org.trypticon.luceneupgrader.lucene6.internal.lucene.codecs.lucene60.Lucene60PointsFormat Maven / Gradle / Ivy
/*
* 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.trypticon.luceneupgrader.lucene6.internal.lucene.codecs.lucene60;
import java.io.IOException;
import org.trypticon.luceneupgrader.lucene6.internal.lucene.codecs.CodecUtil;
import org.trypticon.luceneupgrader.lucene6.internal.lucene.codecs.PointsFormat;
import org.trypticon.luceneupgrader.lucene6.internal.lucene.codecs.PointsReader;
import org.trypticon.luceneupgrader.lucene6.internal.lucene.codecs.PointsWriter;
import org.trypticon.luceneupgrader.lucene6.internal.lucene.index.SegmentReadState;
import org.trypticon.luceneupgrader.lucene6.internal.lucene.index.SegmentWriteState;
/**
* Lucene 6.0 point format, which encodes dimensional values in a block KD-tree structure
* for fast 1D range and N dimesional shape intersection filtering.
* See this paper for details.
*
* This data structure is written as a series of blocks on disk, with an in-memory perfectly balanced
* binary tree of split values referencing those blocks at the leaves.
*
*
The .dim file has both blocks and the index split
* values, for each field. The file starts with {@link CodecUtil#writeIndexHeader}.
*
*
The blocks are written like this:
*
*
* - count (vInt)
*
- delta-docID (vInt) count (delta coded docIDs, in sorted order)
*
- packedValuecount (the
byte[] value of each dimension packed into a single byte[])
*
*
* After all blocks for a field are written, then the index is written:
*
* - numDims (vInt)
*
- maxPointsInLeafNode (vInt)
*
- bytesPerDim (vInt)
*
- count (vInt)
*
- packed index (byte[])
*
*
* The packed index uses hierarchical delta and prefix coding to compactly encode the file pointer for
* all leaf blocks, once the tree is traversed, as well as the split dimension and split value for each
* inner node of the tree.
*
*
After all fields blocks + index data are written, {@link CodecUtil#writeFooter} writes the checksum.
*
*
The .dii file records the file pointer in the .dim file where each field's
* index data was written. It starts with {@link CodecUtil#writeIndexHeader}, then has:
*
*
* - fieldCount (vInt)
*
- (fieldNumber (vInt), fieldFilePointer (vLong))fieldCount
*
*
* After all fields blocks + index data are written, {@link CodecUtil#writeFooter} writes the checksum.
*
* @lucene.experimental
*/
public final class Lucene60PointsFormat extends PointsFormat {
static final String DATA_CODEC_NAME = "Lucene60PointsFormatData";
static final String META_CODEC_NAME = "Lucene60PointsFormatMeta";
/**
* Filename extension for the leaf blocks
*/
public static final String DATA_EXTENSION = "dim";
/**
* Filename extension for the index per field
*/
public static final String INDEX_EXTENSION = "dii";
static final int DATA_VERSION_START = 0;
static final int DATA_VERSION_CURRENT = DATA_VERSION_START;
static final int INDEX_VERSION_START = 0;
static final int INDEX_VERSION_CURRENT = INDEX_VERSION_START;
/** Sole constructor */
public Lucene60PointsFormat() {
}
@Override
public PointsWriter fieldsWriter(SegmentWriteState state) throws IOException {
return new Lucene60PointsWriter(state);
}
@Override
public PointsReader fieldsReader(SegmentReadState state) throws IOException {
return new Lucene60PointsReader(state);
}
}