I want to parse a file that looks like this (FASTA-like text format):
>InfoHeader
\"Some text sequence that h
Previous: Step 3: MOAR FASTER WITH ZERO-COPY
Return to Step 1. Cleaning up + Profiling
Since you're not using it, we can drop the stateful iterator, which is likely to inhibit quite a lot of optimizations (and was indirectly visible in the profiler output)
Live On Coliru
#define BOOST_SPIRIT_USE_PHOENIX_V3
#include
#include
#include
namespace io = boost::iostreams;
namespace fs = boost::filesystem;
class FastaReader {
public:
typedef std::pair Entry;
typedef std::vector Data;
private:
Data fV;
fs::path file;
public:
FastaReader(const fs::path & f);
~FastaReader();
const fs::path & getFile() const;
const Data::const_iterator begin() const;
const Data::const_iterator end() const;
private:
io::mapped_file_source mmap;
void parse();
};
#include
#include
#include
#include
#include
#include
#include
#include
//#include "fastaReader.hpp"
#include
using namespace std;
namespace fs = boost::filesystem;
namespace qi = boost::spirit::qi;
namespace pt = boost::posix_time;
namespace io = boost::iostreams;
namespace boost { namespace spirit { namespace traits {
template
struct assign_to_attribute_from_iterators {
static void call(It f, It l, boost::string_ref& attr) { attr = boost::string_ref { f, size_t(std::distance(f,l)) }; }
};
} } }
template
struct FastaGrammar : qi::grammar {
FastaGrammar() : FastaGrammar::base_type(fasta) {
using namespace qi;
using boost::phoenix::construct;
using boost::phoenix::begin;
using boost::phoenix::size;
entry = ('>' >> raw[ *~char_('\n') ] >> '\n' >> raw[ *~char_('>') ]);
fasta = *entry >> *eol >> eoi ;
BOOST_SPIRIT_DEBUG_NODES((fasta)(entry));
}
private:
qi::rule fasta;
qi::rule entry;
};
FastaReader::FastaReader(const fs::path & f) : file(f), mmap(file.c_str()) {
parse();
}
FastaReader::~FastaReader() {}
const fs::path & FastaReader::getFile() const {
return this->file;
}
const FastaReader::Data::const_iterator FastaReader::begin() const {
return this->fV.cbegin();
}
const FastaReader::Data::const_iterator FastaReader::end() const {
return this->fV.cend();
}
void FastaReader::parse() {
if (this->file.empty()) throw std::runtime_error("FastaReader: No file specified.");
if (! fs::is_regular_file(this->file)) throw std::runtime_error(string("FastaReader: File not found: ") + this->file.string());
typedef char const* iterator_type;
typedef FastaGrammar fastaGr;
static const fastaGr fG{};
try {
std::cerr << "Measuring: Parsing." << std::endl;
const pt::ptime startMeasurement = pt::microsec_clock::universal_time();
iterator_type first(mmap.data()), last(mmap.end());
qi::phrase_parse(first, last, fG, boost::spirit::ascii::space, this->fV);
const pt::ptime endMeasurement = pt::microsec_clock::universal_time();
pt::time_duration duration (endMeasurement - startMeasurement);
std::cerr << duration << std::endl;
} catch (std::exception const& e) {
cerr << "error message: " << e.what() << endl;
}
}
int main() {
FastaReader reader("input.txt");
for (auto& e : reader) std::cout << '>' << e.first << '\n' << e.second << "\n\n";
}
Now it's 74.8x faster.
$ time ./test | head -n4
Measuring: Parsing.
00:00:00.194432