ICU-9013 deprecate API for Unicode 1.0 character names & ISO comments, remove support & data

X-SVN-Rev: 31125

icu4c/source/common/unames.cpp

@@ -700,6 +700,18 @@ enumNames(UCharNames *names,
     /* find the group that contains start, or the highest before it */
     group=getGroup(names, start);
 
+    if(startGroupMSB<group[GROUP_MSB] && nameChoice==U_EXTENDED_CHAR_NAME) {
+        /* enumerate synthetic names between start and the group start */
+        UChar32 extLimit=((UChar32)group[GROUP_MSB]<<GROUP_SHIFT);
+        if(extLimit>limit) {
+            extLimit=limit;
+        }
+        if(!enumExtNames(start, extLimit-1, fn, context)) {
+            return FALSE;
+        }
+        start=extLimit;
+    }
+
     if(startGroupMSB==endGroupMSB) {
         if(startGroupMSB==group[GROUP_MSB]) {
             /* if start and limit-1 are in the same group, then enumerate only in that one */
@@ -1508,11 +1520,9 @@ u_charName(UChar32 code, UCharNameChoice nameChoice,
 }
 
 U_CAPI int32_t U_EXPORT2
-u_getISOComment(UChar32 c,
+u_getISOComment(UChar32 /*c*/,
                 char *dest, int32_t destCapacity,
                 UErrorCode *pErrorCode) {
-    int32_t length;
-
     /* check the argument values */
     if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) {
         return 0;
@@ -1521,13 +1531,7 @@ u_getISOComment(UChar32 c,
         return 0;
     }
 
-    if((uint32_t)c>UCHAR_MAX_VALUE || !isDataLoaded(pErrorCode)) {
+    return u_terminateChars(dest, destCapacity, 0, pErrorCode);
-        return u_terminateChars(dest, destCapacity, 0, pErrorCode);
-    }
-
-    /* the ISO comment is stored like a normal character name */
-    length=getName(uCharNames, (uint32_t)c, U_ISO_COMMENT, dest, (uint16_t)destCapacity);
-    return u_terminateChars(dest, destCapacity, length, pErrorCode);
 }
 
 U_CAPI UChar32 U_EXPORT2

icu4c/source/common/unicode/uchar.h

@@ -527,8 +527,8 @@ typedef enum UProperty {
     /** String property Case_Folding.
         Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */
     UCHAR_CASE_FOLDING=0x4002,
-    /** String property ISO_Comment.
+    /** Deprecated string property ISO_Comment.
-        Corresponds to u_getISOComment. @stable ICU 2.4 */
+        Corresponds to u_getISOComment. @deprecated ICU 49 */
     UCHAR_ISO_COMMENT=0x4003,
     /** String property Lowercase_Mapping.
         Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */
@@ -552,7 +552,9 @@ typedef enum UProperty {
         Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */
     UCHAR_TITLECASE_MAPPING=0x400A,
     /** String property Unicode_1_Name.
-        Corresponds to u_charName. @stable ICU 2.4 */
+        This property is of little practical value.
+        Beginning with ICU 49, ICU APIs return an empty string for this property.
+        Corresponds to u_charName(U_UNICODE_10_CHAR_NAME). @deprecated ICU 49 */
     UCHAR_UNICODE_1_NAME=0x400B,
     /** String property Uppercase_Mapping.
         Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */
@@ -1451,10 +1453,19 @@ typedef enum UEastAsianWidth {
  * @stable ICU 2.0
  */
 typedef enum UCharNameChoice {
+    /** Unicode character name (Name property). @stable ICU 2.0 */
     U_UNICODE_CHAR_NAME,
+    /**
+     * The Unicode_1_Name property value which is of little practical value.
+     * Beginning with ICU 49, ICU APIs return an empty string for this name choice.
+     * @deprecated ICU 49
+     */
     U_UNICODE_10_CHAR_NAME,
+    /** Standard or synthetic character name. @stable ICU 2.0 */
     U_EXTENDED_CHAR_NAME,
-    U_CHAR_NAME_ALIAS,          /**< Corrected name from NameAliases.txt. @stable ICU 4.4 */
+    /** Corrected name from NameAliases.txt. @stable ICU 4.4 */
+    U_CHAR_NAME_ALIAS,
+    /** @stable ICU 2.0 */
     U_CHAR_NAME_CHOICE_COUNT
 } UCharNameChoice;
 
