summaryrefslogtreecommitdiffstats
path: root/util/unicode/data/LineBreak.txt
diff options
context:
space:
mode:
authorEdward Welbourne <edward.welbourne@qt.io>2020-03-13 17:26:53 +0100
committerEdward Welbourne <edward.welbourne@qt.io>2020-03-14 11:26:59 +0100
commit54f8be6cc0e53bcd8b2e67d302b7cbcaed9387b9 (patch)
tree0bbb40e4a5000c5ff891fe05a904040f2b687f93 /util/unicode/data/LineBreak.txt
parent7ddbd179a191c45946959fa0a898ba3e1f1c0cea (diff)
Update UCD to Revision 26
Include WordBreakTest.html, since a test uses sample strings from it, albeit without actually reading the file. Had to comment out more of the new tests, as at Revision 24, pending an update to harfbuzz and the text boundary detection code. Task-number: QTBUG-79631 Task-number: QTBUG-79418 Task-number: QTBUG-82747 Change-Id: I0082294b09d67ffdc6a9b5c15acf77ad3b86f65f Reviewed-by: Lars Knoll <lars.knoll@qt.io>
Diffstat (limited to 'util/unicode/data/LineBreak.txt')
-rw-r--r--util/unicode/data/LineBreak.txt148
1 files changed, 98 insertions, 50 deletions
diff --git a/util/unicode/data/LineBreak.txt b/util/unicode/data/LineBreak.txt
index 9728582ab1..22abddcd90 100644
--- a/util/unicode/data/LineBreak.txt
+++ b/util/unicode/data/LineBreak.txt
@@ -1,6 +1,6 @@
-# LineBreak-12.1.0.txt
-# Date: 2019-03-31, 22:04:15 GMT [KW, LI]
-# © 2019 Unicode®, Inc.
+# LineBreak-13.0.0.txt
+# Date: 2020-02-17, 07:43:02 GMT [KW, LI]
+# © 2020 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
#
@@ -32,9 +32,10 @@
# outside of allocated blocks, default to "ID":
# Plane 2: U+20000..U+2FFFD
# Plane 3: U+30000..U+3FFFD
-# - All unassigned code points in the following Plane 1 range, whether
+# - All unassigned code points in the following Plane 1 ranges, whether
# inside or outside of allocated blocks, also default to "ID":
-# Plane 1 range: U+1F000..U+1FFFD
+# Plane 1 range: U+1F000..U+1FAFF
+# Plane 1 range: U+1FC00..U+1FFFD
# - The unassigned code points in the following block default to "PR":
# Currency Symbols: U+20A0..U+20CF
#
@@ -277,7 +278,7 @@
085E;AL # Po MANDAIC PUNCTUATION
0860..086A;AL # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA
08A0..08B4;AL # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
-08B6..08BD;AL # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON
+08B6..08C7;AL # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE
08D3..08E1;CM # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA
08E2;AL # Cf ARABIC DISPUTED END OF AYAH
08E3..08FF;CM # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA
@@ -396,7 +397,7 @@
0B47..0B48;CM # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI
0B4B..0B4C;CM # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU
0B4D;CM # Mn ORIYA SIGN VIRAMA
-0B56;CM # Mn ORIYA AI LENGTH MARK
+0B55..0B56;CM # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK
0B57;CM # Mc ORIYA AU LENGTH MARK
0B5C..0B5D;AL # Lo [2] ORIYA LETTER RRA..ORIYA LETTER RHA
0B5F..0B61;AL # Lo [3] ORIYA LETTER YYA..ORIYA LETTER VOCALIC LL
@@ -475,7 +476,7 @@
0CF1..0CF2;AL # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
0D00..0D01;CM # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
0D02..0D03;CM # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
-0D05..0D0C;AL # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L
+0D04..0D0C;AL # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L
0D0E..0D10;AL # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI
0D12..0D3A;AL # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA
0D3B..0D3C;CM # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
@@ -496,6 +497,7 @@
0D70..0D78;AL # No [9] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE SIXTEENTHS
0D79;PO # So MALAYALAM DATE MARK
0D7A..0D7F;AL # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K
+0D81;CM # Mn SINHALA SIGN CANDRABINDU
0D82..0D83;CM # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA
0D85..0D96;AL # Lo [18] SINHALA LETTER AYANNA..SINHALA LETTER AUYANNA
0D9A..0DB1;AL # Lo [24] SINHALA LETTER ALPAPRAANA KAYANNA..SINHALA LETTER DANTAJA NAYANNA
@@ -764,6 +766,7 @@
1AA8..1AAD;SA # Po [6] TAI THAM SIGN KAAN..TAI THAM SIGN CAANG
1AB0..1ABD;CM # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW
1ABE;CM # Me COMBINING PARENTHESES OVERLAY
+1ABF..1AC0;CM # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW
1B00..1B03;CM # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG
1B04;CM # Mc BALINESE SIGN BISAH
1B05..1B33;AL # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA
@@ -1303,7 +1306,7 @@
2B55..2B59;AI # So [5] HEAVY LARGE CIRCLE..HEAVY CIRCLED SALTIRE
2B5A..2B73;AL # So [26] SLANTED NORTH ARROW WITH HOOKED HEAD..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR
2B76..2B95;AL # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW
-2B98..2BFF;AL # So [104] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..HELLSCHREIBER PAUSE SYMBOL
+2B97..2BFF;AL # So [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL
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
@@ -1385,6 +1388,8 @@
2E4C;BA # Po MEDIEVAL COMMA
2E4D;AL # Po PARAGRAPHUS MARK
2E4E..2E4F;BA # Po [2] PUNCTUS ELEVATUS MARK..CORNISH VERSE DIVIDER
+2E50..2E51;AL # So [2] CROSS PATTY WITH RIGHT CROSSBAR..CROSS PATTY WITH LEFT CROSSBAR
+2E52;AL # Po TIRONIAN SIGN CAPITAL ET
2E80..2E99;ID # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP
2E9B..2EF3;ID # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE
2F00..2FD5;ID # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE
@@ -1488,7 +1493,7 @@
3190..3191;ID # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK
3192..3195;ID # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK
3196..319F;ID # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK
-31A0..31BA;ID # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY
+31A0..31BF;ID # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH
31C0..31E3;ID # So [36] CJK STROKE T..CJK STROKE Q
31F0..31FF;CJ # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO
3200..321E;ID # So [31] PARENTHESIZED HANGUL KIYEOK..PARENTHESIZED KOREAN CHARACTER O HU
@@ -1503,11 +1508,10 @@
32B1..32BF;ID # No [15] CIRCLED NUMBER THIRTY SIX..CIRCLED NUMBER FIFTY
32C0..32FF;ID # So [64] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..SQUARE ERA NAME REIWA
3300..33FF;ID # So [256] SQUARE APAATO..SQUARE GAL
-3400..4DB5;ID # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
-4DB6..4DBF;ID # Cn [10] <reserved-4DB6>..<reserved-4DBF>
+3400..4DBF;ID # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF
4DC0..4DFF;AL # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION
-4E00..9FEF;ID # Lo [20976] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEF
-9FF0..9FFF;ID # Cn [16] <reserved-9FF0>..<reserved-9FFF>
+4E00..9FFC;ID # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC
+9FFD..9FFF;ID # Cn [3] <reserved-9FFD>..<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
@@ -1550,7 +1554,8 @@ A789..A78A;AL # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUA
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..A7BF;AL # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U
-A7C2..A7C6;AL # L& [5] LATIN CAPITAL LETTER ANGLICANA W..LATIN CAPITAL LETTER Z WITH PALATAL HOOK
+A7C2..A7CA;AL # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY
+A7F5..A7F6;AL # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H
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
@@ -1566,6 +1571,7 @@ A823..A824;CM # Mc [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIG
A825..A826;CM # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E
A827;CM # Mc SYLOTI NAGRI VOWEL SIGN OO
A828..A82B;AL # So [4] SYLOTI NAGRI POETRY MARK-1..SYLOTI NAGRI POETRY MARK-4
+A82C;CM # Mn SYLOTI NAGRI SIGN ALTERNATE HASANTA
A830..A835;AL # No [6] NORTH INDIC FRACTION ONE QUARTER..NORTH INDIC FRACTION THREE SIXTEENTHS
A836..A837;AL # So [2] NORTH INDIC QUARTER MARK..NORTH INDIC PLACEHOLDER MARK
A838;PO # Sc NORTH INDIC RUPEE MARK
@@ -1670,7 +1676,9 @@ 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
-AB60..AB67;AL # Ll [8] LATIN SMALL LETTER SAKHA YAT..LATIN SMALL LETTER TS DIGRAPH WITH RETROFLEX HOOK
+AB60..AB68;AL # Ll [9] LATIN SMALL LETTER SAKHA YAT..LATIN SMALL LETTER TURNED R WITH MIDDLE TILDE
+AB69;AL # Lm MODIFIER LETTER SMALL TURNED W
+AB6A..AB6B;AL # Sk [2] MODIFIER LETTER LEFT TACK..MODIFIER LETTER RIGHT TACK
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
@@ -2642,7 +2650,7 @@ FFFD;AI # So REPLACEMENT CHARACTER
10179..10189;AL # So [17] GREEK YEAR SIGN..GREEK TRYBLION BASE SIGN
1018A..1018B;AL # No [2] GREEK ZERO SIGN..GREEK ONE QUARTER SIGN
1018C..1018E;AL # So [3] GREEK SINUSOID SIGN..NOMISMA SIGN
-10190..1019B;AL # So [12] ROMAN SEXTANS SIGN..ROMAN CENTURIAL SIGN
+10190..1019C;AL # So [13] ROMAN SEXTANS SIGN..ASCIA SYMBOL
101A0;AL # So GREEK SYMBOL TAU RHO
101D0..101FC;AL # So [45] PHAISTOS DISC SIGN PEDESTRIAN..PHAISTOS DISC SIGN WAVY BAND
101FD;CM # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE
@@ -2746,6 +2754,10 @@ FFFD;AI # So REPLACEMENT CHARACTER
10D24..10D27;CM # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
10D30..10D39;NU # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE
10E60..10E7E;AL # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS
+10E80..10EA9;AL # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET
+10EAB..10EAC;CM # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK
+10EAD;BA # Pd YEZIDI HYPHENATION MARK
+10EB0..10EB1;AL # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE
10F00..10F1C;AL # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL
10F1D..10F26;AL # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF
10F27;AL # Lo OLD SOGDIAN LIGATURE AYIN-DALETH
@@ -2753,6 +2765,8 @@ FFFD;AI # So REPLACEMENT CHARACTER
10F46..10F50;CM # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW
10F51..10F54;AL # No [4] SOGDIAN NUMBER ONE..SOGDIAN NUMBER ONE HUNDRED
10F55..10F59;AL # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT
+10FB0..10FC4;AL # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW
+10FC5..10FCB;AL # No [7] CHORASMIAN NUMBER ONE..CHORASMIAN NUMBER ONE HUNDRED
10FE0..10FF6;AL # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH
11000;CM # Mc BRAHMI SIGN CANDRABINDU
11001;CM # Mn BRAHMI SIGN ANUSVARA
@@ -2786,6 +2800,7 @@ FFFD;AI # So REPLACEMENT CHARACTER
11140..11143;BA # Po [4] CHAKMA SECTION MARK..CHAKMA QUESTION MARK
11144;AL # Lo CHAKMA LETTER LHAA
11145..11146;CM # Mc [2] CHAKMA VOWEL SIGN AA..CHAKMA VOWEL SIGN EI
+11147;AL # Lo CHAKMA LETTER VAA
11150..11172;AL # Lo [35] MAHAJANI LETTER A..MAHAJANI LETTER RRA
11173;CM # Mn MAHAJANI SIGN NUKTA
11174;AL # Po MAHAJANI ABBREVIATION SIGN
@@ -2803,6 +2818,8 @@ FFFD;AI # So REPLACEMENT CHARACTER
111C8;BA # Po SHARADA SEPARATOR
111C9..111CC;CM # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK
111CD;AL # Po SHARADA SUTRA MARK
+111CE;CM # Mc SHARADA VOWEL SIGN PRISHTHAMATRA E
+111CF;CM # Mn SHARADA SIGN INVERTED CANDRABINDU
111D0..111D9;NU # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE
111DA;AL # Lo SHARADA EKAM
111DB;BB # Po SHARADA SIGN SIDDHAM
@@ -2865,10 +2882,10 @@ FFFD;AI # So REPLACEMENT CHARACTER
1144B..1144E;BA # Po [4] NEWA DANDA..NEWA GAP FILLER
1144F;AL # Po NEWA ABBREVIATION SIGN
11450..11459;NU # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE
-1145B;BA # Po NEWA PLACEHOLDER MARK
+1145A..1145B;BA # Po [2] NEWA DOUBLE COMMA..NEWA PLACEHOLDER MARK
1145D;AL # Po NEWA INSERTION SIGN
1145E;CM # Mn NEWA SANDHI MARK
-1145F;AL # Lo NEWA LETTER VEDIC ANUSVARA
+1145F..11461;AL # Lo [3] NEWA LETTER VEDIC ANUSVARA..NEWA SIGN UPADHMANIYA
11480..114AF;AL # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA
114B0..114B2;CM # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II
114B3..114B8;CM # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL
@@ -2938,6 +2955,23 @@ FFFD;AI # So REPLACEMENT CHARACTER
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
+11900..11906;AL # Lo [7] DIVES AKURU LETTER A..DIVES AKURU LETTER E
+11909;AL # Lo DIVES AKURU LETTER O
+1190C..11913;AL # Lo [8] DIVES AKURU LETTER KA..DIVES AKURU LETTER JA
+11915..11916;AL # Lo [2] DIVES AKURU LETTER NYA..DIVES AKURU LETTER TTA
+11918..1192F;AL # Lo [24] DIVES AKURU LETTER DDA..DIVES AKURU LETTER ZA
+11930..11935;CM # Mc [6] DIVES AKURU VOWEL SIGN AA..DIVES AKURU VOWEL SIGN E
+11937..11938;CM # Mc [2] DIVES AKURU VOWEL SIGN AI..DIVES AKURU VOWEL SIGN O
+1193B..1193C;CM # Mn [2] DIVES AKURU SIGN ANUSVARA..DIVES AKURU SIGN CANDRABINDU
+1193D;CM # Mc DIVES AKURU SIGN HALANTA
+1193E;CM # Mn DIVES AKURU VIRAMA
+1193F;AL # Lo DIVES AKURU PREFIXED NASAL SIGN
+11940;CM # Mc DIVES AKURU MEDIAL YA
+11941;AL # Lo DIVES AKURU INITIAL RA
+11942;CM # Mc DIVES AKURU MEDIAL RA
+11943;CM # Mn DIVES AKURU SIGN NUKTA
+11944..11946;BA # Po [3] DIVES AKURU DOUBLE DANDA..DIVES AKURU END OF TEXT MARK
+11950..11959;NU # Nd [10] DIVES AKURU DIGIT ZERO..DIVES AKURU DIGIT NINE
119A0..119A7;AL # Lo [8] NANDINAGARI LETTER A..NANDINAGARI LETTER VOCALIC RR
119AA..119D0;AL # Lo [39] NANDINAGARI LETTER E..NANDINAGARI LETTER RRA
119D1..119D3;CM # Mc [3] NANDINAGARI VOWEL SIGN AA..NANDINAGARI VOWEL SIGN II
@@ -3021,6 +3055,7 @@ FFFD;AI # So REPLACEMENT CHARACTER
11EF3..11EF4;CM # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
11EF5..11EF6;CM # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
11EF7..11EF8;AL # Po [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION
+11FB0;AL # Lo LISU LETTER YHA
11FC0..11FD4;AL # No [21] TAMIL FRACTION ONE THREE-HUNDRED-AND-TWENTIETH..TAMIL FRACTION DOWNSCALING FACTOR KIIZH
11FD5..11FDC;AL # So [8] TAMIL SIGN NEL..TAMIL SIGN MUKKURUNI
11FDD..11FE0;PO # Sc [4] TAMIL SIGN KAACU..TAMIL SIGN VARAAKAN
@@ -3083,8 +3118,12 @@ FFFD;AI # So REPLACEMENT CHARACTER
16FE0..16FE1;NS # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK
16FE2;NS # Po OLD CHINESE HOOK MARK
16FE3;NS # Lm OLD CHINESE ITERATION MARK
+16FE4;GL # Mn KHITAN SMALL SCRIPT FILLER
+16FF0..16FF1;CM # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
17000..187F7;ID # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7
-18800..18AF2;ID # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
+18800..18AFF;ID # Lo [768] TANGUT COMPONENT-001..TANGUT COMPONENT-768
+18B00..18CD5;AL # Lo [470] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CD5
+18D00..18D08;ID # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08
1B000..1B0FF;ID # Lo [256] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER RE-2
1B100..1B11E;ID # Lo [31] HENTAIGANA LETTER RE-3..HENTAIGANA LETTER N-MU-MO-2
1B150..1B152;CJ # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO
@@ -3250,14 +3289,15 @@ FFFD;AI # So REPLACEMENT CHARACTER
1F0D1..1F0F5;ID # So [37] PLAYING CARD ACE OF CLUBS..PLAYING CARD TRUMP-21
1F0F6..1F0FF;ID # Cn [10] <reserved-1F0F6>..<reserved-1F0FF>
1F100..1F10C;AI # No [13] DIGIT ZERO FULL STOP..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO
-1F10D..1F10F;ID # Cn [3] <reserved-1F10D>..<reserved-1F10F>
+1F10D..1F10F;ID # So [3] CIRCLED ZERO WITH SLASH..CIRCLED DOLLAR SIGN WITH OVERLAID BACKSLASH
1F110..1F12D;AI # So [30] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED CD
1F12E..1F12F;AL # So [2] CIRCLED WZ..COPYLEFT SYMBOL
1F130..1F169;AI # So [58] SQUARED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
1F16A..1F16C;AL # So [3] RAISED MC SIGN..RAISED MR SIGN
-1F16D..1F16F;ID # Cn [3] <reserved-1F16D>..<reserved-1F16F>
+1F16D..1F16F;ID # So [3] CIRCLED CC..CIRCLED HUMAN FIGURE
1F170..1F1AC;AI # So [61] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VOD
-1F1AD..1F1E5;ID # Cn [57] <reserved-1F1AD>..<reserved-1F1E5>
+1F1AD;ID # So MASK WORK SYMBOL
+1F1AE..1F1E5;ID # Cn [56] <reserved-1F1AE>..<reserved-1F1E5>
1F1E6..1F1FF;RI # So [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z
1F200..1F202;ID # So [3] SQUARE HIRAGANA HOKA..SQUARED KATAKANA SA
1F203..1F20F;ID # Cn [13] <reserved-1F203>..<reserved-1F20F>
@@ -3348,12 +3388,12 @@ FFFD;AI # So REPLACEMENT CHARACTER
1F6C0;EB # So BATH
1F6C1..1F6CB;ID # So [11] BATHTUB..COUCH AND LAMP
1F6CC;EB # So SLEEPING ACCOMMODATION
-1F6CD..1F6D5;ID # So [9] SHOPPING BAGS..HINDU TEMPLE
-1F6D6..1F6DF;ID # Cn [10] <reserved-1F6D6>..<reserved-1F6DF>
+1F6CD..1F6D7;ID # So [11] SHOPPING BAGS..ELEVATOR
+1F6D8..1F6DF;ID # Cn [8] <reserved-1F6D8>..<reserved-1F6DF>
1F6E0..1F6EC;ID # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING
1F6ED..1F6EF;ID # Cn [3] <reserved-1F6ED>..<reserved-1F6EF>
-1F6F0..1F6FA;ID # So [11] SATELLITE..AUTO RICKSHAW
-1F6FB..1F6FF;ID # Cn [5] <reserved-1F6FB>..<reserved-1F6FF>
+1F6F0..1F6FC;ID # So [13] SATELLITE..ROLLER SKATE
+1F6FD..1F6FF;ID # Cn [3] <reserved-1F6FD>..<reserved-1F6FF>
1F700..1F773;AL # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
1F774..1F77F;ID # Cn [12] <reserved-1F774>..<reserved-1F77F>
1F780..1F7D4;AL # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR
@@ -3370,9 +3410,11 @@ FFFD;AI # So REPLACEMENT CHARACTER
1F860..1F887;AL # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW
1F888..1F88F;ID # Cn [8] <reserved-1F888>..<reserved-1F88F>
1F890..1F8AD;AL # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS
-1F8AE..1F8FF;ID # Cn [82] <reserved-1F8AE>..<reserved-1F8FF>
+1F8AE..1F8AF;ID # Cn [2] <reserved-1F8AE>..<reserved-1F8AF>
+1F8B0..1F8B1;ID # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST
+1F8B2..1F8FF;ID # Cn [78] <reserved-1F8B2>..<reserved-1F8FF>
1F900..1F90B;AL # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT
-1F90C;ID # Cn <reserved-1F90C>
+1F90C;EB # So PINCHED FINGERS
1F90D..1F90E;ID # So [2] WHITE HEART..BROWN HEART
1F90F;EB # So PINCHING HAND
1F910..1F917;ID # So [8] ZIPPER-MOUTH FACE..HUGGING FACE
@@ -3383,22 +3425,18 @@ FFFD;AI # So REPLACEMENT CHARACTER
1F930..1F939;EB # So [10] PREGNANT WOMAN..JUGGLING
1F93A..1F93B;ID # So [2] FENCER..MODERN PENTATHLON
1F93C..1F93E;EB # So [3] WRESTLERS..HANDBALL
-1F93F..1F971;ID # So [51] DIVING MASK..YAWNING FACE
-1F972;ID # Cn <reserved-1F972>
-1F973..1F976;ID # So [4] FACE WITH PARTY HORN AND PARTY HAT..FREEZING FACE
-1F977..1F979;ID # Cn [3] <reserved-1F977>..<reserved-1F979>
-1F97A..1F9A2;ID # So [41] FACE WITH PLEADING EYES..SWAN
-1F9A3..1F9A4;ID # Cn [2] <reserved-1F9A3>..<reserved-1F9A4>
-1F9A5..1F9AA;ID # So [6] SLOTH..OYSTER
-1F9AB..1F9AD;ID # Cn [3] <reserved-1F9AB>..<reserved-1F9AD>
-1F9AE..1F9B4;ID # So [7] GUIDE DOG..BONE
+1F93F..1F976;ID # So [56] DIVING MASK..FREEZING FACE
+1F977;EB # So NINJA
+1F978;ID # So DISGUISED FACE
+1F979;ID # Cn <reserved-1F979>
+1F97A..1F9B4;ID # So [59] FACE WITH PLEADING EYES..BONE
1F9B5..1F9B6;EB # So [2] LEG..FOOT
1F9B7;ID # So TOOTH
1F9B8..1F9B9;EB # So [2] SUPERHERO..SUPERVILLAIN
1F9BA;ID # So SAFETY VEST
1F9BB;EB # So EAR WITH HEARING AID
-1F9BC..1F9CA;ID # So [15] MOTORIZED WHEELCHAIR..ICE CUBE
-1F9CB..1F9CC;ID # Cn [2] <reserved-1F9CB>..<reserved-1F9CC>
+1F9BC..1F9CB;ID # So [16] MOTORIZED WHEELCHAIR..BUBBLE TEA
+1F9CC;ID # Cn <reserved-1F9CC>
1F9CD..1F9CF;EB # So [3] STANDING PERSON..DEAF PERSON
1F9D0;ID # So FACE WITH MONOCLE
1F9D1..1F9DD;EB # So [13] ADULT..ELF
@@ -3407,17 +3445,26 @@ FFFD;AI # So REPLACEMENT CHARACTER
1FA54..1FA5F;ID # Cn [12] <reserved-1FA54>..<reserved-1FA5F>
1FA60..1FA6D;ID # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER
1FA6E..1FA6F;ID # Cn [2] <reserved-1FA6E>..<reserved-1FA6F>
-1FA70..1FA73;ID # So [4] BALLET SHOES..SHORTS
-1FA74..1FA77;ID # Cn [4] <reserved-1FA74>..<reserved-1FA77>
+1FA70..1FA74;ID # So [5] BALLET SHOES..THONG SANDAL
+1FA75..1FA77;ID # Cn [3] <reserved-1FA75>..<reserved-1FA77>
1FA78..1FA7A;ID # So [3] DROP OF BLOOD..STETHOSCOPE
1FA7B..1FA7F;ID # Cn [5] <reserved-1FA7B>..<reserved-1FA7F>
-1FA80..1FA82;ID # So [3] YO-YO..PARACHUTE
-1FA83..1FA8F;ID # Cn [13] <reserved-1FA83>..<reserved-1FA8F>
-1FA90..1FA95;ID # So [6] RINGED PLANET..BANJO
-1FA96..1FAFF;ID # Cn [106] <reserved-1FA96>..<reserved-1FAFF>
-1FB00..1FFFD;ID # Cn [1278] <reserved-1FB00>..<reserved-1FFFD>
-20000..2A6D6;ID # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
-2A6D7..2A6FF;ID # Cn [41] <reserved-2A6D7>..<reserved-2A6FF>
+1FA80..1FA86;ID # So [7] YO-YO..NESTING DOLLS
+1FA87..1FA8F;ID # Cn [9] <reserved-1FA87>..<reserved-1FA8F>
+1FA90..1FAA8;ID # So [25] RINGED PLANET..ROCK
+1FAA9..1FAAF;ID # Cn [7] <reserved-1FAA9>..<reserved-1FAAF>
+1FAB0..1FAB6;ID # So [7] FLY..FEATHER
+1FAB7..1FABF;ID # Cn [9] <reserved-1FAB7>..<reserved-1FABF>
+1FAC0..1FAC2;ID # So [3] ANATOMICAL HEART..PEOPLE HUGGING
+1FAC3..1FACF;ID # Cn [13] <reserved-1FAC3>..<reserved-1FACF>
+1FAD0..1FAD6;ID # So [7] BLUEBERRIES..TEAPOT
+1FAD7..1FAFF;ID # Cn [41] <reserved-1FAD7>..<reserved-1FAFF>
+1FB00..1FB92;AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK
+1FB94..1FBCA;AL # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON
+1FBF0..1FBF9;NU # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE
+1FC00..1FFFD;ID # Cn [1022] <reserved-1FC00>..<reserved-1FFFD>
+20000..2A6DD;ID # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD
+2A6DE..2A6FF;ID # Cn [34] <reserved-2A6DE>..<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
@@ -3429,7 +3476,8 @@ FFFD;AI # So REPLACEMENT CHARACTER
2F800..2FA1D;ID # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
2FA1E..2FA1F;ID # Cn [2] <reserved-2FA1E>..<reserved-2FA1F>
2FA20..2FFFD;ID # Cn [1502] <reserved-2FA20>..<reserved-2FFFD>
-30000..3FFFD;ID # Cn [65534] <reserved-30000>..<reserved-3FFFD>
+30000..3134A;ID # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
+3134B..3FFFD;ID # Cn [60595] <reserved-3134B>..<reserved-3FFFD>
E0001;CM # Cf LANGUAGE TAG
E0020..E007F;CM # Cf [96] TAG SPACE..CANCEL TAG
E0100..E01EF;CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256