17#if U_SHOW_CPLUSPLUS_API
25#ifndef UBRK_TYPEDEF_UBREAK_ITERATOR
26# define UBRK_TYPEDEF_UBREAK_ITERATOR
34#if !UCONFIG_NO_BREAK_ITERATION
112#ifndef U_HIDE_DEPRECATED_API
133#define UBRK_DONE ((int32_t) -1)
296 const UChar * text, int32_t textLength,
299#ifndef U_HIDE_DEPRECATED_API
324 int32_t *pBufferSize,
340#ifndef U_HIDE_DEPRECATED_API
346#define U_BRK_SAFECLONE_BUFFERSIZE 1
359#if U_SHOW_CPLUSPLUS_API
513U_CAPI const char* U_EXPORT2
581U_CAPI const char* U_EXPORT2
642 uint8_t * binaryRules, int32_t rulesCapacity,
"Smart pointer" class, closes a UBreakIterator via ubrk_close().
C++ API: "Smart pointers" for use with and in ICU4C C++ code.
#define U_DEFINE_LOCAL_OPEN_POINTER(LocalPointerClassName, Type, closeFunction)
"Smart pointer" definition macro, deletes objects via the closeFunction.
C API: Parse Error Information.
A UParseError struct is used to returned detailed information about parsing errors.
U_CAPI int32_t ubrk_preceding(UBreakIterator *bi, int32_t offset)
Set the iterator position to the first boundary preceding the specified offset.
UBreakIteratorType
The possible types of text boundaries.
@ UBRK_TITLE
Title Case breaks The iterator created using this type locates title boundaries as described for Unic...
@ UBRK_CHARACTER
Character breaks.
@ UBRK_COUNT
One more than the highest normal UBreakIteratorType value.
@ UBRK_SENTENCE
Sentence breaks.
U_CAPI 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.
U_CAPI int32_t ubrk_previous(UBreakIterator *bi)
Set the iterator position to the boundary preceding the current boundary.
U_CAPI const char * ubrk_getAvailable(int32_t index)
Get a locale for which text breaking information is available.
U_CAPI int32_t ubrk_following(UBreakIterator *bi, int32_t offset)
Advance the iterator to the first boundary following the specified offset.
U_CAPI int32_t ubrk_getBinaryRules(UBreakIterator *bi, uint8_t *binaryRules, int32_t rulesCapacity, UErrorCode *status)
Get a compiled binary version of the rules specifying the behavior of a UBreakIterator.
U_CAPI int32_t ubrk_first(UBreakIterator *bi)
Set the iterator position to zero, the start of the text being scanned.
U_CAPI int32_t ubrk_current(const UBreakIterator *bi)
Determine the most recently-returned text boundary.
U_CAPI int32_t ubrk_getRuleStatus(UBreakIterator *bi)
Return the status from the break rule that determined the most recently returned break position.
U_CAPI 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.
U_CAPI UBreakIterator * ubrk_clone(const UBreakIterator *bi, UErrorCode *status)
Thread safe cloning operation.
U_CAPI void ubrk_setUText(UBreakIterator *bi, UText *text, UErrorCode *status)
Sets an existing iterator to point to a new piece of text.
U_CAPI UBool ubrk_isBoundary(UBreakIterator *bi, int32_t offset)
Returns true if the specified position is a boundary position.
U_CAPI void ubrk_close(UBreakIterator *bi)
Close a UBreakIterator.
ULineBreakTag
Enum constants for the line break tags returned by getRuleStatus().
@ UBRK_LINE_SOFT
Tag value for soft line breaks, positions at which a line break is acceptable but not required
@ UBRK_LINE_HARD
Tag value for a hard, or mandatory line break
@ UBRK_LINE_HARD_LIMIT
Upper bound for hard line breaks.
@ UBRK_LINE_SOFT_LIMIT
Upper bound for soft line breaks.
U_CAPI int32_t ubrk_next(UBreakIterator *bi)
Advance the iterator to the boundary following the current boundary.
U_CAPI void ubrk_refreshUText(UBreakIterator *bi, UText *text, UErrorCode *status)
Set the subject text string upon which the break iterator is operating without changing any other asp...
U_CAPI int32_t ubrk_last(UBreakIterator *bi)
Set the iterator position to the index immediately beyond the last character in the text being scanne...
U_CAPI 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.
U_CAPI 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.
USentenceBreakTag
Enum constants for the sentence break tags returned by getRuleStatus().
@ UBRK_SENTENCE_TERM_LIMIT
Upper bound for tags for sentences ended by sentence terminators.
@ UBRK_SENTENCE_SEP
Tag value for for sentences that do not contain an ending sentence terminator ('.
@ UBRK_SENTENCE_TERM
Tag value for for sentences ending with a sentence terminator ('.
@ UBRK_SENTENCE_SEP_LIMIT
Upper bound for tags for sentences ended by a separator.
U_CAPI const char * ubrk_getLocaleByType(const UBreakIterator *bi, ULocDataLocaleType type, UErrorCode *status)
Return the locale of the break iterator.
UBreakIterator * ubrk_safeClone(const UBreakIterator *bi, void *stackBuffer, int32_t *pBufferSize, UErrorCode *status)
Thread safe cloning operation.
struct UBreakIterator UBreakIterator
Opaque type representing an ICU Break iterator object.
U_CAPI UBreakIterator * ubrk_openBinaryRules(const uint8_t *binaryRules, int32_t rulesLength, const UChar *text, int32_t textLength, UErrorCode *status)
Open a new UBreakIterator for locating text boundaries using precompiled binary rules.
U_CAPI int32_t ubrk_countAvailable(void)
Determine how many locales have text breaking information available.
UWordBreak
Enum constants for the word break tags returned by getRuleStatus().
@ UBRK_WORD_IDEO
Tag value for words containing ideographic characters, lower limit.
@ UBRK_WORD_NUMBER
Tag value for words that appear to be numbers, lower limit.
@ UBRK_WORD_NONE_LIMIT
Upper bound for tags for uncategorized words.
@ UBRK_WORD_LETTER_LIMIT
Tag value for words containing letters, upper limit
@ UBRK_WORD_KANA
Tag value for words containing kana characters, lower limit.
@ UBRK_WORD_KANA_LIMIT
Tag value for words containing kana characters, upper limit.
@ UBRK_WORD_IDEO_LIMIT
Tag value for words containing ideographic characters, upper limit.
@ UBRK_WORD_NONE
Tag value for "words" that do not fit into any of other categories.
@ UBRK_WORD_NUMBER_LIMIT
Tag value for words that appear to be numbers, upper limit.
@ UBRK_WORD_LETTER
Tag value for words that contain letters, excluding hiragana, katakana or ideographic characters,...
C API: Locale ID functionality similar to C++ class Locale.
ULocDataLocaleType
Constants for *_getLocale() Allow user to select whether she wants information on requested,...
#define U_DEPRECATED
This is used to declare a function as a deprecated public ICU C API
int8_t UBool
The ICU boolean type, a signed-byte integer.
#define U_CAPI
This is used to declare a function as a public ICU C API.
char16_t UChar
The base type for UTF-16 code units and pointers.
C API: Abstract Unicode Text API.
Basic definitions for ICU, for both C and C++ APIs.
UErrorCode
Standard ICU4C error code type, a substitute for exceptions.