提交 71d225ba 编写于 作者: P peytoia

7198195: Support Unicode 6.2.0

Reviewed-by: okutsu
上级 5329fd1d
/*
* Copyright (c) 2003, 2011, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2003, 2012, Oracle and/or its affiliates. All rights reserved.
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
......@@ -311,6 +311,8 @@ class CharacterData01 extends CharacterData {
case 0x011063: retval = 90; break; // BRAHMI NUMBER NINETY
case 0x011064: retval = 100; break; // BRAHMI NUMBER ONE HUNDRED
case 0x011065: retval = 1000; break; // BRAHMI NUMBER ONE THOUSAND
case 0x012432: retval = 216000; break; // CUNEIFORM NUMERIC SIGN SHAR2 TIMES GAL PLUS DISH
case 0x012433: retval = 432000; break; // CUNEIFORM NUMERIC SIGN SHAR2 TIMES GAL PLUS MIN
case 0x01D36C: retval = 40; break; // COUNTING ROD TENS DIGIT FOUR
case 0x01D36D: retval = 50; break; // COUNTING ROD TENS DIGIT FIVE
case 0x01D36E: retval = 60; break; // COUNTING ROD TENS DIGIT SIX
......
# PropList-6.1.0.txt
# Date: 2011-11-30, 01:49:54 GMT [MD]
# PropList-6.2.0.txt
# Date: 2012-05-23, 20:34:59 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
......
# Scripts-6.1.0.txt
# Date: 2011-11-27, 05:10:50 GMT [MD]
# Scripts-6.2.0.txt
# Date: 2012-06-04, 17:21:29 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
......@@ -146,7 +146,7 @@
208A..208C ; Common # Sm [3] SUBSCRIPT PLUS SIGN..SUBSCRIPT EQUALS SIGN
208D ; Common # Ps SUBSCRIPT LEFT PARENTHESIS
208E ; Common # Pe SUBSCRIPT RIGHT PARENTHESIS
20A0..20B9 ; Common # Sc [26] EURO-CURRENCY SIGN..INDIAN RUPEE SIGN
20A0..20BA ; Common # Sc [27] EURO-CURRENCY SIGN..TURKISH LIRA SIGN
2100..2101 ; Common # So [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT
2102 ; Common # L& DOUBLE-STRUCK CAPITAL C
2103..2106 ; Common # So [4] DEGREE CELSIUS..CADA UNA
......@@ -576,7 +576,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
E0001 ; Common # Cf LANGUAGE TAG
E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
# Total code points: 6412
# Total code points: 6413
# ================================================
......@@ -760,7 +760,7 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU
061E ; Arabic # Po ARABIC TRIPLE DOT PUNCTUATION MARK
0620..063F ; Arabic # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE
0641..064A ; Arabic # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH
0656..065E ; Arabic # Mn [9] ARABIC SUBSCRIPT ALEF..ARABIC FATHA WITH TWO DOTS
0656..065F ; Arabic # Mn [10] ARABIC SUBSCRIPT ALEF..ARABIC WAVY HAMZA BELOW
066A..066D ; Arabic # Po [4] ARABIC PERCENT SIGN..ARABIC FIVE POINTED STAR
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
......@@ -827,7 +827,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
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: 1234
# Total code points: 1235
# ================================================
......@@ -1477,7 +1477,6 @@ A490..A4C6 ; Yi # So [55] YI RADICAL QOT..YI RADICAL KE
0300..036F ; Inherited # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X
0485..0486 ; Inherited # Mn [2] COMBINING CYRILLIC DASIA PNEUMATA..COMBINING CYRILLIC PSILI PNEUMATA
064B..0655 ; Inherited # Mn [11] ARABIC FATHATAN..ARABIC HAMZA BELOW
065F ; Inherited # Mn ARABIC WAVY HAMZA BELOW
0670 ; Inherited # Mn ARABIC LETTER SUPERSCRIPT ALEF
0951..0952 ; Inherited # Mn [2] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI STRESS SIGN ANUDATTA
1CD0..1CD2 ; Inherited # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA
......@@ -1504,7 +1503,7 @@ FE20..FE26 ; Inherited # Mn [7] COMBINING LIGATURE LEFT HALF..COMBINING CON
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: 524
# Total code points: 523
# ================================================
......
# SpecialCasing-6.1.0.txt
# Date: 2011-11-27, 05:10:51 GMT [MD]
# SpecialCasing-6.2.0.txt
# Date: 2012-05-23, 20:35:15 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
#
......
......@@ -7190,6 +7190,7 @@
20B7;SPESMILO SIGN;Sc;0;ET;;;;;N;;;;;
20B8;TENGE SIGN;Sc;0;ET;;;;;N;;;;;
20B9;INDIAN RUPEE SIGN;Sc;0;ET;;;;;N;;;;;
20BA;TURKISH LIRA SIGN;Sc;0;ET;;;;;N;;;;;
20D0;COMBINING LEFT HARPOON ABOVE;Mn;230;NSM;;;;;N;NON-SPACING LEFT HARPOON ABOVE;;;;
20D1;COMBINING RIGHT HARPOON ABOVE;Mn;230;NSM;;;;;N;NON-SPACING RIGHT HARPOON ABOVE;;;;
20D2;COMBINING LONG VERTICAL LINE OVERLAY;Mn;1;NSM;;;;;N;NON-SPACING LONG VERTICAL BAR OVERLAY;;;;
......@@ -18703,8 +18704,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
1242F;CUNEIFORM NUMERIC SIGN THREE SHARU VARIANT FORM;Nl;0;L;;;;3;N;;;;;
12430;CUNEIFORM NUMERIC SIGN FOUR SHARU;Nl;0;L;;;;4;N;;;;;
12431;CUNEIFORM NUMERIC SIGN FIVE SHARU;Nl;0;L;;;;5;N;;;;;
12432;CUNEIFORM NUMERIC SIGN SHAR2 TIMES GAL PLUS DISH;Nl;0;L;;;;;N;;;;;
12433;CUNEIFORM NUMERIC SIGN SHAR2 TIMES GAL PLUS MIN;Nl;0;L;;;;;N;;;;;
12432;CUNEIFORM NUMERIC SIGN SHAR2 TIMES GAL PLUS DISH;Nl;0;L;;;;216000;N;;;;;
12433;CUNEIFORM NUMERIC SIGN SHAR2 TIMES GAL PLUS MIN;Nl;0;L;;;;432000;N;;;;;
12434;CUNEIFORM NUMERIC SIGN ONE BURU;Nl;0;L;;;;1;N;;;;;
12435;CUNEIFORM NUMERIC SIGN TWO BURU;Nl;0;L;;;;2;N;;;;;
12436;CUNEIFORM NUMERIC SIGN THREE BURU;Nl;0;L;;;;3;N;;;;;
......@@ -18739,8 +18740,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
12453;CUNEIFORM NUMERIC SIGN FOUR BAN2 VARIANT FORM;Nl;0;L;;;;4;N;;;;;
12454;CUNEIFORM NUMERIC SIGN FIVE BAN2;Nl;0;L;;;;5;N;;;;;
12455;CUNEIFORM NUMERIC SIGN FIVE BAN2 VARIANT FORM;Nl;0;L;;;;5;N;;;;;
12456;CUNEIFORM NUMERIC SIGN NIGIDAMIN;Nl;0;L;;;;;N;;;;;
12457;CUNEIFORM NUMERIC SIGN NIGIDAESH;Nl;0;L;;;;;N;;;;;
12456;CUNEIFORM NUMERIC SIGN NIGIDAMIN;Nl;0;L;;;;-1;N;;;;;
12457;CUNEIFORM NUMERIC SIGN NIGIDAESH;Nl;0;L;;;;-1;N;;;;;
12458;CUNEIFORM NUMERIC SIGN ONE ESHE3;Nl;0;L;;;;1;N;;;;;
12459;CUNEIFORM NUMERIC SIGN TWO ESHE3;Nl;0;L;;;;2;N;;;;;
1245A;CUNEIFORM NUMERIC SIGN ONE THIRD DISH;Nl;0;L;;;;1/3;N;;;;;
......@@ -40,7 +40,7 @@ import java.util.Locale;
* a character's category (lowercase letter, digit, etc.) and for converting
* characters from uppercase to lowercase and vice versa.
* <p>
* Character information is based on the Unicode Standard, version 6.1.0.
* Character information is based on the Unicode Standard, version 6.2.0.
* <p>
* The methods and data of class {@code Character} are defined by
* the information in the <i>UnicodeData</i> file that is part of the
......@@ -3758,8 +3758,7 @@ class Character implements java.io.Serializable, Comparable<Character> {
0x0640, // 0640..0640; COMMON
0x0641, // 0641..064A; ARABIC
0x064B, // 064B..0655; INHERITED
0x0656, // 0656..065E; ARABIC
0x065F, // 065F..065F; INHERITED
0x0656, // 0656..065F; ARABIC
0x0660, // 0660..0669; COMMON
0x066A, // 066A..066F; ARABIC
0x0670, // 0670..0670; INHERITED
......@@ -4081,7 +4080,6 @@ class Character implements java.io.Serializable, Comparable<Character> {
ARABIC,
INHERITED,
ARABIC,
INHERITED,
COMMON,
ARABIC,
INHERITED,
......
......@@ -24,7 +24,7 @@
/**
* @test
* @bug 7037261 7070436
* @bug 7037261 7070436 7198195
* @summary Check j.l.Character.isLowerCase/isUppercase/isAlphabetic/isIdeographic
*/
......
......@@ -24,7 +24,7 @@
/**
* @test
* @bug 6945564 6959267 7033561 7070436
* @bug 6945564 6959267 7033561 7070436 7198195
* @summary Check that the j.l.Character.UnicodeScript
*/
......
# PropList-6.1.0.txt
# Date: 2011-11-30, 01:49:54 GMT [MD]
# PropList-6.2.0.txt
# Date: 2012-05-23, 20:34:59 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
......
# PropertyValueAliases-6.1.0.txt
# Date: 2011-12-07, 23:40:57 GMT [MD]
# PropertyValueAliases-6.2.0.txt
# Date: 2012-08-14, 16:05:11 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
#
......@@ -73,6 +73,7 @@ age; 5.1 ; V5_1
age; 5.2 ; V5_2
age; 6.0 ; V6_0
age; 6.1 ; V6_1
age; 6.2 ; V6_2
age; NA ; Unassigned
# Alphabetic (Alpha)
......@@ -382,7 +383,8 @@ ccc; 118; CCC118 ; CCC118
ccc; 122; CCC122 ; CCC122
ccc; 129; CCC129 ; CCC129
ccc; 130; CCC130 ; CCC130
ccc; 132; CCC133 ; CCC133
ccc; 132; CCC132 ; CCC132
ccc; 133; CCC133 ; CCC133 # RESERVED
ccc; 200; ATBL ; Attached_Below_Left
ccc; 202; ATB ; Attached_Below
ccc; 214; ATA ; Attached_Above
......@@ -592,6 +594,7 @@ GCB; LF ; LF
GCB; LV ; LV
GCB; LVT ; LVT
GCB; PP ; Prepend
GCB; RI ; Regional_Indicator
GCB; SM ; SpacingMark
GCB; T ; T
GCB; V ; V
......@@ -862,6 +865,7 @@ lb ; OP ; Open_Punctuation
lb ; PO ; Postfix_Numeric
lb ; PR ; Prefix_Numeric
lb ; QU ; Quotation
lb ; RI ; Regional_Indicator
lb ; SA ; Complex_Context
lb ; SG ; Surrogate
lb ; SP ; Space
......@@ -880,10 +884,6 @@ LOE; Y ; Yes ; T
Lower; N ; No ; F ; False
Lower; Y ; Yes ; T ; True
# Lowercase_Mapping (lc)
# @missing: 0000..10FFFF; Lowercase_Mapping; <code point>
# Math (Math)
Math; N ; No ; F ; False
......@@ -1159,10 +1159,6 @@ SD ; Y ; Yes ; T
Term; N ; No ; F ; False
Term; Y ; Yes ; T ; True
# Titlecase_Mapping (tc)
# @missing: 0000..10FFFF; Titlecase_Mapping; <code point>
# Unicode_1_Name (na1)
# @missing: 0000..10FFFF; Unicode_1_Name; <none>
......@@ -1177,10 +1173,6 @@ UIdeo; Y ; Yes ; T
Upper; N ; No ; F ; False
Upper; Y ; Yes ; T ; True
# Uppercase_Mapping (uc)
# @missing: 0000..10FFFF; Uppercase_Mapping; <code point>
# Variation_Selector (VS)
VS ; N ; No ; F ; False
......@@ -1205,6 +1197,7 @@ WB ; ML ; MidLetter
WB ; MN ; MidNum
WB ; NL ; Newline
WB ; NU ; Numeric
WB ; RI ; Regional_Indicator
WB ; XX ; Other
# XID_Continue (XIDC)
......
# Scripts-6.1.0.txt
# Date: 2011-11-27, 05:10:50 GMT [MD]
# Scripts-6.2.0.txt
# Date: 2012-06-04, 17:21:29 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
......@@ -146,7 +146,7 @@
208A..208C ; Common # Sm [3] SUBSCRIPT PLUS SIGN..SUBSCRIPT EQUALS SIGN
208D ; Common # Ps SUBSCRIPT LEFT PARENTHESIS
208E ; Common # Pe SUBSCRIPT RIGHT PARENTHESIS
20A0..20B9 ; Common # Sc [26] EURO-CURRENCY SIGN..INDIAN RUPEE SIGN
20A0..20BA ; Common # Sc [27] EURO-CURRENCY SIGN..TURKISH LIRA SIGN
2100..2101 ; Common # So [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT
2102 ; Common # L& DOUBLE-STRUCK CAPITAL C
2103..2106 ; Common # So [4] DEGREE CELSIUS..CADA UNA
......@@ -576,7 +576,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
E0001 ; Common # Cf LANGUAGE TAG
E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
# Total code points: 6412
# Total code points: 6413
# ================================================
......@@ -760,7 +760,7 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU
061E ; Arabic # Po ARABIC TRIPLE DOT PUNCTUATION MARK
0620..063F ; Arabic # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE
0641..064A ; Arabic # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH
0656..065E ; Arabic # Mn [9] ARABIC SUBSCRIPT ALEF..ARABIC FATHA WITH TWO DOTS
0656..065F ; Arabic # Mn [10] ARABIC SUBSCRIPT ALEF..ARABIC WAVY HAMZA BELOW
066A..066D ; Arabic # Po [4] ARABIC PERCENT SIGN..ARABIC FIVE POINTED STAR
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
......@@ -827,7 +827,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
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: 1234
# Total code points: 1235
# ================================================
......@@ -1477,7 +1477,6 @@ A490..A4C6 ; Yi # So [55] YI RADICAL QOT..YI RADICAL KE
0300..036F ; Inherited # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X
0485..0486 ; Inherited # Mn [2] COMBINING CYRILLIC DASIA PNEUMATA..COMBINING CYRILLIC PSILI PNEUMATA
064B..0655 ; Inherited # Mn [11] ARABIC FATHATAN..ARABIC HAMZA BELOW
065F ; Inherited # Mn ARABIC WAVY HAMZA BELOW
0670 ; Inherited # Mn ARABIC LETTER SUPERSCRIPT ALEF
0951..0952 ; Inherited # Mn [2] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI STRESS SIGN ANUDATTA
1CD0..1CD2 ; Inherited # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA
......@@ -1504,7 +1503,7 @@ FE20..FE26 ; Inherited # Mn [7] COMBINING LIGATURE LEFT HALF..COMBINING CON
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: 524
# Total code points: 523
# ================================================
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册