Refactoring Wikipedia collection classes to make more consistent with other collection processing classes.

Author: jimmy0017

docs/content/wikipedia.html

@@ -186,8 +186,8 @@ <h2>Sequentially-Numbered Docnos</h2>
 docids and docnos by the following command:</p>
 
 <pre class="code">
-etc/hadoop-cluster.sh edu.umd.cloud9.collection.wikipedia.BuildWikipediaDocnoMapping \
-  -input /shared/collections/wikipedia/raw/enwiki-20130503-pages-articles.xml -output_path tmp \
+etc/hadoop-cluster.sh edu.umd.cloud9.collection.wikipedia.WikipediaDocnoMappingBuilder \
+  -input /shared/collections/wikipedia/raw/enwiki-20130503-pages-articles.xml \
   -output_file enwiki-20130503-docno.dat -wiki_language en -keep_all 
 </pre>
 
@@ -201,7 +201,7 @@ <h2>Sequentially-Numbered Docnos</h2>
 fast lookup), using article titles as docids would be expensive (lots
 of strings to store in memory).</p>
 
-<p>Note that by default, <code>BuildWikipediaDocnoMapping</code>
+<p>Note that by default, <code>WikipediaDocnoMappingBuilder</code>
 discards non-articles (e.g., disambiguation pages, redirects,
 etc.). To retain all pages, use the <code>-keep_all</code> option.</p>
 
@@ -288,9 +288,8 @@ <h2>Supporting Random Access</h2>
 index:</p>
 
 <pre class="code">
-etc/hadoop-cluster.sh edu.umd.cloud9.collection.wikipedia.BuildWikipediaForwardIndex \
-  -input /user/jimmylin/enwiki-20130503.block \
-  -output tmp -index_file enwiki-20130503.findex.dat
+etc/hadoop-cluster.sh edu.umd.cloud9.collection.wikipedia.WikipediaForwardIndexBuilder \
+  -input /user/jimmylin/enwiki-20130503.block -index_file enwiki-20130503.findex.dat
 </pre>
 
 <p><b>Note:</b> It mostly doesn't matter elsewhere, but

etc/TODO.txt

@@ -1 +1,2 @@
-- Wikipedia examples: eliminate the -tmp option
+- write test cases for Bidimap
+

src/dist/edu/umd/cloud9/collection/trec/TrecDocnoMappingBuilder.java

@@ -48,7 +48,7 @@
  */
 public class TrecDocnoMappingBuilder extends Configured implements Tool, DocnoMapping.Builder {
   private static final Logger LOG = Logger.getLogger(TrecDocnoMappingBuilder.class);
-  private static final Random random = new Random();
+  private static final Random RANDOM = new Random();
   private static enum Count { DOCS };
 
   private static class MyMapper extends Mapper<LongWritable, TrecDocument, Text, IntWritable> {
@@ -93,12 +93,12 @@ public int build(Path src, Path dest, Configuration conf) throws IOException {
    */
   public int run(String[] args) throws IOException {
     DocnoMapping.DefaultBuilderOptions options = DocnoMapping.BuilderUtils.parseDefaultOptions(args);
-    if ( options == null) {
+    if (options == null) {
       return -1;
     }
 
     // Temp directory.
-    String tmpDir = "tmp-" + TrecDocnoMappingBuilder.class.getSimpleName() + "-" + random.nextInt(10000);
+    String tmpDir = "tmp-" + TrecDocnoMappingBuilder.class.getSimpleName() + "-" + RANDOM.nextInt(10000);
 
     LOG.info("Tool name: " + TrecDocnoMappingBuilder.class.getCanonicalName());
     LOG.info(" - input path: " + options.collection);

src/dist/edu/umd/cloud9/collection/wikipedia/BuildWikipediaForwardIndex.java

@@ -37,12 +37,6 @@
  * etc/hadoop-cluster.sh edu.umd.cloud9.collection.wikipedia.LookupWikipediaArticle \
  *  enwiki-20130503.findex.dat enwiki-20130503-docno.dat
  * </pre></blockquote>
- *
- * <p>
- * Note, you'll have to build a jar that contains the contents of bliki-core-3.0.15.jar and
- * commons-lang-2.5.jar, since -libjars won't work for this program (since it's not a MapReduce
- * job).
- * </p>
  * 
  * @author Jimmy Lin
  */

src/dist/edu/umd/cloud9/collection/wikipedia/LookupWikipediaArticle.java

@@ -77,7 +77,7 @@ public void loadMapping(Path p, FileSystem fs) throws IOException {
 
   /**
    * Creates a mappings file from the contents of a flat text file containing docid to docno
-   * mappings. This method is used by {@link BuildWikipediaDocnoMapping} internally.
+   * mappings. This method is used by {@link WikipediaDocnoMappingBuilder} internally.
    *
    * @param inputFile flat text file containing docid to docno mappings
    * @param outputFile output mappings file
@@ -133,7 +133,7 @@ static public int[] readDocnoMappingData(Path p, FileSystem fs) throws IOExcepti
 
   @Override
   public Builder getBuilder() {
-    throw new UnsupportedOperationException();
+    return new WikipediaDocnoMappingBuilder();
   }
 
   /**