@@ -2584,12 +2595,9 @@ u_charName(UChar32 code, UCharNameChoice nameChoice,
            UErrorCode *pErrorCode);
 
 /**
- * Get the ISO 10646 comment for a character.
+ * Returns an empty string.
- * The ISO 10646 comment is an informative field in the Unicode Character
+ * Used to return the ISO 10646 comment for a character.
- * Database (UnicodeData.txt field 11) and is from the ISO 10646 names list.
+ * The Unicode ISO_Comment property is deprecated and has no values.
- *
- * Note: Unicode 5.2 removes all ISO comment data, resulting in empty strings
- * returned for all characters.
  *
  * @param c The character (code point) for which to get the ISO comment.
  *             It must be <code>0<=c<=0x10ffff</code>.
@@ -2600,13 +2608,9 @@ u_charName(UChar32 code, UCharNameChoice nameChoice,
  * @param pErrorCode Pointer to a UErrorCode variable;
  *        check for <code>U_SUCCESS()</code> after <code>u_getISOComment()</code>
  *        returns.
- * @return The length of the comment, or 0 if there is no comment for this character.
+ * @return 0
- *         If the destCapacity is less than or equal to the length, then the buffer
- *         contains the truncated name and the returned length indicates the full
- *         length of the name.
- *         The length does not include the zero-termination.
  *
- * @stable ICU 2.2
+ * @deprecated ICU 49
  */
 U_STABLE int32_t U_EXPORT2
 u_getISOComment(UChar32 c,

icu4c/source/common/uniset_props.cpp

@@ -1040,15 +1040,12 @@ UnicodeSet::applyPropertyAlias(const UnicodeString& prop,
                 }
                 break;
             case UCHAR_NAME:
-            case UCHAR_UNICODE_1_NAME:
                 {
                     // Must munge name, since u_charFromName() does not do
                     // 'loose' matching.
                     char buf[128]; // it suffices that this be > uprv_getMaxCharNameLength
                     if (!mungeCharName(buf, vname.data(), sizeof(buf))) FAIL(ec);
-                    UCharNameChoice choice = (p == UCHAR_NAME) ?
+                    UChar32 ch = u_charFromName(U_EXTENDED_CHAR_NAME, buf, &ec);
-                        U_EXTENDED_CHAR_NAME : U_UNICODE_10_CHAR_NAME;
-                    UChar32 ch = u_charFromName(choice, buf, &ec);
                     if (U_SUCCESS(ec)) {
                         clear();
                         add(ch);
@@ -1058,6 +1055,9 @@ UnicodeSet::applyPropertyAlias(const UnicodeString& prop,
                     }
                 }
                 break;
+            case UCHAR_UNICODE_1_NAME:
+                // ICU 49 deprecates the Unicode_1_Name property APIs.
+                FAIL(ec);
             case UCHAR_AGE:
                 {
                     // Must munge name, since u_versionFromString() does not do

icu4c/source/samples/ucnv/convsamp.cpp

@@ -58,20 +58,13 @@ void prettyPrintUChar(UChar c)
     char buf[1000];
     UErrorCode status = U_ZERO_ERROR;
     int32_t o;
-    
+
-    o = u_charName(c, U_UNICODE_CHAR_NAME, buf, 1000, &status);
+    o = u_charName(c, U_EXTENDED_CHAR_NAME, buf, 1000, &status);
     if(U_SUCCESS(status) && (o>0) ) {
       buf[6] = 0;
       printf("%7s", buf);
     } else {
-      o = u_charName(c, U_UNICODE_10_CHAR_NAME, buf, 1000, &status);
+      printf(" ??????");
-      if(U_SUCCESS(status) && (o>0)) {
-        buf[5] = 0;
-        printf("~%6s", buf);
-      }
-      else {
-        printf(" ??????");
-      }
     }
   } else {
     switch((char)(c & 0x007F)) {

icu4c/source/test/cintltst/cucdtst.c

@@ -1581,12 +1581,10 @@ static const struct {
     const char *name, *oldName, *extName, *alias;
 } names[]={
     {0x0061, "LATIN SMALL LETTER A", "", "LATIN SMALL LETTER A"},
-    {0x01a2, "LATIN CAPITAL LETTER OI",
+    {0x01a2, "LATIN CAPITAL LETTER OI", "",
-             "LATIN CAPITAL LETTER O I",
              "LATIN CAPITAL LETTER OI",
              "LATIN CAPITAL LETTER GHA"},
-    {0x0284, "LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK",
+    {0x0284, "LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK", "",
-             "LATIN SMALL LETTER DOTLESS J BAR HOOK",
              "LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK" },
     {0x0fd0, "TIBETAN MARK BSKA- SHOG GI MGO RGYAN", "",
              "TIBETAN MARK BSKA- SHOG GI MGO RGYAN",
@@ -1597,7 +1595,7 @@ static const struct {
     {0xd7a3, "HANGUL SYLLABLE HIH", "", "HANGUL SYLLABLE HIH" },
     {0xd800, "", "", "<lead surrogate-D800>" },
     {0xdc00, "", "", "<trail surrogate-DC00>" },
-    {0xff08, "FULLWIDTH LEFT PARENTHESIS", "FULLWIDTH OPENING PARENTHESIS", "FULLWIDTH LEFT PARENTHESIS" },
+    {0xff08, "FULLWIDTH LEFT PARENTHESIS", "", "FULLWIDTH LEFT PARENTHESIS" },
     {0xffe5, "FULLWIDTH YEN SIGN", "", "FULLWIDTH YEN SIGN" },
     {0xffff, "", "", "<noncharacter-FFFF>" },
     {0x1d0c5, "BYZANTINE MUSICAL SYMBOL FHTORA SKLIRON CHROMA VASIS", "",

icu4c/source/test/intltest/transtst.cpp

@@ -1277,8 +1277,8 @@ void TransliteratorTest::TestNameMap(void) {
 
     // Careful:  CharsToUS will convert "\\N" => "N"; use "\\\\N" for \N
     expect(*uni2name, CharsToUnicodeString("\\u00A0abc\\u4E01\\u00B5\\u0A81\\uFFFD\\u0004\\u0009\\u0081\\uFFFF"),
-           CharsToUnicodeString("\\\\N{NO-BREAK SPACE}abc\\\\N{CJK UNIFIED IDEOGRAPH-4E01}\\\\N{MICRO SIGN}\\\\N{GUJARATI SIGN CANDRABINDU}\\\\N{REPLACEMENT CHARACTER}\\\\N{END OF TRANSMISSION}\\\\N{CHARACTER TABULATION}\\\\N{<control-0081>}\\\\N{<noncharacter-FFFF>}"));
+           CharsToUnicodeString("\\\\N{NO-BREAK SPACE}abc\\\\N{CJK UNIFIED IDEOGRAPH-4E01}\\\\N{MICRO SIGN}\\\\N{GUJARATI SIGN CANDRABINDU}\\\\N{REPLACEMENT CHARACTER}\\\\N{<control-0004>}\\\\N{<control-0009>}\\\\N{<control-0081>}\\\\N{<noncharacter-FFFF>}"));
-    expect(*name2uni, UNICODE_STRING_SIMPLE("{\\N { NO-BREAK SPACE}abc\\N{  CJK UNIFIED  IDEOGRAPH-4E01  }\\N{x\\N{MICRO SIGN}\\N{GUJARATI SIGN CANDRABINDU}\\N{REPLACEMENT CHARACTER}\\N{END OF TRANSMISSION}\\N{CHARACTER TABULATION}\\N{<control-0081>}\\N{<noncharacter-FFFF>}\\N{<control-0004>}\\N{"),
+    expect(*name2uni, UNICODE_STRING_SIMPLE("{\\N { NO-BREAK SPACE}abc\\N{  CJK UNIFIED  IDEOGRAPH-4E01  }\\N{x\\N{MICRO SIGN}\\N{GUJARATI SIGN CANDRABINDU}\\N{REPLACEMENT CHARACTER}\\N{<control-0004>}\\N{<control-0009>}\\N{<control-0081>}\\N{<noncharacter-FFFF>}\\N{<control-0004>}\\N{"),
            CharsToUnicodeString("{\\u00A0abc\\u4E01\\\\N{x\\u00B5\\u0A81\\uFFFD\\u0004\\u0009\\u0081\\uFFFF\\u0004\\\\N{"));
 
     delete uni2name;