I need to count the occurrences of the string "<page>"
in a 104gb file, for getting the number of articles in a given Wikipedia dump. First, I've tried this.
grep -F '<page>' enwiki-20141208-pages-meta-current.xml | uniq -c
However, grep crashes after a while. Therefore, I wrote the following program. However, it only processes 20mb/s of the input file on my machine which is about 5% workload of my HDD. How can I speed up this code?
#include <iostream>
#include <fstream>
#include <string>
int main()
{
// Open up file
std::ifstream in("enwiki-20141208-pages-meta-current.xml");
if (!in.is_open()) {
std::cout << "Could not open file." << std::endl;
return 0;
}
// Statistics counters
size_t chars = 0, pages = 0;
// Token to look for
const std::string token = "<page>";
size_t token_length = token.length();
// Read one char at a time
size_t matching = 0;
while (in.good()) {
// Read one char at a time
char current;
in.read(¤t, 1);
if (in.eof())
break;
chars++;
// Continue matching the token
if (current == token[matching]) {
matching++;
// Reached full token
if (matching == token_length) {
pages++;
matching = 0;
// Print progress
if (pages % 1000 == 0) {
std::cout << pages << " pages, ";
std::cout << (chars / 1024 / 1024) << " mb" << std::endl;
}
}
}
// Start over again
else {
matching = 0;
}
}
// Print result
std::cout << "Overall pages: " << pages << std::endl;
// Cleanup
in.close();
return 0;
}