mirror of
git://git.code.sf.net/p/sbcl/sbcl
synced 2026-09-10 07:26:40 -04:00
update to Unicode 8.0.0
(except for Confusables, which got updated to 12.0.0 at some point) Unicode 8.0.0 is not very recent (though more recent than Unicode 7.0.0, which we supported previously). A large point of this exercise was to discover the irritating manual fixups to SBCL source and to the Unicode data files which following commits will lessen the need for, after which an update to Unicode 9, 10, 11, or 12 should be more straightforward. In the process, fix a bug in line breaking after a hebrew letter followed by a hyphen. (This was a bug in our Unicode 7.0.0 support, but the test case was only included with Unicode 8.0.0)
This commit is contained in:
parent
df5a595ba9
commit
5d8a6cfca2
|
|
@ -187,7 +187,7 @@
|
|||
(setf **character-cases** table))
|
||||
|
||||
(setf **character-collations**
|
||||
(let* ((table (make-hash-table :size 27978
|
||||
(let* ((table (make-hash-table :size 30057
|
||||
#+64-bit :test #+64-bit #'eq))
|
||||
(index 0)
|
||||
(info (make-ubn-vector ,collations 4))
|
||||
|
|
@ -209,7 +209,7 @@
|
|||
(incf index))
|
||||
(setf (gethash (apply #'pack-3-codepoints codepoints) table)
|
||||
key)))
|
||||
(assert (= (hash-table-count table) 27978))
|
||||
(assert (= (hash-table-count table) 30057))
|
||||
table))))
|
||||
|
||||
,(with-open-file
|
||||
|
|
|
|||
|
|
@ -1115,7 +1115,7 @@ sentence breaking rules specified in UAX #29"
|
|||
((eql state :nobrk-next) (nobrk) (setf state nil))
|
||||
((member c1 '(:sep :cr :lf)) (brk))
|
||||
((and (eql c1 :aterm) (eql c2 :numeric)) (nobrk))
|
||||
((and (eql c1 :upper) (eql c2 :aterm)
|
||||
((and (member c1 '(:lower :upper)) (eql c2 :aterm)
|
||||
(eql c3 :upper)) (nobrk) (setf state :nobrk-next))
|
||||
((or (and (member c1 '(:sterm :aterm)) (member c2 '(:close :sp))
|
||||
(member c3 '(:scontinue :sterm :aterm)))
|
||||
|
|
@ -1265,12 +1265,16 @@ sentence breaking rules specified in UAX #29"
|
|||
(between :qu :any :cant)
|
||||
(between :any :cb :can)
|
||||
(between :cb :any :can)
|
||||
(when (and (eql t1 :hl) (member t2 '(:hy :ba)))
|
||||
(cmpush :cant) (cmpush second)
|
||||
(setf first second tail (cdr tail))
|
||||
(setf second (car tail))
|
||||
(cmpush (if second :cant :must)) (cmpush second)
|
||||
(setf after-spaces :can) (go tail))
|
||||
(between :any '(:ba :hy :ns) :cant)
|
||||
(between :bb :any :cant)
|
||||
(when (and (eql t1 :hl) (eql t2 :hy))
|
||||
(cmpush :cant) (cmpush second)
|
||||
(setf after-spaces :can) (go tail))
|
||||
(between '(:al :hl :id :in :nu) :in :cant)
|
||||
(between :sy :hl :cant)
|
||||
(between '(:al :hl :ex :id :in :nu) :in :cant)
|
||||
(between :id :po :cant)
|
||||
(between '(:al :hl) :nu :cant)
|
||||
(between '(:nu :po) '(:al :hl) :cant)
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load diff
|
|
@ -1,8 +1,8 @@
|
|||
# DerivedBidiClass-7.0.0.txt
|
||||
# Date: 2014-02-07, 18:42:07 GMT [MD]
|
||||
# DerivedBidiClass-8.0.0.txt
|
||||
# Date: 2015-02-13, 13:47:08 GMT [MD]
|
||||
#
|
||||
# Unicode Character Database
|
||||
# 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
|
||||
# For documentation, see http://www.unicode.org/reports/tr44/
|
||||
|
||||
|
|
@ -165,6 +165,7 @@
|
|||
0AE0..0AE1 ; L # Lo [2] GUJARATI LETTER VOCALIC RR..GUJARATI LETTER VOCALIC LL
|
||||
0AE6..0AEF ; L # Nd [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE
|
||||
0AF0 ; L # Po GUJARATI ABBREVIATION SIGN
|
||||
0AF9 ; L # Lo GUJARATI LETTER ZHA
|
||||
0B02..0B03 ; L # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA
|
||||
0B05..0B0C ; L # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L
|
||||
0B0F..0B10 ; L # Lo [2] ORIYA LETTER E..ORIYA LETTER AI
|
||||
|
|
@ -209,7 +210,7 @@
|
|||
0C2A..0C39 ; L # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA
|
||||
0C3D ; L # Lo TELUGU SIGN AVAGRAHA
|
||||
0C41..0C44 ; L # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR
|
||||
0C58..0C59 ; L # Lo [2] TELUGU LETTER TSA..TELUGU LETTER DZA
|
||||
0C58..0C5A ; L # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA
|
||||
0C60..0C61 ; L # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL
|
||||
0C66..0C6F ; L # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE
|
||||
0C7F ; L # So TELUGU SIGN TUUMU
|
||||
|
|
@ -241,7 +242,7 @@
|
|||
0D4A..0D4C ; L # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU
|
||||
0D4E ; L # Lo MALAYALAM LETTER DOT REPH
|
||||
0D57 ; L # Mc MALAYALAM AU LENGTH MARK
|
||||
0D60..0D61 ; L # Lo [2] MALAYALAM LETTER VOCALIC RR..MALAYALAM LETTER VOCALIC LL
|
||||
0D5F..0D61 ; L # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL
|
||||
0D66..0D6F ; L # Nd [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE
|
||||
0D70..0D75 ; L # No [6] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE QUARTERS
|
||||
0D79 ; L # So MALAYALAM DATE MARK
|
||||
|
|
@ -355,7 +356,8 @@
|
|||
1360..1368 ; L # Po [9] ETHIOPIC SECTION MARK..ETHIOPIC PARAGRAPH SEPARATOR
|
||||
1369..137C ; L # No [20] ETHIOPIC DIGIT ONE..ETHIOPIC NUMBER TEN THOUSAND
|
||||
1380..138F ; L # Lo [16] ETHIOPIC SYLLABLE SEBATBEIT MWA..ETHIOPIC SYLLABLE PWE
|
||||
13A0..13F4 ; L # Lo [85] CHEROKEE LETTER A..CHEROKEE LETTER YV
|
||||
13A0..13F5 ; L # L& [86] CHEROKEE LETTER A..CHEROKEE LETTER MV
|
||||
13F8..13FD ; L # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV
|
||||
1401..166C ; L # Lo [620] CANADIAN SYLLABICS E..CANADIAN SYLLABICS CARRIER TTSA
|
||||
166D..166E ; L # Po [2] CANADIAN SYLLABICS CHI SIGN..CANADIAN SYLLABICS FULL STOP
|
||||
166F..167F ; L # Lo [17] CANADIAN SYLLABICS QAI..CANADIAN SYLLABICS BLACKFOOT W
|
||||
|
|
@ -396,9 +398,7 @@
|
|||
1950..196D ; L # Lo [30] TAI LE LETTER KA..TAI LE LETTER AI
|
||||
1970..1974 ; L # Lo [5] TAI LE LETTER TONE-2..TAI LE LETTER TONE-6
|
||||
1980..19AB ; L # Lo [44] NEW TAI LUE LETTER HIGH QA..NEW TAI LUE LETTER LOW SUA
|
||||
19B0..19C0 ; L # Mc [17] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE VOWEL SIGN IY
|
||||
19C1..19C7 ; L # Lo [7] NEW TAI LUE LETTER FINAL V..NEW TAI LUE LETTER FINAL B
|
||||
19C8..19C9 ; L # Mc [2] NEW TAI LUE TONE MARK-1..NEW TAI LUE TONE MARK-2
|
||||
19B0..19C9 ; L # Lo [26] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2
|
||||
19D0..19D9 ; L # Nd [10] NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE
|
||||
19DA ; L # No NEW TAI LUE THAM DIGIT ONE
|
||||
1A00..1A16 ; L # Lo [23] BUGINESE LETTER KA..BUGINESE LETTER HA
|
||||
|
|
@ -567,7 +567,7 @@
|
|||
337B..33DD ; L # So [99] SQUARE ERA NAME HEISEI..SQUARE WB
|
||||
33E0..33FE ; L # So [31] IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY ONE..IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY THIRTY-ONE
|
||||
3400..4DB5 ; L # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
|
||||
4E00..9FCC ; L # Lo [20941] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCC
|
||||
4E00..9FD5 ; L # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
|
||||
A000..A014 ; L # Lo [21] YI SYLLABLE IT..YI SYLLABLE E
|
||||
A015 ; L # Lm YI SYLLABLE WU
|
||||
A016..A48C ; L # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR
|
||||
|
|
@ -591,8 +591,9 @@ A770 ; L # Lm MODIFIER LETTER US
|
|||
A771..A787 ; L # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T
|
||||
A789..A78A ; L # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN
|
||||
A78B..A78E ; L # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
|
||||
A78F ; L # Lo LATIN LETTER SINOLOGICAL DOT
|
||||
A790..A7AD ; L # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT
|
||||
A7B0..A7B1 ; L # L& [2] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER TURNED T
|
||||
A7B0..A7B7 ; L # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA
|
||||
A7F7 ; L # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I
|
||||
A7F8..A7F9 ; L # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
|
||||
A7FA ; L # L& LATIN LETTER SMALL CAPITAL TURNED M
|
||||
|
|
@ -613,6 +614,8 @@ A8D0..A8D9 ; L # Nd [10] SAURASHTRA DIGIT ZERO..SAURASHTRA DIGIT NINE
|
|||
A8F2..A8F7 ; L # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA
|
||||
A8F8..A8FA ; L # Po [3] DEVANAGARI SIGN PUSHPIKA..DEVANAGARI CARET
|
||||
A8FB ; L # Lo DEVANAGARI HEADSTROKE
|
||||
A8FC ; L # Po DEVANAGARI SIGN SIDDHAM
|
||||
A8FD ; L # Lo DEVANAGARI JAIN OM
|
||||
A900..A909 ; L # Nd [10] KAYAH LI DIGIT ZERO..KAYAH LI DIGIT NINE
|
||||
A90A..A925 ; L # Lo [28] KAYAH LI LETTER KA..KAYAH LI LETTER OO
|
||||
A92E..A92F ; L # Po [2] KAYAH LI SIGN CWI..KAYAH LI SIGN SHYA
|
||||
|
|
@ -673,7 +676,8 @@ AB28..AB2E ; L # Lo [7] ETHIOPIC SYLLABLE BBA..ETHIOPIC SYLLABLE BBO
|
|||
AB30..AB5A ; L # L& [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG
|
||||
AB5B ; L # Sk MODIFIER BREVE WITH INVERTED BREVE
|
||||
AB5C..AB5F ; L # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK
|
||||
AB64..AB65 ; L # L& [2] LATIN SMALL LETTER INVERTED ALPHA..GREEK LETTER SMALL CAPITAL OMEGA
|
||||
AB60..AB65 ; L # L& [6] LATIN SMALL LETTER SAKHA YAT..GREEK LETTER SMALL CAPITAL OMEGA
|
||||
AB70..ABBF ; L # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA
|
||||
ABC0..ABE2 ; L # Lo [35] MEETEI MAYEK LETTER KOK..MEETEI MAYEK LETTER I LONSUM
|
||||
ABE3..ABE4 ; L # Mc [2] MEETEI MAYEK VOWEL SIGN ONAP..MEETEI MAYEK VOWEL SIGN INAP
|
||||
ABE6..ABE7 ; L # Mc [2] MEETEI MAYEK VOWEL SIGN YENAP..MEETEI MAYEK VOWEL SIGN SOUNAP
|
||||
|
|
@ -762,10 +766,13 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER
|
|||
111B3..111B5 ; L # Mc [3] SHARADA VOWEL SIGN AA..SHARADA VOWEL SIGN II
|
||||
111BF..111C0 ; L # Mc [2] SHARADA VOWEL SIGN AU..SHARADA SIGN VIRAMA
|
||||
111C1..111C4 ; L # Lo [4] SHARADA SIGN AVAGRAHA..SHARADA OM
|
||||
111C5..111C8 ; L # Po [4] SHARADA DANDA..SHARADA SEPARATOR
|
||||
111C5..111C9 ; L # Po [5] SHARADA DANDA..SHARADA SANDHI MARK
|
||||
111CD ; L # Po SHARADA SUTRA MARK
|
||||
111D0..111D9 ; L # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE
|
||||
111DA ; L # Lo SHARADA EKAM
|
||||
111DB ; L # Po SHARADA SIGN SIDDHAM
|
||||
111DC ; L # Lo SHARADA HEADSTROKE
|
||||
111DD..111DF ; L # Po [3] SHARADA CONTINUATION SIGN..SHARADA SECTION MARK-2
|
||||
111E1..111F4 ; L # No [20] SINHALA ARCHAIC DIGIT ONE..SINHALA ARCHAIC NUMBER ONE THOUSAND
|
||||
11200..11211 ; L # Lo [18] KHOJKI LETTER A..KHOJKI LETTER JJA
|
||||
11213..1122B ; L # Lo [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA
|
||||
|
|
@ -773,6 +780,12 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER
|
|||
11232..11233 ; L # Mc [2] KHOJKI VOWEL SIGN O..KHOJKI VOWEL SIGN AU
|
||||
11235 ; L # Mc KHOJKI SIGN VIRAMA
|
||||
11238..1123D ; L # Po [6] KHOJKI DANDA..KHOJKI ABBREVIATION SIGN
|
||||
11280..11286 ; L # Lo [7] MULTANI LETTER A..MULTANI LETTER GA
|
||||
11288 ; L # Lo MULTANI LETTER GHA
|
||||
1128A..1128D ; L # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA
|
||||
1128F..1129D ; L # Lo [15] MULTANI LETTER NYA..MULTANI LETTER BA
|
||||
1129F..112A8 ; L # Lo [10] MULTANI LETTER BHA..MULTANI LETTER RHA
|
||||
112A9 ; L # Po MULTANI SECTION MARK
|
||||
112B0..112DE ; L # Lo [47] KHUDAWADI LETTER A..KHUDAWADI LETTER HA
|
||||
112E0..112E2 ; L # Mc [3] KHUDAWADI VOWEL SIGN AA..KHUDAWADI VOWEL SIGN II
|
||||
112F0..112F9 ; L # Nd [10] KHUDAWADI DIGIT ZERO..KHUDAWADI DIGIT NINE
|
||||
|
|
@ -788,6 +801,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER
|
|||
11341..11344 ; L # Mc [4] GRANTHA VOWEL SIGN U..GRANTHA VOWEL SIGN VOCALIC RR
|
||||
11347..11348 ; L # Mc [2] GRANTHA VOWEL SIGN EE..GRANTHA VOWEL SIGN AI
|
||||
1134B..1134D ; L # Mc [3] GRANTHA VOWEL SIGN OO..GRANTHA SIGN VIRAMA
|
||||
11350 ; L # Lo GRANTHA OM
|
||||
11357 ; L # Mc GRANTHA AU LENGTH MARK
|
||||
1135D..11361 ; L # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL
|
||||
11362..11363 ; L # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL
|
||||
|
|
@ -804,7 +818,8 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER
|
|||
115AF..115B1 ; L # Mc [3] SIDDHAM VOWEL SIGN AA..SIDDHAM VOWEL SIGN II
|
||||
115B8..115BB ; L # Mc [4] SIDDHAM VOWEL SIGN E..SIDDHAM VOWEL SIGN AU
|
||||
115BE ; L # Mc SIDDHAM SIGN VISARGA
|
||||
115C1..115C9 ; L # Po [9] SIDDHAM SIGN SIDDHAM..SIDDHAM END OF TEXT MARK
|
||||
115C1..115D7 ; L # Po [23] SIDDHAM SIGN SIDDHAM..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES
|
||||
115D8..115DB ; L # Lo [4] SIDDHAM LETTER THREE-CIRCLE ALTERNATE I..SIDDHAM LETTER ALTERNATE U
|
||||
11600..1162F ; L # Lo [48] MODI LETTER A..MODI LETTER LLA
|
||||
11630..11632 ; L # Mc [3] MODI VOWEL SIGN AA..MODI VOWEL SIGN II
|
||||
1163B..1163C ; L # Mc [2] MODI VOWEL SIGN O..MODI VOWEL SIGN AU
|
||||
|
|
@ -817,15 +832,24 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER
|
|||
116AE..116AF ; L # Mc [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II
|
||||
116B6 ; L # Mc TAKRI SIGN VIRAMA
|
||||
116C0..116C9 ; L # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE
|
||||
11700..11719 ; L # Lo [26] AHOM LETTER KA..AHOM LETTER JHA
|
||||
11720..11721 ; L # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA
|
||||
11726 ; L # Mc AHOM VOWEL SIGN E
|
||||
11730..11739 ; L # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE
|
||||
1173A..1173B ; L # No [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY
|
||||
1173C..1173E ; L # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI
|
||||
1173F ; L # So AHOM SYMBOL VI
|
||||
118A0..118DF ; L # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO
|
||||
118E0..118E9 ; L # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE
|
||||
118EA..118F2 ; L # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY
|
||||
118FF ; L # Lo WARANG CITI OM
|
||||
11AC0..11AF8 ; L # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
|
||||
12000..12398 ; L # Lo [921] CUNEIFORM SIGN A..CUNEIFORM SIGN UM TIMES ME
|
||||
12000..12399 ; L # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
|
||||
12400..1246E ; L # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
|
||||
12470..12474 ; L # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON
|
||||
12480..12543 ; L # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
|
||||
13000..1342E ; L # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
|
||||
14400..14646 ; L # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530
|
||||
16800..16A38 ; L # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ
|
||||
16A40..16A5E ; L # Lo [31] MRO LETTER TA..MRO LETTER TEK
|
||||
16A60..16A69 ; L # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE
|
||||
|
|
@ -861,7 +885,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER
|
|||
1D16D..1D172 ; L # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5
|
||||
1D183..1D184 ; L # So [2] MUSICAL SYMBOL ARPEGGIATO UP..MUSICAL SYMBOL ARPEGGIATO DOWN
|
||||
1D18C..1D1A9 ; L # So [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH
|
||||
1D1AE..1D1DD ; L # So [48] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL PES SUBPUNCTIS
|
||||
1D1AE..1D1E8 ; L # So [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN
|
||||
1D360..1D371 ; L # No [18] COUNTING ROD UNIT DIGIT ONE..COUNTING ROD TENS DIGIT NINE
|
||||
1D400..1D454 ; L # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G
|
||||
1D456..1D49C ; L # L& [71] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL SCRIPT CAPITAL A
|
||||
|
|
@ -898,6 +922,12 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER
|
|||
1D7A9 ; L # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC NABLA
|
||||
1D7AA..1D7C2 ; L # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA
|
||||
1D7C4..1D7CB ; L # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA
|
||||
1D800..1D9FF ; L # So [512] SIGNWRITING HAND-FIST INDEX..SIGNWRITING HEAD
|
||||
1DA37..1DA3A ; L # So [4] SIGNWRITING AIR BLOW SMALL ROTATIONS..SIGNWRITING BREATH EXHALE
|
||||
1DA6D..1DA74 ; L # So [8] SIGNWRITING SHOULDER HIP SPINE..SIGNWRITING TORSO-FLOORPLANE TWISTING
|
||||
1DA76..1DA83 ; L # So [14] SIGNWRITING LIMB COMBINATION..SIGNWRITING LOCATION DEPTH
|
||||
1DA85..1DA86 ; L # So [2] SIGNWRITING LOCATION TORSO..SIGNWRITING LOCATION LIMBS DIGITS
|
||||
1DA87..1DA8B ; L # Po [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS
|
||||
1F110..1F12E ; L # So [31] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED WZ
|
||||
1F130..1F169 ; L # So [58] SQUARED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
|
||||
1F170..1F19A ; L # So [43] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VS
|
||||
|
|
@ -908,12 +938,13 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER
|
|||
20000..2A6D6 ; L # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
|
||||
2A700..2B734 ; L # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
|
||||
2B740..2B81D ; L # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
|
||||
2B820..2CEA1 ; L # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
|
||||
2F800..2FA1D ; L # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
|
||||
F0000..FFFFD ; L # Co [65534] <private-use-F0000>..<private-use-FFFFD>
|
||||
100000..10FFFD; L # Co [65534] <private-use-100000>..<private-use-10FFFD>
|
||||
|
||||
# The above property value applies to 856513 code points not listed here.
|
||||
# Total code points: 1097670
|
||||
# The above property value applies to 848999 code points not listed here.
|
||||
# Total code points: 1097474
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -980,7 +1011,12 @@ FB46..FB4F ; R # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE AL
|
|||
10880..1089E ; R # Lo [31] NABATAEAN LETTER FINAL ALEPH..NABATAEAN LETTER TAW
|
||||
1089F..108A6 ; R # Cn [8] <reserved-1089F>..<reserved-108A6>
|
||||
108A7..108AF ; R # No [9] NABATAEAN NUMBER ONE..NABATAEAN NUMBER ONE HUNDRED
|
||||
108B0..108FF ; R # Cn [80] <reserved-108B0>..<reserved-108FF>
|
||||
108B0..108DF ; R # Cn [48] <reserved-108B0>..<reserved-108DF>
|
||||
108E0..108F2 ; R # Lo [19] HATRAN LETTER ALEPH..HATRAN LETTER QOPH
|
||||
108F3 ; R # Cn <reserved-108F3>
|
||||
108F4..108F5 ; R # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW
|
||||
108F6..108FA ; R # Cn [5] <reserved-108F6>..<reserved-108FA>
|
||||
108FB..108FF ; R # No [5] HATRAN NUMBER ONE..HATRAN NUMBER ONE HUNDRED
|
||||
10900..10915 ; R # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU
|
||||
10916..1091B ; R # No [6] PHOENICIAN NUMBER ONE..PHOENICIAN NUMBER THREE
|
||||
1091C..1091E ; R # Cn [3] <reserved-1091C>..<reserved-1091E>
|
||||
|
|
@ -989,9 +1025,12 @@ FB46..FB4F ; R # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE AL
|
|||
1093F ; R # Po LYDIAN TRIANGULAR MARK
|
||||
10940..1097F ; R # Cn [64] <reserved-10940>..<reserved-1097F>
|
||||
10980..109B7 ; R # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA
|
||||
109B8..109BD ; R # Cn [6] <reserved-109B8>..<reserved-109BD>
|
||||
109B8..109BB ; R # Cn [4] <reserved-109B8>..<reserved-109BB>
|
||||
109BC..109BD ; R # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF
|
||||
109BE..109BF ; R # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN
|
||||
109C0..109FF ; R # Cn [64] <reserved-109C0>..<reserved-109FF>
|
||||
109C0..109CF ; R # No [16] MEROITIC CURSIVE NUMBER ONE..MEROITIC CURSIVE NUMBER SEVENTY
|
||||
109D0..109D1 ; R # Cn [2] <reserved-109D0>..<reserved-109D1>
|
||||
109D2..109FF ; R # No [46] MEROITIC CURSIVE NUMBER ONE HUNDRED..MEROITIC CURSIVE FRACTION TEN TWELFTHS
|
||||
10A00 ; R # Lo KHAROSHTHI LETTER A
|
||||
10A04 ; R # Cn <reserved-10A04>
|
||||
10A07..10A0B ; R # Cn [5] <reserved-10A07>..<reserved-10A0B>
|
||||
|
|
@ -1034,7 +1073,13 @@ FB46..FB4F ; R # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE AL
|
|||
10BA9..10BAF ; R # No [7] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER ONE HUNDRED
|
||||
10BB0..10BFF ; R # Cn [80] <reserved-10BB0>..<reserved-10BFF>
|
||||
10C00..10C48 ; R # Lo [73] OLD TURKIC LETTER ORKHON A..OLD TURKIC LETTER ORKHON BASH
|
||||
10C49..10E5F ; R # Cn [535] <reserved-10C49>..<reserved-10E5F>
|
||||
10C49..10C7F ; R # Cn [55] <reserved-10C49>..<reserved-10C7F>
|
||||
10C80..10CB2 ; R # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US
|
||||
10CB3..10CBF ; R # Cn [13] <reserved-10CB3>..<reserved-10CBF>
|
||||
10CC0..10CF2 ; R # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US
|
||||
10CF3..10CF9 ; R # Cn [7] <reserved-10CF3>..<reserved-10CF9>
|
||||
10CFA..10CFF ; R # No [6] OLD HUNGARIAN NUMBER ONE..OLD HUNGARIAN NUMBER ONE THOUSAND
|
||||
10D00..10E5F ; R # Cn [352] <reserved-10D00>..<reserved-10E5F>
|
||||
10E7F..10FFF ; R # Cn [385] <reserved-10E7F>..<reserved-10FFF>
|
||||
1E800..1E8C4 ; R # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON
|
||||
1E8C5..1E8C6 ; R # Cn [2] <reserved-1E8C5>..<reserved-1E8C6>
|
||||
|
|
@ -1100,8 +1145,8 @@ FF0D ; ES # Pd FULLWIDTH HYPHEN-MINUS
|
|||
0E3F ; ET # Sc THAI CURRENCY SYMBOL BAHT
|
||||
17DB ; ET # Sc KHMER CURRENCY SYMBOL RIEL
|
||||
2030..2034 ; ET # Po [5] PER MILLE SIGN..TRIPLE PRIME
|
||||
20A0..20BD ; ET # Sc [30] EURO-CURRENCY SIGN..RUBLE SIGN
|
||||
20BE..20CF ; ET # Cn [18] <reserved-20BE>..<reserved-20CF>
|
||||
20A0..20BE ; ET # Sc [31] EURO-CURRENCY SIGN..LARI SIGN
|
||||
20BF..20CF ; ET # Cn [17] <reserved-20BF>..<reserved-20CF>
|
||||
212E ; ET # So ESTIMATED SYMBOL
|
||||
2213 ; ET # Sm MINUS-OR-PLUS SIGN
|
||||
A838 ; ET # Sc NORTH INDIC RUPEE MARK
|
||||
|
|
@ -1316,6 +1361,7 @@ FF1A ; CS # Po FULLWIDTH COLON
|
|||
214C..214D ; ON # So [2] PER SIGN..AKTIESELSKAB
|
||||
2150..215F ; ON # No [16] VULGAR FRACTION ONE SEVENTH..FRACTION NUMERATOR ONE
|
||||
2189 ; ON # No VULGAR FRACTION ZERO THIRDS
|
||||
218A..218B ; ON # So [2] TURNED DIGIT TWO..TURNED DIGIT THREE
|
||||
2190..2194 ; ON # Sm [5] LEFTWARDS ARROW..LEFT RIGHT ARROW
|
||||
2195..2199 ; ON # So [5] UP DOWN ARROW..SOUTH WEST ARROW
|
||||
219A..219B ; ON # Sm [2] LEFTWARDS ARROW WITH STROKE..RIGHTWARDS ARROW WITH STROKE
|
||||
|
|
@ -1441,6 +1487,7 @@ FF1A ; CS # Po FULLWIDTH COLON
|
|||
2B98..2BB9 ; ON # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX
|
||||
2BBD..2BC8 ; ON # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
|
||||
2BCA..2BD1 ; ON # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN
|
||||
2BEC..2BEF ; ON # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS
|
||||
2CE5..2CEA ; ON # So [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA
|
||||
2CF9..2CFC ; ON # Po [4] COPTIC OLD NUBIAN FULL STOP..COPTIC OLD NUBIAN VERSE DIVIDER
|
||||
2CFD ; ON # No COPTIC FRACTION ONE HALF
|
||||
|
|
@ -1645,16 +1692,11 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE
|
|||
1F0D1..1F0F5 ; ON # So [37] PLAYING CARD ACE OF CLUBS..PLAYING CARD TRUMP-21
|
||||
1F10B..1F10C ; ON # No [2] DINGBAT CIRCLED SANS-SERIF DIGIT ZERO..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO
|
||||
1F16A..1F16B ; ON # So [2] RAISED MC SIGN..RAISED MD SIGN
|
||||
1F300..1F32C ; ON # So [45] CYCLONE..WIND BLOWING FACE
|
||||
1F330..1F37D ; ON # So [78] CHESTNUT..FORK AND KNIFE WITH PLATE
|
||||
1F380..1F3CE ; ON # So [79] RIBBON..RACING CAR
|
||||
1F3D4..1F3F7 ; ON # So [36] SNOW CAPPED MOUNTAIN..LABEL
|
||||
1F400..1F4FE ; ON # So [255] RAT..PORTABLE STEREO
|
||||
1F500..1F54A ; ON # So [75] TWISTED RIGHTWARDS ARROWS..DOVE OF PEACE
|
||||
1F550..1F579 ; ON # So [42] CLOCK FACE ONE OCLOCK..JOYSTICK
|
||||
1F300..1F3FA ; ON # So [251] CYCLONE..AMPHORA
|
||||
1F3FB..1F3FF ; ON # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
|
||||
1F400..1F579 ; ON # So [378] RAT..JOYSTICK
|
||||
1F57B..1F5A3 ; ON # So [41] LEFT HAND TELEPHONE RECEIVER..BLACK DOWN POINTING BACKHAND INDEX
|
||||
1F5A5..1F642 ; ON # So [158] DESKTOP COMPUTER..SLIGHTLY SMILING FACE
|
||||
1F645..1F6CF ; ON # So [139] FACE WITH NO GOOD GESTURE..BED
|
||||
1F5A5..1F6D0 ; ON # So [300] DESKTOP COMPUTER..PLACE OF WORSHIP
|
||||
1F6E0..1F6EC ; ON # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING
|
||||
1F6F0..1F6F3 ; ON # So [4] SATELLITE..PASSENGER SHIP
|
||||
1F700..1F773 ; ON # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
|
||||
|
|
@ -1664,8 +1706,11 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE
|
|||
1F850..1F859 ; ON # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW
|
||||
1F860..1F887 ; ON # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW
|
||||
1F890..1F8AD ; ON # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS
|
||||
1F910..1F918 ; ON # So [9] ZIPPER-MOUTH FACE..SIGN OF THE HORNS
|
||||
1F980..1F984 ; ON # So [5] CRAB..UNICORN FACE
|
||||
1F9C0 ; ON # So CHEESE WEDGE
|
||||
|
||||
# Total code points: 5126
|
||||
# Total code points: 5174
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -1739,7 +1784,7 @@ FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF>
|
|||
0825..0827 ; NSM # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U
|
||||
0829..082D ; NSM # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA
|
||||
0859..085B ; NSM # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK
|
||||
08E4..0902 ; NSM # Mn [31] ARABIC CURLY FATHA..DEVANAGARI SIGN ANUSVARA
|
||||
08E3..0902 ; NSM # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA
|
||||
093A ; NSM # Mn DEVANAGARI VOWEL SIGN OE
|
||||
093C ; NSM # Mn DEVANAGARI SIGN NUKTA
|
||||
0941..0948 ; NSM # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI
|
||||
|
|
@ -1884,7 +1929,7 @@ FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF>
|
|||
A66F ; NSM # Mn COMBINING CYRILLIC VZMET
|
||||
A670..A672 ; NSM # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN
|
||||
A674..A67D ; NSM # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK
|
||||
A69F ; NSM # Mn COMBINING CYRILLIC LETTER IOTIFIED E
|
||||
A69E..A69F ; NSM # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E
|
||||
A6F0..A6F1 ; NSM # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS
|
||||
A802 ; NSM # Mn SYLOTI NAGRI SIGN DVISVARA
|
||||
A806 ; NSM # Mn SYLOTI NAGRI SIGN HASANTA
|
||||
|
|
@ -1917,7 +1962,7 @@ ABE8 ; NSM # Mn MEETEI MAYEK VOWEL SIGN UNAP
|
|||
ABED ; NSM # Mn MEETEI MAYEK APUN IYEK
|
||||
FB1E ; NSM # Mn HEBREW POINT JUDEO-SPANISH VARIKA
|
||||
FE00..FE0F ; NSM # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
|
||||
FE20..FE2D ; NSM # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON BELOW
|
||||
FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF
|
||||
101FD ; NSM # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE
|
||||
102E0 ; NSM # Mn COPTIC EPACT THOUSANDS MARK
|
||||
10376..1037A ; NSM # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII
|
||||
|
|
@ -1938,12 +1983,13 @@ FE20..FE2D ; NSM # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOININ
|
|||
11173 ; NSM # Mn MAHAJANI SIGN NUKTA
|
||||
11180..11181 ; NSM # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA
|
||||
111B6..111BE ; NSM # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O
|
||||
111CA..111CC ; NSM # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK
|
||||
1122F..11231 ; NSM # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI
|
||||
11234 ; NSM # Mn KHOJKI SIGN ANUSVARA
|
||||
11236..11237 ; NSM # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
|
||||
112DF ; NSM # Mn KHUDAWADI SIGN ANUSVARA
|
||||
112E3..112EA ; NSM # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
|
||||
11301 ; NSM # Mn GRANTHA SIGN CANDRABINDU
|
||||
11300..11301 ; NSM # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
|
||||
1133C ; NSM # Mn GRANTHA SIGN NUKTA
|
||||
11340 ; NSM # Mn GRANTHA VOWEL SIGN II
|
||||
11366..1136C ; NSM # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX
|
||||
|
|
@ -1955,6 +2001,7 @@ FE20..FE2D ; NSM # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOININ
|
|||
115B2..115B5 ; NSM # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR
|
||||
115BC..115BD ; NSM # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA
|
||||
115BF..115C0 ; NSM # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA
|
||||
115DC..115DD ; NSM # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU
|
||||
11633..1163A ; NSM # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI
|
||||
1163D ; NSM # Mn MODI SIGN ANUSVARA
|
||||
1163F..11640 ; NSM # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA
|
||||
|
|
@ -1962,6 +2009,9 @@ FE20..FE2D ; NSM # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOININ
|
|||
116AD ; NSM # Mn TAKRI VOWEL SIGN AA
|
||||
116B0..116B5 ; NSM # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU
|
||||
116B7 ; NSM # Mn TAKRI SIGN NUKTA
|
||||
1171D..1171F ; NSM # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA
|
||||
11722..11725 ; NSM # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
|
||||
11727..1172B ; NSM # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER
|
||||
16AF0..16AF4 ; NSM # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
|
||||
16B30..16B36 ; NSM # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
|
||||
16F8F..16F92 ; NSM # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
|
||||
|
|
@ -1971,10 +2021,16 @@ FE20..FE2D ; NSM # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOININ
|
|||
1D185..1D18B ; NSM # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
|
||||
1D1AA..1D1AD ; NSM # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
|
||||
1D242..1D244 ; NSM # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
|
||||
1DA00..1DA36 ; NSM # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN
|
||||
1DA3B..1DA6C ; NSM # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT
|
||||
1DA75 ; NSM # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS
|
||||
1DA84 ; NSM # Mn SIGNWRITING LOCATION HEAD NECK
|
||||
1DA9B..1DA9F ; NSM # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6
|
||||
1DAA1..1DAAF ; NSM # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16
|
||||
1E8D0..1E8D6 ; NSM # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
|
||||
E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
|
||||
|
||||
# Total code points: 1429
|
||||
# Total code points: 1578
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -2009,8 +2065,8 @@ E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
|
|||
074D..07A5 ; AL # Lo [89] SYRIAC LETTER SOGDIAN ZHAIN..THAANA LETTER WAAVU
|
||||
07B1 ; AL # Lo THAANA LETTER NAA
|
||||
07B2..07BF ; AL # Cn [14] <reserved-07B2>..<reserved-07BF>
|
||||
08A0..08B2 ; AL # Lo [19] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE
|
||||
08B3..08E3 ; AL # Cn [49] <reserved-08B3>..<reserved-08E3>
|
||||
08A0..08B4 ; AL # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
|
||||
08B5..08E2 ; AL # Cn [46] <reserved-08B5>..<reserved-08E2>
|
||||
FB50..FBB1 ; AL # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM
|
||||
FBB2..FBC1 ; AL # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW
|
||||
FBC2..FBD2 ; AL # Cn [17] <reserved-FBC2>..<reserved-FBD2>
|
||||
|
|
@ -2095,7 +2151,7 @@ FEFD..FEFE ; AL # Cn [2] <reserved-FEFD>..<reserved-FEFE>
|
|||
1EEBC..1EEEF ; AL # Cn [52] <reserved-1EEBC>..<reserved-1EEEF>
|
||||
1EEF2..1EEFF ; AL # Cn [14] <reserved-1EEF2>..<reserved-1EEFF>
|
||||
|
||||
# Total code points: 1436
|
||||
# Total code points: 1435
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
# GraphemeBreakProperty-7.0.0.txt
|
||||
# Date: 2014-02-19, 15:51:21 GMT [MD]
|
||||
# GraphemeBreakProperty-8.0.0.txt
|
||||
# Date: 2015-02-13, 13:47:14 GMT [MD]
|
||||
#
|
||||
# Unicode Character Database
|
||||
# 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
|
||||
# For documentation, see http://www.unicode.org/reports/tr44/
|
||||
|
||||
|
|
@ -89,7 +89,7 @@ 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
|
||||
08E4..0902 ; Extend # Mn [31] ARABIC CURLY FATHA..DEVANAGARI SIGN ANUSVARA
|
||||
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
|
||||
|
|
@ -250,7 +250,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
|
|||
A66F ; Extend # Mn COMBINING CYRILLIC VZMET
|
||||
A670..A672 ; Extend # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN
|
||||
A674..A67D ; Extend # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK
|
||||
A69F ; Extend # Mn COMBINING CYRILLIC LETTER IOTIFIED E
|
||||
A69E..A69F ; Extend # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E
|
||||
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
|
||||
|
|
@ -283,7 +283,7 @@ ABE8 ; Extend # Mn MEETEI MAYEK VOWEL SIGN UNAP
|
|||
ABED ; Extend # Mn MEETEI MAYEK APUN IYEK
|
||||
FB1E ; Extend # Mn HEBREW POINT JUDEO-SPANISH VARIKA
|
||||
FE00..FE0F ; Extend # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
|
||||
FE20..FE2D ; Extend # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON BELOW
|
||||
FE20..FE2F ; Extend # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF
|
||||
FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
|
||||
101FD ; Extend # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE
|
||||
102E0 ; Extend # Mn COPTIC EPACT THOUSANDS MARK
|
||||
|
|
@ -305,12 +305,13 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
|||
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
|
||||
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
|
||||
112DF ; Extend # Mn KHUDAWADI SIGN ANUSVARA
|
||||
112E3..112EA ; Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
|
||||
11301 ; Extend # Mn GRANTHA SIGN CANDRABINDU
|
||||
11300..11301 ; Extend # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
|
||||
1133C ; Extend # Mn GRANTHA SIGN NUKTA
|
||||
1133E ; Extend # Mc GRANTHA VOWEL SIGN AA
|
||||
11340 ; Extend # Mn GRANTHA VOWEL SIGN II
|
||||
|
|
@ -327,6 +328,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
|||
115B2..115B5 ; Extend # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR
|
||||
115BC..115BD ; Extend # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA
|
||||
115BF..115C0 ; Extend # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA
|
||||
115DC..115DD ; Extend # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU
|
||||
11633..1163A ; Extend # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI
|
||||
1163D ; Extend # Mn MODI SIGN ANUSVARA
|
||||
1163F..11640 ; Extend # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA
|
||||
|
|
@ -334,6 +336,9 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
|||
116AD ; Extend # Mn TAKRI VOWEL SIGN AA
|
||||
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
|
||||
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
|
||||
16F8F..16F92 ; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
|
||||
|
|
@ -345,10 +350,16 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
|||
1D185..1D18B ; Extend # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
|
||||
1D1AA..1D1AD ; Extend # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
|
||||
1D242..1D244 ; Extend # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
|
||||
1DA00..1DA36 ; Extend # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN
|
||||
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
|
||||
1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
|
||||
E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
|
||||
|
||||
# Total code points: 1461
|
||||
# Total code points: 1610
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -412,8 +423,6 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
|
|||
1929..192B ; SpacingMark # Mc [3] LIMBU SUBJOINED LETTER YA..LIMBU SUBJOINED LETTER WA
|
||||
1930..1931 ; SpacingMark # Mc [2] LIMBU SMALL LETTER KA..LIMBU SMALL LETTER NGA
|
||||
1933..1938 ; SpacingMark # Mc [6] LIMBU SMALL LETTER TA..LIMBU SMALL LETTER LA
|
||||
19B5..19B7 ; SpacingMark # Mc [3] NEW TAI LUE VOWEL SIGN E..NEW TAI LUE VOWEL SIGN O
|
||||
19BA ; SpacingMark # Mc NEW TAI LUE VOWEL SIGN AY
|
||||
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
|
||||
|
|
@ -487,11 +496,13 @@ 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
|
||||
16F51..16F7E ; SpacingMark # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
|
||||
1D166 ; SpacingMark # Mc MUSICAL SYMBOL COMBINING SPRECHGESANG STEM
|
||||
1D16D ; SpacingMark # Mc MUSICAL SYMBOL COMBINING AUGMENTATION DOT
|
||||
|
||||
# Total code points: 331
|
||||
# Total code points: 330
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
# GraphemeBreakTest-7.0.0.txt
|
||||
# Date: 2013-11-27, 09:54:39 GMT [MD]
|
||||
# GraphemeBreakTest-8.0.0.txt
|
||||
# Date: 2015-02-13, 13:47:15 GMT [MD]
|
||||
#
|
||||
# Unicode Character Database
|
||||
# Copyright (c) 1991-2013 Unicode, Inc.
|
||||
# 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/
|
||||
#
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load diff
|
|
@ -1,8 +1,8 @@
|
|||
# SentenceBreakProperty-7.0.0.txt
|
||||
# Date: 2014-02-19, 15:51:38 GMT [MD]
|
||||
# SentenceBreakProperty-8.0.0.txt
|
||||
# Date: 2015-03-11, 22:29:43 GMT [MD]
|
||||
#
|
||||
# Unicode Character Database
|
||||
# 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
|
||||
# For documentation, see http://www.unicode.org/reports/tr44/
|
||||
|
||||
|
|
@ -53,7 +53,7 @@
|
|||
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
|
||||
08E4..0902 ; Extend # Mn [31] ARABIC CURLY FATHA..DEVANAGARI SIGN ANUSVARA
|
||||
08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA
|
||||
0903 ; Extend # Mc DEVANAGARI SIGN VISARGA
|
||||
093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE
|
||||
093B ; Extend # Mc DEVANAGARI VOWEL SIGN OOE
|
||||
|
|
@ -216,8 +216,6 @@
|
|||
1932 ; Extend # Mn LIMBU SMALL LETTER ANUSVARA
|
||||
1933..1938 ; Extend # Mc [6] LIMBU SMALL LETTER TA..LIMBU SMALL LETTER LA
|
||||
1939..193B ; Extend # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I
|
||||
19B0..19C0 ; Extend # Mc [17] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE VOWEL SIGN IY
|
||||
19C8..19C9 ; Extend # Mc [2] NEW TAI LUE TONE MARK-1..NEW TAI LUE TONE MARK-2
|
||||
1A17..1A18 ; Extend # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U
|
||||
1A19..1A1A ; Extend # Mc [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O
|
||||
1A1B ; Extend # Mn BUGINESE VOWEL SIGN AE
|
||||
|
|
@ -291,7 +289,7 @@
|
|||
A66F ; Extend # Mn COMBINING CYRILLIC VZMET
|
||||
A670..A672 ; Extend # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN
|
||||
A674..A67D ; Extend # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK
|
||||
A69F ; Extend # Mn COMBINING CYRILLIC LETTER IOTIFIED E
|
||||
A69E..A69F ; Extend # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E
|
||||
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
|
||||
|
|
@ -345,7 +343,7 @@ ABEC ; Extend # Mc MEETEI MAYEK LUM IYEK
|
|||
ABED ; Extend # Mn MEETEI MAYEK APUN IYEK
|
||||
FB1E ; Extend # Mn HEBREW POINT JUDEO-SPANISH VARIKA
|
||||
FE00..FE0F ; Extend # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
|
||||
FE20..FE2D ; Extend # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON BELOW
|
||||
FE20..FE2F ; Extend # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF
|
||||
FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
|
||||
101FD ; Extend # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE
|
||||
102E0 ; Extend # Mn COPTIC EPACT THOUSANDS MARK
|
||||
|
|
@ -376,6 +374,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
|||
111B3..111B5 ; Extend # Mc [3] SHARADA VOWEL SIGN AA..SHARADA VOWEL SIGN II
|
||||
111B6..111BE ; Extend # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O
|
||||
111BF..111C0 ; Extend # Mc [2] SHARADA VOWEL SIGN AU..SHARADA SIGN VIRAMA
|
||||
111CA..111CC ; Extend # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK
|
||||
1122C..1122E ; Extend # Mc [3] KHOJKI VOWEL SIGN AA..KHOJKI VOWEL SIGN II
|
||||
1122F..11231 ; Extend # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI
|
||||
11232..11233 ; Extend # Mc [2] KHOJKI VOWEL SIGN O..KHOJKI VOWEL SIGN AU
|
||||
|
|
@ -385,7 +384,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
|||
112DF ; Extend # Mn KHUDAWADI SIGN ANUSVARA
|
||||
112E0..112E2 ; Extend # Mc [3] KHUDAWADI VOWEL SIGN AA..KHUDAWADI VOWEL SIGN II
|
||||
112E3..112EA ; Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
|
||||
11301 ; Extend # Mn GRANTHA SIGN CANDRABINDU
|
||||
11300..11301 ; Extend # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
|
||||
11302..11303 ; Extend # Mc [2] GRANTHA SIGN ANUSVARA..GRANTHA SIGN VISARGA
|
||||
1133C ; Extend # Mn GRANTHA SIGN NUKTA
|
||||
1133E..1133F ; Extend # Mc [2] GRANTHA VOWEL SIGN AA..GRANTHA VOWEL SIGN I
|
||||
|
|
@ -411,6 +410,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
|||
115BC..115BD ; Extend # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA
|
||||
115BE ; Extend # Mc SIDDHAM SIGN VISARGA
|
||||
115BF..115C0 ; Extend # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA
|
||||
115DC..115DD ; Extend # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU
|
||||
11630..11632 ; Extend # Mc [3] MODI VOWEL SIGN AA..MODI VOWEL SIGN II
|
||||
11633..1163A ; Extend # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI
|
||||
1163B..1163C ; Extend # Mc [2] MODI VOWEL SIGN O..MODI VOWEL SIGN AU
|
||||
|
|
@ -424,6 +424,11 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
|||
116B0..116B5 ; Extend # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU
|
||||
116B6 ; Extend # Mc TAKRI SIGN VIRAMA
|
||||
116B7 ; Extend # Mn TAKRI SIGN NUKTA
|
||||
1171D..1171F ; Extend # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA
|
||||
11720..11721 ; Extend # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA
|
||||
11722..11725 ; Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
|
||||
11726 ; Extend # Mc AHOM VOWEL SIGN E
|
||||
11727..1172B ; Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER
|
||||
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
|
||||
16F51..16F7E ; Extend # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
|
||||
|
|
@ -436,10 +441,16 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
|||
1D185..1D18B ; Extend # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
|
||||
1D1AA..1D1AD ; Extend # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
|
||||
1D242..1D244 ; Extend # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
|
||||
1DA00..1DA36 ; Extend # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN
|
||||
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
|
||||
1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
|
||||
E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
|
||||
|
||||
# Total code points: 1834
|
||||
# Total code points: 1967
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -764,6 +775,7 @@ E0020..E007F ; Format # Cf [96] TAG SPACE..CANCEL TAG
|
|||
052D ; Lower # L& CYRILLIC SMALL LETTER DCHE
|
||||
052F ; Lower # L& CYRILLIC SMALL LETTER EL WITH DESCENDER
|
||||
0561..0587 ; Lower # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN
|
||||
13F8..13FD ; Lower # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV
|
||||
1D00..1D2B ; Lower # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL
|
||||
1D2C..1D6A ; Lower # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI
|
||||
1D6B..1D77 ; Lower # L& [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G
|
||||
|
|
@ -1094,15 +1106,19 @@ A7A3 ; Lower # L& LATIN SMALL LETTER K WITH OBLIQUE STROKE
|
|||
A7A5 ; Lower # L& LATIN SMALL LETTER N WITH OBLIQUE STROKE
|
||||
A7A7 ; Lower # L& LATIN SMALL LETTER R WITH OBLIQUE STROKE
|
||||
A7A9 ; Lower # L& LATIN SMALL LETTER S WITH OBLIQUE STROKE
|
||||
A7B5 ; Lower # L& LATIN SMALL LETTER BETA
|
||||
A7B7 ; Lower # L& LATIN SMALL LETTER OMEGA
|
||||
A7F8..A7F9 ; Lower # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
|
||||
A7FA ; Lower # L& LATIN LETTER SMALL CAPITAL TURNED M
|
||||
AB30..AB5A ; Lower # L& [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG
|
||||
AB5C..AB5F ; Lower # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK
|
||||
AB64..AB65 ; Lower # L& [2] LATIN SMALL LETTER INVERTED ALPHA..GREEK LETTER SMALL CAPITAL OMEGA
|
||||
AB60..AB65 ; Lower # L& [6] LATIN SMALL LETTER SAKHA YAT..GREEK LETTER SMALL CAPITAL OMEGA
|
||||
AB70..ABBF ; Lower # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA
|
||||
FB00..FB06 ; Lower # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST
|
||||
FB13..FB17 ; Lower # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH
|
||||
FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z
|
||||
10428..1044F ; Lower # L& [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW
|
||||
10CC0..10CF2 ; Lower # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US
|
||||
118C0..118DF ; Lower # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO
|
||||
1D41A..1D433 ; Lower # L& [26] MATHEMATICAL BOLD SMALL A..MATHEMATICAL BOLD SMALL Z
|
||||
1D44E..1D454 ; Lower # L& [7] MATHEMATICAL ITALIC SMALL A..MATHEMATICAL ITALIC SMALL G
|
||||
|
|
@ -1133,7 +1149,7 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN
|
|||
1D7C4..1D7C9 ; Lower # L& [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL
|
||||
1D7CB ; Lower # L& MATHEMATICAL BOLD SMALL DIGAMMA
|
||||
|
||||
# Total code points: 2029
|
||||
# Total code points: 2172
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -1412,6 +1428,7 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN
|
|||
10A0..10C5 ; Upper # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE
|
||||
10C7 ; Upper # L& GEORGIAN CAPITAL LETTER YN
|
||||
10CD ; Upper # L& GEORGIAN CAPITAL LETTER AEN
|
||||
13A0..13F5 ; Upper # L& [86] CHEROKEE LETTER A..CHEROKEE LETTER MV
|
||||
1E00 ; Upper # L& LATIN CAPITAL LETTER A WITH RING BELOW
|
||||
1E02 ; Upper # L& LATIN CAPITAL LETTER B WITH DOT ABOVE
|
||||
1E04 ; Upper # L& LATIN CAPITAL LETTER B WITH DOT BELOW
|
||||
|
|
@ -1729,9 +1746,11 @@ A7A4 ; Upper # L& LATIN CAPITAL LETTER N WITH OBLIQUE STROKE
|
|||
A7A6 ; Upper # L& LATIN CAPITAL LETTER R WITH OBLIQUE STROKE
|
||||
A7A8 ; Upper # L& LATIN CAPITAL LETTER S WITH OBLIQUE STROKE
|
||||
A7AA..A7AD ; Upper # L& [4] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER L WITH BELT
|
||||
A7B0..A7B1 ; Upper # L& [2] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER TURNED T
|
||||
A7B0..A7B4 ; Upper # L& [5] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER BETA
|
||||
A7B6 ; Upper # L& LATIN CAPITAL LETTER OMEGA
|
||||
FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z
|
||||
10400..10427 ; Upper # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW
|
||||
10C80..10CB2 ; Upper # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US
|
||||
118A0..118BF ; Upper # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO
|
||||
1D400..1D419 ; Upper # L& [26] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL BOLD CAPITAL Z
|
||||
1D434..1D44D ; Upper # L& [26] MATHEMATICAL ITALIC CAPITAL A..MATHEMATICAL ITALIC CAPITAL Z
|
||||
|
|
@ -1768,7 +1787,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
|
|||
1F150..1F169 ; Upper # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
|
||||
1F170..1F189 ; Upper # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z
|
||||
|
||||
# Total code points: 1641
|
||||
# Total code points: 1782
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -1806,7 +1825,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
|
|||
0824 ; OLetter # Lm SAMARITAN MODIFIER LETTER SHORT A
|
||||
0828 ; OLetter # Lm SAMARITAN MODIFIER LETTER I
|
||||
0840..0858 ; OLetter # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN
|
||||
08A0..08B2 ; OLetter # Lo [19] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE
|
||||
08A0..08B4 ; OLetter # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
|
||||
0904..0939 ; OLetter # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA
|
||||
093D ; OLetter # Lo DEVANAGARI SIGN AVAGRAHA
|
||||
0950 ; OLetter # Lo DEVANAGARI OM
|
||||
|
|
@ -1843,6 +1862,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
|
|||
0ABD ; OLetter # Lo GUJARATI SIGN AVAGRAHA
|
||||
0AD0 ; OLetter # Lo GUJARATI OM
|
||||
0AE0..0AE1 ; OLetter # Lo [2] GUJARATI LETTER VOCALIC RR..GUJARATI LETTER VOCALIC LL
|
||||
0AF9 ; OLetter # Lo GUJARATI LETTER ZHA
|
||||
0B05..0B0C ; OLetter # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L
|
||||
0B0F..0B10 ; OLetter # Lo [2] ORIYA LETTER E..ORIYA LETTER AI
|
||||
0B13..0B28 ; OLetter # Lo [22] ORIYA LETTER O..ORIYA LETTER NA
|
||||
|
|
@ -1869,7 +1889,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
|
|||
0C12..0C28 ; OLetter # Lo [23] TELUGU LETTER O..TELUGU LETTER NA
|
||||
0C2A..0C39 ; OLetter # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA
|
||||
0C3D ; OLetter # Lo TELUGU SIGN AVAGRAHA
|
||||
0C58..0C59 ; OLetter # Lo [2] TELUGU LETTER TSA..TELUGU LETTER DZA
|
||||
0C58..0C5A ; OLetter # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA
|
||||
0C60..0C61 ; OLetter # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL
|
||||
0C85..0C8C ; OLetter # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L
|
||||
0C8E..0C90 ; OLetter # Lo [3] KANNADA LETTER E..KANNADA LETTER AI
|
||||
|
|
@ -1885,7 +1905,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
|
|||
0D12..0D3A ; OLetter # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA
|
||||
0D3D ; OLetter # Lo MALAYALAM SIGN AVAGRAHA
|
||||
0D4E ; OLetter # Lo MALAYALAM LETTER DOT REPH
|
||||
0D60..0D61 ; OLetter # Lo [2] MALAYALAM LETTER VOCALIC RR..MALAYALAM LETTER VOCALIC LL
|
||||
0D5F..0D61 ; OLetter # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL
|
||||
0D7A..0D7F ; OLetter # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K
|
||||
0D85..0D96 ; OLetter # Lo [18] SINHALA LETTER AYANNA..SINHALA LETTER AUYANNA
|
||||
0D9A..0DB1 ; OLetter # Lo [24] SINHALA LETTER ALPAPRAANA KAYANNA..SINHALA LETTER DANTAJA NAYANNA
|
||||
|
|
@ -1945,7 +1965,6 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
|
|||
1312..1315 ; OLetter # Lo [4] ETHIOPIC SYLLABLE GWI..ETHIOPIC SYLLABLE GWE
|
||||
1318..135A ; OLetter # Lo [67] ETHIOPIC SYLLABLE GGA..ETHIOPIC SYLLABLE FYA
|
||||
1380..138F ; OLetter # Lo [16] ETHIOPIC SYLLABLE SEBATBEIT MWA..ETHIOPIC SYLLABLE PWE
|
||||
13A0..13F4 ; OLetter # Lo [85] CHEROKEE LETTER A..CHEROKEE LETTER YV
|
||||
1401..166C ; OLetter # Lo [620] CANADIAN SYLLABICS E..CANADIAN SYLLABICS CARRIER TTSA
|
||||
166F..167F ; OLetter # Lo [17] CANADIAN SYLLABICS QAI..CANADIAN SYLLABICS BLACKFOOT W
|
||||
1681..169A ; OLetter # Lo [26] OGHAM LETTER BEITH..OGHAM LETTER PEITH
|
||||
|
|
@ -1971,7 +1990,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
|
|||
1950..196D ; OLetter # Lo [30] TAI LE LETTER KA..TAI LE LETTER AI
|
||||
1970..1974 ; OLetter # Lo [5] TAI LE LETTER TONE-2..TAI LE LETTER TONE-6
|
||||
1980..19AB ; OLetter # Lo [44] NEW TAI LUE LETTER HIGH QA..NEW TAI LUE LETTER LOW SUA
|
||||
19C1..19C7 ; OLetter # Lo [7] NEW TAI LUE LETTER FINAL V..NEW TAI LUE LETTER FINAL B
|
||||
19B0..19C9 ; OLetter # Lo [26] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2
|
||||
1A00..1A16 ; OLetter # Lo [23] BUGINESE LETTER KA..BUGINESE LETTER HA
|
||||
1A20..1A54 ; OLetter # Lo [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA
|
||||
1AA7 ; OLetter # Lm TAI THAM SIGN MAI YAMOK
|
||||
|
|
@ -2021,7 +2040,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
|
|||
31A0..31BA ; OLetter # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY
|
||||
31F0..31FF ; OLetter # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO
|
||||
3400..4DB5 ; OLetter # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
|
||||
4E00..9FCC ; OLetter # Lo [20941] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCC
|
||||
4E00..9FD5 ; OLetter # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
|
||||
A000..A014 ; OLetter # Lo [21] YI SYLLABLE IT..YI SYLLABLE E
|
||||
A015 ; OLetter # Lm YI SYLLABLE WU
|
||||
A016..A48C ; OLetter # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR
|
||||
|
|
@ -2037,6 +2056,7 @@ A6A0..A6E5 ; OLetter # Lo [70] BAMUM LETTER A..BAMUM LETTER KI
|
|||
A6E6..A6EF ; OLetter # Nl [10] BAMUM LETTER MO..BAMUM LETTER KOGHOM
|
||||
A717..A71F ; OLetter # Lm [9] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOW INVERTED EXCLAMATION MARK
|
||||
A788 ; OLetter # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT
|
||||
A78F ; OLetter # Lo LATIN LETTER SINOLOGICAL DOT
|
||||
A7F7 ; OLetter # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I
|
||||
A7FB..A801 ; OLetter # Lo [7] LATIN EPIGRAPHIC LETTER REVERSED F..SYLOTI NAGRI LETTER I
|
||||
A803..A805 ; OLetter # Lo [3] SYLOTI NAGRI LETTER U..SYLOTI NAGRI LETTER O
|
||||
|
|
@ -2046,6 +2066,7 @@ A840..A873 ; OLetter # Lo [52] PHAGS-PA LETTER KA..PHAGS-PA LETTER CANDRABIN
|
|||
A882..A8B3 ; OLetter # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA
|
||||
A8F2..A8F7 ; OLetter # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA
|
||||
A8FB ; OLetter # Lo DEVANAGARI HEADSTROKE
|
||||
A8FD ; OLetter # Lo DEVANAGARI JAIN OM
|
||||
A90A..A925 ; OLetter # Lo [28] KAYAH LI LETTER KA..KAYAH LI LETTER OO
|
||||
A930..A946 ; OLetter # Lo [23] REJANG LETTER KA..REJANG LETTER A
|
||||
A960..A97C ; OLetter # Lo [29] HANGUL CHOSEONG TIKEUT-MIEUM..HANGUL CHOSEONG SSANGYEORINHIEUH
|
||||
|
|
@ -2140,6 +2161,8 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
|
|||
1083F..10855 ; OLetter # Lo [23] CYPRIOT SYLLABLE ZO..IMPERIAL ARAMAIC LETTER TAW
|
||||
10860..10876 ; OLetter # Lo [23] PALMYRENE LETTER ALEPH..PALMYRENE LETTER TAW
|
||||
10880..1089E ; OLetter # Lo [31] NABATAEAN LETTER FINAL ALEPH..NABATAEAN LETTER TAW
|
||||
108E0..108F2 ; OLetter # Lo [19] HATRAN LETTER ALEPH..HATRAN LETTER QOPH
|
||||
108F4..108F5 ; OLetter # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW
|
||||
10900..10915 ; OLetter # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU
|
||||
10920..10939 ; OLetter # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C
|
||||
10980..109B7 ; OLetter # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA
|
||||
|
|
@ -2166,8 +2189,14 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
|
|||
11183..111B2 ; OLetter # Lo [48] SHARADA LETTER A..SHARADA LETTER HA
|
||||
111C1..111C4 ; OLetter # Lo [4] SHARADA SIGN AVAGRAHA..SHARADA OM
|
||||
111DA ; OLetter # Lo SHARADA EKAM
|
||||
111DC ; OLetter # Lo SHARADA HEADSTROKE
|
||||
11200..11211 ; OLetter # Lo [18] KHOJKI LETTER A..KHOJKI LETTER JJA
|
||||
11213..1122B ; OLetter # Lo [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA
|
||||
11280..11286 ; OLetter # Lo [7] MULTANI LETTER A..MULTANI LETTER GA
|
||||
11288 ; OLetter # Lo MULTANI LETTER GHA
|
||||
1128A..1128D ; OLetter # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA
|
||||
1128F..1129D ; OLetter # Lo [15] MULTANI LETTER NYA..MULTANI LETTER BA
|
||||
1129F..112A8 ; OLetter # Lo [10] MULTANI LETTER BHA..MULTANI LETTER RHA
|
||||
112B0..112DE ; OLetter # Lo [47] KHUDAWADI LETTER A..KHUDAWADI LETTER HA
|
||||
11305..1130C ; OLetter # Lo [8] GRANTHA LETTER A..GRANTHA LETTER VOCALIC L
|
||||
1130F..11310 ; OLetter # Lo [2] GRANTHA LETTER EE..GRANTHA LETTER AI
|
||||
|
|
@ -2176,19 +2205,24 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
|
|||
11332..11333 ; OLetter # Lo [2] GRANTHA LETTER LA..GRANTHA LETTER LLA
|
||||
11335..11339 ; OLetter # Lo [5] GRANTHA LETTER VA..GRANTHA LETTER HA
|
||||
1133D ; OLetter # Lo GRANTHA SIGN AVAGRAHA
|
||||
11350 ; OLetter # Lo GRANTHA OM
|
||||
1135D..11361 ; OLetter # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL
|
||||
11480..114AF ; OLetter # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA
|
||||
114C4..114C5 ; OLetter # Lo [2] TIRHUTA SIGN AVAGRAHA..TIRHUTA GVANG
|
||||
114C7 ; OLetter # Lo TIRHUTA OM
|
||||
11580..115AE ; OLetter # Lo [47] SIDDHAM LETTER A..SIDDHAM LETTER HA
|
||||
115D8..115DB ; OLetter # Lo [4] SIDDHAM LETTER THREE-CIRCLE ALTERNATE I..SIDDHAM LETTER ALTERNATE U
|
||||
11600..1162F ; OLetter # Lo [48] MODI LETTER A..MODI LETTER LLA
|
||||
11644 ; OLetter # Lo MODI SIGN HUVA
|
||||
11680..116AA ; OLetter # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA
|
||||
11700..11719 ; OLetter # Lo [26] AHOM LETTER KA..AHOM LETTER JHA
|
||||
118FF ; OLetter # Lo WARANG CITI OM
|
||||
11AC0..11AF8 ; OLetter # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
|
||||
12000..12398 ; OLetter # Lo [921] CUNEIFORM SIGN A..CUNEIFORM SIGN UM TIMES ME
|
||||
12000..12399 ; OLetter # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
|
||||
12400..1246E ; OLetter # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
|
||||
12480..12543 ; OLetter # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
|
||||
13000..1342E ; OLetter # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
|
||||
14400..14646 ; OLetter # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530
|
||||
16800..16A38 ; OLetter # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ
|
||||
16A40..16A5E ; OLetter # Lo [31] MRO LETTER TA..MRO LETTER TEK
|
||||
16AD0..16AED ; OLetter # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I
|
||||
|
|
@ -2241,9 +2275,10 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
|
|||
20000..2A6D6 ; OLetter # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
|
||||
2A700..2B734 ; OLetter # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
|
||||
2B740..2B81D ; OLetter # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
|
||||
2B820..2CEA1 ; OLetter # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
|
||||
2F800..2FA1D ; OLetter # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
|
||||
|
||||
# Total code points: 99420
|
||||
# Total code points: 106002
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -2293,12 +2328,13 @@ ABF0..ABF9 ; Numeric # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT N
|
|||
114D0..114D9 ; Numeric # Nd [10] TIRHUTA DIGIT ZERO..TIRHUTA DIGIT NINE
|
||||
11650..11659 ; Numeric # Nd [10] MODI DIGIT ZERO..MODI DIGIT NINE
|
||||
116C0..116C9 ; Numeric # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE
|
||||
11730..11739 ; Numeric # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE
|
||||
118E0..118E9 ; Numeric # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE
|
||||
16A60..16A69 ; Numeric # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE
|
||||
16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE
|
||||
1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
|
||||
|
||||
# Total code points: 532
|
||||
# Total code points: 542
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -2358,18 +2394,22 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP
|
|||
11141..11143 ; STerm # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK
|
||||
111C5..111C6 ; STerm # Po [2] SHARADA DANDA..SHARADA DOUBLE DANDA
|
||||
111CD ; STerm # Po SHARADA SUTRA MARK
|
||||
111DE..111DF ; STerm # Po [2] SHARADA SECTION MARK-1..SHARADA SECTION MARK-2
|
||||
11238..11239 ; STerm # Po [2] KHOJKI DANDA..KHOJKI DOUBLE DANDA
|
||||
1123B..1123C ; STerm # Po [2] KHOJKI SECTION MARK..KHOJKI DOUBLE SECTION MARK
|
||||
112A9 ; STerm # Po MULTANI SECTION MARK
|
||||
115C2..115C3 ; STerm # Po [2] SIDDHAM DANDA..SIDDHAM DOUBLE DANDA
|
||||
115C9 ; STerm # Po SIDDHAM END OF TEXT MARK
|
||||
115C9..115D7 ; STerm # Po [15] SIDDHAM END OF TEXT MARK..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES
|
||||
11641..11642 ; STerm # Po [2] MODI DANDA..MODI DOUBLE DANDA
|
||||
1173C..1173E ; STerm # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI
|
||||
16A6E..16A6F ; STerm # Po [2] MRO DANDA..MRO DOUBLE DANDA
|
||||
16AF5 ; STerm # Po BASSA VAH FULL STOP
|
||||
16B37..16B38 ; STerm # Po [2] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN VOS TSHAB CEEB
