1 /*
2 *****************************************************************************************
3 * Copyright (C) 2014, 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 /**
57  * URegionType is an enumeration defining the different types of regions.  Current possible
58  * values are URGN_WORLD, URGN_CONTINENT, URGN_SUBCONTINENT, URGN_TERRITORY, URGN_GROUPING,
59  * URGN_DEPRECATED, and URGN_UNKNOWN.
60  *
61  * @stable ICU 51
62  */
63 typedef enum URegionType {
64     /**
65      * Type representing the unknown region.
66      * @stable ICU 51
67      */
68     URGN_UNKNOWN,
69 
70     /**
71      * Type representing a territory.
72      * @stable ICU 51
73      */
74     URGN_TERRITORY,
75 
76     /**
77      * Type representing the whole world.
78      * @stable ICU 51
79      */
80     URGN_WORLD,
81 
82     /**
83      * Type representing a continent.
84      * @stable ICU 51
85      */
86     URGN_CONTINENT,
87 
88     /**
89      * Type representing a sub-continent.
90      * @stable ICU 51
91      */
92     URGN_SUBCONTINENT,
93 
94     /**
95      * Type representing a grouping of territories that is not to be used in
96      * the normal WORLD/CONTINENT/SUBCONTINENT/TERRITORY containment tree.
97      * @stable ICU 51
98      */
99     URGN_GROUPING,
100 
101     /**
102      * Type representing a region whose code has been deprecated, usually
103      * due to a country splitting into multiple territories or changing its name.
104      * @stable ICU 51
105      */
106     URGN_DEPRECATED,
107 
108     /**
109      * Maximum value for this unumeration.
110      * @stable ICU 51
111      */
112     URGN_LIMIT
113 } URegionType;
114 
115 #if !UCONFIG_NO_FORMATTING
116 
117 /**
118  * Opaque URegion object for use in C programs.
119  * @stable ICU 52
120  */
121 struct URegion;
122 typedef struct URegion URegion; /**< @stable ICU 52 */
123 
124 /**
125  * Returns a pointer to a URegion for the specified region code: A 2-letter or 3-letter ISO 3166
126  * code, UN M.49 numeric code (superset of ISO 3166 numeric codes), or other valid Unicode Region
127  * Code as defined by the LDML specification. The code will be canonicalized internally. If the
128  * region code is NULL or not recognized, the appropriate error code will be set
129  * (U_ILLEGAL_ARGUMENT_ERROR).
130  * @stable ICU 52
131  */
132 U_STABLE const URegion* U_EXPORT2
133 uregion_getRegionFromCode(const char *regionCode, UErrorCode *status);
134 
135 /**
136  * Returns a pointer to a URegion for the specified numeric region code. If the numeric region
137  * code is not recognized, the appropriate error code will be set (U_ILLEGAL_ARGUMENT_ERROR).
138  * @stable ICU 52
139  */
140 U_STABLE const URegion* U_EXPORT2
141 uregion_getRegionFromNumericCode (int32_t code, UErrorCode *status);
142 
143 /**
144  * Returns an enumeration over the canonical codes of all known regions that match the given type.
145  * The enumeration must be closed with with uenum_close().
146  * @stable ICU 52
147  */
148 U_STABLE UEnumeration* U_EXPORT2
149 uregion_getAvailable(URegionType type, UErrorCode *status);
150 
151 /**
152  * Returns true if the specified uregion is equal to the specified otherRegion.
153  * @stable ICU 52
154  */
155 U_STABLE UBool U_EXPORT2
156 uregion_areEqual(const URegion* uregion, const URegion* otherRegion);
157 
158 /**
159  * Returns a pointer to the URegion that contains the specified uregion. Returns NULL if the
160  * specified uregion is code "001" (World) or "ZZ" (Unknown region). For example, calling
161  * this method with region "IT" (Italy) returns the URegion for "039" (Southern Europe).
162  * @stable ICU 52
163  */
164 U_STABLE const URegion* U_EXPORT2
165 uregion_getContainingRegion(const URegion* uregion);
166 
167 /**
168  * Return a pointer to the URegion that geographically contains this uregion and matches the
169  * specified type, moving multiple steps up the containment chain if necessary. Returns NULL if no
170  * containing region can be found that matches the specified type. Will return NULL if URegionType
171  * is URGN_GROUPING, URGN_DEPRECATED, or URGN_UNKNOWN which are not appropriate for this API.
172  * For example, calling this method with uregion "IT" (Italy) for type URGN_CONTINENT returns the
173  * URegion "150" (Europe).
174  * @stable ICU 52
175  */
176 U_STABLE const URegion* U_EXPORT2
177 uregion_getContainingRegionOfType(const URegion* uregion, URegionType type);
178 
179 /**
180  * Return an enumeration over the canonical codes of all the regions that are immediate children
181  * of the specified uregion in the region hierarchy. These returned regions could be either macro
182  * regions, territories, or a mixture of the two, depending on the containment data as defined in
183  * CLDR. This API returns NULL if this uregion doesn't have any sub-regions. For example, calling
184  * this function for uregion "150" (Europe) returns an enumeration containing the various
185  * sub-regions of Europe: "039" (Southern Europe), "151" (Eastern Europe), "154" (Northern Europe),
186  * and "155" (Western Europe). The enumeration must be closed with with uenum_close().
187  * @stable ICU 52
188  */
189 U_STABLE UEnumeration* U_EXPORT2
190 uregion_getContainedRegions(const URegion* uregion, UErrorCode *status);
191 
192 /**
193  * Returns an enumeration over the canonical codes of all the regions that are children of the
194  * specified uregion anywhere in the region hierarchy and match the given type. This API may return
195  * an empty enumeration if this uregion doesn't have any sub-regions that match the given type.
196  * For example, calling this method with region "150" (Europe) and type URGN_TERRITORY" returns an
197  * enumeration containing all the territories in Europe: "FR" (France), "IT" (Italy), "DE" (Germany),
198  * etc. The enumeration must be closed with with uenum_close().
199  * @stable ICU 52
200  */
201 U_STABLE UEnumeration* U_EXPORT2
202 uregion_getContainedRegionsOfType(const URegion* uregion, URegionType type, UErrorCode *status);
203 
204 /**
205  * Returns true if the specified uregion contains the specified otherRegion anywhere in the region
206  * hierarchy.
207  * @stable ICU 52
208  */
209 U_STABLE UBool U_EXPORT2
210 uregion_contains(const URegion* uregion, const URegion* otherRegion);
211 
212 /**
213  * If the specified uregion is deprecated, returns an enumeration over the canonical codes of the
214  * regions that are the preferred replacement regions for the specified uregion. If the specified
215  * uregion is not deprecated, returns NULL. For example, calling this method with uregion
216  * "SU" (Soviet Union) returns a list of the regions containing "RU" (Russia), "AM" (Armenia),
217  * "AZ" (Azerbaijan), etc... The enumeration must be closed with with uenum_close().
218  * @stable ICU 52
219  */
220 U_STABLE UEnumeration* U_EXPORT2
221 uregion_getPreferredValues(const URegion* uregion, UErrorCode *status);
222 
223 /**
224  * Returns the specified uregion's canonical code.
225  * @stable ICU 52
226  */
227 U_STABLE const char* U_EXPORT2
228 uregion_getRegionCode(const URegion* uregion);
229 
230 /**
231  * Returns the specified uregion's numeric code, or a negative value if there is no numeric code
232  * for the specified uregion.
233  * @stable ICU 52
234  */
235 U_STABLE int32_t U_EXPORT2
236 uregion_getNumericCode(const URegion* uregion);
237 
238 /**
239  * Returns the URegionType of the specified uregion.
240  * @stable ICU 52
241  */
242 U_STABLE URegionType U_EXPORT2
243 uregion_getType(const URegion* uregion);
244 
245 
246 #endif /* #if !UCONFIG_NO_FORMATTING */
247 
248 #endif
249