/src/icu/source/common/ulocimp.h
Line  | Count  | Source (jump to first uncovered line)  | 
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  |  | #include "charstr.h"  | 
17  |  |  | 
18  |  | /**  | 
19  |  |  * Create an iterator over the specified keywords list  | 
20  |  |  * @param keywordList double-null terminated list. Will be copied.  | 
21  |  |  * @param keywordListSize size in bytes of keywordList  | 
22  |  |  * @param status err code  | 
23  |  |  * @return enumeration (owned by caller) of the keyword list.  | 
24  |  |  * @internal ICU 3.0  | 
25  |  |  */  | 
26  |  | U_CAPI UEnumeration* U_EXPORT2  | 
27  |  | uloc_openKeywordList(const char *keywordList, int32_t keywordListSize, UErrorCode* status);  | 
28  |  |  | 
29  |  | /**  | 
30  |  |  * Look up a resource bundle table item with fallback on the table level.  | 
31  |  |  * This is accessible so it can be called by C++ code.  | 
32  |  |  */  | 
33  |  | U_CAPI const UChar * U_EXPORT2  | 
34  |  | uloc_getTableStringWithFallback(  | 
35  |  |     const char *path,  | 
36  |  |     const char *locale,  | 
37  |  |     const char *tableKey,  | 
38  |  |     const char *subTableKey,  | 
39  |  |     const char *itemKey,  | 
40  |  |     int32_t *pLength,  | 
41  |  |     UErrorCode *pErrorCode);  | 
42  |  |  | 
43  |  | /*returns true if a is an ID separator false otherwise*/  | 
44  | 0  | #define _isIDSeparator(a) (a == '_' || a == '-')  | 
45  |  |  | 
46  |  | U_CFUNC const char*   | 
47  |  | uloc_getCurrentCountryID(const char* oldID);  | 
48  |  |  | 
49  |  | U_CFUNC const char*   | 
50  |  | uloc_getCurrentLanguageID(const char* oldID);  | 
51  |  |  | 
52  |  | U_CFUNC void  | 
53  |  | ulocimp_getKeywords(const char *localeID,  | 
54  |  |              char prev,  | 
55  |  |              icu::ByteSink& sink,  | 
56  |  |              UBool valuesToo,  | 
57  |  |              UErrorCode *status);  | 
58  |  |  | 
59  |  | icu::CharString U_EXPORT2  | 
60  |  | ulocimp_getLanguage(const char *localeID,  | 
61  |  |                     const char **pEnd,  | 
62  |  |                     UErrorCode &status);  | 
63  |  |  | 
64  |  | icu::CharString U_EXPORT2  | 
65  |  | ulocimp_getScript(const char *localeID,  | 
66  |  |                   const char **pEnd,  | 
67  |  |                   UErrorCode &status);  | 
68  |  |  | 
69  |  | icu::CharString U_EXPORT2  | 
70  |  | ulocimp_getCountry(const char *localeID,  | 
71  |  |                    const char **pEnd,  | 
72  |  |                    UErrorCode &status);  | 
73  |  |  | 
74  |  | U_CAPI void U_EXPORT2  | 
75  |  | ulocimp_getName(const char* localeID,  | 
76  |  |                 icu::ByteSink& sink,  | 
77  |  |                 UErrorCode* err);  | 
78  |  |  | 
79  |  | U_CAPI void U_EXPORT2  | 
80  |  | ulocimp_getBaseName(const char* localeID,  | 
81  |  |                     icu::ByteSink& sink,  | 
82  |  |                     UErrorCode* err);  | 
83  |  |  | 
84  |  | U_CAPI void U_EXPORT2  | 
85  |  | ulocimp_canonicalize(const char* localeID,  | 
86  |  |                      icu::ByteSink& sink,  | 
87  |  |                      UErrorCode* err);  | 
88  |  |  | 
89  |  | U_CAPI void U_EXPORT2  | 
90  |  | ulocimp_getKeywordValue(const char* localeID,  | 
91  |  |                         const char* keywordName,  | 
92  |  |                         icu::ByteSink& sink,  | 
93  |  |                         UErrorCode* status);  | 
94  |  |  | 
95  |  | /**  | 
96  |  |  * Writes a well-formed language tag for this locale ID.  | 
97  |  |  *  | 
98  |  |  * **Note**: When `strict` is false, any locale fields which do not satisfy the  | 
99  |  |  * BCP47 syntax requirement will be omitted from the result.  When `strict` is  | 
100  |  |  * true, this function sets U_ILLEGAL_ARGUMENT_ERROR to the `err` if any locale  | 
101  |  |  * fields do not satisfy the BCP47 syntax requirement.  | 
102  |  |  *  | 
103  |  |  * @param localeID  the input locale ID  | 
104  |  |  * @param sink      the output sink receiving the BCP47 language  | 
105  |  |  *                  tag for this Locale.  | 
106  |  |  * @param strict    boolean value indicating if the function returns  | 
107  |  |  *                  an error for an ill-formed input locale ID.  | 
108  |  |  * @param err       error information if receiving the language  | 
109  |  |  *                  tag failed.  | 
110  |  |  * @return          The length of the BCP47 language tag.  | 
111  |  |  *  | 
112  |  |  * @internal ICU 64  | 
113  |  |  */  | 
114  |  | U_CAPI void U_EXPORT2  | 
115  |  | ulocimp_toLanguageTag(const char* localeID,  | 
116  |  |                       icu::ByteSink& sink,  | 
117  |  |                       UBool strict,  | 
118  |  |                       UErrorCode* err);  | 
119  |  |  | 
120  |  | /**  | 
121  |  |  * Returns a locale ID for the specified BCP47 language tag string.  | 
122  |  |  * If the specified language tag contains any ill-formed subtags,  | 
123  |  |  * the first such subtag and all following subtags are ignored.  | 
124  |  |  * <p>  | 
125  |  |  * This implements the 'Language-Tag' production of BCP 47, and so  | 
126  |  |  * supports legacy language tags (marked as “Type: grandfathered” in BCP 47)  | 
127  |  |  * (regular and irregular) as well as private use language tags.  | 
128  |  |  *  | 
129  |  |  * Private use tags are represented as 'x-whatever',  | 
130  |  |  * and legacy tags are converted to their canonical replacements where they exist.  | 
131  |  |  *  | 
132  |  |  * Note that a few legacy tags have no modern replacement;  | 
133  |  |  * these will be converted using the fallback described in  | 
134  |  |  * the first paragraph, so some information might be lost.  | 
135  |  |  *  | 
136  |  |  * @param langtag   the input BCP47 language tag.  | 
137  |  |  * @param tagLen    the length of langtag, or -1 to call uprv_strlen().  | 
138  |  |  * @param sink      the output sink receiving a locale ID for the  | 
139  |  |  *                  specified BCP47 language tag.  | 
140  |  |  * @param parsedLength  if not NULL, successfully parsed length  | 
141  |  |  *                      for the input language tag is set.  | 
142  |  |  * @param err       error information if receiving the locald ID  | 
143  |  |  *                  failed.  | 
144  |  |  * @internal ICU 63  | 
145  |  |  */  | 
146  |  | U_CAPI void U_EXPORT2  | 
147  |  | ulocimp_forLanguageTag(const char* langtag,  | 
148  |  |                        int32_t tagLen,  | 
149  |  |                        icu::ByteSink& sink,  | 
150  |  |                        int32_t* parsedLength,  | 
151  |  |                        UErrorCode* err);  | 
152  |  |  | 
153  |  | /**  | 
154  |  |  * Get the region to use for supplemental data lookup. Uses  | 
155  |  |  * (1) any region specified by locale tag "rg"; if none then  | 
156  |  |  * (2) any unicode_region_tag in the locale ID; if none then  | 
157  |  |  * (3) if inferRegion is true, the region suggested by  | 
158  |  |  * getLikelySubtags on the localeID.  | 
159  |  |  * If no region is found, returns length 0.  | 
160  |  |  *   | 
161  |  |  * @param localeID  | 
162  |  |  *     The complete locale ID (with keywords) from which  | 
163  |  |  *     to get the region to use for supplemental data.  | 
164  |  |  * @param inferRegion  | 
165  |  |  *     If true, will try to infer region from localeID if  | 
166  |  |  *     no other region is found.  | 
167  |  |  * @param region  | 
168  |  |  *     Buffer in which to put the region ID found; should  | 
169  |  |  *     have a capacity at least ULOC_COUNTRY_CAPACITY.   | 
170  |  |  * @param regionCapacity  | 
171  |  |  *     The actual capacity of the region buffer.  | 
172  |  |  * @param status  | 
173  |  |  *     Pointer to in/out UErrorCode value for latest status.  | 
174  |  |  * @return  | 
175  |  |  *     The length of any region code found, or 0 if none.  | 
176  |  |  * @internal ICU 57  | 
177  |  |  */  | 
178  |  | U_CAPI int32_t U_EXPORT2  | 
179  |  | ulocimp_getRegionForSupplementalData(const char *localeID, UBool inferRegion,  | 
180  |  |                                      char *region, int32_t regionCapacity, UErrorCode* status);  | 
181  |  |  | 
182  |  | /**  | 
183  |  |  * Add the likely subtags for a provided locale ID, per the algorithm described  | 
184  |  |  * in the following CLDR technical report:  | 
185  |  |  *  | 
186  |  |  *   http://www.unicode.org/reports/tr35/#Likely_Subtags  | 
187  |  |  *  | 
188  |  |  * If localeID is already in the maximal form, or there is no data available  | 
189  |  |  * for maximization, it will be copied to the output buffer.  For example,  | 
190  |  |  * "und-Zzzz" cannot be maximized, since there is no reasonable maximization.  | 
191  |  |  *  | 
192  |  |  * Examples:  | 
193  |  |  *  | 
194  |  |  * "en" maximizes to "en_Latn_US"  | 
195  |  |  *  | 
196  |  |  * "de" maximizes to "de_Latn_US"  | 
197  |  |  *  | 
198  |  |  * "sr" maximizes to "sr_Cyrl_RS"  | 
199  |  |  *  | 
200  |  |  * "sh" maximizes to "sr_Latn_RS" (Note this will not reverse.)  | 
201  |  |  *  | 
202  |  |  * "zh_Hani" maximizes to "zh_Hans_CN" (Note this will not reverse.)  | 
203  |  |  *  | 
204  |  |  * @param localeID The locale to maximize  | 
205  |  |  * @param sink The output sink receiving the maximized locale  | 
206  |  |  * @param err Error information if maximizing the locale failed.  If the length  | 
207  |  |  * of the localeID and the null-terminator is greater than the maximum allowed size,  | 
208  |  |  * or the localeId is not well-formed, the error code is U_ILLEGAL_ARGUMENT_ERROR.  | 
209  |  |  * @internal ICU 64  | 
210  |  |  */  | 
211  |  | U_CAPI void U_EXPORT2  | 
212  |  | ulocimp_addLikelySubtags(const char* localeID,  | 
213  |  |                          icu::ByteSink& sink,  | 
214  |  |                          UErrorCode* err);  | 
215  |  |  | 
216  |  | /**  | 
217  |  |  * Minimize the subtags for a provided locale ID, per the algorithm described  | 
218  |  |  * in the following CLDR technical report:  | 
219  |  |  *  | 
220  |  |  *   http://www.unicode.org/reports/tr35/#Likely_Subtags  | 
221  |  |  *  | 
222  |  |  * If localeID is already in the minimal form, or there is no data available  | 
223  |  |  * for minimization, it will be copied to the output buffer.  Since the  | 
