8221431: Support for Unicode 12.1
Reviewed-by: erikj, rriggs
This commit is contained in:
parent
e4f31b1cd7
commit
93fabcdc5a
@ -39,7 +39,7 @@ $(eval $(call IncludeCustomExtension, CompileJavaModules.gmk))
|
||||
# Module specific build settings
|
||||
|
||||
java.base_ADD_JAVAC_FLAGS += -Xdoclint:all/protected,-reference,-accessibility '-Xdoclint/package:java.*,javax.*' -XDstringConcat=inline
|
||||
java.base_COPY += .icu .dat .spp content-types.properties hijrah-config-islamic-umalqura.properties
|
||||
java.base_COPY += .icu .dat .spp .nrm content-types.properties hijrah-config-islamic-umalqura.properties
|
||||
java.base_CLEAN += intrinsic.properties
|
||||
|
||||
java.base_EXCLUDE_FILES += \
|
||||
|
@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2011, 2018, Oracle and/or its affiliates. All rights reserved.
|
||||
# Copyright (c) 2011, 2019, 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
|
||||
@ -73,6 +73,9 @@ TOOL_BLACKLISTED_CERTS = $(JAVA_SMALL) -cp $(BUILDTOOLS_OUTPUTDIR)/jdk_tools_cla
|
||||
TOOL_MAKEJAVASECURITY = $(JAVA_SMALL) -cp $(BUILDTOOLS_OUTPUTDIR)/jdk_tools_classes \
|
||||
build.tools.makejavasecurity.MakeJavaSecurity
|
||||
|
||||
TOOL_GENERATEEMOJIDATA = $(JAVA_SMALL) -cp $(BUILDTOOLS_OUTPUTDIR)/jdk_tools_classes \
|
||||
build.tools.generateemojidata.GenerateEmojiData
|
||||
|
||||
|
||||
# TODO: There are references to the jdwpgen.jar in jdk/make/netbeans/jdwpgen/build.xml
|
||||
# and nbproject/project.properties in the same dir. Needs to be looked at.
|
||||
|
@ -1,5 +1,5 @@
|
||||
/*
|
||||
* Copyright (c) 2003, 2018, Oracle and/or its affiliates. All rights reserved.
|
||||
* Copyright (c) 2003, 2019, 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
|
||||
@ -365,6 +365,8 @@ class CharacterData00 extends CharacterData {
|
||||
case 0xA7B1: mapChar = 0x0287; break;
|
||||
case 0xA7B2: mapChar = 0x029D; break;
|
||||
case 0xA7B3: mapChar = 0xAB53; break;
|
||||
case 0xA7C5: mapChar = 0x0282; break;
|
||||
case 0xA7C6: mapChar = 0x1D8E; break;
|
||||
// default mapChar is already set, so no
|
||||
// need to redo it here.
|
||||
// default : mapChar = ch;
|
||||
@ -400,6 +402,7 @@ class CharacterData00 extends CharacterData {
|
||||
case 0x026C: mapChar = 0xA7AD; break;
|
||||
case 0x0271: mapChar = 0x2C6E; break;
|
||||
case 0x027D: mapChar = 0x2C64; break;
|
||||
case 0x0282: mapChar = 0xA7C5; break;
|
||||
case 0x0287: mapChar = 0xA7B1; break;
|
||||
case 0x029D: mapChar = 0xA7B2; break;
|
||||
case 0x029E: mapChar = 0xA7B0; break;
|
||||
@ -460,6 +463,7 @@ class CharacterData00 extends CharacterData {
|
||||
case 0x1C88: mapChar = 0xA64A; break;
|
||||
case 0x1D79: mapChar = 0xA77D; break;
|
||||
case 0x1D7D: mapChar = 0x2C63; break;
|
||||
case 0x1D8E: mapChar = 0xA7C6; break;
|
||||
case 0x1F80: mapChar = 0x1F88; break;
|
||||
case 0x1F81: mapChar = 0x1F89; break;
|
||||
case 0x1F82: mapChar = 0x1F8A; break;
|
||||
@ -854,6 +858,7 @@ class CharacterData00 extends CharacterData {
|
||||
case 0x026C: mapChar = 0xA7AD; break;
|
||||
case 0x0271: mapChar = 0x2C6E; break;
|
||||
case 0x027D: mapChar = 0x2C64; break;
|
||||
case 0x0282: mapChar = 0xA7C5; break;
|
||||
case 0x0287: mapChar = 0xA7B1; break;
|
||||
case 0x029D: mapChar = 0xA7B2; break;
|
||||
case 0x029E: mapChar = 0xA7B0; break;
|
||||
@ -914,6 +919,7 @@ class CharacterData00 extends CharacterData {
|
||||
case 0x1C88: mapChar = 0xA64A; break;
|
||||
case 0x1D79: mapChar = 0xA77D; break;
|
||||
case 0x1D7D: mapChar = 0x2C63; break;
|
||||
case 0x1D8E: mapChar = 0xA7C6; break;
|
||||
case 0x1FBE: mapChar = 0x0399; break;
|
||||
case 0x2C65: mapChar = 0x023A; break;
|
||||
case 0x2C66: mapChar = 0x023E; break;
|
||||
|
@ -1,5 +1,5 @@
|
||||
/*
|
||||
* Copyright (c) 2003, 2018, Oracle and/or its affiliates. All rights reserved.
|
||||
* Copyright (c) 2003, 2019, 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
|
||||
@ -433,22 +433,59 @@ class CharacterData01 extends CharacterData {
|
||||
case 0X1EC92: retval = 7000; break; // INDIC SIYAQ NUMBER SEVEN THOUSAND
|
||||
case 0X1EC93: retval = 8000; break; // INDIC SIYAQ NUMBER EIGHT THOUSAND
|
||||
case 0X1EC94: retval = 9000; break; // INDIC SIYAQ NUMBER NINE THOUSAND
|
||||
case 0X1EC95: retval = 10000; break; // INDIC SIYAQ NUMBER TEN THOUSAND
|
||||
case 0X1EC96: retval = 20000; break; // INDIC SIYAQ NUMBER TWENTY THOUSAND
|
||||
case 0X1EC97: retval = 30000; break; // INDIC SIYAQ NUMBER THIRTY THOUSAND
|
||||
case 0X1EC98: retval = 40000; break; // INDIC SIYAQ NUMBER FORTY THOUSAND
|
||||
case 0X1EC99: retval = 50000; break; // INDIC SIYAQ NUMBER FIFTY THOUSAND
|
||||
case 0X1EC9A: retval = 60000; break; // INDIC SIYAQ NUMBER SIXTY THOUSAND
|
||||
case 0X1EC9B: retval = 70000; break; // INDIC SIYAQ NUMBER SEVENTY THOUSAND
|
||||
case 0X1EC9C: retval = 80000; break; // INDIC SIYAQ NUMBER EIGHTY THOUSAND
|
||||
case 0X1EC9D: retval = 90000; break; // INDIC SIYAQ NUMBER NINETY THOUSAND
|
||||
case 0X1EC9E: retval = 100000; break; // INDIC SIYAQ NUMBER LAKH
|
||||
case 0X1EC9F: retval = 200000; break; // INDIC SIYAQ NUMBER LAKHAN
|
||||
case 0X1ECA0: retval = 100000; break; // INDIC SIYAQ LAKH MARK
|
||||
case 0X1ECA1: retval = 10000000; break; // INDIC SIYAQ NUMBER KAROR
|
||||
case 0X1ECA2: retval = 20000000; break; // INDIC SIYAQ NUMBER KARORAN
|
||||
case 0X1ECB3: retval = 10000; break; // INDIC SIYAQ NUMBER ALTERNATE TEN THOUSAND
|
||||
case 0X1ECB4: retval = 100000; break; // INDIC SIYAQ NUMBER ALTERNATE LAKH MARK
|
||||
case 0X1EC95: retval = 10000; break; // INDIC SIYAQ NUMBER TEN THOUSAND
|
||||
case 0X1EC96: retval = 20000; break; // INDIC SIYAQ NUMBER TWENTY THOUSAND
|
||||
case 0X1EC97: retval = 30000; break; // INDIC SIYAQ NUMBER THIRTY THOUSAND
|
||||
case 0X1EC98: retval = 40000; break; // INDIC SIYAQ NUMBER FORTY THOUSAND
|
||||
case 0X1EC99: retval = 50000; break; // INDIC SIYAQ NUMBER FIFTY THOUSAND
|
||||
case 0X1EC9A: retval = 60000; break; // INDIC SIYAQ NUMBER SIXTY THOUSAND
|
||||
case 0X1EC9B: retval = 70000; break; // INDIC SIYAQ NUMBER SEVENTY THOUSAND
|
||||
case 0X1EC9C: retval = 80000; break; // INDIC SIYAQ NUMBER EIGHTY THOUSAND
|
||||
case 0X1EC9D: retval = 90000; break; // INDIC SIYAQ NUMBER NINETY THOUSAND
|
||||
case 0X1EC9E: retval = 100000; break; // INDIC SIYAQ NUMBER LAKH
|
||||
case 0X1EC9F: retval = 200000; break; // INDIC SIYAQ NUMBER LAKHAN
|
||||
case 0X1ECA0: retval = 100000; break; // INDIC SIYAQ LAKH MARK
|
||||
case 0X1ECA1: retval = 10000000; break;// INDIC SIYAQ NUMBER KAROR
|
||||
case 0X1ECA2: retval = 20000000; break;// INDIC SIYAQ NUMBER KARORAN
|
||||
case 0X1ECB3: retval = 10000; break; // INDIC SIYAQ NUMBER ALTERNATE TEN THOUSAND
|
||||
case 0X1ECB4: retval = 100000; break; // INDIC SIYAQ NUMBER ALTERNATE LAKH MARK
|
||||
case 0X1ED0D: retval = 40; break; // OTTOMAN SIYAQ NUMBER FORTY
|
||||
case 0X1ED0E: retval = 50; break; // OTTOMAN SIYAQ NUMBER FIFTY
|
||||
case 0X1ED0F: retval = 60; break; // OTTOMAN SIYAQ NUMBER SIXTY
|
||||
case 0X1ED10: retval = 70; break; // OTTOMAN SIYAQ NUMBER SEVENTY
|
||||
case 0X1ED11: retval = 80; break; // OTTOMAN SIYAQ NUMBER EIGHTY
|
||||
case 0X1ED12: retval = 90; break; // OTTOMAN SIYAQ NUMBER NINETY
|
||||
case 0X1ED13: retval = 100; break; // OTTOMAN SIYAQ NUMBER ONE HUNDRED
|
||||
case 0X1ED14: retval = 200; break; // OTTOMAN SIYAQ NUMBER TWO HUNDRED
|
||||
case 0X1ED15: retval = 300; break; // OTTOMAN SIYAQ NUMBER THREE HUNDRED
|
||||
case 0X1ED16: retval = 400; break; // OTTOMAN SIYAQ NUMBER FOUR HUNDRED
|
||||
case 0X1ED17: retval = 500; break; // OTTOMAN SIYAQ NUMBER FIVE HUNDRED
|
||||
case 0X1ED18: retval = 600; break; // OTTOMAN SIYAQ NUMBER SIX HUNDRED
|
||||
case 0X1ED19: retval = 700; break; // OTTOMAN SIYAQ NUMBER SEVEN HUNDRED
|
||||
case 0X1ED1A: retval = 800; break; // OTTOMAN SIYAQ NUMBER EIGHT HUNDRED
|
||||
case 0X1ED1B: retval = 900; break; // OTTOMAN SIYAQ NUMBER NINE HUNDRED
|
||||
case 0X1ED1C: retval = 1000; break; // OTTOMAN SIYAQ NUMBER ONE THOUSAND
|
||||
case 0X1ED1D: retval = 2000; break; // OTTOMAN SIYAQ NUMBER TWO THOUSAND
|
||||
case 0X1ED1E: retval = 3000; break; // OTTOMAN SIYAQ NUMBER THREE THOUSAND
|
||||
case 0X1ED1F: retval = 4000; break; // OTTOMAN SIYAQ NUMBER FOUR THOUSAND
|
||||
case 0X1ED20: retval = 5000; break; // OTTOMAN SIYAQ NUMBER FIVE THOUSAND
|
||||
case 0X1ED21: retval = 6000; break; // OTTOMAN SIYAQ NUMBER SIX THOUSAND
|
||||
case 0X1ED22: retval = 7000; break; // OTTOMAN SIYAQ NUMBER SEVEN THOUSAND
|
||||
case 0X1ED23: retval = 8000; break; // OTTOMAN SIYAQ NUMBER EIGHT THOUSAND
|
||||
case 0X1ED24: retval = 9000; break; // OTTOMAN SIYAQ NUMBER NINE THOUSAND
|
||||
case 0X1ED25: retval = 10000; break; // OTTOMAN SIYAQ NUMBER TEN THOUSAND
|
||||
case 0X1ED26: retval = 20000; break; // OTTOMAN SIYAQ NUMBER TWENTY THOUSAND
|
||||
case 0X1ED27: retval = 30000; break; // OTTOMAN SIYAQ NUMBER THIRTY THOUSAND
|
||||
case 0X1ED28: retval = 40000; break; // OTTOMAN SIYAQ NUMBER FORTY THOUSAND
|
||||
case 0X1ED29: retval = 50000; break; // OTTOMAN SIYAQ NUMBER FIFTY THOUSAND
|
||||
case 0X1ED2A: retval = 60000; break; // OTTOMAN SIYAQ NUMBER SIXTY THOUSAND
|
||||
case 0X1ED2B: retval = 70000; break; // OTTOMAN SIYAQ NUMBER SEVENTY THOUSAND
|
||||
case 0X1ED2C: retval = 80000; break; // OTTOMAN SIYAQ NUMBER EIGHTY THOUSAND
|
||||
case 0X1ED2D: retval = 90000; break; // OTTOMAN SIYAQ NUMBER NINETY THOUSAND
|
||||
case 0X1ED38: retval = 400; break; // OTTOMAN SIYAQ ALTERNATE NUMBER FOUR HUNDRED
|
||||
case 0X1ED39: retval = 600; break; // OTTOMAN SIYAQ ALTERNATE NUMBER SIX HUNDRED
|
||||
case 0X1ED3A: retval = 2000; break; // OTTOMAN SIYAQ ALTERNATE NUMBER TWO THOUSAND
|
||||
case 0X1ED3B: retval = 10000; break; // OTTOMAN SIYAQ ALTERNATE NUMBER TEN THOUSAND
|
||||
default: retval = -2; break;
|
||||
}
|
||||
|
||||
|
@ -1,6 +1,6 @@
|
||||
# Blocks-11.0.0.txt
|
||||
# Date: 2017-10-16, 24:39:00 GMT [KW]
|
||||
# Copyright (c) 2018 Unicode, Inc.
|
||||
# Blocks-12.1.0.txt
|
||||
# Date: 2019-03-08, 23:59:00 GMT [KW]
|
||||
# Copyright (c) 2019 Unicode, Inc.
|
||||
# For terms of use, see http://www.unicode.org/terms_of_use.html
|
||||
#
|
||||
# Unicode Character Database
|
||||
@ -239,6 +239,7 @@ FFF0..FFFF; Specials
|
||||
10E60..10E7F; Rumi Numeral Symbols
|
||||
10F00..10F2F; Old Sogdian
|
||||
10F30..10F6F; Sogdian
|
||||
10FE0..10FFF; Elymaic
|
||||
11000..1107F; Brahmi
|
||||
11080..110CF; Kaithi
|
||||
110D0..110FF; Sora Sompeng
|
||||
@ -259,6 +260,7 @@ FFF0..FFFF; Specials
|
||||
11700..1173F; Ahom
|
||||
11800..1184F; Dogra
|
||||
118A0..118FF; Warang Citi
|
||||
119A0..119FF; Nandinagari
|
||||
11A00..11A4F; Zanabazar Square
|
||||
11A50..11AAF; Soyombo
|
||||
11AC0..11AFF; Pau Cin Hau
|
||||
@ -267,10 +269,12 @@ FFF0..FFFF; Specials
|
||||
11D00..11D5F; Masaram Gondi
|
||||
11D60..11DAF; Gunjala Gondi
|
||||
11EE0..11EFF; Makasar
|
||||
11FC0..11FFF; Tamil Supplement
|
||||
12000..123FF; Cuneiform
|
||||
12400..1247F; Cuneiform Numbers and Punctuation
|
||||
12480..1254F; Early Dynastic Cuneiform
|
||||
13000..1342F; Egyptian Hieroglyphs
|
||||
13430..1343F; Egyptian Hieroglyph Format Controls
|
||||
14400..1467F; Anatolian Hieroglyphs
|
||||
16800..16A3F; Bamum Supplement
|
||||
16A40..16A6F; Mro
|
||||
@ -283,6 +287,7 @@ FFF0..FFFF; Specials
|
||||
18800..18AFF; Tangut Components
|
||||
1B000..1B0FF; Kana Supplement
|
||||
1B100..1B12F; Kana Extended-A
|
||||
1B130..1B16F; Small Kana Extension
|
||||
1B170..1B2FF; Nushu
|
||||
1BC00..1BC9F; Duployan
|
||||
1BCA0..1BCAF; Shorthand Format Controls
|
||||
@ -295,9 +300,12 @@ FFF0..FFFF; Specials
|
||||
1D400..1D7FF; Mathematical Alphanumeric Symbols
|
||||
1D800..1DAAF; Sutton SignWriting
|
||||
1E000..1E02F; Glagolitic Supplement
|
||||
1E100..1E14F; Nyiakeng Puachue Hmong
|
||||
1E2C0..1E2FF; Wancho
|
||||
1E800..1E8DF; Mende Kikakui
|
||||
1E900..1E95F; Adlam
|
||||
1EC70..1ECBF; Indic Siyaq Numbers
|
||||
1ED00..1ED4F; Ottoman Siyaq Numbers
|
||||
1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
|
||||
1F000..1F02F; Mahjong Tiles
|
||||
1F030..1F09F; Domino Tiles
|
||||
@ -313,6 +321,7 @@ FFF0..FFFF; Specials
|
||||
1F800..1F8FF; Supplemental Arrows-C
|
||||
1F900..1F9FF; Supplemental Symbols and Pictographs
|
||||
1FA00..1FA6F; Chess Symbols
|
||||
1FA70..1FAFF; Symbols and Pictographs Extended-A
|
||||
20000..2A6DF; CJK Unified Ideographs Extension B
|
||||
2A700..2B73F; CJK Unified Ideographs Extension C
|
||||
2B740..2B81F; CJK Unified Ideographs Extension D
|
18875
make/data/unicodedata/NormalizationTest.txt
Normal file
18875
make/data/unicodedata/NormalizationTest.txt
Normal file
File diff suppressed because it is too large
Load Diff
@ -1,6 +1,6 @@
|
||||
# PropList-11.0.0.txt
|
||||
# Date: 2018-03-15, 04:28:35 GMT
|
||||
# Copyright (c) 2018 Unicode, Inc.
|
||||
# PropList-12.1.0.txt
|
||||
# Date: 2019-03-10, 10:53:16 GMT
|
||||
# Copyright (c) 2019 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
|
||||
#
|
||||
@ -138,7 +138,7 @@ FF63 ; Quotation_Mark # Pe HALFWIDTH RIGHT CORNER BRACKET
|
||||
0F0D..0F12 ; Terminal_Punctuation # Po [6] TIBETAN MARK SHAD..TIBETAN MARK RGYA GRAM SHAD
|
||||
104A..104B ; Terminal_Punctuation # Po [2] MYANMAR SIGN LITTLE SECTION..MYANMAR SIGN SECTION
|
||||
1361..1368 ; Terminal_Punctuation # Po [8] ETHIOPIC WORDSPACE..ETHIOPIC PARAGRAPH SEPARATOR
|
||||
166D..166E ; Terminal_Punctuation # Po [2] CANADIAN SYLLABICS CHI SIGN..CANADIAN SYLLABICS FULL STOP
|
||||
166E ; Terminal_Punctuation # Po CANADIAN SYLLABICS FULL STOP
|
||||
16EB..16ED ; Terminal_Punctuation # Po [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION
|
||||
1735..1736 ; Terminal_Punctuation # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION
|
||||
17D4..17D6 ; Terminal_Punctuation # Po [3] KHMER SIGN KHAN..KHMER SIGN CAMNUC PII KUUH
|
||||
@ -157,7 +157,7 @@ FF63 ; Quotation_Mark # Pe HALFWIDTH RIGHT CORNER BRACKET
|
||||
2E3C ; Terminal_Punctuation # Po STENOGRAPHIC FULL STOP
|
||||
2E41 ; Terminal_Punctuation # Po REVERSED COMMA
|
||||
2E4C ; Terminal_Punctuation # Po MEDIEVAL COMMA
|
||||
2E4E ; Terminal_Punctuation # Po PUNCTUS ELEVATUS MARK
|
||||
2E4E..2E4F ; Terminal_Punctuation # Po [2] PUNCTUS ELEVATUS MARK..CORNISH VERSE DIVIDER
|
||||
3001..3002 ; Terminal_Punctuation # Po [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP
|
||||
A4FE..A4FF ; Terminal_Punctuation # Po [2] LISU PUNCTUATION COMMA..LISU PUNCTUATION FULL STOP
|
||||
A60D..A60F ; Terminal_Punctuation # Po [3] VAI COMMA..VAI QUESTION MARK
|
||||
@ -553,15 +553,17 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
|
||||
1056..1057 ; Other_Alphabetic # Mc [2] MYANMAR VOWEL SIGN VOCALIC R..MYANMAR VOWEL SIGN VOCALIC RR
|
||||
1058..1059 ; Other_Alphabetic # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL
|
||||
105E..1060 ; Other_Alphabetic # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA
|
||||
1062 ; Other_Alphabetic # Mc MYANMAR VOWEL SIGN SGAW KAREN EU
|
||||
1067..1068 ; Other_Alphabetic # Mc [2] MYANMAR VOWEL SIGN WESTERN PWO KAREN EU..MYANMAR VOWEL SIGN WESTERN PWO KAREN UE
|
||||
1062..1064 ; Other_Alphabetic # Mc [3] MYANMAR VOWEL SIGN SGAW KAREN EU..MYANMAR TONE MARK SGAW KAREN KE PHO
|
||||
1067..106D ; Other_Alphabetic # Mc [7] MYANMAR VOWEL SIGN WESTERN PWO KAREN EU..MYANMAR SIGN WESTERN PWO KAREN TONE-5
|
||||
1071..1074 ; Other_Alphabetic # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE
|
||||
1082 ; Other_Alphabetic # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA
|
||||
1083..1084 ; Other_Alphabetic # Mc [2] MYANMAR VOWEL SIGN SHAN AA..MYANMAR VOWEL SIGN SHAN E
|
||||
1085..1086 ; Other_Alphabetic # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y
|
||||
109C ; Other_Alphabetic # Mc MYANMAR VOWEL SIGN AITON A
|
||||
1087..108C ; Other_Alphabetic # Mc [6] MYANMAR SIGN SHAN TONE-2..MYANMAR SIGN SHAN COUNCIL TONE-3
|
||||
108D ; Other_Alphabetic # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE
|
||||
108F ; Other_Alphabetic # Mc MYANMAR SIGN RUMAI PALAUNG TONE-5
|
||||
109A..109C ; Other_Alphabetic # Mc [3] MYANMAR SIGN KHAMTI TONE-1..MYANMAR VOWEL SIGN AITON A
|
||||
109D ; Other_Alphabetic # Mn MYANMAR VOWEL SIGN AITON AI
|
||||
135F ; Other_Alphabetic # Mn ETHIOPIC COMBINING GEMINATION MARK
|
||||
1712..1713 ; Other_Alphabetic # Mn [2] TAGALOG VOWEL SIGN I..TAGALOG VOWEL SIGN U
|
||||
1732..1733 ; Other_Alphabetic # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U
|
||||
1752..1753 ; Other_Alphabetic # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U
|
||||
@ -618,18 +620,21 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
|
||||
1C24..1C2B ; Other_Alphabetic # Mc [8] LEPCHA SUBJOINED LETTER YA..LEPCHA VOWEL SIGN UU
|
||||
1C2C..1C33 ; Other_Alphabetic # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T
|
||||
1C34..1C35 ; Other_Alphabetic # Mc [2] LEPCHA CONSONANT SIGN NYIN-DO..LEPCHA CONSONANT SIGN KANG
|
||||
1CF2..1CF3 ; Other_Alphabetic # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
|
||||
1C36 ; Other_Alphabetic # Mn LEPCHA SIGN RAN
|
||||
1DE7..1DF4 ; Other_Alphabetic # Mn [14] COMBINING LATIN SMALL LETTER ALPHA..COMBINING LATIN SMALL LETTER U WITH DIAERESIS
|
||||
24B6..24E9 ; Other_Alphabetic # So [52] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN SMALL LETTER Z
|
||||
2DE0..2DFF ; Other_Alphabetic # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS
|
||||
A674..A67B ; Other_Alphabetic # Mn [8] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC LETTER OMEGA
|
||||
A69E..A69F ; Other_Alphabetic # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E
|
||||
A802 ; Other_Alphabetic # Mn SYLOTI NAGRI SIGN DVISVARA
|
||||
A80B ; Other_Alphabetic # Mn SYLOTI NAGRI SIGN ANUSVARA
|
||||
A823..A824 ; Other_Alphabetic # Mc [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIGN I
|
||||
A825..A826 ; Other_Alphabetic # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E
|
||||
A827 ; Other_Alphabetic # Mc SYLOTI NAGRI VOWEL SIGN OO
|
||||
A880..A881 ; Other_Alphabetic # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA
|
||||
A8B4..A8C3 ; Other_Alphabetic # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU
|
||||
A8C5 ; Other_Alphabetic # Mn SAURASHTRA SIGN CANDRABINDU
|
||||
A8FF ; Other_Alphabetic # Mn DEVANAGARI VOWEL SIGN AY
|
||||
A926..A92A ; Other_Alphabetic # Mn [5] KAYAH LI VOWEL UE..KAYAH LI VOWEL O
|
||||
A947..A951 ; Other_Alphabetic # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R
|
||||
A952 ; Other_Alphabetic # Mc REJANG CONSONANT SIGN H
|
||||
@ -638,8 +643,9 @@ A983 ; Other_Alphabetic # Mc JAVANESE SIGN WIGNYAN
|
||||
A9B4..A9B5 ; Other_Alphabetic # Mc [2] JAVANESE VOWEL SIGN TARUNG..JAVANESE VOWEL SIGN TOLONG
|
||||
A9B6..A9B9 ; Other_Alphabetic # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT
|
||||
A9BA..A9BB ; Other_Alphabetic # Mc [2] JAVANESE VOWEL SIGN TALING..JAVANESE VOWEL SIGN DIRGA MURE
|
||||
A9BC ; Other_Alphabetic # Mn JAVANESE VOWEL SIGN PEPET
|
||||
A9BD..A9BF ; Other_Alphabetic # Mc [3] JAVANESE CONSONANT SIGN KERET..JAVANESE CONSONANT SIGN CAKRA
|
||||
A9BC..A9BD ; Other_Alphabetic # Mn [2] JAVANESE VOWEL SIGN PEPET..JAVANESE CONSONANT SIGN KERET
|
||||
A9BE..A9BF ; Other_Alphabetic # Mc [2] JAVANESE CONSONANT SIGN PENGKAL..JAVANESE CONSONANT SIGN CAKRA
|
||||
A9E5 ; Other_Alphabetic # Mn MYANMAR SIGN SHAN SAW
|
||||
AA29..AA2E ; Other_Alphabetic # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE
|
||||
AA2F..AA30 ; Other_Alphabetic # Mc [2] CHAM VOWEL SIGN O..CHAM VOWEL SIGN AI
|
||||
AA31..AA32 ; Other_Alphabetic # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE
|
||||
@ -648,6 +654,9 @@ AA35..AA36 ; Other_Alphabetic # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONA
|
||||
AA43 ; Other_Alphabetic # Mn CHAM CONSONANT SIGN FINAL NG
|
||||
AA4C ; Other_Alphabetic # Mn CHAM CONSONANT SIGN FINAL M
|
||||
AA4D ; Other_Alphabetic # Mc CHAM CONSONANT SIGN FINAL H
|
||||
AA7B ; Other_Alphabetic # Mc MYANMAR SIGN PAO KAREN TONE
|
||||
AA7C ; Other_Alphabetic # Mn MYANMAR SIGN TAI LAING TONE-2
|
||||
AA7D ; Other_Alphabetic # Mc MYANMAR SIGN TAI LAING TONE-5
|
||||
AAB0 ; Other_Alphabetic # Mn TAI VIET MAI KANG
|
||||
AAB2..AAB4 ; Other_Alphabetic # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U
|
||||
AAB7..AAB8 ; Other_Alphabetic # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA
|
||||
@ -740,6 +749,11 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
|
||||
1182C..1182E ; Other_Alphabetic # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II
|
||||
1182F..11837 ; Other_Alphabetic # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA
|
||||
11838 ; Other_Alphabetic # Mc DOGRA SIGN VISARGA
|
||||
119D1..119D3 ; Other_Alphabetic # Mc [3] NANDINAGARI VOWEL SIGN AA..NANDINAGARI VOWEL SIGN II
|
||||
119D4..119D7 ; Other_Alphabetic # Mn [4] NANDINAGARI VOWEL SIGN U..NANDINAGARI VOWEL SIGN VOCALIC RR
|
||||
119DA..119DB ; Other_Alphabetic # Mn [2] NANDINAGARI VOWEL SIGN E..NANDINAGARI VOWEL SIGN AI
|
||||
119DC..119DF ; Other_Alphabetic # Mc [4] NANDINAGARI VOWEL SIGN O..NANDINAGARI SIGN VISARGA
|
||||
119E4 ; Other_Alphabetic # Mc NANDINAGARI VOWEL SIGN PRISHTHAMATRA E
|
||||
11A01..11A0A ; Other_Alphabetic # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK
|
||||
11A35..11A38 ; Other_Alphabetic # Mn [4] ZANABAZAR SQUARE SIGN CANDRABINDU..ZANABAZAR SQUARE SIGN ANUSVARA
|
||||
11A39 ; Other_Alphabetic # Mc ZANABAZAR SQUARE SIGN VISARGA
|
||||
@ -773,8 +787,9 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
|
||||
11D96 ; Other_Alphabetic # Mc GUNJALA GONDI SIGN VISARGA
|
||||
11EF3..11EF4 ; Other_Alphabetic # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
|
||||
11EF5..11EF6 ; Other_Alphabetic # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
|
||||
16B30..16B36 ; Other_Alphabetic # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
|
||||
16F51..16F7E ; Other_Alphabetic # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
|
||||
16F4F ; Other_Alphabetic # Mn MIAO SIGN CONSONANT MODIFIER BAR
|
||||
16F51..16F87 ; Other_Alphabetic # Mc [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI
|
||||
16F8F..16F92 ; Other_Alphabetic # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
|
||||
1BC9E ; Other_Alphabetic # Mn DUPLOYAN DOUBLE MARK
|
||||
1E000..1E006 ; Other_Alphabetic # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
|
||||
1E008..1E018 ; Other_Alphabetic # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
|
||||
@ -786,7 +801,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
|
||||
1F150..1F169 ; Other_Alphabetic # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
|
||||
1F170..1F189 ; Other_Alphabetic # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z
|
||||
|
||||
# Total code points: 1334
|
||||
# Total code points: 1377
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -798,7 +813,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
|
||||
4E00..9FEF ; Ideographic # Lo [20976] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEF
|
||||
F900..FA6D ; Ideographic # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D
|
||||
FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9
|
||||
17000..187F1 ; Ideographic # Lo [6130] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F1
|
||||
17000..187F7 ; Ideographic # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7
|
||||
18800..18AF2 ; Ideographic # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
|
||||
1B170..1B2FB ; Ideographic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
|
||||
20000..2A6D6 ; Ideographic # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
|
||||
@ -808,7 +823,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
|
||||
2CEB0..2EBE0 ; Ideographic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
|
||||
2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
|
||||
|
||||
# Total code points: 96184
|
||||
# Total code points: 96190
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -876,6 +891,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
|
||||
0DCA ; Diacritic # Mn SINHALA SIGN AL-LAKUNA
|
||||
0E47..0E4C ; Diacritic # Mn [6] THAI CHARACTER MAITAIKHU..THAI CHARACTER THANTHAKHAT
|
||||
0E4E ; Diacritic # Mn THAI CHARACTER YAMAKKAN
|
||||
0EBA ; Diacritic # Mn LAO SIGN PALI VIRAMA
|
||||
0EC8..0ECC ; Diacritic # Mn [5] LAO TONE MAI EK..LAO CANCELLATION MARK
|
||||
0F18..0F19 ; Diacritic # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS
|
||||
0F35 ; Diacritic # Mn TIBETAN MARK NGAS BZUNG NYI ZLA
|
||||
@ -887,10 +903,13 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
|
||||
0FC6 ; Diacritic # Mn TIBETAN SYMBOL PADMA GDAN
|
||||
1037 ; Diacritic # Mn MYANMAR SIGN DOT BELOW
|
||||
1039..103A ; Diacritic # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT
|
||||
1063..1064 ; Diacritic # Mc [2] MYANMAR TONE MARK SGAW KAREN HATHI..MYANMAR TONE MARK SGAW KAREN KE PHO
|
||||
1069..106D ; Diacritic # Mc [5] MYANMAR SIGN WESTERN PWO KAREN TONE-1..MYANMAR SIGN WESTERN PWO KAREN TONE-5
|
||||
1087..108C ; Diacritic # Mc [6] MYANMAR SIGN SHAN TONE-2..MYANMAR SIGN SHAN COUNCIL TONE-3
|
||||
108D ; Diacritic # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE
|
||||
108F ; Diacritic # Mc MYANMAR SIGN RUMAI PALAUNG TONE-5
|
||||
109A..109B ; Diacritic # Mc [2] MYANMAR SIGN KHAMTI TONE-1..MYANMAR SIGN KHAMTI TONE-3
|
||||
135D..135F ; Diacritic # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK
|
||||
17C9..17D3 ; Diacritic # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT
|
||||
17DD ; Diacritic # Mn KHMER SIGN ATTHACAN
|
||||
1939..193B ; Diacritic # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I
|
||||
@ -935,9 +954,11 @@ A67C..A67D ; Diacritic # Mn [2] COMBINING CYRILLIC KAVYKA..COMBINING CYRILL
|
||||
A67F ; Diacritic # Lm CYRILLIC PAYEROK
|
||||
A69C..A69D ; Diacritic # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN
|
||||
A6F0..A6F1 ; Diacritic # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS
|
||||
A700..A716 ; Diacritic # Sk [23] MODIFIER LETTER CHINESE TONE YIN PING..MODIFIER LETTER EXTRA-LOW LEFT-STEM TONE BAR
|
||||
A717..A71F ; Diacritic # Lm [9] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOW INVERTED EXCLAMATION MARK
|
||||
A720..A721 ; Diacritic # Sk [2] MODIFIER LETTER STRESS AND HIGH TONE..MODIFIER LETTER STRESS AND LOW TONE
|
||||
A788 ; Diacritic # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT
|
||||
A789..A78A ; Diacritic # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN
|
||||
A7F8..A7F9 ; Diacritic # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
|
||||
A8C4 ; Diacritic # Mn SAURASHTRA SIGN VIRAMA
|
||||
A8E0..A8F1 ; Diacritic # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA
|
||||
@ -992,6 +1013,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON
|
||||
116B7 ; Diacritic # Mn TAKRI SIGN NUKTA
|
||||
1172B ; Diacritic # Mn AHOM SIGN KILLER
|
||||
11839..1183A ; Diacritic # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA
|
||||
119E0 ; Diacritic # Mn NANDINAGARI SIGN VIRAMA
|
||||
11A34 ; Diacritic # Mn ZANABAZAR SQUARE SIGN VIRAMA
|
||||
11A47 ; Diacritic # Mn ZANABAZAR SQUARE SUBJOINER
|
||||
11A99 ; Diacritic # Mn SOYOMBO SUBJOINER
|
||||
@ -1000,6 +1022,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON
|
||||
11D44..11D45 ; Diacritic # Mn [2] MASARAM GONDI SIGN HALANTA..MASARAM GONDI VIRAMA
|
||||
11D97 ; Diacritic # Mn GUNJALA GONDI VIRAMA
|
||||
16AF0..16AF4 ; Diacritic # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
|
||||
16B30..16B36 ; Diacritic # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
|
||||
16F8F..16F92 ; Diacritic # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
|
||||
16F93..16F9F ; Diacritic # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8
|
||||
1D167..1D169 ; Diacritic # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3
|
||||
@ -1007,11 +1030,13 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON
|
||||
1D17B..1D182 ; Diacritic # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE
|
||||
1D185..1D18B ; Diacritic # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
|
||||
1D1AA..1D1AD ; Diacritic # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
|
||||
1E130..1E136 ; Diacritic # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
|
||||
1E2EC..1E2EF ; Diacritic # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI
|
||||
1E8D0..1E8D6 ; Diacritic # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
|
||||
1E944..1E946 ; Diacritic # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK
|
||||
1E948..1E94A ; Diacritic # Mn [3] ADLAM CONSONANT MODIFIER..ADLAM NUKTA
|
||||
|
||||
# Total code points: 818
|
||||
# Total code points: 873
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -1043,9 +1068,11 @@ FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND
|
||||
11A98 ; Extender # Mn SOYOMBO GEMINATION MARK
|
||||
16B42..16B43 ; Extender # Lm [2] PAHAWH HMONG SIGN VOS NRUA..PAHAWH HMONG SIGN IB YAM
|
||||
16FE0..16FE1 ; Extender # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK
|
||||
16FE3 ; Extender # Lm OLD CHINESE ITERATION MARK
|
||||
1E13C..1E13D ; Extender # Lm [2] NYIAKENG PUACHUE HMONG SIGN XW XW..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER
|
||||
1E944..1E946 ; Extender # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK
|
||||
|
||||
# Total code points: 44
|
||||
# Total code points: 47
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -1119,6 +1146,7 @@ FFFFE..FFFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-FFFFE>..<noncha
|
||||
0D57 ; Other_Grapheme_Extend # Mc MALAYALAM AU LENGTH MARK
|
||||
0DCF ; Other_Grapheme_Extend # Mc SINHALA VOWEL SIGN AELA-PILLA
|
||||
0DDF ; Other_Grapheme_Extend # Mc SINHALA VOWEL SIGN GAYANUKITTA
|
||||
1B35 ; Other_Grapheme_Extend # Mc BALINESE VOWEL SIGN TEDUNG
|
||||
200C ; Other_Grapheme_Extend # Cf ZERO WIDTH NON-JOINER
|
||||
302E..302F ; Other_Grapheme_Extend # Mc [2] HANGUL SINGLE DOT TONE MARK..HANGUL DOUBLE DOT TONE MARK
|
||||
FF9E..FF9F ; Other_Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
|
||||
@ -1131,7 +1159,7 @@ FF9E..FF9F ; Other_Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND
|
||||
1D16E..1D172 ; Other_Grapheme_Extend # Mc [5] MUSICAL SYMBOL COMBINING FLAG-1..MUSICAL SYMBOL COMBINING FLAG-5
|
||||
E0020..E007F ; Other_Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG
|
||||
|
||||
# Total code points: 125
|
||||
# Total code points: 126
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -1547,10 +1575,7 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S
|
||||
2B74..2B75 ; Pattern_Syntax # Cn [2] <reserved-2B74>..<reserved-2B75>
|
||||
2B76..2B95 ; Pattern_Syntax # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW
|
||||
2B96..2B97 ; Pattern_Syntax # Cn [2] <reserved-2B96>..<reserved-2B97>
|
||||
2B98..2BC8 ; Pattern_Syntax # So [49] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
|
||||
2BC9 ; Pattern_Syntax # Cn <reserved-2BC9>
|
||||
2BCA..2BFE ; Pattern_Syntax # So [53] TOP HALF BLACK CIRCLE..REVERSED RIGHT ANGLE
|
||||
2BFF ; Pattern_Syntax # Cn <reserved-2BFF>
|
||||
2B98..2BFF ; Pattern_Syntax # So [104] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..HELLSCHREIBER PAUSE SYMBOL
|
||||
2E00..2E01 ; Pattern_Syntax # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER
|
||||
2E02 ; Pattern_Syntax # Pi LEFT SUBSTITUTION BRACKET
|
||||
2E03 ; Pattern_Syntax # Pf RIGHT SUBSTITUTION BRACKET
|
||||
@ -1588,8 +1613,8 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S
|
||||
2E40 ; Pattern_Syntax # Pd DOUBLE HYPHEN
|
||||
2E41 ; Pattern_Syntax # Po REVERSED COMMA
|
||||
2E42 ; Pattern_Syntax # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK
|
||||
2E43..2E4E ; Pattern_Syntax # Po [12] DASH WITH LEFT UPTURN..PUNCTUS ELEVATUS MARK
|
||||
2E4F..2E7F ; Pattern_Syntax # Cn [49] <reserved-2E4F>..<reserved-2E7F>
|
||||
2E43..2E4F ; Pattern_Syntax # Po [13] DASH WITH LEFT UPTURN..CORNISH VERSE DIVIDER
|
||||
2E50..2E7F ; Pattern_Syntax # Cn [48] <reserved-2E50>..<reserved-2E7F>
|
||||
3001..3003 ; Pattern_Syntax # Po [3] IDEOGRAPHIC COMMA..DITTO MARK
|
||||
3008 ; Pattern_Syntax # Ps LEFT ANGLE BRACKET
|
||||
3009 ; Pattern_Syntax # Pe RIGHT ANGLE BRACKET
|
||||
|
@ -1,6 +1,6 @@
|
||||
# PropertyValueAliases-11.0.0.txt
|
||||
# Date: 2018-05-20, 09:03:12 GMT
|
||||
# Copyright (c) 2018 Unicode, Inc.
|
||||
# PropertyValueAliases-12.1.0.txt
|
||||
# Date: 2019-03-10, 10:53:18 GMT
|
||||
# Copyright (c) 2019 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
|
||||
#
|
||||
@ -22,12 +22,15 @@
|
||||
# First Field: The first field describes the property for which that
|
||||
# property value name is used.
|
||||
#
|
||||
# Second Field: The second field is an abbreviated name.
|
||||
# Second Field: The second field is the short name for the property value.
|
||||
# It is typically an abbreviation, but in a number of cases it is simply
|
||||
# a duplicate of the "long name" in the third field.
|
||||
#
|
||||
# Third Field: The third field is a long name.
|
||||
# Third Field: The third field is the long name for the property value,
|
||||
# typically the formal name used in documentation about the property value.
|
||||
#
|
||||
# In the case of ccc, there are 4 fields. The second field is numeric, third
|
||||
# is abbreviated, and fourth is long.
|
||||
# In the case of Canonical_Combining_Class (ccc), there are 4 fields:
|
||||
# The second field is numeric, the third is the short name, and the fourth is the long name.
|
||||
#
|
||||
# The above are the preferred aliases. Other aliases may be listed in additional fields.
|
||||
#
|
||||
@ -51,7 +54,8 @@
|
||||
#
|
||||
# The combination of property value and property name is, however, unique.
|
||||
#
|
||||
# For more information, see UTS #18: Unicode Regular Expressions
|
||||
# For more information, see UAX #44, Unicode Character Database, and
|
||||
# UTS #18, Unicode Regular Expressions.
|
||||
# ================================================
|
||||
|
||||
|
||||
@ -82,6 +86,8 @@ age; 8.0 ; V8_0
|
||||
age; 9.0 ; V9_0
|
||||
age; 10.0 ; V10_0
|
||||
age; 11.0 ; V11_0
|
||||
age; 12.0 ; V12_0
|
||||
age; 12.1 ; V12_1
|
||||
age; NA ; Unassigned
|
||||
|
||||
# Alphabetic (Alpha)
|
||||
@ -224,8 +230,10 @@ blk; Dogra ; Dogra
|
||||
blk; Domino ; Domino_Tiles
|
||||
blk; Duployan ; Duployan
|
||||
blk; Early_Dynastic_Cuneiform ; Early_Dynastic_Cuneiform
|
||||
blk; Egyptian_Hieroglyph_Format_Controls; Egyptian_Hieroglyph_Format_Controls
|
||||
blk; Egyptian_Hieroglyphs ; Egyptian_Hieroglyphs
|
||||
blk; Elbasan ; Elbasan
|
||||
blk; Elymaic ; Elymaic
|
||||
blk; Emoticons ; Emoticons
|
||||
blk; Enclosed_Alphanum ; Enclosed_Alphanumerics
|
||||
blk; Enclosed_Alphanum_Sup ; Enclosed_Alphanumeric_Supplement
|
||||
@ -339,12 +347,14 @@ blk; Myanmar ; Myanmar
|
||||
blk; Myanmar_Ext_A ; Myanmar_Extended_A
|
||||
blk; Myanmar_Ext_B ; Myanmar_Extended_B
|
||||
blk; Nabataean ; Nabataean
|
||||
blk; Nandinagari ; Nandinagari
|
||||
blk; NB ; No_Block
|
||||
blk; New_Tai_Lue ; New_Tai_Lue
|
||||
blk; Newa ; Newa
|
||||
blk; NKo ; NKo
|
||||
blk; Number_Forms ; Number_Forms
|
||||
blk; Nushu ; Nushu
|
||||
blk; Nyiakeng_Puachue_Hmong ; Nyiakeng_Puachue_Hmong
|
||||
blk; OCR ; Optical_Character_Recognition
|
||||
blk; Ogham ; Ogham
|
||||
blk; Ol_Chiki ; Ol_Chiki
|
||||
@ -360,6 +370,7 @@ blk; Oriya ; Oriya
|
||||
blk; Ornamental_Dingbats ; Ornamental_Dingbats
|
||||
blk; Osage ; Osage
|
||||
blk; Osmanya ; Osmanya
|
||||
blk; Ottoman_Siyaq_Numbers ; Ottoman_Siyaq_Numbers
|
||||
blk; Pahawh_Hmong ; Pahawh_Hmong
|
||||
blk; Palmyrene ; Palmyrene
|
||||
blk; Pau_Cin_Hau ; Pau_Cin_Hau
|
||||
@ -384,6 +395,7 @@ blk; Siddham ; Siddham
|
||||
blk; Sinhala ; Sinhala
|
||||
blk; Sinhala_Archaic_Numbers ; Sinhala_Archaic_Numbers
|
||||
blk; Small_Forms ; Small_Form_Variants
|
||||
blk; Small_Kana_Ext ; Small_Kana_Extension
|
||||
blk; Sogdian ; Sogdian
|
||||
blk; Sora_Sompeng ; Sora_Sompeng
|
||||
blk; Soyombo ; Soyombo
|
||||
@ -401,6 +413,7 @@ blk; Sup_Symbols_And_Pictographs ; Supplemental_Symbols_And_Pictographs
|
||||
blk; Super_And_Sub ; Superscripts_And_Subscripts
|
||||
blk; Sutton_SignWriting ; Sutton_SignWriting
|
||||
blk; Syloti_Nagri ; Syloti_Nagri
|
||||
blk; Symbols_And_Pictographs_Ext_A ; Symbols_And_Pictographs_Extended_A
|
||||
blk; Syriac ; Syriac
|
||||
blk; Syriac_Sup ; Syriac_Supplement
|
||||
blk; Tagalog ; Tagalog
|
||||
@ -412,6 +425,7 @@ blk; Tai_Viet ; Tai_Viet
|
||||
blk; Tai_Xuan_Jing ; Tai_Xuan_Jing_Symbols
|
||||
blk; Takri ; Takri
|
||||
blk; Tamil ; Tamil
|
||||
blk; Tamil_Sup ; Tamil_Supplement
|
||||
blk; Tangut ; Tangut
|
||||
blk; Tangut_Components ; Tangut_Components
|
||||
blk; Telugu ; Telugu
|
||||
@ -429,6 +443,7 @@ blk; Vedic_Ext ; Vedic_Extensions
|
||||
blk; Vertical_Forms ; Vertical_Forms
|
||||
blk; VS ; Variation_Selectors
|
||||
blk; VS_Sup ; Variation_Selectors_Supplement
|
||||
blk; Wancho ; Wancho
|
||||
blk; Warang_Citi ; Warang_Citi
|
||||
blk; Yi_Radicals ; Yi_Radicals
|
||||
blk; Yi_Syllables ; Yi_Syllables
|
||||
@ -1213,6 +1228,7 @@ sc ; Dsrt ; Deseret
|
||||
sc ; Dupl ; Duployan
|
||||
sc ; Egyp ; Egyptian_Hieroglyphs
|
||||
sc ; Elba ; Elbasan
|
||||
sc ; Elym ; Elymaic
|
||||
sc ; Ethi ; Ethiopic
|
||||
sc ; Geor ; Georgian
|
||||
sc ; Glag ; Glagolitic
|
||||
@ -1231,6 +1247,7 @@ sc ; Hebr ; Hebrew
|
||||
sc ; Hira ; Hiragana
|
||||
sc ; Hluw ; Anatolian_Hieroglyphs
|
||||
sc ; Hmng ; Pahawh_Hmong
|
||||
sc ; Hmnp ; Nyiakeng_Puachue_Hmong
|
||||
sc ; Hrkt ; Katakana_Or_Hiragana
|
||||
sc ; Hung ; Old_Hungarian
|
||||
sc ; Ital ; Old_Italic
|
||||
@ -1268,6 +1285,7 @@ sc ; Mroo ; Mro
|
||||
sc ; Mtei ; Meetei_Mayek
|
||||
sc ; Mult ; Multani
|
||||
sc ; Mymr ; Myanmar
|
||||
sc ; Nand ; Nandinagari
|
||||
sc ; Narb ; Old_North_Arabian
|
||||
sc ; Nbat ; Nabataean
|
||||
sc ; Newa ; Newa
|
||||
@ -1324,6 +1342,7 @@ sc ; Tirh ; Tirhuta
|
||||
sc ; Ugar ; Ugaritic
|
||||
sc ; Vaii ; Vai
|
||||
sc ; Wara ; Warang_Citi
|
||||
sc ; Wcho ; Wancho
|
||||
sc ; Xpeo ; Old_Persian
|
||||
sc ; Xsux ; Cuneiform
|
||||
sc ; Yiii ; Yi
|
@ -1,6 +1,6 @@
|
||||
# Scripts-11.0.0.txt
|
||||
# Date: 2018-02-21, 05:34:31 GMT
|
||||
# Copyright (c) 2018 Unicode, Inc.
|
||||
# Scripts-12.1.0.txt
|
||||
# Date: 2019-04-01, 09:10:42 GMT
|
||||
# Copyright (c) 2019 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
|
||||
#
|
||||
@ -108,10 +108,10 @@
|
||||
1CD3 ; Common # Po VEDIC SIGN NIHSHVASA
|
||||
1CE1 ; Common # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA
|
||||
1CE9..1CEC ; Common # Lo [4] VEDIC SIGN ANUSVARA ANTARGOMUKHA..VEDIC SIGN ANUSVARA VAMAGOMUKHA WITH TAIL
|
||||
1CEE..1CF1 ; Common # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA
|
||||
1CF2..1CF3 ; Common # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
|
||||
1CEE..1CF3 ; Common # Lo [6] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ROTATED ARDHAVISARGA
|
||||
1CF5..1CF6 ; Common # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA
|
||||
1CF7 ; Common # Mc VEDIC SIGN ATIKRAMA
|
||||
1CFA ; Common # Lo VEDIC SIGN DOUBLE ANUSVARA ANTARGOMUKHA
|
||||
2000..200A ; Common # Zs [11] EN QUAD..HAIR SPACE
|
||||
200B ; Common # Cf ZERO WIDTH SPACE
|
||||
200E..200F ; Common # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
|
||||
@ -308,8 +308,7 @@
|
||||
2B47..2B4C ; Common # Sm [6] REVERSE TILDE OPERATOR ABOVE RIGHTWARDS ARROW..RIGHTWARDS ARROW ABOVE REVERSE TILDE OPERATOR
|
||||
2B4D..2B73 ; Common # So [39] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR
|
||||
2B76..2B95 ; Common # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW
|
||||
2B98..2BC8 ; Common # So [49] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
|
||||
2BCA..2BFE ; Common # So [53] TOP HALF BLACK CIRCLE..REVERSED RIGHT ANGLE
|
||||
2B98..2BFF ; Common # So [104] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..HELLSCHREIBER PAUSE SYMBOL
|
||||
2E00..2E01 ; Common # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER
|
||||
2E02 ; Common # Pi LEFT SUBSTITUTION BRACKET
|
||||
2E03 ; Common # Pf RIGHT SUBSTITUTION BRACKET
|
||||
@ -347,7 +346,7 @@
|
||||
2E40 ; Common # Pd DOUBLE HYPHEN
|
||||
2E41 ; Common # Po REVERSED COMMA
|
||||
2E42 ; Common # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK
|
||||
2E43..2E4E ; Common # Po [12] DASH WITH LEFT UPTURN..PUNCTUS ELEVATUS MARK
|
||||
2E43..2E4F ; Common # Po [13] DASH WITH LEFT UPTURN..CORNISH VERSE DIVIDER
|
||||
2FF0..2FFB ; Common # So [12] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
|
||||
3000 ; Common # Zs IDEOGRAPHIC SPACE
|
||||
3001..3003 ; Common # Po [3] IDEOGRAPHIC COMMA..DITTO MARK
|
||||
@ -400,6 +399,7 @@
|
||||
328A..32B0 ; Common # So [39] CIRCLED IDEOGRAPH MOON..CIRCLED IDEOGRAPH NIGHT
|
||||
32B1..32BF ; Common # No [15] CIRCLED NUMBER THIRTY SIX..CIRCLED NUMBER FIFTY
|
||||
32C0..32CF ; Common # So [16] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..LIMITED LIABILITY SIGN
|
||||
32FF ; Common # So SQUARE ERA NAME REIWA
|
||||
3358..33FF ; Common # So [168] IDEOGRAPHIC TELEGRAPH SYMBOL FOR HOUR ZERO..SQUARE GAL
|
||||
4DC0..4DFF ; Common # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION
|
||||
A700..A716 ; Common # Sk [23] MODIFIER LETTER CHINESE TONE YIN PING..MODIFIER LETTER EXTRA-LOW LEFT-STEM TONE BAR
|
||||
@ -509,6 +509,8 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
|
||||
10190..1019B ; Common # So [12] ROMAN SEXTANS SIGN..ROMAN CENTURIAL SIGN
|
||||
101D0..101FC ; Common # So [45] PHAISTOS DISC SIGN PEDESTRIAN..PHAISTOS DISC SIGN WAVY BAND
|
||||
102E1..102FB ; Common # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED
|
||||
16FE2 ; Common # Po OLD CHINESE HOOK MARK
|
||||
16FE3 ; Common # Lm OLD CHINESE ITERATION MARK
|
||||
1BCA0..1BCA3 ; Common # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
|
||||
1D000..1D0F5 ; Common # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO
|
||||
1D100..1D126 ; Common # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2
|
||||
@ -569,6 +571,9 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
|
||||
1ECAD..1ECAF ; Common # No [3] INDIC SIYAQ FRACTION ONE QUARTER..INDIC SIYAQ FRACTION THREE QUARTERS
|
||||
1ECB0 ; Common # Sc INDIC SIYAQ RUPEE MARK
|
||||
1ECB1..1ECB4 ; Common # No [4] INDIC SIYAQ NUMBER ALTERNATE ONE..INDIC SIYAQ ALTERNATE LAKH MARK
|
||||
1ED01..1ED2D ; Common # No [45] OTTOMAN SIYAQ NUMBER ONE..OTTOMAN SIYAQ NUMBER NINETY THOUSAND
|
||||
1ED2E ; Common # So OTTOMAN SIYAQ MARRATAN
|
||||
1ED2F..1ED3D ; Common # No [15] OTTOMAN SIYAQ ALTERNATE NUMBER TWO..OTTOMAN SIYAQ FRACTION ONE SIXTH
|
||||
1F000..1F02B ; Common # So [44] MAHJONG TILE EAST WIND..MAHJONG TILE BACK
|
||||
1F030..1F093 ; Common # So [100] DOMINO TILE HORIZONTAL BACK..DOMINO TILE VERTICAL-06-06
|
||||
1F0A0..1F0AE ; Common # So [15] PLAYING CARD BACK..PLAYING CARD KING OF SPADES
|
||||
@ -576,7 +581,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
|
||||
1F0C1..1F0CF ; Common # So [15] PLAYING CARD ACE OF DIAMONDS..PLAYING CARD BLACK JOKER
|
||||
1F0D1..1F0F5 ; Common # So [37] PLAYING CARD ACE OF CLUBS..PLAYING CARD TRUMP-21
|
||||
1F100..1F10C ; Common # No [13] DIGIT ZERO FULL STOP..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO
|
||||
1F110..1F16B ; Common # So [92] PARENTHESIZED LATIN CAPITAL LETTER A..RAISED MD SIGN
|
||||
1F110..1F16C ; Common # So [93] PARENTHESIZED LATIN CAPITAL LETTER A..RAISED MR SIGN
|
||||
1F170..1F1AC ; Common # So [61] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VOD
|
||||
1F1E6..1F1FF ; Common # So [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z
|
||||
1F201..1F202 ; Common # So [2] SQUARED KATAKANA KOKO..SQUARED KATAKANA SA
|
||||
@ -586,30 +591,33 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
|
||||
1F260..1F265 ; Common # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI
|
||||
1F300..1F3FA ; Common # So [251] CYCLONE..AMPHORA
|
||||
1F3FB..1F3FF ; Common # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
|
||||
1F400..1F6D4 ; Common # So [725] RAT..PAGODA
|
||||
1F400..1F6D5 ; Common # So [726] RAT..HINDU TEMPLE
|
||||
1F6E0..1F6EC ; Common # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING
|
||||
1F6F0..1F6F9 ; Common # So [10] SATELLITE..SKATEBOARD
|
||||
1F6F0..1F6FA ; Common # So [11] SATELLITE..AUTO RICKSHAW
|
||||
1F700..1F773 ; Common # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
|
||||
1F780..1F7D8 ; Common # So [89] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NEGATIVE CIRCLED SQUARE
|
||||
1F7E0..1F7EB ; Common # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE
|
||||
1F800..1F80B ; Common # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD
|
||||
1F810..1F847 ; Common # So [56] LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW
|
||||
1F850..1F859 ; Common # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW
|
||||
1F860..1F887 ; Common # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW
|
||||
1F890..1F8AD ; Common # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS
|
||||
1F900..1F90B ; Common # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT
|
||||
1F910..1F93E ; Common # So [47] ZIPPER-MOUTH FACE..HANDBALL
|
||||
1F940..1F970 ; Common # So [49] WILTED FLOWER..SMILING FACE WITH SMILING EYES AND THREE HEARTS
|
||||
1F90D..1F971 ; Common # So [101] WHITE HEART..YAWNING FACE
|
||||
1F973..1F976 ; Common # So [4] FACE WITH PARTY HORN AND PARTY HAT..FREEZING FACE
|
||||
1F97A ; Common # So FACE WITH PLEADING EYES
|
||||
1F97C..1F9A2 ; Common # So [39] LAB COAT..SWAN
|
||||
1F9B0..1F9B9 ; Common # So [10] EMOJI COMPONENT RED HAIR..SUPERVILLAIN
|
||||
1F9C0..1F9C2 ; Common # So [3] CHEESE WEDGE..SALT SHAKER
|
||||
1F9D0..1F9FF ; Common # So [48] FACE WITH MONOCLE..NAZAR AMULET
|
||||
1F97A..1F9A2 ; Common # So [41] FACE WITH PLEADING EYES..SWAN
|
||||
1F9A5..1F9AA ; Common # So [6] SLOTH..OYSTER
|
||||
1F9AE..1F9CA ; Common # So [29] GUIDE DOG..ICE CUBE
|
||||
1F9CD..1FA53 ; Common # So [135] STANDING PERSON..BLACK CHESS KNIGHT-BISHOP
|
||||
1FA60..1FA6D ; Common # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER
|
||||
1FA70..1FA73 ; Common # So [4] BALLET SHOES..SHORTS
|
||||
1FA78..1FA7A ; Common # So [3] DROP OF BLOOD..STETHOSCOPE
|
||||
1FA80..1FA82 ; Common # So [3] YO-YO..PARACHUTE
|
||||
1FA90..1FA95 ; Common # So [6] RINGED PLANET..BANJO
|
||||
E0001 ; Common # Cf LANGUAGE TAG
|
||||
E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
|
||||
|
||||
# Total code points: 7591
|
||||
# Total code points: 7805
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -652,7 +660,8 @@ A770 ; Latin # Lm MODIFIER LETTER US
|
||||
A771..A787 ; Latin # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T
|
||||
A78B..A78E ; Latin # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
|
||||
A78F ; Latin # Lo LATIN LETTER SINOLOGICAL DOT
|
||||
A790..A7B9 ; Latin # L& [42] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER U WITH STROKE
|
||||
A790..A7BF ; Latin # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U
|
||||
A7C2..A7C6 ; Latin # L& [5] LATIN CAPITAL LETTER ANGLICANA W..LATIN CAPITAL LETTER Z WITH PALATAL HOOK
|
||||
A7F7 ; Latin # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I
|
||||
A7F8..A7F9 ; Latin # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
|
||||
A7FA ; Latin # L& LATIN LETTER SMALL CAPITAL TURNED M
|
||||
@ -660,11 +669,12 @@ A7FB..A7FF ; Latin # Lo [5] LATIN EPIGRAPHIC LETTER REVERSED F..LATIN EPIGR
|
||||
AB30..AB5A ; Latin # L& [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG
|
||||
AB5C..AB5F ; Latin # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK
|
||||
AB60..AB64 ; Latin # L& [5] LATIN SMALL LETTER SAKHA YAT..LATIN SMALL LETTER INVERTED ALPHA
|
||||
AB66..AB67 ; Latin # L& [2] LATIN SMALL LETTER DZ DIGRAPH WITH RETROFLEX HOOK..LATIN SMALL LETTER TS DIGRAPH WITH RETROFLEX HOOK
|
||||
FB00..FB06 ; Latin # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST
|
||||
FF21..FF3A ; Latin # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z
|
||||
FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z
|
||||
|
||||
# Total code points: 1353
|
||||
# Total code points: 1366
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -914,7 +924,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
|
||||
094D ; Devanagari # Mn DEVANAGARI SIGN VIRAMA
|
||||
094E..094F ; Devanagari # Mc [2] DEVANAGARI VOWEL SIGN PRISHTHAMATRA E..DEVANAGARI VOWEL SIGN AW
|
||||
0950 ; Devanagari # Lo DEVANAGARI OM
|
||||
0953..0957 ; Devanagari # Mn [5] DEVANAGARI GRAVE ACCENT..DEVANAGARI VOWEL SIGN UUE
|
||||
0955..0957 ; Devanagari # Mn [3] DEVANAGARI VOWEL SIGN CANDRA LONG E..DEVANAGARI VOWEL SIGN UUE
|
||||
0958..0961 ; Devanagari # Lo [10] DEVANAGARI LETTER QA..DEVANAGARI LETTER VOCALIC LL
|
||||
0962..0963 ; Devanagari # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL
|
||||
0966..096F ; Devanagari # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE
|
||||
@ -929,7 +939,7 @@ A8FC ; Devanagari # Po DEVANAGARI SIGN SIDDHAM
|
||||
A8FD..A8FE ; Devanagari # Lo [2] DEVANAGARI JAIN OM..DEVANAGARI LETTER AY
|
||||
A8FF ; Devanagari # Mn DEVANAGARI VOWEL SIGN AY
|
||||
|
||||
# Total code points: 156
|
||||
# Total code points: 154
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -1079,8 +1089,13 @@ A8FF ; Devanagari # Mn DEVANAGARI VOWEL SIGN AY
|
||||
0BF3..0BF8 ; Tamil # So [6] TAMIL DAY SIGN..TAMIL AS ABOVE SIGN
|
||||
0BF9 ; Tamil # Sc TAMIL RUPEE SIGN
|
||||
0BFA ; Tamil # So TAMIL NUMBER SIGN
|
||||
11FC0..11FD4 ; Tamil # No [21] TAMIL FRACTION ONE THREE-HUNDRED-AND-TWENTIETH..TAMIL FRACTION DOWNSCALING FACTOR KIIZH
|
||||
11FD5..11FDC ; Tamil # So [8] TAMIL SIGN NEL..TAMIL SIGN MUKKURUNI
|
||||
11FDD..11FE0 ; Tamil # Sc [4] TAMIL SIGN KAACU..TAMIL SIGN VARAAKAN
|
||||
11FE1..11FF1 ; Tamil # So [17] TAMIL SIGN PAARAM..TAMIL SIGN VAKAIYARAA
|
||||
11FFF ; Tamil # Po TAMIL PUNCTUATION END OF TEXT
|
||||
|
||||
# Total code points: 72
|
||||
# Total code points: 123
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -1101,10 +1116,11 @@ A8FF ; Devanagari # Mn DEVANAGARI VOWEL SIGN AY
|
||||
0C60..0C61 ; Telugu # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL
|
||||
0C62..0C63 ; Telugu # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL
|
||||
0C66..0C6F ; Telugu # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE
|
||||
0C77 ; Telugu # Po TELUGU SIGN SIDDHAM
|
||||
0C78..0C7E ; Telugu # No [7] TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR..TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR
|
||||
0C7F ; Telugu # So TELUGU SIGN TUUMU
|
||||
|
||||
# Total code points: 97
|
||||
# Total code points: 98
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -1202,20 +1218,13 @@ A8FF ; Devanagari # Mn DEVANAGARI VOWEL SIGN AY
|
||||
|
||||
0E81..0E82 ; Lao # Lo [2] LAO LETTER KO..LAO LETTER KHO SUNG
|
||||
0E84 ; Lao # Lo LAO LETTER KHO TAM
|
||||
0E87..0E88 ; Lao # Lo [2] LAO LETTER NGO..LAO LETTER CO
|
||||
0E8A ; Lao # Lo LAO LETTER SO TAM
|
||||
0E8D ; Lao # Lo LAO LETTER NYO
|
||||
0E94..0E97 ; Lao # Lo [4] LAO LETTER DO..LAO LETTER THO TAM
|
||||
0E99..0E9F ; Lao # Lo [7] LAO LETTER NO..LAO LETTER FO SUNG
|
||||
0EA1..0EA3 ; Lao # Lo [3] LAO LETTER MO..LAO LETTER LO LING
|
||||
0E86..0E8A ; Lao # Lo [5] LAO LETTER PALI GHA..LAO LETTER SO TAM
|
||||
0E8C..0EA3 ; Lao # Lo [24] LAO LETTER PALI JHA..LAO LETTER LO LING
|
||||
0EA5 ; Lao # Lo LAO LETTER LO LOOT
|
||||
0EA7 ; Lao # Lo LAO LETTER WO
|
||||
0EAA..0EAB ; Lao # Lo [2] LAO LETTER SO SUNG..LAO LETTER HO SUNG
|
||||
0EAD..0EB0 ; Lao # Lo [4] LAO LETTER O..LAO VOWEL SIGN A
|
||||
0EA7..0EB0 ; Lao # Lo [10] LAO LETTER WO..LAO VOWEL SIGN A
|
||||
0EB1 ; Lao # Mn LAO VOWEL SIGN MAI KAN
|
||||
0EB2..0EB3 ; Lao # Lo [2] LAO VOWEL SIGN AA..LAO VOWEL SIGN AM
|
||||
0EB4..0EB9 ; Lao # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU
|
||||
0EBB..0EBC ; Lao # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO
|
||||
0EB4..0EBC ; Lao # Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO
|
||||
0EBD ; Lao # Lo LAO SEMIVOWEL SIGN NYO
|
||||
0EC0..0EC4 ; Lao # Lo [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI
|
||||
0EC6 ; Lao # Lm LAO KO LA
|
||||
@ -1223,7 +1232,7 @@ A8FF ; Devanagari # Mn DEVANAGARI VOWEL SIGN AY
|
||||
0ED0..0ED9 ; Lao # Nd [10] LAO DIGIT ZERO..LAO DIGIT NINE
|
||||
0EDC..0EDF ; Lao # Lo [4] LAO HO NO..LAO LETTER KHMU NYO
|
||||
|
||||
# Total code points: 67
|
||||
# Total code points: 82
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -1409,7 +1418,8 @@ AB70..ABBF ; Cherokee # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETT
|
||||
|
||||
1400 ; Canadian_Aboriginal # Pd CANADIAN SYLLABICS HYPHEN
|
||||
1401..166C ; Canadian_Aboriginal # Lo [620] CANADIAN SYLLABICS E..CANADIAN SYLLABICS CARRIER TTSA
|
||||
166D..166E ; Canadian_Aboriginal # Po [2] CANADIAN SYLLABICS CHI SIGN..CANADIAN SYLLABICS FULL STOP
|
||||
166D ; Canadian_Aboriginal # So CANADIAN SYLLABICS CHI SIGN
|
||||
166E ; Canadian_Aboriginal # Po CANADIAN SYLLABICS FULL STOP
|
||||
166F..167F ; Canadian_Aboriginal # Lo [17] CANADIAN SYLLABICS QAI..CANADIAN SYLLABICS BLACKFOOT W
|
||||
18B0..18F5 ; Canadian_Aboriginal # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S
|
||||
|
||||
@ -1481,9 +1491,10 @@ AB70..ABBF ; Cherokee # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETT
|
||||
309D..309E ; Hiragana # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK
|
||||
309F ; Hiragana # Lo HIRAGANA DIGRAPH YORI
|
||||
1B001..1B11E ; Hiragana # Lo [286] HIRAGANA LETTER ARCHAIC YE..HENTAIGANA LETTER N-MU-MO-2
|
||||
1B150..1B152 ; Hiragana # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO
|
||||
1F200 ; Hiragana # So SQUARE HIRAGANA HOKA
|
||||
|
||||
# Total code points: 376
|
||||
# Total code points: 379
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -1496,8 +1507,9 @@ AB70..ABBF ; Cherokee # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETT
|
||||
FF66..FF6F ; Katakana # Lo [10] HALFWIDTH KATAKANA LETTER WO..HALFWIDTH KATAKANA LETTER SMALL TU
|
||||
FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAKANA LETTER N
|
||||
1B000 ; Katakana # Lo KATAKANA LETTER ARCHAIC E
|
||||
1B164..1B167 ; Katakana # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N
|
||||
|
||||
# Total code points: 300
|
||||
# Total code points: 304
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -1568,7 +1580,7 @@ A490..A4C6 ; Yi # So [55] YI RADICAL QOT..YI RADICAL KE
|
||||
0485..0486 ; Inherited # Mn [2] COMBINING CYRILLIC DASIA PNEUMATA..COMBINING CYRILLIC PSILI PNEUMATA
|
||||
064B..0655 ; Inherited # Mn [11] ARABIC FATHATAN..ARABIC HAMZA BELOW
|
||||
0670 ; Inherited # Mn ARABIC LETTER SUPERSCRIPT ALEF
|
||||
0951..0952 ; Inherited # Mn [2] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI STRESS SIGN ANUDATTA
|
||||
0951..0954 ; Inherited # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT
|
||||
1AB0..1ABD ; Inherited # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW
|
||||
1ABE ; Inherited # Me COMBINING PARENTHESES OVERLAY
|
||||
1CD0..1CD2 ; Inherited # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA
|
||||
@ -1598,7 +1610,7 @@ FE20..FE2D ; Inherited # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CON
|
||||
1D1AA..1D1AD ; Inherited # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
|
||||
E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
|
||||
|
||||
# Total code points: 569
|
||||
# Total code points: 571
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -2028,8 +2040,9 @@ AADE..AADF ; Tai_Viet # Po [2] TAI VIET SYMBOL HO HOI..TAI VIET SYMBOL KOI
|
||||
# ================================================
|
||||
|
||||
13000..1342E ; Egyptian_Hieroglyphs # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
|
||||
13430..13438 ; Egyptian_Hieroglyphs # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT
|
||||
|
||||
# Total code points: 1071
|
||||
# Total code points: 1080
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -2072,8 +2085,8 @@ A9B3 ; Javanese # Mn JAVANESE SIGN CECAK TELU
|
||||
A9B4..A9B5 ; Javanese # Mc [2] JAVANESE VOWEL SIGN TARUNG..JAVANESE VOWEL SIGN TOLONG
|
||||
A9B6..A9B9 ; Javanese # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT
|
||||
A9BA..A9BB ; Javanese # Mc [2] JAVANESE VOWEL SIGN TALING..JAVANESE VOWEL SIGN DIRGA MURE
|
||||
A9BC ; Javanese # Mn JAVANESE VOWEL SIGN PEPET
|
||||
A9BD..A9C0 ; Javanese # Mc [4] JAVANESE CONSONANT SIGN KERET..JAVANESE PANGKON
|
||||
A9BC..A9BD ; Javanese # Mn [2] JAVANESE VOWEL SIGN PEPET..JAVANESE CONSONANT SIGN KERET
|
||||
A9BE..A9C0 ; Javanese # Mc [3] JAVANESE CONSONANT SIGN PENGKAL..JAVANESE PANGKON
|
||||
A9C1..A9CD ; Javanese # Po [13] JAVANESE LEFT RERENGGAN..JAVANESE TURNED PADA PISELEH
|
||||
A9D0..A9D9 ; Javanese # Nd [10] JAVANESE DIGIT ZERO..JAVANESE DIGIT NINE
|
||||
A9DE..A9DF ; Javanese # Po [2] JAVANESE PADA TIRTA TUMETES..JAVANESE PADA ISEN-ISEN
|
||||
@ -2225,13 +2238,14 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
|
||||
|
||||
# ================================================
|
||||
|
||||
16F00..16F44 ; Miao # Lo [69] MIAO LETTER PA..MIAO LETTER HHA
|
||||
16F00..16F4A ; Miao # Lo [75] MIAO LETTER PA..MIAO LETTER RTE
|
||||
16F4F ; Miao # Mn MIAO SIGN CONSONANT MODIFIER BAR
|
||||
16F50 ; Miao # Lo MIAO LETTER NASALIZATION
|
||||
16F51..16F7E ; Miao # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
|
||||
16F51..16F87 ; Miao # Mc [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI
|
||||
16F8F..16F92 ; Miao # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
|
||||
16F93..16F9F ; Miao # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8
|
||||
|
||||
# Total code points: 133
|
||||
# Total code points: 149
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -2270,9 +2284,10 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
|
||||
116B0..116B5 ; Takri # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU
|
||||
116B6 ; Takri # Mc TAKRI SIGN VIRAMA
|
||||
116B7 ; Takri # Mn TAKRI SIGN NUKTA
|
||||
116B8 ; Takri # Lo TAKRI LETTER ARCHAIC KHA
|
||||
116C0..116C9 ; Takri # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE
|
||||
|
||||
# Total code points: 66
|
||||
# Total code points: 67
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -2587,10 +2602,11 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
|
||||
|
||||
1E900..1E943 ; Adlam # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA
|
||||
1E944..1E94A ; Adlam # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA
|
||||
1E94B ; Adlam # Lm ADLAM NASALIZATION MARK
|
||||
1E950..1E959 ; Adlam # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE
|
||||
1E95E..1E95F ; Adlam # Po [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK
|
||||
|
||||
# Total code points: 87
|
||||
# Total code points: 88
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -2637,8 +2653,9 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
|
||||
1145B ; Newa # Po NEWA PLACEHOLDER MARK
|
||||
1145D ; Newa # Po NEWA INSERTION SIGN
|
||||
1145E ; Newa # Mn NEWA SANDHI MARK
|
||||
1145F ; Newa # Lo NEWA LETTER VEDIC ANUSVARA
|
||||
|
||||
# Total code points: 93
|
||||
# Total code points: 94
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -2650,10 +2667,10 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
|
||||
# ================================================
|
||||
|
||||
16FE0 ; Tangut # Lm TANGUT ITERATION MARK
|
||||
17000..187F1 ; Tangut # Lo [6130] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F1
|
||||
17000..187F7 ; Tangut # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7
|
||||
18800..18AF2 ; Tangut # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
|
||||
|
||||
# Total code points: 6886
|
||||
# Total code points: 6892
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -2683,8 +2700,7 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
|
||||
11A51..11A56 ; Soyombo # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE
|
||||
11A57..11A58 ; Soyombo # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU
|
||||
11A59..11A5B ; Soyombo # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK
|
||||
11A5C..11A83 ; Soyombo # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA
|
||||
11A86..11A89 ; Soyombo # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA
|
||||
11A5C..11A89 ; Soyombo # Lo [46] SOYOMBO LETTER KA..SOYOMBO CLUSTER-INITIAL LETTER SA
|
||||
11A8A..11A96 ; Soyombo # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA
|
||||
11A97 ; Soyombo # Mc SOYOMBO SIGN VISARGA
|
||||
11A98..11A99 ; Soyombo # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER
|
||||
@ -2692,7 +2708,7 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
|
||||
11A9D ; Soyombo # Lo SOYOMBO MARK PLUTA
|
||||
11A9E..11AA2 ; Soyombo # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2
|
||||
|
||||
# Total code points: 81
|
||||
# Total code points: 83
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -2777,4 +2793,46 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
|
||||
|
||||
# Total code points: 40
|
||||
|
||||
# ================================================
|
||||
|
||||
10FE0..10FF6 ; Elymaic # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH
|
||||
|
||||
# Total code points: 23
|
||||
|
||||
# ================================================
|
||||
|
||||
119A0..119A7 ; Nandinagari # Lo [8] NANDINAGARI LETTER A..NANDINAGARI LETTER VOCALIC RR
|
||||
119AA..119D0 ; Nandinagari # Lo [39] NANDINAGARI LETTER E..NANDINAGARI LETTER RRA
|
||||
119D1..119D3 ; Nandinagari # Mc [3] NANDINAGARI VOWEL SIGN AA..NANDINAGARI VOWEL SIGN II
|
||||
119D4..119D7 ; Nandinagari # Mn [4] NANDINAGARI VOWEL SIGN U..NANDINAGARI VOWEL SIGN VOCALIC RR
|
||||
119DA..119DB ; Nandinagari # Mn [2] NANDINAGARI VOWEL SIGN E..NANDINAGARI VOWEL SIGN AI
|
||||
119DC..119DF ; Nandinagari # Mc [4] NANDINAGARI VOWEL SIGN O..NANDINAGARI SIGN VISARGA
|
||||
119E0 ; Nandinagari # Mn NANDINAGARI SIGN VIRAMA
|
||||
119E1 ; Nandinagari # Lo NANDINAGARI SIGN AVAGRAHA
|
||||
119E2 ; Nandinagari # Po NANDINAGARI SIGN SIDDHAM
|
||||
119E3 ; Nandinagari # Lo NANDINAGARI HEADSTROKE
|
||||
119E4 ; Nandinagari # Mc NANDINAGARI VOWEL SIGN PRISHTHAMATRA E
|
||||
|
||||
# Total code points: 65
|
||||
|
||||
# ================================================
|
||||
|
||||
1E100..1E12C ; Nyiakeng_Puachue_Hmong # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W
|
||||
1E130..1E136 ; Nyiakeng_Puachue_Hmong # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
|
||||
1E137..1E13D ; Nyiakeng_Puachue_Hmong # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER
|
||||
1E140..1E149 ; Nyiakeng_Puachue_Hmong # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE
|
||||
1E14E ; Nyiakeng_Puachue_Hmong # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ
|
||||
1E14F ; Nyiakeng_Puachue_Hmong # So NYIAKENG PUACHUE HMONG CIRCLED CA
|
||||
|
||||
# Total code points: 71
|
||||
|
||||
# ================================================
|
||||
|
||||
1E2C0..1E2EB ; Wancho # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH
|
||||
1E2EC..1E2EF ; Wancho # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI
|
||||
1E2F0..1E2F9 ; Wancho # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE
|
||||
1E2FF ; Wancho # Sc WANCHO NGUN SIGN
|
||||
|
||||
# Total code points: 59
|
||||
|
||||
# EOF
|
||||
|
@ -1,6 +1,6 @@
|
||||
# SpecialCasing-11.0.0.txt
|
||||
# Date: 2018-02-22, 06:16:47 GMT
|
||||
# Copyright (c) 2018 Unicode, Inc.
|
||||
# SpecialCasing-12.1.0.txt
|
||||
# Date: 2019-03-10, 10:53:28 GMT
|
||||
# Copyright (c) 2019 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
|
||||
#
|
||||
|
@ -640,7 +640,7 @@
|
||||
027F;LATIN SMALL LETTER REVERSED R WITH FISHHOOK;Ll;0;L;;;;;N;LATIN SMALL LETTER REVERSED FISHHOOK R;;;;
|
||||
0280;LATIN LETTER SMALL CAPITAL R;Ll;0;L;;;;;N;;;01A6;;01A6
|
||||
0281;LATIN LETTER SMALL CAPITAL INVERTED R;Ll;0;L;;;;;N;;;;;
|
||||
0282;LATIN SMALL LETTER S WITH HOOK;Ll;0;L;;;;;N;LATIN SMALL LETTER S HOOK;;;;
|
||||
0282;LATIN SMALL LETTER S WITH HOOK;Ll;0;L;;;;;N;LATIN SMALL LETTER S HOOK;;A7C5;;A7C5
|
||||
0283;LATIN SMALL LETTER ESH;Ll;0;L;;;;;N;;;01A9;;01A9
|
||||
0284;LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK;Ll;0;L;;;;;N;LATIN SMALL LETTER DOTLESS J BAR HOOK;;;;
|
||||
0285;LATIN SMALL LETTER SQUAT REVERSED ESH;Ll;0;L;;;;;N;;;;;
|
||||
@ -2809,6 +2809,7 @@
|
||||
0C6D;TELUGU DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;;
|
||||
0C6E;TELUGU DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;;
|
||||
0C6F;TELUGU DIGIT NINE;Nd;0;L;;9;9;9;N;;;;;
|
||||
0C77;TELUGU SIGN SIDDHAM;Po;0;L;;;;;N;;;;;
|
||||
0C78;TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR;No;0;ON;;;;0;N;;;;;
|
||||
0C79;TELUGU FRACTION DIGIT ONE FOR ODD POWERS OF FOUR;No;0;ON;;;;1;N;;;;;
|
||||
0C7A;TELUGU FRACTION DIGIT TWO FOR ODD POWERS OF FOUR;No;0;ON;;;;2;N;;;;;
|
||||
@ -3203,14 +3204,24 @@
|
||||
0E81;LAO LETTER KO;Lo;0;L;;;;;N;;;;;
|
||||
0E82;LAO LETTER KHO SUNG;Lo;0;L;;;;;N;;;;;
|
||||
0E84;LAO LETTER KHO TAM;Lo;0;L;;;;;N;;;;;
|
||||
0E86;LAO LETTER PALI GHA;Lo;0;L;;;;;N;;;;;
|
||||
0E87;LAO LETTER NGO;Lo;0;L;;;;;N;;;;;
|
||||
0E88;LAO LETTER CO;Lo;0;L;;;;;N;;;;;
|
||||
0E89;LAO LETTER PALI CHA;Lo;0;L;;;;;N;;;;;
|
||||
0E8A;LAO LETTER SO TAM;Lo;0;L;;;;;N;;;;;
|
||||
0E8C;LAO LETTER PALI JHA;Lo;0;L;;;;;N;;;;;
|
||||
0E8D;LAO LETTER NYO;Lo;0;L;;;;;N;;;;;
|
||||
0E8E;LAO LETTER PALI NYA;Lo;0;L;;;;;N;;;;;
|
||||
0E8F;LAO LETTER PALI TTA;Lo;0;L;;;;;N;;;;;
|
||||
0E90;LAO LETTER PALI TTHA;Lo;0;L;;;;;N;;;;;
|
||||
0E91;LAO LETTER PALI DDA;Lo;0;L;;;;;N;;;;;
|
||||
0E92;LAO LETTER PALI DDHA;Lo;0;L;;;;;N;;;;;
|
||||
0E93;LAO LETTER PALI NNA;Lo;0;L;;;;;N;;;;;
|
||||
0E94;LAO LETTER DO;Lo;0;L;;;;;N;;;;;
|
||||
0E95;LAO LETTER TO;Lo;0;L;;;;;N;;;;;
|
||||
0E96;LAO LETTER THO SUNG;Lo;0;L;;;;;N;;;;;
|
||||
0E97;LAO LETTER THO TAM;Lo;0;L;;;;;N;;;;;
|
||||
0E98;LAO LETTER PALI DHA;Lo;0;L;;;;;N;;;;;
|
||||
0E99;LAO LETTER NO;Lo;0;L;;;;;N;;;;;
|
||||
0E9A;LAO LETTER BO;Lo;0;L;;;;;N;;;;;
|
||||
0E9B;LAO LETTER PO;Lo;0;L;;;;;N;;;;;
|
||||
@ -3218,13 +3229,17 @@
|
||||
0E9D;LAO LETTER FO TAM;Lo;0;L;;;;;N;;;;;
|
||||
0E9E;LAO LETTER PHO TAM;Lo;0;L;;;;;N;;;;;
|
||||
0E9F;LAO LETTER FO SUNG;Lo;0;L;;;;;N;;;;;
|
||||
0EA0;LAO LETTER PALI BHA;Lo;0;L;;;;;N;;;;;
|
||||
0EA1;LAO LETTER MO;Lo;0;L;;;;;N;;;;;
|
||||
0EA2;LAO LETTER YO;Lo;0;L;;;;;N;;;;;
|
||||
0EA3;LAO LETTER LO LING;Lo;0;L;;;;;N;;;;;
|
||||
0EA5;LAO LETTER LO LOOT;Lo;0;L;;;;;N;;;;;
|
||||
0EA7;LAO LETTER WO;Lo;0;L;;;;;N;;;;;
|
||||
0EA8;LAO LETTER SANSKRIT SHA;Lo;0;L;;;;;N;;;;;
|
||||
0EA9;LAO LETTER SANSKRIT SSA;Lo;0;L;;;;;N;;;;;
|
||||
0EAA;LAO LETTER SO SUNG;Lo;0;L;;;;;N;;;;;
|
||||
0EAB;LAO LETTER HO SUNG;Lo;0;L;;;;;N;;;;;
|
||||
0EAC;LAO LETTER PALI LLA;Lo;0;L;;;;;N;;;;;
|
||||
0EAD;LAO LETTER O;Lo;0;L;;;;;N;;;;;
|
||||
0EAE;LAO LETTER HO TAM;Lo;0;L;;;;;N;;;;;
|
||||
0EAF;LAO ELLIPSIS;Lo;0;L;;;;;N;;;;;
|
||||
@ -3238,6 +3253,7 @@
|
||||
0EB7;LAO VOWEL SIGN YY;Mn;0;NSM;;;;;N;;;;;
|
||||
0EB8;LAO VOWEL SIGN U;Mn;118;NSM;;;;;N;;;;;
|
||||
0EB9;LAO VOWEL SIGN UU;Mn;118;NSM;;;;;N;;;;;
|
||||
0EBA;LAO SIGN PALI VIRAMA;Mn;9;NSM;;;;;N;;;;;
|
||||
0EBB;LAO VOWEL SIGN MAI KON;Mn;0;NSM;;;;;N;;;;;
|
||||
0EBC;LAO SEMIVOWEL SIGN LO;Mn;0;NSM;;;;;N;;;;;
|
||||
0EBD;LAO SEMIVOWEL SIGN NYO;Lo;0;L;;;;;N;;;;;
|
||||
@ -5079,7 +5095,7 @@
|
||||
166A;CANADIAN SYLLABICS CARRIER TTSEE;Lo;0;L;;;;;N;;;;;
|
||||
166B;CANADIAN SYLLABICS CARRIER TTSI;Lo;0;L;;;;;N;;;;;
|
||||
166C;CANADIAN SYLLABICS CARRIER TTSA;Lo;0;L;;;;;N;;;;;
|
||||
166D;CANADIAN SYLLABICS CHI SIGN;Po;0;L;;;;;N;;;;;
|
||||
166D;CANADIAN SYLLABICS CHI SIGN;So;0;L;;;;;N;;;;;
|
||||
166E;CANADIAN SYLLABICS FULL STOP;Po;0;L;;;;;N;;;;;
|
||||
166F;CANADIAN SYLLABICS QAI;Lo;0;L;;;;;N;;;;;
|
||||
1670;CANADIAN SYLLABICS NGAI;Lo;0;L;;;;;N;;;;;
|
||||
@ -6488,14 +6504,15 @@
|
||||
1CEF;VEDIC SIGN LONG ANUSVARA;Lo;0;L;;;;;N;;;;;
|
||||
1CF0;VEDIC SIGN RTHANG LONG ANUSVARA;Lo;0;L;;;;;N;;;;;
|
||||
1CF1;VEDIC SIGN ANUSVARA UBHAYATO MUKHA;Lo;0;L;;;;;N;;;;;
|
||||
1CF2;VEDIC SIGN ARDHAVISARGA;Mc;0;L;;;;;N;;;;;
|
||||
1CF3;VEDIC SIGN ROTATED ARDHAVISARGA;Mc;0;L;;;;;N;;;;;
|
||||
1CF2;VEDIC SIGN ARDHAVISARGA;Lo;0;L;;;;;N;;;;;
|
||||
1CF3;VEDIC SIGN ROTATED ARDHAVISARGA;Lo;0;L;;;;;N;;;;;
|
||||
1CF4;VEDIC TONE CANDRA ABOVE;Mn;230;NSM;;;;;N;;;;;
|
||||
1CF5;VEDIC SIGN JIHVAMULIYA;Lo;0;L;;;;;N;;;;;
|
||||
1CF6;VEDIC SIGN UPADHMANIYA;Lo;0;L;;;;;N;;;;;
|
||||
1CF7;VEDIC SIGN ATIKRAMA;Mc;0;L;;;;;N;;;;;
|
||||
1CF8;VEDIC TONE RING ABOVE;Mn;230;NSM;;;;;N;;;;;
|
||||
1CF9;VEDIC TONE DOUBLE RING ABOVE;Mn;230;NSM;;;;;N;;;;;
|
||||
1CFA;VEDIC SIGN DOUBLE ANUSVARA ANTARGOMUKHA;Lo;0;L;;;;;N;;;;;
|
||||
1D00;LATIN LETTER SMALL CAPITAL A;Ll;0;L;;;;;N;;;;;
|
||||
1D01;LATIN LETTER SMALL CAPITAL AE;Ll;0;L;;;;;N;;;;;
|
||||
1D02;LATIN SMALL LETTER TURNED AE;Ll;0;L;;;;;N;;;;;
|
||||
@ -6638,7 +6655,7 @@
|
||||
1D8B;LATIN SMALL LETTER ESH WITH PALATAL HOOK;Ll;0;L;;;;;N;;;;;
|
||||
1D8C;LATIN SMALL LETTER V WITH PALATAL HOOK;Ll;0;L;;;;;N;;;;;
|
||||
1D8D;LATIN SMALL LETTER X WITH PALATAL HOOK;Ll;0;L;;;;;N;;;;;
|
||||
1D8E;LATIN SMALL LETTER Z WITH PALATAL HOOK;Ll;0;L;;;;;N;;;;;
|
||||
1D8E;LATIN SMALL LETTER Z WITH PALATAL HOOK;Ll;0;L;;;;;N;;;A7C6;;A7C6
|
||||
1D8F;LATIN SMALL LETTER A WITH RETROFLEX HOOK;Ll;0;L;;;;;N;;;;;
|
||||
1D90;LATIN SMALL LETTER ALPHA WITH RETROFLEX HOOK;Ll;0;L;;;;;N;;;;;
|
||||
1D91;LATIN SMALL LETTER D WITH HOOK AND TAIL;Ll;0;L;;;;;N;;;;;
|
||||
@ -10165,6 +10182,7 @@
|
||||
2BC6;BLACK MEDIUM DOWN-POINTING TRIANGLE CENTRED;So;0;ON;;;;;N;;;;;
|
||||
2BC7;BLACK MEDIUM LEFT-POINTING TRIANGLE CENTRED;So;0;ON;;;;;N;;;;;
|
||||
2BC8;BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED;So;0;ON;;;;;N;;;;;
|
||||
2BC9;NEPTUNE FORM TWO;So;0;ON;;;;;N;;;;;
|
||||
2BCA;TOP HALF BLACK CIRCLE;So;0;ON;;;;;N;;;;;
|
||||
2BCB;BOTTOM HALF BLACK CIRCLE;So;0;ON;;;;;N;;;;;
|
||||
2BCC;LIGHT FOUR POINTED BLACK CUSP;So;0;ON;;;;;N;;;;;
|
||||
@ -10218,6 +10236,7 @@
|
||||
2BFC;DOUBLED SYMBOL;So;0;ON;;;;;N;;;;;
|
||||
2BFD;PASSED SYMBOL;So;0;ON;;;;;N;;;;;
|
||||
2BFE;REVERSED RIGHT ANGLE;So;0;ON;;;;;Y;;;;;
|
||||
2BFF;HELLSCHREIBER PAUSE SYMBOL;So;0;ON;;;;;N;;;;;
|
||||
2C00;GLAGOLITIC CAPITAL LETTER AZU;Lu;0;L;;;;;N;;;;2C30;
|
||||
2C01;GLAGOLITIC CAPITAL LETTER BUKY;Lu;0;L;;;;;N;;;;2C31;
|
||||
2C02;GLAGOLITIC CAPITAL LETTER VEDE;Lu;0;L;;;;;N;;;;2C32;
|
||||
@ -10756,6 +10775,7 @@
|
||||
2E4C;MEDIEVAL COMMA;Po;0;ON;;;;;N;;;;;
|
||||
2E4D;PARAGRAPHUS MARK;Po;0;ON;;;;;N;;;;;
|
||||
2E4E;PUNCTUS ELEVATUS MARK;Po;0;ON;;;;;N;;;;;
|
||||
2E4F;CORNISH VERSE DIVIDER;Po;0;ON;;;;;N;;;;;
|
||||
2E80;CJK RADICAL REPEAT;So;0;ON;;;;;N;;;;;
|
||||
2E81;CJK RADICAL CLIFF;So;0;ON;;;;;N;;;;;
|
||||
2E82;CJK RADICAL SECOND ONE;So;0;ON;;;;;N;;;;;
|
||||
@ -11836,7 +11856,7 @@
|
||||
32FC;CIRCLED KATAKANA WI;So;0;L;<circle> 30F0;;;;N;;;;;
|
||||
32FD;CIRCLED KATAKANA WE;So;0;L;<circle> 30F1;;;;N;;;;;
|
||||
32FE;CIRCLED KATAKANA WO;So;0;L;<circle> 30F2;;;;N;;;;;
|
||||
32FF;SQUARE ERA NAME REIWA;So;0;L;<square> 4EE4 548C;;;;N;SQUARED TWO IDEOGRAPHS ERA NAME REIWA;;;;
|
||||
32FF;SQUARE ERA NAME REIWA;So;0;L;<square> 4EE4 548C;;;;N;;;;;
|
||||
3300;SQUARE APAATO;So;0;L;<square> 30A2 30D1 30FC 30C8;;;;N;SQUARED APAATO;;;;
|
||||
3301;SQUARE ARUHUA;So;0;L;<square> 30A2 30EB 30D5 30A1;;;;N;SQUARED ARUHUA;;;;
|
||||
3302;SQUARE ANPEA;So;0;L;<square> 30A2 30F3 30DA 30A2;;;;N;SQUARED ANPEA;;;;
|
||||
@ -14061,7 +14081,7 @@ A790;LATIN CAPITAL LETTER N WITH DESCENDER;Lu;0;L;;;;;N;;;;A791;
|
||||
A791;LATIN SMALL LETTER N WITH DESCENDER;Ll;0;L;;;;;N;;;A790;;A790
|
||||
A792;LATIN CAPITAL LETTER C WITH BAR;Lu;0;L;;;;;N;;;;A793;
|
||||
A793;LATIN SMALL LETTER C WITH BAR;Ll;0;L;;;;;N;;;A792;;A792
|
||||
A794;LATIN SMALL LETTER C WITH PALATAL HOOK;Ll;0;L;;;;;N;;;;;
|
||||
A794;LATIN SMALL LETTER C WITH PALATAL HOOK;Ll;0;L;;;;;N;;;A7C4;;A7C4
|
||||
A795;LATIN SMALL LETTER H WITH PALATAL HOOK;Ll;0;L;;;;;N;;;;;
|
||||
A796;LATIN CAPITAL LETTER B WITH FLOURISH;Lu;0;L;;;;;N;;;;A797;
|
||||
A797;LATIN SMALL LETTER B WITH FLOURISH;Ll;0;L;;;;;N;;;A796;;A796
|
||||
@ -14099,6 +14119,17 @@ A7B6;LATIN CAPITAL LETTER OMEGA;Lu;0;L;;;;;N;;;;A7B7;
|
||||
A7B7;LATIN SMALL LETTER OMEGA;Ll;0;L;;;;;N;;;A7B6;;A7B6
|
||||
A7B8;LATIN CAPITAL LETTER U WITH STROKE;Lu;0;L;;;;;N;;;;A7B9;
|
||||
A7B9;LATIN SMALL LETTER U WITH STROKE;Ll;0;L;;;;;N;;;A7B8;;A7B8
|
||||
A7BA;LATIN CAPITAL LETTER GLOTTAL A;Lu;0;L;;;;;N;;;;A7BB;
|
||||
A7BB;LATIN SMALL LETTER GLOTTAL A;Ll;0;L;;;;;N;;;A7BA;;A7BA
|
||||
A7BC;LATIN CAPITAL LETTER GLOTTAL I;Lu;0;L;;;;;N;;;;A7BD;
|
||||
A7BD;LATIN SMALL LETTER GLOTTAL I;Ll;0;L;;;;;N;;;A7BC;;A7BC
|
||||
A7BE;LATIN CAPITAL LETTER GLOTTAL U;Lu;0;L;;;;;N;;;;A7BF;
|
||||
A7BF;LATIN SMALL LETTER GLOTTAL U;Ll;0;L;;;;;N;;;A7BE;;A7BE
|
||||
A7C2;LATIN CAPITAL LETTER ANGLICANA W;Lu;0;L;;;;;N;;;;A7C3;
|
||||
A7C3;LATIN SMALL LETTER ANGLICANA W;Ll;0;L;;;;;N;;;A7C2;;A7C2
|
||||
A7C4;LATIN CAPITAL LETTER C WITH PALATAL HOOK;Lu;0;L;;;;;N;;;;A794;
|
||||
A7C5;LATIN CAPITAL LETTER S WITH HOOK;Lu;0;L;;;;;N;;;;0282;
|
||||
A7C6;LATIN CAPITAL LETTER Z WITH PALATAL HOOK;Lu;0;L;;;;;N;;;;1D8E;
|
||||
A7F7;LATIN EPIGRAPHIC LETTER SIDEWAYS I;Lo;0;L;;;;;N;;;;;
|
||||
A7F8;MODIFIER LETTER CAPITAL H WITH STROKE;Lm;0;L;<super> 0126;;;;N;;;;;
|
||||
A7F9;MODIFIER LETTER SMALL LIGATURE OE;Lm;0;L;<super> 0153;;;;N;;;;;
|
||||
@ -14507,7 +14538,7 @@ A9B9;JAVANESE VOWEL SIGN SUKU MENDUT;Mn;0;NSM;;;;;N;;;;;
|
||||
A9BA;JAVANESE VOWEL SIGN TALING;Mc;0;L;;;;;N;;;;;
|
||||
A9BB;JAVANESE VOWEL SIGN DIRGA MURE;Mc;0;L;;;;;N;;;;;
|
||||
A9BC;JAVANESE VOWEL SIGN PEPET;Mn;0;NSM;;;;;N;;;;;
|
||||
A9BD;JAVANESE CONSONANT SIGN KERET;Mc;0;L;;;;;N;;;;;
|
||||
A9BD;JAVANESE CONSONANT SIGN KERET;Mn;0;NSM;;;;;N;;;;;
|
||||
A9BE;JAVANESE CONSONANT SIGN PENGKAL;Mc;0;L;;;;;N;;;;;
|
||||
A9BF;JAVANESE CONSONANT SIGN CAKRA;Mc;0;L;;;;;N;;;;;
|
||||
A9C0;JAVANESE PANGKON;Mc;9;L;;;;;N;;;;;
|
||||
@ -14864,6 +14895,8 @@ AB62;LATIN SMALL LETTER OPEN OE;Ll;0;L;;;;;N;;;;;
|
||||
AB63;LATIN SMALL LETTER UO;Ll;0;L;;;;;N;;;;;
|
||||
AB64;LATIN SMALL LETTER INVERTED ALPHA;Ll;0;L;;;;;N;;;;;
|
||||
AB65;GREEK LETTER SMALL CAPITAL OMEGA;Ll;0;L;;;;;N;;;;;
|
||||
AB66;LATIN SMALL LETTER DZ DIGRAPH WITH RETROFLEX HOOK;Ll;0;L;;;;;N;;;;;
|
||||
AB67;LATIN SMALL LETTER TS DIGRAPH WITH RETROFLEX HOOK;Ll;0;L;;;;;N;;;;;
|
||||
AB70;CHEROKEE SMALL LETTER A;Ll;0;L;;;;;N;;;13A0;;13A0
|
||||
AB71;CHEROKEE SMALL LETTER E;Ll;0;L;;;;;N;;;13A1;;13A1
|
||||
AB72;CHEROKEE SMALL LETTER I;Ll;0;L;;;;;N;;;13A2;;13A2
|
||||
@ -19106,6 +19139,29 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
10F57;SOGDIAN PUNCTUATION CIRCLE WITH DOT;Po;0;AL;;;;;N;;;;;
|
||||
10F58;SOGDIAN PUNCTUATION TWO CIRCLES WITH DOTS;Po;0;AL;;;;;N;;;;;
|
||||
10F59;SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT;Po;0;AL;;;;;N;;;;;
|
||||
10FE0;ELYMAIC LETTER ALEPH;Lo;0;R;;;;;N;;;;;
|
||||
10FE1;ELYMAIC LETTER BETH;Lo;0;R;;;;;N;;;;;
|
||||
10FE2;ELYMAIC LETTER GIMEL;Lo;0;R;;;;;N;;;;;
|
||||
10FE3;ELYMAIC LETTER DALETH;Lo;0;R;;;;;N;;;;;
|
||||
10FE4;ELYMAIC LETTER HE;Lo;0;R;;;;;N;;;;;
|
||||
10FE5;ELYMAIC LETTER WAW;Lo;0;R;;;;;N;;;;;
|
||||
10FE6;ELYMAIC LETTER ZAYIN;Lo;0;R;;;;;N;;;;;
|
||||
10FE7;ELYMAIC LETTER HETH;Lo;0;R;;;;;N;;;;;
|
||||
10FE8;ELYMAIC LETTER TETH;Lo;0;R;;;;;N;;;;;
|
||||
10FE9;ELYMAIC LETTER YODH;Lo;0;R;;;;;N;;;;;
|
||||
10FEA;ELYMAIC LETTER KAPH;Lo;0;R;;;;;N;;;;;
|
||||
10FEB;ELYMAIC LETTER LAMEDH;Lo;0;R;;;;;N;;;;;
|
||||
10FEC;ELYMAIC LETTER MEM;Lo;0;R;;;;;N;;;;;
|
||||
10FED;ELYMAIC LETTER NUN;Lo;0;R;;;;;N;;;;;
|
||||
10FEE;ELYMAIC LETTER SAMEKH;Lo;0;R;;;;;N;;;;;
|
||||
10FEF;ELYMAIC LETTER AYIN;Lo;0;R;;;;;N;;;;;
|
||||
10FF0;ELYMAIC LETTER PE;Lo;0;R;;;;;N;;;;;
|
||||
10FF1;ELYMAIC LETTER SADHE;Lo;0;R;;;;;N;;;;;
|
||||
10FF2;ELYMAIC LETTER QOPH;Lo;0;R;;;;;N;;;;;
|
||||
10FF3;ELYMAIC LETTER RESH;Lo;0;R;;;;;N;;;;;
|
||||
10FF4;ELYMAIC LETTER SHIN;Lo;0;R;;;;;N;;;;;
|
||||
10FF5;ELYMAIC LETTER TAW;Lo;0;R;;;;;N;;;;;
|
||||
10FF6;ELYMAIC LIGATURE ZAYIN-YODH;Lo;0;R;;;;;N;;;;;
|
||||
11000;BRAHMI SIGN CANDRABINDU;Mc;0;L;;;;;N;;;;;
|
||||
11001;BRAHMI SIGN ANUSVARA;Mn;0;NSM;;;;;N;;;;;
|
||||
11002;BRAHMI SIGN VISARGA;Mc;0;L;;;;;N;;;;;
|
||||
@ -19888,6 +19944,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
1145B;NEWA PLACEHOLDER MARK;Po;0;L;;;;;N;;;;;
|
||||
1145D;NEWA INSERTION SIGN;Po;0;L;;;;;N;;;;;
|
||||
1145E;NEWA SANDHI MARK;Mn;230;NSM;;;;;N;;;;;
|
||||
1145F;NEWA LETTER VEDIC ANUSVARA;Lo;0;L;;;;;N;;;;;
|
||||
11480;TIRHUTA ANJI;Lo;0;L;;;;;N;;;;;
|
||||
11481;TIRHUTA LETTER A;Lo;0;L;;;;;N;;;;;
|
||||
11482;TIRHUTA LETTER AA;Lo;0;L;;;;;N;;;;;
|
||||
@ -20210,6 +20267,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
116B5;TAKRI VOWEL SIGN AU;Mn;0;NSM;;;;;N;;;;;
|
||||
116B6;TAKRI SIGN VIRAMA;Mc;9;L;;;;;N;;;;;
|
||||
116B7;TAKRI SIGN NUKTA;Mn;7;NSM;;;;;N;;;;;
|
||||
116B8;TAKRI LETTER ARCHAIC KHA;Lo;0;L;;;;;N;;;;;
|
||||
116C0;TAKRI DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;;
|
||||
116C1;TAKRI DIGIT ONE;Nd;0;L;;1;1;1;N;;;;;
|
||||
116C2;TAKRI DIGIT TWO;Nd;0;L;;2;2;2;N;;;;;
|
||||
@ -20422,6 +20480,71 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
118F1;WARANG CITI NUMBER EIGHTY;No;0;L;;;;80;N;;;;;
|
||||
118F2;WARANG CITI NUMBER NINETY;No;0;L;;;;90;N;;;;;
|
||||
118FF;WARANG CITI OM;Lo;0;L;;;;;N;;;;;
|
||||
119A0;NANDINAGARI LETTER A;Lo;0;L;;;;;N;;;;;
|
||||
119A1;NANDINAGARI LETTER AA;Lo;0;L;;;;;N;;;;;
|
||||
119A2;NANDINAGARI LETTER I;Lo;0;L;;;;;N;;;;;
|
||||
119A3;NANDINAGARI LETTER II;Lo;0;L;;;;;N;;;;;
|
||||
119A4;NANDINAGARI LETTER U;Lo;0;L;;;;;N;;;;;
|
||||
119A5;NANDINAGARI LETTER UU;Lo;0;L;;;;;N;;;;;
|
||||
119A6;NANDINAGARI LETTER VOCALIC R;Lo;0;L;;;;;N;;;;;
|
||||
119A7;NANDINAGARI LETTER VOCALIC RR;Lo;0;L;;;;;N;;;;;
|
||||
119AA;NANDINAGARI LETTER E;Lo;0;L;;;;;N;;;;;
|
||||
119AB;NANDINAGARI LETTER AI;Lo;0;L;;;;;N;;;;;
|
||||
119AC;NANDINAGARI LETTER O;Lo;0;L;;;;;N;;;;;
|
||||
119AD;NANDINAGARI LETTER AU;Lo;0;L;;;;;N;;;;;
|
||||
119AE;NANDINAGARI LETTER KA;Lo;0;L;;;;;N;;;;;
|
||||
119AF;NANDINAGARI LETTER KHA;Lo;0;L;;;;;N;;;;;
|
||||
119B0;NANDINAGARI LETTER GA;Lo;0;L;;;;;N;;;;;
|
||||
119B1;NANDINAGARI LETTER GHA;Lo;0;L;;;;;N;;;;;
|
||||
119B2;NANDINAGARI LETTER NGA;Lo;0;L;;;;;N;;;;;
|
||||
119B3;NANDINAGARI LETTER CA;Lo;0;L;;;;;N;;;;;
|
||||
119B4;NANDINAGARI LETTER CHA;Lo;0;L;;;;;N;;;;;
|
||||
119B5;NANDINAGARI LETTER JA;Lo;0;L;;;;;N;;;;;
|
||||
119B6;NANDINAGARI LETTER JHA;Lo;0;L;;;;;N;;;;;
|
||||
119B7;NANDINAGARI LETTER NYA;Lo;0;L;;;;;N;;;;;
|
||||
119B8;NANDINAGARI LETTER TTA;Lo;0;L;;;;;N;;;;;
|
||||
119B9;NANDINAGARI LETTER TTHA;Lo;0;L;;;;;N;;;;;
|
||||
119BA;NANDINAGARI LETTER DDA;Lo;0;L;;;;;N;;;;;
|
||||
119BB;NANDINAGARI LETTER DDHA;Lo;0;L;;;;;N;;;;;
|
||||
119BC;NANDINAGARI LETTER NNA;Lo;0;L;;;;;N;;;;;
|
||||
119BD;NANDINAGARI LETTER TA;Lo;0;L;;;;;N;;;;;
|
||||
119BE;NANDINAGARI LETTER THA;Lo;0;L;;;;;N;;;;;
|
||||
119BF;NANDINAGARI LETTER DA;Lo;0;L;;;;;N;;;;;
|
||||
119C0;NANDINAGARI LETTER DHA;Lo;0;L;;;;;N;;;;;
|
||||
119C1;NANDINAGARI LETTER NA;Lo;0;L;;;;;N;;;;;
|
||||
119C2;NANDINAGARI LETTER PA;Lo;0;L;;;;;N;;;;;
|
||||
119C3;NANDINAGARI LETTER PHA;Lo;0;L;;;;;N;;;;;
|
||||
119C4;NANDINAGARI LETTER BA;Lo;0;L;;;;;N;;;;;
|
||||
119C5;NANDINAGARI LETTER BHA;Lo;0;L;;;;;N;;;;;
|
||||
119C6;NANDINAGARI LETTER MA;Lo;0;L;;;;;N;;;;;
|
||||
119C7;NANDINAGARI LETTER YA;Lo;0;L;;;;;N;;;;;
|
||||
119C8;NANDINAGARI LETTER RA;Lo;0;L;;;;;N;;;;;
|
||||
119C9;NANDINAGARI LETTER LA;Lo;0;L;;;;;N;;;;;
|
||||
119CA;NANDINAGARI LETTER VA;Lo;0;L;;;;;N;;;;;
|
||||
119CB;NANDINAGARI LETTER SHA;Lo;0;L;;;;;N;;;;;
|
||||
119CC;NANDINAGARI LETTER SSA;Lo;0;L;;;;;N;;;;;
|
||||
119CD;NANDINAGARI LETTER SA;Lo;0;L;;;;;N;;;;;
|
||||
119CE;NANDINAGARI LETTER HA;Lo;0;L;;;;;N;;;;;
|
||||
119CF;NANDINAGARI LETTER LLA;Lo;0;L;;;;;N;;;;;
|
||||
119D0;NANDINAGARI LETTER RRA;Lo;0;L;;;;;N;;;;;
|
||||
119D1;NANDINAGARI VOWEL SIGN AA;Mc;0;L;;;;;N;;;;;
|
||||
119D2;NANDINAGARI VOWEL SIGN I;Mc;0;L;;;;;N;;;;;
|
||||
119D3;NANDINAGARI VOWEL SIGN II;Mc;0;L;;;;;N;;;;;
|
||||
119D4;NANDINAGARI VOWEL SIGN U;Mn;0;NSM;;;;;N;;;;;
|
||||
119D5;NANDINAGARI VOWEL SIGN UU;Mn;0;NSM;;;;;N;;;;;
|
||||
119D6;NANDINAGARI VOWEL SIGN VOCALIC R;Mn;0;NSM;;;;;N;;;;;
|
||||
119D7;NANDINAGARI VOWEL SIGN VOCALIC RR;Mn;0;NSM;;;;;N;;;;;
|
||||
119DA;NANDINAGARI VOWEL SIGN E;Mn;0;NSM;;;;;N;;;;;
|
||||
119DB;NANDINAGARI VOWEL SIGN AI;Mn;0;NSM;;;;;N;;;;;
|
||||
119DC;NANDINAGARI VOWEL SIGN O;Mc;0;L;;;;;N;;;;;
|
||||
119DD;NANDINAGARI VOWEL SIGN AU;Mc;0;L;;;;;N;;;;;
|
||||
119DE;NANDINAGARI SIGN ANUSVARA;Mc;0;L;;;;;N;;;;;
|
||||
119DF;NANDINAGARI SIGN VISARGA;Mc;0;L;;;;;N;;;;;
|
||||
119E0;NANDINAGARI SIGN VIRAMA;Mn;9;NSM;;;;;N;;;;;
|
||||
119E1;NANDINAGARI SIGN AVAGRAHA;Lo;0;L;;;;;N;;;;;
|
||||
119E2;NANDINAGARI SIGN SIDDHAM;Po;0;L;;;;;N;;;;;
|
||||
119E3;NANDINAGARI HEADSTROKE;Lo;0;L;;;;;N;;;;;
|
||||
119E4;NANDINAGARI VOWEL SIGN PRISHTHAMATRA E;Mc;0;L;;;;;N;;;;;
|
||||
11A00;ZANABAZAR SQUARE LETTER A;Lo;0;L;;;;;N;;;;;
|
||||
11A01;ZANABAZAR SQUARE VOWEL SIGN I;Mn;0;NSM;;;;;N;;;;;
|
||||
11A02;ZANABAZAR SQUARE VOWEL SIGN UE;Mn;0;NSM;;;;;N;;;;;
|
||||
@ -20546,6 +20669,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
11A81;SOYOMBO LETTER SA;Lo;0;L;;;;;N;;;;;
|
||||
11A82;SOYOMBO LETTER HA;Lo;0;L;;;;;N;;;;;
|
||||
11A83;SOYOMBO LETTER KSSA;Lo;0;L;;;;;N;;;;;
|
||||
11A84;SOYOMBO SIGN JIHVAMULIYA;Lo;0;L;;;;;N;;;;;
|
||||
11A85;SOYOMBO SIGN UPADHMANIYA;Lo;0;L;;;;;N;;;;;
|
||||
11A86;SOYOMBO CLUSTER-INITIAL LETTER RA;Lo;0;L;;;;;N;;;;;
|
||||
11A87;SOYOMBO CLUSTER-INITIAL LETTER LA;Lo;0;L;;;;;N;;;;;
|
||||
11A88;SOYOMBO CLUSTER-INITIAL LETTER SHA;Lo;0;L;;;;;N;;;;;
|
||||
@ -20960,6 +21085,57 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
11EF6;MAKASAR VOWEL SIGN O;Mc;0;L;;;;;N;;;;;
|
||||
11EF7;MAKASAR PASSIMBANG;Po;0;L;;;;;N;;;;;
|
||||
11EF8;MAKASAR END OF SECTION;Po;0;L;;;;;N;;;;;
|
||||
11FC0;TAMIL FRACTION ONE THREE-HUNDRED-AND-TWENTIETH;No;0;L;;;;1/320;N;;;;;
|
||||
11FC1;TAMIL FRACTION ONE ONE-HUNDRED-AND-SIXTIETH;No;0;L;;;;1/160;N;;;;;
|
||||
11FC2;TAMIL FRACTION ONE EIGHTIETH;No;0;L;;;;1/80;N;;;;;
|
||||
11FC3;TAMIL FRACTION ONE SIXTY-FOURTH;No;0;L;;;;1/64;N;;;;;
|
||||
11FC4;TAMIL FRACTION ONE FORTIETH;No;0;L;;;;1/40;N;;;;;
|
||||
11FC5;TAMIL FRACTION ONE THIRTY-SECOND;No;0;L;;;;1/32;N;;;;;
|
||||
11FC6;TAMIL FRACTION THREE EIGHTIETHS;No;0;L;;;;3/80;N;;;;;
|
||||
11FC7;TAMIL FRACTION THREE SIXTY-FOURTHS;No;0;L;;;;3/64;N;;;;;
|
||||
11FC8;TAMIL FRACTION ONE TWENTIETH;No;0;L;;;;1/20;N;;;;;
|
||||
11FC9;TAMIL FRACTION ONE SIXTEENTH-1;No;0;L;;;;1/16;N;;;;;
|
||||
11FCA;TAMIL FRACTION ONE SIXTEENTH-2;No;0;L;;;;1/16;N;;;;;
|
||||
11FCB;TAMIL FRACTION ONE TENTH;No;0;L;;;;1/10;N;;;;;
|
||||
11FCC;TAMIL FRACTION ONE EIGHTH;No;0;L;;;;1/8;N;;;;;
|
||||
11FCD;TAMIL FRACTION THREE TWENTIETHS;No;0;L;;;;3/20;N;;;;;
|
||||
11FCE;TAMIL FRACTION THREE SIXTEENTHS;No;0;L;;;;3/16;N;;;;;
|
||||
11FCF;TAMIL FRACTION ONE FIFTH;No;0;L;;;;1/5;N;;;;;
|
||||
11FD0;TAMIL FRACTION ONE QUARTER;No;0;L;;;;1/4;N;;;;;
|
||||
11FD1;TAMIL FRACTION ONE HALF-1;No;0;L;;;;1/2;N;;;;;
|
||||
11FD2;TAMIL FRACTION ONE HALF-2;No;0;L;;;;1/2;N;;;;;
|
||||
11FD3;TAMIL FRACTION THREE QUARTERS;No;0;L;;;;3/4;N;;;;;
|
||||
11FD4;TAMIL FRACTION DOWNSCALING FACTOR KIIZH;No;0;L;;;;1/320;N;;;;;
|
||||
11FD5;TAMIL SIGN NEL;So;0;ON;;;;;N;;;;;
|
||||
11FD6;TAMIL SIGN CEVITU;So;0;ON;;;;;N;;;;;
|
||||
11FD7;TAMIL SIGN AAZHAAKKU;So;0;ON;;;;;N;;;;;
|
||||
11FD8;TAMIL SIGN UZHAKKU;So;0;ON;;;;;N;;;;;
|
||||
11FD9;TAMIL SIGN MUUVUZHAKKU;So;0;ON;;;;;N;;;;;
|
||||
11FDA;TAMIL SIGN KURUNI;So;0;ON;;;;;N;;;;;
|
||||
11FDB;TAMIL SIGN PATHAKKU;So;0;ON;;;;;N;;;;;
|
||||
11FDC;TAMIL SIGN MUKKURUNI;So;0;ON;;;;;N;;;;;
|
||||
11FDD;TAMIL SIGN KAACU;Sc;0;ET;;;;;N;;;;;
|
||||
11FDE;TAMIL SIGN PANAM;Sc;0;ET;;;;;N;;;;;
|
||||
11FDF;TAMIL SIGN PON;Sc;0;ET;;;;;N;;;;;
|
||||
11FE0;TAMIL SIGN VARAAKAN;Sc;0;ET;;;;;N;;;;;
|
||||
11FE1;TAMIL SIGN PAARAM;So;0;ON;;;;;N;;;;;
|
||||
11FE2;TAMIL SIGN KUZHI;So;0;ON;;;;;N;;;;;
|
||||
11FE3;TAMIL SIGN VELI;So;0;ON;;;;;N;;;;;
|
||||
11FE4;TAMIL WET CULTIVATION SIGN;So;0;ON;;;;;N;;;;;
|
||||
11FE5;TAMIL DRY CULTIVATION SIGN;So;0;ON;;;;;N;;;;;
|
||||
11FE6;TAMIL LAND SIGN;So;0;ON;;;;;N;;;;;
|
||||
11FE7;TAMIL SALT PAN SIGN;So;0;ON;;;;;N;;;;;
|
||||
11FE8;TAMIL TRADITIONAL CREDIT SIGN;So;0;ON;;;;;N;;;;;
|
||||
11FE9;TAMIL TRADITIONAL NUMBER SIGN;So;0;ON;;;;;N;;;;;
|
||||
11FEA;TAMIL CURRENT SIGN;So;0;ON;;;;;N;;;;;
|
||||
11FEB;TAMIL AND ODD SIGN;So;0;ON;;;;;N;;;;;
|
||||
11FEC;TAMIL SPENT SIGN;So;0;ON;;;;;N;;;;;
|
||||
11FED;TAMIL TOTAL SIGN;So;0;ON;;;;;N;;;;;
|
||||
11FEE;TAMIL IN POSSESSION SIGN;So;0;ON;;;;;N;;;;;
|
||||
11FEF;TAMIL STARTING FROM SIGN;So;0;ON;;;;;N;;;;;
|
||||
11FF0;TAMIL SIGN MUTHALIYA;So;0;ON;;;;;N;;;;;
|
||||
11FF1;TAMIL SIGN VAKAIYARAA;So;0;ON;;;;;N;;;;;
|
||||
11FFF;TAMIL PUNCTUATION END OF TEXT;Po;0;L;;;;;N;;;;;
|
||||
12000;CUNEIFORM SIGN A;Lo;0;L;;;;;N;;;;;
|
||||
12001;CUNEIFORM SIGN A TIMES A;Lo;0;L;;;;;N;;;;;
|
||||
12002;CUNEIFORM SIGN A TIMES BAD;Lo;0;L;;;;;N;;;;;
|
||||
@ -23265,6 +23441,15 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
1342C;EGYPTIAN HIEROGLYPH AA030;Lo;0;L;;;;;N;;;;;
|
||||
1342D;EGYPTIAN HIEROGLYPH AA031;Lo;0;L;;;;;N;;;;;
|
||||
1342E;EGYPTIAN HIEROGLYPH AA032;Lo;0;L;;;;;N;;;;;
|
||||
13430;EGYPTIAN HIEROGLYPH VERTICAL JOINER;Cf;0;L;;;;;N;;;;;
|
||||
13431;EGYPTIAN HIEROGLYPH HORIZONTAL JOINER;Cf;0;L;;;;;N;;;;;
|
||||
13432;EGYPTIAN HIEROGLYPH INSERT AT TOP START;Cf;0;L;;;;;N;;;;;
|
||||
13433;EGYPTIAN HIEROGLYPH INSERT AT BOTTOM START;Cf;0;L;;;;;N;;;;;
|
||||
13434;EGYPTIAN HIEROGLYPH INSERT AT TOP END;Cf;0;L;;;;;N;;;;;
|
||||
13435;EGYPTIAN HIEROGLYPH INSERT AT BOTTOM END;Cf;0;L;;;;;N;;;;;
|
||||
13436;EGYPTIAN HIEROGLYPH OVERLAY MIDDLE;Cf;0;L;;;;;N;;;;;
|
||||
13437;EGYPTIAN HIEROGLYPH BEGIN SEGMENT;Cf;0;L;;;;;N;;;;;
|
||||
13438;EGYPTIAN HIEROGLYPH END SEGMENT;Cf;0;L;;;;;N;;;;;
|
||||
14400;ANATOLIAN HIEROGLYPH A001;Lo;0;L;;;;;N;;;;;
|
||||
14401;ANATOLIAN HIEROGLYPH A002;Lo;0;L;;;;;N;;;;;
|
||||
14402;ANATOLIAN HIEROGLYPH A003;Lo;0;L;;;;;N;;;;;
|
||||
@ -24783,6 +24968,13 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
16F42;MIAO LETTER WA;Lo;0;L;;;;;N;;;;;
|
||||
16F43;MIAO LETTER AH;Lo;0;L;;;;;N;;;;;
|
||||
16F44;MIAO LETTER HHA;Lo;0;L;;;;;N;;;;;
|
||||
16F45;MIAO LETTER BRI;Lo;0;L;;;;;N;;;;;
|
||||
16F46;MIAO LETTER SYI;Lo;0;L;;;;;N;;;;;
|
||||
16F47;MIAO LETTER DZYI;Lo;0;L;;;;;N;;;;;
|
||||
16F48;MIAO LETTER TE;Lo;0;L;;;;;N;;;;;
|
||||
16F49;MIAO LETTER TSE;Lo;0;L;;;;;N;;;;;
|
||||
16F4A;MIAO LETTER RTE;Lo;0;L;;;;;N;;;;;
|
||||
16F4F;MIAO SIGN CONSONANT MODIFIER BAR;Mn;0;NSM;;;;;N;;;;;
|
||||
16F50;MIAO LETTER NASALIZATION;Lo;0;L;;;;;N;;;;;
|
||||
16F51;MIAO SIGN ASPIRATION;Mc;0;L;;;;;N;;;;;
|
||||
16F52;MIAO SIGN REFORMED VOICING;Mc;0;L;;;;;N;;;;;
|
||||
@ -24830,6 +25022,15 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
16F7C;MIAO VOWEL SIGN OU;Mc;0;L;;;;;N;;;;;
|
||||
16F7D;MIAO VOWEL SIGN N;Mc;0;L;;;;;N;;;;;
|
||||
16F7E;MIAO VOWEL SIGN NG;Mc;0;L;;;;;N;;;;;
|
||||
16F7F;MIAO VOWEL SIGN UOG;Mc;0;L;;;;;N;;;;;
|
||||
16F80;MIAO VOWEL SIGN YUI;Mc;0;L;;;;;N;;;;;
|
||||
16F81;MIAO VOWEL SIGN OG;Mc;0;L;;;;;N;;;;;
|
||||
16F82;MIAO VOWEL SIGN OER;Mc;0;L;;;;;N;;;;;
|
||||
16F83;MIAO VOWEL SIGN VW;Mc;0;L;;;;;N;;;;;
|
||||
16F84;MIAO VOWEL SIGN IG;Mc;0;L;;;;;N;;;;;
|
||||
16F85;MIAO VOWEL SIGN EA;Mc;0;L;;;;;N;;;;;
|
||||
16F86;MIAO VOWEL SIGN IONG;Mc;0;L;;;;;N;;;;;
|
||||
16F87;MIAO VOWEL SIGN UI;Mc;0;L;;;;;N;;;;;
|
||||
16F8F;MIAO TONE RIGHT;Mn;0;NSM;;;;;N;;;;;
|
||||
16F90;MIAO TONE TOP RIGHT;Mn;0;NSM;;;;;N;;;;;
|
||||
16F91;MIAO TONE ABOVE;Mn;0;NSM;;;;;N;;;;;
|
||||
@ -24849,8 +25050,10 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
16F9F;MIAO LETTER REFORMED TONE-8;Lm;0;L;;;;;N;;;;;
|
||||
16FE0;TANGUT ITERATION MARK;Lm;0;L;;;;;N;;;;;
|
||||
16FE1;NUSHU ITERATION MARK;Lm;0;L;;;;;N;;;;;
|
||||
16FE2;OLD CHINESE HOOK MARK;Po;0;ON;;;;;N;;;;;
|
||||
16FE3;OLD CHINESE ITERATION MARK;Lm;0;L;;;;;N;;;;;
|
||||
17000;<Tangut Ideograph, First>;Lo;0;L;;;;;N;;;;;
|
||||
187F1;<Tangut Ideograph, Last>;Lo;0;L;;;;;N;;;;;
|
||||
187F7;<Tangut Ideograph, Last>;Lo;0;L;;;;;N;;;;;
|
||||
18800;TANGUT COMPONENT-001;Lo;0;L;;;;;N;;;;;
|
||||
18801;TANGUT COMPONENT-002;Lo;0;L;;;;;N;;;;;
|
||||
18802;TANGUT COMPONENT-003;Lo;0;L;;;;;N;;;;;
|
||||
@ -25893,6 +26096,13 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
1B11C;HENTAIGANA LETTER WO-7;Lo;0;L;;;;;N;;;;;
|
||||
1B11D;HENTAIGANA LETTER N-MU-MO-1;Lo;0;L;;;;;N;;;;;
|
||||
1B11E;HENTAIGANA LETTER N-MU-MO-2;Lo;0;L;;;;;N;;;;;
|
||||
1B150;HIRAGANA LETTER SMALL WI;Lo;0;L;;;;;N;;;;;
|
||||
1B151;HIRAGANA LETTER SMALL WE;Lo;0;L;;;;;N;;;;;
|
||||
1B152;HIRAGANA LETTER SMALL WO;Lo;0;L;;;;;N;;;;;
|
||||
1B164;KATAKANA LETTER SMALL WI;Lo;0;L;;;;;N;;;;;
|
||||
1B165;KATAKANA LETTER SMALL WE;Lo;0;L;;;;;N;;;;;
|
||||
1B166;KATAKANA LETTER SMALL WO;Lo;0;L;;;;;N;;;;;
|
||||
1B167;KATAKANA LETTER SMALL N;Lo;0;L;;;;;N;;;;;
|
||||
1B170;NUSHU CHARACTER-1B170;Lo;0;L;;;;;N;;;;;
|
||||
1B171;NUSHU CHARACTER-1B171;Lo;0;L;;;;;N;;;;;
|
||||
1B172;NUSHU CHARACTER-1B172;Lo;0;L;;;;;N;;;;;
|
||||
@ -28821,6 +29031,136 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
1E028;COMBINING GLAGOLITIC LETTER BIG YUS;Mn;230;NSM;;;;;N;;;;;
|
||||
1E029;COMBINING GLAGOLITIC LETTER IOTATED BIG YUS;Mn;230;NSM;;;;;N;;;;;
|
||||
1E02A;COMBINING GLAGOLITIC LETTER FITA;Mn;230;NSM;;;;;N;;;;;
|
||||
1E100;NYIAKENG PUACHUE HMONG LETTER MA;Lo;0;L;;;;;N;;;;;
|
||||
1E101;NYIAKENG PUACHUE HMONG LETTER TSA;Lo;0;L;;;;;N;;;;;
|
||||
1E102;NYIAKENG PUACHUE HMONG LETTER NTA;Lo;0;L;;;;;N;;;;;
|
||||
1E103;NYIAKENG PUACHUE HMONG LETTER TA;Lo;0;L;;;;;N;;;;;
|
||||
1E104;NYIAKENG PUACHUE HMONG LETTER HA;Lo;0;L;;;;;N;;;;;
|
||||
1E105;NYIAKENG PUACHUE HMONG LETTER NA;Lo;0;L;;;;;N;;;;;
|
||||
1E106;NYIAKENG PUACHUE HMONG LETTER XA;Lo;0;L;;;;;N;;;;;
|
||||
1E107;NYIAKENG PUACHUE HMONG LETTER NKA;Lo;0;L;;;;;N;;;;;
|
||||
1E108;NYIAKENG PUACHUE HMONG LETTER CA;Lo;0;L;;;;;N;;;;;
|
||||
1E109;NYIAKENG PUACHUE HMONG LETTER LA;Lo;0;L;;;;;N;;;;;
|
||||
1E10A;NYIAKENG PUACHUE HMONG LETTER SA;Lo;0;L;;;;;N;;;;;
|
||||
1E10B;NYIAKENG PUACHUE HMONG LETTER ZA;Lo;0;L;;;;;N;;;;;
|
||||
1E10C;NYIAKENG PUACHUE HMONG LETTER NCA;Lo;0;L;;;;;N;;;;;
|
||||
1E10D;NYIAKENG PUACHUE HMONG LETTER NTSA;Lo;0;L;;;;;N;;;;;
|
||||
1E10E;NYIAKENG PUACHUE HMONG LETTER KA;Lo;0;L;;;;;N;;;;;
|
||||
1E10F;NYIAKENG PUACHUE HMONG LETTER DA;Lo;0;L;;;;;N;;;;;
|
||||
1E110;NYIAKENG PUACHUE HMONG LETTER NYA;Lo;0;L;;;;;N;;;;;
|
||||
1E111;NYIAKENG PUACHUE HMONG LETTER NRA;Lo;0;L;;;;;N;;;;;
|
||||
1E112;NYIAKENG PUACHUE HMONG LETTER VA;Lo;0;L;;;;;N;;;;;
|
||||
1E113;NYIAKENG PUACHUE HMONG LETTER NTXA;Lo;0;L;;;;;N;;;;;
|
||||
1E114;NYIAKENG PUACHUE HMONG LETTER TXA;Lo;0;L;;;;;N;;;;;
|
||||
1E115;NYIAKENG PUACHUE HMONG LETTER FA;Lo;0;L;;;;;N;;;;;
|
||||
1E116;NYIAKENG PUACHUE HMONG LETTER RA;Lo;0;L;;;;;N;;;;;
|
||||
1E117;NYIAKENG PUACHUE HMONG LETTER QA;Lo;0;L;;;;;N;;;;;
|
||||
1E118;NYIAKENG PUACHUE HMONG LETTER YA;Lo;0;L;;;;;N;;;;;
|
||||
1E119;NYIAKENG PUACHUE HMONG LETTER NQA;Lo;0;L;;;;;N;;;;;
|
||||
1E11A;NYIAKENG PUACHUE HMONG LETTER PA;Lo;0;L;;;;;N;;;;;
|
||||
1E11B;NYIAKENG PUACHUE HMONG LETTER XYA;Lo;0;L;;;;;N;;;;;
|
||||
1E11C;NYIAKENG PUACHUE HMONG LETTER NPA;Lo;0;L;;;;;N;;;;;
|
||||
1E11D;NYIAKENG PUACHUE HMONG LETTER DLA;Lo;0;L;;;;;N;;;;;
|
||||
1E11E;NYIAKENG PUACHUE HMONG LETTER NPLA;Lo;0;L;;;;;N;;;;;
|
||||
1E11F;NYIAKENG PUACHUE HMONG LETTER HAH;Lo;0;L;;;;;N;;;;;
|
||||
1E120;NYIAKENG PUACHUE HMONG LETTER MLA;Lo;0;L;;;;;N;;;;;
|
||||
1E121;NYIAKENG PUACHUE HMONG LETTER PLA;Lo;0;L;;;;;N;;;;;
|
||||
1E122;NYIAKENG PUACHUE HMONG LETTER GA;Lo;0;L;;;;;N;;;;;
|
||||
1E123;NYIAKENG PUACHUE HMONG LETTER RRA;Lo;0;L;;;;;N;;;;;
|
||||
1E124;NYIAKENG PUACHUE HMONG LETTER A;Lo;0;L;;;;;N;;;;;
|
||||
1E125;NYIAKENG PUACHUE HMONG LETTER AA;Lo;0;L;;;;;N;;;;;
|
||||
1E126;NYIAKENG PUACHUE HMONG LETTER I;Lo;0;L;;;;;N;;;;;
|
||||
1E127;NYIAKENG PUACHUE HMONG LETTER U;Lo;0;L;;;;;N;;;;;
|
||||
1E128;NYIAKENG PUACHUE HMONG LETTER O;Lo;0;L;;;;;N;;;;;
|
||||
1E129;NYIAKENG PUACHUE HMONG LETTER OO;Lo;0;L;;;;;N;;;;;
|
||||
1E12A;NYIAKENG PUACHUE HMONG LETTER E;Lo;0;L;;;;;N;;;;;
|
||||
1E12B;NYIAKENG PUACHUE HMONG LETTER EE;Lo;0;L;;;;;N;;;;;
|
||||
1E12C;NYIAKENG PUACHUE HMONG LETTER W;Lo;0;L;;;;;N;;;;;
|
||||
1E130;NYIAKENG PUACHUE HMONG TONE-B;Mn;230;NSM;;;;;N;;;;;
|
||||
1E131;NYIAKENG PUACHUE HMONG TONE-M;Mn;230;NSM;;;;;N;;;;;
|
||||
1E132;NYIAKENG PUACHUE HMONG TONE-J;Mn;230;NSM;;;;;N;;;;;
|
||||
1E133;NYIAKENG PUACHUE HMONG TONE-V;Mn;230;NSM;;;;;N;;;;;
|
||||
1E134;NYIAKENG PUACHUE HMONG TONE-S;Mn;230;NSM;;;;;N;;;;;
|
||||
1E135;NYIAKENG PUACHUE HMONG TONE-G;Mn;230;NSM;;;;;N;;;;;
|
||||
1E136;NYIAKENG PUACHUE HMONG TONE-D;Mn;230;NSM;;;;;N;;;;;
|
||||
1E137;NYIAKENG PUACHUE HMONG SIGN FOR PERSON;Lm;0;L;;;;;N;;;;;
|
||||
1E138;NYIAKENG PUACHUE HMONG SIGN FOR THING;Lm;0;L;;;;;N;;;;;
|
||||
1E139;NYIAKENG PUACHUE HMONG SIGN FOR LOCATION;Lm;0;L;;;;;N;;;;;
|
||||
1E13A;NYIAKENG PUACHUE HMONG SIGN FOR ANIMAL;Lm;0;L;;;;;N;;;;;
|
||||
1E13B;NYIAKENG PUACHUE HMONG SIGN FOR INVERTEBRATE;Lm;0;L;;;;;N;;;;;
|
||||
1E13C;NYIAKENG PUACHUE HMONG SIGN XW XW;Lm;0;L;;;;;N;;;;;
|
||||
1E13D;NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER;Lm;0;L;;;;;N;;;;;
|
||||
1E140;NYIAKENG PUACHUE HMONG DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;;
|
||||
1E141;NYIAKENG PUACHUE HMONG DIGIT ONE;Nd;0;L;;1;1;1;N;;;;;
|
||||
1E142;NYIAKENG PUACHUE HMONG DIGIT TWO;Nd;0;L;;2;2;2;N;;;;;
|
||||
1E143;NYIAKENG PUACHUE HMONG DIGIT THREE;Nd;0;L;;3;3;3;N;;;;;
|
||||
1E144;NYIAKENG PUACHUE HMONG DIGIT FOUR;Nd;0;L;;4;4;4;N;;;;;
|
||||
1E145;NYIAKENG PUACHUE HMONG DIGIT FIVE;Nd;0;L;;5;5;5;N;;;;;
|
||||
1E146;NYIAKENG PUACHUE HMONG DIGIT SIX;Nd;0;L;;6;6;6;N;;;;;
|
||||
1E147;NYIAKENG PUACHUE HMONG DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;;
|
||||
1E148;NYIAKENG PUACHUE HMONG DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;;
|
||||
1E149;NYIAKENG PUACHUE HMONG DIGIT NINE;Nd;0;L;;9;9;9;N;;;;;
|
||||
1E14E;NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ;Lo;0;L;;;;;N;;;;;
|
||||
1E14F;NYIAKENG PUACHUE HMONG CIRCLED CA;So;0;L;;;;;N;;;;;
|
||||
1E2C0;WANCHO LETTER AA;Lo;0;L;;;;;N;;;;;
|
||||
1E2C1;WANCHO LETTER A;Lo;0;L;;;;;N;;;;;
|
||||
1E2C2;WANCHO LETTER BA;Lo;0;L;;;;;N;;;;;
|
||||
1E2C3;WANCHO LETTER CA;Lo;0;L;;;;;N;;;;;
|
||||
1E2C4;WANCHO LETTER DA;Lo;0;L;;;;;N;;;;;
|
||||
1E2C5;WANCHO LETTER GA;Lo;0;L;;;;;N;;;;;
|
||||
1E2C6;WANCHO LETTER YA;Lo;0;L;;;;;N;;;;;
|
||||
1E2C7;WANCHO LETTER PHA;Lo;0;L;;;;;N;;;;;
|
||||
1E2C8;WANCHO LETTER LA;Lo;0;L;;;;;N;;;;;
|
||||
1E2C9;WANCHO LETTER NA;Lo;0;L;;;;;N;;;;;
|
||||
1E2CA;WANCHO LETTER PA;Lo;0;L;;;;;N;;;;;
|
||||
1E2CB;WANCHO LETTER TA;Lo;0;L;;;;;N;;;;;
|
||||
1E2CC;WANCHO LETTER THA;Lo;0;L;;;;;N;;;;;
|
||||
1E2CD;WANCHO LETTER FA;Lo;0;L;;;;;N;;;;;
|
||||
1E2CE;WANCHO LETTER SA;Lo;0;L;;;;;N;;;;;
|
||||
1E2CF;WANCHO LETTER SHA;Lo;0;L;;;;;N;;;;;
|
||||
1E2D0;WANCHO LETTER JA;Lo;0;L;;;;;N;;;;;
|
||||
1E2D1;WANCHO LETTER ZA;Lo;0;L;;;;;N;;;;;
|
||||
1E2D2;WANCHO LETTER WA;Lo;0;L;;;;;N;;;;;
|
||||
1E2D3;WANCHO LETTER VA;Lo;0;L;;;;;N;;;;;
|
||||
1E2D4;WANCHO LETTER KA;Lo;0;L;;;;;N;;;;;
|
||||
1E2D5;WANCHO LETTER O;Lo;0;L;;;;;N;;;;;
|
||||
1E2D6;WANCHO LETTER AU;Lo;0;L;;;;;N;;;;;
|
||||
1E2D7;WANCHO LETTER RA;Lo;0;L;;;;;N;;;;;
|
||||
1E2D8;WANCHO LETTER MA;Lo;0;L;;;;;N;;;;;
|
||||
1E2D9;WANCHO LETTER KHA;Lo;0;L;;;;;N;;;;;
|
||||
1E2DA;WANCHO LETTER HA;Lo;0;L;;;;;N;;;;;
|
||||
1E2DB;WANCHO LETTER E;Lo;0;L;;;;;N;;;;;
|
||||
1E2DC;WANCHO LETTER I;Lo;0;L;;;;;N;;;;;
|
||||
1E2DD;WANCHO LETTER NGA;Lo;0;L;;;;;N;;;;;
|
||||
1E2DE;WANCHO LETTER U;Lo;0;L;;;;;N;;;;;
|
||||
1E2DF;WANCHO LETTER LLHA;Lo;0;L;;;;;N;;;;;
|
||||
1E2E0;WANCHO LETTER TSA;Lo;0;L;;;;;N;;;;;
|
||||
1E2E1;WANCHO LETTER TRA;Lo;0;L;;;;;N;;;;;
|
||||
1E2E2;WANCHO LETTER ONG;Lo;0;L;;;;;N;;;;;
|
||||
1E2E3;WANCHO LETTER AANG;Lo;0;L;;;;;N;;;;;
|
||||
1E2E4;WANCHO LETTER ANG;Lo;0;L;;;;;N;;;;;
|
||||
1E2E5;WANCHO LETTER ING;Lo;0;L;;;;;N;;;;;
|
||||
1E2E6;WANCHO LETTER ON;Lo;0;L;;;;;N;;;;;
|
||||
1E2E7;WANCHO LETTER EN;Lo;0;L;;;;;N;;;;;
|
||||
1E2E8;WANCHO LETTER AAN;Lo;0;L;;;;;N;;;;;
|
||||
1E2E9;WANCHO LETTER NYA;Lo;0;L;;;;;N;;;;;
|
||||
1E2EA;WANCHO LETTER UEN;Lo;0;L;;;;;N;;;;;
|
||||
1E2EB;WANCHO LETTER YIH;Lo;0;L;;;;;N;;;;;
|
||||
1E2EC;WANCHO TONE TUP;Mn;230;NSM;;;;;N;;;;;
|
||||
1E2ED;WANCHO TONE TUPNI;Mn;230;NSM;;;;;N;;;;;
|
||||
1E2EE;WANCHO TONE KOI;Mn;230;NSM;;;;;N;;;;;
|
||||
1E2EF;WANCHO TONE KOINI;Mn;230;NSM;;;;;N;;;;;
|
||||
1E2F0;WANCHO DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;;
|
||||
1E2F1;WANCHO DIGIT ONE;Nd;0;L;;1;1;1;N;;;;;
|
||||
1E2F2;WANCHO DIGIT TWO;Nd;0;L;;2;2;2;N;;;;;
|
||||
1E2F3;WANCHO DIGIT THREE;Nd;0;L;;3;3;3;N;;;;;
|
||||
1E2F4;WANCHO DIGIT FOUR;Nd;0;L;;4;4;4;N;;;;;
|
||||
1E2F5;WANCHO DIGIT FIVE;Nd;0;L;;5;5;5;N;;;;;
|
||||
1E2F6;WANCHO DIGIT SIX;Nd;0;L;;6;6;6;N;;;;;
|
||||
1E2F7;WANCHO DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;;
|
||||
1E2F8;WANCHO DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;;
|
||||
1E2F9;WANCHO DIGIT NINE;Nd;0;L;;9;9;9;N;;;;;
|
||||
1E2FF;WANCHO NGUN SIGN;Sc;0;ET;;;;;N;;;;;
|
||||
1E800;MENDE KIKAKUI SYLLABLE M001 KI;Lo;0;R;;;;;N;;;;;
|
||||
1E801;MENDE KIKAKUI SYLLABLE M002 KA;Lo;0;R;;;;;N;;;;;
|
||||
1E802;MENDE KIKAKUI SYLLABLE M003 KU;Lo;0;R;;;;;N;;;;;
|
||||
@ -29109,6 +29449,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
1E948;ADLAM CONSONANT MODIFIER;Mn;230;NSM;;;;;N;;;;;
|
||||
1E949;ADLAM GEMINATE CONSONANT MODIFIER;Mn;230;NSM;;;;;N;;;;;
|
||||
1E94A;ADLAM NUKTA;Mn;7;NSM;;;;;N;;;;;
|
||||
1E94B;ADLAM NASALIZATION MARK;Lm;0;R;;;;;N;;;;;
|
||||
1E950;ADLAM DIGIT ZERO;Nd;0;R;;0;0;0;N;;;;;
|
||||
1E951;ADLAM DIGIT ONE;Nd;0;R;;1;1;1;N;;;;;
|
||||
1E952;ADLAM DIGIT TWO;Nd;0;R;;2;2;2;N;;;;;
|
||||
@ -29189,6 +29530,67 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
1ECB2;INDIC SIYAQ NUMBER ALTERNATE TWO;No;0;AL;;;;2;N;;;;;
|
||||
1ECB3;INDIC SIYAQ NUMBER ALTERNATE TEN THOUSAND;No;0;AL;;;;10000;N;;;;;
|
||||
1ECB4;INDIC SIYAQ ALTERNATE LAKH MARK;No;0;AL;;;;100000;N;;;;;
|
||||
1ED01;OTTOMAN SIYAQ NUMBER ONE;No;0;AL;;;;1;N;;;;;
|
||||
1ED02;OTTOMAN SIYAQ NUMBER TWO;No;0;AL;;;;2;N;;;;;
|
||||
1ED03;OTTOMAN SIYAQ NUMBER THREE;No;0;AL;;;;3;N;;;;;
|
||||
1ED04;OTTOMAN SIYAQ NUMBER FOUR;No;0;AL;;;;4;N;;;;;
|
||||
1ED05;OTTOMAN SIYAQ NUMBER FIVE;No;0;AL;;;;5;N;;;;;
|
||||
1ED06;OTTOMAN SIYAQ NUMBER SIX;No;0;AL;;;;6;N;;;;;
|
||||
1ED07;OTTOMAN SIYAQ NUMBER SEVEN;No;0;AL;;;;7;N;;;;;
|
||||
1ED08;OTTOMAN SIYAQ NUMBER EIGHT;No;0;AL;;;;8;N;;;;;
|
||||
1ED09;OTTOMAN SIYAQ NUMBER NINE;No;0;AL;;;;9;N;;;;;
|
||||
1ED0A;OTTOMAN SIYAQ NUMBER TEN;No;0;AL;;;;10;N;;;;;
|
||||
1ED0B;OTTOMAN SIYAQ NUMBER TWENTY;No;0;AL;;;;20;N;;;;;
|
||||
1ED0C;OTTOMAN SIYAQ NUMBER THIRTY;No;0;AL;;;;30;N;;;;;
|
||||
1ED0D;OTTOMAN SIYAQ NUMBER FORTY;No;0;AL;;;;40;N;;;;;
|
||||
1ED0E;OTTOMAN SIYAQ NUMBER FIFTY;No;0;AL;;;;50;N;;;;;
|
||||
1ED0F;OTTOMAN SIYAQ NUMBER SIXTY;No;0;AL;;;;60;N;;;;;
|
||||
1ED10;OTTOMAN SIYAQ NUMBER SEVENTY;No;0;AL;;;;70;N;;;;;
|
||||
1ED11;OTTOMAN SIYAQ NUMBER EIGHTY;No;0;AL;;;;80;N;;;;;
|
||||
1ED12;OTTOMAN SIYAQ NUMBER NINETY;No;0;AL;;;;90;N;;;;;
|
||||
1ED13;OTTOMAN SIYAQ NUMBER ONE HUNDRED;No;0;AL;;;;100;N;;;;;
|
||||
1ED14;OTTOMAN SIYAQ NUMBER TWO HUNDRED;No;0;AL;;;;200;N;;;;;
|
||||
1ED15;OTTOMAN SIYAQ NUMBER THREE HUNDRED;No;0;AL;;;;300;N;;;;;
|
||||
1ED16;OTTOMAN SIYAQ NUMBER FOUR HUNDRED;No;0;AL;;;;400;N;;;;;
|
||||
1ED17;OTTOMAN SIYAQ NUMBER FIVE HUNDRED;No;0;AL;;;;500;N;;;;;
|
||||
1ED18;OTTOMAN SIYAQ NUMBER SIX HUNDRED;No;0;AL;;;;600;N;;;;;
|
||||
1ED19;OTTOMAN SIYAQ NUMBER SEVEN HUNDRED;No;0;AL;;;;700;N;;;;;
|
||||
1ED1A;OTTOMAN SIYAQ NUMBER EIGHT HUNDRED;No;0;AL;;;;800;N;;;;;
|
||||
1ED1B;OTTOMAN SIYAQ NUMBER NINE HUNDRED;No;0;AL;;;;900;N;;;;;
|
||||
1ED1C;OTTOMAN SIYAQ NUMBER ONE THOUSAND;No;0;AL;;;;1000;N;;;;;
|
||||
1ED1D;OTTOMAN SIYAQ NUMBER TWO THOUSAND;No;0;AL;;;;2000;N;;;;;
|
||||
1ED1E;OTTOMAN SIYAQ NUMBER THREE THOUSAND;No;0;AL;;;;3000;N;;;;;
|
||||
1ED1F;OTTOMAN SIYAQ NUMBER FOUR THOUSAND;No;0;AL;;;;4000;N;;;;;
|
||||
1ED20;OTTOMAN SIYAQ NUMBER FIVE THOUSAND;No;0;AL;;;;5000;N;;;;;
|
||||
1ED21;OTTOMAN SIYAQ NUMBER SIX THOUSAND;No;0;AL;;;;6000;N;;;;;
|
||||
1ED22;OTTOMAN SIYAQ NUMBER SEVEN THOUSAND;No;0;AL;;;;7000;N;;;;;
|
||||
1ED23;OTTOMAN SIYAQ NUMBER EIGHT THOUSAND;No;0;AL;;;;8000;N;;;;;
|
||||
1ED24;OTTOMAN SIYAQ NUMBER NINE THOUSAND;No;0;AL;;;;9000;N;;;;;
|
||||
1ED25;OTTOMAN SIYAQ NUMBER TEN THOUSAND;No;0;AL;;;;10000;N;;;;;
|
||||
1ED26;OTTOMAN SIYAQ NUMBER TWENTY THOUSAND;No;0;AL;;;;20000;N;;;;;
|
||||
1ED27;OTTOMAN SIYAQ NUMBER THIRTY THOUSAND;No;0;AL;;;;30000;N;;;;;
|
||||
1ED28;OTTOMAN SIYAQ NUMBER FORTY THOUSAND;No;0;AL;;;;40000;N;;;;;
|
||||
1ED29;OTTOMAN SIYAQ NUMBER FIFTY THOUSAND;No;0;AL;;;;50000;N;;;;;
|
||||
1ED2A;OTTOMAN SIYAQ NUMBER SIXTY THOUSAND;No;0;AL;;;;60000;N;;;;;
|
||||
1ED2B;OTTOMAN SIYAQ NUMBER SEVENTY THOUSAND;No;0;AL;;;;70000;N;;;;;
|
||||
1ED2C;OTTOMAN SIYAQ NUMBER EIGHTY THOUSAND;No;0;AL;;;;80000;N;;;;;
|
||||
1ED2D;OTTOMAN SIYAQ NUMBER NINETY THOUSAND;No;0;AL;;;;90000;N;;;;;
|
||||
1ED2E;OTTOMAN SIYAQ MARRATAN;So;0;AL;;;;;N;;;;;
|
||||
1ED2F;OTTOMAN SIYAQ ALTERNATE NUMBER TWO;No;0;AL;;;;2;N;;;;;
|
||||
1ED30;OTTOMAN SIYAQ ALTERNATE NUMBER THREE;No;0;AL;;;;3;N;;;;;
|
||||
1ED31;OTTOMAN SIYAQ ALTERNATE NUMBER FOUR;No;0;AL;;;;4;N;;;;;
|
||||
1ED32;OTTOMAN SIYAQ ALTERNATE NUMBER FIVE;No;0;AL;;;;5;N;;;;;
|
||||
1ED33;OTTOMAN SIYAQ ALTERNATE NUMBER SIX;No;0;AL;;;;6;N;;;;;
|
||||
1ED34;OTTOMAN SIYAQ ALTERNATE NUMBER SEVEN;No;0;AL;;;;7;N;;;;;
|
||||
1ED35;OTTOMAN SIYAQ ALTERNATE NUMBER EIGHT;No;0;AL;;;;8;N;;;;;
|
||||
1ED36;OTTOMAN SIYAQ ALTERNATE NUMBER NINE;No;0;AL;;;;9;N;;;;;
|
||||
1ED37;OTTOMAN SIYAQ ALTERNATE NUMBER TEN;No;0;AL;;;;10;N;;;;;
|
||||
1ED38;OTTOMAN SIYAQ ALTERNATE NUMBER FOUR HUNDRED;No;0;AL;;;;400;N;;;;;
|
||||
1ED39;OTTOMAN SIYAQ ALTERNATE NUMBER SIX HUNDRED;No;0;AL;;;;600;N;;;;;
|
||||
1ED3A;OTTOMAN SIYAQ ALTERNATE NUMBER TWO THOUSAND;No;0;AL;;;;2000;N;;;;;
|
||||
1ED3B;OTTOMAN SIYAQ ALTERNATE NUMBER TEN THOUSAND;No;0;AL;;;;10000;N;;;;;
|
||||
1ED3C;OTTOMAN SIYAQ FRACTION ONE HALF;No;0;AL;;;;1/2;N;;;;;
|
||||
1ED3D;OTTOMAN SIYAQ FRACTION ONE SIXTH;No;0;AL;;;;1/6;N;;;;;
|
||||
1EE00;ARABIC MATHEMATICAL ALEF;Lo;0;AL;<font> 0627;;;;N;;;;;
|
||||
1EE01;ARABIC MATHEMATICAL BEH;Lo;0;AL;<font> 0628;;;;N;;;;;
|
||||
1EE02;ARABIC MATHEMATICAL JEEM;Lo;0;AL;<font> 062C;;;;N;;;;;
|
||||
@ -29663,6 +30065,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
1F169;NEGATIVE CIRCLED LATIN CAPITAL LETTER Z;So;0;L;;;;;N;;;;;
|
||||
1F16A;RAISED MC SIGN;So;0;ON;<super> 004D 0043;;;;N;;;;;
|
||||
1F16B;RAISED MD SIGN;So;0;ON;<super> 004D 0044;;;;N;;;;;
|
||||
1F16C;RAISED MR SIGN;So;0;ON;<super> 004D 0052;;;;N;;;;;
|
||||
1F170;NEGATIVE SQUARED LATIN CAPITAL LETTER A;So;0;L;;;;;N;;;;;
|
||||
1F171;NEGATIVE SQUARED LATIN CAPITAL LETTER B;So;0;L;;;;;N;;;;;
|
||||
1F172;NEGATIVE SQUARED LATIN CAPITAL LETTER C;So;0;L;;;;;N;;;;;
|
||||
@ -30795,6 +31198,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
1F6D2;SHOPPING TROLLEY;So;0;ON;;;;;N;;;;;
|
||||
1F6D3;STUPA;So;0;ON;;;;;N;;;;;
|
||||
1F6D4;PAGODA;So;0;ON;;;;;N;;;;;
|
||||
1F6D5;HINDU TEMPLE;So;0;ON;;;;;N;;;;;
|
||||
1F6E0;HAMMER AND WRENCH;So;0;ON;;;;;N;;;;;
|
||||
1F6E1;SHIELD;So;0;ON;;;;;N;;;;;
|
||||
1F6E2;OIL DRUM;So;0;ON;;;;;N;;;;;
|
||||
@ -30818,6 +31222,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
1F6F7;SLED;So;0;ON;;;;;N;;;;;
|
||||
1F6F8;FLYING SAUCER;So;0;ON;;;;;N;;;;;
|
||||
1F6F9;SKATEBOARD;So;0;ON;;;;;N;;;;;
|
||||
1F6FA;AUTO RICKSHAW;So;0;ON;;;;;N;;;;;
|
||||
1F700;ALCHEMICAL SYMBOL FOR QUINTESSENCE;So;0;ON;;;;;N;;;;;
|
||||
1F701;ALCHEMICAL SYMBOL FOR AIR;So;0;ON;;;;;N;;;;;
|
||||
1F702;ALCHEMICAL SYMBOL FOR FIRE;So;0;ON;;;;;N;;;;;
|
||||
@ -31023,6 +31428,18 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
1F7D6;NEGATIVE CIRCLED TRIANGLE;So;0;ON;;;;;N;;;;;
|
||||
1F7D7;CIRCLED SQUARE;So;0;ON;;;;;N;;;;;
|
||||
1F7D8;NEGATIVE CIRCLED SQUARE;So;0;ON;;;;;N;;;;;
|
||||
1F7E0;LARGE ORANGE CIRCLE;So;0;ON;;;;;N;;;;;
|
||||
1F7E1;LARGE YELLOW CIRCLE;So;0;ON;;;;;N;;;;;
|
||||
1F7E2;LARGE GREEN CIRCLE;So;0;ON;;;;;N;;;;;
|
||||
1F7E3;LARGE PURPLE CIRCLE;So;0;ON;;;;;N;;;;;
|
||||
1F7E4;LARGE BROWN CIRCLE;So;0;ON;;;;;N;;;;;
|
||||
1F7E5;LARGE RED SQUARE;So;0;ON;;;;;N;;;;;
|
||||
1F7E6;LARGE BLUE SQUARE;So;0;ON;;;;;N;;;;;
|
||||
1F7E7;LARGE ORANGE SQUARE;So;0;ON;;;;;N;;;;;
|
||||
1F7E8;LARGE YELLOW SQUARE;So;0;ON;;;;;N;;;;;
|
||||
1F7E9;LARGE GREEN SQUARE;So;0;ON;;;;;N;;;;;
|
||||
1F7EA;LARGE PURPLE SQUARE;So;0;ON;;;;;N;;;;;
|
||||
1F7EB;LARGE BROWN SQUARE;So;0;ON;;;;;N;;;;;
|
||||
1F800;LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD;So;0;ON;;;;;N;;;;;
|
||||
1F801;UPWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD;So;0;ON;;;;;N;;;;;
|
||||
1F802;RIGHTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD;So;0;ON;;;;;N;;;;;
|
||||
@ -31183,6 +31600,9 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
1F909;DOWNWARD FACING NOTCHED HOOK;So;0;ON;;;;;N;;;;;
|
||||
1F90A;DOWNWARD FACING HOOK WITH DOT;So;0;ON;;;;;N;;;;;
|
||||
1F90B;DOWNWARD FACING NOTCHED HOOK WITH DOT;So;0;ON;;;;;N;;;;;
|
||||
1F90D;WHITE HEART;So;0;ON;;;;;N;;;;;
|
||||
1F90E;BROWN HEART;So;0;ON;;;;;N;;;;;
|
||||
1F90F;PINCHING HAND;So;0;ON;;;;;N;;;;;
|
||||
1F910;ZIPPER-MOUTH FACE;So;0;ON;;;;;N;;;;;
|
||||
1F911;MONEY-MOUTH FACE;So;0;ON;;;;;N;;;;;
|
||||
1F912;FACE WITH THERMOMETER;So;0;ON;;;;;N;;;;;
|
||||
@ -31230,6 +31650,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
1F93C;WRESTLERS;So;0;ON;;;;;N;;;;;
|
||||
1F93D;WATER POLO;So;0;ON;;;;;N;;;;;
|
||||
1F93E;HANDBALL;So;0;ON;;;;;N;;;;;
|
||||
1F93F;DIVING MASK;So;0;ON;;;;;N;;;;;
|
||||
1F940;WILTED FLOWER;So;0;ON;;;;;N;;;;;
|
||||
1F941;DRUM WITH DRUMSTICKS;So;0;ON;;;;;N;;;;;
|
||||
1F942;CLINKING GLASSES;So;0;ON;;;;;N;;;;;
|
||||
@ -31279,11 +31700,13 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
1F96E;MOON CAKE;So;0;ON;;;;;N;;;;;
|
||||
1F96F;BAGEL;So;0;ON;;;;;N;;;;;
|
||||
1F970;SMILING FACE WITH SMILING EYES AND THREE HEARTS;So;0;ON;;;;;N;;;;;
|
||||
1F971;YAWNING FACE;So;0;ON;;;;;N;;;;;
|
||||
1F973;FACE WITH PARTY HORN AND PARTY HAT;So;0;ON;;;;;N;;;;;
|
||||
1F974;FACE WITH UNEVEN EYES AND WAVY MOUTH;So;0;ON;;;;;N;;;;;
|
||||
1F975;OVERHEATED FACE;So;0;ON;;;;;N;;;;;
|
||||
1F976;FREEZING FACE;So;0;ON;;;;;N;;;;;
|
||||
1F97A;FACE WITH PLEADING EYES;So;0;ON;;;;;N;;;;;
|
||||
1F97B;SARI;So;0;ON;;;;;N;;;;;
|
||||
1F97C;LAB COAT;So;0;ON;;;;;N;;;;;
|
||||
1F97D;GOGGLES;So;0;ON;;;;;N;;;;;
|
||||
1F97E;HIKING BOOT;So;0;ON;;;;;N;;;;;
|
||||
@ -31323,6 +31746,14 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
1F9A0;MICROBE;So;0;ON;;;;;N;;;;;
|
||||
1F9A1;BADGER;So;0;ON;;;;;N;;;;;
|
||||
1F9A2;SWAN;So;0;ON;;;;;N;;;;;
|
||||
1F9A5;SLOTH;So;0;ON;;;;;N;;;;;
|
||||
1F9A6;OTTER;So;0;ON;;;;;N;;;;;
|
||||
1F9A7;ORANGUTAN;So;0;ON;;;;;N;;;;;
|
||||
1F9A8;SKUNK;So;0;ON;;;;;N;;;;;
|
||||
1F9A9;FLAMINGO;So;0;ON;;;;;N;;;;;
|
||||
1F9AA;OYSTER;So;0;ON;;;;;N;;;;;
|
||||
1F9AE;GUIDE DOG;So;0;ON;;;;;N;;;;;
|
||||
1F9AF;PROBING CANE;So;0;ON;;;;;N;;;;;
|
||||
1F9B0;EMOJI COMPONENT RED HAIR;So;0;ON;;;;;N;;;;;
|
||||
1F9B1;EMOJI COMPONENT CURLY HAIR;So;0;ON;;;;;N;;;;;
|
||||
1F9B2;EMOJI COMPONENT BALD;So;0;ON;;;;;N;;;;;
|
||||
@ -31333,9 +31764,26 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
1F9B7;TOOTH;So;0;ON;;;;;N;;;;;
|
||||
1F9B8;SUPERHERO;So;0;ON;;;;;N;;;;;
|
||||
1F9B9;SUPERVILLAIN;So;0;ON;;;;;N;;;;;
|
||||
1F9BA;SAFETY VEST;So;0;ON;;;;;N;;;;;
|
||||
1F9BB;EAR WITH HEARING AID;So;0;ON;;;;;N;;;;;
|
||||
1F9BC;MOTORIZED WHEELCHAIR;So;0;ON;;;;;N;;;;;
|
||||
1F9BD;MANUAL WHEELCHAIR;So;0;ON;;;;;N;;;;;
|
||||
1F9BE;MECHANICAL ARM;So;0;ON;;;;;N;;;;;
|
||||
1F9BF;MECHANICAL LEG;So;0;ON;;;;;N;;;;;
|
||||
1F9C0;CHEESE WEDGE;So;0;ON;;;;;N;;;;;
|
||||
1F9C1;CUPCAKE;So;0;ON;;;;;N;;;;;
|
||||
1F9C2;SALT SHAKER;So;0;ON;;;;;N;;;;;
|
||||
1F9C3;BEVERAGE BOX;So;0;ON;;;;;N;;;;;
|
||||
1F9C4;GARLIC;So;0;ON;;;;;N;;;;;
|
||||
1F9C5;ONION;So;0;ON;;;;;N;;;;;
|
||||
1F9C6;FALAFEL;So;0;ON;;;;;N;;;;;
|
||||
1F9C7;WAFFLE;So;0;ON;;;;;N;;;;;
|
||||
1F9C8;BUTTER;So;0;ON;;;;;N;;;;;
|
||||
1F9C9;MATE DRINK;So;0;ON;;;;;N;;;;;
|
||||
1F9CA;ICE CUBE;So;0;ON;;;;;N;;;;;
|
||||
1F9CD;STANDING PERSON;So;0;ON;;;;;N;;;;;
|
||||
1F9CE;KNEELING PERSON;So;0;ON;;;;;N;;;;;
|
||||
1F9CF;DEAF PERSON;So;0;ON;;;;;N;;;;;
|
||||
1F9D0;FACE WITH MONOCLE;So;0;ON;;;;;N;;;;;
|
||||
1F9D1;ADULT;So;0;ON;;;;;N;;;;;
|
||||
1F9D2;CHILD;So;0;ON;;;;;N;;;;;
|
||||
@ -31384,6 +31832,90 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
1F9FD;SPONGE;So;0;ON;;;;;N;;;;;
|
||||
1F9FE;RECEIPT;So;0;ON;;;;;N;;;;;
|
||||
1F9FF;NAZAR AMULET;So;0;ON;;;;;N;;;;;
|
||||
1FA00;NEUTRAL CHESS KING;So;0;ON;;;;;N;;;;;
|
||||
1FA01;NEUTRAL CHESS QUEEN;So;0;ON;;;;;N;;;;;
|
||||
1FA02;NEUTRAL CHESS ROOK;So;0;ON;;;;;N;;;;;
|
||||
1FA03;NEUTRAL CHESS BISHOP;So;0;ON;;;;;N;;;;;
|
||||
1FA04;NEUTRAL CHESS KNIGHT;So;0;ON;;;;;N;;;;;
|
||||
1FA05;NEUTRAL CHESS PAWN;So;0;ON;;;;;N;;;;;
|
||||
1FA06;WHITE CHESS KNIGHT ROTATED FORTY-FIVE DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA07;BLACK CHESS KNIGHT ROTATED FORTY-FIVE DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA08;NEUTRAL CHESS KNIGHT ROTATED FORTY-FIVE DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA09;WHITE CHESS KING ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA0A;WHITE CHESS QUEEN ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA0B;WHITE CHESS ROOK ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA0C;WHITE CHESS BISHOP ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA0D;WHITE CHESS KNIGHT ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA0E;WHITE CHESS PAWN ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA0F;BLACK CHESS KING ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA10;BLACK CHESS QUEEN ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA11;BLACK CHESS ROOK ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA12;BLACK CHESS BISHOP ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA13;BLACK CHESS KNIGHT ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA14;BLACK CHESS PAWN ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA15;NEUTRAL CHESS KING ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA16;NEUTRAL CHESS QUEEN ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA17;NEUTRAL CHESS ROOK ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA18;NEUTRAL CHESS BISHOP ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA19;NEUTRAL CHESS KNIGHT ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA1A;NEUTRAL CHESS PAWN ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA1B;WHITE CHESS KNIGHT ROTATED ONE HUNDRED THIRTY-FIVE DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA1C;BLACK CHESS KNIGHT ROTATED ONE HUNDRED THIRTY-FIVE DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA1D;NEUTRAL CHESS KNIGHT ROTATED ONE HUNDRED THIRTY-FIVE DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA1E;WHITE CHESS TURNED KING;So;0;ON;;;;;N;;;;;
|
||||
1FA1F;WHITE CHESS TURNED QUEEN;So;0;ON;;;;;N;;;;;
|
||||
1FA20;WHITE CHESS TURNED ROOK;So;0;ON;;;;;N;;;;;
|
||||
1FA21;WHITE CHESS TURNED BISHOP;So;0;ON;;;;;N;;;;;
|
||||
1FA22;WHITE CHESS TURNED KNIGHT;So;0;ON;;;;;N;;;;;
|
||||
1FA23;WHITE CHESS TURNED PAWN;So;0;ON;;;;;N;;;;;
|
||||
1FA24;BLACK CHESS TURNED KING;So;0;ON;;;;;N;;;;;
|
||||
1FA25;BLACK CHESS TURNED QUEEN;So;0;ON;;;;;N;;;;;
|
||||
1FA26;BLACK CHESS TURNED ROOK;So;0;ON;;;;;N;;;;;
|
||||
1FA27;BLACK CHESS TURNED BISHOP;So;0;ON;;;;;N;;;;;
|
||||
1FA28;BLACK CHESS TURNED KNIGHT;So;0;ON;;;;;N;;;;;
|
||||
1FA29;BLACK CHESS TURNED PAWN;So;0;ON;;;;;N;;;;;
|
||||
1FA2A;NEUTRAL CHESS TURNED KING;So;0;ON;;;;;N;;;;;
|
||||
1FA2B;NEUTRAL CHESS TURNED QUEEN;So;0;ON;;;;;N;;;;;
|
||||
1FA2C;NEUTRAL CHESS TURNED ROOK;So;0;ON;;;;;N;;;;;
|
||||
1FA2D;NEUTRAL CHESS TURNED BISHOP;So;0;ON;;;;;N;;;;;
|
||||
1FA2E;NEUTRAL CHESS TURNED KNIGHT;So;0;ON;;;;;N;;;;;
|
||||
1FA2F;NEUTRAL CHESS TURNED PAWN;So;0;ON;;;;;N;;;;;
|
||||
1FA30;WHITE CHESS KNIGHT ROTATED TWO HUNDRED TWENTY-FIVE DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA31;BLACK CHESS KNIGHT ROTATED TWO HUNDRED TWENTY-FIVE DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA32;NEUTRAL CHESS KNIGHT ROTATED TWO HUNDRED TWENTY-FIVE DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA33;WHITE CHESS KING ROTATED TWO HUNDRED SEVENTY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA34;WHITE CHESS QUEEN ROTATED TWO HUNDRED SEVENTY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA35;WHITE CHESS ROOK ROTATED TWO HUNDRED SEVENTY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA36;WHITE CHESS BISHOP ROTATED TWO HUNDRED SEVENTY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA37;WHITE CHESS KNIGHT ROTATED TWO HUNDRED SEVENTY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA38;WHITE CHESS PAWN ROTATED TWO HUNDRED SEVENTY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA39;BLACK CHESS KING ROTATED TWO HUNDRED SEVENTY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA3A;BLACK CHESS QUEEN ROTATED TWO HUNDRED SEVENTY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA3B;BLACK CHESS ROOK ROTATED TWO HUNDRED SEVENTY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA3C;BLACK CHESS BISHOP ROTATED TWO HUNDRED SEVENTY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA3D;BLACK CHESS KNIGHT ROTATED TWO HUNDRED SEVENTY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA3E;BLACK CHESS PAWN ROTATED TWO HUNDRED SEVENTY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA3F;NEUTRAL CHESS KING ROTATED TWO HUNDRED SEVENTY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA40;NEUTRAL CHESS QUEEN ROTATED TWO HUNDRED SEVENTY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA41;NEUTRAL CHESS ROOK ROTATED TWO HUNDRED SEVENTY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA42;NEUTRAL CHESS BISHOP ROTATED TWO HUNDRED SEVENTY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA43;NEUTRAL CHESS KNIGHT ROTATED TWO HUNDRED SEVENTY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA44;NEUTRAL CHESS PAWN ROTATED TWO HUNDRED SEVENTY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA45;WHITE CHESS KNIGHT ROTATED THREE HUNDRED FIFTEEN DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA46;BLACK CHESS KNIGHT ROTATED THREE HUNDRED FIFTEEN DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA47;NEUTRAL CHESS KNIGHT ROTATED THREE HUNDRED FIFTEEN DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA48;WHITE CHESS EQUIHOPPER;So;0;ON;;;;;N;;;;;
|
||||
1FA49;BLACK CHESS EQUIHOPPER;So;0;ON;;;;;N;;;;;
|
||||
1FA4A;NEUTRAL CHESS EQUIHOPPER;So;0;ON;;;;;N;;;;;
|
||||
1FA4B;WHITE CHESS EQUIHOPPER ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA4C;BLACK CHESS EQUIHOPPER ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA4D;NEUTRAL CHESS EQUIHOPPER ROTATED NINETY DEGREES;So;0;ON;;;;;N;;;;;
|
||||
1FA4E;WHITE CHESS KNIGHT-QUEEN;So;0;ON;;;;;N;;;;;
|
||||
1FA4F;WHITE CHESS KNIGHT-ROOK;So;0;ON;;;;;N;;;;;
|
||||
1FA50;WHITE CHESS KNIGHT-BISHOP;So;0;ON;;;;;N;;;;;
|
||||
1FA51;BLACK CHESS KNIGHT-QUEEN;So;0;ON;;;;;N;;;;;
|
||||
1FA52;BLACK CHESS KNIGHT-ROOK;So;0;ON;;;;;N;;;;;
|
||||
1FA53;BLACK CHESS KNIGHT-BISHOP;So;0;ON;;;;;N;;;;;
|
||||
1FA60;XIANGQI RED GENERAL;So;0;ON;;;;;N;;;;;
|
||||
1FA61;XIANGQI RED MANDARIN;So;0;ON;;;;;N;;;;;
|
||||
1FA62;XIANGQI RED ELEPHANT;So;0;ON;;;;;N;;;;;
|
||||
@ -31398,6 +31930,22 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
||||
1FA6B;XIANGQI BLACK CHARIOT;So;0;ON;;;;;N;;;;;
|
||||
1FA6C;XIANGQI BLACK CANNON;So;0;ON;;;;;N;;;;;
|
||||
1FA6D;XIANGQI BLACK SOLDIER;So;0;ON;;;;;N;;;;;
|
||||
1FA70;BALLET SHOES;So;0;ON;;;;;N;;;;;
|
||||
1FA71;ONE-PIECE SWIMSUIT;So;0;ON;;;;;N;;;;;
|
||||
1FA72;BRIEFS;So;0;ON;;;;;N;;;;;
|
||||
1FA73;SHORTS;So;0;ON;;;;;N;;;;;
|
||||
1FA78;DROP OF BLOOD;So;0;ON;;;;;N;;;;;
|
||||
1FA79;ADHESIVE BANDAGE;So;0;ON;;;;;N;;;;;
|
||||
1FA7A;STETHOSCOPE;So;0;ON;;;;;N;;;;;
|
||||
1FA80;YO-YO;So;0;ON;;;;;N;;;;;
|
||||
1FA81;KITE;So;0;ON;;;;;N;;;;;
|
||||
1FA82;PARACHUTE;So;0;ON;;;;;N;;;;;
|
||||
1FA90;RINGED PLANET;So;0;ON;;;;;N;;;;;
|
||||
1FA91;CHAIR;So;0;ON;;;;;N;;;;;
|
||||
1FA92;RAZOR;So;0;ON;;;;;N;;;;;
|
||||
1FA93;AXE;So;0;ON;;;;;N;;;;;
|
||||
1FA94;DIYA LAMP;So;0;ON;;;;;N;;;;;
|
||||
1FA95;BANJO;So;0;ON;;;;;N;;;;;
|
||||
20000;<CJK Ideograph Extension B, First>;Lo;0;L;;;;;N;;;;;
|
||||
2A6D6;<CJK Ideograph Extension B, Last>;Lo;0;L;;;;;N;;;;;
|
||||
2A700;<CJK Ideograph Extension C, First>;Lo;0;L;;;;;N;;;;;
|
||||
|
@ -1 +1 @@
|
||||
11.0.0
|
||||
12.1.0
|
||||
|
@ -1,10 +1,11 @@
|
||||
# GraphemeBreakProperty-8.0.0.txt
|
||||
# Date: 2015-02-13, 13:47:14 GMT [MD]
|
||||
# GraphemeBreakProperty-12.1.0.txt
|
||||
# Date: 2019-03-10, 10:53:12 GMT
|
||||
# Copyright (c) 2019 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
|
||||
#
|
||||
# Unicode Character Database
|
||||
# Copyright (c) 1991-2015 Unicode, Inc.
|
||||
# For terms of use, see http://www.unicode.org/terms_of_use.html
|
||||
# For documentation, see http://www.unicode.org/reports/tr44/
|
||||
# For documentation, see http://www.unicode.org/reports/tr44/
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -17,6 +18,22 @@
|
||||
|
||||
# ================================================
|
||||
|
||||
0600..0605 ; Prepend # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE
|
||||
06DD ; Prepend # Cf ARABIC END OF AYAH
|
||||
070F ; Prepend # Cf SYRIAC ABBREVIATION MARK
|
||||
08E2 ; Prepend # Cf ARABIC DISPUTED END OF AYAH
|
||||
0D4E ; Prepend # Lo MALAYALAM LETTER DOT REPH
|
||||
110BD ; Prepend # Cf KAITHI NUMBER SIGN
|
||||
110CD ; Prepend # Cf KAITHI NUMBER SIGN ABOVE
|
||||
111C2..111C3 ; Prepend # Lo [2] SHARADA SIGN JIHVAMULIYA..SHARADA SIGN UPADHMANIYA
|
||||
11A3A ; Prepend # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA
|
||||
11A84..11A89 ; Prepend # Lo [6] SOYOMBO SIGN JIHVAMULIYA..SOYOMBO CLUSTER-INITIAL LETTER SA
|
||||
11D46 ; Prepend # Lo MASARAM GONDI REPHA
|
||||
|
||||
# Total code points: 22
|
||||
|
||||
# ================================================
|
||||
|
||||
000D ; CR # Cc <control-000D>
|
||||
|
||||
# Total code points: 1
|
||||
@ -34,10 +51,7 @@
|
||||
000E..001F ; Control # Cc [18] <control-000E>..<control-001F>
|
||||
007F..009F ; Control # Cc [33] <control-007F>..<control-009F>
|
||||
00AD ; Control # Cf SOFT HYPHEN
|
||||
0600..0605 ; Control # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE
|
||||
061C ; Control # Cf ARABIC LETTER MARK
|
||||
06DD ; Control # Cf ARABIC END OF AYAH
|
||||
070F ; Control # Cf SYRIAC ABBREVIATION MARK
|
||||
180E ; Control # Cf MONGOLIAN VOWEL SEPARATOR
|
||||
200B ; Control # Cf ZERO WIDTH SPACE
|
||||
200E..200F ; Control # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
|
||||
@ -47,21 +61,19 @@
|
||||
2060..2064 ; Control # Cf [5] WORD JOINER..INVISIBLE PLUS
|
||||
2065 ; Control # Cn <reserved-2065>
|
||||
2066..206F ; Control # Cf [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES
|
||||
D800..DFFF ; Control # Cs [2048] <surrogate-D800>..<surrogate-DFFF>
|
||||
FEFF ; Control # Cf ZERO WIDTH NO-BREAK SPACE
|
||||
FFF0..FFF8 ; Control # Cn [9] <reserved-FFF0>..<reserved-FFF8>
|
||||
FFF9..FFFB ; Control # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR
|
||||
110BD ; Control # Cf KAITHI NUMBER SIGN
|
||||
13430..13438 ; Control # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT
|
||||
1BCA0..1BCA3 ; Control # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
|
||||
1D173..1D17A ; Control # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
|
||||
E0000 ; Control # Cn <reserved-E0000>
|
||||
E0001 ; Control # Cf LANGUAGE TAG
|
||||
E0002..E001F ; Control # Cn [30] <reserved-E0002>..<reserved-E001F>
|
||||
E0020..E007F ; Control # Cf [96] TAG SPACE..CANCEL TAG
|
||||
E0080..E00FF ; Control # Cn [128] <reserved-E0080>..<reserved-E00FF>
|
||||
E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
|
||||
|
||||
# Total code points: 6030
|
||||
# Total code points: 3886
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -84,11 +96,13 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
|
||||
0730..074A ; Extend # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH
|
||||
07A6..07B0 ; Extend # Mn [11] THAANA ABAFILI..THAANA SUKUN
|
||||
07EB..07F3 ; Extend # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE
|
||||
07FD ; Extend # Mn NKO DANTAYALAN
|
||||
0816..0819 ; Extend # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH
|
||||
081B..0823 ; Extend # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A
|
||||
0825..0827 ; Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U
|
||||
0829..082D ; Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA
|
||||
0859..085B ; Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK
|
||||
08D3..08E1 ; Extend # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA
|
||||
08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA
|
||||
093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE
|
||||
093C ; Extend # Mn DEVANAGARI SIGN NUKTA
|
||||
@ -103,6 +117,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
|
||||
09CD ; Extend # Mn BENGALI SIGN VIRAMA
|
||||
09D7 ; Extend # Mc BENGALI AU LENGTH MARK
|
||||
09E2..09E3 ; Extend # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL
|
||||
09FE ; Extend # Mn BENGALI SANDHI MARK
|
||||
0A01..0A02 ; Extend # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI
|
||||
0A3C ; Extend # Mn GURMUKHI SIGN NUKTA
|
||||
0A41..0A42 ; Extend # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU
|
||||
@ -117,6 +132,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
|
||||
0AC7..0AC8 ; Extend # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI
|
||||
0ACD ; Extend # Mn GUJARATI SIGN VIRAMA
|
||||
0AE2..0AE3 ; Extend # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL
|
||||
0AFA..0AFF ; Extend # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
|
||||
0B01 ; Extend # Mn ORIYA SIGN CANDRABINDU
|
||||
0B3C ; Extend # Mn ORIYA SIGN NUKTA
|
||||
0B3E ; Extend # Mc ORIYA VOWEL SIGN AA
|
||||
@ -132,6 +148,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
|
||||
0BCD ; Extend # Mn TAMIL SIGN VIRAMA
|
||||
0BD7 ; Extend # Mc TAMIL AU LENGTH MARK
|
||||
0C00 ; Extend # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE
|
||||
0C04 ; Extend # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE
|
||||
0C3E..0C40 ; Extend # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II
|
||||
0C46..0C48 ; Extend # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI
|
||||
0C4A..0C4D ; Extend # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA
|
||||
@ -145,7 +162,8 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
|
||||
0CCC..0CCD ; Extend # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA
|
||||
0CD5..0CD6 ; Extend # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK
|
||||
0CE2..0CE3 ; Extend # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
|
||||
0D01 ; Extend # Mn MALAYALAM SIGN CANDRABINDU
|
||||
0D00..0D01 ; Extend # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
|
||||
0D3B..0D3C ; Extend # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
|
||||
0D3E ; Extend # Mc MALAYALAM VOWEL SIGN AA
|
||||
0D41..0D44 ; Extend # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR
|
||||
0D4D ; Extend # Mn MALAYALAM SIGN VIRAMA
|
||||
@ -160,8 +178,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
|
||||
0E34..0E3A ; Extend # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU
|
||||
0E47..0E4E ; Extend # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN
|
||||
0EB1 ; Extend # Mn LAO VOWEL SIGN MAI KAN
|
||||
0EB4..0EB9 ; Extend # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU
|
||||
0EBB..0EBC ; Extend # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO
|
||||
0EB4..0EBC ; Extend # Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO
|
||||
0EC8..0ECD ; Extend # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA
|
||||
0F18..0F19 ; Extend # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS
|
||||
0F35 ; Extend # Mn TIBETAN MARK NGAS BZUNG NYI ZLA
|
||||
@ -195,6 +212,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
|
||||
17C9..17D3 ; Extend # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT
|
||||
17DD ; Extend # Mn KHMER SIGN ATTHACAN
|
||||
180B..180D ; Extend # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
|
||||
1885..1886 ; Extend # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA
|
||||
18A9 ; Extend # Mn MONGOLIAN LETTER ALI GALI DAGALGA
|
||||
1920..1922 ; Extend # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U
|
||||
1927..1928 ; Extend # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O
|
||||
@ -213,6 +231,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
|
||||
1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY
|
||||
1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG
|
||||
1B34 ; Extend # Mn BALINESE SIGN REREKAN
|
||||
1B35 ; Extend # Mc BALINESE VOWEL SIGN TEDUNG
|
||||
1B36..1B3A ; Extend # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA
|
||||
1B3C ; Extend # Mn BALINESE VOWEL SIGN LA LENGA
|
||||
1B42 ; Extend # Mn BALINESE VOWEL SIGN PEPET
|
||||
@ -233,9 +252,9 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
|
||||
1CED ; Extend # Mn VEDIC SIGN TIRYAK
|
||||
1CF4 ; Extend # Mn VEDIC TONE CANDRA ABOVE
|
||||
1CF8..1CF9 ; Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE
|
||||
1DC0..1DF5 ; Extend # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE
|
||||
1DFC..1DFF ; Extend # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
|
||||
200C..200D ; Extend # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER
|
||||
1DC0..1DF9 ; Extend # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW
|
||||
1DFB..1DFF ; Extend # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
|
||||
200C ; Extend # Cf ZERO WIDTH NON-JOINER
|
||||
20D0..20DC ; Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
|
||||
20DD..20E0 ; Extend # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH
|
||||
20E1 ; Extend # Mn COMBINING LEFT RIGHT ARROW ABOVE
|
||||
@ -256,14 +275,15 @@ A802 ; Extend # Mn SYLOTI NAGRI SIGN DVISVARA
|
||||
A806 ; Extend # Mn SYLOTI NAGRI SIGN HASANTA
|
||||
A80B ; Extend # Mn SYLOTI NAGRI SIGN ANUSVARA
|
||||
A825..A826 ; Extend # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E
|
||||
A8C4 ; Extend # Mn SAURASHTRA SIGN VIRAMA
|
||||
A8C4..A8C5 ; Extend # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU
|
||||
A8E0..A8F1 ; Extend # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA
|
||||
A8FF ; Extend # Mn DEVANAGARI VOWEL SIGN AY
|
||||
A926..A92D ; Extend # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU
|
||||
A947..A951 ; Extend # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R
|
||||
A980..A982 ; Extend # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR
|
||||
A9B3 ; Extend # Mn JAVANESE SIGN CECAK TELU
|
||||
A9B6..A9B9 ; Extend # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT
|
||||
A9BC ; Extend # Mn JAVANESE VOWEL SIGN PEPET
|
||||
A9BC..A9BD ; Extend # Mn [2] JAVANESE VOWEL SIGN PEPET..JAVANESE CONSONANT SIGN KERET
|
||||
A9E5 ; Extend # Mn MYANMAR SIGN SHAN SAW
|
||||
AA29..AA2E ; Extend # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE
|
||||
AA31..AA32 ; Extend # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE
|
||||
@ -294,6 +314,8 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
||||
10A38..10A3A ; Extend # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW
|
||||
10A3F ; Extend # Mn KHAROSHTHI VIRAMA
|
||||
10AE5..10AE6 ; Extend # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW
|
||||
10D24..10D27 ; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
|
||||
10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW
|
||||
11001 ; Extend # Mn BRAHMI SIGN ANUSVARA
|
||||
11038..11046 ; Extend # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA
|
||||
1107F..11081 ; Extend # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA
|
||||
@ -305,19 +327,24 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
||||
11173 ; Extend # Mn MAHAJANI SIGN NUKTA
|
||||
11180..11181 ; Extend # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA
|
||||
111B6..111BE ; Extend # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O
|
||||
111CA..111CC ; Extend # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK
|
||||
111C9..111CC ; Extend # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK
|
||||
1122F..11231 ; Extend # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI
|
||||
11234 ; Extend # Mn KHOJKI SIGN ANUSVARA
|
||||
11236..11237 ; Extend # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
|
||||
1123E ; Extend # Mn KHOJKI SIGN SUKUN
|
||||
112DF ; Extend # Mn KHUDAWADI SIGN ANUSVARA
|
||||
112E3..112EA ; Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
|
||||
11300..11301 ; Extend # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
|
||||
1133C ; Extend # Mn GRANTHA SIGN NUKTA
|
||||
1133B..1133C ; Extend # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA
|
||||
1133E ; Extend # Mc GRANTHA VOWEL SIGN AA
|
||||
11340 ; Extend # Mn GRANTHA VOWEL SIGN II
|
||||
11357 ; Extend # Mc GRANTHA AU LENGTH MARK
|
||||
11366..1136C ; Extend # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX
|
||||
11370..11374 ; Extend # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA
|
||||
11438..1143F ; Extend # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI
|
||||
11442..11444 ; Extend # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA
|
||||
11446 ; Extend # Mn NEWA SIGN NUKTA
|
||||
1145E ; Extend # Mn NEWA SANDHI MARK
|
||||
114B0 ; Extend # Mc TIRHUTA VOWEL SIGN AA
|
||||
114B3..114B8 ; Extend # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL
|
||||
114BA ; Extend # Mn TIRHUTA VOWEL SIGN SHORT E
|
||||
@ -339,8 +366,38 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
||||
1171D..1171F ; Extend # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA
|
||||
11722..11725 ; Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
|
||||
11727..1172B ; Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER
|
||||
1182F..11837 ; Extend # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA
|
||||
11839..1183A ; Extend # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA
|
||||
119D4..119D7 ; Extend # Mn [4] NANDINAGARI VOWEL SIGN U..NANDINAGARI VOWEL SIGN VOCALIC RR
|
||||
119DA..119DB ; Extend # Mn [2] NANDINAGARI VOWEL SIGN E..NANDINAGARI VOWEL SIGN AI
|
||||
119E0 ; Extend # Mn NANDINAGARI SIGN VIRAMA
|
||||
11A01..11A0A ; Extend # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK
|
||||
11A33..11A38 ; Extend # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA
|
||||
11A3B..11A3E ; Extend # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA
|
||||
11A47 ; Extend # Mn ZANABAZAR SQUARE SUBJOINER
|
||||
11A51..11A56 ; Extend # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE
|
||||
11A59..11A5B ; Extend # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK
|
||||
11A8A..11A96 ; Extend # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA
|
||||
11A98..11A99 ; Extend # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER
|
||||
11C30..11C36 ; Extend # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L
|
||||
11C38..11C3D ; Extend # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA
|
||||
11C3F ; Extend # Mn BHAIKSUKI SIGN VIRAMA
|
||||
11C92..11CA7 ; Extend # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA
|
||||
11CAA..11CB0 ; Extend # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA
|
||||
11CB2..11CB3 ; Extend # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E
|
||||
11CB5..11CB6 ; Extend # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU
|
||||
11D31..11D36 ; Extend # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R
|
||||
11D3A ; Extend # Mn MASARAM GONDI VOWEL SIGN E
|
||||
11D3C..11D3D ; Extend # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O
|
||||
11D3F..11D45 ; Extend # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA
|
||||
11D47 ; Extend # Mn MASARAM GONDI RA-KARA
|
||||
11D90..11D91 ; Extend # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI
|
||||
11D95 ; Extend # Mn GUNJALA GONDI SIGN ANUSVARA
|
||||
11D97 ; Extend # Mn GUNJALA GONDI VIRAMA
|
||||
11EF3..11EF4 ; Extend # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
|
||||
16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
|
||||
16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
|
||||
16F4F ; Extend # Mn MIAO SIGN CONSONANT MODIFIER BAR
|
||||
16F8F..16F92 ; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
|
||||
1BC9D..1BC9E ; Extend # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK
|
||||
1D165 ; Extend # Mc MUSICAL SYMBOL COMBINING STEM
|
||||
@ -356,10 +413,20 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
||||
1DA84 ; Extend # Mn SIGNWRITING LOCATION HEAD NECK
|
||||
1DA9B..1DA9F ; Extend # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6
|
||||
1DAA1..1DAAF ; Extend # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16
|
||||
1E000..1E006 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
|
||||
1E008..1E018 ; Extend # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
|
||||
1E01B..1E021 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
|
||||
1E023..1E024 ; Extend # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
|
||||
1E026..1E02A ; Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
|
||||
1E130..1E136 ; Extend # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
|
||||
1E2EC..1E2EF ; Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI
|
||||
1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
|
||||
1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA
|
||||
1F3FB..1F3FF ; Extend # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
|
||||
E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG
|
||||
E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
|
||||
|
||||
# Total code points: 1610
|
||||
# Total code points: 1970
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -428,7 +495,6 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
|
||||
1A57 ; SpacingMark # Mc TAI THAM CONSONANT SIGN LA TANG LAI
|
||||
1A6D..1A72 ; SpacingMark # Mc [6] TAI THAM VOWEL SIGN OY..TAI THAM VOWEL SIGN THAM AI
|
||||
1B04 ; SpacingMark # Mc BALINESE SIGN BISAH
|
||||
1B35 ; SpacingMark # Mc BALINESE VOWEL SIGN TEDUNG
|
||||
1B3B ; SpacingMark # Mc BALINESE VOWEL SIGN RA REPA TEDUNG
|
||||
1B3D..1B41 ; SpacingMark # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG
|
||||
1B43..1B44 ; SpacingMark # Mc [2] BALINESE VOWEL SIGN PEPET TEDUNG..BALINESE ADEG ADEG
|
||||
@ -443,7 +509,7 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
|
||||
1C24..1C2B ; SpacingMark # Mc [8] LEPCHA SUBJOINED LETTER YA..LEPCHA VOWEL SIGN UU
|
||||
1C34..1C35 ; SpacingMark # Mc [2] LEPCHA CONSONANT SIGN NYIN-DO..LEPCHA CONSONANT SIGN KANG
|
||||
1CE1 ; SpacingMark # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA
|
||||
1CF2..1CF3 ; SpacingMark # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
|
||||
1CF7 ; SpacingMark # Mc VEDIC SIGN ATIKRAMA
|
||||
A823..A824 ; SpacingMark # Mc [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIGN I
|
||||
A827 ; SpacingMark # Mc SYLOTI NAGRI VOWEL SIGN OO
|
||||
A880..A881 ; SpacingMark # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA
|
||||
@ -452,7 +518,7 @@ A952..A953 ; SpacingMark # Mc [2] REJANG CONSONANT SIGN H..REJANG VIRAMA
|
||||
A983 ; SpacingMark # Mc JAVANESE SIGN WIGNYAN
|
||||
A9B4..A9B5 ; SpacingMark # Mc [2] JAVANESE VOWEL SIGN TARUNG..JAVANESE VOWEL SIGN TOLONG
|
||||
A9BA..A9BB ; SpacingMark # Mc [2] JAVANESE VOWEL SIGN TALING..JAVANESE VOWEL SIGN DIRGA MURE
|
||||
A9BD..A9C0 ; SpacingMark # Mc [4] JAVANESE CONSONANT SIGN KERET..JAVANESE PANGKON
|
||||
A9BE..A9C0 ; SpacingMark # Mc [3] JAVANESE CONSONANT SIGN PENGKAL..JAVANESE PANGKON
|
||||
AA2F..AA30 ; SpacingMark # Mc [2] CHAM VOWEL SIGN O..CHAM VOWEL SIGN AI
|
||||
AA33..AA34 ; SpacingMark # Mc [2] CHAM CONSONANT SIGN YA..CHAM CONSONANT SIGN RA
|
||||
AA4D ; SpacingMark # Mc CHAM CONSONANT SIGN FINAL H
|
||||
@ -469,6 +535,7 @@ ABEC ; SpacingMark # Mc MEETEI MAYEK LUM IYEK
|
||||
110B0..110B2 ; SpacingMark # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II
|
||||
110B7..110B8 ; SpacingMark # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU
|
||||
1112C ; SpacingMark # Mc CHAKMA VOWEL SIGN E
|
||||
11145..11146 ; SpacingMark # Mc [2] CHAKMA VOWEL SIGN AA..CHAKMA VOWEL SIGN EI
|
||||
11182 ; SpacingMark # Mc SHARADA SIGN VISARGA
|
||||
111B3..111B5 ; SpacingMark # Mc [3] SHARADA VOWEL SIGN AA..SHARADA VOWEL SIGN II
|
||||
111BF..111C0 ; SpacingMark # Mc [2] SHARADA VOWEL SIGN AU..SHARADA SIGN VIRAMA
|
||||
@ -482,6 +549,9 @@ ABEC ; SpacingMark # Mc MEETEI MAYEK LUM IYEK
|
||||
11347..11348 ; SpacingMark # Mc [2] GRANTHA VOWEL SIGN EE..GRANTHA VOWEL SIGN AI
|
||||
1134B..1134D ; SpacingMark # Mc [3] GRANTHA VOWEL SIGN OO..GRANTHA SIGN VIRAMA
|
||||
11362..11363 ; SpacingMark # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL
|
||||
11435..11437 ; SpacingMark # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II
|
||||
11440..11441 ; SpacingMark # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU
|
||||
11445 ; SpacingMark # Mc NEWA SIGN VISARGA
|
||||
114B1..114B2 ; SpacingMark # Mc [2] TIRHUTA VOWEL SIGN I..TIRHUTA VOWEL SIGN II
|
||||
114B9 ; SpacingMark # Mc TIRHUTA VOWEL SIGN E
|
||||
114BB..114BC ; SpacingMark # Mc [2] TIRHUTA VOWEL SIGN AI..TIRHUTA VOWEL SIGN O
|
||||
@ -498,11 +568,28 @@ ABEC ; SpacingMark # Mc MEETEI MAYEK LUM IYEK
|
||||
116B6 ; SpacingMark # Mc TAKRI SIGN VIRAMA
|
||||
11720..11721 ; SpacingMark # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA
|
||||
11726 ; SpacingMark # Mc AHOM VOWEL SIGN E
|
||||
16F51..16F7E ; SpacingMark # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
|
||||
1182C..1182E ; SpacingMark # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II
|
||||
11838 ; SpacingMark # Mc DOGRA SIGN VISARGA
|
||||
119D1..119D3 ; SpacingMark # Mc [3] NANDINAGARI VOWEL SIGN AA..NANDINAGARI VOWEL SIGN II
|
||||
119DC..119DF ; SpacingMark # Mc [4] NANDINAGARI VOWEL SIGN O..NANDINAGARI SIGN VISARGA
|
||||
119E4 ; SpacingMark # Mc NANDINAGARI VOWEL SIGN PRISHTHAMATRA E
|
||||
11A39 ; SpacingMark # Mc ZANABAZAR SQUARE SIGN VISARGA
|
||||
11A57..11A58 ; SpacingMark # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU
|
||||
11A97 ; SpacingMark # Mc SOYOMBO SIGN VISARGA
|
||||
11C2F ; SpacingMark # Mc BHAIKSUKI VOWEL SIGN AA
|
||||
11C3E ; SpacingMark # Mc BHAIKSUKI SIGN VISARGA
|
||||
11CA9 ; SpacingMark # Mc MARCHEN SUBJOINED LETTER YA
|
||||
11CB1 ; SpacingMark # Mc MARCHEN VOWEL SIGN I
|
||||
11CB4 ; SpacingMark # Mc MARCHEN VOWEL SIGN O
|
||||
11D8A..11D8E ; SpacingMark # Mc [5] GUNJALA GONDI VOWEL SIGN AA..GUNJALA GONDI VOWEL SIGN UU
|
||||
11D93..11D94 ; SpacingMark # Mc [2] GUNJALA GONDI VOWEL SIGN OO..GUNJALA GONDI VOWEL SIGN AU
|
||||
11D96 ; SpacingMark # Mc GUNJALA GONDI SIGN VISARGA
|
||||
11EF5..11EF6 ; SpacingMark # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
|
||||
16F51..16F87 ; SpacingMark # Mc [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI
|
||||
1D166 ; SpacingMark # Mc MUSICAL SYMBOL COMBINING SPRECHGESANG STEM
|
||||
1D16D ; SpacingMark # Mc MUSICAL SYMBOL COMBINING AUGMENTATION DOT
|
||||
|
||||
# Total code points: 330
|
||||
# Total code points: 375
|
||||
|
||||
# ================================================
|
||||
|
||||
@ -1333,4 +1420,10 @@ D789..D7A3 ; LVT # Lo [27] HANGUL SYLLABLE HIG..HANGUL SYLLABLE HIH
|
||||
|
||||
# Total code points: 10773
|
||||
|
||||
# ================================================
|
||||
|
||||
200D ; ZWJ # Cf ZERO WIDTH JOINER
|
||||
|
||||
# Total code points: 1
|
||||
|
||||
# EOF
|
630
make/data/unicodedata/auxiliary/GraphemeBreakTest.txt
Normal file
630
make/data/unicodedata/auxiliary/GraphemeBreakTest.txt
Normal file
@ -0,0 +1,630 @@
|
||||
# GraphemeBreakTest-12.1.0.txt
|
||||
# Date: 2019-03-10, 10:53:12 GMT
|
||||
# Copyright (c) 2019 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
|
||||
#
|
||||
# Unicode Character Database
|
||||
# For documentation, see http://www.unicode.org/reports/tr44/
|
||||
#
|
||||
# Default Grapheme_Cluster_Break Test
|
||||
#
|
||||
# Format:
|
||||
# <string> (# <comment>)?
|
||||
# <string> contains hex Unicode code points, with
|
||||
# ÷ wherever there is a break opportunity, and
|
||||
# × wherever there is not.
|
||||
# <comment> the format can change, but currently it shows:
|
||||
# - the sample character name
|
||||
# - (x) the Grapheme_Cluster_Break property value for the sample character
|
||||
# - [x] the rule that determines whether there is a break or not,
|
||||
# as listed in the Rules section of GraphemeBreakTest.html
|
||||
#
|
||||
# These samples may be extended or changed in the future.
|
||||
#
|
||||
÷ 0020 ÷ 0020 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0020 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0020 ÷ 000D ÷ # ÷ [0.2] SPACE (Other) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 000D ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0020 ÷ 000A ÷ # ÷ [0.2] SPACE (Other) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 000A ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0020 ÷ 0001 ÷ # ÷ [0.2] SPACE (Other) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0001 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0020 × 034F ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 0020 × 0308 × 034F ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 0020 ÷ 1F1E6 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 0020 ÷ 0600 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0600 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 0020 × 0903 ÷ # ÷ [0.2] SPACE (Other) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0020 × 0308 × 0903 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0020 ÷ 1100 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 1100 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0020 ÷ 1160 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 1160 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0020 ÷ 11A8 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 11A8 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0020 ÷ AC00 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ AC00 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0020 ÷ AC01 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ AC01 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0020 ÷ 231A ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 231A ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 0020 × 0300 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0020 × 0308 × 0300 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0020 × 200D ÷ # ÷ [0.2] SPACE (Other) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0020 × 0308 × 200D ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0020 ÷ 0378 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0378 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 000D ÷ 0020 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ 0020 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 000D ÷ 000D ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ 000D ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 000D × 000A ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) × [3.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ 000A ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 000D ÷ 0001 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ 0001 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 000D ÷ 034F ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 × 034F ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 000D ÷ 1F1E6 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 000D ÷ 0600 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ 0600 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 000D ÷ 0903 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 × 0903 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 000D ÷ 1100 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ 1100 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 000D ÷ 1160 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ 1160 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 000D ÷ 11A8 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ 11A8 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 000D ÷ AC00 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ AC00 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 000D ÷ AC01 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ AC01 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 000D ÷ 231A ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ 231A ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 000D ÷ 0300 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 × 0300 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 000D ÷ 200D ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 × 200D ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 000D ÷ 0378 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ 0378 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 000A ÷ 0020 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ 0020 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 000A ÷ 000D ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ 000D ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 000A ÷ 000A ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ 000A ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 000A ÷ 0001 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ 0001 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 000A ÷ 034F ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 × 034F ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 000A ÷ 1F1E6 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 000A ÷ 0600 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ 0600 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 000A ÷ 0903 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 × 0903 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 000A ÷ 1100 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ 1100 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 000A ÷ 1160 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ 1160 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 000A ÷ 11A8 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ 11A8 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 000A ÷ AC00 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ AC00 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 000A ÷ AC01 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ AC01 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 000A ÷ 231A ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ 231A ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 000A ÷ 0300 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 × 0300 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 000A ÷ 200D ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 × 200D ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 000A ÷ 0378 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ 0378 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0001 ÷ 0020 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ 0020 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0001 ÷ 000D ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ 000D ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0001 ÷ 000A ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ 000A ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0001 ÷ 0001 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ 0001 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0001 ÷ 034F ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 × 034F ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 0001 ÷ 1F1E6 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 0001 ÷ 0600 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ 0600 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 0001 ÷ 0903 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 × 0903 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0001 ÷ 1100 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ 1100 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0001 ÷ 1160 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ 1160 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0001 ÷ 11A8 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ 11A8 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0001 ÷ AC00 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ AC00 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0001 ÷ AC01 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ AC01 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0001 ÷ 231A ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ 231A ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 0001 ÷ 0300 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 × 0300 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0001 ÷ 200D ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 × 200D ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0001 ÷ 0378 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ 0378 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 034F ÷ 0020 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 034F × 0308 ÷ 0020 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 034F ÷ 000D ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 034F × 0308 ÷ 000D ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 034F ÷ 000A ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 034F × 0308 ÷ 000A ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 034F ÷ 0001 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 034F × 0308 ÷ 0001 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 034F × 034F ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 034F × 0308 × 034F ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 034F ÷ 1F1E6 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 034F × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 034F ÷ 0600 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 034F × 0308 ÷ 0600 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 034F × 0903 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 034F × 0308 × 0903 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 034F ÷ 1100 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 034F × 0308 ÷ 1100 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 034F ÷ 1160 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 034F × 0308 ÷ 1160 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 034F ÷ 11A8 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 034F × 0308 ÷ 11A8 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 034F ÷ AC00 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 034F × 0308 ÷ AC00 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 034F ÷ AC01 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 034F × 0308 ÷ AC01 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 034F ÷ 231A ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 034F × 0308 ÷ 231A ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 034F × 0300 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 034F × 0308 × 0300 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 034F × 200D ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 034F × 0308 × 200D ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 034F ÷ 0378 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 034F × 0308 ÷ 0378 ÷ # ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ 0020 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ 0020 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ 000D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ 000D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ 000A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ 000A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ 0001 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ 0001 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 1F1E6 × 034F ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 × 034F ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 1F1E6 × 1F1E6 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [12.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ 0600 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ 0600 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 1F1E6 × 0903 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 × 0903 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ 1100 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ 1100 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ 1160 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ 1160 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ 11A8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ 11A8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ AC00 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ AC00 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ AC01 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ AC01 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ 231A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ 231A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 1F1E6 × 0300 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 × 0300 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 1F1E6 × 200D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 × 200D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ 0378 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ 0378 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0600 × 0020 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] SPACE (Other) ÷ [0.3]
|
||||
÷ 0600 × 0308 ÷ 0020 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0600 ÷ 000D ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0600 × 0308 ÷ 000D ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0600 ÷ 000A ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0600 × 0308 ÷ 000A ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0600 ÷ 0001 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0600 × 0308 ÷ 0001 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0600 × 034F ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 0600 × 0308 × 034F ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 0600 × 1F1E6 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 0600 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 0600 × 0600 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 0600 × 0308 ÷ 0600 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 0600 × 0903 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0600 × 0308 × 0903 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0600 × 1100 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0600 × 0308 ÷ 1100 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0600 × 1160 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0600 × 0308 ÷ 1160 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0600 × 11A8 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0600 × 0308 ÷ 11A8 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0600 × AC00 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0600 × 0308 ÷ AC00 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0600 × AC01 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0600 × 0308 ÷ AC01 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0600 × 231A ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 0600 × 0308 ÷ 231A ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 0600 × 0300 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0600 × 0308 × 0300 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0600 × 200D ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0600 × 0308 × 200D ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0600 × 0378 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0600 × 0308 ÷ 0378 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0903 ÷ 0020 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ 0020 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0903 ÷ 000D ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ 000D ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0903 ÷ 000A ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ 000A ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0903 ÷ 0001 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ 0001 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0903 × 034F ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 0903 × 0308 × 034F ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 0903 ÷ 1F1E6 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 0903 ÷ 0600 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ 0600 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 0903 × 0903 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0903 × 0308 × 0903 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0903 ÷ 1100 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ 1100 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0903 ÷ 1160 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ 1160 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0903 ÷ 11A8 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ 11A8 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0903 ÷ AC00 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ AC00 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0903 ÷ AC01 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ AC01 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0903 ÷ 231A ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ 231A ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 0903 × 0300 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0903 × 0308 × 0300 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0903 × 200D ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0903 × 0308 × 200D ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0903 ÷ 0378 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ 0378 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 1100 ÷ 0020 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ 0020 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 1100 ÷ 000D ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ 000D ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 1100 ÷ 000A ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ 000A ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 1100 ÷ 0001 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ 0001 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 1100 × 034F ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 1100 × 0308 × 034F ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 1100 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 1100 ÷ 0600 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ 0600 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 1100 × 0903 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 1100 × 0308 × 0903 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 1100 × 1100 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ 1100 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 1100 × 1160 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ 1160 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 1100 ÷ 11A8 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ 11A8 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 1100 × AC00 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 1100 × AC01 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 1100 ÷ 231A ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ 231A ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 1100 × 0300 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 1100 × 0308 × 0300 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 1100 × 200D ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 1100 × 0308 × 200D ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 1100 ÷ 0378 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 1160 ÷ 0020 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ 0020 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 1160 ÷ 000D ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ 000D ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 1160 ÷ 000A ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ 000A ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 1160 ÷ 0001 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ 0001 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 1160 × 034F ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 1160 × 0308 × 034F ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 1160 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 1160 ÷ 0600 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ 0600 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 1160 × 0903 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 1160 × 0308 × 0903 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 1160 ÷ 1100 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ 1100 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 1160 × 1160 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [7.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ 1160 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 1160 × 11A8 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [7.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ 11A8 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 1160 ÷ AC00 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 1160 ÷ AC01 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 1160 ÷ 231A ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ 231A ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 1160 × 0300 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 1160 × 0308 × 0300 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 1160 × 200D ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 1160 × 0308 × 200D ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 1160 ÷ 0378 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 11A8 ÷ 0020 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ 0020 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 11A8 ÷ 000D ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ 000D ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 11A8 ÷ 000A ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ 000A ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 11A8 ÷ 0001 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ 0001 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 11A8 × 034F ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 11A8 × 0308 × 034F ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 11A8 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 11A8 ÷ 0600 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ 0600 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 11A8 × 0903 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 11A8 × 0308 × 0903 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 11A8 ÷ 1100 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ 1100 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 11A8 ÷ 1160 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ 1160 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 11A8 × 11A8 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [8.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ 11A8 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 11A8 ÷ AC00 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 11A8 ÷ AC01 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 11A8 ÷ 231A ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ 231A ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 11A8 × 0300 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 11A8 × 0308 × 0300 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 11A8 × 200D ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 11A8 × 0308 × 200D ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 11A8 ÷ 0378 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ AC00 ÷ 0020 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ 0020 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ AC00 ÷ 000D ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ 000D ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ AC00 ÷ 000A ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ 000A ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ AC00 ÷ 0001 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ 0001 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ AC00 × 034F ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ AC00 × 0308 × 034F ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ AC00 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ AC00 ÷ 0600 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ 0600 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ AC00 × 0903 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ AC00 × 0308 × 0903 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ AC00 ÷ 1100 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ 1100 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ AC00 × 1160 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [7.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ 1160 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ AC00 × 11A8 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [7.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ 11A8 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ AC00 ÷ AC00 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ AC00 ÷ AC01 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ AC00 ÷ 231A ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ 231A ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ AC00 × 0300 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ AC00 × 0308 × 0300 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ AC00 × 200D ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ AC00 × 0308 × 200D ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ AC00 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ AC01 ÷ 0020 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ 0020 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ AC01 ÷ 000D ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ 000D ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ AC01 ÷ 000A ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ 000A ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ AC01 ÷ 0001 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ 0001 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ AC01 × 034F ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ AC01 × 0308 × 034F ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ AC01 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ AC01 ÷ 0600 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ 0600 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ AC01 × 0903 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ AC01 × 0308 × 0903 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ AC01 ÷ 1100 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ 1100 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ AC01 ÷ 1160 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ 1160 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ AC01 × 11A8 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [8.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ 11A8 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ AC01 ÷ AC00 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ AC01 ÷ AC01 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ AC01 ÷ 231A ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ 231A ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ AC01 × 0300 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ AC01 × 0308 × 0300 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ AC01 × 200D ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ AC01 × 0308 × 200D ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ AC01 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 231A ÷ 0020 ÷ # ÷ [0.2] WATCH (ExtPict) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 231A × 0308 ÷ 0020 ÷ # ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 231A ÷ 000D ÷ # ÷ [0.2] WATCH (ExtPict) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 231A × 0308 ÷ 000D ÷ # ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 231A ÷ 000A ÷ # ÷ [0.2] WATCH (ExtPict) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 231A × 0308 ÷ 000A ÷ # ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 231A ÷ 0001 ÷ # ÷ [0.2] WATCH (ExtPict) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 231A × 0308 ÷ 0001 ÷ # ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 231A × 034F ÷ # ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 231A × 0308 × 034F ÷ # ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 231A ÷ 1F1E6 ÷ # ÷ [0.2] WATCH (ExtPict) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 231A × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 231A ÷ 0600 ÷ # ÷ [0.2] WATCH (ExtPict) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 231A × 0308 ÷ 0600 ÷ # ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 231A × 0903 ÷ # ÷ [0.2] WATCH (ExtPict) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 231A × 0308 × 0903 ÷ # ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 231A ÷ 1100 ÷ # ÷ [0.2] WATCH (ExtPict) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 231A × 0308 ÷ 1100 ÷ # ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 231A ÷ 1160 ÷ # ÷ [0.2] WATCH (ExtPict) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 231A × 0308 ÷ 1160 ÷ # ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 231A ÷ 11A8 ÷ # ÷ [0.2] WATCH (ExtPict) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 231A × 0308 ÷ 11A8 ÷ # ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 231A ÷ AC00 ÷ # ÷ [0.2] WATCH (ExtPict) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 231A × 0308 ÷ AC00 ÷ # ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 231A ÷ AC01 ÷ # ÷ [0.2] WATCH (ExtPict) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 231A × 0308 ÷ AC01 ÷ # ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 231A ÷ 231A ÷ # ÷ [0.2] WATCH (ExtPict) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 231A × 0308 ÷ 231A ÷ # ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 231A × 0300 ÷ # ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 231A × 0308 × 0300 ÷ # ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 231A × 200D ÷ # ÷ [0.2] WATCH (ExtPict) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 231A × 0308 × 200D ÷ # ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 231A ÷ 0378 ÷ # ÷ [0.2] WATCH (ExtPict) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 231A × 0308 ÷ 0378 ÷ # ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0300 ÷ 0020 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ 0020 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0300 ÷ 000D ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ 000D ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0300 ÷ 000A ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ 000A ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0300 ÷ 0001 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ 0001 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0300 × 034F ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 0300 × 0308 × 034F ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 0300 ÷ 1F1E6 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 0300 ÷ 0600 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ 0600 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 0300 × 0903 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0300 × 0308 × 0903 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0300 ÷ 1100 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ 1100 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0300 ÷ 1160 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ 1160 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0300 ÷ 11A8 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ 11A8 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0300 ÷ AC00 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ AC00 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0300 ÷ AC01 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ AC01 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0300 ÷ 231A ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ 231A ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 0300 × 0300 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0300 × 0308 × 0300 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0300 × 200D ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0300 × 0308 × 200D ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0300 ÷ 0378 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ 0378 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 200D ÷ 0020 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 200D × 0308 ÷ 0020 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 200D ÷ 000D ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 200D × 0308 ÷ 000D ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 200D ÷ 000A ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 200D × 0308 ÷ 000A ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 200D ÷ 0001 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 200D × 0308 ÷ 0001 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 200D × 034F ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 200D × 0308 × 034F ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 200D ÷ 1F1E6 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 200D × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 200D ÷ 0600 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 200D × 0308 ÷ 0600 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 200D × 0903 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 200D × 0308 × 0903 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 200D ÷ 1100 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 200D × 0308 ÷ 1100 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 200D ÷ 1160 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 200D × 0308 ÷ 1160 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 200D ÷ 11A8 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 200D × 0308 ÷ 11A8 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 200D ÷ AC00 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 200D × 0308 ÷ AC00 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 200D ÷ AC01 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 200D × 0308 ÷ AC01 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 200D ÷ 231A ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 200D × 0308 ÷ 231A ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 200D × 0300 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 200D × 0308 × 0300 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 200D × 200D ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 200D × 0308 × 200D ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 200D ÷ 0378 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 200D × 0308 ÷ 0378 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0378 ÷ 0020 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ 0020 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0378 ÷ 000D ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ 000D ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0378 ÷ 000A ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ 000A ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0378 ÷ 0001 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ 0001 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0378 × 034F ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 0378 × 0308 × 034F ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
|
||||
÷ 0378 ÷ 1F1E6 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 0378 ÷ 0600 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ 0600 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
|
||||
÷ 0378 × 0903 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0378 × 0308 × 0903 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0378 ÷ 1100 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ 1100 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0378 ÷ 1160 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ 1160 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0378 ÷ 11A8 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ 11A8 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0378 ÷ AC00 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ AC00 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0378 ÷ AC01 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ AC01 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0378 ÷ 231A ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ 231A ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 0378 × 0300 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0378 × 0308 × 0300 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0378 × 200D ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0378 × 0308 × 200D ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0378 ÷ 0378 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ 0378 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 000D × 000A ÷ 0061 ÷ 000A ÷ 0308 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) × [3.0] <LINE FEED (LF)> (LF) ÷ [4.0] LATIN SMALL LETTER A (Other) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0061 × 0308 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0020 × 200D ÷ 0646 ÷ # ÷ [0.2] SPACE (Other) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] ARABIC LETTER NOON (Other) ÷ [0.3]
|
||||
÷ 0646 × 200D ÷ 0020 ÷ # ÷ [0.2] ARABIC LETTER NOON (Other) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 1100 × 1100 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ AC00 × 11A8 ÷ 1100 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [7.0] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ AC01 × 11A8 ÷ 1100 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [8.0] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 1F1E6 × 1F1E7 ÷ 1F1E8 ÷ 0062 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [12.0] REGIONAL INDICATOR SYMBOL LETTER B (RI) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER C (RI) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
|
||||
÷ 0061 ÷ 1F1E6 × 1F1E7 ÷ 1F1E8 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [13.0] REGIONAL INDICATOR SYMBOL LETTER B (RI) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER C (RI) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
|
||||
÷ 0061 ÷ 1F1E6 × 1F1E7 × 200D ÷ 1F1E8 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [13.0] REGIONAL INDICATOR SYMBOL LETTER B (RI) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER C (RI) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
|
||||
÷ 0061 ÷ 1F1E6 × 200D ÷ 1F1E7 × 1F1E8 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER B (RI) × [13.0] REGIONAL INDICATOR SYMBOL LETTER C (RI) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
|
||||
÷ 0061 ÷ 1F1E6 × 1F1E7 ÷ 1F1E8 × 1F1E9 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [13.0] REGIONAL INDICATOR SYMBOL LETTER B (RI) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER C (RI) × [13.0] REGIONAL INDICATOR SYMBOL LETTER D (RI) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
|
||||
÷ 0061 × 200D ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
|
||||
÷ 0061 × 0308 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
|
||||
÷ 0061 × 0903 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
|
||||
÷ 0061 ÷ 0600 × 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) × [9.2] LATIN SMALL LETTER B (Other) ÷ [0.3]
|
||||
÷ 1F476 × 1F3FF ÷ 1F476 ÷ # ÷ [0.2] BABY (ExtPict) × [9.0] EMOJI MODIFIER FITZPATRICK TYPE-6 (Extend) ÷ [999.0] BABY (ExtPict) ÷ [0.3]
|
||||
÷ 0061 × 1F3FF ÷ 1F476 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] EMOJI MODIFIER FITZPATRICK TYPE-6 (Extend) ÷ [999.0] BABY (ExtPict) ÷ [0.3]
|
||||
÷ 0061 × 1F3FF ÷ 1F476 × 200D × 1F6D1 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] EMOJI MODIFIER FITZPATRICK TYPE-6 (Extend) ÷ [999.0] BABY (ExtPict) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [11.0] OCTAGONAL SIGN (ExtPict) ÷ [0.3]
|
||||
÷ 1F476 × 1F3FF × 0308 × 200D × 1F476 × 1F3FF ÷ # ÷ [0.2] BABY (ExtPict) × [9.0] EMOJI MODIFIER FITZPATRICK TYPE-6 (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [11.0] BABY (ExtPict) × [9.0] EMOJI MODIFIER FITZPATRICK TYPE-6 (Extend) ÷ [0.3]
|
||||
÷ 1F6D1 × 200D × 1F6D1 ÷ # ÷ [0.2] OCTAGONAL SIGN (ExtPict) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [11.0] OCTAGONAL SIGN (ExtPict) ÷ [0.3]
|
||||
÷ 0061 × 200D ÷ 1F6D1 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] OCTAGONAL SIGN (ExtPict) ÷ [0.3]
|
||||
÷ 2701 × 200D × 2701 ÷ # ÷ [0.2] UPPER BLADE SCISSORS (Other) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [11.0] UPPER BLADE SCISSORS (Other) ÷ [0.3]
|
||||
÷ 0061 × 200D ÷ 2701 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] UPPER BLADE SCISSORS (Other) ÷ [0.3]
|
||||
#
|
||||
# Lines: 602
|
||||
#
|
||||
# EOF
|
769
make/data/unicodedata/emoji-data.txt
Normal file
769
make/data/unicodedata/emoji-data.txt
Normal file
@ -0,0 +1,769 @@
|
||||
# emoji-data.txt
|
||||
# Date: 2019-01-15, 12:10:05 GMT
|
||||
# Copyright (c) 2019 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
|
||||
#
|
||||
# Emoji Data for UTS #51
|
||||
# Version: 12.0
|
||||
#
|
||||
# For documentation and usage, see http://www.unicode.org/reports/tr51
|
||||
#
|
||||
# Format:
|
||||
# <codepoint(s)> ; <property> # <comments>
|
||||
# Note: there is no guarantee as to the structure of whitespace or comments
|
||||
#
|
||||
# Characters and sequences are listed in code point order. Users should be shown a more natural order.
|
||||
# See the CLDR collation order for Emoji.
|
||||
|
||||
|
||||
# ================================================
|
||||
|
||||
# All omitted code points have Emoji=No
|
||||
# @missing: 0000..10FFFF ; Emoji ; No
|
||||
|
||||
0023 ; Emoji # 1.1 [1] (#️) number sign
|
||||
002A ; Emoji # 1.1 [1] (*️) asterisk
|
||||
0030..0039 ; Emoji # 1.1 [10] (0️..9️) digit zero..digit nine
|
||||
00A9 ; Emoji # 1.1 [1] (©️) copyright
|
||||
00AE ; Emoji # 1.1 [1] (®️) registered
|
||||
203C ; Emoji # 1.1 [1] (‼️) double exclamation mark
|
||||
2049 ; Emoji # 3.0 [1] (⁉️) exclamation question mark
|
||||
2122 ; Emoji # 1.1 [1] (™️) trade mark
|
||||
2139 ; Emoji # 3.0 [1] (ℹ️) information
|
||||
2194..2199 ; Emoji # 1.1 [6] (↔️..↙️) left-right arrow..down-left arrow
|
||||
21A9..21AA ; Emoji # 1.1 [2] (↩️..↪️) right arrow curving left..left arrow curving right
|
||||
231A..231B ; Emoji # 1.1 [2] (⌚..⌛) watch..hourglass done
|
||||
2328 ; Emoji # 1.1 [1] (⌨️) keyboard
|
||||
23CF ; Emoji # 4.0 [1] (⏏️) eject button
|
||||
23E9..23F3 ; Emoji # 6.0 [11] (⏩..⏳) fast-forward button..hourglass not done
|
||||
23F8..23FA ; Emoji # 7.0 [3] (⏸️..⏺️) pause button..record button
|
||||
24C2 ; Emoji # 1.1 [1] (Ⓜ️) circled M
|
||||
25AA..25AB ; Emoji # 1.1 [2] (▪️..▫️) black small square..white small square
|
||||
25B6 ; Emoji # 1.1 [1] (▶️) play button
|
||||
25C0 ; Emoji # 1.1 [1] (◀️) reverse button
|
||||
25FB..25FE ; Emoji # 3.2 [4] (◻️..◾) white medium square..black medium-small square
|
||||
2600..2604 ; Emoji # 1.1 [5] (☀️..☄️) sun..comet
|
||||
260E ; Emoji # 1.1 [1] (☎️) telephone
|
||||
2611 ; Emoji # 1.1 [1] (☑️) check box with check
|
||||
2614..2615 ; Emoji # 4.0 [2] (☔..☕) umbrella with rain drops..hot beverage
|
||||
2618 ; Emoji # 4.1 [1] (☘️) shamrock
|
||||
261D ; Emoji # 1.1 [1] (☝️) index pointing up
|
||||
2620 ; Emoji # 1.1 [1] (☠️) skull and crossbones
|
||||
2622..2623 ; Emoji # 1.1 [2] (☢️..☣️) radioactive..biohazard
|
||||
2626 ; Emoji # 1.1 [1] (☦️) orthodox cross
|
||||
262A ; Emoji # 1.1 [1] (☪️) star and crescent
|
||||
262E..262F ; Emoji # 1.1 [2] (☮️..☯️) peace symbol..yin yang
|
||||
2638..263A ; Emoji # 1.1 [3] (☸️..☺️) wheel of dharma..smiling face
|
||||
2640 ; Emoji # 1.1 [1] (♀️) female sign
|
||||
2642 ; Emoji # 1.1 [1] (♂️) male sign
|
||||
2648..2653 ; Emoji # 1.1 [12] (♈..♓) Aries..Pisces
|
||||
265F..2660 ; Emoji # 1.1 [2] (♟️..♠️) chess pawn..spade suit
|
||||
2663 ; Emoji # 1.1 [1] (♣️) club suit
|
||||
2665..2666 ; Emoji # 1.1 [2] (♥️..♦️) heart suit..diamond suit
|
||||
2668 ; Emoji # 1.1 [1] (♨️) hot springs
|
||||
267B ; Emoji # 3.2 [1] (♻️) recycling symbol
|
||||
267E..267F ; Emoji # 4.1 [2] (♾️..♿) infinity..wheelchair symbol
|
||||
2692..2697 ; Emoji # 4.1 [6] (⚒️..⚗️) hammer and pick..alembic
|
||||
2699 ; Emoji # 4.1 [1] (⚙️) gear
|
||||
269B..269C ; Emoji # 4.1 [2] (⚛️..⚜️) atom symbol..fleur-de-lis
|
||||
26A0..26A1 ; Emoji # 4.0 [2] (⚠️..⚡) warning..high voltage
|
||||
26AA..26AB ; Emoji # 4.1 [2] (⚪..⚫) white circle..black circle
|
||||
26B0..26B1 ; Emoji # 4.1 [2] (⚰️..⚱️) coffin..funeral urn
|
||||
26BD..26BE ; Emoji # 5.2 [2] (⚽..⚾) soccer ball..baseball
|
||||
26C4..26C5 ; Emoji # 5.2 [2] (⛄..⛅) snowman without snow..sun behind cloud
|
||||
26C8 ; Emoji # 5.2 [1] (⛈️) cloud with lightning and rain
|
||||
26CE ; Emoji # 6.0 [1] (⛎) Ophiuchus
|
||||
26CF ; Emoji # 5.2 [1] (⛏️) pick
|
||||
26D1 ; Emoji # 5.2 [1] (⛑️) rescue worker’s helmet
|
||||
26D3..26D4 ; Emoji # 5.2 [2] (⛓️..⛔) chains..no entry
|
||||
26E9..26EA ; Emoji # 5.2 [2] (⛩️..⛪) shinto shrine..church
|
||||
26F0..26F5 ; Emoji # 5.2 [6] (⛰️..⛵) mountain..sailboat
|
||||
26F7..26FA ; Emoji # 5.2 [4] (⛷️..⛺) skier..tent
|
||||
26FD ; Emoji # 5.2 [1] (⛽) fuel pump
|
||||
2702 ; Emoji # 1.1 [1] (✂️) scissors
|
||||
2705 ; Emoji # 6.0 [1] (✅) check mark button
|
||||
2708..2709 ; Emoji # 1.1 [2] (✈️..✉️) airplane..envelope
|
||||
270A..270B ; Emoji # 6.0 [2] (✊..✋) raised fist..raised hand
|
||||
270C..270D ; Emoji # 1.1 [2] (✌️..✍️) victory hand..writing hand
|
||||
270F ; Emoji # 1.1 [1] (✏️) pencil
|
||||
2712 ; Emoji # 1.1 [1] (✒️) black nib
|
||||
2714 ; Emoji # 1.1 [1] (✔️) check mark
|
||||
2716 ; Emoji # 1.1 [1] (✖️) multiplication sign
|
||||
271D ; Emoji # 1.1 [1] (✝️) latin cross
|
||||
2721 ; Emoji # 1.1 [1] (✡️) star of David
|
||||
2728 ; Emoji # 6.0 [1] (✨) sparkles
|
||||
2733..2734 ; Emoji # 1.1 [2] (✳️..✴️) eight-spoked asterisk..eight-pointed star
|
||||
2744 ; Emoji # 1.1 [1] (❄️) snowflake
|
||||
2747 ; Emoji # 1.1 [1] (❇️) sparkle
|
||||
274C ; Emoji # 6.0 [1] (❌) cross mark
|
||||
274E ; Emoji # 6.0 [1] (❎) cross mark button
|
||||
2753..2755 ; Emoji # 6.0 [3] (❓..❕) question mark..white exclamation mark
|
||||
2757 ; Emoji # 5.2 [1] (❗) exclamation mark
|
||||
2763..2764 ; Emoji # 1.1 [2] (❣️..❤️) heart exclamation..red heart
|
||||
2795..2797 ; Emoji # 6.0 [3] (➕..➗) plus sign..division sign
|
||||
27A1 ; Emoji # 1.1 [1] (➡️) right arrow
|
||||
27B0 ; Emoji # 6.0 [1] (➰) curly loop
|
||||
27BF ; Emoji # 6.0 [1] (➿) double curly loop
|
||||
2934..2935 ; Emoji # 3.2 [2] (⤴️..⤵️) right arrow curving up..right arrow curving down
|
||||
2B05..2B07 ; Emoji # 4.0 [3] (⬅️..⬇️) left arrow..down arrow
|
||||
2B1B..2B1C ; Emoji # 5.1 [2] (⬛..⬜) black large square..white large square
|
||||
2B50 ; Emoji # 5.1 [1] (⭐) star
|
||||
2B55 ; Emoji # 5.2 [1] (⭕) hollow red circle
|
||||
3030 ; Emoji # 1.1 [1] (〰️) wavy dash
|
||||
303D ; Emoji # 3.2 [1] (〽️) part alternation mark
|
||||
3297 ; Emoji # 1.1 [1] (㊗️) Japanese “congratulations” button
|
||||
3299 ; Emoji # 1.1 [1] (㊙️) Japanese “secret” button
|
||||
1F004 ; Emoji # 5.1 [1] (🀄) mahjong red dragon
|
||||
1F0CF ; Emoji # 6.0 [1] (🃏) joker
|
||||
1F170..1F171 ; Emoji # 6.0 [2] (🅰️..🅱️) A button (blood type)..B button (blood type)
|
||||
1F17E ; Emoji # 6.0 [1] (🅾️) O button (blood type)
|
||||
1F17F ; Emoji # 5.2 [1] (🅿️) P button
|
||||
1F18E ; Emoji # 6.0 [1] (🆎) AB button (blood type)
|
||||
1F191..1F19A ; Emoji # 6.0 [10] (🆑..🆚) CL button..VS button
|
||||
1F1E6..1F1FF ; Emoji # 6.0 [26] (🇦..🇿) regional indicator symbol letter a..regional indicator symbol letter z
|
||||
1F201..1F202 ; Emoji # 6.0 [2] (🈁..🈂️) Japanese “here” button..Japanese “service charge” button
|
||||
1F21A ; Emoji # 5.2 [1] (🈚) Japanese “free of charge” button
|
||||
1F22F ; Emoji # 5.2 [1] (🈯) Japanese “reserved” button
|
||||
1F232..1F23A ; Emoji # 6.0 [9] (🈲..🈺) Japanese “prohibited” button..Japanese “open for business” button
|
||||
1F250..1F251 ; Emoji # 6.0 [2] (🉐..🉑) Japanese “bargain” button..Japanese “acceptable” button
|
||||
1F300..1F320 ; Emoji # 6.0 [33] (🌀..🌠) cyclone..shooting star
|
||||
1F321 ; Emoji # 7.0 [1] (🌡️) thermometer
|
||||
1F324..1F32C ; Emoji # 7.0 [9] (🌤️..🌬️) sun behind small cloud..wind face
|
||||
1F32D..1F32F ; Emoji # 8.0 [3] (🌭..🌯) hot dog..burrito
|
||||
1F330..1F335 ; Emoji # 6.0 [6] (🌰..🌵) chestnut..cactus
|
||||
1F336 ; Emoji # 7.0 [1] (🌶️) hot pepper
|
||||
1F337..1F37C ; Emoji # 6.0 [70] (🌷..🍼) tulip..baby bottle
|
||||
1F37D ; Emoji # 7.0 [1] (🍽️) fork and knife with plate
|
||||
1F37E..1F37F ; Emoji # 8.0 [2] (🍾..🍿) bottle with popping cork..popcorn
|
||||
1F380..1F393 ; Emoji # 6.0 [20] (🎀..🎓) ribbon..graduation cap
|
||||
1F396..1F397 ; Emoji # 7.0 [2] (🎖️..🎗️) military medal..reminder ribbon
|
||||
1F399..1F39B ; Emoji # 7.0 [3] (🎙️..🎛️) studio microphone..control knobs
|
||||
1F39E..1F39F ; Emoji # 7.0 [2] (🎞️..🎟️) film frames..admission tickets
|
||||
1F3A0..1F3C4 ; Emoji # 6.0 [37] (🎠..🏄) carousel horse..person surfing
|
||||
1F3C5 ; Emoji # 7.0 [1] (🏅) sports medal
|
||||
1F3C6..1F3CA ; Emoji # 6.0 [5] (🏆..🏊) trophy..person swimming
|
||||
1F3CB..1F3CE ; Emoji # 7.0 [4] (🏋️..🏎️) person lifting weights..racing car
|
||||
1F3CF..1F3D3 ; Emoji # 8.0 [5] (🏏..🏓) cricket game..ping pong
|
||||
1F3D4..1F3DF ; Emoji # 7.0 [12] (🏔️..🏟️) snow-capped mountain..stadium
|
||||
1F3E0..1F3F0 ; Emoji # 6.0 [17] (🏠..🏰) house..castle
|
||||
1F3F3..1F3F5 ; Emoji # 7.0 [3] (🏳️..🏵️) white flag..rosette
|
||||
1F3F7 ; Emoji # 7.0 [1] (🏷️) label
|
||||
1F3F8..1F3FF ; Emoji # 8.0 [8] (🏸..🏿) badminton..dark skin tone
|
||||
1F400..1F43E ; Emoji # 6.0 [63] (🐀..🐾) rat..paw prints
|
||||
1F43F ; Emoji # 7.0 [1] (🐿️) chipmunk
|
||||
1F440 ; Emoji # 6.0 [1] (👀) eyes
|
||||
1F441 ; Emoji # 7.0 [1] (👁️) eye
|
||||
1F442..1F4F7 ; Emoji # 6.0[182] (👂..📷) ear..camera
|
||||
1F4F8 ; Emoji # 7.0 [1] (📸) camera with flash
|
||||
1F4F9..1F4FC ; Emoji # 6.0 [4] (📹..📼) video camera..videocassette
|
||||
1F4FD ; Emoji # 7.0 [1] (📽️) film projector
|
||||
1F4FF ; Emoji # 8.0 [1] (📿) prayer beads
|
||||
1F500..1F53D ; Emoji # 6.0 [62] (🔀..🔽) shuffle tracks button..downwards button
|
||||
1F549..1F54A ; Emoji # 7.0 [2] (🕉️..🕊️) om..dove
|
||||
1F54B..1F54E ; Emoji # 8.0 [4] (🕋..🕎) kaaba..menorah
|
||||
1F550..1F567 ; Emoji # 6.0 [24] (🕐..🕧) one o’clock..twelve-thirty
|
||||
1F56F..1F570 ; Emoji # 7.0 [2] (🕯️..🕰️) candle..mantelpiece clock
|
||||
1F573..1F579 ; Emoji # 7.0 [7] (🕳️..🕹️) hole..joystick
|
||||
1F57A ; Emoji # 9.0 [1] (🕺) man dancing
|
||||
1F587 ; Emoji # 7.0 [1] (🖇️) linked paperclips
|
||||
1F58A..1F58D ; Emoji # 7.0 [4] (🖊️..🖍️) pen..crayon
|
||||
1F590 ; Emoji # 7.0 [1] (🖐️) hand with fingers splayed
|
||||
1F595..1F596 ; Emoji # 7.0 [2] (🖕..🖖) middle finger..vulcan salute
|
||||
1F5A4 ; Emoji # 9.0 [1] (🖤) black heart
|
||||
1F5A5 ; Emoji # 7.0 [1] (🖥️) desktop computer
|
||||
1F5A8 ; Emoji # 7.0 [1] (🖨️) printer
|
||||
1F5B1..1F5B2 ; Emoji # 7.0 [2] (🖱️..🖲️) computer mouse..trackball
|
||||
1F5BC ; Emoji # 7.0 [1] (🖼️) framed picture
|
||||
1F5C2..1F5C4 ; Emoji # 7.0 [3] (🗂️..🗄️) card index dividers..file cabinet
|
||||
1F5D1..1F5D3 ; Emoji # 7.0 [3] (🗑️..🗓️) wastebasket..spiral calendar
|
||||
1F5DC..1F5DE ; Emoji # 7.0 [3] (🗜️..🗞️) clamp..rolled-up newspaper
|
||||
1F5E1 ; Emoji # 7.0 [1] (🗡️) dagger
|
||||
1F5E3 ; Emoji # 7.0 [1] (🗣️) speaking head
|
||||
1F5E8 ; Emoji # 7.0 [1] (🗨️) left speech bubble
|
||||
1F5EF ; Emoji # 7.0 [1] (🗯️) right anger bubble
|
||||
1F5F3 ; Emoji # 7.0 [1] (🗳️) ballot box with ballot
|
||||
1F5FA ; Emoji # 7.0 [1] (🗺️) world map
|
||||
1F5FB..1F5FF ; Emoji # 6.0 [5] (🗻..🗿) mount fuji..moai
|
||||
1F600 ; Emoji # 6.1 [1] (😀) grinning face
|
||||
1F601..1F610 ; Emoji # 6.0 [16] (😁..😐) beaming face with smiling eyes..neutral face
|
||||
1F611 ; Emoji # 6.1 [1] (😑) expressionless face
|
||||
1F612..1F614 ; Emoji # 6.0 [3] (😒..😔) unamused face..pensive face
|
||||
1F615 ; Emoji # 6.1 [1] (😕) confused face
|
||||
1F616 ; Emoji # 6.0 [1] (😖) confounded face
|
||||
1F617 ; Emoji # 6.1 [1] (😗) kissing face
|
||||
1F618 ; Emoji # 6.0 [1] (😘) face blowing a kiss
|
||||
1F619 ; Emoji # 6.1 [1] (😙) kissing face with smiling eyes
|
||||
1F61A ; Emoji # 6.0 [1] (😚) kissing face with closed eyes
|
||||
1F61B ; Emoji # 6.1 [1] (😛) face with tongue
|
||||
1F61C..1F61E ; Emoji # 6.0 [3] (😜..😞) winking face with tongue..disappointed face
|
||||
1F61F ; Emoji # 6.1 [1] (😟) worried face
|
||||
1F620..1F625 ; Emoji # 6.0 [6] (😠..😥) angry face..sad but relieved face
|
||||
1F626..1F627 ; Emoji # 6.1 [2] (😦..😧) frowning face with open mouth..anguished face
|
||||
1F628..1F62B ; Emoji # 6.0 [4] (😨..😫) fearful face..tired face
|
||||
1F62C ; Emoji # 6.1 [1] (😬) grimacing face
|
||||
1F62D ; Emoji # 6.0 [1] (😭) loudly crying face
|
||||
1F62E..1F62F ; Emoji # 6.1 [2] (😮..😯) face with open mouth..hushed face
|
||||
1F630..1F633 ; Emoji # 6.0 [4] (😰..😳) anxious face with sweat..flushed face
|
||||
1F634 ; Emoji # 6.1 [1] (😴) sleeping face
|
||||
1F635..1F640 ; Emoji # 6.0 [12] (😵..🙀) dizzy face..weary cat
|
||||
1F641..1F642 ; Emoji # 7.0 [2] (🙁..🙂) slightly frowning face..slightly smiling face
|
||||
1F643..1F644 ; Emoji # 8.0 [2] (🙃..🙄) upside-down face..face with rolling eyes
|
||||
1F645..1F64F ; Emoji # 6.0 [11] (🙅..🙏) person gesturing NO..folded hands
|
||||
1F680..1F6C5 ; Emoji # 6.0 [70] (🚀..🛅) rocket..left luggage
|
||||
1F6CB..1F6CF ; Emoji # 7.0 [5] (🛋️..🛏️) couch and lamp..bed
|
||||
1F6D0 ; Emoji # 8.0 [1] (🛐) place of worship
|
||||
1F6D1..1F6D2 ; Emoji # 9.0 [2] (🛑..🛒) stop sign..shopping cart
|
||||
1F6D5 ; Emoji # 12.0 [1] (🛕) hindu temple
|
||||
1F6E0..1F6E5 ; Emoji # 7.0 [6] (🛠️..🛥️) hammer and wrench..motor boat
|
||||
1F6E9 ; Emoji # 7.0 [1] (🛩️) small airplane
|
||||
1F6EB..1F6EC ; Emoji # 7.0 [2] (🛫..🛬) airplane departure..airplane arrival
|
||||
1F6F0 ; Emoji # 7.0 [1] (🛰️) satellite
|
||||
1F6F3 ; Emoji # 7.0 [1] (🛳️) passenger ship
|
||||
1F6F4..1F6F6 ; Emoji # 9.0 [3] (🛴..🛶) kick scooter..canoe
|
||||
1F6F7..1F6F8 ; Emoji # 10.0 [2] (🛷..🛸) sled..flying saucer
|
||||
1F6F9 ; Emoji # 11.0 [1] (🛹) skateboard
|
||||
1F6FA ; Emoji # 12.0 [1] (🛺) auto rickshaw
|
||||
1F7E0..1F7EB ; Emoji # 12.0 [12] (🟠..🟫) orange circle..brown square
|
||||
1F90D..1F90F ; Emoji # 12.0 [3] (🤍..🤏) white heart..pinching hand
|
||||
1F910..1F918 ; Emoji # 8.0 [9] (🤐..🤘) zipper-mouth face..sign of the horns
|
||||
1F919..1F91E ; Emoji # 9.0 [6] (🤙..🤞) call me hand..crossed fingers
|
||||
1F91F ; Emoji # 10.0 [1] (🤟) love-you gesture
|
||||
1F920..1F927 ; Emoji # 9.0 [8] (🤠..🤧) cowboy hat face..sneezing face
|
||||
1F928..1F92F ; Emoji # 10.0 [8] (🤨..🤯) face with raised eyebrow..exploding head
|
||||
1F930 ; Emoji # 9.0 [1] (🤰) pregnant woman
|
||||
1F931..1F932 ; Emoji # 10.0 [2] (🤱..🤲) breast-feeding..palms up together
|
||||
1F933..1F93A ; Emoji # 9.0 [8] (🤳..🤺) selfie..person fencing
|
||||
1F93C..1F93E ; Emoji # 9.0 [3] (🤼..🤾) people wrestling..person playing handball
|
||||
1F93F ; Emoji # 12.0 [1] (🤿) diving mask
|
||||
1F940..1F945 ; Emoji # 9.0 [6] (🥀..🥅) wilted flower..goal net
|
||||
1F947..1F94B ; Emoji # 9.0 [5] (🥇..🥋) 1st place medal..martial arts uniform
|
||||
1F94C ; Emoji # 10.0 [1] (🥌) curling stone
|
||||
1F94D..1F94F ; Emoji # 11.0 [3] (🥍..🥏) lacrosse..flying disc
|
||||
1F950..1F95E ; Emoji # 9.0 [15] (🥐..🥞) croissant..pancakes
|
||||
1F95F..1F96B ; Emoji # 10.0 [13] (🥟..🥫) dumpling..canned food
|
||||
1F96C..1F970 ; Emoji # 11.0 [5] (🥬..🥰) leafy green..smiling face with hearts
|
||||
1F971 ; Emoji # 12.0 [1] (🥱) yawning face
|
||||
1F973..1F976 ; Emoji # 11.0 [4] (🥳..🥶) partying face..cold face
|
||||
1F97A ; Emoji # 11.0 [1] (🥺) pleading face
|
||||
1F97B ; Emoji # 12.0 [1] (🥻) sari
|
||||
1F97C..1F97F ; Emoji # 11.0 [4] (🥼..🥿) lab coat..flat shoe
|
||||
1F980..1F984 ; Emoji # 8.0 [5] (🦀..🦄) crab..unicorn
|
||||
1F985..1F991 ; Emoji # 9.0 [13] (🦅..🦑) eagle..squid
|
||||
1F992..1F997 ; Emoji # 10.0 [6] (🦒..🦗) giraffe..cricket
|
||||
1F998..1F9A2 ; Emoji # 11.0 [11] (🦘..🦢) kangaroo..swan
|
||||
1F9A5..1F9AA ; Emoji # 12.0 [6] (🦥..🦪) sloth..oyster
|
||||
1F9AE..1F9AF ; Emoji # 12.0 [2] (🦮..🦯) guide dog..probing cane
|
||||
1F9B0..1F9B9 ; Emoji # 11.0 [10] (🦰..🦹) red hair..supervillain
|
||||
1F9BA..1F9BF ; Emoji # 12.0 [6] (🦺..🦿) safety vest..mechanical leg
|
||||
1F9C0 ; Emoji # 8.0 [1] (🧀) cheese wedge
|
||||
1F9C1..1F9C2 ; Emoji # 11.0 [2] (🧁..🧂) cupcake..salt
|
||||
1F9C3..1F9CA ; Emoji # 12.0 [8] (🧃..🧊) beverage box..ice cube
|
||||
1F9CD..1F9CF ; Emoji # 12.0 [3] (🧍..🧏) person standing..deaf person
|
||||
1F9D0..1F9E6 ; Emoji # 10.0 [23] (🧐..🧦) face with monocle..socks
|
||||
1F9E7..1F9FF ; Emoji # 11.0 [25] (🧧..🧿) red envelope..nazar amulet
|
||||
1FA70..1FA73 ; Emoji # 12.0 [4] (🩰..🩳) ballet shoes..shorts
|
||||
1FA78..1FA7A ; Emoji # 12.0 [3] (🩸..🩺) drop of blood..stethoscope
|
||||
1FA80..1FA82 ; Emoji # 12.0 [3] (🪀..🪂) yo-yo..parachute
|
||||
1FA90..1FA95 ; Emoji # 12.0 [6] (🪐..🪕) ringed planet..banjo
|
||||
|
||||
# Total elements: 1311
|
||||
|
||||
# ================================================
|
||||
|
||||
# All omitted code points have Emoji_Presentation=No
|
||||
# @missing: 0000..10FFFF ; Emoji_Presentation ; No
|
||||
|
||||
231A..231B ; Emoji_Presentation # 1.1 [2] (⌚..⌛) watch..hourglass done
|
||||
23E9..23EC ; Emoji_Presentation # 6.0 [4] (⏩..⏬) fast-forward button..fast down button
|
||||
23F0 ; Emoji_Presentation # 6.0 [1] (⏰) alarm clock
|
||||
23F3 ; Emoji_Presentation # 6.0 [1] (⏳) hourglass not done
|
||||
25FD..25FE ; Emoji_Presentation # 3.2 [2] (◽..◾) white medium-small square..black medium-small square
|
||||
2614..2615 ; Emoji_Presentation # 4.0 [2] (☔..☕) umbrella with rain drops..hot beverage
|
||||
2648..2653 ; Emoji_Presentation # 1.1 [12] (♈..♓) Aries..Pisces
|
||||
267F ; Emoji_Presentation # 4.1 [1] (♿) wheelchair symbol
|
||||
2693 ; Emoji_Presentation # 4.1 [1] (⚓) anchor
|
||||
26A1 ; Emoji_Presentation # 4.0 [1] (⚡) high voltage
|
||||
26AA..26AB ; Emoji_Presentation # 4.1 [2] (⚪..⚫) white circle..black circle
|
||||
26BD..26BE ; Emoji_Presentation # 5.2 [2] (⚽..⚾) soccer ball..baseball
|
||||
26C4..26C5 ; Emoji_Presentation # 5.2 [2] (⛄..⛅) snowman without snow..sun behind cloud
|
||||
26CE ; Emoji_Presentation # 6.0 [1] (⛎) Ophiuchus
|
||||
26D4 ; Emoji_Presentation # 5.2 [1] (⛔) no entry
|
||||
26EA ; Emoji_Presentation # 5.2 [1] (⛪) church
|
||||
26F2..26F3 ; Emoji_Presentation # 5.2 [2] (⛲..⛳) fountain..flag in hole
|
||||
26F5 ; Emoji_Presentation # 5.2 [1] (⛵) sailboat
|
||||
26FA ; Emoji_Presentation # 5.2 [1] (⛺) tent
|
||||
26FD ; Emoji_Presentation # 5.2 [1] (⛽) fuel pump
|
||||
2705 ; Emoji_Presentation # 6.0 [1] (✅) check mark button
|
||||
270A..270B ; Emoji_Presentation # 6.0 [2] (✊..✋) raised fist..raised hand
|
||||
2728 ; Emoji_Presentation # 6.0 [1] (✨) sparkles
|
||||
274C ; Emoji_Presentation # 6.0 [1] (❌) cross mark
|
||||
274E ; Emoji_Presentation # 6.0 [1] (❎) cross mark button
|
||||
2753..2755 ; Emoji_Presentation # 6.0 [3] (❓..❕) question mark..white exclamation mark
|
||||
2757 ; Emoji_Presentation # 5.2 [1] (❗) exclamation mark
|
||||
2795..2797 ; Emoji_Presentation # 6.0 [3] (➕..➗) plus sign..division sign
|
||||
27B0 ; Emoji_Presentation # 6.0 [1] (➰) curly loop
|
||||
27BF ; Emoji_Presentation # 6.0 [1] (➿) double curly loop
|
||||
2B1B..2B1C ; Emoji_Presentation # 5.1 [2] (⬛..⬜) black large square..white large square
|
||||
2B50 ; Emoji_Presentation # 5.1 [1] (⭐) star
|
||||
2B55 ; Emoji_Presentation # 5.2 [1] (⭕) hollow red circle
|
||||
1F004 ; Emoji_Presentation # 5.1 [1] (🀄) mahjong red dragon
|
||||
1F0CF ; Emoji_Presentation # 6.0 [1] (🃏) joker
|
||||
1F18E ; Emoji_Presentation # 6.0 [1] (🆎) AB button (blood type)
|
||||
1F191..1F19A ; Emoji_Presentation # 6.0 [10] (🆑..🆚) CL button..VS button
|
||||
1F1E6..1F1FF ; Emoji_Presentation # 6.0 [26] (🇦..🇿) regional indicator symbol letter a..regional indicator symbol letter z
|
||||
1F201 ; Emoji_Presentation # 6.0 [1] (🈁) Japanese “here” button
|
||||
1F21A ; Emoji_Presentation # 5.2 [1] (🈚) Japanese “free of charge” button
|
||||
1F22F ; Emoji_Presentation # 5.2 [1] (🈯) Japanese “reserved” button
|
||||
1F232..1F236 ; Emoji_Presentation # 6.0 [5] (🈲..🈶) Japanese “prohibited” button..Japanese “not free of charge” button
|
||||
1F238..1F23A ; Emoji_Presentation # 6.0 [3] (🈸..🈺) Japanese “application” button..Japanese “open for business” button
|
||||
1F250..1F251 ; Emoji_Presentation # 6.0 [2] (🉐..🉑) Japanese “bargain” button..Japanese “acceptable” button
|
||||
1F300..1F320 ; Emoji_Presentation # 6.0 [33] (🌀..🌠) cyclone..shooting star
|
||||
1F32D..1F32F ; Emoji_Presentation # 8.0 [3] (🌭..🌯) hot dog..burrito
|
||||
1F330..1F335 ; Emoji_Presentation # 6.0 [6] (🌰..🌵) chestnut..cactus
|
||||
1F337..1F37C ; Emoji_Presentation # 6.0 [70] (🌷..🍼) tulip..baby bottle
|
||||
1F37E..1F37F ; Emoji_Presentation # 8.0 [2] (🍾..🍿) bottle with popping cork..popcorn
|
||||
1F380..1F393 ; Emoji_Presentation # 6.0 [20] (🎀..🎓) ribbon..graduation cap
|
||||
1F3A0..1F3C4 ; Emoji_Presentation # 6.0 [37] (🎠..🏄) carousel horse..person surfing
|
||||
1F3C5 ; Emoji_Presentation # 7.0 [1] (🏅) sports medal
|
||||
1F3C6..1F3CA ; Emoji_Presentation # 6.0 [5] (🏆..🏊) trophy..person swimming
|
||||
1F3CF..1F3D3 ; Emoji_Presentation # 8.0 [5] (🏏..🏓) cricket game..ping pong
|
||||
1F3E0..1F3F0 ; Emoji_Presentation # 6.0 [17] (🏠..🏰) house..castle
|
||||
1F3F4 ; Emoji_Presentation # 7.0 [1] (🏴) black flag
|
||||
1F3F8..1F3FF ; Emoji_Presentation # 8.0 [8] (🏸..🏿) badminton..dark skin tone
|
||||
1F400..1F43E ; Emoji_Presentation # 6.0 [63] (🐀..🐾) rat..paw prints
|
||||
1F440 ; Emoji_Presentation # 6.0 [1] (👀) eyes
|
||||
1F442..1F4F7 ; Emoji_Presentation # 6.0[182] (👂..📷) ear..camera
|
||||
1F4F8 ; Emoji_Presentation # 7.0 [1] (📸) camera with flash
|
||||
1F4F9..1F4FC ; Emoji_Presentation # 6.0 [4] (📹..📼) video camera..videocassette
|
||||
1F4FF ; Emoji_Presentation # 8.0 [1] (📿) prayer beads
|
||||
1F500..1F53D ; Emoji_Presentation # 6.0 [62] (🔀..🔽) shuffle tracks button..downwards button
|
||||
1F54B..1F54E ; Emoji_Presentation # 8.0 [4] (🕋..🕎) kaaba..menorah
|
||||
1F550..1F567 ; Emoji_Presentation # 6.0 [24] (🕐..🕧) one o’clock..twelve-thirty
|
||||
1F57A ; Emoji_Presentation # 9.0 [1] (🕺) man dancing
|
||||
1F595..1F596 ; Emoji_Presentation # 7.0 [2] (🖕..🖖) middle finger..vulcan salute
|
||||
1F5A4 ; Emoji_Presentation # 9.0 [1] (🖤) black heart
|
||||
1F5FB..1F5FF ; Emoji_Presentation # 6.0 [5] (🗻..🗿) mount fuji..moai
|
||||
1F600 ; Emoji_Presentation # 6.1 [1] (😀) grinning face
|
||||
1F601..1F610 ; Emoji_Presentation # 6.0 [16] (😁..😐) beaming face with smiling eyes..neutral face
|
||||
1F611 ; Emoji_Presentation # 6.1 [1] (😑) expressionless face
|
||||
1F612..1F614 ; Emoji_Presentation # 6.0 [3] (😒..😔) unamused face..pensive face
|
||||
1F615 ; Emoji_Presentation # 6.1 [1] (😕) confused face
|
||||
1F616 ; Emoji_Presentation # 6.0 [1] (😖) confounded face
|
||||
1F617 ; Emoji_Presentation # 6.1 [1] (😗) kissing face
|
||||
1F618 ; Emoji_Presentation # 6.0 [1] (😘) face blowing a kiss
|
||||
1F619 ; Emoji_Presentation # 6.1 [1] (😙) kissing face with smiling eyes
|
||||
1F61A ; Emoji_Presentation # 6.0 [1] (😚) kissing face with closed eyes
|
||||
1F61B ; Emoji_Presentation # 6.1 [1] (😛) face with tongue
|
||||
1F61C..1F61E ; Emoji_Presentation # 6.0 [3] (😜..😞) winking face with tongue..disappointed face
|
||||
1F61F ; Emoji_Presentation # 6.1 [1] (😟) worried face
|
||||
1F620..1F625 ; Emoji_Presentation # 6.0 [6] (😠..😥) angry face..sad but relieved face
|
||||
1F626..1F627 ; Emoji_Presentation # 6.1 [2] (😦..😧) frowning face with open mouth..anguished face
|
||||
1F628..1F62B ; Emoji_Presentation # 6.0 [4] (😨..😫) fearful face..tired face
|
||||
1F62C ; Emoji_Presentation # 6.1 [1] (😬) grimacing face
|
||||
1F62D ; Emoji_Presentation # 6.0 [1] (😭) loudly crying face
|
||||
1F62E..1F62F ; Emoji_Presentation # 6.1 [2] (😮..😯) face with open mouth..hushed face
|
||||
1F630..1F633 ; Emoji_Presentation # 6.0 [4] (😰..😳) anxious face with sweat..flushed face
|
||||
1F634 ; Emoji_Presentation # 6.1 [1] (😴) sleeping face
|
||||
1F635..1F640 ; Emoji_Presentation # 6.0 [12] (😵..🙀) dizzy face..weary cat
|
||||
1F641..1F642 ; Emoji_Presentation # 7.0 [2] (🙁..🙂) slightly frowning face..slightly smiling face
|
||||
1F643..1F644 ; Emoji_Presentation # 8.0 [2] (🙃..🙄) upside-down face..face with rolling eyes
|
||||
1F645..1F64F ; Emoji_Presentation # 6.0 [11] (🙅..🙏) person gesturing NO..folded hands
|
||||
1F680..1F6C5 ; Emoji_Presentation # 6.0 [70] (🚀..🛅) rocket..left luggage
|
||||
1F6CC ; Emoji_Presentation # 7.0 [1] (🛌) person in bed
|
||||
1F6D0 ; Emoji_Presentation # 8.0 [1] (🛐) place of worship
|
||||
1F6D1..1F6D2 ; Emoji_Presentation # 9.0 [2] (🛑..🛒) stop sign..shopping cart
|
||||
1F6D5 ; Emoji_Presentation # 12.0 [1] (🛕) hindu temple
|
||||
1F6EB..1F6EC ; Emoji_Presentation # 7.0 [2] (🛫..🛬) airplane departure..airplane arrival
|
||||
1F6F4..1F6F6 ; Emoji_Presentation # 9.0 [3] (🛴..🛶) kick scooter..canoe
|
||||
1F6F7..1F6F8 ; Emoji_Presentation # 10.0 [2] (🛷..🛸) sled..flying saucer
|
||||
1F6F9 ; Emoji_Presentation # 11.0 [1] (🛹) skateboard
|
||||
1F6FA ; Emoji_Presentation # 12.0 [1] (🛺) auto rickshaw
|
||||
1F7E0..1F7EB ; Emoji_Presentation # 12.0 [12] (🟠..🟫) orange circle..brown square
|
||||
1F90D..1F90F ; Emoji_Presentation # 12.0 [3] (🤍..🤏) white heart..pinching hand
|
||||
1F910..1F918 ; Emoji_Presentation # 8.0 [9] (🤐..🤘) zipper-mouth face..sign of the horns
|
||||
1F919..1F91E ; Emoji_Presentation # 9.0 [6] (🤙..🤞) call me hand..crossed fingers
|
||||
1F91F ; Emoji_Presentation # 10.0 [1] (🤟) love-you gesture
|
||||
1F920..1F927 ; Emoji_Presentation # 9.0 [8] (🤠..🤧) cowboy hat face..sneezing face
|
||||
1F928..1F92F ; Emoji_Presentation # 10.0 [8] (🤨..🤯) face with raised eyebrow..exploding head
|
||||
1F930 ; Emoji_Presentation # 9.0 [1] (🤰) pregnant woman
|
||||
1F931..1F932 ; Emoji_Presentation # 10.0 [2] (🤱..🤲) breast-feeding..palms up together
|
||||
1F933..1F93A ; Emoji_Presentation # 9.0 [8] (🤳..🤺) selfie..person fencing
|
||||
1F93C..1F93E ; Emoji_Presentation # 9.0 [3] (🤼..🤾) people wrestling..person playing handball
|
||||
1F93F ; Emoji_Presentation # 12.0 [1] (🤿) diving mask
|
||||
1F940..1F945 ; Emoji_Presentation # 9.0 [6] (🥀..🥅) wilted flower..goal net
|
||||
1F947..1F94B ; Emoji_Presentation # 9.0 [5] (🥇..🥋) 1st place medal..martial arts uniform
|
||||
1F94C ; Emoji_Presentation # 10.0 [1] (🥌) curling stone
|
||||
1F94D..1F94F ; Emoji_Presentation # 11.0 [3] (🥍..🥏) lacrosse..flying disc
|
||||
1F950..1F95E ; Emoji_Presentation # 9.0 [15] (🥐..🥞) croissant..pancakes
|
||||
1F95F..1F96B ; Emoji_Presentation # 10.0 [13] (🥟..🥫) dumpling..canned food
|
||||
1F96C..1F970 ; Emoji_Presentation # 11.0 [5] (🥬..🥰) leafy green..smiling face with hearts
|
||||
1F971 ; Emoji_Presentation # 12.0 [1] (🥱) yawning face
|
||||
1F973..1F976 ; Emoji_Presentation # 11.0 [4] (🥳..🥶) partying face..cold face
|
||||
1F97A ; Emoji_Presentation # 11.0 [1] (🥺) pleading face
|
||||
1F97B ; Emoji_Presentation # 12.0 [1] (🥻) sari
|
||||
1F97C..1F97F ; Emoji_Presentation # 11.0 [4] (🥼..🥿) lab coat..flat shoe
|
||||
1F980..1F984 ; Emoji_Presentation # 8.0 [5] (🦀..🦄) crab..unicorn
|
||||
1F985..1F991 ; Emoji_Presentation # 9.0 [13] (🦅..🦑) eagle..squid
|
||||
1F992..1F997 ; Emoji_Presentation # 10.0 [6] (🦒..🦗) giraffe..cricket
|
||||
1F998..1F9A2 ; Emoji_Presentation # 11.0 [11] (🦘..🦢) kangaroo..swan
|
||||
1F9A5..1F9AA ; Emoji_Presentation # 12.0 [6] (🦥..🦪) sloth..oyster
|
||||
1F9AE..1F9AF ; Emoji_Presentation # 12.0 [2] (🦮..🦯) guide dog..probing cane
|
||||
1F9B0..1F9B9 ; Emoji_Presentation # 11.0 [10] (🦰..🦹) red hair..supervillain
|
||||
1F9BA..1F9BF ; Emoji_Presentation # 12.0 [6] (🦺..🦿) safety vest..mechanical leg
|
||||
1F9C0 ; Emoji_Presentation # 8.0 [1] (🧀) cheese wedge
|
||||
1F9C1..1F9C2 ; Emoji_Presentation # 11.0 [2] (🧁..🧂) cupcake..salt
|
||||
1F9C3..1F9CA ; Emoji_Presentation # 12.0 [8] (🧃..🧊) beverage box..ice cube
|
||||
1F9CD..1F9CF ; Emoji_Presentation # 12.0 [3] (🧍..🧏) person standing..deaf person
|
||||
1F9D0..1F9E6 ; Emoji_Presentation # 10.0 [23] (🧐..🧦) face with monocle..socks
|
||||
1F9E7..1F9FF ; Emoji_Presentation # 11.0 [25] (🧧..🧿) red envelope..nazar amulet
|
||||
1FA70..1FA73 ; Emoji_Presentation # 12.0 [4] (🩰..🩳) ballet shoes..shorts
|
||||
1FA78..1FA7A ; Emoji_Presentation # 12.0 [3] (🩸..🩺) drop of blood..stethoscope
|
||||
1FA80..1FA82 ; Emoji_Presentation # 12.0 [3] (🪀..🪂) yo-yo..parachute
|
||||
1FA90..1FA95 ; Emoji_Presentation # 12.0 [6] (🪐..🪕) ringed planet..banjo
|
||||
|
||||
# Total elements: 1093
|
||||
|
||||
# ================================================
|
||||
|
||||
# All omitted code points have Emoji_Modifier=No
|
||||
# @missing: 0000..10FFFF ; Emoji_Modifier ; No
|
||||
|
||||
1F3FB..1F3FF ; Emoji_Modifier # 8.0 [5] (🏻..🏿) light skin tone..dark skin tone
|
||||
|
||||
# Total elements: 5
|
||||
|
||||
# ================================================
|
||||
|
||||
# All omitted code points have Emoji_Modifier_Base=No
|
||||
# @missing: 0000..10FFFF ; Emoji_Modifier_Base ; No
|
||||
|
||||
261D ; Emoji_Modifier_Base # 1.1 [1] (☝️) index pointing up
|
||||
26F9 ; Emoji_Modifier_Base # 5.2 [1] (⛹️) person bouncing ball
|
||||
270A..270B ; Emoji_Modifier_Base # 6.0 [2] (✊..✋) raised fist..raised hand
|
||||
270C..270D ; Emoji_Modifier_Base # 1.1 [2] (✌️..✍️) victory hand..writing hand
|
||||
1F385 ; Emoji_Modifier_Base # 6.0 [1] (🎅) Santa Claus
|
||||
1F3C2..1F3C4 ; Emoji_Modifier_Base # 6.0 [3] (🏂..🏄) snowboarder..person surfing
|
||||
1F3C7 ; Emoji_Modifier_Base # 6.0 [1] (🏇) horse racing
|
||||
1F3CA ; Emoji_Modifier_Base # 6.0 [1] (🏊) person swimming
|
||||
1F3CB..1F3CC ; Emoji_Modifier_Base # 7.0 [2] (🏋️..🏌️) person lifting weights..person golfing
|
||||
1F442..1F443 ; Emoji_Modifier_Base # 6.0 [2] (👂..👃) ear..nose
|
||||
1F446..1F450 ; Emoji_Modifier_Base # 6.0 [11] (👆..👐) backhand index pointing up..open hands
|
||||
1F466..1F478 ; Emoji_Modifier_Base # 6.0 [19] (👦..👸) boy..princess
|
||||
1F47C ; Emoji_Modifier_Base # 6.0 [1] (👼) baby angel
|
||||
1F481..1F483 ; Emoji_Modifier_Base # 6.0 [3] (💁..💃) person tipping hand..woman dancing
|
||||
1F485..1F487 ; Emoji_Modifier_Base # 6.0 [3] (💅..💇) nail polish..person getting haircut
|
||||
1F48F ; Emoji_Modifier_Base # 6.0 [1] (💏) kiss
|
||||
1F491 ; Emoji_Modifier_Base # 6.0 [1] (💑) couple with heart
|
||||
1F4AA ; Emoji_Modifier_Base # 6.0 [1] (💪) flexed biceps
|
||||
1F574..1F575 ; Emoji_Modifier_Base # 7.0 [2] (🕴️..🕵️) man in suit levitating..detective
|
||||
1F57A ; Emoji_Modifier_Base # 9.0 [1] (🕺) man dancing
|
||||
1F590 ; Emoji_Modifier_Base # 7.0 [1] (🖐️) hand with fingers splayed
|
||||
1F595..1F596 ; Emoji_Modifier_Base # 7.0 [2] (🖕..🖖) middle finger..vulcan salute
|
||||
1F645..1F647 ; Emoji_Modifier_Base # 6.0 [3] (🙅..🙇) person gesturing NO..person bowing
|
||||
1F64B..1F64F ; Emoji_Modifier_Base # 6.0 [5] (🙋..🙏) person raising hand..folded hands
|
||||
1F6A3 ; Emoji_Modifier_Base # 6.0 [1] (🚣) person rowing boat
|
||||
1F6B4..1F6B6 ; Emoji_Modifier_Base # 6.0 [3] (🚴..🚶) person biking..person walking
|
||||
1F6C0 ; Emoji_Modifier_Base # 6.0 [1] (🛀) person taking bath
|
||||
1F6CC ; Emoji_Modifier_Base # 7.0 [1] (🛌) person in bed
|
||||
1F90F ; Emoji_Modifier_Base # 12.0 [1] (🤏) pinching hand
|
||||
1F918 ; Emoji_Modifier_Base # 8.0 [1] (🤘) sign of the horns
|
||||
1F919..1F91E ; Emoji_Modifier_Base # 9.0 [6] (🤙..🤞) call me hand..crossed fingers
|
||||
1F91F ; Emoji_Modifier_Base # 10.0 [1] (🤟) love-you gesture
|
||||
1F926 ; Emoji_Modifier_Base # 9.0 [1] (🤦) person facepalming
|
||||
1F930 ; Emoji_Modifier_Base # 9.0 [1] (🤰) pregnant woman
|
||||
1F931..1F932 ; Emoji_Modifier_Base # 10.0 [2] (🤱..🤲) breast-feeding..palms up together
|
||||
1F933..1F939 ; Emoji_Modifier_Base # 9.0 [7] (🤳..🤹) selfie..person juggling
|
||||
1F93C..1F93E ; Emoji_Modifier_Base # 9.0 [3] (🤼..🤾) people wrestling..person playing handball
|
||||
1F9B5..1F9B6 ; Emoji_Modifier_Base # 11.0 [2] (🦵..🦶) leg..foot
|
||||
1F9B8..1F9B9 ; Emoji_Modifier_Base # 11.0 [2] (🦸..🦹) superhero..supervillain
|
||||
1F9BB ; Emoji_Modifier_Base # 12.0 [1] (🦻) ear with hearing aid
|
||||
1F9CD..1F9CF ; Emoji_Modifier_Base # 12.0 [3] (🧍..🧏) person standing..deaf person
|
||||
1F9D1..1F9DD ; Emoji_Modifier_Base # 10.0 [13] (🧑..🧝) person..elf
|
||||
|
||||
# Total elements: 120
|
||||
|
||||
# ================================================
|
||||
|
||||
# All omitted code points have Emoji_Component=No
|
||||
# @missing: 0000..10FFFF ; Emoji_Component ; No
|
||||
|
||||
0023 ; Emoji_Component # 1.1 [1] (#️) number sign
|
||||
002A ; Emoji_Component # 1.1 [1] (*️) asterisk
|
||||
0030..0039 ; Emoji_Component # 1.1 [10] (0️..9️) digit zero..digit nine
|
||||
200D ; Emoji_Component # 1.1 [1] () zero width joiner
|
||||
20E3 ; Emoji_Component # 3.0 [1] (⃣) combining enclosing keycap
|
||||
FE0F ; Emoji_Component # 3.2 [1] () VARIATION SELECTOR-16
|
||||
1F1E6..1F1FF ; Emoji_Component # 6.0 [26] (🇦..🇿) regional indicator symbol letter a..regional indicator symbol letter z
|
||||
1F3FB..1F3FF ; Emoji_Component # 8.0 [5] (🏻..🏿) light skin tone..dark skin tone
|
||||
1F9B0..1F9B3 ; Emoji_Component # 11.0 [4] (🦰..🦳) red hair..white hair
|
||||
E0020..E007F ; Emoji_Component # 3.1 [96] (..) tag space..cancel tag
|
||||
|
||||
# Total elements: 146
|
||||
|
||||
# ================================================
|
||||
|
||||
# All omitted code points have Extended_Pictographic=No
|
||||
# @missing: 0000..10FFFF ; Extended_Pictographic ; No
|
||||
|
||||
00A9 ; Extended_Pictographic# 1.1 [1] (©️) copyright
|
||||
00AE ; Extended_Pictographic# 1.1 [1] (®️) registered
|
||||
203C ; Extended_Pictographic# 1.1 [1] (‼️) double exclamation mark
|
||||
2049 ; Extended_Pictographic# 3.0 [1] (⁉️) exclamation question mark
|
||||
2122 ; Extended_Pictographic# 1.1 [1] (™️) trade mark
|
||||
2139 ; Extended_Pictographic# 3.0 [1] (ℹ️) information
|
||||
2194..2199 ; Extended_Pictographic# 1.1 [6] (↔️..↙️) left-right arrow..down-left arrow
|
||||
21A9..21AA ; Extended_Pictographic# 1.1 [2] (↩️..↪️) right arrow curving left..left arrow curving right
|
||||
231A..231B ; Extended_Pictographic# 1.1 [2] (⌚..⌛) watch..hourglass done
|
||||
2328 ; Extended_Pictographic# 1.1 [1] (⌨️) keyboard
|
||||
2388 ; Extended_Pictographic# 3.0 [1] (⎈) HELM SYMBOL
|
||||
23CF ; Extended_Pictographic# 4.0 [1] (⏏️) eject button
|
||||
23E9..23F3 ; Extended_Pictographic# 6.0 [11] (⏩..⏳) fast-forward button..hourglass not done
|
||||
23F8..23FA ; Extended_Pictographic# 7.0 [3] (⏸️..⏺️) pause button..record button
|
||||
24C2 ; Extended_Pictographic# 1.1 [1] (Ⓜ️) circled M
|
||||
25AA..25AB ; Extended_Pictographic# 1.1 [2] (▪️..▫️) black small square..white small square
|
||||
25B6 ; Extended_Pictographic# 1.1 [1] (▶️) play button
|
||||
25C0 ; Extended_Pictographic# 1.1 [1] (◀️) reverse button
|
||||
25FB..25FE ; Extended_Pictographic# 3.2 [4] (◻️..◾) white medium square..black medium-small square
|
||||
2600..2605 ; Extended_Pictographic# 1.1 [6] (☀️..★) sun..BLACK STAR
|
||||
2607..2612 ; Extended_Pictographic# 1.1 [12] (☇..☒) LIGHTNING..BALLOT BOX WITH X
|
||||
2614..2615 ; Extended_Pictographic# 4.0 [2] (☔..☕) umbrella with rain drops..hot beverage
|
||||
2616..2617 ; Extended_Pictographic# 3.2 [2] (☖..☗) WHITE SHOGI PIECE..BLACK SHOGI PIECE
|
||||
2618 ; Extended_Pictographic# 4.1 [1] (☘️) shamrock
|
||||
2619 ; Extended_Pictographic# 3.0 [1] (☙) REVERSED ROTATED FLORAL HEART BULLET
|
||||
261A..266F ; Extended_Pictographic# 1.1 [86] (☚..♯) BLACK LEFT POINTING INDEX..MUSIC SHARP SIGN
|
||||
2670..2671 ; Extended_Pictographic# 3.0 [2] (♰..♱) WEST SYRIAC CROSS..EAST SYRIAC CROSS
|
||||
2672..267D ; Extended_Pictographic# 3.2 [12] (♲..♽) UNIVERSAL RECYCLING SYMBOL..PARTIALLY-RECYCLED PAPER SYMBOL
|
||||
267E..267F ; Extended_Pictographic# 4.1 [2] (♾️..♿) infinity..wheelchair symbol
|
||||
2680..2685 ; Extended_Pictographic# 3.2 [6] (⚀..⚅) DIE FACE-1..DIE FACE-6
|
||||
2690..2691 ; Extended_Pictographic# 4.0 [2] (⚐..⚑) WHITE FLAG..BLACK FLAG
|
||||
2692..269C ; Extended_Pictographic# 4.1 [11] (⚒️..⚜️) hammer and pick..fleur-de-lis
|
||||
269D ; Extended_Pictographic# 5.1 [1] (⚝) OUTLINED WHITE STAR
|
||||
269E..269F ; Extended_Pictographic# 5.2 [2] (⚞..⚟) THREE LINES CONVERGING RIGHT..THREE LINES CONVERGING LEFT
|
||||
26A0..26A1 ; Extended_Pictographic# 4.0 [2] (⚠️..⚡) warning..high voltage
|
||||
26A2..26B1 ; Extended_Pictographic# 4.1 [16] (⚢..⚱️) DOUBLED FEMALE SIGN..funeral urn
|
||||
26B2 ; Extended_Pictographic# 5.0 [1] (⚲) NEUTER
|
||||
26B3..26BC ; Extended_Pictographic# 5.1 [10] (⚳..⚼) CERES..SESQUIQUADRATE
|
||||
26BD..26BF ; Extended_Pictographic# 5.2 [3] (⚽..⚿) soccer ball..SQUARED KEY
|
||||
26C0..26C3 ; Extended_Pictographic# 5.1 [4] (⛀..⛃) WHITE DRAUGHTS MAN..BLACK DRAUGHTS KING
|
||||
26C4..26CD ; Extended_Pictographic# 5.2 [10] (⛄..⛍) snowman without snow..DISABLED CAR
|
||||
26CE ; Extended_Pictographic# 6.0 [1] (⛎) Ophiuchus
|
||||
26CF..26E1 ; Extended_Pictographic# 5.2 [19] (⛏️..⛡) pick..RESTRICTED LEFT ENTRY-2
|
||||
26E2 ; Extended_Pictographic# 6.0 [1] (⛢) ASTRONOMICAL SYMBOL FOR URANUS
|
||||
26E3 ; Extended_Pictographic# 5.2 [1] (⛣) HEAVY CIRCLE WITH STROKE AND TWO DOTS ABOVE
|
||||
26E4..26E7 ; Extended_Pictographic# 6.0 [4] (⛤..⛧) PENTAGRAM..INVERTED PENTAGRAM
|
||||
26E8..26FF ; Extended_Pictographic# 5.2 [24] (⛨..⛿) BLACK CROSS ON SHIELD..WHITE FLAG WITH HORIZONTAL MIDDLE BLACK STRIPE
|
||||
2700 ; Extended_Pictographic# 7.0 [1] (✀) BLACK SAFETY SCISSORS
|
||||
2701..2704 ; Extended_Pictographic# 1.1 [4] (✁..✄) UPPER BLADE SCISSORS..WHITE SCISSORS
|
||||
2705 ; Extended_Pictographic# 6.0 [1] (✅) check mark button
|
||||
2708..2709 ; Extended_Pictographic# 1.1 [2] (✈️..✉️) airplane..envelope
|
||||
270A..270B ; Extended_Pictographic# 6.0 [2] (✊..✋) raised fist..raised hand
|
||||
270C..2712 ; Extended_Pictographic# 1.1 [7] (✌️..✒️) victory hand..black nib
|
||||
2714 ; Extended_Pictographic# 1.1 [1] (✔️) check mark
|
||||
2716 ; Extended_Pictographic# 1.1 [1] (✖️) multiplication sign
|
||||
271D ; Extended_Pictographic# 1.1 [1] (✝️) latin cross
|
||||
2721 ; Extended_Pictographic# 1.1 [1] (✡️) star of David
|
||||
2728 ; Extended_Pictographic# 6.0 [1] (✨) sparkles
|
||||
2733..2734 ; Extended_Pictographic# 1.1 [2] (✳️..✴️) eight-spoked asterisk..eight-pointed star
|
||||
2744 ; Extended_Pictographic# 1.1 [1] (❄️) snowflake
|
||||
2747 ; Extended_Pictographic# 1.1 [1] (❇️) sparkle
|
||||
274C ; Extended_Pictographic# 6.0 [1] (❌) cross mark
|
||||
274E ; Extended_Pictographic# 6.0 [1] (❎) cross mark button
|
||||
2753..2755 ; Extended_Pictographic# 6.0 [3] (❓..❕) question mark..white exclamation mark
|
||||
2757 ; Extended_Pictographic# 5.2 [1] (❗) exclamation mark
|
||||
2763..2767 ; Extended_Pictographic# 1.1 [5] (❣️..❧) heart exclamation..ROTATED FLORAL HEART BULLET
|
||||
2795..2797 ; Extended_Pictographic# 6.0 [3] (➕..➗) plus sign..division sign
|
||||
27A1 ; Extended_Pictographic# 1.1 [1] (➡️) right arrow
|
||||
27B0 ; Extended_Pictographic# 6.0 [1] (➰) curly loop
|
||||
27BF ; Extended_Pictographic# 6.0 [1] (➿) double curly loop
|
||||
2934..2935 ; Extended_Pictographic# 3.2 [2] (⤴️..⤵️) right arrow curving up..right arrow curving down
|
||||
2B05..2B07 ; Extended_Pictographic# 4.0 [3] (⬅️..⬇️) left arrow..down arrow
|
||||
2B1B..2B1C ; Extended_Pictographic# 5.1 [2] (⬛..⬜) black large square..white large square
|
||||
2B50 ; Extended_Pictographic# 5.1 [1] (⭐) star
|
||||
2B55 ; Extended_Pictographic# 5.2 [1] (⭕) hollow red circle
|
||||
3030 ; Extended_Pictographic# 1.1 [1] (〰️) wavy dash
|
||||
303D ; Extended_Pictographic# 3.2 [1] (〽️) part alternation mark
|
||||
3297 ; Extended_Pictographic# 1.1 [1] (㊗️) Japanese “congratulations” button
|
||||
3299 ; Extended_Pictographic# 1.1 [1] (㊙️) Japanese “secret” button
|
||||
1F000..1F02B ; Extended_Pictographic# 5.1 [44] (🀀..🀫) MAHJONG TILE EAST WIND..MAHJONG TILE BACK
|
||||
1F02C..1F02F ; Extended_Pictographic# NA [4] (..) <reserved-1F02C>..<reserved-1F02F>
|
||||
1F030..1F093 ; Extended_Pictographic# 5.1[100] (🀰..🂓) DOMINO TILE HORIZONTAL BACK..DOMINO TILE VERTICAL-06-06
|
||||
1F094..1F09F ; Extended_Pictographic# NA [12] (..) <reserved-1F094>..<reserved-1F09F>
|
||||
1F0A0..1F0AE ; Extended_Pictographic# 6.0 [15] (🂠..🂮) PLAYING CARD BACK..PLAYING CARD KING OF SPADES
|
||||
1F0AF..1F0B0 ; Extended_Pictographic# NA [2] (..) <reserved-1F0AF>..<reserved-1F0B0>
|
||||
1F0B1..1F0BE ; Extended_Pictographic# 6.0 [14] (🂱..🂾) PLAYING CARD ACE OF HEARTS..PLAYING CARD KING OF HEARTS
|
||||
1F0BF ; Extended_Pictographic# 7.0 [1] (🂿) PLAYING CARD RED JOKER
|
||||
1F0C0 ; Extended_Pictographic# NA [1] () <reserved-1F0C0>
|
||||
1F0C1..1F0CF ; Extended_Pictographic# 6.0 [15] (🃁..🃏) PLAYING CARD ACE OF DIAMONDS..joker
|
||||
1F0D0 ; Extended_Pictographic# NA [1] () <reserved-1F0D0>
|
||||
1F0D1..1F0DF ; Extended_Pictographic# 6.0 [15] (🃑..🃟) PLAYING CARD ACE OF CLUBS..PLAYING CARD WHITE JOKER
|
||||
1F0E0..1F0F5 ; Extended_Pictographic# 7.0 [22] (🃠..🃵) PLAYING CARD FOOL..PLAYING CARD TRUMP-21
|
||||
1F0F6..1F0FF ; Extended_Pictographic# NA [10] (..) <reserved-1F0F6>..<reserved-1F0FF>
|
||||
1F10D..1F10F ; Extended_Pictographic# NA [3] (🄍..🄏) <reserved-1F10D>..<reserved-1F10F>
|
||||
1F12F ; Extended_Pictographic# 11.0 [1] (🄯) COPYLEFT SYMBOL
|
||||
1F16C ; Extended_Pictographic# 12.0 [1] (🅬) RAISED MR SIGN
|
||||
1F16D..1F16F ; Extended_Pictographic# NA [3] (🅭..🅯) <reserved-1F16D>..<reserved-1F16F>
|
||||
1F170..1F171 ; Extended_Pictographic# 6.0 [2] (🅰️..🅱️) A button (blood type)..B button (blood type)
|
||||
1F17E ; Extended_Pictographic# 6.0 [1] (🅾️) O button (blood type)
|
||||
1F17F ; Extended_Pictographic# 5.2 [1] (🅿️) P button
|
||||
1F18E ; Extended_Pictographic# 6.0 [1] (🆎) AB button (blood type)
|
||||
1F191..1F19A ; Extended_Pictographic# 6.0 [10] (🆑..🆚) CL button..VS button
|
||||
1F1AD..1F1E5 ; Extended_Pictographic# NA [57] (🆭..) <reserved-1F1AD>..<reserved-1F1E5>
|
||||
1F201..1F202 ; Extended_Pictographic# 6.0 [2] (🈁..🈂️) Japanese “here” button..Japanese “service charge” button
|
||||
1F203..1F20F ; Extended_Pictographic# NA [13] (..) <reserved-1F203>..<reserved-1F20F>
|
||||
1F21A ; Extended_Pictographic# 5.2 [1] (🈚) Japanese “free of charge” button
|
||||
1F22F ; Extended_Pictographic# 5.2 [1] (🈯) Japanese “reserved” button
|
||||
1F232..1F23A ; Extended_Pictographic# 6.0 [9] (🈲..🈺) Japanese “prohibited” button..Japanese “open for business” button
|
||||
1F23C..1F23F ; Extended_Pictographic# NA [4] (..) <reserved-1F23C>..<reserved-1F23F>
|
||||
1F249..1F24F ; Extended_Pictographic# NA [7] (..) <reserved-1F249>..<reserved-1F24F>
|
||||
1F250..1F251 ; Extended_Pictographic# 6.0 [2] (🉐..🉑) Japanese “bargain” button..Japanese “acceptable” button
|
||||
1F252..1F25F ; Extended_Pictographic# NA [14] (..) <reserved-1F252>..<reserved-1F25F>
|
||||
1F260..1F265 ; Extended_Pictographic# 10.0 [6] (🉠..🉥) ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI
|
||||
1F266..1F2FF ; Extended_Pictographic# NA[154] (..) <reserved-1F266>..<reserved-1F2FF>
|
||||
1F300..1F320 ; Extended_Pictographic# 6.0 [33] (🌀..🌠) cyclone..shooting star
|
||||
1F321..1F32C ; Extended_Pictographic# 7.0 [12] (🌡️..🌬️) thermometer..wind face
|
||||
1F32D..1F32F ; Extended_Pictographic# 8.0 [3] (🌭..🌯) hot dog..burrito
|
||||
1F330..1F335 ; Extended_Pictographic# 6.0 [6] (🌰..🌵) chestnut..cactus
|
||||
1F336 ; Extended_Pictographic# 7.0 [1] (🌶️) hot pepper
|
||||
1F337..1F37C ; Extended_Pictographic# 6.0 [70] (🌷..🍼) tulip..baby bottle
|
||||
1F37D ; Extended_Pictographic# 7.0 [1] (🍽️) fork and knife with plate
|
||||
1F37E..1F37F ; Extended_Pictographic# 8.0 [2] (🍾..🍿) bottle with popping cork..popcorn
|
||||
1F380..1F393 ; Extended_Pictographic# 6.0 [20] (🎀..🎓) ribbon..graduation cap
|
||||
1F394..1F39F ; Extended_Pictographic# 7.0 [12] (🎔..🎟️) HEART WITH TIP ON THE LEFT..admission tickets
|
||||
1F3A0..1F3C4 ; Extended_Pictographic# 6.0 [37] (🎠..🏄) carousel horse..person surfing
|
||||
1F3C5 ; Extended_Pictographic# 7.0 [1] (🏅) sports medal
|
||||
1F3C6..1F3CA ; Extended_Pictographic# 6.0 [5] (🏆..🏊) trophy..person swimming
|
||||
1F3CB..1F3CE ; Extended_Pictographic# 7.0 [4] (🏋️..🏎️) person lifting weights..racing car
|
||||
1F3CF..1F3D3 ; Extended_Pictographic# 8.0 [5] (🏏..🏓) cricket game..ping pong
|
||||
1F3D4..1F3DF ; Extended_Pictographic# 7.0 [12] (🏔️..🏟️) snow-capped mountain..stadium
|
||||
1F3E0..1F3F0 ; Extended_Pictographic# 6.0 [17] (🏠..🏰) house..castle
|
||||
1F3F1..1F3F7 ; Extended_Pictographic# 7.0 [7] (🏱..🏷️) WHITE PENNANT..label
|
||||
1F3F8..1F3FA ; Extended_Pictographic# 8.0 [3] (🏸..🏺) badminton..amphora
|
||||
1F400..1F43E ; Extended_Pictographic# 6.0 [63] (🐀..🐾) rat..paw prints
|
||||
1F43F ; Extended_Pictographic# 7.0 [1] (🐿️) chipmunk
|
||||
1F440 ; Extended_Pictographic# 6.0 [1] (👀) eyes
|
||||
1F441 ; Extended_Pictographic# 7.0 [1] (👁️) eye
|
||||
1F442..1F4F7 ; Extended_Pictographic# 6.0[182] (👂..📷) ear..camera
|
||||
1F4F8 ; Extended_Pictographic# 7.0 [1] (📸) camera with flash
|
||||
1F4F9..1F4FC ; Extended_Pictographic# 6.0 [4] (📹..📼) video camera..videocassette
|
||||
1F4FD..1F4FE ; Extended_Pictographic# 7.0 [2] (📽️..📾) film projector..PORTABLE STEREO
|
||||
1F4FF ; Extended_Pictographic# 8.0 [1] (📿) prayer beads
|
||||
1F500..1F53D ; Extended_Pictographic# 6.0 [62] (🔀..🔽) shuffle tracks button..downwards button
|
||||
1F546..1F54A ; Extended_Pictographic# 7.0 [5] (🕆..🕊️) WHITE LATIN CROSS..dove
|
||||
1F54B..1F54F ; Extended_Pictographic# 8.0 [5] (🕋..🕏) kaaba..BOWL OF HYGIEIA
|
||||
1F550..1F567 ; Extended_Pictographic# 6.0 [24] (🕐..🕧) one o’clock..twelve-thirty
|
||||
1F568..1F579 ; Extended_Pictographic# 7.0 [18] (🕨..🕹️) RIGHT SPEAKER..joystick
|
||||
1F57A ; Extended_Pictographic# 9.0 [1] (🕺) man dancing
|
||||
1F57B..1F5A3 ; Extended_Pictographic# 7.0 [41] (🕻..🖣) LEFT HAND TELEPHONE RECEIVER..BLACK DOWN POINTING BACKHAND INDEX
|
||||
1F5A4 ; Extended_Pictographic# 9.0 [1] (🖤) black heart
|
||||
1F5A5..1F5FA ; Extended_Pictographic# 7.0 [86] (🖥️..🗺️) desktop computer..world map
|
||||
1F5FB..1F5FF ; Extended_Pictographic# 6.0 [5] (🗻..🗿) mount fuji..moai
|
||||
1F600 ; Extended_Pictographic# 6.1 [1] (😀) grinning face
|
||||
1F601..1F610 ; Extended_Pictographic# 6.0 [16] (😁..😐) beaming face with smiling eyes..neutral face
|
||||
1F611 ; Extended_Pictographic# 6.1 [1] (😑) expressionless face
|
||||
1F612..1F614 ; Extended_Pictographic# 6.0 [3] (😒..😔) unamused face..pensive face
|
||||
1F615 ; Extended_Pictographic# 6.1 [1] (😕) confused face
|
||||
1F616 ; Extended_Pictographic# 6.0 [1] (😖) confounded face
|
||||
1F617 ; Extended_Pictographic# 6.1 [1] (😗) kissing face
|
||||
1F618 ; Extended_Pictographic# 6.0 [1] (😘) face blowing a kiss
|
||||
1F619 ; Extended_Pictographic# 6.1 [1] (😙) kissing face with smiling eyes
|
||||
1F61A ; Extended_Pictographic# 6.0 [1] (😚) kissing face with closed eyes
|
||||
1F61B ; Extended_Pictographic# 6.1 [1] (😛) face with tongue
|
||||
1F61C..1F61E ; Extended_Pictographic# 6.0 [3] (😜..😞) winking face with tongue..disappointed face
|
||||
1F61F ; Extended_Pictographic# 6.1 [1] (😟) worried face
|
||||
1F620..1F625 ; Extended_Pictographic# 6.0 [6] (😠..😥) angry face..sad but relieved face
|
||||
1F626..1F627 ; Extended_Pictographic# 6.1 [2] (😦..😧) frowning face with open mouth..anguished face
|
||||
1F628..1F62B ; Extended_Pictographic# 6.0 [4] (😨..😫) fearful face..tired face
|
||||
1F62C ; Extended_Pictographic# 6.1 [1] (😬) grimacing face
|
||||
1F62D ; Extended_Pictographic# 6.0 [1] (😭) loudly crying face
|
||||
1F62E..1F62F ; Extended_Pictographic# 6.1 [2] (😮..😯) face with open mouth..hushed face
|
||||
1F630..1F633 ; Extended_Pictographic# 6.0 [4] (😰..😳) anxious face with sweat..flushed face
|
||||
1F634 ; Extended_Pictographic# 6.1 [1] (😴) sleeping face
|
||||
1F635..1F640 ; Extended_Pictographic# 6.0 [12] (😵..🙀) dizzy face..weary cat
|
||||
1F641..1F642 ; Extended_Pictographic# 7.0 [2] (🙁..🙂) slightly frowning face..slightly smiling face
|
||||
1F643..1F644 ; Extended_Pictographic# 8.0 [2] (🙃..🙄) upside-down face..face with rolling eyes
|
||||
1F645..1F64F ; Extended_Pictographic# 6.0 [11] (🙅..🙏) person gesturing NO..folded hands
|
||||
1F680..1F6C5 ; Extended_Pictographic# 6.0 [70] (🚀..🛅) rocket..left luggage
|
||||
1F6C6..1F6CF ; Extended_Pictographic# 7.0 [10] (🛆..🛏️) TRIANGLE WITH ROUNDED CORNERS..bed
|
||||
1F6D0 ; Extended_Pictographic# 8.0 [1] (🛐) place of worship
|
||||
1F6D1..1F6D2 ; Extended_Pictographic# 9.0 [2] (🛑..🛒) stop sign..shopping cart
|
||||
1F6D3..1F6D4 ; Extended_Pictographic# 10.0 [2] (🛓..🛔) STUPA..PAGODA
|
||||
1F6D5 ; Extended_Pictographic# 12.0 [1] (🛕) hindu temple
|
||||
1F6D6..1F6DF ; Extended_Pictographic# NA [10] (🛖..🛟) <reserved-1F6D6>..<reserved-1F6DF>
|
||||
1F6E0..1F6EC ; Extended_Pictographic# 7.0 [13] (🛠️..🛬) hammer and wrench..airplane arrival
|
||||
1F6ED..1F6EF ; Extended_Pictographic# NA [3] (..) <reserved-1F6ED>..<reserved-1F6EF>
|
||||
1F6F0..1F6F3 ; Extended_Pictographic# 7.0 [4] (🛰️..🛳️) satellite..passenger ship
|
||||
1F6F4..1F6F6 ; Extended_Pictographic# 9.0 [3] (🛴..🛶) kick scooter..canoe
|
||||
1F6F7..1F6F8 ; Extended_Pictographic# 10.0 [2] (🛷..🛸) sled..flying saucer
|
||||
1F6F9 ; Extended_Pictographic# 11.0 [1] (🛹) skateboard
|
||||
1F6FA ; Extended_Pictographic# 12.0 [1] (🛺) auto rickshaw
|
||||
1F6FB..1F6FF ; Extended_Pictographic# NA [5] (🛻..) <reserved-1F6FB>..<reserved-1F6FF>
|
||||
1F774..1F77F ; Extended_Pictographic# NA [12] (🝴..🝿) <reserved-1F774>..<reserved-1F77F>
|
||||
1F7D5..1F7D8 ; Extended_Pictographic# 11.0 [4] (🟕..🟘) CIRCLED TRIANGLE..NEGATIVE CIRCLED SQUARE
|
||||
1F7D9..1F7DF ; Extended_Pictographic# NA [7] (🟙..) <reserved-1F7D9>..<reserved-1F7DF>
|
||||
1F7E0..1F7EB ; Extended_Pictographic# 12.0 [12] (🟠..🟫) orange circle..brown square
|
||||
1F7EC..1F7FF ; Extended_Pictographic# NA [20] (..) <reserved-1F7EC>..<reserved-1F7FF>
|
||||
1F80C..1F80F ; Extended_Pictographic# NA [4] (..) <reserved-1F80C>..<reserved-1F80F>
|
||||
1F848..1F84F ; Extended_Pictographic# NA [8] (..) <reserved-1F848>..<reserved-1F84F>
|
||||
1F85A..1F85F ; Extended_Pictographic# NA [6] (..) <reserved-1F85A>..<reserved-1F85F>
|
||||
1F888..1F88F ; Extended_Pictographic# NA [8] (..) <reserved-1F888>..<reserved-1F88F>
|
||||
1F8AE..1F8FF ; Extended_Pictographic# NA [82] (..) <reserved-1F8AE>..<reserved-1F8FF>
|
||||
1F90C ; Extended_Pictographic# NA [1] (🤌) <reserved-1F90C>
|
||||
1F90D..1F90F ; Extended_Pictographic# 12.0 [3] (🤍..🤏) white heart..pinching hand
|
||||
1F910..1F918 ; Extended_Pictographic# 8.0 [9] (🤐..🤘) zipper-mouth face..sign of the horns
|
||||
1F919..1F91E ; Extended_Pictographic# 9.0 [6] (🤙..🤞) call me hand..crossed fingers
|
||||
1F91F ; Extended_Pictographic# 10.0 [1] (🤟) love-you gesture
|
||||
1F920..1F927 ; Extended_Pictographic# 9.0 [8] (🤠..🤧) cowboy hat face..sneezing face
|
||||
1F928..1F92F ; Extended_Pictographic# 10.0 [8] (🤨..🤯) face with raised eyebrow..exploding head
|
||||
1F930 ; Extended_Pictographic# 9.0 [1] (🤰) pregnant woman
|
||||
1F931..1F932 ; Extended_Pictographic# 10.0 [2] (🤱..🤲) breast-feeding..palms up together
|
||||
1F933..1F93A ; Extended_Pictographic# 9.0 [8] (🤳..🤺) selfie..person fencing
|
||||
1F93C..1F93E ; Extended_Pictographic# 9.0 [3] (🤼..🤾) people wrestling..person playing handball
|
||||
1F93F ; Extended_Pictographic# 12.0 [1] (🤿) diving mask
|
||||
1F940..1F945 ; Extended_Pictographic# 9.0 [6] (🥀..🥅) wilted flower..goal net
|
||||
1F947..1F94B ; Extended_Pictographic# 9.0 [5] (🥇..🥋) 1st place medal..martial arts uniform
|
||||
1F94C ; Extended_Pictographic# 10.0 [1] (🥌) curling stone
|
||||
1F94D..1F94F ; Extended_Pictographic# 11.0 [3] (🥍..🥏) lacrosse..flying disc
|
||||
1F950..1F95E ; Extended_Pictographic# 9.0 [15] (🥐..🥞) croissant..pancakes
|
||||
1F95F..1F96B ; Extended_Pictographic# 10.0 [13] (🥟..🥫) dumpling..canned food
|
||||
1F96C..1F970 ; Extended_Pictographic# 11.0 [5] (🥬..🥰) leafy green..smiling face with hearts
|
||||
1F971 ; Extended_Pictographic# 12.0 [1] (🥱) yawning face
|
||||
1F972 ; Extended_Pictographic# NA [1] (🥲) <reserved-1F972>
|
||||
1F973..1F976 ; Extended_Pictographic# 11.0 [4] (🥳..🥶) partying face..cold face
|
||||
1F977..1F979 ; Extended_Pictographic# NA [3] (🥷..🥹) <reserved-1F977>..<reserved-1F979>
|
||||
1F97A ; Extended_Pictographic# 11.0 [1] (🥺) pleading face
|
||||
1F97B ; Extended_Pictographic# 12.0 [1] (🥻) sari
|
||||
1F97C..1F97F ; Extended_Pictographic# 11.0 [4] (🥼..🥿) lab coat..flat shoe
|
||||
1F980..1F984 ; Extended_Pictographic# 8.0 [5] (🦀..🦄) crab..unicorn
|
||||
1F985..1F991 ; Extended_Pictographic# 9.0 [13] (🦅..🦑) eagle..squid
|
||||
1F992..1F997 ; Extended_Pictographic# 10.0 [6] (🦒..🦗) giraffe..cricket
|
||||
1F998..1F9A2 ; Extended_Pictographic# 11.0 [11] (🦘..🦢) kangaroo..swan
|
||||
1F9A3..1F9A4 ; Extended_Pictographic# NA [2] (🦣..🦤) <reserved-1F9A3>..<reserved-1F9A4>
|
||||
1F9A5..1F9AA ; Extended_Pictographic# 12.0 [6] (🦥..🦪) sloth..oyster
|
||||
1F9AB..1F9AD ; Extended_Pictographic# NA [3] (🦫..🦭) <reserved-1F9AB>..<reserved-1F9AD>
|
||||
1F9AE..1F9AF ; Extended_Pictographic# 12.0 [2] (🦮..🦯) guide dog..probing cane
|
||||
1F9B0..1F9B9 ; Extended_Pictographic# 11.0 [10] (🦰..🦹) red hair..supervillain
|
||||
1F9BA..1F9BF ; Extended_Pictographic# 12.0 [6] (🦺..🦿) safety vest..mechanical leg
|
||||
1F9C0 ; Extended_Pictographic# 8.0 [1] (🧀) cheese wedge
|
||||
1F9C1..1F9C2 ; Extended_Pictographic# 11.0 [2] (🧁..🧂) cupcake..salt
|
||||
1F9C3..1F9CA ; Extended_Pictographic# 12.0 [8] (🧃..🧊) beverage box..ice cube
|
||||
1F9CB..1F9CC ; Extended_Pictographic# NA [2] (🧋..🧌) <reserved-1F9CB>..<reserved-1F9CC>
|
||||
1F9CD..1F9CF ; Extended_Pictographic# 12.0 [3] (🧍..🧏) person standing..deaf person
|
||||
1F9D0..1F9E6 ; Extended_Pictographic# 10.0 [23] (🧐..🧦) face with monocle..socks
|
||||
1F9E7..1F9FF ; Extended_Pictographic# 11.0 [25] (🧧..🧿) red envelope..nazar amulet
|
||||
1FA00..1FA53 ; Extended_Pictographic# 12.0 [84] (🨀..🩓) NEUTRAL CHESS KING..BLACK CHESS KNIGHT-BISHOP
|
||||
1FA54..1FA5F ; Extended_Pictographic# NA [12] (..) <reserved-1FA54>..<reserved-1FA5F>
|
||||
1FA60..1FA6D ; Extended_Pictographic# 11.0 [14] (🩠..🩭) XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER
|
||||
1FA6E..1FA6F ; Extended_Pictographic# NA [2] (..) <reserved-1FA6E>..<reserved-1FA6F>
|
||||
1FA70..1FA73 ; Extended_Pictographic# 12.0 [4] (🩰..🩳) ballet shoes..shorts
|
||||
1FA74..1FA77 ; Extended_Pictographic# NA [4] (🩴..🩷) <reserved-1FA74>..<reserved-1FA77>
|
||||
1FA78..1FA7A ; Extended_Pictographic# 12.0 [3] (🩸..🩺) drop of blood..stethoscope
|
||||
1FA7B..1FA7F ; Extended_Pictographic# NA [5] (🩻..) <reserved-1FA7B>..<reserved-1FA7F>
|
||||
1FA80..1FA82 ; Extended_Pictographic# 12.0 [3] (🪀..🪂) yo-yo..parachute
|
||||
1FA83..1FA8F ; Extended_Pictographic# NA [13] (🪃..) <reserved-1FA83>..<reserved-1FA8F>
|
||||
1FA90..1FA95 ; Extended_Pictographic# 12.0 [6] (🪐..🪕) ringed planet..banjo
|
||||
1FA96..1FFFD ; Extended_Pictographic# NA[1384] (🪖..) <reserved-1FA96>..<reserved-1FFFD>
|
||||
|
||||
# Total elements: 3793
|
||||
|
||||
#EOF
|
@ -34,6 +34,7 @@ include GensrcBuffer.gmk
|
||||
include GensrcExceptions.gmk
|
||||
include GensrcVarHandles.gmk
|
||||
include GensrcModuleLoaderMap.gmk
|
||||
include GensrcEmojiData.gmk
|
||||
|
||||
################################################################################
|
||||
|
||||
|
44
make/gensrc/GensrcEmojiData.gmk
Normal file
44
make/gensrc/GensrcEmojiData.gmk
Normal file
@ -0,0 +1,44 @@
|
||||
#
|
||||
# Copyright (c) 2019, 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
|
||||
# under the terms of the GNU General Public License version 2 only, as
|
||||
# published by the Free Software Foundation. Oracle designates this
|
||||
# particular file as subject to the "Classpath" exception as provided
|
||||
# by Oracle in the LICENSE file that accompanied this code.
|
||||
#
|
||||
# This code is distributed in the hope that it will be useful, but WITHOUT
|
||||
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
||||
# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
|
||||
# version 2 for more details (a copy is included in the LICENSE file that
|
||||
# accompanied this code).
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License version
|
||||
# 2 along with this work; if not, write to the Free Software Foundation,
|
||||
# Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
|
||||
#
|
||||
# Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
|
||||
# or visit www.oracle.com if you need additional information or have any
|
||||
# questions.
|
||||
#
|
||||
|
||||
#
|
||||
# Rules to create $(SUPPORT_OUTPUTDIR)/gensrc/java.base/java/util/regex/EmojiData.java
|
||||
#
|
||||
|
||||
GENSRC_EMOJIDATA := $(SUPPORT_OUTPUTDIR)/gensrc/java.base/java/util/regex/EmojiData.java
|
||||
|
||||
EMOJIDATATEMP = $(TOPDIR)/src/java.base/share/classes/java/util/regex/EmojiData.java.template
|
||||
UNICODEDATA = $(TOPDIR)/make/data/unicodedata
|
||||
|
||||
$(GENSRC_EMOJIDATA): $(BUILD_TOOLS_JDK) $(EMOJIDATATEMP) $(UNICODEDATA)/emoji-data.txt
|
||||
$(call LogInfo, Generating $@)
|
||||
$(call MakeTargetDir)
|
||||
$(TOOL_GENERATEEMOJIDATA) \
|
||||
$(EMOJIDATATEMP) \
|
||||
$(UNICODEDATA) \
|
||||
$(GENSRC_EMOJIDATA)
|
||||
|
||||
GENSRC_JAVA_BASE += $(GENSRC_EMOJIDATA)
|
||||
|
@ -0,0 +1,142 @@
|
||||
/*
|
||||
* Copyright (c) 2019, 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
|
||||
* under the terms of the GNU General Public License version 2 only, as
|
||||
* published by the Free Software Foundation. Oracle designates this
|
||||
* particular file as subject to the "Classpath" exception as provided
|
||||
* by Oracle in the LICENSE file that accompanied this code.
|
||||
*
|
||||
* This code is distributed in the hope that it will be useful, but WITHOUT
|
||||
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
||||
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
|
||||
* version 2 for more details (a copy is included in the LICENSE file that
|
||||
* accompanied this code).
|
||||
*
|
||||
* You should have received a copy of the GNU General Public License version
|
||||
* 2 along with this work; if not, write to the Free Software Foundation,
|
||||
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
|
||||
*
|
||||
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
|
||||
* or visit www.oracle.com if you need additional information or have any
|
||||
* questions.
|
||||
*/
|
||||
|
||||
package build.tools.generateemojidata;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.nio.file.Files;
|
||||
import java.nio.file.Paths;
|
||||
import java.nio.file.StandardOpenOption;
|
||||
import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
import java.util.function.Predicate;
|
||||
import java.util.stream.Collectors;
|
||||
import java.util.stream.Stream;
|
||||
|
||||
/**
|
||||
* Generate EmojiData.java
|
||||
* args[0]: Full path string to the template file
|
||||
* args[1]: Full path string to the directory that contains "emoji-data.txt"
|
||||
* args[2]: Full path string to the generated .java file
|
||||
*/
|
||||
public class GenerateEmojiData {
|
||||
public static void main(String[] args) {
|
||||
try {
|
||||
final Range[] last = new Range[1]; // last extended pictographic range
|
||||
last[0] = new Range(0, 0);
|
||||
|
||||
List<Range> extPictRanges = Files.lines(Paths.get(args[1], "emoji-data.txt"))
|
||||
.filter(Predicate.not(l -> l.startsWith("#") || l.isBlank()))
|
||||
.filter(l -> l.contains("; Extended_Pictograph"))
|
||||
.map(l -> new Range(l.replaceFirst(" .*", "")))
|
||||
.sorted()
|
||||
.collect(ArrayList<Range>::new,
|
||||
(list, r) -> {
|
||||
// collapsing consecutive pictographic ranges
|
||||
int lastIndex = list.size() - 1;
|
||||
if (lastIndex >= 0) {
|
||||
Range lastRange = list.get(lastIndex);
|
||||
if (lastRange.last + 1 == r.start) {
|
||||
list.set(lastIndex, new Range(lastRange.start, r.last));
|
||||
return;
|
||||
}
|
||||
}
|
||||
list.add(r);
|
||||
},
|
||||
ArrayList<Range>::addAll);
|
||||
|
||||
// make the code point conditions
|
||||
String extPictCodePoints = extPictRanges.stream()
|
||||
.map(r -> {
|
||||
if (r.start == r.last) {
|
||||
return (" ".repeat(12) + "cp == 0x" + toHexString(r.start));
|
||||
} else if (r.start == r.last - 1) {
|
||||
return " ".repeat(12) + "cp == 0x" + toHexString(r.start) + " ||\n" +
|
||||
" ".repeat(12) + "cp == 0x" + toHexString(r.last);
|
||||
} else {
|
||||
return " ".repeat(11) + "(cp >= 0x" + toHexString(r.start) +
|
||||
" && cp <= 0x" + toHexString(r.last) + ")";
|
||||
}
|
||||
})
|
||||
.collect(Collectors.joining(" ||\n")) + ";\n";
|
||||
|
||||
// Generate EmojiData.java file
|
||||
Files.write(Paths.get(args[2]),
|
||||
Files.lines(Paths.get(args[0]))
|
||||
.flatMap(l -> {
|
||||
if (l.equals("%%%EXTPICT%%%")) {
|
||||
return Stream.of(extPictCodePoints);
|
||||
} else {
|
||||
return Stream.of(l);
|
||||
}
|
||||
})
|
||||
.collect(Collectors.toList()),
|
||||
StandardOpenOption.CREATE, StandardOpenOption.TRUNCATE_EXISTING);
|
||||
} catch (IOException e) {
|
||||
e.printStackTrace();
|
||||
}
|
||||
}
|
||||
|
||||
static int toInt(String hexStr) {
|
||||
return Integer.parseUnsignedInt(hexStr, 16);
|
||||
}
|
||||
|
||||
static String toHexString(int cp) {
|
||||
String ret = Integer.toUnsignedString(cp, 16).toUpperCase();
|
||||
if (ret.length() < 4) {
|
||||
ret = "0".repeat(4 - ret.length()) + ret;
|
||||
}
|
||||
return ret;
|
||||
}
|
||||
|
||||
static class Range implements Comparable<Range> {
|
||||
int start;
|
||||
int last;
|
||||
|
||||
Range (int start, int last) {
|
||||
this.start = start;
|
||||
this.last = last;
|
||||
}
|
||||
|
||||
Range (String input) {
|
||||
input = input.replaceFirst("\\s#.*", "");
|
||||
start = toInt(input.replaceFirst("[\\s\\.].*", ""));
|
||||
last = input.contains("..") ?
|
||||
toInt(input.replaceFirst(".*\\.\\.", "")
|
||||
.replaceFirst(";.*", "").trim())
|
||||
: start;
|
||||
}
|
||||
|
||||
@Override
|
||||
public String toString() {
|
||||
return "Start: " + toHexString(start) + ", Last: " + toHexString(last);
|
||||
}
|
||||
|
||||
@Override
|
||||
public int compareTo(Range other) {
|
||||
return Integer.compare(start, other.start);
|
||||
}
|
||||
}
|
||||
}
|
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,46 @@
|
||||
/*
|
||||
* Copyright (c) 2019, 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
|
||||
* under the terms of the GNU General Public License version 2 only, as
|
||||
* published by the Free Software Foundation. Oracle designates this
|
||||
* particular file as subject to the "Classpath" exception as provided
|
||||
* by Oracle in the LICENSE file that accompanied this code.
|
||||
*
|
||||
* This code is distributed in the hope that it will be useful, but WITHOUT
|
||||
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
||||
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
|
||||
* version 2 for more details (a copy is included in the LICENSE file that
|
||||
* accompanied this code).
|
||||
*
|
||||
* You should have received a copy of the GNU General Public License version
|
||||
* 2 along with this work; if not, write to the Free Software Foundation,
|
||||
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
|
||||
*
|
||||
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
|
||||
* or visit www.oracle.com if you need additional information or have any
|
||||
* questions.
|
||||
*/
|
||||
|
||||
package java.util.regex;
|
||||
|
||||
/**
|
||||
* Holds data contained in the Unicode Technical Standard #51: Unicode
|
||||
* Emoji.
|
||||
*
|
||||
* Currently it is only used for the rule "GB11" in UAX #29 Unicode Text
|
||||
* Segmentation.
|
||||
*/
|
||||
final class EmojiData {
|
||||
/**
|
||||
* Returns whether the code point is an extended pictographic or not.
|
||||
*
|
||||
* @param cp code point to examine
|
||||
* @return true if {@code cp} is an extended pictographic
|
||||
*/
|
||||
static boolean isExtendedPictographic(int cp) {
|
||||
return
|
||||
%%%EXTPICT%%%
|
||||
}
|
||||
}
|
@ -1,5 +1,5 @@
|
||||
/*
|
||||
* Copyright (c) 2016, Oracle and/or its affiliates. All rights reserved.
|
||||
* Copyright (c) 2016, 2019, 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
|
||||
@ -25,17 +25,56 @@
|
||||
|
||||
package java.util.regex;
|
||||
|
||||
import java.util.Objects;
|
||||
|
||||
final class Grapheme {
|
||||
|
||||
/**
|
||||
* Determines if there is an extended grapheme cluster boundary between two
|
||||
* continuing characters {@code cp1} and {@code cp2}.
|
||||
* Look for the next extended grapheme cluster boundary in a CharSequence. It assumes
|
||||
* the start of the char sequence is a boundary.
|
||||
* <p>
|
||||
* See Unicode Standard Annex #29 Unicode Text Segmentation for the specification
|
||||
* for the extended grapheme cluster boundary rules
|
||||
* for the extended grapheme cluster boundary rules. The following implementation
|
||||
* is based on version 12.0 of the annex.
|
||||
* (http://www.unicode.org/reports/tr29/tr29-35.html)
|
||||
*
|
||||
* @param src the {@code CharSequence} to be scanned
|
||||
* @param off offset to start looking for the next boundary in the src
|
||||
* @param limit limit offset in the src (exclusive)
|
||||
* @return the next possible boundary
|
||||
*/
|
||||
static boolean isBoundary(int cp1, int cp2) {
|
||||
return rules[getType(cp1)][getType(cp2)];
|
||||
static int nextBoundary(CharSequence src, int off, int limit) {
|
||||
Objects.checkFromToIndex(off, limit, src.length());
|
||||
|
||||
int ch0 = Character.codePointAt(src, 0);
|
||||
int ret = Character.charCount(ch0);
|
||||
int ch1;
|
||||
// indicates whether gb11 or gb12 is underway
|
||||
boolean gb11 = EmojiData.isExtendedPictographic(ch0);
|
||||
int riCount = getType(ch0) == RI ? 1 : 0;
|
||||
while (ret < limit) {
|
||||
ch1 = Character.codePointAt(src, ret);
|
||||
int t0 = getType(ch0);
|
||||
int t1 = getType(ch1);
|
||||
|
||||
if (gb11 && t0 == ZWJ && t1 == EXTENDED_PICTOGRAPHIC) {
|
||||
gb11 = false;
|
||||
} else if (riCount % 2 == 1 && t0 == RI && t1 == RI) {
|
||||
// continue for gb12
|
||||
} else if (rules[t0][t1]) {
|
||||
if (ret > off) {
|
||||
break;
|
||||
} else {
|
||||
gb11 = EmojiData.isExtendedPictographic(ch1);
|
||||
riCount = 0;
|
||||
}
|
||||
}
|
||||
|
||||
riCount += getType(ch1) == RI ? 1 : 0;
|
||||
ch0 = ch1;
|
||||
ret += Character.charCount(ch1);
|
||||
}
|
||||
return ret;
|
||||
}
|
||||
|
||||
// types
|
||||
@ -44,22 +83,24 @@ final class Grapheme {
|
||||
private static final int LF = 2;
|
||||
private static final int CONTROL = 3;
|
||||
private static final int EXTEND = 4;
|
||||
private static final int RI = 5;
|
||||
private static final int PREPEND = 6;
|
||||
private static final int SPACINGMARK = 7;
|
||||
private static final int L = 8;
|
||||
private static final int V = 9;
|
||||
private static final int T = 10;
|
||||
private static final int LV = 11;
|
||||
private static final int LVT = 12;
|
||||
private static final int ZWJ = 5;
|
||||
private static final int RI = 6;
|
||||
private static final int PREPEND = 7;
|
||||
private static final int SPACINGMARK = 8;
|
||||
private static final int L = 9;
|
||||
private static final int V = 10;
|
||||
private static final int T = 11;
|
||||
private static final int LV = 12;
|
||||
private static final int LVT = 13;
|
||||
private static final int EXTENDED_PICTOGRAPHIC = 14;
|
||||
|
||||
private static final int FIRST_TYPE = 0;
|
||||
private static final int LAST_TYPE = 12;
|
||||
private static final int LAST_TYPE = 14;
|
||||
|
||||
private static boolean[][] rules;
|
||||
static {
|
||||
rules = new boolean[LAST_TYPE + 1][LAST_TYPE + 1];
|
||||
// default, any + any
|
||||
// GB 999 Any + Any -> default
|
||||
for (int i = FIRST_TYPE; i <= LAST_TYPE; i++)
|
||||
for (int j = FIRST_TYPE; j <= LAST_TYPE; j++)
|
||||
rules[i][j] = true;
|
||||
@ -76,13 +117,12 @@ final class Grapheme {
|
||||
// GB 8 (LVT | T) x T
|
||||
rules[LVT][T] = false;
|
||||
rules[T][T] = false;
|
||||
// GB 8a RI x RI
|
||||
rules[RI][RI] = false;
|
||||
// GB 9 x Extend
|
||||
// GB 9 x (Extend|ZWJ)
|
||||
// GB 9a x Spacing Mark
|
||||
// GB 9b Prepend x
|
||||
for (int i = FIRST_TYPE; i <= LAST_TYPE; i++) {
|
||||
rules[i][EXTEND] = false;
|
||||
rules[i][ZWJ] = false;
|
||||
rules[i][SPACINGMARK] = false;
|
||||
rules[PREPEND][i] = false;
|
||||
}
|
||||
@ -95,7 +135,9 @@ final class Grapheme {
|
||||
}
|
||||
// GB 3 CR x LF
|
||||
rules[CR][LF] = false;
|
||||
// GB 10 Any + Any -> default
|
||||
// GB 11 Exended_Pictographic x (Extend|ZWJ)
|
||||
rules[EXTENDED_PICTOGRAPHIC][EXTEND] = false;
|
||||
rules[EXTENDED_PICTOGRAPHIC][ZWJ] = false;
|
||||
}
|
||||
|
||||
// Hangul syllables
|
||||
@ -123,6 +165,10 @@ final class Grapheme {
|
||||
|
||||
@SuppressWarnings("fallthrough")
|
||||
private static int getType(int cp) {
|
||||
if (EmojiData.isExtendedPictographic(cp)) {
|
||||
return EXTENDED_PICTOGRAPHIC;
|
||||
}
|
||||
|
||||
int type = Character.getType(cp);
|
||||
switch(type) {
|
||||
case Character.CONTROL:
|
||||
@ -131,29 +177,36 @@ final class Grapheme {
|
||||
if (cp == 0x000A)
|
||||
return LF;
|
||||
return CONTROL;
|
||||
case Character.UNASSIGNED:
|
||||
case Character.UNASSIGNED:
|
||||
// NOTE: #tr29 lists "Unassigned and Default_Ignorable_Code_Point" as Control
|
||||
// but GraphemeBreakTest.txt lists u+0378/reserved-0378 as "Other"
|
||||
// so type it as "Other" to make the test happy
|
||||
if (cp == 0x0378)
|
||||
return OTHER;
|
||||
if (cp == 0x0378)
|
||||
return OTHER;
|
||||
|
||||
case Character.LINE_SEPARATOR:
|
||||
case Character.PARAGRAPH_SEPARATOR:
|
||||
case Character.SURROGATE:
|
||||
return CONTROL;
|
||||
case Character.FORMAT:
|
||||
if (cp == 0x200C || cp == 0x200D)
|
||||
if (cp == 0x200C ||
|
||||
cp >= 0xE0020 && cp <= 0xE007F)
|
||||
return EXTEND;
|
||||
if (cp == 0x200D)
|
||||
return ZWJ;
|
||||
if (cp >= 0x0600 && cp <= 0x0605 ||
|
||||
cp == 0x06DD || cp == 0x070F || cp == 0x08E2 ||
|
||||
cp == 0x110BD || cp == 0x110CD)
|
||||
return PREPEND;
|
||||
return CONTROL;
|
||||
case Character.NON_SPACING_MARK:
|
||||
case Character.ENCLOSING_MARK:
|
||||
// NOTE:
|
||||
// #tr29 "plus a few General_Category = Spacing_Mark needed for
|
||||
// canonical equivalence."
|
||||
// but for "extended grapheme clusters" support, there is no
|
||||
// need actually to diff "extend" and "spackmark" given GB9, GB9a
|
||||
return EXTEND;
|
||||
// NOTE:
|
||||
// #tr29 "plus a few General_Category = Spacing_Mark needed for
|
||||
// canonical equivalence."
|
||||
// but for "extended grapheme clusters" support, there is no
|
||||
// need actually to diff "extend" and "spackmark" given GB9, GB9a
|
||||
return EXTEND;
|
||||
case Character.COMBINING_SPACING_MARK:
|
||||
if (isExcludedSpacingMark(cp))
|
||||
return OTHER;
|
||||
@ -167,9 +220,11 @@ final class Grapheme {
|
||||
return RI;
|
||||
return OTHER;
|
||||
case Character.MODIFIER_LETTER:
|
||||
case Character.MODIFIER_SYMBOL:
|
||||
// WARNING:
|
||||
// not mentioned in #tr29 but listed in GraphemeBreakProperty.txt
|
||||
if (cp == 0xFF9E || cp == 0xFF9F)
|
||||
if (cp == 0xFF9E || cp == 0xFF9F ||
|
||||
cp >= 0x1F3FB && cp <= 0x1F3FF)
|
||||
return EXTEND;
|
||||
return OTHER;
|
||||
case Character.OTHER_LETTER:
|
||||
@ -199,6 +254,22 @@ final class Grapheme {
|
||||
return V;
|
||||
if (cp >= 0xD7CB && cp <= 0xD7FB)
|
||||
return T;
|
||||
|
||||
// Prepend
|
||||
switch (cp) {
|
||||
case 0x0D4E:
|
||||
case 0x111C2:
|
||||
case 0x111C3:
|
||||
case 0x11A3A:
|
||||
case 0x11A84:
|
||||
case 0x11A85:
|
||||
case 0x11A86:
|
||||
case 0x11A87:
|
||||
case 0x11A88:
|
||||
case 0x11A89:
|
||||
case 0x11D46:
|
||||
return PREPEND;
|
||||
}
|
||||
}
|
||||
return OTHER;
|
||||
}
|
||||
|
@ -540,7 +540,7 @@ import jdk.internal.util.ArraysSupport;
|
||||
* <p> This class is in conformance with Level 1 of <a
|
||||
* href="http://www.unicode.org/reports/tr18/"><i>Unicode Technical
|
||||
* Standard #18: Unicode Regular Expression</i></a>, plus RL2.1
|
||||
* Canonical Equivalents.
|
||||
* Canonical Equivalents and RL2.2 Extended Grapheme Clusters.
