summaryrefslogtreecommitdiffstats
path: root/util/unicode/data/SentenceBreakProperty.txt
diff options
context:
space:
mode:
Diffstat (limited to 'util/unicode/data/SentenceBreakProperty.txt')
-rw-r--r--util/unicode/data/SentenceBreakProperty.txt90
1 files changed, 65 insertions, 25 deletions
diff --git a/util/unicode/data/SentenceBreakProperty.txt b/util/unicode/data/SentenceBreakProperty.txt
index 19752103f9..8dd1abff0f 100644
--- a/util/unicode/data/SentenceBreakProperty.txt
+++ b/util/unicode/data/SentenceBreakProperty.txt
@@ -1,8 +1,8 @@
-# SentenceBreakProperty-7.0.0.txt
-# Date: 2014-02-19, 15:51:38 GMT [MD]
+# SentenceBreakProperty-8.0.0.txt
+# Date: 2015-03-11, 22:29:43 GMT [MD]
#
# Unicode Character Database
-# Copyright (c) 1991-2014 Unicode, Inc.
+# Copyright (c) 1991-2015 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
@@ -53,7 +53,7 @@
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..0902 ; Extend # Mn [31] ARABIC CURLY FATHA..DEVANAGARI SIGN ANUSVARA
+08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA
0903 ; Extend # Mc DEVANAGARI SIGN VISARGA
093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE
093B ; Extend # Mc DEVANAGARI VOWEL SIGN OOE
@@ -216,8 +216,6 @@
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..1A1A ; Extend # Mc [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O
1A1B ; Extend # Mn BUGINESE VOWEL SIGN AE
@@ -291,7 +289,7 @@
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
+A69E..A69F ; Extend # Mn [2] COMBINING CYRILLIC LETTER EF..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
@@ -345,7 +343,7 @@ 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..FE2D ; Extend # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON BELOW
+FE20..FE2F ; Extend # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF
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
102E0 ; Extend # Mn COPTIC EPACT THOUSANDS MARK
@@ -376,6 +374,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
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
+111CA..111CC ; Extend # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK
1122C..1122E ; Extend # Mc [3] KHOJKI VOWEL SIGN AA..KHOJKI VOWEL SIGN II
1122F..11231 ; Extend # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI
11232..11233 ; Extend # Mc [2] KHOJKI VOWEL SIGN O..KHOJKI VOWEL SIGN AU
@@ -385,7 +384,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
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
-11301 ; Extend # Mn GRANTHA SIGN CANDRABINDU
+11300..11301 ; Extend # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
11302..11303 ; Extend # Mc [2] GRANTHA SIGN ANUSVARA..GRANTHA SIGN VISARGA
1133C ; Extend # Mn GRANTHA SIGN NUKTA
1133E..1133F ; Extend # Mc [2] GRANTHA VOWEL SIGN AA..GRANTHA VOWEL SIGN I
@@ -411,6 +410,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
115BC..115BD ; Extend # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA
115BE ; Extend # Mc SIDDHAM SIGN VISARGA
115BF..115C0 ; Extend # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA
+115DC..115DD ; Extend # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU
11630..11632 ; Extend # Mc [3] MODI VOWEL SIGN AA..MODI VOWEL SIGN II
11633..1163A ; Extend # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI
1163B..1163C ; Extend # Mc [2] MODI VOWEL SIGN O..MODI VOWEL SIGN AU
@@ -424,6 +424,11 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
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
+1171D..1171F ; Extend # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA
+11720..11721 ; Extend # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA
+11722..11725 ; Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
+11726 ; Extend # Mc AHOM VOWEL SIGN E
+11727..1172B ; Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER
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
16F51..16F7E ; Extend # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
@@ -436,10 +441,16 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
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
+1DA00..1DA36 ; Extend # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN
+1DA3B..1DA6C ; Extend # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT
+1DA75 ; Extend # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS
+1DA84 ; Extend # Mn SIGNWRITING LOCATION HEAD NECK
+1DA9B..1DA9F ; Extend # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6
+1DAA1..1DAAF ; Extend # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16
1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
-# Total code points: 1834
+# Total code points: 1967
# ================================================
@@ -764,6 +775,7 @@ E0020..E007F ; Format # Cf [96] TAG SPACE..CANCEL TAG
052D ; Lower # L& CYRILLIC SMALL LETTER DCHE
052F ; Lower # L& CYRILLIC SMALL LETTER EL WITH DESCENDER
0561..0587 ; Lower # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN
+13F8..13FD ; Lower # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV
1D00..1D2B ; Lower # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL
1D2C..1D6A ; Lower # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI
1D6B..1D77 ; Lower # L& [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G
@@ -1094,15 +1106,19 @@ A7A3 ; Lower # L& LATIN SMALL LETTER K WITH OBLIQUE STROKE
A7A5 ; Lower # L& LATIN SMALL LETTER N WITH OBLIQUE STROKE
A7A7 ; Lower # L& LATIN SMALL LETTER R WITH OBLIQUE STROKE
A7A9 ; Lower # L& LATIN SMALL LETTER S WITH OBLIQUE STROKE
+A7B5 ; Lower # L& LATIN SMALL LETTER BETA
+A7B7 ; Lower # L& LATIN SMALL LETTER OMEGA
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
-AB64..AB65 ; Lower # L& [2] LATIN SMALL LETTER INVERTED ALPHA..GREEK LETTER SMALL CAPITAL OMEGA
+AB60..AB65 ; Lower # L& [6] LATIN SMALL LETTER SAKHA YAT..GREEK LETTER SMALL CAPITAL OMEGA
+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
FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z
10428..1044F ; Lower # L& [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW
+10CC0..10CF2 ; Lower # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US
118C0..118DF ; Lower # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO
1D41A..1D433 ; Lower # L& [26] MATHEMATICAL BOLD SMALL A..MATHEMATICAL BOLD SMALL Z
1D44E..1D454 ; Lower # L& [7] MATHEMATICAL ITALIC SMALL A..MATHEMATICAL ITALIC SMALL G
@@ -1133,7 +1149,7 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN
1D7C4..1D7C9 ; Lower # L& [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL
1D7CB ; Lower # L& MATHEMATICAL BOLD SMALL DIGAMMA
-# Total code points: 2029
+# Total code points: 2172
# ================================================
@@ -1412,6 +1428,7 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN
10A0..10C5 ; Upper # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE
10C7 ; Upper # L& GEORGIAN CAPITAL LETTER YN
10CD ; Upper # L& GEORGIAN CAPITAL LETTER AEN
+13A0..13F5 ; Upper # L& [86] CHEROKEE LETTER A..CHEROKEE LETTER MV
1E00 ; Upper # L& LATIN CAPITAL LETTER A WITH RING BELOW
1E02 ; Upper # L& LATIN CAPITAL LETTER B WITH DOT ABOVE
1E04 ; Upper # L& LATIN CAPITAL LETTER B WITH DOT BELOW
@@ -1729,9 +1746,11 @@ A7A4 ; Upper # L& LATIN CAPITAL LETTER N WITH OBLIQUE STROKE
A7A6 ; Upper # L& LATIN CAPITAL LETTER R WITH OBLIQUE STROKE
A7A8 ; Upper # L& LATIN CAPITAL LETTER S WITH OBLIQUE STROKE
A7AA..A7AD ; Upper # L& [4] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER L WITH BELT
-A7B0..A7B1 ; Upper # L& [2] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER TURNED T
