Can I use a mask to iterate files in a directory using Boost?

Question

I want to iterate over all the files in the directory matching "somefiles * .txt". Does boost :: filesystem have something built in for this, or do I need a regex or something against each sheet ()?

Answer 1

EDIT . As noted in the comments, the code below is valid for boost::filesystem versions prior to v3. For v3, refer to the suggestions in the comments.

---

boost::filesystem does not have a wildcard search, you must filter the files yourself.

This is sample code that extracts the contents of a directory with boost::filesystem directory_iterator and filters it using 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(), what, my_filter ) ) continue; // File matches, store it all_matching_files.push_back( i->leaf() ); } 

(If you're looking for a ready-to-use class with integrated directory filtering, check out Qt QDir .)

Answer 2

There is a Boost Range Adaptors method:

 #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; } 

Answer 3

My solution is essentially the same as Julien-L, but encapsulated in an include file which is better to use. Implemented using boost :: filesystem v3. I assume that something like this is not included in boost :: filesystem directly, because it will lead to a 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 to search for recursive subdirectories:

 #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 &regexMask ); 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 &regexMask ) : FilteredDirectoryIteratorTmpl(iteratedDir, boost::regex(regexMask)) { } template <class NonFilteredIterator> FilteredDirectoryIteratorTmpl<NonFilteredIterator>::FilteredDirectoryIteratorTmpl( const path &iteratedDir,const boost::regex &regexMask ) : 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 

Answer 4

I believe that directory_iterators will only provide all the files in a directory. It is up to you to filter them as needed.

Answer 5

As mentioned at the end of the Julien-L post QDir exactly what you want.
https://qt-project.org/doc/qt-5.0/qtcore/qdir.html#QDir-3

Answer 6

I have been looking for a solution for this before, and I think my solution is the easiest

 #include <boost/filesystem.hpp> #include <boost/regex.hpp> #include <boost/iterator/iterator_facade.hpp> #include <boost/exception/all.hpp> struct dir_filter_iter : public boost::iterator_facade< dir_filter_iter, boost::filesystem::path, boost::forward_traversal_tag, boost::filesystem::path > { using path = boost::filesystem::path; using impl_type = boost::filesystem::directory_iterator; dir_filter_iter():impl_(){} dir_filter_iter(path p, boost::regex rgx):impl_(std::move(p)),rgx_(std::move(rgx)){ namespace bf = boost::filesystem; if( ! bf::is_directory(p) ){ BOOST_THROW_EXCEPTION( boost::enable_error_info(std::domain_error("not a dir")) << boost::errinfo_file_name(p.string())); } } private: friend class boost::iterator_core_access; bool equal(const dir_filter_iter& that)const{ return this->impl_ == that.impl_; } void increment(){ assert( impl_ != impl_type() ); for(;;){ ++impl_; if( impl_ == impl_type() ) break; std::string s(impl_->path().string()); if( boost::regex_match( s, rgx_ ) ){ break; } } } path dereference()const{ assert( impl_ != impl_type() ); return *impl_; } impl_type impl_; boost::regex rgx_; }; struct dir_filter_iter_maker{ using value_type = dir_filter_iter; explicit dir_filter_iter_maker(boost::regex rgx):rgx_(rgx){} value_type make()const{ return value_type(); } value_type make(boost::filesystem::path p)const{ return value_type(std::move(p),rgx_); } template<typename... Args> auto operator()(Args&&... args)->decltype(make(args...)){ return this->make(std::forward<Args>(args)...); } private: boost::regex rgx_; }; 

Then you can do

  dir_filter_iter_maker di_maker(boost::regex(R"_(.*\.hpp)_")); std::for_each( di_maker(p), di_maker(), [](const bf::path& p){std::cout << p.string() << "\n";}); 

Answer 7

The accepted answer did not compile for me, even when I used i->path().extension() instead of leaf() . For me it was an example from this website . Here is the code modified to apply the filter:

 vector<string> results; filesystem::path filepath(fullpath_to_file); filesystem::directory_iterator it(filepath); filesystem::directory_iterator end; const boost::regex filter("myfilter(capturing group)"); BOOST_FOREACH(filesystem::path const &p, make_pair(it, end)) { if(is_regular_File(p)) { match_results<string::const_iterator> what; if (regex_search(it->path().filename().string(), what, pidFileFilter, match_default)) { string res = what[1]; results.push_back(res); } } } 

I am using Boost version: 1.53.0.

Why are we all not just using glob() , but some regular expression is outside of me.