Collator
class performs locale-sensitive string comparison.
#include <coll.h>
Inheritance diagram for Collator:
Public Types | |
enum | ECollationStrength { PRIMARY = 0, SECONDARY = 1, TERTIARY = 2, QUATERNARY = 3, IDENTICAL = 15 } |
Base letter represents a primary difference. More... | |
enum | EComparisonResult { LESS = -1, EQUAL = 0, GREATER = 1 } |
LESS is returned if source string is compared to be less than target string in the compare() method. More... | |
Public Member Functions | |
virtual | ~Collator () |
Destructor . | |
virtual UBool | operator== (const Collator &other) const |
Returns true if "other" is the same as "this". | |
virtual UBool | operator!= (const Collator &other) const |
Returns true if "other" is not the same as "this". | |
virtual Collator * | clone (void) const =0 |
Makes a shallow copy of the current object. | |
virtual EComparisonResult | compare (const UnicodeString &source, const UnicodeString &target) const =0 |
The comparison function compares the character data stored in two different strings. | |
virtual EComparisonResult | compare (const UnicodeString &source, const UnicodeString &target, int32_t length) const =0 |
Does the same thing as compare but limits the comparison to a specified length. | |
virtual EComparisonResult | compare (const UChar *source, int32_t sourceLength, const UChar *target, int32_t targetLength) const =0 |
The comparison function compares the character data stored in two different string arrays. | |
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. | |
virtual CollationKey & | getCollationKey (const UChar *source, int32_t sourceLength, CollationKey &key, UErrorCode &status) const =0 |
Transforms the string into a series of characters that can be compared with CollationKey::compareTo. | |
virtual int32_t | hashCode (void) const =0 |
Generates the hash code for the collation object . | |
virtual const Locale | getLocale (ULocDataLocaleType type, UErrorCode &status) const =0 |
Gets the locale of the Collator ICU 2.1. | |
UBool | greater (const UnicodeString &source, const UnicodeString &target) const |
Convenience method for comparing two strings based on the collation rules. | |
UBool | greaterOrEqual (const UnicodeString &source, const UnicodeString &target) const |
Convenience method for comparing two strings based on the collation rules. | |
UBool | equals (const UnicodeString &source, const UnicodeString &target) const |
Convenience method for comparing two strings based on the collation rules. | |
virtual ECollationStrength | getStrength (void) const =0 |
Determines the minimum strength that will be use in comparison or transformation. | |
virtual void | setStrength (ECollationStrength newStrength)=0 |
Sets the minimum strength to be used in comparison or transformation. | |
virtual void | getVersion (UVersionInfo info) const =0 |
Gets the version information for a Collator. | |
virtual UClassID | getDynamicClassID (void) const =0 |
Returns a unique class ID POLYMORPHICALLY. | |
virtual void | setAttribute (UColAttribute attr, UColAttributeValue value, UErrorCode &status)=0 |
Universal attribute setter. | |
virtual UColAttributeValue | getAttribute (UColAttribute attr, UErrorCode &status)=0 |
Universal attribute getter. | |
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. | |
virtual uint32_t | setVariableTop (const UnicodeString varTop, UErrorCode &status)=0 |
Sets the variable top to a collation element value of a string supplied. | |
virtual void | setVariableTop (const uint32_t varTop, UErrorCode &status)=0 |
Sets the variable top to a collation element value supplied. | |
virtual uint32_t | getVariableTop (UErrorCode &status) const =0 |
Gets the variable top value of a Collator. | |
virtual Collator * | safeClone (void)=0 |
Thread safe cloning operation. | |
virtual int32_t | getSortKey (const UnicodeString &source, uint8_t *result, int32_t resultLength) const =0 |
Get the sort key as an array of bytes from an UnicodeString. | |
virtual int32_t | getSortKey (const UChar *source, int32_t sourceLength, uint8_t *result, int32_t resultLength) const =0 |
Get the sort key as an array of bytes from an UChar buffer. | |
virtual Normalizer::EMode | getDecomposition (void) const =0 |
Get the decomposition mode of the Collator object. | |
virtual void | setDecomposition (Normalizer::EMode mode)=0 |
Set the decomposition mode of the Collator object. | |
Static Public Member Functions | |
Collator * | createInstance (UErrorCode &err) |
Creates the Collator object for the current default locale. | |
Collator * | createInstance (const Locale &loc, UErrorCode &err) |
Gets the table-based collation object for the desired locale. | |
Collator * | createInstance (const Locale &loc, UVersionInfo version, UErrorCode &err) |
Create a Collator with a specific version. | |
UnicodeString & | getDisplayName (const Locale &objectLocale, const Locale &displayLocale, UnicodeString &name) |
Get name of the object for the desired Locale, in the desired langauge. | |
UnicodeString & | getDisplayName (const Locale &objectLocale, UnicodeString &name) |
Get name of the object for the desired Locale, in the langauge of the default locale. | |
const Locale * | getAvailableLocales (int32_t &count) |
Get the set of Locales for which Collations are installed. | |
int32_t | getBound (const uint8_t *source, int32_t sourceLength, UColBoundMode boundType, uint32_t noOfLevels, uint8_t *result, int32_t resultLength, UErrorCode &status) |
Produce a bound for a given sortkey and a number of levels. | |
Protected Member Functions | |
Collator () | |
Default constructor. | |
Collator (UCollationStrength collationStrength, UNormalizationMode decompositionMode) | |
Constructor. | |
Collator (const Collator &other) | |
Copy constructor. |
Collator
class performs locale-sensitive string comparison.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. <blockquote>
// 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;
You can set a Collator
's strength property to determine the level of difference considered significant in comparisons. Five strengths are provided: PRIMARY
, SECONDARY
, TERTIARY
, QUATERNARY
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. <blockquote>
//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;
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, and CollationStrength 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.
Locale
|
Base letter represents a primary difference.
Set comparison level to PRIMARY to ignore secondary and tertiary differences.
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.
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.
Two characters are considered "identical" when they have the same unicode spellings. UCollationStrength is also used to determine the strength of sort keys generated from Collator objects. |
|
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.
|
|
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. |
|
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.
|
|
Copy constructor.
|
|
Makes a shallow copy of the current object.
Implemented in RuleBasedCollator. |
|
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.
Implemented in RuleBasedCollator. |
|
Does the same thing as compare but limits the comparison to a specified length.
Implemented in RuleBasedCollator. |
|
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.
Implemented in RuleBasedCollator. |
|
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.
|
|
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.
|
|
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.
|
|
Convenience method for comparing two strings based on the collation rules.
|
|
Universal attribute getter.
Implemented in RuleBasedCollator. |
|
Get the set of Locales for which Collations are installed.
|
|
Produce a bound for a given sortkey and a number of levels.
Return value is always the number of bytes needed, regardless of whether the result buffer was big enough or even valid.
|
|
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.
Implemented in RuleBasedCollator. |
|
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.
Implemented in RuleBasedCollator. |
|
Get the decomposition mode of the Collator object.
Implemented in RuleBasedCollator. |
|
Get name of the object for the desired Locale, in the langauge of the default locale.
|
|
Get name of the object for the desired Locale, in the desired langauge.
|
|
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) } static char fgClassID;
Implemented in RuleBasedCollator. |
|
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().
Implemented in RuleBasedCollator. |
|
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().
Implemented in RuleBasedCollator. |
|
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.
Implemented in RuleBasedCollator. |
|
Gets the variable top value of a Collator. Lower 16 bits are undefined and should be ignored.
Implemented in RuleBasedCollator. |
|
Gets the version information for a Collator.
Implemented in RuleBasedCollator. |
|
Convenience method for comparing two strings based on the collation rules.
|
|
Convenience method for comparing two strings based on the collation rules.
|
|
Returns true if "other" is not the same as "this".
Reimplemented in RuleBasedCollator. |
|
Returns true if "other" is the same as "this".
Reimplemented in RuleBasedCollator. |
|
Thread safe cloning operation.
Implemented in RuleBasedCollator. |
|
Universal attribute setter.
Implemented in RuleBasedCollator. |
|
Set the decomposition mode of the Collator object. success is equal to U_ILLEGAL_ARGUMENT_ERROR if error occurs.
Implemented in RuleBasedCollator. |
|
Sets the minimum strength to be used in comparison or transformation. Example of use:
Implemented in RuleBasedCollator. |
|
Sets the variable top to a collation element value supplied. Variable top is set to the upper 16 bits. Lower 16 bits are ignored.
Implemented in RuleBasedCollator. |
|
Sets the variable top to a collation element value of a string supplied.
Implemented in RuleBasedCollator. |
|
Sets the variable top to a collation element value of a string supplied.
Implemented in RuleBasedCollator. |