1999-12-28 23:57:50 +00:00
|
|
|
|
/*
|
2001-01-18 00:22:38 +00:00
|
|
|
|
******************************************************************************
|
2001-01-30 18:52:58 +00:00
|
|
|
|
* Copyright (C) 1996-2001, International Business Machines *
|
2001-01-18 00:22:38 +00:00
|
|
|
|
* Corporation and others. All Rights Reserved. *
|
|
|
|
|
******************************************************************************
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
/**
|
2001-01-30 18:52:58 +00:00
|
|
|
|
* File coll.h
|
|
|
|
|
*
|
|
|
|
|
* Created by: Helena Shih
|
|
|
|
|
*
|
|
|
|
|
* Modification History:
|
|
|
|
|
*
|
|
|
|
|
* Date Name Description
|
|
|
|
|
* 02/5/97 aliu Modified createDefault to load collation data from
|
|
|
|
|
* binary files when possible. Added related methods
|
|
|
|
|
* createCollationFromFile, chopLocale, createPathName.
|
|
|
|
|
* 02/11/97 aliu Added members addToCache, findInCache, and fgCache.
|
|
|
|
|
* 02/12/97 aliu Modified to create objects from RuleBasedCollator cache.
|
|
|
|
|
* Moved cache out of Collation class.
|
|
|
|
|
* 02/13/97 aliu Moved several methods out of this class and into
|
|
|
|
|
* RuleBasedCollator, with modifications. Modified
|
|
|
|
|
* createDefault() to call new RuleBasedCollator(Locale&)
|
|
|
|
|
* constructor. General clean up and documentation.
|
|
|
|
|
* 02/20/97 helena Added clone, operator==, operator!=, operator=, copy
|
|
|
|
|
* constructor and getDynamicClassID.
|
|
|
|
|
* 03/25/97 helena Updated with platform independent data types.
|
|
|
|
|
* 05/06/97 helena Added memory allocation error detection.
|
|
|
|
|
* 06/20/97 helena Java class name change.
|
|
|
|
|
* 09/03/97 helena Added createCollationKeyValues().
|
|
|
|
|
* 02/10/98 damiba Added compare() with length as parameter.
|
|
|
|
|
* 04/23/99 stephen Removed EDecompositionMode, merged with
|
|
|
|
|
* Normalizer::EMode.
|
|
|
|
|
* 11/02/99 helena Collator performance enhancements. Eliminates the
|
|
|
|
|
* UnicodeString construction and special case for NO_OP.
|
|
|
|
|
* 11/23/99 srl More performance enhancements. Inlining of
|
|
|
|
|
* critical accessors.
|
|
|
|
|
* 05/15/00 helena Added version information API.
|
|
|
|
|
* 01/29/01 synwee Modified into a C++ wrapper which calls C apis
|
|
|
|
|
* (ucoll.h).
|
1999-12-28 23:57:50 +00:00
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#ifndef COLL_H
|
|
|
|
|
#define COLL_H
|
|
|
|
|
|
2000-11-20 19:17:17 +00:00
|
|
|
|
#include "unicode/ucol.h"
|
1999-12-28 23:57:50 +00:00
|
|
|
|
#include "unicode/normlzr.h"
|
2001-01-18 00:22:38 +00:00
|
|
|
|
#include "unicode/locid.h"
|
1999-12-28 23:57:50 +00:00
|
|
|
|
|
2001-10-08 23:26:58 +00:00
|
|
|
|
U_NAMESPACE_BEGIN
|
|
|
|
|
|
1999-12-28 23:57:50 +00:00
|
|
|
|
class CollationKey;
|
|
|
|
|
|
|
|
|
|
/**
|
2001-01-18 00:22:38 +00:00
|
|
|
|
* The <code>Collator</code> class performs locale-sensitive string
|
|
|
|
|
* comparison.<br>
|
|
|
|
|
* You use this class to build searching and sorting routines for natural
|
|
|
|
|
* language text.<br>
|
2001-11-15 22:49:24 +00:00
|
|
|
|
* <em>Important: </em>The ICU collation service has been reimplemented
|
|
|
|
|
* in order to achieve better performance and UCA compliance.
|
2001-01-18 00:22:38 +00:00
|
|
|
|
* For details, see the
|
2001-11-15 22:49:24 +00:00
|
|
|
|
* <a href="http://oss.software.ibm.com/cvs/icu/~checkout~/icuhtml/design/collation/ICU_collation_design.htm">
|
2001-01-18 00:22:38 +00:00
|
|
|
|
* collation design document</a>.
|
|
|
|
|
* <p>
|
|
|
|
|
* <code>Collator</code> is an abstract base class. Subclasses implement
|
|
|
|
|
* specific collation strategies. One subclass,
|
|
|
|
|
* <code>RuleBasedCollator</code>, is currently provided and is applicable
|
|
|
|
|
* to a wide set of languages. Other subclasses may be created to handle more
|
|
|
|
|
* specialized needs.
|
|
|
|
|
* <p>
|
|
|
|
|
* Like other locale-sensitive classes, you can use the static factory method,
|
|
|
|
|
* <code>createInstance</code>, to obtain the appropriate
|
|
|
|
|
* <code>Collator</code> object for a given locale. You will only need to
|
|
|
|
|
* look at the subclasses of <code>Collator</code> if you need to
|
|
|
|
|
* understand the details of a particular collation strategy or if you need to
|
|
|
|
|
* modify that strategy.
