diff --git a/lucene/CHANGES.txt b/lucene/CHANGES.txt index 14a28b8a111..f0b7a4e8a43 100644 --- a/lucene/CHANGES.txt +++ b/lucene/CHANGES.txt @@ -72,6 +72,9 @@ New Features * LUCENE-6549: Add preload option to MMapDirectory. (Robert Muir) +* LUCENE-6504: Add Lucene53Codec, with norms implemented directly + via the Directory's RandomAccessInput api. (Robert Muir) + API Changes * LUCENE-6508: Simplify Lock api, there is now just diff --git a/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50Codec.java b/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene50/Lucene50Codec.java similarity index 98% rename from lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50Codec.java rename to lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene50/Lucene50Codec.java index a9aa5448201..d58f5223716 100644 --- a/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50Codec.java +++ b/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene50/Lucene50Codec.java @@ -42,8 +42,9 @@ import org.apache.lucene.codecs.perfield.PerFieldPostingsFormat; * {@link FilterCodec}. * * @see org.apache.lucene.codecs.lucene50 package documentation for file format details. - * @lucene.experimental + * @deprecated Only for reading old 5.0-5.2 segments */ +@Deprecated public class Lucene50Codec extends Codec { private final TermVectorsFormat vectorsFormat = new Lucene50TermVectorsFormat(); private final FieldInfosFormat fieldInfosFormat = new Lucene50FieldInfosFormat(); @@ -157,7 +158,7 @@ public class Lucene50Codec extends Codec { private final NormsFormat normsFormat = new Lucene50NormsFormat(); @Override - public final NormsFormat normsFormat() { + public NormsFormat normsFormat() { return normsFormat; } } diff --git a/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene50/Lucene50NormsFormat.java b/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene50/Lucene50NormsFormat.java new file mode 100644 index 00000000000..06a50cef58b --- /dev/null +++ b/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene50/Lucene50NormsFormat.java @@ -0,0 +1,62 @@ +package org.apache.lucene.codecs.lucene50; + +/* + * 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.NormsConsumer; +import org.apache.lucene.codecs.NormsFormat; +import org.apache.lucene.codecs.NormsProducer; +import org.apache.lucene.index.SegmentReadState; +import org.apache.lucene.index.SegmentWriteState; + +/** + * Lucene 5.0 Score normalization format. + * @deprecated Only for reading old 5.0-5.2 segments + */ +@Deprecated +class Lucene50NormsFormat extends NormsFormat { + + /** Sole Constructor */ + public Lucene50NormsFormat() {} + + @Override + public NormsConsumer normsConsumer(SegmentWriteState state) throws IOException { + throw new UnsupportedOperationException("this codec can only be used for reading"); + } + + @Override + public NormsProducer normsProducer(SegmentReadState state) throws IOException { + return new Lucene50NormsProducer(state, DATA_CODEC, DATA_EXTENSION, METADATA_CODEC, METADATA_EXTENSION); + } + + static final String DATA_CODEC = "Lucene50NormsData"; + static final String DATA_EXTENSION = "nvd"; + static final String METADATA_CODEC = "Lucene50NormsMetadata"; + static final String METADATA_EXTENSION = "nvm"; + static final int VERSION_START = 0; + static final int VERSION_CURRENT = VERSION_START; + + static final byte DELTA_COMPRESSED = 0; + static final byte TABLE_COMPRESSED = 1; + static final byte CONST_COMPRESSED = 2; + static final byte UNCOMPRESSED = 3; + static final byte INDIRECT = 4; + static final byte PATCHED_BITSET = 5; + static final byte PATCHED_TABLE = 6; +} diff --git a/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50NormsProducer.java b/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene50/Lucene50NormsProducer.java similarity index 95% rename from lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50NormsProducer.java rename to lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene50/Lucene50NormsProducer.java index d0c8dc050b0..c4495f8589d 100644 --- a/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50NormsProducer.java +++ b/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene50/Lucene50NormsProducer.java @@ -17,13 +17,13 @@ package org.apache.lucene.codecs.lucene50; * limitations under the License. */ -import static org.apache.lucene.codecs.lucene50.Lucene50NormsConsumer.CONST_COMPRESSED; -import static org.apache.lucene.codecs.lucene50.Lucene50NormsConsumer.DELTA_COMPRESSED; -import static org.apache.lucene.codecs.lucene50.Lucene50NormsConsumer.INDIRECT; -import static org.apache.lucene.codecs.lucene50.Lucene50NormsConsumer.PATCHED_BITSET; -import static org.apache.lucene.codecs.lucene50.Lucene50NormsConsumer.PATCHED_TABLE; -import static org.apache.lucene.codecs.lucene50.Lucene50NormsConsumer.TABLE_COMPRESSED; -import static org.apache.lucene.codecs.lucene50.Lucene50NormsConsumer.UNCOMPRESSED; +import static org.apache.lucene.codecs.lucene50.Lucene50NormsFormat.CONST_COMPRESSED; +import static org.apache.lucene.codecs.lucene50.Lucene50NormsFormat.DELTA_COMPRESSED; +import static org.apache.lucene.codecs.lucene50.Lucene50NormsFormat.INDIRECT; +import static org.apache.lucene.codecs.lucene50.Lucene50NormsFormat.PATCHED_BITSET; +import static org.apache.lucene.codecs.lucene50.Lucene50NormsFormat.PATCHED_TABLE; +import static org.apache.lucene.codecs.lucene50.Lucene50NormsFormat.TABLE_COMPRESSED; +import static org.apache.lucene.codecs.lucene50.Lucene50NormsFormat.UNCOMPRESSED; import static org.apache.lucene.codecs.lucene50.Lucene50NormsFormat.VERSION_CURRENT; import static org.apache.lucene.codecs.lucene50.Lucene50NormsFormat.VERSION_START; @@ -58,8 +58,10 @@ import org.apache.lucene.util.packed.PackedInts; /** * Reader for {@link Lucene50NormsFormat} + * @deprecated Only for reading old 5.0-5.2 segments */ -class Lucene50NormsProducer extends NormsProducer { +@Deprecated +final class Lucene50NormsProducer extends NormsProducer { // metadata maps (just file pointers and minimal stuff) private final Map norms = new HashMap<>(); private final IndexInput data; diff --git a/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene50/package.html b/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene50/package.html new file mode 100644 index 00000000000..352cef4bf9a --- /dev/null +++ b/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene50/package.html @@ -0,0 +1,25 @@ + + + + + + + +Lucene 5.0 file format. + + diff --git a/lucene/backward-codecs/src/resources/META-INF/services/org.apache.lucene.codecs.Codec b/lucene/backward-codecs/src/resources/META-INF/services/org.apache.lucene.codecs.Codec index cccdbfab854..2d066a7234c 100644 --- a/lucene/backward-codecs/src/resources/META-INF/services/org.apache.lucene.codecs.Codec +++ b/lucene/backward-codecs/src/resources/META-INF/services/org.apache.lucene.codecs.Codec @@ -13,4 +13,4 @@ # See the License for the specific language governing permissions and # limitations under the License. - +org.apache.lucene.codecs.lucene50.Lucene50Codec diff --git a/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50NormsConsumer.java b/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene50/Lucene50NormsConsumer.java similarity index 95% rename from lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50NormsConsumer.java rename to lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene50/Lucene50NormsConsumer.java index 4f1d3221994..119fbdaaf6d 100644 --- a/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50NormsConsumer.java +++ b/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene50/Lucene50NormsConsumer.java @@ -39,15 +39,10 @@ import static org.apache.lucene.codecs.lucene50.Lucene50NormsFormat.VERSION_CURR /** * Writer for {@link Lucene50NormsFormat} + * @deprecated Only for testing old 5.0-5.2 segments */ -class Lucene50NormsConsumer extends NormsConsumer { - static final byte DELTA_COMPRESSED = 0; - static final byte TABLE_COMPRESSED = 1; - static final byte CONST_COMPRESSED = 2; - static final byte UNCOMPRESSED = 3; - static final byte INDIRECT = 4; - static final byte PATCHED_BITSET = 5; - static final byte PATCHED_TABLE = 6; +@Deprecated +final class Lucene50NormsConsumer extends NormsConsumer { static final int BLOCK_SIZE = 1 << 14; // threshold for indirect encoding, computed as 1 - 1/log2(maxint) @@ -181,13 +176,13 @@ class Lucene50NormsConsumer extends NormsConsumer { private void addConstant(byte constant) throws IOException { meta.writeVInt(0); - meta.writeByte(CONST_COMPRESSED); + meta.writeByte(Lucene50NormsFormat.CONST_COMPRESSED); meta.writeLong(constant); } private void addUncompressed(Iterable values, int count) throws IOException { meta.writeVInt(count); - meta.writeByte(UNCOMPRESSED); // uncompressed byte[] + meta.writeByte(Lucene50NormsFormat.UNCOMPRESSED); // uncompressed byte[] meta.writeLong(data.getFilePointer()); for (Number nv : values) { data.writeByte(nv.byteValue()); @@ -196,7 +191,7 @@ class Lucene50NormsConsumer extends NormsConsumer { private void addTableCompressed(Iterable values, FormatAndBits compression, int count, NormMap uniqueValues) throws IOException { meta.writeVInt(count); - meta.writeByte(TABLE_COMPRESSED); // table-compressed + meta.writeByte(Lucene50NormsFormat.TABLE_COMPRESSED); // table-compressed meta.writeLong(data.getFilePointer()); writeTable(values, compression, count, uniqueValues, uniqueValues.size); @@ -226,7 +221,7 @@ class Lucene50NormsConsumer extends NormsConsumer { private void addDeltaCompressed(Iterable values, int count) throws IOException { meta.writeVInt(count); - meta.writeByte(DELTA_COMPRESSED); // delta-compressed + meta.writeByte(Lucene50NormsFormat.DELTA_COMPRESSED); // delta-compressed meta.writeLong(data.getFilePointer()); data.writeVInt(PackedInts.VERSION_CURRENT); data.writeVInt(BLOCK_SIZE); @@ -245,7 +240,7 @@ class Lucene50NormsConsumer extends NormsConsumer { int commonCount = uniqueValues.freqs[0]; meta.writeVInt(count - commonCount); - meta.writeByte(PATCHED_BITSET); + meta.writeByte(Lucene50NormsFormat.PATCHED_BITSET); meta.writeLong(data.getFilePointer()); // write docs with value @@ -268,7 +263,7 @@ class Lucene50NormsConsumer extends NormsConsumer { // the exceptions should not be accessed very often, since the values are uncommon private void addPatchedTable(FieldInfo field, final Iterable values, final int numCommonValues, int commonValuesCount, int count, final NormMap uniqueValues) throws IOException { meta.writeVInt(count); - meta.writeByte(PATCHED_TABLE); + meta.writeByte(Lucene50NormsFormat.PATCHED_TABLE); meta.writeLong(data.getFilePointer()); assert numCommonValues == 3 || numCommonValues == 15; @@ -287,7 +282,7 @@ class Lucene50NormsConsumer extends NormsConsumer { int commonCount = uniqueValues.freqs[minOrd]; meta.writeVInt(count - commonCount); - meta.writeByte(INDIRECT); + meta.writeByte(Lucene50NormsFormat.INDIRECT); meta.writeLong(data.getFilePointer()); // write docs with value diff --git a/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene50/Lucene50RWCodec.java b/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene50/Lucene50RWCodec.java new file mode 100644 index 00000000000..5737d879327 --- /dev/null +++ b/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene50/Lucene50RWCodec.java @@ -0,0 +1,34 @@ +package org.apache.lucene.codecs.lucene50; + +/* + * 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 org.apache.lucene.codecs.NormsFormat; + +/** + * Codec for testing 5.0 index format + * @deprecated Only for testing old 5.0-5.2 segments + */ +@Deprecated +final class Lucene50RWCodec extends Lucene50Codec { + private final NormsFormat normsFormat = new Lucene50RWNormsFormat(); + + @Override + public NormsFormat normsFormat() { + return normsFormat; + } +} diff --git a/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene50/Lucene50RWNormsFormat.java b/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene50/Lucene50RWNormsFormat.java new file mode 100644 index 00000000000..22a80cac029 --- /dev/null +++ b/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene50/Lucene50RWNormsFormat.java @@ -0,0 +1,36 @@ +package org.apache.lucene.codecs.lucene50; + +/* + * 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.NormsConsumer; +import org.apache.lucene.index.SegmentWriteState; + +/** + * Read-write version of 5.0 norms format for testing + * @deprecated for test purposes only + */ +@Deprecated +final class Lucene50RWNormsFormat extends Lucene50NormsFormat { + + @Override + public NormsConsumer normsConsumer(SegmentWriteState state) throws IOException { + return new Lucene50NormsConsumer(state, DATA_CODEC, DATA_EXTENSION, METADATA_CODEC, METADATA_EXTENSION); + } +} diff --git a/lucene/core/src/test/org/apache/lucene/codecs/lucene50/TestLucene50NormsFormat.java b/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene50/TestLucene50NormsFormat.java similarity index 97% rename from lucene/core/src/test/org/apache/lucene/codecs/lucene50/TestLucene50NormsFormat.java rename to lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene50/TestLucene50NormsFormat.java index 22359447ef3..6e41e84d33c 100644 --- a/lucene/core/src/test/org/apache/lucene/codecs/lucene50/TestLucene50NormsFormat.java +++ b/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene50/TestLucene50NormsFormat.java @@ -28,10 +28,10 @@ import org.apache.lucene.index.BaseNormsFormatTestCase; import org.apache.lucene.util.TestUtil; /** - * Tests Lucene49NormsFormat + * Tests Lucene50NormsFormat */ public class TestLucene50NormsFormat extends BaseNormsFormatTestCase { - private final Codec codec = TestUtil.getDefaultCodec(); + private final Codec codec = new Lucene50RWCodec(); @Override protected Codec getCodec() { diff --git a/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/CreateIndexTask.java b/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/CreateIndexTask.java index cfd2c12eb4a..4d3851ec12f 100644 --- a/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/CreateIndexTask.java +++ b/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/CreateIndexTask.java @@ -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.lucene50.Lucene50Codec; +import org.apache.lucene.codecs.lucene53.Lucene53Codec; 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 Lucene50Codec(){ + iwConf.setCodec(new Lucene53Codec() { @Override public PostingsFormat getPostingsFormatForField(String field) { return postingsFormatChosen; diff --git a/lucene/core/src/java/org/apache/lucene/codecs/Codec.java b/lucene/core/src/java/org/apache/lucene/codecs/Codec.java index 92a47011051..7ae80fef2bb 100644 --- a/lucene/core/src/java/org/apache/lucene/codecs/Codec.java +++ b/lucene/core/src/java/org/apache/lucene/codecs/Codec.java @@ -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("Lucene50"); + static Codec defaultCodec = LOADER.lookup("Lucene53"); } private final String name; diff --git a/lucene/core/src/java/org/apache/lucene/codecs/MultiLevelSkipListReader.java b/lucene/core/src/java/org/apache/lucene/codecs/MultiLevelSkipListReader.java index 673dc63f6db..bb59b9399d6 100644 --- a/lucene/core/src/java/org/apache/lucene/codecs/MultiLevelSkipListReader.java +++ b/lucene/core/src/java/org/apache/lucene/codecs/MultiLevelSkipListReader.java @@ -53,7 +53,6 @@ public abstract class MultiLevelSkipListReader implements Closeable { private int numberOfLevelsToBuffer = 1; private int docCount; - private boolean haveSkipped; /** skipStream for each level. */ private IndexInput[] skipStream; @@ -120,12 +119,7 @@ public abstract class MultiLevelSkipListReader implements Closeable { * greater than or equal to target. Returns the current doc count. */ public int skipTo(int target) throws IOException { - if (!haveSkipped) { - // first time, load skip levels - loadSkipLevels(); - haveSkipped = true; - } - + // walk up the levels until highest level is found that has a skip // for this target int level = 0; @@ -196,7 +190,7 @@ public abstract class MultiLevelSkipListReader implements Closeable { } /** Initializes the reader, for reuse on a new term. */ - public void init(long skipPointer, int df) { + public void init(long skipPointer, int df) throws IOException { this.skipPointer[0] = skipPointer; this.docCount = df; assert skipPointer >= 0 && skipPointer <= skipStream[0].length() @@ -205,10 +199,10 @@ public abstract class MultiLevelSkipListReader implements Closeable { Arrays.fill(numSkipped, 0); Arrays.fill(childPointer, 0); - haveSkipped = false; for (int i = 1; i < numberOfSkipLevels; i++) { skipStream[i] = null; } + loadSkipLevels(); } /** Loads the skip levels */ diff --git a/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50NormsFormat.java b/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50NormsFormat.java deleted file mode 100644 index d3c6c18bcf1..00000000000 --- a/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50NormsFormat.java +++ /dev/null @@ -1,137 +0,0 @@ -package org.apache.lucene.codecs.lucene50; - -/* - * 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.NormsConsumer; -import org.apache.lucene.codecs.NormsFormat; -import org.apache.lucene.codecs.NormsProducer; -import org.apache.lucene.index.SegmentReadState; -import org.apache.lucene.index.SegmentWriteState; -import org.apache.lucene.store.DataOutput; -import org.apache.lucene.util.SmallFloat; -import org.apache.lucene.util.packed.BlockPackedWriter; -import org.apache.lucene.util.packed.MonotonicBlockPackedWriter; -import org.apache.lucene.util.packed.PackedInts; - -/** - * Lucene 5.0 Score normalization format. - *

