1berry/qtbase
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update UCD to Revision 30

Browse Source 
This corresponds to Unicode version 15.0.0.

Added the following scripts:

    * Kawi
    * Nag Mundari

Full support of these scripts requires harfbuzz version 5.2.0,
this version adds support for Unicode 15.0:

    https://github.com/harfbuzz/harfbuzz/releases/tag/5.2.0

Fixes: QTBUG-106810
Change-Id: Ib06c526e49b0f01ef9f21123bcf875c6b19f2601
Reviewed-by: Edward Welbourne <edward.welbourne@qt.io>
This commit is contained in:
Ievgenii Meshcheriakov 2022-10-04 13:57:44 +02:00
parent 20144aab0b
commit c4e550703c
30 changed files with 11638 additions and 10589 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/corelib/text/qchar.cpp
View File

@ -164,6 +164,7 @@ QT_BEGIN_NAMESPACE
\value [since 5.15] Unicode_12_1 Version 12.1
\value [since 5.15] Unicode_13_0 Version 13.0
\value [since 6.3] Unicode_14_0 Version 14.0
\value [since 6.5] Unicode_15_0 Version 15.0
\value Unicode_Unassigned The value is not assigned to any character
in version 8.0 of Unicode.
@ -323,6 +324,7 @@ QT_BEGIN_NAMESPACE
\value Script_Kaithi
\value Script_Kannada
\value Script_Katakana
\value [since 6.5] Script_Kawi
\value Script_KayahLi
\value Script_Kharoshthi
\value [since 5.15] Script_KhitanSmallScript
@ -357,6 +359,7 @@ QT_BEGIN_NAMESPACE
\value [since 5.6] Script_Multani
\value Script_Myanmar
\value [since 5.5] Script_Nabataean
\value [since 6.3] Script_NagMundari
\value [since 5.15] Script_Nandinagari
\value [since 5.11] Script_Newa
\value Script_NewTaiLue

7
src/corelib/text/qchar.h
View File

@ -334,6 +334,10 @@ public:
Script_Toto,
Script_Vithkuqi,
// Unicode 15.0 additions
Script_Kawi,
Script_NagMundari,
ScriptCount
};
@ -425,7 +429,8 @@ public:
Unicode_12_0,
Unicode_12_1,
Unicode_13_0,
Unicode_14_0
Unicode_14_0,
Unicode_15_0,
};
inline Category category() const noexcept { return QChar::category(ucs); }

4
src/corelib/text/qt_attribution.json
View File

@ -12,11 +12,11 @@
"Homepage": "https://www.unicode.org/ucd/",
"Version": "Don't use the Unicode standard version;
UCD has its own 'Revision' numbers, see the 'UAX #44, UCD' page (https://www.unicode.org/reports/tr44/)",
"Version": "28",
"Version": "30",
"License": "Unicode License Agreement - Data Files and Software (2016)",
"LicenseId": "Unicode-DFS-2016",
"LicenseFile": "UNICODE_LICENSE.txt",
"Copyright": "Copyright (C) 1991-2021 Unicode, Inc."
"Copyright": "Copyright (C) 1991-2022 Unicode, Inc."
},
{
"Id": "unicode-cldr",

10954
src/corelib/text/qunicodetables.cpp
View File

File diff suppressed because it is too large Load Diff

8
src/gui/text/qharfbuzzng.cpp
View File

@ -221,6 +221,14 @@ static const hb_script_t _qtscript_to_hbscript[] = {
HB_SCRIPT_TANGSA,
HB_SCRIPT_TOTO,
HB_SCRIPT_VITHKUQI,
#endif
// Unicode 15.0 additions (not present in harfbuzz-ng 5.1.0 and earlier)
#if !HB_VERSION_ATLEAST(5, 2, 0)
hb_script_t(HB_TAG('K','a','w','i')), // Script_Kawi
hb_script_t(HB_TAG('N','a','g','m')), // Script_NagMundari
#else
HB_SCRIPT_KAWI,
HB_SCRIPT_NAG_MUNDARI,
#endif
};
static_assert(QChar::ScriptCount == sizeof(_qtscript_to_hbscript) / sizeof(_qtscript_to_hbscript[0]));

2
src/gui/text/unix/qfontconfigdatabase.cpp
View File

@ -246,6 +246,8 @@ static const char specialLanguages[][6] = {
"", // Tangsa
"", // Toto
"", // Vithkuqi
"", // Kawi
"", // NagMundari
};
static_assert(sizeof specialLanguages / sizeof *specialLanguages == QChar::ScriptCount);

9998
tests/auto/corelib/io/qurluts46/testdata/IdnaTestV2.txt vendored
View File

File diff suppressed because it is too large Load Diff

10
tests/auto/corelib/text/qtextboundaryfinder/data/GraphemeBreakTest.txt
View File

@ -1,11 +1,11 @@
# GraphemeBreakTest-14.0.0.txt
# Date: 2021-03-08, 06:22:32 GMT
# © 2021 Unicode®, Inc.
# GraphemeBreakTest-15.0.0.txt
# Date: 2022-02-26, 00:38:37 GMT
# © 2022 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
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see https://www.unicode.org/reports/tr44/
#
# Default Grapheme_Cluster_Break Test
#

10
tests/auto/corelib/text/qtextboundaryfinder/data/LineBreakTest.txt
View File

@ -1,11 +1,11 @@
# LineBreakTest-14.0.0.txt
# Date: 2021-08-20, 21:08:45 GMT
# © 2021 Unicode®, Inc.
# LineBreakTest-15.0.0.txt
# Date: 2022-02-26, 00:38:39 GMT
# © 2022 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
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see https://www.unicode.org/reports/tr44/
#
# Default Line_Break Test
#

10
tests/auto/corelib/text/qtextboundaryfinder/data/SentenceBreakTest.txt
View File

@ -1,11 +1,11 @@
# SentenceBreakTest-14.0.0.txt
# Date: 2021-03-08, 06:22:40 GMT
# © 2021 Unicode®, Inc.
# SentenceBreakTest-15.0.0.txt
# Date: 2022-02-26, 00:39:00 GMT
# © 2022 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
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see https://www.unicode.org/reports/tr44/
#
# Default Sentence_Break Test
#

8
tests/auto/corelib/text/qtextboundaryfinder/data/WordBreakTest.html
View File

@ -6,8 +6,8 @@ td, th { vertical-align: top }
</style></head>
<body bgcolor='#FFFFFF'>
<h2>Word_Break Chart</h2>
<p><b>Unicode Version:</b> 14.0.0</p>
<p><b>Date:</b> 2021-07-10, 00:35:32 GMT</p>
<p><b>Unicode Version:</b> 15.0.0</p>
<p><b>Date:</b> 2021-11-24, 21:43:58 GMT</p>
<p>This page illustrates the application of the Word_Break specification. The material here is informative, not normative.</p> <p>The first chart shows where breaks would appear between different sample characters or strings. The sample characters are chosen mechanically to represent the different properties used by the specification.</p><p>Each cell shows the break-status for the position between the character(s) in its row header and the character(s) in its column header. The × symbol indicates no break, while the ÷ symbol indicated a break. The cells with × are also shaded to make it easier to scan the table. For example, in the cell at the intersection of the row headed by “CR” and the column headed by “LF”, there is a × symbol, indicating that there is no break between CR and LF.</p>
<p>After the heavy blue line in the table are additional rows, either with different sample characters or for sequences, such as “ALetter MidLetter”. Some column headers may be composed, reflecting “treat as” or “ignore” rules.</p>
<p>If your browser handles titles (tooltips), then hovering the mouse over the row header will show a sample character of that type. Hovering over a column header will show the sample character, plus its abbreviated general category and script. Hovering over the intersected cells shows the rule number that produces the break-status. For example, hovering over the cell at the intersection of ExtendNumLet and ALetter shows ×, with the rule 13.2. Checking below the table, rule 13.2 is “ExtendNumLet × (AHLetter | Numeric | Katakana)”, which is the one that applies to that case. Note that a rule is invoked only when no lower-numbered rules have applied.</p>
@ -182,11 +182,9 @@ td, th { vertical-align: top }
<table cellspacing='0' cellpadding='0' border='0'>
<tr>
<td><a href='https://www.unicode.org/copyright.html'>
<img src='http://www.unicode.org/img/hb_notice.gif' border='0' alt='Access to Copyright and terms of use' width='216' height='50'></a></td>
<img src='https://www.unicode.org/img/hb_notice.gif' border='0' alt='Access to Copyright and terms of use' width='216' height='50'></a></td>
</tr>
</table>
<script language='Javascript' type='text/javascript' src='http://www.unicode.org/webscripts/lastModified.js'>
</script>
</center>
</div>
<br>

10
tests/auto/corelib/text/qtextboundaryfinder/data/WordBreakTest.txt
View File

@ -1,11 +1,11 @@
# WordBreakTest-14.0.0.txt
# Date: 2021-03-08, 06:22:40 GMT
# © 2021 Unicode®, Inc.
# WordBreakTest-15.0.0.txt
# Date: 2022-02-26, 00:39:00 GMT
# © 2022 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
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see https://www.unicode.org/reports/tr44/
#
# Default Word_Break Test
#

8
util/unicode/data/ArabicShaping.txt
View File

@ -1,8 +1,8 @@
# ArabicShaping-14.0.0.txt
# Date: 2021-05-21, 01:54:00 GMT [KW, RP]
# © 2021 Unicode®, Inc.
# ArabicShaping-15.0.0.txt
# Date: 2022-02-14, 18:50:00 GMT [KW, RP]
# © 2022 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
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# This file is a normative contributory data file in the
# Unicode Character Database.

8
util/unicode/data/BidiMirroring.txt
View File

@ -1,6 +1,6 @@
# BidiMirroring-14.0.0.txt
# Date: 2021-08-08, 22:55:00 GMT [KW, RP]
# © 2021 Unicode®, Inc.
# BidiMirroring-15.0.0.txt
# Date: 2022-05-03, 18:47:00 GMT [KW, RP]
# © 2022 Unicode®, Inc.
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
@ -15,7 +15,7 @@
# value, for which there is another Unicode character that typically has a glyph
# that is the mirror image of the original character's glyph.
#
# The repertoire covered by the file is Unicode 14.0.0.
# The repertoire covered by the file is Unicode 15.0.0.
#
# The file contains a list of lines with mappings from one code point
# to another one for character-based mirroring.

21
util/unicode/data/Blocks.txt
View File

@ -1,10 +1,10 @@
# Blocks-14.0.0.txt
# Date: 2021-01-22, 23:29:00 GMT [KW]
# © 2021 Unicode®, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# Blocks-15.0.0.txt
# Date: 2022-01-28, 20:58:00 GMT [KW]
# © 2022 Unicode®, Inc.
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see https://www.unicode.org/reports/tr44/
#
# Format:
# Start Code..End Code; Block Name
@ -15,7 +15,7 @@
# and underbars are ignored.
# For example, "Latin Extended-A" and "latin extended a" are equivalent.
# For more information on the comparison of property values,
# see UAX #44: http://www.unicode.org/reports/tr44/
# see UAX #44: https://www.unicode.org/reports/tr44/
#
# All block ranges start with a value where (cp MOD 16) = 0,
# and end with a value where (cp MOD 16) = 15. In other words,
@ -241,6 +241,7 @@ FFF0..FFFF; Specials
10D00..10D3F; Hanifi Rohingya
10E60..10E7F; Rumi Numeral Symbols
10E80..10EBF; Yezidi
10EC0..10EFF; Arabic Extended-C
10F00..10F2F; Old Sogdian
10F30..10F6F; Sogdian
10F70..10FAF; Old Uyghur
@ -272,11 +273,13 @@ FFF0..FFFF; Specials
11A50..11AAF; Soyombo
11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A
11AC0..11AFF; Pau Cin Hau
11B00..11B5F; Devanagari Extended-A
11C00..11C6F; Bhaiksuki
11C70..11CBF; Marchen
11D00..11D5F; Masaram Gondi
11D60..11DAF; Gunjala Gondi
11EE0..11EFF; Makasar
11F00..11F5F; Kawi
11FB0..11FBF; Lisu Supplement
11FC0..11FFF; Tamil Supplement
12000..123FF; Cuneiform
@ -284,7 +287,7 @@ FFF0..FFFF; Specials
12480..1254F; Early Dynastic Cuneiform
12F90..12FFF; Cypro-Minoan
13000..1342F; Egyptian Hieroglyphs
13430..1343F; Egyptian Hieroglyph Format Controls
13430..1345F; Egyptian Hieroglyph Format Controls
14400..1467F; Anatolian Hieroglyphs
16800..16A3F; Bamum Supplement
16A40..16A6F; Mro
@ -309,6 +312,7 @@ FFF0..FFFF; Specials
1D000..1D0FF; Byzantine Musical Symbols
1D100..1D1FF; Musical Symbols
1D200..1D24F; Ancient Greek Musical Notation
1D2C0..1D2DF; Kaktovik Numerals
1D2E0..1D2FF; Mayan Numerals
1D300..1D35F; Tai Xuan Jing Symbols
1D360..1D37F; Counting Rod Numerals
@ -316,9 +320,11 @@ FFF0..FFFF; Specials
1D800..1DAAF; Sutton SignWriting
1DF00..1DFFF; Latin Extended-G
1E000..1E02F; Glagolitic Supplement
1E030..1E08F; Cyrillic Extended-D
1E100..1E14F; Nyiakeng Puachue Hmong
1E290..1E2BF; Toto
1E2C0..1E2FF; Wancho
1E4D0..1E4FF; Nag Mundari
1E7E0..1E7FF; Ethiopic Extended-B
1E800..1E8DF; Mende Kikakui
1E900..1E95F; Adlam
@ -348,6 +354,7 @@ FFF0..FFFF; Specials
2CEB0..2EBEF; CJK Unified Ideographs Extension F
2F800..2FA1F; CJK Compatibility Ideographs Supplement
30000..3134F; CJK Unified Ideographs Extension G
31350..323AF; CJK Unified Ideographs Extension H
E0000..E007F; Tags
E0100..E01EF; Variation Selectors Supplement
F0000..FFFFF; Supplementary Private Use Area-A

10
util/unicode/data/CaseFolding.txt
View File

@ -1,11 +1,11 @@
# CaseFolding-14.0.0.txt
# Date: 2021-03-08, 19:35:41 GMT
# © 2021 Unicode®, Inc.
# CaseFolding-15.0.0.txt
# Date: 2022-02-02, 23:35:35 GMT
# © 2022 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
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see https://www.unicode.org/reports/tr44/
#
# Case Folding Properties
#

52
util/unicode/data/DerivedAge.txt
View File

@ -1,11 +1,11 @@
# DerivedAge-14.0.0.txt
# Date: 2021-07-10, 00:35:00 GMT
# © 2021 Unicode®, Inc.
# DerivedAge-15.0.0.txt
# Date: 2022-04-26, 23:14:23 GMT
# © 2022 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
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see https://www.unicode.org/reports/tr44/
#
# Unicode Character Database: Derived Property Data
# This file shows when various code points were first assigned in Unicode.
@ -1949,4 +1949,46 @@ FDFE..FDFF ; 14.0 # [2] ARABIC LIGATURE SUBHAANAHU WA TAAALAA..ARABIC LIGAT
# Total code points: 838
# ================================================
# Age=V15_0
# Newly assigned in Unicode 15.0.0 (September, 2022)
0CF3 ; 15.0 # KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
0ECE ; 15.0 # LAO YAMAKKAN
10EFD..10EFF ; 15.0 # [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA
1123F..11241 ; 15.0 # [3] KHOJKI LETTER QA..KHOJKI VOWEL SIGN VOCALIC R
11B00..11B09 ; 15.0 # [10] DEVANAGARI HEAD MARK..DEVANAGARI SIGN MINDU
11F00..11F10 ; 15.0 # [17] KAWI SIGN CANDRABINDU..KAWI LETTER O
11F12..11F3A ; 15.0 # [41] KAWI LETTER KA..KAWI VOWEL SIGN VOCALIC R
11F3E..11F59 ; 15.0 # [28] KAWI VOWEL SIGN E..KAWI DIGIT NINE
1342F ; 15.0 # EGYPTIAN HIEROGLYPH V011D
13439..1343F ; 15.0 # [7] EGYPTIAN HIEROGLYPH INSERT AT MIDDLE..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE
13440..13455 ; 15.0 # [22] EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED
1B132 ; 15.0 # HIRAGANA LETTER SMALL KO
1B155 ; 15.0 # KATAKANA LETTER SMALL KO
1D2C0..1D2D3 ; 15.0 # [20] KAKTOVIK NUMERAL ZERO..KAKTOVIK NUMERAL NINETEEN
1DF25..1DF2A ; 15.0 # [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
1E030..1E06D ; 15.0 # [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
1E08F ; 15.0 # COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
1E4D0..1E4F9 ; 15.0 # [42] NAG MUNDARI LETTER O..NAG MUNDARI DIGIT NINE
1F6DC ; 15.0 # WIRELESS
1F774..1F776 ; 15.0 # [3] LOT OF FORTUNE..LUNAR ECLIPSE
1F77B..1F77F ; 15.0 # [5] HAUMEA..ORCUS
1F7D9 ; 15.0 # NINE POINTED WHITE STAR
1FA75..1FA77 ; 15.0 # [3] LIGHT BLUE HEART..PINK HEART
1FA87..1FA88 ; 15.0 # [2] MARACAS..FLUTE
1FAAD..1FAAF ; 15.0 # [3] FOLDING HAND FAN..KHANDA
1FABB..1FABD ; 15.0 # [3] HYACINTH..WING
1FABF ; 15.0 # GOOSE
1FACE..1FACF ; 15.0 # [2] MOOSE..DONKEY
1FADA..1FADB ; 15.0 # [2] GINGER ROOT..PEA POD
1FAE8 ; 15.0 # SHAKING FACE
1FAF7..1FAF8 ; 15.0 # [2] LEFTWARDS PUSHING HAND..RIGHTWARDS PUSHING HAND
2B739 ; 15.0 # CJK UNIFIED IDEOGRAPH-2B739
31350..323AF ; 15.0 # [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
# Total code points: 4489
# EOF

83
util/unicode/data/DerivedNormalizationProps.txt
View File

@ -1,11 +1,11 @@
# DerivedNormalizationProps-14.0.0.txt
# Date: 2021-06-04, 02:19:20 GMT
# © 2021 Unicode®, Inc.
# DerivedNormalizationProps-15.0.0.txt
# Date: 2022-04-02, 01:29:03 GMT
# © 2022 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
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see https://www.unicode.org/reports/tr44/
# ================================================
@ -1652,6 +1652,7 @@ FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI
1D7C3 ; NFKD_QC; N # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL
1D7C4..1D7CB ; NFKD_QC; N # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA
1D7CE..1D7FF ; NFKD_QC; N # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
1E030..1E06D ; NFKD_QC; N # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
1EE00..1EE03 ; NFKD_QC; N # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL
1EE05..1EE1F ; NFKD_QC; N # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF
1EE21..1EE22 ; NFKD_QC; N # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM
@ -1697,7 +1698,7 @@ FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI
1FBF0..1FBF9 ; NFKD_QC; N # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE
2F800..2FA1D ; NFKD_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 16967
# Total code points: 17029
# ================================================
@ -2060,6 +2061,7 @@ FFED..FFEE ; NFKC_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI
1D7C3 ; NFKC_QC; N # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL
1D7C4..1D7CB ; NFKC_QC; N # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA
1D7CE..1D7FF ; NFKC_QC; N # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
1E030..1E06D ; NFKC_QC; N # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
1EE00..1EE03 ; NFKC_QC; N # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL
1EE05..1EE1F ; NFKC_QC; N # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF
1EE21..1EE22 ; NFKC_QC; N # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM
@ -2105,7 +2107,7 @@ FFED..FFEE ; NFKC_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI
1FBF0..1FBF9 ; NFKC_QC; N # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE
2F800..2FA1D ; NFKC_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 4866
# Total code points: 4928
# ================================================
@ -8076,6 +8078,68 @@ FFF0..FFF8 ; NFKC_CF; # Cn [9] <reserved-FFF0>..<reserved-FF
1D7FD ; NFKC_CF; 0037 # Nd MATHEMATICAL MONOSPACE DIGIT SEVEN
1D7FE ; NFKC_CF; 0038 # Nd MATHEMATICAL MONOSPACE DIGIT EIGHT
1D7FF ; NFKC_CF; 0039 # Nd MATHEMATICAL MONOSPACE DIGIT NINE
1E030 ; NFKC_CF; 0430 # Lm MODIFIER LETTER CYRILLIC SMALL A
1E031 ; NFKC_CF; 0431 # Lm MODIFIER LETTER CYRILLIC SMALL BE
1E032 ; NFKC_CF; 0432 # Lm MODIFIER LETTER CYRILLIC SMALL VE
1E033 ; NFKC_CF; 0433 # Lm MODIFIER LETTER CYRILLIC SMALL GHE
1E034 ; NFKC_CF; 0434 # Lm MODIFIER LETTER CYRILLIC SMALL DE
1E035 ; NFKC_CF; 0435 # Lm MODIFIER LETTER CYRILLIC SMALL IE
1E036 ; NFKC_CF; 0436 # Lm MODIFIER LETTER CYRILLIC SMALL ZHE
1E037 ; NFKC_CF; 0437 # Lm MODIFIER LETTER CYRILLIC SMALL ZE
1E038 ; NFKC_CF; 0438 # Lm MODIFIER LETTER CYRILLIC SMALL I
1E039 ; NFKC_CF; 043A # Lm MODIFIER LETTER CYRILLIC SMALL KA
1E03A ; NFKC_CF; 043B # Lm MODIFIER LETTER CYRILLIC SMALL EL
1E03B ; NFKC_CF; 043C # Lm MODIFIER LETTER CYRILLIC SMALL EM
1E03C ; NFKC_CF; 043E # Lm MODIFIER LETTER CYRILLIC SMALL O
1E03D ; NFKC_CF; 043F # Lm MODIFIER LETTER CYRILLIC SMALL PE
1E03E ; NFKC_CF; 0440 # Lm MODIFIER LETTER CYRILLIC SMALL ER
1E03F ; NFKC_CF; 0441 # Lm MODIFIER LETTER CYRILLIC SMALL ES
1E040 ; NFKC_CF; 0442 # Lm MODIFIER LETTER CYRILLIC SMALL TE
1E041 ; NFKC_CF; 0443 # Lm MODIFIER LETTER CYRILLIC SMALL U
1E042 ; NFKC_CF; 0444 # Lm MODIFIER LETTER CYRILLIC SMALL EF
1E043 ; NFKC_CF; 0445 # Lm MODIFIER LETTER CYRILLIC SMALL HA
1E044 ; NFKC_CF; 0446 # Lm MODIFIER LETTER CYRILLIC SMALL TSE
1E045 ; NFKC_CF; 0447 # Lm MODIFIER LETTER CYRILLIC SMALL CHE
1E046 ; NFKC_CF; 0448 # Lm MODIFIER LETTER CYRILLIC SMALL SHA
1E047 ; NFKC_CF; 044B # Lm MODIFIER LETTER CYRILLIC SMALL YERU
1E048 ; NFKC_CF; 044D # Lm MODIFIER LETTER CYRILLIC SMALL E
1E049 ; NFKC_CF; 044E # Lm MODIFIER LETTER CYRILLIC SMALL YU
1E04A ; NFKC_CF; A689 # Lm MODIFIER LETTER CYRILLIC SMALL DZZE
1E04B ; NFKC_CF; 04D9 # Lm MODIFIER LETTER CYRILLIC SMALL SCHWA
1E04C ; NFKC_CF; 0456 # Lm MODIFIER LETTER CYRILLIC SMALL BYELORUSSIAN-UKRAINIAN I
1E04D ; NFKC_CF; 0458 # Lm MODIFIER LETTER CYRILLIC SMALL JE
1E04E ; NFKC_CF; 04E9 # Lm MODIFIER LETTER CYRILLIC SMALL BARRED O
1E04F ; NFKC_CF; 04AF # Lm MODIFIER LETTER CYRILLIC SMALL STRAIGHT U
1E050 ; NFKC_CF; 04CF # Lm MODIFIER LETTER CYRILLIC SMALL PALOCHKA
1E051 ; NFKC_CF; 0430 # Lm CYRILLIC SUBSCRIPT SMALL LETTER A
1E052 ; NFKC_CF; 0431 # Lm CYRILLIC SUBSCRIPT SMALL LETTER BE
1E053 ; NFKC_CF; 0432 # Lm CYRILLIC SUBSCRIPT SMALL LETTER VE
1E054 ; NFKC_CF; 0433 # Lm CYRILLIC SUBSCRIPT SMALL LETTER GHE
1E055 ; NFKC_CF; 0434 # Lm CYRILLIC SUBSCRIPT SMALL LETTER DE
1E056 ; NFKC_CF; 0435 # Lm CYRILLIC SUBSCRIPT SMALL LETTER IE
1E057 ; NFKC_CF; 0436 # Lm CYRILLIC SUBSCRIPT SMALL LETTER ZHE
1E058 ; NFKC_CF; 0437 # Lm CYRILLIC SUBSCRIPT SMALL LETTER ZE
1E059 ; NFKC_CF; 0438 # Lm CYRILLIC SUBSCRIPT SMALL LETTER I
1E05A ; NFKC_CF; 043A # Lm CYRILLIC SUBSCRIPT SMALL LETTER KA
1E05B ; NFKC_CF; 043B # Lm CYRILLIC SUBSCRIPT SMALL LETTER EL
1E05C ; NFKC_CF; 043E # Lm CYRILLIC SUBSCRIPT SMALL LETTER O
1E05D ; NFKC_CF; 043F # Lm CYRILLIC SUBSCRIPT SMALL LETTER PE
1E05E ; NFKC_CF; 0441 # Lm CYRILLIC SUBSCRIPT SMALL LETTER ES
1E05F ; NFKC_CF; 0443 # Lm CYRILLIC SUBSCRIPT SMALL LETTER U
1E060 ; NFKC_CF; 0444 # Lm CYRILLIC SUBSCRIPT SMALL LETTER EF
1E061 ; NFKC_CF; 0445 # Lm CYRILLIC SUBSCRIPT SMALL LETTER HA
1E062 ; NFKC_CF; 0446 # Lm CYRILLIC SUBSCRIPT SMALL LETTER TSE
1E063 ; NFKC_CF; 0447 # Lm CYRILLIC SUBSCRIPT SMALL LETTER CHE
1E064 ; NFKC_CF; 0448 # Lm CYRILLIC SUBSCRIPT SMALL LETTER SHA
1E065 ; NFKC_CF; 044A # Lm CYRILLIC SUBSCRIPT SMALL LETTER HARD SIGN
1E066 ; NFKC_CF; 044B # Lm CYRILLIC SUBSCRIPT SMALL LETTER YERU
1E067 ; NFKC_CF; 0491 # Lm CYRILLIC SUBSCRIPT SMALL LETTER GHE WITH UPTURN
1E068 ; NFKC_CF; 0456 # Lm CYRILLIC SUBSCRIPT SMALL LETTER BYELORUSSIAN-UKRAINIAN I
1E069 ; NFKC_CF; 0455 # Lm CYRILLIC SUBSCRIPT SMALL LETTER DZE
1E06A ; NFKC_CF; 045F # Lm CYRILLIC SUBSCRIPT SMALL LETTER DZHE
1E06B ; NFKC_CF; 04AB # Lm MODIFIER LETTER CYRILLIC SMALL ES WITH DESCENDER
1E06C ; NFKC_CF; A651 # Lm MODIFIER LETTER CYRILLIC SMALL YERU WITH BACK YER
1E06D ; NFKC_CF; 04B1 # Lm MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
1E900 ; NFKC_CF; 1E922 # L& ADLAM CAPITAL LETTER ALIF
1E901 ; NFKC_CF; 1E923 # L& ADLAM CAPITAL LETTER DAALI
1E902 ; NFKC_CF; 1E924 # L& ADLAM CAPITAL LETTER LAAM
@ -8937,7 +9001,7 @@ E0080..E00FF ; NFKC_CF; # Cn [128] <reserved-E0080>..<reserved-E
E0100..E01EF ; NFKC_CF; # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
E01F0..E0FFF ; NFKC_CF; # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
# Total code points: 10429
# Total code points: 10491
# ================================================
@ -9895,6 +9959,7 @@ FFF0..FFF8 ; Changes_When_NFKC_Casefolded # Cn [9] <reserved-FFF0>..<reserv
1D7C3 ; Changes_When_NFKC_Casefolded # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL
1D7C4..1D7CB ; Changes_When_NFKC_Casefolded # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA
1D7CE..1D7FF ; Changes_When_NFKC_Casefolded # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
1E030..1E06D ; Changes_When_NFKC_Casefolded # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
1E900..1E921 ; Changes_When_NFKC_Casefolded # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA
1EE00..1EE03 ; Changes_When_NFKC_Casefolded # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL
1EE05..1EE1F ; Changes_When_NFKC_Casefolded # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF
@ -9948,6 +10013,6 @@ E0080..E00FF ; Changes_When_NFKC_Casefolded # Cn [128] <reserved-E0080>..<reser
E0100..E01EF ; Changes_When_NFKC_Casefolded # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
E01F0..E0FFF ; Changes_When_NFKC_Casefolded # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
# Total code points: 10429
# Total code points: 10491
# EOF

