1// © 2016 and later: Unicode, Inc. and others.
2// License & terms of use: http://www.unicode.org/copyright.html
3/*
4 *******************************************************************************
5 * Copyright (C) 2014-2016, International Business Machines Corporation and others.
6 * All Rights Reserved.
7 *******************************************************************************
8 */
9
10#ifndef REGION_H
11#define REGION_H
12
13/**
14 * \file
15 * \brief C++ API: Region classes (territory containment)
16 */
17
18#include "unicode/utypes.h"
19
20#if U_SHOW_CPLUSPLUS_API
21
22#if !UCONFIG_NO_FORMATTING
23
24#include "unicode/uregion.h"
25#include "unicode/uobject.h"
26#include "unicode/uniset.h"
27#include "unicode/unistr.h"
28#include "unicode/strenum.h"
29
30U_NAMESPACE_BEGIN
31
32/**
33 * <code>Region</code> is the class representing a Unicode Region Code, also known as a
34 * Unicode Region Subtag, which is defined based upon the BCP 47 standard. We often think of
35 * "regions" as "countries" when defining the characteristics of a locale. Region codes There are different
36 * types of region codes that are important to distinguish.
37 * <p>
38 * Macroregion - A code for a "macro geographical (continental) region, geographical sub-region, or
39 * selected economic and other grouping" as defined in
40 * UN M.49 (http://unstats.un.org/unsd/methods/m49/m49regin.htm).
41 * These are typically 3-digit codes, but contain some 2-letter codes, such as the LDML code QO
42 * added for Outlying Oceania. Not all UNM.49 codes are defined in LDML, but most of them are.
43 * Macroregions are represented in ICU by one of three region types: WORLD ( region code 001 ),
44 * CONTINENTS ( regions contained directly by WORLD ), and SUBCONTINENTS ( things contained directly
45 * by a continent ).
46 * <p>
47 * TERRITORY - A Region that is not a Macroregion. These are typically codes for countries, but also
48 * include areas that are not separate countries, such as the code "AQ" for Antarctica or the code
49 * "HK" for Hong Kong (SAR China). Overseas dependencies of countries may or may not have separate
50 * codes. The codes are typically 2-letter codes aligned with the ISO 3166 standard, but BCP47 allows
51 * for the use of 3-digit codes in the future.
52 * <p>
53 * UNKNOWN - The code ZZ is defined by Unicode LDML for use to indicate that the Region is unknown,
54 * or that the value supplied as a region was invalid.
55 * <p>
56 * DEPRECATED - Region codes that have been defined in the past but are no longer in modern usage,
57 * usually due to a country splitting into multiple territories or changing its name.
58 * <p>
59 * GROUPING - A widely understood grouping of territories that has a well defined membership such
60 * that a region code has been assigned for it. Some of these are UNM.49 codes that do't fall into
61 * the world/continent/sub-continent hierarchy, while others are just well known groupings that have
62 * their own region code. Region "EU" (European Union) is one such region code that is a grouping.
63 * Groupings will never be returned by the getContainingRegion() API, since a different type of region
64 * ( WORLD, CONTINENT, or SUBCONTINENT ) will always be the containing region instead.
65 *
66 * The Region class is not intended for public subclassing.
67 *
68 * @author John Emmons
69 * @stable ICU 51
70 */
71
72class U_I18N_API Region : public UObject {
73public:
74 /**
75 * Destructor.
76 * @stable ICU 51
77 */
78 virtual ~Region();
79
80 /**
81 * Returns true if the two regions are equal.
82 * @stable ICU 51
83 */
84 UBool operator==(const Region &that) const;
85
86 /**
87 * Returns true if the two regions are NOT equal; that is, if operator ==() returns false.
88 * @stable ICU 51
89 */
90 UBool operator!=(const Region &that) const;
91
92 /**
93 * Returns a pointer to a Region using the given region code. The region code can be either 2-letter ISO code,
94 * 3-letter ISO code, UNM.49 numeric code, or other valid Unicode Region Code as defined by the LDML specification.
95 * The identifier will be canonicalized internally using the supplemental metadata as defined in the CLDR.
96 * If the region code is NULL or not recognized, the appropriate error code will be set ( U_ILLEGAL_ARGUMENT_ERROR )
97 * @stable ICU 51
98 */
99 static const Region* U_EXPORT2 getInstance(const char *region_code, UErrorCode &status);
100
101 /**
102 * Returns a pointer to a Region using the given numeric region code. If the numeric region code is not recognized,
103 * the appropriate error code will be set ( U_ILLEGAL_ARGUMENT_ERROR ).
104 * @stable ICU 51
105 */
106 static const Region* U_EXPORT2 getInstance (int32_t code, UErrorCode &status);
107
108 /**
109 * Returns an enumeration over the IDs of all known regions that match the given type.
110 * @stable ICU 55
111 */
112 static StringEnumeration* U_EXPORT2 getAvailable(URegionType type, UErrorCode &status);
113
114 /**
115 * Returns a pointer to the region that contains this region. Returns NULL if this region is code "001" (World)
116 * or "ZZ" (Unknown region). For example, calling this method with region "IT" (Italy) returns the
117 * region "039" (Southern Europe).
118 * @stable ICU 51
119 */
120 const Region* getContainingRegion() const;
121
122 /**
123 * Return a pointer to the region that geographically contains this region and matches the given type,
124 * moving multiple steps up the containment chain if necessary. Returns NULL if no containing region can be found
125 * that matches the given type. Note: The URegionTypes = "URGN_GROUPING", "URGN_DEPRECATED", or "URGN_UNKNOWN"
126 * are not appropriate for use in this API. NULL will be returned in this case. For example, calling this method
127 * with region "IT" (Italy) for type "URGN_CONTINENT" returns the region "150" ( Europe ).
128 * @stable ICU 51
129 */
130 const Region* getContainingRegion(URegionType type) const;
131
132 /**
133 * Return an enumeration over the IDs of all the regions that are immediate children of this region in the
134 * region hierarchy. These returned regions could be either macro regions, territories, or a mixture of the two,
135 * depending on the containment data as defined in CLDR. This API may return NULL if this region doesn't have
136 * any sub-regions. For example, calling this method with region "150" (Europe) returns an enumeration containing
137 * the various sub regions of Europe - "039" (Southern Europe) - "151" (Eastern Europe) - "154" (Northern Europe)
138 * and "155" (Western Europe).
139 * @stable ICU 55
140 */
141 StringEnumeration* getContainedRegions(UErrorCode &status) const;
142
143 /**
144 * Returns an enumeration over the IDs of all the regions that are children of this region anywhere in the region
145 * hierarchy and match the given type. This API may return an empty enumeration if this region doesn't have any
146 * sub-regions that match the given type. For example, calling this method with region "150" (Europe) and type
147 * "URGN_TERRITORY" returns a set containing all the territories in Europe ( "FR" (France) - "IT" (Italy) - "DE" (Germany) etc. )
148 * @stable ICU 55
149 */
150 StringEnumeration* getContainedRegions( URegionType type, UErrorCode &status ) const;
151
152 /**
153 * Returns true if this region contains the supplied other region anywhere in the region hierarchy.
154 * @stable ICU 51
155 */
156 UBool contains(const Region &other) const;
157
158 /**
159 * For deprecated regions, return an enumeration over the IDs of the regions that are the preferred replacement
160 * regions for this region. Returns null for a non-deprecated region. For example, calling this method with region
161 * "SU" (Soviet Union) would return a list of the regions containing "RU" (Russia), "AM" (Armenia), "AZ" (Azerbaijan), etc...
162 * @stable ICU 55
163 */
164 StringEnumeration* getPreferredValues(UErrorCode &status) const;
165
166 /**
167 * Return this region's canonical region code.
168 * @stable ICU 51
169 */
170 const char* getRegionCode() const;
171
172 /**
173 * Return this region's numeric code.
174 * Returns a negative value if the given region does not have a numeric code assigned to it.
175 * @stable ICU 51
176 */
177 int32_t getNumericCode() const;
178
179 /**
180 * Returns the region type of this region.
181 * @stable ICU 51
182 */
183 URegionType getType() const;
184
185#ifndef U_HIDE_INTERNAL_API
186 /**
187 * Cleans up statically allocated memory.
188 * @internal
189 */
190 static void cleanupRegionData();
191#endif /* U_HIDE_INTERNAL_API */
192
193private:
194 char id[4];
195 UnicodeString idStr;
196 int32_t code;
197 URegionType fType;
198 Region *containingRegion;
199 UVector *containedRegions;
200 UVector *preferredValues;
201
202 /**
203 * Default Constructor. Internal - use factory methods only.
204 */
205 Region();
206
207
208 /*
209 * Initializes the region data from the ICU resource bundles. The region data
210 * contains the basic relationships such as which regions are known, what the numeric
211 * codes are, any known aliases, and the territory containment data.
212 *
213 * If the region data has already loaded, then this method simply returns without doing
214 * anything meaningful.
215 */
216
217 static void U_CALLCONV loadRegionData(UErrorCode &status);
218
219};
220
221U_NAMESPACE_END
222
223#endif /* #if !UCONFIG_NO_FORMATTING */
224
225#endif /* U_SHOW_CPLUSPLUS_API */
226
227#endif // REGION_H
228
229//eof
230