xref: /aosp_15_r20/libcore/ojluni/src/test/resources/data/unicodedata/Blocks.txt (revision 89a6322812dc8573315e60046e7959c50dad91d4)
1# Blocks-15.0.0.txt
2# Date: 2022-01-28, 20:58:00 GMT [KW]
3# Copyright (c) 2022 Unicode, Inc.
4# For terms of use, see https://www.unicode.org/terms_of_use.html
5#
6# Unicode Character Database
7# For documentation, see https://www.unicode.org/reports/tr44/
8#
9# Format:
10# Start Code..End Code; Block Name
11
12# ================================================
13
14# Note:   When comparing block names, casing, whitespace, hyphens,
15#         and underbars are ignored.
16#         For example, "Latin Extended-A" and "latin extended a" are equivalent.
17#         For more information on the comparison of property values,
18#            see UAX #44: https://www.unicode.org/reports/tr44/
19#
20#  All block ranges start with a value where (cp MOD 16) = 0,
21#  and end with a value where (cp MOD 16) = 15. In other words,
22#  the last hexadecimal digit of the start of range is ...0
23#  and the last hexadecimal digit of the end of range is ...F.
24#  This constraint on block ranges guarantees that allocations
25#  are done in terms of whole columns, and that code chart display
26#  never involves splitting columns in the charts.
27#
28#  All code points not explicitly listed for Block
29#  have the value No_Block.
30
31# Property:	Block
32#
33# @missing: 0000..10FFFF; No_Block
34
350000..007F; Basic Latin
360080..00FF; Latin-1 Supplement
370100..017F; Latin Extended-A
380180..024F; Latin Extended-B
390250..02AF; IPA Extensions
4002B0..02FF; Spacing Modifier Letters
410300..036F; Combining Diacritical Marks
420370..03FF; Greek and Coptic
430400..04FF; Cyrillic
440500..052F; Cyrillic Supplement
450530..058F; Armenian
460590..05FF; Hebrew
470600..06FF; Arabic
480700..074F; Syriac
490750..077F; Arabic Supplement
500780..07BF; Thaana
5107C0..07FF; NKo
520800..083F; Samaritan
530840..085F; Mandaic
540860..086F; Syriac Supplement
550870..089F; Arabic Extended-B
5608A0..08FF; Arabic Extended-A
570900..097F; Devanagari
580980..09FF; Bengali
590A00..0A7F; Gurmukhi
600A80..0AFF; Gujarati
610B00..0B7F; Oriya
620B80..0BFF; Tamil
630C00..0C7F; Telugu
640C80..0CFF; Kannada
650D00..0D7F; Malayalam
660D80..0DFF; Sinhala
670E00..0E7F; Thai
680E80..0EFF; Lao
690F00..0FFF; Tibetan
701000..109F; Myanmar
7110A0..10FF; Georgian
721100..11FF; Hangul Jamo
731200..137F; Ethiopic
741380..139F; Ethiopic Supplement
7513A0..13FF; Cherokee
761400..167F; Unified Canadian Aboriginal Syllabics
771680..169F; Ogham
7816A0..16FF; Runic
791700..171F; Tagalog
801720..173F; Hanunoo
811740..175F; Buhid
821760..177F; Tagbanwa
831780..17FF; Khmer
841800..18AF; Mongolian
8518B0..18FF; Unified Canadian Aboriginal Syllabics Extended
861900..194F; Limbu
871950..197F; Tai Le
881980..19DF; New Tai Lue
8919E0..19FF; Khmer Symbols
901A00..1A1F; Buginese
911A20..1AAF; Tai Tham
921AB0..1AFF; Combining Diacritical Marks Extended
931B00..1B7F; Balinese
941B80..1BBF; Sundanese
951BC0..1BFF; Batak
961C00..1C4F; Lepcha
971C50..1C7F; Ol Chiki
981C80..1C8F; Cyrillic Extended-C
991C90..1CBF; Georgian Extended
1001CC0..1CCF; Sundanese Supplement
1011CD0..1CFF; Vedic Extensions
1021D00..1D7F; Phonetic Extensions
1031D80..1DBF; Phonetic Extensions Supplement
1041DC0..1DFF; Combining Diacritical Marks Supplement
1051E00..1EFF; Latin Extended Additional
1061F00..1FFF; Greek Extended
1072000..206F; General Punctuation
1082070..209F; Superscripts and Subscripts
10920A0..20CF; Currency Symbols
11020D0..20FF; Combining Diacritical Marks for Symbols
1112100..214F; Letterlike Symbols
1122150..218F; Number Forms
1132190..21FF; Arrows
1142200..22FF; Mathematical Operators
1152300..23FF; Miscellaneous Technical
1162400..243F; Control Pictures
1172440..245F; Optical Character Recognition
1182460..24FF; Enclosed Alphanumerics
1192500..257F; Box Drawing
1202580..259F; Block Elements
12125A0..25FF; Geometric Shapes
1222600..26FF; Miscellaneous Symbols
1232700..27BF; Dingbats
12427C0..27EF; Miscellaneous Mathematical Symbols-A
12527F0..27FF; Supplemental Arrows-A
1262800..28FF; Braille Patterns
1272900..297F; Supplemental Arrows-B
1282980..29FF; Miscellaneous Mathematical Symbols-B
1292A00..2AFF; Supplemental Mathematical Operators
1302B00..2BFF; Miscellaneous Symbols and Arrows
1312C00..2C5F; Glagolitic
1322C60..2C7F; Latin Extended-C
1332C80..2CFF; Coptic
1342D00..2D2F; Georgian Supplement
1352D30..2D7F; Tifinagh
1362D80..2DDF; Ethiopic Extended
1372DE0..2DFF; Cyrillic Extended-A
1382E00..2E7F; Supplemental Punctuation
1392E80..2EFF; CJK Radicals Supplement
1402F00..2FDF; Kangxi Radicals
1412FF0..2FFF; Ideographic Description Characters
1423000..303F; CJK Symbols and Punctuation
1433040..309F; Hiragana
14430A0..30FF; Katakana
1453100..312F; Bopomofo
1463130..318F; Hangul Compatibility Jamo
1473190..319F; Kanbun
14831A0..31BF; Bopomofo Extended
14931C0..31EF; CJK Strokes
15031F0..31FF; Katakana Phonetic Extensions
1513200..32FF; Enclosed CJK Letters and Months
1523300..33FF; CJK Compatibility
1533400..4DBF; CJK Unified Ideographs Extension A
1544DC0..4DFF; Yijing Hexagram Symbols
1554E00..9FFF; CJK Unified Ideographs
156A000..A48F; Yi Syllables
157A490..A4CF; Yi Radicals
158A4D0..A4FF; Lisu
159A500..A63F; Vai
160A640..A69F; Cyrillic Extended-B
161A6A0..A6FF; Bamum
162A700..A71F; Modifier Tone Letters
163A720..A7FF; Latin Extended-D
164A800..A82F; Syloti Nagri
165A830..A83F; Common Indic Number Forms
166A840..A87F; Phags-pa
167A880..A8DF; Saurashtra
168A8E0..A8FF; Devanagari Extended
169A900..A92F; Kayah Li
170A930..A95F; Rejang
171A960..A97F; Hangul Jamo Extended-A
172A980..A9DF; Javanese
173A9E0..A9FF; Myanmar Extended-B
174AA00..AA5F; Cham
175AA60..AA7F; Myanmar Extended-A
176AA80..AADF; Tai Viet
177AAE0..AAFF; Meetei Mayek Extensions
178AB00..AB2F; Ethiopic Extended-A
179AB30..AB6F; Latin Extended-E
180AB70..ABBF; Cherokee Supplement
181ABC0..ABFF; Meetei Mayek
182AC00..D7AF; Hangul Syllables
183D7B0..D7FF; Hangul Jamo Extended-B
184D800..DB7F; High Surrogates
185DB80..DBFF; High Private Use Surrogates
186DC00..DFFF; Low Surrogates
187E000..F8FF; Private Use Area
188F900..FAFF; CJK Compatibility Ideographs
189FB00..FB4F; Alphabetic Presentation Forms
190FB50..FDFF; Arabic Presentation Forms-A
191FE00..FE0F; Variation Selectors
192FE10..FE1F; Vertical Forms
193FE20..FE2F; Combining Half Marks
194FE30..FE4F; CJK Compatibility Forms
195FE50..FE6F; Small Form Variants
196FE70..FEFF; Arabic Presentation Forms-B
197FF00..FFEF; Halfwidth and Fullwidth Forms
198FFF0..FFFF; Specials
19910000..1007F; Linear B Syllabary
20010080..100FF; Linear B Ideograms
20110100..1013F; Aegean Numbers
20210140..1018F; Ancient Greek Numbers
20310190..101CF; Ancient Symbols
204101D0..101FF; Phaistos Disc
20510280..1029F; Lycian
206102A0..102DF; Carian
207102E0..102FF; Coptic Epact Numbers
20810300..1032F; Old Italic
20910330..1034F; Gothic
21010350..1037F; Old Permic
21110380..1039F; Ugaritic
212103A0..103DF; Old Persian
21310400..1044F; Deseret
21410450..1047F; Shavian
21510480..104AF; Osmanya
216104B0..104FF; Osage
21710500..1052F; Elbasan
21810530..1056F; Caucasian Albanian
21910570..105BF; Vithkuqi
22010600..1077F; Linear A
22110780..107BF; Latin Extended-F
22210800..1083F; Cypriot Syllabary
22310840..1085F; Imperial Aramaic
22410860..1087F; Palmyrene
22510880..108AF; Nabataean
226108E0..108FF; Hatran
22710900..1091F; Phoenician
22810920..1093F; Lydian
22910980..1099F; Meroitic Hieroglyphs
230109A0..109FF; Meroitic Cursive
23110A00..10A5F; Kharoshthi
23210A60..10A7F; Old South Arabian
23310A80..10A9F; Old North Arabian
23410AC0..10AFF; Manichaean
23510B00..10B3F; Avestan
23610B40..10B5F; Inscriptional Parthian
23710B60..10B7F; Inscriptional Pahlavi
23810B80..10BAF; Psalter Pahlavi
23910C00..10C4F; Old Turkic
24010C80..10CFF; Old Hungarian
24110D00..10D3F; Hanifi Rohingya
24210E60..10E7F; Rumi Numeral Symbols
24310E80..10EBF; Yezidi
24410EC0..10EFF; Arabic Extended-C
24510F00..10F2F; Old Sogdian
24610F30..10F6F; Sogdian
24710F70..10FAF; Old Uyghur
24810FB0..10FDF; Chorasmian
24910FE0..10FFF; Elymaic
25011000..1107F; Brahmi
25111080..110CF; Kaithi
252110D0..110FF; Sora Sompeng
25311100..1114F; Chakma
25411150..1117F; Mahajani
25511180..111DF; Sharada
256111E0..111FF; Sinhala Archaic Numbers
25711200..1124F; Khojki
25811280..112AF; Multani
259112B0..112FF; Khudawadi
26011300..1137F; Grantha
26111400..1147F; Newa
26211480..114DF; Tirhuta
26311580..115FF; Siddham
26411600..1165F; Modi
26511660..1167F; Mongolian Supplement
26611680..116CF; Takri
26711700..1174F; Ahom
26811800..1184F; Dogra
269118A0..118FF; Warang Citi
27011900..1195F; Dives Akuru
271119A0..119FF; Nandinagari
27211A00..11A4F; Zanabazar Square
27311A50..11AAF; Soyombo
27411AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A
27511AC0..11AFF; Pau Cin Hau
27611B00..11B5F; Devanagari Extended-A
27711C00..11C6F; Bhaiksuki
27811C70..11CBF; Marchen
27911D00..11D5F; Masaram Gondi
28011D60..11DAF; Gunjala Gondi
28111EE0..11EFF; Makasar
28211F00..11F5F; Kawi
28311FB0..11FBF; Lisu Supplement