74
util/unicode/data/EastAsianWidth.txt
View File

@ -1,6 +1,6 @@
# EastAsianWidth-14.0.0.txt
# Date: 2021-07-06, 09:58:53 GMT [KW, LI]
# © 2021 Unicode®, Inc.
# EastAsianWidth-15.0.0.txt
# Date: 2022-05-24, 17:40:20 GMT [KW, LI]
# © 2022 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
#
@ -534,6 +534,7 @@
0CE2..0CE3;N # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
0CE6..0CEF;N # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE
0CF1..0CF2;N # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
0CF3;N # Mc KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
0D00..0D01;N # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
0D02..0D03;N # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
0D04..0D0C;N # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L
@ -595,7 +596,7 @@
0EBD;N # Lo LAO SEMIVOWEL SIGN NYO
0EC0..0EC4;N # Lo [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI
0EC6;N # Lm LAO KO LA
0EC8..0ECD;N # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA
0EC8..0ECE;N # Mn [7] LAO TONE MAI EK..LAO YAMAKKAN
0ED0..0ED9;N # Nd [10] LAO DIGIT ZERO..LAO DIGIT NINE
0EDC..0EDF;N # Lo [4] LAO HO NO..LAO LETTER KHMU NYO
0F00;N # Lo TIBETAN SYLLABLE OM
@ -1946,6 +1947,7 @@ FFFD;A # So REPLACEMENT CHARACTER
10EAB..10EAC;N # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK
10EAD;N # Pd YEZIDI HYPHENATION MARK
10EB0..10EB1;N # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE
10EFD..10EFF;N # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA
10F00..10F1C;N # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL
10F1D..10F26;N # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF
10F27;N # Lo OLD SOGDIAN LIGATURE AYIN-DALETH
@ -2028,6 +2030,8 @@ FFFD;A # So REPLACEMENT CHARACTER
11236..11237;N # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
11238..1123D;N # Po [6] KHOJKI DANDA..KHOJKI ABBREVIATION SIGN
1123E;N # Mn KHOJKI SIGN SUKUN
1123F..11240;N # Lo [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I
11241;N # Mn KHOJKI VOWEL SIGN VOCALIC R
11280..11286;N # Lo [7] MULTANI LETTER A..MULTANI LETTER GA
11288;N # Lo MULTANI LETTER GHA
1128A..1128D;N # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA
@ -2190,6 +2194,7 @@ FFFD;A # So REPLACEMENT CHARACTER
11A9E..11AA2;N # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2
11AB0..11ABF;N # Lo [16] CANADIAN SYLLABICS NATTILIK HI..CANADIAN SYLLABICS SPA
11AC0..11AF8;N # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
11B00..11B09;N # Po [10] DEVANAGARI HEAD MARK..DEVANAGARI SIGN MINDU
11C00..11C08;N # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L
11C0A..11C2E;N # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA
11C2F;N # Mc BHAIKSUKI VOWEL SIGN AA
@ -2235,6 +2240,19 @@ FFFD;A # So REPLACEMENT CHARACTER
11EF3..11EF4;N # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
11EF5..11EF6;N # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
11EF7..11EF8;N # Po [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION
11F00..11F01;N # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA
11F02;N # Lo KAWI SIGN REPHA
11F03;N # Mc KAWI SIGN VISARGA
11F04..11F10;N # Lo [13] KAWI LETTER A..KAWI LETTER O
11F12..11F33;N # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA
11F34..11F35;N # Mc [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA
11F36..11F3A;N # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R
11F3E..11F3F;N # Mc [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI
11F40;N # Mn KAWI VOWEL SIGN EU
11F41;N # Mc KAWI SIGN KILLER
11F42;N # Mn KAWI CONJOINER
11F43..11F4F;N # Po [13] KAWI DANDA..KAWI PUNCTUATION CLOSING SPIRAL
11F50..11F59;N # Nd [10] KAWI DIGIT ZERO..KAWI DIGIT NINE
11FB0;N # Lo LISU LETTER YHA
11FC0..11FD4;N # No [21] TAMIL FRACTION ONE THREE-HUNDRED-AND-TWENTIETH..TAMIL FRACTION DOWNSCALING FACTOR KIIZH
11FD5..11FDC;N # So [8] TAMIL SIGN NEL..TAMIL SIGN MUKKURUNI
@ -2247,8 +2265,11 @@ FFFD;A # So REPLACEMENT CHARACTER
12480..12543;N # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
12F90..12FF0;N # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114
12FF1..12FF2;N # Po [2] CYPRO-MINOAN SIGN CM301..CYPRO-MINOAN SIGN CM302
13000..1342E;N # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
13430..13438;N # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT
13000..1342F;N # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D
13430..1343F;N # Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE
13440;N # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY
13441..13446;N # Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN
13447..13455;N # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED
14400..14646;N # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530
16800..16A38;N # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ
16A40..16A5E;N # Lo [31] MRO LETTER TA..MRO LETTER TEK
@ -2293,7 +2314,9 @@ FFFD;A # So REPLACEMENT CHARACTER
1AFFD..1AFFE;W # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
1B000..1B0FF;W # Lo [256] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER RE-2
1B100..1B122;W # Lo [35] HENTAIGANA LETTER RE-3..KATAKANA LETTER ARCHAIC WU
1B132;W # Lo HIRAGANA LETTER SMALL KO
1B150..1B152;W # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO
1B155;W # Lo KATAKANA LETTER SMALL KO
1B164..1B167;W # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N
1B170..1B2FB;W # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
1BC00..1BC6A;N # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
@ -2324,6 +2347,7 @@ FFFD;A # So REPLACEMENT CHARACTER
1D200..1D241;N # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54
1D242..1D244;N # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
1D245;N # So GREEK MUSICAL LEIMMA
1D2C0..1D2D3;N # No [20] KAKTOVIK NUMERAL ZERO..KAKTOVIK NUMERAL NINETEEN
1D2E0..1D2F3;N # No [20] MAYAN NUMERAL ZERO..MAYAN NUMERAL NINETEEN
1D300..1D356;N # So [87] MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING
1D360..1D378;N # No [25] COUNTING ROD UNIT DIGIT ONE..TALLY MARK FIVE
@ -2383,11 +2407,14 @@ FFFD;A # So REPLACEMENT CHARACTER
1DF00..1DF09;N # Ll [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK
1DF0A;N # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK
1DF0B..1DF1E;N # Ll [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL
1DF25..1DF2A;N # Ll [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
1E000..1E006;N # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
1E008..1E018;N # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
1E01B..1E021;N # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
1E023..1E024;N # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
1E026..1E02A;N # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
1E030..1E06D;N # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
1E08F;N # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
1E100..1E12C;N # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W
1E130..1E136;N # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
1E137..1E13D;N # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER
@ -2400,6 +2427,10 @@ FFFD;A # So REPLACEMENT CHARACTER
1E2EC..1E2EF;N # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI
1E2F0..1E2F9;N # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE
1E2FF;N # Sc WANCHO NGUN SIGN
1E4D0..1E4EA;N # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL
1E4EB;N # Lm NAG MUNDARI SIGN OJOD
1E4EC..1E4EF;N # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH
1E4F0..1E4F9;N # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE
1E7E0..1E7E6;N # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO
1E7E8..1E7EB;N # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE
1E7ED..1E7EE;N # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE
@ -2528,13 +2559,14 @@ FFFD;A # So REPLACEMENT CHARACTER
1F6D0..1F6D2;W # So [3] PLACE OF WORSHIP..SHOPPING TROLLEY
1F6D3..1F6D4;N # So [2] STUPA..PAGODA
1F6D5..1F6D7;W # So [3] HINDU TEMPLE..ELEVATOR
1F6DD..1F6DF;W # So [3] PLAYGROUND SLIDE..RING BUOY
1F6DC..1F6DF;W # So [4] WIRELESS..RING BUOY
1F6E0..1F6EA;N # So [11] HAMMER AND WRENCH..NORTHEAST-POINTING AIRPLANE
1F6EB..1F6EC;W # So [2] AIRPLANE DEPARTURE..AIRPLANE ARRIVING
1F6F0..1F6F3;N # So [4] SATELLITE..PASSENGER SHIP
1F6F4..1F6FC;W # So [9] SCOOTER..ROLLER SKATE
1F700..1F773;N # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
1F780..1F7D8;N # So [89] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NEGATIVE CIRCLED SQUARE
1F700..1F776;N # So [119] ALCHEMICAL SYMBOL FOR QUINTESSENCE..LUNAR ECLIPSE
1F77B..1F77F;N # So [5] HAUMEA..ORCUS
1F780..1F7D9;N # So [90] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NINE POINTED WHITE STAR
1F7E0..1F7EB;W # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE
1F7F0;W # So HEAVY EQUALS SIGN
1F800..1F80B;N # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD
@ -2551,22 +2583,20 @@ FFFD;A # So REPLACEMENT CHARACTER
1F947..1F9FF;W # So [185] FIRST PLACE MEDAL..NAZAR AMULET
1FA00..1FA53;N # So [84] NEUTRAL CHESS KING..BLACK CHESS KNIGHT-BISHOP
1FA60..1FA6D;N # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER
1FA70..1FA74;W # So [5] BALLET SHOES..THONG SANDAL
1FA78..1FA7C;W # So [5] DROP OF BLOOD..CRUTCH
1FA80..1FA86;W # So [7] YO-YO..NESTING DOLLS
1FA90..1FAAC;W # So [29] RINGED PLANET..HAMSA
1FAB0..1FABA;W # So [11] FLY..NEST WITH EGGS
1FAC0..1FAC5;W # So [6] ANATOMICAL HEART..PERSON WITH CROWN
1FAD0..1FAD9;W # So [10] BLUEBERRIES..JAR
1FAE0..1FAE7;W # So [8] MELTING FACE..BUBBLES
1FAF0..1FAF6;W # So [7] HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS
1FA70..1FA7C;W # So [13] BALLET SHOES..CRUTCH
1FA80..1FA88;W # So [9] YO-YO..FLUTE
1FA90..1FABD;W # So [46] RINGED PLANET..WING
1FABF..1FAC5;W # So [7] GOOSE..PERSON WITH CROWN
1FACE..1FADB;W # So [14] MOOSE..PEA POD
1FAE0..1FAE8;W # So [9] MELTING FACE..SHAKING FACE
1FAF0..1FAF8;W # So [9] HAND WITH INDEX FINGER AND THUMB CROSSED..RIGHTWARDS PUSHING HAND
1FB00..1FB92;N # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK
1FB94..1FBCA;N # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON
1FBF0..1FBF9;N # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE
20000..2A6DF;W # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF
2A6E0..2A6FF;W # Cn [32] <reserved-2A6E0>..<reserved-2A6FF>
2A700..2B738;W # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738
2B739..2B73F;W # Cn [7] <reserved-2B739>..<reserved-2B73F>
2A700..2B739;W # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739
2B73A..2B73F;W # Cn [6] <reserved-2B73A>..<reserved-2B73F>
2B740..2B81D;W # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2B81E..2B81F;W # Cn [2] <reserved-2B81E>..<reserved-2B81F>
2B820..2CEA1;W # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
@ -2577,7 +2607,9 @@ FFFD;A # So REPLACEMENT CHARACTER
2FA1E..2FA1F;W # Cn [2] <reserved-2FA1E>..<reserved-2FA1F>
2FA20..2FFFD;W # Cn [1502] <reserved-2FA20>..<reserved-2FFFD>
30000..3134A;W # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
3134B..3FFFD;W # Cn [60595] <reserved-3134B>..<reserved-3FFFD>
3134B..3134F;W # Cn [5] <reserved-3134B>..<reserved-3134F>
31350..323AF;W # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
323B0..3FFFD;W # Cn [56398] <reserved-323B0>..<reserved-3FFFD>
E0001;N # Cf LANGUAGE TAG
E0020..E007F;N # Cf [96] TAG SPACE..CANCEL TAG
E0100..E01EF;A # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256

38
util/unicode/data/GraphemeBreakProperty.txt
View File

@ -1,11 +1,11 @@
# GraphemeBreakProperty-14.0.0.txt
# Date: 2021-08-12, 23:13:02 GMT
# © 2021 Unicode®, Inc.
# GraphemeBreakProperty-15.0.0.txt
# Date: 2022-04-27, 17:07:38 GMT
# © 2022 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
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see https://www.unicode.org/reports/tr44/
# ================================================
@ -32,8 +32,9 @@
11A3A ; Prepend # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA
11A84..11A89 ; Prepend # Lo [6] SOYOMBO SIGN JIHVAMULIYA..SOYOMBO CLUSTER-INITIAL LETTER SA
11D46 ; Prepend # Lo MASARAM GONDI REPHA
11F02 ; Prepend # Lo KAWI SIGN REPHA
# Total code points: 26
# Total code points: 27
# ================================================
@ -67,7 +68,7 @@
FEFF ; Control # Cf ZERO WIDTH NO-BREAK SPACE
FFF0..FFF8 ; Control # Cn [9] <reserved-FFF0>..<reserved-FFF8>
FFF9..FFFB ; Control # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR
13430..13438 ; Control # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT
13430..1343F ; Control # Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE
1BCA0..1BCA3 ; Control # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
1D173..1D17A ; Control # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
E0000 ; Control # Cn <reserved-E0000>
@ -76,7 +77,7 @@ E0002..E001F ; Control # Cn [30] <reserved-E0002>..<reserved-E001F>
E0080..E00FF ; Control # Cn [128] <reserved-E0080>..<reserved-E00FF>
E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
# Total code points: 3886
# Total code points: 3893
# ================================================
@ -185,7 +186,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
0E47..0E4E ; Extend # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN
0EB1 ; Extend # Mn LAO VOWEL SIGN MAI KAN
0EB4..0EBC ; Extend # Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO
0EC8..0ECD ; Extend # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA
0EC8..0ECE ; Extend # Mn [7] LAO TONE MAI EK..LAO YAMAKKAN
0F18..0F19 ; Extend # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS
0F35 ; Extend # Mn TIBETAN MARK NGAS BZUNG NYI ZLA
0F37 ; Extend # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS
@ -324,6 +325,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
10AE5..10AE6 ; Extend # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW
10D24..10D27 ; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
10EAB..10EAC ; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK
10EFD..10EFF ; Extend # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA
10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW
10F82..10F85 ; Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW
11001 ; Extend # Mn BRAHMI SIGN ANUSVARA
@ -346,6 +348,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
11234 ; Extend # Mn KHOJKI SIGN ANUSVARA
11236..11237 ; Extend # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
1123E ; Extend # Mn KHOJKI SIGN SUKUN
11241 ; Extend # Mn KHOJKI VOWEL SIGN VOCALIC R
112DF ; Extend # Mn KHUDAWADI SIGN ANUSVARA
112E3..112EA ; Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
11300..11301 ; Extend # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
@ -413,6 +416,12 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
11D95 ; Extend # Mn GUNJALA GONDI SIGN ANUSVARA
11D97 ; Extend # Mn GUNJALA GONDI VIRAMA
11EF3..11EF4 ; Extend # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
11F00..11F01 ; Extend # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA
11F36..11F3A ; Extend # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R
11F40 ; Extend # Mn KAWI VOWEL SIGN EU
11F42 ; Extend # Mn KAWI CONJOINER
13440 ; Extend # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY
13447..13455 ; Extend # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED
16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
16F4F ; Extend # Mn MIAO SIGN CONSONANT MODIFIER BAR
@ -439,16 +448,18 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
1E01B..1E021 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
1E023..1E024 ; Extend # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
1E026..1E02A ; Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
1E08F ; Extend # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
1E130..1E136 ; Extend # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
1E2AE ; Extend # Mn TOTO SIGN RISING TONE
1E2EC..1E2EF ; Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI
1E4EC..1E4EF ; Extend # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH
1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA
1F3FB..1F3FF ; Extend # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG
E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# Total code points: 2095
# Total code points: 2130
# ================================================
@ -489,6 +500,7 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
0CC3..0CC4 ; SpacingMark # Mc [2] KANNADA VOWEL SIGN VOCALIC R..KANNADA VOWEL SIGN VOCALIC RR
0CC7..0CC8 ; SpacingMark # Mc [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI
0CCA..0CCB ; SpacingMark # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO
0CF3 ; SpacingMark # Mc KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
0D02..0D03 ; SpacingMark # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
0D3F..0D40 ; SpacingMark # Mc [2] MALAYALAM VOWEL SIGN I..MALAYALAM VOWEL SIGN II
0D46..0D48 ; SpacingMark # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI
@ -614,12 +626,16 @@ ABEC ; SpacingMark # Mc MEETEI MAYEK LUM IYEK
11D93..11D94 ; SpacingMark # Mc [2] GUNJALA GONDI VOWEL SIGN OO..GUNJALA GONDI VOWEL SIGN AU
11D96 ; SpacingMark # Mc GUNJALA GONDI SIGN VISARGA
11EF5..11EF6 ; SpacingMark # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
11F03 ; SpacingMark # Mc KAWI SIGN VISARGA
11F34..11F35 ; SpacingMark # Mc [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA
11F3E..11F3F ; SpacingMark # Mc [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI
11F41 ; SpacingMark # Mc KAWI SIGN KILLER
16F51..16F87 ; SpacingMark # Mc [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI
16FF0..16FF1 ; SpacingMark # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
1D166 ; SpacingMark # Mc MUSICAL SYMBOL COMBINING SPRECHGESANG STEM
1D16D ; SpacingMark # Mc MUSICAL SYMBOL COMBINING AUGMENTATION DOT
# Total code points: 388
# Total code points: 395
# ================================================

169
util/unicode/data/IdnaMappingTable.txt
View File

@ -1,13 +1,13 @@
# IdnaMappingTable.txt
# Date: 2021-07-10, 00:49:51 GMT
# © 2021 Unicode®, Inc.
# Date: 2022-05-02, 19:29:26 GMT
# © 2022 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
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Unicode IDNA Compatible Preprocessing for UTS #46
# Version: 14.0.0
# Version: 15.0.0
#
# For documentation and usage, see http://www.unicode.org/reports/tr46
# For documentation and usage, see https://www.unicode.org/reports/tr46
#
0000..002C ; disallowed_STD3_valid # 1.1 <control-0000>..COMMA
002D..002E ; valid # 1.1 HYPHEN-MINUS..FULL STOP
@ -1278,7 +1278,8 @@
0CE6..0CEF ; valid # 1.1 KANNADA DIGIT ZERO..KANNADA DIGIT NINE
0CF0 ; disallowed # NA <reserved-0CF0>
0CF1..0CF2 ; valid # 5.0 KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
0CF3..0CFF ; disallowed # NA <reserved-0CF3>..<reserved-0CFF>
0CF3 ; valid # 15.0 KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
0CF4..0CFF ; disallowed # NA <reserved-0CF4>..<reserved-0CFF>
0D00 ; valid # 10.0 MALAYALAM SIGN COMBINING ANUSVARA ABOVE
0D01 ; valid # 7.0 MALAYALAM SIGN CANDRABINDU
0D02..0D03 ; valid # 1.1 MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
@ -1386,7 +1387,8 @@
0EC6 ; valid # 1.1 LAO KO LA
0EC7 ; disallowed # NA <reserved-0EC7>
0EC8..0ECD ; valid # 1.1 LAO TONE MAI EK..LAO NIGGAHITA
0ECE..0ECF ; disallowed # NA <reserved-0ECE>..<reserved-0ECF>
0ECE ; valid # 15.0 LAO YAMAKKAN
0ECF ; disallowed # NA <reserved-0ECF>
0ED0..0ED9 ; valid # 1.1 LAO DIGIT ZERO..LAO DIGIT NINE
0EDA..0EDB ; disallowed # NA <reserved-0EDA>..<reserved-0EDB>
0EDC ; mapped ; 0EAB 0E99 # 1.1 LAO HO NO
@ -6206,7 +6208,8 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
10EAD ; valid ; ; NV8 # 13.0 YEZIDI HYPHENATION MARK
10EAE..10EAF ; disallowed # NA <reserved-10EAE>..<reserved-10EAF>
10EB0..10EB1 ; valid # 13.0 YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE
10EB2..10EFF ; disallowed # NA <reserved-10EB2>..<reserved-10EFF>
10EB2..10EFC ; disallowed # NA <reserved-10EB2>..<reserved-10EFC>
10EFD..10EFF ; valid # 15.0 ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA
10F00..10F1C ; valid # 11.0 OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL
10F1D..10F26 ; valid ; ; NV8 # 11.0 OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF
10F27 ; valid # 11.0 OLD SOGDIAN LIGATURE AYIN-DALETH
@ -6271,7 +6274,8 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
11213..11237 ; valid # 7.0 KHOJKI LETTER NYA..KHOJKI SIGN SHADDA
11238..1123D ; valid ; ; NV8 # 7.0 KHOJKI DANDA..KHOJKI ABBREVIATION SIGN
1123E ; valid # 9.0 KHOJKI SIGN SUKUN
1123F..1127F ; disallowed # NA <reserved-1123F>..<reserved-1127F>
1123F..11241 ; valid # 15.0 KHOJKI LETTER QA..KHOJKI VOWEL SIGN VOCALIC R
11242..1127F ; disallowed # NA <reserved-11242>..<reserved-1127F>
11280..11286 ; valid # 8.0 MULTANI LETTER A..MULTANI LETTER GA
11287 ; disallowed # NA <reserved-11287>
11288 ; valid # 8.0 MULTANI LETTER GHA
@ -6443,7 +6447,9 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
11AA3..11AAF ; disallowed # NA <reserved-11AA3>..<reserved-11AAF>
11AB0..11ABF ; valid # 14.0 CANADIAN SYLLABICS NATTILIK HI..CANADIAN SYLLABICS SPA
11AC0..11AF8 ; valid # 7.0 PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
11AF9..11BFF ; disallowed # NA <reserved-11AF9>..<reserved-11BFF>
11AF9..11AFF ; disallowed # NA <reserved-11AF9>..<reserved-11AFF>
11B00..11B09 ; valid ; ; NV8 # 15.0 DEVANAGARI HEAD MARK..DEVANAGARI SIGN MINDU
11B0A..11BFF ; disallowed # NA <reserved-11B0A>..<reserved-11BFF>
11C00..11C08 ; valid # 9.0 BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L
11C09 ; disallowed # NA <reserved-11C09>
11C0A..11C36 ; valid # 9.0 BHAIKSUKI LETTER E..BHAIKSUKI VOWEL SIGN VOCALIC L
@ -6489,7 +6495,15 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
11DAA..11EDF ; disallowed # NA <reserved-11DAA>..<reserved-11EDF>
11EE0..11EF6 ; valid # 11.0 MAKASAR LETTER KA..MAKASAR VOWEL SIGN O
11EF7..11EF8 ; valid ; ; NV8 # 11.0 MAKASAR PASSIMBANG..MAKASAR END OF SECTION
11EF9..11FAF ; disallowed # NA <reserved-11EF9>..<reserved-11FAF>
11EF9..11EFF ; disallowed # NA <reserved-11EF9>..<reserved-11EFF>
11F00..11F10 ; valid # 15.0 KAWI SIGN CANDRABINDU..KAWI LETTER O
11F11 ; disallowed # NA <reserved-11F11>
11F12..11F3A ; valid # 15.0 KAWI LETTER KA..KAWI VOWEL SIGN VOCALIC R
11F3B..11F3D ; disallowed # NA <reserved-11F3B>..<reserved-11F3D>
11F3E..11F42 ; valid # 15.0 KAWI VOWEL SIGN E..KAWI CONJOINER
11F43..11F4F ; valid ; ; NV8 # 15.0 KAWI DANDA..KAWI PUNCTUATION CLOSING SPIRAL
11F50..11F59 ; valid # 15.0 KAWI DIGIT ZERO..KAWI DIGIT NINE
11F5A..11FAF ; disallowed # NA <reserved-11F5A>..<reserved-11FAF>
11FB0 ; valid # 13.0 LISU LETTER YHA
11FB1..11FBF ; disallowed # NA <reserved-11FB1>..<reserved-11FBF>
11FC0..11FF1 ; valid ; ; NV8 # 12.0 TAMIL FRACTION ONE THREE-HUNDRED-AND-TWENTIETH..TAMIL SIGN VAKAIYARAA
@ -6511,9 +6525,11 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
12FF1..12FF2 ; valid ; ; NV8 # 14.0 CYPRO-MINOAN SIGN CM301..CYPRO-MINOAN SIGN CM302
12FF3..12FFF ; disallowed # NA <reserved-12FF3>..<reserved-12FFF>
13000..1342E ; valid # 5.2 EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
1342F ; disallowed # NA <reserved-1342F>
1342F ; valid # 15.0 EGYPTIAN HIEROGLYPH V011D
13430..13438 ; disallowed # 12.0 EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT
13439..143FF ; disallowed # NA <reserved-13439>..<reserved-143FF>
13439..1343F ; disallowed # 15.0 EGYPTIAN HIEROGLYPH INSERT AT MIDDLE..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE
13440..13455 ; valid # 15.0 EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED
13456..143FF ; disallowed # NA <reserved-13456>..<reserved-143FF>
14400..14646 ; valid # 8.0 ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530
14647..167FF ; disallowed # NA <reserved-14647>..<reserved-167FF>
16800..16A38 ; valid # 6.0 BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ
@ -6615,9 +6631,13 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
1B000..1B001 ; valid # 6.0 KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE
1B002..1B11E ; valid # 10.0 HENTAIGANA LETTER A-1..HENTAIGANA LETTER N-MU-MO-2
1B11F..1B122 ; valid # 14.0 HIRAGANA LETTER ARCHAIC WU..KATAKANA LETTER ARCHAIC WU
1B123..1B14F ; disallowed # NA <reserved-1B123>..<reserved-1B14F>
1B123..1B131 ; disallowed # NA <reserved-1B123>..<reserved-1B131>
1B132 ; valid # 15.0 HIRAGANA LETTER SMALL KO
1B133..1B14F ; disallowed # NA <reserved-1B133>..<reserved-1B14F>
1B150..1B152 ; valid # 12.0 HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO
1B153..1B163 ; disallowed # NA <reserved-1B153>..<reserved-1B163>
1B153..1B154 ; disallowed # NA <reserved-1B153>..<reserved-1B154>
1B155 ; valid # 15.0 KATAKANA LETTER SMALL KO
1B156..1B163 ; disallowed # NA <reserved-1B156>..<reserved-1B163>
1B164..1B167 ; valid # 12.0 KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N
1B168..1B16F ; disallowed # NA <reserved-1B168>..<reserved-1B16F>
1B170..1B2FB ; valid # 10.0 NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
@ -6668,7 +6688,9 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
1D1E9..1D1EA ; valid ; ; NV8 # 14.0 MUSICAL SYMBOL SORI..MUSICAL SYMBOL KORON
1D1EB..1D1FF ; disallowed # NA <reserved-1D1EB>..<reserved-1D1FF>
1D200..1D245 ; valid ; ; NV8 # 4.1 GREEK VOCAL NOTATION SYMBOL-1..GREEK MUSICAL LEIMMA
1D246..1D2DF ; disallowed # NA <reserved-1D246>..<reserved-1D2DF>
1D246..1D2BF ; disallowed # NA <reserved-1D246>..<reserved-1D2BF>
1D2C0..1D2D3 ; valid ; ; NV8 # 15.0 KAKTOVIK NUMERAL ZERO..KAKTOVIK NUMERAL NINETEEN
1D2D4..1D2DF ; disallowed # NA <reserved-1D2D4>..<reserved-1D2DF>
1D2E0..1D2F3 ; valid ; ; NV8 # 11.0 MAYAN NUMERAL ZERO..MAYAN NUMERAL NINETEEN
1D2F4..1D2FF ; disallowed # NA <reserved-1D2F4>..<reserved-1D2FF>
1D300..1D356 ; valid ; ; NV8 # 4.0 MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING
@ -7701,7 +7723,9 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
1DAA1..1DAAF ; valid # 8.0 SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16
1DAB0..1DEFF ; disallowed # NA <reserved-1DAB0>..<reserved-1DEFF>
1DF00..1DF1E ; valid # 14.0 LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER S WITH CURL
1DF1F..1DFFF ; disallowed # NA <reserved-1DF1F>..<reserved-1DFFF>
1DF1F..1DF24 ; disallowed # NA <reserved-1DF1F>..<reserved-1DF24>
1DF25..1DF2A ; valid # 15.0 LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
1DF2B..1DFFF ; disallowed # NA <reserved-1DF2B>..<reserved-1DFFF>
1E000..1E006 ; valid # 9.0 COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
1E007 ; disallowed # NA <reserved-1E007>
1E008..1E018 ; valid # 9.0 COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
@ -7711,7 +7735,72 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
1E023..1E024 ; valid # 9.0 COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
1E025 ; disallowed # NA <reserved-1E025>
1E026..1E02A ; valid # 9.0 COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
1E02B..1E0FF ; disallowed # NA <reserved-1E02B>..<reserved-1E0FF>
1E02B..1E02F ; disallowed # NA <reserved-1E02B>..<reserved-1E02F>
1E030 ; mapped ; 0430 # 15.0 MODIFIER LETTER CYRILLIC SMALL A
1E031 ; mapped ; 0431 # 15.0 MODIFIER LETTER CYRILLIC SMALL BE
1E032 ; mapped ; 0432 # 15.0 MODIFIER LETTER CYRILLIC SMALL VE
1E033 ; mapped ; 0433 # 15.0 MODIFIER LETTER CYRILLIC SMALL GHE
1E034 ; mapped ; 0434 # 15.0 MODIFIER LETTER CYRILLIC SMALL DE
1E035 ; mapped ; 0435 # 15.0 MODIFIER LETTER CYRILLIC SMALL IE
1E036 ; mapped ; 0436 # 15.0 MODIFIER LETTER CYRILLIC SMALL ZHE
1E037 ; mapped ; 0437 # 15.0 MODIFIER LETTER CYRILLIC SMALL ZE
1E038 ; mapped ; 0438 # 15.0 MODIFIER LETTER CYRILLIC SMALL I
1E039 ; mapped ; 043A # 15.0 MODIFIER LETTER CYRILLIC SMALL KA
1E03A ; mapped ; 043B # 15.0 MODIFIER LETTER CYRILLIC SMALL EL
1E03B ; mapped ; 043C # 15.0 MODIFIER LETTER CYRILLIC SMALL EM
1E03C ; mapped ; 043E # 15.0 MODIFIER LETTER CYRILLIC SMALL O
1E03D ; mapped ; 043F # 15.0 MODIFIER LETTER CYRILLIC SMALL PE
1E03E ; mapped ; 0440 # 15.0 MODIFIER LETTER CYRILLIC SMALL ER
1E03F ; mapped ; 0441 # 15.0 MODIFIER LETTER CYRILLIC SMALL ES
1E040 ; mapped ; 0442 # 15.0 MODIFIER LETTER CYRILLIC SMALL TE
1E041 ; mapped ; 0443 # 15.0 MODIFIER LETTER CYRILLIC SMALL U
1E042 ; mapped ; 0444 # 15.0 MODIFIER LETTER CYRILLIC SMALL EF
1E043 ; mapped ; 0445 # 15.0 MODIFIER LETTER CYRILLIC SMALL HA
1E044 ; mapped ; 0446 # 15.0 MODIFIER LETTER CYRILLIC SMALL TSE
1E045 ; mapped ; 0447 # 15.0 MODIFIER LETTER CYRILLIC SMALL CHE
1E046 ; mapped ; 0448 # 15.0 MODIFIER LETTER CYRILLIC SMALL SHA
1E047 ; mapped ; 044B # 15.0 MODIFIER LETTER CYRILLIC SMALL YERU
1E048 ; mapped ; 044D # 15.0 MODIFIER LETTER CYRILLIC SMALL E
1E049 ; mapped ; 044E # 15.0 MODIFIER LETTER CYRILLIC SMALL YU
1E04A ; mapped ; A689 # 15.0 MODIFIER LETTER CYRILLIC SMALL DZZE
1E04B ; mapped ; 04D9 # 15.0 MODIFIER LETTER CYRILLIC SMALL SCHWA
1E04C ; mapped ; 0456 # 15.0 MODIFIER LETTER CYRILLIC SMALL BYELORUSSIAN-UKRAINIAN I
1E04D ; mapped ; 0458 # 15.0 MODIFIER LETTER CYRILLIC SMALL JE
1E04E ; mapped ; 04E9 # 15.0 MODIFIER LETTER CYRILLIC SMALL BARRED O
1E04F ; mapped ; 04AF # 15.0 MODIFIER LETTER CYRILLIC SMALL STRAIGHT U
1E050 ; mapped ; 04CF # 15.0 MODIFIER LETTER CYRILLIC SMALL PALOCHKA
1E051 ; mapped ; 0430 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER A
1E052 ; mapped ; 0431 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER BE
1E053 ; mapped ; 0432 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER VE
1E054 ; mapped ; 0433 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER GHE
1E055 ; mapped ; 0434 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER DE
1E056 ; mapped ; 0435 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER IE
1E057 ; mapped ; 0436 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER ZHE
1E058 ; mapped ; 0437 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER ZE
1E059 ; mapped ; 0438 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER I
1E05A ; mapped ; 043A # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER KA
1E05B ; mapped ; 043B # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER EL
1E05C ; mapped ; 043E # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER O
1E05D ; mapped ; 043F # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER PE
1E05E ; mapped ; 0441 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER ES
1E05F ; mapped ; 0443 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER U
1E060 ; mapped ; 0444 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER EF
1E061 ; mapped ; 0445 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER HA
1E062 ; mapped ; 0446 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER TSE
1E063 ; mapped ; 0447 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER CHE
1E064 ; mapped ; 0448 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER SHA
1E065 ; mapped ; 044A # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER HARD SIGN
1E066 ; mapped ; 044B # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER YERU
1E067 ; mapped ; 0491 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER GHE WITH UPTURN
1E068 ; mapped ; 0456 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER BYELORUSSIAN-UKRAINIAN I
1E069 ; mapped ; 0455 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER DZE
1E06A ; mapped ; 045F # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER DZHE
1E06B ; mapped ; 04AB # 15.0 MODIFIER LETTER CYRILLIC SMALL ES WITH DESCENDER
1E06C ; mapped ; A651 # 15.0 MODIFIER LETTER CYRILLIC SMALL YERU WITH BACK YER
1E06D ; mapped ; 04B1 # 15.0 MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
1E06E..1E08E ; disallowed # NA <reserved-1E06E>..<reserved-1E08E>
1E08F ; valid # 15.0 COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
1E090..1E0FF ; disallowed # NA <reserved-1E090>..<reserved-1E0FF>
1E100..1E12C ; valid # 12.0 NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W
1E12D..1E12F ; disallowed # NA <reserved-1E12D>..<reserved-1E12F>
1E130..1E13D ; valid # 12.0 NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER
@ -7726,7 +7815,9 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
1E2C0..1E2F9 ; valid # 12.0 WANCHO LETTER AA..WANCHO DIGIT NINE
1E2FA..1E2FE ; disallowed # NA <reserved-1E2FA>..<reserved-1E2FE>
1E2FF ; valid ; ; NV8 # 12.0 WANCHO NGUN SIGN
1E300..1E7DF ; disallowed # NA <reserved-1E300>..<reserved-1E7DF>
1E300..1E4CF ; disallowed # NA <reserved-1E300>..<reserved-1E4CF>
1E4D0..1E4F9 ; valid # 15.0 NAG MUNDARI LETTER O..NAG MUNDARI DIGIT NINE
1E4FA..1E7DF ; disallowed # NA <reserved-1E4FA>..<reserved-1E7DF>
1E7E0..1E7E6 ; valid # 14.0 ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO
1E7E7 ; disallowed # NA <reserved-1E7E7>
1E7E8..1E7EB ; valid # 14.0 ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE
@ -8213,7 +8304,8 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
1F6D3..1F6D4 ; valid ; ; NV8 # 10.0 STUPA..PAGODA
1F6D5 ; valid ; ; NV8 # 12.0 HINDU TEMPLE
1F6D6..1F6D7 ; valid ; ; NV8 # 13.0 HUT..ELEVATOR
1F6D8..1F6DC ; disallowed # NA <reserved-1F6D8>..<reserved-1F6DC>
1F6D8..1F6DB ; disallowed # NA <reserved-1F6D8>..<reserved-1F6DB>
1F6DC ; valid ; ; NV8 # 15.0 WIRELESS
1F6DD..1F6DF ; valid ; ; NV8 # 14.0 PLAYGROUND SLIDE..RING BUOY
1F6E0..1F6EC ; valid ; ; NV8 # 7.0 HAMMER AND WRENCH..AIRPLANE ARRIVING
1F6ED..1F6EF ; disallowed # NA <reserved-1F6ED>..<reserved-1F6EF>
@ -8225,10 +8317,13 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
1F6FB..1F6FC ; valid ; ; NV8 # 13.0 PICKUP TRUCK..ROLLER SKATE
1F6FD..1F6FF ; disallowed # NA <reserved-1F6FD>..<reserved-1F6FF>
1F700..1F773 ; valid ; ; NV8 # 6.0 ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
1F774..1F77F ; disallowed # NA <reserved-1F774>..<reserved-1F77F>
1F774..1F776 ; valid ; ; NV8 # 15.0 LOT OF FORTUNE..LUNAR ECLIPSE
1F777..1F77A ; disallowed # NA <reserved-1F777>..<reserved-1F77A>
1F77B..1F77F ; valid ; ; NV8 # 15.0 HAUMEA..ORCUS
1F780..1F7D4 ; valid ; ; NV8 # 7.0 BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR
1F7D5..1F7D8 ; valid ; ; NV8 # 11.0 CIRCLED TRIANGLE..NEGATIVE CIRCLED SQUARE
1F7D9..1F7DF ; disallowed # NA <reserved-1F7D9>..<reserved-1F7DF>
1F7D9 ; valid ; ; NV8 # 15.0 NINE POINTED WHITE STAR
1F7DA..1F7DF ; disallowed # NA <reserved-1F7DA>..<reserved-1F7DF>
1F7E0..1F7EB ; valid ; ; NV8 # 12.0 LARGE ORANGE CIRCLE..LARGE BROWN SQUARE
1F7EC..1F7EF ; disallowed # NA <reserved-1F7EC>..<reserved-1F7EF>
1F7F0 ; valid ; ; NV8 # 14.0 HEAVY EQUALS SIGN
@ -8295,30 +8390,37 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
1FA6E..1FA6F ; disallowed # NA <reserved-1FA6E>..<reserved-1FA6F>
1FA70..1FA73 ; valid ; ; NV8 # 12.0 BALLET SHOES..SHORTS
1FA74 ; valid ; ; NV8 # 13.0 THONG SANDAL
1FA75..1FA77 ; disallowed # NA <reserved-1FA75>..<reserved-1FA77>
1FA75..1FA77 ; valid ; ; NV8 # 15.0 LIGHT BLUE HEART..PINK HEART
1FA78..1FA7A ; valid ; ; NV8 # 12.0 DROP OF BLOOD..STETHOSCOPE
1FA7B..1FA7C ; valid ; ; NV8 # 14.0 X-RAY..CRUTCH
1FA7D..1FA7F ; disallowed # NA <reserved-1FA7D>..<reserved-1FA7F>
1FA80..1FA82 ; valid ; ; NV8 # 12.0 YO-YO..PARACHUTE
1FA83..1FA86 ; valid ; ; NV8 # 13.0 BOOMERANG..NESTING DOLLS
1FA87..1FA8F ; disallowed # NA <reserved-1FA87>..<reserved-1FA8F>
1FA87..1FA88 ; valid ; ; NV8 # 15.0 MARACAS..FLUTE
1FA89..1FA8F ; disallowed # NA <reserved-1FA89>..<reserved-1FA8F>
1FA90..1FA95 ; valid ; ; NV8 # 12.0 RINGED PLANET..BANJO
1FA96..1FAA8 ; valid ; ; NV8 # 13.0 MILITARY HELMET..ROCK
1FAA9..1FAAC ; valid ; ; NV8 # 14.0 MIRROR BALL..HAMSA
1FAAD..1FAAF ; disallowed # NA <reserved-1FAAD>..<reserved-1FAAF>
1FAAD..1FAAF ; valid ; ; NV8 # 15.0 FOLDING HAND FAN..KHANDA
1FAB0..1FAB6 ; valid ; ; NV8 # 13.0 FLY..FEATHER
1FAB7..1FABA ; valid ; ; NV8 # 14.0 LOTUS..NEST WITH EGGS
1FABB..1FABF ; disallowed # NA <reserved-1FABB>..<reserved-1FABF>
1FABB..1FABD ; valid ; ; NV8 # 15.0 HYACINTH..WING
1FABE ; disallowed # NA <reserved-1FABE>
1FABF ; valid ; ; NV8 # 15.0 GOOSE
1FAC0..1FAC2 ; valid ; ; NV8 # 13.0 ANATOMICAL HEART..PEOPLE HUGGING
1FAC3..1FAC5 ; valid ; ; NV8 # 14.0 PREGNANT MAN..PERSON WITH CROWN
1FAC6..1FACF ; disallowed # NA <reserved-1FAC6>..<reserved-1FACF>
1FAC6..1FACD ; disallowed # NA <reserved-1FAC6>..<reserved-1FACD>
1FACE..1FACF ; valid ; ; NV8 # 15.0 MOOSE..DONKEY
1FAD0..1FAD6 ; valid ; ; NV8 # 13.0 BLUEBERRIES..TEAPOT
1FAD7..1FAD9 ; valid ; ; NV8 # 14.0 POURING LIQUID..JAR
1FADA..1FADF ; disallowed # NA <reserved-1FADA>..<reserved-1FADF>
1FADA..1FADB ; valid ; ; NV8 # 15.0 GINGER ROOT..PEA POD
1FADC..1FADF ; disallowed # NA <reserved-1FADC>..<reserved-1FADF>
1FAE0..1FAE7 ; valid ; ; NV8 # 14.0 MELTING FACE..BUBBLES
1FAE8..1FAEF ; disallowed # NA <reserved-1FAE8>..<reserved-1FAEF>
1FAE8 ; valid ; ; NV8 # 15.0 SHAKING FACE
1FAE9..1FAEF ; disallowed # NA <reserved-1FAE9>..<reserved-1FAEF>
1FAF0..1FAF6 ; valid ; ; NV8 # 14.0 HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS
1FAF7..1FAFF ; disallowed # NA <reserved-1FAF7>..<reserved-1FAFF>
1FAF7..1FAF8 ; valid ; ; NV8 # 15.0 LEFTWARDS PUSHING HAND..RIGHTWARDS PUSHING HAND
1FAF9..1FAFF ; disallowed # NA <reserved-1FAF9>..<reserved-1FAFF>
1FB00..1FB92 ; valid ; ; NV8 # 13.0 BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK
1FB93 ; disallowed # NA <reserved-1FB93>
1FB94..1FBCA ; valid ; ; NV8 # 13.0 LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON
@ -8341,7 +8443,8 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
2A6E0..2A6FF ; disallowed # NA <reserved-2A6E0>..<reserved-2A6FF>
2A700..2B734 ; valid # 5.2 CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
2B735..2B738 ; valid # 14.0 CJK UNIFIED IDEOGRAPH-2B735..CJK UNIFIED IDEOGRAPH-2B738
2B739..2B73F ; disallowed # NA <reserved-2B739>..<reserved-2B73F>
2B739 ; valid # 15.0 CJK UNIFIED IDEOGRAPH-2B739
2B73A..2B73F ; disallowed # NA <reserved-2B73A>..<reserved-2B73F>
2B740..2B81D ; valid # 6.0 CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2B81E..2B81F ; disallowed # NA <reserved-2B81E>..<reserved-2B81F>
2B820..2CEA1 ; valid # 8.0 CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
@ -8883,7 +8986,9 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
2FA1E..2FFFD ; disallowed # NA <reserved-2FA1E>..<reserved-2FFFD>
2FFFE..2FFFF ; disallowed # 2.0 <noncharacter-2FFFE>..<noncharacter-2FFFF>
30000..3134A ; valid # 13.0 CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
3134B..3FFFD ; disallowed # NA <reserved-3134B>..<reserved-3FFFD>
3134B..3134F ; disallowed # NA <reserved-3134B>..<reserved-3134F>
31350..323AF ; valid # 15.0 CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
323B0..3FFFD ; disallowed # NA <reserved-323B0>..<reserved-3FFFD>
3FFFE..3FFFF ; disallowed # 2.0 <noncharacter-3FFFE>..<noncharacter-3FFFF>
40000..4FFFD ; disallowed # NA <reserved-40000>..<reserved-4FFFD>
4FFFE..4FFFF ; disallowed # 2.0 <noncharacter-4FFFE>..<noncharacter-4FFFF>

