summaryrefslogtreecommitdiffstats
path: root/util/unicode/data/GraphemeBreakProperty.txt
diff options
context:
space:
mode:
Diffstat (limited to 'util/unicode/data/GraphemeBreakProperty.txt')
-rw-r--r--util/unicode/data/GraphemeBreakProperty.txt61
1 files changed, 44 insertions, 17 deletions
diff --git a/util/unicode/data/GraphemeBreakProperty.txt b/util/unicode/data/GraphemeBreakProperty.txt
index 6ee92f6eec..12453cbdb5 100644
--- a/util/unicode/data/GraphemeBreakProperty.txt
+++ b/util/unicode/data/GraphemeBreakProperty.txt
@@ -1,11 +1,11 @@
-# GraphemeBreakProperty-13.0.0.txt
-# Date: 2019-10-21, 14:30:35 GMT
-# © 2019 Unicode®, Inc.
+# GraphemeBreakProperty-15.1.0.txt
+# Date: 2023-01-05, 20:34:41 GMT
+# © 2023 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
+# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
-# For documentation, see http://www.unicode.org/reports/tr44/
+# For documentation, see https://www.unicode.org/reports/tr44/
# ================================================
@@ -21,6 +21,7 @@
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
+0890..0891 ; Prepend # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE
08E2 ; Prepend # Cf ARABIC DISPUTED END OF AYAH
0D4E ; Prepend # Lo MALAYALAM LETTER DOT REPH
110BD ; Prepend # Cf KAITHI NUMBER SIGN
@@ -31,8 +32,9 @@
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
+11F02 ; Prepend # Lo KAWI SIGN REPHA
-# Total code points: 24
+# Total code points: 27
# ================================================
@@ -66,7 +68,7 @@
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
-13430..13438 ; Control # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT
+13430..1343F ; Control # Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE
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>
@@ -75,7 +77,7 @@ E0002..E001F ; Control # Cn [30] <reserved-E0002>..<reserved-E001F>
E0080..E00FF ; Control # Cn [128] <reserved-E0080>..<reserved-E00FF>
E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
-# Total code points: 3886
+# Total code points: 3893
# ================================================
@@ -104,7 +106,8 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
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
+0898..089F ; Extend # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA
+08CA..08E1 ; Extend # Mn [24] ARABIC SMALL HIGH FARSI YEH..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
@@ -151,6 +154,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
0BD7 ; Extend # Mc TAMIL AU LENGTH MARK
0C00 ; Extend # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE
0C04 ; Extend # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE
+0C3C ; Extend # Mn TELUGU SIGN NUKTA
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
@@ -182,7 +186,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
0E47..0E4E ; Extend # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN
0EB1 ; Extend # Mn LAO VOWEL SIGN MAI KAN
0EB4..0EBC ; Extend # Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO
-0EC8..0ECD ; Extend # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA
+0EC8..0ECE ; Extend # Mn [7] LAO TONE MAI EK..LAO YAMAKKAN
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
@@ -206,7 +210,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
109D ; Extend # Mn MYANMAR VOWEL SIGN AITON AI
135D..135F ; Extend # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK
1712..1714 ; Extend # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA
-1732..1734 ; Extend # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD
+1732..1733 ; Extend # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U
1752..1753 ; Extend # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U
1772..1773 ; Extend # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U
17B4..17B5 ; Extend # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
@@ -215,6 +219,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
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
+180F ; Extend # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR
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
@@ -232,7 +237,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
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
-1ABF..1AC0 ; Extend # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW
+1ABF..1ACE ; Extend # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T
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
@@ -256,8 +261,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
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..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
+1DC0..1DFF ; Extend # Mn [64] COMBINING DOTTED GRAVE ACCENT..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
@@ -321,12 +325,17 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
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
10EAB..10EAC ; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK
+10EFD..10EFF ; Extend # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA
10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW
+10F82..10F85 ; Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW
11001 ; Extend # Mn BRAHMI SIGN ANUSVARA
11038..11046 ; Extend # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA
+11070 ; Extend # Mn BRAHMI SIGN OLD TAMIL VIRAMA
+11073..11074 ; Extend # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O
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
+110C2 ; Extend # Mn KAITHI VOWEL SIGN VOCALIC R
11100..11102 ; Extend # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA
11127..1112B ; Extend # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU
1112D..11134 ; Extend # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA
@@ -339,6 +348,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
11234 ; Extend # Mn KHOJKI SIGN ANUSVARA
11236..11237 ; Extend # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
1123E ; Extend # Mn KHOJKI SIGN SUKUN
+11241 ; Extend # Mn KHOJKI VOWEL SIGN VOCALIC R
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
@@ -406,12 +416,20 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
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
+11F00..11F01 ; Extend # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA
+11F36..11F3A ; Extend # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R
+11F40 ; Extend # Mn KAWI VOWEL SIGN EU
+11F42 ; Extend # Mn KAWI CONJOINER
+13440 ; Extend # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY
+13447..13455 ; Extend # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED
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
16FE4 ; Extend # Mn KHITAN SMALL SCRIPT FILLER
1BC9D..1BC9E ; Extend # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK
+1CF00..1CF2D ; Extend # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT
+1CF30..1CF46 ; Extend # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG
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
@@ -430,15 +448,18 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
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
+1E08F ; Extend # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
1E130..1E136 ; Extend # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
+1E2AE ; Extend # Mn TOTO SIGN RISING TONE
1E2EC..1E2EF ; Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI
+1E4EC..1E4EF ; Extend # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH
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: 1984
+# Total code points: 2130
# ================================================
@@ -479,6 +500,7 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
0CC3..0CC4 ; SpacingMark # Mc [2] KANNADA VOWEL SIGN VOCALIC R..KANNADA VOWEL SIGN VOCALIC RR
0CC7..0CC8 ; SpacingMark # Mc [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI
0CCA..0CCB ; SpacingMark # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO
+0CF3 ; SpacingMark # Mc KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
0D02..0D03 ; SpacingMark # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
0D3F..0D40 ; SpacingMark # Mc [2] MALAYALAM VOWEL SIGN I..MALAYALAM VOWEL SIGN II
0D46..0D48 ; SpacingMark # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI
@@ -495,6 +517,8 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
103B..103C ; SpacingMark # Mc [2] MYANMAR CONSONANT SIGN MEDIAL YA..MYANMAR CONSONANT SIGN MEDIAL RA
1056..1057 ; SpacingMark # Mc [2] MYANMAR VOWEL SIGN VOCALIC R..MYANMAR VOWEL SIGN VOCALIC RR
1084 ; SpacingMark # Mc MYANMAR VOWEL SIGN SHAN E
+1715 ; SpacingMark # Mc TAGALOG SIGN PAMUDPOD
+1734 ; SpacingMark # Mc HANUNOO SIGN PAMUDPOD
17B6 ; SpacingMark # Mc KHMER VOWEL SIGN AA
17BE..17C5 ; SpacingMark # Mc [8] KHMER VOWEL SIGN OE..KHMER VOWEL SIGN AU
17C7..17C8 ; SpacingMark # Mc [2] KHMER SIGN REAHMUK..KHMER SIGN YUUKALEAPINTU
@@ -579,7 +603,6 @@ ABEC ; SpacingMark # Mc MEETEI MAYEK LUM IYEK
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
1182C..1182E ; SpacingMark # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II
11838 ; SpacingMark # Mc DOGRA SIGN VISARGA
@@ -603,12 +626,16 @@ ABEC ; SpacingMark # Mc MEETEI MAYEK LUM IYEK
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
+11F03 ; SpacingMark # Mc KAWI SIGN VISARGA
+11F34..11F35 ; SpacingMark # Mc [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA
+11F3E..11F3F ; SpacingMark # Mc [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI
+11F41 ; SpacingMark # Mc KAWI SIGN KILLER
16F51..16F87 ; SpacingMark # Mc [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI
16FF0..16FF1 ; SpacingMark # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
1D166 ; SpacingMark # Mc MUSICAL SYMBOL COMBINING SPRECHGESANG STEM
1D16D ; SpacingMark # Mc MUSICAL SYMBOL COMBINING AUGMENTATION DOT
-# Total code points: 388
+# Total code points: 395
# ================================================