Created
April 30, 2011 07:18
-
-
Save mad/949508 to your computer and use it in GitHub Desktop.
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 <iostream> // cout, endl | |
#include <fstream> // fstream | |
#include <vector> | |
#include <string> | |
#include <algorithm> // copy | |
#include <iterator> // ostream_operator | |
#include <stdio.h> | |
#include <stdlib.h> | |
#include <string.h> | |
// #include <boost/tokenizer.hpp> | |
#include <boost/algorithm/string.hpp> | |
using namespace std; | |
//using namespace boost; | |
void boost_tokenizer(string in, string out); | |
void boost_split(string in, string out); | |
inline void fast_split(char **fields, char* str); | |
int main(int argc, char *argv[]) | |
{ | |
string in(argv[1]); | |
string out(argv[2]); | |
boost_split(in, out); | |
return 0; | |
} | |
#if 0 | |
void boost_tokenizer(string in_file, string out_file) | |
{ | |
ifstream in(in_file.c_str()); | |
ofstream out(out_file.c_str()); | |
if (!in.is_open()) return; | |
escaped_list_separator<char> separator("\\","\t", "\""); | |
typedef tokenizer< escaped_list_separator<char> > Tokenizer; | |
vector< string > vec; | |
string line; | |
while (getline(in, line)) | |
{ | |
Tokenizer tok(line, separator); | |
vec.assign(tok.begin(), tok.end()); | |
// vector now contains strings from one row, output to cout here | |
copy(vec.begin(), vec.end(), ostream_iterator<string>(out, ";")); | |
out << endl; | |
} | |
} | |
#endif | |
#define LINE_SIZE 256 | |
#define NUM_FIELDS 8 | |
void boost_split(string in_file, string out_file) | |
{ | |
ifstream in(in_file.c_str()); | |
ofstream out(out_file.c_str()); | |
char str[LINE_SIZE]; | |
if (!in.is_open()) return; | |
std::vector< string > vec(8, ""); | |
string line; | |
char **fields; | |
// fields = (char **) malloc(10 * sizeof(char**)); | |
while (in.getline(str, LINE_SIZE)) | |
{ | |
boost::split(vec, str, boost::is_any_of("\t")); | |
// fast_split(fields, str); | |
// vec.push_back(string("wqe")); | |
out << vec[0] << ";" << vec[1] << ";" << vec[2] << ";" << vec[3] << ";" << vec[4] << ";" << vec[5] << ";" << vec[6] << ";" << vec[7] << "\n"; | |
// vector now contains strings from one row, output to cout here | |
// copy(vec.begin(), vec.end(), ostream_iterator<string>(out, ";")); | |
} | |
} | |
// XXX: NOT THREAD SAFED | |
inline void fast_split(char **fields, char* str) | |
{ | |
char * pch; | |
int i = 0; | |
pch = strtok (str, "\t"); | |
// vector<string>::iterator it; | |
// it = vec.begin(); | |
// vec.clear(); | |
while (pch != NULL) { | |
// it = vec.begin(); | |
// vec.insert(it, string(strdup(pch))); | |
// vec[i] = strdup(pch); | |
// fields[i] = strdup(pch); | |
pch = strtok (NULL, "\t"); | |
i++; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment