mirror of https://github.com/apache/lucene.git
LUCENE-8461: Add Lucene80Codec.
This commit is contained in:
Adrien Grand
parent
8cde1277ec
commit
025350ea12
|
|
@ -0,0 +1,133 @@
|
|||
/*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
* this work for additional information regarding copyright ownership.
|
||||
* The ASF licenses this file to You under the Apache License, Version 2.0
|
||||
* (the "License"); you may not use this file except in compliance with
|
||||
* the License. You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
package org.apache.lucene.codecs.lucene70;
|
||||
|
||||
import org.apache.lucene.codecs.Codec;
|
||||
import org.apache.lucene.codecs.CompoundFormat;
|
||||
import org.apache.lucene.codecs.DocValuesFormat;
|
||||
import org.apache.lucene.codecs.FieldInfosFormat;
|
||||
import org.apache.lucene.codecs.FilterCodec;
|
||||
import org.apache.lucene.codecs.LiveDocsFormat;
|
||||
import org.apache.lucene.codecs.NormsFormat;
|
||||
import org.apache.lucene.codecs.PointsFormat;
|
||||
import org.apache.lucene.codecs.PostingsFormat;
|
||||
import org.apache.lucene.codecs.SegmentInfoFormat;
|
||||
import org.apache.lucene.codecs.StoredFieldsFormat;
|
||||
import org.apache.lucene.codecs.TermVectorsFormat;
|
||||
import org.apache.lucene.codecs.lucene50.Lucene50CompoundFormat;
|
||||
import org.apache.lucene.codecs.lucene50.Lucene50LiveDocsFormat;
|
||||
import org.apache.lucene.codecs.lucene50.Lucene50StoredFieldsFormat;
|
||||
import org.apache.lucene.codecs.lucene50.Lucene50StoredFieldsFormat.Mode;
|
||||
import org.apache.lucene.codecs.lucene50.Lucene50TermVectorsFormat;
|
||||
import org.apache.lucene.codecs.lucene60.Lucene60FieldInfosFormat;
|
||||
import org.apache.lucene.codecs.lucene60.Lucene60PointsFormat;
|
||||
import org.apache.lucene.codecs.perfield.PerFieldDocValuesFormat;
|
||||
import org.apache.lucene.codecs.perfield.PerFieldPostingsFormat;
|
||||
|
||||
/**
|
||||
* Implements the Lucene 7.0 index format, with configurable per-field postings
|
||||
* and docvalues formats.
|
||||
* <p>
|
||||
* If you want to reuse functionality of this codec in another codec, extend
|
||||
* {@link FilterCodec}.
|
||||
*
|
||||
* @see org.apache.lucene.codecs.lucene70 package documentation for file format details.
|
||||
*
|
||||
* @lucene.experimental
|
||||
*/
|
||||
public class Lucene70Codec extends Codec {
|
||||
private final TermVectorsFormat vectorsFormat = new Lucene50TermVectorsFormat();
|
||||
private final FieldInfosFormat fieldInfosFormat = new Lucene60FieldInfosFormat();
|
||||
private final SegmentInfoFormat segmentInfosFormat = new Lucene70SegmentInfoFormat();
|
||||
private final LiveDocsFormat liveDocsFormat = new Lucene50LiveDocsFormat();
|
||||
private final CompoundFormat compoundFormat = new Lucene50CompoundFormat();
|
||||
|
||||
private final PostingsFormat postingsFormat = new PerFieldPostingsFormat() {
|
||||
@Override
|
||||
public PostingsFormat getPostingsFormatForField(String field) {
|
||||
throw new IllegalStateException("This codec should only be used for reading, not writing");
|
||||
}
|
||||
};
|
||||
|
||||
private final DocValuesFormat docValuesFormat = new PerFieldDocValuesFormat() {
|
||||
@Override
|
||||
public DocValuesFormat getDocValuesFormatForField(String field) {
|
||||
throw new IllegalStateException("This codec should only be used for reading, not writing");
|
||||
}
|
||||
};
|
||||
|
||||
private final StoredFieldsFormat storedFieldsFormat = new Lucene50StoredFieldsFormat(Mode.BEST_SPEED);
|
||||
|
||||
/**
|
||||
* Instantiates a new codec.
|
||||
*/
|
||||
public Lucene70Codec() {
|
||||
super("Lucene70");
|
||||
}
|
||||
|
||||
@Override
|
||||
public final StoredFieldsFormat storedFieldsFormat() {
|
||||
return storedFieldsFormat;
|
||||
}
|
||||
|
||||
@Override
|
||||
public final TermVectorsFormat termVectorsFormat() {
|
||||
return vectorsFormat;
|
||||
}
|
||||
|
||||
@Override
|
||||
public final PostingsFormat postingsFormat() {
|
||||
return postingsFormat;
|
||||
}
|
||||
|
||||
@Override
|
||||
public final FieldInfosFormat fieldInfosFormat() {
|
||||
return fieldInfosFormat;
|
||||
}
|
||||
|
||||
@Override
|
||||
public final SegmentInfoFormat segmentInfoFormat() {
|
||||
return segmentInfosFormat;
|
||||
}
|
||||
|
||||
@Override
|
||||
public final LiveDocsFormat liveDocsFormat() {
|
||||
return liveDocsFormat;
|
||||
}
|
||||
|
||||
@Override
|
||||
public final CompoundFormat compoundFormat() {
|
||||
return compoundFormat;
|
||||
}
|
||||
|
||||
@Override
|
||||
public final PointsFormat pointsFormat() {
|
||||
return new Lucene60PointsFormat();
|
||||
}
|
||||
|
||||
@Override
|
||||
public final DocValuesFormat docValuesFormat() {
|
||||
return docValuesFormat;
|
||||
}
|
||||
|
||||
private final NormsFormat normsFormat = new Lucene70NormsFormat();
|
||||
|
||||
@Override
|
||||
public final NormsFormat normsFormat() {
|
||||
return normsFormat;
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,25 @@
|
|||
<!doctype html public "-//w3c//dtd html 4.0 transitional//en">
|
||||
<!--
|
||||
Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
contributor license agreements. See the NOTICE file distributed with
|
||||
this work for additional information regarding copyright ownership.
|
||||
The ASF licenses this file to You under the Apache License, Version 2.0
|
||||
(the "License"); you may not use this file except in compliance with
|
||||
the License. You may obtain a copy of the License at
|
||||
|
||||
http://www.apache.org/licenses/LICENSE-2.0
|
||||
|
||||
Unless required by applicable law or agreed to in writing, software
|
||||
distributed under the License is distributed on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
See the License for the specific language governing permissions and
|
||||
limitations under the License.
|
||||
-->
|
||||
<html>
|
||||
<head>
|
||||
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
|
||||
</head>
|
||||
<body>
|
||||
Lucene 7.0 file format.
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -13,3 +13,4 @@
|
|||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
org.apache.lucene.codecs.lucene70.Lucene70Codec
|
||||
|
|
|
|||
|
|
@ -29,7 +29,7 @@ import org.apache.lucene.benchmark.byTask.PerfRunData;
|
|||
import org.apache.lucene.benchmark.byTask.utils.Config;
|
||||
import org.apache.lucene.codecs.Codec;
|
||||
import org.apache.lucene.codecs.PostingsFormat;
|
||||
import org.apache.lucene.codecs.lucene70.Lucene70Codec;
|
||||
import org.apache.lucene.codecs.lucene80.Lucene80Codec;
|
||||
import org.apache.lucene.index.ConcurrentMergeScheduler;
|
||||
import org.apache.lucene.index.IndexCommit;
|
||||
import org.apache.lucene.index.IndexDeletionPolicy;
|
||||
|
|
@ -139,7 +139,7 @@ public class CreateIndexTask extends PerfTask {
|
|||
if (defaultCodec == null && postingsFormat != null) {
|
||||
try {
|
||||
final PostingsFormat postingsFormatChosen = PostingsFormat.forName(postingsFormat);
|
||||
iwConf.setCodec(new Lucene70Codec() {
|
||||
iwConf.setCodec(new Lucene80Codec() {
|
||||
@Override
|
||||
public PostingsFormat getPostingsFormatForField(String field) {
|
||||
return postingsFormatChosen;
|
||||
|
|
|
|||
|
|
@ -57,7 +57,7 @@ public abstract class Codec implements NamedSPILoader.NamedSPI {
|
|||
}
|
||||
|
||||
// TODO: should we use this, or maybe a system property is better?
|
||||
static Codec defaultCodec = LOADER.lookup("Lucene70");
|
||||
static Codec defaultCodec = LOADER.lookup("Lucene80");
|
||||
}
|
||||
|
||||
private final String name;
|
||||
|
|
|
|||
|
|
@ -14,7 +14,7 @@
|
|||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
package org.apache.lucene.codecs.lucene70;
|
||||
package org.apache.lucene.codecs.lucene80;
|
||||
|
||||
import java.util.Objects;
|
||||
|
||||
|
|
@ -37,21 +37,23 @@ import org.apache.lucene.codecs.lucene50.Lucene50StoredFieldsFormat.Mode;
|
|||
import org.apache.lucene.codecs.lucene50.Lucene50TermVectorsFormat;
|
||||
import org.apache.lucene.codecs.lucene60.Lucene60FieldInfosFormat;
|
||||
import org.apache.lucene.codecs.lucene60.Lucene60PointsFormat;
|
||||
import org.apache.lucene.codecs.lucene70.Lucene70NormsFormat;
|
||||
import org.apache.lucene.codecs.lucene70.Lucene70SegmentInfoFormat;
|
||||
import org.apache.lucene.codecs.perfield.PerFieldDocValuesFormat;
|
||||
import org.apache.lucene.codecs.perfield.PerFieldPostingsFormat;
|
||||
|
||||
/**
|
||||
* Implements the Lucene 7.0 index format, with configurable per-field postings
|
||||
* Implements the Lucene 8.0 index format, with configurable per-field postings
|
||||
* and docvalues formats.
|
||||
* <p>
|
||||
* If you want to reuse functionality of this codec in another codec, extend
|
||||
* {@link FilterCodec}.
|
||||
*
|
||||
* @see org.apache.lucene.codecs.lucene70 package documentation for file format details.
|
||||
* @see org.apache.lucene.codecs.lucene80 package documentation for file format details.
|
||||
*
|
||||
* @lucene.experimental
|
||||
*/
|
||||
public class Lucene70Codec extends Codec {
|
||||
public class Lucene80Codec extends Codec {
|
||||
private final TermVectorsFormat vectorsFormat = new Lucene50TermVectorsFormat();
|
||||
private final FieldInfosFormat fieldInfosFormat = new Lucene60FieldInfosFormat();
|
||||
private final SegmentInfoFormat segmentInfosFormat = new Lucene70SegmentInfoFormat();
|
||||
|
|
@ -61,14 +63,14 @@ public class Lucene70Codec extends Codec {
|
|||
private final PostingsFormat postingsFormat = new PerFieldPostingsFormat() {
|
||||
@Override
|
||||
public PostingsFormat getPostingsFormatForField(String field) {
|
||||
return Lucene70Codec.this.getPostingsFormatForField(field);
|
||||
return Lucene80Codec.this.getPostingsFormatForField(field);
|
||||
}
|
||||
};
|
||||
|
||||
private final DocValuesFormat docValuesFormat = new PerFieldDocValuesFormat() {
|
||||
@Override
|
||||
public DocValuesFormat getDocValuesFormatForField(String field) {
|
||||
return Lucene70Codec.this.getDocValuesFormatForField(field);
|
||||
return Lucene80Codec.this.getDocValuesFormatForField(field);
|
||||
}
|
||||
};
|
||||
|
||||
|
|
@ -77,7 +79,7 @@ public class Lucene70Codec extends Codec {
|
|||
/**
|
||||
* Instantiates a new codec.
|
||||
*/
|
||||
public Lucene70Codec() {
|
||||
public Lucene80Codec() {
|
||||
this(Mode.BEST_SPEED);
|
||||
}
|
||||
|
||||
|
|
@ -87,8 +89,8 @@ public class Lucene70Codec extends Codec {
|
|||
* @param mode stored fields compression mode to use for newly
|
||||
* flushed/merged segments.
|
||||
*/
|
||||
public Lucene70Codec(Mode mode) {
|
||||
super("Lucene70");
|
||||
public Lucene80Codec(Mode mode) {
|
||||
super("Lucene80");
|
||||
this.storedFieldsFormat = new Lucene50StoredFieldsFormat(Objects.requireNonNull(mode));
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,409 @@
|
|||
/*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
* this work for additional information regarding copyright ownership.
|
||||
* The ASF licenses this file to You under the Apache License, Version 2.0
|
||||
* (the "License"); you may not use this file except in compliance with
|
||||
* the License. You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
/**
|
||||
* Lucene 8.0 file format.
|
||||
*
|
||||
* <h1>Apache Lucene - Index File Formats</h1>
|
||||
* <div>
|
||||
* <ul>
|
||||
* <li><a href="#Introduction">Introduction</a></li>
|
||||
* <li><a href="#Definitions">Definitions</a>
|
||||
* <ul>
|
||||
* <li><a href="#Inverted_Indexing">Inverted Indexing</a></li>
|
||||
* <li><a href="#Types_of_Fields">Types of Fields</a></li>
|
||||
* <li><a href="#Segments">Segments</a></li>
|
||||
* <li><a href="#Document_Numbers">Document Numbers</a></li>
|
||||
* </ul>
|
||||
* </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>
|
||||
* <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>
|
||||
* <h2>Introduction</h2>
|
||||
* <div>
|
||||
* <p>This document defines the index file formats used in this version of Lucene.
|
||||
* If you are using a different version of Lucene, please consult the copy of
|
||||
* <code>docs/</code> that was distributed with
|
||||
* the version you are using.</p>
|
||||
* <p>This document attempts to provide a high-level definition of the Apache
|
||||
* Lucene file formats.</p>
|
||||
* </div>
|
||||
* <a name="Definitions"></a>
|
||||
* <h2>Definitions</h2>
|
||||
* <div>
|
||||
* <p>The fundamental concepts in Lucene are index, document, field and term.</p>
|
||||
* <p>An index contains a sequence of documents.</p>
|
||||
* <ul>
|
||||
* <li>A document is a sequence of fields.</li>
|
||||
* <li>A field is a named sequence of terms.</li>
|
||||
* <li>A term is a sequence of bytes.</li>
|
||||
* </ul>
|
||||
* <p>The same sequence of bytes in two different fields is considered a different
|
||||
* term. Thus terms are represented as a pair: the string naming the field, and the
|
||||
* bytes within the field.</p>
|
||||
* <a name="Inverted_Indexing"></a>
|
||||
* <h3>Inverted Indexing</h3>
|
||||
* <p>The index stores statistics about terms in order to make term-based search
|
||||
* more efficient. Lucene's index falls into the family of indexes known as an
|
||||
* <i>inverted index.</i> This is because it can list, for a term, the documents
|
||||
* that contain it. This is the inverse of the natural relationship, in which
|
||||
* documents list terms.</p>
|
||||
* <a name="Types_of_Fields"></a>
|
||||
* <h3>Types of Fields</h3>
|
||||
* <p>In Lucene, fields may be <i>stored</i>, in which case their text is stored
|
||||
* in the index literally, in a non-inverted manner. Fields that are inverted are
|
||||
* called <i>indexed</i>. A field may be both stored and indexed.</p>
|
||||
* <p>The text of a field may be <i>tokenized</i> into terms to be indexed, or the
|
||||
* text of a field may be used literally as a term to be indexed. Most fields are
|
||||
* tokenized, but sometimes it is useful for certain identifier fields to be
|
||||
* indexed literally.</p>
|
||||
* <p>See the {@link org.apache.lucene.document.Field Field}
|
||||
* java docs for more information on Fields.</p>
|
||||
* <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.
|
||||
* Indexes evolve by:</p>
|
||||
* <ol>
|
||||
* <li>Creating new segments for newly added documents.</li>
|
||||
* <li>Merging existing segments.</li>
|
||||
* </ol>
|
||||
* <p>Searches may involve multiple segments and/or multiple indexes, each index
|
||||
* potentially composed of a set of segments.</p>
|
||||
* <a name="Document_Numbers"></a>
|
||||
* <h3>Document Numbers</h3>
|
||||
* <p>Internally, Lucene refers to documents by an integer <i>document number</i>.
|
||||
* The first document added to an index is numbered zero, and each subsequent
|
||||
* document added gets a number one greater than the previous.</p>
|
||||
* <p>Note that a document's number may change, so caution should be taken when
|
||||
* storing these numbers outside of Lucene. In particular, numbers may change in
|
||||
* the following situations:</p>
|
||||
* <ul>
|
||||
* <li>
|
||||
* <p>The numbers stored in each segment are unique only within the segment, and
|
||||
* must be converted before they can be used in a larger context. The standard
|
||||
* technique is to allocate each segment a range of values, based on the range of
|
||||
* numbers used in that segment. To convert a document number from a segment to an
|
||||
* external value, the segment's <i>base</i> document number is added. To convert
|
||||
* an external value back to a segment-specific value, the segment is identified
|
||||
* by the range that the external value is in, and the segment's base value is
|
||||
* subtracted. For example two five document segments might be combined, so that
|
||||
* the first segment has a base value of zero, and the second of five. Document
|
||||
* three from the second segment would have an external value of eight.</p>
|
||||
* </li>
|
||||
* <li>
|
||||
* <p>When documents are deleted, gaps are created in the numbering. These are
|
||||
* eventually removed as the index evolves through merging. Deleted documents are
|
||||
* dropped when segments are merged. A freshly-merged segment thus has no gaps in
|
||||
* its numbering.</p>
|
||||
* </li>
|
||||
* </ul>
|
||||
* </div>
|
||||
* <a name="Overview"></a>
|
||||
* <h2>Index Structure Overview</h2>
|
||||
* <div>
|
||||
* <p>Each segment index maintains the following:</p>
|
||||
* <ul>
|
||||
* <li>
|
||||
* {@link org.apache.lucene.codecs.lucene70.Lucene70SegmentInfoFormat Segment info}.
|
||||
* This contains metadata about a segment, such as the number of documents,
|
||||
* what files it uses,
|
||||
* </li>
|
||||
* <li>
|
||||
* {@link org.apache.lucene.codecs.lucene50.Lucene50FieldInfosFormat Field names}.
|
||||
* This contains the set of field names used in the index.
|
||||
* </li>
|
||||
* <li>
|
||||
* {@link org.apache.lucene.codecs.lucene50.Lucene50StoredFieldsFormat Stored Field values}.
|
||||
* This contains, for each document, a list of attribute-value pairs, where the attributes
|
||||
* are field names. These are used to store auxiliary information about the document, such as
|
||||
* its title, url, or an identifier to access a database. The set of stored fields are what is
|
||||
* returned for each hit when searching. This is keyed by document number.
|
||||
* </li>
|
||||
* <li>
|
||||
* {@link org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat Term dictionary}.
|
||||
* A dictionary containing all of the terms used in all of the
|
||||
* indexed fields of all of the documents. The dictionary also contains the number
|
||||
* of documents which contain the term, and pointers to the term's frequency and
|
||||
* proximity data.
|
||||
* </li>
|
||||
* <li>
|
||||
* {@link org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat Term Frequency data}.
|
||||
* For each term in the dictionary, the numbers of all the
|
||||
* documents that contain that term, and the frequency of the term in that
|
||||
* document, unless frequencies are omitted (IndexOptions.DOCS_ONLY)
|
||||
* </li>
|
||||
* <li>
|
||||
* {@link org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat Term Proximity data}.
|
||||
* For each term in the dictionary, the positions that the
|
||||
* term occurs in each document. Note that this will not exist if all fields in
|
||||
* all documents omit position data.
|
||||
* </li>
|
||||
* <li>
|
||||
* {@link org.apache.lucene.codecs.lucene70.Lucene70NormsFormat Normalization factors}.
|
||||
* For each field in each document, a value is stored
|
||||
* that is multiplied into the score for hits on that field.
|
||||
* </li>
|
||||
* <li>
|
||||
* {@link org.apache.lucene.codecs.lucene50.Lucene50TermVectorsFormat Term Vectors}.
|
||||
* For each field in each document, the term vector (sometimes
|
||||
* called document vector) may be stored. A term vector consists of term text and
|
||||
* term frequency. To add Term Vectors to your index see the
|
||||
* {@link org.apache.lucene.document.Field Field} constructors
|
||||
* </li>
|
||||
* <li>
|
||||
* {@link org.apache.lucene.codecs.lucene70.Lucene70DocValuesFormat Per-document values}.
|
||||
* Like stored values, these are also keyed by document
|
||||
* number, but are generally intended to be loaded into main memory for fast
|
||||
* access. Whereas stored values are generally intended for summary results from
|
||||
* searches, per-document values are useful for things like scoring factors.
|
||||
* </li>
|
||||
* <li>
|
||||
* {@link org.apache.lucene.codecs.lucene50.Lucene50LiveDocsFormat Live documents}.
|
||||
* An optional file indicating which documents are live.
|
||||
* </li>
|
||||
* <li>
|
||||
* {@link org.apache.lucene.codecs.lucene60.Lucene60PointsFormat Point values}.
|
||||
* Optional pair of files, recording dimensionally indexed fields, to enable fast
|
||||
* numeric range filtering and large numeric values like BigInteger and BigDecimal (1D)
|
||||
* and geographic shape intersection (2D, 3D).
|
||||
* </li>
|
||||
* </ul>
|
||||
* <p>Details on each of these are provided in their linked pages.</p>
|
||||
* </div>
|
||||
* <a name="File_Naming"></a>
|
||||
* <h2>File Naming</h2>
|
||||
* <div>
|
||||
* <p>All files belonging to a segment have the same name with varying extensions.
|
||||
* The extensions correspond to the different file formats described below. When
|
||||
* using the Compound File format (default for small segments) these files (except
|
||||
* for the Segment info file, the Lock file, and Deleted documents file) are collapsed
|
||||
* into a single .cfs file (see below for details)</p>
|
||||
* <p>Typically, all segments in an index are stored in a single directory,
|
||||
* although this is not required.</p>
|
||||
* <p>File names are never re-used. That is, when any file is saved
|
||||
* to the Directory it is given a never before used filename. This is achieved
|
||||
* using a simple generations approach. For example, the first segments file is
|
||||
* 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"></a>
|
||||
* <h2>Summary of File Extensions</h2>
|
||||
* <div>
|
||||
* <p>The following table summarizes the names and extensions of the files in
|
||||
* Lucene:</p>
|
||||
* <table cellspacing="1" cellpadding="4" summary="lucene filenames by extension">
|
||||
* <tr>
|
||||
* <th>Name</th>
|
||||
* <th>Extension</th>
|
||||
* <th>Brief Description</th>
|
||||
* </tr>
|
||||
* <tr>
|
||||
* <td>{@link org.apache.lucene.index.SegmentInfos Segments File}</td>
|
||||
* <td>segments_N</td>
|
||||
* <td>Stores information about a commit point</td>
|
||||
* </tr>
|
||||
* <tr>
|
||||
* <td><a href="#Lock_File">Lock File</a></td>
|
||||
* <td>write.lock</td>
|
||||
* <td>The Write lock prevents multiple IndexWriters from writing to the same
|
||||
* file.</td>
|
||||
* </tr>
|
||||
* <tr>
|
||||
* <td>{@link org.apache.lucene.codecs.lucene70.Lucene70SegmentInfoFormat Segment Info}</td>
|
||||
* <td>.si</td>
|
||||
* <td>Stores metadata about a segment</td>
|
||||
* </tr>
|
||||
* <tr>
|
||||
* <td>{@link org.apache.lucene.codecs.lucene50.Lucene50CompoundFormat Compound File}</td>
|
||||
* <td>.cfs, .cfe</td>
|
||||
* <td>An optional "virtual" file consisting of all the other index files for
|
||||
* systems that frequently run out of file handles.</td>
|
||||
* </tr>
|
||||
* <tr>
|
||||
* <td>{@link org.apache.lucene.codecs.lucene50.Lucene50FieldInfosFormat Fields}</td>
|
||||
* <td>.fnm</td>
|
||||
* <td>Stores information about the fields</td>
|
||||
* </tr>
|
||||
* <tr>
|
||||
* <td>{@link org.apache.lucene.codecs.lucene50.Lucene50StoredFieldsFormat Field Index}</td>
|
||||
* <td>.fdx</td>
|
||||
* <td>Contains pointers to field data</td>
|
||||
* </tr>
|
||||
* <tr>
|
||||
* <td>{@link org.apache.lucene.codecs.lucene50.Lucene50StoredFieldsFormat Field Data}</td>
|
||||
* <td>.fdt</td>
|
||||
* <td>The stored fields for documents</td>
|
||||
* </tr>
|
||||
* <tr>
|
||||
* <td>{@link org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat Term Dictionary}</td>
|
||||
* <td>.tim</td>
|
||||
* <td>The term dictionary, stores term info</td>
|
||||
* </tr>
|
||||
* <tr>
|
||||
* <td>{@link org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat Term Index}</td>
|
||||
* <td>.tip</td>
|
||||
* <td>The index into the Term Dictionary</td>
|
||||
* </tr>
|
||||
* <tr>
|
||||
* <td>{@link org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat Frequencies}</td>
|
||||
* <td>.doc</td>
|
||||
* <td>Contains the list of docs which contain each term along with frequency</td>
|
||||
* </tr>
|
||||
* <tr>
|
||||
* <td>{@link org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat Positions}</td>
|
||||
* <td>.pos</td>
|
||||
* <td>Stores position information about where a term occurs in the index</td>
|
||||
* </tr>
|
||||
* <tr>
|
||||
* <td>{@link org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat Payloads}</td>
|
||||
* <td>.pay</td>
|
||||
* <td>Stores additional per-position metadata information such as character offsets and user payloads</td>
|
||||
* </tr>
|
||||
* <tr>
|
||||
* <td>{@link org.apache.lucene.codecs.lucene70.Lucene70NormsFormat Norms}</td>
|
||||
* <td>.nvd, .nvm</td>
|
||||
* <td>Encodes length and boost factors for docs and fields</td>
|
||||
* </tr>
|
||||
* <tr>
|
||||
* <td>{@link org.apache.lucene.codecs.lucene70.Lucene70DocValuesFormat Per-Document Values}</td>
|
||||
* <td>.dvd, .dvm</td>
|
||||
* <td>Encodes additional scoring factors or other per-document information.</td>
|
||||
* </tr>
|
||||
* <tr>
|
||||
* <td>{@link org.apache.lucene.codecs.lucene50.Lucene50TermVectorsFormat Term Vector Index}</td>
|
||||
* <td>.tvx</td>
|
||||
* <td>Stores offset into the document data file</td>
|
||||
* </tr>
|
||||
* <tr>
|
||||
* <td>{@link org.apache.lucene.codecs.lucene50.Lucene50TermVectorsFormat Term Vector Data}</td>
|
||||
* <td>.tvd</td>
|
||||
* <td>Contains term vector data.</td>
|
||||
* </tr>
|
||||
* <tr>
|
||||
* <td>{@link org.apache.lucene.codecs.lucene50.Lucene50LiveDocsFormat Live Documents}</td>
|
||||
* <td>.liv</td>
|
||||
* <td>Info about what documents are live</td>
|
||||
* </tr>
|
||||
* <tr>
|
||||
* <td>{@link org.apache.lucene.codecs.lucene60.Lucene60PointsFormat Point values}</td>
|
||||
* <td>.dii, .dim</td>
|
||||
* <td>Holds indexed points, if any</td>
|
||||
* </tr>
|
||||
* </table>
|
||||
* </div>
|
||||
* <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.
|
||||
* <a name="History"></a>
|
||||
* <h2>History</h2>
|
||||
* <p>Compatibility notes are provided in this document, describing how file
|
||||
* formats have changed from prior versions:</p>
|
||||
* <ul>
|
||||
* <li>In version 2.1, the file format was changed to allow lock-less commits (ie,
|
||||
* no more commit lock). The change is fully backwards compatible: you can open a
|
||||
* pre-2.1 index for searching or adding/deleting of docs. When the new segments
|
||||
* file is saved (committed), it will be written in the new file format (meaning
|
||||
* no specific "upgrade" process is needed). But note that once a commit has
|
||||
* occurred, pre-2.1 Lucene will not be able to read the index.</li>
|
||||
* <li>In version 2.3, the file format was changed to allow segments to share a
|
||||
* single set of doc store (vectors & stored fields) files. This allows for
|
||||
* faster indexing in certain cases. The change is fully backwards compatible (in
|
||||
* the same way as the lock-less commits change in 2.1).</li>
|
||||
* <li>In version 2.4, Strings are now written as true UTF-8 byte sequence, not
|
||||
* Java's modified UTF-8. See <a href="http://issues.apache.org/jira/browse/LUCENE-510">
|
||||
* LUCENE-510</a> for details.</li>
|
||||
* <li>In version 2.9, an optional opaque Map<String,String> CommitUserData
|
||||
* may be passed to IndexWriter's commit methods (and later retrieved), which is
|
||||
* recorded in the segments_N file. See <a href="http://issues.apache.org/jira/browse/LUCENE-1382">
|
||||
* LUCENE-1382</a> for details. Also,
|
||||
* diagnostics were added to each segment written recording details about why it
|
||||
* was written (due to flush, merge; which OS/JRE was used; etc.). See issue
|
||||
* <a href="http://issues.apache.org/jira/browse/LUCENE-1654">LUCENE-1654</a> for details.</li>
|
||||
* <li>In version 3.0, compressed fields are no longer written to the index (they
|
||||
* can still be read, but on merge the new segment will write them, uncompressed).
|
||||
* See issue <a href="http://issues.apache.org/jira/browse/LUCENE-1960">LUCENE-1960</a>
|
||||
* for details.</li>
|
||||
* <li>In version 3.1, segments records the code version that created them. See
|
||||
* <a href="http://issues.apache.org/jira/browse/LUCENE-2720">LUCENE-2720</a> for details.
|
||||
* Additionally segments track explicitly whether or not they have term vectors.
|
||||
* See <a href="http://issues.apache.org/jira/browse/LUCENE-2811">LUCENE-2811</a>
|
||||
* for details.</li>
|
||||
* <li>In version 3.2, numeric fields are written as natively to stored fields
|
||||
* file, previously they were stored in text format only.</li>
|
||||
* <li>In version 3.4, fields can omit position data while still indexing term
|
||||
* frequencies.</li>
|
||||
* <li>In version 4.0, the format of the inverted index became extensible via
|
||||
* the {@link org.apache.lucene.codecs.Codec Codec} api. Fast per-document storage
|
||||
* ({@code DocValues}) was introduced. Normalization factors need no longer be a
|
||||
* single byte, they can be any {@link org.apache.lucene.index.NumericDocValues NumericDocValues}.
|
||||
* Terms need not be unicode strings, they can be any byte sequence. Term offsets
|
||||
* can optionally be indexed into the postings lists. Payloads can be stored in the
|
||||
* term vectors.</li>
|
||||
* <li>In version 4.1, the format of the postings list changed to use either
|
||||
* of FOR compression or variable-byte encoding, depending upon the frequency
|
||||
* of the term. Terms appearing only once were changed to inline directly into
|
||||
* the term dictionary. Stored fields are compressed by default. </li>
|
||||
* <li>In version 4.2, term vectors are compressed by default. DocValues has
|
||||
* a new multi-valued type (SortedSet), that can be used for faceting/grouping/joining
|
||||
* on multi-valued fields.</li>
|
||||
* <li>In version 4.5, DocValues were extended to explicitly represent missing values.</li>
|
||||
* <li>In version 4.6, FieldInfos were extended to support per-field DocValues generation, to
|
||||
* allow updating NumericDocValues fields.</li>
|
||||
* <li>In version 4.8, checksum footers were added to the end of each index file
|
||||
* for improved data integrity. Specifically, the last 8 bytes of every index file
|
||||
* contain the zlib-crc32 checksum of the file.</li>
|
||||
* <li>In version 4.9, DocValues has a new multi-valued numeric type (SortedNumeric)
|
||||
* that is suitable for faceting/sorting/analytics.
|
||||
* <li>In version 5.4, DocValues have been improved to store more information on disk:
|
||||
* addresses for binary fields and ord indexes for multi-valued fields.
|
||||
* <li>In version 6.0, Points were added, for multi-dimensional range/distance search.
|
||||
* <li>In version 6.2, new Segment info format that reads/writes the index sort, to support index sorting.
