perl
view release on metacpan or search on metacpan
lib/unicore/auxiliary/GraphemeBreakProperty.txt view on Meta::CPAN
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see https://www.unicode.org/reports/tr44/
# ================================================
# Property: Grapheme_Cluster_Break
# All code points not explicitly listed for Grapheme_Cluster_Break
# have the value Other (XX).
# @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
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
110CD ; Prepend # Cf KAITHI NUMBER SIGN ABOVE
111C2..111C3 ; Prepend # Lo [2] SHARADA SIGN JIHVAMULIYA..SHARADA SIGN UPADHMANIYA
113D1 ; Prepend # Lo TULU-TIGALARI REPHA
1193F ; Prepend # Lo DIVES AKURU PREFIXED NASAL SIGN
11941 ; Prepend # Lo DIVES AKURU INITIAL RA
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: 28
# ================================================
000D ; CR # Cc <control-000D>
# Total code points: 1
# ================================================
000A ; LF # Cc <control-000A>
# Total code points: 1
# ================================================
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
061C ; Control # Cf ARABIC LETTER 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
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..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>
E0001 ; Control # Cf LANGUAGE TAG
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: 3893
# ================================================
0300..036F ; Extend # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X
0483..0487 ; Extend # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE
0488..0489 ; Extend # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN
0591..05BD ; Extend # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG
05BF ; Extend # Mn HEBREW POINT RAFE
05C1..05C2 ; Extend # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT
05C4..05C5 ; Extend # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT
05C7 ; Extend # Mn HEBREW POINT QAMATS QATAN
0610..061A ; Extend # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA
064B..065F ; Extend # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW
0670 ; Extend # Mn ARABIC LETTER SUPERSCRIPT ALEF
06D6..06DC ; Extend # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN
06DF..06E4 ; Extend # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA
06E7..06E8 ; Extend # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON
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
0897..089F ; Extend # Mn [9] ARABIC PEPET..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
0941..0948 ; Extend # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI
094D ; Extend # Mn DEVANAGARI SIGN VIRAMA
0951..0957 ; Extend # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE
0962..0963 ; Extend # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL
0981 ; Extend # Mn BENGALI SIGN CANDRABINDU
09BC ; Extend # Mn BENGALI SIGN NUKTA
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
( run in 0.413 second using v1.01-cache-2.11-cpan-71847e10f99 )