For Compiling:
$ g++ code.cpp -lbz2
Need to open two FILE*
one to read from and second to write compressed data
#include <bzlib.h>
int bzerror = BZ_OK;
BZFILE *bfp = BZ2_bzWriteOpen(&bzerror, fpout, 9, 0, 30);
if (bzerror != BZ_OK)
{
BZ2_bzWriteClose(&bzerror, bfp, 0, NULL, NULL);
fclose(fpin);
fclose(fpout);
return 1;
}
memset(buf, 0, nBuf);
while (fgets(buf, nBuf, fpin) != NULL)
{
len = strlen(buf);
BZ2_bzWrite(&bzerror, bfp, buf, len);
if (bzerror == BZ_IO_ERROR)
{
std::cout << "bz-io-error detected\n";
break;
}
memset(buf, 0, nBuf);
}
BZ2_bzWriteClose(&bzerror, bfp, 0, NULL, NULL);
// ---- end ----
BZFILE *BZ2_bzWriteOpen( int *bzerror,
FILE *f,
int blockSize100k,
int verbosity,
int workFactor );
- blockSize100k specifies the block size to be used for compression
- verbosity should be set to a number between 0 and 4 inclusive.
0 is silent, and greater numbers give increasingly verbose monitoring/debugging output
- workFactor controls how the compression phase behaves when presented with worst case, highly repetitive, input data.
If compression runs into difficulties caused by repetitive data,the library switches from the standard sorting algorithm to a fallback algorithm.
The fallback is slower than the standard algorithm by perhaps a factor of three, but always behaves reasonably, no matter how bad the input
=====================================
Reading Compressed file ie Extracting Data
#include <bzlib.h>
int nBuf = 512;
memset(buf, 0, nBuf);
bzerror = BZ_OK;
while (bzerror == BZ_OK)
{
BZ2_bzRead(&bzerror, bfp, (char*)buf, nBuf);
if (bzerror == BZ_IO_ERROR)
{
std::cout << "bz-io-error detected\n";
break;
}
std::cout << buf;
memset(buf, 0, nBuf);
}
BZ2_bzReadClose(&bzerror, bfp);
fclose(fpin);
// ---- end ----
BZFILE *BZ2_bzReadOpen(int *bzerror,
FILE *f,
int verbosity,
int small,
void *unused,
int nUnused );
- If small is 1, the library will try to decompress using less memory, at the expense of speed.
- decompress the nUnused bytes starting at unused
