/**
 * @(#)Wiki.java 0.03 10/06/2007
 * Copyright (C) 2007 MER-C
 * Modified by TheFearow
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version 2
 * of the License, or (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
 */

import java.io.*;
import java.util.*;
import java.net.*;

/**
 *  This is somewhat of a sketchy bot framework for editing MediaWiki wikis.
 *  @author MER-C
 *  @version 0.03
 */
public class Wiki
{
    /**
     *  Denotes the namespace of images and media, such that there is no description page.
     *  Uses the "Media:" prefix.
     *  @see IMAGE_NAMESPACE
     *  @since 0.03
     */
    public static final int MEDIA_NAMESPACE = -2;
    
    /**
     *  Denotes the namespace of pages with the "Special:" prefix. Note that many methods
     *  dealing with special pages may spew due to raw content not being available.
     *  @since 0.03
     */
    public static final int SPECIAL_NAMESPACE = -1;
    
    /**
     *  Denotes the main namespace, with no prefix.
     *  @since 0.03
     */
    public static final int MAIN_NAMESPACE = 0;
    
    /**
     *  Denotes the namespace for talk pages relating to the main namespace, denoted by the
     *  prefix "Talk:".
     *  @since 0.03
     */
    public static final int TALK_NAMESPACE = 1;
    
    /**
     *  Denotes the namespace for user pages, given the prefix "User:".
     *  @since 0.03
     */
    public static final int USER_NAMESPACE = 2;
    
    /**
     *  Denotes the namespace for user talk pages, given the prefix "User talk:".
     *  @since 0.03
     */
    public static final int USER_TALK_NAMESPACE = 3;
    
    /**
     *  Denotes the namespace for pages relating to the project, with prefix "Project:". It
     *  also goes by the name of whatever the project name was.
     *  @since 0.03
     */
    public static final int PROJECT_NAMESPACE = 4;
    
    /**
     *  Denotes the namespace for talk pages relating to project pages, with prefix "Project
     *  talk:". It also goes by the name of whatever the project name was, + "talk:".
     *  @since 0.03
     */
    public static final int PROJECT_TALK_NAMESPACE = 5;
    
    /**
     *  Denotes the namespace for image description pages. Has the prefix "Image:". Do not
     *  create these directly, use upload() instead.
     *  @see MEDIA_NAMESPACE
     *  @since 0.03
     */
    public static final int IMAGE_NAMESPACE = 6;
    
    /**
     *  Denotes talk pages for image description pages. Has the prefix "Image talk:".
     *  @since 0.03
     */
    public static final int IMAGE_TALK_NAMESPACE = 7;
    
    /**
     *  Denotes the namespace for (wiki) system messages, given the prefix "MediaWiki:".
     *  @since 0.03
     */
    public static final int MEDIAWIKI_NAMESPACE = 8;
    
    /**
     *  Denotes the namespace for talk pages relating to system messages, given the prefix
     *  "MediaWiki talk:".
     *  @since 0.03
     */
    public static final int MEDIAWIKI_TALK_NAMESPACE = 9;
    
    /**
     *  Denotes the namespace for templates, given the prefix "Template:".
     *  @since 0.03
     */
    public static final int TEMPLATE_NAMESPACE = 10;
    
    /**
     *  Denotes the namespace for talk pages regarding templates, given the prefix
     *  "Template talk:". 
     *  @since 0.03
     */
    public static final int TEMPLATE_TALK_NAMESPACE = 11;
    
    /**
     *  Denotes the namespace for help pages, given the prefix "Help:".
     *  @since 0.03
     */
    public static final int HELP_NAMESPACE = 12;
    
    /**
     *  Denotes the namespace for talk pages regarding help pages, given the prefix "Help
     *  talk:".
     *  @since 0.03
     */
    public static final int HELP_TALK_NAMESPACE = 13;
    
    /**
     *  Denotes the namespace for category description pages. Has the prefix "Category:".
     *  @since 0.03
     */
    public static final int CATEGORY_NAMESPACE = 14;
    
    /**
     *  Denotes the namespace for talk pages regarding categories. Has the prefix "Category
     *  talk:".
     *  @since 0.03
     */
    public static final int CATEGORY_TALK_NAMESPACE = 15;
    
    /**
     *  Denotes all namespaces.
     *  @since 0.03
     */
    public static final int ALL_NAMESPACES = 0x09f91102;
    
    // the domain of the wiki
    private String domain;
    private String query;

    // something to handle cookies
    private Map cookies = new HashMap(10);
    
    // internal data storage
    private Map namespaces = null;

    /**
     *  Creates a new connection to the English Wikipedia.
     *  @since 0.02
     */
    public Wiki()
    {
        this("");
    }

    /**
     *  Creates a new connection to a wiki.
     *  @param domain the wiki domain name e.g. en.wikipedia.org (defaults to en.wikipedia.org)
     */
    public Wiki(String domain)
    {
        if (domain == null || domain == "")
            domain = "en.wikipedia.org";
        this.domain = "http://" + domain + "/w/index.php";
        query = "http://" + domain + "/w/query.php";
    }
    
    /**
     *  Logs in to the wiki
     *  @param username a username
     *  @param password a password (as a char[] due to JPasswordField)
     *  @return whether the login succeeded
     *  @throws IOException if something goes wrong
     */
    public boolean login(String username, char[] password) throws IOException
    {
        // sanitize
        String ps = new String(password);
        username = URLEncoder.encode(username);
        ps = URLEncoder.encode(ps);

        // "enable" cookies
        String URL = domain + "?title=Special:Userlogin";
        URLConnection connection = new URL(URL).openConnection();
        grabCookies(connection);
        
        // find the target
        URL = domain + "?title=Special:Userlogin&action=submitlogin&type=login";
        connection = new URL(URL).openConnection();
        setCookies(connection);
        connection.setDoOutput(true);
        PrintWriter out = new PrintWriter(connection.getOutputStream());
        
        // now we send the data
        out.print("wpName=");
        out.print(username);
        out.print("&wpPassword=");
        out.print(ps);
        out.print("&wpRemember=1&wpLoginattempt=Log+in");
        out.close();

        // make it stick by grabbing the cookie
        grabCookies(connection);
        BufferedReader in = null;
        try
        {
            in = new BufferedReader(new InputStreamReader(connection.getInputStream()));
        }
        catch (IOException e)
        {
            if (!(connection instanceof HttpURLConnection))
                throw e;
            InputStream err = ((HttpURLConnection)connection).getInputStream();
            if (err == null)
                throw e;
            in = new BufferedReader(new InputStreamReader(err));
        }
        in.readLine();
        
        // test for success
        String line;
        while ((line = in.readLine()) != null)
            if (line.indexOf("Login successful") != -1)
                return true;
        return false;
    }

    /**
     *  Logs out of the wiki.
     */
    public void logout()
    {
        cookies.clear();
    }

    /**
     *  Gets the raw wikicode for a page. WARNING: does not support special pages.
     *  @param title the title of the page.
     *  @throws IOException if something stuffs up the connection between here and wiki
     *  @return the raw wikicode of a page
     *  @throws IllegalArgumentException if you try to retrieve the text of a Special: page or a Media: page
     */
    public String getPageText(String title) throws IOException
    {
        // pitfall check
        if (namespace(title) < 0)
            throw new IllegalArgumentException("Cannot retrieve Special: or Media: pages!");
        
        // sanitise the title
        title = URLEncoder.encode(title);
                    
        // go for it
        String URL = domain + "?title=" + title + "&action=raw";
        URLConnection connection = new URL(URL).openConnection();
        connection.connect();
        BufferedReader in = new BufferedReader(new InputStreamReader(connection.getInputStream()));
        
        // get the text
        String line;
        StringBuffer text = new StringBuffer();
        while ((line = in.readLine()) != null)
            text.append(line+"\n");
        return text.toString();
    }

