michael@0: /*
michael@0:  ******************************************************************************
michael@0:  *   Copyright (C) 1997-2013, International Business Machines
michael@0:  *   Corporation and others.  All Rights Reserved.
michael@0:  ******************************************************************************
michael@0:  */
michael@0: 
michael@0: /**
michael@0:  * \file 
michael@0:  * \brief C++ API: Collation Element Iterator.
michael@0:  */
michael@0: 
michael@0: /**
michael@0: * File coleitr.h
michael@0: *
michael@0: * 
michael@0: *
michael@0: * Created by: Helena Shih
michael@0: *
michael@0: * Modification History:
michael@0: *
michael@0: *  Date       Name        Description
michael@0: *
michael@0: *  8/18/97    helena      Added internal API documentation.
michael@0: * 08/03/98    erm         Synched with 1.2 version CollationElementIterator.java
michael@0: * 12/10/99    aliu        Ported Thai collation support from Java.
michael@0: * 01/25/01    swquek      Modified into a C++ wrapper calling C APIs (ucoliter.h)
michael@0: * 02/19/01    swquek      Removed CollationElementsIterator() since it is 
michael@0: *                         private constructor and no calls are made to it
michael@0: */
michael@0: 
michael@0: #ifndef COLEITR_H
michael@0: #define COLEITR_H
michael@0: 
michael@0: #include "unicode/utypes.h"
michael@0: 
michael@0:  
michael@0: #if !UCONFIG_NO_COLLATION
michael@0: 
michael@0: #include "unicode/uobject.h"
michael@0: #include "unicode/tblcoll.h"
michael@0: #include "unicode/ucoleitr.h"
michael@0: 
michael@0: /** 
michael@0:  * The UCollationElements struct.
michael@0:  * For usage in C programs.
michael@0:  * @stable ICU 2.0
michael@0:  */
michael@0: typedef struct UCollationElements UCollationElements;
michael@0: 
michael@0: U_NAMESPACE_BEGIN
michael@0: 
michael@0: /**
michael@0: * The CollationElementIterator class is used as an iterator to walk through     
michael@0: * each character of an international string. Use the iterator to return the
michael@0: * ordering priority of the positioned character. The ordering priority of a 
michael@0: * character, which we refer to as a key, defines how a character is collated in 
michael@0: * the given collation object.
michael@0: * For example, consider the following in Spanish:
michael@0: * <pre>
michael@0: *        "ca" -> the first key is key('c') and second key is key('a').
michael@0: *        "cha" -> the first key is key('ch') and second key is key('a').</pre>
michael@0: * And in German,
michael@0: * <pre> \htmlonly       "&#x00E6;b"-> the first key is key('a'), the second key is key('e'), and
michael@0: *        the third key is key('b'). \endhtmlonly </pre>
michael@0: * The key of a character, is an integer composed of primary order(short),
michael@0: * secondary order(char), and tertiary order(char). Java strictly defines the 
michael@0: * size and signedness of its primitive data types. Therefore, the static
michael@0: * functions primaryOrder(), secondaryOrder(), and tertiaryOrder() return 
michael@0: * int32_t to ensure the correctness of the key value.
michael@0: * <p>Example of the iterator usage: (without error checking)
michael@0: * <pre>
michael@0: * \code
michael@0: *   void CollationElementIterator_Example()
michael@0: *   {
michael@0: *       UnicodeString str = "This is a test";
michael@0: *       UErrorCode success = U_ZERO_ERROR;
michael@0: *       RuleBasedCollator* rbc =
michael@0: *           (RuleBasedCollator*) RuleBasedCollator::createInstance(success);
michael@0: *       CollationElementIterator* c =
michael@0: *           rbc->createCollationElementIterator( str );
michael@0: *       int32_t order = c->next(success);
michael@0: *       c->reset();
michael@0: *       order = c->previous(success);
michael@0: *       delete c;
michael@0: *       delete rbc;
michael@0: *   }
michael@0: * \endcode
michael@0: * </pre>
michael@0: * <p>
michael@0: * The method next() returns the collation order of the next character based on
michael@0: * the comparison level of the collator. The method previous() returns the
michael@0: * collation order of the previous character based on the comparison level of
michael@0: * the collator. The Collation Element Iterator moves only in one direction
michael@0: * between calls to reset(), setOffset(), or setText(). That is, next() 
michael@0: * and previous() can not be inter-used. Whenever previous() is to be called after 
michael@0: * next() or vice versa, reset(), setOffset() or setText() has to be called first
michael@0: * to reset the status, shifting pointers to either the end or the start of
michael@0: * the string (reset() or setText()), or the specified position (setOffset()).
michael@0: * Hence at the next call of next() or previous(), the first or last collation order,
michael@0: * or collation order at the spefcifieid position will be returned. If a change of
michael@0: * direction is done without one of these calls, the result is undefined.
michael@0: * <p>
michael@0: * The result of a forward iterate (next()) and reversed result of the backward
michael@0: * iterate (previous()) on the same string are equivalent, if collation orders
michael@0: * with the value UCOL_IGNORABLE are ignored.
michael@0: * Character based on the comparison level of the collator.  A collation order 
michael@0: * consists of primary order, secondary order and tertiary order.  The data 
michael@0: * type of the collation order is <strong>t_int32</strong>. 
michael@0: *
michael@0: * Note, CollationElementIterator should not be subclassed.
michael@0: * @see     Collator
michael@0: * @see     RuleBasedCollator
michael@0: * @version 1.8 Jan 16 2001
michael@0: */
michael@0: class U_I18N_API CollationElementIterator : public UObject {
michael@0: public: 
michael@0: 
michael@0:     // CollationElementIterator public data member ------------------------------
michael@0: 
michael@0:     enum {
michael@0:         /**
michael@0:          * NULLORDER indicates that an error has occured while processing
michael@0:          * @stable ICU 2.0
michael@0:          */
michael@0:         NULLORDER = (int32_t)0xffffffff
michael@0:     };
michael@0: 
michael@0:     // CollationElementIterator public constructor/destructor -------------------
michael@0: 
michael@0:     /**
michael@0:     * Copy constructor.
michael@0:     *
michael@0:     * @param other    the object to be copied from
michael@0:     * @stable ICU 2.0
michael@0:     */
michael@0:     CollationElementIterator(const CollationElementIterator& other);
michael@0: 
michael@0:     /** 
michael@0:     * Destructor
michael@0:     * @stable ICU 2.0
michael@0:     */
michael@0:     virtual ~CollationElementIterator();
michael@0: 
michael@0:     // CollationElementIterator public methods ----------------------------------
michael@0: 
michael@0:     /**
michael@0:     * Returns true if "other" is the same as "this"
michael@0:     *
michael@0:     * @param other    the object to be compared
michael@0:     * @return         true if "other" is the same as "this"
michael@0:     * @stable ICU 2.0
michael@0:     */
michael@0:     UBool operator==(const CollationElementIterator& other) const;
michael@0: 
michael@0:     /**
michael@0:     * Returns true if "other" is not the same as "this".
michael@0:     *
michael@0:     * @param other    the object to be compared
michael@0:     * @return         true if "other" is not the same as "this"
michael@0:     * @stable ICU 2.0
michael@0:     */
michael@0:     UBool operator!=(const CollationElementIterator& other) const;
michael@0: 
michael@0:     /**
michael@0:     * Resets the cursor to the beginning of the string.
michael@0:     * @stable ICU 2.0
michael@0:     */
michael@0:     void reset(void);
michael@0: 
michael@0:     /**
michael@0:     * Gets the ordering priority of the next character in the string.
michael@0:     * @param status the error code status.
michael@0:     * @return the next character's ordering. otherwise returns NULLORDER if an 
michael@0:     *         error has occured or if the end of string has been reached
michael@0:     * @stable ICU 2.0
michael@0:     */
michael@0:     int32_t next(UErrorCode& status);
michael@0: 
michael@0:     /**
michael@0:     * Get the ordering priority of the previous collation element in the string.
michael@0:     * @param status the error code status.
