infernap12/jdk
1
0
Fork 0
mirror of https://github.com/openjdk/jdk.git synced 2026-02-24 09:10:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

7070436: Support Unicode 6.1.0 in JDK 8

Browse Source 
Reviewed-by: okutsu
This commit is contained in:
Yuka Kamiya 2012-03-29 18:02:36 +09:00
parent 193b4ea20e
commit e127bc8acf
16 changed files with 2479 additions and 1020 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
jdk/make/tools/GenerateCharacter/CharacterData00.java.template
View File

@ -1,5 +1,5 @@
/*
* Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2003, 2012, 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
@ -211,6 +211,8 @@ class CharacterData00 extends CharacterData {
case 0x10C3 : mapChar = 0x2D23; break;
case 0x10C4 : mapChar = 0x2D24; break;
case 0x10C5 : mapChar = 0x2D25; break;
case 0x10C7 : mapChar = 0x2D27; break;
case 0x10CD : mapChar = 0x2D2D; break;
case 0x1E9E : mapChar = 0x00DF; break;
case 0x2C62 : mapChar = 0x026B; break;
case 0x2C63 : mapChar = 0x1D7D; break;
@ -223,6 +225,7 @@ class CharacterData00 extends CharacterData {
case 0x2C7F : mapChar = 0x0240; break;
case 0xA77D : mapChar = 0x1D79; break;
case 0xA78D : mapChar = 0x0265; break;
case 0xA7AA : mapChar = 0x0266; break;
// default mapChar is already set, so no
// need to redo it here.
// default : mapChar = ch;
@ -282,6 +285,7 @@ class CharacterData00 extends CharacterData {
case 0x0251 : mapChar = 0x2C6D; break;
case 0x0252 : mapChar = 0x2C70; break;
case 0x0265 : mapChar = 0xA78D; break;
case 0x0266 : mapChar = 0xA7AA; break;
case 0x026B : mapChar = 0x2C62; break;
case 0x0271 : mapChar = 0x2C6E; break;
case 0x027D : mapChar = 0x2C64; break;
@ -327,6 +331,8 @@ class CharacterData00 extends CharacterData {
case 0x2D23 : mapChar = 0x10C3; break;
case 0x2D24 : mapChar = 0x10C4; break;
case 0x2D25 : mapChar = 0x10C5; break;
case 0x2D27 : mapChar = 0x10C7; break;
case 0x2D2D : mapChar = 0x10CD; break;
// ch must have a 1:M case mapping, but we
// can't handle it here. Return ch.
// since mapChar is already set, no need
@ -425,6 +431,11 @@ class CharacterData00 extends CharacterData {
case 0x2181: retval = 5000; break; // ROMAN NUMERAL FIVE THOUSAND
case 0x2182: retval = 10000; break; // ROMAN NUMERAL TEN THOUSAND
case 0x324B: retval = 40; break;
case 0x324C: retval = 50; break;
case 0x324D: retval = 60; break;
case 0x324E: retval = 70; break;
case 0x324F: retval = 80; break;
case 0x325C: retval = 32; break;
case 0x325D: retval = 33; break; // CIRCLED NUMBER THIRTY THREE
@ -527,6 +538,7 @@ class CharacterData00 extends CharacterData {
case 0x0251 : mapChar = 0x2C6D; break;
case 0x0252 : mapChar = 0x2C70; break;
case 0x0265 : mapChar = 0xA78D; break;
case 0x0266 : mapChar = 0xA7AA; break;
case 0x026B : mapChar = 0x2C62; break;
case 0x0271 : mapChar = 0x2C6E; break;
case 0x027D : mapChar = 0x2C64; break;
@ -572,6 +584,8 @@ class CharacterData00 extends CharacterData {
case 0x2D23 : mapChar = 0x10C3; break;
case 0x2D24 : mapChar = 0x10C4; break;
case 0x2D25 : mapChar = 0x10C5; break;
case 0x2D27 : mapChar = 0x10C7; break;
case 0x2D2D : mapChar = 0x10CD; break;
default : mapChar = Character.ERROR; break;
}
}

155
jdk/make/tools/UnicodeData/PropList.txt
View File

@ -1,8 +1,8 @@
# PropList-6.0.0.txt
# Date: 2010-08-19, 00:48:28 GMT [MD]
# PropList-6.1.0.txt
# Date: 2011-11-30, 01:49:54 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2010 Unicode, Inc.
# Copyright (c) 1991-2011 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
@ -50,6 +50,7 @@
2212 ; Dash # Sm MINUS SIGN
2E17 ; Dash # Pd DOUBLE OBLIQUE HYPHEN
2E1A ; Dash # Pd HYPHEN WITH DIAERESIS
2E3A..2E3B ; Dash # Pd [2] TWO-EM DASH..THREE-EM DASH
301C ; Dash # Pd WAVE DASH
3030 ; Dash # Pd WAVY DASH
30A0 ; Dash # Pd KATAKANA-HIRAGANA DOUBLE HYPHEN
@ -58,7 +59,7 @@ FE58 ; Dash # Pd SMALL EM DASH
FE63 ; Dash # Pd SMALL HYPHEN-MINUS
FF0D ; Dash # Pd FULLWIDTH HYPHEN-MINUS
# Total code points: 25
# Total code points: 27
# ================================================
@ -158,6 +159,7 @@ A92F ; Terminal_Punctuation # Po KAYAH LI SIGN SHYA
A9C7..A9C9 ; Terminal_Punctuation # Po [3] JAVANESE PADA PANGKAT..JAVANESE PADA LUNGSI
AA5D..AA5F ; Terminal_Punctuation # Po [3] CHAM PUNCTUATION DANDA..CHAM PUNCTUATION TRIPLE DANDA
AADF ; Terminal_Punctuation # Po TAI VIET SYMBOL KOI KOI
AAF0..AAF1 ; Terminal_Punctuation # Po [2] MEETEI MAYEK CHEIKHAN..MEETEI MAYEK AHANG KHUDAM
ABEB ; Terminal_Punctuation # Po MEETEI MAYEK CHEIKHEI
FE50..FE52 ; Terminal_Punctuation # Po [3] SMALL COMMA..SMALL FULL STOP
FE54..FE57 ; Terminal_Punctuation # Po [4] SMALL SEMICOLON..SMALL EXCLAMATION MARK
@ -175,9 +177,11 @@ FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA
10B3A..10B3F ; Terminal_Punctuation # Po [6] TINY TWO DOTS OVER ONE DOT PUNCTUATION..LARGE ONE RING OVER TWO RINGS PUNCTUATION
11047..1104D ; Terminal_Punctuation # Po [7] BRAHMI DANDA..BRAHMI PUNCTUATION LOTUS
110BE..110C1 ; Terminal_Punctuation # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA
11141..11143 ; Terminal_Punctuation # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK
111C5..111C6 ; Terminal_Punctuation # Po [2] SHARADA DANDA..SHARADA DOUBLE DANDA
12470..12473 ; Terminal_Punctuation # Po [4] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL TRICOLON
# Total code points: 169
# Total code points: 176
# ================================================
@ -320,8 +324,41 @@ FF3E ; Other_Math # Sk FULLWIDTH CIRCUMFLEX ACCENT
1D7AA..1D7C2 ; Other_Math # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA
1D7C4..1D7CB ; Other_Math # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA
1D7CE..1D7FF ; Other_Math # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
1EE00..1EE03 ; Other_Math # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL
1EE05..1EE1F ; Other_Math # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF
1EE21..1EE22 ; Other_Math # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM
1EE24 ; Other_Math # Lo ARABIC MATHEMATICAL INITIAL HEH
1EE27 ; Other_Math # Lo ARABIC MATHEMATICAL INITIAL HAH
1EE29..1EE32 ; Other_Math # Lo [10] ARABIC MATHEMATICAL INITIAL YEH..ARABIC MATHEMATICAL INITIAL QAF
1EE34..1EE37 ; Other_Math # Lo [4] ARABIC MATHEMATICAL INITIAL SHEEN..ARABIC MATHEMATICAL INITIAL KHAH
1EE39 ; Other_Math # Lo ARABIC MATHEMATICAL INITIAL DAD
1EE3B ; Other_Math # Lo ARABIC MATHEMATICAL INITIAL GHAIN
1EE42 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED JEEM
1EE47 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED HAH
1EE49 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED YEH
1EE4B ; Other_Math # Lo ARABIC MATHEMATICAL TAILED LAM
1EE4D..1EE4F ; Other_Math # Lo [3] ARABIC MATHEMATICAL TAILED NOON..ARABIC MATHEMATICAL TAILED AIN
1EE51..1EE52 ; Other_Math # Lo [2] ARABIC MATHEMATICAL TAILED SAD..ARABIC MATHEMATICAL TAILED QAF
1EE54 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED SHEEN
1EE57 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED KHAH
1EE59 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED DAD
1EE5B ; Other_Math # Lo ARABIC MATHEMATICAL TAILED GHAIN
1EE5D ; Other_Math # Lo ARABIC MATHEMATICAL TAILED DOTLESS NOON
1EE5F ; Other_Math # Lo ARABIC MATHEMATICAL TAILED DOTLESS QAF
1EE61..1EE62 ; Other_Math # Lo [2] ARABIC MATHEMATICAL STRETCHED BEH..ARABIC MATHEMATICAL STRETCHED JEEM
1EE64 ; Other_Math # Lo ARABIC MATHEMATICAL STRETCHED HEH
1EE67..1EE6A ; Other_Math # Lo [4] ARABIC MATHEMATICAL STRETCHED HAH..ARABIC MATHEMATICAL STRETCHED KAF
1EE6C..1EE72 ; Other_Math # Lo [7] ARABIC MATHEMATICAL STRETCHED MEEM..ARABIC MATHEMATICAL STRETCHED QAF
1EE74..1EE77 ; Other_Math # Lo [4] ARABIC MATHEMATICAL STRETCHED SHEEN..ARABIC MATHEMATICAL STRETCHED KHAH
1EE79..1EE7C ; Other_Math # Lo [4] ARABIC MATHEMATICAL STRETCHED DAD..ARABIC MATHEMATICAL STRETCHED DOTLESS BEH
1EE7E ; Other_Math # Lo ARABIC MATHEMATICAL STRETCHED DOTLESS FEH
1EE80..1EE89 ; Other_Math # Lo [10] ARABIC MATHEMATICAL LOOPED ALEF..ARABIC MATHEMATICAL LOOPED YEH
1EE8B..1EE9B ; Other_Math # Lo [17] ARABIC MATHEMATICAL LOOPED LAM..ARABIC MATHEMATICAL LOOPED GHAIN
1EEA1..1EEA3 ; Other_Math # Lo [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL
1EEA5..1EEA9 ; Other_Math # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH
1EEAB..1EEBB ; Other_Math # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
# Total code points: 1217
# Total code points: 1358
# ================================================
@ -365,6 +402,8 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
081B..0823 ; Other_Alphabetic # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A
0825..0827 ; Other_Alphabetic # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U
0829..082C ; Other_Alphabetic # Mn [4] SAMARITAN VOWEL SIGN LONG I..SAMARITAN VOWEL SIGN SUKUN
08E4..08E9 ; Other_Alphabetic # Mn [6] ARABIC CURLY FATHA..ARABIC CURLY KASRATAN
08F0..08FE ; Other_Alphabetic # Mn [15] ARABIC OPEN FATHATAN..ARABIC DAMMA WITH DOT
0900..0902 ; Other_Alphabetic # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA
0903 ; Other_Alphabetic # Mc DEVANAGARI SIGN VISARGA
093A ; Other_Alphabetic # Mn DEVANAGARI VOWEL SIGN OE
@ -525,6 +564,7 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
1BA2..1BA5 ; Other_Alphabetic # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU
1BA6..1BA7 ; Other_Alphabetic # Mc [2] SUNDANESE VOWEL SIGN PANAELAENG..SUNDANESE VOWEL SIGN PANOLONG
1BA8..1BA9 ; Other_Alphabetic # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG
1BAC..1BAD ; Other_Alphabetic # Mc [2] SUNDANESE CONSONANT SIGN PASANGAN MA..SUNDANESE CONSONANT SIGN PASANGAN WA
1BE7 ; Other_Alphabetic # Mc BATAK VOWEL SIGN E
1BE8..1BE9 ; Other_Alphabetic # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE
1BEA..1BEC ; Other_Alphabetic # Mc [3] BATAK VOWEL SIGN I..BATAK VOWEL SIGN O
@ -534,9 +574,11 @@ 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 ; Other_Alphabetic # Mc VEDIC SIGN ARDHAVISARGA
1CF2..1CF3 ; Other_Alphabetic # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
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
A69F ; Other_Alphabetic # Mn COMBINING CYRILLIC LETTER IOTIFIED E
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
@ -564,6 +606,10 @@ 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
AABE ; Other_Alphabetic # Mn TAI VIET VOWEL AM
AAEB ; Other_Alphabetic # Mc MEETEI MAYEK VOWEL SIGN II
AAEC..AAED ; Other_Alphabetic # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI
AAEE..AAEF ; Other_Alphabetic # Mc [2] MEETEI MAYEK VOWEL SIGN AU..MEETEI MAYEK VOWEL SIGN AAU
AAF5 ; Other_Alphabetic # Mc MEETEI MAYEK VOWEL SIGN VISARGA
ABE3..ABE4 ; Other_Alphabetic # Mc [2] MEETEI MAYEK VOWEL SIGN ONAP..MEETEI MAYEK VOWEL SIGN INAP
ABE5 ; Other_Alphabetic # Mn MEETEI MAYEK VOWEL SIGN ANAP
ABE6..ABE7 ; Other_Alphabetic # Mc [2] MEETEI MAYEK VOWEL SIGN YENAP..MEETEI MAYEK VOWEL SIGN SOUNAP
@ -581,8 +627,23 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
110B0..110B2 ; Other_Alphabetic # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II
110B3..110B6 ; Other_Alphabetic # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI
110B7..110B8 ; Other_Alphabetic # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU
11100..11102 ; Other_Alphabetic # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA
11127..1112B ; Other_Alphabetic # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU
1112C ; Other_Alphabetic # Mc CHAKMA VOWEL SIGN E
1112D..11132 ; Other_Alphabetic # Mn [6] CHAKMA VOWEL SIGN AI..CHAKMA AU MARK
11180..11181 ; Other_Alphabetic # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA
11182 ; Other_Alphabetic # Mc SHARADA SIGN VISARGA
111B3..111B5 ; Other_Alphabetic # Mc [3] SHARADA VOWEL SIGN AA..SHARADA VOWEL SIGN II
111B6..111BE ; Other_Alphabetic # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O
111BF ; Other_Alphabetic # Mc SHARADA VOWEL SIGN AU
116AB ; Other_Alphabetic # Mn TAKRI SIGN ANUSVARA
116AC ; Other_Alphabetic # Mc TAKRI SIGN VISARGA
116AD ; Other_Alphabetic # Mn TAKRI VOWEL SIGN AA
116AE..116AF ; Other_Alphabetic # Mc [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II
116B0..116B5 ; Other_Alphabetic # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU
16F51..16F7E ; Other_Alphabetic # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
# Total code points: 795
# Total code points: 922
# ================================================
@ -591,16 +652,15 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
3021..3029 ; Ideographic # Nl [9] HANGZHOU NUMERAL ONE..HANGZHOU NUMERAL NINE
3038..303A ; Ideographic # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY
3400..4DB5 ; Ideographic # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4E00..9FCB ; Ideographic # Lo [20940] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCB
F900..FA2D ; Ideographic # Lo [302] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA2D
FA30..FA6D ; Ideographic # Lo [62] CJK COMPATIBILITY IDEOGRAPH-FA30..CJK COMPATIBILITY IDEOGRAPH-FA6D
4E00..9FCC ; Ideographic # Lo [20941] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCC
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
20000..2A6D6 ; Ideographic # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
2A700..2B734 ; Ideographic # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
2B740..2B81D ; Ideographic # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 75630
# Total code points: 75633
# ================================================
@ -645,6 +705,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
07EB..07F3 ; Diacritic # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE
07F4..07F5 ; Diacritic # Lm [2] NKO HIGH TONE APOSTROPHE..NKO LOW TONE APOSTROPHE
0818..0819 ; Diacritic # Mn [2] SAMARITAN MARK OCCLUSION..SAMARITAN MARK DAGESH
08E4..08FE ; Diacritic # Mn [27] ARABIC CURLY FATHA..ARABIC DAMMA WITH DOT
093C ; Diacritic # Mn DEVANAGARI SIGN NUKTA
094D ; Diacritic # Mn DEVANAGARI SIGN VIRAMA
0951..0954 ; Diacritic # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT
@ -689,6 +750,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
1B44 ; Diacritic # Mc BALINESE ADEG ADEG
1B6B..1B73 ; Diacritic # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG
1BAA ; Diacritic # Mc SUNDANESE SIGN PAMAAEH
1BAB ; Diacritic # Mn SUNDANESE SIGN VIRAMA
1C36..1C37 ; Diacritic # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA
1C78..1C7D ; Diacritic # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD
1CD0..1CD2 ; Diacritic # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA
@ -697,8 +759,8 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
1CE1 ; Diacritic # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA
1CE2..1CE8 ; Diacritic # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL
1CED ; Diacritic # Mn VEDIC SIGN TIRYAK
1D2C..1D61 ; Diacritic # Lm [54] MODIFIER LETTER CAPITAL A..MODIFIER LETTER SMALL CHI
1D62..1D6A ; Diacritic # L& [9] LATIN SUBSCRIPT SMALL LETTER I..GREEK SUBSCRIPT SMALL LETTER CHI
1CF4 ; Diacritic # Mn VEDIC TONE CANDRA ABOVE
1D2C..1D6A ; Diacritic # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI
1DC4..1DCF ; Diacritic # Mn [12] COMBINING MACRON-ACUTE..COMBINING ZIGZAG BELOW
1DFD..1DFF ; Diacritic # Mn [3] COMBINING ALMOST EQUAL TO BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
1FBD ; Diacritic # Sk GREEK KORONIS
@ -709,7 +771,8 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
1FFD..1FFE ; Diacritic # Sk [2] GREEK OXIA..GREEK DASIA
2CEF..2CF1 ; Diacritic # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS
2E2F ; Diacritic # Lm VERTICAL TILDE
302A..302F ; Diacritic # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK
302A..302D ; Diacritic # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK
302E..302F ; Diacritic # Mc [2] HANGUL SINGLE DOT TONE MARK..HANGUL DOUBLE DOT TONE MARK
3099..309A ; Diacritic # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
309B..309C ; Diacritic # Sk [2] KATAKANA-HIRAGANA VOICED SOUND MARK..KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
30FC ; Diacritic # Lm KATAKANA-HIRAGANA PROLONGED SOUND MARK
@ -720,6 +783,7 @@ A6F0..A6F1 ; Diacritic # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINI
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
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
A92B..A92D ; Diacritic # Mn [3] KAYAH LI TONE PLOPHU..KAYAH LI TONE CALYA PLOPHU
@ -732,6 +796,7 @@ AABF ; Diacritic # Mn TAI VIET TONE MAI EK
AAC0 ; Diacritic # Lo TAI VIET TONE MAI NUENG
AAC1 ; Diacritic # Mn TAI VIET TONE MAI THO
AAC2 ; Diacritic # Lo TAI VIET TONE MAI SONG
AAF6 ; Diacritic # Mn MEETEI MAYEK VIRAMA
ABEC ; Diacritic # Mc MEETEI MAYEK LUM IYEK
ABED ; Diacritic # Mn MEETEI MAYEK APUN IYEK
FB1E ; Diacritic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
@ -742,13 +807,19 @@ FF70 ; Diacritic # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND
FF9E..FF9F ; Diacritic # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
FFE3 ; Diacritic # Sk FULLWIDTH MACRON
110B9..110BA ; Diacritic # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA
11133..11134 ; Diacritic # Mn [2] CHAKMA VIRAMA..CHAKMA MAAYYAA
111C0 ; Diacritic # Mc SHARADA SIGN VIRAMA
116B6 ; Diacritic # Mc TAKRI SIGN VIRAMA
116B7 ; Diacritic # Mn TAKRI SIGN NUKTA
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
1D16D..1D172 ; Diacritic # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5
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
# Total code points: 639
# Total code points: 693
# ================================================
@ -758,6 +829,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON
07FA ; Extender # Lm NKO LAJANYALAN
0E46 ; Extender # Lm THAI CHARACTER MAIYAMOK
0EC6 ; Extender # Lm LAO KO LA
180A ; Extender # Po MONGOLIAN NIRUGU
1843 ; Extender # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN
1AA7 ; Extender # Lm TAI THAM SIGN MAI YAMOK
1C36 ; Extender # Mn LEPCHA SIGN RAN
@ -771,27 +843,33 @@ A60C ; Extender # Lm VAI SYLLABLE LENGTHENER
A9CF ; Extender # Lm JAVANESE PANGRANGKEP
AA70 ; Extender # Lm MYANMAR MODIFIER LETTER KHAMTI REDUPLICATION
AADD ; Extender # Lm TAI VIET SYMBOL SAM
AAF3..AAF4 ; Extender # Lm [2] MEETEI MAYEK SYLLABLE REPETITION MARK..MEETEI MAYEK WORD REPETITION MARK
FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
# Total code points: 28
# Total code points: 31
# ================================================
00AA ; Other_Lowercase # Lo FEMININE ORDINAL INDICATOR
00BA ; Other_Lowercase # Lo MASCULINE ORDINAL INDICATOR
02B0..02B8 ; Other_Lowercase # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y
02C0..02C1 ; Other_Lowercase # Lm [2] MODIFIER LETTER GLOTTAL STOP..MODIFIER LETTER REVERSED GLOTTAL STOP
02E0..02E4 ; Other_Lowercase # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
0345 ; Other_Lowercase # Mn COMBINING GREEK YPOGEGRAMMENI
037A ; Other_Lowercase # Lm GREEK YPOGEGRAMMENI
1D2C..1D61 ; Other_Lowercase # Lm [54] MODIFIER LETTER CAPITAL A..MODIFIER LETTER SMALL CHI
1D2C..1D6A ; Other_Lowercase # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI
1D78 ; Other_Lowercase # Lm MODIFIER LETTER CYRILLIC EN
1D9B..1DBF ; Other_Lowercase # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA
2090..2094 ; Other_Lowercase # Lm [5] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER SCHWA
2071 ; Other_Lowercase # Lm SUPERSCRIPT LATIN SMALL LETTER I
207F ; Other_Lowercase # Lm SUPERSCRIPT LATIN SMALL LETTER N
2090..209C ; Other_Lowercase # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T
2170..217F ; Other_Lowercase # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND
24D0..24E9 ; Other_Lowercase # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z
2C7D ; Other_Lowercase # Lm MODIFIER LETTER CAPITAL V
2C7C..2C7D ; Other_Lowercase # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V
A770 ; Other_Lowercase # Lm MODIFIER LETTER US
A7F8..A7F9 ; Other_Lowercase # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
# Total code points: 159
# Total code points: 183
# ================================================
@ -838,11 +916,12 @@ FFFFE..FFFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-FFFFE>..<noncha
0DCF ; Other_Grapheme_Extend # Mc SINHALA VOWEL SIGN AELA-PILLA
0DDF ; Other_Grapheme_Extend # Mc SINHALA VOWEL SIGN GAYANUKITTA
200C..200D ; Other_Grapheme_Extend # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH 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
1D165 ; Other_Grapheme_Extend # Mc MUSICAL SYMBOL COMBINING STEM
1D16E..1D172 ; Other_Grapheme_Extend # Mc [5] MUSICAL SYMBOL COMBINING FLAG-1..MUSICAL SYMBOL COMBINING FLAG-5
# Total code points: 23
# Total code points: 25
# ================================================
@ -868,7 +947,7 @@ FF9E..FF9F ; Other_Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND
# ================================================
3400..4DB5 ; Unified_Ideograph # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4E00..9FCB ; Unified_Ideograph # Lo [20940] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCB
4E00..9FCC ; Unified_Ideograph # Lo [20941] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCC
FA0E..FA0F ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA0E..CJK COMPATIBILITY IDEOGRAPH-FA0F
FA11 ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA11
FA13..FA14 ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA13..CJK COMPATIBILITY IDEOGRAPH-FA14
@ -880,12 +959,13 @@ FA27..FA29 ; Unified_Ideograph # Lo [3] CJK COMPATIBILITY IDEOGRAPH-FA27..C
2A700..2B734 ; Unified_Ideograph # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
2B740..2B81D ; Unified_Ideograph # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
# Total code points: 74616
# Total code points: 74617
# ================================================
034F ; Other_Default_Ignorable_Code_Point # Mn COMBINING GRAPHEME JOINER
115F..1160 ; Other_Default_Ignorable_Code_Point # Lo [2] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG FILLER
17B4..17B5 ; Other_Default_Ignorable_Code_Point # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
2065..2069 ; Other_Default_Ignorable_Code_Point # Cn [5] <reserved-2065>..<reserved-2069>
3164 ; Other_Default_Ignorable_Code_Point # Lo HANGUL FILLER
FFA0 ; Other_Default_Ignorable_Code_Point # Lo HALFWIDTH HANGUL FILLER
@ -895,7 +975,7 @@ E0002..E001F ; Other_Default_Ignorable_Code_Point # Cn [30] <reserved-E0002>..
E0080..E00FF ; Other_Default_Ignorable_Code_Point # Cn [128] <reserved-E0080>..<reserved-E00FF>
E01F0..E0FFF ; Other_Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
# Total code points: 3778
# Total code points: 3780
# ================================================
@ -923,7 +1003,7 @@ E0020..E007F ; Deprecated # Cf [96] TAG SPACE..CANCEL TAG
03F3 ; Soft_Dotted # L& GREEK LETTER YOT
0456 ; Soft_Dotted # L& CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
0458 ; Soft_Dotted # L& CYRILLIC SMALL LETTER JE
1D62 ; Soft_Dotted # L& LATIN SUBSCRIPT SMALL LETTER I
1D62 ; Soft_Dotted # Lm LATIN SUBSCRIPT SMALL LETTER I
1D96 ; Soft_Dotted # L& LATIN SMALL LETTER I WITH RETROFLEX HOOK
1DA4 ; Soft_Dotted # Lm MODIFIER LETTER SMALL I WITH STROKE
1DA8 ; Soft_Dotted # Lm MODIFIER LETTER SMALL J WITH CROSSED-TAIL
@ -931,7 +1011,7 @@ E0020..E007F ; Deprecated # Cf [96] TAG SPACE..CANCEL TAG
1ECB ; Soft_Dotted # L& LATIN SMALL LETTER I WITH DOT BELOW
2071 ; Soft_Dotted # Lm SUPERSCRIPT LATIN SMALL LETTER I
2148..2149 ; Soft_Dotted # L& [2] DOUBLE-STRUCK ITALIC SMALL I..DOUBLE-STRUCK ITALIC SMALL J
2C7C ; Soft_Dotted # L& LATIN SUBSCRIPT SMALL LETTER J
2C7C ; Soft_Dotted # Lm LATIN SUBSCRIPT SMALL LETTER J
1D422..1D423 ; Soft_Dotted # L& [2] MATHEMATICAL BOLD SMALL I..MATHEMATICAL BOLD SMALL J
1D456..1D457 ; Soft_Dotted # L& [2] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL ITALIC SMALL J
1D48A..1D48B ; Soft_Dotted # L& [2] MATHEMATICAL BOLD ITALIC SMALL I..MATHEMATICAL BOLD ITALIC SMALL J
@ -1014,6 +1094,7 @@ A8CE..A8CF ; STerm # Po [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA
A92F ; STerm # Po KAYAH LI SIGN SHYA
A9C8..A9C9 ; STerm # Po [2] JAVANESE PADA LINGSA..JAVANESE PADA LUNGSI
AA5D..AA5F ; STerm # Po [3] CHAM PUNCTUATION DANDA..CHAM PUNCTUATION TRIPLE DANDA
AAF0..AAF1 ; STerm # Po [2] MEETEI MAYEK CHEIKHAN..MEETEI MAYEK AHANG KHUDAM
ABEB ; STerm # Po MEETEI MAYEK CHEIKHEI
FE52 ; STerm # Po SMALL FULL STOP
FE56..FE57 ; STerm # Po [2] SMALL QUESTION MARK..SMALL EXCLAMATION MARK
@ -1024,8 +1105,10 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP
10A56..10A57 ; STerm # Po [2] KHAROSHTHI PUNCTUATION DANDA..KHAROSHTHI PUNCTUATION DOUBLE DANDA
11047..11048 ; STerm # Po [2] BRAHMI DANDA..BRAHMI DOUBLE DANDA
110BE..110C1 ; STerm # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA
11141..11143 ; STerm # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK
111C5..111C6 ; STerm # Po [2] SHARADA DANDA..SHARADA DOUBLE DANDA
# Total code points: 76
# Total code points: 83
# ================================================
@ -1072,14 +1155,15 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S
007E ; Pattern_Syntax # Sm TILDE
00A1 ; Pattern_Syntax # Po INVERTED EXCLAMATION MARK
00A2..00A5 ; Pattern_Syntax # Sc [4] CENT SIGN..YEN SIGN
00A6..00A7 ; Pattern_Syntax # So [2] BROKEN BAR..SECTION SIGN
00A6 ; Pattern_Syntax # So BROKEN BAR
00A7 ; Pattern_Syntax # Po SECTION SIGN
00A9 ; Pattern_Syntax # So COPYRIGHT SIGN
00AB ; Pattern_Syntax # Pi LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
00AC ; Pattern_Syntax # Sm NOT SIGN
00AE ; Pattern_Syntax # So REGISTERED SIGN
00B0 ; Pattern_Syntax # So DEGREE SIGN
00B1 ; Pattern_Syntax # Sm PLUS-MINUS SIGN
00B6 ; Pattern_Syntax # So PILCROW SIGN
00B6 ; Pattern_Syntax # Po PILCROW SIGN
00BB ; Pattern_Syntax # Pf RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
00BF ; Pattern_Syntax # Po INVERTED QUESTION MARK
00D7 ; Pattern_Syntax # Sm MULTIPLICATION SIGN
@ -1173,11 +1257,7 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S
27C0..27C4 ; Pattern_Syntax # Sm [5] THREE DIMENSIONAL ANGLE..OPEN SUPERSET
27C5 ; Pattern_Syntax # Ps LEFT S-SHAPED BAG DELIMITER
27C6 ; Pattern_Syntax # Pe RIGHT S-SHAPED BAG DELIMITER
27C7..27CA ; Pattern_Syntax # Sm [4] OR WITH DOT INSIDE..VERTICAL BAR WITH HORIZONTAL STROKE
27CB ; Pattern_Syntax # Cn <reserved-27CB>
27CC ; Pattern_Syntax # Sm LONG DIVISION
27CD ; Pattern_Syntax # Cn <reserved-27CD>
27CE..27E5 ; Pattern_Syntax # Sm [24] SQUARED LOGICAL AND..WHITE SQUARE WITH RIGHTWARDS TICK
27C7..27E5 ; Pattern_Syntax # Sm [31] OR WITH DOT INSIDE..WHITE SQUARE WITH RIGHTWARDS TICK
27E6 ; Pattern_Syntax # Ps MATHEMATICAL LEFT WHITE SQUARE BRACKET
27E7 ; Pattern_Syntax # Pe MATHEMATICAL RIGHT WHITE SQUARE BRACKET
27E8 ; Pattern_Syntax # Ps MATHEMATICAL LEFT ANGLE BRACKET
@ -1260,8 +1340,9 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S
2E29 ; Pattern_Syntax # Pe RIGHT DOUBLE PARENTHESIS
2E2A..2E2E ; Pattern_Syntax # Po [5] TWO DOTS OVER ONE DOT PUNCTUATION..REVERSED QUESTION MARK
2E2F ; Pattern_Syntax # Lm VERTICAL TILDE
2E30..2E31 ; Pattern_Syntax # Po [2] RING POINT..WORD SEPARATOR MIDDLE DOT
2E32..2E7F ; Pattern_Syntax # Cn [78] <reserved-2E32>..<reserved-2E7F>
2E30..2E39 ; Pattern_Syntax # Po [10] RING POINT..TOP HALF SECTION SIGN
2E3A..2E3B ; Pattern_Syntax # Pd [2] TWO-EM DASH..THREE-EM DASH
2E3C..2E7F ; Pattern_Syntax # Cn [68] <reserved-2E3C>..<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

