Skip to content

Commit 4eba067

Browse files
naotojnaotoj
committed
iniital commit
1 parent 0d593cd commit 4eba067

13 files changed

+7398
-567
lines changed

‎src/java.base/share/classes/java/lang/Character.java

+3-1
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
/*
2-
* Copyright (c) 2002, 2023, Oracle and/or its affiliates. All rights reserved.
2+
* Copyright (c) 2002, 2024, Oracle and/or its affiliates. All rights reserved.
33
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
44
*
55
* This code is free software; you can redistribute it and/or modify it
@@ -75,6 +75,8 @@
7575
* <th scope="col">Unicode version</th></tr>
7676
* </thead>
7777
* <tbody>
78+
* <tr><th scope="row" style="text-align:left">Java SE 24</th>
79+
* <td>Unicode 16.0</td></tr>
7880
* <tr><th scope="row" style="text-align:left">Java SE 22</th>
7981
* <td>Unicode 15.1</td></tr>
8082
* <tr><th scope="row" style="text-align:left">Java SE 20</th>

‎src/java.base/share/data/unicodedata/Blocks.txt

+15-4
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,8 @@
1-
# Blocks-15.1.0.txt
2-
# Date: 2023-07-28, 15:47:20 GMT
3-
# Copyright (c) 2023 Unicode, Inc.
4-
# For terms of use, see https://www.unicode.org/terms_of_use.html
1+
# Blocks-16.0.0.txt
2+
# Date: 2024-02-02
3+
# Copyright (c) 2024 Unicode, Inc.
4+
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
5+
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
56
#
67
# Unicode Character Database
78
# For documentation, see https://www.unicode.org/reports/tr44/
@@ -217,6 +218,7 @@ FFF0..FFFF; Specials
217218
10500..1052F; Elbasan
218219
10530..1056F; Caucasian Albanian
219220
10570..105BF; Vithkuqi
221+
105C0..105FF; Todhri
220222
10600..1077F; Linear A
221223
10780..107BF; Latin Extended-F
222224
10800..1083F; Cypriot Syllabary
@@ -239,6 +241,7 @@ FFF0..FFFF; Specials
239241
10C00..10C4F; Old Turkic
240242
10C80..10CFF; Old Hungarian
241243
10D00..10D3F; Hanifi Rohingya
244+
10D40..10D8F; Garay
242245
10E60..10E7F; Rumi Numeral Symbols
243246
10E80..10EBF; Yezidi
244247
10EC0..10EFF; Arabic Extended-C
@@ -258,12 +261,14 @@ FFF0..FFFF; Specials
258261
11280..112AF; Multani
259262
112B0..112FF; Khudawadi
260263
11300..1137F; Grantha
264+
11380..113FF; Tulu-Tigalari
261265
11400..1147F; Newa
262266
11480..114DF; Tirhuta
263267
11580..115FF; Siddham
264268
11600..1165F; Modi
265269
11660..1167F; Mongolian Supplement
266270
11680..116CF; Takri
271+
116D0..116FF; Myanmar Extended-C
267272
11700..1174F; Ahom
268273
11800..1184F; Dogra
269274
118A0..118FF; Warang Citi
@@ -274,6 +279,7 @@ FFF0..FFFF; Specials
274279
11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A
275280
11AC0..11AFF; Pau Cin Hau
276281
11B00..11B5F; Devanagari Extended-A
282+
11BC0..11BFF; Sunuwar
277283
11C00..11C6F; Bhaiksuki
278284
11C70..11CBF; Marchen
279285
11D00..11D5F; Masaram Gondi
@@ -288,12 +294,15 @@ FFF0..FFFF; Specials
288294
12F90..12FFF; Cypro-Minoan
289295
13000..1342F; Egyptian Hieroglyphs
290296
13430..1345F; Egyptian Hieroglyph Format Controls
297+
13460..143FF; Egyptian Hieroglyphs Extended-A
291298
14400..1467F; Anatolian Hieroglyphs
299+
16100..1613F; Gurung Khema
292300
16800..16A3F; Bamum Supplement
293301
16A40..16A6F; Mro
294302
16A70..16ACF; Tangsa
295303
16AD0..16AFF; Bassa Vah
296304
16B00..16B8F; Pahawh Hmong
305+
16D40..16D7F; Kirat Rai
297306
16E40..16E9F; Medefaidrin
298307
16F00..16F9F; Miao
299308
16FE0..16FFF; Ideographic Symbols and Punctuation
@@ -308,6 +317,7 @@ FFF0..FFFF; Specials
308317
1B170..1B2FF; Nushu
309318
1BC00..1BC9F; Duployan
310319
1BCA0..1BCAF; Shorthand Format Controls
320+
1CC00..1CEBF; Symbols for Legacy Computing Supplement
311321
1CF00..1CFCF; Znamenny Musical Notation
312322
1D000..1D0FF; Byzantine Musical Symbols
313323
1D100..1D1FF; Musical Symbols
@@ -325,6 +335,7 @@ FFF0..FFFF; Specials
325335
1E290..1E2BF; Toto
326336
1E2C0..1E2FF; Wancho
327337
1E4D0..1E4FF; Nag Mundari
338+
1E5D0..1E5FF; Ol Onal
328339
1E7E0..1E7FF; Ethiopic Extended-B
329340
1E800..1E8DF; Mende Kikakui
330341
1E900..1E95F; Adlam

