Use a default parser factory in the core and hand it in to every URL fetcher.

[arachne.git] / src / net / pterodactylus / arachne / core / URLFetcher.java

diff --git a/src/net/pterodactylus/arachne/core/URLFetcher.java b/src/net/pterodactylus/arachne/core/URLFetcher.java
index 0b4cb47..cdccd2b 100644 (file)
--- a/src/net/pterodactylus/arachne/core/URLFetcher.java
+++ b/src/net/pterodactylus/arachne/core/URLFetcher.java
@@ -5,11 +5,17 @@ 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;
 
 /**
@@ -23,26 +29,81 @@ 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}
         *
@@ -50,13 +111,18 @@ class URLFetcher implements Runnable, ParserListener {
         */
        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);
+                       parser.parse(this, hashInputStream, "UTF-8");
+                       hash = messageDigest.digest();
                } catch (IOException ioe1) {
                        logger.log(Level.WARNING, "Could not fetch “" + url + "”.", ioe1);
                }
@@ -73,11 +139,12 @@ class URLFetcher implements Runnable, ParserListener {
                URL newLink = null;
                try {
                        newLink = new URL(url, linkTarget);
-                       core.addPage(newLink);
+                       Page newPage = Page.fromURL(newLink);
+                       if (newPage != null) {
+                               collectedPages.add(newPage);
+                       }
                } 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);
                }
        }
 
@@ -85,6 +152,7 @@ class URLFetcher implements Runnable, ParserListener {
         * {@inheritDoc}
         */
        public void parsedTitle(InputStream inputStream, String title) {
+               this.title = title;
        }
 
 }