< prev index next >

make/data/unicodedata/auxiliary/GraphemeBreakProperty.txt

Print this page
rev 54996 : 8221431: Support for Unicode 12.1
Reviewed-by:

@@ -1,11 +1,12 @@
-# GraphemeBreakProperty-8.0.0.txt
-# Date: 2015-02-13, 13:47:14 GMT [MD]
+# GraphemeBreakProperty-12.1.0.txt
+# Date: 2019-03-10, 10:53:12 GMT
+# Copyright (c) 2019 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/
 
 # ================================================
 
 # Property:     Grapheme_Cluster_Break

@@ -15,10 +16,26 @@
 
 # @missing: 0000..10FFFF; Other
 
 # ================================================
 
+0600..0605    ; Prepend # Cf   [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE
+06DD          ; Prepend # Cf       ARABIC END OF AYAH
+070F          ; Prepend # Cf       SYRIAC ABBREVIATION MARK
+08E2          ; Prepend # Cf       ARABIC DISPUTED END OF AYAH
+0D4E          ; Prepend # Lo       MALAYALAM LETTER DOT REPH
+110BD         ; Prepend # Cf       KAITHI NUMBER SIGN
+110CD         ; Prepend # Cf       KAITHI NUMBER SIGN ABOVE
+111C2..111C3  ; Prepend # Lo   [2] SHARADA SIGN JIHVAMULIYA..SHARADA SIGN UPADHMANIYA
+11A3A         ; Prepend # Lo       ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA
+11A84..11A89  ; Prepend # Lo   [6] SOYOMBO SIGN JIHVAMULIYA..SOYOMBO CLUSTER-INITIAL LETTER SA
+11D46         ; Prepend # Lo       MASARAM GONDI REPHA
+
+# Total code points: 22
+
+# ================================================
+
 000D          ; CR # Cc       <control-000D>
 
 # Total code points: 1
 
 # ================================================

@@ -32,38 +49,33 @@
 0000..0009    ; Control # Cc  [10] <control-0000>..<control-0009>
 000B..000C    ; Control # Cc   [2] <control-000B>..<control-000C>
 000E..001F    ; Control # Cc  [18] <control-000E>..<control-001F>
 007F..009F    ; Control # Cc  [33] <control-007F>..<control-009F>
 00AD          ; Control # Cf       SOFT HYPHEN
-0600..0605    ; Control # Cf   [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE
 061C          ; Control # Cf       ARABIC LETTER MARK
-06DD          ; Control # Cf       ARABIC END OF AYAH
-070F          ; Control # Cf       SYRIAC ABBREVIATION MARK
 180E          ; Control # Cf       MONGOLIAN VOWEL SEPARATOR
 200B          ; Control # Cf       ZERO WIDTH SPACE
 200E..200F    ; Control # Cf   [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
 2028          ; Control # Zl       LINE SEPARATOR
 2029          ; Control # Zp       PARAGRAPH SEPARATOR
 202A..202E    ; Control # Cf   [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE
 2060..2064    ; Control # Cf   [5] WORD JOINER..INVISIBLE PLUS
 2065          ; Control # Cn       <reserved-2065>
 2066..206F    ; Control # Cf  [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES
-D800..DFFF    ; Control # Cs [2048] <surrogate-D800>..<surrogate-DFFF>
 FEFF          ; Control # Cf       ZERO WIDTH NO-BREAK SPACE
 FFF0..FFF8    ; Control # Cn   [9] <reserved-FFF0>..<reserved-FFF8>
 FFF9..FFFB    ; Control # Cf   [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR
-110BD         ; Control # Cf       KAITHI NUMBER SIGN
+13430..13438  ; Control # Cf   [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT
 1BCA0..1BCA3  ; Control # Cf   [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
 1D173..1D17A  ; Control # Cf   [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
 E0000         ; Control # Cn       <reserved-E0000>
 E0001         ; Control # Cf       LANGUAGE TAG
 E0002..E001F  ; Control # Cn  [30] <reserved-E0002>..<reserved-E001F>
-E0020..E007F  ; Control # Cf  [96] TAG SPACE..CANCEL TAG
 E0080..E00FF  ; Control # Cn [128] <reserved-E0080>..<reserved-E00FF>
 E01F0..E0FFF  ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
 
-# Total code points: 6030
+# Total code points: 3886
 
 # ================================================
 
 0300..036F    ; Extend # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X
 0483..0487    ; Extend # Mn   [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE

@@ -82,15 +94,17 @@
 06EA..06ED    ; Extend # Mn   [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM
 0711          ; Extend # Mn       SYRIAC LETTER SUPERSCRIPT ALAPH
 0730..074A    ; Extend # Mn  [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH
 07A6..07B0    ; Extend # Mn  [11] THAANA ABAFILI..THAANA SUKUN
 07EB..07F3    ; Extend # Mn   [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE
+07FD          ; Extend # Mn       NKO DANTAYALAN
 0816..0819    ; Extend # Mn   [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH
 081B..0823    ; Extend # Mn   [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A
 0825..0827    ; Extend # Mn   [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U
 0829..082D    ; Extend # Mn   [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA
 0859..085B    ; Extend # Mn   [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK
+08D3..08E1    ; Extend # Mn  [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA
 08E3..0902    ; Extend # Mn  [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA
 093A          ; Extend # Mn       DEVANAGARI VOWEL SIGN OE
 093C          ; Extend # Mn       DEVANAGARI SIGN NUKTA
 0941..0948    ; Extend # Mn   [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI
 094D          ; Extend # Mn       DEVANAGARI SIGN VIRAMA

@@ -101,10 +115,11 @@
 09BE          ; Extend # Mc       BENGALI VOWEL SIGN AA
 09C1..09C4    ; Extend # Mn   [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR
 09CD          ; Extend # Mn       BENGALI SIGN VIRAMA
 09D7          ; Extend # Mc       BENGALI AU LENGTH MARK
 09E2..09E3    ; Extend # Mn   [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL
+09FE          ; Extend # Mn       BENGALI SANDHI MARK
 0A01..0A02    ; Extend # Mn   [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI
 0A3C          ; Extend # Mn       GURMUKHI SIGN NUKTA
 0A41..0A42    ; Extend # Mn   [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU
 0A47..0A48    ; Extend # Mn   [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI
 0A4B..0A4D    ; Extend # Mn   [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA

@@ -115,10 +130,11 @@
 0ABC          ; Extend # Mn       GUJARATI SIGN NUKTA
 0AC1..0AC5    ; Extend # Mn   [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E
 0AC7..0AC8    ; Extend # Mn   [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI
 0ACD          ; Extend # Mn       GUJARATI SIGN VIRAMA
 0AE2..0AE3    ; Extend # Mn   [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL
+0AFA..0AFF    ; Extend # Mn   [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
 0B01          ; Extend # Mn       ORIYA SIGN CANDRABINDU
 0B3C          ; Extend # Mn       ORIYA SIGN NUKTA
 0B3E          ; Extend # Mc       ORIYA VOWEL SIGN AA
 0B3F          ; Extend # Mn       ORIYA VOWEL SIGN I
 0B41..0B44    ; Extend # Mn   [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR

@@ -130,10 +146,11 @@
 0BBE          ; Extend # Mc       TAMIL VOWEL SIGN AA
 0BC0          ; Extend # Mn       TAMIL VOWEL SIGN II
 0BCD          ; Extend # Mn       TAMIL SIGN VIRAMA
 0BD7          ; Extend # Mc       TAMIL AU LENGTH MARK
 0C00          ; Extend # Mn       TELUGU SIGN COMBINING CANDRABINDU ABOVE
+0C04          ; Extend # Mn       TELUGU SIGN COMBINING ANUSVARA ABOVE
 0C3E..0C40    ; Extend # Mn   [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II
 0C46..0C48    ; Extend # Mn   [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI
 0C4A..0C4D    ; Extend # Mn   [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA
 0C55..0C56    ; Extend # Mn   [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK
 0C62..0C63    ; Extend # Mn   [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL

@@ -143,11 +160,12 @@
 0CC2          ; Extend # Mc       KANNADA VOWEL SIGN UU
 0CC6          ; Extend # Mn       KANNADA VOWEL SIGN E
 0CCC..0CCD    ; Extend # Mn   [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA
 0CD5..0CD6    ; Extend # Mc   [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK
 0CE2..0CE3    ; Extend # Mn   [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
-0D01          ; Extend # Mn       MALAYALAM SIGN CANDRABINDU
+0D00..0D01    ; Extend # Mn   [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
+0D3B..0D3C    ; Extend # Mn   [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
 0D3E          ; Extend # Mc       MALAYALAM VOWEL SIGN AA
 0D41..0D44    ; Extend # Mn   [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR
 0D4D          ; Extend # Mn       MALAYALAM SIGN VIRAMA
 0D57          ; Extend # Mc       MALAYALAM AU LENGTH MARK
 0D62..0D63    ; Extend # Mn   [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL

@@ -158,12 +176,11 @@
 0DDF          ; Extend # Mc       SINHALA VOWEL SIGN GAYANUKITTA
 0E31          ; Extend # Mn       THAI CHARACTER MAI HAN-AKAT
 0E34..0E3A    ; Extend # Mn   [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU
 0E47..0E4E    ; Extend # Mn   [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN
 0EB1          ; Extend # Mn       LAO VOWEL SIGN MAI KAN
-0EB4..0EB9    ; Extend # Mn   [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU
-0EBB..0EBC    ; Extend # Mn   [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO
+0EB4..0EBC    ; Extend # Mn   [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO
 0EC8..0ECD    ; Extend # Mn   [6] LAO TONE MAI EK..LAO NIGGAHITA
 0F18..0F19    ; Extend # Mn   [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS
 0F35          ; Extend # Mn       TIBETAN MARK NGAS BZUNG NYI ZLA
 0F37          ; Extend # Mn       TIBETAN MARK NGAS BZUNG SGOR RTAGS
 0F39          ; Extend # Mn       TIBETAN MARK TSA -PHRU

@@ -193,10 +210,11 @@
 17B7..17BD    ; Extend # Mn   [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA
 17C6          ; Extend # Mn       KHMER SIGN NIKAHIT
 17C9..17D3    ; Extend # Mn  [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT
 17DD          ; Extend # Mn       KHMER SIGN ATTHACAN
 180B..180D    ; Extend # Mn   [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
+1885..1886    ; Extend # Mn   [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA
 18A9          ; Extend # Mn       MONGOLIAN LETTER ALI GALI DAGALGA
 1920..1922    ; Extend # Mn   [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U
 1927..1928    ; Extend # Mn   [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O
 1932          ; Extend # Mn       LIMBU SMALL LETTER ANUSVARA
 1939..193B    ; Extend # Mn   [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I

@@ -211,10 +229,11 @@
 1A7F          ; Extend # Mn       TAI THAM COMBINING CRYPTOGRAMMIC DOT
 1AB0..1ABD    ; Extend # Mn  [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW
 1ABE          ; Extend # Me       COMBINING PARENTHESES OVERLAY
 1B00..1B03    ; Extend # Mn   [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG
 1B34          ; Extend # Mn       BALINESE SIGN REREKAN
+1B35          ; Extend # Mc       BALINESE VOWEL SIGN TEDUNG
 1B36..1B3A    ; Extend # Mn   [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA
 1B3C          ; Extend # Mn       BALINESE VOWEL SIGN LA LENGA
 1B42          ; Extend # Mn       BALINESE VOWEL SIGN PEPET
 1B6B..1B73    ; Extend # Mn   [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG
 1B80..1B81    ; Extend # Mn   [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR

@@ -231,13 +250,13 @@
 1CD4..1CE0    ; Extend # Mn  [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA
 1CE2..1CE8    ; Extend # Mn   [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL
 1CED          ; Extend # Mn       VEDIC SIGN TIRYAK
 1CF4          ; Extend # Mn       VEDIC TONE CANDRA ABOVE
 1CF8..1CF9    ; Extend # Mn   [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE
-1DC0..1DF5    ; Extend # Mn  [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE
-1DFC..1DFF    ; Extend # Mn   [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
-200C..200D    ; Extend # Cf   [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER
+1DC0..1DF9    ; Extend # Mn  [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW
+1DFB..1DFF    ; Extend # Mn   [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
+200C          ; Extend # Cf       ZERO WIDTH NON-JOINER
 20D0..20DC    ; Extend # Mn  [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
 20DD..20E0    ; Extend # Me   [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH
 20E1          ; Extend # Mn       COMBINING LEFT RIGHT ARROW ABOVE
 20E2..20E4    ; Extend # Me   [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE
 20E5..20F0    ; Extend # Mn  [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE

@@ -254,18 +273,19 @@
 A6F0..A6F1    ; Extend # Mn   [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS
 A802          ; Extend # Mn       SYLOTI NAGRI SIGN DVISVARA
 A806          ; Extend # Mn       SYLOTI NAGRI SIGN HASANTA
 A80B          ; Extend # Mn       SYLOTI NAGRI SIGN ANUSVARA
 A825..A826    ; Extend # Mn   [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E
-A8C4          ; Extend # Mn       SAURASHTRA SIGN VIRAMA
+A8C4..A8C5    ; Extend # Mn   [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU
 A8E0..A8F1    ; Extend # Mn  [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA
+A8FF          ; Extend # Mn       DEVANAGARI VOWEL SIGN AY
 A926..A92D    ; Extend # Mn   [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU
 A947..A951    ; Extend # Mn  [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R
 A980..A982    ; Extend # Mn   [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR
 A9B3          ; Extend # Mn       JAVANESE SIGN CECAK TELU
 A9B6..A9B9    ; Extend # Mn   [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT
-A9BC          ; Extend # Mn       JAVANESE VOWEL SIGN PEPET
+A9BC..A9BD    ; Extend # Mn   [2] JAVANESE VOWEL SIGN PEPET..JAVANESE CONSONANT SIGN KERET
 A9E5          ; Extend # Mn       MYANMAR SIGN SHAN SAW
 AA29..AA2E    ; Extend # Mn   [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE
 AA31..AA32    ; Extend # Mn   [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE
 AA35..AA36    ; Extend # Mn   [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA
 AA43          ; Extend # Mn       CHAM CONSONANT SIGN FINAL NG

@@ -292,10 +312,12 @@
 10A05..10A06  ; Extend # Mn   [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O
 10A0C..10A0F  ; Extend # Mn   [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA
 10A38..10A3A  ; Extend # Mn   [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW
 10A3F         ; Extend # Mn       KHAROSHTHI VIRAMA
 10AE5..10AE6  ; Extend # Mn   [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW
+10D24..10D27  ; Extend # Mn   [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
+10F46..10F50  ; Extend # Mn  [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW
 11001         ; Extend # Mn       BRAHMI SIGN ANUSVARA
 11038..11046  ; Extend # Mn  [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA
 1107F..11081  ; Extend # Mn   [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA
 110B3..110B6  ; Extend # Mn   [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI
 110B9..110BA  ; Extend # Mn   [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA

@@ -303,23 +325,28 @@
 11127..1112B  ; Extend # Mn   [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU
 1112D..11134  ; Extend # Mn   [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA
 11173         ; Extend # Mn       MAHAJANI SIGN NUKTA
 11180..11181  ; Extend # Mn   [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA
 111B6..111BE  ; Extend # Mn   [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O
-111CA..111CC  ; Extend # Mn   [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK
+111C9..111CC  ; Extend # Mn   [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK
 1122F..11231  ; Extend # Mn   [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI
 11234         ; Extend # Mn       KHOJKI SIGN ANUSVARA
 11236..11237  ; Extend # Mn   [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
+1123E         ; Extend # Mn       KHOJKI SIGN SUKUN
 112DF         ; Extend # Mn       KHUDAWADI SIGN ANUSVARA
 112E3..112EA  ; Extend # Mn   [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
 11300..11301  ; Extend # Mn   [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
-1133C         ; Extend # Mn       GRANTHA SIGN NUKTA
+1133B..1133C  ; Extend # Mn   [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA
 1133E         ; Extend # Mc       GRANTHA VOWEL SIGN AA
 11340         ; Extend # Mn       GRANTHA VOWEL SIGN II
 11357         ; Extend # Mc       GRANTHA AU LENGTH MARK
 11366..1136C  ; Extend # Mn   [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX
 11370..11374  ; Extend # Mn   [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA
+11438..1143F  ; Extend # Mn   [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI
+11442..11444  ; Extend # Mn   [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA
+11446         ; Extend # Mn       NEWA SIGN NUKTA
+1145E         ; Extend # Mn       NEWA SANDHI MARK
 114B0         ; Extend # Mc       TIRHUTA VOWEL SIGN AA
 114B3..114B8  ; Extend # Mn   [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL
 114BA         ; Extend # Mn       TIRHUTA VOWEL SIGN SHORT E
 114BD         ; Extend # Mc       TIRHUTA VOWEL SIGN SHORT O
 114BF..114C0  ; Extend # Mn   [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA

@@ -337,12 +364,42 @@
 116B0..116B5  ; Extend # Mn   [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU
 116B7         ; Extend # Mn       TAKRI SIGN NUKTA
 1171D..1171F  ; Extend # Mn   [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA
 11722..11725  ; Extend # Mn   [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
 11727..1172B  ; Extend # Mn   [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER
+1182F..11837  ; Extend # Mn   [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA
+11839..1183A  ; Extend # Mn   [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA
+119D4..119D7  ; Extend # Mn   [4] NANDINAGARI VOWEL SIGN U..NANDINAGARI VOWEL SIGN VOCALIC RR
+119DA..119DB  ; Extend # Mn   [2] NANDINAGARI VOWEL SIGN E..NANDINAGARI VOWEL SIGN AI
+119E0         ; Extend # Mn       NANDINAGARI SIGN VIRAMA
+11A01..11A0A  ; Extend # Mn  [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK
+11A33..11A38  ; Extend # Mn   [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA
+11A3B..11A3E  ; Extend # Mn   [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA
+11A47         ; Extend # Mn       ZANABAZAR SQUARE SUBJOINER
+11A51..11A56  ; Extend # Mn   [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE
+11A59..11A5B  ; Extend # Mn   [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK
+11A8A..11A96  ; Extend # Mn  [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA
+11A98..11A99  ; Extend # Mn   [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER
+11C30..11C36  ; Extend # Mn   [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L
+11C38..11C3D  ; Extend # Mn   [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA
+11C3F         ; Extend # Mn       BHAIKSUKI SIGN VIRAMA
+11C92..11CA7  ; Extend # Mn  [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA
+11CAA..11CB0  ; Extend # Mn   [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA
+11CB2..11CB3  ; Extend # Mn   [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E
+11CB5..11CB6  ; Extend # Mn   [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU
+11D31..11D36  ; Extend # Mn   [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R
+11D3A         ; Extend # Mn       MASARAM GONDI VOWEL SIGN E
+11D3C..11D3D  ; Extend # Mn   [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O
+11D3F..11D45  ; Extend # Mn   [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA
+11D47         ; Extend # Mn       MASARAM GONDI RA-KARA
+11D90..11D91  ; Extend # Mn   [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI
+11D95         ; Extend # Mn       GUNJALA GONDI SIGN ANUSVARA
+11D97         ; Extend # Mn       GUNJALA GONDI VIRAMA
+11EF3..11EF4  ; Extend # Mn   [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
 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
+16F4F         ; Extend # Mn       MIAO SIGN CONSONANT MODIFIER BAR
 16F8F..16F92  ; Extend # Mn   [4] MIAO TONE RIGHT..MIAO TONE BELOW
 1BC9D..1BC9E  ; Extend # Mn   [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK
 1D165         ; Extend # Mc       MUSICAL SYMBOL COMBINING STEM
 1D167..1D169  ; Extend # Mn   [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3
 1D16E..1D172  ; Extend # Mc   [5] MUSICAL SYMBOL COMBINING FLAG-1..MUSICAL SYMBOL COMBINING FLAG-5

@@ -354,14 +411,24 @@
 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
+1E000..1E006  ; Extend # Mn   [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
+1E008..1E018  ; Extend # Mn  [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
+1E01B..1E021  ; Extend # Mn   [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
+1E023..1E024  ; Extend # Mn   [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
+1E026..1E02A  ; Extend # Mn   [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
+1E130..1E136  ; Extend # Mn   [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
+1E2EC..1E2EF  ; Extend # Mn   [4] WANCHO TONE TUP..WANCHO TONE KOINI
 1E8D0..1E8D6  ; Extend # Mn   [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
+1E944..1E94A  ; Extend # Mn   [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA
+1F3FB..1F3FF  ; Extend # Sk   [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
+E0020..E007F  ; Extend # Cf  [96] TAG SPACE..CANCEL TAG
 E0100..E01EF  ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 
-# Total code points: 1610
+# Total code points: 1970
 
 # ================================================
 
 1F1E6..1F1FF  ; Regional_Indicator # So  [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z
 

@@ -426,11 +493,10 @@
 1A19..1A1A    ; SpacingMark # Mc   [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O
 1A55          ; SpacingMark # Mc       TAI THAM CONSONANT SIGN MEDIAL RA
 1A57          ; SpacingMark # Mc       TAI THAM CONSONANT SIGN LA TANG LAI
 1A6D..1A72    ; SpacingMark # Mc   [6] TAI THAM VOWEL SIGN OY..TAI THAM VOWEL SIGN THAM AI
 1B04          ; SpacingMark # Mc       BALINESE SIGN BISAH
-1B35          ; SpacingMark # Mc       BALINESE VOWEL SIGN TEDUNG
 1B3B          ; SpacingMark # Mc       BALINESE VOWEL SIGN RA REPA TEDUNG
 1B3D..1B41    ; SpacingMark # Mc   [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG
 1B43..1B44    ; SpacingMark # Mc   [2] BALINESE VOWEL SIGN PEPET TEDUNG..BALINESE ADEG ADEG
 1B82          ; SpacingMark # Mc       SUNDANESE SIGN PANGWISAD
 1BA1          ; SpacingMark # Mc       SUNDANESE CONSONANT SIGN PAMINGKAL

@@ -441,20 +507,20 @@
 1BEE          ; SpacingMark # Mc       BATAK VOWEL SIGN U
 1BF2..1BF3    ; SpacingMark # Mc   [2] BATAK PANGOLAT..BATAK PANONGONAN
 1C24..1C2B    ; SpacingMark # Mc   [8] LEPCHA SUBJOINED LETTER YA..LEPCHA VOWEL SIGN UU
 1C34..1C35    ; SpacingMark # Mc   [2] LEPCHA CONSONANT SIGN NYIN-DO..LEPCHA CONSONANT SIGN KANG
 1CE1          ; SpacingMark # Mc       VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA
-1CF2..1CF3    ; SpacingMark # Mc   [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
+1CF7          ; SpacingMark # Mc       VEDIC SIGN ATIKRAMA
 A823..A824    ; SpacingMark # Mc   [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIGN I
 A827          ; SpacingMark # Mc       SYLOTI NAGRI VOWEL SIGN OO
 A880..A881    ; SpacingMark # Mc   [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA
 A8B4..A8C3    ; SpacingMark # Mc  [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU
 A952..A953    ; SpacingMark # Mc   [2] REJANG CONSONANT SIGN H..REJANG VIRAMA
 A983          ; SpacingMark # Mc       JAVANESE SIGN WIGNYAN
 A9B4..A9B5    ; SpacingMark # Mc   [2] JAVANESE VOWEL SIGN TARUNG..JAVANESE VOWEL SIGN TOLONG
 A9BA..A9BB    ; SpacingMark # Mc   [2] JAVANESE VOWEL SIGN TALING..JAVANESE VOWEL SIGN DIRGA MURE
-A9BD..A9C0    ; SpacingMark # Mc   [4] JAVANESE CONSONANT SIGN KERET..JAVANESE PANGKON
+A9BE..A9C0    ; SpacingMark # Mc   [3] JAVANESE CONSONANT SIGN PENGKAL..JAVANESE PANGKON
 AA2F..AA30    ; SpacingMark # Mc   [2] CHAM VOWEL SIGN O..CHAM VOWEL SIGN AI
 AA33..AA34    ; SpacingMark # Mc   [2] CHAM CONSONANT SIGN YA..CHAM CONSONANT SIGN RA
 AA4D          ; SpacingMark # Mc       CHAM CONSONANT SIGN FINAL H
 AAEB          ; SpacingMark # Mc       MEETEI MAYEK VOWEL SIGN II
 AAEE..AAEF    ; SpacingMark # Mc   [2] MEETEI MAYEK VOWEL SIGN AU..MEETEI MAYEK VOWEL SIGN AAU

@@ -467,10 +533,11 @@
 11002         ; SpacingMark # Mc       BRAHMI SIGN VISARGA
 11082         ; SpacingMark # Mc       KAITHI SIGN VISARGA
 110B0..110B2  ; SpacingMark # Mc   [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II
 110B7..110B8  ; SpacingMark # Mc   [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU
 1112C         ; SpacingMark # Mc       CHAKMA VOWEL SIGN E
+11145..11146  ; SpacingMark # Mc   [2] CHAKMA VOWEL SIGN AA..CHAKMA VOWEL SIGN EI
 11182         ; SpacingMark # Mc       SHARADA SIGN VISARGA
 111B3..111B5  ; SpacingMark # Mc   [3] SHARADA VOWEL SIGN AA..SHARADA VOWEL SIGN II
 111BF..111C0  ; SpacingMark # Mc   [2] SHARADA VOWEL SIGN AU..SHARADA SIGN VIRAMA
 1122C..1122E  ; SpacingMark # Mc   [3] KHOJKI VOWEL SIGN AA..KHOJKI VOWEL SIGN II
 11232..11233  ; SpacingMark # Mc   [2] KHOJKI VOWEL SIGN O..KHOJKI VOWEL SIGN AU

@@ -480,10 +547,13 @@
 1133F         ; SpacingMark # Mc       GRANTHA VOWEL SIGN I
 11341..11344  ; SpacingMark # Mc   [4] GRANTHA VOWEL SIGN U..GRANTHA VOWEL SIGN VOCALIC RR
 11347..11348  ; SpacingMark # Mc   [2] GRANTHA VOWEL SIGN EE..GRANTHA VOWEL SIGN AI
 1134B..1134D  ; SpacingMark # Mc   [3] GRANTHA VOWEL SIGN OO..GRANTHA SIGN VIRAMA
 11362..11363  ; SpacingMark # Mc   [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL
+11435..11437  ; SpacingMark # Mc   [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II
+11440..11441  ; SpacingMark # Mc   [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU
+11445         ; SpacingMark # Mc       NEWA SIGN VISARGA
 114B1..114B2  ; SpacingMark # Mc   [2] TIRHUTA VOWEL SIGN I..TIRHUTA VOWEL SIGN II
 114B9         ; SpacingMark # Mc       TIRHUTA VOWEL SIGN E
 114BB..114BC  ; SpacingMark # Mc   [2] TIRHUTA VOWEL SIGN AI..TIRHUTA VOWEL SIGN O
 114BE         ; SpacingMark # Mc       TIRHUTA VOWEL SIGN AU
 114C1         ; SpacingMark # Mc       TIRHUTA SIGN VISARGA

@@ -496,15 +566,32 @@
 116AC         ; SpacingMark # Mc       TAKRI SIGN VISARGA
 116AE..116AF  ; SpacingMark # Mc   [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II
 116B6         ; SpacingMark # Mc       TAKRI SIGN VIRAMA
 11720..11721  ; SpacingMark # Mc   [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA
 11726         ; SpacingMark # Mc       AHOM VOWEL SIGN E
-16F51..16F7E  ; SpacingMark # Mc  [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
+1182C..1182E  ; SpacingMark # Mc   [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II
+11838         ; SpacingMark # Mc       DOGRA SIGN VISARGA
+119D1..119D3  ; SpacingMark # Mc   [3] NANDINAGARI VOWEL SIGN AA..NANDINAGARI VOWEL SIGN II
+119DC..119DF  ; SpacingMark # Mc   [4] NANDINAGARI VOWEL SIGN O..NANDINAGARI SIGN VISARGA
+119E4         ; SpacingMark # Mc       NANDINAGARI VOWEL SIGN PRISHTHAMATRA E
+11A39         ; SpacingMark # Mc       ZANABAZAR SQUARE SIGN VISARGA
+11A57..11A58  ; SpacingMark # Mc   [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU
+11A97         ; SpacingMark # Mc       SOYOMBO SIGN VISARGA
+11C2F         ; SpacingMark # Mc       BHAIKSUKI VOWEL SIGN AA
+11C3E         ; SpacingMark # Mc       BHAIKSUKI SIGN VISARGA
+11CA9         ; SpacingMark # Mc       MARCHEN SUBJOINED LETTER YA
+11CB1         ; SpacingMark # Mc       MARCHEN VOWEL SIGN I
+11CB4         ; SpacingMark # Mc       MARCHEN VOWEL SIGN O
+11D8A..11D8E  ; SpacingMark # Mc   [5] GUNJALA GONDI VOWEL SIGN AA..GUNJALA GONDI VOWEL SIGN UU
+11D93..11D94  ; SpacingMark # Mc   [2] GUNJALA GONDI VOWEL SIGN OO..GUNJALA GONDI VOWEL SIGN AU
+11D96         ; SpacingMark # Mc       GUNJALA GONDI SIGN VISARGA
+11EF5..11EF6  ; SpacingMark # Mc   [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
+16F51..16F87  ; SpacingMark # Mc  [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI
 1D166         ; SpacingMark # Mc       MUSICAL SYMBOL COMBINING SPRECHGESANG STEM
 1D16D         ; SpacingMark # Mc       MUSICAL SYMBOL COMBINING AUGMENTATION DOT
 
-# Total code points: 330
+# Total code points: 375
 
 # ================================================
 
 1100..115F    ; L # Lo  [96] HANGUL CHOSEONG KIYEOK..HANGUL CHOSEONG FILLER
 A960..A97C    ; L # Lo  [29] HANGUL CHOSEONG TIKEUT-MIEUM..HANGUL CHOSEONG SSANGYEORINHIEUH

@@ -1331,6 +1418,12 @@
 D76D..D787    ; LVT # Lo  [27] HANGUL SYLLABLE HYIG..HANGUL SYLLABLE HYIH
 D789..D7A3    ; LVT # Lo  [27] HANGUL SYLLABLE HIG..HANGUL SYLLABLE HIH
 
 # Total code points: 10773
 
+# ================================================
+
+200D          ; ZWJ # Cf       ZERO WIDTH JOINER
+
+# Total code points: 1
+
 # EOF
< prev index next >