/*
    My c++ solution for the c++ vs. perl bakeoff at 
    http://www.hardforum.com/showthread.php?t=1077745.

    The program takes a MySQL SQL dump file (lines with a comma-separated 
    list of quoted values with \ used to escape certain chars in each value) 
    from Wikipedia and chops it up into a tab-delimited file (lines with a 
    tab-separated list of values). The file used is page.sql.gz from 
    http://download.wikimedia.org/enwiki/20060702/.

    See http://www.hardforum.com/showpost.php?p=1029721556&postcount=56 
    for correct results.

*/

#include <string>
#include <fstream>
using namespace std;

inline void parseQuotedValue(const string& s, size_t& i, string& out) {
    while (i < s.size()) {
        ++i;
        if (s[i] == '\\' && i + 1 < s.size()) {
            char h = s[i + 1];
            if (h == '\'') {
                out.push_back('\'');
                ++i;
            } else if (h == '\\') {
                out.push_back('\\');
                ++i;
            } 
        } else if (s[i] == '\'') {
            break;
        } else if (s[i] == '_') {
            out.push_back(' ');
        } else if (s[i] != ' ') {
            out.push_back(s[i]);
        }
    }
}

inline void parseLine(const string& s, ofstream& out) {
    string buffer;
    for (size_t i = 26; i < s.size(); ++i) {
        if ( s[i] == '\'' ) {
            parseQuotedValue(s, i, buffer);
        } else if (s[i] == ',') {
            buffer.push_back('\t');
        } else if (s[i] == ')') {
            buffer.push_back('\r');
            buffer.push_back('\n');
            i += 2;
        } else if (s[i] != '(') {
            buffer.push_back(s[i]);
        }
    }
    out << buffer;
}

int main(int argc, char* argv[]) {
    if (argc != 3) {
        return 1;
    }
    ifstream in(argv[1], ios::binary);
    if (!in) {
        return 1;
    }
    ofstream out(argv[2], ios::binary);
    if (!out) {
        return 1;
    }
    for (string s; getline(in, s); ) {
        if (s.find("INSERT INTO `page` VALUES") == 0) {
            parseLine(s, out);
        }
    }
}

// g++ -Wall -Wextra bakeoff-0.cpp -o bakeoff-0 -O3 -s