248
jdk/make/tools/UnicodeData/Scripts.txt
View File

@ -1,8 +1,8 @@
# Scripts-6.0.0.txt
# Date: 2010-08-19, 00:48:47 GMT [MD]
# Scripts-6.1.0.txt
# Date: 2011-11-27, 05:10:50 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2010 Unicode, Inc.
# Copyright (c) 1991-2011 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
@ -47,7 +47,8 @@
00A0 ; Common # Zs NO-BREAK SPACE
00A1 ; Common # Po INVERTED EXCLAMATION MARK
00A2..00A5 ; Common # Sc [4] CENT SIGN..YEN SIGN
00A6..00A7 ; Common # So [2] BROKEN BAR..SECTION SIGN
00A6 ; Common # So BROKEN BAR
00A7 ; Common # Po SECTION SIGN
00A8 ; Common # Sk DIAERESIS
00A9 ; Common # So COPYRIGHT SIGN
00AB ; Common # Pi LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
@ -60,8 +61,7 @@
00B2..00B3 ; Common # No [2] SUPERSCRIPT TWO..SUPERSCRIPT THREE
00B4 ; Common # Sk ACUTE ACCENT
00B5 ; Common # L& MICRO SIGN
00B6 ; Common # So PILCROW SIGN
00B7 ; Common # Po MIDDLE DOT
00B6..00B7 ; Common # Po [2] PILCROW SIGN..MIDDLE DOT
00B8 ; Common # Sk CEDILLA
00B9 ; Common # No SUPERSCRIPT ONE
00BB ; Common # Pf RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
@ -90,7 +90,6 @@
0660..0669 ; Common # Nd [10] ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE
06DD ; Common # Cf ARABIC END OF AYAH
0964..0965 ; Common # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA
0970 ; Common # Po DEVANAGARI ABBREVIATION SIGN
0E3F ; Common # Sc THAI CURRENCY SYMBOL BAHT
0FD5..0FD8 ; Common # So [4] RIGHT-FACING SVASTI SIGN..LEFT-FACING SVASTI SIGN WITH DOTS
10FB ; Common # Po GEORGIAN PARAGRAPH SEPARATOR
@ -102,7 +101,8 @@
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 ; Common # Mc VEDIC SIGN ARDHAVISARGA
1CF2..1CF3 ; Common # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
1CF5..1CF6 ; Common # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA
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
@ -247,9 +247,7 @@
27C0..27C4 ; Common # Sm [5] THREE DIMENSIONAL ANGLE..OPEN SUPERSET
27C5 ; Common # Ps LEFT S-SHAPED BAG DELIMITER
27C6 ; Common # Pe RIGHT S-SHAPED BAG DELIMITER
27C7..27CA ; Common # Sm [4] OR WITH DOT INSIDE..VERTICAL BAR WITH HORIZONTAL STROKE
27CC ; Common # Sm LONG DIVISION
27CE..27E5 ; Common # Sm [24] SQUARED LOGICAL AND..WHITE SQUARE WITH RIGHTWARDS TICK
27C7..27E5 ; Common # Sm [31] OR WITH DOT INSIDE..WHITE SQUARE WITH RIGHTWARDS TICK
27E6 ; Common # Ps MATHEMATICAL LEFT WHITE SQUARE BRACKET
27E7 ; Common # Pe MATHEMATICAL RIGHT WHITE SQUARE BRACKET
27E8 ; Common # Ps MATHEMATICAL LEFT ANGLE BRACKET
@ -329,7 +327,8 @@
2E29 ; Common # Pe RIGHT DOUBLE PARENTHESIS
2E2A..2E2E ; Common # Po [5] TWO DOTS OVER ONE DOT PUNCTUATION..REVERSED QUESTION MARK
2E2F ; Common # Lm VERTICAL TILDE
2E30..2E31 ; Common # Po [2] RING POINT..WORD SEPARATOR MIDDLE DOT
2E30..2E39 ; Common # Po [10] RING POINT..TOP HALF SECTION SIGN
2E3A..2E3B ; Common # Pd [2] TWO-EM DASH..THREE-EM DASH
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
@ -373,7 +372,9 @@
3196..319F ; Common # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK
31C0..31E3 ; Common # So [36] CJK STROKE T..CJK STROKE Q
3220..3229 ; Common # No [10] PARENTHESIZED IDEOGRAPH ONE..PARENTHESIZED IDEOGRAPH TEN
322A..3250 ; Common # So [39] PARENTHESIZED IDEOGRAPH MOON..PARTNERSHIP SIGN
322A..3247 ; Common # So [30] PARENTHESIZED IDEOGRAPH MOON..CIRCLED IDEOGRAPH KOTO
3248..324F ; Common # No [8] CIRCLED NUMBER TEN ON BLACK SQUARE..CIRCLED NUMBER EIGHTY ON BLACK SQUARE
3250 ; Common # So PARTNERSHIP SIGN
3251..325F ; Common # No [15] CIRCLED NUMBER TWENTY ONE..CIRCLED NUMBER THIRTY FIVE
327F ; Common # So KOREAN STANDARD SYMBOL
3280..3289 ; Common # No [10] CIRCLED IDEOGRAPH ONE..CIRCLED IDEOGRAPH TEN
@ -481,8 +482,7 @@ FFE9..FFEC ; Common # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS
FFED..FFEE ; Common # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE
FFF9..FFFB ; Common # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR
FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER
10100..10101 ; Common # Po [2] AEGEAN WORD SEPARATOR LINE..AEGEAN WORD SEPARATOR DOT
10102 ; Common # So AEGEAN CHECK MARK
10100..10102 ; Common # Po [3] AEGEAN WORD SEPARATOR LINE..AEGEAN CHECK MARK
10107..10133 ; Common # No [45] AEGEAN NUMBER ONE..AEGEAN NUMBER NINETY THOUSAND
10137..1013F ; Common # So [9] AEGEAN WEIGHT BASE UNIT..AEGEAN MEASURE THIRD SUBUNIT
10190..1019B ; Common # So [12] ROMAN SEXTANS SIGN..ROMAN CENTURIAL SIGN
@ -548,7 +548,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1F0D1..1F0DF ; Common # So [15] PLAYING CARD ACE OF CLUBS..PLAYING CARD WHITE JOKER
1F100..1F10A ; Common # No [11] DIGIT ZERO FULL STOP..DIGIT NINE COMMA
1F110..1F12E ; Common # So [31] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED WZ
1F130..1F169 ; Common # So [58] SQUARED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
1F130..1F16B ; Common # So [60] SQUARED LATIN CAPITAL LETTER A..RAISED MD SIGN
1F170..1F19A ; Common # So [43] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VS
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
@ -567,33 +567,23 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1F442..1F4F7 ; Common # So [182] EAR..CAMERA
1F4F9..1F4FC ; Common # So [4] VIDEO CAMERA..VIDEOCASSETTE
1F500..1F53D ; Common # So [62] TWISTED RIGHTWARDS ARROWS..DOWN-POINTING SMALL RED TRIANGLE
1F540..1F543 ; Common # So [4] CIRCLED CROSS POMMEE..NOTCHED LEFT SEMICIRCLE WITH THREE DOTS
1F550..1F567 ; Common # So [24] CLOCK FACE ONE OCLOCK..CLOCK FACE TWELVE-THIRTY
1F5FB..1F5FF ; Common # So [5] MOUNT FUJI..MOYAI
1F601..1F610 ; Common # So [16] GRINNING FACE WITH SMILING EYES..NEUTRAL FACE
1F612..1F614 ; Common # So [3] UNAMUSED FACE..PENSIVE FACE
1F616 ; Common # So CONFOUNDED FACE
1F618 ; Common # So FACE THROWING A KISS
1F61A ; Common # So KISSING FACE WITH CLOSED EYES
1F61C..1F61E ; Common # So [3] FACE WITH STUCK-OUT TONGUE AND WINKING EYE..DISAPPOINTED FACE
1F620..1F625 ; Common # So [6] ANGRY FACE..DISAPPOINTED BUT RELIEVED FACE
1F628..1F62B ; Common # So [4] FEARFUL FACE..TIRED FACE
1F62D ; Common # So LOUDLY CRYING FACE
1F630..1F633 ; Common # So [4] FACE WITH OPEN MOUTH AND COLD SWEAT..FLUSHED FACE
1F635..1F640 ; Common # So [12] DIZZY FACE..WEARY CAT FACE
1F5FB..1F640 ; Common # So [70] MOUNT FUJI..WEARY CAT FACE
1F645..1F64F ; Common # So [11] FACE WITH NO GOOD GESTURE..PERSON WITH FOLDED HANDS
1F680..1F6C5 ; Common # So [70] ROCKET..LEFT LUGGAGE
1F700..1F773 ; Common # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
E0001 ; Common # Cf LANGUAGE TAG
E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
# Total code points: 6379
# Total code points: 6412
# ================================================
0041..005A ; Latin # L& [26] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER Z
0061..007A ; Latin # L& [26] LATIN SMALL LETTER A..LATIN SMALL LETTER Z
00AA ; Latin # L& FEMININE ORDINAL INDICATOR
00BA ; Latin # L& MASCULINE ORDINAL INDICATOR
00AA ; Latin # Lo FEMININE ORDINAL INDICATOR
00BA ; Latin # Lo MASCULINE ORDINAL INDICATOR
00C0..00D6 ; Latin # L& [23] LATIN CAPITAL LETTER A WITH GRAVE..LATIN CAPITAL LETTER O WITH DIAERESIS
00D8..00F6 ; Latin # L& [31] LATIN CAPITAL LETTER O WITH STROKE..LATIN SMALL LETTER O WITH DIAERESIS
00F8..01BA ; Latin # L& [195] LATIN SMALL LETTER O WITH STROKE..LATIN SMALL LETTER EZH WITH TAIL
@ -607,7 +597,7 @@ E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
02E0..02E4 ; Latin # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
1D00..1D25 ; Latin # L& [38] LATIN LETTER SMALL CAPITAL A..LATIN LETTER AIN
1D2C..1D5C ; Latin # Lm [49] MODIFIER LETTER CAPITAL A..MODIFIER LETTER SMALL AIN
1D62..1D65 ; Latin # L& [4] LATIN SUBSCRIPT SMALL LETTER I..LATIN SUBSCRIPT SMALL LETTER V
1D62..1D65 ; Latin # Lm [4] LATIN SUBSCRIPT SMALL LETTER I..LATIN SUBSCRIPT SMALL LETTER V
1D6B..1D77 ; Latin # L& [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G
1D79..1D9A ; Latin # L& [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK
1D9B..1DBE ; Latin # Lm [36] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL EZH
@ -621,22 +611,23 @@ E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
2160..2182 ; Latin # Nl [35] ROMAN NUMERAL ONE..ROMAN NUMERAL TEN THOUSAND
2183..2184 ; Latin # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C
2185..2188 ; Latin # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND
2C60..2C7C ; Latin # L& [29] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN SUBSCRIPT SMALL LETTER J
2C7D ; Latin # Lm MODIFIER LETTER CAPITAL V
2C60..2C7B ; Latin # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E
2C7C..2C7D ; Latin # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V
2C7E..2C7F ; Latin # L& [2] LATIN CAPITAL LETTER S WITH SWASH TAIL..LATIN CAPITAL LETTER Z WITH SWASH TAIL
A722..A76F ; Latin # L& [78] LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF..LATIN SMALL LETTER CON
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
A790..A791 ; Latin # L& [2] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER N WITH DESCENDER
A7A0..A7A9 ; Latin # L& [10] LATIN CAPITAL LETTER G WITH OBLIQUE STROKE..LATIN SMALL LETTER S WITH OBLIQUE STROKE
A790..A793 ; Latin # L& [4] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER C WITH BAR
A7A0..A7AA ; Latin # L& [11] LATIN CAPITAL LETTER G WITH OBLIQUE STROKE..LATIN CAPITAL LETTER H WITH HOOK
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
A7FB..A7FF ; Latin # Lo [5] LATIN EPIGRAPHIC LETTER REVERSED F..LATIN EPIGRAPHIC LETTER ARCHAIC M
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: 1267
# Total code points: 1272
# ================================================
@ -656,7 +647,7 @@ FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN
03F7..03FF ; Greek # L& [9] GREEK CAPITAL LETTER SHO..GREEK CAPITAL REVERSED DOTTED LUNATE SIGMA SYMBOL
1D26..1D2A ; Greek # L& [5] GREEK LETTER SMALL CAPITAL GAMMA..GREEK LETTER SMALL CAPITAL PSI
1D5D..1D61 ; Greek # Lm [5] MODIFIER LETTER SMALL BETA..MODIFIER LETTER SMALL CHI
1D66..1D6A ; Greek # L& [5] GREEK SUBSCRIPT SMALL LETTER BETA..GREEK SUBSCRIPT SMALL LETTER CHI
1D66..1D6A ; Greek # Lm [5] GREEK SUBSCRIPT SMALL LETTER BETA..GREEK SUBSCRIPT SMALL LETTER CHI
1DBF ; Greek # Lm MODIFIER LETTER SMALL THETA
1F00..1F15 ; Greek # L& [22] GREEK SMALL LETTER ALPHA WITH PSILI..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA
1F18..1F1D ; Greek # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA
@ -710,12 +701,13 @@ A66E ; Cyrillic # Lo CYRILLIC LETTER MULTIOCULAR O
A66F ; Cyrillic # Mn COMBINING CYRILLIC VZMET
A670..A672 ; Cyrillic # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN
A673 ; Cyrillic # Po SLAVONIC ASTERISK
A67C..A67D ; Cyrillic # Mn [2] COMBINING CYRILLIC KAVYKA..COMBINING CYRILLIC PAYEROK
A674..A67D ; Cyrillic # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK
A67E ; Cyrillic # Po CYRILLIC KAVYKA
A67F ; Cyrillic # Lm CYRILLIC PAYEROK
A680..A697 ; Cyrillic # L& [24] CYRILLIC CAPITAL LETTER DWE..CYRILLIC SMALL LETTER SHWE
A69F ; Cyrillic # Mn COMBINING CYRILLIC LETTER IOTIFIED E
# Total code points: 408
# Total code points: 417
# ================================================
@ -724,9 +716,10 @@ A680..A697 ; Cyrillic # L& [24] CYRILLIC CAPITAL LETTER DWE..CYRILLIC SMALL
055A..055F ; Armenian # Po [6] ARMENIAN APOSTROPHE..ARMENIAN ABBREVIATION MARK
0561..0587 ; Armenian # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN
058A ; Armenian # Pd ARMENIAN HYPHEN
058F ; Armenian # Sc ARMENIAN DRAM SIGN
FB13..FB17 ; Armenian # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH
# Total code points: 90
# Total code points: 91
# ================================================
@ -757,7 +750,7 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU
# ================================================
0600..0603 ; Arabic # Cf [4] ARABIC NUMBER SIGN..ARABIC SIGN SAFHA
0600..0604 ; Arabic # Cf [5] ARABIC NUMBER SIGN..ARABIC SIGN SAMVAT
0606..0608 ; Arabic # Sm [3] ARABIC-INDIC CUBE ROOT..ARABIC RAY
0609..060A ; Arabic # Po [2] ARABIC-INDIC PER MILLE SIGN..ARABIC-INDIC PER TEN THOUSAND SIGN
060B ; Arabic # Sc AFGHANI SIGN
@ -786,6 +779,9 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU
06FD..06FE ; Arabic # So [2] ARABIC SIGN SINDHI AMPERSAND..ARABIC SIGN SINDHI POSTPOSITION MEN
06FF ; Arabic # Lo ARABIC LETTER HEH WITH INVERTED V
0750..077F ; Arabic # Lo [48] ARABIC LETTER BEH WITH THREE DOTS HORIZONTALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS ABOVE
08A0 ; Arabic # Lo ARABIC LETTER BEH WITH SMALL V BELOW
08A2..08AC ; Arabic # Lo [11] ARABIC LETTER JEEM WITH TWO DOTS ABOVE..ARABIC LETTER ROHINGYA YEH
08E4..08FE ; Arabic # Mn [27] ARABIC CURLY FATHA..ARABIC DAMMA WITH DOT
FB50..FBB1 ; Arabic # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM
FBB2..FBC1 ; Arabic # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW
FBD3..FD3D ; Arabic # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM
@ -796,8 +792,42 @@ FDFC ; Arabic # Sc RIAL SIGN
FE70..FE74 ; Arabic # Lo [5] ARABIC FATHATAN ISOLATED FORM..ARABIC KASRATAN ISOLATED FORM
FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM
10E60..10E7E ; Arabic # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS
1EE00..1EE03 ; Arabic # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL
1EE05..1EE1F ; Arabic # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF
1EE21..1EE22 ; Arabic # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM
1EE24 ; Arabic # Lo ARABIC MATHEMATICAL INITIAL HEH
1EE27 ; Arabic # Lo ARABIC MATHEMATICAL INITIAL HAH
1EE29..1EE32 ; Arabic # Lo [10] ARABIC MATHEMATICAL INITIAL YEH..ARABIC MATHEMATICAL INITIAL QAF
1EE34..1EE37 ; Arabic # Lo [4] ARABIC MATHEMATICAL INITIAL SHEEN..ARABIC MATHEMATICAL INITIAL KHAH
1EE39 ; Arabic # Lo ARABIC MATHEMATICAL INITIAL DAD
1EE3B ; Arabic # Lo ARABIC MATHEMATICAL INITIAL GHAIN
1EE42 ; Arabic # Lo ARABIC MATHEMATICAL TAILED JEEM
1EE47 ; Arabic # Lo ARABIC MATHEMATICAL TAILED HAH
1EE49 ; Arabic # Lo ARABIC MATHEMATICAL TAILED YEH
1EE4B ; Arabic # Lo ARABIC MATHEMATICAL TAILED LAM
1EE4D..1EE4F ; Arabic # Lo [3] ARABIC MATHEMATICAL TAILED NOON..ARABIC MATHEMATICAL TAILED AIN
1EE51..1EE52 ; Arabic # Lo [2] ARABIC MATHEMATICAL TAILED SAD..ARABIC MATHEMATICAL TAILED QAF
1EE54 ; Arabic # Lo ARABIC MATHEMATICAL TAILED SHEEN
1EE57 ; Arabic # Lo ARABIC MATHEMATICAL TAILED KHAH
1EE59 ; Arabic # Lo ARABIC MATHEMATICAL TAILED DAD
1EE5B ; Arabic # Lo ARABIC MATHEMATICAL TAILED GHAIN
1EE5D ; Arabic # Lo ARABIC MATHEMATICAL TAILED DOTLESS NOON
1EE5F ; Arabic # Lo ARABIC MATHEMATICAL TAILED DOTLESS QAF
1EE61..1EE62 ; Arabic # Lo [2] ARABIC MATHEMATICAL STRETCHED BEH..ARABIC MATHEMATICAL STRETCHED JEEM
1EE64 ; Arabic # Lo ARABIC MATHEMATICAL STRETCHED HEH
1EE67..1EE6A ; Arabic # Lo [4] ARABIC MATHEMATICAL STRETCHED HAH..ARABIC MATHEMATICAL STRETCHED KAF
1EE6C..1EE72 ; Arabic # Lo [7] ARABIC MATHEMATICAL STRETCHED MEEM..ARABIC MATHEMATICAL STRETCHED QAF
1EE74..1EE77 ; Arabic # Lo [4] ARABIC MATHEMATICAL STRETCHED SHEEN..ARABIC MATHEMATICAL STRETCHED KHAH
1EE79..1EE7C ; Arabic # Lo [4] ARABIC MATHEMATICAL STRETCHED DAD..ARABIC MATHEMATICAL STRETCHED DOTLESS BEH
1EE7E ; Arabic # Lo ARABIC MATHEMATICAL STRETCHED DOTLESS FEH
1EE80..1EE89 ; Arabic # Lo [10] ARABIC MATHEMATICAL LOOPED ALEF..ARABIC MATHEMATICAL LOOPED YEH
1EE8B..1EE9B ; Arabic # Lo [17] ARABIC MATHEMATICAL LOOPED LAM..ARABIC MATHEMATICAL LOOPED GHAIN
1EEA1..1EEA3 ; Arabic # Lo [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL
1EEA5..1EEA9 ; Arabic # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH
1EEAB..1EEBB ; Arabic # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
1EEF0..1EEF1 ; Arabic # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL
# Total code points: 1051
# Total code points: 1234
# ================================================
@ -838,6 +868,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
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
0970 ; Devanagari # Po DEVANAGARI ABBREVIATION SIGN
0971 ; Devanagari # Lm DEVANAGARI SIGN HIGH SPACING DOT
0972..0977 ; Devanagari # Lo [6] DEVANAGARI LETTER CANDRA A..DEVANAGARI LETTER UUE
0979..097F ; Devanagari # Lo [7] DEVANAGARI LETTER ZHA..DEVANAGARI LETTER BBA
@ -846,7 +877,7 @@ A8F2..A8F7 ; Devanagari # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVAN
A8F8..A8FA ; Devanagari # Po [3] DEVANAGARI SIGN PUSHPIKA..DEVANAGARI CARET
A8FB ; Devanagari # Lo DEVANAGARI HEADSTROKE
# Total code points: 150
# Total code points: 151
# ================================================
@ -927,9 +958,10 @@ A8FB ; Devanagari # Lo DEVANAGARI HEADSTROKE
0AE0..0AE1 ; Gujarati # Lo [2] GUJARATI LETTER VOCALIC RR..GUJARATI LETTER VOCALIC LL
0AE2..0AE3 ; Gujarati # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL
0AE6..0AEF ; Gujarati # Nd [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE
0AF0 ; Gujarati # Po GUJARATI ABBREVIATION SIGN
0AF1 ; Gujarati # Sc GUJARATI RUPEE SIGN
# Total code points: 83
# Total code points: 84
# ================================================
@ -1119,16 +1151,18 @@ A8FB ; Devanagari # Lo DEVANAGARI HEADSTROKE
0EC6 ; Lao # Lm LAO KO LA
0EC8..0ECD ; Lao # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA
0ED0..0ED9 ; Lao # Nd [10] LAO DIGIT ZERO..LAO DIGIT NINE
0EDC..0EDD ; Lao # Lo [2] LAO HO NO..LAO HO MO
0EDC..0EDF ; Lao # Lo [4] LAO HO NO..LAO LETTER KHMU NYO
# Total code points: 65
# Total code points: 67
# ================================================
0F00 ; Tibetan # Lo TIBETAN SYLLABLE OM
0F01..0F03 ; Tibetan # So [3] TIBETAN MARK GTER YIG MGO TRUNCATED A..TIBETAN MARK GTER YIG MGO -UM GTER TSHEG MA
0F04..0F12 ; Tibetan # Po [15] TIBETAN MARK INITIAL YIG MGO MDUN MA..TIBETAN MARK RGYA GRAM SHAD
0F13..0F17 ; Tibetan # So [5] TIBETAN MARK CARET -DZUD RTAGS ME LONG CAN..TIBETAN ASTROLOGICAL SIGN SGRA GCAN -CHAR RTAGS
0F13 ; Tibetan # So TIBETAN MARK CARET -DZUD RTAGS ME LONG CAN
0F14 ; Tibetan # Po TIBETAN MARK GTER TSHEG
0F15..0F17 ; Tibetan # So [3] TIBETAN LOGOTYPE SIGN CHAD RTAGS..TIBETAN ASTROLOGICAL SIGN SGRA GCAN -CHAR RTAGS
0F18..0F19 ; Tibetan # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS
0F1A..0F1F ; Tibetan # So [6] TIBETAN SIGN RDEL DKAR GCIG..TIBETAN SIGN RDEL DKAR RDEL NAG
0F20..0F29 ; Tibetan # Nd [10] TIBETAN DIGIT ZERO..TIBETAN DIGIT NINE
@ -1212,16 +1246,21 @@ AA7B ; Myanmar # Mc MYANMAR SIGN PAO KAREN TONE
# ================================================
10A0..10C5 ; Georgian # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE
10C7 ; Georgian # L& GEORGIAN CAPITAL LETTER YN
10CD ; Georgian # L& GEORGIAN CAPITAL LETTER AEN
10D0..10FA ; Georgian # Lo [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN
10FC ; Georgian # Lm MODIFIER LETTER GEORGIAN NAR
10FD..10FF ; Georgian # Lo [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN
2D00..2D25 ; Georgian # L& [38] GEORGIAN SMALL LETTER AN..GEORGIAN SMALL LETTER HOE
2D27 ; Georgian # L& GEORGIAN SMALL LETTER YN
2D2D ; Georgian # L& GEORGIAN SMALL LETTER AEN
# Total code points: 120
# Total code points: 127
# ================================================
1100..11FF ; Hangul # Lo [256] HANGUL CHOSEONG KIYEOK..HANGUL JONGSEONG SSANGNIEUN
302E..302F ; Hangul # Mn [2] HANGUL SINGLE DOT TONE MARK..HANGUL DOUBLE DOT TONE MARK
302E..302F ; Hangul # Mc [2] HANGUL SINGLE DOT TONE MARK..HANGUL DOUBLE DOT TONE MARK
3131..318E ; Hangul # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE
3200..321E ; Hangul # So [31] PARENTHESIZED HANGUL KIYEOK..PARENTHESIZED KOREAN CHARACTER O HU
3260..327E ; Hangul # So [31] CIRCLED HANGUL KIYEOK..CIRCLED HANGUL IEUNG U
@ -1256,8 +1295,7 @@ FFDA..FFDC ; Hangul # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL L
1312..1315 ; Ethiopic # Lo [4] ETHIOPIC SYLLABLE GWI..ETHIOPIC SYLLABLE GWE
1318..135A ; Ethiopic # Lo [67] ETHIOPIC SYLLABLE GGA..ETHIOPIC SYLLABLE FYA
135D..135F ; Ethiopic # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK
1360 ; Ethiopic # So ETHIOPIC SECTION MARK
1361..1368 ; Ethiopic # Po [8] ETHIOPIC WORDSPACE..ETHIOPIC PARAGRAPH SEPARATOR
1360..1368 ; Ethiopic # Po [9] ETHIOPIC SECTION MARK..ETHIOPIC PARAGRAPH SEPARATOR
1369..137C ; Ethiopic # No [20] ETHIOPIC DIGIT ONE..ETHIOPIC NUMBER TEN THOUSAND
1380..138F ; Ethiopic # Lo [16] ETHIOPIC SYLLABLE SEBATBEIT MWA..ETHIOPIC SYLLABLE PWE
1390..1399 ; Ethiopic # So [10] ETHIOPIC TONAL MARK YIZET..ETHIOPIC TONAL MARK KURT
@ -1313,7 +1351,7 @@ AB28..AB2E ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE BBA..ETHIOPIC SYLLABLE BBO
# ================================================
1780..17B3 ; Khmer # Lo [52] KHMER LETTER KA..KHMER INDEPENDENT VOWEL QAU
17B4..17B5 ; Khmer # Cf [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
17B4..17B5 ; Khmer # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
17B6 ; Khmer # Mc KHMER VOWEL SIGN AA
17B7..17BD ; Khmer # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA
17BE..17C5 ; Khmer # Mc [8] KHMER VOWEL SIGN OE..KHMER VOWEL SIGN AU
@ -1393,16 +1431,15 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
3038..303A ; Han # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY
303B ; Han # Lm VERTICAL IDEOGRAPHIC ITERATION MARK
3400..4DB5 ; Han # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4E00..9FCB ; Han # Lo [20940] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCB
F900..FA2D ; Han # Lo [302] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA2D
FA30..FA6D ; Han # Lo [62] CJK COMPATIBILITY IDEOGRAPH-FA30..CJK COMPATIBILITY IDEOGRAPH-FA6D
4E00..9FCC ; Han # Lo [20941] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCC
F900..FA6D ; Han # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D
FA70..FAD9 ; Han # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9
20000..2A6D6 ; Han # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
2A700..2B734 ; Han # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
2B740..2B81D ; Han # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2F800..2FA1D ; Han # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 75960
# Total code points: 75963
# ================================================
@ -1447,6 +1484,7 @@ A490..A4C6 ; Yi # So [55] YI RADICAL QOT..YI RADICAL KE
1CD4..1CE0 ; Inherited # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA
1CE2..1CE8 ; Inherited # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL
1CED ; Inherited # Mn VEDIC SIGN TIRYAK
1CF4 ; Inherited # Mn VEDIC TONE CANDRA ABOVE
1DC0..1DE6 ; Inherited # Mn [39] COMBINING DOTTED GRAVE ACCENT..COMBINING LATIN SMALL LETTER Z
1DFC..1DFF ; Inherited # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
200C..200D ; Inherited # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER
@ -1466,7 +1504,7 @@ FE20..FE26 ; Inherited # Mn [7] 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: 523
# Total code points: 524
# ================================================
@ -1587,11 +1625,12 @@ E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-2
2CE5..2CEA ; Coptic # So [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA
2CEB..2CEE ; Coptic # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA
2CEF..2CF1 ; Coptic # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS
2CF2..2CF3 ; Coptic # L& [2] COPTIC CAPITAL LETTER BOHAIRIC KHEI..COPTIC SMALL LETTER BOHAIRIC KHEI
2CF9..2CFC ; Coptic # Po [4] COPTIC OLD NUBIAN FULL STOP..COPTIC OLD NUBIAN VERSE DIVIDER
2CFD ; Coptic # No COPTIC FRACTION ONE HALF
2CFE..2CFF ; Coptic # Po [2] COPTIC FULL STOP..COPTIC MORPHOLOGICAL DIVIDER
# Total code points: 135
# Total code points: 137
# ================================================
@ -1614,12 +1653,12 @@ E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-2
# ================================================
2D30..2D65 ; Tifinagh # Lo [54] TIFINAGH LETTER YA..TIFINAGH LETTER YAZZ
2D30..2D67 ; Tifinagh # Lo [56] TIFINAGH LETTER YA..TIFINAGH LETTER YO
2D6F ; Tifinagh # Lm TIFINAGH MODIFIER LETTER LABIALIZATION MARK
2D70 ; Tifinagh # Po TIFINAGH SEPARATOR MARK
2D7F ; Tifinagh # Mn TIFINAGH CONSONANT JOINER
# Total code points: 57
# Total code points: 59
# ================================================
@ -1729,10 +1768,14 @@ A874..A877 ; Phags_Pa # Po [4] PHAGS-PA SINGLE HEAD MARK..PHAGS-PA MARK DOU
1BA6..1BA7 ; Sundanese # Mc [2] SUNDANESE VOWEL SIGN PANAELAENG..SUNDANESE VOWEL SIGN PANOLONG
1BA8..1BA9 ; Sundanese # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG
1BAA ; Sundanese # Mc SUNDANESE SIGN PAMAAEH
1BAB ; Sundanese # Mn SUNDANESE SIGN VIRAMA
1BAC..1BAD ; Sundanese # Mc [2] SUNDANESE CONSONANT SIGN PASANGAN MA..SUNDANESE CONSONANT SIGN PASANGAN WA
1BAE..1BAF ; Sundanese # Lo [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA
1BB0..1BB9 ; Sundanese # Nd [10] SUNDANESE DIGIT ZERO..SUNDANESE DIGIT NINE
1BBA..1BBF ; Sundanese # Lo [6] SUNDANESE AVAGRAHA..SUNDANESE LETTER FINAL M
1CC0..1CC7 ; Sundanese # Po [8] SUNDANESE PUNCTUATION BINDU SURYA..SUNDANESE PUNCTUATION BINDU BA SATANGA
# Total code points: 55
# Total code points: 72
# ================================================
@ -1940,6 +1983,15 @@ A9DE..A9DF ; Javanese # Po [2] JAVANESE PADA TIRTA TUMETES..JAVANESE PADA I
# ================================================
AAE0..AAEA ; Meetei_Mayek # Lo [11] MEETEI MAYEK LETTER E..MEETEI MAYEK LETTER SSA
AAEB ; Meetei_Mayek # Mc MEETEI MAYEK VOWEL SIGN II
AAEC..AAED ; Meetei_Mayek # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI
AAEE..AAEF ; Meetei_Mayek # Mc [2] MEETEI MAYEK VOWEL SIGN AU..MEETEI MAYEK VOWEL SIGN AAU
AAF0..AAF1 ; Meetei_Mayek # Po [2] MEETEI MAYEK CHEIKHAN..MEETEI MAYEK AHANG KHUDAM
AAF2 ; Meetei_Mayek # Lo MEETEI MAYEK ANJI
AAF3..AAF4 ; Meetei_Mayek # Lm [2] MEETEI MAYEK SYLLABLE REPETITION MARK..MEETEI MAYEK WORD REPETITION MARK
AAF5 ; Meetei_Mayek # Mc MEETEI MAYEK VOWEL SIGN VISARGA
AAF6 ; Meetei_Mayek # Mn MEETEI MAYEK VIRAMA
ABC0..ABE2 ; Meetei_Mayek # Lo [35] MEETEI MAYEK LETTER KOK..MEETEI MAYEK LETTER I LONSUM
ABE3..ABE4 ; Meetei_Mayek # Mc [2] MEETEI MAYEK VOWEL SIGN ONAP..MEETEI MAYEK VOWEL SIGN INAP
ABE5 ; Meetei_Mayek # Mn MEETEI MAYEK VOWEL SIGN ANAP
@ -1951,7 +2003,7 @@ ABEC ; Meetei_Mayek # Mc MEETEI MAYEK LUM IYEK
ABED ; Meetei_Mayek # Mn MEETEI MAYEK APUN IYEK
ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE
# Total code points: 56
# Total code points: 79
# ================================================
@ -2040,4 +2092,74 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
# Total code points: 29
# ================================================
11100..11102 ; Chakma # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA
11103..11126 ; Chakma # Lo [36] CHAKMA LETTER AA..CHAKMA LETTER HAA
11127..1112B ; Chakma # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU
1112C ; Chakma # Mc CHAKMA VOWEL SIGN E
1112D..11134 ; Chakma # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA
11136..1113F ; Chakma # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE
11140..11143 ; Chakma # Po [4] CHAKMA SECTION MARK..CHAKMA QUESTION MARK
# Total code points: 67
# ================================================
109A0..109B7 ; Meroitic_Cursive # Lo [24] MEROITIC CURSIVE LETTER A..MEROITIC CURSIVE LETTER DA
109BE..109BF ; Meroitic_Cursive # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN
# Total code points: 26
# ================================================
10980..1099F ; Meroitic_Hieroglyphs # Lo [32] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC HIEROGLYPHIC SYMBOL VIDJ-2
# Total code points: 32
# ================================================
16F00..16F44 ; Miao # Lo [69] MIAO LETTER PA..MIAO LETTER HHA
16F50 ; Miao # Lo MIAO LETTER NASALIZATION
16F51..16F7E ; Miao # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
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
# ================================================
11180..11181 ; Sharada # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA
11182 ; Sharada # Mc SHARADA SIGN VISARGA
11183..111B2 ; Sharada # Lo [48] SHARADA LETTER A..SHARADA LETTER HA
111B3..111B5 ; Sharada # Mc [3] SHARADA VOWEL SIGN AA..SHARADA VOWEL SIGN II
111B6..111BE ; Sharada # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O
111BF..111C0 ; Sharada # Mc [2] SHARADA VOWEL SIGN AU..SHARADA SIGN VIRAMA
111C1..111C4 ; Sharada # Lo [4] SHARADA SIGN AVAGRAHA..SHARADA OM
111C5..111C8 ; Sharada # Po [4] SHARADA DANDA..SHARADA SEPARATOR
111D0..111D9 ; Sharada # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE
# Total code points: 83
# ================================================
110D0..110E8 ; Sora_Sompeng # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE
110F0..110F9 ; Sora_Sompeng # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE
# Total code points: 35
# ================================================
11680..116AA ; Takri # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA
116AB ; Takri # Mn TAKRI SIGN ANUSVARA
116AC ; Takri # Mc TAKRI SIGN VISARGA
116AD ; Takri # Mn TAKRI VOWEL SIGN AA
116AE..116AF ; Takri # Mc [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II
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
116C0..116C9 ; Takri # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE
# Total code points: 66
# EOF

10
jdk/make/tools/UnicodeData/SpecialCasing.txt
View File

@ -1,8 +1,8 @@
# SpecialCasing-6.0.0.txt
# Date: 2010-05-18, 00:49:39 GMT [MD]
# SpecialCasing-6.1.0.txt
# Date: 2011-11-27, 05:10:51 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2010 Unicode, Inc.
# Copyright (c) 1991-2011 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
#
@ -47,7 +47,9 @@
# * Additional contexts
# * Additional fields
# ================================================================================
# @missing 0000..10FFFF; <slc>; <stc>; <suc>
# @missing: 0000..10FFFF; <slc>; <stc>; <suc>;
# ================================================================================
# Unconditional mappings
# ================================================================================

797
jdk/make/tools/UnicodeData/UnicodeData.txt
View File

File diff suppressed because it is too large Load Diff

2
jdk/make/tools/UnicodeData/VERSION
View File

@ -1 +1 @@
6.0.0
6.1.0

28
jdk/src/share/classes/java/awt/font/NumericShaper.java
View File

@ -1,5 +1,5 @@
/*
* Copyright (c) 2000, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2000, 2012, 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
@ -633,7 +633,6 @@ public final class NumericShaper implements java.io.Serializable {
0x06d6, 0x06e5,
0x06e7, 0x06ee,
0x06f0, 0x06fa,
0x070f, 0x0710,
0x0711, 0x0712,
0x0730, 0x074d,
0x07a6, 0x07b1,
@ -644,7 +643,7 @@ public final class NumericShaper implements java.io.Serializable {
0x0825, 0x0828,
0x0829, 0x0830,
0x0859, 0x085e,
0x0900, 0x0903,
0x08e4, 0x0903,
0x093a, 0x093b,
0x093c, 0x093d,
0x0941, 0x0949,
@ -723,6 +722,7 @@ public final class NumericShaper implements java.io.Serializable {
0x1732, 0x1735,
0x1752, 0x1760,
0x1772, 0x1780,
0x17b4, 0x17b6,
0x17b7, 0x17be,
0x17c6, 0x17c7,
0x17c9, 0x17d4,
@ -750,6 +750,7 @@ public final class NumericShaper implements java.io.Serializable {
0x1b80, 0x1b82,
0x1ba2, 0x1ba6,
0x1ba8, 0x1baa,
0x1bab, 0x1bac,
0x1be6, 0x1be7,
0x1be8, 0x1bea,
0x1bed, 0x1bee,
@ -760,6 +761,7 @@ public final class NumericShaper implements java.io.Serializable {
0x1cd4, 0x1ce1,
0x1ce2, 0x1ce9,
0x1ced, 0x1cee,
0x1cf4, 0x1cf5,
0x1dc0, 0x1e00,
0x1fbd, 0x1fbe,
0x1fbf, 0x1fc2,
@ -791,7 +793,8 @@ public final class NumericShaper implements java.io.Serializable {
0x26ad, 0x2800,
0x2900, 0x2c00,
0x2ce5, 0x2ceb,
0x2cef, 0x2d00,
0x2cef, 0x2cf2,
0x2cf9, 0x2d00,
0x2d7f, 0x2d80,
0x2de0, 0x3005,
0x3008, 0x3021,
@ -814,6 +817,7 @@ public final class NumericShaper implements java.io.Serializable {
0xa490, 0xa4d0,
0xa60d, 0xa610,
0xa66f, 0xa680,
0xa69f, 0xa6a0,
0xa6f0, 0xa6f2,
0xa700, 0xa722,
0xa788, 0xa789,
@ -842,6 +846,8 @@ public final class NumericShaper implements java.io.Serializable {
0xaab7, 0xaab9,
0xaabe, 0xaac0,
0xaac1, 0xaac2,
0xaaec, 0xaaee,
0xaaf6, 0xab01,
0xabe5, 0xabe6,
0xabe8, 0xabe9,
0xabed, 0xabf0,
@ -867,6 +873,16 @@ public final class NumericShaper implements java.io.Serializable {
0x11080, 0x11082,
0x110b3, 0x110b7,
0x110b9, 0x110bb,
0x11100, 0x11103,
0x11127, 0x1112c,
0x1112d, 0x11136,
0x11180, 0x11182,
0x111b6, 0x111bf,
0x116ab, 0x116ac,
0x116ad, 0x116ae,
0x116b0, 0x116b6,
0x116b7, 0x116c0,
0x16f8f, 0x16f93,
0x1d167, 0x1d16a,
0x1d173, 0x1d183,
0x1d185, 0x1d18c,
@ -877,7 +893,9 @@ public final class NumericShaper implements java.io.Serializable {
0x1d74f, 0x1d750,
0x1d789, 0x1d78a,
0x1d7c3, 0x1d7c4,
0x1d7ce, 0x1f110,
0x1d7ce, 0x1ee00,
0x1eef0, 0x1f110,
0x1f16a, 0x1f170,
0x1f300, 0x1f48c,
0x1f48d, 0x1f524,
0x1f525, 0x20000,

