ICU-1923 upgrade to Unicode 3.2

X-SVN-Rev: 8764
This commit is contained in:
Markus Scherer 2002-06-01 00:34:36 +00:00
parent 185ac97303
commit 067b86e8a3
2 changed files with 76 additions and 32 deletions

View file

@ -65,7 +65,11 @@ typedef enum UScriptCode {
USCRIPT_TIBETAN = 39, /* Tibt */
USCRIPT_UCAS = 40, /* Cans */
USCRIPT_YI = 41, /* Yiii */
USCRIPT_CODE_LIMIT = 42
USCRIPT_TAGALOG = 42, /* Tglg */
USCRIPT_HANUNOO = 43, /* Hano */
USCRIPT_BUHID = 44, /* Buhd */
USCRIPT_TAGBANWA = 45, /* Tagb */
USCRIPT_CODE_LIMIT
} UScriptCode;
/**

View file

@ -1,8 +1,8 @@
# Scripts-3.1.0.txt
# Scripts-3.2.0.txt
# Date: 2002-03-19,23:31:26 GMT [MD]
#
# For documentation, see UTR #24: Script Names
# http://www.unicode.org/unicode/reports/tr24/
# Date: 2001-03-02 00:06:02.6 GMT [MD]
# Note: Unassigned and Noncharacter codepoints are omitted,
# except when listing Noncharacter or Cn.
# ================================================
@ -22,20 +22,21 @@
01BB ; LATIN # Lo LATIN LETTER TWO WITH STROKE
01BC..01BF ; LATIN # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN
01C0..01C3 ; LATIN # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK
01C4..021F ; LATIN # L& [92] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER H WITH CARON
01C4..0220 ; LATIN # L& [93] LATIN CAPITAL LETTER DZ WITH CARON..LATIN CAPITAL LETTER N WITH LONG RIGHT LEG
0222..0233 ; LATIN # L& [18] LATIN CAPITAL LETTER OU..LATIN SMALL LETTER Y WITH MACRON
0250..02AD ; LATIN # L& [94] LATIN SMALL LETTER TURNED A..LATIN LETTER BIDENTAL PERCUSSIVE
02B0..02B8 ; LATIN # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y
02E0..02E4 ; LATIN # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
1E00..1E9B ; LATIN # L& [156] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER LONG S WITH DOT ABOVE
1EA0..1EF9 ; LATIN # L& [90] LATIN CAPITAL LETTER A WITH DOT BELOW..LATIN SMALL LETTER Y WITH TILDE
2071 ; LATIN # L& SUPERSCRIPT LATIN SMALL LETTER I
207F ; LATIN # L& SUPERSCRIPT LATIN SMALL LETTER N
212A..212B ; LATIN # L& [2] KELVIN SIGN..ANGSTROM SIGN
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: 838
# Total code points: 840
# ================================================
@ -46,8 +47,7 @@ FF41..FF5A ; LATIN # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN
038C ; GREEK # L& GREEK CAPITAL LETTER OMICRON WITH TONOS
038E..03A1 ; GREEK # L& [20] GREEK CAPITAL LETTER UPSILON WITH TONOS..GREEK CAPITAL LETTER RHO
03A3..03CE ; GREEK # L& [44] GREEK CAPITAL LETTER SIGMA..GREEK SMALL LETTER OMEGA WITH TONOS
03D0..03D7 ; GREEK # L& [8] GREEK BETA SYMBOL..GREEK KAI SYMBOL
03DA..03F5 ; GREEK # L& [28] GREEK LETTER STIGMA..GREEK LUNATE EPSILON SYMBOL
03D0..03F5 ; GREEK # L& [38] GREEK BETA SYMBOL..GREEK LUNATE EPSILON SYMBOL
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
1F20..1F45 ; GREEK # L& [38] GREEK SMALL LETTER ETA WITH PSILI..GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA
@ -69,19 +69,18 @@ FF41..FF5A ; LATIN # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN
1FF6..1FFC ; GREEK # L& [7] GREEK SMALL LETTER OMEGA WITH PERISPOMENI..GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI
2126 ; GREEK # L& OHM SIGN
# Total code points: 326
# Total code points: 328
# ================================================
0400..0481 ; CYRILLIC # L& [130] CYRILLIC CAPITAL LETTER IE WITH GRAVE..CYRILLIC SMALL LETTER KOPPA
0483..0486 ; CYRILLIC # Mn [4] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC PSILI PNEUMATA
048C..04C4 ; CYRILLIC # L& [57] CYRILLIC CAPITAL LETTER SEMISOFT SIGN..CYRILLIC SMALL LETTER KA WITH HOOK
04C7..04C8 ; CYRILLIC # L& [2] CYRILLIC CAPITAL LETTER EN WITH HOOK..CYRILLIC SMALL LETTER EN WITH HOOK
04CB..04CC ; CYRILLIC # L& [2] CYRILLIC CAPITAL LETTER KHAKASSIAN CHE..CYRILLIC SMALL LETTER KHAKASSIAN CHE
048A..04CE ; CYRILLIC # L& [69] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EM WITH TAIL
04D0..04F5 ; CYRILLIC # L& [38] CYRILLIC CAPITAL LETTER A WITH BREVE..CYRILLIC SMALL LETTER CHE WITH DIAERESIS
04F8..04F9 ; CYRILLIC # L& [2] CYRILLIC CAPITAL LETTER YERU WITH DIAERESIS..CYRILLIC SMALL LETTER YERU WITH DIAERESIS
0500..050F ; CYRILLIC # L& [16] CYRILLIC CAPITAL LETTER KOMI DE..CYRILLIC SMALL LETTER KOMI TJE
# Total code points: 235
# Total code points: 259
# ================================================
@ -111,6 +110,7 @@ FB46..FB4F ; HEBREW # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU
0621..063A ; ARABIC # Lo [26] ARABIC LETTER HAMZA..ARABIC LETTER GHAIN
0641..064A ; ARABIC # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH
066E..066F ; ARABIC # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF
0671..06D3 ; ARABIC # Lo [99] ARABIC LETTER ALEF WASLA..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE
06D5 ; ARABIC # Lo ARABIC LETTER AE
06E5..06E6 ; ARABIC # Lm [2] ARABIC SMALL WAW..ARABIC SMALL YEH
@ -120,11 +120,10 @@ FBD3..FD3D ; ARABIC # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATUR
FD50..FD8F ; ARABIC # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM
FD92..FDC7 ; ARABIC # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM
FDF0..FDFB ; ARABIC # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU
FE70..FE72 ; ARABIC # Lo [3] ARABIC FATHATAN ISOLATED FORM..ARABIC DAMMATAN ISOLATED FORM
FE74 ; ARABIC # Lo ARABIC KASRATAN ISOLATED FORM
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
# Total code points: 871
# Total code points: 874
# ================================================
@ -139,8 +138,9 @@ FE76..FEFC ; ARABIC # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
0780..07A5 ; THAANA # Lo [38] THAANA LETTER HAA..THAANA LETTER WAAVU
07A6..07B0 ; THAANA # Mn [11] THAANA ABAFILI..THAANA SUKUN
07B1 ; THAANA # Lo THAANA LETTER NAA
# Total code points: 49
# Total code points: 50
# ================================================
@ -164,6 +164,7 @@ FE76..FEFC ; ARABIC # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
# ================================================
0981 ; BENGALI # Mn BENGALI SIGN CANDRABINDU
0982..0983 ; BENGALI # Mc [2] BENGALI SIGN ANUSVARA..BENGALI SIGN VISARGA
0985..098C ; BENGALI # Lo [8] BENGALI LETTER A..BENGALI LETTER VOCALIC L
098F..0990 ; BENGALI # Lo [2] BENGALI LETTER E..BENGALI LETTER AI
0993..09A8 ; BENGALI # Lo [22] BENGALI LETTER O..BENGALI LETTER NA
@ -183,7 +184,7 @@ FE76..FEFC ; ARABIC # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
09E6..09EF ; BENGALI # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE
09F0..09F1 ; BENGALI # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL
# Total code points: 78
# Total code points: 80
# ================================================
@ -263,7 +264,7 @@ FE76..FEFC ; ARABIC # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
# ================================================
0B82 ; TAMIL # Mn TAMIL SIGN ANUSVARA
0B83 ; TAMIL # Mc TAMIL SIGN VISARGA
0B83 ; TAMIL # Lo TAMIL SIGN VISARGA
0B85..0B8A ; TAMIL # Lo [6] TAMIL LETTER A..TAMIL LETTER UU
0B8E..0B90 ; TAMIL # Lo [3] TAMIL LETTER E..TAMIL LETTER AI
0B92..0B95 ; TAMIL # Lo [4] TAMIL LETTER O..TAMIL LETTER KA
@ -445,9 +446,9 @@ FE76..FEFC ; ARABIC # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
# ================================================
10A0..10C5 ; GEORGIAN # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE
10D0..10F6 ; GEORGIAN # Lo [39] GEORGIAN LETTER AN..GEORGIAN LETTER FI
10D0..10F8 ; GEORGIAN # Lo [41] GEORGIAN LETTER AN..GEORGIAN LETTER ELIFI
# Total code points: 77
# Total code points: 79
# ================================================
@ -504,8 +505,8 @@ FFDA..FFDC ; HANGUL # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL L
# ================================================
1401..166C ; CANADIAN-ABORIGINAL # Lo [620] CANADIAN SYLLABICS E..CANADIAN SYLLABICS CARRIER TTSA
166F..1676 ; CANADIAN-ABORIGINAL # Lo [8] CANADIAN SYLLABICS QAI..CANADIAN SYLLABICS NNGAA
1401..166C ; CANADIAN_ABORIGINAL # Lo [620] CANADIAN SYLLABICS E..CANADIAN SYLLABICS CARRIER TTSA
166F..1676 ; CANADIAN_ABORIGINAL # Lo [8] CANADIAN SYLLABICS QAI..CANADIAN SYLLABICS NNGAA
# Total code points: 628
@ -548,19 +549,22 @@ FFDA..FFDC ; HANGUL # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL L
# ================================================
3041..3094 ; HIRAGANA # Lo [84] HIRAGANA LETTER SMALL A..HIRAGANA LETTER VU
3041..3096 ; HIRAGANA # Lo [86] HIRAGANA LETTER SMALL A..HIRAGANA LETTER SMALL KE
309D..309E ; HIRAGANA # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK
309F ; HIRAGANA # Lo HIRAGANA DIGRAPH YORI
# Total code points: 86
# Total code points: 89
# ================================================
30A1..30FA ; KATAKANA # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO
30FD..30FE ; KATAKANA # Lm [2] KATAKANA ITERATION MARK..KATAKANA VOICED ITERATION MARK
30FF ; KATAKANA # Lo KATAKANA DIGRAPH KOTO
31F0..31FF ; KATAKANA # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO
FF66..FF6F ; KATAKANA # Lo [10] HALFWIDTH KATAKANA LETTER WO..HALFWIDTH KATAKANA LETTER SMALL TU
FF71..FF9D ; KATAKANA # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAKANA LETTER N
# Total code points: 147
# Total code points: 164
# ================================================
@ -578,13 +582,15 @@ FF71..FF9D ; KATAKANA # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
3007 ; HAN # Nl IDEOGRAPHIC NUMBER ZERO
3021..3029 ; HAN # Nl [9] HANGZHOU NUMERAL ONE..HANGZHOU NUMERAL NINE
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..9FA5 ; HAN # Lo [20902] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FA5
F900..FA2D ; HAN # Lo [302] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA2D
FA30..FA6A ; HAN # Lo [59] CJK COMPATIBILITY IDEOGRAPH-FA30..CJK COMPATIBILITY IDEOGRAPH-FA6A
20000..2A6D6 ; HAN # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
2F800..2FA1D ; HAN # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 71382
# Total code points: 71442
# ================================================
@ -599,7 +605,7 @@ A4C6 ; YI # So YI RADICAL KE
# ================================================
10300..1031E ; OLD-ITALIC # Lo [31] OLD ITALIC LETTER A..OLD ITALIC LETTER UU
10300..1031E ; OLD_ITALIC # Lo [31] OLD ITALIC LETTER A..OLD ITALIC LETTER UU
# Total code points: 31
@ -619,8 +625,8 @@ A4C6 ; YI # So YI RADICAL KE
# ================================================
0300..034E ; INHERITED # Mn [79] COMBINING GRAVE ACCENT..COMBINING UPWARDS ARROW BELOW
0360..0362 ; INHERITED # Mn [3] COMBINING DOUBLE TILDE..COMBINING DOUBLE RIGHTWARDS ARROW BELOW
0300..034F ; INHERITED # Mn [80] COMBINING GRAVE ACCENT..COMBINING GRAPHEME JOINER
0360..036F ; INHERITED # Mn [16] COMBINING DOUBLE TILDE..COMBINING LATIN SMALL LETTER X
0488..0489 ; INHERITED # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN
0591..05A1 ; INHERITED # Mn [17] HEBREW ACCENT ETNAHTA..HEBREW ACCENT PAZER
05A3..05B9 ; INHERITED # Mn [23] HEBREW ACCENT MUNAH..HEBREW POINT HOLAM
@ -631,22 +637,56 @@ A4C6 ; YI # So YI RADICAL KE
064B..0655 ; INHERITED # Mn [11] ARABIC FATHATAN..ARABIC HAMZA BELOW
0670 ; INHERITED # Mn ARABIC LETTER SUPERSCRIPT ALEF
06D6..06DC ; INHERITED # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN
06DD..06DE ; INHERITED # Me [2] ARABIC END OF AYAH..ARABIC START OF RUB EL HIZB
06DD ; INHERITED # Cf ARABIC END OF AYAH
06DE ; INHERITED # Me ARABIC START OF RUB EL HIZB
06DF..06E4 ; INHERITED # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA
06E7..06E8 ; INHERITED # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON
06EA..06ED ; INHERITED # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM
180B..180D ; INHERITED # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
20D0..20DC ; INHERITED # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
20DD..20E0 ; INHERITED # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH
20E1 ; INHERITED # Mn COMBINING LEFT RIGHT ARROW ABOVE
20E2..20E3 ; INHERITED # Me [2] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING KEYCAP
20E2..20E4 ; INHERITED # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE
20E5..20EA ; INHERITED # Mn [6] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING LEFTWARDS ARROW OVERLAY
302A..302F ; INHERITED # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK
3099..309A ; INHERITED # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
FB1E ; INHERITED # Mn HEBREW POINT JUDEO-SPANISH VARIKA
FE00..FE0F ; INHERITED # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
FE20..FE23 ; INHERITED # Mn [4] COMBINING LIGATURE LEFT HALF..COMBINING DOUBLE TILDE RIGHT HALF
1D167..1D169 ; INHERITED # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3
1D17B..1D182 ; INHERITED # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE
1D185..1D18B ; INHERITED # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
1D1AA..1D1AD ; INHERITED # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
# Total code points: 219
# Total code points: 259
# ================================================
1700..170C ; TAGALOG # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA
170E..1711 ; TAGALOG # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA
1712..1714 ; TAGALOG # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA
# Total code points: 20
# ================================================
1720..1731 ; HANUNOO # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA
1732..1734 ; HANUNOO # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD
# Total code points: 21
# ================================================
1740..1751 ; BUHID # Lo [18] BUHID LETTER A..BUHID LETTER HA
1752..1753 ; BUHID # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U
# Total code points: 20
# ================================================
1760..176C ; TAGBANWA # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA
176E..1770 ; TAGBANWA # Lo [3] TAGBANWA LETTER LA..TAGBANWA LETTER SA
1772..1773 ; TAGBANWA # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U
# Total code points: 18