- * Encodes normalization values with these strategies: - *

    - *
  • 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. - *
  • Constant: when there is only one value present for the entire field, no actual data - * is written: this constant is encoded in the metadata - *
  • Table-compressed: when the number of unique values is very small (< 64), and - * when there are unused "gaps" in the range of values used (such as {@link SmallFloat}), - * a lookup table is written instead. Each per-document entry is instead the ordinal - * to this table, and those ordinals are compressed with bitpacking ({@link PackedInts}). - *
  • Delta-compressed: per-document integers written as deltas from the minimum value, - * compressed with bitpacking. For more information, see {@link BlockPackedWriter}. - * This is only used when norms of larger than one byte are present. - *
  • Indirect: when norms are extremely sparse, missing values are omitted. - * Access to an individual value is slower, but missing norm values are never accessed - * by search code. - *
  • Patched bitset: when a single norm value dominates, a sparse bitset encodes docs - * with exceptions, so that access to the common value is still very fast. outliers - * fall through to an exception handling mechanism (Indirect or Constant). - *
  • Patched table: when a small number of norm values dominate, a table is used for the - * common values to allow fast access. less common values fall through to an exception - * handling mechanism (Indirect). - *
- *

- * Files: - *

    - *
  1. .nvd: Norms data
    2. - *
  2. .nvm: Norms metadata
    3. - *
- *
    - *
  1. - *

    The Norms metadata or .nvm file.

    - *

    For each norms field, this stores metadata, such as the offset into the - * Norms data (.nvd)

    - *

    Norms metadata (.dvm) --> Header,<Entry>NumFields,Footer

    - *
      - *
    • Header --> {@link CodecUtil#writeIndexHeader IndexHeader}
      • - *
    • Entry --> FieldNumber,Type,Offset
      • - *
    • FieldNumber --> {@link DataOutput#writeVInt vInt}
      • - *
    • Type --> {@link DataOutput#writeByte Byte}
      • - *
    • Offset --> {@link DataOutput#writeLong Int64}
      • - *
    • Footer --> {@link CodecUtil#writeFooter CodecFooter}
      • - *
    - *

    FieldNumber of -1 indicates the end of metadata.

    - *

    Offset is the pointer to the start of the data in the norms data (.nvd), or the singleton value for Constant

    - *

    Type indicates how Numeric values will be compressed: - *

      - *
    • 0 --> delta-compressed. For each block of 16k integers, every integer is delta-encoded - * from the minimum value within the block. - *
    • 1 --> table-compressed. When the number of unique numeric values is small and it would save space, - * a lookup table of unique values is written, followed by the ordinal for each document. - *
    • 2 --> constant. When there is a single value for the entire field. - *
    • 3 --> uncompressed: Values written as a simple byte[]. - *
    • 4 --> indirect. Only documents with a value are written with monotonic compression. a nested - * entry for the same field will follow for the exception handler. - *
    • 5 --> patched bitset. Encoded the same as indirect. - *
    • 6 --> patched table. Documents with very common values are written with a lookup table. - * Other values are written using a nested indirect. - *
    - *
  2. - *

    The Norms data or .nvd file.

