#include <rbbi.h>
Inheritance diagram for RuleBasedBreakIterator:
Public Member Functions | |
RuleBasedBreakIterator () | |
Default constructor. | |
RuleBasedBreakIterator (const RuleBasedBreakIterator &that) | |
Copy constructor. | |
RuleBasedBreakIterator (const UnicodeString &rules, UParseError &parseError, UErrorCode &status) | |
Construct a RuleBasedBreakIterator from a set of rules supplied as a string. | |
RuleBasedBreakIterator (UDataMemory *image, UErrorCode &status) | |
This constructor uses the udata interface to create a BreakIterator whose internal tables live in a memory-mapped file. | |
virtual | ~RuleBasedBreakIterator () |
Destructor. | |
RuleBasedBreakIterator & | operator= (const RuleBasedBreakIterator &that) |
Assignment operator. | |
virtual UBool | operator== (const BreakIterator &that) const |
Equality operator. | |
UBool | operator!= (const BreakIterator &that) const |
Not-equal operator. | |
virtual BreakIterator * | clone () const |
Returns a newly-constructed RuleBasedBreakIterator with the same behavior, and iterating over the same text, as this one. | |
virtual int32_t | hashCode (void) const |
Compute a hash code for this BreakIterator. | |
virtual const UnicodeString & | getRules (void) const |
Returns the description used to create this iterator. | |
virtual CharacterIterator & | getText (void) const |
virtual UText * | getUText (UText *fillIn, UErrorCode &status) const |
Get a UText for the text being analyzed. | |
virtual void | adoptText (CharacterIterator *newText) |
Set the iterator to analyze a new piece of text. | |
virtual void | setText (const UnicodeString &newText) |
Set the iterator to analyze a new piece of text. | |
virtual void | setText (UText *text, UErrorCode &status) |
Reset the break iterator to operate over the text represented by the UText. | |
virtual int32_t | first (void) |
Sets the current iteration position to the beginning of the text. | |
virtual int32_t | last (void) |
Sets the current iteration position to the end of the text. | |
virtual int32_t | next (int32_t n) |
Advances the iterator either forward or backward the specified number of steps. | |
virtual int32_t | next (void) |
Advances the iterator to the next boundary position. | |
virtual int32_t | previous (void) |
Moves the iterator backwards, to the last boundary preceding this one. | |
virtual int32_t | following (int32_t offset) |
Sets the iterator to refer to the first boundary position following the specified position. | |
virtual int32_t | preceding (int32_t offset) |
Sets the iterator to refer to the last boundary position before the specified position. | |
virtual UBool | isBoundary (int32_t offset) |
Returns true if the specfied position is a boundary position. | |
virtual int32_t | current (void) const |
Returns the current iteration position. | |
virtual int32_t | getRuleStatus () const |
Return the status tag from the break rule that determined the most recently returned break position. | |
virtual int32_t | getRuleStatusVec (int32_t *fillInVec, int32_t capacity, UErrorCode &status) |
Get the status (tag) values from the break rule(s) that determined the most recently returned break position. | |
virtual UClassID | getDynamicClassID (void) const |
Returns a unique class ID POLYMORPHICALLY. | |
virtual BreakIterator * | createBufferClone (void *stackBuffer, int32_t &BufferSize, UErrorCode &status) |
Thread safe client-buffer-based cloning operation Do NOT call delete on a safeclone, since 'new' is not used to create it. | |
virtual const uint8_t * | getBinaryRules (uint32_t &length) |
Return the binary form of compiled break rules, which can then be used to create a new break iterator at some time in the future. | |
Static Public Member Functions | |
UClassID | getStaticClassID (void) |
Returns the class ID for this class. | |
Protected Member Functions | |
RuleBasedBreakIterator (RBBIDataHeader *data, UErrorCode &status) | |
Constructor from a flattened set of RBBI data in malloced memory. | |
virtual void | reset (void) |
Dumps caches and performs other actions associated with a complete change in text or iteration position. | |
virtual void | setBreakType (int32_t type) |
Set the type of the break iterator. | |
void | init () |
Common initialization function, used by constructors and bufferClone. | |
int32_t | checkDictionary (int32_t startPos, int32_t endPos, UBool reverse) |
This is the function that actually implements dictionary-based breaking. | |
Protected Attributes | |
UText * | fText |
The UText through which this BreakIterator accesses the text. | |
CharacterIterator * | fCharIter |
A character iterator that refers to the same text as the UText, above. | |
StringCharacterIterator * | fSCharIter |
When the input text is provided by a UnicodeString, this will point to a characterIterator that wraps that data. | |
UCharCharacterIterator * | fDCharIter |
When the input text is provided by a UText, this dummy CharacterIterator over an empty string will be returned from getText(). | |
RBBIDataWrapper * | fData |
The rule data for this BreakIterator instance. | |
int32_t | fLastRuleStatusIndex |
Index of the Rule {tag} values for the most recent match. | |
UBool | fLastStatusIndexValid |
Rule tag value valid flag. | |
uint32_t | fDictionaryCharCount |
Counter for the number of characters encountered with the "dictionary" flag set. | |
int32_t * | fCachedBreakPositions |
When a range of characters is divided up using the dictionary, the break positions that are discovered are stored here, preventing us from having to use either the dictionary or the state table again until the iterator leaves this range of text. | |
int32_t | fNumCachedBreakPositions |
The number of elements in fCachedBreakPositions. | |
int32_t | fPositionInCache |
if fCachedBreakPositions is not null, this indicates which item in the cache the current iteration position refers to | |
UStack * | fLanguageBreakEngines |
If present, UStack of LanguageBreakEngine objects that might handle dictionary characters. | |
UnhandledEngine * | fUnhandledBreakEngine |
If present, the special LanguageBreakEngine used for handling characters that are in the dictionary set, but not handled by any LangugageBreakEngine. | |
int32_t | fBreakType |
The type of the break iterator, or -1 if it has not been set. | |
Friends | |
class | RBBIRuleBuilder |
class | BreakIterator |
Instances of this class are most commonly created by the factory methods of BreakIterator::createWordInstance(), BreakIterator::createLineInstance(), etc., and then used via the abstract API in class BreakIterator
See the ICU User Guide for information on Break Iterator Rules.
This class is not intended to be subclassed. (Class DictionaryBasedBreakIterator is a subclass, but that relationship is effectively internal to the ICU implementation. The subclassing interface to RulesBasedBreakIterator is not part of the ICU API, and may not remain stable.
Definition at line 65 of file rbbi.h.
|
Constructor from a flattened set of RBBI data in malloced memory. RulesBasedBreakIterators built from a custom set of rules are created via this constructor; the rules are compiled into memory, then the break iterator is constructed here. The break iterator adopts the memory, and will free it when done.
|
|
Default constructor. Creates an empty shell of an iterator, with no rules or text to iterate over. Object can subsequently be assigned to.
|
|
Copy constructor. Will produce a break iterator with the same behavior, and which iterates over the same text, as the one passed in.
|
|
Construct a RuleBasedBreakIterator from a set of rules supplied as a string.
|
|
This constructor uses the udata interface to create a BreakIterator whose internal tables live in a memory-mapped file. "image" is an ICU UDataMemory handle for the pre-compiled break iterator tables.
|
|
Destructor.
|
|
Set the iterator to analyze a new piece of text. This function resets the current iteration position to the beginning of the text.
Implements BreakIterator. |
|
This is the function that actually implements dictionary-based breaking. Covering at least the range from startPos to endPos, it checks for dictionary characters, and if it finds them determines the appropriate object to deal with them. It may cache found breaks in fCachedBreakPositions as it goes. It may well also look at text outside the range startPos to endPos. If going forward, endPos is the normal Unicode break result, and if goind in reverse, startPos is the normal Unicode break result
|
|
Returns a newly-constructed RuleBasedBreakIterator with the same behavior, and iterating over the same text, as this one. Differs from the copy constructor in that it is polymorphic, and will correctly clone (copy) a derived class. clone() is thread safe. Multiple threads may simultaeneously clone the same source break iterator.
Implements BreakIterator. |
|
Thread safe client-buffer-based cloning operation Do NOT call delete on a safeclone, since 'new' is not used to create it.
Implements BreakIterator. |
|
Returns the current iteration position.
Implements BreakIterator. |
|
Sets the current iteration position to the beginning of the text.
Implements BreakIterator. |
|
Sets the iterator to refer to the first boundary position following the specified position.
Implements BreakIterator. |
|
Return the binary form of compiled break rules, which can then be used to create a new break iterator at some time in the future. Creating a break iterator from pre-compiled rules is much faster than building one from the source form of the break rules. The binary data can only be used with the same version of ICU and on the same platform type (processor endian-ness)
|
|
Returns a unique class ID POLYMORPHICALLY. Pure virtual override. This method is to implement a simple version of RTTI, since not all C++ compilers support genuine RTTI. Polymorphic operator==() and clone() methods call this method.
Implements BreakIterator. |
|
Returns the description used to create this iterator.
|
|
Return the status tag from the break rule that determined the most recently returned break position. For break rules that do not specify a status, a default value of 0 is returned. If more than one break rule would cause a boundary to be located at some position in the text, the numerically largest of the applicable status values is returned. Of the standard types of ICU break iterators, only word break and line break provide status values. The values are defined in the header file ubrk.h. For Word breaks, the status allows distinguishing between words that contain alphabetic letters, "words" that appear to be numbers, punctuation and spaces, words containing ideographic characters, and more. For Line Break, the status distinguishes between hard (mandatory) breaks and soft (potential) break positions.
When creating custom break rules, one is free to define whatever status values may be convenient for the application. Note: this function is not thread safe. It should not have been declared const, and the const remains only for compatibility reasons. (The function is logically const, but not bit-wise const).
|
|
Get the status (tag) values from the break rule(s) that determined the most recently returned break position. The returned status value(s) are stored into an array provided by the caller. The values are stored in sorted (ascending) order. If the capacity of the output array is insufficient to hold the data, the output will be truncated to the available length, and a U_BUFFER_OVERFLOW_ERROR will be signaled.
|
|
Returns the class ID for this class. This is useful only for comparing to a return value from getDynamicClassID(). For example: Base* polymorphic_pointer = createPolymorphicObject(); if (polymorphic_pointer->getDynamicClassID() == Derived::getStaticClassID()) ...
|
|
Return a CharacterIterator over the text being analyzed. The returned character iterator is owned by the break iterator, and must not be deleted by the caller. Repeated calls to this function may return the same CharacterIterator. The returned character iterator must not be used concurrently with the break iterator. If concurrent operation is needed, clone the returned character iterator first and operate on the clone. When the break iterator is operating on text supplied via a UText, this function will fail. Lacking any way to signal failures, it returns an CharacterIterator containing no text. The function getUText() provides similar functionality, is reliable, and is more efficient. TODO: deprecate this function?
Implements BreakIterator. |
|
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.
Implements BreakIterator. |
|
Compute a hash code for this BreakIterator.
|
|
Common initialization function, used by constructors and bufferClone. (Also used by DictionaryBasedBreakIterator::createBufferClone().)
|
|
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".
Implements BreakIterator. |
|
Sets the current iteration position to the end of the text.
Implements BreakIterator. |
|
Advances the iterator to the next boundary position.
Implements BreakIterator. |
|
Advances the iterator either forward or backward the specified number of steps. Negative values move backward, and positive values move forward. This is equivalent to repeatedly calling next() or previous().
Implements BreakIterator. |
|
Not-equal operator. If operator== returns TRUE, this returns FALSE, and vice versa.
Reimplemented from BreakIterator. Definition at line 692 of file rbbi.h. References operator==(), and UBool. |
|
Assignment operator. Sets this iterator to have the same behavior, and iterate over the same text, as the one passed in.
|
|
Equality operator. Returns TRUE if both BreakIterators are of the same class, have the same behavior, and iterate over the same text.
Implements BreakIterator. Referenced by operator!=(). |
|
Sets the iterator to refer to the last boundary position before the specified position.
Implements BreakIterator. |
|
Moves the iterator backwards, to the last boundary preceding this one.
Implements BreakIterator. |
|
Dumps caches and performs other actions associated with a complete change in text or iteration position.
|
|
Set the type of the break iterator.
|
|
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.
Implements BreakIterator. |
|
Set the iterator to analyze a new piece of text. This function resets the current iteration position to the beginning of the text.
Implements BreakIterator. |
|
|
|
The type of the break iterator, or -1 if it has not been set.
|
|
When a range of characters is divided up using the dictionary, the break positions that are discovered are stored here, preventing us from having to use either the dictionary or the state table again until the iterator leaves this range of text. Has the most impact for line breaking.
|
|
A character iterator that refers to the same text as the UText, above. Only included for compatibility with old API, which was based on CharacterIterators. Value may be adopted from outside, or one of fSCharIter or fDCharIter, below. |
|
The rule data for this BreakIterator instance.
|
|
Counter for the number of characters encountered with the "dictionary" flag set.
|
|
If present, UStack of LanguageBreakEngine objects that might handle dictionary characters. Searched from top to bottom to find an object to handle a given character.
|
|
Index of the Rule {tag} values for the most recent match.
|
|
Rule tag value valid flag. Some iterator operations don't intrinsically set the correct tag value. This flag lets us lazily compute the value if we are ever asked for it.
|
|
The number of elements in fCachedBreakPositions.
|
|
if fCachedBreakPositions is not null, this indicates which item in the cache the current iteration position refers to
|
|
When the input text is provided by a UnicodeString, this will point to a characterIterator that wraps that data. Needed only for the implementation of getText(), a backwards compatibility issue. |
|
The UText through which this BreakIterator accesses the text.
|
|
If present, the special LanguageBreakEngine used for handling characters that are in the dictionary set, but not handled by any LangugageBreakEngine.
|