‎src/java.base/share/data/unicodedata/DerivedCoreProperties.txt

+682-152
Large diffs are not rendered by default.

‎src/java.base/share/data/unicodedata/NormalizationTest.txt

+901-4
Large diffs are not rendered by default.

‎src/java.base/share/data/unicodedata/PropList.txt

+124-23
Large diffs are not rendered by default.

‎src/java.base/share/data/unicodedata/PropertyValueAliases.txt

+60-5
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,8 @@
1-
# PropertyValueAliases-15.1.0.txt
2-
# Date: 2023-08-07, 15:21:34 GMT
3-
# Copyright (c) 2023 Unicode, Inc.
1+
# PropertyValueAliases-16.0.0.txt
2+
# Date: 2024-07-30, 19:59:00 GMT
3+
# Copyright (c) 2024 Unicode, Inc.
44
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
5-
# For terms of use, see https://www.unicode.org/terms_of_use.html
5+
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
66
#
77
# Unicode Character Database
88
# For documentation, see https://www.unicode.org/reports/tr44/
@@ -92,6 +92,7 @@ age; 13.0 ; V13_0
9292
age; 14.0 ; V14_0
9393
age; 15.0 ; V15_0
9494
age; 15.1 ; V15_1
95+
age; 16.0 ; V16_0
9596
age; NA ; Unassigned
9697