105
util/unicode/data/LineBreak.txt
View File

@ -1,6 +1,6 @@
# LineBreak-14.0.0.txt
# Date: 2021-07-06, 09:58:55 GMT [KW, LI]
# © 2021 Unicode®, Inc.
# LineBreak-15.0.0.txt
# Date: 2022-07-28, 09:20:42 GMT [KW, LI]
# © 2022 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
#
@ -481,6 +481,7 @@
0CE2..0CE3;CM # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
0CE6..0CEF;NU # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE
0CF1..0CF2;AL # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
0CF3;CM # Mc KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
0D00..0D01;CM # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
0D02..0D03;CM # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
0D04..0D0C;AL # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L
@ -542,7 +543,7 @@
0EBD;SA # Lo LAO SEMIVOWEL SIGN NYO
0EC0..0EC4;SA # Lo [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI
0EC6;SA # Lm LAO KO LA
0EC8..0ECD;SA # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA
0EC8..0ECE;SA # Mn [7] LAO TONE MAI EK..LAO YAMAKKAN
0ED0..0ED9;NU # Nd [10] LAO DIGIT ZERO..LAO DIGIT NINE
0EDC..0EDF;SA # Lo [4] LAO HO NO..LAO LETTER KHMU NYO
0F00;AL # Lo TIBETAN SYLLABLE OM
@ -855,7 +856,11 @@
1D79..1D7F;AL # Ll [7] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER UPSILON WITH STROKE
1D80..1D9A;AL # Ll [27] LATIN SMALL LETTER B WITH PALATAL HOOK..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK
1D9B..1DBF;AL # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA
1DC0..1DFF;CM # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
1DC0..1DCC;CM # Mn [13] COMBINING DOTTED GRAVE ACCENT..COMBINING MACRON-BREVE
1DCD;GL # Mn COMBINING DOUBLE CIRCUMFLEX ABOVE
1DCE..1DFB;CM # Mn [46] COMBINING OGONEK ABOVE..COMBINING DELETION MARK
1DFC;GL # Mn COMBINING DOUBLE INVERTED BREVE BELOW
1DFD..1DFF;CM # Mn [3] COMBINING ALMOST EQUAL TO BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
1E00..1EFF;AL # L& [256] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER Y WITH LOOP
1F00..1F15;AL # L& [22] GREEK SMALL LETTER ALPHA WITH PSILI..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA
1F18..1F1D;AL # Lu [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA
@ -931,7 +936,7 @@
2054;AL # Pc INVERTED UNDERTIE
2055;AL # Po FLOWER PUNCTUATION MARK
2056;BA # Po THREE DOT PUNCTUATION
2057;AL # Po QUADRUPLE PRIME
2057;PO # Po QUADRUPLE PRIME
2058..205B;BA # Po [4] FOUR DOT PUNCTUATION..FOUR DOT MARK
205C;AL # Po DOTTED CROSS
205D..205E;BA # Po [2] TRICOLON..VERTICAL FOUR DOTS
@ -2793,6 +2798,7 @@ FFFD;AI # So REPLACEMENT CHARACTER
10EAB..10EAC;CM # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK
10EAD;BA # Pd YEZIDI HYPHENATION MARK
10EB0..10EB1;AL # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE
10EFD..10EFF;CM # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA
10F00..10F1C;AL # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL
10F1D..10F26;AL # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF
10F27;AL # Lo OLD SOGDIAN LIGATURE AYIN-DALETH
@ -2882,6 +2888,8 @@ FFFD;AI # So REPLACEMENT CHARACTER
1123B..1123C;BA # Po [2] KHOJKI SECTION MARK..KHOJKI DOUBLE SECTION MARK
1123D;AL # Po KHOJKI ABBREVIATION SIGN
1123E;CM # Mn KHOJKI SIGN SUKUN
1123F..11240;AL # Lo [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I
11241;CM # Mn KHOJKI VOWEL SIGN VOCALIC R
11280..11286;AL # Lo [7] MULTANI LETTER A..MULTANI LETTER GA
11288;AL # Lo MULTANI LETTER GHA
1128A..1128D;AL # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA
@ -3055,6 +3063,7 @@ FFFD;AI # So REPLACEMENT CHARACTER
11AA1..11AA2;BA # Po [2] SOYOMBO TERMINAL MARK-1..SOYOMBO TERMINAL MARK-2
11AB0..11ABF;AL # Lo [16] CANADIAN SYLLABICS NATTILIK HI..CANADIAN SYLLABICS SPA
11AC0..11AF8;AL # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
11B00..11B09;BB # Po [10] DEVANAGARI HEAD MARK..DEVANAGARI SIGN MINDU
11C00..11C08;AL # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L
11C0A..11C2E;AL # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA
11C2F;CM # Mc BHAIKSUKI VOWEL SIGN AA
@ -3101,6 +3110,20 @@ FFFD;AI # So REPLACEMENT CHARACTER
11EF3..11EF4;CM # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
11EF5..11EF6;CM # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
11EF7..11EF8;AL # Po [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION
11F00..11F01;CM # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA
11F02;AL # Lo KAWI SIGN REPHA
11F03;CM # Mc KAWI SIGN VISARGA
11F04..11F10;AL # Lo [13] KAWI LETTER A..KAWI LETTER O
11F12..11F33;AL # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA
11F34..11F35;CM # Mc [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA
11F36..11F3A;CM # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R
11F3E..11F3F;CM # Mc [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI
11F40;CM # Mn KAWI VOWEL SIGN EU
11F41;CM # Mc KAWI SIGN KILLER
11F42;CM # Mn KAWI CONJOINER
11F43..11F44;BA # Po [2] KAWI DANDA..KAWI DOUBLE DANDA
11F45..11F4F;ID # Po [11] KAWI PUNCTUATION SECTION MARKER..KAWI PUNCTUATION CLOSING SPIRAL
11F50..11F59;NU # Nd [10] KAWI DIGIT ZERO..KAWI DIGIT NINE
11FB0;AL # Lo LISU LETTER YHA
11FC0..11FD4;AL # No [21] TAMIL FRACTION ONE THREE-HUNDRED-AND-TWENTIETH..TAMIL FRACTION DOWNSCALING FACTOR KIIZH
11FD5..11FDC;AL # So [8] TAMIL SIGN NEL..TAMIL SIGN MUKKURUNI
@ -3126,10 +3149,18 @@ FFFD;AI # So REPLACEMENT CHARACTER
1328A..13378;AL # Lo [239] EGYPTIAN HIEROGLYPH O037..EGYPTIAN HIEROGLYPH V011
13379;OP # Lo EGYPTIAN HIEROGLYPH V011A
1337A..1337B;CL # Lo [2] EGYPTIAN HIEROGLYPH V011B..EGYPTIAN HIEROGLYPH V011C
1337C..1342E;AL # Lo [179] EGYPTIAN HIEROGLYPH V012..EGYPTIAN HIEROGLYPH AA032
1337C..1342F;AL # Lo [180] EGYPTIAN HIEROGLYPH V012..EGYPTIAN HIEROGLYPH V011D
13430..13436;GL # Cf [7] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH OVERLAY MIDDLE
13437;OP # Cf EGYPTIAN HIEROGLYPH BEGIN SEGMENT
13438;CL # Cf EGYPTIAN HIEROGLYPH END SEGMENT
13439..1343B;GL # Cf [3] EGYPTIAN HIEROGLYPH INSERT AT MIDDLE..EGYPTIAN HIEROGLYPH INSERT AT BOTTOM
1343C;OP # Cf EGYPTIAN HIEROGLYPH BEGIN ENCLOSURE
1343D;CL # Cf EGYPTIAN HIEROGLYPH END ENCLOSURE
1343E;OP # Cf EGYPTIAN HIEROGLYPH BEGIN WALLED ENCLOSURE
1343F;CL # Cf EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE
13440;CM # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY
13441..13446;AL # Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN
13447..13455;CM # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED
14400..145CD;AL # Lo [462] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A409
145CE;OP # Lo ANATOLIAN HIEROGLYPH A410 BEGIN LOGOGRAM MARK
145CF;CL # Lo ANATOLIAN HIEROGLYPH A410A END LOGOGRAM MARK
@ -3179,7 +3210,9 @@ FFFD;AI # So REPLACEMENT CHARACTER
1AFFD..1AFFE;AL # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
1B000..1B0FF;ID # Lo [256] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER RE-2
1B100..1B122;ID # Lo [35] HENTAIGANA LETTER RE-3..KATAKANA LETTER ARCHAIC WU
1B132;CJ # Lo HIRAGANA LETTER SMALL KO
1B150..1B152;CJ # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO
1B155;CJ # Lo KATAKANA LETTER SMALL KO
1B164..1B167;CJ # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N
1B170..1B2FB;ID # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
1BC00..1BC6A;AL # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
@ -3210,6 +3243,7 @@ FFFD;AI # So REPLACEMENT CHARACTER
1D200..1D241;AL # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54
1D242..1D244;CM # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
1D245;AL # So GREEK MUSICAL LEIMMA
1D2C0..1D2D3;AL # No [20] KAKTOVIK NUMERAL ZERO..KAKTOVIK NUMERAL NINETEEN
1D2E0..1D2F3;AL # No [20] MAYAN NUMERAL ZERO..MAYAN NUMERAL NINETEEN
1D300..1D356;AL # So [87] MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING
1D360..1D378;AL # No [25] COUNTING ROD UNIT DIGIT ONE..TALLY MARK FIVE
@ -3270,11 +3304,14 @@ FFFD;AI # So REPLACEMENT CHARACTER
1DF00..1DF09;AL # Ll [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK
1DF0A;AL # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK
1DF0B..1DF1E;AL # Ll [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL
1DF25..1DF2A;AL # Ll [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
1E000..1E006;CM # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
1E008..1E018;CM # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
1E01B..1E021;CM # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
1E023..1E024;CM # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
1E026..1E02A;CM # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
1E030..1E06D;AL # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
1E08F;CM # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
1E100..1E12C;AL # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W
1E130..1E136;CM # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
1E137..1E13D;AL # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER
@ -3287,6 +3324,10 @@ FFFD;AI # So REPLACEMENT CHARACTER
1E2EC..1E2EF;CM # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI
1E2F0..1E2F9;NU # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE
1E2FF;PR # Sc WANCHO NGUN SIGN
1E4D0..1E4EA;AL # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL
1E4EB;AL # Lm NAG MUNDARI SIGN OJOD
1E4EC..1E4EF;CM # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH
1E4F0..1E4F9;NU # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE
1E7E0..1E7E6;AL # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO
1E7E8..1E7EB;AL # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE
1E7ED..1E7EE;AL # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE
@ -3454,16 +3495,18 @@ FFFD;AI # So REPLACEMENT CHARACTER
1F6C1..1F6CB;ID # So [11] BATHTUB..COUCH AND LAMP
1F6CC;EB # So SLEEPING ACCOMMODATION
1F6CD..1F6D7;ID # So [11] SHOPPING BAGS..ELEVATOR
1F6D8..1F6DC;ID # Cn [5] <reserved-1F6D8>..<reserved-1F6DC>
1F6DD..1F6EC;ID # So [16] PLAYGROUND SLIDE..AIRPLANE ARRIVING
1F6D8..1F6DB;ID # Cn [4] <reserved-1F6D8>..<reserved-1F6DB>
1F6DC..1F6EC;ID # So [17] WIRELESS..AIRPLANE ARRIVING
1F6ED..1F6EF;ID # Cn [3] <reserved-1F6ED>..<reserved-1F6EF>
1F6F0..1F6FC;ID # So [13] SATELLITE..ROLLER SKATE
1F6FD..1F6FF;ID # Cn [3] <reserved-1F6FD>..<reserved-1F6FF>
1F700..1F773;AL # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
1F774..1F77F;ID # Cn [12] <reserved-1F774>..<reserved-1F77F>
1F774..1F776;ID # So [3] LOT OF FORTUNE..LUNAR ECLIPSE
1F777..1F77A;ID # Cn [4] <reserved-1F777>..<reserved-1F77A>
1F77B..1F77F;ID # So [5] HAUMEA..ORCUS
1F780..1F7D4;AL # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR
1F7D5..1F7D8;ID # So [4] CIRCLED TRIANGLE..NEGATIVE CIRCLED SQUARE
1F7D9..1F7DF;ID # Cn [7] <reserved-1F7D9>..<reserved-1F7DF>
1F7D5..1F7D9;ID # So [5] CIRCLED TRIANGLE..NINE POINTED WHITE STAR
1F7DA..1F7DF;ID # Cn [6] <reserved-1F7DA>..<reserved-1F7DF>
1F7E0..1F7EB;ID # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE
1F7EC..1F7EF;ID # Cn [4] <reserved-1F7EC>..<reserved-1F7EF>
1F7F0;ID # So HEAVY EQUALS SIGN
@ -3509,33 +3552,29 @@ FFFD;AI # So REPLACEMENT CHARACTER
1FA54..1FA5F;ID # Cn [12] <reserved-1FA54>..<reserved-1FA5F>
1FA60..1FA6D;ID # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER
1FA6E..1FA6F;ID # Cn [2] <reserved-1FA6E>..<reserved-1FA6F>
1FA70..1FA74;ID # So [5] BALLET SHOES..THONG SANDAL
1FA75..1FA77;ID # Cn [3] <reserved-1FA75>..<reserved-1FA77>
1FA78..1FA7C;ID # So [5] DROP OF BLOOD..CRUTCH
1FA70..1FA7C;ID # So [13] BALLET SHOES..CRUTCH
1FA7D..1FA7F;ID # Cn [3] <reserved-1FA7D>..<reserved-1FA7F>
1FA80..1FA86;ID # So [7] YO-YO..NESTING DOLLS
1FA87..1FA8F;ID # Cn [9] <reserved-1FA87>..<reserved-1FA8F>
1FA90..1FAAC;ID # So [29] RINGED PLANET..HAMSA
1FAAD..1FAAF;ID # Cn [3] <reserved-1FAAD>..<reserved-1FAAF>
1FAB0..1FABA;ID # So [11] FLY..NEST WITH EGGS
1FABB..1FABF;ID # Cn [5] <reserved-1FABB>..<reserved-1FABF>
1FAC0..1FAC2;ID # So [3] ANATOMICAL HEART..PEOPLE HUGGING
1FA80..1FA88;ID # So [9] YO-YO..FLUTE
1FA89..1FA8F;ID # Cn [7] <reserved-1FA89>..<reserved-1FA8F>
1FA90..1FABD;ID # So [46] RINGED PLANET..WING
1FABE;ID # Cn <reserved-1FABE>
1FABF..1FAC2;ID # So [4] GOOSE..PEOPLE HUGGING
1FAC3..1FAC5;EB # So [3] PREGNANT MAN..PERSON WITH CROWN
1FAC6..1FACF;ID # Cn [10] <reserved-1FAC6>..<reserved-1FACF>
1FAD0..1FAD9;ID # So [10] BLUEBERRIES..JAR
1FADA..1FADF;ID # Cn [6] <reserved-1FADA>..<reserved-1FADF>
1FAE0..1FAE7;ID # So [8] MELTING FACE..BUBBLES
1FAE8..1FAEF;ID # Cn [8] <reserved-1FAE8>..<reserved-1FAEF>
1FAF0..1FAF6;EB # So [7] HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS
1FAF7..1FAFF;ID # Cn [9] <reserved-1FAF7>..<reserved-1FAFF>
1FAC6..1FACD;ID # Cn [8] <reserved-1FAC6>..<reserved-1FACD>
1FACE..1FADB;ID # So [14] MOOSE..PEA POD
1FADC..1FADF;ID # Cn [4] <reserved-1FADC>..<reserved-1FADF>
1FAE0..1FAE8;ID # So [9] MELTING FACE..SHAKING FACE
1FAE9..1FAEF;ID # Cn [7] <reserved-1FAE9>..<reserved-1FAEF>
1FAF0..1FAF8;EB # So [9] HAND WITH INDEX FINGER AND THUMB CROSSED..RIGHTWARDS PUSHING HAND
1FAF9..1FAFF;ID # Cn [7] <reserved-1FAF9>..<reserved-1FAFF>
1FB00..1FB92;AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK
1FB94..1FBCA;AL # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON
1FBF0..1FBF9;NU # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE
1FC00..1FFFD;ID # Cn [1022] <reserved-1FC00>..<reserved-1FFFD>
20000..2A6DF;ID # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF
2A6E0..2A6FF;ID # Cn [32] <reserved-2A6E0>..<reserved-2A6FF>
2A700..2B738;ID # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738
2B739..2B73F;ID # Cn [7] <reserved-2B739>..<reserved-2B73F>
2A700..2B739;ID # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739
2B73A..2B73F;ID # Cn [6] <reserved-2B73A>..<reserved-2B73F>
2B740..2B81D;ID # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2B81E..2B81F;ID # Cn [2] <reserved-2B81E>..<reserved-2B81F>
2B820..2CEA1;ID # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
@ -3546,7 +3585,9 @@ FFFD;AI # So REPLACEMENT CHARACTER
2FA1E..2FA1F;ID # Cn [2] <reserved-2FA1E>..<reserved-2FA1F>
2FA20..2FFFD;ID # Cn [1502] <reserved-2FA20>..<reserved-2FFFD>
30000..3134A;ID # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
3134B..3FFFD;ID # Cn [60595] <reserved-3134B>..<reserved-3FFFD>
3134B..3134F;ID # Cn [5] <reserved-3134B>..<reserved-3134F>
31350..323AF;ID # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
323B0..3FFFD;ID # Cn [56398] <reserved-323B0>..<reserved-3FFFD>
E0001;CM # Cf LANGUAGE TAG
E0020..E007F;CM # Cf [96] TAG SPACE..CANCEL TAG
E0100..E01EF;CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256

10
util/unicode/data/NormalizationCorrections.txt
View File

@ -1,10 +1,10 @@
# NormalizationCorrections-14.0.0.txt
# Date: 2021-03-16, 22:07:00 GMT [KW, LI]
# © 2021 Unicode®, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# NormalizationCorrections-15.0.0.txt
# Date: 2022-05-03, 18:53:00 GMT [KW, LI]
# © 2022 Unicode®, Inc.
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see https://www.unicode.org/reports/tr44/
#
# This file is a normative contributory data file in the
# Unicode Character Database.

