LUCENE-3902: add javadoc

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1334769 13f79535-47bb-0310-9956-ffa450edef68

lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/DocMaker.java

@@ -90,6 +90,10 @@ public class DocMaker implements Closeable {
   private Random r;
   private int updateDocIDLimit;
 
+  /**
+   * Document state, supports reuse of field instances
+   * across documents (see <code>reuseFields</code> parameter).
+   */
   protected static class DocState {
     
     private final Map<String,Field> fields;

lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/Entities.java

@@ -20,6 +20,9 @@ package org.apache.lucene.benchmark.byTask.feeds.demohtml;
 import java.util.HashMap;
 import java.util.Map;
 
+/**
+ * Utility class for encoding and decoding HTML entities.
+ */
 public class Entities {
   static final Map<String,String> decoder = new HashMap<String,String>(300);
   static final String[]  encoder = new String[0x100];

lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/HTMLParser.java

@@ -5,6 +5,9 @@ import java.io.*;
 import java.util.Locale;
 import java.util.Properties;
 
+/**
+ * Basic html parser (for demo/testing purposes only!)
+ */
 public class HTMLParser implements HTMLParserConstants {
   public static int SUMMARY_LENGTH = 200;
 

lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/HTMLParser.jj

@@ -32,6 +32,9 @@ import java.io.*;
 import java.util.Locale;
 import java.util.Properties;
 
+/**
+ * Basic html parser (for demo/testing purposes only!)
+ */
 public class HTMLParser {
   public static int SUMMARY_LENGTH = 200;
 

lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/Tags.java

@@ -17,19 +17,22 @@ package org.apache.lucene.benchmark.byTask.feeds.demohtml;
  * limitations under the License.
  */
 
-import java.util.Collections;
 import java.util.HashSet;
 import java.util.Set;
 
 
+/**
+ * Utility class storing set of commonly-used html tags.
+ */
 public final class Tags {
 
   /**
    * contains all tags for which whitespaces have to be inserted for proper tokenization
    */
-  public static final Set<String> WS_ELEMS = Collections.synchronizedSet(new HashSet<String>());
+  public static final Set<String> WS_ELEMS;
 
   static{
+    WS_ELEMS = new HashSet<String>();
     WS_ELEMS.add("<hr");
     WS_ELEMS.add("<hr/");  // note that "<hr />" does not need to be listed explicitly
     WS_ELEMS.add("<br");

lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/BenchmarkHighlighter.java

@@ -21,6 +21,9 @@ import org.apache.lucene.analysis.Analyzer;
 import org.apache.lucene.document.Document;
 import org.apache.lucene.index.IndexReader;
 
+/**
+ * Abstract class for benchmarking highlighting performance
+ */
 public abstract class BenchmarkHighlighter {
   public abstract int doHighlight( IndexReader reader, int doc, String field,
       Document document, Analyzer analyzer, String text ) throws Exception ;

lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/NewCollationAnalyzerTask.java

@@ -36,6 +36,13 @@ import org.apache.lucene.util.Version;
  * </p>
  */
 public class NewCollationAnalyzerTask extends PerfTask {
+  /**
+   * Different Collation implementations: currently 
+   * limited to what is provided in the JDK and ICU.
+   * 
+   * @see <a href="http://site.icu-project.org/charts/collation-icu4j-sun">
+   *      Comparison of implementations</a>
+   */
   public enum Implementation { 
     JDK("org.apache.lucene.collation.CollationKeyAnalyzer", 
         "java.text.Collator"),

lucene/build.xml

@@ -201,16 +201,15 @@
       <check-missing-javadocs dir="build/docs/analyzers-common" level="class"/>
       <check-missing-javadocs dir="build/docs/analyzers-icu" level="class"/>
       <check-missing-javadocs dir="build/docs/analyzers-kuromoji" level="class"/>
-      <check-missing-javadocs dir="build/docs/analyzers-kuromoji" level="class"/>
       <check-missing-javadocs dir="build/docs/analyzers-morfologik" level="class"/>
       <check-missing-javadocs dir="build/docs/analyzers-phonetic" level="class"/>
       <check-missing-javadocs dir="build/docs/analyzers-smartcn" level="class"/>
       <check-missing-javadocs dir="build/docs/analyzers-stempel" level="class"/>
       <check-missing-javadocs dir="build/docs/analyzers-uima" level="class"/>
-      <!-- benchmark: problems -->
+      <check-missing-javadocs dir="build/docs/benchmark" level="class"/>
       <!-- core: problems -->
       <check-missing-javadocs dir="build/docs/demo" level="class"/>
-      <!-- facet: problems -->
+      <check-missing-javadocs dir="build/docs/facet" level="class"/>
       <!-- grouping: problems -->
       <!-- highlighter: problems -->
       <check-missing-javadocs dir="build/docs/join" level="class"/>
@@ -218,7 +217,7 @@
       <check-missing-javadocs dir="build/docs/misc" level="class"/>
       <!-- queries: problems -->
       <!-- queryparser: problems -->
-      <!-- sandbox: problems -->
+      <check-missing-javadocs dir="build/docs/sandbox" level="class"/>
       <!-- spatial: problems -->
       <check-missing-javadocs dir="build/docs/suggest" level="class"/>
       <!-- test-framework: problems -->

lucene/facet/src/java/org/apache/lucene/facet/index/FacetsPayloadProcessorProvider.java

@@ -9,6 +9,7 @@ import java.util.Map;
 
 import org.apache.lucene.index.AtomicReader;
 import org.apache.lucene.index.PayloadProcessorProvider;
+import org.apache.lucene.index.PayloadProcessorProvider.ReaderPayloadProcessor; // javadocs
 import org.apache.lucene.index.SegmentReader;
 import org.apache.lucene.index.Term;
 import org.apache.lucene.store.Directory;
@@ -121,6 +122,10 @@ public class FacetsPayloadProcessorProvider extends PayloadProcessorProvider {
     return null;
   }
   
+  /**
+   * {@link ReaderPayloadProcessor} that processes 
+   * facet ordinals according to the passed in {@link FacetIndexingParams}.
+   */
   public static class FacetsDirPayloadProcessor extends ReaderPayloadProcessor {
     
     private final Map<Term, CategoryListParams> termMap = new HashMap<Term, CategoryListParams>(1);

lucene/facet/src/java/org/apache/lucene/facet/taxonomy/writercache/lru/LruTaxonomyWriterCache.java

@@ -27,6 +27,11 @@ import org.apache.lucene.facet.taxonomy.writercache.TaxonomyWriterCache;
  */
 public class LruTaxonomyWriterCache implements TaxonomyWriterCache {
 
+  /**
+   * Determines cache type.
+   * For guaranteed correctness - not relying on no-collisions in the hash
+   * function, LRU_STRING should be used.
+   */
   public enum LRUType { LRU_HASHED, LRU_STRING }
 
   private NameIntCacheLRU cache;

lucene/sandbox/src/java/org/apache/lucene/sandbox/queries/DuplicateFilter.java

@@ -26,6 +26,15 @@ import org.apache.lucene.util.FixedBitSet;
 
 import java.io.IOException;
 
+/**
+ * Filter to remove duplicate values from search results.
+ * <p>
+ * WARNING: for this to work correctly, you may have to wrap
+ * your reader as it cannot current deduplicate across different
+ * index segments.
+ * 
+ * @see SlowCompositeReaderWrapper
+ */
 public class DuplicateFilter extends Filter {
   // TODO: make duplicate filter aware of ReaderContext such that we can
   // filter duplicates across segments
@@ -45,7 +54,7 @@ public class DuplicateFilter extends Filter {
    * for documents that contain the given field and are identified as none-duplicates.
    * <p/>
    * "Fast" processing sets all bits to true then unsets all duplicate docs found for the
-   * given field. This approach avoids the need to read TermDocs for terms that are seen
+   * given field. This approach avoids the need to read DocsEnum for terms that are seen
    * to have a document frequency of exactly "1" (i.e. no duplicates). While a potentially
    * faster approach , the downside is that bitsets produced will include bits set for
    * documents that do not actually contain the field given.