9798
# Alphabetic (Alpha)
@@ -245,6 +246,7 @@ blk; Duployan ; Duployan
245246
blk; Early_Dynastic_Cuneiform ; Early_Dynastic_Cuneiform
246247
blk; Egyptian_Hieroglyph_Format_Controls; Egyptian_Hieroglyph_Format_Controls
247248
blk; Egyptian_Hieroglyphs ; Egyptian_Hieroglyphs
249+
blk; Egyptian_Hieroglyphs_Ext_A ; Egyptian_Hieroglyphs_Extended_A
248250
blk; Elbasan ; Elbasan
249251
blk; Elymaic ; Elymaic
250252
blk; Emoticons ; Emoticons
@@ -257,6 +259,7 @@ blk; Ethiopic_Ext ; Ethiopic_Extended
257259
blk; Ethiopic_Ext_A ; Ethiopic_Extended_A
258260
blk; Ethiopic_Ext_B ; Ethiopic_Extended_B
259261
blk; Ethiopic_Sup ; Ethiopic_Supplement
262+
blk; Garay ; Garay
260263
blk; Geometric_Shapes ; Geometric_Shapes
261264
blk; Geometric_Shapes_Ext ; Geometric_Shapes_Extended
262265
blk; Georgian ; Georgian
@@ -271,6 +274,7 @@ blk; Greek_Ext ; Greek_Extended
271274
blk; Gujarati ; Gujarati
272275
blk; Gunjala_Gondi ; Gunjala_Gondi
273276
blk; Gurmukhi ; Gurmukhi
277+
blk; Gurung_Khema ; Gurung_Khema
274278
blk; Half_And_Full_Forms ; Halfwidth_And_Fullwidth_Forms
275279
blk; Half_Marks ; Combining_Half_Marks
276280
blk; Hangul ; Hangul_Syllables
@@ -311,6 +315,7 @@ blk; Khmer ; Khmer
311315
blk; Khmer_Symbols ; Khmer_Symbols
312316
blk; Khojki ; Khojki
313317
blk; Khudawadi ; Khudawadi
318+
blk; Kirat_Rai ; Kirat_Rai
314319
blk; Lao ; Lao
315320
blk; Latin_1_Sup ; Latin_1_Supplement ; Latin_1
316321
blk; Latin_Ext_A ; Latin_Extended_A
@@ -367,6 +372,7 @@ blk; Music ; Musical_Symbols
367372
blk; Myanmar ; Myanmar
368373
blk; Myanmar_Ext_A ; Myanmar_Extended_A
369374
blk; Myanmar_Ext_B ; Myanmar_Extended_B
375+
blk; Myanmar_Ext_C ; Myanmar_Extended_C
370376
blk; Nabataean ; Nabataean
371377
blk; Nag_Mundari ; Nag_Mundari
372378
blk; Nandinagari ; Nandinagari
@@ -380,6 +386,7 @@ blk; Nyiakeng_Puachue_Hmong ; Nyiakeng_Puachue_Hmong
380386
blk; OCR ; Optical_Character_Recognition
381387
blk; Ogham ; Ogham
382388
blk; Ol_Chiki ; Ol_Chiki
389+
blk; Ol_Onal ; Ol_Onal
383390
blk; Old_Hungarian ; Old_Hungarian
384391
blk; Old_Italic ; Old_Italic
385392
blk; Old_North_Arabian ; Old_North_Arabian
@@ -425,6 +432,7 @@ blk; Soyombo ; Soyombo
425432
blk; Specials ; Specials
426433
blk; Sundanese ; Sundanese
427434
blk; Sundanese_Sup ; Sundanese_Supplement
435+
blk; Sunuwar ; Sunuwar
428436
blk; Sup_Arrows_A ; Supplemental_Arrows_A
429437
blk; Sup_Arrows_B ; Supplemental_Arrows_B
430438
blk; Sup_Arrows_C ; Supplemental_Arrows_C
@@ -438,6 +446,7 @@ blk; Sutton_SignWriting ; Sutton_SignWriting
438446
blk; Syloti_Nagri ; Syloti_Nagri
439447
blk; Symbols_And_Pictographs_Ext_A ; Symbols_And_Pictographs_Extended_A
440448
blk; Symbols_For_Legacy_Computing ; Symbols_For_Legacy_Computing
449+
blk; Symbols_For_Legacy_Computing_Sup ; Symbols_For_Legacy_Computing_Supplement
441450
blk; Syriac ; Syriac
442451
blk; Syriac_Sup ; Syriac_Supplement
443452
blk; Tagalog ; Tagalog
@@ -460,8 +469,10 @@ blk; Thai ; Thai
460469
blk; Tibetan ; Tibetan
461470
blk; Tifinagh ; Tifinagh
462471
blk; Tirhuta ; Tirhuta
472+
blk; Todhri ; Todhri
463473
blk; Toto ; Toto
464474
blk; Transport_And_Map ; Transport_And_Map_Symbols
475+
blk; Tulu_Tigalari ; Tulu_Tigalari
465476
blk; UCAS ; Unified_Canadian_Aboriginal_Syllabics; Canadian_Syllabics
466477
blk; UCAS_Ext ; Unified_Canadian_Aboriginal_Syllabics_Extended
467478
blk; UCAS_Ext_A ; Unified_Canadian_Aboriginal_Syllabics_Extended_A
@@ -909,6 +920,7 @@ InSC; Number_Joiner ; Number_Joiner
909920
InSC; Other ; Other
910921
InSC; Pure_Killer ; Pure_Killer
911922
InSC; Register_Shifter ; Register_Shifter
923+
InSC; Reordering_Killer ; Reordering_Killer
912924
InSC; Syllable_Modifier ; Syllable_Modifier
913925
InSC; Tone_Letter ; Tone_Letter
914926
InSC; Tone_Mark ; Tone_Mark
@@ -1008,6 +1020,7 @@ jg ; Heh_Goal ; Heh_Goal
10081020
jg ; Heth ; Heth
10091021
jg ; Kaf ; Kaf
10101022
jg ; Kaph ; Kaph
1023+
jg ; Kashmiri_Yeh ; Kashmiri_Yeh
10111024
jg ; Khaph ; Khaph
10121025
jg ; Knotted_Heh ; Knotted_Heh
10131026
jg ; Lam ; Lam
@@ -1073,7 +1086,7 @@ jg ; Syriac_Waw ; Syriac_Waw
10731086
jg ; Tah ; Tah
10741087
jg ; Taw ; Taw
10751088
jg ; Teh_Marbuta ; Teh_Marbuta
1076-
jg ; Teh_Marbuta_Goal ; Hamza_On_Heh_Goal
1089+
jg ; Teh_Marbuta_Goal ; Teh_Marbuta_Goal ; Hamza_On_Heh_Goal
10771090
jg ; Teth ; Teth
10781091
jg ; Thin_Yeh ; Thin_Yeh
10791092
jg ; Vertical_Tail ; Vertical_Tail
@@ -1165,6 +1178,11 @@ Lower; Y ; Yes ; T
11651178
Math; N ; No ; F ; False
11661179
Math; Y ; Yes ; T ; True
11671180

1181+
# Modifier_Combining_Mark (MCM)
1182+
1183+
MCM; N ; No ; F ; False
1184+
MCM; Y ; Yes ; T ; True
1185+
11681186
# NFC_Quick_Check (NFC_QC)
11691187

11701188
NFC_QC; M ; Maybe
@@ -1326,6 +1344,7 @@ sc ; Egyp ; Egyptian_Hieroglyphs
13261344
sc ; Elba ; Elbasan
13271345
sc ; Elym ; Elymaic
13281346
sc ; Ethi ; Ethiopic
1347+
sc ; Gara ; Garay
13291348
sc ; Geor ; Georgian
13301349
sc ; Glag ; Glagolitic
13311350
sc ; Gong ; Gunjala_Gondi
@@ -1334,6 +1353,7 @@ sc ; Goth ; Gothic
13341353
sc ; Gran ; Grantha
13351354
sc ; Grek ; Greek
13361355
sc ; Gujr ; Gujarati
1356+
sc ; Gukh ; Gurung_Khema
13371357
sc ; Guru ; Gurmukhi
13381358
sc ; Hang ; Hangul
13391359
sc ; Hani ; Han
@@ -1356,6 +1376,7 @@ sc ; Khmr ; Khmer
13561376
sc ; Khoj ; Khojki
13571377
sc ; Kits ; Khitan_Small_Script
13581378
sc ; Knda ; Kannada
1379+
sc ; Krai ; Kirat_Rai
13591380
sc ; Kthi ; Kaithi
13601381
sc ; Lana ; Tai_Tham
13611382
sc ; Laoo ; Lao
@@ -1392,6 +1413,7 @@ sc ; Nkoo ; Nko
13921413
sc ; Nshu ; Nushu
13931414
sc ; Ogam ; Ogham
13941415
sc ; Olck ; Ol_Chiki
1416+
sc ; Onao ; Ol_Onal
13951417
sc ; Orkh ; Old_Turkic
13961418
sc ; Orya ; Oriya
13971419
sc ; Osge ; Osage
@@ -1423,6 +1445,7 @@ sc ; Sogo ; Old_Sogdian
14231445
sc ; Sora ; Sora_Sompeng
14241446
sc ; Soyo ; Soyombo
14251447
sc ; Sund ; Sundanese
1448+
sc ; Sunu ; Sunuwar
14261449
sc ; Sylo ; Syloti_Nagri
14271450
sc ; Syrc ; Syriac
14281451
sc ; Tagb ; Tagbanwa
@@ -1440,7 +1463,9 @@ sc ; Thai ; Thai
14401463
sc ; Tibt ; Tibetan
14411464
sc ; Tirh ; Tirhuta
14421465
sc ; Tnsa ; Tangsa
1466+
sc ; Todr ; Todhri
14431467
sc ; Toto ; Toto
1468+
sc ; Tutg ; Tulu_Tigalari
14441469
sc ; Ugar ; Ugaritic
14451470
sc ; Vaii ; Vai
14461471
sc ; Vith ; Vithkuqi
@@ -1650,4 +1675,34 @@ XIDS; Y ; Yes ; T
16501675

16511676
# @missing: 0000..10FFFF; cjkRSUnicode; <none>
16521677

1678+
# kEH_Cat (kEH_Cat)
1679+
1680+
# @missing: 0000..10FFFF; kEH_Cat; <none>
1681+
1682+
# kEH_Desc (kEH_Desc)
1683+
1684+
# @missing: 0000..10FFFF; kEH_Desc; <none>
1685+
1686+
# kEH_HG (kEH_HG)
1687+
1688+
# @missing: 0000..10FFFF; kEH_HG; <none>
1689+
1690+
# kEH_IFAO (kEH_IFAO)
1691+
1692+
# @missing: 0000..10FFFF; kEH_IFAO; <none>
1693+
1694+
# kEH_JSesh (kEH_JSesh)
1695+
1696+
# @missing: 0000..10FFFF; kEH_JSesh; <none>
1697+
1698+
# kEH_NoMirror (kEH_NoMirror)
1699+
1700+
kEH_NoMirror; N ; No ; F ; False
1701+
kEH_NoMirror; Y ; Yes ; T ; True
1702+
1703+
# kEH_NoRotate (kEH_NoRotate)
1704+
1705+
kEH_NoRotate; N ; No ; F ; False
1706+
kEH_NoRotate; Y ; Yes ; T ; True
1707+
16531708
# EOF

‎src/java.base/share/data/unicodedata/ReadMe.txt

+6-5
Original file line numberDiff line numberDiff line change
@@ -1,16 +1,17 @@
11
# Unicode Character Database
2-
# Date: 2023-08-28
3-
# Copyright (c) 2023 Unicode, Inc.
2+
# Date: 2024-08-25
3+
# Copyright (c) 2024 Unicode, Inc.
44
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
5-
# For terms of use, see https://www.unicode.org/terms_of_use.html
5+
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
66
#
77
# For documentation, see the following:
88
# NamesList.html
99
# UAX #38, "Unicode Han Database (Unihan)"
1010
# UAX #44, "Unicode Character Database"
1111
# UTS #51, "Unicode Emoji"
12+
# UAX #57, "Unicode Egyptian Hieroglyph Database"
1213
#
13-
# The UAXes and UTS #51 can be accessed at https://www.unicode.org/versions/Unicode15.1.0/
14+
# The UAXes and UTS #51 can be accessed at https://www.unicode.org/versions/Unicode16.0.0/
1415

1516
This directory contains final data files
16-
for the Unicode Character Database, for Version 15.1.0 of the Unicode Standard.
17+
for the Unicode Character Database, for Version 16.0.0 of the Unicode Standard.

0 commit comments

Comments
 (0)