|
||||
* <li>In version 7.0, DocValues have been improved to better support sparse doc values
|
||||
* thanks to an iterator API.</li>
|
||||
* <li>In version 8.0, postings have been enhanced to record, for each block of
|
||||
* doc ids, the (term freq, normalization factor) pairs that may trigger the
|
||||
* maximum score of the block. This information is recorded alongside skip data
|
||||
* in order to be able to skip blocks of doc ids if they may not produce high
|
||||
* enough scores.</li>
|
||||
* </ul>
|
||||
* <a name="Limitations"></a>
|
||||
* <h2>Limitations</h2>
|
||||
* <div>
|
||||
* <p>Lucene uses a Java <code>int</code> to refer to
|
||||
* document numbers, and the index file format uses an <code>Int32</code>
|
||||
* on-disk to store document numbers. This is a limitation
|
||||
* of both the index file format and the current implementation. Eventually these
|
||||
* should be replaced with either <code>UInt64</code> values, or
|
||||
* better yet, {@link org.apache.lucene.store.DataOutput#writeVInt VInt} values which have no limit.</p>
|
||||
* </div>
|
||||
*/
|
||||
package org.apache.lucene.codecs.lucene80;
|
||||
|
|
@ -13,4 +13,4 @@
|
|||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
org.apache.lucene.codecs.lucene70.Lucene70Codec
|
||||
org.apache.lucene.codecs.lucene80.Lucene80Codec
|
||||
|
|
|
|||
|
|
@ -19,7 +19,7 @@ package org.apache.lucene.codecs.lucene50;
|
|||
|
||||
import org.apache.lucene.codecs.Codec;
|
||||
import org.apache.lucene.codecs.lucene50.Lucene50StoredFieldsFormat.Mode;
|
||||
import org.apache.lucene.codecs.lucene70.Lucene70Codec;
|
||||
import org.apache.lucene.codecs.lucene80.Lucene80Codec;
|
||||
import org.apache.lucene.document.Document;
|
||||
import org.apache.lucene.document.StoredField;
|
||||
import org.apache.lucene.index.BaseStoredFieldsFormatTestCase;
|
||||
|
|
@ -33,7 +33,7 @@ import com.carrotsearch.randomizedtesting.generators.RandomPicks;
|
|||
public class TestLucene50StoredFieldsFormatHighCompression extends BaseStoredFieldsFormatTestCase {
|
||||
@Override
|
||||
protected Codec getCodec() {
|
||||
return new Lucene70Codec(Mode.BEST_COMPRESSION);
|
||||
return new Lucene80Codec(Mode.BEST_COMPRESSION);
|
||||
}
|
||||
|
||||
/**
|
||||
|
|
@ -44,7 +44,7 @@ public class TestLucene50StoredFieldsFormatHighCompression extends BaseStoredFie
|
|||
Directory dir = newDirectory();
|
||||
for (int i = 0; i < 10; i++) {
|
||||
IndexWriterConfig iwc = newIndexWriterConfig();
|
||||
iwc.setCodec(new Lucene70Codec(RandomPicks.randomFrom(random(), Mode.values())));
|
||||
iwc.setCodec(new Lucene80Codec(RandomPicks.randomFrom(random(), Mode.values())));
|
||||
IndexWriter iw = new IndexWriter(dir, newIndexWriterConfig());
|
||||
Document doc = new Document();
|
||||
doc.add(new StoredField("field1", "value1"));
|
||||
|
|
@ -71,7 +71,7 @@ public class TestLucene50StoredFieldsFormatHighCompression extends BaseStoredFie
|
|||
|
||||
public void testInvalidOptions() throws Exception {
|
||||
expectThrows(NullPointerException.class, () -> {
|
||||
new Lucene70Codec(null);
|
||||
new Lucene80Codec(null);
|
||||
});
|
||||
|
||||
expectThrows(NullPointerException.class, () -> {
|
||||
|
|
|
|||
|
|
@ -18,14 +18,14 @@ package org.apache.lucene.codecs.lucene70;
|
|||
|
||||
|
||||
import org.apache.lucene.codecs.Codec;
|
||||
import org.apache.lucene.codecs.lucene70.Lucene70Codec;
|
||||
import org.apache.lucene.codecs.lucene80.Lucene80Codec;
|
||||
import org.apache.lucene.index.BaseNormsFormatTestCase;
|
||||
|
||||
/**
|
||||
* Tests Lucene70NormsFormat
|
||||
*/
|
||||
public class TestLucene70NormsFormat extends BaseNormsFormatTestCase {
|
||||
private final Codec codec = new Lucene70Codec();
|
||||
private final Codec codec = new Lucene80Codec();
|
||||
|
||||
@Override
|
||||
protected Codec getCodec() {
|
||||
|
|
|
|||
|
|
@ -135,6 +135,6 @@ public class Test2BPoints extends LuceneTestCase {
|
|||
}
|
||||
|
||||
private static Codec getCodec() {
|
||||
return Codec.forName("Lucene70");
|
||||
return Codec.forName("Lucene80");
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -393,11 +393,11 @@ public class TestPointValues extends LuceneTestCase {
|
|||
dir.close();
|
||||
}
|
||||
|
||||
// Write point values, one segment with Lucene70, another with SimpleText, then forceMerge with SimpleText
|
||||
// Write point values, one segment with Lucene80, another with SimpleText, then forceMerge with SimpleText
|
||||
public void testDifferentCodecs1() throws Exception {
|
||||
Directory dir = newDirectory();
|
||||
IndexWriterConfig iwc = new IndexWriterConfig(new MockAnalyzer(random()));
|
||||
iwc.setCodec(Codec.forName("Lucene70"));
|
||||
iwc.setCodec(Codec.forName("Lucene80"));
|
||||
IndexWriter w = new IndexWriter(dir, iwc);
|
||||
Document doc = new Document();
|
||||
doc.add(new IntPoint("int", 1));
|
||||
|
|
@ -416,7 +416,7 @@ public class TestPointValues extends LuceneTestCase {
|
|||
dir.close();
|
||||
}
|
||||
|
||||
// Write point values, one segment with Lucene70, another with SimpleText, then forceMerge with Lucene70
|
||||
// Write point values, one segment with Lucene80, another with SimpleText, then forceMerge with Lucene80
|
||||
public void testDifferentCodecs2() throws Exception {
|
||||
Directory dir = newDirectory();
|
||||
IndexWriterConfig iwc = new IndexWriterConfig(new MockAnalyzer(random()));
|
||||
|
|
@ -428,7 +428,7 @@ public class TestPointValues extends LuceneTestCase {
|
|||
w.close();
|
||||
|
||||
iwc = new IndexWriterConfig(new MockAnalyzer(random()));
|
||||
iwc.setCodec(Codec.forName("Lucene70"));
|
||||
iwc.setCodec(Codec.forName("Lucene80"));
|
||||
w = new IndexWriter(dir, iwc);
|
||||
doc = new Document();
|
||||
doc.add(new IntPoint("int", 1));
|
||||
|
|
|
|||
|
|
@ -96,7 +96,7 @@ public class TestBoolean2 extends LuceneTestCase {
|
|||
|
||||
IndexWriterConfig iwc = newIndexWriterConfig(new MockAnalyzer(random()));
|
||||
// randomized codecs are sometimes too costly for this test:
|
||||
iwc.setCodec(Codec.forName("Lucene70"));
|
||||
iwc.setCodec(Codec.forName("Lucene80"));
|
||||
iwc.setMergePolicy(newLogMergePolicy());
|
||||
RandomIndexWriter writer= new RandomIndexWriter(random(), directory, iwc);
|
||||
// we'll make a ton of docs, disable store/norms/vectors
|
||||
|
|
@ -141,7 +141,7 @@ public class TestBoolean2 extends LuceneTestCase {
|
|||
iwc = newIndexWriterConfig(new MockAnalyzer(random()));
|
||||
// we need docID order to be preserved:
|
||||
// randomized codecs are sometimes too costly for this test:
|
||||
iwc.setCodec(Codec.forName("Lucene70"));
|
||||
iwc.setCodec(Codec.forName("Lucene80"));
|
||||
iwc.setMergePolicy(newLogMergePolicy());
|
||||
try (IndexWriter w = new IndexWriter(singleSegmentDirectory, iwc)) {
|
||||
w.forceMerge(1, true);
|
||||
|
|
@ -167,7 +167,7 @@ public class TestBoolean2 extends LuceneTestCase {
|
|||
|
||||
iwc = newIndexWriterConfig(new MockAnalyzer(random()));
|
||||
// randomized codecs are sometimes too costly for this test:
|
||||
iwc.setCodec(Codec.forName("Lucene70"));
|
||||
iwc.setCodec(Codec.forName("Lucene80"));
|
||||
RandomIndexWriter w = new RandomIndexWriter(random(), dir2, iwc);
|
||||
w.addIndexes(copy);
|
||||
copy.close();
|
||||
|
|
@ -179,7 +179,7 @@ public class TestBoolean2 extends LuceneTestCase {
|
|||
iwc = newIndexWriterConfig(new MockAnalyzer(random()));
|
||||
iwc.setMaxBufferedDocs(TestUtil.nextInt(random(), 50, 1000));
|
||||
// randomized codecs are sometimes too costly for this test:
|
||||
iwc.setCodec(Codec.forName("Lucene70"));
|
||||
iwc.setCodec(Codec.forName("Lucene80"));
|
||||
RandomIndexWriter w = new RandomIndexWriter(random(), dir2, iwc);
|
||||
|
||||
doc = new Document();
|
||||
|
|
|
|||
|
|
@ -1161,14 +1161,14 @@ public class TestPointQueries extends LuceneTestCase {
|
|||
}
|
||||
|
||||
private static Codec getCodec() {
|
||||
if (Codec.getDefault().getName().equals("Lucene70")) {
|
||||
if (Codec.getDefault().getName().equals("Lucene80")) {
|
||||
int maxPointsInLeafNode = TestUtil.nextInt(random(), 16, 2048);
|
||||
double maxMBSortInHeap = 5.0 + (3*random().nextDouble());
|
||||
if (VERBOSE) {
|
||||
System.out.println("TEST: using Lucene60PointsFormat with maxPointsInLeafNode=" + maxPointsInLeafNode + " and maxMBSortInHeap=" + maxMBSortInHeap);
|
||||
}
|
||||
|
||||
return new FilterCodec("Lucene70", Codec.getDefault()) {
|
||||
return new FilterCodec("Lucene80", Codec.getDefault()) {
|
||||
@Override
|
||||
public PointsFormat pointsFormat() {
|
||||
return new PointsFormat() {
|
||||
|
|
|
|||
|
|
@ -234,7 +234,7 @@ public class TestFloatPointNearestNeighbor extends LuceneTestCase {
|
|||
|
||||
private IndexWriterConfig getIndexWriterConfig() {
|
||||
IndexWriterConfig iwc = newIndexWriterConfig();
|
||||
iwc.setCodec(Codec.forName("Lucene70"));
|
||||
iwc.setCodec(Codec.forName("Lucene80"));
|
||||
return iwc;
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -247,7 +247,7 @@ public class TestNearest extends LuceneTestCase {
|
|||
|
||||
private IndexWriterConfig getIndexWriterConfig() {
|
||||
IndexWriterConfig iwc = newIndexWriterConfig();
|
||||
iwc.setCodec(Codec.forName("Lucene70"));
|
||||
iwc.setCodec(Codec.forName("Lucene80"));
|
||||
return iwc;
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -86,14 +86,14 @@ import com.carrotsearch.randomizedtesting.generators.RandomNumbers;
|
|||
public class TestGeo3DPoint extends LuceneTestCase {
|
||||
|
||||
private static Codec getCodec() {
|
||||
if (Codec.getDefault().getName().equals("Lucene70")) {
|
||||
if (Codec.getDefault().getName().equals("Lucene80")) {
|
||||
int maxPointsInLeafNode = TestUtil.nextInt(random(), 16, 2048);
|
||||
double maxMBSortInHeap = 3.0 + (3*random().nextDouble());
|
||||
if (VERBOSE) {
|
||||
System.out.println("TEST: using Lucene60PointsFormat with maxPointsInLeafNode=" + maxPointsInLeafNode + " and maxMBSortInHeap=" + maxMBSortInHeap);
|
||||
}
|
||||
|
||||
return new FilterCodec("Lucene70", Codec.getDefault()) {
|
||||
return new FilterCodec("Lucene80", Codec.getDefault()) {
|
||||
@Override
|
||||
public PointsFormat pointsFormat() {
|
||||
return new PointsFormat() {
|
||||
|
|
|
|||
|
|
@ -39,7 +39,7 @@ import org.apache.lucene.analysis.tokenattributes.PayloadAttribute;
|
|||
import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
|
||||
import org.apache.lucene.codecs.Codec;
|
||||
import org.apache.lucene.codecs.PostingsFormat;
|
||||
import org.apache.lucene.codecs.lucene70.Lucene70Codec;
|
||||
import org.apache.lucene.codecs.lucene80.Lucene80Codec;
|
||||
import org.apache.lucene.document.Document;
|
||||
import org.apache.lucene.document.Field;
|
||||
import org.apache.lucene.document.IntPoint;
|
||||
|
|
@ -884,7 +884,7 @@ public class TestSuggestField extends LuceneTestCase {
|
|||
static IndexWriterConfig iwcWithSuggestField(Analyzer analyzer, final Set<String> suggestFields) {
|
||||
IndexWriterConfig iwc = newIndexWriterConfig(random(), analyzer);
|
||||
iwc.setMergePolicy(newLogMergePolicy());
|
||||
Codec filterCodec = new Lucene70Codec() {
|
||||
Codec filterCodec = new Lucene80Codec() {
|
||||
PostingsFormat postingsFormat = new Completion50PostingsFormat();
|
||||
|
||||
@Override
|
||||
|
|
|
|||
|
|
@ -1252,7 +1252,7 @@ public abstract class BaseGeoPointTestCase extends LuceneTestCase {
|
|||
// Else seeds may not reproduce:
|
||||
iwc.setMergeScheduler(new SerialMergeScheduler());
|
||||
int pointsInLeaf = 2 + random().nextInt(4);
|
||||
iwc.setCodec(new FilterCodec("Lucene70", TestUtil.getDefaultCodec()) {
|
||||
iwc.setCodec(new FilterCodec("Lucene80", TestUtil.getDefaultCodec()) {
|
||||
@Override
|
||||
public PointsFormat pointsFormat() {
|
||||
return new PointsFormat() {
|
||||
|
|
|
|||
|
|
@ -16,6 +16,17 @@
|
|||
*/
|
||||
package org.apache.lucene.util;
|
||||
|
||||
import static org.apache.lucene.util.LuceneTestCase.INFOSTREAM;
|
||||
import static org.apache.lucene.util.LuceneTestCase.TEST_CODEC;
|
||||
import static org.apache.lucene.util.LuceneTestCase.TEST_DOCVALUESFORMAT;
|
||||
import static org.apache.lucene.util.LuceneTestCase.TEST_POSTINGSFORMAT;
|
||||
import static org.apache.lucene.util.LuceneTestCase.VERBOSE;
|
||||
import static org.apache.lucene.util.LuceneTestCase.assumeFalse;
|
||||
import static org.apache.lucene.util.LuceneTestCase.localeForLanguageTag;
|
||||
import static org.apache.lucene.util.LuceneTestCase.random;
|
||||
import static org.apache.lucene.util.LuceneTestCase.randomLocale;
|
||||
import static org.apache.lucene.util.LuceneTestCase.randomTimeZone;
|
||||
|
||||
import java.io.PrintStream;
|
||||
import java.util.Arrays;
|
||||
import java.util.HashSet;
|
||||
|
|
@ -32,31 +43,20 @@ import org.apache.lucene.codecs.asserting.AssertingPostingsFormat;
|
|||
import org.apache.lucene.codecs.cheapbastard.CheapBastardCodec;
|
||||
import org.apache.lucene.codecs.compressing.CompressingCodec;
|
||||
import org.apache.lucene.codecs.lucene50.Lucene50StoredFieldsFormat;
|
||||
import org.apache.lucene.codecs.lucene70.Lucene70Codec;
|
||||
import org.apache.lucene.codecs.lucene80.Lucene80Codec;
|
||||
import org.apache.lucene.codecs.mockrandom.MockRandomPostingsFormat;
|
||||
import org.apache.lucene.codecs.simpletext.SimpleTextCodec;
|
||||
import org.apache.lucene.index.RandomCodec;
|
||||
import org.apache.lucene.search.similarities.AssertingSimilarity;
|
||||
import org.apache.lucene.search.similarities.RandomSimilarity;
|
||||
import org.apache.lucene.search.similarities.Similarity;
|
||||
import org.apache.lucene.util.LuceneTestCase.LiveIWCFlushMode;
|
||||
import org.apache.lucene.util.LuceneTestCase.SuppressCodecs;
|
||||
import org.junit.internal.AssumptionViolatedException;
|
||||
|
||||
import com.carrotsearch.randomizedtesting.RandomizedContext;
|
||||
import com.carrotsearch.randomizedtesting.generators.RandomPicks;
|
||||
|
||||
import static org.apache.lucene.util.LuceneTestCase.INFOSTREAM;
|
||||
import static org.apache.lucene.util.LuceneTestCase.LiveIWCFlushMode;
|
||||
import static org.apache.lucene.util.LuceneTestCase.TEST_CODEC;
|
||||
import static org.apache.lucene.util.LuceneTestCase.TEST_DOCVALUESFORMAT;
|
||||
import static org.apache.lucene.util.LuceneTestCase.TEST_POSTINGSFORMAT;
|
||||
import static org.apache.lucene.util.LuceneTestCase.VERBOSE;
|
||||
import static org.apache.lucene.util.LuceneTestCase.assumeFalse;
|
||||
import static org.apache.lucene.util.LuceneTestCase.localeForLanguageTag;
|
||||
import static org.apache.lucene.util.LuceneTestCase.random;
|
||||
import static org.apache.lucene.util.LuceneTestCase.randomLocale;
|
||||
import static org.apache.lucene.util.LuceneTestCase.randomTimeZone;
|
||||
|
||||
/**
|
||||
* Setup and restore suite-level environment (fine grained junk that
|
||||
* doesn't fit anywhere else).
|
||||
|
|
@ -188,8 +188,8 @@ final class TestRuleSetupAndRestoreClassEnv extends AbstractBeforeAfterRule {
|
|||
codec = new AssertingCodec();
|
||||
} else if ("Compressing".equals(TEST_CODEC) || ("random".equals(TEST_CODEC) && randomVal == 6 && !shouldAvoidCodec("Compressing"))) {
|
||||
codec = CompressingCodec.randomInstance(random);
|
||||
} else if ("Lucene70".equals(TEST_CODEC) || ("random".equals(TEST_CODEC) && randomVal == 5 && !shouldAvoidCodec("Lucene70"))) {
|
||||
codec = new Lucene70Codec(RandomPicks.randomFrom(random, Lucene50StoredFieldsFormat.Mode.values()));
|
||||
} else if ("Lucene80".equals(TEST_CODEC) || ("random".equals(TEST_CODEC) && randomVal == 5 && !shouldAvoidCodec("Lucene80"))) {
|
||||
codec = new Lucene80Codec(RandomPicks.randomFrom(random, Lucene50StoredFieldsFormat.Mode.values()));
|
||||
} else if (!"random".equals(TEST_CODEC)) {
|
||||
codec = Codec.forName(TEST_CODEC);
|
||||
} else if ("random".equals(TEST_POSTINGSFORMAT)) {
|
||||
|
|
|
|||
|
|
@ -53,8 +53,8 @@ import org.apache.lucene.codecs.asserting.AssertingCodec;
|
|||
import org.apache.lucene.codecs.blockterms.LuceneFixedGap;
|
||||
import org.apache.lucene.codecs.blocktreeords.BlockTreeOrdsPostingsFormat;
|
||||
import org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat;
|
||||
import org.apache.lucene.codecs.lucene70.Lucene70Codec;
|
||||
import org.apache.lucene.codecs.lucene70.Lucene70DocValuesFormat;
|
||||
import org.apache.lucene.codecs.lucene80.Lucene80Codec;
|
||||
import org.apache.lucene.codecs.perfield.PerFieldDocValuesFormat;
|
||||
import org.apache.lucene.codecs.perfield.PerFieldPostingsFormat;
|
||||
import org.apache.lucene.document.BinaryDocValuesField;
|
||||
|
|
@ -914,7 +914,7 @@ public final class TestUtil {
|
|||
* This may be different than {@link Codec#getDefault()} because that is randomized.
|
||||
*/
|
||||
public static Codec getDefaultCodec() {
|
||||
return new Lucene70Codec();
|
||||
return new Lucene80Codec();
|
||||
}
|
||||
|
||||
/**
|
||||
|
|
|
|||
|
|
@ -24,7 +24,7 @@ import org.apache.lucene.codecs.Codec;
|
|||
import org.apache.lucene.codecs.DocValuesFormat;
|
||||
import org.apache.lucene.codecs.PostingsFormat;
|
||||
import org.apache.lucene.codecs.lucene50.Lucene50StoredFieldsFormat.Mode;
|
||||
import org.apache.lucene.codecs.lucene70.Lucene70Codec;
|
||||
import org.apache.lucene.codecs.lucene80.Lucene80Codec;
|
||||
import org.apache.solr.common.SolrException.ErrorCode;
|
||||
import org.apache.solr.common.SolrException;
|
||||
import org.apache.solr.common.util.NamedList;
|
||||
|
|
@ -91,7 +91,7 @@ public class SchemaCodecFactory extends CodecFactory implements SolrCoreAware {
|
|||
compressionMode = SOLR_DEFAULT_COMPRESSION_MODE;
|
||||
log.debug("Using default compressionMode: " + compressionMode);
|
||||
}
|
||||
codec = new Lucene70Codec(compressionMode) {
|
||||
codec = new Lucene80Codec(compressionMode) {
|
||||
@Override
|
||||
public PostingsFormat getPostingsFormatForField(String field) {
|
||||
final SchemaField schemaField = core.getLatestSchema().getFieldOrNull(field);
|
||||
|
|
|
|||
|
|
@ -19,7 +19,7 @@
|
|||
<fieldType name="string_direct" class="solr.StrField" postingsFormat="Direct" docValuesFormat="Direct"/>
|
||||
<fieldType name="string_standard" class="solr.StrField" postingsFormat="Lucene50"/>
|
||||
|
||||
<fieldType name="string_disk" class="solr.StrField" docValuesFormat="Lucene70"/>
|
||||
<fieldType name="string_disk" class="solr.StrField" docValuesFormat="Lucene80"/>
|
||||
|
||||
<fieldType name="string" class="solr.StrField"/>
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue