diff --git a/src/java.base/share/classes/java/lang/Character.java b/src/java.base/share/classes/java/lang/Character.java index 4c6af132a6a..afe1fb8f7c0 100644 --- a/src/java.base/share/classes/java/lang/Character.java +++ b/src/java.base/share/classes/java/lang/Character.java @@ -63,7 +63,7 @@ import static java.lang.constant.ConstantDescs.DEFAULT_NAME; * from the Unicode Consortium at * http://www.unicode.org. *

- * Character information is based on the Unicode Standard, version 14.0. + * Character information is based on the Unicode Standard, version 15.0. *

* The Java platform has supported different versions of the Unicode * Standard over time. Upgrades to newer versions of the Unicode Standard @@ -75,6 +75,8 @@ import static java.lang.constant.ConstantDescs.DEFAULT_NAME; * Unicode version * * + * Java SE 20 + * Unicode 15.0 * Java SE 19 * Unicode 14.0 * Java SE 15 @@ -737,13 +739,11 @@ class Character implements java.io.Serializable, Comparable, Constabl */ public static final class UnicodeBlock extends Subset { /** - * NUM_ENTITIES should match the total number of UnicodeBlocks - * to calculate the initial capacity of the map. It should be - * adjusted whenever the Unicode Character Database is upgraded. - * - * 0.75 - the default load factor of HashMap + * NUM_ENTITIES should match the total number of UnicodeBlocks. + * It should be adjusted whenever the Unicode Character Database + * is upgraded. */ - private static final int NUM_ENTITIES = 737; + private static final int NUM_ENTITIES = 756; private static Map map = HashMap.newHashMap(NUM_ENTITIES); /** @@ -3542,6 +3542,74 @@ class Character implements java.io.Serializable, Comparable, Constabl "ETHIOPIC EXTENDED-B", "ETHIOPICEXTENDED-B"); + /** + * Constant for the "Arabic Extended-C" Unicode + * character block. + * @since 20 + */ + public static final UnicodeBlock ARABIC_EXTENDED_C = + new UnicodeBlock("ARABIC_EXTENDED_C", + "ARABIC EXTENDED-C", + "ARABICEXTENDED-C"); + + /** + * Constant for the "Devanagari Extended-A" Unicode + * character block. + * @since 20 + */ + public static final UnicodeBlock DEVANAGARI_EXTENDED_A = + new UnicodeBlock("DEVANAGARI_EXTENDED_A", + "DEVANAGARI EXTENDED-A", + "DEVANAGARIEXTENDED-A"); + + /** + * Constant for the "Kawi" Unicode + * character block. + * @since 20 + */ + public static final UnicodeBlock KAWI = + new UnicodeBlock("KAWI"); + + /** + * Constant for the "Kaktovik Numerals" Unicode + * character block. + * @since 20 + */ + public static final UnicodeBlock KAKTOVIK_NUMERALS = + new UnicodeBlock("KAKTOVIK_NUMERALS", + "KAKTOVIK NUMERALS", + "KAKTOVIKNUMERALS"); + + /** + * Constant for the "Cyrillic Extended-D" Unicode + * character block. + * @since 20 + */ + public static final UnicodeBlock CYRILLIC_EXTENDED_D = + new UnicodeBlock("CYRILLIC_EXTENDED_D", + "CYRILLIC EXTENDED-D", + "CYRILLICEXTENDED-D"); + + /** + * Constant for the "Nag Mundari" Unicode + * character block. + * @since 20 + */ + public static final UnicodeBlock NAG_MUNDARI = + new UnicodeBlock("NAG_MUNDARI", + "NAG MUNDARI", + "NAGMUNDARI"); + + /** + * Constant for the "CJK Unified Ideographs Extension H" Unicode + * character block. + * @since 20 + */ + public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H = + new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H", + "CJK UNIFIED IDEOGRAPHS EXTENSION H", + "CJKUNIFIEDIDEOGRAPHSEXTENSIONH"); + private static final int[] blockStarts = { 0x0000, // 0000..007F; Basic Latin 0x0080, // 0080..00FF; Latin-1 Supplement @@ -3763,7 +3831,7 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x10D40, // unassigned 0x10E60, // 10E60..10E7F; Rumi Numeral Symbols 0x10E80, // 10E80..10EBF; Yezidi - 0x10EC0, // unassigned + 0x10EC0, // 10EC0..10EFF; Arabic Extended-C 0x10F00, // 10F00..10F2F; Old Sogdian 0x10F30, // 10F30..10F6F; Sogdian 0x10F70, // 10F70..10FAF; Old Uyghur @@ -3802,7 +3870,8 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x11A50, // 11A50..11AAF; Soyombo 0x11AB0, // 11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A 0x11AC0, // 11AC0..11AFF; Pau Cin Hau - 0x11B00, // unassigned + 0x11B00, // 11B00..11B5F; Devanagari Extended-A + 0x11B60, // unassigned 0x11C00, // 11C00..11C6F; Bhaiksuki 0x11C70, // 11C70..11CBF; Marchen 0x11CC0, // unassigned @@ -3810,7 +3879,8 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x11D60, // 11D60..11DAF; Gunjala Gondi 0x11DB0, // unassigned 0x11EE0, // 11EE0..11EFF; Makasar - 0x11F00, // unassigned + 0x11F00, // 11F00..11F5F; Kawi + 0x11F60, // unassigned 0x11FB0, // 11FB0..11FBF; Lisu Supplement 0x11FC0, // 11FC0..11FFF; Tamil Supplement 0x12000, // 12000..123FF; Cuneiform @@ -3819,8 +3889,8 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x12550, // unassigned 0x12F90, // 12F90..12FFF; Cypro-Minoan 0x13000, // 13000..1342F; Egyptian Hieroglyphs - 0x13430, // 13430..1343F; Egyptian Hieroglyph Format Controls - 0x13440, // unassigned + 0x13430, // 13430..1345F; Egyptian Hieroglyph Format Controls + 0x13460, // unassigned 0x14400, // 14400..1467F; Anatolian Hieroglyphs 0x14680, // unassigned 0x16800, // 16800..16A3F; Bamum Supplement @@ -3854,6 +3924,7 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x1D100, // 1D100..1D1FF; Musical Symbols 0x1D200, // 1D200..1D24F; Ancient Greek Musical Notation 0x1D250, // unassigned + 0x1D2C0, // 1D2C0..1D2DF; Kaktovik Numerals 0x1D2E0, // 1D2E0..1D2FF; Mayan Numerals 0x1D300, // 1D300..1D35F; Tai Xuan Jing Symbols 0x1D360, // 1D360..1D37F; Counting Rod Numerals @@ -3863,12 +3934,15 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x1DAB0, // unassigned 0x1DF00, // 1DF00..1DFFF; Latin Extended-G 0x1E000, // 1E000..1E02F; Glagolitic Supplement - 0x1E030, // unassigned + 0x1E030, // 1E030..1E08F; Cyrillic Extended-D + 0x1E090, // unassigned 0x1E100, // 1E100..1E14F; Nyiakeng Puachue Hmong 0x1E150, // unassigned 0x1E290, // 1E290..1E2BF; Toto 0x1E2C0, // 1E2C0..1E2FF; Wancho 0x1E300, // unassigned + 0x1E4D0, // 1E4D0..1E4FF; Nag Mundari + 0x1E500, // unassigned 0x1E7E0, // 1E7E0..1E7FF; Ethiopic Extended-B 0x1E800, // 1E800..1E8DF; Mende Kikakui 0x1E8E0, // unassigned @@ -3907,7 +3981,8 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x2F800, // 2F800..2FA1F; CJK Compatibility Ideographs Supplement 0x2FA20, // unassigned 0x30000, // 30000..3134F; CJK Unified Ideographs Extension G - 0x31350, // unassigned + 0x31350, // 31350..323AF; CJK Unified Ideographs Extension H + 0x323B0, // unassigned 0xE0000, // E0000..E007F; Tags 0xE0080, // unassigned 0xE0100, // E0100..E01EF; Variation Selectors Supplement @@ -4137,7 +4212,7 @@ class Character implements java.io.Serializable, Comparable, Constabl null, RUMI_NUMERAL_SYMBOLS, YEZIDI, - null, + ARABIC_EXTENDED_C, OLD_SOGDIAN, SOGDIAN, OLD_UYGHUR, @@ -4176,6 +4251,7 @@ class Character implements java.io.Serializable, Comparable, Constabl SOYOMBO, UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A, PAU_CIN_HAU, + DEVANAGARI_EXTENDED_A, null, BHAIKSUKI, MARCHEN, @@ -4184,6 +4260,7 @@ class Character implements java.io.Serializable, Comparable, Constabl GUNJALA_GONDI, null, MAKASAR, + KAWI, null, LISU_SUPPLEMENT, TAMIL_SUPPLEMENT, @@ -4228,6 +4305,7 @@ class Character implements java.io.Serializable, Comparable, Constabl MUSICAL_SYMBOLS, ANCIENT_GREEK_MUSICAL_NOTATION, null, + KAKTOVIK_NUMERALS, MAYAN_NUMERALS, TAI_XUAN_JING_SYMBOLS, COUNTING_ROD_NUMERALS, @@ -4237,12 +4315,15 @@ class Character implements java.io.Serializable, Comparable, Constabl null, LATIN_EXTENDED_G, GLAGOLITIC_SUPPLEMENT, + CYRILLIC_EXTENDED_D, null, NYIAKENG_PUACHUE_HMONG, null, TOTO, WANCHO, null, + NAG_MUNDARI, + null, ETHIOPIC_EXTENDED_B, MENDE_KIKAKUI, null, @@ -4281,6 +4362,7 @@ class Character implements java.io.Serializable, Comparable, Constabl CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT, null, CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G, + CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H, null, TAGS, null, @@ -5282,6 +5364,18 @@ class Character implements java.io.Serializable, Comparable, Constabl */ TOTO, + /** + * Unicode script "Kawi". + * @since 20 + */ + KAWI, + + /** + * Unicode script "Nag Mundari". + * @since 20 + */ + NAG_MUNDARI, + /** * Unicode script "Unknown". */ @@ -5592,8 +5686,8 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x0CE4, // 0CE4..0CE5; UNKNOWN 0x0CE6, // 0CE6..0CEF; KANNADA 0x0CF0, // 0CF0 ; UNKNOWN - 0x0CF1, // 0CF1..0CF2; KANNADA - 0x0CF3, // 0CF3..0CFF; UNKNOWN + 0x0CF1, // 0CF1..0CF3; KANNADA + 0x0CF4, // 0CF4..0CFF; UNKNOWN 0x0D00, // 0D00..0D0C; MALAYALAM 0x0D0D, // 0D0D ; UNKNOWN 0x0D0E, // 0D0E..0D10; MALAYALAM @@ -5653,8 +5747,8 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x0EC5, // 0EC5 ; UNKNOWN 0x0EC6, // 0EC6 ; LAO 0x0EC7, // 0EC7 ; UNKNOWN - 0x0EC8, // 0EC8..0ECD; LAO - 0x0ECE, // 0ECE..0ECF; UNKNOWN + 0x0EC8, // 0EC8..0ECE; LAO + 0x0ECF, // 0ECF ; UNKNOWN 0x0ED0, // 0ED0..0ED9; LAO 0x0EDA, // 0EDA..0EDB; UNKNOWN 0x0EDC, // 0EDC..0EDF; LAO @@ -6353,7 +6447,8 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x10EAB, // 10EAB..10EAD; YEZIDI 0x10EAE, // 10EAE..10EAF; UNKNOWN 0x10EB0, // 10EB0..10EB1; YEZIDI - 0x10EB2, // 10EB2..10EFF; UNKNOWN + 0x10EB2, // 10EB2..10EFC; UNKNOWN + 0x10EFD, // 10EFD..10EFF; ARABIC 0x10F00, // 10F00..10F27; OLD_SOGDIAN 0x10F28, // 10F28..10F2F; UNKNOWN 0x10F30, // 10F30..10F59; SOGDIAN @@ -6389,8 +6484,8 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x111F5, // 111F5..111FF; UNKNOWN 0x11200, // 11200..11211; KHOJKI 0x11212, // 11212 ; UNKNOWN - 0x11213, // 11213..1123E; KHOJKI - 0x1123F, // 1123F..1127F; UNKNOWN + 0x11213, // 11213..11241; KHOJKI + 0x11242, // 11242..1127F; UNKNOWN 0x11280, // 11280..11286; MULTANI 0x11287, // 11287 ; UNKNOWN 0x11288, // 11288 ; MULTANI @@ -6497,7 +6592,9 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x11AA3, // 11AA3..11AAF; UNKNOWN 0x11AB0, // 11AB0..11ABF; CANADIAN_ABORIGINAL 0x11AC0, // 11AC0..11AF8; PAU_CIN_HAU - 0x11AF9, // 11AF9..11BFF; UNKNOWN + 0x11AF9, // 11AF9..11AFF; UNKNOWN + 0x11B00, // 11B00..11B09; DEVANAGARI + 0x11B0A, // 11B0A..11BFF; UNKNOWN 0x11C00, // 11C00..11C08; BHAIKSUKI 0x11C09, // 11C09 ; UNKNOWN 0x11C0A, // 11C0A..11C36; BHAIKSUKI @@ -6539,7 +6636,13 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x11DA0, // 11DA0..11DA9; GUNJALA_GONDI 0x11DAA, // 11DAA..11EDF; UNKNOWN 0x11EE0, // 11EE0..11EF8; MAKASAR - 0x11EF9, // 11EF9..11FAF; UNKNOWN + 0x11EF9, // 11EF9..11EFF; UNKNOWN + 0x11F00, // 11F00..11F10; KAWI + 0x11F11, // 11F11 ; UNKNOWN + 0x11F12, // 11F12..11F3A; KAWI + 0x11F3B, // 11F3B..11F3D; UNKNOWN + 0x11F3E, // 11F3E..11F59; KAWI + 0x11F5A, // 11F5A..11FAF; UNKNOWN 0x11FB0, // 11FB0 ; LISU 0x11FB1, // 11FB1..11FBF; UNKNOWN 0x11FC0, // 11FC0..11FF1; TAMIL @@ -6555,10 +6658,8 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x12544, // 12544..12F8F; UNKNOWN 0x12F90, // 12F90..12FF2; CYPRO_MINOAN 0x12FF3, // 12FF3..12FFF; UNKNOWN - 0x13000, // 13000..1342E; EGYPTIAN_HIEROGLYPHS - 0x1342F, // 1342F ; UNKNOWN - 0x13430, // 13430..13438; EGYPTIAN_HIEROGLYPHS - 0x13439, // 13439..143FF; UNKNOWN + 0x13000, // 13000..13455; EGYPTIAN_HIEROGLYPHS + 0x13456, // 13456..143FF; UNKNOWN 0x14400, // 14400..14646; ANATOLIAN_HIEROGLYPHS 0x14647, // 14647..167FF; UNKNOWN 0x16800, // 16800..16A38; BAMUM @@ -6617,9 +6718,13 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x1B000, // 1B000 ; KATAKANA 0x1B001, // 1B001..1B11F; HIRAGANA 0x1B120, // 1B120..1B122; KATAKANA - 0x1B123, // 1B123..1B14F; UNKNOWN + 0x1B123, // 1B123..1B131; UNKNOWN + 0x1B132, // 1B132 ; HIRAGANA + 0x1B133, // 1B133..1B14F; UNKNOWN 0x1B150, // 1B150..1B152; HIRAGANA - 0x1B153, // 1B153..1B163; UNKNOWN + 0x1B153, // 1B153..1B154; UNKNOWN + 0x1B155, // 1B155 ; KATAKANA + 0x1B156, // 1B156..1B163; UNKNOWN 0x1B164, // 1B164..1B167; KATAKANA 0x1B168, // 1B168..1B16F; UNKNOWN 0x1B170, // 1B170..1B2FB; NUSHU @@ -6656,7 +6761,9 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x1D1AE, // 1D1AE..1D1EA; COMMON 0x1D1EB, // 1D1EB..1D1FF; UNKNOWN 0x1D200, // 1D200..1D245; GREEK - 0x1D246, // 1D246..1D2DF; UNKNOWN + 0x1D246, // 1D246..1D2BF; UNKNOWN + 0x1D2C0, // 1D2C0..1D2D3; COMMON + 0x1D2D4, // 1D2D4..1D2DF; UNKNOWN 0x1D2E0, // 1D2E0..1D2F3; COMMON 0x1D2F4, // 1D2F4..1D2FF; UNKNOWN 0x1D300, // 1D300..1D356; COMMON @@ -6711,7 +6818,9 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x1DAA1, // 1DAA1..1DAAF; SIGNWRITING 0x1DAB0, // 1DAB0..1DEFF; UNKNOWN 0x1DF00, // 1DF00..1DF1E; LATIN - 0x1DF1F, // 1DF1F..1DFFF; UNKNOWN + 0x1DF1F, // 1DF1F..1DF24; UNKNOWN + 0x1DF25, // 1DF25..1DF2A; LATIN + 0x1DF2B, // 1DF2B..1DFFF; UNKNOWN 0x1E000, // 1E000..1E006; GLAGOLITIC 0x1E007, // 1E007 ; UNKNOWN 0x1E008, // 1E008..1E018; GLAGOLITIC @@ -6721,7 +6830,11 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x1E023, // 1E023..1E024; GLAGOLITIC 0x1E025, // 1E025 ; UNKNOWN 0x1E026, // 1E026..1E02A; GLAGOLITIC - 0x1E02B, // 1E02B..1E0FF; UNKNOWN + 0x1E02B, // 1E02B..1E02F; UNKNOWN + 0x1E030, // 1E030..1E06D; CYRILLIC + 0x1E06E, // 1E06E..1E08E; UNKNOWN + 0x1E08F, // 1E08F ; CYRILLIC + 0x1E090, // 1E090..1E0FF; UNKNOWN 0x1E100, // 1E100..1E12C; NYIAKENG_PUACHUE_HMONG 0x1E12D, // 1E12D..1E12F; UNKNOWN 0x1E130, // 1E130..1E13D; NYIAKENG_PUACHUE_HMONG @@ -6735,7 +6848,9 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x1E2C0, // 1E2C0..1E2F9; WANCHO 0x1E2FA, // 1E2FA..1E2FE; UNKNOWN 0x1E2FF, // 1E2FF ; WANCHO - 0x1E300, // 1E300..1E7DF; UNKNOWN + 0x1E300, // 1E300..1E4CF; UNKNOWN + 0x1E4D0, // 1E4D0..1E4F9; NAG_MUNDARI + 0x1E4FA, // 1E4FA..1E7DF; UNKNOWN 0x1E7E0, // 1E7E0..1E7E6; ETHIOPIC 0x1E7E7, // 1E7E7 ; UNKNOWN 0x1E7E8, // 1E7E8..1E7EB; ETHIOPIC @@ -6853,15 +6968,15 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x1F260, // 1F260..1F265; COMMON 0x1F266, // 1F266..1F2FF; UNKNOWN 0x1F300, // 1F300..1F6D7; COMMON - 0x1F6D8, // 1F6D8..1F6DC; UNKNOWN - 0x1F6DD, // 1F6DD..1F6EC; COMMON + 0x1F6D8, // 1F6D8..1F6DB; UNKNOWN + 0x1F6DC, // 1F6DC..1F6EC; COMMON 0x1F6ED, // 1F6ED..1F6EF; UNKNOWN 0x1F6F0, // 1F6F0..1F6FC; COMMON 0x1F6FD, // 1F6FD..1F6FF; UNKNOWN - 0x1F700, // 1F700..1F773; COMMON - 0x1F774, // 1F774..1F77F; UNKNOWN - 0x1F780, // 1F780..1F7D8; COMMON - 0x1F7D9, // 1F7D9..1F7DF; UNKNOWN + 0x1F700, // 1F700..1F776; COMMON + 0x1F777, // 1F777..1F77A; UNKNOWN + 0x1F77B, // 1F77B..1F7D9; COMMON + 0x1F7DA, // 1F7DA..1F7DF; UNKNOWN 0x1F7E0, // 1F7E0..1F7EB; COMMON 0x1F7EC, // 1F7EC..1F7EF; UNKNOWN 0x1F7F0, // 1F7F0 ; COMMON @@ -6882,24 +6997,20 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x1FA54, // 1FA54..1FA5F; UNKNOWN 0x1FA60, // 1FA60..1FA6D; COMMON 0x1FA6E, // 1FA6E..1FA6F; UNKNOWN - 0x1FA70, // 1FA70..1FA74; COMMON - 0x1FA75, // 1FA75..1FA77; UNKNOWN - 0x1FA78, // 1FA78..1FA7C; COMMON + 0x1FA70, // 1FA70..1FA7C; COMMON 0x1FA7D, // 1FA7D..1FA7F; UNKNOWN - 0x1FA80, // 1FA80..1FA86; COMMON - 0x1FA87, // 1FA87..1FA8F; UNKNOWN - 0x1FA90, // 1FA90..1FAAC; COMMON - 0x1FAAD, // 1FAAD..1FAAF; UNKNOWN - 0x1FAB0, // 1FAB0..1FABA; COMMON - 0x1FABB, // 1FABB..1FABF; UNKNOWN - 0x1FAC0, // 1FAC0..1FAC5; COMMON - 0x1FAC6, // 1FAC6..1FACF; UNKNOWN - 0x1FAD0, // 1FAD0..1FAD9; COMMON - 0x1FADA, // 1FADA..1FADF; UNKNOWN - 0x1FAE0, // 1FAE0..1FAE7; COMMON - 0x1FAE8, // 1FAE8..1FAEF; UNKNOWN - 0x1FAF0, // 1FAF0..1FAF6; COMMON - 0x1FAF7, // 1FAF7..1FAFF; UNKNOWN + 0x1FA80, // 1FA80..1FA88; COMMON + 0x1FA89, // 1FA89..1FA8F; UNKNOWN + 0x1FA90, // 1FA90..1FABD; COMMON + 0x1FABE, // 1FABE ; UNKNOWN + 0x1FABF, // 1FABF..1FAC5; COMMON + 0x1FAC6, // 1FAC6..1FACD; UNKNOWN + 0x1FACE, // 1FACE..1FADB; COMMON + 0x1FADC, // 1FADC..1FADF; UNKNOWN + 0x1FAE0, // 1FAE0..1FAE8; COMMON + 0x1FAE9, // 1FAE9..1FAEF; UNKNOWN + 0x1FAF0, // 1FAF0..1FAF8; COMMON + 0x1FAF9, // 1FAF9..1FAFF; UNKNOWN 0x1FB00, // 1FB00..1FB92; COMMON 0x1FB93, // 1FB93 ; UNKNOWN 0x1FB94, // 1FB94..1FBCA; COMMON @@ -6908,8 +7019,8 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x1FBFA, // 1FBFA..1FFFF; UNKNOWN 0x20000, // 20000..2A6DF; HAN 0x2A6E0, // 2A6E0..2A6FF; UNKNOWN - 0x2A700, // 2A700..2B738; HAN - 0x2B739, // 2B739..2B73F; UNKNOWN + 0x2A700, // 2A700..2B739; HAN + 0x2B73A, // 2B73A..2B73F; UNKNOWN 0x2B740, // 2B740..2B81D; HAN 0x2B81E, // 2B81E..2B81F; UNKNOWN 0x2B820, // 2B820..2CEA1; HAN @@ -6919,7 +7030,9 @@ class Character implements java.io.Serializable, Comparable, Constabl 0x2F800, // 2F800..2FA1D; HAN 0x2FA1E, // 2FA1E..2FFFF; UNKNOWN 0x30000, // 30000..3134A; HAN - 0x3134B, // 3134B..E0000; UNKNOWN + 0x3134B, // 3134B..3134F; UNKNOWN + 0x31350, // 31350..323AF; HAN + 0x323B0, // 323B0..E0000; UNKNOWN 0xE0001, // E0001 ; COMMON 0xE0002, // E0002..E001F; UNKNOWN 0xE0020, // E0020..E007F; COMMON @@ -7233,8 +7346,8 @@ class Character implements java.io.Serializable, Comparable, Constabl UNKNOWN, // 0CE4..0CE5 KANNADA, // 0CE6..0CEF UNKNOWN, // 0CF0 - KANNADA, // 0CF1..0CF2 - UNKNOWN, // 0CF3..0CFF + KANNADA, // 0CF1..0CF3 + UNKNOWN, // 0CF4..0CFF MALAYALAM, // 0D00..0D0C UNKNOWN, // 0D0D MALAYALAM, // 0D0E..0D10 @@ -7294,8 +7407,8 @@ class Character implements java.io.Serializable, Comparable, Constabl UNKNOWN, // 0EC5 LAO, // 0EC6 UNKNOWN, // 0EC7 - LAO, // 0EC8..0ECD - UNKNOWN, // 0ECE..0ECF + LAO, // 0EC8..0ECE + UNKNOWN, // 0ECF LAO, // 0ED0..0ED9 UNKNOWN, // 0EDA..0EDB LAO, // 0EDC..0EDF @@ -7994,7 +8107,8 @@ class Character implements java.io.Serializable, Comparable, Constabl YEZIDI, // 10EAB..10EAD UNKNOWN, // 10EAE..10EAF YEZIDI, // 10EB0..10EB1 - UNKNOWN, // 10EB2..10EFF + UNKNOWN, // 10EB2..10EFC + ARABIC, // 10EFD..10EFF OLD_SOGDIAN, // 10F00..10F27 UNKNOWN, // 10F28..10F2F SOGDIAN, // 10F30..10F59 @@ -8030,8 +8144,8 @@ class Character implements java.io.Serializable, Comparable, Constabl UNKNOWN, // 111F5..111FF KHOJKI, // 11200..11211 UNKNOWN, // 11212 - KHOJKI, // 11213..1123E - UNKNOWN, // 1123F..1127F + KHOJKI, // 11213..11241 + UNKNOWN, // 11242..1127F MULTANI, // 11280..11286 UNKNOWN, // 11287 MULTANI, // 11288 @@ -8138,7 +8252,9 @@ class Character implements java.io.Serializable, Comparable, Constabl UNKNOWN, // 11AA3..11AAF CANADIAN_ABORIGINAL, // 11AB0..11ABF PAU_CIN_HAU, // 11AC0..11AF8 - UNKNOWN, // 11AF9..11BFF + UNKNOWN, // 11AF9..11AFF + DEVANAGARI, // 11B00..11B09 + UNKNOWN, // 11B0A..11BFF BHAIKSUKI, // 11C00..11C08 UNKNOWN, // 11C09 BHAIKSUKI, // 11C0A..11C36 @@ -8180,7 +8296,13 @@ class Character implements java.io.Serializable, Comparable, Constabl GUNJALA_GONDI, // 11DA0..11DA9 UNKNOWN, // 11DAA..11EDF MAKASAR, // 11EE0..11EF8 - UNKNOWN, // 11EF9..11FAF + UNKNOWN, // 11EF9..11EFF + KAWI, // 11F00..11F10 + UNKNOWN, // 11F11 + KAWI, // 11F12..11F3A + UNKNOWN, // 11F3B..11F3D + KAWI, // 11F3E..11F59 + UNKNOWN, // 11F5A..11FAF LISU, // 11FB0 UNKNOWN, // 11FB1..11FBF TAMIL, // 11FC0..11FF1 @@ -8196,10 +8318,8 @@ class Character implements java.io.Serializable, Comparable, Constabl UNKNOWN, // 12544..12F8F CYPRO_MINOAN, // 12F90..12FF2 UNKNOWN, // 12FF3..12FFF - EGYPTIAN_HIEROGLYPHS, // 13000..1342E - UNKNOWN, // 1342F - EGYPTIAN_HIEROGLYPHS, // 13430..13438 - UNKNOWN, // 13439..143FF + EGYPTIAN_HIEROGLYPHS, // 13000..13455 + UNKNOWN, // 13456..143FF ANATOLIAN_HIEROGLYPHS, // 14400..14646 UNKNOWN, // 14647..167FF BAMUM, // 16800..16A38 @@ -8258,9 +8378,13 @@ class Character implements java.io.Serializable, Comparable, Constabl KATAKANA, // 1B000 HIRAGANA, // 1B001..1B11F KATAKANA, // 1B120..1B122 - UNKNOWN, // 1B123..1B14F + UNKNOWN, // 1B123..1B131 + HIRAGANA, // 1B132 + UNKNOWN, // 1B133..1B14F HIRAGANA, // 1B150..1B152 - UNKNOWN, // 1B153..1B163 + UNKNOWN, // 1B153..1B154 + KATAKANA, // 1B155 + UNKNOWN, // 1B156..1B163 KATAKANA, // 1B164..1B167 UNKNOWN, // 1B168..1B16F NUSHU, // 1B170..1B2FB @@ -8297,7 +8421,9 @@ class Character implements java.io.Serializable, Comparable, Constabl COMMON, // 1D1AE..1D1EA UNKNOWN, // 1D1EB..1D1FF GREEK, // 1D200..1D245 - UNKNOWN, // 1D246..1D2DF + UNKNOWN, // 1D246..1D2BF + COMMON, // 1D2C0..1D2D3 + UNKNOWN, // 1D2D4..1D2DF COMMON, // 1D2E0..1D2F3 UNKNOWN, // 1D2F4..1D2FF COMMON, // 1D300..1D356 @@ -8352,7 +8478,9 @@ class Character implements java.io.Serializable, Comparable, Constabl SIGNWRITING, // 1DAA1..1DAAF UNKNOWN, // 1DAB0..1DEFF LATIN, // 1DF00..1DF1E - UNKNOWN, // 1DF1F..1DFFF + UNKNOWN, // 1DF1F..1DF24 + LATIN, // 1DF25..1DF2A + UNKNOWN, // 1DF2B..1DFFF GLAGOLITIC, // 1E000..1E006 UNKNOWN, // 1E007 GLAGOLITIC, // 1E008..1E018 @@ -8362,7 +8490,11 @@ class Character implements java.io.Serializable, Comparable, Constabl GLAGOLITIC, // 1E023..1E024 UNKNOWN, // 1E025 GLAGOLITIC, // 1E026..1E02A - UNKNOWN, // 1E02B..1E0FF + UNKNOWN, // 1E02B..1E02F + CYRILLIC, // 1E030..1E06D + UNKNOWN, // 1E06E..1E08E + CYRILLIC, // 1E08F + UNKNOWN, // 1E090..1E0FF NYIAKENG_PUACHUE_HMONG, // 1E100..1E12C UNKNOWN, // 1E12D..1E12F NYIAKENG_PUACHUE_HMONG, // 1E130..1E13D @@ -8376,7 +8508,9 @@ class Character implements java.io.Serializable, Comparable, Constabl WANCHO, // 1E2C0..1E2F9 UNKNOWN, // 1E2FA..1E2FE WANCHO, // 1E2FF - UNKNOWN, // 1E300..1E7DF + UNKNOWN, // 1E300..1E4CF + NAG_MUNDARI, // 1E4D0..1E4F9 + UNKNOWN, // 1E4FA..1E7DF ETHIOPIC, // 1E7E0..1E7E6 UNKNOWN, // 1E7E7 ETHIOPIC, // 1E7E8..1E7EB @@ -8494,15 +8628,15 @@ class Character implements java.io.Serializable, Comparable, Constabl COMMON, // 1F260..1F265 UNKNOWN, // 1F266..1F2FF COMMON, // 1F300..1F6D7 - UNKNOWN, // 1F6D8..1F6DC - COMMON, // 1F6DD..1F6EC + UNKNOWN, // 1F6D8..1F6DB + COMMON, // 1F6DC..1F6EC UNKNOWN, // 1F6ED..1F6EF COMMON, // 1F6F0..1F6FC UNKNOWN, // 1F6FD..1F6FF - COMMON, // 1F700..1F773 - UNKNOWN, // 1F774..1F77F - COMMON, // 1F780..1F7D8 - UNKNOWN, // 1F7D9..1F7DF + COMMON, // 1F700..1F776 + UNKNOWN, // 1F777..1F77A + COMMON, // 1F77B..1F7D9 + UNKNOWN, // 1F7DA..1F7DF COMMON, // 1F7E0..1F7EB UNKNOWN, // 1F7EC..1F7EF COMMON, // 1F7F0 @@ -8523,24 +8657,20 @@ class Character implements java.io.Serializable, Comparable, Constabl UNKNOWN, // 1FA54..1FA5F COMMON, // 1FA60..1FA6D UNKNOWN, // 1FA6E..1FA6F - COMMON, // 1FA70..1FA74 - UNKNOWN, // 1FA75..1FA77 - COMMON, // 1FA78..1FA7C + COMMON, // 1FA70..1FA7C UNKNOWN, // 1FA7D..1FA7F - COMMON, // 1FA80..1FA86 - UNKNOWN, // 1FA87..1FA8F - COMMON, // 1FA90..1FAAC - UNKNOWN, // 1FAAD..1FAAF - COMMON, // 1FAB0..1FABA - UNKNOWN, // 1FABB..1FABF - COMMON, // 1FAC0..1FAC5 - UNKNOWN, // 1FAC6..1FACF - COMMON, // 1FAD0..1FAD9 - UNKNOWN, // 1FADA..1FADF - COMMON, // 1FAE0..1FAE7 - UNKNOWN, // 1FAE8..1FAEF - COMMON, // 1FAF0..1FAF6 - UNKNOWN, // 1FAF7..1FAFF + COMMON, // 1FA80..1FA88 + UNKNOWN, // 1FA89..1FA8F + COMMON, // 1FA90..1FABD + UNKNOWN, // 1FABE + COMMON, // 1FABF..1FAC5 + UNKNOWN, // 1FAC6..1FACD + COMMON, // 1FACE..1FADB + UNKNOWN, // 1FADC..1FADF + COMMON, // 1FAE0..1FAE8 + UNKNOWN, // 1FAE9..1FAEF + COMMON, // 1FAF0..1FAF8 + UNKNOWN, // 1FAF9..1FAFF COMMON, // 1FB00..1FB92 UNKNOWN, // 1FB93 COMMON, // 1FB94..1FBCA @@ -8549,8 +8679,8 @@ class Character implements java.io.Serializable, Comparable, Constabl UNKNOWN, // 1FBFA..1FFFF HAN, // 20000..2A6DF UNKNOWN, // 2A6E0..2A6FF - HAN, // 2A700..2B738 - UNKNOWN, // 2B739..2B73F + HAN, // 2A700..2B739 + UNKNOWN, // 2B73A..2B73F HAN, // 2B740..2B81D UNKNOWN, // 2B81E..2B81F HAN, // 2B820..2CEA1 @@ -8560,7 +8690,9 @@ class Character implements java.io.Serializable, Comparable, Constabl HAN, // 2F800..2FA1D UNKNOWN, // 2FA1E..2FFFF HAN, // 30000..3134A - UNKNOWN, // 3134B..E0000 + UNKNOWN, // 3134B..3134F + HAN, // 31350..323AF + UNKNOWN, // 323B0..E0000 COMMON, // E0001 UNKNOWN, // E0002..E001F COMMON, // E0020..E007F @@ -8611,9 +8743,9 @@ class Character implements java.io.Serializable, Comparable, Constabl aliases.put("ETHI", ETHIOPIC); aliases.put("GEOR", GEORGIAN); aliases.put("GLAG", GLAGOLITIC); + aliases.put("GONG", GUNJALA_GONDI); aliases.put("GONM", MASARAM_GONDI); aliases.put("GOTH", GOTHIC); - aliases.put("GONG", GUNJALA_GONDI); aliases.put("GRAN", GRANTHA); aliases.put("GREK", GREEK); aliases.put("GUJR", GUJARATI); @@ -8627,13 +8759,12 @@ class Character implements java.io.Serializable, Comparable, Constabl aliases.put("HLUW", ANATOLIAN_HIEROGLYPHS); aliases.put("HMNG", PAHAWH_HMONG); aliases.put("HMNP", NYIAKENG_PUACHUE_HMONG); - // it appears we don't have the KATAKANA_OR_HIRAGANA - //aliases.put("HRKT", KATAKANA_OR_HIRAGANA); aliases.put("HUNG", OLD_HUNGARIAN); aliases.put("ITAL", OLD_ITALIC); aliases.put("JAVA", JAVANESE); aliases.put("KALI", KAYAH_LI); aliases.put("KANA", KATAKANA); + aliases.put("KAWI", KAWI); aliases.put("KHAR", KHAROSHTHI); aliases.put("KHMR", KHMER); aliases.put("KHOJ", KHOJKI); @@ -8652,9 +8783,9 @@ class Character implements java.io.Serializable, Comparable, Constabl aliases.put("LYDI", LYDIAN); aliases.put("MAHJ", MAHAJANI); aliases.put("MAKA", MAKASAR); - aliases.put("MARC", MARCHEN); aliases.put("MAND", MANDAIC); aliases.put("MANI", MANICHAEAN); + aliases.put("MARC", MARCHEN); aliases.put("MEDF", MEDEFAIDRIN); aliases.put("MEND", MENDE_KIKAKUI); aliases.put("MERC", MEROITIC_CURSIVE); @@ -8666,6 +8797,7 @@ class Character implements java.io.Serializable, Comparable, Constabl aliases.put("MTEI", MEETEI_MAYEK); aliases.put("MULT", MULTANI); aliases.put("MYMR", MYANMAR); + aliases.put("NAGM", NAG_MUNDARI); aliases.put("NAND", NANDINAGARI); aliases.put("NARB", OLD_NORTH_ARABIAN); aliases.put("NBAT", NABATAEAN); @@ -8730,8 +8862,8 @@ class Character implements java.io.Serializable, Comparable, Constabl aliases.put("WCHO", WANCHO); aliases.put("XPEO", OLD_PERSIAN); aliases.put("XSUX", CUNEIFORM); - aliases.put("YIII", YI); aliases.put("YEZI", YEZIDI); + aliases.put("YIII", YI); aliases.put("ZANB", ZANABAZAR_SQUARE); aliases.put("ZINH", INHERITED); aliases.put("ZYYY", COMMON); diff --git a/src/java.base/share/classes/jdk/internal/icu/impl/NormalizerImpl.java b/src/java.base/share/classes/jdk/internal/icu/impl/NormalizerImpl.java index c1530c18001..291653f9995 100644 --- a/src/java.base/share/classes/jdk/internal/icu/impl/NormalizerImpl.java +++ b/src/java.base/share/classes/jdk/internal/icu/impl/NormalizerImpl.java @@ -1,5 +1,5 @@ /* - * Copyright (c) 2009, 2020, Oracle and/or its affiliates. All rights reserved. + * Copyright (c) 2009, 2022, Oracle and/or its affiliates. All rights reserved. * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. * * This code is free software; you can redistribute it and/or modify it @@ -25,7 +25,7 @@ /* ******************************************************************************* - * Copyright (C) 2009-2014, International Business Machines + * Copyright (C) 2009-2015, International Business Machines * Corporation and others. All Rights Reserved. ******************************************************************************* */ @@ -556,8 +556,8 @@ public final class NormalizerImpl { public static final int MIN_YES_YES_WITH_CC=0xfe02; public static final int JAMO_VT=0xfe00; public static final int MIN_NORMAL_MAYBE_YES=0xfc00; - public static final int JAMO_L=2; // offset=1 hasCompBoundaryAfter=FALSE - public static final int INERT=1; // offset=0 hasCompBoundaryAfter=TRUE + public static final int JAMO_L=2; // offset=1 hasCompBoundaryAfter=false + public static final int INERT=1; // offset=0 hasCompBoundaryAfter=true // norm16 bit 0 is comp-boundary-after. public static final int HAS_COMP_BOUNDARY_AFTER=1; diff --git a/src/java.base/share/classes/jdk/internal/icu/impl/Utility.java b/src/java.base/share/classes/jdk/internal/icu/impl/Utility.java index 98f757ab75c..62c6c5a77ba 100644 --- a/src/java.base/share/classes/jdk/internal/icu/impl/Utility.java +++ b/src/java.base/share/classes/jdk/internal/icu/impl/Utility.java @@ -1,5 +1,5 @@ /* - * Copyright (c) 2005, 2020, Oracle and/or its affiliates. All rights reserved. + * Copyright (c) 2005, 2022, Oracle and/or its affiliates. All rights reserved. * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. * * This code is free software; you can redistribute it and/or modify it @@ -24,7 +24,7 @@ */ /* ******************************************************************************* - * Copyright (C) 1996-2011, International Business Machines Corporation and * + * Copyright (C) 1996-2015, International Business Machines Corporation and * * others. All Rights Reserved. * ******************************************************************************* */ @@ -246,8 +246,8 @@ public final class Utility { * Escape unprintable characters using uxxxx notation * for U+0000 to U+FFFF and Uxxxxxxxx for U+10000 and * above. If the character is printable ASCII, then do nothing - * and return FALSE. Otherwise, append the escaped notation and - * return TRUE. + * and return false. Otherwise, append the escaped notation and + * return true. */ public static boolean escapeUnprintable(T result, int c) { try { diff --git a/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt70b/nfc.nrm b/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt70b/nfc.nrm deleted file mode 100644 index b42accf8ad1..00000000000 Binary files a/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt70b/nfc.nrm and /dev/null differ diff --git a/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt70b/nfkc.nrm b/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt70b/nfkc.nrm deleted file mode 100644 index 450b6ed323b..00000000000 Binary files a/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt70b/nfkc.nrm and /dev/null differ diff --git a/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt70b/uprops.icu b/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt70b/uprops.icu deleted file mode 100644 index 335caa93cc2..00000000000 Binary files a/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt70b/uprops.icu and /dev/null differ diff --git a/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt72b/nfc.nrm b/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt72b/nfc.nrm new file mode 100644 index 00000000000..2b0e972807e Binary files /dev/null and b/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt72b/nfc.nrm differ diff --git a/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt72b/nfkc.nrm b/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt72b/nfkc.nrm new file mode 100644 index 00000000000..c97c70276d3 Binary files /dev/null and b/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt72b/nfkc.nrm differ diff --git a/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt70b/ubidi.icu b/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt72b/ubidi.icu similarity index 75% rename from src/java.base/share/classes/jdk/internal/icu/impl/data/icudt70b/ubidi.icu rename to src/java.base/share/classes/jdk/internal/icu/impl/data/icudt72b/ubidi.icu index b125866b8e2..cfde07406cc 100644 Binary files a/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt70b/ubidi.icu and b/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt72b/ubidi.icu differ diff --git a/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt72b/uprops.icu b/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt72b/uprops.icu new file mode 100644 index 00000000000..31b3864d689 Binary files /dev/null and b/src/java.base/share/classes/jdk/internal/icu/impl/data/icudt72b/uprops.icu differ diff --git a/src/java.base/share/classes/jdk/internal/icu/text/BidiLine.java b/src/java.base/share/classes/jdk/internal/icu/text/BidiLine.java index d8fa4f61fa4..54c7e9de32f 100644 --- a/src/java.base/share/classes/jdk/internal/icu/text/BidiLine.java +++ b/src/java.base/share/classes/jdk/internal/icu/text/BidiLine.java @@ -117,7 +117,7 @@ final class BidiLine { are already set to paragraph level. Setting trailingWSStart to pBidi->length will avoid changing the level of B chars from 0 to paraLevel in getLevels when - orderParagraphsLTR==TRUE + orderParagraphsLTR==true */ if (dirProps[start - 1] == BidiBase.B) { bidiBase.trailingWSStart = start; /* currently == bidiBase.length */ diff --git a/src/java.base/share/classes/jdk/internal/icu/util/VersionInfo.java b/src/java.base/share/classes/jdk/internal/icu/util/VersionInfo.java index 799d570e2aa..b270124c980 100644 --- a/src/java.base/share/classes/jdk/internal/icu/util/VersionInfo.java +++ b/src/java.base/share/classes/jdk/internal/icu/util/VersionInfo.java @@ -54,7 +54,7 @@ public final class VersionInfo * @deprecated This API is ICU internal only. */ @Deprecated - public static final String ICU_DATA_VERSION_PATH = "70b"; + public static final String ICU_DATA_VERSION_PATH = "72b"; // public methods ------------------------------------------------------ diff --git a/src/java.base/share/classes/jdk/internal/util/regex/Grapheme.java b/src/java.base/share/classes/jdk/internal/util/regex/Grapheme.java index 38c062ab89f..8fc9c1eaac5 100644 --- a/src/java.base/share/classes/jdk/internal/util/regex/Grapheme.java +++ b/src/java.base/share/classes/jdk/internal/util/regex/Grapheme.java @@ -35,8 +35,8 @@ public final class Grapheme { *

* See Unicode Standard Annex #29 Unicode Text Segmentation for the specification * for the extended grapheme cluster boundary rules. The following implementation - * is based on the annex for Unicode version 14.0. - * (http://www.unicode.org/reports/tr29/tr29-38.html) + * is based on the annex for Unicode version 15.0. + * (http://www.unicode.org/reports/tr29/tr29-40.html) * * @param src the {@code CharSequence} to be scanned * @param off offset to start looking for the next boundary in the src @@ -277,6 +277,7 @@ public final class Grapheme { case 0x11A88: case 0x11A89: case 0x11D46: + case 0x11F02: return PREPEND; } } diff --git a/src/java.base/share/data/unicodedata/Blocks.txt b/src/java.base/share/data/unicodedata/Blocks.txt index d3c73191e76..fbcf4526e5f 100644 --- a/src/java.base/share/data/unicodedata/Blocks.txt +++ b/src/java.base/share/data/unicodedata/Blocks.txt @@ -1,10 +1,10 @@ -# Blocks-14.0.0.txt -# Date: 2021-01-22, 23:29:00 GMT [KW] -# Copyright (c) 2021 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html +# Blocks-15.0.0.txt +# Date: 2022-01-28, 20:58:00 GMT [KW] +# Copyright (c) 2022 Unicode, Inc. +# For terms of use, see https://www.unicode.org/terms_of_use.html # # Unicode Character Database -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see https://www.unicode.org/reports/tr44/ # # Format: # Start Code..End Code; Block Name @@ -15,7 +15,7 @@ # and underbars are ignored. # For example, "Latin Extended-A" and "latin extended a" are equivalent. # For more information on the comparison of property values, -# see UAX #44: http://www.unicode.org/reports/tr44/ +# see UAX #44: https://www.unicode.org/reports/tr44/ # # All block ranges start with a value where (cp MOD 16) = 0, # and end with a value where (cp MOD 16) = 15. In other words, @@ -241,6 +241,7 @@ FFF0..FFFF; Specials 10D00..10D3F; Hanifi Rohingya 10E60..10E7F; Rumi Numeral Symbols 10E80..10EBF; Yezidi +10EC0..10EFF; Arabic Extended-C 10F00..10F2F; Old Sogdian 10F30..10F6F; Sogdian 10F70..10FAF; Old Uyghur @@ -272,11 +273,13 @@ FFF0..FFFF; Specials 11A50..11AAF; Soyombo 11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A 11AC0..11AFF; Pau Cin Hau +11B00..11B5F; Devanagari Extended-A 11C00..11C6F; Bhaiksuki 11C70..11CBF; Marchen 11D00..11D5F; Masaram Gondi 11D60..11DAF; Gunjala Gondi 11EE0..11EFF; Makasar +11F00..11F5F; Kawi 11FB0..11FBF; Lisu Supplement 11FC0..11FFF; Tamil Supplement 12000..123FF; Cuneiform @@ -284,7 +287,7 @@ FFF0..FFFF; Specials 12480..1254F; Early Dynastic Cuneiform 12F90..12FFF; Cypro-Minoan 13000..1342F; Egyptian Hieroglyphs -13430..1343F; Egyptian Hieroglyph Format Controls +13430..1345F; Egyptian Hieroglyph Format Controls 14400..1467F; Anatolian Hieroglyphs 16800..16A3F; Bamum Supplement 16A40..16A6F; Mro @@ -309,6 +312,7 @@ FFF0..FFFF; Specials 1D000..1D0FF; Byzantine Musical Symbols 1D100..1D1FF; Musical Symbols 1D200..1D24F; Ancient Greek Musical Notation +1D2C0..1D2DF; Kaktovik Numerals 1D2E0..1D2FF; Mayan Numerals 1D300..1D35F; Tai Xuan Jing Symbols 1D360..1D37F; Counting Rod Numerals @@ -316,9 +320,11 @@ FFF0..FFFF; Specials 1D800..1DAAF; Sutton SignWriting 1DF00..1DFFF; Latin Extended-G 1E000..1E02F; Glagolitic Supplement +1E030..1E08F; Cyrillic Extended-D 1E100..1E14F; Nyiakeng Puachue Hmong 1E290..1E2BF; Toto 1E2C0..1E2FF; Wancho +1E4D0..1E4FF; Nag Mundari 1E7E0..1E7FF; Ethiopic Extended-B 1E800..1E8DF; Mende Kikakui 1E900..1E95F; Adlam @@ -348,6 +354,7 @@ FFF0..FFFF; Specials 2CEB0..2EBEF; CJK Unified Ideographs Extension F 2F800..2FA1F; CJK Compatibility Ideographs Supplement 30000..3134F; CJK Unified Ideographs Extension G +31350..323AF; CJK Unified Ideographs Extension H E0000..E007F; Tags E0100..E01EF; Variation Selectors Supplement F0000..FFFFF; Supplementary Private Use Area-A diff --git a/src/java.base/share/data/unicodedata/DerivedCoreProperties.txt b/src/java.base/share/data/unicodedata/DerivedCoreProperties.txt index 2fb971d7ff5..03059d68e7b 100644 --- a/src/java.base/share/data/unicodedata/DerivedCoreProperties.txt +++ b/src/java.base/share/data/unicodedata/DerivedCoreProperties.txt @@ -1,11 +1,11 @@ -# DerivedCoreProperties-14.0.0.txt -# Date: 2021-08-12, 23:12:53 GMT -# Copyright (c) 2021 Unicode, Inc. +# DerivedCoreProperties-15.0.0.txt +# Date: 2022-08-05, 22:17:05 GMT +# Copyright (c) 2022 Unicode, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. -# For terms of use, see http://www.unicode.org/terms_of_use.html +# For terms of use, see https://www.unicode.org/terms_of_use.html # # Unicode Character Database -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see https://www.unicode.org/reports/tr44/ # ================================================ @@ -462,6 +462,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0BD7 ; Alphabetic # Mc TAMIL AU LENGTH MARK 0C00 ; Alphabetic # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE 0C01..0C03 ; Alphabetic # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA +0C04 ; Alphabetic # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE 0C05..0C0C ; Alphabetic # Lo [8] TELUGU LETTER A..TELUGU LETTER VOCALIC L 0C0E..0C10 ; Alphabetic # Lo [3] TELUGU LETTER E..TELUGU LETTER AI 0C12..0C28 ; Alphabetic # Lo [23] TELUGU LETTER O..TELUGU LETTER NA @@ -497,6 +498,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0CE0..0CE1 ; Alphabetic # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; Alphabetic # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CF1..0CF2 ; Alphabetic # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA +0CF3 ; Alphabetic # Mc KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT 0D00..0D01 ; Alphabetic # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; Alphabetic # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D04..0D0C ; Alphabetic # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -552,7 +554,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0F49..0F6C ; Alphabetic # Lo [36] TIBETAN LETTER NYA..TIBETAN LETTER RRA 0F71..0F7E ; Alphabetic # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO 0F7F ; Alphabetic # Mc TIBETAN SIGN RNAM BCAD -0F80..0F81 ; Alphabetic # Mn [2] TIBETAN VOWEL SIGN REVERSED I..TIBETAN VOWEL SIGN REVERSED II +0F80..0F83 ; Alphabetic # Mn [4] TIBETAN VOWEL SIGN REVERSED I..TIBETAN SIGN SNA LDAN 0F88..0F8C ; Alphabetic # Lo [5] TIBETAN SIGN LCE TSA CAN..TIBETAN SIGN INVERTED MCHU CAN 0F8D..0F97 ; Alphabetic # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA 0F99..0FBC ; Alphabetic # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA @@ -1053,6 +1055,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11071..11072 ; Alphabetic # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O 11073..11074 ; Alphabetic # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O 11075 ; Alphabetic # Lo BRAHMI LETTER OLD TAMIL LLA +11080..11081 ; Alphabetic # Mn [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA 11082 ; Alphabetic # Mc KAITHI SIGN VISARGA 11083..110AF ; Alphabetic # Lo [45] KAITHI LETTER A..KAITHI LETTER HA 110B0..110B2 ; Alphabetic # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II @@ -1089,6 +1092,8 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11234 ; Alphabetic # Mn KHOJKI SIGN ANUSVARA 11237 ; Alphabetic # Mn KHOJKI SIGN SHADDA 1123E ; Alphabetic # Mn KHOJKI SIGN SUKUN +1123F..11240 ; Alphabetic # Lo [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I +11241 ; Alphabetic # Mn KHOJKI VOWEL SIGN VOCALIC R 11280..11286 ; Alphabetic # Lo [7] MULTANI LETTER A..MULTANI LETTER GA 11288 ; Alphabetic # Lo MULTANI LETTER GHA 1128A..1128D ; Alphabetic # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA @@ -1243,12 +1248,22 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11EE0..11EF2 ; Alphabetic # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA 11EF3..11EF4 ; Alphabetic # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U 11EF5..11EF6 ; Alphabetic # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O +11F00..11F01 ; Alphabetic # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA +11F02 ; Alphabetic # Lo KAWI SIGN REPHA +11F03 ; Alphabetic # Mc KAWI SIGN VISARGA +11F04..11F10 ; Alphabetic # Lo [13] KAWI LETTER A..KAWI LETTER O +11F12..11F33 ; Alphabetic # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA +11F34..11F35 ; Alphabetic # Mc [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA +11F36..11F3A ; Alphabetic # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R +11F3E..11F3F ; Alphabetic # Mc [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI +11F40 ; Alphabetic # Mn KAWI VOWEL SIGN EU 11FB0 ; Alphabetic # Lo LISU LETTER YHA 12000..12399 ; Alphabetic # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; Alphabetic # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; Alphabetic # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU 12F90..12FF0 ; Alphabetic # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 -13000..1342E ; Alphabetic # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 +13000..1342F ; Alphabetic # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D +13441..13446 ; Alphabetic # Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN 14400..14646 ; Alphabetic # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; Alphabetic # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; Alphabetic # Lo [31] MRO LETTER TA..MRO LETTER TEK @@ -1275,7 +1290,9 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 1AFF5..1AFFB ; Alphabetic # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; Alphabetic # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000..1B122 ; Alphabetic # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B132 ; Alphabetic # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; Alphabetic # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO +1B155 ; Alphabetic # Lo KATAKANA LETTER SMALL KO 1B164..1B167 ; Alphabetic # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; Alphabetic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; Alphabetic # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M @@ -1316,16 +1333,21 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 1DF00..1DF09 ; Alphabetic # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0A ; Alphabetic # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF1E ; Alphabetic # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL +1DF25..1DF2A ; Alphabetic # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK 1E000..1E006 ; Alphabetic # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; Alphabetic # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; Alphabetic # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI 1E023..1E024 ; Alphabetic # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; Alphabetic # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E030..1E06D ; Alphabetic # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE +1E08F ; Alphabetic # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I 1E100..1E12C ; Alphabetic # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; Alphabetic # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E14E ; Alphabetic # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ 1E290..1E2AD ; Alphabetic # Lo [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; Alphabetic # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH +1E4D0..1E4EA ; Alphabetic # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL +1E4EB ; Alphabetic # Lm NAG MUNDARI SIGN OJOD 1E7E0..1E7E6 ; Alphabetic # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; Alphabetic # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; Alphabetic # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -1371,14 +1393,15 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 1F150..1F169 ; Alphabetic # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Alphabetic # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z 20000..2A6DF ; Alphabetic # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF -2A700..2B738 ; Alphabetic # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 +2A700..2B739 ; Alphabetic # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 2B740..2B81D ; Alphabetic # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Alphabetic # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; Alphabetic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; Alphabetic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A +31350..323AF ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 133396 +# Total code points: 137765 # ================================================ @@ -1663,6 +1686,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 052F ; Lowercase # L& CYRILLIC SMALL LETTER EL WITH DESCENDER 0560..0588 ; Lowercase # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE 10D0..10FA ; Lowercase # L& [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN +10FC ; Lowercase # Lm MODIFIER LETTER GEORGIAN NAR 10FD..10FF ; Lowercase # L& [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN 13F8..13FD ; Lowercase # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV 1C80..1C88 ; Lowercase # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK @@ -2012,12 +2036,14 @@ A7D3 ; Lowercase # L& LATIN SMALL LETTER DOUBLE THORN A7D5 ; Lowercase # L& LATIN SMALL LETTER DOUBLE WYNN A7D7 ; Lowercase # L& LATIN SMALL LETTER MIDDLE SCOTS S A7D9 ; Lowercase # L& LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; Lowercase # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F6 ; Lowercase # L& LATIN SMALL LETTER REVERSED HALF H A7F8..A7F9 ; Lowercase # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; Lowercase # L& LATIN LETTER SMALL CAPITAL TURNED M AB30..AB5A ; Lowercase # L& [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG AB5C..AB5F ; Lowercase # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK AB60..AB68 ; Lowercase # L& [9] LATIN SMALL LETTER SAKHA YAT..LATIN SMALL LETTER TURNED R WITH MIDDLE TILDE +AB69 ; Lowercase # Lm MODIFIER LETTER SMALL TURNED W AB70..ABBF ; Lowercase # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA FB00..FB06 ; Lowercase # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST FB13..FB17 ; Lowercase # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH @@ -2065,9 +2091,11 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 1D7CB ; Lowercase # L& MATHEMATICAL BOLD SMALL DIGAMMA 1DF00..1DF09 ; Lowercase # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0B..1DF1E ; Lowercase # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL +1DF25..1DF2A ; Lowercase # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1E030..1E06D ; Lowercase # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E922..1E943 ; Lowercase # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2471 +# Total code points: 2544 # ================================================ @@ -2767,6 +2795,7 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH 10C7 ; Cased # L& GEORGIAN CAPITAL LETTER YN 10CD ; Cased # L& GEORGIAN CAPITAL LETTER AEN 10D0..10FA ; Cased # L& [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN +10FC ; Cased # Lm MODIFIER LETTER GEORGIAN NAR 10FD..10FF ; Cased # L& [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN 13A0..13F5 ; Cased # L& [86] CHEROKEE LETTER A..CHEROKEE LETTER MV 13F8..13FD ; Cased # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV @@ -2837,12 +2866,14 @@ A790..A7CA ; Cased # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SM A7D0..A7D1 ; Cased # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; Cased # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7D9 ; Cased # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; Cased # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Cased # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F8..A7F9 ; Cased # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; Cased # L& LATIN LETTER SMALL CAPITAL TURNED M AB30..AB5A ; Cased # L& [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG AB5C..AB5F ; Cased # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK AB60..AB68 ; Cased # L& [9] LATIN SMALL LETTER SAKHA YAT..LATIN SMALL LETTER TURNED R WITH MIDDLE TILDE +AB69 ; Cased # Lm MODIFIER LETTER SMALL TURNED W AB70..ABBF ; Cased # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA FB00..FB06 ; Cased # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST FB13..FB17 ; Cased # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH @@ -2899,12 +2930,14 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1D7C4..1D7CB ; Cased # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA 1DF00..1DF09 ; Cased # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0B..1DF1E ; Cased # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL +1DF25..1DF2A ; Cased # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1E030..1E06D ; Cased # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E900..1E943 ; Cased # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1F130..1F149 ; Cased # So [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z 1F150..1F169 ; Cased # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Cased # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 4453 +# Total code points: 4526 # ================================================ @@ -3054,7 +3087,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 0EB1 ; Case_Ignorable # Mn LAO VOWEL SIGN MAI KAN 0EB4..0EBC ; Case_Ignorable # Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO 0EC6 ; Case_Ignorable # Lm LAO KO LA -0EC8..0ECD ; Case_Ignorable # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0EC8..0ECE ; Case_Ignorable # Mn [7] LAO TONE MAI EK..LAO YAMAKKAN 0F18..0F19 ; Case_Ignorable # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS 0F35 ; Case_Ignorable # Mn TIBETAN MARK NGAS BZUNG NYI ZLA 0F37 ; Case_Ignorable # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS @@ -3263,6 +3296,7 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 10AE5..10AE6 ; Case_Ignorable # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW 10D24..10D27 ; Case_Ignorable # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10EAB..10EAC ; Case_Ignorable # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK +10EFD..10EFF ; Case_Ignorable # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Case_Ignorable # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; Case_Ignorable # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; Case_Ignorable # Mn BRAHMI SIGN ANUSVARA @@ -3287,6 +3321,7 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 11234 ; Case_Ignorable # Mn KHOJKI SIGN ANUSVARA 11236..11237 ; Case_Ignorable # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA 1123E ; Case_Ignorable # Mn KHOJKI SIGN SUKUN +11241 ; Case_Ignorable # Mn KHOJKI VOWEL SIGN VOCALIC R 112DF ; Case_Ignorable # Mn KHUDAWADI SIGN ANUSVARA 112E3..112EA ; Case_Ignorable # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA 11300..11301 ; Case_Ignorable # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU @@ -3348,7 +3383,13 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 11D95 ; Case_Ignorable # Mn GUNJALA GONDI SIGN ANUSVARA 11D97 ; Case_Ignorable # Mn GUNJALA GONDI VIRAMA 11EF3..11EF4 ; Case_Ignorable # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U -13430..13438 ; Case_Ignorable # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT +11F00..11F01 ; Case_Ignorable # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA +11F36..11F3A ; Case_Ignorable # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R +11F40 ; Case_Ignorable # Mn KAWI VOWEL SIGN EU +11F42 ; Case_Ignorable # Mn KAWI CONJOINER +13430..1343F ; Case_Ignorable # Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE +13440 ; Case_Ignorable # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY +13447..13455 ; Case_Ignorable # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED 16AF0..16AF4 ; Case_Ignorable # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Case_Ignorable # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16B40..16B43 ; Case_Ignorable # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM @@ -3382,10 +3423,14 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 1E01B..1E021 ; Case_Ignorable # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI 1E023..1E024 ; Case_Ignorable # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; Case_Ignorable # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E030..1E06D ; Case_Ignorable # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE +1E08F ; Case_Ignorable # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I 1E130..1E136 ; Case_Ignorable # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D 1E137..1E13D ; Case_Ignorable # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E2AE ; Case_Ignorable # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; Case_Ignorable # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI +1E4EB ; Case_Ignorable # Lm NAG MUNDARI SIGN OJOD +1E4EC..1E4EF ; Case_Ignorable # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH 1E8D0..1E8D6 ; Case_Ignorable # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Case_Ignorable # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA 1E94B ; Case_Ignorable # Lm ADLAM NASALIZATION MARK @@ -3394,7 +3439,7 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2602 +# Total code points: 2707 # ================================================ @@ -6617,6 +6662,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 111DC ; ID_Start # Lo SHARADA HEADSTROKE 11200..11211 ; ID_Start # Lo [18] KHOJKI LETTER A..KHOJKI LETTER JJA 11213..1122B ; ID_Start # Lo [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA +1123F..11240 ; ID_Start # Lo [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I 11280..11286 ; ID_Start # Lo [7] MULTANI LETTER A..MULTANI LETTER GA 11288 ; ID_Start # Lo MULTANI LETTER GHA 1128A..1128D ; ID_Start # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA @@ -6679,12 +6725,16 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11D6A..11D89 ; ID_Start # Lo [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA 11D98 ; ID_Start # Lo GUNJALA GONDI OM 11EE0..11EF2 ; ID_Start # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA +11F02 ; ID_Start # Lo KAWI SIGN REPHA +11F04..11F10 ; ID_Start # Lo [13] KAWI LETTER A..KAWI LETTER O +11F12..11F33 ; ID_Start # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA 11FB0 ; ID_Start # Lo LISU LETTER YHA 12000..12399 ; ID_Start # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; ID_Start # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; ID_Start # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU 12F90..12FF0 ; ID_Start # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 -13000..1342E ; ID_Start # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 +13000..1342F ; ID_Start # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D +13441..13446 ; ID_Start # Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN 14400..14646 ; ID_Start # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; ID_Start # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; ID_Start # Lo [31] MRO LETTER TA..MRO LETTER TEK @@ -6707,7 +6757,9 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1AFF5..1AFFB ; ID_Start # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; ID_Start # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000..1B122 ; ID_Start # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B132 ; ID_Start # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; ID_Start # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO +1B155 ; ID_Start # Lo KATAKANA LETTER SMALL KO 1B164..1B167 ; ID_Start # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; ID_Start # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; ID_Start # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M @@ -6747,11 +6799,15 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1DF00..1DF09 ; ID_Start # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0A ; ID_Start # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF1E ; ID_Start # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL +1DF25..1DF2A ; ID_Start # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1E030..1E06D ; ID_Start # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E100..1E12C ; ID_Start # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; ID_Start # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E14E ; ID_Start # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ 1E290..1E2AD ; ID_Start # Lo [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; ID_Start # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH +1E4D0..1E4EA ; ID_Start # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL +1E4EB ; ID_Start # Lm NAG MUNDARI SIGN OJOD 1E7E0..1E7E6 ; ID_Start # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; ID_Start # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; ID_Start # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -6793,14 +6849,15 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1EEA5..1EEA9 ; ID_Start # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; ID_Start # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 20000..2A6DF ; ID_Start # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF -2A700..2B738 ; ID_Start # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 +2A700..2B739 ; ID_Start # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 2B740..2B81D ; ID_Start # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; ID_Start # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; ID_Start # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; ID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A +31350..323AF ; ID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 131997 +# Total code points: 136345 # ================================================ @@ -7083,6 +7140,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0CE2..0CE3 ; ID_Continue # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; ID_Continue # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2 ; ID_Continue # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA +0CF3 ; ID_Continue # Mc KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT 0D00..0D01 ; ID_Continue # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; ID_Continue # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D04..0D0C ; ID_Continue # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -7136,7 +7194,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0EBD ; ID_Continue # Lo LAO SEMIVOWEL SIGN NYO 0EC0..0EC4 ; ID_Continue # Lo [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI 0EC6 ; ID_Continue # Lm LAO KO LA -0EC8..0ECD ; ID_Continue # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0EC8..0ECE ; ID_Continue # Mn [7] LAO TONE MAI EK..LAO YAMAKKAN 0ED0..0ED9 ; ID_Continue # Nd [10] LAO DIGIT ZERO..LAO DIGIT NINE 0EDC..0EDF ; ID_Continue # Lo [4] LAO HO NO..LAO LETTER KHMU NYO 0F00 ; ID_Continue # Lo TIBETAN SYLLABLE OM @@ -7719,6 +7777,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 10E80..10EA9 ; ID_Continue # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EAB..10EAC ; ID_Continue # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EB0..10EB1 ; ID_Continue # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE +10EFD..10EFF ; ID_Continue # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; ID_Continue # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ID_Continue # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -7781,6 +7840,8 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11235 ; ID_Continue # Mc KHOJKI SIGN VIRAMA 11236..11237 ; ID_Continue # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA 1123E ; ID_Continue # Mn KHOJKI SIGN SUKUN +1123F..11240 ; ID_Continue # Lo [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I +11241 ; ID_Continue # Mn KHOJKI VOWEL SIGN VOCALIC R 11280..11286 ; ID_Continue # Lo [7] MULTANI LETTER A..MULTANI LETTER GA 11288 ; ID_Continue # Lo MULTANI LETTER GHA 1128A..1128D ; ID_Continue # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA @@ -7963,12 +8024,27 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11EE0..11EF2 ; ID_Continue # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA 11EF3..11EF4 ; ID_Continue # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U 11EF5..11EF6 ; ID_Continue # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O +11F00..11F01 ; ID_Continue # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA +11F02 ; ID_Continue # Lo KAWI SIGN REPHA +11F03 ; ID_Continue # Mc KAWI SIGN VISARGA +11F04..11F10 ; ID_Continue # Lo [13] KAWI LETTER A..KAWI LETTER O +11F12..11F33 ; ID_Continue # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA +11F34..11F35 ; ID_Continue # Mc [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA +11F36..11F3A ; ID_Continue # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R +11F3E..11F3F ; ID_Continue # Mc [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI +11F40 ; ID_Continue # Mn KAWI VOWEL SIGN EU +11F41 ; ID_Continue # Mc KAWI SIGN KILLER +11F42 ; ID_Continue # Mn KAWI CONJOINER +11F50..11F59 ; ID_Continue # Nd [10] KAWI DIGIT ZERO..KAWI DIGIT NINE 11FB0 ; ID_Continue # Lo LISU LETTER YHA 12000..12399 ; ID_Continue # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; ID_Continue # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; ID_Continue # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU 12F90..12FF0 ; ID_Continue # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 -13000..1342E ; ID_Continue # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 +13000..1342F ; ID_Continue # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D +13440 ; ID_Continue # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY +13441..13446 ; ID_Continue # Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN +13447..13455 ; ID_Continue # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED 14400..14646 ; ID_Continue # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; ID_Continue # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; ID_Continue # Lo [31] MRO LETTER TA..MRO LETTER TEK @@ -8001,7 +8077,9 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1AFF5..1AFFB ; ID_Continue # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; ID_Continue # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000..1B122 ; ID_Continue # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B132 ; ID_Continue # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; ID_Continue # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO +1B155 ; ID_Continue # Lo KATAKANA LETTER SMALL KO 1B164..1B167 ; ID_Continue # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; ID_Continue # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; ID_Continue # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M @@ -8058,11 +8136,14 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1DF00..1DF09 ; ID_Continue # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0A ; ID_Continue # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF1E ; ID_Continue # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL +1DF25..1DF2A ; ID_Continue # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK 1E000..1E006 ; ID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; ID_Continue # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; ID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI 1E023..1E024 ; ID_Continue # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; ID_Continue # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E030..1E06D ; ID_Continue # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE +1E08F ; ID_Continue # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I 1E100..1E12C ; ID_Continue # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E130..1E136 ; ID_Continue # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D 1E137..1E13D ; ID_Continue # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER @@ -8073,6 +8154,10 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1E2C0..1E2EB ; ID_Continue # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E2EC..1E2EF ; ID_Continue # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E2F0..1E2F9 ; ID_Continue # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE +1E4D0..1E4EA ; ID_Continue # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL +1E4EB ; ID_Continue # Lm NAG MUNDARI SIGN OJOD +1E4EC..1E4EF ; ID_Continue # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH +1E4F0..1E4F9 ; ID_Continue # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE 1E7E0..1E7E6 ; ID_Continue # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; ID_Continue # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; ID_Continue # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -8118,15 +8203,16 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1EEAB..1EEBB ; ID_Continue # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1FBF0..1FBF9 ; ID_Continue # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE 20000..2A6DF ; ID_Continue # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF -2A700..2B738 ; ID_Continue # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 +2A700..2B739 ; ID_Continue # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 2B740..2B81D ; ID_Continue # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; ID_Continue # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; ID_Continue # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; ID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; ID_Continue # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A +31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 135072 +# Total code points: 139482 # ================================================ @@ -8685,6 +8771,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 111DC ; XID_Start # Lo SHARADA HEADSTROKE 11200..11211 ; XID_Start # Lo [18] KHOJKI LETTER A..KHOJKI LETTER JJA 11213..1122B ; XID_Start # Lo [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA +1123F..11240 ; XID_Start # Lo [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I 11280..11286 ; XID_Start # Lo [7] MULTANI LETTER A..MULTANI LETTER GA 11288 ; XID_Start # Lo MULTANI LETTER GHA 1128A..1128D ; XID_Start # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA @@ -8747,12 +8834,16 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 11D6A..11D89 ; XID_Start # Lo [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA 11D98 ; XID_Start # Lo GUNJALA GONDI OM 11EE0..11EF2 ; XID_Start # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA +11F02 ; XID_Start # Lo KAWI SIGN REPHA +11F04..11F10 ; XID_Start # Lo [13] KAWI LETTER A..KAWI LETTER O +11F12..11F33 ; XID_Start # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA 11FB0 ; XID_Start # Lo LISU LETTER YHA 12000..12399 ; XID_Start # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; XID_Start # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; XID_Start # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU 12F90..12FF0 ; XID_Start # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 -13000..1342E ; XID_Start # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 +13000..1342F ; XID_Start # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D +13441..13446 ; XID_Start # Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN 14400..14646 ; XID_Start # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; XID_Start # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; XID_Start # Lo [31] MRO LETTER TA..MRO LETTER TEK @@ -8775,7 +8866,9 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1AFF5..1AFFB ; XID_Start # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; XID_Start # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000..1B122 ; XID_Start # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B132 ; XID_Start # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; XID_Start # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO +1B155 ; XID_Start # Lo KATAKANA LETTER SMALL KO 1B164..1B167 ; XID_Start # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; XID_Start # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; XID_Start # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M @@ -8815,11 +8908,15 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1DF00..1DF09 ; XID_Start # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0A ; XID_Start # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF1E ; XID_Start # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL +1DF25..1DF2A ; XID_Start # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1E030..1E06D ; XID_Start # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E100..1E12C ; XID_Start # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; XID_Start # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E14E ; XID_Start # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ 1E290..1E2AD ; XID_Start # Lo [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; XID_Start # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH +1E4D0..1E4EA ; XID_Start # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL +1E4EB ; XID_Start # Lm NAG MUNDARI SIGN OJOD 1E7E0..1E7E6 ; XID_Start # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; XID_Start # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; XID_Start # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -8861,14 +8958,15 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1EEA5..1EEA9 ; XID_Start # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; XID_Start # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 20000..2A6DF ; XID_Start # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF -2A700..2B738 ; XID_Start # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 +2A700..2B739 ; XID_Start # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 2B740..2B81D ; XID_Start # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; XID_Start # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; XID_Start # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; XID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A +31350..323AF ; XID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 131974 +# Total code points: 136322 # ================================================ @@ -9147,6 +9245,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0CE2..0CE3 ; XID_Continue # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; XID_Continue # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2 ; XID_Continue # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA +0CF3 ; XID_Continue # Mc KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT 0D00..0D01 ; XID_Continue # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; XID_Continue # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D04..0D0C ; XID_Continue # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -9200,7 +9299,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0EBD ; XID_Continue # Lo LAO SEMIVOWEL SIGN NYO 0EC0..0EC4 ; XID_Continue # Lo [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI 0EC6 ; XID_Continue # Lm LAO KO LA -0EC8..0ECD ; XID_Continue # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0EC8..0ECE ; XID_Continue # Mn [7] LAO TONE MAI EK..LAO YAMAKKAN 0ED0..0ED9 ; XID_Continue # Nd [10] LAO DIGIT ZERO..LAO DIGIT NINE 0EDC..0EDF ; XID_Continue # Lo [4] LAO HO NO..LAO LETTER KHMU NYO 0F00 ; XID_Continue # Lo TIBETAN SYLLABLE OM @@ -9788,6 +9887,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 10E80..10EA9 ; XID_Continue # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EAB..10EAC ; XID_Continue # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EB0..10EB1 ; XID_Continue # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE +10EFD..10EFF ; XID_Continue # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; XID_Continue # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; XID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; XID_Continue # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -9850,6 +9950,8 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11235 ; XID_Continue # Mc KHOJKI SIGN VIRAMA 11236..11237 ; XID_Continue # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA 1123E ; XID_Continue # Mn KHOJKI SIGN SUKUN +1123F..11240 ; XID_Continue # Lo [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I +11241 ; XID_Continue # Mn KHOJKI VOWEL SIGN VOCALIC R 11280..11286 ; XID_Continue # Lo [7] MULTANI LETTER A..MULTANI LETTER GA 11288 ; XID_Continue # Lo MULTANI LETTER GHA 1128A..1128D ; XID_Continue # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA @@ -10032,12 +10134,27 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11EE0..11EF2 ; XID_Continue # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA 11EF3..11EF4 ; XID_Continue # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U 11EF5..11EF6 ; XID_Continue # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O +11F00..11F01 ; XID_Continue # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA +11F02 ; XID_Continue # Lo KAWI SIGN REPHA +11F03 ; XID_Continue # Mc KAWI SIGN VISARGA +11F04..11F10 ; XID_Continue # Lo [13] KAWI LETTER A..KAWI LETTER O +11F12..11F33 ; XID_Continue # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA +11F34..11F35 ; XID_Continue # Mc [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA +11F36..11F3A ; XID_Continue # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R +11F3E..11F3F ; XID_Continue # Mc [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI +11F40 ; XID_Continue # Mn KAWI VOWEL SIGN EU +11F41 ; XID_Continue # Mc KAWI SIGN KILLER +11F42 ; XID_Continue # Mn KAWI CONJOINER +11F50..11F59 ; XID_Continue # Nd [10] KAWI DIGIT ZERO..KAWI DIGIT NINE 11FB0 ; XID_Continue # Lo LISU LETTER YHA 12000..12399 ; XID_Continue # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; XID_Continue # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; XID_Continue # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU 12F90..12FF0 ; XID_Continue # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 -13000..1342E ; XID_Continue # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 +13000..1342F ; XID_Continue # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D +13440 ; XID_Continue # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY +13441..13446 ; XID_Continue # Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN +13447..13455 ; XID_Continue # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED 14400..14646 ; XID_Continue # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; XID_Continue # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; XID_Continue # Lo [31] MRO LETTER TA..MRO LETTER TEK @@ -10070,7 +10187,9 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1AFF5..1AFFB ; XID_Continue # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; XID_Continue # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000..1B122 ; XID_Continue # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B132 ; XID_Continue # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; XID_Continue # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO +1B155 ; XID_Continue # Lo KATAKANA LETTER SMALL KO 1B164..1B167 ; XID_Continue # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; XID_Continue # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; XID_Continue # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M @@ -10127,11 +10246,14 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1DF00..1DF09 ; XID_Continue # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0A ; XID_Continue # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF1E ; XID_Continue # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL +1DF25..1DF2A ; XID_Continue # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK 1E000..1E006 ; XID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; XID_Continue # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; XID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI 1E023..1E024 ; XID_Continue # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; XID_Continue # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E030..1E06D ; XID_Continue # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE +1E08F ; XID_Continue # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I 1E100..1E12C ; XID_Continue # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E130..1E136 ; XID_Continue # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D 1E137..1E13D ; XID_Continue # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER @@ -10142,6 +10264,10 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1E2C0..1E2EB ; XID_Continue # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E2EC..1E2EF ; XID_Continue # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E2F0..1E2F9 ; XID_Continue # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE +1E4D0..1E4EA ; XID_Continue # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL +1E4EB ; XID_Continue # Lm NAG MUNDARI SIGN OJOD +1E4EC..1E4EF ; XID_Continue # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH +1E4F0..1E4F9 ; XID_Continue # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE 1E7E0..1E7E6 ; XID_Continue # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; XID_Continue # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; XID_Continue # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -10187,15 +10313,16 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1EEAB..1EEBB ; XID_Continue # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1FBF0..1FBF9 ; XID_Continue # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE 20000..2A6DF ; XID_Continue # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF -2A700..2B738 ; XID_Continue # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 +2A700..2B739 ; XID_Continue # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 2B740..2B81D ; XID_Continue # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; XID_Continue # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; XID_Continue # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; XID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; XID_Continue # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A +31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 135053 +# Total code points: 139463 # ================================================ @@ -10206,7 +10333,7 @@ E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTO # + Variation_Selector # - White_Space # - FFF9..FFFB (Interlinear annotation format characters) -# - 13430..13438 (Egyptian hieroglyph format characters) +# - 13430..13440 (Egyptian hieroglyph format characters) # - Prepended_Concatenation_Mark (Exceptional format characters that should be visible) 00AD ; Default_Ignorable_Code_Point # Cf SOFT HYPHEN @@ -10351,7 +10478,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] .. # Bidi_Paired_Bracket (bpb) @@ -162,6 +162,7 @@ blk; Ancient_Symbols ; Ancient_Symbols blk; Arabic ; Arabic blk; Arabic_Ext_A ; Arabic_Extended_A blk; Arabic_Ext_B ; Arabic_Extended_B +blk; Arabic_Ext_C ; Arabic_Extended_C blk; Arabic_Math ; Arabic_Mathematical_Alphabetic_Symbols blk; Arabic_PF_A ; Arabic_Presentation_Forms_A ; Arabic_Presentation_Forms-A blk; Arabic_PF_B ; Arabic_Presentation_Forms_B @@ -206,6 +207,7 @@ blk; CJK_Ext_D ; CJK_Unified_Ideographs_Extension_D blk; CJK_Ext_E ; CJK_Unified_Ideographs_Extension_E blk; CJK_Ext_F ; CJK_Unified_Ideographs_Extension_F blk; CJK_Ext_G ; CJK_Unified_Ideographs_Extension_G +blk; CJK_Ext_H ; CJK_Unified_Ideographs_Extension_H blk; CJK_Radicals_Sup ; CJK_Radicals_Supplement blk; CJK_Strokes ; CJK_Strokes blk; CJK_Symbols ; CJK_Symbols_And_Punctuation @@ -223,10 +225,12 @@ blk; Cyrillic ; Cyrillic blk; Cyrillic_Ext_A ; Cyrillic_Extended_A blk; Cyrillic_Ext_B ; Cyrillic_Extended_B blk; Cyrillic_Ext_C ; Cyrillic_Extended_C +blk; Cyrillic_Ext_D ; Cyrillic_Extended_D blk; Cyrillic_Sup ; Cyrillic_Supplement ; Cyrillic_Supplementary blk; Deseret ; Deseret blk; Devanagari ; Devanagari blk; Devanagari_Ext ; Devanagari_Extended +blk; Devanagari_Ext_A ; Devanagari_Extended_A blk; Diacriticals ; Combining_Diacritical_Marks blk; Diacriticals_Ext ; Combining_Diacritical_Marks_Extended blk; Diacriticals_For_Symbols ; Combining_Diacritical_Marks_For_Symbols; Combining_Marks_For_Symbols @@ -288,6 +292,7 @@ blk; Jamo_Ext_A ; Hangul_Jamo_Extended_A blk; Jamo_Ext_B ; Hangul_Jamo_Extended_B blk; Javanese ; Javanese blk; Kaithi ; Kaithi +blk; Kaktovik_Numerals ; Kaktovik_Numerals blk; Kana_Ext_A ; Kana_Extended_A blk; Kana_Ext_B ; Kana_Extended_B blk; Kana_Sup ; Kana_Supplement @@ -296,6 +301,7 @@ blk; Kangxi ; Kangxi_Radicals blk; Kannada ; Kannada blk; Katakana ; Katakana blk; Katakana_Ext ; Katakana_Phonetic_Extensions +blk; Kawi ; Kawi blk; Kayah_Li ; Kayah_Li blk; Kharoshthi ; Kharoshthi blk; Khitan_Small_Script ; Khitan_Small_Script @@ -360,6 +366,7 @@ blk; Myanmar ; Myanmar blk; Myanmar_Ext_A ; Myanmar_Extended_A blk; Myanmar_Ext_B ; Myanmar_Extended_B blk; Nabataean ; Nabataean +blk; Nag_Mundari ; Nag_Mundari blk; Nandinagari ; Nandinagari blk; NB ; No_Block blk; New_Tai_Lue ; New_Tai_Lue @@ -663,7 +670,6 @@ EPres; Y ; Yes ; T # Equivalent_Unified_Ideograph (EqUIdeo) -# @missing: 0000..10FFFF; Equivalent_Unified_Ideograph; # Expands_On_NFC (XO_NFC) @@ -1143,7 +1149,6 @@ NFD_QC; Y ; Yes # NFKC_Casefold (NFKC_CF) -# @missing: 0000..10FFFF; NFKC_Casefold; # NFKC_Quick_Check (NFKC_QC) @@ -1313,6 +1318,7 @@ sc ; Ital ; Old_Italic sc ; Java ; Javanese sc ; Kali ; Kayah_Li sc ; Kana ; Katakana +sc ; Kawi ; Kawi sc ; Khar ; Kharoshthi sc ; Khmr ; Khmer sc ; Khoj ; Khojki @@ -1345,6 +1351,7 @@ sc ; Mroo ; Mro sc ; Mtei ; Meetei_Mayek sc ; Mult ; Multani sc ; Mymr ; Myanmar +sc ; Nagm ; Nag_Mundari sc ; Nand ; Nandinagari sc ; Narb ; Old_North_Arabian sc ; Nbat ; Nabataean @@ -1418,7 +1425,6 @@ sc ; Zzzz ; Unknown # Script_Extensions (scx) -# @missing: 0000..10FFFF; Script_Extensions;