ICU 72.1 72.1
|
C API: Locale ID functionality similar to C++ class Locale. More...
Go to the source code of this file.
Macros | |
#define | ULOC_CHINESE "zh" |
Useful constant for this language. More... | |
#define | ULOC_ENGLISH "en" |
Useful constant for this language. More... | |
#define | ULOC_FRENCH "fr" |
Useful constant for this language. More... | |
#define | ULOC_GERMAN "de" |
Useful constant for this language. More... | |
#define | ULOC_ITALIAN "it" |
Useful constant for this language. More... | |
#define | ULOC_JAPANESE "ja" |
Useful constant for this language. More... | |
#define | ULOC_KOREAN "ko" |
Useful constant for this language. More... | |
#define | ULOC_SIMPLIFIED_CHINESE "zh_CN" |
Useful constant for this language. More... | |
#define | ULOC_TRADITIONAL_CHINESE "zh_TW" |
Useful constant for this language. More... | |
#define | ULOC_CANADA "en_CA" |
Useful constant for this country/region. More... | |
#define | ULOC_CANADA_FRENCH "fr_CA" |
Useful constant for this country/region. More... | |
#define | ULOC_CHINA "zh_CN" |
Useful constant for this country/region. More... | |
#define | ULOC_PRC "zh_CN" |
Useful constant for this country/region. More... | |
#define | ULOC_FRANCE "fr_FR" |
Useful constant for this country/region. More... | |
#define | ULOC_GERMANY "de_DE" |
Useful constant for this country/region. More... | |
#define | ULOC_ITALY "it_IT" |
Useful constant for this country/region. More... | |
#define | ULOC_JAPAN "ja_JP" |
Useful constant for this country/region. More... | |
#define | ULOC_KOREA "ko_KR" |
Useful constant for this country/region. More... | |
#define | ULOC_TAIWAN "zh_TW" |
Useful constant for this country/region. More... | |
#define | ULOC_UK "en_GB" |
Useful constant for this country/region. More... | |
#define | ULOC_US "en_US" |
Useful constant for this country/region. More... | |
#define | ULOC_LANG_CAPACITY 12 |
Useful constant for the maximum size of the language part of a locale ID. More... | |
#define | ULOC_COUNTRY_CAPACITY 4 |
Useful constant for the maximum size of the country part of a locale ID (including the terminating NULL). More... | |
#define | ULOC_FULLNAME_CAPACITY 157 |
Useful constant for the maximum size of the whole locale ID (including the terminating NULL and all keywords). More... | |
#define | ULOC_SCRIPT_CAPACITY 6 |
Useful constant for the maximum size of the script part of a locale ID (including the terminating NULL). More... | |
#define | ULOC_KEYWORDS_CAPACITY 96 |
Useful constant for the maximum size of keywords in a locale. More... | |
#define | ULOC_KEYWORD_AND_VALUES_CAPACITY 100 |
Useful constant for the maximum total size of keywords and their values in a locale. More... | |
#define | ULOC_KEYWORD_SEPARATOR '@' |
Invariant character separating keywords from the locale string. More... | |
#define | ULOC_KEYWORD_SEPARATOR_UNICODE 0x40 |
Unicode code point for '@' separating keywords from the locale string. More... | |
#define | ULOC_KEYWORD_ASSIGN '=' |
Invariant character for assigning value to a keyword. More... | |
#define | ULOC_KEYWORD_ASSIGN_UNICODE 0x3D |
Unicode code point for '=' for assigning value to a keyword. More... | |
#define | ULOC_KEYWORD_ITEM_SEPARATOR ';' |
Invariant character separating keywords. More... | |
#define | ULOC_KEYWORD_ITEM_SEPARATOR_UNICODE 0x3B |
Unicode code point for ';' separating keywords. More... | |
Typedefs | |
typedef enum ULocAvailableType | ULocAvailableType |
Types for uloc_getAvailableByType and uloc_countAvailableByType. More... | |
Enumerations | |
enum | ULocDataLocaleType { ULOC_ACTUAL_LOCALE = 0 , ULOC_VALID_LOCALE = 1 , ULOC_REQUESTED_LOCALE = 2 , ULOC_DATA_LOCALE_TYPE_LIMIT = 3 } |
Constants for *_getLocale() Allow user to select whether she wants information on requested, valid or actual locale. More... | |
enum | ULocAvailableType { ULOC_AVAILABLE_DEFAULT , ULOC_AVAILABLE_ONLY_LEGACY_ALIASES , ULOC_AVAILABLE_WITH_LEGACY_ALIASES , ULOC_AVAILABLE_COUNT } |
Types for uloc_getAvailableByType and uloc_countAvailableByType. More... | |
enum | ULayoutType { ULOC_LAYOUT_LTR = 0 , ULOC_LAYOUT_RTL = 1 , ULOC_LAYOUT_TTB = 2 , ULOC_LAYOUT_BTT = 3 , ULOC_LAYOUT_UNKNOWN } |
enums for the return value for the character and line orientation functions. More... | |
enum | UAcceptResult { ULOC_ACCEPT_FAILED = 0 , ULOC_ACCEPT_VALID = 1 , ULOC_ACCEPT_FALLBACK = 2 } |
Output values which uloc_acceptLanguage() writes to the 'outResult' parameter. More... | |
Functions | |
U_CAPI const char * | uloc_getDefault (void) |
Gets ICU's default locale. More... | |
U_CAPI void | uloc_setDefault (const char *localeID, UErrorCode *status) |
Sets ICU's default locale. More... | |
U_CAPI int32_t | uloc_getLanguage (const char *localeID, char *language, int32_t languageCapacity, UErrorCode *err) |
Gets the language code for the specified locale. More... | |
U_CAPI int32_t | uloc_getScript (const char *localeID, char *script, int32_t scriptCapacity, UErrorCode *err) |
Gets the script code for the specified locale. More... | |
U_CAPI int32_t | uloc_getCountry (const char *localeID, char *country, int32_t countryCapacity, UErrorCode *err) |
Gets the country code for the specified locale. More... | |
U_CAPI int32_t | uloc_getVariant (const char *localeID, char *variant, int32_t variantCapacity, UErrorCode *err) |
Gets the variant code for the specified locale. More... | |
U_CAPI int32_t | uloc_getName (const char *localeID, char *name, int32_t nameCapacity, UErrorCode *err) |
Gets the full name for the specified locale. More... | |
U_CAPI int32_t | uloc_canonicalize (const char *localeID, char *name, int32_t nameCapacity, UErrorCode *err) |
Gets the full name for the specified locale. More... | |
U_CAPI const char * | uloc_getISO3Language (const char *localeID) |
Gets the ISO language code for the specified locale. More... | |
U_CAPI const char * | uloc_getISO3Country (const char *localeID) |
Gets the ISO country code for the specified locale. More... | |
U_CAPI uint32_t | uloc_getLCID (const char *localeID) |
Gets the Win32 LCID value for the specified locale. More... | |
U_CAPI int32_t | uloc_getDisplayLanguage (const char *locale, const char *displayLocale, UChar *language, int32_t languageCapacity, UErrorCode *status) |
Gets the language name suitable for display for the specified locale. More... | |
U_CAPI int32_t | uloc_getDisplayScript (const char *locale, const char *displayLocale, UChar *script, int32_t scriptCapacity, UErrorCode *status) |
Gets the script name suitable for display for the specified locale. More... | |
U_CAPI int32_t | uloc_getDisplayCountry (const char *locale, const char *displayLocale, UChar *country, int32_t countryCapacity, UErrorCode *status) |
Gets the country name suitable for display for the specified locale. More... | |
U_CAPI int32_t | uloc_getDisplayVariant (const char *locale, const char *displayLocale, UChar *variant, int32_t variantCapacity, UErrorCode *status) |
Gets the variant name suitable for display for the specified locale. More... | |
U_CAPI int32_t | uloc_getDisplayKeyword (const char *keyword, const char *displayLocale, UChar *dest, int32_t destCapacity, UErrorCode *status) |
Gets the keyword name suitable for display for the specified locale. More... | |
U_CAPI int32_t | uloc_getDisplayKeywordValue (const char *locale, const char *keyword, const char *displayLocale, UChar *dest, int32_t destCapacity, UErrorCode *status) |
Gets the value of the keyword suitable for display for the specified locale. More... | |
U_CAPI int32_t | uloc_getDisplayName (const char *localeID, const char *inLocaleID, UChar *result, int32_t maxResultSize, UErrorCode *err) |
Gets the full name suitable for display for the specified locale. More... | |
U_CAPI const char * | uloc_getAvailable (int32_t n) |
Gets the specified locale from a list of available locales. More... | |
U_CAPI int32_t | uloc_countAvailable (void) |
Gets the size of the all available locale list. More... | |
U_CAPI UEnumeration * | uloc_openAvailableByType (ULocAvailableType type, UErrorCode *status) |
Gets a list of available locales according to the type argument, allowing the user to access different sets of supported locales in ICU. More... | |
U_CAPI const char *const * | uloc_getISOLanguages (void) |
Gets a list of all available 2-letter language codes defined in ISO 639, plus additional 3-letter codes determined to be useful for locale generation as defined by Unicode CLDR. More... | |
U_CAPI const char *const * | uloc_getISOCountries (void) |
Gets a list of all available 2-letter country codes defined in ISO 639. More... | |
U_CAPI int32_t | uloc_getParent (const char *localeID, char *parent, int32_t parentCapacity, UErrorCode *err) |
Truncate the locale ID string to get the parent locale ID. More... | |
U_CAPI int32_t | uloc_getBaseName (const char *localeID, char *name, int32_t nameCapacity, UErrorCode *err) |
Gets the full name for the specified locale, like uloc_getName(), but without keywords. More... | |
U_CAPI UEnumeration * | uloc_openKeywords (const char *localeID, UErrorCode *status) |
Gets an enumeration of keywords for the specified locale. More... | |
U_CAPI int32_t | uloc_getKeywordValue (const char *localeID, const char *keywordName, char *buffer, int32_t bufferCapacity, UErrorCode *status) |
Get the value for a keyword. More... | |
U_CAPI int32_t | uloc_setKeywordValue (const char *keywordName, const char *keywordValue, char *buffer, int32_t bufferCapacity, UErrorCode *status) |
Sets or removes the value of the specified keyword. More... | |
U_CAPI UBool | uloc_isRightToLeft (const char *locale) |
Returns whether the locale's script is written right-to-left. More... | |
U_CAPI ULayoutType | uloc_getCharacterOrientation (const char *localeId, UErrorCode *status) |
Get the layout character orientation for the specified locale. More... | |
U_CAPI ULayoutType | uloc_getLineOrientation (const char *localeId, UErrorCode *status) |
Get the layout line orientation for the specified locale. More... | |
U_CAPI int32_t | uloc_acceptLanguageFromHTTP (char *result, int32_t resultAvailable, UAcceptResult *outResult, const char *httpAcceptLanguage, UEnumeration *availableLocales, UErrorCode *status) |
Based on a HTTP header from a web browser and a list of available locales, determine an acceptable locale for the user. More... | |
U_CAPI int32_t | uloc_acceptLanguage (char *result, int32_t resultAvailable, UAcceptResult *outResult, const char **acceptList, int32_t acceptListCount, UEnumeration *availableLocales, UErrorCode *status) |
Based on a list of available locales, determine an acceptable locale for the user. More... | |
U_CAPI int32_t | uloc_getLocaleForLCID (uint32_t hostID, char *locale, int32_t localeCapacity, UErrorCode *status) |
Gets the ICU locale ID for the specified Win32 LCID value. More... | |
U_CAPI int32_t | uloc_addLikelySubtags (const char *localeID, char *maximizedLocaleID, int32_t maximizedLocaleIDCapacity, UErrorCode *err) |
Add the likely subtags for a provided locale ID, per the algorithm described in the following CLDR technical report: More... | |
U_CAPI int32_t | uloc_minimizeSubtags (const char *localeID, char *minimizedLocaleID, int32_t minimizedLocaleIDCapacity, UErrorCode *err) |
Minimize the subtags for a provided locale ID, per the algorithm described in the following CLDR technical report: More... | |
U_CAPI int32_t | uloc_forLanguageTag (const char *langtag, char *localeID, int32_t localeIDCapacity, int32_t *parsedLength, UErrorCode *err) |
Returns a locale ID for the specified BCP47 language tag string. More... | |
U_CAPI int32_t | uloc_toLanguageTag (const char *localeID, char *langtag, int32_t langtagCapacity, UBool strict, UErrorCode *err) |
Returns a well-formed language tag for this locale ID. More... | |
U_CAPI const char * | uloc_toUnicodeLocaleKey (const char *keyword) |
Converts the specified keyword (legacy key, or BCP 47 Unicode locale extension key) to the equivalent BCP 47 Unicode locale extension key. More... | |
U_CAPI const char * | uloc_toUnicodeLocaleType (const char *keyword, const char *value) |
Converts the specified keyword value (legacy type, or BCP 47 Unicode locale extension type) to the well-formed BCP 47 Unicode locale extension type for the specified keyword (category). More... | |
U_CAPI const char * | uloc_toLegacyKey (const char *keyword) |
Converts the specified keyword (BCP 47 Unicode locale extension key, or legacy key) to the legacy key. More... | |
U_CAPI const char * | uloc_toLegacyType (const char *keyword, const char *value) |
Converts the specified keyword value (BCP 47 Unicode locale extension type, or legacy type or type alias) to the canonical legacy type. More... | |
C API: Locale ID functionality similar to C++ class Locale.
A Locale
represents a specific geographical, political, or cultural region. An operation that requires a Locale
to perform its task is called locale-sensitive and uses the Locale
to tailor information for the user. For example, displaying a number is a locale-sensitive operation–the number should be formatted according to the customs/conventions of the user's native country, region, or culture. In the C APIs, a locales is simply a const char string.
You create a Locale
with one of the three options listed below. Each of the component is separated by '_' in the locale string.
The first option is a valid ISO Language Code. These codes are the lower-case two-letter codes as defined by ISO-639. You can find a full list of these codes at a number of sites, such as:newLanguagenewLanguage + newCountrynewLanguage + newCountry + newVariant
The second option includes an additional ISO Country Code. These codes are the upper-case two-letter codes as defined by ISO-3166. You can find a full list of these codes at a number of sites, such as:
http://www.chemie.fu-berlin.de/diverse/doc/ISO_3166.html
The third option requires another additional information–the Variant. The Variant codes are vendor and browser-specific. For example, use WIN for Windows, MAC for Macintosh, and POSIX for POSIX. Where there are two variants, separate them with an underscore, and put the most important one first. For example, a Traditional Spanish collation might be referenced, with "ES", "ES", "Traditional_WIN".
Because a Locale
is just an identifier for a region, no validity check is performed when you specify a Locale
. If you want to see whether particular resources are available for the Locale
you asked for, you must query those resources. For example, ask the UNumberFormat
for the locales it supports using its getAvailable
method.
Note: When you ask for a resource for a particular locale, you get back the best available match, not necessarily precisely what you asked for. For more information, look at UResourceBundle
.
The Locale
provides a number of convenient constants that you can use to specify the commonly used locales. For example, the following refers to a locale for the United States:
Once you've specified a locale you can query it for information about itself. Use uloc_getCountry
to get the ISO Country Code and uloc_getLanguage
to get the ISO Language Code. You can use uloc_getDisplayCountry
to get the name of the country suitable for displaying to the user. Similarly, you can use uloc_getDisplayLanguage
to get the name of the language suitable for displaying to the user. Interestingly, the uloc_getDisplayXXX
methods are themselves locale-sensitive and have two versions: one that uses the default locale and one that takes a locale as an argument and displays the name or country in a language appropriate to that locale.
The ICU provides a number of services that perform locale-sensitive operations. For example, the unum_xxx
functions format numbers, currency, or percentages in a locale-sensitive manner.
Each of these methods has two variants; one with an explicit locale and one without; the latter using the default locale.UErrorCode success = U_ZERO_ERROR;UNumberFormat *nf;const char* myLocale = "fr_FR";unum_close(nf);unum_close(nf);unum_close(nf);U_CAPI UNumberFormat * unum_open(UNumberFormatStyle style, const UChar *pattern, int32_t patternLength, const char *locale, UParseError *parseErr, UErrorCode *status)Create and return a new UNumberFormat for formatting and parsing numbers.#define NULLDefine NULL if necessary, to nullptr for C++ and to ((void *)0) for C.Definition: utypes.h:188
Anf = unum_open( UNUM_DEFAULT, myLocale, success );unum_close(nf);nf = unum_open( UNUM_CURRENCY, myLocale, success );unum_close(nf);nf = unum_open( UNUM_PERCENT, myLocale, success );unum_close(nf);
Locale
is the mechanism for identifying the kind of services (UNumberFormat
) that you would like to get. The locale is just a mechanism for identifying these services.
Each international service that performs locale-sensitive operations allows you to get all the available objects of that type. You can sift through these objects by language, country, or variant, and use the display names to present a menu to the user. For example, you can create a menu of all the collation objects suitable for a given language. Such classes implement these three class methods:
int32_t uloc_countAvailable();int32_tconst char* inLocaleID,UChar* result,int32_t maxResultSize,UErrorCode* err);U_CAPI int32_t uloc_getDisplayName(const char *localeID, const char *inLocaleID, UChar *result, int32_t maxResultSize, UErrorCode *err)Gets the full name suitable for display for the specified locale.U_CAPI const char * uloc_getAvailable(int32_t n)Gets the specified locale from a list of available locales.U_CAPI int32_t uloc_countAvailable(void)Gets the size of the all available locale list.
Concerning POSIX/RFC1766 Locale IDs, the getLanguage/getCountry/getVariant/getName functions do understand the POSIX type form of language_COUNTRY.ENCODING@VARIANT and if there is not an ICU-stype variant, uloc_getVariant() for example will return the one listed after the @at sign. As well, the hyphen "-" is recognized as a country/variant separator similarly to RFC1766. So for example, "en-us" will be interpreted as en_US.
As a result, uloc_getName() is far from a no-op, and will have the effect of converting POSIX/RFC1766 IDs into ICU form, although it does NOT map any of the actual codes (i.e. russian->ru) in any way. Applications should call uloc_getName() at the point where a locale ID is coming from an external source (user entry, OS, web browser) and pass the resulting string to other ICU functions. For example, don't use de-de@EURO as an argument to resourcebundle.
Definition in file uloc.h.
#define ULOC_CANADA "en_CA" |
#define ULOC_CANADA_FRENCH "fr_CA" |
#define ULOC_CHINA "zh_CN" |
#define ULOC_CHINESE "zh" |
#define ULOC_COUNTRY_CAPACITY 4 |
#define ULOC_ENGLISH "en" |
#define ULOC_FRANCE "fr_FR" |
#define ULOC_FRENCH "fr" |
#define ULOC_FULLNAME_CAPACITY 157 |
#define ULOC_GERMAN "de" |
#define ULOC_GERMANY "de_DE" |
#define ULOC_ITALIAN "it" |
#define ULOC_ITALY "it_IT" |
#define ULOC_JAPAN "ja_JP" |
#define ULOC_JAPANESE "ja" |
#define ULOC_KEYWORD_AND_VALUES_CAPACITY 100 |
#define ULOC_KEYWORD_ASSIGN '=' |
#define ULOC_KEYWORD_ASSIGN_UNICODE 0x3D |
Unicode code point for '=' for assigning value to a keyword.
#define ULOC_KEYWORD_ITEM_SEPARATOR ';' |
#define ULOC_KEYWORD_ITEM_SEPARATOR_UNICODE 0x3B |
#define ULOC_KEYWORD_SEPARATOR '@' |
#define ULOC_KEYWORD_SEPARATOR_UNICODE 0x40 |
Unicode code point for '@' separating keywords from the locale string.
#define ULOC_KEYWORDS_CAPACITY 96 |
#define ULOC_KOREA "ko_KR" |
#define ULOC_KOREAN "ko" |
#define ULOC_LANG_CAPACITY 12 |
#define ULOC_PRC "zh_CN" |
#define ULOC_SCRIPT_CAPACITY 6 |
#define ULOC_SIMPLIFIED_CHINESE "zh_CN" |
#define ULOC_TAIWAN "zh_TW" |
#define ULOC_TRADITIONAL_CHINESE "zh_TW" |
#define ULOC_UK "en_GB" |
#define ULOC_US "en_US" |
typedef enum ULocAvailableType ULocAvailableType |
Types for uloc_getAvailableByType and uloc_countAvailableByType.
enum UAcceptResult |
Output values which uloc_acceptLanguage() writes to the 'outResult' parameter.
Enumerator | |
---|---|
ULOC_ACCEPT_FAILED | No exact match was found.
|
ULOC_ACCEPT_VALID | An exact match was found.
|
ULOC_ACCEPT_FALLBACK | A fallback was found. For example, the Accept-Language list includes 'ja_JP' and is matched with available locale 'ja'.
|
enum ULayoutType |
enum ULocAvailableType |
Types for uloc_getAvailableByType and uloc_countAvailableByType.
Enumerator | |
---|---|
ULOC_AVAILABLE_DEFAULT | Locales that return data when passed to ICU APIs, but not including legacy or alias locales.
|
ULOC_AVAILABLE_ONLY_LEGACY_ALIASES | Legacy or alias locales that return data when passed to ICU APIs. Examples of supported legacy or alias locales:
The locales in this set are disjoint from the ones in ULOC_AVAILABLE_DEFAULT. To get both sets at the same time, use ULOC_AVAILABLE_WITH_LEGACY_ALIASES.
|
ULOC_AVAILABLE_WITH_LEGACY_ALIASES | The union of the locales in ULOC_AVAILABLE_DEFAULT and ULOC_AVAILABLE_ONLY_LEGACY_ALIAS.
|
ULOC_AVAILABLE_COUNT |
|
enum ULocDataLocaleType |
Constants for *_getLocale() Allow user to select whether she wants information on requested, valid or actual locale.
For example, a collator for "en_US_CALIFORNIA" was requested. In the current state of ICU (2.0), the requested locale is "en_US_CALIFORNIA", the valid locale is "en_US" (most specific locale supported by ICU) and the actual locale is "root" (the collation data comes unmodified from the UCA) The locale is considered supported by ICU if there is a core ICU bundle for that locale (although it may be empty).
Enumerator | |
---|---|
ULOC_ACTUAL_LOCALE | This is locale the data actually comes from.
|
ULOC_VALID_LOCALE | This is the most specific locale supported by ICU.
|
ULOC_REQUESTED_LOCALE | This is the requested locale.
|
ULOC_DATA_LOCALE_TYPE_LIMIT | One more than the highest normal ULocDataLocaleType value.
|
U_CAPI int32_t uloc_acceptLanguage | ( | char * | result, |
int32_t | resultAvailable, | ||
UAcceptResult * | outResult, | ||
const char ** | acceptList, | ||
int32_t | acceptListCount, | ||
UEnumeration * | availableLocales, | ||
UErrorCode * | status | ||
) |
Based on a list of available locales, determine an acceptable locale for the user.
This is a thin wrapper over C++ class LocaleMatcher.
result | - buffer to accept the result locale |
resultAvailable | the size of the result buffer. |
outResult | - An out parameter that contains the fallback status |
acceptList | - list of acceptable languages |
acceptListCount | - count of acceptList items |
availableLocales | - list of available locales to match |
status | ICU error code. Its input value must pass the U_SUCCESS() test, or else the function returns immediately. Check for U_FAILURE() on output or use with function chaining. (See User Guide for details.) |
U_CAPI int32_t uloc_acceptLanguageFromHTTP | ( | char * | result, |
int32_t | resultAvailable, | ||
UAcceptResult * | outResult, | ||
const char * | httpAcceptLanguage, | ||
UEnumeration * | availableLocales, | ||
UErrorCode * | status | ||
) |
Based on a HTTP header from a web browser and a list of available locales, determine an acceptable locale for the user.
This is a thin wrapper over C++ class LocaleMatcher.
result | - buffer to accept the result locale |
resultAvailable | the size of the result buffer. |
outResult | - An out parameter that contains the fallback status |
httpAcceptLanguage | - "Accept-Language:" header as per HTTP. |
availableLocales | - list of available locales to match |
status | ICU error code. Its input value must pass the U_SUCCESS() test, or else the function returns immediately. Check for U_FAILURE() on output or use with function chaining. (See User Guide for details.) |
U_CAPI int32_t uloc_addLikelySubtags | ( | const char * | localeID, |
char * | maximizedLocaleID, | ||
int32_t | maximizedLocaleIDCapacity, | ||
UErrorCode * | err | ||
) |
Add the likely subtags for a provided locale ID, per the algorithm described in the following CLDR technical report:
http://www.unicode.org/reports/tr35/#Likely_Subtags
If localeID is already in the maximal form, or there is no data available for maximization, it will be copied to the output buffer. For example, "und-Zzzz" cannot be maximized, since there is no reasonable maximization.
Examples:
"en" maximizes to "en_Latn_US"
"de" maximizes to "de_Latn_US"
"sr" maximizes to "sr_Cyrl_RS"
"sh" maximizes to "sr_Latn_RS" (Note this will not reverse.)
"zh_Hani" maximizes to "zh_Hans_CN" (Note this will not reverse.)
localeID | The locale to maximize |
maximizedLocaleID | The maximized locale |
maximizedLocaleIDCapacity | The capacity of the maximizedLocaleID buffer |
err | Error information if maximizing the locale failed. If the length of the localeID and the null-terminator is greater than the maximum allowed size, or the localeId is not well-formed, the error code is U_ILLEGAL_ARGUMENT_ERROR. |
U_CAPI int32_t uloc_canonicalize | ( | const char * | localeID, |
char * | name, | ||
int32_t | nameCapacity, | ||
UErrorCode * | err | ||
) |
Gets the full name for the specified locale.
Note: This has the effect of 'canonicalizing' the string to a certain extent. Upper and lower case are set as needed, and if the components were in 'POSIX' format they are changed to ICU format. It does NOT map aliased names in any way. See the top of this header file.
localeID | the locale to get the full name with |
name | the full name for localeID |
nameCapacity | the size of the name buffer to store the full name with |
err | error information if retrieving the full name failed |
U_CAPI int32_t uloc_countAvailable | ( | void | ) |
U_CAPI int32_t uloc_forLanguageTag | ( | const char * | langtag, |
char * | localeID, | ||
int32_t | localeIDCapacity, | ||
int32_t * | parsedLength, | ||
UErrorCode * | err | ||
) |
Returns a locale ID for the specified BCP47 language tag string.
If the specified language tag contains any ill-formed subtags, the first such subtag and all following subtags are ignored.
This implements the 'Language-Tag' production of BCP 47, and so supports legacy language tags (marked as “Type: grandfathered” in BCP 47) (regular and irregular) as well as private use language tags.
Private use tags are represented as 'x-whatever', and legacy tags are converted to their canonical replacements where they exist.
Note that a few legacy tags have no modern replacement; these will be converted using the fallback described in the first paragraph, so some information might be lost.
langtag | the input BCP47 language tag. |
localeID | the output buffer receiving a locale ID for the specified BCP47 language tag. |
localeIDCapacity | the size of the locale ID output buffer. |
parsedLength | if not NULL, successfully parsed length for the input language tag is set. |
err | error information if receiving the locald ID failed. |
U_CAPI const char * uloc_getAvailable | ( | int32_t | n | ) |
Gets the specified locale from a list of available locales.
This method corresponds to uloc_openAvailableByType called with the ULOC_AVAILABLE_DEFAULT type argument.
The return value is a pointer to an item of a locale name array. Both this array and the pointers it contains are owned by ICU and should not be deleted or written through by the caller. The locale name is terminated by a null pointer.
n | the specific locale name index of the available locale list; should not exceed the number returned by uloc_countAvailable. |
U_CAPI int32_t uloc_getBaseName | ( | const char * | localeID, |
char * | name, | ||
int32_t | nameCapacity, | ||
UErrorCode * | err | ||
) |
Gets the full name for the specified locale, like uloc_getName(), but without keywords.
Note: This has the effect of 'canonicalizing' the string to a certain extent. Upper and lower case are set as needed, and if the components were in 'POSIX' format they are changed to ICU format. It does NOT map aliased names in any way. See the top of this header file.
This API strips off the keyword part, so "de_DE\@collation=phonebook" will become "de_DE". This API supports preflighting.
localeID | the locale to get the full name with |
name | fill in buffer for the name without keywords. |
nameCapacity | capacity of the fill in buffer. |
err | error information if retrieving the full name failed |
U_CAPI ULayoutType uloc_getCharacterOrientation | ( | const char * | localeId, |
UErrorCode * | status | ||
) |
Get the layout character orientation for the specified locale.
localeId | locale name |
status | Error status |
U_CAPI int32_t uloc_getCountry | ( | const char * | localeID, |
char * | country, | ||
int32_t | countryCapacity, | ||
UErrorCode * | err | ||
) |
Gets the country code for the specified locale.
localeID | the locale to get the country code with |
country | the country code for localeID |
countryCapacity | the size of the country buffer to store the country code with |
err | error information if retrieving the country code failed |
U_CAPI const char * uloc_getDefault | ( | void | ) |
Gets ICU's default locale.
The returned string is a snapshot in time, and will remain valid and unchanged even when uloc_setDefault() is called. The returned storage is owned by ICU, and must not be altered or deleted by the caller.
U_CAPI int32_t uloc_getDisplayCountry | ( | const char * | locale, |
const char * | displayLocale, | ||
UChar * | country, | ||
int32_t | countryCapacity, | ||
UErrorCode * | status | ||
) |
Gets the country name suitable for display for the specified locale.
Warning: this is for the region part of a valid locale ID; it cannot just be the region code (like "FR"). To get the display name for a region alone, or for other options, use ULocaleDisplayNames instead.
locale | the locale to get the displayable country code with. NULL may be used to specify the default. |
displayLocale | Specifies the locale to be used to display the name. In other words, if the locale's language code is "en", passing Locale::getFrench() for inLocale would result in "Anglais", while passing Locale::getGerman() for inLocale would result in "Englisch". NULL may be used to specify the default. |
country | the displayable country code for localeID. |
countryCapacity | the size of the country buffer to store the displayable country code with. |
status | error information if retrieving the displayable country code failed. U_USING_DEFAULT_WARNING indicates that no data was found from the locale resources and a case canonicalized country code is placed into country as fallback. |
U_CAPI int32_t uloc_getDisplayKeyword | ( | const char * | keyword, |
const char * | displayLocale, | ||
UChar * | dest, | ||
int32_t | destCapacity, | ||
UErrorCode * | status | ||
) |
Gets the keyword name suitable for display for the specified locale.
E.g: for the locale string de_DE@collation=PHONEBOOK, this API gets the display string for the keyword collation. Usage: UErrorCode status = U_ZERO_ERROR; const char* keyword =NULL; int32_t keywordLen = 0; int32_t keywordCount = 0; UChar displayKeyword[256]; int32_t displayKeywordLen = 0; UEnumeration* keywordEnum = uloc_openKeywords("de_DE@collation=PHONEBOOK;calendar=TRADITIONAL", &status); for(keywordCount = uenum_count(keywordEnum, &status); keywordCount > 0 ; keywordCount–){ if(U_FAILURE(status)){ ...something went wrong so handle the error... break; } // the uenum_next returns NUL terminated string keyword = uenum_next(keywordEnum, &keywordLen, &status); displayKeywordLen = uloc_getDisplayKeyword(keyword, "en_US", displayKeyword, 256); ... do something interesting ..... } uenum_close(keywordEnum);
keyword | The keyword whose display string needs to be returned. |
displayLocale | Specifies the locale to be used to display the name. In other words, if the locale's language code is "en", passing Locale::getFrench() for inLocale would result in "Anglais", while passing Locale::getGerman() for inLocale would result in "Englisch". NULL may be used to specify the default. |
dest | the buffer to which the displayable keyword should be written. |
destCapacity | The size of the buffer (number of UChars). If it is 0, then dest may be NULL and the function will only return the length of the result without writing any of the result string (pre-flighting). |
status | error information if retrieving the displayable string failed. Should not be NULL and should not indicate failure on entry. U_USING_DEFAULT_WARNING indicates that no data was found from the locale resources and the keyword is placed into dest as fallback. |
U_CAPI int32_t uloc_getDisplayKeywordValue | ( | const char * | locale, |
const char * | keyword, | ||
const char * | displayLocale, | ||
UChar * | dest, | ||
int32_t | destCapacity, | ||
UErrorCode * | status | ||
) |
Gets the value of the keyword suitable for display for the specified locale.
E.g: for the locale string de_DE@collation=PHONEBOOK, this API gets the display string for PHONEBOOK, in the display locale, when "collation" is specified as the keyword.
locale | The locale to get the displayable variant code with. NULL may be used to specify the default. |
keyword | The keyword for whose value should be used. |
displayLocale | Specifies the locale to be used to display the name. In other words, if the locale's language code is "en", passing Locale::getFrench() for inLocale would result in "Anglais", while passing Locale::getGerman() for inLocale would result in "Englisch". NULL may be used to specify the default. |
dest | the buffer to which the displayable keyword should be written. |
destCapacity | The size of the buffer (number of UChars). If it is 0, then dest may be NULL and the function will only return the length of the result without writing any of the result string (pre-flighting). |
status | error information if retrieving the displayable string failed. Should not be NULL and must not indicate failure on entry. U_USING_DEFAULT_WARNING indicates that no data was found from the locale resources and the value of the keyword is placed into dest as fallback. |
U_CAPI int32_t uloc_getDisplayLanguage | ( | const char * | locale, |
const char * | displayLocale, | ||
UChar * | language, | ||
int32_t | languageCapacity, | ||
UErrorCode * | status | ||
) |
Gets the language name suitable for display for the specified locale.
locale | the locale to get the ISO language code with |
displayLocale | Specifies the locale to be used to display the name. In other words, if the locale's language code is "en", passing Locale::getFrench() for inLocale would result in "Anglais", while passing Locale::getGerman() for inLocale would result in "Englisch". |
language | the displayable language code for localeID |
languageCapacity | the size of the language buffer to store the displayable language code with. |
status | error information if retrieving the displayable language code failed. U_USING_DEFAULT_WARNING indicates that no data was found from the locale resources and a case canonicalized language code is placed into language as fallback. |
U_CAPI int32_t uloc_getDisplayName | ( | const char * | localeID, |
const char * | inLocaleID, | ||
UChar * | result, | ||
int32_t | maxResultSize, | ||
UErrorCode * | err | ||
) |
Gets the full name suitable for display for the specified locale.
localeID | the locale to get the displayable name with. NULL may be used to specify the default. |
inLocaleID | Specifies the locale to be used to display the name. In other words, if the locale's language code is "en", passing Locale::getFrench() for inLocale would result in "Anglais", while passing Locale::getGerman() for inLocale would result in "Englisch". NULL may be used to specify the default. |
result | the displayable name for localeID |
maxResultSize | the size of the name buffer to store the displayable full name with |
err | error information if retrieving the displayable name failed |
U_CAPI int32_t uloc_getDisplayScript | ( | const char * | locale, |
const char * | displayLocale, | ||
UChar * | script, | ||
int32_t | scriptCapacity, | ||
UErrorCode * | status | ||
) |
Gets the script name suitable for display for the specified locale.
locale | the locale to get the displayable script code with. NULL may be used to specify the default. |
displayLocale | Specifies the locale to be used to display the name. In other words, if the locale's language code is "en", passing Locale::getFrench() for inLocale would result in "", while passing Locale::getGerman() for inLocale would result in "". NULL may be used to specify the default. |
script | the displayable script for the localeID. |
scriptCapacity | the size of the script buffer to store the displayable script code with. |
status | error information if retrieving the displayable script code failed. U_USING_DEFAULT_WARNING indicates that no data was found from the locale resources and a case canonicalized script code is placed into script as fallback. |
U_CAPI int32_t uloc_getDisplayVariant | ( | const char * | locale, |
const char * | displayLocale, | ||
UChar * | variant, | ||
int32_t | variantCapacity, | ||
UErrorCode * | status | ||
) |
Gets the variant name suitable for display for the specified locale.
locale | the locale to get the displayable variant code with. NULL may be used to specify the default. |
displayLocale | Specifies the locale to be used to display the name. In other words, if the locale's language code is "en", passing Locale::getFrench() for inLocale would result in "Anglais", while passing Locale::getGerman() for inLocale would result in "Englisch". NULL may be used to specify the default. |
variant | the displayable variant code for localeID. |
variantCapacity | the size of the variant buffer to store the displayable variant code with. |
status | error information if retrieving the displayable variant code failed. U_USING_DEFAULT_WARNING indicates that no data was found from the locale resources and a case canonicalized variant code is placed into variant as fallback. |
U_CAPI const char * uloc_getISO3Country | ( | const char * | localeID | ) |
Gets the ISO country code for the specified locale.
localeID | the locale to get the ISO country code with |
U_CAPI const char * uloc_getISO3Language | ( | const char * | localeID | ) |
Gets the ISO language code for the specified locale.
localeID | the locale to get the ISO language code with |
U_CAPI const char *const * uloc_getISOCountries | ( | void | ) |
Gets a list of all available 2-letter country codes defined in ISO 639.
This is a pointer to an array of pointers to arrays of char. All of these pointers are owned by ICU– do not delete them, and do not write through them. The array is terminated with a null pointer.
U_CAPI const char *const * uloc_getISOLanguages | ( | void | ) |
Gets a list of all available 2-letter language codes defined in ISO 639, plus additional 3-letter codes determined to be useful for locale generation as defined by Unicode CLDR.
This is a pointer to an array of pointers to arrays of char. All of these pointers are owned by ICU– do not delete them, and do not write through them. The array is terminated with a null pointer.
U_CAPI int32_t uloc_getKeywordValue | ( | const char * | localeID, |
const char * | keywordName, | ||
char * | buffer, | ||
int32_t | bufferCapacity, | ||
UErrorCode * | status | ||
) |
Get the value for a keyword.
Locale name does not need to be normalized.
localeID | locale name containing the keyword ("de_DE@currency=EURO;collation=PHONEBOOK") |
keywordName | name of the keyword for which we want the value; must not be NULL or empty, and must consist only of [A-Za-z0-9]. Case insensitive. |
buffer | receiving buffer |
bufferCapacity | capacity of receiving buffer |
status | containing error code: e.g. buffer not big enough or ill-formed localeID or keywordName parameters. |
U_CAPI int32_t uloc_getLanguage | ( | const char * | localeID, |
char * | language, | ||
int32_t | languageCapacity, | ||
UErrorCode * | err | ||
) |
Gets the language code for the specified locale.
localeID | the locale to get the ISO language code with |
language | the language code for localeID |
languageCapacity | the size of the language buffer to store the language code with |
err | error information if retrieving the language code failed |
U_CAPI uint32_t uloc_getLCID | ( | const char * | localeID | ) |
Gets the Win32 LCID value for the specified locale.
If the ICU locale is not recognized by Windows, 0 will be returned.
LCIDs were deprecated with Windows Vista and Microsoft recommends that developers use BCP47 style tags instead (uloc_toLanguageTag).
localeID | the locale to get the Win32 LCID value with |
U_CAPI ULayoutType uloc_getLineOrientation | ( | const char * | localeId, |
UErrorCode * | status | ||
) |
Get the layout line orientation for the specified locale.
localeId | locale name |
status | Error status |
U_CAPI int32_t uloc_getLocaleForLCID | ( | uint32_t | hostID, |
char * | locale, | ||
int32_t | localeCapacity, | ||
UErrorCode * | status | ||
) |
Gets the ICU locale ID for the specified Win32 LCID value.
hostID | the Win32 LCID to translate |
locale | the output buffer for the ICU locale ID, which will be NUL-terminated if there is room. |
localeCapacity | the size of the output buffer |
status | an error is returned if the LCID is unrecognized or the output buffer is too small |
U_CAPI int32_t uloc_getName | ( | const char * | localeID, |
char * | name, | ||
int32_t | nameCapacity, | ||
UErrorCode * | err | ||
) |
Gets the full name for the specified locale.
Note: This has the effect of 'canonicalizing' the ICU locale ID to a certain extent. Upper and lower case are set as needed. It does NOT map aliased names in any way. See the top of this header file. This API supports preflighting.
localeID | the locale to get the full name with |
name | fill in buffer for the name without keywords. |
nameCapacity | capacity of the fill in buffer. |
err | error information if retrieving the full name failed |
U_CAPI int32_t uloc_getParent | ( | const char * | localeID, |
char * | parent, | ||
int32_t | parentCapacity, | ||
UErrorCode * | err | ||
) |
Truncate the locale ID string to get the parent locale ID.
Copies the part of the string before the last underscore. The parent locale ID will be an empty string if there is no underscore, or if there is only one underscore at localeID[0].
localeID | Input locale ID string. |
parent | Output string buffer for the parent locale ID. |
parentCapacity | Size of the output buffer. |
err | A UErrorCode value. |
U_CAPI int32_t uloc_getScript | ( | const char * | localeID, |
char * | script, | ||
int32_t | scriptCapacity, | ||
UErrorCode * | err | ||
) |
Gets the script code for the specified locale.
localeID | the locale to get the ISO language code with |
script | the language code for localeID |
scriptCapacity | the size of the language buffer to store the language code with |
err | error information if retrieving the language code failed |
U_CAPI int32_t uloc_getVariant | ( | const char * | localeID, |
char * | variant, | ||
int32_t | variantCapacity, | ||
UErrorCode * | err | ||
) |
Gets the variant code for the specified locale.
localeID | the locale to get the variant code with |
variant | the variant code for localeID |
variantCapacity | the size of the variant buffer to store the variant code with |
err | error information if retrieving the variant code failed |
Returns whether the locale's script is written right-to-left.
If there is no script subtag, then the likely script is used, see uloc_addLikelySubtags(). If no likely script is known, then false is returned.
A script is right-to-left according to the CLDR script metadata which corresponds to whether the script's letters have Bidi_Class=R or AL.
Returns true for "ar" and "en-Hebr", false for "zh" and "fa-Cyrl".
locale | input locale ID |
U_CAPI int32_t uloc_minimizeSubtags | ( | const char * | localeID, |
char * | minimizedLocaleID, | ||
int32_t | minimizedLocaleIDCapacity, | ||
UErrorCode * | err | ||
) |
Minimize the subtags for a provided locale ID, per the algorithm described in the following CLDR technical report:
http://www.unicode.org/reports/tr35/#Likely_Subtags
If localeID is already in the minimal form, or there is no data available for minimization, it will be copied to the output buffer. Since the minimization algorithm relies on proper maximization, see the comments for uloc_addLikelySubtags for reasons why there might not be any data.
Examples:
"en_Latn_US" minimizes to "en"
"de_Latn_US" minimizes to "de"
"sr_Cyrl_RS" minimizes to "sr"
"zh_Hant_TW" minimizes to "zh_TW" (The region is preferred to the script, and minimizing to "zh" would imply "zh_Hans_CN".)
localeID | The locale to minimize |
minimizedLocaleID | The minimized locale |
minimizedLocaleIDCapacity | The capacity of the minimizedLocaleID buffer |
err | Error information if minimizing the locale failed. If the length of the localeID and the null-terminator is greater than the maximum allowed size, or the localeId is not well-formed, the error code is U_ILLEGAL_ARGUMENT_ERROR. |
U_CAPI UEnumeration * uloc_openAvailableByType | ( | ULocAvailableType | type, |
UErrorCode * | status | ||
) |
Gets a list of available locales according to the type argument, allowing the user to access different sets of supported locales in ICU.
The returned UEnumeration must be closed by the caller.
type | Type choice from ULocAvailableType. |
status | Set if an error occurred. |
U_CAPI UEnumeration * uloc_openKeywords | ( | const char * | localeID, |
UErrorCode * | status | ||
) |
Gets an enumeration of keywords for the specified locale.
Enumeration must get disposed of by the client using uenum_close function.
localeID | the locale to get the variant code with |
status | error information if retrieving the keywords failed |
U_CAPI void uloc_setDefault | ( | const char * | localeID, |
UErrorCode * | status | ||
) |
Sets ICU's default locale.
By default (without calling this function), ICU's default locale will be based on information obtained from the underlying system environment.
Changes to ICU's default locale do not propagate back to the system environment.
Changes to ICU's default locale to not affect any ICU services that may already be open based on the previous default locale value.
localeID | the new ICU default locale. A value of NULL will try to get the system's default locale. |
status | the error information if the setting of default locale fails |
U_CAPI int32_t uloc_setKeywordValue | ( | const char * | keywordName, |
const char * | keywordValue, | ||
char * | buffer, | ||
int32_t | bufferCapacity, | ||
UErrorCode * | status | ||
) |
Sets or removes the value of the specified keyword.
For removing all keywords, use uloc_getBaseName().
NOTE: Unlike almost every other ICU function which takes a buffer, this function will NOT truncate the output text, and will not update the buffer with unterminated text setting a status of U_STRING_NOT_TERMINATED_WARNING. If a BUFFER_OVERFLOW_ERROR is received, it means a terminated version of the updated locale ID would not fit in the buffer, and the original buffer is untouched. This is done to prevent incorrect or possibly even malformed locales from being generated and used.
keywordName | name of the keyword to be set; must not be NULL or empty, and must consist only of [A-Za-z0-9]. Case insensitive. |
keywordValue | value of the keyword to be set. If 0-length or NULL, will result in the keyword being removed; no error is given if that keyword does not exist. Otherwise, must consist only of [A-Za-z0-9] and [/_+-]. |
buffer | input buffer containing well-formed locale ID to be modified. |
bufferCapacity | capacity of receiving buffer |
status | containing error code: e.g. buffer not big enough or ill-formed keywordName or keywordValue parameters, or ill-formed locale ID in buffer on input. |
U_CAPI int32_t uloc_toLanguageTag | ( | const char * | localeID, |
char * | langtag, | ||
int32_t | langtagCapacity, | ||
UBool | strict, | ||
UErrorCode * | err | ||
) |
Returns a well-formed language tag for this locale ID.
Note: When strict
is false, any locale fields which do not satisfy the BCP47 syntax requirement will be omitted from the result. When strict
is true, this function sets U_ILLEGAL_ARGUMENT_ERROR to the err
if any locale fields do not satisfy the BCP47 syntax requirement.
localeID | the input locale ID |
langtag | the output buffer receiving BCP47 language tag for the locale ID. |
langtagCapacity | the size of the BCP47 language tag output buffer. |
strict | boolean value indicating if the function returns an error for an ill-formed input locale ID. |
err | error information if receiving the language tag failed. |
U_CAPI const char * uloc_toLegacyKey | ( | const char * | keyword | ) |
Converts the specified keyword (BCP 47 Unicode locale extension key, or legacy key) to the legacy key.
For example, legacy key "collation" is returned for the input BCP 47 Unicode locale extension key "co".
keyword | the input locale keyword (either BCP 47 Unicode locale extension key or legacy key). |
U_CAPI const char * uloc_toLegacyType | ( | const char * | keyword, |
const char * | value | ||
) |
Converts the specified keyword value (BCP 47 Unicode locale extension type, or legacy type or type alias) to the canonical legacy type.
For example, the legacy type "phonebook" is returned for the input BCP 47 Unicode locale extension type "phonebk" with the keyword "collation" (or "co").
When the specified keyword is not recognized, but the specified value satisfies the syntax of legacy key, or when the specified keyword allows 'variable' type and the specified value satisfies the syntax, then the pointer to the input type value itself will be returned. For example, uloc_toLegacyType("Foo", "Bar")
returns "Bar", uloc_toLegacyType("vt", "00A4")
returns "00A4".
keyword | the locale keyword (either legacy keyword such as "collation" or BCP 47 Unicode locale extension key such as "co"). |
value | the locale keyword value (either BCP 47 Unicode locale extension type such as "phonebk" or legacy keyword value such as "phonebook"). |
U_CAPI const char * uloc_toUnicodeLocaleKey | ( | const char * | keyword | ) |
Converts the specified keyword (legacy key, or BCP 47 Unicode locale extension key) to the equivalent BCP 47 Unicode locale extension key.
For example, BCP 47 Unicode locale extension key "co" is returned for the input keyword "collation".
When the specified keyword is unknown, but satisfies the BCP syntax, then the pointer to the input keyword itself will be returned. For example, uloc_toUnicodeLocaleKey("ZZ")
returns "ZZ".
keyword | the input locale keyword (either legacy key such as "collation" or BCP 47 Unicode locale extension key such as "co"). |
U_CAPI const char * uloc_toUnicodeLocaleType | ( | const char * | keyword, |
const char * | value | ||
) |
Converts the specified keyword value (legacy type, or BCP 47 Unicode locale extension type) to the well-formed BCP 47 Unicode locale extension type for the specified keyword (category).
For example, BCP 47 Unicode locale extension type "phonebk" is returned for the input keyword value "phonebook", with the keyword "collation" (or "co").
When the specified keyword is not recognized, but the specified value satisfies the syntax of the BCP 47 Unicode locale extension type, or when the specified keyword allows 'variable' type and the specified value satisfies the syntax, then the pointer to the input type value itself will be returned. For example, uloc_toUnicodeLocaleType("Foo", "Bar")
returns "Bar", uloc_toUnicodeLocaleType("variableTop", "00A4")
returns "00A4".
keyword | the locale keyword (either legacy key such as "collation" or BCP 47 Unicode locale extension key such as "co"). |
value | the locale keyword value (either legacy type such as "phonebook" or BCP 47 Unicode locale extension type such as "phonebk"). |