Reputation: 1147
I currently have code that essentially contains these commands:
std::string line;
std::getline(ifs, line);
ifs
is some std::ifstream
. The code works.
I now would like to use the same on data I decompress from another source. Basically, I'd read in chunks that I buffer somewhere, and then retrieve data from this buffer using a function that is a bit like fgetc
. This all works, but is a bad mix of non-STL with STL code.
What I would like to do is encapsulate the decompression and provide an iterator so that the call to std::getline
works. I guess that would be an istream_iterator
? What is the minimum that this class needs to contain?
UPDATE: Based on the comments I got, and the streambuf implementation at http://www.voidcn.com/article/p-vjnlygmc-gy.html, I now have the following code that works. As a test case, I used the zlib compression. The code is not really nice, and I appreciate any hint to improve it.
class gzip_streambuf: public std::streambuf
{
private:
gzip_streambuf(const gzip_streambuf &);
gzip_streambuf &operator= (const gzip_streambuf &);
public:
explicit gzip_streambuf(gzFile h_, std::size_t buf_sz_ = 1024, std::size_t putback_sz_ = 2) :
putback_sz(std::max(putback_sz_, std::size_t(1))),
buffer(std::max(putback_sz_, buf_sz_ ) + putback_sz_),
h(h_)
{
char *end = &buffer.front() + buffer.size();
setg(end, end, end);
}
~gzip_streambuf() {}
bool error(void)
{
return gzerr;
}
private:
int_type underflow()
{
if (gptr() < egptr())
return traits_type::to_int_type(*gptr());
char *base = &buffer.front();
char *start = base;
if (eback() == base) {
std::memmove(base, egptr() - putback_sz, putback_sz);
start += putback_sz;
}
int n = gzread(h, start, buffer.size() - (start - base));
if ( n < 0 )
gzerr = true;
if ( n <= 0)
return traits_type::eof();
setg(base, start, start + n);
return traits_type::to_int_type(*gptr());
}
private:
bool gzerr = false;
gzFile h = nullptr;
const std::size_t putback_sz;
std::vector<char> buffer;
};
class gzip_istream: public std::istream
{
public:
gzip_istream() {};
~gzip_istream() { delete gzbuf; };
private:
gzip_istream(const gzip_istream &);
gzip_istream &operator= (const gzip_istream &);
public:
void open( const char * filename) {
if ( h = gzopen(filename, "rb") ) {
delete gzbuf;
if ( gzbuf = new gzip_streambuf(h) ) {
set_rdbuf(gzbuf);
clear();
} else
close();
}
}
void close() {
if (h)
gzclose( std::exchange(h, nullptr) );
delete std::exchange(gzbuf, nullptr);
set_rdbuf(nullptr);
}
bool is_open(void) {
return h != nullptr;
}
private:
gzFile h = nullptr;
gzip_streambuf *gzbuf = nullptr;
};
It can be used as follows:
std::string line;
gzip_istream gin;
gin.open("file.gz");
if (gin.good()) {
while (std::getline( gin, line))
std::cout << line << std::endl;
gin.close();
}
I have tried to use std::unique_ptr
for the gzip_streambuf
member in gzip_istream
, but all attempts failed because of the lack of copy constructor. I'd like to get rid of the new/delete stuff but am not sure how.
Upvotes: 1
Views: 65