230909.1.1 · 5509479987d4a6b482f1fef7dac29d2afc112dd6
Upgrade to Unicode v15.0.0 (and regnerate accordingly)
reading declarations
Changes to wordproperties.go. All files
@@ -3,11 +3,11 @@ package uniseg // workBreakCodePoints are taken from-// https://www.unicode.org/Public/14.0.0/ucd/auxiliary/WordBreakProperty.txt+// https://www.unicode.org/Public/15.0.0/ucd/auxiliary/WordBreakProperty.txt // and-// https://unicode.org/Public/14.0.0/ucd/emoji/emoji-data.txt+// https://unicode.org/Public/15.0.0/ucd/emoji/emoji-data.txt // ("Extended_Pictographic" only)-// on July 17, 2023. See https://www.unicode.org/license.html for the Unicode+// on September 5, 2023. See https://www.unicode.org/license.html for the Unicode // license agreement. var workBreakCodePoints = [][3]int{ {0x000A, 0x000A, prLF}, // Cc <control-000A>@@ -318,6 +318,7 @@ var workBreakCodePoints = [][3]int{ {0x0CE2, 0x0CE3, prExtend}, // Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL {0x0CE6, 0x0CEF, prNumeric}, // Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE {0x0CF1, 0x0CF2, prALetter}, // Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA+ {0x0CF3, 0x0CF3, prExtend}, // Mc KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT {0x0D00, 0x0D01, prExtend}, // Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU {0x0D02, 0x0D03, prExtend}, // Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA {0x0D04, 0x0D0C, prALetter}, // Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L@@ -357,7 +358,7 @@ var workBreakCodePoints = [][3]int{ {0x0E50, 0x0E59, prNumeric}, // Nd [10] THAI DIGIT ZERO..THAI DIGIT NINE {0x0EB1, 0x0EB1, prExtend}, // Mn LAO VOWEL SIGN MAI KAN {0x0EB4, 0x0EBC, prExtend}, // Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO- {0x0EC8, 0x0ECD, prExtend}, // Mn [6] LAO TONE MAI EK..LAO NIGGAHITA+ {0x0EC8, 0x0ECE, prExtend}, // Mn [7] LAO TONE MAI EK..LAO YAMAKKAN {0x0ED0, 0x0ED9, prNumeric}, // Nd [10] LAO DIGIT ZERO..LAO DIGIT NINE {0x0F00, 0x0F00, prALetter}, // Lo TIBETAN SYLLABLE OM {0x0F18, 0x0F19, prExtend}, // Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS@@ -1093,6 +1094,7 @@ var workBreakCodePoints = [][3]int{ {0x10E80, 0x10EA9, prALetter}, // Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET {0x10EAB, 0x10EAC, prExtend}, // Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK {0x10EB0, 0x10EB1, prALetter}, // Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE+ {0x10EFD, 0x10EFF, prExtend}, // Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA {0x10F00, 0x10F1C, prALetter}, // Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL {0x10F27, 0x10F27, prALetter}, // Lo OLD SOGDIAN LIGATURE AYIN-DALETH {0x10F30, 0x10F45, prALetter}, // Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN@@ -1157,6 +1159,8 @@ var workBreakCodePoints = [][3]int{ {0x11235, 0x11235, prExtend}, // Mc KHOJKI SIGN VIRAMA {0x11236, 0x11237, prExtend}, // Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA {0x1123E, 0x1123E, prExtend}, // Mn KHOJKI SIGN SUKUN+ {0x1123F, 0x11240, prALetter}, // Lo [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I+ {0x11241, 0x11241, prExtend}, // Mn KHOJKI VOWEL SIGN VOCALIC R {0x11280, 0x11286, prALetter}, // Lo [7] MULTANI LETTER A..MULTANI LETTER GA {0x11288, 0x11288, prALetter}, // Lo MULTANI LETTER GHA {0x1128A, 0x1128D, prALetter}, // Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA@@ -1337,13 +1341,28 @@ var workBreakCodePoints = [][3]int{ {0x11EE0, 0x11EF2, prALetter}, // Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA {0x11EF3, 0x11EF4, prExtend}, // Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U {0x11EF5, 0x11EF6, prExtend}, // Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O+ {0x11F00, 0x11F01, prExtend}, // Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA+ {0x11F02, 0x11F02, prALetter}, // Lo KAWI SIGN REPHA+ {0x11F03, 0x11F03, prExtend}, // Mc KAWI SIGN VISARGA+ {0x11F04, 0x11F10, prALetter}, // Lo [13] KAWI LETTER A..KAWI LETTER O+ {0x11F12, 0x11F33, prALetter}, // Lo [34] KAWI LETTER KA..KAWI LETTER JNYA+ {0x11F34, 0x11F35, prExtend}, // Mc [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA+ {0x11F36, 0x11F3A, prExtend}, // Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R+ {0x11F3E, 0x11F3F, prExtend}, // Mc [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI+ {0x11F40, 0x11F40, prExtend}, // Mn KAWI VOWEL SIGN EU+ {0x11F41, 0x11F41, prExtend}, // Mc KAWI SIGN KILLER+ {0x11F42, 0x11F42, prExtend}, // Mn KAWI CONJOINER+ {0x11F50, 0x11F59, prNumeric}, // Nd [10] KAWI DIGIT ZERO..KAWI DIGIT NINE {0x11FB0, 0x11FB0, prALetter}, // Lo LISU LETTER YHA {0x12000, 0x12399, prALetter}, // Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U {0x12400, 0x1246E, prALetter}, // Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM {0x12480, 0x12543, prALetter}, // Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU {0x12F90, 0x12FF0, prALetter}, // Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114- {0x13000, 0x1342E, prALetter}, // Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032- {0x13430, 0x13438, prFormat}, // Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT+ {0x13000, 0x1342F, prALetter}, // Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D+ {0x13430, 0x1343F, prFormat}, // Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE+ {0x13440, 0x13440, prExtend}, // Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY+ {0x13441, 0x13446, prALetter}, // Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN+ {0x13447, 0x13455, prExtend}, // Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED {0x14400, 0x14646, prALetter}, // Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 {0x16800, 0x16A38, prALetter}, // Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ {0x16A40, 0x16A5E, prALetter}, // Lo [31] MRO LETTER TA..MRO LETTER TEK@@ -1374,6 +1393,7 @@ var workBreakCodePoints = [][3]int{ {0x1AFFD, 0x1AFFE, prKatakana}, // Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 {0x1B000, 0x1B000, prKatakana}, // Lo KATAKANA LETTER ARCHAIC E {0x1B120, 0x1B122, prKatakana}, // Lo [3] KATAKANA LETTER ARCHAIC YI..KATAKANA LETTER ARCHAIC WU+ {0x1B155, 0x1B155, prKatakana}, // Lo KATAKANA LETTER SMALL KO {0x1B164, 0x1B167, prKatakana}, // Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N {0x1BC00, 0x1BC6A, prALetter}, // Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M {0x1BC70, 0x1BC7C, prALetter}, // Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK@@ -1431,11 +1451,14 @@ var workBreakCodePoints = [][3]int{ {0x1DF00, 0x1DF09, prALetter}, // L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK {0x1DF0A, 0x1DF0A, prALetter}, // Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK {0x1DF0B, 0x1DF1E, prALetter}, // L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL+ {0x1DF25, 0x1DF2A, prALetter}, // L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK {0x1E000, 0x1E006, prExtend}, // Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE {0x1E008, 0x1E018, prExtend}, // Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU {0x1E01B, 0x1E021, prExtend}, // Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI {0x1E023, 0x1E024, prExtend}, // Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS {0x1E026, 0x1E02A, prExtend}, // Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA+ {0x1E030, 0x1E06D, prALetter}, // Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE+ {0x1E08F, 0x1E08F, prExtend}, // Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I {0x1E100, 0x1E12C, prALetter}, // Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W {0x1E130, 0x1E136, prExtend}, // Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D {0x1E137, 0x1E13D, prALetter}, // Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER@@ -1446,6 +1469,10 @@ var workBreakCodePoints = [][3]int{ {0x1E2C0, 0x1E2EB, prALetter}, // Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH {0x1E2EC, 0x1E2EF, prExtend}, // Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI {0x1E2F0, 0x1E2F9, prNumeric}, // Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE+ {0x1E4D0, 0x1E4EA, prALetter}, // Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL+ {0x1E4EB, 0x1E4EB, prALetter}, // Lm NAG MUNDARI SIGN OJOD+ {0x1E4EC, 0x1E4EF, prExtend}, // Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH+ {0x1E4F0, 0x1E4F9, prNumeric}, // Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE {0x1E7E0, 0x1E7E6, prALetter}, // Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO {0x1E7E8, 0x1E7EB, prALetter}, // Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE {0x1E7ED, 0x1E7EE, prALetter}, // Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE@@ -1740,7 +1767,8 @@ var workBreakCodePoints = [][3]int{ {0x1F6D3, 0x1F6D4, prExtendedPictographic}, // E0.0 [2] (🛓..🛔) STUPA..PAGODA {0x1F6D5, 0x1F6D5, prExtendedPictographic}, // E12.0 [1] (🛕) hindu temple {0x1F6D6, 0x1F6D7, prExtendedPictographic}, // E13.0 [2] (🛖..🛗) hut..elevator- {0x1F6D8, 0x1F6DC, prExtendedPictographic}, // E0.0 [5] (..🛜) <reserved-1F6D8>..<reserved-1F6DC>+ {0x1F6D8, 0x1F6DB, prExtendedPictographic}, // E0.0 [4] (..) <reserved-1F6D8>..<reserved-1F6DB>+ {0x1F6DC, 0x1F6DC, prExtendedPictographic}, // E15.0 [1] (🛜) wireless {0x1F6DD, 0x1F6DF, prExtendedPictographic}, // E14.0 [3] (🛝..🛟) playground slide..ring buoy {0x1F6E0, 0x1F6E5, prExtendedPictographic}, // E0.7 [6] (🛠️..🛥️) hammer and wrench..motor boat {0x1F6E6, 0x1F6E8, prExtendedPictographic}, // E0.0 [3] (🛦..🛨) UP-POINTING MILITARY AIRPLANE..UP-POINTING SMALL AIRPLANE@@ -1757,7 +1785,7 @@ var workBreakCodePoints = [][3]int{ {0x1F6FA, 0x1F6FA, prExtendedPictographic}, // E12.0 [1] (🛺) auto rickshaw {0x1F6FB, 0x1F6FC, prExtendedPictographic}, // E13.0 [2] (🛻..🛼) pickup truck..roller skate {0x1F6FD, 0x1F6FF, prExtendedPictographic}, // E0.0 [3] (..) <reserved-1F6FD>..<reserved-1F6FF>- {0x1F774, 0x1F77F, prExtendedPictographic}, // E0.0 [12] (🝴..🝿) <reserved-1F774>..<reserved-1F77F>+ {0x1F774, 0x1F77F, prExtendedPictographic}, // E0.0 [12] (🝴..🝿) LOT OF FORTUNE..ORCUS {0x1F7D5, 0x1F7DF, prExtendedPictographic}, // E0.0 [11] (🟕..) CIRCLED TRIANGLE..<reserved-1F7DF> {0x1F7E0, 0x1F7EB, prExtendedPictographic}, // E12.0 [12] (🟠..🟫) orange circle..brown square {0x1F7EC, 0x1F7EF, prExtendedPictographic}, // E0.0 [4] (..) <reserved-1F7EC>..<reserved-1F7EF>@@ -1816,30 +1844,37 @@ var workBreakCodePoints = [][3]int{ {0x1FA00, 0x1FA6F, prExtendedPictographic}, // E0.0 [112] (🨀..) NEUTRAL CHESS KING..<reserved-1FA6F> {0x1FA70, 0x1FA73, prExtendedPictographic}, // E12.0 [4] (🩰..🩳) ballet shoes..shorts {0x1FA74, 0x1FA74, prExtendedPictographic}, // E13.0 [1] (🩴) thong sandal- {0x1FA75, 0x1FA77, prExtendedPictographic}, // E0.0 [3] (🩵..🩷) <reserved-1FA75>..<reserved-1FA77>+ {0x1FA75, 0x1FA77, prExtendedPictographic}, // E15.0 [3] (🩵..