+A7B0..A7B4 ; Upper # L& [5] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER BETA
+A7B6 ; Upper # L& LATIN CAPITAL LETTER OMEGA
FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z
10400..10427 ; Upper # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW
+10C80..10CB2 ; Upper # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US
118A0..118BF ; Upper # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO
1D400..1D419 ; Upper # L& [26] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL BOLD CAPITAL Z
1D434..1D44D ; Upper # L& [26] MATHEMATICAL ITALIC CAPITAL A..MATHEMATICAL ITALIC CAPITAL Z
@@ -1768,7 +1787,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
1F150..1F169 ; Upper # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
1F170..1F189 ; Upper # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z
-# Total code points: 1641
+# Total code points: 1782
# ================================================
@@ -1806,7 +1825,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
0824 ; OLetter # Lm SAMARITAN MODIFIER LETTER SHORT A
0828 ; OLetter # Lm SAMARITAN MODIFIER LETTER I
0840..0858 ; OLetter # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN
-08A0..08B2 ; OLetter # Lo [19] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE
+08A0..08B4 ; OLetter # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
0904..0939 ; OLetter # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA
093D ; OLetter # Lo DEVANAGARI SIGN AVAGRAHA
0950 ; OLetter # Lo DEVANAGARI OM
@@ -1843,6 +1862,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
0ABD ; OLetter # Lo GUJARATI SIGN AVAGRAHA
0AD0 ; OLetter # Lo GUJARATI OM
0AE0..0AE1 ; OLetter # Lo [2] GUJARATI LETTER VOCALIC RR..GUJARATI LETTER VOCALIC LL
+0AF9 ; OLetter # Lo GUJARATI LETTER ZHA
0B05..0B0C ; OLetter # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L
0B0F..0B10 ; OLetter # Lo [2] ORIYA LETTER E..ORIYA LETTER AI
0B13..0B28 ; OLetter # Lo [22] ORIYA LETTER O..ORIYA LETTER NA
@@ -1869,7 +1889,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
0C12..0C28 ; OLetter # Lo [23] TELUGU LETTER O..TELUGU LETTER NA
0C2A..0C39 ; OLetter # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA
0C3D ; OLetter # Lo TELUGU SIGN AVAGRAHA
-0C58..0C59 ; OLetter # Lo [2] TELUGU LETTER TSA..TELUGU LETTER DZA
+0C58..0C5A ; OLetter # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA
0C60..0C61 ; OLetter # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL
0C85..0C8C ; OLetter # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L
0C8E..0C90 ; OLetter # Lo [3] KANNADA LETTER E..KANNADA LETTER AI
@@ -1885,7 +1905,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
0D12..0D3A ; OLetter # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA
0D3D ; OLetter # Lo MALAYALAM SIGN AVAGRAHA
0D4E ; OLetter # Lo MALAYALAM LETTER DOT REPH
-0D60..0D61 ; OLetter # Lo [2] MALAYALAM LETTER VOCALIC RR..MALAYALAM LETTER VOCALIC LL
+0D5F..0D61 ; OLetter # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL
0D7A..0D7F ; OLetter # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K
0D85..0D96 ; OLetter # Lo [18] SINHALA LETTER AYANNA..SINHALA LETTER AUYANNA
0D9A..0DB1 ; OLetter # Lo [24] SINHALA LETTER ALPAPRAANA KAYANNA..SINHALA LETTER DANTAJA NAYANNA
@@ -1945,7 +1965,6 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
1312..1315 ; OLetter # Lo [4] ETHIOPIC SYLLABLE GWI..ETHIOPIC SYLLABLE GWE
1318..135A ; OLetter # Lo [67] ETHIOPIC SYLLABLE GGA..ETHIOPIC SYLLABLE FYA
1380..138F ; OLetter # Lo [16] ETHIOPIC SYLLABLE SEBATBEIT MWA..ETHIOPIC SYLLABLE PWE
-13A0..13F4 ; OLetter # Lo [85] CHEROKEE LETTER A..CHEROKEE LETTER YV