222
jdk/src/share/classes/java/lang/Character.java
View File

@ -1,5 +1,5 @@
/*
* Copyright (c) 2002, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2002, 2012, 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
@ -40,7 +40,7 @@ import java.util.Locale;
* a character's category (lowercase letter, digit, etc.) and for converting
* characters from uppercase to lowercase and vice versa.
* <p>
* Character information is based on the Unicode Standard, version 6.0.0.
* Character information is based on the Unicode Standard, version 6.1.0.
* <p>
* The methods and data of class {@code Character} are defined by
* the information in the <i>UnicodeData</i> file that is part of the
@ -2465,6 +2465,98 @@ class Character implements java.io.Serializable, Comparable<Character> {
"CJK UNIFIED IDEOGRAPHS EXTENSION D",
"CJKUNIFIEDIDEOGRAPHSEXTENSIOND");
/**
* Constant for the "Arabic Extended-A" Unicode character block.
* @since 1.8
*/
public static final UnicodeBlock ARABIC_EXTENDED_A =
new UnicodeBlock("ARABIC_EXTENDED_A",
"ARABIC EXTENDED-A",
"ARABICEXTENDED-A");
/**
* Constant for the "Sundanese Supplement" Unicode character block.
* @since 1.8
*/
public static final UnicodeBlock SUNDANESE_SUPPLEMENT =
new UnicodeBlock("SUNDANESE_SUPPLEMENT",
"SUNDANESE SUPPLEMENT",
"SUNDANESESUPPLEMENT");
/**
* Constant for the "Meetei Mayek Extensions" Unicode character block.
* @since 1.8
*/
public static final UnicodeBlock MEETEI_MAYEK_EXTENSIONS =
new UnicodeBlock("MEETEI_MAYEK_EXTENSIONS",
"MEETEI MAYEK EXTENSIONS",
"MEETEIMAYEKEXTENSIONS");
/**
* Constant for the "Meroitic Hieroglyphs" Unicode character block.
* @since 1.8
*/
public static final UnicodeBlock MEROITIC_HIEROGLYPHS =
new UnicodeBlock("MEROITIC_HIEROGLYPHS",
"MEROITIC HIEROGLYPHS",
"MEROITICHIEROGLYPHS");
/**
* Constant for the "Meroitic Cursive" Unicode character block.
* @since 1.8
*/
public static final UnicodeBlock MEROITIC_CURSIVE =
new UnicodeBlock("MEROITIC_CURSIVE",
"MEROITIC CURSIVE",
"MEROITICCURSIVE");
/**
* Constant for the "Sora Sompeng" Unicode character block.
* @since 1.8
*/
public static final UnicodeBlock SORA_SOMPENG =
new UnicodeBlock("SORA_SOMPENG",
"SORA SOMPENG",
"SORASOMPENG");
/**
* Constant for the "Chakma" Unicode character block.
* @since 1.8
*/
public static final UnicodeBlock CHAKMA =
new UnicodeBlock("CHAKMA");
/**
* Constant for the "Sharada" Unicode character block.
* @since 1.8
*/
public static final UnicodeBlock SHARADA =
new UnicodeBlock("SHARADA");
/**
* Constant for the "Takri" Unicode character block.
* @since 1.8
*/
public static final UnicodeBlock TAKRI =
new UnicodeBlock("TAKRI");
/**
* Constant for the "Miao" Unicode character block.
* @since 1.8
*/
public static final UnicodeBlock MIAO =
new UnicodeBlock("MIAO");
/**
* Constant for the "Arabic Mathematical Alphabetic Symbols" Unicode
* character block.
* @since 1.8
*/
public static final UnicodeBlock ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS =
new UnicodeBlock("ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS",
"ARABIC MATHEMATICAL ALPHABETIC SYMBOLS",
"ARABICMATHEMATICALALPHABETICSYMBOLS");
private static final int blockStarts[] = {
0x0000, // 0000..007F; Basic Latin
0x0080, // 0080..00FF; Latin-1 Supplement
@ -2486,6 +2578,7 @@ class Character implements java.io.Serializable, Comparable<Character> {
0x0800, // 0800..083F; Samaritan
0x0840, // 0840..085F; Mandaic
0x0860, // unassigned
0x08A0, // 08A0..08FF; Arabic Extended-A
0x0900, // 0900..097F; Devanagari
0x0980, // 0980..09FF; Bengali
0x0A00, // 0A00..0A7F; Gurmukhi
@ -2528,6 +2621,7 @@ class Character implements java.io.Serializable, Comparable<Character> {
0x1C00, // 1C00..1C4F; Lepcha
0x1C50, // 1C50..1C7F; Ol Chiki
0x1C80, // unassigned
0x1CC0, // 1CC0..1CCF; Sundanese Supplement
0x1CD0, // 1CD0..1CFF; Vedic Extensions
0x1D00, // 1D00..1D7F; Phonetic Extensions
0x1D80, // 1D80..1DBF; Phonetic Extensions Supplement
@ -2605,7 +2699,7 @@ class Character implements java.io.Serializable, Comparable<Character> {
0xAA00, // AA00..AA5F; Cham
0xAA60, // AA60..AA7F; Myanmar Extended-A
0xAA80, // AA80..AADF; Tai Viet
0xAAE0, // unassigned
0xAAE0, // AAE0..AAFF; Meetei Mayek Extensions
0xAB00, // AB00..AB2F; Ethiopic Extended-A
0xAB30, // unassigned
0xABC0, // ABC0..ABFF; Meetei Mayek
@ -2652,6 +2746,8 @@ class Character implements java.io.Serializable, Comparable<Character> {
0x10900, // 10900..1091F; Phoenician
0x10920, // 10920..1093F; Lydian
0x10940, // unassigned
0x10980, // 10980..1099F; Meroitic Hieroglyphs
0x109A0, // 109A0..109FF; Meroitic Cursive
0x10A00, // 10A00..10A5F; Kharoshthi
0x10A60, // 10A60..10A7F; Old South Arabian
0x10A80, // unassigned
@ -2665,7 +2761,13 @@ class Character implements java.io.Serializable, Comparable<Character> {
0x10E80, // unassigned
0x11000, // 11000..1107F; Brahmi
0x11080, // 11080..110CF; Kaithi
0x110D0, // unassigned
0x110D0, // 110D0..110FF; Sora Sompeng
0x11100, // 11100..1114F; Chakma
0x11150, // unassigned
0x11180, // 11180..111DF; Sharada
0x111E0, // unassigned
0x11680, // 11680..116CF; Takri
0x116D0, // unassigned
0x12000, // 12000..123FF; Cuneiform
0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation
0x12480, // unassigned
@ -2673,6 +2775,8 @@ class Character implements java.io.Serializable, Comparable<Character> {
0x13430, // unassigned
0x16800, // 16800..16A3F; Bamum Supplement
0x16A40, // unassigned
0x16F00, // 16F00..16F9F; Miao
0x16FA0, // unassigned
0x1B000, // 1B000..1B0FF; Kana Supplement
0x1B100, // unassigned
0x1D000, // 1D000..1D0FF; Byzantine Musical Symbols
@ -2684,6 +2788,8 @@ class Character implements java.io.Serializable, Comparable<Character> {
0x1D380, // unassigned
0x1D400, // 1D400..1D7FF; Mathematical Alphanumeric Symbols
0x1D800, // unassigned
0x1EE00, // 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
0x1EF00, // unassigned
0x1F000, // 1F000..1F02F; Mahjong Tiles
0x1F030, // 1F030..1F09F; Domino Tiles
0x1F0A0, // 1F0A0..1F0FF; Playing Cards
@ -2731,6 +2837,7 @@ class Character implements java.io.Serializable, Comparable<Character> {
SAMARITAN,
MANDAIC,
null,
ARABIC_EXTENDED_A,
DEVANAGARI,
BENGALI,
GURMUKHI,
@ -2773,6 +2880,7 @@ class Character implements java.io.Serializable, Comparable<Character> {
LEPCHA,
OL_CHIKI,
null,
SUNDANESE_SUPPLEMENT,
VEDIC_EXTENSIONS,
PHONETIC_EXTENSIONS,
PHONETIC_EXTENSIONS_SUPPLEMENT,
@ -2850,7 +2958,7 @@ class Character implements java.io.Serializable, Comparable<Character> {
CHAM,
MYANMAR_EXTENDED_A,
TAI_VIET,
null,
MEETEI_MAYEK_EXTENSIONS,
ETHIOPIC_EXTENDED_A,
null,
MEETEI_MAYEK,
@ -2897,6 +3005,8 @@ class Character implements java.io.Serializable, Comparable<Character> {
PHOENICIAN,
LYDIAN,
null,
MEROITIC_HIEROGLYPHS,
MEROITIC_CURSIVE,
KHAROSHTHI,
OLD_SOUTH_ARABIAN,
null,
@ -2910,6 +3020,12 @@ class Character implements java.io.Serializable, Comparable<Character> {
null,
BRAHMI,
KAITHI,
SORA_SOMPENG,
CHAKMA,
null,
SHARADA,
null,
TAKRI,
null,
CUNEIFORM,
CUNEIFORM_NUMBERS_AND_PUNCTUATION,
@ -2918,6 +3034,8 @@ class Character implements java.io.Serializable, Comparable<Character> {
null,
BAMUM_SUPPLEMENT,
null,
MIAO,
null,
KANA_SUPPLEMENT,
null,
BYZANTINE_MUSICAL_SYMBOLS,
@ -2929,6 +3047,8 @@ class Character implements java.io.Serializable, Comparable<Character> {
null,
MATHEMATICAL_ALPHANUMERIC_SYMBOLS,
null,
ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS,
null,
MAHJONG_TILES,
DOMINO_TILES,
PLAYING_CARDS,
@ -3549,6 +3669,41 @@ class Character implements java.io.Serializable, Comparable<Character> {
*/
KAITHI,
/**
* Unicode script "Meroitic Hieroglyphs".
*/
MEROITIC_HIEROGLYPHS,
/**
* Unicode script "Meroitic Cursive".
*/
MEROITIC_CURSIVE,
/**
* Unicode script "Sora Sompeng".
*/
SORA_SOMPENG,
/**
* Unicode script "Chakma".
*/
CHAKMA,
/**
* Unicode script "Sharada".
*/
SHARADA,
/**
* Unicode script "Takri".
*/
TAKRI,
/**
* Unicode script "Miao".
*/
MIAO,
/**
* Unicode script "Unknown".
*/
@ -3616,14 +3771,13 @@ class Character implements java.io.Serializable, Comparable<Character> {
0x0780, // 0780..07BF; THAANA
0x07C0, // 07C0..07FF; NKO
0x0800, // 0800..083F; SAMARITAN
0x0840, // 0840..08FF; MANDAIC
0x0840, // 0840..089F; MANDAIC
0x08A0, // 08A0..08FF; ARABIC
0x0900, // 0900..0950; DEVANAGARI
0x0951, // 0951..0952; INHERITED
0x0953, // 0953..0963; DEVANAGARI
0x0964, // 0964..0965; COMMON
0x0966, // 0966..096F; DEVANAGARI
0x0970, // 0970..0970; COMMON
0x0971, // 0971..0980; DEVANAGARI
0x0966, // 0966..0980; DEVANAGARI
0x0981, // 0981..0A00; BENGALI
0x0A01, // 0A01..0A80; GURMUKHI
0x0A81, // 0A81..0B00; GUJARATI
@ -3674,7 +3828,8 @@ class Character implements java.io.Serializable, Comparable<Character> {
0x1B80, // 1B80..1BBF; SUNDANESE
0x1BC0, // 1BC0..1BFF; BATAK
0x1C00, // 1C00..1C4F; LEPCHA
0x1C50, // 1C50..1CCF; OL_CHIKI
0x1C50, // 1C50..1CBF; OL_CHIKI
0x1CC0, // 1CC0..1CCF; SUNDANESE
0x1CD0, // 1CD0..1CD2; INHERITED
0x1CD3, // 1CD3..1CD3; COMMON
0x1CD4, // 1CD4..1CE0; INHERITED
@ -3682,7 +3837,9 @@ class Character implements java.io.Serializable, Comparable<Character> {
0x1CE2, // 1CE2..1CE8; INHERITED
0x1CE9, // 1CE9..1CEC; COMMON
0x1CED, // 1CED..1CED; INHERITED
0x1CEE, // 1CEE..1CFF; COMMON
0x1CEE, // 1CEE..1CF3; COMMON
0x1CF4, // 1CF4..1CF4; INHERITED
0x1CF5, // 1CF5..1CFF; COMMON
0x1D00, // 1D00..1D25; LATIN
0x1D26, // 1D26..1D2A; GREEK
0x1D2B, // 1D2B..1D2B; CYRILLIC
@ -3783,7 +3940,8 @@ class Character implements java.io.Serializable, Comparable<Character> {
0xA980, // A980..A9FF; JAVANESE
0xAA00, // AA00..AA5F; CHAM
0xAA60, // AA60..AA7F; MYANMAR
0xAA80, // AA80..AB00; TAI_VIET
0xAA80, // AA80..AADF; TAI_VIET
0xAAE0, // AAE0..AB00; MEETEI_MAYEK
0xAB01, // AB01..ABBF; ETHIOPIC
0xABC0, // ABC0..ABFF; MEETEI_MAYEK
0xAC00, // AC00..D7FB; HANGUL
@ -3829,7 +3987,9 @@ class Character implements java.io.Serializable, Comparable<Character> {
0x10800, // 10800..1083F; CYPRIOT
0x10840, // 10840..108FF; IMPERIAL_ARAMAIC
0x10900, // 10900..1091F; PHOENICIAN
0x10920, // 10920..109FF; LYDIAN
0x10920, // 10920..1097F; LYDIAN
0x10980, // 10980..1099F; MEROITIC_HIEROGLYPHS
0x109A0, // 109A0..109FF; MEROITIC_CURSIVE
0x10A00, // 10A00..10A5F; KHAROSHTHI
0x10A60, // 10A60..10AFF; OLD_SOUTH_ARABIAN
0x10B00, // 10B00..10B3F; AVESTAN
@ -3838,10 +3998,15 @@ class Character implements java.io.Serializable, Comparable<Character> {
0x10C00, // 10C00..10E5F; OLD_TURKIC
0x10E60, // 10E60..10FFF; ARABIC
0x11000, // 11000..1107F; BRAHMI
0x11080, // 11080..11FFF; KAITHI
0x11080, // 11080..110CF; KAITHI
0x110D0, // 110D0..110FF; SORA_SOMPENG
0x11100, // 11100..1117F; CHAKMA
0x11180, // 11180..1167F; SHARADA
0x11680, // 11680..116CF; TAKRI
0x12000, // 12000..12FFF; CUNEIFORM
0x13000, // 13000..167FF; EGYPTIAN_HIEROGLYPHS
0x16800, // 16800..16A38; BAMUM
0x16F00, // 16F00..16F9F; MIAO
0x1B000, // 1B000..1B000; KATAKANA
0x1B001, // 1B001..1CFFF; HIRAGANA
0x1D000, // 1D000..1D166; COMMON
@ -3854,7 +4019,9 @@ class Character implements java.io.Serializable, Comparable<Character> {
0x1D1AA, // 1D1AA..1D1AD; INHERITED
0x1D1AE, // 1D1AE..1D1FF; COMMON
0x1D200, // 1D200..1D2FF; GREEK
0x1D300, // 1D300..1F1FF; COMMON
0x1D300, // 1D300..1EDFF; COMMON
0x1EE00, // 1EE00..1EFFF; ARABIC
0x1F000, // 1F000..1F1FF; COMMON
0x1F200, // 1F200..1F200; HIRAGANA
0x1F201, // 1F210..1FFFF; COMMON
0x20000, // 20000..E0000; HAN
@ -3927,13 +4094,12 @@ class Character implements java.io.Serializable, Comparable<Character> {
NKO,
SAMARITAN,
MANDAIC,
ARABIC,
DEVANAGARI,
INHERITED,
DEVANAGARI,
COMMON,
DEVANAGARI,
COMMON,
DEVANAGARI,
BENGALI,
GURMUKHI,
GUJARATI,
@ -3985,6 +4151,9 @@ class Character implements java.io.Serializable, Comparable<Character> {
BATAK,
LEPCHA,
OL_CHIKI,
SUNDANESE,
INHERITED,
COMMON,
INHERITED,
COMMON,
INHERITED,
@ -4094,10 +4263,11 @@ class Character implements java.io.Serializable, Comparable<Character> {
CHAM,
MYANMAR,
TAI_VIET,
MEETEI_MAYEK,
ETHIOPIC,
MEETEI_MAYEK,
HANGUL,
UNKNOWN,
UNKNOWN ,
HAN,
LATIN,
ARMENIAN,
@ -4140,6 +4310,8 @@ class Character implements java.io.Serializable, Comparable<Character> {
IMPERIAL_ARAMAIC,
PHOENICIAN,
LYDIAN,
MEROITIC_HIEROGLYPHS,
MEROITIC_CURSIVE,
KHAROSHTHI,
OLD_SOUTH_ARABIAN,
AVESTAN,
@ -4149,9 +4321,14 @@ class Character implements java.io.Serializable, Comparable<Character> {
ARABIC,
BRAHMI,
KAITHI,
SORA_SOMPENG,
CHAKMA,
SHARADA,
TAKRI,
CUNEIFORM,
EGYPTIAN_HIEROGLYPHS,
BAMUM,
MIAO,
KATAKANA,
HIRAGANA,
COMMON,
@ -4165,6 +4342,8 @@ class Character implements java.io.Serializable, Comparable<Character> {
COMMON,
GREEK,
COMMON,
ARABIC,
COMMON,
HIRAGANA,
COMMON,
HAN,
@ -4189,6 +4368,7 @@ class Character implements java.io.Serializable, Comparable<Character> {
aliases.put("BRAH", BRAHMI);
aliases.put("BUGI", BUGINESE);
aliases.put("BUHD", BUHID);
aliases.put("CAKM", CHAKMA);
aliases.put("CANS", CANADIAN_ABORIGINAL);
aliases.put("CARI", CARIAN);
aliases.put("CHAM", CHAM);
@ -4231,6 +4411,8 @@ class Character implements java.io.Serializable, Comparable<Character> {
aliases.put("LYCI", LYCIAN);
aliases.put("LYDI", LYDIAN);
aliases.put("MAND", MANDAIC);
aliases.put("MERC", MEROITIC_CURSIVE);
aliases.put("MERO", MEROITIC_HIEROGLYPHS);
aliases.put("MLYM", MALAYALAM);
aliases.put("MONG", MONGOLIAN);
aliases.put("MTEI", MEETEI_MAYEK);
@ -4242,6 +4424,7 @@ class Character implements java.io.Serializable, Comparable<Character> {
aliases.put("ORYA", ORIYA);
aliases.put("OSMA", OSMANYA);
aliases.put("PHAG", PHAGS_PA);
aliases.put("PLRD", MIAO);
aliases.put("PHLI", INSCRIPTIONAL_PAHLAVI);
aliases.put("PHNX", PHOENICIAN);
aliases.put("PRTI", INSCRIPTIONAL_PARTHIAN);
@ -4251,12 +4434,15 @@ class Character implements java.io.Serializable, Comparable<Character> {
aliases.put("SARB", OLD_SOUTH_ARABIAN);
aliases.put("SAUR", SAURASHTRA);
aliases.put("SHAW", SHAVIAN);
aliases.put("SHRD", SHARADA);
aliases.put("SINH", SINHALA);
aliases.put("SORA", SORA_SOMPENG);
aliases.put("SUND", SUNDANESE);
aliases.put("SYLO", SYLOTI_NAGRI);
aliases.put("SYRC", SYRIAC);
aliases.put("TAGB", TAGBANWA);
aliases.put("TALE", TAI_LE);
aliases.put("TAKR", TAKRI);
aliases.put("TALU", NEW_TAI_LUE);
aliases.put("TAML", TAMIL);
aliases.put("TAVT", TAI_VIET);

BIN
jdk/src/share/classes/sun/text/resources/ubidi.icu
View File

Binary file not shown.

BIN
jdk/src/share/classes/sun/text/resources/unorm.icu
View File

Binary file not shown.

BIN
jdk/src/share/classes/sun/text/resources/uprops.icu
View File

Binary file not shown.

2
jdk/test/java/lang/Character/CheckProp.java
View File

@ -24,7 +24,7 @@
/**
* @test
* @bug 7037261
* @bug 7037261 7070436
* @summary Check j.l.Character.isLowerCase/isUppercase/isAlphabetic/isIdeographic
*/

2
jdk/test/java/lang/Character/CheckScript.java
View File

@ -24,7 +24,7 @@
/**
* @test
* @bug 6945564 6959267 7033561
* @bug 6945564 6959267 7033561 7070436
* @summary Check that the j.l.Character.UnicodeScript
*/

155
jdk/test/java/lang/Character/PropList.txt
View File

@ -1,8 +1,8 @@
# PropList-6.0.0.txt
# Date: 2010-08-19, 00:48:28 GMT [MD]
# PropList-6.1.0.txt
# Date: 2011-11-30, 01:49:54 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2010 Unicode, Inc.
# Copyright (c) 1991-2011 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
@ -50,6 +50,7 @@
2212 ; Dash # Sm MINUS SIGN
2E17 ; Dash # Pd DOUBLE OBLIQUE HYPHEN
2E1A ; Dash # Pd HYPHEN WITH DIAERESIS
2E3A..2E3B ; Dash # Pd [2] TWO-EM DASH..THREE-EM DASH
301C ; Dash # Pd WAVE DASH
3030 ; Dash # Pd WAVY DASH
30A0 ; Dash # Pd KATAKANA-HIRAGANA DOUBLE HYPHEN
@ -58,7 +59,7 @@ FE58 ; Dash # Pd SMALL EM DASH
FE63 ; Dash # Pd SMALL HYPHEN-MINUS
FF0D ; Dash # Pd FULLWIDTH HYPHEN-MINUS
# Total code points: 25
# Total code points: 27
# ================================================
@ -158,6 +159,7 @@ A92F ; Terminal_Punctuation # Po KAYAH LI SIGN SHYA
A9C7..A9C9 ; Terminal_Punctuation # Po [3] JAVANESE PADA PANGKAT..JAVANESE PADA LUNGSI
AA5D..AA5F ; Terminal_Punctuation # Po [3] CHAM PUNCTUATION DANDA..CHAM PUNCTUATION TRIPLE DANDA
AADF ; Terminal_Punctuation # Po TAI VIET SYMBOL KOI KOI
AAF0..AAF1 ; Terminal_Punctuation # Po [2] MEETEI MAYEK CHEIKHAN..MEETEI MAYEK AHANG KHUDAM
ABEB ; Terminal_Punctuation # Po MEETEI MAYEK CHEIKHEI
FE50..FE52 ; Terminal_Punctuation # Po [3] SMALL COMMA..SMALL FULL STOP
FE54..FE57 ; Terminal_Punctuation # Po [4] SMALL SEMICOLON..SMALL EXCLAMATION MARK
@ -175,9 +177,11 @@ FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA
10B3A..10B3F ; Terminal_Punctuation # Po [6] TINY TWO DOTS OVER ONE DOT PUNCTUATION..LARGE ONE RING OVER TWO RINGS PUNCTUATION
11047..1104D ; Terminal_Punctuation # Po [7] BRAHMI DANDA..BRAHMI PUNCTUATION LOTUS
110BE..110C1 ; Terminal_Punctuation # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA
11141..11143 ; Terminal_Punctuation # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK
111C5..111C6 ; Terminal_Punctuation # Po [2] SHARADA DANDA..SHARADA DOUBLE DANDA
12470..12473 ; Terminal_Punctuation # Po [4] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL TRICOLON
# Total code points: 169
# Total code points: 176
# ================================================
@ -320,8 +324,41 @@ FF3E ; Other_Math # Sk FULLWIDTH CIRCUMFLEX ACCENT
1D7AA..1D7C2 ; Other_Math # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA
1D7C4..1D7CB ; Other_Math # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA
1D7CE..1D7FF ; Other_Math # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
1EE00..1EE03 ; Other_Math # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL
1EE05..1EE1F ; Other_Math # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF
1EE21..1EE22 ; Other_Math # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM
1EE24 ; Other_Math # Lo ARABIC MATHEMATICAL INITIAL HEH
1EE27 ; Other_Math # Lo ARABIC MATHEMATICAL INITIAL HAH
1EE29..1EE32 ; Other_Math # Lo [10] ARABIC MATHEMATICAL INITIAL YEH..ARABIC MATHEMATICAL INITIAL QAF
1EE34..1EE37 ; Other_Math # Lo [4] ARABIC MATHEMATICAL INITIAL SHEEN..ARABIC MATHEMATICAL INITIAL KHAH
1EE39 ; Other_Math # Lo ARABIC MATHEMATICAL INITIAL DAD
1EE3B ; Other_Math # Lo ARABIC MATHEMATICAL INITIAL GHAIN
1EE42 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED JEEM
1EE47 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED HAH
1EE49 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED YEH
1EE4B ; Other_Math # Lo ARABIC MATHEMATICAL TAILED LAM
1EE4D..1EE4F ; Other_Math # Lo [3] ARABIC MATHEMATICAL TAILED NOON..ARABIC MATHEMATICAL TAILED AIN
1EE51..1EE52 ; Other_Math # Lo [2] ARABIC MATHEMATICAL TAILED SAD..ARABIC MATHEMATICAL TAILED QAF
1EE54 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED SHEEN
1EE57 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED KHAH
1EE59 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED DAD
1EE5B ; Other_Math # Lo ARABIC MATHEMATICAL TAILED GHAIN
1EE5D ; Other_Math # Lo ARABIC MATHEMATICAL TAILED DOTLESS NOON
1EE5F ; Other_Math # Lo ARABIC MATHEMATICAL TAILED DOTLESS QAF
1EE61..1EE62 ; Other_Math # Lo [2] ARABIC MATHEMATICAL STRETCHED BEH..ARABIC MATHEMATICAL STRETCHED JEEM
1EE64 ; Other_Math # Lo ARABIC MATHEMATICAL STRETCHED HEH
1EE67..1EE6A ; Other_Math # Lo [4] ARABIC MATHEMATICAL STRETCHED HAH..ARABIC MATHEMATICAL STRETCHED KAF
1EE6C..1EE72 ; Other_Math # Lo [7] ARABIC MATHEMATICAL STRETCHED MEEM..ARABIC MATHEMATICAL STRETCHED QAF
1EE74..1EE77 ; Other_Math # Lo [4] ARABIC MATHEMATICAL STRETCHED SHEEN..ARABIC MATHEMATICAL STRETCHED KHAH
1EE79..1EE7C ; Other_Math # Lo [4] ARABIC MATHEMATICAL STRETCHED DAD..ARABIC MATHEMATICAL STRETCHED DOTLESS BEH
1EE7E ; Other_Math # Lo ARABIC MATHEMATICAL STRETCHED DOTLESS FEH
1EE80..1EE89 ; Other_Math # Lo [10] ARABIC MATHEMATICAL LOOPED ALEF..ARABIC MATHEMATICAL LOOPED YEH
1EE8B..1EE9B ; Other_Math # Lo [17] ARABIC MATHEMATICAL LOOPED LAM..ARABIC MATHEMATICAL LOOPED GHAIN
1EEA1..1EEA3 ; Other_Math # Lo [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL
1EEA5..1EEA9 ; Other_Math # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH
1EEAB..1EEBB ; Other_Math # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
# Total code points: 1217
# Total code points: 1358
# ================================================
@ -365,6 +402,8 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
081B..0823 ; Other_Alphabetic # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A
0825..0827 ; Other_Alphabetic # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U
0829..082C ; Other_Alphabetic # Mn [4] SAMARITAN VOWEL SIGN LONG I..SAMARITAN VOWEL SIGN SUKUN
08E4..08E9 ; Other_Alphabetic # Mn [6] ARABIC CURLY FATHA..ARABIC CURLY KASRATAN
08F0..08FE ; Other_Alphabetic # Mn [15] ARABIC OPEN FATHATAN..ARABIC DAMMA WITH DOT
0900..0902 ; Other_Alphabetic # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA
0903 ; Other_Alphabetic # Mc DEVANAGARI SIGN VISARGA
093A ; Other_Alphabetic # Mn DEVANAGARI VOWEL SIGN OE
@ -525,6 +564,7 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
1BA2..1BA5 ; Other_Alphabetic # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU
1BA6..1BA7 ; Other_Alphabetic # Mc [2] SUNDANESE VOWEL SIGN PANAELAENG..SUNDANESE VOWEL SIGN PANOLONG
1BA8..1BA9 ; Other_Alphabetic # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG
1BAC..1BAD ; Other_Alphabetic # Mc [2] SUNDANESE CONSONANT SIGN PASANGAN MA..SUNDANESE CONSONANT SIGN PASANGAN WA
1BE7 ; Other_Alphabetic # Mc BATAK VOWEL SIGN E
1BE8..1BE9 ; Other_Alphabetic # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE
1BEA..1BEC ; Other_Alphabetic # Mc [3] BATAK VOWEL SIGN I..BATAK VOWEL SIGN O
@ -534,9 +574,11 @@ 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 ; Other_Alphabetic # Mc VEDIC SIGN ARDHAVISARGA
1CF2..1CF3 ; Other_Alphabetic # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
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
A69F ; Other_Alphabetic # Mn COMBINING CYRILLIC LETTER IOTIFIED E
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
@ -564,6 +606,10 @@ 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
AABE ; Other_Alphabetic # Mn TAI VIET VOWEL AM
AAEB ; Other_Alphabetic # Mc MEETEI MAYEK VOWEL SIGN II
AAEC..AAED ; Other_Alphabetic # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI
AAEE..AAEF ; Other_Alphabetic # Mc [2] MEETEI MAYEK VOWEL SIGN AU..MEETEI MAYEK VOWEL SIGN AAU
AAF5 ; Other_Alphabetic # Mc MEETEI MAYEK VOWEL SIGN VISARGA
ABE3..ABE4 ; Other_Alphabetic # Mc [2] MEETEI MAYEK VOWEL SIGN ONAP..MEETEI MAYEK VOWEL SIGN INAP
ABE5 ; Other_Alphabetic # Mn MEETEI MAYEK VOWEL SIGN ANAP
ABE6..ABE7 ; Other_Alphabetic # Mc [2] MEETEI MAYEK VOWEL SIGN YENAP..MEETEI MAYEK VOWEL SIGN SOUNAP
@ -581,8 +627,23 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
110B0..110B2 ; Other_Alphabetic # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II
110B3..110B6 ; Other_Alphabetic # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI
110B7..110B8 ; Other_Alphabetic # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU
11100..11102 ; Other_Alphabetic # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA
11127..1112B ; Other_Alphabetic # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU
1112C ; Other_Alphabetic # Mc CHAKMA VOWEL SIGN E
1112D..11132 ; Other_Alphabetic # Mn [6] CHAKMA VOWEL SIGN AI..CHAKMA AU MARK
11180..11181 ; Other_Alphabetic # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA
11182 ; Other_Alphabetic # Mc SHARADA SIGN VISARGA
111B3..111B5 ; Other_Alphabetic # Mc [3] SHARADA VOWEL SIGN AA..SHARADA VOWEL SIGN II
111B6..111BE ; Other_Alphabetic # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O
111BF ; Other_Alphabetic # Mc SHARADA VOWEL SIGN AU
116AB ; Other_Alphabetic # Mn TAKRI SIGN ANUSVARA
116AC ; Other_Alphabetic # Mc TAKRI SIGN VISARGA
116AD ; Other_Alphabetic # Mn TAKRI VOWEL SIGN AA
116AE..116AF ; Other_Alphabetic # Mc [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II
116B0..116B5 ; Other_Alphabetic # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU
16F51..16F7E ; Other_Alphabetic # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
# Total code points: 795
# Total code points: 922
# ================================================
@ -591,16 +652,15 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
3021..3029 ; Ideographic # Nl [9] HANGZHOU NUMERAL ONE..HANGZHOU NUMERAL NINE
3038..303A ; Ideographic # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY
3400..4DB5 ; Ideographic # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4E00..9FCB ; Ideographic # Lo [20940] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCB
F900..FA2D ; Ideographic # Lo [302] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA2D
FA30..FA6D ; Ideographic # Lo [62] CJK COMPATIBILITY IDEOGRAPH-FA30..CJK COMPATIBILITY IDEOGRAPH-FA6D
4E00..9FCC ; Ideographic # Lo [20941] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCC
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
20000..2A6D6 ; Ideographic # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
2A700..2B734 ; Ideographic # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
2B740..2B81D ; Ideographic # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 75630
# Total code points: 75633
# ================================================
@ -645,6 +705,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
07EB..07F3 ; Diacritic # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE
07F4..07F5 ; Diacritic # Lm [2] NKO HIGH TONE APOSTROPHE..NKO LOW TONE APOSTROPHE
0818..0819 ; Diacritic # Mn [2] SAMARITAN MARK OCCLUSION..SAMARITAN MARK DAGESH
08E4..08FE ; Diacritic # Mn [27] ARABIC CURLY FATHA..ARABIC DAMMA WITH DOT
093C ; Diacritic # Mn DEVANAGARI SIGN NUKTA
094D ; Diacritic # Mn DEVANAGARI SIGN VIRAMA
0951..0954 ; Diacritic # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT
@ -689,6 +750,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
1B44 ; Diacritic # Mc BALINESE ADEG ADEG
1B6B..1B73 ; Diacritic # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG
1BAA ; Diacritic # Mc SUNDANESE SIGN PAMAAEH
1BAB ; Diacritic # Mn SUNDANESE SIGN VIRAMA
1C36..1C37 ; Diacritic # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA
1C78..1C7D ; Diacritic # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD
1CD0..1CD2 ; Diacritic # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA
@ -697,8 +759,8 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
1CE1 ; Diacritic # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA
1CE2..1CE8 ; Diacritic # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL
1CED ; Diacritic # Mn VEDIC SIGN TIRYAK
1D2C..1D61 ; Diacritic # Lm [54] MODIFIER LETTER CAPITAL A..MODIFIER LETTER SMALL CHI
1D62..1D6A ; Diacritic # L& [9] LATIN SUBSCRIPT SMALL LETTER I..GREEK SUBSCRIPT SMALL LETTER CHI
1CF4 ; Diacritic # Mn VEDIC TONE CANDRA ABOVE
1D2C..1D6A ; Diacritic # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI
1DC4..1DCF ; Diacritic # Mn [12] COMBINING MACRON-ACUTE..COMBINING ZIGZAG BELOW
1DFD..1DFF ; Diacritic # Mn [3] COMBINING ALMOST EQUAL TO BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
1FBD ; Diacritic # Sk GREEK KORONIS
@ -709,7 +771,8 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
1FFD..1FFE ; Diacritic # Sk [2] GREEK OXIA..GREEK DASIA
2CEF..2CF1 ; Diacritic # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS
2E2F ; Diacritic # Lm VERTICAL TILDE
302A..302F ; Diacritic # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK
302A..302D ; Diacritic # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK
302E..302F ; Diacritic # Mc [2] HANGUL SINGLE DOT TONE MARK..HANGUL DOUBLE DOT TONE MARK
3099..309A ; Diacritic # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
309B..309C ; Diacritic # Sk [2] KATAKANA-HIRAGANA VOICED SOUND MARK..KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
30FC ; Diacritic # Lm KATAKANA-HIRAGANA PROLONGED SOUND MARK
@ -720,6 +783,7 @@ A6F0..A6F1 ; Diacritic # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINI
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
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
A92B..A92D ; Diacritic # Mn [3] KAYAH LI TONE PLOPHU..KAYAH LI TONE CALYA PLOPHU
@ -732,6 +796,7 @@ AABF ; Diacritic # Mn TAI VIET TONE MAI EK
AAC0 ; Diacritic # Lo TAI VIET TONE MAI NUENG
AAC1 ; Diacritic # Mn TAI VIET TONE MAI THO
AAC2 ; Diacritic # Lo TAI VIET TONE MAI SONG
AAF6 ; Diacritic # Mn MEETEI MAYEK VIRAMA
ABEC ; Diacritic # Mc MEETEI MAYEK LUM IYEK
ABED ; Diacritic # Mn MEETEI MAYEK APUN IYEK
FB1E ; Diacritic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
@ -742,13 +807,19 @@ FF70 ; Diacritic # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND
FF9E..FF9F ; Diacritic # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
FFE3 ; Diacritic # Sk FULLWIDTH MACRON
110B9..110BA ; Diacritic # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA
11133..11134 ; Diacritic # Mn [2] CHAKMA VIRAMA..CHAKMA MAAYYAA
111C0 ; Diacritic # Mc SHARADA SIGN VIRAMA
116B6 ; Diacritic # Mc TAKRI SIGN VIRAMA
116B7 ; Diacritic # Mn TAKRI SIGN NUKTA
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
1D16D..1D172 ; Diacritic # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5
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
# Total code points: 639
# Total code points: 693
# ================================================
@ -758,6 +829,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON
07FA ; Extender # Lm NKO LAJANYALAN
0E46 ; Extender # Lm THAI CHARACTER MAIYAMOK
0EC6 ; Extender # Lm LAO KO LA
180A ; Extender # Po MONGOLIAN NIRUGU
1843 ; Extender # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN
1AA7 ; Extender # Lm TAI THAM SIGN MAI YAMOK
1C36 ; Extender # Mn LEPCHA SIGN RAN
@ -771,27 +843,33 @@ A60C ; Extender # Lm VAI SYLLABLE LENGTHENER
A9CF ; Extender # Lm JAVANESE PANGRANGKEP
AA70 ; Extender # Lm MYANMAR MODIFIER LETTER KHAMTI REDUPLICATION
AADD ; Extender # Lm TAI VIET SYMBOL SAM
AAF3..AAF4 ; Extender # Lm [2] MEETEI MAYEK SYLLABLE REPETITION MARK..MEETEI MAYEK WORD REPETITION MARK
FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
# Total code points: 28
# Total code points: 31
# ================================================
00AA ; Other_Lowercase # Lo FEMININE ORDINAL INDICATOR
00BA ; Other_Lowercase # Lo MASCULINE ORDINAL INDICATOR
02B0..02B8 ; Other_Lowercase # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y
02C0..02C1 ; Other_Lowercase # Lm [2] MODIFIER LETTER GLOTTAL STOP..MODIFIER LETTER REVERSED GLOTTAL STOP
02E0..02E4 ; Other_Lowercase # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
0345 ; Other_Lowercase # Mn COMBINING GREEK YPOGEGRAMMENI
037A ; Other_Lowercase # Lm GREEK YPOGEGRAMMENI
1D2C..1D61 ; Other_Lowercase # Lm [54] MODIFIER LETTER CAPITAL A..MODIFIER LETTER SMALL CHI
1D2C..1D6A ; Other_Lowercase # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI
1D78 ; Other_Lowercase # Lm MODIFIER LETTER CYRILLIC EN
1D9B..1DBF ; Other_Lowercase # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA
2090..2094 ; Other_Lowercase # Lm [5] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER SCHWA
2071 ; Other_Lowercase # Lm SUPERSCRIPT LATIN SMALL LETTER I
207F ; Other_Lowercase # Lm SUPERSCRIPT LATIN SMALL LETTER N
2090..209C ; Other_Lowercase # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T
2170..217F ; Other_Lowercase # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND
24D0..24E9 ; Other_Lowercase # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z
2C7D ; Other_Lowercase # Lm MODIFIER LETTER CAPITAL V
2C7C..2C7D ; Other_Lowercase # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V
A770 ; Other_Lowercase # Lm MODIFIER LETTER US
A7F8..A7F9 ; Other_Lowercase # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
# Total code points: 159
# Total code points: 183
# ================================================
@ -838,11 +916,12 @@ FFFFE..FFFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-FFFFE>..<noncha
0DCF ; Other_Grapheme_Extend # Mc SINHALA VOWEL SIGN AELA-PILLA
0DDF ; Other_Grapheme_Extend # Mc SINHALA VOWEL SIGN GAYANUKITTA
200C..200D ; Other_Grapheme_Extend # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH 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
1D165 ; Other_Grapheme_Extend # Mc MUSICAL SYMBOL COMBINING STEM
1D16E..1D172 ; Other_Grapheme_Extend # Mc [5] MUSICAL SYMBOL COMBINING FLAG-1..MUSICAL SYMBOL COMBINING FLAG-5
# Total code points: 23
# Total code points: 25
# ================================================
@ -868,7 +947,7 @@ FF9E..FF9F ; Other_Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND
# ================================================
3400..4DB5 ; Unified_Ideograph # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4E00..9FCB ; Unified_Ideograph # Lo [20940] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCB
4E00..9FCC ; Unified_Ideograph # Lo [20941] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCC
FA0E..FA0F ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA0E..CJK COMPATIBILITY IDEOGRAPH-FA0F
FA11 ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA11
FA13..FA14 ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA13..CJK COMPATIBILITY IDEOGRAPH-FA14
@ -880,12 +959,13 @@ FA27..FA29 ; Unified_Ideograph # Lo [3] CJK COMPATIBILITY IDEOGRAPH-FA27..C
2A700..2B734 ; Unified_Ideograph # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
2B740..2B81D ; Unified_Ideograph # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
# Total code points: 74616
# Total code points: 74617
# ================================================
034F ; Other_Default_Ignorable_Code_Point # Mn COMBINING GRAPHEME JOINER
115F..1160 ; Other_Default_Ignorable_Code_Point # Lo [2] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG FILLER
17B4..17B5 ; Other_Default_Ignorable_Code_Point # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
2065..2069 ; Other_Default_Ignorable_Code_Point # Cn [5] <reserved-2065>..<reserved-2069>
3164 ; Other_Default_Ignorable_Code_Point # Lo HANGUL FILLER
FFA0 ; Other_Default_Ignorable_Code_Point # Lo HALFWIDTH HANGUL FILLER
@ -895,7 +975,7 @@ E0002..E001F ; Other_Default_Ignorable_Code_Point # Cn [30] <reserved-E0002>..
E0080..E00FF ; Other_Default_Ignorable_Code_Point # Cn [128] <reserved-E0080>..<reserved-E00FF>
E01F0..E0FFF ; Other_Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
# Total code points: 3778
# Total code points: 3780
# ================================================
@ -923,7 +1003,7 @@ E0020..E007F ; Deprecated # Cf [96] TAG SPACE..CANCEL TAG
03F3 ; Soft_Dotted # L& GREEK LETTER YOT
0456 ; Soft_Dotted # L& CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
0458 ; Soft_Dotted # L& CYRILLIC SMALL LETTER JE
1D62 ; Soft_Dotted # L& LATIN SUBSCRIPT SMALL LETTER I
1D62 ; Soft_Dotted # Lm LATIN SUBSCRIPT SMALL LETTER I
1D96 ; Soft_Dotted # L& LATIN SMALL LETTER I WITH RETROFLEX HOOK
1DA4 ; Soft_Dotted # Lm MODIFIER LETTER SMALL I WITH STROKE
1DA8 ; Soft_Dotted # Lm MODIFIER LETTER SMALL J WITH CROSSED-TAIL
@ -931,7 +1011,7 @@ E0020..E007F ; Deprecated # Cf [96] TAG SPACE..CANCEL TAG
1ECB ; Soft_Dotted # L& LATIN SMALL LETTER I WITH DOT BELOW
2071 ; Soft_Dotted # Lm SUPERSCRIPT LATIN SMALL LETTER I
2148..2149 ; Soft_Dotted # L& [2] DOUBLE-STRUCK ITALIC SMALL I..DOUBLE-STRUCK ITALIC SMALL J
2C7C ; Soft_Dotted # L& LATIN SUBSCRIPT SMALL LETTER J
2C7C ; Soft_Dotted # Lm LATIN SUBSCRIPT SMALL LETTER J
1D422..1D423 ; Soft_Dotted # L& [2] MATHEMATICAL BOLD SMALL I..MATHEMATICAL BOLD SMALL J
1D456..1D457 ; Soft_Dotted # L& [2] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL ITALIC SMALL J
1D48A..1D48B ; Soft_Dotted # L& [2] MATHEMATICAL BOLD ITALIC SMALL I..MATHEMATICAL BOLD ITALIC SMALL J
@ -1014,6 +1094,7 @@ A8CE..A8CF ; STerm # Po [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA
A92F ; STerm # Po KAYAH LI SIGN SHYA
A9C8..A9C9 ; STerm # Po [2] JAVANESE PADA LINGSA..JAVANESE PADA LUNGSI
AA5D..AA5F ; STerm # Po [3] CHAM PUNCTUATION DANDA..CHAM PUNCTUATION TRIPLE DANDA
AAF0..AAF1 ; STerm # Po [2] MEETEI MAYEK CHEIKHAN..MEETEI MAYEK AHANG KHUDAM
ABEB ; STerm # Po MEETEI MAYEK CHEIKHEI
FE52 ; STerm # Po SMALL FULL STOP
FE56..FE57 ; STerm # Po [2] SMALL QUESTION MARK..SMALL EXCLAMATION MARK
@ -1024,8 +1105,10 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP
10A56..10A57 ; STerm # Po [2] KHAROSHTHI PUNCTUATION DANDA..KHAROSHTHI PUNCTUATION DOUBLE DANDA
11047..11048 ; STerm # Po [2] BRAHMI DANDA..BRAHMI DOUBLE DANDA
110BE..110C1 ; STerm # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA
11141..11143 ; STerm # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK
111C5..111C6 ; STerm # Po [2] SHARADA DANDA..SHARADA DOUBLE DANDA
# Total code points: 76
# Total code points: 83
# ================================================
@ -1072,14 +1155,15 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S
007E ; Pattern_Syntax # Sm TILDE
00A1 ; Pattern_Syntax # Po INVERTED EXCLAMATION MARK
00A2..00A5 ; Pattern_Syntax # Sc [4] CENT SIGN..YEN SIGN
00A6..00A7 ; Pattern_Syntax # So [2] BROKEN BAR..SECTION SIGN
00A6 ; Pattern_Syntax # So BROKEN BAR
00A7 ; Pattern_Syntax # Po SECTION SIGN
00A9 ; Pattern_Syntax # So COPYRIGHT SIGN
00AB ; Pattern_Syntax # Pi LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
00AC ; Pattern_Syntax # Sm NOT SIGN
00AE ; Pattern_Syntax # So REGISTERED SIGN
00B0 ; Pattern_Syntax # So DEGREE SIGN
00B1 ; Pattern_Syntax # Sm PLUS-MINUS SIGN
00B6 ; Pattern_Syntax # So PILCROW SIGN
00B6 ; Pattern_Syntax # Po PILCROW SIGN
00BB ; Pattern_Syntax # Pf RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
00BF ; Pattern_Syntax # Po INVERTED QUESTION MARK
00D7 ; Pattern_Syntax # Sm MULTIPLICATION SIGN
@ -1173,11 +1257,7 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S
27C0..27C4 ; Pattern_Syntax # Sm [5] THREE DIMENSIONAL ANGLE..OPEN SUPERSET
27C5 ; Pattern_Syntax # Ps LEFT S-SHAPED BAG DELIMITER
27C6 ; Pattern_Syntax # Pe RIGHT S-SHAPED BAG DELIMITER
27C7..27CA ; Pattern_Syntax # Sm [4] OR WITH DOT INSIDE..VERTICAL BAR WITH HORIZONTAL STROKE
27CB ; Pattern_Syntax # Cn <reserved-27CB>
27CC ; Pattern_Syntax # Sm LONG DIVISION
27CD ; Pattern_Syntax # Cn <reserved-27CD>
27CE..27E5 ; Pattern_Syntax # Sm [24] SQUARED LOGICAL AND..WHITE SQUARE WITH RIGHTWARDS TICK
27C7..27E5 ; Pattern_Syntax # Sm [31] OR WITH DOT INSIDE..WHITE SQUARE WITH RIGHTWARDS TICK
27E6 ; Pattern_Syntax # Ps MATHEMATICAL LEFT WHITE SQUARE BRACKET
27E7 ; Pattern_Syntax # Pe MATHEMATICAL RIGHT WHITE SQUARE BRACKET
27E8 ; Pattern_Syntax # Ps MATHEMATICAL LEFT ANGLE BRACKET
@ -1260,8 +1340,9 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S
2E29 ; Pattern_Syntax # Pe RIGHT DOUBLE PARENTHESIS
2E2A..2E2E ; Pattern_Syntax # Po [5] TWO DOTS OVER ONE DOT PUNCTUATION..REVERSED QUESTION MARK
2E2F ; Pattern_Syntax # Lm VERTICAL TILDE
2E30..2E31 ; Pattern_Syntax # Po [2] RING POINT..WORD SEPARATOR MIDDLE DOT
2E32..2E7F ; Pattern_Syntax # Cn [78] <reserved-2E32>..<reserved-2E7F>
2E30..2E39 ; Pattern_Syntax # Po [10] RING POINT..TOP HALF SECTION SIGN
2E3A..2E3B ; Pattern_Syntax # Pd [2] TWO-EM DASH..THREE-EM DASH
2E3C..2E7F ; Pattern_Syntax # Cn [68] <reserved-2E3C>..<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

