ICU-64232.0.1.tar.gz

[apple/icu.git] / icuSources / common / uloc.cpp

diff --git a/icuSources/common/uloc.cpp b/icuSources/common/uloc.cpp
index 85791dd13e6cfeb5126905b4f6c171b05056983c..10f9e8d6e37b55e145f77b068670a35e5a8e2974 100644 (file)
--- a/icuSources/common/uloc.cpp
+++ b/icuSources/common/uloc.cpp
@@ -457,8 +457,6 @@ NULL
 typedef struct CanonicalizationMap {
     const char *id;          /* input ID */
     const char *canonicalID; /* canonicalized output ID */
 typedef struct CanonicalizationMap {
     const char *id;          /* input ID */
     const char *canonicalID; /* canonicalized output ID */

-    const char *keyword;     /* keyword, or NULL if none */
-    const char *value;       /* keyword value, or NULL if kw==NULL */

 } CanonicalizationMap;
 
 /**
 } CanonicalizationMap;
 
 /**


@@ -466,64 +464,19 @@ typedef struct CanonicalizationMap {
  * different semantic kinds of transformations.
  */
 static const CanonicalizationMap CANONICALIZE_MAP[] = {
  * different semantic kinds of transformations.
  */
 static const CanonicalizationMap CANONICALIZE_MAP[] = {

-    { "",               "en_US_POSIX", NULL, NULL }, /* .NET name */
-    { "c",              "en_US_POSIX", NULL, NULL }, /* POSIX name */
-    { "posix",          "en_US_POSIX", NULL, NULL }, /* POSIX name (alias of C) */
-    { "art_LOJBAN",     "jbo", NULL, NULL }, /* registered name */
-    { "az_AZ_CYRL",     "az_Cyrl_AZ", NULL, NULL }, /* .NET name */
-    { "az_AZ_LATN",     "az_Latn_AZ", NULL, NULL }, /* .NET name */
-    { "ca_ES_PREEURO",  "ca_ES", "currency", "ESP" },
-    { "de__PHONEBOOK",  "de", "collation", "phonebook" }, /* Old ICU name */
-    { "de_AT_PREEURO",  "de_AT", "currency", "ATS" },
-    { "de_DE_PREEURO",  "de_DE", "currency", "DEM" },
-    { "de_LU_PREEURO",  "de_LU", "currency", "LUF" },
-    { "el_GR_PREEURO",  "el_GR", "currency", "GRD" },
-    { "en_BE_PREEURO",  "en_BE", "currency", "BEF" },
-    { "en_IE_PREEURO",  "en_IE", "currency", "IEP" },
-    { "es__TRADITIONAL", "es", "collation", "traditional" }, /* Old ICU name */
-    { "es_ES_PREEURO",  "es_ES", "currency", "ESP" },
-    { "eu_ES_PREEURO",  "eu_ES", "currency", "ESP" },
-    { "fi_FI_PREEURO",  "fi_FI", "currency", "FIM" },
-    { "fr_BE_PREEURO",  "fr_BE", "currency", "BEF" },
-    { "fr_FR_PREEURO",  "fr_FR", "currency", "FRF" },
-    { "fr_LU_PREEURO",  "fr_LU", "currency", "LUF" },
-    { "ga_IE_PREEURO",  "ga_IE", "currency", "IEP" },
-    { "gl_ES_PREEURO",  "gl_ES", "currency", "ESP" },
-    { "hi__DIRECT",     "hi", "collation", "direct" }, /* Old ICU name */
-    { "it_IT_PREEURO",  "it_IT", "currency", "ITL" },
-    { "ja_JP_TRADITIONAL", "ja_JP", "calendar", "japanese" }, /* Old ICU name */
-    { "nb_NO_NY",       "nn_NO", NULL, NULL },  /* "markus said this was ok" :-) */
-    { "nl_BE_PREEURO",  "nl_BE", "currency", "BEF" },
-    { "nl_NL_PREEURO",  "nl_NL", "currency", "NLG" },
-    { "pt_PT_PREEURO",  "pt_PT", "currency", "PTE" },
-    { "sr_SP_CYRL",     "sr_Cyrl_RS", NULL, NULL }, /* .NET name */
-    { "sr_SP_LATN",     "sr_Latn_RS", NULL, NULL }, /* .NET name */
-    { "sr_YU_CYRILLIC", "sr_Cyrl_RS", NULL, NULL }, /* Linux name */
-    { "th_TH_TRADITIONAL", "th_TH", "calendar", "buddhist" }, /* Old ICU name */
-    { "uz_UZ_CYRILLIC", "uz_Cyrl_UZ", NULL, NULL }, /* Linux name */
-    { "uz_UZ_CYRL",     "uz_Cyrl_UZ", NULL, NULL }, /* .NET name */
-    { "uz_UZ_LATN",     "uz_Latn_UZ", NULL, NULL }, /* .NET name */
-    { "zh_CHS",         "zh_Hans", NULL, NULL }, /* .NET name */
-    { "zh_CHT",         "zh_Hant", NULL, NULL }, /* .NET name */
-    { "zh_GAN",         "gan", NULL, NULL }, /* registered name */
-    { "zh_GUOYU",       "zh", NULL, NULL }, /* registered name */
-    { "zh_HAKKA",       "hak", NULL, NULL }, /* registered name */
-    { "zh_MIN_NAN",     "nan", NULL, NULL }, /* registered name */
-    { "zh_WUU",         "wuu", NULL, NULL }, /* registered name */
-    { "zh_XIANG",       "hsn", NULL, NULL }, /* registered name */
-    { "zh_YUE",         "yue", NULL, NULL }, /* registered name */
-};
-
-typedef struct VariantMap {
-    const char *variant;          /* input ID */
-    const char *keyword;     /* keyword, or NULL if none */
-    const char *value;       /* keyword value, or NULL if kw==NULL */
-} VariantMap;
-
-static const VariantMap VARIANT_MAP[] = {
-    { "EURO",   "currency", "EUR" },
-    { "PINYIN", "collation", "pinyin" }, /* Solaris variant */
-    { "STROKE", "collation", "stroke" }  /* Solaris variant */
+    { "",               "en_US_POSIX" }, /* .NET name */ // open ICU 64 deleted, we restore
+    { "c",              "en_US_POSIX" }, /* POSIX name */ // open ICU 64 deleted, we restore
+    { "posix",          "en_US_POSIX" }, /* POSIX name (alias of C) */ // open ICU 64 deleted, we restore
+    { "art_LOJBAN",     "jbo" }, /* registered name */
+    { "hy__AREVELA",    "hy" }, /* Registered IANA variant */
+    { "hy__AREVMDA",    "hyw" }, /* Registered IANA variant */
+    { "zh_GAN",         "gan" }, /* registered name */
+    { "zh_GUOYU",       "zh" }, /* registered name */
+    { "zh_HAKKA",       "hak" }, /* registered name */
+    { "zh_MIN_NAN",     "nan" }, /* registered name */
+    { "zh_WUU",         "wuu" }, /* registered name */
+    { "zh_XIANG",       "hsn" }, /* registered name */
+    { "zh_YUE",         "yue" }, /* registered name */

