chromium/third_party/icu/source/i18n/unicode/coleitr.h

// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
 ******************************************************************************
 *   Copyright (C) 1997-2014, International Business Machines
 *   Corporation and others.  All Rights Reserved.
 ******************************************************************************
 */

/**
 * \file 
 * \brief C++ API: Collation Element Iterator.
 */

/**
* File coleitr.h
*
* Created by: Helena Shih
*
* Modification History:
*
*  Date       Name        Description
*
*  8/18/97    helena      Added internal API documentation.
* 08/03/98    erm         Synched with 1.2 version CollationElementIterator.java
* 12/10/99    aliu        Ported Thai collation support from Java.
* 01/25/01    swquek      Modified into a C++ wrapper calling C APIs (ucoliter.h)
* 02/19/01    swquek      Removed CollationElementsIterator() since it is 
*                         private constructor and no calls are made to it
* 2012-2014   markus      Rewritten in C++ again.
*/

#ifndef COLEITR_H
#define COLEITR_H

#include "unicode/utypes.h"

#if U_SHOW_CPLUSPLUS_API

#if !UCONFIG_NO_COLLATION

#include "unicode/unistr.h"
#include "unicode/uobject.h"

struct UCollationElements;
struct UHashtable;

U_NAMESPACE_BEGIN

struct CollationData;

class CharacterIterator;
class CollationIterator;
class RuleBasedCollator;
class UCollationPCE;
class UVector32;

/**
* The CollationElementIterator class is used as an iterator to walk through     
* each character of an international string. Use the iterator to return the
* ordering priority of the positioned character. The ordering priority of a 
* character, which we refer to as a key, defines how a character is collated in 
* the given collation object.
* For example, consider the following in Slovak and in traditional Spanish collation:
* <pre>
*        "ca" -> the first key is key('c') and second key is key('a').
*        "cha" -> the first key is key('ch') and second key is key('a').</pre>
* And in German phonebook collation,
* <pre> \htmlonly       "&#x00E6;b"-> the first key is key('a'), the second key is key('e'), and
*        the third key is key('b'). \endhtmlonly </pre>
* The key of a character, is an integer composed of primary order(short),
* secondary order(char), and tertiary order(char). Java strictly defines the 
* size and signedness of its primitive data types. Therefore, the static
* functions primaryOrder(), secondaryOrder(), and tertiaryOrder() return 
* int32_t to ensure the correctness of the key value.
* <p>Example of the iterator usage: (without error checking)
* <pre>
* \code
*   void CollationElementIterator_Example()
*   {
*       UnicodeString str = "This is a test";
*       UErrorCode success = U_ZERO_ERROR;
*       RuleBasedCollator* rbc =
*           (RuleBasedCollator*) RuleBasedCollator::createInstance(success);
*       CollationElementIterator* c =
*           rbc->createCollationElementIterator( str );
*       int32_t order = c->next(success);
*       c->reset();
*       order = c->previous(success);
*       delete c;
*       delete rbc;
*   }
* \endcode
* </pre>
* <p>
* The method next() returns the collation order of the next character based on
* the comparison level of the collator. The method previous() returns the
* collation order of the previous character based on the comparison level of
* the collator. The Collation Element Iterator moves only in one direction
* between calls to reset(), setOffset(), or setText(). That is, next() 
* and previous() can not be inter-used. Whenever previous() is to be called after 
* next() or vice versa, reset(), setOffset() or setText() has to be called first
* to reset the status, shifting pointers to either the end or the start of
* the string (reset() or setText()), or the specified position (setOffset()).
* Hence at the next call of next() or previous(), the first or last collation order,
* or collation order at the specified position will be returned. If a change of
* direction is done without one of these calls, the result is undefined.
* <p>
* The result of a forward iterate (next()) and reversed result of the backward
* iterate (previous()) on the same string are equivalent, if collation orders
* with the value 0 are ignored.
* Character based on the comparison level of the collator.  A collation order 
* consists of primary order, secondary order and tertiary order.  The data 
* type of the collation order is <strong>int32_t</strong>. 
*
* Note, CollationElementIterator should not be subclassed.
* @see     Collator
* @see     RuleBasedCollator
* @version 1.8 Jan 16 2001
*/
class U_I18N_API CollationElementIterator final : public UObject { … };

// CollationElementIterator inline method definitions --------------------------

inline int32_t CollationElementIterator::primaryOrder(int32_t order)
{ … }

inline int32_t CollationElementIterator::secondaryOrder(int32_t order)
{ … }

inline int32_t CollationElementIterator::tertiaryOrder(int32_t order)
{ … }

inline UBool CollationElementIterator::isIgnorable(int32_t order)
{ … }

U_NAMESPACE_END

#endif /* #if !UCONFIG_NO_COLLATION */

#endif /* U_SHOW_CPLUSPLUS_API */

#endif