static void TestCharLength()
{
static const uint32_t codepoint[]={
1, 0x0061,
1, 0x007f,
2, 0x016f,
2, 0x07ff,
3, 0x0865,
3, 0x20ac,
4, 0x20402,
4, 0x23456,
4, 0x24506,
4, 0x20402,
4, 0x10402,
3, 0xd7ff,
3, 0xe000,
};
int16_t i;
UBool multiple;
for(i=0; i<sizeof(codepoint)/sizeof(codepoint[0]); i=(int16_t)(i+2)){
UChar32 c=codepoint[i+1];
if(UTF8_CHAR_LENGTH(c) != (uint16_t)codepoint[i] || U8_LENGTH(c) != (uint16_t)codepoint[i]){
log_err("The no: of code units for %lx:- Expected: %d Got: %d\n", c, codepoint[i], UTF8_CHAR_LENGTH(c));
}else{
log_verbose("The no: of code units for %lx is %d\n",c, UTF8_CHAR_LENGTH(c) );
}
multiple=(UBool)(codepoint[i] == 1 ? FALSE : TRUE);
if(UTF8_NEED_MULTIPLE_UCHAR(c) != multiple){
log_err("ERROR: UTF8_NEED_MULTIPLE_UCHAR failed for %lx\n", c);
}
}
}
int UString::getUnicodeFromIterator()
{
char* str = utf_data+iter;
if(!(*str)){
iter = 0;
return -1;
}
int ch = UTF8_GET_CHAR(str);
if (!ch){
iter = 0;
return -1;
}
iter += UTF8_CHAR_LENGTH(ch);
return ch;
}
int UString::getUnicodeFromIterator()
{
char* str = m_mallocBuffer+m_iter;
if(!(*str)){
m_iter = 0;
return -1;
}
int ch = UTF8_GET_CHAR(str);
if (!ch){
m_iter = 0;
return -1;
}
m_iter += UTF8_CHAR_LENGTH(ch);
return ch;
}
int UString::get(size_t index) const
{
char* str = utf_data;
if(!str_len){
return -1;
}
while (index > 0){
int ch = UTF8_GET_CHAR(str);
if (!ch){
return -1;
}
str += UTF8_CHAR_LENGTH(ch);
index--;
}
return UTF8_GET_CHAR(str);
}
int UString::get(size_t index) const
{
char* str = m_mallocBuffer;
if(!m_strLen){
return -1;
}
while (index > 0){
int ch = UTF8_GET_CHAR(str);
if (!ch){
return -1;
}
str += UTF8_CHAR_LENGTH(ch);
index--;
}
return UTF8_GET_CHAR(str);
}
