mirror of
https://github.com/openjdk/jdk.git
synced 2025-08-28 07:14:30 +02:00
8296246: Update Unicode Data Files to Version 15.1.0
Reviewed-by: erikj, joehw, srl, rriggs
This commit is contained in:
Naoto Sato
parent
a021dbcb9e
commit
7c991cc567
22 changed files with 1511 additions and 224 deletions
|
|
@ -1,6 +1,6 @@
|
|||
# Blocks-15.0.0.txt
|
||||
# Date: 2022-01-28, 20:58:00 GMT [KW]
|
||||
# Copyright (c) 2022 Unicode, Inc.
|
||||
# Blocks-15.1.0.txt
|
||||
# Date: 2023-07-28, 15:47:20 GMT
|
||||
# Copyright (c) 2023 Unicode, Inc.
|
||||
# For terms of use, see https://www.unicode.org/terms_of_use.html
|
||||
#
|
||||
# Unicode Character Database
|
||||
|
|
@ -352,6 +352,7 @@ FFF0..FFFF; Specials
|
|||
2B740..2B81F; CJK Unified Ideographs Extension D
|
||||
2B820..2CEAF; CJK Unified Ideographs Extension E
|
||||
2CEB0..2EBEF; CJK Unified Ideographs Extension F
|
||||
2EBF0..2EE5F; CJK Unified Ideographs Extension I
|
||||
2F800..2FA1F; CJK Compatibility Ideographs Supplement
|
||||
30000..3134F; CJK Unified Ideographs Extension G
|
||||
31350..323AF; CJK Unified Ideographs Extension H
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# DerivedCoreProperties-15.0.0.txt
|
||||
# Date: 2022-08-05, 22:17:05 GMT
|
||||
# Copyright (c) 2022 Unicode, Inc.
|
||||
# DerivedCoreProperties-15.1.0.txt
|
||||
# Date: 2023-08-07, 15:21:24 GMT
|
||||
# Copyright (c) 2023 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 https://www.unicode.org/terms_of_use.html
|
||||
#
|
||||
|
|
@ -1397,11 +1397,12 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
|
|||
2B740..2B81D ; Alphabetic # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
|
||||
2B820..2CEA1 ; Alphabetic # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
|
||||
2CEB0..2EBE0 ; Alphabetic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
|
||||
2EBF0..2EE5D ; Alphabetic # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
|
||||
2F800..2FA1D ; Alphabetic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
|
||||
30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
|
||||
31350..323AF ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
|
||||
|
||||
# Total code points: 137765
|
||||
# Total code points: 138387
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -6853,11 +6854,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
|
|||
2B740..2B81D ; ID_Start # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
|
||||
2B820..2CEA1 ; ID_Start # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
|
||||
2CEB0..2EBE0 ; ID_Start # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
|
||||
2EBF0..2EE5D ; ID_Start # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
|
||||
2F800..2FA1D ; ID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
|
||||
30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
|
||||
31350..323AF ; ID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
|
||||
|
||||
# Total code points: 136345
|
||||
# Total code points: 136967
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -7438,6 +7440,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
|
|||
1FE0..1FEC ; ID_Continue # L& [13] GREEK SMALL LETTER UPSILON WITH VRACHY..GREEK CAPITAL LETTER RHO WITH DASIA
|
||||
1FF2..1FF4 ; ID_Continue # L& [3] GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI..GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI
|
||||
1FF6..1FFC ; ID_Continue # L& [7] GREEK SMALL LETTER OMEGA WITH PERISPOMENI..GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI
|
||||
200C..200D ; ID_Continue # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER
|
||||
203F..2040 ; ID_Continue # Pc [2] UNDERTIE..CHARACTER TIE
|
||||
2054 ; ID_Continue # Pc INVERTED UNDERTIE
|
||||
2071 ; ID_Continue # Lm SUPERSCRIPT LATIN SMALL LETTER I
|
||||
|
|
@ -7504,6 +7507,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
|
|||
309D..309E ; ID_Continue # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK
|
||||
309F ; ID_Continue # Lo HIRAGANA DIGRAPH YORI
|
||||
30A1..30FA ; ID_Continue # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO
|
||||
30FB ; ID_Continue # Po KATAKANA MIDDLE DOT
|
||||
30FC..30FE ; ID_Continue # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK
|
||||
30FF ; ID_Continue # Lo KATAKANA DIGRAPH KOTO
|
||||
3105..312F ; ID_Continue # Lo [43] BOPOMOFO LETTER B..BOPOMOFO LETTER NN
|
||||
|
|
@ -7683,6 +7687,7 @@ FF10..FF19 ; ID_Continue # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NIN
|
|||
FF21..FF3A ; ID_Continue # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z
|
||||
FF3F ; ID_Continue # Pc FULLWIDTH LOW LINE
|
||||
FF41..FF5A ; ID_Continue # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z
|
||||
FF65 ; ID_Continue # Po HALFWIDTH KATAKANA MIDDLE DOT
|
||||
FF66..FF6F ; ID_Continue # Lo [10] HALFWIDTH KATAKANA LETTER WO..HALFWIDTH KATAKANA LETTER SMALL TU
|
||||
FF70 ; ID_Continue # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
|
||||
FF71..FF9D ; ID_Continue # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAKANA LETTER N
|
||||
|
|
@ -8207,12 +8212,13 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
|
|||
2B740..2B81D ; ID_Continue # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
|
||||
2B820..2CEA1 ; ID_Continue # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
|
||||
2CEB0..2EBE0 ; ID_Continue # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
|
||||
2EBF0..2EE5D ; ID_Continue # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
|
||||
2F800..2FA1D ; ID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
|
||||
30000..3134A ; ID_Continue # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
|
||||
31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
|
||||
E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
|
||||
|
||||
# Total code points: 139482
|
||||
# Total code points: 140108
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -8962,11 +8968,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
|
|||
2B740..2B81D ; XID_Start # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
|
||||
2B820..2CEA1 ; XID_Start # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
|
||||
2CEB0..2EBE0 ; XID_Start # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
|
||||
2EBF0..2EE5D ; XID_Start # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
|
||||
2F800..2FA1D ; XID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
|
||||
30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
|
||||
31350..323AF ; XID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
|
||||
|
||||
# Total code points: 136322
|
||||
# Total code points: 136944
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -9543,6 +9550,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
|
|||
1FE0..1FEC ; XID_Continue # L& [13] GREEK SMALL LETTER UPSILON WITH VRACHY..GREEK CAPITAL LETTER RHO WITH DASIA
|
||||
1FF2..1FF4 ; XID_Continue # L& [3] GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI..GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI
|
||||
1FF6..1FFC ; XID_Continue # L& [7] GREEK SMALL LETTER OMEGA WITH PERISPOMENI..GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI
|
||||
200C..200D ; XID_Continue # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER
|
||||
203F..2040 ; XID_Continue # Pc [2] UNDERTIE..CHARACTER TIE
|
||||
2054 ; XID_Continue # Pc INVERTED UNDERTIE
|
||||
2071 ; XID_Continue # Lm SUPERSCRIPT LATIN SMALL LETTER I
|
||||
|
|
@ -9608,6 +9616,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
|
|||
309D..309E ; XID_Continue # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK
|
||||
309F ; XID_Continue # Lo HIRAGANA DIGRAPH YORI
|
||||
30A1..30FA ; XID_Continue # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO
|
||||
30FB ; XID_Continue # Po KATAKANA MIDDLE DOT
|
||||
30FC..30FE ; XID_Continue # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK
|
||||
30FF ; XID_Continue # Lo KATAKANA DIGRAPH KOTO
|
||||
3105..312F ; XID_Continue # Lo [43] BOPOMOFO LETTER B..BOPOMOFO LETTER NN
|
||||
|
|
@ -9793,6 +9802,7 @@ FF10..FF19 ; XID_Continue # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NI
|
|||
FF21..FF3A ; XID_Continue # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z
|
||||
FF3F ; XID_Continue # Pc FULLWIDTH LOW LINE
|
||||
FF41..FF5A ; XID_Continue # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z
|
||||
FF65 ; XID_Continue # Po HALFWIDTH KATAKANA MIDDLE DOT
|
||||
FF66..FF6F ; XID_Continue # Lo [10] HALFWIDTH KATAKANA LETTER WO..HALFWIDTH KATAKANA LETTER SMALL TU
|
||||
FF70 ; XID_Continue # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
|
||||
FF71..FF9D ; XID_Continue # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAKANA LETTER N
|
||||
|
|
@ -10317,12 +10327,13 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
|
|||
2B740..2B81D ; XID_Continue # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
|
||||
2B820..2CEA1 ; XID_Continue # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
|
||||
2CEB0..2EBE0 ; XID_Continue # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
|
||||
2EBF0..2EE5D ; XID_Continue # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
|
||||
2F800..2FA1D ; XID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
|
||||
30000..3134A ; XID_Continue # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
|
||||
31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
|
||||
E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
|
||||
|
||||
# Total code points: 139463
|
||||
# Total code points: 140089
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -10335,6 +10346,15 @@ E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTO
|
|||
# - FFF9..FFFB (Interlinear annotation format characters)
|
||||
# - 13430..13440 (Egyptian hieroglyph format characters)
|
||||
# - Prepended_Concatenation_Mark (Exceptional format characters that should be visible)
|
||||
#
|
||||
# There are currently no stability guarantees for DICP. However, the
|
||||
# values of DICP interact with the derivation of XID_Continue
|
||||
# and NFKC_CF, for which there are stability guarantees.
|
||||
# Maintainers of this property should note that in the
|
||||
# unlikely case that the DICP value changes for an existing character
|
||||
# which is also XID_Continue=Yes, then exceptions must be put
|
||||
# in place to ensure that the NFKC_CF mapping value for that
|
||||
# existing character does not change.
|
||||
|
||||
00AD ; Default_Ignorable_Code_Point # Cf SOFT HYPHEN
|
||||
034F ; Default_Ignorable_Code_Point # Mn COMBINING GRAPHEME JOINER
|
||||
|
|
@ -11602,7 +11622,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE
|
|||
2E80..2E99 ; Grapheme_Base # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP
|
||||
2E9B..2EF3 ; Grapheme_Base # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE
|
||||
2F00..2FD5 ; Grapheme_Base # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE
|
||||
2FF0..2FFB ; Grapheme_Base # So [12] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
|
||||
2FF0..2FFF ; Grapheme_Base # So [16] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER ROTATION
|
||||
3000 ; Grapheme_Base # Zs IDEOGRAPHIC SPACE
|
||||
3001..3003 ; Grapheme_Base # Po [3] IDEOGRAPHIC COMMA..DITTO MARK
|
||||
3004 ; Grapheme_Base # So JAPANESE INDUSTRIAL STANDARD SYMBOL
|
||||
|
|
@ -11657,6 +11677,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE
|
|||
3196..319F ; Grapheme_Base # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK
|
||||
31A0..31BF ; Grapheme_Base # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH
|
||||
31C0..31E3 ; Grapheme_Base # So [36] CJK STROKE T..CJK STROKE Q
|
||||
31EF ; Grapheme_Base # So IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION
|
||||
31F0..31FF ; Grapheme_Base # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO
|
||||
3200..321E ; Grapheme_Base # So [31] PARENTHESIZED HANGUL KIYEOK..PARENTHESIZED KOREAN CHARACTER O HU
|
||||
3220..3229 ; Grapheme_Base # No [10] PARENTHESIZED IDEOGRAPH ONE..PARENTHESIZED IDEOGRAPH TEN
|
||||
|
|
@ -12497,11 +12518,12 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME
|
|||
2B740..2B81D ; Grapheme_Base # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
|
||||
2B820..2CEA1 ; Grapheme_Base # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
|
||||
2CEB0..2EBE0 ; Grapheme_Base # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
|
||||
2EBF0..2EE5D ; Grapheme_Base # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
|
||||
2F800..2FA1D ; Grapheme_Base # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
|
||||
30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
|
||||
31350..323AF ; Grapheme_Base # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
|
||||
|
||||
# Total code points: 146986
|
||||
# Total code points: 147613
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -12572,4 +12594,239 @@ ABED ; Grapheme_Link # Mn MEETEI MAYEK APUN IYEK
|
|||
|
||||
# Total code points: 65
|
||||
|
||||
# ================================================
|
||||
|
||||
# Derived Property: Indic_Conjunct_Break
|
||||
# Generated from the Grapheme_Cluster_Break, Indic_Syllabic_Category,
|
||||
# Canonical_Combining_Class, and Script properties as described in UAX #44:
|
||||
# https://www.unicode.org/reports/tr44/.
|
||||
|
||||
# All code points not explicitly listed for Indic_Conjunct_Break
|
||||
# have the value None.
|
||||
|
||||
# @missing: 0000..10FFFF; InCB; None
|
||||
|
||||
# ================================================
|
||||
|
||||
# Indic_Conjunct_Break=Linker
|
||||
|
||||
094D ; InCB; Linker # Mn DEVANAGARI SIGN VIRAMA
|
||||
09CD ; InCB; Linker # Mn BENGALI SIGN VIRAMA
|
||||
0ACD ; InCB; Linker # Mn GUJARATI SIGN VIRAMA
|
||||
0B4D ; InCB; Linker # Mn ORIYA SIGN VIRAMA
|
||||
0C4D ; InCB; Linker # Mn TELUGU SIGN VIRAMA
|
||||
0D4D ; InCB; Linker # Mn MALAYALAM SIGN VIRAMA
|
||||
|
||||
# Total code points: 6
|
||||
|
||||
# ================================================
|
||||
|
||||
# Indic_Conjunct_Break=Consonant
|
||||
|
||||
0915..0939 ; InCB; Consonant # Lo [37] DEVANAGARI LETTER KA..DEVANAGARI LETTER HA
|
||||
0958..095F ; InCB; Consonant # Lo [8] DEVANAGARI LETTER QA..DEVANAGARI LETTER YYA
|
||||
0978..097F ; InCB; Consonant # Lo [8] DEVANAGARI LETTER MARWARI DDA..DEVANAGARI LETTER BBA
|
||||
0995..09A8 ; InCB; Consonant # Lo [20] BENGALI LETTER KA..BENGALI LETTER NA
|
||||
09AA..09B0 ; InCB; Consonant # Lo [7] BENGALI LETTER PA..BENGALI LETTER RA
|
||||
09B2 ; InCB; Consonant # Lo BENGALI LETTER LA
|
||||
09B6..09B9 ; InCB; Consonant # Lo [4] BENGALI LETTER SHA..BENGALI LETTER HA
|
||||
09DC..09DD ; InCB; Consonant # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA
|
||||
09DF ; InCB; Consonant # Lo BENGALI LETTER YYA
|
||||
09F0..09F1 ; InCB; Consonant # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL
|
||||
0A95..0AA8 ; InCB; Consonant # Lo [20] GUJARATI LETTER KA..GUJARATI LETTER NA
|
||||
0AAA..0AB0 ; InCB; Consonant # Lo [7] GUJARATI LETTER PA..GUJARATI LETTER RA
|
||||
0AB2..0AB3 ; InCB; Consonant # Lo [2] GUJARATI LETTER LA..GUJARATI LETTER LLA
|
||||
0AB5..0AB9 ; InCB; Consonant # Lo [5] GUJARATI LETTER VA..GUJARATI LETTER HA
|
||||
0AF9 ; InCB; Consonant # Lo GUJARATI LETTER ZHA
|
||||
0B15..0B28 ; InCB; Consonant # Lo [20] ORIYA LETTER KA..ORIYA LETTER NA
|
||||
0B2A..0B30 ; InCB; Consonant # Lo [7] ORIYA LETTER PA..ORIYA LETTER RA
|
||||
0B32..0B33 ; InCB; Consonant # Lo [2] ORIYA LETTER LA..ORIYA LETTER LLA
|
||||
0B35..0B39 ; InCB; Consonant # Lo [5] ORIYA LETTER VA..ORIYA LETTER HA
|
||||
0B5C..0B5D ; InCB; Consonant # Lo [2] ORIYA LETTER RRA..ORIYA LETTER RHA
|
||||
0B5F ; InCB; Consonant # Lo ORIYA LETTER YYA
|
||||
0B71 ; InCB; Consonant # Lo ORIYA LETTER WA
|
||||
0C15..0C28 ; InCB; Consonant # Lo [20] TELUGU LETTER KA..TELUGU LETTER NA
|
||||
0C2A..0C39 ; InCB; Consonant # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA
|
||||
0C58..0C5A ; InCB; Consonant # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA
|
||||
0D15..0D3A ; InCB; Consonant # Lo [38] MALAYALAM LETTER KA..MALAYALAM LETTER TTTA
|
||||
|
||||
# Total code points: 240
|
||||
|
||||
# ================================================
|
||||
|
||||
# Indic_Conjunct_Break=Extend
|
||||
|
||||
0300..034E ; InCB; Extend # Mn [79] COMBINING GRAVE ACCENT..COMBINING UPWARDS ARROW BELOW
|
||||
0350..036F ; InCB; Extend # Mn [32] COMBINING RIGHT ARROWHEAD ABOVE..COMBINING LATIN SMALL LETTER X
|
||||
0483..0487 ; InCB; Extend # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE
|
||||
0591..05BD ; InCB; Extend # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG
|
||||
05BF ; InCB; Extend # Mn HEBREW POINT RAFE
|
||||
05C1..05C2 ; InCB; Extend # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT
|
||||
05C4..05C5 ; InCB; Extend # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT
|
||||
05C7 ; InCB; Extend # Mn HEBREW POINT QAMATS QATAN
|
||||
0610..061A ; InCB; Extend # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA
|
||||
064B..065F ; InCB; Extend # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW
|
||||
0670 ; InCB; Extend # Mn ARABIC LETTER SUPERSCRIPT ALEF
|
||||
06D6..06DC ; InCB; Extend # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN
|
||||
06DF..06E4 ; InCB; Extend # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA
|
||||
06E7..06E8 ; InCB; Extend # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON
|
||||
06EA..06ED ; InCB; Extend # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM
|
||||
0711 ; InCB; Extend # Mn SYRIAC LETTER SUPERSCRIPT ALAPH
|
||||
0730..074A ; InCB; Extend # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH
|
||||
07EB..07F3 ; InCB; Extend # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE
|
||||
07FD ; InCB; Extend # Mn NKO DANTAYALAN
|
||||
0816..0819 ; InCB; Extend # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH
|
||||
081B..0823 ; InCB; Extend # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A
|
||||
0825..0827 ; InCB; Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U
|
||||
0829..082D ; InCB; Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA
|
||||
0859..085B ; InCB; Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK
|
||||
0898..089F ; InCB; Extend # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA
|
||||
08CA..08E1 ; InCB; Extend # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA
|
||||
08E3..08FF ; InCB; Extend # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA
|
||||
093C ; InCB; Extend # Mn DEVANAGARI SIGN NUKTA
|
||||
0951..0954 ; InCB; Extend # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT
|
||||
09BC ; InCB; Extend # Mn BENGALI SIGN NUKTA
|
||||
09FE ; InCB; Extend # Mn BENGALI SANDHI MARK
|
||||
0A3C ; InCB; Extend # Mn GURMUKHI SIGN NUKTA
|
||||
0ABC ; InCB; Extend # Mn GUJARATI SIGN NUKTA
|
||||
0B3C ; InCB; Extend # Mn ORIYA SIGN NUKTA
|
||||
0C3C ; InCB; Extend # Mn TELUGU SIGN NUKTA
|
||||
0C55..0C56 ; InCB; Extend # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK
|
||||
0CBC ; InCB; Extend # Mn KANNADA SIGN NUKTA
|
||||
0D3B..0D3C ; InCB; Extend # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
|
||||
0E38..0E3A ; InCB; Extend # Mn [3] THAI CHARACTER SARA U..THAI CHARACTER PHINTHU
|
||||
0E48..0E4B ; InCB; Extend # Mn [4] THAI CHARACTER MAI EK..THAI CHARACTER MAI CHATTAWA
|
||||
0EB8..0EBA ; InCB; Extend # Mn [3] LAO VOWEL SIGN U..LAO SIGN PALI VIRAMA
|
||||
0EC8..0ECB ; InCB; Extend # Mn [4] LAO TONE MAI EK..LAO TONE MAI CATAWA
|
||||
0F18..0F19 ; InCB; Extend # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS
|
||||
0F35 ; InCB; Extend # Mn TIBETAN MARK NGAS BZUNG NYI ZLA
|
||||
0F37 ; InCB; Extend # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS
|
||||
0F39 ; InCB; Extend # Mn TIBETAN MARK TSA -PHRU
|
||||
0F71..0F72 ; InCB; Extend # Mn [2] TIBETAN VOWEL SIGN AA..TIBETAN VOWEL SIGN I
|
||||
0F74 ; InCB; Extend # Mn TIBETAN VOWEL SIGN U
|
||||
0F7A..0F7D ; InCB; Extend # Mn [4] TIBETAN VOWEL SIGN E..TIBETAN VOWEL SIGN OO
|
||||
0F80 ; InCB; Extend # Mn TIBETAN VOWEL SIGN REVERSED I
|
||||
0F82..0F84 ; InCB; Extend # Mn [3] TIBETAN SIGN NYI ZLA NAA DA..TIBETAN MARK HALANTA
|
||||
0F86..0F87 ; InCB; Extend # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS
|
||||
0FC6 ; InCB; Extend # Mn TIBETAN SYMBOL PADMA GDAN
|
||||
1037 ; InCB; Extend # Mn MYANMAR SIGN DOT BELOW
|
||||
1039..103A ; InCB; Extend # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT
|
||||
108D ; InCB; Extend # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE
|
||||
135D..135F ; InCB; Extend # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK
|
||||
1714 ; InCB; Extend # Mn TAGALOG SIGN VIRAMA
|
||||
17D2 ; InCB; Extend # Mn KHMER SIGN COENG
|
||||
17DD ; InCB; Extend # Mn KHMER SIGN ATTHACAN
|
||||
18A9 ; InCB; Extend # Mn MONGOLIAN LETTER ALI GALI DAGALGA
|
||||
1939..193B ; InCB; Extend # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I
|
||||
1A17..1A18 ; InCB; Extend # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U
|
||||
1A60 ; InCB; Extend # Mn TAI THAM SIGN SAKOT
|
||||
1A75..1A7C ; InCB; Extend # Mn [8] TAI THAM SIGN TONE-1..TAI THAM SIGN KHUEN-LUE KARAN
|
||||
1A7F ; InCB; Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT
|
||||
1AB0..1ABD ; InCB; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW
|
||||
1ABF..1ACE ; InCB; Extend # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T
|
||||
1B34 ; InCB; Extend # Mn BALINESE SIGN REREKAN
|
||||
1B6B..1B73 ; InCB; Extend # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG
|
||||
1BAB ; InCB; Extend # Mn SUNDANESE SIGN VIRAMA
|
||||
1BE6 ; InCB; Extend # Mn BATAK SIGN TOMPI
|
||||
1C37 ; InCB; Extend # Mn LEPCHA SIGN NUKTA
|
||||
1CD0..1CD2 ; InCB; Extend # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA
|
||||
1CD4..1CE0 ; InCB; Extend # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA
|
||||
1CE2..1CE8 ; InCB; Extend # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL
|
||||
1CED ; InCB; Extend # Mn VEDIC SIGN TIRYAK
|
||||
1CF4 ; InCB; Extend # Mn VEDIC TONE CANDRA ABOVE
|
||||
1CF8..1CF9 ; InCB; Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE
|
||||
1DC0..1DFF ; InCB; Extend # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
|
||||
200D ; InCB; Extend # Cf ZERO WIDTH JOINER
|
||||
20D0..20DC ; InCB; Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
|
||||
20E1 ; InCB; Extend # Mn COMBINING LEFT RIGHT ARROW ABOVE
|
||||
20E5..20F0 ; InCB; Extend # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE
|
||||
2CEF..2CF1 ; InCB; Extend # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS
|
||||
2D7F ; InCB; Extend # Mn TIFINAGH CONSONANT JOINER
|
||||
2DE0..2DFF ; InCB; Extend # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS
|
||||
302A..302D ; InCB; Extend # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK
|
||||
302E..302F ; InCB; Extend # Mc [2] HANGUL SINGLE DOT TONE MARK..HANGUL DOUBLE DOT TONE MARK
|
||||
3099..309A ; InCB; Extend # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
|
||||
A66F ; InCB; Extend # Mn COMBINING CYRILLIC VZMET
|
||||
A674..A67D ; InCB; Extend # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK
|
||||
A69E..A69F ; InCB; Extend # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E
|
||||
A6F0..A6F1 ; InCB; Extend # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS
|
||||
A82C ; InCB; Extend # Mn SYLOTI NAGRI SIGN ALTERNATE HASANTA
|
||||
A8E0..A8F1 ; InCB; Extend # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA
|
||||
A92B..A92D ; InCB; Extend # Mn [3] KAYAH LI TONE PLOPHU..KAYAH LI TONE CALYA PLOPHU
|
||||
A9B3 ; InCB; Extend # Mn JAVANESE SIGN CECAK TELU
|
||||
AAB0 ; InCB; Extend # Mn TAI VIET MAI KANG
|
||||
AAB2..AAB4 ; InCB; Extend # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U
|
||||
AAB7..AAB8 ; InCB; Extend # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA
|
||||
AABE..AABF ; InCB; Extend # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK
|
||||
AAC1 ; InCB; Extend # Mn TAI VIET TONE MAI THO
|
||||
AAF6 ; InCB; Extend # Mn MEETEI MAYEK VIRAMA
|
||||
ABED ; InCB; Extend # Mn MEETEI MAYEK APUN IYEK
|
||||
FB1E ; InCB; Extend # Mn HEBREW POINT JUDEO-SPANISH VARIKA
|
||||
FE20..FE2F ; InCB; Extend # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF
|
||||
101FD ; InCB; Extend # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE
|
||||
102E0 ; InCB; Extend # Mn COPTIC EPACT THOUSANDS MARK
|
||||
10376..1037A ; InCB; Extend # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII
|
||||
10A0D ; InCB; Extend # Mn KHAROSHTHI SIGN DOUBLE RING BELOW
|
||||
10A0F ; InCB; Extend # Mn KHAROSHTHI SIGN VISARGA
|
||||
10A38..10A3A ; InCB; Extend # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW
|
||||
10A3F ; InCB; Extend # Mn KHAROSHTHI VIRAMA
|
||||
10AE5..10AE6 ; InCB; Extend # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW
|
||||
10D24..10D27 ; InCB; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
|
||||
10EAB..10EAC ; InCB; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK
|
||||
10EFD..10EFF ; InCB; Extend # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA
|
