Can I use a mask to iterate files in a directory with Boost?
My solution is essentially the same as Julien-L, but encapsulated in the include file it is nicer to use. Implemented using boost::filesystem v3. I guess that something like that is not included in the boost::filesystem directly because it would introduce dependency on boost::regex.
#include "FilteredDirectoryIterator.h"
std::vector< std::string > all_matching_files;
std::for_each(
FilteredDirectoryIterator("/my/directory","somefiles.*\.txt"),
FilteredDirectoryIterator(),
[&all_matching_files](const FilteredDirectoryIterator::value_type &dirEntry){
all_matching_files.push_back(dirEntry.path());
}
);
alternatively use FilteredRecursiveDirectoryIterator for recursive sub directories search:
#include "FilteredDirectoryIterator.h"
std::vector< std::string > all_matching_files;
std::for_each(
FilteredRecursiveDirectoryIterator("/my/directory","somefiles.*\.txt"),
FilteredRecursiveDirectoryIterator(),
[&all_matching_files](const FilteredRecursiveDirectoryIterator::value_type &dirEntry){
all_matching_files.push_back(dirEntry.path());
}
);
FilteredDirectoryIterator.h
#ifndef TOOLS_BOOST_FILESYSTEM_FILTEREDDIRECTORYITERATOR_H_
#define TOOLS_BOOST_FILESYSTEM_FILTEREDDIRECTORYITERATOR_H_
#include "boost/filesystem.hpp"
#include "boost/regex.hpp"
#include <functional>
template <class NonFilteredIterator = boost::filesystem::directory_iterator>
class FilteredDirectoryIteratorTmpl
: public std::iterator<
std::input_iterator_tag, typename NonFilteredIterator::value_type
>
{
private:
typedef std::string string;
typedef boost::filesystem::path path;
typedef
std::function<
bool(const typename NonFilteredIterator::value_type &dirEntry)
>
FilterFunction;
NonFilteredIterator it;
NonFilteredIterator end;
const FilterFunction filter;
public:
FilteredDirectoryIteratorTmpl();
FilteredDirectoryIteratorTmpl(
const path &iteratedDir, const string ®exMask
);
FilteredDirectoryIteratorTmpl(
const path &iteratedDir, const boost::regex &mask
);
FilteredDirectoryIteratorTmpl(
const path &iteratedDir,
const FilterFunction &filter
);
//preincrement
FilteredDirectoryIteratorTmpl<NonFilteredIterator>& operator++() {
for(++it;it!=end && !filter(*it);++it);
return *this;
};
//postincrement
FilteredDirectoryIteratorTmpl<NonFilteredIterator> operator++(int) {
for(++it;it!=end && !filter(*it);++it);
return FilteredDirectoryIteratorTmpl<NonFilteredIterator>(it,filter);
};
const boost::filesystem::directory_entry &operator*() {return *it;};
bool operator!=(const FilteredDirectoryIteratorTmpl<NonFilteredIterator>& other)
{
return it!=other.it;
};
bool operator==(const FilteredDirectoryIteratorTmpl<NonFilteredIterator>& other)
{
return it==other.it;
};
};
typedef
FilteredDirectoryIteratorTmpl<boost::filesystem::directory_iterator>
FilteredDirectoryIterator;
typedef
FilteredDirectoryIteratorTmpl<boost::filesystem::recursive_directory_iterator>
FilteredRecursiveDirectoryIterator;
template <class NonFilteredIterator>
FilteredDirectoryIteratorTmpl<NonFilteredIterator>::FilteredDirectoryIteratorTmpl()
: it(),
filter(
[](const boost::filesystem::directory_entry& /*dirEntry*/){return true;}
)
{
}
template <class NonFilteredIterator>
FilteredDirectoryIteratorTmpl<NonFilteredIterator>::FilteredDirectoryIteratorTmpl(
const path &iteratedDir,const string ®exMask
)
: FilteredDirectoryIteratorTmpl(iteratedDir, boost::regex(regexMask))
{
}
template <class NonFilteredIterator>
FilteredDirectoryIteratorTmpl<NonFilteredIterator>::FilteredDirectoryIteratorTmpl(
const path &iteratedDir,const boost::regex ®exMask
)
: it(NonFilteredIterator(iteratedDir)),
filter(
[regexMask](const boost::filesystem::directory_entry& dirEntry){
using std::endl;
// return false to skip dirEntry if no match
const string filename = dirEntry.path().filename().native();
return boost::regex_match(filename, regexMask);
}
)
{
if (it!=end && !filter(*it)) ++(*this);
}
template <class NonFilteredIterator>
FilteredDirectoryIteratorTmpl<NonFilteredIterator>::FilteredDirectoryIteratorTmpl(
const path &iteratedDir, const FilterFunction &filter
)
: it(NonFilteredIterator(iteratedDir)),
filter(filter)
{
if (it!=end && !filter(*it)) ++(*this);
}
#endif
EDIT: As noted in the comments, the code below is valid for versions of boost::filesystem
prior to v3. For v3, refer to the suggestions in the comments.
boost::filesystem
does not have wildcard search, you have to filter files yourself.
This is a code sample extracting the content of a directory with a boost::filesystem
's directory_iterator
and filtering it with boost::regex
:
const std::string target_path( "/my/directory/" );
const boost::regex my_filter( "somefiles.*\.txt" );
std::vector< std::string > all_matching_files;
boost::filesystem::directory_iterator end_itr; // Default ctor yields past-the-end
for( boost::filesystem::directory_iterator i( target_path ); i != end_itr; ++i )
{
// Skip if not a file
if( !boost::filesystem::is_regular_file( i->status() ) ) continue;
boost::smatch what;
// Skip if no match for V2:
if( !boost::regex_match( i->leaf(), what, my_filter ) ) continue;
// For V3:
//if( !boost::regex_match( i->path().filename().string(), what, my_filter ) ) continue;
// File matches, store it
all_matching_files.push_back( i->leaf() );
}
(If you are looking for a ready-to-use class with builtin directory filtering, have a look at Qt's QDir
.)
I believe the directory_iterators will only provide all files in a directory. It up to you to filter them as necessary.
There is a Boost Range Adaptors
way:
#define BOOST_RANGE_ENABLE_CONCEPT_ASSERT 0
#include <boost/filesystem.hpp>
#include <boost/range/adaptors.hpp>
namespace bfs = boost::filesystem;
namespace ba = boost::adaptors;
const std::string target_path( "/my/directory/" );
const boost::regex my_filter( "somefiles.*\.txt" );
boost::smatch what;
for (auto &entry: boost::make_iterator_range(bfs::directory_iterator(target_path), {})
| ba::filtered(static_cast<bool (*)(const bfs::path &)>(&bfs::is_regular_file))
| ba::filtered([&](const bfs::path &path){ return boost::regex_match(path.filename().string(), what, my_filter); })
)
{
// There are only files matching defined pattern "somefiles*.txt".
std::cout << entry.path().filename() << std::endl;
}