28411FC0..11FFF; Tamil Supplement
28512000..123FF; Cuneiform
28612400..1247F; Cuneiform Numbers and Punctuation
28712480..1254F; Early Dynastic Cuneiform
28812F90..12FFF; Cypro-Minoan
28913000..1342F; Egyptian Hieroglyphs
29013430..1345F; Egyptian Hieroglyph Format Controls
29114400..1467F; Anatolian Hieroglyphs
29216800..16A3F; Bamum Supplement
29316A40..16A6F; Mro
29416A70..16ACF; Tangsa
29516AD0..16AFF; Bassa Vah
29616B00..16B8F; Pahawh Hmong
29716E40..16E9F; Medefaidrin
29816F00..16F9F; Miao
29916FE0..16FFF; Ideographic Symbols and Punctuation
30017000..187FF; Tangut
30118800..18AFF; Tangut Components
30218B00..18CFF; Khitan Small Script
30318D00..18D7F; Tangut Supplement
3041AFF0..1AFFF; Kana Extended-B
3051B000..1B0FF; Kana Supplement
3061B100..1B12F; Kana Extended-A
3071B130..1B16F; Small Kana Extension
3081B170..1B2FF; Nushu
3091BC00..1BC9F; Duployan
3101BCA0..1BCAF; Shorthand Format Controls
3111CF00..1CFCF; Znamenny Musical Notation
3121D000..1D0FF; Byzantine Musical Symbols
3131D100..1D1FF; Musical Symbols
3141D200..1D24F; Ancient Greek Musical Notation
3151D2C0..1D2DF; Kaktovik Numerals
3161D2E0..1D2FF; Mayan Numerals
3171D300..1D35F; Tai Xuan Jing Symbols
3181D360..1D37F; Counting Rod Numerals
3191D400..1D7FF; Mathematical Alphanumeric Symbols
3201D800..1DAAF; Sutton SignWriting
3211DF00..1DFFF; Latin Extended-G
3221E000..1E02F; Glagolitic Supplement
3231E030..1E08F; Cyrillic Extended-D
3241E100..1E14F; Nyiakeng Puachue Hmong
3251E290..1E2BF; Toto
3261E2C0..1E2FF; Wancho
3271E4D0..1E4FF; Nag Mundari
3281E7E0..1E7FF; Ethiopic Extended-B
3291E800..1E8DF; Mende Kikakui
3301E900..1E95F; Adlam
3311EC70..1ECBF; Indic Siyaq Numbers
3321ED00..1ED4F; Ottoman Siyaq Numbers
3331EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
3341F000..1F02F; Mahjong Tiles
3351F030..1F09F; Domino Tiles
3361F0A0..1F0FF; Playing Cards
3371F100..1F1FF; Enclosed Alphanumeric Supplement
3381F200..1F2FF; Enclosed Ideographic Supplement
3391F300..1F5FF; Miscellaneous Symbols and Pictographs
3401F600..1F64F; Emoticons
3411F650..1F67F; Ornamental Dingbats
3421F680..1F6FF; Transport and Map Symbols
3431F700..1F77F; Alchemical Symbols
3441F780..1F7FF; Geometric Shapes Extended
3451F800..1F8FF; Supplemental Arrows-C
3461F900..1F9FF; Supplemental Symbols and Pictographs
3471FA00..1FA6F; Chess Symbols
3481FA70..1FAFF; Symbols and Pictographs Extended-A
3491FB00..1FBFF; Symbols for Legacy Computing
35020000..2A6DF; CJK Unified Ideographs Extension B
3512A700..2B73F; CJK Unified Ideographs Extension C
3522B740..2B81F; CJK Unified Ideographs Extension D
3532B820..2CEAF; CJK Unified Ideographs Extension E
3542CEB0..2EBEF; CJK Unified Ideographs Extension F
3552F800..2FA1F; CJK Compatibility Ideographs Supplement
35630000..3134F; CJK Unified Ideographs Extension G
35731350..323AF; CJK Unified Ideographs Extension H
358E0000..E007F; Tags
359E0100..E01EF; Variation Selectors Supplement
360F0000..FFFFF; Supplementary Private Use Area-A
361100000..10FFFF; Supplementary Private Use Area-B
362
363# EOF
364