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