|
||||
16B44 ; STerm # Po PAHAWH HMONG SIGN XAUS
|
||||
1BC9F ; STerm # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP
|
||||
1DA88 ; STerm # Po SIGNWRITING FULL STOP
|
||||
|
||||
# Total code points: 96
|
||||
# Total code points: 117
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
# SentenceBreakTest-7.0.0.txt
|
||||
# Date: 2013-11-27, 09:54:53 GMT [MD]
|
||||
# SentenceBreakTest-8.0.0.txt
|
||||
# Date: 2015-04-30, 09:40:15 GMT [MD]
|
||||
#
|
||||
# Unicode Character Database
|
||||
# Copyright (c) 1991-2013 Unicode, Inc.
|
||||
# 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/
|
||||
#
|
||||
|
|
@ -477,6 +477,9 @@
|
|||
÷ 0055 × 002E × 0053 × 002E × 0041 × 0300 × 002E ÷ # ÷ [0.2] LATIN CAPITAL LETTER U (Upper) × [12.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER S (Upper) × [12.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) × [12.0] FULL STOP (ATerm) ÷ [0.3]
|
||||
÷ 0033 × 002E × 0034 ÷ # ÷ [0.2] DIGIT THREE (Numeric) × [12.0] FULL STOP (ATerm) × [6.0] DIGIT FOUR (Numeric) ÷ [0.3]
|
||||
÷ 0063 × 002E × 0064 ÷ # ÷ [0.2] LATIN SMALL LETTER C (Lower) × [12.0] FULL STOP (ATerm) × [8.0] LATIN SMALL LETTER D (Lower) ÷ [0.3]
|
||||
÷ 0043 × 002E × 0064 ÷ # ÷ [0.2] LATIN CAPITAL LETTER C (Upper) × [12.0] FULL STOP (ATerm) × [8.0] LATIN SMALL LETTER D (Lower) ÷ [0.3]
|
||||
÷ 0063 × 002E × 0044 ÷ # ÷ [0.2] LATIN SMALL LETTER C (Lower) × [12.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER D (Upper) ÷ [0.3]
|
||||
÷ 0043 × 002E × 0044 ÷ # ÷ [0.2] LATIN CAPITAL LETTER C (Upper) × [12.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER D (Upper) ÷ [0.3]
|
||||
÷ 0065 × 0074 × 0063 × 002E × 0029 × 2019 × 00A0 × 0074 × 0068 × 0065 ÷ # ÷ [0.2] LATIN SMALL LETTER E (Lower) × [12.0] LATIN SMALL LETTER T (Lower) × [12.0] LATIN SMALL LETTER C (Lower) × [12.0] FULL STOP (ATerm) × [8.0] RIGHT PARENTHESIS (Close) × [8.0] RIGHT SINGLE QUOTATION MARK (Close) × [8.0] NO-BREAK SPACE (Sp) × [8.0] LATIN SMALL LETTER T (Lower) × [12.0] LATIN SMALL LETTER H (Lower) × [12.0] LATIN SMALL LETTER E (Lower) ÷ [0.3]
|
||||
÷ 0065 × 0074 × 0063 × 002E × 0029 × 2019 × 00A0 ÷ 0054 × 0068 × 0065 ÷ # ÷ [0.2] LATIN SMALL LETTER E (Lower) × [12.0] LATIN SMALL LETTER T (Lower) × [12.0] LATIN SMALL LETTER C (Lower) × [12.0] FULL STOP (ATerm) × [9.0] RIGHT PARENTHESIS (Close) × [9.0] RIGHT SINGLE QUOTATION MARK (Close) × [9.0] NO-BREAK SPACE (Sp) ÷ [11.0] LATIN CAPITAL LETTER T (Upper) × [12.0] LATIN SMALL LETTER H (Lower) × [12.0] LATIN SMALL LETTER E (Lower) ÷ [0.3]
|
||||
÷ 0065 × 0074 × 0063 × 002E × 0029 × 2019 × 00A0 × 2018 × 0028 × 0074 × 0068 × 0065 ÷ # ÷ [0.2] LATIN SMALL LETTER E (Lower) × [12.0] LATIN SMALL LETTER T (Lower) × [12.0] LATIN SMALL LETTER C (Lower) × [12.0] FULL STOP (ATerm) × [8.0] RIGHT PARENTHESIS (Close) × [8.0] RIGHT SINGLE QUOTATION MARK (Close) × [8.0] NO-BREAK SPACE (Sp) × [8.0] LEFT SINGLE QUOTATION MARK (Close) × [12.0] LEFT PARENTHESIS (Close) × [12.0] LATIN SMALL LETTER T (Lower) × [12.0] LATIN SMALL LETTER H (Lower) × [12.0] LATIN SMALL LETTER E (Lower) ÷ [0.3]
|
||||
|
|
@ -490,6 +493,7 @@
|
|||
÷ 0065 × 0074 × 0063 × 002E ÷ 5B83 ÷ # ÷ [0.2] LATIN SMALL LETTER E (Lower) × [12.0] LATIN SMALL LETTER T (Lower) × [12.0] LATIN SMALL LETTER C (Lower) × [12.0] FULL STOP (ATerm) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B83 (OLetter) ÷ [0.3]
|
||||
÷ 0065 × 0074 × 0063 × 002E × 3002 ÷ # ÷ [0.2] LATIN SMALL LETTER E (Lower) × [12.0] LATIN SMALL LETTER T (Lower) × [12.0] LATIN SMALL LETTER C (Lower) × [12.0] FULL STOP (ATerm) × [8.1] IDEOGRAPHIC FULL STOP (STerm) ÷ [0.3]
|
||||
÷ 5B57 × 3002 ÷ 5B83 ÷ # ÷ [0.2] CJK UNIFIED IDEOGRAPH-5B57 (OLetter) × [12.0] IDEOGRAPHIC FULL STOP (STerm) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B83 (OLetter) ÷ [0.3]
|
||||
÷ 0021 × 0020 × 0020 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [9.0] SPACE (Sp) × [10.0] SPACE (Sp) ÷ [0.3]
|
||||
÷ 2060 × 0028 × 2060 × 0022 × 2060 × 0047 × 2060 × 006F × 2060 × 002E × 2060 × 0022 × 2060 × 0029 × 2060 × 0020 × 2060 ÷ 0028 × 2060 × 0048 × 2060 × 0065 × 2060 × 0020 × 2060 × 0064 × 2060 × 0069 × 2060 × 0064 × 2060 × 002E × 2060 × 0029 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [12.0] QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN CAPITAL LETTER G (Upper) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER O (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN CAPITAL LETTER H (Upper) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER I (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 × 0028 × 2060 × 201C × 2060 × 0047 × 2060 × 006F × 2060 × 003F × 2060 × 201D × 2060 × 0029 × 2060 × 0020 × 2060 ÷ 0028 × 2060 × 0048 × 2060 × 0065 × 2060 × 0020 × 2060 × 0064 × 2060 × 0069 × 2060 × 0064 × 2060 × 002E × 2060 × 0029 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [12.0] LEFT DOUBLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN CAPITAL LETTER G (Upper) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER O (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] QUESTION MARK (STerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT DOUBLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN CAPITAL LETTER H (Upper) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER I (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 × 0055 × 2060 × 002E × 2060 × 0053 × 2060 × 002E × 2060 × 0041 × 2060 × 0300 × 002E × 2060 × 0020 × 2060 × 0069 × 2060 × 0073 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] LATIN CAPITAL LETTER U (Upper) × [5.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER S (Upper) × [5.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER A (Upper) × [5.0] WORD JOINER (Format_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [8.0] LATIN SMALL LETTER I (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER S (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
|
|
@ -497,6 +501,9 @@
|
|||
÷ 2060 × 0055 × 2060 × 002E × 2060 × 0053 × 2060 × 002E × 2060 × 0041 × 2060 × 0300 × 002E × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] LATIN CAPITAL LETTER U (Upper) × [5.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER S (Upper) × [5.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER A (Upper) × [5.0] WORD JOINER (Format_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 × 0033 × 2060 × 002E × 2060 × 0034 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] DIGIT THREE (Numeric) × [5.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [6.0] DIGIT FOUR (Numeric) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 × 0063 × 2060 × 002E × 2060 × 0064 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 × 0043 × 2060 × 002E × 2060 × 0064 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] LATIN CAPITAL LETTER C (Upper) × [5.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 × 0063 × 2060 × 002E × 2060 × 0044 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER D (Upper) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 × 0043 × 2060 × 002E × 2060 × 0044 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] LATIN CAPITAL LETTER C (Upper) × [5.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER D (Upper) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 0029 × 2060 × 2019 × 2060 × 00A0 × 2060 × 0074 × 2060 × 0068 × 2060 × 0065 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [8.0] RIGHT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [8.0] NO-BREAK SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [8.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 0029 × 2060 × 2019 × 2060 × 00A0 × 2060 ÷ 0054 × 2060 × 0068 × 2060 × 0065 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] NO-BREAK SPACE (Sp) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] LATIN CAPITAL LETTER T (Upper) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 0029 × 2060 × 2019 × 2060 × 00A0 × 2060 × 2018 × 2060 × 0028 × 2060 × 0074 × 2060 × 0068 × 2060 × 0065 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [8.0] RIGHT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [8.0] NO-BREAK SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [8.0] LEFT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [12.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
|
|
@ -510,12 +517,13 @@
|
|||
÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 ÷ 5B83 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B83 (OLetter) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 3002 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.1] IDEOGRAPHIC FULL STOP (STerm) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 × 5B57 × 2060 × 3002 × 2060 ÷ 5B83 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] CJK UNIFIED IDEOGRAPH-5B57 (OLetter) × [5.0] WORD JOINER (Format_FE) × [12.0] IDEOGRAPHIC FULL STOP (STerm) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B83 (OLetter) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 × 0021 × 2060 × 0020 × 2060 × 0020 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] EXCLAMATION MARK (STerm) × [5.0] WORD JOINER (Format_FE) × [9.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [10.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 1F1E6 × 1F1E7 × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Other) × [12.0] REGIONAL INDICATOR SYMBOL LETTER B (Other) × [12.0] REGIONAL INDICATOR SYMBOL LETTER C (Other) ÷ [0.3]
|
||||
÷ 1F1E6 × 200D × 1F1E7 × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Other) × [5.0] ZERO WIDTH JOINER (Extend_FE) × [12.0] REGIONAL INDICATOR SYMBOL LETTER B (Other) × [12.0] REGIONAL INDICATOR SYMBOL LETTER C (Other) ÷ [0.3]
|
||||
÷ 1F1E6 × 1F1E7 × 200D × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Other) × [12.0] REGIONAL INDICATOR SYMBOL LETTER B (Other) × [5.0] ZERO WIDTH JOINER (Extend_FE) × [12.0] REGIONAL INDICATOR SYMBOL LETTER C (Other) ÷ [0.3]
|
||||
÷ 0020 × 200D × 0646 ÷ # ÷ [0.2] SPACE (Sp) × [5.0] ZERO WIDTH JOINER (Extend_FE) × [12.0] ARABIC LETTER NOON (OLetter) ÷ [0.3]
|
||||
÷ 0646 × 200D × 0020 ÷ # ÷ [0.2] ARABIC LETTER NOON (OLetter) × [5.0] ZERO WIDTH JOINER (Extend_FE) × [12.0] SPACE (Sp) ÷ [0.3]
|
||||
#
|
||||
# Lines: 495
|
||||
# Lines: 503
|
||||
#
|
||||
# EOF
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
# WordBreakProperty-7.0.0.txt
|
||||
# Date: 2014-02-19, 15:51:39 GMT [MD]
|
||||
# WordBreakProperty-8.0.0.txt
|
||||
# Date: 2015-02-14, 10:26:15 GMT [MD]
|
||||
#
|
||||
# Unicode Character Database
|
||||
# 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
|
||||
# For documentation, see http://www.unicode.org/reports/tr44/
|
||||
|
||||
|
|
@ -89,7 +89,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW
|
|||
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
|
||||
08E4..0902 ; Extend # Mn [31] ARABIC CURLY FATHA..DEVANAGARI SIGN ANUSVARA
|
||||
08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA
|
||||
0903 ; Extend # Mc DEVANAGARI SIGN VISARGA
|
||||
093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE
|
||||
093B ; Extend # Mc DEVANAGARI VOWEL SIGN OOE
|
||||
|
|
@ -252,8 +252,6 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW
|
|||
1932 ; Extend # Mn LIMBU SMALL LETTER ANUSVARA
|
||||
1933..1938 ; Extend # Mc [6] LIMBU SMALL LETTER TA..LIMBU SMALL LETTER LA
|
||||
1939..193B ; Extend # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I
|
||||
19B0..19C0 ; Extend # Mc [17] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE VOWEL SIGN IY
|
||||
19C8..19C9 ; Extend # Mc [2] NEW TAI LUE TONE MARK-1..NEW TAI LUE TONE MARK-2
|
||||
1A17..1A18 ; Extend # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U
|
||||
1A19..1A1A ; Extend # Mc [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O
|
||||
1A1B ; Extend # Mn BUGINESE VOWEL SIGN AE
|
||||
|
|
@ -327,7 +325,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW
|
|||
A66F ; Extend # Mn COMBINING CYRILLIC VZMET
|
||||
A670..A672 ; Extend # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN
|
||||
A674..A67D ; Extend # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK
|
||||
A69F ; Extend # Mn COMBINING CYRILLIC LETTER IOTIFIED E
|
||||
A69E..A69F ; Extend # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E
|
||||
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
|
||||
|
|
@ -381,7 +379,7 @@ ABEC ; Extend # Mc MEETEI MAYEK LUM IYEK
|
|||
ABED ; Extend # Mn MEETEI MAYEK APUN IYEK
|
||||
FB1E ; Extend # Mn HEBREW POINT JUDEO-SPANISH VARIKA
|
||||
FE00..FE0F ; Extend # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
|
||||
FE20..FE2D ; Extend # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON BELOW
|
||||
FE20..FE2F ; Extend # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF
|
||||
FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
|
||||
101FD ; Extend # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE
|
||||
102E0 ; Extend # Mn COPTIC EPACT THOUSANDS MARK
|
||||
|
|
@ -412,6 +410,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
|||
111B3..111B5 ; Extend # Mc [3] SHARADA VOWEL SIGN AA..SHARADA VOWEL SIGN II
|
||||
111B6..111BE ; Extend # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O
|
||||
111BF..111C0 ; Extend # Mc [2] SHARADA VOWEL SIGN AU..SHARADA SIGN VIRAMA
|
||||
111CA..111CC ; Extend # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK
|
||||
1122C..1122E ; Extend # Mc [3] KHOJKI VOWEL SIGN AA..KHOJKI VOWEL SIGN II
|
||||
1122F..11231 ; Extend # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI
|
||||
11232..11233 ; Extend # Mc [2] KHOJKI VOWEL SIGN O..KHOJKI VOWEL SIGN AU
|
||||
|
|
@ -421,7 +420,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
|||
112DF ; Extend # Mn KHUDAWADI SIGN ANUSVARA
|
||||
112E0..112E2 ; Extend # Mc [3] KHUDAWADI VOWEL SIGN AA..KHUDAWADI VOWEL SIGN II
|
||||
112E3..112EA ; Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
|
||||
11301 ; Extend # Mn GRANTHA SIGN CANDRABINDU
|
||||
11300..11301 ; Extend # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
|
||||
11302..11303 ; Extend # Mc [2] GRANTHA SIGN ANUSVARA..GRANTHA SIGN VISARGA
|
||||
1133C ; Extend # Mn GRANTHA SIGN NUKTA
|
||||
1133E..1133F ; Extend # Mc [2] GRANTHA VOWEL SIGN AA..GRANTHA VOWEL SIGN I
|
||||
|
|
@ -447,6 +446,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
|||
115BC..115BD ; Extend # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA
|
||||
115BE ; Extend # Mc SIDDHAM SIGN VISARGA
|
||||
115BF..115C0 ; Extend # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA
|
||||
115DC..115DD ; Extend # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU
|
||||
11630..11632 ; Extend # Mc [3] MODI VOWEL SIGN AA..MODI VOWEL SIGN II
|
||||
11633..1163A ; Extend # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI
|
||||
1163B..1163C ; Extend # Mc [2] MODI VOWEL SIGN O..MODI VOWEL SIGN AU
|
||||
|
|
@ -460,6 +460,11 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
|||
116B0..116B5 ; Extend # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU
|
||||
116B6 ; Extend # Mc TAKRI SIGN VIRAMA
|
||||
116B7 ; Extend # Mn TAKRI SIGN NUKTA
|
||||
1171D..1171F ; Extend # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA
|
||||
11720..11721 ; Extend # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA
|
||||
11722..11725 ; Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
|
||||
11726 ; Extend # Mc AHOM VOWEL SIGN E
|
||||
11727..1172B ; Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER
|
||||
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
|
||||
16F51..16F7E ; Extend # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
|
||||
|
|
@ -472,10 +477,16 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
|||
1D185..1D18B ; Extend # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
|
||||
1D1AA..1D1AD ; Extend # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
|
||||
1D242..1D244 ; Extend # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
|
||||
1DA00..1DA36 ; Extend # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN
|
||||
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
|
||||
1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
|
||||
E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
|
||||
|
||||
# Total code points: 1834
|
||||
# Total code points: 1967
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -583,7 +594,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
|
|||
0824 ; ALetter # Lm SAMARITAN MODIFIER LETTER SHORT A
|
||||
0828 ; ALetter # Lm SAMARITAN MODIFIER LETTER I
|
||||
0840..0858 ; ALetter # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN
|
||||
08A0..08B2 ; ALetter # Lo [19] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE
|
||||
08A0..08B4 ; ALetter # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
|
||||
0904..0939 ; ALetter # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA
|
||||
093D ; ALetter # Lo DEVANAGARI SIGN AVAGRAHA
|
||||
0950 ; ALetter # Lo DEVANAGARI OM
|
||||
|
|
@ -620,6 +631,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
|
|||
0ABD ; ALetter # Lo GUJARATI SIGN AVAGRAHA
|
||||
0AD0 ; ALetter # Lo GUJARATI OM
|
||||
0AE0..0AE1 ; ALetter # Lo [2] GUJARATI LETTER VOCALIC RR..GUJARATI LETTER VOCALIC LL
|
||||
0AF9 ; ALetter # Lo GUJARATI LETTER ZHA
|
||||
0B05..0B0C ; ALetter # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L
|
||||
0B0F..0B10 ; ALetter # Lo [2] ORIYA LETTER E..ORIYA LETTER AI
|
||||
0B13..0B28 ; ALetter # Lo [22] ORIYA LETTER O..ORIYA LETTER NA
|
||||
|
|
@ -646,7 +658,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
|
|||
0C12..0C28 ; ALetter # Lo [23] TELUGU LETTER O..TELUGU LETTER NA
|
||||
0C2A..0C39 ; ALetter # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA
|
||||
0C3D ; ALetter # Lo TELUGU SIGN AVAGRAHA
|
||||
0C58..0C59 ; ALetter # Lo [2] TELUGU LETTER TSA..TELUGU LETTER DZA
|
||||
0C58..0C5A ; ALetter # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA
|
||||
0C60..0C61 ; ALetter # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL
|
||||
0C85..0C8C ; ALetter # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L
|
||||
0C8E..0C90 ; ALetter # Lo [3] KANNADA LETTER E..KANNADA LETTER AI
|
||||
|
|
@ -662,7 +674,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
|
|||
0D12..0D3A ; ALetter # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA
|
||||
0D3D ; ALetter # Lo MALAYALAM SIGN AVAGRAHA
|
||||
0D4E ; ALetter # Lo MALAYALAM LETTER DOT REPH
|
||||
0D60..0D61 ; ALetter # Lo [2] MALAYALAM LETTER VOCALIC RR..MALAYALAM LETTER VOCALIC LL
|
||||
0D5F..0D61 ; ALetter # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL
|
||||
0D7A..0D7F ; ALetter # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K
|
||||
0D85..0D96 ; ALetter # Lo [18] SINHALA LETTER AYANNA..SINHALA LETTER AUYANNA
|
||||
0D9A..0DB1 ; ALetter # Lo [24] SINHALA LETTER ALPAPRAANA KAYANNA..SINHALA LETTER DANTAJA NAYANNA
|
||||
|
|
@ -695,7 +707,8 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
|
|||
1312..1315 ; ALetter # Lo [4] ETHIOPIC SYLLABLE GWI..ETHIOPIC SYLLABLE GWE
|
||||
1318..135A ; ALetter # Lo [67] ETHIOPIC SYLLABLE GGA..ETHIOPIC SYLLABLE FYA
|
||||
1380..138F ; ALetter # Lo [16] ETHIOPIC SYLLABLE SEBATBEIT MWA..ETHIOPIC SYLLABLE PWE
|
||||
13A0..13F4 ; ALetter # Lo [85] CHEROKEE LETTER A..CHEROKEE LETTER YV
|
||||
13A0..13F5 ; ALetter # L& [86] CHEROKEE LETTER A..CHEROKEE LETTER MV
|
||||
13F8..13FD ; ALetter # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV
|
||||
1401..166C ; ALetter # Lo [620] CANADIAN SYLLABICS E..CANADIAN SYLLABICS CARRIER TTSA
|
||||
166F..167F ; ALetter # Lo [17] CANADIAN SYLLABICS QAI..CANADIAN SYLLABICS BLACKFOOT W
|
||||
1681..169A ; ALetter # Lo [26] OGHAM LETTER BEITH..OGHAM LETTER PEITH
|
||||
|
|
@ -825,8 +838,9 @@ A770 ; ALetter # Lm MODIFIER LETTER US
|
|||
A771..A787 ; ALetter # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T
|
||||
A788 ; ALetter # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT
|
||||
A78B..A78E ; ALetter # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
|
||||
A78F ; ALetter # Lo LATIN LETTER SINOLOGICAL DOT
|
||||
A790..A7AD ; ALetter # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT
|
||||
A7B0..A7B1 ; ALetter # L& [2] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER TURNED T
|
||||
A7B0..A7B7 ; ALetter # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA
|
||||
A7F7 ; ALetter # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I
|
||||
A7F8..A7F9 ; ALetter # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
|
||||
A7FA ; ALetter # L& LATIN LETTER SMALL CAPITAL TURNED M
|
||||
|
|
@ -838,6 +852,7 @@ A840..A873 ; ALetter # Lo [52] PHAGS-PA LETTER KA..PHAGS-PA LETTER CANDRABIN
|
|||
A882..A8B3 ; ALetter # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA
|
||||
A8F2..A8F7 ; ALetter # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA
|
||||
A8FB ; ALetter # Lo DEVANAGARI HEADSTROKE
|
||||
A8FD ; ALetter # Lo DEVANAGARI JAIN OM
|
||||
A90A..A925 ; ALetter # Lo [28] KAYAH LI LETTER KA..KAYAH LI LETTER OO
|
||||
A930..A946 ; ALetter # Lo [23] REJANG LETTER KA..REJANG LETTER A
|
||||
A960..A97C ; ALetter # Lo [29] HANGUL CHOSEONG TIKEUT-MIEUM..HANGUL CHOSEONG SSANGYEORINHIEUH
|
||||
|
|
@ -856,7 +871,8 @@ AB20..AB26 ; ALetter # Lo [7] ETHIOPIC SYLLABLE CCHHA..ETHIOPIC SYLLABLE CC
|
|||
AB28..AB2E ; ALetter # Lo [7] ETHIOPIC SYLLABLE BBA..ETHIOPIC SYLLABLE BBO
|
||||
AB30..AB5A ; ALetter # L& [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG
|
||||
AB5C..AB5F ; ALetter # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK
|
||||
AB64..AB65 ; ALetter # L& [2] LATIN SMALL LETTER INVERTED ALPHA..GREEK LETTER SMALL CAPITAL OMEGA
|
||||
AB60..AB65 ; ALetter # L& [6] LATIN SMALL LETTER SAKHA YAT..GREEK LETTER SMALL CAPITAL OMEGA
|
||||
AB70..ABBF ; ALetter # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA
|
||||
ABC0..ABE2 ; ALetter # Lo [35] MEETEI MAYEK LETTER KOK..MEETEI MAYEK LETTER I LONSUM
|
||||
AC00..D7A3 ; ALetter # Lo [11172] HANGUL SYLLABLE GA..HANGUL SYLLABLE HIH
|
||||
D7B0..D7C6 ; ALetter # Lo [23] HANGUL JUNGSEONG O-YEO..HANGUL JUNGSEONG ARAEA-E
|
||||
|
|
@ -912,6 +928,8 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
|
|||
1083F..10855 ; ALetter # Lo [23] CYPRIOT SYLLABLE ZO..IMPERIAL ARAMAIC LETTER TAW
|
||||
10860..10876 ; ALetter # Lo [23] PALMYRENE LETTER ALEPH..PALMYRENE LETTER TAW
|
||||
10880..1089E ; ALetter # Lo [31] NABATAEAN LETTER FINAL ALEPH..NABATAEAN LETTER TAW
|
||||
108E0..108F2 ; ALetter # Lo [19] HATRAN LETTER ALEPH..HATRAN LETTER QOPH
|
||||
108F4..108F5 ; ALetter # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW
|
||||
10900..10915 ; ALetter # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU
|
||||
10920..10939 ; ALetter # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C
|
||||
10980..109B7 ; ALetter # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA
|
||||
|
|
@ -929,6 +947,8 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
|
|||
10B60..10B72 ; ALetter # Lo [19] INSCRIPTIONAL PAHLAVI LETTER ALEPH..INSCRIPTIONAL PAHLAVI LETTER TAW
|
||||
10B80..10B91 ; ALetter # Lo [18] PSALTER PAHLAVI LETTER ALEPH..PSALTER PAHLAVI LETTER TAW
|
||||
10C00..10C48 ; ALetter # Lo [73] OLD TURKIC LETTER ORKHON A..OLD TURKIC LETTER ORKHON BASH
|
||||
10C80..10CB2 ; ALetter # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US
|
||||
10CC0..10CF2 ; ALetter # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US
|
||||
11003..11037 ; ALetter # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA
|
||||
11083..110AF ; ALetter # Lo [45] KAITHI LETTER A..KAITHI LETTER HA
|
||||
110D0..110E8 ; ALetter # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE
|
||||
|
|
@ -938,8 +958,14 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
|
|||
11183..111B2 ; ALetter # Lo [48] SHARADA LETTER A..SHARADA LETTER HA
|
||||
111C1..111C4 ; ALetter # Lo [4] SHARADA SIGN AVAGRAHA..SHARADA OM
|
||||
111DA ; ALetter # Lo SHARADA EKAM
|
||||
111DC ; ALetter # Lo SHARADA HEADSTROKE
|
||||
11200..11211 ; ALetter # Lo [18] KHOJKI LETTER A..KHOJKI LETTER JJA
|
||||
11213..1122B ; ALetter # Lo [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA
|
||||
11280..11286 ; ALetter # Lo [7] MULTANI LETTER A..MULTANI LETTER GA
|
||||
11288 ; ALetter # Lo MULTANI LETTER GHA
|
||||
1128A..1128D ; ALetter # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA
|
||||
1128F..1129D ; ALetter # Lo [15] MULTANI LETTER NYA..MULTANI LETTER BA
|
||||
1129F..112A8 ; ALetter # Lo [10] MULTANI LETTER BHA..MULTANI LETTER RHA
|
||||
112B0..112DE ; ALetter # Lo [47] KHUDAWADI LETTER A..KHUDAWADI LETTER HA
|
||||
11305..1130C ; ALetter # Lo [8] GRANTHA LETTER A..GRANTHA LETTER VOCALIC L
|
||||
1130F..11310 ; ALetter # Lo [2] GRANTHA LETTER EE..GRANTHA LETTER AI
|
||||
|
|
@ -948,20 +974,24 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
|
|||
11332..11333 ; ALetter # Lo [2] GRANTHA LETTER LA..GRANTHA LETTER LLA
|
||||
11335..11339 ; ALetter # Lo [5] GRANTHA LETTER VA..GRANTHA LETTER HA
|
||||
1133D ; ALetter # Lo GRANTHA SIGN AVAGRAHA
|
||||
11350 ; ALetter # Lo GRANTHA OM
|
||||
1135D..11361 ; ALetter # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL
|
||||
11480..114AF ; ALetter # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA
|
||||
114C4..114C5 ; ALetter # Lo [2] TIRHUTA SIGN AVAGRAHA..TIRHUTA GVANG
|
||||
114C7 ; ALetter # Lo TIRHUTA OM
|
||||
11580..115AE ; ALetter # Lo [47] SIDDHAM LETTER A..SIDDHAM LETTER HA
|
||||
115D8..115DB ; ALetter # Lo [4] SIDDHAM LETTER THREE-CIRCLE ALTERNATE I..SIDDHAM LETTER ALTERNATE U
|
||||
11600..1162F ; ALetter # Lo [48] MODI LETTER A..MODI LETTER LLA
|
||||
11644 ; ALetter # Lo MODI SIGN HUVA
|
||||
11680..116AA ; ALetter # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA
|
||||
118A0..118DF ; ALetter # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO
|
||||
118FF ; ALetter # Lo WARANG CITI OM
|
||||
11AC0..11AF8 ; ALetter # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
|
||||
12000..12398 ; ALetter # Lo [921] CUNEIFORM SIGN A..CUNEIFORM SIGN UM TIMES ME
|
||||
12000..12399 ; ALetter # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
|
||||
12400..1246E ; ALetter # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
|
||||
12480..12543 ; ALetter # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
|
||||
13000..1342E ; ALetter # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
|
||||
14400..14646 ; ALetter # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530
|
||||
16800..16A38 ; ALetter # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ
|
||||
16A40..16A5E ; ALetter # Lo [31] MRO LETTER TA..MRO LETTER TEK
|
||||
16AD0..16AED ; ALetter # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I
|
||||
|
|
@ -1044,7 +1074,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
|
|||
1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
|
||||
1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z
|
||||
|
||||
# Total code points: 26647
|
||||
# Total code points: 27697
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -1139,12 +1169,13 @@ ABF0..ABF9 ; Numeric # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT N
|
|||
114D0..114D9 ; Numeric # Nd [10] TIRHUTA DIGIT ZERO..TIRHUTA DIGIT NINE
|
||||
11650..11659 ; Numeric # Nd [10] MODI DIGIT ZERO..MODI DIGIT NINE
|
||||
116C0..116C9 ; Numeric # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE
|
||||
11730..11739 ; Numeric # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE
|
||||
118E0..118E9 ; Numeric # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE
|
||||
16A60..16A69 ; Numeric # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE
|
||||
16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE
|
||||
1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
|
||||
|
||||
# Total code points: 531
|
||||
# Total code points: 541
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
# WordBreakTest-7.0.0.txt
|
||||
# Date: 2013-11-27, 09:54:53 GMT [MD]
|
||||
# WordBreakTest-8.0.0.txt
|
||||
# Date: 2015-05-02, 14:48:55 GMT [MD]
|
||||
#
|
||||
# Unicode Character Database
|
||||
# Copyright (c) 1991-2013 Unicode, Inc.
|
||||
# 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/
|
||||
#
|
||||
|
|
@ -1377,22 +1377,139 @@
|
|||
÷ 0061 × 0062 × 00AD × 0062 × 0079 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [5.0] LATIN SMALL LETTER B (ALetter) × [4.0] SOFT HYPHEN (Format_FE) × [5.0] LATIN SMALL LETTER B (ALetter) × [5.0] LATIN SMALL LETTER Y (ALetter) ÷ [0.3]
|
||||
÷ 0061 ÷ 0024 ÷ 002D ÷ 0033 × 0034 × 002C × 0035 × 0036 × 0037 × 002E × 0031 × 0034 ÷ 0025 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] DOLLAR SIGN (Other) ÷ [999.0] HYPHEN-MINUS (Other) ÷ [999.0] DIGIT THREE (Numeric) × [8.0] DIGIT FOUR (Numeric) × [12.0] COMMA (MidNum) × [11.0] DIGIT FIVE (Numeric) × [8.0] DIGIT SIX (Numeric) × [8.0] DIGIT SEVEN (Numeric) × [12.0] FULL STOP (MidNumLet) × [11.0] DIGIT ONE (Numeric) × [8.0] DIGIT FOUR (Numeric) ÷ [999.0] PERCENT SIGN (Other) ÷ [999.0] LATIN SMALL LETTER B (ALetter) ÷ [0.3]
|
||||
÷ 0033 × 0061 ÷ # ÷ [0.2] DIGIT THREE (Numeric) × [10.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0063 × 002E × 0064 ÷ # ÷ [0.2] LATIN SMALL LETTER C (ALetter) × [6.0] FULL STOP (MidNumLet) × [7.0] LATIN SMALL LETTER D (ALetter) ÷ [0.3]
|
||||
÷ 0043 × 002E × 0064 ÷ # ÷ [0.2] LATIN CAPITAL LETTER C (ALetter) × [6.0] FULL STOP (MidNumLet) × [7.0] LATIN SMALL LETTER D (ALetter) ÷ [0.3]
|
||||
÷ 0063 × 002E × 0044 ÷ # ÷ [0.2] LATIN SMALL LETTER C (ALetter) × [6.0] FULL STOP (MidNumLet) × [7.0] LATIN CAPITAL LETTER D (ALetter) ÷ [0.3]
|
||||
÷ 0043 × 002E × 0044 ÷ # ÷ [0.2] LATIN CAPITAL LETTER C (ALetter) × [6.0] FULL STOP (MidNumLet) × [7.0] LATIN CAPITAL LETTER D (ALetter) ÷ [0.3]
|
||||
÷ 2060 ÷ 0063 × 2060 × 0061 × 2060 × 006E × 2060 × 0027 × 2060 × 0074 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) ÷ [999.0] LATIN SMALL LETTER C (ALetter) × [4.0] WORD JOINER (Format_FE) × [5.0] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) × [5.0] LATIN SMALL LETTER N (ALetter) × [4.0] WORD JOINER (Format_FE) × [6.0] APOSTROPHE (Single_Quote) × [4.0] WORD JOINER (Format_FE) × [7.0] LATIN SMALL LETTER T (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 ÷ 0063 × 2060 × 0061 × 2060 × 006E × 2060 × 2019 × 2060 × 0074 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) ÷ [999.0] LATIN SMALL LETTER C (ALetter) × [4.0] WORD JOINER (Format_FE) × [5.0] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) × [5.0] LATIN SMALL LETTER N (ALetter) × [4.0] WORD JOINER (Format_FE) × [6.0] RIGHT SINGLE QUOTATION MARK (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [7.0] LATIN SMALL LETTER T (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 ÷ 0061 × 2060 × 0062 × 2060 × 00AD × 2060 × 0062 × 2060 × 0079 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) × [5.0] LATIN SMALL LETTER B (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] SOFT HYPHEN (Format_FE) × [4.0] WORD JOINER (Format_FE) × [5.0] LATIN SMALL LETTER B (ALetter) × [4.0] WORD JOINER (Format_FE) × [5.0] LATIN SMALL LETTER Y (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 ÷ 0061 × 2060 ÷ 0024 × 2060 ÷ 002D × 2060 ÷ 0033 × 2060 × 0034 × 2060 × 002C × 2060 × 0035 × 2060 × 0036 × 2060 × 0037 × 2060 × 002E × 2060 × 0031 × 2060 × 0034 × 2060 ÷ 0025 × 2060 ÷ 0062 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] DOLLAR SIGN (Other) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] HYPHEN-MINUS (Other) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] DIGIT THREE (Numeric) × [4.0] WORD JOINER (Format_FE) × [8.0] DIGIT FOUR (Numeric) × [4.0] WORD JOINER (Format_FE) × [12.0] COMMA (MidNum) × [4.0] WORD JOINER (Format_FE) × [11.0] DIGIT FIVE (Numeric) × [4.0] WORD JOINER (Format_FE) × [8.0] DIGIT SIX (Numeric) × [4.0] WORD JOINER (Format_FE) × [8.0] DIGIT SEVEN (Numeric) × [4.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [11.0] DIGIT ONE (Numeric) × [4.0] WORD JOINER (Format_FE) × [8.0] DIGIT FOUR (Numeric) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] PERCENT SIGN (Other) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] LATIN SMALL LETTER B (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 ÷ 0033 × 2060 × 0061 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) ÷ [999.0] DIGIT THREE (Numeric) × [4.0] WORD JOINER (Format_FE) × [10.0] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 ÷ 0063 × 2060 × 002E × 2060 × 0064 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) ÷ [999.0] LATIN SMALL LETTER C (ALetter) × [4.0] WORD JOINER (Format_FE) × [6.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [7.0] LATIN SMALL LETTER D (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 ÷ 0043 × 2060 × 002E × 2060 × 0064 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) ÷ [999.0] LATIN CAPITAL LETTER C (ALetter) × [4.0] WORD JOINER (Format_FE) × [6.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [7.0] LATIN SMALL LETTER D (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 ÷ 0063 × 2060 × 002E × 2060 × 0044 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) ÷ [999.0] LATIN SMALL LETTER C (ALetter) × [4.0] WORD JOINER (Format_FE) × [6.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER D (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 2060 ÷ 0043 × 2060 × 002E × 2060 × 0044 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) ÷ [999.0] LATIN CAPITAL LETTER C (ALetter) × [4.0] WORD JOINER (Format_FE) × [6.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER D (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 0061 ÷ 1F1E6 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] LATIN SMALL LETTER B (ALetter) ÷ [0.3]
|
||||
÷ 1F1F7 × 1F1FA ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) ÷ [0.3]
|
||||
÷ 1F1F7 × 1F1FA × 1F1F8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER S (Regional_Indicator) ÷ [0.3]
|
||||
÷ 1F1F7 × 1F1FA × 1F1F8 × 1F1EA ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER S (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER E (Regional_Indicator) ÷ [0.3]
|
||||
÷ 1F1F7 × 1F1FA ÷ 200B ÷ 1F1F8 × 1F1EA ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) ÷ [999.0] ZERO WIDTH SPACE (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER S (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER E (Regional_Indicator) ÷ [0.3]
|
||||
÷ 05D0 × 0022 × 05D0 ÷ # ÷ [0.2] HEBREW LETTER ALEF (Hebrew_Letter) × [7.2] QUOTATION MARK (Double_Quote) × [7.3] HEBREW LETTER ALEF (Hebrew_Letter) ÷ [0.3]
|
||||
÷ 1F1E6 × 1F1E7 × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER B (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER C (Regional_Indicator) ÷ [0.3]
|
||||
÷ 1F1E6 × 200D × 1F1E7 × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] ZERO WIDTH JOINER (Extend_FE) × [13.3] REGIONAL INDICATOR SYMBOL LETTER B (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER C (Regional_Indicator) ÷ [0.3]
|
||||
÷ 1F1E6 × 1F1E7 × 200D × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER B (Regional_Indicator) × [4.0] ZERO WIDTH JOINER (Extend_FE) × [13.3] REGIONAL INDICATOR SYMBOL LETTER C (Regional_Indicator) ÷ [0.3]
|
||||
÷ 0020 × 200D ÷ 0646 ÷ # ÷ [0.2] SPACE (Other) × [4.0] ZERO WIDTH JOINER (Extend_FE) ÷ [999.0] ARABIC LETTER NOON (ALetter) ÷ [0.3]
|
||||
÷ 0646 × 200D ÷ 0020 ÷ # ÷ [0.2] ARABIC LETTER NOON (ALetter) × [4.0] ZERO WIDTH JOINER (Extend_FE) ÷ [999.0] SPACE (Other) ÷ [0.3]
|
||||
÷ 0031 ÷ 003A ÷ 003A ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0031 ÷ 003A ÷ 003A ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0061 ÷ 003A ÷ 003A ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 ÷ 003A ÷ 003A ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0031 ÷ 003A ÷ 003A ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0061 ÷ 003A ÷ 003A ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 ÷ 003A ÷ 002E ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0031 ÷ 003A ÷ 002E ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0061 ÷ 003A ÷ 002E ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 ÷ 003A ÷ 002E ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0031 ÷ 003A ÷ 002E ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0061 ÷ 003A ÷ 002E ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 ÷ 003A ÷ 002C ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0031 ÷ 003A ÷ 002C ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0061 ÷ 003A ÷ 002C ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 ÷ 003A ÷ 002C ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0031 ÷ 003A ÷ 002C ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0061 ÷ 003A ÷ 002C ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 ÷ 002E ÷ 003A ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0031 ÷ 002E ÷ 003A ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0061 ÷ 002E ÷ 003A ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 ÷ 002E ÷ 003A ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0031 ÷ 002E ÷ 003A ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0061 ÷ 002E ÷ 003A ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 ÷ 002E ÷ 002E ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0031 ÷ 002E ÷ 002E ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0061 ÷ 002E ÷ 002E ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 ÷ 002E ÷ 002E ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0031 ÷ 002E ÷ 002E ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0061 ÷ 002E ÷ 002E ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 ÷ 002E ÷ 002C ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COMMA (MidNum) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0031 ÷ 002E ÷ 002C ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COMMA (MidNum) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0061 ÷ 002E ÷ 002C ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COMMA (MidNum) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 ÷ 002E ÷ 002C ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0031 ÷ 002E ÷ 002C ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0061 ÷ 002E ÷ 002C ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 ÷ 002C ÷ 003A ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0031 ÷ 002C ÷ 003A ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0061 ÷ 002C ÷ 003A ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 ÷ 002C ÷ 003A ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0031 ÷ 002C ÷ 003A ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0061 ÷ 002C ÷ 003A ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 ÷ 002C ÷ 002E ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0031 ÷ 002C ÷ 002E ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0061 ÷ 002C ÷ 002E ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 ÷ 002C ÷ 002E ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0031 ÷ 002C ÷ 002E ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0061 ÷ 002C ÷ 002E ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 ÷ 002C ÷ 002C ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COMMA (MidNum) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0031 ÷ 002C ÷ 002C ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COMMA (MidNum) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0061 ÷ 002C ÷ 002C ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COMMA (MidNum) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 ÷ 002C ÷ 002C ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0031 ÷ 002C ÷ 002C ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0061 ÷ 002C ÷ 002C ÷ 0061 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 ÷ 003A ÷ 003A ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0031 ÷ 003A ÷ 003A ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0061 ÷ 003A ÷ 003A ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 ÷ 003A ÷ 003A ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0031 ÷ 003A ÷ 003A ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0061 ÷ 003A ÷ 003A ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 ÷ 003A ÷ 002E ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0031 ÷ 003A ÷ 002E ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0061 ÷ 003A ÷ 002E ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 ÷ 003A ÷ 002E ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0031 ÷ 003A ÷ 002E ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0061 ÷ 003A ÷ 002E ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 ÷ 003A ÷ 002C ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0031 ÷ 003A ÷ 002C ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0061 ÷ 003A ÷ 002C ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 ÷ 003A ÷ 002C ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0031 ÷ 003A ÷ 002C ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0061 ÷ 003A ÷ 002C ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 ÷ 002E ÷ 003A ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0031 ÷ 002E ÷ 003A ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0061 ÷ 002E ÷ 003A ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 ÷ 002E ÷ 003A ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0031 ÷ 002E ÷ 003A ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0061 ÷ 002E ÷ 003A ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 ÷ 002E ÷ 002E ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0031 ÷ 002E ÷ 002E ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0061 ÷ 002E ÷ 002E ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 ÷ 002E ÷ 002E ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0031 ÷ 002E ÷ 002E ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0061 ÷ 002E ÷ 002E ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 ÷ 002E ÷ 002C ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COMMA (MidNum) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0031 ÷ 002E ÷ 002C ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COMMA (MidNum) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0061 ÷ 002E ÷ 002C ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COMMA (MidNum) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 ÷ 002E ÷ 002C ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0031 ÷ 002E ÷ 002C ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0061 ÷ 002E ÷ 002C ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 ÷ 002C ÷ 003A ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0031 ÷ 002C ÷ 003A ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0061 ÷ 002C ÷ 003A ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 ÷ 002C ÷ 003A ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0031 ÷ 002C ÷ 003A ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0061 ÷ 002C ÷ 003A ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 ÷ 002C ÷ 002E ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0031 ÷ 002C ÷ 002E ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0061 ÷ 002C ÷ 002E ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 ÷ 002C ÷ 002E ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0031 ÷ 002C ÷ 002E ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0061 ÷ 002C ÷ 002E ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] FULL STOP (MidNumLet) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 ÷ 002C ÷ 002C ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COMMA (MidNum) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0031 ÷ 002C ÷ 002C ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COMMA (MidNum) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0061 ÷ 002C ÷ 002C ÷ 0031 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COMMA (MidNum) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0061 ÷ 002C ÷ 002C ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0031 ÷ 002C ÷ 002C ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0061 × 005F × 0061 ÷ 002C ÷ 002C ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
|
||||
#
|
||||
# Lines: 1372
|
||||
# Lines: 1489
|
||||
#
|
||||
# EOF
|
||||
|
|
|
|||
|
|
@ -62,7 +62,7 @@
|
|||
"tools-for-build/PropList.txt"
|
||||
"tools-for-build/BidiMirroring.txt"
|
||||
"tools-for-build/DerivedAge.txt"
|
||||
"tools-for-build/LineBreakProperty.txt"
|
||||
"tools-for-build/LineBreak.txt"
|
||||
"tests/data/DerivedBidiClass.txt"
|
||||
"tests/data/HangulSyllableType.txt"
|
||||
"tests/data/GraphemeBreakProperty.txt"
|
||||
|
|
|
|||
|
|
@ -313,7 +313,7 @@ Wanted ~S, got ~S."
|
|||
|
||||
(defun test-line-break-class ()
|
||||
(declare (optimize (debug 2)))
|
||||
(with-open-file (s "../tools-for-build/LineBreakProperty.txt"
|
||||
(with-open-file (s "../tools-for-build/LineBreak.txt"
|
||||
:external-format :ascii)
|
||||
(with-test (:name (:line-break-class))
|
||||
(loop for line = (read-line s nil nil)
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load diff
30058
tools-for-build/Allkeys80.txt
Normal file
30058
tools-for-build/Allkeys80.txt
Normal file
File diff suppressed because it is too large
Load diff
|
|
@ -1,19 +1,19 @@
|
|||
# BidiMirroring-7.0.0.txt
|
||||
# Date: 2013-12-17, 00:00:00 GMT [KW, LI]
|
||||
# BidiMirroring-8.0.0.txt
|
||||
# Date: 2015-01-20, 18:30:00 GMT [KW, LI]
|
||||
#
|
||||
# Bidi_Mirroring_Glyph Property
|
||||
#
|
||||
# This file is an informative contributory data file in the
|
||||
# Unicode Character Database.
|
||||
#
|
||||
# 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
|
||||
#
|
||||
# This data file lists characters that have the Bidi_Mirrored=Yes property
|
||||
# value, for which there is another Unicode character that typically has a glyph
|
||||
# that is the mirror image of the original character's glyph.
|
||||
#
|
||||
# The repertoire covered by the file is Unicode 7.0.0.
|
||||
# The repertoire covered by the file is Unicode 8.0.0.
|
||||
#
|
||||
# The file contains a list of lines with mappings from one code point
|
||||
# to another one for character-based mirroring.
|
||||
|
|
@ -42,7 +42,7 @@
|
|||
#
|
||||
# This file was originally created by Markus Scherer.
|
||||
# Extended for Unicode 3.2, 4.0, 4.1, 5.0, 5.1, 5.2, and 6.0 by Ken Whistler,
|
||||
# and for Unicode 6.1, 6.2, 6.3, and 7.0 by Ken Whistler and Laurentiu Iancu.
|
||||
# and for subsequent versions by Ken Whistler and Laurentiu Iancu.
|
||||
#
|
||||
# ############################################################
|
||||
#
|
||||
|
|
|
|||
|
|
@ -1,14 +1,11 @@
|
|||
# Blocks-7.0.0.txt
|
||||
# Date: 2014-04-03, 23:23:00 GMT [RP, KW]
|
||||
# Blocks-8.0.0.txt
|
||||
# Date: 2014-11-10, 23:04:00 GMT [KW]
|
||||
#
|
||||
# Unicode Character Database
|
||||
# Copyright (c) 1991-2014 Unicode, Inc.
|
||||
# For terms of use, see http://www.unicode.org/terms_of_use.html
|
||||
# For documentation, see http://www.unicode.org/reports/tr44/
|
||||
#
|
||||
# Note: The casing of block names is not normative.
|
||||
# For example, "Basic Latin" and "BASIC LATIN" are equivalent.
|
||||
#
|
||||
# Format:
|
||||
# Start Code..End Code; Block Name
|
||||
|
||||
|
|
@ -20,6 +17,14 @@
|
|||
# For more information on the comparison of property values,
|
||||
# see UAX #44: http://www.unicode.org/reports/tr44/
|
||||
#
|
||||
# All block ranges start with a value where (cp MOD 16) = 0,
|
||||
# and end with a value where (cp MOD 16) = 15. In other words,
|
||||
# the last hexadecimal digit of the start of range is ...0
|
||||
# and the last hexadecimal digit of the end of range is ...F.
|
||||
# This constraint on block ranges guarantees that allocations
|
||||
# are done in terms of whole columns, and that code chart display
|
||||
# never involves splitting columns in the charts.
|
||||
#
|
||||
# All code points not explicitly listed for Block
|
||||
# have the value No_Block.
|
||||
|
||||
|
|
@ -168,6 +173,7 @@ AA80..AADF; Tai Viet
|
|||
AAE0..AAFF; Meetei Mayek Extensions
|
||||
AB00..AB2F; Ethiopic Extended-A
|
||||
AB30..AB6F; Latin Extended-E
|
||||
AB70..ABBF; Cherokee Supplement
|
||||
ABC0..ABFF; Meetei Mayek
|
||||
AC00..D7AF; Hangul Syllables
|
||||
D7B0..D7FF; Hangul Jamo Extended-B
|
||||
|
|
@ -210,6 +216,7 @@ FFF0..FFFF; Specials
|
|||
10840..1085F; Imperial Aramaic
|
||||
10860..1087F; Palmyrene
|
||||
10880..108AF; Nabataean
|
||||
108E0..108FF; Hatran
|
||||
10900..1091F; Phoenician
|
||||
10920..1093F; Lydian
|
||||
10980..1099F; Meroitic Hieroglyphs
|
||||
|
|
@ -223,6 +230,7 @@ FFF0..FFFF; Specials
|
|||
10B60..10B7F; Inscriptional Pahlavi
|
||||
10B80..10BAF; Psalter Pahlavi
|
||||
10C00..10C4F; Old Turkic
|
||||
10C80..10CFF; Old Hungarian
|
||||
10E60..10E7F; Rumi Numeral Symbols
|
||||
11000..1107F; Brahmi
|
||||
11080..110CF; Kaithi
|
||||
|
|
@ -232,17 +240,21 @@ FFF0..FFFF; Specials
|
|||
11180..111DF; Sharada
|
||||
111E0..111FF; Sinhala Archaic Numbers
|
||||
11200..1124F; Khojki
|
||||
11280..112AF; Multani
|
||||
112B0..112FF; Khudawadi
|
||||
11300..1137F; Grantha
|
||||
11480..114DF; Tirhuta
|
||||
11580..115FF; Siddham
|
||||
11600..1165F; Modi
|
||||
11680..116CF; Takri
|
||||
11700..1173F; Ahom
|
||||
118A0..118FF; Warang Citi
|
||||
11AC0..11AFF; Pau Cin Hau
|
||||
12000..123FF; Cuneiform
|
||||
12400..1247F; Cuneiform Numbers and Punctuation
|
||||
12480..1254F; Early Dynastic Cuneiform
|
||||
13000..1342F; Egyptian Hieroglyphs
|
||||
14400..1467F; Anatolian Hieroglyphs
|
||||
16800..16A3F; Bamum Supplement
|
||||
16A40..16A6F; Mro
|
||||
16AD0..16AFF; Bassa Vah
|
||||
|
|
@ -257,6 +269,7 @@ FFF0..FFFF; Specials
|
|||
1D300..1D35F; Tai Xuan Jing Symbols
|
||||
1D360..1D37F; Counting Rod Numerals
|
||||
1D400..1D7FF; Mathematical Alphanumeric Symbols
|
||||
1D800..1DAAF; Sutton SignWriting
|
||||
1E800..1E8DF; Mende Kikakui
|
||||
1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
|
||||
1F000..1F02F; Mahjong Tiles
|
||||
|
|
@ -271,9 +284,11 @@ FFF0..FFFF; Specials
|
|||
1F700..1F77F; Alchemical Symbols
|
||||
1F780..1F7FF; Geometric Shapes Extended
|
||||
1F800..1F8FF; Supplemental Arrows-C
|
||||
1F900..1F9FF; Supplemental Symbols and Pictographs
|
||||
20000..2A6DF; CJK Unified Ideographs Extension B
|
||||
2A700..2B73F; CJK Unified Ideographs Extension C
|
||||
2B740..2B81F; CJK Unified Ideographs Extension D
|
||||
2B820..2CEAF; CJK Unified Ideographs Extension E
|
||||
2F800..2FA1F; CJK Compatibility Ideographs Supplement
|
||||
E0000..E007F; Tags
|
||||
E0100..E01EF; Variation Selectors Supplement
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
# CaseFolding-7.0.0.txt
|
||||
# Date: 2014-04-09, 20:00:56 GMT [MD]
|
||||
# CaseFolding-8.0.0.txt
|
||||
# Date: 2015-01-13, 18:16:36 GMT [MD]
|
||||
#
|
||||
# Unicode Character Database
|
||||
# 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
|
||||
# For documentation, see http://www.unicode.org/reports/tr44/
|
||||
#
|
||||
|
|
@ -17,7 +17,7 @@
|
|||
# The data supports both implementations that require simple case foldings
|
||||
# (where string lengths don't change), and implementations that allow full case folding
|
||||
# (where string lengths may grow). Note that where they can be supported, the
|
||||
# full case foldings are superior: for example, they allow "MASSE" and "Ma[eszet (removed to prevent encoding issues)]e" to match.
|
||||
# full case foldings are superior: for example, they allow "MASSE" and "Ma<eszet>e" to match.
|
||||
#
|
||||
# All code points not listed in this file map to themselves.
|
||||
#
|
||||
|
|
@ -587,6 +587,12 @@
|
|||
10C5; C; 2D25; # GEORGIAN CAPITAL LETTER HOE
|
||||
10C7; C; 2D27; # GEORGIAN CAPITAL LETTER YN
|
||||
10CD; C; 2D2D; # GEORGIAN CAPITAL LETTER AEN
|
||||
13F8; C; 13F0; # CHEROKEE SMALL LETTER YE
|
||||
13F9; C; 13F1; # CHEROKEE SMALL LETTER YI
|
||||
13FA; C; 13F2; # CHEROKEE SMALL LETTER YO
|
||||
13FB; C; 13F3; # CHEROKEE SMALL LETTER YU
|
||||
13FC; C; 13F4; # CHEROKEE SMALL LETTER YV
|
||||
13FD; C; 13F5; # CHEROKEE SMALL LETTER MV
|
||||
1E00; C; 1E01; # LATIN CAPITAL LETTER A WITH RING BELOW
|
||||
1E02; C; 1E03; # LATIN CAPITAL LETTER B WITH DOT ABOVE
|
||||
1E04; C; 1E05; # LATIN CAPITAL LETTER B WITH DOT BELOW
|
||||
|
|
@ -1159,6 +1165,90 @@ A7AC; C; 0261; # LATIN CAPITAL LETTER SCRIPT G
|
|||
A7AD; C; 026C; # LATIN CAPITAL LETTER L WITH BELT
|
||||
A7B0; C; 029E; # LATIN CAPITAL LETTER TURNED K
|
||||
A7B1; C; 0287; # LATIN CAPITAL LETTER TURNED T
|
||||
A7B2; C; 029D; # LATIN CAPITAL LETTER J WITH CROSSED-TAIL
|
||||
A7B3; C; AB53; # LATIN CAPITAL LETTER CHI
|
||||
A7B4; C; A7B5; # LATIN CAPITAL LETTER BETA
|
||||
A7B6; C; A7B7; # LATIN CAPITAL LETTER OMEGA
|
||||
AB70; C; 13A0; # CHEROKEE SMALL LETTER A
|
||||
AB71; C; 13A1; # CHEROKEE SMALL LETTER E
|
||||
AB72; C; 13A2; # CHEROKEE SMALL LETTER I
|
||||
AB73; C; 13A3; # CHEROKEE SMALL LETTER O
|
||||
AB74; C; 13A4; # CHEROKEE SMALL LETTER U
|
||||
AB75; C; 13A5; # CHEROKEE SMALL LETTER V
|
||||
AB76; C; 13A6; # CHEROKEE SMALL LETTER GA
|
||||
AB77; C; 13A7; # CHEROKEE SMALL LETTER KA
|
||||
AB78; C; 13A8; # CHEROKEE SMALL LETTER GE
|
||||
AB79; C; 13A9; # CHEROKEE SMALL LETTER GI
|
||||
AB7A; C; 13AA; # CHEROKEE SMALL LETTER GO
|
||||
AB7B; C; 13AB; # CHEROKEE SMALL LETTER GU
|
||||
AB7C; C; 13AC; # CHEROKEE SMALL LETTER GV
|
||||
AB7D; C; 13AD; # CHEROKEE SMALL LETTER HA
|
||||
AB7E; C; 13AE; # CHEROKEE SMALL LETTER HE
|
||||
AB7F; C; 13AF; # CHEROKEE SMALL LETTER HI
|
||||
AB80; C; 13B0; # CHEROKEE SMALL LETTER HO
|
||||
AB81; C; 13B1; # CHEROKEE SMALL LETTER HU
|
||||
AB82; C; 13B2; # CHEROKEE SMALL LETTER HV
|
||||
AB83; C; 13B3; # CHEROKEE SMALL LETTER LA
|
||||
AB84; C; 13B4; # CHEROKEE SMALL LETTER LE
|
||||
AB85; C; 13B5; # CHEROKEE SMALL LETTER LI
|
||||
AB86; C; 13B6; # CHEROKEE SMALL LETTER LO
|
||||
AB87; C; 13B7; # CHEROKEE SMALL LETTER LU
|
||||
AB88; C; 13B8; # CHEROKEE SMALL LETTER LV
|
||||
AB89; C; 13B9; # CHEROKEE SMALL LETTER MA
|
||||
AB8A; C; 13BA; # CHEROKEE SMALL LETTER ME
|
||||
AB8B; C; 13BB; # CHEROKEE SMALL LETTER MI
|
||||
AB8C; C; 13BC; # CHEROKEE SMALL LETTER MO
|
||||
AB8D; C; 13BD; # CHEROKEE SMALL LETTER MU
|
||||
AB8E; C; 13BE; # CHEROKEE SMALL LETTER NA
|
||||
AB8F; C; 13BF; # CHEROKEE SMALL LETTER HNA
|
||||
AB90; C; 13C0; # CHEROKEE SMALL LETTER NAH
|
||||
AB91; C; 13C1; # CHEROKEE SMALL LETTER NE
|
||||
AB92; C; 13C2; # CHEROKEE SMALL LETTER NI
|
||||
AB93; C; 13C3; # CHEROKEE SMALL LETTER NO
|
||||
AB94; C; 13C4; # CHEROKEE SMALL LETTER NU
|
||||
AB95; C; 13C5; # CHEROKEE SMALL LETTER NV
|
||||
AB96; C; 13C6; # CHEROKEE SMALL LETTER QUA
|
||||
AB97; C; 13C7; # CHEROKEE SMALL LETTER QUE
|
||||
AB98; C; 13C8; # CHEROKEE SMALL LETTER QUI
|
||||
AB99; C; 13C9; # CHEROKEE SMALL LETTER QUO
|
||||
AB9A; C; 13CA; # CHEROKEE SMALL LETTER QUU
|
||||
AB9B; C; 13CB; # CHEROKEE SMALL LETTER QUV
|
||||
AB9C; C; 13CC; # CHEROKEE SMALL LETTER SA
|
||||
AB9D; C; 13CD; # CHEROKEE SMALL LETTER S
|
||||
AB9E; C; 13CE; # CHEROKEE SMALL LETTER SE
|
||||
AB9F; C; 13CF; # CHEROKEE SMALL LETTER SI
|
||||
ABA0; C; 13D0; # CHEROKEE SMALL LETTER SO
|
||||
ABA1; C; 13D1; # CHEROKEE SMALL LETTER SU
|
||||
ABA2; C; 13D2; # CHEROKEE SMALL LETTER SV
|
||||
ABA3; C; 13D3; # CHEROKEE SMALL LETTER DA
|
||||
ABA4; C; 13D4; # CHEROKEE SMALL LETTER TA
|
||||
ABA5; C; 13D5; # CHEROKEE SMALL LETTER DE
|
||||
ABA6; C; 13D6; # CHEROKEE SMALL LETTER TE
|
||||
ABA7; C; 13D7; # CHEROKEE SMALL LETTER DI
|
||||
ABA8; C; 13D8; # CHEROKEE SMALL LETTER TI
|
||||
ABA9; C; 13D9; # CHEROKEE SMALL LETTER DO
|
||||
ABAA; C; 13DA; # CHEROKEE SMALL LETTER DU
|
||||
ABAB; C; 13DB; # CHEROKEE SMALL LETTER DV
|
||||
ABAC; C; 13DC; # CHEROKEE SMALL LETTER DLA
|
||||
ABAD; C; 13DD; # CHEROKEE SMALL LETTER TLA
|
||||
ABAE; C; 13DE; # CHEROKEE SMALL LETTER TLE
|
||||
ABAF; C; 13DF; # CHEROKEE SMALL LETTER TLI
|
||||
ABB0; C; 13E0; # CHEROKEE SMALL LETTER TLO
|
||||
ABB1; C; 13E1; # CHEROKEE SMALL LETTER TLU
|
||||
ABB2; C; 13E2; # CHEROKEE SMALL LETTER TLV
|
||||
ABB3; C; 13E3; # CHEROKEE SMALL LETTER TSA
|
||||
ABB4; C; 13E4; # CHEROKEE SMALL LETTER TSE
|
||||
ABB5; C; 13E5; # CHEROKEE SMALL LETTER TSI
|
||||
ABB6; C; 13E6; # CHEROKEE SMALL LETTER TSO
|
||||
ABB7; C; 13E7; # CHEROKEE SMALL LETTER TSU
|
||||
ABB8; C; 13E8; # CHEROKEE SMALL LETTER TSV
|
||||
ABB9; C; 13E9; # CHEROKEE SMALL LETTER WA
|
||||
ABBA; C; 13EA; # CHEROKEE SMALL LETTER WE
|
||||
ABBB; C; 13EB; # CHEROKEE SMALL LETTER WI
|
||||
ABBC; C; 13EC; # CHEROKEE SMALL LETTER WO
|
||||
ABBD; C; 13ED; # CHEROKEE SMALL LETTER WU
|
||||
ABBE; C; 13EE; # CHEROKEE SMALL LETTER WV
|
||||
ABBF; C; 13EF; # CHEROKEE SMALL LETTER YA
|
||||
FB00; F; 0066 0066; # LATIN SMALL LIGATURE FF
|
||||
FB01; F; 0066 0069; # LATIN SMALL LIGATURE FI
|
||||
FB02; F; 0066 006C; # LATIN SMALL LIGATURE FL
|
||||
|
|
@ -1237,6 +1327,57 @@ FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z
|
|||
10425; C; 1044D; # DESERET CAPITAL LETTER ENG
|
||||
10426; C; 1044E; # DESERET CAPITAL LETTER OI
|
||||
10427; C; 1044F; # DESERET CAPITAL LETTER EW
|
||||
10C80; C; 10CC0; # OLD HUNGARIAN CAPITAL LETTER A
|
||||
10C81; C; 10CC1; # OLD HUNGARIAN CAPITAL LETTER AA
|
||||
10C82; C; 10CC2; # OLD HUNGARIAN CAPITAL LETTER EB
|
||||
10C83; C; 10CC3; # OLD HUNGARIAN CAPITAL LETTER AMB
|
||||
10C84; C; 10CC4; # OLD HUNGARIAN CAPITAL LETTER EC
|
||||
10C85; C; 10CC5; # OLD HUNGARIAN CAPITAL LETTER ENC
|
||||
10C86; C; 10CC6; # OLD HUNGARIAN CAPITAL LETTER ECS
|
||||
10C87; C; 10CC7; # OLD HUNGARIAN CAPITAL LETTER ED
|
||||
10C88; C; 10CC8; # OLD HUNGARIAN CAPITAL LETTER AND
|
||||
10C89; C; 10CC9; # OLD HUNGARIAN CAPITAL LETTER E
|
||||
10C8A; C; 10CCA; # OLD HUNGARIAN CAPITAL LETTER CLOSE E
|
||||
10C8B; C; 10CCB; # OLD HUNGARIAN CAPITAL LETTER EE
|
||||
10C8C; C; 10CCC; # OLD HUNGARIAN CAPITAL LETTER EF
|
||||
10C8D; C; 10CCD; # OLD HUNGARIAN CAPITAL LETTER EG
|
||||
10C8E; C; 10CCE; # OLD HUNGARIAN CAPITAL LETTER EGY
|
||||
10C8F; C; 10CCF; # OLD HUNGARIAN CAPITAL LETTER EH
|
||||
10C90; C; 10CD0; # OLD HUNGARIAN CAPITAL LETTER I
|
||||
10C91; C; 10CD1; # OLD HUNGARIAN CAPITAL LETTER II
|
||||
10C92; C; 10CD2; # OLD HUNGARIAN CAPITAL LETTER EJ
|
||||
10C93; C; 10CD3; # OLD HUNGARIAN CAPITAL LETTER EK
|
||||
10C94; C; 10CD4; # OLD HUNGARIAN CAPITAL LETTER AK
|
||||
10C95; C; 10CD5; # OLD HUNGARIAN CAPITAL LETTER UNK
|
||||
10C96; C; 10CD6; # OLD HUNGARIAN CAPITAL LETTER EL
|
||||
10C97; C; 10CD7; # OLD HUNGARIAN CAPITAL LETTER ELY
|
||||
10C98; C; 10CD8; # OLD HUNGARIAN CAPITAL LETTER EM
|
||||
10C99; C; 10CD9; # OLD HUNGARIAN CAPITAL LETTER EN
|
||||
10C9A; C; 10CDA; # OLD HUNGARIAN CAPITAL LETTER ENY
|
||||
10C9B; C; 10CDB; # OLD HUNGARIAN CAPITAL LETTER O
|
||||
10C9C; C; 10CDC; # OLD HUNGARIAN CAPITAL LETTER OO
|
||||
10C9D; C; 10CDD; # OLD HUNGARIAN CAPITAL LETTER NIKOLSBURG OE
|
||||
10C9E; C; 10CDE; # OLD HUNGARIAN CAPITAL LETTER RUDIMENTA OE
|
||||
10C9F; C; 10CDF; # OLD HUNGARIAN CAPITAL LETTER OEE
|
||||
10CA0; C; 10CE0; # OLD HUNGARIAN CAPITAL LETTER EP
|
||||
10CA1; C; 10CE1; # OLD HUNGARIAN CAPITAL LETTER EMP
|
||||
10CA2; C; 10CE2; # OLD HUNGARIAN CAPITAL LETTER ER
|
||||
10CA3; C; 10CE3; # OLD HUNGARIAN CAPITAL LETTER SHORT ER
|
||||
10CA4; C; 10CE4; # OLD HUNGARIAN CAPITAL LETTER ES
|
||||
10CA5; C; 10CE5; # OLD HUNGARIAN CAPITAL LETTER ESZ
|
||||
10CA6; C; 10CE6; # OLD HUNGARIAN CAPITAL LETTER ET
|
||||
10CA7; C; 10CE7; # OLD HUNGARIAN CAPITAL LETTER ENT
|
||||
10CA8; C; 10CE8; # OLD HUNGARIAN CAPITAL LETTER ETY
|
||||
10CA9; C; 10CE9; # OLD HUNGARIAN CAPITAL LETTER ECH
|
||||
10CAA; C; 10CEA; # OLD HUNGARIAN CAPITAL LETTER U
|
||||
10CAB; C; 10CEB; # OLD HUNGARIAN CAPITAL LETTER UU
|
||||
10CAC; C; 10CEC; # OLD HUNGARIAN CAPITAL LETTER NIKOLSBURG UE
|
||||
10CAD; C; 10CED; # OLD HUNGARIAN CAPITAL LETTER RUDIMENTA UE
|
||||
10CAE; C; 10CEE; # OLD HUNGARIAN CAPITAL LETTER EV
|
||||
10CAF; C; 10CEF; # OLD HUNGARIAN CAPITAL LETTER EZ
|
||||
10CB0; C; 10CF0; # OLD HUNGARIAN CAPITAL LETTER EZS
|
||||
10CB1; C; 10CF1; # OLD HUNGARIAN CAPITAL LETTER ENT-SHAPED SIGN
|
||||
10CB2; C; 10CF2; # OLD HUNGARIAN CAPITAL LETTER US
|
||||
118A0; C; 118C0; # WARANG CITI CAPITAL LETTER NGAA
|
||||
118A1; C; 118C1; # WARANG CITI CAPITAL LETTER A
|
||||
118A2; C; 118C2; # WARANG CITI CAPITAL LETTER WI
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
# CompositionExclusions-7.0.0.txt
|
||||
# Date: 2014-01-24, 15:00:00 GMT [KW, LI]
|
||||
# CompositionExclusions-8.0.0.txt
|
||||
# Date: 2015-02-19, 00:30:00 GMT [KW, LI]
|
||||
#
|
||||
# This file lists the characters for the Composition Exclusion Table
|
||||
# defined in UAX #15, Unicode Normalization Forms.
|
||||
|
|
@ -7,7 +7,7 @@
|
|||
# This file is a normative contributory data file in the
|
||||
# Unicode Character Database.
|
||||
#
|
||||
# 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
|
||||
#
|
||||
# For more information, see
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
# DerivedAge-7.0.0.txt
|
||||
# Date: 2014-05-28, 18:42:04 GMT [MD]
|
||||
# DerivedAge-8.0.0.txt
|
||||
# Date: 2015-02-13, 13:30:18 GMT [MD]
|
||||
#
|
||||
# Unicode Character Database
|
||||
# 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
|
||||
# For documentation, see http://www.unicode.org/reports/tr44/
|
||||
#
|
||||
|
|
@ -1467,4 +1467,72 @@ FE27..FE2D ; 7.0 # [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CONJOI
|
|||
|
||||
# Total code points: 2834
|
||||
|
||||
# ================================================
|
||||
|
||||
# Age=V8_0
|
||||
|
||||
# Newly assigned in Unicode 8.0.0 (June, 2015)
|
||||
|
||||
08B3..08B4 ; 8.0 # [2] ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER KAF WITH DOT BELOW
|
||||
08E3 ; 8.0 # ARABIC TURNED DAMMA BELOW
|
||||
0AF9 ; 8.0 # GUJARATI LETTER ZHA
|
||||
0C5A ; 8.0 # TELUGU LETTER RRRA
|
||||
0D5F ; 8.0 # MALAYALAM LETTER ARCHAIC II
|
||||
13F5 ; 8.0 # CHEROKEE LETTER MV
|
||||
13F8..13FD ; 8.0 # [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV
|
||||
20BE ; 8.0 # LARI SIGN
|
||||
218A..218B ; 8.0 # [2] TURNED DIGIT TWO..TURNED DIGIT THREE
|
||||
2BEC..2BEF ; 8.0 # [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS
|
||||
9FCD..9FD5 ; 8.0 # [9] CJK UNIFIED IDEOGRAPH-9FCD..CJK UNIFIED IDEOGRAPH-9FD5
|
||||
A69E ; 8.0 # COMBINING CYRILLIC LETTER EF
|
||||
A78F ; 8.0 # LATIN LETTER SINOLOGICAL DOT
|
||||
A7B2..A7B7 ; 8.0 # [6] LATIN CAPITAL LETTER J WITH CROSSED-TAIL..LATIN SMALL LETTER OMEGA
|
||||
A8FC..A8FD ; 8.0 # [2] DEVANAGARI SIGN SIDDHAM..DEVANAGARI JAIN OM
|
||||
AB60..AB63 ; 8.0 # [4] LATIN SMALL LETTER SAKHA YAT..LATIN SMALL LETTER UO
|
||||
AB70..ABBF ; 8.0 # [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA
|
||||
FE2E..FE2F ; 8.0 # [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF
|
||||
108E0..108F2 ; 8.0 # [19] HATRAN LETTER ALEPH..HATRAN LETTER QOPH
|
||||
108F4..108F5 ; 8.0 # [2] HATRAN LETTER SHIN..HATRAN LETTER TAW
|
||||
108FB..108FF ; 8.0 # [5] HATRAN NUMBER ONE..HATRAN NUMBER ONE HUNDRED
|
||||
109BC..109BD ; 8.0 # [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF
|
||||
109C0..109CF ; 8.0 # [16] MEROITIC CURSIVE NUMBER ONE..MEROITIC CURSIVE NUMBER SEVENTY
|
||||
109D2..109FF ; 8.0 # [46] MEROITIC CURSIVE NUMBER ONE HUNDRED..MEROITIC CURSIVE FRACTION TEN TWELFTHS
|
||||
10C80..10CB2 ; 8.0 # [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US
|
||||
10CC0..10CF2 ; 8.0 # [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US
|
||||
10CFA..10CFF ; 8.0 # [6] OLD HUNGARIAN NUMBER ONE..OLD HUNGARIAN NUMBER ONE THOUSAND
|
||||
111C9..111CC ; 8.0 # [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK
|
||||
111DB..111DF ; 8.0 # [5] SHARADA SIGN SIDDHAM..SHARADA SECTION MARK-2
|
||||
11280..11286 ; 8.0 # [7] MULTANI LETTER A..MULTANI LETTER GA
|
||||
11288 ; 8.0 # MULTANI LETTER GHA
|
||||
1128A..1128D ; 8.0 # [4] MULTANI LETTER CA..MULTANI LETTER JJA
|
||||
1128F..1129D ; 8.0 # [15] MULTANI LETTER NYA..MULTANI LETTER BA
|
||||
1129F..112A9 ; 8.0 # [11] MULTANI LETTER BHA..MULTANI SECTION MARK
|
||||
11300 ; 8.0 # GRANTHA SIGN COMBINING ANUSVARA ABOVE
|
||||
11350 ; 8.0 # GRANTHA OM
|
||||
115CA..115DD ; 8.0 # [20] SIDDHAM SECTION MARK WITH TRIDENT AND U-SHAPED ORNAMENTS..SIDDHAM VOWEL SIGN ALTERNATE UU
|
||||
11700..11719 ; 8.0 # [26] AHOM LETTER KA..AHOM LETTER JHA
|
||||
1171D..1172B ; 8.0 # [15] AHOM CONSONANT SIGN MEDIAL LA..AHOM SIGN KILLER
|
||||
11730..1173F ; 8.0 # [16] AHOM DIGIT ZERO..AHOM SYMBOL VI
|
||||
12399 ; 8.0 # CUNEIFORM SIGN U U
|
||||
12480..12543 ; 8.0 # [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
|
||||
14400..14646 ; 8.0 # [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530
|
||||
1D1DE..1D1E8 ; 8.0 # [11] MUSICAL SYMBOL KIEVAN C CLEF..MUSICAL SYMBOL KIEVAN FLAT SIGN
|
||||
1D800..1DA8B ; 8.0 # [652] SIGNWRITING HAND-FIST INDEX..SIGNWRITING PARENTHESIS
|
||||
1DA9B..1DA9F ; 8.0 # [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6
|
||||
1DAA1..1DAAF ; 8.0 # [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16
|
||||
1F32D..1F32F ; 8.0 # [3] HOT DOG..BURRITO
|
||||
1F37E..1F37F ; 8.0 # [2] BOTTLE WITH POPPING CORK..POPCORN
|
||||
1F3CF..1F3D3 ; 8.0 # [5] CRICKET BAT AND BALL..TABLE TENNIS PADDLE AND BALL
|
||||
1F3F8..1F3FF ; 8.0 # [8] BADMINTON RACQUET AND SHUTTLECOCK..EMOJI MODIFIER FITZPATRICK TYPE-6
|
||||
1F4FF ; 8.0 # PRAYER BEADS
|
||||
1F54B..1F54F ; 8.0 # [5] KAABA..BOWL OF HYGIEIA
|
||||
1F643..1F644 ; 8.0 # [2] UPSIDE-DOWN FACE..FACE WITH ROLLING EYES
|
||||
1F6D0 ; 8.0 # PLACE OF WORSHIP
|
||||
1F910..1F918 ; 8.0 # [9] ZIPPER-MOUTH FACE..SIGN OF THE HORNS
|
||||
1F980..1F984 ; 8.0 # [5] CRAB..UNICORN FACE
|
||||
1F9C0 ; 8.0 # CHEESE WEDGE
|
||||
2B820..2CEA1 ; 8.0 # [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
|
||||
|
||||
# Total code points: 7716
|
||||
|
||||
# EOF
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
# DerivedNormalizationProps-7.0.0.txt
|
||||
# Date: 2013-12-03, 15:11:47 GMT [MD]
|
||||
# DerivedNormalizationProps-8.0.0.txt
|
||||
# Date: 2015-02-13, 13:30:23 GMT [MD]
|
||||
#
|
||||
# Unicode Character Database
|
||||
# Copyright (c) 1991-2013 Unicode, Inc.
|
||||
# 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/
|
||||
|
||||
|
|
@ -3504,6 +3504,12 @@ FFE3 ; Expands_On_NFKC # Sk FULLWIDTH MACRON
|
|||
10CD ; NFKC_CF; 2D2D # L& GEORGIAN CAPITAL LETTER AEN
|
||||
10FC ; NFKC_CF; 10DC # Lm MODIFIER LETTER GEORGIAN NAR
|
||||
115F..1160 ; NFKC_CF; # Lo [2] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG FILLER
|
||||
13F8 ; NFKC_CF; 13F0 # L& CHEROKEE SMALL LETTER YE
|
||||
13F9 ; NFKC_CF; 13F1 # L& CHEROKEE SMALL LETTER YI
|
||||
13FA ; NFKC_CF; 13F2 # L& CHEROKEE SMALL LETTER YO
|
||||
13FB ; NFKC_CF; 13F3 # L& CHEROKEE SMALL LETTER YU
|
||||
13FC ; NFKC_CF; 13F4 # L& CHEROKEE SMALL LETTER YV
|
||||
13FD ; NFKC_CF; 13F5 # L& CHEROKEE SMALL LETTER MV
|
||||
17B4..17B5 ; NFKC_CF; # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
|
||||
180B..180D ; NFKC_CF; # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
|
||||
180E ; NFKC_CF; # Cf MONGOLIAN VOWEL SEPARATOR
|
||||
|
|
@ -5259,12 +5265,96 @@ A7AC ; NFKC_CF; 0261 # L& LATIN CAPITAL LETTER SCRIPT G
|
|||
A7AD ; NFKC_CF; 026C # L& LATIN CAPITAL LETTER L WITH BELT
|
||||
A7B0 ; NFKC_CF; 029E # L& LATIN CAPITAL LETTER TURNED K
|
||||
A7B1 ; NFKC_CF; 0287 # L& LATIN CAPITAL LETTER TURNED T
|
||||
A7B2 ; NFKC_CF; 029D # L& LATIN CAPITAL LETTER J WITH CROSSED-TAIL
|
||||
A7B3 ; NFKC_CF; AB53 # L& LATIN CAPITAL LETTER CHI
|
||||
A7B4 ; NFKC_CF; A7B5 # L& LATIN CAPITAL LETTER BETA
|
||||
A7B6 ; NFKC_CF; A7B7 # L& LATIN CAPITAL LETTER OMEGA
|
||||
A7F8 ; NFKC_CF; 0127 # Lm MODIFIER LETTER CAPITAL H WITH STROKE
|
||||
A7F9 ; NFKC_CF; 0153 # Lm MODIFIER LETTER SMALL LIGATURE OE
|
||||
AB5C ; NFKC_CF; A727 # Lm MODIFIER LETTER SMALL HENG
|
||||
AB5D ; NFKC_CF; AB37 # Lm MODIFIER LETTER SMALL L WITH INVERTED LAZY S
|
||||
AB5E ; NFKC_CF; 026B # Lm MODIFIER LETTER SMALL L WITH MIDDLE TILDE
|
||||
AB5F ; NFKC_CF; AB52 # Lm MODIFIER LETTER SMALL U WITH LEFT HOOK
|
||||
AB70 ; NFKC_CF; 13A0 # L& CHEROKEE SMALL LETTER A
|
||||
AB71 ; NFKC_CF; 13A1 # L& CHEROKEE SMALL LETTER E
|
||||
AB72 ; NFKC_CF; 13A2 # L& CHEROKEE SMALL LETTER I
|
||||
AB73 ; NFKC_CF; 13A3 # L& CHEROKEE SMALL LETTER O
|
||||
AB74 ; NFKC_CF; 13A4 # L& CHEROKEE SMALL LETTER U
|
||||
AB75 ; NFKC_CF; 13A5 # L& CHEROKEE SMALL LETTER V
|
||||
AB76 ; NFKC_CF; 13A6 # L& CHEROKEE SMALL LETTER GA
|
||||
AB77 ; NFKC_CF; 13A7 # L& CHEROKEE SMALL LETTER KA
|
||||
AB78 ; NFKC_CF; 13A8 # L& CHEROKEE SMALL LETTER GE
|
||||
AB79 ; NFKC_CF; 13A9 # L& CHEROKEE SMALL LETTER GI
|
||||
AB7A ; NFKC_CF; 13AA # L& CHEROKEE SMALL LETTER GO
|
||||
AB7B ; NFKC_CF; 13AB # L& CHEROKEE SMALL LETTER GU
|
||||
AB7C ; NFKC_CF; 13AC # L& CHEROKEE SMALL LETTER GV
|
||||
AB7D ; NFKC_CF; 13AD # L& CHEROKEE SMALL LETTER HA
|
||||
AB7E ; NFKC_CF; 13AE # L& CHEROKEE SMALL LETTER HE
|
||||
AB7F ; NFKC_CF; 13AF # L& CHEROKEE SMALL LETTER HI
|
||||
AB80 ; NFKC_CF; 13B0 # L& CHEROKEE SMALL LETTER HO
|
||||
AB81 ; NFKC_CF; 13B1 # L& CHEROKEE SMALL LETTER HU
|
||||
AB82 ; NFKC_CF; 13B2 # L& CHEROKEE SMALL LETTER HV
|
||||
AB83 ; NFKC_CF; 13B3 # L& CHEROKEE SMALL LETTER LA
|
||||
AB84 ; NFKC_CF; 13B4 # L& CHEROKEE SMALL LETTER LE
|
||||
AB85 ; NFKC_CF; 13B5 # L& CHEROKEE SMALL LETTER LI
|
||||
AB86 ; NFKC_CF; 13B6 # L& CHEROKEE SMALL LETTER LO
|
||||
AB87 ; NFKC_CF; 13B7 # L& CHEROKEE SMALL LETTER LU
|
||||
AB88 ; NFKC_CF; 13B8 # L& CHEROKEE SMALL LETTER LV
|
||||
AB89 ; NFKC_CF; 13B9 # L& CHEROKEE SMALL LETTER MA
|
||||
AB8A ; NFKC_CF; 13BA # L& CHEROKEE SMALL LETTER ME
|
||||
AB8B ; NFKC_CF; 13BB # L& CHEROKEE SMALL LETTER MI
|
||||
AB8C ; NFKC_CF; 13BC # L& CHEROKEE SMALL LETTER MO
|
||||
AB8D ; NFKC_CF; 13BD # L& CHEROKEE SMALL LETTER MU
|
||||
AB8E ; NFKC_CF; 13BE # L& CHEROKEE SMALL LETTER NA
|
||||
AB8F ; NFKC_CF; 13BF # L& CHEROKEE SMALL LETTER HNA
|
||||
AB90 ; NFKC_CF; 13C0 # L& CHEROKEE SMALL LETTER NAH
|
||||
AB91 ; NFKC_CF; 13C1 # L& CHEROKEE SMALL LETTER NE
|
||||
AB92 ; NFKC_CF; 13C2 # L& CHEROKEE SMALL LETTER NI
|
||||
AB93 ; NFKC_CF; 13C3 # L& CHEROKEE SMALL LETTER NO
|
||||
AB94 ; NFKC_CF; 13C4 # L& CHEROKEE SMALL LETTER NU
|
||||
AB95 ; NFKC_CF; 13C5 # L& CHEROKEE SMALL LETTER NV
|
||||
AB96 ; NFKC_CF; 13C6 # L& CHEROKEE SMALL LETTER QUA
|
||||
AB97 ; NFKC_CF; 13C7 # L& CHEROKEE SMALL LETTER QUE
|
||||
AB98 ; NFKC_CF; 13C8 # L& CHEROKEE SMALL LETTER QUI
|
||||
AB99 ; NFKC_CF; 13C9 # L& CHEROKEE SMALL LETTER QUO
|
||||
AB9A ; NFKC_CF; 13CA # L& CHEROKEE SMALL LETTER QUU
|
||||
AB9B ; NFKC_CF; 13CB # L& CHEROKEE SMALL LETTER QUV
|
||||
AB9C ; NFKC_CF; 13CC # L& CHEROKEE SMALL LETTER SA
|
||||
AB9D ; NFKC_CF; 13CD # L& CHEROKEE SMALL LETTER S
|
||||
AB9E ; NFKC_CF; 13CE # L& CHEROKEE SMALL LETTER SE
|
||||
AB9F ; NFKC_CF; 13CF # L& CHEROKEE SMALL LETTER SI
|
||||
ABA0 ; NFKC_CF; 13D0 # L& CHEROKEE SMALL LETTER SO
|
||||
ABA1 ; NFKC_CF; 13D1 # L& CHEROKEE SMALL LETTER SU
|
||||
ABA2 ; NFKC_CF; 13D2 # L& CHEROKEE SMALL LETTER SV
|
||||
ABA3 ; NFKC_CF; 13D3 # L& CHEROKEE SMALL LETTER DA
|
||||
ABA4 ; NFKC_CF; 13D4 # L& CHEROKEE SMALL LETTER TA
|
||||
ABA5 ; NFKC_CF; 13D5 # L& CHEROKEE SMALL LETTER DE
|
||||
ABA6 ; NFKC_CF; 13D6 # L& CHEROKEE SMALL LETTER TE
|
||||
ABA7 ; NFKC_CF; 13D7 # L& CHEROKEE SMALL LETTER DI
|
||||
ABA8 ; NFKC_CF; 13D8 # L& CHEROKEE SMALL LETTER TI
|
||||
ABA9 ; NFKC_CF; 13D9 # L& CHEROKEE SMALL LETTER DO
|
||||
ABAA ; NFKC_CF; 13DA # L& CHEROKEE SMALL LETTER DU
|
||||
ABAB ; NFKC_CF; 13DB # L& CHEROKEE SMALL LETTER DV
|
||||
ABAC ; NFKC_CF; 13DC # L& CHEROKEE SMALL LETTER DLA
|
||||
ABAD ; NFKC_CF; 13DD # L& CHEROKEE SMALL LETTER TLA
|
||||
ABAE ; NFKC_CF; 13DE # L& CHEROKEE SMALL LETTER TLE
|
||||
ABAF ; NFKC_CF; 13DF # L& CHEROKEE SMALL LETTER TLI
|
||||
ABB0 ; NFKC_CF; 13E0 # L& CHEROKEE SMALL LETTER TLO
|
||||
ABB1 ; NFKC_CF; 13E1 # L& CHEROKEE SMALL LETTER TLU
|
||||
ABB2 ; NFKC_CF; 13E2 # L& CHEROKEE SMALL LETTER TLV
|
||||
ABB3 ; NFKC_CF; 13E3 # L& CHEROKEE SMALL LETTER TSA
|
||||
ABB4 ; NFKC_CF; 13E4 # L& CHEROKEE SMALL LETTER TSE
|
||||
ABB5 ; NFKC_CF; 13E5 # L& CHEROKEE SMALL LETTER TSI
|
||||
ABB6 ; NFKC_CF; 13E6 # L& CHEROKEE SMALL LETTER TSO
|
||||
ABB7 ; NFKC_CF; 13E7 # L& CHEROKEE SMALL LETTER TSU
|
||||
ABB8 ; NFKC_CF; 13E8 # L& CHEROKEE SMALL LETTER TSV
|
||||
ABB9 ; NFKC_CF; 13E9 # L& CHEROKEE SMALL LETTER WA
|
||||
ABBA ; NFKC_CF; 13EA # L& CHEROKEE SMALL LETTER WE
|
||||
ABBB ; NFKC_CF; 13EB # L& CHEROKEE SMALL LETTER WI
|
||||
ABBC ; NFKC_CF; 13EC # L& CHEROKEE SMALL LETTER WO
|
||||
ABBD ; NFKC_CF; 13ED # L& CHEROKEE SMALL LETTER WU
|
||||
ABBE ; NFKC_CF; 13EE # L& CHEROKEE SMALL LETTER WV
|
||||
ABBF ; NFKC_CF; 13EF # L& CHEROKEE SMALL LETTER YA
|
||||
F900 ; NFKC_CF; 8C48 # Lo CJK COMPATIBILITY IDEOGRAPH-F900
|
||||
F901 ; NFKC_CF; 66F4 # Lo CJK COMPATIBILITY IDEOGRAPH-F901
|
||||
F902 ; NFKC_CF; 8ECA # Lo CJK COMPATIBILITY IDEOGRAPH-F902
|
||||
|
|
@ -6641,6 +6731,57 @@ FFF0..FFF8 ; NFKC_CF; # Cn [9] <reserved-FFF0>..<reserved-FF
|
|||
10425 ; NFKC_CF; 1044D # L& DESERET CAPITAL LETTER ENG
|
||||
10426 ; NFKC_CF; 1044E # L& DESERET CAPITAL LETTER OI
|
||||
10427 ; NFKC_CF; 1044F # L& DESERET CAPITAL LETTER EW
|
||||
10C80 ; NFKC_CF; 10CC0 # L& OLD HUNGARIAN CAPITAL LETTER A
|
||||
10C81 ; NFKC_CF; 10CC1 # L& OLD HUNGARIAN CAPITAL LETTER AA
|
||||
10C82 ; NFKC_CF; 10CC2 # L& OLD HUNGARIAN CAPITAL LETTER EB
|
||||
10C83 ; NFKC_CF; 10CC3 # L& OLD HUNGARIAN CAPITAL LETTER AMB
|
||||
10C84 ; NFKC_CF; 10CC4 # L& OLD HUNGARIAN CAPITAL LETTER EC
|
||||
10C85 ; NFKC_CF; 10CC5 # L& OLD HUNGARIAN CAPITAL LETTER ENC
|
||||
10C86 ; NFKC_CF; 10CC6 # L& OLD HUNGARIAN CAPITAL LETTER ECS
|
||||
10C87 ; NFKC_CF; 10CC7 # L& OLD HUNGARIAN CAPITAL LETTER ED
|
||||
10C88 ; NFKC_CF; 10CC8 # L& OLD HUNGARIAN CAPITAL LETTER AND
|
||||
10C89 ; NFKC_CF; 10CC9 # L& OLD HUNGARIAN CAPITAL LETTER E
|
||||
10C8A ; NFKC_CF; 10CCA # L& OLD HUNGARIAN CAPITAL LETTER CLOSE E
|
||||
10C8B ; NFKC_CF; 10CCB # L& OLD HUNGARIAN CAPITAL LETTER EE
|
||||
10C8C ; NFKC_CF; 10CCC # L& OLD HUNGARIAN CAPITAL LETTER EF
|
||||
10C8D ; NFKC_CF; 10CCD # L& OLD HUNGARIAN CAPITAL LETTER EG
|
||||
10C8E ; NFKC_CF; 10CCE # L& OLD HUNGARIAN CAPITAL LETTER EGY
|
||||
10C8F ; NFKC_CF; 10CCF # L& OLD HUNGARIAN CAPITAL LETTER EH
|
||||
10C90 ; NFKC_CF; 10CD0 # L& OLD HUNGARIAN CAPITAL LETTER I
|
||||
10C91 ; NFKC_CF; 10CD1 # L& OLD HUNGARIAN CAPITAL LETTER II
|
||||
10C92 ; NFKC_CF; 10CD2 # L& OLD HUNGARIAN CAPITAL LETTER EJ
|
||||
10C93 ; NFKC_CF; 10CD3 # L& OLD HUNGARIAN CAPITAL LETTER EK
|
||||
10C94 ; NFKC_CF; 10CD4 # L& OLD HUNGARIAN CAPITAL LETTER AK
|
||||
10C95 ; NFKC_CF; 10CD5 # L& OLD HUNGARIAN CAPITAL LETTER UNK
|
||||
10C96 ; NFKC_CF; 10CD6 # L& OLD HUNGARIAN CAPITAL LETTER EL
|
||||
10C97 ; NFKC_CF; 10CD7 # L& OLD HUNGARIAN CAPITAL LETTER ELY
|
||||
10C98 ; NFKC_CF; 10CD8 # L& OLD HUNGARIAN CAPITAL LETTER EM
|
||||
10C99 ; NFKC_CF; 10CD9 # L& OLD HUNGARIAN CAPITAL LETTER EN
|
||||
10C9A ; NFKC_CF; 10CDA # L& OLD HUNGARIAN CAPITAL LETTER ENY
|
||||
10C9B ; NFKC_CF; 10CDB # L& OLD HUNGARIAN CAPITAL LETTER O
|
||||
10C9C ; NFKC_CF; 10CDC # L& OLD HUNGARIAN CAPITAL LETTER OO
|
||||
10C9D ; NFKC_CF; 10CDD # L& OLD HUNGARIAN CAPITAL LETTER NIKOLSBURG OE
|
||||
10C9E ; NFKC_CF; 10CDE # L& OLD HUNGARIAN CAPITAL LETTER RUDIMENTA OE
|
||||
10C9F ; NFKC_CF; 10CDF # L& OLD HUNGARIAN CAPITAL LETTER OEE
|
||||
10CA0 ; NFKC_CF; 10CE0 # L& OLD HUNGARIAN CAPITAL LETTER EP
|
||||
10CA1 ; NFKC_CF; 10CE1 # L& OLD HUNGARIAN CAPITAL LETTER EMP
|
||||
10CA2 ; NFKC_CF; 10CE2 # L& OLD HUNGARIAN CAPITAL LETTER ER
|
||||
10CA3 ; NFKC_CF; 10CE3 # L& OLD HUNGARIAN CAPITAL LETTER SHORT ER
|
||||
10CA4 ; NFKC_CF; 10CE4 # L& OLD HUNGARIAN CAPITAL LETTER ES
|
||||
10CA5 ; NFKC_CF; 10CE5 # L& OLD HUNGARIAN CAPITAL LETTER ESZ
|
||||
10CA6 ; NFKC_CF; 10CE6 # L& OLD HUNGARIAN CAPITAL LETTER ET
|
||||
10CA7 ; NFKC_CF; 10CE7 # L& OLD HUNGARIAN CAPITAL LETTER ENT
|
||||
10CA8 ; NFKC_CF; 10CE8 # L& OLD HUNGARIAN CAPITAL LETTER ETY
|
||||
10CA9 ; NFKC_CF; 10CE9 # L& OLD HUNGARIAN CAPITAL LETTER ECH
|
||||
10CAA ; NFKC_CF; 10CEA # L& OLD HUNGARIAN CAPITAL LETTER U
|
||||
10CAB ; NFKC_CF; 10CEB # L& OLD HUNGARIAN CAPITAL LETTER UU
|
||||
10CAC ; NFKC_CF; 10CEC # L& OLD HUNGARIAN CAPITAL LETTER NIKOLSBURG UE
|
||||
10CAD ; NFKC_CF; 10CED # L& OLD HUNGARIAN CAPITAL LETTER RUDIMENTA UE
|
||||
10CAE ; NFKC_CF; 10CEE # L& OLD HUNGARIAN CAPITAL LETTER EV
|
||||
10CAF ; NFKC_CF; 10CEF # L& OLD HUNGARIAN CAPITAL LETTER EZ
|
||||
10CB0 ; NFKC_CF; 10CF0 # L& OLD HUNGARIAN CAPITAL LETTER EZS
|
||||
10CB1 ; NFKC_CF; 10CF1 # L& OLD HUNGARIAN CAPITAL LETTER ENT-SHAPED SIGN
|
||||
10CB2 ; NFKC_CF; 10CF2 # L& OLD HUNGARIAN CAPITAL LETTER US
|
||||
118A0 ; NFKC_CF; 118C0 # L& WARANG CITI CAPITAL LETTER NGAA
|
||||
118A1 ; NFKC_CF; 118C1 # L& WARANG CITI CAPITAL LETTER A
|
||||
118A2 ; NFKC_CF; 118C2 # L& WARANG CITI CAPITAL LETTER WI
|
||||
|
|
@ -8493,7 +8634,7 @@ E0080..E00FF ; NFKC_CF; # Cn [128] <reserved-E0080>..<reserved-E
|
|||
E0100..E01EF ; NFKC_CF; # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
|
||||
E01F0..E0FFF ; NFKC_CF; # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
|
||||
|
||||
# Total code points: 10005
|
||||
# Total code points: 10146
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -8827,6 +8968,7 @@ E01F0..E0FFF ; NFKC_CF; # Cn [3600] <reserved-E01F0>..<reserved-
|
|||
10CD ; Changes_When_NFKC_Casefolded # L& GEORGIAN CAPITAL LETTER AEN
|
||||
10FC ; Changes_When_NFKC_Casefolded # Lm MODIFIER LETTER GEORGIAN NAR
|
||||
115F..1160 ; Changes_When_NFKC_Casefolded # Lo [2] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG FILLER
|
||||
13F8..13FD ; Changes_When_NFKC_Casefolded # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV
|
||||
17B4..17B5 ; Changes_When_NFKC_Casefolded # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
|
||||
180B..180D ; Changes_When_NFKC_Casefolded # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
|
||||
180E ; Changes_When_NFKC_Casefolded # Cf MONGOLIAN VOWEL SEPARATOR
|
||||
|
|
@ -9248,9 +9390,11 @@ A7A4 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER N W
|
|||
A7A6 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER R WITH OBLIQUE STROKE
|
||||
A7A8 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER S WITH OBLIQUE STROKE
|
||||
A7AA..A7AD ; Changes_When_NFKC_Casefolded # L& [4] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER L WITH BELT
|
||||
A7B0..A7B1 ; Changes_When_NFKC_Casefolded # L& [2] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER TURNED T
|
||||
A7B0..A7B4 ; Changes_When_NFKC_Casefolded # L& [5] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER BETA
|
||||
A7B6 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER OMEGA
|
||||
A7F8..A7F9 ; Changes_When_NFKC_Casefolded # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
|
||||
AB5C..AB5F ; Changes_When_NFKC_Casefolded # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK
|
||||
AB70..ABBF ; Changes_When_NFKC_Casefolded # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA
|
||||
F900..FA0D ; Changes_When_NFKC_Casefolded # Lo [270] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA0D
|
||||
FA10 ; Changes_When_NFKC_Casefolded # Lo CJK COMPATIBILITY IDEOGRAPH-FA10
|
||||
FA12 ; Changes_When_NFKC_Casefolded # Lo CJK COMPATIBILITY IDEOGRAPH-FA12
|
||||
|
|
@ -9375,6 +9519,7 @@ FFE9..FFEC ; Changes_When_NFKC_Casefolded # Sm [4] HALFWIDTH LEFTWARDS ARRO
|
|||
FFED..FFEE ; Changes_When_NFKC_Casefolded # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE
|
||||
FFF0..FFF8 ; Changes_When_NFKC_Casefolded # Cn [9] <reserved-FFF0>..<reserved-FFF8>
|
||||
10400..10427 ; Changes_When_NFKC_Casefolded # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW
|
||||
10C80..10CB2 ; Changes_When_NFKC_Casefolded # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US
|
||||
118A0..118BF ; Changes_When_NFKC_Casefolded # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO
|
||||
1BCA0..1BCA3 ; Changes_When_NFKC_Casefolded # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
|
||||
1D15E..1D164 ; Changes_When_NFKC_Casefolded # So [7] MUSICAL SYMBOL HALF NOTE..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE
|
||||
|
|
@ -9472,6 +9617,6 @@ E0080..E00FF ; Changes_When_NFKC_Casefolded # Cn [128] <reserved-E0080>..<reser
|
|||
E0100..E01EF ; Changes_When_NFKC_Casefolded # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
|
||||
E01F0..E0FFF ; Changes_When_NFKC_Casefolded # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
|
||||
|
||||
# Total code points: 10005
|
||||
# Total code points: 10146
|
||||
|
||||
# EOF
|
||||
|
|
|
|||
|
|
@ -1,12 +1,12 @@
|
|||
# EastAsianWidth-7.0.0.txt
|
||||
# Date: 2014-02-28, 23:15:00 GMT [KW, LI]
|
||||
# EastAsianWidth-8.0.0.txt
|
||||
# Date: 2015-02-10, 21:00:00 GMT [KW, LI]
|
||||
#
|
||||
# East_Asian_Width Property
|
||||
#
|
||||
# This file is an informative contributory data file in the
|
||||
# Unicode Character Database.
|
||||
#
|
||||
# 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.
|
||||
|
|
@ -23,6 +23,7 @@
|
|||
# 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
|
||||
|
|
@ -328,8 +329,8 @@
|
|||
0840..0858;N # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN
|
||||
0859..085B;N # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK
|
||||
085E;N # Po MANDAIC PUNCTUATION
|
||||
08A0..08B2;N # Lo [19] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE
|
||||
08E4..08FF;N # Mn [28] ARABIC CURLY FATHA..ARABIC MARK SIDEWAYS NOON GHUNNA
|
||||
08A0..08B4;N # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
|
||||
08E3..08FF;N # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA
|
||||
0900..0902;N # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA
|
||||
0903;N # Mc DEVANAGARI SIGN VISARGA
|
||||
0904..0939;N # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA
|
||||
|
|
@ -421,6 +422,7 @@
|
|||
0AE6..0AEF;N # Nd [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE
|
||||
0AF0;N # Po GUJARATI ABBREVIATION SIGN
|
||||
0AF1;N # Sc GUJARATI RUPEE SIGN
|
||||
0AF9;N # Lo GUJARATI LETTER ZHA
|
||||
0B01;N # Mn ORIYA SIGN CANDRABINDU
|
||||
0B02..0B03;N # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA
|
||||
0B05..0B0C;N # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L
|
||||
|
|
@ -483,7 +485,7 @@
|
|||
0C46..0C48;N # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI
|
||||
0C4A..0C4D;N # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA
|
||||
0C55..0C56;N # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK
|
||||
0C58..0C59;N # Lo [2] TELUGU LETTER TSA..TELUGU LETTER DZA
|
||||
0C58..0C5A;N # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA
|
||||
0C60..0C61;N # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL
|
||||
0C62..0C63;N # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL
|
||||
0C66..0C6F;N # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE
|
||||
|
|
@ -524,7 +526,7 @@
|
|||
0D4D;N # Mn MALAYALAM SIGN VIRAMA
|
||||
0D4E;N # Lo MALAYALAM LETTER DOT REPH
|
||||
0D57;N # Mc MALAYALAM AU LENGTH MARK
|
||||
0D60..0D61;N # Lo [2] MALAYALAM LETTER VOCALIC RR..MALAYALAM LETTER VOCALIC LL
|
||||
0D5F..0D61;N # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL
|
||||
0D62..0D63;N # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL
|
||||
0D66..0D6F;N # Nd [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE
|
||||
0D70..0D75;N # No [6] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE QUARTERS
|
||||
|
|
@ -680,7 +682,8 @@
|
|||
1369..137C;N # No [20] ETHIOPIC DIGIT ONE..ETHIOPIC NUMBER TEN THOUSAND
|
||||
1380..138F;N # Lo [16] ETHIOPIC SYLLABLE SEBATBEIT MWA..ETHIOPIC SYLLABLE PWE
|
||||
1390..1399;N # So [10] ETHIOPIC TONAL MARK YIZET..ETHIOPIC TONAL MARK KURT
|
||||
13A0..13F4;N # Lo [85] CHEROKEE LETTER A..CHEROKEE LETTER YV
|
||||
13A0..13F5;N # Lu [86] CHEROKEE LETTER A..CHEROKEE LETTER MV
|
||||
13F8..13FD;N # Ll [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV
|
||||
1400;N # Pd CANADIAN SYLLABICS HYPHEN
|
||||
1401..166C;N # Lo [620] CANADIAN SYLLABICS E..CANADIAN SYLLABICS CARRIER TTSA
|
||||
166D..166E;N # Po [2] CANADIAN SYLLABICS CHI SIGN..CANADIAN SYLLABICS FULL STOP
|
||||
|
|
@ -748,9 +751,7 @@
|
|||
1950..196D;N # Lo [30] TAI LE LETTER KA..TAI LE LETTER AI
|
||||
1970..1974;N # Lo [5] TAI LE LETTER TONE-2..TAI LE LETTER TONE-6
|
||||
1980..19AB;N # Lo [44] NEW TAI LUE LETTER HIGH QA..NEW TAI LUE LETTER LOW SUA
|
||||
19B0..19C0;N # Mc [17] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE VOWEL SIGN IY
|
||||
19C1..19C7;N # Lo [7] NEW TAI LUE LETTER FINAL V..NEW TAI LUE LETTER FINAL B
|
||||
19C8..19C9;N # Mc [2] NEW TAI LUE TONE MARK-1..NEW TAI LUE TONE MARK-2
|
||||
19B0..19C9;N # Lo [26] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2
|
||||
19D0..19D9;N # Nd [10] NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE
|
||||
19DA;N # No NEW TAI LUE THAM DIGIT ONE
|
||||
19DE..19DF;N # So [2] NEW TAI LUE SIGN LAE..NEW TAI LUE SIGN LAEV
|
||||
|
|
@ -944,7 +945,7 @@
|
|||
20A9;H # Sc WON SIGN
|
||||
20AA..20AB;N # Sc [2] NEW SHEQEL SIGN..DONG SIGN
|
||||
20AC;A # Sc EURO SIGN
|
||||
20AD..20BD;N # Sc [17] KIP SIGN..RUBLE SIGN
|
||||
20AD..20BE;N # Sc [18] KIP SIGN..LARI SIGN
|
||||
20D0..20DC;N # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
|
||||
20DD..20E0;N # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH
|
||||
20E1;N # Mn COMBINING LEFT RIGHT ARROW ABOVE
|
||||
|
|
@ -1004,6 +1005,7 @@
|
|||
2183..2184;N # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C
|
||||
2185..2188;N # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND
|
||||
2189;A # No VULGAR FRACTION ZERO THIRDS
|
||||
218A..218B;N # So [2] TURNED DIGIT TWO..TURNED DIGIT THREE
|
||||
2190..2194;A # Sm [5] LEFTWARDS ARROW..LEFT RIGHT ARROW
|
||||
2195..2199;A # So [5] UP DOWN ARROW..SOUTH WEST ARROW
|
||||
219A..219B;N # Sm [2] LEFTWARDS ARROW WITH STROKE..RIGHTWARDS ARROW WITH STROKE
|
||||
|
|
@ -1262,6 +1264,7 @@
|
|||
2B98..2BB9;N # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX
|
||||
2BBD..2BC8;N # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
|
||||
2BCA..2BD1;N # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN
|
||||
2BEC..2BEF;N # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS
|
||||
2C00..2C2E;N # Lu [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
|
||||
2C30..2C5E;N # Ll [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE
|
||||
2C60..2C7B;N # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E
|
||||
|
|
@ -1407,8 +1410,8 @@
|
|||
3400..4DB5;W # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
|
||||
4DB6..4DBF;W # Cn [10] <reserved-4DB6>..<reserved-4DBF>
|
||||
4DC0..4DFF;N # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION
|
||||
4E00..9FCC;W # Lo [20941] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCC
|
||||
9FCD..9FFF;W # Cn [51] <reserved-9FCD>..<reserved-9FFF>
|
||||
4E00..9FD5;W # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
|
||||
9FD6..9FFF;W # Cn [42] <reserved-9FD6>..<reserved-9FFF>
|
||||
A000..A014;W # Lo [21] YI SYLLABLE IT..YI SYLLABLE E
|
||||
A015;W # Lm YI SYLLABLE WU
|
||||
A016..A48C;W # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR
|
||||
|
|
@ -1432,7 +1435,7 @@ A67E;N # Po CYRILLIC KAVYKA
|
|||
A67F;N # Lm CYRILLIC PAYEROK
|
||||
A680..A69B;N # L& [28] CYRILLIC CAPITAL LETTER DWE..CYRILLIC SMALL LETTER CROSSED O
|
||||
A69C..A69D;N # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN
|
||||
A69F;N # Mn COMBINING CYRILLIC LETTER IOTIFIED E
|
||||
A69E..A69F;N # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E
|
||||
A6A0..A6E5;N # Lo [70] BAMUM LETTER A..BAMUM LETTER KI
|
||||
A6E6..A6EF;N # Nl [10] BAMUM LETTER MO..BAMUM LETTER KOGHOM
|
||||
A6F0..A6F1;N # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS
|
||||
|
|
@ -1446,8 +1449,9 @@ A771..A787;N # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR
|
|||
A788;N # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT
|
||||
A789..A78A;N # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN
|
||||
A78B..A78E;N # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
|
||||
A78F;N # Lo LATIN LETTER SINOLOGICAL DOT
|
||||
A790..A7AD;N # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT
|
||||
A7B0..A7B1;N # Lu [2] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER TURNED T
|
||||
A7B0..A7B7;N # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA
|
||||
A7F7;N # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I
|
||||
A7F8..A7F9;N # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
|
||||
A7FA;N # Ll LATIN LETTER SMALL CAPITAL TURNED M
|
||||
|
|
@ -1479,6 +1483,8 @@ A8E0..A8F1;N # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAG
|
|||
A8F2..A8F7;N # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA
|
||||
A8F8..A8FA;N # Po [3] DEVANAGARI SIGN PUSHPIKA..DEVANAGARI CARET
|
||||
A8FB;N # Lo DEVANAGARI HEADSTROKE
|
||||
A8FC;N # Po DEVANAGARI SIGN SIDDHAM
|
||||
A8FD;N # Lo DEVANAGARI JAIN OM
|
||||
A900..A909;N # Nd [10] KAYAH LI DIGIT ZERO..KAYAH LI DIGIT NINE
|
||||
A90A..A925;N # Lo [28] KAYAH LI LETTER KA..KAYAH LI LETTER OO
|
||||
A926..A92D;N # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU
|
||||
|
|
@ -1560,7 +1566,8 @@ AB28..AB2E;N # Lo [7] ETHIOPIC SYLLABLE BBA..ETHIOPIC SYLLABLE BBO
|
|||
AB30..AB5A;N # Ll [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG
|
||||
AB5B;N # Sk MODIFIER BREVE WITH INVERTED BREVE
|
||||
AB5C..AB5F;N # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK
|
||||
AB64..AB65;N # Ll [2] LATIN SMALL LETTER INVERTED ALPHA..GREEK LETTER SMALL CAPITAL OMEGA
|
||||
AB60..AB65;N # Ll [6] LATIN SMALL LETTER SAKHA YAT..GREEK LETTER SMALL CAPITAL OMEGA
|
||||
AB70..ABBF;N # Ll [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA
|
||||
ABC0..ABE2;N # Lo [35] MEETEI MAYEK LETTER KOK..MEETEI MAYEK LETTER I LONSUM
|
||||
ABE3..ABE4;N # Mc [2] MEETEI MAYEK VOWEL SIGN ONAP..MEETEI MAYEK VOWEL SIGN INAP
|
||||
ABE5;N # Mn MEETEI MAYEK VOWEL SIGN ANAP
|
||||
|
|
@ -1609,7 +1616,7 @@ FE10..FE16;W # Po [7] PRESENTATION FORM FOR VERTICAL COMMA..PRESENTATION
|
|||
FE17;W # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE LENTICULAR BRACKET
|
||||
FE18;W # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRAKCET
|
||||
FE19;W # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS
|
||||
FE20..FE2D;N # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON BELOW
|
||||
FE20..FE2F;N # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF
|
||||
FE30;W # Po PRESENTATION FORM FOR VERTICAL TWO DOT LEADER
|
||||
FE31..FE32;W # Pd [2] PRESENTATION FORM FOR VERTICAL EM DASH..PRESENTATION FORM FOR VERTICAL EN DASH
|
||||
FE33..FE34;W # Pc [2] PRESENTATION FORM FOR VERTICAL LOW LINE..PRESENTATION FORM FOR VERTICAL WAVY LOW LINE
|
||||
|
|
@ -1766,6 +1773,9 @@ FFFD;A # So REPLACEMENT CHARACTER
|
|||
10879..1087F;N # No [7] PALMYRENE NUMBER ONE..PALMYRENE NUMBER TWENTY
|
||||
10880..1089E;N # Lo [31] NABATAEAN LETTER FINAL ALEPH..NABATAEAN LETTER TAW
|
||||
108A7..108AF;N # No [9] NABATAEAN NUMBER ONE..NABATAEAN NUMBER ONE HUNDRED
|
||||
108E0..108F2;N # Lo [19] HATRAN LETTER ALEPH..HATRAN LETTER QOPH
|
||||
108F4..108F5;N # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW
|
||||
108FB..108FF;N # No [5] HATRAN NUMBER ONE..HATRAN NUMBER ONE HUNDRED
|
||||
10900..10915;N # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU
|
||||
10916..1091B;N # No [6] PHOENICIAN NUMBER ONE..PHOENICIAN NUMBER THREE
|
||||
1091F;N # Po PHOENICIAN WORD SEPARATOR
|
||||
|
|
@ -1773,7 +1783,10 @@ FFFD;A # So REPLACEMENT CHARACTER
|
|||
1093F;N # Po LYDIAN TRIANGULAR MARK
|
||||
10980..1099F;N # Lo [32] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC HIEROGLYPHIC SYMBOL VIDJ-2
|
||||
109A0..109B7;N # Lo [24] MEROITIC CURSIVE LETTER A..MEROITIC CURSIVE LETTER DA
|
||||
109BC..109BD;N # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF
|
||||
109BE..109BF;N # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN
|
||||
109C0..109CF;N # No [16] MEROITIC CURSIVE NUMBER ONE..MEROITIC CURSIVE NUMBER SEVENTY
|
||||
109D2..109FF;N # No [46] MEROITIC CURSIVE NUMBER ONE HUNDRED..MEROITIC CURSIVE FRACTION TEN TWELFTHS
|
||||
10A00;N # Lo KHAROSHTHI LETTER A
|
||||
10A01..10A03;N # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R
|
||||
10A05..10A06;N # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O
|
||||
|
|
@ -1806,6 +1819,9 @@ FFFD;A # So REPLACEMENT CHARACTER
|
|||
10B99..10B9C;N # Po [4] PSALTER PAHLAVI SECTION MARK..PSALTER PAHLAVI FOUR DOTS WITH DOT
|
||||
10BA9..10BAF;N # No [7] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER ONE HUNDRED
|
||||
10C00..10C48;N # Lo [73] OLD TURKIC LETTER ORKHON A..OLD TURKIC LETTER ORKHON BASH
|
||||
10C80..10CB2;N # Lu [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US
|
||||
10CC0..10CF2;N # Ll [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US
|
||||
10CFA..10CFF;N # No [6] OLD HUNGARIAN NUMBER ONE..OLD HUNGARIAN NUMBER ONE THOUSAND
|
||||
10E60..10E7E;N # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS
|
||||
11000;N # Mc BRAHMI SIGN CANDRABINDU
|
||||
11001;N # Mn BRAHMI SIGN ANUSVARA
|
||||
|
|
@ -1846,10 +1862,14 @@ FFFD;A # So REPLACEMENT CHARACTER
|
|||
111B6..111BE;N # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O
|
||||
111BF..111C0;N # Mc [2] SHARADA VOWEL SIGN AU..SHARADA SIGN VIRAMA
|
||||
111C1..111C4;N # Lo [4] SHARADA SIGN AVAGRAHA..SHARADA OM
|
||||
111C5..111C8;N # Po [4] SHARADA DANDA..SHARADA SEPARATOR
|
||||
111C5..111C9;N # Po [5] SHARADA DANDA..SHARADA SANDHI MARK
|
||||
111CA..111CC;N # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK
|
||||
111CD;N # Po SHARADA SUTRA MARK
|
||||
111D0..111D9;N # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE
|
||||
111DA;N # Lo SHARADA EKAM
|
||||
111DB;N # Po SHARADA SIGN SIDDHAM
|
||||
111DC;N # Lo SHARADA HEADSTROKE
|
||||
111DD..111DF;N # Po [3] SHARADA CONTINUATION SIGN..SHARADA SECTION MARK-2
|
||||
111E1..111F4;N # No [20] SINHALA ARCHAIC DIGIT ONE..SINHALA ARCHAIC NUMBER ONE THOUSAND
|
||||
11200..11211;N # Lo [18] KHOJKI LETTER A..KHOJKI LETTER JJA
|
||||
11213..1122B;N # Lo [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA
|
||||
|
|
@ -1860,12 +1880,18 @@ FFFD;A # So REPLACEMENT CHARACTER
|
|||
11235;N # Mc KHOJKI SIGN VIRAMA
|
||||
11236..11237;N # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
|
||||
11238..1123D;N # Po [6] KHOJKI DANDA..KHOJKI ABBREVIATION SIGN
|
||||
11280..11286;N # Lo [7] MULTANI LETTER A..MULTANI LETTER GA
|
||||
11288;N # Lo MULTANI LETTER GHA
|
||||
1128A..1128D;N # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA
|
||||
1128F..1129D;N # Lo [15] MULTANI LETTER NYA..MULTANI LETTER BA
|
||||
1129F..112A8;N # Lo [10] MULTANI LETTER BHA..MULTANI LETTER RHA
|
||||
112A9;N # Po MULTANI SECTION MARK
|
||||
112B0..112DE;N # Lo [47] KHUDAWADI LETTER A..KHUDAWADI LETTER HA
|
||||
112DF;N # Mn KHUDAWADI SIGN ANUSVARA
|
||||
112E0..112E2;N # Mc [3] KHUDAWADI VOWEL SIGN AA..KHUDAWADI VOWEL SIGN II
|
||||
112E3..112EA;N # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
|
||||
112F0..112F9;N # Nd [10] KHUDAWADI DIGIT ZERO..KHUDAWADI DIGIT NINE
|
||||
11301;N # Mn GRANTHA SIGN CANDRABINDU
|
||||
11300..11301;N # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
|
||||
11302..11303;N # Mc [2] GRANTHA SIGN ANUSVARA..GRANTHA SIGN VISARGA
|
||||
11305..1130C;N # Lo [8] GRANTHA LETTER A..GRANTHA LETTER VOCALIC L
|
||||
1130F..11310;N # Lo [2] GRANTHA LETTER EE..GRANTHA LETTER AI
|
||||
|
|
@ -1880,6 +1906,7 @@ FFFD;A # So REPLACEMENT CHARACTER
|
|||
11341..11344;N # Mc [4] GRANTHA VOWEL SIGN U..GRANTHA VOWEL SIGN VOCALIC RR
|
||||
11347..11348;N # Mc [2] GRANTHA VOWEL SIGN EE..GRANTHA VOWEL SIGN AI
|
||||
1134B..1134D;N # Mc [3] GRANTHA VOWEL SIGN OO..GRANTHA SIGN VIRAMA
|
||||
11350;N # Lo GRANTHA OM
|
||||
11357;N # Mc GRANTHA AU LENGTH MARK
|
||||
1135D..11361;N # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL
|
||||
11362..11363;N # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL
|
||||
|
|
@ -1905,7 +1932,9 @@ FFFD;A # So REPLACEMENT CHARACTER
|
|||
115BC..115BD;N # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA
|
||||
115BE;N # Mc SIDDHAM SIGN VISARGA
|
||||
115BF..115C0;N # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA
|
||||
115C1..115C9;N # Po [9] SIDDHAM SIGN SIDDHAM..SIDDHAM END OF TEXT MARK
|
||||
115C1..115D7;N # Po [23] SIDDHAM SIGN SIDDHAM..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES
|
||||
115D8..115DB;N # Lo [4] SIDDHAM LETTER THREE-CIRCLE ALTERNATE I..SIDDHAM LETTER ALTERNATE U
|
||||
115DC..115DD;N # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU
|
||||
11600..1162F;N # Lo [48] MODI LETTER A..MODI LETTER LLA
|
||||
11630..11632;N # Mc [3] MODI VOWEL SIGN AA..MODI VOWEL SIGN II
|
||||
11633..1163A;N # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI
|
||||
|
|
@ -1925,15 +1954,27 @@ FFFD;A # So REPLACEMENT CHARACTER
|
|||
116B6;N # Mc TAKRI SIGN VIRAMA
|
||||
116B7;N # Mn TAKRI SIGN NUKTA
|
||||
116C0..116C9;N # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE
|
||||
11700..11719;N # Lo [26] AHOM LETTER KA..AHOM LETTER JHA
|
||||
1171D..1171F;N # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA
|
||||
11720..11721;N # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA
|
||||
11722..11725;N # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
|
||||
11726;N # Mc AHOM VOWEL SIGN E
|
||||
11727..1172B;N # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER
|
||||
11730..11739;N # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE
|
||||
1173A..1173B;N # No [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY
|
||||
1173C..1173E;N # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI
|
||||
1173F;N # So AHOM SYMBOL VI
|
||||
118A0..118DF;N # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO
|
||||
118E0..118E9;N # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE
|
||||
118EA..118F2;N # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY
|
||||
118FF;N # Lo WARANG CITI OM
|
||||
11AC0..11AF8;N # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
|
||||
12000..12398;N # Lo [921] CUNEIFORM SIGN A..CUNEIFORM SIGN UM TIMES ME
|
||||
12000..12399;N # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
|
||||
12400..1246E;N # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
|
||||
12470..12474;N # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON
|
||||
12480..12543;N # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
|
||||
13000..1342E;N # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
|
||||
14400..14646;N # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530
|
||||
16800..16A38;N # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ
|
||||
16A40..16A5E;N # Lo [31] MRO LETTER TA..MRO LETTER TEK
|
||||
16A60..16A69;N # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE
|
||||
|
|
@ -1979,7 +2020,7 @@ FFFD;A # So REPLACEMENT CHARACTER
|
|||
1D185..1D18B;N # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
|
||||
1D18C..1D1A9;N # So [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH
|
||||
1D1AA..1D1AD;N # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
|
||||
1D1AE..1D1DD;N # So [48] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL PES SUBPUNCTIS
|
||||
1D1AE..1D1E8;N # So [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN
|
||||
1D200..1D241;N # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54
|
||||
1D242..1D244;N # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
|
||||
1D245;N # So GREEK MUSICAL LEIMMA
|
||||
|
|
@ -2026,6 +2067,18 @@ FFFD;A # So REPLACEMENT CHARACTER
|
|||
1D7C3;N # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL
|
||||
1D7C4..1D7CB;N # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA
|
||||
1D7CE..1D7FF;N # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
|
||||
1D800..1D9FF;N # So [512] SIGNWRITING HAND-FIST INDEX..SIGNWRITING HEAD
|
||||
1DA00..1DA36;N # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN
|
||||
1DA37..1DA3A;N # So [4] SIGNWRITING AIR BLOW SMALL ROTATIONS..SIGNWRITING BREATH EXHALE
|
||||
1DA3B..1DA6C;N # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT
|
||||
1DA6D..1DA74;N # So [8] SIGNWRITING SHOULDER HIP SPINE..SIGNWRITING TORSO-FLOORPLANE TWISTING
|
||||
1DA75;N # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS
|
||||
1DA76..1DA83;N # So [14] SIGNWRITING LIMB COMBINATION..SIGNWRITING LOCATION DEPTH
|
||||
1DA84;N # Mn SIGNWRITING LOCATION HEAD NECK
|
||||
1DA85..1DA86;N # So [2] SIGNWRITING LOCATION TORSO..SIGNWRITING LOCATION LIMBS DIGITS
|
||||
1DA87..1DA8B;N # Po [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS
|
||||
1DA9B..1DA9F;N # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6
|
||||
1DAA1..1DAAF;N # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16
|
||||
1E800..1E8C4;N # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON
|
||||
1E8C7..1E8CF;N # No [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE
|
||||
1E8D0..1E8D6;N # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
|
||||
|
|
@ -2081,19 +2134,14 @@ FFFD;A # So REPLACEMENT CHARACTER
|
|||
1F210..1F23A;W # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6
|
||||
1F240..1F248;W # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557
|
||||
1F250..1F251;W # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT
|
||||
1F300..1F32C;N # So [45] CYCLONE..WIND BLOWING FACE
|
||||
1F330..1F37D;N # So [78] CHESTNUT..FORK AND KNIFE WITH PLATE
|
||||
1F380..1F3CE;N # So [79] RIBBON..RACING CAR
|
||||
1F3D4..1F3F7;N # So [36] SNOW CAPPED MOUNTAIN..LABEL
|
||||
1F400..1F4FE;N # So [255] RAT..PORTABLE STEREO
|
||||
1F500..1F54A;N # So [75] TWISTED RIGHTWARDS ARROWS..DOVE OF PEACE
|
||||
1F550..1F579;N # So [42] CLOCK FACE ONE OCLOCK..JOYSTICK
|
||||
1F300..1F3FA;N # So [251] CYCLONE..AMPHORA
|
||||
1F3FB..1F3FF;N # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
|
||||
1F400..1F579;N # So [378] RAT..JOYSTICK
|
||||
1F57B..1F5A3;N # So [41] LEFT HAND TELEPHONE RECEIVER..BLACK DOWN POINTING BACKHAND INDEX
|
||||
1F5A5..1F5FF;N # So [91] DESKTOP COMPUTER..MOYAI
|
||||
1F600..1F642;N # So [67] GRINNING FACE..SLIGHTLY SMILING FACE
|
||||
1F645..1F64F;N # So [11] FACE WITH NO GOOD GESTURE..PERSON WITH FOLDED HANDS
|
||||
1F600..1F64F;N # So [80] GRINNING FACE..PERSON WITH FOLDED HANDS
|
||||
1F650..1F67F;N # So [48] NORTH WEST POINTING LEAF..REVERSE CHECKER BOARD
|
||||
1F680..1F6CF;N # So [80] ROCKET..BED
|
||||
1F680..1F6D0;N # So [81] ROCKET..PLACE OF WORSHIP
|
||||
1F6E0..1F6EC;N # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING
|
||||
1F6F0..1F6F3;N # So [4] SATELLITE..PASSENGER SHIP
|
||||
1F700..1F773;N # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
|
||||
|
|
@ -2103,12 +2151,17 @@ FFFD;A # So REPLACEMENT CHARACTER
|
|||
1F850..1F859;N # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW
|
||||
1F860..1F887;N # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW
|
||||
1F890..1F8AD;N # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS
|
||||
1F910..1F918;N # So [9] ZIPPER-MOUTH FACE..SIGN OF THE HORNS
|
||||
1F980..1F984;N # So [5] CRAB..UNICORN FACE
|
||||
1F9C0;N # So CHEESE WEDGE
|
||||
20000..2A6D6;W # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
|
||||
2A6D7..2A6FF;W # Cn [41] <reserved-2A6D7>..<reserved-2A6FF>
|
||||
2A700..2B734;W # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
|
||||
2B735..2B73F;W # Cn [11] <reserved-2B735>..<reserved-2B73F>
|
||||
2B740..2B81D;W # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
|
||||
2B81E..2F7FF;W # Cn [16354] <reserved-2B81E>..<reserved-2F7FF>
|
||||
2B81E..2B81F;W # Cn [2] <reserved-2B81E>..<reserved-2B81F>
|
||||
2B820..2CEA1;W # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
|
||||
2CEA2..2F7FF;W # Cn [10590] <reserved-2CEA2>..<reserved-2F7FF>
|
||||
2F800..2FA1D;W # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
|
||||
2FA1E..2FFFD;W # Cn [1504] <reserved-2FA1E>..<reserved-2FFFD>
|
||||
30000..3FFFD;W # Cn [65534] <reserved-30000>..<reserved-3FFFD>
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
# GraphemeBreakProperty-7.0.0.txt
|
||||
# Date: 2014-02-19, 15:51:21 GMT [MD]
|
||||
# GraphemeBreakProperty-8.0.0.txt
|
||||
# Date: 2015-02-13, 13:47:14 GMT [MD]
|
||||
#
|
||||
# Unicode Character Database
|
||||
# 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
|
||||
# For documentation, see http://www.unicode.org/reports/tr44/
|
||||
|
||||
|
|
@ -89,7 +89,7 @@ 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
|
||||
08E4..0902 ; Extend # Mn [31] ARABIC CURLY FATHA..DEVANAGARI SIGN ANUSVARA
|
||||
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
|
||||
|
|
@ -250,7 +250,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
|
|||
A66F ; Extend # Mn COMBINING CYRILLIC VZMET
|
||||
A670..A672 ; Extend # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN
|
||||
A674..A67D ; Extend # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK
|
||||
A69F ; Extend # Mn COMBINING CYRILLIC LETTER IOTIFIED E
|
||||
A69E..A69F ; Extend # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E
|
||||
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
|
||||
|
|
@ -283,7 +283,7 @@ ABE8 ; Extend # Mn MEETEI MAYEK VOWEL SIGN UNAP
|
|||
ABED ; Extend # Mn MEETEI MAYEK APUN IYEK
|
||||
FB1E ; Extend # Mn HEBREW POINT JUDEO-SPANISH VARIKA
|
||||
FE00..FE0F ; Extend # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
|
||||
FE20..FE2D ; Extend # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON BELOW
|
||||
FE20..FE2F ; Extend # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF
|
||||
FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
|
||||
101FD ; Extend # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE
|
||||
102E0 ; Extend # Mn COPTIC EPACT THOUSANDS MARK
|
||||
|
|
@ -305,12 +305,13 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
|||
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
|
||||
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
|
||||
112DF ; Extend # Mn KHUDAWADI SIGN ANUSVARA
|
||||
112E3..112EA ; Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
|
||||
11301 ; Extend # Mn GRANTHA SIGN CANDRABINDU
|
||||
11300..11301 ; Extend # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
|
||||
1133C ; Extend # Mn GRANTHA SIGN NUKTA
|
||||
1133E ; Extend # Mc GRANTHA VOWEL SIGN AA
|
||||
11340 ; Extend # Mn GRANTHA VOWEL SIGN II
|
||||
|
|
@ -327,6 +328,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
|||
115B2..115B5 ; Extend # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR
|
||||
115BC..115BD ; Extend # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA
|
||||
115BF..115C0 ; Extend # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA
|
||||
115DC..115DD ; Extend # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU
|
||||
11633..1163A ; Extend # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI
|
||||
1163D ; Extend # Mn MODI SIGN ANUSVARA
|
||||
1163F..11640 ; Extend # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA
|
||||
|
|
@ -334,6 +336,9 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
|||
116AD ; Extend # Mn TAKRI VOWEL SIGN AA
|
||||
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
|
||||
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
|
||||
16F8F..16F92 ; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
|
||||
|
|
@ -345,10 +350,16 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
|
|||
1D185..1D18B ; Extend # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
|
||||
1D1AA..1D1AD ; Extend # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
|
||||
1D242..1D244 ; Extend # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
|
||||
1DA00..1DA36 ; Extend # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN
|
||||
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
|
||||
1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
|
||||
E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
|
||||
|
||||
# Total code points: 1461
|
||||
# Total code points: 1610
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -412,8 +423,6 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
|
|||
1929..192B ; SpacingMark # Mc [3] LIMBU SUBJOINED LETTER YA..LIMBU SUBJOINED LETTER WA
|
||||
1930..1931 ; SpacingMark # Mc [2] LIMBU SMALL LETTER KA..LIMBU SMALL LETTER NGA
|
||||
1933..1938 ; SpacingMark # Mc [6] LIMBU SMALL LETTER TA..LIMBU SMALL LETTER LA
|
||||
19B5..19B7 ; SpacingMark # Mc [3] NEW TAI LUE VOWEL SIGN E..NEW TAI LUE VOWEL SIGN O
|
||||
19BA ; SpacingMark # Mc NEW TAI LUE VOWEL SIGN AY
|
||||
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
|
||||
|
|
@ -487,11 +496,13 @@ 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
|
||||
16F51..16F7E ; SpacingMark # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
|
||||
1D166 ; SpacingMark # Mc MUSICAL SYMBOL COMBINING SPRECHGESANG STEM
|
||||
1D16D ; SpacingMark # Mc MUSICAL SYMBOL COMBINING AUGMENTATION DOT
|
||||
|
||||
# Total code points: 331
|
||||
# Total code points: 330
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
|
|||
|
|
@ -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>
|
||||
|
|
@ -1,10 +1,10 @@
|
|||
# NormalizationCorrections-7.0.0.txt
|
||||
# Date: 2013-12-17, 00:00:00 GMT [KW, LI]
|
||||
# NormalizationCorrections-8.0.0.txt
|
||||
# Date: 2015-03-07, 01:30:00 GMT [KW, LI]
|
||||
#
|
||||
# This file is a normative contributory data file in the
|
||||
# Unicode Character Database.
|
||||
#
|
||||
# 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 normalization stability policy of the Unicode Consortium
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
# PropList-7.0.0.txt
|
||||
# Date: 2014-02-19, 15:51:26 GMT [MD]
|
||||
# PropList-8.0.0.txt
|
||||
# Date: 2015-05-16, 17:50:38 GMT [MD]
|
||||
#
|
||||
# Unicode Character Database
|
||||
# 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
|
||||
# For documentation, see http://www.unicode.org/reports/tr44/
|
||||
|
||||
|
|
@ -189,18 +189,22 @@ FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA
|
|||
11141..11143 ; Terminal_Punctuation # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK
|
||||
111C5..111C6 ; Terminal_Punctuation # Po [2] SHARADA DANDA..SHARADA DOUBLE DANDA
|
||||
111CD ; Terminal_Punctuation # Po SHARADA SUTRA MARK
|
||||
111DE..111DF ; Terminal_Punctuation # Po [2] SHARADA SECTION MARK-1..SHARADA SECTION MARK-2
|
||||
11238..1123C ; Terminal_Punctuation # Po [5] KHOJKI DANDA..KHOJKI DOUBLE SECTION MARK
|
||||
112A9 ; Terminal_Punctuation # Po MULTANI SECTION MARK
|
||||
115C2..115C5 ; Terminal_Punctuation # Po [4] SIDDHAM DANDA..SIDDHAM SEPARATOR BAR
|
||||
115C9 ; Terminal_Punctuation # Po SIDDHAM END OF TEXT MARK
|
||||
115C9..115D7 ; Terminal_Punctuation # Po [15] SIDDHAM END OF TEXT MARK..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES
|
||||
11641..11642 ; Terminal_Punctuation # Po [2] MODI DANDA..MODI DOUBLE DANDA
|
||||
1173C..1173E ; Terminal_Punctuation # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI
|
||||
12470..12474 ; Terminal_Punctuation # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON
|
||||
16A6E..16A6F ; Terminal_Punctuation # Po [2] MRO DANDA..MRO DOUBLE DANDA
|
||||
16AF5 ; Terminal_Punctuation # Po BASSA VAH FULL STOP
|
||||
16B37..16B39 ; Terminal_Punctuation # Po [3] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN CIM CHEEM
|
||||
16B44 ; Terminal_Punctuation # Po PAHAWH HMONG SIGN XAUS
|
||||
1BC9F ; Terminal_Punctuation # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP
|
||||
1DA87..1DA8A ; Terminal_Punctuation # Po [4] SIGNWRITING COMMA..SIGNWRITING COLON
|
||||
|
||||
# Total code points: 214
|
||||
# Total code points: 238
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -425,7 +429,7 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
|
|||
081B..0823 ; Other_Alphabetic # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A
|
||||
0825..0827 ; Other_Alphabetic # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U
|
||||
0829..082C ; Other_Alphabetic # Mn [4] SAMARITAN VOWEL SIGN LONG I..SAMARITAN VOWEL SIGN SUKUN
|
||||
08E4..08E9 ; Other_Alphabetic # Mn [6] ARABIC CURLY FATHA..ARABIC CURLY KASRATAN
|
||||
08E3..08E9 ; Other_Alphabetic # Mn [7] ARABIC TURNED DAMMA BELOW..ARABIC CURLY KASRATAN
|
||||
08F0..0902 ; Other_Alphabetic # Mn [19] ARABIC OPEN FATHATAN..DEVANAGARI SIGN ANUSVARA
|
||||
0903 ; Other_Alphabetic # Mc DEVANAGARI SIGN VISARGA
|
||||
093A ; Other_Alphabetic # Mn DEVANAGARI VOWEL SIGN OE
|
||||
|
|
@ -560,8 +564,6 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
|
|||
1930..1931 ; Other_Alphabetic # Mc [2] LIMBU SMALL LETTER KA..LIMBU SMALL LETTER NGA
|
||||
1932 ; Other_Alphabetic # Mn LIMBU SMALL LETTER ANUSVARA
|
||||
1933..1938 ; Other_Alphabetic # Mc [6] LIMBU SMALL LETTER TA..LIMBU SMALL LETTER LA
|
||||
19B0..19C0 ; Other_Alphabetic # Mc [17] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE VOWEL SIGN IY
|
||||
19C8..19C9 ; Other_Alphabetic # Mc [2] NEW TAI LUE TONE MARK-1..NEW TAI LUE TONE MARK-2
|
||||
1A17..1A18 ; Other_Alphabetic # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U
|
||||
1A19..1A1A ; Other_Alphabetic # Mc [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O
|
||||
1A1B ; Other_Alphabetic # Mn BUGINESE VOWEL SIGN AE
|
||||
|
|
@ -605,7 +607,7 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
|
|||
24B6..24E9 ; Other_Alphabetic # So [52] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN SMALL LETTER Z
|
||||
2DE0..2DFF ; Other_Alphabetic # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS
|
||||
A674..A67B ; Other_Alphabetic # Mn [8] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC LETTER OMEGA
|
||||
A69F ; Other_Alphabetic # Mn COMBINING CYRILLIC LETTER IOTIFIED E
|
||||
A69E..A69F ; Other_Alphabetic # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E
|
||||
A823..A824 ; Other_Alphabetic # Mc [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIGN I
|
||||
A825..A826 ; Other_Alphabetic # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E
|
||||
A827 ; Other_Alphabetic # Mc SYLOTI NAGRI VOWEL SIGN OO
|
||||
|
|
@ -672,7 +674,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
|
|||
112DF ; Other_Alphabetic # Mn KHUDAWADI SIGN ANUSVARA
|
||||
112E0..112E2 ; Other_Alphabetic # Mc [3] KHUDAWADI VOWEL SIGN AA..KHUDAWADI VOWEL SIGN II
|
||||
112E3..112E8 ; Other_Alphabetic # Mn [6] KHUDAWADI VOWEL SIGN U..KHUDAWADI VOWEL SIGN AU
|
||||
11301 ; Other_Alphabetic # Mn GRANTHA SIGN CANDRABINDU
|
||||
11300..11301 ; Other_Alphabetic # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
|
||||
11302..11303 ; Other_Alphabetic # Mc [2] GRANTHA SIGN ANUSVARA..GRANTHA SIGN VISARGA
|
||||
1133E..1133F ; Other_Alphabetic # Mc [2] GRANTHA VOWEL SIGN AA..GRANTHA VOWEL SIGN I
|
||||
11340 ; Other_Alphabetic # Mn GRANTHA VOWEL SIGN II
|
||||
|
|
@ -693,6 +695,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
|
|||
115B8..115BB ; Other_Alphabetic # Mc [4] SIDDHAM VOWEL SIGN E..SIDDHAM VOWEL SIGN AU
|
||||
115BC..115BD ; Other_Alphabetic # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA
|
||||
115BE ; Other_Alphabetic # Mc SIDDHAM SIGN VISARGA
|
||||
115DC..115DD ; Other_Alphabetic # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU
|
||||
11630..11632 ; Other_Alphabetic # Mc [3] MODI VOWEL SIGN AA..MODI VOWEL SIGN II
|
||||
11633..1163A ; Other_Alphabetic # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI
|
||||
1163B..1163C ; Other_Alphabetic # Mc [2] MODI VOWEL SIGN O..MODI VOWEL SIGN AU
|
||||
|
|
@ -704,6 +707,11 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
|
|||
116AD ; Other_Alphabetic # Mn TAKRI VOWEL SIGN AA
|
||||
116AE..116AF ; Other_Alphabetic # Mc [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II
|
||||
116B0..116B5 ; Other_Alphabetic # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU
|
||||
1171D..1171F ; Other_Alphabetic # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA
|
||||
11720..11721 ; Other_Alphabetic # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA
|
||||
11722..11725 ; Other_Alphabetic # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
|
||||
11726 ; Other_Alphabetic # Mc AHOM VOWEL SIGN E
|
||||
11727..1172A ; Other_Alphabetic # Mn [4] AHOM VOWEL SIGN AW..AHOM VOWEL SIGN AM
|
||||
16B30..16B36 ; Other_Alphabetic # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
|
||||
16F51..16F7E ; Other_Alphabetic # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
|
||||
1BC9E ; Other_Alphabetic # Mn DUPLOYAN DOUBLE MARK
|
||||
|
|
@ -720,15 +728,16 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
|
|||
3021..3029 ; Ideographic # Nl [9] HANGZHOU NUMERAL ONE..HANGZHOU NUMERAL NINE
|
||||
3038..303A ; Ideographic # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY
|
||||
3400..4DB5 ; Ideographic # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
|
||||
4E00..9FCC ; Ideographic # Lo [20941] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCC
|
||||
4E00..9FD5 ; Ideographic # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
|
||||
F900..FA6D ; Ideographic # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D
|
||||
FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9
|
||||
20000..2A6D6 ; Ideographic # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
|
||||
2A700..2B734 ; Ideographic # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
|
||||
2B740..2B81D ; Ideographic # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
|
||||
2B820..2CEA1 ; Ideographic # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
|
||||
2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
|
||||
|
||||
# Total code points: 75633
|
||||
# Total code points: 81404
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -773,7 +782,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
|
|||
07EB..07F3 ; Diacritic # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE
|
||||
07F4..07F5 ; Diacritic # Lm [2] NKO HIGH TONE APOSTROPHE..NKO LOW TONE APOSTROPHE
|
||||
0818..0819 ; Diacritic # Mn [2] SAMARITAN MARK OCCLUSION..SAMARITAN MARK DAGESH
|
||||
08E4..08FE ; Diacritic # Mn [27] ARABIC CURLY FATHA..ARABIC DAMMA WITH DOT
|
||||
08E3..08FE ; Diacritic # Mn [28] ARABIC TURNED DAMMA BELOW..ARABIC DAMMA WITH DOT
|
||||
093C ; Diacritic # Mn DEVANAGARI SIGN NUKTA
|
||||
094D ; Diacritic # Mn DEVANAGARI SIGN VIRAMA
|
||||
0951..0954 ; Diacritic # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT
|
||||
|
|
@ -877,7 +886,7 @@ AB5C..AB5F ; Diacritic # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER
|
|||
ABEC ; Diacritic # Mc MEETEI MAYEK LUM IYEK
|
||||
ABED ; Diacritic # Mn MEETEI MAYEK APUN IYEK
|
||||
FB1E ; Diacritic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
|
||||
FE20..FE2D ; Diacritic # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON BELOW
|
||||
FE20..FE2F ; Diacritic # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF
|
||||
FF3E ; Diacritic # Sk FULLWIDTH CIRCUMFLEX ACCENT
|
||||
FF40 ; Diacritic # Sk FULLWIDTH GRAVE ACCENT
|
||||
FF70 ; Diacritic # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
|
||||
|
|
@ -889,6 +898,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON
|
|||
11133..11134 ; Diacritic # Mn [2] CHAKMA VIRAMA..CHAKMA MAAYYAA
|
||||
11173 ; Diacritic # Mn MAHAJANI SIGN NUKTA
|
||||
111C0 ; Diacritic # Mc SHARADA SIGN VIRAMA
|
||||
111CA..111CC ; Diacritic # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK
|
||||
11235 ; Diacritic # Mc KHOJKI SIGN VIRAMA
|
||||
11236 ; Diacritic # Mn KHOJKI SIGN NUKTA
|
||||
112E9..112EA ; Diacritic # Mn [2] KHUDAWADI SIGN NUKTA..KHUDAWADI SIGN VIRAMA
|
||||
|
|
@ -901,6 +911,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON
|
|||
1163F ; Diacritic # Mn MODI SIGN VIRAMA
|
||||
116B6 ; Diacritic # Mc TAKRI SIGN VIRAMA
|
||||
116B7 ; Diacritic # Mn TAKRI SIGN NUKTA
|
||||
1172B ; Diacritic # Mn AHOM SIGN KILLER
|
||||
16AF0..16AF4 ; Diacritic # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
|
||||
16F8F..16F92 ; Diacritic # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
|
||||
16F93..16F9F ; Diacritic # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8
|
||||
|
|
@ -911,7 +922,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON
|
|||
1D1AA..1D1AD ; Diacritic # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
|
||||
1E8D0..1E8D6 ; Diacritic # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
|
||||
|
||||
# Total code points: 766
|
||||
# Total code points: 773
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -1053,7 +1064,7 @@ FF9E..FF9F ; Other_Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND
|
|||
# ================================================
|
||||
|
||||
3400..4DB5 ; Unified_Ideograph # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
|
||||
4E00..9FCC ; Unified_Ideograph # Lo [20941] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCC
|
||||
4E00..9FD5 ; Unified_Ideograph # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
|
||||
FA0E..FA0F ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA0E..CJK COMPATIBILITY IDEOGRAPH-FA0F
|
||||
FA11 ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA11
|
||||
FA13..FA14 ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA13..CJK COMPATIBILITY IDEOGRAPH-FA14
|
||||
|
|
@ -1064,8 +1075,9 @@ FA27..FA29 ; Unified_Ideograph # Lo [3] CJK COMPATIBILITY IDEOGRAPH-FA27..C
|
|||
20000..2A6D6 ; Unified_Ideograph # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
|
||||
2A700..2B734 ; Unified_Ideograph # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
|
||||
2B740..2B81D ; Unified_Ideograph # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
|
||||
2B820..2CEA1 ; Unified_Ideograph # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
|
||||
|
||||
# Total code points: 74617
|
||||
# Total code points: 80388
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -1094,9 +1106,9 @@ E01F0..E0FFF ; Other_Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>.
|
|||
2329 ; Deprecated # Ps LEFT-POINTING ANGLE BRACKET
|
||||
232A ; Deprecated # Pe RIGHT-POINTING ANGLE BRACKET
|
||||
E0001 ; Deprecated # Cf LANGUAGE TAG
|
||||
E0020..E007F ; Deprecated # Cf [96] TAG SPACE..CANCEL TAG
|
||||
E007F ; Deprecated # Cf CANCEL TAG
|
||||
|
||||
# Total code points: 111
|
||||
# Total code points: 16
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -1138,11 +1150,13 @@ E0020..E007F ; Deprecated # Cf [96] TAG SPACE..CANCEL TAG
|
|||
|
||||
0E40..0E44 ; Logical_Order_Exception # Lo [5] THAI CHARACTER SARA E..THAI CHARACTER SARA AI MAIMALAI
|
||||
0EC0..0EC4 ; Logical_Order_Exception # Lo [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI
|
||||
19B5..19B7 ; Logical_Order_Exception # Lo [3] NEW TAI LUE VOWEL SIGN E..NEW TAI LUE VOWEL SIGN O
|
||||
19BA ; Logical_Order_Exception # Lo NEW TAI LUE VOWEL SIGN AY
|
||||
AAB5..AAB6 ; Logical_Order_Exception # Lo [2] TAI VIET VOWEL E..TAI VIET VOWEL O
|
||||
AAB9 ; Logical_Order_Exception # Lo TAI VIET VOWEL UEA
|
||||
AABB..AABC ; Logical_Order_Exception # Lo [2] TAI VIET VOWEL AUE..TAI VIET VOWEL AY
|
||||
|
||||
# Total code points: 15
|
||||
# Total code points: 19
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -1213,18 +1227,22 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP
|
|||
11141..11143 ; STerm # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK
|
||||
111C5..111C6 ; STerm # Po [2] SHARADA DANDA..SHARADA DOUBLE DANDA
|
||||
111CD ; STerm # Po SHARADA SUTRA MARK
|
||||
111DE..111DF ; STerm # Po [2] SHARADA SECTION MARK-1..SHARADA SECTION MARK-2
|
||||
11238..11239 ; STerm # Po [2] KHOJKI DANDA..KHOJKI DOUBLE DANDA
|
||||
1123B..1123C ; STerm # Po [2] KHOJKI SECTION MARK..KHOJKI DOUBLE SECTION MARK
|
||||
112A9 ; STerm # Po MULTANI SECTION MARK
|
||||
115C2..115C3 ; STerm # Po [2] SIDDHAM DANDA..SIDDHAM DOUBLE DANDA
|
||||
115C9 ; STerm # Po SIDDHAM END OF TEXT MARK
|
||||
115C9..115D7 ; STerm # Po [15] SIDDHAM END OF TEXT MARK..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES
|
||||
11641..11642 ; STerm # Po [2] MODI DANDA..MODI DOUBLE DANDA
|
||||
1173C..1173E ; STerm # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI
|
||||
16A6E..16A6F ; STerm # Po [2] MRO DANDA..MRO DOUBLE DANDA
|
||||
16AF5 ; STerm # Po BASSA VAH FULL STOP
|
||||
16B37..16B38 ; STerm # Po [2] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN VOS TSHAB CEEB
|
||||
16B44 ; STerm # Po PAHAWH HMONG SIGN XAUS
|
||||
1BC9F ; STerm # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP
|
||||
1DA88 ; STerm # Po SIGNWRITING FULL STOP
|
||||
|
||||
# Total code points: 99
|
||||
# Total code points: 120
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -1432,7 +1450,9 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S
|
|||
2BBD..2BC8 ; Pattern_Syntax # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
|
||||
2BC9 ; Pattern_Syntax # Cn <reserved-2BC9>
|
||||
2BCA..2BD1 ; Pattern_Syntax # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN
|
||||
2BD2..2BFF ; Pattern_Syntax # Cn [46] <reserved-2BD2>..<reserved-2BFF>
|
||||
2BD2..2BEB ; Pattern_Syntax # Cn [26] <reserved-2BD2>..<reserved-2BEB>
|
||||
2BEC..2BEF ; Pattern_Syntax # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS
|
||||
2BF0..2BFF ; Pattern_Syntax # Cn [16] <reserved-2BF0>..<reserved-2BFF>
|
||||
2E00..2E01 ; Pattern_Syntax # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER
|
||||
2E02 ; Pattern_Syntax # Pi LEFT SUBSTITUTION BRACKET
|
||||
2E03 ; Pattern_Syntax # Pf RIGHT SUBSTITUTION BRACKET
|
||||
|
|
|
|||
|
|
@ -1,10 +1,16 @@
|
|||
# Scripts-7.0.0.txt
|
||||
# Date: 2014-05-15, 00:11:35 GMT [MD]
|
||||
# Scripts-8.0.0.txt
|
||||
# Date: 2015-03-11, 22:29:42 GMT [MD]
|
||||
#
|
||||
# Unicode Character Database
|
||||
# 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
|
||||
# For documentation, see http://www.unicode.org/reports/tr44/
|
||||
# For more information, see:
|
||||
# UAX #24, Unicode Script Property: http://www.unicode.org/reports/tr24/
|
||||
# Especially the sections:
|
||||
# http://www.unicode.org/reports/tr24/#Assignment_Script_Values
|
||||
# http://www.unicode.org/reports/tr24/#Assignment_ScriptX_Values
|
||||
#
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -89,7 +95,6 @@
|
|||
061C ; Common # Cf ARABIC LETTER MARK
|
||||
061F ; Common # Po ARABIC QUESTION MARK
|
||||
0640 ; Common # Lm ARABIC TATWEEL
|
||||
0660..0669 ; Common # Nd [10] ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE
|
||||
06DD ; Common # Cf ARABIC END OF AYAH
|
||||
0964..0965 ; Common # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA
|
||||
0E3F ; Common # Sc THAI CURRENCY SYMBOL BAHT
|
||||
|
|
@ -148,7 +153,7 @@
|
|||
208A..208C ; Common # Sm [3] SUBSCRIPT PLUS SIGN..SUBSCRIPT EQUALS SIGN
|
||||
208D ; Common # Ps SUBSCRIPT LEFT PARENTHESIS
|
||||
208E ; Common # Pe SUBSCRIPT RIGHT PARENTHESIS
|
||||
20A0..20BD ; Common # Sc [30] EURO-CURRENCY SIGN..RUBLE SIGN
|
||||
20A0..20BE ; Common # Sc [31] EURO-CURRENCY SIGN..LARI SIGN
|
||||
2100..2101 ; Common # So [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT
|
||||
2102 ; Common # L& DOUBLE-STRUCK CAPITAL C
|
||||
2103..2106 ; Common # So [4] DEGREE CELSIUS..CADA UNA
|
||||
|
|
@ -182,6 +187,7 @@
|
|||
214F ; Common # So SYMBOL FOR SAMARITAN SOURCE
|
||||
2150..215F ; Common # No [16] VULGAR FRACTION ONE SEVENTH..FRACTION NUMERATOR ONE
|
||||
2189 ; Common # No VULGAR FRACTION ZERO THIRDS
|
||||
218A..218B ; Common # So [2] TURNED DIGIT TWO..TURNED DIGIT THREE
|
||||
2190..2194 ; Common # Sm [5] LEFTWARDS ARROW..LEFT RIGHT ARROW
|
||||
2195..2199 ; Common # So [5] UP DOWN ARROW..SOUTH WEST ARROW
|
||||
219A..219B ; Common # Sm [2] LEFTWARDS ARROW WITH STROKE..RIGHTWARDS ARROW WITH STROKE
|
||||
|
|
@ -304,6 +310,7 @@
|
|||
2B98..2BB9 ; Common # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX
|
||||
2BBD..2BC8 ; Common # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
|
||||
2BCA..2BD1 ; Common # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN
|
||||
2BEC..2BEF ; Common # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS
|
||||
2E00..2E01 ; Common # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER
|
||||
2E02 ; Common # Pi LEFT SUBSTITUTION BRACKET
|
||||
2E03 ; Common # Pf RIGHT SUBSTITUTION BRACKET
|
||||
|
|
@ -512,7 +519,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
|
|||
1D173..1D17A ; Common # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
|
||||
1D183..1D184 ; Common # So [2] MUSICAL SYMBOL ARPEGGIATO UP..MUSICAL SYMBOL ARPEGGIATO DOWN
|
||||
1D18C..1D1A9 ; Common # So [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH
|
||||
1D1AE..1D1DD ; Common # So [48] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL PES SUBPUNCTIS
|
||||
1D1AE..1D1E8 ; Common # So [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN
|
||||
1D300..1D356 ; Common # So [87] MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING
|
||||
1D360..1D371 ; Common # No [18] COUNTING ROD UNIT DIGIT ONE..COUNTING ROD TENS DIGIT NINE
|
||||
1D400..1D454 ; Common # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G
|
||||
|
|
@ -571,16 +578,11 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
|
|||
1F210..1F23A ; Common # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6
|
||||
1F240..1F248 ; Common # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557
|
||||
1F250..1F251 ; Common # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT
|
||||
1F300..1F32C ; Common # So [45] CYCLONE..WIND BLOWING FACE
|
||||
1F330..1F37D ; Common # So [78] CHESTNUT..FORK AND KNIFE WITH PLATE
|
||||
1F380..1F3CE ; Common # So [79] RIBBON..RACING CAR
|
||||
1F3D4..1F3F7 ; Common # So [36] SNOW CAPPED MOUNTAIN..LABEL
|
||||
1F400..1F4FE ; Common # So [255] RAT..PORTABLE STEREO
|
||||
1F500..1F54A ; Common # So [75] TWISTED RIGHTWARDS ARROWS..DOVE OF PEACE
|
||||
1F550..1F579 ; Common # So [42] CLOCK FACE ONE OCLOCK..JOYSTICK
|
||||
1F300..1F3FA ; Common # So [251] CYCLONE..AMPHORA
|
||||
1F3FB..1F3FF ; Common # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
|
||||
1F400..1F579 ; Common # So [378] RAT..JOYSTICK
|
||||
1F57B..1F5A3 ; Common # So [41] LEFT HAND TELEPHONE RECEIVER..BLACK DOWN POINTING BACKHAND INDEX
|
||||
1F5A5..1F642 ; Common # So [158] DESKTOP COMPUTER..SLIGHTLY SMILING FACE
|
||||
1F645..1F6CF ; Common # So [139] FACE WITH NO GOOD GESTURE..BED
|
||||
1F5A5..1F6D0 ; Common # So [300] DESKTOP COMPUTER..PLACE OF WORSHIP
|
||||
1F6E0..1F6EC ; Common # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING
|
||||
1F6F0..1F6F3 ; Common # So [4] SATELLITE..PASSENGER SHIP
|
||||
1F700..1F773 ; Common # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
|
||||
|
|
@ -590,10 +592,13 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
|
|||
1F850..1F859 ; Common # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW
|
||||
1F860..1F887 ; Common # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW
|
||||
1F890..1F8AD ; Common # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS
|
||||
1F910..1F918 ; Common # So [9] ZIPPER-MOUTH FACE..SIGN OF THE HORNS
|
||||
1F980..1F984 ; Common # So [5] CRAB..UNICORN FACE
|
||||
1F9C0 ; Common # So CHEESE WEDGE
|
||||
E0001 ; Common # Cf LANGUAGE TAG
|
||||
E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
|
||||
|
||||
# Total code points: 7129
|
||||
# Total code points: 7179
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -635,20 +640,21 @@ A722..A76F ; Latin # L& [78] LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF..LATIN
|
|||
A770 ; Latin # Lm MODIFIER LETTER US
|
||||
A771..A787 ; Latin # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T
|
||||
A78B..A78E ; Latin # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
|
||||
A78F ; Latin # Lo LATIN LETTER SINOLOGICAL DOT
|
||||
A790..A7AD ; Latin # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT
|
||||
A7B0..A7B1 ; Latin # L& [2] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER TURNED T
|
||||
A7B0..A7B7 ; Latin # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA
|
||||
A7F7 ; Latin # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I
|
||||
A7F8..A7F9 ; Latin # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
|
||||
A7FA ; Latin # L& LATIN LETTER SMALL CAPITAL TURNED M
|
||||
A7FB..A7FF ; Latin # Lo [5] LATIN EPIGRAPHIC LETTER REVERSED F..LATIN EPIGRAPHIC LETTER ARCHAIC M
|
||||
AB30..AB5A ; Latin # L& [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG
|
||||
AB5C..AB5F ; Latin # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK
|
||||
AB64 ; Latin # L& LATIN SMALL LETTER INVERTED ALPHA
|
||||
AB60..AB64 ; Latin # L& [5] LATIN SMALL LETTER SAKHA YAT..LATIN SMALL LETTER INVERTED ALPHA
|
||||
FB00..FB06 ; Latin # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST
|
||||
FF21..FF3A ; Latin # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z
|
||||
FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z
|
||||
|
||||
# Total code points: 1338
|
||||
# Total code points: 1349
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -731,9 +737,10 @@ A67E ; Cyrillic # Po CYRILLIC KAVYKA
|
|||
A67F ; Cyrillic # Lm CYRILLIC PAYEROK
|
||||
A680..A69B ; Cyrillic # L& [28] CYRILLIC CAPITAL LETTER DWE..CYRILLIC SMALL LETTER CROSSED O
|
||||
A69C..A69D ; Cyrillic # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN
|
||||
A69F ; Cyrillic # Mn COMBINING CYRILLIC LETTER IOTIFIED E
|
||||
A69E..A69F ; Cyrillic # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E
|
||||
FE2E..FE2F ; Cyrillic # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF
|
||||
|
||||
# Total code points: 431
|
||||
# Total code points: 434
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -788,6 +795,7 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU
|
|||
0620..063F ; Arabic # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE
|
||||
0641..064A ; Arabic # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH
|
||||
0656..065F ; Arabic # Mn [10] ARABIC SUBSCRIPT ALEF..ARABIC WAVY HAMZA BELOW
|
||||
0660..0669 ; Arabic # Nd [10] ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE
|
||||
066A..066D ; Arabic # Po [4] ARABIC PERCENT SIGN..ARABIC FIVE POINTED STAR
|
||||
066E..066F ; Arabic # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF
|
||||
0671..06D3 ; Arabic # Lo [99] ARABIC LETTER ALEF WASLA..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE
|
||||
|
|
@ -806,8 +814,8 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU
|
|||
06FD..06FE ; Arabic # So [2] ARABIC SIGN SINDHI AMPERSAND..ARABIC SIGN SINDHI POSTPOSITION MEN
|
||||
06FF ; Arabic # Lo ARABIC LETTER HEH WITH INVERTED V
|
||||
0750..077F ; Arabic # Lo [48] ARABIC LETTER BEH WITH THREE DOTS HORIZONTALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS ABOVE
|
||||
08A0..08B2 ; Arabic # Lo [19] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE
|
||||
08E4..08FF ; Arabic # Mn [28] ARABIC CURLY FATHA..ARABIC MARK SIDEWAYS NOON GHUNNA
|
||||
08A0..08B4 ; Arabic # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
|
||||
08E3..08FF ; Arabic # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA
|
||||
FB50..FBB1 ; Arabic # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM
|
||||
FBB2..FBC1 ; Arabic # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW
|
||||
FBD3..FD3D ; Arabic # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM
|
||||
|
|
@ -854,7 +862,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
|
|||
1EEAB..1EEBB ; Arabic # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
|
||||
1EEF0..1EEF1 ; Arabic # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL
|
||||
|
||||
# Total code points: 1244
|
||||
# Total code points: 1257
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -902,8 +910,10 @@ A8E0..A8F1 ; Devanagari # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING
|
|||
A8F2..A8F7 ; Devanagari # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA
|
||||
A8F8..A8FA ; Devanagari # Po [3] DEVANAGARI SIGN PUSHPIKA..DEVANAGARI CARET
|
||||
A8FB ; Devanagari # Lo DEVANAGARI HEADSTROKE
|
||||
A8FC ; Devanagari # Po DEVANAGARI SIGN SIDDHAM
|
||||
A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
|
||||
|
||||
# Total code points: 152
|
||||
# Total code points: 154
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -987,8 +997,9 @@ A8FB ; Devanagari # Lo DEVANAGARI HEADSTROKE
|
|||
0AE6..0AEF ; Gujarati # Nd [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE
|
||||
0AF0 ; Gujarati # Po GUJARATI ABBREVIATION SIGN
|
||||
0AF1 ; Gujarati # Sc GUJARATI RUPEE SIGN
|
||||
0AF9 ; Gujarati # Lo GUJARATI LETTER ZHA
|
||||
|
||||
# Total code points: 84
|
||||
# Total code points: 85
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -1064,14 +1075,14 @@ A8FB ; Devanagari # Lo DEVANAGARI HEADSTROKE
|
|||
0C46..0C48 ; Telugu # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI
|
||||
0C4A..0C4D ; Telugu # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA
|
||||
0C55..0C56 ; Telugu # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK
|
||||
0C58..0C59 ; Telugu # Lo [2] TELUGU LETTER TSA..TELUGU LETTER DZA
|
||||
0C58..0C5A ; Telugu # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA
|
||||
0C60..0C61 ; Telugu # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL
|
||||
0C62..0C63 ; Telugu # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL
|
||||
0C66..0C6F ; Telugu # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE
|
||||
0C78..0C7E ; Telugu # No [7] TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR..TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR
|
||||
0C7F ; Telugu # So TELUGU SIGN TUUMU
|
||||
|
||||
# Total code points: 95
|
||||
# Total code points: 96
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -1115,14 +1126,14 @@ A8FB ; Devanagari # Lo DEVANAGARI HEADSTROKE
|
|||
0D4D ; Malayalam # Mn MALAYALAM SIGN VIRAMA
|
||||
0D4E ; Malayalam # Lo MALAYALAM LETTER DOT REPH
|
||||
0D57 ; Malayalam # Mc MALAYALAM AU LENGTH MARK
|
||||
0D60..0D61 ; Malayalam # Lo [2] MALAYALAM LETTER VOCALIC RR..MALAYALAM LETTER VOCALIC LL
|
||||
0D5F..0D61 ; Malayalam # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL
|
||||
0D62..0D63 ; Malayalam # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL
|
||||
0D66..0D6F ; Malayalam # Nd [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE
|
||||
0D70..0D75 ; Malayalam # No [6] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE QUARTERS
|
||||
0D79 ; Malayalam # So MALAYALAM DATE MARK
|
||||
0D7A..0D7F ; Malayalam # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K
|
||||
|
||||
# Total code points: 99
|
||||
# Total code points: 100
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -1358,9 +1369,11 @@ AB28..AB2E ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE BBA..ETHIOPIC SYLLABLE BBO
|
|||
|
||||
# ================================================
|
||||
|
||||
13A0..13F4 ; Cherokee # Lo [85] CHEROKEE LETTER A..CHEROKEE LETTER YV
|
||||
13A0..13F5 ; Cherokee # L& [86] CHEROKEE LETTER A..CHEROKEE LETTER MV
|
||||
13F8..13FD ; Cherokee # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV
|
||||
AB70..ABBF ; Cherokee # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA
|
||||
|
||||
# Total code points: 85
|
||||
# Total code points: 172
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -1472,15 +1485,16 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
|
|||
3038..303A ; Han # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY
|
||||
303B ; Han # Lm VERTICAL IDEOGRAPHIC ITERATION MARK
|
||||
3400..4DB5 ; Han # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
|
||||
4E00..9FCC ; Han # Lo [20941] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCC
|
||||
4E00..9FD5 ; Han # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
|
||||
F900..FA6D ; Han # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D
|
||||
FA70..FAD9 ; Han # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9
|
||||
20000..2A6D6 ; Han # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
|
||||
2A700..2B734 ; Han # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
|
||||
2B740..2B81D ; Han # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
|
||||
2B820..2CEA1 ; Han # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
|
||||
2F800..2FA1D ; Han # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
|
||||
|
||||
# Total code points: 75963
|
||||
# Total code points: 81734
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -1680,9 +1694,7 @@ E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-2
|
|||
# ================================================
|
||||
|
||||
1980..19AB ; New_Tai_Lue # Lo [44] NEW TAI LUE LETTER HIGH QA..NEW TAI LUE LETTER LOW SUA
|
||||
19B0..19C0 ; New_Tai_Lue # Mc [17] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE VOWEL SIGN IY
|
||||
19C1..19C7 ; New_Tai_Lue # Lo [7] NEW TAI LUE LETTER FINAL V..NEW TAI LUE LETTER FINAL B
|
||||
19C8..19C9 ; New_Tai_Lue # Mc [2] NEW TAI LUE TONE MARK-1..NEW TAI LUE TONE MARK-2
|
||||
19B0..19C9 ; New_Tai_Lue # Lo [26] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2
|
||||
19D0..19D9 ; New_Tai_Lue # Nd [10] NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE
|
||||
19DA ; New_Tai_Lue # No NEW TAI LUE THAM DIGIT ONE
|
||||
19DE..19DF ; New_Tai_Lue # So [2] NEW TAI LUE SIGN LAE..NEW TAI LUE SIGN LAEV
|
||||
|
|
@ -1770,11 +1782,12 @@ A828..A82B ; Syloti_Nagri # So [4] SYLOTI NAGRI POETRY MARK-1..SYLOTI NAGRI
|
|||
|
||||
# ================================================
|
||||
|
||||
12000..12398 ; Cuneiform # Lo [921] CUNEIFORM SIGN A..CUNEIFORM SIGN UM TIMES ME
|
||||
12000..12399 ; Cuneiform # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
|
||||
12400..1246E ; Cuneiform # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
|
||||
12470..12474 ; Cuneiform # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON
|
||||
12480..12543 ; Cuneiform # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
|
||||
|
||||
# Total code points: 1037
|
||||
# Total code points: 1234
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -2151,9 +2164,12 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
|
|||
# ================================================
|
||||
|
||||
109A0..109B7 ; Meroitic_Cursive # Lo [24] MEROITIC CURSIVE LETTER A..MEROITIC CURSIVE LETTER DA
|
||||
109BC..109BD ; Meroitic_Cursive # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF
|
||||
109BE..109BF ; Meroitic_Cursive # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN
|
||||
109C0..109CF ; Meroitic_Cursive # No [16] MEROITIC CURSIVE NUMBER ONE..MEROITIC CURSIVE NUMBER SEVENTY
|
||||
109D2..109FF ; Meroitic_Cursive # No [46] MEROITIC CURSIVE NUMBER ONE HUNDRED..MEROITIC CURSIVE FRACTION TEN TWELFTHS
|
||||
|
||||
# Total code points: 26
|
||||
# Total code points: 90
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -2180,12 +2196,16 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
|
|||
111B6..111BE ; Sharada # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O
|
||||
111BF..111C0 ; Sharada # Mc [2] SHARADA VOWEL SIGN AU..SHARADA SIGN VIRAMA
|
||||
111C1..111C4 ; Sharada # Lo [4] SHARADA SIGN AVAGRAHA..SHARADA OM
|
||||
111C5..111C8 ; Sharada # Po [4] SHARADA DANDA..SHARADA SEPARATOR
|
||||
111C5..111C9 ; Sharada # Po [5] SHARADA DANDA..SHARADA SANDHI MARK
|
||||
111CA..111CC ; Sharada # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK
|
||||
111CD ; Sharada # Po SHARADA SUTRA MARK
|
||||
111D0..111D9 ; Sharada # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE
|
||||
111DA ; Sharada # Lo SHARADA EKAM
|
||||
111DB ; Sharada # Po SHARADA SIGN SIDDHAM
|
||||
111DC ; Sharada # Lo SHARADA HEADSTROKE
|
||||
111DD..111DF ; Sharada # Po [3] SHARADA CONTINUATION SIGN..SHARADA SECTION MARK-2
|
||||
|
||||
# Total code points: 85
|
||||
# Total code points: 94
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -2243,7 +2263,7 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
|
|||
|
||||
# ================================================
|
||||
|
||||
11301 ; Grantha # Mn GRANTHA SIGN CANDRABINDU
|
||||
11300..11301 ; Grantha # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
|
||||
11302..11303 ; Grantha # Mc [2] GRANTHA SIGN ANUSVARA..GRANTHA SIGN VISARGA
|
||||
11305..1130C ; Grantha # Lo [8] GRANTHA LETTER A..GRANTHA LETTER VOCALIC L
|
||||
1130F..11310 ; Grantha # Lo [2] GRANTHA LETTER EE..GRANTHA LETTER AI
|
||||
|
|
@ -2258,13 +2278,14 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
|
|||
11341..11344 ; Grantha # Mc [4] GRANTHA VOWEL SIGN U..GRANTHA VOWEL SIGN VOCALIC RR
|
||||
11347..11348 ; Grantha # Mc [2] GRANTHA VOWEL SIGN EE..GRANTHA VOWEL SIGN AI
|
||||
1134B..1134D ; Grantha # Mc [3] GRANTHA VOWEL SIGN OO..GRANTHA SIGN VIRAMA
|
||||
11350 ; Grantha # Lo GRANTHA OM
|
||||
11357 ; Grantha # Mc GRANTHA AU LENGTH MARK
|
||||
1135D..11361 ; Grantha # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL
|
||||
11362..11363 ; Grantha # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL
|
||||
11366..1136C ; Grantha # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX
|
||||
11370..11374 ; Grantha # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA
|
||||
|
||||
# Total code points: 83
|
||||
# Total code points: 85
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -2407,9 +2428,11 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
|
|||
115BC..115BD ; Siddham # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA
|
||||
115BE ; Siddham # Mc SIDDHAM SIGN VISARGA
|
||||
115BF..115C0 ; Siddham # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA
|
||||
115C1..115C9 ; Siddham # Po [9] SIDDHAM SIGN SIDDHAM..SIDDHAM END OF TEXT MARK
|
||||
115C1..115D7 ; Siddham # Po [23] SIDDHAM SIGN SIDDHAM..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES
|
||||
115D8..115DB ; Siddham # Lo [4] SIDDHAM LETTER THREE-CIRCLE ALTERNATE I..SIDDHAM LETTER ALTERNATE U
|
||||
115DC..115DD ; Siddham # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU
|
||||
|
||||
# Total code points: 72
|
||||
# Total code points: 92
|
||||
|
||||
# ================================================
|
||||
|
||||
|
|
@ -2448,4 +2471,69 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
|
|||
|
||||
# Total code points: 84
|
||||
|
||||
# ================================================
|
||||
|
||||
11700..11719 ; Ahom # Lo [26] AHOM LETTER KA..AHOM LETTER JHA
|
||||
1171D..1171F ; Ahom # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA
|
||||
11720..11721 ; Ahom # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA
|
||||
11722..11725 ; Ahom # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
|
||||
11726 ; Ahom # Mc AHOM VOWEL SIGN E
|
||||
11727..1172B ; Ahom # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER
|
||||
11730..11739 ; Ahom # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE
|
||||
1173A..1173B ; Ahom # No [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY
|
||||
1173C..1173E ; Ahom # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI
|
||||
1173F ; Ahom # So AHOM SYMBOL VI
|
||||
|
||||
# Total code points: 57
|
||||
|
||||
# ================================================
|
||||
|
||||
14400..14646 ; Anatolian_Hieroglyphs # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530
|
||||
|
||||
# Total code points: 583
|
||||
|
||||
# ================================================
|
||||
|
||||
108E0..108F2 ; Hatran # Lo [19] HATRAN LETTER ALEPH..HATRAN LETTER QOPH
|
||||
108F4..108F5 ; Hatran # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW
|
||||
108FB..108FF ; Hatran # No [5] HATRAN NUMBER ONE..HATRAN NUMBER ONE HUNDRED
|
||||
|
||||
# Total code points: 26
|
||||
|
||||
# ================================================
|
||||
|
||||
11280..11286 ; Multani # Lo [7] MULTANI LETTER A..MULTANI LETTER GA
|
||||
11288 ; Multani # Lo MULTANI LETTER GHA
|
||||
1128A..1128D ; Multani # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA
|
||||
1128F..1129D ; Multani # Lo [15] MULTANI LETTER NYA..MULTANI LETTER BA
|
||||
1129F..112A8 ; Multani # Lo [10] MULTANI LETTER BHA..MULTANI LETTER RHA
|
||||
112A9 ; Multani # Po MULTANI SECTION MARK
|
||||
|
||||
# Total code points: 38
|
||||
|
||||
# ================================================
|
||||
|
||||
10C80..10CB2 ; Old_Hungarian # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US
|
||||
10CC0..10CF2 ; Old_Hungarian # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US
|
||||
10CFA..10CFF ; Old_Hungarian # No [6] OLD HUNGARIAN NUMBER ONE..OLD HUNGARIAN NUMBER ONE THOUSAND
|
||||
|
||||
# Total code points: 108
|
||||
|
||||
# ================================================
|
||||
|
||||
1D800..1D9FF ; SignWriting # So [512] SIGNWRITING HAND-FIST INDEX..SIGNWRITING HEAD
|
||||
1DA00..1DA36 ; SignWriting # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN
|
||||
1DA37..1DA3A ; SignWriting # So [4] SIGNWRITING AIR BLOW SMALL ROTATIONS..SIGNWRITING BREATH EXHALE
|
||||
1DA3B..1DA6C ; SignWriting # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT
|
||||
1DA6D..1DA74 ; SignWriting # So [8] SIGNWRITING SHOULDER HIP SPINE..SIGNWRITING TORSO-FLOORPLANE TWISTING
|
||||
1DA75 ; SignWriting # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS
|
||||
1DA76..1DA83 ; SignWriting # So [14] SIGNWRITING LIMB COMBINATION..SIGNWRITING LOCATION DEPTH
|
||||
1DA84 ; SignWriting # Mn SIGNWRITING LOCATION HEAD NECK
|
||||
1DA85..1DA86 ; SignWriting # So [2] SIGNWRITING LOCATION TORSO..SIGNWRITING LOCATION LIMBS DIGITS
|
||||
1DA87..1DA8B ; SignWriting # Po [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS
|
||||
1DA9B..1DA9F ; SignWriting # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6
|
||||
1DAA1..1DAAF ; SignWriting # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16
|
||||
|
||||
# Total code points: 672
|
||||
|
||||
# EOF
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
# SpecialCasing-7.0.0.txt
|
||||
# Date: 2014-03-18, 07:18:02 GMT [MD]
|
||||
# SpecialCasing-8.0.0.txt
|
||||
# Date: 2014-12-16, 23:08:04 GMT [MD]
|
||||
#
|
||||
# Unicode Character Database
|
||||
# Copyright (c) 1991-2014 Unicode, Inc.
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load diff
|
|
@ -34,7 +34,9 @@
|
|||
"Bassa_Vah" "Mahajani" "Pahawh_Hmong" "Caucasian_Albanian" "Manichaean"
|
||||
"Palmyrene" "Duployan" "Mende_Kikakui" "Pau_Cin_Hau" "Elbasan" "Modi"
|
||||
"Psalter_Pahlavi" "Grantha" "Mro" "Siddham" "Khojki" "Nabataean" "Tirhuta"
|
||||
"Khudawadi" "Old_North_Arabian" "Warang_Citi" "Linear_A" "Old_Permic"))
|
||||
"Khudawadi" "Old_North_Arabian" "Warang_Citi" "Linear_A" "Old_Permic"
|
||||
"Ahom" "Anatolian_Hieroglyphs" "Hatran" "Multani" "Old_Hungarian"
|
||||
"SignWriting"))
|
||||
|
||||
(*line-break-classes*
|
||||
("XX" "AI" "AL" "B2" "BA" "BB" "BK" "CB" "CJ" "CL" "CM" "CP" "CR" "EX" "GL"
|
||||
|
|
|
|||
|
|
@ -1,5 +1,7 @@
|
|||
(in-package "SB-COLD")
|
||||
|
||||
(declaim (optimize debug))
|
||||
|
||||
;;; Common functions
|
||||
|
||||
(defvar *output-directory*
|
||||
|
|
@ -185,7 +187,7 @@ Length should be adjusted when the standard changes.")
|
|||
"Table of scripts. Used in the creation of misc entries.")
|
||||
|
||||
(defparameter *line-break-class-table*
|
||||
(with-input-txt-file (s "LineBreakProperty")
|
||||
(with-input-txt-file (s "LineBreak")
|
||||
(loop with hash = (make-hash-table)
|
||||
for line = (read-line s nil nil) while line
|
||||
unless (or (not (position #\# line)) (= 0 (position #\# line)))
|
||||
|
|
@ -707,7 +709,7 @@ Length should be adjusted when the standard changes.")
|
|||
(values code-points ret))))
|
||||
|
||||
(defparameter *collation-table*
|
||||
(with-input-txt-file (stream "Allkeys70")
|
||||
(with-input-txt-file (stream "Allkeys80")
|
||||
(loop with hash = (make-hash-table :test #'equal)
|
||||
for line = (read-line stream nil nil) while line
|
||||
unless (eql 0 (position #\# line))
|
||||
|
|
|
|||
Loading…
Reference in a new issue