1// © 2016 and later: Unicode, Inc. and others.
2// License & terms of use: http://www.unicode.org/copyright.html
3/*
4*****************************************************************************************
5* Copyright (C) 2014, International Business Machines
6* Corporation and others. All Rights Reserved.
7*****************************************************************************************
8*/
9
10#ifndef UREGION_H
11#define UREGION_H
12
13#include "unicode/utypes.h"
14#include "unicode/uenum.h"
15
16/**
17 * \file
18 * \brief C API: URegion (territory containment and mapping)
19 *
20 * URegion objects represent data associated with a particular Unicode Region Code, also known as a
21 * Unicode Region Subtag, which is defined based upon the BCP 47 standard. These include:
22 * * Two-letter codes defined by ISO 3166-1, with special LDML treatment of certain private-use or
23 * reserved codes;
24 * * A subset of 3-digit numeric codes defined by UN M.49.
25 * URegion objects can also provide mappings to and from additional codes. There are different types
26 * of regions that are important to distinguish:
27 * <p>
28 * Macroregion - A code for a "macro geographical (continental) region, geographical sub-region, or
29 * selected economic and other grouping" as defined in UN M.49. These are typically 3-digit codes,
30 * but contain some 2-letter codes for LDML extensions, such as "QO" for Outlying Oceania.
31 * Macroregions are represented in ICU by one of three region types: WORLD (code 001),
32 * CONTINENTS (regions contained directly by WORLD), and SUBCONTINENTS (regions contained directly
33 * by a continent ).
34 * <p>
35 * TERRITORY - A Region that is not a Macroregion. These are typically codes for countries, but also
36 * include areas that are not separate countries, such as the code "AQ" for Antarctica or the code
37 * "HK" for Hong Kong (SAR China). Overseas dependencies of countries may or may not have separate
38 * codes. The codes are typically 2-letter codes aligned with ISO 3166, but BCP47 allows for the use
39 * of 3-digit codes in the future.
40 * <p>
41 * UNKNOWN - The code ZZ is defined by Unicode LDML for use in indicating that region is unknown,
42 * or that the value supplied as a region was invalid.
43 * <p>
44 * DEPRECATED - Region codes that have been defined in the past but are no longer in modern usage,
45 * usually due to a country splitting into multiple territories or changing its name.
46 * <p>
47 * GROUPING - A widely understood grouping of territories that has a well defined membership such
48 * that a region code has been assigned for it. Some of these are UN M.49 codes that don't fall into
49 * the world/continent/sub-continent hierarchy, while others are just well-known groupings that have
50 * their own region code. Region "EU" (European Union) is one such region code that is a grouping.
51 * Groupings will never be returned by the uregion_getContainingRegion, since a different type of region
52 * (WORLD, CONTINENT, or SUBCONTINENT) will always be the containing region instead.
53 *
54 * URegion objects are const/immutable, owned and maintained by ICU itself, so there are not functions
55 * to open or close them.
56 */
57
58/**
59 * URegionType is an enumeration defining the different types of regions. Current possible
60 * values are URGN_WORLD, URGN_CONTINENT, URGN_SUBCONTINENT, URGN_TERRITORY, URGN_GROUPING,
61 * URGN_DEPRECATED, and URGN_UNKNOWN.
62 *
63 * @stable ICU 51
64 */
65typedef enum URegionType {
66 /**
67 * Type representing the unknown region.
68 * @stable ICU 51
69 */
70 URGN_UNKNOWN,
71
72 /**
73 * Type representing a territory.
74 * @stable ICU 51
75 */
76 URGN_TERRITORY,
77
78 /**
79 * Type representing the whole world.
80 * @stable ICU 51
81 */
82 URGN_WORLD,
83
84 /**
85 * Type representing a continent.
86 * @stable ICU 51
87 */
88 URGN_CONTINENT,
89
90 /**
91 * Type representing a sub-continent.
92 * @stable ICU 51
93 */
94 URGN_SUBCONTINENT,
95
96 /**
97 * Type representing a grouping of territories that is not to be used in
98 * the normal WORLD/CONTINENT/SUBCONTINENT/TERRITORY containment tree.
99 * @stable ICU 51
100 */
101 URGN_GROUPING,
102
103 /**
104 * Type representing a region whose code has been deprecated, usually
105 * due to a country splitting into multiple territories or changing its name.
106 * @stable ICU 51
107 */
108 URGN_DEPRECATED,
109
110#ifndef U_HIDE_DEPRECATED_API
111 /**
112 * One more than the highest normal URegionType value.
113 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
114 */
115 URGN_LIMIT
116#endif /* U_HIDE_DEPRECATED_API */
117} URegionType;
118
119#if !UCONFIG_NO_FORMATTING
120
121/**
122 * Opaque URegion object for use in C programs.
123 * @stable ICU 52
124 */
125struct URegion;
126typedef struct URegion URegion; /**< @stable 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 * @stable ICU 52
135 */
136U_STABLE const URegion* U_EXPORT2
137uregion_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 * @stable ICU 52
143 */
144U_STABLE const URegion* U_EXPORT2
145uregion_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 * @stable ICU 52
151 */
152U_STABLE UEnumeration* U_EXPORT2
153uregion_getAvailable(URegionType type, UErrorCode *status);
154
155/**
156 * Returns true if the specified uregion is equal to the specified otherRegion.
157 * @stable ICU 52
158 */
159U_STABLE UBool U_EXPORT2
160uregion_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 * @stable ICU 52
167 */
168U_STABLE const URegion* U_EXPORT2
169uregion_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 * @stable ICU 52
179 */
180U_STABLE const URegion* U_EXPORT2
181uregion_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 * @stable ICU 52
192 */
193U_STABLE UEnumeration* U_EXPORT2
194uregion_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 * @stable ICU 52
204 */
205U_STABLE UEnumeration* U_EXPORT2
206uregion_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 * @stable ICU 52
212 */
213U_STABLE UBool U_EXPORT2
214uregion_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 * @stable ICU 52
223 */
224U_STABLE UEnumeration* U_EXPORT2
225uregion_getPreferredValues(const URegion* uregion, UErrorCode *status);
226
227/**
228 * Returns the specified uregion's canonical code.
229 * @stable ICU 52
230 */
231U_STABLE const char* U_EXPORT2
232uregion_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 * @stable ICU 52
238 */
239U_STABLE int32_t U_EXPORT2
240uregion_getNumericCode(const URegion* uregion);
241
242/**
243 * Returns the URegionType of the specified uregion.
244 * @stable ICU 52
245 */
246U_STABLE URegionType U_EXPORT2
247uregion_getType(const URegion* uregion);
248
249
250#endif /* #if !UCONFIG_NO_FORMATTING */
251
252#endif
253