#include "unicode/utypes.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 |
Typedefs | |
typedef void * | UBreakIterator |
A text-break iterator. | |
typedef enum UBreakIteratorType | UBreakIteratorType |
Enumerations | |
enum | UBreakIteratorType { UBRK_CHARACTER, UBRK_WORD, UBRK_LINE, UBRK_SENTENCE, UBRK_TITLE } |
The possible types of text boundaries. More... | |
Functions | |
U_CAPI 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_CAPI UBreakIterator *U_EXPORT2 | ubrk_openRules (const UChar *rules, int32_t rulesLength, const UChar *text, int32_t textLength, UErrorCode *status) |
Open a new UBreakIterator for locating text boundaries using specified breaking rules. | |
U_CAPI UBreakIterator *U_EXPORT2 | ubrk_safeClone (const UBreakIterator *bi, void *stackBuffer, int32_t *pBufferSize, UErrorCode *status) |
Thread safe cloning operation. | |
U_CAPI void U_EXPORT2 | ubrk_close (UBreakIterator *bi) |
Close a UBreakIterator. | |
U_CAPI 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_CAPI int32_t U_EXPORT2 | ubrk_current (const UBreakIterator *bi) |
Determine the most recently-returned text boundary. | |
U_CAPI int32_t U_EXPORT2 | ubrk_next (UBreakIterator *bi) |
Determine the text boundary following the current text boundary. | |
U_CAPI int32_t U_EXPORT2 | ubrk_previous (UBreakIterator *bi) |
Determine the text boundary preceding the current text boundary. | |
U_CAPI int32_t U_EXPORT2 | ubrk_first (UBreakIterator *bi) |
Determine the index of the first character in the text being scanned. | |
U_CAPI int32_t U_EXPORT2 | ubrk_last (UBreakIterator *bi) |
Determine the index immediately beyond the last character in the text being scanned. | |
U_CAPI int32_t U_EXPORT2 | ubrk_preceding (UBreakIterator *bi, int32_t offset) |
Determine the text boundary preceding the specified offset. | |
U_CAPI int32_t U_EXPORT2 | ubrk_following (UBreakIterator *bi, int32_t offset) |
Determine the text boundary following the specified offset. | |
U_CAPI const char *U_EXPORT2 | ubrk_getAvailable (int32_t index) |
Get a locale for which text breaking information is available. | |
U_CAPI int32_t U_EXPORT2 | ubrk_countAvailable (void) |
Determine how many locales have text breaking information available. | |
U_CAPI UBool U_EXPORT2 | ubrk_isBoundary (UBreakIterator *bi, int32_t offset) |
Returns true if the specfied position is a boundary position. |
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); }Typedef Documentation
|
A text-break iterator. For usage in C programs. |
|
The possible types of text boundaries.
|
|
Close a UBreakIterator. Once closed, a UBreakIterator may no longer be used.
|
|
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}.
|
|
Determine the most recently-returned text boundary.
|
|
Determine the index of the first character in the text being scanned. This is not always the same as index 0 of the text.
|
|
Determine the text boundary following the specified offset. The value returned is always greater than offset, or UBRK_DONE.
|
|
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.
|
|
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".
|
|
Determine the index immediately beyond the last character in the text being scanned. This is not the same as the last character.
|
|
Determine the text boundary following the current text boundary.
|
|
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.
|
|
Open a new UBreakIterator for locating text boundaries using specified breaking rules. The rule syntax is ... (TBD)
|
|
Determine the text boundary preceding the specified offset. The value returned is always smaller than offset, or UBRK_DONE.
|
|
Determine the text boundary preceding the current text boundary.
|
|
Thread safe cloning operation.
|