/*
******************************************************************************
* Copyright (C) 1996-2001, International Business Machines *
* Corporation and others. All Rights Reserved. *
******************************************************************************
*/
/**
* 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).
*/
#ifndef COLL_H
#define COLL_H
#include "unicode/ucol.h"
#include "unicode/normlzr.h"
#include "unicode/locid.h"
U_NAMESPACE_BEGIN
class CollationKey;
/**
* The Collator
class performs locale-sensitive string
* comparison.
* You use this class to build searching and sorting routines for natural
* language text.
* Important: The ICU collation implementation is being reworked.
* This means that collation results and especially sort keys will change
* from ICU 1.6 to 1.7 and again to 1.8.
* For details, see the
*
* collation design document.
*
* Collator
is an abstract base class. Subclasses implement
* specific collation strategies. One subclass,
* RuleBasedCollator
, is currently provided and is applicable
* to a wide set of languages. Other subclasses may be created to handle more
* specialized needs.
*
* Like other locale-sensitive classes, you can use the static factory method,
* createInstance
, to obtain the appropriate
* Collator
object for a given locale. You will only need to
* look at the subclasses of Collator
if you need to
* understand the details of a particular collation strategy or if you need to
* modify that strategy.
*
* The following example shows how to compare two strings using the
* Collator
for the default locale.
*
*** \code * // Compare two strings in the default locale * UErrorCode success = U_ZERO_ERROR; * Collator* myCollator = Collator::createInstance(success); * if (myCollator->compare("abc", "ABC") < 0) * cout << "abc is less than ABC" << endl; * else * cout << "abc is greater than or equal to ABC" << endl; * \endcode **
* You can set a Collator
's strength property to
* determine the level of difference considered significant in comparisons.
* Four strengths are provided: PRIMARY
, SECONDARY
,
* TERTIARY
, and IDENTICAL
. The exact assignment of
* 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.
*
*** \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) * cout << * "'abc' and 'ABC' strings are equivalent with strength PRIMARY" << * endl; * \endcode **
* For comparing strings exactly once, the compare
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 getSortKey
methods
* convert a string to a series of bytes that can be compared bitwise against
* other sort keys using strcmp()
. 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.
*
* An older set of APIs returns a CollationKey
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.
*
* Note: Collator
s with different Locale,
* CollationStrength and DecompositionMode settings will return different sort
* 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.
*
Example of use: *
* \code * UErrorCode status = U_ZERO_ERROR; * Collator*myCollation = Collator::createInstance(Locale::US, * status); * if (U_FAILURE(status)) return; * myCollation->setStrength(Collator::PRIMARY); * // result would be Collator::EQUAL ("abc" == "ABC") * // (no primary difference between "abc" and "ABC") * UCollationResult result = myCollation->compare("abc", "ABC"); * myCollation->setStrength(Collator::TERTIARY); * // result would be Collator::LESS ("abc" <<< "ABC") * // (with tertiary difference between "abc" and "ABC") * UCollationResult result = myCollation->compare("abc", "ABC"); * \endcode ** @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 * * * *
Example of use: *
* \code * UErrorCode status = U_ZERO_ERROR; * Collator*myCollation = Collator::createInstance(Locale::US, * status); * if (U_FAILURE(status)) return; * myCollation->setStrength(Collator::PRIMARY); * // result would be Collator::EQUAL ("abc" == "ABC") * // (no primary difference between "abc" and "ABC") * UCollationResult result = myCollation->compare("abc", "ABC",3); * myCollation->setStrength(Collator::TERTIARY); * // result would be Collator::LESS (abc" <<< "ABC") * // (with tertiary difference between "abc" and "ABC") * UCollationResult result = myCollation->compare("abc", "ABC",3); * \endcode ** @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. */ virtual EComparisonResult compare(const UnicodeString& source, const UnicodeString& target, int32_t length) const = 0; /** * 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. *
Example of use: *
* \code * UErrorCode status = U_ZERO_ERROR; * Collator*myCollation = Collator::createInstance(Locale::US, * status); * if (U_FAILURE(status)) return; * myCollation->setStrength(Collator::PRIMARY); * // result would be Collator::EQUAL ("abc" == "ABC") * // (no primary difference between "abc" and "ABC") * UCollationResult result = myCollation->compare(L"abc", 3, L"ABC", 3); * myCollation->setStrength(Collator::TERTIARY); * // result would be Collator::LESS (abc" <<< "ABC") * // (with tertiary difference between "abc" and "ABC") * UCollationResult result = myCollation->compare(L"abc", 3, L"ABC", 3); * \endcode ** @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 */ 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. *
Use CollationKey::equals or CollationKey::compare to compare the * generated sort keys. *
Example of use: *
* \code * UErrorCode status = U_ZERO_ERROR; * Collator*myCollation = Collator::createInstance(Locale::US, * status); * if (U_FAILURE(status)) return; * myCollation->setStrength(Collator::PRIMARY); * UErrorCode key1Status, key2Status; * CollationKey CollationKey1 * CollationKey1 = myCollation->getCollationKey("abc", CollationKey1, * key1Status); * CollationKey CollationKey2 * CollationKey2 = myCollation->getCollationKey("ABC", CollationKey2, * key2Status); * if (U_FAILURE(key1Status) || U_FAILURE(key2Status)) * { * delete myCollation; * return; * } * // Use CollationKey::compare() to compare the sort keys * // result would be 0 (CollationKey1 == CollationKey2) * int result = CollationKey1.compare(CollationKey2); * myCollation->setStrength(Collator::TERTIARY); * CollationKey1 = myCollation->getCollationKey("abc", CollationKey1, * key1Status); * CollationKey2 = myCollation->getCollationKey("ABC", CollationKey2, * key2Status); * if (U_FAILURE(key1Status) || U_FAILURE(key2Status)) * { * delete myCollation; * return; * } * // Use CollationKey::compareTo to compare the collation keys * // result would be -1 (CollationKey1 < CollationKey2) * result = CollationKey1.compareTo(CollationKey2); * delete myCollation; * \endcode **
* 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 */ 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. *
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 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 */ virtual CollationKey& getCollationKey(const UChar*source, int32_t sourceLength, CollationKey& key, UErrorCode& status) const = 0; /** * Generates the hash code for the collation object */ 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 */ 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 */ 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 */ UBool equals(const UnicodeString& source, const UnicodeString& target) const; /** * Get the decomposition mode of the Collator object. * @return the decomposition mode * @see Collator#setDecomposition */ 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 */ virtual void setDecomposition(Normalizer::EMode mode) = 0; /** * Determines the minimum strength that will be use in comparison or * transformation. *
E.g. with strength == SECONDARY, the tertiary difference is ignored *
E.g. with strength == PRIMARY, the secondary and tertiary difference * are ignored. * @return the current comparison level. * @see Collator#setStrength */ virtual ECollationStrength getStrength(void) const = 0; /** * Sets the minimum strength to be used in comparison or transformation. *
Example of use: *
* \code * UErrorCode status = U_ZERO_ERROR; * Collator*myCollation = Collator::createInstance(Locale::US, * status); * 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", * "ABC"); * \endcode ** @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 */ 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 */ 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 */ 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 */ void getVersion(UVersionInfo info) const; /** * 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. */ virtual UClassID getDynamicClassID(void) const = 0; /** * 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 */ virtual void setAttribute(UColAttribute attr, UColAttributeValue value, UErrorCode &status) = 0; /** * Universal attribute getter * @param attr attribute type * @param status to indicate whether the operation went on smoothly or * there were errors * @return attribute value */ virtual UColAttributeValue getAttribute(UColAttribute attr, UErrorCode &status) = 0; /** * 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: