1
1
# IdentifierType.txt
2
- # Date: 2019-11-05, 08:05:20 GMT
3
- # © 2019 Unicode®, Inc.
2
+ # Date: 2020-02-07, 22:02:47 GMT
3
+ # © 2020 Unicode®, Inc.
4
4
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
5
5
# For terms of use, see http://www.unicode.org/terms_of_use.html
6
6
#
15
15
# Field 1: set of Identifier_Type values (see Table 1 of http://www.unicode.org/reports/tr39)
16
16
#
17
17
# Any missing code points have the Identifier_Type value Not_Character
18
+ #
19
+ # For the purpose of regular expressions, the property Identifier_Type is defined as
20
+ # mapping each code point to a set of enumerated values.
21
+ # The short name of Identifier_Type is the same as the long name.
22
+ # The possible values are:
23
+ # Not_Character, Deprecated, Default_Ignorable, Not_NFKC, Not_XID,
24
+ # Exclusion, Obsolete, Technical, Uncommon_Use, Limited_Use, Inclusion, Recommended
25
+ # The short name of each value is the same as its long name.
26
+ # The default property value for all Unicode code points U+0000..U+10FFFF
27
+ # not mentioned in this data file is Not_Character.
28
+ # As usual, sets are unordered, with no duplicate values.
29
+
18
30
19
31
# Identifier_Type: Recommended
20
32
264
276
0CF1..0CF2 ; Recommended # 5.0 [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
265
277
0D00 ; Recommended # 10.0 MALAYALAM SIGN COMBINING ANUSVARA ABOVE
266
278
0D02..0D03 ; Recommended # 1.1 [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
267
- 0D04 ; Recommended # 13.0 MALAYALAM LETTER VEDIC ANUSVARA
268
279
0D05..0D0C ; Recommended # 1.1 [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L
269
280
0D0E..0D10 ; Recommended # 1.1 [3] MALAYALAM LETTER E..MALAYALAM LETTER AI
270
281
0D12..0D28 ; Recommended # 1.1 [23] MALAYALAM LETTER O..MALAYALAM LETTER NA
281
292
0D60..0D61 ; Recommended # 1.1 [2] MALAYALAM LETTER VOCALIC RR..MALAYALAM LETTER VOCALIC LL
282
293
0D66..0D6F ; Recommended # 1.1 [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE
283
294
0D7A..0D7F ; Recommended # 5.1 [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K
284
- 0D81 ; Recommended # 13.0 SINHALA SIGN CANDRABINDU
285
295
0D82..0D83 ; Recommended # 3.0 [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA
286
296
0D85..0D8E ; Recommended # 3.0 [10] SINHALA LETTER AYANNA..SINHALA LETTER IRUUYANNA
287
297
0D91..0D96 ; Recommended # 3.0 [6] SINHALA LETTER EYANNA..SINHALA LETTER AUYANNA
425
435
17D7 ; Recommended # 3.0 KHMER SIGN LEK TOO
426
436
17DC ; Recommended # 3.0 KHMER SIGN AVAKRAHASANYA
427
437
17E0..17E9 ; Recommended # 3.0 [10] KHMER DIGIT ZERO..KHMER DIGIT NINE
428
- 1ABF..1AC0 ; Recommended # 13.0 [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW
429
438
1C90..1CBA ; Recommended # 11.0 [43] GEORGIAN MTAVRULI CAPITAL LETTER AN..GEORGIAN MTAVRULI CAPITAL LETTER AIN
430
439
1CBD..1CBF ; Recommended # 11.0 [3] GEORGIAN MTAVRULI CAPITAL LETTER AEN..GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN
431
440
1E00..1E99 ; Recommended # 1.1 [154] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER Y WITH RING ABOVE
