< prev index next >
test/jdk/java/lang/Character/PropList.txt
Print this page
@@ -1,11 +1,12 @@
-# PropList-8.0.0.txt
-# Date: 2015-05-16, 17:50:38 GMT [MD]
+# PropList-10.0.0.txt
+# Date: 2017-03-10, 08:25:30 GMT
+# © 2017 Unicode®, Inc.
+# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
+# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
-# Copyright (c) 1991-2015 Unicode, Inc.
-# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
# ================================================
0009..000D ; White_Space # Cc [5] <control-0009>..<control-000D>
@@ -190,23 +191,30 @@
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
+1144B..1144D ; Terminal_Punctuation # Po [3] NEWA DANDA..NEWA COMMA
+1145B ; Terminal_Punctuation # Po NEWA PLACEHOLDER MARK
115C2..115C5 ; Terminal_Punctuation # Po [4] SIDDHAM DANDA..SIDDHAM SEPARATOR BAR
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
+11A42..11A43 ; Terminal_Punctuation # Po [2] ZANABAZAR SQUARE MARK SHAD..ZANABAZAR SQUARE MARK DOUBLE SHAD
+11A9B..11A9C ; Terminal_Punctuation # Po [2] SOYOMBO MARK SHAD..SOYOMBO MARK DOUBLE SHAD
+11AA1..11AA2 ; Terminal_Punctuation # Po [2] SOYOMBO TERMINAL MARK-1..SOYOMBO TERMINAL MARK-2
+11C41..11C43 ; Terminal_Punctuation # Po [3] BHAIKSUKI DANDA..BHAIKSUKI WORD SEPARATOR
+11C71 ; Terminal_Punctuation # Po MARCHEN MARK SHAD
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: 238
+# Total code points: 252
# ================================================
005E ; Other_Math # Sk CIRCUMFLEX ACCENT
03D0..03D2 ; Other_Math # L& [3] GREEK BETA SYMBOL..GREEK UPSILON WITH HOOK SYMBOL
@@ -427,10 +435,11 @@
07A6..07B0 ; Other_Alphabetic # Mn [11] THAANA ABAFILI..THAANA SUKUN
0816..0817 ; Other_Alphabetic # Mn [2] SAMARITAN MARK IN..SAMARITAN MARK IN-ALAF
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
+08D4..08DF ; Other_Alphabetic # Mn [12] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH WORD WAQFA
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
093B ; Other_Alphabetic # Mc DEVANAGARI VOWEL SIGN OOE
@@ -463,10 +472,11 @@
0AC1..0AC5 ; Other_Alphabetic # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E
0AC7..0AC8 ; Other_Alphabetic # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI
0AC9 ; Other_Alphabetic # Mc GUJARATI VOWEL SIGN CANDRA O
0ACB..0ACC ; Other_Alphabetic # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU
0AE2..0AE3 ; Other_Alphabetic # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL
+0AFA..0AFC ; Other_Alphabetic # Mn [3] GUJARATI SIGN SUKUN..GUJARATI SIGN MADDAH
0B01 ; Other_Alphabetic # Mn ORIYA SIGN CANDRABINDU
0B02..0B03 ; Other_Alphabetic # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA
0B3E ; Other_Alphabetic # Mc ORIYA VOWEL SIGN AA
0B3F ; Other_Alphabetic # Mn ORIYA VOWEL SIGN I
0B40 ; Other_Alphabetic # Mc ORIYA VOWEL SIGN II
@@ -500,11 +510,11 @@
0CC7..0CC8 ; Other_Alphabetic # Mc [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI
0CCA..0CCB ; Other_Alphabetic # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO
0CCC ; Other_Alphabetic # Mn KANNADA VOWEL SIGN AU
0CD5..0CD6 ; Other_Alphabetic # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK
0CE2..0CE3 ; Other_Alphabetic # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
-0D01 ; Other_Alphabetic # Mn MALAYALAM SIGN CANDRABINDU
+0D00..0D01 ; Other_Alphabetic # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
0D02..0D03 ; Other_Alphabetic # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
0D3E..0D40 ; Other_Alphabetic # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II
0D41..0D44 ; Other_Alphabetic # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR
0D46..0D48 ; Other_Alphabetic # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI
0D4A..0D4C ; Other_Alphabetic # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU
@@ -554,10 +564,11 @@
17B6 ; Other_Alphabetic # Mc KHMER VOWEL SIGN AA
17B7..17BD ; Other_Alphabetic # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA
17BE..17C5 ; Other_Alphabetic # Mc [8] KHMER VOWEL SIGN OE..KHMER VOWEL SIGN AU
17C6 ; Other_Alphabetic # Mn KHMER SIGN NIKAHIT
17C7..17C8 ; Other_Alphabetic # Mc [2] KHMER SIGN REAHMUK..KHMER SIGN YUUKALEAPINTU
+1885..1886 ; Other_Alphabetic # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA
18A9 ; Other_Alphabetic # Mn MONGOLIAN LETTER ALI GALI DAGALGA
1920..1922 ; Other_Alphabetic # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U
1923..1926 ; Other_Alphabetic # Mc [4] LIMBU VOWEL SIGN EE..LIMBU VOWEL SIGN AU
1927..1928 ; Other_Alphabetic # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O
1929..192B ; Other_Alphabetic # Mc [3] LIMBU SUBJOINED LETTER YA..LIMBU SUBJOINED LETTER WA
@@ -611,10 +622,11 @@
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
A880..A881 ; Other_Alphabetic # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA
A8B4..A8C3 ; Other_Alphabetic # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU
+A8C5 ; Other_Alphabetic # Mn SAURASHTRA SIGN CANDRABINDU
A926..A92A ; Other_Alphabetic # Mn [5] KAYAH LI VOWEL UE..KAYAH LI VOWEL O
A947..A951 ; Other_Alphabetic # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R
A952 ; Other_Alphabetic # Mc REJANG CONSONANT SIGN H
A980..A982 ; Other_Alphabetic # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR
A983 ; Other_Alphabetic # Mc JAVANESE SIGN WIGNYAN
@@ -669,10 +681,11 @@
1122C..1122E ; Other_Alphabetic # Mc [3] KHOJKI VOWEL SIGN AA..KHOJKI VOWEL SIGN II
1122F..11231 ; Other_Alphabetic # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI
11232..11233 ; Other_Alphabetic # Mc [2] KHOJKI VOWEL SIGN O..KHOJKI VOWEL SIGN AU
11234 ; Other_Alphabetic # Mn KHOJKI SIGN ANUSVARA
11237 ; Other_Alphabetic # Mn KHOJKI SIGN SHADDA
+1123E ; Other_Alphabetic # Mn KHOJKI SIGN SUKUN
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
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
@@ -681,10 +694,15 @@
11341..11344 ; Other_Alphabetic # Mc [4] GRANTHA VOWEL SIGN U..GRANTHA VOWEL SIGN VOCALIC RR
11347..11348 ; Other_Alphabetic # Mc [2] GRANTHA VOWEL SIGN EE..GRANTHA VOWEL SIGN AI
1134B..1134C ; Other_Alphabetic # Mc [2] GRANTHA VOWEL SIGN OO..GRANTHA VOWEL SIGN AU
11357 ; Other_Alphabetic # Mc GRANTHA AU LENGTH MARK
11362..11363 ; Other_Alphabetic # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL
+11435..11437 ; Other_Alphabetic # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II
+11438..1143F ; Other_Alphabetic # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI
+11440..11441 ; Other_Alphabetic # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU
+11443..11444 ; Other_Alphabetic # Mn [2] NEWA SIGN CANDRABINDU..NEWA SIGN ANUSVARA
+11445 ; Other_Alphabetic # Mc NEWA SIGN VISARGA
114B0..114B2 ; Other_Alphabetic # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II
114B3..114B8 ; Other_Alphabetic # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL
114B9 ; Other_Alphabetic # Mc TIRHUTA VOWEL SIGN E
114BA ; Other_Alphabetic # Mn TIRHUTA VOWEL SIGN SHORT E
114BB..114BE ; Other_Alphabetic # Mc [4] TIRHUTA VOWEL SIGN AI..TIRHUTA VOWEL SIGN AU
@@ -710,36 +728,74 @@
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
+11A01..11A06 ; Other_Alphabetic # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O
+11A07..11A08 ; Other_Alphabetic # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU
+11A09..11A0A ; Other_Alphabetic # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK
+11A35..11A38 ; Other_Alphabetic # Mn [4] ZANABAZAR SQUARE SIGN CANDRABINDU..ZANABAZAR SQUARE SIGN ANUSVARA
+11A39 ; Other_Alphabetic # Mc ZANABAZAR SQUARE SIGN VISARGA
+11A3B..11A3E ; Other_Alphabetic # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA
+11A51..11A56 ; Other_Alphabetic # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE
+11A57..11A58 ; Other_Alphabetic # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU
+11A59..11A5B ; Other_Alphabetic # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK
+11A8A..11A96 ; Other_Alphabetic # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA
+11A97 ; Other_Alphabetic # Mc SOYOMBO SIGN VISARGA
+11C2F ; Other_Alphabetic # Mc BHAIKSUKI VOWEL SIGN AA
+11C30..11C36 ; Other_Alphabetic # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L
+11C38..11C3D ; Other_Alphabetic # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA
+11C3E ; Other_Alphabetic # Mc BHAIKSUKI SIGN VISARGA
+11C92..11CA7 ; Other_Alphabetic # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA
+11CA9 ; Other_Alphabetic # Mc MARCHEN SUBJOINED LETTER YA
+11CAA..11CB0 ; Other_Alphabetic # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA
+11CB1 ; Other_Alphabetic # Mc MARCHEN VOWEL SIGN I
+11CB2..11CB3 ; Other_Alphabetic # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E
+11CB4 ; Other_Alphabetic # Mc MARCHEN VOWEL SIGN O
+11CB5..11CB6 ; Other_Alphabetic # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU
+11D31..11D36 ; Other_Alphabetic # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R
+11D3A ; Other_Alphabetic # Mn MASARAM GONDI VOWEL SIGN E
+11D3C..11D3D ; Other_Alphabetic # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O
+11D3F..11D41 ; Other_Alphabetic # Mn [3] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI SIGN VISARGA
+11D43 ; Other_Alphabetic # Mn MASARAM GONDI SIGN CANDRA
+11D47 ; Other_Alphabetic # Mn MASARAM GONDI RA-KARA
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
+1E000..1E006 ; Other_Alphabetic # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
+1E008..1E018 ; Other_Alphabetic # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
+1E01B..1E021 ; Other_Alphabetic # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
+1E023..1E024 ; Other_Alphabetic # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
+1E026..1E02A ; Other_Alphabetic # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
+1E947 ; Other_Alphabetic # Mn ADLAM HAMZA
1F130..1F149 ; Other_Alphabetic # So [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z
1F150..1F169 ; Other_Alphabetic # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
1F170..1F189 ; Other_Alphabetic # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z
-# Total code points: 1116
+# Total code points: 1300
# ================================================
3006 ; Ideographic # Lo IDEOGRAPHIC CLOSING MARK
3007 ; Ideographic # Nl IDEOGRAPHIC NUMBER ZERO
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..9FD5 ; Ideographic # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
+4E00..9FEA ; Ideographic # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
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
+17000..187EC ; Ideographic # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC
+18800..18AF2 ; Ideographic # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
+1B170..1B2FB ; Ideographic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
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
+2CEB0..2EBE0 ; Ideographic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
-# Total code points: 81404
+# Total code points: 96174
# ================================================
005E ; Diacritic # Sk CIRCUMFLEX ACCENT
0060 ; Diacritic # Sk GRAVE ACCENT
@@ -791,16 +847,18 @@
09CD ; Diacritic # Mn BENGALI SIGN VIRAMA
0A3C ; Diacritic # Mn GURMUKHI SIGN NUKTA
0A4D ; Diacritic # Mn GURMUKHI SIGN VIRAMA
0ABC ; Diacritic # Mn GUJARATI SIGN NUKTA
0ACD ; Diacritic # Mn GUJARATI SIGN VIRAMA
+0AFD..0AFF ; Diacritic # Mn [3] GUJARATI SIGN THREE-DOT NUKTA ABOVE..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
0B3C ; Diacritic # Mn ORIYA SIGN NUKTA
0B4D ; Diacritic # Mn ORIYA SIGN VIRAMA
0BCD ; Diacritic # Mn TAMIL SIGN VIRAMA
0C4D ; Diacritic # Mn TELUGU SIGN VIRAMA
0CBC ; Diacritic # Mn KANNADA SIGN NUKTA
0CCD ; Diacritic # Mn KANNADA SIGN VIRAMA
+0D3B..0D3C ; Diacritic # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
0D4D ; Diacritic # Mn MALAYALAM SIGN VIRAMA
0DCA ; Diacritic # Mn SINHALA SIGN AL-LAKUNA
0E47..0E4C ; Diacritic # Mn [6] THAI CHARACTER MAITAIKHU..THAI CHARACTER THANTHAKHAT
0E4E ; Diacritic # Mn THAI CHARACTER YAMAKKAN
0EC8..0ECC ; Diacritic # Mn [5] LAO TONE MAI EK..LAO CANCELLATION MARK
@@ -836,14 +894,15 @@
1CD4..1CE0 ; Diacritic # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA
1CE1 ; Diacritic # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA
1CE2..1CE8 ; Diacritic # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL
1CED ; Diacritic # Mn VEDIC SIGN TIRYAK
1CF4 ; Diacritic # Mn VEDIC TONE CANDRA ABOVE
+1CF7 ; Diacritic # Mc VEDIC SIGN ATIKRAMA
1CF8..1CF9 ; Diacritic # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE
1D2C..1D6A ; Diacritic # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI
1DC4..1DCF ; Diacritic # Mn [12] COMBINING MACRON-ACUTE..COMBINING ZIGZAG BELOW
-1DF5 ; Diacritic # Mn COMBINING UP TACK ABOVE
+1DF5..1DF9 ; Diacritic # Mn [5] COMBINING UP TACK ABOVE..COMBINING WIDE INVERTED BRIDGE BELOW
1DFD..1DFF ; Diacritic # Mn [3] COMBINING ALMOST EQUAL TO BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
1FBD ; Diacritic # Sk GREEK KORONIS
1FBF..1FC1 ; Diacritic # Sk [3] GREEK PSILI..GREEK DIALYTIKA AND PERISPOMENI
1FCD..1FCF ; Diacritic # Sk [3] GREEK PSILI AND VARIA..GREEK PSILI AND PERISPOMENI
1FDD..1FDF ; Diacritic # Sk [3] GREEK DASIA AND VARIA..GREEK DASIA AND PERISPOMENI
@@ -904,27 +963,37 @@
112E9..112EA ; Diacritic # Mn [2] KHUDAWADI SIGN NUKTA..KHUDAWADI SIGN VIRAMA
1133C ; Diacritic # Mn GRANTHA SIGN NUKTA
1134D ; Diacritic # Mc GRANTHA SIGN VIRAMA
11366..1136C ; Diacritic # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX
11370..11374 ; Diacritic # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA
+11442 ; Diacritic # Mn NEWA SIGN VIRAMA
+11446 ; Diacritic # Mn NEWA SIGN NUKTA
114C2..114C3 ; Diacritic # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA
115BF..115C0 ; Diacritic # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA
1163F ; Diacritic # Mn MODI SIGN VIRAMA
116B6 ; Diacritic # Mc TAKRI SIGN VIRAMA
116B7 ; Diacritic # Mn TAKRI SIGN NUKTA
1172B ; Diacritic # Mn AHOM SIGN KILLER
+11A34 ; Diacritic # Mn ZANABAZAR SQUARE SIGN VIRAMA
+11A47 ; Diacritic # Mn ZANABAZAR SQUARE SUBJOINER
+11A99 ; Diacritic # Mn SOYOMBO SUBJOINER
+11C3F ; Diacritic # Mn BHAIKSUKI SIGN VIRAMA
+11D42 ; Diacritic # Mn MASARAM GONDI SIGN NUKTA
+11D44..11D45 ; Diacritic # Mn [2] MASARAM GONDI SIGN HALANTA..MASARAM GONDI VIRAMA
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
1D167..1D169 ; Diacritic # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3
1D16D..1D172 ; Diacritic # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5
1D17B..1D182 ; Diacritic # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE
1D185..1D18B ; Diacritic # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
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
+1E944..1E946 ; Diacritic # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK
+1E948..1E94A ; Diacritic # Mn [3] ADLAM CONSONANT MODIFIER..ADLAM NUKTA
-# Total code points: 773
+# Total code points: 798
# ================================================
00B7 ; Extender # Po MIDDLE DOT
02D0..02D1 ; Extender # Lm [2] MODIFIER LETTER TRIANGULAR COLON..MODIFIER LETTER HALF TRIANGULAR COLON
@@ -949,13 +1018,16 @@
AADD ; Extender # Lm TAI VIET SYMBOL SAM
AAF3..AAF4 ; Extender # Lm [2] MEETEI MAYEK SYLLABLE REPETITION MARK..MEETEI MAYEK WORD REPETITION MARK
FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
1135D ; Extender # Lo GRANTHA SIGN PLUTA
115C6..115C8 ; Extender # Po [3] SIDDHAM REPETITION MARK-1..SIDDHAM REPETITION MARK-3
+11A98 ; Extender # Mn SOYOMBO GEMINATION MARK
16B42..16B43 ; Extender # Lm [2] PAHAWH HMONG SIGN VOS NRUA..PAHAWH HMONG SIGN IB YAM
+16FE0..16FE1 ; Extender # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK
+1E944..1E946 ; Extender # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK
-# Total code points: 38
+# Total code points: 44
# ================================================
00AA ; Other_Lowercase # Lo FEMININE ORDINAL INDICATOR
00BA ; Other_Lowercase # Lo MASCULINE ORDINAL INDICATOR
@@ -1025,22 +1097,23 @@
0CD5..0CD6 ; Other_Grapheme_Extend # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK
0D3E ; Other_Grapheme_Extend # Mc MALAYALAM VOWEL SIGN AA
0D57 ; Other_Grapheme_Extend # Mc MALAYALAM AU LENGTH MARK
0DCF ; Other_Grapheme_Extend # Mc SINHALA VOWEL SIGN AELA-PILLA
0DDF ; Other_Grapheme_Extend # Mc SINHALA VOWEL SIGN GAYANUKITTA
-200C..200D ; Other_Grapheme_Extend # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER
+200C ; Other_Grapheme_Extend # Cf ZERO WIDTH NON-JOINER
302E..302F ; Other_Grapheme_Extend # Mc [2] HANGUL SINGLE DOT TONE MARK..HANGUL DOUBLE DOT TONE MARK
FF9E..FF9F ; Other_Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
1133E ; Other_Grapheme_Extend # Mc GRANTHA VOWEL SIGN AA
11357 ; Other_Grapheme_Extend # Mc GRANTHA AU LENGTH MARK
114B0 ; Other_Grapheme_Extend # Mc TIRHUTA VOWEL SIGN AA
114BD ; Other_Grapheme_Extend # Mc TIRHUTA VOWEL SIGN SHORT O
115AF ; Other_Grapheme_Extend # Mc SIDDHAM VOWEL SIGN AA
1D165 ; Other_Grapheme_Extend # Mc MUSICAL SYMBOL COMBINING STEM
1D16E..1D172 ; Other_Grapheme_Extend # Mc [5] MUSICAL SYMBOL COMBINING FLAG-1..MUSICAL SYMBOL COMBINING FLAG-5
+E0020..E007F ; Other_Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG
-# Total code points: 30
+# Total code points: 125
# ================================================
2FF0..2FF1 ; IDS_Binary_Operator # So [2] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER ABOVE TO BELOW
2FF4..2FFB ; IDS_Binary_Operator # So [8] IDEOGRAPHIC DESCRIPTION CHARACTER FULL SURROUND..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
@@ -1062,11 +1135,11 @@
# Total code points: 329
# ================================================
3400..4DB5 ; Unified_Ideograph # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
-4E00..9FD5 ; Unified_Ideograph # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
+4E00..9FEA ; Unified_Ideograph # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
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
FA1F ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA1F
FA21 ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA21
@@ -1074,12 +1147,13 @@
FA27..FA29 ; Unified_Ideograph # Lo [3] CJK COMPATIBILITY IDEOGRAPH-FA27..CJK COMPATIBILITY IDEOGRAPH-FA29
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
+2CEB0..2EBE0 ; Unified_Ideograph # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
-# Total code points: 80388
+# Total code points: 87882
# ================================================
034F ; Other_Default_Ignorable_Code_Point # Mn COMBINING GRAPHEME JOINER
115F..1160 ; Other_Default_Ignorable_Code_Point # Lo [2] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG FILLER
@@ -1104,13 +1178,12 @@
17A3..17A4 ; Deprecated # Lo [2] KHMER INDEPENDENT VOWEL QAQ..KHMER INDEPENDENT VOWEL QAA
206A..206F ; Deprecated # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES
2329 ; Deprecated # Ps LEFT-POINTING ANGLE BRACKET
232A ; Deprecated # Pe RIGHT-POINTING ANGLE BRACKET
E0001 ; Deprecated # Cf LANGUAGE TAG
-E007F ; Deprecated # Cf CANCEL TAG
-# Total code points: 16
+# Total code points: 15
# ================================================
0069..006A ; Soft_Dotted # L& [2] LATIN SMALL LETTER I..LATIN SMALL LETTER J
012F ; Soft_Dotted # L& LATIN SMALL LETTER I WITH OGONEK
@@ -1158,15 +1231,16 @@
# Total code points: 19
# ================================================
+1885..1886 ; Other_ID_Start # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA
2118 ; Other_ID_Start # Sm SCRIPT CAPITAL P
212E ; Other_ID_Start # So ESTIMATED SYMBOL
309B..309C ; Other_ID_Start # Sk [2] KATAKANA-HIRAGANA VOICED SOUND MARK..KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
-# Total code points: 4
+# Total code points: 6
# ================================================
00B7 ; Other_ID_Continue # Po MIDDLE DOT
0387 ; Other_ID_Continue # Po GREEK ANO TELEIA
@@ -1175,76 +1249,80 @@
# Total code points: 12
# ================================================
-0021 ; STerm # Po EXCLAMATION MARK
-002E ; STerm # Po FULL STOP
-003F ; STerm # Po QUESTION MARK
-0589 ; STerm # Po ARMENIAN FULL STOP
-061F ; STerm # Po ARABIC QUESTION MARK
-06D4 ; STerm # Po ARABIC FULL STOP
-0700..0702 ; STerm # Po [3] SYRIAC END OF PARAGRAPH..SYRIAC SUBLINEAR FULL STOP
-07F9 ; STerm # Po NKO EXCLAMATION MARK
-0964..0965 ; STerm # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA
-104A..104B ; STerm # Po [2] MYANMAR SIGN LITTLE SECTION..MYANMAR SIGN SECTION
-1362 ; STerm # Po ETHIOPIC FULL STOP
-1367..1368 ; STerm # Po [2] ETHIOPIC QUESTION MARK..ETHIOPIC PARAGRAPH SEPARATOR
-166E ; STerm # Po CANADIAN SYLLABICS FULL STOP
-1735..1736 ; STerm # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION
-1803 ; STerm # Po MONGOLIAN FULL STOP
-1809 ; STerm # Po MONGOLIAN MANCHU FULL STOP
-1944..1945 ; STerm # Po [2] LIMBU EXCLAMATION MARK..LIMBU QUESTION MARK
-1AA8..1AAB ; STerm # Po [4] TAI THAM SIGN KAAN..TAI THAM SIGN SATKAANKUU
-1B5A..1B5B ; STerm # Po [2] BALINESE PANTI..BALINESE PAMADA
-1B5E..1B5F ; STerm # Po [2] BALINESE CARIK SIKI..BALINESE CARIK PAREREN
-1C3B..1C3C ; STerm # Po [2] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION NYET THYOOM TA-ROL
-1C7E..1C7F ; STerm # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD
-203C..203D ; STerm # Po [2] DOUBLE EXCLAMATION MARK..INTERROBANG
-2047..2049 ; STerm # Po [3] DOUBLE QUESTION MARK..EXCLAMATION QUESTION MARK
-2E2E ; STerm # Po REVERSED QUESTION MARK
-2E3C ; STerm # Po STENOGRAPHIC FULL STOP
-3002 ; STerm # Po IDEOGRAPHIC FULL STOP
-A4FF ; STerm # Po LISU PUNCTUATION FULL STOP
-A60E..A60F ; STerm # Po [2] VAI FULL STOP..VAI QUESTION MARK
-A6F3 ; STerm # Po BAMUM FULL STOP
-A6F7 ; STerm # Po BAMUM QUESTION MARK
-A876..A877 ; STerm # Po [2] PHAGS-PA MARK SHAD..PHAGS-PA MARK DOUBLE SHAD
-A8CE..A8CF ; STerm # Po [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA
-A92F ; STerm # Po KAYAH LI SIGN SHYA
-A9C8..A9C9 ; STerm # Po [2] JAVANESE PADA LINGSA..JAVANESE PADA LUNGSI
-AA5D..AA5F ; STerm # Po [3] CHAM PUNCTUATION DANDA..CHAM PUNCTUATION TRIPLE DANDA
-AAF0..AAF1 ; STerm # Po [2] MEETEI MAYEK CHEIKHAN..MEETEI MAYEK AHANG KHUDAM
-ABEB ; STerm # Po MEETEI MAYEK CHEIKHEI
-FE52 ; STerm # Po SMALL FULL STOP
-FE56..FE57 ; STerm # Po [2] SMALL QUESTION MARK..SMALL EXCLAMATION MARK
-FF01 ; STerm # Po FULLWIDTH EXCLAMATION MARK
-FF0E ; STerm # Po FULLWIDTH FULL STOP
-FF1F ; STerm # Po FULLWIDTH QUESTION MARK
-FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP
-10A56..10A57 ; STerm # Po [2] KHAROSHTHI PUNCTUATION DANDA..KHAROSHTHI PUNCTUATION DOUBLE DANDA
-11047..11048 ; STerm # Po [2] BRAHMI DANDA..BRAHMI DOUBLE DANDA
-110BE..110C1 ; STerm # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA
-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..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
+0021 ; Sentence_Terminal # Po EXCLAMATION MARK
+002E ; Sentence_Terminal # Po FULL STOP
+003F ; Sentence_Terminal # Po QUESTION MARK
+0589 ; Sentence_Terminal # Po ARMENIAN FULL STOP
+061F ; Sentence_Terminal # Po ARABIC QUESTION MARK
+06D4 ; Sentence_Terminal # Po ARABIC FULL STOP
+0700..0702 ; Sentence_Terminal # Po [3] SYRIAC END OF PARAGRAPH..SYRIAC SUBLINEAR FULL STOP
+07F9 ; Sentence_Terminal # Po NKO EXCLAMATION MARK
+0964..0965 ; Sentence_Terminal # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA
+104A..104B ; Sentence_Terminal # Po [2] MYANMAR SIGN LITTLE SECTION..MYANMAR SIGN SECTION
+1362 ; Sentence_Terminal # Po ETHIOPIC FULL STOP
+1367..1368 ; Sentence_Terminal # Po [2] ETHIOPIC QUESTION MARK..ETHIOPIC PARAGRAPH SEPARATOR
+166E ; Sentence_Terminal # Po CANADIAN SYLLABICS FULL STOP
+1735..1736 ; Sentence_Terminal # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION
+1803 ; Sentence_Terminal # Po MONGOLIAN FULL STOP
+1809 ; Sentence_Terminal # Po MONGOLIAN MANCHU FULL STOP
+1944..1945 ; Sentence_Terminal # Po [2] LIMBU EXCLAMATION MARK..LIMBU QUESTION MARK
+1AA8..1AAB ; Sentence_Terminal # Po [4] TAI THAM SIGN KAAN..TAI THAM SIGN SATKAANKUU
+1B5A..1B5B ; Sentence_Terminal # Po [2] BALINESE PANTI..BALINESE PAMADA
+1B5E..1B5F ; Sentence_Terminal # Po [2] BALINESE CARIK SIKI..BALINESE CARIK PAREREN
+1C3B..1C3C ; Sentence_Terminal # Po [2] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION NYET THYOOM TA-ROL
+1C7E..1C7F ; Sentence_Terminal # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD
+203C..203D ; Sentence_Terminal # Po [2] DOUBLE EXCLAMATION MARK..INTERROBANG
+2047..2049 ; Sentence_Terminal # Po [3] DOUBLE QUESTION MARK..EXCLAMATION QUESTION MARK
+2E2E ; Sentence_Terminal # Po REVERSED QUESTION MARK
+2E3C ; Sentence_Terminal # Po STENOGRAPHIC FULL STOP
+3002 ; Sentence_Terminal # Po IDEOGRAPHIC FULL STOP
+A4FF ; Sentence_Terminal # Po LISU PUNCTUATION FULL STOP
+A60E..A60F ; Sentence_Terminal # Po [2] VAI FULL STOP..VAI QUESTION MARK
+A6F3 ; Sentence_Terminal # Po BAMUM FULL STOP
+A6F7 ; Sentence_Terminal # Po BAMUM QUESTION MARK
+A876..A877 ; Sentence_Terminal # Po [2] PHAGS-PA MARK SHAD..PHAGS-PA MARK DOUBLE SHAD
+A8CE..A8CF ; Sentence_Terminal # Po [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA
+A92F ; Sentence_Terminal # Po KAYAH LI SIGN SHYA
+A9C8..A9C9 ; Sentence_Terminal # Po [2] JAVANESE PADA LINGSA..JAVANESE PADA LUNGSI
+AA5D..AA5F ; Sentence_Terminal # Po [3] CHAM PUNCTUATION DANDA..CHAM PUNCTUATION TRIPLE DANDA
+AAF0..AAF1 ; Sentence_Terminal # Po [2] MEETEI MAYEK CHEIKHAN..MEETEI MAYEK AHANG KHUDAM
+ABEB ; Sentence_Terminal # Po MEETEI MAYEK CHEIKHEI
+FE52 ; Sentence_Terminal # Po SMALL FULL STOP
+FE56..FE57 ; Sentence_Terminal # Po [2] SMALL QUESTION MARK..SMALL EXCLAMATION MARK
+FF01 ; Sentence_Terminal # Po FULLWIDTH EXCLAMATION MARK
+FF0E ; Sentence_Terminal # Po FULLWIDTH FULL STOP
+FF1F ; Sentence_Terminal # Po FULLWIDTH QUESTION MARK
+FF61 ; Sentence_Terminal # Po HALFWIDTH IDEOGRAPHIC FULL STOP
+10A56..10A57 ; Sentence_Terminal # Po [2] KHAROSHTHI PUNCTUATION DANDA..KHAROSHTHI PUNCTUATION DOUBLE DANDA
+11047..11048 ; Sentence_Terminal # Po [2] BRAHMI DANDA..BRAHMI DOUBLE DANDA
+110BE..110C1 ; Sentence_Terminal # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA
+11141..11143 ; Sentence_Terminal # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK
+111C5..111C6 ; Sentence_Terminal # Po [2] SHARADA DANDA..SHARADA DOUBLE DANDA
+111CD ; Sentence_Terminal # Po SHARADA SUTRA MARK
+111DE..111DF ; Sentence_Terminal # Po [2] SHARADA SECTION MARK-1..SHARADA SECTION MARK-2
+11238..11239 ; Sentence_Terminal # Po [2] KHOJKI DANDA..KHOJKI DOUBLE DANDA
+1123B..1123C ; Sentence_Terminal # Po [2] KHOJKI SECTION MARK..KHOJKI DOUBLE SECTION MARK
+112A9 ; Sentence_Terminal # Po MULTANI SECTION MARK
+1144B..1144C ; Sentence_Terminal # Po [2] NEWA DANDA..NEWA DOUBLE DANDA
+115C2..115C3 ; Sentence_Terminal # Po [2] SIDDHAM DANDA..SIDDHAM DOUBLE DANDA
+115C9..115D7 ; Sentence_Terminal # Po [15] SIDDHAM END OF TEXT MARK..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES
+11641..11642 ; Sentence_Terminal # Po [2] MODI DANDA..MODI DOUBLE DANDA
+1173C..1173E ; Sentence_Terminal # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI
+11A42..11A43 ; Sentence_Terminal # Po [2] ZANABAZAR SQUARE MARK SHAD..ZANABAZAR SQUARE MARK DOUBLE SHAD
+11A9B..11A9C ; Sentence_Terminal # Po [2] SOYOMBO MARK SHAD..SOYOMBO MARK DOUBLE SHAD
+11C41..11C42 ; Sentence_Terminal # Po [2] BHAIKSUKI DANDA..BHAIKSUKI DOUBLE DANDA
+16A6E..16A6F ; Sentence_Terminal # Po [2] MRO DANDA..MRO DOUBLE DANDA
+16AF5 ; Sentence_Terminal # Po BASSA VAH FULL STOP
+16B37..16B38 ; Sentence_Terminal # Po [2] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN VOS TSHAB CEEB
+16B44 ; Sentence_Terminal # Po PAHAWH HMONG SIGN XAUS
+1BC9F ; Sentence_Terminal # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP
+1DA88 ; Sentence_Terminal # Po SIGNWRITING FULL STOP
-# Total code points: 120
+# Total code points: 128
# ================================================
180B..180D ; Variation_Selector # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
FE00..FE0F ; Variation_Selector # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
@@ -1357,13 +1435,11 @@
237C ; Pattern_Syntax # Sm RIGHT ANGLE WITH DOWNWARDS ZIGZAG ARROW
237D..239A ; Pattern_Syntax # So [30] SHOULDERED OPEN BOX..CLEAR SCREEN SYMBOL
239B..23B3 ; Pattern_Syntax # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM
23B4..23DB ; Pattern_Syntax # So [40] TOP SQUARE BRACKET..FUSE
23DC..23E1 ; Pattern_Syntax # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET
-23E2..23FA ; Pattern_Syntax # So [25] WHITE TRAPEZIUM..BLACK CIRCLE FOR RECORD
-23FB..23FF ; Pattern_Syntax # Cn [5] <reserved-23FB>..<reserved-23FF>
-2400..2426 ; Pattern_Syntax # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO
+23E2..2426 ; Pattern_Syntax # So [69] WHITE TRAPEZIUM..SYMBOL FOR SUBSTITUTE FORM TWO
2427..243F ; Pattern_Syntax # Cn [25] <reserved-2427>..<reserved-243F>
2440..244A ; Pattern_Syntax # So [11] OCR HOOK..OCR DOUBLE BACKSLASH
244B..245F ; Pattern_Syntax # Cn [21] <reserved-244B>..<reserved-245F>
2500..25B6 ; Pattern_Syntax # So [183] BOX DRAWINGS LIGHT HORIZONTAL..BLACK RIGHT-POINTING TRIANGLE
25B7 ; Pattern_Syntax # Sm WHITE RIGHT-POINTING TRIANGLE
@@ -1447,12 +1523,12 @@
2B96..2B97 ; Pattern_Syntax # Cn [2] <reserved-2B96>..<reserved-2B97>
2B98..2BB9 ; Pattern_Syntax # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX
2BBA..2BBC ; Pattern_Syntax # Cn [3] <reserved-2BBA>..<reserved-2BBC>
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..2BEB ; Pattern_Syntax # Cn [26] <reserved-2BD2>..<reserved-2BEB>
+2BCA..2BD2 ; Pattern_Syntax # So [9] TOP HALF BLACK CIRCLE..GROUP MARK
+2BD3..2BEB ; Pattern_Syntax # Cn [25] <reserved-2BD3>..<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
@@ -1488,11 +1564,12 @@
2E3A..2E3B ; Pattern_Syntax # Pd [2] TWO-EM DASH..THREE-EM DASH
2E3C..2E3F ; Pattern_Syntax # Po [4] STENOGRAPHIC FULL STOP..CAPITULUM
2E40 ; Pattern_Syntax # Pd DOUBLE HYPHEN
2E41 ; Pattern_Syntax # Po REVERSED COMMA
2E42 ; Pattern_Syntax # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK
-2E43..2E7F ; Pattern_Syntax # Cn [61] <reserved-2E43>..<reserved-2E7F>
+2E43..2E49 ; Pattern_Syntax # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA
+2E4A..2E7F ; Pattern_Syntax # Cn [54] <reserved-2E4A>..<reserved-2E7F>
3001..3003 ; Pattern_Syntax # Po [3] IDEOGRAPHIC COMMA..DITTO MARK
3008 ; Pattern_Syntax # Ps LEFT ANGLE BRACKET
3009 ; Pattern_Syntax # Pe RIGHT ANGLE BRACKET
300A ; Pattern_Syntax # Ps LEFT DOUBLE ANGLE BRACKET
300B ; Pattern_Syntax # Pe RIGHT DOUBLE ANGLE BRACKET
@@ -1520,6 +1597,22 @@
FD3F ; Pattern_Syntax # Ps ORNATE RIGHT PARENTHESIS
FE45..FE46 ; Pattern_Syntax # Po [2] SESAME DOT..WHITE SESAME DOT
# Total code points: 2760
+# ================================================
+
+0600..0605 ; Prepended_Concatenation_Mark # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE
+06DD ; Prepended_Concatenation_Mark # Cf ARABIC END OF AYAH
+070F ; Prepended_Concatenation_Mark # Cf SYRIAC ABBREVIATION MARK
+08E2 ; Prepended_Concatenation_Mark # Cf ARABIC DISPUTED END OF AYAH
+110BD ; Prepended_Concatenation_Mark # Cf KAITHI NUMBER SIGN
+
+# Total code points: 10
+
+# ================================================
+
+1F1E6..1F1FF ; Regional_Indicator # So [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z
+
+# Total code points: 26
+
# EOF
< prev index next >