|
||||
* <p>
|
||||
* <b>Unicode escape sequences</b> such as <code>\u2014</code> in Java source code
|
||||
* are processed as described in section 3.3 of
|
||||
@ -1501,15 +1501,8 @@ public final class Pattern
|
||||
off++;
|
||||
continue;
|
||||
}
|
||||
int j = off + Character.charCount(ch0);
|
||||
int j = Grapheme.nextBoundary(src, off, limit);
|
||||
int ch1;
|
||||
while (j < limit) {
|
||||
ch1 = src.codePointAt(j);
|
||||
if (Grapheme.isBoundary(ch0, ch1))
|
||||
break;
|
||||
ch0 = ch1;
|
||||
j += Character.charCount(ch1);
|
||||
}
|
||||
String seq = src.substring(off, j);
|
||||
String nfd = Normalizer.normalize(seq, Normalizer.Form.NFD);
|
||||
off = j;
|
||||
@ -3975,14 +3968,7 @@ loop: for(int x=0, offset=0; x<nCodePoints; x++, offset+=len) {
|
||||
if (i < matcher.to) {
|
||||
int ch0 = Character.codePointAt(seq, i);
|
||||
int n = Character.charCount(ch0);
|
||||
int j = i + n;
|
||||
while (j < matcher.to) {
|
||||
int ch1 = Character.codePointAt(seq, j);
|
||||
if (Grapheme.isBoundary(ch0, ch1))
|
||||
break;
|
||||
ch0 = ch1;
|
||||
j += Character.charCount(ch1);
|
||||
}
|
||||
int j = Grapheme.nextBoundary(seq, i, matcher.to);
|
||||
if (i + n == j) { // single, assume nfc cp
|
||||
if (predicate.is(ch0))
|
||||
return next.match(matcher, j, seq);
|
||||
@ -4021,15 +4007,7 @@ loop: for(int x=0, offset=0; x<nCodePoints; x++, offset+=len) {
|
||||
static class XGrapheme extends Node {
|
||||
boolean match(Matcher matcher, int i, CharSequence seq) {
|
||||
if (i < matcher.to) {
|
||||
int ch0 = Character.codePointAt(seq, i);
|
||||
i += Character.charCount(ch0);
|
||||
while (i < matcher.to) {
|
||||
int ch1 = Character.codePointAt(seq, i);
|
||||
if (Grapheme.isBoundary(ch0, ch1))
|
||||
break;
|
||||
ch0 = ch1;
|
||||
i += Character.charCount(ch1);
|
||||
}
|
||||
i = Grapheme.nextBoundary(seq, i, matcher.to);
|
||||
return next.match(matcher, i, seq);
|
||||
}
|
||||
matcher.hitEnd = true;
|
||||
@ -4059,8 +4037,9 @@ loop: for(int x=0, offset=0; x<nCodePoints; x++, offset+=len) {
|
||||
}
|
||||
if (i < endIndex) {
|
||||
if (Character.isSurrogatePair(seq.charAt(i-1), seq.charAt(i)) ||
|
||||
!Grapheme.isBoundary(Character.codePointBefore(seq, i),
|
||||
Character.codePointAt(seq, i))) {
|
||||
Grapheme.nextBoundary(seq,
|
||||
i - Character.charCount(Character.codePointBefore(seq, i)),
|
||||
i + Character.charCount(Character.codePointAt(seq, i))) > i) {
|
||||
return false;
|
||||
}
|
||||
} else {
|
||||
|
@ -0,0 +1,501 @@
|
||||
/*
|
||||
* Copyright (c) 2019, 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
|
||||
* under the terms of the GNU General Public License version 2 only, as
|
||||
* published by the Free Software Foundation. Oracle designates this
|
||||
* particular file as subject to the "Classpath" exception as provided
|
||||
* by Oracle in the LICENSE file that accompanied this code.
|
||||
*
|
||||
* This code is distributed in the hope that it will be useful, but WITHOUT
|
||||
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
||||
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
|
||||
* version 2 for more details (a copy is included in the LICENSE file that
|
||||
* accompanied this code).
|
||||
*
|
||||
* You should have received a copy of the GNU General Public License version
|
||||
* 2 along with this work; if not, write to the Free Software Foundation,
|
||||
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
|
||||
*
|
||||
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
|
||||
* or visit www.oracle.com if you need additional information or have any
|
||||
* questions.
|
||||
*/
|
||||
// (c) 2018 and later: Unicode, Inc. and others.
|
||||
// License & terms of use: http://www.unicode.org/copyright.html#License
|
||||
|
||||
// created: 2018may10 Markus W. Scherer
|
||||
|
||||
package sun.text.normalizer;
|
||||
|
||||
import java.util.Iterator;
|
||||
import java.util.NoSuchElementException;
|
||||
|
||||
/**
|
||||
* Abstract map from Unicode code points (U+0000..U+10FFFF) to integer values.
|
||||
* This does not implement java.util.Map.
|
||||
*
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public abstract class CodePointMap implements Iterable<CodePointMap.Range> {
|
||||
/**
|
||||
* Selectors for how getRange() should report value ranges overlapping with surrogates.
|
||||
* Most users should use NORMAL.
|
||||
*
|
||||
* @see #getRange
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public enum RangeOption {
|
||||
/**
|
||||
* getRange() enumerates all same-value ranges as stored in the map.
|
||||
* Most users should use this option.
|
||||
*
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
NORMAL,
|
||||
/**
|
||||
* getRange() enumerates all same-value ranges as stored in the map,
|
||||
* except that lead surrogates (U+D800..U+DBFF) are treated as having the
|
||||
* surrogateValue, which is passed to getRange() as a separate parameter.
|
||||
* The surrogateValue is not transformed via filter().
|
||||
* See {@link Character#isHighSurrogate}.
|
||||
*
|
||||
* <p>Most users should use NORMAL instead.
|
||||
*
|
||||
* <p>This option is useful for maps that map surrogate code *units* to
|
||||
* special values optimized for UTF-16 string processing
|
||||
* or for special error behavior for unpaired surrogates,
|
||||
* but those values are not to be associated with the lead surrogate code *points*.
|
||||
*
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
FIXED_LEAD_SURROGATES,
|
||||
/**
|
||||
* getRange() enumerates all same-value ranges as stored in the map,
|
||||
* except that all surrogates (U+D800..U+DFFF) are treated as having the
|
||||
* surrogateValue, which is passed to getRange() as a separate parameter.
|
||||
* The surrogateValue is not transformed via filter().
|
||||
* See {@link Character#isSurrogate}.
|
||||
*
|
||||
* <p>Most users should use NORMAL instead.
|
||||
*
|
||||
* <p>This option is useful for maps that map surrogate code *units* to
|
||||
* special values optimized for UTF-16 string processing
|
||||
* or for special error behavior for unpaired surrogates,
|
||||
* but those values are not to be associated with the lead surrogate code *points*.
|
||||
*
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
FIXED_ALL_SURROGATES
|
||||
}
|
||||
|
||||
/**
|
||||
* Callback function interface: Modifies a map value.
|
||||
* Optionally called by getRange().
|
||||
* The modified value will be returned by the getRange() function.
|
||||
*
|
||||
* <p>Can be used to ignore some of the value bits,
|
||||
* make a filter for one of several values,
|
||||
* return a value index computed from the map value, etc.
|
||||
*
|
||||
* @see #getRange
|
||||
* @see #iterator
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public interface ValueFilter {
|
||||
/**
|
||||
* Modifies the map value.
|
||||
*
|
||||
* @param value map value
|
||||
* @return modified value
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public int apply(int value);
|
||||
}
|
||||
|
||||
/**
|
||||
* Range iteration result data.
|
||||
* Code points from start to end map to the same value.
|
||||
* The value may have been modified by {@link ValueFilter#apply(int)},
|
||||
* or it may be the surrogateValue if a RangeOption other than "normal" was used.
|
||||
*
|
||||
* @see #getRange
|
||||
* @see #iterator
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public static final class Range {
|
||||
private int start;
|
||||
private int end;
|
||||
private int value;
|
||||
|
||||
/**
|
||||
* Constructor. Sets start and end to -1 and value to 0.
|
||||
*
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public Range() {
|
||||
start = end = -1;
|
||||
value = 0;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return the start code point
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public int getStart() { return start; }
|
||||
/**
|
||||
* @return the (inclusive) end code point
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public int getEnd() { return end; }
|
||||
/**
|
||||
* @return the range value
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public int getValue() { return value; }
|
||||
/**
|
||||
* Sets the range. When using {@link #iterator()},
|
||||
* iteration will resume after the newly set end.
|
||||
*
|
||||
* @param start new start code point
|
||||
* @param end new end code point
|
||||
* @param value new value
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public void set(int start, int end, int value) {
|
||||
this.start = start;
|
||||
this.end = end;
|
||||
this.value = value;
|
||||
}
|
||||
}
|
||||
|
||||
private final class RangeIterator implements Iterator<Range> {
|
||||
private Range range = new Range();
|
||||
|
||||
@Override
|
||||
public boolean hasNext() {
|
||||
return -1 <= range.end && range.end < 0x10ffff;
|
||||
}
|
||||
|
||||
@Override
|
||||
public Range next() {
|
||||
if (getRange(range.end + 1, null, range)) {
|
||||
return range;
|
||||
} else {
|
||||
throw new NoSuchElementException();
|
||||
}
|
||||
}
|
||||
|
||||
@Override
|
||||
public final void remove() {
|
||||
throw new UnsupportedOperationException();
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Iterates over code points of a string and fetches map values.
|
||||
* This does not implement java.util.Iterator.
|
||||
*
|
||||
* <pre>
|
||||
* void onString(CodePointMap map, CharSequence s, int start) {
|
||||
* CodePointMap.StringIterator iter = map.stringIterator(s, start);
|
||||
* while (iter.next()) {
|
||||
* int end = iter.getIndex(); // code point from between start and end
|
||||
* useValue(s, start, end, iter.getCodePoint(), iter.getValue());
|
||||
* start = end;
|
||||
* }
|
||||
* }
|
||||
* </pre>
|
||||
*
|
||||
* <p>This class is not intended for public subclassing.
|
||||
*
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public class StringIterator {
|
||||
/**
|
||||
* @internal
|
||||
* @deprecated This API is ICU internal only.
|
||||
*/
|
||||
@Deprecated
|
||||
protected CharSequence s;
|
||||
/**
|
||||
* @internal
|
||||
* @deprecated This API is ICU internal only.
|
||||
*/
|
||||
@Deprecated
|
||||
protected int sIndex;
|
||||
/**
|
||||
* @internal
|
||||
* @deprecated This API is ICU internal only.
|
||||
*/
|
||||
@Deprecated
|
||||
protected int c;
|
||||
/**
|
||||
* @internal
|
||||
* @deprecated This API is ICU internal only.
|
||||
*/
|
||||
@Deprecated
|
||||
protected int value;
|
||||
|
||||
/**
|
||||
* @internal
|
||||
* @deprecated This API is ICU internal only.
|
||||
*/
|
||||
@Deprecated
|
||||
protected StringIterator(CharSequence s, int sIndex) {
|
||||
this.s = s;
|
||||
this.sIndex = sIndex;
|
||||
c = -1;
|
||||
value = 0;
|
||||
}
|
||||
|
||||
/**
|
||||
* Resets the iterator to a new string and/or a new string index.
|
||||
*
|
||||
* @param s string to iterate over
|
||||
* @param sIndex string index where the iteration will start
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public void reset(CharSequence s, int sIndex) {
|
||||
this.s = s;
|
||||
this.sIndex = sIndex;
|
||||
c = -1;
|
||||
value = 0;
|
||||
}
|
||||
|
||||
/**
|
||||
* Reads the next code point, post-increments the string index,
|
||||
* and gets a value from the map.
|
||||
* Sets an implementation-defined error value if the code point is an unpaired surrogate.
|
||||
*
|
||||
* @return true if the string index was not yet at the end of the string;
|
||||
* otherwise the iterator did not advance
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public boolean next() {
|
||||
if (sIndex >= s.length()) {
|
||||
return false;
|
||||
}
|
||||
c = Character.codePointAt(s, sIndex);
|
||||
sIndex += Character.charCount(c);
|
||||
value = get(c);
|
||||
return true;
|
||||
}
|
||||
|
||||
/**
|
||||
* Reads the previous code point, pre-decrements the string index,
|
||||
* and gets a value from the map.
|
||||
* Sets an implementation-defined error value if the code point is an unpaired surrogate.
|
||||
*
|
||||
* @return true if the string index was not yet at the start of the string;
|
||||
* otherwise the iterator did not advance
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public boolean previous() {
|
||||
if (sIndex <= 0) {
|
||||
return false;
|
||||
}
|
||||
c = Character.codePointBefore(s, sIndex);
|
||||
sIndex -= Character.charCount(c);
|
||||
value = get(c);
|
||||
return true;
|
||||
}
|
||||
/**
|
||||
* @return the string index
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public final int getIndex() { return sIndex; }
|
||||
/**
|
||||
* @return the code point
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public final int getCodePoint() { return c; }
|
||||
/**
|
||||
* @return the map value,
|
||||
* or an implementation-defined error value if
|
||||
* the code point is an unpaired surrogate
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public final int getValue() { return value; }
|
||||
}
|
||||
|
||||
/**
|
||||
* Protected no-args constructor.
|
||||
*
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
protected CodePointMap() {
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns the value for a code point as stored in the map, with range checking.
|
||||
* Returns an implementation-defined error value if c is not in the range 0..U+10FFFF.
|
||||
*
|
||||
* @param c the code point
|
||||
* @return the map value,
|
||||
* or an implementation-defined error value if
|
||||
* the code point is not in the range 0..U+10FFFF
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public abstract int get(int c);
|
||||
|
||||
/**
|
||||
* Sets the range object to a range of code points beginning with the start parameter.
|
||||
* The range start is the same as the start input parameter
|
||||
* (even if there are preceding code points that have the same value).
|
||||
* The range end is the last code point such that
|
||||
* all those from start to there have the same value.
|
||||
* Returns false if start is not 0..U+10FFFF.
|
||||
* Can be used to efficiently iterate over all same-value ranges in a map.
|
||||
* (This is normally faster than iterating over code points and get()ting each value,
|
||||
* but may be much slower than a data structure that stores ranges directly.)
|
||||
*
|
||||
* <p>If the {@link ValueFilter} parameter is not null, then
|
||||
* the value to be delivered is passed through that filter, and the return value is the end
|
||||
* of the range where all values are modified to the same actual value.
|
||||
* The value is unchanged if that parameter is null.
|
||||
*
|
||||
* <p>Example:
|
||||
* <pre>
|
||||
* int start = 0;
|
||||
* CodePointMap.Range range = new CodePointMap.Range();
|
||||
* while (map.getRange(start, null, range)) {
|
||||
* int end = range.getEnd();
|
||||
* int value = range.getValue();
|
||||
* // Work with the range start..end and its value.
|
||||
* start = end + 1;
|
||||
* }
|
||||
* </pre>
|
||||
*
|
||||
* @param start range start
|
||||
* @param filter an object that may modify the map data value,
|
||||
* or null if the values from the map are to be used unmodified
|
||||
* @param range the range object that will be set to the code point range and value
|
||||
* @return true if start is 0..U+10FFFF; otherwise no new range is fetched
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public abstract boolean getRange(int start, ValueFilter filter, Range range);
|
||||
|
||||
/**
|
||||
* Sets the range object to a range of code points beginning with the start parameter.
|
||||
* The range start is the same as the start input parameter
|
||||
* (even if there are preceding code points that have the same value).
|
||||
* The range end is the last code point such that
|
||||
* all those from start to there have the same value.
|
||||
* Returns false if start is not 0..U+10FFFF.
|
||||
*
|
||||
* <p>Same as the simpler {@link #getRange(int, ValueFilter, Range)} but optionally
|
||||
* modifies the range if it overlaps with surrogate code points.
|
||||
*
|
||||
* @param start range start
|
||||
* @param option defines whether surrogates are treated normally,
|
||||
* or as having the surrogateValue; usually {@link RangeOption#NORMAL}
|
||||
* @param surrogateValue value for surrogates; ignored if option=={@link RangeOption#NORMAL}
|
||||
* @param filter an object that may modify the map data value,
|
||||
* or null if the values from the map are to be used unmodified
|
||||
* @param range the range object that will be set to the code point range and value
|
||||
* @return true if start is 0..U+10FFFF; otherwise no new range is fetched
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public boolean getRange(int start, RangeOption option, int surrogateValue,
|
||||
ValueFilter filter, Range range) {
|
||||
assert option != null;
|
||||
if (!getRange(start, filter, range)) {
|
||||
return false;
|
||||
}
|
||||
if (option == RangeOption.NORMAL) {
|
||||
return true;
|
||||
}
|
||||
int surrEnd = option == RangeOption.FIXED_ALL_SURROGATES ? 0xdfff : 0xdbff;
|
||||
int end = range.end;
|
||||
if (end < 0xd7ff || start > surrEnd) {
|
||||
return true;
|
||||
}
|
||||
// The range overlaps with surrogates, or ends just before the first one.
|
||||
if (range.value == surrogateValue) {
|
||||
if (end >= surrEnd) {
|
||||
// Surrogates followed by a non-surrValue range,
|
||||
// or surrogates are part of a larger surrValue range.
|
||||
return true;
|
||||
}
|
||||
} else {
|
||||
if (start <= 0xd7ff) {
|
||||
range.end = 0xd7ff; // Non-surrValue range ends before surrValue surrogates.
|
||||
return true;
|
||||
}
|
||||
// Start is a surrogate with a non-surrValue code *unit* value.
|
||||
// Return a surrValue code *point* range.
|
||||
range.value = surrogateValue;
|
||||
if (end > surrEnd) {
|
||||
range.end = surrEnd; // Surrogate range ends before non-surrValue rest of range.
|
||||
return true;
|
||||
}
|
||||
}
|
||||
// See if the surrValue surrogate range can be merged with
|
||||
// an immediately following range.
|
||||
if (getRange(surrEnd + 1, filter, range) && range.value == surrogateValue) {
|
||||
range.start = start;
|
||||
return true;
|
||||
}
|
||||
range.start = start;
|
||||
range.end = surrEnd;
|
||||
range.value = surrogateValue;
|
||||
return true;
|
||||
}
|
||||
|
||||
/**
|
||||
* Convenience iterator over same-map-value code point ranges.
|
||||
* Same as looping over all ranges with {@link #getRange(int, ValueFilter, Range)}
|
||||
* without filtering.
|
||||
* Adjacent ranges have different map values.
|
||||
*
|
||||
* <p>The iterator always returns the same Range object.
|
||||
*
|
||||
* @return a Range iterator
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
@Override
|
||||
public Iterator<Range> iterator() {
|
||||
return new RangeIterator();
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns an iterator (not a java.util.Iterator) over code points of a string
|
||||
* for fetching map values.
|
||||
*
|
||||
* @param s string to iterate over
|
||||
* @param sIndex string index where the iteration will start
|
||||
* @return the iterator
|
||||
* @draft ICU 63
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public StringIterator stringIterator(CharSequence s, int sIndex) {
|
||||
return new StringIterator(s, sIndex);
|
||||
}
|
||||
}
|
1310
src/java.base/share/classes/sun/text/normalizer/CodePointTrie.java
Normal file
1310
src/java.base/share/classes/sun/text/normalizer/CodePointTrie.java
Normal file
File diff suppressed because it is too large
Load Diff
@ -1,5 +1,5 @@
|
||||
/*
|
||||
* Copyright (c) 2003, 2018, Oracle and/or its affiliates. All rights reserved.
|
||||
* Copyright (c) 2003, 2019, 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
|
||||
@ -119,10 +119,7 @@ public final class ICUBinary {
|
||||
} else if (capacity < 0x4000) {
|
||||
capacity *= 2; // Grow faster until we reach 16kB.
|
||||
}
|
||||
// TODO Java 6 replace new byte[] and arraycopy(): bytes = Arrays.copyOf(bytes, capacity);
|
||||
byte[] newBytes = new byte[capacity];
|
||||
System.arraycopy(bytes, 0, newBytes, 0, length);
|
||||
bytes = newBytes;
|
||||
bytes = Arrays.copyOf(bytes, capacity);
|
||||
bytes[length++] = (byte) nextByte;
|
||||
}
|
||||
}
|
||||
@ -264,6 +261,36 @@ public final class ICUBinary {
|
||||
}
|
||||
}
|
||||
|
||||
public static byte[] getBytes(ByteBuffer bytes, int length, int additionalSkipLength) {
|
||||
byte[] dest = new byte[length];
|
||||
bytes.get(dest);
|
||||
if (additionalSkipLength > 0) {
|
||||
skipBytes(bytes, additionalSkipLength);
|
||||
}
|
||||
return dest;
|
||||
}
|
||||
|
||||
public static String getString(ByteBuffer bytes, int length, int additionalSkipLength) {
|
||||
CharSequence cs = bytes.asCharBuffer();
|
||||
String s = cs.subSequence(0, length).toString();
|
||||
skipBytes(bytes, length * 2 + additionalSkipLength);
|
||||
return s;
|
||||
}
|
||||
|
||||
public static char[] getChars(ByteBuffer bytes, int length, int additionalSkipLength) {
|
||||
char[] dest = new char[length];
|
||||
bytes.asCharBuffer().get(dest);
|
||||
skipBytes(bytes, length * 2 + additionalSkipLength);
|
||||
return dest;
|
||||
}
|
||||
|
||||
public static int[] getInts(ByteBuffer bytes, int length, int additionalSkipLength) {
|
||||
int[] dest = new int[length];
|
||||
bytes.asIntBuffer().get(dest);
|
||||
skipBytes(bytes, length * 4 + additionalSkipLength);
|
||||
return dest;
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns a VersionInfo for the bytes in the compact version integer.
|
||||
*/
|
||||
|
@ -1,5 +1,5 @@
|
||||
/*
|
||||
* Copyright (c) 2015, 2018, Oracle and/or its affiliates. All rights reserved.
|
||||
* Copyright (c) 2015, 2019, 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
|
||||
@ -265,7 +265,7 @@ final class Norm2AllModes {
|
||||
private static final class Norm2AllModesSingleton {
|
||||
private Norm2AllModesSingleton(String name) {
|
||||
try {
|
||||
String DATA_FILE_NAME = "/sun/text/resources/" + name + ".icu";
|
||||
String DATA_FILE_NAME = "/sun/text/resources/" + name + ".nrm";
|
||||
NormalizerImpl impl=new NormalizerImpl().load(DATA_FILE_NAME);
|
||||
allModes=new Norm2AllModes(impl);
|
||||
} catch (RuntimeException e) {
|
||||
|
@ -1,5 +1,5 @@
|
||||
/*
|
||||
* Copyright (c) 2009, 2018, Oracle and/or its affiliates. All rights reserved.
|
||||
* Copyright (c) 2009, 2019, 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
|
||||
@ -61,7 +61,7 @@ public final class NormalizerImpl {
|
||||
return 0<=c && c<HANGUL_COUNT && c%JAMO_T_COUNT==0;
|
||||
}
|
||||
|
||||
/**
|
||||
/**
|
||||
* Decomposes c, which must be a Hangul syllable, into buffer
|
||||
* and returns the length of the decomposition (2 or 3).
|
||||
*/
|
||||
@ -145,8 +145,7 @@ public final class NormalizerImpl {
|
||||
insert(c, cc);
|
||||
}
|
||||
}
|
||||
// s must be in NFD, otherwise change the implementation.
|
||||
public void append(CharSequence s, int start, int limit,
|
||||
public void append(CharSequence s, int start, int limit, boolean isNFD,
|
||||
int leadCC, int trailCC) {
|
||||
if(start==limit) {
|
||||
return;
|
||||
@ -167,8 +166,11 @@ public final class NormalizerImpl {
|
||||
c=Character.codePointAt(s, start);
|
||||
start+=Character.charCount(c);
|
||||
if(start<limit) {
|
||||
// s must be in NFD, otherwise we need to use getCC().
|
||||
leadCC=getCCFromYesOrMaybe(impl.getNorm16(c));
|
||||
if (isNFD) {
|
||||
leadCC = getCCFromYesOrMaybe(impl.getNorm16(c));
|
||||
} else {
|
||||
leadCC = impl.getCC(impl.getNorm16(c));
|
||||
}
|
||||
} else {
|
||||
leadCC=trailCC;
|
||||
}
|
||||
@ -310,6 +312,12 @@ public final class NormalizerImpl {
|
||||
// TODO: Propose widening UTF16 methods that take char to take int.
|
||||
// TODO: Propose widening UTF16 methods that take String to take CharSequence.
|
||||
public static final class UTF16Plus {
|
||||
/**
|
||||
* Is this code point a lead surrogate (U+d800..U+dbff)?
|
||||
* @param c code unit or code point
|
||||
* @return true or false
|
||||
*/
|
||||
public static boolean isLeadSurrogate(int c) { return (c & 0xfffffc00) == 0xd800; }
|
||||
/**
|
||||
* Assuming c is a surrogate code point (UTF16.isSurrogate(c)),
|
||||
* is it a lead surrogate?
|
||||
@ -350,7 +358,7 @@ public final class NormalizerImpl {
|
||||
|
||||
private static final class IsAcceptable implements ICUBinary.Authenticate {
|
||||
public boolean isDataVersionAcceptable(byte version[]) {
|
||||
return version[0]==3;
|
||||
return version[0]==4;
|
||||
}
|
||||
}
|
||||
private static final IsAcceptable IS_ACCEPTABLE = new IsAcceptable();
|
||||
@ -387,8 +395,9 @@ public final class NormalizerImpl {
|
||||
// Read the normTrie.
|
||||
int offset=inIndexes[IX_NORM_TRIE_OFFSET];
|
||||
int nextOffset=inIndexes[IX_EXTRA_DATA_OFFSET];
|
||||
normTrie=Trie2_16.createFromSerialized(bytes);
|
||||
int trieLength=normTrie.getSerializedLength();
|
||||
int triePosition = bytes.position();
|
||||
normTrie = CodePointTrie.Fast16.fromBinary(bytes);
|
||||
int trieLength = bytes.position() - triePosition;
|
||||
if(trieLength>(nextOffset-offset)) {
|
||||
throw new InternalError("Normalizer2 data: not enough bytes for normTrie");
|
||||
}
|
||||
@ -398,13 +407,8 @@ public final class NormalizerImpl {
|
||||
offset=nextOffset;
|
||||
nextOffset=inIndexes[IX_SMALL_FCD_OFFSET];
|
||||
int numChars=(nextOffset-offset)/2;
|
||||
char[] chars;
|
||||
if(numChars!=0) {
|
||||
chars=new char[numChars];
|
||||
for(int i=0; i<numChars; ++i) {
|
||||
chars[i]=bytes.getChar();
|
||||
}
|
||||
maybeYesCompositions=new String(chars);
|
||||
maybeYesCompositions=ICUBinary.getString(bytes, numChars, 0);
|
||||
extraData=maybeYesCompositions.substring((MIN_NORMAL_MAYBE_YES-minMaybeYes)>>OFFSET_SHIFT);
|
||||
}
|
||||
|
||||
@ -422,8 +426,12 @@ public final class NormalizerImpl {
|
||||
return load(ICUBinary.getRequiredData(name));
|
||||
}
|
||||
|
||||
|
||||
public int getNorm16(int c) { return normTrie.get(c); }
|
||||
// The trie stores values for lead surrogate code *units*.
|
||||
// Surrogate code *points* are inert.
|
||||
public int getNorm16(int c) {
|
||||
return UTF16Plus.isLeadSurrogate(c) ? INERT : normTrie.get(c);
|
||||
}
|
||||
public int getRawNorm16(int c) { return normTrie.get(c); }
|
||||
public boolean isAlgorithmicNoNo(int norm16) { return limitNoNo<=norm16 && norm16<minMaybeYes; }
|
||||
public boolean isCompNo(int norm16) { return minNoNo<=norm16 && norm16<minMaybeYes; }
|
||||
public boolean isDecompYes(int norm16) { return norm16<minYesNo || minMaybeYes<=norm16; }
|
||||
@ -486,7 +494,7 @@ public final class NormalizerImpl {
|
||||
}
|
||||
// Maps to an isCompYesAndZeroCC.
|
||||
c=mapAlgorithmic(c, norm16);
|
||||
norm16=getNorm16(c);
|
||||
norm16=getRawNorm16(c);
|
||||
}
|
||||
}
|
||||
if(norm16<=minYesNo || isHangulLVT(norm16)) {
|
||||
@ -519,7 +527,7 @@ public final class NormalizerImpl {
|
||||
// Maps to an isCompYesAndZeroCC.
|
||||
decomp=c=mapAlgorithmic(c, norm16);
|
||||
// The mapping might decompose further.
|
||||
norm16 = getNorm16(c);
|
||||
norm16 = getRawNorm16(c);
|
||||
}
|
||||
if (norm16 < minYesNo) {
|
||||
if(decomp<0) {
|
||||
@ -641,27 +649,23 @@ public final class NormalizerImpl {
|
||||
// count code units below the minimum or with irrelevant data for the quick check
|
||||
for(prevSrc=src; src!=limit;) {
|
||||
if( (c=s.charAt(src))<minNoCP ||
|
||||
isMostDecompYesAndZeroCC(norm16=normTrie.getFromU16SingleLead((char)c))
|
||||
isMostDecompYesAndZeroCC(norm16=normTrie.bmpGet(c))
|
||||
) {
|
||||
++src;
|
||||
} else if(!UTF16.isSurrogate((char)c)) {
|
||||
} else if(!UTF16Plus.isLeadSurrogate(c)) {
|
||||
break;
|
||||
} else {
|
||||
char c2;
|
||||
if(UTF16Plus.isSurrogateLead(c)) {
|
||||
if((src+1)!=limit && Character.isLowSurrogate(c2=s.charAt(src+1))) {
|
||||
c=Character.toCodePoint((char)c, c2);
|
||||
if ((src + 1) != limit && Character.isLowSurrogate(c2 = s.charAt(src + 1))) {
|
||||
c = Character.toCodePoint((char)c, c2);
|
||||
norm16 = normTrie.suppGet(c);
|
||||
if (isMostDecompYesAndZeroCC(norm16)) {
|
||||
src += 2;
|
||||
} else {
|
||||
break;
|
||||
}
|
||||
} else /* trail surrogate */ {
|
||||
if(prevSrc<src && Character.isHighSurrogate(c2=s.charAt(src-1))) {
|
||||
--src;
|
||||
c=Character.toCodePoint(c2, (char)c);
|
||||
}
|
||||
}
|
||||
if(isMostDecompYesAndZeroCC(norm16=getNorm16(c))) {
|
||||
src+=Character.charCount(c);
|
||||
} else {
|
||||
break;
|
||||
++src; // unpaired lead surrogate: inert
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -721,7 +725,7 @@ public final class NormalizerImpl {
|
||||
c=Character.codePointAt(s, src);
|
||||
cc=getCC(getNorm16(c));
|
||||
};
|
||||
buffer.append(s, 0, src, firstCC, prevCC);
|
||||
buffer.append(s, 0, src, false, firstCC, prevCC);
|
||||
buffer.append(s, src, limit);
|
||||
}
|
||||
|
||||
@ -749,28 +753,22 @@ public final class NormalizerImpl {
|
||||
return true;
|
||||
}
|
||||
if( (c=s.charAt(src))<minNoMaybeCP ||
|
||||
isCompYesAndZeroCC(norm16=normTrie.getFromU16SingleLead((char)c))
|
||||
isCompYesAndZeroCC(norm16=normTrie.bmpGet(c))
|
||||
) {
|
||||
++src;
|
||||
} else {
|
||||
prevSrc = src++;
|
||||
if(!UTF16.isSurrogate((char)c)) {
|
||||
if (!UTF16Plus.isLeadSurrogate(c)) {
|
||||
break;
|
||||
} else {
|
||||
char c2;
|
||||
if(UTF16Plus.isSurrogateLead(c)) {
|
||||
if(src!=limit && Character.isLowSurrogate(c2=s.charAt(src))) {
|
||||
++src;
|
||||
c=Character.toCodePoint((char)c, c2);
|
||||
if (src != limit && Character.isLowSurrogate(c2 = s.charAt(src))) {
|
||||
++src;
|
||||
c = Character.toCodePoint((char)c, c2);
|
||||
norm16 = normTrie.suppGet(c);
|
||||
if (!isCompYesAndZeroCC(norm16)) {
|
||||
break;
|
||||
}
|
||||
} else /* trail surrogate */ {
|
||||
if(prevBoundary<prevSrc && Character.isHighSurrogate(c2=s.charAt(prevSrc-1))) {
|
||||
--prevSrc;
|
||||
c=Character.toCodePoint(c2, (char)c);
|
||||
}
|
||||
}
|
||||
if(!isCompYesAndZeroCC(norm16=getNorm16(c))) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -991,28 +989,22 @@ public final class NormalizerImpl {
|
||||
return (src<<1)|qcResult; // "yes" or "maybe"
|
||||
}
|
||||
if( (c=s.charAt(src))<minNoMaybeCP ||
|
||||
isCompYesAndZeroCC(norm16=normTrie.getFromU16SingleLead((char)c))
|
||||
isCompYesAndZeroCC(norm16=normTrie.bmpGet(c))
|
||||
) {
|
||||
++src;
|
||||
} else {
|
||||
prevSrc = src++;
|
||||
if(!UTF16.isSurrogate((char)c)) {
|
||||
if (!UTF16Plus.isLeadSurrogate(c)) {
|
||||
break;
|
||||
} else {
|
||||
char c2;
|
||||
if(UTF16Plus.isSurrogateLead(c)) {
|
||||
if(src!=limit && Character.isLowSurrogate(c2=s.charAt(src))) {
|
||||
++src;
|
||||
c=Character.toCodePoint((char)c, c2);
|
||||
if (src != limit && Character.isLowSurrogate(c2 = s.charAt(src))) {
|
||||
++src;
|
||||
c = Character.toCodePoint((char)c, c2);
|
||||
norm16 = normTrie.suppGet(c);
|
||||
if (!isCompYesAndZeroCC(norm16)) {
|
||||
break;
|
||||
}
|
||||
} else /* trail surrogate */ {
|
||||
if(prevBoundary<prevSrc && Character.isHighSurrogate(c2=s.charAt(prevSrc-1))) {
|
||||
--prevSrc;
|
||||
c=Character.toCodePoint(c2, (char)c);
|
||||
}
|
||||
}
|
||||
if(!isCompYesAndZeroCC(norm16=getNorm16(c))) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -1134,17 +1126,10 @@ public final class NormalizerImpl {
|
||||
prevFCD16=0;
|
||||
++src;
|
||||
} else {
|
||||
if(UTF16.isSurrogate((char)c)) {
|
||||
if (UTF16Plus.isLeadSurrogate(c)) {
|
||||
char c2;
|
||||
if(UTF16Plus.isSurrogateLead(c)) {
|
||||
if((src+1)!=limit && Character.isLowSurrogate(c2=s.charAt(src+1))) {
|
||||
c=Character.toCodePoint((char)c, c2);
|
||||
}
|
||||
} else /* trail surrogate */ {
|
||||
if(prevSrc<src && Character.isHighSurrogate(c2=s.charAt(src-1))) {
|
||||
--src;
|
||||
c=Character.toCodePoint(c2, (char)c);
|
||||
}
|
||||
if ((src + 1) != limit && Character.isLowSurrogate(c2 = s.charAt(src + 1))) {
|
||||
c = Character.toCodePoint((char)c, c2);
|
||||
}
|
||||
}
|
||||
if((fcd16=getFCD16FromNormData(c))<=0xff) {
|
||||
@ -1430,7 +1415,7 @@ public final class NormalizerImpl {
|
||||
}
|
||||
// Maps to an isCompYesAndZeroCC.
|
||||
c=mapAlgorithmic(c, norm16);
|
||||
norm16=getNorm16(c);
|
||||
norm16=getRawNorm16(c);
|
||||
}
|
||||
if (norm16 < minYesNo) {
|
||||
// c does not decompose
|
||||
@ -1451,7 +1436,7 @@ public final class NormalizerImpl {
|
||||
leadCC=0;
|
||||
}
|
||||
++mapping; // skip over the firstUnit
|
||||
buffer.append(extraData, mapping, mapping+length, leadCC, trailCC);
|
||||
buffer.append(extraData, mapping, mapping+length, true, leadCC, trailCC);
|
||||
}
|
||||
}
|
||||
|
||||
@ -1643,7 +1628,7 @@ public final class NormalizerImpl {
|
||||
// Is the composite a starter that combines forward?
|
||||
if((compositeAndFwd&1)!=0) {
|
||||
compositionsList=
|
||||
getCompositionsListForComposite(getNorm16(composite));
|
||||
getCompositionsListForComposite(getRawNorm16(composite));
|
||||
} else {
|
||||
compositionsList=-1;
|
||||
}
|
||||
@ -2196,9 +2181,8 @@ public final class NormalizerImpl {
|
||||
private int centerNoNoDelta;
|
||||
private int minMaybeYes;
|
||||
|
||||
private Trie2_16 normTrie;
|
||||
private CodePointTrie.Fast16 normTrie;
|
||||
private String maybeYesCompositions;
|
||||
private String extraData; // mappings and/or compositions for yesYes, yesNo & noNo characters
|
||||
private byte[] smallFCD; // [0x100] one bit per 32 BMP code points, set if any FCD!=0
|
||||
|
||||
}
|
||||
}
|
||||
|
Binary file not shown.
Binary file not shown.
BIN
src/java.base/share/classes/sun/text/resources/nfkc.nrm
Normal file
BIN
src/java.base/share/classes/sun/text/resources/nfkc.nrm
Normal file
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@ -1,38 +1,11 @@
|
||||
## International Components for Unicode (ICU4J) v62.1
|
||||
## International Components for Unicode (ICU4J) v64.2
|
||||
|
||||
### ICU4J License
|
||||
|
||||
```
|
||||
COPYRIGHT AND PERMISSION NOTICE (ICU 58 and later)
|
||||
|
||||
UNICODE, INC. LICENSE AGREEMENT - DATA FILES AND SOFTWARE
|
||||
Unicode Data Files include all data files under the directories
|
||||
http://www.unicode.org/Public/, http://www.unicode.org/reports/,
|
||||
http://www.unicode.org/cldr/data/,
|
||||
http://source.icu-project.org/repos/icu/, and
|
||||
http://www.unicode.org/utility/trac/browser/.
|
||||
|
||||
Unicode Data Files do not include PDF online code charts under the
|
||||
directory http://www.unicode.org/Public/.
|
||||
|
||||
Software includes any source code published in the Unicode Standard
|
||||
or under the directories
|
||||
http://www.unicode.org/Public/, http://www.unicode.org/reports/,
|
||||
http://www.unicode.org/cldr/data/,
|
||||
http://source.icu-project.org/repos/icu/, and
|
||||
http://www.unicode.org/utility/trac/browser/.
|
||||
|
||||
NOTICE TO USER: Carefully read the following legal agreement.
|
||||
BY DOWNLOADING, INSTALLING, COPYING OR OTHERWISE USING UNICODE INC.'S
|
||||
DATA FILES ("DATA FILES"), AND/OR SOFTWARE ("SOFTWARE"),
|
||||
YOU UNEQUIVOCALLY ACCEPT, AND AGREE TO BE BOUND BY, ALL OF THE
|
||||
TERMS AND CONDITIONS OF THIS AGREEMENT.
|
||||
IF YOU DO NOT AGREE, DO NOT DOWNLOAD, INSTALL, COPY, DISTRIBUTE OR USE
|
||||
THE DATA FILES OR SOFTWARE.
|
||||
|
||||
COPYRIGHT AND PERMISSION NOTICE
|
||||
|
||||
Copyright © 1991-2018 Unicode, Inc. All rights reserved.
|
||||
Distributed under the Terms of Use in http://www.unicode.org/copyright.html.
|
||||
Copyright © 1991-2019 Unicode, Inc. All rights reserved.
|
||||
Distributed under the Terms of Use in https://www.unicode.org/copyright.html.
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining
|
||||
a copy of the Unicode data files and any associated documentation
|
||||
@ -63,4 +36,354 @@ shall not be used in advertising or otherwise to promote the sale,
|
||||
use or other dealings in these Data Files or Software without prior
|
||||
written authorization of the copyright holder.
|
||||
|
||||
```
|
||||
---------------------
|
||||
|
||||
Third-Party Software Licenses
|
||||
|
||||
This section contains third-party software notices and/or additional
|
||||
terms for licensed third-party software components included within ICU
|
||||
libraries.
|
||||
|
||||
1. ICU License - ICU 1.8.1 to ICU 57.1
|
||||
|
||||
COPYRIGHT AND PERMISSION NOTICE
|
||||
|
||||
Copyright (c) 1995-2016 International Business Machines Corporation and others
|
||||
All rights reserved.
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining
|
||||
a copy of this software and associated documentation files (the
|
||||
"Software"), to deal in the Software without restriction, including
|
||||
without limitation the rights to use, copy, modify, merge, publish,
|
||||
distribute, and/or sell copies of the Software, and to permit persons
|
||||
to whom the Software is furnished to do so, provided that the above
|
||||
copyright notice(s) and this permission notice appear in all copies of
|
||||
the Software and that both the above copyright notice(s) and this
|
||||
permission notice appear in supporting documentation.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT
|
||||
OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR
|
||||
HOLDERS INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY
|
||||
SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER
|
||||
RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF
|
||||
CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
|
||||
CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
|
||||
|
||||
Except as contained in this notice, the name of a copyright holder
|
||||
shall not be used in advertising or otherwise to promote the sale, use
|
||||
or other dealings in this Software without prior written authorization
|
||||
of the copyright holder.
|
||||
|
||||
All trademarks and registered trademarks mentioned herein are the
|
||||
property of their respective owners.
|
||||
|
||||
2. Chinese/Japanese Word Break Dictionary Data (cjdict.txt)
|
||||
|
||||
# The Google Chrome software developed by Google is licensed under
|
||||
# the BSD license. Other software included in this distribution is
|
||||
# provided under other licenses, as set forth below.
|
||||
#
|
||||
# The BSD License
|
||||
# http://opensource.org/licenses/bsd-license.php
|
||||
# Copyright (C) 2006-2008, Google Inc.
|
||||
#
|
||||
# All rights reserved.
|
||||
#
|
||||
# Redistribution and use in source and binary forms, with or without
|
||||
# modification, are permitted provided that the following conditions are met:
|
||||
#
|
||||
# Redistributions of source code must retain the above copyright notice,
|
||||
# this list of conditions and the following disclaimer.
|
||||
# Redistributions in binary form must reproduce the above
|
||||
# copyright notice, this list of conditions and the following
|
||||
# disclaimer in the documentation and/or other materials provided with
|
||||
# the distribution.
|
||||
# Neither the name of Google Inc. nor the names of its
|
||||
# contributors may be used to endorse or promote products derived from
|
||||
# this software without specific prior written permission.
|
||||
#
|
||||
#
|
||||
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
|
||||
# CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
|
||||
# INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
|
||||
# MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
||||
# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
|
||||
# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
||||
# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
||||
# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
|
||||
# BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
|
||||
# LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
|
||||
# NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
||||
# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
#
|
||||
#
|
||||
# The word list in cjdict.txt are generated by combining three word lists
|
||||
# listed below with further processing for compound word breaking. The
|
||||
# frequency is generated with an iterative training against Google web
|
||||
# corpora.
|
||||
#
|
||||
# * Libtabe (Chinese)
|
||||
# - https://sourceforge.net/project/?group_id=1519
|
||||
# - Its license terms and conditions are shown below.
|
||||
#
|
||||
# * IPADIC (Japanese)
|
||||
# - http://chasen.aist-nara.ac.jp/chasen/distribution.html
|
||||
# - Its license terms and conditions are shown below.
|
||||
#
|
||||
# ---------COPYING.libtabe ---- BEGIN--------------------
|
||||
#
|
||||
# /*
|
||||
# * Copyright (c) 1999 TaBE Project.
|
||||
# * Copyright (c) 1999 Pai-Hsiang Hsiao.
|
||||
# * All rights reserved.
|
||||
# *
|
||||
# * Redistribution and use in source and binary forms, with or without
|
||||
# * modification, are permitted provided that the following conditions
|
||||
# * are met:
|
||||
# *
|
||||
# * . Redistributions of source code must retain the above copyright
|
||||
# * notice, this list of conditions and the following disclaimer.
|
||||
# * . Redistributions in binary form must reproduce the above copyright
|
||||
# * notice, this list of conditions and the following disclaimer in
|
||||
# * the documentation and/or other materials provided with the
|
||||
# * distribution.
|
||||
# * . Neither the name of the TaBE Project nor the names of its
|
||||
# * contributors may be used to endorse or promote products derived
|
||||
# * from this software without specific prior written permission.
|
||||
# *
|
||||
# * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
# * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
# * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
|
||||
# * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
|
||||
# * REGENTS OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
|
||||
# * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
|
||||
# * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
||||
# * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
||||
# * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
|
||||
# * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
||||
# * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
|
||||
# * OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
# */
|
||||
#
|
||||
# /*
|
||||
# * Copyright (c) 1999 Computer Systems and Communication Lab,
|
||||
# * Institute of Information Science, Academia
|
||||
# * Sinica. All rights reserved.
|
||||
# *
|
||||
# * Redistribution and use in source and binary forms, with or without
|
||||
# * modification, are permitted provided that the following conditions
|
||||
# * are met:
|
||||
# *
|
||||
# * . Redistributions of source code must retain the above copyright
|
||||
# * notice, this list of conditions and the following disclaimer.
|
||||
# * . Redistributions in binary form must reproduce the above copyright
|
||||
# * notice, this list of conditions and the following disclaimer in
|
||||
# * the documentation and/or other materials provided with the
|
||||
# * distribution.
|
||||
# * . Neither the name of the Computer Systems and Communication Lab
|
||||
# * nor the names of its contributors may be used to endorse or
|
||||
# * promote products derived from this software without specific
|
||||
# * prior written permission.
|
||||
# *
|
||||
# * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
# * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
# * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
|
||||
# * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
|
||||
# * REGENTS OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
|
||||
# * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
|
||||
# * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
||||
# * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
||||
# * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
|
||||
# * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
||||
# * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
|
||||
# * OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
# */
|
||||
#
|
||||
# Copyright 1996 Chih-Hao Tsai @ Beckman Institute,
|
||||
# University of Illinois
|
||||
# c-tsai4@uiuc.edu http://casper.beckman.uiuc.edu/~c-tsai4
|
||||
#
|
||||
# ---------------COPYING.libtabe-----END--------------------------------
|
||||
#
|
||||
#
|
||||
# ---------------COPYING.ipadic-----BEGIN-------------------------------
|
||||
#
|
||||
# Copyright 2000, 2001, 2002, 2003 Nara Institute of Science
|
||||
# and Technology. All Rights Reserved.
|
||||
#
|
||||
# Use, reproduction, and distribution of this software is permitted.
|
||||
# Any copy of this software, whether in its original form or modified,
|
||||
# must include both the above copyright notice and the following
|
||||
# paragraphs.
|
||||
#
|
||||
# Nara Institute of Science and Technology (NAIST),
|
||||
# the copyright holders, disclaims all warranties with regard to this
|
||||
# software, including all implied warranties of merchantability and
|
||||
# fitness, in no event shall NAIST be liable for
|
||||
# any special, indirect or consequential damages or any damages
|
||||
# whatsoever resulting from loss of use, data or profits, whether in an
|
||||
# action of contract, negligence or other tortuous action, arising out
|
||||
# of or in connection with the use or performance of this software.
|
||||
#
|
||||
# A large portion of the dictionary entries
|
||||
# originate from ICOT Free Software. The following conditions for ICOT
|
||||
# Free Software applies to the current dictionary as well.
|
||||
#
|
||||
# Each User may also freely distribute the Program, whether in its
|
||||
# original form or modified, to any third party or parties, PROVIDED
|
||||
# that the provisions of Section 3 ("NO WARRANTY") will ALWAYS appear
|
||||
# on, or be attached to, the Program, which is distributed substantially
|
||||
# in the same form as set out herein and that such intended
|
||||
# distribution, if actually made, will neither violate or otherwise
|
||||
# contravene any of the laws and regulations of the countries having
|
||||
# jurisdiction over the User or the intended distribution itself.
|
||||
#
|
||||
# NO WARRANTY
|
||||
#
|
||||
# The program was produced on an experimental basis in the course of the
|
||||
# research and development conducted during the project and is provided
|
||||
# to users as so produced on an experimental basis. Accordingly, the
|
||||
# program is provided without any warranty whatsoever, whether express,
|
||||
# implied, statutory or otherwise. The term "warranty" used herein
|
||||
# includes, but is not limited to, any warranty of the quality,
|
||||
# performance, merchantability and fitness for a particular purpose of
|
||||
# the program and the nonexistence of any infringement or violation of
|
||||
# any right of any third party.
|
||||
#
|
||||
# Each user of the program will agree and understand, and be deemed to
|
||||
# have agreed and understood, that there is no warranty whatsoever for
|
||||
# the program and, accordingly, the entire risk arising from or
|
||||
# otherwise connected with the program is assumed by the user.
|
||||
#
|
||||
# Therefore, neither ICOT, the copyright holder, or any other
|
||||
# organization that participated in or was otherwise related to the
|
||||
# development of the program and their respective officials, directors,
|
||||
# officers and other employees shall be held liable for any and all
|
||||
# damages, including, without limitation, general, special, incidental
|
||||
# and consequential damages, arising out of or otherwise in connection
|
||||
# with the use or inability to use the program or any product, material
|
||||
# or result produced or otherwise obtained by using the program,
|
||||
# regardless of whether they have been advised of, or otherwise had
|
||||
# knowledge of, the possibility of such damages at any time during the
|
||||
# project or thereafter. Each user will be deemed to have agreed to the
|
||||
# foregoing by his or her commencement of use of the program. The term
|
||||
# "use" as used herein includes, but is not limited to, the use,
|
||||
# modification, copying and distribution of the program and the
|
||||
# production of secondary products from the program.
|
||||
#
|
||||
# In the case where the program, whether in its original form or
|
||||
# modified, was distributed or delivered to or received by a user from
|
||||
# any person, organization or entity other than ICOT, unless it makes or
|
||||
# grants independently of ICOT any specific warranty to the user in
|
||||
# writing, such person, organization or entity, will also be exempted
|
||||
# from and not be held liable to the user for any such damages as noted
|
||||
# above as far as the program is concerned.
|
||||
#
|
||||
# ---------------COPYING.ipadic-----END----------------------------------
|
||||
|
||||
3. Lao Word Break Dictionary Data (laodict.txt)
|
||||
|
||||
# Copyright (c) 2013 International Business Machines Corporation
|
||||
# and others. All Rights Reserved.
|
||||
#
|
||||
# Project: http://code.google.com/p/lao-dictionary/
|
||||
# Dictionary: http://lao-dictionary.googlecode.com/git/Lao-Dictionary.txt
|
||||
# License: http://lao-dictionary.googlecode.com/git/Lao-Dictionary-LICENSE.txt
|
||||
# (copied below)
|
||||
#
|
||||
# This file is derived from the above dictionary, with slight
|
||||
# modifications.
|
||||
# ----------------------------------------------------------------------
|
||||
# Copyright (C) 2013 Brian Eugene Wilson, Robert Martin Campbell.
|
||||
# All rights reserved.
|
||||
#
|
||||
# Redistribution and use in source and binary forms, with or without
|
||||
# modification,
|
||||
# are permitted provided that the following conditions are met:
|
||||
#
|
||||
#
|
||||
# Redistributions of source code must retain the above copyright notice, this
|
||||
# list of conditions and the following disclaimer. Redistributions in
|
||||
# binary form must reproduce the above copyright notice, this list of
|
||||
# conditions and the following disclaimer in the documentation and/or
|
||||
# other materials provided with the distribution.
|
||||
#
|
||||
#
|
||||
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
|
||||
# FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
|
||||
# COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT,
|
||||
# INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
|
||||
# (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
||||
# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
||||
# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
|
||||
# STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
||||
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
|
||||
# OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
# --------------------------------------------------------------------------
|
||||
|
||||
4. Burmese Word Break Dictionary Data (burmesedict.txt)
|
||||
|
||||
# Copyright (c) 2014 International Business Machines Corporation
|
||||
# and others. All Rights Reserved.
|
||||
#
|
||||
# This list is part of a project hosted at:
|
||||
# github.com/kanyawtech/myanmar-karen-word-lists
|
||||
#
|
||||
# --------------------------------------------------------------------------
|
||||
# Copyright (c) 2013, LeRoy Benjamin Sharon
|
||||
# All rights reserved.
|
||||
#
|
||||
# Redistribution and use in source and binary forms, with or without
|
||||
# modification, are permitted provided that the following conditions
|
||||
# are met: Redistributions of source code must retain the above
|
||||
# copyright notice, this list of conditions and the following
|
||||
# disclaimer. Redistributions in binary form must reproduce the
|
||||
# above copyright notice, this list of conditions and the following
|
||||
# disclaimer in the documentation and/or other materials provided
|
||||
# with the distribution.
|
||||
#
|
||||
# Neither the name Myanmar Karen Word Lists, nor the names of its
|
||||
# contributors may be used to endorse or promote products derived
|
||||
# from this software without specific prior written permission.
|
||||
#
|
||||
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
|
||||
# CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
|
||||
# INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
|
||||
# MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
||||
# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS
|
||||
# BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
|
||||
# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
|
||||
# TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
|
||||
# ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR
|
||||
# TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF
|
||||
# THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
||||
# SUCH DAMAGE.
|
||||
# --------------------------------------------------------------------------
|
||||
|
||||
5. Time Zone Database
|
||||
|
||||
ICU uses the public domain data and code derived from Time Zone
|
||||
Database for its time zone support. The ownership of the TZ database
|
||||
is explained in BCP 175: Procedure for Maintaining the Time Zone
|
||||
Database section 7.
|
||||
|
||||
# 7. Database Ownership
|
||||
#
|
||||
# The TZ database itself is not an IETF Contribution or an IETF
|
||||
# document. Rather it is a pre-existing and regularly updated work
|
||||
# that is in the public domain, and is intended to remain in the
|
||||
# public domain. Therefore, BCPs 78 [RFC5378] and 79 [RFC3979] do
|
||||
# not apply to the TZ Database or contributions that individuals make
|
||||
# to it. Should any claims be made and substantiated against the TZ
|
||||
# Database, the organization that is providing the IANA
|
||||
# Considerations defined in this RFC, under the memorandum of
|
||||
# understanding with the IETF, currently ICANN, may act in accordance
|
||||
# with all competent court orders. No ownership claims will be made
|
||||
# by ICANN or the IETF Trust on the database or the code. Any person
|
||||
# making a contribution to the database or code waives all rights to
|
||||
# future claims in that contribution or in the TZ Database.
|
||||
|
@ -1,25 +1,11 @@
|
||||
## The Unicode Standard, Unicode Character Database, Version 11.0.0
|
||||
|
||||
## The Unicode Standard, Unicode Character Database, Version 12.1.0
|
||||
|
||||
### Unicode Character Database
|
||||
|
||||
```
|
||||
|
||||
UNICODE, INC. LICENSE AGREEMENT - DATA FILES AND SOFTWARE
|
||||
Unicode Data Files include all data files under the directories
|
||||
http://www.unicode.org/Public/, http://www.unicode.org/reports/,
|
||||
http://www.unicode.org/cldr/data/,
|
||||
http://source.icu-project.org/repos/icu/, and
|
||||
http://www.unicode.org/utility/trac/browser/.
|
||||
|
||||
Unicode Data Files do not include PDF online code charts under the
|
||||
directory http://www.unicode.org/Public/.
|
||||
|
||||
Software includes any source code published in the Unicode Standard
|
||||
or under the directories
|
||||
http://www.unicode.org/Public/, http://www.unicode.org/reports/,
|
||||
http://www.unicode.org/cldr/data/,
|
||||
http://source.icu-project.org/repos/icu/, and
|
||||
http://www.unicode.org/utility/trac/browser/.
|
||||
See Terms of Use for definitions of Unicode Inc.'s
|
||||
Data Files and Software.
|
||||
|
||||
NOTICE TO USER: Carefully read the following legal agreement.
|
||||
BY DOWNLOADING, INSTALLING, COPYING OR OTHERWISE USING UNICODE INC.'S
|
||||
@ -31,8 +17,8 @@ THE DATA FILES OR SOFTWARE.
|
||||
|
||||
COPYRIGHT AND PERMISSION NOTICE
|
||||
|
||||
Copyright © 1991-2018 Unicode, Inc. All rights reserved.
|
||||
Distributed under the Terms of Use in http://www.unicode.org/copyright.html.
|
||||
Copyright © 1991-2019 Unicode, Inc. All rights reserved.
|
||||
Distributed under the Terms of Use in https://www.unicode.org/copyright.html.
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining
|
||||
a copy of the Unicode data files and any associated documentation
|
||||
@ -62,5 +48,3 @@ Except as contained in this notice, the name of a copyright holder
|
||||
shall not be used in advertising or otherwise to promote the sale,
|
||||
use or other dealings in these Data Files or Software without prior
|
||||
written authorization of the copyright holder.
|
||||
|
||||
```
|
||||
|
@ -1,5 +1,5 @@
|
||||
/*
|
||||
* Copyright (c) 2018, Oracle and/or its affiliates. All rights reserved.
|
||||
* Copyright (c) 2018, 2019, 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
|
||||
@ -23,17 +23,16 @@
|
||||
|
||||
/*
|
||||
* @test
|
||||
* @bug 8202771
|
||||
* @bug 8202771 8221431
|
||||
* @summary Check j.l.Character.isDigit/isLetter/isLetterOrDigit/isSpaceChar
|
||||
* /isWhitespace/isTitleCase/isISOControl/isIdentifierIgnorable
|
||||
* /isJavaIdentifierStart/isJavaIdentifierPart/isUnicodeIdentifierStart
|
||||
* /isUnicodeIdentifierPart
|
||||
* @library /lib/testlibrary/java/lang
|
||||
* @run main CharPropTest
|
||||
*/
|
||||
|
||||
import java.nio.file.Files;
|
||||
import java.nio.file.Path;
|
||||
import java.nio.file.Paths;
|
||||
import java.util.stream.Stream;
|
||||
|
||||
public class CharPropTest {
|
||||
@ -42,9 +41,7 @@ public class CharPropTest {
|
||||
private static boolean isRange = false;
|
||||
|
||||
public static void main(String[] args) throws Exception {
|
||||
Path path = Paths.get(System.getProperty("test.src", "."),
|
||||
"UnicodeData.txt");
|
||||
try (Stream<String> lines = Files.lines(path)) {
|
||||
try (Stream<String> lines = Files.lines(UCDFiles.UNICODE_DATA)) {
|
||||
lines.map(String::trim)
|
||||
.filter(line -> line.length() != 0 && line.charAt(0) != '#')
|
||||
.forEach(line -> handleOneLine(line));
|
||||
|
@ -1,5 +1,5 @@
|
||||
/*
|
||||
* Copyright (c) 2011, 2015, Oracle and/or its affiliates. All rights reserved.
|
||||
* Copyright (c) 2011, 2019, 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
|
||||
@ -24,8 +24,9 @@
|
||||
|
||||
/**
|
||||
* @test
|
||||
* @bug 7037261 7070436 7198195 8032446 8072600
|
||||
* @bug 7037261 7070436 7198195 8032446 8072600 8221431
|
||||
* @summary Check j.l.Character.isLowerCase/isUppercase/isAlphabetic/isIdeographic
|
||||
* @library /lib/testlibrary/java/lang
|
||||
*/
|
||||
|
||||
import java.util.regex.*;
|
||||
@ -36,7 +37,7 @@ import static java.lang.Character.*;
|
||||
public class CheckProp {
|
||||
|
||||
public static void main(String[] args) throws IOException {
|
||||
File fPropList = new File(System.getProperty("test.src", "."), "PropList.txt");
|
||||
File fPropList = UCDFiles.PROP_LIST.toFile();
|
||||
int i, j;
|
||||
BufferedReader sbfr = new BufferedReader(new FileReader(fPropList));
|
||||
Matcher m = Pattern.compile("(\\p{XDigit}+)(?:\\.{2}(\\p{XDigit}+))?\\s*;\\s+(\\w+)\\s+#.*").matcher("");
|
||||
|
@ -1,5 +1,5 @@
|
||||
/*
|
||||
* Copyright (c) 2010, 2015, Oracle and/or its affiliates. All rights reserved.
|
||||
* Copyright (c) 2010, 2019, 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
|
||||
@ -23,8 +23,9 @@
|
||||
|
||||
/**
|
||||
* @test
|
||||
* @bug 6945564 6959267 7033561 7070436 7198195 8032446 8072600
|
||||
* @bug 6945564 6959267 7033561 7070436 7198195 8032446 8072600 8221431
|
||||
* @summary Check that the j.l.Character.UnicodeScript
|
||||
* @library /lib/testlibrary/java/lang
|
||||
*/
|
||||
|
||||
import java.io.*;
|
||||
@ -38,8 +39,8 @@ public class CheckScript {
|
||||
File fScripts;
|
||||
File fAliases;
|
||||
if (args.length == 0) {
|
||||
fScripts = new File(System.getProperty("test.src", "."), "Scripts.txt");
|
||||
fAliases = new File(System.getProperty("test.src", "."), "PropertyValueAliases.txt");
|
||||
fScripts = UCDFiles.SCRIPTS.toFile();
|
||||
fAliases = UCDFiles.PROPERTY_VALUE_ALIASES.toFile();
|
||||
} else if (args.length == 2) {
|
||||
fScripts = new File(args[0]);
|
||||
fAliases = new File(args[1]);
|
||||
|
@ -1,5 +1,5 @@
|
||||
/*
|
||||
* Copyright (c) 2018, Oracle and/or its affiliates. All rights reserved.
|
||||
* Copyright (c) 2018, 2019, 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
|
||||
@ -25,11 +25,12 @@
|
||||
|
||||
/**
|
||||
* @test
|
||||
* @bug 4114080 6565620 6959267 7070436 7198195 8032446 8072600
|
||||
* @bug 4114080 6565620 6959267 7070436 7198195 8032446 8072600 8221431
|
||||
* @summary Make sure the attributes of Unicode characters, as
|
||||
* returned by the Character API, are as expected. Do this by
|
||||
* comparing them to a baseline file together with a list of
|
||||
* known diffs.
|
||||
* @library /lib/testlibrary/java/lang
|
||||
* @build UnicodeSpec CharCheck
|
||||
* @run main CheckUnicode
|
||||
* @author Alan Liu
|
||||
@ -41,40 +42,18 @@ import java.io.*;
|
||||
public class CheckUnicode {
|
||||
public static void main(String args[]) throws Exception {
|
||||
|
||||
// 1. Check that the dumped property files for planes 0, 1, 2, 3, 14, 15, and 16
|
||||
// are the same as in the current Character properties.
|
||||
int[] planes = {0, 1, 2, 3, 14, 15, 16};
|
||||
String[] fileNames = {"charprop00.bin", "charprop01.bin", "charprop02.bin", "charprop03.bin",
|
||||
"charprop0E.bin", "charprop0F.bin", "charprop10.bin" };
|
||||
|
||||
// Read in the Unicode 4.0 data
|
||||
|
||||
for (int x=0; x < planes.length && x < fileNames.length; ++x) {
|
||||
File unicodeProp = new File(System.getProperty("test.src", "."), fileNames[x]);
|
||||
ObjectInputStream ois = new ObjectInputStream(new FileInputStream(unicodeProp));
|
||||
// Find differences -- should be none
|
||||
int diffs = CharCheck.load(planes[x], ois);
|
||||
if (diffs != 0) {
|
||||
throw new RuntimeException("Bug 4114080 - Unicode properties have changed " +
|
||||
"in an unexpected way");
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
// 2. Check that the current 4.0 spec file is handled by the current
|
||||
// 1. Check that the current 12.1 spec file is handled by the current
|
||||
// version of Character.
|
||||
File unicodeSpec = new File(System.getProperty("test.src", "."), "UnicodeData.txt");
|
||||
for (int x=0; x<planes.length; ++x) {
|
||||
int diffs = CharCheck.check(planes[x], unicodeSpec);
|
||||
if (diffs != 0) {
|
||||
throw new RuntimeException("Bug 4114080 - Unicode properties have changed " +
|
||||
"in an unexpected way");
|
||||
}
|
||||
}
|
||||
File unicodeSpec = UCDFiles.UNICODE_DATA.toFile();
|
||||
for (int x = 0; x < 16; ++x) {
|
||||
int diffs = CharCheck.check(x, unicodeSpec);
|
||||
if (diffs != 0) {
|
||||
throw new RuntimeException("Unicode properties have changed " +
|
||||
"in an unexpected way");
|
||||
}
|
||||
}
|
||||
|
||||
// 3. Check that Java identifiers are recognized correctly.
|
||||
// 2. Check that Java identifiers are recognized correctly.
|
||||
// test a few characters that are good id starts
|
||||
char[] idStartChar = {'$', '\u20AC', 'a', 'A', 'z', 'Z', '_', '\u0E3F',
|
||||
'\u1004', '\u10A0', '\u3400', '\u4E00', '\uAC00' };
|
||||
@ -104,8 +83,5 @@ public class CheckUnicode {
|
||||
"should not be start characters.");
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
}
|
||||
}
|
||||
|
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@ -1,281 +0,0 @@
|
||||
# SpecialCasing-11.0.0.txt
|
||||
# Date: 2018-02-22, 06:16:47 GMT
|
||||
# Copyright (c) 2018 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
|
||||
#
|
||||
# Unicode Character Database
|
||||
# For documentation, see http://www.unicode.org/reports/tr44/
|
||||
#
|
||||
# Special Casing
|
||||
#
|
||||
# This file is a supplement to the UnicodeData.txt file. It does not define any
|
||||
# properties, but rather provides additional information about the casing of
|
||||
# Unicode characters, for situations when casing incurs a change in string length
|
||||
# or is dependent on context or locale. For compatibility, the UnicodeData.txt
|
||||
# file only contains simple case mappings for characters where they are one-to-one
|
||||
# and independent of context and language. The data in this file, combined with
|
||||
# the simple case mappings in UnicodeData.txt, defines the full case mappings
|
||||
# Lowercase_Mapping (lc), Titlecase_Mapping (tc), and Uppercase_Mapping (uc).
|
||||
#
|
||||
# Note that the preferred mechanism for defining tailored casing operations is
|
||||
# the Unicode Common Locale Data Repository (CLDR). For more information, see the
|
||||
# discussion of case mappings and case algorithms in the Unicode Standard.
|
||||
#
|
||||
# All code points not listed in this file that do not have a simple case mappings
|
||||
# in UnicodeData.txt map to themselves.
|
||||
# ================================================================================
|
||||
# Format
|
||||
# ================================================================================
|
||||
# The entries in this file are in the following machine-readable format:
|
||||
#
|
||||
# <code>; <lower>; <title>; <upper>; (<condition_list>;)? # <comment>
|
||||
#
|
||||
# <code>, <lower>, <title>, and <upper> provide the respective full case mappings
|
||||
# of <code>, expressed as character values in hex. If there is more than one character,
|
||||
# they are separated by spaces. Other than as used to separate elements, spaces are
|
||||
# to be ignored.
|
||||
#
|
||||
# The <condition_list> is optional. Where present, it consists of one or more language IDs
|
||||
# or casing contexts, separated by spaces. In these conditions:
|
||||
# - A condition list overrides the normal behavior if all of the listed conditions are true.
|
||||
# - The casing context is always the context of the characters in the original string,
|
||||
# NOT in the resulting string.
|
||||
# - Case distinctions in the condition list are not significant.
|
||||
# - Conditions preceded by "Not_" represent the negation of the condition.
|
||||
# The condition list is not represented in the UCD as a formal property.
|
||||
#
|
||||
# A language ID is defined by BCP 47, with '-' and '_' treated equivalently.
|
||||
#
|
||||
# A casing context for a character is defined by Section 3.13 Default Case Algorithms
|
||||
# of The Unicode Standard.
|
||||
#
|
||||
# Parsers of this file must be prepared to deal with future additions to this format:
|
||||
# * Additional contexts
|
||||
# * Additional fields
|
||||
# ================================================================================
|
||||
|
||||
# ================================================================================
|
||||
# Unconditional mappings
|
||||
# ================================================================================
|
||||
|
||||
# The German es-zed is special--the normal mapping is to SS.
|
||||
# Note: the titlecase should never occur in practice. It is equal to titlecase(uppercase(<es-zed>))
|
||||
|
||||
00DF; 00DF; 0053 0073; 0053 0053; # LATIN SMALL LETTER SHARP S
|
||||
|
||||
# Preserve canonical equivalence for I with dot. Turkic is handled below.
|
||||
|
||||
0130; 0069 0307; 0130; 0130; # LATIN CAPITAL LETTER I WITH DOT ABOVE
|
||||
|
||||
# Ligatures
|
||||
|
||||
FB00; FB00; 0046 0066; 0046 0046; # LATIN SMALL LIGATURE FF
|
||||
FB01; FB01; 0046 0069; 0046 0049; # LATIN SMALL LIGATURE FI
|
||||
FB02; FB02; 0046 006C; 0046 004C; # LATIN SMALL LIGATURE FL
|
||||
FB03; FB03; 0046 0066 0069; 0046 0046 0049; # LATIN SMALL LIGATURE FFI
|
||||
FB04; FB04; 0046 0066 006C; 0046 0046 004C; # LATIN SMALL LIGATURE FFL
|
||||
FB05; FB05; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE LONG S T
|
||||
FB06; FB06; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE ST
|
||||
|
||||
0587; 0587; 0535 0582; 0535 0552; # ARMENIAN SMALL LIGATURE ECH YIWN
|
||||
FB13; FB13; 0544 0576; 0544 0546; # ARMENIAN SMALL LIGATURE MEN NOW
|
||||
FB14; FB14; 0544 0565; 0544 0535; # ARMENIAN SMALL LIGATURE MEN ECH
|
||||
FB15; FB15; 0544 056B; 0544 053B; # ARMENIAN SMALL LIGATURE MEN INI
|
||||
FB16; FB16; 054E 0576; 054E 0546; # ARMENIAN SMALL LIGATURE VEW NOW
|
||||
FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH
|
||||
|
||||
# No corresponding uppercase precomposed character
|
||||
|
||||
0149; 0149; 02BC 004E; 02BC 004E; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE
|
||||
0390; 0390; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
|
||||
03B0; 03B0; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
|
||||
01F0; 01F0; 004A 030C; 004A 030C; # LATIN SMALL LETTER J WITH CARON
|
||||
1E96; 1E96; 0048 0331; 0048 0331; # LATIN SMALL LETTER H WITH LINE BELOW
|
||||
1E97; 1E97; 0054 0308; 0054 0308; # LATIN SMALL LETTER T WITH DIAERESIS
|
||||
1E98; 1E98; 0057 030A; 0057 030A; # LATIN SMALL LETTER W WITH RING ABOVE
|
||||
1E99; 1E99; 0059 030A; 0059 030A; # LATIN SMALL LETTER Y WITH RING ABOVE
|
||||
1E9A; 1E9A; 0041 02BE; 0041 02BE; # LATIN SMALL LETTER A WITH RIGHT HALF RING
|
||||
1F50; 1F50; 03A5 0313; 03A5 0313; # GREEK SMALL LETTER UPSILON WITH PSILI
|
||||
1F52; 1F52; 03A5 0313 0300; 03A5 0313 0300; # GREEK SMALL LETTER UPSILON WITH PSILI AND VARIA
|
||||
1F54; 1F54; 03A5 0313 0301; 03A5 0313 0301; # GREEK SMALL LETTER UPSILON WITH PSILI AND OXIA
|
||||
1F56; 1F56; 03A5 0313 0342; 03A5 0313 0342; # GREEK SMALL LETTER UPSILON WITH PSILI AND PERISPOMENI
|
||||
1FB6; 1FB6; 0391 0342; 0391 0342; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI
|
||||
1FC6; 1FC6; 0397 0342; 0397 0342; # GREEK SMALL LETTER ETA WITH PERISPOMENI
|
||||
1FD2; 1FD2; 0399 0308 0300; 0399 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA
|
||||
1FD3; 1FD3; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
|
||||
1FD6; 1FD6; 0399 0342; 0399 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI
|
||||
1FD7; 1FD7; 0399 0308 0342; 0399 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI
|
||||
1FE2; 1FE2; 03A5 0308 0300; 03A5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA
|
||||
1FE3; 1FE3; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
|
||||
1FE4; 1FE4; 03A1 0313; 03A1 0313; # GREEK SMALL LETTER RHO WITH PSILI
|
||||
1FE6; 1FE6; 03A5 0342; 03A5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI
|
||||
1FE7; 1FE7; 03A5 0308 0342; 03A5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI
|
||||
1FF6; 1FF6; 03A9 0342; 03A9 0342; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI
|
||||
|
||||
# IMPORTANT-when iota-subscript (0345) is uppercased or titlecased,
|
||||
# the result will be incorrect unless the iota-subscript is moved to the end
|
||||
# of any sequence of combining marks. Otherwise, the accents will go on the capital iota.
|
||||
# This process can be achieved by first transforming the text to NFC before casing.
|
||||
# E.g. <alpha><iota_subscript><acute> is uppercased to <ALPHA><acute><IOTA>
|
||||
|
||||
# The following cases are already in the UnicodeData.txt file, so are only commented here.
|
||||
|
||||
# 0345; 0345; 0399; 0399; # COMBINING GREEK YPOGEGRAMMENI
|
||||
|
||||
# All letters with YPOGEGRAMMENI (iota-subscript) or PROSGEGRAMMENI (iota adscript)
|
||||
# have special uppercases.
|
||||
# Note: characters with PROSGEGRAMMENI are actually titlecase, not uppercase!
|
||||
|
||||
1F80; 1F80; 1F88; 1F08 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI
|
||||
1F81; 1F81; 1F89; 1F09 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND YPOGEGRAMMENI
|
||||
1F82; 1F82; 1F8A; 1F0A 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND VARIA AND YPOGEGRAMMENI
|
||||
1F83; 1F83; 1F8B; 1F0B 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND VARIA AND YPOGEGRAMMENI
|
||||
1F84; 1F84; 1F8C; 1F0C 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA AND YPOGEGRAMMENI
|
||||
1F85; 1F85; 1F8D; 1F0D 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND OXIA AND YPOGEGRAMMENI
|
||||
1F86; 1F86; 1F8E; 1F0E 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
|
||||
1F87; 1F87; 1F8F; 1F0F 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
|
||||
1F88; 1F80; 1F88; 1F08 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI
|
||||
1F89; 1F81; 1F89; 1F09 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI
|
||||
1F8A; 1F82; 1F8A; 1F0A 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI
|
||||
1F8B; 1F83; 1F8B; 1F0B 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI
|
||||
1F8C; 1F84; 1F8C; 1F0C 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI
|
||||
1F8D; 1F85; 1F8D; 1F0D 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI
|
||||
1F8E; 1F86; 1F8E; 1F0E 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
|
||||
1F8F; 1F87; 1F8F; 1F0F 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
|
||||
1F90; 1F90; 1F98; 1F28 0399; # GREEK SMALL LETTER ETA WITH PSILI AND YPOGEGRAMMENI
|
||||
1F91; 1F91; 1F99; 1F29 0399; # GREEK SMALL LETTER ETA WITH DASIA AND YPOGEGRAMMENI
|
||||
1F92; 1F92; 1F9A; 1F2A 0399; # GREEK SMALL LETTER ETA WITH PSILI AND VARIA AND YPOGEGRAMMENI
|
||||
1F93; 1F93; 1F9B; 1F2B 0399; # GREEK SMALL LETTER ETA WITH DASIA AND VARIA AND YPOGEGRAMMENI
|
||||
1F94; 1F94; 1F9C; 1F2C 0399; # GREEK SMALL LETTER ETA WITH PSILI AND OXIA AND YPOGEGRAMMENI
|
||||
1F95; 1F95; 1F9D; 1F2D 0399; # GREEK SMALL LETTER ETA WITH DASIA AND OXIA AND YPOGEGRAMMENI
|
||||
1F96; 1F96; 1F9E; 1F2E 0399; # GREEK SMALL LETTER ETA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
|
||||
1F97; 1F97; 1F9F; 1F2F 0399; # GREEK SMALL LETTER ETA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
|
||||
1F98; 1F90; 1F98; 1F28 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI
|
||||
1F99; 1F91; 1F99; 1F29 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI
|
||||
1F9A; 1F92; 1F9A; 1F2A 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI
|
||||
1F9B; 1F93; 1F9B; 1F2B 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI
|
||||
1F9C; 1F94; 1F9C; 1F2C 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI
|
||||
1F9D; 1F95; 1F9D; 1F2D 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI
|
||||
1F9E; 1F96; 1F9E; 1F2E 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
|
||||
1F9F; 1F97; 1F9F; 1F2F 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
|
||||
1FA0; 1FA0; 1FA8; 1F68 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND YPOGEGRAMMENI
|
||||
1FA1; 1FA1; 1FA9; 1F69 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND YPOGEGRAMMENI
|
||||
1FA2; 1FA2; 1FAA; 1F6A 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND VARIA AND YPOGEGRAMMENI
|
||||
1FA3; 1FA3; 1FAB; 1F6B 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND VARIA AND YPOGEGRAMMENI
|
||||
1FA4; 1FA4; 1FAC; 1F6C 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND OXIA AND YPOGEGRAMMENI
|
||||
1FA5; 1FA5; 1FAD; 1F6D 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND OXIA AND YPOGEGRAMMENI
|
||||
1FA6; 1FA6; 1FAE; 1F6E 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
|
||||
1FA7; 1FA7; 1FAF; 1F6F 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
|
||||
1FA8; 1FA0; 1FA8; 1F68 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI
|
||||
1FA9; 1FA1; 1FA9; 1F69 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI
|
||||
1FAA; 1FA2; 1FAA; 1F6A 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI
|
||||
1FAB; 1FA3; 1FAB; 1F6B 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI
|
||||
1FAC; 1FA4; 1FAC; 1F6C 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI
|
||||
1FAD; 1FA5; 1FAD; 1F6D 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI
|
||||
1FAE; 1FA6; 1FAE; 1F6E 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
|
||||
1FAF; 1FA7; 1FAF; 1F6F 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
|
||||
1FB3; 1FB3; 1FBC; 0391 0399; # GREEK SMALL LETTER ALPHA WITH YPOGEGRAMMENI
|
||||
1FBC; 1FB3; 1FBC; 0391 0399; # GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI
|
||||
1FC3; 1FC3; 1FCC; 0397 0399; # GREEK SMALL LETTER ETA WITH YPOGEGRAMMENI
|
||||
1FCC; 1FC3; 1FCC; 0397 0399; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI
|
||||
1FF3; 1FF3; 1FFC; 03A9 0399; # GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI
|
||||
1FFC; 1FF3; 1FFC; 03A9 0399; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI
|
||||
|
||||
# Some characters with YPOGEGRAMMENI also have no corresponding titlecases
|
||||
|
||||
1FB2; 1FB2; 1FBA 0345; 1FBA 0399; # GREEK SMALL LETTER ALPHA WITH VARIA AND YPOGEGRAMMENI
|
||||
1FB4; 1FB4; 0386 0345; 0386 0399; # GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI
|
||||
1FC2; 1FC2; 1FCA 0345; 1FCA 0399; # GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI
|
||||
1FC4; 1FC4; 0389 0345; 0389 0399; # GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI
|
||||
1FF2; 1FF2; 1FFA 0345; 1FFA 0399; # GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI
|
||||
1FF4; 1FF4; 038F 0345; 038F 0399; # GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI
|
||||
|
||||
1FB7; 1FB7; 0391 0342 0345; 0391 0342 0399; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI
|
||||
1FC7; 1FC7; 0397 0342 0345; 0397 0342 0399; # GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI
|
||||
1FF7; 1FF7; 03A9 0342 0345; 03A9 0342 0399; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI AND YPOGEGRAMMENI
|
||||
|
||||
# ================================================================================
|
||||
# Conditional Mappings
|
||||
# The remainder of this file provides conditional casing data used to produce
|
||||
# full case mappings.
|
||||
# ================================================================================
|
||||
# Language-Insensitive Mappings
|
||||
# These are characters whose full case mappings do not depend on language, but do
|
||||
# depend on context (which characters come before or after). For more information
|
||||
# see the header of this file and the Unicode Standard.
|
||||
# ================================================================================
|
||||
|
||||
# Special case for final form of sigma
|
||||
|
||||
03A3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK CAPITAL LETTER SIGMA
|
||||
|
||||
# Note: the following cases for non-final are already in the UnicodeData.txt file.
|
||||
|
||||
# 03A3; 03C3; 03A3; 03A3; # GREEK CAPITAL LETTER SIGMA
|
||||
# 03C3; 03C3; 03A3; 03A3; # GREEK SMALL LETTER SIGMA
|
||||
# 03C2; 03C2; 03A3; 03A3; # GREEK SMALL LETTER FINAL SIGMA
|
||||
|
||||
# Note: the following cases are not included, since they would case-fold in lowercasing
|
||||
|
||||
# 03C3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK SMALL LETTER SIGMA
|
||||
# 03C2; 03C3; 03A3; 03A3; Not_Final_Sigma; # GREEK SMALL LETTER FINAL SIGMA
|
||||
|
||||
# ================================================================================
|
||||
# Language-Sensitive Mappings
|
||||
# These are characters whose full case mappings depend on language and perhaps also
|
||||
# context (which characters come before or after). For more information
|
||||
# see the header of this file and the Unicode Standard.
|
||||
# ================================================================================
|
||||
|
||||
# Lithuanian
|
||||
|
||||
# Lithuanian retains the dot in a lowercase i when followed by accents.
|
||||
|
||||
# Remove DOT ABOVE after "i" with upper or titlecase
|
||||
|
||||
0307; 0307; ; ; lt After_Soft_Dotted; # COMBINING DOT ABOVE
|
||||
|
||||
# Introduce an explicit dot above when lowercasing capital I's and J's
|
||||
# whenever there are more accents above.
|
||||
# (of the accents used in Lithuanian: grave, acute, tilde above, and ogonek)
|
||||
|
||||
0049; 0069 0307; 0049; 0049; lt More_Above; # LATIN CAPITAL LETTER I
|
||||
004A; 006A 0307; 004A; 004A; lt More_Above; # LATIN CAPITAL LETTER J
|
||||
012E; 012F 0307; 012E; 012E; lt More_Above; # LATIN CAPITAL LETTER I WITH OGONEK
|
||||
00CC; 0069 0307 0300; 00CC; 00CC; lt; # LATIN CAPITAL LETTER I WITH GRAVE
|
||||
00CD; 0069 0307 0301; 00CD; 00CD; lt; # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0128; 0069 0307 0303; 0128; 0128; lt; # LATIN CAPITAL LETTER I WITH TILDE
|
||||
|
||||
# ================================================================================
|
||||
|
||||
# Turkish and Azeri
|
||||
|
||||
# I and i-dotless; I-dot and i are case pairs in Turkish and Azeri
|
||||
# The following rules handle those cases.
|
||||
|
||||
0130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE
|
||||
0130; 0069; 0130; 0130; az; # LATIN CAPITAL LETTER I WITH DOT ABOVE
|
||||
|
||||
# When lowercasing, remove dot_above in the sequence I + dot_above, which will turn into i.
|
||||
# This matches the behavior of the canonically equivalent I-dot_above
|
||||
|
||||
0307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE
|
||||
0307; ; 0307; 0307; az After_I; # COMBINING DOT ABOVE
|
||||
|
||||
# When lowercasing, unless an I is before a dot_above, it turns into a dotless i.
|
||||
|
||||
0049; 0131; 0049; 0049; tr Not_Before_Dot; # LATIN CAPITAL LETTER I
|
||||
0049; 0131; 0049; 0049; az Not_Before_Dot; # LATIN CAPITAL LETTER I
|
||||
|
||||
# When uppercasing, i turns into a dotted capital I
|
||||
|
||||
0069; 0069; 0130; 0130; tr; # LATIN SMALL LETTER I
|
||||
0069; 0069; 0130; 0130; az; # LATIN SMALL LETTER I
|
||||
|
||||
# Note: the following case is already in the UnicodeData.txt file.
|
||||
|
||||
# 0131; 0131; 0049; 0049; tr; # LATIN SMALL LETTER DOTLESS I
|
||||
|
||||
# EOF
|
||||
|
@ -1,5 +1,5 @@
|
||||
/*
|
||||
* Copyright (c) 2007, 2018, Oracle and/or its affiliates. All rights reserved.
|
||||
* Copyright (c) 2007, 2019, 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
|
||||
@ -26,7 +26,10 @@
|
||||
/*
|
||||
* @test
|
||||
* @bug 4830803 4886934 6565620 6959267 7070436 7198195 8032446 8072600 8202771
|
||||
* @summary Check that the UnicodeBlock forName() method works as expected and block ranges are correct for all Unicode characters.
|
||||
* 8221431
|
||||
* @summary Check that the UnicodeBlock forName() method works as expected
|
||||
* and block ranges are correct for all Unicode characters.
|
||||
* @library /lib/testlibrary/java/lang
|
||||
* @run main CheckBlocks
|
||||
* @author John O'Conner
|
||||
*/
|
||||
@ -276,8 +279,7 @@ public class CheckBlocks {
|
||||
public static HashSet<Block> blocks = new HashSet<>();
|
||||
|
||||
private static void generateBlockList() throws Exception {
|
||||
File blockData = new File(System.getProperty("test.src", "."),
|
||||
"Blocks.txt");
|
||||
File blockData = UCDFiles.BLOCKS.toFile();
|
||||
try (BufferedReader f = new BufferedReader(new FileReader(blockData))) {
|
||||
String line;
|
||||
while ((line = f.readLine()) != null) {
|
||||
|
@ -1,5 +1,5 @@
|
||||
/*
|
||||
* Copyright (c) 2015, 2018 Oracle and/or its affiliates. All rights reserved.
|
||||
* Copyright (c) 2015, 2019 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
|
||||
@ -23,7 +23,7 @@
|
||||
|
||||
/**
|
||||
* @test
|
||||
* @bug 8080535 8191410 8215194
|
||||
* @bug 8080535 8191410 8215194 8221431
|
||||
* @summary Expected size of Character.UnicodeBlock.map is not optimal
|
||||
* @library /test/lib
|
||||
* @modules java.base/java.lang:open
|
||||
@ -46,13 +46,14 @@ import jdk.test.lib.util.OptimalCapacity;
|
||||
// be 638 entries in Character.UnicodeBlock.map.
|
||||
//
|
||||
// As of Unicode 11, 667 entries are expected.
|
||||
// As of Unicode 12.1, 676 entries are expected.
|
||||
//
|
||||
// Initialization of the map and this test will have to be adjusted
|
||||
// accordingly then.
|
||||
//
|
||||
// Note that HashMap's implementation aligns the initial capacity to
|
||||
// a power of two size, so it will end up 1024 (and thus succeed) in
|
||||
// cases, such as 638 and 667.
|
||||
// cases, such as 638, 667, and 676.
|
||||
|
||||
public class OptimalMapSize {
|
||||
public static void main(String[] args) throws Throwable {
|
||||
@ -61,7 +62,7 @@ public class OptimalMapSize {
|
||||
Field f = Character.UnicodeBlock.class.getDeclaredField("NUM_ENTITIES");
|
||||
f.setAccessible(true);
|
||||
int num_entities = f.getInt(null);
|
||||
assert num_entities == 667;
|
||||
assert num_entities == 676;
|
||||
int initialCapacity = (int)(num_entities / 0.75f + 1.0f);
|
||||
|
||||
OptimalCapacity.ofHashMap(Character.UnicodeBlock.class,
|
||||
|
@ -1,5 +1,5 @@
|
||||
/*
|
||||
* Copyright (c) 2018, Oracle and/or its affiliates. All rights reserved.
|
||||
* Copyright (c) 2018, 2019, 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
|
||||
@ -25,8 +25,9 @@
|
||||
|
||||
/*
|
||||
* @test
|
||||
* @bug 4397357 6565620 6959267 8032446 8072600
|
||||
* @bug 4397357 6565620 6959267 8032446 8072600 8221431
|
||||
* @summary Confirm normal case mappings are handled correctly.
|
||||
* @library /lib/testlibrary/java/lang
|
||||
* @run main/timeout=200 UnicodeCasingTest
|
||||
*/
|
||||
|
||||
@ -60,8 +61,7 @@ public class UnicodeCasingTest {
|
||||
BufferedReader in = null;
|
||||
|
||||
try {
|
||||
File file = new File(System.getProperty("test.src", "."),
|
||||
"UnicodeData.txt");
|
||||
File file = UCDFiles.UNICODE_DATA.toFile();
|
||||
|
||||
int locale_num = locales.size();
|
||||
for (int l = 0; l < locale_num; l++) {
|
||||
|
File diff suppressed because it is too large
Load Diff
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@ -1,5 +1,5 @@
|
||||
/*
|
||||
* Copyright (c) 2018, Oracle and/or its affiliates. All rights reserved.
|
||||
* Copyright (c) 2018, 2019, 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
|
||||
@ -26,7 +26,9 @@
|
||||
/*
|
||||
* @test
|
||||
* @bug 4397357 6565620 6959267 7070436 7198195 8041791 8032446 8072600
|
||||
* 8221431
|
||||
* @summary Confirm special case mappings are handled correctly.
|
||||
* @library /lib/testlibrary/java/lang
|
||||
*/
|
||||
|
||||
import java.io.BufferedReader;
|
||||
@ -137,8 +139,7 @@ public class SpecialCasingTest {
|
||||
} else {
|
||||
specificLocale = false;
|
||||
}
|
||||
in = Files.newBufferedReader(Paths.get(System.getProperty("test.src.path"), "..", "/Character/SpecialCasing.txt")
|
||||
.toRealPath());
|
||||
in = Files.newBufferedReader(UCDFiles.SPECIAL_CASING.toRealPath());
|
||||
String line;
|
||||
while ((line = in.readLine()) != null) {
|
||||
if (line.length() == 0 || line.charAt(0) == '#') {
|
||||
|
@ -1,5 +1,5 @@
|
||||
/*
|
||||
* Copyright (c) 2018, Oracle and/or its affiliates. All rights reserved.
|
||||
* Copyright (c) 2018, 2019, 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
|
||||
@ -25,8 +25,9 @@
|
||||
|
||||
/*
|
||||
* @test
|
||||
* @bug 4397357 6565620 6959267 7070436 7198195 8032446 8072600
|
||||
* @bug 4397357 6565620 6959267 7070436 7198195 8032446 8072600 8221431
|
||||
* @summary Confirm normal case mappings are handled correctly.
|
||||
* @library /lib/testlibrary/java/lang
|
||||
* @run main/timeout=200 UnicodeCasingTest
|
||||
*/
|
||||
|
||||
@ -70,8 +71,7 @@ public class UnicodeCasingTest {
|
||||
// First, we create exlude lists of characters whose mappings exist
|
||||
// in SpecialCasing.txt and mapping rules in UnicodeData.txt aren't
|
||||
// applicable.
|
||||
in = Files.newBufferedReader(Paths.get(System.getProperty("test.src.path"), "..", "/Character/SpecialCasing.txt")
|
||||
.toRealPath());
|
||||
in = Files.newBufferedReader(UCDFiles.SPECIAL_CASING.toRealPath());
|
||||
String line;
|
||||
while ((line = in.readLine()) != null) {
|
||||
if (line.length() == 0 || line.charAt(0) == '#') {
|
||||
@ -88,8 +88,7 @@ public class UnicodeCasingTest {
|
||||
defaultLang = locale.getLanguage();
|
||||
// System.out.println("Testing on " + locale + " locale....");
|
||||
System.err.println("Testing on " + locale + " locale....");
|
||||
in = Files.newBufferedReader(Paths.get(System.getProperty("test.src.path"), "..", "/Character/UnicodeData.txt")
|
||||
.toRealPath());
|
||||
in = Files.newBufferedReader(UCDFiles.UNICODE_DATA.toRealPath());
|
||||
while ((line = in.readLine()) != null) {
|
||||
if (line.length() == 0 || line.charAt(0) == '#') {
|
||||
continue;
|
||||
|
529
test/jdk/java/text/Normalizer/ConformanceTest.java
Normal file
529
test/jdk/java/text/Normalizer/ConformanceTest.java
Normal file
@ -0,0 +1,529 @@
|
||||
/*
|
||||
* Copyright (c) 2019, 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
|
||||
* under the terms of the GNU General Public License version 2 only, as
|
||||
* published by the Free Software Foundation.
|
||||
*
|
||||
* This code is distributed in the hope that it will be useful, but WITHOUT
|
||||
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
||||
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
|
||||
* version 2 for more details (a copy is included in the LICENSE file that
|
||||
* accompanied this code).
|
||||
*
|
||||
* You should have received a copy of the GNU General Public License version
|
||||
* 2 along with this work; if not, write to the Free Software Foundation,
|
||||
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
|
||||
*
|
||||
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
|
||||
* or visit www.oracle.com if you need additional information or have any
|
||||
* questions.
|
||||
*/
|
||||
/*
|
||||
* @test
|
||||
* @bug 4221795 6565620 6959267 7070436 7198195 8032446 8221431
|
||||
* @summary Confirm Normalizer's fundamental behavior
|
||||
* @library /lib/testlibrary/java/lang
|
||||
* @modules java.base/sun.text java.base/sun.text.normalizer
|
||||
* @compile -XDignore.symbol.file ConformanceTest.java
|
||||
* @run main/timeout=3000 ConformanceTest
|
||||
*/
|
||||
|
||||
import java.io.BufferedReader;
|
||||
import java.io.File;
|
||||
import java.io.FileInputStream;
|
||||
import java.io.InputStreamReader;
|
||||
import java.lang.reflect.Method;
|
||||
import java.nio.charset.Charset;
|
||||
import java.nio.charset.CharsetDecoder;
|
||||
import java.util.BitSet;
|
||||
import java.util.StringTokenizer;
|
||||
|
||||
import sun.text.normalizer.NormalizerBase;
|
||||
import sun.text.normalizer.NormalizerImpl;
|
||||
|
||||
/*
|
||||
* Conformance test for java.text.Normalizer and sun.text.Normalizer.
|
||||
*/
|
||||
public class ConformanceTest {
|
||||
|
||||
//
|
||||
// Options to be used with sun.text.Normalizer
|
||||
//
|
||||
|
||||
/*
|
||||
* Default Unicode 3.2.0 normalization. (Provided for IDNA/StringPrep)
|
||||
*
|
||||
* - Without Corrigendum 4 fix
|
||||
* (Different from ICU4J 3.2's Normalizer.)
|
||||
* - Without Public Review Issue #29 fix
|
||||
* (Different from ICU4J 3.2's Normalizer.)
|
||||
*/
|
||||
private static final int UNICODE_3_2_0 = sun.text.Normalizer.UNICODE_3_2;
|
||||
|
||||
/*
|
||||
* Original Unicode 3.2.0 normalization. (Provided for testing only)
|
||||
*
|
||||
* - With Corrigendum 4 fix
|
||||
* - With Public Revilew Issue #29 fix
|
||||
*/
|
||||
private static final int UNICODE_3_2_0_ORIGINAL =
|
||||
NormalizerBase.UNICODE_3_2;
|
||||
|
||||
/*
|
||||
* Default normalization. In JDK 6,
|
||||
* - Unicode 4.0.0
|
||||
* - With Corrigendum 4 fix
|
||||
* - Without Public Review Issue #29 fix
|
||||
*
|
||||
* In JDK 7,
|
||||
* - Unicode 5.1.0
|
||||
* (Different from ICU4J 3.2's Normalizer.)
|
||||
* - With Corrigendum 4 fix
|
||||
* - With Public Review Issue #29 fix
|
||||
*
|
||||
* In JDK 8,
|
||||
* - Unicode 6.1.0
|
||||
* - With Corrigendum 4 fix
|
||||
* - With Public Review Issue #29 fix
|
||||
*
|
||||
* When we support Unicode 4.1.0 or later, we need to do normalization
|
||||
* with Public Review Issue #29 fix. For more details of PRI #29, see
|
||||
* http://unicode.org/review/pr-29.html .
|
||||
*/
|
||||
private static final int UNICODE_LATEST = NormalizerBase.UNICODE_LATEST;
|
||||
|
||||
//
|
||||
// Conformance test datafiles
|
||||
//
|
||||
|
||||
/*
|
||||
* Conformance test datafile for Unicode 3.2.0 with Corrigendum4
|
||||
* corrections.
|
||||
* This testdata is for sun.text.Normalize(UNICODE_3_2)
|
||||
*
|
||||
* This is NOT an original Conformace test data. Some inconvenient test
|
||||
* cases are commented out. About corrigendum 4, please refer
|
||||
* http://www.unicode.org/review/resolved-pri.html#pri29
|
||||
*
|
||||
*/
|
||||
static final String DATA_3_2_0_CORRIGENDUM =
|
||||
"NormalizationTest-3.2.0.Corrigendum4.txt";
|
||||
|
||||
/*
|
||||
* Conformance test datafile for Unicode 3.2.0 without Corrigendum4
|
||||
* corrections. This is the original Conformace test data.
|
||||
*
|
||||
* This testdata is for sun.text.Normalize(UNICODE_3_2_IDNA)
|
||||
*/
|
||||
static final String DATA_3_2_0 = "NormalizationTest-3.2.0.txt";
|
||||
|
||||
/*
|
||||
* Conformance test datafile for the latest Unicode which is supported
|
||||
* by J2SE.
|
||||
* Unicode 4.0.0 is the latest version in JDK 5.0 and JDK 6. Unicode 5.1.0
|
||||
* in JDK 7, and 6.1.0 in JDK 8. This Unicode can be used via both
|
||||
* java.text.Normalizer and sun.text.Normalizer.
|
||||
*
|
||||
* This testdata is for sun.text.Normalize(UNICODE_LATEST)
|
||||
*/
|
||||
static final String DATA_LATEST = "NormalizationTest-Latest.txt";
|
||||
|
||||
/*
|
||||
* Conformance test datafile in ICU4J 3.2.
|
||||
*/
|
||||
static final String DATA_ICU = "ICUNormalizationTest.txt";
|
||||
|
||||
/*
|
||||
* Decorder
|
||||
*/
|
||||
static final CharsetDecoder decoder = Charset.forName("UTF-8").newDecoder();
|
||||
|
||||
/*
|
||||
* List to pick up characters which are not listed in Part1
|
||||
*/
|
||||
static BitSet charList = new BitSet(Character.MAX_CODE_POINT+1);
|
||||
|
||||
/*
|
||||
* Shortcuts
|
||||
*/
|
||||
private static final java.text.Normalizer.Form NFC =
|
||||
java.text.Normalizer.Form.NFC;
|
||||
private static final java.text.Normalizer.Form NFD =
|
||||
java.text.Normalizer.Form.NFD;
|
||||
private static final java.text.Normalizer.Form NFKC =
|
||||
java.text.Normalizer.Form.NFKC;
|
||||
private static final java.text.Normalizer.Form NFKD =
|
||||
java.text.Normalizer.Form.NFKD;
|
||||
static final java.text.Normalizer.Form[] forms = {NFC, NFD, NFKC, NFKD};
|
||||
|
||||
|
||||
static TestNormalizer normalizer;
|
||||
|
||||
public static void main(String[] args) throws Exception {
|
||||
ConformanceTest ct = new ConformanceTest();
|
||||
ct.test();
|
||||
}
|
||||
|
||||
void test() throws Exception {
|
||||
normalizer = new testJavaNormalizer();
|
||||
test(DATA_LATEST, UNICODE_LATEST);
|
||||
|
||||
normalizer = new testSunNormalizer();
|
||||
test(DATA_3_2_0_CORRIGENDUM, UNICODE_3_2_0);
|
||||
test(DATA_LATEST, UNICODE_LATEST);
|
||||
test(DATA_ICU, UNICODE_LATEST);
|
||||
|
||||
/* Unconformity test */
|
||||
// test(DATA_3_2_0, UNICODE_LATEST);
|
||||
// test(DATA_LATEST, UNICODE_3_2_0);
|
||||
}
|
||||
|
||||
/*
|
||||
* Main routine of conformance test
|
||||
*/
|
||||
private static void test(String filename, int unicodeVer) throws Exception {
|
||||
|
||||
File f = filename.equals(DATA_LATEST) ?
|
||||
UCDFiles.NORMALIZATION_TEST.toFile() :
|
||||
new File(System.getProperty("test.src", "."), filename);
|
||||
FileInputStream fis = new FileInputStream(f);
|
||||
BufferedReader in =
|
||||
new BufferedReader(new InputStreamReader(fis, decoder));
|
||||
|
||||
System.out.println("\nStart testing for " + normalizer.name +
|
||||
" with " + filename + " for options: " +
|
||||
(((unicodeVer & NormalizerBase.UNICODE_3_2) != 0) ?
|
||||
"Unicode 3.2.0" : "the latest Unicode"));
|
||||
|
||||
int lineNo = 0;
|
||||
String text;
|
||||
boolean part1test = false;
|
||||
boolean part1testExists = false;
|
||||
String[] columns = new String[6];
|
||||
|
||||
while ((text = in.readLine()) != null) {
|
||||
lineNo ++;
|
||||
|
||||
char c = text.charAt(0);
|
||||
if (c == '#') {
|
||||
continue;
|
||||
} else if (c == '@') {
|
||||
if (text.startsWith("@Part")) {
|
||||
System.out.println("# Testing data in " + text);
|
||||
|
||||
if (text.startsWith("@Part1 ")) {
|
||||
part1test = true;
|
||||
part1testExists = true;
|
||||
} else {
|
||||
part1test = false;
|
||||
}
|
||||
|
||||
continue;
|
||||
}
|
||||
}
|
||||
|
||||
prepareColumns(columns, text, filename, lineNo, part1test);
|
||||
|
||||
testNFC(columns, unicodeVer, filename, lineNo);
|
||||
testNFD(columns, unicodeVer, filename, lineNo);
|
||||
testNFKC(columns, unicodeVer, filename, lineNo);
|
||||
testNFKD(columns, unicodeVer, filename, lineNo);
|
||||
}
|
||||
|
||||
in.close();
|
||||
fis.close();
|
||||
|
||||
if (part1testExists) {
|
||||
System.out.println("# Testing characters which are not listed in Part1");
|
||||
testRemainingChars(filename, unicodeVer);
|
||||
part1testExists = false;
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Test for NFC
|
||||
*
|
||||
* c2 == NFC(c1) == NFC(c2) == NFC(c3)
|
||||
* c4 == NFC(c4) == NFC(c5)
|
||||
*/
|
||||
private static void testNFC(String[] c, int unicodeVer,
|
||||
String file, int line) throws Exception {
|
||||
test(2, c, 1, 3, NFC, unicodeVer, file, line);
|
||||
test(4, c, 4, 5, NFC, unicodeVer, file, line);
|
||||
}
|
||||
|
||||
/*
|
||||
* Test for NFD
|
||||
*
|
||||
* c3 == NFD(c1) == NFD(c2) == NFD(c3)
|
||||
* c5 == NFD(c4) == NFD(c5)
|
||||
*/
|
||||
private static void testNFD(String[] c, int unicodeVer,
|
||||
String file, int line) throws Exception {
|
||||
test(3, c, 1, 3, NFD, unicodeVer, file, line);
|
||||
test(5, c, 4, 5, NFD, unicodeVer, file, line);
|
||||
}
|
||||
|
||||
/*
|
||||
* Test for NFKC
|
||||
*
|
||||
* c4 == NFKC(c1) == NFKC(c2) == NFKC(c3) == NFKC(c4) == NFKC(c5)
|
||||
*/
|
||||
private static void testNFKC(String[] c, int unicodeVer,
|
||||
String file, int line) throws Exception {
|
||||
test(4, c, 1, 5, NFKC, unicodeVer, file, line);
|
||||
}
|
||||
|
||||
/*
|
||||
* Test for NFKD
|
||||
*
|
||||
* c5 == NFKD(c1) == NFKD(c2) == NFKD(c3) == NFKD(c4) == NFKD(c5)
|
||||
*/
|
||||
private static void testNFKD(String[] c, int unicodeVer,
|
||||
String file, int line) throws Exception {
|
||||
test(5, c, 1, 5, NFKD, unicodeVer, file, line);
|
||||
}
|
||||
|
||||
/*
|
||||
* Test for characters which aren't listed in Part1
|
||||
*
|
||||
* X == NFC(X) == NFD(X) == NFKC(X) == NFKD(X)
|
||||
*/
|
||||
private static void testRemainingChars(String file,
|
||||
int unicodeVer) throws Exception {
|
||||
for (int i = Character.MIN_CODE_POINT;
|
||||
i <= Character.MAX_CODE_POINT;
|
||||
i++) {
|
||||
if (!charList.get(i)) {
|
||||
String from = String.valueOf(Character.toChars(i));
|
||||
String to;
|
||||
|
||||
for (int j = 0; j < forms.length; j++) {
|
||||
java.text.Normalizer.Form form = forms[j];
|
||||
|
||||
to = normalizer.normalize(from, form, unicodeVer);
|
||||
if (!from.equals(to)) {
|
||||
error(form, from, from, to, file, -1);
|
||||
// } else {
|
||||
// okay(form, from, from, to, file, -1);
|
||||
}
|
||||
|
||||
if (!normalizer.isNormalized(from, form, unicodeVer)) {
|
||||
error(form, from, file, -1);
|
||||
// } else {
|
||||
// okay(form, from, file, -1);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Test normalize() and isNormalized()
|
||||
*/
|
||||
private static void test(int col, String[] c,
|
||||
int FROM, int TO,
|
||||
java.text.Normalizer.Form form, int unicodeVer,
|
||||
String file, int line) throws Exception {
|
||||
for (int i = FROM; i <= TO; i++) {
|
||||
String got = normalizer.normalize(c[i], form, unicodeVer);
|
||||
if (!c[col].equals(got)) {
|
||||
error(form, c[i], c[col], got, file, line);
|
||||
// } else {
|
||||
// okay(form, c[i], c[col], got, file, line);
|
||||
}
|
||||
|
||||
/*
|
||||
* If the original String equals its normalized String, it means
|
||||
* that the original String is normalizerd. Thus, isNormalized()
|
||||
* should return true. And, vice versa!
|
||||
*/
|
||||
if (c[col].equals(c[i])) {
|
||||
if (!normalizer.isNormalized(c[i], form, unicodeVer)) {
|
||||
error(form, c[i], file, line);
|
||||
// } else {
|
||||
// okay(form, c[i], file, line);
|
||||
}
|
||||
} else {
|
||||
if (normalizer.isNormalized(c[i], form, unicodeVer)) {
|
||||
error(form, c[i], file, line);
|
||||
// } else {
|
||||
// okay(form, c[i], file, line);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Generate an array of String from a line of conformance datafile.
|
||||
*/
|
||||
private static void prepareColumns(String[] cols, String text,
|
||||
String file, int line,
|
||||
boolean part1test) throws Exception {
|
||||
int index = text.indexOf('#');
|
||||
if (index != -1) {
|
||||
text = text.substring(0, index);
|
||||
}
|
||||
|
||||
StringTokenizer st = new StringTokenizer(text, ";");
|
||||
int tokenCount = st.countTokens();
|
||||
if (tokenCount < 5) {
|
||||
throw new RuntimeException("# of tokens in datafile should be 6, but got: " + tokenCount + " at line " + line + " in " + file);
|
||||
}
|
||||
|
||||
StringBuffer sb = new StringBuffer();
|
||||
for (int i = 1; i <= 5; i++) {
|
||||
StringTokenizer tst = new StringTokenizer(st.nextToken(), " ");
|
||||
|
||||
while (tst.hasMoreTokens()) {
|
||||
int code = Integer.parseInt(tst.nextToken(), 16);
|
||||
sb.append(Character.toChars(code));
|
||||
}
|
||||
|
||||
cols[i] = sb.toString();
|
||||
sb.setLength(0);
|
||||
}
|
||||
|
||||
if (part1test) {
|
||||
charList.set(cols[1].codePointAt(0));
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Show an error message when normalize() didn't return the expected value.
|
||||
* (An exception is sometimes convenient. Therefore, it is commented out
|
||||
* for the moment.)
|
||||
*/
|
||||
private static void error(java.text.Normalizer.Form form,
|
||||
String from, String to, String got,
|
||||
String file, int line) throws Exception {
|
||||
System.err.println("-\t" + form.toString() + ": normalize(" +
|
||||
toHexString(from) + ") doesn't equal <" + toHexString(to) +
|
||||
"> at line " + line + " in " + file + ". Got [" +
|
||||
toHexString(got) + "]");
|
||||
throw new RuntimeException("Normalization(" + form.toString() + ") failed");
|
||||
}
|
||||
|
||||
/*
|
||||
* Show an error message when isNormalize() didn't return the expected
|
||||
* value.
|
||||
* (An exception is sometimes convenient. Therefore, it is commented out
|
||||
* for the moment.)
|
||||
*/
|
||||
private static void error(java.text.Normalizer.Form form, String s,
|
||||
String file, int line) throws Exception {
|
||||
System.err.println("\t" + form.toString() + ": isNormalized(" +
|
||||
toHexString(s) + ") returned the wrong value at line " + line +
|
||||
" in " + file);
|
||||
throw new RuntimeException("Normalization(" + form.toString() +") failed");
|
||||
}
|
||||
|
||||
/*
|
||||
* (For debugging)
|
||||
* Shows a message when normalize() returned the expected value.
|
||||
*/
|
||||
private static void okay(java.text.Normalizer.Form form,
|
||||
String from, String to, String got,
|
||||
String file, int line) {
|
||||
System.out.println("\t" + form.toString() + ": normalize(" +
|
||||
toHexString(from) + ") equals <" + toHexString(to) +
|
||||
"> at line " + line + " in " + file + ". Got [" +
|
||||
toHexString(got) + "]");
|
||||
}
|
||||
|
||||
/*
|
||||
* (For debugging)
|
||||
* Shows a message when isNormalized() returned the expected value.
|
||||
*/
|
||||
private static void okay(java.text.Normalizer.Form form, String s,
|
||||
String file, int line) {
|
||||
System.out.println("\t" + form.toString() + ": isNormalized(" +
|
||||
toHexString(s) + ") returned the correct value at line " +
|
||||
line + " in " + file);
|
||||
}
|
||||
|
||||
/*
|
||||
* Returns a spece-delimited hex String
|
||||
*/
|
||||
private static String toHexString(String s) {
|
||||
StringBuffer sb = new StringBuffer(" ");
|
||||
|
||||
for (int i = 0; i < s.length(); i++) {
|
||||
sb.append(Integer.toHexString(s.charAt(i)));
|
||||
sb.append(' ');
|
||||
}
|
||||
|
||||
return sb.toString();
|
||||
}
|
||||
|
||||
/*
|
||||
* Abstract class to call each Normalizer in java.text or sun.text.
|
||||
*/
|
||||
private abstract class TestNormalizer {
|
||||
String name;
|
||||
|
||||
TestNormalizer(String str) {
|
||||
name = str;
|
||||
}
|
||||
|
||||
String getNormalizerName() {
|
||||
return name;
|
||||
}
|
||||
|
||||
abstract String normalize(CharSequence cs,
|
||||
java.text.Normalizer.Form form,
|
||||
int option);
|
||||
|
||||
abstract boolean isNormalized(CharSequence cs,
|
||||
java.text.Normalizer.Form form,
|
||||
int option);
|
||||
}
|
||||
|
||||
/*
|
||||
* For java.text.Normalizer
|
||||
* - normalize(CharSequence, Normalizer.Form)
|
||||
* - isNormalized(CharSequence, Normalizer.Form)
|
||||
*/
|
||||
private class testJavaNormalizer extends TestNormalizer {
|
||||
testJavaNormalizer() {
|
||||
super("java.text.Normalizer");
|
||||
}
|
||||
|
||||
String normalize(CharSequence cs,
|
||||
java.text.Normalizer.Form form,
|
||||
int option) {
|
||||
return java.text.Normalizer.normalize(cs, form);
|
||||
}
|
||||
|
||||
boolean isNormalized(CharSequence cs,
|
||||
java.text.Normalizer.Form form,
|
||||
int option) {
|
||||
return java.text.Normalizer.isNormalized(cs, form);
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* For sun.text.Normalizer
|
||||
* - normalize(CharSequence, Normalizer.Form, int)
|
||||
* - isNormalized(CharSequence, Normalizer.Form, int)
|
||||
*/
|
||||
private class testSunNormalizer extends TestNormalizer {
|
||||
testSunNormalizer() {
|
||||
super("sun.text.Normalizer");
|
||||
}
|
||||
|
||||
String normalize(CharSequence cs,
|
||||
java.text.Normalizer.Form form,
|
||||
int option) {
|
||||
return sun.text.Normalizer.normalize(cs, form, option);
|
||||
}
|
||||
|
||||
boolean isNormalized(CharSequence cs,
|
||||
java.text.Normalizer.Form form,
|
||||
int option) {
|
||||
return sun.text.Normalizer.isNormalized(cs, form, option);
|
||||
}
|
||||
}
|
||||
}
|
447
test/jdk/java/text/Normalizer/DataValidationTest.java
Normal file
447
test/jdk/java/text/Normalizer/DataValidationTest.java
Normal file
@ -0,0 +1,447 @@
|
||||
/*
|
||||
* Copyright (c) 2019, 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
|
||||
* under the terms of the GNU General Public License version 2 only, as
|
||||
* published by the Free Software Foundation.
|
||||
*
|
||||
* This code is distributed in the hope that it will be useful, but WITHOUT
|
||||
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
||||
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
|
||||
* version 2 for more details (a copy is included in the LICENSE file that
|
||||
* accompanied this code).
|
||||
*
|
||||
* You should have received a copy of the GNU General Public License version
|
||||
* 2 along with this work; if not, write to the Free Software Foundation,
|
||||
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
|
||||
*
|
||||
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
|
||||
* or visit www.oracle.com if you need additional information or have any
|
||||
* questions.
|
||||
*/
|
||||
/*
|
||||
* test
|
||||
* bug 4221795
|
||||
* summary Confirm *.icu data using ICU4J Normalizer
|
||||
*/
|
||||
|
||||
import java.io.BufferedReader;
|
||||
import java.io.FileInputStream;
|
||||
import java.io.InputStreamReader;
|
||||
import java.nio.charset.Charset;
|
||||
import java.nio.charset.CharsetDecoder;
|
||||
import java.util.BitSet;
|
||||
import java.util.StringTokenizer;
|
||||
|
||||
import com.ibm.icu.text.Normalizer;
|
||||
import com.ibm.icu.impl.NormalizerImpl;
|
||||
|
||||
/**
|
||||
* This is not a test program but a data validation utility.
|
||||
* Two datafiles for Normalizer, unorm.icu and uprops.icu under
|
||||
* sun/text/resouces, are generated using generators in ICU4C 3.2 on a
|
||||
* BIG-ENDIAN machine. Before using them with java.text.Normalizer and
|
||||
* sun.text.Normalizer, you may want to check these test datafile's validation.
|
||||
* You can test datafiles using Normalizer in ICU4J 3.2. Download ICU4J 3.2 and
|
||||
* run this test program with -cp <ICU4J 3.2>.
|
||||
*/
|
||||
public class DataValidationTest {
|
||||
|
||||
//
|
||||
// Options to be used with com.ibm.icu.text.Normalizer
|
||||
//
|
||||
|
||||
/*
|
||||
* Default Unicode 3.2.0 normalization.
|
||||
*
|
||||
* - With Corrigendum 4 fix
|
||||
* (Different from Mustang's Normalizer.)
|
||||
* - With Public Review Issue #29 fix
|
||||
* (Different from Mustang's Normalizer.)
|
||||
*/
|
||||
private static final int UNICODE_3_2_0 = Normalizer.UNICODE_3_2;
|
||||
|
||||
/*
|
||||
* *Incomplete* Unicode 3.2.0 normalization for IDNA/StringPrep.
|
||||
*
|
||||
* - With Corrigendum 4 fix
|
||||
* - Without Public Review Issue #29 fix
|
||||
*
|
||||
* ICU4J's Normalizer itself doesn't support normalization for Unicode 3.2.0
|
||||
* without Corrigendum 4 fix, which is necessary for IDNA/StringPrep. It is
|
||||
* done in StringPrep. Therefore, we don't test the normlaization in this
|
||||
* test program. We merely test normalization for Unicode 3.2.0 without
|
||||
* Public Review Issue #29 fix with this test program.
|
||||
*/
|
||||
private static final int UNICODE_3_2_0_BEFORE_PRI_29 =
|
||||
Normalizer.UNICODE_3_2 |
|
||||
NormalizerImpl.BEFORE_PRI_29;
|
||||
|
||||
/*
|
||||
* Default normalization.
|
||||
*
|
||||
* - Unicode 4.0.1
|
||||
* (Different from Mustang's Normalizer.)
|
||||
* - With Corrigendum 4 fix
|
||||
* - With Public Review Issue #29 fix
|
||||
* (Different from Mustang's Normalizer.)
|
||||
*
|
||||
* Because Public Review Issue #29 is fixed in Unicode 4.1.0. I think that
|
||||
* IUC4J 3.2 should not support it. But it actually supports PRI #29 fix
|
||||
* as default....
|
||||
*/
|
||||
private static final int UNICODE_LATEST = 0x00;
|
||||
|
||||
/*
|
||||
* Normalization without Public Review Issue #29 fix.
|
||||
*
|
||||
* - Unicode 4.0.1
|
||||
* - Without Corrigendum 4 fix
|
||||
* - Without Public Review Issue #29 fix
|
||||
*/
|
||||
static final int UNICODE_LATEST_BEFORE_PRI_29 =
|
||||
NormalizerImpl.BEFORE_PRI_29;
|
||||
|
||||
//
|
||||
// Conformance test datafiles
|
||||
//
|
||||
|
||||
/*
|
||||
* Conformance test datafile for normalization for Unicode 3.2.0 with
|
||||
* Corrigendum 4 corrections. This is NOT an original Conformace test
|
||||
* data. Some inconvenient test cases are commented out.
|
||||
* About corrigendum 4, please refer
|
||||
* http://www.unicode.org/versions/corrigendum4.html
|
||||
*
|
||||
* ICU4J 3.2's Normalizer itself doesn't support normalization for Unicode
|
||||
* 3.2.0 without Corrigendum 4 corrections. StringPrep helps it. So, we
|
||||
* don't test the normalization with this test program.
|
||||
*/
|
||||
static final String DATA_3_2_0 = "NormalizationTest-3.2.0.Corrigendum4.txt";
|
||||
|
||||
/*
|
||||
* Conformance test datafile for the latest Unicode which is supported
|
||||
* by J2SE.
|
||||
*/
|
||||
static final String DATA_LATEST = "NormalizationTest-Latest.txt";
|
||||
|
||||
/*
|
||||
* Decorder
|
||||
*/
|
||||
static final CharsetDecoder decoder = Charset.forName("UTF-8").newDecoder();
|
||||
|
||||
/*
|
||||
* List to pick up characters which are not listed in Part1
|
||||
*/
|
||||
static BitSet charList = new BitSet(Character.MAX_CODE_POINT+1);
|
||||
|
||||
/*
|
||||
* Shortcuts
|
||||
*/
|
||||
static final Normalizer.Mode NFC = com.ibm.icu.text.Normalizer.NFC;
|
||||
static final Normalizer.Mode NFD = com.ibm.icu.text.Normalizer.NFD;
|
||||
static final Normalizer.Mode NFKC = com.ibm.icu.text.Normalizer.NFKC;
|
||||
static final Normalizer.Mode NFKD = com.ibm.icu.text.Normalizer.NFKD;
|
||||
static final Normalizer.Mode[] modes = {NFC, NFD, NFKC, NFKD};
|
||||
|
||||
|
||||
public static void main(String[] args) throws Exception {
|
||||
test(DATA_3_2_0, UNICODE_3_2_0);
|
||||
test(DATA_3_2_0, UNICODE_3_2_0_BEFORE_PRI_29);
|
||||
test(DATA_LATEST, UNICODE_LATEST);
|
||||
// This test started failing since ICU4J 3.6.
|
||||
// test(DATA_LATEST, UNICODE_LATEST_BEFORE_PRI_29);
|
||||
|
||||
/* Unconformity test */
|
||||
// test(DATA_3_2_0, UNICODE_LATEST);
|
||||
// test(DATA_LATEST, UNICODE_3_2);
|
||||
}
|
||||
|
||||
private static void test(String filename, int unicodeVer) throws Exception {
|
||||
|
||||
FileInputStream fis = new FileInputStream(filename);
|
||||
BufferedReader in =
|
||||
new BufferedReader(new InputStreamReader(fis, decoder));
|
||||
|
||||
System.out.println("\nStart testing with " + filename +
|
||||
" for options: " +
|
||||
(((unicodeVer & Normalizer.UNICODE_3_2) != 0) ?
|
||||
"Unicode 3.2.0" : "the latest Unicode") + ", " +
|
||||
(((unicodeVer & NormalizerImpl.BEFORE_PRI_29) != 0) ?
|
||||
"with" : "without") + " PRI #29 fix");
|
||||
|
||||
int lineNo = 0;
|
||||
String text;
|
||||
String[] columns = new String[6];
|
||||
boolean part1test = false;
|
||||
|
||||
while ((text = in.readLine()) != null) {
|
||||
lineNo ++;
|
||||
|
||||
char c = text.charAt(0);
|
||||
if (c == '#') {
|
||||
continue;
|
||||
} else if (c == '@') {
|
||||
if (text.startsWith("@Part")) {
|
||||
System.out.println("# Testing data in " + text);
|
||||
|
||||
if (text.startsWith("@Part1 ")) {
|
||||
part1test = true;
|
||||
} else {
|
||||
part1test = false;
|
||||
}
|
||||
|
||||
continue;
|
||||
}
|
||||
}
|
||||
|
||||
prepareColumns(columns, text, filename, lineNo, part1test);
|
||||
|
||||
testNFC(columns, unicodeVer, filename, lineNo);
|
||||
testNFD(columns, unicodeVer, filename, lineNo);
|
||||
testNFKC(columns, unicodeVer, filename, lineNo);
|
||||
testNFKD(columns, unicodeVer, filename, lineNo);
|
||||
}
|
||||
|
||||
in.close();
|
||||
fis.close();
|
||||
|
||||
if (unicodeVer == UNICODE_LATEST) {
|
||||
System.out.println("# Testing characters which are not listed in Part1");
|
||||
testRemainingChars(filename, unicodeVer);
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Test for NFC
|
||||
*
|
||||
* c2 == NFC(c1) == NFC(c2) == NFC(c3)
|
||||
* c4 == NFC(c4) == NFC(c5)
|
||||
*/
|
||||
private static void testNFC(String[] c, int unicodeVer,
|
||||
String file, int line) throws Exception {
|
||||
test(2, c, 1, 3, NFC, unicodeVer, file, line);
|
||||
test(4, c, 4, 5, NFC, unicodeVer, file, line);
|
||||
}
|
||||
|
||||
/*
|
||||
* Test for NFD
|
||||
*
|
||||
* c3 == NFD(c1) == NFD(c2) == NFD(c3)
|
||||
* c5 == NFD(c4) == NFD(c5)
|
||||
*/
|
||||
private static void testNFD(String[] c, int unicodeVer,
|
||||
String file, int line) throws Exception {
|
||||
test(3, c, 1, 3, NFD, unicodeVer, file, line);
|
||||
test(5, c, 4, 5, NFD, unicodeVer, file, line);
|
||||
}
|
||||
|
||||
/*
|
||||
* Test for NFKC
|
||||
*
|
||||
* c4 == NFKC(c1) == NFKC(c2) == NFKC(c3) == NFKC(c4) == NFKC(c5)
|
||||
*/
|
||||
private static void testNFKC(String[] c, int unicodeVer,
|
||||
String file, int line) throws Exception {
|
||||
test(4, c, 1, 5, NFKC, unicodeVer, file, line);
|
||||
}
|
||||
|
||||
/*
|
||||
* Test for NFKD
|
||||
*
|
||||
* c5 == NFKD(c1) == NFKD(c2) == NFKD(c3) == NFKD(c4) == NFKD(c5)
|
||||
*/
|
||||
private static void testNFKD(String[] c, int unicodeVer,
|
||||
String file, int line) throws Exception {
|
||||
test(5, c, 1, 5, NFKD, unicodeVer, file, line);
|
||||
}
|
||||
|
||||
/*
|
||||
* Test for characters which aren't listed in Part1
|
||||
*
|
||||
* X == NFC(X) == NFD(X) == NFKC(X) == NFKD(X)
|
||||
*/
|
||||
private static void testRemainingChars(String file,
|
||||
int unicodeVer) throws Exception {
|
||||
for (int i = Character.MIN_CODE_POINT;
|
||||
i <= Character.MAX_CODE_POINT;
|
||||
i++) {
|
||||
if (!charList.get(i)) {
|
||||
String from = String.valueOf(Character.toChars(i));
|
||||
String to;
|
||||
|
||||
for (int j = 0; j < modes.length; j++) {
|
||||
Normalizer.Mode mode = modes[j];
|
||||
|
||||
to = Normalizer.normalize(from, mode, unicodeVer);
|
||||
if (!from.equals(to)) {
|
||||
error(mode, from, from, to, file, -1);
|
||||
// } else {
|
||||
// okay(mode, from, from, to, file, -1);
|
||||
}
|
||||
|
||||
if (!Normalizer.isNormalized(from, mode, unicodeVer)) {
|
||||
error(mode, from, file, -1);
|
||||
// } else {
|
||||
// okay(mode, from, file, -1);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Test normalize() and isNormalized()
|
||||
*/
|
||||
private static void test(int col, String[] c,
|
||||
int FROM, int TO,
|
||||
Normalizer.Mode mode, int unicodeVer,
|
||||
String file, int line) throws Exception {
|
||||
for (int i = FROM; i <= TO; i++) {
|
||||
String got = Normalizer.normalize(c[i], mode, unicodeVer);
|
||||
if (!c[col].equals(got)) {
|
||||
error(mode, c[i], c[col], got, file, line);
|
||||
// } else {
|
||||
// okay(mode, c[i], c[col], got, file, line);
|
||||
}
|
||||
|
||||
/*
|
||||
* If the original String equals its normalized String, it means
|
||||
* that the original String is normalizerd. Thus, isNormalized()
|
||||
* should return true. And, vice versa!
|
||||
*/
|
||||
if (c[col].equals(c[i])) {
|
||||
if (!Normalizer.isNormalized(c[i], mode, unicodeVer)) {
|
||||
error(mode, c[i], file, line);
|
||||
// } else {
|
||||
// okay(mode, c[i], file, line);
|
||||
}
|
||||
} else {
|
||||
if (Normalizer.isNormalized(c[i], mode, unicodeVer)) {
|
||||
error(mode, c[i], file, line);
|
||||
// } else {
|
||||
// okay(mode, c[i], file, line);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Generate an array of String from a line of conformance datafile.
|
||||
*/
|
||||
private static void prepareColumns(String[] col, String text,
|
||||
String file, int line,
|
||||
boolean part1test) throws Exception {
|
||||
int index = text.indexOf('#');
|
||||
if (index != -1) {
|
||||
text = text.substring(0, index);
|
||||
}
|
||||
|
||||
StringTokenizer st = new StringTokenizer(text, ";");
|
||||
int tokenCount = st.countTokens();
|
||||
if (tokenCount < 5) {
|
||||
throw new RuntimeException("# of tokens in datafile should be 6, but got: " + tokenCount + " at line " + line + " in " + file);
|
||||
}
|
||||
|
||||
StringBuffer sb = new StringBuffer();
|
||||
for (int i = 1; i <= 5; i++) {
|
||||
StringTokenizer tst = new StringTokenizer(st.nextToken(), " ");
|
||||
|
||||
while (tst.hasMoreTokens()) {
|
||||
int code = Integer.parseInt(tst.nextToken(), 16);
|
||||
sb.append(Character.toChars(code));
|
||||
}
|
||||
|
||||
col[i] = sb.toString();
|
||||
sb.setLength(0);
|
||||
}
|
||||
|
||||
if (part1test) {
|
||||
charList.set(col[1].codePointAt(0));
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Show an error message when normalize() didn't return the expected value.
|
||||
* (An exception is sometimes convenient. Therefore, it is commented out
|
||||
* for the moment.)
|
||||
*/
|
||||
private static void error(Normalizer.Mode mode,
|
||||
String from, String to, String got,
|
||||
String file, int line) throws Exception {
|
||||
System.err.println("\t" + toString(mode) + ": normalize(" +
|
||||
toHexString(from) + ") doesn't equal <" + toHexString(to) +
|
||||
"> at line " + line + " in " + file + ". Got <" +
|
||||
toHexString(got) + ">.");
|
||||
// throw new RuntimeException("Normalization(" + toString(mode) + ") failed");
|
||||
}
|
||||
|
||||
/*
|
||||
* Show an error message when isNormalize() didn't return the expected value.
|
||||
* (An exception is sometimes convenient. Therefore, it is commented out
|
||||
* for the moment.)
|
||||
*/
|
||||
private static void error(Normalizer.Mode mode, String orig,
|
||||
String file, int line) throws Exception {
|
||||
System.err.println("\t" + toString(mode) + ": isNormalized(" +
|
||||
toHexString(orig) + ") returned the wrong value at line " + line +
|
||||
" in " + file + ".");
|
||||
// throw new RuntimeException("Normalization(" + toString(mode) +") failed");
|
||||
}
|
||||
|
||||
/*
|
||||
* (For debugging)
|
||||
* Shows a message when normalize() returned the expected value.
|
||||
*/
|
||||
private static void okay(Normalizer.Mode mode,
|
||||
String from, String to, String got,
|
||||
String file, int line) {
|
||||
System.out.println("\t" + toString(mode) + ": normalize(" +
|
||||
toHexString(from) + ") equals <" + toHexString(to) +
|
||||
"> at line " + line + " in " + file + ". Got <" +
|
||||
toHexString(got) + ">.");
|
||||
}
|
||||
|
||||
/*
|
||||
* (For debugging)
|
||||
* Shows a message when isNormalized() returned the expected value.
|
||||
*/
|
||||
private static void okay(Normalizer.Mode mode, String orig,
|
||||
String file, int line) {
|
||||
System.out.println("\t" + toString(mode) + ": isNormalized(" +
|
||||
toHexString(orig) + ") returned the correct value at line " +
|
||||
line + " in " + file + ".");
|
||||
}
|
||||
|
||||
/*
|
||||
* Returns a spece-delimited hex String
|
||||
*/
|
||||
private static String toHexString(String s) {
|
||||
StringBuffer sb = new StringBuffer(" ");
|
||||
|
||||
for (int i = 0; i < s.length(); i++) {
|
||||
sb.append(Integer.toHexString(s.charAt(i)));
|
||||
sb.append(' ');
|
||||
}
|
||||
|
||||
return sb.toString();
|
||||
}
|
||||
|
||||
/*
|
||||
* Returns the name of Normalizer.Mode
|
||||
*/
|
||||
private static String toString(Normalizer.Mode mode) {
|
||||
if (mode == Normalizer.NFC) {
|
||||
return "NFC";
|
||||
} else if (mode == Normalizer.NFD) {
|
||||
return "NFD";
|
||||
} else if (mode == Normalizer.NFKC) {
|
||||
return "NFKC";
|
||||
} else if (mode == Normalizer.NFKD) {
|
||||
return "NFKD";
|
||||
}
|
||||
|
||||
return "unknown";
|
||||
}
|
||||
}
|
610
test/jdk/java/text/Normalizer/ICUBasicTest.java
Normal file
610
test/jdk/java/text/Normalizer/ICUBasicTest.java
Normal file
@ -0,0 +1,610 @@
|
||||
/*
|
||||
* Copyright (c) 2019, 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
|
||||
* under the terms of the GNU General Public License version 2 only, as
|
||||
* published by the Free Software Foundation.
|
||||
*
|
||||
* This code is distributed in the hope that it will be useful, but WITHOUT
|
||||
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
||||
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
|
||||
* version 2 for more details (a copy is included in the LICENSE file that
|
||||
* accompanied this code).
|
||||
*
|
||||
* You should have received a copy of the GNU General Public License version
|
||||
* 2 along with this work; if not, write to the Free Software Foundation,
|
||||
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
|
||||
*
|
||||
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
|
||||
* or visit www.oracle.com if you need additional information or have any
|
||||
* questions.
|
||||
*/
|
||||
/*
|
||||
* @test
|
||||
* @bug 4221795 8032446
|
||||
* @summary Confirm Normalizer's fundamental behavior. Imported from ICU4J 3.2's
|
||||
* src/com/ibm/icu/dev/test and modified.
|
||||
* @modules java.base/sun.text java.base/sun.text.normalizer
|
||||
* @library /java/text/testlib
|
||||
* @compile -XDignore.symbol.file ICUBasicTest.java
|
||||
* @run main/timeout=30 ICUBasicTest
|
||||
*/
|
||||
|
||||
/*
|
||||
*******************************************************************************
|
||||
* Copyright (C) 1996-2004, International Business Machines Corporation and *
|
||||
* others. All Rights Reserved. *
|
||||
*******************************************************************************
|
||||
*/
|
||||
|
||||
import sun.text.Normalizer;
|
||||
import sun.text.normalizer.NormalizerBase;
|
||||
import sun.text.normalizer.NormalizerImpl;
|
||||
|
||||
import static java.text.Normalizer.Form.*;
|
||||
import static sun.text.normalizer.NormalizerBase.Mode.*;
|
||||
|
||||
public class ICUBasicTest extends IntlTest {
|
||||
|
||||
public static void main(String[] args) throws Exception {
|
||||
new ICUBasicTest().run(args);
|
||||
}
|
||||
|
||||
/*
|
||||
* Normalization modes
|
||||
*/
|
||||
private static final NormalizerBase.Mode NFCmode = NormalizerBase.NFC;
|
||||
private static final NormalizerBase.Mode NFDmode = NormalizerBase.NFD;
|
||||
private static final NormalizerBase.Mode NFKCmode = NormalizerBase.NFKC;
|
||||
private static final NormalizerBase.Mode NFKDmode = NormalizerBase.NFKD;
|
||||
private static final NormalizerBase.Mode NONEmode = NormalizerBase.NONE;
|
||||
|
||||
/*
|
||||
* Normalization options
|
||||
*/
|
||||
|
||||
/* Normal Unicode versions */
|
||||
private static final int UNICODE_3_2_0 = Normalizer.UNICODE_3_2;
|
||||
private static final int UNICODE_LATEST = NormalizerBase.UNICODE_LATEST;
|
||||
|
||||
/*
|
||||
* Special cases for UAX #15 bug
|
||||
* see Unicode Public Review Issue #29
|
||||
* at http://www.unicode.org/review/resolved-pri.html#pri29
|
||||
*
|
||||
* Note:
|
||||
* PRI #29 is supported in Unicode 4.1.0. Therefore, expected results are
|
||||
* different for earlier Unicode versions.
|
||||
*/
|
||||
public void TestComposition() {
|
||||
|
||||
final TestCompositionCase cases[] = new TestCompositionCase[] {
|
||||
new TestCompositionCase(NFC, UNICODE_3_2_0,
|
||||
"\u1100\u0300\u1161\u0327",
|
||||
"\u1100\u0300\u1161\u0327"),
|
||||
new TestCompositionCase(NFC, UNICODE_LATEST,
|
||||
"\u1100\u0300\u1161\u0327",
|
||||
"\u1100\u0300\u1161\u0327"),
|
||||
|
||||
new TestCompositionCase(NFC, UNICODE_3_2_0,
|
||||
"\u1100\u0300\u1161\u0327\u11a8",
|
||||
"\u1100\u0300\u1161\u0327\u11a8"),
|
||||
new TestCompositionCase(NFC, UNICODE_LATEST,
|
||||
"\u1100\u0300\u1161\u0327\u11a8",
|
||||
"\u1100\u0300\u1161\u0327\u11a8"),
|
||||
|
||||
new TestCompositionCase(NFC, UNICODE_3_2_0,
|
||||
"\uac00\u0300\u0327\u11a8",
|
||||
"\uac00\u0327\u0300\u11a8"),
|
||||
new TestCompositionCase(NFC, UNICODE_LATEST,
|
||||
"\uac00\u0300\u0327\u11a8",
|
||||
"\uac00\u0327\u0300\u11a8"),
|
||||
|
||||
new TestCompositionCase(NFC, UNICODE_3_2_0,
|
||||
"\u0b47\u0300\u0b3e",
|
||||
"\u0b47\u0300\u0b3e"),
|
||||
new TestCompositionCase(NFC, UNICODE_LATEST,
|
||||
"\u0b47\u0300\u0b3e",
|
||||
"\u0b47\u0300\u0b3e"),
|
||||
};
|
||||
|
||||
String output;
|
||||
int i, length;
|
||||
|
||||
for (i=0; i<cases.length; ++i) {
|
||||
output = Normalizer.normalize(cases[i].input,
|
||||
cases[i].form, cases[i].options);
|
||||
if (!output.equals(cases[i].expect)) {
|
||||
errln("unexpected result for case " + i + ". Expected="
|
||||
+ cases[i].expect + ", Actual=" + output);
|
||||
} else if (verbose) {
|
||||
logln("expected result for case " + i + ". Expected="
|
||||
+ cases[i].expect + ", Actual=" + output);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private final static class TestCompositionCase {
|
||||
public java.text.Normalizer.Form form;
|
||||
public int options;
|
||||
public String input, expect;
|
||||
|
||||
TestCompositionCase(java.text.Normalizer.Form form,
|
||||
int options,
|
||||
String input,
|
||||
String expect) {
|
||||
this.form = form;
|
||||
this.options = options;
|
||||
this.input = input;
|
||||
this.expect = expect;
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Added in order to detect a regression.
|
||||
*/
|
||||
public void TestCombiningMarks() {
|
||||
String src = "\u0f71\u0f72\u0f73\u0f74\u0f75";
|
||||
String expected = "\u0F71\u0F71\u0F71\u0F72\u0F72\u0F74\u0F74";
|
||||
String result = NormalizerBase.normalize(src, NFD);
|
||||
|
||||
if (!expected.equals(result)) {
|
||||
errln("Reordering of combining marks failed. Expected: " +
|
||||
toHexString(expected) + " Got: "+ toHexString(result));
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Added in order to detect a regression.
|
||||
*/
|
||||
public void TestBengali() throws Exception {
|
||||
String input = "\u09bc\u09be\u09cd\u09be";
|
||||
String output=NormalizerBase.normalize(input, NFC);
|
||||
|
||||
if (!input.equals(output)) {
|
||||
errln("ERROR in NFC of string");
|
||||
}
|
||||
return;
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
* Added in order to detect a regression.
|
||||
*/
|
||||
/**
|
||||
* Test for a problem found by Verisign. Problem is that
|
||||
* characters at the start of a string are not put in canonical
|
||||
* order correctly by compose() if there is no starter.
|
||||
*/
|
||||
public void TestVerisign() throws Exception {
|
||||
String[] inputs = {
|
||||
"\u05b8\u05b9\u05b1\u0591\u05c3\u05b0\u05ac\u059f",
|
||||
"\u0592\u05b7\u05bc\u05a5\u05b0\u05c0\u05c4\u05ad"
|
||||
};
|
||||
String[] outputs = {
|
||||
"\u05b1\u05b8\u05b9\u0591\u05c3\u05b0\u05ac\u059f",
|
||||
"\u05b0\u05b7\u05bc\u05a5\u0592\u05c0\u05ad\u05c4"
|
||||
};
|
||||
|
||||
for (int i = 0; i < inputs.length; ++i) {
|
||||
String input = inputs[i];
|
||||
String output = outputs[i];
|
||||
|
||||
String result = NormalizerBase.normalize(input, NFD);
|
||||
if (!result.equals(output)) {
|
||||
errln("FAIL input: " + toHexString(input) + "\n" +
|
||||
" decompose: " + toHexString(result) + "\n" +
|
||||
" expected: " + toHexString(output));
|
||||
}
|
||||
|
||||
result = NormalizerBase.normalize(input, NFC);
|
||||
if (!result.equals(output)) {
|
||||
errln("FAIL input: " + toHexString(input) + "\n" +
|
||||
" compose: " + toHexString(result) + "\n" +
|
||||
" expected: " + toHexString(output));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Test for a problem that showed up just before ICU 1.6 release
|
||||
* having to do with combining characters with an index of zero.
|
||||
* Such characters do not participate in any canonical
|
||||
* decompositions. However, having an index of zero means that
|
||||
* they all share one typeMask[] entry, that is, they all have to
|
||||
* map to the same canonical class, which is not the case, in
|
||||
* reality.
|
||||
*/
|
||||
public void TestZeroIndex() throws Exception {
|
||||
String[] DATA = {
|
||||
// Expect col1 x COMPOSE_COMPAT => col2
|
||||
// Expect col2 x DECOMP => col3
|
||||
"A\u0316\u0300", "\u00C0\u0316", "A\u0316\u0300",
|
||||
"A\u0300\u0316", "\u00C0\u0316", "A\u0316\u0300",
|
||||
"A\u0327\u0300", "\u00C0\u0327", "A\u0327\u0300",
|
||||
"c\u0321\u0327", "c\u0321\u0327", "c\u0321\u0327",
|
||||
"c\u0327\u0321", "\u00E7\u0321", "c\u0327\u0321",
|
||||
};
|
||||
|
||||
for (int i=0; i<DATA.length; i+=3) {
|
||||
String a = DATA[i];
|
||||
String b = NormalizerBase.normalize(a, NFKC);
|
||||
String exp = DATA[i+1];
|
||||
|
||||
if (b.equals(exp)) {
|
||||
logln("Ok: " + toHexString(a) + " x COMPOSE_COMPAT => " +
|
||||
toHexString(b));
|
||||
} else {
|
||||
errln("FAIL: " + toHexString(a) + " x COMPOSE_COMPAT => " +
|
||||
toHexString(b) + ", expect " + toHexString(exp));
|
||||
}
|
||||
|
||||
a = NormalizerBase.normalize(b, NFD);
|
||||
exp = DATA[i+2];
|
||||
if (a.equals(exp)) {
|
||||
logln("Ok: " + toHexString(b) + " x DECOMP => " +
|
||||
toHexString(a));
|
||||
} else {
|
||||
errln("FAIL: " + toHexString(b) + " x DECOMP => " +
|
||||
toHexString(a) + ", expect " + toHexString(exp));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Make sure characters in the CompositionExclusion.txt list do not get
|
||||
* composed to.
|
||||
*/
|
||||
public void TestCompositionExclusion() throws Exception {
|
||||
// This list is generated from CompositionExclusion.txt.
|
||||
// Update whenever the normalizer tables are updated. Note
|
||||
// that we test all characters listed, even those that can be
|
||||
// derived from the Unicode DB and are therefore commented
|
||||
// out.
|
||||
|
||||
/*
|
||||
* kyuka's note:
|
||||
* Original data seemed to be based on Unicode 3.0.0(the initial
|
||||
* Composition Exclusions list) and seemed to have some mistakes.
|
||||
* Updated in order to correct mistakes and to support Unicode 4.0.0.
|
||||
* And, this table can be used also for Unicode 3.2.0.
|
||||
*/
|
||||
String[][] EXCLUDED_UNICODE_3_2_0 = {
|
||||
{"\u0340"},
|
||||
{"\u0341"},
|
||||
{"\u0343"},
|
||||
{"\u0344"},
|
||||
{"\u0374"},
|
||||
{"\u037E"},
|
||||
{"\u0387"},
|
||||
{"\u0958"},
|
||||
{"\u0959", "\u095F"},
|
||||
{"\u09DC"},
|
||||
{"\u09DD"},
|
||||
{"\u09DF"},
|
||||
{"\u0A33"},
|
||||
{"\u0A36"},
|
||||
{"\u0A59", "\u0A5B"},
|
||||
{"\u0A5E"},
|
||||
{"\u0B5C"},
|
||||
{"\u0B5D"},
|
||||
{"\u0F43"},
|
||||
{"\u0F4D"},
|
||||
{"\u0F52"},
|
||||
{"\u0F57"},
|
||||
{"\u0F5C"},
|
||||
{"\u0F69"},
|
||||
{"\u0F73"},
|
||||
{"\u0F75"},
|
||||
{"\u0F76"},
|
||||
{"\u0F78"},
|
||||
{"\u0F81"},
|
||||
{"\u0F93"},
|
||||
{"\u0F9D"},
|
||||
{"\u0FA2"},
|
||||
{"\u0FA7"},
|
||||
{"\u0FAC"},
|
||||
{"\u0FB9"},
|
||||
{"\u1F71"},
|
||||
{"\u1F73"},
|
||||
{"\u1F75"},
|
||||
{"\u1F77"},
|
||||
{"\u1F79"},
|
||||
{"\u1F7B"},
|
||||
{"\u1F7D"},
|
||||
{"\u1FBB"},
|
||||
{"\u1FBE"},
|
||||
{"\u1FC9"},
|
||||
{"\u1FCB"},
|
||||
{"\u1FD3"},
|
||||
{"\u1FDB"},
|
||||
{"\u1FE3"},
|
||||
{"\u1FEB"},
|
||||
{"\u1FEE"},
|
||||
{"\u1FEF"},
|
||||
{"\u1FF9"},
|
||||
{"\u1FFB"},
|
||||
{"\u1FFD"},
|
||||
{"\u2000"},
|
||||
{"\u2001"},
|
||||
{"\u2126"},
|
||||
{"\u212A"},
|
||||
{"\u212B"},
|
||||
{"\u2329"},
|
||||
{"\u232A"},
|
||||
{"\u2ADC"},
|
||||
{"\uF900", "\uFA0D"},
|
||||
{"\uFA10"},
|
||||
{"\uFA12"},
|
||||
{"\uFA15", "\uFA1E"},
|
||||
{"\uFA20"},
|
||||
{"\uFA22"},
|
||||
{"\uFA25"},
|
||||
{"\uFA26"},
|
||||
{"\uFA2A", "\uFA2D"},
|
||||
{"\uFA30", "\uFA6A"},
|
||||
{"\uFB1D"},
|
||||
{"\uFB1F"},
|
||||
{"\uFB2A", "\uFB36"},
|
||||
{"\uFB38", "\uFB3C"},
|
||||
{"\uFB3E"},
|
||||
{"\uFB40"},
|
||||
{"\uFB41"},
|
||||
{"\uFB43"},
|
||||
{"\uFB44"},
|
||||
{"\uFB46", "\uFB4E"},
|
||||
{"\uD834\uDD5E", "\uD834\uDD64"},
|
||||
{"\uD834\uDDBB", "\uD834\uDDC0"},
|
||||
{"\uD87E\uDC00", "\uD87E\uDE1D"}
|
||||
};
|
||||
|
||||
String[][] EXCLUDED_LATEST = {
|
||||
|
||||
};
|
||||
|
||||
for (int i = 0; i < EXCLUDED_UNICODE_3_2_0.length; ++i) {
|
||||
if (EXCLUDED_UNICODE_3_2_0[i].length == 1) {
|
||||
checkCompositionExclusion_320(EXCLUDED_UNICODE_3_2_0[i][0]);
|
||||
} else {
|
||||
int from, to;
|
||||
from = Character.codePointAt(EXCLUDED_UNICODE_3_2_0[i][0], 0);
|
||||
to = Character.codePointAt(EXCLUDED_UNICODE_3_2_0[i][1], 0);
|
||||
|
||||
for (int j = from; j <= to; j++) {
|
||||
checkCompositionExclusion_320(String.valueOf(Character.toChars(j)));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private void checkCompositionExclusion_320(String s) throws Exception {
|
||||
String a = String.valueOf(s);
|
||||
String b = NormalizerBase.normalize(a, NFKD);
|
||||
String c = NormalizerBase.normalize(b, NFC);
|
||||
|
||||
if (c.equals(a)) {
|
||||
errln("FAIL: " + toHexString(a) + " x DECOMP_COMPAT => " +
|
||||
toHexString(b) + " x COMPOSE => " +
|
||||
toHexString(c) + " for the latest Unicode");
|
||||
} else if (verbose) {
|
||||
logln("Ok: " + toHexString(a) + " x DECOMP_COMPAT => " +
|
||||
toHexString(b) + " x COMPOSE => " +
|
||||
toHexString(c) + " for the latest Unicode");
|
||||
}
|
||||
|
||||
b = NormalizerBase.normalize(a, NFKD, Normalizer.UNICODE_3_2);
|
||||
c = NormalizerBase.normalize(b, NFC, Normalizer.UNICODE_3_2);
|
||||
if (c.equals(a)) {
|
||||
errln("FAIL: " + toHexString(a) + " x DECOMP_COMPAT => " +
|
||||
toHexString(b) + " x COMPOSE => " +
|
||||
toHexString(c) + " for Unicode 3.2.0");
|
||||
} else if (verbose) {
|
||||
logln("Ok: " + toHexString(a) + " x DECOMP_COMPAT => " +
|
||||
toHexString(b) + " x COMPOSE => " +
|
||||
toHexString(c) + " for Unicode 3.2.0");
|
||||
}
|
||||
}
|
||||
|
||||
public void TestTibetan() throws Exception {
|
||||
String[][] decomp = {
|
||||
{ "\u0f77", "\u0f77", "\u0fb2\u0f71\u0f80" }
|
||||
};
|
||||
String[][] compose = {
|
||||
{ "\u0fb2\u0f71\u0f80", "\u0fb2\u0f71\u0f80", "\u0fb2\u0f71\u0f80" }
|
||||
};
|
||||
|
||||
staticTest(NFD, decomp, 1);
|
||||
staticTest(NFKD,decomp, 2);
|
||||
staticTest(NFC, compose, 1);
|
||||
staticTest(NFKC,compose, 2);
|
||||
}
|
||||
|
||||
public void TestExplodingBase() throws Exception{
|
||||
// \u017f - Latin small letter long s
|
||||
// \u0307 - combining dot above
|
||||
// \u1e61 - Latin small letter s with dot above
|
||||
// \u1e9b - Latin small letter long s with dot above
|
||||
String[][] canon = {
|
||||
// Input Decomposed Composed
|
||||
{ "Tschu\u017f", "Tschu\u017f", "Tschu\u017f" },
|
||||
{ "Tschu\u1e9b", "Tschu\u017f\u0307", "Tschu\u1e9b" },
|
||||
};
|
||||
String[][] compat = {
|
||||
// Input Decomposed Composed
|
||||
{ "\u017f", "s", "s" },
|
||||
{ "\u1e9b", "s\u0307", "\u1e61" },
|
||||
};
|
||||
|
||||
staticTest(NFD, canon, 1);
|
||||
staticTest(NFC, canon, 2);
|
||||
staticTest(NFKD, compat, 1);
|
||||
staticTest(NFKC, compat, 2);
|
||||
}
|
||||
|
||||
private String[][] canonTests = {
|
||||
// Input Decomposed Composed
|
||||
|
||||
{ "cat", "cat", "cat" },
|
||||
{ "\u00e0ardvark", "a\u0300ardvark", "\u00e0ardvark", },
|
||||
|
||||
// D-dot_above
|
||||
{ "\u1e0a", "D\u0307", "\u1e0a" },
|
||||
|
||||
// D dot_above
|
||||
{ "D\u0307", "D\u0307", "\u1e0a" },
|
||||
|
||||
// D-dot_below dot_above
|
||||
{ "\u1e0c\u0307", "D\u0323\u0307", "\u1e0c\u0307" },
|
||||
|
||||
// D-dot_above dot_below
|
||||
{ "\u1e0a\u0323", "D\u0323\u0307", "\u1e0c\u0307" },
|
||||
|
||||
// D dot_below dot_above
|
||||
{ "D\u0307\u0323", "D\u0323\u0307", "\u1e0c\u0307" },
|
||||
|
||||
// D dot_below cedilla dot_above
|
||||
{ "\u1e10\u0307\u0323", "D\u0327\u0323\u0307", "\u1e10\u0323\u0307"},
|
||||
|
||||
// D dot_above ogonek dot_below
|
||||
{ "D\u0307\u0328\u0323","D\u0328\u0323\u0307", "\u1e0c\u0328\u0307"},
|
||||
|
||||
// E-macron-grave
|
||||
{ "\u1E14", "E\u0304\u0300", "\u1E14" },
|
||||
|
||||
// E-macron + grave
|
||||
{ "\u0112\u0300", "E\u0304\u0300", "\u1E14" },
|
||||
|
||||
// E-grave + macron
|
||||
{ "\u00c8\u0304", "E\u0300\u0304", "\u00c8\u0304" },
|
||||
|
||||
// angstrom_sign
|
||||
{ "\u212b", "A\u030a", "\u00c5" },
|
||||
|
||||
// A-ring
|
||||
{ "\u00c5", "A\u030a", "\u00c5" },
|
||||
{ "\u00c4ffin", "A\u0308ffin", "\u00c4ffin" },
|
||||
{ "\u00c4\uFB03n", "A\u0308\uFB03n", "\u00c4\uFB03n" },
|
||||
|
||||
//updated with 3.0
|
||||
{ "\u00fdffin", "y\u0301ffin", "\u00fdffin" },
|
||||
{ "\u00fd\uFB03n", "y\u0301\uFB03n", "\u00fd\uFB03n" },
|
||||
|
||||
{ "Henry IV", "Henry IV", "Henry IV" },
|
||||
{ "Henry \u2163", "Henry \u2163", "Henry \u2163" },
|
||||
|
||||
// ga(Zenkaku-Katakana)
|
||||
{ "\u30AC", "\u30AB\u3099", "\u30AC" },
|
||||
|
||||
// ka(Zenkaku-Katakana) + ten(Zenkaku)
|
||||
{ "\u30AB\u3099", "\u30AB\u3099", "\u30AC" },
|
||||
|
||||
// ka(Hankaku-Katakana) + ten(Hankaku-Katakana)
|
||||
{ "\uFF76\uFF9E", "\uFF76\uFF9E", "\uFF76\uFF9E" },
|
||||
|
||||
// ka(Zenkaku-Katakana) + ten(Hankaku)
|
||||
{ "\u30AB\uFF9E", "\u30AB\uFF9E", "\u30AB\uFF9E" },
|
||||
// ka(Hankaku-Katakana) + ten(Zenkaku)
|
||||
{ "\uFF76\u3099", "\uFF76\u3099", "\uFF76\u3099" },
|
||||
|
||||
{ "A\u0300\u0316", "A\u0316\u0300", "\u00C0\u0316" },
|
||||
|
||||
{ "\ud834\udd5e\ud834\udd57\ud834\udd65\ud834\udd5e",
|
||||
"\ud834\udd57\ud834\udd65\ud834\udd57\ud834\udd65\ud834\udd57\ud834\udd65",
|
||||
"\ud834\udd57\ud834\udd65\ud834\udd57\ud834\udd65\ud834\udd57\ud834\udd65" },
|
||||
};
|
||||
|
||||
private String[][] compatTests = {
|
||||
// Input Decomposed Composed
|
||||
|
||||
{ "cat", "cat", "cat" },
|
||||
|
||||
// Alef-Lamed vs. Alef, Lamed
|
||||
{ "\uFB4f", "\u05D0\u05DC", "\u05D0\u05DC", },
|
||||
|
||||
{ "\u00C4ffin", "A\u0308ffin", "\u00C4ffin" },
|
||||
|
||||
// ffi ligature -> f + f + i
|
||||
{ "\u00C4\uFB03n", "A\u0308ffin", "\u00C4ffin" },
|
||||
|
||||
//updated for 3.0
|
||||
{ "\u00fdffin", "y\u0301ffin", "\u00fdffin" },
|
||||
|
||||
// ffi ligature -> f + f + i
|
||||
{ "\u00fd\uFB03n", "y\u0301ffin", "\u00fdffin" },
|
||||
|
||||
{ "Henry IV", "Henry IV", "Henry IV" },
|
||||
{ "Henry \u2163", "Henry IV", "Henry IV" },
|
||||
|
||||
// ga(Zenkaku-Katakana)
|
||||
{ "\u30AC", "\u30AB\u3099", "\u30AC" },
|
||||
|
||||
// ka(Zenkaku-Katakana) + ten(Zenkaku)
|
||||
{ "\u30AB\u3099", "\u30AB\u3099", "\u30AC" },
|
||||
|
||||
// ka(Hankaku-Katakana) + ten(Zenkaku)
|
||||
{ "\uFF76\u3099", "\u30AB\u3099", "\u30AC" },
|
||||
|
||||
/* These two are broken in Unicode 2.1.2 but fixed in 2.1.5 and later*/
|
||||
// ka(Hankaku-Katakana) + ten(Hankaku)
|
||||
{ "\uFF76\uFF9E", "\u30AB\u3099", "\u30AC" },
|
||||
|
||||
// ka(Zenkaku-Katakana) + ten(Hankaku)
|
||||
{ "\u30AB\uFF9E", "\u30AB\u3099", "\u30AC" },
|
||||
};
|
||||
|
||||
public void TestNFD() throws Exception{
|
||||
staticTest(NFD, canonTests, 1);
|
||||
}
|
||||
|
||||
public void TestNFC() throws Exception{
|
||||
staticTest(NFC, canonTests, 2);
|
||||
}
|
||||
|
||||
public void TestNFKD() throws Exception{
|
||||
staticTest(NFKD, compatTests, 1);
|
||||
}
|
||||
|
||||
public void TestNFKC() throws Exception{
|
||||
staticTest(NFKC, compatTests, 2);
|
||||
}
|
||||
|
||||
private void staticTest(java.text.Normalizer.Form form,
|
||||
String[][] tests,
|
||||
int outCol) throws Exception {
|
||||
for (int i = 0; i < tests.length; i++) {
|
||||
String input = tests[i][0];
|
||||
logln("Normalizing '" + input + "' (" + toHexString(input) + ")" );
|
||||
|
||||
String expect =tests[i][outCol];
|
||||
String output = java.text.Normalizer.normalize(input, form);
|
||||
|
||||
if (!output.equals(expect)) {
|
||||
errln("FAIL: case " + i
|
||||
+ " expected '" + expect + "' (" + toHexString(expect) + ")"
|
||||
+ " but got '" + output + "' (" + toHexString(output) + ")"
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// With Canonical decomposition, Hangul syllables should get decomposed
|
||||
// into Jamo, but Jamo characters should not be decomposed into
|
||||
// conjoining Jamo
|
||||
private String[][] hangulCanon = {
|
||||
// Input Decomposed Composed
|
||||
{ "\ud4db", "\u1111\u1171\u11b6", "\ud4db" },
|
||||
{ "\u1111\u1171\u11b6", "\u1111\u1171\u11b6", "\ud4db" },
|
||||
};
|
||||
|
||||
public void TestHangulCompose() throws Exception{
|
||||
logln("Canonical composition...");
|
||||
staticTest(NFC, hangulCanon, 2);
|
||||
}
|
||||
|
||||
public void TestHangulDecomp() throws Exception{
|
||||
logln("Canonical decomposition...");
|
||||
staticTest(NFD, hangulCanon, 1);
|
||||
}
|
||||
|
||||
}
|
11
test/jdk/java/text/Normalizer/ICUNormalizationTest.txt
Normal file
11
test/jdk/java/text/Normalizer/ICUNormalizationTest.txt
Normal file
@ -0,0 +1,11 @@
|
||||
#
|
||||
#
|
||||
#
|
||||
# Conformance test data which was added by Markus Scherer of IBM.
|
||||
# According to him, "more interesting conformance test cases, not in the
|
||||
# unicode.org NormalizationTest.txt".
|
||||
# Found in ConformanceTest.java in
|
||||
# src/com/ibm/icu/dev/test/normalizer/ConformanceTest.java of ICU4J 3.2.
|
||||
@Part0 # Other (ICU4J test data)
|
||||
0061 0332 0308;00E4 0332;0061 0332 0308;00E4 0332;0061 0332 0308; # Markus 0",
|
||||
0061 0301 0F73;00E1 0F71 0F72;0061 0F71 0F72 0301;00E1 0F71 0F72;0061 0F71 0F72 0301; # Markus 1"
|
17035
test/jdk/java/text/Normalizer/NormalizationTest-3.2.0.Corrigendum4.txt
Normal file
17035
test/jdk/java/text/Normalizer/NormalizationTest-3.2.0.Corrigendum4.txt
Normal file
File diff suppressed because it is too large
Load Diff
17035
test/jdk/java/text/Normalizer/NormalizationTest-3.2.0.txt
Normal file
17035
test/jdk/java/text/Normalizer/NormalizationTest-3.2.0.txt
Normal file
File diff suppressed because it is too large
Load Diff
62
test/jdk/java/text/Normalizer/SquareEraCharacterTest.java
Normal file
62
test/jdk/java/text/Normalizer/SquareEraCharacterTest.java
Normal file
@ -0,0 +1,62 @@
|
||||
/*
|
||||
* Copyright (c) 2019, 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
|
||||
* under the terms of the GNU General Public License version 2 only, as
|
||||
* published by the Free Software Foundation.
|
||||
*
|
||||
* This code is distributed in the hope that it will be useful, but WITHOUT
|
||||
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
||||
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
|
||||
* version 2 for more details (a copy is included in the LICENSE file that
|
||||
* accompanied this code).
|
||||
*
|
||||
* You should have received a copy of the GNU General Public License version
|
||||
* 2 along with this work; if not, write to the Free Software Foundation,
|
||||
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
|
||||
*
|
||||
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
|
||||
* or visit www.oracle.com if you need additional information or have any
|
||||
* questions.
|
||||
*/
|
||||
|
||||
/*
|
||||
* @test
|
||||
* @bug 8221431
|
||||
* @summary Tests decomposition of Japanese square era characters.
|
||||
* @run testng/othervm SquareEraCharacterTest
|
||||
*/
|
||||
|
||||
import static org.testng.Assert.assertEquals;
|
||||
|
||||
import java.text.Normalizer;
|
||||
|
||||
import org.testng.annotations.DataProvider;
|
||||
import org.testng.annotations.Test;
|
||||
|
||||
@Test
|
||||
public class SquareEraCharacterTest {
|
||||
|
||||
@DataProvider
|
||||
Object[][] squareEras() {
|
||||
return new Object[][] {
|
||||
|
||||
// square era character, expected decomposed string
|
||||
{'\u337e', "\u660e\u6cbb"}, // Meizi
|
||||
{'\u337d', "\u5927\u6b63"}, // Taisho
|
||||
{'\u337c', "\u662d\u548c"}, // Showa
|
||||
{'\u337b', "\u5e73\u6210"}, // Heisei
|
||||
{'\u32ff', "\u4ee4\u548c"}, // Reiwa
|
||||
};
|
||||
}
|
||||
|
||||
@Test(dataProvider="squareEras")
|
||||
public void test_normalize(char squareChar, String expected) {
|
||||
|
||||
assertEquals(
|
||||
Normalizer.normalize(Character.toString(squareChar), Normalizer.Form.NFKD),
|
||||
expected,
|
||||
"decomposing " + Character.getName(squareChar) + ".");
|
||||
}
|
||||
}
|
@ -1,429 +0,0 @@
|
||||
# GraphemeBreakTest-8.0.0.txt
|
||||
# Date: 2015-02-13, 13:47:15 GMT [MD]
|
||||
#
|
||||
# Unicode Character Database
|
||||
# Copyright (c) 1991-2015 Unicode, Inc.
|
||||
# For terms of use, see http://www.unicode.org/terms_of_use.html
|
||||
# For documentation, see http://www.unicode.org/reports/tr44/
|
||||
#
|
||||
# Default Grapheme Break Test
|
||||
#
|
||||
# Format:
|
||||
# <string> (# <comment>)?
|
||||
# <string> contains hex Unicode code points, with
|
||||
# ÷ wherever there is a break opportunity, and
|
||||
# × wherever there is not.
|
||||
# <comment> the format can change, but currently it shows:
|
||||
# - the sample character name
|
||||
# - (x) the Grapheme_Cluster_Break property value for the sample character
|
||||
# - [x] the rule that determines whether there is a break or not
|
||||
#
|
||||
# These samples may be extended or changed in the future.
|
||||
#
|
||||
÷ 0020 ÷ 0020 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0020 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0020 ÷ 000D ÷ # ÷ [0.2] SPACE (Other) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 000D ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0020 ÷ 000A ÷ # ÷ [0.2] SPACE (Other) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 000A ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0020 ÷ 0001 ÷ # ÷ [0.2] SPACE (Other) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0001 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0020 × 0300 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 0020 × 0308 × 0300 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 0020 × 0903 ÷ # ÷ [0.2] SPACE (Other) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0020 × 0308 × 0903 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0020 ÷ 1100 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 1100 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0020 ÷ 1160 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 1160 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0020 ÷ 11A8 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 11A8 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0020 ÷ AC00 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ AC00 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0020 ÷ AC01 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ AC01 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0020 ÷ 1F1E6 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 0020 ÷ 0378 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0378 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0020 ÷ D800 ÷ # ÷ [0.2] SPACE (Other) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ D800 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 000D ÷ 0020 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ 0020 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 000D ÷ 000D ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ 000D ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 000D × 000A ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) × [3.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ 000A ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 000D ÷ 0001 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ 0001 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 000D ÷ 0300 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 × 0300 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 000D ÷ 0903 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 × 0903 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 000D ÷ 1100 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ 1100 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 000D ÷ 1160 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ 1160 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 000D ÷ 11A8 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ 11A8 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 000D ÷ AC00 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ AC00 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 000D ÷ AC01 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ AC01 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 000D ÷ 1F1E6 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 000D ÷ 0378 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ 0378 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 000D ÷ D800 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 000D ÷ 0308 ÷ D800 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 000A ÷ 0020 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ 0020 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 000A ÷ 000D ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ 000D ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 000A ÷ 000A ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ 000A ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 000A ÷ 0001 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ 0001 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 000A ÷ 0300 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 × 0300 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 000A ÷ 0903 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 × 0903 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 000A ÷ 1100 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ 1100 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 000A ÷ 1160 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ 1160 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 000A ÷ 11A8 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ 11A8 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 000A ÷ AC00 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ AC00 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 000A ÷ AC01 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ AC01 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 000A ÷ 1F1E6 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 000A ÷ 0378 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ 0378 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 000A ÷ D800 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 000A ÷ 0308 ÷ D800 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 0001 ÷ 0020 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ 0020 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0001 ÷ 000D ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ 000D ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0001 ÷ 000A ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ 000A ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0001 ÷ 0001 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ 0001 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0001 ÷ 0300 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 × 0300 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 0001 ÷ 0903 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 × 0903 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0001 ÷ 1100 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ 1100 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0001 ÷ 1160 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ 1160 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0001 ÷ 11A8 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ 11A8 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0001 ÷ AC00 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ AC00 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0001 ÷ AC01 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ AC01 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0001 ÷ 1F1E6 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 0001 ÷ 0378 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ 0378 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0001 ÷ D800 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 0001 ÷ 0308 ÷ D800 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 0300 ÷ 0020 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ 0020 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0300 ÷ 000D ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ 000D ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0300 ÷ 000A ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ 000A ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0300 ÷ 0001 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ 0001 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0300 × 0300 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 0300 × 0308 × 0300 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 0300 × 0903 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0300 × 0308 × 0903 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0300 ÷ 1100 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ 1100 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0300 ÷ 1160 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ 1160 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0300 ÷ 11A8 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ 11A8 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0300 ÷ AC00 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ AC00 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0300 ÷ AC01 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ AC01 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0300 ÷ 1F1E6 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 0300 ÷ 0378 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ 0378 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0300 ÷ D800 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 0300 × 0308 ÷ D800 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 0903 ÷ 0020 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ 0020 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0903 ÷ 000D ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ 000D ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0903 ÷ 000A ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ 000A ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0903 ÷ 0001 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ 0001 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0903 × 0300 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 0903 × 0308 × 0300 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 0903 × 0903 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0903 × 0308 × 0903 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0903 ÷ 1100 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ 1100 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0903 ÷ 1160 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ 1160 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0903 ÷ 11A8 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ 11A8 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0903 ÷ AC00 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ AC00 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0903 ÷ AC01 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ AC01 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0903 ÷ 1F1E6 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 0903 ÷ 0378 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ 0378 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0903 ÷ D800 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 0903 × 0308 ÷ D800 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 1100 ÷ 0020 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ 0020 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 1100 ÷ 000D ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ 000D ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 1100 ÷ 000A ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ 000A ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 1100 ÷ 0001 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ 0001 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 1100 × 0300 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 1100 × 0308 × 0300 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 1100 × 0903 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 1100 × 0308 × 0903 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 1100 × 1100 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ 1100 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 1100 × 1160 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ 1160 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 1100 ÷ 11A8 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ 11A8 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 1100 × AC00 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 1100 × AC01 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 1100 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 1100 ÷ 0378 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 1100 ÷ D800 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 1100 × 0308 ÷ D800 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 1160 ÷ 0020 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ 0020 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 1160 ÷ 000D ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ 000D ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 1160 ÷ 000A ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ 000A ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 1160 ÷ 0001 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ 0001 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 1160 × 0300 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 1160 × 0308 × 0300 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 1160 × 0903 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 1160 × 0308 × 0903 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 1160 ÷ 1100 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ 1100 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 1160 × 1160 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [7.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ 1160 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 1160 × 11A8 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [7.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ 11A8 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 1160 ÷ AC00 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 1160 ÷ AC01 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 1160 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 1160 ÷ 0378 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 1160 ÷ D800 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 1160 × 0308 ÷ D800 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 11A8 ÷ 0020 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ 0020 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 11A8 ÷ 000D ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ 000D ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 11A8 ÷ 000A ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ 000A ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 11A8 ÷ 0001 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ 0001 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 11A8 × 0300 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 11A8 × 0308 × 0300 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 11A8 × 0903 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 11A8 × 0308 × 0903 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 11A8 ÷ 1100 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ 1100 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 11A8 ÷ 1160 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ 1160 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 11A8 × 11A8 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [8.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ 11A8 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 11A8 ÷ AC00 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 11A8 ÷ AC01 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 11A8 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 11A8 ÷ 0378 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 11A8 ÷ D800 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 11A8 × 0308 ÷ D800 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ AC00 ÷ 0020 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ 0020 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ AC00 ÷ 000D ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ 000D ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ AC00 ÷ 000A ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ 000A ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ AC00 ÷ 0001 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ 0001 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ AC00 × 0300 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ AC00 × 0308 × 0300 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ AC00 × 0903 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ AC00 × 0308 × 0903 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ AC00 ÷ 1100 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ 1100 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ AC00 × 1160 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [7.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ 1160 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ AC00 × 11A8 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [7.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ 11A8 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ AC00 ÷ AC00 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ AC00 ÷ AC01 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ AC00 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ AC00 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ AC00 ÷ D800 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ AC00 × 0308 ÷ D800 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ AC01 ÷ 0020 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ 0020 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ AC01 ÷ 000D ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ 000D ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ AC01 ÷ 000A ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ 000A ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ AC01 ÷ 0001 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ 0001 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ AC01 × 0300 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ AC01 × 0308 × 0300 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ AC01 × 0903 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ AC01 × 0308 × 0903 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ AC01 ÷ 1100 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ 1100 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ AC01 ÷ 1160 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ 1160 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ AC01 × 11A8 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [8.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ 11A8 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ AC01 ÷ AC00 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ AC01 ÷ AC01 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ AC01 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ AC01 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ AC01 ÷ D800 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ AC01 × 0308 ÷ D800 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ 0020 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ 0020 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ 000D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ 000D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ 000A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ 000A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ 0001 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ 0001 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 1F1E6 × 0300 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 × 0300 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 1F1E6 × 0903 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 × 0903 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ 1100 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ 1100 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ 1160 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ 1160 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ 11A8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ 11A8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ AC00 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ AC00 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ AC01 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ AC01 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 1F1E6 × 1F1E6 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ 0378 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ 0378 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 1F1E6 ÷ D800 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 1F1E6 × 0308 ÷ D800 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 0378 ÷ 0020 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ 0020 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0378 ÷ 000D ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ 000D ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0378 ÷ 000A ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ 000A ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0378 ÷ 0001 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ 0001 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ 0378 × 0300 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 0378 × 0308 × 0300 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ 0378 × 0903 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0378 × 0308 × 0903 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ 0378 ÷ 1100 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ 1100 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ 0378 ÷ 1160 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ 1160 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ 0378 ÷ 11A8 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ 11A8 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ 0378 ÷ AC00 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ AC00 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ 0378 ÷ AC01 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ AC01 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ 0378 ÷ 1F1E6 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ 0378 ÷ 0378 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ 0378 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ 0378 ÷ D800 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 0378 × 0308 ÷ D800 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ D800 ÷ 0020 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] SPACE (Other) ÷ [0.3]
|
||||
÷ D800 ÷ 0308 ÷ 0020 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ D800 ÷ 000D ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ D800 ÷ 0308 ÷ 000D ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ D800 ÷ 000A ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ D800 ÷ 0308 ÷ 000A ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ D800 ÷ 0001 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ D800 ÷ 0308 ÷ 0001 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
|
||||
÷ D800 ÷ 0300 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ D800 ÷ 0308 × 0300 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
|
||||
÷ D800 ÷ 0903 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ D800 ÷ 0308 × 0903 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
|
||||
÷ D800 ÷ 1100 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ D800 ÷ 0308 ÷ 1100 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
|
||||
÷ D800 ÷ 1160 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ D800 ÷ 0308 ÷ 1160 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
|
||||
÷ D800 ÷ 11A8 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ D800 ÷ 0308 ÷ 11A8 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
|
||||
÷ D800 ÷ AC00 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ D800 ÷ 0308 ÷ AC00 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
|
||||
÷ D800 ÷ AC01 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ D800 ÷ 0308 ÷ AC01 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
|
||||
÷ D800 ÷ 1F1E6 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ D800 ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
|
||||
÷ D800 ÷ 0378 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ D800 ÷ 0308 ÷ 0378 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
|
||||
÷ D800 ÷ D800 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ D800 ÷ 0308 ÷ D800 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
|
||||
÷ 0061 ÷ 1F1E6 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
|
||||
÷ 1F1F7 × 1F1FA ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) ÷ [0.3]
|
||||
÷ 1F1F7 × 1F1FA × 1F1F8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER S (Regional_Indicator) ÷ [0.3]
|
||||
÷ 1F1F7 × 1F1FA × 1F1F8 × 1F1EA ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER S (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER E (Regional_Indicator) ÷ [0.3]
|
||||
÷ 1F1F7 × 1F1FA ÷ 200B ÷ 1F1F8 × 1F1EA ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) ÷ [5.0] ZERO WIDTH SPACE (Control) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER S (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER E (Regional_Indicator) ÷ [0.3]
|
||||
÷ 1F1E6 × 1F1E7 × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER B (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER C (Regional_Indicator) ÷ [0.3]
|
||||
÷ 1F1E6 × 200D ÷ 1F1E7 × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] ZERO WIDTH JOINER (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER B (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER C (Regional_Indicator) ÷ [0.3]
|
||||
÷ 1F1E6 × 1F1E7 × 200D ÷ 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER B (Regional_Indicator) × [9.0] ZERO WIDTH JOINER (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER C (Regional_Indicator) ÷ [0.3]
|
||||
÷ 0020 × 200D ÷ 0646 ÷ # ÷ [0.2] SPACE (Other) × [9.0] ZERO WIDTH JOINER (Extend) ÷ [999.0] ARABIC LETTER NOON (Other) ÷ [0.3]
|
||||
÷ 0646 × 200D ÷ 0020 ÷ # ÷ [0.2] ARABIC LETTER NOON (Other) × [9.0] ZERO WIDTH JOINER (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
|
||||
#
|
||||
# Lines: 402
|
||||
#
|
||||
# EOF
|
@ -1,5 +1,5 @@
|
||||
/*
|
||||
* Copyright (c) 2016, Oracle and/or its affiliates. All rights reserved.
|
||||
* Copyright (c) 2016, 2019, 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
|
||||
@ -23,8 +23,9 @@
|
||||
|
||||
/*
|
||||
* @test
|
||||
* @bug 7071819
|
||||
* @bug 7071819 8221431
|
||||
* @summary tests Unicode Extended Grapheme support
|
||||
* @library /lib/testlibrary/java/lang
|
||||
* @run main GraphemeTest
|
||||
*/
|
||||
|
||||
@ -41,15 +42,14 @@ import java.util.regex.Matcher;
|
||||
public class GraphemeTest {
|
||||
|
||||
public static void main(String[] args) throws Throwable {
|
||||
testProps(Paths.get(System.getProperty("test.src", "."),
|
||||
"GraphemeBreakProperty.txt"));
|
||||
testBreak(Paths.get(System.getProperty("test.src", "."),
|
||||
"GraphemeBreakTest.txt"));
|
||||
testProps(UCDFiles.GRAPHEME_BREAK_PROPERTY);
|
||||
testProps(UCDFiles.EMOJI_DATA);
|
||||
}
|
||||
|
||||
private static void testProps(Path path) throws IOException {
|
||||
Files.lines(path)
|
||||
.filter( ln -> ln.length() != 0 && !ln.startsWith("#") )
|
||||
.map( ln -> ln.replaceFirst("#.*", "") )
|
||||
.filter( ln -> ln.length() != 0 )
|
||||
.forEach(ln -> {
|
||||
String[] strs = ln.split("\\s+");
|
||||
int off = strs[0].indexOf("..");
|
||||
@ -62,6 +62,11 @@ public class GraphemeTest {
|
||||
cp0 = cp1 = Integer.parseInt(strs[0], 16);
|
||||
}
|
||||
for (int cp = cp0; cp <= cp1; cp++) {
|
||||
// Ignore Emoji* for now (only interested in Extended_Pictographic)
|
||||
if (expected.startsWith("Emoji")) {
|
||||
continue;
|
||||
}
|
||||
|
||||
// NOTE:
|
||||
// #tr29 "plus a few General_Category = Spacing_Mark needed for
|
||||
// canonical equivalence."
|
||||
@ -81,68 +86,39 @@ public class GraphemeTest {
|
||||
});
|
||||
}
|
||||
|
||||
private static void testBreak(Path path) throws IOException {
|
||||
Files.lines(path)
|
||||
.filter( ln -> ln.length() != 0 && !ln.startsWith("#") )
|
||||
.forEach(ln -> {
|
||||
String str = ln.replaceAll("\\s+|\\([a-zA-Z]+\\)|\\[[a-zA-Z]]+\\]|#.*", "");
|
||||
// System.out.println(str);
|
||||
String[] cstrs = str.split("\u00f7|\u00d7");
|
||||
int prevCp = -1;
|
||||
char prevBk = '\u00f7';
|
||||
int offBk = 0;
|
||||
for (String cstr : cstrs) {
|
||||
if (cstr.length() == 0) // first empty str
|
||||
continue;
|
||||
int cp = Integer.parseInt(cstr, 16);
|
||||
if (prevCp == -1) {
|
||||
prevCp = cp;
|
||||
} else {
|
||||
// test against the rules directly
|
||||
if (rules[getType(prevCp)][getType(cp)] != (prevBk == '\u00f7')) {
|
||||
throw new RuntimeException(String.format(
|
||||
"NG %x[%d] %x[%d] -> %b [%s]%n",
|
||||
prevCp, getType(prevCp), cp, getType(cp),
|
||||
rules[getType(prevCp)][getType(cp)],
|
||||
ln));
|
||||
}
|
||||
}
|
||||
prevCp = cp;
|
||||
offBk += (cstr.length() + 1);
|
||||
prevBk = str.charAt(offBk);
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
private static final String[] types = {
|
||||
"Other", "CR", "LF", "Control", "Extend", "Regional_Indicator",
|
||||
"Other", "CR", "LF", "Control", "Extend", "ZWJ", "Regional_Indicator",
|
||||
"Prepend", "SpacingMark",
|
||||
"L", "V", "T", "LV", "LVT" };
|
||||
"L", "V", "T", "LV", "LVT",
|
||||
"Extended_Pictographic" };
|
||||
|
||||
///////////////////////////////////////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
// from java.util.regex.Grapheme.java
|
||||
// types
|
||||
private static final int OTHER = 0;
|
||||
private static final int CR = 1;
|
||||
private static final int LF = 2;
|
||||
private static final int CONTROL = 3;
|
||||
private static final int EXTEND = 4;
|
||||
private static final int RI = 5;
|
||||
private static final int PREPEND = 6;
|
||||
private static final int SPACINGMARK = 7;
|
||||
private static final int L = 8;
|
||||
private static final int V = 9;
|
||||
private static final int T = 10;
|
||||
private static final int LV = 11;
|
||||
private static final int LVT = 12;
|
||||
private static final int ZWJ = 5;
|
||||
private static final int RI = 6;
|
||||
private static final int PREPEND = 7;
|
||||
private static final int SPACINGMARK = 8;
|
||||
private static final int L = 9;
|
||||
private static final int V = 10;
|
||||
private static final int T = 11;
|
||||
private static final int LV = 12;
|
||||
private static final int LVT = 13;
|
||||
private static final int EXTENDED_PICTOGRAPHIC = 14;
|
||||
|
||||
private static final int FIRST_TYPE = 0;
|
||||
private static final int LAST_TYPE = 12;
|
||||
private static final int LAST_TYPE = 14;
|
||||
|
||||
private static boolean[][] rules;
|
||||
static {
|
||||
rules = new boolean[LAST_TYPE + 1][LAST_TYPE + 1];
|
||||
// default, any + any
|
||||
// GB 999 Any + Any -> default
|
||||
for (int i = FIRST_TYPE; i <= LAST_TYPE; i++)
|
||||
for (int j = FIRST_TYPE; j <= LAST_TYPE; j++)
|
||||
rules[i][j] = true;
|
||||
@ -159,13 +135,12 @@ public class GraphemeTest {
|
||||
// GB 8 (LVT | T) x T
|
||||
rules[LVT][T] = false;
|
||||
rules[T][T] = false;
|
||||
// GB 8a RI x RI
|
||||
rules[RI][RI] = false;
|
||||
// GB 9 x Extend
|
||||
// GB 9 x (Extend|ZWJ)
|
||||
// GB 9a x Spacing Mark
|
||||
// GB 9b Prepend x
|
||||
for (int i = FIRST_TYPE; i <= LAST_TYPE; i++) {
|
||||
rules[i][EXTEND] = false;
|
||||
rules[i][ZWJ] = false;
|
||||
rules[i][SPACINGMARK] = false;
|
||||
rules[PREPEND][i] = false;
|
||||
}
|
||||
@ -178,7 +153,9 @@ public class GraphemeTest {
|
||||
}
|
||||
// GB 3 CR x LF
|
||||
rules[CR][LF] = false;
|
||||
// GB 10 Any + Any -> default
|
||||
// GB 11 Exended_Pictographic x (Extend|ZWJ)
|
||||
rules[EXTENDED_PICTOGRAPHIC][EXTEND] = false;
|
||||
rules[EXTENDED_PICTOGRAPHIC][ZWJ] = false;
|
||||
}
|
||||
|
||||
// Hangul syllables
|
||||
@ -204,7 +181,12 @@ public class GraphemeTest {
|
||||
cp == 0xAA7B || cp == 0xAA7D;
|
||||
}
|
||||
|
||||
@SuppressWarnings("fallthrough")
|
||||
private static int getType(int cp) {
|
||||
if (isExtendedPictographic(cp)) {
|
||||
return EXTENDED_PICTOGRAPHIC;
|
||||
}
|
||||
|
||||
int type = Character.getType(cp);
|
||||
switch(type) {
|
||||
case Character.CONTROL:
|
||||
@ -213,28 +195,36 @@ public class GraphemeTest {
|
||||
if (cp == 0x000A)
|
||||
return LF;
|
||||
return CONTROL;
|
||||
case Character.UNASSIGNED:
|
||||
case Character.UNASSIGNED:
|
||||
// NOTE: #tr29 lists "Unassigned and Default_Ignorable_Code_Point" as Control
|
||||
// but GraphemeBreakTest.txt lists u+0378/reserved-0378 as "Other"
|
||||
// so type it as "Other" to make the test happy
|
||||
if (cp == 0x0378)
|
||||
return OTHER;
|
||||
if (cp == 0x0378)
|
||||
return OTHER;
|
||||
|
||||
case Character.LINE_SEPARATOR:
|
||||
case Character.PARAGRAPH_SEPARATOR:
|
||||
case Character.SURROGATE:
|
||||
return CONTROL;
|
||||
case Character.FORMAT:
|
||||
if (cp == 0x200C || cp == 0x200D)
|
||||
if (cp == 0x200C ||
|
||||
cp >= 0xE0020 && cp <= 0xE007F)
|
||||
return EXTEND;
|
||||
if (cp == 0x200D)
|
||||
return ZWJ;
|
||||
if (cp >= 0x0600 && cp <= 0x0605 ||
|
||||
cp == 0x06DD || cp == 0x070F || cp == 0x08E2 ||
|
||||
cp == 0x110BD || cp == 0x110CD)
|
||||
return PREPEND;
|
||||
return CONTROL;
|
||||
case Character.NON_SPACING_MARK:
|
||||
case Character.ENCLOSING_MARK:
|
||||
// NOTE:
|
||||
// #tr29 "plus a few General_Category = Spacing_Mark needed for
|
||||
// canonical equivalence."
|
||||
// but for "extended grapheme clusters" support, there is no
|
||||
// need actually to diff "extend" and "spackmark" given GB9, GB9a
|
||||
return EXTEND;
|
||||
// NOTE:
|
||||
// #tr29 "plus a few General_Category = Spacing_Mark needed for
|
||||
// canonical equivalence."
|
||||
// but for "extended grapheme clusters" support, there is no
|
||||
// need actually to diff "extend" and "spackmark" given GB9, GB9a
|
||||
return EXTEND;
|
||||
case Character.COMBINING_SPACING_MARK:
|
||||
if (isExcludedSpacingMark(cp))
|
||||
return OTHER;
|
||||
@ -248,9 +238,11 @@ public class GraphemeTest {
|
||||
return RI;
|
||||
return OTHER;
|
||||
case Character.MODIFIER_LETTER:
|
||||
case Character.MODIFIER_SYMBOL:
|
||||
// WARNING:
|
||||
// not mentioned in #tr29 but listed in GraphemeBreakProperty.txt
|
||||
if (cp == 0xFF9E || cp == 0xFF9F)
|
||||
if (cp == 0xFF9E || cp == 0xFF9F ||
|
||||
cp >= 0x1F3FB && cp <= 0x1F3FF)
|
||||
return EXTEND;
|
||||
return OTHER;
|
||||
case Character.OTHER_LETTER:
|
||||
@ -280,7 +272,113 @@ public class GraphemeTest {
|
||||
return V;
|
||||
if (cp >= 0xD7CB && cp <= 0xD7FB)
|
||||
return T;
|
||||
|
||||
// Prepend
|
||||
switch (cp) {
|
||||
case 0x0D4E:
|
||||
case 0x111C2:
|
||||
case 0x111C3:
|
||||
case 0x11A3A:
|
||||
case 0x11A84:
|
||||
case 0x11A85:
|
||||
case 0x11A86:
|
||||
case 0x11A87:
|
||||
case 0x11A88:
|
||||
case 0x11A89:
|
||||
case 0x11D46:
|
||||
return PREPEND;
|
||||
}
|
||||
}
|
||||
return OTHER;
|
||||
}
|
||||
|
||||
// from generated java.util.regex.EmojiData.java
|
||||
static boolean isExtendedPictographic(int cp) {
|
||||
return
|
||||
cp == 0x00A9 ||
|
||||
cp == 0x00AE ||
|
||||
cp == 0x203C ||
|
||||
cp == 0x2049 ||
|
||||
cp == 0x2122 ||
|
||||
cp == 0x2139 ||
|
||||
(cp >= 0x2194 && cp <= 0x2199) ||
|
||||
cp == 0x21A9 ||
|
||||
cp == 0x21AA ||
|
||||
cp == 0x231A ||
|
||||
cp == 0x231B ||
|
||||
cp == 0x2328 ||
|
||||
cp == 0x2388 ||
|
||||
cp == 0x23CF ||
|
||||
(cp >= 0x23E9 && cp <= 0x23F3) ||
|
||||
(cp >= 0x23F8 && cp <= 0x23FA) ||
|
||||
cp == 0x24C2 ||
|
||||
cp == 0x25AA ||
|
||||
cp == 0x25AB ||
|
||||
cp == 0x25B6 ||
|
||||
cp == 0x25C0 ||
|
||||
(cp >= 0x25FB && cp <= 0x25FE) ||
|
||||
(cp >= 0x2600 && cp <= 0x2605) ||
|
||||
(cp >= 0x2607 && cp <= 0x2612) ||
|
||||
(cp >= 0x2614 && cp <= 0x2685) ||
|
||||
(cp >= 0x2690 && cp <= 0x2705) ||
|
||||
(cp >= 0x2708 && cp <= 0x2712) ||
|
||||
cp == 0x2714 ||
|
||||
cp == 0x2716 ||
|
||||
cp == 0x271D ||
|
||||
cp == 0x2721 ||
|
||||
cp == 0x2728 ||
|
||||
cp == 0x2733 ||
|
||||
cp == 0x2734 ||
|
||||
cp == 0x2744 ||
|
||||
cp == 0x2747 ||
|
||||
cp == 0x274C ||
|
||||
cp == 0x274E ||
|
||||
(cp >= 0x2753 && cp <= 0x2755) ||
|
||||
cp == 0x2757 ||
|
||||
(cp >= 0x2763 && cp <= 0x2767) ||
|
||||
(cp >= 0x2795 && cp <= 0x2797) ||
|
||||
cp == 0x27A1 ||
|
||||
cp == 0x27B0 ||
|
||||
cp == 0x27BF ||
|
||||
cp == 0x2934 ||
|
||||
cp == 0x2935 ||
|
||||
(cp >= 0x2B05 && cp <= 0x2B07) ||
|
||||
cp == 0x2B1B ||
|
||||
cp == 0x2B1C ||
|
||||
cp == 0x2B50 ||
|
||||
cp == 0x2B55 ||
|
||||
cp == 0x3030 ||
|
||||
cp == 0x303D ||
|
||||
cp == 0x3297 ||
|
||||
cp == 0x3299 ||
|
||||
(cp >= 0x1F000 && cp <= 0x1F0FF) ||
|
||||
(cp >= 0x1F10D && cp <= 0x1F10F) ||
|
||||
cp == 0x1F12F ||
|
||||
(cp >= 0x1F16C && cp <= 0x1F171) ||
|
||||
cp == 0x1F17E ||
|
||||
cp == 0x1F17F ||
|
||||
cp == 0x1F18E ||
|
||||
(cp >= 0x1F191 && cp <= 0x1F19A) ||
|
||||
(cp >= 0x1F1AD && cp <= 0x1F1E5) ||
|
||||
(cp >= 0x1F201 && cp <= 0x1F20F) ||
|
||||
cp == 0x1F21A ||
|
||||
cp == 0x1F22F ||
|
||||
(cp >= 0x1F232 && cp <= 0x1F23A) ||
|
||||
(cp >= 0x1F23C && cp <= 0x1F23F) ||
|
||||
(cp >= 0x1F249 && cp <= 0x1F3FA) ||
|
||||
(cp >= 0x1F400 && cp <= 0x1F53D) ||
|
||||
(cp >= 0x1F546 && cp <= 0x1F64F) ||
|
||||
(cp >= 0x1F680 && cp <= 0x1F6FF) ||
|
||||
(cp >= 0x1F774 && cp <= 0x1F77F) ||
|
||||
(cp >= 0x1F7D5 && cp <= 0x1F7FF) ||
|
||||
(cp >= 0x1F80C && cp <= 0x1F80F) ||
|
||||
(cp >= 0x1F848 && cp <= 0x1F84F) ||
|
||||
(cp >= 0x1F85A && cp <= 0x1F85F) ||
|
||||
(cp >= 0x1F888 && cp <= 0x1F88F) ||
|
||||
(cp >= 0x1F8AE && cp <= 0x1F8FF) ||
|
||||
(cp >= 0x1F90C && cp <= 0x1F93A) ||
|
||||
(cp >= 0x1F93C && cp <= 0x1F945) ||
|
||||
(cp >= 0x1F947 && cp <= 0x1FFFD);
|
||||
|
||||
}
|
||||
}
|
||||
|
@ -35,9 +35,10 @@
|
||||
* 8027645 8035076 8039124 8035975 8074678 6854417 8143854 8147531 7071819
|
||||
* 8151481 4867170 7080302 6728861 6995635 6736245 4916384 6328855 6192895
|
||||
* 6345469 6988218 6693451 7006761 8140212 8143282 8158482 8176029 8184706
|
||||
* 8194667 8197462 8184692
|
||||
* 8194667 8197462 8184692 8221431
|
||||
*
|
||||
* @library /test/lib
|
||||
* @library /lib/testlibrary/java/lang
|
||||
* @build jdk.test.lib.RandomFactory
|
||||
* @run main RegExTest
|
||||
* @key randomness
|
||||
@ -4755,8 +4756,7 @@ public class RegExTest {
|
||||
}
|
||||
|
||||
private static void grapheme() throws Exception {
|
||||
Files.lines(Paths.get(System.getProperty("test.src", "."),
|
||||
"GraphemeBreakTest.txt"))
|
||||
Files.lines(UCDFiles.GRAPHEME_BREAK_TEST)
|
||||
.filter( ln -> ln.length() != 0 && !ln.startsWith("#") )
|
||||
.forEach( ln -> {
|
||||
ln = ln.replaceAll("\\s+|\\([a-zA-Z]+\\)|\\[[a-zA-Z]]+\\]|#.*", "");
|
||||
|
57
test/jdk/lib/testlibrary/java/lang/UCDFiles.java
Normal file
57
test/jdk/lib/testlibrary/java/lang/UCDFiles.java
Normal file
@ -0,0 +1,57 @@
|
||||
/*
|
||||
* Copyright (c) 2019, 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
|
||||
* under the terms of the GNU General Public License version 2 only, as
|
||||
* published by the Free Software Foundation.
|
||||
*
|
||||
* This code is distributed in the hope that it will be useful, but WITHOUT
|
||||
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
||||
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
|
||||
* version 2 for more details (a copy is included in the LICENSE file that
|
||||
* accompanied this code).
|
||||
*
|
||||
* You should have received a copy of the GNU General Public License version
|
||||
* 2 along with this work; if not, write to the Free Software Foundation,
|
||||
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
|
||||
*
|
||||
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
|
||||
* or visit www.oracle.com if you need additional information or have any
|
||||
* questions.
|
||||
*/
|
||||
|
||||
/**
|
||||
* Holds the file paths to the Unicode Character Database source files.
|
||||
* Paths to the source files in the "make" directory are relative, and
|
||||
* subject to change due to future repository structure re-org.
|
||||
*/
|
||||
|
||||
import java.nio.file.Path;
|
||||
import java.nio.file.Paths;
|
||||
|
||||
public class UCDFiles {
|
||||
public static Path UCD_DIR = Paths.get(
|
||||
System.getProperty("test.root"), "..", "..", "make", "data", "unicodedata");
|
||||
|
||||
public static Path BLOCKS =
|
||||
UCD_DIR.resolve("Blocks.txt");
|
||||
public static Path GRAPHEME_BREAK_PROPERTY =
|
||||
UCD_DIR.resolve("auxiliary").resolve("GraphemeBreakProperty.txt");
|
||||
public static Path GRAPHEME_BREAK_TEST =
|
||||
UCD_DIR.resolve("auxiliary").resolve("GraphemeBreakTest.txt");
|
||||
public static Path NORMALIZATION_TEST =
|
||||
UCD_DIR.resolve("NormalizationTest.txt");
|
||||
public static Path PROP_LIST =
|
||||
UCD_DIR.resolve("PropList.txt");
|
||||
public static Path PROPERTY_VALUE_ALIASES =
|
||||
UCD_DIR.resolve("PropertyValueAliases.txt");
|
||||
public static Path SCRIPTS =
|
||||
UCD_DIR.resolve("Scripts.txt");
|
||||
public static Path SPECIAL_CASING =
|
||||
UCD_DIR.resolve("SpecialCasing.txt");
|
||||
public static Path UNICODE_DATA =
|
||||
UCD_DIR.resolve("UnicodeData.txt");
|
||||
public static Path EMOJI_DATA =
|
||||
UCD_DIR.resolve("emoji-data.txt");
|
||||
}
|
Loading…
Reference in New Issue
Block a user