#include "unicode/utypes.h"
#include "unicode/uloc.h"
#include "unicode/utext.h"
#include "unicode/parseerr.h"
Go to the source code of this file.
Defines | |
#define | UBRK_DONE ((int32_t) -1) |
Value indicating all text boundaries have been returned. | |
#define | U_BRK_SAFECLONE_BUFFERSIZE 512 |
A recommended size (in bytes) for the memory buffer to be passed to ubrk_saveClone(). | |
Typedefs | |
typedef void | UBreakIterator |
Opaque type representing an ICU Break iterator object. | |
Enumerations | |
enum | UBreakIteratorType { UBRK_CHARACTER, UBRK_WORD, UBRK_LINE, UBRK_SENTENCE, UBRK_TITLE } |
The possible types of text boundaries. More... | |
enum | UWordBreak { UBRK_WORD_NONE = 0, UBRK_WORD_NONE_LIMIT = 100, UBRK_WORD_NUMBER = 100, UBRK_WORD_NUMBER_LIMIT = 200, UBRK_WORD_LETTER = 200, UBRK_WORD_LETTER_LIMIT = 300, UBRK_WORD_KANA = 300, UBRK_WORD_KANA_LIMIT = 400, UBRK_WORD_IDEO = 400, UBRK_WORD_IDEO_LIMIT = 500 } |
Enum constants for the word break tags returned by getRuleStatus(). More... | |
enum | ULineBreakTag { UBRK_LINE_SOFT = 0, UBRK_LINE_SOFT_LIMIT = 100, UBRK_LINE_HARD = 100, UBRK_LINE_HARD_LIMIT = 200 } |
Enum constants for the line break tags returned by getRuleStatus(). More... | |
enum | USentenceBreakTag { UBRK_SENTENCE_TERM = 0, UBRK_SENTENCE_TERM_LIMIT = 100, UBRK_SENTENCE_SEP = 100, UBRK_SENTENCE_SEP_LIMIT = 200 } |
Enum constants for the sentence break tags returned by getRuleStatus(). More... | |
Functions | |
U_STABLE UBreakIterator *U_EXPORT2 | 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_STABLE UBreakIterator *U_EXPORT2 | 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. | |
U_STABLE UBreakIterator *U_EXPORT2 | ubrk_safeClone (const UBreakIterator *bi, void *stackBuffer, int32_t *pBufferSize, UErrorCode *status) |
Thread safe cloning operation. | |
U_STABLE void U_EXPORT2 | ubrk_close (UBreakIterator *bi) |
Close a UBreakIterator. | |
U_STABLE void U_EXPORT2 | 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_DRAFT void U_EXPORT2 | ubrk_setUText (UBreakIterator *bi, UText *text, UErrorCode *status) |
Sets an existing iterator to point to a new piece of text. | |
U_STABLE int32_t U_EXPORT2 | ubrk_current (const UBreakIterator *bi) |
Determine the most recently-returned text boundary. | |
U_STABLE int32_t U_EXPORT2 | ubrk_next (UBreakIterator *bi) |
Determine the text boundary following the current text boundary. | |
U_STABLE int32_t U_EXPORT2 | ubrk_previous (UBreakIterator *bi) |
Determine the text boundary preceding the current text boundary. | |
U_STABLE int32_t U_EXPORT2 | ubrk_first (UBreakIterator *bi) |
Determine the index of the first character in the text being scanned. | |
U_STABLE int32_t U_EXPORT2 | ubrk_last (UBreakIterator *bi) |
Determine the index immediately beyond the last character in the text being scanned. | |
U_STABLE int32_t U_EXPORT2 | ubrk_preceding (UBreakIterator *bi, int32_t offset) |
Determine the text boundary preceding the specified offset. | |
U_STABLE int32_t U_EXPORT2 | ubrk_following (UBreakIterator *bi, int32_t offset) |
Determine the text boundary following the specified offset. | |
U_STABLE const char *U_EXPORT2 | ubrk_getAvailable (int32_t index) |
Get a locale for which text breaking information is available. | |
U_STABLE int32_t U_EXPORT2 | ubrk_countAvailable (void) |
Determine how many locales have text breaking information available. | |
U_STABLE UBool U_EXPORT2 | ubrk_isBoundary (UBreakIterator *bi, int32_t offset) |
Returns true if the specfied position is a boundary position. | |
U_STABLE int32_t U_EXPORT2 | ubrk_getRuleStatus (UBreakIterator *bi) |
Return the status from the break rule that determined the most recently returned break position. | |
U_DRAFT int32_t U_EXPORT2 | 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_DRAFT const char *U_EXPORT2 | ubrk_getLocaleByType (const UBreakIterator *bi, ULocDataLocaleType type, UErrorCode *status) |
Return the locale of the break iterator. |
The BreakIterator C API defines methods for finding the location of boundaries in text. Pointer to a UBreakIterator maintain a current position and scan over text returning the index of characters where boundaries occur.
Line boundary analysis determines where a text string can be broken when line-wrapping. The mechanism correctly handles punctuation and hyphenated words.
Sentence boundary analysis allows selection with correct interpretation of periods within numbers and abbreviations, and trailing punctuation marks such as quotation marks and parentheses.
Word boundary analysis is used by search and replace functions, as well as within text editing applications that allow the user to select words with a double click. Word selection provides correct interpretation of punctuation marks within and following words. Characters that are not part of a word, such as symbols or punctuation marks, have word-breaks on both sides.
Character boundary analysis allows users to interact with characters as they expect to, for example, when moving the cursor through a text string. Character boundary analysis provides correct navigation of through character strings, regardless of how the character is stored. For example, an accented character might be stored as a base character and a diacritical mark. What users consider to be a character can differ between languages.
Title boundary analysis locates all positions, typically starts of words, that should be set to Title Case when title casing the text.
This is the interface for all text boundaries.
Examples:
Helper function to output text
Print each element in order:void printTextRange(UChar* str, int32_t start, int32_t end ) { UChar* result; UChar* temp; const char* res; temp=(UChar*)malloc(sizeof(UChar) * ((u_strlen(str)-start)+1)); result=(UChar*)malloc(sizeof(UChar) * ((end-start)+1)); u_strcpy(temp, &str[start]); u_strncpy(result, temp, end-start); res=(char*)malloc(sizeof(char) * (u_strlen(result)+1)); u_austrcpy(res, result); printf("%s\n", res); }
Print each element in reverse order:void printEachForward( UBreakIterator* boundary, UChar* str) { int32_t end; int32_t start = ubrk_first(boundary); for (end = ubrk_next(boundary)); end != UBRK_DONE; start = end, end = ubrk_next(boundary)) { printTextRange(str, start, end ); } }
Print first elementvoid printEachBackward( UBreakIterator* boundary, UChar* str) { int32_t start; int32_t end = ubrk_last(boundary); for (start = ubrk_previous(boundary); start != UBRK_DONE; end = start, start =ubrk_previous(boundary)) { printTextRange( str, start, end ); } }
Print last elementvoid printFirst(UBreakIterator* boundary, UChar* str) { int32_t end; int32_t start = ubrk_first(boundary); end = ubrk_next(boundary); printTextRange( str, start, end ); }
Print the element at a specified positionvoid printLast(UBreakIterator* boundary, UChar* str) { int32_t start; int32_t end = ubrk_last(boundary); start = ubrk_previous(boundary); printTextRange(str, start, end ); }
Creating and using text boundariesvoid printAt(UBreakIterator* boundary, int32_t pos , UChar* str) { int32_t start; int32_t end = ubrk_following(boundary, pos); start = ubrk_previous(boundary); printTextRange(str, start, end ); }
void BreakIterator_Example( void ) { UBreakIterator* boundary; UChar *stringToExamine; stringToExamine=(UChar*)malloc(sizeof(UChar) * (strlen("Aaa bbb ccc. Ddd eee fff.")+1) ); u_uastrcpy(stringToExamine, "Aaa bbb ccc. Ddd eee fff."); printf("Examining: "Aaa bbb ccc. Ddd eee fff."); //print each sentence in forward and reverse order boundary = ubrk_open(UBRK_SENTENCE, "en_us", stringToExamine, u_strlen(stringToExamine), &status); printf("----- forward: -----------\n"); printEachForward(boundary, stringToExamine); printf("----- backward: ----------\n"); printEachBackward(boundary, stringToExamine); ubrk_close(boundary); //print each word in order boundary = ubrk_open(UBRK_WORD, "en_us", stringToExamine, u_strlen(stringToExamine), &status); printf("----- forward: -----------\n"); printEachForward(boundary, stringToExamine); printf("----- backward: ----------\n"); printEachBackward(boundary, stringToExamine); //print first element printf("----- first: -------------\n"); printFirst(boundary, stringToExamine); //print last element printf("----- last: --------------\n"); printLast(boundary, stringToExamine); //print word at charpos 10 printf("----- at pos 10: ---------\n"); printAt(boundary, 10 , stringToExamine); ubrk_close(boundary); }
Definition in file ubrk.h.
#define U_BRK_SAFECLONE_BUFFERSIZE 512 |
#define UBRK_DONE ((int32_t) -1) |
typedef void UBreakIterator |
enum UBreakIteratorType |
The possible types of text boundaries.
enum ULineBreakTag |
Enum constants for the line break tags returned by getRuleStatus().
A range of values is defined for each category of word, to allow for further subdivisions of a category in future releases. Applications should check for tag values falling within the range, rather than for single individual values.
enum USentenceBreakTag |
Enum constants for the sentence break tags returned by getRuleStatus().
A range of values is defined for each category of sentence, to allow for further subdivisions of a category in future releases. Applications should check for tag values falling within the range, rather than for single individual values.
enum UWordBreak |
Enum constants for the word break tags returned by getRuleStatus().
A range of values is defined for each category of word, to allow for further subdivisions of a category in future releases. Applications should check for tag values falling within the range, rather than for single individual values.
U_STABLE void U_EXPORT2 ubrk_close | ( | UBreakIterator * | bi | ) |
Close a UBreakIterator.
Once closed, a UBreakIterator may no longer be used.
bi | The break iterator to close. |
U_STABLE int32_t U_EXPORT2 ubrk_countAvailable | ( | void | ) |
Determine how many locales have text breaking information available.
This function is most useful as determining the loop ending condition for calls to ubrk_getAvailable.
U_STABLE int32_t U_EXPORT2 ubrk_current | ( | const UBreakIterator * | bi | ) |
Determine the most recently-returned text boundary.
bi | The break iterator to use. |
U_STABLE int32_t U_EXPORT2 ubrk_first | ( | UBreakIterator * | bi | ) |
Determine the index of the first character in the text being scanned.
This is not always the same as index 0 of the text.
bi | The break iterator to use. |
U_STABLE int32_t U_EXPORT2 ubrk_following | ( | UBreakIterator * | bi, | |
int32_t | offset | |||
) |
Determine the text boundary following the specified offset.
The value returned is always greater than offset, or UBRK_DONE.
bi | The break iterator to use. | |
offset | The offset to begin scanning. |
U_STABLE const char* U_EXPORT2 ubrk_getAvailable | ( | int32_t | index | ) |
Get a locale for which text breaking information is available.
A UBreakIterator in a locale returned by this function will perform the correct text breaking for the locale.
index | The index of the desired locale. |
U_DRAFT const char* U_EXPORT2 ubrk_getLocaleByType | ( | const UBreakIterator * | bi, | |
ULocDataLocaleType | type, | |||
UErrorCode * | status | |||
) |
Return the locale of the break iterator.
You can choose between the valid and the actual locale.
bi | break iterator | |
type | locale type (valid or actual) | |
status | error code |
U_STABLE int32_t U_EXPORT2 ubrk_getRuleStatus | ( | UBreakIterator * | bi | ) |
Return the status from the break rule that determined the most recently returned break position.
The values appear in the rule source within brackets, {123}, for example. For rules that do not specify a status, a default value of 0 is returned.
For word break iterators, the possible values are defined in enum UWordBreak.
U_DRAFT int32_t U_EXPORT2 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.
The values appear in the rule source within brackets, {123}, for example. The default status value for rules that do not explicitly provide one is zero.
For word break iterators, the possible values are defined in enum UWordBreak.
bi | The break iterator to use | |
fillInVec | an array to be filled in with the status values. | |
capacity | the length of the supplied vector. A length of zero causes the function to return the number of status values, in the normal way, without attemtping to store any values. | |
status | receives error codes. |
U_STABLE UBool U_EXPORT2 ubrk_isBoundary | ( | UBreakIterator * | bi, | |
int32_t | offset | |||
) |
Returns true if the specfied position is a boundary position.
As a side effect, leaves the iterator pointing to the first boundary position at or after "offset".
bi | The break iterator to use. | |
offset | the offset to check. |
U_STABLE int32_t U_EXPORT2 ubrk_last | ( | UBreakIterator * | bi | ) |
Determine the index immediately beyond the last character in the text being scanned.
This is not the same as the last character.
bi | The break iterator to use. |
U_STABLE int32_t U_EXPORT2 ubrk_next | ( | UBreakIterator * | bi | ) |
Determine the text boundary following the current text boundary.
bi | The break iterator to use. |
U_STABLE UBreakIterator* U_EXPORT2 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.
A UBreakIterator may be used for detecting character, line, word, and sentence breaks in text.
type | The type of UBreakIterator to open: one of UBRK_CHARACTER, UBRK_WORD, UBRK_LINE, UBRK_SENTENCE | |
locale | The locale specifying the text-breaking conventions. | |
text | The text to be iterated over. | |
textLength | The number of characters in text, or -1 if null-terminated. | |
status | A UErrorCode to receive any errors. |
U_STABLE UBreakIterator* U_EXPORT2 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.
The rule syntax is ... (TBD)
rules | A set of rules specifying the text breaking conventions. | |
rulesLength | The number of characters in rules, or -1 if null-terminated. | |
text | The text to be iterated over. May be null, in which case ubrk_setText() is used to specify the text to be iterated. | |
textLength | The number of characters in text, or -1 if null-terminated. | |
parseErr | Receives position and context information for any syntax errors detected while parsing the rules. | |
status | A UErrorCode to receive any errors. |
U_STABLE int32_t U_EXPORT2 ubrk_preceding | ( | UBreakIterator * | bi, | |
int32_t | offset | |||
) |
Determine the text boundary preceding the specified offset.
The value returned is always smaller than offset, or UBRK_DONE.
bi | The break iterator to use. | |
offset | The offset to begin scanning. |
U_STABLE int32_t U_EXPORT2 ubrk_previous | ( | UBreakIterator * | bi | ) |
Determine the text boundary preceding the current text boundary.
bi | The break iterator to use. |
U_STABLE UBreakIterator* U_EXPORT2 ubrk_safeClone | ( | const UBreakIterator * | bi, | |
void * | stackBuffer, | |||
int32_t * | pBufferSize, | |||
UErrorCode * | status | |||
) |
Thread safe cloning operation.
bi | iterator to be cloned | |
stackBuffer | user allocated space for the new clone. If NULL new memory will be allocated. If buffer is not large enough, new memory will be allocated. Clients can use the U_BRK_SAFECLONE_BUFFERSIZE. This will probably be enough to avoid memory allocations. | |
pBufferSize | pointer to size of allocated space. If *pBufferSize == 0, a sufficient size for use in cloning will be returned ('pre-flighting') If *pBufferSize is not enough for a stack-based safe clone, new memory will be allocated. | |
status | to indicate whether the operation went on smoothly or there were errors An informational status value, U_SAFECLONE_ALLOCATED_ERROR, is used if any allocations were necessary. |
U_STABLE void U_EXPORT2 ubrk_setText | ( | UBreakIterator * | bi, | |
const UChar * | text, | |||
int32_t | textLength, | |||
UErrorCode * | status | |||
) |
Sets an existing iterator to point to a new piece of text.
bi | The iterator to use | |
text | The text to be set | |
textLength | The length of the text | |
status | The error code |
U_DRAFT void U_EXPORT2 ubrk_setUText | ( | UBreakIterator * | bi, | |
UText * | text, | |||
UErrorCode * | status | |||
) |
Sets an existing iterator to point to a new piece of text.
bi | The iterator to use | |
text | The text to be set | |
status | The error code |