You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by rm...@apache.org on 2015/02/07 11:10:37 UTC
svn commit: r1658040 [2/4] - in /lucene/dev/trunk/lucene: ./
analysis/common/src/java/org/apache/lucene/analysis/bg/
analysis/common/src/java/org/apache/lucene/analysis/charfilter/
analysis/common/src/java/org/apache/lucene/analysis/cjk/ analysis/commo...
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/ReadTask.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/ReadTask.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/ReadTask.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/ReadTask.java Sat Feb 7 10:10:34 2015
@@ -51,7 +51,6 @@ import org.apache.lucene.util.Bits;
* Read index (abstract) task.
* Sub classes implement withSearch(), withWarm(), withTraverse() and withRetrieve()
* methods to configure the actual action.
- * <p/>
* <p>Note: All ReadTasks reuse the reader if it is already open.
* Otherwise a reader is opened at start and closed at the end.
* <p>
@@ -238,7 +237,7 @@ public abstract class ReadTask extends P
/**
* Specify the number of hits to traverse. Tasks should override this if they want to restrict the number
* of hits that are traversed when {@link #withTraverse()} is true. Must be greater than 0.
- * <p/>
+ * <p>
* Read task calculates the traversal as: Math.min(hits.length(), traversalSize())
*
* @return Integer.MAX_VALUE
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/SearchTravTask.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/SearchTravTask.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/SearchTravTask.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/SearchTravTask.java Sat Feb 7 10:10:34 2015
@@ -25,7 +25,6 @@ import org.apache.lucene.benchmark.byTas
*
* <p>Note: This task reuses the reader if it is already open.
* Otherwise a reader is opened at start and closed at the end.
- * <p/>
*
* <p>Takes optional param: traversal size (otherwise all results are traversed).</p>
*
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/utils/Config.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/utils/Config.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/utils/Config.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/utils/Config.java Sat Feb 7 10:10:34 2015
@@ -30,11 +30,11 @@ import java.util.StringTokenizer;
/**
* Perf run configuration properties.
- * <p/>
+ * <p>
* Numeric property containing ":", e.g. "10:100:5" is interpreted
* as array of numeric values. It is extracted once, on first use, and
* maintain a round number to return the appropriate value.
- * <p/>
+ * <p>
* The config property "work.dir" tells where is the root of
* docs data dirs and indexes dirs. It is set to either of: <ul>
* <li>value supplied for it in the alg file;</li>
Modified: lucene/dev/trunk/lucene/classification/src/java/org/apache/lucene/classification/CachingNaiveBayesClassifier.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/classification/src/java/org/apache/lucene/classification/CachingNaiveBayesClassifier.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/classification/src/java/org/apache/lucene/classification/CachingNaiveBayesClassifier.java (original)
+++ lucene/dev/trunk/lucene/classification/src/java/org/apache/lucene/classification/CachingNaiveBayesClassifier.java Sat Feb 7 10:10:34 2015
@@ -42,7 +42,7 @@ import org.apache.lucene.util.BytesRef;
/**
* A simplistic Lucene based NaiveBayes classifier, with caching feature, see
* <code>http://en.wikipedia.org/wiki/Naive_Bayes_classifier</code>
- * <p/>
+ * <p>
* This is NOT an online classifier.
*
* @lucene.experimental
Modified: lucene/dev/trunk/lucene/codecs/src/java/org/apache/lucene/codecs/bloom/FuzzySet.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/codecs/src/java/org/apache/lucene/codecs/bloom/FuzzySet.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/codecs/src/java/org/apache/lucene/codecs/bloom/FuzzySet.java (original)
+++ lucene/dev/trunk/lucene/codecs/src/java/org/apache/lucene/codecs/bloom/FuzzySet.java Sat Feb 7 10:10:34 2015
@@ -38,7 +38,6 @@ import org.apache.lucene.util.RamUsageEs
* </p>
* Another application of the set is that it can be used to perform fuzzy counting because
* it can estimate reasonably accurately how many unique values are contained in the set.
- * </p>
* <p>This class is NOT threadsafe.</p>
* <p>
* Internally a Bitset is used to record values and once a client has finished recording
Modified: lucene/dev/trunk/lucene/codecs/src/java/org/apache/lucene/codecs/memory/FSTOrdTermsWriter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/codecs/src/java/org/apache/lucene/codecs/memory/FSTOrdTermsWriter.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/codecs/src/java/org/apache/lucene/codecs/memory/FSTOrdTermsWriter.java (original)
+++ lucene/dev/trunk/lucene/codecs/src/java/org/apache/lucene/codecs/memory/FSTOrdTermsWriter.java Sat Feb 7 10:10:34 2015
@@ -63,9 +63,8 @@ import org.apache.lucene.util.fst.Util;
* <li><tt>.tix</tt>: <a href="#Termindex">Term Index</a></li>
* <li><tt>.tbk</tt>: <a href="#Termblock">Term Block</a></li>
* </ul>
- * </p>
*
- * <a name="Termindex" id="Termindex"></a>
+ * <a name="Termindex"></a>
* <h3>Term Index</h3>
* <p>
* The .tix contains a list of FSTs, one for each field.
@@ -87,7 +86,7 @@ import org.apache.lucene.util.fst.Util;
* </li>
* </ul>
*
- * <a name="Termblock" id="Termblock"></a>
+ * <a name="Termblock"></a>
* <h3>Term Block</h3>
* <p>
* The .tbk contains all the statistics and metadata for terms, along with field summary (e.g.
@@ -98,7 +97,6 @@ import org.apache.lucene.util.fst.Util;
* <li>metadata bytes block: encodes other parts of metadata; </li>
* <li>skip block: contains skip data, to speed up metadata seeking and decoding</li>
* </ul>
- * </p>
*
* <p>File Format:</p>
* <ul>
Modified: lucene/dev/trunk/lucene/codecs/src/java/org/apache/lucene/codecs/memory/FSTTermsWriter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/codecs/src/java/org/apache/lucene/codecs/memory/FSTTermsWriter.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/codecs/src/java/org/apache/lucene/codecs/memory/FSTTermsWriter.java (original)
+++ lucene/dev/trunk/lucene/codecs/src/java/org/apache/lucene/codecs/memory/FSTTermsWriter.java Sat Feb 7 10:10:34 2015
@@ -61,7 +61,7 @@ import org.apache.lucene.util.fst.Util;
* </ul>
* <p>
*
- * <a name="Termdictionary" id="Termdictionary"></a>
+ * <a name="Termdictionary"></a>
* <h3>Term Dictionary</h3>
* <p>
* The .tst contains a list of FSTs, one for each field.
@@ -80,7 +80,6 @@ import org.apache.lucene.util.fst.Util;
* Generic byte array: Used to store non-monotonic metadata.
* </li>
* </ul>
- * </p>
*
* File format:
* <ul>
Modified: lucene/dev/trunk/lucene/common-build.xml
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/common-build.xml?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/common-build.xml (original)
+++ lucene/dev/trunk/lucene/common-build.xml Sat Feb 7 10:10:34 2015
@@ -164,7 +164,7 @@
<property name="javac.debug" value="on"/>
<property name="javac.source" value="1.8"/>
<property name="javac.target" value="1.8"/>
- <property name="javac.args" value="-Xlint -Xlint:-deprecation -Xlint:-serial -Xlint:-options -Xdoclint:all/protected -Xdoclint:-html -Xdoclint:-missing"/>
+ <property name="javac.args" value="-Xlint -Xlint:-deprecation -Xlint:-serial -Xlint:-options -Xdoclint:all/protected -Xdoclint:-missing"/>
<property name="javadoc.link" value="http://download.oracle.com/javase/8/docs/api/"/>
<property name="javadoc.link.junit" value="http://junit.sourceforge.net/javadoc/"/>
<property name="javadoc.packagelist.dir" location="${common.dir}/tools/javadoc"/>
@@ -373,7 +373,7 @@
</target>
<!-- for now enable only some doclint: -->
- <property name="javadoc.args" value="-Xdoclint:all -Xdoclint:-html -Xdoclint:-missing"/>
+ <property name="javadoc.args" value="-Xdoclint:all -Xdoclint:-missing"/>
<!-- Import custom ANT tasks. -->
<import file="${common.dir}/tools/custom-tasks.xml" />
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/analysis/CachingTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/analysis/CachingTokenFilter.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/analysis/CachingTokenFilter.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/analysis/CachingTokenFilter.java Sat Feb 7 10:10:34 2015
@@ -29,7 +29,7 @@ import org.apache.lucene.util.AttributeS
* are intended to be consumed more than once. It caches
* all token attribute states locally in a List when the first call to
* {@link #incrementToken()} is called. Subsequent calls will used the cache.
- * <p/>
+ * <p>
* <em>Important:</em> Like any proper TokenFilter, {@link #reset()} propagates
* to the input, although only before {@link #incrementToken()} is called the
* first time. Prior to Lucene 5, it was never propagated.
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/analysis/Token.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/analysis/Token.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/analysis/Token.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/analysis/Token.java Sat Feb 7 10:10:34 2015
@@ -34,7 +34,7 @@ import org.apache.lucene.util.BytesRef;
<p>
The start and end offsets permit applications to re-associate a token with
its source text, e.g., to display highlighted query terms in a document
- browser, or to show matching text fragments in a <abbr title="KeyWord In Context">KWIC</abbr>
+ browser, or to show matching text fragments in a <a href="http://en.wikipedia.org/wiki/Key_Word_in_Context">KWIC</a>
display, etc.
<p>
The type is a string, assigned by a lexical analyzer
@@ -61,12 +61,10 @@ import org.apache.lucene.util.BytesRef;
<li>The startOffset and endOffset represent the start and offset in the source text, so be careful in adjusting them.</li>
<li>When caching a reusable token, clone it. When injecting a cached token into a stream that can be reset, clone it again.</li>
</ul>
- </p>
<p>
<b>Please note:</b> With Lucene 3.1, the <code>{@linkplain #toString toString()}</code> method had to be changed to match the
{@link CharSequence} interface introduced by the interface {@link org.apache.lucene.analysis.tokenattributes.CharTermAttribute}.
This method now only prints the term text, no additional information anymore.
- </p>
@deprecated This class is outdated and no longer used since Lucene 2.9. Nuke it finally!
*/
@Deprecated
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/analysis/TokenStream.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/analysis/TokenStream.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/analysis/TokenStream.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/analysis/TokenStream.java Sat Feb 7 10:10:34 2015
@@ -161,7 +161,7 @@ public abstract class TokenStream extend
* consumed, after {@link #incrementToken()} returned <code>false</code>
* (using the new <code>TokenStream</code> API). Streams implementing the old API
* should upgrade to use this feature.
- * <p/>
+ * <p>
* This method can be used to perform any end-of-stream operations, such as
* setting the final offset of a stream. The final offset of a stream might
* differ from the offset of the last token eg in case one or more whitespaces
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/analysis/package-info.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/analysis/package-info.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/analysis/package-info.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/analysis/package-info.java Sat Feb 7 10:10:34 2015
@@ -21,13 +21,11 @@
* <h2>Parsing? Tokenization? Analysis!</h2>
* <p>
* Lucene, an indexing and search library, accepts only plain text input.
- * <p>
* <h2>Parsing</h2>
* <p>
* Applications that build their search capabilities upon Lucene may support documents in various formats – HTML, XML, PDF, Word – just to name a few.
* Lucene does not care about the <i>Parsing</i> of these and other document formats, and it is the responsibility of the
* application using Lucene to use an appropriate <i>Parser</i> to convert the original format into plain text before passing that plain text to Lucene.
- * <p>
* <h2>Tokenization</h2>
* <p>
* Plain text passed to Lucene for indexing goes through a process generally called tokenization. Tokenization is the process
@@ -67,8 +65,7 @@
* Adding in synonyms at the same token position as the current word can mean better
* matching when users search with words in the synonym set.
* </li>
- * </ul>
- * <p>
+ * </ul>
* <h2>Core Analysis</h2>
* <p>
* The analysis package provides the mechanism to convert Strings and Readers
@@ -249,7 +246,6 @@
* This might sometimes require a modified analyzer – see the next section on how to do that.
* </li>
* </ol>
- * </p>
* <h2>Implementing your own Analyzer and Analysis Components</h2>
* <p>
* Creating your own Analyzer is straightforward. Your Analyzer should subclass {@link org.apache.lucene.analysis.Analyzer}. It can use
@@ -416,7 +412,7 @@
* This new attribute makes clear that "IBM" and "International Business Machines" start and end
* at the same positions.
* </p>
- * <a name="corrupt" />
+ * <a name="corrupt"></a>
* <h3>How to not write corrupt token streams</h3>
* <p>
* There are a few rules to observe when writing custom Tokenizers and TokenFilters:
@@ -586,7 +582,6 @@
* a chain of a TokenStream and multiple TokenFilters is used, then all TokenFilters in that chain share the Attributes
* with the TokenStream.
* </li>
- * <br>
* <li>
* Attribute instances are reused for all tokens of a document. Thus, a TokenStream/-Filter needs to update
* the appropriate Attribute(s) in incrementToken(). The consumer, commonly the Lucene indexer, consumes the data in the
@@ -594,13 +589,11 @@
* was reached. This means that in each call of incrementToken() a TokenStream/-Filter can safely overwrite the data in
* the Attribute instances.
* </li>
- * <br>
* <li>
* For performance reasons a TokenStream/-Filter should add/get Attributes during instantiation; i.e., create an attribute in the
* constructor and store references to it in an instance variable. Using an instance variable instead of calling addAttribute()/getAttribute()
* in incrementToken() will avoid attribute lookups for every token in the document.
* </li>
- * <br>
* <li>
* All methods in AttributeSource are idempotent, which means calling them multiple times always yields the same
* result. This is especially important to know for addAttribute(). The method takes the <b>type</b> (<code>Class</code>)
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/SegmentInfoFormat.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/SegmentInfoFormat.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/SegmentInfoFormat.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/SegmentInfoFormat.java Sat Feb 7 10:10:34 2015
@@ -26,8 +26,6 @@ import org.apache.lucene.store.IOContext
/**
* Expert: Controls the format of the
* {@link SegmentInfo} (segment metadata file).
- * <p>
- *
* @see SegmentInfo
* @lucene.experimental
*/
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/StoredFieldsWriter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/StoredFieldsWriter.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/StoredFieldsWriter.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/StoredFieldsWriter.java Sat Feb 7 10:10:34 2015
@@ -32,7 +32,6 @@ import org.apache.lucene.util.BytesRef;
/**
* Codec API for writing stored fields:
- * <p>
* <ol>
* <li>For every document, {@link #startDocument()} is called,
* informing the Codec that a new document has started.
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/TermVectorsWriter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/TermVectorsWriter.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/TermVectorsWriter.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/TermVectorsWriter.java Sat Feb 7 10:10:34 2015
@@ -36,7 +36,6 @@ import org.apache.lucene.util.BytesRefBu
/**
* Codec API for writing term vectors:
- * <p>
* <ol>
* <li>For every document, {@link #startDocument(int)} is called,
* informing the Codec how many fields will be written.
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/blocktree/BlockTreeTermsWriter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/blocktree/BlockTreeTermsWriter.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/blocktree/BlockTreeTermsWriter.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/blocktree/BlockTreeTermsWriter.java Sat Feb 7 10:10:34 2015
@@ -93,7 +93,7 @@ import org.apache.lucene.util.packed.Pac
* <li><tt>.tip</tt>: <a href="#Termindex">Term Index</a></li>
* </ul>
* <p>
- * <a name="Termdictionary" id="Termdictionary"></a>
+ * <a name="Termdictionary"></a>
* <h3>Term Dictionary</h3>
*
* <p>The .tim file contains the list of terms in each
@@ -152,7 +152,7 @@ import org.apache.lucene.util.packed.Pac
* <li>For inner nodes of the tree, every entry will steal one bit to mark whether it points
* to child nodes(sub-block). If so, the corresponding TermStats and TermMetaData are omitted </li>
* </ul>
- * <a name="Termindex" id="Termindex"></a>
+ * <a name="Termindex"></a>
* <h3>Term Index</h3>
* <p>The .tip file contains an index into the term dictionary, so that it can be
* accessed randomly. The index is also used to determine
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/compressing/CompressingStoredFieldsIndexWriter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/compressing/CompressingStoredFieldsIndexWriter.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/compressing/CompressingStoredFieldsIndexWriter.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/compressing/CompressingStoredFieldsIndexWriter.java Sat Feb 7 10:10:34 2015
@@ -37,8 +37,8 @@ import org.apache.lucene.util.packed.Pac
* 1024 chunks, this index computes the average number of bytes per
* chunk and for every chunk, only stores the difference between<ul>
* <li>${chunk number} * ${average length of a chunk}</li>
- * <li>and the actual start offset of the chunk</li></ul></p>
- * <p>Data is written as follows:</p>
+ * <li>and the actual start offset of the chunk</li></ul>
+ * <p>Data is written as follows:
* <ul>
* <li>PackedIntsVersion, <Block><sup>BlockCount</sup>, BlocksEndMarker</li>
* <li>PackedIntsVersion --> {@link PackedInts#VERSION_CURRENT} as a {@link DataOutput#writeVInt VInt}</li>
@@ -57,7 +57,7 @@ import org.apache.lucene.util.packed.Pac
* <li>StartPointerDeltas --> {@link PackedInts packed} array of BlockChunks elements of BitsPerStartPointerDelta bits each, representing the deltas from the average start pointer using <a href="https://developers.google.com/protocol-buffers/docs/encoding#types">ZigZag encoding</a></li>
* <li>Footer --> {@link CodecUtil#writeFooter CodecFooter}</li>
* </ul>
- * <p>Notes</p>
+ * <p>Notes
* <ul>
* <li>For any block, the doc base of the n-th chunk can be restored with
* <code>DocBase + AvgChunkDocs * n + DocBaseDeltas[n]</code>.</li>
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50DocValuesFormat.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50DocValuesFormat.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50DocValuesFormat.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50DocValuesFormat.java Sat Feb 7 10:10:34 2015
@@ -89,7 +89,7 @@ import org.apache.lucene.util.packed.Mon
* <li><tt>.dvm</tt>: DocValues metadata</li>
* </ol>
* <ol>
- * <li><a name="dvm" id="dvm"></a>
+ * <li><a name="dvm"></a>
* <p>The DocValues metadata or .dvm file.</p>
* <p>For DocValues field, this stores metadata, such as the offset into the
* DocValues data (.dvd)</p>
@@ -150,7 +150,7 @@ import org.apache.lucene.util.packed.Mon
* is written for the addresses.
* <p>MissingOffset points to a byte[] containing a bitset of all documents that had a value for the field.
* If it's -1, then there are no missing values. If it's -2, all values are missing.
- * <li><a name="dvd" id="dvd"></a>
+ * <li><a name="dvd"></a>
* <p>The DocValues data or .dvd file.</p>
* <p>For DocValues field, this stores the actual per-document data (the heavy-lifting)</p>
* <p>DocValues data (.dvd) --> Header,<NumericData | BinaryData | SortedData><sup>NumFields</sup>,Footer</p>
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50FieldInfosFormat.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50FieldInfosFormat.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50FieldInfosFormat.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50FieldInfosFormat.java Sat Feb 7 10:10:34 2015
@@ -40,10 +40,9 @@ import org.apache.lucene.store.IndexOutp
/**
* Lucene 5.0 Field Infos format.
- * <p>
- * <p>Field names are stored in the field info file, with suffix <tt>.fnm</tt>.</p>
+ * <p>Field names are stored in the field info file, with suffix <tt>.fnm</tt>.
* <p>FieldInfos (.fnm) --> Header,FieldsCount, <FieldName,FieldNumber,
- * FieldBits,DocValuesBits,DocValuesGen,Attributes> <sup>FieldsCount</sup>,Footer</p>
+ * FieldBits,DocValuesBits,DocValuesGen,Attributes> <sup>FieldsCount</sup>,Footer
* <p>Data types:
* <ul>
* <li>Header --> {@link CodecUtil#checkIndexHeader IndexHeader}</li>
@@ -55,7 +54,6 @@ import org.apache.lucene.store.IndexOutp
* <li>DocValuesGen --> {@link DataOutput#writeLong(long) Int64}</li>
* <li>Footer --> {@link CodecUtil#writeFooter CodecFooter}</li>
* </ul>
- * </p>
* Field Descriptions:
* <ul>
* <li>FieldsCount: the number of fields in this file.</li>
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50LiveDocsFormat.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50LiveDocsFormat.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50LiveDocsFormat.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50LiveDocsFormat.java Sat Feb 7 10:10:34 2015
@@ -36,12 +36,11 @@ import org.apache.lucene.util.MutableBit
/**
* Lucene 5.0 live docs format
- * <p>
* <p>The .liv file is optional, and only exists when a segment contains
- * deletions.</p>
+ * deletions.
* <p>Although per-segment, this file is maintained exterior to compound segment
- * files.</p>
- * <p>Deletions (.liv) --> IndexHeader,Generation,Bits</p>
+ * files.
+ * <p>Deletions (.liv) --> IndexHeader,Generation,Bits
* <ul>
* <li>SegmentHeader --> {@link CodecUtil#writeIndexHeader IndexHeader}</li>
* <li>Bits --> <{@link DataOutput#writeLong Int64}> <sup>LongCount</sup></li>
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50NormsFormat.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50NormsFormat.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50NormsFormat.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50NormsFormat.java Sat Feb 7 10:10:34 2015
@@ -35,7 +35,6 @@ import org.apache.lucene.util.packed.Pac
* Lucene 5.0 Score normalization format.
* <p>
* Encodes normalization values with these strategies:
- * <p>
* <ul>
* <li>Uncompressed: when values fit into a single byte and would require more than 4 bits
* per value, they are just encoded as an uncompressed byte array.
@@ -65,7 +64,7 @@ import org.apache.lucene.util.packed.Pac
* <li><tt>.nvm</tt>: Norms metadata</li>
* </ol>
* <ol>
- * <li><a name="nvm" id="nvm"></a>
+ * <li><a name="nvm"></a>
* <p>The Norms metadata or .nvm file.</p>
* <p>For each norms field, this stores metadata, such as the offset into the
* Norms data (.nvd)</p>
@@ -94,7 +93,7 @@ import org.apache.lucene.util.packed.Pac
* <li>6 --> patched table. Documents with very common values are written with a lookup table.
* Other values are written using a nested indirect.
* </ul>
- * <li><a name="nvd" id="nvd"></a>
+ * <li><a name="nvd"></a>
* <p>The Norms data or .nvd file.</p>
* <p>For each Norms field, this stores the actual per-document data (the heavy-lifting)</p>
* <p>Norms data (.nvd) --> Header,<Uncompressed | TableCompressed | DeltaCompressed | MonotonicCompressed ><sup>NumFields</sup>,Footer</p>
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50PostingsFormat.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50PostingsFormat.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50PostingsFormat.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50PostingsFormat.java Sat Feb 7 10:10:34 2015
@@ -95,7 +95,6 @@ import org.apache.lucene.util.packed.Pac
* this reduces disk pre-fetches.</p>
* </li>
* </ul>
- * </p>
*
* <p>
* Files and detailed format:
@@ -106,9 +105,8 @@ import org.apache.lucene.util.packed.Pac
* <li><tt>.pos</tt>: <a href="#Positions">Positions</a></li>
* <li><tt>.pay</tt>: <a href="#Payloads">Payloads and Offsets</a></li>
* </ul>
- * </p>
*
- * <a name="Termdictionary" id="Termdictionary"></a>
+ * <a name="Termdictionary"></a>
* <dl>
* <dd>
* <b>Term Dictionary</b>
@@ -118,11 +116,10 @@ import org.apache.lucene.util.packed.Pac
* and pointers to the frequencies, positions, payload and
* skip data in the .doc, .pos, and .pay files.
* See {@link BlockTreeTermsWriter} for more details on the format.
- * </p>
*
* <p>NOTE: The term dictionary can plug into different postings implementations:
* the postings writer/reader are actually responsible for encoding
- * and decoding the PostingsHeader and TermMetadata sections described here:</p>
+ * and decoding the PostingsHeader and TermMetadata sections described here:
*
* <ul>
* <li>PostingsHeader --> Header, PackedBlockSize</li>
@@ -133,7 +130,7 @@ import org.apache.lucene.util.packed.Pac
* <li>DocFPDelta, PosFPDelta, PayFPDelta, PosVIntBlockFPDelta, SkipFPDelta --> {@link DataOutput#writeVLong VLong}</li>
* <li>Footer --> {@link CodecUtil#writeFooter CodecFooter}</li>
* </ul>
- * <p>Notes:</p>
+ * <p>Notes:
* <ul>
* <li>Header is a {@link CodecUtil#writeIndexHeader IndexHeader} storing the version information
* for the postings.</li>
@@ -169,17 +166,17 @@ import org.apache.lucene.util.packed.Pac
* </dd>
* </dl>
*
- * <a name="Termindex" id="Termindex"></a>
+ * <a name="Termindex"></a>
* <dl>
* <dd>
* <b>Term Index</b>
* <p>The .tip file contains an index into the term dictionary, so that it can be
- * accessed randomly. See {@link BlockTreeTermsWriter} for more details on the format.</p>
+ * accessed randomly. See {@link BlockTreeTermsWriter} for more details on the format.
* </dd>
* </dl>
*
*
- * <a name="Frequencies" id="Frequencies"></a>
+ * <a name="Frequencies"></a>
* <dl>
* <dd>
* <b>Frequencies and Skip Data</b>
@@ -208,7 +205,7 @@ import org.apache.lucene.util.packed.Pac
* <li>SkipChildLevelPointer --> {@link DataOutput#writeVLong VLong}</li>
* <li>Footer --> {@link CodecUtil#writeFooter CodecFooter}</li>
* </ul>
- * <p>Notes:</p>
+ * <p>Notes:
* <ul>
* <li>PackedDocDeltaBlock is theoretically generated from two steps:
* <ol>
@@ -267,7 +264,7 @@ import org.apache.lucene.util.packed.Pac
* </dd>
* </dl>
*
- * <a name="Positions" id="Positions"></a>
+ * <a name="Positions"></a>
* <dl>
* <dd>
* <b>Positions</b>
@@ -286,7 +283,7 @@ import org.apache.lucene.util.packed.Pac
* <li>PayloadData --> {@link DataOutput#writeByte byte}<sup>PayLength</sup></li>
* <li>Footer --> {@link CodecUtil#writeFooter CodecFooter}</li>
* </ul>
- * <p>Notes:</p>
+ * <p>Notes:
* <ul>
* <li>TermPositions are order by term (terms are implicit, from the term dictionary), and position
* values for each term document pair are incremental, and ordered by document number.</li>
@@ -320,12 +317,12 @@ import org.apache.lucene.util.packed.Pac
* </dd>
* </dl>
*
- * <a name="Payloads" id="Payloads"></a>
+ * <a name="Payloads"></a>
* <dl>
* <dd>
* <b>Payloads and Offsets</b>
* <p>The .pay file will store payloads and offsets associated with certain term-document positions.
- * Some payloads and offsets will be separated out into .pos file, for performance reasons.</p>
+ * Some payloads and offsets will be separated out into .pos file, for performance reasons.
* <ul>
* <li>PayFile(.pay): --> Header, <TermPayloads, TermOffsets?> <sup>TermCount</sup>, Footer</li>
* <li>Header --> {@link CodecUtil#writeIndexHeader IndexHeader}</li>
@@ -336,7 +333,7 @@ import org.apache.lucene.util.packed.Pac
* <li>PayData --> {@link DataOutput#writeByte byte}<sup>SumPayLength</sup></li>
* <li>Footer --> {@link CodecUtil#writeFooter CodecFooter}</li>
* </ul>
- * <p>Notes:</p>
+ * <p>Notes:
* <ul>
* <li>The order of TermPayloads/TermOffsets will be the same as TermPositions, note that part of
* payload/offsets are stored in .pos.</li>
@@ -352,7 +349,6 @@ import org.apache.lucene.util.packed.Pac
* </ul>
* </dd>
* </dl>
- * </p>
*
* @lucene.experimental
*/
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50SegmentInfoFormat.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50SegmentInfoFormat.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50SegmentInfoFormat.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50SegmentInfoFormat.java Sat Feb 7 10:10:34 2015
@@ -43,9 +43,7 @@ import org.apache.lucene.util.Version;
* <ul>
* <li><tt>.si</tt>: Header, SegVersion, SegSize, IsCompoundFile, Diagnostics, Files, Attributes, Footer
* </ul>
- * </p>
* Data types:
- * <p>
* <ul>
* <li>Header --> {@link CodecUtil#writeIndexHeader IndexHeader}</li>
* <li>SegSize --> {@link DataOutput#writeInt Int32}</li>
@@ -55,9 +53,7 @@ import org.apache.lucene.util.Version;
* <li>IsCompoundFile --> {@link DataOutput#writeByte Int8}</li>
* <li>Footer --> {@link CodecUtil#writeFooter CodecFooter}</li>
* </ul>
- * </p>
* Field Descriptions:
- * <p>
* <ul>
* <li>SegVersion is the code version that created the segment.</li>
* <li>SegSize is the number of documents contained in the segment index.</li>
@@ -70,7 +66,6 @@ import org.apache.lucene.util.Version;
* addIndexes), etc.</li>
* <li>Files is a list of files referred to by this segment.</li>
* </ul>
- * </p>
*
* @see SegmentInfos
* @lucene.experimental
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50StoredFieldsFormat.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50StoredFieldsFormat.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50StoredFieldsFormat.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50StoredFieldsFormat.java Sat Feb 7 10:10:34 2015
@@ -38,7 +38,7 @@ import org.apache.lucene.util.packed.Pac
/**
* Lucene 5.0 stored fields format.
*
- * <p><b>Principle</b></p>
+ * <p><b>Principle</b>
* <p>This {@link StoredFieldsFormat} compresses blocks of documents in
* order to improve the compression ratio compared to document-level
* compression. It uses the <a href="http://code.google.com/p/lz4/">LZ4</a>
@@ -50,17 +50,17 @@ import org.apache.lucene.util.packed.Pac
* compression, you can choose ({@link Mode#BEST_COMPRESSION BEST_COMPRESSION}), which uses
* the <a href="http://en.wikipedia.org/wiki/DEFLATE">DEFLATE</a> algorithm with 60KB blocks
* for a better ratio at the expense of slower performance.
- * These two options can be configured like this: </p>
+ * These two options can be configured like this:
* <pre class="prettyprint">
* // the default: for high performance
* indexWriterConfig.setCodec(new Lucene50Codec(Mode.BEST_SPEED));
* // instead for higher performance (but slower):
* // indexWriterConfig.setCodec(new Lucene50Codec(Mode.BEST_COMPRESSION));
* </pre>
- * <p><b>File formats</b></p>
- * <p>Stored fields are represented by two files:</p>
+ * <p><b>File formats</b>
+ * <p>Stored fields are represented by two files:
* <ol>
- * <li><a name="field_data" id="field_data"></a>
+ * <li><a name="field_data"></a>
* <p>A fields data file (extension <tt>.fdt</tt>). This file stores a compact
* representation of documents in compressed blocks of 16KB or more. When
* writing a segment, documents are appended to an in-memory <tt>byte[]</tt>
@@ -106,7 +106,7 @@ import org.apache.lucene.util.packed.Pac
* <li>DirtyChunkCount --> the number of prematurely flushed chunks in this file</li>
* <li>Footer --> {@link CodecUtil#writeFooter CodecFooter}</li>
* </ul>
- * <p>Notes</p>
+ * <p>Notes
* <ul>
* <li>If documents are larger than 16KB then chunks will likely contain only
* one document. However, documents can never spread across several chunks (all
@@ -123,7 +123,7 @@ import org.apache.lucene.util.packed.Pac
* 0.5% larger than Docs.</li>
* </ul>
* </li>
- * <li><a name="field_index" id="field_index"></a>
+ * <li><a name="field_index"></a>
* <p>A fields index file (extension <tt>.fdx</tt>).</p>
* <ul>
* <li>FieldsIndex (.fdx) --> <Header>, <ChunkIndex>, Footer</li>
@@ -133,9 +133,9 @@ import org.apache.lucene.util.packed.Pac
* </ul>
* </li>
* </ol>
- * <p><b>Known limitations</b></p>
+ * <p><b>Known limitations</b>
* <p>This {@link StoredFieldsFormat} does not support individual documents
- * larger than (<tt>2<sup>31</sup> - 2<sup>14</sup></tt>) bytes.</p>
+ * larger than (<tt>2<sup>31</sup> - 2<sup>14</sup></tt>) bytes.
* @lucene.experimental
*/
public final class Lucene50StoredFieldsFormat extends StoredFieldsFormat {
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50TermVectorsFormat.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50TermVectorsFormat.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50TermVectorsFormat.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50TermVectorsFormat.java Sat Feb 7 10:10:34 2015
@@ -48,7 +48,7 @@ import org.apache.lucene.util.packed.Pac
* Looking up term vectors for any document requires at most 1 disk seek.
* <p><b>File formats</b>
* <ol>
- * <li><a name="vector_data" id="vector_data"></a>
+ * <li><a name="vector_data"></a>
* <p>A vector data file (extension <tt>.tvd</tt>). This file stores terms,
* frequencies, positions, offsets and payloads for every document. Upon writing
* a new segment, it accumulates data into memory until the buffer used to store
@@ -111,8 +111,8 @@ import org.apache.lucene.util.packed.Pac
* <li>Footer --> {@link CodecUtil#writeFooter CodecFooter}</li>
* </ul>
* </li>
- * <li><a name="vector_index" id="vector_index"></a>
- * <p>An index file (extension <tt>.tvx</tt>).</p>
+ * <li><a name="vector_index"></a>
+ * <p>An index file (extension <tt>.tvx</tt>).
* <ul>
* <li>VectorIndex (.tvx) --> <Header>, <ChunkIndex>, Footer</li>
* <li>Header --> {@link CodecUtil#writeIndexHeader IndexHeader}</li>
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/package-info.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/package-info.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/package-info.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/lucene50/package-info.java Sat Feb 7 10:10:34 2015
@@ -32,12 +32,13 @@
* </li>
* <li><a href="#Overview">Index Structure Overview</a></li>
* <li><a href="#File_Naming">File Naming</a></li>
- * <li><a href="#file-names">Summary of File Extensions</a></li>
+ * <li><a href="#file-names">Summary of File Extensions</a>
* <ul>
* <li><a href="#Lock_File">Lock File</a></li>
* <li><a href="#History">History</a></li>
* <li><a href="#Limitations">Limitations</a></li>
* </ul>
+ * </li>
* </ul>
* </div>
* <a name="Introduction"></a>
@@ -57,7 +58,7 @@
* different programming languages should endeavor to agree on file formats, and
* generate new versions of this document.</p>
* </div>
- * <a name="Definitions" id="Definitions"></a>
+ * <a name="Definitions"></a>
* <h2>Definitions</h2>
* <div>
* <p>The fundamental concepts in Lucene are index, document, field and term.</p>
@@ -88,7 +89,7 @@
* indexed literally.</p>
* <p>See the {@link org.apache.lucene.document.Field Field}
* java docs for more information on Fields.</p>
- * <a name="Segments" id="Segments"></a>
+ * <a name="Segments"></a>
* <h3>Segments</h3>
* <p>Lucene indexes may be composed of multiple sub-indexes, or <i>segments</i>.
* Each segment is a fully independent index, which could be searched separately.
@@ -128,7 +129,7 @@
* </li>
* </ul>
* </div>
- * <a name="Overview" id="Overview"></a>
+ * <a name="Overview"></a>
* <h2>Index Structure Overview</h2>
* <div>
* <p>Each segment index maintains the following:</p>
@@ -211,7 +212,7 @@
* segments_1, then segments_2, etc. The generation is a sequential long integer
* represented in alpha-numeric (base 36) form.</p>
* </div>
- * <a name="file-names" id="file-names"></a>
+ * <a name="file-names"></a>
* <h2>Summary of File Extensions</h2>
* <div>
* <p>The following table summarizes the names and extensions of the files in
@@ -316,14 +317,14 @@
* </tr>
* </table>
* </div>
- * <a name="Lock_File" id="Lock_File"></a>
+ * <a name="Lock_File"></a>
* <h2>Lock File</h2>
* The write lock, which is stored in the index directory by default, is named
* "write.lock". If the lock directory is different from the index directory then
* the write lock will be named "XXXX-write.lock" where XXXX is a unique prefix
* derived from the full path to the index directory. When this file is present, a
* writer is currently modifying the index (adding or removing documents). This
- * lock file ensures that only one writer is modifying the index at a time.</p>
+ * lock file ensures that only one writer is modifying the index at a time.
* <a name="History"></a>
* <h2>History</h2>
* <p>Compatibility notes are provided in this document, describing how file
@@ -386,7 +387,7 @@
* that is suitable for faceting/sorting/analytics.
* </li>
* </ul>
- * <a name="Limitations" id="Limitations"></a>
+ * <a name="Limitations"></a>
* <h2>Limitations</h2>
* <div>
* <p>Lucene uses a Java <code>int</code> to refer to
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/package-info.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/package-info.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/package-info.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/package-info.java Sat Feb 7 10:10:34 2015
@@ -30,7 +30,6 @@
* <li>Norms - see {@link org.apache.lucene.codecs.NormsFormat}</li>
* <li>Live documents - see {@link org.apache.lucene.codecs.LiveDocsFormat}</li>
* </ul>
- * </p>
*
* For some concrete implementations beyond Lucene's official index format, see
* the <a href="{@docRoot}/../codecs/overview-summary.html">Codecs module</a>.
@@ -51,7 +50,6 @@
* You will need to register the Codec class so that the {@link java.util.ServiceLoader ServiceLoader} can find it, by including a
* META-INF/services/org.apache.lucene.codecs.Codec file on your classpath that contains the package-qualified
* name of your codec.
- * </p>
*
* <p>
* If you just want to customise the {@link org.apache.lucene.codecs.PostingsFormat}, or use different postings
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/document/Field.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/document/Field.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/document/Field.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/document/Field.java Sat Feb 7 10:10:34 2015
@@ -42,13 +42,13 @@ import org.apache.lucene.util.BytesRef;
* NumericDocValuesField}, {@link SortedDocValuesField}, {@link
* StringField}, {@link TextField}, {@link StoredField}.
*
- * <p/> A field is a section of a Document. Each field has three
+ * <p> A field is a section of a Document. Each field has three
* parts: name, type and value. Values may be text
* (String, Reader or pre-analyzed TokenStream), binary
* (byte[]), or numeric (a Number). Fields are optionally stored in the
* index, so that they may be returned with hits on the document.
*
- * <p/>
+ * <p>
* NOTE: the field type is an {@link IndexableFieldType}. Making changes
* to the state of the IndexableFieldType will impact any
* Field it is used in. It is strongly recommended that no
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/document/LongField.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/document/LongField.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/document/LongField.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/document/LongField.java Sat Feb 7 10:10:34 2015
@@ -59,21 +59,21 @@ import org.apache.lucene.util.NumericUti
* value, either by dividing the result of
* {@link java.util.Date#getTime} or using the separate getters
* (for year, month, etc.) to construct an <code>int</code> or
- * <code>long</code> value.</p>
+ * <code>long</code> value.
*
* <p>To perform range querying or filtering against a
* <code>LongField</code>, use {@link NumericRangeQuery} or {@link
* NumericRangeFilter}. To sort according to a
* <code>LongField</code>, use the normal numeric sort types, eg
* {@link org.apache.lucene.search.SortField.Type#LONG}. <code>LongField</code>
- * values can also be loaded directly from {@link org.apache.lucene.index.LeafReader#getNumericDocValues}.</p>
+ * values can also be loaded directly from {@link org.apache.lucene.index.LeafReader#getNumericDocValues}.
*
* <p>You may add the same field name as an <code>LongField</code> to
* the same document more than once. Range querying and
* filtering will be the logical OR of all values; so a range query
* will hit all documents that have at least one value in
* the range. However sort behavior is not defined. If you need to sort,
- * you should separately index a single-valued <code>LongField</code>.</p>
+ * you should separately index a single-valued <code>LongField</code>.
*
* <p>A <code>LongField</code> will consume somewhat more disk space
* in the index than an ordinary single-valued field.
@@ -111,7 +111,7 @@ import org.apache.lucene.util.NumericUti
* <p>If you only need to sort by numeric value, and never
* run range querying/filtering, you can index using a
* <code>precisionStep</code> of {@link Integer#MAX_VALUE}.
- * This will minimize disk space consumed. </p>
+ * This will minimize disk space consumed.
*
* <p>More advanced users can instead use {@link
* NumericTokenStream} directly, when indexing numbers. This
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/DirectoryReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/DirectoryReader.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/DirectoryReader.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/DirectoryReader.java Sat Feb 7 10:10:34 2015
@@ -384,7 +384,6 @@ public abstract class DirectoryReader ex
/**
* Expert: return the IndexCommit that this reader has opened.
- * <p/>
* @lucene.experimental
*/
public abstract IndexCommit getIndexCommit() throws IOException;
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/SegmentInfos.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/SegmentInfos.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/SegmentInfos.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/SegmentInfos.java Sat Feb 7 10:10:34 2015
@@ -63,9 +63,7 @@ import org.apache.lucene.util.StringHelp
* HasSegID, SegID, SegCodec, DelGen, DeletionCount, FieldInfosGen, DocValuesGen,
* UpdatesFiles><sup>SegCount</sup>, CommitUserData, Footer
* </ul>
- * </p>
* Data types:
- * <p>
* <ul>
* <li>Header --> {@link CodecUtil#writeIndexHeader IndexHeader}</li>
* <li>NameCounter, SegCount, DeletionCount -->
@@ -81,9 +79,7 @@ import org.apache.lucene.util.StringHelp
* {@link DataOutput#writeStringSet(Set) Set<String>}></li>
* <li>Footer --> {@link CodecUtil#writeFooter CodecFooter}</li>
* </ul>
- * </p>
* Field Descriptions:
- * <p>
* <ul>
* <li>Version counts how often the index has been changed by adding or deleting
* documents.</li>
@@ -113,7 +109,6 @@ import org.apache.lucene.util.StringHelp
* <li>UpdatesFiles stores the set of files that were updated in that segment
* per field.</li>
* </ul>
- * </p>
*
* @lucene.experimental
*/
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/package-info.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/package-info.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/package-info.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/package-info.java Sat Feb 7 10:10:34 2015
@@ -19,7 +19,6 @@
* Code to maintain and access indices.
* <!-- TODO: add IndexWriter, IndexWriterConfig, DocValues, etc etc -->
* <h2>Table Of Contents</h2>
- * <p>
* <ol>
* <li><a href="#postings">Postings APIs</a>
* <ul>
@@ -38,7 +37,6 @@
* </ul>
* </li>
* </ol>
- * </p>
* <a name="postings"></a>
* <h2>Postings APIs</h2>
* <a name="fields"></a>
@@ -63,7 +61,6 @@
* Terms terms = fields.terms(field);
* }
* </pre>
- * </p>
* <a name="terms"></a>
* <h3>
* Terms
@@ -100,7 +97,6 @@
* DocsAndPositionsEnum docsAndPositions = termsEnum.docsAndPositions(null, null);
* }
* </pre>
- * </p>
* <a name="documents"></a>
* <h3>
* Documents
@@ -116,7 +112,6 @@
* System.out.println(docsEnum.freq());
* }
* </pre>
- * </p>
* <a name="positions"></a>
* <h3>
* Positions
@@ -140,14 +135,12 @@
* }
* }
* </pre>
- * </p>
* <a name="stats"></a>
* <h2>Index Statistics</h2>
* <a name="termstats"></a>
* <h3>
* Term statistics
* </h3>
- * <p>
* <ul>
* <li>{@link org.apache.lucene.index.TermsEnum#docFreq}: Returns the number of
* documents that contain at least one occurrence of the term. This statistic
@@ -162,12 +155,10 @@
* for the field. Like docFreq(), it will also count occurrences that appear in
* deleted documents.
* </ul>
- * </p>
* <a name="fieldstats"></a>
* <h3>
* Field statistics
* </h3>
- * <p>
* <ul>
* <li>{@link org.apache.lucene.index.Terms#size}: Returns the number of
* unique terms in the field. This statistic may be unavailable
@@ -194,12 +185,10 @@
* ({@link org.apache.lucene.index.IndexOptions#DOCS DOCS})
* for the field.
* </ul>
- * </p>
* <a name="segmentstats"></a>
* <h3>
* Segment statistics
* </h3>
- * <p>
* <ul>
* <li>{@link org.apache.lucene.index.IndexReader#maxDoc}: Returns the number of
* documents (including deleted documents) in the index.
@@ -210,7 +199,6 @@
* <li>{@link org.apache.lucene.index.Fields#size}: Returns the number of indexed
* fields.
