
org.apache.lucene.codecs.lucene40.Lucene40DocValuesFormat Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of oak-lucene Show documentation
Show all versions of oak-lucene Show documentation
Oak Lucene integration subproject
/*
* COPIED FROM APACHE LUCENE 4.7.2
*
* Git URL: [email protected]:apache/lucene.git, tag: releases/lucene-solr/4.7.2, path: lucene/core/src/java
*
* (see https://issues.apache.org/jira/browse/OAK-10786 for details)
*/
package org.apache.lucene.codecs.lucene40;
/*
* 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.
*/
import java.io.IOException;
import org.apache.lucene.codecs.CodecUtil;
import org.apache.lucene.codecs.DocValuesConsumer;
import org.apache.lucene.codecs.DocValuesFormat;
import org.apache.lucene.codecs.DocValuesProducer;
import org.apache.lucene.index.IndexFileNames;
import org.apache.lucene.index.SegmentReadState;
import org.apache.lucene.index.SegmentWriteState;
import org.apache.lucene.store.CompoundFileDirectory;
import org.apache.lucene.store.DataOutput;
import org.apache.lucene.util.packed.PackedInts;
/**
* Lucene 4.0 DocValues format.
*
* Files:
*
* - .dv.cfs: {@link CompoundFileDirectory compound container}
* - .dv.cfe: {@link CompoundFileDirectory compound entries}
*
* Entries within the compound file:
*
* - <segment>_<fieldNumber>.dat: data values
* - <segment>_<fieldNumber>.idx: index into the .dat for DEREF types
*
*
* There are several many types of {@code DocValues} with different encodings.
* From the perspective of filenames, all types store their values in .dat
* entries within the compound file. In the case of dereferenced/sorted types, the .dat
* actually contains only the unique values, and an additional .idx file contains
* pointers to these unique values.
*
* Formats:
*
* - {@code VAR_INTS} .dat --> Header, PackedType, MinValue,
* DefaultValue, PackedStream
* - {@code FIXED_INTS_8} .dat --> Header, ValueSize,
* {@link DataOutput#writeByte Byte}maxdoc
* - {@code FIXED_INTS_16} .dat --> Header, ValueSize,
* {@link DataOutput#writeShort Short}maxdoc
* - {@code FIXED_INTS_32} .dat --> Header, ValueSize,
* {@link DataOutput#writeInt Int32}maxdoc
* - {@code FIXED_INTS_64} .dat --> Header, ValueSize,
* {@link DataOutput#writeLong Int64}maxdoc
* - {@code FLOAT_32} .dat --> Header, ValueSize, Float32maxdoc
* - {@code FLOAT_64} .dat --> Header, ValueSize, Float64maxdoc
* - {@code BYTES_FIXED_STRAIGHT} .dat --> Header, ValueSize,
* ({@link DataOutput#writeByte Byte} * ValueSize)maxdoc
* - {@code BYTES_VAR_STRAIGHT} .idx --> Header, TotalBytes, Addresses
* - {@code BYTES_VAR_STRAIGHT} .dat --> Header,
({@link DataOutput#writeByte Byte} * variable ValueSize)maxdoc
* - {@code BYTES_FIXED_DEREF} .idx --> Header, NumValues, Addresses
* - {@code BYTES_FIXED_DEREF} .dat --> Header, ValueSize,
* ({@link DataOutput#writeByte Byte} * ValueSize)NumValues
* - {@code BYTES_VAR_DEREF} .idx --> Header, TotalVarBytes, Addresses
* - {@code BYTES_VAR_DEREF} .dat --> Header,
* (LengthPrefix + {@link DataOutput#writeByte Byte} * variable ValueSize)NumValues
* - {@code BYTES_FIXED_SORTED} .idx --> Header, NumValues, Ordinals
* - {@code BYTES_FIXED_SORTED} .dat --> Header, ValueSize,
* ({@link DataOutput#writeByte Byte} * ValueSize)NumValues
* - {@code BYTES_VAR_SORTED} .idx --> Header, TotalVarBytes, Addresses, Ordinals
* - {@code BYTES_VAR_SORTED} .dat --> Header,
* ({@link DataOutput#writeByte Byte} * variable ValueSize)NumValues
*
* Data Types:
*
* - Header --> {@link CodecUtil#writeHeader CodecHeader}
* - PackedType --> {@link DataOutput#writeByte Byte}
* - MaxAddress, MinValue, DefaultValue --> {@link DataOutput#writeLong Int64}
* - PackedStream, Addresses, Ordinals --> {@link PackedInts}
* - ValueSize, NumValues --> {@link DataOutput#writeInt Int32}
* - Float32 --> 32-bit float encoded with {@link Float#floatToRawIntBits(float)}
* then written as {@link DataOutput#writeInt Int32}
* - Float64 --> 64-bit float encoded with {@link Double#doubleToRawLongBits(double)}
* then written as {@link DataOutput#writeLong Int64}
* - TotalBytes --> {@link DataOutput#writeVLong VLong}
* - TotalVarBytes --> {@link DataOutput#writeLong Int64}
* - LengthPrefix --> Length of the data value as {@link DataOutput#writeVInt VInt} (maximum
* of 2 bytes)
*
* Notes:
*
* - PackedType is a 0 when compressed, 1 when the stream is written as 64-bit integers.
* - Addresses stores pointers to the actual byte location (indexed by docid). In the VAR_STRAIGHT
* case, each entry can have a different length, so to determine the length, docid+1 is
* retrieved. A sentinel address is written at the end for the VAR_STRAIGHT case, so the Addresses
* stream contains maxdoc+1 indices. For the deduplicated VAR_DEREF case, each length
* is encoded as a prefix to the data itself as a {@link DataOutput#writeVInt VInt}
* (maximum of 2 bytes).
* - Ordinals stores the term ID in sorted order (indexed by docid). In the FIXED_SORTED case,
* the address into the .dat can be computed from the ordinal as
*
Header+ValueSize+(ordinal*ValueSize)
because the byte length is fixed.
* In the VAR_SORTED case, there is double indirection (docid -> ordinal -> address), but
* an additional sentinel ordinal+address is always written (so there are NumValues+1 ordinals). To
* determine the length, ord+1's address is looked up as well.
* - {@code BYTES_VAR_STRAIGHT BYTES_VAR_STRAIGHT} in contrast to other straight
* variants uses a .idx file to improve lookup perfromance. In contrast to
* {@code BYTES_VAR_DEREF BYTES_VAR_DEREF} it doesn't apply deduplication of the document values.
*
*
*
* Limitations:
*
* - Binary doc values can be at most {@link #MAX_BINARY_FIELD_LENGTH} in length.
*
* @deprecated Only for reading old 4.0 and 4.1 segments
*/
@Deprecated
// NOTE: not registered in SPI, doesnt respect segment suffix, etc
// for back compat only!
public class Lucene40DocValuesFormat extends DocValuesFormat {
/** Maximum length for each binary doc values field. */
public static final int MAX_BINARY_FIELD_LENGTH = (1 << 15) - 2;
/** Sole constructor. */
public Lucene40DocValuesFormat() {
super("Lucene40");
}
@Override
public DocValuesConsumer fieldsConsumer(SegmentWriteState state) throws IOException {
throw new UnsupportedOperationException("this codec can only be used for reading");
}
@Override
public DocValuesProducer fieldsProducer(SegmentReadState state) throws IOException {
String filename = IndexFileNames.segmentFileName(state.segmentInfo.name,
"dv",
IndexFileNames.COMPOUND_FILE_EXTENSION);
return new Lucene40DocValuesReader(state, filename, Lucene40FieldInfosReader.LEGACY_DV_TYPE_KEY);
}
// constants for VAR_INTS
static final String VAR_INTS_CODEC_NAME = "PackedInts";
static final int VAR_INTS_VERSION_START = 0;
static final int VAR_INTS_VERSION_CURRENT = VAR_INTS_VERSION_START;
static final byte VAR_INTS_PACKED = 0x00;
static final byte VAR_INTS_FIXED_64 = 0x01;
// constants for FIXED_INTS_8, FIXED_INTS_16, FIXED_INTS_32, FIXED_INTS_64
static final String INTS_CODEC_NAME = "Ints";
static final int INTS_VERSION_START = 0;
static final int INTS_VERSION_CURRENT = INTS_VERSION_START;
// constants for FLOAT_32, FLOAT_64
static final String FLOATS_CODEC_NAME = "Floats";
static final int FLOATS_VERSION_START = 0;
static final int FLOATS_VERSION_CURRENT = FLOATS_VERSION_START;
// constants for BYTES_FIXED_STRAIGHT
static final String BYTES_FIXED_STRAIGHT_CODEC_NAME = "FixedStraightBytes";
static final int BYTES_FIXED_STRAIGHT_VERSION_START = 0;
static final int BYTES_FIXED_STRAIGHT_VERSION_CURRENT = BYTES_FIXED_STRAIGHT_VERSION_START;
// constants for BYTES_VAR_STRAIGHT
static final String BYTES_VAR_STRAIGHT_CODEC_NAME_IDX = "VarStraightBytesIdx";
static final String BYTES_VAR_STRAIGHT_CODEC_NAME_DAT = "VarStraightBytesDat";
static final int BYTES_VAR_STRAIGHT_VERSION_START = 0;
static final int BYTES_VAR_STRAIGHT_VERSION_CURRENT = BYTES_VAR_STRAIGHT_VERSION_START;
// constants for BYTES_FIXED_DEREF
static final String BYTES_FIXED_DEREF_CODEC_NAME_IDX = "FixedDerefBytesIdx";
static final String BYTES_FIXED_DEREF_CODEC_NAME_DAT = "FixedDerefBytesDat";
static final int BYTES_FIXED_DEREF_VERSION_START = 0;
static final int BYTES_FIXED_DEREF_VERSION_CURRENT = BYTES_FIXED_DEREF_VERSION_START;
// constants for BYTES_VAR_DEREF
static final String BYTES_VAR_DEREF_CODEC_NAME_IDX = "VarDerefBytesIdx";
static final String BYTES_VAR_DEREF_CODEC_NAME_DAT = "VarDerefBytesDat";
static final int BYTES_VAR_DEREF_VERSION_START = 0;
static final int BYTES_VAR_DEREF_VERSION_CURRENT = BYTES_VAR_DEREF_VERSION_START;
// constants for BYTES_FIXED_SORTED
static final String BYTES_FIXED_SORTED_CODEC_NAME_IDX = "FixedSortedBytesIdx";
static final String BYTES_FIXED_SORTED_CODEC_NAME_DAT = "FixedSortedBytesDat";
static final int BYTES_FIXED_SORTED_VERSION_START = 0;
static final int BYTES_FIXED_SORTED_VERSION_CURRENT = BYTES_FIXED_SORTED_VERSION_START;
// constants for BYTES_VAR_SORTED
// NOTE THIS IS NOT A BUG! 4.0 actually screwed this up (VAR_SORTED and VAR_DEREF have same codec header)
static final String BYTES_VAR_SORTED_CODEC_NAME_IDX = "VarDerefBytesIdx";
static final String BYTES_VAR_SORTED_CODEC_NAME_DAT = "VarDerefBytesDat";
static final int BYTES_VAR_SORTED_VERSION_START = 0;
static final int BYTES_VAR_SORTED_VERSION_CURRENT = BYTES_VAR_SORTED_VERSION_START;
}
© 2015 - 2025 Weber Informatics LLC | Privacy Policy