X-Git-Url: https://git.pterodactylus.net/?a=blobdiff_plain;f=src%2Fnet%2Fpterodactylus%2Farachne%2Fcore%2FURLFetcher.java;h=59ad6230a034dcc971cdd1baf477f3f89ad3037d;hb=2257173f299e8d0af6e28a19f87ab6036b75ef80;hp=d57e15f69960a3073daa2fe7332df1e2aafc79cb;hpb=cb88a7c9368c4bc32ba5c6caf32c5c51110fde35;p=arachne.git

diff --git a/src/net/pterodactylus/arachne/core/URLFetcher.java b/src/net/pterodactylus/arachne/core/URLFetcher.java
index d57e15f..59ad623 100644
--- a/src/net/pterodactylus/arachne/core/URLFetcher.java
+++ b/src/net/pterodactylus/arachne/core/URLFetcher.java
@@ -7,12 +7,16 @@ 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.number.Hex;
 import de.ina.util.validation.Validation;
 
 /**
@@ -26,8 +30,8 @@ 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;
@@ -38,20 +42,27 @@ class URLFetcher implements Runnable, ParserListener {
 	/** 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 core
-	 *            The core new pages are queued in
+	 * @param parserFactory
+	 *            The parser factory that is used to create content-type
+	 *            specific parsers
 	 * @param url
 	 *            The URL to fetch
 	 * @throws NoSuchAlgorithmException
 	 *             if no {@link MessageDigest} instance with an
 	 *             <code>SHA-256</code> algorithm can be created
 	 */
-	public URLFetcher(Core core, URL url) throws NoSuchAlgorithmException {
-		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");
 	}
@@ -61,6 +72,24 @@ class URLFetcher implements Runnable, ParserListener {
 	//
 
 	/**
+	 * 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.
 	 *
@@ -77,7 +106,7 @@ class URLFetcher implements Runnable, ParserListener {
 	//
 
 	/**
-	 * {@inheritdoc}
+	 * {@inheritDoc}
 	 *
 	 * @see java.lang.Runnable#run()
 	 */
@@ -92,9 +121,14 @@ class URLFetcher implements Runnable, ParserListener {
 			logger.log(Level.INFO, "Type is “" + contentType + "”, length is " + contentLength + ".");
 			urlInputStream = urlConnection.getInputStream();
 			hashInputStream = new MessageDigestInputStream(urlInputStream, messageDigest);
-			HtmlEditorKitParser htmlEditorKitParser = new HtmlEditorKitParser();
-			htmlEditorKitParser.parse(this, hashInputStream, "UTF-8");
+			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();
+			logger.log(Level.FINE, "Hashed “" + url + "” to “" + Hex.toHex(hash) + "”.");
 		} catch (IOException ioe1) {
 			logger.log(Level.WARNING, "Could not fetch “" + url + "”.", ioe1);
 		}
@@ -111,11 +145,16 @@ class URLFetcher implements Runnable, ParserListener {
 		URL newLink = null;
 		try {
 			newLink = new URL(url, linkTarget);
-			core.addPage(newLink);
+			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);
-		} catch (IllegalArgumentException iae1) {
-			logger.log(Level.WARNING, "Could not add “" + newLink + "” to core queue.", iae1);
 		}
 	}
 
@@ -123,6 +162,7 @@ class URLFetcher implements Runnable, ParserListener {
 	 * {@inheritDoc}
 	 */
 	public void parsedTitle(InputStream inputStream, String title) {
+		this.title = title;
 	}
 
 }