organicmaps/icu
13
Fork 0
mirror of https://github.com/unicode-org/icu.git synced 2025-04-06 05:55:35 +00:00
Code Issues 1 Projects Releases Wiki Activity Actions 11

ICU-12526 integrate Unicode 9 beta

Browse source 
X-SVN-Rev: 38753
This commit is contained in:
Markus Scherer 2016-05-19 22:48:18 +00:00
parent 8cf118d150
commit 5e69db5c2f
73 changed files with 40214 additions and 19249 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1076
icu4c/source/common/norm2_nfc_data.h
View file

File diff suppressed because it is too large Load diff

1489
icu4c/source/common/propname_data.h
View file

File diff suppressed because it is too large Load diff

1178
icu4c/source/common/ubidi_props_data.h
View file

File diff suppressed because it is too large Load diff

1335
icu4c/source/common/ucase_props_data.h
View file

File diff suppressed because it is too large Load diff

10
icu4c/source/common/uchar.c
View file

@ -1,6 +1,6 @@
/*
********************************************************************************
* Copyright (C) 1996-2014, International Business Machines
* Copyright (C) 1996-2016, International Business Machines
* Corporation and others. All Rights Reserved.
********************************************************************************
*
@ -434,7 +434,7 @@ u_getNumericValue(UChar32 c) {
}
return numValue;
} else if(ntv<UPROPS_NTV_RESERVED_START) {
} else if(ntv<UPROPS_NTV_FRACTION20_START) {
/* sexagesimal (base 60) integer */
int32_t numValue=(ntv>>2)-0xbf;
int32_t exp=(ntv&3)+1;
@ -458,6 +458,12 @@ u_getNumericValue(UChar32 c) {
}
return numValue;
} else if(ntv<UPROPS_NTV_RESERVED_START) {
// fraction-20 e.g. 3/80
int32_t frac20=ntv-UPROPS_NTV_FRACTION20_START; // 0..0x17
int32_t numerator=2*(frac20&3)+1;
int32_t denominator=20<<(frac20>>2);
return (double)numerator/denominator;
} else {
/* reserved */
return U_NO_NUMERIC_VALUE;

6080
icu4c/source/common/uchar_props_data.h
View file

File diff suppressed because it is too large Load diff

87
icu4c/source/common/unicode/uchar.h
View file

@ -39,7 +39,7 @@ U_CDECL_BEGIN
* @see u_getUnicodeVersion
* @stable ICU 2.0
*/
#define U_UNICODE_VERSION "8.0"
#define U_UNICODE_VERSION "9.0"
/**
* \file
@ -1572,8 +1572,33 @@ enum UBlockCode {
/** @stable ICU 56 */
UBLOCK_SUTTON_SIGNWRITING = 262, /*[1D800]*/
/* New blocks in Unicode 9.0 */
/** @stable ICU 58 */
UBLOCK_ADLAM = 263, /*[1E900]*/
/** @stable ICU 58 */
UBLOCK_BHAIKSUKI = 264, /*[11C00]*/
/** @stable ICU 58 */
UBLOCK_CYRILLIC_EXTENDED_C = 265, /*[1C80]*/
/** @stable ICU 58 */
UBLOCK_GLAGOLITIC_SUPPLEMENT = 266, /*[1E000]*/
/** @stable ICU 58 */
UBLOCK_IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION = 267, /*[16FE0]*/
/** @stable ICU 58 */
UBLOCK_MARCHEN = 268, /*[11C70]*/
/** @stable ICU 58 */
UBLOCK_MONGOLIAN_SUPPLEMENT = 269, /*[11660]*/
/** @stable ICU 58 */
UBLOCK_NEWA = 270, /*[11400]*/
/** @stable ICU 58 */
UBLOCK_OSAGE = 271, /*[104B0]*/
/** @stable ICU 58 */
UBLOCK_TANGUT = 272, /*[17000]*/
/** @stable ICU 58 */
UBLOCK_TANGUT_COMPONENTS = 273, /*[18800]*/
/** @stable ICU 2.0 */
UBLOCK_COUNT = 263,
UBLOCK_COUNT = 274,
/** @stable ICU 2.0 */
UBLOCK_INVALID_CODE=-1
@ -1810,6 +1835,9 @@ typedef enum UJoiningGroup {
U_JG_MANICHAEAN_YODH, /**< @stable ICU 54 */
U_JG_MANICHAEAN_ZAYIN, /**< @stable ICU 54 */
U_JG_STRAIGHT_WAW, /**< @stable ICU 54 */
U_JG_AFRICAN_FEH, /**< @stable ICU 58 */
U_JG_AFRICAN_NOON, /**< @stable ICU 58 */
U_JG_AFRICAN_QAF, /**< @stable ICU 58 */
U_JG_COUNT
} UJoiningGroup;
@ -1836,10 +1864,23 @@ typedef enum UGraphemeClusterBreak {
U_GCB_LVT = 7, /*[LVT]*/
U_GCB_T = 8, /*[T]*/
U_GCB_V = 9, /*[V]*/
/** @stable ICU 4.0 */
U_GCB_SPACING_MARK = 10, /*[SM]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
/** @stable ICU 4.0 */
U_GCB_PREPEND = 11, /*[PP]*/
/** @stable ICU 50 */
U_GCB_REGIONAL_INDICATOR = 12, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */
U_GCB_COUNT = 13
/** @stable ICU 58 */
U_GCB_E_BASE = 13, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */
/** @stable ICU 58 */
U_GCB_E_BASE_GAZ = 14, /*[EBG]*/
/** @stable ICU 58 */
U_GCB_E_MODIFIER = 15, /*[EM]*/
/** @stable ICU 58 */
U_GCB_GLUE_AFTER_ZWJ = 16, /*[GAZ]*/
/** @stable ICU 58 */
U_GCB_ZWJ = 17, /*[ZWJ]*/
U_GCB_COUNT = 18
} UGraphemeClusterBreak;
/**
@ -1864,16 +1905,35 @@ typedef enum UWordBreakValues {
U_WB_MIDNUM = 5, /*[MN]*/
U_WB_NUMERIC = 6, /*[NU]*/
U_WB_EXTENDNUMLET = 7, /*[EX]*/
/** @stable ICU 4.0 */
U_WB_CR = 8, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
/** @stable ICU 4.0 */
U_WB_EXTEND = 9, /*[Extend]*/
/** @stable ICU 4.0 */
U_WB_LF = 10, /*[LF]*/
/** @stable ICU 4.0 */
U_WB_MIDNUMLET =11, /*[MB]*/
/** @stable ICU 4.0 */
U_WB_NEWLINE =12, /*[NL]*/
/** @stable ICU 50 */
U_WB_REGIONAL_INDICATOR = 13, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */
/** @stable ICU 52 */
U_WB_HEBREW_LETTER = 14, /*[HL]*/ /* from here on: new in Unicode 6.3/ICU 52 */
/** @stable ICU 52 */
U_WB_SINGLE_QUOTE = 15, /*[SQ]*/
/** @stable ICU 52 */
U_WB_DOUBLE_QUOTE = 16, /*[DQ]*/
U_WB_COUNT = 17
/** @stable ICU 58 */
U_WB_E_BASE = 17, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */
/** @stable ICU 58 */
U_WB_E_BASE_GAZ = 18, /*[EBG]*/
/** @stable ICU 58 */
U_WB_E_MODIFIER = 19, /*[EM]*/
/** @stable ICU 58 */
U_WB_GLUE_AFTER_ZWJ = 20, /*[GAZ]*/
/** @stable ICU 58 */
U_WB_ZWJ = 21, /*[ZWJ]*/
U_WB_COUNT = 22
} UWordBreakValues;
/**
@ -1951,18 +2011,35 @@ typedef enum ULineBreak {
U_LB_SPACE = 26, /*[SP]*/
U_LB_BREAK_SYMBOLS = 27, /*[SY]*/
U_LB_ZWSPACE = 28, /*[ZW]*/
/** @stable ICU 2.6 */
U_LB_NEXT_LINE = 29, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */
/** @stable ICU 2.6 */
U_LB_WORD_JOINER = 30, /*[WJ]*/
/** @stable ICU 3.4 */
U_LB_H2 = 31, /*[H2]*/ /* from here on: new in Unicode 4.1/ICU 3.4 */
/** @stable ICU 3.4 */
U_LB_H3 = 32, /*[H3]*/
/** @stable ICU 3.4 */
U_LB_JL = 33, /*[JL]*/
/** @stable ICU 3.4 */
U_LB_JT = 34, /*[JT]*/
/** @stable ICU 3.4 */
U_LB_JV = 35, /*[JV]*/
/** @stable ICU 4.4 */
U_LB_CLOSE_PARENTHESIS = 36, /*[CP]*/ /* new in Unicode 5.2/ICU 4.4 */
/** @stable ICU 49 */
U_LB_CONDITIONAL_JAPANESE_STARTER = 37,/*[CJ]*/ /* new in Unicode 6.1/ICU 49 */
/** @stable ICU 49 */
U_LB_HEBREW_LETTER = 38, /*[HL]*/ /* new in Unicode 6.1/ICU 49 */
/** @stable ICU 50 */
U_LB_REGIONAL_INDICATOR = 39,/*[RI]*/ /* new in Unicode 6.2/ICU 50 */
U_LB_COUNT = 40
/** @stable ICU 58 */
U_LB_E_BASE = 40, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */
/** @stable ICU 58 */
U_LB_E_MODIFIER = 41, /*[EM]*/
/** @stable ICU 58 */
U_LB_ZWJ = 42, /*[ZWJ]*/
U_LB_COUNT = 43
} ULineBreak;
/**

9
icu4c/source/common/uprops.h
View file

@ -86,8 +86,15 @@ enum {
* ((ntv>>2)-0xbf) * 60^((ntv&3)+1) = (1..9)*(60^1..60^4)
*/
UPROPS_NTV_BASE60_START=0x300,
/**
* Fraction-20 values:
* frac20 = ntv-0x324 = 0..0x17 -> 1|3|5|7 / 20|40|80|160|320|640
* numerator: num = 2*(frac20&3)+1
* denominator: den = 20<<(frac20>>2)
*/
UPROPS_NTV_FRACTION20_START=UPROPS_NTV_BASE60_START+36, // 0x300+9*4=0x324
/** No numeric value (yet). */
UPROPS_NTV_RESERVED_START=UPROPS_NTV_BASE60_START+36, /* 0x300+9*4=0x324 */
UPROPS_NTV_RESERVED_START=UPROPS_NTV_FRACTION20_START+24, // 0x324+6*4=0x34c
UPROPS_NTV_MAX_SMALL_INT=UPROPS_NTV_FRACTION_START-UPROPS_NTV_NUMERIC_START-1
};

24
icu4c/source/common/uscript_props.cpp
View file

@ -1,6 +1,6 @@
/*
*******************************************************************************
* Copyright (C) 2013-2015, International Business Machines
* Copyright (C) 2013-2016, International Business Machines
* Corporation and others. All Rights Reserved.
*******************************************************************************
* file name: uscript_props.cpp
@ -72,7 +72,7 @@ const int32_t SCRIPT_PROPS[] = {
0x1826 | ASPIRATIONAL, // Mong
0x1000 | RECOMMENDED | LB_LETTERS, // Mymr
0x168F | EXCLUSION, // Ogam
0x10308 | EXCLUSION, // Ital
0x10300 | EXCLUSION, // Ital
0x0B15 | RECOMMENDED, // Orya
0x16A0 | EXCLUSION, // Runr
0x0D85 | RECOMMENDED, // Sinh
@ -102,7 +102,7 @@ const int32_t SCRIPT_PROPS[] = {
0x10A00 | EXCLUSION | RTL, // Khar
0xA800 | LIMITED_USE, // Sylo
0x1980 | LIMITED_USE | LB_LETTERS, // Talu
0x2D5E | ASPIRATIONAL, // Tfng
0x2D30 | ASPIRATIONAL, // Tfng
0x103A0 | EXCLUSION, // Xpeo
0x1B05 | LIMITED_USE, // Bali
0x1BC0 | LIMITED_USE, // Batk
@ -129,7 +129,7 @@ const int32_t SCRIPT_PROPS[] = {
0x0840 | LIMITED_USE | RTL, // Mand
0,
0x10980 | EXCLUSION | RTL, // Mero
0x07D8 | LIMITED_USE | RTL, // Nkoo
0x07CA | LIMITED_USE | RTL, // Nkoo
0x10C00 | EXCLUSION | RTL, // Orkh
0x1036B | EXCLUSION, // Perm
0xA840 | EXCLUSION, // Phag
@ -146,7 +146,7 @@ const int32_t SCRIPT_PROPS[] = {
0x12000 | EXCLUSION, // Xsux
0,
0xFDD0 | UNKNOWN, // Zzzz
0x102B7 | EXCLUSION, // Cari
0x102A0 | EXCLUSION, // Cari
0x304B | RECOMMENDED | LB_LETTERS, // Jpan
0x1A20 | LIMITED_USE | LB_LETTERS, // Lana
0x10280 | EXCLUSION, // Lyci
@ -163,7 +163,7 @@ const int32_t SCRIPT_PROPS[] = {
0x11103 | LIMITED_USE, // Cakm
0xAC00 | RECOMMENDED, // Kore
0x11083 | EXCLUSION, // Kthi
0x10AC1 | EXCLUSION | RTL, // Mani
0x10AD8 | EXCLUSION | RTL, // Mani
0x10B60 | EXCLUSION | RTL, // Phli
0x10B8F | EXCLUSION | RTL, // Phlp
0,
@ -173,7 +173,7 @@ const int32_t SCRIPT_PROPS[] = {
0,
0,
0xA6A0 | LIMITED_USE, // Bamu
0xA4E8 | LIMITED_USE, // Lisu
0xA4D0 | LIMITED_USE, // Lisu
0,
0x10A60 | EXCLUSION | RTL, // Sarb
0x16AE6 | EXCLUSION, // Bass
@ -196,7 +196,7 @@ const int32_t SCRIPT_PROPS[] = {
0x11183 | EXCLUSION, // Shrd
0x110D0 | EXCLUSION, // Sora
0x11680 | EXCLUSION, // Takr
0,
0x18229 | EXCLUSION | LB_LETTERS, // Tang
0,
0x14400 | EXCLUSION, // Hluw
0x11208 | EXCLUSION, // Khoj
@ -209,6 +209,14 @@ const int32_t SCRIPT_PROPS[] = {
0x1128F | EXCLUSION, // Mult
0x11AC0 | EXCLUSION, // Pauc
0x1158E | EXCLUSION, // Sidd
0x1E909 | LIMITED_USE | RTL | CASED, // Adlm
0x11C0E | EXCLUSION, // Bhks
0x11C72 | EXCLUSION, // Marc
0x11412 | LIMITED_USE, // Newa
0x104B5 | LIMITED_USE | CASED, // Osge
0x5B57 | RECOMMENDED | LB_LETTERS, // Hanb
0x1112 | RECOMMENDED, // Jamo
0,
// End copy-paste from parsescriptmetadata.py
};

68
icu4c/source/data/brkitr/rules/char.txt
View file

@ -2,11 +2,11 @@
# Copyright (C) 2002-2016, International Business Machines Corporation and others.
# All Rights Reserved.
#
# file: char.txt
# file: char.txt
#
# ICU Character Break Rules, also known as Grapheme Cluster Boundaries
# See Unicode Standard Annex #29.
# These rules are based on UAX #29 Revision 28 (Draft 3) for Unicode Version 9.0
# These rules are based on UAX #29 Revision 28 (Draft 7) for Unicode Version 9.0
#
#
@ -14,30 +14,29 @@
#
$CR = [\p{Grapheme_Cluster_Break = CR}];
$LF = [\p{Grapheme_Cluster_Break = LF}];
$Control = [[\p{Grapheme_Cluster_Break = Control}]-[:Block=Tags:]];
# TODO: Restore if the Prepend set becomes non-empty again: $Prepend = [\p{Grapheme_Cluster_Break = Prepend}];
$Extend = [[\p{Grapheme_Cluster_Break = Extend}][:Block=Tags:]];
$SpacingMark = [\p{Grapheme_Cluster_Break = SpacingMark}];
$Control = [[\p{Grapheme_Cluster_Break = Control}]];
$Extend = [[\p{Grapheme_Cluster_Break = Extend}]];
$ZWJ = [\p{Grapheme_Cluster_Break = ZWJ}];
$Regional_Indicator = [\p{Grapheme_Cluster_Break = Regional_Indicator}];
$Prepend = [\p{Grapheme_Cluster_Break = Prepend}];
$SpacingMark = [\p{Grapheme_Cluster_Break = SpacingMark}];
#
# Korean Syllable Definitions
#
$L = [\p{Grapheme_Cluster_Break = L}];
$V = [\p{Grapheme_Cluster_Break = V}];
$T = [\p{Grapheme_Cluster_Break = T}];
$L = [\p{Grapheme_Cluster_Break = L}];
$V = [\p{Grapheme_Cluster_Break = V}];
$T = [\p{Grapheme_Cluster_Break = T}];
$LV = [\p{Grapheme_Cluster_Break = LV}];
$LVT = [\p{Grapheme_Cluster_Break = LVT}];
$LV = [\p{Grapheme_Cluster_Break = LV}];
$LVT = [\p{Grapheme_Cluster_Break = LVT}];
# Emoji defintions scraped from http://www.unicode.org/Public/emoji/2.0//emoji-data.txt
# Emoji defintions
$E_Base = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
$E_Modifier = [\U0001F3FB-\U0001F3FF];
$ZWJ = [\u200D];
$GAZ = [\U0001F466-\U0001F469\U0001F48B\U0001F5E8\u2764];
$E_Base = [\p{Grapheme_Cluster_Break = EB}];
$E_Modifier = [\p{Grapheme_Cluster_Break = EM}];
$GAZ = [\p{Grapheme_Cluster_Break = GAZ}];
$E_Base_GAZ = [\p{Grapheme_Cluster_Break = EBG}];
## -------------------------------------------------
!!chain;
@ -53,21 +52,23 @@ $L ($L | $V | $LV | $LVT);
# GB 8. Keep pairs of regional indicators together
# Note that hard break '/' rule triggers only if there are three or more initial RIs,
^$Regional_Indicator $Regional_Indicator / $Regional_Indicator;
^$Regional_Indicator $Regional_Indicator;
^$Prepend* $Regional_Indicator $Regional_Indicator / $Regional_Indicator;
^$Prepend* $Regional_Indicator $Regional_Indicator;
# GB 9
[^$Control $CR $LF] ($Extend | $ZWJ);
# GB 9a (only for extended grapheme clusters)
[^$Control $CR $LF] $SpacingMark;
# GB 9b Restore if the Prepend set becomes non-empty again: $Prepend [^$Control $CR $LF];
# GB9c Emoji proposal
($E_Base | $GAZ) $E_Modifier;
# GB 9b
$Prepend [^$Control $CR $LF];
# GB 9d Don't break between ZWJ and Glue_After_Zwj
$ZWJ $GAZ;
# GB 10 Do not break within emoji modifier sequences or emoji zwj sequences.
($E_Base | $E_Base_GAZ) $E_Modifier;
# GB 11
$ZWJ ($GAZ | $E_Base_GAZ);
## -------------------------------------------------
@ -79,20 +80,25 @@ $T ($LVT | $T);
# GB 8. Going backwards, we must scan through any number of regional indicators as pairs.
#
$Regional_Indicator $Regional_Indicator / ($Regional_Indicator $Regional_Indicator)* [{eof}[^$Regional_Indicator]];
[{bof} $Extend $ZWJ $SpacingMark] $Regional_Indicator $Regional_Indicator / ($Regional_Indicator $Regional_Indicator)+ [{eof}[^$Regional_Indicator]];
[{bof} $Extend $ZWJ $SpacingMark] $Regional_Indicator / ($Regional_Indicator $Regional_Indicator)+ [{eof}[^$Regional_Indicator]];
$Regional_Indicator $Regional_Indicator;
$Regional_Indicator $Prepend;
# GB 9
($Extend | $ZWJ) [^$Control $CR $LF]; #note that this will chain into Regional_Indicator when needed.
# GB 9a
$SpacingMark [^$Control $CR $LF];
# GB 9b Restore if the Prepend set becomes non-empty again: [^$Control $CR $LF] $Prepend;
# GB 9c
$E_Modifier ($E_Base | $GAZ);
# GB 9b
[^$Control $CR $LF] $Prepend;
# GB 9d Don't break between ZWJ and Glue_After_Zwj
$GAZ $ZWJ;
# GB 10
$E_Modifier ($E_Base | $E_Base_GAZ);
# GB 11 Don't break between ZWJ and Glue_After_ZWJ
($GAZ | $E_Base_GAZ) $ZWJ;
## -------------------------------------------------

37
icu4c/source/data/brkitr/rules/line.txt
View file

@ -24,14 +24,8 @@
!!chain;
# Temporary definitions of Emoji Base and Emoji Modifiers, until properties are available.
$EB = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
$EM = [\U0001F3FB-\U0001F3FF];
$AI = [:LineBreak = Ambiguous:];
$AL = [[:LineBreak = Alphabetic:] - [$EM\u2764]];
$AL = [:LineBreak = Alphabetic:];
$BA = [:LineBreak = Break_After:];
$BB = [:LineBreak = Break_Before:];
$BK = [:LineBreak = Mandatory_Break:];
@ -39,16 +33,18 @@ $B2 = [:LineBreak = Break_Both:];
$CB = [:LineBreak = Contingent_Break:];
$CJ = [:LineBreak = Conditional_Japanese_Starter:];
$CL = [:LineBreak = Close_Punctuation:];
$CM = [[:LineBreak = Combining_Mark:] \u200d];
# $CM = [:LineBreak = Combining_Mark:];
$CP = [:LineBreak = Close_Parenthesis:];
$CR = [:LineBreak = Carriage_Return:];
$EB = [:LineBreak = EB:];
$EM = [:LineBreak = EM:];
$EX = [:LineBreak = Exclamation:];
$GL = [:LineBreak = Glue:];
$HL = [:LineBreak = Hebrew_Letter:];
$HY = [:LineBreak = Hyphen:];
$H2 = [:LineBreak = H2:];
$H3 = [:LineBreak = H3:];
$ID = [[:LineBreak = Ideographic:][\u2764] - $EB];
$ID = [:LineBreak = Ideographic:];
$IN = [:LineBreak = Inseperable:];
$IS = [:LineBreak = Infix_Numeric:];
$JL = [:LineBreak = JL:];
@ -56,6 +52,7 @@ $JV = [:LineBreak = JV:];
$JT = [:LineBreak = JT:];
$LF = [:LineBreak = Line_Feed:];
$NL = [:LineBreak = Next_Line:];
# NS includes CJ for CSS strict line breaking.
$NS = [[:LineBreak = Nonstarter:] $CJ];
$NU = [:LineBreak = Numeric:];
$OP = [:LineBreak = Open_Punctuation:];
@ -70,23 +67,27 @@ $SY = [:LineBreak = Break_Symbols:];
$WJ = [:LineBreak = Word_Joiner:];
$XX = [:LineBreak = Unknown:];
$ZW = [:LineBreak = ZWSpace:];
$ZWJ = [\u200d];
$ZWJ = [:LineBreak = ZWJ:];
# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
# list it in the numerous rules that use CM.
# By LB1, SA characters with general categor of Mn or Mc also resolve to CM.
$CM = [[:LineBreak = Combining_Mark:] $ZWJ [$SA & [[:Mn:][:Mc:]]]];
# Dictionary character set, for triggering language-based break engines. Currently
# limited to LineBreak=Complex_Context. Note that this set only works in Unicode
# 5.0 or later as the definition of Complex_Context was corrected to include all
# characters requiring dictionary break.
# limited to LineBreak=Complex_Context (SA).
$dictionary = [:LineBreak = Complex_Context:];
$dictionary = [$SA];
#
# Rule LB1. By default, treat AI (characters with ambiguous east Asian width),
# SA (South East Asian: Thai, Lao, Khmer)
# SA (Dictionary chars, excluding Mn and Mc)
# SG (Unpaired Surrogates)
# XX (Unknown, unassigned)
# as $AL (Alphabetic)
#
$ALPlus = [$AL $AI $SA $SG $XX];
$ALPlus = [$AL $AI $SG $XX [$SA-[[:Mn:][:Mc:]]]];
## -------------------------------------------------
@ -140,7 +141,7 @@ $CAN_CM $CM* [$SP $ZW];
$LB8Breaks = [$LB4Breaks $ZW];
$LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
# LB 8a ZWJ x ID Emoji proposal.
# LB 8a ZWJ x (ID | EB | EM) Emoji ZWJ sequences.
#
$ZWJ ($ID | $EB | $EM);
@ -287,7 +288,7 @@ $PR $CM* ($ID | $EB | $EM);
#
# LB 25 Numbers.
#
(($PR | $PO) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
(($PR | $PO) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
($CM* ($CL | $CP))? ($CM* ($PR | $PO))?;
# LB 26 Do not break a Korean syllable

37
icu4c/source/data/brkitr/rules/line_fi.txt
View file

@ -29,14 +29,8 @@
!!chain;
# Temporary definitions of Emoji Base and Emoji Modifiers, until properties are available.
$EB = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
$EM = [\U0001F3FB-\U0001F3FF];
$AI = [:LineBreak = Ambiguous:];
$AL = [[:LineBreak = Alphabetic:] - [$EM\u2764]];
$AL = [:LineBreak = Alphabetic:];
$BA = [:LineBreak = Break_After:];
$HH = [\u2010]; # \u2010 is HYPHEN, default line break is BA.
$BB = [:LineBreak = Break_Before:];
@ -45,16 +39,18 @@ $B2 = [:LineBreak = Break_Both:];
$CB = [:LineBreak = Contingent_Break:];
$CJ = [:LineBreak = Conditional_Japanese_Starter:];
$CL = [:LineBreak = Close_Punctuation:];
$CM = [[:LineBreak = Combining_Mark:] \u200d];
# $CM = [:LineBreak = Combining_Mark:];
$CP = [:LineBreak = Close_Parenthesis:];
$CR = [:LineBreak = Carriage_Return:];
$EB = [:LineBreak = EB:];
$EM = [:LineBreak = EM:];
$EX = [:LineBreak = Exclamation:];
$GL = [:LineBreak = Glue:];
$HL = [:LineBreak = Hebrew_Letter:];
$HY = [:LineBreak = Hyphen:];
$H2 = [:LineBreak = H2:];
$H3 = [:LineBreak = H3:];
$ID = [[:LineBreak = Ideographic:][\u2764] - $EB];
$ID = [:LineBreak = Ideographic:];
$IN = [:LineBreak = Inseperable:];
$IS = [:LineBreak = Infix_Numeric:];
$JL = [:LineBreak = JL:];
@ -62,6 +58,7 @@ $JV = [:LineBreak = JV:];
$JT = [:LineBreak = JT:];
$LF = [:LineBreak = Line_Feed:];
$NL = [:LineBreak = Next_Line:];
# NS includes CJ for CSS strict line breaking.
$NS = [[:LineBreak = Nonstarter:] $CJ];
$NU = [:LineBreak = Numeric:];
$OP = [:LineBreak = Open_Punctuation:];
@ -76,23 +73,27 @@ $SY = [:LineBreak = Break_Symbols:];
$WJ = [:LineBreak = Word_Joiner:];
$XX = [:LineBreak = Unknown:];
$ZW = [:LineBreak = ZWSpace:];
$ZWJ = [\u200d];
$ZWJ = [:LineBreak = ZWJ:];
# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
# list it in the numerous rules that use CM.
# By LB1, SA characters with general categor of Mn or Mc also resolve to CM.
$CM = [[:LineBreak = Combining_Mark:] $ZWJ [$SA & [[:Mn:][:Mc:]]]];
# Dictionary character set, for triggering language-based break engines. Currently
# limited to LineBreak=Complex_Context. Note that this set only works in Unicode
# 5.0 or later as the definition of Complex_Context was corrected to include all
# characters requiring dictionary break.
# limited to LineBreak=Complex_Context (SA).
$dictionary = [:LineBreak = Complex_Context:];
$dictionary = [$SA];
#
# Rule LB1. By default, treat AI (characters with ambiguous east Asian width),
# SA (South East Asian: Thai, Lao, Khmer)
# SA (Dictionary chars, excluding Mn and Mc)
# SG (Unpaired Surrogates)
# XX (Unknown, unassigned)
# as $AL (Alphabetic)
#
$ALPlus = [$AL $AI $SA $SG $XX];
$ALPlus = [$AL $AI $SG $XX [$SA-[[:Mn:][:Mc:]]]];
## -------------------------------------------------
@ -146,7 +147,7 @@ $CAN_CM $CM* [$SP $ZW];
$LB8Breaks = [$LB4Breaks $ZW];
$LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
# LB 8a ZWJ x ID Emoji proposal.
# LB 8a ZWJ x (ID | EB | EM) Emoji ZWJ sequences.
#
$ZWJ ($ID | $EB | $EM);
@ -296,7 +297,7 @@ $PR $CM* ($ID | $EB | $EM);
#
# LB 25 Numbers.
#
(($PR | $PO) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
(($PR | $PO) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
($CM* ($CL | $CP))? ($CM* ($PR | $PO))?;
# LB 26 Do not break a Korean syllable

39
icu4c/source/data/brkitr/rules/line_loose.txt
View file

@ -18,7 +18,7 @@
# not because the older behavior is desirable.
#
# This tailors the line break behavior to correspond to CSS
# line-break=loose (BCP47 -u-lb-loose) as defined for languages other than
# line-break=loose (BCP47 -u-lb-loose) as defined for languages other than
# Chinese & Japanese.
# It sets characters of class CJ to behave like ID.
# In addition, it allows breaks:
@ -31,14 +31,8 @@
!!chain;
# Temporary definitions of Emoji Base and Emoji Modifiers, until properties are available.
$EB = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
$EM = [\U0001F3FB-\U0001F3FF];
$AI = [:LineBreak = Ambiguous:];
$AL = [[:LineBreak = Alphabetic:] - [$EM\u2764]];
$AL = [:LineBreak = Alphabetic:];
$BA = [:LineBreak = Break_After:];
$BB = [:LineBreak = Break_Before:];
$BK = [:LineBreak = Mandatory_Break:];
@ -46,16 +40,19 @@ $B2 = [:LineBreak = Break_Both:];
$CB = [:LineBreak = Contingent_Break:];
$CJ = [:LineBreak = Conditional_Japanese_Starter:];
$CL = [:LineBreak = Close_Punctuation:];
$CM = [[:LineBreak = Combining_Mark:] \u200d];
# $CM = [:LineBreak = Combining_Mark:];
$CP = [:LineBreak = Close_Parenthesis:];
$CR = [:LineBreak = Carriage_Return:];
$EB = [:LineBreak = EB:];
$EM = [:LineBreak = EM:];
$EX = [:LineBreak = Exclamation:];
$GL = [:LineBreak = Glue:];
$HL = [:LineBreak = Hebrew_Letter:];
$HY = [:LineBreak = Hyphen:];
$H2 = [:LineBreak = H2:];
$H3 = [:LineBreak = H3:];
$ID = [[:LineBreak = Ideographic:]$CJ[\u2764] - $EB];
# CSS Loose tailoring: CJ resolves to ID
$ID = [[:LineBreak = Ideographic:] $CJ];
$IN = [:LineBreak = Inseperable:];
$IS = [:LineBreak = Infix_Numeric:];
$JL = [:LineBreak = JL:];
@ -78,23 +75,27 @@ $SY = [:LineBreak = Break_Symbols:];
$WJ = [:LineBreak = Word_Joiner:];
$XX = [:LineBreak = Unknown:];
$ZW = [:LineBreak = ZWSpace:];
$ZWJ = [\u200d];
$ZWJ = [:LineBreak = ZWJ:];
# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
# list it in the numerous rules that use CM.
# By LB1, SA characters with general categor of Mn or Mc also resolve to CM.
$CM = [[:LineBreak = Combining_Mark:] $ZWJ [$SA & [[:Mn:][:Mc:]]]];
# Dictionary character set, for triggering language-based break engines. Currently
# limited to LineBreak=Complex_Context. Note that this set only works in Unicode
# 5.0 or later as the definition of Complex_Context was corrected to include all
# characters requiring dictionary break.
# limited to LineBreak=Complex_Context (SA).
$dictionary = [:LineBreak = Complex_Context:];
$dictionary = [$SA];
#
# Rule LB1. By default, treat AI (characters with ambiguous east Asian width),
# SA (South East Asian: Thai, Lao, Khmer)
# SA (Dictionary chars, excluding Mn and Mc)
# SG (Unpaired Surrogates)
# XX (Unknown, unassigned)
# as $AL (Alphabetic)
#
$ALPlus = [$AL $AI $SA $SG $XX];
$ALPlus = [$AL $AI $SG $XX [$SA-[[:Mn:][:Mc:]]]];
## -------------------------------------------------
@ -148,7 +149,7 @@ $CAN_CM $CM* [$SP $ZW];
$LB8Breaks = [$LB4Breaks $ZW];
$LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
# LB 8a ZWJ x ID Emoji proposal.
# LB 8a ZWJ x (ID | EB | EM) Emoji ZWJ sequences.
#
$ZWJ ($ID | $EB | $EM);
@ -298,7 +299,7 @@ $PR $CM* ($ID | $EB | $EM);
#
# LB 25 Numbers.
#
(($PR | $PO) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
(($PR | $PO) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
($CM* ($CL | $CP))? ($CM* ($PR | $PO))?;
# LB 26 Do not break a Korean syllable

37
icu4c/source/data/brkitr/rules/line_loose_cj.txt
View file

@ -38,14 +38,8 @@
!!chain;
# Temporary definitions of Emoji Base and Emoji Modifiers, until properties are available.
$EB = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
$EM = [\U0001F3FB-\U0001F3FF];
$AI = [:LineBreak = Ambiguous:];
$AL = [[:LineBreak = Alphabetic:] - [$EM\u2764]];
$AL = [:LineBreak = Alphabetic:];
$BAX = [\u2010 \u2013];
$BA = [[:LineBreak = Break_After:] - $BAX];
$BB = [:LineBreak = Break_Before:];
@ -54,9 +48,11 @@ $B2 = [:LineBreak = Break_Both:];
$CB = [:LineBreak = Contingent_Break:];
$CJ = [:LineBreak = Conditional_Japanese_Starter:];
$CL = [:LineBreak = Close_Punctuation:];
$CM = [[:LineBreak = Combining_Mark:] \u200d];
# $CM = [:LineBreak = Combining_Mark:];
$CP = [:LineBreak = Close_Parenthesis:];
$CR = [:LineBreak = Carriage_Return:];
$EB = [:LineBreak = EB:];
$EM = [:LineBreak = EM:];
$EXX = [\uFF01 \uFF1F];
$EX = [[:LineBreak = Exclamation:] - $EXX];
$GL = [:LineBreak = Glue:];
@ -64,7 +60,8 @@ $HL = [:LineBreak = Hebrew_Letter:];
$HY = [:LineBreak = Hyphen:];
$H2 = [:LineBreak = H2:];
$H3 = [:LineBreak = H3:];
$ID = [[:LineBreak = Ideographic:] $CJ [\u2764] - $EB];
# CSS Loose tailoring: CJ resolves to ID
$ID = [[:LineBreak = Ideographic:] $CJ];
$IN = [:LineBreak = Inseperable:];
$IS = [:LineBreak = Infix_Numeric:];
$JL = [:LineBreak = JL:];
@ -89,23 +86,27 @@ $SY = [:LineBreak = Break_Symbols:];
$WJ = [:LineBreak = Word_Joiner:];
$XX = [:LineBreak = Unknown:];
$ZW = [:LineBreak = ZWSpace:];
$ZWJ = [\u200d];
$ZWJ = [:LineBreak = ZWJ:];
# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
# list it in the numerous rules that use CM.
# By LB1, SA characters with general categor of Mn or Mc also resolve to CM.
$CM = [[:LineBreak = Combining_Mark:] $ZWJ [$SA & [[:Mn:][:Mc:]]]];
# Dictionary character set, for triggering language-based break engines. Currently
# limited to LineBreak=Complex_Context. Note that this set only works in Unicode
# 5.0 or later as the definition of Complex_Context was corrected to include all
# characters requiring dictionary break.
# limited to LineBreak=Complex_Context (SA).
$dictionary = [:LineBreak = Complex_Context:];
$dictionary = [$SA];
#
# Rule LB1. By default, treat AI (characters with ambiguous east Asian width),
# SA (South East Asian: Thai, Lao, Khmer)
# SA (Dictionary chars, excluding Mn and Mc)
# SG (Unpaired Surrogates)
# XX (Unknown, unassigned)
# as $AL (Alphabetic)
#
$ALPlus = [$AL $AI $SA $SG $XX];
$ALPlus = [$AL $AI $SG $XX [$SA-[[:Mn:][:Mc:]]]];
## -------------------------------------------------
@ -159,7 +160,7 @@ $CAN_CM $CM* [$SP $ZW];
$LB8Breaks = [$LB4Breaks $ZW];
$LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
# LB 8a ZWJ x ID Emoji proposal.
# LB 8a ZWJ x (ID | EB | EM) Emoji ZWJ sequences.
#
$ZWJ ($ID | $EB | $EM);
@ -312,7 +313,7 @@ $PR $CM* ($ID | $EB | $EM);
# LB 25 Numbers.
#
# Here do not include $PRX at the beginning or $POX at the end
(($PR | $PO | $POX) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
(($PR | $PO | $POX) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
($CM* ($CL | $CP))? ($CM* ($PR | $PRX | $PO))?;
# LB 26 Do not break a Korean syllable

35
icu4c/source/data/brkitr/rules/line_loose_fi.txt
View file

@ -29,14 +29,8 @@
!!chain;
# Temporary definitions of Emoji Base and Emoji Modifiers, until properties are available.
$EB = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
$EM = [\U0001F3FB-\U0001F3FF];
$AI = [:LineBreak = Ambiguous:];
$AL = [[:LineBreak = Alphabetic:] - [$EM\u2764]];
$AL = [:LineBreak = Alphabetic:];
$BA = [:LineBreak = Break_After:];
$HH = [\u2010]; # \u2010 is HYPHEN, default line break is BA.
$BB = [:LineBreak = Break_Before:];
@ -45,16 +39,19 @@ $B2 = [:LineBreak = Break_Both:];
$CB = [:LineBreak = Contingent_Break:];
$CJ = [:LineBreak = Conditional_Japanese_Starter:];
$CL = [:LineBreak = Close_Punctuation:];
$CM = [[:LineBreak = Combining_Mark:] \u200d];
# $CM = [:LineBreak = Combining_Mark:];
$CP = [:LineBreak = Close_Parenthesis:];
$CR = [:LineBreak = Carriage_Return:];
$EB = [:LineBreak = EB:];
$EM = [:LineBreak = EM:];
$EX = [:LineBreak = Exclamation:];
$GL = [:LineBreak = Glue:];
$HL = [:LineBreak = Hebrew_Letter:];
$HY = [:LineBreak = Hyphen:];
$H2 = [:LineBreak = H2:];
$H3 = [:LineBreak = H3:];
$ID = [[:LineBreak = Ideographic:]$CJ[\u2764] - $EB];
# CSS Loose tailoring: CJ resolves to ID
$ID = [[:LineBreak = Ideographic:] $CJ];
$IN = [:LineBreak = Inseperable:];
$IS = [:LineBreak = Infix_Numeric:];
$JL = [:LineBreak = JL:];
@ -77,23 +74,27 @@ $SY = [:LineBreak = Break_Symbols:];
$WJ = [:LineBreak = Word_Joiner:];
$XX = [:LineBreak = Unknown:];
$ZW = [:LineBreak = ZWSpace:];
$ZWJ = [\u200d];
$ZWJ = [:LineBreak = ZWJ:];
# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
# list it in the numerous rules that use CM.
# By LB1, SA characters with general categor of Mn or Mc also resolve to CM.
$CM = [[:LineBreak = Combining_Mark:] $ZWJ [$SA & [[:Mn:][:Mc:]]]];
# Dictionary character set, for triggering language-based break engines. Currently
# limited to LineBreak=Complex_Context. Note that this set only works in Unicode
# 5.0 or later as the definition of Complex_Context was corrected to include all
# characters requiring dictionary break.
# limited to LineBreak=Complex_Context (SA).
$dictionary = [:LineBreak = Complex_Context:];
$dictionary = [$SA];
#
# Rule LB1. By default, treat AI (characters with ambiguous east Asian width),
# SA (South East Asian: Thai, Lao, Khmer)
# SA (Dictionary chars, excluding Mn and Mc)
# SG (Unpaired Surrogates)
# XX (Unknown, unassigned)
# as $AL (Alphabetic)
#
$ALPlus = [$AL $AI $SA $SG $XX];
$ALPlus = [$AL $AI $SG $XX [$SA-[[:Mn:][:Mc:]]]];
## -------------------------------------------------
@ -147,7 +148,7 @@ $CAN_CM $CM* [$SP $ZW];
$LB8Breaks = [$LB4Breaks $ZW];
$LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
# LB 8a ZWJ x ID Emoji proposal.
# LB 8a ZWJ x (ID | EB | EM) Emoji ZWJ sequences.
#
$ZWJ ($ID | $EB | $EM);

39
icu4c/source/data/brkitr/rules/line_normal.txt
View file

@ -18,7 +18,7 @@
# not because the older behavior is desirable.
#
# This tailors the line break behavior to correspond to CSS
# line-break=normal (BCP47 -u-lb-normal) as defined for languages other than
# line-break=normal (BCP47 -u-lb-normal) as defined for languages other than
# Chinese & Japanese.
# It sets characters of class CJ to behave like ID.
@ -28,14 +28,8 @@
!!chain;
# Temporary definitions of Emoji Base and Emoji Modifiers, until properties are available.
$EB = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
$EM = [\U0001F3FB-\U0001F3FF];
$AI = [:LineBreak = Ambiguous:];
$AL = [[:LineBreak = Alphabetic:] - [$EM\u2764]];
$AL = [:LineBreak = Alphabetic:];
$BA = [:LineBreak = Break_After:];
$BB = [:LineBreak = Break_Before:];
$BK = [:LineBreak = Mandatory_Break:];
@ -43,16 +37,19 @@ $B2 = [:LineBreak = Break_Both:];
$CB = [:LineBreak = Contingent_Break:];
$CJ = [:LineBreak = Conditional_Japanese_Starter:];
$CL = [:LineBreak = Close_Punctuation:];
$CM = [[:LineBreak = Combining_Mark:] \u200d];
# $CM = [:LineBreak = Combining_Mark:];
$CP = [:LineBreak = Close_Parenthesis:];
$CR = [:LineBreak = Carriage_Return:];
$EB = [:LineBreak = EB:];
$EM = [:LineBreak = EM:];
$EX = [:LineBreak = Exclamation:];
$GL = [:LineBreak = Glue:];
$HL = [:LineBreak = Hebrew_Letter:];
$HY = [:LineBreak = Hyphen:];
$H2 = [:LineBreak = H2:];
$H3 = [:LineBreak = H3:];
$ID = [[:LineBreak = Ideographic:] $CJ [\u2764] - $EB];
# CSS Normal tailoring: CJ resolves to ID
$ID = [[:LineBreak = Ideographic:] $CJ];
$IN = [:LineBreak = Inseperable:];
$IS = [:LineBreak = Infix_Numeric:];
$JL = [:LineBreak = JL:];
@ -74,23 +71,27 @@ $SY = [:LineBreak = Break_Symbols:];
$WJ = [:LineBreak = Word_Joiner:];
$XX = [:LineBreak = Unknown:];
$ZW = [:LineBreak = ZWSpace:];
$ZWJ = [\u200d];
$ZWJ = [:LineBreak = ZWJ:];
# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
# list it in the numerous rules that use CM.
# By LB1, SA characters with general categor of Mn or Mc also resolve to CM.
$CM = [[:LineBreak = Combining_Mark:] $ZWJ [$SA & [[:Mn:][:Mc:]]]];
# Dictionary character set, for triggering language-based break engines. Currently
# limited to LineBreak=Complex_Context. Note that this set only works in Unicode
# 5.0 or later as the definition of Complex_Context was corrected to include all
# characters requiring dictionary break.
# limited to LineBreak=Complex_Context (SA).
$dictionary = [:LineBreak = Complex_Context:];
$dictionary = [$SA];
#
# Rule LB1. By default, treat AI (characters with ambiguous east Asian width),
# SA (South East Asian: Thai, Lao, Khmer)
# SA (Dictionary chars, excluding Mn and Mc)
# SG (Unpaired Surrogates)
# XX (Unknown, unassigned)
# as $AL (Alphabetic)
#
$ALPlus = [$AL $AI $SA $SG $XX];
$ALPlus = [$AL $AI $SG $XX [$SA-[[:Mn:][:Mc:]]]];
## -------------------------------------------------
@ -144,7 +145,7 @@ $CAN_CM $CM* [$SP $ZW];
$LB8Breaks = [$LB4Breaks $ZW];
$LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
# LB 8a ZWJ x ID Emoji proposal.
# LB 8a ZWJ x (ID | EB | EM) Emoji ZWJ sequences.
#
$ZWJ ($ID | $EB | $EM);
@ -291,7 +292,7 @@ $PR $CM* ($ID | $EB | $EM);
#
# LB 25 Numbers.
#
(($PR | $PO) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
(($PR | $PO) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
($CM* ($CL | $CP))? ($CM* ($PR | $PO))?;
# LB 26 Do not break a Korean syllable

37
icu4c/source/data/brkitr/rules/line_normal_cj.txt
View file

@ -29,14 +29,8 @@
!!chain;
# Temporary definitions of Emoji Base and Emoji Modifiers, until properties are available.
$EB = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
$EM = [\U0001F3FB-\U0001F3FF];
$AI = [:LineBreak = Ambiguous:];
$AL = [[:LineBreak = Alphabetic:] - [$EM\u2764]];
$AL = [:LineBreak = Alphabetic:];
$BAX = [\u2010 \u2013];
$BA = [[:LineBreak = Break_After:] - $BAX];
$BB = [:LineBreak = Break_Before:];
@ -45,16 +39,19 @@ $B2 = [:LineBreak = Break_Both:];
$CB = [:LineBreak = Contingent_Break:];
$CJ = [:LineBreak = Conditional_Japanese_Starter:];
$CL = [:LineBreak = Close_Punctuation:];
$CM = [[:LineBreak = Combining_Mark:] \u200d];
# $CM = [:LineBreak = Combining_Mark:];
$CP = [:LineBreak = Close_Parenthesis:];
$CR = [:LineBreak = Carriage_Return:];
$EB = [:LineBreak = EB:];
$EM = [:LineBreak = EM:];
$EX = [:LineBreak = Exclamation:];
$GL = [:LineBreak = Glue:];
$HL = [:LineBreak = Hebrew_Letter:];
$HY = [:LineBreak = Hyphen:];
$H2 = [:LineBreak = H2:];
$H3 = [:LineBreak = H3:];
$ID = [[:LineBreak = Ideographic:] $CJ [\u2764] - $EB];
# CSS Normal tailoring: CJ resolves to ID
$ID = [[:LineBreak = Ideographic:] $CJ];
$IN = [:LineBreak = Inseperable:];
$IS = [:LineBreak = Infix_Numeric:];
$JL = [:LineBreak = JL:];
@ -77,23 +74,27 @@ $SY = [:LineBreak = Break_Symbols:];
$WJ = [:LineBreak = Word_Joiner:];
$XX = [:LineBreak = Unknown:];
$ZW = [:LineBreak = ZWSpace:];
$ZWJ = [\u200d];
$ZWJ = [:LineBreak = ZWJ:];
# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
# list it in the numerous rules that use CM.
# By LB1, SA characters with general categor of Mn or Mc also resolve to CM.
$CM = [[:LineBreak = Combining_Mark:] $ZWJ [$SA & [[:Mn:][:Mc:]]]];
# Dictionary character set, for triggering language-based break engines. Currently
# limited to LineBreak=Complex_Context. Note that this set only works in Unicode
# 5.0 or later as the definition of Complex_Context was corrected to include all
# characters requiring dictionary break.
# limited to LineBreak=Complex_Context (SA).
$dictionary = [:LineBreak = Complex_Context:];
$dictionary = [$SA];
#
# Rule LB1. By default, treat AI (characters with ambiguous east Asian width),
# SA (South East Asian: Thai, Lao, Khmer)
# SA (Dictionary chars, excluding Mn and Mc)
# SG (Unpaired Surrogates)
# XX (Unknown, unassigned)
# as $AL (Alphabetic)
#
$ALPlus = [$AL $AI $SA $SG $XX];
$ALPlus = [$AL $AI $SG $XX [$SA-[[:Mn:][:Mc:]]]];
## -------------------------------------------------
@ -147,7 +148,7 @@ $CAN_CM $CM* [$SP $ZW];
$LB8Breaks = [$LB4Breaks $ZW];
$LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
# LB 8a ZWJ x ID Emoji proposal.
# LB 8a ZWJ x (ID | EB | EM) Emoji ZWJ sequences.
#
$ZWJ ($ID | $EB | $EM);
@ -297,7 +298,7 @@ $PR $CM* ($ID | $EB | $EM);
#
# LB 25 Numbers.
#
(($PR | $PO) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
(($PR | $PO) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
($CM* ($CL | $CP))? ($CM* ($PR | $PO))?;
# LB 26 Do not break a Korean syllable

39
icu4c/source/data/brkitr/rules/line_normal_fi.txt
View file

@ -19,7 +19,7 @@
# not because the older behavior is desirable.
#
# This tailors the line break behavior for Finnish, and to correspond to CSS
# line-break=normal (BCP47 -u-lb-normal) as defined for languages other than
# line-break=normal (BCP47 -u-lb-normal) as defined for languages other than
# Chinese & Japanese.
# It sets characters of class CJ to behave like ID.
@ -29,14 +29,8 @@
!!chain;
# Temporary definitions of Emoji Base and Emoji Modifiers, until properties are available.
$EB = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
$EM = [\U0001F3FB-\U0001F3FF];
$AI = [:LineBreak = Ambiguous:];
$AL = [[:LineBreak = Alphabetic:] - [$EM\u2764]];
$AL = [:LineBreak = Alphabetic:];
$BA = [:LineBreak = Break_After:];
$HH = [\u2010]; # \u2010 is HYPHEN, default line break is BA.
$BB = [:LineBreak = Break_Before:];
@ -45,16 +39,19 @@ $B2 = [:LineBreak = Break_Both:];
$CB = [:LineBreak = Contingent_Break:];
$CJ = [:LineBreak = Conditional_Japanese_Starter:];
$CL = [:LineBreak = Close_Punctuation:];
$CM = [[:LineBreak = Combining_Mark:] \u200d];
# $CM = [:LineBreak = Combining_Mark:];
$CP = [:LineBreak = Close_Parenthesis:];
$CR = [:LineBreak = Carriage_Return:];
$EB = [:LineBreak = EB:];
$EM = [:LineBreak = EM:];
$EX = [:LineBreak = Exclamation:];
$GL = [:LineBreak = Glue:];
$HL = [:LineBreak = Hebrew_Letter:];
$HY = [:LineBreak = Hyphen:];
$H2 = [:LineBreak = H2:];
$H3 = [:LineBreak = H3:];
$ID = [[:LineBreak = Ideographic:] $CJ [\u2764] - $EB];
# CSS Normal tailoring: CJ resolves to ID
$ID = [[:LineBreak = Ideographic:] $CJ];
$IN = [:LineBreak = Inseperable:];
$IS = [:LineBreak = Infix_Numeric:];
$JL = [:LineBreak = JL:];
@ -76,23 +73,27 @@ $SY = [:LineBreak = Break_Symbols:];
$WJ = [:LineBreak = Word_Joiner:];
$XX = [:LineBreak = Unknown:];
$ZW = [:LineBreak = ZWSpace:];
$ZWJ = [\u200d];
$ZWJ = [:LineBreak = ZWJ:];
# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
# list it in the numerous rules that use CM.
# By LB1, SA characters with general categor of Mn or Mc also resolve to CM.
$CM = [[:LineBreak = Combining_Mark:] $ZWJ [$SA & [[:Mn:][:Mc:]]]];
# Dictionary character set, for triggering language-based break engines. Currently
# limited to LineBreak=Complex_Context. Note that this set only works in Unicode
# 5.0 or later as the definition of Complex_Context was corrected to include all
# characters requiring dictionary break.
# limited to LineBreak=Complex_Context (SA).
$dictionary = [:LineBreak = Complex_Context:];
$dictionary = [$SA];
#
# Rule LB1. By default, treat AI (characters with ambiguous east Asian width),
# SA (South East Asian: Thai, Lao, Khmer)
# SA (Dictionary chars, excluding Mn and Mc)
# SG (Unpaired Surrogates)
# XX (Unknown, unassigned)
# as $AL (Alphabetic)
#
$ALPlus = [$AL $AI $SA $SG $XX];
$ALPlus = [$AL $AI $SG $XX [$SA-[[:Mn:][:Mc:]]]];
## -------------------------------------------------
@ -146,7 +147,7 @@ $CAN_CM $CM* [$SP $ZW];
$LB8Breaks = [$LB4Breaks $ZW];
$LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
# LB 8a ZWJ x ID Emoji proposal.
# LB 8a ZWJ x (ID | EB | EM) Emoji ZWJ sequences.
#
$ZWJ ($ID | $EB | $EM);
@ -296,7 +297,7 @@ $PR $CM* ($ID | $EB | $EM);
#
# LB 25 Numbers.
#
(($PR | $PO) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
(($PR | $PO) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
($CM* ($CL | $CP))? ($CM* ($PR | $PO))?;
# LB 26 Do not break a Korean syllable

56
icu4c/source/data/brkitr/rules/word.txt
View file

@ -6,8 +6,7 @@
#
# ICU Word Break Rules
# See Unicode Standard Annex #29.
# These rules are based on UAX #29 Revision 27 for Unicode Version 8.0
# with additions from L2/16-011R3 for Emoji sequences.
# These rules are based on UAX #29 Revision 28 (draft 7) for Unicode Version 9.0
#
# Note: Updates to word.txt will usually need to be merged into
# word_POSIX.txt also.
@ -25,17 +24,13 @@
# Character Class Definitions.
#
$E_Base = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
$E_Modifier = [\U0001F3FB-\U0001F3FF];
$ZWJ = [\u200D];
$GAZ = [\U0001F466-\U0001F469\U0001F48B\U0001F5E8\u2764];
$CR = [\p{Word_Break = CR}];
$LF = [\p{Word_Break = LF}];
$Newline = [\p{Word_Break = Newline} ];
$Extend = [[\p{Word_Break = Extend}][:Block=Tags:]];
$Extend = [\p{Word_Break = Extend}];
$ZWJ = [\p{Word_Break = ZWJ}];
$Regional_Indicator = [\p{Word_Break = Regional_Indicator}];
$Format = [[\p{Word_Break = Format}] - [:Block=Tags:]];
$Format = [\p{Word_Break = Format}];
$Katakana = [\p{Word_Break = Katakana}];
$Hebrew_Letter = [\p{Word_Break = Hebrew_Letter}];
$ALetter = [\p{Word_Break = ALetter}];
@ -46,6 +41,10 @@ $MidLetter = [\p{Word_Break = MidLetter}];
$MidNum = [\p{Word_Break = MidNum}];
$Numeric = [\p{Word_Break = Numeric}];
$ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
$E_Base = [\p{Word_Break = EB}];
$E_Modifier = [\p{Word_Break = EM}];
$GAZ = [\p{Word_Break = GAZ}];
$EBG = [\p{Word_Break = EBG}];
$Han = [:Han:];
$Hiragana = [:Hiragana:];
@ -99,7 +98,7 @@ $CR $LF;
# Rule 3c ZWJ x GAZ. Preceeds WB4, so no intervening Extend chars allowed.
#
$ZWJ $GAZ;
$ZWJ ($GAZ | $EBG);
# Rule 4 - ignore Format and Extend characters, except when they appear at the beginning
@ -171,7 +170,12 @@ $ExtendNumLetEx $Hebrew_Letter {200}; # (13b)
$ExtendNumLetEx $NumericEx {100}; # (13b)
$ExtendNumLetEx $KatakanaEx {400}; # (13b)
# rule 13c
# rule 14
# Do not break within emoji modifier sequences
($E_Base | $EBG) ($Format | $Extend | $ZWJ)* $E_Modifier;
# rules 15 - 17
# Pairs of Regional Indicators stay together.
# With rule chaining disabled by ^, this rule will match exactly two of them.
# No other rule begins with a Regional_Indicator, so chaining cannot extend the match.
@ -182,11 +186,6 @@ $ExtendNumLetEx $KatakanaEx {400}; # (13b)
$HangulSyllable $HangulSyllable {200};
$KanaKanji $KanaKanji {400}; # different rule status if both kana and kanji found
# rule 13d
# E_Base x E_Modifier
#
($E_Base | $GAZ) ($Format | $Extend | $ZWJ)* $E_Modifier;
## -------------------------------------------------
@ -210,7 +209,7 @@ $LF $CR;
# Rule 3c ZWJ x GAZ. Preceeds WB4, so no intervening Extend chars allowed.
#
$GAZ $ZWJ;
($GAZ | $EBG) $ZWJ;
# rule 4
($Format | $Extend | $ZWJ)* [^$CR $LF $Newline]?;
@ -254,26 +253,27 @@ $BackKatakanaEx $BackKatakanaEx;
$BackExtendNumLetEx ($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $BackKatakanaEx | $BackExtendNumLetEx);
($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $BackKatakanaEx) $BackExtendNumLetEx;
# rule 13c
# special handling for CJK characters: chain for later dictionary segmentation
$HangulSyllable $HangulSyllable;
$KanaKanji $KanaKanji; #different rule status if both kanji and kana found
# rule 14
$E_Modifier ($Format | $Extend | $ZWJ)* ($E_Base | $EBG);
# rule 15 - 17
# Pairs of Regional Indicators stay together.
^$BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
^$BackRegional_IndicatorEx $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
$GAZ $ZWJ $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
($GAZ | $EBG) $ZWJ $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
$GAZ $ZWJ $BackRegional_IndicatorEx $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
($GAZ | $EBG) $ZWJ $BackRegional_IndicatorEx $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
# special handling for CJK characters: chain for later dictionary segmentation
$HangulSyllable $HangulSyllable;
$KanaKanji $KanaKanji; #different rule status if both kanji and kana found
# rule 13d
$E_Modifier ($Format | $Extend | $ZWJ)* ($E_Base | $GAZ);
## -------------------------------------------------

74
icu4c/source/data/brkitr/rules/word_POSIX.txt
View file

@ -1,13 +1,12 @@
#
# Copyright (C) 2002-2016, International Business Machines Corporation
# Copyright (C) 2002-2016, International Business Machines Corporation
# and others. All Rights Reserved.
#
# file: word_POSIX.txt
#
# ICU Word Break Rules, POSIX locale.
# See Unicode Standard Annex #29.
# These rules are based on UAX #29 Revision 27 for Unicode Version 8.0
# with additions from L2/16-011R3 for Emoji sequences.
# These rules are based on UAX #29 Revision 28 (draft 7) for Unicode Version 9.0
#
# Note: Updates to word.txt will usually need to be merged into
# word_POSIX.txt also.
@ -25,17 +24,13 @@
# Character Class Definitions.
#
$E_Base = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
$E_Modifier = [\U0001F3FB-\U0001F3FF];
$ZWJ = [\u200D];
$GAZ = [\U0001F466-\U0001F469\U0001F48B\U0001F5E8\u2764];
$CR = [\p{Word_Break = CR}];
$LF = [\p{Word_Break = LF}];
$Newline = [\p{Word_Break = Newline} ];
$Extend = [[\p{Word_Break = Extend}][:Block=Tags:]];
$Extend = [\p{Word_Break = Extend}];
$ZWJ = [\p{Word_Break = ZWJ}];
$Regional_Indicator = [\p{Word_Break = Regional_Indicator}];
$Format = [[\p{Word_Break = Format}] - [:Block=Tags:]];
$Format = [\p{Word_Break = Format}];
$Katakana = [\p{Word_Break = Katakana}];
$Hebrew_Letter = [\p{Word_Break = Hebrew_Letter}];
$ALetter = [\p{Word_Break = ALetter}];
@ -46,6 +41,10 @@ $MidLetter = [\p{Word_Break = MidLetter} - [\:]];
$MidNum = [\p{Word_Break = MidNum} [.]];
$Numeric = [\p{Word_Break = Numeric}];
$ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
$E_Base = [\p{Word_Break = EB}];
$E_Modifier = [\p{Word_Break = EM}];
$GAZ = [\p{Word_Break = GAZ}];
$EBG = [\p{Word_Break = EBG}];
$Han = [:Han:];
$Hiragana = [:Hiragana:];
@ -56,7 +55,7 @@ $Hiragana = [:Hiragana:];
# 5.0 or later as the definition of Complex_Context was corrected to include all
# characters requiring dictionary break.
$Control = [\p{Grapheme_Cluster_Break = Control}];
$Control = [\p{Grapheme_Cluster_Break = Control}];
$HangulSyllable = [\uac00-\ud7a3];
$ComplexContext = [:LineBreak = Complex_Context:];
$KanaKanji = [$Han $Hiragana $Katakana];
@ -68,7 +67,7 @@ $ALetterPlus = [$ALetter-$dictionaryCJK [$ComplexContext-$Extend-$Control]];
#
# Rules 4 Ignore Format and Extend characters,
# Rules 4 Ignore Format and Extend characters,
# except when they appear at the beginning of a region of text.
#
# TODO: check if handling of katakana in dictionary makes rules incorrect/void
@ -99,7 +98,7 @@ $CR $LF;
# Rule 3c ZWJ x GAZ. Preceeds WB4, so no intervening Extend chars allowed.
#
$ZWJ $GAZ;
$ZWJ ($GAZ | $EBG);
# Rule 4 - ignore Format and Extend characters, except when they appear at the beginning
@ -148,7 +147,7 @@ $NumericEx $NumericEx {100};
$NumericEx ($ALetterEx | $Hebrew_LetterEx) {200};
# rule 11 and 12
# rule 11 and 12
$NumericEx ($MidNumEx | $MidNumLetEx | $Single_QuoteEx) $NumericEx {100};
@ -171,7 +170,12 @@ $ExtendNumLetEx $Hebrew_Letter {200}; # (13b)
$ExtendNumLetEx $NumericEx {100}; # (13b)
$ExtendNumLetEx $KatakanaEx {400}; # (13b)
# rule 13c
# rule 14
# Do not break within emoji modifier sequences
($E_Base | $EBG) ($Format | $Extend | $ZWJ)* $E_Modifier;
# rules 15 - 17
# Pairs of Regional Indicators stay together.
# With rule chaining disabled by ^, this rule will match exactly two of them.
# No other rule begins with a Regional_Indicator, so chaining cannot extend the match.
@ -180,12 +184,7 @@ $ExtendNumLetEx $KatakanaEx {400}; # (13b)
# special handling for CJK characters: chain for later dictionary segmentation
$HangulSyllable $HangulSyllable {200};
$KanaKanji $KanaKanji {400}; # different rule status if both kana and kanji found
# rule 13d
# E_Base x E_Modifier
#
($E_Base | $GAZ) ($Format | $Extend | $ZWJ)* $E_Modifier;
$KanaKanji $KanaKanji {400}; # different rule status if both kana and kanji found
## -------------------------------------------------
@ -210,7 +209,7 @@ $LF $CR;
# Rule 3c ZWJ x GAZ. Preceeds WB4, so no intervening Extend chars allowed.
#
$GAZ $ZWJ;
($GAZ | $EBG) $ZWJ;
# rule 4
($Format | $Extend | $ZWJ)* [^$CR $LF $Newline]?;
@ -252,27 +251,28 @@ $BackKatakanaEx $BackKatakanaEx;
# rules 13 a/b
#
$BackExtendNumLetEx ($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $BackKatakanaEx | $BackExtendNumLetEx);
($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $BackKatakanaEx) $BackExtendNumLetEx;
# rule 13c
^$BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
^$BackRegional_IndicatorEx $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
$GAZ $ZWJ $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
$GAZ $ZWJ $BackRegional_IndicatorEx $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $BackKatakanaEx) $BackExtendNumLetEx;
# special handling for CJK characters: chain for later dictionary segmentation
$HangulSyllable $HangulSyllable;
$KanaKanji $KanaKanji; #different rule status if both kanji and kana found
# rule 13d
# rule 14
$E_Modifier ($Format | $Extend | $ZWJ)* ($E_Base | $GAZ);
$E_Modifier ($Format | $Extend | $ZWJ)* ($E_Base | $EBG);
# rule 15 - 17
# Pairs of Regional Indicators stay together.
^$BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
^$BackRegional_IndicatorEx $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
($GAZ | $EBG) $ZWJ $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
($GAZ | $EBG) $ZWJ $BackRegional_IndicatorEx $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];

1733
icu4c/source/data/coll/zh.txt
View file

File diff suppressed because one or more lines are too long

BIN
icu4c/source/data/in/coll/ucadata-implicithan.icu
View file

Binary file not shown.

BIN
icu4c/source/data/in/coll/ucadata-unihan.icu
View file

Binary file not shown.

BIN
icu4c/source/data/in/nfc.nrm
View file

Binary file not shown.

BIN
icu4c/source/data/in/nfkc.nrm
View file

Binary file not shown.

BIN
icu4c/source/data/in/nfkc_cf.nrm
View file

Binary file not shown.

BIN
icu4c/source/data/in/pnames.icu
View file

Binary file not shown.

BIN
icu4c/source/data/in/ubidi.icu
View file

Binary file not shown.

BIN
icu4c/source/data/in/ucase.icu
View file

Binary file not shown.

BIN
icu4c/source/data/in/unames.icu
View file

Binary file not shown.

BIN
icu4c/source/data/in/uprops.icu
View file

Binary file not shown.

BIN
icu4c/source/data/in/uts46.nrm
View file

Binary file not shown.

2
icu4c/source/data/makedata.mak
View file

@ -13,7 +13,7 @@
U_ICUDATA_NAME=icudt58
##############################################################################
U_ICUDATA_ENDIAN_SUFFIX=l
UNICODE_VERSION=8.0
UNICODE_VERSION=9.0
ICU_LIB_TARGET=$(DLL_OUTPUT)\$(U_ICUDATA_NAME).dll
# ICUMAKE

91
icu4c/source/data/unidata/CaseFolding.txt
View file

@ -1,10 +1,11 @@
# CaseFolding-8.0.0.txt
# Date: 2015-01-13, 18:16:36 GMT [MD]
# CaseFolding-9.0.0.txt
# Date: 2016-03-02, 18:54:54 GMT
# © 2016 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# Copyright (c) 1991-2015 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see http://www.unicode.org/reports/tr44/
#
# Case Folding Properties
#
@ -593,6 +594,15 @@
13FB; C; 13F3; # CHEROKEE SMALL LETTER YU
13FC; C; 13F4; # CHEROKEE SMALL LETTER YV
13FD; C; 13F5; # CHEROKEE SMALL LETTER MV
1C80; C; 0432; # CYRILLIC SMALL LETTER ROUNDED VE
1C81; C; 0434; # CYRILLIC SMALL LETTER LONG-LEGGED DE
1C82; C; 043E; # CYRILLIC SMALL LETTER NARROW O
1C83; C; 0441; # CYRILLIC SMALL LETTER WIDE ES
1C84; C; 0442; # CYRILLIC SMALL LETTER TALL TE
1C85; C; 0442; # CYRILLIC SMALL LETTER THREE-LEGGED TE
1C86; C; 044A; # CYRILLIC SMALL LETTER TALL HARD SIGN
1C87; C; 0463; # CYRILLIC SMALL LETTER TALL YAT
1C88; C; A64B; # CYRILLIC SMALL LETTER UNBLENDED UK
1E00; C; 1E01; # LATIN CAPITAL LETTER A WITH RING BELOW
1E02; C; 1E03; # LATIN CAPITAL LETTER B WITH DOT ABOVE
1E04; C; 1E05; # LATIN CAPITAL LETTER B WITH DOT BELOW
@ -1163,6 +1173,7 @@ A7AA; C; 0266; # LATIN CAPITAL LETTER H WITH HOOK
A7AB; C; 025C; # LATIN CAPITAL LETTER REVERSED OPEN E
A7AC; C; 0261; # LATIN CAPITAL LETTER SCRIPT G
A7AD; C; 026C; # LATIN CAPITAL LETTER L WITH BELT
A7AE; C; 026A; # LATIN CAPITAL LETTER SMALL CAPITAL I
A7B0; C; 029E; # LATIN CAPITAL LETTER TURNED K
A7B1; C; 0287; # LATIN CAPITAL LETTER TURNED T
A7B2; C; 029D; # LATIN CAPITAL LETTER J WITH CROSSED-TAIL
@ -1327,6 +1338,42 @@ FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z
10425; C; 1044D; # DESERET CAPITAL LETTER ENG
10426; C; 1044E; # DESERET CAPITAL LETTER OI
10427; C; 1044F; # DESERET CAPITAL LETTER EW
104B0; C; 104D8; # OSAGE CAPITAL LETTER A
104B1; C; 104D9; # OSAGE CAPITAL LETTER AI
104B2; C; 104DA; # OSAGE CAPITAL LETTER AIN
104B3; C; 104DB; # OSAGE CAPITAL LETTER AH
104B4; C; 104DC; # OSAGE CAPITAL LETTER BRA
104B5; C; 104DD; # OSAGE CAPITAL LETTER CHA
104B6; C; 104DE; # OSAGE CAPITAL LETTER EHCHA
104B7; C; 104DF; # OSAGE CAPITAL LETTER E
104B8; C; 104E0; # OSAGE CAPITAL LETTER EIN
104B9; C; 104E1; # OSAGE CAPITAL LETTER HA
104BA; C; 104E2; # OSAGE CAPITAL LETTER HYA
104BB; C; 104E3; # OSAGE CAPITAL LETTER I
104BC; C; 104E4; # OSAGE CAPITAL LETTER KA
104BD; C; 104E5; # OSAGE CAPITAL LETTER EHKA
104BE; C; 104E6; # OSAGE CAPITAL LETTER KYA
104BF; C; 104E7; # OSAGE CAPITAL LETTER LA
104C0; C; 104E8; # OSAGE CAPITAL LETTER MA
104C1; C; 104E9; # OSAGE CAPITAL LETTER NA
104C2; C; 104EA; # OSAGE CAPITAL LETTER O
104C3; C; 104EB; # OSAGE CAPITAL LETTER OIN
104C4; C; 104EC; # OSAGE CAPITAL LETTER PA
104C5; C; 104ED; # OSAGE CAPITAL LETTER EHPA
104C6; C; 104EE; # OSAGE CAPITAL LETTER SA
104C7; C; 104EF; # OSAGE CAPITAL LETTER SHA
104C8; C; 104F0; # OSAGE CAPITAL LETTER TA
104C9; C; 104F1; # OSAGE CAPITAL LETTER EHTA
104CA; C; 104F2; # OSAGE CAPITAL LETTER TSA
104CB; C; 104F3; # OSAGE CAPITAL LETTER EHTSA
104CC; C; 104F4; # OSAGE CAPITAL LETTER TSHA
104CD; C; 104F5; # OSAGE CAPITAL LETTER DHA
104CE; C; 104F6; # OSAGE CAPITAL LETTER U
104CF; C; 104F7; # OSAGE CAPITAL LETTER WA
104D0; C; 104F8; # OSAGE CAPITAL LETTER KHA
104D1; C; 104F9; # OSAGE CAPITAL LETTER GHA
104D2; C; 104FA; # OSAGE CAPITAL LETTER ZA
104D3; C; 104FB; # OSAGE CAPITAL LETTER ZHA
10C80; C; 10CC0; # OLD HUNGARIAN CAPITAL LETTER A
10C81; C; 10CC1; # OLD HUNGARIAN CAPITAL LETTER AA
10C82; C; 10CC2; # OLD HUNGARIAN CAPITAL LETTER EB
@ -1410,5 +1457,39 @@ FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z
118BD; C; 118DD; # WARANG CITI CAPITAL LETTER SSUU
118BE; C; 118DE; # WARANG CITI CAPITAL LETTER SII
118BF; C; 118DF; # WARANG CITI CAPITAL LETTER VIYO
1E900; C; 1E922; # ADLAM CAPITAL LETTER ALIF
1E901; C; 1E923; # ADLAM CAPITAL LETTER DAALI
1E902; C; 1E924; # ADLAM CAPITAL LETTER LAAM
1E903; C; 1E925; # ADLAM CAPITAL LETTER MIIM
1E904; C; 1E926; # ADLAM CAPITAL LETTER BA
1E905; C; 1E927; # ADLAM CAPITAL LETTER SINNYIIYHE
1E906; C; 1E928; # ADLAM CAPITAL LETTER PE
1E907; C; 1E929; # ADLAM CAPITAL LETTER BHE
1E908; C; 1E92A; # ADLAM CAPITAL LETTER RA
1E909; C; 1E92B; # ADLAM CAPITAL LETTER E
1E90A; C; 1E92C; # ADLAM CAPITAL LETTER FA
1E90B; C; 1E92D; # ADLAM CAPITAL LETTER I
1E90C; C; 1E92E; # ADLAM CAPITAL LETTER O
1E90D; C; 1E92F; # ADLAM CAPITAL LETTER DHA
1E90E; C; 1E930; # ADLAM CAPITAL LETTER YHE
1E90F; C; 1E931; # ADLAM CAPITAL LETTER WAW
1E910; C; 1E932; # ADLAM CAPITAL LETTER NUN
1E911; C; 1E933; # ADLAM CAPITAL LETTER KAF
1E912; C; 1E934; # ADLAM CAPITAL LETTER YA
1E913; C; 1E935; # ADLAM CAPITAL LETTER U
1E914; C; 1E936; # ADLAM CAPITAL LETTER JIIM
1E915; C; 1E937; # ADLAM CAPITAL LETTER CHI
1E916; C; 1E938; # ADLAM CAPITAL LETTER HA
1E917; C; 1E939; # ADLAM CAPITAL LETTER QAAF
1E918; C; 1E93A; # ADLAM CAPITAL LETTER GA
1E919; C; 1E93B; # ADLAM CAPITAL LETTER NYA
1E91A; C; 1E93C; # ADLAM CAPITAL LETTER TU
1E91B; C; 1E93D; # ADLAM CAPITAL LETTER NHA
1E91C; C; 1E93E; # ADLAM CAPITAL LETTER VA
1E91D; C; 1E93F; # ADLAM CAPITAL LETTER KHA
1E91E; C; 1E940; # ADLAM CAPITAL LETTER GBE
1E91F; C; 1E941; # ADLAM CAPITAL LETTER ZAL
1E920; C; 1E942; # ADLAM CAPITAL LETTER KPO
1E921; C; 1E943; # ADLAM CAPITAL LETTER SHA
#
# EOF

413
icu4c/source/data/unidata/DerivedCoreProperties.txt
View file

File diff suppressed because it is too large Load diff

110
icu4c/source/data/unidata/DerivedNormalizationProps.txt
View file

@ -1,10 +1,11 @@
# DerivedNormalizationProps-8.0.0.txt
# Date: 2015-02-13, 13:30:23 GMT [MD]
# DerivedNormalizationProps-9.0.0.txt
# Date: 2016-03-02, 18:54:59 GMT
# © 2016 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# Copyright (c) 1991-2015 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see http://www.unicode.org/reports/tr44/
# ================================================
@ -1679,12 +1680,12 @@ FFED..FFEE ; NFKD_QC; N
1F16A..1F16B ; NFKD_QC; N
1F190 ; NFKD_QC; N
1F200..1F202 ; NFKD_QC; N
1F210..1F23A ; NFKD_QC; N
1F210..1F23B ; NFKD_QC; N
1F240..1F248 ; NFKD_QC; N
1F250..1F251 ; NFKD_QC; N
2F800..2FA1D ; NFKD_QC; N
# Total code points: 16893
# Total code points: 16894
# ================================================
@ -2082,12 +2083,12 @@ FFED..FFEE ; NFKC_QC; N
1F16A..1F16B ; NFKC_QC; N
1F190 ; NFKC_QC; N
1F200..1F202 ; NFKC_QC; N
1F210..1F23A ; NFKC_QC; N
1F210..1F23B ; NFKC_QC; N
1F240..1F248 ; NFKC_QC; N
1F250..1F251 ; NFKC_QC; N
2F800..2FA1D ; NFKC_QC; N
# Total code points: 4793
# Total code points: 4794
# ================================================
@ -3513,6 +3514,14 @@ FFE3 ; Expands_On_NFKC
17B4..17B5 ; NFKC_CF;
180B..180D ; NFKC_CF;
180E ; NFKC_CF;
1C80 ; NFKC_CF; 0432
1C81 ; NFKC_CF; 0434
1C82 ; NFKC_CF; 043E
1C83 ; NFKC_CF; 0441
1C84..1C85 ; NFKC_CF; 0442
1C86 ; NFKC_CF; 044A
1C87 ; NFKC_CF; 0463
1C88 ; NFKC_CF; A64B
1D2C ; NFKC_CF; 0061
1D2D ; NFKC_CF; 00E6
1D2E ; NFKC_CF; 0062
@ -5263,6 +5272,7 @@ A7AA ; NFKC_CF; 0266
A7AB ; NFKC_CF; 025C
A7AC ; NFKC_CF; 0261
A7AD ; NFKC_CF; 026C
A7AE ; NFKC_CF; 026A
A7B0 ; NFKC_CF; 029E
A7B1 ; NFKC_CF; 0287
A7B2 ; NFKC_CF; 029D
@ -6731,6 +6741,42 @@ FFF0..FFF8 ; NFKC_CF;
10425 ; NFKC_CF; 1044D
10426 ; NFKC_CF; 1044E
10427 ; NFKC_CF; 1044F
104B0 ; NFKC_CF; 104D8
104B1 ; NFKC_CF; 104D9
104B2 ; NFKC_CF; 104DA
104B3 ; NFKC_CF; 104DB
104B4 ; NFKC_CF; 104DC
104B5 ; NFKC_CF; 104DD
104B6 ; NFKC_CF; 104DE
104B7 ; NFKC_CF; 104DF
104B8 ; NFKC_CF; 104E0
104B9 ; NFKC_CF; 104E1
104BA ; NFKC_CF; 104E2
104BB ; NFKC_CF; 104E3
104BC ; NFKC_CF; 104E4
104BD ; NFKC_CF; 104E5
104BE ; NFKC_CF; 104E6
104BF ; NFKC_CF; 104E7
104C0 ; NFKC_CF; 104E8
104C1 ; NFKC_CF; 104E9
104C2 ; NFKC_CF; 104EA
104C3 ; NFKC_CF; 104EB
104C4 ; NFKC_CF; 104EC
104C5 ; NFKC_CF; 104ED
104C6 ; NFKC_CF; 104EE
104C7 ; NFKC_CF; 104EF
104C8 ; NFKC_CF; 104F0
104C9 ; NFKC_CF; 104F1
104CA ; NFKC_CF; 104F2
104CB ; NFKC_CF; 104F3
104CC ; NFKC_CF; 104F4
104CD ; NFKC_CF; 104F5
104CE ; NFKC_CF; 104F6
104CF ; NFKC_CF; 104F7
104D0 ; NFKC_CF; 104F8
104D1 ; NFKC_CF; 104F9
104D2 ; NFKC_CF; 104FA
104D3 ; NFKC_CF; 104FB
10C80 ; NFKC_CF; 10CC0
10C81 ; NFKC_CF; 10CC1
10C82 ; NFKC_CF; 10CC2
@ -7819,6 +7865,40 @@ FFF0..FFF8 ; NFKC_CF;
1D7FD ; NFKC_CF; 0037
1D7FE ; NFKC_CF; 0038
1D7FF ; NFKC_CF; 0039
1E900 ; NFKC_CF; 1E922
1E901 ; NFKC_CF; 1E923
1E902 ; NFKC_CF; 1E924
1E903 ; NFKC_CF; 1E925
1E904 ; NFKC_CF; 1E926
1E905 ; NFKC_CF; 1E927
1E906 ; NFKC_CF; 1E928
1E907 ; NFKC_CF; 1E929
1E908 ; NFKC_CF; 1E92A
1E909 ; NFKC_CF; 1E92B
1E90A ; NFKC_CF; 1E92C
1E90B ; NFKC_CF; 1E92D
1E90C ; NFKC_CF; 1E92E
1E90D ; NFKC_CF; 1E92F
1E90E ; NFKC_CF; 1E930
1E90F ; NFKC_CF; 1E931
1E910 ; NFKC_CF; 1E932
1E911 ; NFKC_CF; 1E933
1E912 ; NFKC_CF; 1E934
1E913 ; NFKC_CF; 1E935
1E914 ; NFKC_CF; 1E936
1E915 ; NFKC_CF; 1E937
1E916 ; NFKC_CF; 1E938
1E917 ; NFKC_CF; 1E939
1E918 ; NFKC_CF; 1E93A
1E919 ; NFKC_CF; 1E93B
1E91A ; NFKC_CF; 1E93C
1E91B ; NFKC_CF; 1E93D
1E91C ; NFKC_CF; 1E93E
1E91D ; NFKC_CF; 1E93F
1E91E ; NFKC_CF; 1E940
1E91F ; NFKC_CF; 1E941
1E920 ; NFKC_CF; 1E942
1E921 ; NFKC_CF; 1E943
1EE00 ; NFKC_CF; 0627
1EE01 ; NFKC_CF; 0628
1EE02 ; NFKC_CF; 062C
@ -8083,6 +8163,7 @@ FFF0..FFF8 ; NFKC_CF;
1F238 ; NFKC_CF; 7533
1F239 ; NFKC_CF; 5272
1F23A ; NFKC_CF; 55B6
1F23B ; NFKC_CF; 914D
1F240 ; NFKC_CF; 3014 672C 3015
1F241 ; NFKC_CF; 3014 4E09 3015
1F242 ; NFKC_CF; 3014 4E8C 3015
@ -8634,7 +8715,7 @@ E0080..E00FF ; NFKC_CF;
E0100..E01EF ; NFKC_CF;
E01F0..E0FFF ; NFKC_CF;
# Total code points: 10146
# Total code points: 10227
# ================================================
@ -8972,6 +9053,7 @@ E01F0..E0FFF ; NFKC_CF;
17B4..17B5 ; Changes_When_NFKC_Casefolded
180B..180D ; Changes_When_NFKC_Casefolded
180E ; Changes_When_NFKC_Casefolded
1C80..1C88 ; Changes_When_NFKC_Casefolded
1D2C..1D2E ; Changes_When_NFKC_Casefolded
1D30..1D3A ; Changes_When_NFKC_Casefolded
1D3C..1D4D ; Changes_When_NFKC_Casefolded
@ -9389,7 +9471,7 @@ A7A2 ; Changes_When_NFKC_Casefolded
A7A4 ; Changes_When_NFKC_Casefolded
A7A6 ; Changes_When_NFKC_Casefolded
A7A8 ; Changes_When_NFKC_Casefolded
A7AA..A7AD ; Changes_When_NFKC_Casefolded
A7AA..A7AE ; Changes_When_NFKC_Casefolded
A7B0..A7B4 ; Changes_When_NFKC_Casefolded
A7B6 ; Changes_When_NFKC_Casefolded
A7F8..A7F9 ; Changes_When_NFKC_Casefolded
@ -9519,6 +9601,7 @@ FFE9..FFEC ; Changes_When_NFKC_Casefolded
FFED..FFEE ; Changes_When_NFKC_Casefolded
FFF0..FFF8 ; Changes_When_NFKC_Casefolded
10400..10427 ; Changes_When_NFKC_Casefolded
104B0..104D3 ; Changes_When_NFKC_Casefolded
10C80..10CB2 ; Changes_When_NFKC_Casefolded
118A0..118BF ; Changes_When_NFKC_Casefolded
1BCA0..1BCA3 ; Changes_When_NFKC_Casefolded
@ -9566,6 +9649,7 @@ FFF0..FFF8 ; Changes_When_NFKC_Casefolded
1D7C3 ; Changes_When_NFKC_Casefolded
1D7C4..1D7CB ; Changes_When_NFKC_Casefolded
1D7CE..1D7FF ; Changes_When_NFKC_Casefolded
1E900..1E921 ; Changes_When_NFKC_Casefolded
1EE00..1EE03 ; Changes_When_NFKC_Casefolded
1EE05..1EE1F ; Changes_When_NFKC_Casefolded
1EE21..1EE22 ; Changes_When_NFKC_Casefolded
@ -9605,7 +9689,7 @@ FFF0..FFF8 ; Changes_When_NFKC_Casefolded
1F16A..1F16B ; Changes_When_NFKC_Casefolded
1F190 ; Changes_When_NFKC_Casefolded
1F200..1F202 ; Changes_When_NFKC_Casefolded
1F210..1F23A ; Changes_When_NFKC_Casefolded
1F210..1F23B ; Changes_When_NFKC_Casefolded
1F240..1F248 ; Changes_When_NFKC_Casefolded
1F250..1F251 ; Changes_When_NFKC_Casefolded
2F800..2FA1D ; Changes_When_NFKC_Casefolded
@ -9617,6 +9701,6 @@ E0080..E00FF ; Changes_When_NFKC_Casefolded
E0100..E01EF ; Changes_When_NFKC_Casefolded
E01F0..E0FFF ; Changes_When_NFKC_Casefolded
# Total code points: 10146
# Total code points: 10227
# EOF

26464
icu4c/source/data/unidata/FractionalUCA.txt
View file

File diff suppressed because it is too large Load diff

12
icu4c/source/data/unidata/NormalizationCorrections.txt
View file

@ -1,12 +1,14 @@
# NormalizationCorrections-8.0.0.txt
# Date: 2015-03-07, 01:30:00 GMT [KW, LI]
# NormalizationCorrections-9.0.0.txt
# Date: 2016-01-21, 22:00:00 GMT [KW, LI]
# © 2016 Unicode®, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see http://www.unicode.org/reports/tr44/
#
# This file is a normative contributory data file in the
# Unicode Character Database.
#
# Copyright (c) 1991-2015 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# The normalization stability policy of the Unicode Consortium
# ordinarily precludes any change to the decomposition
# for any character, once established in a relevant version

140
icu4c/source/data/unidata/NormalizationTest.txt
View file

@ -1,10 +1,11 @@
# NormalizationTest-8.0.0.txt
# Date: 2015-02-13, 13:30:27 GMT [MD]
# NormalizationTest-9.0.0.txt
# Date: 2016-04-04, 11:41:55 GMT
# © 2016 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# Copyright (c) 1991-2015 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see http://www.unicode.org/reports/tr44/
#
# Normalization Test Suite
# Format:
@ -63,6 +64,8 @@
0045 0300 0304;00C8 0304;0045 0300 0304;00C8 0304;0045 0300 0304;
05B8 05B9 05B1 0591 05C3 05B0 05AC 059F;05B1 05B8 05B9 0591 05C3 05B0 05AC 059F;05B1 05B8 05B9 0591 05C3 05B0 05AC 059F;05B1 05B8 05B9 0591 05C3 05B0 05AC 059F;05B1 05B8 05B9 0591 05C3 05B0 05AC 059F;
0592 05B7 05BC 05A5 05B0 05C0 05C4 05AD;05B0 05B7 05BC 05A5 0592 05C0 05AD 05C4;05B0 05B7 05BC 05A5 0592 05C0 05AD 05C4;05B0 05B7 05BC 05A5 0592 05C0 05AD 05C4;05B0 05B7 05BC 05A5 0592 05C0 05AD 05C4;
1100 AC00 11A8;1100 AC01;1100 1100 1161 11A8;1100 AC01;1100 1100 1161 11A8;
1100 AC00 11A8 11A8;1100 AC01 11A8;1100 1100 1161 11A8 11A8;1100 AC01 11A8;1100 1100 1161 11A8 11A8;
#
@Part1 # Character by character test
# All characters not explicitly occurring in c1 of Part 1 have identical NFC, D, KC, KD forms.
@ -16407,6 +16410,7 @@ FFEE;FFEE;FFEE;25CB;25CB;
1F238;1F238;1F238;7533;7533;
1F239;1F239;1F239;5272;5272;
1F23A;1F23A;1F23A;55B6;55B6;
1F23B;1F23B;1F23B;914D;914D;
1F240;1F240;1F240;3014 672C 3015;3014 672C 3015;
1F241;1F241;1F241;3014 4E09 3015;3014 4E09 3015;
1F242;1F242;1F242;3014 4E8C 3015;3014 4E8C 3015;
@ -17523,6 +17527,34 @@ FFEE;FFEE;FFEE;25CB;25CB;
0061 085A 059A 0316 302A 0062;0061 302A 085A 0316 059A 0062;0061 302A 085A 0316 059A 0062;0061 302A 085A 0316 059A 0062;0061 302A 085A 0316 059A 0062;
0061 059A 0316 302A 085B 0062;0061 302A 0316 085B 059A 0062;0061 302A 0316 085B 059A 0062;0061 302A 0316 085B 059A 0062;0061 302A 0316 085B 059A 0062;
0061 085B 059A 0316 302A 0062;0061 302A 085B 0316 059A 0062;0061 302A 085B 0316 059A 0062;0061 302A 085B 0316 059A 0062;0061 302A 085B 0316 059A 0062;
0061 0315 0300 05AE 08D4 0062;00E0 05AE 08D4 0315 0062;0061 05AE 0300 08D4 0315 0062;00E0 05AE 08D4 0315 0062;0061 05AE 0300 08D4 0315 0062;
0061 08D4 0315 0300 05AE 0062;0061 05AE 08D4 0300 0315 0062;0061 05AE 08D4 0300 0315 0062;0061 05AE 08D4 0300 0315 0062;0061 05AE 08D4 0300 0315 0062;
0061 0315 0300 05AE 08D5 0062;00E0 05AE 08D5 0315 0062;0061 05AE 0300 08D5 0315 0062;00E0 05AE 08D5 0315 0062;0061 05AE 0300 08D5 0315 0062;
0061 08D5 0315 0300 05AE 0062;0061 05AE 08D5 0300 0315 0062;0061 05AE 08D5 0300 0315 0062;0061 05AE 08D5 0300 0315 0062;0061 05AE 08D5 0300 0315 0062;
0061 0315 0300 05AE 08D6 0062;00E0 05AE 08D6 0315 0062;0061 05AE 0300 08D6 0315 0062;00E0 05AE 08D6 0315 0062;0061 05AE 0300 08D6 0315 0062;
0061 08D6 0315 0300 05AE 0062;0061 05AE 08D6 0300 0315 0062;0061 05AE 08D6 0300 0315 0062;0061 05AE 08D6 0300 0315 0062;0061 05AE 08D6 0300 0315 0062;
0061 0315 0300 05AE 08D7 0062;00E0 05AE 08D7 0315 0062;0061 05AE 0300 08D7 0315 0062;00E0 05AE 08D7 0315 0062;0061 05AE 0300 08D7 0315 0062;
0061 08D7 0315 0300 05AE 0062;0061 05AE 08D7 0300 0315 0062;0061 05AE 08D7 0300 0315 0062;0061 05AE 08D7 0300 0315 0062;0061 05AE 08D7 0300 0315 0062;
0061 0315 0300 05AE 08D8 0062;00E0 05AE 08D8 0315 0062;0061 05AE 0300 08D8 0315 0062;00E0 05AE 08D8 0315 0062;0061 05AE 0300 08D8 0315 0062;
0061 08D8 0315 0300 05AE 0062;0061 05AE 08D8 0300 0315 0062;0061 05AE 08D8 0300 0315 0062;0061 05AE 08D8 0300 0315 0062;0061 05AE 08D8 0300 0315 0062;
0061 0315 0300 05AE 08D9 0062;00E0 05AE 08D9 0315 0062;0061 05AE 0300 08D9 0315 0062;00E0 05AE 08D9 0315 0062;0061 05AE 0300 08D9 0315 0062;
0061 08D9 0315 0300 05AE 0062;0061 05AE 08D9 0300 0315 0062;0061 05AE 08D9 0300 0315 0062;0061 05AE 08D9 0300 0315 0062;0061 05AE 08D9 0300 0315 0062;
0061 0315 0300 05AE 08DA 0062;00E0 05AE 08DA 0315 0062;0061 05AE 0300 08DA 0315 0062;00E0 05AE 08DA 0315 0062;0061 05AE 0300 08DA 0315 0062;
0061 08DA 0315 0300 05AE 0062;0061 05AE 08DA 0300 0315 0062;0061 05AE 08DA 0300 0315 0062;0061 05AE 08DA 0300 0315 0062;0061 05AE 08DA 0300 0315 0062;
0061 0315 0300 05AE 08DB 0062;00E0 05AE 08DB 0315 0062;0061 05AE 0300 08DB 0315 0062;00E0 05AE 08DB 0315 0062;0061 05AE 0300 08DB 0315 0062;
0061 08DB 0315 0300 05AE 0062;0061 05AE 08DB 0300 0315 0062;0061 05AE 08DB 0300 0315 0062;0061 05AE 08DB 0300 0315 0062;0061 05AE 08DB 0300 0315 0062;
0061 0315 0300 05AE 08DC 0062;00E0 05AE 08DC 0315 0062;0061 05AE 0300 08DC 0315 0062;00E0 05AE 08DC 0315 0062;0061 05AE 0300 08DC 0315 0062;
0061 08DC 0315 0300 05AE 0062;0061 05AE 08DC 0300 0315 0062;0061 05AE 08DC 0300 0315 0062;0061 05AE 08DC 0300 0315 0062;0061 05AE 08DC 0300 0315 0062;
0061 0315 0300 05AE 08DD 0062;00E0 05AE 08DD 0315 0062;0061 05AE 0300 08DD 0315 0062;00E0 05AE 08DD 0315 0062;0061 05AE 0300 08DD 0315 0062;
0061 08DD 0315 0300 05AE 0062;0061 05AE 08DD 0300 0315 0062;0061 05AE 08DD 0300 0315 0062;0061 05AE 08DD 0300 0315 0062;0061 05AE 08DD 0300 0315 0062;
0061 0315 0300 05AE 08DE 0062;00E0 05AE 08DE 0315 0062;0061 05AE 0300 08DE 0315 0062;00E0 05AE 08DE 0315 0062;0061 05AE 0300 08DE 0315 0062;
0061 08DE 0315 0300 05AE 0062;0061 05AE 08DE 0300 0315 0062;0061 05AE 08DE 0300 0315 0062;0061 05AE 08DE 0300 0315 0062;0061 05AE 08DE 0300 0315 0062;
0061 0315 0300 05AE 08DF 0062;00E0 05AE 08DF 0315 0062;0061 05AE 0300 08DF 0315 0062;00E0 05AE 08DF 0315 0062;0061 05AE 0300 08DF 0315 0062;
0061 08DF 0315 0300 05AE 0062;0061 05AE 08DF 0300 0315 0062;0061 05AE 08DF 0300 0315 0062;0061 05AE 08DF 0300 0315 0062;0061 05AE 08DF 0300 0315 0062;
0061 0315 0300 05AE 08E0 0062;00E0 05AE 08E0 0315 0062;0061 05AE 0300 08E0 0315 0062;00E0 05AE 08E0 0315 0062;0061 05AE 0300 08E0 0315 0062;
0061 08E0 0315 0300 05AE 0062;0061 05AE 08E0 0300 0315 0062;0061 05AE 08E0 0300 0315 0062;0061 05AE 08E0 0300 0315 0062;0061 05AE 08E0 0300 0315 0062;
0061 0315 0300 05AE 08E1 0062;00E0 05AE 08E1 0315 0062;0061 05AE 0300 08E1 0315 0062;00E0 05AE 08E1 0315 0062;0061 05AE 0300 08E1 0315 0062;
0061 08E1 0315 0300 05AE 0062;0061 05AE 08E1 0300 0315 0062;0061 05AE 08E1 0300 0315 0062;0061 05AE 08E1 0300 0315 0062;0061 05AE 08E1 0300 0315 0062;
0061 059A 0316 302A 08E3 0062;0061 302A 0316 08E3 059A 0062;0061 302A 0316 08E3 059A 0062;0061 302A 0316 08E3 059A 0062;0061 302A 0316 08E3 059A 0062;
0061 08E3 059A 0316 302A 0062;0061 302A 08E3 0316 059A 0062;0061 302A 08E3 0316 059A 0062;0061 302A 08E3 0316 059A 0062;0061 302A 08E3 0316 059A 0062;
0061 0315 0300 05AE 08E4 0062;00E0 05AE 08E4 0315 0062;0061 05AE 0300 08E4 0315 0062;00E0 05AE 08E4 0315 0062;0061 05AE 0300 08E4 0315 0062;
@ -17967,6 +17999,8 @@ FFEE;FFEE;FFEE;25CB;25CB;
0061 1DF4 0315 0300 05AE 0062;0061 05AE 1DF4 0300 0315 0062;0061 05AE 1DF4 0300 0315 0062;0061 05AE 1DF4 0300 0315 0062;0061 05AE 1DF4 0300 0315 0062;
0061 0315 0300 05AE 1DF5 0062;00E0 05AE 1DF5 0315 0062;0061 05AE 0300 1DF5 0315 0062;00E0 05AE 1DF5 0315 0062;0061 05AE 0300 1DF5 0315 0062;
0061 1DF5 0315 0300 05AE 0062;0061 05AE 1DF5 0300 0315 0062;0061 05AE 1DF5 0300 0315 0062;0061 05AE 1DF5 0300 0315 0062;0061 05AE 1DF5 0300 0315 0062;
0061 0315 0300 05AE 1DFB 0062;00E0 05AE 1DFB 0315 0062;0061 05AE 0300 1DFB 0315 0062;00E0 05AE 1DFB 0315 0062;0061 05AE 0300 1DFB 0315 0062;
0061 1DFB 0315 0300 05AE 0062;0061 05AE 1DFB 0300 0315 0062;0061 05AE 1DFB 0300 0315 0062;0061 05AE 1DFB 0300 0315 0062;0061 05AE 1DFB 0300 0315 0062;
0061 035D 035C 0315 1DFC 0062;0061 0315 035C 1DFC 035D 0062;0061 0315 035C 1DFC 035D 0062;0061 0315 035C 1DFC 035D 0062;0061 0315 035C 1DFC 035D 0062;
0061 1DFC 035D 035C 0315 0062;0061 0315 1DFC 035C 035D 0062;0061 0315 1DFC 035C 035D 0062;0061 0315 1DFC 035C 035D 0062;0061 0315 1DFC 035C 035D 0062;
0061 059A 0316 302A 1DFD 0062;0061 302A 0316 1DFD 059A 0062;0061 302A 0316 1DFD 059A 0062;0061 302A 0316 1DFD 059A 0062;0061 302A 0316 1DFD 059A 0062;
@ -18343,6 +18377,10 @@ FFEE;FFEE;FFEE;25CB;25CB;
0061 11373 0315 0300 05AE 0062;0061 05AE 11373 0300 0315 0062;0061 05AE 11373 0300 0315 0062;0061 05AE 11373 0300 0315 0062;0061 05AE 11373 0300 0315 0062;
0061 0315 0300 05AE 11374 0062;00E0 05AE 11374 0315 0062;0061 05AE 0300 11374 0315 0062;00E0 05AE 11374 0315 0062;0061 05AE 0300 11374 0315 0062;
0061 11374 0315 0300 05AE 0062;0061 05AE 11374 0300 0315 0062;0061 05AE 11374 0300 0315 0062;0061 05AE 11374 0300 0315 0062;0061 05AE 11374 0300 0315 0062;
0061 05B0 094D 3099 11442 0062;0061 3099 094D 11442 05B0 0062;0061 3099 094D 11442 05B0 0062;0061 3099 094D 11442 05B0 0062;0061 3099 094D 11442 05B0 0062;
0061 11442 05B0 094D 3099 0062;0061 3099 11442 094D 05B0 0062;0061 3099 11442 094D 05B0 0062;0061 3099 11442 094D 05B0 0062;0061 3099 11442 094D 05B0 0062;
0061 3099 093C 0334 11446 0062;0061 0334 093C 11446 3099 0062;0061 0334 093C 11446 3099 0062;0061 0334 093C 11446 3099 0062;0061 0334 093C 11446 3099 0062;
0061 11446 3099 093C 0334 0062;0061 0334 11446 093C 3099 0062;0061 0334 11446 093C 3099 0062;0061 0334 11446 093C 3099 0062;0061 0334 11446 093C 3099 0062;
0061 05B0 094D 3099 114C2 0062;0061 3099 094D 114C2 05B0 0062;0061 3099 094D 114C2 05B0 0062;0061 3099 094D 114C2 05B0 0062;0061 3099 094D 114C2 05B0 0062;
0061 114C2 05B0 094D 3099 0062;0061 3099 114C2 094D 05B0 0062;0061 3099 114C2 094D 05B0 0062;0061 3099 114C2 094D 05B0 0062;0061 3099 114C2 094D 05B0 0062;
0061 3099 093C 0334 114C3 0062;0061 0334 093C 114C3 3099 0062;0061 0334 093C 114C3 3099 0062;0061 0334 093C 114C3 3099 0062;0061 0334 093C 114C3 3099 0062;
@ -18359,6 +18397,8 @@ FFEE;FFEE;FFEE;25CB;25CB;
0061 116B7 3099 093C 0334 0062;0061 0334 116B7 093C 3099 0062;0061 0334 116B7 093C 3099 0062;0061 0334 116B7 093C 3099 0062;0061 0334 116B7 093C 3099 0062;
0061 05B0 094D 3099 1172B 0062;0061 3099 094D 1172B 05B0 0062;0061 3099 094D 1172B 05B0 0062;0061 3099 094D 1172B 05B0 0062;0061 3099 094D 1172B 05B0 0062;
0061 1172B 05B0 094D 3099 0062;0061 3099 1172B 094D 05B0 0062;0061 3099 1172B 094D 05B0 0062;0061 3099 1172B 094D 05B0 0062;0061 3099 1172B 094D 05B0 0062;
0061 05B0 094D 3099 11C3F 0062;0061 3099 094D 11C3F 05B0 0062;0061 3099 094D 11C3F 05B0 0062;0061 3099 094D 11C3F 05B0 0062;0061 3099 094D 11C3F 05B0 0062;
0061 11C3F 05B0 094D 3099 0062;0061 3099 11C3F 094D 05B0 0062;0061 3099 11C3F 094D 05B0 0062;0061 3099 11C3F 094D 05B0 0062;0061 3099 11C3F 094D 05B0 0062;
0061 093C 0334 16AF0 0062;0061 0334 16AF0 093C 0062;0061 0334 16AF0 093C 0062;0061 0334 16AF0 093C 0062;0061 0334 16AF0 093C 0062;
0061 16AF0 093C 0334 0062;0061 16AF0 0334 093C 0062;0061 16AF0 0334 093C 0062;0061 16AF0 0334 093C 0062;0061 16AF0 0334 093C 0062;
0061 093C 0334 16AF1 0062;0061 0334 16AF1 093C 0062;0061 0334 16AF1 093C 0062;0061 0334 16AF1 093C 0062;0061 0334 16AF1 093C 0062;
@ -18451,6 +18491,82 @@ FFEE;FFEE;FFEE;25CB;25CB;
0061 1D243 0315 0300 05AE 0062;0061 05AE 1D243 0300 0315 0062;0061 05AE 1D243 0300 0315 0062;0061 05AE 1D243 0300 0315 0062;0061 05AE 1D243 0300 0315 0062;
0061 0315 0300 05AE 1D244 0062;00E0 05AE 1D244 0315 0062;0061 05AE 0300 1D244 0315 0062;00E0 05AE 1D244 0315 0062;0061 05AE 0300 1D244 0315 0062;
0061 1D244 0315 0300 05AE 0062;0061 05AE 1D244 0300 0315 0062;0061 05AE 1D244 0300 0315 0062;0061 05AE 1D244 0300 0315 0062;0061 05AE 1D244 0300 0315 0062;
0061 0315 0300 05AE 1E000 0062;00E0 05AE 1E000 0315 0062;0061 05AE 0300 1E000 0315 0062;00E0 05AE 1E000 0315 0062;0061 05AE 0300 1E000 0315 0062;
0061 1E000 0315 0300 05AE 0062;0061 05AE 1E000 0300 0315 0062;0061 05AE 1E000 0300 0315 0062;0061 05AE 1E000 0300 0315 0062;0061 05AE 1E000 0300 0315 0062;
0061 0315 0300 05AE 1E001 0062;00E0 05AE 1E001 0315 0062;0061 05AE 0300 1E001 0315 0062;00E0 05AE 1E001 0315 0062;0061 05AE 0300 1E001 0315 0062;
0061 1E001 0315 0300 05AE 0062;0061 05AE 1E001 0300 0315 0062;0061 05AE 1E001 0300 0315 0062;0061 05AE 1E001 0300 0315 0062;0061 05AE 1E001 0300 0315 0062;
0061 0315 0300 05AE 1E002 0062;00E0 05AE 1E002 0315 0062;0061 05AE 0300 1E002 0315 0062;00E0 05AE 1E002 0315 0062;0061 05AE 0300 1E002 0315 0062;
0061 1E002 0315 0300 05AE 0062;0061 05AE 1E002 0300 0315 0062;0061 05AE 1E002 0300 0315 0062;0061 05AE 1E002 0300 0315 0062;0061 05AE 1E002 0300 0315 0062;
0061 0315 0300 05AE 1E003 0062;00E0 05AE 1E003 0315 0062;0061 05AE 0300 1E003 0315 0062;00E0 05AE 1E003 0315 0062;0061 05AE 0300 1E003 0315 0062;
0061 1E003 0315 0300 05AE 0062;0061 05AE 1E003 0300 0315 0062;0061 05AE 1E003 0300 0315 0062;0061 05AE 1E003 0300 0315 0062;0061 05AE 1E003 0300 0315 0062;
0061 0315 0300 05AE 1E004 0062;00E0 05AE 1E004 0315 0062;0061 05AE 0300 1E004 0315 0062;00E0 05AE 1E004 0315 0062;0061 05AE 0300 1E004 0315 0062;
0061 1E004 0315 0300 05AE 0062;0061 05AE 1E004 0300 0315 0062;0061 05AE 1E004 0300 0315 0062;0061 05AE 1E004 0300 0315 0062;0061 05AE 1E004 0300 0315 0062;
0061 0315 0300 05AE 1E005 0062;00E0 05AE 1E005 0315 0062;0061 05AE 0300 1E005 0315 0062;00E0 05AE 1E005 0315 0062;0061 05AE 0300 1E005 0315 0062;
0061 1E005 0315 0300 05AE 0062;0061 05AE 1E005 0300 0315 0062;0061 05AE 1E005 0300 0315 0062;0061 05AE 1E005 0300 0315 0062;0061 05AE 1E005 0300 0315 0062;
0061 0315 0300 05AE 1E006 0062;00E0 05AE 1E006 0315 0062;0061 05AE 0300 1E006 0315 0062;00E0 05AE 1E006 0315 0062;0061 05AE 0300 1E006 0315 0062;
0061 1E006 0315 0300 05AE 0062;0061 05AE 1E006 0300 0315 0062;0061 05AE 1E006 0300 0315 0062;0061 05AE 1E006 0300 0315 0062;0061 05AE 1E006 0300 0315 0062;
0061 0315 0300 05AE 1E008 0062;00E0 05AE 1E008 0315 0062;0061 05AE 0300 1E008 0315 0062;00E0 05AE 1E008 0315 0062;0061 05AE 0300 1E008 0315 0062;
0061 1E008 0315 0300 05AE 0062;0061 05AE 1E008 0300 0315 0062;0061 05AE 1E008 0300 0315 0062;0061 05AE 1E008 0300 0315 0062;0061 05AE 1E008 0300 0315 0062;
0061 0315 0300 05AE 1E009 0062;00E0 05AE 1E009 0315 0062;0061 05AE 0300 1E009 0315 0062;00E0 05AE 1E009 0315 0062;0061 05AE 0300 1E009 0315 0062;
0061 1E009 0315 0300 05AE 0062;0061 05AE 1E009 0300 0315 0062;0061 05AE 1E009 0300 0315 0062;0061 05AE 1E009 0300 0315 0062;0061 05AE 1E009 0300 0315 0062;
0061 0315 0300 05AE 1E00A 0062;00E0 05AE 1E00A 0315 0062;0061 05AE 0300 1E00A 0315 0062;00E0 05AE 1E00A 0315 0062;0061 05AE 0300 1E00A 0315 0062;
0061 1E00A 0315 0300 05AE 0062;0061 05AE 1E00A 0300 0315 0062;0061 05AE 1E00A 0300 0315 0062;0061 05AE 1E00A 0300 0315 0062;0061 05AE 1E00A 0300 0315 0062;
0061 0315 0300 05AE 1E00B 0062;00E0 05AE 1E00B 0315 0062;0061 05AE 0300 1E00B 0315 0062;00E0 05AE 1E00B 0315 0062;0061 05AE 0300 1E00B 0315 0062;
0061 1E00B 0315 0300 05AE 0062;0061 05AE 1E00B 0300 0315 0062;0061 05AE 1E00B 0300 0315 0062;0061 05AE 1E00B 0300 0315 0062;0061 05AE 1E00B 0300 0315 0062;
0061 0315 0300 05AE 1E00C 0062;00E0 05AE 1E00C 0315 0062;0061 05AE 0300 1E00C 0315 0062;00E0 05AE 1E00C 0315 0062;0061 05AE 0300 1E00C 0315 0062;
0061 1E00C 0315 0300 05AE 0062;0061 05AE 1E00C 0300 0315 0062;0061 05AE 1E00C 0300 0315 0062;0061 05AE 1E00C 0300 0315 0062;0061 05AE 1E00C 0300 0315 0062;
0061 0315 0300 05AE 1E00D 0062;00E0 05AE 1E00D 0315 0062;0061 05AE 0300 1E00D 0315 0062;00E0 05AE 1E00D 0315 0062;0061 05AE 0300 1E00D 0315 0062;
0061 1E00D 0315 0300 05AE 0062;0061 05AE 1E00D 0300 0315 0062;0061 05AE 1E00D 0300 0315 0062;0061 05AE 1E00D 0300 0315 0062;0061 05AE 1E00D 0300 0315 0062;
0061 0315 0300 05AE 1E00E 0062;00E0 05AE 1E00E 0315 0062;0061 05AE 0300 1E00E 0315 0062;00E0 05AE 1E00E 0315 0062;0061 05AE 0300 1E00E 0315 0062;
0061 1E00E 0315 0300 05AE 0062;0061 05AE 1E00E 0300 0315 0062;0061 05AE 1E00E 0300 0315 0062;0061 05AE 1E00E 0300 0315 0062;0061 05AE 1E00E 0300 0315 0062;
0061 0315 0300 05AE 1E00F 0062;00E0 05AE 1E00F 0315 0062;0061 05AE 0300 1E00F 0315 0062;00E0 05AE 1E00F 0315 0062;0061 05AE 0300 1E00F 0315 0062;
0061 1E00F 0315 0300 05AE 0062;0061 05AE 1E00F 0300 0315 0062;0061 05AE 1E00F 0300 0315 0062;0061 05AE 1E00F 0300 0315 0062;0061 05AE 1E00F 0300 0315 0062;
0061 0315 0300 05AE 1E010 0062;00E0 05AE 1E010 0315 0062;0061 05AE 0300 1E010 0315 0062;00E0 05AE 1E010 0315 0062;0061 05AE 0300 1E010 0315 0062;
0061 1E010 0315 0300 05AE 0062;0061 05AE 1E010 0300 0315 0062;0061 05AE 1E010 0300 0315 0062;0061 05AE 1E010 0300 0315 0062;0061 05AE 1E010 0300 0315 0062;
0061 0315 0300 05AE 1E011 0062;00E0 05AE 1E011 0315 0062;0061 05AE 0300 1E011 0315 0062;00E0 05AE 1E011 0315 0062;0061 05AE 0300 1E011 0315 0062;
0061 1E011 0315 0300 05AE 0062;0061 05AE 1E011 0300 0315 0062;0061 05AE 1E011 0300 0315 0062;0061 05AE 1E011 0300 0315 0062;0061 05AE 1E011 0300 0315 0062;
0061 0315 0300 05AE 1E012 0062;00E0 05AE 1E012 0315 0062;0061 05AE 0300 1E012 0315 0062;00E0 05AE 1E012 0315 0062;0061 05AE 0300 1E012 0315 0062;
0061 1E012 0315 0300 05AE 0062;0061 05AE 1E012 0300 0315 0062;0061 05AE 1E012 0300 0315 0062;0061 05AE 1E012 0300 0315 0062;0061 05AE 1E012 0300 0315 0062;
0061 0315 0300 05AE 1E013 0062;00E0 05AE 1E013 0315 0062;0061 05AE 0300 1E013 0315 0062;00E0 05AE 1E013 0315 0062;0061 05AE 0300 1E013 0315 0062;
0061 1E013 0315 0300 05AE 0062;0061 05AE 1E013 0300 0315 0062;0061 05AE 1E013 0300 0315 0062;0061 05AE 1E013 0300 0315 0062;0061 05AE 1E013 0300 0315 0062;
0061 0315 0300 05AE 1E014 0062;00E0 05AE 1E014 0315 0062;0061 05AE 0300 1E014 0315 0062;00E0 05AE 1E014 0315 0062;0061 05AE 0300 1E014 0315 0062;
0061 1E014 0315 0300 05AE 0062;0061 05AE 1E014 0300 0315 0062;0061 05AE 1E014 0300 0315 0062;0061 05AE 1E014 0300 0315 0062;0061 05AE 1E014 0300 0315 0062;
0061 0315 0300 05AE 1E015 0062;00E0 05AE 1E015 0315 0062;0061 05AE 0300 1E015 0315 0062;00E0 05AE 1E015 0315 0062;0061 05AE 0300 1E015 0315 0062;
0061 1E015 0315 0300 05AE 0062;0061 05AE 1E015 0300 0315 0062;0061 05AE 1E015 0300 0315 0062;0061 05AE 1E015 0300 0315 0062;0061 05AE 1E015 0300 0315 0062;
0061 0315 0300 05AE 1E016 0062;00E0 05AE 1E016 0315 0062;0061 05AE 0300 1E016 0315 0062;00E0 05AE 1E016 0315 0062;0061 05AE 0300 1E016 0315 0062;
0061 1E016 0315 0300 05AE 0062;0061 05AE 1E016 0300 0315 0062;0061 05AE 1E016 0300 0315 0062;0061 05AE 1E016 0300 0315 0062;0061 05AE 1E016 0300 0315 0062;
0061 0315 0300 05AE 1E017 0062;00E0 05AE 1E017 0315 0062;0061 05AE 0300 1E017 0315 0062;00E0 05AE 1E017 0315 0062;0061 05AE 0300 1E017 0315 0062;
0061 1E017 0315 0300 05AE 0062;0061 05AE 1E017 0300 0315 0062;0061 05AE 1E017 0300 0315 0062;0061 05AE 1E017 0300 0315 0062;0061 05AE 1E017 0300 0315 0062;
0061 0315 0300 05AE 1E018 0062;00E0 05AE 1E018 0315 0062;0061 05AE 0300 1E018 0315 0062;00E0 05AE 1E018 0315 0062;0061 05AE 0300 1E018 0315 0062;
0061 1E018 0315 0300 05AE 0062;0061 05AE 1E018 0300 0315 0062;0061 05AE 1E018 0300 0315 0062;0061 05AE 1E018 0300 0315 0062;0061 05AE 1E018 0300 0315 0062;
0061 0315 0300 05AE 1E01B 0062;00E0 05AE 1E01B 0315 0062;0061 05AE 0300 1E01B 0315 0062;00E0 05AE 1E01B 0315 0062;0061 05AE 0300 1E01B 0315 0062;
0061 1E01B 0315 0300 05AE 0062;0061 05AE 1E01B 0300 0315 0062;0061 05AE 1E01B 0300 0315 0062;0061 05AE 1E01B 0300 0315 0062;0061 05AE 1E01B 0300 0315 0062;
0061 0315 0300 05AE 1E01C 0062;00E0 05AE 1E01C 0315 0062;0061 05AE 0300 1E01C 0315 0062;00E0 05AE 1E01C 0315 0062;0061 05AE 0300 1E01C 0315 0062;
0061 1E01C 0315 0300 05AE 0062;0061 05AE 1E01C 0300 0315 0062;0061 05AE 1E01C 0300 0315 0062;0061 05AE 1E01C 0300 0315 0062;0061 05AE 1E01C 0300 0315 0062;
0061 0315 0300 05AE 1E01D 0062;00E0 05AE 1E01D 0315 0062;0061 05AE 0300 1E01D 0315 0062;00E0 05AE 1E01D 0315 0062;0061 05AE 0300 1E01D 0315 0062;
0061 1E01D 0315 0300 05AE 0062;0061 05AE 1E01D 0300 0315 0062;0061 05AE 1E01D 0300 0315 0062;0061 05AE 1E01D 0300 0315 0062;0061 05AE 1E01D 0300 0315 0062;
0061 0315 0300 05AE 1E01E 0062;00E0 05AE 1E01E 0315 0062;0061 05AE 0300 1E01E 0315 0062;00E0 05AE 1E01E 0315 0062;0061 05AE 0300 1E01E 0315 0062;
0061 1E01E 0315 0300 05AE 0062;0061 05AE 1E01E 0300 0315 0062;0061 05AE 1E01E 0300 0315 0062;0061 05AE 1E01E 0300 0315 0062;0061 05AE 1E01E 0300 0315 0062;
0061 0315 0300 05AE 1E01F 0062;00E0 05AE 1E01F 0315 0062;0061 05AE 0300 1E01F 0315 0062;00E0 05AE 1E01F 0315 0062;0061 05AE 0300 1E01F 0315 0062;
0061 1E01F 0315 0300 05AE 0062;0061 05AE 1E01F 0300 0315 0062;0061 05AE 1E01F 0300 0315 0062;0061 05AE 1E01F 0300 0315 0062;0061 05AE 1E01F 0300 0315 0062;
0061 0315 0300 05AE 1E020 0062;00E0 05AE 1E020 0315 0062;0061 05AE 0300 1E020 0315 0062;00E0 05AE 1E020 0315 0062;0061 05AE 0300 1E020 0315 0062;
0061 1E020 0315 0300 05AE 0062;0061 05AE 1E020 0300 0315 0062;0061 05AE 1E020 0300 0315 0062;0061 05AE 1E020 0300 0315 0062;0061 05AE 1E020 0300 0315 0062;
0061 0315 0300 05AE 1E021 0062;00E0 05AE 1E021 0315 0062;0061 05AE 0300 1E021 0315 0062;00E0 05AE 1E021 0315 0062;0061 05AE 0300 1E021 0315 0062;
0061 1E021 0315 0300 05AE 0062;0061 05AE 1E021 0300 0315 0062;0061 05AE 1E021 0300 0315 0062;0061 05AE 1E021 0300 0315 0062;0061 05AE 1E021 0300 0315 0062;
0061 0315 0300 05AE 1E023 0062;00E0 05AE 1E023 0315 0062;0061 05AE 0300 1E023 0315 0062;00E0 05AE 1E023 0315 0062;0061 05AE 0300 1E023 0315 0062;
0061 1E023 0315 0300 05AE 0062;0061 05AE 1E023 0300 0315 0062;0061 05AE 1E023 0300 0315 0062;0061 05AE 1E023 0300 0315 0062;0061 05AE 1E023 0300 0315 0062;
0061 0315 0300 05AE 1E024 0062;00E0 05AE 1E024 0315 0062;0061 05AE 0300 1E024 0315 0062;00E0 05AE 1E024 0315 0062;0061 05AE 0300 1E024 0315 0062;
0061 1E024 0315 0300 05AE 0062;0061 05AE 1E024 0300 0315 0062;0061 05AE 1E024 0300 0315 0062;0061 05AE 1E024 0300 0315 0062;0061 05AE 1E024 0300 0315 0062;
0061 0315 0300 05AE 1E026 0062;00E0 05AE 1E026 0315 0062;0061 05AE 0300 1E026 0315 0062;00E0 05AE 1E026 0315 0062;0061 05AE 0300 1E026 0315 0062;
0061 1E026 0315 0300 05AE 0062;0061 05AE 1E026 0300 0315 0062;0061 05AE 1E026 0300 0315 0062;0061 05AE 1E026 0300 0315 0062;0061 05AE 1E026 0300 0315 0062;
0061 0315 0300 05AE 1E027 0062;00E0 05AE 1E027 0315 0062;0061 05AE 0300 1E027 0315 0062;00E0 05AE 1E027 0315 0062;0061 05AE 0300 1E027 0315 0062;
0061 1E027 0315 0300 05AE 0062;0061 05AE 1E027 0300 0315 0062;0061 05AE 1E027 0300 0315 0062;0061 05AE 1E027 0300 0315 0062;0061 05AE 1E027 0300 0315 0062;
0061 0315 0300 05AE 1E028 0062;00E0 05AE 1E028 0315 0062;0061 05AE 0300 1E028 0315 0062;00E0 05AE 1E028 0315 0062;0061 05AE 0300 1E028 0315 0062;
0061 1E028 0315 0300 05AE 0062;0061 05AE 1E028 0300 0315 0062;0061 05AE 1E028 0300 0315 0062;0061 05AE 1E028 0300 0315 0062;0061 05AE 1E028 0300 0315 0062;
0061 0315 0300 05AE 1E029 0062;00E0 05AE 1E029 0315 0062;0061 05AE 0300 1E029 0315 0062;00E0 05AE 1E029 0315 0062;0061 05AE 0300 1E029 0315 0062;
0061 1E029 0315 0300 05AE 0062;0061 05AE 1E029 0300 0315 0062;0061 05AE 1E029 0300 0315 0062;0061 05AE 1E029 0300 0315 0062;0061 05AE 1E029 0300 0315 0062;
0061 0315 0300 05AE 1E02A 0062;00E0 05AE 1E02A 0315 0062;0061 05AE 0300 1E02A 0315 0062;00E0 05AE 1E02A 0315 0062;0061 05AE 0300 1E02A 0315 0062;
0061 1E02A 0315 0300 05AE 0062;0061 05AE 1E02A 0300 0315 0062;0061 05AE 1E02A 0300 0315 0062;0061 05AE 1E02A 0300 0315 0062;0061 05AE 1E02A 0300 0315 0062;
0061 059A 0316 302A 1E8D0 0062;0061 302A 0316 1E8D0 059A 0062;0061 302A 0316 1E8D0 059A 0062;0061 302A 0316 1E8D0 059A 0062;0061 302A 0316 1E8D0 059A 0062;
0061 1E8D0 059A 0316 302A 0062;0061 302A 1E8D0 0316 059A 0062;0061 302A 1E8D0 0316 059A 0062;0061 302A 1E8D0 0316 059A 0062;0061 302A 1E8D0 0316 059A 0062;
0061 059A 0316 302A 1E8D1 0062;0061 302A 0316 1E8D1 059A 0062;0061 302A 0316 1E8D1 059A 0062;0061 302A 0316 1E8D1 059A 0062;0061 302A 0316 1E8D1 059A 0062;
@ -18465,6 +18581,20 @@ FFEE;FFEE;FFEE;25CB;25CB;
0061 1E8D5 059A 0316 302A 0062;0061 302A 1E8D5 0316 059A 0062;0061 302A 1E8D5 0316 059A 0062;0061 302A 1E8D5 0316 059A 0062;0061 302A 1E8D5 0316 059A 0062;
0061 059A 0316 302A 1E8D6 0062;0061 302A 0316 1E8D6 059A 0062;0061 302A 0316 1E8D6 059A 0062;0061 302A 0316 1E8D6 059A 0062;0061 302A 0316 1E8D6 059A 0062;
0061 1E8D6 059A 0316 302A 0062;0061 302A 1E8D6 0316 059A 0062;0061 302A 1E8D6 0316 059A 0062;0061 302A 1E8D6 0316 059A 0062;0061 302A 1E8D6 0316 059A 0062;
0061 0315 0300 05AE 1E944 0062;00E0 05AE 1E944 0315 0062;0061 05AE 0300 1E944 0315 0062;00E0 05AE 1E944 0315 0062;0061 05AE 0300 1E944 0315 0062;
0061 1E944 0315 0300 05AE 0062;0061 05AE 1E944 0300 0315 0062;0061 05AE 1E944 0300 0315 0062;0061 05AE 1E944 0300 0315 0062;0061 05AE 1E944 0300 0315 0062;
0061 0315 0300 05AE 1E945 0062;00E0 05AE 1E945 0315 0062;0061 05AE 0300 1E945 0315 0062;00E0 05AE 1E945 0315 0062;0061 05AE 0300 1E945 0315 0062;
0061 1E945 0315 0300 05AE 0062;0061 05AE 1E945 0300 0315 0062;0061 05AE 1E945 0300 0315 0062;0061 05AE 1E945 0300 0315 0062;0061 05AE 1E945 0300 0315 0062;
0061 0315 0300 05AE 1E946 0062;00E0 05AE 1E946 0315 0062;0061 05AE 0300 1E946 0315 0062;00E0 05AE 1E946 0315 0062;0061 05AE 0300 1E946 0315 0062;
0061 1E946 0315 0300 05AE 0062;0061 05AE 1E946 0300 0315 0062;0061 05AE 1E946 0300 0315 0062;0061 05AE 1E946 0300 0315 0062;0061 05AE 1E946 0300 0315 0062;
0061 0315 0300 05AE 1E947 0062;00E0 05AE 1E947 0315 0062;0061 05AE 0300 1E947 0315 0062;00E0 05AE 1E947 0315 0062;0061 05AE 0300 1E947 0315 0062;
0061 1E947 0315 0300 05AE 0062;0061 05AE 1E947 0300 0315 0062;0061 05AE 1E947 0300 0315 0062;0061 05AE 1E947 0300 0315 0062;0061 05AE 1E947 0300 0315 0062;
0061 0315 0300 05AE 1E948 0062;00E0 05AE 1E948 0315 0062;0061 05AE 0300 1E948 0315 0062;00E0 05AE 1E948 0315 0062;0061 05AE 0300 1E948 0315 0062;
0061 1E948 0315 0300 05AE 0062;0061 05AE 1E948 0300 0315 0062;0061 05AE 1E948 0300 0315 0062;0061 05AE 1E948 0300 0315 0062;0061 05AE 1E948 0300 0315 0062;
0061 0315 0300 05AE 1E949 0062;00E0 05AE 1E949 0315 0062;0061 05AE 0300 1E949 0315 0062;00E0 05AE 1E949 0315 0062;0061 05AE 0300 1E949 0315 0062;
0061 1E949 0315 0300 05AE 0062;0061 05AE 1E949 0300 0315 0062;0061 05AE 1E949 0300 0315 0062;0061 05AE 1E949 0300 0315 0062;0061 05AE 1E949 0300 0315 0062;
0061 3099 093C 0334 1E94A 0062;0061 0334 093C 1E94A 3099 0062;0061 0334 093C 1E94A 3099 0062;0061 0334 093C 1E94A 3099 0062;0061 0334 093C 1E94A 3099 0062;
0061 1E94A 3099 093C 0334 0062;0061 0334 1E94A 093C 3099 0062;0061 0334 1E94A 093C 3099 0062;0061 0334 1E94A 093C 3099 0062;0061 0334 1E94A 093C 3099 0062;
#
@Part3 # PRI #29 Test
#

11
icu4c/source/data/unidata/SpecialCasing.txt
View file

@ -1,10 +1,11 @@
# SpecialCasing-8.0.0.txt
# Date: 2014-12-16, 23:08:04 GMT [MD]
# SpecialCasing-9.0.0.txt
# Date: 2016-03-02, 18:55:13 GMT
# © 2016 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# Copyright (c) 1991-2014 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see http://www.unicode.org/reports/tr44/
#
# Special Casing
#

980
icu4c/source/data/unidata/UCARules.txt
View file

File diff suppressed because it is too large Load diff

1383
icu4c/source/data/unidata/UnicodeData.txt
View file

File diff suppressed because it is too large Load diff

359
icu4c/source/data/unidata/changes.txt
View file

@ -38,6 +38,365 @@ For new script codes see http://www.unicode.org/iso15924/codechanges.html
---------------------------------------------------------------------------- ***
Unicode 9.0 update for ICU 58
* Command-line environment setup
ICU_ROOT=~/svn.icu/trunk
ICU_SRC_DIR=$ICU_ROOT/src
ICUDT=icudt58b
export LD_LIBRARY_PATH=$ICU_ROOT/dbg/lib
SRC_DATA_IN=$ICU_SRC_DIR/source/data/in
UNIDATA=$ICU_SRC_DIR/source/data/unidata
http://www.unicode.org/review/pri323/ -- beta review
http://www.unicode.org/reports/uax-proposed-updates.html
http://www.unicode.org/versions/beta-9.0.0.html
http://www.unicode.org/versions/Unicode9.0.0/
http://www.unicode.org/reports/tr44/tr44-17.html
*** ICU Trac
- ticket:12526: integrate Unicode 9
- C++ ^/icu/branches/markus/uni90
- Java ^/icu4j/branches/markus/uni90
*** CLDR Trac
- cldrbug 9414: UCA 9
- ^/branches/markus/uni90 at r11518 from trunk at r11517
- TODO cldrbug 8109: Unicode 8.0 script metadata
- TODO cldrbug 8418: Updated segmentation for Unicode 8.0
*** Unicode version numbers
- makedata.mak
- uchar.h
- com.ibm.icu.util.VersionInfo
- com.ibm.icu.dev.test.lang.UCharacterTest.VERSION_
- Run ICU4C "configure" _after_ updating the Unicode version number in uchar.h
so that the makefiles see the new version number.
*** data files & enums & parser code
* file preparation
- download UCD & IDNA files
- make sure that the Unicode data folder passed into preparseucd.py
includes a copy of the latest IdnaMappingTable.txt (can be in some subfolder)
- only for manual diffs: remove version suffixes from the file names
~/unidata/uni70/20140403$ ../../desuffixucd.py .
(see https://sites.google.com/site/unicodetools/inputdata)
- only for manual diffs: extract Unihan.zip to "here" (.../ucd/Unihan/*.txt), delete Unihan.zip
- ~/svn.icutools/trunk/src/unicode$ py/preparseucd.py ~/unidata/uni90/20160503 $ICU_SRC_DIR ~/svn.icutools/trunk/src
- This writes files (especially ppucd.txt) to the ICU4C unidata and testdata subfolders.
- also: from http://unicode.org/Public/security/9.0.0/ download new confusables.txt
and copy to $UNIDATA
cp ~/unidata/uni90/20160503/security/confusables.txt $UNIDATA
* preparseucd.py changes
- remove or add new Unicode scripts from/to the
only-in-ISO-15924 list according to the error messages:
ValueError: remove ['Tang'] from _scripts_only_in_iso15924
ValueError: sc = Hanb (uchar.h USCRIPT_HAN_WITH_BOPOMOFO) not in the UCD
ValueError: sc = Jamo (uchar.h USCRIPT_JAMO) not in the UCD
ValueError: sc = Zsye (uchar.h USCRIPT_SYMBOLS_EMOJI) not in the UCD
-> fix expectedLong names in cucdapi.c/TestUScriptCodeAPI()
and in com.ibm.icu.dev.test.lang.TestUScript.java
- DerivedNumericValues.txt new numeric values
0D58 ; 0.00625 ; ; 1/160 # No MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH
0D59 ; 0.025 ; ; 1/40 # No MALAYALAM FRACTION ONE FORTIETH
0D5A ; 0.0375 ; ; 3/80 # No MALAYALAM FRACTION THREE EIGHTIETHS
0D5B ; 0.05 ; ; 1/20 # No MALAYALAM FRACTION ONE TWENTIETH
0D5D ; 0.15 ; ; 3/20 # No MALAYALAM FRACTION THREE TWENTIETHS
-> change uprops.h, corepropsbuilder.cpp/encodeNumericValue(),
uchar.c, UCharacterProperty.java
to support a new series of values
- adjust preparseucd.py for Tangut algorithmic names
in ppucd.txt:
algnamesrange;17000..187EC;han;CJK UNIFIED IDEOGRAPH-
->
algnamesrange;17000..187EC;han;TANGUT IDEOGRAPH-
- avoid block-compressing most String/Miscellaneous property values,
triggered by genprops not coping with a multi-code point Case_Folding on
block;1C80..1C8F;...;Cased;cf=0442;CWCF;...
keep block-compressing empty-string mappings NFKC_CF="" for tags and variation selectors
* PropertyAliases.txt changes
- 1 new property PCM=Prepended_Concatenation_Mark
Ignore: Only useful for layout engines.
Ok to list in ppucd.txt.
* PropertyValueAliases.txt new property values
blk; Adlam ; Adlam
blk; Bhaiksuki ; Bhaiksuki
blk; Cyrillic_Ext_C ; Cyrillic_Extended_C
blk; Glagolitic_Sup ; Glagolitic_Supplement
blk; Ideographic_Symbols ; Ideographic_Symbols_And_Punctuation
blk; Marchen ; Marchen
blk; Mongolian_Sup ; Mongolian_Supplement
blk; Newa ; Newa
blk; Osage ; Osage
blk; Tangut ; Tangut
blk; Tangut_Components ; Tangut_Components
-> add to uchar.h
use long property names for enum constants
-> add to UCharacter.UnicodeBlock IDs
Eclipse find UBLOCK_([^ ]+) = ([0-9]+), (/.+)
replace public static final int \1_ID = \2; \3
-> add to UCharacter.UnicodeBlock objects
Eclipse find UBLOCK_([^ ]+) = [0-9]+, (/.+)
replace public static final UnicodeBlock \1 = new UnicodeBlock("\1", \1_ID); \2
GCB; EB ; E_Base
GCB; EBG ; E_Base_GAZ
GCB; EM ; E_Modifier
GCB; GAZ ; Glue_After_Zwj
GCB; ZWJ ; ZWJ
-> uchar.h & UCharacter.GraphemeClusterBreak
jg ; African_Feh ; African_Feh
jg ; African_Noon ; African_Noon
jg ; African_Qaf ; African_Qaf
-> uchar.h & UCharacter.JoiningGroup
lb ; EB ; E_Base
lb ; EM ; E_Modifier
lb ; ZWJ ; ZWJ
-> uchar.h & UCharacter.LineBreak
sc ; Adlm ; Adlam
sc ; Bhks ; Bhaiksuki
sc ; Marc ; Marchen
sc ; Newa ; Newa
sc ; Osge ; Osage
sc ; Tang ; Tangut
-> all of them had been added already to uscript.h & com.ibm.icu.lang.UScript
WB ; EB ; E_Base
WB ; EBG ; E_Base_GAZ
WB ; EM ; E_Modifier
WB ; GAZ ; Glue_After_Zwj
WB ; ZWJ ; ZWJ
-> uchar.h & UCharacter.WordBreak
* update Script metadata: SCRIPT_PROPS[] in uscript_props.cpp & UScript.ScriptMetadata
(not strictly necessary for NOT_ENCODED scripts)
~/svn.icutools/trunk/src/unicode$ py/parsescriptmetadata.py $ICU_SRC_DIR/source/common/unicode/uscript.h ~/svn.cldr/trunk/common/properties/scriptMetadata.txt
* generate normalization data files
cd $ICU_ROOT/dbg
bin/gennorm2 -o $ICU_SRC_DIR/source/common/norm2_nfc_data.h -s $UNIDATA/norm2 nfc.txt --csource
bin/gennorm2 -o $SRC_DATA_IN/nfc.nrm -s $UNIDATA/norm2 nfc.txt
bin/gennorm2 -o $SRC_DATA_IN/nfkc.nrm -s $UNIDATA/norm2 nfc.txt nfkc.txt
bin/gennorm2 -o $SRC_DATA_IN/nfkc_cf.nrm -s $UNIDATA/norm2 nfc.txt nfkc.txt nfkc_cf.txt
bin/gennorm2 -o $SRC_DATA_IN/uts46.nrm -s $UNIDATA/norm2 nfc.txt uts46.txt
* build ICU (make install)
so that the tools build can pick up the new definitions from the installed header files.
$ICU_ROOT/dbg$ echo;echo;make -j5 install > out.txt 2>&1 ; tail -n 30 out.txt
* build Unicode tools using CMake+make
~/svn.icutools/trunk/src/unicode/c/icudefs.txt:
# Location (--prefix) of where ICU was installed.
set(ICU_INST_DIR /home/mscherer/svn.icu/trunk/inst)
# Location of the ICU source tree.
set(ICU_SRC_DIR /home/mscherer/svn.icu/trunk/src)
~/svn.icutools/trunk/dbg/unicode/c$
cmake ../../../src/unicode/c
make
* generate core properties data files
~/svn.icutools/trunk/dbg/unicode/c$
genprops/genprops $ICU_SRC_DIR
genuca/genuca --hanOrder implicit $ICU_SRC_DIR
genuca/genuca --hanOrder radical-stroke $ICU_SRC_DIR
- rebuild ICU (make install) & tools
* update uts46test.cpp and UTS46Test.java if there are new characters that are equivalent to
sequences with non-LDH ASCII (that is, their decompositions contain '=' or similar)
- grep IdnaMappingTable.txt or uts46.txt for "disallowed_STD3_valid" on non-ASCII characters
- Unicode 6.0..9.0: U+2260, U+226E, U+226F
- nothing new in 9.0, no test file to update
* run & fix ICU4C tests
- Andy handles RBBI & spoof check test failures
* collation: CLDR collation root, UCA DUCET
- UCA DUCET goes into Mark's Unicode tools, see
https://sites.google.com/site/unicodetools/home#TOC-UCA
- CLDR root data files are checked into (CLDR UCA branch)/common/uca/
cp (UCA generated)/CollationAuxiliary/* ~/svn.cldr/trunk/common/uca/
- cd (CLDR UCA branch)/common/uca/
- update source/data/unidata/FractionalUCA.txt with FractionalUCA_SHORT.txt
cp FractionalUCA_SHORT.txt $ICU_SRC_DIR/source/data/unidata/FractionalUCA.txt
- update source/data/unidata/UCARules.txt with UCA_Rules_SHORT.txt
cp $ICU_SRC_DIR/source/data/unidata/UCARules.txt /tmp/UCARules-old.txt
(note removing the underscore before "Rules")
cp UCA_Rules_SHORT.txt $ICU_SRC_DIR/source/data/unidata/UCARules.txt
- restore TODO diffs in UCARules.txt
meld /tmp/UCARules-old.txt $ICU_SRC_DIR/source/data/unidata/UCARules.txt
- update (ICU4C)/source/test/testdata/CollationTest_*.txt
and (ICU4J)/main/tests/collate/src/com/ibm/icu/dev/data/CollationTest_*.txt
from the CLDR root files (..._CLDR_..._SHORT.txt)
cp CollationTest_CLDR_NON_IGNORABLE_SHORT.txt $ICU_SRC_DIR/source/test/testdata/CollationTest_NON_IGNORABLE_SHORT.txt
cp CollationTest_CLDR_SHIFTED_SHORT.txt $ICU_SRC_DIR/source/test/testdata/CollationTest_SHIFTED_SHORT.txt
cp $ICU_SRC_DIR/source/test/testdata/CollationTest_*.txt ~/svn.icu4j/trunk/src/main/tests/collate/src/com/ibm/icu/dev/data
- if CLDR common/uca/unihan-index.txt changes, then update
CLDR common/collation/root.xml <collation type="private-unihan">
and regenerate (or update in parallel) $ICU_SRC_DIR/source/data/coll/root.txt
- run genuca, see command line above;
deal with
Error: Unknown script for first-primary sample character U+104B5 on line 32599 of /home/mscherer/svn.icu/trunk/src/source/data/unidata/FractionalUCA.txt:
FDD1 104B5; [75 B8 02, 05, 05] # Osage first primary (compressible)
(add the character to genuca.cpp sampleCharsToScripts[])
+ look up the USCRIPT_ code for the new sample characters
(should be obvious from the comment in the error output)
+ *add* mappings to sampleCharsToScripts[], do not replace them
(in case the script sample characters flip-flop)
+ insert new scripts in DUCET script order, see the top_byte table
at the beginning of FractionalUCA.txt
- rebuild ICU4C
* Unihan collators
- run Unicode Tools
org.unicode.draft.GenerateUnihanCollators
with VM arguments
-DSVN_WORKSPACE=/home/mscherer/svn.unitools/trunk
-DOTHER_WORKSPACE=/home/mscherer/svn.unitools
-DUCD_DIR=/home/mscherer/svn.unitools/trunk/data
-DCLDR_DIR=/home/mscherer/svn.cldr/trunk
-DUVERSION=9.0.0
-ea
- run Unicode Tools
org.unicode.draft.GenerateUnihanCollatorFiles
with the same arguments
- check CLDR diffs
cd ~/svn.cldr/trunk
meld common/collation/zh.xml ../Generated/cldr/han/replace/zh.xml
meld common/transforms/Han-Latin.xml ../Generated/cldr/han/replace/Han-Latin.xml
- copy to CLDR
cd ~/svn.cldr/trunk
cp ../Generated/cldr/han/replace/zh.xml common/collation/zh.xml
cp ../Generated/cldr/han/replace/Han-Latin.xml common/transforms/Han-Latin.xml
- commit to CLDR
- generate ICU zh collation data: run CLDR
org.unicode.cldr.icu.NewLdml2IcuConverter
with program arguments
-t collation
-s /home/mscherer/svn.cldr/trunk/common/collation
-m /home/mscherer/svn.cldr/trunk/common/supplemental
-d /home/mscherer/svn.icu/trunk/src/source/data/coll
-p /home/mscherer/svn.icu/trunk/src/source/data/xml/collation
zh
and VM arguments
-DCLDR_DIR=/home/mscherer/svn.cldr/trunk
- rebuild ICU4C
* run & fix ICU4C tests, now with new CLDR collation root data
- run all tests with the collation test data *_SHORT.txt or the full files
(the full ones have comments, useful for debugging)
- note on intltest: if collate/UCAConformanceTest fails, then
utility/MultithreadTest/TestCollators will fail as well;
fix the conformance test before looking into the multi-thread test
* update Java data files
- refresh just the UCD/UCA-related/derived files, just to be safe
- see (ICU4C)/source/data/icu4j-readme.txt
- mkdir /tmp/icu4j
- ~/svn.icu/trunk/dbg$ make ICU4J_ROOT=/tmp/icu4j icu4j-data-install
output:
...
Unicode .icu files built to ./out/build/icudt57l
echo timestamp > uni-core-data
mkdir -p ./out/icu4j/com/ibm/icu/impl/data/icudt57b
mkdir -p ./out/icu4j/tzdata/com/ibm/icu/impl/data/icudt57b
echo pnames.icu uprops.icu ucase.icu ubidi.icu nfc.nrm > ./out/icu4j/add.txt
LD_LIBRARY_PATH=../lib:../stubdata:../tools/ctestfw:$LD_LIBRARY_PATH ../bin/icupkg ./out/tmp/icudt57l.dat ./out/icu4j/icudt57b.dat -a ./out/icu4j/add.txt -s ./out/build/icudt57l -x '*' -tb -d ./out/icu4j/com/ibm/icu/impl/data/icudt57b
mv ./out/icu4j/"com/ibm/icu/impl/data/icudt57b/zoneinfo64.res" ./out/icu4j/"com/ibm/icu/impl/data/icudt57b/metaZones.res" ./out/icu4j/"com/ibm/icu/impl/data/icudt57b/timezoneTypes.res" ./out/icu4j/"com/ibm/icu/impl/data/icudt57b/windowsZones.res" "./out/icu4j/tzdata/com/ibm/icu/impl/data/icudt57b"
jar cf ./out/icu4j/icudata.jar -C ./out/icu4j com/ibm/icu/impl/data/icudt57b/
mkdir -p /tmp/icu4j/main/shared/data
cp ./out/icu4j/icudata.jar /tmp/icu4j/main/shared/data
jar cf ./out/icu4j/icutzdata.jar -C ./out/icu4j/tzdata com/ibm/icu/impl/data/icudt57b/
mkdir -p /tmp/icu4j/main/shared/data
cp ./out/icu4j/icutzdata.jar /tmp/icu4j/main/shared/data
make[1]: Leaving directory `/home/mscherer/svn.icu/trunk/dbg/data'
- copy the big-endian Unicode data files to another location,
separate from the other data files,
and then refresh ICU4J
cd ~/svn.icu/trunk/dbg/data/out/icu4j
mkdir -p /tmp/icu4j/com/ibm/icu/impl/data/$ICUDT/coll
mkdir -p /tmp/icu4j/com/ibm/icu/impl/data/$ICUDT/brkitr
cp com/ibm/icu/impl/data/$ICUDT/confusables.cfu /tmp/icu4j/com/ibm/icu/impl/data/$ICUDT
cp com/ibm/icu/impl/data/$ICUDT/*.icu /tmp/icu4j/com/ibm/icu/impl/data/$ICUDT
rm /tmp/icu4j/com/ibm/icu/impl/data/$ICUDT/cnvalias.icu
cp com/ibm/icu/impl/data/$ICUDT/*.nrm /tmp/icu4j/com/ibm/icu/impl/data/$ICUDT
cp com/ibm/icu/impl/data/$ICUDT/coll/* /tmp/icu4j/com/ibm/icu/impl/data/$ICUDT/coll
cp com/ibm/icu/impl/data/$ICUDT/brkitr/* /tmp/icu4j/com/ibm/icu/impl/data/$ICUDT/brkitr
jar uvf ~/svn.icu4j/trunk/src/main/shared/data/icudata.jar -C /tmp/icu4j com/ibm/icu/impl/data/$ICUDT
* When refreshing all of ICU4J data from ICU4C
- ~/svn.icu/trunk/dbg$ make ICU4J_ROOT=/tmp/icu4j icu4j-data-install
- cp /tmp/icu4j/main/shared/data/icudata.jar ~/svn.icu4j/trunk/src/main/shared/data
or
- ~/svn.icu/trunk/dbg$ make ICU4J_ROOT=~/svn.icu4j/trunk/src icu4j-data-install
* update CollationFCD.java
+ copy & paste the initializers of lcccIndex[] etc. from
ICU4C/source/i18n/collationfcd.cpp to
ICU4J/main/classes/collate/src/com/ibm/icu/impl/coll/CollationFCD.java
* refresh Java test .txt files
- copy new .txt files into ICU4J's main/tests/core/src/com/ibm/icu/dev/data/unicode
cd $ICU_SRC_DIR/source/data/unidata
cp confusables.txt confusablesWholeScript.txt NormalizationCorrections.txt NormalizationTest.txt SpecialCasing.txt UnicodeData.txt ~/svn.icu4j/trunk/src/main/tests/core/src/com/ibm/icu/dev/data/unicode
cd ../../test/testdata
cp BidiCharacterTest.txt BidiTest.txt ~/svn.icu4j/trunk/src/main/tests/core/src/com/ibm/icu/dev/data/unicode
cp ~/unidata/uni90/20160503/ucd/CompositionExclusions.txt ~/svn.icu4j/trunk/src/main/tests/core/src/com/ibm/icu/dev/data/unicode
* run & fix ICU4J tests
*** LayoutEngine script information
* Run icu4j-tools: com.ibm.icu.dev.tool.layout.ScriptNameBuilder.
This generates LEScripts.h, LELanguages.h, ScriptAndLanguageTags.h and ScriptAndLanguageTags.cpp
in the working directory.
(It also generates ScriptRunData.cpp, which is no longer needed.)
It also reads and regenerates tools/misc/src/com/ibm/icu/dev/tool/layout/ScriptAndLanguages
(a plain text file)
which maps ICU versions to the numbers of script/language constants
that were added then.
(This mapping is probably obsolete since we do not print "@stable ICU xy" any more.)
The generated files have a current copyright date and "@deprecated" statement.
* Review changes, fix Java tool if necessary, and copy to ICU4C
cd ~/svn.icu4j/trunk/src
meld $ICU_SRC_DIR/source/layout tools/misc/src/com/ibm/icu/dev/tool/layout
cp tools/misc/src/com/ibm/icu/dev/tool/layout/*.h $ICU_SRC_DIR/source/layout
cp tools/misc/src/com/ibm/icu/dev/tool/layout/ScriptAndLanguageTags.cpp $ICU_SRC_DIR/source/layout
*** API additions
- send notice to icu-design about new born-@stable API (enum constants etc.)
*** merge the Unicode update branches back onto the trunk
- do not merge the icudata.jar and testdata.jar,
instead rebuild them from merged & tested ICU4C
- make sure that changes to Unicode tools & ICU tools are checked in
http://www.unicode.org/utility/trac/log/trunk/unicodetools
http://bugs.icu-project.org/trac/log/tools/trunk
---------------------------------------------------------------------------- ***
New script codes early in ICU 58: http://bugs.icu-project.org/trac/ticket/11764
Adding

199
icu4c/source/data/unidata/confusables.txt
View file

@ -1,10 +1,13 @@
# Recommended confusable mapping for IDN
# File: confusables.txt
# Version: 8.0.0
# Generated: 2015-05-17, 03:09:04 GMT
# Checkin: $Revision: 1.32 $
# confusables.txt
# Date: 2016-04-05, 11:47:12 GMT
# © 2016 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# For documentation and usage, see http://www.unicode.org/reports/tr39/
# Unicode Security Mechanisms for UTR #39
# Version: 9.0.0
#
# For documentation and usage, see http://www.unicode.org/reports/tr39
#
05AD ; 0596 ; MA # ( ֭ → ֖ ) HEBREW ACCENT DEHI → HEBREW ACCENT TIPEHA #
@ -57,6 +60,7 @@ A67C ; 0306 ; MA # ( ꙼ → ̆ ) COMBINING CYRILLIC KAVYKA → COMBINING BREVE
0311 ; 0302 ; MA # ( ̑ → ̂ ) COMBINING INVERTED BREVE → COMBINING CIRCUMFLEX ACCENT #
065B ; 0302 ; MA # ( ٛ → ̂ ) ARABIC VOWEL SIGN INVERTED SMALL V ABOVE → COMBINING CIRCUMFLEX ACCENT #
07EE ; 0302 ; MA # ( ߮ → ̂ ) NKO COMBINING LONG DESCENDING TONE → COMBINING CIRCUMFLEX ACCENT #
A6F0 ; 0302 ; MA # ( ꛰ → ̂ ) BAMUM COMBINING MARK KOQNDON → COMBINING CIRCUMFLEX ACCENT #
05AF ; 030A ; MA # ( ֯ → ̊ ) HEBREW MARK MASORA CIRCLE → COMBINING RING ABOVE #
06DF ; 030A ; MA # ( ۟ → ̊ ) ARABIC SMALL HIGH ROUNDED ZERO → COMBINING RING ABOVE # →ْ→
@ -66,6 +70,7 @@ A67C ; 0306 ; MA # ( ꙼ → ̆ ) COMBINING CYRILLIC KAVYKA → COMBINING BREVE
0B82 ; 030A ; MA # ( ஂ → ̊ ) TAMIL SIGN ANUSVARA → COMBINING RING ABOVE #
1036 ; 030A ; MA # ( ံ → ̊ ) MYANMAR SIGN ANUSVARA → COMBINING RING ABOVE #
17C6 ; 030A ; MA # ( ំ → ̊ ) KHMER SIGN NIKAHIT → COMBINING RING ABOVE #
11300 ; 030A ; MA # ( 𑌀 → ̊ ) GRANTHA SIGN COMBINING ANUSVARA ABOVE → COMBINING RING ABOVE # →ஂ→
0E4D ; 030A ; MA # ( ํ → ̊ ) THAI CHARACTER NIKHAHIT → COMBINING RING ABOVE #
0ECD ; 030A ; MA # ( ໍ → ̊ ) LAO NIGGAHITA → COMBINING RING ABOVE #
0366 ; 030A ; MA # ( ͦ → ̊ ) COMBINING LATIN SMALL LETTER O → COMBINING RING ABOVE #
@ -105,6 +110,7 @@ A67C ; 0306 ; MA # ( ꙼ → ̆ ) COMBINING CYRILLIC KAVYKA → COMBINING BREVE
0305 ; 0304 ; MA # ( ̅ → ̄ ) COMBINING OVERLINE → COMBINING MACRON #
0659 ; 0304 ; MA # ( ٙ → ̄ ) ARABIC ZWARAKAY → COMBINING MACRON #
07EB ; 0304 ; MA # ( ߫ → ̄ ) NKO COMBINING SHORT HIGH TONE → COMBINING MACRON #
A6F1 ; 0304 ; MA # ( ꛱ → ̄ ) BAMUM COMBINING MARK TUKWENTIS → COMBINING MACRON #
1CDA ; 030E ; MA # ( ᳚ → ̎ ) VEDIC TONE DOUBLE SVARITA → COMBINING DOUBLE VERTICAL LINE ABOVE #
@ -147,6 +153,7 @@ A67C ; 0306 ; MA # ( ꙼ → ̆ ) COMBINING CYRILLIC KAVYKA → COMBINING BREVE
0A3C ; 0323 ; MA # ( ਼ → ̣ ) GURMUKHI SIGN NUKTA → COMBINING DOT BELOW #
0ABC ; 0323 ; MA # ( ઼ → ̣ ) GUJARATI SIGN NUKTA → COMBINING DOT BELOW #
0B3C ; 0323 ; MA # ( ଼ → ̣ ) ORIYA SIGN NUKTA → COMBINING DOT BELOW #
111CA ; 0323 ; MA # ( 𑇊 → ̣ ) SHARADA SIGN NUKTA → COMBINING DOT BELOW # →़→
114C3 ; 0323 ; MA # ( 𑓃 → ̣ ) TIRHUTA SIGN NUKTA → COMBINING DOT BELOW # →়→
10A3A ; 0323 ; MA # ( 𐨺 → ̣ ) KHAROSHTHI SIGN DOT BELOW → COMBINING DOT BELOW #
@ -216,6 +223,8 @@ FC63 ; FE7C 0670 ; MA #* ( ‎ﱣ‎ → ‎ﹼٰ‎ ) ARABIC LIGATURE SHADDA WI
0ECB ; 0E4B ; MA # ( ໋ → ๋ ) LAO TONE MAI CATAWA → THAI CHARACTER MAI CHATTAWA #
A66F ; 20E9 ; MA # ( ꙯ → ⃩ ) COMBINING CYRILLIC VZMET → COMBINING WIDE BRIDGE ABOVE #
2028 ; 0020 ; MA #* ( → ) LINE SEPARATOR → SPACE #
2029 ; 0020 ; MA #* ( → ) PARAGRAPH SEPARATOR → SPACE #
1680 ; 0020 ; MA #* (   → ) OGHAM SPACE MARK → SPACE #
@ -311,6 +320,7 @@ FF01 ; 0021 ; MA #* ( ！ → ! ) FULLWIDTH EXCLAMATION MARK → EXCLAMATION MAR
0241 ; 003F ; MA # ( Ɂ → ? ) LATIN CAPITAL LETTER GLOTTAL STOP → QUESTION MARK # →ʔ→
097D ; 003F ; MA # ( ॽ → ? ) DEVANAGARI LETTER GLOTTAL STOP → QUESTION MARK #
13AE ; 003F ; MA # ( Ꭾ → ? ) CHEROKEE LETTER HE → QUESTION MARK # →Ɂ→→ʔ→
A6EB ; 003F ; MA # ( ꛫ → ? ) BAMUM LETTER NTUU → QUESTION MARK # →ʔ→
2048 ; 003F 0021 ; MA #* ( ⁈ → ?! ) QUESTION EXCLAMATION MARK → QUESTION MARK, EXCLAMATION MARK #
@ -335,6 +345,8 @@ A4FA ; 002E 002E ; MA # ( ꓺ → .. ) LISU LETTER TONE MYA CYA → FULL STOP, F
2026 ; 002E 002E 002E ; MA #* ( … → ... ) HORIZONTAL ELLIPSIS → FULL STOP, FULL STOP, FULL STOP #
A6F4 ; A6F3 A6F3 ; MA #* ( ꛴ → ꛳꛳ ) BAMUM COLON → BAMUM FULL STOP, BAMUM FULL STOP #
30FB ; 00B7 ; MA #* ( ・ → · ) KATAKANA MIDDLE DOT → MIDDLE DOT # →•→
FF65 ; 00B7 ; MA #* ( ･ → · ) HALFWIDTH KATAKANA MIDDLE DOT → MIDDLE DOT # →•→
16EB ; 00B7 ; MA #* ( ᛫ → · ) RUNIC SINGLE PUNCTUATION → MIDDLE DOT #
@ -345,8 +357,8 @@ FF65 ; 00B7 ; MA #* ( ･ → · ) HALFWIDTH KATAKANA MIDDLE DOT → MIDDLE DOT
2027 ; 00B7 ; MA #* ( ‧ → · ) HYPHENATION POINT → MIDDLE DOT #
2219 ; 00B7 ; MA #* ( ∙ → · ) BULLET OPERATOR → MIDDLE DOT #
22C5 ; 00B7 ; MA #* ( ⋅ → · ) DOT OPERATOR → MIDDLE DOT #
1427 ; 00B7 ; MA # ( ᐧ → · ) CANADIAN SYLLABICS FINAL MIDDLE DOT → MIDDLE DOT #
A78F ; 00B7 ; MA # ( ꞏ → · ) LATIN LETTER SINOLOGICAL DOT → MIDDLE DOT #
1427 ; 00B7 ; MA # ( ᐧ → · ) CANADIAN SYLLABICS FINAL MIDDLE DOT → MIDDLE DOT #
22EF ; 00B7 00B7 00B7 ; MA #* ( ⋯ → ··· ) MIDLINE HORIZONTAL ELLIPSIS → MIDDLE DOT, MIDDLE DOT, MIDDLE DOT #
2D48 ; 00B7 00B7 00B7 ; MA # ( ⵈ → ··· ) TIFINAGH LETTER TUAREG YAQ → MIDDLE DOT, MIDDLE DOT, MIDDLE DOT # →⋯→
@ -514,6 +526,8 @@ A78F ; 00B7 ; MA # ( ꞏ → · ) LATIN LETTER SINOLOGICAL DOT → MIDDLE DOT #
18C2 ; 00B7 18C0 ; MA # ( ᣂ → ·ᣀ ) CANADIAN SYLLABICS SHWOY → MIDDLE DOT, CANADIAN SYLLABICS SHOY # →ᐧᣀ→
A830 ; 0964 ; MA #* ( ꠰ → । ) NORTH INDIC FRACTION ONE QUARTER → DEVANAGARI DANDA #
0965 ; 0964 0964 ; MA #* ( ॥ → ।। ) DEVANAGARI DOUBLE DANDA → DEVANAGARI DANDA, DEVANAGARI DANDA #
1C3C ; 1C3B 1C3B ; MA #* ( ᰼ → ᰻᰻ ) LEPCHA PUNCTUATION NYET THYOOM TA-ROL → LEPCHA PUNCTUATION TA-ROL, LEPCHA PUNCTUATION TA-ROL #
@ -606,7 +620,7 @@ FD3E ; 0028 ; MA #* ( ﴾ → ( ) ORNATE LEFT PARENTHESIS → LEFT PARENTHESIS #
2E28 ; 0028 0028 ; MA #* ( ⸨ → (( ) LEFT DOUBLE PARENTHESIS → LEFT PARENTHESIS, LEFT PARENTHESIS #
3220 ; 0028 30FC 0029 ; MA #* ( ㈠ → (ー) ) PARENTHESIZED IDEOGRAPH ONE → LEFT PARENTHESIS, KATAKANA-HIRAGANA PROLONGED SOUND MARK, RIGHT PARENTHESIS # →(一)→
3220 ; 0028 30FC 0029 ; MA #* ( ㈠ → (ー) ) PARENTHESIZED IDEOGRAPH ONE → LEFT PARENTHESIS, KATAKANA-HIRAGANA PROLONGED SOUND MARK, RIGHT PARENTHESIS # →(一)→→(⼀)→
2475 ; 0028 0032 0029 ; MA #* ( ⑵ → (2) ) PARENTHESIZED DIGIT TWO → LEFT PARENTHESIS, DIGIT TWO, RIGHT PARENTHESIS #
@ -919,6 +933,9 @@ FD3F ; 0029 ; MA #* ( ﴿ → ) ) ORNATE RIGHT PARENTHESIS → RIGHT PARENTHESIS
27E8 ; 276C ; MA #* ( ⟨ → ❬ ) MATHEMATICAL LEFT ANGLE BRACKET → MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT # →〈→
2329 ; 276C ; MA #* ( 〈 → ❬ ) LEFT-POINTING ANGLE BRACKET → MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT # →〈→
3008 ; 276C ; MA #* ( 〈 → ❬ ) LEFT ANGLE BRACKET → MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT #
31DB ; 276C ; MA #* ( ㇛ → ❬ ) CJK STROKE PD → MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT # →⟨→→〈→
304F ; 276C ; MA # ( く → ❬ ) HIRAGANA LETTER KU → MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT # →㇛→→⟨→→〈→
21FE8 ; 276C ; MA # ( 𡿨 → ❬ ) CJK UNIFIED IDEOGRAPH-21FE8 → MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT # →㇛→→⟨→→〈→
27E9 ; 276D ; MA #* ( ⟩ → ❭ ) MATHEMATICAL RIGHT ANGLE BRACKET → MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT # →〉→
232A ; 276D ; MA #* ( 〉 → ❭ ) RIGHT-POINTING ANGLE BRACKET → MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT # →〉→
@ -940,9 +957,11 @@ FF3E ; FE3F ; MA #* ( ＾ → ︿ ) FULLWIDTH CIRCUMFLEX ACCENT → PRESENTATION
2571 ; 002F ; MA #* ( ╱ → / ) BOX DRAWINGS LIGHT DIAGONAL UPPER RIGHT TO LOWER LEFT → SOLIDUS #
27CB ; 002F ; MA #* ( ⟋ → / ) MATHEMATICAL RISING DIAGONAL → SOLIDUS #
29F8 ; 002F ; MA #* ( ⧸ → / ) BIG SOLIDUS → SOLIDUS #
1D23A ; 002F ; MA #* ( 𝈺 → / ) GREEK INSTRUMENTAL NOTATION SYMBOL-47 → SOLIDUS #
31D3 ; 002F ; MA #* ( ㇓ → / ) CJK STROKE SP → SOLIDUS # →⼃→
3033 ; 002F ; MA # ( 〳 → / ) VERTICAL KANA REPEAT MARK UPPER HALF → SOLIDUS #
2CC6 ; 002F ; MA # ( Ⳇ → / ) COPTIC CAPITAL LETTER OLD COPTIC ESH → SOLIDUS #
30CE ; 002F ; MA # ( ノ → / ) KATAKANA LETTER NO → SOLIDUS # →⼃→
4E3F ; 002F ; MA # ( 丿 → / ) CJK UNIFIED IDEOGRAPH-4E3F → SOLIDUS # →⼃→
2F03 ; 002F ; MA #* ( ⼃ → / ) KANGXI RADICAL SLASH → SOLIDUS #
@ -958,6 +977,8 @@ FE68 ; 005C ; MA #* ( ﹨ → \ ) SMALL REVERSE SOLIDUS → REVERSE SOLIDUS #
27CD ; 005C ; MA #* ( ⟍ → \ ) MATHEMATICAL FALLING DIAGONAL → REVERSE SOLIDUS #
29F5 ; 005C ; MA #* ( ⧵ → \ ) REVERSE SOLIDUS OPERATOR → REVERSE SOLIDUS #
29F9 ; 005C ; MA #* ( ⧹ → \ ) BIG REVERSE SOLIDUS → REVERSE SOLIDUS #
1D20F ; 005C ; MA #* ( 𝈏 → \ ) GREEK VOCAL NOTATION SYMBOL-16 → REVERSE SOLIDUS #
1D23B ; 005C ; MA #* ( 𝈻 → \ ) GREEK INSTRUMENTAL NOTATION SYMBOL-48 → REVERSE SOLIDUS # →𝈏→
31D4 ; 005C ; MA #* ( ㇔ → \ ) CJK STROKE D → REVERSE SOLIDUS # →⼂→
4E36 ; 005C ; MA # ( 丶 → \ ) CJK UNIFIED IDEOGRAPH-4E36 → REVERSE SOLIDUS # →⼂→
2F02 ; 005C ; MA #* ( ⼂ → \ ) KANGXI RADICAL DOT → REVERSE SOLIDUS #
@ -974,6 +995,8 @@ A778 ; 0026 ; MA # ( ꝸ → & ) LATIN SMALL LETTER UM → AMPERSAND #
111C7 ; 0970 ; MA #* ( 𑇇 → ॰ ) SHARADA ABBREVIATION SIGN → DEVANAGARI ABBREVIATION SIGN #
26AC ; 0970 ; MA #* ( ⚬ → ॰ ) MEDIUM SMALL WHITE CIRCLE → DEVANAGARI ABBREVIATION SIGN #
111DB ; A8FC ; MA #* ( 𑇛 → ꣼ ) SHARADA SIGN SIDDHAM → DEVANAGARI SIGN SIDDHAM #
17D9 ; 0E4F ; MA #* ( ៙ → ๏ ) KHMER SIGN PHNAEK MUAN → THAI CHARACTER FONGMAN #
17D5 ; 0E5A ; MA #* ( ៕ → ๚ ) KHMER SIGN BARIYOOSAN → THAI CHARACTER ANGKHANKHU #
@ -1001,6 +1024,8 @@ FFE3 ; 02C9 ; MA #* ( ￣ → ˉ ) FULLWIDTH MACRON → MODIFIER LETTER MACRON #
044A ; 02C9 0062 ; MA # ( ъ → ˉb ) CYRILLIC SMALL LETTER HARD SIGN → MODIFIER LETTER MACRON, LATIN SMALL LETTER B # →¯b→
A651 ; 02C9 0062 0069 ; MA # ( ꙑ → ˉbi ) CYRILLIC SMALL LETTER YERU WITH BACK YER → MODIFIER LETTER MACRON, LATIN SMALL LETTER B, LATIN SMALL LETTER I # →ъı→
0375 ; 02CF ; MA #* ( ͵ → ˏ ) GREEK LOWER NUMERAL SIGN → MODIFIER LETTER LOW ACUTE ACCENT #
02FB ; 02EA ; MA #* ( ˻ → ˪ ) MODIFIER LETTER BEGIN LOW TONE → MODIFIER LETTER YIN DEPARTING TONE MARK #
@ -1016,9 +1041,9 @@ A714 ; 02EB ; MA #* ( ꜔ → ˫ ) MODIFIER LETTER MID LEFT-STEM TONE BAR → MO
25CB ; 00B0 ; MA #* ( ○ → ° ) WHITE CIRCLE → DEGREE SIGN # →◦→→∘→
25E6 ; 00B0 ; MA #* ( ◦ → ° ) WHITE BULLET → DEGREE SIGN # →∘→
235C ; 00B0 0332 ; MA #* ( ⍜ → °̲ ) APL FUNCTIONAL SYMBOL CIRCLE UNDERBAR → DEGREE SIGN, COMBINING LOW LINE # →○̲→→∘̲→
235C ; 00B0 0332 ; MA #* ( ⍜ → °̲ ) APL FUNCTIONAL SYMBOL CIRCLE UNDERBAR → DEGREE SIGN, COMBINING LOW LINE # →○̲→
2364 ; 00B0 0308 ; MA #* ( ⍤ → °̈ ) APL FUNCTIONAL SYMBOL JOT DIAERESIS → DEGREE SIGN, COMBINING DIAERESIS # →◦̈→→∘̈→
2364 ; 00B0 0308 ; MA #* ( ⍤ → °̈ ) APL FUNCTIONAL SYMBOL JOT DIAERESIS → DEGREE SIGN, COMBINING DIAERESIS # →◦̈→
2103 ; 00B0 0043 ; MA #* ( ℃ → °C ) DEGREE CELSIUS → DEGREE SIGN, LATIN CAPITAL LETTER C #
@ -1040,6 +1065,8 @@ A714 ; 02EB ; MA #* ( ꜔ → ˫ ) MODIFIER LETTER MID LEFT-STEM TONE BAR → MO
24C5 ; 2117 ; MA #* ( Ⓟ → ℗ ) CIRCLED LATIN CAPITAL LETTER P → SOUND RECORDING COPYRIGHT #
1D21B ; 2144 ; MA #* ( 𝈛 → ⅄ ) GREEK VOCAL NOTATION SYMBOL-53 → TURNED SANS-SERIF CAPITAL Y #
2BEC ; 219E ; MA #* ( ⯬ → ↞ ) LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS → LEFTWARDS TWO HEADED ARROW #
2BED ; 219F ; MA #* ( ⯭ → ↟ ) UPWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS → UPWARDS TWO HEADED ARROW #
@ -1105,6 +1132,7 @@ A714 ; 02EB ; MA #* ( ꜔ → ˫ ) MODIFIER LETTER MID LEFT-STEM TONE BAR → MO
2039 ; 003C ; MA #* ( ‹ → < ) SINGLE LEFT-POINTING ANGLE QUOTATION MARK → LESS-THAN SIGN #
276E ; 003C ; MA #* ( ❮ → < ) HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT → LESS-THAN SIGN # →‹→
02C2 ; 003C ; MA #* ( ˂ → < ) MODIFIER LETTER LEFT ARROWHEAD → LESS-THAN SIGN #
1D236 ; 003C ; MA #* ( 𝈶 → < ) GREEK INSTRUMENTAL NOTATION SYMBOL-40 → LESS-THAN SIGN #
1438 ; 003C ; MA # ( ᐸ → < ) CANADIAN SYLLABICS PA → LESS-THAN SIGN #
16B2 ; 003C ; MA # ( ᚲ → < ) RUNIC LETTER KAUNA → LESS-THAN SIGN #
@ -1142,6 +1170,7 @@ A4FF ; 003D ; MA #* ( ꓿ → = ) LISU PUNCTUATION FULL STOP → EQUALS SIGN #
203A ; 003E ; MA #* ( › → > ) SINGLE RIGHT-POINTING ANGLE QUOTATION MARK → GREATER-THAN SIGN #
276F ; 003E ; MA #* ( ❯ → > ) HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT → GREATER-THAN SIGN # →›→
02C3 ; 003E ; MA #* ( ˃ → > ) MODIFIER LETTER RIGHT ARROWHEAD → GREATER-THAN SIGN #
1D237 ; 003E ; MA #* ( 𝈷 → > ) GREEK INSTRUMENTAL NOTATION SYMBOL-42 → GREATER-THAN SIGN #
1433 ; 003E ; MA # ( ᐳ → > ) CANADIAN SYLLABICS PO → GREATER-THAN SIGN #
1441 ; 003E 00B7 ; MA # ( ᑁ → >· ) CANADIAN SYLLABICS WEST-CREE PWO → GREATER-THAN SIGN, MIDDLE DOT # →ᐳᐧ→
@ -1160,8 +1189,8 @@ A4FF ; 003D ; MA #* ( ꓿ → = ) LISU PUNCTUATION FULL STOP → EQUALS SIGN #
2368 ; 007E 0308 ; MA #* ( ⍨ → ~̈ ) APL FUNCTIONAL SYMBOL TILDE DIAERESIS → TILDE, COMBINING DIAERESIS #
2E1E ; 007E 0307 ; MA #* ( ⸞ → ~̇ ) TILDE WITH DOT ABOVE → TILDE, COMBINING DOT ABOVE # →⩪→→∼̇→→⁓̇→
2A6A ; 007E 0307 ; MA #* ( ⩪ → ~̇ ) TILDE OPERATOR WITH DOT ABOVE → TILDE, COMBINING DOT ABOVE # →∼̇→→⁓̇→
2E1E ; 007E 0307 ; MA #* ( ⸞ → ~̇ ) TILDE WITH DOT ABOVE → TILDE, COMBINING DOT ABOVE # →⩪→→∼̇→
2A6A ; 007E 0307 ; MA #* ( ⩪ → ~̇ ) TILDE OPERATOR WITH DOT ABOVE → TILDE, COMBINING DOT ABOVE # →∼̇→
2E1F ; 007E 0323 ; MA #* ( ⸟ → ~̣ ) TILDE WITH DOT BELOW → TILDE, COMBINING DOT BELOW #
@ -1190,6 +1219,10 @@ A4FF ; 003D ; MA #* ( ꓿ → = ) LISU PUNCTUATION FULL STOP → EQUALS SIGN #
2A04 ; 228E ; MA #* ( ⨄ → ⊎ ) N-ARY UNION OPERATOR WITH PLUS → MULTISET UNION #
1D238 ; 228F ; MA #* ( 𝈸 → ⊏ ) GREEK INSTRUMENTAL NOTATION SYMBOL-43 → SQUARE IMAGE OF #
1D239 ; 2290 ; MA #* ( 𝈹 → ⊐ ) GREEK INSTRUMENTAL NOTATION SYMBOL-45 → SQUARE ORIGINAL OF #
2A05 ; 2293 ; MA #* ( ⨅ → ⊓ ) N-ARY SQUARE INTERSECTION OPERATOR → SQUARE CAP #
2A06 ; 2294 ; MA #* ( ⨆ → ⊔ ) N-ARY SQUARE UNION OPERATOR → SQUARE CUP #
@ -1281,6 +1314,7 @@ FFED ; 25AA ; MA #* ( ￭ → ▪ ) HALFWIDTH BLACK SQUARE → BLACK SMALL SQUAR
1F319 ; 263D ; MA #* ( 🌙 → ☽ ) CRESCENT MOON → FIRST QUARTER MOON #
1F318 ; 263E ; MA #* ( 🌘 → ☾ ) WANING CRESCENT MOON SYMBOL → LAST QUARTER MOON #
23FE ; 263E ; MA #* ( ⏾ → ☾ ) POWER SLEEP SYMBOL → LAST QUARTER MOON #
29D9 ; 299A ; MA #* ( ⧙ → ⦚ ) RIGHT WIGGLY FENCE → VERTICAL ZIGZAG LINE #
@ -1355,6 +1389,7 @@ A75A ; 0032 ; MA # ( Ꝛ → 2 ) LATIN CAPITAL LETTER R ROTUNDA → DIGIT TWO #
03E8 ; 0032 ; MA # ( Ϩ → 2 ) COPTIC CAPITAL LETTER HORI → DIGIT TWO # →Ƨ→
A644 ; 0032 ; MA # ( Ꙅ → 2 ) CYRILLIC CAPITAL LETTER REVERSED DZE → DIGIT TWO # →Ƨ→
14BF ; 0032 ; MA # ( ᒿ → 2 ) CANADIAN SYLLABICS SAYISI M → DIGIT TWO #
A6EF ; 0032 ; MA # ( ꛯ → 2 ) BAMUM LETTER KOGHOM → DIGIT TWO # →Ƨ→
A9CF ; 0662 ; MA # ( ꧏ → ‎٢‎ ) JAVANESE PANGRANGKEP → ARABIC-INDIC DIGIT TWO #
06F2 ; 0662 ; MA # ( ۲ → ‎٢‎ ) EXTENDED ARABIC-INDIC DIGIT TWO → ARABIC-INDIC DIGIT TWO #
@ -1415,6 +1450,7 @@ A9CF ; 0662 ; MA # ( ꧏ → ‎٢‎ ) JAVANESE PANGRANGKEP → ARABIC-INDIC DI
335A ; 0032 70B9 ; MA #* ( ㍚ → 2点 ) IDEOGRAPHIC TELEGRAPH SYMBOL FOR HOUR TWO → DIGIT TWO, CJK UNIFIED IDEOGRAPH-70B9 #
1D206 ; 0033 ; MA #* ( 𝈆 → 3 ) GREEK VOCAL NOTATION SYMBOL-7 → DIGIT THREE #
1D7D1 ; 0033 ; MA # ( 𝟑 → 3 ) MATHEMATICAL BOLD DIGIT THREE → DIGIT THREE #
1D7DB ; 0033 ; MA # ( 𝟛 → 3 ) MATHEMATICAL DOUBLE-STRUCK DIGIT THREE → DIGIT THREE #
1D7E5 ; 0033 ; MA # ( 𝟥 → 3 ) MATHEMATICAL SANS-SERIF DIGIT THREE → DIGIT THREE #
@ -1524,6 +1560,7 @@ A76A ; 0033 ; MA # ( Ꝫ → 3 ) LATIN CAPITAL LETTER ET → DIGIT THREE #
335E ; 0036 70B9 ; MA #* ( ㍞ → 6点 ) IDEOGRAPHIC TELEGRAPH SYMBOL FOR HOUR SIX → DIGIT SIX, CJK UNIFIED IDEOGRAPH-70B9 #
1D212 ; 0037 ; MA #* ( 𝈒 → 7 ) GREEK VOCAL NOTATION SYMBOL-19 → DIGIT SEVEN #
1D7D5 ; 0037 ; MA # ( 𝟕 → 7 ) MATHEMATICAL BOLD DIGIT SEVEN → DIGIT SEVEN #
1D7DF ; 0037 ; MA # ( 𝟟 → 7 ) MATHEMATICAL DOUBLE-STRUCK DIGIT SEVEN → DIGIT SEVEN #
1D7E9 ; 0037 ; MA # ( 𝟩 → 7 ) MATHEMATICAL SANS-SERIF DIGIT SEVEN → DIGIT SEVEN #
@ -1573,6 +1610,7 @@ A76A ; 0033 ; MA # ( Ꝫ → 3 ) LATIN CAPITAL LETTER ET → DIGIT THREE #
0A67 ; 0039 ; MA # ( ੧ → 9 ) GURMUKHI DIGIT ONE → DIGIT NINE #
0B68 ; 0039 ; MA # ( ୨ → 9 ) ORIYA DIGIT TWO → DIGIT NINE #
09ED ; 0039 ; MA # ( ৭ → 9 ) BENGALI DIGIT SEVEN → DIGIT NINE #
0D6D ; 0039 ; MA # ( ൭ → 9 ) MALAYALAM DIGIT SEVEN → DIGIT NINE #
1D7D7 ; 0039 ; MA # ( 𝟗 → 9 ) MATHEMATICAL BOLD DIGIT NINE → DIGIT NINE #
1D7E1 ; 0039 ; MA # ( 𝟡 → 9 ) MATHEMATICAL DOUBLE-STRUCK DIGIT NINE → DIGIT NINE #
1D7EB ; 0039 ; MA # ( 𝟫 → 9 ) MATHEMATICAL SANS-SERIF DIGIT NINE → DIGIT NINE #
@ -1700,6 +1738,7 @@ A73D ; 0061 0079 ; MA # ( ꜽ → ay ) LATIN SMALL LETTER AY → LATIN SMALL LET
A73C ; 0041 0059 ; MA # ( Ꜽ → AY ) LATIN CAPITAL LETTER AY → LATIN CAPITAL LETTER A, LATIN CAPITAL LETTER Y #
2200 ; 2C6F ; MA #* ( ∀ → Ɐ ) FOR ALL → LATIN CAPITAL LETTER TURNED A #
1D217 ; 2C6F ; MA #* ( 𝈗 → Ɐ ) GREEK VOCAL NOTATION SYMBOL-24 → LATIN CAPITAL LETTER TURNED A #
15C4 ; 2C6F ; MA # ( ᗄ → Ɐ ) CANADIAN SYLLABICS CARRIER GHU → LATIN CAPITAL LETTER TURNED A # →∀→
A4EF ; 2C6F ; MA # ( ꓯ → Ɐ ) LISU LETTER AE → LATIN CAPITAL LETTER TURNED A #
@ -1737,6 +1776,7 @@ FF22 ; 0042 ; MA # ( Ｂ → B ) FULLWIDTH LATIN CAPITAL LETTER B → LATIN CAPI
1D609 ; 0042 ; MA # ( 𝘉 → B ) MATHEMATICAL SANS-SERIF ITALIC CAPITAL B → LATIN CAPITAL LETTER B #
1D63D ; 0042 ; MA # ( 𝘽 → B ) MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL B → LATIN CAPITAL LETTER B #
1D671 ; 0042 ; MA # ( 𝙱 → B ) MATHEMATICAL MONOSPACE CAPITAL B → LATIN CAPITAL LETTER B #
A7B4 ; 0042 ; MA # ( Ꞵ → B ) LATIN CAPITAL LETTER BETA → LATIN CAPITAL LETTER B #
0392 ; 0042 ; MA # ( Β → B ) GREEK CAPITAL LETTER BETA → LATIN CAPITAL LETTER B #
1D6A9 ; 0042 ; MA # ( 𝚩 → B ) MATHEMATICAL BOLD CAPITAL BETA → LATIN CAPITAL LETTER B # →Β→
1D6E3 ; 0042 ; MA # ( 𝛣 → B ) MATHEMATICAL ITALIC CAPITAL BETA → LATIN CAPITAL LETTER B # →Β→
@ -1750,7 +1790,6 @@ A4D0 ; 0042 ; MA # ( ꓐ → B ) LISU LETTER BA → LATIN CAPITAL LETTER B #
10282 ; 0042 ; MA # ( 𐊂 → B ) LYCIAN LETTER B → LATIN CAPITAL LETTER B #
102A1 ; 0042 ; MA # ( 𐊡 → B ) CARIAN LETTER P2 → LATIN CAPITAL LETTER B #
10301 ; 0042 ; MA # ( 𐌁 → B ) OLD ITALIC LETTER BE → LATIN CAPITAL LETTER B #
A7B4 ; 0042 ; MA # ( Ꞵ → B ) LATIN CAPITAL LETTER BETA → LATIN CAPITAL LETTER B #
0253 ; 0062 0314 ; MA # ( ɓ → b̔ ) LATIN SMALL LETTER B WITH HOOK → LATIN SMALL LETTER B, COMBINING REVERSED COMMA ABOVE #
@ -2021,8 +2060,13 @@ A4F1 ; 018E ; MA # ( ꓱ → Ǝ ) LISU LETTER EU → LATIN CAPITAL LETTER REVERS
1D14 ; 01DD 006F ; MA # ( ᴔ → ǝo ) LATIN SMALL LETTER TURNED OE → LATIN SMALL LETTER TURNED E, LATIN SMALL LETTER O # →əo→
AB41 ; 01DD 006F 0338 ; MA # ( ꭁ → ǝo̸ ) LATIN SMALL LETTER TURNED OE WITH STROKE → LATIN SMALL LETTER TURNED E, LATIN SMALL LETTER O, COMBINING LONG SOLIDUS OVERLAY # →ǝø→
AB42 ; 01DD 006F 0335 ; MA # ( ꭂ → ǝo̵ ) LATIN SMALL LETTER TURNED OE WITH HORIZONTAL STROKE → LATIN SMALL LETTER TURNED E, LATIN SMALL LETTER O, COMBINING SHORT STROKE OVERLAY # →ǝɵ→
04D8 ; 018F ; MA # ( Ә → Ə ) CYRILLIC CAPITAL LETTER SCHWA → LATIN CAPITAL LETTER SCHWA #
1D221 ; 0190 ; MA #* ( 𝈡 → Ɛ ) GREEK INSTRUMENTAL NOTATION SYMBOL-7 → LATIN CAPITAL LETTER OPEN E #
2107 ; 0190 ; MA # ( ℇ → Ɛ ) EULER CONSTANT → LATIN CAPITAL LETTER OPEN E #
0510 ; 0190 ; MA # ( Ԑ → Ɛ ) CYRILLIC CAPITAL LETTER REVERSED ZE → LATIN CAPITAL LETTER OPEN E #
13CB ; 0190 ; MA # ( Ꮛ → Ɛ ) CHEROKEE LETTER QUV → LATIN CAPITAL LETTER OPEN E #
@ -2035,9 +2079,9 @@ A4F1 ; 018E ; MA # ( ꓱ → Ǝ ) LISU LETTER EU → LATIN CAPITAL LETTER REVERS
0499 ; 025C 0326 ; MA # ( ҙ → ɜ̦ ) CYRILLIC SMALL LETTER ZE WITH DESCENDER → LATIN SMALL LETTER REVERSED OPEN E, COMBINING COMMA BELOW # →з̡→
A79D ; 025E ; MA # ( ꞝ → ɞ ) LATIN SMALL LETTER VOLAPUK OE → LATIN SMALL LETTER CLOSED REVERSED OPEN E #
10442 ; 025E ; MA # ( 𐑂 → ɞ ) DESERET SMALL LETTER VEE → LATIN SMALL LETTER CLOSED REVERSED OPEN E #
A79D ; 029A ; MA # ( ꞝ → ʚ ) LATIN SMALL LETTER VOLAPUK OE → LATIN SMALL LETTER CLOSED OPEN E #
1042A ; 029A ; MA # ( 𐐪 → ʚ ) DESERET SMALL LETTER LONG A → LATIN SMALL LETTER CLOSED OPEN E #
1D41F ; 0066 ; MA # ( 𝐟 → f ) MATHEMATICAL BOLD SMALL F → LATIN SMALL LETTER F #
@ -2059,6 +2103,7 @@ A799 ; 0066 ; MA # ( ꞙ → f ) LATIN SMALL LETTER F WITH STROKE → LATIN SMAL
1E9D ; 0066 ; MA # ( ẝ → f ) LATIN SMALL LETTER LONG S WITH HIGH STROKE → LATIN SMALL LETTER F #
0584 ; 0066 ; MA # ( ք → f ) ARMENIAN SMALL LETTER KEH → LATIN SMALL LETTER F #
1D213 ; 0046 ; MA #* ( 𝈓 → F ) GREEK VOCAL NOTATION SYMBOL-20 → LATIN CAPITAL LETTER F # →Ϝ→
2131 ; 0046 ; MA # ( ℱ → F ) SCRIPT CAPITAL F → LATIN CAPITAL LETTER F #
1D405 ; 0046 ; MA # ( 𝐅 → F ) MATHEMATICAL BOLD CAPITAL F → LATIN CAPITAL LETTER F #
1D439 ; 0046 ; MA # ( 𝐹 → F ) MATHEMATICAL ITALIC CAPITAL F → LATIN CAPITAL LETTER F #
@ -2106,6 +2151,7 @@ FB02 ; 0066 006C ; MA # ( fl → fl ) LATIN SMALL LIGATURE FL → LATIN SMALL L
15B5 ; 2132 ; MA # ( ᖵ → Ⅎ ) CANADIAN SYLLABICS BLACKFOOT WI → TURNED CAPITAL F #
A4DE ; 2132 ; MA # ( ꓞ → Ⅎ ) LISU LETTER TSHA → TURNED CAPITAL F #
1D230 ; A7FB ; MA #* ( 𝈰 → ꟻ ) GREEK INSTRUMENTAL NOTATION SYMBOL-30 → LATIN EPIGRAPHIC LETTER REVERSED F #
15B7 ; A7FB ; MA # ( ᖷ → ꟻ ) CANADIAN SYLLABICS BLACKFOOT WA → LATIN EPIGRAPHIC LETTER REVERSED F #
FF47 ; 0067 ; MA # ( ｇ → g ) FULLWIDTH LATIN SMALL LETTER G → LATIN SMALL LETTER G # →ɡ→
@ -2238,6 +2284,7 @@ A695 ; 0068 0314 ; MA # ( ꚕ → h̔ ) CYRILLIC SMALL LETTER HWE → LATIN SMAL
0370 ; 2C75 ; MA # ( Ͱ → Ⱶ ) GREEK CAPITAL LETTER HETA → LATIN CAPITAL LETTER HALF H # →Ꮀ→
13A8 ; 2C75 ; MA # ( Ꭸ → Ⱶ ) CHEROKEE LETTER GE → LATIN CAPITAL LETTER HALF H # →Ͱ→→Ꮀ→
13B0 ; 2C75 ; MA # ( Ꮀ → Ⱶ ) CHEROKEE LETTER HO → LATIN CAPITAL LETTER HALF H #
A6B1 ; 2C75 ; MA # ( ꚱ → Ⱶ ) BAMUM LETTER NDAA → LATIN CAPITAL LETTER HALF H # →Ͱ→→Ꮀ→
A795 ; A727 ; MA # ( ꞕ → ꜧ ) LATIN SMALL LETTER H WITH PALATAL HOOK → LATIN SMALL LETTER HENG #
@ -2332,12 +2379,12 @@ FF2A ; 004A ; MA # ( Ｊ → J ) FULLWIDTH LATIN CAPITAL LETTER J → LATIN CAPI
1D611 ; 004A ; MA # ( 𝘑 → J ) MATHEMATICAL SANS-SERIF ITALIC CAPITAL J → LATIN CAPITAL LETTER J #
1D645 ; 004A ; MA # ( 𝙅 → J ) MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL J → LATIN CAPITAL LETTER J #
1D679 ; 004A ; MA # ( 𝙹 → J ) MATHEMATICAL MONOSPACE CAPITAL J → LATIN CAPITAL LETTER J #
A7B2 ; 004A ; MA # ( Ʝ → J ) LATIN CAPITAL LETTER J WITH CROSSED-TAIL → LATIN CAPITAL LETTER J #
037F ; 004A ; MA # ( Ϳ → J ) GREEK CAPITAL LETTER YOT → LATIN CAPITAL LETTER J #
0408 ; 004A ; MA # ( Ј → J ) CYRILLIC CAPITAL LETTER JE → LATIN CAPITAL LETTER J #
13AB ; 004A ; MA # ( Ꭻ → J ) CHEROKEE LETTER GU → LATIN CAPITAL LETTER J #
148D ; 004A ; MA # ( ᒍ → J ) CANADIAN SYLLABICS CO → LATIN CAPITAL LETTER J #
A4D9 ; 004A ; MA # ( ꓙ → J ) LISU LETTER JA → LATIN CAPITAL LETTER J #
A7B2 ; 004A ; MA # ( Ʝ → J ) LATIN CAPITAL LETTER J WITH CROSSED-TAIL → LATIN CAPITAL LETTER J #
0249 ; 006A 0335 ; MA # ( ɉ → j̵ ) LATIN SMALL LETTER J WITH STROKE → LATIN SMALL LETTER J, COMBINING SHORT STROKE OVERLAY #
@ -2491,7 +2538,9 @@ FE8D ; 006C ; MA # ( ‎ﺍ‎ → l ) ARABIC LETTER ALEF ISOLATED FORM → LATI
A4F2 ; 006C ; MA # ( ꓲ → l ) LISU LETTER I → LATIN SMALL LETTER L # →I→
1028A ; 006C ; MA # ( 𐊊 → l ) LYCIAN LETTER J → LATIN SMALL LETTER L # →I→
10309 ; 006C ; MA # ( 𐌉 → l ) OLD ITALIC LETTER I → LATIN SMALL LETTER L # →I→
23FD ; 006C ; MA #* ( ⏽ → l ) POWER ON SYMBOL → LATIN SMALL LETTER L # →I→
1D22A ; 004C ; MA #* ( 𝈪 → L ) GREEK INSTRUMENTAL NOTATION SYMBOL-23 → LATIN CAPITAL LETTER L #
216C ; 004C ; MA # ( Ⅼ → L ) ROMAN NUMERAL FIFTY → LATIN CAPITAL LETTER L #
2112 ; 004C ; MA # ( ℒ → L ) SCRIPT CAPITAL L → LATIN CAPITAL LETTER L #
1D40B ; 004C ; MA # ( 𝐋 → L ) MATHEMATICAL BOLD CAPITAL L → LATIN CAPITAL LETTER L #
@ -2848,6 +2897,7 @@ FBA9 ; 006F ; MA # ( ‎ﮩ‎ → o ) ARABIC LETTER HEH GOAL MEDIAL FORM → LA
FBA7 ; 006F ; MA # ( ‎ﮧ‎ → o ) ARABIC LETTER HEH GOAL FINAL FORM → LATIN SMALL LETTER O # →‎ہ‎→→‎ه‎→
FBA6 ; 006F ; MA # ( ‎ﮦ‎ → o ) ARABIC LETTER HEH GOAL ISOLATED FORM → LATIN SMALL LETTER O # →‎ه‎→
06D5 ; 006F ; MA # ( ‎ە‎ → o ) ARABIC LETTER AE → LATIN SMALL LETTER O # →‎ه‎→
0D20 ; 006F ; MA # ( ഠ → o ) MALAYALAM LETTER TTHA → LATIN SMALL LETTER O #
101D ; 006F ; MA # ( ဝ → o ) MYANMAR LETTER WA → LATIN SMALL LETTER O #
118C8 ; 006F ; MA # ( 𑣈 → o ) WARANG CITI SMALL LETTER E → LATIN SMALL LETTER O #
118D7 ; 006F ; MA # ( 𑣗 → o ) WARANG CITI SMALL LETTER BU → LATIN SMALL LETTER O #
@ -2889,8 +2939,8 @@ FF2F ; 004F ; MA # ( Ｏ → O ) FULLWIDTH LATIN CAPITAL LETTER O → LATIN CAPI
041E ; 004F ; MA # ( О → O ) CYRILLIC CAPITAL LETTER O → LATIN CAPITAL LETTER O #
0555 ; 004F ; MA # ( Օ → O ) ARMENIAN CAPITAL LETTER OH → LATIN CAPITAL LETTER O #
2D54 ; 004F ; MA # ( ⵔ → O ) TIFINAGH LETTER YAR → LATIN CAPITAL LETTER O #
12D0 ; 004F ; MA # ( ዐ → O ) ETHIOPIC SYLLABLE PHARYNGEAL A → LATIN CAPITAL LETTER O # →Օ→
0B20 ; 004F ; MA # ( ଠ → O ) ORIYA LETTER TTHA → LATIN CAPITAL LETTER O # →୦→→0→
0D20 ; 004F ; MA # ( ഠ → O ) MALAYALAM LETTER TTHA → LATIN CAPITAL LETTER O #
A4F3 ; 004F ; MA # ( ꓳ → O ) LISU LETTER O → LATIN CAPITAL LETTER O #
118B5 ; 004F ; MA # ( 𑢵 → O ) WARANG CITI CAPITAL LETTER AT → LATIN CAPITAL LETTER O #
10292 ; 004F ; MA # ( 𐊒 → O ) LYCIAN LETTER U → LATIN CAPITAL LETTER O #
@ -2923,6 +2973,7 @@ A74B ; 006F 0335 ; MA # ( ꝋ → o̵ ) LATIN SMALL LETTER O WITH LONG STROKE OV
2296 ; 004F 0335 ; MA #* ( ⊖ → O̵ ) CIRCLED MINUS → LATIN CAPITAL LETTER O, COMBINING SHORT STROKE OVERLAY # →θ→→Ꮎ→
229D ; 004F 0335 ; MA #* ( ⊝ → O̵ ) CIRCLED DASH → LATIN CAPITAL LETTER O, COMBINING SHORT STROKE OVERLAY # →⊖→→θ→→Ꮎ→
236C ; 004F 0335 ; MA #* ( ⍬ → O̵ ) APL FUNCTIONAL SYMBOL ZILDE → LATIN CAPITAL LETTER O, COMBINING SHORT STROKE OVERLAY # →θ→→Ꮎ→
1D21A ; 004F 0335 ; MA #* ( 𝈚 → O̵ ) GREEK VOCAL NOTATION SYMBOL-52 → LATIN CAPITAL LETTER O, COMBINING SHORT STROKE OVERLAY # →Ꝋ→→O̶→
1F714 ; 004F 0335 ; MA #* ( 🜔 → O̵ ) ALCHEMICAL SYMBOL FOR SALT → LATIN CAPITAL LETTER O, COMBINING SHORT STROKE OVERLAY # →Ɵ→→O̶→
019F ; 004F 0335 ; MA # ( Ɵ → O̵ ) LATIN CAPITAL LETTER O WITH MIDDLE TILDE → LATIN CAPITAL LETTER O, COMBINING SHORT STROKE OVERLAY # →O̶→
A74A ; 004F 0335 ; MA # ( Ꝋ → O̵ ) LATIN CAPITAL LETTER O WITH LONG STROKE OVERLAY → LATIN CAPITAL LETTER O, COMBINING SHORT STROKE OVERLAY # →O̶→
@ -3003,7 +3054,7 @@ FD94 ; 006F 0645 0645 ; MA # ( ‎ﶔ‎ → ‎oمم‎ ) ARABIC LIGATURE HEH W
FC53 ; 006F 0649 ; MA # ( ‎ﱓ‎ → ‎oى‎ ) ARABIC LIGATURE HEH WITH ALEF MAKSURA ISOLATED FORM → LATIN SMALL LETTER O, ARABIC LETTER ALEF MAKSURA # →‎هى‎→
FC54 ; 006F 0649 ; MA # ( ‎ﱔ‎ → ‎oى‎ ) ARABIC LIGATURE HEH WITH YEH ISOLATED FORM → LATIN SMALL LETTER O, ARABIC LETTER ALEF MAKSURA # →‎هي‎→
0D5F ; 006F 0D30 006F ; MA # ( ൟ → oരo ) MALAYALAM LETTER ARCHAIC II → LATIN SMALL LETTER O, MALAYALAM LETTER RA, LATIN SMALL LETTER O # →൦ര൦→
0D5F ; 006F 0D30 006F ; MA # ( ൟ → oരo ) MALAYALAM LETTER ARCHAIC II → LATIN SMALL LETTER O, MALAYALAM LETTER RA, LATIN SMALL LETTER O # →ംരം→
1010 ; 006F 102C ; MA # ( တ → oာ ) MYANMAR LETTER TA → LATIN SMALL LETTER O, MYANMAR VOWEL SIGN AA # →ဝာ→
@ -3019,6 +3070,8 @@ FC54 ; 006F 0649 ; MA # ( ‎ﱔ‎ → ‎oى‎ ) ARABIC LIGATURE HEH WITH YEH
A4DB ; 0186 ; MA # ( ꓛ → Ɔ ) LISU LETTER CHA → LATIN CAPITAL LETTER OPEN O #
10423 ; 0186 ; MA # ( 𐐣 → Ɔ ) DESERET CAPITAL LETTER EM → LATIN CAPITAL LETTER OPEN O #
AB3F ; 0254 0338 ; MA # ( ꬿ → ɔ̸ ) LATIN SMALL LETTER OPEN O WITH STROKE → LATIN SMALL LETTER OPEN O, COMBINING LONG SOLIDUS OVERLAY #
1043F ; 0277 ; MA # ( 𐐿 → ɷ ) DESERET SMALL LETTER KAY → LATIN SMALL LETTER CLOSED OMEGA #
2374 ; 0070 ; MA #* ( ⍴ → p ) APL FUNCTIONAL SYMBOL RHO → LATIN SMALL LETTER P # →ρ→
@ -3160,6 +3213,7 @@ AB48 ; 0072 ; MA # ( ꭈ → r ) LATIN SMALL LETTER DOUBLE R → LATIN SMALL LET
2C85 ; 0072 ; MA # ( ⲅ → r ) COPTIC SMALL LETTER GAMMA → LATIN SMALL LETTER R # →г→
0433 ; 0072 ; MA # ( г → r ) CYRILLIC SMALL LETTER GHE → LATIN SMALL LETTER R #
1D216 ; 0052 ; MA #* ( 𝈖 → R ) GREEK VOCAL NOTATION SYMBOL-23 → LATIN CAPITAL LETTER R #
211B ; 0052 ; MA # ( ℛ → R ) SCRIPT CAPITAL R → LATIN CAPITAL LETTER R #
211C ; 0052 ; MA # ( ℜ → R ) BLACK-LETTER CAPITAL R → LATIN CAPITAL LETTER R #
211D ; 0052 ; MA # ( ℝ → R ) DOUBLE-STRUCK CAPITAL R → LATIN CAPITAL LETTER R #
@ -3273,6 +3327,7 @@ A4E2 ; 0053 ; MA # ( ꓢ → S ) LISU LETTER SA → LATIN CAPITAL LETTER S #
1D74 ; 0073 0334 ; MA # ( ᵴ → s̴ ) LATIN SMALL LETTER S WITH MIDDLE TILDE → LATIN SMALL LETTER S, COMBINING TILDE OVERLAY #
A7B5 ; 00DF ; MA # ( ꞵ → ß ) LATIN SMALL LETTER BETA → LATIN SMALL LETTER SHARP S # →β→
03B2 ; 00DF ; MA # ( β → ß ) GREEK SMALL LETTER BETA → LATIN SMALL LETTER SHARP S #
03D0 ; 00DF ; MA # ( ϐ → ß ) GREEK BETA SYMBOL → LATIN SMALL LETTER SHARP S # →β→
1D6C3 ; 00DF ; MA # ( 𝛃 → ß ) MATHEMATICAL BOLD SMALL BETA → LATIN SMALL LETTER SHARP S # →β→
@ -3281,7 +3336,6 @@ A4E2 ; 0053 ; MA # ( ꓢ → S ) LISU LETTER SA → LATIN CAPITAL LETTER S #
1D771 ; 00DF ; MA # ( 𝝱 → ß ) MATHEMATICAL SANS-SERIF BOLD SMALL BETA → LATIN SMALL LETTER SHARP S # →β→
1D7AB ; 00DF ; MA # ( 𝞫 → ß ) MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL BETA → LATIN SMALL LETTER SHARP S # →β→
13F0 ; 00DF ; MA # ( Ᏸ → ß ) CHEROKEE LETTER YE → LATIN SMALL LETTER SHARP S # →β→
A7B5 ; 00DF ; MA # ( ꞵ → ß ) LATIN SMALL LETTER BETA → LATIN SMALL LETTER SHARP S # →β→
1F75C ; 0073 0073 0073 ; MA #* ( 🝜 → sss ) ALCHEMICAL SYMBOL FOR STRATUM SUPER STRATUM → LATIN SMALL LETTER S, LATIN SMALL LETTER S, LATIN SMALL LETTER S #
@ -3446,6 +3500,7 @@ AB52 ; 0075 ; MA # ( ꭒ → u ) LATIN SMALL LETTER U WITH LEFT HOOK → LATIN S
1D650 ; 0055 ; MA # ( 𝙐 → U ) MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL U → LATIN CAPITAL LETTER U #
1D684 ; 0055 ; MA # ( 𝚄 → U ) MATHEMATICAL MONOSPACE CAPITAL U → LATIN CAPITAL LETTER U #
054D ; 0055 ; MA # ( Ս → U ) ARMENIAN CAPITAL LETTER SEH → LATIN CAPITAL LETTER U #
1200 ; 0055 ; MA # ( ሀ → U ) ETHIOPIC SYLLABLE HA → LATIN CAPITAL LETTER U # →Ս→
144C ; 0055 ; MA # ( ᑌ → U ) CANADIAN SYLLABICS TE → LATIN CAPITAL LETTER U #
A4F4 ; 0055 ; MA # ( ꓴ → U ) LISU LETTER U → LATIN CAPITAL LETTER U #
118B8 ; 0055 ; MA # ( 𑢸 → U ) WARANG CITI CAPITAL LETTER PU → LATIN CAPITAL LETTER U #
@ -3466,6 +3521,7 @@ A4F4 ; 0055 ; MA # ( ꓴ → U ) LISU LETTER U → LATIN CAPITAL LETTER U #
1D6B ; 0075 0065 ; MA # ( ᵫ → ue ) LATIN SMALL LETTER UE → LATIN SMALL LETTER U, LATIN SMALL LETTER E #
057A ; 0270 ; MA # ( պ → ɰ ) ARMENIAN SMALL LETTER PEH → LATIN SMALL LETTER TURNED M WITH LONG LEG #
1223 ; 0270 ; MA # ( ሣ → ɰ ) ETHIOPIC SYLLABLE SZAA → LATIN SMALL LETTER TURNED M WITH LONG LEG # →պ→
2127 ; 01B1 ; MA #* ( ℧ → Ʊ ) INVERTED OHM SIGN → LATIN CAPITAL LETTER UPSILON #
162E ; 01B1 ; MA # ( ᘮ → Ʊ ) CANADIAN SYLLABICS CARRIER LHU → LATIN CAPITAL LETTER UPSILON # →℧→
@ -3501,6 +3557,7 @@ FF56 ; 0076 ; MA # ( ｖ → v ) FULLWIDTH LATIN SMALL LETTER V → LATIN SMALL
05D8 ; 0076 ; MA # ( ‎ט‎ → v ) HEBREW LETTER TET → LATIN SMALL LETTER V #
118C0 ; 0076 ; MA # ( 𑣀 → v ) WARANG CITI SMALL LETTER NGAA → LATIN SMALL LETTER V #
1D20D ; 0056 ; MA #* ( 𝈍 → V ) GREEK VOCAL NOTATION SYMBOL-14 → LATIN CAPITAL LETTER V #
0667 ; 0056 ; MA # ( ‎٧‎ → V ) ARABIC-INDIC DIGIT SEVEN → LATIN CAPITAL LETTER V #
06F7 ; 0056 ; MA # ( ۷ → V ) EXTENDED ARABIC-INDIC DIGIT SEVEN → LATIN CAPITAL LETTER V # →‎٧‎→
2164 ; 0056 ; MA # ( Ⅴ → V ) ROMAN NUMERAL FIVE → LATIN CAPITAL LETTER V #
@ -3521,6 +3578,7 @@ FF56 ; 0076 ; MA # ( ｖ → v ) FULLWIDTH LATIN SMALL LETTER V → LATIN SMALL
2D38 ; 0056 ; MA # ( ⴸ → V ) TIFINAGH LETTER YADH → LATIN CAPITAL LETTER V #
13D9 ; 0056 ; MA # ( Ꮩ → V ) CHEROKEE LETTER DO → LATIN CAPITAL LETTER V #
142F ; 0056 ; MA # ( ᐯ → V ) CANADIAN SYLLABICS PE → LATIN CAPITAL LETTER V #
A6DF ; 0056 ; MA # ( ꛟ → V ) BAMUM LETTER KO → LATIN CAPITAL LETTER V #
A4E6 ; 0056 ; MA # ( ꓦ → V ) LISU LETTER HA → LATIN CAPITAL LETTER V #
118A0 ; 0056 ; MA # ( 𑢠 → V ) WARANG CITI CAPITAL LETTER NGAA → LATIN CAPITAL LETTER V #
1051D ; 0056 ; MA # ( 𐔝 → V ) ELBASAN LETTER TE → LATIN CAPITAL LETTER V #
@ -3565,9 +3623,9 @@ A4E6 ; 0056 ; MA # ( ꓦ → V ) LISU LETTER HA → LATIN CAPITAL LETTER V #
1170E ; 0076 0076 ; MA # ( 𑜎 → vv ) AHOM LETTER LA → LATIN SMALL LETTER V, LATIN SMALL LETTER V # →w→
1170F ; 0076 0076 ; MA # ( 𑜏 → vv ) AHOM LETTER SA → LATIN SMALL LETTER V, LATIN SMALL LETTER V # →w→
114C5 ; 0076 0076 0307 ; MA # ( 𑓅 → vv̇ ) TIRHUTA GVANG → LATIN SMALL LETTER V, LATIN SMALL LETTER V, COMBINING DOT ABOVE # →ẇ→
047D ; 0076 0076 0486 0487 ; MA # ( ѽ → vv҆҇ ) CYRILLIC SMALL LETTER OMEGA WITH TITLO → LATIN SMALL LETTER V, LATIN SMALL LETTER V, COMBINING CYRILLIC PSILI PNEUMATA, COMBINING CYRILLIC POKRYTIE # →ѡ҆҇→
047D ; 0076 0076 0483 ; MA # ( ѽ → vv҃ ) CYRILLIC SMALL LETTER OMEGA WITH TITLO → LATIN SMALL LETTER V, LATIN SMALL LETTER V, COMBINING CYRILLIC TITLO # →ѡ҃→
114C5 ; 0076 0076 0307 ; MA # ( 𑓅 → vv̇ ) TIRHUTA GVANG → LATIN SMALL LETTER V, LATIN SMALL LETTER V, COMBINING DOT ABOVE # →ẇ→
A761 ; 0076 0079 ; MA # ( ꝡ → vy ) LATIN SMALL LETTER VY → LATIN SMALL LETTER V, LATIN SMALL LETTER Y #
@ -3584,6 +3642,7 @@ A761 ; 0076 0079 ; MA # ( ꝡ → vy ) LATIN SMALL LETTER VY → LATIN SMALL LET
041B ; 0245 ; MA # ( Л → Ʌ ) CYRILLIC CAPITAL LETTER EL → LATIN CAPITAL LETTER TURNED V # →Λ→
2D37 ; 0245 ; MA # ( ⴷ → Ʌ ) TIFINAGH LETTER YAD → LATIN CAPITAL LETTER TURNED V #
1431 ; 0245 ; MA # ( ᐱ → Ʌ ) CANADIAN SYLLABICS PI → LATIN CAPITAL LETTER TURNED V #
A6CE ; 0245 ; MA # ( ꛎ → Ʌ ) BAMUM LETTER MI → LATIN CAPITAL LETTER TURNED V # →Λ→
A4E5 ; 0245 ; MA # ( ꓥ → Ʌ ) LISU LETTER NGA → LATIN CAPITAL LETTER TURNED V #
1028D ; 0245 ; MA # ( 𐊍 → Ʌ ) LYCIAN LETTER L → LATIN CAPITAL LETTER TURNED V # →Λ→
@ -3656,6 +3715,7 @@ FF38 ; 0058 ; MA # ( Ｘ → X ) FULLWIDTH LATIN CAPITAL LETTER X → LATIN CAPI
1D61F ; 0058 ; MA # ( 𝘟 → X ) MATHEMATICAL SANS-SERIF ITALIC CAPITAL X → LATIN CAPITAL LETTER X #
1D653 ; 0058 ; MA # ( 𝙓 → X ) MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL X → LATIN CAPITAL LETTER X #
1D687 ; 0058 ; MA # ( 𝚇 → X ) MATHEMATICAL MONOSPACE CAPITAL X → LATIN CAPITAL LETTER X #
A7B3 ; 0058 ; MA # ( Ꭓ → X ) LATIN CAPITAL LETTER CHI → LATIN CAPITAL LETTER X #
03A7 ; 0058 ; MA # ( Χ → X ) GREEK CAPITAL LETTER CHI → LATIN CAPITAL LETTER X #
1D6BE ; 0058 ; MA # ( 𝚾 → X ) MATHEMATICAL BOLD CAPITAL CHI → LATIN CAPITAL LETTER X # →Χ→
1D6F8 ; 0058 ; MA # ( 𝛸 → X ) MATHEMATICAL ITALIC CAPITAL CHI → LATIN CAPITAL LETTER X # →Χ→
@ -3671,7 +3731,6 @@ A4EB ; 0058 ; MA # ( ꓫ → X ) LISU LETTER SHA → LATIN CAPITAL LETTER X #
102B4 ; 0058 ; MA # ( 𐊴 → X ) CARIAN LETTER X → LATIN CAPITAL LETTER X #
10317 ; 0058 ; MA # ( 𐌗 → X ) OLD ITALIC LETTER EKS → LATIN CAPITAL LETTER X #
10527 ; 0058 ; MA # ( 𐔧 → X ) ELBASAN LETTER KHE → LATIN CAPITAL LETTER X #
A7B3 ; 0058 ; MA # ( Ꭓ → X ) LATIN CAPITAL LETTER CHI → LATIN CAPITAL LETTER X #
2A30 ; 0078 0307 ; MA #* ( ⨰ → ẋ ) MULTIPLICATION SIGN WITH DOT ABOVE → LATIN SMALL LETTER X, COMBINING DOT ABOVE # →×̇→
@ -3819,6 +3878,8 @@ A4DC ; 005A ; MA # ( ꓜ → Z ) LISU LETTER DZA → LATIN CAPITAL LETTER Z #
03F7 ; 00DE ; MA # ( Ϸ → Þ ) GREEK CAPITAL LETTER SHO → LATIN CAPITAL LETTER THORN #
2079 ; A770 ; MA #* ( ⁹ → ꝰ ) SUPERSCRIPT NINE → MODIFIER LETTER US #
1D24 ; 01A8 ; MA # ( ᴤ → ƨ ) LATIN LETTER VOICED LARYNGEAL SPIRANT → LATIN SMALL LETTER TONE TWO #
03E9 ; 01A8 ; MA # ( ϩ → ƨ ) COPTIC SMALL LETTER HORI → LATIN SMALL LETTER TONE TWO #
A645 ; 01A8 ; MA # ( ꙅ → ƨ ) CYRILLIC SMALL LETTER REVERSED DZE → LATIN SMALL LETTER TONE TWO #
@ -3829,6 +3890,8 @@ A645 ; 01A8 ; MA # ( ꙅ → ƨ ) CYRILLIC SMALL LETTER REVERSED DZE → LATIN S
02E4 ; 02C1 ; MA # ( ˤ → ˁ ) MODIFIER LETTER SMALL REVERSED GLOTTAL STOP → MODIFIER LETTER REVERSED GLOTTAL STOP #
A6CD ; 02A1 ; MA # ( ꛍ → ʡ ) BAMUM LETTER LU → LATIN LETTER GLOTTAL STOP WITH STROKE #
2299 ; 0298 ; MA #* ( ⊙ → ʘ ) CIRCLED DOT OPERATOR → LATIN LETTER BILABIAL CLICK #
2609 ; 0298 ; MA #* ( ☉ → ʘ ) SUN → LATIN LETTER BILABIAL CLICK # →⊙→
2A00 ; 0298 ; MA #* ( ⨀ → ʘ ) N-ARY CIRCLED DOT OPERATOR → LATIN LETTER BILABIAL CLICK # →⊙→
@ -3917,6 +3980,7 @@ A668 ; 0298 ; MA # ( Ꙩ → ʘ ) CYRILLIC CAPITAL LETTER MONOCULAR O → LATIN
1D79F ; 03A0 ; MA # ( 𝞟 → Π ) MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL PI → GREEK CAPITAL LETTER PI #
2CA0 ; 03A0 ; MA # ( Ⲡ → Π ) COPTIC CAPITAL LETTER PI → GREEK CAPITAL LETTER PI #
041F ; 03A0 ; MA # ( П → Π ) CYRILLIC CAPITAL LETTER PE → GREEK CAPITAL LETTER PI #
A6DB ; 03A0 ; MA # ( ꛛ → Π ) BAMUM LETTER NA → GREEK CAPITAL LETTER PI #
102AD ; 03D8 ; MA # ( 𐊭 → Ϙ ) CARIAN LETTER T → GREEK LETTER ARCHAIC KOPPA #
10312 ; 03D8 ; MA # ( 𐌒 → Ϙ ) OLD ITALIC LETTER KU → GREEK LETTER ARCHAIC KOPPA #
@ -3936,6 +4000,7 @@ A668 ; 0298 ; MA # ( Ꙩ → ʘ ) CYRILLIC CAPITAL LETTER MONOCULAR O → LATIN
2CAA ; 03A6 ; MA # ( Ⲫ → Φ ) COPTIC CAPITAL LETTER FI → GREEK CAPITAL LETTER PHI #
0424 ; 03A6 ; MA # ( Ф → Φ ) CYRILLIC CAPITAL LETTER EF → GREEK CAPITAL LETTER PHI #
0553 ; 03A6 ; MA # ( Փ → Φ ) ARMENIAN CAPITAL LETTER PIWR → GREEK CAPITAL LETTER PHI #
1240 ; 03A6 ; MA # ( ቀ → Φ ) ETHIOPIC SYLLABLE QA → GREEK CAPITAL LETTER PHI # →Փ→
16F0 ; 03A6 ; MA # ( ᛰ → Φ ) RUNIC BELGTHOR SYMBOL → GREEK CAPITAL LETTER PHI #
102B3 ; 03A6 ; MA # ( 𐊳 → Φ ) CARIAN LETTER NN → GREEK CAPITAL LETTER PHI #
@ -3966,6 +4031,7 @@ AB55 ; 03C7 ; MA # ( ꭕ → χ ) LATIN SMALL LETTER CHI WITH LOW LEFT SERIF →
102B5 ; 03A8 ; MA # ( 𐊵 → Ψ ) CARIAN LETTER N → GREEK CAPITAL LETTER PSI #
2375 ; 03C9 ; MA #* ( ⍵ → ω ) APL FUNCTIONAL SYMBOL OMEGA → GREEK SMALL LETTER OMEGA #
A7B7 ; 03C9 ; MA # ( ꞷ → ω ) LATIN SMALL LETTER OMEGA → GREEK SMALL LETTER OMEGA #
1D6DA ; 03C9 ; MA # ( 𝛚 → ω ) MATHEMATICAL BOLD SMALL OMEGA → GREEK SMALL LETTER OMEGA #
1D714 ; 03C9 ; MA # ( 𝜔 → ω ) MATHEMATICAL ITALIC SMALL OMEGA → GREEK SMALL LETTER OMEGA #
1D74E ; 03C9 ; MA # ( 𝝎 → ω ) MATHEMATICAL BOLD ITALIC SMALL OMEGA → GREEK SMALL LETTER OMEGA #
@ -3973,7 +4039,6 @@ AB55 ; 03C7 ; MA # ( ꭕ → χ ) LATIN SMALL LETTER CHI WITH LOW LEFT SERIF →
1D7C2 ; 03C9 ; MA # ( 𝟂 → ω ) MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA → GREEK SMALL LETTER OMEGA #
2CB1 ; 03C9 ; MA # ( ⲱ → ω ) COPTIC SMALL LETTER OOU → GREEK SMALL LETTER OMEGA #
A64D ; 03C9 ; MA # ( ꙍ → ω ) CYRILLIC SMALL LETTER BROAD OMEGA → GREEK SMALL LETTER OMEGA # →ꞷ→
A7B7 ; 03C9 ; MA # ( ꞷ → ω ) LATIN SMALL LETTER OMEGA → GREEK SMALL LETTER OMEGA #
2126 ; 03A9 ; MA # ( Ω → Ω ) OHM SIGN → GREEK CAPITAL LETTER OMEGA #
1D6C0 ; 03A9 ; MA # ( 𝛀 → Ω ) MATHEMATICAL BOLD CAPITAL OMEGA → GREEK CAPITAL LETTER OMEGA #
@ -3997,7 +4062,9 @@ A7B7 ; 03C9 ; MA # ( ꞷ → ω ) LATIN SMALL LETTER OMEGA → GREEK SMALL LETTE
0496 ; 0416 0329 ; MA # ( Җ → Ж̩ ) CYRILLIC CAPITAL LETTER ZHE WITH DESCENDER → CYRILLIC CAPITAL LETTER ZHE, COMBINING VERTICAL LINE BELOW #
1D20B ; 0418 ; MA #* ( 𝈋 → И ) GREEK VOCAL NOTATION SYMBOL-12 → CYRILLIC CAPITAL LETTER I # →Ͷ→
0376 ; 0418 ; MA # ( Ͷ → И ) GREEK CAPITAL LETTER PAMPHYLIAN DIGAMMA → CYRILLIC CAPITAL LETTER I #
A6A1 ; 0418 ; MA # ( ꚡ → И ) BAMUM LETTER KA → CYRILLIC CAPITAL LETTER I # →Ͷ→
10425 ; 0418 ; MA # ( 𐐥 → И ) DESERET CAPITAL LETTER ENG → CYRILLIC CAPITAL LETTER I #
0419 ; 040D ; MA # ( Й → Ѝ ) CYRILLIC CAPITAL LETTER SHORT I → CYRILLIC CAPITAL LETTER I WITH GRAVE #
@ -4014,10 +4081,13 @@ A7B7 ; 03C9 ; MA # ( ꞷ → ω ) LATIN SMALL LETTER OMEGA → GREEK SMALL LETTE
AB60 ; 0459 ; MA # ( ꭠ → љ ) LATIN SMALL LETTER SAKHA YAT → CYRILLIC SMALL LETTER LJE #
1D202 ; 04FE ; MA #* ( 𝈂 → Ӿ ) GREEK VOCAL NOTATION SYMBOL-3 → CYRILLIC CAPITAL LETTER HA WITH STROKE #
1D222 ; 0460 ; MA #* ( 𝈢 → Ѡ ) GREEK INSTRUMENTAL NOTATION SYMBOL-8 → CYRILLIC CAPITAL LETTER OMEGA #
13C7 ; 0460 ; MA # ( Ꮗ → Ѡ ) CHEROKEE LETTER QUE → CYRILLIC CAPITAL LETTER OMEGA #
15EF ; 0460 ; MA # ( ᗯ → Ѡ ) CANADIAN SYLLABICS CARRIER GU → CYRILLIC CAPITAL LETTER OMEGA #
047C ; 0460 0483 ; MA # ( Ѽ → Ѡ҃ ) CYRILLIC CAPITAL LETTER OMEGA WITH TITLO → CYRILLIC CAPITAL LETTER OMEGA, COMBINING CYRILLIC TITLO #
047C ; 0460 0486 0487 ; MA # ( Ѽ → Ѡ҆҇ ) CYRILLIC CAPITAL LETTER OMEGA WITH TITLO → CYRILLIC CAPITAL LETTER OMEGA, COMBINING CYRILLIC PSILI PNEUMATA, COMBINING CYRILLIC POKRYTIE #
18ED ; 0460 00B7 ; MA # ( ᣭ → Ѡ· ) CANADIAN SYLLABICS CARRIER GWU → CYRILLIC CAPITAL LETTER OMEGA, MIDDLE DOT # →ᗯᐧ→
@ -4033,10 +4103,18 @@ A7B6 ; A64C ; MA # ( Ꞷ → Ꙍ ) LATIN CAPITAL LETTER OMEGA → CYRILLIC CAPIT
2CBC ; 0428 ; MA # ( Ⲽ → Ш ) COPTIC CAPITAL LETTER CRYPTOGRAMMIC NI → CYRILLIC CAPITAL LETTER SHA #
A650 ; 042A 006C ; MA # ( Ꙑ → Ъl ) CYRILLIC CAPITAL LETTER YERU WITH BACK YER → CYRILLIC CAPITAL LETTER HARD SIGN, LATIN SMALL LETTER L # →ЪІ→
2108 ; 042D ; MA #* ( ℈ → Э ) SCRUPLE → CYRILLIC CAPITAL LETTER E #
1F701 ; A658 ; MA #* ( 🜁 → Ꙙ ) ALCHEMICAL SYMBOL FOR AIR → CYRILLIC CAPITAL LETTER CLOSED LITTLE YUS #
A992 ; 2C3F ; MA # ( ꦒ → ⰿ ) JAVANESE LETTER GA → GLAGOLITIC SMALL LETTER MYSLITE #
0587 ; 0565 0582 ; MA # ( և → եւ ) ARMENIAN SMALL LIGATURE ECH YIWN → ARMENIAN SMALL LETTER ECH, ARMENIAN SMALL LETTER YIWN #
1294 ; 0571 ; MA # ( ኔ → ձ ) ETHIOPIC SYLLABLE NEE → ARMENIAN SMALL LETTER JA #
FB14 ; 0574 0565 ; MA # ( ﬔ → մե ) ARMENIAN SMALL LIGATURE MEN ECH → ARMENIAN SMALL LETTER MEN, ARMENIAN SMALL LETTER ECH #
FB15 ; 0574 056B ; MA # ( ﬕ → մի ) ARMENIAN SMALL LIGATURE MEN INI → ARMENIAN SMALL LETTER MEN, ARMENIAN SMALL LETTER INI #
@ -4047,6 +4125,8 @@ FB13 ; 0574 0576 ; MA # ( ﬓ → մն ) ARMENIAN SMALL LIGATURE MEN NOW → ARM
2229 ; 0548 ; MA #* ( ∩ → Ո ) INTERSECTION → ARMENIAN CAPITAL LETTER VO # →ᑎ→
22C2 ; 0548 ; MA #* ( ⋂ → Ո ) N-ARY INTERSECTION → ARMENIAN CAPITAL LETTER VO # →∩→→ᑎ→
1D245 ; 0548 ; MA #* ( 𝉅 → Ո ) GREEK MUSICAL LEIMMA → ARMENIAN CAPITAL LETTER VO # →∩→→ᑎ→
1260 ; 0548 ; MA # ( በ → Ո ) ETHIOPIC SYLLABLE BA → ARMENIAN CAPITAL LETTER VO #
144E ; 0548 ; MA # ( ᑎ → Ո ) CANADIAN SYLLABICS TI → ARMENIAN CAPITAL LETTER VO #
A4F5 ; 0548 ; MA # ( ꓵ → Ո ) LISU LETTER UE → ARMENIAN CAPITAL LETTER VO # →∩→→ᑎ→
@ -5316,6 +5396,14 @@ FE19 ; 2D57 ; MA #* ( ︙ → ⵗ ) PRESENTATION FORM FOR VERTICAL HORIZONTAL EL
205D ; 2D57 ; MA #* ( ⁝ → ⵗ ) TRICOLON → TIFINAGH LETTER TUAREG YAGH #
22EE ; 2D57 ; MA #* ( ⋮ → ⵗ ) VERTICAL ELLIPSIS → TIFINAGH LETTER TUAREG YAGH # →︙→→⁝→
0544 ; 1206 ; MA # ( Մ → ሆ ) ARMENIAN CAPITAL LETTER MEN → ETHIOPIC SYLLABLE HO #
054C ; 1261 ; MA # ( Ռ → ቡ ) ARMENIAN CAPITAL LETTER RA → ETHIOPIC SYLLABLE BU #
053B ; 12AE ; MA # ( Ի → ኮ ) ARMENIAN CAPITAL LETTER INI → ETHIOPIC SYLLABLE KO #
054A ; 1323 ; MA # ( Պ → ጣ ) ARMENIAN CAPITAL LETTER PEH → ETHIOPIC SYLLABLE THAA #
0906 ; 0905 093E ; MA # ( आ → अा ) DEVANAGARI LETTER AA → DEVANAGARI LETTER A, DEVANAGARI VOWEL SIGN AA #
0912 ; 0905 093E 0946 ; MA # ( ऒ → अाॆ ) DEVANAGARI LETTER SHORT O → DEVANAGARI LETTER A, DEVANAGARI VOWEL SIGN AA, DEVANAGARI VOWEL SIGN SHORT E # →अॊ→→आॆ→
@ -5340,6 +5428,8 @@ FE19 ; 2D57 ; MA #* ( ︙ → ⵗ ) PRESENTATION FORM FOR VERTICAL HORIZONTAL EL
111DC ; A8FB ; MA # ( 𑇜 → ꣻ ) SHARADA HEADSTROKE → DEVANAGARI HEADSTROKE #
111CB ; 093A ; MA # ( 𑇋 → ऺ ) SHARADA VOWEL MODIFIER MARK → DEVANAGARI VOWEL SIGN OE #
0AC1 ; 0941 ; MA # ( ુ → ु ) GUJARATI VOWEL SIGN U → DEVANAGARI VOWEL SIGN U #
0AC2 ; 0942 ; MA # ( ૂ → ू ) GUJARATI VOWEL SIGN UU → DEVANAGARI VOWEL SIGN UU #
@ -5562,18 +5652,25 @@ FE19 ; 2D57 ; MA #* ( ︙ → ⵗ ) PRESENTATION FORM FOR VERTICAL HORIZONTAL EL
0D6B ; 0D26 0D4D 0D30 ; MA # ( ൫ → ദ്ര ) MALAYALAM DIGIT FIVE → MALAYALAM LETTER DA, MALAYALAM SIGN VIRAMA, MALAYALAM LETTER RA #
0D79 ; 0D28 0D41 ; MA #* ( ൹ → നു ) MALAYALAM DATE MARK → MALAYALAM LETTER NA, MALAYALAM VOWEL SIGN U #
0D0C ; 0D28 0D41 ; MA # ( ഌ → നു ) MALAYALAM LETTER VOCALIC L → MALAYALAM LETTER NA, MALAYALAM VOWEL SIGN U #
0D19 ; 0D28 0D41 ; MA # ( ങ → നു ) MALAYALAM LETTER NGA → MALAYALAM LETTER NA, MALAYALAM VOWEL SIGN U # →ഌ→
0D6F ; 0D28 0D4D ; MA # ( ൯ → ന് ) MALAYALAM DIGIT NINE → MALAYALAM LETTER NA, MALAYALAM SIGN VIRAMA #
0D7B ; 0D28 0D4D ; MA # ( ൻ → ന് ) MALAYALAM LETTER CHILLU N → MALAYALAM LETTER NA, MALAYALAM SIGN VIRAMA # →൯→
0D8C ; 0D28 0D4D 0D28 ; MA # ( ඌ → ന്ന ) SINHALA LETTER UUYANNA → MALAYALAM LETTER NA, MALAYALAM SIGN VIRAMA, MALAYALAM LETTER NA #
0D6C ; 0D28 0D4D 0D28 ; MA # ( ൬ → ന്ന ) MALAYALAM DIGIT SIX → MALAYALAM LETTER NA, MALAYALAM SIGN VIRAMA, MALAYALAM LETTER NA #
0D5A ; 0D28 0D4D 0D2E ; MA #* ( ൚ → ന്മ ) MALAYALAM FRACTION THREE EIGHTIETHS → MALAYALAM LETTER NA, MALAYALAM SIGN VIRAMA, MALAYALAM LETTER MA #
0D31 ; 0D30 ; MA # ( റ → ര ) MALAYALAM LETTER RRA → MALAYALAM LETTER RA #
0D6A ; 0D30 0D4D ; MA # ( ൪ → ര് ) MALAYALAM DIGIT FOUR → MALAYALAM LETTER RA, MALAYALAM SIGN VIRAMA #
0D7C ; 0D30 0D4D ; MA # ( ർ → ര് ) MALAYALAM LETTER CHILLU RR → MALAYALAM LETTER RA, MALAYALAM SIGN VIRAMA # →൪→
0D6E ; 0D35 0D4D ; MA # ( ൮ → വ് ) MALAYALAM DIGIT EIGHT → MALAYALAM LETTER VA, MALAYALAM SIGN VIRAMA #
0D6E ; 0D35 0D4D 0D30 ; MA # ( ൮ → വ്ര ) MALAYALAM DIGIT EIGHT → MALAYALAM LETTER VA, MALAYALAM SIGN VIRAMA, MALAYALAM LETTER RA #
0D76 ; 0D39 0D4D 0D2E ; MA #* ( ൶ → ഹ്മ ) MALAYALAM FRACTION ONE SIXTEENTH → MALAYALAM LETTER HA, MALAYALAM SIGN VIRAMA, MALAYALAM LETTER MA #
0D42 ; 0D41 ; MA # ( ൂ → ു ) MALAYALAM VOWEL SIGN UU → MALAYALAM VOWEL SIGN U #
0D43 ; 0D41 ; MA # ( ൃ → ു ) MALAYALAM VOWEL SIGN VOCALIC R → MALAYALAM VOWEL SIGN U # →ൂ→
@ -5591,6 +5688,10 @@ FE19 ; 2D57 ; MA #* ( ︙ → ⵗ ) PRESENTATION FORM FOR VERTICAL HORIZONTAL EL
115DB ; 11584 ; MA # ( 𑗛 → 𑖄 ) SIDDHAM LETTER ALTERNATE U → SIDDHAM LETTER U #
115DC ; 115B2 ; MA # ( 𑗜 → 𑖲 ) SIDDHAM VOWEL SIGN ALTERNATE U → SIDDHAM VOWEL SIGN U #
115DD ; 115B3 ; MA # ( 𑗝 → 𑖳 ) SIDDHAM VOWEL SIGN ALTERNATE UU → SIDDHAM VOWEL SIGN UU #
0E03 ; 0E02 ; MA # ( ฃ → ข ) THAI CHARACTER KHO KHUAT → THAI CHARACTER KHO KHAI #
0E14 ; 0E04 ; MA # ( ด → ค ) THAI CHARACTER DO DEK → THAI CHARACTER KHO KHWAI #
@ -5689,6 +5790,8 @@ AA56 ; AA23 ; MA # ( ꩖ → ꨣ ) CHAM DIGIT SIX → CHAM LETTER RA #
1B58 ; 1B28 ; MA # ( ᭘ → ᬨ ) BALINESE DIGIT EIGHT → BALINESE LETTER PA KAPAL #
A9A3 ; A99D ; MA # ( ꦣ → ꦝ ) JAVANESE LETTER DA MAHAPRANA → JAVANESE LETTER DDA #
1896 ; 185C ; MA # ( ᢖ → ᡜ ) MONGOLIAN LETTER ALI GALI ZA → MONGOLIAN LETTER TODO DZA #
1855 ; 1835 ; MA # ( ᡕ → ᠵ ) MONGOLIAN LETTER TODO YA → MONGOLIAN LETTER JA #
@ -5965,11 +6068,15 @@ A4ED ; 1660 ; MA # ( ꓭ → ᙠ ) LISU LETTER GHA → CANADIAN SYLLABICS CARRIE
02E2 ; 18F5 ; MA # ( ˢ → ᣵ ) MODIFIER LETTER SMALL S → CANADIAN SYLLABICS CARRIER DENTAL S #
A6B0 ; 16B9 ; MA # ( ꚰ → ᚹ ) BAMUM LETTER TAA → RUNIC LETTER WUNJO WYNN W #
16E1 ; 16BC ; MA # ( ᛡ → ᚼ ) RUNIC LETTER IOR → RUNIC LETTER LONG-BRANCH-HAGALL H #
237F ; 16BD ; MA #* ( ⍿ → ᚽ ) VERTICAL LINE WITH MIDDLE DOT → RUNIC LETTER SHORT-TWIG-HAGALL H # →ᛂ→
16C2 ; 16BD ; MA # ( ᛂ → ᚽ ) RUNIC LETTER E → RUNIC LETTER SHORT-TWIG-HAGALL H #
1D23F ; 16CB ; MA #* ( 𝈿 → ᛋ ) GREEK INSTRUMENTAL NOTATION SYMBOL-52 → RUNIC LETTER SIGEL LONG-BRANCH-SOL S #
2191 ; 16CF ; MA #* ( ↑ → ᛏ ) UPWARDS ARROW → RUNIC LETTER TIWAZ TIR TYR T #
21BF ; 16D0 ; MA #* ( ↿ → ᛐ ) UPWARDS HARPOON WITH BARB LEFTWARDS → RUNIC LETTER SHORT-TWIG-TYR T #
@ -6671,6 +6778,7 @@ A4A7 ; A458 ; MA #* ( ꒧ → ꑘ ) YI RADICAL NYOP → YI SYLLABLE NYOP #
22A5 ; A4D5 ; MA #* ( ⊥ → ꓕ ) UP TACK → LISU LETTER THA #
27C2 ; A4D5 ; MA #* ( ⟂ → ꓕ ) PERPENDICULAR → LISU LETTER THA # →⊥→
1D21C ; A4D5 ; MA #* ( 𝈜 → ꓕ ) GREEK VOCAL NOTATION SYMBOL-54 → LISU LETTER THA # →Ʇ→
A7B1 ; A4D5 ; MA # ( Ʇ → ꓕ ) LATIN CAPITAL LETTER TURNED T → LISU LETTER THA #
A79E ; A4E4 ; MA # ( Ꞟ → ꓤ ) LATIN CAPITAL LETTER VOLAPUK UE → LISU LETTER ZA #
@ -6678,13 +6786,17 @@ A79E ; A4E4 ; MA # ( Ꞟ → ꓤ ) LATIN CAPITAL LETTER VOLAPUK UE → LISU LETT
2141 ; A4E8 ; MA #* ( ⅁ → ꓨ ) TURNED SANS-SERIF CAPITAL G → LISU LETTER HHA #
2142 ; A4F6 ; MA #* ( ⅂ → ꓶ ) TURNED SANS-SERIF CAPITAL L → LISU LETTER UH #
1D215 ; A4F6 ; MA #* ( 𝈕 → ꓶ ) GREEK VOCAL NOTATION SYMBOL-22 → LISU LETTER UH # →⅂→
1D22B ; A4F6 ; MA #* ( 𝈫 → ꓶ ) GREEK INSTRUMENTAL NOTATION SYMBOL-24 → LISU LETTER UH # →𝈕→→⅂→
10411 ; A4F6 ; MA # ( 𐐑 → ꓶ ) DESERET CAPITAL LETTER PEE → LISU LETTER UH # →⅂→
2295 ; 102A8 ; MA #* ( ⊕ → 𐊨 ) CIRCLED PLUS → CARIAN LETTER Q #
2A01 ; 102A8 ; MA #* ( ⨁ → 𐊨 ) N-ARY CIRCLED PLUS OPERATOR → CARIAN LETTER Q # →⊕→
1F728 ; 102A8 ; MA #* ( 🜨 → 𐊨 ) ALCHEMICAL SYMBOL FOR VERDIGRIS → CARIAN LETTER Q # →⊕→
A69A ; 102A8 ; MA # ( Ꚛ → 𐊨 ) CYRILLIC CAPITAL LETTER CROSSED O → CARIAN LETTER Q # →⊕→
25BD ; 102BC ; MA #* ( ▽ → 𐊼 ) WHITE DOWN-POINTING TRIANGLE → CARIAN LETTER K #
1D214 ; 102BC ; MA #* ( 𝈔 → 𐊼 ) GREEK VOCAL NOTATION SYMBOL-21 → CARIAN LETTER K # →▽→
1F704 ; 102BC ; MA #* ( 🜄 → 𐊼 ) ALCHEMICAL SYMBOL FOR WATER → CARIAN LETTER K # →▽→
29D6 ; 102C0 ; MA #* ( ⧖ → 𐋀 ) WHITE HOURGLASS → CARIAN LETTER G #
@ -6766,6 +6878,7 @@ F95E ; 4E39 ; MA # ( 丹 → 丹 ) CJK COMPATIBILITY IDEOGRAPH-F95E → CJK UNIF
2E83 ; 4E5A ; MA #* ( ⺃ → 乚 ) CJK RADICAL SECOND TWO → CJK UNIFIED IDEOGRAPH-4E5A #
31D6 ; 4E5B ; MA #* ( ㇖ → 乛 ) CJK STROKE HG → CJK UNIFIED IDEOGRAPH-4E5B #
2E82 ; 4E5B ; MA #* ( ⺂ → 乛 ) CJK RADICAL SECOND ONE → CJK UNIFIED IDEOGRAPH-4E5B # →㇖→
2EF2 ; 4E80 ; MA #* ( ⻲ → 亀 ) CJK RADICAL J-SIMPLIFIED TURTLE → CJK UNIFIED IDEOGRAPH-4E80 #
@ -6776,6 +6889,7 @@ F91B ; 4E82 ; MA # ( 亂 → 亂 ) CJK COMPATIBILITY IDEOGRAPH-F91B → CJK UNIF
F9BA ; 4E86 ; MA # ( 了 → 了 ) CJK COMPATIBILITY IDEOGRAPH-F9BA → CJK UNIFIED IDEOGRAPH-4E86 #
30CB ; 4E8C ; MA # ( ニ → 二 ) KATAKANA LETTER NI → CJK UNIFIED IDEOGRAPH-4E8C #
2F06 ; 4E8C ; MA #* ( ⼆ → 二 ) KANGXI RADICAL TWO → CJK UNIFIED IDEOGRAPH-4E8C #
2F803 ; 20122 ; MA # ( 𠄢 → 𠄢 ) CJK COMPATIBILITY IDEOGRAPH-2F803 → CJK UNIFIED IDEOGRAPH-20122 #
@ -6786,6 +6900,7 @@ F977 ; 4EAE ; MA # ( 亮 → 亮 ) CJK COMPATIBILITY IDEOGRAPH-F977 → CJK UNIF
2F08 ; 4EBA ; MA #* ( ⼈ → 人 ) KANGXI RADICAL MAN → CJK UNIFIED IDEOGRAPH-4EBA #
30A4 ; 4EBB ; MA # ( イ → 亻 ) KATAKANA LETTER I → CJK UNIFIED IDEOGRAPH-4EBB # →⺅→
2E85 ; 4EBB ; MA #* ( ⺅ → 亻 ) CJK RADICAL PERSON → CJK UNIFIED IDEOGRAPH-4EBB #
F9FD ; 4EC0 ; MA # ( 什 → 什 ) CJK COMPATIBILITY IDEOGRAPH-F9FD → CJK UNIFIED IDEOGRAPH-4EC0 #
@ -6851,6 +6966,7 @@ FA72 ; 5168 ; MA # ( 全 → 全 ) CJK COMPATIBILITY IDEOGRAPH-FA72 → CJK UNIF
F978 ; 5169 ; MA # ( 兩 → 兩 ) CJK COMPATIBILITY IDEOGRAPH-F978 → CJK UNIFIED IDEOGRAPH-5169 #
30CF ; 516B ; MA # ( ハ → 八 ) KATAKANA LETTER HA → CJK UNIFIED IDEOGRAPH-516B #
2F0B ; 516B ; MA #* ( ⼋ → 八 ) KANGXI RADICAL EIGHT → CJK UNIFIED IDEOGRAPH-516B #
F9D1 ; 516D ; MA # ( 六 → 六 ) CJK COMPATIBILITY IDEOGRAPH-F9D1 → CJK UNIFIED IDEOGRAPH-516D #
@ -6938,6 +7054,7 @@ F9C7 ; 5289 ; MA # ( 劉 → 劉 ) CJK COMPATIBILITY IDEOGRAPH-F9C7 → CJK UNIF
2F9D9 ; 20804 ; MA # ( 𠠄 → 𠠄 ) CJK COMPATIBILITY IDEOGRAPH-2F9D9 → CJK UNIFIED IDEOGRAPH-20804 #
30AB ; 529B ; MA # ( カ → 力 ) KATAKANA LETTER KA → CJK UNIFIED IDEOGRAPH-529B # →⼒→
F98A ; 529B ; MA # ( 力 → 力 ) CJK COMPATIBILITY IDEOGRAPH-F98A → CJK UNIFIED IDEOGRAPH-529B #
2F12 ; 529B ; MA #* ( ⼒ → 力 ) KANGXI RADICAL POWER → CJK UNIFIED IDEOGRAPH-529B #
@ -6991,11 +7108,16 @@ F9EB ; 533F ; MA # ( 匿 → 匿 ) CJK COMPATIBILITY IDEOGRAPH-F9EB → CJK UNIF
2F82C ; 5349 ; MA # ( 卉 → 卉 ) CJK COMPATIBILITY IDEOGRAPH-2F82C → CJK UNIFIED IDEOGRAPH-5349 #
0FD6 ; 534D ; MA #* ( ࿖ → 卍 ) LEFT-FACING SVASTI SIGN → CJK UNIFIED IDEOGRAPH-534D #
0FD5 ; 5350 ; MA #* ( ࿕ → 卐 ) RIGHT-FACING SVASTI SIGN → CJK UNIFIED IDEOGRAPH-5350 #
FA35 ; 5351 ; MA # ( 卑 → 卑 ) CJK COMPATIBILITY IDEOGRAPH-FA35 → CJK UNIFIED IDEOGRAPH-5351 #
2F82D ; 5351 ; MA # ( 卑 → 卑 ) CJK COMPATIBILITY IDEOGRAPH-2F82D → CJK UNIFIED IDEOGRAPH-5351 #
2F82E ; 535A ; MA # ( 博 → 博 ) CJK COMPATIBILITY IDEOGRAPH-2F82E → CJK UNIFIED IDEOGRAPH-535A #
30C8 ; 535C ; MA # ( ト → 卜 ) KATAKANA LETTER TO → CJK UNIFIED IDEOGRAPH-535C # →⼘→
2F18 ; 535C ; MA #* ( ⼘ → 卜 ) KANGXI RADICAL DIVINATION → CJK UNIFIED IDEOGRAPH-535C #
2F19 ; 5369 ; MA #* ( ⼙ → 卩 ) KANGXI RADICAL SEAL → CJK UNIFIED IDEOGRAPH-5369 #
@ -7028,7 +7150,10 @@ F96B ; 53C3 ; MA # ( 參 → 參 ) CJK COMPATIBILITY IDEOGRAPH-F96B → CJK UNIF
2F838 ; 20B63 ; MA # ( 𠭣 → 𠭣 ) CJK COMPATIBILITY IDEOGRAPH-2F838 → CJK UNIFIED IDEOGRAPH-20B63 #
30ED ; 53E3 ; MA # ( ロ → 口 ) KATAKANA LETTER RO → CJK UNIFIED IDEOGRAPH-53E3 # →⼞→→⼝→
2F1D ; 53E3 ; MA #* ( ⼝ → 口 ) KANGXI RADICAL MOUTH → CJK UNIFIED IDEOGRAPH-53E3 #
56D7 ; 53E3 ; MA # ( 囗 → 口 ) CJK UNIFIED IDEOGRAPH-56D7 → CJK UNIFIED IDEOGRAPH-53E3 # →⼞→→⼝→
2F1E ; 53E3 ; MA #* ( ⼞ → 口 ) KANGXI RADICAL ENCLOSURE → CJK UNIFIED IDEOGRAPH-53E3 # →⼝→
F906 ; 53E5 ; MA # ( 句 → 句 ) CJK COMPATIBILITY IDEOGRAPH-F906 → CJK UNIFIED IDEOGRAPH-53E5 #
@ -7099,8 +7224,6 @@ FA37 ; 5606 ; MA # ( 嘆 → 嘆 ) CJK COMPATIBILITY IDEOGRAPH-FA37 → CJK UNIF
FA38 ; 5668 ; MA # ( 器 → 器 ) CJK COMPATIBILITY IDEOGRAPH-FA38 → CJK UNIFIED IDEOGRAPH-5668 #
2F1E ; 56D7 ; MA #* ( ⼞ → 囗 ) KANGXI RADICAL ENCLOSURE → CJK UNIFIED IDEOGRAPH-56D7 #
F9A9 ; 56F9 ; MA # ( 囹 → 囹 ) CJK COMPATIBILITY IDEOGRAPH-F9A9 → CJK UNIFIED IDEOGRAPH-56F9 #
2F84B ; 5716 ; MA # ( 圖 → 圖 ) CJK COMPATIBILITY IDEOGRAPH-2F84B → CJK UNIFIED IDEOGRAPH-5716 #
@ -7108,6 +7231,8 @@ F9A9 ; 56F9 ; MA # ( 囹 → 囹 ) CJK COMPATIBILITY IDEOGRAPH-F9A9 → CJK UNIF
2F84D ; 5717 ; MA # ( 圗 → 圗 ) CJK COMPATIBILITY IDEOGRAPH-2F84D → CJK UNIFIED IDEOGRAPH-5717 #
2F1F ; 571F ; MA #* ( ⼟ → 土 ) KANGXI RADICAL EARTH → CJK UNIFIED IDEOGRAPH-571F #
58EB ; 571F ; MA # ( 士 → 土 ) CJK UNIFIED IDEOGRAPH-58EB → CJK UNIFIED IDEOGRAPH-571F # →⼠→→⼟→
2F20 ; 571F ; MA #* ( ⼠ → 土 ) KANGXI RADICAL SCHOLAR → CJK UNIFIED IDEOGRAPH-571F # →⼟→
2F855 ; 578B ; MA # ( 型 → 型 ) CJK COMPATIBILITY IDEOGRAPH-2F855 → CJK UNIFIED IDEOGRAPH-578B #
@ -7144,8 +7269,6 @@ F942 ; 58DF ; MA # ( 壟 → 壟 ) CJK COMPATIBILITY IDEOGRAPH-F942 → CJK UNIF
2F859 ; 214E4 ; MA # ( 𡓤 → 𡓤 ) CJK COMPATIBILITY IDEOGRAPH-2F859 → CJK UNIFIED IDEOGRAPH-214E4 #
2F20 ; 58EB ; MA #* ( ⼠ → 士 ) KANGXI RADICAL SCHOLAR → CJK UNIFIED IDEOGRAPH-58EB #
2F851 ; 58EE ; MA # ( 壮 → 壮 ) CJK COMPATIBILITY IDEOGRAPH-2F851 → CJK UNIFIED IDEOGRAPH-58EE #
2F85A ; 58F2 ; MA # ( 売 → 売 ) CJK COMPATIBILITY IDEOGRAPH-2F85A → CJK UNIFIED IDEOGRAPH-58F2 #
@ -7158,6 +7281,7 @@ F942 ; 58DF ; MA # ( 壟 → 壟 ) CJK COMPATIBILITY IDEOGRAPH-F942 → CJK UNIF
2F22 ; 590A ; MA #* ( ⼢ → 夊 ) KANGXI RADICAL GO SLOWLY → CJK UNIFIED IDEOGRAPH-590A #
30BF ; 5915 ; MA # ( タ → 夕 ) KATAKANA LETTER TA → CJK UNIFIED IDEOGRAPH-5915 # →⼣→
2F23 ; 5915 ; MA #* ( ⼣ → 夕 ) KANGXI RADICAL EVENING → CJK UNIFIED IDEOGRAPH-5915 #
2F85D ; 591A ; MA # ( 多 → 多 ) CJK COMPATIBILITY IDEOGRAPH-2F85D → CJK UNIFIED IDEOGRAPH-591A #
@ -7296,6 +7420,7 @@ F9AB ; 5DBA ; MA # ( 嶺 → 嶺 ) CJK COMPATIBILITY IDEOGRAPH-F9AB → CJK UNIF
2F882 ; 5DE2 ; MA # ( 巢 → 巢 ) CJK COMPATIBILITY IDEOGRAPH-2F882 → CJK UNIFIED IDEOGRAPH-5DE2 #
30A8 ; 5DE5 ; MA # ( エ → 工 ) KATAKANA LETTER E → CJK UNIFIED IDEOGRAPH-5DE5 # →⼯→
2F2F ; 5DE5 ; MA #* ( ⼯ → 工 ) KANGXI RADICAL WORK → CJK UNIFIED IDEOGRAPH-5DE5 #
2F30 ; 5DF1 ; MA #* ( ⼰ → 己 ) KANGXI RADICAL ONESELF → CJK UNIFIED IDEOGRAPH-5DF1 #
@ -9268,7 +9393,19 @@ FACE ; 9F9C ; MA # ( 龜 → 龜 ) CJK COMPATIBILITY IDEOGRAPH-FACE → CJK UNIF
2FD5 ; 9FA0 ; MA #* ( ⿕ → 龠 ) KANGXI RADICAL FLUTE → CJK UNIFIED IDEOGRAPH-9FA0 #
111DB ; A8FC ; MA #* ( 𑇛 → ꣼ ) SHARADA SIGN SIDDHAM → DEVANAGARI SIGN SIDDHAM #
23FC ; 23FB ; MA #* ( ⏼ → ⏻ ) POWER ON-OFF SYMBOL → POWER SYMBOL #
# total: 6069
11413 ; 11434 11442 11412 ; MA # ( 𑐓 → 𑐴𑑂𑐒 ) NEWA LETTER NGHA → NEWA LETTER HA, NEWA SIGN VIRAMA, NEWA LETTER NGA #
11419 ; 11434 11442 11418 ; MA # ( 𑐙 → 𑐴𑑂𑐘 ) NEWA LETTER NYHA → NEWA LETTER HA, NEWA SIGN VIRAMA, NEWA LETTER NYA #
11424 ; 11434 11442 11423 ; MA # ( 𑐤 → 𑐴𑑂𑐣 ) NEWA LETTER NHA → NEWA LETTER HA, NEWA SIGN VIRAMA, NEWA LETTER NA #
1142A ; 11434 11442 11429 ; MA # ( 𑐪 → 𑐴𑑂𑐩 ) NEWA LETTER MHA → NEWA LETTER HA, NEWA SIGN VIRAMA, NEWA LETTER MA #
1142D ; 11434 11442 1142C ; MA # ( 𑐭 → 𑐴𑑂𑐬 ) NEWA LETTER RHA → NEWA LETTER HA, NEWA SIGN VIRAMA, NEWA LETTER RA #
1142F ; 11434 11442 1142E ; MA # ( 𑐯 → 𑐴𑑂𑐮 ) NEWA LETTER LHA → NEWA LETTER HA, NEWA SIGN VIRAMA, NEWA LETTER LA #
# total: 6167

14
icu4c/source/data/unidata/norm2/nfc.txt
View file

@ -7,7 +7,7 @@
#
# Complete data for Unicode NFC normalization.
* Unicode 8.0.0
* Unicode 9.0.0
# Canonical_Combining_Class (ccc) values
0300..0314:230
@ -129,6 +129,7 @@
0825..0827:230
0829..082D:230
0859..085B:220
08D4..08E1:230
08E3:220
08E4..08E5:230
08E6:220
@ -233,6 +234,7 @@
1DCF:220
1DD0:202
1DD1..1DF5:230
1DFB:230
1DFC:233
1DFD:220
1DFE:230
@ -310,6 +312,8 @@ FE2E..FE2F:230
1134D:9
11366..1136C:230
11370..11374:230
11442:9
11446:7
114C2:9
114C3:7
115BF:9
@ -318,6 +322,7 @@ FE2E..FE2F:230
116B6:9
116B7:7
1172B:9
11C3F:9
16AF0..16AF4:1
16B30..16B36:230
1BC9E:1
@ -330,7 +335,14 @@ FE2E..FE2F:230
1D18A..1D18B:220
1D1AA..1D1AD:230
1D242..1D244:230
1E000..1E006:230
1E008..1E018:230
1E01B..1E021:230
1E023..1E024:230
1E026..1E02A:230
1E8D0..1E8D6:220
1E944..1E949:230
1E94A:7
# Canonical decomposition mappings
00C0=0041 0300

3
icu4c/source/data/unidata/norm2/nfkc.txt
View file

@ -11,7 +11,7 @@
# to NFKC one-way mappings.
# Use this file as the second gennorm2 input file after nfc.txt.
* Unicode 8.0.0
* Unicode 9.0.0
00A0>0020
00A8>0020 0308
@ -3675,6 +3675,7 @@ FFEE>25CB
1F238>7533
1F239>5272
1F23A>55B6
1F23B>914D
1F240>3014 672C 3015
1F241>3014 4E09 3015
1F242>3014 4E8C 3015

82
icu4c/source/data/unidata/norm2/nfkc_cf.txt
View file

@ -12,7 +12,7 @@
# and reformatted into syntax for the gennorm2 Normalizer2 data generator tool.
# Use this file as the third gennorm2 input file after nfc.txt and nfkc.txt.
* Unicode 8.0.0
* Unicode 9.0.0
0041>0061
0042>0062
@ -640,6 +640,14 @@
13FD>13F5
17B4..17B5>
180B..180E>
1C80>0432
1C81>0434
1C82>043E
1C83>0441
1C84..1C85>0442
1C86>044A
1C87>0463
1C88>A64B
1D2C>0061
1D2D>00E6
1D2E>0062
@ -2388,6 +2396,7 @@ A7AA>0266
A7AB>025C
A7AC>0261
A7AD>026C
A7AE>026A
A7B0>029E
A7B1>0287
A7B2>029D
@ -3856,6 +3865,42 @@ FFF0..FFF8>
10425>1044D
10426>1044E
10427>1044F
104B0>104D8
104B1>104D9
104B2>104DA
104B3>104DB
104B4>104DC
104B5>104DD
104B6>104DE
104B7>104DF
104B8>104E0
104B9>104E1
104BA>104E2
104BB>104E3
104BC>104E4
104BD>104E5
104BE>104E6
104BF>104E7
104C0>104E8
104C1>104E9
104C2>104EA
104C3>104EB
104C4>104EC
104C5>104ED
104C6>104EE
104C7>104EF
104C8>104F0
104C9>104F1
104CA>104F2
104CB>104F3
104CC>104F4
104CD>104F5
104CE>104F6
104CF>104F7
104D0>104F8
104D1>104F9
104D2>104FA
104D3>104FB
10C80>10CC0
10C81>10CC1
10C82>10CC2
@ -4944,6 +4989,40 @@ FFF0..FFF8>
1D7FD>0037
1D7FE>0038
1D7FF>0039
1E900>1E922
1E901>1E923
1E902>1E924
1E903>1E925
1E904>1E926
1E905>1E927
1E906>1E928
1E907>1E929
1E908>1E92A
1E909>1E92B
1E90A>1E92C
1E90B>1E92D
1E90C>1E92E
1E90D>1E92F
1E90E>1E930
1E90F>1E931
1E910>1E932
1E911>1E933
1E912>1E934
1E913>1E935
1E914>1E936
1E915>1E937
1E916>1E938
1E917>1E939
1E918>1E93A
1E919>1E93B
1E91A>1E93C
1E91B>1E93D
1E91C>1E93E
1E91D>1E93F
1E91E>1E940
1E91F>1E941
1E920>1E942
1E921>1E943
1EE00>0627
1EE01>0628
1EE02>062C
@ -5208,6 +5287,7 @@ FFF0..FFF8>
1F238>7533
1F239>5272
1F23A>55B6
1F23B>914D
1F240>3014 672C 3015
1F241>3014 4E09 3015
1F242>3014 4E8C 3015

224
icu4c/source/data/unidata/norm2/uts46.txt
View file

@ -1,10 +1,11 @@
# Original file:
# IdnaMappingTable-8.0.0.txt
# Date: 2015-05-02 12:42:14 GMT [MD]
# IdnaMappingTable-9.0.0.txt
# Date: 2016-03-11, 09:01:52 GMT
# © 2016 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode IDNA Compatible Preprocessing (UTS #46)
# Copyright (c) 1991-2015 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr46/
# ================================================
@ -986,7 +987,11 @@
# 08A2..08AC valid # 6.1 ARABIC LETTER JEEM WITH TWO DOTS ABOVE..ARABIC LETTER ROHINGYA YEH
# 08AD..08B2 valid # 7.0 ARABIC LETTER LOW ALEF..ARABIC LETTER ZAIN WITH INVERTED V ABOVE
# 08B3..08B4 valid # 8.0 ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER KAF WITH DOT BELOW
08B5..08E2 >FFFD # NA <reserved-08B5>..<reserved-08E2>
08B5 >FFFD # NA <reserved-08B5>
# 08B6..08BD valid # 9.0 ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON
08BE..08D3 >FFFD # NA <reserved-08BE>..<reserved-08D3>
# 08D4..08E1 valid # 9.0 ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA
08E2 >FFFD # 9.0 ARABIC DISPUTED END OF AYAH
# 08E3 valid # 8.0 ARABIC TURNED DAMMA BELOW
# 08E4..08FE valid # 6.1 ARABIC CURLY FATHA..ARABIC DAMMA WITH DOT
# 08FF valid # 7.0 ARABIC MARK SIDEWAYS NOON GHUNNA
@ -1232,7 +1237,7 @@
# 0C66..0C6F valid # 1.1 TELUGU DIGIT ZERO..TELUGU DIGIT NINE
0C70..0C77 >FFFD # NA <reserved-0C70>..<reserved-0C77>
# 0C78..0C7F valid # 5.1 TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR..TELUGU SIGN TUUMU
0C80 >FFFD # NA <reserved-0C80>
# 0C80 valid # 9.0 KANNADA SIGN SPACING CANDRABINDU
# 0C81 valid # 7.0 KANNADA SIGN CANDRABINDU
# 0C82..0C83 valid # 1.1 KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA
0C84 >FFFD # NA <reserved-0C84>
@ -1284,16 +1289,18 @@
0D49 >FFFD # NA <reserved-0D49>
# 0D4A..0D4D valid # 1.1 MALAYALAM VOWEL SIGN O..MALAYALAM SIGN VIRAMA
# 0D4E valid # 6.0 MALAYALAM LETTER DOT REPH
0D4F..0D56 >FFFD # NA <reserved-0D4F>..<reserved-0D56>
# 0D4F valid # 9.0 MALAYALAM SIGN PARA
0D50..0D53 >FFFD # NA <reserved-0D50>..<reserved-0D53>
# 0D54..0D56 valid # 9.0 MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL
# 0D57 valid # 1.1 MALAYALAM AU LENGTH MARK
0D58..0D5E >FFFD # NA <reserved-0D58>..<reserved-0D5E>
# 0D58..0D5E valid # 9.0 MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH..MALAYALAM FRACTION ONE FIFTH
# 0D5F valid # 8.0 MALAYALAM LETTER ARCHAIC II
# 0D60..0D61 valid # 1.1 MALAYALAM LETTER VOCALIC RR..MALAYALAM LETTER VOCALIC LL
# 0D62..0D63 valid # 5.1 MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL
0D64..0D65 >FFFD # NA <reserved-0D64>..<reserved-0D65>
# 0D66..0D6F valid # 1.1 MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE
# 0D70..0D75 valid # 5.1 MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE QUARTERS
0D76..0D78 >FFFD # NA <reserved-0D76>..<reserved-0D78>
# 0D76..0D78 valid # 9.0 MALAYALAM FRACTION ONE SIXTEENTH..MALAYALAM FRACTION THREE SIXTEENTHS
# 0D79 valid # 5.1 MALAYALAM DATE MARK
# 0D7A..0D7F valid # 5.1 MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K
0D80..0D81 >FFFD # NA <reserved-0D80>..<reserved-0D81>
@ -1672,7 +1679,15 @@
1C4A..1C4C >FFFD # NA <reserved-1C4A>..<reserved-1C4C>
# 1C4D..1C7D valid # 5.1 LEPCHA LETTER TTA..OL CHIKI AHAD
# 1C7E..1C7F valid # 5.1 OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD
1C80..1CBF >FFFD # NA <reserved-1C80>..<reserved-1CBF>
1C80 >0432 # 9.0 CYRILLIC SMALL LETTER ROUNDED VE
1C81 >0434 # 9.0 CYRILLIC SMALL LETTER LONG-LEGGED DE
1C82 >043E # 9.0 CYRILLIC SMALL LETTER NARROW O
1C83 >0441 # 9.0 CYRILLIC SMALL LETTER WIDE ES
1C84..1C85 >0442 # 9.0 CYRILLIC SMALL LETTER TALL TE..CYRILLIC SMALL LETTER THREE-LEGGED TE
1C86 >044A # 9.0 CYRILLIC SMALL LETTER TALL HARD SIGN
1C87 >0463 # 9.0 CYRILLIC SMALL LETTER TALL YAT
1C88 >A64B # 9.0 CYRILLIC SMALL LETTER UNBLENDED UK
1C89..1CBF >FFFD # NA <reserved-1C89>..<reserved-1CBF>
# 1CC0..1CC7 valid # 6.1 SUNDANESE PUNCTUATION BINDU SURYA..SUNDANESE PUNCTUATION BINDU BA SATANGA
1CC8..1CCF >FFFD # NA <reserved-1CC8>..<reserved-1CCF>
# 1CD0..1CD2 valid # 5.2 VEDIC TONE KARSHANA..VEDIC TONE PRENKHA
@ -1791,7 +1806,8 @@
# 1DC4..1DCA valid # 5.0 COMBINING MACRON-ACUTE..COMBINING LATIN SMALL LETTER R BELOW
# 1DCB..1DE6 valid # 5.1 COMBINING BREVE-MACRON..COMBINING LATIN SMALL LETTER Z
# 1DE7..1DF5 valid # 7.0 COMBINING LATIN SMALL LETTER ALPHA..COMBINING UP TACK ABOVE
1DF6..1DFB >FFFD # NA <reserved-1DF6>..<reserved-1DFB>
1DF6..1DFA >FFFD # NA <reserved-1DF6>..<reserved-1DFA>
# 1DFB valid # 9.0 COMBINING DELETION MARK
# 1DFC valid # 6.0 COMBINING DOUBLE INVERTED BREVE BELOW
# 1DFD valid # 5.2 COMBINING ALMOST EQUAL TO BELOW
# 1DFE..1DFF valid # 5.0 COMBINING LEFT ARROWHEAD ABOVE..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
@ -2497,7 +2513,8 @@
# 23E8 valid # 5.2 DECIMAL EXPONENT SYMBOL
# 23E9..23F3 valid # 6.0 BLACK RIGHT-POINTING DOUBLE TRIANGLE..HOURGLASS WITH FLOWING SAND
# 23F4..23FA valid # 7.0 BLACK MEDIUM LEFT-POINTING TRIANGLE..BLACK CIRCLE FOR RECORD
23FB..23FF >FFFD # NA <reserved-23FB>..<reserved-23FF>
# 23FB..23FE valid # 9.0 POWER SYMBOL..POWER SLEEP SYMBOL
23FF >FFFD # NA <reserved-23FF>
# 2400..2424 valid # 1.1 SYMBOL FOR NULL..SYMBOL FOR NEWLINE
# 2425..2426 valid # 3.0 SYMBOL FOR DELETE FORM TWO..SYMBOL FOR SUBSTITUTE FORM TWO
2427..243F >FFFD # NA <reserved-2427>..<reserved-243F>
@ -2949,7 +2966,8 @@
# 2E31 valid # 5.2 WORD SEPARATOR MIDDLE DOT
# 2E32..2E3B valid # 6.1 TURNED COMMA..THREE-EM DASH
# 2E3C..2E42 valid # 7.0 STENOGRAPHIC FULL STOP..DOUBLE LOW-REVERSED-9 QUOTATION MARK
2E43..2E7F >FFFD # NA <reserved-2E43>..<reserved-2E7F>
# 2E43..2E44 valid # 9.0 DASH WITH LEFT UPTURN..DOUBLE SUSPENSION MARK
2E45..2E7F >FFFD # NA <reserved-2E45>..<reserved-2E7F>
# 2E80..2E99 valid # 3.0 CJK RADICAL REPEAT..CJK RADICAL RAP
2E9A >FFFD # NA <reserved-2E9A>
# 2E9B..2E9E valid # 3.0 CJK RADICAL CHOKE..CJK RADICAL DEATH
@ -4078,7 +4096,8 @@ A7AA >0266 # 6.1 LATIN CAPITAL LETTER H WITH HOOK
A7AB >025C # 7.0 LATIN CAPITAL LETTER REVERSED OPEN E
A7AC >0261 # 7.0 LATIN CAPITAL LETTER SCRIPT G
A7AD >026C # 7.0 LATIN CAPITAL LETTER L WITH BELT
A7AE..A7AF >FFFD # NA <reserved-A7AE>..<reserved-A7AF>
A7AE >026A # 9.0 LATIN CAPITAL LETTER SMALL CAPITAL I
A7AF >FFFD # NA <reserved-A7AF>
A7B0 >029E # 7.0 LATIN CAPITAL LETTER TURNED K
A7B1 >0287 # 7.0 LATIN CAPITAL LETTER TURNED T
A7B2 >029D # 8.0 LATIN CAPITAL LETTER J WITH CROSSED-TAIL
@ -4102,7 +4121,8 @@ A83A..A83F >FFFD # NA <reserved-A83A>..<reserved-A83F>
# A874..A877 valid # 5.0 PHAGS-PA SINGLE HEAD MARK..PHAGS-PA MARK DOUBLE SHAD
A878..A87F >FFFD # NA <reserved-A878>..<reserved-A87F>
# A880..A8C4 valid # 5.1 SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VIRAMA
A8C5..A8CD >FFFD # NA <reserved-A8C5>..<reserved-A8CD>
# A8C5 valid # 9.0 SAURASHTRA SIGN CANDRABINDU
A8C6..A8CD >FFFD # NA <reserved-A8C6>..<reserved-A8CD>
# A8CE..A8CF valid # 5.1 SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA
# A8D0..A8D9 valid # 5.1 SAURASHTRA DIGIT ZERO..SAURASHTRA DIGIT NINE
A8DA..A8DF >FFFD # NA <reserved-A8DA>..<reserved-A8DF>
@ -5665,7 +5685,8 @@ FFFE..FFFF >FFFD # 1.1 <noncharacter-FFFE>..<noncharacte
# 10137..1013Fvalid # 4.0 AEGEAN WEIGHT BASE UNIT..AEGEAN MEASURE THIRD SUBUNIT
# 10140..1018Avalid # 4.1 GREEK ACROPHONIC ATTIC ONE QUARTER..GREEK ZERO SIGN
# 1018B..1018Cvalid # 7.0 GREEK ONE QUARTER SIGN..GREEK SINUSOID SIGN
1018D..1018F >FFFD # NA <reserved-1018D>..<reserved-1018F>
# 1018D..1018Evalid # 9.0 GREEK INDICTION SIGN..NOMISMA SIGN
1018F >FFFD # NA <reserved-1018F>
# 10190..1019Bvalid # 5.1 ROMAN SEXTANS SIGN..ROMAN CENTURIAL SIGN
1019C..1019F >FFFD # NA <reserved-1019C>..<reserved-1019F>
# 101A0 valid # 7.0 GREEK SYMBOL TAU RHO
@ -5743,7 +5764,46 @@ FFFE..FFFF >FFFD # 1.1 <noncharacter-FFFE>..<noncharacte
# 1044E..1049Dvalid # 4.0 DESERET SMALL LETTER OI..OSMANYA LETTER OO
1049E..1049F >FFFD # NA <reserved-1049E>..<reserved-1049F>
# 104A0..104A9valid # 4.0 OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE
104AA..104FF >FFFD # NA <reserved-104AA>..<reserved-104FF>
104AA..104AF >FFFD # NA <reserved-104AA>..<reserved-104AF>
104B0 >104D8 # 9.0 OSAGE CAPITAL LETTER A
104B1 >104D9 # 9.0 OSAGE CAPITAL LETTER AI
104B2 >104DA # 9.0 OSAGE CAPITAL LETTER AIN
104B3 >104DB # 9.0 OSAGE CAPITAL LETTER AH
104B4 >104DC # 9.0 OSAGE CAPITAL LETTER BRA
104B5 >104DD # 9.0 OSAGE CAPITAL LETTER CHA
104B6 >104DE # 9.0 OSAGE CAPITAL LETTER EHCHA
104B7 >104DF # 9.0 OSAGE CAPITAL LETTER E
104B8 >104E0 # 9.0 OSAGE CAPITAL LETTER EIN
104B9 >104E1 # 9.0 OSAGE CAPITAL LETTER HA
104BA >104E2 # 9.0 OSAGE CAPITAL LETTER HYA
104BB >104E3 # 9.0 OSAGE CAPITAL LETTER I
104BC >104E4 # 9.0 OSAGE CAPITAL LETTER KA
104BD >104E5 # 9.0 OSAGE CAPITAL LETTER EHKA
104BE >104E6 # 9.0 OSAGE CAPITAL LETTER KYA
104BF >104E7 # 9.0 OSAGE CAPITAL LETTER LA
104C0 >104E8 # 9.0 OSAGE CAPITAL LETTER MA
104C1 >104E9 # 9.0 OSAGE CAPITAL LETTER NA
104C2 >104EA # 9.0 OSAGE CAPITAL LETTER O
104C3 >104EB # 9.0 OSAGE CAPITAL LETTER OIN
104C4 >104EC # 9.0 OSAGE CAPITAL LETTER PA
104C5 >104ED # 9.0 OSAGE CAPITAL LETTER EHPA
104C6 >104EE # 9.0 OSAGE CAPITAL LETTER SA
104C7 >104EF # 9.0 OSAGE CAPITAL LETTER SHA
104C8 >104F0 # 9.0 OSAGE CAPITAL LETTER TA
104C9 >104F1 # 9.0 OSAGE CAPITAL LETTER EHTA
104CA >104F2 # 9.0 OSAGE CAPITAL LETTER TSA
104CB >104F3 # 9.0 OSAGE CAPITAL LETTER EHTSA
104CC >104F4 # 9.0 OSAGE CAPITAL LETTER TSHA
104CD >104F5 # 9.0 OSAGE CAPITAL LETTER DHA
104CE >104F6 # 9.0 OSAGE CAPITAL LETTER U
104CF >104F7 # 9.0 OSAGE CAPITAL LETTER WA
104D0 >104F8 # 9.0 OSAGE CAPITAL LETTER KHA
104D1 >104F9 # 9.0 OSAGE CAPITAL LETTER GHA
104D2 >104FA # 9.0 OSAGE CAPITAL LETTER ZA
104D3 >104FB # 9.0 OSAGE CAPITAL LETTER ZHA
104D4..104D7 >FFFD # NA <reserved-104D4>..<reserved-104D7>
# 104D8..104FBvalid # 9.0 OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA
104FC..104FF >FFFD # NA <reserved-104FC>..<reserved-104FF>
# 10500..10527valid # 7.0 ELBASAN LETTER A..ELBASAN LETTER KHE
10528..1052F >FFFD # NA <reserved-10528>..<reserved-1052F>
# 10530..10563valid # 7.0 CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW
@ -5943,7 +6003,8 @@ FFFE..FFFF >FFFD # 1.1 <noncharacter-FFFE>..<noncharacte
11212 >FFFD # NA <reserved-11212>
# 11213..11237valid # 7.0 KHOJKI LETTER NYA..KHOJKI SIGN SHADDA
# 11238..1123Dvalid # 7.0 KHOJKI DANDA..KHOJKI ABBREVIATION SIGN
1123E..1127F >FFFD # NA <reserved-1123E>..<reserved-1127F>
# 1123E valid # 9.0 KHOJKI SIGN SUKUN
1123F..1127F >FFFD # NA <reserved-1123F>..<reserved-1127F>
# 11280..11286valid # 8.0 MULTANI LETTER A..MULTANI LETTER GA
11287 >FFFD # NA <reserved-11287>
# 11288 valid # 8.0 MULTANI LETTER GHA
@ -5989,7 +6050,15 @@ FFFE..FFFF >FFFD # 1.1 <noncharacter-FFFE>..<noncharacte
# 11366..1136Cvalid # 7.0 COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX
1136D..1136F >FFFD # NA <reserved-1136D>..<reserved-1136F>
# 11370..11374valid # 7.0 COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA
11375..1147F >FFFD # NA <reserved-11375>..<reserved-1147F>
11375..113FF >FFFD # NA <reserved-11375>..<reserved-113FF>
# 11400..1144Avalid # 9.0 NEWA LETTER A..NEWA SIDDHI
# 1144B..1144Fvalid # 9.0 NEWA DANDA..NEWA ABBREVIATION SIGN
# 11450..11459valid # 9.0 NEWA DIGIT ZERO..NEWA DIGIT NINE
1145A >FFFD # NA <reserved-1145A>
# 1145B valid # 9.0 NEWA PLACEHOLDER MARK
1145C >FFFD # NA <reserved-1145C>
# 1145D valid # 9.0 NEWA INSERTION SIGN
1145E..1147F >FFFD # NA <reserved-1145E>..<reserved-1147F>
# 11480..114C5valid # 7.0 TIRHUTA ANJI..TIRHUTA GVANG
# 114C6 valid # 7.0 TIRHUTA ABBREVIATION SIGN
# 114C7 valid # 7.0 TIRHUTA OM
@ -6008,7 +6077,9 @@ FFFE..FFFF >FFFD # 1.1 <noncharacter-FFFE>..<noncharacte
# 11644 valid # 7.0 MODI SIGN HUVA
11645..1164F >FFFD # NA <reserved-11645>..<reserved-1164F>
# 11650..11659valid # 7.0 MODI DIGIT ZERO..MODI DIGIT NINE
1165A..1167F >FFFD # NA <reserved-1165A>..<reserved-1167F>
1165A..1165F >FFFD # NA <reserved-1165A>..<reserved-1165F>
# 11660..1166Cvalid # 9.0 MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT
1166D..1167F >FFFD # NA <reserved-1166D>..<reserved-1167F>
# 11680..116B7valid # 6.1 TAKRI LETTER A..TAKRI SIGN NUKTA
116B8..116BF >FFFD # NA <reserved-116B8>..<reserved-116BF>
# 116C0..116C9valid # 6.1 TAKRI DIGIT ZERO..TAKRI DIGIT NINE
@ -6058,7 +6129,24 @@ FFFE..FFFF >FFFD # 1.1 <noncharacter-FFFE>..<noncharacte
# 118FF valid # 7.0 WARANG CITI OM
11900..11ABF >FFFD # NA <reserved-11900>..<reserved-11ABF>
# 11AC0..11AF8valid # 7.0 PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
11AF9..11FFF >FFFD # NA <reserved-11AF9>..<reserved-11FFF>
11AF9..11BFF >FFFD # NA <reserved-11AF9>..<reserved-11BFF>
# 11C00..11C08valid # 9.0 BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L
11C09 >FFFD # NA <reserved-11C09>
# 11C0A..11C36valid # 9.0 BHAIKSUKI LETTER E..BHAIKSUKI VOWEL SIGN VOCALIC L
11C37 >FFFD # NA <reserved-11C37>
# 11C38..11C40valid # 9.0 BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN AVAGRAHA
# 11C41..11C45valid # 9.0 BHAIKSUKI DANDA..BHAIKSUKI GAP FILLER-2
11C46..11C4F >FFFD # NA <reserved-11C46>..<reserved-11C4F>
# 11C50..11C59valid # 9.0 BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE
# 11C5A..11C6Cvalid # 9.0 BHAIKSUKI NUMBER ONE..BHAIKSUKI HUNDREDS UNIT MARK
11C6D..11C6F >FFFD # NA <reserved-11C6D>..<reserved-11C6F>
# 11C70..11C71valid # 9.0 MARCHEN HEAD MARK..MARCHEN MARK SHAD
# 11C72..11C8Fvalid # 9.0 MARCHEN LETTER KA..MARCHEN LETTER A
11C90..11C91 >FFFD # NA <reserved-11C90>..<reserved-11C91>
# 11C92..11CA7valid # 9.0 MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA
11CA8 >FFFD # NA <reserved-11CA8>
# 11CA9..11CB6valid # 9.0 MARCHEN SUBJOINED LETTER YA..MARCHEN SIGN CANDRABINDU
11CB7..11FFF >FFFD # NA <reserved-11CB7>..<reserved-11FFF>
# 12000..1236Evalid # 5.0 CUNEIFORM SIGN A..CUNEIFORM SIGN ZUM
# 1236F..12398valid # 7.0 CUNEIFORM SIGN KAP ELAMITE..CUNEIFORM SIGN UM TIMES ME
# 12399 valid # 8.0 CUNEIFORM SIGN U U
@ -6106,7 +6194,13 @@ FFFE..FFFF >FFFD # 1.1 <noncharacter-FFFE>..<noncharacte
# 16F50..16F7Evalid # 6.1 MIAO LETTER NASALIZATION..MIAO VOWEL SIGN NG
16F7F..16F8E >FFFD # NA <reserved-16F7F>..<reserved-16F8E>
# 16F8F..16F9Fvalid # 6.1 MIAO TONE RIGHT..MIAO LETTER REFORMED TONE-8
16FA0..1AFFF >FFFD # NA <reserved-16FA0>..<reserved-1AFFF>
16FA0..16FDF >FFFD # NA <reserved-16FA0>..<reserved-16FDF>
# 16FE0 valid # 9.0 TANGUT ITERATION MARK
16FE1..16FFF >FFFD # NA <reserved-16FE1>..<reserved-16FFF>
# 17000..187ECvalid # 9.0 TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC
187ED..187FF >FFFD # NA <reserved-187ED>..<reserved-187FF>
# 18800..18AF2valid # 9.0 TANGUT COMPONENT-001..TANGUT COMPONENT-755
18AF3..1AFFF >FFFD # NA <reserved-18AF3>..<reserved-1AFFF>
# 1B000..1B001valid # 6.0 KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE
1B002..1BBFF >FFFD # NA <reserved-1B002>..<reserved-1BBFF>
# 1BC00..1BC6Avalid # 7.0 DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
@ -7176,12 +7270,62 @@ FFFE..FFFF >FFFD # 1.1 <noncharacter-FFFE>..<noncharacte
# 1DA9B..1DA9Fvalid # 8.0 SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6
1DAA0 >FFFD # NA <reserved-1DAA0>
# 1DAA1..1DAAFvalid # 8.0 SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16
1DAB0..1E7FF >FFFD # NA <reserved-1DAB0>..<reserved-1E7FF>
1DAB0..1DFFF >FFFD # NA <reserved-1DAB0>..<reserved-1DFFF>
# 1E000..1E006valid # 9.0 COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
1E007 >FFFD # NA <reserved-1E007>
# 1E008..1E018valid # 9.0 COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
1E019..1E01A >FFFD # NA <reserved-1E019>..<reserved-1E01A>
# 1E01B..1E021valid # 9.0 COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
1E022 >FFFD # NA <reserved-1E022>
# 1E023..1E024valid # 9.0 COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
1E025 >FFFD # NA <reserved-1E025>
# 1E026..1E02Avalid # 9.0 COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
1E02B..1E7FF >FFFD # NA <reserved-1E02B>..<reserved-1E7FF>
# 1E800..1E8C4valid # 7.0 MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON
1E8C5..1E8C6 >FFFD # NA <reserved-1E8C5>..<reserved-1E8C6>
# 1E8C7..1E8CFvalid # 7.0 MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE
# 1E8D0..1E8D6valid # 7.0 MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
1E8D7..1EDFF >FFFD # NA <reserved-1E8D7>..<reserved-1EDFF>
1E8D7..1E8FF >FFFD # NA <reserved-1E8D7>..<reserved-1E8FF>
1E900 >1E922 # 9.0 ADLAM CAPITAL LETTER ALIF
1E901 >1E923 # 9.0 ADLAM CAPITAL LETTER DAALI
1E902 >1E924 # 9.0 ADLAM CAPITAL LETTER LAAM
1E903 >1E925 # 9.0 ADLAM CAPITAL LETTER MIIM
1E904 >1E926 # 9.0 ADLAM CAPITAL LETTER BA
1E905 >1E927 # 9.0 ADLAM CAPITAL LETTER SINNYIIYHE
1E906 >1E928 # 9.0 ADLAM CAPITAL LETTER PE
1E907 >1E929 # 9.0 ADLAM CAPITAL LETTER BHE
1E908 >1E92A # 9.0 ADLAM CAPITAL LETTER RA
1E909 >1E92B # 9.0 ADLAM CAPITAL LETTER E
1E90A >1E92C # 9.0 ADLAM CAPITAL LETTER FA
1E90B >1E92D # 9.0 ADLAM CAPITAL LETTER I
1E90C >1E92E # 9.0 ADLAM CAPITAL LETTER O
1E90D >1E92F # 9.0 ADLAM CAPITAL LETTER DHA
1E90E >1E930 # 9.0 ADLAM CAPITAL LETTER YHE
1E90F >1E931 # 9.0 ADLAM CAPITAL LETTER WAW
1E910 >1E932 # 9.0 ADLAM CAPITAL LETTER NUN
1E911 >1E933 # 9.0 ADLAM CAPITAL LETTER KAF
1E912 >1E934 # 9.0 ADLAM CAPITAL LETTER YA
1E913 >1E935 # 9.0 ADLAM CAPITAL LETTER U
1E914 >1E936 # 9.0 ADLAM CAPITAL LETTER JIIM
1E915 >1E937 # 9.0 ADLAM CAPITAL LETTER CHI
1E916 >1E938 # 9.0 ADLAM CAPITAL LETTER HA
1E917 >1E939 # 9.0 ADLAM CAPITAL LETTER QAAF
1E918 >1E93A # 9.0 ADLAM CAPITAL LETTER GA
1E919 >1E93B # 9.0 ADLAM CAPITAL LETTER NYA
1E91A >1E93C # 9.0 ADLAM CAPITAL LETTER TU
1E91B >1E93D # 9.0 ADLAM CAPITAL LETTER NHA
1E91C >1E93E # 9.0 ADLAM CAPITAL LETTER VA
1E91D >1E93F # 9.0 ADLAM CAPITAL LETTER KHA
1E91E >1E940 # 9.0 ADLAM CAPITAL LETTER GBE
1E91F >1E941 # 9.0 ADLAM CAPITAL LETTER ZAL
1E920 >1E942 # 9.0 ADLAM CAPITAL LETTER KPO
1E921 >1E943 # 9.0 ADLAM CAPITAL LETTER SHA
# 1E922..1E94Avalid # 9.0 ADLAM SMALL LETTER ALIF..ADLAM NUKTA
1E94B..1E94F >FFFD # NA <reserved-1E94B>..<reserved-1E94F>
# 1E950..1E959valid # 9.0 ADLAM DIGIT ZERO..ADLAM DIGIT NINE
1E95A..1E95D >FFFD # NA <reserved-1E95A>..<reserved-1E95D>
# 1E95E..1E95Fvalid # 9.0 ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK
1E960..1EDFF >FFFD # NA <reserved-1E960>..<reserved-1EDFF>
1EE00 >0627 # 6.1 ARABIC MATHEMATICAL ALEF
1EE01 >0628 # 6.1 ARABIC MATHEMATICAL BEH
1EE02 >062C # 6.1 ARABIC MATHEMATICAL JEEM
@ -7468,7 +7612,8 @@ FFFE..FFFF >FFFD # 1.1 <noncharacter-FFFE>..<noncharacte
# 1F18E..1F18Fvalid # 6.0 NEGATIVE SQUARED AB..NEGATIVE SQUARED WC
1F190 >0064 006A # 5.2 SQUARE DJ
# 1F191..1F19Avalid # 6.0 SQUARED CL..SQUARED VS
1F19B..1F1E5 >FFFD # NA <reserved-1F19B>..<reserved-1F1E5>
# 1F19B..1F1ACvalid # 9.0 SQUARED THREE D..SQUARED VOD
1F1AD..1F1E5 >FFFD # NA <reserved-1F1AD>..<reserved-1F1E5>
# 1F1E6..1F1FFvalid # 6.0 REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z
1F200 >307B 304B # 5.2 SQUARE HIRAGANA HOKA
1F201 >30B3 30B3 # 6.0 SQUARED KATAKANA KOKO
@ -7517,7 +7662,8 @@ FFFE..FFFF >FFFD # 1.1 <noncharacter-FFFE>..<noncharacte
1F238 >7533 # 6.0 SQUARED CJK UNIFIED IDEOGRAPH-7533
1F239 >5272 # 6.0 SQUARED CJK UNIFIED IDEOGRAPH-5272
1F23A >55B6 # 6.0 SQUARED CJK UNIFIED IDEOGRAPH-55B6
1F23B..1F23F >FFFD # NA <reserved-1F23B>..<reserved-1F23F>
1F23B >914D # 9.0 SQUARED CJK UNIFIED IDEOGRAPH-914D
1F23C..1F23F >FFFD # NA <reserved-1F23C>..<reserved-1F23F>
1F240 >3014 672C 3015 #5.2 TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C
1F241 >3014 4E09 3015 #5.2 TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-4E09
1F242 >3014 4E8C 3015 #5.2 TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-4E8C
@ -7566,9 +7712,9 @@ FFFE..FFFF >FFFD # 1.1 <noncharacter-FFFE>..<noncharacte
# 1F54B..1F54Fvalid # 8.0 KAABA..BOWL OF HYGIEIA
# 1F550..1F567valid # 6.0 CLOCK FACE ONE OCLOCK..CLOCK FACE TWELVE-THIRTY
# 1F568..1F579valid # 7.0 RIGHT SPEAKER..JOYSTICK
1F57A >FFFD # NA <reserved-1F57A>
# 1F57A valid # 9.0 MAN DANCING
# 1F57B..1F5A3valid # 7.0 LEFT HAND TELEPHONE RECEIVER..BLACK DOWN POINTING BACKHAND INDEX
1F5A4 >FFFD # NA <reserved-1F5A4>
# 1F5A4 valid # 9.0 BLACK HEART
# 1F5A5..1F5FAvalid # 7.0 DESKTOP COMPUTER..WORLD MAP
# 1F5FB..1F5FFvalid # 6.0 MOUNT FUJI..MOYAI
# 1F600 valid # 6.1 GRINNING FACE
@ -7600,11 +7746,13 @@ FFFE..FFFF >FFFD # 1.1 <noncharacter-FFFE>..<noncharacte
# 1F680..1F6C5valid # 6.0 ROCKET..LEFT LUGGAGE
# 1F6C6..1F6CFvalid # 7.0 TRIANGLE WITH ROUNDED CORNERS..BED
# 1F6D0 valid # 8.0 PLACE OF WORSHIP
1F6D1..1F6DF >FFFD # NA <reserved-1F6D1>..<reserved-1F6DF>
# 1F6D1..1F6D2valid # 9.0 OCTAGONAL SIGN..SHOPPING TROLLEY
1F6D3..1F6DF >FFFD # NA <reserved-1F6D3>..<reserved-1F6DF>
# 1F6E0..1F6ECvalid # 7.0 HAMMER AND WRENCH..AIRPLANE ARRIVING
1F6ED..1F6EF >FFFD # NA <reserved-1F6ED>..<reserved-1F6EF>
# 1F6F0..1F6F3valid # 7.0 SATELLITE..PASSENGER SHIP
1F6F4..1F6FF >FFFD # NA <reserved-1F6F4>..<reserved-1F6FF>
# 1F6F4..1F6F6valid # 9.0 SCOOTER..CANOE
1F6F7..1F6FF >FFFD # NA <reserved-1F6F7>..<reserved-1F6FF>
# 1F700..1F773valid # 6.0 ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
1F774..1F77F >FFFD # NA <reserved-1F774>..<reserved-1F77F>
# 1F780..1F7D4valid # 7.0 BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR
@ -7620,9 +7768,21 @@ FFFE..FFFF >FFFD # 1.1 <noncharacter-FFFE>..<noncharacte
# 1F890..1F8ADvalid # 7.0 LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS
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>
# 1F919..1F91Evalid # 9.0 CALL ME HAND..HAND WITH INDEX AND MIDDLE FINGERS CROSSED
1F91F >FFFD # NA <reserved-1F91F>
# 1F920..1F927valid # 9.0 FACE WITH COWBOY HAT..SNEEZING FACE
1F928..1F92F >FFFD # NA <reserved-1F928>..<reserved-1F92F>
# 1F930 valid # 9.0 PREGNANT WOMAN
1F931..1F932 >FFFD # NA <reserved-1F931>..<reserved-1F932>
# 1F933..1F93Evalid # 9.0 SELFIE..HANDBALL
1F93F >FFFD # NA <reserved-1F93F>
# 1F940..1F94Bvalid # 9.0 WILTED FLOWER..MARTIAL ARTS UNIFORM
1F94C..1F94F >FFFD # NA <reserved-1F94C>..<reserved-1F94F>
# 1F950..1F95Evalid # 9.0 CROISSANT..PANCAKES
1F95F..1F97F >FFFD # NA <reserved-1F95F>..<reserved-1F97F>
# 1F980..1F984valid # 8.0 CRAB..UNICORN FACE
1F985..1F9BF >FFFD # NA <reserved-1F985>..<reserved-1F9BF>
# 1F985..1F991valid # 9.0 EAGLE..SQUID
1F992..1F9BF >FFFD # NA <reserved-1F992>..<reserved-1F9BF>
# 1F9C0 valid # 8.0 CHEESE WEDGE
1F9C1..1FFFD >FFFD # NA <reserved-1F9C1>..<reserved-1FFFD>
1FFFE..1FFFF >FFFD # 2.0 <noncharacter-1FFFE>..<noncharacter-1FFFF>

3201
icu4c/source/data/unidata/ppucd.txt
View file

File diff suppressed because it is too large Load diff

104
icu4c/source/i18n/collationfcd.cpp
View file

@ -1,5 +1,5 @@
/*
* Copyright (C) 1999-2015, International Business Machines
* Copyright (C) 1999-2016, International Business Machines
* Corporation and others. All Rights Reserved.
*
* file name: collationfcd.cpp
@ -20,27 +20,27 @@ const uint8_t CollationFCD::lcccIndex[2048]={
0,0,0,0,0,0,0,0,1,1,2,3,0,0,0,0,
0,0,0,0,4,0,0,0,0,0,0,0,5,6,7,0,
8,0,9,0xa,0,0,0xb,0xc,0xd,0xe,0xf,0,0,0,0,0x10,
0x11,0x12,0x13,0,0,0,0,0x14,0,0x15,0x16,0,0,0x15,0x17,0,
0,0x15,0x17,0,0,0x15,0x17,0,0,0x15,0x17,0,0,0,0x17,0,
0,0,0x18,0,0,0x15,0x17,0,0,0,0x17,0,0,0,0x19,0,
0,0x1a,0x1b,0,0,0x1c,0x1b,0,0x1c,0x1d,0,0x1e,0x1f,0,0x20,0,
0,0x21,0,0,0x17,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0x22,0,0,0,0,0,
0x11,0x12,0x13,0,0,0,0x14,0x15,0,0x16,0x17,0,0,0x16,0x18,0,
0,0x16,0x18,0,0,0x16,0x18,0,0,0x16,0x18,0,0,0,0x18,0,
0,0,0x19,0,0,0x16,0x18,0,0,0,0x18,0,0,0,0x1a,0,
0,0x1b,0x1c,0,0,0x1d,0x1c,0,0x1d,0x1e,0,0x1f,0x20,0,0x21,0,
0,0x22,0,0,0x18,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0x23,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0x23,0x23,0,0,0,0,0x24,0,
0,0,0,0,0,0x25,0,0,0,0x13,0,0,0,0,0,0,
0x26,0,0,0x27,0,0x28,0,0,0,0x23,0x29,0x10,0,0x2a,0,0x2b,
0,0x2c,0,0,0,0,0x2d,0x2e,0,0,0,0,0,0,1,0x2f,
0,0,0,0,0,0,0,0,0x24,0x24,0,0,0,0,0x25,0,
0,0,0,0,0,0x26,0,0,0,0x13,0,0,0,0,0,0,
0x27,0,0,0x28,0,0x29,0,0,0,0x24,0x2a,0x10,0,0x2b,0,0x2c,
0,0x2d,0,0,0,0,0x2e,0x2f,0,0,0,0,0,0,1,0x30,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0x30,0x31,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0x31,0x32,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0x32,0,0,0,0x33,0,0,0,1,
0,0,0,0,0,0,0,0x33,0,0,0,0x34,0,0,0,1,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0x34,0,0,0x35,0,0,0,0,0,0,0,0,0,0,0,
0,0x35,0,0,0x36,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
@ -99,9 +99,9 @@ const uint8_t CollationFCD::lcccIndex[2048]={
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0x36,0x37,0,0,0x38,0,0,0,0,0,0,0,0,
0x20,0,0,0,0,0,0x29,0x39,0,0x3a,0x3b,0,0,0x3b,0x3c,0,
0,0,0,0,0,0x3d,0x3e,0x3f,0,0,0,0,0,0,0,0x17,
0,0,0,0x37,0x38,0,0,0x39,0,0,0,0,0,0,0,0,
0x21,0,0,0,0,0,0x2a,0x3a,0,0x3b,0x3c,0,0,0x3c,0x3d,0,
0,0,0,0,0,0x3e,0x3f,0x40,0,0,0,0,0,0,0,0x18,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
@ -124,7 +124,7 @@ const uint8_t CollationFCD::lcccIndex[2048]={
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0x40,0x41,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0x41,0x42,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
@ -141,17 +141,17 @@ const uint8_t CollationFCD::lcccIndex[2048]={
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0x42,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0x43,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,3,0,0,0,0,0,0,0,0,0,0,0,0,0,0
};
const uint32_t CollationFCD::lcccBits[67]={
const uint32_t CollationFCD::lcccBits[68]={
0,0xffffffff,0xffff7fff,0xffff,0xf8,0xfffe0000,0xbfffffff,0xb6,0x7ff0000,0xfffff800,0x10000,0x9fc00000,0x3d9f,0x20000,0xffff0000,0x7ff,
0xff800,0xfbc00000,0x3eef,0xe000000,0xfffffff8,0x10000000,0x1e2000,0x2000,0x602000,0x400,0x7000000,0xf00,0x3000000,0x2a00000,0x3c3e0000,0xdf,
0x40,0x6800000,0xe0000000,0x100000,0x20040000,0x200,0x1800000,0x9fe00001,0x3fff0000,0x10,0xc00,0xc0040,0x800000,0xfff70000,0x31021fd,0xf03fffff,
0x1fff0000,0x1ffe2,0x38000,0x80000000,0xfc00,0x6000000,0x3ff08000,0xc0000000,0x30000,0x3ffff,0x3800,0x80000,1,0xc19d0000,2,0x400000,
0x4000035,0x4108000,0x40000000
0xff800,0xfbc00000,0x3eef,0xe000000,0xfff00000,0xfffffffb,0x10000000,0x1e2000,0x2000,0x602000,0x400,0x7000000,0xf00,0x3000000,0x2a00000,0x3c3e0000,
0xdf,0x40,0x6800000,0xe0000000,0x100000,0x20040000,0x200,0x1800000,0x9fe00001,0x3fff0000,0x10,0xc00,0xc0040,0x800000,0xfff70000,0x31021fd,
0xf83fffff,0x1fff0000,0x1ffe2,0x38000,0x80000000,0xfc00,0x6000000,0x3ff08000,0xc0000000,0x30000,0x3ffff,0x3800,0x80000,1,0xc19d0000,2,
0x400000,0x40000b5,0x5108000,0x40000000
};
const uint8_t CollationFCD::tcccIndex[2048]={
@ -159,27 +159,27 @@ const uint8_t CollationFCD::tcccIndex[2048]={
0xb,0xc,0,0,0,0,0,0,1,1,0xd,0xe,0xf,0x10,0x11,0,
0x12,0x13,0x14,0x15,0x16,0,0x17,0x18,0,0,0,0,0x19,0x1a,0x1b,0,
0x1c,0x1d,0x1e,0x1f,0,0,0x20,0x21,0x22,0x23,0x24,0,0,0,0,0x25,
0x26,0x27,0x28,0,0,0,0,0x29,0,0x2a,0x2b,0,0,0x2c,0x2d,0,
0,0x2e,0x2f,0,0,0x2c,0x30,0,0,0x2c,0x31,0,0,0,0x30,0,
0,0,0x32,0,0,0x2c,0x30,0,0,0,0x30,0,0,0,0x33,0,
0,0x34,0x35,0,0,0x36,0x35,0,0x36,0x37,0,0x38,0x39,0,0x3a,0,
0,0x3b,0,0,0x30,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0x3c,0,0,0,0,0,
0x26,0x27,0x28,0,0,0,0x29,0x2a,0,0x2b,0x2c,0,0,0x2d,0x2e,0,
0,0x2f,0x30,0,0,0x2d,0x31,0,0,0x2d,0x32,0,0,0,0x31,0,
0,0,0x33,0,0,0x2d,0x31,0,0,0,0x31,0,0,0,0x34,0,
0,0x35,0x36,0,0,0x37,0x36,0,0x37,0x38,0,0x39,0x3a,0,0x3b,0,
0,0x3c,0,0,0x31,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0x3d,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0x3d,0x3d,0,0,0,0,0x3e,0,
0,0,0,0,0,0x3f,0,0,0,0x28,0,0,0,0,0,0,
0x40,0,0,0x41,0,0x42,0,0,0,0x3d,0x43,0x25,0,0x44,0,0x45,
0,0x46,0,0,0,0,0x47,0x48,0,0,0,0,0,0,1,0x49,
1,1,1,1,0x4a,1,1,0x4b,0x4c,1,0x4d,0x4e,1,0x4f,0x50,0x51,
0,0,0,0,0,0,0x52,0x53,0,0x54,0,0,0x55,0x56,0x57,0,
0x58,0x59,0x5a,0x5b,0x5c,0x5d,0,0x5e,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0x3e,0x3e,0,0,0,0,0x3f,0,
0,0,0,0,0,0x40,0,0,0,0x28,0,0,0,0,0,0,
0x41,0,0,0x42,0,0x43,0,0,0,0x3e,0x44,0x25,0,0x45,0,0x46,
0,0x47,0,0,0,0,0x48,0x49,0,0,0,0,0,0,1,0x4a,
1,1,1,1,0x4b,1,1,0x4c,0x4d,1,0x4e,0x4f,1,0x50,0x51,0x52,
0,0,0,0,0,0,0x53,0x54,0,0x55,0,0,0x56,0x57,0x58,0,
0x59,0x5a,0x5b,0x5c,0x5d,0x5e,0,0x5f,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0x2c,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0x5f,0,0,0,0x60,0,0,0,1,
0,0,0,0,0,0,0x2d,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0x60,0,0,0,0x61,0,0,0,1,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0x61,0x62,0x63,0x64,0x62,0x63,0x65,0,0,0,0,0,0,0,0,
0,0x62,0x63,0x64,0x65,0x63,0x64,0x66,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
@ -238,9 +238,9 @@ const uint8_t CollationFCD::tcccIndex[2048]={
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0x66,0x67,0,0,0x68,0,0,0,0,0,0,0,0,
0x3a,0,0,0,0,0,0x43,0x69,0,0x6a,0x6b,0,0,0x6b,0x6c,0,
0,0,0,0,0,0x6d,0x6e,0x6f,0,0,0,0,0,0,0,0x30,
0,0,0,0x67,0x68,0,0,0x69,0,0,0,0,0,0,0,0,
0x3b,0,0,0,0,0,0x44,0x6a,0,0x6b,0x6c,0,0,0x6c,0x6d,0,
0,0,0,0,0,0x6e,0x6f,0x70,0,0,0,0,0,0,0,0x31,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
@ -263,7 +263,7 @@ const uint8_t CollationFCD::tcccIndex[2048]={
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0x70,0x71,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0x71,0x72,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
@ -280,20 +280,20 @@ const uint8_t CollationFCD::tcccIndex[2048]={
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0x3c,0x72,0x73,0,0,0,0,0,
0,0,0,0,0,0,0,0,0x3d,0x73,0x74,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0xe,0,0,0,0,0,0,0,0,0,0,0,0,0,0
};
const uint32_t CollationFCD::tcccBits[116]={
const uint32_t CollationFCD::tcccBits[117]={
0,0xffffffff,0x3e7effbf,0xbe7effbf,0xfffcffff,0x7ef1ff3f,0xfff3f1f8,0x7fffff3f,0x18003,0xdfffe000,0xff31ffcf,0xcfffffff,0xfffc0,0xffff7fff,0xffff,0x1d760,
0x1fc00,0x187c00,0x200708b,0x2000000,0x708b0000,0xc00000,0xf8,0xfccf0006,0x33ffcfc,0xfffe0000,0xbfffffff,0xb6,0x7ff0000,0x7c,0xfffff800,0x10000,
0x9fc80005,0x3d9f,0x20000,0xffff0000,0x7ff,0xff800,0xfbc00000,0x3eef,0xe000000,0xfffffff8,0x10120200,0xff1e2000,0x10000000,0xb0002000,0x10480000,0x4e002000,
0x2000,0x30002000,0x602100,0x24000400,0x7000000,0xf00,0x3000000,0x2a00000,0x3d7e0000,0xdf,0x40,0x6800000,0xe0000000,0x100000,0x20040000,0x200,
0x1800000,0x9fe00001,0x3fff0000,0x10,0xc00,0xc0040,0x800000,0xfff70000,0x31021fd,0xf03fffff,0xbffffff,0x3ffffff,0x3f3fffff,0xaaff3f3f,0x3fffffff,0x1fdfffff,
0xefcfffde,0x1fdc7fff,0x1fff0000,0x1ffe2,0x800,0xc000000,0x4000,0xe000,0x1210,0x50,0x292,0x333e005,0x333,0xf000,0x3c0f,0x38000,
0x80000000,0xfc00,0x55555000,0x36db02a5,0x46100000,0x47900000,0x3ff08000,0xc0000000,0x30000,0x3ffff,0x3800,0x80000,1,0xc19d0000,2,0x400000,
0x4000035,0x4108000,0x5f7ffc00,0x7fdb
0x9fc80005,0x3d9f,0x20000,0xffff0000,0x7ff,0xff800,0xfbc00000,0x3eef,0xe000000,0xfff00000,0xfffffffb,0x10120200,0xff1e2000,0x10000000,0xb0002000,0x10480000,
0x4e002000,0x2000,0x30002000,0x602100,0x24000400,0x7000000,0xf00,0x3000000,0x2a00000,0x3d7e0000,0xdf,0x40,0x6800000,0xe0000000,0x100000,0x20040000,
0x200,0x1800000,0x9fe00001,0x3fff0000,0x10,0xc00,0xc0040,0x800000,0xfff70000,0x31021fd,0xf83fffff,0xbffffff,0x3ffffff,0x3f3fffff,0xaaff3f3f,0x3fffffff,
0x1fdfffff,0xefcfffde,0x1fdc7fff,0x1fff0000,0x1ffe2,0x800,0xc000000,0x4000,0xe000,0x1210,0x50,0x292,0x333e005,0x333,0xf000,0x3c0f,
0x38000,0x80000000,0xfc00,0x55555000,0x36db02a5,0x46100000,0x47900000,0x3ff08000,0xc0000000,0x30000,0x3ffff,0x3800,0x80000,1,0xc19d0000,2,
0x400000,0x40000b5,0x5108000,0x5f7ffc00,0x7fdb
};
U_NAMESPACE_END

2
icu4c/source/layout/LELanguages.h
View file

@ -5,7 +5,7 @@
* WARNING: THIS FILE IS MACHINE GENERATED. DO NOT HAND EDIT IT UNLESS
* YOU REALLY KNOW WHAT YOU'RE DOING.
*
* Generated on: 04/08/2016 02:00:11 PM PDT
* Generated on: 05/10/2016 11:13:24 AM PDT
*/
#ifndef __LELANGUAGES_H

2
icu4c/source/layout/LEScripts.h
View file

@ -5,7 +5,7 @@
* WARNING: THIS FILE IS MACHINE GENERATED. DO NOT HAND EDIT IT UNLESS
* YOU REALLY KNOW WHAT YOU'RE DOING.
*
* Generated on: 04/08/2016 02:00:11 PM PDT
* Generated on: 05/10/2016 11:13:24 AM PDT
*/
#ifndef __LESCRIPTS_H

4
icu4c/source/layout/ScriptAndLanguageTags.cpp
View file

@ -5,7 +5,7 @@
* WARNING: THIS FILE IS MACHINE GENERATED. DO NOT HAND EDIT IT UNLESS
* YOU REALLY KNOW WHAT YOU'RE DOING.
*
* Generated on: 04/08/2016 02:00:11 PM PDT
* Generated on: 05/10/2016 11:13:24 AM PDT
*/
#include "LETypes.h"
@ -169,7 +169,7 @@ const LETag OpenTypeLayoutEngine::scriptTags[] = {
shrdScriptTag, /* 'shrd' (SHARADA) */
soraScriptTag, /* 'sora' (SORA_SOMPENG) */
takrScriptTag, /* 'takr' (TAKRI) */
tangScriptTag, /* 'tang' (TANG) */
tangScriptTag, /* 'tang' (TANGUT) */
woleScriptTag, /* 'wole' (WOLE) */
hluwScriptTag, /* 'hluw' (ANATOLIAN_HIEROGLYPHS) */
khojScriptTag, /* 'khoj' (KHOJKI) */

4
icu4c/source/layout/ScriptAndLanguageTags.h
View file

@ -5,7 +5,7 @@
* WARNING: THIS FILE IS MACHINE GENERATED. DO NOT HAND EDIT IT UNLESS
* YOU REALLY KNOW WHAT YOU'RE DOING.
*
* Generated on: 04/08/2016 02:00:11 PM PDT
* Generated on: 05/10/2016 11:13:24 AM PDT
*/
#ifndef __SCRIPTANDLANGUAGES_H
@ -183,7 +183,7 @@ const LETag nshuScriptTag = 0x6E736875; /* 'nshu' (NSHU) */
const LETag shrdScriptTag = 0x73687264; /* 'shrd' (SHARADA) */
const LETag soraScriptTag = 0x736F7261; /* 'sora' (SORA_SOMPENG) */
const LETag takrScriptTag = 0x74616B72; /* 'takr' (TAKRI) */
const LETag tangScriptTag = 0x74616E67; /* 'tang' (TANG) */
const LETag tangScriptTag = 0x74616E67; /* 'tang' (TANGUT) */
const LETag woleScriptTag = 0x776F6C65; /* 'wole' (WOLE) */
const LETag hluwScriptTag = 0x686C7577; /* 'hluw' (ANATOLIAN_HIEROGLYPHS) */
const LETag khojScriptTag = 0x6B686F6A; /* 'khoj' (KHOJKI) */

2
icu4c/source/test/cintltst/cucdapi.c
View file

@ -401,7 +401,7 @@ void TestUScriptCodeAPI(){
"Loma", "Mende_Kikakui", "Meroitic_Cursive",
"Old_North_Arabian", "Nabataean", "Palmyrene", "Khudawadi", "Warang_Citi",
/* new in ICU 4.8 */
"Afak", "Jurc", "Mro", "Nshu", "Sharada", "Sora_Sompeng", "Takri", "Tang", "Wole",
"Afak", "Jurc", "Mro", "Nshu", "Sharada", "Sora_Sompeng", "Takri", "Tangut", "Wole",
/* new in ICU 49 */
"Anatolian_Hieroglyphs", "Khojki", "Tirhuta",
/* new in ICU 52 */

162
icu4c/source/test/intltest/rbbitst.cpp
View file

@ -1966,6 +1966,7 @@ private:
UnicodeSet *fCRLFSet;
UnicodeSet *fControlSet;
UnicodeSet *fExtendSet;
UnicodeSet *fZWJSet;
UnicodeSet *fRegionalIndicatorSet;
UnicodeSet *fPrependSet;
UnicodeSet *fSpacingSet;
@ -1975,11 +1976,11 @@ private:
UnicodeSet *fLVSet;
UnicodeSet *fLVTSet;
UnicodeSet *fHangulSet;
UnicodeSet *fAnySet;
UnicodeSet *fEmojiModifierSet;
UnicodeSet *fEmojiBaseSet;
UnicodeSet *fZWJSet;
UnicodeSet *fEmojiModifierSet;
UnicodeSet *fGAZSet;
UnicodeSet *fEBGSet; // ***new
UnicodeSet *fAnySet;
const UnicodeString *fText;
};
@ -1991,9 +1992,11 @@ RBBICharMonkey::RBBICharMonkey() {
fText = NULL;
fCRLFSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\r\\n]"), status);
fControlSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[[\\p{Grapheme_Cluster_Break = Control}]-[:Block=Tags:]]"), status);
fExtendSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[[\\p{Grapheme_Cluster_Break = Extend}][:Block=Tags:]]"), status);
fRegionalIndicatorSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Grapheme_Cluster_Break = Regional_Indicator}]"), status);
fControlSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[[\\p{Grapheme_Cluster_Break = Control}]]"), status);
fExtendSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[[\\p{Grapheme_Cluster_Break = Extend}]]"), status);
fZWJSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Grapheme_Cluster_Break = ZWJ}]"), status);
fRegionalIndicatorSet =
new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Grapheme_Cluster_Break = Regional_Indicator}]"), status);
fPrependSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Grapheme_Cluster_Break = Prepend}]"), status);
fSpacingSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Grapheme_Cluster_Break = SpacingMark}]"), status);
fLSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Grapheme_Cluster_Break = L}]"), status);
@ -2007,21 +2010,14 @@ RBBICharMonkey::RBBICharMonkey() {
fHangulSet->addAll(*fTSet);
fHangulSet->addAll(*fLVSet);
fHangulSet->addAll(*fLVTSet);
fAnySet = new UnicodeSet(0, 0x10ffff);
fEmojiBaseSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Grapheme_Cluster_Break = EB}]"), status);
fEmojiModifierSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Grapheme_Cluster_Break = EM}]"), status);
fGAZSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Grapheme_Cluster_Break = GAZ}]"), status);
fEBGSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Grapheme_Cluster_Break = EBG}]"), status);
fAnySet = new UnicodeSet(0, 0x10ffff);
fEmojiBaseSet = new UnicodeSet(UnicodeString(
"[\\u261D\\u26F9\\u270A-\\u270D\\U0001F385\\U0001F3C3-\\U0001F3C4\\U0001F3CA-\\U0001F3CB\\U0001F442-\\U0001F443"
"\\U0001F446-\\U0001F450\\U0001F466-\\U0001F469\\U0001F46E\\U0001F470-\\U0001F478\\U0001F47C\\U0001F481-\\U0001F483"
"\\U0001F485-\\U0001F487\\U0001F4AA\\U0001F575\\U0001F590\\U0001F595-\\U0001F596\\U0001F645-\\U0001F647"
"\\U0001F64B-\\U0001F64F\\U0001F6A3\\U0001F6B4-\\U0001F6B6\\U0001F6C0\\U0001F918]"), status);
fEmojiModifierSet = new UnicodeSet(0x0001F3FB, 0x0001F3FF);
fZWJSet = new UnicodeSet(0x200D, 0x200D);
fGAZSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\U0001F466-\\U0001F469\\U0001F48B\\U0001F5E8\\u2764]"), status);
fSets = new UVector(status);
fSets = new UVector(status);
fSets->addElement(fCRLFSet, status);
fSets->addElement(fControlSet, status);
fSets->addElement(fExtendSet, status);
@ -2036,6 +2032,7 @@ RBBICharMonkey::RBBICharMonkey() {
fSets->addElement(fEmojiModifierSet, status);
fSets->addElement(fZWJSet, status);
fSets->addElement(fGAZSet, status);
fSets->addElement(fEBGSet, status);
if (U_FAILURE(status)) {
deferredStatus = status;
}
@ -2149,7 +2146,7 @@ int32_t RBBICharMonkey::next(int32_t prevPos) {
continue;
}
// Rule (GB9) x Extend
// Rule (GB9) x (Extend | ZWJ)
if (fExtendSet->contains(c2) || fZWJSet->contains(c2)) {
continue;
}
@ -2164,17 +2161,17 @@ int32_t RBBICharMonkey::next(int32_t prevPos) {
continue;
}
// Rule (GB9c) Emoji_Base x Emoji_Modifier
if ((fEmojiBaseSet->contains(c1) || fGAZSet->contains(c1)) && fEmojiModifierSet->contains(c2)) {
// Rule (GB10) (Emoji_Base | EBG) x Emoji_Modifier
if ((fEmojiBaseSet->contains(c1) || fEBGSet->contains(c1)) && fEmojiModifierSet->contains(c2)) {
continue;
}
// Rule (GB9d) ZWJ x Glue_After_Zwj
if (fZWJSet->contains(c1) && fGAZSet->contains(c2)) {
// Rule (GB11) ZWJ x (Glue_After_ZWJ | EBG)
if (fZWJSet->contains(c1) && (fGAZSet->contains(c2) || fEBGSet->contains(c2))) {
continue;
}
// Rule (GB10) Any <break> Any
// Rule (GB999) Any <break> Any
break;
}
@ -2208,6 +2205,7 @@ RBBICharMonkey::~RBBICharMonkey() {
delete fEmojiModifierSet;
delete fZWJSet;
delete fGAZSet;
delete fEBGSet;
}
//------------------------------------------------------------------------------------------
@ -2233,8 +2231,6 @@ private:
UnicodeSet *fKatakanaSet;
UnicodeSet *fHebrew_LetterSet;
UnicodeSet *fALetterSet;
// TODO(jungshik): Do we still need this change?
// UnicodeSet *fALetterSet; // matches ALetterPlus in word.txt
UnicodeSet *fSingle_QuoteSet;
UnicodeSet *fDouble_QuoteSet;
UnicodeSet *fMidNumLetSet;
@ -2245,10 +2241,11 @@ private:
UnicodeSet *fOtherSet;
UnicodeSet *fExtendSet;
UnicodeSet *fExtendNumLetSet;
UnicodeSet *fDictionaryCjkSet;
UnicodeSet *fDictionarySet;
UnicodeSet *fEBaseSet;
UnicodeSet *fEBGSet;
UnicodeSet *fEModifierSet;
UnicodeSet *fZWSSet;
UnicodeSet *fZWJSet;
UnicodeSet *fGAZSet;
const UnicodeString *fText;
@ -2261,48 +2258,34 @@ RBBIWordMonkey::RBBIWordMonkey()
fSets = new UVector(status);
fCRSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = CR}]"), status);
fLFSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = LF}]"), status);
fNewlineSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = Newline}]"), status);
fDictionaryCjkSet= new UnicodeSet("[[\\uac00-\\ud7a3][:Han:][:Hiragana:][:Katakana:]]", status);
// Exclude Hangul syllables from ALetterSet during testing.
// Leave CJK dictionary characters out from the monkey tests!
#if 0
fALetterSet = new UnicodeSet("[\\p{Word_Break = ALetter}"
"[\\p{Line_Break = Complex_Context}"
"-\\p{Grapheme_Cluster_Break = Extend}"
"-\\p{Grapheme_Cluster_Break = Control}"
"]]",
status);
#endif
fRegionalIndicatorSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = Regional_Indicator}]"), status);
fCRSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = CR}]"), status);
fLFSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = LF}]"), status);
fNewlineSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = Newline}]"), status);
fKatakanaSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = Katakana}]"), status);
fRegionalIndicatorSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = Regional_Indicator}]"), status);
fHebrew_LetterSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = Hebrew_Letter}]"), status);
fALetterSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = ALetter}]"), status);
fALetterSet->removeAll(*fDictionaryCjkSet);
fSingle_QuoteSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = Single_Quote}]"), status);
fDouble_QuoteSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = Double_Quote}]"), status);
fMidNumLetSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = MidNumLet}]"), status);
fMidLetterSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = MidLetter}]"), status);
fMidNumSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = MidNum}]"), status);
// TODO: this set used to contain [\\uff10-\\uff19] (fullwidth digits), but this breaks the test
// we should figure out why
fNumericSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = Numeric}]"), status);
fFormatSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = Format}]"), status);
fExtendNumLetSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = ExtendNumLet}]"), status);
fExtendSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = Extend}]"), status);
fEBaseSet = new UnicodeSet(UnicodeString(
"[\\u261D\\u26F9\\u270A-\\u270D\\U0001F385\\U0001F3C3-\\U0001F3C4\\U0001F3CA-\\U0001F3CB\\U0001F442-\\U0001F443"
"\\U0001F446-\\U0001F450\\U0001F466-\\U0001F469\\U0001F46E\\U0001F470-\\U0001F478\\U0001F47C\\U0001F481-\\U0001F483"
"\\U0001F485-\\U0001F487\\U0001F4AA\\U0001F575\\U0001F590\\U0001F595-\\U0001F596\\U0001F645-\\U0001F647"
"\\U0001F64B-\\U0001F64F\\U0001F6A3\\U0001F6B4-\\U0001F6B6\\U0001F6C0\\U0001F918]"), status);
fEBaseSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = EB}]"), status);
fEBGSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = EBG}]"), status);
fEModifierSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = EM}]"), status);
fZWJSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = ZWJ}]"), status);
fGAZSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Word_Break = GAZ}]"), status);
fEModifierSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\U0001F3FB-\\U0001F3FF]"), status);
fZWSSet = new UnicodeSet((UChar32)0x200D, (UChar32)0x200D);;
fGAZSet = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\U0001F466-\\U0001F469\\U0001F48B\\U0001F5E8\\u2764]"), status);
fExtendSet->removeAll(*fZWSSet);
fDictionarySet = new UnicodeSet(UNICODE_STRING_SIMPLE("[[\\uac00-\\ud7a3][:Han:][:Hiragana:]]"), status);
fDictionarySet->addAll(*fKatakanaSet);
fDictionarySet->addAll(UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{LineBreak = Complex_Context}]"), status));
fALetterSet->removeAll(*fDictionarySet);
fOtherSet = new UnicodeSet();
if(U_FAILURE(status)) {
@ -2327,13 +2310,13 @@ RBBIWordMonkey::RBBIWordMonkey()
fOtherSet->removeAll(*fExtendSet);
fOtherSet->removeAll(*fRegionalIndicatorSet);
fOtherSet->removeAll(*fEBaseSet);
fOtherSet->removeAll(*fEBGSet);
fOtherSet->removeAll(*fEModifierSet);
fOtherSet->removeAll(*fZWSSet);
fOtherSet->removeAll(*fZWJSet);
fOtherSet->removeAll(*fGAZSet);
// Inhibit dictionary characters from being tested at all.
fOtherSet->removeAll(*fDictionaryCjkSet);
fOtherSet->removeAll(UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{LineBreak = Complex_Context}]"), status));
fOtherSet->removeAll(*fDictionarySet);
fSets->addElement(fCRSet, status);
fSets->addElement(fLFSet, status);
@ -2343,7 +2326,9 @@ RBBIWordMonkey::RBBIWordMonkey()
fSets->addElement(fALetterSet, status);
fSets->addElement(fSingle_QuoteSet, status);
fSets->addElement(fDouble_QuoteSet, status);
//fSets->addElement(fKatakanaSet, status); //TODO: work out how to test katakana
//fSets->addElement(fKatakanaSet, status); // Omit Katakana from fSets, which omits Katakana characters
// from the test data. They are all in the dictionary set,
// which this (old, to be retired) monkey test cannot handle.
fSets->addElement(fMidLetterSet, status);
fSets->addElement(fMidNumLetSet, status);
fSets->addElement(fMidNumSet, status);
@ -2354,8 +2339,9 @@ RBBIWordMonkey::RBBIWordMonkey()
fSets->addElement(fExtendNumLetSet, status);
fSets->addElement(fEBaseSet, status);
fSets->addElement(fEBGSet, status);
fSets->addElement(fEModifierSet, status);
fSets->addElement(fZWSSet, status);
fSets->addElement(fZWJSet, status);
fSets->addElement(fGAZSet, status);
if (U_FAILURE(status)) {
@ -2406,7 +2392,7 @@ int32_t RBBIWordMonkey::next(int32_t prevPos) {
break;
};
}
while (fFormatSet->contains(c3) || fExtendSet->contains(c3) || fZWSSet->contains(c3));
while (fFormatSet->contains(c3) || fExtendSet->contains(c3) || fZWJSet->contains(c3));
if (p1 == p2) {
@ -2435,12 +2421,12 @@ int32_t RBBIWordMonkey::next(int32_t prevPos) {
break;
};
// Rule (3c) ZWJ x GAZ (Glue after ZWJ).
// Rule (3c) ZWJ x (Glue_after_ZWJ | EBG).
// Not ignoring extend chars, so peek into input text to
// get the potential ZWJ, the character immediately preceding c2.
// Sloppy UChar32 indexing: p2-1 may reference trail half
// but char32At will get the full code point.
if (fZWSSet->contains(fText->char32At(p2-1)) && fGAZSet->contains(c2)) {
if (fZWJSet->contains(fText->char32At(p2-1)) && (fGAZSet->contains(c2) || fEBGSet->contains(c2))) {
continue;
}
@ -2513,6 +2499,8 @@ int32_t RBBIWordMonkey::next(int32_t prevPos) {
}
// Rule (13) Katakana x Katakana
// Note: matches UAX 29 rules, but doesn't come into play for ICU because
// all Katakana are handled by the dictionary breaker.
if (fKatakanaSet->contains(c1) &&
fKatakanaSet->contains(c2)) {
continue;
@ -2532,7 +2520,12 @@ int32_t RBBIWordMonkey::next(int32_t prevPos) {
continue;
}
// Rule 13c
// WB 14 (E_Base | EBG) x E_Modifier
if ((fEBaseSet->contains(c1) || fEBGSet->contains(c1)) && fEModifierSet->contains(c2)) {
continue;
}
// Rule 15 - 17 Group pairs of Regional Indicators.
if (fRegionalIndicatorSet->contains(c0) && fRegionalIndicatorSet->contains(c1)) {
break;
}
@ -2540,12 +2533,7 @@ int32_t RBBIWordMonkey::next(int32_t prevPos) {
continue;
}
// Rule 13d
if ((fEBaseSet->contains(c1) || fGAZSet->contains(c1)) && fEModifierSet->contains(c2)) {
continue;
}
// Rule 14. Break found here.
// Rule 999. Break found here.
break;
}
@ -2577,11 +2565,12 @@ RBBIWordMonkey::~RBBIWordMonkey() {
delete fExtendSet;
delete fExtendNumLetSet;
delete fRegionalIndicatorSet;
delete fDictionaryCjkSet;
delete fDictionarySet;
delete fOtherSet;
delete fEBaseSet;
delete fEBGSet;
delete fEModifierSet;
delete fZWSSet;
delete fZWJSet;
delete fGAZSet;
}
@ -3034,13 +3023,9 @@ RBBILineMonkey::RBBILineMonkey() :
fRI = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Line_break=RI}]"), status);
fSG = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\ud800-\\udfff]"), status);
fXX = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Line_break=XX}]"), status);
fEB = new UnicodeSet(UnicodeString(
"[\\u261D\\u26F9\\u270A-\\u270D\\U0001F385\\U0001F3C3-\\U0001F3C4\\U0001F3CA-\\U0001F3CB\\U0001F442-\\U0001F443"
"\\U0001F446-\\U0001F450\\U0001F466-\\U0001F469\\U0001F46E\\U0001F470-\\U0001F478\\U0001F47C\\U0001F481-\\U0001F483"
"\\U0001F485-\\U0001F487\\U0001F4AA\\U0001F575\\U0001F590\\U0001F595-\\U0001F596\\U0001F645-\\U0001F647"
"\\U0001F64B-\\U0001F64F\\U0001F6A3\\U0001F6B4-\\U0001F6B6\\U0001F6C0\\U0001F918]"), status);
fEM = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\U0001F3FB-\\U0001F3FF]"), status);
fZJ = new UnicodeSet((UChar32)0x200D, (UChar32)0x200D);
fEB = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Line_break=EB}]"), status);
fEM = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Line_break=EM}]"), status);
fZJ = new UnicodeSet(UNICODE_STRING_SIMPLE("[\\p{Line_break=ZWJ}]"), status);
if (U_FAILURE(status)) {
deferredStatus = status;
@ -3055,11 +3040,8 @@ RBBILineMonkey::RBBILineMonkey() :
fID->addAll(*fEB); // Emoji Base and Emoji Modifier behave as ID.
fID->addAll(*fEM);
fAL->removeAll(*fEM);
fAL->remove((UChar32)0x2764); // Emoji Proposal: move u2764 from Al to Id
fID->add((UChar32)0x2764);
fCM->addAll(*fZJ); // ZWJ behaves as a CM.
fSets->addElement(fBK, status);
fSets->addElement(fCR, status);
@ -3104,12 +3086,12 @@ RBBILineMonkey::RBBILineMonkey() :
fSets->addElement(fZJ, status);
const char *rules =
"((\\p{Line_Break=PR}|\\p{Line_Break=PO})\\p{Line_Break=CM}*)?"
"((\\p{Line_Break=OP}|\\p{Line_Break=HY})\\p{Line_Break=CM}*)?"
"\\p{Line_Break=NU}\\p{Line_Break=CM}*"
"((\\p{Line_Break=NU}|\\p{Line_Break=IS}|\\p{Line_Break=SY})\\p{Line_Break=CM}*)*"
"((\\p{Line_Break=CL}|\\p{Line_Break=CP})\\p{Line_Break=CM}*)?"
"((\\p{Line_Break=PR}|\\p{Line_Break=PO})\\p{Line_Break=CM}*)?";
"((\\p{Line_Break=PR}|\\p{Line_Break=PO})(\\p{Line_Break=CM}|\\u200d)*)?"
"((\\p{Line_Break=OP}|\\p{Line_Break=HY})(\\p{Line_Break=CM}|\\u200d)*)?"
"\\p{Line_Break=NU}(\\p{Line_Break=CM}|\\u200d)*"
"((\\p{Line_Break=NU}|\\p{Line_Break=IS}|\\p{Line_Break=SY})(\\p{Line_Break=CM}|\\u200d)*)*"
"((\\p{Line_Break=CL}|\\p{Line_Break=CP})(\\p{Line_Break=CM}|\\u200d)*)?"
"((\\p{Line_Break=PR}|\\p{Line_Break=PO})(\\p{Line_Break=CM}|\\u200d)*)?";
fNumberMatcher = new RegexMatcher(
UnicodeString(rules, -1, US_INV), 0, status);

6
icu4c/source/test/intltest/ucdtest.cpp
View file

@ -418,13 +418,17 @@ namespace {
*/
UScriptCode getCharScript(UScriptCode script) {
switch(script) {
case USCRIPT_HAN_WITH_BOPOMOFO:
case USCRIPT_SIMPLIFIED_HAN:
case USCRIPT_TRADITIONAL_HAN:
return USCRIPT_HAN;
case USCRIPT_JAPANESE:
return USCRIPT_HIRAGANA;
case USCRIPT_JAMO:
case USCRIPT_KOREAN:
return USCRIPT_HANGUL;
case USCRIPT_SYMBOLS_EMOJI:
return USCRIPT_SYMBOLS;
default:
return script;
}
@ -441,7 +445,7 @@ void UnicodeTest::TestScriptMetadata() {
for(int32_t sci = 0; sci < USCRIPT_CODE_LIMIT; ++sci) {
UScriptCode sc = (UScriptCode)sci;
// Run the test with -v to see which script has failures:
// .../intltest$ make && ./intltest utility/UnicodeTest/TestScriptMetadata -v | grep -C 3 FAIL
// .../intltest$ make && ./intltest utility/UnicodeTest/TestScriptMetadata -v | grep -C 6 FAIL
logln(uscript_getShortName(sc));
UScriptUsage usage = uscript_getUsage(sc);
UnicodeString sample = uscript_getSampleUnicodeString(sc);

11
icu4c/source/test/testdata/BidiTest.txt vendored
View file

@ -1,10 +1,11 @@
# BidiTest-8.0.0.txt
# Date: 2014-12-16, 23:07:28 GMT [MD]
# BidiTest-9.0.0.txt
# Date: 2016-03-02, 18:54:52 GMT
# © 2016 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# Copyright (c) 1991-2014 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see http://www.unicode.org/reports/tr44/
#
# This file provides a conformance test for UBA (Unicode Bidi Algorithm) implementations.
# It is designed to be reasonably compact, and yet provide a thorough test of all cases up to

4841
icu4c/source/test/testdata/CollationTest_NON_IGNORABLE_SHORT.txt vendored
View file

File diff suppressed because it is too large Load diff

5366
icu4c/source/test/testdata/CollationTest_SHIFTED_SHORT.txt vendored
View file

File diff suppressed because it is too large Load diff

568
icu4c/source/test/testdata/GraphemeBreakTest.txt vendored
View file

@ -1,18 +1,18 @@
# GraphemeBreakTest-8.0.0.txt
# Date: 2015-02-13, 13:47:15 GMT [MD]
# Hand patched for Emoji breaking proposal L2/16-011R3.
# GraphemeBreakTest-9.0.0.txt
# Date: 2016-03-03, 12:43:52 GMT
# © 2016 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# Copyright (c) 1991-2015 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see http://www.unicode.org/reports/tr44/
#
# Default Grapheme Break Test
#
# Format:
# <string> (# <comment>)?
# <string> contains hex Unicode code points, with
# ÷ wherever there is a break opportunity, and
# <string> (# <comment>)?
# <string> contains hex Unicode code points, with
# ÷ wherever there is a break opportunity, and
# × wherever there is not.
# <comment> the format can change, but currently it shows:
# - the sample character name
@ -31,6 +31,8 @@
÷ 0020 × 0308 ÷ 0001 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 0020 × 0300 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 0020 × 0308 × 0300 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 0020 ÷ 0600 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 0020 × 0308 ÷ 0600 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 0020 × 0903 ÷ # ÷ [0.2] SPACE (Other) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 0020 × 0308 × 0903 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 0020 ÷ 1100 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
@ -43,8 +45,18 @@
÷ 0020 × 0308 ÷ AC00 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 0020 ÷ AC01 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0020 × 0308 ÷ AC01 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0020 ÷ 1F1E6 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0020 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0020 ÷ 1F1E6 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 0020 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 0020 ÷ 261D ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 0020 × 0308 ÷ 261D ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 0020 ÷ 1F3FB ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 0020 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 0020 × 200D ÷ # ÷ [0.2] SPACE (Other) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 0020 × 0308 × 200D ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 0020 ÷ 2764 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 0020 × 0308 ÷ 2764 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 0020 ÷ 1F466 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 0020 × 0308 ÷ 1F466 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 0020 ÷ 0378 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0020 × 0308 ÷ 0378 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0020 ÷ D800 ÷ # ÷ [0.2] SPACE (Other) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
@ -59,6 +71,8 @@
÷ 000D ÷ 0308 ÷ 0001 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 000D ÷ 0300 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 000D ÷ 0308 × 0300 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 000D ÷ 0600 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 000D ÷ 0308 ÷ 0600 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 000D ÷ 0903 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 000D ÷ 0308 × 0903 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 000D ÷ 1100 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
@ -71,8 +85,18 @@
÷ 000D ÷ 0308 ÷ AC00 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 000D ÷ AC01 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 000D ÷ 0308 ÷ AC01 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 000D ÷ 1F1E6 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 000D ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 000D ÷ 1F1E6 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 000D ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 000D ÷ 261D ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 000D ÷ 0308 ÷ 261D ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 000D ÷ 1F3FB ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 000D ÷ 0308 ÷ 1F3FB ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 000D ÷ 200D ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 000D ÷ 0308 × 200D ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 000D ÷ 2764 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 000D ÷ 0308 ÷ 2764 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 000D ÷ 1F466 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] BOY (EBG) ÷ [0.3]
÷ 000D ÷ 0308 ÷ 1F466 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 000D ÷ 0378 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3]
÷ 000D ÷ 0308 ÷ 0378 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 000D ÷ D800 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <surrogate-D800> (Control) ÷ [0.3]
@ -87,6 +111,8 @@
÷ 000A ÷ 0308 ÷ 0001 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 000A ÷ 0300 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 000A ÷ 0308 × 0300 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 000A ÷ 0600 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 000A ÷ 0308 ÷ 0600 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 000A ÷ 0903 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 000A ÷ 0308 × 0903 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 000A ÷ 1100 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
@ -99,8 +125,18 @@
÷ 000A ÷ 0308 ÷ AC00 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 000A ÷ AC01 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 000A ÷ 0308 ÷ AC01 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 000A ÷ 1F1E6 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 000A ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 000A ÷ 1F1E6 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 000A ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 000A ÷ 261D ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 000A ÷ 0308 ÷ 261D ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 000A ÷ 1F3FB ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 000A ÷ 0308 ÷ 1F3FB ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 000A ÷ 200D ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 000A ÷ 0308 × 200D ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 000A ÷ 2764 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 000A ÷ 0308 ÷ 2764 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 000A ÷ 1F466 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] BOY (EBG) ÷ [0.3]
÷ 000A ÷ 0308 ÷ 1F466 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 000A ÷ 0378 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3]
÷ 000A ÷ 0308 ÷ 0378 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 000A ÷ D800 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <surrogate-D800> (Control) ÷ [0.3]
@ -115,6 +151,8 @@
÷ 0001 ÷ 0308 ÷ 0001 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 0001 ÷ 0300 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 0001 ÷ 0308 × 0300 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 0001 ÷ 0600 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 0001 ÷ 0308 ÷ 0600 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 0001 ÷ 0903 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 0001 ÷ 0308 × 0903 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 0001 ÷ 1100 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
@ -127,8 +165,18 @@
÷ 0001 ÷ 0308 ÷ AC00 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 0001 ÷ AC01 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0001 ÷ 0308 ÷ AC01 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0001 ÷ 1F1E6 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0001 ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0001 ÷ 1F1E6 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 0001 ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 0001 ÷ 261D ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 0001 ÷ 0308 ÷ 261D ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 0001 ÷ 1F3FB ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 0001 ÷ 0308 ÷ 1F3FB ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 0001 ÷ 200D ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 0001 ÷ 0308 × 200D ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 0001 ÷ 2764 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 0001 ÷ 0308 ÷ 2764 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 0001 ÷ 1F466 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] BOY (EBG) ÷ [0.3]
÷ 0001 ÷ 0308 ÷ 1F466 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 0001 ÷ 0378 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0001 ÷ 0308 ÷ 0378 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0001 ÷ D800 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] <surrogate-D800> (Control) ÷ [0.3]
@ -143,6 +191,8 @@
÷ 0300 × 0308 ÷ 0001 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 0300 × 0300 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 0300 × 0308 × 0300 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 0300 ÷ 0600 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 0300 × 0308 ÷ 0600 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 0300 × 0903 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 0300 × 0308 × 0903 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 0300 ÷ 1100 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
@ -155,12 +205,62 @@
÷ 0300 × 0308 ÷ AC00 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 0300 ÷ AC01 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0300 × 0308 ÷ AC01 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0300 ÷ 1F1E6 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0300 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0300 ÷ 1F1E6 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 0300 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 0300 ÷ 261D ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 0300 × 0308 ÷ 261D ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 0300 ÷ 1F3FB ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 0300 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 0300 × 200D ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 0300 × 0308 × 200D ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 0300 ÷ 2764 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 0300 × 0308 ÷ 2764 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 0300 ÷ 1F466 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 0300 × 0308 ÷ 1F466 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 0300 ÷ 0378 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0300 × 0308 ÷ 0378 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0300 ÷ D800 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 0300 × 0308 ÷ D800 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 0600 × 0020 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] SPACE (Other) ÷ [0.3]
÷ 0600 × 0308 ÷ 0020 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 0600 ÷ 000D ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
÷ 0600 × 0308 ÷ 000D ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
÷ 0600 ÷ 000A ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 0600 × 0308 ÷ 000A ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 0600 ÷ 0001 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 0600 × 0308 ÷ 0001 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 0600 × 0300 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 0600 × 0308 × 0300 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 0600 × 0600 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 0600 × 0308 ÷ 0600 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 0600 × 0903 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 0600 × 0308 × 0903 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 0600 × 1100 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ 0600 × 0308 ÷ 1100 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ 0600 × 1160 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
÷ 0600 × 0308 ÷ 1160 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
÷ 0600 × 11A8 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
÷ 0600 × 0308 ÷ 11A8 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
÷ 0600 × AC00 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 0600 × 0308 ÷ AC00 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 0600 × AC01 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0600 × 0308 ÷ AC01 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0600 × 1F1E6 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 0600 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 0600 × 261D ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 0600 × 0308 ÷ 261D ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 0600 × 1F3FB ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 0600 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 0600 × 200D ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 0600 × 0308 × 200D ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 0600 × 2764 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 0600 × 0308 ÷ 2764 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 0600 × 1F466 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] BOY (EBG) ÷ [0.3]
÷ 0600 × 0308 ÷ 1F466 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 0600 × 0378 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] <reserved-0378> (Other) ÷ [0.3]
÷ 0600 × 0308 ÷ 0378 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0600 ÷ D800 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 0600 × 0308 ÷ D800 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 0903 ÷ 0020 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 0903 × 0308 ÷ 0020 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 0903 ÷ 000D ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
@ -171,6 +271,8 @@
÷ 0903 × 0308 ÷ 0001 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 0903 × 0300 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 0903 × 0308 × 0300 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 0903 ÷ 0600 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 0903 × 0308 ÷ 0600 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 0903 × 0903 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 0903 × 0308 × 0903 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 0903 ÷ 1100 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
@ -183,8 +285,18 @@
÷ 0903 × 0308 ÷ AC00 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 0903 ÷ AC01 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0903 × 0308 ÷ AC01 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0903 ÷ 1F1E6 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0903 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0903 ÷ 1F1E6 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 0903 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 0903 ÷ 261D ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 0903 × 0308 ÷ 261D ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 0903 ÷ 1F3FB ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 0903 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 0903 × 200D ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 0903 × 0308 × 200D ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 0903 ÷ 2764 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 0903 × 0308 ÷ 2764 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 0903 ÷ 1F466 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 0903 × 0308 ÷ 1F466 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 0903 ÷ 0378 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0903 × 0308 ÷ 0378 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0903 ÷ D800 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
@ -199,6 +311,8 @@
÷ 1100 × 0308 ÷ 0001 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 1100 × 0300 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 1100 × 0308 × 0300 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 1100 ÷ 0600 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 1100 × 0308 ÷ 0600 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 1100 × 0903 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 1100 × 0308 × 0903 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 1100 × 1100 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
@ -211,8 +325,18 @@
÷ 1100 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 1100 × AC01 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 1100 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 1100 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 1100 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 1100 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 1100 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 1100 ÷ 261D ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 1100 × 0308 ÷ 261D ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 1100 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 1100 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 1100 × 200D ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 1100 × 0308 × 200D ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 1100 ÷ 2764 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 1100 × 0308 ÷ 2764 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 1100 ÷ 1F466 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 1100 × 0308 ÷ 1F466 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 1100 ÷ 0378 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 1100 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 1100 ÷ D800 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
@ -227,6 +351,8 @@
÷ 1160 × 0308 ÷ 0001 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 1160 × 0300 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 1160 × 0308 × 0300 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 1160 ÷ 0600 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 1160 × 0308 ÷ 0600 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 1160 × 0903 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 1160 × 0308 × 0903 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 1160 ÷ 1100 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
@ -239,8 +365,18 @@
÷ 1160 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 1160 ÷ AC01 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 1160 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 1160 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 1160 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 1160 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 1160 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 1160 ÷ 261D ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 1160 × 0308 ÷ 261D ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 1160 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 1160 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 1160 × 200D ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 1160 × 0308 × 200D ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 1160 ÷ 2764 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 1160 × 0308 ÷ 2764 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 1160 ÷ 1F466 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 1160 × 0308 ÷ 1F466 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 1160 ÷ 0378 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 1160 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 1160 ÷ D800 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
@ -255,6 +391,8 @@
÷ 11A8 × 0308 ÷ 0001 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 11A8 × 0300 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 11A8 × 0308 × 0300 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 11A8 ÷ 0600 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 11A8 × 0308 ÷ 0600 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 11A8 × 0903 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 11A8 × 0308 × 0903 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 11A8 ÷ 1100 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
@ -267,8 +405,18 @@
÷ 11A8 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 11A8 ÷ AC01 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 11A8 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 11A8 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 11A8 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 11A8 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 11A8 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 11A8 ÷ 261D ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 11A8 × 0308 ÷ 261D ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 11A8 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 11A8 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 11A8 × 200D ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 11A8 × 0308 × 200D ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 11A8 ÷ 2764 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 11A8 × 0308 ÷ 2764 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 11A8 ÷ 1F466 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 11A8 × 0308 ÷ 1F466 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 11A8 ÷ 0378 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 11A8 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 11A8 ÷ D800 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
@ -283,6 +431,8 @@
÷ AC00 × 0308 ÷ 0001 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ AC00 × 0300 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ AC00 × 0308 × 0300 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ AC00 ÷ 0600 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ AC00 × 0308 ÷ 0600 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ AC00 × 0903 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ AC00 × 0308 × 0903 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ AC00 ÷ 1100 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
@ -295,8 +445,18 @@
÷ AC00 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ AC00 ÷ AC01 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ AC00 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ AC00 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ AC00 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ AC00 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ AC00 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ AC00 ÷ 261D ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ AC00 × 0308 ÷ 261D ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ AC00 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ AC00 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ AC00 × 200D ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ AC00 × 0308 × 200D ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ AC00 ÷ 2764 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ AC00 × 0308 ÷ 2764 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ AC00 ÷ 1F466 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ AC00 × 0308 ÷ 1F466 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ AC00 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ AC00 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ AC00 ÷ D800 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
@ -311,6 +471,8 @@
÷ AC01 × 0308 ÷ 0001 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ AC01 × 0300 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ AC01 × 0308 × 0300 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ AC01 ÷ 0600 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ AC01 × 0308 ÷ 0600 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ AC01 × 0903 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ AC01 × 0308 × 0903 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ AC01 ÷ 1100 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
@ -323,40 +485,262 @@
÷ AC01 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ AC01 ÷ AC01 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ AC01 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ AC01 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ AC01 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ AC01 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ AC01 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ AC01 ÷ 261D ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ AC01 × 0308 ÷ 261D ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ AC01 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ AC01 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ AC01 × 200D ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ AC01 × 0308 × 200D ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ AC01 ÷ 2764 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ AC01 × 0308 ÷ 2764 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ AC01 ÷ 1F466 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ AC01 × 0308 ÷ 1F466 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ AC01 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ AC01 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ AC01 ÷ D800 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ AC01 × 0308 ÷ D800 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 1F1E6 ÷ 0020 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0020 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 1F1E6 ÷ 000D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 000D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
÷ 1F1E6 ÷ 000A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 000A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 1F1E6 ÷ 0001 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0001 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 1F1E6 × 0300 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 1F1E6 × 0308 × 0300 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 1F1E6 × 0903 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 1F1E6 × 0308 × 0903 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 1F1E6 ÷ 1100 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 1100 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ 1F1E6 ÷ 1160 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 1160 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
÷ 1F1E6 ÷ 11A8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 11A8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
÷ 1F1E6 ÷ AC00 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ AC00 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 1F1E6 ÷ AC01 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ AC01 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 1F1E6 × 1F1E6 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 1F1E6 ÷ 0378 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0378 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 1F1E6 ÷ D800 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ D800 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 1F1E6 ÷ 0020 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0020 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 1F1E6 ÷ 000D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 000D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
÷ 1F1E6 ÷ 000A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 000A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 1F1E6 ÷ 0001 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0001 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 1F1E6 × 0300 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 1F1E6 × 0308 × 0300 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 1F1E6 ÷ 0600 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0600 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 1F1E6 × 0903 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 1F1E6 × 0308 × 0903 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 1F1E6 ÷ 1100 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 1100 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ 1F1E6 ÷ 1160 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 1160 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
÷ 1F1E6 ÷ 11A8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 11A8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
÷ 1F1E6 ÷ AC00 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ AC00 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 1F1E6 ÷ AC01 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ AC01 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 1F1E6 × 1F1E6 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [8.11] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 1F1E6 ÷ 261D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 261D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 1F1E6 ÷ 1F3FB ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 1F1E6 × 200D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 1F1E6 × 0308 × 200D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 1F1E6 ÷ 2764 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 2764 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 1F1E6 ÷ 1F466 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 1F466 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 1F1E6 ÷ 0378 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0378 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 1F1E6 ÷ D800 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ D800 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 261D ÷ 0020 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 261D × 0308 ÷ 0020 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 261D ÷ 000D ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
÷ 261D × 0308 ÷ 000D ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
÷ 261D ÷ 000A ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 261D × 0308 ÷ 000A ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 261D ÷ 0001 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 261D × 0308 ÷ 0001 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 261D × 0300 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 261D × 0308 × 0300 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 261D ÷ 0600 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 261D × 0308 ÷ 0600 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 261D × 0903 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 261D × 0308 × 0903 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 261D ÷ 1100 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ 261D × 0308 ÷ 1100 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ 261D ÷ 1160 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
÷ 261D × 0308 ÷ 1160 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
÷ 261D ÷ 11A8 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
÷ 261D × 0308 ÷ 11A8 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
÷ 261D ÷ AC00 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 261D × 0308 ÷ AC00 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 261D ÷ AC01 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 261D × 0308 ÷ AC01 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 261D ÷ 1F1E6 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 261D × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 261D ÷ 261D ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 261D × 0308 ÷ 261D ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 261D × 1F3FB ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 261D × 0308 ÷ 1F3FB ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 261D × 200D ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 261D × 0308 × 200D ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 261D ÷ 2764 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 261D × 0308 ÷ 2764 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 261D ÷ 1F466 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 261D × 0308 ÷ 1F466 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 261D ÷ 0378 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 261D × 0308 ÷ 0378 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 261D ÷ D800 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 261D × 0308 ÷ D800 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 1F3FB ÷ 0020 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 1F3FB × 0308 ÷ 0020 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 1F3FB ÷ 000D ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
÷ 1F3FB × 0308 ÷ 000D ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
÷ 1F3FB ÷ 000A ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 1F3FB × 0308 ÷ 000A ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 1F3FB ÷ 0001 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 1F3FB × 0308 ÷ 0001 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 1F3FB × 0300 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 1F3FB × 0308 × 0300 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 1F3FB ÷ 0600 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 1F3FB × 0308 ÷ 0600 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 1F3FB × 0903 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 1F3FB × 0308 × 0903 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 1F3FB ÷ 1100 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ 1F3FB × 0308 ÷ 1100 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ 1F3FB ÷ 1160 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
÷ 1F3FB × 0308 ÷ 1160 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
÷ 1F3FB ÷ 11A8 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
÷ 1F3FB × 0308 ÷ 11A8 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
÷ 1F3FB ÷ AC00 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 1F3FB × 0308 ÷ AC00 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 1F3FB ÷ AC01 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 1F3FB × 0308 ÷ AC01 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 1F3FB ÷ 1F1E6 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 1F3FB × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 1F3FB ÷ 261D ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 1F3FB × 0308 ÷ 261D ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 1F3FB ÷ 1F3FB ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 1F3FB × 0308 ÷ 1F3FB ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 1F3FB × 200D ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 1F3FB × 0308 × 200D ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 1F3FB ÷ 2764 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 1F3FB × 0308 ÷ 2764 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 1F3FB ÷ 1F466 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 1F3FB × 0308 ÷ 1F466 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 1F3FB ÷ 0378 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 1F3FB × 0308 ÷ 0378 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 1F3FB ÷ D800 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 1F3FB × 0308 ÷ D800 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 200D ÷ 0020 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 200D × 0308 ÷ 0020 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 200D ÷ 000D ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
÷ 200D × 0308 ÷ 000D ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
÷ 200D ÷ 000A ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 200D × 0308 ÷ 000A ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 200D ÷ 0001 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 200D × 0308 ÷ 0001 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 200D × 0300 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 200D × 0308 × 0300 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 200D ÷ 0600 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 200D × 0308 ÷ 0600 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 200D × 0903 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 200D × 0308 × 0903 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 200D ÷ 1100 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ 200D × 0308 ÷ 1100 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ 200D ÷ 1160 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
÷ 200D × 0308 ÷ 1160 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
÷ 200D ÷ 11A8 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
÷ 200D × 0308 ÷ 11A8 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
÷ 200D ÷ AC00 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 200D × 0308 ÷ AC00 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 200D ÷ AC01 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 200D × 0308 ÷ AC01 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 200D ÷ 1F1E6 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 200D × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 200D ÷ 261D ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 200D × 0308 ÷ 261D ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 200D ÷ 1F3FB ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 200D × 0308 ÷ 1F3FB ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 200D × 200D ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 200D × 0308 × 200D ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 200D × 2764 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.4] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 200D × 0308 ÷ 2764 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 200D × 1F466 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.4] BOY (EBG) ÷ [0.3]
÷ 200D × 0308 ÷ 1F466 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 200D ÷ 0378 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 200D × 0308 ÷ 0378 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 200D ÷ D800 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 200D × 0308 ÷ D800 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 2764 ÷ 0020 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 2764 × 0308 ÷ 0020 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 2764 ÷ 000D ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
÷ 2764 × 0308 ÷ 000D ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
÷ 2764 ÷ 000A ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 2764 × 0308 ÷ 000A ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 2764 ÷ 0001 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 2764 × 0308 ÷ 0001 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 2764 × 0300 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 2764 × 0308 × 0300 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 2764 ÷ 0600 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 2764 × 0308 ÷ 0600 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 2764 × 0903 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 2764 × 0308 × 0903 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 2764 ÷ 1100 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ 2764 × 0308 ÷ 1100 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ 2764 ÷ 1160 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
÷ 2764 × 0308 ÷ 1160 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
÷ 2764 ÷ 11A8 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
÷ 2764 × 0308 ÷ 11A8 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
÷ 2764 ÷ AC00 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 2764 × 0308 ÷ AC00 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 2764 ÷ AC01 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 2764 × 0308 ÷ AC01 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 2764 ÷ 1F1E6 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 2764 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 2764 ÷ 261D ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 2764 × 0308 ÷ 261D ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 2764 ÷ 1F3FB ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 2764 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 2764 × 200D ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 2764 × 0308 × 200D ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 2764 ÷ 2764 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 2764 × 0308 ÷ 2764 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 2764 ÷ 1F466 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 2764 × 0308 ÷ 1F466 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 2764 ÷ 0378 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 2764 × 0308 ÷ 0378 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 2764 ÷ D800 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 2764 × 0308 ÷ D800 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 1F466 ÷ 0020 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 1F466 × 0308 ÷ 0020 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 1F466 ÷ 000D ÷ # ÷ [0.2] BOY (EBG) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
÷ 1F466 × 0308 ÷ 000D ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
÷ 1F466 ÷ 000A ÷ # ÷ [0.2] BOY (EBG) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 1F466 × 0308 ÷ 000A ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 1F466 ÷ 0001 ÷ # ÷ [0.2] BOY (EBG) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 1F466 × 0308 ÷ 0001 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 1F466 × 0300 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 1F466 × 0308 × 0300 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 1F466 ÷ 0600 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 1F466 × 0308 ÷ 0600 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 1F466 × 0903 ÷ # ÷ [0.2] BOY (EBG) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 1F466 × 0308 × 0903 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 1F466 ÷ 1100 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ 1F466 × 0308 ÷ 1100 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ 1F466 ÷ 1160 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
÷ 1F466 × 0308 ÷ 1160 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
÷ 1F466 ÷ 11A8 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
÷ 1F466 × 0308 ÷ 11A8 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
÷ 1F466 ÷ AC00 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 1F466 × 0308 ÷ AC00 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 1F466 ÷ AC01 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 1F466 × 0308 ÷ AC01 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 1F466 ÷ 1F1E6 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 1F466 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 1F466 ÷ 261D ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 1F466 × 0308 ÷ 261D ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 1F466 × 1F3FB ÷ # ÷ [0.2] BOY (EBG) × [9.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 1F466 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 1F466 × 200D ÷ # ÷ [0.2] BOY (EBG) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 1F466 × 0308 × 200D ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 1F466 ÷ 2764 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 1F466 × 0308 ÷ 2764 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 1F466 ÷ 1F466 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 1F466 × 0308 ÷ 1F466 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 1F466 ÷ 0378 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 1F466 × 0308 ÷ 0378 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 1F466 ÷ D800 ÷ # ÷ [0.2] BOY (EBG) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 1F466 × 0308 ÷ D800 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 0378 ÷ 0020 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 0378 × 0308 ÷ 0020 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 0378 ÷ 000D ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
@ -367,6 +751,8 @@
÷ 0378 × 0308 ÷ 0001 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 0378 × 0300 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 0378 × 0308 × 0300 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 0378 ÷ 0600 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 0378 × 0308 ÷ 0600 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ 0378 × 0903 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 0378 × 0308 × 0903 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 0378 ÷ 1100 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
@ -379,8 +765,18 @@
÷ 0378 × 0308 ÷ AC00 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 0378 ÷ AC01 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0378 × 0308 ÷ AC01 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0378 ÷ 1F1E6 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0378 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0378 ÷ 1F1E6 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 0378 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ 0378 ÷ 261D ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 0378 × 0308 ÷ 261D ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 0378 ÷ 1F3FB ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 0378 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 0378 × 200D ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 0378 × 0308 × 200D ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 0378 ÷ 2764 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 0378 × 0308 ÷ 2764 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 0378 ÷ 1F466 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 0378 × 0308 ÷ 1F466 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ 0378 ÷ 0378 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0378 × 0308 ÷ 0378 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0378 ÷ D800 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
@ -395,6 +791,8 @@
÷ D800 ÷ 0308 ÷ 0001 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ D800 ÷ 0300 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ D800 ÷ 0308 × 0300 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ D800 ÷ 0600 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ D800 ÷ 0308 ÷ 0600 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
÷ D800 ÷ 0903 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ D800 ÷ 0308 × 0903 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ D800 ÷ 1100 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
@ -407,23 +805,45 @@
÷ D800 ÷ 0308 ÷ AC00 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ D800 ÷ AC01 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ D800 ÷ 0308 ÷ AC01 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ D800 ÷ 1F1E6 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ D800 ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ D800 ÷ 1F1E6 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ D800 ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
÷ D800 ÷ 261D ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ D800 ÷ 0308 ÷ 261D ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ D800 ÷ 1F3FB ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ D800 ÷ 0308 ÷ 1F3FB ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ D800 ÷ 200D ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ D800 ÷ 0308 × 200D ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ D800 ÷ 2764 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ D800 ÷ 0308 ÷ 2764 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ D800 ÷ 1F466 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] BOY (EBG) ÷ [0.3]
÷ D800 ÷ 0308 ÷ 1F466 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3]
÷ D800 ÷ 0378 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3]
÷ D800 ÷ 0308 ÷ 0378 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ D800 ÷ D800 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] <surrogate-D800> (Control) ÷ [0.3]
÷ D800 ÷ 0308 ÷ D800 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 0061 ÷ 1F1E6 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
÷ 1F1F7 × 1F1FA ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) ÷ [0.3]
÷ 1F1F7 × 1F1FA ÷ 1F1F8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER S (Regional_Indicator) ÷ [0.3]
÷ 1F1F7 × 1F1FA ÷ 1F1F8 × 1F1EA ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER S (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER E (Regional_Indicator) ÷ [0.3]
÷ 1F1F7 × 1F1FA ÷ 200B ÷ 1F1F8 × 1F1EA ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) ÷ [5.0] ZERO WIDTH SPACE (Control) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER S (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER E (Regional_Indicator) ÷ [0.3]
÷ 1F1E6 × 1F1E7 ÷ 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER B (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER C (Regional_Indicator) ÷ [0.3]
÷ 1F1E6 × 200D ÷ 1F1E7 × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] ZERO WIDTH JOINER (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER B (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER C (Regional_Indicator) ÷ [0.3]
÷ 1F1E6 × 1F1E7 × 200D ÷ 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER B (Regional_Indicator) × [9.0] ZERO WIDTH JOINER (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER C (Regional_Indicator) ÷ [0.3]
÷ 0020 × 200D ÷ 0646 ÷ # ÷ [0.2] SPACE (Other) × [9.0] ZERO WIDTH JOINER (Extend) ÷ [999.0] ARABIC LETTER NOON (Other) ÷ [0.3]
÷ 0646 × 200D ÷ 0020 ÷ # ÷ [0.2] ARABIC LETTER NOON (Other) × [9.0] ZERO WIDTH JOINER (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 000D × 000A ÷ 0061 ÷ 000A ÷ 0308 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) × [3.0] <LINE FEED (LF)> (LF) ÷ [4.0] LATIN SMALL LETTER A (Other) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [0.3]
÷ 0061 × 0308 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [0.3]
÷ 0020 × 200D ÷ 0646 ÷ # ÷ [0.2] SPACE (Other) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] ARABIC LETTER NOON (Other) ÷ [0.3]
÷ 0646 × 200D ÷ 0020 ÷ # ÷ [0.2] ARABIC LETTER NOON (Other) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 1100 × 1100 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ AC00 × 11A8 ÷ 1100 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [7.0] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ AC01 × 11A8 ÷ 1100 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [8.0] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ 1F1E6 × 1F1E7 ÷ 1F1E8 ÷ 0062 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [8.11] REGIONAL INDICATOR SYMBOL LETTER B (RI) ÷ [8.13] REGIONAL INDICATOR SYMBOL LETTER C (RI) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
÷ 0061 ÷ 1F1E6 × 1F1E7 ÷ 1F1E8 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [8.12] REGIONAL INDICATOR SYMBOL LETTER B (RI) ÷ [8.13] REGIONAL INDICATOR SYMBOL LETTER C (RI) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
÷ 0061 ÷ 1F1E6 × 1F1E7 × 200D ÷ 1F1E8 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [8.12] REGIONAL INDICATOR SYMBOL LETTER B (RI) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER C (RI) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
÷ 0061 ÷ 1F1E6 × 200D ÷ 1F1E7 × 1F1E8 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER B (RI) × [8.12] REGIONAL INDICATOR SYMBOL LETTER C (RI) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
÷ 0061 ÷ 1F1E6 × 1F1E7 ÷ 1F1E8 × 1F1E9 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [8.12] REGIONAL INDICATOR SYMBOL LETTER B (RI) ÷ [8.13] REGIONAL INDICATOR SYMBOL LETTER C (RI) × [8.12] REGIONAL INDICATOR SYMBOL LETTER D (RI) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
÷ 0061 × 200D ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3]
÷ 0061 × 0308 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
÷ 0061 × 0903 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
÷ 0061 ÷ 0600 × 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) × [9.2] LATIN SMALL LETTER B (Other) ÷ [0.3]
÷ 261D × 1F3FB ÷ 261D ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3]
÷ 1F466 × 1F3FB ÷ # ÷ [0.2] BOY (EBG) × [9.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 200D × 1F466 × 1F3FB ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.4] BOY (EBG) × [9.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3]
÷ 200D × 2764 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.4] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3]
÷ 200D × 1F466 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.4] BOY (EBG) ÷ [0.3]
÷ 1F466 ÷ 1F466 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] BOY (EBG) ÷ [0.3]
#
# Lines: 402
# Lines: 822
#
# EOF

2
icu4c/source/test/testdata/LineBreakTest.txt vendored
View file

@ -1,4 +1,4 @@
# LineBreakTest-9.0.0.txt
# LineBreakTest-9.0.0.txt
# Date: 2016-03-23, 11:24:44 GMT
# © 2016 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.

22
icu4c/source/test/testdata/SentenceBreakTest.txt vendored
View file

@ -1,10 +1,11 @@
# SentenceBreakTest-8.0.0.txt
# Date: 2015-04-30, 09:40:15 GMT [MD]
# SentenceBreakTest-9.0.0.txt
# Date: 2016-03-03, 12:44:04 GMT
# © 2016 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# Copyright (c) 1991-2015 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see http://www.unicode.org/reports/tr44/
#
# Default Sentence Break Test
#
@ -470,6 +471,10 @@
÷ 0300 × 0308 × 00AD ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0300 × 0300 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
÷ 0300 × 0308 × 0300 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
÷ 000D × 000A ÷ 0061 × 000A ÷ 0308 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) × [3.0] <LINE FEED (LF)> (LF) ÷ [4.0] LATIN SMALL LETTER A (Lower) × [12.0] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [0.3]
÷ 0061 × 0308 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [0.3]
÷ 0020 × 200D × 0646 ÷ # ÷ [0.2] SPACE (Sp) × [5.0] ZERO WIDTH JOINER (Extend_FE) × [12.0] ARABIC LETTER NOON (OLetter) ÷ [0.3]
÷ 0646 × 200D × 0020 ÷ # ÷ [0.2] ARABIC LETTER NOON (OLetter) × [5.0] ZERO WIDTH JOINER (Extend_FE) × [12.0] SPACE (Sp) ÷ [0.3]
÷ 0028 × 0022 × 0047 × 006F × 002E × 0022 × 0029 × 0020 ÷ 0028 × 0048 × 0065 × 0020 × 0064 × 0069 × 0064 × 002E × 0029 ÷ # ÷ [0.2] LEFT PARENTHESIS (Close) × [12.0] QUOTATION MARK (Close) × [12.0] LATIN CAPITAL LETTER G (Upper) × [12.0] LATIN SMALL LETTER O (Lower) × [12.0] FULL STOP (ATerm) × [9.0] QUOTATION MARK (Close) × [9.0] RIGHT PARENTHESIS (Close) × [9.0] SPACE (Sp) ÷ [11.0] LEFT PARENTHESIS (Close) × [12.0] LATIN CAPITAL LETTER H (Upper) × [12.0] LATIN SMALL LETTER E (Lower) × [12.0] SPACE (Sp) × [12.0] LATIN SMALL LETTER D (Lower) × [12.0] LATIN SMALL LETTER I (Lower) × [12.0] LATIN SMALL LETTER D (Lower) × [12.0] FULL STOP (ATerm) × [9.0] RIGHT PARENTHESIS (Close) ÷ [0.3]
÷ 0028 × 201C × 0047 × 006F × 003F × 201D × 0029 × 0020 ÷ 0028 × 0048 × 0065 × 0020 × 0064 × 0069 × 0064 × 002E × 0029 ÷ # ÷ [0.2] LEFT PARENTHESIS (Close) × [12.0] LEFT DOUBLE QUOTATION MARK (Close) × [12.0] LATIN CAPITAL LETTER G (Upper) × [12.0] LATIN SMALL LETTER O (Lower) × [12.0] QUESTION MARK (STerm) × [9.0] RIGHT DOUBLE QUOTATION MARK (Close) × [9.0] RIGHT PARENTHESIS (Close) × [9.0] SPACE (Sp) ÷ [11.0] LEFT PARENTHESIS (Close) × [12.0] LATIN CAPITAL LETTER H (Upper) × [12.0] LATIN SMALL LETTER E (Lower) × [12.0] SPACE (Sp) × [12.0] LATIN SMALL LETTER D (Lower) × [12.0] LATIN SMALL LETTER I (Lower) × [12.0] LATIN SMALL LETTER D (Lower) × [12.0] FULL STOP (ATerm) × [9.0] RIGHT PARENTHESIS (Close) ÷ [0.3]
÷ 0055 × 002E × 0053 × 002E × 0041 × 0300 × 002E × 0020 × 0069 × 0073 ÷ # ÷ [0.2] LATIN CAPITAL LETTER U (Upper) × [12.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER S (Upper) × [12.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) × [12.0] FULL STOP (ATerm) × [8.0] SPACE (Sp) × [8.0] LATIN SMALL LETTER I (Lower) × [12.0] LATIN SMALL LETTER S (Lower) ÷ [0.3]
@ -518,12 +523,7 @@
÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 3002 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.1] IDEOGRAPHIC FULL STOP (STerm) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
÷ 2060 × 5B57 × 2060 × 3002 × 2060 ÷ 5B83 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] CJK UNIFIED IDEOGRAPH-5B57 (OLetter) × [5.0] WORD JOINER (Format_FE) × [12.0] IDEOGRAPHIC FULL STOP (STerm) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B83 (OLetter) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
÷ 2060 × 0021 × 2060 × 0020 × 2060 × 0020 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] EXCLAMATION MARK (STerm) × [5.0] WORD JOINER (Format_FE) × [9.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [10.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
÷ 1F1E6 × 1F1E7 × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Other) × [12.0] REGIONAL INDICATOR SYMBOL LETTER B (Other) × [12.0] REGIONAL INDICATOR SYMBOL LETTER C (Other) ÷ [0.3]
÷ 1F1E6 × 200D × 1F1E7 × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Other) × [5.0] ZERO WIDTH JOINER (Extend_FE) × [12.0] REGIONAL INDICATOR SYMBOL LETTER B (Other) × [12.0] REGIONAL INDICATOR SYMBOL LETTER C (Other) ÷ [0.3]
÷ 1F1E6 × 1F1E7 × 200D × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Other) × [12.0] REGIONAL INDICATOR SYMBOL LETTER B (Other) × [5.0] ZERO WIDTH JOINER (Extend_FE) × [12.0] REGIONAL INDICATOR SYMBOL LETTER C (Other) ÷ [0.3]
÷ 0020 × 200D × 0646 ÷ # ÷ [0.2] SPACE (Sp) × [5.0] ZERO WIDTH JOINER (Extend_FE) × [12.0] ARABIC LETTER NOON (OLetter) ÷ [0.3]
÷ 0646 × 200D × 0020 ÷ # ÷ [0.2] ARABIC LETTER NOON (OLetter) × [5.0] ZERO WIDTH JOINER (Extend_FE) × [12.0] SPACE (Sp) ÷ [0.3]
#
# Lines: 503
# Lines: 502
#
# EOF

843
icu4c/source/test/testdata/WordBreakTest.txt vendored
View file

File diff suppressed because it is too large Load diff

40
icu4c/source/test/testdata/break_rules/grapheme.txt vendored
View file

@ -12,28 +12,32 @@
type = grapheme; # one of grapheme | word | line | sentence
locale = en;
CR = [\u000d];
LF = [\u000a];
CR = [\p{Grapheme_Cluster_Break = CR}];
LF = [\p{Grapheme_Cluster_Break = LF}];
Control = [[\p{Grapheme_Cluster_Break = Control}]-[:Block=Tags:]];
Extend = [[\p{Grapheme_Cluster_Break = Extend}][:Block=Tags:]];
Control = [[\p{Grapheme_Cluster_Break = Control}]];
Extend = [[\p{Grapheme_Cluster_Break = Extend}]];
ZWJ = [\p{Grapheme_Cluster_Break = ZWJ}];
Regional_Indicator = [\p{Grapheme_Cluster_Break = Regional_Indicator}];
Prepend = [];
Prepend = [\p{Grapheme_Cluster_Break = Prepend}];
SpacingMark = [\p{Grapheme_Cluster_Break = SpacingMark}];
E_Base = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
E_Modifier = [\U0001F3FB-\U0001F3FF];
GAZ = [\U0001F466-\U0001F469\U0001F48B\U0001F5E8\u2764];
ZWJ = [\u200D];
#
# Korean Syllable Definitions
#
L = [\p{Grapheme_Cluster_Break = L}];
V = [\p{Grapheme_Cluster_Break = V}];
T = [\p{Grapheme_Cluster_Break = T}];
L = [\p{Grapheme_Cluster_Break = L}];
V = [\p{Grapheme_Cluster_Break = V}];
T = [\p{Grapheme_Cluster_Break = T}];
LV = [\p{Grapheme_Cluster_Break = LV}];
LVT = [\p{Grapheme_Cluster_Break = LVT}];
# Emoji defintions
E_Base = [\p{Grapheme_Cluster_Break = EB}];
E_Modifier = [\p{Grapheme_Cluster_Break = EM}];
GAZ = [\p{Grapheme_Cluster_Break = GAZ}];
E_Base_GAZ = [\p{Grapheme_Cluster_Break = EBG}];
LV = [\p{Grapheme_Cluster_Break = LV}];
LVT = [\p{Grapheme_Cluster_Break = LVT}];
GB3: CR LF;
GB4: (Control | CR | LF) ÷;
@ -50,11 +54,11 @@ GB8: (LVT | T) T;
GB8a.1: Regional_Indicator Regional_Indicator ÷ Regional_Indicator;
GB8a.2: Regional_Indicator Regional_Indicator;
GB9: . Extend;
GB9: . (Extend | ZWJ);
GB9a: . SpacingMark;
GB9b: Prepend .;
GB9c: (E_Base | GAZ) E_Modifier;
GB9d: ZWJ GAZ;
GB10: (E_Base | E_Base_GAZ) E_Modifier;
GB11: ZWJ (GAZ | E_Base_GAZ);
GB10: . ÷;
GB999: . ÷;

41
icu4c/source/test/testdata/break_rules/line.txt vendored
View file

@ -14,7 +14,7 @@ locale = en;
AI = [:LineBreak = Ambiguous:];
AL = [[:LineBreak = Alphabetic:]-[\u2764]];
AL = [:LineBreak = Alphabetic:];
BA = [:LineBreak = Break_After:];
BB = [:LineBreak = Break_Before:];
BK = [:LineBreak = Mandatory_Break:];
@ -25,17 +25,15 @@ CL = [:LineBreak = Close_Punctuation:];
CM = [:LineBreak = Combining_Mark:];
CP = [:LineBreak = Close_Parenthesis:];
CR = [:LineBreak = Carriage_Return:];
EB = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
EM = [\U0001F3FB-\U0001F3FF];
EB = [:LineBreak = EB:];
EM = [:LineBreak = EM:];
EX = [:LineBreak = Exclamation:];
GL = [:LineBreak = Glue:];
HL = [:LineBreak = Hebrew_Letter:];
HY = [:LineBreak = Hyphen:];
H2 = [:LineBreak = H2:];
H3 = [:LineBreak = H3:];
ID = [[:LineBreak = Ideographic:][\u2764]];
ID = [:LineBreak = Ideographic:];
IN = [:LineBreak = Inseperable:];
IS = [:LineBreak = Infix_Numeric:];
JL = [:LineBreak = JL:];
@ -43,7 +41,7 @@ JV = [:LineBreak = JV:];
JT = [:LineBreak = JT:];
LF = [:LineBreak = Line_Feed:];
NL = [:LineBreak = Next_Line:];
NS = [[:LineBreak = Nonstarter:] CJ];
NS = [[:LineBreak = Nonstarter:] CJ]; # CSS Strict tailoring: CJ resolves to NS.
NU = [:LineBreak = Numeric:];
OP = [:LineBreak = Open_Punctuation:];
PO = [:LineBreak = Postfix_Numeric:];
@ -57,16 +55,15 @@ SY = [:LineBreak = Break_Symbols:];
WJ = [:LineBreak = Word_Joiner:];
XX = [:LineBreak = Unknown:];
ZW = [:LineBreak = ZWSpace:];
ZJ = [\u200D];
ZWJ = [:LineBreak = ZWJ:];
# TODO: adjustment to sets needed only until Unicode properties are updated for Emoji.
ID = [ID - EB];
AL = [AL - EM];
# LB1 - Resolve AI, CB, CJ, SA, SG, and XX into other line breaking classes
AL = [AL AI SG XX ];
dictionary = SA;
dictionary = [:LineBreak = Complex_Context:];
# Redfine AL. LB1. TODO: refine according to latest UAX.
AL = [ AL AI SA SG XX ];
# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
# list it in the numerous rules that use CM.
CM = [CM ZWJ];
LB4: BK ÷;
LB5: CR LF;
@ -96,7 +93,7 @@ LB8: ZW ÷;
# LB8a, from Emoji proposal L2/16-011R3
# ZWJ x ID
LB8a: ZJ (ID | EB | EM);
LB8a: ZWJ (ID | EB | EM);
# LB9: X CM -> X
@ -131,11 +128,11 @@ LB19: . CM* QU;
LB19.1: QU CM* [^CM];
# LB 20 Break before and after CB.
# Interaction with LB8a: ZJ x ID is tricky because CM includes ZJ.
# ZJ acts like a CM to the left, combining with CB.
# ZJ acts independently to the right, no break from ID by LB8a.
# Interaction with LB8a: ZWJ x ID is tricky because CM includes ZWJ.
# ZWJ acts like a CM to the left, combining with CB.
# ZWJ acts independently to the right, no break from ID by LB8a.
LB20: . CM* ÷ CB;
LB20.1a: CB CM* ZJ (ID | EB | EM);
LB20.1a: CB CM* ZWJ (ID | EB | EM);
LB20.1b: CB CM* ÷;
# Note: Rule 21a must come before 21 to prevent 21.1 from matching HL BA, then
@ -185,7 +182,7 @@ LB30.2: CP CM* (AL | HL | NU);
# LB31 keep pairs of RI together.
LB30a.1: RI CM* RI CM* [BK CR LF NL SP ZW WJ GL CL CP EX IS SY QU BA HY NS];
LB30a.2: RI CM* RI CM* ZJ (ID | EB | EM);
LB30a.2: RI CM* RI CM* ZWJ (ID | EB | EM);
LB30a.3: RI CM* RI CM* ÷;
# LB30b Do not break between Emoji Base and Emoji Modifier
@ -193,5 +190,5 @@ LB30b: EB CM* EM;
# LB31 Break Everywhere Else.
# Include combining marks
LB31.1: . CM* ZJ (ID | EB | EM);
LB31.1: . CM* ZWJ (ID | EB | EM);
LB31.2: . CM* ÷;

41
icu4c/source/test/testdata/break_rules/line_loose.txt vendored
View file

@ -9,7 +9,7 @@
# They are expected to change with review and the addition of support for rule tailoring.
#
# This tailors the line break behavior to correspond to CSS
# line-break=loose (BCP47 -u-lb-loose) as defined for languages other than
# line-break=loose (BCP47 -u-lb-loose) as defined for languages other than
# Chinese & Japanese.
# It sets characters of class CJ to behave like ID.
# In addition, it allows breaks:
@ -21,7 +21,7 @@ locale = en@lb=loose;
AI = [:LineBreak = Ambiguous:];
AL = [[:LineBreak = Alphabetic:]-[\u2764]];
AL = [:LineBreak = Alphabetic:];
BA = [:LineBreak = Break_After:];
BB = [:LineBreak = Break_Before:];
BK = [:LineBreak = Mandatory_Break:];
@ -32,17 +32,15 @@ CL = [:LineBreak = Close_Punctuation:];
CM = [:LineBreak = Combining_Mark:];
CP = [:LineBreak = Close_Parenthesis:];
CR = [:LineBreak = Carriage_Return:];
EB = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
EM = [\U0001F3FB-\U0001F3FF];
EB = [:LineBreak = EB:];
EM = [:LineBreak = EM:];
EX = [:LineBreak = Exclamation:];
GL = [:LineBreak = Glue:];
HL = [:LineBreak = Hebrew_Letter:];
HY = [:LineBreak = Hyphen:];
H2 = [:LineBreak = H2:];
H3 = [:LineBreak = H3:];
ID = [[:LineBreak = Ideographic:] CJ [\u2764]];
ID = [[:LineBreak = Ideographic:] CJ]; # CSS Normal tailoring: CJ resolves to ID
IN = [:LineBreak = Inseperable:];
IS = [:LineBreak = Infix_Numeric:];
JL = [:LineBreak = JL:];
@ -65,16 +63,15 @@ SY = [:LineBreak = Break_Symbols:];
WJ = [:LineBreak = Word_Joiner:];
XX = [:LineBreak = Unknown:];
ZW = [:LineBreak = ZWSpace:];
ZJ = [\u200D];
ZWJ = [:LineBreak = ZWJ:];
# TODO: adjustment to sets needed only until Unicode properties are updated for Emoji.
ID = [ID - EB];
AL = [AL - EM];
# LB1 - Resolve AI, CB, CJ, SA, SG, and XX into other line breaking classes
AL = [AL AI SG XX ];
dictionary = SA;
dictionary = [:LineBreak = Complex_Context:];
# Redfine AL. LB1. TODO: refine according to latest UAX.
AL = [ AL AI SA SG XX ];
# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
# list it in the numerous rules that use CM.
CM = [CM ZWJ];
LB4: BK ÷;
LB5: CR LF;
@ -104,7 +101,7 @@ LB8: ZW ÷;
# LB8a, from Emoji proposal L2/16-011R3
# ZWJ x ID
LB8a: ZJ (ID | EB | EM);
LB8a: ZWJ (ID | EB | EM);
# LB9: X CM -> X
@ -139,11 +136,11 @@ LB19: . CM* QU;
LB19.1: QU CM* [^CM];
# LB 20 Break before and after CB.
# Interaction with LB8a: ZJ x ID is tricky because CM includes ZJ.
# ZJ acts like a CM to the left, combining with CB.
# ZJ acts independently to the right, no break from ID by LB8a.
# Interaction with LB8a: ZWJ x ID is tricky because CM includes ZWJ.
# ZWJ acts like a CM to the left, combining with CB.
# ZWJ acts independently to the right, no break from ID by LB8a.
LB20: . CM* ÷ CB;
LB20.1a: CB CM* ZJ (ID | EB | EM);
LB20.1a: CB CM* ZWJ (ID | EB | EM);
LB20.1b: CB CM* ÷;
# Note: Rule 21a must come before 21 to prevent 21.1 from matching HL BA, then
@ -193,7 +190,7 @@ LB30.2: CP CM* (AL | HL | NU);
# LB31 keep pairs of RI together.
LB30a.1: RI CM* RI CM* [BK CR LF NL SP ZW WJ GL CL CP EX IS SY QU BA HY NS];
LB30a.2: RI CM* RI CM* ZJ (ID | EB | EM);
LB30a.2: RI CM* RI CM* ZWJ (ID | EB | EM);
LB30a.3: RI CM* RI CM* ÷;
# LB30b Do not break between Emoji Base and Emoji Modifier
@ -201,5 +198,5 @@ LB30b: EB CM* EM;
# LB31 Break Everywhere Else.
# Include combining marks
LB31.1: . CM* ZJ (ID | EB | EM);
LB31.1: . CM* ZWJ (ID | EB | EM);
LB31.2: . CM* ÷;

41
icu4c/source/test/testdata/break_rules/line_loose_cj.txt vendored
View file

@ -9,7 +9,7 @@
# They are expected to change with review and the addition of support for rule tailoring.
#
# Line Breaking Rules
# Implement default line breaking as defined by
# Implement default line breaking as defined by
# Unicode Standard Annex #14 Revision 34 for Unicode 8.0
# http://www.unicode.org/reports/tr14/
# tailored as noted in 2nd paragraph below..
@ -34,7 +34,7 @@ locale = ja@lb=loose;
AI = [:LineBreak = Ambiguous:];
AL = [[:LineBreak = Alphabetic:]-[\u2764]];
AL = [[:LineBreak = Alphabetic:]];
BAX = [\u2010 \u2013];
BA = [[:LineBreak = Break_After:] - BAX];
BB = [:LineBreak = Break_Before:];
@ -46,10 +46,8 @@ CL = [:LineBreak = Close_Punctuation:];
CM = [:LineBreak = Combining_Mark:];
CP = [:LineBreak = Close_Parenthesis:];
CR = [:LineBreak = Carriage_Return:];
EB = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
EM = [\U0001F3FB-\U0001F3FF];
EB = [:LineBreak = EB:];
EM = [:LineBreak = EM:];
EXX = [\uFF01 \uFF1F];
EX = [[:LineBreak = Exclamation:] - EXX];
GL = [:LineBreak = Glue:];
@ -57,7 +55,7 @@ HL = [:LineBreak = Hebrew_Letter:];
HY = [:LineBreak = Hyphen:];
H2 = [:LineBreak = H2:];
H3 = [:LineBreak = H3:];
ID = [[:LineBreak = Ideographic:][\u2764]CJ];
ID = [[:LineBreak = Ideographic:] CJ]; # CSS Loose tailoring: CJ resolves to ID
IN = [:LineBreak = Inseperable:];
IS = [:LineBreak = Infix_Numeric:];
JL = [:LineBreak = JL:];
@ -82,16 +80,15 @@ SY = [:LineBreak = Break_Symbols:];
WJ = [:LineBreak = Word_Joiner:];
XX = [:LineBreak = Unknown:];
ZW = [:LineBreak = ZWSpace:];
ZJ = [\u200D];
ZWJ = [:LineBreak = ZWJ:];
# TODO: adjustment to sets needed only until Unicode properties are updated for Emoji.
ID = [ID - EB];
AL = [AL - EM];
# LB1 - Resolve AI, CB, CJ, SA, SG, and XX into other line breaking classes
AL = [AL AI SG XX ];
dictionary = SA;
dictionary = [:LineBreak = Complex_Context:];
# Redfine AL. LB1. TODO: refine according to latest UAX.
AL = [ AL AI SA SG XX ];
# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
# list it in the numerous rules that use CM.
CM = [CM ZWJ];
LB4: BK ÷;
LB5: CR LF;
@ -121,7 +118,7 @@ LB8: ZW ÷;
# LB8a, from Emoji proposal L2/16-011R3
# ZWJ x ID
LB8a: ZJ (ID | EB | EM);
LB8a: ZWJ (ID | EB | EM);
# LB9: X CM -> X
@ -156,11 +153,11 @@ LB19: . CM* QU;
LB19.1: QU CM* [^CM];
# LB 20 Break before and after CB.
# Interaction with LB8a: ZJ x ID is tricky because CM includes ZJ.
# ZJ acts like a CM to the left, combining with CB.
# ZJ acts independently to the right, no break from ID by LB8a.
# Interaction with LB8a: ZWJ x ID is tricky because CM includes ZWJ.
# ZWJ acts like a CM to the left, combining with CB.
# ZWJ acts independently to the right, no break from ID by LB8a.
LB20: . CM* ÷ CB;
LB20.1a: CB CM* ZJ (ID | EB | EM);
LB20.1a: CB CM* ZWJ (ID | EB | EM);
LB20.1b: CB CM* ÷;
# Note: Rule 21a must come before 21 to prevent 21.1 from matching HL BA, then
@ -214,7 +211,7 @@ LB30.2: CP CM* (AL | HL | NU);
# LB31 keep pairs of RI together.
LB30a.1: RI CM* RI CM* [BK CR LF NL SP ZW WJ GL CL CP EX IS SY QU BA HY NS];
LB30a.2: RI CM* RI CM* ZJ (ID | EB | EM);
LB30a.2: RI CM* RI CM* ZWJ (ID | EB | EM);
LB30a.3: RI CM* RI CM* ÷;
# LB30b Do not break between Emoji Base and Emoji Modifier
@ -222,5 +219,5 @@ LB30b: EB CM* EM;
# LB31 Break Everywhere Else.
# Include combining marks
LB31.1: . CM* ZJ (ID | EB | EM);
LB31.1: . CM* ZWJ (ID | EB | EM);
LB31.2: . CM* ÷;

45
icu4c/source/test/testdata/break_rules/line_normal.txt vendored
View file

@ -9,17 +9,17 @@
# They are expected to change with review and the addition of support for rule tailoring.
#
# Line Breaking Rules
# Implement default line breaking as defined by
# Implement default line breaking as defined by
# Unicode Standard Annex #14 Revision 34 for Unicode 8.0
# http://www.unicode.org/reports/tr14/
# tailored as noted in 2nd paragraph below..
# tailored as noted in 2nd paragraph below.
#
# TODO: Rule LB 8 remains as it was in Unicode 5.2
# This is only because of a limitation of ICU break engine implementation,
# not because the older behavior is desirable.
#
# This tailors the line break behavior to correspond to CSS
# line-break=normal (BCP47 -u-lb-normal) as defined for languages other than
# line-break=normal (BCP47 -u-lb-normal) as defined for languages other than
# Chinese & Japanese.
# It sets characters of class CJ to behave like ID.
@ -28,7 +28,7 @@ type = line;
locale = en@lb=normal;
AI = [:LineBreak = Ambiguous:];
AL = [[:LineBreak = Alphabetic:]-[\u2764]];
AL = [:LineBreak = Alphabetic:];
BA = [:LineBreak = Break_After:];
BB = [:LineBreak = Break_Before:];
BK = [:LineBreak = Mandatory_Break:];
@ -39,17 +39,15 @@ CL = [:LineBreak = Close_Punctuation:];
CM = [:LineBreak = Combining_Mark:];
CP = [:LineBreak = Close_Parenthesis:];
CR = [:LineBreak = Carriage_Return:];
EB = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
EM = [\U0001F3FB-\U0001F3FF];
EB = [:LineBreak = EB:];
EM = [:LineBreak = EM:];
EX = [:LineBreak = Exclamation:];
GL = [:LineBreak = Glue:];
HL = [:LineBreak = Hebrew_Letter:];
HY = [:LineBreak = Hyphen:];
H2 = [:LineBreak = H2:];
H3 = [:LineBreak = H3:];
ID = [[:LineBreak = Ideographic:] CJ [\u2764]];
ID = [[:LineBreak = Ideographic:] CJ]; # CSS Normal tailoring: CJ resolves to ID
IN = [:LineBreak = Inseperable:];
IS = [:LineBreak = Infix_Numeric:];
JL = [:LineBreak = JL:];
@ -71,16 +69,15 @@ SY = [:LineBreak = Break_Symbols:];
WJ = [:LineBreak = Word_Joiner:];
XX = [:LineBreak = Unknown:];
ZW = [:LineBreak = ZWSpace:];
ZJ = [\u200D];
ZWJ = [:LineBreak = ZWJ:];
# TODO: adjustment to sets needed only until Unicode properties are updated for Emoji.
ID = [ID - EB];
AL = [AL - EM];
# LB1 - Resolve AI, CB, CJ, SA, SG, and XX into other line breaking classes
AL = [AL AI SG XX ];
dictionary = SA;
dictionary = [:LineBreak = Complex_Context:];
# Redfine AL. LB1. TODO: refine according to latest UAX.
AL = [ AL AI SA SG XX ];
# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
# list it in the numerous rules that use CM.
CM = [CM ZWJ];
LB4: BK ÷;
LB5: CR LF;
@ -110,7 +107,7 @@ LB8: ZW ÷;
# LB8a, from Emoji proposal L2/16-011R3
# ZWJ x ID
LB8a: ZJ (ID | EB | EM);
LB8a: ZWJ (ID | EB | EM);
# LB9: X CM -> X
@ -145,11 +142,11 @@ LB19: . CM* QU;
LB19.1: QU CM* [^CM];
# LB 20 Break before and after CB.
# Interaction with LB8a: ZJ x ID is tricky because CM includes ZJ.
# ZJ acts like a CM to the left, combining with CB.
# ZJ acts independently to the right, no break from ID by LB8a.
# Interaction with LB8a: ZWJ x ID is tricky because CM includes ZWJ.
# ZWJ acts like a CM to the left, combining with CB.
# ZWJ acts independently to the right, no break from ID by LB8a.
LB20: . CM* ÷ CB;
LB20.1a: CB CM* ZJ (ID | EB | EM);
LB20.1a: CB CM* ZWJ (ID | EB | EM);
LB20.1b: CB CM* ÷;
# Note: Rule 21a must come before 21 to prevent 21.1 from matching HL BA, then
@ -199,7 +196,7 @@ LB30.2: CP CM* (AL | HL | NU);
# LB31 keep pairs of RI together.
LB30a.1: RI CM* RI CM* [BK CR LF NL SP ZW WJ GL CL CP EX IS SY QU BA HY NS];
LB30a.2: RI CM* RI CM* ZJ (ID | EB | EM);
LB30a.2: RI CM* RI CM* ZWJ (ID | EB | EM);
LB30a.3: RI CM* RI CM* ÷;
# LB30b Do not break between Emoji Base and Emoji Modifier
@ -207,5 +204,5 @@ LB30b: EB CM* EM;
# LB31 Break Everywhere Else.
# Include combining marks
LB31.1: . CM* ZJ (ID | EB | EM);
LB31.1: . CM* ZWJ (ID | EB | EM);
LB31.2: . CM* ÷;

43
icu4c/source/test/testdata/break_rules/line_normal_cj.txt vendored
View file

@ -8,10 +8,10 @@
# They are expected to change with review and the addition of support for rule tailoring.
#
# Line Breaking Rules
# Implement default line breaking as defined by
# Implement default line breaking as defined by
# Unicode Standard Annex #14 Revision 34 for Unicode 8.0
# http://www.unicode.org/reports/tr14/
# tailored as noted in 2nd paragraph below..
# tailored as noted in 2nd paragraph below.
#
# TODO: Rule LB 8 remains as it was in Unicode 5.2
# This is only because of a limitation of ICU break engine implementation,
@ -27,7 +27,7 @@ type = line;
locale = ja@lb=normal;
AI = [:LineBreak = Ambiguous:];
AL = [[:LineBreak = Alphabetic:]-[\u2764]];
AL = [:LineBreak = Alphabetic:];
BAX = [\u2010 \u2013];
BA = [[:LineBreak = Break_After:] - BAX];
BB = [:LineBreak = Break_Before:];
@ -39,17 +39,15 @@ CL = [:LineBreak = Close_Punctuation:];
CM = [:LineBreak = Combining_Mark:];
CP = [:LineBreak = Close_Parenthesis:];
CR = [:LineBreak = Carriage_Return:];
EB = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
EM = [\U0001F3FB-\U0001F3FF];
EB = [:LineBreak = EB:];
EM = [:LineBreak = EM:];
EX = [:LineBreak = Exclamation:];
GL = [:LineBreak = Glue:];
HL = [:LineBreak = Hebrew_Letter:];
HY = [:LineBreak = Hyphen:];
H2 = [:LineBreak = H2:];
H3 = [:LineBreak = H3:];
ID = [[:LineBreak = Ideographic:] CJ [\u2764]];
ID = [[:LineBreak = Ideographic:] CJ]; # CSS Normal tailoring: CJ resolves to ID
IN = [:LineBreak = Inseperable:];
IS = [:LineBreak = Infix_Numeric:];
JL = [:LineBreak = JL:];
@ -72,16 +70,15 @@ SY = [:LineBreak = Break_Symbols:];
WJ = [:LineBreak = Word_Joiner:];
XX = [:LineBreak = Unknown:];
ZW = [:LineBreak = ZWSpace:];
ZJ = [\u200D];
ZWJ = [:LineBreak = ZWJ:];
# TODO: adjustment to sets needed only until Unicode properties are updated for Emoji.
ID = [ID - EB];
AL = [AL - EM];
# LB1 - Resolve AI, CB, CJ, SA, SG, and XX into other line breaking classes
AL = [AL AI SG XX ];
dictionary = SA;
dictionary = [:LineBreak = Complex_Context:];
# Redfine AL. LB1. TODO: refine according to latest UAX.
AL = [ AL AI SA SG XX ];
# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
# list it in the numerous rules that use CM.
CM = [CM ZWJ];
LB4: BK ÷;
LB5: CR LF;
@ -114,7 +111,7 @@ LB8: ZW ÷;
# LB8a, from Emoji proposal L2/16-011R3
# ZWJ x ID
LB8a: ZJ (ID | EB | EM);
LB8a: ZWJ (ID | EB | EM);
# LB9: X CM -> X
@ -149,11 +146,11 @@ LB19: . CM* QU;
LB19.1: QU CM* [^CM];
# LB 20 Break before and after CB.
# Interaction with LB8a: ZJ x ID is tricky because CM includes ZJ.
# ZJ acts like a CM to the left, combining with CB.
# ZJ acts independently to the right, no break from ID by LB8a.
# Interaction with LB8a: ZWJ x ID is tricky because CM includes ZWJ.
# ZWJ acts like a CM to the left, combining with CB.
# ZWJ acts independently to the right, no break from ID by LB8a.
LB20: . CM* ÷ CB;
LB20.1a: CB CM* ZJ (ID | EB | EM);
LB20.1a: CB CM* ZWJ (ID | EB | EM);
LB20.1b: CB CM* ÷;
# Note: Rule 21a must come before 21 to prevent 21.1 from matching HL BA, then
@ -207,7 +204,7 @@ LB30.2: CP CM* (AL | HL | NU);
# LB31 keep pairs of RI together.
LB30a.1: RI CM* RI CM* [BK CR LF NL SP ZW WJ GL CL CP EX IS SY QU BA HY NS];
LB30a.2: RI CM* RI CM* ZJ (ID | EB | EM);
LB30a.2: RI CM* RI CM* ZWJ (ID | EB | EM);
LB30a.3: RI CM* RI CM* ÷;
# LB30b Do not break between Emoji Base and Emoji Modifier
@ -215,5 +212,5 @@ LB30b: EB CM* EM;
# LB31 Break Everywhere Else.
# Include combining marks
LB31.1: . CM* ZJ (ID | EB | EM);
LB31.1: . CM* ZWJ (ID | EB | EM);
LB31.2: . CM* ÷;

31
icu4c/source/test/testdata/break_rules/word.txt vendored
View file

@ -12,17 +12,14 @@
type = word; # one of grapheme | word | line | sentence
locale = en;
E_Base = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
E_Modifier = [\U0001F3FB-\U0001F3FF];
ZWJ = [\u200D];
GAZ = [\U0001F466-\U0001F469\U0001F48B\U0001F5E8\u2764];
CR = [\p{Word_Break = CR}];
LF = [\p{Word_Break = LF}];
Newline = [\p{Word_Break = Newline}];
Extend = [[[\p{Word_Break = Extend}][:Block=Tags:]]-ZWJ];
Extend = [\p{Word_Break = Extend}];
ZWJ = [\p{Word_Break = ZWJ}];
Regional_Indicator = [\p{Word_Break = Regional_Indicator}];
Format = [[\p{Word_Break = Format}]-[:Block=Tags:]];
Format = [\p{Word_Break = Format}];
Katakana = [\p{Word_Break = Katakana}];
Hebrew_Letter = [\p{Word_Break = Hebrew_Letter}];
ALetter = [\p{Word_Break = ALetter}];
@ -33,6 +30,10 @@ MidLetter = [\p{Word_Break = MidLetter}];
MidNum = [\p{Word_Break = MidNum}];
Numeric = [\p{Word_Break = Numeric}];
ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
E_Base = [\p{Word_Break = EB}];
E_Modifier = [\p{Word_Break = EM}];
GAZ = [\p{Word_Break = GAZ}];
EBG = [\p{Word_Break = EBG}];
#define dicitionary, with the effect being that those characters don't appear in test data.
@ -63,7 +64,7 @@ WB3: CR LF;
WB3a: (Newline | CR | LF) ÷;
WB3b: . ÷ (Newline | CR | LF); # actually redundant? No other rule combines.
# (but needed with UAX treat-as scheme.)
WB3c: ZWJ GAZ;
WB3c: ZWJ (GAZ | EBG);
WB5: AHLetter ExtFmt* AHLetter;
@ -83,15 +84,15 @@ WB13: Katakana ExtFmt* Katakana;
WB13a: (AHLetter | Numeric | Katakana | ExtendNumLet) ExtFmt* ExtendNumLet;
WB13b: ExtendNumLet ExtFmt* (AHLetter | Numeric | Katakana);
# WB rule 13c, pairs of Regional Indicators stay unbroken.
# WB rule 15 - 17, pairs of Regional Indicators stay unbroken.
# Interacts with WB3c.
WB13c.1: Regional_Indicator ExtFmt* Regional_Indicator ExtFmt* ZWJ GAZ;
WB13c.2: Regional_Indicator ExtFmt* Regional_Indicator ExtFmt* ÷;
WB15: Regional_Indicator ExtFmt* Regional_Indicator ExtFmt* ZWJ (GAZ | EBG);
WB17: Regional_Indicator ExtFmt* Regional_Indicator ExtFmt* ÷;
WB13d: (E_Base | GAZ) ExtFmt* E_Modifier;
WB14: (E_Base | EBG) ExtFmt* E_Modifier;
# Rule WB 14 Any ÷ Any
# Interacts with WB3c, do not break between ZWJ and GAZ.
WB14.1: . ExtFmt* ZWJ GAZ;
WB14.2: . ExtFmt* ÷;
# Rule WB 999 Any ÷ Any
# Interacts with WB3c, do not break between ZWJ and (GAZ | EBG).
WB999.1: . ExtFmt* ZWJ (GAZ | EBG);
WB999.2: . ExtFmt* ÷;

31
icu4c/source/test/testdata/break_rules/word_POSIX.txt vendored
View file

@ -11,17 +11,14 @@
type = word; # one of grapheme | word | line | sentence
locale = en_US_POSIX;
E_Base = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
E_Modifier = [\U0001F3FB-\U0001F3FF];
ZWJ = [\u200D];
GAZ = [\U0001F466-\U0001F469\U0001F48B\U0001F5E8\u2764];
CR = [\p{Word_Break = CR}];
LF = [\p{Word_Break = LF}];
Newline = [\p{Word_Break = Newline}];
Extend = [[[\p{Word_Break = Extend}][:Block=Tags:]]-ZWJ];
Extend = [\p{Word_Break = Extend}];
ZWJ = [\p{Word_Break = ZWJ}];
Regional_Indicator = [\p{Word_Break = Regional_Indicator}];
Format = [[\p{Word_Break = Format}]-[:Block=Tags:]];
Format = [\p{Word_Break = Format}];
Katakana = [\p{Word_Break = Katakana}];
Hebrew_Letter = [\p{Word_Break = Hebrew_Letter}];
ALetter = [\p{Word_Break = ALetter}];
@ -32,6 +29,10 @@ MidLetter = [\p{Word_Break = MidLetter} - [\:]];
MidNum = [\p{Word_Break = MidNum} [.]];
Numeric = [\p{Word_Break = Numeric}];
ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
E_Base = [\p{Word_Break = EB}];
E_Modifier = [\p{Word_Break = EM}];
GAZ = [\p{Word_Break = GAZ}];
EBG = [\p{Word_Break = EBG}];
#define dicitionary, with the effect being that those characters don't appear in test data.
@ -62,7 +63,7 @@ WB3: CR LF;
WB3a: (Newline | CR | LF) ÷;
WB3b: . ÷ (Newline | CR | LF); # actually redundant? No other rule combines.
# (but needed with UAX treat-as scheme.)
WB3c: ZWJ GAZ;
WB3c: ZWJ (GAZ | EBG);
WB5: AHLetter ExtFmt* AHLetter;
@ -82,15 +83,15 @@ WB13: Katakana ExtFmt* Katakana;
WB13a: (AHLetter | Numeric | Katakana | ExtendNumLet) ExtFmt* ExtendNumLet;
WB13b: ExtendNumLet ExtFmt* (AHLetter | Numeric | Katakana);
# WB rule 13c, pairs of Regional Indicators stay unbroken.
# WB rule 15 - 17, pairs of Regional Indicators stay unbroken.
# Interacts with WB3c.
WB13c.1: Regional_Indicator ExtFmt* Regional_Indicator ExtFmt* ZWJ GAZ;
WB13c.2: Regional_Indicator ExtFmt* Regional_Indicator ExtFmt* ÷;
WB15: Regional_Indicator ExtFmt* Regional_Indicator ExtFmt* ZWJ (GAZ | EBG);
WB17: Regional_Indicator ExtFmt* Regional_Indicator ExtFmt* ÷;
WB13d: (E_Base | GAZ) ExtFmt* E_Modifier;
WB14: (E_Base | EBG) ExtFmt* E_Modifier;
# Rule WB 14 Any ÷ Any
# Interacts with WB3c, do not break between ZWJ and GAZ.
WB14.1: . ExtFmt* ZWJ GAZ;
WB14.2: . ExtFmt* ÷;
# Rule WB 999 Any ÷ Any
# Interacts with WB3c, do not break between ZWJ and (GAZ | EBG).
WB999.1: . ExtFmt* ZWJ (GAZ | EBG);
WB999.2: . ExtFmt* ÷;

4
icu4c/source/tools/gennorm2/n2builder.cpp
View file

@ -1,7 +1,7 @@
/*
*******************************************************************************
*
* Copyright (C) 2009-2014, International Business Machines
* Copyright (C) 2009-2016, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
@ -1247,6 +1247,7 @@ Normalizer2DataBuilder::writeCSourceFile(const char *filename) {
exit(U_FILE_ACCESS_ERROR);
return;
}
fputs("#ifdef INCLUDED_FROM_NORMALIZER2_CPP\n\n", f);
char line[100];
sprintf(line, "static const UVersionInfo %s_formatVersion={", dataName.data());
usrc_writeArray(f, line, dataInfo.formatVersion, 8, 4, "};\n");
@ -1287,6 +1288,7 @@ Normalizer2DataBuilder::writeCSourceFile(const char *filename) {
line,
norm16Trie, line2, NULL,
"};\n");
fputs("\n#endif // INCLUDED_FROM_NORMALIZER2_CPP\n", f);
fclose(f);
}