/*
Copyright (c) 2008  Franklin Schmidt <fschmidt@gmail.com>

Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.
*/

package fschmidt.tools;

import java.io.IOException;
import java.net.URL;
import java.util.Set;
import java.util.HashSet;
import java.util.Map;
import java.util.HashMap;
import java.util.Arrays;
import java.util.Iterator;
import fschmidt.util.java.IoUtils;
import fschmidt.html.Html;
import fschmidt.html.HtmlTag;


public class CrawlSite {
	private static final Set<String> endings = new HashSet<String>( Arrays.asList( new String[]{
		"html", "htm", "ssp", "jsp", "jtp",
	} ) );
	private static final Map<String,String> tagMap = new HashMap<String,String>();
	static {
		tagMap.put("a","href");
		tagMap.put("area","href");
		tagMap.put("base","href");
		tagMap.put("form","action");
		tagMap.put("frame","src");
		tagMap.put("img","src");
		tagMap.put("link","href");
		tagMap.put("input","src");
	}

	private String baseUrl;
	private Set<String> done = new HashSet<String>();

	public CrawlSite(String baseUrl) {
		this.baseUrl = baseUrl;
	}

	protected boolean isHtml(String url) {
		url = url.substring( url.lastIndexOf('/') + 1 );
		int i = url.indexOf('.');
		if( i == -1 )
			return true;
		String ending = url.substring(i+1);
		return endings.contains(ending);
	}

	protected void process(String url) {
		System.out.println(url);
	}

	public void crawl()
		throws IOException
	{
		crawl(baseUrl);
	}

	private void crawl(String url)
		throws IOException
	{
		if( !done.add(url) )
			return;

		process(url);

		if( !isHtml(url) )
			return;

		String page = IoUtils.readPage(url);
		Html html = new Html(page);
		Iterator iter = html.iterator();
		while( iter.hasNext() ) {
			Object o = iter.next();
			if( !(o instanceof HtmlTag) )
				continue;
			HtmlTag tag = (HtmlTag)o;
			String tagName = tag.getName().toLowerCase();
			String attrName = (String)tagMap.get(tagName);
			if( attrName==null )
				continue;
			String val = tag.getAttributeValue(attrName);
			if( val==null )
				continue;
			String url2 = HtmlTag.unquote(val);
			url2 = new URL(new URL(url),url2).toString();
			if( !url2.startsWith(baseUrl) )
				continue;
			int i = url2.indexOf('#');
			if( i != -1 )
				url2 = url2.substring(0,i);
			String file = url2.substring( url2.lastIndexOf('/') + 1 );
			if( file.length() > 0 && file.indexOf('.') == -1 )
				url2 += '/';
			try {
				crawl(url2);
			} catch(IOException e) {
//				System.err.println(e);
				System.err.println(e+"  referred to from "+url);
//				e.printStackTrace();
			}
		}
	}

	public static void main(String[] args) throws Exception {
		new CrawlSite(args[0]).crawl();
	}
}