1614
jdk/test/java/lang/Character/PropertyValueAliases.txt
View File

File diff suppressed because it is too large Load Diff

248
jdk/test/java/lang/Character/Scripts.txt
View File

@ -1,8 +1,8 @@
# Scripts-6.0.0.txt
# Date: 2010-08-19, 00:48:47 GMT [MD]
# Scripts-6.1.0.txt
# Date: 2011-11-27, 05:10:50 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2010 Unicode, Inc.
# Copyright (c) 1991-2011 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
@ -47,7 +47,8 @@
00A0 ; Common # Zs NO-BREAK SPACE
00A1 ; Common # Po INVERTED EXCLAMATION MARK
00A2..00A5 ; Common # Sc [4] CENT SIGN..YEN SIGN
00A6..00A7 ; Common # So [2] BROKEN BAR..SECTION SIGN
00A6 ; Common # So BROKEN BAR
00A7 ; Common # Po SECTION SIGN
00A8 ; Common # Sk DIAERESIS
00A9 ; Common # So COPYRIGHT SIGN
00AB ; Common # Pi LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
@ -60,8 +61,7 @@
00B2..00B3 ; Common # No [2] SUPERSCRIPT TWO..SUPERSCRIPT THREE
00B4 ; Common # Sk ACUTE ACCENT
00B5 ; Common # L& MICRO SIGN
00B6 ; Common # So PILCROW SIGN
00B7 ; Common # Po MIDDLE DOT
00B6..00B7 ; Common # Po [2] PILCROW SIGN..MIDDLE DOT
00B8 ; Common # Sk CEDILLA
00B9 ; Common # No SUPERSCRIPT ONE
00BB ; Common # Pf RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
@ -90,7 +90,6 @@
0660..0669 ; Common # Nd [10] ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE
06DD ; Common # Cf ARABIC END OF AYAH
0964..0965 ; Common # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA
0970 ; Common # Po DEVANAGARI ABBREVIATION SIGN
0E3F ; Common # Sc THAI CURRENCY SYMBOL BAHT
0FD5..0FD8 ; Common # So [4] RIGHT-FACING SVASTI SIGN..LEFT-FACING SVASTI SIGN WITH DOTS
10FB ; Common # Po GEORGIAN PARAGRAPH SEPARATOR
@ -102,7 +101,8 @@
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 ; Common # Mc VEDIC SIGN ARDHAVISARGA
1CF2..1CF3 ; Common # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
1CF5..1CF6 ; Common # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA
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
@ -247,9 +247,7 @@
27C0..27C4 ; Common # Sm [5] THREE DIMENSIONAL ANGLE..OPEN SUPERSET
27C5 ; Common # Ps LEFT S-SHAPED BAG DELIMITER
27C6 ; Common # Pe RIGHT S-SHAPED BAG DELIMITER
27C7..27CA ; Common # Sm [4] OR WITH DOT INSIDE..VERTICAL BAR WITH HORIZONTAL STROKE
27CC ; Common # Sm LONG DIVISION
27CE..27E5 ; Common # Sm [24] SQUARED LOGICAL AND..WHITE SQUARE WITH RIGHTWARDS TICK
27C7..27E5 ; Common # Sm [31] OR WITH DOT INSIDE..WHITE SQUARE WITH RIGHTWARDS TICK
27E6 ; Common # Ps MATHEMATICAL LEFT WHITE SQUARE BRACKET
27E7 ; Common # Pe MATHEMATICAL RIGHT WHITE SQUARE BRACKET
27E8 ; Common # Ps MATHEMATICAL LEFT ANGLE BRACKET
@ -329,7 +327,8 @@
2E29 ; Common # Pe RIGHT DOUBLE PARENTHESIS
2E2A..2E2E ; Common # Po [5] TWO DOTS OVER ONE DOT PUNCTUATION..REVERSED QUESTION MARK
2E2F ; Common # Lm VERTICAL TILDE
2E30..2E31 ; Common # Po [2] RING POINT..WORD SEPARATOR MIDDLE DOT
2E30..2E39 ; Common # Po [10] RING POINT..TOP HALF SECTION SIGN
2E3A..2E3B ; Common # Pd [2] TWO-EM DASH..THREE-EM DASH
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
@ -373,7 +372,9 @@
3196..319F ; Common # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK
31C0..31E3 ; Common # So [36] CJK STROKE T..CJK STROKE Q
3220..3229 ; Common # No [10] PARENTHESIZED IDEOGRAPH ONE..PARENTHESIZED IDEOGRAPH TEN
322A..3250 ; Common # So [39] PARENTHESIZED IDEOGRAPH MOON..PARTNERSHIP SIGN
322A..3247 ; Common # So [30] PARENTHESIZED IDEOGRAPH MOON..CIRCLED IDEOGRAPH KOTO
3248..324F ; Common # No [8] CIRCLED NUMBER TEN ON BLACK SQUARE..CIRCLED NUMBER EIGHTY ON BLACK SQUARE
3250 ; Common # So PARTNERSHIP SIGN
3251..325F ; Common # No [15] CIRCLED NUMBER TWENTY ONE..CIRCLED NUMBER THIRTY FIVE
327F ; Common # So KOREAN STANDARD SYMBOL
3280..3289 ; Common # No [10] CIRCLED IDEOGRAPH ONE..CIRCLED IDEOGRAPH TEN
@ -481,8 +482,7 @@ FFE9..FFEC ; Common # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS
FFED..FFEE ; Common # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE
FFF9..FFFB ; Common # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR
FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER
10100..10101 ; Common # Po [2] AEGEAN WORD SEPARATOR LINE..AEGEAN WORD SEPARATOR DOT
10102 ; Common # So AEGEAN CHECK MARK
10100..10102 ; Common # Po [3] AEGEAN WORD SEPARATOR LINE..AEGEAN CHECK MARK
10107..10133 ; Common # No [45] AEGEAN NUMBER ONE..AEGEAN NUMBER NINETY THOUSAND
10137..1013F ; Common # So [9] AEGEAN WEIGHT BASE UNIT..AEGEAN MEASURE THIRD SUBUNIT
10190..1019B ; Common # So [12] ROMAN SEXTANS SIGN..ROMAN CENTURIAL SIGN
@ -548,7 +548,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1F0D1..1F0DF ; Common # So [15] PLAYING CARD ACE OF CLUBS..PLAYING CARD WHITE JOKER
1F100..1F10A ; Common # No [11] DIGIT ZERO FULL STOP..DIGIT NINE COMMA
1F110..1F12E ; Common # So [31] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED WZ
1F130..1F169 ; Common # So [58] SQUARED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
1F130..1F16B ; Common # So [60] SQUARED LATIN CAPITAL LETTER A..RAISED MD SIGN
1F170..1F19A ; Common # So [43] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VS
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
@ -567,33 +567,23 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1F442..1F4F7 ; Common # So [182] EAR..CAMERA
1F4F9..1F4FC ; Common # So [4] VIDEO CAMERA..VIDEOCASSETTE
1F500..1F53D ; Common # So [62] TWISTED RIGHTWARDS ARROWS..DOWN-POINTING SMALL RED TRIANGLE
1F540..1F543 ; Common # So [4] CIRCLED CROSS POMMEE..NOTCHED LEFT SEMICIRCLE WITH THREE DOTS
1F550..1F567 ; Common # So [24] CLOCK FACE ONE OCLOCK..CLOCK FACE TWELVE-THIRTY
1F5FB..1F5FF ; Common # So [5] MOUNT FUJI..MOYAI
1F601..1F610 ; Common # So [16] GRINNING FACE WITH SMILING EYES..NEUTRAL FACE
1F612..1F614 ; Common # So [3] UNAMUSED FACE..PENSIVE FACE
1F616 ; Common # So CONFOUNDED FACE
1F618 ; Common # So FACE THROWING A KISS
1F61A ; Common # So KISSING FACE WITH CLOSED EYES
1F61C..1F61E ; Common # So [3] FACE WITH STUCK-OUT TONGUE AND WINKING EYE..DISAPPOINTED FACE
1F620..1F625 ; Common # So [6] ANGRY FACE..DISAPPOINTED BUT RELIEVED FACE
1F628..1F62B ; Common # So [4] FEARFUL FACE..TIRED FACE
1F62D ; Common # So LOUDLY CRYING FACE
1F630..1F633 ; Common # So [4] FACE WITH OPEN MOUTH AND COLD SWEAT..FLUSHED FACE
1F635..1F640 ; Common # So [12] DIZZY FACE..WEARY CAT FACE
1F5FB..1F640 ; Common # So [70] MOUNT FUJI..WEARY CAT FACE
1F645..1F64F ; Common # So [11] FACE WITH NO GOOD GESTURE..PERSON WITH FOLDED HANDS
1F680..1F6C5 ; Common # So [70] ROCKET..LEFT LUGGAGE
1F700..1F773 ; Common # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
E0001 ; Common # Cf LANGUAGE TAG
E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
# Total code points: 6379
# Total code points: 6412
# ================================================
0041..005A ; Latin # L& [26] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER Z
0061..007A ; Latin # L& [26] LATIN SMALL LETTER A..LATIN SMALL LETTER Z
00AA ; Latin # L& FEMININE ORDINAL INDICATOR
00BA ; Latin # L& MASCULINE ORDINAL INDICATOR
00AA ; Latin # Lo FEMININE ORDINAL INDICATOR
00BA ; Latin # Lo MASCULINE ORDINAL INDICATOR
00C0..00D6 ; Latin # L& [23] LATIN CAPITAL LETTER A WITH GRAVE..LATIN CAPITAL LETTER O WITH DIAERESIS
00D8..00F6 ; Latin # L& [31] LATIN CAPITAL LETTER O WITH STROKE..LATIN SMALL LETTER O WITH DIAERESIS
00F8..01BA ; Latin # L& [195] LATIN SMALL LETTER O WITH STROKE..LATIN SMALL LETTER EZH WITH TAIL
@ -607,7 +597,7 @@ E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
02E0..02E4 ; Latin # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
1D00..1D25 ; Latin # L& [38] LATIN LETTER SMALL CAPITAL A..LATIN LETTER AIN
1D2C..1D5C ; Latin # Lm [49] MODIFIER LETTER CAPITAL A..MODIFIER LETTER SMALL AIN
1D62..1D65 ; Latin # L& [4] LATIN SUBSCRIPT SMALL LETTER I..LATIN SUBSCRIPT SMALL LETTER V
1D62..1D65 ; Latin # Lm [4] LATIN SUBSCRIPT SMALL LETTER I..LATIN SUBSCRIPT SMALL LETTER V
1D6B..1D77 ; Latin # L& [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G
1D79..1D9A ; Latin # L& [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK
1D9B..1DBE ; Latin # Lm [36] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL EZH
@ -621,22 +611,23 @@ E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
2160..2182 ; Latin # Nl [35] ROMAN NUMERAL ONE..ROMAN NUMERAL TEN THOUSAND
2183..2184 ; Latin # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C
2185..2188 ; Latin # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND
2C60..2C7C ; Latin # L& [29] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN SUBSCRIPT SMALL LETTER J
2C7D ; Latin # Lm MODIFIER LETTER CAPITAL V
2C60..2C7B ; Latin # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E
2C7C..2C7D ; Latin # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V
2C7E..2C7F ; Latin # L& [2] LATIN CAPITAL LETTER S WITH SWASH TAIL..LATIN CAPITAL LETTER Z WITH SWASH TAIL
A722..A76F ; Latin # L& [78] LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF..LATIN SMALL LETTER CON
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
A790..A791 ; Latin # L& [2] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER N WITH DESCENDER
A7A0..A7A9 ; Latin # L& [10] LATIN CAPITAL LETTER G WITH OBLIQUE STROKE..LATIN SMALL LETTER S WITH OBLIQUE STROKE
A790..A793 ; Latin # L& [4] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER C WITH BAR
A7A0..A7AA ; Latin # L& [11] LATIN CAPITAL LETTER G WITH OBLIQUE STROKE..LATIN CAPITAL LETTER H WITH HOOK
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
A7FB..A7FF ; Latin # Lo [5] LATIN EPIGRAPHIC LETTER REVERSED F..LATIN EPIGRAPHIC LETTER ARCHAIC M
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: 1267
# Total code points: 1272
# ================================================
@ -656,7 +647,7 @@ FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN
03F7..03FF ; Greek # L& [9] GREEK CAPITAL LETTER SHO..GREEK CAPITAL REVERSED DOTTED LUNATE SIGMA SYMBOL
1D26..1D2A ; Greek # L& [5] GREEK LETTER SMALL CAPITAL GAMMA..GREEK LETTER SMALL CAPITAL PSI
1D5D..1D61 ; Greek # Lm [5] MODIFIER LETTER SMALL BETA..MODIFIER LETTER SMALL CHI
1D66..1D6A ; Greek # L& [5] GREEK SUBSCRIPT SMALL LETTER BETA..GREEK SUBSCRIPT SMALL LETTER CHI
1D66..1D6A ; Greek # Lm [5] GREEK SUBSCRIPT SMALL LETTER BETA..GREEK SUBSCRIPT SMALL LETTER CHI
1DBF ; Greek # Lm MODIFIER LETTER SMALL THETA
1F00..1F15 ; Greek # L& [22] GREEK SMALL LETTER ALPHA WITH PSILI..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA
1F18..1F1D ; Greek # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA
@ -710,12 +701,13 @@ A66E ; Cyrillic # Lo CYRILLIC LETTER MULTIOCULAR O
A66F ; Cyrillic # Mn COMBINING CYRILLIC VZMET
A670..A672 ; Cyrillic # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN
A673 ; Cyrillic # Po SLAVONIC ASTERISK
A67C..A67D ; Cyrillic # Mn [2] COMBINING CYRILLIC KAVYKA..COMBINING CYRILLIC PAYEROK
A674..A67D ; Cyrillic # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK
A67E ; Cyrillic # Po CYRILLIC KAVYKA
A67F ; Cyrillic # Lm CYRILLIC PAYEROK
A680..A697 ; Cyrillic # L& [24] CYRILLIC CAPITAL LETTER DWE..CYRILLIC SMALL LETTER SHWE
A69F ; Cyrillic # Mn COMBINING CYRILLIC LETTER IOTIFIED E
# Total code points: 408
# Total code points: 417
# ================================================
@ -724,9 +716,10 @@ A680..A697 ; Cyrillic # L& [24] CYRILLIC CAPITAL LETTER DWE..CYRILLIC SMALL
055A..055F ; Armenian # Po [6] ARMENIAN APOSTROPHE..ARMENIAN ABBREVIATION MARK
0561..0587 ; Armenian # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN
058A ; Armenian # Pd ARMENIAN HYPHEN
058F ; Armenian # Sc ARMENIAN DRAM SIGN
FB13..FB17 ; Armenian # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH
# Total code points: 90
# Total code points: 91
# ================================================
@ -757,7 +750,7 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU
# ================================================
0600..0603 ; Arabic # Cf [4] ARABIC NUMBER SIGN..ARABIC SIGN SAFHA
0600..0604 ; Arabic # Cf [5] ARABIC NUMBER SIGN..ARABIC SIGN SAMVAT
0606..0608 ; Arabic # Sm [3] ARABIC-INDIC CUBE ROOT..ARABIC RAY
0609..060A ; Arabic # Po [2] ARABIC-INDIC PER MILLE SIGN..ARABIC-INDIC PER TEN THOUSAND SIGN
060B ; Arabic # Sc AFGHANI SIGN
@ -786,6 +779,9 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU
06FD..06FE ; Arabic # So [2] ARABIC SIGN SINDHI AMPERSAND..ARABIC SIGN SINDHI POSTPOSITION MEN
06FF ; Arabic # Lo ARABIC LETTER HEH WITH INVERTED V
0750..077F ; Arabic # Lo [48] ARABIC LETTER BEH WITH THREE DOTS HORIZONTALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS ABOVE
08A0 ; Arabic # Lo ARABIC LETTER BEH WITH SMALL V BELOW
08A2..08AC ; Arabic # Lo [11] ARABIC LETTER JEEM WITH TWO DOTS ABOVE..ARABIC LETTER ROHINGYA YEH
08E4..08FE ; Arabic # Mn [27] ARABIC CURLY FATHA..ARABIC DAMMA WITH DOT
FB50..FBB1 ; Arabic # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM
FBB2..FBC1 ; Arabic # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW
FBD3..FD3D ; Arabic # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM
@ -796,8 +792,42 @@ FDFC ; Arabic # Sc RIAL SIGN
FE70..FE74 ; Arabic # Lo [5] ARABIC FATHATAN ISOLATED FORM..ARABIC KASRATAN ISOLATED FORM
FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM
10E60..10E7E ; Arabic # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS
1EE00..1EE03 ; Arabic # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL
1EE05..1EE1F ; Arabic # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF
1EE21..1EE22 ; Arabic # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM
1EE24 ; Arabic # Lo ARABIC MATHEMATICAL INITIAL HEH
1EE27 ; Arabic # Lo ARABIC MATHEMATICAL INITIAL HAH
1EE29..1EE32 ; Arabic # Lo [10] ARABIC MATHEMATICAL INITIAL YEH..ARABIC MATHEMATICAL INITIAL QAF
1EE34..1EE37 ; Arabic # Lo [4] ARABIC MATHEMATICAL INITIAL SHEEN..ARABIC MATHEMATICAL INITIAL KHAH
1EE39 ; Arabic # Lo ARABIC MATHEMATICAL INITIAL DAD
1EE3B ; Arabic # Lo ARABIC MATHEMATICAL INITIAL GHAIN
1EE42 ; Arabic # Lo ARABIC MATHEMATICAL TAILED JEEM
1EE47 ; Arabic # Lo ARABIC MATHEMATICAL TAILED HAH
1EE49 ; Arabic # Lo ARABIC MATHEMATICAL TAILED YEH
1EE4B ; Arabic # Lo ARABIC MATHEMATICAL TAILED LAM
1EE4D..1EE4F ; Arabic # Lo [3] ARABIC MATHEMATICAL TAILED NOON..ARABIC MATHEMATICAL TAILED AIN
1EE51..1EE52 ; Arabic # Lo [2] ARABIC MATHEMATICAL TAILED SAD..ARABIC MATHEMATICAL TAILED QAF
1EE54 ; Arabic # Lo ARABIC MATHEMATICAL TAILED SHEEN
1EE57 ; Arabic # Lo ARABIC MATHEMATICAL TAILED KHAH
1EE59 ; Arabic # Lo ARABIC MATHEMATICAL TAILED DAD
1EE5B ; Arabic # Lo ARABIC MATHEMATICAL TAILED GHAIN
1EE5D ; Arabic # Lo ARABIC MATHEMATICAL TAILED DOTLESS NOON
1EE5F ; Arabic # Lo ARABIC MATHEMATICAL TAILED DOTLESS QAF
1EE61..1EE62 ; Arabic # Lo [2] ARABIC MATHEMATICAL STRETCHED BEH..ARABIC MATHEMATICAL STRETCHED JEEM
1EE64 ; Arabic # Lo ARABIC MATHEMATICAL STRETCHED HEH
1EE67..1EE6A ; Arabic # Lo [4] ARABIC MATHEMATICAL STRETCHED HAH..ARABIC MATHEMATICAL STRETCHED KAF
1EE6C..1EE72 ; Arabic # Lo [7] ARABIC MATHEMATICAL STRETCHED MEEM..ARABIC MATHEMATICAL STRETCHED QAF
1EE74..1EE77 ; Arabic # Lo [4] ARABIC MATHEMATICAL STRETCHED SHEEN..ARABIC MATHEMATICAL STRETCHED KHAH
1EE79..1EE7C ; Arabic # Lo [4] ARABIC MATHEMATICAL STRETCHED DAD..ARABIC MATHEMATICAL STRETCHED DOTLESS BEH
1EE7E ; Arabic # Lo ARABIC MATHEMATICAL STRETCHED DOTLESS FEH
1EE80..1EE89 ; Arabic # Lo [10] ARABIC MATHEMATICAL LOOPED ALEF..ARABIC MATHEMATICAL LOOPED YEH
1EE8B..1EE9B ; Arabic # Lo [17] ARABIC MATHEMATICAL LOOPED LAM..ARABIC MATHEMATICAL LOOPED GHAIN
1EEA1..1EEA3 ; Arabic # Lo [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL
1EEA5..1EEA9 ; Arabic # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH
1EEAB..1EEBB ; Arabic # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
1EEF0..1EEF1 ; Arabic # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL
# Total code points: 1051
# Total code points: 1234
# ================================================
@ -838,6 +868,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
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
0970 ; Devanagari # Po DEVANAGARI ABBREVIATION SIGN
0971 ; Devanagari # Lm DEVANAGARI SIGN HIGH SPACING DOT
0972..0977 ; Devanagari # Lo [6] DEVANAGARI LETTER CANDRA A..DEVANAGARI LETTER UUE
0979..097F ; Devanagari # Lo [7] DEVANAGARI LETTER ZHA..DEVANAGARI LETTER BBA
@ -846,7 +877,7 @@ A8F2..A8F7 ; Devanagari # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVAN
A8F8..A8FA ; Devanagari # Po [3] DEVANAGARI SIGN PUSHPIKA..DEVANAGARI CARET
A8FB ; Devanagari # Lo DEVANAGARI HEADSTROKE
# Total code points: 150
# Total code points: 151
# ================================================
@ -927,9 +958,10 @@ A8FB ; Devanagari # Lo DEVANAGARI HEADSTROKE
0AE0..0AE1 ; Gujarati # Lo [2] GUJARATI LETTER VOCALIC RR..GUJARATI LETTER VOCALIC LL
0AE2..0AE3 ; Gujarati # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL
0AE6..0AEF ; Gujarati # Nd [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE
0AF0 ; Gujarati # Po GUJARATI ABBREVIATION SIGN
0AF1 ; Gujarati # Sc GUJARATI RUPEE SIGN
# Total code points: 83
# Total code points: 84
# ================================================
@ -1119,16 +1151,18 @@ A8FB ; Devanagari # Lo DEVANAGARI HEADSTROKE
0EC6 ; Lao # Lm LAO KO LA
0EC8..0ECD ; Lao # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA
0ED0..0ED9 ; Lao # Nd [10] LAO DIGIT ZERO..LAO DIGIT NINE
0EDC..0EDD ; Lao # Lo [2] LAO HO NO..LAO HO MO
0EDC..0EDF ; Lao # Lo [4] LAO HO NO..LAO LETTER KHMU NYO
# Total code points: 65
# Total code points: 67
# ================================================
0F00 ; Tibetan # Lo TIBETAN SYLLABLE OM
0F01..0F03 ; Tibetan # So [3] TIBETAN MARK GTER YIG MGO TRUNCATED A..TIBETAN MARK GTER YIG MGO -UM GTER TSHEG MA
0F04..0F12 ; Tibetan # Po [15] TIBETAN MARK INITIAL YIG MGO MDUN MA..TIBETAN MARK RGYA GRAM SHAD
0F13..0F17 ; Tibetan # So [5] TIBETAN MARK CARET -DZUD RTAGS ME LONG CAN..TIBETAN ASTROLOGICAL SIGN SGRA GCAN -CHAR RTAGS
0F13 ; Tibetan # So TIBETAN MARK CARET -DZUD RTAGS ME LONG CAN
0F14 ; Tibetan # Po TIBETAN MARK GTER TSHEG
0F15..0F17 ; Tibetan # So [3] TIBETAN LOGOTYPE SIGN CHAD RTAGS..TIBETAN ASTROLOGICAL SIGN SGRA GCAN -CHAR RTAGS
0F18..0F19 ; Tibetan # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS
0F1A..0F1F ; Tibetan # So [6] TIBETAN SIGN RDEL DKAR GCIG..TIBETAN SIGN RDEL DKAR RDEL NAG
0F20..0F29 ; Tibetan # Nd [10] TIBETAN DIGIT ZERO..TIBETAN DIGIT NINE
@ -1212,16 +1246,21 @@ AA7B ; Myanmar # Mc MYANMAR SIGN PAO KAREN TONE
# ================================================
10A0..10C5 ; Georgian # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE
10C7 ; Georgian # L& GEORGIAN CAPITAL LETTER YN
10CD ; Georgian # L& GEORGIAN CAPITAL LETTER AEN
10D0..10FA ; Georgian # Lo [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN
10FC ; Georgian # Lm MODIFIER LETTER GEORGIAN NAR
10FD..10FF ; Georgian # Lo [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN
2D00..2D25 ; Georgian # L& [38] GEORGIAN SMALL LETTER AN..GEORGIAN SMALL LETTER HOE
2D27 ; Georgian # L& GEORGIAN SMALL LETTER YN
2D2D ; Georgian # L& GEORGIAN SMALL LETTER AEN
# Total code points: 120
# Total code points: 127
# ================================================
1100..11FF ; Hangul # Lo [256] HANGUL CHOSEONG KIYEOK..HANGUL JONGSEONG SSANGNIEUN
302E..302F ; Hangul # Mn [2] HANGUL SINGLE DOT TONE MARK..HANGUL DOUBLE DOT TONE MARK
302E..302F ; Hangul # Mc [2] HANGUL SINGLE DOT TONE MARK..HANGUL DOUBLE DOT TONE MARK
3131..318E ; Hangul # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE
3200..321E ; Hangul # So [31] PARENTHESIZED HANGUL KIYEOK..PARENTHESIZED KOREAN CHARACTER O HU
3260..327E ; Hangul # So [31] CIRCLED HANGUL KIYEOK..CIRCLED HANGUL IEUNG U
@ -1256,8 +1295,7 @@ FFDA..FFDC ; Hangul # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL L
1312..1315 ; Ethiopic # Lo [4] ETHIOPIC SYLLABLE GWI..ETHIOPIC SYLLABLE GWE
1318..135A ; Ethiopic # Lo [67] ETHIOPIC SYLLABLE GGA..ETHIOPIC SYLLABLE FYA
135D..135F ; Ethiopic # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK
1360 ; Ethiopic # So ETHIOPIC SECTION MARK
1361..1368 ; Ethiopic # Po [8] ETHIOPIC WORDSPACE..ETHIOPIC PARAGRAPH SEPARATOR
1360..1368 ; Ethiopic # Po [9] ETHIOPIC SECTION MARK..ETHIOPIC PARAGRAPH SEPARATOR
1369..137C ; Ethiopic # No [20] ETHIOPIC DIGIT ONE..ETHIOPIC NUMBER TEN THOUSAND
1380..138F ; Ethiopic # Lo [16] ETHIOPIC SYLLABLE SEBATBEIT MWA..ETHIOPIC SYLLABLE PWE
1390..1399 ; Ethiopic # So [10] ETHIOPIC TONAL MARK YIZET..ETHIOPIC TONAL MARK KURT
@ -1313,7 +1351,7 @@ AB28..AB2E ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE BBA..ETHIOPIC SYLLABLE BBO
# ================================================
1780..17B3 ; Khmer # Lo [52] KHMER LETTER KA..KHMER INDEPENDENT VOWEL QAU
17B4..17B5 ; Khmer # Cf [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
17B4..17B5 ; Khmer # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
17B6 ; Khmer # Mc KHMER VOWEL SIGN AA
17B7..17BD ; Khmer # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA
17BE..17C5 ; Khmer # Mc [8] KHMER VOWEL SIGN OE..KHMER VOWEL SIGN AU
@ -1393,16 +1431,15 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
3038..303A ; Han # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY
303B ; Han # Lm VERTICAL IDEOGRAPHIC ITERATION MARK
3400..4DB5 ; Han # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4E00..9FCB ; Han # Lo [20940] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCB
F900..FA2D ; Han # Lo [302] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA2D
FA30..FA6D ; Han # Lo [62] CJK COMPATIBILITY IDEOGRAPH-FA30..CJK COMPATIBILITY IDEOGRAPH-FA6D
4E00..9FCC ; Han # Lo [20941] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCC
F900..FA6D ; Han # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D
FA70..FAD9 ; Han # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9
20000..2A6D6 ; Han # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
2A700..2B734 ; Han # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
2B740..2B81D ; Han # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2F800..2FA1D ; Han # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 75960
# Total code points: 75963
# ================================================
@ -1447,6 +1484,7 @@ A490..A4C6 ; Yi # So [55] YI RADICAL QOT..YI RADICAL KE
1CD4..1CE0 ; Inherited # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA
1CE2..1CE8 ; Inherited # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL
1CED ; Inherited # Mn VEDIC SIGN TIRYAK
1CF4 ; Inherited # Mn VEDIC TONE CANDRA ABOVE
1DC0..1DE6 ; Inherited # Mn [39] COMBINING DOTTED GRAVE ACCENT..COMBINING LATIN SMALL LETTER Z
1DFC..1DFF ; Inherited # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
200C..200D ; Inherited # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER
@ -1466,7 +1504,7 @@ FE20..FE26 ; Inherited # Mn [7] 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: 523
# Total code points: 524
# ================================================
@ -1587,11 +1625,12 @@ E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-2
2CE5..2CEA ; Coptic # So [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA
2CEB..2CEE ; Coptic # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA
2CEF..2CF1 ; Coptic # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS
2CF2..2CF3 ; Coptic # L& [2] COPTIC CAPITAL LETTER BOHAIRIC KHEI..COPTIC SMALL LETTER BOHAIRIC KHEI
2CF9..2CFC ; Coptic # Po [4] COPTIC OLD NUBIAN FULL STOP..COPTIC OLD NUBIAN VERSE DIVIDER
2CFD ; Coptic # No COPTIC FRACTION ONE HALF
2CFE..2CFF ; Coptic # Po [2] COPTIC FULL STOP..COPTIC MORPHOLOGICAL DIVIDER
# Total code points: 135
# Total code points: 137
# ================================================
@ -1614,12 +1653,12 @@ E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-2
# ================================================
2D30..2D65 ; Tifinagh # Lo [54] TIFINAGH LETTER YA..TIFINAGH LETTER YAZZ
2D30..2D67 ; Tifinagh # Lo [56] TIFINAGH LETTER YA..TIFINAGH LETTER YO
2D6F ; Tifinagh # Lm TIFINAGH MODIFIER LETTER LABIALIZATION MARK
2D70 ; Tifinagh # Po TIFINAGH SEPARATOR MARK
2D7F ; Tifinagh # Mn TIFINAGH CONSONANT JOINER
# Total code points: 57
# Total code points: 59
# ================================================
@ -1729,10 +1768,14 @@ A874..A877 ; Phags_Pa # Po [4] PHAGS-PA SINGLE HEAD MARK..PHAGS-PA MARK DOU
1BA6..1BA7 ; Sundanese # Mc [2] SUNDANESE VOWEL SIGN PANAELAENG..SUNDANESE VOWEL SIGN PANOLONG
1BA8..1BA9 ; Sundanese # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG
1BAA ; Sundanese # Mc SUNDANESE SIGN PAMAAEH
1BAB ; Sundanese # Mn SUNDANESE SIGN VIRAMA
1BAC..1BAD ; Sundanese # Mc [2] SUNDANESE CONSONANT SIGN PASANGAN MA..SUNDANESE CONSONANT SIGN PASANGAN WA
1BAE..1BAF ; Sundanese # Lo [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA
1BB0..1BB9 ; Sundanese # Nd [10] SUNDANESE DIGIT ZERO..SUNDANESE DIGIT NINE
1BBA..1BBF ; Sundanese # Lo [6] SUNDANESE AVAGRAHA..SUNDANESE LETTER FINAL M
1CC0..1CC7 ; Sundanese # Po [8] SUNDANESE PUNCTUATION BINDU SURYA..SUNDANESE PUNCTUATION BINDU BA SATANGA
# Total code points: 55
# Total code points: 72
# ================================================
@ -1940,6 +1983,15 @@ A9DE..A9DF ; Javanese # Po [2] JAVANESE PADA TIRTA TUMETES..JAVANESE PADA I
# ================================================
AAE0..AAEA ; Meetei_Mayek # Lo [11] MEETEI MAYEK LETTER E..MEETEI MAYEK LETTER SSA
AAEB ; Meetei_Mayek # Mc MEETEI MAYEK VOWEL SIGN II
AAEC..AAED ; Meetei_Mayek # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI
AAEE..AAEF ; Meetei_Mayek # Mc [2] MEETEI MAYEK VOWEL SIGN AU..MEETEI MAYEK VOWEL SIGN AAU
AAF0..AAF1 ; Meetei_Mayek # Po [2] MEETEI MAYEK CHEIKHAN..MEETEI MAYEK AHANG KHUDAM
AAF2 ; Meetei_Mayek # Lo MEETEI MAYEK ANJI
AAF3..AAF4 ; Meetei_Mayek # Lm [2] MEETEI MAYEK SYLLABLE REPETITION MARK..MEETEI MAYEK WORD REPETITION MARK
AAF5 ; Meetei_Mayek # Mc MEETEI MAYEK VOWEL SIGN VISARGA
AAF6 ; Meetei_Mayek # Mn MEETEI MAYEK VIRAMA
ABC0..ABE2 ; Meetei_Mayek # Lo [35] MEETEI MAYEK LETTER KOK..MEETEI MAYEK LETTER I LONSUM
ABE3..ABE4 ; Meetei_Mayek # Mc [2] MEETEI MAYEK VOWEL SIGN ONAP..MEETEI MAYEK VOWEL SIGN INAP
ABE5 ; Meetei_Mayek # Mn MEETEI MAYEK VOWEL SIGN ANAP
@ -1951,7 +2003,7 @@ ABEC ; Meetei_Mayek # Mc MEETEI MAYEK LUM IYEK
ABED ; Meetei_Mayek # Mn MEETEI MAYEK APUN IYEK
ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE
# Total code points: 56
# Total code points: 79
# ================================================
@ -2040,4 +2092,74 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
# Total code points: 29
# ================================================
11100..11102 ; Chakma # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA
11103..11126 ; Chakma # Lo [36] CHAKMA LETTER AA..CHAKMA LETTER HAA
11127..1112B ; Chakma # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU
1112C ; Chakma # Mc CHAKMA VOWEL SIGN E
1112D..11134 ; Chakma # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA
11136..1113F ; Chakma # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE
11140..11143 ; Chakma # Po [4] CHAKMA SECTION MARK..CHAKMA QUESTION MARK
# Total code points: 67
# ================================================
109A0..109B7 ; Meroitic_Cursive # Lo [24] MEROITIC CURSIVE LETTER A..MEROITIC CURSIVE LETTER DA
109BE..109BF ; Meroitic_Cursive # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN
# Total code points: 26
# ================================================
10980..1099F ; Meroitic_Hieroglyphs # Lo [32] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC HIEROGLYPHIC SYMBOL VIDJ-2
# Total code points: 32
# ================================================
16F00..16F44 ; Miao # Lo [69] MIAO LETTER PA..MIAO LETTER HHA
16F50 ; Miao # Lo MIAO LETTER NASALIZATION
16F51..16F7E ; Miao # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
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
# ================================================
11180..11181 ; Sharada # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA
11182 ; Sharada # Mc SHARADA SIGN VISARGA
11183..111B2 ; Sharada # Lo [48] SHARADA LETTER A..SHARADA LETTER HA
111B3..111B5 ; Sharada # Mc [3] SHARADA VOWEL SIGN AA..SHARADA VOWEL SIGN II
111B6..111BE ; Sharada # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O
111BF..111C0 ; Sharada # Mc [2] SHARADA VOWEL SIGN AU..SHARADA SIGN VIRAMA
111C1..111C4 ; Sharada # Lo [4] SHARADA SIGN AVAGRAHA..SHARADA OM
111C5..111C8 ; Sharada # Po [4] SHARADA DANDA..SHARADA SEPARATOR
111D0..111D9 ; Sharada # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE
# Total code points: 83
# ================================================
110D0..110E8 ; Sora_Sompeng # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE
110F0..110F9 ; Sora_Sompeng # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE
# Total code points: 35
# ================================================
11680..116AA ; Takri # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA
116AB ; Takri # Mn TAKRI SIGN ANUSVARA
116AC ; Takri # Mc TAKRI SIGN VISARGA
116AD ; Takri # Mn TAKRI VOWEL SIGN AA
116AE..116AF ; Takri # Mc [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II
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
116C0..116C9 ; Takri # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE
# Total code points: 66
# EOF