@@ -508,7 +517,6 @@ A7AE ; Recommended # 9.0 LATIN CAPITAL LETTER
508
517
A7B8..A7B9 ; Recommended # 11.0 [2] LATIN CAPITAL LETTER U WITH STROKE..LATIN SMALL LETTER U WITH STROKE
509
518
A7C2..A7C6 ; Recommended # 12.0 [5] LATIN CAPITAL LETTER ANGLICANA W..LATIN CAPITAL LETTER Z WITH PALATAL HOOK
510
519
A7C7..A7CA ; Recommended # 13.0 [4] LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY
511
- A7F5..A7F6 ; Recommended # 13.0 [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H
512
520
A9E7..A9FE ; Recommended # 7.0 [24] MYANMAR LETTER TAI LAING NYA..MYANMAR LETTER TAI LAING BHA
513
521
AA60..AA76 ; Recommended # 5.2 [23] MYANMAR LETTER KHAMTI GA..MYANMAR LOGOGRAM KHAMTI HM
514
522
AA7A..AA7B ; Recommended # 5.2 [2] MYANMAR LETTER AITON RA..MYANMAR SIGN PAO KAREN TONE
@@ -519,7 +527,6 @@ AB11..AB16 ; Recommended # 6.0 [6] ETHIOPIC SYLLABLE DZ
519
527
AB20..AB26 ; Recommended # 6.0 [7] ETHIOPIC SYLLABLE CCHHA..ETHIOPIC SYLLABLE CCHHO
520
528
AB28..AB2E ; Recommended # 6.0 [7] ETHIOPIC SYLLABLE BBA..ETHIOPIC SYLLABLE BBO
521
529
AB66..AB67 ; Recommended # 12.0 [2] LATIN SMALL LETTER DZ DIGRAPH WITH RETROFLEX HOOK..LATIN SMALL LETTER TS DIGRAPH WITH RETROFLEX HOOK
522
- AB68 ; Recommended # 13.0 LATIN SMALL LETTER TURNED R WITH MIDDLE TILDE
523
530
AC00..D7A3 ; Recommended # 2.0 [11172] HANGUL SYLLABLE GA..HANGUL SYLLABLE HIH
524
531
FA0E..FA0F ; Recommended # 1.1 [2] CJK COMPATIBILITY IDEOGRAPH-FA0E..CJK COMPATIBILITY IDEOGRAPH-FA0F
525
532
FA11 ; Recommended # 1.1 CJK COMPATIBILITY IDEOGRAPH-FA11
@@ -543,7 +550,7 @@ FA27..FA29 ; Recommended # 1.1 [3] CJK COMPATIBILITY ID
543
550
2CEB0..2EBE0 ; Recommended # 10.0 [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
544
551
30000..3134A ; Recommended # 13.0 [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
545
552
546
- # Total code points: 107823
553
+ # Total code points: 107816
547
554
548
555
# Identifier_Type: Inclusion
549
556
@@ -922,8 +929,10 @@ A8FC ; Uncommon_Use Obsolete Not_XID # 8.0 DEVANAGARI SIGN SIDD
922
929
0560 ; Technical # 11.0 ARMENIAN SMALL LETTER TURNED AYB
923
930
0588 ; Technical # 11.0 ARMENIAN SMALL LETTER YI WITH STROKE
924
931
0953..0954 ; Technical # 1.1 [2] DEVANAGARI GRAVE ACCENT..DEVANAGARI ACUTE ACCENT
932
+ 0D81 ; Technical # 13.0 SINHALA SIGN CANDRABINDU
925
933
0F18..0F19 ; Technical # 2.0 [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS
926
934
17CB..17D0 ; Technical # 3.0 [6] KHMER SIGN BANTOC..KHMER SIGN SAMYOK SANNYA
935
+ 1ABF..1AC0 ; Technical # 13.0 [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW
927
936
1D00..1D2B ; Technical # 4.0 [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL
928
937
1D2F ; Technical # 4.0 MODIFIER LETTER CAPITAL BARRED B
929
938
1D3B ; Technical # 4.0 MODIFIER LETTER CAPITAL REVERSED N
@@ -963,6 +972,7 @@ A78E ; Technical # 6.0 LATIN SMALL LETTER L
963
972
A7AF ; Technical # 11.0 LATIN LETTER SMALL CAPITAL Q
964
973
A7BA..A7BF ; Technical # 12.0 [6] LATIN CAPITAL LETTER GLOTTAL A..LATIN SMALL LETTER GLOTTAL U
965
974
A7FA ; Technical # 6.0 LATIN LETTER SMALL CAPITAL TURNED M
975
+ AB68 ; Technical # 13.0 LATIN SMALL LETTER TURNED R WITH MIDDLE TILDE
966
976
FE20..FE23 ; Technical # 1.1 [4] COMBINING LIGATURE LEFT HALF..COMBINING DOUBLE TILDE RIGHT HALF
967
977
FE24..FE26 ; Technical # 5.1 [3] COMBINING MACRON LEFT HALF..COMBINING CONJOINING MACRON
968
978
FE27..FE2D ; Technical # 7.0 [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CONJOINING MACRON BELOW
@@ -973,7 +983,7 @@ FE73 ; Technical # 3.2 ARABIC TAIL FRAGMENT
973
983
1D185..1D18B ; Technical # 3.1 [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
974
984
1D1AA..1D1AD ; Technical # 3.1 [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
975
985
976
- # Total code points: 447
986
+ # Total code points: 451
977
987
978
988
# Identifier_Type: Technical Exclusion
979
989
@@ -993,6 +1003,7 @@ FE73 ; Technical # 3.2 ARABIC TAIL FRAGMENT
993
1003
03F3 ; Technical Obsolete # 1.1 GREEK LETTER YOT
994
1004
0484..0486 ; Technical Obsolete # 1.1 [3] COMBINING CYRILLIC PALATALIZATION..COMBINING CYRILLIC PSILI PNEUMATA
995
1005
0487 ; Technical Obsolete # 5.1 COMBINING CYRILLIC POKRYTIE
1006
+ 0D04 ; Technical Obsolete # 13.0 MALAYALAM LETTER VEDIC ANUSVARA
996
1007
17D1 ; Technical Obsolete # 3.0 KHMER SIGN VIRIAM
997
1008
17DD ; Technical Obsolete # 4.0 KHMER SIGN ATTHACAN
998
1009
1DC0..1DC3 ; Technical Obsolete # 4.1 [4] COMBINING DOTTED GRAVE ACCENT..COMBINING SUSPENSION MARK
@@ -1004,7 +1015,7 @@ FE73 ; Technical # 3.2 ARABIC TAIL FRAGMENT
1004
1015
A722..A72F ; Technical Obsolete # 5.1 [14] LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF..LATIN SMALL LETTER CUATRILLO WITH COMMA
1005
1016
1D242..1D244 ; Technical Obsolete # 4.1 [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
1006
1017
1007
- # Total code points: 66
1018
+ # Total code points: 67
1008
1019
1009
1020
# Identifier_Type: Technical Obsolete Not_XID
1010
1021
@@ -1464,6 +1475,7 @@ A794..A79F ; Obsolete # 7.0 [12] LATIN SMALL LETTER C
1464
1475
A7A0..A7A9 ; Obsolete # 6.0 [10] LATIN CAPITAL LETTER G WITH OBLIQUE STROKE..LATIN SMALL LETTER S WITH OBLIQUE STROKE
1465
1476
A7AB..A7AD ; Obsolete # 7.0 [3] LATIN CAPITAL LETTER REVERSED OPEN E..LATIN CAPITAL LETTER L WITH BELT
1466
1477
A7B0..A7B1 ; Obsolete # 7.0 [2] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER TURNED T
1478
+ A7F5..A7F6 ; Obsolete # 13.0 [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H
1467
1479
A7F7 ; Obsolete # 7.0 LATIN EPIGRAPHIC LETTER SIDEWAYS I
1468
1480
A7FB..A7FF ; Obsolete # 5.1 [5] LATIN EPIGRAPHIC LETTER REVERSED F..LATIN EPIGRAPHIC LETTER ARCHAIC M
1469
1481
A8E0..A8F7 ; Obsolete # 5.2 [24] COMBINING DEVANAGARI DIGIT ZERO..DEVANAGARI SIGN CANDRABINDU AVAGRAHA
@@ -1482,7 +1494,7 @@ D7CB..D7FB ; Obsolete # 5.2 [49] HANGUL JONGSEONG NIE
1482
1494
1B000..1B001 ; Obsolete # 6.0 [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE
1483
1495
1B002..1B11E ; Obsolete # 10.0 [285] HENTAIGANA LETTER A-1..HENTAIGANA LETTER N-MU-MO-2
1484
1496
1485
- # Total code points: 1323
1497
+ # Total code points: 1325
1486
1498
1487
1499
# Identifier_Type: Obsolete Not_XID
1488
1500
0 commit comments