jpayne@69: * Line boundary analysis determines where a text string can be broken jpayne@69: * when line-wrapping. The mechanism correctly handles punctuation and jpayne@69: * hyphenated words. jpayne@69: *
jpayne@69: * Note: The locale keyword "lb" can be used to modify line break
jpayne@69: * behavior according to the CSS level 3 line-break options, see
jpayne@69: *
jpayne@69: * Sentence boundary analysis allows selection with correct
jpayne@69: * interpretation of periods within numbers and abbreviations, and
jpayne@69: * trailing punctuation marks such as quotation marks and parentheses.
jpayne@69: *
jpayne@69: * Note: The locale keyword "ss" can be used to enable use of
jpayne@69: * segmentation suppression data (preventing breaks in English after
jpayne@69: * abbreviations such as "Mr." or "Est.", for example), as follows:
jpayne@69: * "en@ss=standard".
jpayne@69: *
jpayne@69: * Word boundary analysis is used by search and replace functions, as
jpayne@69: * well as within text editing applications that allow the user to
jpayne@69: * select words with a double click. Word selection provides correct
jpayne@69: * interpretation of punctuation marks within and following
jpayne@69: * words. Characters that are not part of a word, such as symbols or
jpayne@69: * punctuation marks, have word-breaks on both sides.
jpayne@69: *
jpayne@69: * Character boundary analysis identifies the boundaries of
jpayne@69: * "Extended Grapheme Clusters", which are groupings of codepoints
jpayne@69: * that should be treated as character-like units for many text operations.
jpayne@69: * Please see Unicode Standard Annex #29, Unicode Text Segmentation,
jpayne@69: * http://www.unicode.org/reports/tr29/ for additional information
jpayne@69: * on grapheme clusters and guidelines on their use.
jpayne@69: *
jpayne@69: * Title boundary analysis locates all positions,
jpayne@69: * typically starts of words, that should be set to Title Case
jpayne@69: * when title casing the text.
jpayne@69: *
jpayne@69: * The text boundary positions are found according to the rules
jpayne@69: * described in Unicode Standard Annex #29, Text Boundaries, and
jpayne@69: * Unicode Standard Annex #14, Line Breaking Properties. These
jpayne@69: * are available at http://www.unicode.org/reports/tr14/ and
jpayne@69: * http://www.unicode.org/reports/tr29/.
jpayne@69: *
jpayne@69: * In addition to the plain C API defined in this header file, an
jpayne@69: * object oriented C++ API with equivalent functionality is defined in the
jpayne@69: * file brkiter.h.
jpayne@69: *
jpayne@69: * Code snippets illustrating the use of the Break Iterator APIs
jpayne@69: * are available in the ICU User Guide,
jpayne@69: * http://icu-project.org/userguide/boundaryAnalysis.html
jpayne@69: * and in the sample program icu/source/samples/break/break.cpp
jpayne@69: */
jpayne@69:
jpayne@69: /** The possible types of text boundaries. @stable ICU 2.0 */
jpayne@69: typedef enum UBreakIteratorType {
jpayne@69: /** Character breaks @stable ICU 2.0 */
jpayne@69: UBRK_CHARACTER = 0,
jpayne@69: /** Word breaks @stable ICU 2.0 */
jpayne@69: UBRK_WORD = 1,
jpayne@69: /** Line breaks @stable ICU 2.0 */
jpayne@69: UBRK_LINE = 2,
jpayne@69: /** Sentence breaks @stable ICU 2.0 */
jpayne@69: UBRK_SENTENCE = 3,
jpayne@69:
jpayne@69: #ifndef U_HIDE_DEPRECATED_API
jpayne@69: /**
jpayne@69: * Title Case breaks
jpayne@69: * The iterator created using this type locates title boundaries as described for
jpayne@69: * Unicode 3.2 only. For Unicode 4.0 and above title boundary iteration,
jpayne@69: * please use Word Boundary iterator.
