stan/jdk-24
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

8209923: Unicode 11.0.0

Browse Source 
Updated JDK to support Unicode 11.0.0.

Reviewed-by: naoto
This commit is contained in:
Rachna Goel 2018-11-21 14:24:31 +05:30
parent 11e54e0749
commit f8518a2c05
30 changed files with 2580 additions and 509 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

157
make/data/characterdata/CharacterData00.java.template
View File

@ -25,7 +25,7 @@
package java.lang;
/**
/**
* The CharacterData00 class encapsulates the large tables once found in
* java.lang.Character
*/
@ -265,6 +265,54 @@ class CharacterData00 extends CharacterData {
case 0x13ED: mapChar = 0xABBD; break;
case 0x13EE: mapChar = 0xABBE; break;
case 0x13EF: mapChar = 0xABBF; break;
case 0x1C90: mapChar = 0x10D0; break;
case 0x1C91: mapChar = 0x10D1; break;
case 0x1C92: mapChar = 0x10D2; break;
case 0x1C93: mapChar = 0x10D3; break;
case 0x1C94: mapChar = 0x10D4; break;
case 0x1C95: mapChar = 0x10D5; break;
case 0x1C96: mapChar = 0x10D6; break;
case 0x1C97: mapChar = 0x10D7; break;
case 0x1C98: mapChar = 0x10D8; break;
case 0x1C99: mapChar = 0x10D9; break;
case 0x1C9A: mapChar = 0x10DA; break;
case 0x1C9B: mapChar = 0x10DB; break;
case 0x1C9C: mapChar = 0x10DC; break;
case 0x1C9D: mapChar = 0x10DD; break;
case 0x1C9E: mapChar = 0x10DE; break;
case 0x1C9F: mapChar = 0x10DF; break;
case 0x1CA0: mapChar = 0x10E0; break;
case 0x1CA1: mapChar = 0x10E1; break;
case 0x1CA2: mapChar = 0x10E2; break;
case 0x1CA3: mapChar = 0x10E3; break;
case 0x1CA4: mapChar = 0x10E4; break;
case 0x1CA5: mapChar = 0x10E5; break;
case 0x1CA6: mapChar = 0x10E6; break;
case 0x1CA7: mapChar = 0x10E7; break;
case 0x1CA8: mapChar = 0x10E8; break;
case 0x1CA9: mapChar = 0x10E9; break;
case 0x1CAA: mapChar = 0x10EA; break;
case 0x1CAB: mapChar = 0x10EB; break;
case 0x1CAC: mapChar = 0x10EC; break;
case 0x1CAD: mapChar = 0x10ED; break;
case 0x1CAE: mapChar = 0x10EE; break;
case 0x1CAF: mapChar = 0x10EF; break;
case 0x1CB0: mapChar = 0x10F0; break;
case 0x1CB1: mapChar = 0x10F1; break;
case 0x1CB2: mapChar = 0x10F2; break;
case 0x1CB3: mapChar = 0x10F3; break;
case 0x1CB4: mapChar = 0x10F4; break;
case 0x1CB5: mapChar = 0x10F5; break;
case 0x1CB6: mapChar = 0x10F6; break;
case 0x1CB7: mapChar = 0x10F7; break;
case 0x1CB8: mapChar = 0x10F8; break;
case 0x1CB9: mapChar = 0x10F9; break;
case 0x1CBA: mapChar = 0x10FA; break;
case 0x1CBB: mapChar = 0x10FB; break;
case 0x1CBC: mapChar = 0x10FC; break;
case 0x1CBD: mapChar = 0x10FD; break;
case 0x1CBE: mapChar = 0x10FE; break;
case 0x1CBF: mapChar = 0x10FF; break;
case 0x1E9E: mapChar = 0x00DF; break;
case 0x1F88: mapChar = 0x1F80; break;
case 0x1F89: mapChar = 0x1F81; break;
@ -355,6 +403,52 @@ class CharacterData00 extends CharacterData {
case 0x0287: mapChar = 0xA7B1; break;
case 0x029D: mapChar = 0xA7B2; break;
case 0x029E: mapChar = 0xA7B0; break;
case 0x10D0: mapChar = 0x1C90; break;
case 0x10D1: mapChar = 0x1C91; break;
case 0x10D2: mapChar = 0x1C92; break;
case 0x10D3: mapChar = 0x1C93; break;
case 0x10D4: mapChar = 0x1C94; break;
case 0x10D5: mapChar = 0x1C95; break;
case 0x10D6: mapChar = 0x1C96; break;
case 0x10D7: mapChar = 0x1C97; break;
case 0x10D8: mapChar = 0x1C98; break;
case 0x10D9: mapChar = 0x1C99; break;
case 0x10DA: mapChar = 0x1C9A; break;
case 0x10DB: mapChar = 0x1C9B; break;
case 0x10DC: mapChar = 0x1C9C; break;
case 0x10DD: mapChar = 0x1C9D; break;
case 0x10DE: mapChar = 0x1C9E; break;
case 0x10DF: mapChar = 0x1C9F; break;
case 0x10E0: mapChar = 0x1CA0; break;
case 0x10E1: mapChar = 0x1CA1; break;
case 0x10E2: mapChar = 0x1CA2; break;
case 0x10E3: mapChar = 0x1CA3; break;
case 0x10E4: mapChar = 0x1CA4; break;
case 0x10E5: mapChar = 0x1CA5; break;
case 0x10E6: mapChar = 0x1CA6; break;
case 0x10E7: mapChar = 0x1CA7; break;
case 0x10E8: mapChar = 0x1CA8; break;
case 0x10E9: mapChar = 0x1CA9; break;
case 0x10EA: mapChar = 0x1CAA; break;
case 0x10EB: mapChar = 0x1CAB; break;
case 0x10EC: mapChar = 0x1CAC; break;
case 0x10ED: mapChar = 0x1CAD; break;
case 0x10EE: mapChar = 0x1CAE; break;
case 0x10EF: mapChar = 0x1CAF; break;
case 0x10F0: mapChar = 0x1CB0; break;
case 0x10F1: mapChar = 0x1CB1; break;
case 0x10F2: mapChar = 0x1CB2; break;
case 0x10F3: mapChar = 0x1CB3; break;
case 0x10F4: mapChar = 0x1CB4; break;
case 0x10F5: mapChar = 0x1CB5; break;
case 0x10F6: mapChar = 0x1CB6; break;
case 0x10F7: mapChar = 0x1CB7; break;
case 0x10F8: mapChar = 0x1CB8; break;
case 0x10F9: mapChar = 0x1CB9; break;
case 0x10FA: mapChar = 0x1CBA; break;
case 0x10FD: mapChar = 0x1CBD; break;
case 0x10FE: mapChar = 0x1CBE; break;
case 0x10FF: mapChar = 0x1CBF; break;
case 0x1C80: mapChar = 0x0412; break;
case 0x1C81: mapChar = 0x0414; break;
case 0x1C82: mapChar = 0x041E; break;
@ -544,9 +638,16 @@ class CharacterData00 extends CharacterData {
mapChar = ch + 1;
}
else if ((val & $$maskLowerCase) == 0) {
// The character does not have a lowercase equivalent, so it must
// already be lowercase; so subtract 1 to get the titlecase form.
mapChar = ch - 1;
// For some Georgian letters, titlecase form is
// same as this character.
if(ch >= 0x10D0 && ch <= 0x10FF) {
mapChar = ch;
}
else {
// The character does not have a lowercase equivalent, so it must
// already be lowercase; so subtract 1 to get the titlecase form.
mapChar = ch - 1;
}
}
// else {
// The character has both an uppercase equivalent and a lowercase
@ -741,6 +842,52 @@ class CharacterData00 extends CharacterData {
case 0x0287: mapChar = 0xA7B1; break;
case 0x029D: mapChar = 0xA7B2; break;
case 0x029E: mapChar = 0xA7B0; break;
case 0x10D0: mapChar = 0x1C90; break;
case 0x10D1: mapChar = 0x1C91; break;
case 0x10D2: mapChar = 0x1C92; break;
case 0x10D3: mapChar = 0x1C93; break;
case 0x10D4: mapChar = 0x1C94; break;
case 0x10D5: mapChar = 0x1C95; break;
case 0x10D6: mapChar = 0x1C96; break;
case 0x10D7: mapChar = 0x1C97; break;
case 0x10D8: mapChar = 0x1C98; break;
case 0x10D9: mapChar = 0x1C99; break;
case 0x10DA: mapChar = 0x1C9A; break;
case 0x10DB: mapChar = 0x1C9B; break;
case 0x10DC: mapChar = 0x1C9C; break;
case 0x10DD: mapChar = 0x1C9D; break;
case 0x10DE: mapChar = 0x1C9E; break;
case 0x10DF: mapChar = 0x1C9F; break;
case 0x10E0: mapChar = 0x1CA0; break;
case 0x10E1: mapChar = 0x1CA1; break;
case 0x10E2: mapChar = 0x1CA2; break;
case 0x10E3: mapChar = 0x1CA3; break;
case 0x10E4: mapChar = 0x1CA4; break;
case 0x10E5: mapChar = 0x1CA5; break;
case 0x10E6: mapChar = 0x1CA6; break;
case 0x10E7: mapChar = 0x1CA7; break;
case 0x10E8: mapChar = 0x1CA8; break;
case 0x10E9: mapChar = 0x1CA9; break;
case 0x10EA: mapChar = 0x1CAA; break;
case 0x10EB: mapChar = 0x1CAB; break;
case 0x10EC: mapChar = 0x1CAC; break;
case 0x10ED: mapChar = 0x1CAD; break;
case 0x10EE: mapChar = 0x1CAE; break;
case 0x10EF: mapChar = 0x1CAF; break;
case 0x10F0: mapChar = 0x1CB0; break;
case 0x10F1: mapChar = 0x1CB1; break;
case 0x10F2: mapChar = 0x1CB2; break;
case 0x10F3: mapChar = 0x1CB3; break;
case 0x10F4: mapChar = 0x1CB4; break;
case 0x10F5: mapChar = 0x1CB5; break;
case 0x10F6: mapChar = 0x1CB6; break;
case 0x10F7: mapChar = 0x1CB7; break;
case 0x10F8: mapChar = 0x1CB8; break;
case 0x10F9: mapChar = 0x1CB9; break;
case 0x10FA: mapChar = 0x1CBA; break;
case 0x10FD: mapChar = 0x1CBD; break;
case 0x10FE: mapChar = 0x1CBE; break;
case 0x10FF: mapChar = 0x1CBF; break;
case 0x1C80: mapChar = 0x0412; break;
case 0x1C81: mapChar = 0x0414; break;
case 0x1C82: mapChar = 0x041E; break;
@ -928,5 +1075,5 @@ class CharacterData00 extends CharacterData {
static {
$$Initializers
}
}
}

42
make/data/characterdata/CharacterData01.java.template
View File

@ -364,6 +364,8 @@ class CharacterData01 extends CharacterData {
case 0x10E78: retval = 700; break; // RUMI NUMBER SEVEN HUNDRED
case 0x10E79: retval = 800; break; // RUMI NUMBER EIGHT HUNDRED
case 0x10E7A: retval = 900; break; // RUMI NUMBER NINE HUNDRED
case 0x10F25: retval = 100; break; // OLD SOGDIAN NUMBER ONE HUNDRED
case 0x10F54: retval = 100; break; // SOGDIAN NUMBER ONE HUNDRED
case 0x1105E: retval = 40; break; // BRAHMI NUMBER FORTY
case 0x1105F: retval = 50; break; // BRAHMI NUMBER FIFTY
case 0x11060: retval = 60; break; // BRAHMI NUMBER SIXTY
@ -407,6 +409,46 @@ class CharacterData01 extends CharacterData {
case 0x1D36F: retval = 70; break; // COUNTING ROD TENS DIGIT SEVEN
case 0x1D370: retval = 80; break; // COUNTING ROD TENS DIGIT EIGHT
case 0x1D371: retval = 90; break; // COUNTING ROD TENS DIGIT NINE
case 0x1EC7D: retval = 40; break; // INDIC SIYAQ NUMBER FORTY
case 0x1EC7E: retval = 50; break; // INDIC SIYAQ NUMBER FIFTY
case 0x1EC7F: retval = 60; break; // INDIC SIYAQ NUMBER SIXTY
case 0X1EC80: retval = 70; break; // INDIC SIYAQ NUMBER SEVENTY
case 0X1EC81: retval = 80; break; // INDIC SIYAQ NUMBER EIGHTY
case 0X1EC82: retval = 90; break; // INDIC SIYAQ NUMBER NINETY
case 0X1EC83: retval = 100; break; // INDIC SIYAQ NUMBER ONE HUNDRED
case 0X1EC84: retval = 200; break; // INDIC SIYAQ NUMBER TWO HUNDRED
case 0X1EC85: retval = 300; break; // INDIC SIYAQ NUMBER THREE HUNDRED
case 0X1EC86: retval = 400; break; // INDIC SIYAQ NUMBER FOUR HUNDRED
case 0X1EC87: retval = 500; break; // INDIC SIYAQ NUMBER FIVE HUNDRED
case 0X1EC88: retval = 600; break; // INDIC SIYAQ NUMBER SIX HUNDRED
case 0X1EC89: retval = 700; break; // INDIC SIYAQ NUMBER SEVEN HUNDRED
case 0X1EC8A: retval = 800; break; // INDIC SIYAQ NUMBER EIGHT HUNDRED
case 0X1EC8B: retval = 900; break; // INDIC SIYAQ NUMBER NINE HUNDRED
case 0X1EC8C: retval = 1000; break; // INDIC SIYAQ NUMBER ONE THOUSAND
case 0X1EC8D: retval = 2000; break; // INDIC SIYAQ NUMBER TWO THOUSAND
case 0X1EC8E: retval = 3000; break; // INDIC SIYAQ NUMBER THREE THOUSAND
case 0X1EC8F: retval = 4000; break; // INDIC SIYAQ NUMBER FOUR THOUSAND
case 0X1EC90: retval = 5000; break; // INDIC SIYAQ NUMBER FIVE THOUSAND
case 0X1EC91: retval = 6000; break; // INDIC SIYAQ NUMBER SIX THOUSAND
case 0X1EC92: retval = 7000; break; // INDIC SIYAQ NUMBER SEVEN THOUSAND
case 0X1EC93: retval = 8000; break; // INDIC SIYAQ NUMBER EIGHT THOUSAND
case 0X1EC94: retval = 9000; break; // INDIC SIYAQ NUMBER NINE THOUSAND
case 0X1EC95: retval = 10000; break; // INDIC SIYAQ NUMBER TEN THOUSAND
case 0X1EC96: retval = 20000; break; // INDIC SIYAQ NUMBER TWENTY THOUSAND
case 0X1EC97: retval = 30000; break; // INDIC SIYAQ NUMBER THIRTY THOUSAND
case 0X1EC98: retval = 40000; break; // INDIC SIYAQ NUMBER FORTY THOUSAND
case 0X1EC99: retval = 50000; break; // INDIC SIYAQ NUMBER FIFTY THOUSAND
case 0X1EC9A: retval = 60000; break; // INDIC SIYAQ NUMBER SIXTY THOUSAND
case 0X1EC9B: retval = 70000; break; // INDIC SIYAQ NUMBER SEVENTY THOUSAND
case 0X1EC9C: retval = 80000; break; // INDIC SIYAQ NUMBER EIGHTY THOUSAND
case 0X1EC9D: retval = 90000; break; // INDIC SIYAQ NUMBER NINETY THOUSAND
case 0X1EC9E: retval = 100000; break; // INDIC SIYAQ NUMBER LAKH
case 0X1EC9F: retval = 200000; break; // INDIC SIYAQ NUMBER LAKHAN
case 0X1ECA0: retval = 100000; break; // INDIC SIYAQ LAKH MARK
case 0X1ECA1: retval = 10000000; break; // INDIC SIYAQ NUMBER KAROR
case 0X1ECA2: retval = 20000000; break; // INDIC SIYAQ NUMBER KARORAN
case 0X1ECB3: retval = 10000; break; // INDIC SIYAQ NUMBER ALTERNATE TEN THOUSAND
case 0X1ECB4: retval = 100000; break; // INDIC SIYAQ NUMBER ALTERNATE LAKH MARK
default: retval = -2; break;
}

