#include <brkiter.h>
Inheritance diagram for BreakIterator:
Public Types | |
enum | { DONE = (int32_t)-1 } |
Public Member Functions | |
virtual | ~BreakIterator () |
destructor | |
virtual UBool | operator== (const BreakIterator &) const =0 |
Return true if another object is semantically equal to this one. | |
UBool | operator!= (const BreakIterator &rhs) const |
Returns the complement of the result of operator==. | |
virtual BreakIterator * | clone (void) const =0 |
Return a polymorphic copy of this object. | |
virtual UClassID | getDynamicClassID (void) const =0 |
Return a polymorphic class ID for this object. | |
virtual const CharacterIterator & | getText (void) const =0 |
Return a CharacterIterator over the text being analyzed. | |
virtual UText * | getUText (UText *fillIn, UErrorCode &status) const =0 |
Get a UText for the text being analyzed. | |
virtual void | setText (const UnicodeString &text)=0 |
Change the text over which this operates. | |
virtual void | setText (UText *text, UErrorCode &status)=0 |
Reset the break iterator to operate over the text represented by the UText. | |
virtual void | adoptText (CharacterIterator *it)=0 |
Change the text over which this operates. | |
virtual int32_t | first (void)=0 |
Return the index of the first character in the text being scanned. | |
virtual int32_t | last (void)=0 |
Return the index immediately BEYOND the last character in the text being scanned. | |
virtual int32_t | previous (void)=0 |
Return the boundary preceding the current boundary. | |
virtual int32_t | next (void)=0 |
Return the boundary following the current boundary. | |
virtual int32_t | current (void) const =0 |
Return character index of the current interator position within the text. | |
virtual int32_t | following (int32_t offset)=0 |
Return the first boundary following the specified offset. | |
virtual int32_t | preceding (int32_t offset)=0 |
Return the first boundary preceding the specified offset. | |
virtual UBool | isBoundary (int32_t offset)=0 |
Return true if the specfied position is a boundary position. | |
virtual int32_t | next (int32_t n)=0 |
Return the nth boundary from the current boundary. | |
virtual BreakIterator * | createBufferClone (void *stackBuffer, int32_t &BufferSize, UErrorCode &status)=0 |
Thread safe client-buffer-based cloning operation Do NOT call delete on a safeclone, since 'new' is not used to create it. | |
UBool | isBufferClone (void) |
Determine whether the BreakIterator was created in user memory by createBufferClone(), and thus should not be deleted. | |
Locale | getLocale (ULocDataLocaleType type, UErrorCode &status) const |
Returns the locale for this break iterator. | |
const char * | getLocaleID (ULocDataLocaleType type, UErrorCode &status) const |
Get the locale for this break iterator object. | |
Static Public Member Functions | |
static BreakIterator *U_EXPORT2 | createWordInstance (const Locale &where, UErrorCode &status) |
Create BreakIterator for word-breaks using the given locale. | |
static BreakIterator *U_EXPORT2 | createLineInstance (const Locale &where, UErrorCode &status) |
Create BreakIterator for line-breaks using specified locale. | |
static BreakIterator *U_EXPORT2 | createCharacterInstance (const Locale &where, UErrorCode &status) |
Create BreakIterator for character-breaks using specified locale Returns an instance of a BreakIterator implementing character breaks. | |
static BreakIterator *U_EXPORT2 | createSentenceInstance (const Locale &where, UErrorCode &status) |
Create BreakIterator for sentence-breaks using specified locale Returns an instance of a BreakIterator implementing sentence breaks. | |
static BreakIterator *U_EXPORT2 | createTitleInstance (const Locale &where, UErrorCode &status) |
Create BreakIterator for title-casing breaks using the specified locale Returns an instance of a BreakIterator implementing title breaks. | |
static const Locale *U_EXPORT2 | getAvailableLocales (int32_t &count) |
Get the set of Locales for which TextBoundaries are installed. | |
static UnicodeString &U_EXPORT2 | getDisplayName (const Locale &objectLocale, const Locale &displayLocale, UnicodeString &name) |
Get name of the object for the desired Locale, in the desired langauge. | |
static UnicodeString &U_EXPORT2 | getDisplayName (const Locale &objectLocale, UnicodeString &name) |
Get name of the object for the desired Locale, in the langauge of the default locale. | |
static URegistryKey U_EXPORT2 | registerInstance (BreakIterator *toAdopt, const Locale &locale, UBreakIteratorType kind, UErrorCode &status) |
Register a new break iterator of the indicated kind, to use in the given locale. | |
static UBool U_EXPORT2 | unregister (URegistryKey key, UErrorCode &status) |
Unregister a previously-registered BreakIterator using the key returned from the register call. | |
static StringEnumeration *U_EXPORT2 | getAvailableLocales (void) |
Return a StringEnumeration over the locales available at the time of the call, including registered locales. | |
Protected Member Functions | |
BreakIterator () | |
BreakIterator (const BreakIterator &other) | |
Protected Attributes | |
UBool | fBufferClone |
Friends | |
class | ICUBreakIteratorFactory |
class | ICUBreakIteratorService |
BreakIterator is an abstract base class. Instances of BreakIterator 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.
This is the interface for all text boundaries.
Examples:
Helper function to output text
Print each element in order:void printTextRange( BreakIterator& iterator, int32_t start, int32_t end ) { UnicodeString textBuffer, temp; CharacterIterator *strIter = iterator.createText(); strIter->getText(temp); cout << " " << start << " " << end << " |" << temp.extractBetween(start, end, textBuffer) << "|" << endl; delete strIter; }
Print each element in reverse order:void printEachForward( BreakIterator& boundary) { int32_t start = boundary.first(); for (int32_t end = boundary.next(); end != BreakIterator::DONE; start = end, end = boundary.next()) { printTextRange( boundary, start, end ); } }
Print first elementvoid printEachBackward( BreakIterator& boundary) { int32_t end = boundary.last(); for (int32_t start = boundary.previous(); start != BreakIterator::DONE; end = start, start = boundary.previous()) { printTextRange( boundary, start, end ); } }
Print last elementvoid printFirst(BreakIterator& boundary) { int32_t start = boundary.first(); int32_t end = boundary.next(); printTextRange( boundary, start, end ); }
Print the element at a specified positionvoid printLast(BreakIterator& boundary) { int32_t end = boundary.last(); int32_t start = boundary.previous(); printTextRange( boundary, start, end ); }
Creating and using text boundaries
void BreakIterator_Example( void ) { BreakIterator* boundary; UnicodeString stringToExamine("Aaa bbb ccc. Ddd eee fff."); cout << "Examining: " << stringToExamine << endl; //print each sentence in forward and reverse order boundary = BreakIterator::createSentenceInstance( Locale::US ); boundary->setText(stringToExamine); cout << "----- forward: -----------" << endl; printEachForward(*boundary); cout << "----- backward: ----------" << endl; printEachBackward(*boundary); delete boundary; //print each word in order boundary = BreakIterator::createWordInstance(); boundary->setText(stringToExamine); cout << "----- forward: -----------" << endl; printEachForward(*boundary); //print first element cout << "----- first: -------------" << endl; printFirst(*boundary); //print last element cout << "----- last: --------------" << endl; printLast(*boundary); //print word at charpos 10 cout << "----- at pos 10: ---------" << endl; printAt(*boundary, 10 ); delete boundary; }
Definition at line 211 of file brkiter.h.
|
|
|
destructor
|
|
|
|
|
|
Change the text over which this operates. The text boundary is reset to the start.
Implemented in RuleBasedBreakIterator. |
|
Return a polymorphic copy of this object. This is an abstract method which subclasses implement.
Implemented in DictionaryBasedBreakIterator, and RuleBasedBreakIterator. |
|
Thread safe client-buffer-based cloning operation Do NOT call delete on a safeclone, since 'new' is not used to create it.
Implemented in DictionaryBasedBreakIterator, and RuleBasedBreakIterator. |
|
Create BreakIterator for character-breaks using specified locale Returns an instance of a BreakIterator implementing character breaks. Character breaks are boundaries of combining character sequences.
|
|
Create BreakIterator for line-breaks using specified locale. Returns an instance of a BreakIterator implementing line breaks. Line breaks are logically possible line breaks, actual line breaks are usually determined based on display width. LineBreak is useful for word wrapping text.
|
|
Create BreakIterator for sentence-breaks using specified locale Returns an instance of a BreakIterator implementing sentence breaks.
|
|
Create BreakIterator for title-casing breaks using the specified locale Returns an instance of a BreakIterator implementing title breaks. The iterator returned locates title boundaries as described for Unicode 3.2 only. For Unicode 4.0 and above title boundary iteration, please use Word Boundary iterator.createWordInstance
|
|
Create BreakIterator for word-breaks using the given locale. Returns an instance of a BreakIterator implementing word breaks. WordBreak is useful for word selection (ex. double click)
|
|
Return character index of the current interator position within the text.
Implemented in RuleBasedBreakIterator. |
|
Return the index of the first character in the text being scanned.
Implemented in RuleBasedBreakIterator. |
|
Return the first boundary following the specified offset. The value returned is always greater than the offset or the value BreakIterator.DONE
Implemented in DictionaryBasedBreakIterator, and RuleBasedBreakIterator. |
|
Return a StringEnumeration over the locales available at the time of the call, including registered locales.
|
|
Get the set of Locales for which TextBoundaries are installed. Note: this will not return locales added through the register call. To see the registered locales too, use the getAvailableLocales function that returns a StringEnumeration object
|
|
Get name of the object for the desired Locale, in the langauge of the default locale.
|
|
Get name of the object for the desired Locale, in the desired langauge.
|
|
Return a polymorphic class ID for this object. Different subclasses will return distinct unequal values.
Implements UObject. Implemented in DictionaryBasedBreakIterator, and RuleBasedBreakIterator. |
|
Returns the locale for this break iterator. Two flavors are available: valid and actual locale.
|
|
Get the locale for this break iterator object. You can choose between valid and actual locale.
|
|
Return a CharacterIterator over the text being analyzed. Changing the state of the returned iterator can have undefined consequences on the operation of the break iterator. If you need to change it, clone it first.
Implemented in RuleBasedBreakIterator. |
|
Get a UText for the text being analyzed. The returned UText is a shallow clone of the UText used internally by the break iterator implementation. It can safely be used to access the text without impacting any break iterator operations, but the underlying text itself must not be altered.
Implemented in RuleBasedBreakIterator. |
|
Return true if the specfied position is a boundary position. As a side effect, the current position of the iterator is set to the first boundary position at or following the specified offset.
Implemented in RuleBasedBreakIterator. |
|
Determine whether the BreakIterator was created in user memory by createBufferClone(), and thus should not be deleted. Such objects must be closed by an explicit call to the destructor (not delete).
Definition at line 657 of file brkiter.h. References fBufferClone. |
|
Return the index immediately BEYOND the last character in the text being scanned.
Implemented in RuleBasedBreakIterator. |
|
Return the nth boundary from the current boundary.
Implemented in RuleBasedBreakIterator. |
|
Return the boundary following the current boundary.
Implemented in RuleBasedBreakIterator. |
|
Returns the complement of the result of operator==.
Reimplemented in RuleBasedBreakIterator. |
|
Return true if another object is semantically equal to this one. The other object should be an instance of the same subclass of BreakIterator. Objects of different subclasses are considered unequal. Return true if this BreakIterator is at the same position in the same text, and is the same class and type (word, line, etc.) of BreakIterator, as the argument. Text is considered the same if it contains the same characters, it need not be the same object, and styles are not considered.
Implemented in RuleBasedBreakIterator. |
|
Return the first boundary preceding the specified offset. The value returned is always smaller than the offset or the value BreakIterator.DONE
Implemented in DictionaryBasedBreakIterator, and RuleBasedBreakIterator. |
|
Return the boundary preceding the current boundary.
Implemented in DictionaryBasedBreakIterator, and RuleBasedBreakIterator. |
|
Register a new break iterator of the indicated kind, to use in the given locale. The break iterator will be adopted. Clones of the iterator will be returned if a request for a break iterator of the given kind matches or falls back to this locale.
|
|
Reset the break iterator to operate over the text represented by the UText. The iterator position is reset to the start. This function makes a shallow clone of the supplied UText. This means that the caller is free to immediately close or otherwise reuse the Utext that was passed as a parameter, but that the underlying text itself must not be altered while being referenced by the break iterator.
Implemented in RuleBasedBreakIterator. |
|
Change the text over which this operates. The text boundary is reset to the start.
Implemented in RuleBasedBreakIterator. |
|
Unregister a previously-registered BreakIterator using the key returned from the register call. Key becomes invalid after a successful call and should not be used again. The BreakIterator corresponding to the key will be deleted.
|
|
Definition at line 640 of file brkiter.h. Referenced by isBufferClone(). |