Created
March 31, 2015 11:53
-
-
Save HappyCerberus/3d6bd6fe1d8dbeeb2929 to your computer and use it in GitHub Desktop.
Fast line-by-line file parser
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#include "FastLineReader.h" | |
// POSIX | |
#include <sys/types.h> | |
#include <sys/mman.h> | |
#include <sys/stat.h> | |
#include <fcntl.h> | |
#include <unistd.h> | |
#include <errno.h> | |
// C++ STD | |
#include <iostream> | |
#include <cstring> | |
using namespace std; | |
int fastLineParser(const char * const filename, void (*callback)(const char * const, const char * const)) | |
{ | |
int fd = open(filename, O_RDONLY); // open file | |
if (fd == -1) | |
{ | |
cerr << "Could not open \"" << filename << "\" for reading (" << strerror(errno) << ")." << endl; | |
return -1; | |
} | |
struct stat fs; | |
if (fstat(fd, &fs) == -1) | |
{ | |
cerr << "Could not stat \"" << filename << "\" for reading (" << strerror(errno) << ")." << endl; | |
close(fd); | |
return -1; | |
} | |
posix_fadvise(fd,0,0,1); // announce the desire to sequentialy read this file | |
// silent error handling - weak error | |
char *buf = static_cast<char*>(mmap(0, static_cast<size_t>(fs.st_size), PROT_READ, MAP_SHARED, fd, 0)); | |
if (buf == MAP_FAILED) | |
{ | |
cerr << "Could not memory map file \"" << filename << "\" (" << strerror(errno) << ")." << endl; | |
close(fd); | |
return -1; | |
} | |
char *buff_end = buf + fs.st_size; | |
char *begin = buf, *end = NULL; | |
// search for newline in the remainder in the file | |
while ((end = static_cast<char*>(memchr(begin,'\n',static_cast<size_t>(buff_end-begin)))) != NULL) | |
{ | |
callback(begin,end); | |
if (end != buff_end) | |
begin = end+1; | |
else | |
break; | |
} | |
// enable if you are working with malformed text files, proper text file needs to end with a newline | |
#ifdef MALFORMED_TEXFILE | |
callback(begin,buff_end); | |
#endif | |
munmap(buf, static_cast<size_t>(fs.st_size)); | |
// silent error handling - weak error | |
close(fd); | |
return 0; | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/* Copyright (c) 2015 Simon Toth kontakt@simontoth.cz | |
* Lincensed under the MIT license: http://opensource.org/licenses/MIT | |
*/ | |
#ifndef FASTLINEREADER_H | |
#define FASTLINEREADER_H | |
// STD C++ | |
#include <iosfwd> | |
/** Quick line-by-line parser of text files for POSIX/Linux | |
* | |
* This function provides a fast line parser with a callback model. | |
* | |
* @param filename file to be parsed | |
* @param callback function that will be called for each line | |
* @returns 0 on success, -1 if file could not be opened | |
**/ | |
int fastLineParser(const char * const filename, void (*callback)(const char * const, const char * const)); | |
#endif // FASTLINEREADER_H |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
callback may be replaced by std::function to archive better scalablity in c++11