19 #ifndef UBRK_TYPEDEF_UBREAK_ITERATOR
20 # define UBRK_TYPEDEF_UBREAK_ITERATOR
28 #if !UCONFIG_NO_BREAK_ITERATION
96 #ifndef U_HIDE_DEPRECATED_API
113 #define UBRK_DONE ((int32_t) -1)
269 #define U_BRK_SAFECLONE_BUFFERSIZE 512
Tag value for for sentences that do not contain an ending sentence terminator ('. ...
UBreakIterator * ubrk_safeClone(const UBreakIterator *bi, void *stackBuffer, int32_t *pBufferSize, UErrorCode *status)
Thread safe cloning operation.
Tag value for words containing kana characters, upper limit.
Tag value for words containing ideographic characters, lower limit.
void ubrk_setUText(UBreakIterator *bi, UText *text, UErrorCode *status)
Sets an existing iterator to point to a new piece of text.
Tag value for words containing letters, upper limit.
int32_t ubrk_next(UBreakIterator *bi)
Determine the text boundary following the current text boundary.
Upper bound for hard line breaks.
Tag value for words containing kana characters, lower limit.
ULineBreakTag
Enum constants for the line break tags returned by getRuleStatus().
UWordBreak
Enum constants for the word break tags returned by getRuleStatus().
USentenceBreakTag
Enum constants for the sentence break tags returned by getRuleStatus().
Tag value for a hard, or mandatory line break.
Upper bound for tags for sentences ended by sentence terminators.
UBreakIteratorType
The possible types of text boundaries.
void UBreakIterator
Opaque type representing an ICU Break iterator object.
Tag value for for sentences ending with a sentence terminator ('.
UBreakIterator * ubrk_open(UBreakIteratorType type, const char *locale, const UChar *text, int32_t textLength, UErrorCode *status)
Open a new UBreakIterator for locating text boundaries for a specified locale.
int32_t ubrk_getRuleStatusVec(UBreakIterator *bi, int32_t *fillInVec, int32_t capacity, UErrorCode *status)
Get the statuses from the break rules that determined the most recently returned break position...
int32_t ubrk_first(UBreakIterator *bi)
Determine the index of the first character in the text being scanned.
int32_t ubrk_preceding(UBreakIterator *bi, int32_t offset)
Determine the text boundary preceding the specified offset.
C API: Abstract Unicode Text API.
void ubrk_setText(UBreakIterator *bi, const UChar *text, int32_t textLength, UErrorCode *status)
Sets an existing iterator to point to a new piece of text.
const char * ubrk_getAvailable(int32_t index)
Get a locale for which text breaking information is available.
Upper bound for tags for uncategorized words.
Tag value for words that appear to be numbers, upper limit.
int32_t ubrk_previous(UBreakIterator *bi)
Determine the text boundary preceding the current text boundary.
Tag value for soft line breaks, positions at which a line break is acceptable but not required...
Upper bound for tags for sentences ended by a separator.
UBreakIterator * ubrk_openRules(const UChar *rules, int32_t rulesLength, const UChar *text, int32_t textLength, UParseError *parseErr, UErrorCode *status)
Open a new UBreakIterator for locating text boundaries using specified breaking rules.
int32_t ubrk_countAvailable(void)
Determine how many locales have text breaking information available.
int32_t ubrk_last(UBreakIterator *bi)
Determine the index immediately beyond the last character in the text being scanned.
uint16_t UChar
Define UChar to be wchar_t if that is 16 bits wide; always assumed to be unsigned.
int32_t ubrk_getRuleStatus(UBreakIterator *bi)
Return the status from the break rule that determined the most recently returned break position...
const char * ubrk_getLocaleByType(const UBreakIterator *bi, ULocDataLocaleType type, UErrorCode *status)
Return the locale of the break iterator.
C API: Parse Error Information.
int32_t ubrk_current(const UBreakIterator *bi)
Determine the most recently-returned text boundary.
Tag value for "words" that do not fit into any of other categories.
UErrorCode
Error code to replace exception handling, so that the code is compatible with all C++ compilers...
ULocDataLocaleType
Constants for *_getLocale() Allow user to select whether she wants information on requested...
A UParseError struct is used to returned detailed information about parsing errors.
Basic definitions for ICU, for both C and C++ APIs.
void ubrk_close(UBreakIterator *bi)
Close a UBreakIterator.
Tag value for words that contain letters, excluding hiragana, katakana or ideographic characters...
Tag value for words that appear to be numbers, lower limit.
Upper bound for soft line breaks.
Title Case breaks The iterator created using this type locates title boundaries as described for Unic...
signed int int32_t
Define 64 bit limits.
UBool ubrk_isBoundary(UBreakIterator *bi, int32_t offset)
Returns true if the specfied position is a boundary position.
int32_t ubrk_following(UBreakIterator *bi, int32_t offset)
Determine the text boundary following the specified offset.
#define U_STABLE
This is used to declare a function as a stable public ICU C API.
Tag value for words containing ideographic characters, upper limit.
int8_t UBool
The ICU boolean type.