UCS2 *Parser::String_Literal_To_UCS2(const char *str, bool pathname)
{
UCS2 *char_string = NULL;
UCS2 *char_array = NULL;
int char_array_size = 0;
int utf8arraysize = 0;
unsigned char *utf8array = NULL;
int index_in = 0;
int index_out = 0;
char buffer[8];
char *dummy_ptr = NULL;
int i = 0;
if(strlen(str) == 0)
{
char_string = reinterpret_cast<UCS2 *>(POV_MALLOC(sizeof(UCS2), "UCS2 String"));
char_string[0] = 0;
return char_string;
}
switch(sceneData->stringEncoding)
{
case kStringEncoding_ASCII:
char_array_size = (int)strlen(str);
char_array = reinterpret_cast<UCS2 *>(POV_MALLOC(char_array_size * sizeof(UCS2), "Character Array"));
for(i = 0; i < char_array_size; i++)
{
if(sceneData->EffectiveLanguageVersion() < 350)
char_array[i] = (unsigned char)(str[i]);
else
{
char_array[i] = str[i] & 0x007F;
if(char_array[i] != str[i])
{
char_array[i] = ' ';
PossibleError("Non-ASCII character has been replaced by space character.");
}
}
}
break;
case kStringEncoding_UTF8:
char_array = Convert_UTF8_To_UCS2(reinterpret_cast<const unsigned char *>(str), (int)strlen(str), &char_array_size);
break;
case kStringEncoding_System:
char_array = POV_CONVERT_TEXT_TO_UCS2(reinterpret_cast<const unsigned char *>(str), strlen(str), &char_array_size);
if(char_array == NULL)
Error("Cannot convert system specific text format to Unicode.");
break;
default:
Error("Unsupported text encoding format.");
break;
}
if(char_array == NULL)
Error("Cannot convert text to UCS2 format.");
char_string = reinterpret_cast<UCS2 *>(POV_MALLOC((char_array_size + 1) * sizeof(UCS2), "UCS2 String"));
for(index_in = 0, index_out = 0; index_in < char_array_size; index_in++, index_out++)
{
if((char_array[index_in] == '\\') && (sceneData->EffectiveLanguageVersion() >= 371 || !pathname))
{
// Historically, escape sequences were ignored when parsing for a filename.
// As of POV-Ray 3.71, this has been changed.
#if (FILENAME_SEPARATOR == '\\')
if (pathname)
{
Warning("Backslash encountered while parsing for a filename."
" As of version 3.71, this is interpreted as an escape sequence just like in any other string literal."
" If this is supposed to be a path separator, use a forward slash instead.");
}
#endif
index_in++;
switch(char_array[index_in])
{
case 'a':
char_string[index_out] = 0x07;
break;
case 'b':
char_string[index_out] = 0x08;
break;
case 'f':
char_string[index_out] = 0x0c;
break;
case 'n':
char_string[index_out] = 0x0a;
break;
case 'r':
char_string[index_out] = 0x0d;
break;
case 't':
char_string[index_out] = 0x09;
break;
case 'v':
char_string[index_out] = 0x0b;
break;
case '\0':
// [CLi] shouldn't happen, as having a backslash as the last character of a string literal would invalidate the string terminator
Error("Unexpected end of escape sequence in text string.");
break;
case '\'':
case '\"':
case '\\':
char_string[index_out] = char_array[index_in];
break;
case 'u':
if(index_in + 4 >= char_array_size)
Error("Unexpected end of escape sequence in text string.");
buffer[0] = char_array[++index_in];
buffer[1] = char_array[++index_in];
buffer[2] = char_array[++index_in];
buffer[3] = char_array[++index_in];
buffer[4] = 0;
char_string[index_out] = (UCS2)strtoul(buffer, &dummy_ptr, 16);
break;
default:
char_string[index_out] = char_array[index_in];
if ( char_array )
POV_FREE(char_array);
char_array = NULL;
Error( "Illegal escape sequence in string." );
break;
}
}
else
{
if ((char_array[index_in] == '\\') && pathname)
{
// Historically, escape sequences were ignored when parsing for a filename.
// As of POV-Ray 3.71, this has been changed.
#if (FILENAME_SEPARATOR == '\\')
Warning("Backslash encountered while parsing for a filename."
" In legacy (pre-3.71) scenes, this is NOT interpreted as the start of an escape sequence."
" However, for future compatibility it is recommended to use a forward slash as path separator instead.");
#else
Warning("Backslash encountered while parsing for a filename."
" In legacy (pre-3.71) scenes, this is NOT interpreted as the start of an escape sequence.");
#endif
}
char_string[index_out] = char_array[index_in];
}
}
char_string[index_out] = 0;
index_out++;
char_string = reinterpret_cast<UCS2 *>(POV_REALLOC(char_string, index_out * sizeof(UCS2), "UCS2 String"));
if(char_array != NULL)
POV_FREE(char_array);
return char_string;
}
UCS2 *Parser::String_To_UCS2(const char *str, bool pathname)
{
UCS2 *char_string = NULL;
UCS2 *char_array = NULL;
int char_array_size = 0;
int utf8arraysize = 0;
unsigned char *utf8array = NULL;
int index_in = 0;
int index_out = 0;
char buffer[8];
char *dummy_ptr = NULL;
int i = 0;
if(strlen(str) == 0)
{
char_string = reinterpret_cast<UCS2 *>(POV_MALLOC(sizeof(UCS2), "UCS2 String"));
char_string[0] = 0;
return char_string;
}
switch(sceneData->stringEncoding)
{
case 0: // ASCII
char_array_size = (int)strlen(str);
char_array = reinterpret_cast<UCS2 *>(POV_MALLOC(char_array_size * sizeof(UCS2), "Character Array"));
for(i = 0; i < char_array_size; i++)
{
if(sceneData->languageVersion < 350)
char_array[i] = (unsigned char)(str[i]);
else
{
char_array[i] = str[i] & 0x007F;
if(char_array[i] != str[i])
{
char_array[i] = ' ';
PossibleError("Non-ASCII character has been replaced by space character.");
}
}
}
break;
case 1: // UTF8
char_array = Convert_UTF8_To_UCS2(reinterpret_cast<const unsigned char *>(str), (int)strlen(str), &char_array_size);
break;
case 2: // System Specific
char_array = POV_CONVERT_TEXT_TO_UCS2(reinterpret_cast<const unsigned char *>(str), strlen(str), &char_array_size);
if(char_array == NULL)
Error("Cannot convert system specific text format to Unicode.");
break;
default:
Error("Unsupported text encoding format.");
break;
}
if(char_array == NULL)
Error("Cannot convert text to UCS2 format.");
char_string = reinterpret_cast<UCS2 *>(POV_MALLOC((char_array_size + 1) * sizeof(UCS2), "UCS2 String"));
for(index_in = 0, index_out = 0; index_in < char_array_size; index_in++, index_out++)
{
if((char_array[index_in] == '\\') && (pathname == false))
{
index_in++;
switch(char_array[index_in])
{
case 'a':
char_string[index_out] = 0x07;
break;
case 'b':
char_string[index_out] = 0x08;
break;
case 'f':
char_string[index_out] = 0x0c;
break;
case 'n':
char_string[index_out] = 0x0a;
break;
case 'r':
char_string[index_out] = 0x0d;
break;
case 't':
char_string[index_out] = 0x09;
break;
case 'v':
char_string[index_out] = 0x0b;
break;
case '\0':
char_string[index_out] = 0x5c;
break;
case '\'':
char_string[index_out] = 0x27;
break;
case '\\':
char_string[index_out] = '\\';
break;
case 'u':
if(index_in + 4 >= char_array_size)
Error("Unexpected end of escape sequence in text string.");
buffer[0] = char_array[++index_in];
buffer[1] = char_array[++index_in];
buffer[2] = char_array[++index_in];
buffer[3] = char_array[++index_in];
buffer[4] = 0;
char_string[index_out] = (UCS2)strtoul(buffer, &dummy_ptr, 16);
break;
default:
char_string[index_out] = char_array[index_in];
if ( char_array )
POV_FREE(char_array);
char_array = NULL;
Error( "Illegal escape sequence in string." );
break;
}
}
else
char_string[index_out] = char_array[index_in];
}
char_string[index_out] = 0;
index_out++;
char_string = reinterpret_cast<UCS2 *>(POV_REALLOC(char_string, index_out * sizeof(UCS2), "UCS2 String"));
if(char_array != NULL)
POV_FREE(char_array);
return char_string;
}
UCS2 *Parser::String_To_UCS2(const char *str)
{
UCS2 *char_string = NULL;
UCS2 *char_array = NULL;
int char_array_size = 0;
int utf8arraysize = 0;
unsigned char *utf8array = NULL;
int index_in = 0;
int index_out = 0;
char *dummy_ptr = NULL;
int i = 0;
if(strlen(str) == 0)
{
char_string = reinterpret_cast<UCS2 *>(POV_MALLOC(sizeof(UCS2), "UCS2 String"));
char_string[0] = 0;
return char_string;
}
switch(sceneData->stringEncoding)
{
case kStringEncoding_ASCII:
char_array_size = (int)strlen(str);
char_array = reinterpret_cast<UCS2 *>(POV_MALLOC(char_array_size * sizeof(UCS2), "Character Array"));
for(i = 0; i < char_array_size; i++)
{
if(sceneData->EffectiveLanguageVersion() < 350)
char_array[i] = (unsigned char)(str[i]);
else
{
char_array[i] = str[i] & 0x007F;
if(char_array[i] != str[i])
{
char_array[i] = ' ';
PossibleError("Non-ASCII character has been replaced by space character.");
}
}
}
break;
case kStringEncoding_UTF8:
char_array = Convert_UTF8_To_UCS2(reinterpret_cast<const unsigned char *>(str), (int)strlen(str), &char_array_size);
break;
case kStringEncoding_System:
char_array = POV_CONVERT_TEXT_TO_UCS2(reinterpret_cast<const unsigned char *>(str), strlen(str), &char_array_size);
if(char_array == NULL)
Error("Cannot convert system specific text format to Unicode.");
break;
default:
Error("Unsupported text encoding format.");
break;
}
if(char_array == NULL)
Error("Cannot convert text to UCS2 format.");
char_string = reinterpret_cast<UCS2 *>(POV_MALLOC((char_array_size + 1) * sizeof(UCS2), "UCS2 String"));
for(index_in = 0, index_out = 0; index_in < char_array_size; index_in++, index_out++)
char_string[index_out] = char_array[index_in];
char_string[index_out] = 0;
index_out++;
if(char_array != NULL)
POV_FREE(char_array);
return char_string;
}
