7070436: Support Unicode 6.1.0 in JDK 8
Reviewed-by: okutsu
diff --git a/test/java/lang/Character/CheckProp.java b/test/java/lang/Character/CheckProp.java
index 92da9d3..db511f9 100644
--- a/test/java/lang/Character/CheckProp.java
+++ b/test/java/lang/Character/CheckProp.java
@@ -24,7 +24,7 @@
/**
* @test
- * @bug 7037261
+ * @bug 7037261 7070436
* @summary Check j.l.Character.isLowerCase/isUppercase/isAlphabetic/isIdeographic
*/
diff --git a/test/java/lang/Character/CheckScript.java b/test/java/lang/Character/CheckScript.java
index 3c441d6..3678aee 100644
--- a/test/java/lang/Character/CheckScript.java
+++ b/test/java/lang/Character/CheckScript.java
@@ -24,7 +24,7 @@
/**
* @test
- * @bug 6945564 6959267 7033561
+ * @bug 6945564 6959267 7033561 7070436
* @summary Check that the j.l.Character.UnicodeScript
*/
diff --git a/test/java/lang/Character/PropList.txt b/test/java/lang/Character/PropList.txt
index eeeb818..f9dcb2a 100644
--- a/test/java/lang/Character/PropList.txt
+++ b/test/java/lang/Character/PropList.txt
@@ -1,8 +1,8 @@
-# PropList-6.0.0.txt
-# Date: 2010-08-19, 00:48:28 GMT [MD]
+# PropList-6.1.0.txt
+# Date: 2011-11-30, 01:49:54 GMT [MD]
#
# Unicode Character Database
-# Copyright (c) 1991-2010 Unicode, Inc.
+# Copyright (c) 1991-2011 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
@@ -50,6 +50,7 @@
2212 ; Dash # Sm MINUS SIGN
2E17 ; Dash # Pd DOUBLE OBLIQUE HYPHEN
2E1A ; Dash # Pd HYPHEN WITH DIAERESIS
+2E3A..2E3B ; Dash # Pd [2] TWO-EM DASH..THREE-EM DASH
301C ; Dash # Pd WAVE DASH
3030 ; Dash # Pd WAVY DASH
30A0 ; Dash # Pd KATAKANA-HIRAGANA DOUBLE HYPHEN
@@ -58,7 +59,7 @@
FE63 ; Dash # Pd SMALL HYPHEN-MINUS
FF0D ; Dash # Pd FULLWIDTH HYPHEN-MINUS
-# Total code points: 25
+# Total code points: 27
# ================================================
@@ -158,6 +159,7 @@
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
+AAF0..AAF1 ; Terminal_Punctuation # Po [2] MEETEI MAYEK CHEIKHAN..MEETEI MAYEK AHANG KHUDAM
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
@@ -175,9 +177,11 @@
10B3A..10B3F ; Terminal_Punctuation # Po [6] TINY TWO DOTS OVER ONE DOT PUNCTUATION..LARGE ONE RING OVER TWO RINGS PUNCTUATION
11047..1104D ; Terminal_Punctuation # Po [7] BRAHMI DANDA..BRAHMI PUNCTUATION LOTUS
110BE..110C1 ; Terminal_Punctuation # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA
+11141..11143 ; Terminal_Punctuation # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK
+111C5..111C6 ; Terminal_Punctuation # Po [2] SHARADA DANDA..SHARADA DOUBLE DANDA
12470..12473 ; Terminal_Punctuation # Po [4] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL TRICOLON
-# Total code points: 169
+# Total code points: 176
# ================================================
@@ -320,8 +324,41 @@
1D7AA..1D7C2 ; Other_Math # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA
1D7C4..1D7CB ; Other_Math # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA
1D7CE..1D7FF ; Other_Math # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
+1EE00..1EE03 ; Other_Math # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL
+1EE05..1EE1F ; Other_Math # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF
+1EE21..1EE22 ; Other_Math # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM
+1EE24 ; Other_Math # Lo ARABIC MATHEMATICAL INITIAL HEH
+1EE27 ; Other_Math # Lo ARABIC MATHEMATICAL INITIAL HAH
+1EE29..1EE32 ; Other_Math # Lo [10] ARABIC MATHEMATICAL INITIAL YEH..ARABIC MATHEMATICAL INITIAL QAF
+1EE34..1EE37 ; Other_Math # Lo [4] ARABIC MATHEMATICAL INITIAL SHEEN..ARABIC MATHEMATICAL INITIAL KHAH
+1EE39 ; Other_Math # Lo ARABIC MATHEMATICAL INITIAL DAD
+1EE3B ; Other_Math # Lo ARABIC MATHEMATICAL INITIAL GHAIN
+1EE42 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED JEEM
+1EE47 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED HAH
+1EE49 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED YEH
+1EE4B ; Other_Math # Lo ARABIC MATHEMATICAL TAILED LAM
+1EE4D..1EE4F ; Other_Math # Lo [3] ARABIC MATHEMATICAL TAILED NOON..ARABIC MATHEMATICAL TAILED AIN
+1EE51..1EE52 ; Other_Math # Lo [2] ARABIC MATHEMATICAL TAILED SAD..ARABIC MATHEMATICAL TAILED QAF
+1EE54 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED SHEEN
+1EE57 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED KHAH
+1EE59 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED DAD
+1EE5B ; Other_Math # Lo ARABIC MATHEMATICAL TAILED GHAIN
+1EE5D ; Other_Math # Lo ARABIC MATHEMATICAL TAILED DOTLESS NOON
+1EE5F ; Other_Math # Lo ARABIC MATHEMATICAL TAILED DOTLESS QAF
+1EE61..1EE62 ; Other_Math # Lo [2] ARABIC MATHEMATICAL STRETCHED BEH..ARABIC MATHEMATICAL STRETCHED JEEM
+1EE64 ; Other_Math # Lo ARABIC MATHEMATICAL STRETCHED HEH
+1EE67..1EE6A ; Other_Math # Lo [4] ARABIC MATHEMATICAL STRETCHED HAH..ARABIC MATHEMATICAL STRETCHED KAF
+1EE6C..1EE72 ; Other_Math # Lo [7] ARABIC MATHEMATICAL STRETCHED MEEM..ARABIC MATHEMATICAL STRETCHED QAF
+1EE74..1EE77 ; Other_Math # Lo [4] ARABIC MATHEMATICAL STRETCHED SHEEN..ARABIC MATHEMATICAL STRETCHED KHAH
+1EE79..1EE7C ; Other_Math # Lo [4] ARABIC MATHEMATICAL STRETCHED DAD..ARABIC MATHEMATICAL STRETCHED DOTLESS BEH
+1EE7E ; Other_Math # Lo ARABIC MATHEMATICAL STRETCHED DOTLESS FEH
+1EE80..1EE89 ; Other_Math # Lo [10] ARABIC MATHEMATICAL LOOPED ALEF..ARABIC MATHEMATICAL LOOPED YEH
+1EE8B..1EE9B ; Other_Math # Lo [17] ARABIC MATHEMATICAL LOOPED LAM..ARABIC MATHEMATICAL LOOPED GHAIN
+1EEA1..1EEA3 ; Other_Math # Lo [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL
+1EEA5..1EEA9 ; Other_Math # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH
+1EEAB..1EEBB ; Other_Math # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
-# Total code points: 1217
+# Total code points: 1358
# ================================================
@@ -365,6 +402,8 @@
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
+08F0..08FE ; Other_Alphabetic # Mn [15] ARABIC OPEN FATHATAN..ARABIC DAMMA WITH DOT
0900..0902 ; Other_Alphabetic # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA
0903 ; Other_Alphabetic # Mc DEVANAGARI SIGN VISARGA
093A ; Other_Alphabetic # Mn DEVANAGARI VOWEL SIGN OE
@@ -525,6 +564,7 @@
1BA2..1BA5 ; Other_Alphabetic # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU
1BA6..1BA7 ; Other_Alphabetic # Mc [2] SUNDANESE VOWEL SIGN PANAELAENG..SUNDANESE VOWEL SIGN PANOLONG
1BA8..1BA9 ; Other_Alphabetic # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG
+1BAC..1BAD ; Other_Alphabetic # Mc [2] SUNDANESE CONSONANT SIGN PASANGAN MA..SUNDANESE CONSONANT SIGN PASANGAN WA
1BE7 ; Other_Alphabetic # Mc BATAK VOWEL SIGN E
1BE8..1BE9 ; Other_Alphabetic # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE
1BEA..1BEC ; Other_Alphabetic # Mc [3] BATAK VOWEL SIGN I..BATAK VOWEL SIGN O
@@ -534,9 +574,11 @@
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
+1CF2..1CF3 ; Other_Alphabetic # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED 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
+A674..A67B ; Other_Alphabetic # Mn [8] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC LETTER OMEGA
+A69F ; Other_Alphabetic # Mn 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
@@ -564,6 +606,10 @@
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
+AAEB ; Other_Alphabetic # Mc MEETEI MAYEK VOWEL SIGN II
+AAEC..AAED ; Other_Alphabetic # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI
+AAEE..AAEF ; Other_Alphabetic # Mc [2] MEETEI MAYEK VOWEL SIGN AU..MEETEI MAYEK VOWEL SIGN AAU
+AAF5 ; Other_Alphabetic # Mc MEETEI MAYEK VOWEL SIGN VISARGA
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
@@ -581,8 +627,23 @@
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
+11100..11102 ; Other_Alphabetic # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA
+11127..1112B ; Other_Alphabetic # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU
+1112C ; Other_Alphabetic # Mc CHAKMA VOWEL SIGN E
+1112D..11132 ; Other_Alphabetic # Mn [6] CHAKMA VOWEL SIGN AI..CHAKMA AU MARK
+11180..11181 ; Other_Alphabetic # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA
+11182 ; Other_Alphabetic # Mc SHARADA SIGN VISARGA
+111B3..111B5 ; Other_Alphabetic # Mc [3] SHARADA VOWEL SIGN AA..SHARADA VOWEL SIGN II
+111B6..111BE ; Other_Alphabetic # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O
+111BF ; Other_Alphabetic # Mc SHARADA VOWEL SIGN AU
+116AB ; Other_Alphabetic # Mn TAKRI SIGN ANUSVARA
+116AC ; Other_Alphabetic # Mc TAKRI SIGN VISARGA
+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
+16F51..16F7E ; Other_Alphabetic # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
-# Total code points: 795
+# Total code points: 922
# ================================================
@@ -591,16 +652,15 @@
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..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..FA6D ; Ideographic # Lo [62] CJK COMPATIBILITY IDEOGRAPH-FA30..CJK COMPATIBILITY IDEOGRAPH-FA6D
+4E00..9FCC ; Ideographic # Lo [20941] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCC
+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
2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
-# Total code points: 75630
+# Total code points: 75633
# ================================================
@@ -645,6 +705,7 @@
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
093C ; Diacritic # Mn DEVANAGARI SIGN NUKTA
094D ; Diacritic # Mn DEVANAGARI SIGN VIRAMA
0951..0954 ; Diacritic # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT
@@ -689,6 +750,7 @@
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
+1BAB ; Diacritic # Mn SUNDANESE SIGN VIRAMA
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
@@ -697,8 +759,8 @@
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
+1CF4 ; Diacritic # Mn VEDIC TONE CANDRA 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
1DFD..1DFF ; Diacritic # Mn [3] COMBINING ALMOST EQUAL TO BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
1FBD ; Diacritic # Sk GREEK KORONIS
@@ -709,7 +771,8 @@
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
+302A..302D ; Diacritic # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK
+302E..302F ; Diacritic # Mc [2] HANGUL SINGLE DOT 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
309B..309C ; Diacritic # Sk [2] KATAKANA-HIRAGANA VOICED SOUND MARK..KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
30FC ; Diacritic # Lm KATAKANA-HIRAGANA PROLONGED SOUND MARK
@@ -720,6 +783,7 @@
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
+A7F8..A7F9 ; Diacritic # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
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
@@ -732,6 +796,7 @@
AAC0 ; Diacritic # Lo TAI VIET TONE MAI NUENG
AAC1 ; Diacritic # Mn TAI VIET TONE MAI THO
AAC2 ; Diacritic # Lo TAI VIET TONE MAI SONG
+AAF6 ; Diacritic # Mn MEETEI MAYEK VIRAMA
ABEC ; Diacritic # Mc MEETEI MAYEK LUM IYEK
ABED ; Diacritic # Mn MEETEI MAYEK APUN IYEK
FB1E ; Diacritic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
@@ -742,13 +807,19 @@
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
+11133..11134 ; Diacritic # Mn [2] CHAKMA VIRAMA..CHAKMA MAAYYAA
+111C0 ; Diacritic # Mc SHARADA SIGN VIRAMA
+116B6 ; Diacritic # Mc TAKRI SIGN VIRAMA
+116B7 ; Diacritic # Mn TAKRI SIGN NUKTA
+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
-# Total code points: 639
+# Total code points: 693
# ================================================
@@ -758,6 +829,7 @@
07FA ; Extender # Lm NKO LAJANYALAN
0E46 ; Extender # Lm THAI CHARACTER MAIYAMOK
0EC6 ; Extender # Lm LAO KO LA
+180A ; Extender # Po MONGOLIAN NIRUGU
1843 ; Extender # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN
1AA7 ; Extender # Lm TAI THAM SIGN MAI YAMOK
1C36 ; Extender # Mn LEPCHA SIGN RAN
@@ -771,27 +843,33 @@
A9CF ; Extender # Lm JAVANESE PANGRANGKEP
AA70 ; Extender # Lm MYANMAR MODIFIER LETTER KHAMTI REDUPLICATION
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
-# Total code points: 28
+# Total code points: 31
# ================================================
+00AA ; Other_Lowercase # Lo FEMININE ORDINAL INDICATOR
+00BA ; Other_Lowercase # Lo MASCULINE ORDINAL INDICATOR
02B0..02B8 ; Other_Lowercase # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y
02C0..02C1 ; Other_Lowercase # Lm [2] MODIFIER LETTER GLOTTAL STOP..MODIFIER LETTER REVERSED GLOTTAL STOP
02E0..02E4 ; Other_Lowercase # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
0345 ; Other_Lowercase # Mn COMBINING GREEK YPOGEGRAMMENI
037A ; Other_Lowercase # Lm GREEK YPOGEGRAMMENI
-1D2C..1D61 ; Other_Lowercase # Lm [54] MODIFIER LETTER CAPITAL A..MODIFIER LETTER SMALL CHI
+1D2C..1D6A ; Other_Lowercase # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI
1D78 ; Other_Lowercase # Lm MODIFIER LETTER CYRILLIC EN
1D9B..1DBF ; Other_Lowercase # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA
-2090..2094 ; Other_Lowercase # Lm [5] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER SCHWA
+2071 ; Other_Lowercase # Lm SUPERSCRIPT LATIN SMALL LETTER I
+207F ; Other_Lowercase # Lm SUPERSCRIPT LATIN SMALL LETTER N
+2090..209C ; Other_Lowercase # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T
2170..217F ; Other_Lowercase # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND
24D0..24E9 ; Other_Lowercase # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z
-2C7D ; Other_Lowercase # Lm MODIFIER LETTER CAPITAL V
+2C7C..2C7D ; Other_Lowercase # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V
A770 ; Other_Lowercase # Lm MODIFIER LETTER US
+A7F8..A7F9 ; Other_Lowercase # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
-# Total code points: 159
+# Total code points: 183
# ================================================
@@ -838,11 +916,12 @@
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
+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
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
-# Total code points: 23
+# Total code points: 25
# ================================================
@@ -868,7 +947,7 @@
# ================================================
3400..4DB5 ; Unified_Ideograph # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
-4E00..9FCB ; Unified_Ideograph # Lo [20940] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCB
+4E00..9FCC ; Unified_Ideograph # Lo [20941] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCC
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
@@ -880,12 +959,13 @@
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
-# Total code points: 74616
+# Total code points: 74617
# ================================================
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
+17B4..17B5 ; Other_Default_Ignorable_Code_Point # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
2065..2069 ; Other_Default_Ignorable_Code_Point # Cn [5] <reserved-2065>..<reserved-2069>
3164 ; Other_Default_Ignorable_Code_Point # Lo HANGUL FILLER
FFA0 ; Other_Default_Ignorable_Code_Point # Lo HALFWIDTH HANGUL FILLER
@@ -895,7 +975,7 @@
E0080..E00FF ; Other_Default_Ignorable_Code_Point # Cn [128] <reserved-E0080>..<reserved-E00FF>
E01F0..E0FFF ; Other_Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
-# Total code points: 3778
+# Total code points: 3780
# ================================================
@@ -923,7 +1003,7 @@
03F3 ; Soft_Dotted # L& GREEK LETTER YOT
0456 ; Soft_Dotted # L& CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
0458 ; Soft_Dotted # L& CYRILLIC SMALL LETTER JE
-1D62 ; Soft_Dotted # L& LATIN SUBSCRIPT SMALL LETTER I
+1D62 ; Soft_Dotted # Lm LATIN SUBSCRIPT SMALL LETTER I
1D96 ; Soft_Dotted # L& LATIN SMALL LETTER I WITH RETROFLEX HOOK
1DA4 ; Soft_Dotted # Lm MODIFIER LETTER SMALL I WITH STROKE
1DA8 ; Soft_Dotted # Lm MODIFIER LETTER SMALL J WITH CROSSED-TAIL
@@ -931,7 +1011,7 @@
1ECB ; Soft_Dotted # L& LATIN SMALL LETTER I WITH DOT BELOW
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
+2C7C ; Soft_Dotted # Lm LATIN SUBSCRIPT SMALL LETTER J
1D422..1D423 ; Soft_Dotted # L& [2] MATHEMATICAL BOLD SMALL I..MATHEMATICAL BOLD SMALL J
1D456..1D457 ; Soft_Dotted # L& [2] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL ITALIC SMALL J
1D48A..1D48B ; Soft_Dotted # L& [2] MATHEMATICAL BOLD ITALIC SMALL I..MATHEMATICAL BOLD ITALIC SMALL J
@@ -1014,6 +1094,7 @@
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
@@ -1024,8 +1105,10 @@
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
-# Total code points: 76
+# Total code points: 83
# ================================================
@@ -1072,14 +1155,15 @@
007E ; Pattern_Syntax # Sm TILDE
00A1 ; Pattern_Syntax # Po INVERTED EXCLAMATION MARK
00A2..00A5 ; Pattern_Syntax # Sc [4] CENT SIGN..YEN SIGN
-00A6..00A7 ; Pattern_Syntax # So [2] BROKEN BAR..SECTION SIGN
+00A6 ; Pattern_Syntax # So BROKEN BAR
+00A7 ; Pattern_Syntax # Po SECTION SIGN
00A9 ; Pattern_Syntax # So COPYRIGHT SIGN
00AB ; Pattern_Syntax # Pi LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
00AC ; Pattern_Syntax # Sm NOT SIGN
00AE ; Pattern_Syntax # So REGISTERED SIGN
00B0 ; Pattern_Syntax # So DEGREE SIGN
00B1 ; Pattern_Syntax # Sm PLUS-MINUS SIGN
-00B6 ; Pattern_Syntax # So PILCROW SIGN
+00B6 ; Pattern_Syntax # Po PILCROW SIGN
00BB ; Pattern_Syntax # Pf RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
00BF ; Pattern_Syntax # Po INVERTED QUESTION MARK
00D7 ; Pattern_Syntax # Sm MULTIPLICATION SIGN
@@ -1173,11 +1257,7 @@
27C0..27C4 ; Pattern_Syntax # Sm [5] THREE DIMENSIONAL ANGLE..OPEN SUPERSET
27C5 ; Pattern_Syntax # Ps LEFT S-SHAPED BAG DELIMITER
27C6 ; Pattern_Syntax # Pe RIGHT S-SHAPED BAG DELIMITER
-27C7..27CA ; Pattern_Syntax # Sm [4] OR WITH DOT INSIDE..VERTICAL BAR WITH HORIZONTAL STROKE
-27CB ; Pattern_Syntax # Cn <reserved-27CB>
-27CC ; Pattern_Syntax # Sm LONG DIVISION
-27CD ; Pattern_Syntax # Cn <reserved-27CD>
-27CE..27E5 ; Pattern_Syntax # Sm [24] SQUARED LOGICAL AND..WHITE SQUARE WITH RIGHTWARDS TICK
+27C7..27E5 ; Pattern_Syntax # Sm [31] OR WITH DOT INSIDE..WHITE SQUARE WITH RIGHTWARDS TICK
27E6 ; Pattern_Syntax # Ps MATHEMATICAL LEFT WHITE SQUARE BRACKET
27E7 ; Pattern_Syntax # Pe MATHEMATICAL RIGHT WHITE SQUARE BRACKET
27E8 ; Pattern_Syntax # Ps MATHEMATICAL LEFT ANGLE BRACKET
@@ -1260,8 +1340,9 @@
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..2E31 ; Pattern_Syntax # Po [2] RING POINT..WORD SEPARATOR MIDDLE DOT
-2E32..2E7F ; Pattern_Syntax # Cn [78] <reserved-2E32>..<reserved-2E7F>
+2E30..2E39 ; Pattern_Syntax # Po [10] RING POINT..TOP HALF SECTION SIGN
+2E3A..2E3B ; Pattern_Syntax # Pd [2] TWO-EM DASH..THREE-EM DASH
+2E3C..2E7F ; Pattern_Syntax # Cn [68] <reserved-2E3C>..<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
diff --git a/test/java/lang/Character/PropertyValueAliases.txt b/test/java/lang/Character/PropertyValueAliases.txt
index 01f18a0..2f7bde2 100644
--- a/test/java/lang/Character/PropertyValueAliases.txt
+++ b/test/java/lang/Character/PropertyValueAliases.txt
@@ -1,15 +1,14 @@
-# PropertyValueAliases-6.0.0.txt
-# Date: 2010-07-17, 22:44:06 GMT [MD]
+# PropertyValueAliases-6.1.0.txt
+# Date: 2011-12-07, 23:40:57 GMT [MD]
#
# Unicode Character Database
-# Copyright (c) 1991-2010 Unicode, Inc.
+# Copyright (c) 1991-2011 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
#
# This file contains aliases for property values used in the UCD.
# These names can be used for XML formats of UCD data, for regular-expression
# property tests, and other programmatic textual descriptions of Unicode data.
-# For information on which properties are normative, see UCD.html.
#
# The names may be translated in appropriate environments, and additional
# aliases may be useful.
@@ -23,7 +22,6 @@
# property value name is used.
#
# Second Field: The second field is an abbreviated name.
-# If there is no abbreviated name available, the field is marked with "n/a".
#
# Third Field: The third field is a long name.
#
@@ -57,61 +55,62 @@
# ASCII_Hex_Digit (AHex)
-AHex; N ; No ; F ; False
-AHex; Y ; Yes ; T ; True
+AHex; N ; No ; F ; False
+AHex; Y ; Yes ; T ; True
# Age (age)
-age; n/a ; 1.1
-age; n/a ; 2.0
-age; n/a ; 2.1
-age; n/a ; 3.0
-age; n/a ; 3.1
-age; n/a ; 3.2
-age; n/a ; 4.0
-age; n/a ; 4.1
-age; n/a ; 5.0
-age; n/a ; 5.1
-age; n/a ; 5.2
-age; n/a ; 6.0
-age; n/a ; unassigned
+age; 1.1 ; V1_1
+age; 2.0 ; V2_0
+age; 2.1 ; V2_1
+age; 3.0 ; V3_0
+age; 3.1 ; V3_1
+age; 3.2 ; V3_2
+age; 4.0 ; V4_0
+age; 4.1 ; V4_1
+age; 5.0 ; V5_0
+age; 5.1 ; V5_1
+age; 5.2 ; V5_2
+age; 6.0 ; V6_0
+age; 6.1 ; V6_1
+age; NA ; Unassigned
# Alphabetic (Alpha)
-Alpha; N ; No ; F ; False
-Alpha; Y ; Yes ; T ; True
+Alpha; N ; No ; F ; False
+Alpha; Y ; Yes ; T ; True
# Bidi_Class (bc)
-bc ; AL ; Arabic_Letter
-bc ; AN ; Arabic_Number
-bc ; B ; Paragraph_Separator
-bc ; BN ; Boundary_Neutral
-bc ; CS ; Common_Separator
-bc ; EN ; European_Number
-bc ; ES ; European_Separator
-bc ; ET ; European_Terminator
-bc ; L ; Left_To_Right
-bc ; LRE ; Left_To_Right_Embedding
-bc ; LRO ; Left_To_Right_Override
-bc ; NSM ; Nonspacing_Mark
-bc ; ON ; Other_Neutral
-bc ; PDF ; Pop_Directional_Format
-bc ; R ; Right_To_Left
-bc ; RLE ; Right_To_Left_Embedding
-bc ; RLO ; Right_To_Left_Override
-bc ; S ; Segment_Separator
-bc ; WS ; White_Space
+bc ; AL ; Arabic_Letter
+bc ; AN ; Arabic_Number
+bc ; B ; Paragraph_Separator
+bc ; BN ; Boundary_Neutral
+bc ; CS ; Common_Separator
+bc ; EN ; European_Number
+bc ; ES ; European_Separator
+bc ; ET ; European_Terminator
+bc ; L ; Left_To_Right
+bc ; LRE ; Left_To_Right_Embedding
+bc ; LRO ; Left_To_Right_Override
+bc ; NSM ; Nonspacing_Mark
+bc ; ON ; Other_Neutral
+bc ; PDF ; Pop_Directional_Format
+bc ; R ; Right_To_Left
+bc ; RLE ; Right_To_Left_Embedding
+bc ; RLO ; Right_To_Left_Override
+bc ; S ; Segment_Separator
+bc ; WS ; White_Space
# Bidi_Control (Bidi_C)
-Bidi_C; N ; No ; F ; False
-Bidi_C; Y ; Yes ; T ; True
+Bidi_C; N ; No ; F ; False
+Bidi_C; Y ; Yes ; T ; True
# Bidi_Mirrored (Bidi_M)
-Bidi_M; N ; No ; F ; False
-Bidi_M; Y ; Yes ; T ; True
+Bidi_M; N ; No ; F ; False
+Bidi_M; Y ; Yes ; T ; True
# Bidi_Mirroring_Glyph (bmg)
@@ -119,239 +118,286 @@
# Block (blk)
-blk; n/a ; Aegean_Numbers
-blk; n/a ; Alchemical_Symbols
-blk; n/a ; Alphabetic_Presentation_Forms
-blk; n/a ; Ancient_Greek_Musical_Notation
-blk; n/a ; Ancient_Greek_Numbers
-blk; n/a ; Ancient_Symbols
-blk; n/a ; Arabic
-blk; n/a ; Arabic_Presentation_Forms_A ; Arabic_Presentation_Forms-A
-blk; n/a ; Arabic_Presentation_Forms_B
-blk; n/a ; Arabic_Supplement
-blk; n/a ; Armenian
-blk; n/a ; Arrows
-blk; n/a ; Avestan
-blk; n/a ; Balinese
-blk; n/a ; Bamum
-blk; n/a ; Bamum_Supplement
-blk; n/a ; Basic_Latin ; ASCII
-blk; n/a ; Batak
-blk; n/a ; Bengali
-blk; n/a ; Block_Elements
-blk; n/a ; Bopomofo
-blk; n/a ; Bopomofo_Extended
-blk; n/a ; Box_Drawing
-blk; n/a ; Brahmi
-blk; n/a ; Braille_Patterns
-blk; n/a ; Buginese
-blk; n/a ; Buhid
-blk; n/a ; Byzantine_Musical_Symbols
-blk; n/a ; Carian
-blk; n/a ; Cham
-blk; n/a ; Cherokee
-blk; n/a ; CJK_Compatibility
-blk; n/a ; CJK_Compatibility_Forms
-blk; n/a ; CJK_Compatibility_Ideographs
-blk; n/a ; CJK_Compatibility_Ideographs_Supplement
-blk; n/a ; CJK_Radicals_Supplement
-blk; n/a ; CJK_Strokes
-blk; n/a ; CJK_Symbols_And_Punctuation
-blk; n/a ; CJK_Unified_Ideographs
-blk; n/a ; CJK_Unified_Ideographs_Extension_A
-blk; n/a ; CJK_Unified_Ideographs_Extension_B
-blk; n/a ; CJK_Unified_Ideographs_Extension_C
-blk; n/a ; CJK_Unified_Ideographs_Extension_D
-blk; n/a ; Combining_Diacritical_Marks
-blk; n/a ; Combining_Diacritical_Marks_For_Symbols; Combining_Marks_For_Symbols
-blk; n/a ; Combining_Diacritical_Marks_Supplement
-blk; n/a ; Combining_Half_Marks
-blk; n/a ; Common_Indic_Number_Forms
-blk; n/a ; Control_Pictures
-blk; n/a ; Coptic
-blk; n/a ; Counting_Rod_Numerals
-blk; n/a ; Cuneiform
-blk; n/a ; Cuneiform_Numbers_And_Punctuation
-blk; n/a ; Currency_Symbols
-blk; n/a ; Cypriot_Syllabary
-blk; n/a ; Cyrillic
-blk; n/a ; Cyrillic_Extended_A
-blk; n/a ; Cyrillic_Extended_B
-blk; n/a ; Cyrillic_Supplement ; Cyrillic_Supplementary
-blk; n/a ; Deseret
-blk; n/a ; Devanagari
-blk; n/a ; Devanagari_Extended
-blk; n/a ; Dingbats
-blk; n/a ; Domino_Tiles
-blk; n/a ; Egyptian_Hieroglyphs
-blk; n/a ; Emoticons
-blk; n/a ; Enclosed_Alphanumeric_Supplement
-blk; n/a ; Enclosed_Alphanumerics
-blk; n/a ; Enclosed_CJK_Letters_And_Months
-blk; n/a ; Enclosed_Ideographic_Supplement
-blk; n/a ; Ethiopic
-blk; n/a ; Ethiopic_Extended
-blk; n/a ; Ethiopic_Extended_A
-blk; n/a ; Ethiopic_Supplement
-blk; n/a ; General_Punctuation
-blk; n/a ; Geometric_Shapes
-blk; n/a ; Georgian
-blk; n/a ; Georgian_Supplement
-blk; n/a ; Glagolitic
-blk; n/a ; Gothic
-blk; n/a ; Greek_And_Coptic ; Greek
-blk; n/a ; Greek_Extended
-blk; n/a ; Gujarati
-blk; n/a ; Gurmukhi
-blk; n/a ; Halfwidth_And_Fullwidth_Forms
-blk; n/a ; Hangul_Compatibility_Jamo
-blk; n/a ; Hangul_Jamo
-blk; n/a ; Hangul_Jamo_Extended_A
-blk; n/a ; Hangul_Jamo_Extended_B
-blk; n/a ; Hangul_Syllables
-blk; n/a ; Hanunoo
-blk; n/a ; Hebrew
-blk; n/a ; High_Private_Use_Surrogates
-blk; n/a ; High_Surrogates
-blk; n/a ; Hiragana
-blk; n/a ; Ideographic_Description_Characters
-blk; n/a ; Imperial_Aramaic
-blk; n/a ; Inscriptional_Pahlavi
-blk; n/a ; Inscriptional_Parthian
-blk; n/a ; IPA_Extensions
-blk; n/a ; Javanese
-blk; n/a ; Kaithi
-blk; n/a ; Kana_Supplement
-blk; n/a ; Kanbun
-blk; n/a ; Kangxi_Radicals
-blk; n/a ; Kannada
-blk; n/a ; Katakana
-blk; n/a ; Katakana_Phonetic_Extensions
-blk; n/a ; Kayah_Li
-blk; n/a ; Kharoshthi
-blk; n/a ; Khmer
-blk; n/a ; Khmer_Symbols
-blk; n/a ; Lao
-blk; n/a ; Latin_1_Supplement ; Latin_1
-blk; n/a ; Latin_Extended_A
-blk; n/a ; Latin_Extended_Additional
-blk; n/a ; Latin_Extended_B
-blk; n/a ; Latin_Extended_C
-blk; n/a ; Latin_Extended_D
-blk; n/a ; Lepcha
-blk; n/a ; Letterlike_Symbols
-blk; n/a ; Limbu
-blk; n/a ; Linear_B_Ideograms
-blk; n/a ; Linear_B_Syllabary
-blk; n/a ; Lisu
-blk; n/a ; Low_Surrogates
-blk; n/a ; Lycian
-blk; n/a ; Lydian
-blk; n/a ; Mahjong_Tiles
-blk; n/a ; Malayalam
-blk; n/a ; Mandaic
-blk; n/a ; Mathematical_Alphanumeric_Symbols
-blk; n/a ; Mathematical_Operators
-blk; n/a ; Meetei_Mayek
-blk; n/a ; Miscellaneous_Mathematical_Symbols_A
-blk; n/a ; Miscellaneous_Mathematical_Symbols_B
-blk; n/a ; Miscellaneous_Symbols
-blk; n/a ; Miscellaneous_Symbols_And_Arrows
-blk; n/a ; Miscellaneous_Symbols_And_Pictographs
-blk; n/a ; Miscellaneous_Technical
-blk; n/a ; Modifier_Tone_Letters
-blk; n/a ; Mongolian
-blk; n/a ; Musical_Symbols
-blk; n/a ; Myanmar
-blk; n/a ; Myanmar_Extended_A
-blk; n/a ; New_Tai_Lue
-blk; n/a ; NKo
-blk; n/a ; No_Block
-blk; n/a ; Number_Forms
-blk; n/a ; Ogham
-blk; n/a ; Ol_Chiki
-blk; n/a ; Old_Italic
-blk; n/a ; Old_Persian
-blk; n/a ; Old_South_Arabian
-blk; n/a ; Old_Turkic
-blk; n/a ; Optical_Character_Recognition
-blk; n/a ; Oriya
-blk; n/a ; Osmanya
-blk; n/a ; Phags_Pa
-blk; n/a ; Phaistos_Disc
-blk; n/a ; Phoenician
-blk; n/a ; Phonetic_Extensions
-blk; n/a ; Phonetic_Extensions_Supplement
-blk; n/a ; Playing_Cards
-blk; n/a ; Private_Use_Area ; Private_Use
-blk; n/a ; Rejang
-blk; n/a ; Rumi_Numeral_Symbols
-blk; n/a ; Runic
-blk; n/a ; Samaritan
-blk; n/a ; Saurashtra
-blk; n/a ; Shavian
-blk; n/a ; Sinhala
-blk; n/a ; Small_Form_Variants
-blk; n/a ; Spacing_Modifier_Letters
-blk; n/a ; Specials
-blk; n/a ; Sundanese
-blk; n/a ; Superscripts_And_Subscripts
-blk; n/a ; Supplemental_Arrows_A
-blk; n/a ; Supplemental_Arrows_B
-blk; n/a ; Supplemental_Mathematical_Operators
-blk; n/a ; Supplemental_Punctuation
-blk; n/a ; Supplementary_Private_Use_Area_A
-blk; n/a ; Supplementary_Private_Use_Area_B
-blk; n/a ; Syloti_Nagri
-blk; n/a ; Syriac
-blk; n/a ; Tagalog
-blk; n/a ; Tagbanwa
-blk; n/a ; Tags
-blk; n/a ; Tai_Le
-blk; n/a ; Tai_Tham
-blk; n/a ; Tai_Viet
-blk; n/a ; Tai_Xuan_Jing_Symbols
-blk; n/a ; Tamil
-blk; n/a ; Telugu
-blk; n/a ; Thaana
-blk; n/a ; Thai
-blk; n/a ; Tibetan
-blk; n/a ; Tifinagh
-blk; n/a ; Transport_And_Map_Symbols
-blk; n/a ; Ugaritic
-blk; n/a ; Unified_Canadian_Aboriginal_Syllabics; Canadian_Syllabics
-blk; n/a ; Unified_Canadian_Aboriginal_Syllabics_Extended
-blk; n/a ; Vai
-blk; n/a ; Variation_Selectors
-blk; n/a ; Variation_Selectors_Supplement
-blk; n/a ; Vedic_Extensions
-blk; n/a ; Vertical_Forms
-blk; n/a ; Yi_Radicals
-blk; n/a ; Yi_Syllables
-blk; n/a ; Yijing_Hexagram_Symbols
+blk; Aegean_Numbers ; Aegean_Numbers
+blk; Alchemical ; Alchemical_Symbols
+blk; Alphabetic_PF ; Alphabetic_Presentation_Forms
+blk; Ancient_Greek_Music ; Ancient_Greek_Musical_Notation
+blk; Ancient_Greek_Numbers ; Ancient_Greek_Numbers
+blk; Ancient_Symbols ; Ancient_Symbols
+blk; Arabic ; Arabic
+blk; Arabic_Ext_A ; Arabic_Extended_A
+blk; Arabic_Math ; Arabic_Mathematical_Alphabetic_Symbols
+blk; Arabic_PF_A ; Arabic_Presentation_Forms_A ; Arabic_Presentation_Forms-A
+blk; Arabic_PF_B ; Arabic_Presentation_Forms_B
+blk; Arabic_Sup ; Arabic_Supplement
+blk; Armenian ; Armenian
+blk; Arrows ; Arrows
+blk; ASCII ; Basic_Latin
+blk; Avestan ; Avestan
+blk; Balinese ; Balinese
+blk; Bamum ; Bamum
+blk; Bamum_Sup ; Bamum_Supplement
+blk; Batak ; Batak
+blk; Bengali ; Bengali
+blk; Block_Elements ; Block_Elements
+blk; Bopomofo ; Bopomofo
+blk; Bopomofo_Ext ; Bopomofo_Extended
+blk; Box_Drawing ; Box_Drawing
+blk; Brahmi ; Brahmi
+blk; Braille ; Braille_Patterns
+blk; Buginese ; Buginese
+blk; Buhid ; Buhid
+blk; Byzantine_Music ; Byzantine_Musical_Symbols
+blk; Carian ; Carian
+blk; Chakma ; Chakma
+blk; Cham ; Cham
+blk; Cherokee ; Cherokee
+blk; CJK ; CJK_Unified_Ideographs
+blk; CJK_Compat ; CJK_Compatibility
+blk; CJK_Compat_Forms ; CJK_Compatibility_Forms
+blk; CJK_Compat_Ideographs ; CJK_Compatibility_Ideographs
+blk; CJK_Compat_Ideographs_Sup ; CJK_Compatibility_Ideographs_Supplement
+blk; CJK_Ext_A ; CJK_Unified_Ideographs_Extension_A
+blk; CJK_Ext_B ; CJK_Unified_Ideographs_Extension_B
+blk; CJK_Ext_C ; CJK_Unified_Ideographs_Extension_C
+blk; CJK_Ext_D ; CJK_Unified_Ideographs_Extension_D
+blk; CJK_Radicals_Sup ; CJK_Radicals_Supplement
+blk; CJK_Strokes ; CJK_Strokes
+blk; CJK_Symbols ; CJK_Symbols_And_Punctuation
+blk; Compat_Jamo ; Hangul_Compatibility_Jamo
+blk; Control_Pictures ; Control_Pictures
+blk; Coptic ; Coptic
+blk; Counting_Rod ; Counting_Rod_Numerals
+blk; Cuneiform ; Cuneiform
+blk; Cuneiform_Numbers ; Cuneiform_Numbers_And_Punctuation
+blk; Currency_Symbols ; Currency_Symbols
+blk; Cypriot_Syllabary ; Cypriot_Syllabary
+blk; Cyrillic ; Cyrillic
+blk; Cyrillic_Ext_A ; Cyrillic_Extended_A
+blk; Cyrillic_Ext_B ; Cyrillic_Extended_B
+blk; Cyrillic_Sup ; Cyrillic_Supplement ; Cyrillic_Supplementary
+blk; Deseret ; Deseret
+blk; Devanagari ; Devanagari
+blk; Devanagari_Ext ; Devanagari_Extended
+blk; Diacriticals ; Combining_Diacritical_Marks
+blk; Diacriticals_For_Symbols ; Combining_Diacritical_Marks_For_Symbols; Combining_Marks_For_Symbols
+blk; Diacriticals_Sup ; Combining_Diacritical_Marks_Supplement
+blk; Dingbats ; Dingbats
+blk; Domino ; Domino_Tiles
+blk; Egyptian_Hieroglyphs ; Egyptian_Hieroglyphs
+blk; Emoticons ; Emoticons
+blk; Enclosed_Alphanum ; Enclosed_Alphanumerics
+blk; Enclosed_Alphanum_Sup ; Enclosed_Alphanumeric_Supplement
+blk; Enclosed_CJK ; Enclosed_CJK_Letters_And_Months
+blk; Enclosed_Ideographic_Sup ; Enclosed_Ideographic_Supplement
+blk; Ethiopic ; Ethiopic
+blk; Ethiopic_Ext ; Ethiopic_Extended
+blk; Ethiopic_Ext_A ; Ethiopic_Extended_A
+blk; Ethiopic_Sup ; Ethiopic_Supplement
+blk; Geometric_Shapes ; Geometric_Shapes
+blk; Georgian ; Georgian
+blk; Georgian_Sup ; Georgian_Supplement
+blk; Glagolitic ; Glagolitic
+blk; Gothic ; Gothic
+blk; Greek ; Greek_And_Coptic
+blk; Greek_Ext ; Greek_Extended
+blk; Gujarati ; Gujarati
+blk; Gurmukhi ; Gurmukhi
+blk; Half_And_Full_Forms ; Halfwidth_And_Fullwidth_Forms
+blk; Half_Marks ; Combining_Half_Marks
+blk; Hangul ; Hangul_Syllables
+blk; Hanunoo ; Hanunoo
+blk; Hebrew ; Hebrew
+blk; High_PU_Surrogates ; High_Private_Use_Surrogates
+blk; High_Surrogates ; High_Surrogates
+blk; Hiragana ; Hiragana
+blk; IDC ; Ideographic_Description_Characters
+blk; Imperial_Aramaic ; Imperial_Aramaic
+blk; Indic_Number_Forms ; Common_Indic_Number_Forms
+blk; Inscriptional_Pahlavi ; Inscriptional_Pahlavi
+blk; Inscriptional_Parthian ; Inscriptional_Parthian
+blk; IPA_Ext ; IPA_Extensions
+blk; Jamo ; Hangul_Jamo
+blk; Jamo_Ext_A ; Hangul_Jamo_Extended_A
+blk; Jamo_Ext_B ; Hangul_Jamo_Extended_B
+blk; Javanese ; Javanese
+blk; Kaithi ; Kaithi
+blk; Kana_Sup ; Kana_Supplement
+blk; Kanbun ; Kanbun
+blk; Kangxi ; Kangxi_Radicals
+blk; Kannada ; Kannada
+blk; Katakana ; Katakana
+blk; Katakana_Ext ; Katakana_Phonetic_Extensions
+blk; Kayah_Li ; Kayah_Li
+blk; Kharoshthi ; Kharoshthi
+blk; Khmer ; Khmer
+blk; Khmer_Symbols ; Khmer_Symbols
+blk; Lao ; Lao
+blk; Latin_1_Sup ; Latin_1_Supplement ; Latin_1
+blk; Latin_Ext_A ; Latin_Extended_A
+blk; Latin_Ext_Additional ; Latin_Extended_Additional
+blk; Latin_Ext_B ; Latin_Extended_B
+blk; Latin_Ext_C ; Latin_Extended_C
+blk; Latin_Ext_D ; Latin_Extended_D
+blk; Lepcha ; Lepcha
+blk; Letterlike_Symbols ; Letterlike_Symbols
+blk; Limbu ; Limbu
+blk; Linear_B_Ideograms ; Linear_B_Ideograms
+blk; Linear_B_Syllabary ; Linear_B_Syllabary
+blk; Lisu ; Lisu
+blk; Low_Surrogates ; Low_Surrogates
+blk; Lycian ; Lycian
+blk; Lydian ; Lydian
+blk; Mahjong ; Mahjong_Tiles
+blk; Malayalam ; Malayalam
+blk; Mandaic ; Mandaic
+blk; Math_Alphanum ; Mathematical_Alphanumeric_Symbols
+blk; Math_Operators ; Mathematical_Operators
+blk; Meetei_Mayek ; Meetei_Mayek
+blk; Meetei_Mayek_Ext ; Meetei_Mayek_Extensions
+blk; Meroitic_Cursive ; Meroitic_Cursive
+blk; Meroitic_Hieroglyphs ; Meroitic_Hieroglyphs
+blk; Miao ; Miao
+blk; Misc_Arrows ; Miscellaneous_Symbols_And_Arrows
+blk; Misc_Math_Symbols_A ; Miscellaneous_Mathematical_Symbols_A
+blk; Misc_Math_Symbols_B ; Miscellaneous_Mathematical_Symbols_B
+blk; Misc_Pictographs ; Miscellaneous_Symbols_And_Pictographs
+blk; Misc_Symbols ; Miscellaneous_Symbols
+blk; Misc_Technical ; Miscellaneous_Technical
+blk; Modifier_Letters ; Spacing_Modifier_Letters
+blk; Modifier_Tone_Letters ; Modifier_Tone_Letters
+blk; Mongolian ; Mongolian
+blk; Music ; Musical_Symbols
+blk; Myanmar ; Myanmar
+blk; Myanmar_Ext_A ; Myanmar_Extended_A
+blk; NB ; No_Block
+blk; New_Tai_Lue ; New_Tai_Lue
+blk; NKo ; NKo
+blk; Number_Forms ; Number_Forms
+blk; OCR ; Optical_Character_Recognition
+blk; Ogham ; Ogham
+blk; Ol_Chiki ; Ol_Chiki
+blk; Old_Italic ; Old_Italic
+blk; Old_Persian ; Old_Persian
+blk; Old_South_Arabian ; Old_South_Arabian
+blk; Old_Turkic ; Old_Turkic
+blk; Oriya ; Oriya
+blk; Osmanya ; Osmanya
+blk; Phags_Pa ; Phags_Pa
+blk; Phaistos ; Phaistos_Disc
+blk; Phoenician ; Phoenician
+blk; Phonetic_Ext ; Phonetic_Extensions
+blk; Phonetic_Ext_Sup ; Phonetic_Extensions_Supplement
+blk; Playing_Cards ; Playing_Cards
+blk; PUA ; Private_Use_Area ; Private_Use
+blk; Punctuation ; General_Punctuation
+blk; Rejang ; Rejang
+blk; Rumi ; Rumi_Numeral_Symbols
+blk; Runic ; Runic
+blk; Samaritan ; Samaritan
+blk; Saurashtra ; Saurashtra
+blk; Sharada ; Sharada
+blk; Shavian ; Shavian
+blk; Sinhala ; Sinhala
+blk; Small_Forms ; Small_Form_Variants
+blk; Sora_Sompeng ; Sora_Sompeng
+blk; Specials ; Specials
+blk; Sundanese ; Sundanese
+blk; Sundanese_Sup ; Sundanese_Supplement
+blk; Sup_Arrows_A ; Supplemental_Arrows_A
+blk; Sup_Arrows_B ; Supplemental_Arrows_B
+blk; Sup_Math_Operators ; Supplemental_Mathematical_Operators
+blk; Sup_PUA_A ; Supplementary_Private_Use_Area_A
+blk; Sup_PUA_B ; Supplementary_Private_Use_Area_B
+blk; Sup_Punctuation ; Supplemental_Punctuation
+blk; Super_And_Sub ; Superscripts_And_Subscripts
+blk; Syloti_Nagri ; Syloti_Nagri
+blk; Syriac ; Syriac
+blk; Tagalog ; Tagalog
+blk; Tagbanwa ; Tagbanwa
+blk; Tags ; Tags
+blk; Tai_Le ; Tai_Le
+blk; Tai_Tham ; Tai_Tham
+blk; Tai_Viet ; Tai_Viet
+blk; Tai_Xuan_Jing ; Tai_Xuan_Jing_Symbols
+blk; Takri ; Takri
+blk; Tamil ; Tamil
+blk; Telugu ; Telugu
+blk; Thaana ; Thaana
+blk; Thai ; Thai
+blk; Tibetan ; Tibetan
+blk; Tifinagh ; Tifinagh
+blk; Transport_And_Map ; Transport_And_Map_Symbols
+blk; UCAS ; Unified_Canadian_Aboriginal_Syllabics; Canadian_Syllabics
+blk; UCAS_Ext ; Unified_Canadian_Aboriginal_Syllabics_Extended
+blk; Ugaritic ; Ugaritic
+blk; Vai ; Vai
+blk; Vedic_Ext ; Vedic_Extensions
+blk; Vertical_Forms ; Vertical_Forms
+blk; VS ; Variation_Selectors
+blk; VS_Sup ; Variation_Selectors_Supplement
+blk; Yi_Radicals ; Yi_Radicals
+blk; Yi_Syllables ; Yi_Syllables
+blk; Yijing ; Yijing_Hexagram_Symbols
# Canonical_Combining_Class (ccc)
-ccc; 0; NR ; Not_Reordered
-ccc; 1; OV ; Overlay
-ccc; 7; NK ; Nukta
-ccc; 8; KV ; Kana_Voicing
-ccc; 9; VR ; Virama
-ccc; 200; ATBL ; Attached_Below_Left
-ccc; 202; ATB ; Attached_Below
-ccc; 214; ATA ; Attached_Above
-ccc; 216; ATAR ; Attached_Above_Right
-ccc; 218; BL ; Below_Left
-ccc; 220; B ; Below
-ccc; 222; BR ; Below_Right
-ccc; 224; L ; Left
-ccc; 226; R ; Right
-ccc; 228; AL ; Above_Left
-ccc; 230; A ; Above
-ccc; 232; AR ; Above_Right
-ccc; 233; DB ; Double_Below
-ccc; 234; DA ; Double_Above
-ccc; 240; IS ; Iota_Subscript
+ccc; 0; NR ; Not_Reordered
+ccc; 1; OV ; Overlay
+ccc; 7; NK ; Nukta
+ccc; 8; KV ; Kana_Voicing
+ccc; 9; VR ; Virama
+ccc; 10; CCC10 ; CCC10
+ccc; 11; CCC11 ; CCC11
+ccc; 12; CCC12 ; CCC12
+ccc; 13; CCC13 ; CCC13
+ccc; 14; CCC14 ; CCC14
+ccc; 15; CCC15 ; CCC15
+ccc; 16; CCC16 ; CCC16
+ccc; 17; CCC17 ; CCC17
+ccc; 18; CCC18 ; CCC18
+ccc; 19; CCC19 ; CCC19
+ccc; 20; CCC20 ; CCC20
+ccc; 21; CCC21 ; CCC21
+ccc; 22; CCC22 ; CCC22
+ccc; 23; CCC23 ; CCC23
+ccc; 24; CCC24 ; CCC24
+ccc; 25; CCC25 ; CCC25
+ccc; 26; CCC26 ; CCC26
+ccc; 27; CCC27 ; CCC27
+ccc; 28; CCC28 ; CCC28
+ccc; 29; CCC29 ; CCC29
+ccc; 30; CCC30 ; CCC30
+ccc; 31; CCC31 ; CCC31
+ccc; 32; CCC32 ; CCC32
+ccc; 33; CCC33 ; CCC33
+ccc; 34; CCC34 ; CCC34
+ccc; 35; CCC35 ; CCC35
+ccc; 36; CCC36 ; CCC36
+ccc; 84; CCC84 ; CCC84
+ccc; 91; CCC91 ; CCC91
+ccc; 103; CCC103 ; CCC103
+ccc; 107; CCC107 ; CCC107
+ccc; 118; CCC118 ; CCC118
+ccc; 122; CCC122 ; CCC122
+ccc; 129; CCC129 ; CCC129
+ccc; 130; CCC130 ; CCC130
+ccc; 132; CCC133 ; CCC133
+ccc; 200; ATBL ; Attached_Below_Left
+ccc; 202; ATB ; Attached_Below
+ccc; 214; ATA ; Attached_Above
+ccc; 216; ATAR ; Attached_Above_Right
+ccc; 218; BL ; Below_Left
+ccc; 220; B ; Below
+ccc; 222; BR ; Below_Right
+ccc; 224; L ; Left
+ccc; 226; R ; Right
+ccc; 228; AL ; Above_Left
+ccc; 230; A ; Above
+ccc; 232; AR ; Above_Right
+ccc; 233; DB ; Double_Below
+ccc; 234; DA ; Double_Above
+ccc; 240; IS ; Iota_Subscript
# Case_Folding (cf)
@@ -359,53 +405,53 @@
# Case_Ignorable (CI)
-CI ; N ; No ; F ; False
-CI ; Y ; Yes ; T ; True
+CI ; N ; No ; F ; False
+CI ; Y ; Yes ; T ; True
# Cased (Cased)
-Cased; N ; No ; F ; False
-Cased; Y ; Yes ; T ; True
+Cased; N ; No ; F ; False
+Cased; Y ; Yes ; T ; True
# Changes_When_Casefolded (CWCF)
-CWCF; N ; No ; F ; False
-CWCF; Y ; Yes ; T ; True
+CWCF; N ; No ; F ; False
+CWCF; Y ; Yes ; T ; True
# Changes_When_Casemapped (CWCM)
-CWCM; N ; No ; F ; False
-CWCM; Y ; Yes ; T ; True
+CWCM; N ; No ; F ; False
+CWCM; Y ; Yes ; T ; True
# Changes_When_Lowercased (CWL)
-CWL; N ; No ; F ; False
-CWL; Y ; Yes ; T ; True
+CWL; N ; No ; F ; False
+CWL; Y ; Yes ; T ; True
# Changes_When_NFKC_Casefolded (CWKCF)
-CWKCF; N ; No ; F ; False
-CWKCF; Y ; Yes ; T ; True
+CWKCF; N ; No ; F ; False
+CWKCF; Y ; Yes ; T ; True
# Changes_When_Titlecased (CWT)
-CWT; N ; No ; F ; False
-CWT; Y ; Yes ; T ; True
+CWT; N ; No ; F ; False
+CWT; Y ; Yes ; T ; True
# Changes_When_Uppercased (CWU)
-CWU; N ; No ; F ; False
-CWU; Y ; Yes ; T ; True
+CWU; N ; No ; F ; False
+CWU; Y ; Yes ; T ; True
# Composition_Exclusion (CE)
-CE ; N ; No ; F ; False
-CE ; Y ; Yes ; T ; True
+CE ; N ; No ; F ; False
+CE ; Y ; Yes ; T ; True
# Dash (Dash)
-Dash; N ; No ; F ; False
-Dash; Y ; Yes ; T ; True
+Dash; N ; No ; F ; False
+Dash; Y ; Yes ; T ; True
# Decomposition_Mapping (dm)
@@ -413,73 +459,73 @@
# Decomposition_Type (dt)
-dt ; Can ; Canonical ; can
-dt ; Com ; Compat ; com
-dt ; Enc ; Circle ; enc
-dt ; Fin ; Final ; fin
-dt ; Font ; font
-dt ; Fra ; Fraction ; fra
-dt ; Init ; Initial ; init
-dt ; Iso ; Isolated ; iso
-dt ; Med ; Medial ; med
-dt ; Nar ; Narrow ; nar
-dt ; Nb ; Nobreak ; nb
-dt ; None ; none
-dt ; Sml ; Small ; sml
-dt ; Sqr ; Square ; sqr
-dt ; Sub ; sub
-dt ; Sup ; Super ; sup
-dt ; Vert ; Vertical ; vert
-dt ; Wide ; wide
+dt ; Can ; Canonical ; can
+dt ; Com ; Compat ; com
+dt ; Enc ; Circle ; enc
+dt ; Fin ; Final ; fin
+dt ; Font ; Font ; font
+dt ; Fra ; Fraction ; fra
+dt ; Init ; Initial ; init
+dt ; Iso ; Isolated ; iso
+dt ; Med ; Medial ; med
+dt ; Nar ; Narrow ; nar
+dt ; Nb ; Nobreak ; nb
+dt ; None ; None ; none
+dt ; Sml ; Small ; sml
+dt ; Sqr ; Square ; sqr
+dt ; Sub ; Sub ; sub
+dt ; Sup ; Super ; sup
+dt ; Vert ; Vertical ; vert
+dt ; Wide ; Wide ; wide
# Default_Ignorable_Code_Point (DI)
-DI ; N ; No ; F ; False
-DI ; Y ; Yes ; T ; True
+DI ; N ; No ; F ; False
+DI ; Y ; Yes ; T ; True
# Deprecated (Dep)
-Dep; N ; No ; F ; False
-Dep; Y ; Yes ; T ; True
+Dep; N ; No ; F ; False
+Dep; Y ; Yes ; T ; True
# Diacritic (Dia)
-Dia; N ; No ; F ; False
-Dia; Y ; Yes ; T ; True
+Dia; N ; No ; F ; False
+Dia; Y ; Yes ; T ; True
# East_Asian_Width (ea)
-ea ; A ; Ambiguous
-ea ; F ; Fullwidth
-ea ; H ; Halfwidth
-ea ; N ; Neutral
-ea ; Na ; Narrow
-ea ; W ; Wide
+ea ; A ; Ambiguous
+ea ; F ; Fullwidth
+ea ; H ; Halfwidth
+ea ; N ; Neutral
+ea ; Na ; Narrow
+ea ; W ; Wide
# Expands_On_NFC (XO_NFC)
-XO_NFC; N ; No ; F ; False
-XO_NFC; Y ; Yes ; T ; True
+XO_NFC; N ; No ; F ; False
+XO_NFC; Y ; Yes ; T ; True
# Expands_On_NFD (XO_NFD)
-XO_NFD; N ; No ; F ; False
-XO_NFD; Y ; Yes ; T ; True
+XO_NFD; N ; No ; F ; False
+XO_NFD; Y ; Yes ; T ; True
# Expands_On_NFKC (XO_NFKC)
-XO_NFKC; N ; No ; F ; False
-XO_NFKC; Y ; Yes ; T ; True
+XO_NFKC; N ; No ; F ; False
+XO_NFKC; Y ; Yes ; T ; True
# Expands_On_NFKD (XO_NFKD)
-XO_NFKD; N ; No ; F ; False
-XO_NFKD; Y ; Yes ; T ; True
+XO_NFKD; N ; No ; F ; False
+XO_NFKD; Y ; Yes ; T ; True
# Extender (Ext)
-Ext; N ; No ; F ; False
-Ext; Y ; Yes ; T ; True
+Ext; N ; No ; F ; False
+Ext; Y ; Yes ; T ; True
# FC_NFKC_Closure (FC_NFKC)
@@ -487,118 +533,118 @@
# Full_Composition_Exclusion (Comp_Ex)
-Comp_Ex; N ; No ; F ; False
-Comp_Ex; Y ; Yes ; T ; True
+Comp_Ex; N ; No ; F ; False
+Comp_Ex; Y ; Yes ; T ; True
# General_Category (gc)
-gc ; C ; Other # Cc | Cf | Cn | Co | Cs
-gc ; Cc ; Control ; cntrl
-gc ; Cf ; Format
-gc ; Cn ; Unassigned
-gc ; Co ; Private_Use
-gc ; Cs ; Surrogate
-gc ; L ; Letter # Ll | Lm | Lo | Lt | Lu
-gc ; LC ; Cased_Letter # Ll | Lt | Lu
-gc ; Ll ; Lowercase_Letter
-gc ; Lm ; Modifier_Letter
-gc ; Lo ; Other_Letter
-gc ; Lt ; Titlecase_Letter
-gc ; Lu ; Uppercase_Letter
-gc ; M ; Mark # Mc | Me | Mn
-gc ; Mc ; Spacing_Mark
-gc ; Me ; Enclosing_Mark
-gc ; Mn ; Nonspacing_Mark
-gc ; N ; Number # Nd | Nl | No
-gc ; Nd ; Decimal_Number ; digit
-gc ; Nl ; Letter_Number
-gc ; No ; Other_Number
-gc ; P ; Punctuation ; punct # Pc | Pd | Pe | Pf | Pi | Po | Ps
-gc ; Pc ; Connector_Punctuation
-gc ; Pd ; Dash_Punctuation
-gc ; Pe ; Close_Punctuation
-gc ; Pf ; Final_Punctuation
-gc ; Pi ; Initial_Punctuation
-gc ; Po ; Other_Punctuation
-gc ; Ps ; Open_Punctuation
-gc ; S ; Symbol # Sc | Sk | Sm | So
-gc ; Sc ; Currency_Symbol
-gc ; Sk ; Modifier_Symbol
-gc ; Sm ; Math_Symbol
-gc ; So ; Other_Symbol
-gc ; Z ; Separator # Zl | Zp | Zs
-gc ; Zl ; Line_Separator
-gc ; Zp ; Paragraph_Separator
-gc ; Zs ; Space_Separator
+gc ; C ; Other # Cc | Cf | Cn | Co | Cs
+gc ; Cc ; Control ; cntrl
+gc ; Cf ; Format
+gc ; Cn ; Unassigned
+gc ; Co ; Private_Use
+gc ; Cs ; Surrogate
+gc ; L ; Letter # Ll | Lm | Lo | Lt | Lu
+gc ; LC ; Cased_Letter # Ll | Lt | Lu
+gc ; Ll ; Lowercase_Letter
+gc ; Lm ; Modifier_Letter
+gc ; Lo ; Other_Letter
+gc ; Lt ; Titlecase_Letter
+gc ; Lu ; Uppercase_Letter
+gc ; M ; Mark ; Combining_Mark # Mc | Me | Mn
+gc ; Mc ; Spacing_Mark
+gc ; Me ; Enclosing_Mark
+gc ; Mn ; Nonspacing_Mark
+gc ; N ; Number # Nd | Nl | No
+gc ; Nd ; Decimal_Number ; digit
+gc ; Nl ; Letter_Number
+gc ; No ; Other_Number
+gc ; P ; Punctuation ; punct # Pc | Pd | Pe | Pf | Pi | Po | Ps
+gc ; Pc ; Connector_Punctuation
+gc ; Pd ; Dash_Punctuation
+gc ; Pe ; Close_Punctuation
+gc ; Pf ; Final_Punctuation
+gc ; Pi ; Initial_Punctuation
+gc ; Po ; Other_Punctuation
+gc ; Ps ; Open_Punctuation
+gc ; S ; Symbol # Sc | Sk | Sm | So
+gc ; Sc ; Currency_Symbol
+gc ; Sk ; Modifier_Symbol
+gc ; Sm ; Math_Symbol
+gc ; So ; Other_Symbol
+gc ; Z ; Separator # Zl | Zp | Zs
+gc ; Zl ; Line_Separator
+gc ; Zp ; Paragraph_Separator
+gc ; Zs ; Space_Separator
# Grapheme_Base (Gr_Base)
-Gr_Base; N ; No ; F ; False
-Gr_Base; Y ; Yes ; T ; True
+Gr_Base; N ; No ; F ; False
+Gr_Base; Y ; Yes ; T ; True
# Grapheme_Cluster_Break (GCB)
-GCB; CN ; Control
-GCB; CR ; CR
-GCB; EX ; Extend
-GCB; L ; L
-GCB; LF ; LF
-GCB; LV ; LV
-GCB; LVT ; LVT
-GCB; PP ; Prepend
-GCB; SM ; SpacingMark
-GCB; T ; T
-GCB; V ; V
-GCB; XX ; Other
+GCB; CN ; Control
+GCB; CR ; CR
+GCB; EX ; Extend
+GCB; L ; L
+GCB; LF ; LF
+GCB; LV ; LV
+GCB; LVT ; LVT
+GCB; PP ; Prepend
+GCB; SM ; SpacingMark
+GCB; T ; T
+GCB; V ; V
+GCB; XX ; Other
# Grapheme_Extend (Gr_Ext)
-Gr_Ext; N ; No ; F ; False
-Gr_Ext; Y ; Yes ; T ; True
+Gr_Ext; N ; No ; F ; False
+Gr_Ext; Y ; Yes ; T ; True
# Grapheme_Link (Gr_Link)
-Gr_Link; N ; No ; F ; False
-Gr_Link; Y ; Yes ; T ; True
+Gr_Link; N ; No ; F ; False
+Gr_Link; Y ; Yes ; T ; True
# Hangul_Syllable_Type (hst)
-hst; L ; Leading_Jamo
-hst; LV ; LV_Syllable
-hst; LVT ; LVT_Syllable
-hst; NA ; Not_Applicable
-hst; T ; Trailing_Jamo
-hst; V ; Vowel_Jamo
+hst; L ; Leading_Jamo
+hst; LV ; LV_Syllable
+hst; LVT ; LVT_Syllable
+hst; NA ; Not_Applicable
+hst; T ; Trailing_Jamo
+hst; V ; Vowel_Jamo
# Hex_Digit (Hex)
-Hex; N ; No ; F ; False
-Hex; Y ; Yes ; T ; True
+Hex; N ; No ; F ; False
+Hex; Y ; Yes ; T ; True
# Hyphen (Hyphen)
-Hyphen; N ; No ; F ; False
-Hyphen; Y ; Yes ; T ; True
+Hyphen; N ; No ; F ; False
+Hyphen; Y ; Yes ; T ; True
# IDS_Binary_Operator (IDSB)
-IDSB; N ; No ; F ; False
-IDSB; Y ; Yes ; T ; True
+IDSB; N ; No ; F ; False
+IDSB; Y ; Yes ; T ; True
# IDS_Trinary_Operator (IDST)
-IDST; N ; No ; F ; False
-IDST; Y ; Yes ; T ; True
+IDST; N ; No ; F ; False
+IDST; Y ; Yes ; T ; True
# ID_Continue (IDC)
-IDC; N ; No ; F ; False
-IDC; Y ; Yes ; T ; True
+IDC; N ; No ; F ; False
+IDC; Y ; Yes ; T ; True
# ID_Start (IDS)
-IDS; N ; No ; F ; False
-IDS; Y ; Yes ; T ; True
+IDS; N ; No ; F ; False
+IDS; Y ; Yes ; T ; True
# ISO_Comment (isc)
@@ -606,188 +652,233 @@
# Ideographic (Ideo)
-Ideo; N ; No ; F ; False
-Ideo; Y ; Yes ; T ; True
+Ideo; N ; No ; F ; False
+Ideo; Y ; Yes ; T ; True
+
+# Indic_Matra_Category (InMC)
+
+InMC; Bottom ; Bottom
+InMC; Bottom_And_Right ; Bottom_And_Right
+InMC; Invisible ; Invisible
+InMC; Left ; Left
+InMC; Left_And_Right ; Left_And_Right
+InMC; NA ; NA
+InMC; Overstruck ; Overstruck
+InMC; Right ; Right
+InMC; Top ; Top
+InMC; Top_And_Bottom ; Top_And_Bottom
+InMC; Top_And_Bottom_And_Right ; Top_And_Bottom_And_Right
+InMC; Top_And_Left ; Top_And_Left
+InMC; Top_And_Left_And_Right ; Top_And_Left_And_Right
+InMC; Top_And_Right ; Top_And_Right
+InMC; Visual_Order_Left ; Visual_Order_Left
+
+# Indic_Syllabic_Category (InSC)
+
+InSC; Avagraha ; Avagraha
+InSC; Bindu ; Bindu
+InSC; Consonant ; Consonant
+InSC; Consonant_Dead ; Consonant_Dead
+InSC; Consonant_Final ; Consonant_Final
+InSC; Consonant_Head_Letter ; Consonant_Head_Letter
+InSC; Consonant_Medial ; Consonant_Medial
+InSC; Consonant_Placeholder ; Consonant_Placeholder
+InSC; Consonant_Repha ; Consonant_Repha
+InSC; Consonant_Subjoined ; Consonant_Subjoined
+InSC; Modifying_Letter ; Modifying_Letter
+InSC; Nukta ; Nukta
+InSC; Other ; Other
+InSC; Register_Shifter ; Register_Shifter
+InSC; Tone_Letter ; Tone_Letter
+InSC; Tone_Mark ; Tone_Mark
+InSC; Virama ; Virama
+InSC; Visarga ; Visarga
+InSC; Vowel ; Vowel
+InSC; Vowel_Dependent ; Vowel_Dependent
+InSC; Vowel_Independent ; Vowel_Independent
# Jamo_Short_Name (JSN)
# @missing: 0000..10FFFF; Jamo_Short_Name; <none>
-JSN; A ; A
-JSN; AE ; AE
-JSN; B ; B
-JSN; BB ; BB
-JSN; BS ; BS
-JSN; C ; C
-JSN; D ; D
-JSN; DD ; DD
-JSN; E ; E
-JSN; EO ; EO
-JSN; EU ; EU
-JSN; G ; G
-JSN; GG ; GG
-JSN; GS ; GS
-JSN; H ; H
-JSN; I ; I
-JSN; J ; J
-JSN; JJ ; JJ
-JSN; K ; K
-JSN; L ; L
-JSN; LB ; LB
-JSN; LG ; LG
-JSN; LH ; LH
-JSN; LM ; LM
-JSN; LP ; LP
-JSN; LS ; LS
-JSN; LT ; LT
-JSN; M ; M
-JSN; N ; N
-JSN; NG ; NG
-JSN; NH ; NH
-JSN; NJ ; NJ
-JSN; O ; O
-JSN; OE ; OE
-JSN; P ; P
-JSN; R ; R
-JSN; S ; S
-JSN; SS ; SS
-JSN; T ; T
-JSN; U ; U
-JSN; WA ; WA
-JSN; WAE ; WAE
-JSN; WE ; WE
-JSN; WEO ; WEO
-JSN; WI ; WI
-JSN; YA ; YA
-JSN; YAE ; YAE
-JSN; YE ; YE
-JSN; YEO ; YEO
-JSN; YI ; YI
-JSN; YO ; YO
-JSN; YU ; YU
+JSN; A ; A
+JSN; AE ; AE
+JSN; B ; B
+JSN; BB ; BB
+JSN; BS ; BS
+JSN; C ; C
+JSN; D ; D
+JSN; DD ; DD
+JSN; E ; E
+JSN; EO ; EO
+JSN; EU ; EU
+JSN; G ; G
+JSN; GG ; GG
+JSN; GS ; GS
+JSN; H ; H
+JSN; I ; I
+JSN; J ; J
+JSN; JJ ; JJ
+JSN; K ; K
+JSN; L ; L
+JSN; LB ; LB
+JSN; LG ; LG
+JSN; LH ; LH
+JSN; LM ; LM
+JSN; LP ; LP
+JSN; LS ; LS
+JSN; LT ; LT
+JSN; M ; M
+JSN; N ; N
+JSN; NG ; NG
+JSN; NH ; NH
+JSN; NJ ; NJ
+JSN; O ; O
+JSN; OE ; OE
+JSN; P ; P
+JSN; R ; R
+JSN; S ; S
+JSN; SS ; SS
+JSN; T ; T
+JSN; U ; U
+JSN; WA ; WA
+JSN; WAE ; WAE
+JSN; WE ; WE
+JSN; WEO ; WEO
+JSN; WI ; WI
+JSN; YA ; YA
+JSN; YAE ; YAE
+JSN; YE ; YE
+JSN; YEO ; YEO
+JSN; YI ; YI
+JSN; YO ; YO
+JSN; YU ; YU
# Join_Control (Join_C)
-Join_C; N ; No ; F ; False
-Join_C; Y ; Yes ; T ; True
+Join_C; N ; No ; F ; False
+Join_C; Y ; Yes ; T ; True
# Joining_Group (jg)
-jg ; n/a ; Ain
-jg ; n/a ; Alaph
-jg ; n/a ; Alef
-jg ; n/a ; Beh
-jg ; n/a ; Beth
-jg ; n/a ; Burushaski_Yeh_Barree
-jg ; n/a ; Dal
-jg ; n/a ; Dalath_Rish
-jg ; n/a ; E
-jg ; n/a ; Farsi_Yeh
-jg ; n/a ; Fe
-jg ; n/a ; Feh
-jg ; n/a ; Final_Semkath
-jg ; n/a ; Gaf
-jg ; n/a ; Gamal
-jg ; n/a ; Hah
-jg ; n/a ; He
-jg ; n/a ; Heh
-jg ; n/a ; Heh_Goal
-jg ; n/a ; Heth
-jg ; n/a ; Kaf
-jg ; n/a ; Kaph
-jg ; n/a ; Khaph
-jg ; n/a ; Knotted_Heh
-jg ; n/a ; Lam
-jg ; n/a ; Lamadh
-jg ; n/a ; Meem
-jg ; n/a ; Mim
-jg ; n/a ; No_Joining_Group
-jg ; n/a ; Noon
-jg ; n/a ; Nun
-jg ; n/a ; Nya
-jg ; n/a ; Pe
-jg ; n/a ; Qaf
-jg ; n/a ; Qaph
-jg ; n/a ; Reh
-jg ; n/a ; Reversed_Pe
-jg ; n/a ; Sad
-jg ; n/a ; Sadhe
-jg ; n/a ; Seen
-jg ; n/a ; Semkath
-jg ; n/a ; Shin
-jg ; n/a ; Swash_Kaf
-jg ; n/a ; Syriac_Waw
-jg ; n/a ; Tah
-jg ; n/a ; Taw
-jg ; n/a ; Teh_Marbuta
-jg ; n/a ; Teh_Marbuta_Goal ; Hamza_On_Heh_Goal
-jg ; n/a ; Teth
-jg ; n/a ; Waw
-jg ; n/a ; Yeh
-jg ; n/a ; Yeh_Barree
-jg ; n/a ; Yeh_With_Tail
-jg ; n/a ; Yudh
-jg ; n/a ; Yudh_He
-jg ; n/a ; Zain
-jg ; n/a ; Zhain
+jg ; Ain ; Ain
+jg ; Alaph ; Alaph
+jg ; Alef ; Alef
+jg ; Beh ; Beh
+jg ; Beth ; Beth
+jg ; Burushaski_Yeh_Barree ; Burushaski_Yeh_Barree
+jg ; Dal ; Dal
+jg ; Dalath_Rish ; Dalath_Rish
+jg ; E ; E
+jg ; Farsi_Yeh ; Farsi_Yeh
+jg ; Fe ; Fe
+jg ; Feh ; Feh
+jg ; Final_Semkath ; Final_Semkath
+jg ; Gaf ; Gaf
+jg ; Gamal ; Gamal
+jg ; Hah ; Hah
+jg ; He ; He
+jg ; Heh ; Heh
+jg ; Heh_Goal ; Heh_Goal
+jg ; Heth ; Heth
+jg ; Kaf ; Kaf
+jg ; Kaph ; Kaph
+jg ; Khaph ; Khaph
+jg ; Knotted_Heh ; Knotted_Heh
+jg ; Lam ; Lam
+jg ; Lamadh ; Lamadh
+jg ; Meem ; Meem
+jg ; Mim ; Mim
+jg ; No_Joining_Group ; No_Joining_Group
+jg ; Noon ; Noon
+jg ; Nun ; Nun
+jg ; Nya ; Nya
+jg ; Pe ; Pe
+jg ; Qaf ; Qaf
+jg ; Qaph ; Qaph
+jg ; Reh ; Reh
+jg ; Reversed_Pe ; Reversed_Pe
+jg ; Rohingya_Yeh ; Rohingya_Yeh
+jg ; Sad ; Sad
+jg ; Sadhe ; Sadhe
+jg ; Seen ; Seen
+jg ; Semkath ; Semkath
+jg ; Shin ; Shin
+jg ; Swash_Kaf ; Swash_Kaf
+jg ; Syriac_Waw ; Syriac_Waw
+jg ; Tah ; Tah
+jg ; Taw ; Taw
+jg ; Teh_Marbuta ; Teh_Marbuta
+jg ; Teh_Marbuta_Goal ; Hamza_On_Heh_Goal
+jg ; Teth ; Teth
+jg ; Waw ; Waw
+jg ; Yeh ; Yeh
+jg ; Yeh_Barree ; Yeh_Barree
+jg ; Yeh_With_Tail ; Yeh_With_Tail
+jg ; Yudh ; Yudh
+jg ; Yudh_He ; Yudh_He
+jg ; Zain ; Zain
+jg ; Zhain ; Zhain
# Joining_Type (jt)
-jt ; C ; Join_Causing
-jt ; D ; Dual_Joining
-jt ; L ; Left_Joining
-jt ; R ; Right_Joining
-jt ; T ; Transparent
-jt ; U ; Non_Joining
+jt ; C ; Join_Causing
+jt ; D ; Dual_Joining
+jt ; L ; Left_Joining
+jt ; R ; Right_Joining
+jt ; T ; Transparent
+jt ; U ; Non_Joining
# Line_Break (lb)
-lb ; AI ; Ambiguous
-lb ; AL ; Alphabetic
-lb ; B2 ; Break_Both
-lb ; BA ; Break_After
-lb ; BB ; Break_Before
-lb ; BK ; Mandatory_Break
-lb ; CB ; Contingent_Break
-lb ; CL ; Close_Punctuation
-lb ; CM ; Combining_Mark
-lb ; CP ; Close_Parenthesis
-lb ; CR ; Carriage_Return
-lb ; EX ; Exclamation
-lb ; GL ; Glue
-lb ; H2 ; H2
-lb ; H3 ; H3
-lb ; HY ; Hyphen
-lb ; ID ; Ideographic
-lb ; IN ; Inseparable ; Inseperable
-lb ; IS ; Infix_Numeric
-lb ; JL ; JL
-lb ; JT ; JT
-lb ; JV ; JV
-lb ; LF ; Line_Feed
-lb ; NL ; Next_Line
-lb ; NS ; Nonstarter
-lb ; NU ; Numeric
-lb ; OP ; Open_Punctuation
-lb ; PO ; Postfix_Numeric
-lb ; PR ; Prefix_Numeric
-lb ; QU ; Quotation
-lb ; SA ; Complex_Context
-lb ; SG ; Surrogate
-lb ; SP ; Space
-lb ; SY ; Break_Symbols
-lb ; WJ ; Word_Joiner
-lb ; XX ; Unknown
-lb ; ZW ; ZWSpace
+lb ; AI ; Ambiguous
+lb ; AL ; Alphabetic
+lb ; B2 ; Break_Both
+lb ; BA ; Break_After
+lb ; BB ; Break_Before
+lb ; BK ; Mandatory_Break
+lb ; CB ; Contingent_Break
+lb ; CJ ; Conditional_Japanese_Starter
+lb ; CL ; Close_Punctuation
+lb ; CM ; Combining_Mark
+lb ; CP ; Close_Parenthesis
+lb ; CR ; Carriage_Return
+lb ; EX ; Exclamation
+lb ; GL ; Glue
+lb ; H2 ; H2
+lb ; H3 ; H3
+lb ; HL ; Hebrew_Letter
+lb ; HY ; Hyphen
+lb ; ID ; Ideographic
+lb ; IN ; Inseparable ; Inseperable
+lb ; IS ; Infix_Numeric
+lb ; JL ; JL
+lb ; JT ; JT
+lb ; JV ; JV
+lb ; LF ; Line_Feed
+lb ; NL ; Next_Line
+lb ; NS ; Nonstarter
+lb ; NU ; Numeric
+lb ; OP ; Open_Punctuation
+lb ; PO ; Postfix_Numeric
+lb ; PR ; Prefix_Numeric
+lb ; QU ; Quotation
+lb ; SA ; Complex_Context
+lb ; SG ; Surrogate
+lb ; SP ; Space
+lb ; SY ; Break_Symbols
+lb ; WJ ; Word_Joiner
+lb ; XX ; Unknown
+lb ; ZW ; ZWSpace
# Logical_Order_Exception (LOE)
-LOE; N ; No ; F ; False
-LOE; Y ; Yes ; T ; True
+LOE; N ; No ; F ; False
+LOE; Y ; Yes ; T ; True
# Lowercase (Lower)
-Lower; N ; No ; F ; False
-Lower; Y ; Yes ; T ; True
+Lower; N ; No ; F ; False
+Lower; Y ; Yes ; T ; True
# Lowercase_Mapping (lc)
@@ -795,19 +886,19 @@
# Math (Math)
-Math; N ; No ; F ; False
-Math; Y ; Yes ; T ; True
+Math; N ; No ; F ; False
+Math; Y ; Yes ; T ; True
# NFC_Quick_Check (NFC_QC)
-NFC_QC; M ; Maybe
-NFC_QC; N ; No
-NFC_QC; Y ; Yes
+NFC_QC; M ; Maybe
+NFC_QC; N ; No
+NFC_QC; Y ; Yes
# NFD_Quick_Check (NFD_QC)
-NFD_QC; N ; No
-NFD_QC; Y ; Yes
+NFD_QC; N ; No
+NFD_QC; Y ; Yes
# NFKC_Casefold (NFKC_CF)
@@ -815,14 +906,14 @@
# NFKC_Quick_Check (NFKC_QC)
-NFKC_QC; M ; Maybe
-NFKC_QC; N ; No
-NFKC_QC; Y ; Yes
+NFKC_QC; M ; Maybe
+NFKC_QC; N ; No
+NFKC_QC; Y ; Yes
# NFKD_Quick_Check (NFKD_QC)
-NFKD_QC; N ; No
-NFKD_QC; Y ; Yes
+NFKD_QC; N ; No
+NFKD_QC; Y ; Yes
# Name (na)
@@ -834,15 +925,15 @@
# Noncharacter_Code_Point (NChar)
-NChar; N ; No ; F ; False
-NChar; Y ; Yes ; T ; True
+NChar; N ; No ; F ; False
+NChar; Y ; Yes ; T ; True
# Numeric_Type (nt)
-nt ; De ; Decimal
-nt ; Di ; Digit
-nt ; None ; None
-nt ; Nu ; Numeric
+nt ; De ; Decimal
+nt ; Di ; Digit
+nt ; None ; None
+nt ; Nu ; Numeric
# Numeric_Value (nv)
@@ -850,186 +941,197 @@
# Other_Alphabetic (OAlpha)
-OAlpha; N ; No ; F ; False
-OAlpha; Y ; Yes ; T ; True
+OAlpha; N ; No ; F ; False
+OAlpha; Y ; Yes ; T ; True
# Other_Default_Ignorable_Code_Point (ODI)
-ODI; N ; No ; F ; False
-ODI; Y ; Yes ; T ; True
+ODI; N ; No ; F ; False
+ODI; Y ; Yes ; T ; True
# Other_Grapheme_Extend (OGr_Ext)
-OGr_Ext; N ; No ; F ; False
-OGr_Ext; Y ; Yes ; T ; True
+OGr_Ext; N ; No ; F ; False
+OGr_Ext; Y ; Yes ; T ; True
# Other_ID_Continue (OIDC)
-OIDC; N ; No ; F ; False
-OIDC; Y ; Yes ; T ; True
+OIDC; N ; No ; F ; False
+OIDC; Y ; Yes ; T ; True
# Other_ID_Start (OIDS)
-OIDS; N ; No ; F ; False
-OIDS; Y ; Yes ; T ; True
+OIDS; N ; No ; F ; False
+OIDS; Y ; Yes ; T ; True
# Other_Lowercase (OLower)
-OLower; N ; No ; F ; False
-OLower; Y ; Yes ; T ; True
+OLower; N ; No ; F ; False
+OLower; Y ; Yes ; T ; True
# Other_Math (OMath)
-OMath; N ; No ; F ; False
-OMath; Y ; Yes ; T ; True
+OMath; N ; No ; F ; False
+OMath; Y ; Yes ; T ; True
# Other_Uppercase (OUpper)
-OUpper; N ; No ; F ; False
-OUpper; Y ; Yes ; T ; True
+OUpper; N ; No ; F ; False
+OUpper; Y ; Yes ; T ; True
# Pattern_Syntax (Pat_Syn)
-Pat_Syn; N ; No ; F ; False
-Pat_Syn; Y ; Yes ; T ; True
+Pat_Syn; N ; No ; F ; False
+Pat_Syn; Y ; Yes ; T ; True
# Pattern_White_Space (Pat_WS)
-Pat_WS; N ; No ; F ; False
-Pat_WS; Y ; Yes ; T ; True
+Pat_WS; N ; No ; F ; False
+Pat_WS; Y ; Yes ; T ; True
# Quotation_Mark (QMark)
-QMark; N ; No ; F ; False
-QMark; Y ; Yes ; T ; True
+QMark; N ; No ; F ; False
+QMark; Y ; Yes ; T ; True
# Radical (Radical)
-Radical; N ; No ; F ; False
-Radical; Y ; Yes ; T ; True
+Radical; N ; No ; F ; False
+Radical; Y ; Yes ; T ; True
# STerm (STerm)
-STerm; N ; No ; F ; False
-STerm; Y ; Yes ; T ; True
+STerm; N ; No ; F ; False
+STerm; Y ; Yes ; T ; True
# Script (sc)
-sc ; Arab ; Arabic
-sc ; Armi ; Imperial_Aramaic
-sc ; Armn ; Armenian
-sc ; Avst ; Avestan
-sc ; Bali ; Balinese
-sc ; Bamu ; Bamum
-sc ; Batk ; Batak
-sc ; Beng ; Bengali
-sc ; Bopo ; Bopomofo
-sc ; Brah ; Brahmi
-sc ; Brai ; Braille
-sc ; Bugi ; Buginese
-sc ; Buhd ; Buhid
-sc ; Cans ; Canadian_Aboriginal
-sc ; Cari ; Carian
-sc ; Cham ; Cham
-sc ; Cher ; Cherokee
-sc ; Copt ; Coptic ; Qaac
-sc ; Cprt ; Cypriot
-sc ; Cyrl ; Cyrillic
-sc ; Deva ; Devanagari
-sc ; Dsrt ; Deseret
-sc ; Egyp ; Egyptian_Hieroglyphs
-sc ; Ethi ; Ethiopic
-sc ; Geor ; Georgian
-sc ; Glag ; Glagolitic
-sc ; Goth ; Gothic
-sc ; Grek ; Greek
-sc ; Gujr ; Gujarati
-sc ; Guru ; Gurmukhi
-sc ; Hang ; Hangul
-sc ; Hani ; Han
-sc ; Hano ; Hanunoo
-sc ; Hebr ; Hebrew
-sc ; Hira ; Hiragana
-sc ; Hrkt ; Katakana_Or_Hiragana
-sc ; Ital ; Old_Italic
-sc ; Java ; Javanese
-sc ; Kali ; Kayah_Li
-sc ; Kana ; Katakana
-sc ; Khar ; Kharoshthi
-sc ; Khmr ; Khmer
-sc ; Knda ; Kannada
-sc ; Kthi ; Kaithi
-sc ; Lana ; Tai_Tham
-sc ; Laoo ; Lao
-sc ; Latn ; Latin
-sc ; Lepc ; Lepcha
-sc ; Limb ; Limbu
-sc ; Linb ; Linear_B
-sc ; Lisu ; Lisu
-sc ; Lyci ; Lycian
-sc ; Lydi ; Lydian
-sc ; Mand ; Mandaic
-sc ; Mlym ; Malayalam
-sc ; Mong ; Mongolian
-sc ; Mtei ; Meetei_Mayek
-sc ; Mymr ; Myanmar
-sc ; Nkoo ; Nko
-sc ; Ogam ; Ogham
-sc ; Olck ; Ol_Chiki
-sc ; Orkh ; Old_Turkic
-sc ; Orya ; Oriya
-sc ; Osma ; Osmanya
-sc ; Phag ; Phags_Pa
-sc ; Phli ; Inscriptional_Pahlavi
-sc ; Phnx ; Phoenician
-sc ; Prti ; Inscriptional_Parthian
-sc ; Rjng ; Rejang
-sc ; Runr ; Runic
-sc ; Samr ; Samaritan
-sc ; Sarb ; Old_South_Arabian
-sc ; Saur ; Saurashtra
-sc ; Shaw ; Shavian
-sc ; Sinh ; Sinhala
-sc ; Sund ; Sundanese
-sc ; Sylo ; Syloti_Nagri
-sc ; Syrc ; Syriac
-sc ; Tagb ; Tagbanwa
-sc ; Tale ; Tai_Le
-sc ; Talu ; New_Tai_Lue
-sc ; Taml ; Tamil
-sc ; Tavt ; Tai_Viet
-sc ; Telu ; Telugu
-sc ; Tfng ; Tifinagh
-sc ; Tglg ; Tagalog
-sc ; Thaa ; Thaana
-sc ; Thai ; Thai
-sc ; Tibt ; Tibetan
-sc ; Ugar ; Ugaritic
-sc ; Vaii ; Vai
-sc ; Xpeo ; Old_Persian
-sc ; Xsux ; Cuneiform
-sc ; Yiii ; Yi
-sc ; Zinh ; Inherited ; Qaai
-sc ; Zyyy ; Common
-sc ; Zzzz ; Unknown
+sc ; Arab ; Arabic
+sc ; Armi ; Imperial_Aramaic
+sc ; Armn ; Armenian
+sc ; Avst ; Avestan
+sc ; Bali ; Balinese
+sc ; Bamu ; Bamum
+sc ; Batk ; Batak
+sc ; Beng ; Bengali
+sc ; Bopo ; Bopomofo
+sc ; Brah ; Brahmi
+sc ; Brai ; Braille
+sc ; Bugi ; Buginese
+sc ; Buhd ; Buhid
+sc ; Cakm ; Chakma
+sc ; Cans ; Canadian_Aboriginal
+sc ; Cari ; Carian
+sc ; Cham ; Cham
+sc ; Cher ; Cherokee
+sc ; Copt ; Coptic ; Qaac
+sc ; Cprt ; Cypriot
+sc ; Cyrl ; Cyrillic
+sc ; Deva ; Devanagari
+sc ; Dsrt ; Deseret
+sc ; Egyp ; Egyptian_Hieroglyphs
+sc ; Ethi ; Ethiopic
+sc ; Geor ; Georgian
+sc ; Glag ; Glagolitic
+sc ; Goth ; Gothic
+sc ; Grek ; Greek
+sc ; Gujr ; Gujarati
+sc ; Guru ; Gurmukhi
+sc ; Hang ; Hangul
+sc ; Hani ; Han
+sc ; Hano ; Hanunoo
+sc ; Hebr ; Hebrew
+sc ; Hira ; Hiragana
+sc ; Hrkt ; Katakana_Or_Hiragana
+sc ; Ital ; Old_Italic
+sc ; Java ; Javanese
+sc ; Kali ; Kayah_Li
+sc ; Kana ; Katakana
+sc ; Khar ; Kharoshthi
+sc ; Khmr ; Khmer
+sc ; Knda ; Kannada
+sc ; Kthi ; Kaithi
+sc ; Lana ; Tai_Tham
+sc ; Laoo ; Lao
+sc ; Latn ; Latin
+sc ; Lepc ; Lepcha
+sc ; Limb ; Limbu
+sc ; Linb ; Linear_B
+sc ; Lisu ; Lisu
+sc ; Lyci ; Lycian
+sc ; Lydi ; Lydian
+sc ; Mand ; Mandaic
+sc ; Merc ; Meroitic_Cursive
+sc ; Mero ; Meroitic_Hieroglyphs
+sc ; Mlym ; Malayalam
+sc ; Mong ; Mongolian
+sc ; Mtei ; Meetei_Mayek
+sc ; Mymr ; Myanmar
+sc ; Nkoo ; Nko
+sc ; Ogam ; Ogham
+sc ; Olck ; Ol_Chiki
+sc ; Orkh ; Old_Turkic
+sc ; Orya ; Oriya
+sc ; Osma ; Osmanya
+sc ; Phag ; Phags_Pa
+sc ; Phli ; Inscriptional_Pahlavi
+sc ; Phnx ; Phoenician
+sc ; Plrd ; Miao
+sc ; Prti ; Inscriptional_Parthian
+sc ; Rjng ; Rejang
+sc ; Runr ; Runic
+sc ; Samr ; Samaritan
+sc ; Sarb ; Old_South_Arabian
+sc ; Saur ; Saurashtra
+sc ; Shaw ; Shavian
+sc ; Shrd ; Sharada
+sc ; Sinh ; Sinhala
+sc ; Sora ; Sora_Sompeng
+sc ; Sund ; Sundanese
+sc ; Sylo ; Syloti_Nagri
+sc ; Syrc ; Syriac
+sc ; Tagb ; Tagbanwa
+sc ; Takr ; Takri
+sc ; Tale ; Tai_Le
+sc ; Talu ; New_Tai_Lue
+sc ; Taml ; Tamil
+sc ; Tavt ; Tai_Viet
+sc ; Telu ; Telugu
+sc ; Tfng ; Tifinagh
+sc ; Tglg ; Tagalog
+sc ; Thaa ; Thaana
+sc ; Thai ; Thai
+sc ; Tibt ; Tibetan
+sc ; Ugar ; Ugaritic
+sc ; Vaii ; Vai
+sc ; Xpeo ; Old_Persian
+sc ; Xsux ; Cuneiform
+sc ; Yiii ; Yi
+sc ; Zinh ; Inherited ; Qaai
+sc ; Zyyy ; Common
+sc ; Zzzz ; Unknown
+
+# Script_Extensions (scx)
+
+# @missing: 0000..10FFFF; Script_Extensions; <script>
# Sentence_Break (SB)
-SB ; AT ; ATerm
-SB ; CL ; Close
-SB ; CR ; CR
-SB ; EX ; Extend
-SB ; FO ; Format
-SB ; LE ; OLetter
-SB ; LF ; LF
-SB ; LO ; Lower
-SB ; NU ; Numeric
-SB ; SC ; SContinue
-SB ; SE ; Sep
-SB ; SP ; Sp
-SB ; ST ; STerm
-SB ; UP ; Upper
-SB ; XX ; Other
+SB ; AT ; ATerm
+SB ; CL ; Close
+SB ; CR ; CR
+SB ; EX ; Extend
+SB ; FO ; Format
+SB ; LE ; OLetter
+SB ; LF ; LF
+SB ; LO ; Lower
+SB ; NU ; Numeric
+SB ; SC ; SContinue
+SB ; SE ; Sep
+SB ; SP ; Sp
+SB ; ST ; STerm
+SB ; UP ; Upper
+SB ; XX ; Other
# Simple_Case_Folding (scf)
@@ -1049,13 +1151,13 @@
# Soft_Dotted (SD)
-SD ; N ; No ; F ; False
-SD ; Y ; Yes ; T ; True
+SD ; N ; No ; F ; False
+SD ; Y ; Yes ; T ; True
# Terminal_Punctuation (Term)
-Term; N ; No ; F ; False
-Term; Y ; Yes ; T ; True
+Term; N ; No ; F ; False
+Term; Y ; Yes ; T ; True
# Titlecase_Mapping (tc)
@@ -1067,13 +1169,13 @@
# Unified_Ideograph (UIdeo)
-UIdeo; N ; No ; F ; False
-UIdeo; Y ; Yes ; T ; True
+UIdeo; N ; No ; F ; False
+UIdeo; Y ; Yes ; T ; True
# Uppercase (Upper)
-Upper; N ; No ; F ; False
-Upper; Y ; Yes ; T ; True
+Upper; N ; No ; F ; False
+Upper; Y ; Yes ; T ; True
# Uppercase_Mapping (uc)
@@ -1081,39 +1183,39 @@
# Variation_Selector (VS)
-VS ; N ; No ; F ; False
-VS ; Y ; Yes ; T ; True
+VS ; N ; No ; F ; False
+VS ; Y ; Yes ; T ; True
# White_Space (WSpace)
-WSpace; N ; No ; F ; False
-WSpace; Y ; Yes ; T ; True
+WSpace; N ; No ; F ; False
+WSpace; Y ; Yes ; T ; True
# Word_Break (WB)
-WB ; CR ; CR
-WB ; EX ; ExtendNumLet
-WB ; Extend ; Extend
-WB ; FO ; Format
-WB ; KA ; Katakana
-WB ; LE ; ALetter
-WB ; LF ; LF
-WB ; MB ; MidNumLet
-WB ; ML ; MidLetter
-WB ; MN ; MidNum
-WB ; NL ; Newline
-WB ; NU ; Numeric
-WB ; XX ; Other
+WB ; CR ; CR
+WB ; EX ; ExtendNumLet
+WB ; Extend ; Extend
+WB ; FO ; Format
+WB ; KA ; Katakana
+WB ; LE ; ALetter
+WB ; LF ; LF
+WB ; MB ; MidNumLet
+WB ; ML ; MidLetter
+WB ; MN ; MidNum
+WB ; NL ; Newline
+WB ; NU ; Numeric
+WB ; XX ; Other
# XID_Continue (XIDC)
-XIDC; N ; No ; F ; False
-XIDC; Y ; Yes ; T ; True
+XIDC; N ; No ; F ; False
+XIDC; Y ; Yes ; T ; True
# XID_Start (XIDS)
-XIDS; N ; No ; F ; False
-XIDS; Y ; Yes ; T ; True
+XIDS; N ; No ; F ; False
+XIDS; Y ; Yes ; T ; True
# cjkAccountingNumeric (cjkAccountingNumeric)
diff --git a/test/java/lang/Character/Scripts.txt b/test/java/lang/Character/Scripts.txt
index 70a6707..2516f88 100644
--- a/test/java/lang/Character/Scripts.txt
+++ b/test/java/lang/Character/Scripts.txt
@@ -1,8 +1,8 @@
-# Scripts-6.0.0.txt
-# Date: 2010-08-19, 00:48:47 GMT [MD]
+# Scripts-6.1.0.txt
+# Date: 2011-11-27, 05:10:50 GMT [MD]
#
# Unicode Character Database
-# Copyright (c) 1991-2010 Unicode, Inc.
+# Copyright (c) 1991-2011 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
@@ -47,7 +47,8 @@
00A0 ; Common # Zs NO-BREAK SPACE
00A1 ; Common # Po INVERTED EXCLAMATION MARK
00A2..00A5 ; Common # Sc [4] CENT SIGN..YEN SIGN
-00A6..00A7 ; Common # So [2] BROKEN BAR..SECTION SIGN
+00A6 ; Common # So BROKEN BAR
+00A7 ; Common # Po SECTION SIGN
00A8 ; Common # Sk DIAERESIS
00A9 ; Common # So COPYRIGHT SIGN
00AB ; Common # Pi LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
@@ -60,8 +61,7 @@
00B2..00B3 ; Common # No [2] SUPERSCRIPT TWO..SUPERSCRIPT THREE
00B4 ; Common # Sk ACUTE ACCENT
00B5 ; Common # L& MICRO SIGN
-00B6 ; Common # So PILCROW SIGN
-00B7 ; Common # Po MIDDLE DOT
+00B6..00B7 ; Common # Po [2] PILCROW SIGN..MIDDLE DOT
00B8 ; Common # Sk CEDILLA
00B9 ; Common # No SUPERSCRIPT ONE
00BB ; Common # Pf RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
@@ -90,7 +90,6 @@
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
-0970 ; Common # Po DEVANAGARI ABBREVIATION SIGN
0E3F ; Common # Sc THAI CURRENCY SYMBOL BAHT
0FD5..0FD8 ; Common # So [4] RIGHT-FACING SVASTI SIGN..LEFT-FACING SVASTI SIGN WITH DOTS
10FB ; Common # Po GEORGIAN PARAGRAPH SEPARATOR
@@ -102,7 +101,8 @@
1CE1 ; Common # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA
1CE9..1CEC ; Common # Lo [4] VEDIC SIGN ANUSVARA ANTARGOMUKHA..VEDIC SIGN ANUSVARA VAMAGOMUKHA WITH TAIL
1CEE..1CF1 ; Common # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA
-1CF2 ; Common # Mc VEDIC SIGN ARDHAVISARGA
+1CF2..1CF3 ; Common # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
+1CF5..1CF6 ; Common # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA
2000..200A ; Common # Zs [11] EN QUAD..HAIR SPACE
200B ; Common # Cf ZERO WIDTH SPACE
200E..200F ; Common # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
@@ -247,9 +247,7 @@
27C0..27C4 ; Common # Sm [5] THREE DIMENSIONAL ANGLE..OPEN SUPERSET
27C5 ; Common # Ps LEFT S-SHAPED BAG DELIMITER
27C6 ; Common # Pe RIGHT S-SHAPED BAG DELIMITER
-27C7..27CA ; Common # Sm [4] OR WITH DOT INSIDE..VERTICAL BAR WITH HORIZONTAL STROKE
-27CC ; Common # Sm LONG DIVISION
-27CE..27E5 ; Common # Sm [24] SQUARED LOGICAL AND..WHITE SQUARE WITH RIGHTWARDS TICK
+27C7..27E5 ; Common # Sm [31] OR WITH DOT INSIDE..WHITE SQUARE WITH RIGHTWARDS TICK
27E6 ; Common # Ps MATHEMATICAL LEFT WHITE SQUARE BRACKET
27E7 ; Common # Pe MATHEMATICAL RIGHT WHITE SQUARE BRACKET
27E8 ; Common # Ps MATHEMATICAL LEFT ANGLE BRACKET
@@ -329,7 +327,8 @@
2E29 ; Common # Pe RIGHT DOUBLE PARENTHESIS
2E2A..2E2E ; Common # Po [5] TWO DOTS OVER ONE DOT PUNCTUATION..REVERSED QUESTION MARK
2E2F ; Common # Lm VERTICAL TILDE
-2E30..2E31 ; Common # Po [2] RING POINT..WORD SEPARATOR MIDDLE DOT
+2E30..2E39 ; Common # Po [10] RING POINT..TOP HALF SECTION SIGN
+2E3A..2E3B ; Common # Pd [2] TWO-EM DASH..THREE-EM DASH
2FF0..2FFB ; Common # So [12] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
3000 ; Common # Zs IDEOGRAPHIC SPACE
3001..3003 ; Common # Po [3] IDEOGRAPHIC COMMA..DITTO MARK
@@ -373,7 +372,9 @@
3196..319F ; Common # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK
31C0..31E3 ; Common # So [36] CJK STROKE T..CJK STROKE Q
3220..3229 ; Common # No [10] PARENTHESIZED IDEOGRAPH ONE..PARENTHESIZED IDEOGRAPH TEN
-322A..3250 ; Common # So [39] PARENTHESIZED IDEOGRAPH MOON..PARTNERSHIP SIGN
+322A..3247 ; Common # So [30] PARENTHESIZED IDEOGRAPH MOON..CIRCLED IDEOGRAPH KOTO
+3248..324F ; Common # No [8] CIRCLED NUMBER TEN ON BLACK SQUARE..CIRCLED NUMBER EIGHTY ON BLACK SQUARE
+3250 ; Common # So PARTNERSHIP SIGN
3251..325F ; Common # No [15] CIRCLED NUMBER TWENTY ONE..CIRCLED NUMBER THIRTY FIVE
327F ; Common # So KOREAN STANDARD SYMBOL
3280..3289 ; Common # No [10] CIRCLED IDEOGRAPH ONE..CIRCLED IDEOGRAPH TEN
@@ -481,8 +482,7 @@
FFED..FFEE ; Common # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE
FFF9..FFFB ; Common # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR
FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER
-10100..10101 ; Common # Po [2] AEGEAN WORD SEPARATOR LINE..AEGEAN WORD SEPARATOR DOT
-10102 ; Common # So AEGEAN CHECK MARK
+10100..10102 ; Common # Po [3] AEGEAN WORD SEPARATOR LINE..AEGEAN CHECK MARK
10107..10133 ; Common # No [45] AEGEAN NUMBER ONE..AEGEAN NUMBER NINETY THOUSAND
10137..1013F ; Common # So [9] AEGEAN WEIGHT BASE UNIT..AEGEAN MEASURE THIRD SUBUNIT
10190..1019B ; Common # So [12] ROMAN SEXTANS SIGN..ROMAN CENTURIAL SIGN
@@ -548,7 +548,7 @@
1F0D1..1F0DF ; Common # So [15] PLAYING CARD ACE OF CLUBS..PLAYING CARD WHITE JOKER
1F100..1F10A ; Common # No [11] DIGIT ZERO FULL STOP..DIGIT NINE COMMA
1F110..1F12E ; Common # So [31] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED WZ
-1F130..1F169 ; Common # So [58] SQUARED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
+1F130..1F16B ; Common # So [60] SQUARED LATIN CAPITAL LETTER A..RAISED MD SIGN
1F170..1F19A ; Common # So [43] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VS
1F1E6..1F1FF ; Common # So [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z
1F201..1F202 ; Common # So [2] SQUARED KATAKANA KOKO..SQUARED KATAKANA SA
@@ -567,33 +567,23 @@
1F442..1F4F7 ; Common # So [182] EAR..CAMERA
1F4F9..1F4FC ; Common # So [4] VIDEO CAMERA..VIDEOCASSETTE
1F500..1F53D ; Common # So [62] TWISTED RIGHTWARDS ARROWS..DOWN-POINTING SMALL RED TRIANGLE
+1F540..1F543 ; Common # So [4] CIRCLED CROSS POMMEE..NOTCHED LEFT SEMICIRCLE WITH THREE DOTS
1F550..1F567 ; Common # So [24] CLOCK FACE ONE OCLOCK..CLOCK FACE TWELVE-THIRTY
-1F5FB..1F5FF ; Common # So [5] MOUNT FUJI..MOYAI
-1F601..1F610 ; Common # So [16] GRINNING FACE WITH SMILING EYES..NEUTRAL FACE
-1F612..1F614 ; Common # So [3] UNAMUSED FACE..PENSIVE FACE
-1F616 ; Common # So CONFOUNDED FACE
-1F618 ; Common # So FACE THROWING A KISS
-1F61A ; Common # So KISSING FACE WITH CLOSED EYES
-1F61C..1F61E ; Common # So [3] FACE WITH STUCK-OUT TONGUE AND WINKING EYE..DISAPPOINTED FACE
-1F620..1F625 ; Common # So [6] ANGRY FACE..DISAPPOINTED BUT RELIEVED FACE
-1F628..1F62B ; Common # So [4] FEARFUL FACE..TIRED FACE
-1F62D ; Common # So LOUDLY CRYING FACE
-1F630..1F633 ; Common # So [4] FACE WITH OPEN MOUTH AND COLD SWEAT..FLUSHED FACE
-1F635..1F640 ; Common # So [12] DIZZY FACE..WEARY CAT FACE
+1F5FB..1F640 ; Common # So [70] MOUNT FUJI..WEARY CAT FACE
1F645..1F64F ; Common # So [11] FACE WITH NO GOOD GESTURE..PERSON WITH FOLDED HANDS
1F680..1F6C5 ; Common # So [70] ROCKET..LEFT LUGGAGE
1F700..1F773 ; Common # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
E0001 ; Common # Cf LANGUAGE TAG
E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
-# Total code points: 6379
+# Total code points: 6412
# ================================================
0041..005A ; Latin # L& [26] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER Z
0061..007A ; Latin # L& [26] LATIN SMALL LETTER A..LATIN SMALL LETTER Z
-00AA ; Latin # L& FEMININE ORDINAL INDICATOR
-00BA ; Latin # L& MASCULINE ORDINAL INDICATOR
+00AA ; Latin # Lo FEMININE ORDINAL INDICATOR
+00BA ; Latin # Lo MASCULINE ORDINAL INDICATOR
00C0..00D6 ; Latin # L& [23] LATIN CAPITAL LETTER A WITH GRAVE..LATIN CAPITAL LETTER O WITH DIAERESIS
00D8..00F6 ; Latin # L& [31] LATIN CAPITAL LETTER O WITH STROKE..LATIN SMALL LETTER O WITH DIAERESIS
00F8..01BA ; Latin # L& [195] LATIN SMALL LETTER O WITH STROKE..LATIN SMALL LETTER EZH WITH TAIL
@@ -607,7 +597,7 @@
02E0..02E4 ; Latin # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
1D00..1D25 ; Latin # L& [38] LATIN LETTER SMALL CAPITAL A..LATIN LETTER AIN
1D2C..1D5C ; Latin # Lm [49] MODIFIER LETTER CAPITAL A..MODIFIER LETTER SMALL AIN
-1D62..1D65 ; Latin # L& [4] LATIN SUBSCRIPT SMALL LETTER I..LATIN SUBSCRIPT SMALL LETTER V
+1D62..1D65 ; Latin # Lm [4] LATIN SUBSCRIPT SMALL LETTER I..LATIN SUBSCRIPT SMALL LETTER V
1D6B..1D77 ; Latin # L& [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G
1D79..1D9A ; Latin # L& [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK
1D9B..1DBE ; Latin # Lm [36] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL EZH
@@ -621,22 +611,23 @@
2160..2182 ; Latin # Nl [35] ROMAN NUMERAL ONE..ROMAN NUMERAL TEN THOUSAND
2183..2184 ; Latin # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C
2185..2188 ; Latin # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND
-2C60..2C7C ; Latin # L& [29] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN SUBSCRIPT SMALL LETTER J
-2C7D ; Latin # Lm MODIFIER LETTER CAPITAL V
+2C60..2C7B ; Latin # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E
+2C7C..2C7D ; Latin # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V
2C7E..2C7F ; Latin # L& [2] LATIN CAPITAL LETTER S WITH SWASH TAIL..LATIN CAPITAL LETTER Z WITH SWASH TAIL
A722..A76F ; Latin # L& [78] LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF..LATIN SMALL LETTER CON
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
-A790..A791 ; Latin # L& [2] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER N WITH DESCENDER
-A7A0..A7A9 ; Latin # L& [10] LATIN CAPITAL LETTER G WITH OBLIQUE STROKE..LATIN SMALL LETTER S WITH OBLIQUE STROKE
+A790..A793 ; Latin # L& [4] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER C WITH BAR
+A7A0..A7AA ; Latin # L& [11] LATIN CAPITAL LETTER G WITH OBLIQUE STROKE..LATIN CAPITAL LETTER H WITH HOOK
+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
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: 1267
+# Total code points: 1272
# ================================================
@@ -656,7 +647,7 @@
03F7..03FF ; Greek # L& [9] GREEK CAPITAL LETTER SHO..GREEK CAPITAL REVERSED DOTTED LUNATE SIGMA SYMBOL
1D26..1D2A ; Greek # L& [5] GREEK LETTER SMALL CAPITAL GAMMA..GREEK LETTER SMALL CAPITAL PSI
1D5D..1D61 ; Greek # Lm [5] MODIFIER LETTER SMALL BETA..MODIFIER LETTER SMALL CHI
-1D66..1D6A ; Greek # L& [5] GREEK SUBSCRIPT SMALL LETTER BETA..GREEK SUBSCRIPT SMALL LETTER CHI
+1D66..1D6A ; Greek # Lm [5] GREEK SUBSCRIPT SMALL LETTER BETA..GREEK SUBSCRIPT SMALL LETTER CHI
1DBF ; Greek # Lm MODIFIER LETTER SMALL THETA
1F00..1F15 ; Greek # L& [22] GREEK SMALL LETTER ALPHA WITH PSILI..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA
1F18..1F1D ; Greek # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA
@@ -710,12 +701,13 @@
A66F ; Cyrillic # Mn COMBINING CYRILLIC VZMET
A670..A672 ; Cyrillic # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN
A673 ; Cyrillic # Po SLAVONIC ASTERISK
-A67C..A67D ; Cyrillic # Mn [2] COMBINING CYRILLIC KAVYKA..COMBINING CYRILLIC PAYEROK
+A674..A67D ; Cyrillic # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK
A67E ; Cyrillic # Po CYRILLIC KAVYKA
A67F ; Cyrillic # Lm CYRILLIC PAYEROK
A680..A697 ; Cyrillic # L& [24] CYRILLIC CAPITAL LETTER DWE..CYRILLIC SMALL LETTER SHWE
+A69F ; Cyrillic # Mn COMBINING CYRILLIC LETTER IOTIFIED E
-# Total code points: 408
+# Total code points: 417
# ================================================
@@ -724,9 +716,10 @@
055A..055F ; Armenian # Po [6] ARMENIAN APOSTROPHE..ARMENIAN ABBREVIATION MARK
0561..0587 ; Armenian # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN
058A ; Armenian # Pd ARMENIAN HYPHEN
+058F ; Armenian # Sc ARMENIAN DRAM SIGN
FB13..FB17 ; Armenian # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH
-# Total code points: 90
+# Total code points: 91
# ================================================
@@ -757,7 +750,7 @@
# ================================================
-0600..0603 ; Arabic # Cf [4] ARABIC NUMBER SIGN..ARABIC SIGN SAFHA
+0600..0604 ; Arabic # Cf [5] ARABIC NUMBER SIGN..ARABIC SIGN SAMVAT
0606..0608 ; Arabic # Sm [3] ARABIC-INDIC CUBE ROOT..ARABIC RAY
0609..060A ; Arabic # Po [2] ARABIC-INDIC PER MILLE SIGN..ARABIC-INDIC PER TEN THOUSAND SIGN
060B ; Arabic # Sc AFGHANI SIGN
@@ -786,6 +779,9 @@
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 ; Arabic # Lo ARABIC LETTER BEH WITH SMALL V BELOW
+08A2..08AC ; Arabic # Lo [11] ARABIC LETTER JEEM WITH TWO DOTS ABOVE..ARABIC LETTER ROHINGYA YEH
+08E4..08FE ; Arabic # Mn [27] ARABIC CURLY FATHA..ARABIC DAMMA WITH DOT
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
@@ -796,8 +792,42 @@
FE70..FE74 ; Arabic # Lo [5] ARABIC FATHATAN ISOLATED FORM..ARABIC KASRATAN ISOLATED FORM
FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM
10E60..10E7E ; Arabic # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS
+1EE00..1EE03 ; Arabic # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL
+1EE05..1EE1F ; Arabic # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF
+1EE21..1EE22 ; Arabic # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM
+1EE24 ; Arabic # Lo ARABIC MATHEMATICAL INITIAL HEH
+1EE27 ; Arabic # Lo ARABIC MATHEMATICAL INITIAL HAH
+1EE29..1EE32 ; Arabic # Lo [10] ARABIC MATHEMATICAL INITIAL YEH..ARABIC MATHEMATICAL INITIAL QAF
+1EE34..1EE37 ; Arabic # Lo [4] ARABIC MATHEMATICAL INITIAL SHEEN..ARABIC MATHEMATICAL INITIAL KHAH
+1EE39 ; Arabic # Lo ARABIC MATHEMATICAL INITIAL DAD
+1EE3B ; Arabic # Lo ARABIC MATHEMATICAL INITIAL GHAIN
+1EE42 ; Arabic # Lo ARABIC MATHEMATICAL TAILED JEEM
+1EE47 ; Arabic # Lo ARABIC MATHEMATICAL TAILED HAH
+1EE49 ; Arabic # Lo ARABIC MATHEMATICAL TAILED YEH
+1EE4B ; Arabic # Lo ARABIC MATHEMATICAL TAILED LAM
+1EE4D..1EE4F ; Arabic # Lo [3] ARABIC MATHEMATICAL TAILED NOON..ARABIC MATHEMATICAL TAILED AIN
+1EE51..1EE52 ; Arabic # Lo [2] ARABIC MATHEMATICAL TAILED SAD..ARABIC MATHEMATICAL TAILED QAF
+1EE54 ; Arabic # Lo ARABIC MATHEMATICAL TAILED SHEEN
+1EE57 ; Arabic # Lo ARABIC MATHEMATICAL TAILED KHAH
+1EE59 ; Arabic # Lo ARABIC MATHEMATICAL TAILED DAD
+1EE5B ; Arabic # Lo ARABIC MATHEMATICAL TAILED GHAIN
+1EE5D ; Arabic # Lo ARABIC MATHEMATICAL TAILED DOTLESS NOON
+1EE5F ; Arabic # Lo ARABIC MATHEMATICAL TAILED DOTLESS QAF
+1EE61..1EE62 ; Arabic # Lo [2] ARABIC MATHEMATICAL STRETCHED BEH..ARABIC MATHEMATICAL STRETCHED JEEM
+1EE64 ; Arabic # Lo ARABIC MATHEMATICAL STRETCHED HEH
+1EE67..1EE6A ; Arabic # Lo [4] ARABIC MATHEMATICAL STRETCHED HAH..ARABIC MATHEMATICAL STRETCHED KAF
+1EE6C..1EE72 ; Arabic # Lo [7] ARABIC MATHEMATICAL STRETCHED MEEM..ARABIC MATHEMATICAL STRETCHED QAF
+1EE74..1EE77 ; Arabic # Lo [4] ARABIC MATHEMATICAL STRETCHED SHEEN..ARABIC MATHEMATICAL STRETCHED KHAH
+1EE79..1EE7C ; Arabic # Lo [4] ARABIC MATHEMATICAL STRETCHED DAD..ARABIC MATHEMATICAL STRETCHED DOTLESS BEH
+1EE7E ; Arabic # Lo ARABIC MATHEMATICAL STRETCHED DOTLESS FEH
+1EE80..1EE89 ; Arabic # Lo [10] ARABIC MATHEMATICAL LOOPED ALEF..ARABIC MATHEMATICAL LOOPED YEH
+1EE8B..1EE9B ; Arabic # Lo [17] ARABIC MATHEMATICAL LOOPED LAM..ARABIC MATHEMATICAL LOOPED GHAIN
+1EEA1..1EEA3 ; Arabic # Lo [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL
+1EEA5..1EEA9 ; Arabic # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH
+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: 1051
+# Total code points: 1234
# ================================================
@@ -838,6 +868,7 @@
0958..0961 ; Devanagari # Lo [10] DEVANAGARI LETTER QA..DEVANAGARI LETTER VOCALIC LL
0962..0963 ; Devanagari # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL
0966..096F ; Devanagari # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE
+0970 ; Devanagari # Po DEVANAGARI ABBREVIATION SIGN
0971 ; Devanagari # Lm DEVANAGARI SIGN HIGH SPACING DOT
0972..0977 ; Devanagari # Lo [6] DEVANAGARI LETTER CANDRA A..DEVANAGARI LETTER UUE
0979..097F ; Devanagari # Lo [7] DEVANAGARI LETTER ZHA..DEVANAGARI LETTER BBA
@@ -846,7 +877,7 @@
A8F8..A8FA ; Devanagari # Po [3] DEVANAGARI SIGN PUSHPIKA..DEVANAGARI CARET
A8FB ; Devanagari # Lo DEVANAGARI HEADSTROKE
-# Total code points: 150
+# Total code points: 151
# ================================================
@@ -927,9 +958,10 @@
0AE0..0AE1 ; Gujarati # Lo [2] GUJARATI LETTER VOCALIC RR..GUJARATI LETTER VOCALIC LL
0AE2..0AE3 ; Gujarati # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL
0AE6..0AEF ; Gujarati # Nd [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE
+0AF0 ; Gujarati # Po GUJARATI ABBREVIATION SIGN
0AF1 ; Gujarati # Sc GUJARATI RUPEE SIGN
-# Total code points: 83
+# Total code points: 84
# ================================================
@@ -1119,16 +1151,18 @@
0EC6 ; Lao # Lm LAO KO LA
0EC8..0ECD ; Lao # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA
0ED0..0ED9 ; Lao # Nd [10] LAO DIGIT ZERO..LAO DIGIT NINE
-0EDC..0EDD ; Lao # Lo [2] LAO HO NO..LAO HO MO
+0EDC..0EDF ; Lao # Lo [4] LAO HO NO..LAO LETTER KHMU NYO
-# Total code points: 65
+# Total code points: 67
# ================================================
0F00 ; Tibetan # Lo TIBETAN SYLLABLE OM
0F01..0F03 ; Tibetan # So [3] TIBETAN MARK GTER YIG MGO TRUNCATED A..TIBETAN MARK GTER YIG MGO -UM GTER TSHEG MA
0F04..0F12 ; Tibetan # Po [15] TIBETAN MARK INITIAL YIG MGO MDUN MA..TIBETAN MARK RGYA GRAM SHAD
-0F13..0F17 ; Tibetan # So [5] TIBETAN MARK CARET -DZUD RTAGS ME LONG CAN..TIBETAN ASTROLOGICAL SIGN SGRA GCAN -CHAR RTAGS
+0F13 ; Tibetan # So TIBETAN MARK CARET -DZUD RTAGS ME LONG CAN
+0F14 ; Tibetan # Po TIBETAN MARK GTER TSHEG
+0F15..0F17 ; Tibetan # So [3] TIBETAN LOGOTYPE SIGN CHAD RTAGS..TIBETAN ASTROLOGICAL SIGN SGRA GCAN -CHAR RTAGS
0F18..0F19 ; Tibetan # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS
0F1A..0F1F ; Tibetan # So [6] TIBETAN SIGN RDEL DKAR GCIG..TIBETAN SIGN RDEL DKAR RDEL NAG
0F20..0F29 ; Tibetan # Nd [10] TIBETAN DIGIT ZERO..TIBETAN DIGIT NINE
@@ -1212,16 +1246,21 @@
# ================================================
10A0..10C5 ; Georgian # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE
+10C7 ; Georgian # L& GEORGIAN CAPITAL LETTER YN
+10CD ; Georgian # L& GEORGIAN CAPITAL LETTER AEN
10D0..10FA ; Georgian # Lo [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN
10FC ; Georgian # Lm MODIFIER LETTER GEORGIAN NAR
+10FD..10FF ; Georgian # Lo [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN
2D00..2D25 ; Georgian # L& [38] GEORGIAN SMALL LETTER AN..GEORGIAN SMALL LETTER HOE
+2D27 ; Georgian # L& GEORGIAN SMALL LETTER YN
+2D2D ; Georgian # L& GEORGIAN SMALL LETTER AEN
-# Total code points: 120
+# Total code points: 127
# ================================================
1100..11FF ; Hangul # Lo [256] HANGUL CHOSEONG KIYEOK..HANGUL JONGSEONG SSANGNIEUN
-302E..302F ; Hangul # Mn [2] HANGUL SINGLE DOT TONE MARK..HANGUL DOUBLE DOT TONE MARK
+302E..302F ; Hangul # Mc [2] HANGUL SINGLE DOT TONE MARK..HANGUL DOUBLE DOT TONE MARK
3131..318E ; Hangul # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE
3200..321E ; Hangul # So [31] PARENTHESIZED HANGUL KIYEOK..PARENTHESIZED KOREAN CHARACTER O HU
3260..327E ; Hangul # So [31] CIRCLED HANGUL KIYEOK..CIRCLED HANGUL IEUNG U
@@ -1256,8 +1295,7 @@
1312..1315 ; Ethiopic # Lo [4] ETHIOPIC SYLLABLE GWI..ETHIOPIC SYLLABLE GWE
1318..135A ; Ethiopic # Lo [67] ETHIOPIC SYLLABLE GGA..ETHIOPIC SYLLABLE FYA
135D..135F ; Ethiopic # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK
-1360 ; Ethiopic # So ETHIOPIC SECTION MARK
-1361..1368 ; Ethiopic # Po [8] ETHIOPIC WORDSPACE..ETHIOPIC PARAGRAPH SEPARATOR
+1360..1368 ; Ethiopic # Po [9] ETHIOPIC SECTION MARK..ETHIOPIC PARAGRAPH SEPARATOR
1369..137C ; Ethiopic # No [20] ETHIOPIC DIGIT ONE..ETHIOPIC NUMBER TEN THOUSAND
1380..138F ; Ethiopic # Lo [16] ETHIOPIC SYLLABLE SEBATBEIT MWA..ETHIOPIC SYLLABLE PWE
1390..1399 ; Ethiopic # So [10] ETHIOPIC TONAL MARK YIZET..ETHIOPIC TONAL MARK KURT
@@ -1313,7 +1351,7 @@
# ================================================
1780..17B3 ; Khmer # Lo [52] KHMER LETTER KA..KHMER INDEPENDENT VOWEL QAU
-17B4..17B5 ; Khmer # Cf [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
+17B4..17B5 ; Khmer # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
17B6 ; Khmer # Mc KHMER VOWEL SIGN AA
17B7..17BD ; Khmer # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA
17BE..17C5 ; Khmer # Mc [8] KHMER VOWEL SIGN OE..KHMER VOWEL SIGN AU
@@ -1393,16 +1431,15 @@
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..9FCB ; Han # Lo [20940] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCB
-F900..FA2D ; Han # Lo [302] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA2D
-FA30..FA6D ; Han # Lo [62] CJK COMPATIBILITY IDEOGRAPH-FA30..CJK COMPATIBILITY IDEOGRAPH-FA6D
+4E00..9FCC ; Han # Lo [20941] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCC
+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
2F800..2FA1D ; Han # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
-# Total code points: 75960
+# Total code points: 75963
# ================================================
@@ -1447,6 +1484,7 @@
1CD4..1CE0 ; Inherited # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA
1CE2..1CE8 ; Inherited # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL
1CED ; Inherited # Mn VEDIC SIGN TIRYAK
+1CF4 ; Inherited # Mn VEDIC TONE CANDRA ABOVE
1DC0..1DE6 ; Inherited # Mn [39] COMBINING DOTTED GRAVE ACCENT..COMBINING LATIN SMALL LETTER Z
1DFC..1DFF ; Inherited # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
200C..200D ; Inherited # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER
@@ -1466,7 +1504,7 @@
1D1AA..1D1AD ; Inherited # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
-# Total code points: 523
+# Total code points: 524
# ================================================
@@ -1587,11 +1625,12 @@
2CE5..2CEA ; Coptic # So [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA
2CEB..2CEE ; Coptic # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA
2CEF..2CF1 ; Coptic # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS
+2CF2..2CF3 ; Coptic # L& [2] COPTIC CAPITAL LETTER BOHAIRIC KHEI..COPTIC SMALL LETTER BOHAIRIC KHEI
2CF9..2CFC ; Coptic # Po [4] COPTIC OLD NUBIAN FULL STOP..COPTIC OLD NUBIAN VERSE DIVIDER
2CFD ; Coptic # No COPTIC FRACTION ONE HALF
2CFE..2CFF ; Coptic # Po [2] COPTIC FULL STOP..COPTIC MORPHOLOGICAL DIVIDER
-# Total code points: 135
+# Total code points: 137
# ================================================
@@ -1614,12 +1653,12 @@
# ================================================
-2D30..2D65 ; Tifinagh # Lo [54] TIFINAGH LETTER YA..TIFINAGH LETTER YAZZ
+2D30..2D67 ; Tifinagh # Lo [56] TIFINAGH LETTER YA..TIFINAGH LETTER YO
2D6F ; Tifinagh # Lm TIFINAGH MODIFIER LETTER LABIALIZATION MARK
2D70 ; Tifinagh # Po TIFINAGH SEPARATOR MARK
2D7F ; Tifinagh # Mn TIFINAGH CONSONANT JOINER
-# Total code points: 57
+# Total code points: 59
# ================================================
@@ -1729,10 +1768,14 @@
1BA6..1BA7 ; Sundanese # Mc [2] SUNDANESE VOWEL SIGN PANAELAENG..SUNDANESE VOWEL SIGN PANOLONG
1BA8..1BA9 ; Sundanese # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG
1BAA ; Sundanese # Mc SUNDANESE SIGN PAMAAEH
+1BAB ; Sundanese # Mn SUNDANESE SIGN VIRAMA
+1BAC..1BAD ; Sundanese # Mc [2] SUNDANESE CONSONANT SIGN PASANGAN MA..SUNDANESE CONSONANT SIGN PASANGAN WA
1BAE..1BAF ; Sundanese # Lo [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA
1BB0..1BB9 ; Sundanese # Nd [10] SUNDANESE DIGIT ZERO..SUNDANESE DIGIT NINE
+1BBA..1BBF ; Sundanese # Lo [6] SUNDANESE AVAGRAHA..SUNDANESE LETTER FINAL M
+1CC0..1CC7 ; Sundanese # Po [8] SUNDANESE PUNCTUATION BINDU SURYA..SUNDANESE PUNCTUATION BINDU BA SATANGA
-# Total code points: 55
+# Total code points: 72
# ================================================
@@ -1940,6 +1983,15 @@
# ================================================
+AAE0..AAEA ; Meetei_Mayek # Lo [11] MEETEI MAYEK LETTER E..MEETEI MAYEK LETTER SSA
+AAEB ; Meetei_Mayek # Mc MEETEI MAYEK VOWEL SIGN II
+AAEC..AAED ; Meetei_Mayek # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI
+AAEE..AAEF ; Meetei_Mayek # Mc [2] MEETEI MAYEK VOWEL SIGN AU..MEETEI MAYEK VOWEL SIGN AAU
+AAF0..AAF1 ; Meetei_Mayek # Po [2] MEETEI MAYEK CHEIKHAN..MEETEI MAYEK AHANG KHUDAM
+AAF2 ; Meetei_Mayek # Lo MEETEI MAYEK ANJI
+AAF3..AAF4 ; Meetei_Mayek # Lm [2] MEETEI MAYEK SYLLABLE REPETITION MARK..MEETEI MAYEK WORD REPETITION MARK
+AAF5 ; Meetei_Mayek # Mc MEETEI MAYEK VOWEL SIGN VISARGA
+AAF6 ; Meetei_Mayek # Mn MEETEI MAYEK VIRAMA
ABC0..ABE2 ; Meetei_Mayek # Lo [35] MEETEI MAYEK LETTER KOK..MEETEI MAYEK LETTER I LONSUM
ABE3..ABE4 ; Meetei_Mayek # Mc [2] MEETEI MAYEK VOWEL SIGN ONAP..MEETEI MAYEK VOWEL SIGN INAP
ABE5 ; Meetei_Mayek # Mn MEETEI MAYEK VOWEL SIGN ANAP
@@ -1951,7 +2003,7 @@
ABED ; Meetei_Mayek # Mn MEETEI MAYEK APUN IYEK
ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE
-# Total code points: 56
+# Total code points: 79
# ================================================
@@ -2040,4 +2092,74 @@
# Total code points: 29
+# ================================================
+
+11100..11102 ; Chakma # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA
+11103..11126 ; Chakma # Lo [36] CHAKMA LETTER AA..CHAKMA LETTER HAA
+11127..1112B ; Chakma # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU
+1112C ; Chakma # Mc CHAKMA VOWEL SIGN E
+1112D..11134 ; Chakma # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA
+11136..1113F ; Chakma # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE
+11140..11143 ; Chakma # Po [4] CHAKMA SECTION MARK..CHAKMA QUESTION MARK
+
+# Total code points: 67
+
+# ================================================
+
+109A0..109B7 ; Meroitic_Cursive # Lo [24] MEROITIC CURSIVE LETTER A..MEROITIC CURSIVE LETTER DA
+109BE..109BF ; Meroitic_Cursive # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN
+
+# Total code points: 26
+
+# ================================================
+
+10980..1099F ; Meroitic_Hieroglyphs # Lo [32] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC HIEROGLYPHIC SYMBOL VIDJ-2
+
+# Total code points: 32
+
+# ================================================
+
+16F00..16F44 ; Miao # Lo [69] MIAO LETTER PA..MIAO LETTER HHA
+16F50 ; Miao # Lo MIAO LETTER NASALIZATION
+16F51..16F7E ; Miao # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
+16F8F..16F92 ; Miao # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
+16F93..16F9F ; Miao # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8
+
+# Total code points: 133
+
+# ================================================
+
+11180..11181 ; Sharada # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA
+11182 ; Sharada # Mc SHARADA SIGN VISARGA
+11183..111B2 ; Sharada # Lo [48] SHARADA LETTER A..SHARADA LETTER HA
+111B3..111B5 ; Sharada # Mc [3] SHARADA VOWEL SIGN AA..SHARADA VOWEL SIGN II
+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
+111D0..111D9 ; Sharada # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE
+
+# Total code points: 83
+
+# ================================================
+
+110D0..110E8 ; Sora_Sompeng # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE
+110F0..110F9 ; Sora_Sompeng # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE
+
+# Total code points: 35
+
+# ================================================
+
+11680..116AA ; Takri # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA
+116AB ; Takri # Mn TAKRI SIGN ANUSVARA
+116AC ; Takri # Mc TAKRI SIGN VISARGA
+116AD ; Takri # Mn TAKRI VOWEL SIGN AA
+116AE..116AF ; Takri # Mc [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II
+116B0..116B5 ; Takri # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU
+116B6 ; Takri # Mc TAKRI SIGN VIRAMA
+116B7 ; Takri # Mn TAKRI SIGN NUKTA
+116C0..116C9 ; Takri # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE
+
+# Total code points: 66
+
# EOF