, 0x1EE9B], + [0x1EEA1, 0x1EEA3], + [0x1EEA5, 0x1EEA9], + [0x1EEAB, 0x1EEBB], + [0x1F130, 0x1F149], + [0x1F150, 0x1F169], + [0x1F170, 0x1F189], + [0x20000, 0x2A6D6], + [0x2A700, 0x2B734], + [0x2B740, 0x2B81D], + [0x2F800, 0x2FA1D] +]; diff --git a/tools/unicodejs-properties.py b/tools/unicodejs-properties.py index 2b6a69d..c7f1655 100755 --- a/tools/unicodejs-properties.py +++ b/tools/unicodejs-properties.py @@ -4,6 +4,32 @@ import re, urllib2, os +wordRanges = [] # list of (start, end) +for line in urllib2.urlopen( "http://unicode.org/Public/UNIDATA/DerivedCoreProperties.txt" ): + m = re.search( r"^([0-9A-F]{4,6})(?:\.\.([0-9A-F]{4,6}))?\s*;\s*Alphabetic.*$", line ) + if not m: + continue + first = m.group(1) + last = m.group(2) or None + wordRanges.append( (first, last) ) +# Translate ranges into js +rangeStrings = [] +for start, end in wordRanges: + if not end: + rangeStrings.append( "0x" + start ) + else: + rangeStrings.append( "[0x" + start + ", 0x" + end + "]" ) +# Write js file +js = "// This file is GENERATED by tools/unicodejs-properties.py\n" +js += "// DO NOT EDIT\n" +js += "unicodeJS.alphabetic = [\n\t" +js += ",\n\t".join( rangeStrings ) +js += "\n];\n" +jsFilename = os.path.dirname( os.path.realpath( __file__ ) ) + "/../src/unicodejs.alphabetic.js" +open( jsFilename, "w" ).write( js ) +print "wrote " + jsFilename + + for breaktype in ['Grapheme', 'Word']: # a list of property name strings like "Extend", "Format" etc properties = [] -- To view, visit https://gerrit.wikimedia.org/r/185103 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: newchange Gerrit-Change-Id: I1b785a369a2c80f6afc27f792787f6590948241e Gerrit-PatchSet: 1 Gerrit-Project: unicodejs Gerrit-Branch: master Gerrit-Owner: Divec <[email protected]> _______________________________________________ MediaWiki-commits mailing list [email protected] https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits
