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

public class URLWords {
    /**
     * The URL as a string.
     */
    protected String urlString;

    /**
     * The HashSet containing the words in the web page referred to by the URL.
     */
    protected HashSet words;

    /**
     * Creates a URLWords object for the specified URL.
     *
     * @param url  the URL to download HTML from.
     */
    public URLWords(URL url) {
	InputStream is;

	urlString = url.toString();
	words = new HashSet();
	try {
	    is = url.openStream();
	    HTMLWordParser parser = new HTMLWordParser(is);
	    try {
		String word;
		while ((word = parser.nextWord()) != null)
		    words.add(word.toLowerCase());
	    }

	    catch (IOException e) {
		System.out.println("Error while reading from URL: " +
				   urlString);
	    }

	    finally {
		try {
		    is.close();
		}

		catch (IOException e) {
		    System.out.println("Cannot close stream for URL: " +
				       urlString);
		}
	    }
	}

	catch (IOException e) {
	    System.out.println("Cannot open stream for URL: " + urlString);
	}
    }

    /**
     * Accessor method for the urlString field.
     *
     * @return  the urlString field.
     */
    public String getURL() {
	return urlString;
    }

    /**
     * Determines whether all of the given words are contained in the web page.
     *
     * @param searchWords  the Vector of words to search for.
     * @return             true if all of the words are contained in the web
     *                     page, otherwise false.
     */
    public boolean containsWords(Vector searchWords) {
	Iterator i = searchWords.iterator();
	while (i.hasNext())
	    if (!words.contains((String) i.next()))
		return false;
	return true;
    }
}