293 lines
10 KiB
C
293 lines
10 KiB
C
/********************************************************************
|
|
* COPYRIGHT:
|
|
* Copyright (c) 1997-2005, International Business Machines Corporation and
|
|
* others. All Rights Reserved.
|
|
********************************************************************/
|
|
|
|
#include <string.h>
|
|
#include "unicode/utypes.h"
|
|
#include "unicode/uscript.h"
|
|
#include "unicode/uchar.h"
|
|
#include "cintltst.h"
|
|
#include "cucdapi.h"
|
|
|
|
void TestUScriptCodeAPI(){
|
|
int i =0;
|
|
int numErrors =0;
|
|
{
|
|
const char* testNames[]={
|
|
/* test locale */
|
|
"en", "en_US", "sr", "ta" , "te_IN",
|
|
"hi", "he", "ar",
|
|
/* test abbr */
|
|
"Hani", "Hang","Hebr","Hira",
|
|
"Knda","Kana","Khmr","Lao",
|
|
"Latn",/*"Latf","Latg",*/
|
|
"Mlym", "Mong",
|
|
|
|
/* test names */
|
|
"CYRILLIC","DESERET","DEVANAGARI","ETHIOPIC","GEORGIAN",
|
|
"GOTHIC", "GREEK", "GUJARATI", "COMMON", "INHERITED",
|
|
/* test lower case names */
|
|
"malayalam", "mongolian", "myanmar", "ogham", "old-italic",
|
|
"oriya", "runic", "sinhala", "syriac","tamil",
|
|
"telugu", "thaana", "thai", "tibetan",
|
|
/* test the bounds*/
|
|
"tagb", "arabic",
|
|
/* test bogus */
|
|
"asfdasd", "5464", "12235",
|
|
/* test the last index */
|
|
"zyyy", "YI",
|
|
'\0'
|
|
};
|
|
UScriptCode expected[] ={
|
|
/* locales should return */
|
|
USCRIPT_LATIN, USCRIPT_LATIN, USCRIPT_CYRILLIC, USCRIPT_TAMIL, USCRIPT_TELUGU,
|
|
USCRIPT_DEVANAGARI, USCRIPT_HEBREW, USCRIPT_ARABIC,
|
|
/* abbr should return */
|
|
USCRIPT_HAN, USCRIPT_HANGUL, USCRIPT_HEBREW, USCRIPT_HIRAGANA,
|
|
USCRIPT_KANNADA, USCRIPT_KATAKANA, USCRIPT_KHMER, USCRIPT_LAO,
|
|
USCRIPT_LATIN,/* USCRIPT_LATIN, USCRIPT_LATIN,*/
|
|
USCRIPT_MALAYALAM, USCRIPT_MONGOLIAN,
|
|
/* names should return */
|
|
USCRIPT_CYRILLIC, USCRIPT_DESERET, USCRIPT_DEVANAGARI, USCRIPT_ETHIOPIC, USCRIPT_GEORGIAN,
|
|
USCRIPT_GOTHIC, USCRIPT_GREEK, USCRIPT_GUJARATI, USCRIPT_COMMON, USCRIPT_INHERITED,
|
|
/* lower case names should return */
|
|
USCRIPT_MALAYALAM, USCRIPT_MONGOLIAN, USCRIPT_MYANMAR, USCRIPT_OGHAM, USCRIPT_OLD_ITALIC,
|
|
USCRIPT_ORIYA, USCRIPT_RUNIC, USCRIPT_SINHALA, USCRIPT_SYRIAC, USCRIPT_TAMIL,
|
|
USCRIPT_TELUGU, USCRIPT_THAANA, USCRIPT_THAI, USCRIPT_TIBETAN,
|
|
/* bounds */
|
|
USCRIPT_TAGBANWA, USCRIPT_ARABIC,
|
|
/* bogus names should return invalid code */
|
|
USCRIPT_INVALID_CODE, USCRIPT_INVALID_CODE, USCRIPT_INVALID_CODE,
|
|
USCRIPT_COMMON, USCRIPT_YI,
|
|
};
|
|
|
|
UErrorCode err = U_ZERO_ERROR;
|
|
|
|
const int32_t capacity = 10;
|
|
|
|
for( ; testNames[i]!='\0'; i++){
|
|
UScriptCode script[10]={USCRIPT_INVALID_CODE};
|
|
uscript_getCode(testNames[i],script,capacity, &err);
|
|
if( script[0] != expected[i]){
|
|
log_err("Error getting script code Got: %i Expected: %i for name %s\n",
|
|
script[0],expected[i],testNames[i]);
|
|
numErrors++;
|
|
}
|
|
}
|
|
if(numErrors >0 ){
|
|
log_data_err("Errors uchar_getScriptCode() : %i \n",numErrors);
|
|
}
|
|
}
|
|
|
|
{
|
|
UErrorCode err = U_ZERO_ERROR;
|
|
int32_t capacity=0;
|
|
UScriptCode jaCode[]={USCRIPT_KATAKANA, USCRIPT_HIRAGANA, USCRIPT_HAN };
|
|
UScriptCode script[10]={USCRIPT_INVALID_CODE};
|
|
int32_t num = uscript_getCode("ja",script,capacity, &err);
|
|
/* preflight */
|
|
if(err==U_BUFFER_OVERFLOW_ERROR){
|
|
err = U_ZERO_ERROR;
|
|
capacity = 10;
|
|
num = uscript_getCode("ja",script,capacity, &err);
|
|
if(num!=(sizeof(jaCode)/sizeof(UScriptCode)) || script[0]!=jaCode[0] || script[1]!=jaCode[1]){
|
|
log_err("Errors uscript_getScriptCode() for Japaneese locale \n");
|
|
}
|
|
}else{
|
|
log_data_err("Errors in uscript_getScriptCode() expected error : %s got: %s \n",
|
|
"U_BUFFER_OVERFLOW_ERROR",
|
|
u_errorName(err));
|
|
}
|
|
|
|
}
|
|
|
|
{
|
|
UScriptCode testAbbr[]={
|
|
/* names should return */
|
|
USCRIPT_CYRILLIC, USCRIPT_DESERET, USCRIPT_DEVANAGARI, USCRIPT_ETHIOPIC, USCRIPT_GEORGIAN,
|
|
USCRIPT_GOTHIC, USCRIPT_GREEK, USCRIPT_GUJARATI,
|
|
};
|
|
|
|
const char* expectedNames[]={
|
|
|
|
/* test names */
|
|
"Cyrillic","Deseret","Devanagari","Ethiopic","Georgian",
|
|
"Gothic", "Greek", "Gujarati",
|
|
'\0'
|
|
};
|
|
i=0;
|
|
while(i<sizeof(testAbbr)/sizeof(UScriptCode)){
|
|
const char* name = uscript_getName(testAbbr[i]);
|
|
if(name == NULL) {
|
|
log_data_err("Couldn't get script name\n");
|
|
return;
|
|
}
|
|
numErrors=0;
|
|
if(strcmp(expectedNames[i],name)!=0){
|
|
log_err("Error getting abbreviations Got: %s Expected: %s\n",name,expectedNames[i]);
|
|
numErrors++;
|
|
}
|
|
if(numErrors > 0){
|
|
if(numErrors >0 ){
|
|
log_err("Errors uchar_getScriptAbbr() : %i \n",numErrors);
|
|
}
|
|
}
|
|
i++;
|
|
}
|
|
|
|
}
|
|
|
|
{
|
|
UScriptCode testAbbr[]={
|
|
/* abbr should return */
|
|
USCRIPT_HAN, USCRIPT_HANGUL, USCRIPT_HEBREW, USCRIPT_HIRAGANA,
|
|
USCRIPT_KANNADA, USCRIPT_KATAKANA, USCRIPT_KHMER, USCRIPT_LAO,
|
|
USCRIPT_LATIN,
|
|
USCRIPT_MALAYALAM, USCRIPT_MONGOLIAN,
|
|
};
|
|
|
|
const char* expectedAbbr[]={
|
|
/* test abbr */
|
|
"Hani", "Hang","Hebr","Hira",
|
|
"Knda","Kana","Khmr","Laoo",
|
|
"Latn",
|
|
"Mlym", "Mong",
|
|
'\0'
|
|
};
|
|
i=0;
|
|
while(i<sizeof(testAbbr)/sizeof(UScriptCode)){
|
|
const char* name = uscript_getShortName(testAbbr[i]);
|
|
numErrors=0;
|
|
if(strcmp(expectedAbbr[i],name)!=0){
|
|
log_err("Error getting abbreviations Got: %s Expected: %s\n",name,expectedAbbr[i]);
|
|
numErrors++;
|
|
}
|
|
if(numErrors > 0){
|
|
if(numErrors >0 ){
|
|
log_err("Errors uchar_getScriptAbbr() : %i \n",numErrors);
|
|
}
|
|
}
|
|
i++;
|
|
}
|
|
|
|
}
|
|
/* now test uscript_getScript() API */
|
|
{
|
|
#define MAX_ARRAY_SIZE 23
|
|
uint32_t codepoints[] = {
|
|
0x0000FF9D, /* USCRIPT_KATAKANA*/
|
|
0x0000FFBE, /* USCRIPT_HANGUL*/
|
|
0x0000FFC7, /* USCRIPT_HANGUL*/
|
|
0x0000FFCF, /* USCRIPT_HANGUL*/
|
|
0x0000FFD7, /* USCRIPT_HANGUL*/
|
|
0x0000FFDC, /* USCRIPT_HANGUL*/
|
|
0x00010300, /* USCRIPT_OLD_ITALIC*/
|
|
0x00010330, /* USCRIPT_GOTHIC*/
|
|
0x0001034A, /* USCRIPT_GOTHIC*/
|
|
0x00010400, /* USCRIPT_DESERET*/
|
|
0x00010428, /* USCRIPT_DESERET*/
|
|
0x0001D167, /* USCRIPT_INHERITED*/
|
|
0x0001D17B, /* USCRIPT_INHERITED*/
|
|
0x0001D185, /* USCRIPT_INHERITED*/
|
|
0x0001D1AA, /* USCRIPT_INHERITED*/
|
|
0x00020000, /* USCRIPT_HAN*/
|
|
0x00000D02, /* USCRIPT_MALAYALAM*/
|
|
0x00000D00, /* USCRIPT_COMMON */
|
|
0x00000000, /* USCRIPT_COMMON*/
|
|
0x0001D169, /* USCRIPT_INHERITED*/
|
|
0x0001D182, /* USCRIPT_INHERITED*/
|
|
0x0001D18B, /* USCRIPT_INHERITED*/
|
|
0x0001D1AD, /* USCRIPT_INHERITED*/
|
|
0x00110000, /* USCRIPT_INVALID_CODE */
|
|
};
|
|
|
|
UScriptCode expected[] = {
|
|
USCRIPT_KATAKANA ,
|
|
USCRIPT_HANGUL ,
|
|
USCRIPT_HANGUL ,
|
|
USCRIPT_HANGUL ,
|
|
USCRIPT_HANGUL ,
|
|
USCRIPT_HANGUL ,
|
|
USCRIPT_OLD_ITALIC,
|
|
USCRIPT_GOTHIC ,
|
|
USCRIPT_GOTHIC ,
|
|
USCRIPT_DESERET ,
|
|
USCRIPT_DESERET ,
|
|
USCRIPT_INHERITED,
|
|
USCRIPT_INHERITED,
|
|
USCRIPT_INHERITED,
|
|
USCRIPT_INHERITED,
|
|
USCRIPT_HAN ,
|
|
USCRIPT_MALAYALAM,
|
|
USCRIPT_COMMON,
|
|
USCRIPT_COMMON,
|
|
USCRIPT_INHERITED ,
|
|
USCRIPT_INHERITED ,
|
|
USCRIPT_INHERITED ,
|
|
USCRIPT_INHERITED ,
|
|
USCRIPT_INVALID_CODE,
|
|
};
|
|
UScriptCode code = USCRIPT_INVALID_CODE;
|
|
UErrorCode status = U_ZERO_ERROR;
|
|
UBool passed = TRUE;
|
|
|
|
i =0;
|
|
while(i< MAX_ARRAY_SIZE){
|
|
code = uscript_getScript(codepoints[i],&status);
|
|
if(U_SUCCESS(status)){
|
|
if( code != expected[i] ||
|
|
code != (UScriptCode)u_getIntPropertyValue(codepoints[i], UCHAR_SCRIPT)
|
|
) {
|
|
log_err("uscript_getScript for codepoint \\U%08X failed\n",codepoints[i]);
|
|
passed = FALSE;
|
|
}
|
|
}else{
|
|
log_err("uscript_getScript for codepoint \\U%08X failed. Error: %s\n",
|
|
codepoints[i],u_errorName(status));
|
|
break;
|
|
}
|
|
i++;
|
|
}
|
|
|
|
if(passed==FALSE){
|
|
log_err("uscript_getScript failed.\n");
|
|
}
|
|
}
|
|
{
|
|
UScriptCode code= USCRIPT_INVALID_CODE;
|
|
UErrorCode status = U_ZERO_ERROR;
|
|
code = uscript_getScript(0x001D169,&status);
|
|
if(code != USCRIPT_INHERITED){
|
|
log_err("\\U001D169 is not contained in USCRIPT_INHERITED");
|
|
}
|
|
}
|
|
{
|
|
UScriptCode code= USCRIPT_INVALID_CODE;
|
|
UErrorCode status = U_ZERO_ERROR;
|
|
int32_t err = 0;
|
|
|
|
for(i = 0; i<=0x10ffff; i++){
|
|
code = uscript_getScript(i,&status);
|
|
if(code == USCRIPT_INVALID_CODE){
|
|
err++;
|
|
log_err("uscript_getScript for codepoint \\U%08X failed.\n", i);
|
|
}
|
|
}
|
|
if(err>0){
|
|
log_err("uscript_getScript failed for %d codepoints\n", err);
|
|
}
|
|
}
|
|
{
|
|
for(i=0; (UScriptCode)i< USCRIPT_CODE_LIMIT; i++){
|
|
const char* name = uscript_getName((UScriptCode)i);
|
|
if(name==NULL || strcmp(name,"")==0){
|
|
log_err("uscript_getName failed for code : %i\n",i);
|
|
}
|
|
}
|
|
}
|
|
|
|
|
|
}
|