diff options
author | Konstantin Ritt <ritt.ks@gmail.com> | 2014-04-10 13:50:53 +0300 |
---|---|---|
committer | The Qt Project <gerrit-noreply@qt-project.org> | 2014-04-14 06:43:57 +0200 |
commit | 0ec07b68ad34e135451dd5291732bf73d297ba0c (patch) | |
tree | 33a7cafbe977729a2d97beb70c18853a31203154 /src/corelib/tools | |
parent | ef77c16cb00ef3788e58da8b35cb91eaf2eaa591 (diff) |
Improve the Unicode script itemization implementation
Make it closer to the Unicode specs (UAX#24):
* Common now inherits the preceding character's script, if any;
* In a combining character sequence, if the base character is
of Common script, the entire sequence is treated like if it were
of the first non-Inherited, non-Common script in the sequence.
See http://www.unicode.org/reports/tr24/tr24-21.html for more details.
[ChangeLog][QtGui] Fixed regression in arabic text rendering.
Task-number: QTBUG-28813
Task-number: QTBUG-29930 (related)
Task-number: QTBUG-35836
Change-Id: Id85761965b08ca94c674d5f3613fe58b82b2ce9c
Reviewed-by: Eskil Abrahamsen Blomfeldt <eskil.abrahamsen-blomfeldt@digia.com>
Reviewed-by: Ahmed Saidi <justroftest@gmail.com>
Diffstat (limited to 'src/corelib/tools')
-rw-r--r-- | src/corelib/tools/qunicodetools.cpp | 38 |
1 files changed, 34 insertions, 4 deletions
diff --git a/src/corelib/tools/qunicodetools.cpp b/src/corelib/tools/qunicodetools.cpp index fac795051a..fc36d07a4a 100644 --- a/src/corelib/tools/qunicodetools.cpp +++ b/src/corelib/tools/qunicodetools.cpp @@ -667,7 +667,7 @@ Q_CORE_EXPORT void initCharAttributes(const ushort *string, int length, // ---------------------------------------------------------------------------- // -// The Unicode script property. See http://www.unicode.org/reports/tr24/ (some very old version) +// The Unicode script property. See http://www.unicode.org/reports/tr24/tr24-21.html // // ---------------------------------------------------------------------------- @@ -689,15 +689,36 @@ Q_CORE_EXPORT void initScripts(const ushort *string, int length, uchar *scripts) const QUnicodeTables::Properties *prop = QUnicodeTables::properties(ucs4); - if (Q_LIKELY(prop->script == script || prop->script == QChar::Script_Inherited)) + if (Q_LIKELY(prop->script == script || prop->script <= QChar::Script_Inherited)) continue; // Never break between a combining mark (gc= Mc, Mn or Me) and its base character. // Thus, a combining mark — whatever its script property value is — should inherit // the script property value of its base character. static const int test = (FLAG(QChar::Mark_NonSpacing) | FLAG(QChar::Mark_SpacingCombining) | FLAG(QChar::Mark_Enclosing)); - if (Q_UNLIKELY(FLAG(prop->category) & test)) - continue; + if (Q_UNLIKELY(FLAG(prop->category) & test)) { + // In cases where the base character itself has the Common script property value, + // and it is followed by one or more combining marks with a specific script property value, + // it may be even better for processing to let the base acquire the script property value + // from the first mark. This approach can be generalized by treating all the characters + // of a combining character sequence as having the script property value + // of the first non-Inherited, non-Common character in the sequence if there is one, + // and otherwise treating all the characters as having the Common script property value. + if (Q_LIKELY(script > QChar::Script_Common || prop->script <= QChar::Script_Common)) + continue; + + script = QChar::Script(prop->script); + } + + if (Q_LIKELY(script != QChar::Script_Common)) { + // override preceding Common-s + while (sor > 0 && scripts[sor - 1] == QChar::Script_Common) + --sor; + } else { + // see if we are inheriting preceding run + if (sor > 0) + script = scripts[sor - 1]; + } while (sor < eor) scripts[sor++] = script; @@ -705,6 +726,15 @@ Q_CORE_EXPORT void initScripts(const ushort *string, int length, uchar *scripts) script = prop->script; } eor = length; + if (Q_LIKELY(script != QChar::Script_Common)) { + // override preceding Common-s + while (sor > 0 && scripts[sor - 1] == QChar::Script_Common) + --sor; + } else { + // see if we are inheriting preceding run + if (sor > 0) + script = scripts[sor - 1]; + } while (sor < eor) scripts[sor++] = script; } |