User:Micke/WikiFind

Notice

How to

Regex capability

Reference

1. ↑ Thanx to Jozef Wagner

A few pointers

TODO (and list of things that doesn't work yet):

See also

Source version 1

////////////////////////////////////////////////////////////
//	WikiFind is a program used for reading database dumps 
//	from MediaWiki, written by Mikael Nordin, licensed under 
//	the GNU General Public License (GPL) version 3, 
//	or any later version.				 
//	Copyright Mikael Nordin 2008. 
#include<iostream> //for cin and cout
#include<string>	//for strings
#include<fstream> // for ifstream
#include<boost/regex.hpp> //for regex
usingnamespacestd;
stringkeyword,line,filenamein,filenameout,title,problem,found,looking;//Global variables
stringtitle2="qqqqqqxxxxwpppppzzzzzwwwwqqqq";//title not likely to exist
intnooftitles=0;
voidLang();//Sub-routines
voidSearch();
intmain()//main function
{
Lang();//select language

Search();//searching file
return0;

}
voidLang()//Localization and input/query/output function
{
stringlang,q1,q2,q3;//variables
intlang2=1;

while(lang2!=0)//selecting language
{
cout<<"Välj språk / Please choose language:\n";
cout<<"1. Svenska (sv)\n";
cout<<"2. English (en)\n";
cin>>lang;

if(lang=="sv")//Swedish localization
{
q1="Vilken fil vill du genomsöka: ",
q2="Var vill du spara resultatet: ",
q3="Vilket sökord vill du hitta: ",
problem="Filen kunde inte öppnas\n",
found=" träffar gjordes\n",
looking="Letar efter: ",
lang2=0;
}

elseif(lang=="en")//English localization
{
q1="Which file do you want to search: ",
q2="Where do you want to store results: ",
q3="Which string do you want to seach for: ",
problem="Could not open file\n",
found=" titles found\n",
looking="Looking for: ",
lang2=0;
}

else//incorrect lang choice
{
cout<<"Fel val / Wrong choice\n";
}
}

cin.get();
cout<<q1;
getline(cin,filenamein);

cout<<q2;
getline(cin,filenameout);

cout<<q3;
getline(cin,keyword);
}
voidSearch()//searching database dump
{
ifstreamFileIn(filenamein.c_str());//Open dump
if(!FileIn)//if something goes wrong with file opening
{
cout<<problem;
}

ofstreamFileOut(filenameout.c_str(),ios::app);//Open output file

FileOut<<"== "<<keyword<<" ==\n";//headline to file
cout<<looking<<keyword<<endl;//what we are doing

while(getline(FileIn,line))//reading file line by line
{//checking to see if it's a pagename
if(line[0]==' '&&line[1]==' '&&line[2]==' '&&line[3]==' '
&&line[4]=='<'&&line[5]=='t'&&line[6]=='i'&&line[7]=='t'
&&line[8]=='l'&&line[9]=='e'&&line[10]=='>')
{
title=line;//saving any pagenames

}

boost::regexrexp(keyword);
boost::smatchtokens;

if(boost::regex_search(line,tokens,rexp))//if keyword is found
{
while(title2!=title)//checking to see if pagename is allready stored
{

intlangd=title.length()-19;//removingt xml- taggs
inti=11;

FileOut<<"* [[";//wikiformating

while(langd>0)//printing pagename
{
FileOut<<title[i];
i=i+1;
langd=langd-1;

}

FileOut<<"]]\n";//wikiformating

nooftitles=nooftitles+1;//counting articles

title2=title;//saving new title

langd=title.length()-19;//removingt xml- taggs again
i=11;

cout<<"* [[";//wikiformating

while(langd>0)//printing pagename on screen
{
cout<<title[i];
i=i+1;
langd=langd-1;

}

cout<<"]]\n";//wikiformating	 
}
}
}

FileOut<<endl<<nooftitles<<found<<endl;//printing number of articles to file

cout<<endl<<nooftitles<<found;//printing number of articles to screen
}

Source version 2

////////////////////////////////////////////////////////////
//	WikiFind is a programme used for reading databse dumps 
// from MediaWiki written by Mikael Nordin, licensed under 
//	the GNU General Public License (GPL) version 3, 
// or any later version.				 
//	Copyright Mikael Nordin 2008. 
#include<iostream> //for cin and cout
#include<string>	//for strings
#include<fstream> // for ifstream
#include<boost/regex.hpp> //for regex
usingnamespacestd;
stringline,filenamein,title,problem,found,looking;//Global variables
stringtitle2="qqqqqqxxxxwpppppzzzzzwwwwqqqq";//title not likely to exist
intnooftitles=0;
voidSearch(stringfilenameout,stringkeyword);
intmain(intargc,char*argv[])//main function
{
stringfilenameout=argv[1];
stringkeyword=argv[2];
Search(filenameout,keyword);//searching file
return0;

}
voidSearch(stringfilenameout,stringkeyword)//searching database dump
{
ofstreamFileOut(filenameout.c_str(),ios::app);//Open output file

FileOut<<"== "<<keyword<<" ==\n";//headline to file
cout<<"Looking for: "<<keyword<<endl;//what we are doing
while(getline(cin,line))//reading file line by line
{//checking to see if it's a pagename
if(line[0]==' '&&line[1]==' '&&line[2]==' '&&line[3]==' '
&&line[4]=='<'&&line[5]=='t'&&line[6]=='i'&&line[7]=='t'
&&line[8]=='l'&&line[9]=='e'&&line[10]=='>')
{
title=line;//saving any pagenames

}
boost::regexrexp(keyword);
boost::smatchtokens;

if(boost::regex_search(line,tokens,rexp))//if keyword is found
{
while(title2!=title)//checking to see if pagename is allready stored
{

intlangd=title.length()-19;//removingt xml- taggs
inti=11;

FileOut<<"* [[";//wikiformating

while(langd>0)//printing pagename
{
FileOut<<title[i];
i=i+1;
langd=langd-1;

}

FileOut<<"]]\n";//wikiformating

nooftitles=nooftitles+1;//counting articles

title2=title;//saving new title

langd=title.length()-19;//removingt xml- taggs again
i=11;

cout<<"* [[";//wikiformating

while(langd>0)//printing pagename on screen
{
cout<<title[i];
i=i+1;
langd=langd-1;

}

cout<<"]]\n";//wikiformating	 
}
}
}

FileOut<<endl<<" pages found"<<endl;//printing number of articles to file

cout<<endl<<nooftitles<<" pages found"<<endl;//printing number of articles to screen
}