106
util/unicode/data/Scripts.txt
View File

@ -1,11 +1,11 @@
# Scripts-14.0.0.txt
# Date: 2021-07-10, 00:35:31 GMT
# © 2021 Unicode®, Inc.
# Scripts-15.0.0.txt
# Date: 2022-04-26, 23:15:02 GMT
# © 2022 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
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see https://www.unicode.org/reports/tr44/
# For more information, see:
# UAX #24, Unicode Script Property: https://www.unicode.org/reports/tr24/
# Especially the sections:
@ -532,6 +532,7 @@ 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..1D1EA ; Common # So [61] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KORON
1D2C0..1D2D3 ; Common # No [20] KAKTOVIK NUMERAL ZERO..KAKTOVIK NUMERAL NINETEEN
1D2E0..1D2F3 ; Common # No [20] MAYAN NUMERAL ZERO..MAYAN NUMERAL NINETEEN
1D300..1D356 ; Common # So [87] MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING
1D360..1D378 ; Common # No [25] COUNTING ROD UNIT DIGIT ONE..TALLY MARK FIVE
@ -601,10 +602,10 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1F300..1F3FA ; Common # So [251] CYCLONE..AMPHORA
1F3FB..1F3FF ; Common # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
1F400..1F6D7 ; Common # So [728] RAT..ELEVATOR
1F6DD..1F6EC ; Common # So [16] PLAYGROUND SLIDE..AIRPLANE ARRIVING
1F6DC..1F6EC ; Common # So [17] WIRELESS..AIRPLANE ARRIVING
1F6F0..1F6FC ; Common # So [13] SATELLITE..ROLLER SKATE
1F700..1F773 ; Common # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
1F780..1F7D8 ; Common # So [89] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NEGATIVE CIRCLED SQUARE
1F700..1F776 ; Common # So [119] ALCHEMICAL SYMBOL FOR QUINTESSENCE..LUNAR ECLIPSE
1F77B..1F7D9 ; Common # So [95] HAUMEA..NINE POINTED WHITE STAR
1F7E0..1F7EB ; Common # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE
1F7F0 ; Common # So HEAVY EQUALS SIGN
1F800..1F80B ; Common # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD
@ -615,22 +616,20 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1F8B0..1F8B1 ; Common # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST
1F900..1FA53 ; Common # So [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP
1FA60..1FA6D ; Common # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER
1FA70..1FA74 ; Common # So [5] BALLET SHOES..THONG SANDAL
1FA78..1FA7C ; Common # So [5] DROP OF BLOOD..CRUTCH
1FA80..1FA86 ; Common # So [7] YO-YO..NESTING DOLLS
1FA90..1FAAC ; Common # So [29] RINGED PLANET..HAMSA
1FAB0..1FABA ; Common # So [11] FLY..NEST WITH EGGS
1FAC0..1FAC5 ; Common # So [6] ANATOMICAL HEART..PERSON WITH CROWN
1FAD0..1FAD9 ; Common # So [10] BLUEBERRIES..JAR
1FAE0..1FAE7 ; Common # So [8] MELTING FACE..BUBBLES
1FAF0..1FAF6 ; Common # So [7] HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS
1FA70..1FA7C ; Common # So [13] BALLET SHOES..CRUTCH
1FA80..1FA88 ; Common # So [9] YO-YO..FLUTE
1FA90..1FABD ; Common # So [46] RINGED PLANET..WING
1FABF..1FAC5 ; Common # So [7] GOOSE..PERSON WITH CROWN
1FACE..1FADB ; Common # So [14] MOOSE..PEA POD
1FAE0..1FAE8 ; Common # So [9] MELTING FACE..SHAKING FACE
1FAF0..1FAF8 ; Common # So [9] HAND WITH INDEX FINGER AND THUMB CROSSED..RIGHTWARDS PUSHING HAND
1FB00..1FB92 ; Common # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK
1FB94..1FBCA ; Common # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON
1FBF0..1FBF9 ; Common # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE
E0001 ; Common # Cf LANGUAGE TAG
E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
# Total code points: 8252
# Total code points: 8301
# ================================================
@ -697,8 +696,9 @@ FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN
1DF00..1DF09 ; Latin # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK
1DF0A ; Latin # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK
1DF0B..1DF1E ; Latin # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL
1DF25..1DF2A ; Latin # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
# Total code points: 1475
# Total code points: 1481
# ================================================
@ -784,8 +784,10 @@ A680..A69B ; Cyrillic # L& [28] CYRILLIC CAPITAL LETTER DWE..CYRILLIC SMALL
A69C..A69D ; Cyrillic # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN
A69E..A69F ; Cyrillic # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E
FE2E..FE2F ; Cyrillic # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF
1E030..1E06D ; Cyrillic # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
1E08F ; Cyrillic # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
# Total code points: 443
# Total code points: 506
# ================================================
@ -883,6 +885,7 @@ FDFD..FDFF ; Arabic # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM.
FE70..FE74 ; Arabic # Lo [5] ARABIC FATHATAN ISOLATED FORM..ARABIC KASRATAN ISOLATED FORM
FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM
10E60..10E7E ; Arabic # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS
10EFD..10EFF ; Arabic # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA
1EE00..1EE03 ; Arabic # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL
1EE05..1EE1F ; Arabic # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF
1EE21..1EE22 ; Arabic # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM
@ -918,7 +921,7 @@ 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: 1365
# Total code points: 1368
# ================================================
@ -970,8 +973,9 @@ A8FB ; Devanagari # Lo DEVANAGARI HEADSTROKE
A8FC ; Devanagari # Po DEVANAGARI SIGN SIDDHAM
A8FD..A8FE ; Devanagari # Lo [2] DEVANAGARI JAIN OM..DEVANAGARI LETTER AY
A8FF ; Devanagari # Mn DEVANAGARI VOWEL SIGN AY
11B00..11B09 ; Devanagari # Po [10] DEVANAGARI HEAD MARK..DEVANAGARI SIGN MINDU
# Total code points: 154
# Total code points: 164
# ================================================
@ -1182,8 +1186,9 @@ A8FF ; Devanagari # Mn DEVANAGARI VOWEL SIGN AY
0CE2..0CE3 ; Kannada # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
0CE6..0CEF ; Kannada # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE
0CF1..0CF2 ; Kannada # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
0CF3 ; Kannada # Mc KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
# Total code points: 90
# Total code points: 91
# ================================================
@ -1263,11 +1268,11 @@ A8FF ; Devanagari # Mn DEVANAGARI VOWEL SIGN AY
0EBD ; Lao # Lo LAO SEMIVOWEL SIGN NYO
0EC0..0EC4 ; Lao # Lo [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI
0EC6 ; Lao # Lm LAO KO LA
0EC8..0ECD ; Lao # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA
0EC8..0ECE ; Lao # Mn [7] LAO TONE MAI EK..LAO YAMAKKAN
0ED0..0ED9 ; Lao # Nd [10] LAO DIGIT ZERO..LAO DIGIT NINE
0EDC..0EDF ; Lao # Lo [4] LAO HO NO..LAO LETTER KHMU NYO
# Total code points: 82
# Total code points: 83
# ================================================
@ -1532,10 +1537,11 @@ AB70..ABBF ; Cherokee # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETT
309D..309E ; Hiragana # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK
309F ; Hiragana # Lo HIRAGANA DIGRAPH YORI
1B001..1B11F ; Hiragana # Lo [287] HIRAGANA LETTER ARCHAIC YE..HIRAGANA LETTER ARCHAIC WU
1B132 ; Hiragana # Lo HIRAGANA LETTER SMALL KO
1B150..1B152 ; Hiragana # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO
1F200 ; Hiragana # So SQUARE HIRAGANA HOKA
# Total code points: 380
# Total code points: 381
# ================================================
@ -1552,9 +1558,10 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
1AFFD..1AFFE ; Katakana # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
1B000 ; Katakana # Lo KATAKANA LETTER ARCHAIC E
1B120..1B122 ; Katakana # Lo [3] KATAKANA LETTER ARCHAIC YI..KATAKANA LETTER ARCHAIC WU
1B155 ; Katakana # Lo KATAKANA LETTER SMALL KO
1B164..1B167 ; Katakana # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N
# Total code points: 320
# Total code points: 321
# ================================================
@ -1582,14 +1589,15 @@ FA70..FAD9 ; Han # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILI
16FE3 ; Han # Lm OLD CHINESE ITERATION MARK
16FF0..16FF1 ; Han # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
20000..2A6DF ; Han # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF
2A700..2B738 ; Han # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738
2A700..2B739 ; Han # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739
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
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: 94215
# Total code points: 98408
# ================================================
@ -2093,10 +2101,13 @@ AADE..AADF ; Tai_Viet # Po [2] TAI VIET SYMBOL HO HOI..TAI VIET SYMBOL KOI
# ================================================
13000..1342E ; Egyptian_Hieroglyphs # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
13430..13438 ; Egyptian_Hieroglyphs # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT
13000..1342F ; Egyptian_Hieroglyphs # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D
13430..1343F ; Egyptian_Hieroglyphs # Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE
13440 ; Egyptian_Hieroglyphs # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY
13441..13446 ; Egyptian_Hieroglyphs # Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN
13447..13455 ; Egyptian_Hieroglyphs # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED
# Total code points: 1080
# Total code points: 1110
# ================================================
@ -2440,8 +2451,10 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
11236..11237 ; Khojki # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
11238..1123D ; Khojki # Po [6] KHOJKI DANDA..KHOJKI ABBREVIATION SIGN
1123E ; Khojki # Mn KHOJKI SIGN SUKUN
1123F..11240 ; Khojki # Lo [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I
11241 ; Khojki # Mn KHOJKI VOWEL SIGN VOCALIC R
# Total code points: 62
# Total code points: 65
# ================================================
@ -2988,4 +3001,31 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
# Total code points: 70
# ================================================
11F00..11F01 ; Kawi # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA
11F02 ; Kawi # Lo KAWI SIGN REPHA
11F03 ; Kawi # Mc KAWI SIGN VISARGA
11F04..11F10 ; Kawi # Lo [13] KAWI LETTER A..KAWI LETTER O
11F12..11F33 ; Kawi # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA
11F34..11F35 ; Kawi # Mc [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA
11F36..11F3A ; Kawi # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R
11F3E..11F3F ; Kawi # Mc [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI
11F40 ; Kawi # Mn KAWI VOWEL SIGN EU
11F41 ; Kawi # Mc KAWI SIGN KILLER
11F42 ; Kawi # Mn KAWI CONJOINER
11F43..11F4F ; Kawi # Po [13] KAWI DANDA..KAWI PUNCTUATION CLOSING SPIRAL
11F50..11F59 ; Kawi # Nd [10] KAWI DIGIT ZERO..KAWI DIGIT NINE
# Total code points: 86
# ================================================
1E4D0..1E4EA ; Nag_Mundari # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL
1E4EB ; Nag_Mundari # Lm NAG MUNDARI SIGN OJOD
1E4EC..1E4EF ; Nag_Mundari # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH
1E4F0..1E4F9 ; Nag_Mundari # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE
# Total code points: 42
# EOF

66
util/unicode/data/SentenceBreakProperty.txt
View File

@ -1,11 +1,11 @@
# SentenceBreakProperty-14.0.0.txt
# Date: 2021-08-12, 23:13:21 GMT
# © 2021 Unicode®, Inc.
# SentenceBreakProperty-15.0.0.txt
# Date: 2022-08-05, 22:17:35 GMT
# © 2022 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
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see https://www.unicode.org/reports/tr44/
# ================================================
@ -144,6 +144,7 @@
0CCC..0CCD ; Extend # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA
0CD5..0CD6 ; Extend # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK
0CE2..0CE3 ; Extend # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
0CF3 ; Extend # Mc KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
0D00..0D01 ; Extend # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
0D02..0D03 ; Extend # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
0D3B..0D3C ; Extend # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
@ -167,7 +168,7 @@
0E47..0E4E ; Extend # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN
0EB1 ; Extend # Mn LAO VOWEL SIGN MAI KAN
0EB4..0EBC ; Extend # Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO
0EC8..0ECD ; Extend # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA
0EC8..0ECE ; Extend # Mn [7] LAO TONE MAI EK..LAO YAMAKKAN
0F18..0F19 ; Extend # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS
0F35 ; Extend # Mn TIBETAN MARK NGAS BZUNG NYI ZLA
0F37 ; Extend # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS
@ -371,6 +372,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
10AE5..10AE6 ; Extend # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW
10D24..10D27 ; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
10EAB..10EAC ; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK
10EFD..10EFF ; Extend # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA
10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW
10F82..10F85 ; Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW
11000 ; Extend # Mc BRAHMI SIGN CANDRABINDU
@ -407,6 +409,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
11235 ; Extend # Mc KHOJKI SIGN VIRAMA
11236..11237 ; Extend # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
1123E ; Extend # Mn KHOJKI SIGN SUKUN
11241 ; Extend # Mn KHOJKI VOWEL SIGN VOCALIC R
112DF ; Extend # Mn KHUDAWADI SIGN ANUSVARA
112E0..112E2 ; Extend # Mc [3] KHUDAWADI VOWEL SIGN AA..KHUDAWADI VOWEL SIGN II
112E3..112EA ; Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
@ -516,6 +519,16 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
11D97 ; Extend # Mn GUNJALA GONDI VIRAMA
11EF3..11EF4 ; Extend # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
11EF5..11EF6 ; Extend # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
11F00..11F01 ; Extend # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA
11F03 ; Extend # Mc KAWI SIGN VISARGA
11F34..11F35 ; Extend # Mc [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA
11F36..11F3A ; Extend # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R
11F3E..11F3F ; Extend # Mc [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI
11F40 ; Extend # Mn KAWI VOWEL SIGN EU
11F41 ; Extend # Mc KAWI SIGN KILLER
11F42 ; Extend # Mn KAWI CONJOINER
13440 ; Extend # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY
13447..13455 ; Extend # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED
16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
16F4F ; Extend # Mn MIAO SIGN CONSONANT MODIFIER BAR
@ -544,15 +557,17 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
1E01B..1E021 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
1E023..1E024 ; Extend # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
1E026..1E02A ; Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
1E08F ; Extend # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
1E130..1E136 ; Extend # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
1E2AE ; Extend # Mn TOTO SIGN RISING TONE
1E2EC..1E2EF ; Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI
1E4EC..1E4EF ; Extend # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH
1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA
E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG
E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# Total code points: 2508
# Total code points: 2550
# ================================================
@ -581,12 +596,12 @@ FEFF ; Format # Cf ZERO WIDTH NO-BREAK SPACE
FFF9..FFFB ; Format # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR
110BD ; Format # Cf KAITHI NUMBER SIGN
110CD ; Format # Cf KAITHI NUMBER SIGN ABOVE
13430..13438 ; Format # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT
13430..1343F ; Format # Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE
1BCA0..1BCA3 ; Format # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
1D173..1D17A ; Format # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
E0001 ; Format # Cf LANGUAGE TAG
# Total code points: 65
# Total code points: 72
# ================================================
@ -880,6 +895,7 @@ E0001 ; Format # Cf LANGUAGE TAG
052D ; Lower # L& CYRILLIC SMALL LETTER DCHE
052F ; Lower # L& CYRILLIC SMALL LETTER EL WITH DESCENDER
0560..0588 ; Lower # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE
10FC ; Lower # Lm MODIFIER LETTER GEORGIAN NAR
13F8..13FD ; Lower # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV
1C80..1C88 ; Lower # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK
1D00..1D2B ; Lower # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL
@ -1228,12 +1244,14 @@ A7D3 ; Lower # L& LATIN SMALL LETTER DOUBLE THORN
A7D5 ; Lower # L& LATIN SMALL LETTER DOUBLE WYNN
A7D7 ; Lower # L& LATIN SMALL LETTER MIDDLE SCOTS S
A7D9 ; Lower # L& LATIN SMALL LETTER SIGMOID S
A7F2..A7F4 ; Lower # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q
A7F6 ; Lower # L& LATIN SMALL LETTER REVERSED HALF H
A7F8..A7F9 ; Lower # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
A7FA ; Lower # L& LATIN LETTER SMALL CAPITAL TURNED M
AB30..AB5A ; Lower # L& [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG
AB5C..AB5F ; Lower # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK
AB60..AB68 ; Lower # L& [9] LATIN SMALL LETTER SAKHA YAT..LATIN SMALL LETTER TURNED R WITH MIDDLE TILDE
AB69 ; Lower # Lm MODIFIER LETTER SMALL TURNED W
AB70..ABBF ; Lower # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA
FB00..FB06 ; Lower # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST
FB13..FB17 ; Lower # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH
@ -1281,9 +1299,11 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN
1D7CB ; Lower # L& MATHEMATICAL BOLD SMALL DIGAMMA
1DF00..1DF09 ; Lower # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK
1DF0B..1DF1E ; Lower # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL
1DF25..1DF2A ; Lower # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
1E030..1E06D ; Lower # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
1E922..1E943 ; Lower # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA
# Total code points: 2424
# Total code points: 2497
# ================================================
@ -2102,7 +2122,6 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
1075..1081 ; OLetter # Lo [13] MYANMAR LETTER SHAN KA..MYANMAR LETTER SHAN HA
108E ; OLetter # Lo MYANMAR LETTER RUMAI PALAUNG FA
10D0..10FA ; OLetter # L& [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN
10FC ; OLetter # Lm MODIFIER LETTER GEORGIAN NAR
10FD..10FF ; OLetter # L& [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN
1100..1248 ; OLetter # Lo [329] HANGUL CHOSEONG KIYEOK..ETHIOPIC SYLLABLE QWA
124A..124D ; OLetter # Lo [4] ETHIOPIC SYLLABLE QWI..ETHIOPIC SYLLABLE QWE
@ -2215,7 +2234,6 @@ A6E6..A6EF ; OLetter # Nl [10] BAMUM LETTER MO..BAMUM LETTER KOGHOM
A717..A71F ; OLetter # Lm [9] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOW INVERTED EXCLAMATION MARK
A788 ; OLetter # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT
A78F ; OLetter # Lo LATIN LETTER SINOLOGICAL DOT
A7F2..A7F4 ; OLetter # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q
A7F7 ; OLetter # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I
A7FB..A801 ; OLetter # Lo [7] LATIN EPIGRAPHIC LETTER REVERSED F..SYLOTI NAGRI LETTER I
A803..A805 ; OLetter # Lo [3] SYLOTI NAGRI LETTER U..SYLOTI NAGRI LETTER O
@ -2258,7 +2276,6 @@ AB09..AB0E ; OLetter # Lo [6] ETHIOPIC SYLLABLE DDHU..ETHIOPIC SYLLABLE DDH
AB11..AB16 ; OLetter # Lo [6] ETHIOPIC SYLLABLE DZU..ETHIOPIC SYLLABLE DZO
AB20..AB26 ; OLetter # Lo [7] ETHIOPIC SYLLABLE CCHHA..ETHIOPIC SYLLABLE CCHHO
AB28..AB2E ; OLetter # Lo [7] ETHIOPIC SYLLABLE BBA..ETHIOPIC SYLLABLE BBO
AB69 ; OLetter # Lm MODIFIER LETTER SMALL TURNED W
ABC0..ABE2 ; OLetter # Lo [35] MEETEI MAYEK LETTER KOK..MEETEI MAYEK LETTER I LONSUM
AC00..D7A3 ; OLetter # Lo [11172] HANGUL SYLLABLE GA..HANGUL SYLLABLE HIH
D7B0..D7C6 ; OLetter # Lo [23] HANGUL JUNGSEONG O-YEO..HANGUL JUNGSEONG ARAEA-E
@ -2366,6 +2383,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
111DC ; OLetter # Lo SHARADA HEADSTROKE
11200..11211 ; OLetter # Lo [18] KHOJKI LETTER A..KHOJKI LETTER JJA
11213..1122B ; OLetter # Lo [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA
1123F..11240 ; OLetter # Lo [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I
11280..11286 ; OLetter # Lo [7] MULTANI LETTER A..MULTANI LETTER GA
11288 ; OLetter # Lo MULTANI LETTER GHA
1128A..1128D ; OLetter # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA
@ -2427,12 +2445,16 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
11D6A..11D89 ; OLetter # Lo [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA
11D98 ; OLetter # Lo GUNJALA GONDI OM
11EE0..11EF2 ; OLetter # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA
11F02 ; OLetter # Lo KAWI SIGN REPHA
11F04..11F10 ; OLetter # Lo [13] KAWI LETTER A..KAWI LETTER O
11F12..11F33 ; OLetter # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA
11FB0 ; OLetter # Lo LISU LETTER YHA
12000..12399 ; OLetter # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
12400..1246E ; OLetter # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
12480..12543 ; OLetter # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
12F90..12FF0 ; OLetter # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114
13000..1342E ; OLetter # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
13000..1342F ; OLetter # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D
13441..13446 ; OLetter # Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN
14400..14646 ; OLetter # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530
16800..16A38 ; OLetter # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ
16A40..16A5E ; OLetter # Lo [31] MRO LETTER TA..MRO LETTER TEK
@ -2454,7 +2476,9 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
1AFF5..1AFFB ; OLetter # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
1AFFD..1AFFE ; OLetter # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
1B000..1B122 ; OLetter # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU
1B132 ; OLetter # Lo HIRAGANA LETTER SMALL KO
1B150..1B152 ; OLetter # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO
1B155 ; OLetter # Lo KATAKANA LETTER SMALL KO
1B164..1B167 ; OLetter # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N
1B170..1B2FB ; OLetter # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
1BC00..1BC6A ; OLetter # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
@ -2467,6 +2491,8 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
1E14E ; OLetter # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ
1E290..1E2AD ; OLetter # Lo [30] TOTO LETTER PA..TOTO LETTER A
1E2C0..1E2EB ; OLetter # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH
1E4D0..1E4EA ; OLetter # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL
1E4EB ; OLetter # Lm NAG MUNDARI SIGN OJOD
1E7E0..1E7E6 ; OLetter # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO
1E7E8..1E7EB ; OLetter # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE
1E7ED..1E7EE ; OLetter # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE
@ -2507,14 +2533,15 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
1EEA5..1EEA9 ; OLetter # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH
1EEAB..1EEBB ; OLetter # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
20000..2A6DF ; OLetter # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF
2A700..2B738 ; OLetter # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738
2A700..2B739 ; OLetter # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739
2B740..2B81D ; OLetter # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2B820..2CEA1 ; OLetter # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
2CEB0..2EBE0 ; OLetter # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2F800..2FA1D ; OLetter # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
31350..323AF ; OLetter # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
# Total code points: 127761
# Total code points: 132036
# ================================================
@ -2573,16 +2600,18 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE
11C50..11C59 ; Numeric # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE
11D50..11D59 ; Numeric # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE
11DA0..11DA9 ; Numeric # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE
11F50..11F59 ; Numeric # Nd [10] KAWI DIGIT ZERO..KAWI DIGIT NINE
16A60..16A69 ; Numeric # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE
16AC0..16AC9 ; Numeric # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE
16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE
1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
1E140..1E149 ; Numeric # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE
1E2F0..1E2F9 ; Numeric # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE
1E4F0..1E4F9 ; Numeric # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE
1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE
1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE
# Total code points: 662
# Total code points: 682
# ================================================
@ -2664,6 +2693,7 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP
11A9B..11A9C ; STerm # Po [2] SOYOMBO MARK SHAD..SOYOMBO MARK DOUBLE SHAD
11C41..11C42 ; STerm # Po [2] BHAIKSUKI DANDA..BHAIKSUKI DOUBLE DANDA
11EF7..11EF8 ; STerm # Po [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION
11F43..11F44 ; STerm # Po [2] KAWI DANDA..KAWI DOUBLE DANDA
16A6E..16A6F ; STerm # Po [2] MRO DANDA..MRO DOUBLE DANDA
16AF5 ; STerm # Po BASSA VAH FULL STOP
16B37..16B38 ; STerm # Po [2] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN VOS TSHAB CEEB
@ -2672,7 +2702,7 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP
1BC9F ; STerm # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP
1DA88 ; STerm # Po SIGNWRITING FULL STOP
# Total code points: 149
# Total code points: 151
# ================================================

10
util/unicode/data/SpecialCasing.txt
View File

@ -1,11 +1,11 @@
# SpecialCasing-14.0.0.txt
# Date: 2021-03-08, 19:35:55 GMT
# © 2021 Unicode®, Inc.
# SpecialCasing-15.0.0.txt
# Date: 2022-02-02, 23:35:52 GMT
# © 2022 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
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see https://www.unicode.org/reports/tr44/
#
# Special Casing
#

300
util/unicode/data/UnicodeData.txt
View File

@ -2975,6 +2975,7 @@
0CEF;KANNADA DIGIT NINE;Nd;0;L;;9;9;9;N;;;;;
0CF1;KANNADA SIGN JIHVAMULIYA;Lo;0;L;;;;;N;;;;;
0CF2;KANNADA SIGN UPADHMANIYA;Lo;0;L;;;;;N;;;;;
0CF3;KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT;Mc;0;L;;;;;N;;;;;
0D00;MALAYALAM SIGN COMBINING ANUSVARA ABOVE;Mn;0;NSM;;;;;N;;;;;
0D01;MALAYALAM SIGN CANDRABINDU;Mn;0;NSM;;;;;N;;;;;
0D02;MALAYALAM SIGN ANUSVARA;Mc;0;L;;;;;N;;;;;
@ -3339,6 +3340,7 @@
0ECB;LAO TONE MAI CATAWA;Mn;122;NSM;;;;;N;;;;;
0ECC;LAO CANCELLATION MARK;Mn;0;NSM;;;;;N;;;;;
0ECD;LAO NIGGAHITA;Mn;0;NSM;;;;;N;;;;;
0ECE;LAO YAMAKKAN;Mn;0;NSM;;;;;N;;;;;
0ED0;LAO DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;;
0ED1;LAO DIGIT ONE;Nd;0;L;;1;1;1;N;;;;;
0ED2;LAO DIGIT TWO;Nd;0;L;;2;2;2;N;;;;;
@ -19393,6 +19395,9 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
10EAD;YEZIDI HYPHENATION MARK;Pd;0;R;;;;;N;;;;;
10EB0;YEZIDI LETTER LAM WITH DOT ABOVE;Lo;0;R;;;;;N;;;;;
10EB1;YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE;Lo;0;R;;;;;N;;;;;
10EFD;ARABIC SMALL LOW WORD SAKTA;Mn;220;NSM;;;;;N;;;;;
10EFE;ARABIC SMALL LOW WORD QASR;Mn;220;NSM;;;;;N;;;;;
10EFF;ARABIC SMALL LOW WORD MADDA;Mn;220;NSM;;;;;N;;;;;
10F00;OLD SOGDIAN LETTER ALEPH;Lo;0;R;;;;;N;;;;;
10F01;OLD SOGDIAN LETTER FINAL ALEPH;Lo;0;R;;;;;N;;;;;
10F02;OLD SOGDIAN LETTER BETH;Lo;0;R;;;;;N;;;;;
@ -20058,6 +20063,9 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
1123C;KHOJKI DOUBLE SECTION MARK;Po;0;L;;;;;N;;;;;
1123D;KHOJKI ABBREVIATION SIGN;Po;0;L;;;;;N;;;;;
1123E;KHOJKI SIGN SUKUN;Mn;0;NSM;;;;;N;;;;;
1123F;KHOJKI LETTER QA;Lo;0;L;;;;;N;;;;;
11240;KHOJKI LETTER SHORT I;Lo;0;L;;;;;N;;;;;
11241;KHOJKI VOWEL SIGN VOCALIC R;Mn;0;NSM;;;;;N;;;;;
11280;MULTANI LETTER A;Lo;0;L;;;;;N;;;;;
11281;MULTANI LETTER I;Lo;0;L;;;;;N;;;;;
11282;MULTANI LETTER U;Lo;0;L;;;;;N;;;;;
@ -21256,6 +21264,16 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
11AF6;PAU CIN HAU LOW-FALLING TONE LONG FINAL;Lo;0;L;;;;;N;;;;;
11AF7;PAU CIN HAU LOW-FALLING TONE FINAL;Lo;0;L;;;;;N;;;;;
11AF8;PAU CIN HAU GLOTTAL STOP FINAL;Lo;0;L;;;;;N;;;;;
11B00;DEVANAGARI HEAD MARK;Po;0;L;;;;;N;;;;;
11B01;DEVANAGARI HEAD MARK WITH HEADSTROKE;Po;0;L;;;;;N;;;;;
11B02;DEVANAGARI SIGN BHALE;Po;0;L;;;;;N;;;;;
11B03;DEVANAGARI SIGN BHALE WITH HOOK;Po;0;L;;;;;N;;;;;
11B04;DEVANAGARI SIGN EXTENDED BHALE;Po;0;L;;;;;N;;;;;
11B05;DEVANAGARI SIGN EXTENDED BHALE WITH HOOK;Po;0;L;;;;;N;;;;;
11B06;DEVANAGARI SIGN WESTERN FIVE-LIKE BHALE;Po;0;L;;;;;N;;;;;
11B07;DEVANAGARI SIGN WESTERN NINE-LIKE BHALE;Po;0;L;;;;;N;;;;;
11B08;DEVANAGARI SIGN REVERSED NINE-LIKE BHALE;Po;0;L;;;;;N;;;;;
11B09;DEVANAGARI SIGN MINDU;Po;0;L;;;;;N;;;;;
11C00;BHAIKSUKI LETTER A;Lo;0;L;;;;;N;;;;;
11C01;BHAIKSUKI LETTER AA;Lo;0;L;;;;;N;;;;;
11C02;BHAIKSUKI LETTER I;Lo;0;L;;;;;N;;;;;
@ -21584,6 +21602,92 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
11EF6;MAKASAR VOWEL SIGN O;Mc;0;L;;;;;N;;;;;
11EF7;MAKASAR PASSIMBANG;Po;0;L;;;;;N;;;;;
11EF8;MAKASAR END OF SECTION;Po;0;L;;;;;N;;;;;
11F00;KAWI SIGN CANDRABINDU;Mn;0;NSM;;;;;N;;;;;
11F01;KAWI SIGN ANUSVARA;Mn;0;NSM;;;;;N;;;;;
11F02;KAWI SIGN REPHA;Lo;0;L;;;;;N;;;;;
11F03;KAWI SIGN VISARGA;Mc;0;L;;;;;N;;;;;
11F04;KAWI LETTER A;Lo;0;L;;;;;N;;;;;
11F05;KAWI LETTER AA;Lo;0;L;;;;;N;;;;;
11F06;KAWI LETTER I;Lo;0;L;;;;;N;;;;;
11F07;KAWI LETTER II;Lo;0;L;;;;;N;;;;;
11F08;KAWI LETTER U;Lo;0;L;;;;;N;;;;;
11F09;KAWI LETTER UU;Lo;0;L;;;;;N;;;;;
11F0A;KAWI LETTER VOCALIC R;Lo;0;L;;;;;N;;;;;
11F0B;KAWI LETTER VOCALIC RR;Lo;0;L;;;;;N;;;;;
11F0C;KAWI LETTER VOCALIC L;Lo;0;L;;;;;N;;;;;
11F0D;KAWI LETTER VOCALIC LL;Lo;0;L;;;;;N;;;;;
11F0E;KAWI LETTER E;Lo;0;L;;;;;N;;;;;
11F0F;KAWI LETTER AI;Lo;0;L;;;;;N;;;;;
11F10;KAWI LETTER O;Lo;0;L;;;;;N;;;;;
11F12;KAWI LETTER KA;Lo;0;L;;;;;N;;;;;
11F13;KAWI LETTER KHA;Lo;0;L;;;;;N;;;;;
11F14;KAWI LETTER GA;Lo;0;L;;;;;N;;;;;
11F15;KAWI LETTER GHA;Lo;0;L;;;;;N;;;;;
11F16;KAWI LETTER NGA;Lo;0;L;;;;;N;;;;;
11F17;KAWI LETTER CA;Lo;0;L;;;;;N;;;;;
11F18;KAWI LETTER CHA;Lo;0;L;;;;;N;;;;;
11F19;KAWI LETTER JA;Lo;0;L;;;;;N;;;;;
11F1A;KAWI LETTER JHA;Lo;0;L;;;;;N;;;;;
11F1B;KAWI LETTER NYA;Lo;0;L;;;;;N;;;;;
11F1C;KAWI LETTER TTA;Lo;0;L;;;;;N;;;;;
11F1D;KAWI LETTER TTHA;Lo;0;L;;;;;N;;;;;
11F1E;KAWI LETTER DDA;Lo;0;L;;;;;N;;;;;
11F1F;KAWI LETTER DDHA;Lo;0;L;;;;;N;;;;;
11F20;KAWI LETTER NNA;Lo;0;L;;;;;N;;;;;
11F21;KAWI LETTER TA;Lo;0;L;;;;;N;;;;;
11F22;KAWI LETTER THA;Lo;0;L;;;;;N;;;;;
11F23;KAWI LETTER DA;Lo;0;L;;;;;N;;;;;
11F24;KAWI LETTER DHA;Lo;0;L;;;;;N;;;;;
11F25;KAWI LETTER NA;Lo;0;L;;;;;N;;;;;
11F26;KAWI LETTER PA;Lo;0;L;;;;;N;;;;;
11F27;KAWI LETTER PHA;Lo;0;L;;;;;N;;;;;
11F28;KAWI LETTER BA;Lo;0;L;;;;;N;;;;;
11F29;KAWI LETTER BHA;Lo;0;L;;;;;N;;;;;
11F2A;KAWI LETTER MA;Lo;0;L;;;;;N;;;;;
11F2B;KAWI LETTER YA;Lo;0;L;;;;;N;;;;;
11F2C;KAWI LETTER RA;Lo;0;L;;;;;N;;;;;
11F2D;KAWI LETTER LA;Lo;0;L;;;;;N;;;;;
11F2E;KAWI LETTER WA;Lo;0;L;;;;;N;;;;;
11F2F;KAWI LETTER SHA;Lo;0;L;;;;;N;;;;;
11F30;KAWI LETTER SSA;Lo;0;L;;;;;N;;;;;
11F31;KAWI LETTER SA;Lo;0;L;;;;;N;;;;;
11F32;KAWI LETTER HA;Lo;0;L;;;;;N;;;;;
11F33;KAWI LETTER JNYA;Lo;0;L;;;;;N;;;;;
11F34;KAWI VOWEL SIGN AA;Mc;0;L;;;;;N;;;;;
11F35;KAWI VOWEL SIGN ALTERNATE AA;Mc;0;L;;;;;N;;;;;
11F36;KAWI VOWEL SIGN I;Mn;0;NSM;;;;;N;;;;;
11F37;KAWI VOWEL SIGN II;Mn;0;NSM;;;;;N;;;;;
11F38;KAWI VOWEL SIGN U;Mn;0;NSM;;;;;N;;;;;
11F39;KAWI VOWEL SIGN UU;Mn;0;NSM;;;;;N;;;;;
11F3A;KAWI VOWEL SIGN VOCALIC R;Mn;0;NSM;;;;;N;;;;;
11F3E;KAWI VOWEL SIGN E;Mc;0;L;;;;;N;;;;;
11F3F;KAWI VOWEL SIGN AI;Mc;0;L;;;;;N;;;;;
11F40;KAWI VOWEL SIGN EU;Mn;0;NSM;;;;;N;;;;;
11F41;KAWI SIGN KILLER;Mc;9;L;;;;;N;;;;;
11F42;KAWI CONJOINER;Mn;9;NSM;;;;;N;;;;;
11F43;KAWI DANDA;Po;0;L;;;;;N;;;;;
11F44;KAWI DOUBLE DANDA;Po;0;L;;;;;N;;;;;
11F45;KAWI PUNCTUATION SECTION MARKER;Po;0;L;;;;;N;;;;;
11F46;KAWI PUNCTUATION ALTERNATE SECTION MARKER;Po;0;L;;;;;N;;;;;
11F47;KAWI PUNCTUATION FLOWER;Po;0;L;;;;;N;;;;;
11F48;KAWI PUNCTUATION SPACE FILLER;Po;0;L;;;;;N;;;;;
11F49;KAWI PUNCTUATION DOT;Po;0;L;;;;;N;;;;;
11F4A;KAWI PUNCTUATION DOUBLE DOT;Po;0;L;;;;;N;;;;;
11F4B;KAWI PUNCTUATION TRIPLE DOT;Po;0;L;;;;;N;;;;;
11F4C;KAWI PUNCTUATION CIRCLE;Po;0;L;;;;;N;;;;;
11F4D;KAWI PUNCTUATION FILLED CIRCLE;Po;0;L;;;;;N;;;;;
11F4E;KAWI PUNCTUATION SPIRAL;Po;0;L;;;;;N;;;;;
11F4F;KAWI PUNCTUATION CLOSING SPIRAL;Po;0;L;;;;;N;;;;;
11F50;KAWI DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;;
11F51;KAWI DIGIT ONE;Nd;0;L;;1;1;1;N;;;;;
11F52;KAWI DIGIT TWO;Nd;0;L;;2;2;2;N;;;;;
11F53;KAWI DIGIT THREE;Nd;0;L;;3;3;3;N;;;;;
11F54;KAWI DIGIT FOUR;Nd;0;L;;4;4;4;N;;;;;
11F55;KAWI DIGIT FIVE;Nd;0;L;;5;5;5;N;;;;;
11F56;KAWI DIGIT SIX;Nd;0;L;;6;6;6;N;;;;;
11F57;KAWI DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;;
11F58;KAWI DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;;
11F59;KAWI DIGIT NINE;Nd;0;L;;9;9;9;N;;;;;
11FB0;LISU LETTER YHA;Lo;0;L;;;;;N;;;;;
11FC0;TAMIL FRACTION ONE THREE-HUNDRED-AND-TWENTIETH;No;0;L;;;;1/320;N;;;;;
11FC1;TAMIL FRACTION ONE ONE-HUNDRED-AND-SIXTIETH;No;0;L;;;;1/160;N;;;;;
@ -24040,6 +24144,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
1342C;EGYPTIAN HIEROGLYPH AA030;Lo;0;L;;;;;N;;;;;
1342D;EGYPTIAN HIEROGLYPH AA031;Lo;0;L;;;;;N;;;;;
1342E;EGYPTIAN HIEROGLYPH AA032;Lo;0;L;;;;;N;;;;;
1342F;EGYPTIAN HIEROGLYPH V011D;Lo;0;L;;;;;N;;;;;
13430;EGYPTIAN HIEROGLYPH VERTICAL JOINER;Cf;0;L;;;;;N;;;;;
13431;EGYPTIAN HIEROGLYPH HORIZONTAL JOINER;Cf;0;L;;;;;N;;;;;
13432;EGYPTIAN HIEROGLYPH INSERT AT TOP START;Cf;0;L;;;;;N;;;;;
@ -24049,6 +24154,35 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
13436;EGYPTIAN HIEROGLYPH OVERLAY MIDDLE;Cf;0;L;;;;;N;;;;;
13437;EGYPTIAN HIEROGLYPH BEGIN SEGMENT;Cf;0;L;;;;;N;;;;;
13438;EGYPTIAN HIEROGLYPH END SEGMENT;Cf;0;L;;;;;N;;;;;
13439;EGYPTIAN HIEROGLYPH INSERT AT MIDDLE;Cf;0;L;;;;;N;;;;;
1343A;EGYPTIAN HIEROGLYPH INSERT AT TOP;Cf;0;L;;;;;N;;;;;
1343B;EGYPTIAN HIEROGLYPH INSERT AT BOTTOM;Cf;0;L;;;;;N;;;;;
1343C;EGYPTIAN HIEROGLYPH BEGIN ENCLOSURE;Cf;0;L;;;;;N;;;;;
1343D;EGYPTIAN HIEROGLYPH END ENCLOSURE;Cf;0;L;;;;;N;;;;;
1343E;EGYPTIAN HIEROGLYPH BEGIN WALLED ENCLOSURE;Cf;0;L;;;;;N;;;;;
1343F;EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE;Cf;0;L;;;;;N;;;;;
13440;EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY;Mn;0;NSM;;;;;N;;;;;
13441;EGYPTIAN HIEROGLYPH FULL BLANK;Lo;0;L;;;;;N;;;;;
13442;EGYPTIAN HIEROGLYPH HALF BLANK;Lo;0;L;;;;;N;;;;;
13443;EGYPTIAN HIEROGLYPH LOST SIGN;Lo;0;L;;;;;N;;;;;
13444;EGYPTIAN HIEROGLYPH HALF LOST SIGN;Lo;0;L;;;;;N;;;;;
13445;EGYPTIAN HIEROGLYPH TALL LOST SIGN;Lo;0;L;;;;;N;;;;;
13446;EGYPTIAN HIEROGLYPH WIDE LOST SIGN;Lo;0;L;;;;;N;;;;;
13447;EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START;Mn;0;NSM;;;;;N;;;;;
13448;EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT BOTTOM START;Mn;0;NSM;;;;;N;;;;;
13449;EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT START;Mn;0;NSM;;;;;N;;;;;
1344A;EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP END;Mn;0;NSM;;;;;N;;;;;
1344B;EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP;Mn;0;NSM;;;;;N;;;;;
1344C;EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT BOTTOM START AND TOP END;Mn;0;NSM;;;;;N;;;;;
1344D;EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT START AND TOP;Mn;0;NSM;;;;;N;;;;;
1344E;EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT BOTTOM END;Mn;0;NSM;;;;;N;;;;;
1344F;EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START AND BOTTOM END;Mn;0;NSM;;;;;N;;;;;
13450;EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT BOTTOM;Mn;0;NSM;;;;;N;;;;;
13451;EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT START AND BOTTOM;Mn;0;NSM;;;;;N;;;;;
13452;EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT END;Mn;0;NSM;;;;;N;;;;;
13453;EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP AND END;Mn;0;NSM;;;;;N;;;;;
13454;EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT BOTTOM AND END;Mn;0;NSM;;;;;N;;;;;
13455;EGYPTIAN HIEROGLYPH MODIFIER DAMAGED;Mn;0;NSM;;;;;N;;;;;
14400;ANATOLIAN HIEROGLYPH A001;Lo;0;L;;;;;N;;;;;
14401;ANATOLIAN HIEROGLYPH A002;Lo;0;L;;;;;N;;;;;
14402;ANATOLIAN HIEROGLYPH A003;Lo;0;L;;;;;N;;;;;
@ -27289,9 +27423,11 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
1B120;KATAKANA LETTER ARCHAIC YI;Lo;0;L;;;;;N;;;;;
1B121;KATAKANA LETTER ARCHAIC YE;Lo;0;L;;;;;N;;;;;
1B122;KATAKANA LETTER ARCHAIC WU;Lo;0;L;;;;;N;;;;;
1B132;HIRAGANA LETTER SMALL KO;Lo;0;L;;;;;N;;;;;
1B150;HIRAGANA LETTER SMALL WI;Lo;0;L;;;;;N;;;;;
1B151;HIRAGANA LETTER SMALL WE;Lo;0;L;;;;;N;;;;;
1B152;HIRAGANA LETTER SMALL WO;Lo;0;L;;;;;N;;;;;
1B155;KATAKANA LETTER SMALL KO;Lo;0;L;;;;;N;;;;;
1B164;KATAKANA LETTER SMALL WI;Lo;0;L;;;;;N;;;;;
1B165;KATAKANA LETTER SMALL WE;Lo;0;L;;;;;N;;;;;
1B166;KATAKANA LETTER SMALL WO;Lo;0;L;;;;;N;;;;;
@ -28573,6 +28709,26 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
1D243;COMBINING GREEK MUSICAL TETRASEME;Mn;230;NSM;;;;;N;;;;;
1D244;COMBINING GREEK MUSICAL PENTASEME;Mn;230;NSM;;;;;N;;;;;
1D245;GREEK MUSICAL LEIMMA;So;0;ON;;;;;N;;;;;
1D2C0;KAKTOVIK NUMERAL ZERO;No;0;L;;;;0;N;;;;;
1D2C1;KAKTOVIK NUMERAL ONE;No;0;L;;;;1;N;;;;;
1D2C2;KAKTOVIK NUMERAL TWO;No;0;L;;;;2;N;;;;;
1D2C3;KAKTOVIK NUMERAL THREE;No;0;L;;;;3;N;;;;;
1D2C4;KAKTOVIK NUMERAL FOUR;No;0;L;;;;4;N;;;;;
1D2C5;KAKTOVIK NUMERAL FIVE;No;0;L;;;;5;N;;;;;
1D2C6;KAKTOVIK NUMERAL SIX;No;0;L;;;;6;N;;;;;
1D2C7;KAKTOVIK NUMERAL SEVEN;No;0;L;;;;7;N;;;;;
1D2C8;KAKTOVIK NUMERAL EIGHT;No;0;L;;;;8;N;;;;;
1D2C9;KAKTOVIK NUMERAL NINE;No;0;L;;;;9;N;;;;;
1D2CA;KAKTOVIK NUMERAL TEN;No;0;L;;;;10;N;;;;;
1D2CB;KAKTOVIK NUMERAL ELEVEN;No;0;L;;;;11;N;;;;;
1D2CC;KAKTOVIK NUMERAL TWELVE;No;0;L;;;;12;N;;;;;
1D2CD;KAKTOVIK NUMERAL THIRTEEN;No;0;L;;;;13;N;;;;;
1D2CE;KAKTOVIK NUMERAL FOURTEEN;No;0;L;;;;14;N;;;;;
1D2CF;KAKTOVIK NUMERAL FIFTEEN;No;0;L;;;;15;N;;;;;
1D2D0;KAKTOVIK NUMERAL SIXTEEN;No;0;L;;;;16;N;;;;;
1D2D1;KAKTOVIK NUMERAL SEVENTEEN;No;0;L;;;;17;N;;;;;
1D2D2;KAKTOVIK NUMERAL EIGHTEEN;No;0;L;;;;18;N;;;;;
1D2D3;KAKTOVIK NUMERAL NINETEEN;No;0;L;;;;19;N;;;;;
1D2E0;MAYAN NUMERAL ZERO;No;0;L;;;;0;N;;;;;
1D2E1;MAYAN NUMERAL ONE;No;0;L;;;;1;N;;;;;
1D2E2;MAYAN NUMERAL TWO;No;0;L;;;;2;N;;;;;
@ -30404,6 +30560,12 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
1DF1C;LATIN SMALL LETTER TESH DIGRAPH WITH RETROFLEX HOOK;Ll;0;L;;;;;N;;;;;
1DF1D;LATIN SMALL LETTER C WITH RETROFLEX HOOK;Ll;0;L;;;;;N;;;;;
1DF1E;LATIN SMALL LETTER S WITH CURL;Ll;0;L;;;;;N;;;;;
1DF25;LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK;Ll;0;L;;;;;N;;;;;
1DF26;LATIN SMALL LETTER L WITH MID-HEIGHT LEFT HOOK;Ll;0;L;;;;;N;;;;;
1DF27;LATIN SMALL LETTER N WITH MID-HEIGHT LEFT HOOK;Ll;0;L;;;;;N;;;;;
1DF28;LATIN SMALL LETTER R WITH MID-HEIGHT LEFT HOOK;Ll;0;L;;;;;N;;;;;
1DF29;LATIN SMALL LETTER S WITH MID-HEIGHT LEFT HOOK;Ll;0;L;;;;;N;;;;;
1DF2A;LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK;Ll;0;L;;;;;N;;;;;
1E000;COMBINING GLAGOLITIC LETTER AZU;Mn;230;NSM;;;;;N;;;;;
1E001;COMBINING GLAGOLITIC LETTER BUKY;Mn;230;NSM;;;;;N;;;;;
1E002;COMBINING GLAGOLITIC LETTER VEDE;Mn;230;NSM;;;;;N;;;;;
@ -30442,6 +30604,69 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
1E028;COMBINING GLAGOLITIC LETTER BIG YUS;Mn;230;NSM;;;;;N;;;;;
1E029;COMBINING GLAGOLITIC LETTER IOTATED BIG YUS;Mn;230;NSM;;;;;N;;;;;
1E02A;COMBINING GLAGOLITIC LETTER FITA;Mn;230;NSM;;;;;N;;;;;
1E030;MODIFIER LETTER CYRILLIC SMALL A;Lm;0;L;<super> 0430;;;;N;;;;;
1E031;MODIFIER LETTER CYRILLIC SMALL BE;Lm;0;L;<super> 0431;;;;N;;;;;
1E032;MODIFIER LETTER CYRILLIC SMALL VE;Lm;0;L;<super> 0432;;;;N;;;;;
1E033;MODIFIER LETTER CYRILLIC SMALL GHE;Lm;0;L;<super> 0433;;;;N;;;;;
1E034;MODIFIER LETTER CYRILLIC SMALL DE;Lm;0;L;<super> 0434;;;;N;;;;;
1E035;MODIFIER LETTER CYRILLIC SMALL IE;Lm;0;L;<super> 0435;;;;N;;;;;
1E036;MODIFIER LETTER CYRILLIC SMALL ZHE;Lm;0;L;<super> 0436;;;;N;;;;;
1E037;MODIFIER LETTER CYRILLIC SMALL ZE;Lm;0;L;<super> 0437;;;;N;;;;;
1E038;MODIFIER LETTER CYRILLIC SMALL I;Lm;0;L;<super> 0438;;;;N;;;;;
1E039;MODIFIER LETTER CYRILLIC SMALL KA;Lm;0;L;<super> 043A;;;;N;;;;;
1E03A;MODIFIER LETTER CYRILLIC SMALL EL;Lm;0;L;<super> 043B;;;;N;;;;;
1E03B;MODIFIER LETTER CYRILLIC SMALL EM;Lm;0;L;<super> 043C;;;;N;;;;;
1E03C;MODIFIER LETTER CYRILLIC SMALL O;Lm;0;L;<super> 043E;;;;N;;;;;
1E03D;MODIFIER LETTER CYRILLIC SMALL PE;Lm;0;L;<super> 043F;;;;N;;;;;
1E03E;MODIFIER LETTER CYRILLIC SMALL ER;Lm;0;L;<super> 0440;;;;N;;;;;
1E03F;MODIFIER LETTER CYRILLIC SMALL ES;Lm;0;L;<super> 0441;;;;N;;;;;
1E040;MODIFIER LETTER CYRILLIC SMALL TE;Lm;0;L;<super> 0442;;;;N;;;;;
1E041;MODIFIER LETTER CYRILLIC SMALL U;Lm;0;L;<super> 0443;;;;N;;;;;
1E042;MODIFIER LETTER CYRILLIC SMALL EF;Lm;0;L;<super> 0444;;;;N;;;;;
1E043;MODIFIER LETTER CYRILLIC SMALL HA;Lm;0;L;<super> 0445;;;;N;;;;;
1E044;MODIFIER LETTER CYRILLIC SMALL TSE;Lm;0;L;<super> 0446;;;;N;;;;;
1E045;MODIFIER LETTER CYRILLIC SMALL CHE;Lm;0;L;<super> 0447;;;;N;;;;;
1E046;MODIFIER LETTER CYRILLIC SMALL SHA;Lm;0;L;<super> 0448;;;;N;;;;;
1E047;MODIFIER LETTER CYRILLIC SMALL YERU;Lm;0;L;<super> 044B;;;;N;;;;;
1E048;MODIFIER LETTER CYRILLIC SMALL E;Lm;0;L;<super> 044D;;;;N;;;;;
1E049;MODIFIER LETTER CYRILLIC SMALL YU;Lm;0;L;<super> 044E;;;;N;;;;;
1E04A;MODIFIER LETTER CYRILLIC SMALL DZZE;Lm;0;L;<super> A689;;;;N;;;;;
1E04B;MODIFIER LETTER CYRILLIC SMALL SCHWA;Lm;0;L;<super> 04D9;;;;N;;;;;
1E04C;MODIFIER LETTER CYRILLIC SMALL BYELORUSSIAN-UKRAINIAN I;Lm;0;L;<super> 0456;;;;N;;;;;
1E04D;MODIFIER LETTER CYRILLIC SMALL JE;Lm;0;L;<super> 0458;;;;N;;;;;
1E04E;MODIFIER LETTER CYRILLIC SMALL BARRED O;Lm;0;L;<super> 04E9;;;;N;;;;;
1E04F;MODIFIER LETTER CYRILLIC SMALL STRAIGHT U;Lm;0;L;<super> 04AF;;;;N;;;;;
1E050;MODIFIER LETTER CYRILLIC SMALL PALOCHKA;Lm;0;L;<super> 04CF;;;;N;;;;;
1E051;CYRILLIC SUBSCRIPT SMALL LETTER A;Lm;0;L;<sub> 0430;;;;N;;;;;
1E052;CYRILLIC SUBSCRIPT SMALL LETTER BE;Lm;0;L;<sub> 0431;;;;N;;;;;
1E053;CYRILLIC SUBSCRIPT SMALL LETTER VE;Lm;0;L;<sub> 0432;;;;N;;;;;
1E054;CYRILLIC SUBSCRIPT SMALL LETTER GHE;Lm;0;L;<sub> 0433;;;;N;;;;;
1E055;CYRILLIC SUBSCRIPT SMALL LETTER DE;Lm;0;L;<sub> 0434;;;;N;;;;;
1E056;CYRILLIC SUBSCRIPT SMALL LETTER IE;Lm;0;L;<sub> 0435;;;;N;;;;;
1E057;CYRILLIC SUBSCRIPT SMALL LETTER ZHE;Lm;0;L;<sub> 0436;;;;N;;;;;
1E058;CYRILLIC SUBSCRIPT SMALL LETTER ZE;Lm;0;L;<sub> 0437;;;;N;;;;;
1E059;CYRILLIC SUBSCRIPT SMALL LETTER I;Lm;0;L;<sub> 0438;;;;N;;;;;
1E05A;CYRILLIC SUBSCRIPT SMALL LETTER KA;Lm;0;L;<sub> 043A;;;;N;;;;;
1E05B;CYRILLIC SUBSCRIPT SMALL LETTER EL;Lm;0;L;<sub> 043B;;;;N;;;;;
1E05C;CYRILLIC SUBSCRIPT SMALL LETTER O;Lm;0;L;<sub> 043E;;;;N;;;;;
1E05D;CYRILLIC SUBSCRIPT SMALL LETTER PE;Lm;0;L;<sub> 043F;;;;N;;;;;
1E05E;CYRILLIC SUBSCRIPT SMALL LETTER ES;Lm;0;L;<sub> 0441;;;;N;;;;;
1E05F;CYRILLIC SUBSCRIPT SMALL LETTER U;Lm;0;L;<sub> 0443;;;;N;;;;;
1E060;CYRILLIC SUBSCRIPT SMALL LETTER EF;Lm;0;L;<sub> 0444;;;;N;;;;;
1E061;CYRILLIC SUBSCRIPT SMALL LETTER HA;Lm;0;L;<sub> 0445;;;;N;;;;;
1E062;CYRILLIC SUBSCRIPT SMALL LETTER TSE;Lm;0;L;<sub> 0446;;;;N;;;;;
1E063;CYRILLIC SUBSCRIPT SMALL LETTER CHE;Lm;0;L;<sub> 0447;;;;N;;;;;
1E064;CYRILLIC SUBSCRIPT SMALL LETTER SHA;Lm;0;L;<sub> 0448;;;;N;;;;;
1E065;CYRILLIC SUBSCRIPT SMALL LETTER HARD SIGN;Lm;0;L;<sub> 044A;;;;N;;;;;
1E066;CYRILLIC SUBSCRIPT SMALL LETTER YERU;Lm;0;L;<sub> 044B;;;;N;;;;;
1E067;CYRILLIC SUBSCRIPT SMALL LETTER GHE WITH UPTURN;Lm;0;L;<sub> 0491;;;;N;;;;;
1E068;CYRILLIC SUBSCRIPT SMALL LETTER BYELORUSSIAN-UKRAINIAN I;Lm;0;L;<sub> 0456;;;;N;;;;;
1E069;CYRILLIC SUBSCRIPT SMALL LETTER DZE;Lm;0;L;<sub> 0455;;;;N;;;;;
1E06A;CYRILLIC SUBSCRIPT SMALL LETTER DZHE;Lm;0;L;<sub> 045F;;;;N;;;;;
1E06B;MODIFIER LETTER CYRILLIC SMALL ES WITH DESCENDER;Lm;0;L;<super> 04AB;;;;N;;;;;
1E06C;MODIFIER LETTER CYRILLIC SMALL YERU WITH BACK YER;Lm;0;L;<super> A651;;;;N;;;;;
1E06D;MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE;Lm;0;L;<super> 04B1;;;;N;;;;;
1E08F;COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I;Mn;230;NSM;;;;;N;;;;;
1E100;NYIAKENG PUACHUE HMONG LETTER MA;Lo;0;L;;;;;N;;;;;
1E101;NYIAKENG PUACHUE HMONG LETTER TSA;Lo;0;L;;;;;N;;;;;
1E102;NYIAKENG PUACHUE HMONG LETTER NTA;Lo;0;L;;;;;N;;;;;
@ -30603,6 +30828,48 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
1E2F8;WANCHO DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;;
1E2F9;WANCHO DIGIT NINE;Nd;0;L;;9;9;9;N;;;;;
1E2FF;WANCHO NGUN SIGN;Sc;0;ET;;;;;N;;;;;
1E4D0;NAG MUNDARI LETTER O;Lo;0;L;;;;;N;;;;;
1E4D1;NAG MUNDARI LETTER OP;Lo;0;L;;;;;N;;;;;
1E4D2;NAG MUNDARI LETTER OL;Lo;0;L;;;;;N;;;;;
1E4D3;NAG MUNDARI LETTER OY;Lo;0;L;;;;;N;;;;;
1E4D4;NAG MUNDARI LETTER ONG;Lo;0;L;;;;;N;;;;;
1E4D5;NAG MUNDARI LETTER A;Lo;0;L;;;;;N;;;;;
1E4D6;NAG MUNDARI LETTER AJ;Lo;0;L;;;;;N;;;;;
1E4D7;NAG MUNDARI LETTER AB;Lo;0;L;;;;;N;;;;;
1E4D8;NAG MUNDARI LETTER ANY;Lo;0;L;;;;;N;;;;;
1E4D9;NAG MUNDARI LETTER AH;Lo;0;L;;;;;N;;;;;
1E4DA;NAG MUNDARI LETTER I;Lo;0;L;;;;;N;;;;;
1E4DB;NAG MUNDARI LETTER IS;Lo;0;L;;;;;N;;;;;
1E4DC;NAG MUNDARI LETTER IDD;Lo;0;L;;;;;N;;;;;
1E4DD;NAG MUNDARI LETTER IT;Lo;0;L;;;;;N;;;;;
1E4DE;NAG MUNDARI LETTER IH;Lo;0;L;;;;;N;;;;;
1E4DF;NAG MUNDARI LETTER U;Lo;0;L;;;;;N;;;;;
1E4E0;NAG MUNDARI LETTER UC;Lo;0;L;;;;;N;;;;;
1E4E1;NAG MUNDARI LETTER UD;Lo;0;L;;;;;N;;;;;
1E4E2;NAG MUNDARI LETTER UK;Lo;0;L;;;;;N;;;;;
1E4E3;NAG MUNDARI LETTER UR;Lo;0;L;;;;;N;;;;;
1E4E4;NAG MUNDARI LETTER E;Lo;0;L;;;;;N;;;;;
1E4E5;NAG MUNDARI LETTER ENN;Lo;0;L;;;;;N;;;;;
1E4E6;NAG MUNDARI LETTER EG;Lo;0;L;;;;;N;;;;;
1E4E7;NAG MUNDARI LETTER EM;Lo;0;L;;;;;N;;;;;
1E4E8;NAG MUNDARI LETTER EN;Lo;0;L;;;;;N;;;;;
1E4E9;NAG MUNDARI LETTER ETT;Lo;0;L;;;;;N;;;;;
1E4EA;NAG MUNDARI LETTER ELL;Lo;0;L;;;;;N;;;;;
1E4EB;NAG MUNDARI SIGN OJOD;Lm;0;L;;;;;N;;;;;
1E4EC;NAG MUNDARI SIGN MUHOR;Mn;232;NSM;;;;;N;;;;;
1E4ED;NAG MUNDARI SIGN TOYOR;Mn;232;NSM;;;;;N;;;;;
1E4EE;NAG MUNDARI SIGN IKIR;Mn;220;NSM;;;;;N;;;;;
1E4EF;NAG MUNDARI SIGN SUTUH;Mn;230;NSM;;;;;N;;;;;
1E4F0;NAG MUNDARI DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;;
1E4F1;NAG MUNDARI DIGIT ONE;Nd;0;L;;1;1;1;N;;;;;
1E4F2;NAG MUNDARI DIGIT TWO;Nd;0;L;;2;2;2;N;;;;;
1E4F3;NAG MUNDARI DIGIT THREE;Nd;0;L;;3;3;3;N;;;;;
1E4F4;NAG MUNDARI DIGIT FOUR;Nd;0;L;;4;4;4;N;;;;;
1E4F5;NAG MUNDARI DIGIT FIVE;Nd;0;L;;5;5;5;N;;;;;
1E4F6;NAG MUNDARI DIGIT SIX;Nd;0;L;;6;6;6;N;;;;;
1E4F7;NAG MUNDARI DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;;
1E4F8;NAG MUNDARI DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;;
1E4F9;NAG MUNDARI DIGIT NINE;Nd;0;L;;9;9;9;N;;;;;
1E7E0;ETHIOPIC SYLLABLE HHYA;Lo;0;L;;;;;N;;;;;
1E7E1;ETHIOPIC SYLLABLE HHYU;Lo;0;L;;;;;N;;;;;
1E7E2;ETHIOPIC SYLLABLE HHYI;Lo;0;L;;;;;N;;;;;
@ -32678,6 +32945,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
1F6D5;HINDU TEMPLE;So;0;ON;;;;;N;;;;;
1F6D6;HUT;So;0;ON;;;;;N;;;;;
1F6D7;ELEVATOR;So;0;ON;;;;;N;;;;;
1F6DC;WIRELESS;So;0;ON;;;;;N;;;;;
1F6DD;PLAYGROUND SLIDE;So;0;ON;;;;;N;;;;;
1F6DE;WHEEL;So;0;ON;;;;;N;;;;;
1F6DF;RING BUOY;So;0;ON;;;;;N;;;;;
@ -32823,6 +33091,14 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
1F771;ALCHEMICAL SYMBOL FOR MONTH;So;0;ON;;;;;N;;;;;
1F772;ALCHEMICAL SYMBOL FOR HALF DRAM;So;0;ON;;;;;N;;;;;
1F773;ALCHEMICAL SYMBOL FOR HALF OUNCE;So;0;ON;;;;;N;;;;;
1F774;LOT OF FORTUNE;So;0;ON;;;;;N;;;;;
1F775;OCCULTATION;So;0;ON;;;;;N;;;;;
1F776;LUNAR ECLIPSE;So;0;ON;;;;;N;;;;;
1F77B;HAUMEA;So;0;ON;;;;;N;;;;;
1F77C;MAKEMAKE;So;0;ON;;;;;N;;;;;
1F77D;GONGGONG;So;0;ON;;;;;N;;;;;
1F77E;QUAOAR;So;0;ON;;;;;N;;;;;
1F77F;ORCUS;So;0;ON;;;;;N;;;;;
1F780;BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE;So;0;ON;;;;;N;;;;;
1F781;BLACK UP-POINTING ISOSCELES RIGHT TRIANGLE;So;0;ON;;;;;N;;;;;
1F782;BLACK RIGHT-POINTING ISOSCELES RIGHT TRIANGLE;So;0;ON;;;;;N;;;;;
@ -32912,6 +33188,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
1F7D6;NEGATIVE CIRCLED TRIANGLE;So;0;ON;;;;;N;;;;;
1F7D7;CIRCLED SQUARE;So;0;ON;;;;;N;;;;;
1F7D8;NEGATIVE CIRCLED SQUARE;So;0;ON;;;;;N;;;;;
1F7D9;NINE POINTED WHITE STAR;So;0;ON;;;;;N;;;;;
1F7E0;LARGE ORANGE CIRCLE;So;0;ON;;;;;N;;;;;
1F7E1;LARGE YELLOW CIRCLE;So;0;ON;;;;;N;;;;;
1F7E2;LARGE GREEN CIRCLE;So;0;ON;;;;;N;;;;;
@ -33434,6 +33711,9 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
1FA72;BRIEFS;So;0;ON;;;;;N;;;;;
1FA73;SHORTS;So;0;ON;;;;;N;;;;;
1FA74;THONG SANDAL;So;0;ON;;;;;N;;;;;
1FA75;LIGHT BLUE HEART;So;0;ON;;;;;N;;;;;
1FA76;GREY HEART;So;0;ON;;;;;N;;;;;
1FA77;PINK HEART;So;0;ON;;;;;N;;;;;
1FA78;DROP OF BLOOD;So;0;ON;;;;;N;;;;;
1FA79;ADHESIVE BANDAGE;So;0;ON;;;;;N;;;;;
1FA7A;STETHOSCOPE;So;0;ON;;;;;N;;;;;
@ -33446,6 +33726,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
1FA84;MAGIC WAND;So;0;ON;;;;;N;;;;;
1FA85;PINATA;So;0;ON;;;;;N;;;;;
1FA86;NESTING DOLLS;So;0;ON;;;;;N;;;;;
1FA87;MARACAS;So;0;ON;;;;;N;;;;;
1FA88;FLUTE;So;0;ON;;;;;N;;;;;
1FA90;RINGED PLANET;So;0;ON;;;;;N;;;;;
1FA91;CHAIR;So;0;ON;;;;;N;;;;;
1FA92;RAZOR;So;0;ON;;;;;N;;;;;
@ -33475,6 +33757,9 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
1FAAA;IDENTIFICATION CARD;So;0;ON;;;;;N;;;;;
1FAAB;LOW BATTERY;So;0;ON;;;;;N;;;;;
1FAAC;HAMSA;So;0;ON;;;;;N;;;;;
1FAAD;FOLDING HAND FAN;So;0;ON;;;;;N;;;;;
1FAAE;HAIR PICK;So;0;ON;;;;;N;;;;;
1FAAF;KHANDA;So;0;ON;;;;;N;;;;;
1FAB0;FLY;So;0;ON;;;;;N;;;;;
1FAB1;WORM;So;0;ON;;;;;N;;;;;
1FAB2;BEETLE;So;0;ON;;;;;N;;;;;
@ -33486,12 +33771,18 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
1FAB8;CORAL;So;0;ON;;;;;N;;;;;
1FAB9;EMPTY NEST;So;0;ON;;;;;N;;;;;
1FABA;NEST WITH EGGS;So;0;ON;;;;;N;;;;;
1FABB;HYACINTH;So;0;ON;;;;;N;;;;;
1FABC;JELLYFISH;So;0;ON;;;;;N;;;;;
1FABD;WING;So;0;ON;;;;;N;;;;;
1FABF;GOOSE;So;0;ON;;;;;N;;;;;
1FAC0;ANATOMICAL HEART;So;0;ON;;;;;N;;;;;
1FAC1;LUNGS;So;0;ON;;;;;N;;;;;
1FAC2;PEOPLE HUGGING;So;0;ON;;;;;N;;;;;
1FAC3;PREGNANT MAN;So;0;ON;;;;;N;;;;;
1FAC4;PREGNANT PERSON;So;0;ON;;;;;N;;;;;
1FAC5;PERSON WITH CROWN;So;0;ON;;;;;N;;;;;
1FACE;MOOSE;So;0;ON;;;;;N;;;;;
1FACF;DONKEY;So;0;ON;;;;;N;;;;;
1FAD0;BLUEBERRIES;So;0;ON;;;;;N;;;;;
1FAD1;BELL PEPPER;So;0;ON;;;;;N;;;;;
1FAD2;OLIVE;So;0;ON;;;;;N;;;;;
@ -33502,6 +33793,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
1FAD7;POURING LIQUID;So;0;ON;;;;;N;;;;;
1FAD8;BEANS;So;0;ON;;;;;N;;;;;
1FAD9;JAR;So;0;ON;;;;;N;;;;;
1FADA;GINGER ROOT;So;0;ON;;;;;N;;;;;
1FADB;PEA POD;So;0;ON;;;;;N;;;;;
1FAE0;MELTING FACE;So;0;ON;;;;;N;;;;;
1FAE1;SALUTING FACE;So;0;ON;;;;;N;;;;;
1FAE2;FACE WITH OPEN EYES AND HAND OVER MOUTH;So;0;ON;;;;;N;;;;;
@ -33510,6 +33803,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
1FAE5;DOTTED LINE FACE;So;0;ON;;;;;N;;;;;
1FAE6;BITING LIP;So;0;ON;;;;;N;;;;;
1FAE7;BUBBLES;So;0;ON;;;;;N;;;;;
1FAE8;SHAKING FACE;So;0;ON;;;;;N;;;;;
1FAF0;HAND WITH INDEX FINGER AND THUMB CROSSED;So;0;ON;;;;;N;;;;;
1FAF1;RIGHTWARDS HAND;So;0;ON;;;;;N;;;;;
1FAF2;LEFTWARDS HAND;So;0;ON;;;;;N;;;;;
@ -33517,6 +33811,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
1FAF4;PALM UP HAND;So;0;ON;;;;;N;;;;;
1FAF5;INDEX POINTING AT THE VIEWER;So;0;ON;;;;;N;;;;;
1FAF6;HEART HANDS;So;0;ON;;;;;N;;;;;
1FAF7;LEFTWARDS PUSHING HAND;So;0;ON;;;;;N;;;;;
1FAF8;RIGHTWARDS PUSHING HAND;So;0;ON;;;;;N;;;;;
1FB00;BLOCK SEXTANT-1;So;0;ON;;;;;N;;;;;
1FB01;BLOCK SEXTANT-2;So;0;ON;;;;;N;;;;;
1FB02;BLOCK SEXTANT-12;So;0;ON;;;;;N;;;;;
@ -33732,7 +34028,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
20000;<CJK Ideograph Extension B, First>;Lo;0;L;;;;;N;;;;;
2A6DF;<CJK Ideograph Extension B, Last>;Lo;0;L;;;;;N;;;;;
2A700;<CJK Ideograph Extension C, First>;Lo;0;L;;;;;N;;;;;
2B738;<CJK Ideograph Extension C, Last>;Lo;0;L;;;;;N;;;;;
2B739;<CJK Ideograph Extension C, Last>;Lo;0;L;;;;;N;;;;;
2B740;<CJK Ideograph Extension D, First>;Lo;0;L;;;;;N;;;;;
2B81D;<CJK Ideograph Extension D, Last>;Lo;0;L;;;;;N;;;;;
2B820;<CJK Ideograph Extension E, First>;Lo;0;L;;;;;N;;;;;
@ -34283,6 +34579,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
2FA1D;CJK COMPATIBILITY IDEOGRAPH-2FA1D;Lo;0;L;2A600;;;;N;;;;;
30000;<CJK Ideograph Extension G, First>;Lo;0;L;;;;;N;;;;;
3134A;<CJK Ideograph Extension G, Last>;Lo;0;L;;;;;N;;;;;
31350;<CJK Ideograph Extension H, First>;Lo;0;L;;;;;N;;;;;
323AF;<CJK Ideograph Extension H, Last>;Lo;0;L;;;;;N;;;;;
E0001;LANGUAGE TAG;Cf;0;BN;;;;;N;;;;;
E0020;TAG SPACE;Cf;0;BN;;;;;N;;;;;
E0021;TAG EXCLAMATION MARK;Cf;0;BN;;;;;N;;;;;