77
make/data/unicodedata/PropList.txt
View File

@ -1,6 +1,6 @@
# PropList-10.0.0.txt
# Date: 2017-03-10, 08:25:30 GMT
# Copyright (c) 2017 Unicode, Inc.
# PropList-11.0.0.txt
# Date: 2018-03-15, 04:28:35 GMT
# Copyright (c) 2018 Unicode, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
@ -125,7 +125,7 @@ FF63 ; Quotation_Mark # Pe HALFWIDTH RIGHT CORNER BRACKET
05C3 ; Terminal_Punctuation # Po HEBREW PUNCTUATION SOF PASUQ
060C ; Terminal_Punctuation # Po ARABIC COMMA
061B ; Terminal_Punctuation # Po ARABIC SEMICOLON
061F ; Terminal_Punctuation # Po ARABIC QUESTION MARK
061E..061F ; Terminal_Punctuation # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK
06D4 ; Terminal_Punctuation # Po ARABIC FULL STOP
0700..070A ; Terminal_Punctuation # Po [11] SYRIAC END OF PARAGRAPH..SYRIAC CONTRACTION
070C ; Terminal_Punctuation # Po SYRIAC HARKLEAN METOBELUS
@ -156,6 +156,8 @@ FF63 ; Quotation_Mark # Pe HALFWIDTH RIGHT CORNER BRACKET
2E2E ; Terminal_Punctuation # Po REVERSED QUESTION MARK
2E3C ; Terminal_Punctuation # Po STENOGRAPHIC FULL STOP
2E41 ; Terminal_Punctuation # Po REVERSED COMMA
2E4C ; Terminal_Punctuation # Po MEDIEVAL COMMA
2E4E ; Terminal_Punctuation # Po PUNCTUS ELEVATUS MARK
3001..3002 ; Terminal_Punctuation # Po [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP
A4FE..A4FF ; Terminal_Punctuation # Po [2] LISU PUNCTUATION COMMA..LISU PUNCTUATION FULL STOP
A60D..A60F ; Terminal_Punctuation # Po [3] VAI COMMA..VAI QUESTION MARK
@ -185,6 +187,7 @@ FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA
10AF0..10AF5 ; Terminal_Punctuation # Po [6] MANICHAEAN PUNCTUATION STAR..MANICHAEAN PUNCTUATION TWO DOTS
10B3A..10B3F ; Terminal_Punctuation # Po [6] TINY TWO DOTS OVER ONE DOT PUNCTUATION..LARGE ONE RING OVER TWO RINGS PUNCTUATION
10B99..10B9C ; Terminal_Punctuation # Po [4] PSALTER PAHLAVI SECTION MARK..PSALTER PAHLAVI FOUR DOTS WITH DOT
10F55..10F59 ; Terminal_Punctuation # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT
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
@ -204,15 +207,17 @@ FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA
11AA1..11AA2 ; Terminal_Punctuation # Po [2] SOYOMBO TERMINAL MARK-1..SOYOMBO TERMINAL MARK-2
11C41..11C43 ; Terminal_Punctuation # Po [3] BHAIKSUKI DANDA..BHAIKSUKI WORD SEPARATOR
11C71 ; Terminal_Punctuation # Po MARCHEN MARK SHAD
11EF7..11EF8 ; Terminal_Punctuation # Po [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION
12470..12474 ; Terminal_Punctuation # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON
16A6E..16A6F ; Terminal_Punctuation # Po [2] MRO DANDA..MRO DOUBLE DANDA
16AF5 ; Terminal_Punctuation # Po BASSA VAH FULL STOP
16B37..16B39 ; Terminal_Punctuation # Po [3] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN CIM CHEEM
16B44 ; Terminal_Punctuation # Po PAHAWH HMONG SIGN XAUS
16E97..16E98 ; Terminal_Punctuation # Po [2] MEDEFAIDRIN COMMA..MEDEFAIDRIN FULL STOP
1BC9F ; Terminal_Punctuation # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP
1DA87..1DA8A ; Terminal_Punctuation # Po [4] SIGNWRITING COMMA..SIGNWRITING COLON
# Total code points: 252
# Total code points: 264
# ================================================
@ -661,6 +666,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
10A01..10A03 ; Other_Alphabetic # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R
10A05..10A06 ; Other_Alphabetic # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O
10A0C..10A0F ; Other_Alphabetic # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA
10D24..10D27 ; Other_Alphabetic # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
11000 ; Other_Alphabetic # Mc BRAHMI SIGN CANDRABINDU
11001 ; Other_Alphabetic # Mn BRAHMI SIGN ANUSVARA
11002 ; Other_Alphabetic # Mc BRAHMI SIGN VISARGA
@ -673,6 +679,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
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
11145..11146 ; Other_Alphabetic # Mc [2] CHAKMA VOWEL SIGN AA..CHAKMA VOWEL SIGN EI
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
@ -730,9 +737,10 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
11722..11725 ; Other_Alphabetic # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
11726 ; Other_Alphabetic # Mc AHOM VOWEL SIGN E
11727..1172A ; Other_Alphabetic # Mn [4] AHOM VOWEL SIGN AW..AHOM VOWEL SIGN AM
11A01..11A06 ; Other_Alphabetic # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O
11A07..11A08 ; Other_Alphabetic # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU
11A09..11A0A ; Other_Alphabetic # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK
1182C..1182E ; Other_Alphabetic # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II
1182F..11837 ; Other_Alphabetic # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA
11838 ; Other_Alphabetic # Mc DOGRA SIGN VISARGA
11A01..11A0A ; Other_Alphabetic # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK
11A35..11A38 ; Other_Alphabetic # Mn [4] ZANABAZAR SQUARE SIGN CANDRABINDU..ZANABAZAR SQUARE SIGN ANUSVARA
11A39 ; Other_Alphabetic # Mc ZANABAZAR SQUARE SIGN VISARGA
11A3B..11A3E ; Other_Alphabetic # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA
@ -758,6 +766,13 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
11D3F..11D41 ; Other_Alphabetic # Mn [3] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI SIGN VISARGA
11D43 ; Other_Alphabetic # Mn MASARAM GONDI SIGN CANDRA
11D47 ; Other_Alphabetic # Mn MASARAM GONDI RA-KARA
11D8A..11D8E ; Other_Alphabetic # Mc [5] GUNJALA GONDI VOWEL SIGN AA..GUNJALA GONDI VOWEL SIGN UU
11D90..11D91 ; Other_Alphabetic # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI
11D93..11D94 ; Other_Alphabetic # Mc [2] GUNJALA GONDI VOWEL SIGN OO..GUNJALA GONDI VOWEL SIGN AU
11D95 ; Other_Alphabetic # Mn GUNJALA GONDI SIGN ANUSVARA
11D96 ; Other_Alphabetic # Mc GUNJALA GONDI SIGN VISARGA
11EF3..11EF4 ; Other_Alphabetic # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
11EF5..11EF6 ; Other_Alphabetic # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
16B30..16B36 ; Other_Alphabetic # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
16F51..16F7E ; Other_Alphabetic # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
1BC9E ; Other_Alphabetic # Mn DUPLOYAN DOUBLE MARK
@ -771,7 +786,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
1F150..1F169 ; Other_Alphabetic # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
1F170..1F189 ; Other_Alphabetic # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z
# Total code points: 1300
# Total code points: 1334
# ================================================
@ -780,10 +795,10 @@ 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..9FEA ; Ideographic # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
4E00..9FEF ; Ideographic # Lo [20976] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEF
F900..FA6D ; Ideographic # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D
FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9
17000..187EC ; Ideographic # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC
17000..187F1 ; Ideographic # Lo [6130] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F1
18800..18AF2 ; Ideographic # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
1B170..1B2FB ; Ideographic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
20000..2A6D6 ; Ideographic # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
@ -793,7 +808,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
2CEB0..2EBE0 ; Ideographic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 96174
# Total code points: 96184
# ================================================
@ -953,6 +968,9 @@ FF9E..FF9F ; Diacritic # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFW
FFE3 ; Diacritic # Sk FULLWIDTH MACRON
102E0 ; Diacritic # Mn COPTIC EPACT THOUSANDS MARK
10AE5..10AE6 ; Diacritic # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW
10D22..10D23 ; Diacritic # Lo [2] HANIFI ROHINGYA MARK SAKIN..HANIFI ROHINGYA MARK NA KHONNA
10D24..10D27 ; Diacritic # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
10F46..10F50 ; Diacritic # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW
110B9..110BA ; Diacritic # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA
11133..11134 ; Diacritic # Mn [2] CHAKMA VIRAMA..CHAKMA MAAYYAA
11173 ; Diacritic # Mn MAHAJANI SIGN NUKTA
@ -973,12 +991,14 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON
116B6 ; Diacritic # Mc TAKRI SIGN VIRAMA
116B7 ; Diacritic # Mn TAKRI SIGN NUKTA
1172B ; Diacritic # Mn AHOM SIGN KILLER
11839..1183A ; Diacritic # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA
11A34 ; Diacritic # Mn ZANABAZAR SQUARE SIGN VIRAMA
11A47 ; Diacritic # Mn ZANABAZAR SQUARE SUBJOINER
11A99 ; Diacritic # Mn SOYOMBO SUBJOINER
11C3F ; Diacritic # Mn BHAIKSUKI SIGN VIRAMA
11D42 ; Diacritic # Mn MASARAM GONDI SIGN NUKTA
11D44..11D45 ; Diacritic # Mn [2] MASARAM GONDI SIGN HALANTA..MASARAM GONDI VIRAMA
11D97 ; Diacritic # Mn GUNJALA GONDI VIRAMA
16AF0..16AF4 ; Diacritic # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
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
@ -991,7 +1011,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON
1E944..1E946 ; Diacritic # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK
1E948..1E94A ; Diacritic # Mn [3] ADLAM CONSONANT MODIFIER..ADLAM NUKTA
# Total code points: 798
# Total code points: 818
# ================================================
@ -1137,7 +1157,7 @@ E0020..E007F ; Other_Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG
# ================================================
3400..4DB5 ; Unified_Ideograph # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4E00..9FEA ; Unified_Ideograph # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
4E00..9FEF ; Unified_Ideograph # Lo [20976] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEF
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
@ -1151,7 +1171,7 @@ FA27..FA29 ; Unified_Ideograph # Lo [3] CJK COMPATIBILITY IDEOGRAPH-FA27..C
2B820..2CEA1 ; Unified_Ideograph # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
2CEB0..2EBE0 ; Unified_Ideograph # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
# Total code points: 87882
# Total code points: 87887
# ================================================
@ -1255,10 +1275,13 @@ AABB..AABC ; Logical_Order_Exception # Lo [2] TAI VIET VOWEL AUE..TAI VIET
002E ; Sentence_Terminal # Po FULL STOP
003F ; Sentence_Terminal # Po QUESTION MARK
0589 ; Sentence_Terminal # Po ARMENIAN FULL STOP
061F ; Sentence_Terminal # Po ARABIC QUESTION MARK
061E..061F ; Sentence_Terminal # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK
06D4 ; Sentence_Terminal # Po ARABIC FULL STOP
0700..0702 ; Sentence_Terminal # Po [3] SYRIAC END OF PARAGRAPH..SYRIAC SUBLINEAR FULL STOP
07F9 ; Sentence_Terminal # Po NKO EXCLAMATION MARK
0837 ; Sentence_Terminal # Po SAMARITAN PUNCTUATION MELODIC QITSA
0839 ; Sentence_Terminal # Po SAMARITAN PUNCTUATION QITSA
083D..083E ; Sentence_Terminal # Po [2] SAMARITAN PUNCTUATION SOF MASHFAAT..SAMARITAN PUNCTUATION ANNAAU
0964..0965 ; Sentence_Terminal # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA
104A..104B ; Sentence_Terminal # Po [2] MYANMAR SIGN LITTLE SECTION..MYANMAR SIGN SECTION
1362 ; Sentence_Terminal # Po ETHIOPIC FULL STOP
@ -1296,6 +1319,7 @@ FF0E ; Sentence_Terminal # Po FULLWIDTH FULL STOP
FF1F ; Sentence_Terminal # Po FULLWIDTH QUESTION MARK
FF61 ; Sentence_Terminal # Po HALFWIDTH IDEOGRAPHIC FULL STOP
10A56..10A57 ; Sentence_Terminal # Po [2] KHAROSHTHI PUNCTUATION DANDA..KHAROSHTHI PUNCTUATION DOUBLE DANDA
10F55..10F59 ; Sentence_Terminal # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT
11047..11048 ; Sentence_Terminal # Po [2] BRAHMI DANDA..BRAHMI DOUBLE DANDA
110BE..110C1 ; Sentence_Terminal # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA
11141..11143 ; Sentence_Terminal # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK
@ -1313,14 +1337,16 @@ FF61 ; Sentence_Terminal # Po HALFWIDTH IDEOGRAPHIC FULL STOP
11A42..11A43 ; Sentence_Terminal # Po [2] ZANABAZAR SQUARE MARK SHAD..ZANABAZAR SQUARE MARK DOUBLE SHAD
11A9B..11A9C ; Sentence_Terminal # Po [2] SOYOMBO MARK SHAD..SOYOMBO MARK DOUBLE SHAD
11C41..11C42 ; Sentence_Terminal # Po [2] BHAIKSUKI DANDA..BHAIKSUKI DOUBLE DANDA
11EF7..11EF8 ; Sentence_Terminal # Po [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION
16A6E..16A6F ; Sentence_Terminal # Po [2] MRO DANDA..MRO DOUBLE DANDA
16AF5 ; Sentence_Terminal # Po BASSA VAH FULL STOP
16B37..16B38 ; Sentence_Terminal # Po [2] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN VOS TSHAB CEEB
16B44 ; Sentence_Terminal # Po PAHAWH HMONG SIGN XAUS
16E98 ; Sentence_Terminal # Po MEDEFAIDRIN FULL STOP
1BC9F ; Sentence_Terminal # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP
1DA88 ; Sentence_Terminal # Po SIGNWRITING FULL STOP
# Total code points: 128
# Total code points: 141
# ================================================
@ -1521,14 +1547,10 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S
2B74..2B75 ; Pattern_Syntax # Cn [2] <reserved-2B74>..<reserved-2B75>
2B76..2B95 ; Pattern_Syntax # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW
2B96..2B97 ; Pattern_Syntax # Cn [2] <reserved-2B96>..<reserved-2B97>
2B98..2BB9 ; Pattern_Syntax # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX
2BBA..2BBC ; Pattern_Syntax # Cn [3] <reserved-2BBA>..<reserved-2BBC>
2BBD..2BC8 ; Pattern_Syntax # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
2B98..2BC8 ; Pattern_Syntax # So [49] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
2BC9 ; Pattern_Syntax # Cn <reserved-2BC9>
2BCA..2BD2 ; Pattern_Syntax # So [9] TOP HALF BLACK CIRCLE..GROUP MARK
2BD3..2BEB ; Pattern_Syntax # Cn [25] <reserved-2BD3>..<reserved-2BEB>
2BEC..2BEF ; Pattern_Syntax # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS
2BF0..2BFF ; Pattern_Syntax # Cn [16] <reserved-2BF0>..<reserved-2BFF>
2BCA..2BFE ; Pattern_Syntax # So [53] TOP HALF BLACK CIRCLE..REVERSED RIGHT ANGLE
2BFF ; Pattern_Syntax # Cn <reserved-2BFF>
2E00..2E01 ; Pattern_Syntax # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER
2E02 ; Pattern_Syntax # Pi LEFT SUBSTITUTION BRACKET
2E03 ; Pattern_Syntax # Pf RIGHT SUBSTITUTION BRACKET
@ -1566,8 +1588,8 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S
2E40 ; Pattern_Syntax # Pd DOUBLE HYPHEN
2E41 ; Pattern_Syntax # Po REVERSED COMMA
2E42 ; Pattern_Syntax # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK
2E43..2E49 ; Pattern_Syntax # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA
2E4A..2E7F ; Pattern_Syntax # Cn [54] <reserved-2E4A>..<reserved-2E7F>
2E43..2E4E ; Pattern_Syntax # Po [12] DASH WITH LEFT UPTURN..PUNCTUS ELEVATUS MARK
2E4F..2E7F ; Pattern_Syntax # Cn [49] <reserved-2E4F>..<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
@ -1606,8 +1628,9 @@ FE45..FE46 ; Pattern_Syntax # Po [2] SESAME DOT..WHITE SESAME DOT
070F ; Prepended_Concatenation_Mark # Cf SYRIAC ABBREVIATION MARK
08E2 ; Prepended_Concatenation_Mark # Cf ARABIC DISPUTED END OF AYAH
110BD ; Prepended_Concatenation_Mark # Cf KAITHI NUMBER SIGN
110CD ; Prepended_Concatenation_Mark # Cf KAITHI NUMBER SIGN ABOVE
# Total code points: 10
# Total code points: 11
# ================================================

