summaryrefslogtreecommitdiffstats
path: root/util/unicode/data/WordBreakProperty.txt
diff options
context:
space:
mode:
authorKonstantin Ritt <ritt.ks@gmail.com>2012-05-25 03:20:48 +0300
committerQt by Nokia <qt-info@nokia.com>2012-06-10 15:57:54 +0200
commitc9100bcce7229fb115caf8531de6d89eaeb00706 (patch)
tree49eb6d781e2a7cf327e65c0f330430fb6c001d20 /util/unicode/data/WordBreakProperty.txt
parent60e1892d836c40955b9939cf74d79e6c0b997c9f (diff)
Update the Unicode data files up to v6.1.0
Change-Id: I20b94634b1f4ebff10757c2348cfdbbd906e8797 Reviewed-by: Lars Knoll <lars.knoll@nokia.com>
Diffstat (limited to 'util/unicode/data/WordBreakProperty.txt')
-rw-r--r--util/unicode/data/WordBreakProperty.txt626
1 files changed, 482 insertions, 144 deletions
diff --git a/util/unicode/data/WordBreakProperty.txt b/util/unicode/data/WordBreakProperty.txt
index 27b3b913bb..7f3225c6a8 100644
--- a/util/unicode/data/WordBreakProperty.txt
+++ b/util/unicode/data/WordBreakProperty.txt
@@ -1,10 +1,10 @@
-# WordBreakProperty-5.0.0.txt
-# Date: 2006-06-07, 23:23:03 GMT [MD]
+# WordBreakProperty-6.1.0.txt
+# Date: 2011-11-27, 05:10:51 GMT [MD]
#
# Unicode Character Database
-# Copyright (c) 1991-2006 Unicode, Inc.
+# Copyright (c) 1991-2011 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
-# For documentation, see UCD.html
+# For documentation, see http://www.unicode.org/reports/tr44/
# ================================================
@@ -17,39 +17,39 @@
# ================================================
-00AD ; Format # Cf SOFT HYPHEN
-0600..0603 ; Format # Cf [4] ARABIC NUMBER SIGN..ARABIC SIGN SAFHA
-06DD ; Format # Cf ARABIC END OF AYAH
-070F ; Format # Cf SYRIAC ABBREVIATION MARK
-17B4..17B5 ; Format # Cf [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
-200B ; Format # Cf ZERO WIDTH SPACE
-200E..200F ; Format # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
-202A..202E ; Format # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE
-2060..2063 ; Format # Cf [4] WORD JOINER..INVISIBLE SEPARATOR
-206A..206F ; Format # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES
-FEFF ; Format # Cf ZERO WIDTH NO-BREAK SPACE
-FFF9..FFFB ; Format # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR
-1D173..1D17A ; Format # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
-E0001 ; Format # Cf LANGUAGE TAG
-E0020..E007F ; Format # Cf [96] TAG SPACE..CANCEL TAG
+000D ; CR # Cc <control-000D>
+
+# Total code points: 1
+
+# ================================================
+
+000A ; LF # Cc <control-000A>
+
+# Total code points: 1
+
+# ================================================
+
+000B..000C ; Newline # Cc [2] <control-000B>..<control-000C>
+0085 ; Newline # Cc <control-0085>
+2028 ; Newline # Zl LINE SEPARATOR
+2029 ; Newline # Zp PARAGRAPH SEPARATOR
-# Total code points: 201
+# Total code points: 5
# ================================================
0300..036F ; Extend # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X
-0483..0486 ; Extend # Mn [4] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC PSILI PNEUMATA
+0483..0487 ; Extend # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE
0488..0489 ; Extend # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN
0591..05BD ; Extend # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG
05BF ; Extend # Mn HEBREW POINT RAFE
05C1..05C2 ; Extend # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT
05C4..05C5 ; Extend # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT
05C7 ; Extend # Mn HEBREW POINT QAMATS QATAN
-0610..0615 ; Extend # Mn [6] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL HIGH TAH
-064B..065E ; Extend # Mn [20] ARABIC FATHATAN..ARABIC FATHA WITH TWO DOTS
+0610..061A ; Extend # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA
+064B..065F ; Extend # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW
0670 ; Extend # Mn ARABIC LETTER SUPERSCRIPT ALEF
06D6..06DC ; Extend # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN
-06DE ; Extend # Me ARABIC START OF RUB EL HIZB
06DF..06E4 ; Extend # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA
06E7..06E8 ; Extend # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON
06EA..06ED ; Extend # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM
@@ -57,64 +57,108 @@ E0020..E007F ; Format # Cf [96] TAG SPACE..CANCEL TAG
0730..074A ; Extend # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH
07A6..07B0 ; Extend # Mn [11] THAANA ABAFILI..THAANA SUKUN
07EB..07F3 ; Extend # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE
-0901..0902 ; Extend # Mn [2] DEVANAGARI SIGN CANDRABINDU..DEVANAGARI SIGN ANUSVARA
+0816..0819 ; Extend # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH
+081B..0823 ; Extend # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A
+0825..0827 ; Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U
+0829..082D ; Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA
+0859..085B ; Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK
+08E4..08FE ; Extend # Mn [27] ARABIC CURLY FATHA..ARABIC DAMMA WITH DOT
+0900..0902 ; Extend # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA
+0903 ; Extend # Mc DEVANAGARI SIGN VISARGA
+093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE
+093B ; Extend # Mc DEVANAGARI VOWEL SIGN OOE
093C ; Extend # Mn DEVANAGARI SIGN NUKTA
+093E..0940 ; Extend # Mc [3] DEVANAGARI VOWEL SIGN AA..DEVANAGARI VOWEL SIGN II
0941..0948 ; Extend # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI
+0949..094C ; Extend # Mc [4] DEVANAGARI VOWEL SIGN CANDRA O..DEVANAGARI VOWEL SIGN AU
094D ; Extend # Mn DEVANAGARI SIGN VIRAMA
-0951..0954 ; Extend # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT
+094E..094F ; Extend # Mc [2] DEVANAGARI VOWEL SIGN PRISHTHAMATRA E..DEVANAGARI VOWEL SIGN AW
+0951..0957 ; Extend # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE
0962..0963 ; Extend # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL
0981 ; Extend # Mn BENGALI SIGN CANDRABINDU
+0982..0983 ; Extend # Mc [2] BENGALI SIGN ANUSVARA..BENGALI SIGN VISARGA
09BC ; Extend # Mn BENGALI SIGN NUKTA
-09BE ; Extend # Mc BENGALI VOWEL SIGN AA
+09BE..09C0 ; Extend # Mc [3] BENGALI VOWEL SIGN AA..BENGALI VOWEL SIGN II
09C1..09C4 ; Extend # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR
+09C7..09C8 ; Extend # Mc [2] BENGALI VOWEL SIGN E..BENGALI VOWEL SIGN AI
+09CB..09CC ; Extend # Mc [2] BENGALI VOWEL SIGN O..BENGALI VOWEL SIGN AU
09CD ; Extend # Mn BENGALI SIGN VIRAMA
09D7 ; Extend # Mc BENGALI AU LENGTH MARK
09E2..09E3 ; Extend # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL
0A01..0A02 ; Extend # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI
+0A03 ; Extend # Mc GURMUKHI SIGN VISARGA
0A3C ; Extend # Mn GURMUKHI SIGN NUKTA
+0A3E..0A40 ; Extend # Mc [3] GURMUKHI VOWEL SIGN AA..GURMUKHI VOWEL SIGN II
0A41..0A42 ; Extend # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU
0A47..0A48 ; Extend # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI
0A4B..0A4D ; Extend # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA
+0A51 ; Extend # Mn GURMUKHI SIGN UDAAT
0A70..0A71 ; Extend # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK
+0A75 ; Extend # Mn GURMUKHI SIGN YAKASH
0A81..0A82 ; Extend # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA
+0A83 ; Extend # Mc GUJARATI SIGN VISARGA
0ABC ; Extend # Mn GUJARATI SIGN NUKTA
+0ABE..0AC0 ; Extend # Mc [3] GUJARATI VOWEL SIGN AA..GUJARATI VOWEL SIGN II
0AC1..0AC5 ; Extend # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E
0AC7..0AC8 ; Extend # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI
+0AC9 ; Extend # Mc GUJARATI VOWEL SIGN CANDRA O
+0ACB..0ACC ; Extend # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU
0ACD ; Extend # Mn GUJARATI SIGN VIRAMA
0AE2..0AE3 ; Extend # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL
0B01 ; Extend # Mn ORIYA SIGN CANDRABINDU
+0B02..0B03 ; Extend # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA
0B3C ; Extend # Mn ORIYA SIGN NUKTA
0B3E ; Extend # Mc ORIYA VOWEL SIGN AA
0B3F ; Extend # Mn ORIYA VOWEL SIGN I
-0B41..0B43 ; Extend # Mn [3] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC R
+0B40 ; Extend # Mc ORIYA VOWEL SIGN II
+0B41..0B44 ; Extend # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR
+0B47..0B48 ; Extend # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI
+0B4B..0B4C ; Extend # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU
0B4D ; Extend # Mn ORIYA SIGN VIRAMA
0B56 ; Extend # Mn ORIYA AI LENGTH MARK
0B57 ; Extend # Mc ORIYA AU LENGTH MARK
+0B62..0B63 ; Extend # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL
0B82 ; Extend # Mn TAMIL SIGN ANUSVARA
-0BBE ; Extend # Mc TAMIL VOWEL SIGN AA
+0BBE..0BBF ; Extend # Mc [2] TAMIL VOWEL SIGN AA..TAMIL VOWEL SIGN I
0BC0 ; Extend # Mn TAMIL VOWEL SIGN II
+0BC1..0BC2 ; Extend # Mc [2] TAMIL VOWEL SIGN U..TAMIL VOWEL SIGN UU
+0BC6..0BC8 ; Extend # Mc [3] TAMIL VOWEL SIGN E..TAMIL VOWEL SIGN AI
+0BCA..0BCC ; Extend # Mc [3] TAMIL VOWEL SIGN O..TAMIL VOWEL SIGN AU
0BCD ; Extend # Mn TAMIL SIGN VIRAMA
0BD7 ; Extend # Mc TAMIL AU LENGTH MARK
+0C01..0C03 ; Extend # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA
0C3E..0C40 ; Extend # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II
+0C41..0C44 ; Extend # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR
0C46..0C48 ; Extend # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI
0C4A..0C4D ; Extend # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA
0C55..0C56 ; Extend # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK
+0C62..0C63 ; Extend # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL
+0C82..0C83 ; Extend # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA
0CBC ; Extend # Mn KANNADA SIGN NUKTA
+0CBE ; Extend # Mc KANNADA VOWEL SIGN AA
0CBF ; Extend # Mn KANNADA VOWEL SIGN I
-0CC2 ; Extend # Mc KANNADA VOWEL SIGN UU
+0CC0..0CC4 ; Extend # Mc [5] KANNADA VOWEL SIGN II..KANNADA VOWEL SIGN VOCALIC RR
0CC6 ; Extend # Mn KANNADA VOWEL SIGN E
+0CC7..0CC8 ; Extend # Mc [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI
+0CCA..0CCB ; Extend # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO
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
-0D3E ; Extend # Mc MALAYALAM VOWEL SIGN AA
-0D41..0D43 ; Extend # Mn [3] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC R
+0D02..0D03 ; Extend # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
+0D3E..0D40 ; Extend # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II
+0D41..0D44 ; Extend # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR
+0D46..0D48 ; Extend # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI
+0D4A..0D4C ; Extend # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU
0D4D ; Extend # Mn MALAYALAM SIGN VIRAMA
0D57 ; Extend # Mc MALAYALAM AU LENGTH MARK
+0D62..0D63 ; Extend # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL
+0D82..0D83 ; Extend # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA
0DCA ; Extend # Mn SINHALA SIGN AL-LAKUNA
-0DCF ; Extend # Mc SINHALA VOWEL SIGN AELA-PILLA
+0DCF..0DD1 ; Extend # Mc [3] SINHALA VOWEL SIGN AELA-PILLA..SINHALA VOWEL SIGN DIGA AEDA-PILLA
0DD2..0DD4 ; Extend # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA
0DD6 ; Extend # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA
-0DDF ; Extend # Mc SINHALA VOWEL SIGN GAYANUKITTA
+0DD8..0DDF ; Extend # Mc [8] SINHALA VOWEL SIGN GAETTA-PILLA..SINHALA VOWEL SIGN GAYANUKITTA
+0DF2..0DF3 ; Extend # Mc [2] SINHALA VOWEL SIGN DIGA GAETTA-PILLA..SINHALA VOWEL SIGN DIGA GAYANUKITTA
0E31 ; Extend # Mn THAI CHARACTER MAI HAN-AKAT
0E34..0E3A ; Extend # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU
0E47..0E4E ; Extend # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN
@@ -126,69 +170,246 @@ E0020..E007F ; Format # Cf [96] TAG SPACE..CANCEL TAG
0F35 ; Extend # Mn TIBETAN MARK NGAS BZUNG NYI ZLA
0F37 ; Extend # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS
0F39 ; Extend # Mn TIBETAN MARK TSA -PHRU
+0F3E..0F3F ; Extend # Mc [2] TIBETAN SIGN YAR TSHES..TIBETAN SIGN MAR TSHES
0F71..0F7E ; Extend # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO
+0F7F ; Extend # Mc TIBETAN SIGN RNAM BCAD
0F80..0F84 ; Extend # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA
0F86..0F87 ; Extend # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS
-0F90..0F97 ; Extend # Mn [8] TIBETAN SUBJOINED LETTER KA..TIBETAN SUBJOINED LETTER JA
+0F8D..0F97 ; Extend # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA
0F99..0FBC ; Extend # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA
0FC6 ; Extend # Mn TIBETAN SYMBOL PADMA GDAN
+102B..102C ; Extend # Mc [2] MYANMAR VOWEL SIGN TALL AA..MYANMAR VOWEL SIGN AA
102D..1030 ; Extend # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU
-1032 ; Extend # Mn MYANMAR VOWEL SIGN AI
-1036..1037 ; Extend # Mn [2] MYANMAR SIGN ANUSVARA..MYANMAR SIGN DOT BELOW
-1039 ; Extend # Mn MYANMAR SIGN VIRAMA
+1031 ; Extend # Mc MYANMAR VOWEL SIGN E
+1032..1037 ; Extend # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW
+1038 ; Extend # Mc MYANMAR SIGN VISARGA
+1039..103A ; Extend # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT
+103B..103C ; Extend # Mc [2] MYANMAR CONSONANT SIGN MEDIAL YA..MYANMAR CONSONANT SIGN MEDIAL RA
+103D..103E ; Extend # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA
+1056..1057 ; Extend # Mc [2] MYANMAR VOWEL SIGN VOCALIC R..MYANMAR VOWEL SIGN VOCALIC RR
1058..1059 ; Extend # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL
-135F ; Extend # Mn ETHIOPIC COMBINING GEMINATION MARK
+105E..1060 ; Extend # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA
+1062..1064 ; Extend # Mc [3] MYANMAR VOWEL SIGN SGAW KAREN EU..MYANMAR TONE MARK SGAW KAREN KE PHO
+1067..106D ; Extend # Mc [7] MYANMAR VOWEL SIGN WESTERN PWO KAREN EU..MYANMAR SIGN WESTERN PWO KAREN TONE-5
+1071..1074 ; Extend # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE
+1082 ; Extend # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA
+1083..1084 ; Extend # Mc [2] MYANMAR VOWEL SIGN SHAN AA..MYANMAR VOWEL SIGN SHAN E
+1085..1086 ; Extend # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y
+1087..108C ; Extend # Mc [6] MYANMAR SIGN SHAN TONE-2..MYANMAR SIGN SHAN COUNCIL TONE-3
+108D ; Extend # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE
+108F ; Extend # Mc MYANMAR SIGN RUMAI PALAUNG TONE-5
+109A..109C ; Extend # Mc [3] MYANMAR SIGN KHAMTI TONE-1..MYANMAR VOWEL SIGN AITON A
+109D ; Extend # Mn MYANMAR VOWEL SIGN AITON AI
+135D..135F ; Extend # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK
1712..1714 ; Extend # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA
1732..1734 ; Extend # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD
1752..1753 ; Extend # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U
1772..1773 ; Extend # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U
+17B4..17B5 ; Extend # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
+17B6 ; Extend # Mc KHMER VOWEL SIGN AA
17B7..17BD ; Extend # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA
+17BE..17C5 ; Extend # Mc [8] KHMER VOWEL SIGN OE..KHMER VOWEL SIGN AU
17C6 ; Extend # Mn KHMER SIGN NIKAHIT
+17C7..17C8 ; Extend # Mc [2] KHMER SIGN REAHMUK..KHMER SIGN YUUKALEAPINTU
17C9..17D3 ; Extend # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT
17DD ; Extend # Mn KHMER SIGN ATTHACAN
180B..180D ; Extend # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
18A9 ; Extend # Mn MONGOLIAN LETTER ALI GALI DAGALGA
1920..1922 ; Extend # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U
+1923..1926 ; Extend # Mc [4] LIMBU VOWEL SIGN EE..LIMBU VOWEL SIGN AU
1927..1928 ; Extend # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O
+1929..192B ; Extend # Mc [3] LIMBU SUBJOINED LETTER YA..LIMBU SUBJOINED LETTER WA
+1930..1931 ; Extend # Mc [2] LIMBU SMALL LETTER KA..LIMBU SMALL LETTER NGA
1932 ; Extend # Mn LIMBU SMALL LETTER ANUSVARA
+1933..1938 ; Extend # Mc [6] LIMBU SMALL LETTER TA..LIMBU SMALL LETTER LA
1939..193B ; Extend # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I
+19B0..19C0 ; Extend # Mc [17] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE VOWEL SIGN IY
+19C8..19C9 ; Extend # Mc [2] NEW TAI LUE TONE MARK-1..NEW TAI LUE TONE MARK-2
1A17..1A18 ; Extend # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U
+1A19..1A1B ; Extend # Mc [3] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN AE
+1A55 ; Extend # Mc TAI THAM CONSONANT SIGN MEDIAL RA
+1A56 ; Extend # Mn TAI THAM CONSONANT SIGN MEDIAL LA
+1A57 ; Extend # Mc TAI THAM CONSONANT SIGN LA TANG LAI
+1A58..1A5E ; Extend # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA
+1A60 ; Extend # Mn TAI THAM SIGN SAKOT
+1A61 ; Extend # Mc TAI THAM VOWEL SIGN A
+1A62 ; Extend # Mn TAI THAM VOWEL SIGN MAI SAT
+1A63..1A64 ; Extend # Mc [2] TAI THAM VOWEL SIGN AA..TAI THAM VOWEL SIGN TALL AA
+1A65..1A6C ; Extend # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW
+1A6D..1A72 ; Extend # Mc [6] TAI THAM VOWEL SIGN OY..TAI THAM VOWEL SIGN THAM AI
+1A73..1A7C ; Extend # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN
+1A7F ; Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT
1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG
+1B04 ; Extend # Mc BALINESE SIGN BISAH
1B34 ; Extend # Mn BALINESE SIGN REREKAN
+1B35 ; Extend # Mc BALINESE VOWEL SIGN TEDUNG
1B36..1B3A ; Extend # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA
+1B3B ; Extend # Mc BALINESE VOWEL SIGN RA REPA TEDUNG
1B3C ; Extend # Mn BALINESE VOWEL SIGN LA LENGA
+1B3D..1B41 ; Extend # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG
1B42 ; Extend # Mn BALINESE VOWEL SIGN PEPET
+1B43..1B44 ; Extend # Mc [2] BALINESE VOWEL SIGN PEPET TEDUNG..BALINESE ADEG ADEG
1B6B..1B73 ; Extend # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG
-1DC0..1DCA ; Extend # Mn [11] COMBINING DOTTED GRAVE ACCENT..COMBINING LATIN SMALL LETTER R BELOW
-1DFE..1DFF ; Extend # Mn [2] COMBINING LEFT ARROWHEAD ABOVE..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
+1B80..1B81 ; Extend # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR
+1B82 ; Extend # Mc SUNDANESE SIGN PANGWISAD
+1BA1 ; Extend # Mc SUNDANESE CONSONANT SIGN PAMINGKAL
+1BA2..1BA5 ; Extend # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU
+1BA6..1BA7 ; Extend # Mc [2] SUNDANESE VOWEL SIGN PANAELAENG..SUNDANESE VOWEL SIGN PANOLONG
+1BA8..1BA9 ; Extend # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG
+1BAA ; Extend # Mc SUNDANESE SIGN PAMAAEH
+1BAB ; Extend # Mn SUNDANESE SIGN VIRAMA
+1BAC..1BAD ; Extend # Mc [2] SUNDANESE CONSONANT SIGN PASANGAN MA..SUNDANESE CONSONANT SIGN PASANGAN WA
+1BE6 ; Extend # Mn BATAK SIGN TOMPI
+1BE7 ; Extend # Mc BATAK VOWEL SIGN E
+1BE8..1BE9 ; Extend # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE
+1BEA..1BEC ; Extend # Mc [3] BATAK VOWEL SIGN I..BATAK VOWEL SIGN O
+1BED ; Extend # Mn BATAK VOWEL SIGN KARO O
+1BEE ; Extend # Mc BATAK VOWEL SIGN U
+1BEF..1BF1 ; Extend # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H
+1BF2..1BF3 ; Extend # Mc [2] BATAK PANGOLAT..BATAK PANONGONAN
+1C24..1C2B ; Extend # Mc [8] LEPCHA SUBJOINED LETTER YA..LEPCHA VOWEL SIGN UU
+1C2C..1C33 ; Extend # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T
+1C34..1C35 ; Extend # Mc [2] LEPCHA CONSONANT SIGN NYIN-DO..LEPCHA CONSONANT SIGN KANG
+1C36..1C37 ; Extend # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA
+1CD0..1CD2 ; Extend # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA
+1CD4..1CE0 ; Extend # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA
+1CE1 ; Extend # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA
+1CE2..1CE8 ; Extend # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL
+1CED ; Extend # Mn VEDIC SIGN TIRYAK
+1CF2..1CF3 ; Extend # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
+1CF4 ; Extend # Mn VEDIC TONE CANDRA ABOVE
+1DC0..1DE6 ; Extend # Mn [39] COMBINING DOTTED GRAVE ACCENT..COMBINING LATIN SMALL LETTER Z
+1DFC..1DFF ; Extend # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
200C..200D ; Extend # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER
20D0..20DC ; Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
20DD..20E0 ; Extend # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH
20E1 ; Extend # Mn COMBINING LEFT RIGHT ARROW ABOVE
20E2..20E4 ; Extend # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE
-20E5..20EF ; Extend # Mn [11] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING RIGHT ARROW BELOW
-302A..302F ; Extend # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK
+20E5..20F0 ; Extend # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE
+2CEF..2CF1 ; Extend # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS
+2D7F ; Extend # Mn TIFINAGH CONSONANT JOINER
+2DE0..2DFF ; Extend # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS
+302A..302D ; Extend # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK
+302E..302F ; Extend # Mc [2] HANGUL SINGLE DOT TONE MARK..HANGUL DOUBLE DOT TONE MARK
3099..309A ; Extend # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
+A66F ; Extend # Mn COMBINING CYRILLIC VZMET
+A670..A672 ; Extend # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN
+A674..A67D ; Extend # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK
+A69F ; Extend # Mn COMBINING CYRILLIC LETTER IOTIFIED E
+A6F0..A6F1 ; Extend # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS
+A802 ; Extend # Mn SYLOTI NAGRI SIGN DVISVARA
A806 ; Extend # Mn SYLOTI NAGRI SIGN HASANTA
A80B ; Extend # Mn SYLOTI NAGRI SIGN ANUSVARA
+A823..A824 ; Extend # Mc [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIGN I
A825..A826 ; Extend # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E
+A827 ; Extend # Mc SYLOTI NAGRI VOWEL SIGN OO
+A880..A881 ; Extend # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA
+A8B4..A8C3 ; Extend # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU
+A8C4 ; Extend # Mn SAURASHTRA SIGN VIRAMA
+A8E0..A8F1 ; Extend # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA
+A926..A92D ; Extend # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU
+A947..A951 ; Extend # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R
+A952..A953 ; Extend # Mc [2] REJANG CONSONANT SIGN H..REJANG VIRAMA
+A980..A982 ; Extend # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR
+A983 ; Extend # Mc JAVANESE SIGN WIGNYAN
+A9B3 ; Extend # Mn JAVANESE SIGN CECAK TELU
+A9B4..A9B5 ; Extend # Mc [2] JAVANESE VOWEL SIGN TARUNG..JAVANESE VOWEL SIGN TOLONG
+A9B6..A9B9 ; Extend # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT
+A9BA..A9BB ; Extend # Mc [2] JAVANESE VOWEL SIGN TALING..JAVANESE VOWEL SIGN DIRGA MURE
+A9BC ; Extend # Mn JAVANESE VOWEL SIGN PEPET
+A9BD..A9C0 ; Extend # Mc [4] JAVANESE CONSONANT SIGN KERET..JAVANESE PANGKON
+AA29..AA2E ; Extend # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE
+AA2F..AA30 ; Extend # Mc [2] CHAM VOWEL SIGN O..CHAM VOWEL SIGN AI
+AA31..AA32 ; Extend # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE
+AA33..AA34 ; Extend # Mc [2] CHAM CONSONANT SIGN YA..CHAM CONSONANT SIGN RA
+AA35..AA36 ; Extend # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA
+AA43 ; Extend # Mn CHAM CONSONANT SIGN FINAL NG
+AA4C ; Extend # Mn CHAM CONSONANT SIGN FINAL M
+AA4D ; Extend # Mc CHAM CONSONANT SIGN FINAL H
+AA7B ; Extend # Mc MYANMAR SIGN PAO KAREN TONE
+AAB0 ; Extend # Mn TAI VIET MAI KANG
+AAB2..AAB4 ; Extend # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U
+AAB7..AAB8 ; Extend # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA
+AABE..AABF ; Extend # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK
+AAC1 ; Extend # Mn TAI VIET TONE MAI THO
+AAEB ; Extend # Mc MEETEI MAYEK VOWEL SIGN II
+AAEC..AAED ; Extend # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI
+AAEE..AAEF ; Extend # Mc [2] MEETEI MAYEK VOWEL SIGN AU..MEETEI MAYEK VOWEL SIGN AAU
+AAF5 ; Extend # Mc MEETEI MAYEK VOWEL SIGN VISARGA
+AAF6 ; Extend # Mn MEETEI MAYEK VIRAMA
+ABE3..ABE4 ; Extend # Mc [2] MEETEI MAYEK VOWEL SIGN ONAP..MEETEI MAYEK VOWEL SIGN INAP
+ABE5 ; Extend # Mn MEETEI MAYEK VOWEL SIGN ANAP
+ABE6..ABE7 ; Extend # Mc [2] MEETEI MAYEK VOWEL SIGN YENAP..MEETEI MAYEK VOWEL SIGN SOUNAP
+ABE8 ; Extend # Mn MEETEI MAYEK VOWEL SIGN UNAP
+ABE9..ABEA ; Extend # Mc [2] MEETEI MAYEK VOWEL SIGN CHEINAP..MEETEI MAYEK VOWEL SIGN NUNG
+ABEC ; Extend # Mc MEETEI MAYEK LUM IYEK
+ABED ; Extend # Mn MEETEI MAYEK APUN IYEK
FB1E ; Extend # Mn HEBREW POINT JUDEO-SPANISH VARIKA
FE00..FE0F ; Extend # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
-FE20..FE23 ; Extend # Mn [4] COMBINING LIGATURE LEFT HALF..COMBINING DOUBLE TILDE RIGHT HALF
+FE20..FE26 ; Extend # Mn [7] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON
+FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
+101FD ; Extend # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE
10A01..10A03 ; Extend # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R
10A05..10A06 ; Extend # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O
10A0C..10A0F ; Extend # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA
10A38..10A3A ; Extend # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW
10A3F ; Extend # Mn KHAROSHTHI VIRAMA
-1D165 ; Extend # Mc MUSICAL SYMBOL COMBINING STEM
+11000 ; Extend # Mc BRAHMI SIGN CANDRABINDU
+11001 ; Extend # Mn BRAHMI SIGN ANUSVARA
+11002 ; Extend # Mc BRAHMI SIGN VISARGA
+11038..11046 ; Extend # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA
+11080..11081 ; Extend # Mn [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA
+11082 ; Extend # Mc KAITHI SIGN VISARGA
+110B0..110B2 ; Extend # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II
+110B3..110B6 ; Extend # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI
+110B7..110B8 ; Extend # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU
+110B9..110BA ; Extend # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA
+11100..11102 ; Extend # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA
+11127..1112B ; Extend # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU
+1112C ; Extend # Mc CHAKMA VOWEL SIGN E
+1112D..11134 ; Extend # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA
+11180..11181 ; Extend # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA
+11182 ; Extend # Mc SHARADA SIGN VISARGA
+111B3..111B5 ; Extend # Mc [3] SHARADA VOWEL SIGN AA..SHARADA VOWEL SIGN II
+111B6..111BE ; Extend # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O
+111BF..111C0 ; Extend # Mc [2] SHARADA VOWEL SIGN AU..SHARADA SIGN VIRAMA
+116AB ; Extend # Mn TAKRI SIGN ANUSVARA
+116AC ; Extend # Mc TAKRI SIGN VISARGA
+116AD ; Extend # Mn TAKRI VOWEL SIGN AA
+116AE..116AF ; Extend # Mc [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II
+116B0..116B5 ; Extend # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU
+116B6 ; Extend # Mc TAKRI SIGN VIRAMA
+116B7 ; Extend # Mn TAKRI SIGN NUKTA
+16F51..16F7E ; Extend # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
+16F8F..16F92 ; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
+1D165..1D166 ; Extend # Mc [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM
1D167..1D169 ; Extend # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3
-1D16E..1D172 ; Extend # Mc [5] MUSICAL SYMBOL COMBINING FLAG-1..MUSICAL SYMBOL COMBINING FLAG-5
+1D16D..1D172 ; Extend # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5
1D17B..1D182 ; Extend # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE
1D185..1D18B ; Extend # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
1D1AA..1D1AD ; Extend # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
1D242..1D244 ; Extend # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
+# Total code points: 1649
+
+# ================================================
+
+00AD ; Format # Cf SOFT HYPHEN
+0600..0604 ; Format # Cf [5] ARABIC NUMBER SIGN..ARABIC SIGN SAMVAT
+06DD ; Format # Cf ARABIC END OF AYAH
+070F ; Format # Cf SYRIAC ABBREVIATION MARK
+200E..200F ; Format # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
+202A..202E ; Format # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE
+2060..2064 ; Format # Cf [5] WORD JOINER..INVISIBLE PLUS
+206A..206F ; Format # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES
+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
+1D173..1D17A ; Format # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
+E0001 ; Format # Cf LANGUAGE TAG
+E0020..E007F ; Format # Cf [96] TAG SPACE..CANCEL TAG
+
# Total code points: 136
# ================================================
@@ -200,20 +421,22 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
30FC..30FE ; Katakana # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK
30FF ; Katakana # Lo KATAKANA DIGRAPH KOTO
31F0..31FF ; Katakana # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO
+32D0..32FE ; Katakana # So [47] CIRCLED KATAKANA A..CIRCLED KATAKANA WO
+3300..3357 ; Katakana # So [88] SQUARE APAATO..SQUARE WATTO
FF66..FF6F ; Katakana # Lo [10] HALFWIDTH KATAKANA LETTER WO..HALFWIDTH KATAKANA LETTER SMALL TU
FF70 ; Katakana # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAKANA LETTER N
-FF9E..FF9F ; Katakana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
+1B000 ; Katakana # Lo KATAKANA LETTER ARCHAIC E
-# Total code points: 176
+# Total code points: 310
# ================================================
0041..005A ; ALetter # L& [26] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER Z
0061..007A ; ALetter # L& [26] LATIN SMALL LETTER A..LATIN SMALL LETTER Z
-00AA ; ALetter # L& FEMININE ORDINAL INDICATOR
+00AA ; ALetter # Lo FEMININE ORDINAL INDICATOR
00B5 ; ALetter # L& MICRO SIGN
-00BA ; ALetter # L& MASCULINE ORDINAL INDICATOR
+00BA ; ALetter # Lo MASCULINE ORDINAL INDICATOR
00C0..00D6 ; ALetter # L& [23] LATIN CAPITAL LETTER A WITH GRAVE..LATIN CAPITAL LETTER O WITH DIAERESIS
00D8..00F6 ; ALetter # L& [31] LATIN CAPITAL LETTER O WITH STROKE..LATIN SMALL LETTER O WITH DIAERESIS
00F8..01BA ; ALetter # L& [195] LATIN SMALL LETTER O WITH STROKE..LATIN SMALL LETTER EZH WITH TAIL
@@ -226,24 +449,27 @@ FF9E..FF9F ; Katakana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWI
02B0..02C1 ; ALetter # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP
02C6..02D1 ; ALetter # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON
02E0..02E4 ; ALetter # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
+02EC ; ALetter # Lm MODIFIER LETTER VOICING
02EE ; ALetter # Lm MODIFIER LETTER DOUBLE APOSTROPHE
+0370..0373 ; ALetter # L& [4] GREEK CAPITAL LETTER HETA..GREEK SMALL LETTER ARCHAIC SAMPI
+0374 ; ALetter # Lm GREEK NUMERAL SIGN
+0376..0377 ; ALetter # L& [2] GREEK CAPITAL LETTER PAMPHYLIAN DIGAMMA..GREEK SMALL LETTER PAMPHYLIAN DIGAMMA
037A ; ALetter # Lm GREEK YPOGEGRAMMENI
037B..037D ; ALetter # L& [3] GREEK SMALL REVERSED LUNATE SIGMA SYMBOL..GREEK SMALL REVERSED DOTTED LUNATE SIGMA SYMBOL
0386 ; ALetter # L& GREEK CAPITAL LETTER ALPHA WITH TONOS
0388..038A ; ALetter # L& [3] GREEK CAPITAL LETTER EPSILON WITH TONOS..GREEK CAPITAL LETTER IOTA WITH TONOS
038C ; ALetter # L& GREEK CAPITAL LETTER OMICRON WITH TONOS
038E..03A1 ; ALetter # L& [20] GREEK CAPITAL LETTER UPSILON WITH TONOS..GREEK CAPITAL LETTER RHO
-03A3..03CE ; ALetter # L& [44] GREEK CAPITAL LETTER SIGMA..GREEK SMALL LETTER OMEGA WITH TONOS
-03D0..03F5 ; ALetter # L& [38] GREEK BETA SYMBOL..GREEK LUNATE EPSILON SYMBOL
+03A3..03F5 ; ALetter # L& [83] GREEK CAPITAL LETTER SIGMA..GREEK LUNATE EPSILON SYMBOL
03F7..0481 ; ALetter # L& [139] GREEK CAPITAL LETTER SHO..CYRILLIC SMALL LETTER KOPPA
-048A..0513 ; ALetter # L& [138] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH HOOK
+048A..0527 ; ALetter # L& [158] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER SHHA WITH DESCENDER
0531..0556 ; ALetter # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH
0559 ; ALetter # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING
0561..0587 ; ALetter # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN
05D0..05EA ; ALetter # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV
05F0..05F2 ; ALetter # Lo [3] HEBREW LIGATURE YIDDISH DOUBLE VAV..HEBREW LIGATURE YIDDISH DOUBLE YOD
05F3 ; ALetter # Po HEBREW PUNCTUATION GERESH
-0621..063A ; ALetter # Lo [26] ARABIC LETTER HAMZA..ARABIC LETTER GHAIN
+0620..063F ; ALetter # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE
0640 ; ALetter # Lm ARABIC TATWEEL
0641..064A ; ALetter # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH
066E..066F ; ALetter # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF
@@ -255,21 +481,25 @@ FF9E..FF9F ; Katakana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWI
06FF ; ALetter # Lo ARABIC LETTER HEH WITH INVERTED V
0710 ; ALetter # Lo SYRIAC LETTER ALAPH
0712..072F ; ALetter # Lo [30] SYRIAC LETTER BETH..SYRIAC LETTER PERSIAN DHALATH
-074D..076D ; ALetter # Lo [33] SYRIAC LETTER SOGDIAN ZHAIN..ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE
-0780..07A5 ; ALetter # Lo [38] THAANA LETTER HAA..THAANA LETTER WAAVU
+074D..07A5 ; ALetter # Lo [89] SYRIAC LETTER SOGDIAN ZHAIN..THAANA LETTER WAAVU
07B1 ; ALetter # Lo THAANA LETTER NAA
07CA..07EA ; ALetter # Lo [33] NKO LETTER A..NKO LETTER JONA RA
07F4..07F5 ; ALetter # Lm [2] NKO HIGH TONE APOSTROPHE..NKO LOW TONE APOSTROPHE
07FA ; ALetter # Lm NKO LAJANYALAN
-0903 ; ALetter # Mc DEVANAGARI SIGN VISARGA
+0800..0815 ; ALetter # Lo [22] SAMARITAN LETTER ALAF..SAMARITAN LETTER TAAF
+081A ; ALetter # Lm SAMARITAN MODIFIER LETTER EPENTHETIC YUT
+0824 ; ALetter # Lm SAMARITAN MODIFIER LETTER SHORT A
+0828 ; ALetter # Lm SAMARITAN MODIFIER LETTER I
+0840..0858 ; ALetter # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN
+08A0 ; ALetter # Lo ARABIC LETTER BEH WITH SMALL V BELOW
+08A2..08AC ; ALetter # Lo [11] ARABIC LETTER JEEM WITH TWO DOTS ABOVE..ARABIC LETTER ROHINGYA YEH
0904..0939 ; ALetter # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA
093D ; ALetter # Lo DEVANAGARI SIGN AVAGRAHA
-093E..0940 ; ALetter # Mc [3] DEVANAGARI VOWEL SIGN AA..DEVANAGARI VOWEL SIGN II
-0949..094C ; ALetter # Mc [4] DEVANAGARI VOWEL SIGN CANDRA O..DEVANAGARI VOWEL SIGN AU
0950 ; ALetter # Lo DEVANAGARI OM
0958..0961 ; ALetter # Lo [10] DEVANAGARI LETTER QA..DEVANAGARI LETTER VOCALIC LL
-097B..097F ; ALetter # Lo [5] DEVANAGARI LETTER GGA..DEVANAGARI LETTER BBA
-0982..0983 ; ALetter # Mc [2] BENGALI SIGN ANUSVARA..BENGALI SIGN VISARGA
+0971 ; ALetter # Lm DEVANAGARI SIGN HIGH SPACING DOT
+0972..0977 ; ALetter # Lo [6] DEVANAGARI LETTER CANDRA A..DEVANAGARI LETTER UUE
+0979..097F ; ALetter # Lo [7] DEVANAGARI LETTER ZHA..DEVANAGARI LETTER BBA
0985..098C ; ALetter # Lo [8] BENGALI LETTER A..BENGALI LETTER VOCALIC L
098F..0990 ; ALetter # Lo [2] BENGALI LETTER E..BENGALI LETTER AI
0993..09A8 ; ALetter # Lo [22] BENGALI LETTER O..BENGALI LETTER NA
@@ -277,14 +507,10 @@ FF9E..FF9F ; Katakana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWI
09B2 ; ALetter # Lo BENGALI LETTER LA
09B6..09B9 ; ALetter # Lo [4] BENGALI LETTER SHA..BENGALI LETTER HA
09BD ; ALetter # Lo BENGALI SIGN AVAGRAHA
-09BF..09C0 ; ALetter # Mc [2] BENGALI VOWEL SIGN I..BENGALI VOWEL SIGN II
-09C7..09C8 ; ALetter # Mc [2] BENGALI VOWEL SIGN E..BENGALI VOWEL SIGN AI
-09CB..09CC ; ALetter # Mc [2] BENGALI VOWEL SIGN O..BENGALI VOWEL SIGN AU
09CE ; ALetter # Lo BENGALI LETTER KHANDA TA
09DC..09DD ; ALetter # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA
09DF..09E1 ; ALetter # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL
09F0..09F1 ; ALetter # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL
-0A03 ; ALetter # Mc GURMUKHI SIGN VISARGA
0A05..0A0A ; ALetter # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU
0A0F..0A10 ; ALetter # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI
0A13..0A28 ; ALetter # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA
@@ -292,11 +518,9 @@ FF9E..FF9F ; Katakana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWI
0A32..0A33 ; ALetter # Lo [2] GURMUKHI LETTER LA..GURMUKHI LETTER LLA
0A35..0A36 ; ALetter # Lo [2] GURMUKHI LETTER VA..GURMUKHI LETTER SHA
0A38..0A39 ; ALetter # Lo [2] GURMUKHI LETTER SA..GURMUKHI LETTER HA
-0A3E..0A40 ; ALetter # Mc [3] GURMUKHI VOWEL SIGN AA..GURMUKHI VOWEL SIGN II
0A59..0A5C ; ALetter # Lo [4] GURMUKHI LETTER KHHA..GURMUKHI LETTER RRA
0A5E ; ALetter # Lo GURMUKHI LETTER FA
0A72..0A74 ; ALetter # Lo [3] GURMUKHI IRI..GURMUKHI EK ONKAR
-0A83 ; ALetter # Mc GUJARATI SIGN VISARGA
0A85..0A8D ; ALetter # Lo [9] GUJARATI LETTER A..GUJARATI VOWEL CANDRA E
0A8F..0A91 ; ALetter # Lo [3] GUJARATI LETTER E..GUJARATI VOWEL CANDRA O
0A93..0AA8 ; ALetter # Lo [22] GUJARATI LETTER O..GUJARATI LETTER NA
@@ -304,12 +528,8 @@ FF9E..FF9F ; Katakana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWI
0AB2..0AB3 ; ALetter # Lo [2] GUJARATI LETTER LA..GUJARATI LETTER LLA
0AB5..0AB9 ; ALetter # Lo [5] GUJARATI LETTER VA..GUJARATI LETTER HA
0ABD ; ALetter # Lo GUJARATI SIGN AVAGRAHA
-0ABE..0AC0 ; ALetter # Mc [3] GUJARATI VOWEL SIGN AA..GUJARATI VOWEL SIGN II
-0AC9 ; ALetter # Mc GUJARATI VOWEL SIGN CANDRA O
-0ACB..0ACC ; ALetter # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU
0AD0 ; ALetter # Lo GUJARATI OM
0AE0..0AE1 ; ALetter # Lo [2] GUJARATI LETTER VOCALIC RR..GUJARATI LETTER VOCALIC LL
-0B02..0B03 ; ALetter # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA
0B05..0B0C ; ALetter # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L
0B0F..0B10 ; ALetter # Lo [2] ORIYA LETTER E..ORIYA LETTER AI
0B13..0B28 ; ALetter # Lo [22] ORIYA LETTER O..ORIYA LETTER NA
@@ -317,9 +537,6 @@ FF9E..FF9F ; Katakana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWI
0B32..0B33 ; ALetter # Lo [2] ORIYA LETTER LA..ORIYA LETTER LLA
0B35..0B39 ; ALetter # Lo [5] ORIYA LETTER VA..ORIYA LETTER HA
0B3D ; ALetter # Lo ORIYA SIGN AVAGRAHA
-0B40 ; ALetter # Mc ORIYA VOWEL SIGN II
-0B47..0B48 ; ALetter # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI
-0B4B..0B4C ; ALetter # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU
0B5C..0B5D ; ALetter # Lo [2] ORIYA LETTER RRA..ORIYA LETTER RHA
0B5F..0B61 ; ALetter # Lo [3] ORIYA LETTER YYA..ORIYA LETTER VOCALIC LL
0B71 ; ALetter # Lo ORIYA LETTER WA
@@ -333,62 +550,46 @@ FF9E..FF9F ; Katakana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWI
0BA3..0BA4 ; ALetter # Lo [2] TAMIL LETTER NNA..TAMIL LETTER TA
0BA8..0BAA ; ALetter # Lo [3] TAMIL LETTER NA..TAMIL LETTER PA
0BAE..0BB9 ; ALetter # Lo [12] TAMIL LETTER MA..TAMIL LETTER HA
-0BBF ; ALetter # Mc TAMIL VOWEL SIGN I
-0BC1..0BC2 ; ALetter # Mc [2] TAMIL VOWEL SIGN U..TAMIL VOWEL SIGN UU
-0BC6..0BC8 ; ALetter # Mc [3] TAMIL VOWEL SIGN E..TAMIL VOWEL SIGN AI
-0BCA..0BCC ; ALetter # Mc [3] TAMIL VOWEL SIGN O..TAMIL VOWEL SIGN AU
-0C01..0C03 ; ALetter # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA
+0BD0 ; ALetter # Lo TAMIL OM
0C05..0C0C ; ALetter # Lo [8] TELUGU LETTER A..TELUGU LETTER VOCALIC L
0C0E..0C10 ; ALetter # Lo [3] TELUGU LETTER E..TELUGU LETTER AI
0C12..0C28 ; ALetter # Lo [23] TELUGU LETTER O..TELUGU LETTER NA
0C2A..0C33 ; ALetter # Lo [10] TELUGU LETTER PA..TELUGU LETTER LLA
0C35..0C39 ; ALetter # Lo [5] TELUGU LETTER VA..TELUGU LETTER HA
-0C41..0C44 ; ALetter # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR
+0C3D ; ALetter # Lo TELUGU SIGN AVAGRAHA
+0C58..0C59 ; ALetter # Lo [2] TELUGU LETTER TSA..TELUGU LETTER DZA
0C60..0C61 ; ALetter # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL
-0C82..0C83 ; ALetter # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA
0C85..0C8C ; ALetter # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L
0C8E..0C90 ; ALetter # Lo [3] KANNADA LETTER E..KANNADA LETTER AI
0C92..0CA8 ; ALetter # Lo [23] KANNADA LETTER O..KANNADA LETTER NA
0CAA..0CB3 ; ALetter # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA
0CB5..0CB9 ; ALetter # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA
0CBD ; ALetter # Lo KANNADA SIGN AVAGRAHA
-0CBE ; ALetter # Mc KANNADA VOWEL SIGN AA
-0CC0..0CC1 ; ALetter # Mc [2] KANNADA VOWEL SIGN II..KANNADA VOWEL SIGN U
-0CC3..0CC4 ; ALetter # Mc [2] KANNADA VOWEL SIGN VOCALIC R..KANNADA VOWEL SIGN VOCALIC RR
-0CC7..0CC8 ; ALetter # Mc [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI
-0CCA..0CCB ; ALetter # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO
0CDE ; ALetter # Lo KANNADA LETTER FA
0CE0..0CE1 ; ALetter # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL
-0D02..0D03 ; ALetter # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
+0CF1..0CF2 ; ALetter # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
0D05..0D0C ; ALetter # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L
0D0E..0D10 ; ALetter # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI
-0D12..0D28 ; ALetter # Lo [23] MALAYALAM LETTER O..MALAYALAM LETTER NA
-0D2A..0D39 ; ALetter # Lo [16] MALAYALAM LETTER PA..MALAYALAM LETTER HA
-0D3F..0D40 ; ALetter # Mc [2] MALAYALAM VOWEL SIGN I..MALAYALAM VOWEL SIGN II
-0D46..0D48 ; ALetter # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI
-0D4A..0D4C ; ALetter # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU
+0D12..0D3A ; ALetter # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA
+0D3D ; ALetter # Lo MALAYALAM SIGN AVAGRAHA
+0D4E ; ALetter # Lo MALAYALAM LETTER DOT REPH
0D60..0D61 ; ALetter # Lo [2] MALAYALAM LETTER VOCALIC RR..MALAYALAM LETTER VOCALIC LL
-0D82..0D83 ; ALetter # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA
+0D7A..0D7F ; ALetter # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K
0D85..0D96 ; ALetter # Lo [18] SINHALA LETTER AYANNA..SINHALA LETTER AUYANNA
0D9A..0DB1 ; ALetter # Lo [24] SINHALA LETTER ALPAPRAANA KAYANNA..SINHALA LETTER DANTAJA NAYANNA
0DB3..0DBB ; ALetter # Lo [9] SINHALA LETTER SANYAKA DAYANNA..SINHALA LETTER RAYANNA
0DBD ; ALetter # Lo SINHALA LETTER DANTAJA LAYANNA
0DC0..0DC6 ; ALetter # Lo [7] SINHALA LETTER VAYANNA..SINHALA LETTER FAYANNA
-0DD0..0DD1 ; ALetter # Mc [2] SINHALA VOWEL SIGN KETTI AEDA-PILLA..SINHALA VOWEL SIGN DIGA AEDA-PILLA
-0DD8..0DDE ; ALetter # Mc [7] SINHALA VOWEL SIGN GAETTA-PILLA..SINHALA VOWEL SIGN KOMBUVA HAA GAYANUKITTA
-0DF2..0DF3 ; ALetter # Mc [2] SINHALA VOWEL SIGN DIGA GAETTA-PILLA..SINHALA VOWEL SIGN DIGA GAYANUKITTA
0F00 ; ALetter # Lo TIBETAN SYLLABLE OM
0F40..0F47 ; ALetter # Lo [8] TIBETAN LETTER KA..TIBETAN LETTER JA
-0F49..0F6A ; ALetter # Lo [34] TIBETAN LETTER NYA..TIBETAN LETTER FIXED-FORM RA
-0F7F ; ALetter # Mc TIBETAN SIGN RNAM BCAD
-0F88..0F8B ; ALetter # Lo [4] TIBETAN SIGN LCE TSA CAN..TIBETAN SIGN GRU MED RGYINGS
+0F49..0F6C ; ALetter # Lo [36] TIBETAN LETTER NYA..TIBETAN LETTER RRA
+0F88..0F8C ; ALetter # Lo [5] TIBETAN SIGN LCE TSA CAN..TIBETAN SIGN INVERTED MCHU CAN
10A0..10C5 ; ALetter # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE
+10C7 ; ALetter # L& GEORGIAN CAPITAL LETTER YN
+10CD ; ALetter # L& GEORGIAN CAPITAL LETTER AEN
10D0..10FA ; ALetter # Lo [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN
10FC ; ALetter # Lm MODIFIER LETTER GEORGIAN NAR
-1100..1159 ; ALetter # Lo [90] HANGUL CHOSEONG KIYEOK..HANGUL CHOSEONG YEORINHIEUH
-115F..11A2 ; ALetter # Lo [68] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG SSANGARAEA
-11A8..11F9 ; ALetter # Lo [82] HANGUL JONGSEONG KIYEOK..HANGUL JONGSEONG YEORINHIEUH
-1200..1248 ; ALetter # Lo [73] ETHIOPIC SYLLABLE HA..ETHIOPIC SYLLABLE QWA
+10FD..1248 ; ALetter # Lo [332] GEORGIAN LETTER AEN..ETHIOPIC SYLLABLE QWA
124A..124D ; ALetter # Lo [4] ETHIOPIC SYLLABLE QWI..ETHIOPIC SYLLABLE QWE
1250..1256 ; ALetter # Lo [7] ETHIOPIC SYLLABLE QHA..ETHIOPIC SYLLABLE QHO
1258 ; ALetter # Lo ETHIOPIC SYLLABLE QHWA
@@ -407,7 +608,7 @@ FF9E..FF9F ; Katakana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWI
1380..138F ; ALetter # Lo [16] ETHIOPIC SYLLABLE SEBATBEIT MWA..ETHIOPIC SYLLABLE PWE
13A0..13F4 ; ALetter # Lo [85] CHEROKEE LETTER A..CHEROKEE LETTER YV
1401..166C ; ALetter # Lo [620] CANADIAN SYLLABICS E..CANADIAN SYLLABICS CARRIER TTSA
-166F..1676 ; ALetter # Lo [8] CANADIAN SYLLABICS QAI..CANADIAN SYLLABICS NNGAA
+166F..167F ; ALetter # Lo [17] CANADIAN SYLLABICS QAI..CANADIAN SYLLABICS BLACKFOOT W
1681..169A ; ALetter # Lo [26] OGHAM LETTER BEITH..OGHAM LETTER PEITH
16A0..16EA ; ALetter # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X
16EE..16F0 ; ALetter # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL
@@ -421,29 +622,29 @@ FF9E..FF9F ; Katakana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWI
1843 ; ALetter # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN
1844..1877 ; ALetter # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA
1880..18A8 ; ALetter # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA
+18AA ; ALetter # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA
+18B0..18F5 ; ALetter # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S
1900..191C ; ALetter # Lo [29] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER HA
-1923..1926 ; ALetter # Mc [4] LIMBU VOWEL SIGN EE..LIMBU VOWEL SIGN AU
-1929..192B ; ALetter # Mc [3] LIMBU SUBJOINED LETTER YA..LIMBU SUBJOINED LETTER WA
-1930..1931 ; ALetter # Mc [2] LIMBU SMALL LETTER KA..LIMBU SMALL LETTER NGA
-1933..1938 ; ALetter # Mc [6] LIMBU SMALL LETTER TA..LIMBU SMALL LETTER LA
1A00..1A16 ; ALetter # Lo [23] BUGINESE LETTER KA..BUGINESE LETTER HA
-1A19..1A1B ; ALetter # Mc [3] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN AE
-1B04 ; ALetter # Mc BALINESE SIGN BISAH
1B05..1B33 ; ALetter # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA
-1B35 ; ALetter # Mc BALINESE VOWEL SIGN TEDUNG
-1B3B ; ALetter # Mc BALINESE VOWEL SIGN RA REPA TEDUNG
-1B3D..1B41 ; ALetter # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG
-1B43 ; ALetter # Mc BALINESE VOWEL SIGN PEPET TEDUNG
1B45..1B4B ; ALetter # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK
+1B83..1BA0 ; ALetter # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA
+1BAE..1BAF ; ALetter # Lo [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA
+1BBA..1BE5 ; ALetter # Lo [44] SUNDANESE AVAGRAHA..BATAK LETTER U
+1C00..1C23 ; ALetter # Lo [36] LEPCHA LETTER KA..LEPCHA LETTER A
+1C4D..1C4F ; ALetter # Lo [3] LEPCHA LETTER TTA..LEPCHA LETTER DDA
+1C5A..1C77 ; ALetter # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH
+1C78..1C7D ; ALetter # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD
+1CE9..1CEC ; ALetter # Lo [4] VEDIC SIGN ANUSVARA ANTARGOMUKHA..VEDIC SIGN ANUSVARA VAMAGOMUKHA WITH TAIL
+1CEE..1CF1 ; ALetter # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA
+1CF5..1CF6 ; ALetter # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA
1D00..1D2B ; ALetter # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL
-1D2C..1D61 ; ALetter # Lm [54] MODIFIER LETTER CAPITAL A..MODIFIER LETTER SMALL CHI
-1D62..1D77 ; ALetter # L& [22] LATIN SUBSCRIPT SMALL LETTER I..LATIN SMALL LETTER TURNED G
+1D2C..1D6A ; ALetter # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI
+1D6B..1D77 ; ALetter # L& [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G
1D78 ; ALetter # Lm MODIFIER LETTER CYRILLIC EN
1D79..1D9A ; ALetter # L& [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK
1D9B..1DBF ; ALetter # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA
-1E00..1E9B ; ALetter # L& [156] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER LONG S WITH DOT ABOVE
-1EA0..1EF9 ; ALetter # L& [90] LATIN CAPITAL LETTER A WITH DOT BELOW..LATIN SMALL LETTER Y WITH TILDE
-1F00..1F15 ; ALetter # L& [22] GREEK SMALL LETTER ALPHA WITH PSILI..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA
+1E00..1F15 ; ALetter # L& [278] LATIN CAPITAL LETTER A WITH RING BELOW..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA
1F18..1F1D ; ALetter # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA
1F20..1F45 ; ALetter # L& [38] GREEK SMALL LETTER ETA WITH PSILI..GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA
1F48..1F4D ; ALetter # L& [6] GREEK CAPITAL LETTER OMICRON WITH PSILI..GREEK CAPITAL LETTER OMICRON WITH DASIA AND OXIA
@@ -462,9 +663,9 @@ FF9E..FF9F ; Katakana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWI
1FE0..1FEC ; ALetter # L& [13] GREEK SMALL LETTER UPSILON WITH VRACHY..GREEK CAPITAL LETTER RHO WITH DASIA
1FF2..1FF4 ; ALetter # L& [3] GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI..GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI
1FF6..1FFC ; ALetter # L& [7] GREEK SMALL LETTER OMEGA WITH PERISPOMENI..GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI
-2071 ; ALetter # L& SUPERSCRIPT LATIN SMALL LETTER I
-207F ; ALetter # L& SUPERSCRIPT LATIN SMALL LETTER N
-2090..2094 ; ALetter # Lm [5] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER SCHWA
+2071 ; ALetter # Lm SUPERSCRIPT LATIN SMALL LETTER I
+207F ; ALetter # Lm SUPERSCRIPT LATIN SMALL LETTER N
+2090..209C ; ALetter # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T
2102 ; ALetter # L& DOUBLE-STRUCK CAPITAL C
2107 ; ALetter # L& EULER CONSTANT
210A..2113 ; ALetter # L& [10] SCRIPT SMALL G..SCRIPT SMALL L
@@ -482,14 +683,19 @@ FF9E..FF9F ; Katakana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWI
214E ; ALetter # L& TURNED SMALL F
2160..2182 ; ALetter # Nl [35] ROMAN NUMERAL ONE..ROMAN NUMERAL TEN THOUSAND
2183..2184 ; ALetter # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C
+2185..2188 ; ALetter # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND
24B6..24E9 ; ALetter # So [52] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN SMALL LETTER Z
2C00..2C2E ; ALetter # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
2C30..2C5E ; ALetter # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE
-2C60..2C6C ; ALetter # L& [13] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN SMALL LETTER Z WITH DESCENDER
-2C74..2C77 ; ALetter # L& [4] LATIN SMALL LETTER V WITH CURL..LATIN SMALL LETTER TAILLESS PHI
-2C80..2CE4 ; ALetter # L& [101] COPTIC CAPITAL LETTER ALFA..COPTIC SYMBOL KAI
+2C60..2C7B ; ALetter # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E
+2C7C..2C7D ; ALetter # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V
+2C7E..2CE4 ; ALetter # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI
+2CEB..2CEE ; ALetter # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA
+2CF2..2CF3 ; ALetter # L& [2] COPTIC CAPITAL LETTER BOHAIRIC KHEI..COPTIC SMALL LETTER BOHAIRIC KHEI
2D00..2D25 ; ALetter # L& [38] GEORGIAN SMALL LETTER AN..GEORGIAN SMALL LETTER HOE
-2D30..2D65 ; ALetter # Lo [54] TIFINAGH LETTER YA..TIFINAGH LETTER YAZZ
+2D27 ; ALetter # L& GEORGIAN SMALL LETTER YN
+2D2D ; ALetter # L& GEORGIAN SMALL LETTER AEN
+2D30..2D67 ; ALetter # Lo [56] TIFINAGH LETTER YA..TIFINAGH LETTER YO
2D6F ; ALetter # Lm TIFINAGH MODIFIER LETTER LABIALIZATION MARK
2D80..2D96 ; ALetter # Lo [23] ETHIOPIC SYLLABLE LOA..ETHIOPIC SYLLABLE GGWE
2DA0..2DA6 ; ALetter # Lo [7] ETHIOPIC SYLLABLE SSA..ETHIOPIC SYLLABLE SSO
@@ -500,25 +706,66 @@ FF9E..FF9F ; Katakana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWI
2DC8..2DCE ; ALetter # Lo [7] ETHIOPIC SYLLABLE KYA..ETHIOPIC SYLLABLE KYO
2DD0..2DD6 ; ALetter # Lo [7] ETHIOPIC SYLLABLE XYA..ETHIOPIC SYLLABLE XYO
2DD8..2DDE ; ALetter # Lo [7] ETHIOPIC SYLLABLE GYA..ETHIOPIC SYLLABLE GYO
+2E2F ; ALetter # Lm VERTICAL TILDE
3005 ; ALetter # Lm IDEOGRAPHIC ITERATION MARK
303B ; ALetter # Lm VERTICAL IDEOGRAPHIC ITERATION MARK
303C ; ALetter # Lo MASU MARK
-3105..312C ; ALetter # Lo [40] BOPOMOFO LETTER B..BOPOMOFO LETTER GN
+3105..312D ; ALetter # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH
3131..318E ; ALetter # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE
-31A0..31B7 ; ALetter # Lo [24] BOPOMOFO LETTER BU..BOPOMOFO FINAL LETTER H
+31A0..31BA ; ALetter # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY
A000..A014 ; ALetter # Lo [21] YI SYLLABLE IT..YI SYLLABLE E
A015 ; ALetter # Lm YI SYLLABLE WU
A016..A48C ; ALetter # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR
-A717..A71A ; ALetter # Lm [4] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOWER RIGHT CORNER ANGLE
-A800..A801 ; ALetter # Lo [2] SYLOTI NAGRI LETTER A..SYLOTI NAGRI LETTER I
+A4D0..A4F7 ; ALetter # Lo [40] LISU LETTER BA..LISU LETTER OE
+A4F8..A4FD ; ALetter # Lm [6] LISU LETTER TONE MYA TI..LISU LETTER TONE MYA JEU
+A500..A60B ; ALetter # Lo [268] VAI SYLLABLE EE..VAI SYLLABLE NG
+A60C ; ALetter # Lm VAI SYLLABLE LENGTHENER
+A610..A61F ; ALetter # Lo [16] VAI SYLLABLE NDOLE FA..VAI SYMBOL JONG
+A62A..A62B ; ALetter # Lo [2] VAI SYLLABLE NDOLE MA..VAI SYLLABLE NDOLE DO
+A640..A66D ; ALetter # L& [46] CYRILLIC CAPITAL LETTER ZEMLYA..CYRILLIC SMALL LETTER DOUBLE MONOCULAR O
+A66E ; ALetter # Lo CYRILLIC LETTER MULTIOCULAR O
+A67F ; ALetter # Lm CYRILLIC PAYEROK
+A680..A697 ; ALetter # L& [24] CYRILLIC CAPITAL LETTER DWE..CYRILLIC SMALL LETTER SHWE
+A6A0..A6E5 ; ALetter # Lo [70] BAMUM LETTER A..BAMUM LETTER KI
+A6E6..A6EF ; ALetter # Nl [10] BAMUM LETTER MO..BAMUM LETTER KOGHOM
+A717..A71F ; ALetter # Lm [9] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOW INVERTED EXCLAMATION MARK
+A722..A76F ; ALetter # L& [78] LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF..LATIN SMALL LETTER CON
+A770 ; ALetter # Lm MODIFIER LETTER US
+A771..A787 ; ALetter # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T
+A788 ; ALetter # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT
+A78B..A78E ; ALetter # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
+A790..A793 ; ALetter # L& [4] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER C WITH BAR
+A7A0..A7AA ; ALetter # L& [11] LATIN CAPITAL LETTER G WITH OBLIQUE STROKE..LATIN CAPITAL LETTER H WITH HOOK
+A7F8..A7F9 ; ALetter # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
+A7FA ; ALetter # L& LATIN LETTER SMALL CAPITAL TURNED M
+A7FB..A801 ; ALetter # Lo [7] LATIN EPIGRAPHIC LETTER REVERSED F..SYLOTI NAGRI LETTER I
A803..A805 ; ALetter # Lo [3] SYLOTI NAGRI LETTER U..SYLOTI NAGRI LETTER O
A807..A80A ; ALetter # Lo [4] SYLOTI NAGRI LETTER KO..SYLOTI NAGRI LETTER GHO
A80C..A822 ; ALetter # Lo [23] SYLOTI NAGRI LETTER CO..SYLOTI NAGRI LETTER HO
-A823..A824 ; ALetter # Mc [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIGN I
-A827 ; ALetter # Mc SYLOTI NAGRI VOWEL SIGN OO
A840..A873 ; ALetter # Lo [52] PHAGS-PA LETTER KA..PHAGS-PA LETTER CANDRABINDU
+A882..A8B3 ; ALetter # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA
+A8F2..A8F7 ; ALetter # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA
+A8FB ; ALetter # Lo DEVANAGARI HEADSTROKE
+A90A..A925 ; ALetter # Lo [28] KAYAH LI LETTER KA..KAYAH LI LETTER OO
+A930..A946 ; ALetter # Lo [23] REJANG LETTER KA..REJANG LETTER A
+A960..A97C ; ALetter # Lo [29] HANGUL CHOSEONG TIKEUT-MIEUM..HANGUL CHOSEONG SSANGYEORINHIEUH
+A984..A9B2 ; ALetter # Lo [47] JAVANESE LETTER A..JAVANESE LETTER HA
+A9CF ; ALetter # Lm JAVANESE PANGRANGKEP
+AA00..AA28 ; ALetter # Lo [41] CHAM LETTER A..CHAM LETTER HA
+AA40..AA42 ; ALetter # Lo [3] CHAM LETTER FINAL K..CHAM LETTER FINAL NG
+AA44..AA4B ; ALetter # Lo [8] CHAM LETTER FINAL CH..CHAM LETTER FINAL SS
+AAE0..AAEA ; ALetter # Lo [11] MEETEI MAYEK LETTER E..MEETEI MAYEK LETTER SSA
+AAF2 ; ALetter # Lo MEETEI MAYEK ANJI
+AAF3..AAF4 ; ALetter # Lm [2] MEETEI MAYEK SYLLABLE REPETITION MARK..MEETEI MAYEK WORD REPETITION MARK
+AB01..AB06 ; ALetter # Lo [6] ETHIOPIC SYLLABLE TTHU..ETHIOPIC SYLLABLE TTHO
+AB09..AB0E ; ALetter # Lo [6] ETHIOPIC SYLLABLE DDHU..ETHIOPIC SYLLABLE DDHO
+AB11..AB16 ; ALetter # Lo [6] ETHIOPIC SYLLABLE DZU..ETHIOPIC SYLLABLE DZO
+AB20..AB26 ; ALetter # Lo [7] ETHIOPIC SYLLABLE CCHHA..ETHIOPIC SYLLABLE CCHHO
+AB28..AB2E ; ALetter # Lo [7] ETHIOPIC SYLLABLE BBA..ETHIOPIC SYLLABLE BBO
+ABC0..ABE2 ; ALetter # Lo [35] MEETEI MAYEK LETTER KOK..MEETEI MAYEK LETTER I LONSUM
AC00..D7A3 ; ALetter # Lo [11172] HANGUL SYLLABLE GA..HANGUL SYLLABLE HIH
-FA30..FA6A ; ALetter # Lo [59] CJK COMPATIBILITY IDEOGRAPH-FA30..CJK COMPATIBILITY IDEOGRAPH-FA6A
+D7B0..D7C6 ; ALetter # Lo [23] HANGUL JUNGSEONG O-YEO..HANGUL JUNGSEONG ARAEA-E
+D7CB..D7FB ; ALetter # Lo [49] HANGUL JONGSEONG NIEUN-RIEUL..HANGUL JONGSEONG PHIEUPH-THIEUTH
FB00..FB06 ; ALetter # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST
FB13..FB17 ; ALetter # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH
FB1D ; ALetter # Lo HEBREW LETTER YOD WITH HIRIQ
@@ -550,6 +797,8 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
10050..1005D ; ALetter # Lo [14] LINEAR B SYMBOL B018..LINEAR B SYMBOL B089
10080..100FA ; ALetter # Lo [123] LINEAR B IDEOGRAM B100 MAN..LINEAR B IDEOGRAM VESSEL B305
10140..10174 ; ALetter # Nl [53] GREEK ACROPHONIC ATTIC ONE QUARTER..GREEK ACROPHONIC STRATIAN FIFTY MNAS
+10280..1029C ; ALetter # Lo [29] LYCIAN LETTER A..LYCIAN LETTER X
+102A0..102D0 ; ALetter # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3
10300..1031E ; ALetter # Lo [31] OLD ITALIC LETTER A..OLD ITALIC LETTER UU
10330..10340 ; ALetter # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA
10341 ; ALetter # Nl GOTHIC LETTER NINETY
@@ -566,14 +815,34 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
1080A..10835 ; ALetter # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO
10837..10838 ; ALetter # Lo [2] CYPRIOT SYLLABLE XA..CYPRIOT SYLLABLE XE
1083C ; ALetter # Lo CYPRIOT SYLLABLE ZA
-1083F ; ALetter # Lo CYPRIOT SYLLABLE ZO
+1083F..10855 ; ALetter # Lo [23] CYPRIOT SYLLABLE ZO..IMPERIAL ARAMAIC LETTER TAW
10900..10915 ; ALetter # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU
+10920..10939 ; ALetter # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C
+10980..109B7 ; ALetter # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA
+109BE..109BF ; ALetter # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN
10A00 ; ALetter # Lo KHAROSHTHI LETTER A
10A10..10A13 ; ALetter # Lo [4] KHAROSHTHI LETTER KA..KHAROSHTHI LETTER GHA
10A15..10A17 ; ALetter # Lo [3] KHAROSHTHI LETTER CA..KHAROSHTHI LETTER JA
10A19..10A33 ; ALetter # Lo [27] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER TTTHA
+10A60..10A7C ; ALetter # Lo [29] OLD SOUTH ARABIAN LETTER HE..OLD SOUTH ARABIAN LETTER THETH
+10B00..10B35 ; ALetter # Lo [54] AVESTAN LETTER A..AVESTAN LETTER HE
+10B40..10B55 ; ALetter # Lo [22] INSCRIPTIONAL PARTHIAN LETTER ALEPH..INSCRIPTIONAL PARTHIAN LETTER TAW
+10B60..10B72 ; ALetter # Lo [19] INSCRIPTIONAL PAHLAVI LETTER ALEPH..INSCRIPTIONAL PAHLAVI LETTER TAW
+10C00..10C48 ; ALetter # Lo [73] OLD TURKIC LETTER ORKHON A..OLD TURKIC LETTER ORKHON BASH
+11003..11037 ; ALetter # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA
+11083..110AF ; ALetter # Lo [45] KAITHI LETTER A..KAITHI LETTER HA
+110D0..110E8 ; ALetter # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE
+11103..11126 ; ALetter # Lo [36] CHAKMA LETTER AA..CHAKMA LETTER HAA
+11183..111B2 ; ALetter # Lo [48] SHARADA LETTER A..SHARADA LETTER HA
+111C1..111C4 ; ALetter # Lo [4] SHARADA SIGN AVAGRAHA..SHARADA OM
+11680..116AA ; ALetter # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA
12000..1236E ; ALetter # Lo [879] CUNEIFORM SIGN A..CUNEIFORM SIGN ZUM
12400..12462 ; ALetter # Nl [99] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN OLD ASSYRIAN ONE QUARTER
+13000..1342E ; ALetter # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
+16800..16A38 ; ALetter # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ
+16F00..16F44 ; ALetter # Lo [69] MIAO LETTER PA..MIAO LETTER HHA
+16F50 ; ALetter # Lo MIAO LETTER NASALIZATION
+16F93..16F9F ; ALetter # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8
1D400..1D454 ; ALetter # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G
1D456..1D49C ; ALetter # L& [71] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL SCRIPT CAPITAL A
1D49E..1D49F ; ALetter # L& [2] MATHEMATICAL SCRIPT CAPITAL C..MATHEMATICAL SCRIPT CAPITAL D
@@ -604,40 +873,92 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
1D78A..1D7A8 ; ALetter # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA
1D7AA..1D7C2 ; ALetter # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA
1D7C4..1D7CB ; ALetter # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA
+1EE00..1EE03 ; ALetter # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL
+1EE05..1EE1F ; ALetter # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF
+1EE21..1EE22 ; ALetter # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM
+1EE24 ; ALetter # Lo ARABIC MATHEMATICAL INITIAL HEH
+1EE27 ; ALetter # Lo ARABIC MATHEMATICAL INITIAL HAH
+1EE29..1EE32 ; ALetter # Lo [10] ARABIC MATHEMATICAL INITIAL YEH..ARABIC MATHEMATICAL INITIAL QAF
+1EE34..1EE37 ; ALetter # Lo [4] ARABIC MATHEMATICAL INITIAL SHEEN..ARABIC MATHEMATICAL INITIAL KHAH
+1EE39 ; ALetter # Lo ARABIC MATHEMATICAL INITIAL DAD
+1EE3B ; ALetter # Lo ARABIC MATHEMATICAL INITIAL GHAIN
+1EE42 ; ALetter # Lo ARABIC MATHEMATICAL TAILED JEEM
+1EE47 ; ALetter # Lo ARABIC MATHEMATICAL TAILED HAH
+1EE49 ; ALetter # Lo ARABIC MATHEMATICAL TAILED YEH
+1EE4B ; ALetter # Lo ARABIC MATHEMATICAL TAILED LAM
+1EE4D..1EE4F ; ALetter # Lo [3] ARABIC MATHEMATICAL TAILED NOON..ARABIC MATHEMATICAL TAILED AIN
+1EE51..1EE52 ; ALetter # Lo [2] ARABIC MATHEMATICAL TAILED SAD..ARABIC MATHEMATICAL TAILED QAF
+1EE54 ; ALetter # Lo ARABIC MATHEMATICAL TAILED SHEEN
+1EE57 ; ALetter # Lo ARABIC MATHEMATICAL TAILED KHAH
+1EE59 ; ALetter # Lo ARABIC MATHEMATICAL TAILED DAD
+1EE5B ; ALetter # Lo ARABIC MATHEMATICAL TAILED GHAIN
+1EE5D ; ALetter # Lo ARABIC MATHEMATICAL TAILED DOTLESS NOON
+1EE5F ; ALetter # Lo ARABIC MATHEMATICAL TAILED DOTLESS QAF
+1EE61..1EE62 ; ALetter # Lo [2] ARABIC MATHEMATICAL STRETCHED BEH..ARABIC MATHEMATICAL STRETCHED JEEM
+1EE64 ; ALetter # Lo ARABIC MATHEMATICAL STRETCHED HEH
+1EE67..1EE6A ; ALetter # Lo [4] ARABIC MATHEMATICAL STRETCHED HAH..ARABIC MATHEMATICAL STRETCHED KAF
+1EE6C..1EE72 ; ALetter # Lo [7] ARABIC MATHEMATICAL STRETCHED MEEM..ARABIC MATHEMATICAL STRETCHED QAF
+1EE74..1EE77 ; ALetter # Lo [4] ARABIC MATHEMATICAL STRETCHED SHEEN..ARABIC MATHEMATICAL STRETCHED KHAH
+1EE79..1EE7C ; ALetter # Lo [4] ARABIC MATHEMATICAL STRETCHED DAD..ARABIC MATHEMATICAL STRETCHED DOTLESS BEH
+1EE7E ; ALetter # Lo ARABIC MATHEMATICAL STRETCHED DOTLESS FEH
+1EE80..1EE89 ; ALetter # Lo [10] ARABIC MATHEMATICAL LOOPED ALEF..ARABIC MATHEMATICAL LOOPED YEH
+1EE8B..1EE9B ; ALetter # Lo [17] ARABIC MATHEMATICAL LOOPED LAM..ARABIC MATHEMATICAL LOOPED GHAIN
+1EEA1..1EEA3 ; ALetter # Lo [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL
+1EEA5..1EEA9 ; ALetter # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH
+1EEAB..1EEBB ; ALetter # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
-# Total code points: 21149
+# Total code points: 24941
# ================================================
-0027 ; MidLetter # Po APOSTROPHE
003A ; MidLetter # Po COLON
00B7 ; MidLetter # Po MIDDLE DOT
+0387 ; MidLetter # Po GREEK ANO TELEIA
05F4 ; MidLetter # Po HEBREW PUNCTUATION GERSHAYIM
-2019 ; MidLetter # Pf RIGHT SINGLE QUOTATION MARK
2027 ; MidLetter # Po HYPHENATION POINT
+FE13 ; MidLetter # Po PRESENTATION FORM FOR VERTICAL COLON
+FE55 ; MidLetter # Po SMALL COLON
+FF1A ; MidLetter # Po FULLWIDTH COLON
-# Total code points: 6
+# Total code points: 8
# ================================================
002C ; MidNum # Po COMMA
-002E ; MidNum # Po FULL STOP
003B ; MidNum # Po SEMICOLON
037E ; MidNum # Po GREEK QUESTION MARK
0589 ; MidNum # Po ARMENIAN FULL STOP
-060D ; MidNum # Po ARABIC DATE SEPARATOR
+060C..060D ; MidNum # Po [2] ARABIC COMMA..ARABIC DATE SEPARATOR
+066C ; MidNum # Po ARABIC THOUSANDS SEPARATOR
07F8 ; MidNum # Po NKO COMMA
2044 ; MidNum # Sm FRACTION SLASH
FE10 ; MidNum # Po PRESENTATION FORM FOR VERTICAL COMMA
-FE13..FE14 ; MidNum # Po [2] PRESENTATION FORM FOR VERTICAL COLON..PRESENTATION FORM FOR VERTICAL SEMICOLON
+FE14 ; MidNum # Po PRESENTATION FORM FOR VERTICAL SEMICOLON
+FE50 ; MidNum # Po SMALL COMMA
+FE54 ; MidNum # Po SMALL SEMICOLON
+FF0C ; MidNum # Po FULLWIDTH COMMA
+FF1B ; MidNum # Po FULLWIDTH SEMICOLON
+
+# Total code points: 15
+
+# ================================================
+
+0027 ; MidNumLet # Po APOSTROPHE
+002E ; MidNumLet # Po FULL STOP
+2018 ; MidNumLet # Pi LEFT SINGLE QUOTATION MARK
+2019 ; MidNumLet # Pf RIGHT SINGLE QUOTATION MARK
+2024 ; MidNumLet # Po ONE DOT LEADER
+FE52 ; MidNumLet # Po SMALL FULL STOP
+FF07 ; MidNumLet # Po FULLWIDTH APOSTROPHE
+FF0E ; MidNumLet # Po FULLWIDTH FULL STOP
-# Total code points: 11
+# Total code points: 8
# ================================================
0030..0039 ; Numeric # Nd [10] DIGIT ZERO..DIGIT NINE
0660..0669 ; Numeric # Nd [10] ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE
-066B..066C ; Numeric # Po [2] ARABIC DECIMAL SEPARATOR..ARABIC THOUSANDS SEPARATOR
+066B ; Numeric # Po ARABIC DECIMAL SEPARATOR
06F0..06F9 ; Numeric # Nd [10] EXTENDED ARABIC-INDIC DIGIT ZERO..EXTENDED ARABIC-INDIC DIGIT NINE
07C0..07C9 ; Numeric # Nd [10] NKO DIGIT ZERO..NKO DIGIT NINE
0966..096F ; Numeric # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE
@@ -653,15 +974,32 @@ FE13..FE14 ; MidNum # Po [2] PRESENTATION FORM FOR VERTICAL COLON..PRESENTA
0ED0..0ED9 ; Numeric # Nd [10] LAO DIGIT ZERO..LAO DIGIT NINE
0F20..0F29 ; Numeric # Nd [10] TIBETAN DIGIT ZERO..TIBETAN DIGIT NINE
1040..1049 ; Numeric # Nd [10] MYANMAR DIGIT ZERO..MYANMAR DIGIT NINE
+1090..1099 ; Numeric # Nd [10] MYANMAR SHAN DIGIT ZERO..MYANMAR SHAN DIGIT NINE
17E0..17E9 ; Numeric # Nd [10] KHMER DIGIT ZERO..KHMER DIGIT NINE
1810..1819 ; Numeric # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE
1946..194F ; Numeric # Nd [10] LIMBU DIGIT ZERO..LIMBU DIGIT NINE
19D0..19D9 ; Numeric # Nd [10] NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE
+1A80..1A89 ; Numeric # Nd [10] TAI THAM HORA DIGIT ZERO..TAI THAM HORA DIGIT NINE
+1A90..1A99 ; Numeric # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE
1B50..1B59 ; Numeric # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE
+1BB0..1BB9 ; Numeric # Nd [10] SUNDANESE DIGIT ZERO..SUNDANESE DIGIT NINE
+1C40..1C49 ; Numeric # Nd [10] LEPCHA DIGIT ZERO..LEPCHA DIGIT NINE
+1C50..1C59 ; Numeric # Nd [10] OL CHIKI DIGIT ZERO..OL CHIKI DIGIT NINE
+A620..A629 ; Numeric # Nd [10] VAI DIGIT ZERO..VAI DIGIT NINE
+A8D0..A8D9 ; Numeric # Nd [10] SAURASHTRA DIGIT ZERO..SAURASHTRA DIGIT NINE
+A900..A909 ; Numeric # Nd [10] KAYAH LI DIGIT ZERO..KAYAH LI DIGIT NINE
+A9D0..A9D9 ; Numeric # Nd [10] JAVANESE DIGIT ZERO..JAVANESE DIGIT NINE
+AA50..AA59 ; Numeric # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE
+ABF0..ABF9 ; Numeric # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE
104A0..104A9 ; Numeric # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE
+11066..1106F ; Numeric # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE
+110F0..110F9 ; Numeric # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE
+11136..1113F ; Numeric # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE
+111D0..111D9 ; Numeric # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE
+116C0..116C9 ; Numeric # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE
1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
-# Total code points: 282
+# Total code points: 451
# ================================================