/**
     *  Gets the rendered HTML for a page. WARNING: does not support special pages.
     *  @param title the title of the page.
     *  @throws IOException if something stuffs up the connection between here and wiki
     *  @return the rendered HTML of a page
     *  @throws IllegalArgumentException if you try to retrieve the text of a Special: page or a Media: page
     */
    public String getPageTextRendered(String title) throws IOException
    {
        // pitfall check
        if (namespace(title) < 0)
            throw new IllegalArgumentException("Cannot retrieve Special: or Media: pages!");
        
        // sanitise the title
        title = URLEncoder.encode(title);
                    
        // go for it
        String URL = domain + "?title=" + title + "&action=render";
        URLConnection connection = new URL(URL).openConnection();
        connection.connect();
        BufferedReader in = new BufferedReader(new InputStreamReader(connection.getInputStream()));
        
        // get the text
        String line;
        StringBuffer text = new StringBuffer();
        while ((line = in.readLine()) != null)
            text.append(line+"\n");
        return text.toString();
    }

    /**
     *  Edits a page by setting its text to the supplied value.
     *  @param text the text of the page
     *  @param title the title of the page
     *  @param summary the edit summary
     *  @param minor whether the edit should be marked as minor
     *  @throws IOException if something stuffs up the connection between here and wiki
     *  @throws IllegalArgumentException if you try to edit a Special: page or a Media: page
     */
    public void editPage(String title, String text, String summary, boolean minor) throws IOException
    {
        // pitfall check
        if (namespace(title) < 0)
            throw new IllegalArgumentException("Cannot edit Special: or Media: pages!");
            
        // sanitise
        title = URLEncoder.encode(title);
        summary = URLEncoder.encode(summary);
        text = URLEncoder.encode(text);
        
        // what we need to do is get the edit page and fish out the wpEditToken, wpAutoSummary
        // wpStartTime and wpEditTime values
        String URL = domain + "?title=" + title + "&action=edit";
        URLConnection connection = new URL(URL).openConnection();
        setCookies(connection);
        connection.connect();
        grabCookies(connection);
        BufferedReader in = new BufferedReader(new InputStreamReader(connection.getInputStream()));
        
        // more specifically, we're looking for "name="wpEditToken"", "name="wpAutoSummary""
        String line, wpEditToken = "", wpAutoSummary = "", wpStarttime = "", wpEdittime = "";
        boolean editRetrieved = false, summaryRetrieved = false, startRetrieved = false,
            timeRetrieved = false, watchRetrieved = false;
        boolean watched = false;
        while ((line = in.readLine()) != null)
        {
            if (line.indexOf("name=\"wpAutoSummary\"") != -1)
            {
                int x = line.indexOf("value=\"") + 7;
                wpAutoSummary = line.substring(x, line.indexOf('\"', x));
                summaryRetrieved = true;
            }
            else if (line.indexOf("name=\"wpEditToken\"") != -1)
            {
                int x = line.indexOf("value=\"") + 7;
                wpEditToken = line.substring(x, line.indexOf('\"', x));
                editRetrieved = true;
            }
            else if (line.indexOf("name=\"wpEdittime\"") != -1)
            {
                int x = line.indexOf("value=\"") + 7;
                wpEdittime = line.substring(x, line.indexOf('\"', x));
                timeRetrieved = true;
            }
            else if (line.indexOf("name=\"wpStarttime\"") != -1)
            {
                int x = line.indexOf("value=\"") + 7;
                wpStarttime = line.substring(x, line.indexOf('\"', x));
                startRetrieved = true;
            }
            else if (line.indexOf("name=\"wpWatchthis\"") != -1)
            {
                watched = (line.indexOf("checked=\"") != -1);
                watchRetrieved = true;
            }
            else if (editRetrieved && summaryRetrieved && startRetrieved && timeRetrieved && watchRetrieved)
                break; // bandwidth hack
        }
            
        // this is what accepts the text
        URL = domain + "?title=" + title + "&action=submit";
        connection = new URL(URL).openConnection();
        setCookies(connection);
        connection.setDoOutput(true);
        PrintWriter out = new PrintWriter(connection.getOutputStream());
        
        // now we send the data
        out.print("wpTextbox1=");
        out.print(text);
        out.print("&wpSummary=");
        out.print(summary);
        if (minor)
            out.print("&wpMinoredit=1");
        if (watched)
            out.print("&wpWatchthis=1");
        out.print("&wpEdittime=");
        out.print(wpEdittime);
        out.print("&wpEditToken=");
        out.print(wpEditToken);
        out.print("&wpStarttime=");
        out.print(wpStarttime);
        out.print("&wpAutoSummary=");
        out.print(wpAutoSummary);
        
        //done, give the servers a rest
        out.close();
        try
        {
            Thread.sleep(2000);
            
            // it's somewhat strange that the edit only sticks when you start reading the
            // response...
            in = new BufferedReader(new InputStreamReader(connection.getInputStream()));
        }
        catch (IOException e)
        {
            if (!(connection instanceof HttpURLConnection))
                throw e;
            InputStream err = ((HttpURLConnection)connection).getInputStream();
            if (err == null)
                throw e;
            in = new BufferedReader(new InputStreamReader(err));
        }
        catch (InterruptedException e)
        {
            // nobody cares
        }
        in.readLine();
        
        // for debugging and/or todo purposes
//        String line;
//        while ((line = in.readLine()) != null)
//        {
//            System.out.println(line);
//        }
     }

    /**
     *  Prepends something to the given page. A convenience method for adding maintainance
     *  templates, rather than getting and setting the page yourself. Edit summary is
     *  automatic, being "+whatever".
     *  @param title the title of the page
     *  @param stuff what to prepend to the page
     *  @param minor whether the edit is minor (a prod compared to a simple tag)
     *  @throws IOException if something goes wrong
     */
    public void addPagePrefix(String title, String stuff, boolean minor) throws IOException
    {
        StringBuffer text = new StringBuffer();
        text.append(stuff);
        text.append(getPageText(title));
        editPage(title, text.toString(), "Added prefix +" + stuff, minor);
    }

/**
     *  Adds something to the end of the given page. A convenience method for adding various
     *  things, rather than getting and setting the page yourself. Edit summary is
     *  automatic, being "+whatever".
     *  @param title the title of the page
     *  @param stuff what to add to the page
     *  @param minor whether the edit is minor (a prod compared to a simple tag)
     *  @throws IOException if something goes wrong
     */
    public void addPageSuffix(String title, String stuff, boolean minor) throws IOException
    {
        StringBuffer text = new StringBuffer();
        text.append(getPageText(title));
        text.append(stuff);
        editPage(title, text.toString(), "Added suffix +" + stuff, minor);
    }
    
    /**
     *  Gets the members of a category.
     *  @param name the name of the category (e.g. Candidates for speedy deletion, not
     *  Category:Candidates for speedy deletion)
     *  @return a String[] containing page titles of members of the category
     *  @throws IOException if something goes wrong
     *  @since 0.02
     */
    public String[] getCategoryMembers(String name) throws IOException
    {
        return getCategoryMembers(name, ALL_NAMESPACES);
    }
    
    /**
     *  Gets the members of a category.
     *  @param name the name of the category (e.g. Candidates for speedy deletion, not
     *  Category:Candidates for speedy deletion)
     *  @param namespace filters by namespace, returns empty if namespace does not exist
     *  @return a String[] containing page titles of members of the category
     *  @throws IOException if something goes wrong
     *  @since 0.03
     */
    public String[] getCategoryMembers(String name, int namespace) throws IOException
    {
        String url;
        if (namespace == ALL_NAMESPACES)
            url = query + "?what=category&format=xml&cptitle=" + URLEncoder.encode(name);
        else
            url = query + "?what=category&format=xml&cptitle=" + URLEncoder.encode(name) + "&cpnamespace=" + namespace;
        URLConnection connection = new URL(url).openConnection();
        connection.connect();
        
