AuroraMiddleware/qt5base-lts
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update the Unicode Data and Algorithms up to Unicode 6.2

Browse Source 
Version 6.2 of the Unicode Standard is a special release
dedicated to the early publication of the newly encoded Turkish lira sign.
In addition, there are some significant changes to the Unicode algorithms
for text segmentation and line breaking to improve breaking for emoji symbols.

For more details, see http://www.unicode.org/versions/Unicode6.2.0/

Change-Id: I21cfd4f307e41b41a19d36cce87f7a44c2661bc2
Reviewed-by: Thiago Macieira <thiago.macieira@intel.com>
Reviewed-by: Lars Knoll <lars.knoll@digia.com>
This commit is contained in:
Konstantin Ritt 2012-09-28 01:57:39 +03:00 committed by The Qt Project
parent b9a2a0141f
commit 2672c4fa91
27 changed files with 4993 additions and 4431 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
dist/changes-5.0.0 vendored
View File

@ -336,6 +336,9 @@ General Improvements
'contains(QT_CONFIG,c++11):CONFIG+=c++11'. This will enable C++11 support
only if Qt was built with C++11 support.
- The Unicode Data and Algorithms has been updated to match the
Unicode Standard of version 6.2. For more information see http://www.unicode.org/
Third party components
----------------------
@ -350,7 +353,12 @@ the 3rdparty directory.
QtCore
------
* drop a bogus QChar::NoCategory enum value; the proper QChar::Other_NotAssigned
* [QTBUG-12144], [QTBUG-18360] The QChar methods are now able to handle the full range
of Unicode codepoints defined by the Unicode Standard of version 6.2.
QChar::isPrint() will no longer return a false positives for
the Unicode format characters, surrogates, and private use characters.
* Drop a bogus QChar::NoCategory enum value; the proper QChar::Other_NotAssigned
value is returned for an unassigned codepoints now.
* layoutAboutToBeChanged is no longer emitted by QAbstractItemModel::beginMoveRows.

3
src/corelib/tools/qchar.cpp
View File

@ -182,8 +182,9 @@ QT_BEGIN_NAMESPACE
\value Unicode_5_2 Version 5.2
\value Unicode_6_0 Version 6.0
\value Unicode_6_1 Version 6.1
\value Unicode_6_2 Version 6.2
\value Unicode_Unassigned The value is not assigned to any character
in version 6.1 of Unicode.
in version 6.2 of Unicode.
\sa unicodeVersion(), currentUnicodeVersion()
*/

3
src/corelib/tools/qchar.h
View File

@ -209,7 +209,8 @@ public:
Unicode_5_1,
Unicode_5_2,
Unicode_6_0,
Unicode_6_1
Unicode_6_1,
Unicode_6_2
};
// ****** WHEN ADDING FUNCTIONS, CONSIDER ADDING TO QCharRef TOO

6082
src/corelib/tools/qunicodetables.cpp
View File

File diff suppressed because it is too large Load Diff

13
src/corelib/tools/qunicodetables_p.h
View File

@ -39,7 +39,7 @@
**
****************************************************************************/
/* This file is autogenerated from the Unicode 6.1 database. Do not edit */
/* This file is autogenerated from the Unicode 6.2 database. Do not edit */
//
// W A R N I N G
@ -59,7 +59,7 @@
QT_BEGIN_NAMESPACE
#define UNICODE_DATA_VERSION QChar::Unicode_6_1
#define UNICODE_DATA_VERSION QChar::Unicode_6_2
namespace QUnicodeTables {
@ -202,6 +202,7 @@ enum GraphemeBreakClass {
GraphemeBreak_LF,
GraphemeBreak_Control,
GraphemeBreak_Extend,
GraphemeBreak_RegionalIndicator,
GraphemeBreak_Prepend,
GraphemeBreak_SpacingMark,
GraphemeBreak_L,
@ -217,6 +218,7 @@ enum WordBreakClass {
WordBreak_LF,
WordBreak_Newline,
WordBreak_Extend,
WordBreak_RegionalIndicator,
WordBreak_Katakana,
WordBreak_ALetter,
WordBreak_MidNumLet,
@ -243,7 +245,7 @@ enum SentenceBreakClass {
SentenceBreak_Close
};
// see http://www.unicode.org/reports/tr14/tr14-28.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.
enum LineBreakClass {
LineBreak_OP, LineBreak_CL, LineBreak_CP, LineBreak_QU, LineBreak_GL,
@ -251,8 +253,9 @@ enum LineBreakClass {
LineBreak_PO, LineBreak_NU, LineBreak_AL, LineBreak_HL, LineBreak_ID,
LineBreak_IN, LineBreak_HY, LineBreak_BA, LineBreak_BB, LineBreak_B2,
LineBreak_ZW, LineBreak_CM, LineBreak_WJ, LineBreak_H2, LineBreak_H3,
LineBreak_JL, LineBreak_JV, LineBreak_JT, LineBreak_CB, LineBreak_SA,
LineBreak_SG, LineBreak_SP, LineBreak_CR, LineBreak_LF, LineBreak_BK
LineBreak_JL, LineBreak_JV, LineBreak_JT, LineBreak_RI, LineBreak_CB,
LineBreak_SA, LineBreak_SG, LineBreak_SP, LineBreak_CR, LineBreak_LF,
LineBreak_BK
};
Q_CORE_EXPORT GraphemeBreakClass QT_FASTCALL graphemeBreakClass(uint ucs4);

121
src/corelib/tools/qunicodetools.cpp
View File

@ -56,26 +56,28 @@ namespace QUnicodeTools {
// -----------------------------------------------------------------------------------------------------
//
// The text boundaries determination algorithm. See http://www.unicode.org/reports/tr29/tr29-19.html
// The text boundaries determination algorithm.
// See http://www.unicode.org/reports/tr29/tr29-21.html
//
// -----------------------------------------------------------------------------------------------------
namespace GB {
static const uchar breakTable[QUnicodeTables::GraphemeBreak_LVT + 1][QUnicodeTables::GraphemeBreak_LVT + 1] = {
// Other CR LF Control Extend Prepend S-Mark L V T LV LVT
{ true , true , true , true , false, true , false, true , true , true , true , true }, // Other
{ true , true , false, true , true , true , true , true , true , true , true , true }, // CR
{ true , true , true , true , true , true , true , true , true , true , true , true }, // LF
{ true , true , true , true , true , true , true , true , true , true , true , true }, // Control
{ true , true , true , true , false, true , false, true , true , true , true , true }, // Extend
{ false, true , true , true , false, false, false, false, false, false, false, false }, // Prepend
{ true , true , true , true , false, true , false, true , true , true , true , true }, // SpacingMark
{ true , true , true , true , false, true , false, false, false, true , false, false }, // L
{ true , true , true , true , false, true , false, true , false, false, true , true }, // V
{ true , true , true , true , false, true , false, true , true , false, true , true }, // T
{ true , true , true , true , false, true , false, true , false, false, true , true }, // LV
{ true , true , true , true , false, true , false, true , true , false, true , true }, // LVT
// Other CR LF Control Extend RI Prepend S-Mark L V T LV LVT
{ true , true , true , true , false, true , true , false, true , true , true , true , true }, // Other
{ true , true , false, true , true , true , true , true , true , true , true , true , true }, // CR
{ true , true , true , true , true , true , true , true , true , true , true , true , true }, // LF
{ true , true , true , true , true , true , true , true , true , true , true , true , true }, // Control
{ true , true , true , true , false, true , true , false, true , true , true , true , true }, // Extend
{ true , true , true , true , false, false, true , false, true , true , true , true , true }, // RegionalIndicator
{ false, true , true , true , false, false, false, false, false, false, false, false, false }, // Prepend
{ true , true , true , true , false, true , true , false, true , true , true , true , true }, // SpacingMark
{ true , true , true , true , false, true , true , false, false, false, true , false, false }, // L
{ true , true , true , true , false, true , true , false, true , false, false, true , true }, // V
{ true , true , true , true , false, true , true , false, true , true , false, true , true }, // T
{ true , true , true , true , false, true , true , false, true , false, false, true , true }, // LV
{ true , true , true , true , false, true , true , false, true , true , false, true , true }, // LVT
};
} // namespace GB
@ -116,19 +118,20 @@ enum Action {
};
static const uchar breakTable[QUnicodeTables::WordBreak_ExtendNumLet + 1][QUnicodeTables::WordBreak_ExtendNumLet + 1] = {
// Other CR LF Newline Extend Katakana ALetter MidNumLet MidLetter MidNum Numeric ExtendNumLet
{ Break , Break , Break , Break , NoBreak, Break , Break , Break , Break , Break , Break , Break }, // Other
{ Break , Break , NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break }, // CR
{ Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // LF
{ Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // Newline
{ Break , Break , Break , Break , NoBreak, Break , Break , Break , Break , Break , Break , Break }, // Extend
{ Break , Break , Break , Break , NoBreak, NoBreak, Break , Break , Break , Break , Break , NoBreak }, // Katakana
{ Break , Break , Break , Break , NoBreak, Break , NoBreak, Lookup , Lookup , Break , NoBreak, NoBreak }, // ALetter
{ Break , Break , Break , Break , NoBreak, Break , Break , Break , Break , Break , Break , Break }, // MidNumLet
{ Break , Break , Break , Break , NoBreak, Break , Break , Break , Break , Break , Break , Break }, // MidLetter
{ Break , Break , Break , Break , NoBreak, Break , Break , Break , Break , Break , Break , Break }, // MidNum
{ Break , Break , Break , Break , NoBreak, Break , NoBreak, Lookup , Break , Lookup , NoBreak, NoBreak }, // Numeric
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , NoBreak, NoBreak }, // ExtendNumLet
// Other CR LF Newline Extend RI Katakana ALetter MidNumLet MidLetter MidNum Numeric ExtendNumLet
{ Break , Break , Break , Break , NoBreak, Break , Break , Break , Break , Break , Break , Break , Break }, // Other
{ Break , Break , NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // CR
{ Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // LF
{ Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // Newline
{ Break , Break , Break , Break , NoBreak, Break , Break , Break , Break , Break , Break , Break , Break }, // Extend
{ Break , Break , Break , Break , NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break }, // RegionalIndicator
{ Break , Break , Break , Break , NoBreak, Break , NoBreak, Break , Break , Break , Break , Break , NoBreak }, // Katakana
{ Break , Break , Break , Break , NoBreak, Break , Break , NoBreak, Lookup , Lookup , Break , NoBreak, NoBreak }, // ALetter
{ Break , Break , Break , Break , NoBreak, Break , Break , Break , Break , Break , Break , Break , Break }, // MidNumLet
{ Break , Break , Break , Break , NoBreak, Break , Break , Break , Break , Break , Break , Break , Break }, // MidLetter
{ Break , Break , Break , Break , NoBreak, Break , Break , Break , Break , Break , Break , Break , Break }, // MidNum
{ Break , Break , Break , Break , NoBreak, Break , Break , NoBreak, Lookup , Break , Lookup , NoBreak, NoBreak }, // Numeric
{ Break , Break , Break , Break , NoBreak, Break , NoBreak, NoBreak, Break , Break , Break , NoBreak, NoBreak }, // ExtendNumLet
};
} // namespace WB
@ -311,7 +314,8 @@ static void getSentenceBreaks(const ushort *string, quint32 len, QCharAttributes
// -----------------------------------------------------------------------------------------------------
//
// The line breaking algorithm. See http://www.unicode.org/reports/tr14/tr14-28.html
// The line breaking algorithm.
// See http://www.unicode.org/reports/tr14/tr14-30.html
//
// -----------------------------------------------------------------------------------------------------
@ -401,36 +405,37 @@ enum Action {
};
static const uchar breakTable[QUnicodeTables::LineBreak_CB + 1][QUnicodeTables::LineBreak_CB + 1] = {
/* OP CL CP QU GL NS EX SY IS PR PO NU AL HL ID IN HY BA BB B2 ZW CM WJ H2 H3 JL JV JT CB */
/* OP */ { PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, CP, PB, PB, PB, PB, PB, PB, PB },
/* CL */ { DB, PB, PB, IB, IB, PB, PB, PB, PB, DB, DB, DB, DB, DB, DB, DB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB },
/* CP */ { DB, PB, PB, IB, IB, PB, PB, PB, PB, DB, DB, IB, IB, IB, DB, DB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB },
/* QU */ { PB, PB, PB, IB, IB, IB, PB, PB, PB, IB, IB, IB, IB, IB, IB, IB, IB, IB, IB, IB, PB, CI, PB, IB, IB, IB, IB, IB, IB },
/* GL */ { IB, PB, PB, IB, IB, IB, PB, PB, PB, IB, IB, IB, IB, IB, IB, IB, IB, IB, IB, IB, PB, CI, PB, IB, IB, IB, IB, IB, IB },
/* NS */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, DB, DB, DB, DB, DB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB },
/* EX */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, DB, DB, DB, DB, DB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB },
/* SY */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, DB, DB, DB, DB, DB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB },
/* IS */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, DB, IB, IB, DB, DB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB },
/* PR */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, IB, IB, IB, IB, DB, IB, IB, DB, DB, PB, CI, PB, IB, IB, IB, IB, IB, DB },
/* PO */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, IB, IB, IB, DB, DB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB },
/* NU */ { IB, PB, PB, IB, IB, IB, PB, PB, PB, IB, IB, IB, IB, IB, DB, IB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB },
/* AL */ { IB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, IB, IB, IB, DB, IB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB },
/* HL */ { IB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, IB, IB, IB, DB, IB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB },
/* ID */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, IB, DB, DB, DB, DB, IB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB },
/* IN */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, DB, DB, DB, DB, IB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB },
/* HY */ { DB, PB, PB, IB, DB, IB, PB, PB, PB, DB, DB, IB, DB, DB, DB, DB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB },
/* BA */ { DB, PB, PB, IB, DB, IB, PB, PB, PB, DB, DB, DB, DB, DB, DB, DB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB },
/* BB */ { IB, PB, PB, IB, IB, IB, PB, PB, PB, IB, IB, IB, IB, IB, IB, IB, IB, IB, IB, IB, PB, CI, PB, IB, IB, IB, IB, IB, DB },
/* B2 */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, DB, DB, DB, DB, DB, IB, IB, DB, PB, PB, CI, PB, DB, DB, DB, DB, DB, DB },
/* ZW */ { DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, PB, DB, DB, DB, DB, DB, DB, DB, DB },
/* CM */ { IB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, IB, IB, IB, DB, IB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB },
/* WJ */ { IB, PB, PB, IB, IB, IB, PB, PB, PB, IB, IB, IB, IB, IB, IB, IB, IB, IB, IB, IB, PB, CI, PB, IB, IB, IB, IB, IB, IB },
/* H2 */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, IB, DB, DB, DB, DB, IB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, IB, IB, DB },
/* H3 */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, IB, DB, DB, DB, DB, IB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, IB, DB },
/* JL */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, IB, DB, DB, DB, DB, IB, IB, IB, DB, DB, PB, CI, PB, IB, IB, IB, IB, DB, DB },
/* JV */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, IB, DB, DB, DB, DB, IB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, IB, IB, DB },
/* JT */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, IB, DB, DB, DB, DB, IB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, IB, DB },
/* CB */ { DB, PB, PB, IB, IB, DB, PB, PB, PB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB }
/* OP CL CP QU GL NS EX SY IS PR PO NU AL HL ID IN HY BA BB B2 ZW CM WJ H2 H3 JL JV JT RI CB */
/* OP */ { PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, PB, CP, PB, PB, PB, PB, PB, PB, PB, PB },
/* CL */ { DB, PB, PB, IB, IB, PB, PB, PB, PB, DB, DB, DB, DB, DB, DB, DB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB, DB },
/* CP */ { DB, PB, PB, IB, IB, PB, PB, PB, PB, DB, DB, IB, IB, IB, DB, DB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB, DB },
/* QU */ { PB, PB, PB, IB, IB, IB, PB, PB, PB, IB, IB, IB, IB, IB, IB, IB, IB, IB, IB, IB, PB, CI, PB, IB, IB, IB, IB, IB, IB, IB },
/* GL */ { IB, PB, PB, IB, IB, IB, PB, PB, PB, IB, IB, IB, IB, IB, IB, IB, IB, IB, IB, IB, PB, CI, PB, IB, IB, IB, IB, IB, IB, IB },
/* NS */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, DB, DB, DB, DB, DB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB, DB },
/* EX */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, DB, DB, DB, DB, DB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB, DB },
/* SY */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, DB, DB, DB, DB, DB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB, DB },
/* IS */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, DB, IB, IB, DB, DB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB, DB },
/* PR */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, IB, IB, IB, IB, DB, IB, IB, DB, DB, PB, CI, PB, IB, IB, IB, IB, IB, DB, DB },
/* PO */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, IB, IB, IB, DB, DB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB, DB },
/* NU */ { IB, PB, PB, IB, IB, IB, PB, PB, PB, IB, IB, IB, IB, IB, DB, IB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB, DB },
/* AL */ { IB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, IB, IB, IB, DB, IB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB, DB },
/* HL */ { IB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, IB, IB, IB, DB, IB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB, DB },
/* ID */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, IB, DB, DB, DB, DB, IB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB, DB },
/* IN */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, DB, DB, DB, DB, IB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB, DB },
/* HY */ { DB, PB, PB, IB, DB, IB, PB, PB, PB, DB, DB, IB, DB, DB, DB, DB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB, DB },
/* BA */ { DB, PB, PB, IB, DB, IB, PB, PB, PB, DB, DB, DB, DB, DB, DB, DB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB, DB },
/* BB */ { IB, PB, PB, IB, IB, IB, PB, PB, PB, IB, IB, IB, IB, IB, IB, IB, IB, IB, IB, IB, PB, CI, PB, IB, IB, IB, IB, IB, IB, DB },
/* B2 */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, DB, DB, DB, DB, DB, IB, IB, DB, PB, PB, CI, PB, DB, DB, DB, DB, DB, DB, DB },
/* ZW */ { DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, PB, DB, DB, DB, DB, DB, DB, DB, DB, DB },
/* CM */ { IB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, IB, IB, IB, DB, IB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB, DB },
/* WJ */ { IB, PB, PB, IB, IB, IB, PB, PB, PB, IB, IB, IB, IB, IB, IB, IB, IB, IB, IB, IB, PB, CI, PB, IB, IB, IB, IB, IB, IB, IB },
/* H2 */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, IB, DB, DB, DB, DB, IB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, IB, IB, DB, DB },
/* H3 */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, IB, DB, DB, DB, DB, IB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, IB, DB, DB },
/* JL */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, IB, DB, DB, DB, DB, IB, IB, IB, DB, DB, PB, CI, PB, IB, IB, IB, IB, DB, DB, DB },
/* JV */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, IB, DB, DB, DB, DB, IB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, IB, IB, DB, DB },
/* JT */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, IB, DB, DB, DB, DB, IB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, IB, DB, DB },
/* RI */ { DB, PB, PB, IB, IB, IB, PB, PB, PB, DB, DB, DB, DB, DB, DB, DB, IB, IB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, IB, DB },
/* CB */ { DB, PB, PB, IB, IB, DB, PB, PB, PB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, DB, PB, CI, PB, DB, DB, DB, DB, DB, DB, DB }
};
} // namespace LB

8
tests/auto/corelib/tools/qchar/data/NormalizationTest.txt
View File

@ -1,8 +1,8 @@
# NormalizationTest-6.1.0.txt
# Date: 2011-11-27, 05:10:33 GMT [MD]
# NormalizationTest-6.2.0.txt
# Date: 2012-08-14, 17:54:58 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
#
@ -18428,4 +18428,4 @@ D750 0334 11B5;D750 0334 11B5;1112 1173 0334 11B5;D750 0334 11B5;1112 1173 0334
11131 0334 11127;11131 0334 11127;11131 0334 11127;11131 0334 11127;11131 0334 11127; # (◌𑄱◌̴◌𑄧; ◌𑄱◌̴◌𑄧; ◌𑄱◌̴◌𑄧; ◌𑄱◌̴◌𑄧; ◌𑄱◌̴◌𑄧; ) CHAKMA O MARK, COMBINING TILDE OVERLAY, CHAKMA VOWEL SIGN A
11132 0334 11127;11132 0334 11127;11132 0334 11127;11132 0334 11127;11132 0334 11127; # (◌𑄲◌̴◌𑄧; ◌𑄲◌̴◌𑄧; ◌𑄲◌̴◌𑄧; ◌𑄲◌̴◌𑄧; ◌𑄲◌̴◌𑄧; ) CHAKMA AU MARK, COMBINING TILDE OVERLAY, CHAKMA VOWEL SIGN A
#
# END OF FILE
# EOF

6
tests/auto/corelib/tools/qchar/tst_qchar.cpp
View File

@ -600,6 +600,11 @@ void tst_QChar::unicodeVersion()
QVERIFY(QChar::unicodeVersion((uint)0xa69f) == QChar::Unicode_6_1);
QVERIFY(QChar::unicodeVersion((uint)0x1f600) == QChar::Unicode_6_1);
QVERIFY(QChar(0x20ba).unicodeVersion() == QChar::Unicode_6_2);
QVERIFY(QChar::unicodeVersion((ushort)0x20ba) == QChar::Unicode_6_2);
QVERIFY(QChar::unicodeVersion((uint)0x20ba) == QChar::Unicode_6_2);
QVERIFY(QChar::unicodeVersion((uint)0x20ba) == QChar::Unicode_6_2);
QVERIFY(QChar(0x09ff).unicodeVersion() == QChar::Unicode_Unassigned);
QVERIFY(QChar::unicodeVersion((ushort)0x09ff) == QChar::Unicode_Unassigned);
QVERIFY(QChar::unicodeVersion((uint)0x09ff) == QChar::Unicode_Unassigned);
@ -695,6 +700,7 @@ void tst_QChar::lineBreakClass()
QVERIFY(QUnicodeTables::lineBreakClass(0xe0164u) == QUnicodeTables::LineBreak_CM);
QVERIFY(QUnicodeTables::lineBreakClass(0x2f9a4u) == QUnicodeTables::LineBreak_ID);
QVERIFY(QUnicodeTables::lineBreakClass(0x10000u) == QUnicodeTables::LineBreak_AL);
QVERIFY(QUnicodeTables::lineBreakClass(0x1f1e6u) == QUnicodeTables::LineBreak_RI);
// mapped to AL:
QVERIFY(QUnicodeTables::lineBreakClass(0xfffdu) == QUnicodeTables::LineBreak_AL); // AI -> AL

77
tests/auto/corelib/tools/qtextboundaryfinder/data/GraphemeBreakTest.txt
View File

@ -1,8 +1,8 @@
# GraphemeBreakTest-6.1.0.txt
# Date: 2011-12-07, 17:54:39 GMT [MD]
# GraphemeBreakTest-6.2.0.txt
# Date: 2012-08-22, 12:41:15 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
#
@ -15,7 +15,7 @@
# × wherever there is not.
# <comment> the format can change, but currently it shows:
# - the sample character name
# - (x) the Grapheme_Break property* for the sample character
# - (x) the Grapheme_Cluster_Break property value for the sample character
# - [x] the rule that determines whether there is a break or not
#
# These samples may be extended or changed in the future.
@ -42,6 +42,8 @@
÷ 0020 × 0308 ÷ AC00 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 0020 ÷ AC01 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0020 × 0308 ÷ AC01 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0020 ÷ 1F1E6 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0020 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0020 ÷ 0378 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0020 × 0308 ÷ 0378 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0020 ÷ D800 ÷ # ÷ [0.2] SPACE (Other) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
@ -68,6 +70,8 @@
÷ 000D ÷ 0308 ÷ AC00 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 000D ÷ AC01 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 000D ÷ 0308 ÷ AC01 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 000D ÷ 1F1E6 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 000D ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 000D ÷ 0378 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3]
÷ 000D ÷ 0308 ÷ 0378 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 000D ÷ D800 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <surrogate-D800> (Control) ÷ [0.3]
@ -94,6 +98,8 @@
÷ 000A ÷ 0308 ÷ AC00 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 000A ÷ AC01 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 000A ÷ 0308 ÷ AC01 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 000A ÷ 1F1E6 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 000A ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 000A ÷ 0378 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3]
÷ 000A ÷ 0308 ÷ 0378 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 000A ÷ D800 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <surrogate-D800> (Control) ÷ [0.3]
@ -120,6 +126,8 @@
÷ 0001 ÷ 0308 ÷ AC00 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 0001 ÷ AC01 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0001 ÷ 0308 ÷ AC01 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0001 ÷ 1F1E6 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0001 ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0001 ÷ 0378 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0001 ÷ 0308 ÷ 0378 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0001 ÷ D800 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] <surrogate-D800> (Control) ÷ [0.3]
@ -146,6 +154,8 @@
÷ 0300 × 0308 ÷ AC00 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 0300 ÷ AC01 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0300 × 0308 ÷ AC01 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0300 ÷ 1F1E6 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0300 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0300 ÷ 0378 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0300 × 0308 ÷ 0378 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0300 ÷ D800 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
@ -172,6 +182,8 @@
÷ 0903 × 0308 ÷ AC00 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 0903 ÷ AC01 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0903 × 0308 ÷ AC01 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0903 ÷ 1F1E6 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0903 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0903 ÷ 0378 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0903 × 0308 ÷ 0378 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0903 ÷ D800 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
@ -198,6 +210,8 @@
÷ 1100 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 1100 × AC01 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 1100 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 1100 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 1100 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 1100 ÷ 0378 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 1100 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 1100 ÷ D800 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
@ -224,6 +238,8 @@
÷ 1160 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 1160 ÷ AC01 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 1160 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 1160 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 1160 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 1160 ÷ 0378 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 1160 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 1160 ÷ D800 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
@ -250,6 +266,8 @@
÷ 11A8 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 11A8 ÷ AC01 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 11A8 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 11A8 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 11A8 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 11A8 ÷ 0378 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 11A8 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 11A8 ÷ D800 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
@ -276,6 +294,8 @@
÷ AC00 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ AC00 ÷ AC01 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ AC00 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ AC00 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ AC00 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ AC00 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ AC00 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ AC00 ÷ D800 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
@ -302,10 +322,40 @@
÷ AC01 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ AC01 ÷ AC01 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ AC01 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ AC01 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ AC01 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ AC01 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ AC01 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ AC01 ÷ D800 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ AC01 × 0308 ÷ D800 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 1F1E6 ÷ 0020 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0020 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 1F1E6 ÷ 000D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 000D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
÷ 1F1E6 ÷ 000A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 000A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 1F1E6 ÷ 0001 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0001 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
÷ 1F1E6 × 0300 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 1F1E6 × 0308 × 0300 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3]
÷ 1F1E6 × 0903 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 1F1E6 × 0308 × 0903 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
÷ 1F1E6 ÷ 1100 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 1100 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
÷ 1F1E6 ÷ 1160 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 1160 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
÷ 1F1E6 ÷ 11A8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 11A8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
÷ 1F1E6 ÷ AC00 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ AC00 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 1F1E6 ÷ AC01 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ AC01 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 1F1E6 × 1F1E6 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 1F1E6 ÷ 0378 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0378 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 1F1E6 ÷ D800 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ D800 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
÷ 0378 ÷ 0020 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 0378 × 0308 ÷ 0020 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
÷ 0378 ÷ 000D ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
@ -328,6 +378,8 @@
÷ 0378 × 0308 ÷ AC00 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ 0378 ÷ AC01 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0378 × 0308 ÷ AC01 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ 0378 ÷ 1F1E6 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0378 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0378 ÷ 0378 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0378 × 0308 ÷ 0378 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ 0378 ÷ D800 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
@ -354,8 +406,23 @@
÷ D800 ÷ 0308 ÷ AC00 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
÷ D800 ÷ AC01 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ D800 ÷ 0308 ÷ AC01 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
÷ D800 ÷ 1F1E6 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ D800 ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ D800 ÷ 0378 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3]
÷ D800 ÷ 0308 ÷ 0378 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
÷ D800 ÷ D800 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] <surrogate-D800> (Control) ÷ [0.3]
÷ D800 ÷ 0308 ÷ D800 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3]
# Lines: 338
÷ 0061 ÷ 1F1E6 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
÷ 1F1F7 × 1F1FA ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) ÷ [0.3]
÷ 1F1F7 × 1F1FA × 1F1F8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER S (Regional_Indicator) ÷ [0.3]
÷ 1F1F7 × 1F1FA × 1F1F8 × 1F1EA ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER S (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER E (Regional_Indicator) ÷ [0.3]
÷ 1F1F7 × 1F1FA ÷ 200B ÷ 1F1F8 × 1F1EA ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) ÷ [5.0] ZERO WIDTH SPACE (Control) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER S (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER E (Regional_Indicator) ÷ [0.3]
÷ 1F1E6 × 1F1E7 × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER B (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER C (Regional_Indicator) ÷ [0.3]
÷ 1F1E6 × 200D ÷ 1F1E7 × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] ZERO WIDTH JOINER (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER B (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER C (Regional_Indicator) ÷ [0.3]
÷ 1F1E6 × 1F1E7 × 200D ÷ 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER B (Regional_Indicator) × [9.0] ZERO WIDTH JOINER (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER C (Regional_Indicator) ÷ [0.3]
÷ 0020 × 200D ÷ 0646 ÷ # ÷ [0.2] SPACE (Other) × [9.0] ZERO WIDTH JOINER (Extend) ÷ [999.0] ARABIC LETTER NOON (Other) ÷ [0.3]
÷ 0646 × 200D ÷ 0020 ÷ # ÷ [0.2] ARABIC LETTER NOON (Other) × [9.0] ZERO WIDTH JOINER (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
#
# Lines: 402
#
# EOF

932
tests/auto/corelib/tools/qtextboundaryfinder/data/LineBreakTest.txt
View File

File diff suppressed because it is too large Load Diff

18
tests/auto/corelib/tools/qtextboundaryfinder/data/SentenceBreakTest.txt
View File

@ -1,8 +1,8 @@
# SentenceBreakTest-6.1.0.txt
# Date: 2011-08-23, 19:45:22 GMT [MD]
# SentenceBreakTest-6.2.0.txt
# Date: 2012-08-22, 12:41:18 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
#
@ -15,7 +15,7 @@
# × wherever there is not.
# <comment> the format can change, but currently it shows:
# - the sample character name
# - (x) the Sentence_Break property* for the sample character
# - (x) the Sentence_Break property value for the sample character
# - [x] the rule that determines whether there is a break or not
#
# These samples may be extended or changed in the future.
@ -510,4 +510,12 @@
÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 ÷ 5B83 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B83 (OLetter) × [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) × [12.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.1] IDEOGRAPHIC FULL STOP (STerm) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
÷ 2060 × 5B57 × 2060 × 3002 × 2060 ÷ 5B83 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [12.0] CJK UNIFIED IDEOGRAPH-5B57 (OLetter) × [5.0] WORD JOINER (Format_FE) × [12.0] IDEOGRAPHIC FULL STOP (STerm) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B83 (OLetter) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
# Lines: 490
÷ 1F1E6 × 1F1E7 × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Other) × [12.0] REGIONAL INDICATOR SYMBOL LETTER B (Other) × [12.0] REGIONAL INDICATOR SYMBOL LETTER C (Other) ÷ [0.3]
÷ 1F1E6 × 200D × 1F1E7 × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Other) × [5.0] ZERO WIDTH JOINER (Extend_FE) × [12.0] REGIONAL INDICATOR SYMBOL LETTER B (Other) × [12.0] REGIONAL INDICATOR SYMBOL LETTER C (Other) ÷ [0.3]
÷ 1F1E6 × 1F1E7 × 200D × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Other) × [12.0] REGIONAL INDICATOR SYMBOL LETTER B (Other) × [5.0] ZERO WIDTH JOINER (Extend_FE) × [12.0] REGIONAL INDICATOR SYMBOL LETTER C (Other) ÷ [0.3]
÷ 0020 × 200D × 0646 ÷ # ÷ [0.2] SPACE (Sp) × [5.0] ZERO WIDTH JOINER (Extend_FE) × [12.0] ARABIC LETTER NOON (OLetter) ÷ [0.3]
÷ 0646 × 200D × 0020 ÷ # ÷ [0.2] ARABIC LETTER NOON (OLetter) × [5.0] ZERO WIDTH JOINER (Extend_FE) × [12.0] SPACE (Sp) ÷ [0.3]
#
# Lines: 495
#
# EOF

113
tests/auto/corelib/tools/qtextboundaryfinder/data/WordBreakTest.txt
View File

@ -1,8 +1,8 @@
# WordBreakTest-6.1.0.txt
# Date: 2011-12-07, 23:28:40 GMT [MD]
# WordBreakTest-6.2.0.txt
# Date: 2012-08-22, 12:41:18 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
#
@ -15,7 +15,7 @@
# × wherever there is not.
# <comment> the format can change, but currently it shows:
# - the sample character name
# - (x) the Word_Break property* for the sample character
# - (x) the Word_Break property value for the sample character
# - [x] the rule that determines whether there is a break or not
#
# These samples may be extended or changed in the future.
@ -42,6 +42,8 @@
÷ 0001 × 0308 ÷ 0030 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 0001 ÷ 005F ÷ # ÷ [0.2] <START OF HEADING> (Other) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0001 × 0308 ÷ 005F ÷ # ÷ [0.2] <START OF HEADING> (Other) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0001 ÷ 1F1E6 ÷ # ÷ [0.2] <START OF HEADING> (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0001 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0001 × 00AD ÷ # ÷ [0.2] <START OF HEADING> (Other) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0001 × 0308 × 00AD ÷ # ÷ [0.2] <START OF HEADING> (Other) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0001 × 0300 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -86,6 +88,8 @@
÷ 000D ÷ 0308 ÷ 0030 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 000D ÷ 005F ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [3.1] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 000D ÷ 0308 ÷ 005F ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 000D ÷ 1F1E6 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [3.1] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 000D ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 000D ÷ 00AD ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [3.1] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 000D ÷ 0308 × 00AD ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 000D ÷ 0300 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [3.1] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -130,6 +134,8 @@
÷ 000A ÷ 0308 ÷ 0030 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 000A ÷ 005F ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [3.1] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 000A ÷ 0308 ÷ 005F ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 000A ÷ 1F1E6 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [3.1] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 000A ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 000A ÷ 00AD ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [3.1] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 000A ÷ 0308 × 00AD ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 000A ÷ 0300 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [3.1] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -174,6 +180,8 @@
÷ 000B ÷ 0308 ÷ 0030 ÷ # ÷ [0.2] <LINE TABULATION> (Newline) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 000B ÷ 005F ÷ # ÷ [0.2] <LINE TABULATION> (Newline) ÷ [3.1] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 000B ÷ 0308 ÷ 005F ÷ # ÷ [0.2] <LINE TABULATION> (Newline) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 000B ÷ 1F1E6 ÷ # ÷ [0.2] <LINE TABULATION> (Newline) ÷ [3.1] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 000B ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <LINE TABULATION> (Newline) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 000B ÷ 00AD ÷ # ÷ [0.2] <LINE TABULATION> (Newline) ÷ [3.1] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 000B ÷ 0308 × 00AD ÷ # ÷ [0.2] <LINE TABULATION> (Newline) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 000B ÷ 0300 ÷ # ÷ [0.2] <LINE TABULATION> (Newline) ÷ [3.1] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -218,6 +226,8 @@
÷ 3031 × 0308 ÷ 0030 ÷ # ÷ [0.2] VERTICAL KANA REPEAT MARK (Katakana) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 3031 × 005F ÷ # ÷ [0.2] VERTICAL KANA REPEAT MARK (Katakana) × [13.1] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 3031 × 0308 × 005F ÷ # ÷ [0.2] VERTICAL KANA REPEAT MARK (Katakana) × [4.0] COMBINING DIAERESIS (Extend_FE) × [13.1] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 3031 ÷ 1F1E6 ÷ # ÷ [0.2] VERTICAL KANA REPEAT MARK (Katakana) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 3031 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] VERTICAL KANA REPEAT MARK (Katakana) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 3031 × 00AD ÷ # ÷ [0.2] VERTICAL KANA REPEAT MARK (Katakana) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 3031 × 0308 × 00AD ÷ # ÷ [0.2] VERTICAL KANA REPEAT MARK (Katakana) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 3031 × 0300 ÷ # ÷ [0.2] VERTICAL KANA REPEAT MARK (Katakana) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -262,6 +272,8 @@
÷ 0041 × 0308 × 0030 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) × [4.0] COMBINING DIAERESIS (Extend_FE) × [9.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 0041 × 005F ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) × [13.1] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0041 × 0308 × 005F ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) × [4.0] COMBINING DIAERESIS (Extend_FE) × [13.1] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0041 ÷ 1F1E6 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0041 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0041 × 00AD ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0041 × 0308 × 00AD ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0041 × 0300 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -306,6 +318,8 @@
÷ 003A × 0308 ÷ 0030 ÷ # ÷ [0.2] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 003A ÷ 005F ÷ # ÷ [0.2] COLON (MidLetter) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 003A × 0308 ÷ 005F ÷ # ÷ [0.2] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 003A ÷ 1F1E6 ÷ # ÷ [0.2] COLON (MidLetter) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 003A × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 003A × 00AD ÷ # ÷ [0.2] COLON (MidLetter) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 003A × 0308 × 00AD ÷ # ÷ [0.2] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 003A × 0300 ÷ # ÷ [0.2] COLON (MidLetter) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -350,6 +364,8 @@
÷ 002C × 0308 ÷ 0030 ÷ # ÷ [0.2] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 002C ÷ 005F ÷ # ÷ [0.2] COMMA (MidNum) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 002C × 0308 ÷ 005F ÷ # ÷ [0.2] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 002C ÷ 1F1E6 ÷ # ÷ [0.2] COMMA (MidNum) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 002C × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 002C × 00AD ÷ # ÷ [0.2] COMMA (MidNum) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 002C × 0308 × 00AD ÷ # ÷ [0.2] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 002C × 0300 ÷ # ÷ [0.2] COMMA (MidNum) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -394,6 +410,8 @@
÷ 0027 × 0308 ÷ 0030 ÷ # ÷ [0.2] APOSTROPHE (MidNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 0027 ÷ 005F ÷ # ÷ [0.2] APOSTROPHE (MidNumLet) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0027 × 0308 ÷ 005F ÷ # ÷ [0.2] APOSTROPHE (MidNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0027 ÷ 1F1E6 ÷ # ÷ [0.2] APOSTROPHE (MidNumLet) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0027 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] APOSTROPHE (MidNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0027 × 00AD ÷ # ÷ [0.2] APOSTROPHE (MidNumLet) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0027 × 0308 × 00AD ÷ # ÷ [0.2] APOSTROPHE (MidNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0027 × 0300 ÷ # ÷ [0.2] APOSTROPHE (MidNumLet) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -438,6 +456,8 @@
÷ 0030 × 0308 × 0030 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [4.0] COMBINING DIAERESIS (Extend_FE) × [8.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 0030 × 005F ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [13.1] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0030 × 0308 × 005F ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [4.0] COMBINING DIAERESIS (Extend_FE) × [13.1] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0030 ÷ 1F1E6 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0030 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0030 × 00AD ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0030 × 0308 × 00AD ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0030 × 0300 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -482,6 +502,8 @@
÷ 005F × 0308 × 0030 ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) × [13.2] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 005F × 005F ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) × [13.1] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 005F × 0308 × 005F ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) × [13.1] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 005F ÷ 1F1E6 ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 005F × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 005F × 00AD ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 005F × 0308 × 00AD ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 005F × 0300 ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -504,6 +526,52 @@
÷ 005F × 0308 × 0031 ÷ 002C ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [0.3]
÷ 005F × 0031 ÷ 002E × 2060 ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
÷ 005F × 0308 × 0031 ÷ 002E × 2060 ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
÷ 1F1E6 ÷ 0001 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] <START OF HEADING> (Other) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0001 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] <START OF HEADING> (Other) ÷ [0.3]
÷ 1F1E6 ÷ 000D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [3.2] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 000D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [3.2] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
÷ 1F1E6 ÷ 000A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [3.2] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 000A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [3.2] <LINE FEED (LF)> (LF) ÷ [0.3]
÷ 1F1E6 ÷ 000B ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [3.2] <LINE TABULATION> (Newline) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 000B ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [3.2] <LINE TABULATION> (Newline) ÷ [0.3]
÷ 1F1E6 ÷ 3031 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] VERTICAL KANA REPEAT MARK (Katakana) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 3031 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] VERTICAL KANA REPEAT MARK (Katakana) ÷ [0.3]
÷ 1F1E6 ÷ 0041 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] LATIN CAPITAL LETTER A (ALetter) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0041 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN CAPITAL LETTER A (ALetter) ÷ [0.3]
÷ 1F1E6 ÷ 003A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] COLON (MidLetter) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 003A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] COLON (MidLetter) ÷ [0.3]
÷ 1F1E6 ÷ 002C ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] COMMA (MidNum) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 002C ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] COMMA (MidNum) ÷ [0.3]
÷ 1F1E6 ÷ 0027 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] APOSTROPHE (MidNumLet) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0027 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] APOSTROPHE (MidNumLet) ÷ [0.3]
÷ 1F1E6 ÷ 0030 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0030 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 1F1E6 ÷ 005F ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 005F ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 1F1E6 × 1F1E6 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 1F1E6 × 0308 × 1F1E6 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) × [13.3] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 1F1E6 × 00AD ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 1F1E6 × 0308 × 00AD ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 1F1E6 × 0300 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
÷ 1F1E6 × 0308 × 0300 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
÷ 1F1E6 ÷ 0061 × 2060 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0061 × 2060 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
÷ 1F1E6 ÷ 0061 ÷ 003A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0061 ÷ 003A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [0.3]
÷ 1F1E6 ÷ 0061 ÷ 0027 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (MidNumLet) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0061 ÷ 0027 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (MidNumLet) ÷ [0.3]
÷ 1F1E6 ÷ 0061 ÷ 0027 × 2060 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0061 ÷ 0027 × 2060 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
÷ 1F1E6 ÷ 0061 ÷ 002C ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0061 ÷ 002C ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [0.3]
÷ 1F1E6 ÷ 0031 ÷ 003A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0031 ÷ 003A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [0.3]
÷ 1F1E6 ÷ 0031 ÷ 0027 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (MidNumLet) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0031 ÷ 0027 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (MidNumLet) ÷ [0.3]
÷ 1F1E6 ÷ 0031 ÷ 002C ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0031 ÷ 002C ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [0.3]
÷ 1F1E6 ÷ 0031 ÷ 002E × 2060 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
÷ 1F1E6 × 0308 ÷ 0031 ÷ 002E × 2060 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
÷ 00AD ÷ 0001 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) ÷ [999.0] <START OF HEADING> (Other) ÷ [0.3]
÷ 00AD × 0308 ÷ 0001 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] <START OF HEADING> (Other) ÷ [0.3]
÷ 00AD ÷ 000D ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) ÷ [3.2] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
@ -526,6 +594,8 @@
÷ 00AD × 0308 ÷ 0030 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 00AD ÷ 005F ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 00AD × 0308 ÷ 005F ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 00AD ÷ 1F1E6 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 00AD × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 00AD × 00AD ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 00AD × 0308 × 00AD ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 00AD × 0300 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -570,6 +640,8 @@
÷ 0300 × 0308 ÷ 0030 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 0300 ÷ 005F ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0300 × 0308 ÷ 005F ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0300 ÷ 1F1E6 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0300 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0300 × 00AD ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0300 × 0308 × 00AD ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0300 × 0300 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -614,6 +686,8 @@
÷ 0061 × 2060 × 0308 × 0030 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) × [9.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 0061 × 2060 × 005F ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) × [13.1] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0061 × 2060 × 0308 × 005F ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) × [13.1] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0061 × 2060 ÷ 1F1E6 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0061 × 2060 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0061 × 2060 × 00AD ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0061 × 2060 × 0308 × 00AD ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0061 × 2060 × 0300 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -658,6 +732,8 @@
÷ 0061 ÷ 003A × 0308 ÷ 0030 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 0061 ÷ 003A ÷ 005F ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0061 ÷ 003A × 0308 ÷ 005F ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0061 ÷ 003A ÷ 1F1E6 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0061 ÷ 003A × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0061 ÷ 003A × 00AD ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0061 ÷ 003A × 0308 × 00AD ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0061 ÷ 003A × 0300 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -702,6 +778,8 @@
÷ 0061 ÷ 0027 × 0308 ÷ 0030 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 0061 ÷ 0027 ÷ 005F ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (MidNumLet) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0061 ÷ 0027 × 0308 ÷ 005F ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0061 ÷ 0027 ÷ 1F1E6 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (MidNumLet) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0061 ÷ 0027 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0061 ÷ 0027 × 00AD ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0061 ÷ 0027 × 0308 × 00AD ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0061 ÷ 0027 × 0300 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -746,6 +824,8 @@
÷ 0061 ÷ 0027 × 2060 × 0308 ÷ 0030 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 0061 ÷ 0027 × 2060 ÷ 005F ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0061 ÷ 0027 × 2060 × 0308 ÷ 005F ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0061 ÷ 0027 × 2060 ÷ 1F1E6 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0061 ÷ 0027 × 2060 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0061 ÷ 0027 × 2060 × 00AD ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0061 ÷ 0027 × 2060 × 0308 × 00AD ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0061 ÷ 0027 × 2060 × 0300 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -790,6 +870,8 @@
÷ 0061 ÷ 002C × 0308 ÷ 0030 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 0061 ÷ 002C ÷ 005F ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0061 ÷ 002C × 0308 ÷ 005F ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0061 ÷ 002C ÷ 1F1E6 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0061 ÷ 002C × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0061 ÷ 002C × 00AD ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0061 ÷ 002C × 0308 × 00AD ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0061 ÷ 002C × 0300 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -834,6 +916,8 @@
÷ 0031 ÷ 003A × 0308 ÷ 0030 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 0031 ÷ 003A ÷ 005F ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0031 ÷ 003A × 0308 ÷ 005F ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0031 ÷ 003A ÷ 1F1E6 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0031 ÷ 003A × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0031 ÷ 003A × 00AD ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0031 ÷ 003A × 0308 × 00AD ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0031 ÷ 003A × 0300 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -878,6 +962,8 @@
÷ 0031 × 0027 × 0308 × 0030 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [12.0] APOSTROPHE (MidNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) × [11.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 0031 ÷ 0027 ÷ 005F ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (MidNumLet) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0031 ÷ 0027 × 0308 ÷ 005F ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0031 ÷ 0027 ÷ 1F1E6 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (MidNumLet) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0031 ÷ 0027 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0031 ÷ 0027 × 00AD ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0031 ÷ 0027 × 0308 × 00AD ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0031 ÷ 0027 × 0300 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (MidNumLet) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -922,6 +1008,8 @@
÷ 0031 × 002C × 0308 × 0030 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [12.0] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) × [11.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 0031 ÷ 002C ÷ 005F ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0031 ÷ 002C × 0308 ÷ 005F ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0031 ÷ 002C ÷ 1F1E6 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0031 ÷ 002C × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0031 ÷ 002C × 00AD ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0031 ÷ 002C × 0308 × 00AD ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0031 ÷ 002C × 0300 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -966,6 +1054,8 @@
÷ 0031 × 002E × 2060 × 0308 × 0030 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [12.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) × [11.0] DIGIT ZERO (Numeric) ÷ [0.3]
÷ 0031 ÷ 002E × 2060 ÷ 005F ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0031 ÷ 002E × 2060 × 0308 ÷ 005F ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
÷ 0031 ÷ 002E × 2060 ÷ 1F1E6 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0031 ÷ 002E × 2060 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3]
÷ 0031 ÷ 002E × 2060 × 00AD ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0031 ÷ 002E × 2060 × 0308 × 00AD ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
÷ 0031 ÷ 002E × 2060 × 0300 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
@ -998,4 +1088,17 @@
÷ 2060 ÷ 0061 × 2060 × 0062 × 2060 × 00AD × 2060 × 0062 × 2060 × 0079 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) × [5.0] LATIN SMALL LETTER B (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] SOFT HYPHEN (Format_FE) × [4.0] WORD JOINER (Format_FE) × [5.0] LATIN SMALL LETTER B (ALetter) × [4.0] WORD JOINER (Format_FE) × [5.0] LATIN SMALL LETTER Y (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
÷ 2060 ÷ 0061 × 2060 ÷ 0024 × 2060 ÷ 002D × 2060 ÷ 0033 × 2060 × 0034 × 2060 × 002C × 2060 × 0035 × 2060 × 0036 × 2060 × 0037 × 2060 × 002E × 2060 × 0031 × 2060 × 0034 × 2060 ÷ 0025 × 2060 ÷ 0062 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] DOLLAR SIGN (Other) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] HYPHEN-MINUS (Other) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] DIGIT THREE (Numeric) × [4.0] WORD JOINER (Format_FE) × [8.0] DIGIT FOUR (Numeric) × [4.0] WORD JOINER (Format_FE) × [12.0] COMMA (MidNum) × [4.0] WORD JOINER (Format_FE) × [11.0] DIGIT FIVE (Numeric) × [4.0] WORD JOINER (Format_FE) × [8.0] DIGIT SIX (Numeric) × [4.0] WORD JOINER (Format_FE) × [8.0] DIGIT SEVEN (Numeric) × [4.0] WORD JOINER (Format_FE) × [12.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [11.0] DIGIT ONE (Numeric) × [4.0] WORD JOINER (Format_FE) × [8.0] DIGIT FOUR (Numeric) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] PERCENT SIGN (Other) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] LATIN SMALL LETTER B (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
÷ 2060 ÷ 0033 × 2060 × 0061 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) ÷ [999.0] DIGIT THREE (Numeric) × [4.0] WORD JOINER (Format_FE) × [10.0] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
# Lines: 978
÷ 0061 ÷ 1F1E6 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] LATIN SMALL LETTER B (ALetter) ÷ [0.3]
÷ 1F1F7 × 1F1FA ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) ÷ [0.3]
÷ 1F1F7 × 1F1FA × 1F1F8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER S (Regional_Indicator) ÷ [0.3]
÷ 1F1F7 × 1F1FA × 1F1F8 × 1F1EA ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER S (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER E (Regional_Indicator) ÷ [0.3]
÷ 1F1F7 × 1F1FA ÷ 200B ÷ 1F1F8 × 1F1EA ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) ÷ [999.0] ZERO WIDTH SPACE (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER S (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER E (Regional_Indicator) ÷ [0.3]
÷ 1F1E6 × 1F1E7 × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER B (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER C (Regional_Indicator) ÷ [0.3]
÷ 1F1E6 × 200D × 1F1E7 × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [4.0] ZERO WIDTH JOINER (Extend_FE) × [13.3] REGIONAL INDICATOR SYMBOL LETTER B (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER C (Regional_Indicator) ÷ [0.3]
÷ 1F1E6 × 1F1E7 × 200D × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [13.3] REGIONAL INDICATOR SYMBOL LETTER B (Regional_Indicator) × [4.0] ZERO WIDTH JOINER (Extend_FE) × [13.3] REGIONAL INDICATOR SYMBOL LETTER C (Regional_Indicator) ÷ [0.3]
÷ 0020 × 200D ÷ 0646 ÷ # ÷ [0.2] SPACE (Other) × [4.0] ZERO WIDTH JOINER (Extend_FE) ÷ [999.0] ARABIC LETTER NOON (ALetter) ÷ [0.3]
÷ 0646 × 200D ÷ 0020 ÷ # ÷ [0.2] ARABIC LETTER NOON (ALetter) × [4.0] ZERO WIDTH JOINER (Extend_FE) ÷ [999.0] SPACE (Other) ÷ [0.3]
#
# Lines: 1078
#
# EOF

10
util/unicode/data/ArabicShaping.txt
View File

@ -1,20 +1,20 @@
# ArabicShaping-6.1.0.txt
# Date: 2011-04-15, 23:16:00 GMT [KW]
# ArabicShaping-6.2.0.txt
# Date: 2012-05-15, 21:05:00 GMT [KW]
#
# This file is a normative contributory data file in the
# Unicode Character Database.
#
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# This file defines the Joining_Type and Joining_Group
# property values for Arabic, Syriac, N'Ko, and Mandaic
# positional shaping, repeating in machine readable form the
# information exemplified in Tables 8-3, 8-8, 8-9, 8-10, 8-13, 8-14,
# 8-15, 13-5, 14-5, and 14-6 of The Unicode Standard, Version 6.1.
# 8-15, 13-5, 14-5, and 14-6 of The Unicode Standard, Version 6.2.
#
# See sections 8.2, 8.3, 13.5, and 14.12 of The Unicode Standard,
# Version 6.1 for more information.
# Version 6.2 for more information.
#
# Each line contains four fields, separated by a semicolon.
#

21
util/unicode/data/BidiMirroring.txt
View File

@ -1,19 +1,19 @@
# BidiMirroring-6.1.0.txt
# Date: 2011-12-20, 19:31:00 GMT [KW, LI]
# BidiMirroring-6.2.0.txt
# Date: 2012-05-15, 24:19:00 GMT [KW, LI]
#
# Bidi_Mirroring_Glyph Property
#
# This file is an informative contributory data file in the
# Unicode Character Database.
#
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# This data file lists characters that have the Bidi_Mirrored=Yes property
# 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 6.1.0.
# The repertoire covered by the file is Unicode 6.2.0.
#
# The file contains a list of lines with mappings from one code point
# to another one for character-based mirroring.
@ -30,16 +30,8 @@
# characters exist with mirrored glyphs, are
# listed as comments at the end of the file.
#
# Note: (2011-12-19) There is an inconsistency between the
# following statement about the default value
# of the Bidi_Mirroring_Glyph property and the
# value of the @missing line for Bidi_Mirroring_Glyph in
# PropertyValueAliases.txt. This inconsistency was discovered too
# late in the release process to be resolved by
# the UTC. The inconsistency will be resolved in a future revision.
#
# Formally, the default value of the Bidi_Mirroring_Glyph property
# for each code point is the code point itself, unless a mapping to
# for each code point is <none>, unless a mapping to
# some other character is specified in this data file. When a code
# point has the default value for the Bidi_Mirroring_Glyph property,
# that means that no other character exists whose glyph is suitable
@ -50,12 +42,13 @@
#
# This file was originally created by Markus Scherer.
# Extended for Unicode 3.2, 4.0, 4.1, 5.0, 5.1, 5.2, and 6.0 by Ken Whistler,
# and for Unicode 6.1 by Ken Whistler and Laurentiu Iancu.
# and for Unicode 6.1 and 6.2 by Ken Whistler and Laurentiu Iancu.
#
# ############################################################
#
# Property: Bidi_Mirroring_Glyph
#
# @missing: 0000..10FFFF; <none>
0028; 0029 # LEFT PARENTHESIS
0029; 0028 # RIGHT PARENTHESIS

6
util/unicode/data/Blocks.txt
View File

@ -1,8 +1,8 @@
# Blocks-6.1.0.txt
# Date: 2011-06-14, 18:26:00 GMT [KW, LI]
# Blocks-6.2.0.txt
# Date: 2012-05-14, 22:42:00 GMT [KW, LI]
#
# Unicode Character Database
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
#

8
util/unicode/data/CaseFolding.txt
View File

@ -1,8 +1,8 @@
# CaseFolding-6.1.0.txt
# Date: 2011-07-25, 21:21:56 GMT [MD]
# CaseFolding-6.2.0.txt
# Date: 2012-08-14, 17:54:49 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
#
@ -1222,3 +1222,5 @@ FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z
10425; C; 1044D; # DESERET CAPITAL LETTER ENG
10426; C; 1044E; # DESERET CAPITAL LETTER OI
10427; C; 1044F; # DESERET CAPITAL LETTER EW
#
# EOF

14
util/unicode/data/DerivedAge.txt
View File

@ -1,5 +1,5 @@
# DerivedAge-6.1.0.txt
# Date: 2012-01-20, 21:47:00 GMT [MD, KW]
# DerivedAge-6.2.0.txt
# Date: 2012-09-20, 21:30:39 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2012 Unicode, Inc.
@ -1294,4 +1294,14 @@ FA2E..FA2F ; 6.1 # [2] CJK COMPATIBILITY IDEOGRAPH-FA2E..CJK COMPATIBILITY
# Total code points: 732
# ================================================
# Age=V6_2
# Newly assigned in Unicode 6.2.0 (September, 2012)
20BA ; 6.2 # TURKISH LIRA SIGN
# Total code points: 1
# EOF

6
util/unicode/data/DerivedNormalizationProps.txt
View File

@ -1,8 +1,8 @@
# DerivedNormalizationProps-6.1.0.txt
# Date: 2011-07-26, 04:18:07 GMT [MD]
# DerivedNormalizationProps-6.2.0.txt
# Date: 2012-05-23, 20:34:48 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/

12
util/unicode/data/GraphemeBreakProperty.txt
View File

@ -1,8 +1,8 @@
# GraphemeBreakProperty-6.1.0.txt
# Date: 2011-12-05, 16:44:15 GMT [MD]
# GraphemeBreakProperty-6.2.0.txt
# Date: 2012-08-13, 19:12:02 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
@ -308,6 +308,12 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# ================================================
1F1E6..1F1FF ; Regional_Indicator # So [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z
# Total code points: 26
# ================================================
0903 ; SpacingMark # Mc DEVANAGARI SIGN VISARGA
093B ; SpacingMark # Mc DEVANAGARI VOWEL SIGN OOE
093E..0940 ; SpacingMark # Mc [3] DEVANAGARI VOWEL SIGN AA..DEVANAGARI VOWEL SIGN II

1875
util/unicode/data/LineBreak.txt
View File

File diff suppressed because it is too large Load Diff

8
util/unicode/data/NormalizationCorrections.txt
View File

@ -1,10 +1,10 @@
# NormalizationCorrections-6.1.0.txt
# Date: 2011-06-23, 00:46:00 GMT [KW, LI]
# NormalizationCorrections-6.2.0.txt
# Date: 2012-05-15, 22:25:00 GMT [KW, LI]
#
# This file is a normative contributory data file in the
# Unicode Character Database.
#
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# The normalization stability policy of the Unicode Consortium
@ -46,3 +46,5 @@ F951;96FB;964B;3.2.0 # Corrigendum 3
2F91F;43AB;243AB;4.0.0 # Corrigendum 4
2F95F;7AAE;7AEE;4.0.0 # Corrigendum 4
2F9BF;4D57;45D7;4.0.0 # Corrigendum 4
# EOF

17
util/unicode/data/Scripts.txt
View File

@ -1,8 +1,8 @@
# Scripts-6.1.0.txt
# Date: 2011-11-27, 05:10:50 GMT [MD]
# Scripts-6.2.0.txt
# Date: 2012-06-04, 17:21:29 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
@ -146,7 +146,7 @@
208A..208C ; Common # Sm [3] SUBSCRIPT PLUS SIGN..SUBSCRIPT EQUALS SIGN
208D ; Common # Ps SUBSCRIPT LEFT PARENTHESIS
208E ; Common # Pe SUBSCRIPT RIGHT PARENTHESIS
20A0..20B9 ; Common # Sc [26] EURO-CURRENCY SIGN..INDIAN RUPEE SIGN
20A0..20BA ; Common # Sc [27] EURO-CURRENCY SIGN..TURKISH LIRA SIGN
2100..2101 ; Common # So [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT
2102 ; Common # L& DOUBLE-STRUCK CAPITAL C
2103..2106 ; Common # So [4] DEGREE CELSIUS..CADA UNA
@ -576,7 +576,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
E0001 ; Common # Cf LANGUAGE TAG
E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
# Total code points: 6412
# Total code points: 6413
# ================================================
@ -760,7 +760,7 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU
061E ; Arabic # Po ARABIC TRIPLE DOT PUNCTUATION MARK
0620..063F ; Arabic # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE
0641..064A ; Arabic # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH
0656..065E ; Arabic # Mn [9] ARABIC SUBSCRIPT ALEF..ARABIC FATHA WITH TWO DOTS
0656..065F ; Arabic # Mn [10] ARABIC SUBSCRIPT ALEF..ARABIC WAVY HAMZA BELOW
066A..066D ; Arabic # Po [4] ARABIC PERCENT SIGN..ARABIC FIVE POINTED STAR
066E..066F ; Arabic # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF
0671..06D3 ; Arabic # Lo [99] ARABIC LETTER ALEF WASLA..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE
@ -827,7 +827,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
1EEAB..1EEBB ; Arabic # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
1EEF0..1EEF1 ; Arabic # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL
# Total code points: 1234
# Total code points: 1235
# ================================================
@ -1477,7 +1477,6 @@ A490..A4C6 ; Yi # So [55] YI RADICAL QOT..YI RADICAL KE
0300..036F ; Inherited # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X
0485..0486 ; Inherited # Mn [2] COMBINING CYRILLIC DASIA PNEUMATA..COMBINING CYRILLIC PSILI PNEUMATA
064B..0655 ; Inherited # Mn [11] ARABIC FATHATAN..ARABIC HAMZA BELOW
065F ; Inherited # Mn ARABIC WAVY HAMZA BELOW
0670 ; Inherited # Mn ARABIC LETTER SUPERSCRIPT ALEF
0951..0952 ; Inherited # Mn [2] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI STRESS SIGN ANUDATTA
1CD0..1CD2 ; Inherited # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA
@ -1504,7 +1503,7 @@ FE20..FE26 ; Inherited # Mn [7] COMBINING LIGATURE LEFT HALF..COMBINING CON
1D1AA..1D1AD ; Inherited # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# Total code points: 524
# Total code points: 523
# ================================================

6
util/unicode/data/SentenceBreakProperty.txt
View File

@ -1,8 +1,8 @@
# SentenceBreakProperty-6.1.0.txt
# Date: 2011-11-27, 05:10:50 GMT [MD]
# SentenceBreakProperty-6.2.0.txt
# Date: 2012-05-23, 20:35:14 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/

6
util/unicode/data/SpecialCasing.txt
View File

@ -1,8 +1,8 @@
# SpecialCasing-6.1.0.txt
# Date: 2011-11-27, 05:10:51 GMT [MD]
# SpecialCasing-6.2.0.txt
# Date: 2012-05-23, 20:35:15 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
#

9
util/unicode/data/UnicodeData.txt
View File

@ -7190,6 +7190,7 @@
20B7;SPESMILO SIGN;Sc;0;ET;;;;;N;;;;;
20B8;TENGE SIGN;Sc;0;ET;;;;;N;;;;;
20B9;INDIAN RUPEE SIGN;Sc;0;ET;;;;;N;;;;;
20BA;TURKISH LIRA SIGN;Sc;0;ET;;;;;N;;;;;
20D0;COMBINING LEFT HARPOON ABOVE;Mn;230;NSM;;;;;N;NON-SPACING LEFT HARPOON ABOVE;;;;
20D1;COMBINING RIGHT HARPOON ABOVE;Mn;230;NSM;;;;;N;NON-SPACING RIGHT HARPOON ABOVE;;;;
20D2;COMBINING LONG VERTICAL LINE OVERLAY;Mn;1;NSM;;;;;N;NON-SPACING LONG VERTICAL BAR OVERLAY;;;;
@ -18703,8 +18704,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
1242F;CUNEIFORM NUMERIC SIGN THREE SHARU VARIANT FORM;Nl;0;L;;;;3;N;;;;;
12430;CUNEIFORM NUMERIC SIGN FOUR SHARU;Nl;0;L;;;;4;N;;;;;
12431;CUNEIFORM NUMERIC SIGN FIVE SHARU;Nl;0;L;;;;5;N;;;;;
12432;CUNEIFORM NUMERIC SIGN SHAR2 TIMES GAL PLUS DISH;Nl;0;L;;;;;N;;;;;
12433;CUNEIFORM NUMERIC SIGN SHAR2 TIMES GAL PLUS MIN;Nl;0;L;;;;;N;;;;;
12432;CUNEIFORM NUMERIC SIGN SHAR2 TIMES GAL PLUS DISH;Nl;0;L;;;;216000;N;;;;;
12433;CUNEIFORM NUMERIC SIGN SHAR2 TIMES GAL PLUS MIN;Nl;0;L;;;;432000;N;;;;;
12434;CUNEIFORM NUMERIC SIGN ONE BURU;Nl;0;L;;;;1;N;;;;;
12435;CUNEIFORM NUMERIC SIGN TWO BURU;Nl;0;L;;;;2;N;;;;;
12436;CUNEIFORM NUMERIC SIGN THREE BURU;Nl;0;L;;;;3;N;;;;;
@ -18739,8 +18740,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
12453;CUNEIFORM NUMERIC SIGN FOUR BAN2 VARIANT FORM;Nl;0;L;;;;4;N;;;;;
12454;CUNEIFORM NUMERIC SIGN FIVE BAN2;Nl;0;L;;;;5;N;;;;;
12455;CUNEIFORM NUMERIC SIGN FIVE BAN2 VARIANT FORM;Nl;0;L;;;;5;N;;;;;
12456;CUNEIFORM NUMERIC SIGN NIGIDAMIN;Nl;0;L;;;;;N;;;;;
12457;CUNEIFORM NUMERIC SIGN NIGIDAESH;Nl;0;L;;;;;N;;;;;
12456;CUNEIFORM NUMERIC SIGN NIGIDAMIN;Nl;0;L;;;;-1;N;;;;;
12457;CUNEIFORM NUMERIC SIGN NIGIDAESH;Nl;0;L;;;;-1;N;;;;;
12458;CUNEIFORM NUMERIC SIGN ONE ESHE3;Nl;0;L;;;;1;N;;;;;
12459;CUNEIFORM NUMERIC SIGN TWO ESHE3;Nl;0;L;;;;2;N;;;;;
1245A;CUNEIFORM NUMERIC SIGN ONE THIRD DISH;Nl;0;L;;;;1/3;N;;;;;

12
util/unicode/data/WordBreakProperty.txt
View File

@ -1,8 +1,8 @@
# WordBreakProperty-6.1.0.txt
# Date: 2011-11-27, 05:10:51 GMT [MD]
# WordBreakProperty-6.2.0.txt
# Date: 2012-08-13, 19:12:09 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2011 Unicode, Inc.
# Copyright (c) 1991-2012 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
@ -395,6 +395,12 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# ================================================
1F1E6..1F1FF ; Regional_Indicator # So [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z
# Total code points: 26
# ================================================
00AD ; Format # Cf SOFT HYPHEN
0600..0604 ; Format # Cf [5] ARABIC NUMBER SIGN..ARABIC SIGN SAMVAT
06DD ; Format # Cf ARABIC END OF AYAH

26
util/unicode/main.cpp
View File

@ -51,8 +51,8 @@
#include <private/qunicodetables_p.h>
#endif
#define DATA_VERSION_S "6.1"
#define DATA_VERSION_STR "QChar::Unicode_6_1"
#define DATA_VERSION_S "6.2"
#define DATA_VERSION_STR "QChar::Unicode_6_2"
static QHash<QByteArray, QChar::UnicodeVersion> age_map;
@ -76,6 +76,7 @@ static void initAgeMap()
{ QChar::Unicode_5_2, "5.2" },
{ QChar::Unicode_6_0, "6.0" },
{ QChar::Unicode_6_1, "6.1" },
{ QChar::Unicode_6_2, "6.2" },
{ QChar::Unicode_Unassigned, 0 }
};
AgeMap *d = ageMap;
@ -254,6 +255,7 @@ static const char *grapheme_break_class_string =
" GraphemeBreak_LF,\n"
" GraphemeBreak_Control,\n"
" GraphemeBreak_Extend,\n"
" GraphemeBreak_RegionalIndicator,\n"
" GraphemeBreak_Prepend,\n"
" GraphemeBreak_SpacingMark,\n"
" GraphemeBreak_L,\n"
@ -269,6 +271,7 @@ enum GraphemeBreakClass {
GraphemeBreak_LF,
GraphemeBreak_Control,
GraphemeBreak_Extend,
GraphemeBreak_RegionalIndicator,
GraphemeBreak_Prepend,
GraphemeBreak_SpacingMark,
GraphemeBreak_L,
@ -293,6 +296,7 @@ static void initGraphemeBreak()
{ GraphemeBreak_LF, "LF" },
{ GraphemeBreak_Control, "Control" },
{ GraphemeBreak_Extend, "Extend" },
{ GraphemeBreak_RegionalIndicator, "Regional_Indicator" },
{ GraphemeBreak_Prepend, "Prepend" },
{ GraphemeBreak_SpacingMark, "SpacingMark" },
{ GraphemeBreak_L, "L" },
@ -317,6 +321,7 @@ static const char *word_break_class_string =
" WordBreak_LF,\n"
" WordBreak_Newline,\n"
" WordBreak_Extend,\n"
" WordBreak_RegionalIndicator,\n"
" WordBreak_Katakana,\n"
" WordBreak_ALetter,\n"
" WordBreak_MidNumLet,\n"
@ -332,6 +337,7 @@ enum WordBreakClass {
WordBreak_LF,
WordBreak_Newline,
WordBreak_Extend,
WordBreak_RegionalIndicator,
WordBreak_Katakana,
WordBreak_ALetter,
WordBreak_MidNumLet,
@ -357,6 +363,7 @@ static void initWordBreak()
{ WordBreak_Newline, "Newline" },
{ WordBreak_Extend, "Extend" },
{ WordBreak_Extend, "Format" },
{ WordBreak_RegionalIndicator, "Regional_Indicator" },
{ WordBreak_Katakana, "Katakana" },
{ WordBreak_ALetter, "ALetter" },
{ WordBreak_MidNumLet, "MidNumLet" },
@ -445,7 +452,7 @@ static void initSentenceBreak()
static const char *line_break_class_string =
"// see http://www.unicode.org/reports/tr14/tr14-28.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"
"enum LineBreakClass {\n"
" LineBreak_OP, LineBreak_CL, LineBreak_CP, LineBreak_QU, LineBreak_GL,\n"
@ -453,8 +460,9 @@ static const char *line_break_class_string =
" LineBreak_PO, LineBreak_NU, LineBreak_AL, LineBreak_HL, LineBreak_ID,\n"
" LineBreak_IN, LineBreak_HY, LineBreak_BA, LineBreak_BB, LineBreak_B2,\n"
" LineBreak_ZW, LineBreak_CM, LineBreak_WJ, LineBreak_H2, LineBreak_H3,\n"
" LineBreak_JL, LineBreak_JV, LineBreak_JT, LineBreak_CB, LineBreak_SA,\n"
" LineBreak_SG, LineBreak_SP, LineBreak_CR, LineBreak_LF, LineBreak_BK\n"
" LineBreak_JL, LineBreak_JV, LineBreak_JT, LineBreak_RI, LineBreak_CB,\n"
" LineBreak_SA, LineBreak_SG, LineBreak_SP, LineBreak_CR, LineBreak_LF,\n"
" LineBreak_BK\n"
"};\n\n";
enum LineBreakClass {
@ -463,8 +471,9 @@ enum LineBreakClass {
LineBreak_PO, LineBreak_NU, LineBreak_AL, LineBreak_HL, LineBreak_ID,
LineBreak_IN, LineBreak_HY, LineBreak_BA, LineBreak_BB, LineBreak_B2,
LineBreak_ZW, LineBreak_CM, LineBreak_WJ, LineBreak_H2, LineBreak_H3,
LineBreak_JL, LineBreak_JV, LineBreak_JT, LineBreak_CB, LineBreak_SA,
LineBreak_SG, LineBreak_SP, LineBreak_CR, LineBreak_LF, LineBreak_BK
LineBreak_JL, LineBreak_JV, LineBreak_JT, LineBreak_RI, LineBreak_CB,
LineBreak_SA, LineBreak_SG, LineBreak_SP, LineBreak_CR, LineBreak_LF,
LineBreak_BK
, LineBreak_Unassigned
};
@ -518,6 +527,7 @@ static void initLineBreak()
{ LineBreak_JL, "JL" },
{ LineBreak_JV, "JV" },
{ LineBreak_JT, "JT" },
{ LineBreak_RI, "RI" },
{ LineBreak_SA, "SA" },
{ LineBreak_AL, "XX" },
{ LineBreak_Unassigned, 0 }
@ -583,7 +593,7 @@ static const char *methods =
static const int SizeOfPropertiesStruct = 20;
struct PropertyFlags {
bool operator ==(const PropertyFlags &o) {
bool operator==(const PropertyFlags &o) const {
return (combiningClass == o.combiningClass
&& category == o.category
&& direction == o.direction