||||
10F46..10F50 ; InCB; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW
|
||||
10F82..10F85 ; InCB; Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW
|
||||
11070 ; InCB; Extend # Mn BRAHMI SIGN OLD TAMIL VIRAMA
|
||||
1107F ; InCB; Extend # Mn BRAHMI NUMBER JOINER
|
||||
110BA ; InCB; Extend # Mn KAITHI SIGN NUKTA
|
||||
11100..11102 ; InCB; Extend # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA
|
||||
11133..11134 ; InCB; Extend # Mn [2] CHAKMA VIRAMA..CHAKMA MAAYYAA
|
||||
11173 ; InCB; Extend # Mn MAHAJANI SIGN NUKTA
|
||||
111CA ; InCB; Extend # Mn SHARADA SIGN NUKTA
|
||||
11236 ; InCB; Extend # Mn KHOJKI SIGN NUKTA
|
||||
112E9..112EA ; InCB; Extend # Mn [2] KHUDAWADI SIGN NUKTA..KHUDAWADI SIGN VIRAMA
|
||||
1133B..1133C ; InCB; Extend # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA
|
||||
11366..1136C ; InCB; Extend # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX
|
||||
11370..11374 ; InCB; Extend # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA
|
||||
11446 ; InCB; Extend # Mn NEWA SIGN NUKTA
|
||||
1145E ; InCB; Extend # Mn NEWA SANDHI MARK
|
||||
114C3 ; InCB; Extend # Mn TIRHUTA SIGN NUKTA
|
||||
115C0 ; InCB; Extend # Mn SIDDHAM SIGN NUKTA
|
||||
116B7 ; InCB; Extend # Mn TAKRI SIGN NUKTA
|
||||
1172B ; InCB; Extend # Mn AHOM SIGN KILLER
|
||||
1183A ; InCB; Extend # Mn DOGRA SIGN NUKTA
|
||||
1193E ; InCB; Extend # Mn DIVES AKURU VIRAMA
|
||||
11943 ; InCB; Extend # Mn DIVES AKURU SIGN NUKTA
|
||||
11A34 ; InCB; Extend # Mn ZANABAZAR SQUARE SIGN VIRAMA
|
||||
11A47 ; InCB; Extend # Mn ZANABAZAR SQUARE SUBJOINER
|
||||
11A99 ; InCB; Extend # Mn SOYOMBO SUBJOINER
|
||||
11D42 ; InCB; Extend # Mn MASARAM GONDI SIGN NUKTA
|
||||
11D44..11D45 ; InCB; Extend # Mn [2] MASARAM GONDI SIGN HALANTA..MASARAM GONDI VIRAMA
|
||||
11D97 ; InCB; Extend # Mn GUNJALA GONDI VIRAMA
|
||||
11F42 ; InCB; Extend # Mn KAWI CONJOINER
|
||||
16AF0..16AF4 ; InCB; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
|
||||
16B30..16B36 ; InCB; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
|
||||
1BC9E ; InCB; Extend # Mn DUPLOYAN DOUBLE MARK
|
||||
1D165 ; InCB; Extend # Mc MUSICAL SYMBOL COMBINING STEM
|
||||
1D167..1D169 ; InCB; Extend # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3
|
||||
1D16E..1D172 ; InCB; Extend # Mc [5] MUSICAL SYMBOL COMBINING FLAG-1..MUSICAL SYMBOL COMBINING FLAG-5
|
||||
1D17B..1D182 ; InCB; Extend # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE
|
||||
1D185..1D18B ; InCB; Extend # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
|
||||
1D1AA..1D1AD ; InCB; Extend # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
|
||||
1D242..1D244 ; InCB; Extend # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
|
||||
1E000..1E006 ; InCB; Extend # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
|
||||
1E008..1E018 ; InCB; Extend # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
|
||||
1E01B..1E021 ; InCB; Extend # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
|
||||
1E023..1E024 ; InCB; Extend # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
|
||||
1E026..1E02A ; InCB; Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
|
||||
1E08F ; InCB; Extend # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
1E130..1E136 ; InCB; Extend # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
|
||||
1E2AE ; InCB; Extend # Mn TOTO SIGN RISING TONE
|
||||
1E2EC..1E2EF ; InCB; Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI
|
||||
1E4EC..1E4EF ; InCB; Extend # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH
|
||||
1E8D0..1E8D6 ; InCB; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
|
||||
1E944..1E94A ; InCB; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA
|
||||
|
||||
# Total code points: 884
|
||||
|
||||
# EOF
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# NormalizationTest-15.0.0.txt
|
||||
# Date: 2022-04-02, 01:29:09 GMT
|
||||
# Copyright (c) 2022 Unicode, Inc.
|
||||
# NormalizationTest-15.1.0.txt
|
||||
# Date: 2023-01-05, 20:34:44 GMT
|
||||
# Copyright (c) 2023 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 https://www.unicode.org/terms_of_use.html
|
||||
#
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# PropList-15.0.0.txt
|
||||
# Date: 2022-08-05, 22:17:16 GMT
|
||||
# Copyright (c) 2022 Unicode, Inc.
|
||||
# PropList-15.1.0.txt
|
||||
# Date: 2023-08-01, 21:56:53 GMT
|
||||
# Copyright (c) 2023 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 https://www.unicode.org/terms_of_use.html
|
||||
#
|
||||
|
|
@ -856,11 +856,12 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
|
|||
2B740..2B81D ; Ideographic # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
|
||||
2B820..2CEA1 ; Ideographic # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
|
||||
2CEB0..2EBE0 ; Ideographic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
|
||||
2EBF0..2EE5D ; Ideographic # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
|
||||
2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
|
||||
30000..3134A ; Ideographic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
|
||||
31350..323AF ; Ideographic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
|
||||
|
||||
# Total code points: 105854
|
||||
# Total code points: 106476
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -1241,9 +1242,10 @@ E0020..E007F ; Other_Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG
|
|||
# ================================================
|
||||
|
||||
2FF0..2FF1 ; IDS_Binary_Operator # So [2] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER ABOVE TO BELOW
|
||||
2FF4..2FFB ; IDS_Binary_Operator # So [8] IDEOGRAPHIC DESCRIPTION CHARACTER FULL SURROUND..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
|
||||
2FF4..2FFD ; IDS_Binary_Operator # So [10] IDEOGRAPHIC DESCRIPTION CHARACTER FULL SURROUND..IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM LOWER RIGHT
|
||||
31EF ; IDS_Binary_Operator # So IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION
|
||||
|
||||
# Total code points: 10
|
||||
# Total code points: 13
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -1253,6 +1255,12 @@ E0020..E007F ; Other_Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG
|
|||
|
||||
# ================================================
|
||||
|
||||
2FFE..2FFF ; IDS_Unary_Operator # So [2] IDEOGRAPHIC DESCRIPTION CHARACTER HORIZONTAL REFLECTION..IDEOGRAPHIC DESCRIPTION CHARACTER ROTATION
|
||||
|
||||
# Total code points: 2
|
||||
|
||||
# ================================================
|
||||
|
||||
2E80..2E99 ; Radical # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP
|
||||
2E9B..2EF3 ; Radical # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE
|
||||
2F00..2FD5 ; Radical # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE
|
||||
|
|
@ -1275,10 +1283,11 @@ FA27..FA29 ; Unified_Ideograph # Lo [3] CJK COMPATIBILITY IDEOGRAPH-FA27..C
|
|||
2B740..2B81D ; Unified_Ideograph # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
|
||||
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
|
||||
2EBF0..2EE5D ; Unified_Ideograph # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
|
||||
30000..3134A ; Unified_Ideograph # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
|
||||
31350..323AF ; Unified_Ideograph # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
|
||||
|
||||
# Total code points: 97058
|
||||
# Total code points: 97680
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -1376,8 +1385,58 @@ AABB..AABC ; Logical_Order_Exception # Lo [2] TAI VIET VOWEL AUE..TAI VIET
|
|||
0387 ; Other_ID_Continue # Po GREEK ANO TELEIA
|
||||
1369..1371 ; Other_ID_Continue # No [9] ETHIOPIC DIGIT ONE..ETHIOPIC DIGIT NINE
|
||||
19DA ; Other_ID_Continue # No NEW TAI LUE THAM DIGIT ONE
|
||||
200C..200D ; Other_ID_Continue # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER
|
||||
30FB ; Other_ID_Continue # Po KATAKANA MIDDLE DOT
|
||||
FF65 ; Other_ID_Continue # Po HALFWIDTH KATAKANA MIDDLE DOT
|
||||
|
||||
# Total code points: 12
|
||||
# Total code points: 16
|
||||
|
||||
# ================================================
|
||||
|
||||
00B2..00B3 ; ID_Compat_Math_Continue # No [2] SUPERSCRIPT TWO..SUPERSCRIPT THREE
|
||||
00B9 ; ID_Compat_Math_Continue # No SUPERSCRIPT ONE
|
||||
2070 ; ID_Compat_Math_Continue # No SUPERSCRIPT ZERO
|
||||
2074..2079 ; ID_Compat_Math_Continue # No [6] SUPERSCRIPT FOUR..SUPERSCRIPT NINE
|
||||
207A..207C ; ID_Compat_Math_Continue # Sm [3] SUPERSCRIPT PLUS SIGN..SUPERSCRIPT EQUALS SIGN
|
||||
207D ; ID_Compat_Math_Continue # Ps SUPERSCRIPT LEFT PARENTHESIS
|
||||
207E ; ID_Compat_Math_Continue # Pe SUPERSCRIPT RIGHT PARENTHESIS
|
||||
2080..2089 ; ID_Compat_Math_Continue # No [10] SUBSCRIPT ZERO..SUBSCRIPT NINE
|
||||
208A..208C ; ID_Compat_Math_Continue # Sm [3] SUBSCRIPT PLUS SIGN..SUBSCRIPT EQUALS SIGN
|
||||
208D ; ID_Compat_Math_Continue # Ps SUBSCRIPT LEFT PARENTHESIS
|
||||
208E ; ID_Compat_Math_Continue # Pe SUBSCRIPT RIGHT PARENTHESIS
|
||||
2202 ; ID_Compat_Math_Continue # Sm PARTIAL DIFFERENTIAL
|
||||
2207 ; ID_Compat_Math_Continue # Sm NABLA
|
||||
221E ; ID_Compat_Math_Continue # Sm INFINITY
|
||||
1D6C1 ; ID_Compat_Math_Continue # Sm MATHEMATICAL BOLD NABLA
|
||||
1D6DB ; ID_Compat_Math_Continue # Sm MATHEMATICAL BOLD PARTIAL DIFFERENTIAL
|
||||
1D6FB ; ID_Compat_Math_Continue # Sm MATHEMATICAL ITALIC NABLA
|
||||
1D715 ; ID_Compat_Math_Continue # Sm MATHEMATICAL ITALIC PARTIAL DIFFERENTIAL
|
||||
1D735 ; ID_Compat_Math_Continue # Sm MATHEMATICAL BOLD ITALIC NABLA
|
||||
1D74F ; ID_Compat_Math_Continue # Sm MATHEMATICAL BOLD ITALIC PARTIAL DIFFERENTIAL
|
||||
1D76F ; ID_Compat_Math_Continue # Sm MATHEMATICAL SANS-SERIF BOLD NABLA
|
||||
1D789 ; ID_Compat_Math_Continue # Sm MATHEMATICAL SANS-SERIF BOLD PARTIAL DIFFERENTIAL
|
||||
1D7A9 ; ID_Compat_Math_Continue # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC NABLA
|
||||
1D7C3 ; ID_Compat_Math_Continue # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL
|
||||
|
||||
# Total code points: 43
|
||||
|
||||
# ================================================
|
||||
|
||||
2202 ; ID_Compat_Math_Start # Sm PARTIAL DIFFERENTIAL
|
||||
2207 ; ID_Compat_Math_Start # Sm NABLA
|
||||
221E ; ID_Compat_Math_Start # Sm INFINITY
|
||||
1D6C1 ; ID_Compat_Math_Start # Sm MATHEMATICAL BOLD NABLA
|
||||
1D6DB ; ID_Compat_Math_Start # Sm MATHEMATICAL BOLD PARTIAL DIFFERENTIAL
|
||||
1D6FB ; ID_Compat_Math_Start # Sm MATHEMATICAL ITALIC NABLA
|
||||
1D715 ; ID_Compat_Math_Start # Sm MATHEMATICAL ITALIC PARTIAL DIFFERENTIAL
|
||||
1D735 ; ID_Compat_Math_Start # Sm MATHEMATICAL BOLD ITALIC NABLA
|
||||
1D74F ; ID_Compat_Math_Start # Sm MATHEMATICAL BOLD ITALIC PARTIAL DIFFERENTIAL
|
||||
1D76F ; ID_Compat_Math_Start # Sm MATHEMATICAL SANS-SERIF BOLD NABLA
|
||||
1D789 ; ID_Compat_Math_Start # Sm MATHEMATICAL SANS-SERIF BOLD PARTIAL DIFFERENTIAL
|
||||
1D7A9 ; ID_Compat_Math_Start # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC NABLA
|
||||
1D7C3 ; ID_Compat_Math_Start # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL
|
||||
|
||||
# Total code points: 13
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -1398,6 +1457,7 @@ AABB..AABC ; Logical_Order_Exception # Lo [2] TAI VIET VOWEL AUE..TAI VIET
|
|||
1367..1368 ; Sentence_Terminal # Po [2] ETHIOPIC QUESTION MARK..ETHIOPIC PARAGRAPH SEPARATOR
|
||||
166E ; Sentence_Terminal # Po CANADIAN SYLLABICS FULL STOP
|
||||
1735..1736 ; Sentence_Terminal # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION
|
||||
17D4..17D5 ; Sentence_Terminal # Po [2] KHMER SIGN KHAN..KHMER SIGN BARIYOOSAN
|
||||
1803 ; Sentence_Terminal # Po MONGOLIAN FULL STOP
|
||||
1809 ; Sentence_Terminal # Po MONGOLIAN MANCHU FULL STOP
|
||||
1944..1945 ; Sentence_Terminal # Po [2] LIMBU EXCLAMATION MARK..LIMBU QUESTION MARK
|
||||
|
|
@ -1462,7 +1522,7 @@ FF61 ; Sentence_Terminal # Po HALFWIDTH IDEOGRAPHIC FULL STOP
|
|||
1BC9F ; Sentence_Terminal # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP
|
||||
1DA88 ; Sentence_Terminal # Po SIGNWRITING FULL STOP
|
||||
|
||||
# Total code points: 154
|
||||
# Total code points: 156
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# PropertyValueAliases-15.0.0.txt
