1// © 2016 and later: Unicode, Inc. and others.
2// License & terms of use: http://www.unicode.org/copyright.html
3/*
4**********************************************************************
5* Copyright (C) 2004-2016, International Business Machines
6* Corporation and others. All Rights Reserved.
7**********************************************************************
8*/
9
10#ifndef ULOCIMP_H
11#define ULOCIMP_H
12
13#include "unicode/bytestream.h"
14#include "unicode/uloc.h"
15
16/**
17 * Create an iterator over the specified keywords list
18 * @param keywordList double-null terminated list. Will be copied.
19 * @param keywordListSize size in bytes of keywordList
20 * @param status err code
21 * @return enumeration (owned by caller) of the keyword list.
22 * @internal ICU 3.0
23 */
24U_CAPI UEnumeration* U_EXPORT2
25uloc_openKeywordList(const char *keywordList, int32_t keywordListSize, UErrorCode* status);
26
27/**
28 * Look up a resource bundle table item with fallback on the table level.
29 * This is accessible so it can be called by C++ code.
30 */
31U_CAPI const UChar * U_EXPORT2
32uloc_getTableStringWithFallback(
33 const char *path,
34 const char *locale,
35 const char *tableKey,
36 const char *subTableKey,
37 const char *itemKey,
38 int32_t *pLength,
39 UErrorCode *pErrorCode);
40
41/*returns TRUE if a is an ID separator FALSE otherwise*/
42#define _isIDSeparator(a) (a == '_' || a == '-')
43
44U_CFUNC const char*
45uloc_getCurrentCountryID(const char* oldID);
46
47U_CFUNC const char*
48uloc_getCurrentLanguageID(const char* oldID);
49
50U_CFUNC int32_t
51ulocimp_getLanguage(const char *localeID,
52 char *language, int32_t languageCapacity,
53 const char **pEnd);
54
55U_CFUNC int32_t
56ulocimp_getScript(const char *localeID,
57 char *script, int32_t scriptCapacity,
58 const char **pEnd);
59
60U_CFUNC int32_t
61ulocimp_getCountry(const char *localeID,
62 char *country, int32_t countryCapacity,
63 const char **pEnd);
64
65U_STABLE void U_EXPORT2
66ulocimp_getName(const char* localeID,
67 icu::ByteSink& sink,
68 UErrorCode* err);
69
70U_STABLE void U_EXPORT2
71ulocimp_getBaseName(const char* localeID,
72 icu::ByteSink& sink,
73 UErrorCode* err);
74
75U_STABLE void U_EXPORT2
76ulocimp_canonicalize(const char* localeID,
77 icu::ByteSink& sink,
78 UErrorCode* err);
79
80/**
81 * Writes a well-formed language tag for this locale ID.
82 *
83 * **Note**: When `strict` is FALSE, any locale fields which do not satisfy the
84 * BCP47 syntax requirement will be omitted from the result. When `strict` is
85 * TRUE, this function sets U_ILLEGAL_ARGUMENT_ERROR to the `err` if any locale
86 * fields do not satisfy the BCP47 syntax requirement.
87 *
88 * @param localeID the input locale ID
89 * @param sink the output sink receiving the BCP47 language
90 * tag for this Locale.
91 * @param strict boolean value indicating if the function returns
92 * an error for an ill-formed input locale ID.
93 * @param err error information if receiving the language
94 * tag failed.
95 * @return The length of the BCP47 language tag.
96 *
97 * @internal ICU 64
98 */
99U_STABLE void U_EXPORT2
100ulocimp_toLanguageTag(const char* localeID,
101 icu::ByteSink& sink,
102 UBool strict,
103 UErrorCode* err);
104
105/**
106 * Returns a locale ID for the specified BCP47 language tag string.
107 * If the specified language tag contains any ill-formed subtags,
108 * the first such subtag and all following subtags are ignored.
109 * <p>
110 * This implements the 'Language-Tag' production of BCP47, and so
111 * supports grandfathered (regular and irregular) as well as private
112 * use language tags. Private use tags are represented as 'x-whatever',
113 * and grandfathered tags are converted to their canonical replacements
114 * where they exist. Note that a few grandfathered tags have no modern
115 * replacement, these will be converted using the fallback described in
116 * the first paragraph, so some information might be lost.
117 * @param langtag the input BCP47 language tag.
118 * @param tagLen the length of langtag, or -1 to call uprv_strlen().
119 * @param sink the output sink receiving a locale ID for the
120 * specified BCP47 language tag.
121 * @param parsedLength if not NULL, successfully parsed length
122 * for the input language tag is set.
123 * @param err error information if receiving the locald ID
124 * failed.
125 * @internal ICU 63
126 */
127U_CAPI void U_EXPORT2
128ulocimp_forLanguageTag(const char* langtag,
129 int32_t tagLen,
130 icu::ByteSink& sink,
131 int32_t* parsedLength,
132 UErrorCode* err);
133
134/**
135 * Get the region to use for supplemental data lookup. Uses
136 * (1) any region specified by locale tag "rg"; if none then
137 * (2) any unicode_region_tag in the locale ID; if none then
138 * (3) if inferRegion is TRUE, the region suggested by
139 * getLikelySubtags on the localeID.
140 * If no region is found, returns length 0.
141 *
142 * @param localeID
143 * The complete locale ID (with keywords) from which
144 * to get the region to use for supplemental data.
145 * @param inferRegion
146 * If TRUE, will try to infer region from localeID if
147 * no other region is found.
148 * @param region
149 * Buffer in which to put the region ID found; should
150 * have a capacity at least ULOC_COUNTRY_CAPACITY.
151 * @param regionCapacity
152 * The actual capacity of the region buffer.
153 * @param status
154 * Pointer to in/out UErrorCode value for latest status.
155 * @return
156 * The length of any region code found, or 0 if none.
157 * @internal ICU 57
158 */
159U_CAPI int32_t U_EXPORT2
160ulocimp_getRegionForSupplementalData(const char *localeID, UBool inferRegion,
161 char *region, int32_t regionCapacity, UErrorCode* status);
162
163/**
164 * Add the likely subtags for a provided locale ID, per the algorithm described
165 * in the following CLDR technical report:
166 *
167 * http://www.unicode.org/reports/tr35/#Likely_Subtags
168 *
169 * If localeID is already in the maximal form, or there is no data available
170 * for maximization, it will be copied to the output buffer. For example,
171 * "und-Zzzz" cannot be maximized, since there is no reasonable maximization.
172 *
173 * Examples:
174 *
175 * "en" maximizes to "en_Latn_US"
176 *
177 * "de" maximizes to "de_Latn_US"
178 *
179 * "sr" maximizes to "sr_Cyrl_RS"
180 *
181 * "sh" maximizes to "sr_Latn_RS" (Note this will not reverse.)
182 *
183 * "zh_Hani" maximizes to "zh_Hans_CN" (Note this will not reverse.)
184 *
185 * @param localeID The locale to maximize
186 * @param sink The output sink receiving the maximized locale
187 * @param err Error information if maximizing the locale failed. If the length
188 * of the localeID and the null-terminator is greater than the maximum allowed size,
189 * or the localeId is not well-formed, the error code is U_ILLEGAL_ARGUMENT_ERROR.
190 * @internal ICU 64
191 */
192U_STABLE void U_EXPORT2
193ulocimp_addLikelySubtags(const char* localeID,
194 icu::ByteSink& sink,
195 UErrorCode* err);
196
197/**
198 * Minimize the subtags for a provided locale ID, per the algorithm described
199 * in the following CLDR technical report:
200 *
201 * http://www.unicode.org/reports/tr35/#Likely_Subtags
202 *
203 * If localeID is already in the minimal form, or there is no data available
204 * for minimization, it will be copied to the output buffer. Since the
205 * minimization algorithm relies on proper maximization, see the comments
206 * for ulocimp_addLikelySubtags for reasons why there might not be any data.
207 *
208 * Examples:
209 *
210 * "en_Latn_US" minimizes to "en"
211 *
212 * "de_Latn_US" minimizes to "de"
213 *
214 * "sr_Cyrl_RS" minimizes to "sr"
215 *
216 * "zh_Hant_TW" minimizes to "zh_TW" (The region is preferred to the
217 * script, and minimizing to "zh" would imply "zh_Hans_CN".)
218 *
219 * @param localeID The locale to minimize
220 * @param sink The output sink receiving the maximized locale
221 * @param err Error information if minimizing the locale failed. If the length
222 * of the localeID and the null-terminator is greater than the maximum allowed size,
223 * or the localeId is not well-formed, the error code is U_ILLEGAL_ARGUMENT_ERROR.
224 * @internal ICU 64
225 */
226U_STABLE void U_EXPORT2
227ulocimp_minimizeSubtags(const char* localeID,
228 icu::ByteSink& sink,
229 UErrorCode* err);
230
231U_CAPI const char * U_EXPORT2
232locale_getKeywordsStart(const char *localeID);
233
234U_CFUNC UBool
235ultag_isExtensionSubtags(const char* s, int32_t len);
236
237U_CFUNC UBool
238ultag_isLanguageSubtag(const char* s, int32_t len);
239
240U_CFUNC UBool
241ultag_isPrivateuseValueSubtags(const char* s, int32_t len);
242
243U_CFUNC UBool
244ultag_isRegionSubtag(const char* s, int32_t len);
245
246U_CFUNC UBool
247ultag_isScriptSubtag(const char* s, int32_t len);
248
249U_CFUNC UBool
250ultag_isTransformedExtensionSubtags(const char* s, int32_t len);
251
252U_CFUNC UBool
253ultag_isUnicodeExtensionSubtags(const char* s, int32_t len);
254
255U_CFUNC UBool
256ultag_isUnicodeLocaleAttribute(const char* s, int32_t len);
257
258U_CFUNC UBool
259ultag_isUnicodeLocaleAttributes(const char* s, int32_t len);
260
261U_CFUNC UBool
262ultag_isUnicodeLocaleKey(const char* s, int32_t len);
263
264U_CFUNC UBool
265ultag_isUnicodeLocaleType(const char* s, int32_t len);
266
267U_CFUNC UBool
268ultag_isVariantSubtags(const char* s, int32_t len);
269
270U_CFUNC const char*
271ulocimp_toBcpKey(const char* key);
272
273U_CFUNC const char*
274ulocimp_toLegacyKey(const char* key);
275
276U_CFUNC const char*
277ulocimp_toBcpType(const char* key, const char* type, UBool* isKnownKey, UBool* isSpecialType);
278
279U_CFUNC const char*
280ulocimp_toLegacyType(const char* key, const char* type, UBool* isKnownKey, UBool* isSpecialType);
281
282#endif
283