LUCENE-3902: add javadocs

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1332791 13f79535-47bb-0310-9956-ffa450edef68

lucene/build.xml

@@ -209,18 +209,18 @@
       <check-missing-javadocs dir="build/docs/analyzers-uima" level="class"/>
       <!-- benchmark: problems -->
       <!-- core: problems -->
-      <!-- demo: problems -->
+      <check-missing-javadocs dir="build/docs/demo" level="class"/>
       <!-- facet: problems -->
       <!-- grouping: problems -->
       <!-- highlighter: problems -->
       <check-missing-javadocs dir="build/docs/join" level="class"/>
       <check-missing-javadocs dir="build/docs/memory" level="class"/>
-      <!-- misc: problems -->
+      <check-missing-javadocs dir="build/docs/misc" level="class"/>
       <!-- queries: problems -->
       <!-- queryparser: problems -->
       <!-- sandbox: problems -->
       <!-- spatial: problems -->
-      <!-- suggest: problems -->
+      <check-missing-javadocs dir="build/docs/suggest" level="class"/>
       <!-- test-framework: problems -->
     </sequential>
   </target>

lucene/core/src/java/org/apache/lucene/codecs/FieldsConsumer.java

@@ -24,12 +24,23 @@ import org.apache.lucene.index.FieldInfo;
 import org.apache.lucene.index.Fields;
 import org.apache.lucene.index.FieldsEnum;
 import org.apache.lucene.index.MergeState;
+import org.apache.lucene.index.SegmentWriteState; // javadocs
 import org.apache.lucene.index.Terms;
 
-/** Abstract API that consumes terms, doc, freq, prox, offset and
- *  payloads postings.  Concrete implementations of this
- *  actually do "something" with the postings (write it into
- *  the index in a specific format).
+/** 
+ * Abstract API that consumes terms, doc, freq, prox, offset and
+ * payloads postings.  Concrete implementations of this
+ * actually do "something" with the postings (write it into
+ * the index in a specific format).
+ * <p>
+ * The lifecycle is:
+ * <ol>
+ *   <li>FieldsConsumer is created by 
+ *       {@link PostingsFormat#fieldsConsumer(SegmentWriteState)}.
+ *   <li>For each field, {@link #addField(FieldInfo)} is called,
+ *       returning a {@link TermsConsumer} for the field.
+ *   <li>After all fields are added, the consumer is {@link #close}d.
+ * </ol>
  *
  * @lucene.experimental
  */

lucene/core/src/java/org/apache/lucene/codecs/PostingsConsumer.java

@@ -28,19 +28,29 @@ import org.apache.lucene.util.BytesRef;
 import org.apache.lucene.util.FixedBitSet;
 
 /**
+ * Abstract API that consumes postings for an individual term.
+ * <p>
+ * The lifecycle is:
+ * <ol>
+ *    <li>PostingsConsumer is returned for each term by
+ *        {@link TermsConsumer#startTerm(BytesRef)}. 
+ *    <li>{@link #startDoc(int, int)} is called for each
+ *        document where the term occurs, specifying id 
+ *        and term frequency for that document.
+ *    <li>If positions are enabled for the field, then
+ *        {@link #addPosition(int, BytesRef, int, int)}
+ *        will be called for each occurrence in the 
+ *        document.
+ *    <li>{@link #finishDoc()} is called when the producer
+ *        is done adding positions to the document.
+ * </ol>
+ * 
  * @lucene.experimental
  */
-
 public abstract class PostingsConsumer {
 
   /** Adds a new doc in this term. */
-  public abstract void startDoc(int docID, int termDocFreq) throws IOException;
-
-  public static class PostingsMergeState {
-    DocsEnum docsEnum;
-    int[] docMap;
-    int docBase;
-  }
+  public abstract void startDoc(int docID, int freq) throws IOException;
 
   /** Add a new position & payload, and start/end offset.  A
    *  null payload means no payload; a non-null payload with

lucene/core/src/java/org/apache/lucene/codecs/PostingsWriterBase.java

@@ -24,9 +24,17 @@ import org.apache.lucene.store.IndexOutput;
 import org.apache.lucene.index.FieldInfo;
 
 /**
+ * Extension of {@link PostingsConsumer} to support pluggable term dictionaries.
+ * <p>
+ * This class contains additional hooks to interact with the provided
+ * term dictionaries such as {@link BlockTreeTermsWriter} and 
+ * {@link BlockTermsWriter}. If you want to re-use one of these existing
+ * implementations and are only interested in customizing the format of
+ * the postings list, extend this class instead.
+ * 
+ * @see PostingsReaderBase
  * @lucene.experimental
  */
-
 // TODO: find a better name; this defines the API that the
 // terms dict impls use to talk to a postings impl.
 // TermsDict + PostingsReader/WriterBase == PostingsConsumer/Producer

lucene/core/src/java/org/apache/lucene/codecs/TermsConsumer.java

@@ -20,6 +20,7 @@ package org.apache.lucene.codecs;
 import java.io.IOException;
 import java.util.Comparator;
 
+import org.apache.lucene.index.FieldInfo; // javadocs
 import org.apache.lucene.index.FieldInfo.IndexOptions;
 import org.apache.lucene.index.MergeState;
 import org.apache.lucene.index.TermsEnum;
@@ -30,9 +31,25 @@ import org.apache.lucene.util.BytesRef;
 import org.apache.lucene.util.FixedBitSet;
 
 /**
+ * Abstract API that consumes terms for an individual field.
+ * <p>
+ * The lifecycle is:
+ * <ol>
+ *   <li>TermsConsumer is returned for each field 
+ *       by {@link FieldsConsumer#addField(FieldInfo)}.
+ *   <li>TermsConsumer returns a {@link PostingsConsumer} for
+ *       each term in {@link #startTerm(BytesRef)}.
+ *   <li>When the producer (e.g. IndexWriter)
+ *       is done adding documents for the term, it calls 
+ *       {@link #finishTerm(BytesRef, TermStats)}, passing in
+ *       the accumulated term statistics.
+ *   <li>Producer calls {@link #finish(long, long, int)} with
+ *       the accumulated collection statistics when it is finished
+ *       adding terms to the field.
+ * </ol>
+ * 
  * @lucene.experimental
  */
-
 public abstract class TermsConsumer {
 
   /** Starts a new term in this field; this may be called
@@ -50,11 +67,11 @@ public abstract class TermsConsumer {
    *  before feeding to this API. */
   public abstract Comparator<BytesRef> getComparator() throws IOException;
 
-  /** Default merge impl */
   private MappingMultiDocsEnum docsEnum;
   private MappingMultiDocsEnum docsAndFreqsEnum;
   private MappingMultiDocsAndPositionsEnum postingsEnum;
 
+  /** Default merge impl */
   public void merge(MergeState mergeState, TermsEnum termsEnum) throws IOException {
 
     BytesRef term;

lucene/core/src/java/org/apache/lucene/codecs/TermsIndexReaderBase.java

@@ -30,9 +30,9 @@ import java.io.Closeable;
 //     frequent indexing
 
 /**
- * TermsDictReader interacts with an instance of this class
+ * {@link BlockTermsReader} interacts with an instance of this class
  * to manage its terms index.  The writer must accept
- * indexed terms (many pairs of CharSequence text + long
+ * indexed terms (many pairs of BytesRef text + long
  * fileOffset), and then this reader must be able to
  * retrieve the nearest index term to a provided term
  * text. 
@@ -48,13 +48,15 @@ public abstract class TermsIndexReaderBase implements Closeable {
 
   public abstract int getDivisor();
 
-  // Similar to TermsEnum, except, the only "metadata" it
-  // reports for a given indexed term is the long fileOffset
-  // into the main terms dict (_X.tis) file:
+  /** 
+   * Similar to TermsEnum, except, the only "metadata" it
+   * reports for a given indexed term is the long fileOffset
+   * into the main terms dictionary file:
+   */
   public static abstract class FieldIndexEnum {
 
     /** Seeks to "largest" indexed term that's <=
-     *  term; retruns file pointer index (into the main
+     *  term; returns file pointer index (into the main
      *  terms index file) for that term */
     public abstract long seek(BytesRef term) throws IOException;
 
@@ -63,8 +65,10 @@ public abstract class TermsIndexReaderBase implements Closeable {
 
     public abstract BytesRef term();
 
-    // Only impl'd if supportsOrd() returns true!
+    /** Only implemented if {@link TermsIndexReaderBase#supportsOrd()} returns true. */
     public abstract long seek(long ord) throws IOException;
+    
+    /** Only implemented if {@link TermsIndexReaderBase#supportsOrd()} returns true. */
     public abstract long ord();
   }
 }

lucene/core/src/java/org/apache/lucene/codecs/TermsIndexWriterBase.java

@@ -23,9 +23,18 @@ import org.apache.lucene.util.BytesRef;
 import java.io.Closeable;
 import java.io.IOException;
 
-/** @lucene.experimental */
+/** 
+ * Base class for terms index implementations to plug
+ * into {@link BlockTermsWriter}.
+ * 
+ * @see TermsIndexReaderBase
+ * @lucene.experimental 
+ */
 public abstract class TermsIndexWriterBase implements Closeable {
 
+  /**
+   * Terms index API for a single field.
+   */
   public abstract class FieldWriter {
     public abstract boolean checkIndexTerm(BytesRef text, TermStats stats) throws IOException;
     public abstract void add(BytesRef text, TermStats stats, long termsFilePointer) throws IOException;

lucene/core/src/java/org/apache/lucene/codecs/intblock/FixedIntBlockIndexInput.java

@@ -66,6 +66,11 @@ public abstract class FixedIntBlockIndexInput extends IntIndexInput {
 
   protected abstract BlockReader getBlockReader(IndexInput in, int[] buffer) throws IOException;
 
+  /**
+   * Interface for fixed-size block decoders.
+   * <p>
+   * Implementations should decode into the buffer in {@link #readBlock}.
+   */
   public interface BlockReader {
     public void readBlock() throws IOException;
   }

lucene/core/src/java/org/apache/lucene/codecs/intblock/VariableIntBlockIndexInput.java

@@ -68,6 +68,11 @@ public abstract class VariableIntBlockIndexInput extends IntIndexInput {
 
   protected abstract BlockReader getBlockReader(IndexInput in, int[] buffer) throws IOException;
 
+  /**
+   * Interface for variable-size block decoders.
+   * <p>
+   * Implementations should decode into the buffer in {@link #readBlock}.
+   */
   public interface BlockReader {
     public int readBlock() throws IOException;
     public void seek(long pos) throws IOException;

lucene/core/src/java/org/apache/lucene/codecs/simpletext/SimpleTextDocValuesConsumer.java

@@ -31,6 +31,10 @@ import org.apache.lucene.util.BytesRefHash;
 import org.apache.lucene.util.IOUtils;
 
 /**
+ * Writes plain-text DocValues.
+ * <p>
+ * <b><font color="red">FOR RECREATIONAL USE ONLY</font></B>
+ * 
  * @lucene.experimental
  */
 public class SimpleTextDocValuesConsumer extends DocValuesConsumer {

lucene/core/src/java/org/apache/lucene/codecs/simpletext/SimpleTextDocValuesFormat.java

@@ -26,7 +26,12 @@ import org.apache.lucene.index.PerDocWriteState;
 import org.apache.lucene.index.SegmentInfo;
 import org.apache.lucene.index.SegmentReadState;
 import org.apache.lucene.util.BytesRef;
+
 /**
+ * Plain-text DocValues format.
+ * <p>
+ * <b><font color="red">FOR RECREATIONAL USE ONLY</font></B>
+ * 
  * @lucene.experimental
  */
 public class SimpleTextDocValuesFormat extends DocValuesFormat {

lucene/core/src/java/org/apache/lucene/codecs/simpletext/SimpleTextNormsFormat.java

@@ -38,7 +38,7 @@ import org.apache.lucene.util.BytesRef;
 import org.apache.lucene.util.IOUtils;
 
 /**
- * plain-text norms format
+ * plain-text norms format.
  * <p>
  * <b><font color="red">FOR RECREATIONAL USE ONLY</font></B>
  * 
@@ -63,6 +63,13 @@ public class SimpleTextNormsFormat extends NormsFormat {
     SimpleTextNormsPerDocConsumer.files(info, files);
   }
   
+  /**
+   * Reads plain-text norms.
+   * <p>
+   * <b><font color="red">FOR RECREATIONAL USE ONLY</font></B>
+   * 
+   * @lucene.experimental
+   */
   public static class SimpleTextNormsPerDocProducer extends
       SimpleTextPerDocProducer {
     
@@ -88,6 +95,13 @@ public class SimpleTextNormsFormat extends NormsFormat {
     
   }
   
+  /**
+   * Writes plain-text norms.
+   * <p>
+   * <b><font color="red">FOR RECREATIONAL USE ONLY</font></B>
+   * 
+   * @lucene.experimental
+   */
   public static class SimpleTextNormsPerDocConsumer extends
       SimpleTextPerDocConsumer {
     

lucene/core/src/java/org/apache/lucene/codecs/simpletext/SimpleTextPerDocProducer.java

@@ -47,6 +47,10 @@ import org.apache.lucene.util.StringHelper;
 import org.apache.lucene.util.packed.PackedInts.Reader;
 
 /**
+ * Reads plain-text DocValues.
+ * <p>
+ * <b><font color="red">FOR RECREATIONAL USE ONLY</font></B>
+ * 
  * @lucene.experimental
  */
 public class SimpleTextPerDocProducer extends PerDocProducerBase {

lucene/demo/src/java/org/apache/lucene/demo/xmlparser/FormBasedXmlQueryDemo.java

@@ -51,6 +51,12 @@ import org.apache.lucene.search.TopDocs;
 import org.apache.lucene.store.RAMDirectory;
 import org.apache.lucene.util.Version;
 
+/**
+ * Example servlet that uses the XML queryparser.
+ * <p>
+ * NOTE: you must provide CSV data in <code>/WEB-INF/data.tsv</code>
+ * for the demo to work!
+ */
 public class FormBasedXmlQueryDemo extends HttpServlet {
 
   private QueryTemplateManager queryTemplateManager;

lucene/misc/src/java/org/apache/lucene/store/NativePosixUtil.java

@@ -21,6 +21,10 @@ import java.io.IOException;
 import java.io.FileDescriptor;
 import java.nio.ByteBuffer;
 
+/**
+ * Provides JNI access to native methods such as madvise() for
+ * {@link NativeUnixDirectory}
+ */
 public final class NativePosixUtil {
   public final static int NORMAL = 0;
   public final static int SEQUENTIAL = 1;

lucene/misc/src/java/org/apache/lucene/store/WindowsDirectory.java

@@ -75,7 +75,7 @@ public class WindowsDirectory extends FSDirectory {
     return new WindowsIndexInput(new File(getDirectory(), name), Math.max(BufferedIndexInput.bufferSize(context), DEFAULT_BUFFERSIZE));
   }
   
-  protected static class WindowsIndexInput extends BufferedIndexInput {
+  static class WindowsIndexInput extends BufferedIndexInput {
     private final long fd;
     private final long length;
     boolean isClone;

lucene/suggest/src/java/org/apache/lucene/search/suggest/jaspell/JaspellLookup.java

@@ -34,6 +34,12 @@ import org.apache.lucene.util.CharsRef;
 import org.apache.lucene.util.IOUtils;
 import org.apache.lucene.util.UnicodeUtil;
 
+/**
+ * Suggest implementation based on 
+ * <a href="http://jaspell.sourceforge.net/">JaSpell</a>.
+ * 
+ * @see JaspellTernarySearchTrie
+ */
 public class JaspellLookup extends Lookup {
   JaspellTernarySearchTrie trie = new JaspellTernarySearchTrie();
   private boolean usePrefix = true;

lucene/suggest/src/java/org/apache/lucene/search/suggest/tst/TSTAutocomplete.java

@@ -19,6 +19,11 @@ package org.apache.lucene.search.suggest.tst;
 
 import java.util.*;
 
+/**
+ * Ternary Search Trie implementation.
+ * 
+ * @see TernaryTreeNode
+ */
 public class TSTAutocomplete {
 
   /**

lucene/suggest/src/java/org/apache/lucene/search/suggest/tst/TSTLookup.java

@@ -33,6 +33,12 @@ import org.apache.lucene.util.CharsRef;
 import org.apache.lucene.util.IOUtils;
 import org.apache.lucene.util.UnicodeUtil;
 
+/**
+ * Suggest implementation based on a 
+ * <a href="http://en.wikipedia.org/wiki/Ternary_search_tree">Ternary Search Tree</a>
+ * 
+ * @see TSTAutocomplete
+ */
 public class TSTLookup extends Lookup {
   TernaryTreeNode root = new TernaryTreeNode();
   TSTAutocomplete autocomplete = new TSTAutocomplete();