X-Git-Url: https://git.pterodactylus.net/?a=blobdiff_plain;f=src%2Fnet%2Fpterodactylus%2Farachne%2Fcore%2FURLFetcher.java;h=ea109d0c82c49f3f6ebabe4ee5d95b0a5bd40dea;hb=bc2a6cc23e93037cae7f52815f20bdf24504ce5d;hp=df8180f038e064a986143bd44b7acbedde07ea92;hpb=0669aab9c004816d56a5e16c17b0492b53ddf9a8;p=arachne.git

diff --git a/src/net/pterodactylus/arachne/core/URLFetcher.java b/src/net/pterodactylus/arachne/core/URLFetcher.java
index df8180f..ea109d0 100644
--- a/src/net/pterodactylus/arachne/core/URLFetcher.java
+++ b/src/net/pterodactylus/arachne/core/URLFetcher.java
@@ -2,13 +2,20 @@ package net.pterodactylus.arachne.core;
 
 import java.io.IOException;
 import java.io.InputStream;
+import java.net.MalformedURLException;
 import java.net.URL;
 import java.net.URLConnection;
+import java.security.MessageDigest;
+import java.security.NoSuchAlgorithmException;
+import java.util.ArrayList;
+import java.util.List;
 import java.util.logging.Level;
 import java.util.logging.Logger;
 
-import net.pterodactylus.arachne.parser.HtmlEditorKitParser;
+import net.pterodactylus.arachne.parser.Parser;
+import net.pterodactylus.arachne.parser.ParserFactory;
 import net.pterodactylus.arachne.parser.ParserListener;
+import de.ina.util.io.MessageDigestInputStream;
 import de.ina.util.validation.Validation;
 
 /**
@@ -22,40 +29,104 @@ class URLFetcher implements Runnable, ParserListener {
 	/** The logger. */
 	private static final Logger logger = Logger.getLogger(URLFetcher.class.getName());
 
-	/** The core. */
-	private final Core core;
+	/** The parser factory. */
+	private final ParserFactory parserFactory;
 
 	/** The URL to fetch. */
 	private final URL url;
 
+	/** The message digest. */
+	private final MessageDigest messageDigest;
+
+	/** The hash of the fetched URL. */
+	private byte[] hash;
+
+	/** The collected URLs. */
+	private final List<Page> collectedPages = new ArrayList<Page>();
+
+	/** The title of the URL. */
+	private String title;
+
 	/**
 	 * Creates a new fetcher for the given URL.
 	 *
+	 * @param parserFactory
+	 *            The parser factory that is used to create content-type
+	 *            specific parsers
 	 * @param url
 	 *            The URL to fetch
-	 * @param core
-	 *            TODO
+	 * @throws NoSuchAlgorithmException
+	 *             if no {@link MessageDigest} instance with an
+	 *             <code>SHA-256</code> algorithm can be created
 	 */
-	public URLFetcher(Core core, URL url) {
-		Validation.begin().isNotNull("core", core).isNotNull("url", url).check();
-		this.core = core;
+	public URLFetcher(ParserFactory parserFactory, URL url) throws NoSuchAlgorithmException {
+		Validation.begin().isNotNull("parserFactory", parserFactory).isNotNull("url", url).check();
+		this.parserFactory = parserFactory;
 		this.url = url;
+		messageDigest = MessageDigest.getInstance("SHA-256");
+	}
+
+	//
+	// ACCESSORS
+	//
+
+	/**
+	 * Returns the title of the fetched URL.
+	 *
+	 * @return The fetched URL’s title
+	 */
+	public String getTitle() {
+		return title;
+	}
+
+	/**
+	 * Returns the pages collected while parsing this URL.
+	 *
+	 * @return The collected pages
+	 */
+	public List<Page> getCollectedPages() {
+		return collectedPages;
+	}
+
+	/**
+	 * Returns the hash of the content of the fetched URL. The returned value is
+	 * only valid after {@link #run()} has been called.
+	 *
+	 * @return The hash of the fetched content
+	 */
+	public byte[] getHash() {
+		byte[] hashCopy = new byte[hash.length];
+		System.arraycopy(hash, 0, hashCopy, 0, hash.length);
+		return hashCopy;
 	}
 
+	//
+	// INTERFACE Runnable
+	//
+
 	/**
-	 * {@inheritdoc}
+	 * {@inheritDoc}
 	 *
 	 * @see java.lang.Runnable#run()
 	 */
 	public void run() {
 		logger.log(Level.INFO, "Starting URL Fetcher for “" + url + "”.");
+		InputStream urlInputStream = null;
+		MessageDigestInputStream hashInputStream = null;
 		try {
 			URLConnection urlConnection = url.openConnection();
 			long contentLength = urlConnection.getContentLength();
 			String contentType = urlConnection.getContentType();
 			logger.log(Level.INFO, "Type is “" + contentType + "”, length is " + contentLength + ".");
-			HtmlEditorKitParser htmlEditorKitParser = new HtmlEditorKitParser();
-			htmlEditorKitParser.parse(this, urlConnection.getInputStream(), "UTF-8");
+			urlInputStream = urlConnection.getInputStream();
+			hashInputStream = new MessageDigestInputStream(urlInputStream, messageDigest);
+			Parser parser = parserFactory.getParser(contentType);
+			if (parser == null) {
+				logger.log(Level.INFO, "No parser found for “" + contentType + "”.");
+				return;
+			}
+			parser.parse(this, hashInputStream, "UTF-8");
+			hash = messageDigest.digest();
 		} catch (IOException ioe1) {
 			logger.log(Level.WARNING, "Could not fetch “" + url + "”.", ioe1);
 		}
@@ -69,14 +140,27 @@ class URLFetcher implements Runnable, ParserListener {
 	 * {@inheritDoc}
 	 */
 	public void parsedLink(InputStream inputStream, String linkTarget, String linkTitle, String linkText) {
-		System.out.println("Found link to “" + linkTarget + "” named “" + linkText + "” or “" + linkTitle + "”.");
+		URL newLink = null;
+		try {
+			newLink = new URL(url, linkTarget);
+			try {
+				Page newPage = Page.fromURL(newLink);
+				if (newPage != null) {
+					collectedPages.add(newPage);
+				}
+			} catch (IllegalArgumentException iae1) {
+				/* ignore. */
+			}
+		} catch (MalformedURLException mue1) {
+			logger.log(Level.WARNING, "Could not create URL from “" + url + "” and “" + linkTarget + "”.", mue1);
+		}
 	}
 
 	/**
 	 * {@inheritDoc}
 	 */
 	public void parsedTitle(InputStream inputStream, String title) {
-		System.out.println("Found title “" + title + "”.");
+		this.title = title;
 	}
 
 }