* </ul>
- * </p>
* <a name="documentstats"></a>
* <h3>
* Document statistics
@@ -220,8 +208,6 @@
* a {@link org.apache.lucene.search.similarities.Similarity} implementation will store some
* of these values (possibly in a lossy way), into the normalization value for the document in
* its {@link org.apache.lucene.search.similarities.Similarity#computeNorm} method.
- * </p>
- * <p>
* <ul>
* <li>{@link org.apache.lucene.index.FieldInvertState#getLength}: Returns the number of
* tokens for this field in the document. Note that this is just the number
@@ -248,11 +234,8 @@
* <li>{@link org.apache.lucene.index.FieldInvertState#getMaxTermFrequency}: Returns the maximum
* frequency across all unique terms encountered for this field in the document.
* </ul>
- * </p>
* <p>
* Additional user-supplied statistics can be added to the document as DocValues fields and
* accessed via {@link org.apache.lucene.index.LeafReader#getNumericDocValues}.
- * </p>
- * <p>
*/
package org.apache.lucene.index;
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/DocValuesTermsFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/DocValuesTermsFilter.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/DocValuesTermsFilter.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/DocValuesTermsFilter.java Sat Feb 7 10:10:34 2015
@@ -32,8 +32,7 @@ import org.apache.lucene.util.FixedBitSe
* term value in the specified field is contained in the
* provided set of allowed terms.
*
- * <p/>
- *
+ * <p>
* This is the same functionality as TermsFilter (from
* queries/), except this filter requires that the
* field contains only a single term for all documents.
@@ -41,9 +40,7 @@ import org.apache.lucene.util.FixedBitSe
* also have different performance characteristics, as
* described below.
*
- *
- * <p/>
- *
+ * <p>
* With each search, this filter translates the specified
* set of Terms into a private {@link FixedBitSet} keyed by
* term number per unique {@link IndexReader} (normally one
@@ -58,8 +55,7 @@ import org.apache.lucene.util.FixedBitSe
* index with a great many small documents may find this
* linear scan too costly.
*
- * <p/>
- *
+ * <p>
* In contrast, TermsFilter builds up an {@link FixedBitSet},
* keyed by docID, every time it's created, by enumerating
* through all matching docs using {@link org.apache.lucene.index.PostingsEnum} to seek
@@ -70,8 +66,7 @@ import org.apache.lucene.util.FixedBitSe
* to the number of terms, which can be exceptionally costly
* when there are cache misses in the OS's IO cache.
*
- * <p/>
- *
+ * <p>
* Generally, this filter will be slower on the first
* invocation for a given field, but subsequent invocations,
* even if you change the allowed set of Terms, should be
@@ -81,8 +76,7 @@ import org.apache.lucene.util.FixedBitSe
* match a very small number of documents, TermsFilter may
* perform faster.
*
- * <p/>
- *
+ * <p>
* Which filter is best is very application dependent.
*/
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/FilteredDocIdSet.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/FilteredDocIdSet.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/FilteredDocIdSet.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/FilteredDocIdSet.java Sat Feb 7 10:10:34 2015
@@ -29,8 +29,7 @@ import org.apache.lucene.util.RamUsageEs
* that provides on-demand filtering/validation
* mechanism on a given DocIdSet.
*
- * <p/>
- *
+ * <p>
* Technically, this same functionality could be achieved
* with ChainedFilter (under queries/), however the
* benefit of this class is it never materializes the full
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/NumericRangeQuery.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/NumericRangeQuery.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/NumericRangeQuery.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/NumericRangeQuery.java Sat Feb 7 10:10:34 2015
@@ -109,7 +109,7 @@ import org.apache.lucene.index.Term; //
* In practice, we have seen up to 300 terms in most cases (index with 500,000 metadata records
* and a uniform value distribution).</p>
*
- * <a name="precisionStepDesc"><h3>Precision Step</h3>
+ * <h3><a name="precisionStepDesc">Precision Step</a></h3>
* <p>You can choose any <code>precisionStep</code> when encoding values.
* Lower step values mean more precisions and so more terms in index (and index gets larger). The number
* of indexed terms per value is (those are generated by {@link NumericTokenStream}):
@@ -123,14 +123,14 @@ import org.apache.lucene.index.Term; //
* of the term dictionary in comparison to one term per value:
* <p>
* <!-- the formula in the alt attribute was transformed from latex to PNG with http://1.618034.com/latex.php (with 110 dpi): -->
- * <img src="doc-files/nrq-formula-1.png" alt="\mathrm{termDictOverhead} = \sum\limits_{i=0}^{\mathrm{indexedTermsPerValue}-1} \frac{1}{2^{\mathrm{precisionStep}\cdot i}}" />
+ * <img src="doc-files/nrq-formula-1.png" alt="\mathrm{termDictOverhead} = \sum\limits_{i=0}^{\mathrm{indexedTermsPerValue}-1} \frac{1}{2^{\mathrm{precisionStep}\cdot i}}">
* </p>
* <p>On the other hand, if the <code>precisionStep</code> is smaller, the maximum number of terms to match reduces,
* which optimizes query speed. The formula to calculate the maximum number of terms that will be visited while
* executing the query is:
* <p>
* <!-- the formula in the alt attribute was transformed from latex to PNG with http://1.618034.com/latex.php (with 110 dpi): -->
- * <img src="doc-files/nrq-formula-2.png" alt="\mathrm{maxQueryTerms} = \left[ \left( \mathrm{indexedTermsPerValue} - 1 \right) \cdot \left(2^\mathrm{precisionStep} - 1 \right) \cdot 2 \right] + \left( 2^\mathrm{precisionStep} - 1 \right)" />
+ * <img src="doc-files/nrq-formula-2.png" alt="\mathrm{maxQueryTerms} = \left[ \left( \mathrm{indexedTermsPerValue} - 1 \right) \cdot \left(2^\mathrm{precisionStep} - 1 \right) \cdot 2 \right] + \left( 2^\mathrm{precisionStep} - 1 \right)">
* </p>
* <p>For longs stored using a precision step of 4, <code>maxQueryTerms = 15*15*2 + 15 = 465</code>, and for a precision
* step of 2, <code>maxQueryTerms = 31*3*2 + 3 = 189</code>. But the faster search speed is reduced by more seeking
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/Sort.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/Sort.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/Sort.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/Sort.java Sat Feb 7 10:10:34 2015
@@ -34,7 +34,7 @@ import java.util.Arrays;
* <p><code>document.add (new Field ("byNumber", Integer.toString(x), Field.Store.NO, Field.Index.NOT_ANALYZED));</code></p>
*
*
- * <p><h3>Valid Types of Values</h3>
+ * <h3>Valid Types of Values</h3>
*
* <p>There are four possible kinds of term values which may be put into
* sorting fields: Integers, Longs, Floats, or Strings. Unless
@@ -67,14 +67,14 @@ import java.util.Arrays;
* of term value has higher memory requirements than the other
* two types.
*
- * <p><h3>Object Reuse</h3>
+ * <h3>Object Reuse</h3>
*
* <p>One of these objects can be
* used multiple times and the sort order changed between usages.
*
* <p>This class is thread safe.
*
- * <p><h3>Memory Usage</h3>
+ * <h3>Memory Usage</h3>
*
* <p>Sorting uses of caches of term values maintained by the
* internal HitQueue(s). The cache is static and contains an integer
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/SortedNumericSortField.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/SortedNumericSortField.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/SortedNumericSortField.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/SortedNumericSortField.java Sat Feb 7 10:10:34 2015
@@ -35,7 +35,6 @@ import org.apache.lucene.index.SortedNum
* <p>
* Like sorting by string, this also supports sorting missing values as first or last,
* via {@link #setMissingValue(Object)}.
- * <p>
* @see SortedNumericSelector
*/
public class SortedNumericSortField extends SortField {
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/SortedSetSortField.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/SortedSetSortField.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/SortedSetSortField.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/SortedSetSortField.java Sat Feb 7 10:10:34 2015
@@ -36,7 +36,6 @@ import org.apache.lucene.index.SortedSet
* <p>
* Like sorting by string, this also supports sorting missing values as first or last,
* via {@link #setMissingValue(Object)}.
- * <p>
* @see SortedSetSelector
*/
public class SortedSetSortField extends SortField {
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/TermRangeTermsEnum.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/TermRangeTermsEnum.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/TermRangeTermsEnum.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/TermRangeTermsEnum.java Sat Feb 7 10:10:34 2015
@@ -24,7 +24,7 @@ import org.apache.lucene.util.BytesRef;
/**
* Subclass of FilteredTermEnum for enumerating all terms that match the
* specified range parameters. Each term in the enumeration is
- * greater than all that precede it.</p>
+ * greater than all that precede it.
*/
public class TermRangeTermsEnum extends FilteredTermsEnum {
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/TimeLimitingCollector.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/TimeLimitingCollector.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/TimeLimitingCollector.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/TimeLimitingCollector.java Sat Feb 7 10:10:34 2015
@@ -94,7 +94,6 @@ public class TimeLimitingCollector imple
* collector.setBaseline(baseline);
* indexSearcher.search(query, collector);
* </pre>
- * </p>
* @see #setBaseline()
*/
public void setBaseline(long clockTime) {
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/TopFieldCollector.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/TopFieldCollector.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/TopFieldCollector.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/TopFieldCollector.java Sat Feb 7 10:10:34 2015
@@ -26,7 +26,7 @@ import org.apache.lucene.util.PriorityQu
/**
* A {@link Collector} that sorts by {@link SortField} using
* {@link FieldComparator}s.
- * <p/>
+ * <p>
* See the {@link #create(org.apache.lucene.search.Sort, int, boolean, boolean, boolean)} method
* for instantiating a TopFieldCollector.
*
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/package-info.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/package-info.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/package-info.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/package-info.java Sat Feb 7 10:10:34 2015
@@ -19,7 +19,6 @@
* Code to search indices.
*
* <h2>Table Of Contents</h2>
- * <p>
* <ol>
* <li><a href="#search">Search Basics</a></li>
* <li><a href="#query">The Query Classes</a></li>
@@ -28,7 +27,6 @@
* <li><a href="#changingScoring">Changing the Scoring</a></li>
* <li><a href="#algorithm">Appendix: Search Algorithm</a></li>
* </ol>
- * </p>
*
*
* <a name="search"></a>
@@ -40,21 +38,17 @@
* variety of ways to provide complex querying capabilities along with information about where matches took place in the document
* collection. The <a href="#query">Query Classes</a> section below highlights some of the more important Query classes. For details
* on implementing your own Query class, see <a href="#customQueriesExpert">Custom Queries -- Expert Level</a> below.
- * </p>
* <p>
* To perform a search, applications usually call {@link
* org.apache.lucene.search.IndexSearcher#search(Query,int)} or {@link
* org.apache.lucene.search.IndexSearcher#search(Query,Filter,int)}.
- * </p>
* <p>
* Once a Query has been created and submitted to the {@link org.apache.lucene.search.IndexSearcher IndexSearcher}, the scoring
* process begins. After some infrastructure setup, control finally passes to the {@link org.apache.lucene.search.Weight Weight}
* implementation and its {@link org.apache.lucene.search.Scorer Scorer} or {@link org.apache.lucene.search.BulkScorer BulkScore}
* instances. See the <a href="#algorithm">Algorithm</a> section for more notes on the process.
- * </p>
* <!-- FILL IN MORE HERE -->
* <!-- TODO: this page over-links the same things too many times -->
- * </p>
*
*
* <a name="query"></a>
@@ -83,7 +77,6 @@
* {@link org.apache.lucene.document.Document Document}s that have the
* {@link org.apache.lucene.document.Field Field} named <tt>"fieldName"</tt>
* containing the word <tt>"term"</tt>.
- * </p>
* <h3>
* {@link org.apache.lucene.search.BooleanQuery BooleanQuery}
* </h3>
@@ -123,7 +116,6 @@
* The default setting for the maximum number
* of clauses 1024, but this can be changed via the
* static method {@link org.apache.lucene.search.BooleanQuery#setMaxClauseCount(int)}.
- * </p>
*
* <h3>Phrases</h3>
*
@@ -156,7 +148,6 @@
* instances.</p>
* </li>
* </ol>
- * </p>
*
* <h3>
* {@link org.apache.lucene.search.TermRangeQuery TermRangeQuery}
@@ -174,7 +165,6 @@
*
* For example, one could find all documents
* that have terms beginning with the letters <tt>a</tt> through <tt>c</tt>.
- * </p>
*
* <h3>
* {@link org.apache.lucene.search.NumericRangeQuery NumericRangeQuery}
@@ -187,7 +177,6 @@
* using a one of the numeric fields ({@link org.apache.lucene.document.IntField IntField},
* {@link org.apache.lucene.document.LongField LongField}, {@link org.apache.lucene.document.FloatField FloatField},
* or {@link org.apache.lucene.document.DoubleField DoubleField}).
- * </p>
*
* <h3>
* {@link org.apache.lucene.search.PrefixQuery PrefixQuery},
@@ -211,7 +200,6 @@
* to remove that protection.
* The {@link org.apache.lucene.search.RegexpQuery RegexpQuery} is even more general than WildcardQuery,
* allowing an application to identify all documents with terms that match a regular expression pattern.
- * </p>
* <h3>
* {@link org.apache.lucene.search.FuzzyQuery FuzzyQuery}
* </h3>
@@ -222,7 +210,6 @@
* determined using
* <a href="http://en.wikipedia.org/wiki/Levenshtein">Levenshtein (edit) distance</a>.
* This type of query can be useful when accounting for spelling variations in the collection.
- * </p>
*
*
* <a name="scoring"></a>
@@ -234,10 +221,8 @@
* <a href="mailto:java-user@lucene.apache.org">java-user@lucene.apache.org</a> to figure out
* why a document with five of our query terms scores lower than a different document with
* only one of the query terms.
- * </p>
* <p>While this document won't answer your specific scoring issues, it will, hopefully, point you
* to the places that can help you figure out the <i>what</i> and <i>why</i> of Lucene scoring.
- * </p>
* <p>Lucene scoring supports a number of pluggable information retrieval
* <a href="http://en.wikipedia.org/wiki/Information_retrieval#Model_types">models</a>, including:
* <ul>
@@ -252,14 +237,12 @@
* that need to be scored based on boolean logic in the Query specification, and then ranks this subset of
* matching documents via the retrieval model. For some valuable references on VSM and IR in general refer to
* <a href="http://wiki.apache.org/lucene-java/InformationRetrieval">Lucene Wiki IR references</a>.
- * </p>
* <p>The rest of this document will cover <a href="#scoringBasics">Scoring basics</a> and explain how to
* change your {@link org.apache.lucene.search.similarities.Similarity Similarity}. Next, it will cover
* ways you can customize the lucene internals in
* <a href="#customQueriesExpert">Custom Queries -- Expert Level</a>, which gives details on
* implementing your own {@link org.apache.lucene.search.Query Query} class and related functionality.
* Finally, we will finish up with some reference material in the <a href="#algorithm">Appendix</a>.
- * </p>
*
*
* <a name="scoringBasics"></a>
@@ -286,7 +269,6 @@
* important because two Documents with the exact same content, but one having the content in two
* Fields and the other in one Field may return different scores for the same query due to length
* normalization.
- * </p>
* <h3>Score Boosting</h3>
* <p>Lucene allows influencing search results by "boosting" at different times:
* <ul>
@@ -296,7 +278,6 @@
* <li><b>Query-time boost</b> by setting a boost on a query clause, calling
* {@link org.apache.lucene.search.Query#setBoost(float) Query.setBoost()}.</li>
* </ul>
- * </p>
* <p>Indexing time boosts are pre-processed for storage efficiency and written to
* storage for a field as follows:
* <ul>
@@ -310,8 +291,6 @@
* <li>Decoding of any index-time normalization values and integration into the document's score is also performed
* at search time by the Similarity.</li>
* </ul>
- * </p>
- *
*
* <a name="changingScoring"></a>
* <h2>Changing Scoring — Similarity</h2>
@@ -324,22 +303,18 @@
* IndexSearcher.setSimilarity(Similarity)}. Be sure to use the same
* Similarity at query-time as at index-time (so that norms are
* encoded/decoded correctly); Lucene makes no effort to verify this.
- * </p>
* <p>
* You can influence scoring by configuring a different built-in Similarity implementation, or by tweaking its
* parameters, subclassing it to override behavior. Some implementations also offer a modular API which you can
* extend by plugging in a different component (e.g. term frequency normalizer).
- * </p>
* <p>
* Finally, you can extend the low level {@link org.apache.lucene.search.similarities.Similarity Similarity} directly
* to implement a new retrieval model, or to use external scoring factors particular to your application. For example,
* a custom Similarity can access per-document values via {@link org.apache.lucene.index.NumericDocValues} and
* integrate them into the score.
- * </p>
* <p>
* See the {@link org.apache.lucene.search.similarities} package documentation for information
* on the built-in available scoring models and extending or changing Similarity.
- * </p>
*
*
* <a name="customQueriesExpert"></a>
@@ -347,7 +322,6 @@
*
* <p>Custom queries are an expert level task, so tread carefully and be prepared to share your code if
* you want help.
- * </p>
*
* <p>With the warning out of the way, it is possible to change a lot more than just the Similarity
* when it comes to matching and scoring in Lucene. Lucene's search is a complex mechanism that is grounded by
@@ -374,7 +348,6 @@
* implementations.</li>
* </ol>
* Details on each of these classes, and their children, can be found in the subsections below.
- * </p>
* <h3>The Query Class</h3>
* <p>In some sense, the
* {@link org.apache.lucene.search.Query Query}
@@ -396,7 +369,6 @@
* {@link org.apache.lucene.search.BooleanQuery BooleanQuery}, <span
* >and other queries that implement {@link org.apache.lucene.search.Query#createWeight(IndexSearcher,boolean) createWeight(IndexSearcher searcher,boolean)}</span></li>
* </ol>
- * </p>
* <a name="weightClass"></a>
* <h3>The Weight Interface</h3>
* <p>The
@@ -449,10 +421,8 @@
* Typically a weight such as TermWeight
* that scores via a {@link org.apache.lucene.search.similarities.Similarity Similarity} will make use of the Similarity's implementation:
* {@link org.apache.lucene.search.similarities.Similarity.SimScorer#explain(int, Explanation) SimScorer#explain(int doc, Explanation freq)}.
- * </li>
- * </li>
+ * </li>
* </ol>
- * </p>
* <a name="scorerClass"></a>
* <h3>The Scorer Class</h3>
* <p>The
@@ -494,7 +464,6 @@
* details on the scoring process.
* </li>
* </ol>
- * </p>
* <a name="bulkScorerClass"></a>
* <h3>The BulkScorer Class</h3>
* <p>The
@@ -506,14 +475,13 @@
* Score all documents up to but not including the specified max document.
* </li>
* </ol>
- * </p>
* <h3>Why would I want to add my own Query?</h3>
*
* <p>In a nutshell, you want to add your own custom Query implementation when you think that Lucene's
* aren't appropriate for the
* task that you want to do. You might be doing some cutting edge research or you need more information
* back
- * out of Lucene (similar to Doug adding SpanQuery functionality).</p>
+ * out of Lucene (similar to Doug adding SpanQuery functionality).
*
* <!-- TODO: integrate this better, it's better served as an intro than an appendix -->
*
@@ -521,10 +489,10 @@
* <a name="algorithm"></a>
* <h2>Appendix: Search Algorithm</h2>
* <p>This section is mostly notes on stepping through the Scoring process and serves as
- * fertilizer for the earlier sections.</p>
+ * fertilizer for the earlier sections.
* <p>In the typical search application, a {@link org.apache.lucene.search.Query Query}
* is passed to the {@link org.apache.lucene.search.IndexSearcher IndexSearcher},
- * beginning the scoring process.</p>
+ * beginning the scoring process.
* <p>Once inside the IndexSearcher, a {@link org.apache.lucene.search.Collector Collector}
* is used for the scoring and sorting of the search results.
* These important objects are involved in a search:
@@ -538,7 +506,6 @@
* <li>A {@link org.apache.lucene.search.Sort Sort} object for specifying how to sort
* the results if the standard score-based sort method is not desired.</li>
* </ol>
- * </p>
* <p>Assuming we are not sorting (since sorting doesn't affect the raw Lucene score),
* we call one of the search methods of the IndexSearcher, passing in the
* {@link org.apache.lucene.search.Weight Weight} object created by
@@ -553,12 +520,10 @@
* see {@link org.apache.lucene.search.IndexSearcher IndexSearcher}). The TopScoreDocCollector
* uses a {@link org.apache.lucene.util.PriorityQueue PriorityQueue} to collect the
* top results for the search.
- * </p>
* <p>If a Filter is being used, some initial setup is done to determine which docs to include.
* Otherwise, we ask the Weight for a {@link org.apache.lucene.search.Scorer Scorer} for each
* {@link org.apache.lucene.index.IndexReader IndexReader} segment and proceed by calling
* {@link org.apache.lucene.search.BulkScorer#score(org.apache.lucene.search.LeafCollector) BulkScorer.score(LeafCollector)}.
- * </p>
* <p>At last, we are actually going to score some documents. The score method takes in the Collector
* (most likely the TopScoreDocCollector or TopFieldCollector) and does its business.Of course, here
* is where things get involved. The {@link org.apache.lucene.search.Scorer Scorer} that is returned
@@ -567,13 +532,12 @@
* {@link org.apache.lucene.search.Scorer Scorer} is going to be a <code>BooleanScorer2</code> created
* from {@link org.apache.lucene.search.BooleanWeight BooleanWeight} (see the section on
* <a href="#customQueriesExpert">custom queries</a> for info on changing this).
- * </p>
* <p>Assuming a BooleanScorer2, we first initialize the Coordinator, which is used to apply the coord()
* factor. We then get a internal Scorer based on the required, optional and prohibited parts of the query.
* Using this internal Scorer, the BooleanScorer2 then proceeds into a while loop based on the
* {@link org.apache.lucene.search.Scorer#nextDoc Scorer.nextDoc()} method. The nextDoc() method advances
* to the next document matching the query. This is an abstract method in the Scorer class and is thus
* overridden by all derived implementations. If you have a simple OR query your internal Scorer is most
- * likely a DisjunctionSumScorer, which essentially combines the scorers from the sub scorers of the OR'd terms.</p>
+ * likely a DisjunctionSumScorer, which essentially combines the scorers from the sub scorers of the OR'd terms.
*/
package org.apache.lucene.search;
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/payloads/AveragePayloadFunction.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/payloads/AveragePayloadFunction.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/payloads/AveragePayloadFunction.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/payloads/AveragePayloadFunction.java Sat Feb 7 10:10:34 2015
@@ -20,7 +20,7 @@ package org.apache.lucene.search.payload
/**
* Calculate the final score as the average score of all payloads seen.
- * <p/>
+ * <p>
* Is thread safe and completely reusable.
*
**/
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/payloads/MaxPayloadFunction.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/payloads/MaxPayloadFunction.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/payloads/MaxPayloadFunction.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/payloads/MaxPayloadFunction.java Sat Feb 7 10:10:34 2015
@@ -20,7 +20,7 @@ package org.apache.lucene.search.payload
/**
* Returns the maximum payload score seen, else 1 if there are no payloads on the doc.
- * <p/>
+ * <p>
* Is thread safe and completely reusable.
*
**/
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/payloads/PayloadNearQuery.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/payloads/PayloadNearQuery.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/payloads/PayloadNearQuery.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/payloads/PayloadNearQuery.java Sat Feb 7 10:10:34 2015
@@ -46,11 +46,11 @@ import org.apache.lucene.util.ToStringUt
* {@link org.apache.lucene.search.spans.SpanNearQuery} except that it factors
* in the value of the payloads located at each of the positions where the
* {@link org.apache.lucene.search.spans.TermSpans} occurs.
- * <p/>
+ * <p>
* NOTE: In order to take advantage of this with the default scoring implementation
* ({@link DefaultSimilarity}), you must override {@link DefaultSimilarity#scorePayload(int, int, int, BytesRef)},
* which returns 1 by default.
- * <p/>
+ * <p>
* Payload scores are aggregated using a pluggable {@link PayloadFunction}.
*
* @see org.apache.lucene.search.similarities.Similarity.SimScorer#computePayloadFactor(int, int, int, BytesRef)
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/payloads/PayloadTermQuery.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/payloads/PayloadTermQuery.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/payloads/PayloadTermQuery.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/payloads/PayloadTermQuery.java Sat Feb 7 10:10:34 2015
@@ -43,11 +43,11 @@ import org.apache.lucene.util.BytesRef;
* {@link org.apache.lucene.search.spans.SpanTermQuery} except that it factors
* in the value of the payload located at each of the positions where the
* {@link org.apache.lucene.index.Term} occurs.
- * <p/>
+ * <p>
* NOTE: In order to take advantage of this with the default scoring implementation
* ({@link DefaultSimilarity}), you must override {@link DefaultSimilarity#scorePayload(int, int, int, BytesRef)},
* which returns 1 by default.
- * <p/>
+ * <p>
* Payload scores are aggregated using a pluggable {@link PayloadFunction}.
* @see org.apache.lucene.search.similarities.Similarity.SimScorer#computePayloadFactor(int, int, int, BytesRef)
**/
@@ -151,7 +151,7 @@ public class PayloadTermQuery extends Sp
/**
* Returns the SpanScorer score only.
- * <p/>
+ * <p>
* Should not be overridden without good cause!
*
* @return the score for just the Span part w/o the payload
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/payloads/package-info.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/payloads/package-info.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/payloads/package-info.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/payloads/package-info.java Sat Feb 7 10:10:34 2015
@@ -24,6 +24,5 @@
* <li>{@link org.apache.lucene.search.payloads.PayloadNearQuery PayloadNearQuery} -- A {@link org.apache.lucene.search.spans.SpanNearQuery SpanNearQuery} that factors in the value of the payloads located
* at each of the positions where the spans occur.</li>
* </ol>
- * </p>
*/
package org.apache.lucene.search.payloads;
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/similarities/IBSimilarity.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/similarities/IBSimilarity.java?rev=1658040&r1=1658039&r2=1658040&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/similarities/IBSimilarity.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/similarities/IBSimilarity.java Sat Feb 7 10:10:34 2015
@@ -36,7 +36,6 @@ import org.apache.lucene.search.similari
* <li><em>t<sup>d</sup><sub>w</sub></em> is the normalized term frequency;</li>
* <li><em>λ<sub>w</sub></em> is a parameter.</li>
* </ul>
- * </p>
* <p>The framework described in the paper has many similarities to the DFR
* framework (see {@link DFRSimilarity}). It is possible that the two
* Similarities will be merged at one point.</p>
@@ -64,7 +63,6 @@ import org.apache.lucene.search.similari
* {@link DFRSimilarity})</blockquote>
* </li>
* </ol>
- * <p>
* @see DFRSimilarity
* @lucene.experimental
*/