michael@0:     * @return the previous element's ordering. otherwise returns NULLORDER if an 
michael@0:     *         error has occured or if the start of string has been reached
michael@0:     * @stable ICU 2.0
michael@0:     */
michael@0:     int32_t previous(UErrorCode& status);
michael@0: 
michael@0:     /**
michael@0:     * Gets the primary order of a collation order.
michael@0:     * @param order the collation order
michael@0:     * @return the primary order of a collation order.
michael@0:     * @stable ICU 2.0
michael@0:     */
michael@0:     static inline int32_t primaryOrder(int32_t order);
michael@0: 
michael@0:     /**
michael@0:     * Gets the secondary order of a collation order.
michael@0:     * @param order the collation order
michael@0:     * @return the secondary order of a collation order.
michael@0:     * @stable ICU 2.0
michael@0:     */
michael@0:     static inline int32_t secondaryOrder(int32_t order);
michael@0: 
michael@0:     /**
michael@0:     * Gets the tertiary order of a collation order.
michael@0:     * @param order the collation order
michael@0:     * @return the tertiary order of a collation order.
michael@0:     * @stable ICU 2.0
michael@0:     */
michael@0:     static inline int32_t tertiaryOrder(int32_t order);
michael@0: 
michael@0:     /**
michael@0:     * Return the maximum length of any expansion sequences that end with the 
michael@0:     * specified comparison order.
michael@0:     * @param order a collation order returned by previous or next.
michael@0:     * @return maximum size of the expansion sequences ending with the collation 
michael@0:     *         element or 1 if collation element does not occur at the end of any 
michael@0:     *         expansion sequence
michael@0:     * @stable ICU 2.0
michael@0:     */
michael@0:     int32_t getMaxExpansion(int32_t order) const;
michael@0: 
michael@0:     /**
michael@0:     * Gets the comparison order in the desired strength. Ignore the other
michael@0:     * differences.
michael@0:     * @param order The order value
michael@0:     * @stable ICU 2.0
michael@0:     */
michael@0:     int32_t strengthOrder(int32_t order) const;
michael@0: 
michael@0:     /**
michael@0:     * Sets the source string.
michael@0:     * @param str the source string.
michael@0:     * @param status the error code status.
michael@0:     * @stable ICU 2.0
michael@0:     */
michael@0:     void setText(const UnicodeString& str, UErrorCode& status);
michael@0: 
michael@0:     /**
michael@0:     * Sets the source string.
michael@0:     * @param str the source character iterator.
michael@0:     * @param status the error code status.
michael@0:     * @stable ICU 2.0
michael@0:     */
michael@0:     void setText(CharacterIterator& str, UErrorCode& status);
michael@0: 
michael@0:     /**
michael@0:     * Checks if a comparison order is ignorable.
michael@0:     * @param order the collation order.
michael@0:     * @return TRUE if a character is ignorable, FALSE otherwise.
michael@0:     * @stable ICU 2.0
michael@0:     */
michael@0:     static inline UBool isIgnorable(int32_t order);
michael@0: 
michael@0:     /**
michael@0:     * Gets the offset of the currently processed character in the source string.
michael@0:     * @return the offset of the character.
michael@0:     * @stable ICU 2.0
michael@0:     */
michael@0:     int32_t getOffset(void) const;
michael@0: 
michael@0:     /**
michael@0:     * Sets the offset of the currently processed character in the source string.
michael@0:     * @param newOffset the new offset.
michael@0:     * @param status the error code status.
michael@0:     * @return the offset of the character.
michael@0:     * @stable ICU 2.0
michael@0:     */
michael@0:     void setOffset(int32_t newOffset, UErrorCode& status);
michael@0: 
michael@0:     /**
michael@0:     * ICU "poor man's RTTI", returns a UClassID for the actual class.
michael@0:     *
michael@0:     * @stable ICU 2.2
michael@0:     */
michael@0:     virtual UClassID getDynamicClassID() const;
michael@0: 
michael@0:     /**
michael@0:     * ICU "poor man's RTTI", returns a UClassID for this class.
michael@0:     *
michael@0:     * @stable ICU 2.2
michael@0:     */
michael@0:     static UClassID U_EXPORT2 getStaticClassID();
michael@0: 
michael@0: private:
michael@0:     friend class RuleBasedCollator;
michael@0: 
michael@0:     /**
michael@0:     * CollationElementIterator constructor. This takes the source string and the 
michael@0:     * collation object. The cursor will walk thru the source string based on the 
michael@0:     * predefined collation rules. If the source string is empty, NULLORDER will 
michael@0:     * be returned on the calls to next().
michael@0:     * @param sourceText    the source string.
michael@0:     * @param order         the collation object.
michael@0:     * @param status        the error code status.
michael@0:     */
michael@0:     CollationElementIterator(const UnicodeString& sourceText,
michael@0:         const RuleBasedCollator* order, UErrorCode& status);
michael@0: 
michael@0:     /**
michael@0:     * CollationElementIterator constructor. This takes the source string and the 
michael@0:     * collation object.  The cursor will walk thru the source string based on the 
michael@0:     * predefined collation rules.  If the source string is empty, NULLORDER will 
michael@0:     * be returned on the calls to next().
michael@0:     * @param sourceText    the source string.
michael@0:     * @param order         the collation object.
michael@0:     * @param status        the error code status.
michael@0:     */
michael@0:     CollationElementIterator(const CharacterIterator& sourceText,
michael@0:         const RuleBasedCollator* order, UErrorCode& status);
michael@0: 
michael@0:     /**
michael@0:     * Assignment operator
michael@0:     *
michael@0:     * @param other    the object to be copied
michael@0:     */
michael@0:     const CollationElementIterator&
michael@0:         operator=(const CollationElementIterator& other);
michael@0: 
michael@0:     CollationElementIterator(); // default constructor not implemented
michael@0: 
michael@0:     // CollationElementIterator private data members ----------------------------
michael@0: 
michael@0:     /**
michael@0:     * Data wrapper for collation elements
michael@0:     */
michael@0:     UCollationElements *m_data_;
michael@0: 
michael@0:     /**
michael@0:     * Indicates if m_data_ belongs to this object.
michael@0:     */
michael@0:     UBool isDataOwned_;
michael@0: };
michael@0: 
michael@0: // CollationElementIterator inline method defination --------------------------
michael@0: 
michael@0: /**
michael@0: * Get the primary order of a collation order.
michael@0: * @param order the collation order
michael@0: * @return the primary order of a collation order.
michael@0: */
michael@0: inline int32_t CollationElementIterator::primaryOrder(int32_t order)
michael@0: {
michael@0:     order &= RuleBasedCollator::PRIMARYORDERMASK;
michael@0:     return (order >> RuleBasedCollator::PRIMARYORDERSHIFT);
michael@0: }
michael@0: 
michael@0: /**
michael@0: * Get the secondary order of a collation order.
michael@0: * @param order the collation order
michael@0: * @return the secondary order of a collation order.
michael@0: */
michael@0: inline int32_t CollationElementIterator::secondaryOrder(int32_t order)
michael@0: {
michael@0:     order = order & RuleBasedCollator::SECONDARYORDERMASK;
michael@0:     return (order >> RuleBasedCollator::SECONDARYORDERSHIFT);
michael@0: }
michael@0: 
michael@0: /**
michael@0: * Get the tertiary order of a collation order.
michael@0: * @param order the collation order
michael@0: * @return the tertiary order of a collation order.
michael@0: */
michael@0: inline int32_t CollationElementIterator::tertiaryOrder(int32_t order)
michael@0: {
michael@0:     return (order &= RuleBasedCollator::TERTIARYORDERMASK);
michael@0: }
michael@0: 
michael@0: inline int32_t CollationElementIterator::getMaxExpansion(int32_t order) const
michael@0: {
michael@0:     return ucol_getMaxExpansion(m_data_, (uint32_t)order);
michael@0: }
michael@0: 
michael@0: inline UBool CollationElementIterator::isIgnorable(int32_t order)
michael@0: {
michael@0:     return (primaryOrder(order) == RuleBasedCollator::PRIMIGNORABLE);
michael@0: }
michael@0: 
michael@0: U_NAMESPACE_END
michael@0: 
michael@0: #endif /* #if !UCONFIG_NO_COLLATION */
michael@0: 
michael@0: #endif