        // read the first line, as it is the only thing worth paying attention to
        BufferedReader in = new BufferedReader(new InputStreamReader(connection.getInputStream()));
        String line = in.readLine();

        // parse
        ArrayList<String> members = new ArrayList<String>(10000); // enough for most cats
        while (line.indexOf("<title>") != -1)
        {
            int x = line.indexOf("<title>");
            int y = line.indexOf("</title");
            members.add(line.substring(x + 7, y));
            line = line.substring(y + 8, line.length());
        }
        return members.toArray(new String[0]);
    }
    
    /**
     *  Returns the namespace the page is in. Uses /w/query.php?what=namespaces to fetch
     *  list of namespaces.
     *  @since 0.03
     *  @return one of namespace types above, or a number for custom namespaces or ALL_NAMESPACES
     *  if we can't make sense of it
     *  @throws IOException if something goes wrong
     */
    public int namespace(String title) throws IOException
    {
        // sanitise
        title = title.replace('_', ' ');
        if (title.indexOf(':') == -1)
            return MAIN_NAMESPACE;
        String namespace = title.substring(0, title.indexOf(':'));

        // all wiki namespace test
        if (namespace.equals("Project talk"))
            return PROJECT_TALK_NAMESPACE;
        if (namespace.equals("Project"))
            return PROJECT_NAMESPACE;
        
        if (namespaces == null)
        {
            URLConnection connection = new URL(query + "?what=namespaces&format=xml").openConnection();
            connection.connect();
        
            // read the first line, as it is the only thing worth paying attention to
            BufferedReader in = new BufferedReader(new InputStreamReader(connection.getInputStream()));
            String line = in.readLine();
            
            namespaces = new HashMap(20);
            while (line.indexOf("<ns") != -1)
            {
                int x = line.indexOf("<ns id=");
                if (line.charAt(x + 8) == '0')
                {
                    line = line.substring(13, line.length());
                    continue;
                }
                int y = line.indexOf("</ns>");
                String working = line.substring(x + 8, y);
                int ns = Integer.parseInt(working.substring(0, working.indexOf('"')));
                String name = working.substring(working.indexOf(">") + 1, working.length());
                namespaces.put(name, new Integer(ns));
                line = line.substring(y + 5, line.length());
            }
        }
        
        if (!namespaces.containsKey(namespace))
            return MAIN_NAMESPACE; // For titles like UN:NRV
        Iterator i = namespaces.entrySet().iterator();
        while (i.hasNext())
        {
            Map.Entry entry = (Map.Entry)i.next();
            if (entry.getKey().equals(namespace))
                return ((Integer)entry.getValue()).intValue();
        }
        return ALL_NAMESPACES; // unintelligble title
    }

     
     /**
      *  Grabs cookies from the URL connection provided.
      *  @param u an unconnected URLConnection
      */
     private void grabCookies(URLConnection u)
     {
        // reset the cookie store
        cookies.clear();
        String headerName = null;
        for (int i = 1; (headerName = u.getHeaderFieldKey(i)) != null; i++)
        {
            if (headerName.equals("Set-Cookie"))
            {
                String cookie = u.getHeaderField(i);     
                cookie = cookie.substring(0, cookie.indexOf(";"));
                String name = cookie.substring(0, cookie.indexOf("="));
                String value = cookie.substring(cookie.indexOf("=") + 1, cookie.length());
                cookies.put(name, value);
            }
        }
    }

    /**
     *  Sets cookies to an unconnected URLConnection.
     *  @param u an unconnected URLConnection
     */
    private void setCookies(URLConnection u)
    {
        Iterator i = cookies.entrySet().iterator();
        StringBuffer cookie = new StringBuffer();
        while (i.hasNext())
        {
            Map.Entry entry = (Map.Entry)i.next();
            cookie.append(entry.getKey());
            cookie.append("=");
            cookie.append(entry.getValue());
            cookie.append("; ");
        }
        u.setRequestProperty("Cookie", cookie.toString());
    }
}