Home | History | Annotate | Download | only in unicode
      1 /*
      2 *****************************************************************************************
      3 * Copyright (C) 2013, International Business Machines
      4 * Corporation and others. All Rights Reserved.
      5 *****************************************************************************************
      6 */
      7 
      8 #ifndef UREGION_H
      9 #define UREGION_H
     10 
     11 #include "unicode/utypes.h"
     12 #include "unicode/uenum.h"
     13 
     14 /**
     15  * \file
     16  * \brief C API: URegion (territory containment and mapping)
     17  *
     18  * URegion objects represent data associated with a particular Unicode Region Code, also known as a
     19  * Unicode Region Subtag, which is defined based upon the BCP 47 standard. These include:
     20  * * Two-letter codes defined by ISO 3166-1, with special LDML treatment of certain private-use or
     21  *   reserved codes;
     22  * * A subset of 3-digit numeric codes defined by UN M.49.
     23  * URegion objects can also provide mappings to and from additional codes. There are different types
     24  * of regions that are important to distinguish:
     25  * <p>
     26  * Macroregion - A code for a "macro geographical (continental) region, geographical sub-region, or
     27  * selected economic and other grouping" as defined in UN M.49. These are typically 3-digit codes,
     28  * but contain some 2-letter codes for LDML extensions, such as "QO" for Outlying Oceania.
     29  * Macroregions are represented in ICU by one of three region types: WORLD (code 001),
     30  * CONTINENTS (regions contained directly by WORLD), and SUBCONTINENTS (regions contained directly
     31  * by a continent ).
     32  * <p>
     33  * TERRITORY - A Region that is not a Macroregion. These are typically codes for countries, but also
     34  * include areas that are not separate countries, such as the code "AQ" for Antarctica or the code
     35  * "HK" for Hong Kong (SAR China). Overseas dependencies of countries may or may not have separate
     36  * codes. The codes are typically 2-letter codes aligned with ISO 3166, but BCP47 allows for the use
     37  * of 3-digit codes in the future.
     38  * <p>
     39  * UNKNOWN - The code ZZ is defined by Unicode LDML for use in indicating that region is unknown,
     40  * or that the value supplied as a region was invalid.
     41  * <p>
     42  * DEPRECATED - Region codes that have been defined in the past but are no longer in modern usage,
     43  * usually due to a country splitting into multiple territories or changing its name.
     44  * <p>
     45  * GROUPING - A widely understood grouping of territories that has a well defined membership such
     46  * that a region code has been assigned for it.  Some of these are UN M.49 codes that don't fall into
     47  * the world/continent/sub-continent hierarchy, while others are just well-known groupings that have
     48  * their own region code. Region "EU" (European Union) is one such region code that is a grouping.
     49  * Groupings will never be returned by the uregion_getContainingRegion, since a different type of region
     50  * (WORLD, CONTINENT, or SUBCONTINENT) will always be the containing region instead.
     51  *
     52  * URegion objects are const/immutable, owned and maintained by ICU itself, so there are not functions
     53  * to open or close them.
     54  */
     55 
     56 #ifndef U_HIDE_DRAFT_API
     57 /**
     58  * URegionType is an enumeration defining the different types of regions.  Current possible
     59  * values are URGN_WORLD, URGN_CONTINENT, URGN_SUBCONTINENT, URGN_TERRITORY, URGN_GROUPING,
     60  * URGN_DEPRECATED, and URGN_UNKNOWN.
     61  *
     62  * @draft ICU 51
     63  */
     64 typedef enum URegionType {
     65     /**
     66      * Type representing the unknown region.
     67      * @draft ICU 51
     68      */
     69     URGN_UNKNOWN,
     70 
     71     /**
     72      * Type representing a territory.
     73      * @draft ICU 51
     74      */
     75     URGN_TERRITORY,
     76 
     77     /**
     78      * Type representing the whole world.
     79      * @draft ICU 51
     80      */
     81     URGN_WORLD,
     82 
     83     /**
     84      * Type representing a continent.
     85      * @draft ICU 51
     86      */
     87     URGN_CONTINENT,
     88 
     89     /**
     90      * Type representing a sub-continent.
     91      * @draft ICU 51
     92      */
     93     URGN_SUBCONTINENT,
     94 
     95     /**
     96      * Type representing a grouping of territories that is not to be used in
     97      * the normal WORLD/CONTINENT/SUBCONTINENT/TERRITORY containment tree.
     98      * @draft ICU 51
     99      */
    100     URGN_GROUPING,
    101 
    102     /**
    103      * Type representing a region whose code has been deprecated, usually
    104      * due to a country splitting into multiple territories or changing its name.
    105      * @draft ICU 51
    106      */
    107     URGN_DEPRECATED,
    108 
    109     /**
    110      * Maximum value for this unumeration.
    111      * @draft ICU 51
    112      */
    113     URGN_LIMIT
    114 } URegionType;
    115 #endif  /* U_HIDE_DRAFT_API */
    116 
    117 #if !UCONFIG_NO_FORMATTING
    118 
    119 #ifndef U_HIDE_DRAFT_API
    120 
    121 /**
    122  * Opaque URegion object for use in C programs.
    123  * @draft ICU 52
    124  */
    125 struct URegion;
    126 typedef struct URegion URegion; /**< @draft ICU 52 */
    127 
    128 /**
    129  * Returns a pointer to a URegion for the specified region code: A 2-letter or 3-letter ISO 3166
    130  * code, UN M.49 numeric code (superset of ISO 3166 numeric codes), or other valid Unicode Region
    131  * Code as defined by the LDML specification. The code will be canonicalized internally. If the
    132  * region code is NULL or not recognized, the appropriate error code will be set
    133  * (U_ILLEGAL_ARGUMENT_ERROR).
    134  * @draft ICU 52
    135  */
    136 U_DRAFT const URegion* U_EXPORT2
    137 uregion_getRegionFromCode(const char *regionCode, UErrorCode *status);
    138 
    139 /**
    140  * Returns a pointer to a URegion for the specified numeric region code. If the numeric region
    141  * code is not recognized, the appropriate error code will be set (U_ILLEGAL_ARGUMENT_ERROR).
    142  * @draft ICU 52
    143  */
    144 U_DRAFT const URegion* U_EXPORT2
    145 uregion_getRegionFromNumericCode (int32_t code, UErrorCode *status);
    146 
    147 /**
    148  * Returns an enumeration over the canonical codes of all known regions that match the given type.
    149  * The enumeration must be closed with with uenum_close().
    150  * @draft ICU 52
    151  */
    152 U_DRAFT UEnumeration* U_EXPORT2
    153 uregion_getAvailable(URegionType type, UErrorCode *status);
    154 
    155 /**
    156  * Returns true if the specified uregion is equal to the specified otherRegion.
    157  * @draft ICU 52
    158  */
    159 U_DRAFT UBool U_EXPORT2
    160 uregion_areEqual(const URegion* uregion, const URegion* otherRegion);
    161 
    162 /**
    163  * Returns a pointer to the URegion that contains the specified uregion. Returns NULL if the
    164  * specified uregion is code "001" (World) or "ZZ" (Unknown region). For example, calling
    165  * this method with region "IT" (Italy) returns the URegion for "039" (Southern Europe).
    166  * @draft ICU 52
    167  */
    168 U_DRAFT const URegion* U_EXPORT2
    169 uregion_getContainingRegion(const URegion* uregion);
    170 
    171 /**
    172  * Return a pointer to the URegion that geographically contains this uregion and matches the
    173  * specified type, moving multiple steps up the containment chain if necessary. Returns NULL if no
    174  * containing region can be found that matches the specified type. Will return NULL if URegionType
    175  * is URGN_GROUPING, URGN_DEPRECATED, or URGN_UNKNOWN which are not appropriate for this API.
    176  * For example, calling this method with uregion "IT" (Italy) for type URGN_CONTINENT returns the
    177  * URegion "150" (Europe).
    178  * @draft ICU 52
    179  */
    180 U_DRAFT const URegion* U_EXPORT2
    181 uregion_getContainingRegionOfType(const URegion* uregion, URegionType type);
    182 
    183 /**
    184  * Return an enumeration over the canonical codes of all the regions that are immediate children
    185  * of the specified uregion in the region hierarchy. These returned regions could be either macro
    186  * regions, territories, or a mixture of the two, depending on the containment data as defined in
    187  * CLDR. This API returns NULL if this uregion doesn't have any sub-regions. For example, calling
    188  * this function for uregion "150" (Europe) returns an enumeration containing the various
    189  * sub-regions of Europe: "039" (Southern Europe), "151" (Eastern Europe), "154" (Northern Europe),
    190  * and "155" (Western Europe). The enumeration must be closed with with uenum_close().
    191  * @draft ICU 52
    192  */
    193 U_DRAFT UEnumeration* U_EXPORT2
    194 uregion_getContainedRegions(const URegion* uregion, UErrorCode *status);
    195 
    196 /**
    197  * Returns an enumeration over the canonical codes of all the regions that are children of the
    198  * specified uregion anywhere in the region hierarchy and match the given type. This API may return
    199  * an empty enumeration if this uregion doesn't have any sub-regions that match the given type.
    200  * For example, calling this method with region "150" (Europe) and type URGN_TERRITORY" returns an
    201  * enumeration containing all the territories in Europe: "FR" (France), "IT" (Italy), "DE" (Germany),
    202  * etc. The enumeration must be closed with with uenum_close().
    203  * @draft ICU 52
    204  */
    205 U_DRAFT UEnumeration* U_EXPORT2
    206 uregion_getContainedRegionsOfType(const URegion* uregion, URegionType type, UErrorCode *status);
    207 
    208 /**
    209  * Returns true if the specified uregion contains the specified otherRegion anywhere in the region
    210  * hierarchy.
    211  * @draft ICU 52
    212  */
    213 U_DRAFT UBool U_EXPORT2
    214 uregion_contains(const URegion* uregion, const URegion* otherRegion);
    215 
    216 /**
    217  * If the specified uregion is deprecated, returns an enumeration over the canonical codes of the
    218  * regions that are the preferred replacement regions for the specified uregion. If the specified
    219  * uregion is not deprecated, returns NULL. For example, calling this method with uregion
    220  * "SU" (Soviet Union) returns a list of the regions containing "RU" (Russia), "AM" (Armenia),
    221  * "AZ" (Azerbaijan), etc... The enumeration must be closed with with uenum_close().
    222  * @draft ICU 52
    223  */
    224 U_DRAFT UEnumeration* U_EXPORT2
    225 uregion_getPreferredValues(const URegion* uregion, UErrorCode *status);
    226 
    227 /**
    228  * Returns the specified uregion's canonical code.
    229  * @draft ICU 52
    230  */
    231 U_DRAFT const char* U_EXPORT2
    232 uregion_getRegionCode(const URegion* uregion);
    233 
    234 /**
    235  * Returns the specified uregion's numeric code, or a negative value if there is no numeric code
    236  * for the specified uregion.
    237  * @draft ICU 52
    238  */
    239 U_DRAFT int32_t U_EXPORT2
    240 uregion_getNumericCode(const URegion* uregion);
    241 
    242 /**
    243  * Returns the URegionType of the specified uregion.
    244  * @draft ICU 52
    245  */
    246 U_DRAFT URegionType U_EXPORT2
    247 uregion_getType(const URegion* uregion);
    248 
    249 #endif  /* U_HIDE_DRAFT_API */
    250 
    251 #endif /* #if !UCONFIG_NO_FORMATTING */
    252 
    253 #endif
    254