icuSources/test/cintltst/cucdapi.c

   1 /********************************************************************
   2  * COPYRIGHT:
   3  * Copyright (c) 1997-2003, International Business Machines Corporation and
   4  * others. All Rights Reserved.
   5  ********************************************************************/
   6
   7 #include <string.h>
   8 #include "unicode/utypes.h"
   9 #include "unicode/uscript.h"
  10 #include "unicode/uchar.h"
  11 #include "cintltst.h"
  12 #include "cucdapi.h"
  13
  14 void TestUScriptCodeAPI(){
  15     int i =0;
  16     int numErrors =0;
  17     {
  18         const char* testNames[]={
  19         /* test locale */
  20         "en", "en_US", "sr", "ta" , "te_IN",
  21         "hi", "he", "ar",
  22         /* test abbr */
  23         "Hani", "Hang","Hebr","Hira",
  24         "Knda","Kana","Khmr","Lao",
  25         "Latn",/*"Latf","Latg",*/
  26         "Mlym", "Mong",
  27
  28         /* test names */
  29         "CYRILLIC","DESERET","DEVANAGARI","ETHIOPIC","GEORGIAN",
  30         "GOTHIC",  "GREEK",  "GUJARATI", "COMMON", "INHERITED",
  31         /* test lower case names */
  32         "malayalam", "mongolian", "myanmar", "ogham", "old-italic",
  33         "oriya",     "runic",     "sinhala", "syriac","tamil",
  34         "telugu",    "thaana",    "thai",    "tibetan",
  35         /* test the bounds*/
  36         "tagb", "arabic",
  37         /* test bogus */
  38         "asfdasd", "5464", "12235",
  39         /* test the last index */
  40         "zyyy", "YI",
  41         '\0'
  42         };
  43         UScriptCode expected[] ={
  44             /* locales should return */
  45             USCRIPT_LATIN, USCRIPT_LATIN, USCRIPT_CYRILLIC, USCRIPT_TAMIL, USCRIPT_TELUGU,
  46             USCRIPT_DEVANAGARI, USCRIPT_HEBREW, USCRIPT_ARABIC,
  47             /* abbr should return */
  48             USCRIPT_HAN, USCRIPT_HANGUL, USCRIPT_HEBREW, USCRIPT_HIRAGANA,
  49             USCRIPT_KANNADA, USCRIPT_KATAKANA, USCRIPT_KHMER, USCRIPT_LAO,
  50             USCRIPT_LATIN,/* USCRIPT_LATIN, USCRIPT_LATIN,*/
  51             USCRIPT_MALAYALAM, USCRIPT_MONGOLIAN,
  52             /* names should return */
  53             USCRIPT_CYRILLIC, USCRIPT_DESERET, USCRIPT_DEVANAGARI, USCRIPT_ETHIOPIC, USCRIPT_GEORGIAN,
  54             USCRIPT_GOTHIC, USCRIPT_GREEK, USCRIPT_GUJARATI, USCRIPT_COMMON, USCRIPT_INHERITED,
  55             /* lower case names should return */
  56             USCRIPT_MALAYALAM, USCRIPT_MONGOLIAN, USCRIPT_MYANMAR, USCRIPT_OGHAM, USCRIPT_OLD_ITALIC,
  57             USCRIPT_ORIYA, USCRIPT_RUNIC, USCRIPT_SINHALA, USCRIPT_SYRIAC, USCRIPT_TAMIL,
  58             USCRIPT_TELUGU, USCRIPT_THAANA, USCRIPT_THAI, USCRIPT_TIBETAN,
  59             /* bounds */
  60             USCRIPT_TAGBANWA, USCRIPT_ARABIC,
  61             /* bogus names should return invalid code */
  62             USCRIPT_INVALID_CODE, USCRIPT_INVALID_CODE, USCRIPT_INVALID_CODE,
  63             USCRIPT_COMMON, USCRIPT_YI,
  64         };
  65
  66         UErrorCode err = U_ZERO_ERROR;
  67
  68         const int32_t capacity = 10;
  69
  70         for( ; testNames[i]!='\0'; i++){
  71             UScriptCode script[10]={USCRIPT_INVALID_CODE};
  72             uscript_getCode(testNames[i],script,capacity, &err);
  73             if( script[0] != expected[i]){
  74                    log_err("Error getting script code Got: %i  Expected: %i for name %s\n",
  75                        script[0],expected[i],testNames[i]);
  76                    numErrors++;
  77             }
  78         }
  79         if(numErrors >0 ){
  80             log_data_err("Errors uchar_getScriptCode() : %i \n",numErrors);
  81         }
  82     }
  83
  84     {
  85         UErrorCode err = U_ZERO_ERROR;
  86         int32_t capacity=0;
  87         UScriptCode jaCode[]={ USCRIPT_KATAKANA,USCRIPT_HIRAGANA,USCRIPT_HAN};
  88         UScriptCode script[10]={USCRIPT_INVALID_CODE};
  89         int32_t num = uscript_getCode("ja",script,capacity, &err);
  90         /* preflight */
  91         if(err==U_BUFFER_OVERFLOW_ERROR){
  92             err = U_ZERO_ERROR;
  93             capacity = 10;
  94             num = uscript_getCode("ja",script,capacity, &err);
  95             if(num!=(sizeof(jaCode)/sizeof(UScriptCode)) || script[0]!=jaCode[0] || script[1]!=jaCode[1]){
  96                 log_err("Errors uscript_getScriptCode() for Japaneese locale \n");
  97             }
  98         }else{
  99             log_data_err("Errors in uscript_getScriptCode() expected error : %s got: %s \n",
 100                 "U_BUFFER_OVERFLOW_ERROR",
 101                  u_errorName(err));
 102         }
 103
 104     }
 105
 106     {
 107         UScriptCode testAbbr[]={
 108             /* names should return */
 109             USCRIPT_CYRILLIC, USCRIPT_DESERET, USCRIPT_DEVANAGARI, USCRIPT_ETHIOPIC, USCRIPT_GEORGIAN,
 110             USCRIPT_GOTHIC, USCRIPT_GREEK, USCRIPT_GUJARATI,
 111         };
 112
 113         const char* expectedNames[]={
 114
 115             /* test names */
 116             "Cyrillic","Deseret","Devanagari","Ethiopic","Georgian",
 117             "Gothic",  "Greek",  "Gujarati",
 118              '\0'
 119         };
 120         i=0;
 121         while(i<sizeof(testAbbr)/sizeof(UScriptCode)){
 122             const char* name = uscript_getName(testAbbr[i]);
 123              if(name == NULL) {
 124                log_data_err("Couldn't get script name\n");
 125                return;
 126              }
 127             numErrors=0;
 128             if(strcmp(expectedNames[i],name)!=0){
 129                 log_err("Error getting abbreviations Got: %s Expected: %s\n",name,expectedNames[i]);
 130                 numErrors++;
 131             }
 132             if(numErrors > 0){
 133                 if(numErrors >0 ){
 134                     log_err("Errors uchar_getScriptAbbr() : %i \n",numErrors);
 135                 }
 136             }
 137             i++;
 138         }
 139
 140     }
 141
 142     {
 143         UScriptCode testAbbr[]={
 144             /* abbr should return */
 145             USCRIPT_HAN, USCRIPT_HANGUL, USCRIPT_HEBREW, USCRIPT_HIRAGANA,
 146             USCRIPT_KANNADA, USCRIPT_KATAKANA, USCRIPT_KHMER, USCRIPT_LAO,
 147             USCRIPT_LATIN,
 148             USCRIPT_MALAYALAM, USCRIPT_MONGOLIAN,
 149         };
 150
 151         const char* expectedAbbr[]={
 152               /* test abbr */
 153             "Hani", "Hang","Hebr","Hira",
 154             "Knda","Kana","Khmr","Laoo",
 155             "Latn",
 156             "Mlym", "Mong",
 157              '\0'
 158         };
 159         i=0;
 160         while(i<sizeof(testAbbr)/sizeof(UScriptCode)){
 161             const char* name = uscript_getShortName(testAbbr[i]);
 162             numErrors=0;
 163             if(strcmp(expectedAbbr[i],name)!=0){
 164                 log_err("Error getting abbreviations Got: %s Expected: %s\n",name,expectedAbbr[i]);
 165                 numErrors++;
 166             }
 167             if(numErrors > 0){
 168                 if(numErrors >0 ){
 169                     log_err("Errors uchar_getScriptAbbr() : %i \n",numErrors);
 170                 }
 171             }
 172             i++;
 173         }
 174
 175     }
 176     /* now test uscript_getScript() API */
 177     {
 178 #define MAX_ARRAY_SIZE 23
 179         uint32_t codepoints[] = {
 180                 0x0000FF9D, /* USCRIPT_KATAKANA*/
 181                 0x0000FFBE, /* USCRIPT_HANGUL*/
 182                 0x0000FFC7, /* USCRIPT_HANGUL*/
 183                 0x0000FFCF, /* USCRIPT_HANGUL*/
 184                 0x0000FFD7, /* USCRIPT_HANGUL*/
 185                 0x0000FFDC, /* USCRIPT_HANGUL*/
 186                 0x00010300, /* USCRIPT_OLD_ITALIC*/
 187                 0x00010330, /* USCRIPT_GOTHIC*/
 188                 0x0001034A, /* USCRIPT_GOTHIC*/
 189                 0x00010400, /* USCRIPT_DESERET*/
 190                 0x00010428, /* USCRIPT_DESERET*/
 191                 0x0001D167, /* USCRIPT_INHERITED*/
 192                 0x0001D17B, /* USCRIPT_INHERITED*/
 193                 0x0001D185, /* USCRIPT_INHERITED*/
 194                 0x0001D1AA, /* USCRIPT_INHERITED*/
 195                 0x00020000, /* USCRIPT_HAN*/
 196                 0x00000D02, /* USCRIPT_MALAYALAM*/
 197                 0x00000D00, /* USCRIPT_COMMON */
 198                 0x00000000, /* USCRIPT_COMMON*/
 199                 0x0001D169, /* USCRIPT_INHERITED*/
 200                 0x0001D182, /* USCRIPT_INHERITED*/
 201                 0x0001D18B, /* USCRIPT_INHERITED*/
 202                 0x0001D1AD, /* USCRIPT_INHERITED*/
 203                 0x00110000, /* USCRIPT_INVALID_CODE */
 204         };
 205
 206         UScriptCode expected[] = {
 207                 USCRIPT_KATAKANA ,
 208                 USCRIPT_HANGUL ,
 209                 USCRIPT_HANGUL ,
 210                 USCRIPT_HANGUL ,
 211                 USCRIPT_HANGUL ,
 212                 USCRIPT_HANGUL ,
 213                 USCRIPT_OLD_ITALIC,
 214                 USCRIPT_GOTHIC ,
 215                 USCRIPT_GOTHIC ,
 216                 USCRIPT_DESERET ,
 217                 USCRIPT_DESERET ,
 218                 USCRIPT_INHERITED,
 219                 USCRIPT_INHERITED,
 220                 USCRIPT_INHERITED,
 221                 USCRIPT_INHERITED,
 222                 USCRIPT_HAN ,
 223                 USCRIPT_MALAYALAM,
 224                 USCRIPT_COMMON,
 225                 USCRIPT_COMMON,
 226                 USCRIPT_INHERITED ,
 227                 USCRIPT_INHERITED ,
 228                 USCRIPT_INHERITED ,
 229                 USCRIPT_INHERITED ,
 230                 USCRIPT_INVALID_CODE,
 231         };
 232         UScriptCode code = USCRIPT_INVALID_CODE;
 233         UErrorCode status = U_ZERO_ERROR;
 234         UBool passed = TRUE;
 235
 236         i =0;
 237         while(i< MAX_ARRAY_SIZE){
 238             code = uscript_getScript(codepoints[i],&status);
 239             if(U_SUCCESS(status)){
 240                 if( code != expected[i] ||
 241                     code != (UScriptCode)u_getIntPropertyValue(codepoints[i], UCHAR_SCRIPT)
 242                 ) {
 243                     log_err("uscript_getScript for codepoint \\U%08X failed\n",codepoints[i]);
 244                     passed = FALSE;
 245                 }
 246             }else{
 247                 log_err("uscript_getScript for codepoint \\U%08X failed. Error: %s\n",
 248                          codepoints[i],u_errorName(status));
 249                 break;
 250             }
 251             i++;
 252         }
 253
 254         if(passed==FALSE){
 255            log_err("uscript_getScript failed.\n");
 256         }
 257     }
 258     {
 259         UScriptCode code= USCRIPT_INVALID_CODE;
 260         UErrorCode  status = U_ZERO_ERROR;
 261         code = uscript_getScript(0x001D169,&status);
 262         if(code != USCRIPT_INHERITED){
 263             log_err("\\U001D169 is not contained in USCRIPT_INHERITED");
 264         }
 265     }
 266     {
 267         UScriptCode code= USCRIPT_INVALID_CODE;
 268         UErrorCode  status = U_ZERO_ERROR;
 269         int32_t err = 0;
 270
 271         for(i = 0; i<=0x10ffff; i++){
 272             code =  uscript_getScript(i,&status);
 273             if(code == USCRIPT_INVALID_CODE){
 274                 err++;
 275                 log_err("uscript_getScript for codepoint \\U%08X failed.\n", i);
 276             }
 277         }
 278         if(err>0){
 279             log_err("uscript_getScript failed for %d codepoints\n", err);
 280         }
 281     }
 282     {
 283         for(i=0; (UScriptCode)i< USCRIPT_CODE_LIMIT; i++){
 284             const char* name = uscript_getName((UScriptCode)i);
 285             if(name==NULL || strcmp(name,"")==0){
 286                 log_err("uscript_getName failed for code : %i\n",i);
 287             }
 288         }
 289     }
 290
 291
 292  }