Improved Java examples

stratosphere-examples/stratosphere-java-examples/src/main/java/eu/stratosphere/example/java/clustering/KMeans.java

@@ -38,7 +38,8 @@ import eu.stratosphere.example.java.clustering.util.KMeansData;
  * Subsequently, each cluster center is moved to the center (<i>mean</i>) of all points that have been assigned to it.
  * The moved cluster centers are fed into the next iteration. 
  * The algorithm terminates after a fixed number of iterations (as in this implementation) 
- * or if cluster centers do not (significantly) move in an iteration.
+ * or if cluster centers do not (significantly) move in an iteration.<br>
+ * This is the Wikipedia entry for the <a href="http://en.wikipedia.org/wiki/K-means_clustering">K-Means Clustering algorithm</a>.
  * 
  * <p>
  * This implementation works on two-dimensional data points. <br>
@@ -290,6 +291,8 @@ public class KMeans {
 		} else {
 			System.out.println("Executing K-Means example with default parameters and built-in default data.");
 			System.out.println("  Provide parameters to read input data from files.");
+			System.out.println("  See the documentation for the correct format of input files.");
+			System.out.println("  We provide a data generator to create synthetic input files for this program.");
 			System.out.println("  Usage: KMeans <points path> <centers path> <result path> <num iterations>");
 		}
 	}

stratosphere-examples/stratosphere-java-examples/src/main/java/eu/stratosphere/example/java/graph/ConnectedComponents.java

@@ -31,15 +31,18 @@ import eu.stratosphere.util.Collector;
 
 /**
  * An implementation of the connected components algorithm, using a delta iteration.
- * Initially, the algorithm assigns each vertex its own ID. After the algorithm has completed, all vertices in the
- * same component will have the same id. In each step, a vertex picks the minimum of its own ID and its
- * neighbors' IDs, as its new ID.
+ * 
+ * <p>
+ * Initially, the algorithm assigns each vertex an unique ID. In each step, a vertex picks the minimum of its own ID and its
+ * neighbors' IDs, as its new ID and tells its neighbors about its new ID. After the algorithm has completed, all vertices in the
+ * same component will have the same ID.
+ * 
  * <p>
- * A vertex whose component did not change needs not propagate its information in the next step. Because of that,
+ * A vertex whose component ID did not change needs not propagate its information in the next step. Because of that,
  * the algorithm is easily expressible via a delta iteration. We here model the solution set as the vertices with
  * their current component ids, and the workset as the changed vertices. Because we see all vertices initially as
  * changed, the initial workset and the initial solution set are identical. Also, the delta to the solution set
- * is consequently also the next workset.
+ * is consequently also the next workset.<br>
  * 
  * <p>
  * Input files are plain text files and must be formatted as follows:
@@ -180,6 +183,7 @@ public class ConnectedComponents implements ProgramDescription {
 		} else {
 			System.out.println("Executing Connected Components example with default parameters and built-in default data.");
 			System.out.println("  Provide parameters to read input data from files.");
+			System.out.println("  See the documentation for the correct format of input files.");
 			System.out.println("  Usage: ConnectedComponents <vertices path> <edges path> <result path> <max number of iterations>");
 		}
 	}

stratosphere-examples/stratosphere-java-examples/src/main/java/eu/stratosphere/example/java/graph/EnumTrianglesBasic.java

@@ -198,6 +198,7 @@ public class EnumTrianglesBasic {
 		} else {
 			System.out.println("Executing Enum Triangles Basic example with built-in default data.");
 			System.out.println("  Provide parameters to read input data from files.");
+			System.out.println("  See the documentation for the correct format of input files.");
 			System.out.println("  Usage: EnumTriangleBasic <edge path> <result path>");
 		}
 	}

stratosphere-examples/stratosphere-java-examples/src/main/java/eu/stratosphere/example/java/graph/EnumTrianglesOpt.java

@@ -322,6 +322,7 @@ public class EnumTrianglesOpt {
 		} else {
 			System.out.println("Executing Enum Triangles Opt example with built-in default data.");
 			System.out.println("  Provide parameters to read input data from files.");
+			System.out.println("  See the documentation for the correct format of input files.");
 			System.out.println("  Usage: EnumTriangleBasic <edge path> <result path>");
 		}
 	}

stratosphere-examples/stratosphere-java-examples/src/main/java/eu/stratosphere/example/java/graph/PageRankBasic.java

@@ -31,7 +31,7 @@ import eu.stratosphere.example.java.graph.util.PageRankData;
 import eu.stratosphere.util.Collector;
 
 /**
- * A basic implementation of the page rank algorithm using a bulk iteration.
+ * A basic implementation of the Page Rank algorithm using a bulk iteration.
  * 
  * <p>
  * This implementation requires a set of pages (vertices) with associated ranks and a set 
@@ -39,7 +39,8 @@ import eu.stratosphere.util.Collector;
  * In each iteration, the rank of every page is evenly distributed to all pages it points to.
  * Each page collects the partial ranks of all pages that point to it, sums them up, and applies a dampening factor to the sum.
  * The result is the new rank of the page. A new iteration is started with the new ranks of all pages.
- * This implementation terminates after a fixed number of iterations.
+ * This implementation terminates after a fixed number of iterations.<br>
+ * This is the Wikipedia entry for the <a href="http://en.wikipedia.org/wiki/Page_rank">Page Rank algorithm</a>. 
  * 
  * <p>
  * Input files are plain text files and must be formatted as follows:
@@ -216,6 +217,7 @@ public class PageRankBasic {
 		} else {
 			System.out.println("Executing PageRank Basic example with default parameters and built-in default data.");
 			System.out.println("  Provide parameters to read input data from files.");
+			System.out.println("  See the documentation for the correct format of input files.");
 			System.out.println("  Usage: PageRankBasic <vertex with initial rank input> <edges path> <output path> <num vertices> <num iterations>");
 			
 			numVertices = PageRankData.getNumberOfPages();

stratosphere-examples/stratosphere-java-examples/src/main/java/eu/stratosphere/example/java/relational/WebLogAnalysis.java

@@ -275,6 +275,8 @@ public class WebLogAnalysis {
 		} else {
 			System.out.println("Executing WebLog Analysis example with built-in default data.");
 			System.out.println("  Provide parameters to read input data from files.");
+			System.out.println("  See the documentation for the correct format of input files.");
+			System.out.println("  We provide a data generator to create synthetic input files for this program.");
 			System.out.println("  Usage: WebLogAnalysis <documents path> <ranks path> <visits path> <result path>");
 		}
 	}

stratosphere-examples/stratosphere-java-examples/src/main/java/eu/stratosphere/example/java/wordcount/WordCount.java

@@ -27,7 +27,7 @@ import eu.stratosphere.util.Collector;
  * over text files. 
  * 
  * <p>
- * The input is plain text files.
+ * The input is a plain text file with lines separated by newline characters.
  * 
  * <p>
  * This example shows how to: