summaryrefslogtreecommitdiff
path: root/lib/unicore/PropList.txt
diff options
context:
space:
mode:
authorKarl Williamson <khw@khw-desktop.(none)>2009-12-02 21:36:17 -0700
committerRafael Garcia-Suarez <rgs@consttype.org>2009-12-03 11:08:42 +0100
commit283b82dc9f704fb99591ed28497a6a263e6ef519 (patch)
tree163772fbf089f2287a3eab20c9805c636d6d4268 /lib/unicore/PropList.txt
parentc9930541bfa04399c3b648e83c9b750cee1154fb (diff)
downloadperl-283b82dc9f704fb99591ed28497a6a263e6ef519.tar.gz
Unicode 5.2
Diffstat (limited to 'lib/unicore/PropList.txt')
-rw-r--r--lib/unicore/PropList.txt168
1 files changed, 130 insertions, 38 deletions
diff --git a/lib/unicore/PropList.txt b/lib/unicore/PropList.txt
index 3bbbd76929..a15ec5ba9e 100644
--- a/lib/unicore/PropList.txt
+++ b/lib/unicore/PropList.txt
@@ -1,10 +1,10 @@
-# PropList-5.1.0.txt
-# Date: 2008-03-20, 17:55:27 GMT [MD]
+# PropList-5.2.0.txt
+# Date: 2009-08-22, 04:58:40 GMT [MD]
#
# Unicode Character Database
-# Copyright (c) 1991-2008 Unicode, Inc.
+# Copyright (c) 1991-2009 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
-# For documentation, see UCD.html
+# For documentation, see http://www.unicode.org/reports/tr44/
# ================================================
@@ -41,6 +41,7 @@
002D ; Dash # Pd HYPHEN-MINUS
058A ; Dash # Pd ARMENIAN HYPHEN
05BE ; Dash # Pd HEBREW PUNCTUATION MAQAF
+1400 ; Dash # Pd CANADIAN SYLLABICS HYPHEN
1806 ; Dash # Pd MONGOLIAN TODO SOFT HYPHEN
2010..2015 ; Dash # Pd [6] HYPHEN..HORIZONTAL BAR
2053 ; Dash # Po SWUNG DASH
@@ -57,7 +58,7 @@ FE58 ; Dash # Pd SMALL EM DASH
FE63 ; Dash # Pd SMALL HYPHEN-MINUS
FF0D ; Dash # Pd FULLWIDTH HYPHEN-MINUS
-# Total code points: 24
+# Total code points: 25
# ================================================
@@ -124,6 +125,7 @@ FF63 ; Quotation_Mark # Pe HALFWIDTH RIGHT CORNER BRACKET
0700..070A ; Terminal_Punctuation # Po [11] SYRIAC END OF PARAGRAPH..SYRIAC CONTRACTION
070C ; Terminal_Punctuation # Po SYRIAC HARKLEAN METOBELUS
07F8..07F9 ; Terminal_Punctuation # Po [2] NKO COMMA..NKO EXCLAMATION MARK
+0830..083E ; Terminal_Punctuation # Po [15] SAMARITAN PUNCTUATION NEQUDAA..SAMARITAN PUNCTUATION ANNAAU
0964..0965 ; Terminal_Punctuation # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA
0E5A..0E5B ; Terminal_Punctuation # Po [2] THAI CHARACTER ANGKHANKHU..THAI CHARACTER KHOMUT
0F08 ; Terminal_Punctuation # Po TIBETAN MARK SBRUL SHAD
@@ -137,6 +139,7 @@ FF63 ; Quotation_Mark # Pe HALFWIDTH RIGHT CORNER BRACKET
1802..1805 ; Terminal_Punctuation # Po [4] MONGOLIAN COMMA..MONGOLIAN FOUR DOTS
1808..1809 ; Terminal_Punctuation # Po [2] MONGOLIAN MANCHU COMMA..MONGOLIAN MANCHU FULL STOP
1944..1945 ; Terminal_Punctuation # Po [2] LIMBU EXCLAMATION MARK..LIMBU QUESTION MARK
+1AA8..1AAB ; Terminal_Punctuation # Po [4] TAI THAM SIGN KAAN..TAI THAM SIGN SATKAANKUU
1B5A..1B5B ; Terminal_Punctuation # Po [2] BALINESE PANTI..BALINESE PAMADA
1B5D..1B5F ; Terminal_Punctuation # Po [3] BALINESE CARIK PAMUNGKAH..BALINESE CARIK PAREREN
1C3B..1C3F ; Terminal_Punctuation # Po [5] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION TSHOOK
@@ -145,11 +148,16 @@ FF63 ; Quotation_Mark # Pe HALFWIDTH RIGHT CORNER BRACKET
2047..2049 ; Terminal_Punctuation # Po [3] DOUBLE QUESTION MARK..EXCLAMATION QUESTION MARK
2E2E ; Terminal_Punctuation # Po REVERSED QUESTION MARK
3001..3002 ; Terminal_Punctuation # Po [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP
+A4FE..A4FF ; Terminal_Punctuation # Po [2] LISU PUNCTUATION COMMA..LISU PUNCTUATION FULL STOP
A60D..A60F ; Terminal_Punctuation # Po [3] VAI COMMA..VAI QUESTION MARK
+A6F3..A6F7 ; Terminal_Punctuation # Po [5] BAMUM FULL STOP..BAMUM QUESTION MARK
A876..A877 ; Terminal_Punctuation # Po [2] PHAGS-PA MARK SHAD..PHAGS-PA MARK DOUBLE SHAD
A8CE..A8CF ; Terminal_Punctuation # Po [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA
A92F ; Terminal_Punctuation # Po KAYAH LI SIGN SHYA
+A9C7..A9C9 ; Terminal_Punctuation # Po [3] JAVANESE PADA PANGKAT..JAVANESE PADA LUNGSI
AA5D..AA5F ; Terminal_Punctuation # Po [3] CHAM PUNCTUATION DANDA..CHAM PUNCTUATION TRIPLE DANDA
+AADF ; Terminal_Punctuation # Po TAI VIET SYMBOL KOI KOI
+ABEB ; Terminal_Punctuation # Po MEETEI MAYEK CHEIKHEI
FE50..FE52 ; Terminal_Punctuation # Po [3] SMALL COMMA..SMALL FULL STOP
FE54..FE57 ; Terminal_Punctuation # Po [4] SMALL SEMICOLON..SMALL EXCLAMATION MARK
FF01 ; Terminal_Punctuation # Po FULLWIDTH EXCLAMATION MARK
@@ -161,10 +169,13 @@ FF61 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC FULL STOP
FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA
1039F ; Terminal_Punctuation # Po UGARITIC WORD DIVIDER
103D0 ; Terminal_Punctuation # Po OLD PERSIAN WORD DIVIDER
+10857 ; Terminal_Punctuation # Po IMPERIAL ARAMAIC SECTION SIGN
1091F ; Terminal_Punctuation # Po PHOENICIAN WORD SEPARATOR
+10B3A..10B3F ; Terminal_Punctuation # Po [6] TINY TWO DOTS OVER ONE DOT PUNCTUATION..LARGE ONE RING OVER TWO RINGS PUNCTUATION
+110BE..110C1 ; Terminal_Punctuation # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA
12470..12473 ; Terminal_Punctuation # Po [4] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL TRICOLON
-# Total code points: 119
+# Total code points: 161
# ================================================
@@ -347,11 +358,17 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
0711 ; Other_Alphabetic # Mn SYRIAC LETTER SUPERSCRIPT ALAPH
0730..073F ; Other_Alphabetic # Mn [16] SYRIAC PTHAHA ABOVE..SYRIAC RWAHA
07A6..07B0 ; Other_Alphabetic # Mn [11] THAANA ABAFILI..THAANA SUKUN
-0901..0902 ; Other_Alphabetic # Mn [2] DEVANAGARI SIGN CANDRABINDU..DEVANAGARI SIGN ANUSVARA
+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
+0900..0902 ; Other_Alphabetic # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA
0903 ; Other_Alphabetic # Mc DEVANAGARI SIGN VISARGA
093E..0940 ; Other_Alphabetic # Mc [3] DEVANAGARI VOWEL SIGN AA..DEVANAGARI VOWEL SIGN II
0941..0948 ; Other_Alphabetic # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI
0949..094C ; Other_Alphabetic # Mc [4] DEVANAGARI VOWEL SIGN CANDRA O..DEVANAGARI VOWEL SIGN AU
+094E ; Other_Alphabetic # Mc DEVANAGARI VOWEL SIGN PRISHTHAMATRA E
+0955 ; Other_Alphabetic # Mn DEVANAGARI VOWEL SIGN CANDRA LONG E
0962..0963 ; Other_Alphabetic # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL
0981 ; Other_Alphabetic # Mn BENGALI SIGN CANDRABINDU
0982..0983 ; Other_Alphabetic # Mc [2] BENGALI SIGN ANUSVARA..BENGALI SIGN VISARGA
@@ -454,6 +471,8 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
1082 ; Other_Alphabetic # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA
1083..1084 ; Other_Alphabetic # Mc [2] MYANMAR VOWEL SIGN SHAN AA..MYANMAR VOWEL SIGN SHAN E
1085..1086 ; Other_Alphabetic # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y
+109C ; Other_Alphabetic # Mc MYANMAR VOWEL SIGN AITON A
+109D ; Other_Alphabetic # Mn MYANMAR VOWEL SIGN AITON AI
135F ; Other_Alphabetic # Mn ETHIOPIC COMBINING GEMINATION MARK
1712..1713 ; Other_Alphabetic # Mn [2] TAGALOG VOWEL SIGN I..TAGALOG VOWEL SIGN U
1732..1733 ; Other_Alphabetic # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U
@@ -476,6 +495,16 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
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..1A1B ; Other_Alphabetic # Mc [3] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN AE
+1A55 ; Other_Alphabetic # Mc TAI THAM CONSONANT SIGN MEDIAL RA
+1A56 ; Other_Alphabetic # Mn TAI THAM CONSONANT SIGN MEDIAL LA
+1A57 ; Other_Alphabetic # Mc TAI THAM CONSONANT SIGN LA TANG LAI
+1A58..1A5E ; Other_Alphabetic # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA
+1A61 ; Other_Alphabetic # Mc TAI THAM VOWEL SIGN A
+1A62 ; Other_Alphabetic # Mn TAI THAM VOWEL SIGN MAI SAT
+1A63..1A64 ; Other_Alphabetic # Mc [2] TAI THAM VOWEL SIGN AA..TAI THAM VOWEL SIGN TALL AA
+1A65..1A6C ; Other_Alphabetic # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW
+1A6D..1A72 ; Other_Alphabetic # Mc [6] TAI THAM VOWEL SIGN OY..TAI THAM VOWEL SIGN THAM AI
+1A73..1A74 ; Other_Alphabetic # Mn [2] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN MAI KANG
1B00..1B03 ; Other_Alphabetic # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG
1B04 ; Other_Alphabetic # Mc BALINESE SIGN BISAH
1B35 ; Other_Alphabetic # Mc BALINESE VOWEL SIGN TEDUNG
@@ -494,6 +523,7 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
1C24..1C2B ; Other_Alphabetic # Mc [8] LEPCHA SUBJOINED LETTER YA..LEPCHA VOWEL SIGN UU
1C2C..1C33 ; Other_Alphabetic # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T
1C34..1C35 ; Other_Alphabetic # Mc [2] LEPCHA CONSONANT SIGN NYIN-DO..LEPCHA CONSONANT SIGN KANG
+1CF2 ; Other_Alphabetic # Mc VEDIC SIGN ARDHAVISARGA
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
A823..A824 ; Other_Alphabetic # Mc [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIGN I
@@ -504,6 +534,14 @@ A8B4..A8C3 ; Other_Alphabetic # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAU
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
+A9B3 ; Other_Alphabetic # Mn JAVANESE SIGN CECAK TELU
+A9B4..A9B5 ; Other_Alphabetic # Mc [2] JAVANESE VOWEL SIGN TARUNG..JAVANESE VOWEL SIGN TOLONG
+A9B6..A9B9 ; Other_Alphabetic # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT
+A9BA..A9BB ; Other_Alphabetic # Mc [2] JAVANESE VOWEL SIGN TALING..JAVANESE VOWEL SIGN DIRGA MURE
+A9BC ; Other_Alphabetic # Mn JAVANESE VOWEL SIGN PEPET
+A9BD..A9BF ; Other_Alphabetic # Mc [3] JAVANESE CONSONANT SIGN KERET..JAVANESE CONSONANT SIGN CAKRA
AA29..AA2E ; Other_Alphabetic # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE
AA2F..AA30 ; Other_Alphabetic # Mc [2] CHAM VOWEL SIGN O..CHAM VOWEL SIGN AI
AA31..AA32 ; Other_Alphabetic # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE
@@ -512,12 +550,25 @@ AA35..AA36 ; Other_Alphabetic # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONA
AA43 ; Other_Alphabetic # Mn CHAM CONSONANT SIGN FINAL NG
AA4C ; Other_Alphabetic # Mn CHAM CONSONANT SIGN FINAL M
AA4D ; Other_Alphabetic # Mc CHAM CONSONANT SIGN FINAL H
+AAB0 ; Other_Alphabetic # Mn TAI VIET MAI KANG
+AAB2..AAB4 ; Other_Alphabetic # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U
+AAB7..AAB8 ; Other_Alphabetic # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA
+AABE ; Other_Alphabetic # Mn TAI VIET VOWEL AM
+ABE3..ABE4 ; Other_Alphabetic # Mc [2] MEETEI MAYEK VOWEL SIGN ONAP..MEETEI MAYEK VOWEL SIGN INAP
+ABE5 ; Other_Alphabetic # Mn MEETEI MAYEK VOWEL SIGN ANAP
+ABE6..ABE7 ; Other_Alphabetic # Mc [2] MEETEI MAYEK VOWEL SIGN YENAP..MEETEI MAYEK VOWEL SIGN SOUNAP
+ABE8 ; Other_Alphabetic # Mn MEETEI MAYEK VOWEL SIGN UNAP
+ABE9..ABEA ; Other_Alphabetic # Mc [2] MEETEI MAYEK VOWEL SIGN CHEINAP..MEETEI MAYEK VOWEL SIGN NUNG
FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
10A01..10A03 ; Other_Alphabetic # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R
10A05..10A06 ; Other_Alphabetic # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O
10A0C..10A0F ; Other_Alphabetic # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA
+11082 ; Other_Alphabetic # Mc KAITHI SIGN VISARGA
+110B0..110B2 ; Other_Alphabetic # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II
+110B3..110B6 ; Other_Alphabetic # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI
+110B7..110B8 ; Other_Alphabetic # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU
-# Total code points: 663
+# Total code points: 759
# ================================================
@@ -526,14 +577,15 @@ 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..9FC3 ; Ideographic # Lo [20932] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FC3
+4E00..9FCB ; Ideographic # Lo [20940] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCB
F900..FA2D ; Ideographic # Lo [302] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA2D
-FA30..FA6A ; Ideographic # Lo [59] CJK COMPATIBILITY IDEOGRAPH-FA30..CJK COMPATIBILITY IDEOGRAPH-FA6A
+FA30..FA6D ; Ideographic # Lo [62] CJK COMPATIBILITY IDEOGRAPH-FA30..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
2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
-# Total code points: 71248
+# Total code points: 75408
# ================================================
@@ -577,6 +629,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
07A6..07B0 ; Diacritic # Mn [11] THAANA ABAFILI..THAANA SUKUN
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
093C ; Diacritic # Mn DEVANAGARI SIGN NUKTA
094D ; Diacritic # Mn DEVANAGARI SIGN VIRAMA
0951..0954 ; Diacritic # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT
@@ -611,25 +664,35 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
1087..108C ; Diacritic # Mc [6] MYANMAR SIGN SHAN TONE-2..MYANMAR SIGN SHAN COUNCIL TONE-3
108D ; Diacritic # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE
108F ; Diacritic # Mc MYANMAR SIGN RUMAI PALAUNG TONE-5
+109A..109B ; Diacritic # Mc [2] MYANMAR SIGN KHAMTI TONE-1..MYANMAR SIGN KHAMTI TONE-3
17C9..17D3 ; Diacritic # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT
17DD ; Diacritic # Mn KHMER SIGN ATTHACAN
1939..193B ; Diacritic # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I
+1A75..1A7C ; Diacritic # Mn [8] TAI THAM SIGN TONE-1..TAI THAM SIGN KHUEN-LUE KARAN
+1A7F ; Diacritic # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT
1B34 ; Diacritic # Mn BALINESE SIGN REREKAN
1B44 ; Diacritic # Mc BALINESE ADEG ADEG
1B6B..1B73 ; Diacritic # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG
1BAA ; Diacritic # Mc SUNDANESE SIGN PAMAAEH
1C36..1C37 ; Diacritic # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA
1C78..1C7D ; Diacritic # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD
+1CD0..1CD2 ; Diacritic # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA
+1CD3 ; Diacritic # Po VEDIC SIGN NIHSHVASA
+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
1D2C..1D61 ; Diacritic # Lm [54] MODIFIER LETTER CAPITAL A..MODIFIER LETTER SMALL CHI
1D62..1D6A ; Diacritic # L& [9] LATIN SUBSCRIPT SMALL LETTER I..GREEK SUBSCRIPT SMALL LETTER CHI
1DC4..1DCF ; Diacritic # Mn [12] COMBINING MACRON-ACUTE..COMBINING ZIGZAG BELOW
-1DFE..1DFF ; Diacritic # Mn [2] COMBINING LEFT ARROWHEAD ABOVE..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD 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
1FED..1FEF ; Diacritic # Sk [3] GREEK DIALYTIKA AND VARIA..GREEK VARIA
1FFD..1FFE ; Diacritic # Sk [2] GREEK OXIA..GREEK DASIA
+2CEF..2CF1 ; Diacritic # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS
2E2F ; Diacritic # Lm VERTICAL TILDE
302A..302F ; Diacritic # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK
3099..309A ; Diacritic # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
@@ -638,13 +701,24 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
A66F ; Diacritic # Mn COMBINING CYRILLIC VZMET
A67C..A67D ; Diacritic # Mn [2] COMBINING CYRILLIC KAVYKA..COMBINING CYRILLIC PAYEROK
A67F ; Diacritic # Lm CYRILLIC PAYEROK
+A6F0..A6F1 ; Diacritic # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS
A717..A71F ; Diacritic # Lm [9] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOW INVERTED EXCLAMATION MARK
A720..A721 ; Diacritic # Sk [2] MODIFIER LETTER STRESS AND HIGH TONE..MODIFIER LETTER STRESS AND LOW TONE
A788 ; Diacritic # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT
A8C4 ; Diacritic # Mn SAURASHTRA SIGN VIRAMA
+A8E0..A8F1 ; Diacritic # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA
A92B..A92D ; Diacritic # Mn [3] KAYAH LI TONE PLOPHU..KAYAH LI TONE CALYA PLOPHU
A92E ; Diacritic # Po KAYAH LI SIGN CWI
A953 ; Diacritic # Mc REJANG VIRAMA
+A9B3 ; Diacritic # Mn JAVANESE SIGN CECAK TELU
+A9C0 ; Diacritic # Mc JAVANESE PANGKON
+AA7B ; Diacritic # Mc MYANMAR SIGN PAO KAREN TONE
+AABF ; Diacritic # Mn TAI VIET TONE MAI EK
+AAC0 ; Diacritic # Lo TAI VIET TONE MAI NUENG
+AAC1 ; Diacritic # Mn TAI VIET TONE MAI THO
+AAC2 ; Diacritic # Lo TAI VIET TONE MAI SONG
+ABEC ; Diacritic # Mc MEETEI MAYEK LUM IYEK
+ABED ; Diacritic # Mn MEETEI MAYEK APUN IYEK
FB1E ; Diacritic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
FE20..FE26 ; Diacritic # Mn [7] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON
FF3E ; Diacritic # Sk FULLWIDTH CIRCUMFLEX ACCENT
@@ -652,13 +726,14 @@ FF40 ; Diacritic # Sk FULLWIDTH GRAVE ACCENT
FF70 ; Diacritic # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
FF9E..FF9F ; Diacritic # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
FFE3 ; Diacritic # Sk FULLWIDTH MACRON
+110B9..110BA ; Diacritic # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA
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
-# Total code points: 565
+# Total code points: 639
# ================================================
@@ -669,6 +744,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON
0E46 ; Extender # Lm THAI CHARACTER MAIYAMOK
0EC6 ; Extender # Lm LAO KO LA
1843 ; Extender # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN
+1AA7 ; Extender # Lm TAI THAM SIGN MAI YAMOK
1C36 ; Extender # Mn LEPCHA SIGN RAN
1C7B ; Extender # Lm OL CHIKI RELAA
3005 ; Extender # Lm IDEOGRAPHIC ITERATION MARK
@@ -677,9 +753,12 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON
30FC..30FE ; Extender # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK
A015 ; Extender # Lm YI SYLLABLE WU
A60C ; Extender # Lm VAI SYLLABLE LENGTHENER
+A9CF ; Extender # Lm JAVANESE PANGRANGKEP
+AA70 ; Extender # Lm MYANMAR MODIFIER LETTER KHAMTI REDUPLICATION
+AADD ; Extender # Lm TAI VIET SYMBOL SAM
FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
-# Total code points: 24
+# Total code points: 28
# ================================================
@@ -774,7 +853,7 @@ 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..9FC3 ; Unified_Ideograph # Lo [20932] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FC3
+4E00..9FCB ; Unified_Ideograph # Lo [20940] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCB
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
@@ -783,8 +862,9 @@ FA21 ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA21
FA23..FA24 ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA23..CJK COMPATIBILITY IDEOGRAPH-FA24
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
-# Total code points: 70237
+# Total code points: 74394
# ================================================
@@ -803,14 +883,17 @@ E01F0..E0FFF ; Other_Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>.
# ================================================
-0340..0341 ; Deprecated # Mn [2] COMBINING GRAVE TONE MARK..COMBINING ACUTE TONE MARK
-17A3 ; Deprecated # Lo KHMER INDEPENDENT VOWEL QAQ
-17D3 ; Deprecated # Mn KHMER SIGN BATHAMASAT
+0149 ; Deprecated # L& LATIN SMALL LETTER N PRECEDED BY APOSTROPHE
+0F77 ; Deprecated # Mn TIBETAN VOWEL SIGN VOCALIC RR
+0F79 ; Deprecated # Mn TIBETAN VOWEL SIGN VOCALIC LL
+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
E0020..E007F ; Deprecated # Cf [96] TAG SPACE..CANCEL TAG
-# Total code points: 107
+# Total code points: 110
# ================================================
@@ -829,7 +912,7 @@ E0020..E007F ; Deprecated # Cf [96] TAG SPACE..CANCEL TAG
1DA8 ; Soft_Dotted # Lm MODIFIER LETTER SMALL J WITH CROSSED-TAIL
1E2D ; Soft_Dotted # L& LATIN SMALL LETTER I WITH TILDE BELOW
1ECB ; Soft_Dotted # L& LATIN SMALL LETTER I WITH DOT BELOW
-2071 ; Soft_Dotted # L& SUPERSCRIPT LATIN SMALL LETTER I
+2071 ; Soft_Dotted # Lm SUPERSCRIPT LATIN SMALL LETTER I
2148..2149 ; Soft_Dotted # L& [2] DOUBLE-STRUCK ITALIC SMALL I..DOUBLE-STRUCK ITALIC SMALL J
2C7C ; Soft_Dotted # L& LATIN SUBSCRIPT SMALL LETTER J
1D422..1D423 ; Soft_Dotted # L& [2] MATHEMATICAL BOLD SMALL I..MATHEMATICAL BOLD SMALL J
@@ -852,8 +935,11 @@ 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
+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: 10
+# Total code points: 15
# ================================================
@@ -899,19 +985,25 @@ E0020..E007F ; Deprecated # Cf [96] TAG SPACE..CANCEL TAG
2047..2049 ; STerm # Po [3] DOUBLE QUESTION MARK..EXCLAMATION QUESTION MARK
2E2E ; STerm # Po REVERSED QUESTION MARK
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
+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
+110BE..110C1 ; STerm # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA
-# Total code points: 56
+# Total code points: 66
# ================================================
@@ -1024,8 +1116,8 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S
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..23E7 ; Pattern_Syntax # So [6] WHITE TRAPEZIUM..ELECTRICAL INTERSECTION
-23E8..23FF ; Pattern_Syntax # Cn [24] <reserved-23E8>..<reserved-23FF>
+23E2..23E8 ; Pattern_Syntax # So [7] WHITE TRAPEZIUM..DECIMAL EXPONENT SYMBOL
+23E9..23FF ; Pattern_Syntax # Cn [23] <reserved-23E9>..<reserved-23FF>
2400..2426 ; Pattern_Syntax # So [39] SYMBOL FOR NULL..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
@@ -1038,12 +1130,14 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S
25F8..25FF ; Pattern_Syntax # Sm [8] UPPER LEFT TRIANGLE..LOWER RIGHT TRIANGLE
2600..266E ; Pattern_Syntax # So [111] BLACK SUN WITH RAYS..MUSIC NATURAL SIGN
266F ; Pattern_Syntax # Sm MUSIC SHARP SIGN
-2670..269D ; Pattern_Syntax # So [46] WEST SYRIAC CROSS..OUTLINED WHITE STAR
-269E..269F ; Pattern_Syntax # Cn [2] <reserved-269E>..<reserved-269F>
-26A0..26BC ; Pattern_Syntax # So [29] WARNING SIGN..SESQUIQUADRATE
-26BD..26BF ; Pattern_Syntax # Cn [3] <reserved-26BD>..<reserved-26BF>
-26C0..26C3 ; Pattern_Syntax # So [4] WHITE DRAUGHTS MAN..BLACK DRAUGHTS KING
-26C4..2700 ; Pattern_Syntax # Cn [61] <reserved-26C4>..<reserved-2700>
+2670..26CD ; Pattern_Syntax # So [94] WEST SYRIAC CROSS..DISABLED CAR
+26CE ; Pattern_Syntax # Cn <reserved-26CE>
+26CF..26E1 ; Pattern_Syntax # So [19] PICK..RESTRICTED LEFT ENTRY-2
+26E2 ; Pattern_Syntax # Cn <reserved-26E2>
+26E3 ; Pattern_Syntax # So HEAVY CIRCLE WITH STROKE AND TWO DOTS ABOVE
+26E4..26E7 ; Pattern_Syntax # Cn [4] <reserved-26E4>..<reserved-26E7>
+26E8..26FF ; Pattern_Syntax # So [24] BLACK CROSS ON SHIELD..WHITE FLAG WITH HORIZONTAL MIDDLE BLACK STRIPE
+2700 ; Pattern_Syntax # Cn <reserved-2700>
2701..2704 ; Pattern_Syntax # So [4] UPPER BLADE SCISSORS..WHITE SCISSORS
2705 ; Pattern_Syntax # Cn <reserved-2705>
2706..2709 ; Pattern_Syntax # So [4] TELEPHONE LOCATION SIGN..ENVELOPE
@@ -1056,9 +1150,7 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S
274E ; Pattern_Syntax # Cn <reserved-274E>
274F..2752 ; Pattern_Syntax # So [4] LOWER RIGHT DROP-SHADOWED WHITE SQUARE..UPPER RIGHT SHADOWED WHITE SQUARE
2753..2755 ; Pattern_Syntax # Cn [3] <reserved-2753>..<reserved-2755>
-2756 ; Pattern_Syntax # So BLACK DIAMOND MINUS WHITE X
-2757 ; Pattern_Syntax # Cn <reserved-2757>
-2758..275E ; Pattern_Syntax # So [7] LIGHT VERTICAL BAR..HEAVY DOUBLE COMMA QUOTATION MARK ORNAMENT
+2756..275E ; Pattern_Syntax # So [9] BLACK DIAMOND MINUS WHITE X..HEAVY DOUBLE COMMA QUOTATION MARK ORNAMENT
275F..2760 ; Pattern_Syntax # Cn [2] <reserved-275F>..<reserved-2760>
2761..2767 ; Pattern_Syntax # So [7] CURVED STEM PARAGRAPH SIGN ORNAMENT..ROTATED FLORAL HEART BULLET
2768 ; Pattern_Syntax # Ps MEDIUM LEFT PARENTHESIS ORNAMENT
@@ -1138,8 +1230,8 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S
2B45..2B46 ; Pattern_Syntax # So [2] LEFTWARDS QUADRUPLE ARROW..RIGHTWARDS QUADRUPLE ARROW
2B47..2B4C ; Pattern_Syntax # Sm [6] REVERSE TILDE OPERATOR ABOVE RIGHTWARDS ARROW..RIGHTWARDS ARROW ABOVE REVERSE TILDE OPERATOR
2B4D..2B4F ; Pattern_Syntax # Cn [3] <reserved-2B4D>..<reserved-2B4F>
-2B50..2B54 ; Pattern_Syntax # So [5] WHITE MEDIUM STAR..WHITE RIGHT-POINTING PENTAGON
-2B55..2BFF ; Pattern_Syntax # Cn [171] <reserved-2B55>..<reserved-2BFF>
+2B50..2B59 ; Pattern_Syntax # So [10] WHITE MEDIUM STAR..HEAVY CIRCLED SALTIRE
+2B5A..2BFF ; Pattern_Syntax # Cn [166] <reserved-2B5A>..<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
@@ -1171,8 +1263,8 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S
2E29 ; Pattern_Syntax # Pe RIGHT DOUBLE PARENTHESIS
2E2A..2E2E ; Pattern_Syntax # Po [5] TWO DOTS OVER ONE DOT PUNCTUATION..REVERSED QUESTION MARK
2E2F ; Pattern_Syntax # Lm VERTICAL TILDE
-2E30 ; Pattern_Syntax # Po RING POINT
-2E31..2E7F ; Pattern_Syntax # Cn [79] <reserved-2E31>..<reserved-2E7F>
+2E30..2E31 ; Pattern_Syntax # Po [2] RING POINT..WORD SEPARATOR MIDDLE DOT
+2E32..2E7F ; Pattern_Syntax # Cn [78] <reserved-2E32>..<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