All Downloads are FREE. Search and download functionalities are using the official Maven repository.

org.apache.lucene.codecs.lucene86.Lucene86SegmentInfoFormat 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.apache.lucene.codecs.lucene86;

import java.io.IOException;
import java.util.Map;
import java.util.Set;

import org.apache.lucene.codecs.CodecUtil;
import org.apache.lucene.codecs.SegmentInfoFormat;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexFileNames;
import org.apache.lucene.index.IndexSorter;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.SegmentInfo;
import org.apache.lucene.index.SegmentInfos;
import org.apache.lucene.index.SortFieldProvider;
import org.apache.lucene.search.Sort;
import org.apache.lucene.search.SortField;
import org.apache.lucene.store.ChecksumIndexInput;
import org.apache.lucene.store.DataInput;
import org.apache.lucene.store.DataOutput;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.IOContext;
import org.apache.lucene.store.IndexOutput;
import org.apache.lucene.util.Version;

/**
 * Lucene 8.6 Segment info format.
 * 

* Files: *

    *
  • .si: Header, SegVersion, SegSize, IsCompoundFile, Diagnostics, Files, Attributes, IndexSort, Footer *
* Data types: *
    *
  • Header --> {@link CodecUtil#writeIndexHeader IndexHeader}
  • *
  • SegSize --> {@link DataOutput#writeInt Int32}
  • *
  • SegVersion --> {@link DataOutput#writeString String}
  • *
  • SegMinVersion --> {@link DataOutput#writeString String}
  • *
  • Files --> {@link DataOutput#writeSetOfStrings Set<String>}
  • *
  • Diagnostics,Attributes --> {@link DataOutput#writeMapOfStrings Map<String,String>}
  • *
  • IsCompoundFile --> {@link DataOutput#writeByte Int8}
  • *
  • IndexSort --> {@link DataOutput#writeVInt Int32} count, followed by {@code count} SortField
  • *
  • SortField --> {@link DataOutput#writeString String} sort class, followed by a per-sort bytestream * (see {@link SortFieldProvider#readSortField(DataInput)}) *
  • Footer --> {@link CodecUtil#writeFooter CodecFooter}
  • *
* Field Descriptions: *
    *
  • SegVersion is the code version that created the segment.
  • *
  • SegMinVersion is the minimum code version that contributed documents to the segment.
  • *
  • SegSize is the number of documents contained in the segment index.
  • *
  • IsCompoundFile records whether the segment is written as a compound file or * not. If this is -1, the segment is not a compound file. If it is 1, the segment * is a compound file.
  • *
  • The Diagnostics Map is privately written by {@link IndexWriter}, as a debugging aid, * for each segment it creates. It includes metadata like the current Lucene * version, OS, Java version, why the segment was created (merge, flush, * addIndexes), etc.
  • *
  • Files is a list of files referred to by this segment.
  • *
* * @see SegmentInfos * @lucene.experimental */ public class Lucene86SegmentInfoFormat extends SegmentInfoFormat { /** Sole constructor. */ public Lucene86SegmentInfoFormat() { } @Override public SegmentInfo read(Directory dir, String segment, byte[] segmentID, IOContext context) throws IOException { final String fileName = IndexFileNames.segmentFileName(segment, "", SI_EXTENSION); try (ChecksumIndexInput input = dir.openChecksumInput(fileName, context)) { Throwable priorE = null; SegmentInfo si = null; try { int format = CodecUtil.checkIndexHeader(input, CODEC_NAME, VERSION_START, VERSION_CURRENT, segmentID, ""); final Version version = Version.fromBits(input.readInt(), input.readInt(), input.readInt()); byte hasMinVersion = input.readByte(); final Version minVersion; switch (hasMinVersion) { case 0: minVersion = null; break; case 1: minVersion = Version.fromBits(input.readInt(), input.readInt(), input.readInt()); break; default: throw new CorruptIndexException("Illegal boolean value " + hasMinVersion, input); } final int docCount = input.readInt(); if (docCount < 0) { throw new CorruptIndexException("invalid docCount: " + docCount, input); } final boolean isCompoundFile = input.readByte() == SegmentInfo.YES; final Map diagnostics = input.readMapOfStrings(); final Set files = input.readSetOfStrings(); final Map attributes = input.readMapOfStrings(); int numSortFields = input.readVInt(); Sort indexSort; if (numSortFields > 0) { SortField[] sortFields = new SortField[numSortFields]; for(int i=0;i= 7 but got: " + version.major + " segment=" + si); } // Write the Lucene version that created this segment, since 3.1 output.writeInt(version.major); output.writeInt(version.minor); output.writeInt(version.bugfix); // Write the min Lucene version that contributed docs to the segment, since 7.0 if (si.getMinVersion() != null) { output.writeByte((byte) 1); Version minVersion = si.getMinVersion(); output.writeInt(minVersion.major); output.writeInt(minVersion.minor); output.writeInt(minVersion.bugfix); } else { output.writeByte((byte) 0); } assert version.prerelease == 0; output.writeInt(si.maxDoc()); output.writeByte((byte) (si.getUseCompoundFile() ? SegmentInfo.YES : SegmentInfo.NO)); output.writeMapOfStrings(si.getDiagnostics()); Set files = si.files(); for (String file : files) { if (!IndexFileNames.parseSegmentName(file).equals(si.name)) { throw new IllegalArgumentException("invalid files: expected segment=" + si.name + ", got=" + files); } } output.writeSetOfStrings(files); output.writeMapOfStrings(si.getAttributes()); Sort indexSort = si.getIndexSort(); int numSortFields = indexSort == null ? 0 : indexSort.getSort().length; output.writeVInt(numSortFields); for (int i = 0; i < numSortFields; ++i) { SortField sortField = indexSort.getSort()[i]; IndexSorter sorter = sortField.getIndexSorter(); if (sorter == null) { throw new IllegalArgumentException("cannot serialize SortField " + sortField); } output.writeString(sorter.getProviderName()); SortFieldProvider.write(sortField, output); } CodecUtil.writeFooter(output); } } /** File extension used to store {@link SegmentInfo}. */ public final static String SI_EXTENSION = "si"; static final String CODEC_NAME = "Lucene86SegmentInfo"; static final int VERSION_START = 0; static final int VERSION_CURRENT = VERSION_START; }




© 2015 - 2025 Weber Informatics LLC | Privacy Policy