TextBreakIterator* wordBreakIterator(StringView string)
{
static TextBreakIterator* staticWordBreakIterator = initializeIterator(UBRK_WORD);
if (!staticWordBreakIterator)
return nullptr;
return setTextForIterator(*staticWordBreakIterator, string);
}
TextBreakIterator* sentenceBreakIterator(StringView string)
{
static TextBreakIterator* staticSentenceBreakIterator = initializeIterator(UBRK_SENTENCE);
if (!staticSentenceBreakIterator)
return nullptr;
return setTextForIterator(*staticSentenceBreakIterator, string);
}
NonSharedCharacterBreakIterator::NonSharedCharacterBreakIterator(StringView string)
{
m_iterator = nonSharedCharacterBreakIterator;
bool createdIterator = m_iterator && compareAndSwapNonSharedCharacterBreakIterator(m_iterator, 0);
if (!createdIterator)
m_iterator = initializeIterator(UBRK_CHARACTER);
if (!m_iterator)
return;
m_iterator = setTextForIterator(*m_iterator, string);
}
TextBreakIterator* cursorMovementIterator(StringView string)
{
#if !PLATFORM(IOS)
// This rule set is based on character-break iterator rules of ICU 4.0
// <http://source.icu-project.org/repos/icu/icu/tags/release-4-0/source/data/brkitr/char.txt>.
// The major differences from the original ones are listed below:
// * Replaced '[\p{Grapheme_Cluster_Break = SpacingMark}]' with '[\p{General_Category = Spacing Mark} - $Extend]' for ICU 3.8 or earlier;
// * Removed rules that prevent a cursor from moving after prepend characters (Bug 24342);
// * Added rules that prevent a cursor from moving after virama signs of Indic languages except Tamil (Bug 15790), and;
// * Added rules that prevent a cursor from moving before Japanese half-width katakara voiced marks.
// * Added rules for regional indicator symbols.
static const char* kRules =
"$CR = [\\p{Grapheme_Cluster_Break = CR}];"
"$LF = [\\p{Grapheme_Cluster_Break = LF}];"
"$Control = [\\p{Grapheme_Cluster_Break = Control}];"
"$VoiceMarks = [\\uFF9E\\uFF9F];" // Japanese half-width katakana voiced marks
"$Extend = [\\p{Grapheme_Cluster_Break = Extend} $VoiceMarks - [\\u0E30 \\u0E32 \\u0E45 \\u0EB0 \\u0EB2]];"
"$SpacingMark = [[\\p{General_Category = Spacing Mark}] - $Extend];"
"$L = [\\p{Grapheme_Cluster_Break = L}];"
"$V = [\\p{Grapheme_Cluster_Break = V}];"
"$T = [\\p{Grapheme_Cluster_Break = T}];"
"$LV = [\\p{Grapheme_Cluster_Break = LV}];"
"$LVT = [\\p{Grapheme_Cluster_Break = LVT}];"
"$Hin0 = [\\u0905-\\u0939];" // Devanagari Letter A,...,Ha
"$HinV = \\u094D;" // Devanagari Sign Virama
"$Hin1 = [\\u0915-\\u0939];" // Devanagari Letter Ka,...,Ha
"$Ben0 = [\\u0985-\\u09B9];" // Bengali Letter A,...,Ha
"$BenV = \\u09CD;" // Bengali Sign Virama
"$Ben1 = [\\u0995-\\u09B9];" // Bengali Letter Ka,...,Ha
"$Pan0 = [\\u0A05-\\u0A39];" // Gurmukhi Letter A,...,Ha
"$PanV = \\u0A4D;" // Gurmukhi Sign Virama
"$Pan1 = [\\u0A15-\\u0A39];" // Gurmukhi Letter Ka,...,Ha
"$Guj0 = [\\u0A85-\\u0AB9];" // Gujarati Letter A,...,Ha
"$GujV = \\u0ACD;" // Gujarati Sign Virama
"$Guj1 = [\\u0A95-\\u0AB9];" // Gujarati Letter Ka,...,Ha
"$Ori0 = [\\u0B05-\\u0B39];" // Oriya Letter A,...,Ha
"$OriV = \\u0B4D;" // Oriya Sign Virama
"$Ori1 = [\\u0B15-\\u0B39];" // Oriya Letter Ka,...,Ha
"$Tel0 = [\\u0C05-\\u0C39];" // Telugu Letter A,...,Ha
"$TelV = \\u0C4D;" // Telugu Sign Virama
"$Tel1 = [\\u0C14-\\u0C39];" // Telugu Letter Ka,...,Ha
"$Kan0 = [\\u0C85-\\u0CB9];" // Kannada Letter A,...,Ha
"$KanV = \\u0CCD;" // Kannada Sign Virama
"$Kan1 = [\\u0C95-\\u0CB9];" // Kannada Letter A,...,Ha
"$Mal0 = [\\u0D05-\\u0D39];" // Malayalam Letter A,...,Ha
"$MalV = \\u0D4D;" // Malayalam Sign Virama
"$Mal1 = [\\u0D15-\\u0D39];" // Malayalam Letter A,...,Ha
"$RI = [\\U0001F1E6-\\U0001F1FF];" // Emoji regional indicators
"!!chain;"
"!!forward;"
"$CR $LF;"
"$L ($L | $V | $LV | $LVT);"
"($LV | $V) ($V | $T);"
"($LVT | $T) $T;"
"[^$Control $CR $LF] $Extend;"
"[^$Control $CR $LF] $SpacingMark;"
"$RI $RI / $RI;"
"$RI $RI;"
"$Hin0 $HinV $Hin1;" // Devanagari Virama (forward)
"$Ben0 $BenV $Ben1;" // Bengali Virama (forward)
"$Pan0 $PanV $Pan1;" // Gurmukhi Virama (forward)
"$Guj0 $GujV $Guj1;" // Gujarati Virama (forward)
"$Ori0 $OriV $Ori1;" // Oriya Virama (forward)
"$Tel0 $TelV $Tel1;" // Telugu Virama (forward)
"$Kan0 $KanV $Kan1;" // Kannada Virama (forward)
"$Mal0 $MalV $Mal1;" // Malayalam Virama (forward)
"!!reverse;"
"$LF $CR;"
"($L | $V | $LV | $LVT) $L;"
"($V | $T) ($LV | $V);"
"$T ($LVT | $T);"
"$Extend [^$Control $CR $LF];"
"$SpacingMark [^$Control $CR $LF];"
"$RI $RI / $RI $RI;"
"$RI $RI;"
"$Hin1 $HinV $Hin0;" // Devanagari Virama (backward)
"$Ben1 $BenV $Ben0;" // Bengali Virama (backward)
"$Pan1 $PanV $Pan0;" // Gurmukhi Virama (backward)
"$Guj1 $GujV $Guj0;" // Gujarati Virama (backward)
"$Ori1 $OriV $Ori0;" // Gujarati Virama (backward)
"$Tel1 $TelV $Tel0;" // Telugu Virama (backward)
"$Kan1 $KanV $Kan0;" // Kannada Virama (backward)
"$Mal1 $MalV $Mal0;" // Malayalam Virama (backward)
"!!safe_reverse;"
"!!safe_forward;";
static TextBreakIterator* staticCursorMovementIterator = initializeIteratorWithRules(kRules);
#else // PLATFORM(IOS)
// Use the special Thai character break iterator for all locales
static TextBreakIterator* staticCursorMovementIterator = initializeIterator(UBRK_CHARACTER, "th");
#endif // !PLATFORM(IOS)
if (!staticCursorMovementIterator)
return nullptr;
return setTextForIterator(*staticCursorMovementIterator, string);
}
NonSharedCharacterBreakIterator::NonSharedCharacterBreakIterator(StringView string)
{
if ((m_iterator = getNonSharedCharacterBreakIterator()))
m_iterator = setTextForIterator(*m_iterator, string);
}