53
util/unicode/data/WordBreakProperty.txt
View File

@ -1,11 +1,11 @@
# WordBreakProperty-14.0.0.txt
# Date: 2021-07-10, 00:35:32 GMT
# © 2021 Unicode®, Inc.
# WordBreakProperty-15.0.0.txt
# Date: 2022-04-27, 02:41:26 GMT
# © 2022 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
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see https://www.unicode.org/reports/tr44/
# ================================================
@ -180,6 +180,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW
0CCC..0CCD ; Extend # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA
0CD5..0CD6 ; Extend # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK
0CE2..0CE3 ; Extend # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
0CF3 ; Extend # Mc KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
0D00..0D01 ; Extend # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
0D02..0D03 ; Extend # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
0D3B..0D3C ; Extend # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
@ -203,7 +204,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW
0E47..0E4E ; Extend # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN
0EB1 ; Extend # Mn LAO VOWEL SIGN MAI KAN
0EB4..0EBC ; Extend # Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO
0EC8..0ECD ; Extend # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA
0EC8..0ECE ; Extend # Mn [7] LAO TONE MAI EK..LAO YAMAKKAN
0F18..0F19 ; Extend # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS
0F35 ; Extend # Mn TIBETAN MARK NGAS BZUNG NYI ZLA
0F37 ; Extend # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS
@ -407,6 +408,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
10AE5..10AE6 ; Extend # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW
10D24..10D27 ; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
10EAB..10EAC ; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK
10EFD..10EFF ; Extend # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA
10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW
10F82..10F85 ; Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW
11000 ; Extend # Mc BRAHMI SIGN CANDRABINDU
@ -443,6 +445,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
11235 ; Extend # Mc KHOJKI SIGN VIRAMA
11236..11237 ; Extend # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
1123E ; Extend # Mn KHOJKI SIGN SUKUN
11241 ; Extend # Mn KHOJKI VOWEL SIGN VOCALIC R
112DF ; Extend # Mn KHUDAWADI SIGN ANUSVARA
112E0..112E2 ; Extend # Mc [3] KHUDAWADI VOWEL SIGN AA..KHUDAWADI VOWEL SIGN II
112E3..112EA ; Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
@ -552,6 +555,16 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
11D97 ; Extend # Mn GUNJALA GONDI VIRAMA
11EF3..11EF4 ; Extend # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
11EF5..11EF6 ; Extend # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
11F00..11F01 ; Extend # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA
11F03 ; Extend # Mc KAWI SIGN VISARGA
11F34..11F35 ; Extend # Mc [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA
11F36..11F3A ; Extend # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R
11F3E..11F3F ; Extend # Mc [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI
11F40 ; Extend # Mn KAWI VOWEL SIGN EU
11F41 ; Extend # Mc KAWI SIGN KILLER
11F42 ; Extend # Mn KAWI CONJOINER
13440 ; Extend # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY
13447..13455 ; Extend # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED
16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
16F4F ; Extend # Mn MIAO SIGN CONSONANT MODIFIER BAR
@ -580,16 +593,18 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
1E01B..1E021 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
1E023..1E024 ; Extend # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
1E026..1E02A ; Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
1E08F ; Extend # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
1E130..1E136 ; Extend # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
1E2AE ; Extend # Mn TOTO SIGN RISING TONE
1E2EC..1E2EF ; Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI
1E4EC..1E4EF ; Extend # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH
1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA
1F3FB..1F3FF ; Extend # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG
E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# Total code points: 2512
# Total code points: 2554
# ================================================
@ -615,12 +630,12 @@ FEFF ; Format # Cf ZERO WIDTH NO-BREAK SPACE
FFF9..FFFB ; Format # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR
110BD ; Format # Cf KAITHI NUMBER SIGN
110CD ; Format # Cf KAITHI NUMBER SIGN ABOVE
13430..13438 ; Format # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT
13430..1343F ; Format # Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE
1BCA0..1BCA3 ; Format # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
1D173..1D17A ; Format # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
E0001 ; Format # Cf LANGUAGE TAG
# Total code points: 64
# Total code points: 71
# ================================================
@ -641,9 +656,10 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
1AFFD..1AFFE ; Katakana # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
1B000 ; Katakana # Lo KATAKANA LETTER ARCHAIC E
1B120..1B122 ; Katakana # Lo [3] KATAKANA LETTER ARCHAIC YI..KATAKANA LETTER ARCHAIC WU
1B155 ; Katakana # Lo KATAKANA LETTER SMALL KO
1B164..1B167 ; Katakana # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N
# Total code points: 330
# Total code points: 331
# ================================================
@ -1127,6 +1143,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
111DC ; ALetter # Lo SHARADA HEADSTROKE
11200..11211 ; ALetter # Lo [18] KHOJKI LETTER A..KHOJKI LETTER JJA
11213..1122B ; ALetter # Lo [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA
1123F..11240 ; ALetter # Lo [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I
11280..11286 ; ALetter # Lo [7] MULTANI LETTER A..MULTANI LETTER GA
11288 ; ALetter # Lo MULTANI LETTER GHA
1128A..1128D ; ALetter # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA
@ -1187,12 +1204,16 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
11D6A..11D89 ; ALetter # Lo [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA
11D98 ; ALetter # Lo GUNJALA GONDI OM
11EE0..11EF2 ; ALetter # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA
11F02 ; ALetter # Lo KAWI SIGN REPHA
11F04..11F10 ; ALetter # Lo [13] KAWI LETTER A..KAWI LETTER O
11F12..11F33 ; ALetter # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA
11FB0 ; ALetter # Lo LISU LETTER YHA
12000..12399 ; ALetter # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
12400..1246E ; ALetter # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
12480..12543 ; ALetter # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
12F90..12FF0 ; ALetter # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114
13000..1342E ; ALetter # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
13000..1342F ; ALetter # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D
13441..13446 ; ALetter # Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN
14400..14646 ; ALetter # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530
16800..16A38 ; ALetter # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ
16A40..16A5E ; ALetter # Lo [31] MRO LETTER TA..MRO LETTER TEK
@ -1245,11 +1266,15 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
1DF00..1DF09 ; ALetter # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK
1DF0A ; ALetter # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK
1DF0B..1DF1E ; ALetter # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL
1DF25..1DF2A ; ALetter # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
1E030..1E06D ; ALetter # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
1E100..1E12C ; ALetter # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W
1E137..1E13D ; ALetter # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER
1E14E ; ALetter # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ
1E290..1E2AD ; ALetter # Lo [30] TOTO LETTER PA..TOTO LETTER A
1E2C0..1E2EB ; ALetter # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH
1E4D0..1E4EA ; ALetter # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL
1E4EB ; ALetter # Lm NAG MUNDARI SIGN OJOD
1E7E0..1E7E6 ; ALetter # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO
1E7E8..1E7EB ; ALetter # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE
1E7ED..1E7EE ; ALetter # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE
@ -1294,7 +1319,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z
# Total code points: 29336
# Total code points: 29489
# ================================================
@ -1398,16 +1423,18 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE
11C50..11C59 ; Numeric # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE
11D50..11D59 ; Numeric # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE
11DA0..11DA9 ; Numeric # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE
11F50..11F59 ; Numeric # Nd [10] KAWI DIGIT ZERO..KAWI DIGIT NINE
16A60..16A69 ; Numeric # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE
16AC0..16AC9 ; Numeric # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE
16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE
1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
1E140..1E149 ; Numeric # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE
1E2F0..1E2F9 ; Numeric # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE
1E4F0..1E4F9 ; Numeric # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE
1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE
1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE
# Total code points: 661
# Total code points: 681
# ================================================

85
util/unicode/data/emoji-data.txt
View File

@ -1,13 +1,13 @@
# emoji-data-14.0.0.txt
# Date: 2021-08-26, 17:22:22 GMT
# © 2021 Unicode®, Inc.
# emoji-data.txt
# Date: 2022-08-02, 00:26:10 GMT
# © 2022 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
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Emoji Data for UTS #51
# Used with Emoji Version 14.0 and subsequent minor revisions (if any)
# Used with Emoji Version 15.0 and subsequent minor revisions (if any)
#
# For documentation and usage, see http://www.unicode.org/reports/tr51
# For documentation and usage, see https://www.unicode.org/reports/tr51
#
# Format:
# <codepoint(s)> ; <property> # <comments>
@ -19,8 +19,7 @@
# ================================================
# All omitted code points have Emoji=No
# @missing: 0000..10FFFF ; Emoji ; No
# All omitted code points have Emoji=No
0023 ; Emoji # E0.0 [1] (#️) hash sign
002A ; Emoji # E0.0 [1] (*️) asterisk
@ -341,6 +340,7 @@
1F6D1..1F6D2 ; Emoji # E3.0 [2] (🛑..🛒) stop sign..shopping cart
1F6D5 ; Emoji # E12.0 [1] (🛕) hindu temple
1F6D6..1F6D7 ; Emoji # E13.0 [2] (🛖..🛗) hut..elevator
1F6DC ; Emoji # E15.0 [1] (🛜) wireless
1F6DD..1F6DF ; Emoji # E14.0 [3] (🛝..🛟) playground slide..ring buoy
1F6E0..1F6E5 ; Emoji # E0.7 [6] (🛠️..🛥️) hammer and wrench..motor boat
1F6E9 ; Emoji # E0.7 [1] (🛩️) small airplane
@ -401,28 +401,36 @@
1F9E7..1F9FF ; Emoji # E11.0 [25] (🧧..🧿) red envelope..nazar amulet
1FA70..1FA73 ; Emoji # E12.0 [4] (🩰..🩳) ballet shoes..shorts
1FA74 ; Emoji # E13.0 [1] (🩴) thong sandal
1FA75..1FA77 ; Emoji # E15.0 [3] (🩵..🩷) light blue heart..pink heart
1FA78..1FA7A ; Emoji # E12.0 [3] (🩸..🩺) drop of blood..stethoscope
1FA7B..1FA7C ; Emoji # E14.0 [2] (🩻..🩼) x-ray..crutch
1FA80..1FA82 ; Emoji # E12.0 [3] (🪀..🪂) yo-yo..parachute
1FA83..1FA86 ; Emoji # E13.0 [4] (🪃..🪆) boomerang..nesting dolls
1FA87..1FA88 ; Emoji # E15.0 [2] (🪇..🪈) maracas..flute
1FA90..1FA95 ; Emoji # E12.0 [6] (🪐..🪕) ringed planet..banjo
1FA96..1FAA8 ; Emoji # E13.0 [19] (🪖..🪨) military helmet..rock
1FAA9..1FAAC ; Emoji # E14.0 [4] (🪩..🪬) mirror ball..hamsa
1FAAD..1FAAF ; Emoji # E15.0 [3] (🪭..🪯) folding hand fan..khanda
1FAB0..1FAB6 ; Emoji # E13.0 [7] (🪰..🪶) fly..feather
1FAB7..1FABA ; Emoji # E14.0 [4] (🪷..🪺) lotus..nest with eggs
1FABB..1FABD ; Emoji # E15.0 [3] (🪻..🪽) hyacinth..wing
1FABF ; Emoji # E15.0 [1] (🪿) goose
1FAC0..1FAC2 ; Emoji # E13.0 [3] (🫀..🫂) anatomical heart..people hugging
1FAC3..1FAC5 ; Emoji # E14.0 [3] (🫃..🫅) pregnant man..person with crown
1FACE..1FACF ; Emoji # E15.0 [2] (🫎..🫏) moose..donkey
1FAD0..1FAD6 ; Emoji # E13.0 [7] (🫐..🫖) blueberries..teapot
1FAD7..1FAD9 ; Emoji # E14.0 [3] (🫗..🫙) pouring liquid..jar
1FADA..1FADB ; Emoji # E15.0 [2] (🫚..🫛) ginger root..pea pod
1FAE0..1FAE7 ; Emoji # E14.0 [8] (🫠..🫧) melting face..bubbles
1FAE8 ; Emoji # E15.0 [1] (🫨) shaking face
1FAF0..1FAF6 ; Emoji # E14.0 [7] (🫰..🫶) hand with index finger and thumb crossed..heart hands
1FAF7..1FAF8 ; Emoji # E15.0 [2] (🫷..🫸) leftwards pushing hand..rightwards pushing hand
# Total elements: 1404
# Total elements: 1424
# ================================================
# All omitted code points have Emoji_Presentation=No
# @missing: 0000..10FFFF ; Emoji_Presentation ; No
# All omitted code points have Emoji_Presentation=No
231A..231B ; Emoji_Presentation # E0.6 [2] (⌚..⌛) watch..hourglass done
23E9..23EC ; Emoji_Presentation # E0.6 [4] (⏩..⏬) fast-forward button..fast down button
@ -625,6 +633,7 @@
1F6D1..1F6D2 ; Emoji_Presentation # E3.0 [2] (🛑..🛒) stop sign..shopping cart
1F6D5 ; Emoji_Presentation # E12.0 [1] (🛕) hindu temple
1F6D6..1F6D7 ; Emoji_Presentation # E13.0 [2] (🛖..🛗) hut..elevator
1F6DC ; Emoji_Presentation # E15.0 [1] (🛜) wireless
1F6DD..1F6DF ; Emoji_Presentation # E14.0 [3] (🛝..🛟) playground slide..ring buoy
1F6EB..1F6EC ; Emoji_Presentation # E1.0 [2] (🛫..🛬) airplane departure..airplane arrival
1F6F4..1F6F6 ; Emoji_Presentation # E3.0 [3] (🛴..🛶) kick scooter..canoe
@ -681,28 +690,36 @@
1F9E7..1F9FF ; Emoji_Presentation # E11.0 [25] (🧧..🧿) red envelope..nazar amulet
1FA70..1FA73 ; Emoji_Presentation # E12.0 [4] (🩰..🩳) ballet shoes..shorts
1FA74 ; Emoji_Presentation # E13.0 [1] (🩴) thong sandal
1FA75..1FA77 ; Emoji_Presentation # E15.0 [3] (🩵..🩷) light blue heart..pink heart
1FA78..1FA7A ; Emoji_Presentation # E12.0 [3] (🩸..🩺) drop of blood..stethoscope
1FA7B..1FA7C ; Emoji_Presentation # E14.0 [2] (🩻..🩼) x-ray..crutch
1FA80..1FA82 ; Emoji_Presentation # E12.0 [3] (🪀..🪂) yo-yo..parachute
1FA83..1FA86 ; Emoji_Presentation # E13.0 [4] (🪃..🪆) boomerang..nesting dolls
1FA87..1FA88 ; Emoji_Presentation # E15.0 [2] (🪇..🪈) maracas..flute
1FA90..1FA95 ; Emoji_Presentation # E12.0 [6] (🪐..🪕) ringed planet..banjo
1FA96..1FAA8 ; Emoji_Presentation # E13.0 [19] (🪖..🪨) military helmet..rock
1FAA9..1FAAC ; Emoji_Presentation # E14.0 [4] (🪩..🪬) mirror ball..hamsa
1FAAD..1FAAF ; Emoji_Presentation # E15.0 [3] (🪭..🪯) folding hand fan..khanda
1FAB0..1FAB6 ; Emoji_Presentation # E13.0 [7] (🪰..🪶) fly..feather
1FAB7..1FABA ; Emoji_Presentation # E14.0 [4] (🪷..🪺) lotus..nest with eggs
1FABB..1FABD ; Emoji_Presentation # E15.0 [3] (🪻..🪽) hyacinth..wing
1FABF ; Emoji_Presentation # E15.0 [1] (🪿) goose
1FAC0..1FAC2 ; Emoji_Presentation # E13.0 [3] (🫀..🫂) anatomical heart..people hugging
1FAC3..1FAC5 ; Emoji_Presentation # E14.0 [3] (🫃..🫅) pregnant man..person with crown
1FACE..1FACF ; Emoji_Presentation # E15.0 [2] (🫎..🫏) moose..donkey
1FAD0..1FAD6 ; Emoji_Presentation # E13.0 [7] (🫐..🫖) blueberries..teapot
1FAD7..1FAD9 ; Emoji_Presentation # E14.0 [3] (🫗..🫙) pouring liquid..jar
1FADA..1FADB ; Emoji_Presentation # E15.0 [2] (🫚..🫛) ginger root..pea pod
1FAE0..1FAE7 ; Emoji_Presentation # E14.0 [8] (🫠..🫧) melting face..bubbles
1FAE8 ; Emoji_Presentation # E15.0 [1] (🫨) shaking face
1FAF0..1FAF6 ; Emoji_Presentation # E14.0 [7] (🫰..🫶) hand with index finger and thumb crossed..heart hands
1FAF7..1FAF8 ; Emoji_Presentation # E15.0 [2] (🫷..🫸) leftwards pushing hand..rightwards pushing hand
# Total elements: 1185
# Total elements: 1205
# ================================================
# All omitted code points have Emoji_Modifier=No
# @missing: 0000..10FFFF ; Emoji_Modifier ; No
# All omitted code points have Emoji_Modifier=No
1F3FB..1F3FF ; Emoji_Modifier # E1.0 [5] (🏻..🏿) light skin tone..dark skin tone
@ -710,8 +727,7 @@
# ================================================
# All omitted code points have Emoji_Modifier_Base=No
# @missing: 0000..10FFFF ; Emoji_Modifier_Base ; No
# All omitted code points have Emoji_Modifier_Base=No
261D ; Emoji_Modifier_Base # E0.6 [1] (☝️) index pointing up
26F9 ; Emoji_Modifier_Base # E0.7 [1] (⛹️) person bouncing ball
@ -762,13 +778,13 @@
1F9D1..1F9DD ; Emoji_Modifier_Base # E5.0 [13] (🧑..🧝) person..elf
1FAC3..1FAC5 ; Emoji_Modifier_Base # E14.0 [3] (🫃..🫅) pregnant man..person with crown
1FAF0..1FAF6 ; Emoji_Modifier_Base # E14.0 [7] (🫰..🫶) hand with index finger and thumb crossed..heart hands
1FAF7..1FAF8 ; Emoji_Modifier_Base # E15.0 [2] (🫷..🫸) leftwards pushing hand..rightwards pushing hand
# Total elements: 132
# Total elements: 134
# ================================================
# All omitted code points have Emoji_Component=No
# @missing: 0000..10FFFF ; Emoji_Component ; No
# All omitted code points have Emoji_Component=No
0023 ; Emoji_Component # E0.0 [1] (#️) hash sign
002A ; Emoji_Component # E0.0 [1] (*️) asterisk
@ -785,8 +801,7 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c
# ================================================
# All omitted code points have Extended_Pictographic=No
# @missing: 0000..10FFFF ; Extended_Pictographic ; No
# All omitted code points have Extended_Pictographic=No
00A9 ; Extended_Pictographic# E0.6 [1] (©️) copyright
00AE ; Extended_Pictographic# E0.6 [1] (®️) registered
@ -1190,7 +1205,8 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c
1F6D3..1F6D4 ; Extended_Pictographic# E0.0 [2] (🛓..🛔) STUPA..PAGODA
1F6D5 ; Extended_Pictographic# E12.0 [1] (🛕) hindu temple
1F6D6..1F6D7 ; Extended_Pictographic# E13.0 [2] (🛖..🛗) hut..elevator
1F6D8..1F6DC ; Extended_Pictographic# E0.0 [5] (🛘..🛜) <reserved-1F6D8>..<reserved-1F6DC>
1F6D8..1F6DB ; Extended_Pictographic# E0.0 [4] (🛘..🛛) <reserved-1F6D8>..<reserved-1F6DB>
1F6DC ; Extended_Pictographic# E15.0 [1] (🛜) wireless
1F6DD..1F6DF ; Extended_Pictographic# E14.0 [3] (🛝..🛟) playground slide..ring buoy
1F6E0..1F6E5 ; Extended_Pictographic# E0.7 [6] (🛠️..🛥️) hammer and wrench..motor boat
1F6E6..1F6E8 ; Extended_Pictographic# E0.0 [3] (🛦..🛨) UP-POINTING MILITARY AIRPLANE..UP-POINTING SMALL AIRPLANE
@ -1207,7 +1223,7 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c
1F6FA ; Extended_Pictographic# E12.0 [1] (🛺) auto rickshaw
1F6FB..1F6FC ; Extended_Pictographic# E13.0 [2] (🛻..🛼) pickup truck..roller skate
1F6FD..1F6FF ; Extended_Pictographic# E0.0 [3] (🛽..🛿) <reserved-1F6FD>..<reserved-1F6FF>
1F774..1F77F ; Extended_Pictographic# E0.0 [12] (🝴..🝿) <reserved-1F774>..<reserved-1F77F>
1F774..1F77F ; Extended_Pictographic# E0.0 [12] (🝴..🝿) LOT OF FORTUNE..ORCUS
1F7D5..1F7DF ; Extended_Pictographic# E0.0 [11] (🟕..🟟) CIRCLED TRIANGLE..<reserved-1F7DF>
1F7E0..1F7EB ; Extended_Pictographic# E12.0 [12] (🟠..🟫) orange circle..brown square
1F7EC..1F7EF ; Extended_Pictographic# E0.0 [4] (🟬..🟯) <reserved-1F7EC>..<reserved-1F7EF>
@ -1266,30 +1282,37 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c
1FA00..1FA6F ; Extended_Pictographic# E0.0 [112] (🨀..🩯) NEUTRAL CHESS KING..<reserved-1FA6F>
1FA70..1FA73 ; Extended_Pictographic# E12.0 [4] (🩰..🩳) ballet shoes..shorts
1FA74 ; Extended_Pictographic# E13.0 [1] (🩴) thong sandal
1FA75..1FA77 ; Extended_Pictographic# E0.0 [3] (🩵..🩷) <reserved-1FA75>..<reserved-1FA77>
1FA75..1FA77 ; Extended_Pictographic# E15.0 [3] (🩵..🩷) light blue heart..pink heart
1FA78..1FA7A ; Extended_Pictographic# E12.0 [3] (🩸..🩺) drop of blood..stethoscope
1FA7B..1FA7C ; Extended_Pictographic# E14.0 [2] (🩻..🩼) x-ray..crutch
1FA7D..1FA7F ; Extended_Pictographic# E0.0 [3] (🩽..🩿) <reserved-1FA7D>..<reserved-1FA7F>
1FA80..1FA82 ; Extended_Pictographic# E12.0 [3] (🪀..🪂) yo-yo..parachute
1FA83..1FA86 ; Extended_Pictographic# E13.0 [4] (🪃..🪆) boomerang..nesting dolls
1FA87..1FA8F ; Extended_Pictographic# E0.0 [9] (🪇..🪏) <reserved-1FA87>..<reserved-1FA8F>
1FA87..1FA88 ; Extended_Pictographic# E15.0 [2] (🪇..🪈) maracas..flute
1FA89..1FA8F ; Extended_Pictographic# E0.0 [7] (🪉..🪏) <reserved-1FA89>..<reserved-1FA8F>
1FA90..1FA95 ; Extended_Pictographic# E12.0 [6] (🪐..🪕) ringed planet..banjo
1FA96..1FAA8 ; Extended_Pictographic# E13.0 [19] (🪖..🪨) military helmet..rock
1FAA9..1FAAC ; Extended_Pictographic# E14.0 [4] (🪩..🪬) mirror ball..hamsa
1FAAD..1FAAF ; Extended_Pictographic# E0.0 [3] (🪭..🪯) <reserved-1FAAD>..<reserved-1FAAF>
1FAAD..1FAAF ; Extended_Pictographic# E15.0 [3] (🪭..🪯) folding hand fan..khanda
1FAB0..1FAB6 ; Extended_Pictographic# E13.0 [7] (🪰..🪶) fly..feather
1FAB7..1FABA ; Extended_Pictographic# E14.0 [4] (🪷..🪺) lotus..nest with eggs
1FABB..1FABF ; Extended_Pictographic# E0.0 [5] (🪻..🪿) <reserved-1FABB>..<reserved-1FABF>
1FABB..1FABD ; Extended_Pictographic# E15.0 [3] (🪻..🪽) hyacinth..wing
1FABE ; Extended_Pictographic# E0.0 [1] (🪾) <reserved-1FABE>
1FABF ; Extended_Pictographic# E15.0 [1] (🪿) goose
1FAC0..1FAC2 ; Extended_Pictographic# E13.0 [3] (🫀..🫂) anatomical heart..people hugging
1FAC3..1FAC5 ; Extended_Pictographic# E14.0 [3] (🫃..🫅) pregnant man..person with crown
1FAC6..1FACF ; Extended_Pictographic# E0.0 [10] (🫆..🫏) <reserved-1FAC6>..<reserved-1FACF>
1FAC6..1FACD ; Extended_Pictographic# E0.0 [8] (🫆..🫍) <reserved-1FAC6>..<reserved-1FACD>
1FACE..1FACF ; Extended_Pictographic# E15.0 [2] (🫎..🫏) moose..donkey
1FAD0..1FAD6 ; Extended_Pictographic# E13.0 [7] (🫐..🫖) blueberries..teapot
1FAD7..1FAD9 ; Extended_Pictographic# E14.0 [3] (🫗..🫙) pouring liquid..jar
1FADA..1FADF ; Extended_Pictographic# E0.0 [6] (🫚..🫟) <reserved-1FADA>..<reserved-1FADF>
1FADA..1FADB ; Extended_Pictographic# E15.0 [2] (🫚..🫛) ginger root..pea pod
1FADC..1FADF ; Extended_Pictographic# E0.0 [4] (🫜..🫟) <reserved-1FADC>..<reserved-1FADF>
1FAE0..1FAE7 ; Extended_Pictographic# E14.0 [8] (🫠..🫧) melting face..bubbles
1FAE8..1FAEF ; Extended_Pictographic# E0.0 [8] (🫨..🫯) <reserved-1FAE8>..<reserved-1FAEF>
1FAE8 ; Extended_Pictographic# E15.0 [1] (🫨) shaking face
1FAE9..1FAEF ; Extended_Pictographic# E0.0 [7] (🫩..🫯) <reserved-1FAE9>..<reserved-1FAEF>
1FAF0..1FAF6 ; Extended_Pictographic# E14.0 [7] (🫰..🫶) hand with index finger and thumb crossed..heart hands
1FAF7..1FAFF ; Extended_Pictographic# E0.0 [9] (🫷..🫿) <reserved-1FAF7>..<reserved-1FAFF>
1FAF7..1FAF8 ; Extended_Pictographic# E15.0 [2] (🫷..🫸) leftwards pushing hand..rightwards pushing hand
1FAF9..1FAFF ; Extended_Pictographic# E0.0 [7] (🫹..🫿) <reserved-1FAF9>..<reserved-1FAFF>
1FC00..1FFFD ; Extended_Pictographic# E0.0[1022] (🰀..🿽) <reserved-1FC00>..<reserved-1FFFD>
# Total elements: 3537

5
util/unicode/main.cpp
View File

@ -50,6 +50,7 @@ static void initAgeMap()
{ QChar::Unicode_12_1, "12.1" }, // UCD Revision 24
{ QChar::Unicode_13_0, "13.0" }, // UCD Revision 26
{ QChar::Unicode_14_0, "14.0" }, // UCD Revision 28
{ QChar::Unicode_15_0, "15.0" }, // UCD Revision 30
{ QChar::Unicode_Unassigned, 0 }
};
AgeMap *d = ageMap;
@ -809,6 +810,10 @@ static void initScriptMap()
{ QChar::Script_Toto, "Toto"},
{ QChar::Script_Vithkuqi, "Vithkuqi"},
// 15.0
{ QChar::Script_Kawi, "Kawi"},
{ QChar::Script_NagMundari, "NagMundari"},
// unhandled
{ QChar::Script_Unknown, 0 }
};