209
make/data/unicodedata/Scripts.txt
View File

@ -1,6 +1,6 @@
# Scripts-10.0.0.txt
# Date: 2017-03-11, 06:40:37 GMT
# Copyright (c) 2017 Unicode, Inc.
# Scripts-11.0.0.txt
# Date: 2018-02-21, 05:34:31 GMT
# Copyright (c) 2018 Unicode, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
@ -308,10 +308,8 @@
2B47..2B4C ; Common # Sm [6] REVERSE TILDE OPERATOR ABOVE RIGHTWARDS ARROW..RIGHTWARDS ARROW ABOVE REVERSE TILDE OPERATOR
2B4D..2B73 ; Common # So [39] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR
2B76..2B95 ; Common # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW
2B98..2BB9 ; Common # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX
2BBD..2BC8 ; Common # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
2BCA..2BD2 ; Common # So [9] TOP HALF BLACK CIRCLE..GROUP MARK
2BEC..2BEF ; Common # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS
2B98..2BC8 ; Common # So [49] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
2BCA..2BFE ; Common # So [53] TOP HALF BLACK CIRCLE..REVERSED RIGHT ANGLE
2E00..2E01 ; Common # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER
2E02 ; Common # Pi LEFT SUBSTITUTION BRACKET
2E03 ; Common # Pf RIGHT SUBSTITUTION BRACKET
@ -349,7 +347,7 @@
2E40 ; Common # Pd DOUBLE HYPHEN
2E41 ; Common # Po REVERSED COMMA
2E42 ; Common # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK
2E43..2E49 ; Common # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA
2E43..2E4E ; Common # Po [12] DASH WITH LEFT UPTURN..PUNCTUS ELEVATUS MARK
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
@ -522,8 +520,9 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1D183..1D184 ; Common # So [2] MUSICAL SYMBOL ARPEGGIATO UP..MUSICAL SYMBOL ARPEGGIATO DOWN
1D18C..1D1A9 ; Common # So [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH
1D1AE..1D1E8 ; Common # So [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN
1D2E0..1D2F3 ; Common # No [20] MAYAN NUMERAL ZERO..MAYAN NUMERAL NINETEEN
1D300..1D356 ; Common # So [87] MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING
1D360..1D371 ; Common # No [18] COUNTING ROD UNIT DIGIT ONE..COUNTING ROD TENS DIGIT NINE
1D360..1D378 ; Common # No [25] COUNTING ROD UNIT DIGIT ONE..TALLY MARK FIVE
1D400..1D454 ; Common # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G
1D456..1D49C ; Common # L& [71] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL SCRIPT CAPITAL A
1D49E..1D49F ; Common # L& [2] MATHEMATICAL SCRIPT CAPITAL C..MATHEMATICAL SCRIPT CAPITAL D
@ -565,6 +564,11 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1D7C3 ; Common # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL
1D7C4..1D7CB ; Common # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA
1D7CE..1D7FF ; Common # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
1EC71..1ECAB ; Common # No [59] INDIC SIYAQ NUMBER ONE..INDIC SIYAQ NUMBER PREFIXED NINE
1ECAC ; Common # So INDIC SIYAQ PLACEHOLDER
1ECAD..1ECAF ; Common # No [3] INDIC SIYAQ FRACTION ONE QUARTER..INDIC SIYAQ FRACTION THREE QUARTERS
1ECB0 ; Common # Sc INDIC SIYAQ RUPEE MARK
1ECB1..1ECB4 ; Common # No [4] INDIC SIYAQ NUMBER ALTERNATE ONE..INDIC SIYAQ ALTERNATE LAKH MARK
1F000..1F02B ; Common # So [44] MAHJONG TILE EAST WIND..MAHJONG TILE BACK
1F030..1F093 ; Common # So [100] DOMINO TILE HORIZONTAL BACK..DOMINO TILE VERTICAL-06-06
1F0A0..1F0AE ; Common # So [15] PLAYING CARD BACK..PLAYING CARD KING OF SPADES
@ -572,8 +576,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1F0C1..1F0CF ; Common # So [15] PLAYING CARD ACE OF DIAMONDS..PLAYING CARD BLACK JOKER
1F0D1..1F0F5 ; Common # So [37] PLAYING CARD ACE OF CLUBS..PLAYING CARD TRUMP-21
1F100..1F10C ; Common # No [13] DIGIT ZERO FULL STOP..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO
1F110..1F12E ; Common # So [31] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED WZ
1F130..1F16B ; Common # So [60] SQUARED LATIN CAPITAL LETTER A..RAISED MD SIGN
1F110..1F16B ; Common # So [92] PARENTHESIZED LATIN CAPITAL LETTER A..RAISED MD SIGN
1F170..1F1AC ; Common # So [61] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VOD
1F1E6..1F1FF ; Common # So [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z
1F201..1F202 ; Common # So [2] SQUARED KATAKANA KOKO..SQUARED KATAKANA SA
@ -585,9 +588,9 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1F3FB..1F3FF ; Common # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
1F400..1F6D4 ; Common # So [725] RAT..PAGODA
1F6E0..1F6EC ; Common # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING
1F6F0..1F6F8 ; Common # So [9] SATELLITE..FLYING SAUCER
1F6F0..1F6F9 ; Common # So [10] SATELLITE..SKATEBOARD
1F700..1F773 ; Common # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
1F780..1F7D4 ; Common # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR
1F780..1F7D8 ; Common # So [89] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NEGATIVE CIRCLED SQUARE
1F800..1F80B ; Common # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD
1F810..1F847 ; Common # So [56] LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW
1F850..1F859 ; Common # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW
@ -595,15 +598,18 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1F890..1F8AD ; Common # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS
1F900..1F90B ; Common # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT
1F910..1F93E ; Common # So [47] ZIPPER-MOUTH FACE..HANDBALL
1F940..1F94C ; Common # So [13] WILTED FLOWER..CURLING STONE
1F950..1F96B ; Common # So [28] CROISSANT..CANNED FOOD
1F980..1F997 ; Common # So [24] CRAB..CRICKET
1F9C0 ; Common # So CHEESE WEDGE
1F9D0..1F9E6 ; Common # So [23] FACE WITH MONOCLE..SOCKS
1F940..1F970 ; Common # So [49] WILTED FLOWER..SMILING FACE WITH SMILING EYES AND THREE HEARTS
1F973..1F976 ; Common # So [4] FACE WITH PARTY HORN AND PARTY HAT..FREEZING FACE
1F97A ; Common # So FACE WITH PLEADING EYES
1F97C..1F9A2 ; Common # So [39] LAB COAT..SWAN
1F9B0..1F9B9 ; Common # So [10] EMOJI COMPONENT RED HAIR..SUPERVILLAIN
1F9C0..1F9C2 ; Common # So [3] CHEESE WEDGE..SALT SHAKER
1F9D0..1F9FF ; Common # So [48] FACE WITH MONOCLE..NAZAR AMULET
1FA60..1FA6D ; Common # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER
E0001 ; Common # Cf LANGUAGE TAG
E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
# Total code points: 7363
# Total code points: 7591
# ================================================
@ -646,8 +652,7 @@ A770 ; Latin # Lm MODIFIER LETTER US
A771..A787 ; Latin # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T
A78B..A78E ; Latin # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
A78F ; Latin # Lo LATIN LETTER SINOLOGICAL DOT
A790..A7AE ; Latin # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I
A7B0..A7B7 ; Latin # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA
A790..A7B9 ; Latin # L& [42] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER U WITH STROKE
A7F7 ; Latin # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I
A7F8..A7F9 ; Latin # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
A7FA ; Latin # L& LATIN LETTER SMALL CAPITAL TURNED M
@ -659,7 +664,7 @@ FB00..FB06 ; Latin # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE S
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: 1350
# Total code points: 1353
# ================================================
@ -753,13 +758,13 @@ FE2E..FE2F ; Cyrillic # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBININ
0531..0556 ; Armenian # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH
0559 ; Armenian # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING
055A..055F ; Armenian # Po [6] ARMENIAN APOSTROPHE..ARMENIAN ABBREVIATION MARK
0561..0587 ; Armenian # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN
0560..0588 ; Armenian # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE
058A ; Armenian # Pd ARMENIAN HYPHEN
058D..058E ; Armenian # So [2] RIGHT-FACING ARMENIAN ETERNITY SIGN..LEFT-FACING ARMENIAN ETERNITY SIGN
058F ; Armenian # Sc ARMENIAN DRAM SIGN
FB13..FB17 ; Armenian # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH
# Total code points: 93
# Total code points: 95
# ================================================
@ -773,7 +778,7 @@ FB13..FB17 ; Armenian # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SM
05C6 ; Hebrew # Po HEBREW PUNCTUATION NUN HAFUKHA
05C7 ; Hebrew # Mn HEBREW POINT QAMATS QATAN
05D0..05EA ; Hebrew # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV
05F0..05F2 ; Hebrew # Lo [3] HEBREW LIGATURE YIDDISH DOUBLE VAV..HEBREW LIGATURE YIDDISH DOUBLE YOD
05EF..05F2 ; Hebrew # Lo [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD
05F3..05F4 ; Hebrew # Po [2] HEBREW PUNCTUATION GERESH..HEBREW PUNCTUATION GERSHAYIM
FB1D ; Hebrew # Lo HEBREW LETTER YOD WITH HIRIQ
FB1E ; Hebrew # Mn HEBREW POINT JUDEO-SPANISH VARIKA
@ -786,7 +791,7 @@ FB40..FB41 ; Hebrew # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER S
FB43..FB44 ; Hebrew # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH
FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE ALEF LAMED
# Total code points: 133
# Total code points: 134
# ================================================
@ -823,7 +828,7 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU
0750..077F ; Arabic # Lo [48] ARABIC LETTER BEH WITH THREE DOTS HORIZONTALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS ABOVE
08A0..08B4 ; Arabic # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
08B6..08BD ; Arabic # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON
08D4..08E1 ; Arabic # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA
08D3..08E1 ; Arabic # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA
08E3..08FF ; Arabic # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA
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
@ -871,7 +876,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
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: 1280
# Total code points: 1281
# ================================================
@ -921,9 +926,10 @@ 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
A8FC ; Devanagari # Po DEVANAGARI SIGN SIDDHAM
A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
A8FD..A8FE ; Devanagari # Lo [2] DEVANAGARI JAIN OM..DEVANAGARI LETTER AY
A8FF ; Devanagari # Mn DEVANAGARI VOWEL SIGN AY
# Total code points: 154
# Total code points: 156
# ================================================
@ -956,8 +962,9 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
09FB ; Bengali # Sc BENGALI GANDA MARK
09FC ; Bengali # Lo BENGALI LETTER VEDIC ANUSVARA
09FD ; Bengali # Po BENGALI ABBREVIATION SIGN
09FE ; Bengali # Mn BENGALI SANDHI MARK
# Total code points: 95
# Total code points: 96
# ================================================
@ -982,8 +989,9 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
0A70..0A71 ; Gurmukhi # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK
0A72..0A74 ; Gurmukhi # Lo [3] GURMUKHI IRI..GURMUKHI EK ONKAR
0A75 ; Gurmukhi # Mn GURMUKHI SIGN YAKASH
0A76 ; Gurmukhi # Po GURMUKHI ABBREVIATION SIGN
# Total code points: 79
# Total code points: 80
# ================================================
@ -1078,6 +1086,7 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
0C00 ; Telugu # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE
0C01..0C03 ; Telugu # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA
0C04 ; Telugu # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE
0C05..0C0C ; Telugu # Lo [8] TELUGU LETTER A..TELUGU LETTER VOCALIC L
0C0E..0C10 ; Telugu # Lo [3] TELUGU LETTER E..TELUGU LETTER AI
0C12..0C28 ; Telugu # Lo [23] TELUGU LETTER O..TELUGU LETTER NA
@ -1095,13 +1104,14 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
0C78..0C7E ; Telugu # No [7] TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR..TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR
0C7F ; Telugu # So TELUGU SIGN TUUMU
# Total code points: 96
# Total code points: 97
# ================================================
0C80 ; Kannada # Lo KANNADA SIGN SPACING CANDRABINDU
0C81 ; Kannada # Mn KANNADA SIGN CANDRABINDU
0C82..0C83 ; Kannada # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA
0C84 ; Kannada # Po KANNADA SIGN SIDDHAM
0C85..0C8C ; Kannada # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L
0C8E..0C90 ; Kannada # Lo [3] KANNADA LETTER E..KANNADA LETTER AI
0C92..0CA8 ; Kannada # Lo [23] KANNADA LETTER O..KANNADA LETTER NA
@ -1123,7 +1133,7 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
0CE6..0CEF ; Kannada # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE
0CF1..0CF2 ; Kannada # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
# Total code points: 88
# Total code points: 89
# ================================================
@ -1317,14 +1327,16 @@ AA7E..AA7F ; Myanmar # Lo [2] MYANMAR LETTER SHWE PALAUNG CHA..MYANMAR LETT
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
10D0..10FA ; Georgian # L& [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
10FD..10FF ; Georgian # L& [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN
1C90..1CBA ; Georgian # L& [43] GEORGIAN MTAVRULI CAPITAL LETTER AN..GEORGIAN MTAVRULI CAPITAL LETTER AIN
1CBD..1CBF ; Georgian # L& [3] GEORGIAN MTAVRULI CAPITAL LETTER AEN..GEORGIAN MTAVRULI CAPITAL 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: 127
# Total code points: 173
# ================================================
@ -1453,7 +1465,7 @@ AB70..ABBF ; Cherokee # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETT
1810..1819 ; Mongolian # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE
1820..1842 ; Mongolian # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI
1843 ; Mongolian # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN
1844..1877 ; Mongolian # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA
1844..1878 ; Mongolian # Lo [53] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER CHA WITH TWO DOTS
1880..1884 ; Mongolian # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA
1885..1886 ; Mongolian # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA
1887..18A8 ; Mongolian # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA
@ -1461,7 +1473,7 @@ AB70..ABBF ; Cherokee # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETT
18AA ; Mongolian # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA
11660..1166C ; Mongolian # Po [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT
# Total code points: 166
# Total code points: 167
# ================================================
@ -1490,10 +1502,10 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
# ================================================
02EA..02EB ; Bopomofo # Sk [2] MODIFIER LETTER YIN DEPARTING TONE MARK..MODIFIER LETTER YANG DEPARTING TONE MARK
3105..312E ; Bopomofo # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE
3105..312F ; Bopomofo # Lo [43] BOPOMOFO LETTER B..BOPOMOFO LETTER NN
31A0..31BA ; Bopomofo # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY
# Total code points: 71
# Total code points: 72
# ================================================
@ -1506,7 +1518,7 @@ 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..9FEA ; Han # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
4E00..9FEF ; Han # Lo [20976] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEF
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
@ -1516,7 +1528,7 @@ FA70..FAD9 ; Han # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILI
2CEB0..2EBE0 ; Han # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2F800..2FA1D ; Han # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 89228
# Total code points: 89233
# ================================================
@ -1579,13 +1591,14 @@ FE00..FE0F ; Inherited # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
FE20..FE2D ; Inherited # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON BELOW
101FD ; Inherited # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE
102E0 ; Inherited # Mn COPTIC EPACT THOUSANDS MARK
1133B ; Inherited # Mn COMBINING BINDU BELOW
1D167..1D169 ; Inherited # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3
1D17B..1D182 ; Inherited # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE
1D185..1D18B ; Inherited # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
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: 568
# Total code points: 569
# ================================================
@ -1778,13 +1791,13 @@ A828..A82B ; Syloti_Nagri # So [4] SYLOTI NAGRI POETRY MARK-1..SYLOTI NAGRI
10A0C..10A0F ; Kharoshthi # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA
10A10..10A13 ; Kharoshthi # Lo [4] KHAROSHTHI LETTER KA..KHAROSHTHI LETTER GHA
10A15..10A17 ; Kharoshthi # Lo [3] KHAROSHTHI LETTER CA..KHAROSHTHI LETTER JA
10A19..10A33 ; Kharoshthi # Lo [27] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER TTTHA
10A19..10A35 ; Kharoshthi # Lo [29] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER VHA
10A38..10A3A ; Kharoshthi # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW
10A3F ; Kharoshthi # Mn KHAROSHTHI VIRAMA
10A40..10A47 ; Kharoshthi # No [8] KHAROSHTHI DIGIT ONE..KHAROSHTHI NUMBER ONE THOUSAND
10A40..10A48 ; Kharoshthi # No [9] KHAROSHTHI DIGIT ONE..KHAROSHTHI FRACTION ONE HALF
10A50..10A58 ; Kharoshthi # Po [9] KHAROSHTHI PUNCTUATION DOT..KHAROSHTHI PUNCTUATION LINES
# Total code points: 65
# Total code points: 68
# ================================================
@ -1841,8 +1854,10 @@ A874..A877 ; Phags_Pa # Po [4] PHAGS-PA SINGLE HEAD MARK..PHAGS-PA MARK DOU
07F6 ; Nko # So NKO SYMBOL OO DENNEN
07F7..07F9 ; Nko # Po [3] NKO SYMBOL GBAKURUNEN..NKO EXCLAMATION MARK
07FA ; Nko # Lm NKO LAJANYALAN
07FD ; Nko # Mn NKO DANTAYALAN
07FE..07FF ; Nko # Sc [2] NKO DOROME SIGN..NKO TAMAN SIGN
# Total code points: 59
# Total code points: 62
# ================================================
@ -2137,8 +2152,9 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
110BB..110BC ; Kaithi # Po [2] KAITHI ABBREVIATION SIGN..KAITHI ENUMERATION SIGN
110BD ; Kaithi # Cf KAITHI NUMBER SIGN
110BE..110C1 ; Kaithi # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA
110CD ; Kaithi # Cf KAITHI NUMBER SIGN ABOVE
# Total code points: 66
# Total code points: 67
# ================================================
@ -2186,8 +2202,10 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
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
11144 ; Chakma # Lo CHAKMA LETTER LHAA
11145..11146 ; Chakma # Mc [2] CHAKMA VOWEL SIGN AA..CHAKMA VOWEL SIGN EI
# Total code points: 67
# Total code points: 70
# ================================================
@ -2224,8 +2242,8 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
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..111C9 ; Sharada # Po [5] SHARADA DANDA..SHARADA SANDHI MARK
111CA..111CC ; Sharada # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK
111C5..111C8 ; Sharada # Po [4] SHARADA DANDA..SHARADA SEPARATOR
111C9..111CC ; Sharada # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK
111CD ; Sharada # Po SHARADA SUTRA MARK
111D0..111D9 ; Sharada # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE
111DA ; Sharada # Lo SHARADA EKAM
@ -2502,7 +2520,7 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
# ================================================
11700..11719 ; Ahom # Lo [26] AHOM LETTER KA..AHOM LETTER JHA
11700..1171A ; Ahom # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA
1171D..1171F ; Ahom # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA
11720..11721 ; Ahom # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA
11722..11725 ; Ahom # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
@ -2513,7 +2531,7 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
1173C..1173E ; Ahom # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI
1173F ; Ahom # So AHOM SYMBOL VI
# Total code points: 57
# Total code points: 58
# ================================================
@ -2618,8 +2636,9 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
11450..11459 ; Newa # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE
1145B ; Newa # Po NEWA PLACEHOLDER MARK
1145D ; Newa # Po NEWA INSERTION SIGN
1145E ; Newa # Mn NEWA SANDHI MARK
# Total code points: 92
# Total code points: 93
# ================================================
@ -2631,10 +2650,10 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
# ================================================
16FE0 ; Tangut # Lm TANGUT ITERATION MARK
17000..187EC ; Tangut # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC
17000..187F1 ; Tangut # Lo [6130] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F1
18800..18AF2 ; Tangut # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
# Total code points: 6881
# Total code points: 6886
# ================================================
@ -2670,16 +2689,15 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
11A97 ; Soyombo # Mc SOYOMBO SIGN VISARGA
11A98..11A99 ; Soyombo # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER
11A9A..11A9C ; Soyombo # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD
11A9D ; Soyombo # Lo SOYOMBO MARK PLUTA
11A9E..11AA2 ; Soyombo # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2
# Total code points: 80
# Total code points: 81
# ================================================
11A00 ; Zanabazar_Square # Lo ZANABAZAR SQUARE LETTER A
11A01..11A06 ; Zanabazar_Square # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O
11A07..11A08 ; Zanabazar_Square # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU
11A09..11A0A ; Zanabazar_Square # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK
11A01..11A0A ; Zanabazar_Square # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK
11A0B..11A32 ; Zanabazar_Square # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA
11A33..11A38 ; Zanabazar_Square # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA
11A39 ; Zanabazar_Square # Mc ZANABAZAR SQUARE SIGN VISARGA
@ -2690,4 +2708,73 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
# Total code points: 72
# ================================================
11800..1182B ; Dogra # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA
1182C..1182E ; Dogra # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II
1182F..11837 ; Dogra # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA
11838 ; Dogra # Mc DOGRA SIGN VISARGA
11839..1183A ; Dogra # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA
1183B ; Dogra # Po DOGRA ABBREVIATION SIGN
# Total code points: 60
# ================================================
11D60..11D65 ; Gunjala_Gondi # Lo [6] GUNJALA GONDI LETTER A..GUNJALA GONDI LETTER UU
11D67..11D68 ; Gunjala_Gondi # Lo [2] GUNJALA GONDI LETTER EE..GUNJALA GONDI LETTER AI
11D6A..11D89 ; Gunjala_Gondi # Lo [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA
11D8A..11D8E ; Gunjala_Gondi # Mc [5] GUNJALA GONDI VOWEL SIGN AA..GUNJALA GONDI VOWEL SIGN UU
11D90..11D91 ; Gunjala_Gondi # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI
11D93..11D94 ; Gunjala_Gondi # Mc [2] GUNJALA GONDI VOWEL SIGN OO..GUNJALA GONDI VOWEL SIGN AU
11D95 ; Gunjala_Gondi # Mn GUNJALA GONDI SIGN ANUSVARA
11D96 ; Gunjala_Gondi # Mc GUNJALA GONDI SIGN VISARGA
11D97 ; Gunjala_Gondi # Mn GUNJALA GONDI VIRAMA
11D98 ; Gunjala_Gondi # Lo GUNJALA GONDI OM
11DA0..11DA9 ; Gunjala_Gondi # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE
# Total code points: 63
# ================================================
11EE0..11EF2 ; Makasar # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA
11EF3..11EF4 ; Makasar # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
11EF5..11EF6 ; Makasar # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
11EF7..11EF8 ; Makasar # Po [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION
# Total code points: 25
# ================================================
16E40..16E7F ; Medefaidrin # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y
16E80..16E96 ; Medefaidrin # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM
16E97..16E9A ; Medefaidrin # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH
# Total code points: 91
# ================================================
10D00..10D23 ; Hanifi_Rohingya # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA
10D24..10D27 ; Hanifi_Rohingya # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
10D30..10D39 ; Hanifi_Rohingya # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE
# Total code points: 50
# ================================================
10F30..10F45 ; Sogdian # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN
10F46..10F50 ; Sogdian # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW
10F51..10F54 ; Sogdian # No [4] SOGDIAN NUMBER ONE..SOGDIAN NUMBER ONE HUNDRED
10F55..10F59 ; Sogdian # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT
# Total code points: 42
# ================================================
10F00..10F1C ; Old_Sogdian # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL
10F1D..10F26 ; Old_Sogdian # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF
10F27 ; Old_Sogdian # Lo OLD SOGDIAN LIGATURE AYIN-DALETH
# Total code points: 40
# EOF

8
make/data/unicodedata/SpecialCasing.txt
View File

@ -1,6 +1,6 @@
# SpecialCasing-10.0.0.txt
# Date: 2017-04-14, 05:40:43 GMT
# Copyright (c) 2017 Unicode, Inc.
# SpecialCasing-11.0.0.txt
# Date: 2018-02-22, 06:16:47 GMT
# Copyright (c) 2018 Unicode, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
@ -121,7 +121,7 @@ FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH
# The following cases are already in the UnicodeData.txt file, so are only commented here.
# 0345; 0345; 0345; 0399; # COMBINING GREEK YPOGEGRAMMENI
# 0345; 0345; 0399; 0399; # COMBINING GREEK YPOGEGRAMMENI
# All letters with YPOGEGRAMMENI (iota-subscript) or PROSGEGRAMMENI (iota adscript)
# have special uppercases.

778
make/data/unicodedata/UnicodeData.txt
View File

File diff suppressed because it is too large Load Diff

2
make/data/unicodedata/VERSION
View File

@ -1 +1 @@
10.0.0
11.0.0

579
src/java.base/share/classes/java/lang/Character.java
View File

File diff suppressed because it is too large Load Diff

47
src/java.base/share/classes/sun/text/normalizer/ICUBinary.java
View File

@ -86,12 +86,47 @@ public final class ICUBinary {
}
})) {
BufferedInputStream b=new BufferedInputStream(is, 4096 /* data buffer size */);
DataInputStream inputStream = new DataInputStream(b);
byte[] bb = new byte[130000];
int n = inputStream.read(bb);
ByteBuffer bytes = ByteBuffer.wrap(bb, 0, n);
return bytes;
// is.available() may return 0, or 1, or the total number of bytes in the stream,
// or some other number.
// Do not try to use is.available() == 0 to find the end of the stream!
byte[] bytes;
int avail = is.available();
if (avail > 32) {
// There are more bytes available than just the ICU data header length.
// With luck, it is the total number of bytes.
bytes = new byte[avail];
} else {
bytes = new byte[128]; // empty .res files are even smaller
}
// Call is.read(...) until one returns a negative value.
int length = 0;
for(;;) {
if (length < bytes.length) {
int numRead = is.read(bytes, length, bytes.length - length);
if (numRead < 0) {
break; // end of stream
}
length += numRead;
} else {
// See if we are at the end of the stream before we grow the array.
int nextByte = is.read();
if (nextByte < 0) {
break;
}
int capacity = 2 * bytes.length;
if (capacity < 128) {
capacity = 128;
} else if (capacity < 0x4000) {
capacity *= 2; // Grow faster until we reach 16kB.
}
// TODO Java 6 replace new byte[] and arraycopy(): bytes = Arrays.copyOf(bytes, capacity);
byte[] newBytes = new byte[capacity];
System.arraycopy(bytes, 0, newBytes, 0, length);
bytes = newBytes;
bytes[length++] = (byte) nextByte;
}
}
return ByteBuffer.wrap(bytes, 0, length);
}
catch (IOException e) {
throw new UncheckedIOException(e);

BIN
src/java.base/share/classes/sun/text/resources/nfc.icu
View File

Binary file not shown.

BIN
src/java.base/share/classes/sun/text/resources/nfkc.icu
View File

Binary file not shown.

BIN
src/java.base/share/classes/sun/text/resources/nfkc_cf.icu
View File

Binary file not shown.

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

Binary file not shown.

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

Binary file not shown.

2
src/java.base/share/legal/icu.md
View File

@ -1,4 +1,4 @@
## International Components for Unicode (ICU4J) v60.2
## International Components for Unicode (ICU4J) v62.1
### ICU4J License

2
src/java.base/share/legal/unicode.md
View File

@ -1,4 +1,4 @@
## The Unicode Standard, Unicode Character Database, Version 10.0.0
## The Unicode Standard, Unicode Character Database, Version 11.0.0
### Unicode Character Database

64
src/java.desktop/share/classes/java/awt/font/NumericShaper.java
View File

@ -649,8 +649,6 @@ public final class NumericShaper implements java.io.Serializable {
0x0483, 0x048a,
0x0530, 0x0531,
0x0557, 0x0559,
0x0560, 0x0561,
0x0588, 0x0589,
0x058a, 0x0590,
0x0591, 0x05be,
0x05bf, 0x05c0,
@ -671,6 +669,7 @@ public final class NumericShaper implements java.io.Serializable {
0x07a6, 0x07b1,
0x07eb, 0x07f4,
0x07f6, 0x07fa,
0x07fd, 0x07fe,
0x0816, 0x081a,
0x081b, 0x0824,
0x0825, 0x0828,
@ -713,7 +712,8 @@ public final class NumericShaper implements java.io.Serializable {
0x0a5d, 0x0a5e,
0x0a5f, 0x0a66,
0x0a70, 0x0a72,
0x0a75, 0x0a83,
0x0a75, 0x0a76,
0x0a73, 0x0a83,
0x0a84, 0x0a85,
0x0a8e, 0x0a8f,
0x0a92, 0x0a93,
@ -771,7 +771,6 @@ public final class NumericShaper implements java.io.Serializable {
0x0c62, 0x0c66,
0x0c70, 0x0c7f,
0x0c81, 0x0c82,
0x0c84, 0x0c85,
0x0c8d, 0x0c8e,
0x0c91, 0x0c92,
0x0ca9, 0x0caa,
@ -890,7 +889,7 @@ public final class NumericShaper implements java.io.Serializable {
0x17dd, 0x17e0,
0x17ea, 0x1810,
0x181a, 0x1820,
0x1878, 0x1884,
0x1879, 0x1884,
0x1885, 0x1887,
0x18a9, 0x18aa,
0x18ab, 0x18b0,
@ -933,6 +932,8 @@ public final class NumericShaper implements java.io.Serializable {
0x1c2c, 0x1c34,
0x1c36, 0x1c3b,
0x1c4a, 0x1c4d,
0x1c89, 0x1c90,
0x1cbb, 0x1cbd,
0x1cc8, 0x1cd3,
0x1cd4, 0x1ce1,
0x1ce2, 0x1ce9,
@ -1010,7 +1011,7 @@ public final class NumericShaper implements java.io.Serializable {
0x30a0, 0x30a1,
0x30fb, 0x30fc,
0x3100, 0x3105,
0x312f, 0x3131,
0x3130, 0x3131,
0x318f, 0x3190,
0x31bb, 0x31f0,
0x321d, 0x3220,
@ -1023,7 +1024,7 @@ public final class NumericShaper implements java.io.Serializable {
0x33de, 0x33e0,
0x33ff, 0x3400,
0x4db6, 0x4e00,
0x9feb, 0xa000,
0x9ff0, 0xa000,
0xa48d, 0xa4d0,
0xa60d, 0xa610,
0xa62c, 0xa640,
@ -1032,8 +1033,7 @@ public final class NumericShaper implements java.io.Serializable {
0xa6f0, 0xa6f2,
0xa6f8, 0xa722,
0xa788, 0xa789,
0xa7af, 0xa7b0,
0xa7b8, 0xa7f7,
0xa7ba, 0xa7f7,
0xa802, 0xa803,
0xa806, 0xa807,
0xa80b, 0xa80c,
@ -1043,7 +1043,7 @@ public final class NumericShaper implements java.io.Serializable {
0xa874, 0xa880,
0xa8c4, 0xa8ce,
0xa8da, 0xa8f2,
0xa8fe, 0xa900,
0xa8ff, 0xa900,
0xa926, 0xa92e,
0xa947, 0xa952,
0xa954, 0xa95f,
@ -1141,23 +1141,26 @@ public final class NumericShaper implements java.io.Serializable {
0x10a3f, 0x10a40,
0x10ae5, 0x10ae7,
0x10b39, 0x10b40,
0x10d00, 0x10d40,
0x10e60, 0x10e7f,
0x10f30, 0x10f70,
0x11001, 0x11002,
0x11038, 0x11047,
0x1104e, 0x11066,
0x11070, 0x11082,
0x110b3, 0x110b7,
0x110b9, 0x110bb,
0x110c2, 0x110d0,
0x110c2, 0x110cd,
0x110ce, 0x110d0,
0x110e9, 0x110f0,
0x110fa, 0x11103,
0x11127, 0x1112c,
0x1112d, 0x11136,
0x11144, 0x11150,
0x11147, 0x11150,
0x11173, 0x11174,
0x11177, 0x11182,
0x111b6, 0x111bf,
0x111ca, 0x111cd,
0x111c9, 0x111cd,
0x111ce, 0x111d0,
0x111e0, 0x111e1,
0x111f5, 0x11200,
@ -1214,10 +1217,12 @@ public final class NumericShaper implements java.io.Serializable {
0x116b0, 0x116b6,
0x116b7, 0x116c0,
0x116ca, 0x11700,
0x1171a, 0x11720,
0x1171b, 0x11720,
0x11722, 0x11726,
0x11727, 0x11730,
0x11740, 0x118a0,
0x1182f, 0x11838,
0x11839, 0x1183b,
0x1183c, 0x118a0,
0x118f3, 0x118ff,
0x11900, 0x11a00,
0x11a01, 0x11a07,
@ -1230,10 +1235,9 @@ public final class NumericShaper implements java.io.Serializable {
0x11a84, 0x11a86,
0x11a8a, 0x11a97,
0x11a98, 0x11a9a,
0x11a9d, 0x11a9e,
0x11aa3, 0x11ac0,
0x11af9, 0x11C00,
0x11C09, 0x11c0a,
0x11af9, 0x11c00,
0x11c09, 0x11c0a,
0x11c30, 0x11c3e,
0x11c46, 0x11c50,
0x11c6d, 0x11c70,
@ -1245,7 +1249,16 @@ public final class NumericShaper implements java.io.Serializable {
0x11d0a, 0x11d0b,
0x11d31, 0x11d46,
0x11d47, 0x11d50,
0x11d5a, 0x12000,
0x11d5a, 0x11d60,
0x11d66, 0x11d67,
0x11d69, 0x11d6a,
0x11d8f, 0x11d93,
0x11d95, 0x11d96,
0x11d97, 0x11d98,
0x11d99, 0x11da0,
0x11daa, 0x11ee0,
0x11ef3, 0x11ef5,
0x11ef9, 0x12000,
0x1239a, 0x12400,
0x1246f, 0x12470,
0x12475, 0x12480,
@ -1263,12 +1276,13 @@ public final class NumericShaper implements java.io.Serializable {
0x16b5a, 0x16b5b,
0x16b62, 0x16b63,
0x16b78, 0x16b7d,
0x16b90, 0x16f00,
0x16b90, 0x16e40,
0x16e9b, 0x16f00,
0x16f45, 0x16f50,
0x16f7f, 0x16f93,
0x16fa0, 0x16fe0,
0x16fe2, 0x17000,
0x187ed, 0x18800,
0x187f2, 0x18800,
0x18af3, 0x1b000,
0x1b11f, 0x1b170,
0x1b2fc, 0x1bc00,
@ -1284,8 +1298,9 @@ public final class NumericShaper implements java.io.Serializable {
0x1d173, 0x1d183,
0x1d185, 0x1d18c,
0x1d1aa, 0x1d1ae,
0x1d1e9, 0x1d360,
0x1d372, 0x1d400,
0x1d1e9, 0x1d2e0,
0x1d2f4, 0x1d360,
0x1d379, 0x1d400,
0x1d455, 0x1d456,
0x1d49d, 0x1d49e,
0x1d4a0, 0x1d4a2,
@ -1318,7 +1333,8 @@ public final class NumericShaper implements java.io.Serializable {
0x1da8c, 0x1e800,
0x1e8d0, 0x1e8d7,
0x1e944, 0x1e94b,
0x1eef0, 0x1eef2,
0x1ec70, 0x1ecc0,
0x1ee00, 0x1ef00,
0x1f000, 0x1f110,
0x1f12f, 0x1f130,
0x1f16a, 0x1f170,

77
test/jdk/java/lang/Character/PropList.txt
View File

@ -1,6 +1,6 @@
# PropList-10.0.0.txt
# Date: 2017-03-10, 08:25:30 GMT
# Copyright (c) 2017 Unicode, Inc.
# PropList-11.0.0.txt
# Date: 2018-03-15, 04:28:35 GMT
# Copyright (c) 2018 Unicode, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
@ -125,7 +125,7 @@ FF63 ; Quotation_Mark # Pe HALFWIDTH RIGHT CORNER BRACKET
05C3 ; Terminal_Punctuation # Po HEBREW PUNCTUATION SOF PASUQ
060C ; Terminal_Punctuation # Po ARABIC COMMA
061B ; Terminal_Punctuation # Po ARABIC SEMICOLON
061F ; Terminal_Punctuation # Po ARABIC QUESTION MARK
061E..061F ; Terminal_Punctuation # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK
06D4 ; Terminal_Punctuation # Po ARABIC FULL STOP
0700..070A ; Terminal_Punctuation # Po [11] SYRIAC END OF PARAGRAPH..SYRIAC CONTRACTION
070C ; Terminal_Punctuation # Po SYRIAC HARKLEAN METOBELUS
@ -156,6 +156,8 @@ FF63 ; Quotation_Mark # Pe HALFWIDTH RIGHT CORNER BRACKET
2E2E ; Terminal_Punctuation # Po REVERSED QUESTION MARK
2E3C ; Terminal_Punctuation # Po STENOGRAPHIC FULL STOP
2E41 ; Terminal_Punctuation # Po REVERSED COMMA
2E4C ; Terminal_Punctuation # Po MEDIEVAL COMMA
2E4E ; Terminal_Punctuation # Po PUNCTUS ELEVATUS MARK
3001..3002 ; Terminal_Punctuation # Po [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP
A4FE..A4FF ; Terminal_Punctuation # Po [2] LISU PUNCTUATION COMMA..LISU PUNCTUATION FULL STOP
A60D..A60F ; Terminal_Punctuation # Po [3] VAI COMMA..VAI QUESTION MARK
@ -185,6 +187,7 @@ FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA
10AF0..10AF5 ; Terminal_Punctuation # Po [6] MANICHAEAN PUNCTUATION STAR..MANICHAEAN PUNCTUATION TWO DOTS
10B3A..10B3F ; Terminal_Punctuation # Po [6] TINY TWO DOTS OVER ONE DOT PUNCTUATION..LARGE ONE RING OVER TWO RINGS PUNCTUATION
10B99..10B9C ; Terminal_Punctuation # Po [4] PSALTER PAHLAVI SECTION MARK..PSALTER PAHLAVI FOUR DOTS WITH DOT
10F55..10F59 ; Terminal_Punctuation # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT
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
@ -204,15 +207,17 @@ FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA
11AA1..11AA2 ; Terminal_Punctuation # Po [2] SOYOMBO TERMINAL MARK-1..SOYOMBO TERMINAL MARK-2
11C41..11C43 ; Terminal_Punctuation # Po [3] BHAIKSUKI DANDA..BHAIKSUKI WORD SEPARATOR
11C71 ; Terminal_Punctuation # Po MARCHEN MARK SHAD
11EF7..11EF8 ; Terminal_Punctuation # Po [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION
12470..12474 ; Terminal_Punctuation # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON
16A6E..16A6F ; Terminal_Punctuation # Po [2] MRO DANDA..MRO DOUBLE DANDA
16AF5 ; Terminal_Punctuation # Po BASSA VAH FULL STOP
16B37..16B39 ; Terminal_Punctuation # Po [3] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN CIM CHEEM
16B44 ; Terminal_Punctuation # Po PAHAWH HMONG SIGN XAUS
16E97..16E98 ; Terminal_Punctuation # Po [2] MEDEFAIDRIN COMMA..MEDEFAIDRIN FULL STOP
1BC9F ; Terminal_Punctuation # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP
1DA87..1DA8A ; Terminal_Punctuation # Po [4] SIGNWRITING COMMA..SIGNWRITING COLON
# Total code points: 252
# Total code points: 264
# ================================================
@ -661,6 +666,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
10A01..10A03 ; Other_Alphabetic # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R
10A05..10A06 ; Other_Alphabetic # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O
10A0C..10A0F ; Other_Alphabetic # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA
10D24..10D27 ; Other_Alphabetic # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
11000 ; Other_Alphabetic # Mc BRAHMI SIGN CANDRABINDU
11001 ; Other_Alphabetic # Mn BRAHMI SIGN ANUSVARA
11002 ; Other_Alphabetic # Mc BRAHMI SIGN VISARGA
@ -673,6 +679,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
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
11145..11146 ; Other_Alphabetic # Mc [2] CHAKMA VOWEL SIGN AA..CHAKMA VOWEL SIGN EI
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
@ -730,9 +737,10 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
11722..11725 ; Other_Alphabetic # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
11726 ; Other_Alphabetic # Mc AHOM VOWEL SIGN E
11727..1172A ; Other_Alphabetic # Mn [4] AHOM VOWEL SIGN AW..AHOM VOWEL SIGN AM
11A01..11A06 ; Other_Alphabetic # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O
11A07..11A08 ; Other_Alphabetic # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU
11A09..11A0A ; Other_Alphabetic # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK
1182C..1182E ; Other_Alphabetic # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II
1182F..11837 ; Other_Alphabetic # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA
11838 ; Other_Alphabetic # Mc DOGRA SIGN VISARGA
11A01..11A0A ; Other_Alphabetic # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK
11A35..11A38 ; Other_Alphabetic # Mn [4] ZANABAZAR SQUARE SIGN CANDRABINDU..ZANABAZAR SQUARE SIGN ANUSVARA
11A39 ; Other_Alphabetic # Mc ZANABAZAR SQUARE SIGN VISARGA
11A3B..11A3E ; Other_Alphabetic # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA
@ -758,6 +766,13 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
11D3F..11D41 ; Other_Alphabetic # Mn [3] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI SIGN VISARGA
11D43 ; Other_Alphabetic # Mn MASARAM GONDI SIGN CANDRA
11D47 ; Other_Alphabetic # Mn MASARAM GONDI RA-KARA
11D8A..11D8E ; Other_Alphabetic # Mc [5] GUNJALA GONDI VOWEL SIGN AA..GUNJALA GONDI VOWEL SIGN UU
11D90..11D91 ; Other_Alphabetic # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI
11D93..11D94 ; Other_Alphabetic # Mc [2] GUNJALA GONDI VOWEL SIGN OO..GUNJALA GONDI VOWEL SIGN AU
11D95 ; Other_Alphabetic # Mn GUNJALA GONDI SIGN ANUSVARA
11D96 ; Other_Alphabetic # Mc GUNJALA GONDI SIGN VISARGA
11EF3..11EF4 ; Other_Alphabetic # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
11EF5..11EF6 ; Other_Alphabetic # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
16B30..16B36 ; Other_Alphabetic # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
16F51..16F7E ; Other_Alphabetic # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
1BC9E ; Other_Alphabetic # Mn DUPLOYAN DOUBLE MARK
@ -771,7 +786,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
1F150..1F169 ; Other_Alphabetic # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
1F170..1F189 ; Other_Alphabetic # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z
# Total code points: 1300
# Total code points: 1334
# ================================================
@ -780,10 +795,10 @@ 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..9FEA ; Ideographic # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
4E00..9FEF ; Ideographic # Lo [20976] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEF
F900..FA6D ; Ideographic # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D
FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9
17000..187EC ; Ideographic # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC
17000..187F1 ; Ideographic # Lo [6130] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F1
18800..18AF2 ; Ideographic # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
1B170..1B2FB ; Ideographic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
20000..2A6D6 ; Ideographic # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
@ -793,7 +808,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
2CEB0..2EBE0 ; Ideographic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 96174
# Total code points: 96184
# ================================================
@ -953,6 +968,9 @@ FF9E..FF9F ; Diacritic # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFW
FFE3 ; Diacritic # Sk FULLWIDTH MACRON
102E0 ; Diacritic # Mn COPTIC EPACT THOUSANDS MARK
10AE5..10AE6 ; Diacritic # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW
10D22..10D23 ; Diacritic # Lo [2] HANIFI ROHINGYA MARK SAKIN..HANIFI ROHINGYA MARK NA KHONNA
10D24..10D27 ; Diacritic # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
10F46..10F50 ; Diacritic # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW
110B9..110BA ; Diacritic # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA
11133..11134 ; Diacritic # Mn [2] CHAKMA VIRAMA..CHAKMA MAAYYAA
11173 ; Diacritic # Mn MAHAJANI SIGN NUKTA
@ -973,12 +991,14 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON
116B6 ; Diacritic # Mc TAKRI SIGN VIRAMA
116B7 ; Diacritic # Mn TAKRI SIGN NUKTA
1172B ; Diacritic # Mn AHOM SIGN KILLER
11839..1183A ; Diacritic # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA
11A34 ; Diacritic # Mn ZANABAZAR SQUARE SIGN VIRAMA
11A47 ; Diacritic # Mn ZANABAZAR SQUARE SUBJOINER
11A99 ; Diacritic # Mn SOYOMBO SUBJOINER
11C3F ; Diacritic # Mn BHAIKSUKI SIGN VIRAMA
11D42 ; Diacritic # Mn MASARAM GONDI SIGN NUKTA
11D44..11D45 ; Diacritic # Mn [2] MASARAM GONDI SIGN HALANTA..MASARAM GONDI VIRAMA
11D97 ; Diacritic # Mn GUNJALA GONDI VIRAMA
16AF0..16AF4 ; Diacritic # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
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
@ -991,7 +1011,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON
1E944..1E946 ; Diacritic # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK
1E948..1E94A ; Diacritic # Mn [3] ADLAM CONSONANT MODIFIER..ADLAM NUKTA
# Total code points: 798
# Total code points: 818
# ================================================
@ -1137,7 +1157,7 @@ E0020..E007F ; Other_Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG
# ================================================
3400..4DB5 ; Unified_Ideograph # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4E00..9FEA ; Unified_Ideograph # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
4E00..9FEF ; Unified_Ideograph # Lo [20976] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEF
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
@ -1151,7 +1171,7 @@ FA27..FA29 ; Unified_Ideograph # Lo [3] CJK COMPATIBILITY IDEOGRAPH-FA27..C
2B820..2CEA1 ; Unified_Ideograph # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
2CEB0..2EBE0 ; Unified_Ideograph # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
# Total code points: 87882
# Total code points: 87887
# ================================================
@ -1255,10 +1275,13 @@ AABB..AABC ; Logical_Order_Exception # Lo [2] TAI VIET VOWEL AUE..TAI VIET
002E ; Sentence_Terminal # Po FULL STOP
003F ; Sentence_Terminal # Po QUESTION MARK
0589 ; Sentence_Terminal # Po ARMENIAN FULL STOP
061F ; Sentence_Terminal # Po ARABIC QUESTION MARK
061E..061F ; Sentence_Terminal # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK
06D4 ; Sentence_Terminal # Po ARABIC FULL STOP
0700..0702 ; Sentence_Terminal # Po [3] SYRIAC END OF PARAGRAPH..SYRIAC SUBLINEAR FULL STOP
07F9 ; Sentence_Terminal # Po NKO EXCLAMATION MARK
0837 ; Sentence_Terminal # Po SAMARITAN PUNCTUATION MELODIC QITSA
0839 ; Sentence_Terminal # Po SAMARITAN PUNCTUATION QITSA
083D..083E ; Sentence_Terminal # Po [2] SAMARITAN PUNCTUATION SOF MASHFAAT..SAMARITAN PUNCTUATION ANNAAU
0964..0965 ; Sentence_Terminal # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA
104A..104B ; Sentence_Terminal # Po [2] MYANMAR SIGN LITTLE SECTION..MYANMAR SIGN SECTION
1362 ; Sentence_Terminal # Po ETHIOPIC FULL STOP
@ -1296,6 +1319,7 @@ FF0E ; Sentence_Terminal # Po FULLWIDTH FULL STOP
FF1F ; Sentence_Terminal # Po FULLWIDTH QUESTION MARK
FF61 ; Sentence_Terminal # Po HALFWIDTH IDEOGRAPHIC FULL STOP
10A56..10A57 ; Sentence_Terminal # Po [2] KHAROSHTHI PUNCTUATION DANDA..KHAROSHTHI PUNCTUATION DOUBLE DANDA
10F55..10F59 ; Sentence_Terminal # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT
11047..11048 ; Sentence_Terminal # Po [2] BRAHMI DANDA..BRAHMI DOUBLE DANDA
110BE..110C1 ; Sentence_Terminal # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA
11141..11143 ; Sentence_Terminal # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK
@ -1313,14 +1337,16 @@ FF61 ; Sentence_Terminal # Po HALFWIDTH IDEOGRAPHIC FULL STOP
11A42..11A43 ; Sentence_Terminal # Po [2] ZANABAZAR SQUARE MARK SHAD..ZANABAZAR SQUARE MARK DOUBLE SHAD
11A9B..11A9C ; Sentence_Terminal # Po [2] SOYOMBO MARK SHAD..SOYOMBO MARK DOUBLE SHAD
11C41..11C42 ; Sentence_Terminal # Po [2] BHAIKSUKI DANDA..BHAIKSUKI DOUBLE DANDA
11EF7..11EF8 ; Sentence_Terminal # Po [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION
16A6E..16A6F ; Sentence_Terminal # Po [2] MRO DANDA..MRO DOUBLE DANDA
16AF5 ; Sentence_Terminal # Po BASSA VAH FULL STOP
16B37..16B38 ; Sentence_Terminal # Po [2] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN VOS TSHAB CEEB
16B44 ; Sentence_Terminal # Po PAHAWH HMONG SIGN XAUS
16E98 ; Sentence_Terminal # Po MEDEFAIDRIN FULL STOP
1BC9F ; Sentence_Terminal # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP
1DA88 ; Sentence_Terminal # Po SIGNWRITING FULL STOP
# Total code points: 128
# Total code points: 141
# ================================================
@ -1521,14 +1547,10 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S
2B74..2B75 ; Pattern_Syntax # Cn [2] <reserved-2B74>..<reserved-2B75>
2B76..2B95 ; Pattern_Syntax # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW
2B96..2B97 ; Pattern_Syntax # Cn [2] <reserved-2B96>..<reserved-2B97>
2B98..2BB9 ; Pattern_Syntax # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX
2BBA..2BBC ; Pattern_Syntax # Cn [3] <reserved-2BBA>..<reserved-2BBC>
2BBD..2BC8 ; Pattern_Syntax # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
2B98..2BC8 ; Pattern_Syntax # So [49] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
2BC9 ; Pattern_Syntax # Cn <reserved-2BC9>
2BCA..2BD2 ; Pattern_Syntax # So [9] TOP HALF BLACK CIRCLE..GROUP MARK
2BD3..2BEB ; Pattern_Syntax # Cn [25] <reserved-2BD3>..<reserved-2BEB>
2BEC..2BEF ; Pattern_Syntax # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS
2BF0..2BFF ; Pattern_Syntax # Cn [16] <reserved-2BF0>..<reserved-2BFF>
2BCA..2BFE ; Pattern_Syntax # So [53] TOP HALF BLACK CIRCLE..REVERSED RIGHT ANGLE
2BFF ; Pattern_Syntax # Cn <reserved-2BFF>
2E00..2E01 ; Pattern_Syntax # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER
2E02 ; Pattern_Syntax # Pi LEFT SUBSTITUTION BRACKET
2E03 ; Pattern_Syntax # Pf RIGHT SUBSTITUTION BRACKET
@ -1566,8 +1588,8 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S
2E40 ; Pattern_Syntax # Pd DOUBLE HYPHEN
2E41 ; Pattern_Syntax # Po REVERSED COMMA
2E42 ; Pattern_Syntax # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK
2E43..2E49 ; Pattern_Syntax # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA
2E4A..2E7F ; Pattern_Syntax # Cn [54] <reserved-2E4A>..<reserved-2E7F>
2E43..2E4E ; Pattern_Syntax # Po [12] DASH WITH LEFT UPTURN..PUNCTUS ELEVATUS MARK
2E4F..2E7F ; Pattern_Syntax # Cn [49] <reserved-2E4F>..<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
@ -1606,8 +1628,9 @@ FE45..FE46 ; Pattern_Syntax # Po [2] SESAME DOT..WHITE SESAME DOT
070F ; Prepended_Concatenation_Mark # Cf SYRIAC ABBREVIATION MARK
08E2 ; Prepended_Concatenation_Mark # Cf ARABIC DISPUTED END OF AYAH
110BD ; Prepended_Concatenation_Mark # Cf KAITHI NUMBER SIGN
110CD ; Prepended_Concatenation_Mark # Cf KAITHI NUMBER SIGN ABOVE
# Total code points: 10
# Total code points: 11
# ================================================

33
test/jdk/java/lang/Character/PropertyValueAliases.txt
View File

@ -1,6 +1,6 @@
# PropertyValueAliases-10.0.0.txt
# Date: 2017-05-17, 08:45:34 GMT
# Copyright (c) 2017 Unicode, Inc.
# PropertyValueAliases-11.0.0.txt
# Date: 2018-05-20, 09:03:12 GMT
# Copyright (c) 2018 Unicode, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
@ -81,6 +81,7 @@ age; 7.0 ; V7_0
age; 8.0 ; V8_0
age; 9.0 ; V9_0
age; 10.0 ; V10_0
age; 11.0 ; V11_0
age; NA ; Unassigned
# Alphabetic (Alpha)
@ -182,6 +183,7 @@ blk; Chakma ; Chakma
blk; Cham ; Cham
blk; Cherokee ; Cherokee
blk; Cherokee_Sup ; Cherokee_Supplement
blk; Chess_Symbols ; Chess_Symbols
blk; CJK ; CJK_Unified_Ideographs
blk; CJK_Compat ; CJK_Compatibility
blk; CJK_Compat_Forms ; CJK_Compatibility_Forms
@ -218,6 +220,7 @@ blk; Diacriticals_Ext ; Combining_Diacritical_Marks_Extended
blk; Diacriticals_For_Symbols ; Combining_Diacritical_Marks_For_Symbols; Combining_Marks_For_Symbols
blk; Diacriticals_Sup ; Combining_Diacritical_Marks_Supplement
blk; Dingbats ; Dingbats
blk; Dogra ; Dogra
blk; Domino ; Domino_Tiles
blk; Duployan ; Duployan
blk; Early_Dynastic_Cuneiform ; Early_Dynastic_Cuneiform
@ -235,6 +238,7 @@ blk; Ethiopic_Sup ; Ethiopic_Supplement
blk; Geometric_Shapes ; Geometric_Shapes
blk; Geometric_Shapes_Ext ; Geometric_Shapes_Extended
blk; Georgian ; Georgian
blk; Georgian_Ext ; Georgian_Extended
blk; Georgian_Sup ; Georgian_Supplement
blk; Glagolitic ; Glagolitic
blk; Glagolitic_Sup ; Glagolitic_Supplement
@ -243,10 +247,12 @@ blk; Grantha ; Grantha
blk; Greek ; Greek_And_Coptic
blk; Greek_Ext ; Greek_Extended
blk; Gujarati ; Gujarati
blk; Gunjala_Gondi ; Gunjala_Gondi
blk; Gurmukhi ; Gurmukhi
blk; Half_And_Full_Forms ; Halfwidth_And_Fullwidth_Forms
blk; Half_Marks ; Combining_Half_Marks
blk; Hangul ; Hangul_Syllables
blk; Hanifi_Rohingya ; Hanifi_Rohingya
blk; Hanunoo ; Hanunoo
blk; Hatran ; Hatran
blk; Hebrew ; Hebrew
@ -257,6 +263,7 @@ blk; IDC ; Ideographic_Description_Characters
blk; Ideographic_Symbols ; Ideographic_Symbols_And_Punctuation
blk; Imperial_Aramaic ; Imperial_Aramaic
blk; Indic_Number_Forms ; Common_Indic_Number_Forms
blk; Indic_Siyaq_Numbers ; Indic_Siyaq_Numbers
blk; Inscriptional_Pahlavi ; Inscriptional_Pahlavi
blk; Inscriptional_Parthian ; Inscriptional_Parthian
blk; IPA_Ext ; IPA_Extensions
@ -298,6 +305,7 @@ blk; Lycian ; Lycian
blk; Lydian ; Lydian
blk; Mahajani ; Mahajani
blk; Mahjong ; Mahjong_Tiles
blk; Makasar ; Makasar
blk; Malayalam ; Malayalam
blk; Mandaic ; Mandaic
blk; Manichaean ; Manichaean
@ -305,6 +313,8 @@ blk; Marchen ; Marchen
blk; Masaram_Gondi ; Masaram_Gondi
blk; Math_Alphanum ; Mathematical_Alphanumeric_Symbols
blk; Math_Operators ; Mathematical_Operators
blk; Mayan_Numerals ; Mayan_Numerals
blk; Medefaidrin ; Medefaidrin
blk; Meetei_Mayek ; Meetei_Mayek
blk; Meetei_Mayek_Ext ; Meetei_Mayek_Extensions
blk; Mende_Kikakui ; Mende_Kikakui
@ -343,6 +353,7 @@ blk; Old_Italic ; Old_Italic
blk; Old_North_Arabian ; Old_North_Arabian
blk; Old_Permic ; Old_Permic
blk; Old_Persian ; Old_Persian
blk; Old_Sogdian ; Old_Sogdian
blk; Old_South_Arabian ; Old_South_Arabian
blk; Old_Turkic ; Old_Turkic
blk; Oriya ; Oriya
@ -373,6 +384,7 @@ blk; Siddham ; Siddham
blk; Sinhala ; Sinhala
blk; Sinhala_Archaic_Numbers ; Sinhala_Archaic_Numbers
blk; Small_Forms ; Small_Form_Variants
blk; Sogdian ; Sogdian
blk; Sora_Sompeng ; Sora_Sompeng
blk; Soyombo ; Soyombo
blk; Specials ; Specials
@ -586,6 +598,10 @@ ea ; N ; Neutral
ea ; Na ; Narrow
ea ; W ; Wide
# Equivalent_Unified_Ideograph (EqUIdeo)
# @missing: 0000..10FFFF; Equivalent_Unified_Ideograph; <none>
# Expands_On_NFC (XO_NFC)
XO_NFC; N ; No ; F ; False
@ -774,6 +790,7 @@ InSC; Consonant ; Consonant
InSC; Consonant_Dead ; Consonant_Dead
InSC; Consonant_Final ; Consonant_Final
InSC; Consonant_Head_Letter ; Consonant_Head_Letter
InSC; Consonant_Initial_Postfixed ; Consonant_Initial_Postfixed
InSC; Consonant_Killer ; Consonant_Killer
InSC; Consonant_Medial ; Consonant_Medial
InSC; Consonant_Placeholder ; Consonant_Placeholder
@ -884,6 +901,8 @@ jg ; Final_Semkath ; Final_Semkath
jg ; Gaf ; Gaf
jg ; Gamal ; Gamal
jg ; Hah ; Hah
jg ; Hanifi_Rohingya_Kinna_Ya ; Hanifi_Rohingya_Kinna_Ya
jg ; Hanifi_Rohingya_Pa ; Hanifi_Rohingya_Pa
jg ; He ; He
jg ; Heh ; Heh
jg ; Heh_Goal ; Heh_Goal
@ -1189,6 +1208,7 @@ sc ; Copt ; Coptic ; Qaac
sc ; Cprt ; Cypriot
sc ; Cyrl ; Cyrillic
sc ; Deva ; Devanagari
sc ; Dogr ; Dogra
sc ; Dsrt ; Deseret
sc ; Dupl ; Duployan
sc ; Egyp ; Egyptian_Hieroglyphs
@ -1196,6 +1216,7 @@ sc ; Elba ; Elbasan
sc ; Ethi ; Ethiopic
sc ; Geor ; Georgian
sc ; Glag ; Glagolitic
sc ; Gong ; Gunjala_Gondi
sc ; Gonm ; Masaram_Gondi
sc ; Goth ; Gothic
sc ; Gran ; Grantha
@ -1232,9 +1253,11 @@ sc ; Lisu ; Lisu
sc ; Lyci ; Lycian
sc ; Lydi ; Lydian
sc ; Mahj ; Mahajani
sc ; Maka ; Makasar
sc ; Mand ; Mandaic
sc ; Mani ; Manichaean
sc ; Marc ; Marchen
sc ; Medf ; Medefaidrin
sc ; Mend ; Mende_Kikakui
sc ; Merc ; Meroitic_Cursive
sc ; Mero ; Meroitic_Hieroglyphs
@ -1266,6 +1289,7 @@ sc ; Phnx ; Phoenician
sc ; Plrd ; Miao
sc ; Prti ; Inscriptional_Parthian
sc ; Rjng ; Rejang
sc ; Rohg ; Hanifi_Rohingya
sc ; Runr ; Runic
sc ; Samr ; Samaritan
sc ; Sarb ; Old_South_Arabian
@ -1276,6 +1300,8 @@ sc ; Shrd ; Sharada
sc ; Sidd ; Siddham
sc ; Sind ; Khudawadi
sc ; Sinh ; Sinhala
sc ; Sogd ; Sogdian
sc ; Sogo ; Old_Sogdian
sc ; Sora ; Sora_Sompeng
sc ; Soyo ; Soyombo
sc ; Sund ; Sundanese
@ -1420,6 +1446,7 @@ WB ; NL ; Newline
WB ; NU ; Numeric
WB ; RI ; Regional_Indicator
WB ; SQ ; Single_Quote
WB ; WSegSpace ; WSegSpace
WB ; XX ; Other
WB ; ZWJ ; ZWJ

209
test/jdk/java/lang/Character/Scripts.txt
View File

@ -1,6 +1,6 @@
# Scripts-10.0.0.txt
# Date: 2017-03-11, 06:40:37 GMT
# Copyright (c) 2017 Unicode, Inc.
# Scripts-11.0.0.txt
# Date: 2018-02-21, 05:34:31 GMT
# Copyright (c) 2018 Unicode, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
@ -308,10 +308,8 @@
2B47..2B4C ; Common # Sm [6] REVERSE TILDE OPERATOR ABOVE RIGHTWARDS ARROW..RIGHTWARDS ARROW ABOVE REVERSE TILDE OPERATOR
2B4D..2B73 ; Common # So [39] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR
2B76..2B95 ; Common # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW
2B98..2BB9 ; Common # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX
2BBD..2BC8 ; Common # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
2BCA..2BD2 ; Common # So [9] TOP HALF BLACK CIRCLE..GROUP MARK
2BEC..2BEF ; Common # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS
2B98..2BC8 ; Common # So [49] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
2BCA..2BFE ; Common # So [53] TOP HALF BLACK CIRCLE..REVERSED RIGHT ANGLE
2E00..2E01 ; Common # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER
2E02 ; Common # Pi LEFT SUBSTITUTION BRACKET
2E03 ; Common # Pf RIGHT SUBSTITUTION BRACKET
@ -349,7 +347,7 @@
2E40 ; Common # Pd DOUBLE HYPHEN
2E41 ; Common # Po REVERSED COMMA
2E42 ; Common # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK
2E43..2E49 ; Common # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA
2E43..2E4E ; Common # Po [12] DASH WITH LEFT UPTURN..PUNCTUS ELEVATUS MARK
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
@ -523,8 +521,9 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1D183..1D184 ; Common # So [2] MUSICAL SYMBOL ARPEGGIATO UP..MUSICAL SYMBOL ARPEGGIATO DOWN
1D18C..1D1A9 ; Common # So [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH
1D1AE..1D1E8 ; Common # So [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN
1D2E0..1D2F3 ; Common # No [20] MAYAN NUMERAL ZERO..MAYAN NUMERAL NINETEEN
1D300..1D356 ; Common # So [87] MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING
1D360..1D371 ; Common # No [18] COUNTING ROD UNIT DIGIT ONE..COUNTING ROD TENS DIGIT NINE
1D360..1D378 ; Common # No [25] COUNTING ROD UNIT DIGIT ONE..TALLY MARK FIVE
1D400..1D454 ; Common # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G
1D456..1D49C ; Common # L& [71] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL SCRIPT CAPITAL A
1D49E..1D49F ; Common # L& [2] MATHEMATICAL SCRIPT CAPITAL C..MATHEMATICAL SCRIPT CAPITAL D
@ -566,6 +565,11 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1D7C3 ; Common # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL
1D7C4..1D7CB ; Common # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA
1D7CE..1D7FF ; Common # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
1EC71..1ECAB ; Common # No [59] INDIC SIYAQ NUMBER ONE..INDIC SIYAQ NUMBER PREFIXED NINE
1ECAC ; Common # So INDIC SIYAQ PLACEHOLDER
1ECAD..1ECAF ; Common # No [3] INDIC SIYAQ FRACTION ONE QUARTER..INDIC SIYAQ FRACTION THREE QUARTERS
1ECB0 ; Common # Sc INDIC SIYAQ RUPEE MARK
1ECB1..1ECB4 ; Common # No [4] INDIC SIYAQ NUMBER ALTERNATE ONE..INDIC SIYAQ ALTERNATE LAKH MARK
1F000..1F02B ; Common # So [44] MAHJONG TILE EAST WIND..MAHJONG TILE BACK
1F030..1F093 ; Common # So [100] DOMINO TILE HORIZONTAL BACK..DOMINO TILE VERTICAL-06-06
1F0A0..1F0AE ; Common # So [15] PLAYING CARD BACK..PLAYING CARD KING OF SPADES
@ -573,8 +577,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1F0C1..1F0CF ; Common # So [15] PLAYING CARD ACE OF DIAMONDS..PLAYING CARD BLACK JOKER
1F0D1..1F0F5 ; Common # So [37] PLAYING CARD ACE OF CLUBS..PLAYING CARD TRUMP-21
1F100..1F10C ; Common # No [13] DIGIT ZERO FULL STOP..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO
1F110..1F12E ; Common # So [31] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED WZ
1F130..1F16B ; Common # So [60] SQUARED LATIN CAPITAL LETTER A..RAISED MD SIGN
1F110..1F16B ; Common # So [92] PARENTHESIZED LATIN CAPITAL LETTER A..RAISED MD SIGN
1F170..1F1AC ; Common # So [61] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VOD
1F1E6..1F1FF ; Common # So [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z
1F201..1F202 ; Common # So [2] SQUARED KATAKANA KOKO..SQUARED KATAKANA SA
@ -586,9 +589,9 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1F3FB..1F3FF ; Common # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
1F400..1F6D4 ; Common # So [725] RAT..PAGODA
1F6E0..1F6EC ; Common # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING
1F6F0..1F6F8 ; Common # So [9] SATELLITE..FLYING SAUCER
1F6F0..1F6F9 ; Common # So [10] SATELLITE..SKATEBOARD
1F700..1F773 ; Common # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
1F780..1F7D4 ; Common # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR
1F780..1F7D8 ; Common # So [89] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NEGATIVE CIRCLED SQUARE
1F800..1F80B ; Common # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD
1F810..1F847 ; Common # So [56] LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW
1F850..1F859 ; Common # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW
@ -596,15 +599,18 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1F890..1F8AD ; Common # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS
1F900..1F90B ; Common # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT
1F910..1F93E ; Common # So [47] ZIPPER-MOUTH FACE..HANDBALL
1F940..1F94C ; Common # So [13] WILTED FLOWER..CURLING STONE
1F950..1F96B ; Common # So [28] CROISSANT..CANNED FOOD
1F980..1F997 ; Common # So [24] CRAB..CRICKET
1F9C0 ; Common # So CHEESE WEDGE
1F9D0..1F9E6 ; Common # So [23] FACE WITH MONOCLE..SOCKS
1F940..1F970 ; Common # So [49] WILTED FLOWER..SMILING FACE WITH SMILING EYES AND THREE HEARTS
1F973..1F976 ; Common # So [4] FACE WITH PARTY HORN AND PARTY HAT..FREEZING FACE
1F97A ; Common # So FACE WITH PLEADING EYES
1F97C..1F9A2 ; Common # So [39] LAB COAT..SWAN
1F9B0..1F9B9 ; Common # So [10] EMOJI COMPONENT RED HAIR..SUPERVILLAIN
1F9C0..1F9C2 ; Common # So [3] CHEESE WEDGE..SALT SHAKER
1F9D0..1F9FF ; Common # So [48] FACE WITH MONOCLE..NAZAR AMULET
1FA60..1FA6D ; Common # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER
E0001 ; Common # Cf LANGUAGE TAG
E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
# Total code points: 7363
# Total code points: 7591
# ================================================
@ -647,8 +653,7 @@ A770 ; Latin # Lm MODIFIER LETTER US
A771..A787 ; Latin # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T
A78B..A78E ; Latin # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
A78F ; Latin # Lo LATIN LETTER SINOLOGICAL DOT
A790..A7AE ; Latin # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I
A7B0..A7B7 ; Latin # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA
A790..A7B9 ; Latin # L& [42] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER U WITH STROKE
A7F7 ; Latin # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I
A7F8..A7F9 ; Latin # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
A7FA ; Latin # L& LATIN LETTER SMALL CAPITAL TURNED M
@ -660,7 +665,7 @@ FB00..FB06 ; Latin # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE S
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: 1350
# Total code points: 1353
# ================================================
@ -754,13 +759,13 @@ FE2E..FE2F ; Cyrillic # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBININ
0531..0556 ; Armenian # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH
0559 ; Armenian # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING
055A..055F ; Armenian # Po [6] ARMENIAN APOSTROPHE..ARMENIAN ABBREVIATION MARK
0561..0587 ; Armenian # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN
0560..0588 ; Armenian # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE
058A ; Armenian # Pd ARMENIAN HYPHEN
058D..058E ; Armenian # So [2] RIGHT-FACING ARMENIAN ETERNITY SIGN..LEFT-FACING ARMENIAN ETERNITY SIGN
058F ; Armenian # Sc ARMENIAN DRAM SIGN
FB13..FB17 ; Armenian # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH
# Total code points: 93
# Total code points: 95
# ================================================
@ -774,7 +779,7 @@ FB13..FB17 ; Armenian # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SM
05C6 ; Hebrew # Po HEBREW PUNCTUATION NUN HAFUKHA
05C7 ; Hebrew # Mn HEBREW POINT QAMATS QATAN
05D0..05EA ; Hebrew # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV
05F0..05F2 ; Hebrew # Lo [3] HEBREW LIGATURE YIDDISH DOUBLE VAV..HEBREW LIGATURE YIDDISH DOUBLE YOD
05EF..05F2 ; Hebrew # Lo [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD
05F3..05F4 ; Hebrew # Po [2] HEBREW PUNCTUATION GERESH..HEBREW PUNCTUATION GERSHAYIM
FB1D ; Hebrew # Lo HEBREW LETTER YOD WITH HIRIQ
FB1E ; Hebrew # Mn HEBREW POINT JUDEO-SPANISH VARIKA
@ -787,7 +792,7 @@ FB40..FB41 ; Hebrew # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER S
FB43..FB44 ; Hebrew # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH
FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE ALEF LAMED
# Total code points: 133
# Total code points: 134
# ================================================
@ -824,7 +829,7 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU
0750..077F ; Arabic # Lo [48] ARABIC LETTER BEH WITH THREE DOTS HORIZONTALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS ABOVE
08A0..08B4 ; Arabic # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
08B6..08BD ; Arabic # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON
08D4..08E1 ; Arabic # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA
08D3..08E1 ; Arabic # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA
08E3..08FF ; Arabic # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA
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
@ -872,7 +877,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
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: 1280
# Total code points: 1281
# ================================================
@ -922,9 +927,10 @@ 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
A8FC ; Devanagari # Po DEVANAGARI SIGN SIDDHAM
A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
A8FD..A8FE ; Devanagari # Lo [2] DEVANAGARI JAIN OM..DEVANAGARI LETTER AY
A8FF ; Devanagari # Mn DEVANAGARI VOWEL SIGN AY
# Total code points: 154
# Total code points: 156
# ================================================
@ -957,8 +963,9 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
09FB ; Bengali # Sc BENGALI GANDA MARK
09FC ; Bengali # Lo BENGALI LETTER VEDIC ANUSVARA
09FD ; Bengali # Po BENGALI ABBREVIATION SIGN
09FE ; Bengali # Mn BENGALI SANDHI MARK
# Total code points: 95
# Total code points: 96
# ================================================
@ -983,8 +990,9 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
0A70..0A71 ; Gurmukhi # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK
0A72..0A74 ; Gurmukhi # Lo [3] GURMUKHI IRI..GURMUKHI EK ONKAR
0A75 ; Gurmukhi # Mn GURMUKHI SIGN YAKASH
0A76 ; Gurmukhi # Po GURMUKHI ABBREVIATION SIGN
# Total code points: 79
# Total code points: 80
# ================================================
@ -1079,6 +1087,7 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
0C00 ; Telugu # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE
0C01..0C03 ; Telugu # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA
0C04 ; Telugu # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE
0C05..0C0C ; Telugu # Lo [8] TELUGU LETTER A..TELUGU LETTER VOCALIC L
0C0E..0C10 ; Telugu # Lo [3] TELUGU LETTER E..TELUGU LETTER AI
0C12..0C28 ; Telugu # Lo [23] TELUGU LETTER O..TELUGU LETTER NA
@ -1096,13 +1105,14 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
0C78..0C7E ; Telugu # No [7] TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR..TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR
0C7F ; Telugu # So TELUGU SIGN TUUMU
# Total code points: 96
# Total code points: 97
# ================================================
0C80 ; Kannada # Lo KANNADA SIGN SPACING CANDRABINDU
0C81 ; Kannada # Mn KANNADA SIGN CANDRABINDU
0C82..0C83 ; Kannada # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA
0C84 ; Kannada # Po KANNADA SIGN SIDDHAM
0C85..0C8C ; Kannada # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L
0C8E..0C90 ; Kannada # Lo [3] KANNADA LETTER E..KANNADA LETTER AI
0C92..0CA8 ; Kannada # Lo [23] KANNADA LETTER O..KANNADA LETTER NA
@ -1124,7 +1134,7 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
0CE6..0CEF ; Kannada # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE
0CF1..0CF2 ; Kannada # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
# Total code points: 88
# Total code points: 89
# ================================================
@ -1318,14 +1328,16 @@ AA7E..AA7F ; Myanmar # Lo [2] MYANMAR LETTER SHWE PALAUNG CHA..MYANMAR LETT
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
10D0..10FA ; Georgian # L& [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
10FD..10FF ; Georgian # L& [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN
1C90..1CBA ; Georgian # L& [43] GEORGIAN MTAVRULI CAPITAL LETTER AN..GEORGIAN MTAVRULI CAPITAL LETTER AIN
1CBD..1CBF ; Georgian # L& [3] GEORGIAN MTAVRULI CAPITAL LETTER AEN..GEORGIAN MTAVRULI CAPITAL 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: 127
# Total code points: 173
# ================================================
@ -1454,7 +1466,7 @@ AB70..ABBF ; Cherokee # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETT
1810..1819 ; Mongolian # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE
1820..1842 ; Mongolian # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI
1843 ; Mongolian # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN
1844..1877 ; Mongolian # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA
1844..1878 ; Mongolian # Lo [53] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER CHA WITH TWO DOTS
1880..1884 ; Mongolian # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA
1885..1886 ; Mongolian # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA
1887..18A8 ; Mongolian # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA
@ -1462,7 +1474,7 @@ AB70..ABBF ; Cherokee # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETT
18AA ; Mongolian # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA
11660..1166C ; Mongolian # Po [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT
# Total code points: 166
# Total code points: 167
# ================================================
@ -1491,10 +1503,10 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
# ================================================
02EA..02EB ; Bopomofo # Sk [2] MODIFIER LETTER YIN DEPARTING TONE MARK..MODIFIER LETTER YANG DEPARTING TONE MARK
3105..312E ; Bopomofo # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE
3105..312F ; Bopomofo # Lo [43] BOPOMOFO LETTER B..BOPOMOFO LETTER NN
31A0..31BA ; Bopomofo # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY
# Total code points: 71
# Total code points: 72
# ================================================
@ -1507,7 +1519,7 @@ 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..9FEA ; Han # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
4E00..9FEF ; Han # Lo [20976] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEF
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
@ -1517,7 +1529,7 @@ FA70..FAD9 ; Han # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILI
2CEB0..2EBE0 ; Han # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2F800..2FA1D ; Han # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 89228
# Total code points: 89233
# ================================================
@ -1580,13 +1592,14 @@ FE00..FE0F ; Inherited # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
FE20..FE2D ; Inherited # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON BELOW
101FD ; Inherited # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE
102E0 ; Inherited # Mn COPTIC EPACT THOUSANDS MARK
1133B ; Inherited # Mn COMBINING BINDU BELOW
1D167..1D169 ; Inherited # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3
1D17B..1D182 ; Inherited # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE
1D185..1D18B ; Inherited # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
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: 568
# Total code points: 569
# ================================================
@ -1779,13 +1792,13 @@ A828..A82B ; Syloti_Nagri # So [4] SYLOTI NAGRI POETRY MARK-1..SYLOTI NAGRI
10A0C..10A0F ; Kharoshthi # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA
10A10..10A13 ; Kharoshthi # Lo [4] KHAROSHTHI LETTER KA..KHAROSHTHI LETTER GHA
10A15..10A17 ; Kharoshthi # Lo [3] KHAROSHTHI LETTER CA..KHAROSHTHI LETTER JA
10A19..10A33 ; Kharoshthi # Lo [27] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER TTTHA
10A19..10A35 ; Kharoshthi # Lo [29] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER VHA
10A38..10A3A ; Kharoshthi # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW
10A3F ; Kharoshthi # Mn KHAROSHTHI VIRAMA
10A40..10A47 ; Kharoshthi # No [8] KHAROSHTHI DIGIT ONE..KHAROSHTHI NUMBER ONE THOUSAND
10A40..10A48 ; Kharoshthi # No [9] KHAROSHTHI DIGIT ONE..KHAROSHTHI FRACTION ONE HALF
10A50..10A58 ; Kharoshthi # Po [9] KHAROSHTHI PUNCTUATION DOT..KHAROSHTHI PUNCTUATION LINES
# Total code points: 65
# Total code points: 68
# ================================================
@ -1842,8 +1855,10 @@ A874..A877 ; Phags_Pa # Po [4] PHAGS-PA SINGLE HEAD MARK..PHAGS-PA MARK DOU
07F6 ; Nko # So NKO SYMBOL OO DENNEN
07F7..07F9 ; Nko # Po [3] NKO SYMBOL GBAKURUNEN..NKO EXCLAMATION MARK
07FA ; Nko # Lm NKO LAJANYALAN
07FD ; Nko # Mn NKO DANTAYALAN
07FE..07FF ; Nko # Sc [2] NKO DOROME SIGN..NKO TAMAN SIGN
# Total code points: 59
# Total code points: 62
# ================================================
@ -2138,8 +2153,9 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
110BB..110BC ; Kaithi # Po [2] KAITHI ABBREVIATION SIGN..KAITHI ENUMERATION SIGN
110BD ; Kaithi # Cf KAITHI NUMBER SIGN
110BE..110C1 ; Kaithi # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA
110CD ; Kaithi # Cf KAITHI NUMBER SIGN ABOVE
# Total code points: 66
# Total code points: 67
# ================================================
@ -2187,8 +2203,10 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
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
11144 ; Chakma # Lo CHAKMA LETTER LHAA
11145..11146 ; Chakma # Mc [2] CHAKMA VOWEL SIGN AA..CHAKMA VOWEL SIGN EI
# Total code points: 67
# Total code points: 70
# ================================================
@ -2225,8 +2243,8 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
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..111C9 ; Sharada # Po [5] SHARADA DANDA..SHARADA SANDHI MARK
111CA..111CC ; Sharada # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK
111C5..111C8 ; Sharada # Po [4] SHARADA DANDA..SHARADA SEPARATOR
111C9..111CC ; Sharada # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK
111CD ; Sharada # Po SHARADA SUTRA MARK
111D0..111D9 ; Sharada # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE
111DA ; Sharada # Lo SHARADA EKAM
@ -2503,7 +2521,7 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
# ================================================
11700..11719 ; Ahom # Lo [26] AHOM LETTER KA..AHOM LETTER JHA
11700..1171A ; Ahom # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA
1171D..1171F ; Ahom # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA
11720..11721 ; Ahom # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA
11722..11725 ; Ahom # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
@ -2514,7 +2532,7 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
1173C..1173E ; Ahom # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI
1173F ; Ahom # So AHOM SYMBOL VI
# Total code points: 57
# Total code points: 58
# ================================================
@ -2619,8 +2637,9 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
11450..11459 ; Newa # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE
1145B ; Newa # Po NEWA PLACEHOLDER MARK
1145D ; Newa # Po NEWA INSERTION SIGN
1145E ; Newa # Mn NEWA SANDHI MARK
# Total code points: 92
# Total code points: 93
# ================================================
@ -2632,10 +2651,10 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
# ================================================
16FE0 ; Tangut # Lm TANGUT ITERATION MARK
17000..187EC ; Tangut # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC
17000..187F1 ; Tangut # Lo [6130] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F1
18800..18AF2 ; Tangut # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
# Total code points: 6881
# Total code points: 6886
# ================================================
@ -2671,16 +2690,15 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
11A97 ; Soyombo # Mc SOYOMBO SIGN VISARGA
11A98..11A99 ; Soyombo # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER
11A9A..11A9C ; Soyombo # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD
11A9D ; Soyombo # Lo SOYOMBO MARK PLUTA
11A9E..11AA2 ; Soyombo # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2
# Total code points: 80
# Total code points: 81
# ================================================
11A00 ; Zanabazar_Square # Lo ZANABAZAR SQUARE LETTER A
11A01..11A06 ; Zanabazar_Square # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O
11A07..11A08 ; Zanabazar_Square # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU
11A09..11A0A ; Zanabazar_Square # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK
11A01..11A0A ; Zanabazar_Square # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK
11A0B..11A32 ; Zanabazar_Square # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA
11A33..11A38 ; Zanabazar_Square # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA
11A39 ; Zanabazar_Square # Mc ZANABAZAR SQUARE SIGN VISARGA
@ -2691,4 +2709,73 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
# Total code points: 72
# ================================================
11800..1182B ; Dogra # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA
1182C..1182E ; Dogra # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II
1182F..11837 ; Dogra # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA
11838 ; Dogra # Mc DOGRA SIGN VISARGA
11839..1183A ; Dogra # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA
1183B ; Dogra # Po DOGRA ABBREVIATION SIGN
# Total code points: 60
# ================================================
11D60..11D65 ; Gunjala_Gondi # Lo [6] GUNJALA GONDI LETTER A..GUNJALA GONDI LETTER UU
11D67..11D68 ; Gunjala_Gondi # Lo [2] GUNJALA GONDI LETTER EE..GUNJALA GONDI LETTER AI
11D6A..11D89 ; Gunjala_Gondi # Lo [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA
11D8A..11D8E ; Gunjala_Gondi # Mc [5] GUNJALA GONDI VOWEL SIGN AA..GUNJALA GONDI VOWEL SIGN UU
11D90..11D91 ; Gunjala_Gondi # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI
11D93..11D94 ; Gunjala_Gondi # Mc [2] GUNJALA GONDI VOWEL SIGN OO..GUNJALA GONDI VOWEL SIGN AU
11D95 ; Gunjala_Gondi # Mn GUNJALA GONDI SIGN ANUSVARA
11D96 ; Gunjala_Gondi # Mc GUNJALA GONDI SIGN VISARGA
11D97 ; Gunjala_Gondi # Mn GUNJALA GONDI VIRAMA
11D98 ; Gunjala_Gondi # Lo GUNJALA GONDI OM
11DA0..11DA9 ; Gunjala_Gondi # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE
# Total code points: 63
# ================================================
11EE0..11EF2 ; Makasar # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA
11EF3..11EF4 ; Makasar # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
11EF5..11EF6 ; Makasar # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
11EF7..11EF8 ; Makasar # Po [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION
# Total code points: 25
# ================================================
16E40..16E7F ; Medefaidrin # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y
16E80..16E96 ; Medefaidrin # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM
16E97..16E9A ; Medefaidrin # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH
# Total code points: 91
# ================================================
10D00..10D23 ; Hanifi_Rohingya # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA
10D24..10D27 ; Hanifi_Rohingya # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
10D30..10D39 ; Hanifi_Rohingya # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE
# Total code points: 50
# ================================================
10F30..10F45 ; Sogdian # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN
10F46..10F50 ; Sogdian # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW
10F51..10F54 ; Sogdian # No [4] SOGDIAN NUMBER ONE..SOGDIAN NUMBER ONE HUNDRED
10F55..10F59 ; Sogdian # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT
# Total code points: 42
# ================================================
10F00..10F1C ; Old_Sogdian # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL
10F1D..10F26 ; Old_Sogdian # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF
10F27 ; Old_Sogdian # Lo OLD SOGDIAN LIGATURE AYIN-DALETH
# Total code points: 40
# EOF

8
test/jdk/java/lang/Character/SpecialCasing.txt
View File

@ -1,6 +1,6 @@
# SpecialCasing-10.0.0.txt
# Date: 2017-04-14, 05:40:43 GMT
# Copyright (c) 2017 Unicode, Inc.
# SpecialCasing-11.0.0.txt
# Date: 2018-02-22, 06:16:47 GMT
# Copyright (c) 2018 Unicode, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
@ -121,7 +121,7 @@ FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH
# The following cases are already in the UnicodeData.txt file, so are only commented here.
# 0345; 0345; 0345; 0399; # COMBINING GREEK YPOGEGRAMMENI
# 0345; 0345; 0399; 0399; # COMBINING GREEK YPOGEGRAMMENI
# All letters with YPOGEGRAMMENI (iota-subscript) or PROSGEGRAMMENI (iota adscript)
# have special uppercases.

17
test/jdk/java/lang/Character/UnicodeBlock/Blocks.txt
View File

@ -1,6 +1,6 @@
# Blocks-10.0.0.txt
# Date: 2017-04-12, 17:30:00 GMT [KW]
# Copyright (c) 2017 Unicode, Inc.
# Blocks-11.0.0.txt
# Date: 2017-10-16, 24:39:00 GMT [KW]
# Copyright (c) 2018 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
@ -95,6 +95,7 @@
1C00..1C4F; Lepcha
1C50..1C7F; Ol Chiki
1C80..1C8F; Cyrillic Extended-C
1C90..1CBF; Georgian Extended
1CC0..1CCF; Sundanese Supplement
1CD0..1CFF; Vedic Extensions
1D00..1D7F; Phonetic Extensions
@ -234,7 +235,10 @@ FFF0..FFFF; Specials
10B80..10BAF; Psalter Pahlavi
10C00..10C4F; Old Turkic
10C80..10CFF; Old Hungarian
10D00..10D3F; Hanifi Rohingya
10E60..10E7F; Rumi Numeral Symbols
10F00..10F2F; Old Sogdian
10F30..10F6F; Sogdian
11000..1107F; Brahmi
11080..110CF; Kaithi
110D0..110FF; Sora Sompeng
@ -253,6 +257,7 @@ FFF0..FFFF; Specials
11660..1167F; Mongolian Supplement
11680..116CF; Takri
11700..1173F; Ahom
11800..1184F; Dogra
118A0..118FF; Warang Citi
11A00..11A4F; Zanabazar Square
11A50..11AAF; Soyombo
@ -260,6 +265,8 @@ FFF0..FFFF; Specials
11C00..11C6F; Bhaiksuki
11C70..11CBF; Marchen
11D00..11D5F; Masaram Gondi
11D60..11DAF; Gunjala Gondi
11EE0..11EFF; Makasar
12000..123FF; Cuneiform
12400..1247F; Cuneiform Numbers and Punctuation
12480..1254F; Early Dynastic Cuneiform
@ -269,6 +276,7 @@ FFF0..FFFF; Specials
16A40..16A6F; Mro
16AD0..16AFF; Bassa Vah
16B00..16B8F; Pahawh Hmong
16E40..16E9F; Medefaidrin
16F00..16F9F; Miao
16FE0..16FFF; Ideographic Symbols and Punctuation
17000..187FF; Tangut
@ -281,6 +289,7 @@ FFF0..FFFF; Specials
1D000..1D0FF; Byzantine Musical Symbols
1D100..1D1FF; Musical Symbols
1D200..1D24F; Ancient Greek Musical Notation
1D2E0..1D2FF; Mayan Numerals
1D300..1D35F; Tai Xuan Jing Symbols
1D360..1D37F; Counting Rod Numerals
1D400..1D7FF; Mathematical Alphanumeric Symbols
@ -288,6 +297,7 @@ FFF0..FFFF; Specials
1E000..1E02F; Glagolitic Supplement
1E800..1E8DF; Mende Kikakui
1E900..1E95F; Adlam
1EC70..1ECBF; Indic Siyaq Numbers
1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
1F000..1F02F; Mahjong Tiles
1F030..1F09F; Domino Tiles
@ -302,6 +312,7 @@ FFF0..FFFF; Specials
1F780..1F7FF; Geometric Shapes Extended
1F800..1F8FF; Supplemental Arrows-C
1F900..1F9FF; Supplemental Symbols and Pictographs
1FA00..1FA6F; Chess Symbols
20000..2A6DF; CJK Unified Ideographs Extension B
2A700..2B73F; CJK Unified Ideographs Extension C
2B740..2B81F; CJK Unified Ideographs Extension D

778
test/jdk/java/lang/Character/UnicodeData.txt
View File

File diff suppressed because it is too large Load Diff

BIN
test/jdk/java/lang/Character/charprop00.bin
View File

Binary file not shown.

BIN
test/jdk/java/lang/Character/charprop01.bin
View File

Binary file not shown.

BIN
test/jdk/java/lang/Character/charprop02.bin
View File

Binary file not shown.

BIN
test/jdk/java/lang/Character/charprop03.bin
View File

Binary file not shown.

BIN
test/jdk/java/lang/Character/charprop0E.bin
View File

Binary file not shown.

BIN
test/jdk/java/lang/Character/charprop0F.bin
View File

Binary file not shown.

BIN
test/jdk/java/lang/Character/charprop10.bin
View File

Binary file not shown.