🩷) light blue heart..pink heart {0x1FA78, 0x1FA7A, prExtendedPictographic}, // E12.0 [3] (🩸..🩺) drop of blood..stethoscope {0x1FA7B, 0x1FA7C, prExtendedPictographic}, // E14.0 [2] (🩻..🩼) x-ray..crutch {0x1FA7D, 0x1FA7F, prExtendedPictographic}, // E0.0 [3] (..) <reserved-1FA7D>..<reserved-1FA7F> {0x1FA80, 0x1FA82, prExtendedPictographic}, // E12.0 [3] (🪀..🪂) yo-yo..parachute {0x1FA83, 0x1FA86, prExtendedPictographic}, // E13.0 [4] (🪃..🪆) boomerang..nesting dolls- {0x1FA87, 0x1FA8F, prExtendedPictographic}, // E0.0 [9] (🪇..) <reserved-1FA87>..<reserved-1FA8F>+ {0x1FA87, 0x1FA88, prExtendedPictographic}, // E15.0 [2] (🪇..🪈) maracas..flute+ {0x1FA89, 0x1FA8F, prExtendedPictographic}, // E0.0 [7] (..) <reserved-1FA89>..<reserved-1FA8F> {0x1FA90, 0x1FA95, prExtendedPictographic}, // E12.0 [6] (🪐..🪕) ringed planet..banjo {0x1FA96, 0x1FAA8, prExtendedPictographic}, // E13.0 [19] (🪖..🪨) military helmet..rock {0x1FAA9, 0x1FAAC, prExtendedPictographic}, // E14.0 [4] (🪩..🪬) mirror ball..hamsa- {0x1FAAD, 0x1FAAF, prExtendedPictographic}, // E0.0 [3] (🪭..🪯) <reserved-1FAAD>..<reserved-1FAAF>+ {0x1FAAD, 0x1FAAF, prExtendedPictographic}, // E15.0 [3] (🪭..🪯) folding hand fan..khanda {0x1FAB0, 0x1FAB6, prExtendedPictographic}, // E13.0 [7] (🪰..🪶) fly..feather {0x1FAB7, 0x1FABA, prExtendedPictographic}, // E14.0 [4] (🪷..🪺) lotus..nest with eggs- {0x1FABB, 0x1FABF, prExtendedPictographic}, // E0.0 [5] (🪻..🪿) <reserved-1FABB>..<reserved-1FABF>+ {0x1FABB, 0x1FABD, prExtendedPictographic}, // E15.0 [3] (🪻..🪽) hyacinth..wing+ {0x1FABE, 0x1FABE, prExtendedPictographic}, // E0.0 [1] () <reserved-1FABE>+ {0x1FABF, 0x1FABF, prExtendedPictographic}, // E15.0 [1] (🪿) goose {0x1FAC0, 0x1FAC2, prExtendedPictographic}, // E13.0 [3] (🫀..🫂) anatomical heart..people hugging {0x1FAC3, 0x1FAC5, prExtendedPictographic}, // E14.0 [3] (🫃..🫅) pregnant man..person with crown- {0x1FAC6, 0x1FACF, prExtendedPictographic}, // E0.0 [10] (..🫏) <reserved-1FAC6>..<reserved-1FACF>+ {0x1FAC6, 0x1FACD, prExtendedPictographic}, // E0.0 [8] (..) <reserved-1FAC6>..<reserved-1FACD>+ {0x1FACE, 0x1FACF, prExtendedPictographic}, // E15.0 [2] (🫎..🫏) moose..donkey {0x1FAD0, 0x1FAD6, prExtendedPictographic}, // E13.0 [7] (🫐..🫖) blueberries..teapot {0x1FAD7, 0x1FAD9, prExtendedPictographic}, // E14.0 [3] (🫗..🫙) pouring liquid..jar- {0x1FADA, 0x1FADF, prExtendedPictographic}, // E0.0 [6] (🫚..) <reserved-1FADA>..<reserved-1FADF>+ {0x1FADA, 0x1FADB, prExtendedPictographic}, // E15.0 [2] (🫚..🫛) ginger root..pea pod+ {0x1FADC, 0x1FADF, prExtendedPictographic}, // E0.0 [4] (..) <reserved-1FADC>..<reserved-1FADF> {0x1FAE0, 0x1FAE7, prExtendedPictographic}, // E14.0 [8] (🫠..🫧) melting face..bubbles- {0x1FAE8, 0x1FAEF, prExtendedPictographic}, // E0.0 [8] (🫨..) <reserved-1FAE8>..<reserved-1FAEF>+ {0x1FAE8, 0x1FAE8, prExtendedPictographic}, // E15.0 [1] (🫨) shaking face+ {0x1FAE9, 0x1FAEF, prExtendedPictographic}, // E0.0 [7] (..) <reserved-1FAE9>..<reserved-1FAEF> {0x1FAF0, 0x1FAF6, prExtendedPictographic}, // E14.0 [7] (🫰..🫶) hand with index finger and thumb crossed..heart hands- {0x1FAF7, 0x1FAFF, prExtendedPictographic}, // E0.0 [9] (🫷..) <reserved-1FAF7>..<reserved-1FAFF>+ {0x1FAF7, 0x1FAF8, prExtendedPictographic}, // E15.0 [2] (🫷..🫸) leftwards pushing hand..rightwards pushing hand+ {0x1FAF9, 0x1FAFF, prExtendedPictographic}, // E0.0 [7] (..) <reserved-1FAF9>..<reserved-1FAFF> {0x1FBF0, 0x1FBF9, prNumeric}, // Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE {0x1FC00, 0x1FFFD, prExtendedPictographic}, // E0.0[1022] (..) <reserved-1FC00>..<reserved-1FFFD> {0xE0001, 0xE0001, prFormat}, // Cf LANGUAGE TAG