jpayne@69: *
jpayne@69: * @deprecated ICU 2.8 Use the word break iterator for titlecasing for Unicode 4 and later.
jpayne@69: */
jpayne@69: UBRK_TITLE = 4,
jpayne@69: /**
jpayne@69: * One more than the highest normal UBreakIteratorType value.
jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69: */
jpayne@69: UBRK_COUNT = 5
jpayne@69: #endif // U_HIDE_DEPRECATED_API
jpayne@69: } UBreakIteratorType;
jpayne@69:
jpayne@69: /** Value indicating all text boundaries have been returned.
jpayne@69: * @stable ICU 2.0
jpayne@69: */
jpayne@69: #define UBRK_DONE ((int32_t) -1)
jpayne@69:
jpayne@69:
jpayne@69: /**
jpayne@69: * Enum constants for the word break tags returned by
jpayne@69: * getRuleStatus(). A range of values is defined for each category of
jpayne@69: * word, to allow for further subdivisions of a category in future releases.
jpayne@69: * Applications should check for tag values falling within the range, rather
jpayne@69: * than for single individual values.
jpayne@69: *
jpayne@69: * The numeric values of all of these constants are stable (will not change).
jpayne@69: *
jpayne@69: * @stable ICU 2.2
jpayne@69: */
jpayne@69: typedef enum UWordBreak {
jpayne@69: /** Tag value for "words" that do not fit into any of other categories.
jpayne@69: * Includes spaces and most punctuation. */
jpayne@69: UBRK_WORD_NONE = 0,
jpayne@69: /** Upper bound for tags for uncategorized words. */
jpayne@69: UBRK_WORD_NONE_LIMIT = 100,
jpayne@69: /** Tag value for words that appear to be numbers, lower limit. */
jpayne@69: UBRK_WORD_NUMBER = 100,
jpayne@69: /** Tag value for words that appear to be numbers, upper limit. */
jpayne@69: UBRK_WORD_NUMBER_LIMIT = 200,
jpayne@69: /** Tag value for words that contain letters, excluding
jpayne@69: * hiragana, katakana or ideographic characters, lower limit. */
jpayne@69: UBRK_WORD_LETTER = 200,
jpayne@69: /** Tag value for words containing letters, upper limit */
jpayne@69: UBRK_WORD_LETTER_LIMIT = 300,
jpayne@69: /** Tag value for words containing kana characters, lower limit */
jpayne@69: UBRK_WORD_KANA = 300,
jpayne@69: /** Tag value for words containing kana characters, upper limit */
jpayne@69: UBRK_WORD_KANA_LIMIT = 400,
jpayne@69: /** Tag value for words containing ideographic characters, lower limit */
jpayne@69: UBRK_WORD_IDEO = 400,
jpayne@69: /** Tag value for words containing ideographic characters, upper limit */
jpayne@69: UBRK_WORD_IDEO_LIMIT = 500
jpayne@69: } UWordBreak;
jpayne@69:
jpayne@69: /**
jpayne@69: * Enum constants for the line break tags returned by getRuleStatus().
jpayne@69: * A range of values is defined for each category of
jpayne@69: * word, to allow for further subdivisions of a category in future releases.
jpayne@69: * Applications should check for tag values falling within the range, rather
jpayne@69: * than for single individual values.
jpayne@69: *
jpayne@69: * The numeric values of all of these constants are stable (will not change).
jpayne@69: *
jpayne@69: * @stable ICU 2.8
jpayne@69: */
jpayne@69: typedef enum ULineBreakTag {
jpayne@69: /** Tag value for soft line breaks, positions at which a line break
jpayne@69: * is acceptable but not required */
jpayne@69: UBRK_LINE_SOFT = 0,
jpayne@69: /** Upper bound for soft line breaks. */
jpayne@69: UBRK_LINE_SOFT_LIMIT = 100,
jpayne@69: /** Tag value for a hard, or mandatory line break */
jpayne@69: UBRK_LINE_HARD = 100,
jpayne@69: /** Upper bound for hard line breaks. */
jpayne@69: UBRK_LINE_HARD_LIMIT = 200
jpayne@69: } ULineBreakTag;
jpayne@69:
jpayne@69:
jpayne@69:
jpayne@69: /**
jpayne@69: * Enum constants for the sentence break tags returned by getRuleStatus().
jpayne@69: * A range of values is defined for each category of
jpayne@69: * sentence, to allow for further subdivisions of a category in future releases.
jpayne@69: * Applications should check for tag values falling within the range, rather
jpayne@69: * than for single individual values.
jpayne@69: *
jpayne@69: * The numeric values of all of these constants are stable (will not change).
jpayne@69: *
jpayne@69: * @stable ICU 2.8
jpayne@69: */
jpayne@69: typedef enum USentenceBreakTag {
jpayne@69: /** Tag value for for sentences ending with a sentence terminator
jpayne@69: * ('.', '?', '!', etc.) character, possibly followed by a
jpayne@69: * hard separator (CR, LF, PS, etc.)
jpayne@69: */
jpayne@69: UBRK_SENTENCE_TERM = 0,
jpayne@69: /** Upper bound for tags for sentences ended by sentence terminators. */
jpayne@69: UBRK_SENTENCE_TERM_LIMIT = 100,
jpayne@69: /** Tag value for for sentences that do not contain an ending
jpayne@69: * sentence terminator ('.', '?', '!', etc.) character, but
jpayne@69: * are ended only by a hard separator (CR, LF, PS, etc.) or end of input.
jpayne@69: */
jpayne@69: UBRK_SENTENCE_SEP = 100,
jpayne@69: /** Upper bound for tags for sentences ended by a separator. */
jpayne@69: UBRK_SENTENCE_SEP_LIMIT = 200
jpayne@69: /** Tag value for a hard, or mandatory line break */
jpayne@69: } USentenceBreakTag;
jpayne@69:
jpayne@69:
jpayne@69: /**
jpayne@69: * Open a new UBreakIterator for locating text boundaries for a specified locale.
jpayne@69: * A UBreakIterator may be used for detecting character, line, word,
jpayne@69: * and sentence breaks in text.
jpayne@69: * @param type The type of UBreakIterator to open: one of UBRK_CHARACTER, UBRK_WORD,
jpayne@69: * UBRK_LINE, UBRK_SENTENCE
jpayne@69: * @param locale The locale specifying the text-breaking conventions. Note that
jpayne@69: * locale keys such as "lb" and "ss" may be used to modify text break behavior,
jpayne@69: * see general discussion of BreakIterator C API.
jpayne@69: * @param text The text to be iterated over. May be null, in which case ubrk_setText() is
jpayne@69: * used to specify the text to be iterated.
jpayne@69: * @param textLength The number of characters in text, or -1 if null-terminated.
jpayne@69: * @param status A UErrorCode to receive any errors.
jpayne@69: * @return A UBreakIterator for the specified locale.
jpayne@69: * @see ubrk_openRules
jpayne@69: * @stable ICU 2.0
jpayne@69: */
jpayne@69: U_STABLE UBreakIterator* U_EXPORT2
jpayne@69: ubrk_open(UBreakIteratorType type,
jpayne@69: const char *locale,
jpayne@69: const UChar *text,
jpayne@69: int32_t textLength,
jpayne@69: UErrorCode *status);
jpayne@69:
jpayne@69: /**
jpayne@69: * Open a new UBreakIterator for locating text boundaries using specified breaking rules.
jpayne@69: * The rule syntax is ... (TBD)
jpayne@69: * @param rules A set of rules specifying the text breaking conventions.
jpayne@69: * @param rulesLength The number of characters in rules, or -1 if null-terminated.
jpayne@69: * @param text The text to be iterated over. May be null, in which case ubrk_setText() is
jpayne@69: * used to specify the text to be iterated.
jpayne@69: * @param textLength The number of characters in text, or -1 if null-terminated.
jpayne@69: * @param parseErr Receives position and context information for any syntax errors
jpayne@69: * detected while parsing the rules.
jpayne@69: * @param status A UErrorCode to receive any errors.
jpayne@69: * @return A UBreakIterator for the specified rules.
jpayne@69: * @see ubrk_open
jpayne@69: * @stable ICU 2.2
jpayne@69: */
jpayne@69: U_STABLE UBreakIterator* U_EXPORT2
jpayne@69: ubrk_openRules(const UChar *rules,
jpayne@69: int32_t rulesLength,
jpayne@69: const UChar *text,
jpayne@69: int32_t textLength,
jpayne@69: UParseError *parseErr,
jpayne@69: UErrorCode *status);
jpayne@69:
jpayne@69: /**
jpayne@69: * Open a new UBreakIterator for locating text boundaries using precompiled binary rules.
jpayne@69: * Opening a UBreakIterator this way is substantially faster than using ubrk_openRules.
jpayne@69: * Binary rules may be obtained using ubrk_getBinaryRules. The compiled rules are not
jpayne@69: * compatible across different major versions of ICU, nor across platforms of different
jpayne@69: * endianness or different base character set family (ASCII vs EBCDIC).
jpayne@69: * @param binaryRules A set of compiled binary rules specifying the text breaking
jpayne@69: * conventions. Ownership of the storage containing the compiled
jpayne@69: * rules remains with the caller of this function. The compiled
jpayne@69: * rules must not be modified or deleted during the life of the
jpayne@69: * break iterator.
jpayne@69: * @param rulesLength The length of binaryRules in bytes; must be >= 0.
jpayne@69: * @param text The text to be iterated over. May be null, in which case
jpayne@69: * ubrk_setText() is used to specify the text to be iterated.
jpayne@69: * @param textLength The number of characters in text, or -1 if null-terminated.
jpayne@69: * @param status Pointer to UErrorCode to receive any errors.
jpayne@69: * @return UBreakIterator for the specified rules.
jpayne@69: * @see ubrk_getBinaryRules
jpayne@69: * @stable ICU 59
jpayne@69: */
jpayne@69: U_STABLE UBreakIterator* U_EXPORT2
jpayne@69: ubrk_openBinaryRules(const uint8_t *binaryRules, int32_t rulesLength,
jpayne@69: const UChar * text, int32_t textLength,
jpayne@69: UErrorCode * status);
jpayne@69:
jpayne@69: /**
jpayne@69: * Thread safe cloning operation
jpayne@69: * @param bi iterator to be cloned
jpayne@69: * @param stackBuffer Deprecated functionality as of ICU 52, use NULL.
jpayne@69: * For word break iterators, the possible values are defined in enum UWordBreak.
jpayne@69: * @stable ICU 2.2
jpayne@69: */
jpayne@69: U_STABLE int32_t U_EXPORT2
jpayne@69: ubrk_getRuleStatus(UBreakIterator *bi);
jpayne@69:
jpayne@69: /**
jpayne@69: * Get the statuses from the break rules that determined the most recently
jpayne@69: * returned break position. The values appear in the rule source
jpayne@69: * within brackets, {123}, for example. The default status value for rules
jpayne@69: * that do not explicitly provide one is zero.
jpayne@69: *
jpayne@69: * For word break iterators, the possible values are defined in enum UWordBreak.
jpayne@69: * @param bi The break iterator to use
jpayne@69: * @param fillInVec an array to be filled in with the status values.
jpayne@69: * @param capacity the length of the supplied vector. A length of zero causes
jpayne@69: * the function to return the number of status values, in the
jpayne@69: * normal way, without attempting to store any values.
jpayne@69: * @param status receives error codes.
jpayne@69: * @return The number of rule status values from rules that determined
jpayne@69: * the most recent boundary returned by the break iterator.
jpayne@69: * @stable ICU 3.0
jpayne@69: */
jpayne@69: U_STABLE int32_t U_EXPORT2
jpayne@69: ubrk_getRuleStatusVec(UBreakIterator *bi, int32_t *fillInVec, int32_t capacity, UErrorCode *status);
jpayne@69:
jpayne@69: /**
jpayne@69: * Return the locale of the break iterator. You can choose between the valid and
jpayne@69: * the actual locale.
jpayne@69: * @param bi break iterator
jpayne@69: * @param type locale type (valid or actual)
jpayne@69: * @param status error code
jpayne@69: * @return locale string
jpayne@69: * @stable ICU 2.8
jpayne@69: */
jpayne@69: U_STABLE const char* U_EXPORT2
jpayne@69: ubrk_getLocaleByType(const UBreakIterator *bi, ULocDataLocaleType type, UErrorCode* status);
jpayne@69:
jpayne@69: /**
jpayne@69: * Set the subject text string upon which the break iterator is operating
jpayne@69: * without changing any other aspect of the state.
jpayne@69: * The new and previous text strings must have the same content.
jpayne@69: *
jpayne@69: * This function is intended for use in environments where ICU is operating on
jpayne@69: * strings that may move around in memory. It provides a mechanism for notifying
jpayne@69: * ICU that the string has been relocated, and providing a new UText to access the
jpayne@69: * string in its new position.
jpayne@69: *
jpayne@69: * Note that the break iterator never copies the underlying text
jpayne@69: * of a string being processed, but always operates directly on the original text
jpayne@69: * provided by the user. Refreshing simply drops the references to the old text
jpayne@69: * and replaces them with references to the new.
jpayne@69: *
jpayne@69: * Caution: this function is normally used only by very specialized
jpayne@69: * system-level code. One example use case is with garbage collection
jpayne@69: * that moves the text in memory.
jpayne@69: *
jpayne@69: * @param bi The break iterator.
jpayne@69: * @param text The new (moved) text string.
jpayne@69: * @param status Receives errors detected by this function.
jpayne@69: *
jpayne@69: * @stable ICU 49
jpayne@69: */
jpayne@69: U_STABLE void U_EXPORT2
jpayne@69: ubrk_refreshUText(UBreakIterator *bi,
jpayne@69: UText *text,
jpayne@69: UErrorCode *status);
jpayne@69:
jpayne@69:
jpayne@69: /**
jpayne@69: * Get a compiled binary version of the rules specifying the behavior of a UBreakIterator.
jpayne@69: * The binary rules may be used with ubrk_openBinaryRules to open a new UBreakIterator
jpayne@69: * more quickly than using ubrk_openRules. The compiled rules are not compatible across
jpayne@69: * different major versions of ICU, nor across platforms of different endianness or
jpayne@69: * different base character set family (ASCII vs EBCDIC). Supports preflighting (with
jpayne@69: * binaryRules=NULL and rulesCapacity=0) to get the rules length without copying them to
jpayne@69: * the binaryRules buffer. However, whether preflighting or not, if the actual length
jpayne@69: * is greater than INT32_MAX, then the function returns 0 and sets *status to
jpayne@69: * U_INDEX_OUTOFBOUNDS_ERROR.
jpayne@69:
jpayne@69: * @param bi The break iterator to use.
jpayne@69: * @param binaryRules Buffer to receive the compiled binary rules; set to NULL for
jpayne@69: * preflighting.
jpayne@69: * @param rulesCapacity Capacity (in bytes) of the binaryRules buffer; set to 0 for
jpayne@69: * preflighting. Must be >= 0.
jpayne@69: * @param status Pointer to UErrorCode to receive any errors, such as
jpayne@69: * U_BUFFER_OVERFLOW_ERROR, U_INDEX_OUTOFBOUNDS_ERROR, or
jpayne@69: * U_ILLEGAL_ARGUMENT_ERROR.
jpayne@69: * @return The actual byte length of the binary rules, if <= INT32_MAX;
jpayne@69: * otherwise 0. If not preflighting and this is larger than
jpayne@69: * rulesCapacity, *status will be set to an error.
jpayne@69: * @see ubrk_openBinaryRules
jpayne@69: * @stable ICU 59
jpayne@69: */
jpayne@69: U_STABLE int32_t U_EXPORT2
jpayne@69: ubrk_getBinaryRules(UBreakIterator *bi,
jpayne@69: uint8_t * binaryRules, int32_t rulesCapacity,
jpayne@69: UErrorCode * status);
jpayne@69:
jpayne@69: #endif /* #if !UCONFIG_NO_BREAK_ITERATION */
jpayne@69:
jpayne@69: #endif
jpayne@69: * user allocated space for the new clone. If NULL new memory will be allocated.
jpayne@69: * If buffer is not large enough, new memory will be allocated.
jpayne@69: * Clients can use the U_BRK_SAFECLONE_BUFFERSIZE.
jpayne@69: * @param pBufferSize Deprecated functionality as of ICU 52, use NULL or 1.
jpayne@69: * pointer to size of allocated space.
jpayne@69: * If *pBufferSize == 0, a sufficient size for use in cloning will
jpayne@69: * be returned ('pre-flighting')
jpayne@69: * If *pBufferSize is not enough for a stack-based safe clone,
jpayne@69: * new memory will be allocated.
jpayne@69: * @param status to indicate whether the operation went on smoothly or there were errors
jpayne@69: * An informational status value, U_SAFECLONE_ALLOCATED_ERROR, is used if any allocations were necessary.
jpayne@69: * @return pointer to the new clone
jpayne@69: * @stable ICU 2.0
jpayne@69: */
jpayne@69: U_STABLE UBreakIterator * U_EXPORT2
jpayne@69: ubrk_safeClone(
jpayne@69: const UBreakIterator *bi,
jpayne@69: void *stackBuffer,
jpayne@69: int32_t *pBufferSize,
jpayne@69: UErrorCode *status);
jpayne@69:
jpayne@69: #ifndef U_HIDE_DEPRECATED_API
jpayne@69:
jpayne@69: /**
jpayne@69: * A recommended size (in bytes) for the memory buffer to be passed to ubrk_saveClone().
jpayne@69: * @deprecated ICU 52. Do not rely on ubrk_safeClone() cloning into any provided buffer.
jpayne@69: */
jpayne@69: #define U_BRK_SAFECLONE_BUFFERSIZE 1
jpayne@69:
jpayne@69: #endif /* U_HIDE_DEPRECATED_API */
jpayne@69:
jpayne@69: /**
jpayne@69: * Close a UBreakIterator.
jpayne@69: * Once closed, a UBreakIterator may no longer be used.
jpayne@69: * @param bi The break iterator to close.
jpayne@69: * @stable ICU 2.0
jpayne@69: */
jpayne@69: U_STABLE void U_EXPORT2
jpayne@69: ubrk_close(UBreakIterator *bi);
jpayne@69:
jpayne@69: #if U_SHOW_CPLUSPLUS_API
jpayne@69:
jpayne@69: U_NAMESPACE_BEGIN
jpayne@69:
jpayne@69: /**
jpayne@69: * \class LocalUBreakIteratorPointer
jpayne@69: * "Smart pointer" class, closes a UBreakIterator via ubrk_close().
jpayne@69: * For most methods see the LocalPointerBase base class.
jpayne@69: *
jpayne@69: * @see LocalPointerBase
jpayne@69: * @see LocalPointer
jpayne@69: * @stable ICU 4.4
jpayne@69: */
jpayne@69: U_DEFINE_LOCAL_OPEN_POINTER(LocalUBreakIteratorPointer, UBreakIterator, ubrk_close);
jpayne@69:
jpayne@69: U_NAMESPACE_END
jpayne@69:
jpayne@69: #endif
jpayne@69:
jpayne@69: /**
jpayne@69: * Sets an existing iterator to point to a new piece of text.
jpayne@69: * The break iterator retains a pointer to the supplied text.
jpayne@69: * The caller must not modify or delete the text while the BreakIterator
jpayne@69: * retains the reference.
jpayne@69: *
jpayne@69: * @param bi The iterator to use
jpayne@69: * @param text The text to be set
jpayne@69: * @param textLength The length of the text
jpayne@69: * @param status The error code
jpayne@69: * @stable ICU 2.0
jpayne@69: */
jpayne@69: U_STABLE void U_EXPORT2
jpayne@69: ubrk_setText(UBreakIterator* bi,
jpayne@69: const UChar* text,
jpayne@69: int32_t textLength,
jpayne@69: UErrorCode* status);
jpayne@69:
jpayne@69:
jpayne@69: /**
jpayne@69: * Sets an existing iterator to point to a new piece of text.
jpayne@69: *
jpayne@69: * All index positions returned by break iterator functions are
jpayne@69: * native indices from the UText. For example, when breaking UTF-8
jpayne@69: * encoded text, the break positions returned by \ref ubrk_next, \ref ubrk_previous, etc.
jpayne@69: * will be UTF-8 string indices, not UTF-16 positions.
jpayne@69: *
jpayne@69: * @param bi The iterator to use
jpayne@69: * @param text The text to be set.
jpayne@69: * This function makes a shallow clone of the supplied UText. This means
jpayne@69: * that the caller is free to immediately close or otherwise reuse the
jpayne@69: * UText that was passed as a parameter, but that the underlying text itself
jpayne@69: * must not be altered while being referenced by the break iterator.
jpayne@69: * @param status The error code
jpayne@69: * @stable ICU 3.4
jpayne@69: */
jpayne@69: U_STABLE void U_EXPORT2
jpayne@69: ubrk_setUText(UBreakIterator* bi,
jpayne@69: UText* text,
jpayne@69: UErrorCode* status);
jpayne@69:
jpayne@69:
jpayne@69:
jpayne@69: /**
jpayne@69: * Determine the most recently-returned text boundary.
jpayne@69: *
jpayne@69: * @param bi The break iterator to use.
jpayne@69: * @return The character index most recently returned by \ref ubrk_next, \ref ubrk_previous,
jpayne@69: * \ref ubrk_first, or \ref ubrk_last.
jpayne@69: * @stable ICU 2.0
jpayne@69: */
jpayne@69: U_STABLE int32_t U_EXPORT2
jpayne@69: ubrk_current(const UBreakIterator *bi);
jpayne@69:
jpayne@69: /**
jpayne@69: * Advance the iterator to the boundary following the current boundary.
jpayne@69: *
jpayne@69: * @param bi The break iterator to use.
jpayne@69: * @return The character index of the next text boundary, or UBRK_DONE
jpayne@69: * if all text boundaries have been returned.
jpayne@69: * @see ubrk_previous
jpayne@69: * @stable ICU 2.0
jpayne@69: */
jpayne@69: U_STABLE int32_t U_EXPORT2
jpayne@69: ubrk_next(UBreakIterator *bi);
jpayne@69:
jpayne@69: /**
jpayne@69: * Set the iterator position to the boundary preceding the current boundary.
jpayne@69: *
jpayne@69: * @param bi The break iterator to use.
jpayne@69: * @return The character index of the preceding text boundary, or UBRK_DONE
jpayne@69: * if all text boundaries have been returned.
jpayne@69: * @see ubrk_next
jpayne@69: * @stable ICU 2.0
jpayne@69: */
jpayne@69: U_STABLE int32_t U_EXPORT2
jpayne@69: ubrk_previous(UBreakIterator *bi);
jpayne@69:
jpayne@69: /**
jpayne@69: * Set the iterator position to zero, the start of the text being scanned.
jpayne@69: * @param bi The break iterator to use.
jpayne@69: * @return The new iterator position (zero).
jpayne@69: * @see ubrk_last
jpayne@69: * @stable ICU 2.0
jpayne@69: */
jpayne@69: U_STABLE int32_t U_EXPORT2
jpayne@69: ubrk_first(UBreakIterator *bi);
jpayne@69:
jpayne@69: /**
jpayne@69: * Set the iterator position to the index immediately beyond the last character in the text being scanned.
jpayne@69: * This is not the same as the last character.
jpayne@69: * @param bi The break iterator to use.
jpayne@69: * @return The character offset immediately beyond the last character in the
jpayne@69: * text being scanned.
jpayne@69: * @see ubrk_first
jpayne@69: * @stable ICU 2.0
jpayne@69: */
jpayne@69: U_STABLE int32_t U_EXPORT2
jpayne@69: ubrk_last(UBreakIterator *bi);
jpayne@69:
jpayne@69: /**
jpayne@69: * Set the iterator position to the first boundary preceding the specified offset.
jpayne@69: * The new position is always smaller than offset, or UBRK_DONE.
jpayne@69: * @param bi The break iterator to use.
jpayne@69: * @param offset The offset to begin scanning.
jpayne@69: * @return The text boundary preceding offset, or UBRK_DONE.
jpayne@69: * @see ubrk_following
jpayne@69: * @stable ICU 2.0
jpayne@69: */
jpayne@69: U_STABLE int32_t U_EXPORT2
jpayne@69: ubrk_preceding(UBreakIterator *bi,
jpayne@69: int32_t offset);
jpayne@69:
jpayne@69: /**
jpayne@69: * Advance the iterator to the first boundary following the specified offset.
jpayne@69: * The value returned is always greater than offset, or UBRK_DONE.
jpayne@69: * @param bi The break iterator to use.
jpayne@69: * @param offset The offset to begin scanning.
jpayne@69: * @return The text boundary following offset, or UBRK_DONE.
jpayne@69: * @see ubrk_preceding
jpayne@69: * @stable ICU 2.0
jpayne@69: */
jpayne@69: U_STABLE int32_t U_EXPORT2
jpayne@69: ubrk_following(UBreakIterator *bi,
jpayne@69: int32_t offset);
jpayne@69:
jpayne@69: /**
jpayne@69: * Get a locale for which text breaking information is available.
jpayne@69: * A UBreakIterator in a locale returned by this function will perform the correct
jpayne@69: * text breaking for the locale.
jpayne@69: * @param index The index of the desired locale.
jpayne@69: * @return A locale for which number text breaking information is available, or 0 if none.
jpayne@69: * @see ubrk_countAvailable
jpayne@69: * @stable ICU 2.0
jpayne@69: */
jpayne@69: U_STABLE const char* U_EXPORT2
jpayne@69: ubrk_getAvailable(int32_t index);
jpayne@69:
jpayne@69: /**
jpayne@69: * Determine how many locales have text breaking information available.
jpayne@69: * This function is most useful as determining the loop ending condition for
jpayne@69: * calls to \ref ubrk_getAvailable.
jpayne@69: * @return The number of locales for which text breaking information is available.
jpayne@69: * @see ubrk_getAvailable
jpayne@69: * @stable ICU 2.0
jpayne@69: */
jpayne@69: U_STABLE int32_t U_EXPORT2
jpayne@69: ubrk_countAvailable(void);
jpayne@69:
jpayne@69:
jpayne@69: /**
jpayne@69: * Returns true if the specified position is a boundary position. As a side
jpayne@69: * effect, leaves the iterator pointing to the first boundary position at
jpayne@69: * or after "offset".
jpayne@69: * @param bi The break iterator to use.
jpayne@69: * @param offset the offset to check.
jpayne@69: * @return True if "offset" is a boundary position.
jpayne@69: * @stable ICU 2.0
jpayne@69: */
jpayne@69: U_STABLE UBool U_EXPORT2
jpayne@69: ubrk_isBoundary(UBreakIterator *bi, int32_t offset);
jpayne@69:
jpayne@69: /**
jpayne@69: * Return the status from the break rule that determined the most recently
jpayne@69: * returned break position. The values appear in the rule source
jpayne@69: * within brackets, {123}, for example. For rules that do not specify a
jpayne@69: * status, a default value of 0 is returned.
jpayne@69: *