ICU-11574 Unicode 8.0 final data

X-SVN-Rev: 37548
This commit is contained in:
Markus Scherer 2015-06-12 11:10:10 +00:00
parent 75ed4ce808
commit 7c3234e250
6 changed files with 1275 additions and 1189 deletions

File diff suppressed because it is too large Load Diff

Binary file not shown.

Binary file not shown.

View File

@ -1,6 +1,6 @@
# Original file:
# IdnaMappingTable-8.0.0.txt
# Date: 2015-02-06 12:20:37 GMT [MD]
# Date: 2015-05-02 12:42:14 GMT [MD]
#
# Unicode IDNA Compatible Preprocessing (UTS #46)
# Copyright (c) 1991-2015 Unicode, Inc.
@ -1543,10 +1543,15 @@
# 1380..138F valid # 4.1 ETHIOPIC SYLLABLE SEBATBEIT MWA..ETHIOPIC SYLLABLE PWE
# 1390..1399 valid # 4.1 ETHIOPIC TONAL MARK YIZET..ETHIOPIC TONAL MARK KURT
139A..139F >FFFD # NA <reserved-139A>..<reserved-139F>
13A0..13F4 >FFFD # 3.0 CHEROKEE LETTER A..CHEROKEE LETTER YV
13F5 >13FD # 8.0 CHEROKEE LETTER MV
# 13A0..13F4 valid # 3.0 CHEROKEE LETTER A..CHEROKEE LETTER YV
# 13F5 valid # 8.0 CHEROKEE LETTER MV
13F6..13F7 >FFFD # NA <reserved-13F6>..<reserved-13F7>
# 13F8..13FD valid # 8.0 CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV
13F8 >13F0 # 8.0 CHEROKEE SMALL LETTER YE
13F9 >13F1 # 8.0 CHEROKEE SMALL LETTER YI
13FA >13F2 # 8.0 CHEROKEE SMALL LETTER YO
13FB >13F3 # 8.0 CHEROKEE SMALL LETTER YU
13FC >13F4 # 8.0 CHEROKEE SMALL LETTER YV
13FD >13F5 # 8.0 CHEROKEE SMALL LETTER MV
13FE..13FF >FFFD # NA <reserved-13FE>..<reserved-13FF>
# 1400 valid # 5.2 CANADIAN SYLLABICS HYPHEN
# 1401..166C valid # 3.0 CANADIAN SYLLABICS E..CANADIAN SYLLABICS CARRIER TTSA
@ -4160,7 +4165,86 @@ AB5F >AB52 # 7.0 MODIFIER LETTER SMALL U WITH LEFT
# AB60..AB63 valid # 8.0 LATIN SMALL LETTER SAKHA YAT..LATIN SMALL LETTER UO
# AB64..AB65 valid # 7.0 LATIN SMALL LETTER INVERTED ALPHA..GREEK LETTER SMALL CAPITAL OMEGA
AB66..AB6F >FFFD # NA <reserved-AB66>..<reserved-AB6F>
# AB70..ABBF valid # 8.0 CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA
AB70 >13A0 # 8.0 CHEROKEE SMALL LETTER A
AB71 >13A1 # 8.0 CHEROKEE SMALL LETTER E
AB72 >13A2 # 8.0 CHEROKEE SMALL LETTER I
AB73 >13A3 # 8.0 CHEROKEE SMALL LETTER O
AB74 >13A4 # 8.0 CHEROKEE SMALL LETTER U
AB75 >13A5 # 8.0 CHEROKEE SMALL LETTER V
AB76 >13A6 # 8.0 CHEROKEE SMALL LETTER GA
AB77 >13A7 # 8.0 CHEROKEE SMALL LETTER KA
AB78 >13A8 # 8.0 CHEROKEE SMALL LETTER GE
AB79 >13A9 # 8.0 CHEROKEE SMALL LETTER GI
AB7A >13AA # 8.0 CHEROKEE SMALL LETTER GO
AB7B >13AB # 8.0 CHEROKEE SMALL LETTER GU
AB7C >13AC # 8.0 CHEROKEE SMALL LETTER GV
AB7D >13AD # 8.0 CHEROKEE SMALL LETTER HA
AB7E >13AE # 8.0 CHEROKEE SMALL LETTER HE
AB7F >13AF # 8.0 CHEROKEE SMALL LETTER HI
AB80 >13B0 # 8.0 CHEROKEE SMALL LETTER HO
AB81 >13B1 # 8.0 CHEROKEE SMALL LETTER HU
AB82 >13B2 # 8.0 CHEROKEE SMALL LETTER HV
AB83 >13B3 # 8.0 CHEROKEE SMALL LETTER LA
AB84 >13B4 # 8.0 CHEROKEE SMALL LETTER LE
AB85 >13B5 # 8.0 CHEROKEE SMALL LETTER LI
AB86 >13B6 # 8.0 CHEROKEE SMALL LETTER LO
AB87 >13B7 # 8.0 CHEROKEE SMALL LETTER LU
AB88 >13B8 # 8.0 CHEROKEE SMALL LETTER LV
AB89 >13B9 # 8.0 CHEROKEE SMALL LETTER MA
AB8A >13BA # 8.0 CHEROKEE SMALL LETTER ME
AB8B >13BB # 8.0 CHEROKEE SMALL LETTER MI
AB8C >13BC # 8.0 CHEROKEE SMALL LETTER MO
AB8D >13BD # 8.0 CHEROKEE SMALL LETTER MU
AB8E >13BE # 8.0 CHEROKEE SMALL LETTER NA
AB8F >13BF # 8.0 CHEROKEE SMALL LETTER HNA
AB90 >13C0 # 8.0 CHEROKEE SMALL LETTER NAH
AB91 >13C1 # 8.0 CHEROKEE SMALL LETTER NE
AB92 >13C2 # 8.0 CHEROKEE SMALL LETTER NI
AB93 >13C3 # 8.0 CHEROKEE SMALL LETTER NO
AB94 >13C4 # 8.0 CHEROKEE SMALL LETTER NU
AB95 >13C5 # 8.0 CHEROKEE SMALL LETTER NV
AB96 >13C6 # 8.0 CHEROKEE SMALL LETTER QUA
AB97 >13C7 # 8.0 CHEROKEE SMALL LETTER QUE
AB98 >13C8 # 8.0 CHEROKEE SMALL LETTER QUI
AB99 >13C9 # 8.0 CHEROKEE SMALL LETTER QUO
AB9A >13CA # 8.0 CHEROKEE SMALL LETTER QUU
AB9B >13CB # 8.0 CHEROKEE SMALL LETTER QUV
AB9C >13CC # 8.0 CHEROKEE SMALL LETTER SA
AB9D >13CD # 8.0 CHEROKEE SMALL LETTER S
AB9E >13CE # 8.0 CHEROKEE SMALL LETTER SE
AB9F >13CF # 8.0 CHEROKEE SMALL LETTER SI
ABA0 >13D0 # 8.0 CHEROKEE SMALL LETTER SO
ABA1 >13D1 # 8.0 CHEROKEE SMALL LETTER SU
ABA2 >13D2 # 8.0 CHEROKEE SMALL LETTER SV
ABA3 >13D3 # 8.0 CHEROKEE SMALL LETTER DA
ABA4 >13D4 # 8.0 CHEROKEE SMALL LETTER TA
ABA5 >13D5 # 8.0 CHEROKEE SMALL LETTER DE
ABA6 >13D6 # 8.0 CHEROKEE SMALL LETTER TE
ABA7 >13D7 # 8.0 CHEROKEE SMALL LETTER DI
ABA8 >13D8 # 8.0 CHEROKEE SMALL LETTER TI
ABA9 >13D9 # 8.0 CHEROKEE SMALL LETTER DO
ABAA >13DA # 8.0 CHEROKEE SMALL LETTER DU
ABAB >13DB # 8.0 CHEROKEE SMALL LETTER DV
ABAC >13DC # 8.0 CHEROKEE SMALL LETTER DLA
ABAD >13DD # 8.0 CHEROKEE SMALL LETTER TLA
ABAE >13DE # 8.0 CHEROKEE SMALL LETTER TLE
ABAF >13DF # 8.0 CHEROKEE SMALL LETTER TLI
ABB0 >13E0 # 8.0 CHEROKEE SMALL LETTER TLO
ABB1 >13E1 # 8.0 CHEROKEE SMALL LETTER TLU
ABB2 >13E2 # 8.0 CHEROKEE SMALL LETTER TLV
ABB3 >13E3 # 8.0 CHEROKEE SMALL LETTER TSA
ABB4 >13E4 # 8.0 CHEROKEE SMALL LETTER TSE
ABB5 >13E5 # 8.0 CHEROKEE SMALL LETTER TSI
ABB6 >13E6 # 8.0 CHEROKEE SMALL LETTER TSO
ABB7 >13E7 # 8.0 CHEROKEE SMALL LETTER TSU
ABB8 >13E8 # 8.0 CHEROKEE SMALL LETTER TSV
ABB9 >13E9 # 8.0 CHEROKEE SMALL LETTER WA
ABBA >13EA # 8.0 CHEROKEE SMALL LETTER WE
ABBB >13EB # 8.0 CHEROKEE SMALL LETTER WI
ABBC >13EC # 8.0 CHEROKEE SMALL LETTER WO
ABBD >13ED # 8.0 CHEROKEE SMALL LETTER WU
ABBE >13EE # 8.0 CHEROKEE SMALL LETTER WV
ABBF >13EF # 8.0 CHEROKEE SMALL LETTER YA
# ABC0..ABEA valid # 5.2 MEETEI MAYEK LETTER KOK..MEETEI MAYEK VOWEL SIGN NUNG
# ABEB valid # 5.2 MEETEI MAYEK CHEIKHEI
# ABEC..ABED valid # 5.2 MEETEI MAYEK LUM IYEK..MEETEI MAYEK APUN IYEK
@ -7465,7 +7549,7 @@ FFFE..FFFF >FFFD # 1.1 <noncharacter-FFFE>..<noncharacte
# 1F3D4..1F3DFvalid # 7.0 SNOW CAPPED MOUNTAIN..STADIUM
# 1F3E0..1F3F0valid # 6.0 HOUSE BUILDING..EUROPEAN CASTLE
# 1F3F1..1F3F7valid # 7.0 WHITE PENNANT..LABEL
# 1F3F8..1F3FFvalid # 8.0 BADMINTON RACQUET AND BIRDIE..EMOJI MODIFIER FITZPATRICK TYPE-6
# 1F3F8..1F3FFvalid # 8.0 BADMINTON RACQUET AND SHUTTLECOCK..EMOJI MODIFIER FITZPATRICK TYPE-6
# 1F400..1F43Evalid # 6.0 RAT..PAW PRINTS
# 1F43F valid # 7.0 CHIPMUNK
# 1F440 valid # 6.0 EYES
@ -7534,9 +7618,7 @@ FFFE..FFFF >FFFD # 1.1 <noncharacter-FFFE>..<noncharacte
# 1F860..1F887valid # 7.0 WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW
1F888..1F88F >FFFD # NA <reserved-1F888>..<reserved-1F88F>
# 1F890..1F8ADvalid # 7.0 LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS
1F8AE..1F8FF >FFFD # NA <reserved-1F8AE>..<reserved-1F8FF>
# 1F900 valid # 8.0 DHYANI BUDDHA
1F901..1F90F >FFFD # NA <reserved-1F901>..<reserved-1F90F>
1F8AE..1F90F >FFFD # NA <reserved-1F8AE>..<reserved-1F90F>
# 1F910..1F918valid # 8.0 ZIPPER-MOUTH FACE..SIGN OF THE HORNS
1F919..1F97F >FFFD # NA <reserved-1F919>..<reserved-1F97F>
# 1F980..1F984valid # 8.0 CRAB..UNICORN FACE

View File

@ -4228,10 +4228,11 @@ cp;0BEF;-Alpha;gc=Nd;InSC=Number;lb=NU;na=TAMIL DIGIT NINE;nt=De;nv=9;SB=NU;scx=
cp;0BF0;-Alpha;gc=No;-IDC;na=TAMIL NUMBER TEN;nt=Nu;nv=10;SB=XX;scx=Gran Taml;WB=XX;-XIDC
cp;0BF1;-Alpha;gc=No;-IDC;na=TAMIL NUMBER ONE HUNDRED;nt=Nu;nv=100;SB=XX;scx=Gran Taml;WB=XX;-XIDC
cp;0BF2;-Alpha;gc=No;-IDC;na=TAMIL NUMBER ONE THOUSAND;nt=Nu;nv=1000;SB=XX;scx=Gran Taml;WB=XX;-XIDC
# Tamil symbols
# Tamil calendrical symbols
cp;0BF3;age=4.0;-Alpha;bc=ON;gc=So;-IDC;na=TAMIL DAY SIGN;SB=XX;WB=XX;-XIDC
cp;0BF4;age=4.0;-Alpha;bc=ON;gc=So;-IDC;na=TAMIL MONTH SIGN;SB=XX;WB=XX;-XIDC
cp;0BF5;age=4.0;-Alpha;bc=ON;gc=So;-IDC;na=TAMIL YEAR SIGN;SB=XX;WB=XX;-XIDC
# Tamil clerical symbols
cp;0BF6;age=4.0;-Alpha;bc=ON;gc=So;-IDC;na=TAMIL DEBIT SIGN;SB=XX;WB=XX;-XIDC
cp;0BF7;age=4.0;-Alpha;bc=ON;gc=So;-IDC;na=TAMIL CREDIT SIGN;SB=XX;WB=XX;-XIDC
cp;0BF8;age=4.0;-Alpha;bc=ON;gc=So;-IDC;na=TAMIL AS ABOVE SIGN;SB=XX;WB=XX;-XIDC
@ -28694,7 +28695,7 @@ cp;1D1B2;na=MUSICAL SYMBOL GLISSANDO DOWN
cp;1D1B3;na=MUSICAL SYMBOL WITH FINGERNAILS
cp;1D1B4;na=MUSICAL SYMBOL DAMP
cp;1D1B5;na=MUSICAL SYMBOL DAMP ALL
# Mensural notation
# Mensural notes
cp;1D1B6;na=MUSICAL SYMBOL MAXIMA
cp;1D1B7;na=MUSICAL SYMBOL LONGA
cp;1D1B8;na=MUSICAL SYMBOL BREVIS
@ -28724,10 +28725,12 @@ cp;1D1CD;na=MUSICAL SYMBOL TEMPUS IMPERFECTUM CUM PROLATIONE IMPERFECTA DIMINUTI
cp;1D1CE;na=MUSICAL SYMBOL TEMPUS IMPERFECTUM CUM PROLATIONE IMPERFECTA DIMINUTION-3
# Miscellaneous symbol
cp;1D1CF;na=MUSICAL SYMBOL CROIX
# Gregorian notation
# Clefs
cp;1D1D0;na=MUSICAL SYMBOL GREGORIAN C CLEF
cp;1D1D1;na=MUSICAL SYMBOL GREGORIAN F CLEF
# Accidental
cp;1D1D2;na=MUSICAL SYMBOL SQUARE B
# Notes
cp;1D1D3;na=MUSICAL SYMBOL VIRGA
cp;1D1D4;na=MUSICAL SYMBOL PODATUS
cp;1D1D5;na=MUSICAL SYMBOL CLIVIS
@ -32943,7 +32946,7 @@ cp;1F79A;na=WHITE DIAMOND CONTAINING BLACK VERY SMALL DIAMOND
cp;1F79B;na=WHITE DIAMOND CONTAINING BLACK MEDIUM DIAMOND
# Target symbol
cp;1F79C;na=DIAMOND TARGET
# Lozenges
# Black lozenges
cp;1F79D;na=BLACK TINY LOZENGE
cp;1F79E;na=BLACK VERY SMALL LOZENGE
cp;1F79F;na=BLACK MEDIUM SMALL LOZENGE
@ -33837,12 +33840,12 @@ cp;CFFFE..CFFFF;age=2.0;bc=BN;NChar
# Noncharacters
cp;DFFFE..DFFFF;age=2.0;bc=BN;NChar
block;E0000..E007F;age=3.1;bc=BN;blk=Tags;CI;CWKCF;Dep;DI;gc=Cf;GCB=CN;jt=T;lb=CM;NFKC_CF=;SB=FO;sc=Zyyy;WB=FO
block;E0000..E007F;age=3.1;bc=BN;blk=Tags;CI;CWKCF;DI;gc=Cf;GCB=CN;jt=T;lb=CM;NFKC_CF=;SB=FO;sc=Zyyy;WB=FO
# E0000..E007F Tags
cp;E0000;age=NA;-CI;-Dep;gc=Cn;jt=U;lb=XX;SB=XX;sc=Zzzz;WB=XX
cp;E0000;age=NA;-CI;gc=Cn;jt=U;lb=XX;SB=XX;sc=Zzzz;WB=XX
# Tag identifiers
cp;E0001;na=LANGUAGE TAG
cp;E0002..E001F;age=NA;-CI;-Dep;gc=Cn;jt=U;lb=XX;SB=XX;sc=Zzzz;WB=XX
cp;E0001;Dep;na=LANGUAGE TAG
cp;E0002..E001F;age=NA;-CI;gc=Cn;jt=U;lb=XX;SB=XX;sc=Zzzz;WB=XX
# Tag components
cp;E0020;na=TAG SPACE
cp;E0021;na=TAG EXCLAMATION MARK
@ -33939,7 +33942,8 @@ cp;E007B;na=TAG LEFT CURLY BRACKET
cp;E007C;na=TAG VERTICAL LINE
cp;E007D;na=TAG RIGHT CURLY BRACKET
cp;E007E;na=TAG TILDE
cp;E007F;na=CANCEL TAG
# Stateful tag terminator
cp;E007F;Dep;na=CANCEL TAG
cp;E0080..E00FF;bc=BN;CWKCF;DI;GCB=CN;NFKC_CF=
block;E0100..E01EF;age=4.0;bc=NSM;blk=VS_Sup;CI;CWKCF;DI;ea=A;gc=Mn;GCB=EX;Gr_Ext;IDC;jt=T;lb=CM;NFKC_CF=;SB=EX;sc=Zinh;VS;WB=Extend;XIDC

View File

@ -1,6 +1,6 @@
/********************************************************************
* COPYRIGHT:
* Copyright (c) 1997-2014, International Business Machines Corporation and
* Copyright (c) 1997-2015, International Business Machines Corporation and
* others. All Rights Reserved.
********************************************************************/
/*******************************************************************************
@ -2395,7 +2395,7 @@ TestAdditionalProperties() {
{ 0x0149, UCHAR_DEPRECATED, TRUE }, /* changed in Unicode 5.2 */
{ 0x0341, UCHAR_DEPRECATED, FALSE }, /* changed in Unicode 5.2 */
{ 0xe0041, UCHAR_DEPRECATED, TRUE }, /* changed from Unicode 5 to 5.1 */
{ 0xe0001, UCHAR_DEPRECATED, TRUE }, /* changed from Unicode 5 to 5.1 */
{ 0xe0100, UCHAR_DEPRECATED, FALSE },
{ 0x00a0, UCHAR_GRAPHEME_BASE, TRUE },