 };
 
 /* ### BCP47 Conversion *******************************************/
 };
 
 /* ### BCP47 Conversion *******************************************/


@@ -643,20 +596,12 @@ compareKeywordStructs(const void * /*context*/, const void *left, const void *ri
     return uprv_strcmp(leftString, rightString);
 }
 
     return uprv_strcmp(leftString, rightString);
 }
 

-/**
- * Both addKeyword and addValue must already be in canonical form.
- * Either both addKeyword and addValue are NULL, or neither is NULL.
- * If they are not NULL they must be zero terminated.
- * If addKeyword is not NULL is must have length small enough to fit in KeywordStruct.keyword.
- */

 static int32_t
 _getKeywords(const char *localeID,
              char prev,
              char *keywords, int32_t keywordCapacity,
              char *values, int32_t valuesCapacity, int32_t *valLen,
              UBool valuesToo,
 static int32_t
 _getKeywords(const char *localeID,
              char prev,
              char *keywords, int32_t keywordCapacity,
              char *values, int32_t valuesCapacity, int32_t *valLen,
              UBool valuesToo,

-             const char* addKeyword,
-             const char* addValue,

              UErrorCode *status)
 {
     KeywordStruct keywordList[ULOC_MAX_NO_KEYWORDS];
              UErrorCode *status)
 {
     KeywordStruct keywordList[ULOC_MAX_NO_KEYWORDS];


@@ -755,33 +700,6 @@ _getKeywords(const char *localeID,
             }
         } while(pos);
 
             }
         } while(pos);
 

-        /* Handle addKeyword/addValue. */
-        if (addKeyword != NULL) {
-            UBool duplicate = FALSE;
-            U_ASSERT(addValue != NULL);
-            /* Search for duplicate; if found, do nothing. Explicit keyword
-               overrides addKeyword. */
-            for (j=0; j<numKeywords; ++j) {
-                if (uprv_strcmp(keywordList[j].keyword, addKeyword) == 0) {
-                    duplicate = TRUE;
-                    break;
-                }
-            }
-            if (!duplicate) {
-                if (numKeywords == maxKeywords) {
-                    *status = U_INTERNAL_PROGRAM_ERROR;
-                    return 0;
-                }
-                uprv_strcpy(keywordList[numKeywords].keyword, addKeyword);
-                keywordList[numKeywords].keywordLen = (int32_t)uprv_strlen(addKeyword);
-                keywordList[numKeywords].valueStart = addValue;
-                keywordList[numKeywords].valueLen = (int32_t)uprv_strlen(addValue);
-                ++numKeywords;
-            }
-        } else {
-            U_ASSERT(addValue == NULL);
-        }
-

         /* now we have a list of keywords */
         /* we need to sort it */
         uprv_sortArray(keywordList, numKeywords, sizeof(KeywordStruct), compareKeywordStructs, NULL, FALSE, status);
         /* now we have a list of keywords */
         /* we need to sort it */
         uprv_sortArray(keywordList, numKeywords, sizeof(KeywordStruct), compareKeywordStructs, NULL, FALSE, status);


@@ -798,7 +716,7 @@ _getKeywords(const char *localeID,
             }
             keywordsLen += keywordList[i].keywordLen + 1;
             if(valuesToo) {
             }
             keywordsLen += keywordList[i].keywordLen + 1;
             if(valuesToo) {

-                if(keywordsLen + keywordList[i].valueLen < keywordCapacity) {
+                if(keywordsLen + keywordList[i].valueLen <= keywordCapacity) {

                     uprv_strncpy(keywords+keywordsLen, keywordList[i].valueStart, keywordList[i].valueLen);
                 }
                 keywordsLen += keywordList[i].valueLen;
                     uprv_strncpy(keywords+keywordsLen, keywordList[i].valueStart, keywordList[i].valueLen);
                 }
                 keywordsLen += keywordList[i].valueLen;


@@ -839,7 +757,7 @@ locale_getKeywords(const char *localeID,
                    UErrorCode *status) {
     return _getKeywords(localeID, prev, keywords, keywordCapacity,
                         values, valuesCapacity, valLen, valuesToo,
                    UErrorCode *status) {
     return _getKeywords(localeID, prev, keywords, keywordCapacity,
                         values, valuesCapacity, valLen, valuesToo,

-                        NULL, NULL, status);
+                        status);

 }
 
 U_CAPI int32_t U_EXPORT2
 }
 
 U_CAPI int32_t U_EXPORT2


@@ -1133,7 +1051,7 @@ uloc_setKeywordValue(const char* keywordName,
             keyValuePrefix = ';'; /* for any subsequent key-value pair */
             updatedKeysAndValues.append(localeKeywordNameBuffer, keyValueLen, *status);
             updatedKeysAndValues.append('=', *status);
             keyValuePrefix = ';'; /* for any subsequent key-value pair */
             updatedKeysAndValues.append(localeKeywordNameBuffer, keyValueLen, *status);
             updatedKeysAndValues.append('=', *status);

-            updatedKeysAndValues.append(nextEqualsign, keyValueTail-nextEqualsign, *status);
+            updatedKeysAndValues.append(nextEqualsign, static_cast<int32_t>(keyValueTail-nextEqualsign), *status);

         }
         if (!nextSeparator && keywordValueLen > 0 && !handledInputKeyAndValue) {
             /* append new entry at the end, it sorts later than existing entries */
         }
         if (!nextSeparator && keywordValueLen > 0 && !handledInputKeyAndValue) {
             /* append new entry at the end, it sorts later than existing entries */


@@ -1188,20 +1106,6 @@ uloc_setKeywordValue(const char* keywordName,
  */
 #define _isTerminator(a)  ((a==0)||(a=='.')||(a=='@'))
 
  */
 #define _isTerminator(a)  ((a==0)||(a=='.')||(a=='@'))
 

-static char* _strnchr(const char* str, int32_t len, char c) {
-    U_ASSERT(str != 0 && len >= 0);
-    while (len-- != 0) {
-        char d = *str;
-        if (d == c) {
-            return (char*) str;
-        } else if (d == 0) {
-            break;
-        }
-        ++str;
-    }
-    return NULL;
-}
-

 /**
  * Lookup 'key' in the array 'list'.  The array 'list' should contain
  * a NULL entry, followed by more entries, and a second NULL entry.
 /**
  * Lookup 'key' in the array 'list'.  The array 'list' should contain
  * a NULL entry, followed by more entries, and a second NULL entry.


@@ -1476,50 +1380,6 @@ _getVariant(const char *localeID,
     return _getVariantEx(localeID, prev, variant, variantCapacity, FALSE);
 }
 
     return _getVariantEx(localeID, prev, variant, variantCapacity, FALSE);
 }
 

-/**
- * Delete ALL instances of a variant from the given list of one or
- * more variants.  Example: "FOO_EURO_BAR_EURO" => "FOO_BAR".
- * @param variants the source string of one or more variants,
- * separated by '_'.  This will be MODIFIED IN PLACE.  Not zero
- * terminated; if it is, trailing zero will NOT be maintained.
- * @param variantsLen length of variants
- * @param toDelete variant to delete, without separators, e.g.  "EURO"
- * or "PREEURO"; not zero terminated
- * @param toDeleteLen length of toDelete
- * @return number of characters deleted from variants
- */
-static int32_t
-_deleteVariant(char* variants, int32_t variantsLen,
-               const char* toDelete, int32_t toDeleteLen)
-{
-    int32_t delta = 0; /* number of chars deleted */
-    for (;;) {
-        UBool flag = FALSE;
-        if (variantsLen < toDeleteLen) {
-            return delta;
-        }
-        if (uprv_strncmp(variants, toDelete, toDeleteLen) == 0 &&
-            (variantsLen == toDeleteLen ||
-             (flag=(variants[toDeleteLen] == '_'))))
-        {
-            int32_t d = toDeleteLen + (flag?1:0);
-            variantsLen -= d;
-            delta += d;
-            if (variantsLen > 0) {
-                uprv_memmove(variants, variants+d, variantsLen);
-            }
-        } else {
-            char* p = _strnchr(variants, variantsLen, '_');
-            if (p == NULL) {
-                return delta;
-            }
-            ++p;
-            variantsLen -= (int32_t)(p - variants);
-            variants = p;
-        }
-    }
-}
-

 /* Keyword enumeration */
 
 typedef struct UKeywordsContext {
 /* Keyword enumeration */
 
 typedef struct UKeywordsContext {


@@ -1698,8 +1558,6 @@ _canonicalize(const char* localeID,
     const char* tmpLocaleID;
     const char* keywordAssign = NULL;
     const char* separatorIndicator = NULL;
     const char* tmpLocaleID;
     const char* keywordAssign = NULL;
     const char* separatorIndicator = NULL;

-    const char* addKeyword = NULL;
-    const char* addValue = NULL;

     char* name;
     char* variant = NULL; /* pointer into name, or NULL */
 
     char* name;
     char* variant = NULL; /* pointer into name, or NULL */
 


@@ -1738,7 +1596,7 @@ _canonicalize(const char* localeID,
         len = (int32_t)uprv_strlen(d);
 
         if (name != NULL) {
         len = (int32_t)uprv_strlen(d);
 
         if (name != NULL) {

-            uprv_strncpy(name, d, len);
+            uprv_memcpy(name, d, len);

         }
     } else if(_isIDSeparator(*tmpLocaleID)) {
         const char *scriptID;
         }
     } else if(_isIDSeparator(*tmpLocaleID)) {
         const char *scriptID;


@@ -1864,27 +1722,6 @@ _canonicalize(const char* localeID,
             }
         }
 
             }
         }
 

-        /* Handle generic variants first */
-        if (variant) {
-            for (j=0; j<UPRV_LENGTHOF(VARIANT_MAP); j++) {
-                const char* variantToCompare = VARIANT_MAP[j].variant;
-                int32_t n = (int32_t)uprv_strlen(variantToCompare);
-                int32_t variantLen = _deleteVariant(variant, uprv_min(variantSize, (nameCapacity-len)), variantToCompare, n);
-                len -= variantLen;
-                if (variantLen > 0) {
-                    if (len > 0 && name[len-1] == '_') { /* delete trailing '_' */
-                        --len;
-                    }
-                    addKeyword = VARIANT_MAP[j].keyword;
-                    addValue = VARIANT_MAP[j].value;
-                    break;
-                }
-            }
-            if (len > 0 && len <= nameCapacity && name[len-1] == '_') { /* delete trailing '_' */
-                --len;
-            }
-        }
-

         /* Look up the ID in the canonicalization map */
         for (j=0; j<UPRV_LENGTHOF(CANONICALIZE_MAP); j++) {
             const char* id = CANONICALIZE_MAP[j].id;
         /* Look up the ID in the canonicalization map */
         for (j=0; j<UPRV_LENGTHOF(CANONICALIZE_MAP); j++) {
             const char* id = CANONICALIZE_MAP[j].id;


@@ -1894,10 +1731,6 @@ _canonicalize(const char* localeID,
                     break; /* Don't remap "" if keywords present */
                 }
                 len = _copyCount(name, nameCapacity, CANONICALIZE_MAP[j].canonicalID);
                     break; /* Don't remap "" if keywords present */
                 }
                 len = _copyCount(name, nameCapacity, CANONICALIZE_MAP[j].canonicalID);

-                if (CANONICALIZE_MAP[j].keyword) {
-                    addKeyword = CANONICALIZE_MAP[j].keyword;
-                    addValue = CANONICALIZE_MAP[j].value;
-                }

                 break;
             }
         }
                 break;
             }
         }


@@ -1912,14 +1745,7 @@ _canonicalize(const char* localeID,
             ++len;
             ++fieldCount;
             len += _getKeywords(tmpLocaleID+1, '@', (len<nameCapacity ? name+len : NULL), nameCapacity-len,
             ++len;
             ++fieldCount;
             len += _getKeywords(tmpLocaleID+1, '@', (len<nameCapacity ? name+len : NULL), nameCapacity-len,

-                                NULL, 0, NULL, TRUE, addKeyword, addValue, err);
-        } else if (addKeyword != NULL) {
-            U_ASSERT(addValue != NULL && len < nameCapacity);
-            /* inelegant but works -- later make _getKeywords do this? */
-            len += _copyCount(name+len, nameCapacity-len, "@");
-            len += _copyCount(name+len, nameCapacity-len, addKeyword);
-            len += _copyCount(name+len, nameCapacity-len, "=");
-            len += _copyCount(name+len, nameCapacity-len, addValue);
+                                NULL, 0, NULL, TRUE, err);

         }
     }
 
         }
     }
 


@@ -1957,6 +1783,7 @@ uloc_getParent(const char*    localeID,
     if(i>0 && parent != localeID) {
         uprv_memcpy(parent, localeID, uprv_min(i, parentCapacity));
     }
     if(i>0 && parent != localeID) {
         uprv_memcpy(parent, localeID, uprv_min(i, parentCapacity));
     }

+

     return u_terminateChars(parent, parentCapacity, i, err);
 }
 
     return u_terminateChars(parent, parentCapacity, i, err);
 }
 


@@ -2179,16 +2006,19 @@ uloc_getLCID(const char* localeID)
         return 0;
     }
 
         return 0;
     }
 

-    // Attempt platform lookup if available
-    lcid = uprv_convertToLCIDPlatform(localeID);
-    if (lcid > 0)
-    {
+    // First, attempt Windows platform lookup if available, but fall
+    // through to catch any special cases (ICU vs Windows name differences).
+    lcid = uprv_convertToLCIDPlatform(localeID, &status);
+    if (U_FAILURE(status)) {
+        return 0;
+    }
+    if (lcid > 0) {

         // Windows found an LCID, return that
         return lcid;
     }
 
     uloc_getLanguage(localeID, langID, sizeof(langID), &status);
         // Windows found an LCID, return that
         return lcid;
     }
 
     uloc_getLanguage(localeID, langID, sizeof(langID), &status);

-    if (U_FAILURE(status)) {
+    if (U_FAILURE(status) || status == U_STRING_NOT_TERMINATED_WARNING) {

         return 0;
     }
 
         return 0;
     }
 


@@ -2412,7 +2242,7 @@ uloc_acceptLanguageFromHTTP(char *result, int32_t resultAvailable, UAcceptResult
         /* eat spaces prior to semi */
         for(t=(paramEnd-1);(paramEnd>s)&&isspace(*t);t--)
             ;
         /* eat spaces prior to semi */
         for(t=(paramEnd-1);(paramEnd>s)&&isspace(*t);t--)
             ;

-        int32_t slen = ((t+1)-s);
+        int32_t slen = static_cast<int32_t>(((t+1)-s));

         if(slen > ULOC_FULLNAME_CAPACITY) {
           *status = U_BUFFER_OVERFLOW_ERROR;
           return -1; // too big
         if(slen > ULOC_FULLNAME_CAPACITY) {
           *status = U_BUFFER_OVERFLOW_ERROR;
           return -1; // too big