Parity with the Google Code project

src/org/yooreeka/algos/reco/collab/similarity/util/SimilarityMatrixRepository.java

@@ -43,6 +43,7 @@
 import org.yooreeka.algos.reco.collab.similarity.naive.UserContentBasedSimilarity;
 import org.yooreeka.algos.reco.collab.similarity.naive.UserItemContentBasedSimilarity;
 import org.yooreeka.config.YooreekaConfigurator;
+import org.yooreeka.util.P;
 
 public class SimilarityMatrixRepository {
 
@@ -115,15 +116,13 @@ public SimilarityMatrix load(RecommendationType type, Dataset data,
 		if (cache != null) {
 			m = cache.get(id);
 			if (m == null) {
-				System.out
-						.println("similarity matrix instance doesn't exist in cache: "
+				P.println("similarity matrix instance doesn't exist in cache: "
 								+ "id: "
 								+ id
 								+ ", cache: '"
 								+ cache.getLocation() + "'.");
 			} else {
-				System.out
-						.println("similarity matrix instance was loaded from cache: "
+				P.println("similarity matrix instance was loaded from cache: "
 								+ "id: "
 								+ id
 								+ ", cache: '"

src/org/yooreeka/util/P.java

@@ -40,12 +40,33 @@
 public class P {
 
 	/**
-	 * Print a 54 character (-) horizontal line.
+	 * Print a horizontal line with 65 characters.
 	 */
 	public static void hline() {
 		println("---------- ---------- ---------- ---------- ---------- ----------");
 	}
-
+
+
+	/**
+	 * Auxiliary method for sending time information to the standard output. 
+	 * Time is measured in milliseconds, see the documentation
+	 * of <tt>System.currentTimeMillis()</tt> for details.
+	 * 
+	 */
+	public static void time() {
+		println("Time: "+System.currentTimeMillis());
+	}
+
+	/**
+	 * Auxiliary method for sending time information to the standard output.
+	 * The time is given in milliseconds and in relation to a given moment
+	 * in the past, determined by the value of the argument <tt>t</tt>. 
+	 * 
+	 */
+	public static void time(long t) {
+		println("Time: "+ (System.currentTimeMillis()-t));
+	}
+
 	public static void main(String[] args) {
 		println(Charset.defaultCharset().displayName());
 		println("" + P.class.getName());

src/org/yooreeka/util/parsing/html/BookmarkParser.java

@@ -0,0 +1,86 @@
+/*
+ *   ________________________________________________________________________________________
+ *   
+ *   Y O O R E E K A
+ *   A library for data mining, machine learning, soft computing, and mathematical analysis
+ *   ________________________________________________________________________________________ 
+ *    
+ *   The Yooreeka project started with the code of the book "Algorithms of the Intelligent Web " 
+ *   (Manning 2009). Although the term "Web" prevailed in the title, in essence, the algorithms 
+ *   are valuable in any software application.
+ *  
+ *   Copyright (c) 2007-2009    Haralambos Marmanis & Dmitry Babenko
+ *   Copyright (c) 2009-2012 Marmanis Group LLC and individual contributors as indicated by the @author tags.  
+ * 
+ *   Certain library functions depend on other Open Source software libraries, which are covered 
+ *   by different license agreements. See the NOTICE file distributed with this work for additional 
+ *   information regarding copyright ownership and licensing.
+ * 
+ *   Marmanis Group LLC licenses this file to You under the Apache License, Version 2.0 (the "License"); 
+ *   you may not use this file except in compliance with the License.  
+ *   You may obtain a copy of the License at
+ *
+ *       http://www.apache.org/licenses/LICENSE-2.0
+ *
+ *   Unless required by applicable law or agreed to in writing, software distributed under 
+ *   the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, 
+ *   either express or implied. See the License for the specific language governing permissions and
+ *   limitations under the License.
+ *
+ */
+package org.yooreeka.util.parsing.html;
+
+import java.io.BufferedInputStream;
+import java.io.FileInputStream;
+import java.io.InputStream;
+import java.io.InputStreamReader;
+import java.io.Reader;
+
+import org.yooreeka.util.parsing.common.ProcessedDocument;
+
+/**
+ * @author haris
+ *
+ */
+public class BookmarkParser extends HTMLDocumentParser {
+
+	/**
+	 * 
+	 */
+	public BookmarkParser() {
+		// TODO Auto-generated constructor stub
+	}
+
+	/**
+	 * @param reader
+	 * @throws HTMLDocumentParserException
+	 */
+	public BookmarkParser(Reader reader) throws HTMLDocumentParserException {
+		super(reader);
+		// TODO Auto-generated constructor stub
+	}
+
+	/**
+	 * @param args
+	 */
+	public static void main(String[] args) {
+
+		String filename = args[0];
+		BookmarkParser bookParser = null;
+		ProcessedDocument doc = null;
+		try {
+			bookParser = new BookmarkParser();
+			InputStream inputStream = new BufferedInputStream(
+					new FileInputStream(filename));
+			Reader reader = new InputStreamReader(inputStream, "UTF-8");
+			doc = bookParser.parse(reader);
+		} catch (Exception e) {
+			throw new RuntimeException("Failed to parse html from file: "
+					+ filename, e);
+		}
+
+		//P.println(doc.getText());
+
+	}
+
+}

test/org/yooreeka/test/TestSandbox.java

@@ -30,8 +30,6 @@
  */
 package org.yooreeka.test;
 
-import org.yooreeka.config.YooreekaConfigurator;
-import org.yooreeka.examples.newsgroups.NewsCrawler;
 
 
 /**
@@ -49,13 +47,5 @@ public class TestSandbox {
 	 * @throws Exception 
 	 */
 	public static void main(String[] args) throws Exception {
-		String rootDir = YooreekaConfigurator.getProperty(YooreekaConfigurator.CRAWL_DATA_DIR);
-
-		NewsCrawler crawler = new NewsCrawler(rootDir, 2, 10);
-
-		crawler.addSeedUrl("http://www.manning.com/");
-
-		crawler.run();
-
 	}
 }