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 6.3] Unicode_14_0 Version 14.0
\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
in version 8.0 of Unicode.

View File

@ -432,6 +432,7 @@ public:
Unicode_13_0,
Unicode_14_0,
Unicode_15_0,
Unicode_15_1,
};
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.
// 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
@ -23,7 +23,7 @@
QT_BEGIN_NAMESPACE
#define UNICODE_DATA_VERSION QChar::Unicode_15_0
#define UNICODE_DATA_VERSION QChar::Unicode_15_1
namespace QUnicodeTables {
@ -142,7 +142,8 @@ enum SentenceBreakClass {
};
// 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 {
LineBreak_OP, LineBreak_CL, LineBreak_CP, LineBreak_QU, LineBreak_GL,
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
# Date: 2022-02-26, 00:39:00 GMT
# © 2022 Unicode®, Inc.
# SentenceBreakTest-15.1.0.txt
# Date: 2023-04-05, 20:41:29 GMT
# © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see 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]
÷ 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]
÷ 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 × 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]
@ -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 × 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 × 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

View File

@ -6,8 +6,8 @@ td, th { vertical-align: top }
</style></head>
<body bgcolor='#FFFFFF'>
<h2>Word_Break Chart</h2>
<p><b>Unicode Version:</b> 15.0.0</p>
<p><b>Date:</b> 2021-11-24, 21:43:58 GMT</p>
<p><b>Unicode Version:</b> 15.1.0</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>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>
@ -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>
</font></td></tr>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
<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>
</font></td></tr>
</table>

View File

@ -1,6 +1,6 @@
# WordBreakTest-15.0.0.txt
# Date: 2022-02-26, 00:39:00 GMT
# © 2022 Unicode®, Inc.
# WordBreakTest-15.1.0.txt
# Date: 2023-03-31, 14:30:32 GMT
# © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see 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]
÷ 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]
÷ 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 × 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]
@ -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 × 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

View File

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

View File

@ -1,6 +1,6 @@
# BidiMirroring-15.0.0.txt
# Date: 2022-05-03, 18:47:00 GMT [KW, RP]
# © 2022 Unicode®, Inc.
# BidiMirroring-15.1.0.txt
# Date: 2023-01-05
# © 2023 Unicode®, Inc.
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
@ -15,7 +15,7 @@
# value, for which there is another Unicode character that typically has a 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
# to another one for character-based mirroring.

View File

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

View File

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

View File

@ -1,6 +1,6 @@
# DerivedAge-15.0.0.txt
# Date: 2022-04-26, 23:14:23 GMT
# © 2022 Unicode®, Inc.
# DerivedAge-15.1.0.txt
# Date: 2023-07-28, 23:33:51 GMT
# © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see 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
# ================================================
# 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

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

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

View File

@ -1,11 +1,11 @@
# IdnaMappingTable.txt
# Date: 2022-05-02, 19:29:26 GMT
# © 2022 Unicode®, Inc.
# Date: 2023-08-10, 22:32:27 GMT
# © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# 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
#
@ -2036,7 +2036,7 @@
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
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
1EA0 ; mapped ; 1EA1 # 1.1 LATIN CAPITAL 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
222F ; mapped ; 222E 222E # 1.1 SURFACE INTEGRAL
2230 ; mapped ; 222E 222E 222E #1.1 VOLUME INTEGRAL
2231..225F ; valid ; ; NV8 # 1.1 CLOCKWISE INTEGRAL..QUESTIONED EQUAL TO
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
2231..22F1 ; valid ; ; NV8 # 1.1 CLOCKWISE INTEGRAL..DOWN RIGHT DIAGONAL ELLIPSIS
22F2..22FF ; valid ; ; NV8 # 3.2 ELEMENT OF WITH LONG HORIZONTAL STROKE..Z NOTATION BAG MEMBERSHIP
2300 ; valid ; ; NV8 # 1.1 DIAMETER SIGN
2301 ; valid ; ; NV8 # 3.0 ELECTRIC ARROW
@ -3273,7 +3269,7 @@
2FD5 ; mapped ; 9FA0 # 3.0 KANGXI RADICAL FLUTE
2FD6..2FEF ; disallowed # NA <reserved-2FD6>..<reserved-2FEF>
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
3001 ; valid ; ; NV8 # 1.1 IDEOGRAPHIC COMMA
3002 ; mapped ; 002E # 1.1 IDEOGRAPHIC FULL STOP
@ -3425,7 +3421,8 @@
31BB..31BF ; valid # 13.0 BOPOMOFO FINAL LETTER G..BOPOMOFO LETTER AH
31C0..31CF ; valid ; ; NV8 # 4.1 CJK STROKE T..CJK STROKE N
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
3200 ; disallowed_STD3_mapped ; 0028 1100 0029 #1.1 PARENTHESIZED HANGUL KIYEOK
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
2CEA2..2CEAF ; disallowed # NA <reserved-2CEA2>..<reserved-2CEAF>
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
2F801 ; mapped ; 4E38 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F801
2F802 ; mapped ; 4E41 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F802

File diff suppressed because it is too large Load Diff

View File

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

View File

@ -1,6 +1,6 @@
# Scripts-15.0.0.txt
# Date: 2022-04-26, 23:15:02 GMT
# © 2022 Unicode®, Inc.
# Scripts-15.1.0.txt
# Date: 2023-07-28, 16:01:07 GMT
# © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
@ -357,7 +357,7 @@
2E5B ; Common # Ps BOTTOM HALF LEFT PARENTHESIS
2E5C ; Common # Pe BOTTOM HALF RIGHT PARENTHESIS
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
3001..3003 ; Common # Po [3] IDEOGRAPHIC COMMA..DITTO MARK
3004 ; Common # So JAPANESE INDUSTRIAL STANDARD SYMBOL
@ -399,6 +399,7 @@
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
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
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
@ -629,7 +630,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
E0001 ; Common # Cf LANGUAGE TAG
E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
# Total code points: 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
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
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
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
# Total code points: 98408
# Total code points: 99030
# ================================================

View File

@ -1,6 +1,6 @@
# SentenceBreakProperty-15.0.0.txt
# Date: 2022-08-05, 22:17:35 GMT
# © 2022 Unicode®, Inc.
# SentenceBreakProperty-15.1.0.txt
# Date: 2023-07-28, 23:34:37 GMT
# © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see 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
0600..0605 ; Format # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE
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
200B ; Format # Cf ZERO WIDTH SPACE
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
FEFF ; Format # Cf ZERO WIDTH NO-BREAK SPACE
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
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
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
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
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
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
# Total code points: 132036
# Total code points: 132658
# ================================================
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
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
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
09E6..09EF ; Numeric # Nd [10] BENGALI DIGIT ZERO..BENGALI 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
10D30..10D39 ; Numeric # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA 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
11136..1113F ; Numeric # Nd [10] CHAKMA DIGIT ZERO..CHAKMA 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
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
166E ; STerm # Po CANADIAN SYLLABICS FULL STOP
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
1809 ; STerm # Po MONGOLIAN MANCHU FULL STOP
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
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
# Date: 2022-02-02, 23:35:52 GMT
# © 2022 Unicode®, Inc.
# SpecialCasing-15.1.0.txt
# Date: 2023-01-05, 20:35:03 GMT
# © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see 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;;;;;
2FFA;IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM LOWER LEFT;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;;;;;
3001;IDEOGRAPHIC COMMA;Po;0;ON;;;;;N;;;;;
3002;IDEOGRAPHIC FULL STOP;Po;0;ON;;;;;N;IDEOGRAPHIC PERIOD;;;;
@ -11705,6 +11709,7 @@
31E1;CJK STROKE HZZZG;So;0;ON;;;;;N;;;;;
31E2;CJK STROKE PG;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;;;;;
31F1;KATAKANA LETTER SMALL SI;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;;;;;
2CEB0;<CJK Ideograph Extension F, First>;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;;;;;
2F801;CJK COMPATIBILITY IDEOGRAPH-2F801;Lo;0;L;4E38;;;;N;;;;;
2F802;CJK COMPATIBILITY IDEOGRAPH-2F802;Lo;0;L;4E41;;;;N;;;;;

View File

@ -1,6 +1,6 @@
# WordBreakProperty-15.0.0.txt
# Date: 2022-04-27, 02:41:26 GMT
# © 2022 Unicode®, Inc.
# WordBreakProperty-15.1.0.txt
# Date: 2023-03-31, 03:19:05 GMT
# © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see 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
0600..0605 ; Format # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE
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
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
@ -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
FEFF ; Format # Cf ZERO WIDTH NO-BREAK SPACE
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
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
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
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
070F ; ALetter # Cf SYRIAC ABBREVIATION MARK
0710 ; ALetter # Lo SYRIAC LETTER ALAPH
0712..072F ; ALetter # Lo [30] SYRIAC LETTER BETH..SYRIAC LETTER PERSIAN DHALATH
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
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
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
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
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
09E6..09EF ; Numeric # Nd [10] BENGALI DIGIT ZERO..BENGALI 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
10D30..10D39 ; Numeric # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA 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
11136..1113F ; Numeric # Nd [10] CHAKMA DIGIT ZERO..CHAKMA 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
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
# Date: 2022-08-02, 00:26:10 GMT
# © 2022 Unicode®, Inc.
# Date: 2023-02-01, 02:22:54 GMT
# © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# 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
#

View File

@ -14,8 +14,8 @@
#include <private/qunicodetables_p.h>
#endif
#define DATA_VERSION_S "15.0"
#define DATA_VERSION_STR "QChar::Unicode_15_0"
#define DATA_VERSION_S "15.1"
#define DATA_VERSION_STR "QChar::Unicode_15_1"
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_14_0, "14.0" }, // UCD Revision 28
{ QChar::Unicode_15_0, "15.0" }, // UCD Revision 30
{ QChar::Unicode_15_1, "15.1" }, // UCD Revision 32
{ QChar::Unicode_Unassigned, 0 }
};
AgeMap *d = ageMap;
@ -528,7 +529,8 @@ static void initSentenceBreak()
static const char *line_break_class_string =
"// 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"
" LineBreak_OP, LineBreak_CL, LineBreak_CP, LineBreak_QU, LineBreak_GL,\n"
" LineBreak_NS, LineBreak_EX, LineBreak_SY, LineBreak_IS, LineBreak_PR,\n"
@ -612,6 +614,11 @@ static void initLineBreak()
{ LineBreak_EB, "EB" },
{ LineBreak_EM, "EM" },
{ LineBreak_ZWJ, "ZWJ" },
{ LineBreak_AL, "AK" },
{ LineBreak_AL, "AP" },
{ LineBreak_AL, "AS" },
{ LineBreak_CM, "VI" },
{ LineBreak_CM, "VF" },
{ LineBreak_Unassigned, 0 }
};
LineBreakList *d = breaks;