summaryrefslogtreecommitdiffstats
path: root/util/unicode/data/Scripts.txt
diff options
context:
space:
mode:
authorLars Knoll <lars.knoll@qt.io>2017-12-12 09:47:53 +0100
committerLars Knoll <lars.knoll@qt.io>2018-01-03 07:46:31 +0000
commit8bfabb34dec8a437a08b5a6e0ecac4a9dd3ae18c (patch)
tree6e69b05e97f6803e9f7ca1b914c341747a8e0d67 /util/unicode/data/Scripts.txt
parent2b2b9c9962e09db1f1ea34773959e3cc626ecce4 (diff)
Update most Unicode data to version 10.0
The text segmentation data is not being updated in this change, as it requires additional code changes. Updating those will come in a follow-up commit. Change-Id: I5d6b6bc96044e8dd0c25cf6f79756e7f68bf6e7c Reviewed-by: Konstantin Ritt <ritt.ks@gmail.com> Reviewed-by: Eskil Abrahamsen Blomfeldt <eskil.abrahamsen-blomfeldt@qt.io>
Diffstat (limited to 'util/unicode/data/Scripts.txt')
-rw-r--r--util/unicode/data/Scripts.txt250
1 files changed, 202 insertions, 48 deletions
diff --git a/util/unicode/data/Scripts.txt b/util/unicode/data/Scripts.txt
index 7e42740407..72319448e9 100644
--- a/util/unicode/data/Scripts.txt
+++ b/util/unicode/data/Scripts.txt
@@ -1,10 +1,11 @@
-# Scripts-8.0.0.txt
-# Date: 2015-03-11, 22:29:42 GMT [MD]
+# Scripts-10.0.0.txt
+# Date: 2017-03-11, 06:40:37 GMT
+# © 2017 Unicode®, Inc.
+# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
+# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
-# 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/
+# For documentation, see http://www.unicode.org/reports/tr44/
# For more information, see:
# UAX #24, Unicode Script Property: http://www.unicode.org/reports/tr24/
# Especially the sections:
@@ -92,10 +93,10 @@
0605 ; Common # Cf ARABIC NUMBER MARK ABOVE
060C ; Common # Po ARABIC COMMA
061B ; Common # Po ARABIC SEMICOLON
-061C ; Common # Cf ARABIC LETTER MARK
061F ; Common # Po ARABIC QUESTION MARK
0640 ; Common # Lm ARABIC TATWEEL
06DD ; Common # Cf ARABIC END OF AYAH
+08E2 ; Common # Cf ARABIC DISPUTED END OF AYAH
0964..0965 ; Common # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA
0E3F ; Common # Sc THAI CURRENCY SYMBOL BAHT
0FD5..0FD8 ; Common # So [4] RIGHT-FACING SVASTI SIGN..LEFT-FACING SVASTI SIGN WITH DOTS
@@ -110,6 +111,7 @@
1CEE..1CF1 ; Common # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA
1CF2..1CF3 ; Common # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
1CF5..1CF6 ; Common # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA
+1CF7 ; Common # Mc VEDIC SIGN ATIKRAMA
2000..200A ; Common # Zs [11] EN QUAD..HAIR SPACE
200B ; Common # Cf ZERO WIDTH SPACE
200E..200F ; Common # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
@@ -153,7 +155,7 @@
208A..208C ; Common # Sm [3] SUBSCRIPT PLUS SIGN..SUBSCRIPT EQUALS SIGN
208D ; Common # Ps SUBSCRIPT LEFT PARENTHESIS
208E ; Common # Pe SUBSCRIPT RIGHT PARENTHESIS
-20A0..20BE ; Common # Sc [31] EURO-CURRENCY SIGN..LARI SIGN
+20A0..20BF ; Common # Sc [32] EURO-CURRENCY SIGN..BITCOIN SIGN
2100..2101 ; Common # So [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT
2102 ; Common # L& DOUBLE-STRUCK CAPITAL C
2103..2106 ; Common # So [4] DEGREE CELSIUS..CADA UNA
@@ -223,8 +225,7 @@
239B..23B3 ; Common # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM
23B4..23DB ; Common # So [40] TOP SQUARE BRACKET..FUSE
23DC..23E1 ; Common # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET
-23E2..23FA ; Common # So [25] WHITE TRAPEZIUM..BLACK CIRCLE FOR RECORD
-2400..2426 ; Common # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO
+23E2..2426 ; Common # So [69] WHITE TRAPEZIUM..SYMBOL FOR SUBSTITUTE FORM TWO
2440..244A ; Common # So [11] OCR HOOK..OCR DOUBLE BACKSLASH
2460..249B ; Common # No [60] CIRCLED DIGIT ONE..NUMBER TWENTY FULL STOP
249C..24E9 ; Common # So [78] PARENTHESIZED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z
@@ -309,7 +310,7 @@
2B76..2B95 ; Common # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW
2B98..2BB9 ; Common # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX
2BBD..2BC8 ; Common # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
-2BCA..2BD1 ; Common # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN
+2BCA..2BD2 ; Common # So [9] TOP HALF BLACK CIRCLE..GROUP MARK
2BEC..2BEF ; Common # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS
2E00..2E01 ; Common # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER
2E02 ; Common # Pi LEFT SUBSTITUTION BRACKET
@@ -348,6 +349,7 @@
2E40 ; Common # Pd DOUBLE HYPHEN
2E41 ; Common # Po REVERSED COMMA
2E42 ; Common # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK
+2E43..2E49 ; Common # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA
2FF0..2FFB ; Common # So [12] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
3000 ; Common # Zs IDEOGRAPHIC SPACE
3001..3003 ; Common # Po [3] IDEOGRAPHIC COMMA..DITTO MARK
@@ -572,19 +574,18 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1F100..1F10C ; Common # No [13] DIGIT ZERO FULL STOP..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO
1F110..1F12E ; Common # So [31] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED WZ
1F130..1F16B ; Common # So [60] SQUARED LATIN CAPITAL LETTER A..RAISED MD SIGN
-1F170..1F19A ; Common # So [43] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VS
+1F170..1F1AC ; Common # So [61] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VOD
1F1E6..1F1FF ; Common # So [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z
1F201..1F202 ; Common # So [2] SQUARED KATAKANA KOKO..SQUARED KATAKANA SA
-1F210..1F23A ; Common # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6
+1F210..1F23B ; Common # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D
1F240..1F248 ; Common # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557
1F250..1F251 ; Common # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT
+1F260..1F265 ; Common # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI
1F300..1F3FA ; Common # So [251] CYCLONE..AMPHORA
1F3FB..1F3FF ; Common # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
-1F400..1F579 ; Common # So [378] RAT..JOYSTICK
-1F57B..1F5A3 ; Common # So [41] LEFT HAND TELEPHONE RECEIVER..BLACK DOWN POINTING BACKHAND INDEX
-1F5A5..1F6D0 ; Common # So [300] DESKTOP COMPUTER..PLACE OF WORSHIP
+1F400..1F6D4 ; Common # So [725] RAT..PAGODA
1F6E0..1F6EC ; Common # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING
-1F6F0..1F6F3 ; Common # So [4] SATELLITE..PASSENGER SHIP
+1F6F0..1F6F8 ; Common # So [9] SATELLITE..FLYING SAUCER
1F700..1F773 ; Common # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
1F780..1F7D4 ; Common # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR
1F800..1F80B ; Common # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD
@@ -592,13 +593,17 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1F850..1F859 ; Common # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW
1F860..1F887 ; Common # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW
1F890..1F8AD ; Common # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS
-1F910..1F918 ; Common # So [9] ZIPPER-MOUTH FACE..SIGN OF THE HORNS
-1F980..1F984 ; Common # So [5] CRAB..UNICORN FACE
+1F900..1F90B ; Common # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT
+1F910..1F93E ; Common # So [47] ZIPPER-MOUTH FACE..HANDBALL
+1F940..1F94C ; Common # So [13] WILTED FLOWER..CURLING STONE
+1F950..1F96B ; Common # So [28] CROISSANT..CANNED FOOD
+1F980..1F997 ; Common # So [24] CRAB..CRICKET
1F9C0 ; Common # So CHEESE WEDGE
+1F9D0..1F9E6 ; Common # So [23] FACE WITH MONOCLE..SOCKS
E0001 ; Common # Cf LANGUAGE TAG
E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
-# Total code points: 7179
+# Total code points: 7363
# ================================================
@@ -641,7 +646,7 @@ A770 ; Latin # Lm MODIFIER LETTER US
A771..A787 ; Latin # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T
A78B..A78E ; Latin # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
A78F ; Latin # Lo LATIN LETTER SINOLOGICAL DOT
-A790..A7AD ; Latin # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT
+A790..A7AE ; Latin # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I
A7B0..A7B7 ; Latin # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA
A7F7 ; Latin # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I
A7F8..A7F9 ; Latin # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
@@ -654,7 +659,7 @@ FB00..FB06 ; Latin # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE S
FF21..FF3A ; Latin # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z
FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z
-# Total code points: 1349
+# Total code points: 1350
# ================================================
@@ -708,13 +713,13 @@ AB65 ; Greek # L& GREEK LETTER SMALL CAPITAL OMEGA
10175..10178 ; Greek # No [4] GREEK ONE HALF SIGN..GREEK THREE QUARTERS SIGN
10179..10189 ; Greek # So [17] GREEK YEAR SIGN..GREEK TRYBLION BASE SIGN
1018A..1018B ; Greek # No [2] GREEK ZERO SIGN..GREEK ONE QUARTER SIGN
-1018C ; Greek # So GREEK SINUSOID SIGN
+1018C..1018E ; Greek # So [3] GREEK SINUSOID SIGN..NOMISMA SIGN
101A0 ; Greek # So GREEK SYMBOL TAU RHO
1D200..1D241 ; Greek # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54
1D242..1D244 ; Greek # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
1D245 ; Greek # So GREEK MUSICAL LEIMMA
-# Total code points: 516
+# Total code points: 518
# ================================================
@@ -724,6 +729,7 @@ AB65 ; Greek # L& GREEK LETTER SMALL CAPITAL OMEGA
0487 ; Cyrillic # Mn COMBINING CYRILLIC POKRYTIE
0488..0489 ; Cyrillic # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN
048A..052F ; Cyrillic # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER
+1C80..1C88 ; Cyrillic # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK
1D2B ; Cyrillic # L& CYRILLIC LETTER SMALL CAPITAL EL
1D78 ; Cyrillic # Lm MODIFIER LETTER CYRILLIC EN
2DE0..2DFF ; Cyrillic # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS
@@ -740,7 +746,7 @@ A69C..A69D ; Cyrillic # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER
A69E..A69F ; Cyrillic # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E
FE2E..FE2F ; Cyrillic # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF
-# Total code points: 434
+# Total code points: 443
# ================================================
@@ -791,6 +797,7 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU
060D ; Arabic # Po ARABIC DATE SEPARATOR
060E..060F ; Arabic # So [2] ARABIC POETIC VERSE SIGN..ARABIC SIGN MISRA
0610..061A ; Arabic # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA
+061C ; Arabic # Cf ARABIC LETTER MARK
061E ; Arabic # Po ARABIC TRIPLE DOT PUNCTUATION MARK
0620..063F ; Arabic # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE
0641..064A ; Arabic # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH
@@ -815,6 +822,8 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU
06FF ; Arabic # Lo ARABIC LETTER HEH WITH INVERTED V
0750..077F ; Arabic # Lo [48] ARABIC LETTER BEH WITH THREE DOTS HORIZONTALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS ABOVE
08A0..08B4 ; Arabic # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
+08B6..08BD ; Arabic # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON
+08D4..08E1 ; Arabic # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA
08E3..08FF ; Arabic # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA
FB50..FBB1 ; Arabic # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM
FBB2..FBC1 ; Arabic # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW
@@ -862,7 +871,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
1EEAB..1EEBB ; Arabic # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
1EEF0..1EEF1 ; Arabic # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL
-# Total code points: 1257
+# Total code points: 1280
# ================================================
@@ -873,8 +882,9 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
0712..072F ; Syriac # Lo [30] SYRIAC LETTER BETH..SYRIAC LETTER PERSIAN DHALATH
0730..074A ; Syriac # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH
074D..074F ; Syriac # Lo [3] SYRIAC LETTER SOGDIAN ZHAIN..SYRIAC LETTER SOGDIAN FE
+0860..086A ; Syriac # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA
-# Total code points: 77
+# Total code points: 88
# ================================================
@@ -944,8 +954,10 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
09F4..09F9 ; Bengali # No [6] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY DENOMINATOR SIXTEEN
09FA ; Bengali # So BENGALI ISSHAR
09FB ; Bengali # Sc BENGALI GANDA MARK
+09FC ; Bengali # Lo BENGALI LETTER VEDIC ANUSVARA
+09FD ; Bengali # Po BENGALI ABBREVIATION SIGN
-# Total code points: 93
+# Total code points: 95
# ================================================
@@ -998,8 +1010,9 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
0AF0 ; Gujarati # Po GUJARATI ABBREVIATION SIGN
0AF1 ; Gujarati # Sc GUJARATI RUPEE SIGN
0AF9 ; Gujarati # Lo GUJARATI LETTER ZHA
+0AFA..0AFF ; Gujarati # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
-# Total code points: 85
+# Total code points: 91
# ================================================
@@ -1086,6 +1099,7 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
# ================================================
+0C80 ; Kannada # Lo KANNADA SIGN SPACING CANDRABINDU
0C81 ; Kannada # Mn KANNADA SIGN CANDRABINDU
0C82..0C83 ; Kannada # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA
0C85..0C8C ; Kannada # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L
@@ -1109,15 +1123,16 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
0CE6..0CEF ; Kannada # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE
0CF1..0CF2 ; Kannada # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
-# Total code points: 87
+# Total code points: 88
# ================================================
-0D01 ; Malayalam # Mn MALAYALAM SIGN CANDRABINDU
+0D00..0D01 ; Malayalam # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
0D02..0D03 ; Malayalam # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
0D05..0D0C ; Malayalam # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L
0D0E..0D10 ; Malayalam # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI
0D12..0D3A ; Malayalam # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA
+0D3B..0D3C ; Malayalam # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
0D3D ; Malayalam # Lo MALAYALAM SIGN AVAGRAHA
0D3E..0D40 ; Malayalam # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II
0D41..0D44 ; Malayalam # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR
@@ -1125,15 +1140,18 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
0D4A..0D4C ; Malayalam # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU
0D4D ; Malayalam # Mn MALAYALAM SIGN VIRAMA
0D4E ; Malayalam # Lo MALAYALAM LETTER DOT REPH
+0D4F ; Malayalam # So MALAYALAM SIGN PARA
+0D54..0D56 ; Malayalam # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL
0D57 ; Malayalam # Mc MALAYALAM AU LENGTH MARK
+0D58..0D5E ; Malayalam # No [7] MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH..MALAYALAM FRACTION ONE FIFTH
0D5F..0D61 ; Malayalam # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL
0D62..0D63 ; Malayalam # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL
0D66..0D6F ; Malayalam # Nd [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE
-0D70..0D75 ; Malayalam # No [6] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE QUARTERS
+0D70..0D78 ; Malayalam # No [9] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE SIXTEENTHS
0D79 ; Malayalam # So MALAYALAM DATE MARK
0D7A..0D7F ; Malayalam # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K
-# Total code points: 100
+# Total code points: 117
# ================================================
@@ -1436,21 +1454,24 @@ AB70..ABBF ; Cherokee # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETT
1820..1842 ; Mongolian # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI
1843 ; Mongolian # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN
1844..1877 ; Mongolian # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA
-1880..18A8 ; Mongolian # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA
+1880..1884 ; Mongolian # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA
+1885..1886 ; Mongolian # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA
+1887..18A8 ; Mongolian # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA
18A9 ; Mongolian # Mn MONGOLIAN LETTER ALI GALI DAGALGA
18AA ; Mongolian # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA
+11660..1166C ; Mongolian # Po [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT
-# Total code points: 153
+# Total code points: 166
# ================================================
3041..3096 ; Hiragana # Lo [86] HIRAGANA LETTER SMALL A..HIRAGANA LETTER SMALL KE
309D..309E ; Hiragana # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK
309F ; Hiragana # Lo HIRAGANA DIGRAPH YORI
-1B001 ; Hiragana # Lo HIRAGANA LETTER ARCHAIC YE
+1B001..1B11E ; Hiragana # Lo [286] HIRAGANA LETTER ARCHAIC YE..HENTAIGANA LETTER N-MU-MO-2
1F200 ; Hiragana # So SQUARE HIRAGANA HOKA
-# Total code points: 91
+# Total code points: 376
# ================================================
@@ -1469,10 +1490,10 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
# ================================================
02EA..02EB ; Bopomofo # Sk [2] MODIFIER LETTER YIN DEPARTING TONE MARK..MODIFIER LETTER YANG DEPARTING TONE MARK
-3105..312D ; Bopomofo # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH
+3105..312E ; Bopomofo # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE
31A0..31BA ; Bopomofo # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY
-# Total code points: 70
+# Total code points: 71
# ================================================
@@ -1485,16 +1506,17 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
3038..303A ; Han # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY
303B ; Han # Lm VERTICAL IDEOGRAPHIC ITERATION MARK
3400..4DB5 ; Han # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
-4E00..9FD5 ; Han # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
+4E00..9FEA ; Han # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
F900..FA6D ; Han # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D
FA70..FAD9 ; Han # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9
20000..2A6D6 ; Han # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
2A700..2B734 ; Han # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
2B740..2B81D ; Han # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2B820..2CEA1 ; Han # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
+2CEB0..2EBE0 ; Han # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2F800..2FA1D ; Han # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
-# Total code points: 81734
+# Total code points: 89228
# ================================================
@@ -1509,8 +1531,9 @@ A490..A4C6 ; Yi # So [55] YI RADICAL QOT..YI RADICAL KE
10300..1031F ; Old_Italic # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS
10320..10323 ; Old_Italic # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY
+1032D..1032F ; Old_Italic # Lo [3] OLD ITALIC LETTER YE..OLD ITALIC LETTER SOUTHERN TSE
-# Total code points: 36
+# Total code points: 39
# ================================================
@@ -1542,8 +1565,8 @@ A490..A4C6 ; Yi # So [55] YI RADICAL QOT..YI RADICAL KE
1CED ; Inherited # Mn VEDIC SIGN TIRYAK
1CF4 ; Inherited # Mn VEDIC TONE CANDRA ABOVE
1CF8..1CF9 ; Inherited # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE
-1DC0..1DF5 ; Inherited # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE
-1DFC..1DFF ; Inherited # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
+1DC0..1DF9 ; Inherited # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW
+1DFB..1DFF ; Inherited # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
200C..200D ; Inherited # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER
20D0..20DC ; Inherited # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
20DD..20E0 ; Inherited # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH
@@ -1562,7 +1585,7 @@ FE20..FE2D ; Inherited # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CON
1D1AA..1D1AD ; Inherited # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
-# Total code points: 563
+# Total code points: 568
# ================================================
@@ -1705,8 +1728,13 @@ E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-2
2C00..2C2E ; Glagolitic # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
2C30..2C5E ; Glagolitic # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE
+1E000..1E006 ; Glagolitic # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
+1E008..1E018 ; Glagolitic # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
+1E01B..1E021 ; Glagolitic # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
+1E023..1E024 ; Glagolitic # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
+1E026..1E02A ; Glagolitic # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
-# Total code points: 94
+# Total code points: 132
# ================================================
@@ -1872,11 +1900,11 @@ A62A..A62B ; Vai # Lo [2] VAI SYLLABLE NDOLE MA..VAI SYLLABLE NDOLE DO
A880..A881 ; Saurashtra # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA
A882..A8B3 ; Saurashtra # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA
A8B4..A8C3 ; Saurashtra # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU
-A8C4 ; Saurashtra # Mn SAURASHTRA SIGN VIRAMA
+A8C4..A8C5 ; Saurashtra # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU
A8CE..A8CF ; Saurashtra # Po [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA
A8D0..A8D9 ; Saurashtra # Nd [10] SAURASHTRA DIGIT ZERO..SAURASHTRA DIGIT NINE
-# Total code points: 81
+# Total code points: 82
# ================================================
@@ -2314,8 +2342,9 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
11235 ; Khojki # Mc KHOJKI SIGN VIRAMA
11236..11237 ; Khojki # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
11238..1123D ; Khojki # Po [6] KHOJKI DANDA..KHOJKI ABBREVIATION SIGN
+1123E ; Khojki # Mn KHOJKI SIGN SUKUN
-# Total code points: 61
+# Total code points: 62
# ================================================
@@ -2536,4 +2565,129 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
# Total code points: 672
+# ================================================
+
+1E900..1E943 ; Adlam # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA
+1E944..1E94A ; Adlam # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA
+1E950..1E959 ; Adlam # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE
+1E95E..1E95F ; Adlam # Po [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK
+
+# Total code points: 87
+
+# ================================================
+
+11C00..11C08 ; Bhaiksuki # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L
+11C0A..11C2E ; Bhaiksuki # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA
+11C2F ; Bhaiksuki # Mc BHAIKSUKI VOWEL SIGN AA
+11C30..11C36 ; Bhaiksuki # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L
+11C38..11C3D ; Bhaiksuki # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA
+11C3E ; Bhaiksuki # Mc BHAIKSUKI SIGN VISARGA
+11C3F ; Bhaiksuki # Mn BHAIKSUKI SIGN VIRAMA
+11C40 ; Bhaiksuki # Lo BHAIKSUKI SIGN AVAGRAHA
+11C41..11C45 ; Bhaiksuki # Po [5] BHAIKSUKI DANDA..BHAIKSUKI GAP FILLER-2
+11C50..11C59 ; Bhaiksuki # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE
+11C5A..11C6C ; Bhaiksuki # No [19] BHAIKSUKI NUMBER ONE..BHAIKSUKI HUNDREDS UNIT MARK
+
+# Total code points: 97
+
+# ================================================
+
+11C70..11C71 ; Marchen # Po [2] MARCHEN HEAD MARK..MARCHEN MARK SHAD
+11C72..11C8F ; Marchen # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A
+11C92..11CA7 ; Marchen # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA
+11CA9 ; Marchen # Mc MARCHEN SUBJOINED LETTER YA
+11CAA..11CB0 ; Marchen # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA
+11CB1 ; Marchen # Mc MARCHEN VOWEL SIGN I
+11CB2..11CB3 ; Marchen # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E
+11CB4 ; Marchen # Mc MARCHEN VOWEL SIGN O
+11CB5..11CB6 ; Marchen # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU
+
+# Total code points: 68
+
+# ================================================
+
+11400..11434 ; Newa # Lo [53] NEWA LETTER A..NEWA LETTER HA
+11435..11437 ; Newa # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II
+11438..1143F ; Newa # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI
+11440..11441 ; Newa # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU
+11442..11444 ; Newa # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA
+11445 ; Newa # Mc NEWA SIGN VISARGA
+11446 ; Newa # Mn NEWA SIGN NUKTA
+11447..1144A ; Newa # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI
+1144B..1144F ; Newa # Po [5] NEWA DANDA..NEWA ABBREVIATION SIGN
+11450..11459 ; Newa # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE
+1145B ; Newa # Po NEWA PLACEHOLDER MARK
+1145D ; Newa # Po NEWA INSERTION SIGN
+
+# Total code points: 92
+
+# ================================================
+
+104B0..104D3 ; Osage # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA
+104D8..104FB ; Osage # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA
+
+# Total code points: 72
+
+# ================================================
+
+16FE0 ; Tangut # Lm TANGUT ITERATION MARK
+17000..187EC ; Tangut # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC
+18800..18AF2 ; Tangut # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
+
+# Total code points: 6881
+
+# ================================================
+
+11D00..11D06 ; Masaram_Gondi # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E
+11D08..11D09 ; Masaram_Gondi # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O
+11D0B..11D30 ; Masaram_Gondi # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA
+11D31..11D36 ; Masaram_Gondi # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R
+11D3A ; Masaram_Gondi # Mn MASARAM GONDI VOWEL SIGN E
+11D3C..11D3D ; Masaram_Gondi # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O
+11D3F..11D45 ; Masaram_Gondi # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA
+11D46 ; Masaram_Gondi # Lo MASARAM GONDI REPHA
+11D47 ; Masaram_Gondi # Mn MASARAM GONDI RA-KARA
+11D50..11D59 ; Masaram_Gondi # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE
+
+# Total code points: 75
+
+# ================================================
+
+16FE1 ; Nushu # Lm NUSHU ITERATION MARK
+1B170..1B2FB ; Nushu # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
+
+# Total code points: 397
+
+# ================================================
+
+11A50 ; Soyombo # Lo SOYOMBO LETTER A
+11A51..11A56 ; Soyombo # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE
+11A57..11A58 ; Soyombo # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU
+11A59..11A5B ; Soyombo # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK
+11A5C..11A83 ; Soyombo # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA
+11A86..11A89 ; Soyombo # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA
+11A8A..11A96 ; Soyombo # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA
+11A97 ; Soyombo # Mc SOYOMBO SIGN VISARGA
+11A98..11A99 ; Soyombo # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER
+11A9A..11A9C ; Soyombo # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD
+11A9E..11AA2 ; Soyombo # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2
+
+# Total code points: 80
+
+# ================================================
+
+11A00 ; Zanabazar_Square # Lo ZANABAZAR SQUARE LETTER A
+11A01..11A06 ; Zanabazar_Square # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O
+11A07..11A08 ; Zanabazar_Square # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU
+11A09..11A0A ; Zanabazar_Square # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK
+11A0B..11A32 ; Zanabazar_Square # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA
+11A33..11A38 ; Zanabazar_Square # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA
+11A39 ; Zanabazar_Square # Mc ZANABAZAR SQUARE SIGN VISARGA
+11A3A ; Zanabazar_Square # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA
+11A3B..11A3E ; Zanabazar_Square # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA
+11A3F..11A46 ; Zanabazar_Square # Po [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK
+11A47 ; Zanabazar_Square # Mn ZANABAZAR SQUARE SUBJOINER
+
+# Total code points: 72
+
# EOF