icuSources/common/ulocimp.h

   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  */
  24 U_CAPI UEnumeration* U_EXPORT2
  25 uloc_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  */
  31 U_CAPI const UChar * U_EXPORT2
  32 uloc_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
  44 U_CFUNC const char*
  45 uloc_getCurrentCountryID(const char* oldID);
  46
  47 U_CFUNC const char*
  48 uloc_getCurrentLanguageID(const char* oldID);
  49
  50 U_CFUNC int32_t
  51 ulocimp_getLanguage(const char *localeID,
  52                     char *language, int32_t languageCapacity,
  53                     const char **pEnd);
  54
  55 U_CFUNC int32_t
  56 ulocimp_getScript(const char *localeID,
  57                    char *script, int32_t scriptCapacity,
  58                    const char **pEnd);
  59
  60 U_CFUNC int32_t
  61 ulocimp_getCountry(const char *localeID,
  62                    char *country, int32_t countryCapacity,
  63                    const char **pEnd);
  64
  65 /**
  66  * Writes a well-formed language tag for this locale ID.
  67  *
  68  * **Note**: When `strict` is FALSE, any locale fields which do not satisfy the
  69  * BCP47 syntax requirement will be omitted from the result.  When `strict` is
  70  * TRUE, this function sets U_ILLEGAL_ARGUMENT_ERROR to the `err` if any locale
  71  * fields do not satisfy the BCP47 syntax requirement.
  72  *
  73  * @param localeID  the input locale ID
  74  * @param sink      the output sink receiving the BCP47 language
  75  *                  tag for this Locale.
  76  * @param strict    boolean value indicating if the function returns
  77  *                  an error for an ill-formed input locale ID.
  78  * @param err       error information if receiving the language
  79  *                  tag failed.
  80  * @return          The length of the BCP47 language tag.
  81  *
  82  * @internal ICU 64
  83  */
  84 U_STABLE void U_EXPORT2
  85 ulocimp_toLanguageTag(const char* localeID,
  86                       icu::ByteSink& sink,
  87                       UBool strict,
  88                       UErrorCode* err);
  89
  90 /**
  91  * Returns a locale ID for the specified BCP47 language tag string.
  92  * If the specified language tag contains any ill-formed subtags,
  93  * the first such subtag and all following subtags are ignored.
  94  * <p>
  95  * This implements the 'Language-Tag' production of BCP47, and so
  96  * supports grandfathered (regular and irregular) as well as private
  97  * use language tags.  Private use tags are represented as 'x-whatever',
  98  * and grandfathered tags are converted to their canonical replacements
  99  * where they exist.  Note that a few grandfathered tags have no modern
 100  * replacement, these will be converted using the fallback described in
 101  * the first paragraph, so some information might be lost.
 102  * @param langtag   the input BCP47 language tag.
 103  * @param tagLen    the length of langtag, or -1 to call uprv_strlen().
 104  * @param sink      the output sink receiving a locale ID for the
 105  *                  specified BCP47 language tag.
 106  * @param parsedLength  if not NULL, successfully parsed length
 107  *                      for the input language tag is set.
 108  * @param err       error information if receiving the locald ID
 109  *                  failed.
 110  * @internal ICU 63
 111  */
 112 U_CAPI void U_EXPORT2
 113 ulocimp_forLanguageTag(const char* langtag,
 114                        int32_t tagLen,
 115                        icu::ByteSink& sink,
 116                        int32_t* parsedLength,
 117                        UErrorCode* err);
 118
 119 /**
 120  * Get the region to use for supplemental data lookup. Uses
 121  * (1) any region specified by locale tag "rg"; if none then
 122  * (2) any unicode_region_tag in the locale ID; if none then
 123  * (3) if inferRegion is TRUE, the region suggested by
 124  * getLikelySubtags on the localeID.
 125  * If no region is found, returns length 0.
 126  *
 127  * @param localeID
 128  *     The complete locale ID (with keywords) from which
 129  *     to get the region to use for supplemental data.
 130  * @param inferRegion
 131  *     If TRUE, will try to infer region from localeID if
 132  *     no other region is found.
 133  * @param region
 134  *     Buffer in which to put the region ID found; should
 135  *     have a capacity at least ULOC_COUNTRY_CAPACITY.
 136  * @param regionCapacity
 137  *     The actual capacity of the region buffer.
 138  * @param status
 139  *     Pointer to in/out UErrorCode value for latest status.
 140  * @return
 141  *     The length of any region code found, or 0 if none.
 142  * @internal ICU 57
 143  */
 144 U_CAPI int32_t U_EXPORT2
 145 ulocimp_getRegionForSupplementalData(const char *localeID, UBool inferRegion,
 146                                      char *region, int32_t regionCapacity, UErrorCode* status);
 147
 148 /**
 149  * Add the likely subtags for a provided locale ID, per the algorithm described
 150  * in the following CLDR technical report:
 151  *
 152  *   http://www.unicode.org/reports/tr35/#Likely_Subtags
 153  *
 154  * If localeID is already in the maximal form, or there is no data available
 155  * for maximization, it will be copied to the output buffer.  For example,
 156  * "und-Zzzz" cannot be maximized, since there is no reasonable maximization.
 157  *
 158  * Examples:
 159  *
 160  * "en" maximizes to "en_Latn_US"
 161  *
 162  * "de" maximizes to "de_Latn_US"
 163  *
 164  * "sr" maximizes to "sr_Cyrl_RS"
 165  *
 166  * "sh" maximizes to "sr_Latn_RS" (Note this will not reverse.)
 167  *
 168  * "zh_Hani" maximizes to "zh_Hans_CN" (Note this will not reverse.)
 169  *
 170  * @param localeID The locale to maximize
 171  * @param sink The output sink receiving the maximized locale
 172  * @param err Error information if maximizing the locale failed.  If the length
 173  * of the localeID and the null-terminator is greater than the maximum allowed size,
 174  * or the localeId is not well-formed, the error code is U_ILLEGAL_ARGUMENT_ERROR.
 175  * @internal ICU 64
 176  */
 177 U_STABLE void U_EXPORT2
 178 ulocimp_addLikelySubtags(const char* localeID,
 179                          icu::ByteSink& sink,
 180                          UErrorCode* err);
 181
 182 /**
 183  * Minimize the 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 minimal form, or there is no data available
 189  * for minimization, it will be copied to the output buffer.  Since the
 190  * minimization algorithm relies on proper maximization, see the comments
 191  * for ulocimp_addLikelySubtags for reasons why there might not be any data.
 192  *
 193  * Examples:
 194  *
 195  * "en_Latn_US" minimizes to "en"
 196  *
 197  * "de_Latn_US" minimizes to "de"
 198  *
 199  * "sr_Cyrl_RS" minimizes to "sr"
 200  *
 201  * "zh_Hant_TW" minimizes to "zh_TW" (The region is preferred to the
 202  * script, and minimizing to "zh" would imply "zh_Hans_CN".)
 203  *
 204  * @param localeID The locale to minimize
 205  * @param sink The output sink receiving the maximized locale
 206  * @param err Error information if minimizing 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_STABLE void U_EXPORT2
 212 ulocimp_minimizeSubtags(const char* localeID,
 213                         icu::ByteSink& sink,
 214                         UErrorCode* err);
 215
 216 U_CAPI const char * U_EXPORT2
 217 locale_getKeywordsStart(const char *localeID);
 218
 219 U_CFUNC UBool
 220 ultag_isExtensionSubtags(const char* s, int32_t len);
 221
 222 U_CFUNC UBool
 223 ultag_isLanguageSubtag(const char* s, int32_t len);
 224
 225 U_CFUNC UBool
 226 ultag_isPrivateuseValueSubtags(const char* s, int32_t len);
 227
 228 U_CFUNC UBool
 229 ultag_isRegionSubtag(const char* s, int32_t len);
 230
 231 U_CFUNC UBool
 232 ultag_isScriptSubtag(const char* s, int32_t len);
 233
 234 U_CFUNC UBool
 235 ultag_isTransformedExtensionSubtags(const char* s, int32_t len);
 236
 237 U_CFUNC UBool
 238 ultag_isUnicodeExtensionSubtags(const char* s, int32_t len);
 239
 240 U_CFUNC UBool
 241 ultag_isUnicodeLocaleAttribute(const char* s, int32_t len);
 242
 243 U_CFUNC UBool
 244 ultag_isUnicodeLocaleAttributes(const char* s, int32_t len);
 245
 246 U_CFUNC UBool
 247 ultag_isUnicodeLocaleKey(const char* s, int32_t len);
 248
 249 U_CFUNC UBool
 250 ultag_isUnicodeLocaleType(const char* s, int32_t len);
 251
 252 U_CFUNC UBool
 253 ultag_isVariantSubtags(const char* s, int32_t len);
 254
 255 U_CFUNC const char*
 256 ulocimp_toBcpKey(const char* key);
 257
 258 U_CFUNC const char*
 259 ulocimp_toLegacyKey(const char* key);
 260
 261 U_CFUNC const char*
 262 ulocimp_toBcpType(const char* key, const char* type, UBool* isKnownKey, UBool* isSpecialType);
 263
 264 U_CFUNC const char*
 265 ulocimp_toLegacyType(const char* key, const char* type, UBool* isKnownKey, UBool* isSpecialType);
 266
 267 #endif