1401..166C ; OLetter # Lo [620] CANADIAN SYLLABICS E..CANADIAN SYLLABICS CARRIER TTSA
166F..167F ; OLetter # Lo [17] CANADIAN SYLLABICS QAI..CANADIAN SYLLABICS BLACKFOOT W
1681..169A ; OLetter # Lo [26] OGHAM LETTER BEITH..OGHAM LETTER PEITH
@@ -1971,7 +1990,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
1950..196D ; OLetter # Lo [30] TAI LE LETTER KA..TAI LE LETTER AI
1970..1974 ; OLetter # Lo [5] TAI LE LETTER TONE-2..TAI LE LETTER TONE-6
1980..19AB ; OLetter # Lo [44] NEW TAI LUE LETTER HIGH QA..NEW TAI LUE LETTER LOW SUA
-19C1..19C7 ; OLetter # Lo [7] NEW TAI LUE LETTER FINAL V..NEW TAI LUE LETTER FINAL B
+19B0..19C9 ; OLetter # Lo [26] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2
1A00..1A16 ; OLetter # Lo [23] BUGINESE LETTER KA..BUGINESE LETTER HA
1A20..1A54 ; OLetter # Lo [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA
1AA7 ; OLetter # Lm TAI THAM SIGN MAI YAMOK
@@ -2021,7 +2040,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
31A0..31BA ; OLetter # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY
31F0..31FF ; OLetter # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO
3400..4DB5 ; OLetter # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
-4E00..9FCC ; OLetter # Lo [20941] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCC
+4E00..9FD5 ; OLetter # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
A000..A014 ; OLetter # Lo [21] YI SYLLABLE IT..YI SYLLABLE E
A015 ; OLetter # Lm YI SYLLABLE WU
A016..A48C ; OLetter # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR
@@ -2037,6 +2056,7 @@ A6A0..A6E5 ; OLetter # Lo [70] BAMUM LETTER A..BAMUM LETTER KI
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
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
@@ -2046,6 +2066,7 @@ A840..A873 ; OLetter # Lo [52] PHAGS-PA LETTER KA..PHAGS-PA LETTER CANDRABIN
A882..A8B3 ; OLetter # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA
A8F2..A8F7 ; OLetter # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA
A8FB ; OLetter # Lo DEVANAGARI HEADSTROKE
+A8FD ; OLetter # Lo DEVANAGARI JAIN OM
A90A..A925 ; OLetter # Lo [28] KAYAH LI LETTER KA..KAYAH LI LETTER OO
A930..A946 ; OLetter # Lo [23] REJANG LETTER KA..REJANG LETTER A
A960..A97C ; OLetter # Lo [29] HANGUL CHOSEONG TIKEUT-MIEUM..HANGUL CHOSEONG SSANGYEORINHIEUH
@@ -2140,6 +2161,8 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
1083F..10855 ; OLetter # Lo [23] CYPRIOT SYLLABLE ZO..IMPERIAL ARAMAIC LETTER TAW
10860..10876 ; OLetter # Lo [23] PALMYRENE LETTER ALEPH..PALMYRENE LETTER TAW
10880..1089E ; OLetter # Lo [31] NABATAEAN LETTER FINAL ALEPH..NABATAEAN LETTER TAW
+108E0..108F2 ; OLetter # Lo [19] HATRAN LETTER ALEPH..HATRAN LETTER QOPH
+108F4..108F5 ; OLetter # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW
10900..10915 ; OLetter # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU
10920..10939 ; OLetter # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C
10980..109B7 ; OLetter # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA
@@ -2166,8 +2189,14 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
11183..111B2 ; OLetter # Lo [48] SHARADA LETTER A..SHARADA LETTER HA
111C1..111C4 ; OLetter # Lo [4] SHARADA SIGN AVAGRAHA..SHARADA OM
111DA ; OLetter # Lo SHARADA EKAM
+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
+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
+1128F..1129D ; OLetter # Lo [15] MULTANI LETTER NYA..MULTANI LETTER BA
+1129F..112A8 ; OLetter # Lo [10] MULTANI LETTER BHA..MULTANI LETTER RHA
112B0..112DE ; OLetter # Lo [47] KHUDAWADI LETTER A..KHUDAWADI LETTER HA
11305..1130C ; OLetter # Lo [8] GRANTHA LETTER A..GRANTHA LETTER VOCALIC L
1130F..11310 ; OLetter # Lo [2] GRANTHA LETTER EE..GRANTHA LETTER AI
@@ -2176,19 +2205,24 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
11332..11333 ; OLetter # Lo [2] GRANTHA LETTER LA..GRANTHA LETTER LLA
11335..11339 ; OLetter # Lo [5] GRANTHA LETTER VA..GRANTHA LETTER HA
1133D ; OLetter # Lo GRANTHA SIGN AVAGRAHA
+11350 ; OLetter # Lo GRANTHA OM
1135D..11361 ; OLetter # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL
11480..114AF ; OLetter # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA
114C4..114C5 ; OLetter # Lo [2] TIRHUTA SIGN AVAGRAHA..TIRHUTA GVANG
114C7 ; OLetter # Lo TIRHUTA OM
11580..115AE ; OLetter # Lo [47] SIDDHAM LETTER A..SIDDHAM LETTER HA
+115D8..115DB ; OLetter # Lo [4] SIDDHAM LETTER THREE-CIRCLE ALTERNATE I..SIDDHAM LETTER ALTERNATE U
11600..1162F ; OLetter # Lo [48] MODI LETTER A..MODI LETTER LLA
11644 ; OLetter # Lo MODI SIGN HUVA
11680..116AA ; OLetter # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA
+11700..11719 ; OLetter # Lo [26] AHOM LETTER KA..AHOM LETTER JHA
118FF ; OLetter # Lo WARANG CITI OM
11AC0..11AF8 ; OLetter # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
-12000..12398 ; OLetter # Lo [921] CUNEIFORM SIGN A..CUNEIFORM SIGN UM TIMES ME
+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
13000..1342E ; OLetter # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
+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
16AD0..16AED ; OLetter # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I
@@ -2241,9 +2275,10 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
20000..2A6D6 ; OLetter # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
2A700..2B734 ; OLetter # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
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
2F800..2FA1D ; OLetter # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
-# Total code points: 99420
+# Total code points: 106002
# ================================================
@@ -2293,12 +2328,13 @@ ABF0..ABF9 ; Numeric # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT N
114D0..114D9 ; Numeric # Nd [10] TIRHUTA DIGIT ZERO..TIRHUTA DIGIT NINE
11650..11659 ; Numeric # Nd [10] MODI DIGIT ZERO..MODI DIGIT NINE
116C0..116C9 ; Numeric # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE
+11730..11739 ; Numeric # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE
118E0..118E9 ; Numeric # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE
16A60..16A69 ; Numeric # Nd [10] MRO DIGIT ZERO..MRO 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
-# Total code points: 532
+# Total code points: 542
# ================================================
@@ -2358,18 +2394,22 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP
11141..11143 ; STerm # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK
111C5..111C6 ; STerm # Po [2] SHARADA DANDA..SHARADA DOUBLE DANDA
111CD ; STerm # Po SHARADA SUTRA MARK
+111DE..111DF ; STerm # Po [2] SHARADA SECTION MARK-1..SHARADA SECTION MARK-2
11238..11239 ; STerm # Po [2] KHOJKI DANDA..KHOJKI DOUBLE DANDA
1123B..1123C ; STerm # Po [2] KHOJKI SECTION MARK..KHOJKI DOUBLE SECTION MARK
+112A9 ; STerm # Po MULTANI SECTION MARK
115C2..115C3 ; STerm # Po [2] SIDDHAM DANDA..SIDDHAM DOUBLE DANDA
-115C9 ; STerm # Po SIDDHAM END OF TEXT MARK
+115C9..115D7 ; STerm # Po [15] SIDDHAM END OF TEXT MARK..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES
11641..11642 ; STerm # Po [2] MODI DANDA..MODI DOUBLE DANDA
+1173C..1173E ; STerm # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI
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
16B44 ; STerm # Po PAHAWH HMONG SIGN XAUS
1BC9F ; STerm # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP
+1DA88 ; STerm # Po SIGNWRITING FULL STOP
-# Total code points: 96
+# Total code points: 117
# ================================================