|
|
|
|
|
* <p>
|
|
|
|
|
* The following example shows how to compare two strings using the
|
|
|
|
|
* <code>Collator</code> for the default locale.
|
|
|
|
|
* <blockquote>
|
|
|
|
|
* <pre>
|
|
|
|
|
* \code
|
|
|
|
|
* // Compare two strings in the default locale
|
|
|
|
|
* UErrorCode success = U_ZERO_ERROR;
|
|
|
|
|
* Collator* myCollator = Collator::createInstance(success);
|
2001-03-19 22:30:38 +00:00
|
|
|
|
* if (myCollator->compare("abc", "ABC") < 0)
|
|
|
|
|
* cout << "abc is less than ABC" << endl;
|
2001-01-18 00:22:38 +00:00
|
|
|
|
* else
|
2001-03-19 22:30:38 +00:00
|
|
|
|
* cout << "abc is greater than or equal to ABC" << endl;
|
2001-01-18 00:22:38 +00:00
|
|
|
|
* \endcode
|
|
|
|
|
* </pre>
|
|
|
|
|
* </blockquote>
|
|
|
|
|
* <p>
|
|
|
|
|
* You can set a <code>Collator</code>'s <em>strength</em> property to
|
|
|
|
|
* determine the level of difference considered significant in comparisons.
|
2001-11-15 22:49:24 +00:00
|
|
|
|
* Five strengths are provided: <code>PRIMARY</code>, <code>SECONDARY</code>,
|
|
|
|
|
* <code>TERTIARY</code>, <code>QUATERNARY</code> and <code>IDENTICAL</code>. The exact assignment of
|
2001-01-18 00:22:38 +00:00
|
|
|
|
* strengths to language features is locale dependant. For example, in Czech,
|
|
|
|
|
* "e" and "f" are considered primary differences, while "e" and "\u00EA" are
|
|
|
|
|
* secondary differences, "e" and "E" are tertiary differences and "e" and "e"
|
|
|
|
|
* are identical. The following shows how both case and accents could be
|
|
|
|
|
* ignored for US English.
|
|
|
|
|
* <blockquote>
|
|
|
|
|
* <pre>
|
|
|
|
|
* \code
|
|
|
|
|
* //Get the Collator for US English and set its strength to PRIMARY
|
|
|
|
|
* UErrorCode success = U_ZERO_ERROR;
|
|
|
|
|
* Collator* usCollator =
|
|
|
|
|
* Collator::createInstance(Locale::US, success);
|
|
|
|
|
* usCollator->setStrength(Collator::PRIMARY);
|
|
|
|
|
* if (usCollator->compare("abc", "ABC") == 0)
|
2001-03-19 22:30:38 +00:00
|
|
|
|
* cout <<
|
|
|
|
|
* "'abc' and 'ABC' strings are equivalent with strength PRIMARY" <<
|
2001-01-18 00:22:38 +00:00
|
|
|
|
* endl;
|
|
|
|
|
* \endcode
|
|
|
|
|
* </pre>
|
|
|
|
|
* </blockquote>
|
|
|
|
|
* <p>
|
|
|
|
|
* For comparing strings exactly once, the <code>compare</code> method
|
|
|
|
|
* provides the best performance. When sorting a list of strings however, it
|
|
|
|
|
* is generally necessary to compare each string multiple times. In this case,
|
|
|
|
|
* sort keys provide better performance. The <code>getSortKey</code> methods
|
|
|
|
|
* convert a string to a series of bytes that can be compared bitwise against
|
|
|
|
|
* other sort keys using <code>strcmp()</code>. Sort keys are written as
|
|
|
|
|
* zero-terminated byte strings. They consist of several substrings, one for
|
|
|
|
|
* each collation strength level, that are delimited by 0x01 bytes.
|
|
|
|
|
* If the string code points are appended for UCOL_IDENTICAL, then they are
|
|
|
|
|
* processed for correct code point order comparison and may contain 0x01
|
|
|
|
|
* bytes but not zero bytes.
|
|
|
|
|
* </p>
|
|
|
|
|
* <p>
|
|
|
|
|
* An older set of APIs returns a <code>CollationKey</code> object that wraps
|
|
|
|
|
* the sort key bytes instead of returning the bytes themselves.
|
|
|
|
|
* Its use is deprecated, but it is still available for compatibility with
|
|
|
|
|
* Java.
|
|
|
|
|
* </p>
|
|
|
|
|
* <p>
|
|
|
|
|
* <strong>Note:</strong> <code>Collator</code>s with different Locale,
|
2001-11-15 22:49:24 +00:00
|
|
|
|
* and CollationStrength settings will return different sort
|
2001-01-18 00:22:38 +00:00
|
|
|
|
* orders for the same set of strings. Locales have specific collation rules,
|
|
|
|
|
* and the way in which secondary and tertiary differences are taken into
|
|
|
|
|
* account, for example, will result in a different sorting order for same
|
|
|
|
|
* strings.
|
|
|
|
|
* </p>
|
|
|
|
|
* @see RuleBasedCollator
|
|
|
|
|
* @see CollationKey
|
|
|
|
|
* @see CollationElementIterator
|
|
|
|
|
* @see Locale
|
|
|
|
|
* @see Normalizer
|
2001-11-15 22:49:24 +00:00
|
|
|
|
* @version 2.0 11/15/01
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
class U_I18N_API Collator
|
|
|
|
|
{
|
1999-12-28 23:57:50 +00:00
|
|
|
|
public:
|
2001-01-18 00:22:38 +00:00
|
|
|
|
|
|
|
|
|
// Collator public enums -----------------------------------------------
|
|
|
|
|
|
1999-12-28 23:57:50 +00:00
|
|
|
|
/**
|
2001-01-18 00:22:38 +00:00
|
|
|
|
* Base letter represents a primary difference. Set comparison level to
|
|
|
|
|
* PRIMARY to ignore secondary and tertiary differences.<br>
|
|
|
|
|
* Use this to set the strength of a Collator object.<br>
|
|
|
|
|
* Example of primary difference, "abc" < "abd"
|
|
|
|
|
*
|
|
|
|
|
* Diacritical differences on the same base letter represent a secondary
|
|
|
|
|
* difference. Set comparison level to SECONDARY to ignore tertiary
|
|
|
|
|
* differences. Use this to set the strength of a Collator object.<br>
|
|
|
|
|
* Example of secondary difference, "<EFBFBD>" >> "a".
|
|
|
|
|
*
|
|
|
|
|
* Uppercase and lowercase versions of the same character represents a
|
|
|
|
|
* tertiary difference. Set comparison level to TERTIARY to include all
|
|
|
|
|
* comparison differences. Use this to set the strength of a Collator
|
|
|
|
|
* object.<br>
|
|
|
|
|
* Example of tertiary difference, "abc" <<< "ABC".
|
|
|
|
|
*
|
|
|
|
|
* Two characters are considered "identical" when they have the same unicode
|
|
|
|
|
* spellings.<br>
|
|
|
|
|
* For example, "<EFBFBD>" == "<EFBFBD>".
|
|
|
|
|
*
|
|
|
|
|
* UCollationStrength is also used to determine the strength of sort keys
|
|
|
|
|
* generated from Collator objects.
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
enum ECollationStrength
|
|
|
|
|
{
|
2001-03-20 00:22:19 +00:00
|
|
|
|
PRIMARY = 0,
|
|
|
|
|
SECONDARY = 1,
|
|
|
|
|
TERTIARY = 2,
|
|
|
|
|
QUATERNARY = 3,
|
|
|
|
|
IDENTICAL = 15
|
1999-12-28 23:57:50 +00:00
|
|
|
|
};
|
2001-01-18 00:22:38 +00:00
|
|
|
|
|
1999-12-28 23:57:50 +00:00
|
|
|
|
/**
|
2001-01-18 00:22:38 +00:00
|
|
|
|
* LESS is returned if source string is compared to be less than target
|
|
|
|
|
* string in the compare() method.
|
|
|
|
|
* EQUAL is returned if source string is compared to be equal to target
|
|
|
|
|
* string in the compare() method.
|
|
|
|
|
* GREATER is returned if source string is compared to be greater than
|
|
|
|
|
* target string in the compare() method.
|
|
|
|
|
* @see Collator#compare
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
enum EComparisonResult
|
|
|
|
|
{
|
1999-12-28 23:57:50 +00:00
|
|
|
|
LESS = -1,
|
|
|
|
|
EQUAL = 0,
|
|
|
|
|
GREATER = 1
|
|
|
|
|
};
|
|
|
|
|
|
2001-01-18 00:22:38 +00:00
|
|
|
|
// Collator public destructor -----------------------------------------
|
|
|
|
|
|
1999-12-28 23:57:50 +00:00
|
|
|
|
/**
|
2001-01-18 00:22:38 +00:00
|
|
|
|
* Destructor
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
virtual ~Collator();
|
|
|
|
|
|
|
|
|
|
// Collator public methods --------------------------------------------
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Returns true if "other" is the same as "this"
|
|
|
|
|
* @param other Collator object to be compared
|
|
|
|
|
* @return true if other is the same as this.
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
virtual UBool operator==(const Collator& other) const;
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Returns true if "other" is not the same as "this".
|
|
|
|
|
* @param other Collator object to be compared
|
|
|
|
|
* @return true if other is not the same as this.
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
virtual UBool operator!=(const Collator& other) const;
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Makes a shallow copy of the current object.
|
|
|
|
|
* @return a copy of this object
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
virtual Collator* clone(void) const = 0;
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Creates the Collator object for the current default locale.
|
|
|
|
|
* The default locale is determined by Locale::getDefault.
|
|
|
|
|
* The UErrorCode& err parameter is used to return status information to the user.
|
|
|
|
|
* To check whether the construction succeeded or not, you should check the
|
|
|
|
|
* value of U_SUCCESS(err). If you wish more detailed information, you can
|
|
|
|
|
* check for informational error results which still indicate success.
|
|
|
|
|
* U_USING_FALLBACK_ERROR indicates that a fall back locale was used. For
|
|
|
|
|
* example, 'de_CH' was requested, but nothing was found there, so 'de' was
|
|
|
|
|
* used. U_USING_DEFAULT_ERROR indicates that the default locale data was
|
|
|
|
|
* used; neither the requested locale nor any of its fall back locales
|
|
|
|
|
* could be found.
|
|
|
|
|
* The caller owns the returned object and is responsible for deleting it.
|
|
|
|
|
* @return the collation object of the default locale.(for example, en_US)
|
|
|
|
|
* @see Locale#getDefault
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
static Collator* createInstance(UErrorCode& err);
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Gets the table-based collation object for the desired locale. The
|
|
|
|
|
* resource of the desired locale will be loaded by ResourceLoader.
|
|
|
|
|
* Locale::ENGLISH is the base collation table and all other languages are
|
|
|
|
|
* built on top of it with additional language-specific modifications.
|
|
|
|
|
* The UErrorCode& err parameter is used to return status information to the user.
|
|
|
|
|
* To check whether the construction succeeded or not, you should check
|
|
|
|
|
* the value of U_SUCCESS(err). If you wish more detailed information, you
|
|
|
|
|
* can check for informational error results which still indicate success.
|
|
|
|
|
* U_USING_FALLBACK_ERROR indicates that a fall back locale was used. For
|
|
|
|
|
* example, 'de_CH' was requested, but nothing was found there, so 'de' was
|
|
|
|
|
* used. U_USING_DEFAULT_ERROR indicates that the default locale data was
|
|
|
|
|
* used; neither the requested locale nor any of its fall back locales
|
|
|
|
|
* could be found.
|
|
|
|
|
* The caller owns the returned object and is responsible for deleting it.
|
|
|
|
|
* @param desiredLocale the desired locale to create the collation table
|
|
|
|
|
* with.
|
|
|
|
|
* @return the created table-based collation object based on the desired
|
|
|
|
|
* locale.
|
|
|
|
|
* @see Locale
|
|
|
|
|
* @see ResourceLoader
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
static Collator* createInstance(const Locale& loc, UErrorCode& err);
|
|
|
|
|
|
2001-03-14 00:23:47 +00:00
|
|
|
|
/**
|
|
|
|
|
* Create a Collator with a specific version.
|
|
|
|
|
* This is the same as createInstance(loc, err) except that getVersion() of
|
|
|
|
|
* the returned object is guaranteed to be the same as the version
|
|
|
|
|
* parameter.
|
|
|
|
|
* This is designed to be used to open the same collator for a given
|
|
|
|
|
* locale even when ICU is updated.
|
|
|
|
|
* The same locale and version guarantees the same sort keys and
|
|
|
|
|
* comparison results.
|
|
|
|
|
*
|
|
|
|
|
* @param loc The locale ID for which to open a collator.
|
|
|
|
|
* @param version The requested collator version.
|
|
|
|
|
* @param err A reference to a UErrorCode,
|
|
|
|
|
* must not indicate a failure before calling this function.
|
|
|
|
|
* @return A pointer to a Collator, or 0 if an error occurred
|
|
|
|
|
* or a collator with the requested version is not available.
|
|
|
|
|
*
|
|
|
|
|
* @see getVersion
|
|
|
|
|
* @draft ICU 1.8
|
|
|
|
|
*/
|
|
|
|
|
static Collator *createInstance(const Locale &loc, UVersionInfo version, UErrorCode &err);
|
|
|
|
|
|
2001-01-18 00:22:38 +00:00
|
|
|
|
/**
|
|
|
|
|
* The comparison function compares the character data stored in two
|
|
|
|
|
* different strings. Returns information about whether a string is less
|
|
|
|
|
* than, greater than or equal to another string.
|
|
|
|
|
* @param source the source string to be compared with.
|
|
|
|
|
* @param target the string that is to be compared with the source string.
|
|
|
|
|
* @return Returns a byte value. GREATER if source is greater
|
|
|
|
|
* than target; EQUAL if source is equal to target; LESS if source is less
|
|
|
|
|
* than target
|
|
|
|
|
* @stable
|
|
|
|
|
**/
|
|
|
|
|
virtual EComparisonResult compare(const UnicodeString& source,
|
|
|
|
|
const UnicodeString& target) const = 0;
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Does the same thing as compare but limits the comparison to a specified
|
|
|
|
|
* length
|
|
|
|
|
* @param source the source string to be compared with.
|
|
|
|
|
* @param target the string that is to be compared with the source string.
|
|
|
|
|
* @param length the length the comparison is limitted to
|
|
|
|
|
* @return Returns a byte value. GREATER if source (up to the specified
|
|
|
|
|
* length) is greater than target; EQUAL if source (up to specified
|
|
|
|
|
* length) is equal to target; LESS if source (up to the specified
|
|
|
|
|
* length) is less than target.
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
virtual EComparisonResult compare(const UnicodeString& source,
|
|
|
|
|
const UnicodeString& target,
|
|
|
|
|
int32_t length) const = 0;
|
1999-12-28 23:57:50 +00:00
|
|
|
|
|
|
|
|
|
/**
|
2001-01-18 00:22:38 +00:00
|
|
|
|
* The comparison function compares the character data stored in two
|
|
|
|
|
* different string arrays. Returns information about whether a string array
|
|
|
|
|
* is less than, greater than or equal to another string array.
|
|
|
|
|
* @param source the source string array to be compared with.
|
|
|
|
|
* @param sourceLength the length of the source string array. If this value
|
|
|
|
|
* is equal to -1, the string array is null-terminated.
|
|
|
|
|
* @param target the string that is to be compared with the source string.
|
|
|
|
|
* @param targetLength the length of the target string array. If this value
|
|
|
|
|
* is equal to -1, the string array is null-terminated.
|
|
|
|
|
* @return Returns a byte value. GREATER if source is greater than target;
|
|
|
|
|
* EQUAL if source is equal to target; LESS if source is less than
|
|
|
|
|
* target
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
virtual EComparisonResult compare(const UChar* source, int32_t sourceLength,
|
|
|
|
|
const UChar* target, int32_t targetLength)
|
|
|
|
|
const = 0;
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Transforms the string into a series of characters that can be compared
|
|
|
|
|
* with CollationKey::compareTo. It is not possible to restore the original
|
|
|
|
|
* string from the chars in the sort key. The generated sort key handles
|
|
|
|
|
* only a limited number of ignorable characters.
|
|
|
|
|
* <p>Use CollationKey::equals or CollationKey::compare to compare the
|
|
|
|
|
* generated sort keys.
|
|
|
|
|
* If the source string is null, a null collation key will be returned.
|
|
|
|
|
* @param source the source string to be transformed into a sort key.
|
|
|
|
|
* @param key the collation key to be filled in
|
|
|
|
|
* @return the collation key of the string based on the collation rules.
|
|
|
|
|
* @see CollationKey#compare
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
virtual CollationKey& getCollationKey(const UnicodeString& source,
|
|
|
|
|
CollationKey& key,
|
|
|
|
|
UErrorCode& status) const = 0;
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Transforms the string into a series of characters that can be compared
|
|
|
|
|
* with CollationKey::compareTo. It is not possible to restore the original
|
|
|
|
|
* string from the chars in the sort key. The generated sort key handles
|
|
|
|
|
* only a limited number of ignorable characters.
|
|
|
|
|
* <p>Use CollationKey::equals or CollationKey::compare to compare the
|
|
|
|
|
* generated sort keys.
|
|
|
|
|
* <p>If the source string is null, a null collation key will be returned.
|
|
|
|
|
* @param source the source string to be transformed into a sort key.
|
|
|
|
|
* @param sourceLength length of the collation key
|
|
|
|
|
* @param key the collation key to be filled in
|
|
|
|
|
* @return the collation key of the string based on the collation rules.
|
|
|
|
|
* @see CollationKey#compare
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
virtual CollationKey& getCollationKey(const UChar*source,
|
|
|
|
|
int32_t sourceLength,
|
|
|
|
|
CollationKey& key,
|
|
|
|
|
UErrorCode& status) const = 0;
|
|
|
|
|
/**
|
|
|
|
|
* Generates the hash code for the collation object
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
virtual int32_t hashCode(void) const = 0;
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Convenience method for comparing two strings based on the collation rules.
|
|
|
|
|
* @param source the source string to be compared with.
|
|
|
|
|
* @param target the target string to be compared with.
|
|
|
|
|
* @return true if the first string is greater than the second one,
|
|
|
|
|
* according to the collation rules. false, otherwise.
|
|
|
|
|
* @see Collator#compare
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
UBool greater(const UnicodeString& source, const UnicodeString& target)
|
|
|
|
|
const;
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Convenience method for comparing two strings based on the collation rules.
|
|
|
|
|
* @param source the source string to be compared with.
|
|
|
|
|
* @param target the target string to be compared with.
|
|
|
|
|
* @return true if the first string is greater than or equal to the second
|
|
|
|
|
* one, according to the collation rules. false, otherwise.
|
|
|
|
|
* @see Collator#compare
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
UBool greaterOrEqual(const UnicodeString& source,
|
|
|
|
|
const UnicodeString& target) const;
|
|
|
|
|
/**
|
|
|
|
|
* Convenience method for comparing two strings based on the collation rules.
|
|
|
|
|
* @param source the source string to be compared with.
|
|
|
|
|
* @param target the target string to be compared with.
|
|
|
|
|
* @return true if the strings are equal according to the collation rules.
|
|
|
|
|
* false, otherwise.
|
|
|
|
|
* @see Collator#compare
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
UBool equals(const UnicodeString& source, const UnicodeString& target) const;
|
1999-12-28 23:57:50 +00:00
|
|
|
|
|
2001-01-18 00:22:38 +00:00
|
|
|
|
/**
|
|
|
|
|
* Determines the minimum strength that will be use in comparison or
|
|
|
|
|
* transformation.
|
|
|
|
|
* <p>E.g. with strength == SECONDARY, the tertiary difference is ignored
|
|
|
|
|
* <p>E.g. with strength == PRIMARY, the secondary and tertiary difference
|
|
|
|
|
* are ignored.
|
|
|
|
|
* @return the current comparison level.
|
|
|
|
|
* @see Collator#setStrength
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
virtual ECollationStrength getStrength(void) const = 0;
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Sets the minimum strength to be used in comparison or transformation.
|
|
|
|
|
* <p>Example of use:
|
|
|
|
|
* <pre>
|
2001-03-19 22:41:39 +00:00
|
|
|
|
* \code
|
|
|
|
|
* UErrorCode status = U_ZERO_ERROR;
|
|
|
|
|
* Collator*myCollation = Collator::createInstance(Locale::US,
|
2001-01-18 00:22:38 +00:00
|
|
|
|
* status);
|
2001-03-19 22:41:39 +00:00
|
|
|
|
* if (U_FAILURE(status)) return;
|
|
|
|
|
* myCollation->setStrength(Collator::PRIMARY);
|
|
|
|
|
* // result will be "abc" == "ABC"
|
|
|
|
|
* // tertiary differences will be ignored
|
|
|
|
|
* Collator::ComparisonResult result = myCollation->compare("abc",
|
2001-03-19 22:45:18 +00:00
|
|
|
|
* "ABC");
|
|
|
|
|
* \endcode
|
2001-01-18 00:22:38 +00:00
|
|
|
|
* </pre>
|
|
|
|
|
* @see Collator#getStrength
|
|
|
|
|
* @param newStrength the new comparison level.
|
|
|
|
|
* @stable
|
|
|
|
|
*/
|
|
|
|
|
virtual void setStrength(ECollationStrength newStrength) = 0;
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Get name of the object for the desired Locale, in the desired langauge
|
|
|
|
|
* @param objectLocale must be from getAvailableLocales
|
|
|
|
|
* @param displayLocale specifies the desired locale for output
|
|
|
|
|
* @param name the fill-in parameter of the return value
|
|
|
|
|
* @return display-able name of the object for the object locale in the
|
|
|
|
|
* desired language
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
static UnicodeString& getDisplayName(const Locale& objectLocale,
|
|
|
|
|
const Locale& displayLocale,
|
|
|
|
|
UnicodeString& name);
|
|
|
|
|
/**
|
|
|
|
|
* Get name of the object for the desired Locale, in the langauge of the
|
|
|
|
|
* default locale.
|
|
|
|
|
* @param objectLocale must be from getAvailableLocales
|
|
|
|
|
* @param name the fill-in parameter of the return value
|
|
|
|
|
* @return name of the object for the desired locale in the default language
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
static UnicodeString& getDisplayName(const Locale& objectLocale,
|
|
|
|
|
UnicodeString& name);
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Get the set of Locales for which Collations are installed
|
|
|
|
|
* @param count the output parameter of number of elements in the locale list
|
|
|
|
|
* @return the list of available locales which collations are installed
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
static const Locale* getAvailableLocales(int32_t& count);
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Gets the version information for a Collator.
|
|
|
|
|
* @param info the version # information, the result will be filled in
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
2000-05-15 19:48:26 +00:00
|
|
|
|
void getVersion(UVersionInfo info) const;
|
|
|
|
|
|
1999-12-28 23:57:50 +00:00
|
|
|
|
/**
|
2001-01-18 00:22:38 +00:00
|
|
|
|
* Returns a unique class ID POLYMORPHICALLY. Pure virtual method.
|
|
|
|
|
* 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.
|
|
|
|
|
* Concrete subclasses of Format must implement getDynamicClassID() and also
|
|
|
|
|
* a static method and data member:
|
|
|
|
|
* static UClassID getStaticClassID()
|
|
|
|
|
* {
|
|
|
|
|
* return (UClassID)&fgClassID;
|
|
|
|
|
* }
|
|
|
|
|
* static char fgClassID;
|
|
|
|
|
* @return The class ID for this object. All objects of a given class have
|
|
|
|
|
* the same class ID. Objects of other classes have different class
|
|
|
|
|
* IDs.
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @stable
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
1999-12-28 23:57:50 +00:00
|
|
|
|
virtual UClassID getDynamicClassID(void) const = 0;
|
2000-11-17 23:32:32 +00:00
|
|
|
|
|
2001-01-18 00:22:38 +00:00
|
|
|
|
/**
|
|
|
|
|
* Universal attribute setter
|
|
|
|
|
* @param attr attribute type
|
|
|
|
|
* @param value attribute value
|
|
|
|
|
* @param status to indicate whether the operation went on smoothly or
|
|
|
|
|
* there were errors
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @draft ICU 1.8
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
virtual void setAttribute(UColAttribute attr, UColAttributeValue value,
|
|
|
|
|
UErrorCode &status) = 0;
|
2000-11-17 23:32:32 +00:00
|
|
|
|
|
2001-01-18 00:22:38 +00:00
|
|
|
|
/**
|
|
|
|
|
* Universal attribute getter
|
|
|
|
|
* @param attr attribute type
|
|
|
|
|
* @param status to indicate whether the operation went on smoothly or
|
|
|
|
|
* there were errors
|
|
|
|
|
* @return attribute value
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @draft ICU 1.8
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
virtual UColAttributeValue getAttribute(UColAttribute attr,
|
|
|
|
|
UErrorCode &status) = 0;
|
2000-11-17 23:32:32 +00:00
|
|
|
|
|
2001-06-26 22:24:10 +00:00
|
|
|
|
/**
|
|
|
|
|
* Sets the variable top to a collation element value of a string supplied.
|
|
|
|
|
* @param varTop one or more (if contraction) UChars to which the variable top should be set
|
|
|
|
|
* @param len length of variable top string. If -1 it is considered to be zero terminated.
|
|
|
|
|
* @param status error code. If error code is set, the return value is undefined. Errors set by this function are: <br>
|
|
|
|
|
* U_CE_NOT_FOUND_ERROR if more than one character was passed and there is no such a contraction<br>
|
|
|
|
|
* U_PRIMARY_TOO_LONG_ERROR if the primary for the variable top has more than two bytes
|
|
|
|
|
* @return a 32 bit value containing the value of the variable top in upper 16 bits. Lower 16 bits are undefined
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @draft ICU 2.0
|
2001-06-26 22:24:10 +00:00
|
|
|
|
*/
|
|
|
|
|
virtual uint32_t setVariableTop(const UChar *varTop, int32_t len, UErrorCode &status) = 0;
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Sets the variable top to a collation element value of a string supplied.
|
|
|
|
|
* @param varTop an UnicodeString size 1 or more (if contraction) of UChars to which the variable top should be set
|
|
|
|
|
* @param status error code. If error code is set, the return value is undefined. Errors set by this function are: <br>
|
|
|
|
|
* U_CE_NOT_FOUND_ERROR if more than one character was passed and there is no such a contraction<br>
|
|
|
|
|
* U_PRIMARY_TOO_LONG_ERROR if the primary for the variable top has more than two bytes
|
|
|
|
|
* @return a 32 bit value containing the value of the variable top in upper 16 bits. Lower 16 bits are undefined
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @draft ICU 2.0
|
2001-06-26 22:24:10 +00:00
|
|
|
|
*/
|
|
|
|
|
virtual uint32_t setVariableTop(const UnicodeString varTop, UErrorCode &status) = 0;
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Sets the variable top to a collation element value supplied. Variable top is set to the upper 16 bits.
|
|
|
|
|
* Lower 16 bits are ignored.
|
|
|
|
|
* @param varTop CE value, as returned by setVariableTop or ucol)getVariableTop
|
|
|
|
|
* @param status error code (not changed by function)
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @draft ICU 2.0
|
2001-06-26 22:24:10 +00:00
|
|
|
|
*/
|
|
|
|
|
virtual void setVariableTop(const uint32_t varTop, UErrorCode &status) = 0;
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Gets the variable top value of a Collator.
|
|
|
|
|
* Lower 16 bits are undefined and should be ignored.
|
|
|
|
|
* @param status error code (not changed by function). If error code is set, the return value is undefined.
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @draft ICU 2.0
|
2001-06-26 22:24:10 +00:00
|
|
|
|
*/
|
|
|
|
|
virtual uint32_t getVariableTop(UErrorCode &status) const = 0;
|
|
|
|
|
|
|
|
|
|
|
2001-01-18 00:22:38 +00:00
|
|
|
|
/**
|
|
|
|
|
* Thread safe cloning operation
|
|
|
|
|
* @return pointer to the new clone, user should remove it.
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @draft ICU 1.8
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
virtual Collator* safeClone(void) = 0;
|
2000-11-17 23:32:32 +00:00
|
|
|
|
|
2001-01-18 00:22:38 +00:00
|
|
|
|
/**
|
|
|
|
|
* Get the sort key as an array of bytes from an UnicodeString.
|
|
|
|
|
* Sort key byte arrays are zero-terminated and can be compared using
|
|
|
|
|
* strcmp().
|
|
|
|
|
* @param source string to be processed.
|
|
|
|
|
* @param result buffer to store result in. If NULL, number of bytes needed
|
|
|
|
|
* will be returned.
|
|
|
|
|
* @param resultLength length of the result buffer. If if not enough the
|
|
|
|
|
* buffer will be filled to capacity.
|
|
|
|
|
* @return Number of bytes needed for storing the sort key
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @draft ICU 1.8
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
virtual int32_t getSortKey(const UnicodeString& source, uint8_t* result,
|
|
|
|
|
int32_t resultLength) const = 0;
|
2000-11-17 23:32:32 +00:00
|
|
|
|
|
2001-01-18 00:22:38 +00:00
|
|
|
|
/**
|
|
|
|
|
* Get the sort key as an array of bytes from an UChar buffer.
|
|
|
|
|
* Sort key byte arrays are zero-terminated and can be compared using
|
|
|
|
|
* strcmp().
|
|
|
|
|
* @param source string to be processed.
|
|
|
|
|
* @param sourceLength length of string to be processed.
|
|
|
|
|
* If -1, the string is 0 terminated and length will be decided by the
|
|
|
|
|
* function.
|
|
|
|
|
* @param result buffer to store result in. If NULL, number of bytes needed
|
|
|
|
|
* will be returned.
|
|
|
|
|
* @param resultLength length of the result buffer. If if not enough the
|
|
|
|
|
* buffer will be filled to capacity.
|
|
|
|
|
* @return Number of bytes needed for storing the sort key
|
2001-11-29 20:22:25 +00:00
|
|
|
|
* @draft ICU 1.8
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
|
|
|
|
virtual int32_t getSortKey(const UChar*source, int32_t sourceLength,
|
|
|
|
|
uint8_t*result, int32_t resultLength) const = 0;
|
2001-11-29 20:22:25 +00:00
|
|
|
|
// start deprecated APIs
|
|
|
|
|
/**
|
|
|
|
|
* Get the decomposition mode of the Collator object.
|
|
|
|
|
* @return the decomposition mode
|
|
|
|
|
* @see Collator#setDecomposition
|
|
|
|
|
* @deprecated To be removed after 2002-sep-30; use getAttribute().
|
|
|
|
|
*/
|
|
|
|
|
virtual Normalizer::EMode getDecomposition(void) const = 0;
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Set the decomposition mode of the Collator object. success is equal to
|
|
|
|
|
* U_ILLEGAL_ARGUMENT_ERROR if error occurs.
|
|
|
|
|
* @param the new decomposition mode
|
|
|
|
|
* @see Collator#getDecomposition
|
|
|
|
|
* @deprecated To be removed after 2002-sep-30; use setAttribute().
|
|
|
|
|
*/
|
|
|
|
|
virtual void setDecomposition(Normalizer::EMode mode) = 0;
|
1999-12-28 23:57:50 +00:00
|
|
|
|
|
|
|
|
|
protected:
|
2001-01-18 00:22:38 +00:00
|
|
|
|
|
|
|
|
|
// Collator protected constructors -------------------------------------
|
|
|
|
|
|
1999-12-28 23:57:50 +00:00
|
|
|
|
/**
|
2001-01-18 00:22:38 +00:00
|
|
|
|
* Default constructor.
|
|
|
|
|
* Constructor is different from the old default Collator constructor.
|
|
|
|
|
* The task for determing the default collation strength and normalization
|
|
|
|
|
* mode is left to the child class.
|
|
|
|
|
*/
|
1999-12-28 23:57:50 +00:00
|
|
|
|
Collator();
|
|
|
|
|
|
|
|
|
|
/**
|
2001-01-18 00:22:38 +00:00
|
|
|
|
* Constructor.
|
|
|
|
|
* Empty constructor, does not handle the arguments.
|
|
|
|
|
* This constructor is done for backward compatibility with 1.7 and 1.8.
|
|
|
|
|
* The task for handling the argument collation strength and normalization
|
|
|
|
|
* mode is left to the child class.
|
|
|
|
|
* @param collationStrength collation strength
|
|
|
|
|
* @param decompositionMode
|
|
|
|
|
*/
|
|
|
|
|
Collator(UCollationStrength collationStrength,
|
|
|
|
|
UNormalizationMode decompositionMode);
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Copy constructor.
|
|
|
|
|
* @param other Collator object to be copied from
|
|
|
|
|
*/
|
|
|
|
|
Collator(const Collator& other);
|
|
|
|
|
|
|
|
|
|
// Collator protected methods -----------------------------------------
|
1999-12-28 23:57:50 +00:00
|
|
|
|
|
|
|
|
|
private:
|
2001-01-18 00:22:38 +00:00
|
|
|
|
|
|
|
|
|
// Collator private data members ---------------------------------------
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
synwee : removed as attributes to be handled by child class
|
|
|
|
|
UCollationStrength strength;
|
1999-12-28 23:57:50 +00:00
|
|
|
|
Normalizer::EMode decmp;
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
2000-05-15 19:48:26 +00:00
|
|
|
|
static const UVersionInfo fVersion;
|
1999-12-28 23:57:50 +00:00
|
|
|
|
};
|
|
|
|
|
|
2001-01-18 00:22:38 +00:00
|
|
|
|
// Collator inline methods -----------------------------------------------
|
|
|
|
|
|
|
|
|
|
inline UBool Collator::operator==(const Collator& other) const
|
1999-12-28 23:57:50 +00:00
|
|
|
|
{
|
2001-02-12 21:12:20 +00:00
|
|
|
|
return (UBool)(this == &other);
|
1999-12-28 23:57:50 +00:00
|
|
|
|
}
|
|
|
|
|
|
2001-01-18 00:22:38 +00:00
|
|
|
|
inline UBool Collator::operator!=(const Collator& other) const
|
1999-12-28 23:57:50 +00:00
|
|
|
|
{
|
2001-02-12 21:12:20 +00:00
|
|
|
|
return (UBool)!(*this == other);
|
1999-12-28 23:57:50 +00:00
|
|
|
|
}
|
|
|
|
|
|
2001-01-18 00:22:38 +00:00
|
|
|
|
/*
|
|
|
|
|
synwee : removed since there's no attribute to be retrieved here
|
|
|
|
|
inline UCollationStrength Collator::getStrength() const
|
1999-12-28 23:57:50 +00:00
|
|
|
|
{
|
|
|
|
|
return strength;
|
|
|
|
|
}
|
|
|
|
|
|
2001-01-18 00:22:38 +00:00
|
|
|
|
inline Normalizer::EMode Collator::getDecomposition() const
|
1999-12-28 23:57:50 +00:00
|
|
|
|
{
|
|
|
|
|
return decmp;
|
|
|
|
|
}
|
2001-01-18 00:22:38 +00:00
|
|
|
|
*/
|
2001-10-08 23:26:58 +00:00
|
|
|
|
U_NAMESPACE_END
|
|
|
|
|
|
1999-12-28 23:57:50 +00:00
|
|
|
|
#endif
|