224  |  |  * minimization algorithm relies on proper maximization, see the comments  | 
225  |  |  * for ulocimp_addLikelySubtags for reasons why there might not be any data.  | 
226  |  |  *  | 
227  |  |  * Examples:  | 
228  |  |  *  | 
229  |  |  * "en_Latn_US" minimizes to "en"  | 
230  |  |  *  | 
231  |  |  * "de_Latn_US" minimizes to "de"  | 
232  |  |  *  | 
233  |  |  * "sr_Cyrl_RS" minimizes to "sr"  | 
234  |  |  *  | 
235  |  |  * "zh_Hant_TW" minimizes to "zh_TW" (The region is preferred to the  | 
236  |  |  * script, and minimizing to "zh" would imply "zh_Hans_CN".)  | 
237  |  |  *  | 
238  |  |  * @param localeID The locale to minimize  | 
239  |  |  * @param sink The output sink receiving the maximized locale  | 
240  |  |  * @param err Error information if minimizing the locale failed.  If the length  | 
241  |  |  * of the localeID and the null-terminator is greater than the maximum allowed size,  | 
242  |  |  * or the localeId is not well-formed, the error code is U_ILLEGAL_ARGUMENT_ERROR.  | 
243  |  |  * @internal ICU 64  | 
244  |  |  */  | 
245  |  | U_CAPI void U_EXPORT2  | 
246  |  | ulocimp_minimizeSubtags(const char* localeID,  | 
247  |  |                         icu::ByteSink& sink,  | 
248  |  |                         UErrorCode* err);  | 
249  |  |  | 
250  |  | U_CAPI const char * U_EXPORT2  | 
251  |  | locale_getKeywordsStart(const char *localeID);  | 
252  |  |  | 
253  |  | U_CFUNC UBool  | 
254  |  | ultag_isExtensionSubtags(const char* s, int32_t len);  | 
255  |  |  | 
256  |  | U_CFUNC UBool  | 
257  |  | ultag_isLanguageSubtag(const char* s, int32_t len);  | 
258  |  |  | 
259  |  | U_CFUNC UBool  | 
260  |  | ultag_isPrivateuseValueSubtags(const char* s, int32_t len);  | 
261  |  |  | 
262  |  | U_CFUNC UBool  | 
263  |  | ultag_isRegionSubtag(const char* s, int32_t len);  | 
264  |  |  | 
265  |  | U_CFUNC UBool  | 
266  |  | ultag_isScriptSubtag(const char* s, int32_t len);  | 
267  |  |  | 
268  |  | U_CFUNC UBool  | 
269  |  | ultag_isTransformedExtensionSubtags(const char* s, int32_t len);  | 
270  |  |  | 
271  |  | U_CFUNC UBool  | 
272  |  | ultag_isUnicodeExtensionSubtags(const char* s, int32_t len);  | 
273  |  |  | 
274  |  | U_CFUNC UBool  | 
275  |  | ultag_isUnicodeLocaleAttribute(const char* s, int32_t len);  | 
276  |  |  | 
277  |  | U_CFUNC UBool  | 
278  |  | ultag_isUnicodeLocaleAttributes(const char* s, int32_t len);  | 
279  |  |  | 
280  |  | U_CFUNC UBool  | 
281  |  | ultag_isUnicodeLocaleKey(const char* s, int32_t len);  | 
282  |  |  | 
283  |  | U_CFUNC UBool  | 
284  |  | ultag_isUnicodeLocaleType(const char* s, int32_t len);  | 
285  |  |  | 
286  |  | U_CFUNC UBool  | 
287  |  | ultag_isVariantSubtags(const char* s, int32_t len);  | 
288  |  |  | 
289  |  | U_CAPI const char * U_EXPORT2  | 
290  |  | ultag_getTKeyStart(const char *localeID);  | 
291  |  |  | 
292  |  | U_CFUNC const char*  | 
293  |  | ulocimp_toBcpKey(const char* key);  | 
294  |  |  | 
295  |  | U_CFUNC const char*  | 
296  |  | ulocimp_toLegacyKey(const char* key);  | 
297  |  |  | 
298  |  | U_CFUNC const char*  | 
299  |  | ulocimp_toBcpType(const char* key, const char* type, UBool* isKnownKey, UBool* isSpecialType);  | 
300  |  |  | 
301  |  | U_CFUNC const char*  | 
302  |  | ulocimp_toLegacyType(const char* key, const char* type, UBool* isKnownKey, UBool* isSpecialType);  | 
303  |  |  | 
304  |  | /* Function for testing purpose */  | 
305  |  | U_CAPI const char* const* ulocimp_getKnownCanonicalizedLocaleForTest(int32_t* length);  | 
306  |  |  | 
307  |  | // Return true if the value is already canonicalized.  | 
308  |  | U_CAPI bool ulocimp_isCanonicalizedLocaleForTest(const char* localeName);  | 
309  |  |  | 
310  |  | /**  | 
311  |  |  * A utility class for handling locale IDs that may be longer than ULOC_FULLNAME_CAPACITY.  | 
312  |  |  * This encompasses all of the logic to allocate a temporary locale ID buffer on the stack,  | 
313  |  |  * and then, if it's not big enough, reallocate it on the heap and try again.  | 
314  |  |  *  | 
315  |  |  * You use it like this:  | 
316  |  |  * UErrorCode err = U_ZERO_ERROR;  | 
317  |  |  *  | 
318  |  |  * PreflightingLocaleIDBuffer tempBuffer;  | 
319  |  |  * do { | 
320  |  |  *     tempBuffer.requestedCapacity = uloc_doSomething(localeID, tempBuffer.getBuffer(), tempBuffer.getCapacity(), &err);  | 
321  |  |  * } while (tempBuffer.needToTryAgain(&err));  | 
322  |  |  * if (U_SUCCESS(err)) { | 
323  |  |  *     uloc_doSomethingWithTheResult(tempBuffer.getBuffer());  | 
324  |  |  * }  | 
325  |  |  */  | 
326  |  | class PreflightingLocaleIDBuffer { | 
327  |  | private:  | 
328  |  |     char stackBuffer[ULOC_FULLNAME_CAPACITY];  | 
329  |  |     char* heapBuffer = nullptr;  | 
330  |  |     int32_t capacity = ULOC_FULLNAME_CAPACITY;  | 
331  |  |       | 
332  |  | public:  | 
333  |  |     int32_t requestedCapacity = ULOC_FULLNAME_CAPACITY;  | 
334  |  |  | 
335  |  |     // No heap allocation. Use only on the stack.  | 
336  |  |     static void* U_EXPORT2 operator new(size_t) U_NOEXCEPT = delete;  | 
337  |  |     static void* U_EXPORT2 operator new[](size_t) U_NOEXCEPT = delete;  | 
338  |  | #if U_HAVE_PLACEMENT_NEW  | 
339  |  |     static void* U_EXPORT2 operator new(size_t, void*) U_NOEXCEPT = delete;  | 
340  |  | #endif  | 
341  |  |  | 
342  | 0  |     PreflightingLocaleIDBuffer() {} | 
343  |  |       | 
344  | 0  |     ~PreflightingLocaleIDBuffer() { uprv_free(heapBuffer); } | 
345  |  |       | 
346  | 0  |     char* getBuffer() { | 
347  | 0  |         if (heapBuffer == nullptr) { | 
348  | 0  |             return stackBuffer;  | 
349  | 0  |         } else { | 
350  | 0  |             return heapBuffer;  | 
351  | 0  |         }  | 
352  | 0  |     }  | 
353  |  |       | 
354  | 0  |     int32_t getCapacity() { | 
355  | 0  |         return capacity;  | 
356  | 0  |     }  | 
357  |  |       | 
358  | 0  |     bool needToTryAgain(UErrorCode* err) { | 
359  | 0  |         if (heapBuffer != nullptr) { | 
360  | 0  |             return false;  | 
361  | 0  |         }  | 
362  |  |       | 
363  | 0  |         if (*err == U_BUFFER_OVERFLOW_ERROR || *err == U_STRING_NOT_TERMINATED_WARNING) { | 
364  | 0  |             int32_t newCapacity = requestedCapacity + 2;    // one for the terminating null, one just for paranoia  | 
365  | 0  |             heapBuffer = static_cast<char*>(uprv_malloc(newCapacity));  | 
366  | 0  |             if (heapBuffer == nullptr) { | 
367  | 0  |                 *err = U_MEMORY_ALLOCATION_ERROR;  | 
368  | 0  |             } else { | 
369  | 0  |                 *err = U_ZERO_ERROR;  | 
370  | 0  |                 capacity = newCapacity;  | 
371  | 0  |             }  | 
372  | 0  |             return U_SUCCESS(*err);  | 
373  | 0  |         }  | 
374  | 0  |         return false;  | 
375  | 0  |     }  | 
376  |  | };  | 
377  |  |  | 
378  |  | #endif  |