|
||||
# Date: 2022-08-05, 23:42:17 GMT
|
||||
# Copyright (c) 2022 Unicode, Inc.
|
||||
# PropertyValueAliases-15.1.0.txt
|
||||
# Date: 2023-08-07, 15:21:34 GMT
|
||||
# Copyright (c) 2023 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 https://www.unicode.org/terms_of_use.html
|
||||
#
|
||||
|
|
@ -91,6 +91,7 @@ age; 12.1 ; V12_1
|
|||
age; 13.0 ; V13_0
|
||||
age; 14.0 ; V14_0
|
||||
age; 15.0 ; V15_0
|
||||
age; 15.1 ; V15_1
|
||||
age; NA ; Unassigned
|
||||
|
||||
# Alphabetic (Alpha)
|
||||
|
|
@ -208,6 +209,7 @@ blk; CJK_Ext_E ; CJK_Unified_Ideographs_Extension_E
|
|||
blk; CJK_Ext_F ; CJK_Unified_Ideographs_Extension_F
|
||||
blk; CJK_Ext_G ; CJK_Unified_Ideographs_Extension_G
|
||||
blk; CJK_Ext_H ; CJK_Unified_Ideographs_Extension_H
|
||||
blk; CJK_Ext_I ; CJK_Unified_Ideographs_Extension_I
|
||||
blk; CJK_Radicals_Sup ; CJK_Radicals_Supplement
|
||||
blk; CJK_Strokes ; CJK_Strokes
|
||||
blk; CJK_Symbols ; CJK_Symbols_And_Punctuation
|
||||
|
|
@ -817,6 +819,21 @@ IDSB; Y ; Yes ; T
|
|||
IDST; N ; No ; F ; False
|
||||
IDST; Y ; Yes ; T ; True
|
||||
|
||||
# IDS_Unary_Operator (IDSU)
|
||||
|
||||
IDSU; N ; No ; F ; False
|
||||
IDSU; Y ; Yes ; T ; True
|
||||
|
||||
# ID_Compat_Math_Continue (ID_Compat_Math_Continue)
|
||||
|
||||
ID_Compat_Math_Continue; N ; No ; F ; False
|
||||
ID_Compat_Math_Continue; Y ; Yes ; T ; True
|
||||
|
||||
# ID_Compat_Math_Start (ID_Compat_Math_Start)
|
||||
|
||||
ID_Compat_Math_Start; N ; No ; F ; False
|
||||
ID_Compat_Math_Start; Y ; Yes ; T ; True
|
||||
|
||||
# ID_Continue (IDC)
|
||||
|
||||
IDC; N ; No ; F ; False
|
||||
|
|
@ -836,6 +853,13 @@ IDS; Y ; Yes ; T
|
|||
Ideo; N ; No ; F ; False
|
||||
Ideo; Y ; Yes ; T ; True
|
||||
|
||||
# Indic_Conjunct_Break (InCB)
|
||||
|
||||
InCB; Consonant ; Consonant
|
||||
InCB; Extend ; Extend
|
||||
InCB; Linker ; Linker
|
||||
InCB; None ; None
|
||||
|
||||
# Indic_Positional_Category (InPC)
|
||||
|
||||
InPC; Bottom ; Bottom
|
||||
|
|
@ -1074,7 +1098,10 @@ jt ; U ; Non_Joining
|
|||
# Line_Break (lb)
|
||||
|
||||
lb ; AI ; Ambiguous
|
||||
lb ; AK ; Aksara
|
||||
lb ; AL ; Alphabetic
|
||||
lb ; AP ; Aksara_Prebase
|
||||
lb ; AS ; Aksara_Start
|
||||
lb ; B2 ; Break_Both
|
||||
lb ; BA ; Break_After
|
||||
lb ; BB ; Break_Before
|
||||
|
|
@ -1112,6 +1139,8 @@ lb ; SA ; Complex_Context
|
|||
lb ; SG ; Surrogate
|
||||
lb ; SP ; Space
|
||||
lb ; SY ; Break_Symbols
|
||||
lb ; VF ; Virama_Final
|
||||
lb ; VI ; Virama
|
||||
lb ; WJ ; Word_Joiner
|
||||
lb ; XX ; Unknown
|
||||
lb ; ZW ; ZWSpace
|
||||
|
|
@ -1156,6 +1185,9 @@ NFKC_QC; M ; Maybe
|
|||
NFKC_QC; N ; No
|
||||
NFKC_QC; Y ; Yes
|
||||
|
||||
# NFKC_Simple_Casefold (NFKC_SCF)
|
||||
|
||||
|
||||
# NFKD_Quick_Check (NFKD_QC)
|
||||
|
||||
NFKD_QC; N ; No
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# Unicode Character Database
|
||||
# Date: 2022-09-02
|
||||
# Copyright (c) 2022 Unicode, Inc.
|
||||
# Date: 2023-08-28
|
||||
# Copyright (c) 2023 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 https://www.unicode.org/terms_of_use.html
|
||||
#
|
||||
|
|
@ -10,7 +10,7 @@
|
|||
# UAX #44, "Unicode Character Database"
|
||||
# UTS #51, "Unicode Emoji"
|
||||
#
|
||||
# The UAXes and UTS #51 can be accessed at https://www.unicode.org/versions/Unicode15.0.0/
|
||||
# The UAXes and UTS #51 can be accessed at https://www.unicode.org/versions/Unicode15.1.0/
|
||||
|
||||
This directory contains the final data files
|
||||
for the Unicode Character Database, for Version 15.0.0 of the Unicode Standard.
|
||||
This directory contains final data files
|
||||
for the Unicode Character Database, for Version 15.1.0 of the Unicode Standard.
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# Scripts-15.0.0.txt
|
||||
# Date: 2022-04-26, 23:15:02 GMT
|
||||
# Copyright (c) 2022 Unicode, Inc.
|
||||
# Scripts-15.1.0.txt
|
||||
# Date: 2023-07-28, 16:01:07 GMT
|
||||
# Copyright (c) 2023 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 https://www.unicode.org/terms_of_use.html
|
||||
#
|
||||
|
|
@ -357,7 +357,7 @@
|
|||
2E5B ; Common # Ps BOTTOM HALF LEFT PARENTHESIS
|
||||
2E5C ; Common # Pe BOTTOM HALF RIGHT PARENTHESIS
|
||||
2E5D ; Common # Pd OBLIQUE HYPHEN
|
||||
2FF0..2FFB ; Common # So [12] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
|
||||
2FF0..2FFF ; Common # So [16] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER ROTATION
|
||||
3000 ; Common # Zs IDEOGRAPHIC SPACE
|
||||
3001..3003 ; Common # Po [3] IDEOGRAPHIC COMMA..DITTO MARK
|
||||
3004 ; Common # So JAPANESE INDUSTRIAL STANDARD SYMBOL
|
||||
|
|
@ -399,6 +399,7 @@
|
|||
3192..3195 ; Common # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK
|
||||
3196..319F ; Common # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK
|
||||
31C0..31E3 ; Common # So [36] CJK STROKE T..CJK STROKE Q
|
||||
31EF ; Common # So IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION
|
||||
3220..3229 ; Common # No [10] PARENTHESIZED IDEOGRAPH ONE..PARENTHESIZED IDEOGRAPH TEN
|
||||
322A..3247 ; Common # So [30] PARENTHESIZED IDEOGRAPH MOON..CIRCLED IDEOGRAPH KOTO
|
||||
3248..324F ; Common # No [8] CIRCLED NUMBER TEN ON BLACK SQUARE..CIRCLED NUMBER EIGHTY ON BLACK SQUARE
|
||||
|
|
@ -629,7 +630,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
|
|||
E0001 ; Common # Cf LANGUAGE TAG
|
||||
E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
|
||||
|
||||
# Total code points: 8301
|
||||
# Total code points: 8306
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -1593,11 +1594,12 @@ FA70..FAD9 ; Han # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILI
|
|||
2B740..2B81D ; Han # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
|
||||
2B820..2CEA1 ; Han # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
|
||||
2CEB0..2EBE0 ; Han # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
|
||||
2EBF0..2EE5D ; Han # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
|
||||
2F800..2FA1D ; Han # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
|
||||
30000..3134A ; Han # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
|
||||
31350..323AF ; Han # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
|
||||
|
||||
# Total code points: 98408
|
||||
# Total code points: 99030
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# SpecialCasing-15.0.0.txt
|
||||
# Date: 2022-02-02, 23:35:52 GMT
|
||||
# Copyright (c) 2022 Unicode, Inc.
|
||||
# SpecialCasing-15.1.0.txt
|
||||
# Date: 2023-01-05, 20:35:03 GMT
|
||||
# Copyright (c) 2023 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 https://www.unicode.org/terms_of_use.html
|
||||
#
|
||||
|
|
|
|||
|
|
@ -11231,6 +11231,10 @@
|
|||
2FF9;IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM UPPER RIGHT;So;0;ON;;;;;N;;;;;
|
||||
2FFA;IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM LOWER LEFT;So;0;ON;;;;;N;;;;;
|
||||
2FFB;IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID;So;0;ON;;;;;N;;;;;
|
||||
2FFC;IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM RIGHT;So;0;ON;;;;;N;;;;;
|
||||
2FFD;IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM LOWER RIGHT;So;0;ON;;;;;N;;;;;
|
||||
2FFE;IDEOGRAPHIC DESCRIPTION CHARACTER HORIZONTAL REFLECTION;So;0;ON;;;;;N;;;;;
|
||||
2FFF;IDEOGRAPHIC DESCRIPTION CHARACTER ROTATION;So;0;ON;;;;;N;;;;;
|
||||
3000;IDEOGRAPHIC SPACE;Zs;0;WS;<wide> 0020;;;;N;;;;;
|
||||
3001;IDEOGRAPHIC COMMA;Po;0;ON;;;;;N;;;;;
|
||||
3002;IDEOGRAPHIC FULL STOP;Po;0;ON;;;;;N;IDEOGRAPHIC PERIOD;;;;
|
||||
|
|
@ -11705,6 +11709,7 @@
|
|||
31E1;CJK STROKE HZZZG;So;0;ON;;;;;N;;;;;
|
||||
31E2;CJK STROKE PG;So;0;ON;;;;;N;;;;;
|
||||
31E3;CJK STROKE Q;So;0;ON;;;;;N;;;;;
|
||||
31EF;IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION;So;0;ON;;;;;N;;;;;
|
||||
31F0;KATAKANA LETTER SMALL KU;Lo;0;L;;;;;N;;;;;
|
||||
31F1;KATAKANA LETTER SMALL SI;Lo;0;L;;;;;N;;;;;
|
||||
31F2;KATAKANA LETTER SMALL SU;Lo;0;L;;;;;N;;;;;
|
||||
|
|
@ -34035,6 +34040,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
|
|||
2CEA1;<CJK Ideograph Extension E, Last>;Lo;0;L;;;;;N;;;;;
|
||||
2CEB0;<CJK Ideograph Extension F, First>;Lo;0;L;;;;;N;;;;;
|
||||
2EBE0;<CJK Ideograph Extension F, Last>;Lo;0;L;;;;;N;;;;;
|
||||
2EBF0;<CJK Ideograph Extension I, First>;Lo;0;L;;;;;N;;;;;
|
||||
2EE5D;<CJK Ideograph Extension I, Last>;Lo;0;L;;;;;N;;;;;
|
||||
2F800;CJK COMPATIBILITY IDEOGRAPH-2F800;Lo;0;L;4E3D;;;;N;;;;;
|
||||
2F801;CJK COMPATIBILITY IDEOGRAPH-2F801;Lo;0;L;4E38;;;;N;;;;;
|
||||
2F802;CJK COMPATIBILITY IDEOGRAPH-2F802;Lo;0;L;4E41;;;;N;;;;;
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# GraphemeBreakProperty-15.0.0.txt
|
||||
# Date: 2022-04-27, 17:07:38 GMT
|
||||
# Copyright (c) 2022 Unicode, Inc.
|
||||
# GraphemeBreakProperty-15.1.0.txt
|
||||
# Date: 2023-01-05, 20:34:41 GMT
|
||||
# Copyright (c) 2023 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 https://www.unicode.org/terms_of_use.html
|
||||
#
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load diff
|
|
@ -1,11 +1,11 @@
|
|||
# emoji-data.txt
|
||||
# Date: 2022-08-02, 00:26:10 GMT
|
||||
# Copyright (c) 2022 Unicode, Inc.
|
||||
# Date: 2023-02-01, 02:22:54 GMT
|
||||
# Copyright (c) 2023 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 https://www.unicode.org/terms_of_use.html
|
||||
#
|
||||
# Emoji Data for UTS #51
|
||||
# Used with Emoji Version 15.0 and subsequent minor revisions (if any)
|
||||
# Used with Emoji Version 15.1 and subsequent minor revisions (if any)
|
||||
#
|
||||
# For documentation and usage, see https://www.unicode.org/reports/tr51
|
||||
#
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue