Mikhail Romanko
fc774fd0ff
Doxygen kind'a sucks and I need multilanguage documentation, so I did that. Also, separated massive Math.h file into smaller files.
69 lines
1.6 KiB
C
69 lines
1.6 KiB
C
#include <BH/IO.h>
|
|
#include <BH/Unicode.h>
|
|
#include <stdlib.h>
|
|
#include <stdio.h>
|
|
|
|
|
|
void printUsage(void)
|
|
{
|
|
printf("Utf8Test <input> <output>\n");
|
|
exit(1);
|
|
}
|
|
|
|
|
|
int main(int argc, char **argv)
|
|
{
|
|
BH_IO *inFile, *outFile;
|
|
char inBuffer[8], outBuffer[8];
|
|
uint32_t unit;
|
|
size_t i, inSize, outSize;
|
|
|
|
if (argc < 2)
|
|
printUsage();
|
|
|
|
inFile = BH_FileNew(argv[1], BH_FILE_READ | BH_FILE_EXIST, NULL);
|
|
outFile = BH_FileNew(argv[2], BH_FILE_WRITE | BH_FILE_TRUNCATE, NULL);
|
|
|
|
if (!inFile || !outFile)
|
|
return -1;
|
|
|
|
inSize = 0;
|
|
while (1)
|
|
{
|
|
/* Read one byte and try to decode */
|
|
if (!inSize || !(outSize = BH_UnicodeDecodeUtf8(inBuffer, inSize, &unit)))
|
|
{
|
|
BH_IOPeek(inFile, inBuffer + inSize, 1, &outSize);
|
|
BH_IORead(inFile, inBuffer + inSize, 1, &outSize);
|
|
inSize += outSize;
|
|
|
|
if (!outSize)
|
|
break;
|
|
|
|
continue;
|
|
}
|
|
|
|
/* Remove readed amount */
|
|
for (i = 0; i < inSize - outSize; i++)
|
|
inBuffer[i] = inBuffer[i + outSize];
|
|
inSize -= outSize;
|
|
|
|
/* Change unit if incorrect and write to output */
|
|
if (unit == -1)
|
|
unit = 0xFFFD;
|
|
outSize = BH_UnicodeEncodeUtf8(unit, outBuffer);
|
|
BH_IOWrite(outFile, outBuffer, outSize, NULL);
|
|
}
|
|
|
|
/* Incomplete UTF-8 sequence */
|
|
if (inSize)
|
|
{
|
|
outSize = BH_UnicodeEncodeUtf8(0xFFFD, outBuffer);
|
|
BH_IOWrite(outFile, outBuffer, outSize, NULL);
|
|
}
|
|
|
|
BH_IOFree(inFile);
|
|
BH_IOFree(outFile);
|
|
return 0;
|
|
}
|