summaryrefslogtreecommitdiffstats
path: root/util/unicode/data/LineBreak.txt
diff options
context:
space:
mode:
Diffstat (limited to 'util/unicode/data/LineBreak.txt')
-rw-r--r--util/unicode/data/LineBreak.txt132
1 files changed, 97 insertions, 35 deletions
diff --git a/util/unicode/data/LineBreak.txt b/util/unicode/data/LineBreak.txt
index e496c5fc0e..b627f874d0 100644
--- a/util/unicode/data/LineBreak.txt
+++ b/util/unicode/data/LineBreak.txt
@@ -1,5 +1,5 @@
-# LineBreak-7.0.0.txt
-# Date: 2014-02-28, 23:15:00 GMT [KW, LI]
+# LineBreak-8.0.0.txt
+# Date: 2015-02-13, 09:15:00 GMT [KW, LI]
#
# Line_Break Property
#
@@ -7,7 +7,7 @@
# Unicode Character Database.
# It contains both normative and informative data.
#
-# 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
#
# The format is two fields separated by a semicolon.
@@ -30,6 +30,7 @@
# CJK Unified Ideographs Extension B: U+20000..U+2A6DF
# CJK Unified Ideographs Extension C: U+2A700..U+2B73F
# CJK Unified Ideographs Extension D: U+2B740..U+2B81F
+# CJK Unified Ideographs Extension E: U+2B820..U+2CEAF
# CJK Compatibility Ideographs Supplement: U+2F800..U+2FA1F
# and any other reserved code points on
# Planes 2 and 3: U+20000..U+2FFFD
@@ -272,8 +273,8 @@
0840..0858;AL # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN
0859..085B;CM # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK
085E;AL # Po MANDAIC PUNCTUATION
-08A0..08B2;AL # Lo [19] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE
-08E4..08FF;CM # Mn [28] ARABIC CURLY FATHA..ARABIC MARK SIDEWAYS NOON GHUNNA
+08A0..08B4;AL # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
+08E3..08FF;CM # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA
0900..0902;CM # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA
0903;CM # Mc DEVANAGARI SIGN VISARGA
0904..0939;AL # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA
@@ -366,6 +367,7 @@
0AE6..0AEF;NU # Nd [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE
0AF0;AL # Po GUJARATI ABBREVIATION SIGN
0AF1;PR # Sc GUJARATI RUPEE SIGN
+0AF9;AL # Lo GUJARATI LETTER ZHA
0B01;CM # Mn ORIYA SIGN CANDRABINDU
0B02..0B03;CM # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA
0B05..0B0C;AL # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L
@@ -428,7 +430,7 @@
0C46..0C48;CM # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI
0C4A..0C4D;CM # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA
0C55..0C56;CM # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK
-0C58..0C59;AL # Lo [2] TELUGU LETTER TSA..TELUGU LETTER DZA
+0C58..0C5A;AL # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA
0C60..0C61;AL # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL
0C62..0C63;CM # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL
0C66..0C6F;NU # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE
@@ -469,7 +471,7 @@
0D4D;CM # Mn MALAYALAM SIGN VIRAMA
0D4E;AL # Lo MALAYALAM LETTER DOT REPH
0D57;CM # Mc MALAYALAM AU LENGTH MARK
-0D60..0D61;AL # Lo [2] MALAYALAM LETTER VOCALIC RR..MALAYALAM LETTER VOCALIC LL
+0D5F..0D61;AL # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL
0D62..0D63;CM # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL
0D66..0D6F;NU # Nd [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE
0D70..0D75;AL # No [6] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE QUARTERS
@@ -641,7 +643,8 @@
1369..137C;AL # No [20] ETHIOPIC DIGIT ONE..ETHIOPIC NUMBER TEN THOUSAND
1380..138F;AL # Lo [16] ETHIOPIC SYLLABLE SEBATBEIT MWA..ETHIOPIC SYLLABLE PWE
1390..1399;AL # So [10] ETHIOPIC TONAL MARK YIZET..ETHIOPIC TONAL MARK KURT
-13A0..13F4;AL # Lo [85] CHEROKEE LETTER A..CHEROKEE LETTER YV
+13A0..13F5;AL # Lu [86] CHEROKEE LETTER A..CHEROKEE LETTER MV
+13F8..13FD;AL # Ll [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV
1400;BA # Pd CANADIAN SYLLABICS HYPHEN
1401..166C;AL # Lo [620] CANADIAN SYLLABICS E..CANADIAN SYLLABICS CARRIER TTSA
166D..166E;AL # Po [2] CANADIAN SYLLABICS CHI SIGN..CANADIAN SYLLABICS FULL STOP
@@ -716,9 +719,7 @@
1950..196D;SA # Lo [30] TAI LE LETTER KA..TAI LE LETTER AI
1970..1974;SA # Lo [5] TAI LE LETTER TONE-2..TAI LE LETTER TONE-6
1980..19AB;SA # Lo [44] NEW TAI LUE LETTER HIGH QA..NEW TAI LUE LETTER LOW SUA
-19B0..19C0;SA # Mc [17] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE VOWEL SIGN IY
-19C1..19C7;SA # Lo [7] NEW TAI LUE LETTER FINAL V..NEW TAI LUE LETTER FINAL B
-19C8..19C9;SA # Mc [2] NEW TAI LUE TONE MARK-1..NEW TAI LUE TONE MARK-2
+19B0..19C9;SA # Lo [26] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2
19D0..19D9;NU # Nd [10] NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE
19DA;SA # No NEW TAI LUE THAM DIGIT ONE
19DE..19DF;SA # So [2] NEW TAI LUE SIGN LAE..NEW TAI LUE SIGN LAEV
@@ -926,7 +927,8 @@
20B7..20BA;PR # Sc [4] SPESMILO SIGN..TURKISH LIRA SIGN
20BB;PO # Sc NORDIC MARK SIGN
20BC..20BD;PR # Sc [2] MANAT SIGN..RUBLE SIGN
-20BE..20CF;PR # Cn [18] <reserved-20BE>..<reserved-20CF>
+20BE;PO # Sc LARI SIGN
+20BF..20CF;PR # Cn [17] <reserved-20BF>..<reserved-20CF>
20D0..20DC;CM # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
20DD..20E0;CM # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH
20E1;CM # Mn COMBINING LEFT RIGHT ARROW ABOVE
@@ -988,6 +990,7 @@
2183..2184;AL # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C
2185..2188;AL # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND
2189;AI # No VULGAR FRACTION ZERO THIRDS
+218A..218B;AL # So [2] TURNED DIGIT TWO..TURNED DIGIT THREE
2190..2194;AI # Sm [5] LEFTWARDS ARROW..LEFT RIGHT ARROW
2195..2199;AI # So [5] UP DOWN ARROW..SOUTH WEST ARROW
219A..219B;AL # Sm [2] LEFTWARDS ARROW WITH STROKE..RIGHTWARDS ARROW WITH STROKE
@@ -1063,7 +1066,9 @@
22A5;AI # Sm UP TACK
22A6..22BE;AL # Sm [25] ASSERTION..RIGHT ANGLE WITH ARC
22BF;AI # Sm RIGHT TRIANGLE
-22C0..22FF;AL # Sm [64] N-ARY LOGICAL AND..Z NOTATION BAG MEMBERSHIP
+22C0..22EE;AL # Sm [47] N-ARY LOGICAL AND..VERTICAL ELLIPSIS
+22EF;IN # Sm MIDLINE HORIZONTAL ELLIPSIS
+22F0..22FF;AL # Sm [16] UP RIGHT DIAGONAL ELLIPSIS..Z NOTATION BAG MEMBERSHIP
2300..2307;AL # So [8] DIAMETER SIGN..WAVY LINE
2308;OP # Ps LEFT CEILING
2309;CL # Pe RIGHT CEILING
@@ -1273,6 +1278,7 @@
2B98..2BB9;AL # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX
2BBD..2BC8;AL # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
2BCA..2BD1;AL # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN
+2BEC..2BEF;AL # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS
2C00..2C2E;AL # Lu [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
2C30..2C5E;AL # Ll [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE
2C60..2C7B;AL # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E
@@ -1470,8 +1476,8 @@
3400..4DB5;ID # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4DB6..4DBF;ID # Cn [10] <reserved-4DB6>..<reserved-4DBF>
4DC0..4DFF;AL # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION
-4E00..9FCC;ID # Lo [20941] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCC
-9FCD..9FFF;ID # Cn [51] <reserved-9FCD>..<reserved-9FFF>
+4E00..9FD5;ID # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
+9FD6..9FFF;ID # Cn [42] <reserved-9FD6>..<reserved-9FFF>
A000..A014;ID # Lo [21] YI SYLLABLE IT..YI SYLLABLE E
A015;NS # Lm YI SYLLABLE WU
A016..A48C;ID # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR
@@ -1497,7 +1503,7 @@ A67E;AL # Po CYRILLIC KAVYKA
A67F;AL # Lm CYRILLIC PAYEROK
A680..A69B;AL # L& [28] CYRILLIC CAPITAL LETTER DWE..CYRILLIC SMALL LETTER CROSSED O
A69C..A69D;AL # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN
-A69F;CM # Mn COMBINING CYRILLIC LETTER IOTIFIED E
+A69E..A69F;CM # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E
A6A0..A6E5;AL # Lo [70] BAMUM LETTER A..BAMUM LETTER KI
A6E6..A6EF;AL # Nl [10] BAMUM LETTER MO..BAMUM LETTER KOGHOM
A6F0..A6F1;CM # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS
@@ -1512,8 +1518,9 @@ A771..A787;AL # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULA
A788;AL # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT
A789..A78A;AL # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN
A78B..A78E;AL # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
+A78F;AL # Lo LATIN LETTER SINOLOGICAL DOT
A790..A7AD;AL # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT
-A7B0..A7B1;AL # Lu [2] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER TURNED T
+A7B0..A7B7;AL # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA
A7F7;AL # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I
A7F8..A7F9;AL # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
A7FA;AL # Ll LATIN LETTER SMALL CAPITAL TURNED M
@@ -1546,6 +1553,8 @@ A8E0..A8F1;CM # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANA
A8F2..A8F7;AL # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA
A8F8..A8FA;AL # Po [3] DEVANAGARI SIGN PUSHPIKA..DEVANAGARI CARET
A8FB;AL # Lo DEVANAGARI HEADSTROKE
+A8FC;BB # Po DEVANAGARI SIGN SIDDHAM
+A8FD;AL # Lo DEVANAGARI JAIN OM
A900..A909;NU # Nd [10] KAYAH LI DIGIT ZERO..KAYAH LI DIGIT NINE
A90A..A925;AL # Lo [28] KAYAH LI LETTER KA..KAYAH LI LETTER OO
A926..A92D;CM # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU
@@ -1630,7 +1639,8 @@ AB28..AB2E;AL # Lo [7] ETHIOPIC SYLLABLE BBA..ETHIOPIC SYLLABLE BBO
AB30..AB5A;AL # Ll [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG
AB5B;AL # Sk MODIFIER BREVE WITH INVERTED BREVE
AB5C..AB5F;AL # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK
-AB64..AB65;AL # Ll [2] LATIN SMALL LETTER INVERTED ALPHA..GREEK LETTER SMALL CAPITAL OMEGA
+AB60..AB65;AL # Ll [6] LATIN SMALL LETTER SAKHA YAT..GREEK LETTER SMALL CAPITAL OMEGA
+AB70..ABBF;AL # Ll [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA
ABC0..ABE2;AL # Lo [35] MEETEI MAYEK LETTER KOK..MEETEI MAYEK LETTER I LONSUM
ABE3..ABE4;CM # Mc [2] MEETEI MAYEK VOWEL SIGN ONAP..MEETEI MAYEK VOWEL SIGN INAP
ABE5;CM # Mn MEETEI MAYEK VOWEL SIGN ANAP
@@ -2479,7 +2489,7 @@ FE15..FE16;EX # Po [2] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK..
FE17;OP # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE LENTICULAR BRACKET
FE18;CL # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRAKCET
FE19;IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS
-FE20..FE2D;CM # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON BELOW
+FE20..FE2F;CM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF
FE30;ID # Po PRESENTATION FORM FOR VERTICAL TWO DOT LEADER
FE31..FE32;ID # Pd [2] PRESENTATION FORM FOR VERTICAL EM DASH..PRESENTATION FORM FOR VERTICAL EN DASH
FE33..FE34;ID # Pc [2] PRESENTATION FORM FOR VERTICAL LOW LINE..PRESENTATION FORM FOR VERTICAL WAVY LOW LINE
@@ -2647,6 +2657,9 @@ FFFD;AI # So REPLACEMENT CHARACTER
10879..1087F;AL # No [7] PALMYRENE NUMBER ONE..PALMYRENE NUMBER TWENTY
10880..1089E;AL # Lo [31] NABATAEAN LETTER FINAL ALEPH..NABATAEAN LETTER TAW
108A7..108AF;AL # No [9] NABATAEAN NUMBER ONE..NABATAEAN NUMBER ONE HUNDRED
+108E0..108F2;AL # Lo [19] HATRAN LETTER ALEPH..HATRAN LETTER QOPH
+108F4..108F5;AL # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW
+108FB..108FF;AL # No [5] HATRAN NUMBER ONE..HATRAN NUMBER ONE HUNDRED
10900..10915;AL # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU
10916..1091B;AL # No [6] PHOENICIAN NUMBER ONE..PHOENICIAN NUMBER THREE
1091F;BA # Po PHOENICIAN WORD SEPARATOR
@@ -2654,7 +2667,10 @@ FFFD;AI # So REPLACEMENT CHARACTER
1093F;AL # Po LYDIAN TRIANGULAR MARK
10980..1099F;AL # Lo [32] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC HIEROGLYPHIC SYMBOL VIDJ-2
109A0..109B7;AL # Lo [24] MEROITIC CURSIVE LETTER A..MEROITIC CURSIVE LETTER DA
+109BC..109BD;AL # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF
109BE..109BF;AL # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN
+109C0..109CF;AL # No [16] MEROITIC CURSIVE NUMBER ONE..MEROITIC CURSIVE NUMBER SEVENTY
+109D2..109FF;AL # No [46] MEROITIC CURSIVE NUMBER ONE HUNDRED..MEROITIC CURSIVE FRACTION TEN TWELFTHS
10A00;AL # Lo KHAROSHTHI LETTER A
10A01..10A03;CM # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R
10A05..10A06;CM # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O
@@ -2689,6 +2705,9 @@ FFFD;AI # So REPLACEMENT CHARACTER
10B99..10B9C;AL # Po [4] PSALTER PAHLAVI SECTION MARK..PSALTER PAHLAVI FOUR DOTS WITH DOT
10BA9..10BAF;AL # No [7] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER ONE HUNDRED
10C00..10C48;AL # Lo [73] OLD TURKIC LETTER ORKHON A..OLD TURKIC LETTER ORKHON BASH
+10C80..10CB2;AL # Lu [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US
+10CC0..10CF2;AL # Ll [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US
+10CFA..10CFF;AL # No [6] OLD HUNGARIAN NUMBER ONE..OLD HUNGARIAN NUMBER ONE THOUSAND
10E60..10E7E;AL # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS
11000;CM # Mc BRAHMI SIGN CANDRABINDU
11001;CM # Mn BRAHMI SIGN ANUSVARA
@@ -2734,9 +2753,14 @@ FFFD;AI # So REPLACEMENT CHARACTER
111C5..111C6;BA # Po [2] SHARADA DANDA..SHARADA DOUBLE DANDA
111C7;AL # Po SHARADA ABBREVIATION SIGN
111C8;BA # Po SHARADA SEPARATOR
+111C9;AL # Po SHARADA SANDHI MARK
+111CA..111CC;CM # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK
111CD;AL # Po SHARADA SUTRA MARK
111D0..111D9;NU # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE
111DA;AL # Lo SHARADA EKAM
+111DB;BB # Po SHARADA SIGN SIDDHAM
+111DC;AL # Lo SHARADA HEADSTROKE
+111DD..111DF;BA # Po [3] SHARADA CONTINUATION SIGN..SHARADA SECTION MARK-2
111E1..111F4;AL # No [20] SINHALA ARCHAIC DIGIT ONE..SINHALA ARCHAIC NUMBER ONE THOUSAND
11200..11211;AL # Lo [18] KHOJKI LETTER A..KHOJKI LETTER JJA
11213..1122B;AL # Lo [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA
@@ -2750,12 +2774,18 @@ FFFD;AI # So REPLACEMENT CHARACTER
1123A;AL # Po KHOJKI WORD SEPARATOR
1123B..1123C;BA # Po [2] KHOJKI SECTION MARK..KHOJKI DOUBLE SECTION MARK
1123D;AL # Po KHOJKI ABBREVIATION SIGN
+11280..11286;AL # Lo [7] MULTANI LETTER A..MULTANI LETTER GA
+11288;AL # Lo MULTANI LETTER GHA
+1128A..1128D;AL # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA
+1128F..1129D;AL # Lo [15] MULTANI LETTER NYA..MULTANI LETTER BA
+1129F..112A8;AL # Lo [10] MULTANI LETTER BHA..MULTANI LETTER RHA
+112A9;BA # Po MULTANI SECTION MARK
112B0..112DE;AL # Lo [47] KHUDAWADI LETTER A..KHUDAWADI LETTER HA
112DF;CM # Mn KHUDAWADI SIGN ANUSVARA
112E0..112E2;CM # Mc [3] KHUDAWADI VOWEL SIGN AA..KHUDAWADI VOWEL SIGN II
112E3..112EA;CM # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
112F0..112F9;NU # Nd [10] KHUDAWADI DIGIT ZERO..KHUDAWADI DIGIT NINE
-11301;CM # Mn GRANTHA SIGN CANDRABINDU
+11300..11301;CM # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
11302..11303;CM # Mc [2] GRANTHA SIGN ANUSVARA..GRANTHA SIGN VISARGA
11305..1130C;AL # Lo [8] GRANTHA LETTER A..GRANTHA LETTER VOCALIC L
1130F..11310;AL # Lo [2] GRANTHA LETTER EE..GRANTHA LETTER AI
@@ -2770,6 +2800,7 @@ FFFD;AI # So REPLACEMENT CHARACTER
11341..11344;CM # Mc [4] GRANTHA VOWEL SIGN U..GRANTHA VOWEL SIGN VOCALIC RR
11347..11348;CM # Mc [2] GRANTHA VOWEL SIGN EE..GRANTHA VOWEL SIGN AI
1134B..1134D;CM # Mc [3] GRANTHA VOWEL SIGN OO..GRANTHA SIGN VIRAMA
+11350;AL # Lo GRANTHA OM
11357;CM # Mc GRANTHA AU LENGTH MARK
1135D..11361;AL # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL
11362..11363;CM # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL
@@ -2799,7 +2830,9 @@ FFFD;AI # So REPLACEMENT CHARACTER
115C2..115C3;BA # Po [2] SIDDHAM DANDA..SIDDHAM DOUBLE DANDA
115C4..115C5;EX # Po [2] SIDDHAM SEPARATOR DOT..SIDDHAM SEPARATOR BAR
115C6..115C8;AL # Po [3] SIDDHAM REPETITION MARK-1..SIDDHAM REPETITION MARK-3
-115C9;BA # Po SIDDHAM END OF TEXT MARK
+115C9..115D7;BA # Po [15] SIDDHAM END OF TEXT MARK..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES
+115D8..115DB;AL # Lo [4] SIDDHAM LETTER THREE-CIRCLE ALTERNATE I..SIDDHAM LETTER ALTERNATE U
+115DC..115DD;CM # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU
11600..1162F;AL # Lo [48] MODI LETTER A..MODI LETTER LLA
11630..11632;CM # Mc [3] MODI VOWEL SIGN AA..MODI VOWEL SIGN II
11633..1163A;CM # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI
@@ -2820,14 +2853,25 @@ FFFD;AI # So REPLACEMENT CHARACTER
116B6;CM # Mc TAKRI SIGN VIRAMA
116B7;CM # Mn TAKRI SIGN NUKTA
116C0..116C9;NU # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE
+11700..11719;SA # Lo [26] AHOM LETTER KA..AHOM LETTER JHA
+1171D..1171F;SA # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA
+11720..11721;SA # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA
+11722..11725;SA # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
+11726;SA # Mc AHOM VOWEL SIGN E
+11727..1172B;SA # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER
+11730..11739;NU # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE
+1173A..1173B;SA # No [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY
+1173C..1173E;BA # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI
+1173F;SA # So AHOM SYMBOL VI
118A0..118DF;AL # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO
118E0..118E9;NU # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE
118EA..118F2;AL # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY
118FF;AL # Lo WARANG CITI OM
11AC0..11AF8;AL # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
-12000..12398;AL # Lo [921] CUNEIFORM SIGN A..CUNEIFORM SIGN UM TIMES ME
+12000..12399;AL # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
12400..1246E;AL # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
12470..12474;BA # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON
+12480..12543;AL # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
13000..13257;AL # Lo [600] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH O006
13258..1325A;OP # Lo [3] EGYPTIAN HIEROGLYPH O006A..EGYPTIAN HIEROGLYPH O006C
1325B..1325D;CL # Lo [3] EGYPTIAN HIEROGLYPH O006D..EGYPTIAN HIEROGLYPH O006F
@@ -2842,6 +2886,10 @@ FFFD;AI # So REPLACEMENT CHARACTER
13379;OP # Lo EGYPTIAN HIEROGLYPH V011A
1337A..1337B;CL # Lo [2] EGYPTIAN HIEROGLYPH V011B..EGYPTIAN HIEROGLYPH V011C
1337C..1342E;AL # Lo [179] EGYPTIAN HIEROGLYPH V012..EGYPTIAN HIEROGLYPH AA032
+14400..145CD;AL # Lo [462] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A409
+145CE;OP # Lo ANATOLIAN HIEROGLYPH A410 BEGIN LOGOGRAM MARK
+145CF;CL # Lo ANATOLIAN HIEROGLYPH A410A END LOGOGRAM MARK
+145D0..14646;AL # Lo [119] ANATOLIAN HIEROGLYPH A411..ANATOLIAN HIEROGLYPH A530
16800..16A38;AL # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ
16A40..16A5E;AL # Lo [31] MRO LETTER TA..MRO LETTER TEK
16A60..16A69;NU # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE
@@ -2888,7 +2936,7 @@ FFFD;AI # So REPLACEMENT CHARACTER
1D185..1D18B;CM # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
1D18C..1D1A9;AL # So [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH
1D1AA..1D1AD;CM # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
-1D1AE..1D1DD;AL # So [48] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL PES SUBPUNCTIS
+1D1AE..1D1E8;AL # So [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN
1D200..1D241;AL # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54
1D242..1D244;CM # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
1D245;AL # So GREEK MUSICAL LEIMMA
@@ -2935,6 +2983,19 @@ FFFD;AI # So REPLACEMENT CHARACTER
1D7C3;AL # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL
1D7C4..1D7CB;AL # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA
1D7CE..1D7FF;NU # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
+1D800..1D9FF;AL # So [512] SIGNWRITING HAND-FIST INDEX..SIGNWRITING HEAD
+1DA00..1DA36;CM # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN
+1DA37..1DA3A;AL # So [4] SIGNWRITING AIR BLOW SMALL ROTATIONS..SIGNWRITING BREATH EXHALE
+1DA3B..1DA6C;CM # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT
+1DA6D..1DA74;AL # So [8] SIGNWRITING SHOULDER HIP SPINE..SIGNWRITING TORSO-FLOORPLANE TWISTING
+1DA75;CM # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS
+1DA76..1DA83;AL # So [14] SIGNWRITING LIMB COMBINATION..SIGNWRITING LOCATION DEPTH
+1DA84;CM # Mn SIGNWRITING LOCATION HEAD NECK
+1DA85..1DA86;AL # So [2] SIGNWRITING LOCATION TORSO..SIGNWRITING LOCATION LIMBS DIGITS
+1DA87..1DA8A;BA # Po [4] SIGNWRITING COMMA..SIGNWRITING COLON
+1DA8B;AL # Po SIGNWRITING PARENTHESIS
+1DA9B..1DA9F;CM # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6
+1DAA1..1DAAF;CM # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16
1E800..1E8C4;AL # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON
1E8C7..1E8CF;AL # No [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE
1E8D0..1E8D6;CM # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
@@ -2989,16 +3050,14 @@ FFFD;AI # So REPLACEMENT CHARACTER
1F210..1F23A;ID # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6
1F240..1F248;ID # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557
1F250..1F251;ID # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT
-1F300..1F32C;ID # So [45] CYCLONE..WIND BLOWING FACE
-1F330..1F37D;ID # So [78] CHESTNUT..FORK AND KNIFE WITH PLATE
-1F380..1F39B;ID # So [28] RIBBON..CONTROL KNOBS
+1F300..1F39B;ID # So [156] CYCLONE..CONTROL KNOBS
1F39C..1F39D;AL # So [2] BEAMED ASCENDING MUSICAL NOTES..BEAMED DESCENDING MUSICAL NOTES
1F39E..1F3B4;ID # So [23] FILM FRAMES..FLOWER PLAYING CARDS
1F3B5..1F3B6;AL # So [2] MUSICAL NOTE..MULTIPLE MUSICAL NOTES
1F3B7..1F3BB;ID # So [5] SAXOPHONE..VIOLIN
1F3BC;AL # So MUSICAL SCORE
-1F3BD..1F3CE;ID # So [18] RUNNING SHIRT WITH SASH..RACING CAR
-1F3D4..1F3F7;ID # So [36] SNOW CAPPED MOUNTAIN..LABEL
+1F3BD..1F3FA;ID # So [62] RUNNING SHIRT WITH SASH..AMPHORA
+1F3FB..1F3FF;AL # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
1F400..1F49F;ID # So [160] RAT..HEART DECORATION
1F4A0;AL # So DIAMOND SHAPE WITH A DOT INSIDE
1F4A1;ID # So ELECTRIC LIGHT BULB
@@ -3009,27 +3068,25 @@ FFFD;AI # So REPLACEMENT CHARACTER
1F4AF;AL # So HUNDRED POINTS SYMBOL
1F4B0;ID # So MONEY BAG
1F4B1..1F4B2;AL # So [2] CURRENCY EXCHANGE..HEAVY DOLLAR SIGN
-1F4B3..1F4FE;ID # So [76] CREDIT CARD..PORTABLE STEREO
+1F4B3..1F4FF;ID # So [77] CREDIT CARD..PRAYER BEADS
1F500..1F506;AL # So [7] TWISTED RIGHTWARDS ARROWS..HIGH BRIGHTNESS SYMBOL
1F507..1F516;ID # So [16] SPEAKER WITH CANCELLATION STROKE..BOOKMARK
1F517..1F524;AL # So [14] LINK SYMBOL..INPUT SYMBOL FOR LATIN LETTERS
1F525..1F531;ID # So [13] FIRE..TRIDENT EMBLEM
1F532..1F549;AL # So [24] BLACK SQUARE BUTTON..OM SYMBOL
-1F54A;ID # So DOVE OF PEACE
-1F550..1F579;ID # So [42] CLOCK FACE ONE OCLOCK..JOYSTICK
+1F54A..1F579;ID # So [48] DOVE OF PEACE..JOYSTICK
1F57B..1F5A3;ID # So [41] LEFT HAND TELEPHONE RECEIVER..BLACK DOWN POINTING BACKHAND INDEX
1F5A5..1F5D3;ID # So [47] DESKTOP COMPUTER..SPIRAL CALENDAR PAD
1F5D4..1F5DB;AL # So [8] DESKTOP WINDOW..DECREASE FONT SIZE SYMBOL
1F5DC..1F5F3;ID # So [24] COMPRESSION..BALLOT BOX WITH BALLOT
1F5F4..1F5F9;AL # So [6] BALLOT SCRIPT X..BALLOT BOX WITH BOLD CHECK
1F5FA..1F5FF;ID # So [6] WORLD MAP..MOYAI
-1F600..1F642;ID # So [67] GRINNING FACE..SLIGHTLY SMILING FACE
-1F645..1F64F;ID # So [11] FACE WITH NO GOOD GESTURE..PERSON WITH FOLDED HANDS
+1F600..1F64F;ID # So [80] GRINNING FACE..PERSON WITH FOLDED HANDS
1F650..1F675;AL # So [38] NORTH WEST POINTING LEAF..SWASH AMPERSAND ORNAMENT
1F676..1F678;QU # So [3] SANS-SERIF HEAVY DOUBLE TURNED COMMA QUOTATION MARK ORNAMENT..SANS-SERIF HEAVY LOW DOUBLE COMMA QUOTATION MARK ORNAMENT
1F679..1F67B;NS # So [3] HEAVY INTERROBANG ORNAMENT..HEAVY SANS-SERIF INTERROBANG ORNAMENT
1F67C..1F67F;AL # So [4] VERY HEAVY SOLIDUS..REVERSE CHECKER BOARD
-1F680..1F6CF;ID # So [80] ROCKET..BED
+1F680..1F6D0;ID # So [81] ROCKET..PLACE OF WORSHIP
1F6E0..1F6EC;ID # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING
1F6F0..1F6F3;ID # So [4] SATELLITE..PASSENGER SHIP
1F700..1F773;AL # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
@@ -3039,12 +3096,17 @@ FFFD;AI # So REPLACEMENT CHARACTER
1F850..1F859;AL # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW
1F860..1F887;AL # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW
1F890..1F8AD;AL # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS
+1F910..1F918;ID # So [9] ZIPPER-MOUTH FACE..SIGN OF THE HORNS
+1F980..1F984;ID # So [5] CRAB..UNICORN FACE
+1F9C0;ID # So CHEESE WEDGE
20000..2A6D6;ID # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
2A6D7..2A6FF;ID # Cn [41] <reserved-2A6D7>..<reserved-2A6FF>
2A700..2B734;ID # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
2B735..2B73F;ID # Cn [11] <reserved-2B735>..<reserved-2B73F>
2B740..2B81D;ID # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
-2B81E..2F7FF;ID # Cn [16354] <reserved-2B81E>..<reserved-2F7FF>
+2B81E..2B81F;ID # Cn [2] <reserved-2B81E>..<reserved-2B81F>
+2B820..2CEA1;ID # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
+2CEA2..2F7FF;ID # Cn [10590] <reserved-2CEA2>..<reserved-2F7FF>
2F800..2FA1D;ID # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
2FA1E..2FFFD;ID # Cn [1504] <reserved-2FA1E>..<reserved-2FFFD>
30000..3FFFD;ID # Cn [65534] <reserved-30000>..<reserved-3FFFD>