unicode: Import version 15.1 (UCD version 32)

Add enumerator for the new Unicode version to QChar::UnicodeVersion.

Remap new line breaking classes to their Unicode 15.0 values:
* AK, AP and AS to AL,
* VI and VF to CM.
These are classes for new line breaking support for Indic scripts
that require more work.

Blacklist failing tests for now:
* tst_QUrlUts46::idnaTestV2
* tst_QTextBoundaryFinder::lineBoundariesDefault
* tst_QTextBoundaryFinder::graphemeBoundariesDefault

Regenerate the source files.

Task-number: QTBUG-121529
Change-Id: I869cc9fbaa53765d8ae6265c22cdbef9f19d05bf
Reviewed-by: Mårten Nordheim <marten.nordheim@qt.io>
Reviewed-by: Edward Welbourne <edward.welbourne@qt.io>
This commit is contained in:
Ievgenii Meshcheriakov 2024-01-25 12:18:48 +01:00 committed by Mårten Nordheim
parent 25b89f2c88
commit bfd09ec38c
30 changed files with 23569 additions and 14108 deletions

View File

@ -157,6 +157,7 @@ QT_BEGIN_NAMESPACE
\value [since 5.15] Unicode_13_0 Version 13.0 \value [since 5.15] Unicode_13_0 Version 13.0
\value [since 6.3] Unicode_14_0 Version 14.0 \value [since 6.3] Unicode_14_0 Version 14.0
\value [since 6.5] Unicode_15_0 Version 15.0 \value [since 6.5] Unicode_15_0 Version 15.0
\value [since 6.8] Unicode_15_1 Version 15.1
\value Unicode_Unassigned The value is not assigned to any character \value Unicode_Unassigned The value is not assigned to any character
in version 8.0 of Unicode. in version 8.0 of Unicode.

View File

@ -432,6 +432,7 @@ public:
Unicode_13_0, Unicode_13_0,
Unicode_14_0, Unicode_14_0,
Unicode_15_0, Unicode_15_0,
Unicode_15_1,
}; };
inline Category category() const noexcept { return QChar::category(ucs); } inline Category category() const noexcept { return QChar::category(ucs); }

File diff suppressed because it is too large Load Diff

View File

@ -1,7 +1,7 @@
// Copyright (C) 2020 The Qt Company Ltd. // Copyright (C) 2020 The Qt Company Ltd.
// SPDX-License-Identifier: LicenseRef-Qt-Commercial OR LGPL-3.0-only OR GPL-2.0-only OR GPL-3.0-only // SPDX-License-Identifier: LicenseRef-Qt-Commercial OR LGPL-3.0-only OR GPL-2.0-only OR GPL-3.0-only
/* This file is autogenerated from the Unicode 15.0 database. Do not edit */ /* This file is autogenerated from the Unicode 15.1 database. Do not edit */
// //
// W A R N I N G // W A R N I N G
@ -23,7 +23,7 @@
QT_BEGIN_NAMESPACE QT_BEGIN_NAMESPACE
#define UNICODE_DATA_VERSION QChar::Unicode_15_0 #define UNICODE_DATA_VERSION QChar::Unicode_15_1
namespace QUnicodeTables { namespace QUnicodeTables {
@ -142,7 +142,8 @@ enum SentenceBreakClass {
}; };
// see http://www.unicode.org/reports/tr14/tr14-30.html // see http://www.unicode.org/reports/tr14/tr14-30.html
// we don't use the XX and AI classes and map them to AL instead. // we don't use the XX, AK, AP, AS and AI classes and map them to AL instead.
// VI and VF classes are mapped to CM.
enum LineBreakClass { enum LineBreakClass {
LineBreak_OP, LineBreak_CL, LineBreak_CP, LineBreak_QU, LineBreak_GL, LineBreak_OP, LineBreak_CL, LineBreak_CP, LineBreak_QU, LineBreak_GL,
LineBreak_NS, LineBreak_EX, LineBreak_SY, LineBreak_IS, LineBreak_PR, LineBreak_NS, LineBreak_EX, LineBreak_SY, LineBreak_IS, LineBreak_PR,

View File

@ -0,0 +1,3 @@
# QTBUG-121529: Tests need to be updated to Unicode 15.1
[idnaTestV2]
*

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,7 @@
# QTBUG-121529: Tests need to be updated to Unicode 15.1
[lineBoundariesDefault]
*
# QTBUG-121529: Tests need to be updated to Unicode 15.1
[graphemeBoundariesDefault]
*

File diff suppressed because one or more lines are too long

View File

@ -1,6 +1,6 @@
# SentenceBreakTest-15.0.0.txt # SentenceBreakTest-15.1.0.txt
# Date: 2022-02-26, 00:39:00 GMT # Date: 2023-04-05, 20:41:29 GMT
# © 2022 Unicode®, Inc. # © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html # For terms of use, see https://www.unicode.org/terms_of_use.html
# #
@ -500,6 +500,11 @@
÷ 0065 × 0074 × 0063 × 002E × 3002 ÷ # ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [8.1] IDEOGRAPHIC FULL STOP (STerm) ÷ [0.3] ÷ 0065 × 0074 × 0063 × 002E × 3002 ÷ # ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [8.1] IDEOGRAPHIC FULL STOP (STerm) ÷ [0.3]
÷ 5B57 × 3002 ÷ 5B83 ÷ # ÷ [0.2] CJK UNIFIED IDEOGRAPH-5B57 (OLetter) × [998.0] IDEOGRAPHIC FULL STOP (STerm) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B83 (OLetter) ÷ [0.3] ÷ 5B57 × 3002 ÷ 5B83 ÷ # ÷ [0.2] CJK UNIFIED IDEOGRAPH-5B57 (OLetter) × [998.0] IDEOGRAPHIC FULL STOP (STerm) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B83 (OLetter) ÷ [0.3]
÷ 0021 × 0020 × 0020 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [9.0] SPACE (Sp) × [10.0] SPACE (Sp) ÷ [0.3] ÷ 0021 × 0020 × 0020 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [9.0] SPACE (Sp) × [10.0] SPACE (Sp) ÷ [0.3]
÷ 0061 × 002E ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] FULL STOP (ATerm) ÷ [0.3]
÷ 0061 × 002E × 000D × 000A ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] FULL STOP (ATerm) × [9.0] <CARRIAGE RETURN (CR)> (CR) × [3.0] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 0061 × 002E × 000D × 000A ÷ 0020 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] FULL STOP (ATerm) × [9.0] <CARRIAGE RETURN (CR)> (CR) × [3.0] <LINE FEED (LF)> (LF) ÷ [4.0] SPACE (Sp) ÷ [0.3]
÷ 0061 × 002E × 000D × 000A ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] FULL STOP (ATerm) × [9.0] <CARRIAGE RETURN (CR)> (CR) × [3.0] <LINE FEED (LF)> (LF) ÷ [4.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
÷ 0041 × 002E × 000D × 000A ÷ 0041 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] FULL STOP (ATerm) × [9.0] <CARRIAGE RETURN (CR)> (CR) × [3.0] <LINE FEED (LF)> (LF) ÷ [4.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
÷ 2060 × 0028 × 2060 × 0022 × 2060 × 0047 × 2060 × 006F × 2060 × 002E × 2060 × 0022 × 2060 × 0029 × 2060 × 0020 × 2060 ÷ 0028 × 2060 × 0048 × 2060 × 0065 × 2060 × 0020 × 2060 × 0064 × 2060 × 0069 × 2060 × 0064 × 2060 × 002E × 2060 × 0029 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER G (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER O (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER H (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER I (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] ÷ 2060 × 0028 × 2060 × 0022 × 2060 × 0047 × 2060 × 006F × 2060 × 002E × 2060 × 0022 × 2060 × 0029 × 2060 × 0020 × 2060 ÷ 0028 × 2060 × 0048 × 2060 × 0065 × 2060 × 0020 × 2060 × 0064 × 2060 × 0069 × 2060 × 0064 × 2060 × 002E × 2060 × 0029 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER G (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER O (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER H (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER I (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
÷ 2060 × 0028 × 2060 × 201C × 2060 × 0047 × 2060 × 006F × 2060 × 003F × 2060 × 201D × 2060 × 0029 × 2060 × 0020 × 2060 ÷ 0028 × 2060 × 0048 × 2060 × 0065 × 2060 × 0020 × 2060 × 0064 × 2060 × 0069 × 2060 × 0064 × 2060 × 002E × 2060 × 0029 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LEFT DOUBLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER G (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER O (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] QUESTION MARK (STerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT DOUBLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER H (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER I (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] ÷ 2060 × 0028 × 2060 × 201C × 2060 × 0047 × 2060 × 006F × 2060 × 003F × 2060 × 201D × 2060 × 0029 × 2060 × 0020 × 2060 ÷ 0028 × 2060 × 0048 × 2060 × 0065 × 2060 × 0020 × 2060 × 0064 × 2060 × 0069 × 2060 × 0064 × 2060 × 002E × 2060 × 0029 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LEFT DOUBLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER G (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER O (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] QUESTION MARK (STerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT DOUBLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER H (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER I (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
÷ 2060 × 0055 × 2060 × 002E × 2060 × 0053 × 2060 × 002E × 2060 × 0041 × 2060 × 0300 × 002E × 2060 × 0020 × 2060 × 0069 × 2060 × 0073 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER U (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER S (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER A (Upper) × [5.0] WORD JOINER (Format_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [8.0] LATIN SMALL LETTER I (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER S (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] ÷ 2060 × 0055 × 2060 × 002E × 2060 × 0053 × 2060 × 002E × 2060 × 0041 × 2060 × 0300 × 002E × 2060 × 0020 × 2060 × 0069 × 2060 × 0073 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER U (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER S (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER A (Upper) × [5.0] WORD JOINER (Format_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [8.0] LATIN SMALL LETTER I (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER S (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
@ -524,7 +529,12 @@
÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 3002 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] 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 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 3002 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] 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) × [998.0] CJK UNIFIED IDEOGRAPH-5B57 (OLetter) × [5.0] WORD JOINER (Format_FE) × [998.0] 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 × 5B57 × 2060 × 3002 × 2060 ÷ 5B83 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] CJK UNIFIED IDEOGRAPH-5B57 (OLetter) × [5.0] WORD JOINER (Format_FE) × [998.0] 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) × [998.0] 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] ÷ 2060 × 0021 × 2060 × 0020 × 2060 × 0020 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] 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]
÷ 2060 × 0061 × 2060 × 002E × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER A (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
÷ 2060 × 0061 × 2060 × 002E × 2060 × 000D ÷ 2060 × 000A ÷ 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER A (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] WORD JOINER (Format_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [4.0] WORD JOINER (Format_FE) ÷ [0.3]
÷ 2060 × 0061 × 2060 × 002E × 2060 × 000D ÷ 2060 × 000A ÷ 0020 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER A (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] WORD JOINER (Format_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [4.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
÷ 2060 × 0061 × 2060 × 002E × 2060 × 000D ÷ 2060 × 000A ÷ 0061 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER A (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] WORD JOINER (Format_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [4.0] LATIN SMALL LETTER A (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
÷ 2060 × 0041 × 2060 × 002E × 2060 × 000D ÷ 2060 × 000A ÷ 0041 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] WORD JOINER (Format_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [4.0] LATIN CAPITAL LETTER A (Upper) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
# #
# Lines: 502 # Lines: 512
# #
# EOF # EOF

View File

@ -6,8 +6,8 @@ td, th { vertical-align: top }
</style></head> </style></head>
<body bgcolor='#FFFFFF'> <body bgcolor='#FFFFFF'>
<h2>Word_Break Chart</h2> <h2>Word_Break Chart</h2>
<p><b>Unicode Version:</b> 15.0.0</p> <p><b>Unicode Version:</b> 15.1.0</p>
<p><b>Date:</b> 2021-11-24, 21:43:58 GMT</p> <p><b>Date:</b> 2023-03-31, 14:30:32 GMT</p>
<p>This page illustrates the application of the Word_Break specification. The material here is informative, not normative.</p> <p>The first chart shows where breaks would appear between different sample characters or strings. The sample characters are chosen mechanically to represent the different properties used by the specification.</p><p>Each cell shows the break-status for the position between the character(s) in its row header and the character(s) in its column header. The × symbol indicates no break, while the ÷ symbol indicated a break. The cells with × are also shaded to make it easier to scan the table. For example, in the cell at the intersection of the row headed by “CR” and the column headed by “LF”, there is a × symbol, indicating that there is no break between CR and LF.</p> <p>This page illustrates the application of the Word_Break specification. The material here is informative, not normative.</p> <p>The first chart shows where breaks would appear between different sample characters or strings. The sample characters are chosen mechanically to represent the different properties used by the specification.</p><p>Each cell shows the break-status for the position between the character(s) in its row header and the character(s) in its column header. The × symbol indicates no break, while the ÷ symbol indicated a break. The cells with × are also shaded to make it easier to scan the table. For example, in the cell at the intersection of the row headed by “CR” and the column headed by “LF”, there is a × symbol, indicating that there is no break between CR and LF.</p>
<p>After the heavy blue line in the table are additional rows, either with different sample characters or for sequences, such as “ALetter MidLetter”. Some column headers may be composed, reflecting “treat as” or “ignore” rules.</p> <p>After the heavy blue line in the table are additional rows, either with different sample characters or for sequences, such as “ALetter MidLetter”. Some column headers may be composed, reflecting “treat as” or “ignore” rules.</p>
<p>If your browser handles titles (tooltips), then hovering the mouse over the row header will show a sample character of that type. Hovering over a column header will show the sample character, plus its abbreviated general category and script. Hovering over the intersected cells shows the rule number that produces the break-status. For example, hovering over the cell at the intersection of ExtendNumLet and ALetter shows ×, with the rule 13.2. Checking below the table, rule 13.2 is “ExtendNumLet × (AHLetter | Numeric | Katakana)”, which is the one that applies to that case. Note that a rule is invoked only when no lower-numbered rules have applied.</p> <p>If your browser handles titles (tooltips), then hovering the mouse over the row header will show a sample character of that type. Hovering over a column header will show the sample character, plus its abbreviated general category and script. Hovering over the intersected cells shows the rule number that produces the break-status. For example, hovering over the cell at the intersection of ExtendNumLet and ALetter shows ×, with the rule 13.2. Checking below the table, rule 13.2 is “ExtendNumLet × (AHLetter | Numeric | Katakana)”, which is the one that applies to that case. Note that a rule is invoked only when no lower-numbered rules have applied.</p>
@ -89,90 +89,99 @@ td, th { vertical-align: top }
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0646 ARABIC LETTER NOON (ALetter)'>&#x646;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0020 SPACE (WSegSpace)'> </span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0646 ARABIC LETTER NOON (ALetter)'>&#x646;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0020 SPACE (WSegSpace)'> </span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s5' name='s5'>5</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s5' name='s5'>5</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0671 ARABIC LETTER ALEF WASLA (ALetter)'>&#x671;</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0644 ARABIC LETTER LAM (ALetter)'>&#x644;</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0631 ARABIC LETTER REH (ALetter)'>&#x631;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+064E ARABIC FATHA (Extend_FE)'>&#x25CC;&#x64E;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0651 ARABIC SHADDA (Extend_FE)'>&#x25CC;&#x651;</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+062D ARABIC LETTER HAH (ALetter)'>&#x62D;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0650 ARABIC KASRA (Extend_FE)'>&#x25CC;&#x650;</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+064A ARABIC LETTER YEH (ALetter)'>&#x64A;</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0645 ARABIC LETTER MEEM (ALetter)'>&#x645;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0650 ARABIC KASRA (Extend_FE)'>&#x25CC;&#x650;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0020 SPACE (WSegSpace)'> </span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+06DD ARABIC END OF AYAH (Numeric)'>&#x25A1;</span><span title='8.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0661 ARABIC-INDIC DIGIT ONE (Numeric)'>&#x661;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s6' name='s6'>6</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s6' name='s6'>6</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='6.0'><span>&nbsp;</span>&nbsp;</span><span title='U+003A COLON (MidLetter)'>:</span><span title='7.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0721 SYRIAC LETTER MIM (ALetter)'>&#x721;</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0719 SYRIAC LETTER ZAIN (ALetter)'>&#x719;</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0721 SYRIAC LETTER MIM (ALetter)'>&#x721;</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0718 SYRIAC LETTER WAW (ALetter)'>&#x718;</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+072A SYRIAC LETTER RISH (ALetter)'>&#x72A;</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0710 SYRIAC LETTER ALAPH (ALetter)'>&#x710;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0020 SPACE (WSegSpace)'> </span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+070F SYRIAC ABBREVIATION MARK (ALetter)'>&#x25A1;</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+071D SYRIAC LETTER YUDH (ALetter)'>&#x71D;</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0717 SYRIAC LETTER HE (ALetter)'>&#x717;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s7' name='s7'>7</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s7' name='s7'>7</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+003A COLON (MidLetter)'>:</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+003A COLON (MidLetter)'>:</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+072C SYRIAC LETTER TAW (ALetter)'>&#x72C;</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+070F SYRIAC ABBREVIATION MARK (ALetter)'>&#x25A1;</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+072B SYRIAC LETTER SHIN (ALetter)'>&#x72B;</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0712 SYRIAC LETTER BETH (ALetter)'>&#x712;</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0718 SYRIAC LETTER WAW (ALetter)'>&#x718;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s8' name='s8'>8</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s8' name='s8'>8</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+05D0 HEBREW LETTER ALEF (Hebrew_Letter)'>&#x5D0;</span><span title='7.1'><span>&nbsp;</span>&nbsp;</span><span title='U+0027 APOSTROPHE (Single_Quote)'>'</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s9' name='s9'>9</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s9' name='s9'>9</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+05D0 HEBREW LETTER ALEF (Hebrew_Letter)'>&#x5D0;</span><span title='7.2'><span>&nbsp;</span>&nbsp;</span><span title='U+0022 QUOTATION MARK (Double_Quote)'>&quot;</span><span title='7.3'><span>&nbsp;</span>&nbsp;</span><span title='U+05D0 HEBREW LETTER ALEF (Hebrew_Letter)'>&#x5D0;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='6.0'><span>&nbsp;</span>&nbsp;</span><span title='U+003A COLON (MidLetter)'>:</span><span title='7.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s10' name='s10'>10</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s10' name='s10'>10</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='9.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0030 DIGIT ZERO (Numeric)'>0</span><span title='8.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0030 DIGIT ZERO (Numeric)'>0</span><span title='10.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+003A COLON (MidLetter)'>:</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+003A COLON (MidLetter)'>:</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s11' name='s11'>11</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s11' name='s11'>11</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0030 DIGIT ZERO (Numeric)'>0</span><span title='12.0'><span>&nbsp;</span>&nbsp;</span><span title='U+002C COMMA (MidNum)'>,</span><span title='11.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0030 DIGIT ZERO (Numeric)'>0</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+05D0 HEBREW LETTER ALEF (Hebrew_Letter)'>&#x5D0;</span><span title='7.1'><span>&nbsp;</span>&nbsp;</span><span title='U+0027 APOSTROPHE (Single_Quote)'>'</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s12' name='s12'>12</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s12' name='s12'>12</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0030 DIGIT ZERO (Numeric)'>0</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+002C COMMA (MidNum)'>,</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+002C COMMA (MidNum)'>,</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0030 DIGIT ZERO (Numeric)'>0</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+05D0 HEBREW LETTER ALEF (Hebrew_Letter)'>&#x5D0;</span><span title='7.2'><span>&nbsp;</span>&nbsp;</span><span title='U+0022 QUOTATION MARK (Double_Quote)'>&quot;</span><span title='7.3'><span>&nbsp;</span>&nbsp;</span><span title='U+05D0 HEBREW LETTER ALEF (Hebrew_Letter)'>&#x5D0;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s13' name='s13'>13</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s13' name='s13'>13</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+3031 VERTICAL KANA REPEAT MARK (Katakana)'>&#x3031;</span><span title='13.0'><span>&nbsp;</span>&nbsp;</span><span title='U+3031 VERTICAL KANA REPEAT MARK (Katakana)'>&#x3031;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='9.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0030 DIGIT ZERO (Numeric)'>0</span><span title='8.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0030 DIGIT ZERO (Numeric)'>0</span><span title='10.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s14' name='s14'>14</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s14' name='s14'>14</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='13.1'><span>&nbsp;</span>&nbsp;</span><span title='U+005F LOW LINE (ExtendNumLet)'>_</span><span title='13.2'><span>&nbsp;</span>&nbsp;</span><span title='U+0030 DIGIT ZERO (Numeric)'>0</span><span title='13.1'><span>&nbsp;</span>&nbsp;</span><span title='U+005F LOW LINE (ExtendNumLet)'>_</span><span title='13.2'><span>&nbsp;</span>&nbsp;</span><span title='U+3031 VERTICAL KANA REPEAT MARK (Katakana)'>&#x3031;</span><span title='13.1'><span>&nbsp;</span>&nbsp;</span><span title='U+005F LOW LINE (ExtendNumLet)'>_</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0030 DIGIT ZERO (Numeric)'>0</span><span title='12.0'><span>&nbsp;</span>&nbsp;</span><span title='U+002C COMMA (MidNum)'>,</span><span title='11.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0030 DIGIT ZERO (Numeric)'>0</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s15' name='s15'>15</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s15' name='s15'>15</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='13.1'><span>&nbsp;</span>&nbsp;</span><span title='U+005F LOW LINE (ExtendNumLet)'>_</span><span title='13.1'><span>&nbsp;</span>&nbsp;</span><span title='U+005F LOW LINE (ExtendNumLet)'>_</span><span title='13.2'><span>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0030 DIGIT ZERO (Numeric)'>0</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+002C COMMA (MidNum)'>,</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+002C COMMA (MidNum)'>,</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0030 DIGIT ZERO (Numeric)'>0</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s16' name='s16'>16</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s16' name='s16'>16</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F1E6 REGIONAL INDICATOR SYMBOL LETTER A (RI)'>&#x1F1E6;</span><span title='15.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F1E7 REGIONAL INDICATOR SYMBOL LETTER B (RI)'>&#x1F1E7;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F1E8 REGIONAL INDICATOR SYMBOL LETTER C (RI)'>&#x1F1E8;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0062 LATIN SMALL LETTER B (ALetter)'>b</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+3031 VERTICAL KANA REPEAT MARK (Katakana)'>&#x3031;</span><span title='13.0'><span>&nbsp;</span>&nbsp;</span><span title='U+3031 VERTICAL KANA REPEAT MARK (Katakana)'>&#x3031;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s17' name='s17'>17</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s17' name='s17'>17</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0061 LATIN SMALL LETTER A (ALetter)'>a</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F1E6 REGIONAL INDICATOR SYMBOL LETTER A (RI)'>&#x1F1E6;</span><span title='16.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F1E7 REGIONAL INDICATOR SYMBOL LETTER B (RI)'>&#x1F1E7;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F1E8 REGIONAL INDICATOR SYMBOL LETTER C (RI)'>&#x1F1E8;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0062 LATIN SMALL LETTER B (ALetter)'>b</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='13.1'><span>&nbsp;</span>&nbsp;</span><span title='U+005F LOW LINE (ExtendNumLet)'>_</span><span title='13.2'><span>&nbsp;</span>&nbsp;</span><span title='U+0030 DIGIT ZERO (Numeric)'>0</span><span title='13.1'><span>&nbsp;</span>&nbsp;</span><span title='U+005F LOW LINE (ExtendNumLet)'>_</span><span title='13.2'><span>&nbsp;</span>&nbsp;</span><span title='U+3031 VERTICAL KANA REPEAT MARK (Katakana)'>&#x3031;</span><span title='13.1'><span>&nbsp;</span>&nbsp;</span><span title='U+005F LOW LINE (ExtendNumLet)'>_</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s18' name='s18'>18</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s18' name='s18'>18</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0061 LATIN SMALL LETTER A (ALetter)'>a</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F1E6 REGIONAL INDICATOR SYMBOL LETTER A (RI)'>&#x1F1E6;</span><span title='16.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F1E7 REGIONAL INDICATOR SYMBOL LETTER B (RI)'>&#x1F1E7;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F1E8 REGIONAL INDICATOR SYMBOL LETTER C (RI)'>&#x1F1E8;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0062 LATIN SMALL LETTER B (ALetter)'>b</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='13.1'><span>&nbsp;</span>&nbsp;</span><span title='U+005F LOW LINE (ExtendNumLet)'>_</span><span title='13.1'><span>&nbsp;</span>&nbsp;</span><span title='U+005F LOW LINE (ExtendNumLet)'>_</span><span title='13.2'><span>&nbsp;</span>&nbsp;</span><span title='U+0041 LATIN CAPITAL LETTER A (ALetter)'>A</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s19' name='s19'>19</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s19' name='s19'>19</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0061 LATIN SMALL LETTER A (ALetter)'>a</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F1E6 REGIONAL INDICATOR SYMBOL LETTER A (RI)'>&#x1F1E6;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='16.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F1E7 REGIONAL INDICATOR SYMBOL LETTER B (RI)'>&#x1F1E7;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F1E8 REGIONAL INDICATOR SYMBOL LETTER C (RI)'>&#x1F1E8;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0062 LATIN SMALL LETTER B (ALetter)'>b</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F1E6 REGIONAL INDICATOR SYMBOL LETTER A (RI)'>&#x1F1E6;</span><span title='15.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F1E7 REGIONAL INDICATOR SYMBOL LETTER B (RI)'>&#x1F1E7;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F1E8 REGIONAL INDICATOR SYMBOL LETTER C (RI)'>&#x1F1E8;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0062 LATIN SMALL LETTER B (ALetter)'>b</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s20' name='s20'>20</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s20' name='s20'>20</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0061 LATIN SMALL LETTER A (ALetter)'>a</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F1E6 REGIONAL INDICATOR SYMBOL LETTER A (RI)'>&#x1F1E6;</span><span title='16.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F1E7 REGIONAL INDICATOR SYMBOL LETTER B (RI)'>&#x1F1E7;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F1E8 REGIONAL INDICATOR SYMBOL LETTER C (RI)'>&#x1F1E8;</span><span title='16.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F1E9 REGIONAL INDICATOR SYMBOL LETTER D (RI)'>&#x1F1E9;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0062 LATIN SMALL LETTER B (ALetter)'>b</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0061 LATIN SMALL LETTER A (ALetter)'>a</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F1E6 REGIONAL INDICATOR SYMBOL LETTER A (RI)'>&#x1F1E6;</span><span title='16.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F1E7 REGIONAL INDICATOR SYMBOL LETTER B (RI)'>&#x1F1E7;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F1E8 REGIONAL INDICATOR SYMBOL LETTER C (RI)'>&#x1F1E8;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0062 LATIN SMALL LETTER B (ALetter)'>b</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s21' name='s21'>21</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s21' name='s21'>21</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F476 BABY (ExtPict)'>&#x1F476;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F3FF EMOJI MODIFIER FITZPATRICK TYPE-6 (Extend_FE)'>&#x1F3FF;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F476 BABY (ExtPict)'>&#x1F476;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0061 LATIN SMALL LETTER A (ALetter)'>a</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F1E6 REGIONAL INDICATOR SYMBOL LETTER A (RI)'>&#x1F1E6;</span><span title='16.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F1E7 REGIONAL INDICATOR SYMBOL LETTER B (RI)'>&#x1F1E7;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F1E8 REGIONAL INDICATOR SYMBOL LETTER C (RI)'>&#x1F1E8;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0062 LATIN SMALL LETTER B (ALetter)'>b</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s22' name='s22'>22</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s22' name='s22'>22</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F6D1 OCTAGONAL SIGN (ExtPict)'>&#x1F6D1;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='3.3'><span>&nbsp;</span>&nbsp;</span><span title='U+1F6D1 OCTAGONAL SIGN (ExtPict)'>&#x1F6D1;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0061 LATIN SMALL LETTER A (ALetter)'>a</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F1E6 REGIONAL INDICATOR SYMBOL LETTER A (RI)'>&#x1F1E6;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='16.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F1E7 REGIONAL INDICATOR SYMBOL LETTER B (RI)'>&#x1F1E7;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F1E8 REGIONAL INDICATOR SYMBOL LETTER C (RI)'>&#x1F1E8;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0062 LATIN SMALL LETTER B (ALetter)'>b</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s23' name='s23'>23</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s23' name='s23'>23</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0061 LATIN SMALL LETTER A (ALetter)'>a</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='3.3'><span>&nbsp;</span>&nbsp;</span><span title='U+1F6D1 OCTAGONAL SIGN (ExtPict)'>&#x1F6D1;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0061 LATIN SMALL LETTER A (ALetter)'>a</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F1E6 REGIONAL INDICATOR SYMBOL LETTER A (RI)'>&#x1F1E6;</span><span title='16.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F1E7 REGIONAL INDICATOR SYMBOL LETTER B (RI)'>&#x1F1E7;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F1E8 REGIONAL INDICATOR SYMBOL LETTER C (RI)'>&#x1F1E8;</span><span title='16.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F1E9 REGIONAL INDICATOR SYMBOL LETTER D (RI)'>&#x1F1E9;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0062 LATIN SMALL LETTER B (ALetter)'>b</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s24' name='s24'>24</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s24' name='s24'>24</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+2701 UPPER BLADE SCISSORS (Other)'>&#x2701;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='3.3'><span>&nbsp;</span>&nbsp;</span><span title='U+2701 UPPER BLADE SCISSORS (Other)'>&#x2701;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F476 BABY (ExtPict)'>&#x1F476;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F3FF EMOJI MODIFIER FITZPATRICK TYPE-6 (Extend_FE)'>&#x1F3FF;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F476 BABY (ExtPict)'>&#x1F476;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s25' name='s25'>25</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s25' name='s25'>25</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0061 LATIN SMALL LETTER A (ALetter)'>a</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='3.3'><span>&nbsp;</span>&nbsp;</span><span title='U+2701 UPPER BLADE SCISSORS (Other)'>&#x2701;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F6D1 OCTAGONAL SIGN (ExtPict)'>&#x1F6D1;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='3.3'><span>&nbsp;</span>&nbsp;</span><span title='U+1F6D1 OCTAGONAL SIGN (ExtPict)'>&#x1F6D1;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s26' name='s26'>26</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s26' name='s26'>26</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F476 BABY (ExtPict)'>&#x1F476;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F3FF EMOJI MODIFIER FITZPATRICK TYPE-6 (Extend_FE)'>&#x1F3FF;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0308 COMBINING DIAERESIS (Extend_FE)'>&#x25CC;&#x308;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='3.3'><span>&nbsp;</span>&nbsp;</span><span title='U+1F476 BABY (ExtPict)'>&#x1F476;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F3FF EMOJI MODIFIER FITZPATRICK TYPE-6 (Extend_FE)'>&#x1F3FF;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0061 LATIN SMALL LETTER A (ALetter)'>a</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='3.3'><span>&nbsp;</span>&nbsp;</span><span title='U+1F6D1 OCTAGONAL SIGN (ExtPict)'>&#x1F6D1;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s27' name='s27'>27</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s27' name='s27'>27</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F6D1 OCTAGONAL SIGN (ExtPict)'>&#x1F6D1;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F3FF EMOJI MODIFIER FITZPATRICK TYPE-6 (Extend_FE)'>&#x1F3FF;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+2701 UPPER BLADE SCISSORS (Other)'>&#x2701;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='3.3'><span>&nbsp;</span>&nbsp;</span><span title='U+2701 UPPER BLADE SCISSORS (Other)'>&#x2701;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s28' name='s28'>28</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s28' name='s28'>28</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='3.3'><span>&nbsp;</span>&nbsp;</span><span title='U+1F6D1 OCTAGONAL SIGN (ExtPict)'>&#x1F6D1;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F3FF EMOJI MODIFIER FITZPATRICK TYPE-6 (Extend_FE)'>&#x1F3FF;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0061 LATIN SMALL LETTER A (ALetter)'>a</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='3.3'><span>&nbsp;</span>&nbsp;</span><span title='U+2701 UPPER BLADE SCISSORS (Other)'>&#x2701;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s29' name='s29'>29</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s29' name='s29'>29</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='3.3'><span>&nbsp;</span>&nbsp;</span><span title='U+1F6D1 OCTAGONAL SIGN (ExtPict)'>&#x1F6D1;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F476 BABY (ExtPict)'>&#x1F476;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F3FF EMOJI MODIFIER FITZPATRICK TYPE-6 (Extend_FE)'>&#x1F3FF;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0308 COMBINING DIAERESIS (Extend_FE)'>&#x25CC;&#x308;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='3.3'><span>&nbsp;</span>&nbsp;</span><span title='U+1F476 BABY (ExtPict)'>&#x1F476;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F3FF EMOJI MODIFIER FITZPATRICK TYPE-6 (Extend_FE)'>&#x1F3FF;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s30' name='s30'>30</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s30' name='s30'>30</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='3.3'><span>&nbsp;</span>&nbsp;</span><span title='U+1F6D1 OCTAGONAL SIGN (ExtPict)'>&#x1F6D1;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F6D1 OCTAGONAL SIGN (ExtPict)'>&#x1F6D1;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F3FF EMOJI MODIFIER FITZPATRICK TYPE-6 (Extend_FE)'>&#x1F3FF;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s31' name='s31'>31</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s31' name='s31'>31</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F6D1 OCTAGONAL SIGN (ExtPict)'>&#x1F6D1;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F6D1 OCTAGONAL SIGN (ExtPict)'>&#x1F6D1;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='3.3'><span>&nbsp;</span>&nbsp;</span><span title='U+1F6D1 OCTAGONAL SIGN (ExtPict)'>&#x1F6D1;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+1F3FF EMOJI MODIFIER FITZPATRICK TYPE-6 (Extend_FE)'>&#x1F3FF;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s32' name='s32'>32</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s32' name='s32'>32</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0061 LATIN SMALL LETTER A (ALetter)'>a</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0308 COMBINING DIAERESIS (Extend_FE)'>&#x25CC;&#x308;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0308 COMBINING DIAERESIS (Extend_FE)'>&#x25CC;&#x308;</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0062 LATIN SMALL LETTER B (ALetter)'>b</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='3.3'><span>&nbsp;</span>&nbsp;</span><span title='U+1F6D1 OCTAGONAL SIGN (ExtPict)'>&#x1F6D1;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
<tr><th style='text-align:right'><a href='#s33' name='s33'>33</a></th><td><font size='5'> <tr><th style='text-align:right'><a href='#s33' name='s33'>33</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='3.3'><span>&nbsp;</span>&nbsp;</span><span title='U+1F6D1 OCTAGONAL SIGN (ExtPict)'>&#x1F6D1;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr>
<tr><th style='text-align:right'><a href='#s34' name='s34'>34</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F6D1 OCTAGONAL SIGN (ExtPict)'>&#x1F6D1;</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+1F6D1 OCTAGONAL SIGN (ExtPict)'>&#x1F6D1;</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr>
<tr><th style='text-align:right'><a href='#s35' name='s35'>35</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0061 LATIN SMALL LETTER A (ALetter)'>a</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0308 COMBINING DIAERESIS (Extend_FE)'>&#x25CC;&#x308;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+200D ZERO WIDTH JOINER (ZWJ_FE)'>&#x25A1;</span><span title='4.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0308 COMBINING DIAERESIS (Extend_FE)'>&#x25CC;&#x308;</span><span title='5.0'><span>&nbsp;</span>&nbsp;</span><span title='U+0062 LATIN SMALL LETTER B (ALetter)'>b</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr>
<tr><th style='text-align:right'><a href='#s36' name='s36'>36</a></th><td><font size='5'>
<span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0061 LATIN SMALL LETTER A (ALetter)'>a</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0020 SPACE (WSegSpace)'> </span><span title='3.4'><span>&nbsp;</span>&nbsp;</span><span title='U+0020 SPACE (WSegSpace)'> </span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0062 LATIN SMALL LETTER B (ALetter)'>b</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span> <span title='0.2'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0061 LATIN SMALL LETTER A (ALetter)'>a</span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0020 SPACE (WSegSpace)'> </span><span title='3.4'><span>&nbsp;</span>&nbsp;</span><span title='U+0020 SPACE (WSegSpace)'> </span><span title='999.0'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span><span title='U+0062 LATIN SMALL LETTER B (ALetter)'>b</span><span title='0.3'><span style='border-right: 1px solid blue'>&nbsp;</span>&nbsp;</span>
</font></td></tr> </font></td></tr>
</table> </table>

View File

@ -1,6 +1,6 @@
# WordBreakTest-15.0.0.txt # WordBreakTest-15.1.0.txt
# Date: 2022-02-26, 00:39:00 GMT # Date: 2023-03-31, 14:30:32 GMT
# © 2022 Unicode®, Inc. # © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html # For terms of use, see https://www.unicode.org/terms_of_use.html
# #
@ -1708,6 +1708,9 @@
÷ 0061 × 0308 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [0.3] ÷ 0061 × 0308 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [0.3]
÷ 0020 × 200D ÷ 0646 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] ZERO WIDTH JOINER (ZWJ_FE) ÷ [999.0] ARABIC LETTER NOON (ALetter) ÷ [0.3] ÷ 0020 × 200D ÷ 0646 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] ZERO WIDTH JOINER (ZWJ_FE) ÷ [999.0] ARABIC LETTER NOON (ALetter) ÷ [0.3]
÷ 0646 × 200D ÷ 0020 ÷ # ÷ [0.2] ARABIC LETTER NOON (ALetter) × [4.0] ZERO WIDTH JOINER (ZWJ_FE) ÷ [999.0] SPACE (WSegSpace) ÷ [0.3] ÷ 0646 × 200D ÷ 0020 ÷ # ÷ [0.2] ARABIC LETTER NOON (ALetter) × [4.0] ZERO WIDTH JOINER (ZWJ_FE) ÷ [999.0] SPACE (WSegSpace) ÷ [0.3]
÷ 0671 × 0644 × 0631 × 064E × 0651 × 062D × 0650 × 064A × 0645 × 0650 ÷ 0020 ÷ 06DD × 0661 ÷ # ÷ [0.2] ARABIC LETTER ALEF WASLA (ALetter) × [5.0] ARABIC LETTER LAM (ALetter) × [5.0] ARABIC LETTER REH (ALetter) × [4.0] ARABIC FATHA (Extend_FE) × [4.0] ARABIC SHADDA (Extend_FE) × [5.0] ARABIC LETTER HAH (ALetter) × [4.0] ARABIC KASRA (Extend_FE) × [5.0] ARABIC LETTER YEH (ALetter) × [5.0] ARABIC LETTER MEEM (ALetter) × [4.0] ARABIC KASRA (Extend_FE) ÷ [999.0] SPACE (WSegSpace) ÷ [999.0] ARABIC END OF AYAH (Numeric) × [8.0] ARABIC-INDIC DIGIT ONE (Numeric) ÷ [0.3]
÷ 0721 × 0719 × 0721 × 0718 × 072A × 0710 ÷ 0020 ÷ 070F × 071D × 0717 ÷ # ÷ [0.2] SYRIAC LETTER MIM (ALetter) × [5.0] SYRIAC LETTER ZAIN (ALetter) × [5.0] SYRIAC LETTER MIM (ALetter) × [5.0] SYRIAC LETTER WAW (ALetter) × [5.0] SYRIAC LETTER RISH (ALetter) × [5.0] SYRIAC LETTER ALAPH (ALetter) ÷ [999.0] SPACE (WSegSpace) ÷ [999.0] SYRIAC ABBREVIATION MARK (ALetter) × [5.0] SYRIAC LETTER YUDH (ALetter) × [5.0] SYRIAC LETTER HE (ALetter) ÷ [0.3]
÷ 072C × 070F × 072B × 0712 × 0718 ÷ # ÷ [0.2] SYRIAC LETTER TAW (ALetter) × [5.0] SYRIAC ABBREVIATION MARK (ALetter) × [5.0] SYRIAC LETTER SHIN (ALetter) × [5.0] SYRIAC LETTER BETH (ALetter) × [5.0] SYRIAC LETTER WAW (ALetter) ÷ [0.3]
÷ 0041 × 0041 × 0041 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) × [5.0] LATIN CAPITAL LETTER A (ALetter) × [5.0] LATIN CAPITAL LETTER A (ALetter) ÷ [0.3] ÷ 0041 × 0041 × 0041 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) × [5.0] LATIN CAPITAL LETTER A (ALetter) × [5.0] LATIN CAPITAL LETTER A (ALetter) ÷ [0.3]
÷ 0041 × 003A × 0041 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) × [6.0] COLON (MidLetter) × [7.0] LATIN CAPITAL LETTER A (ALetter) ÷ [0.3] ÷ 0041 × 003A × 0041 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) × [6.0] COLON (MidLetter) × [7.0] LATIN CAPITAL LETTER A (ALetter) ÷ [0.3]
÷ 0041 ÷ 003A ÷ 003A ÷ 0041 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LATIN CAPITAL LETTER A (ALetter) ÷ [0.3] ÷ 0041 ÷ 003A ÷ 003A ÷ 0041 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LATIN CAPITAL LETTER A (ALetter) ÷ [0.3]
@ -1846,6 +1849,6 @@
÷ 0061 × 005F × 0031 ÷ 002C ÷ 002C ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3] ÷ 0061 × 005F × 0031 ÷ 002C ÷ 002C ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
÷ 0061 × 005F × 0061 ÷ 002C ÷ 002C ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3] ÷ 0061 × 005F × 0061 ÷ 002C ÷ 002C ÷ 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [0.3]
# #
# Lines: 1823 # Lines: 1826
# #
# EOF # EOF

View File

@ -1,6 +1,6 @@
# ArabicShaping-15.0.0.txt # ArabicShaping-15.1.0.txt
# Date: 2022-02-14, 18:50:00 GMT [KW, RP] # Date: 2023-01-05
# © 2022 Unicode®, Inc. # © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html # For terms of use, see https://www.unicode.org/terms_of_use.html
# #

View File

@ -1,6 +1,6 @@
# BidiMirroring-15.0.0.txt # BidiMirroring-15.1.0.txt
# Date: 2022-05-03, 18:47:00 GMT [KW, RP] # Date: 2023-01-05
# © 2022 Unicode®, Inc. # © 2023 Unicode®, Inc.
# For terms of use, see https://www.unicode.org/terms_of_use.html # For terms of use, see https://www.unicode.org/terms_of_use.html
# #
# Unicode Character Database # Unicode Character Database
@ -15,7 +15,7 @@
# value, for which there is another Unicode character that typically has a glyph # value, for which there is another Unicode character that typically has a glyph
# that is the mirror image of the original character's glyph. # that is the mirror image of the original character's glyph.
# #
# The repertoire covered by the file is Unicode 15.0.0. # The repertoire covered by the file is Unicode 15.1.0.
# #
# The file contains a list of lines with mappings from one code point # The file contains a list of lines with mappings from one code point
# to another one for character-based mirroring. # to another one for character-based mirroring.

View File

@ -1,6 +1,6 @@
# Blocks-15.0.0.txt # Blocks-15.1.0.txt
# Date: 2022-01-28, 20:58:00 GMT [KW] # Date: 2023-07-28, 15:47:20 GMT
# © 2022 Unicode®, Inc. # © 2023 Unicode®, Inc.
# For terms of use, see https://www.unicode.org/terms_of_use.html # For terms of use, see https://www.unicode.org/terms_of_use.html
# #
# Unicode Character Database # Unicode Character Database
@ -352,6 +352,7 @@ FFF0..FFFF; Specials
2B740..2B81F; CJK Unified Ideographs Extension D 2B740..2B81F; CJK Unified Ideographs Extension D
2B820..2CEAF; CJK Unified Ideographs Extension E 2B820..2CEAF; CJK Unified Ideographs Extension E
2CEB0..2EBEF; CJK Unified Ideographs Extension F 2CEB0..2EBEF; CJK Unified Ideographs Extension F
2EBF0..2EE5F; CJK Unified Ideographs Extension I
2F800..2FA1F; CJK Compatibility Ideographs Supplement 2F800..2FA1F; CJK Compatibility Ideographs Supplement
30000..3134F; CJK Unified Ideographs Extension G 30000..3134F; CJK Unified Ideographs Extension G
31350..323AF; CJK Unified Ideographs Extension H 31350..323AF; CJK Unified Ideographs Extension H

View File

@ -1,6 +1,6 @@
# CaseFolding-15.0.0.txt # CaseFolding-15.1.0.txt
# Date: 2022-02-02, 23:35:35 GMT # Date: 2023-05-12, 21:53:10 GMT
# © 2022 Unicode®, Inc. # © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html # For terms of use, see https://www.unicode.org/terms_of_use.html
# #
@ -929,6 +929,7 @@
1FCC; S; 1FC3; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI 1FCC; S; 1FC3; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI
1FD2; F; 03B9 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA 1FD2; F; 03B9 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA
1FD3; F; 03B9 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA 1FD3; F; 03B9 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
1FD3; S; 0390; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
1FD6; F; 03B9 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI 1FD6; F; 03B9 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI
1FD7; F; 03B9 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI 1FD7; F; 03B9 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI
1FD8; C; 1FD0; # GREEK CAPITAL LETTER IOTA WITH VRACHY 1FD8; C; 1FD0; # GREEK CAPITAL LETTER IOTA WITH VRACHY
@ -937,6 +938,7 @@
1FDB; C; 1F77; # GREEK CAPITAL LETTER IOTA WITH OXIA 1FDB; C; 1F77; # GREEK CAPITAL LETTER IOTA WITH OXIA
1FE2; F; 03C5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA 1FE2; F; 03C5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA
1FE3; F; 03C5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA 1FE3; F; 03C5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
1FE3; S; 03B0; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
1FE4; F; 03C1 0313; # GREEK SMALL LETTER RHO WITH PSILI 1FE4; F; 03C1 0313; # GREEK SMALL LETTER RHO WITH PSILI
1FE6; F; 03C5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI 1FE6; F; 03C5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI
1FE7; F; 03C5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI 1FE7; F; 03C5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI
@ -1328,6 +1330,7 @@ FB02; F; 0066 006C; # LATIN SMALL LIGATURE FL
FB03; F; 0066 0066 0069; # LATIN SMALL LIGATURE FFI FB03; F; 0066 0066 0069; # LATIN SMALL LIGATURE FFI
FB04; F; 0066 0066 006C; # LATIN SMALL LIGATURE FFL FB04; F; 0066 0066 006C; # LATIN SMALL LIGATURE FFL
FB05; F; 0073 0074; # LATIN SMALL LIGATURE LONG S T FB05; F; 0073 0074; # LATIN SMALL LIGATURE LONG S T
FB05; S; FB06; # LATIN SMALL LIGATURE LONG S T
FB06; F; 0073 0074; # LATIN SMALL LIGATURE ST FB06; F; 0073 0074; # LATIN SMALL LIGATURE ST
FB13; F; 0574 0576; # ARMENIAN SMALL LIGATURE MEN NOW FB13; F; 0574 0576; # ARMENIAN SMALL LIGATURE MEN NOW
FB14; F; 0574 0565; # ARMENIAN SMALL LIGATURE MEN ECH FB14; F; 0574 0565; # ARMENIAN SMALL LIGATURE MEN ECH

View File

@ -1,6 +1,6 @@
# DerivedAge-15.0.0.txt # DerivedAge-15.1.0.txt
# Date: 2022-04-26, 23:14:23 GMT # Date: 2023-07-28, 23:33:51 GMT
# © 2022 Unicode®, Inc. # © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html # For terms of use, see https://www.unicode.org/terms_of_use.html
# #
@ -1991,4 +1991,16 @@ FDFE..FDFF ; 14.0 # [2] ARABIC LIGATURE SUBHAANAHU WA TAAALAA..ARABIC LIGAT
# Total code points: 4489 # Total code points: 4489
# ================================================
# Age=V15_1
# Newly assigned in Unicode 15.1.0 (September, 2023)
2FFC..2FFF ; 15.1 # [4] IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER ROTATION
31EF ; 15.1 # IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION
2EBF0..2EE5D ; 15.1 # [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
# Total code points: 627
# EOF # EOF

File diff suppressed because it is too large Load Diff

View File

@ -1,6 +1,6 @@
# EastAsianWidth-15.0.0.txt # EastAsianWidth-15.1.0.txt
# Date: 2022-05-24, 17:40:20 GMT [KW, LI] # Date: 2023-07-28, 23:34:08 GMT
# © 2022 Unicode®, Inc. # © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html # For terms of use, see https://www.unicode.org/terms_of_use.html
# #
@ -30,11 +30,10 @@
# Character ranges are specified as for other property files in the # Character ranges are specified as for other property files in the
# Unicode Character Database. # Unicode Character Database.
# #
# For legacy reasons, there are no spaces before or after the semicolon # The comments following the number sign "#" list the General_Category
# which separates the two fields. The comments following the number sign # property value or the L& alias of the derived value LC, the Unicode
# "#" list the General_Category property value or the L& alias of the # character name or names, and, in lines with ranges of code points,
# derived value LC, the Unicode character name or names, and, in lines # the code point count in square brackets.
# with ranges of code points, the code point count in square brackets.
# #
# For more information, see UAX #11: East Asian Width, # For more information, see UAX #11: East Asian Width,
# at https://www.unicode.org/reports/tr11/ # at https://www.unicode.org/reports/tr11/
@ -1430,7 +1429,7 @@
2E80..2E99 ; W # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E80..2E99 ; W # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP
2E9B..2EF3 ; W # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE 2E9B..2EF3 ; W # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE
2F00..2FD5 ; W # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE 2F00..2FD5 ; W # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE
2FF0..2FFB;W # So [12] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID 2FF0..2FFF ; W # So [16] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER ROTATION
3000 ; F # Zs IDEOGRAPHIC SPACE 3000 ; F # Zs IDEOGRAPHIC SPACE
3001..3003 ; W # Po [3] IDEOGRAPHIC COMMA..DITTO MARK 3001..3003 ; W # Po [3] IDEOGRAPHIC COMMA..DITTO MARK
3004 ; W # So JAPANESE INDUSTRIAL STANDARD SYMBOL 3004 ; W # So JAPANESE INDUSTRIAL STANDARD SYMBOL
@ -1489,6 +1488,7 @@
3196..319F ; W # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK 3196..319F ; W # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK
31A0..31BF ; W # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH 31A0..31BF ; W # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH
31C0..31E3 ; W # So [36] CJK STROKE T..CJK STROKE Q 31C0..31E3 ; W # So [36] CJK STROKE T..CJK STROKE Q
31EF ; W # So IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION
31F0..31FF ; W # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 31F0..31FF ; W # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO
3200..321E ; W # So [31] PARENTHESIZED HANGUL KIYEOK..PARENTHESIZED KOREAN CHARACTER O HU 3200..321E ; W # So [31] PARENTHESIZED HANGUL KIYEOK..PARENTHESIZED KOREAN CHARACTER O HU
3220..3229 ; W # No [10] PARENTHESIZED IDEOGRAPH ONE..PARENTHESIZED IDEOGRAPH TEN 3220..3229 ; W # No [10] PARENTHESIZED IDEOGRAPH ONE..PARENTHESIZED IDEOGRAPH TEN
@ -2602,7 +2602,9 @@ FFFD;A # So REPLACEMENT CHARACTER
2B820..2CEA1 ; W # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2B820..2CEA1 ; W # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
2CEA2..2CEAF ; W # Cn [14] <reserved-2CEA2>..<reserved-2CEAF> 2CEA2..2CEAF ; W # Cn [14] <reserved-2CEA2>..<reserved-2CEAF>
2CEB0..2EBE0 ; W # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2CEB0..2EBE0 ; W # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2EBE1..2F7FF;W # Cn [3103] <reserved-2EBE1>..<reserved-2F7FF> 2EBE1..2EBEF ; W # Cn [15] <reserved-2EBE1>..<reserved-2EBEF>
2EBF0..2EE5D ; W # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
2EE5E..2F7FF ; W # Cn [2466] <reserved-2EE5E>..<reserved-2F7FF>
2F800..2FA1D ; W # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 2F800..2FA1D ; W # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
2FA1E..2FA1F ; W # Cn [2] <reserved-2FA1E>..<reserved-2FA1F> 2FA1E..2FA1F ; W # Cn [2] <reserved-2FA1E>..<reserved-2FA1F>
2FA20..2FFFD ; W # Cn [1502] <reserved-2FA20>..<reserved-2FFFD> 2FA20..2FFFD ; W # Cn [1502] <reserved-2FA20>..<reserved-2FFFD>

View File

@ -1,6 +1,6 @@
# GraphemeBreakProperty-15.0.0.txt # GraphemeBreakProperty-15.1.0.txt
# Date: 2022-04-27, 17:07:38 GMT # Date: 2023-01-05, 20:34:41 GMT
# © 2022 Unicode®, Inc. # © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html # For terms of use, see https://www.unicode.org/terms_of_use.html
# #

View File

@ -1,11 +1,11 @@
# IdnaMappingTable.txt # IdnaMappingTable.txt
# Date: 2022-05-02, 19:29:26 GMT # Date: 2023-08-10, 22:32:27 GMT
# © 2022 Unicode®, Inc. # © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html # For terms of use, see https://www.unicode.org/terms_of_use.html
# #
# Unicode IDNA Compatible Preprocessing for UTS #46 # Unicode IDNA Compatible Preprocessing for UTS #46
# Version: 15.0.0 # Version: 15.1.0
# #
# For documentation and usage, see https://www.unicode.org/reports/tr46 # For documentation and usage, see https://www.unicode.org/reports/tr46
# #
@ -2036,7 +2036,7 @@
1E9A ; mapped ; 0061 02BE # 1.1 LATIN SMALL LETTER A WITH RIGHT HALF RING 1E9A ; mapped ; 0061 02BE # 1.1 LATIN SMALL LETTER A WITH RIGHT HALF RING
1E9B ; mapped ; 1E61 # 2.0 LATIN SMALL LETTER LONG S WITH DOT ABOVE 1E9B ; mapped ; 1E61 # 2.0 LATIN SMALL LETTER LONG S WITH DOT ABOVE
1E9C..1E9D ; valid # 5.1 LATIN SMALL LETTER LONG S WITH DIAGONAL STROKE..LATIN SMALL LETTER LONG S WITH HIGH STROKE 1E9C..1E9D ; valid # 5.1 LATIN SMALL LETTER LONG S WITH DIAGONAL STROKE..LATIN SMALL LETTER LONG S WITH HIGH STROKE
1E9E ; mapped ; 0073 0073 # 5.1 LATIN CAPITAL LETTER SHARP S 1E9E ; mapped ; 00DF # 5.1 LATIN CAPITAL LETTER SHARP S
1E9F ; valid # 5.1 LATIN SMALL LETTER DELTA 1E9F ; valid # 5.1 LATIN SMALL LETTER DELTA
1EA0 ; mapped ; 1EA1 # 1.1 LATIN CAPITAL LETTER A WITH DOT BELOW 1EA0 ; mapped ; 1EA1 # 1.1 LATIN CAPITAL LETTER A WITH DOT BELOW
1EA1 ; valid # 1.1 LATIN SMALL LETTER A WITH DOT BELOW 1EA1 ; valid # 1.1 LATIN SMALL LETTER A WITH DOT BELOW
@ -2565,11 +2565,7 @@
222E ; valid ; ; NV8 # 1.1 CONTOUR INTEGRAL 222E ; valid ; ; NV8 # 1.1 CONTOUR INTEGRAL
222F ; mapped ; 222E 222E # 1.1 SURFACE INTEGRAL 222F ; mapped ; 222E 222E # 1.1 SURFACE INTEGRAL
2230 ; mapped ; 222E 222E 222E #1.1 VOLUME INTEGRAL 2230 ; mapped ; 222E 222E 222E #1.1 VOLUME INTEGRAL
2231..225F ; valid ; ; NV8 # 1.1 CLOCKWISE INTEGRAL..QUESTIONED EQUAL TO 2231..22F1 ; valid ; ; NV8 # 1.1 CLOCKWISE INTEGRAL..DOWN RIGHT DIAGONAL ELLIPSIS
2260 ; disallowed_STD3_valid # 1.1 NOT EQUAL TO
2261..226D ; valid ; ; NV8 # 1.1 IDENTICAL TO..NOT EQUIVALENT TO
226E..226F ; disallowed_STD3_valid # 1.1 NOT LESS-THAN..NOT GREATER-THAN
2270..22F1 ; valid ; ; NV8 # 1.1 NEITHER LESS-THAN NOR EQUAL TO..DOWN RIGHT DIAGONAL ELLIPSIS
22F2..22FF ; valid ; ; NV8 # 3.2 ELEMENT OF WITH LONG HORIZONTAL STROKE..Z NOTATION BAG MEMBERSHIP 22F2..22FF ; valid ; ; NV8 # 3.2 ELEMENT OF WITH LONG HORIZONTAL STROKE..Z NOTATION BAG MEMBERSHIP
2300 ; valid ; ; NV8 # 1.1 DIAMETER SIGN 2300 ; valid ; ; NV8 # 1.1 DIAMETER SIGN
2301 ; valid ; ; NV8 # 3.0 ELECTRIC ARROW 2301 ; valid ; ; NV8 # 3.0 ELECTRIC ARROW
@ -3273,7 +3269,7 @@
2FD5 ; mapped ; 9FA0 # 3.0 KANGXI RADICAL FLUTE 2FD5 ; mapped ; 9FA0 # 3.0 KANGXI RADICAL FLUTE
2FD6..2FEF ; disallowed # NA <reserved-2FD6>..<reserved-2FEF> 2FD6..2FEF ; disallowed # NA <reserved-2FD6>..<reserved-2FEF>
2FF0..2FFB ; disallowed # 3.0 IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID 2FF0..2FFB ; disallowed # 3.0 IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
2FFC..2FFF ; disallowed # NA <reserved-2FFC>..<reserved-2FFF> 2FFC..2FFF ; disallowed # 15.1 IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER ROTATION
3000 ; disallowed_STD3_mapped ; 0020 # 1.1 IDEOGRAPHIC SPACE 3000 ; disallowed_STD3_mapped ; 0020 # 1.1 IDEOGRAPHIC SPACE
3001 ; valid ; ; NV8 # 1.1 IDEOGRAPHIC COMMA 3001 ; valid ; ; NV8 # 1.1 IDEOGRAPHIC COMMA
3002 ; mapped ; 002E # 1.1 IDEOGRAPHIC FULL STOP 3002 ; mapped ; 002E # 1.1 IDEOGRAPHIC FULL STOP
@ -3425,7 +3421,8 @@
31BB..31BF ; valid # 13.0 BOPOMOFO FINAL LETTER G..BOPOMOFO LETTER AH 31BB..31BF ; valid # 13.0 BOPOMOFO FINAL LETTER G..BOPOMOFO LETTER AH
31C0..31CF ; valid ; ; NV8 # 4.1 CJK STROKE T..CJK STROKE N 31C0..31CF ; valid ; ; NV8 # 4.1 CJK STROKE T..CJK STROKE N
31D0..31E3 ; valid ; ; NV8 # 5.1 CJK STROKE H..CJK STROKE Q 31D0..31E3 ; valid ; ; NV8 # 5.1 CJK STROKE H..CJK STROKE Q
31E4..31EF ; disallowed # NA <reserved-31E4>..<reserved-31EF> 31E4..31EE ; disallowed # NA <reserved-31E4>..<reserved-31EE>
31EF ; disallowed # 15.1 IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION
31F0..31FF ; valid # 3.2 KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 31F0..31FF ; valid # 3.2 KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO
3200 ; disallowed_STD3_mapped ; 0028 1100 0029 #1.1 PARENTHESIZED HANGUL KIYEOK 3200 ; disallowed_STD3_mapped ; 0028 1100 0029 #1.1 PARENTHESIZED HANGUL KIYEOK
3201 ; disallowed_STD3_mapped ; 0028 1102 0029 #1.1 PARENTHESIZED HANGUL NIEUN 3201 ; disallowed_STD3_mapped ; 0028 1102 0029 #1.1 PARENTHESIZED HANGUL NIEUN
@ -8450,7 +8447,9 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
2B820..2CEA1 ; valid # 8.0 CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2B820..2CEA1 ; valid # 8.0 CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
2CEA2..2CEAF ; disallowed # NA <reserved-2CEA2>..<reserved-2CEAF> 2CEA2..2CEAF ; disallowed # NA <reserved-2CEA2>..<reserved-2CEAF>
2CEB0..2EBE0 ; valid # 10.0 CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2CEB0..2EBE0 ; valid # 10.0 CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2EBE1..2F7FF ; disallowed # NA <reserved-2EBE1>..<reserved-2F7FF> 2EBE1..2EBEF ; disallowed # NA <reserved-2EBE1>..<reserved-2EBEF>
2EBF0..2EE5D ; valid # 15.1 CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
2EE5E..2F7FF ; disallowed # NA <reserved-2EE5E>..<reserved-2F7FF>
2F800 ; mapped ; 4E3D # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F800 2F800 ; mapped ; 4E3D # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F800
2F801 ; mapped ; 4E38 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F801 2F801 ; mapped ; 4E38 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F801
2F802 ; mapped ; 4E41 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F802 2F802 ; mapped ; 4E41 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F802

View File

@ -1,6 +1,6 @@
# LineBreak-15.0.0.txt # LineBreak-15.1.0.txt
# Date: 2022-07-28, 09:20:42 GMT [KW, LI] # Date: 2023-07-28, 13:19:22 GMT [KW]
# © 2022 Unicode®, Inc. # © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html # For terms of use, see https://www.unicode.org/terms_of_use.html
# #
@ -18,10 +18,10 @@
# Non-tailorable: # Non-tailorable:
# "BK", "CM", "CR", "GL", "LF", "NL", "SP", "WJ", "ZW", "ZWJ" # "BK", "CM", "CR", "GL", "LF", "NL", "SP", "WJ", "ZW", "ZWJ"
# Tailorable: # Tailorable:
# "AI", "AL", "B2", "BA", "BB", "CB", "CJ", "CL", "CP", "EB", # "AI", "AK", "AL", "AP", "AS", "B2", "BA", "BB", "CB", "CJ",
# "EM", "EX", "H2", "H3", "HL", "HY", "ID", "IN", "IS", "JL", # "CL", "CP", "EB", "EM", "EX", "H2", "H3", "HL", "HY", "ID",
# "JT", "JV", "NS", "NU", "OP", "PO", "PR", "QU", "RI", "SA", # "IN", "IS", "JL", "JT", "JV", "NS", "NU", "OP", "PO", "PR",
# "SG", "SY", "XX" # "QU", "RI", "SA", "SG", "SY", "VF", "VI", "XX"
# - All code points, assigned and unassigned, that are not listed # - All code points, assigned and unassigned, that are not listed
# explicitly are given the value "XX". # explicitly are given the value "XX".
# - The unassigned code points in the following blocks default to "ID": # - The unassigned code points in the following blocks default to "ID":
@ -42,11 +42,10 @@
# Character ranges are specified as for other property files in the # Character ranges are specified as for other property files in the
# Unicode Character Database. # Unicode Character Database.
# #
# For legacy reasons, there are no spaces before or after the semicolon # The comments following the number sign "#" list the General_Category
# which separates the two fields. The comments following the number sign # property value or the L& alias of the derived value LC, the Unicode
# "#" list the General_Category property value or the L& alias of the # character name or names, and, in lines with ranges of code points,
# derived value LC, the Unicode character name or names, and, in lines # the code point count in square brackets.
# with ranges of code points, the code point count in square brackets.
# #
# For more information, see UAX #14: Unicode Line Breaking Algorithm, # For more information, see UAX #14: Unicode Line Breaking Algorithm,
# at https://www.unicode.org/reports/tr14/ # at https://www.unicode.org/reports/tr14/
@ -206,7 +205,7 @@
05D0..05EA ; HL # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV 05D0..05EA ; HL # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV
05EF..05F2 ; HL # Lo [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD 05EF..05F2 ; HL # Lo [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD
05F3..05F4 ; AL # Po [2] HEBREW PUNCTUATION GERESH..HEBREW PUNCTUATION GERSHAYIM 05F3..05F4 ; AL # Po [2] HEBREW PUNCTUATION GERESH..HEBREW PUNCTUATION GERSHAYIM
0600..0605;AL # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE 0600..0605 ; NU # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE
0606..0608 ; AL # Sm [3] ARABIC-INDIC CUBE ROOT..ARABIC RAY 0606..0608 ; AL # Sm [3] ARABIC-INDIC CUBE ROOT..ARABIC RAY
0609..060A ; PO # Po [2] ARABIC-INDIC PER MILLE SIGN..ARABIC-INDIC PER TEN THOUSAND SIGN 0609..060A ; PO # Po [2] ARABIC-INDIC PER MILLE SIGN..ARABIC-INDIC PER TEN THOUSAND SIGN
060B ; PO # Sc AFGHANI SIGN 060B ; PO # Sc AFGHANI SIGN
@ -230,7 +229,7 @@
06D4 ; EX # Po ARABIC FULL STOP 06D4 ; EX # Po ARABIC FULL STOP
06D5 ; AL # Lo ARABIC LETTER AE 06D5 ; AL # Lo ARABIC LETTER AE
06D6..06DC ; CM # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN 06D6..06DC ; CM # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN
06DD;AL # Cf ARABIC END OF AYAH 06DD ; NU # Cf ARABIC END OF AYAH
06DE ; AL # So ARABIC START OF RUB EL HIZB 06DE ; AL # So ARABIC START OF RUB EL HIZB
06DF..06E4 ; CM # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA 06DF..06E4 ; CM # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA
06E5..06E6 ; AL # Lm [2] ARABIC SMALL WAW..ARABIC SMALL YEH 06E5..06E6 ; AL # Lm [2] ARABIC SMALL WAW..ARABIC SMALL YEH
@ -280,12 +279,12 @@
0870..0887 ; AL # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT 0870..0887 ; AL # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT
0888 ; AL # Sk ARABIC RAISED ROUND DOT 0888 ; AL # Sk ARABIC RAISED ROUND DOT
0889..088E ; AL # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL 0889..088E ; AL # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL
0890..0891;AL # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE 0890..0891 ; NU # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE
0898..089F ; CM # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA 0898..089F ; CM # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA
08A0..08C8 ; AL # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08A0..08C8 ; AL # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF
08C9 ; AL # Lm ARABIC SMALL FARSI YEH 08C9 ; AL # Lm ARABIC SMALL FARSI YEH
08CA..08E1 ; CM # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08CA..08E1 ; CM # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA
08E2;AL # Cf ARABIC DISPUTED END OF AYAH 08E2 ; NU # Cf ARABIC DISPUTED END OF AYAH
08E3..08FF ; CM # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA 08E3..08FF ; CM # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA
0900..0902 ; CM # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA 0900..0902 ; CM # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA
0903 ; CM # Mc DEVANAGARI SIGN VISARGA 0903 ; CM # Mc DEVANAGARI SIGN VISARGA
@ -780,7 +779,7 @@
1ABF..1ACE ; CM # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1ABF..1ACE ; CM # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T
1B00..1B03 ; CM # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B00..1B03 ; CM # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG
1B04 ; CM # Mc BALINESE SIGN BISAH 1B04 ; CM # Mc BALINESE SIGN BISAH
1B05..1B33;AL # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA 1B05..1B33 ; AK # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA
1B34 ; CM # Mn BALINESE SIGN REREKAN 1B34 ; CM # Mn BALINESE SIGN REREKAN
1B35 ; CM # Mc BALINESE VOWEL SIGN TEDUNG 1B35 ; CM # Mc BALINESE VOWEL SIGN TEDUNG
1B36..1B3A ; CM # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA 1B36..1B3A ; CM # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA
@ -788,15 +787,16 @@
1B3C ; CM # Mn BALINESE VOWEL SIGN LA LENGA 1B3C ; CM # Mn BALINESE VOWEL SIGN LA LENGA
1B3D..1B41 ; CM # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG 1B3D..1B41 ; CM # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG
1B42 ; CM # Mn BALINESE VOWEL SIGN PEPET 1B42 ; CM # Mn BALINESE VOWEL SIGN PEPET
1B43..1B44;CM # Mc [2] BALINESE VOWEL SIGN PEPET TEDUNG..BALINESE ADEG ADEG 1B43 ; CM # Mc BALINESE VOWEL SIGN PEPET TEDUNG
1B45..1B4C;AL # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B44 ; VI # Mc BALINESE ADEG ADEG
1B50..1B59;NU # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1B45..1B4C ; AK # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA
1B50..1B59 ; ID # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE
1B5A..1B5B ; BA # Po [2] BALINESE PANTI..BALINESE PAMADA 1B5A..1B5B ; BA # Po [2] BALINESE PANTI..BALINESE PAMADA
1B5C;AL # Po BALINESE WINDU 1B5C ; ID # Po BALINESE WINDU
1B5D..1B60 ; BA # Po [4] BALINESE CARIK PAMUNGKAH..BALINESE PAMENENG 1B5D..1B60 ; BA # Po [4] BALINESE CARIK PAMUNGKAH..BALINESE PAMENENG
1B61..1B6A;AL # So [10] BALINESE MUSICAL SYMBOL DONG..BALINESE MUSICAL SYMBOL DANG GEDE 1B61..1B6A ; ID # So [10] BALINESE MUSICAL SYMBOL DONG..BALINESE MUSICAL SYMBOL DANG GEDE
1B6B..1B73 ; CM # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG 1B6B..1B73 ; CM # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG
1B74..1B7C;AL # So [9] BALINESE MUSICAL SYMBOL RIGHT-HAND OPEN DUG..BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING 1B74..1B7C ; ID # So [9] BALINESE MUSICAL SYMBOL RIGHT-HAND OPEN DUG..BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING
1B7D..1B7E ; BA # Po [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG 1B7D..1B7E ; BA # Po [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG
1B80..1B81 ; CM # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR 1B80..1B81 ; CM # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR
1B82 ; CM # Mc SUNDANESE SIGN PANGWISAD 1B82 ; CM # Mc SUNDANESE SIGN PANGWISAD
@ -810,7 +810,7 @@
1BAE..1BAF ; AL # Lo [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA 1BAE..1BAF ; AL # Lo [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA
1BB0..1BB9 ; NU # Nd [10] SUNDANESE DIGIT ZERO..SUNDANESE DIGIT NINE 1BB0..1BB9 ; NU # Nd [10] SUNDANESE DIGIT ZERO..SUNDANESE DIGIT NINE
1BBA..1BBF ; AL # Lo [6] SUNDANESE AVAGRAHA..SUNDANESE LETTER FINAL M 1BBA..1BBF ; AL # Lo [6] SUNDANESE AVAGRAHA..SUNDANESE LETTER FINAL M
1BC0..1BE5;AL # Lo [38] BATAK LETTER A..BATAK LETTER U 1BC0..1BE5 ; AS # Lo [38] BATAK LETTER A..BATAK LETTER U
1BE6 ; CM # Mn BATAK SIGN TOMPI 1BE6 ; CM # Mn BATAK SIGN TOMPI
1BE7 ; CM # Mc BATAK VOWEL SIGN E 1BE7 ; CM # Mc BATAK VOWEL SIGN E
1BE8..1BE9 ; CM # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE 1BE8..1BE9 ; CM # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE
@ -818,7 +818,7 @@
1BED ; CM # Mn BATAK VOWEL SIGN KARO O 1BED ; CM # Mn BATAK VOWEL SIGN KARO O
1BEE ; CM # Mc BATAK VOWEL SIGN U 1BEE ; CM # Mc BATAK VOWEL SIGN U
1BEF..1BF1 ; CM # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H 1BEF..1BF1 ; CM # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H
1BF2..1BF3;CM # Mc [2] BATAK PANGOLAT..BATAK PANONGONAN 1BF2..1BF3 ; VF # Mc [2] BATAK PANGOLAT..BATAK PANONGONAN
1BFC..1BFF ; AL # Po [4] BATAK SYMBOL BINDU NA METEK..BATAK SYMBOL BINDU PANGOLAT 1BFC..1BFF ; AL # Po [4] BATAK SYMBOL BINDU NA METEK..BATAK SYMBOL BINDU PANGOLAT
1C00..1C23 ; AL # Lo [36] LEPCHA LETTER KA..LEPCHA LETTER A 1C00..1C23 ; AL # Lo [36] LEPCHA LETTER KA..LEPCHA LETTER A
1C24..1C2B ; CM # Mc [8] LEPCHA SUBJOINED LETTER YA..LEPCHA VOWEL SIGN UU 1C24..1C2B ; CM # Mc [8] LEPCHA SUBJOINED LETTER YA..LEPCHA VOWEL SIGN UU
@ -1418,7 +1418,7 @@
2E80..2E99 ; ID # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E80..2E99 ; ID # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP
2E9B..2EF3 ; ID # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE 2E9B..2EF3 ; ID # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE
2F00..2FD5 ; ID # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE 2F00..2FD5 ; ID # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE
2FF0..2FFB;ID # So [12] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID 2FF0..2FFF ; ID # So [16] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER ROTATION
3000 ; BA # Zs IDEOGRAPHIC SPACE 3000 ; BA # Zs IDEOGRAPHIC SPACE
3001..3002 ; CL # Po [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP 3001..3002 ; CL # Po [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP
3003 ; ID # Po DITTO MARK 3003 ; ID # Po DITTO MARK
@ -1520,6 +1520,7 @@
3196..319F ; ID # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK 3196..319F ; ID # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK
31A0..31BF ; ID # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH 31A0..31BF ; ID # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH
31C0..31E3 ; ID # So [36] CJK STROKE T..CJK STROKE Q 31C0..31E3 ; ID # So [36] CJK STROKE T..CJK STROKE Q
31EF ; ID # So IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION
31F0..31FF ; CJ # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 31F0..31FF ; CJ # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO
3200..321E ; ID # So [31] PARENTHESIZED HANGUL KIYEOK..PARENTHESIZED KOREAN CHARACTER O HU 3200..321E ; ID # So [31] PARENTHESIZED HANGUL KIYEOK..PARENTHESIZED KOREAN CHARACTER O HU
3220..3229 ; ID # No [10] PARENTHESIZED IDEOGRAPH ONE..PARENTHESIZED IDEOGRAPH TEN 3220..3229 ; ID # No [10] PARENTHESIZED IDEOGRAPH ONE..PARENTHESIZED IDEOGRAPH TEN
@ -1630,38 +1631,39 @@ A95F;AL # Po REJANG SECTION MARK
A960..A97C ; JL # Lo [29] HANGUL CHOSEONG TIKEUT-MIEUM..HANGUL CHOSEONG SSANGYEORINHIEUH A960..A97C ; JL # Lo [29] HANGUL CHOSEONG TIKEUT-MIEUM..HANGUL CHOSEONG SSANGYEORINHIEUH
A980..A982 ; CM # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR A980..A982 ; CM # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR
A983 ; CM # Mc JAVANESE SIGN WIGNYAN A983 ; CM # Mc JAVANESE SIGN WIGNYAN
A984..A9B2;AL # Lo [47] JAVANESE LETTER A..JAVANESE LETTER HA A984..A9B2 ; AK # Lo [47] JAVANESE LETTER A..JAVANESE LETTER HA
A9B3 ; CM # Mn JAVANESE SIGN CECAK TELU A9B3 ; CM # Mn JAVANESE SIGN CECAK TELU
A9B4..A9B5 ; CM # Mc [2] JAVANESE VOWEL SIGN TARUNG..JAVANESE VOWEL SIGN TOLONG A9B4..A9B5 ; CM # Mc [2] JAVANESE VOWEL SIGN TARUNG..JAVANESE VOWEL SIGN TOLONG
A9B6..A9B9 ; CM # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT A9B6..A9B9 ; CM # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT
A9BA..A9BB ; CM # Mc [2] JAVANESE VOWEL SIGN TALING..JAVANESE VOWEL SIGN DIRGA MURE A9BA..A9BB ; CM # Mc [2] JAVANESE VOWEL SIGN TALING..JAVANESE VOWEL SIGN DIRGA MURE
A9BC..A9BD ; CM # Mn [2] JAVANESE VOWEL SIGN PEPET..JAVANESE CONSONANT SIGN KERET A9BC..A9BD ; CM # Mn [2] JAVANESE VOWEL SIGN PEPET..JAVANESE CONSONANT SIGN KERET
A9BE..A9C0;CM # Mc [3] JAVANESE CONSONANT SIGN PENGKAL..JAVANESE PANGKON A9BE..A9BF ; CM # Mc [2] JAVANESE CONSONANT SIGN PENGKAL..JAVANESE CONSONANT SIGN CAKRA
A9C1..A9C6;AL # Po [6] JAVANESE LEFT RERENGGAN..JAVANESE PADA WINDU A9C0 ; VI # Mc JAVANESE PANGKON
A9C1..A9C6 ; ID # Po [6] JAVANESE LEFT RERENGGAN..JAVANESE PADA WINDU
A9C7..A9C9 ; BA # Po [3] JAVANESE PADA PANGKAT..JAVANESE PADA LUNGSI A9C7..A9C9 ; BA # Po [3] JAVANESE PADA PANGKAT..JAVANESE PADA LUNGSI
A9CA..A9CD;AL # Po [4] JAVANESE PADA ADEG..JAVANESE TURNED PADA PISELEH A9CA..A9CD ; ID # Po [4] JAVANESE PADA ADEG..JAVANESE TURNED PADA PISELEH
A9CF;AL # Lm JAVANESE PANGRANGKEP A9CF ; BA # Lm JAVANESE PANGRANGKEP
A9D0..A9D9;NU # Nd [10] JAVANESE DIGIT ZERO..JAVANESE DIGIT NINE A9D0..A9D9 ; ID # Nd [10] JAVANESE DIGIT ZERO..JAVANESE DIGIT NINE
A9DE..A9DF;AL # Po [2] JAVANESE PADA TIRTA TUMETES..JAVANESE PADA ISEN-ISEN A9DE..A9DF ; ID # Po [2] JAVANESE PADA TIRTA TUMETES..JAVANESE PADA ISEN-ISEN
A9E0..A9E4 ; SA # Lo [5] MYANMAR LETTER SHAN GHA..MYANMAR LETTER SHAN BHA A9E0..A9E4 ; SA # Lo [5] MYANMAR LETTER SHAN GHA..MYANMAR LETTER SHAN BHA
A9E5 ; SA # Mn MYANMAR SIGN SHAN SAW A9E5 ; SA # Mn MYANMAR SIGN SHAN SAW
A9E6 ; SA # Lm MYANMAR MODIFIER LETTER SHAN REDUPLICATION A9E6 ; SA # Lm MYANMAR MODIFIER LETTER SHAN REDUPLICATION
A9E7..A9EF ; SA # Lo [9] MYANMAR LETTER TAI LAING NYA..MYANMAR LETTER TAI LAING NNA A9E7..A9EF ; SA # Lo [9] MYANMAR LETTER TAI LAING NYA..MYANMAR LETTER TAI LAING NNA
A9F0..A9F9 ; NU # Nd [10] MYANMAR TAI LAING DIGIT ZERO..MYANMAR TAI LAING DIGIT NINE A9F0..A9F9 ; NU # Nd [10] MYANMAR TAI LAING DIGIT ZERO..MYANMAR TAI LAING DIGIT NINE
A9FA..A9FE ; SA # Lo [5] MYANMAR LETTER TAI LAING LLA..MYANMAR LETTER TAI LAING BHA A9FA..A9FE ; SA # Lo [5] MYANMAR LETTER TAI LAING LLA..MYANMAR LETTER TAI LAING BHA
AA00..AA28;AL # Lo [41] CHAM LETTER A..CHAM LETTER HA AA00..AA28 ; AS # Lo [41] CHAM LETTER A..CHAM LETTER HA
AA29..AA2E ; CM # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE AA29..AA2E ; CM # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE
AA2F..AA30 ; CM # Mc [2] CHAM VOWEL SIGN O..CHAM VOWEL SIGN AI AA2F..AA30 ; CM # Mc [2] CHAM VOWEL SIGN O..CHAM VOWEL SIGN AI
AA31..AA32 ; CM # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE AA31..AA32 ; CM # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE
AA33..AA34 ; CM # Mc [2] CHAM CONSONANT SIGN YA..CHAM CONSONANT SIGN RA AA33..AA34 ; CM # Mc [2] CHAM CONSONANT SIGN YA..CHAM CONSONANT SIGN RA
AA35..AA36 ; CM # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA AA35..AA36 ; CM # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA
AA40..AA42;AL # Lo [3] CHAM LETTER FINAL K..CHAM LETTER FINAL NG AA40..AA42 ; BA # Lo [3] CHAM LETTER FINAL K..CHAM LETTER FINAL NG
AA43 ; CM # Mn CHAM CONSONANT SIGN FINAL NG AA43 ; CM # Mn CHAM CONSONANT SIGN FINAL NG
AA44..AA4B;AL # Lo [8] CHAM LETTER FINAL CH..CHAM LETTER FINAL SS AA44..AA4B ; BA # Lo [8] CHAM LETTER FINAL CH..CHAM LETTER FINAL SS
AA4C ; CM # Mn CHAM CONSONANT SIGN FINAL M AA4C ; CM # Mn CHAM CONSONANT SIGN FINAL M
AA4D ; CM # Mc CHAM CONSONANT SIGN FINAL H AA4D ; CM # Mc CHAM CONSONANT SIGN FINAL H
AA50..AA59;NU # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE AA50..AA59 ; ID # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE
AA5C;AL # Po CHAM PUNCTUATION SPIRAL AA5C ; ID # Po CHAM PUNCTUATION SPIRAL
AA5D..AA5F ; BA # Po [3] CHAM PUNCTUATION DANDA..CHAM PUNCTUATION TRIPLE DANDA AA5D..AA5F ; BA # Po [3] CHAM PUNCTUATION DANDA..CHAM PUNCTUATION TRIPLE DANDA
AA60..AA6F ; SA # Lo [16] MYANMAR LETTER KHAMTI GA..MYANMAR LETTER KHAMTI FA AA60..AA6F ; SA # Lo [16] MYANMAR LETTER KHAMTI GA..MYANMAR LETTER KHAMTI FA
AA70 ; SA # Lm MYANMAR MODIFIER LETTER KHAMTI REDUPLICATION AA70 ; SA # Lm MYANMAR MODIFIER LETTER KHAMTI REDUPLICATION
@ -2815,17 +2817,19 @@ FFFD;AI # So REPLACEMENT CHARACTER
11000 ; CM # Mc BRAHMI SIGN CANDRABINDU 11000 ; CM # Mc BRAHMI SIGN CANDRABINDU
11001 ; CM # Mn BRAHMI SIGN ANUSVARA 11001 ; CM # Mn BRAHMI SIGN ANUSVARA
11002 ; CM # Mc BRAHMI SIGN VISARGA 11002 ; CM # Mc BRAHMI SIGN VISARGA
11003..11037;AL # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA 11003..11004 ; AP # Lo [2] BRAHMI SIGN JIHVAMULIYA..BRAHMI SIGN UPADHMANIYA
11038..11046;CM # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA 11005..11037 ; AK # Lo [51] BRAHMI LETTER A..BRAHMI LETTER OLD TAMIL NNNA
11038..11045 ; CM # Mn [14] BRAHMI VOWEL SIGN AA..BRAHMI VOWEL SIGN AU
11046 ; VI # Mn BRAHMI VIRAMA
11047..11048 ; BA # Po [2] BRAHMI DANDA..BRAHMI DOUBLE DANDA 11047..11048 ; BA # Po [2] BRAHMI DANDA..BRAHMI DOUBLE DANDA
11049..1104D;AL # Po [5] BRAHMI PUNCTUATION DOT..BRAHMI PUNCTUATION LOTUS 11049..1104D ; ID # Po [5] BRAHMI PUNCTUATION DOT..BRAHMI PUNCTUATION LOTUS
11052..11065;AL # No [20] BRAHMI NUMBER ONE..BRAHMI NUMBER ONE THOUSAND 11052..11065 ; ID # No [20] BRAHMI NUMBER ONE..BRAHMI NUMBER ONE THOUSAND
11066..1106F;NU # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE 11066..1106F ; AS # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE
11070 ; CM # Mn BRAHMI SIGN OLD TAMIL VIRAMA 11070 ; CM # Mn BRAHMI SIGN OLD TAMIL VIRAMA
11071..11072;AL # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O 11071..11072 ; AK # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O
11073..11074 ; CM # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O 11073..11074 ; CM # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O
11075;AL # Lo BRAHMI LETTER OLD TAMIL LLA 11075 ; AK # Lo BRAHMI LETTER OLD TAMIL LLA
1107F;CM # Mn BRAHMI NUMBER JOINER 1107F ; GL # Mn BRAHMI NUMBER JOINER
11080..11081 ; CM # Mn [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA 11080..11081 ; CM # Mn [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA
11082 ; CM # Mc KAITHI SIGN VISARGA 11082 ; CM # Mc KAITHI SIGN VISARGA
11083..110AF ; AL # Lo [45] KAITHI LETTER A..KAITHI LETTER HA 11083..110AF ; AL # Lo [45] KAITHI LETTER A..KAITHI LETTER HA
@ -2834,10 +2838,10 @@ FFFD;AI # So REPLACEMENT CHARACTER
110B7..110B8 ; CM # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU 110B7..110B8 ; CM # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU
110B9..110BA ; CM # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA 110B9..110BA ; CM # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA
110BB..110BC ; AL # Po [2] KAITHI ABBREVIATION SIGN..KAITHI ENUMERATION SIGN 110BB..110BC ; AL # Po [2] KAITHI ABBREVIATION SIGN..KAITHI ENUMERATION SIGN
110BD;AL # Cf KAITHI NUMBER SIGN 110BD ; NU # Cf KAITHI NUMBER SIGN
110BE..110C1 ; BA # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA 110BE..110C1 ; BA # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA
110C2 ; CM # Mn KAITHI VOWEL SIGN VOCALIC R 110C2 ; CM # Mn KAITHI VOWEL SIGN VOCALIC R
110CD;AL # Cf KAITHI NUMBER SIGN ABOVE 110CD ; NU # Cf KAITHI NUMBER SIGN ABOVE
110D0..110E8 ; AL # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 110D0..110E8 ; AL # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE
110F0..110F9 ; NU # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE 110F0..110F9 ; NU # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE
11100..11102 ; CM # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA 11100..11102 ; CM # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA
@ -2903,22 +2907,25 @@ FFFD;AI # So REPLACEMENT CHARACTER
112F0..112F9 ; NU # Nd [10] KHUDAWADI DIGIT ZERO..KHUDAWADI DIGIT NINE 112F0..112F9 ; NU # Nd [10] KHUDAWADI DIGIT ZERO..KHUDAWADI DIGIT NINE
11300..11301 ; CM # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU 11300..11301 ; CM # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
11302..11303 ; CM # Mc [2] GRANTHA SIGN ANUSVARA..GRANTHA SIGN VISARGA 11302..11303 ; CM # Mc [2] GRANTHA SIGN ANUSVARA..GRANTHA SIGN VISARGA
11305..1130C;AL # Lo [8] GRANTHA LETTER A..GRANTHA LETTER VOCALIC L 11305..1130C ; AK # Lo [8] GRANTHA LETTER A..GRANTHA LETTER VOCALIC L
1130F..11310;AL # Lo [2] GRANTHA LETTER EE..GRANTHA LETTER AI 1130F..11310 ; AK # Lo [2] GRANTHA LETTER EE..GRANTHA LETTER AI
11313..11328;AL # Lo [22] GRANTHA LETTER OO..GRANTHA LETTER NA 11313..11328 ; AK # Lo [22] GRANTHA LETTER OO..GRANTHA LETTER NA
1132A..11330;AL # Lo [7] GRANTHA LETTER PA..GRANTHA LETTER RA 1132A..11330 ; AK # Lo [7] GRANTHA LETTER PA..GRANTHA LETTER RA
11332..11333;AL # Lo [2] GRANTHA LETTER LA..GRANTHA LETTER LLA 11332..11333 ; AK # Lo [2] GRANTHA LETTER LA..GRANTHA LETTER LLA
11335..11339;AL # Lo [5] GRANTHA LETTER VA..GRANTHA LETTER HA 11335..11339 ; AK # Lo [5] GRANTHA LETTER VA..GRANTHA LETTER HA
1133B..1133C ; CM # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA 1133B..1133C ; CM # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA
1133D;AL # Lo GRANTHA SIGN AVAGRAHA 1133D ; BA # Lo GRANTHA SIGN AVAGRAHA
1133E..1133F ; CM # Mc [2] GRANTHA VOWEL SIGN AA..GRANTHA VOWEL SIGN I 1133E..1133F ; CM # Mc [2] GRANTHA VOWEL SIGN AA..GRANTHA VOWEL SIGN I
11340 ; CM # Mn GRANTHA VOWEL SIGN II 11340 ; CM # Mn GRANTHA VOWEL SIGN II
11341..11344 ; CM # Mc [4] GRANTHA VOWEL SIGN U..GRANTHA VOWEL SIGN VOCALIC RR 11341..11344 ; CM # Mc [4] GRANTHA VOWEL SIGN U..GRANTHA VOWEL SIGN VOCALIC RR
11347..11348 ; CM # Mc [2] GRANTHA VOWEL SIGN EE..GRANTHA VOWEL SIGN AI 11347..11348 ; CM # Mc [2] GRANTHA VOWEL SIGN EE..GRANTHA VOWEL SIGN AI
1134B..1134D;CM # Mc [3] GRANTHA VOWEL SIGN OO..GRANTHA SIGN VIRAMA 1134B..1134C ; CM # Mc [2] GRANTHA VOWEL SIGN OO..GRANTHA VOWEL SIGN AU
11350;AL # Lo GRANTHA OM 1134D ; VI # Mc GRANTHA SIGN VIRAMA
11350 ; AS # Lo GRANTHA OM
11357 ; CM # Mc GRANTHA AU LENGTH MARK 11357 ; CM # Mc GRANTHA AU LENGTH MARK
1135D..11361;AL # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL 1135D ; BA # Lo GRANTHA SIGN PLUTA
1135E..1135F ; AS # Lo [2] GRANTHA LETTER VEDIC ANUSVARA..GRANTHA LETTER VEDIC DOUBLE ANUSVARA
11360..11361 ; AK # Lo [2] GRANTHA LETTER VOCALIC RR..GRANTHA LETTER VOCALIC LL
11362..11363 ; CM # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL 11362..11363 ; CM # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL
11366..1136C ; CM # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11366..1136C ; CM # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX
11370..11374 ; CM # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA 11370..11374 ; CM # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA
@ -3008,23 +3015,23 @@ FFFD;AI # So REPLACEMENT CHARACTER
118E0..118E9 ; NU # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 118E0..118E9 ; NU # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE
118EA..118F2 ; AL # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY 118EA..118F2 ; AL # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY
118FF ; AL # Lo WARANG CITI OM 118FF ; AL # Lo WARANG CITI OM
11900..11906;AL # Lo [7] DIVES AKURU LETTER A..DIVES AKURU LETTER E 11900..11906 ; AK # Lo [7] DIVES AKURU LETTER A..DIVES AKURU LETTER E
11909;AL # Lo DIVES AKURU LETTER O 11909 ; AK # Lo DIVES AKURU LETTER O
1190C..11913;AL # Lo [8] DIVES AKURU LETTER KA..DIVES AKURU LETTER JA 1190C..11913 ; AK # Lo [8] DIVES AKURU LETTER KA..DIVES AKURU LETTER JA
11915..11916;AL # Lo [2] DIVES AKURU LETTER NYA..DIVES AKURU LETTER TTA 11915..11916 ; AK # Lo [2] DIVES AKURU LETTER NYA..DIVES AKURU LETTER TTA
11918..1192F;AL # Lo [24] DIVES AKURU LETTER DDA..DIVES AKURU LETTER ZA 11918..1192F ; AK # Lo [24] DIVES AKURU LETTER DDA..DIVES AKURU LETTER ZA
11930..11935 ; CM # Mc [6] DIVES AKURU VOWEL SIGN AA..DIVES AKURU VOWEL SIGN E 11930..11935 ; CM # Mc [6] DIVES AKURU VOWEL SIGN AA..DIVES AKURU VOWEL SIGN E
11937..11938 ; CM # Mc [2] DIVES AKURU VOWEL SIGN AI..DIVES AKURU VOWEL SIGN O 11937..11938 ; CM # Mc [2] DIVES AKURU VOWEL SIGN AI..DIVES AKURU VOWEL SIGN O
1193B..1193C ; CM # Mn [2] DIVES AKURU SIGN ANUSVARA..DIVES AKURU SIGN CANDRABINDU 1193B..1193C ; CM # Mn [2] DIVES AKURU SIGN ANUSVARA..DIVES AKURU SIGN CANDRABINDU
1193D ; CM # Mc DIVES AKURU SIGN HALANTA 1193D ; CM # Mc DIVES AKURU SIGN HALANTA
1193E;CM # Mn DIVES AKURU VIRAMA 1193E ; VI # Mn DIVES AKURU VIRAMA
1193F;AL # Lo DIVES AKURU PREFIXED NASAL SIGN 1193F ; AP # Lo DIVES AKURU PREFIXED NASAL SIGN
11940 ; CM # Mc DIVES AKURU MEDIAL YA 11940 ; CM # Mc DIVES AKURU MEDIAL YA
11941;AL # Lo DIVES AKURU INITIAL RA 11941 ; AP # Lo DIVES AKURU INITIAL RA
11942 ; CM # Mc DIVES AKURU MEDIAL RA 11942 ; CM # Mc DIVES AKURU MEDIAL RA
11943 ; CM # Mn DIVES AKURU SIGN NUKTA 11943 ; CM # Mn DIVES AKURU SIGN NUKTA
11944..11946 ; BA # Po [3] DIVES AKURU DOUBLE DANDA..DIVES AKURU END OF TEXT MARK 11944..11946 ; BA # Po [3] DIVES AKURU DOUBLE DANDA..DIVES AKURU END OF TEXT MARK
11950..11959;NU # Nd [10] DIVES AKURU DIGIT ZERO..DIVES AKURU DIGIT NINE 11950..11959 ; ID # Nd [10] DIVES AKURU DIGIT ZERO..DIVES AKURU DIGIT NINE
119A0..119A7 ; AL # Lo [8] NANDINAGARI LETTER A..NANDINAGARI LETTER VOCALIC RR 119A0..119A7 ; AL # Lo [8] NANDINAGARI LETTER A..NANDINAGARI LETTER VOCALIC RR
119AA..119D0 ; AL # Lo [39] NANDINAGARI LETTER E..NANDINAGARI LETTER RRA 119AA..119D0 ; AL # Lo [39] NANDINAGARI LETTER E..NANDINAGARI LETTER RRA
119D1..119D3 ; CM # Mc [3] NANDINAGARI VOWEL SIGN AA..NANDINAGARI VOWEL SIGN II 119D1..119D3 ; CM # Mc [3] NANDINAGARI VOWEL SIGN AA..NANDINAGARI VOWEL SIGN II
@ -3106,24 +3113,25 @@ FFFD;AI # So REPLACEMENT CHARACTER
11D97 ; CM # Mn GUNJALA GONDI VIRAMA 11D97 ; CM # Mn GUNJALA GONDI VIRAMA
11D98 ; AL # Lo GUNJALA GONDI OM 11D98 ; AL # Lo GUNJALA GONDI OM
11DA0..11DA9 ; NU # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE 11DA0..11DA9 ; NU # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE
11EE0..11EF2;AL # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA 11EE0..11EF1 ; AS # Lo [18] MAKASAR LETTER KA..MAKASAR LETTER A
11EF2 ; BA # Lo MAKASAR ANGKA
11EF3..11EF4 ; CM # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U 11EF3..11EF4 ; CM # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
11EF5..11EF6 ; CM # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O 11EF5..11EF6 ; CM # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
11EF7..11EF8;AL # Po [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION 11EF7..11EF8 ; BA # Po [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION
11F00..11F01 ; CM # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA 11F00..11F01 ; CM # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA
11F02;AL # Lo KAWI SIGN REPHA 11F02 ; AP # Lo KAWI SIGN REPHA
11F03 ; CM # Mc KAWI SIGN VISARGA 11F03 ; CM # Mc KAWI SIGN VISARGA
11F04..11F10;AL # Lo [13] KAWI LETTER A..KAWI LETTER O 11F04..11F10 ; AK # Lo [13] KAWI LETTER A..KAWI LETTER O
11F12..11F33;AL # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA 11F12..11F33 ; AK # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA
11F34..11F35 ; CM # Mc [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA 11F34..11F35 ; CM # Mc [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA
11F36..11F3A ; CM # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R 11F36..11F3A ; CM # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R
11F3E..11F3F ; CM # Mc [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI 11F3E..11F3F ; CM # Mc [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI
11F40 ; CM # Mn KAWI VOWEL SIGN EU 11F40 ; CM # Mn KAWI VOWEL SIGN EU
11F41 ; CM # Mc KAWI SIGN KILLER 11F41 ; CM # Mc KAWI SIGN KILLER
11F42;CM # Mn KAWI CONJOINER 11F42 ; VI # Mn KAWI CONJOINER
11F43..11F44 ; BA # Po [2] KAWI DANDA..KAWI DOUBLE DANDA 11F43..11F44 ; BA # Po [2] KAWI DANDA..KAWI DOUBLE DANDA
11F45..11F4F ; ID # Po [11] KAWI PUNCTUATION SECTION MARKER..KAWI PUNCTUATION CLOSING SPIRAL 11F45..11F4F ; ID # Po [11] KAWI PUNCTUATION SECTION MARKER..KAWI PUNCTUATION CLOSING SPIRAL
11F50..11F59;NU # Nd [10] KAWI DIGIT ZERO..KAWI DIGIT NINE 11F50..11F59 ; AS # Nd [10] KAWI DIGIT ZERO..KAWI DIGIT NINE
11FB0 ; AL # Lo LISU LETTER YHA 11FB0 ; AL # Lo LISU LETTER YHA
11FC0..11FD4 ; AL # No [21] TAMIL FRACTION ONE THREE-HUNDRED-AND-TWENTIETH..TAMIL FRACTION DOWNSCALING FACTOR KIIZH 11FC0..11FD4 ; AL # No [21] TAMIL FRACTION ONE THREE-HUNDRED-AND-TWENTIETH..TAMIL FRACTION DOWNSCALING FACTOR KIIZH
11FD5..11FDC ; AL # So [8] TAMIL SIGN NEL..TAMIL SIGN MUKKURUNI 11FD5..11FDC ; AL # So [8] TAMIL SIGN NEL..TAMIL SIGN MUKKURUNI
@ -3149,7 +3157,8 @@ FFFD;AI # So REPLACEMENT CHARACTER
1328A..13378 ; AL # Lo [239] EGYPTIAN HIEROGLYPH O037..EGYPTIAN HIEROGLYPH V011 1328A..13378 ; AL # Lo [239] EGYPTIAN HIEROGLYPH O037..EGYPTIAN HIEROGLYPH V011
13379 ; OP # Lo EGYPTIAN HIEROGLYPH V011A 13379 ; OP # Lo EGYPTIAN HIEROGLYPH V011A
1337A..1337B ; CL # Lo [2] EGYPTIAN HIEROGLYPH V011B..EGYPTIAN HIEROGLYPH V011C 1337A..1337B ; CL # Lo [2] EGYPTIAN HIEROGLYPH V011B..EGYPTIAN HIEROGLYPH V011C
1337C..1342F;AL # Lo [180] EGYPTIAN HIEROGLYPH V012..EGYPTIAN HIEROGLYPH V011D 1337C..1342E ; AL # Lo [179] EGYPTIAN HIEROGLYPH V012..EGYPTIAN HIEROGLYPH AA032
1342F ; OP # Lo EGYPTIAN HIEROGLYPH V011D
13430..13436 ; GL # Cf [7] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH OVERLAY MIDDLE 13430..13436 ; GL # Cf [7] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH OVERLAY MIDDLE
13437 ; OP # Cf EGYPTIAN HIEROGLYPH BEGIN SEGMENT 13437 ; OP # Cf EGYPTIAN HIEROGLYPH BEGIN SEGMENT
13438 ; CL # Cf EGYPTIAN HIEROGLYPH END SEGMENT 13438 ; CL # Cf EGYPTIAN HIEROGLYPH END SEGMENT
@ -3580,7 +3589,9 @@ FFFD;AI # So REPLACEMENT CHARACTER
2B820..2CEA1 ; ID # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2B820..2CEA1 ; ID # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
2CEA2..2CEAF ; ID # Cn [14] <reserved-2CEA2>..<reserved-2CEAF> 2CEA2..2CEAF ; ID # Cn [14] <reserved-2CEA2>..<reserved-2CEAF>
2CEB0..2EBE0 ; ID # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2CEB0..2EBE0 ; ID # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2EBE1..2F7FF;ID # Cn [3103] <reserved-2EBE1>..<reserved-2F7FF> 2EBE1..2EBEF ; ID # Cn [15] <reserved-2EBE1>..<reserved-2EBEF>
2EBF0..2EE5D ; ID # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
2EE5E..2F7FF ; ID # Cn [2466] <reserved-2EE5E>..<reserved-2F7FF>
2F800..2FA1D ; ID # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 2F800..2FA1D ; ID # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
2FA1E..2FA1F ; ID # Cn [2] <reserved-2FA1E>..<reserved-2FA1F> 2FA1E..2FA1F ; ID # Cn [2] <reserved-2FA1E>..<reserved-2FA1F>
2FA20..2FFFD ; ID # Cn [1502] <reserved-2FA20>..<reserved-2FFFD> 2FA20..2FFFD ; ID # Cn [1502] <reserved-2FA20>..<reserved-2FFFD>

View File

@ -1,6 +1,6 @@
# NormalizationCorrections-15.0.0.txt # NormalizationCorrections-15.1.0.txt
# Date: 2022-05-03, 18:53:00 GMT [KW, LI] # Date: 2023-01-05
# © 2022 Unicode®, Inc. # © 2023 Unicode®, Inc.
# For terms of use, see https://www.unicode.org/terms_of_use.html # For terms of use, see https://www.unicode.org/terms_of_use.html
# #
# Unicode Character Database # Unicode Character Database

View File

@ -1,6 +1,6 @@
# Scripts-15.0.0.txt # Scripts-15.1.0.txt
# Date: 2022-04-26, 23:15:02 GMT # Date: 2023-07-28, 16:01:07 GMT
# © 2022 Unicode®, Inc. # © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html # For terms of use, see https://www.unicode.org/terms_of_use.html
# #
@ -357,7 +357,7 @@
2E5B ; Common # Ps BOTTOM HALF LEFT PARENTHESIS 2E5B ; Common # Ps BOTTOM HALF LEFT PARENTHESIS
2E5C ; Common # Pe BOTTOM HALF RIGHT PARENTHESIS 2E5C ; Common # Pe BOTTOM HALF RIGHT PARENTHESIS
2E5D ; Common # Pd OBLIQUE HYPHEN 2E5D ; Common # Pd OBLIQUE HYPHEN
2FF0..2FFB ; Common # So [12] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID 2FF0..2FFF ; Common # So [16] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER ROTATION
3000 ; Common # Zs IDEOGRAPHIC SPACE 3000 ; Common # Zs IDEOGRAPHIC SPACE
3001..3003 ; Common # Po [3] IDEOGRAPHIC COMMA..DITTO MARK 3001..3003 ; Common # Po [3] IDEOGRAPHIC COMMA..DITTO MARK
3004 ; Common # So JAPANESE INDUSTRIAL STANDARD SYMBOL 3004 ; Common # So JAPANESE INDUSTRIAL STANDARD SYMBOL
@ -399,6 +399,7 @@
3192..3195 ; Common # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK 3192..3195 ; Common # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK
3196..319F ; Common # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK 3196..319F ; Common # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK
31C0..31E3 ; Common # So [36] CJK STROKE T..CJK STROKE Q 31C0..31E3 ; Common # So [36] CJK STROKE T..CJK STROKE Q
31EF ; Common # So IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION
3220..3229 ; Common # No [10] PARENTHESIZED IDEOGRAPH ONE..PARENTHESIZED IDEOGRAPH TEN 3220..3229 ; Common # No [10] PARENTHESIZED IDEOGRAPH ONE..PARENTHESIZED IDEOGRAPH TEN
322A..3247 ; Common # So [30] PARENTHESIZED IDEOGRAPH MOON..CIRCLED IDEOGRAPH KOTO 322A..3247 ; Common # So [30] PARENTHESIZED IDEOGRAPH MOON..CIRCLED IDEOGRAPH KOTO
3248..324F ; Common # No [8] CIRCLED NUMBER TEN ON BLACK SQUARE..CIRCLED NUMBER EIGHTY ON BLACK SQUARE 3248..324F ; Common # No [8] CIRCLED NUMBER TEN ON BLACK SQUARE..CIRCLED NUMBER EIGHTY ON BLACK SQUARE
@ -629,7 +630,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
E0001 ; Common # Cf LANGUAGE TAG E0001 ; Common # Cf LANGUAGE TAG
E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
# Total code points: 8301 # Total code points: 8306
# ================================================ # ================================================
@ -1593,11 +1594,12 @@ FA70..FAD9 ; Han # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILI
2B740..2B81D ; Han # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B740..2B81D ; Han # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2B820..2CEA1 ; Han # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2B820..2CEA1 ; Han # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
2CEB0..2EBE0 ; Han # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2CEB0..2EBE0 ; Han # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2EBF0..2EE5D ; Han # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
2F800..2FA1D ; Han # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 2F800..2FA1D ; Han # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
30000..3134A ; Han # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 30000..3134A ; Han # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
31350..323AF ; Han # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF 31350..323AF ; Han # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
# Total code points: 98408 # Total code points: 99030
# ================================================ # ================================================

View File

@ -1,6 +1,6 @@
# SentenceBreakProperty-15.0.0.txt # SentenceBreakProperty-15.1.0.txt
# Date: 2022-08-05, 22:17:35 GMT # Date: 2023-07-28, 23:34:37 GMT
# © 2022 Unicode®, Inc. # © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html # For terms of use, see https://www.unicode.org/terms_of_use.html
# #
@ -580,12 +580,8 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# ================================================ # ================================================
00AD ; Format # Cf SOFT HYPHEN 00AD ; Format # Cf SOFT HYPHEN
0600..0605 ; Format # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE
061C ; Format # Cf ARABIC LETTER MARK 061C ; Format # Cf ARABIC LETTER MARK
06DD ; Format # Cf ARABIC END OF AYAH
070F ; Format # Cf SYRIAC ABBREVIATION MARK 070F ; Format # Cf SYRIAC ABBREVIATION MARK
0890..0891 ; Format # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE
08E2 ; Format # Cf ARABIC DISPUTED END OF AYAH
180E ; Format # Cf MONGOLIAN VOWEL SEPARATOR 180E ; Format # Cf MONGOLIAN VOWEL SEPARATOR
200B ; Format # Cf ZERO WIDTH SPACE 200B ; Format # Cf ZERO WIDTH SPACE
200E..200F ; Format # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK 200E..200F ; Format # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
@ -594,14 +590,12 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
2066..206F ; Format # Cf [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES 2066..206F ; Format # Cf [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES
FEFF ; Format # Cf ZERO WIDTH NO-BREAK SPACE FEFF ; Format # Cf ZERO WIDTH NO-BREAK SPACE
FFF9..FFFB ; Format # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR FFF9..FFFB ; Format # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR
110BD ; Format # Cf KAITHI NUMBER SIGN
110CD ; Format # Cf KAITHI NUMBER SIGN ABOVE
13430..1343F ; Format # Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE 13430..1343F ; Format # Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE
1BCA0..1BCA3 ; Format # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP 1BCA0..1BCA3 ; Format # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
1D173..1D17A ; Format # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE 1D173..1D17A ; Format # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
E0001 ; Format # Cf LANGUAGE TAG E0001 ; Format # Cf LANGUAGE TAG
# Total code points: 72 # Total code points: 60
# ================================================ # ================================================
@ -2537,19 +2531,24 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
2B740..2B81D ; OLetter # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B740..2B81D ; OLetter # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2B820..2CEA1 ; OLetter # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2B820..2CEA1 ; OLetter # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
2CEB0..2EBE0 ; OLetter # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2CEB0..2EBE0 ; OLetter # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2EBF0..2EE5D ; OLetter # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
2F800..2FA1D ; OLetter # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 2F800..2FA1D ; OLetter # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
31350..323AF ; OLetter # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF 31350..323AF ; OLetter # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
# Total code points: 132036 # Total code points: 132658
# ================================================ # ================================================
0030..0039 ; Numeric # Nd [10] DIGIT ZERO..DIGIT NINE 0030..0039 ; Numeric # Nd [10] DIGIT ZERO..DIGIT NINE
0600..0605 ; Numeric # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE
0660..0669 ; Numeric # Nd [10] ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE 0660..0669 ; Numeric # Nd [10] ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE
066B..066C ; Numeric # Po [2] ARABIC DECIMAL SEPARATOR..ARABIC THOUSANDS SEPARATOR 066B..066C ; Numeric # Po [2] ARABIC DECIMAL SEPARATOR..ARABIC THOUSANDS SEPARATOR
06DD ; Numeric # Cf ARABIC END OF AYAH
06F0..06F9 ; Numeric # Nd [10] EXTENDED ARABIC-INDIC DIGIT ZERO..EXTENDED ARABIC-INDIC DIGIT NINE 06F0..06F9 ; Numeric # Nd [10] EXTENDED ARABIC-INDIC DIGIT ZERO..EXTENDED ARABIC-INDIC DIGIT NINE
07C0..07C9 ; Numeric # Nd [10] NKO DIGIT ZERO..NKO DIGIT NINE 07C0..07C9 ; Numeric # Nd [10] NKO DIGIT ZERO..NKO DIGIT NINE
0890..0891 ; Numeric # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE
08E2 ; Numeric # Cf ARABIC DISPUTED END OF AYAH
0966..096F ; Numeric # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE 0966..096F ; Numeric # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE
09E6..09EF ; Numeric # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE 09E6..09EF ; Numeric # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE
0A66..0A6F ; Numeric # Nd [10] GURMUKHI DIGIT ZERO..GURMUKHI DIGIT NINE 0A66..0A6F ; Numeric # Nd [10] GURMUKHI DIGIT ZERO..GURMUKHI DIGIT NINE
@ -2586,6 +2585,8 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE
104A0..104A9 ; Numeric # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE 104A0..104A9 ; Numeric # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE
10D30..10D39 ; Numeric # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE 10D30..10D39 ; Numeric # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE
11066..1106F ; Numeric # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE 11066..1106F ; Numeric # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE
110BD ; Numeric # Cf KAITHI NUMBER SIGN
110CD ; Numeric # Cf KAITHI NUMBER SIGN ABOVE
110F0..110F9 ; Numeric # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE 110F0..110F9 ; Numeric # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE
11136..1113F ; Numeric # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE 11136..1113F ; Numeric # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE
111D0..111D9 ; Numeric # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE 111D0..111D9 ; Numeric # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE
@ -2611,7 +2612,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE
1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE
1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE 1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE
# Total code points: 682 # Total code points: 694
# ================================================ # ================================================
@ -2640,6 +2641,7 @@ FF0E ; ATerm # Po FULLWIDTH FULL STOP
1367..1368 ; STerm # Po [2] ETHIOPIC QUESTION MARK..ETHIOPIC PARAGRAPH SEPARATOR 1367..1368 ; STerm # Po [2] ETHIOPIC QUESTION MARK..ETHIOPIC PARAGRAPH SEPARATOR
166E ; STerm # Po CANADIAN SYLLABICS FULL STOP 166E ; STerm # Po CANADIAN SYLLABICS FULL STOP
1735..1736 ; STerm # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION 1735..1736 ; STerm # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION
17D4..17D5 ; STerm # Po [2] KHMER SIGN KHAN..KHMER SIGN BARIYOOSAN
1803 ; STerm # Po MONGOLIAN FULL STOP 1803 ; STerm # Po MONGOLIAN FULL STOP
1809 ; STerm # Po MONGOLIAN MANCHU FULL STOP 1809 ; STerm # Po MONGOLIAN MANCHU FULL STOP
1944..1945 ; STerm # Po [2] LIMBU EXCLAMATION MARK..LIMBU QUESTION MARK 1944..1945 ; STerm # Po [2] LIMBU EXCLAMATION MARK..LIMBU QUESTION MARK
@ -2702,7 +2704,7 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP
1BC9F ; STerm # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BC9F ; STerm # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP
1DA88 ; STerm # Po SIGNWRITING FULL STOP 1DA88 ; STerm # Po SIGNWRITING FULL STOP
# Total code points: 151 # Total code points: 153
# ================================================ # ================================================

View File

@ -1,6 +1,6 @@
# SpecialCasing-15.0.0.txt # SpecialCasing-15.1.0.txt
# Date: 2022-02-02, 23:35:52 GMT # Date: 2023-01-05, 20:35:03 GMT
# © 2022 Unicode®, Inc. # © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html # For terms of use, see https://www.unicode.org/terms_of_use.html
# #

View File

@ -11231,6 +11231,10 @@
2FF9;IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM UPPER RIGHT;So;0;ON;;;;;N;;;;; 2FF9;IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM UPPER RIGHT;So;0;ON;;;;;N;;;;;
2FFA;IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM LOWER LEFT;So;0;ON;;;;;N;;;;; 2FFA;IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM LOWER LEFT;So;0;ON;;;;;N;;;;;
2FFB;IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID;So;0;ON;;;;;N;;;;; 2FFB;IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID;So;0;ON;;;;;N;;;;;
2FFC;IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM RIGHT;So;0;ON;;;;;N;;;;;
2FFD;IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM LOWER RIGHT;So;0;ON;;;;;N;;;;;
2FFE;IDEOGRAPHIC DESCRIPTION CHARACTER HORIZONTAL REFLECTION;So;0;ON;;;;;N;;;;;
2FFF;IDEOGRAPHIC DESCRIPTION CHARACTER ROTATION;So;0;ON;;;;;N;;;;;
3000;IDEOGRAPHIC SPACE;Zs;0;WS;<wide> 0020;;;;N;;;;; 3000;IDEOGRAPHIC SPACE;Zs;0;WS;<wide> 0020;;;;N;;;;;
3001;IDEOGRAPHIC COMMA;Po;0;ON;;;;;N;;;;; 3001;IDEOGRAPHIC COMMA;Po;0;ON;;;;;N;;;;;
3002;IDEOGRAPHIC FULL STOP;Po;0;ON;;;;;N;IDEOGRAPHIC PERIOD;;;; 3002;IDEOGRAPHIC FULL STOP;Po;0;ON;;;;;N;IDEOGRAPHIC PERIOD;;;;
@ -11705,6 +11709,7 @@
31E1;CJK STROKE HZZZG;So;0;ON;;;;;N;;;;; 31E1;CJK STROKE HZZZG;So;0;ON;;;;;N;;;;;
31E2;CJK STROKE PG;So;0;ON;;;;;N;;;;; 31E2;CJK STROKE PG;So;0;ON;;;;;N;;;;;
31E3;CJK STROKE Q;So;0;ON;;;;;N;;;;; 31E3;CJK STROKE Q;So;0;ON;;;;;N;;;;;
31EF;IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION;So;0;ON;;;;;N;;;;;
31F0;KATAKANA LETTER SMALL KU;Lo;0;L;;;;;N;;;;; 31F0;KATAKANA LETTER SMALL KU;Lo;0;L;;;;;N;;;;;
31F1;KATAKANA LETTER SMALL SI;Lo;0;L;;;;;N;;;;; 31F1;KATAKANA LETTER SMALL SI;Lo;0;L;;;;;N;;;;;
31F2;KATAKANA LETTER SMALL SU;Lo;0;L;;;;;N;;;;; 31F2;KATAKANA LETTER SMALL SU;Lo;0;L;;;;;N;;;;;
@ -34035,6 +34040,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
2CEA1;<CJK Ideograph Extension E, Last>;Lo;0;L;;;;;N;;;;; 2CEA1;<CJK Ideograph Extension E, Last>;Lo;0;L;;;;;N;;;;;
2CEB0;<CJK Ideograph Extension F, First>;Lo;0;L;;;;;N;;;;; 2CEB0;<CJK Ideograph Extension F, First>;Lo;0;L;;;;;N;;;;;
2EBE0;<CJK Ideograph Extension F, Last>;Lo;0;L;;;;;N;;;;; 2EBE0;<CJK Ideograph Extension F, Last>;Lo;0;L;;;;;N;;;;;
2EBF0;<CJK Ideograph Extension I, First>;Lo;0;L;;;;;N;;;;;
2EE5D;<CJK Ideograph Extension I, Last>;Lo;0;L;;;;;N;;;;;
2F800;CJK COMPATIBILITY IDEOGRAPH-2F800;Lo;0;L;4E3D;;;;N;;;;; 2F800;CJK COMPATIBILITY IDEOGRAPH-2F800;Lo;0;L;4E3D;;;;N;;;;;
2F801;CJK COMPATIBILITY IDEOGRAPH-2F801;Lo;0;L;4E38;;;;N;;;;; 2F801;CJK COMPATIBILITY IDEOGRAPH-2F801;Lo;0;L;4E38;;;;N;;;;;
2F802;CJK COMPATIBILITY IDEOGRAPH-2F802;Lo;0;L;4E41;;;;N;;;;; 2F802;CJK COMPATIBILITY IDEOGRAPH-2F802;Lo;0;L;4E41;;;;N;;;;;

View File

@ -1,6 +1,6 @@
# WordBreakProperty-15.0.0.txt # WordBreakProperty-15.1.0.txt
# Date: 2022-04-27, 02:41:26 GMT # Date: 2023-03-31, 03:19:05 GMT
# © 2022 Unicode®, Inc. # © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html # For terms of use, see https://www.unicode.org/terms_of_use.html
# #
@ -615,12 +615,7 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# ================================================ # ================================================
00AD ; Format # Cf SOFT HYPHEN 00AD ; Format # Cf SOFT HYPHEN
0600..0605 ; Format # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE
061C ; Format # Cf ARABIC LETTER MARK 061C ; Format # Cf ARABIC LETTER MARK
06DD ; Format # Cf ARABIC END OF AYAH
070F ; Format # Cf SYRIAC ABBREVIATION MARK
0890..0891 ; Format # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE
08E2 ; Format # Cf ARABIC DISPUTED END OF AYAH
180E ; Format # Cf MONGOLIAN VOWEL SEPARATOR 180E ; Format # Cf MONGOLIAN VOWEL SEPARATOR
200E..200F ; Format # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK 200E..200F ; Format # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
202A..202E ; Format # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE 202A..202E ; Format # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE
@ -628,14 +623,12 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
2066..206F ; Format # Cf [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES 2066..206F ; Format # Cf [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES
FEFF ; Format # Cf ZERO WIDTH NO-BREAK SPACE FEFF ; Format # Cf ZERO WIDTH NO-BREAK SPACE
FFF9..FFFB ; Format # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR FFF9..FFFB ; Format # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR
110BD ; Format # Cf KAITHI NUMBER SIGN
110CD ; Format # Cf KAITHI NUMBER SIGN ABOVE
13430..1343F ; Format # Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE 13430..1343F ; Format # Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE
1BCA0..1BCA3 ; Format # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP 1BCA0..1BCA3 ; Format # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
1D173..1D17A ; Format # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE 1D173..1D17A ; Format # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
E0001 ; Format # Cf LANGUAGE TAG E0001 ; Format # Cf LANGUAGE TAG
# Total code points: 71 # Total code points: 58
# ================================================ # ================================================
@ -718,6 +711,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
06EE..06EF ; ALetter # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V 06EE..06EF ; ALetter # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V
06FA..06FC ; ALetter # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW 06FA..06FC ; ALetter # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW
06FF ; ALetter # Lo ARABIC LETTER HEH WITH INVERTED V 06FF ; ALetter # Lo ARABIC LETTER HEH WITH INVERTED V
070F ; ALetter # Cf SYRIAC ABBREVIATION MARK
0710 ; ALetter # Lo SYRIAC LETTER ALAPH 0710 ; ALetter # Lo SYRIAC LETTER ALAPH
0712..072F ; ALetter # Lo [30] SYRIAC LETTER BETH..SYRIAC LETTER PERSIAN DHALATH 0712..072F ; ALetter # Lo [30] SYRIAC LETTER BETH..SYRIAC LETTER PERSIAN DHALATH
074D..07A5 ; ALetter # Lo [89] SYRIAC LETTER SOGDIAN ZHAIN..THAANA LETTER WAAVU 074D..07A5 ; ALetter # Lo [89] SYRIAC LETTER SOGDIAN ZHAIN..THAANA LETTER WAAVU
@ -1319,7 +1313,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z 1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z
# Total code points: 29489 # Total code points: 29490
# ================================================ # ================================================
@ -1369,10 +1363,14 @@ FF0E ; MidNumLet # Po FULLWIDTH FULL STOP
# ================================================ # ================================================
0030..0039 ; Numeric # Nd [10] DIGIT ZERO..DIGIT NINE 0030..0039 ; Numeric # Nd [10] DIGIT ZERO..DIGIT NINE
0600..0605 ; Numeric # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE
0660..0669 ; Numeric # Nd [10] ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE 0660..0669 ; Numeric # Nd [10] ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE
066B ; Numeric # Po ARABIC DECIMAL SEPARATOR 066B ; Numeric # Po ARABIC DECIMAL SEPARATOR
06DD ; Numeric # Cf ARABIC END OF AYAH
06F0..06F9 ; Numeric # Nd [10] EXTENDED ARABIC-INDIC DIGIT ZERO..EXTENDED ARABIC-INDIC DIGIT NINE 06F0..06F9 ; Numeric # Nd [10] EXTENDED ARABIC-INDIC DIGIT ZERO..EXTENDED ARABIC-INDIC DIGIT NINE
07C0..07C9 ; Numeric # Nd [10] NKO DIGIT ZERO..NKO DIGIT NINE 07C0..07C9 ; Numeric # Nd [10] NKO DIGIT ZERO..NKO DIGIT NINE
0890..0891 ; Numeric # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE
08E2 ; Numeric # Cf ARABIC DISPUTED END OF AYAH
0966..096F ; Numeric # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE 0966..096F ; Numeric # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE
09E6..09EF ; Numeric # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE 09E6..09EF ; Numeric # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE
0A66..0A6F ; Numeric # Nd [10] GURMUKHI DIGIT ZERO..GURMUKHI DIGIT NINE 0A66..0A6F ; Numeric # Nd [10] GURMUKHI DIGIT ZERO..GURMUKHI DIGIT NINE
@ -1409,6 +1407,8 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE
104A0..104A9 ; Numeric # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE 104A0..104A9 ; Numeric # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE
10D30..10D39 ; Numeric # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE 10D30..10D39 ; Numeric # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE
11066..1106F ; Numeric # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE 11066..1106F ; Numeric # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE
110BD ; Numeric # Cf KAITHI NUMBER SIGN
110CD ; Numeric # Cf KAITHI NUMBER SIGN ABOVE
110F0..110F9 ; Numeric # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE 110F0..110F9 ; Numeric # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE
11136..1113F ; Numeric # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE 11136..1113F ; Numeric # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE
111D0..111D9 ; Numeric # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE 111D0..111D9 ; Numeric # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE
@ -1434,7 +1434,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE
1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE
1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE 1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE
# Total code points: 681 # Total code points: 693
# ================================================ # ================================================

View File

@ -1,11 +1,11 @@
# emoji-data.txt # emoji-data.txt
# Date: 2022-08-02, 00:26:10 GMT # Date: 2023-02-01, 02:22:54 GMT
# © 2022 Unicode®, Inc. # © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html # For terms of use, see https://www.unicode.org/terms_of_use.html
# #
# Emoji Data for UTS #51 # Emoji Data for UTS #51
# Used with Emoji Version 15.0 and subsequent minor revisions (if any) # Used with Emoji Version 15.1 and subsequent minor revisions (if any)
# #
# For documentation and usage, see https://www.unicode.org/reports/tr51 # For documentation and usage, see https://www.unicode.org/reports/tr51
# #

View File

@ -14,8 +14,8 @@
#include <private/qunicodetables_p.h> #include <private/qunicodetables_p.h>
#endif #endif
#define DATA_VERSION_S "15.0" #define DATA_VERSION_S "15.1"
#define DATA_VERSION_STR "QChar::Unicode_15_0" #define DATA_VERSION_STR "QChar::Unicode_15_1"
static QHash<QByteArray, QChar::UnicodeVersion> age_map; static QHash<QByteArray, QChar::UnicodeVersion> age_map;
@ -51,6 +51,7 @@ static void initAgeMap()
{ QChar::Unicode_13_0, "13.0" }, // UCD Revision 26 { QChar::Unicode_13_0, "13.0" }, // UCD Revision 26
{ QChar::Unicode_14_0, "14.0" }, // UCD Revision 28 { QChar::Unicode_14_0, "14.0" }, // UCD Revision 28
{ QChar::Unicode_15_0, "15.0" }, // UCD Revision 30 { QChar::Unicode_15_0, "15.0" }, // UCD Revision 30
{ QChar::Unicode_15_1, "15.1" }, // UCD Revision 32
{ QChar::Unicode_Unassigned, 0 } { QChar::Unicode_Unassigned, 0 }
}; };
AgeMap *d = ageMap; AgeMap *d = ageMap;
@ -528,7 +529,8 @@ static void initSentenceBreak()
static const char *line_break_class_string = static const char *line_break_class_string =
"// see http://www.unicode.org/reports/tr14/tr14-30.html\n" "// see http://www.unicode.org/reports/tr14/tr14-30.html\n"
"// we don't use the XX and AI classes and map them to AL instead.\n" "// we don't use the XX, AK, AP, AS and AI classes and map them to AL instead.\n"
"// VI and VF classes are mapped to CM.\n"
"enum LineBreakClass {\n" "enum LineBreakClass {\n"
" LineBreak_OP, LineBreak_CL, LineBreak_CP, LineBreak_QU, LineBreak_GL,\n" " LineBreak_OP, LineBreak_CL, LineBreak_CP, LineBreak_QU, LineBreak_GL,\n"
" LineBreak_NS, LineBreak_EX, LineBreak_SY, LineBreak_IS, LineBreak_PR,\n" " LineBreak_NS, LineBreak_EX, LineBreak_SY, LineBreak_IS, LineBreak_PR,\n"
@ -612,6 +614,11 @@ static void initLineBreak()
{ LineBreak_EB, "EB" }, { LineBreak_EB, "EB" },
{ LineBreak_EM, "EM" }, { LineBreak_EM, "EM" },
{ LineBreak_ZWJ, "ZWJ" }, { LineBreak_ZWJ, "ZWJ" },
{ LineBreak_AL, "AK" },
{ LineBreak_AL, "AP" },
{ LineBreak_AL, "AS" },
{ LineBreak_CM, "VI" },
{ LineBreak_CM, "VF" },
{ LineBreak_Unassigned, 0 } { LineBreak_Unassigned, 0 }
}; };
LineBreakList *d = breaks; LineBreakList *d = breaks;