    - *

    For each Norms field, this stores the actual per-document data (the heavy-lifting)

    - *

    Norms data (.nvd) --> Header,<Uncompressed | TableCompressed | DeltaCompressed | MonotonicCompressed >NumFields,Footer

    - *
      - *
    • Header --> {@link CodecUtil#writeIndexHeader IndexHeader}
      • - *
    • Uncompressed --> {@link DataOutput#writeByte Byte}maxDoc
      • - *
    • TableCompressed --> PackedIntsVersion,Table,BitPackedData
      • - *
    • Table --> TableSize, {@link DataOutput#writeLong int64}TableSize
      • - *
    • BitpackedData --> {@link PackedInts}
      • - *
    • DeltaCompressed --> PackedIntsVersion,BlockSize,DeltaCompressedData
      • - *
    • DeltaCompressedData --> {@link BlockPackedWriter BlockPackedWriter(blockSize=16k)}
      • - *
    • MonotonicCompressed --> PackedIntsVersion,BlockSize,MonotonicCompressedData
      • - *
    • MonotonicCompressedData --> {@link MonotonicBlockPackedWriter MonotonicBlockPackedWriter(blockSize=16k)}
      • - *
    • PackedIntsVersion,BlockSize,TableSize --> {@link DataOutput#writeVInt vInt}
      • - *
    • Footer --> {@link CodecUtil#writeFooter CodecFooter}
      • - *
    - *
- * @lucene.experimental - */ -public class Lucene50NormsFormat extends NormsFormat { - - /** Sole Constructor */ - public Lucene50NormsFormat() {} - - @Override - public NormsConsumer normsConsumer(SegmentWriteState state) throws IOException { - return new Lucene50NormsConsumer(state, DATA_CODEC, DATA_EXTENSION, METADATA_CODEC, METADATA_EXTENSION); - } - - @Override - public NormsProducer normsProducer(SegmentReadState state) throws IOException { - return new Lucene50NormsProducer(state, DATA_CODEC, DATA_EXTENSION, METADATA_CODEC, METADATA_EXTENSION); - } - - private static final String DATA_CODEC = "Lucene50NormsData"; - private static final String DATA_EXTENSION = "nvd"; - private static final String METADATA_CODEC = "Lucene50NormsMetadata"; - private static final String METADATA_EXTENSION = "nvm"; - static final int VERSION_START = 0; - static final int VERSION_CURRENT = VERSION_START; -} diff --git a/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50PostingsReader.java b/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50PostingsReader.java index ab07b9e51dc..a77bfe55bc2 100644 --- a/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50PostingsReader.java +++ b/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50PostingsReader.java @@ -414,7 +414,6 @@ public final class Lucene50PostingsReader extends PostingsReaderBase { // Lazy init: first time this enum has ever been used for skipping skipper = new Lucene50SkipReader(docIn.clone(), MAX_SKIP_LEVELS, - BLOCK_SIZE, indexHasPos, indexHasOffsets, indexHasPayloads); @@ -692,7 +691,6 @@ public final class Lucene50PostingsReader extends PostingsReaderBase { // Lazy init: first time this enum has ever been used for skipping skipper = new Lucene50SkipReader(docIn.clone(), MAX_SKIP_LEVELS, - BLOCK_SIZE, true, indexHasOffsets, indexHasPayloads); @@ -1121,7 +1119,6 @@ public final class Lucene50PostingsReader extends PostingsReaderBase { // Lazy init: first time this enum has ever been used for skipping skipper = new Lucene50SkipReader(docIn.clone(), MAX_SKIP_LEVELS, - BLOCK_SIZE, true, indexHasOffsets, indexHasPayloads); diff --git a/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50SkipReader.java b/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50SkipReader.java index e3a8d1b770c..3efdc984576 100644 --- a/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50SkipReader.java +++ b/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50SkipReader.java @@ -23,6 +23,8 @@ import java.util.Arrays; import org.apache.lucene.codecs.MultiLevelSkipListReader; import org.apache.lucene.store.IndexInput; +import static org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat.BLOCK_SIZE; + /** * Implements the skip list reader for block postings format * that stores positions and payloads. @@ -51,8 +53,6 @@ import org.apache.lucene.store.IndexInput; * */ final class Lucene50SkipReader extends MultiLevelSkipListReader { - private final int blockSize; - private long docPointer[]; private long posPointer[]; private long payPointer[]; @@ -65,9 +65,8 @@ final class Lucene50SkipReader extends MultiLevelSkipListReader { private long lastDocPointer; private int lastPosBufferUpto; - public Lucene50SkipReader(IndexInput skipStream, int maxSkipLevels, int blockSize, boolean hasPos, boolean hasOffsets, boolean hasPayloads) { - super(skipStream, maxSkipLevels, blockSize, 8); - this.blockSize = blockSize; + public Lucene50SkipReader(IndexInput skipStream, int maxSkipLevels, boolean hasPos, boolean hasOffsets, boolean hasPayloads) { + super(skipStream, maxSkipLevels, BLOCK_SIZE, 8); docPointer = new long[maxSkipLevels]; if (hasPos) { posPointer = new long[maxSkipLevels]; @@ -97,10 +96,10 @@ final class Lucene50SkipReader extends MultiLevelSkipListReader { * */ protected int trim(int df) { - return df % blockSize == 0? df - 1: df; + return df % BLOCK_SIZE == 0? df - 1: df; } - public void init(long skipPointer, long docBasePointer, long posBasePointer, long payBasePointer, int df) { + public void init(long skipPointer, long docBasePointer, long posBasePointer, long payBasePointer, int df) throws IOException { super.init(skipPointer, trim(df)); lastDocPointer = docBasePointer; lastPosPointer = posBasePointer; diff --git a/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50StoredFieldsFormat.java b/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50StoredFieldsFormat.java index 16bc2d542eb..663396dbc1b 100644 --- a/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50StoredFieldsFormat.java +++ b/lucene/core/src/java/org/apache/lucene/codecs/lucene50/Lucene50StoredFieldsFormat.java @@ -53,9 +53,9 @@ import org.apache.lucene.util.packed.PackedInts; * These two options can be configured like this: * 
  *   // the default: for high performance
- *   indexWriterConfig.setCodec(new Lucene50Codec(Mode.BEST_SPEED));
+ *   indexWriterConfig.setCodec(new Lucene53Codec(Mode.BEST_SPEED));
  *   // instead for higher performance (but slower):
- *   // indexWriterConfig.setCodec(new Lucene50Codec(Mode.BEST_COMPRESSION));
+ *   // indexWriterConfig.setCodec(new Lucene53Codec(Mode.BEST_COMPRESSION));
  *
*

File formats *

Stored fields are represented by two files: diff --git a/lucene/core/src/java/org/apache/lucene/codecs/lucene50/package-info.java b/lucene/core/src/java/org/apache/lucene/codecs/lucene50/package-info.java index 144f01cd5cf..f76ac06392e 100644 --- a/lucene/core/src/java/org/apache/lucene/codecs/lucene50/package-info.java +++ b/lucene/core/src/java/org/apache/lucene/codecs/lucene50/package-info.java @@ -16,386 +16,8 @@ */ /** - * Lucene 5.0 file format. - * - *

Apache Lucene - Index File Formats

- * - * - *

Introduction

- *
- *

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 - * docs/ that was distributed with - * the version you are using.

- *

Apache Lucene is written in Java, but several efforts are underway to write - * versions of - * Lucene in other programming languages. If these versions are to remain - * compatible with Apache Lucene, then a language-independent definition of the - * Lucene index format is required. This document thus attempts to provide a - * complete and independent definition of the Apache Lucene file formats.

- *

As Lucene evolves, this document should evolve. Versions of Lucene in - * different programming languages should endeavor to agree on file formats, and - * generate new versions of this document.

- *
- * - *

Definitions

- *
- *

The fundamental concepts in Lucene are index, document, field and term.

- *

An index contains a sequence of documents.

- *
    - *
  • A document is a sequence of fields.
    • - *
  • A field is a named sequence of terms.
    • - *
  • A term is a sequence of bytes.
    • - *
- *

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.

- * - *

Inverted Indexing

- *

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 - * inverted index. 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.

- * - *

Types of Fields

- *

In Lucene, fields may be stored, in which case their text is stored - * in the index literally, in a non-inverted manner. Fields that are inverted are - * called indexed. A field may be both stored and indexed.

- *

The text of a field may be tokenized 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.

- *

See the {@link org.apache.lucene.document.Field Field} - * java docs for more information on Fields.

- * - *

Segments

- *

Lucene indexes may be composed of multiple sub-indexes, or segments. - * Each segment is a fully independent index, which could be searched separately. - * Indexes evolve by:

- *
    - *
  1. Creating new segments for newly added documents.
    2. - *
  2. Merging existing segments.
    3. - *
- *

Searches may involve multiple segments and/or multiple indexes, each index - * potentially composed of a set of segments.

- * - *

Document Numbers

- *

Internally, Lucene refers to documents by an integer document number. - * The first document added to an index is numbered zero, and each subsequent - * document added gets a number one greater than the previous.

- *

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:

- *
    - *
  • - *

    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 base 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.

    - *
    • - *
  • - *

    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.

    - *
    • - *
- *
- * - *

Index Structure Overview

- *
- *

Each segment index maintains the following:

- *
    - *
  • - * {@link org.apache.lucene.codecs.lucene50.Lucene50SegmentInfoFormat Segment info}. - * This contains metadata about a segment, such as the number of documents, - * what files it uses, - *
    • - *
  • - * {@link org.apache.lucene.codecs.lucene50.Lucene50FieldInfosFormat Field names}. - * This contains the set of field names used in the index. - *
    • - *
  • - * {@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. - *
    • - *
  • - * {@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. - *
    • - *
  • - * {@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) - *
    • - *
  • - * {@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. - *
    • - *
  • - * {@link org.apache.lucene.codecs.lucene50.Lucene50NormsFormat Normalization factors}. - * For each field in each document, a value is stored - * that is multiplied into the score for hits on that field. - *
    • - *
  • - * {@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 - *
    • - *
  • - * {@link org.apache.lucene.codecs.lucene50.Lucene50DocValuesFormat 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. - *
    • - *
  • - * {@link org.apache.lucene.codecs.lucene50.Lucene50LiveDocsFormat Live documents}. - * An optional file indicating which documents are live. - *
    • - *
- *

Details on each of these are provided in their linked pages.

- *
- * - *

File Naming

- *
- *

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 in 1.4 and greater) 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)

- *

Typically, all segments in an index are stored in a single directory, - * although this is not required.

- *

As of version 2.1 (lock-less commits), 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.

- *
- * - *

Summary of File Extensions

- *
- *

The following table summarizes the names and extensions of the files in - * Lucene:

- * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - * - *
NameExtensionBrief Description
{@link org.apache.lucene.index.SegmentInfos Segments File}segments_NStores information about a commit point
Lock Filewrite.lockThe Write lock prevents multiple IndexWriters from writing to the same - * file.
{@link org.apache.lucene.codecs.lucene50.Lucene50SegmentInfoFormat Segment Info}.siStores metadata about a segment
{@link org.apache.lucene.codecs.lucene50.Lucene50CompoundFormat Compound File}.cfs, .cfeAn optional "virtual" file consisting of all the other index files for - * systems that frequently run out of file handles.
{@link org.apache.lucene.codecs.lucene50.Lucene50FieldInfosFormat Fields}.fnmStores information about the fields
{@link org.apache.lucene.codecs.lucene50.Lucene50StoredFieldsFormat Field Index}.fdxContains pointers to field data
{@link org.apache.lucene.codecs.lucene50.Lucene50StoredFieldsFormat Field Data}.fdtThe stored fields for documents
{@link org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat Term Dictionary}.timThe term dictionary, stores term info
{@link org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat Term Index}.tipThe index into the Term Dictionary
{@link org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat Frequencies}.docContains the list of docs which contain each term along with frequency
{@link org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat Positions}.posStores position information about where a term occurs in the index
{@link org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat Payloads}.payStores additional per-position metadata information such as character offsets and user payloads
{@link org.apache.lucene.codecs.lucene50.Lucene50NormsFormat Norms}.nvd, .nvmEncodes length and boost factors for docs and fields
{@link org.apache.lucene.codecs.lucene50.Lucene50DocValuesFormat Per-Document Values}.dvd, .dvmEncodes additional scoring factors or other per-document information.
{@link org.apache.lucene.codecs.lucene50.Lucene50TermVectorsFormat Term Vector Index}.tvxStores offset into the document data file
{@link org.apache.lucene.codecs.lucene50.Lucene50TermVectorsFormat Term Vector Documents}.tvdContains information about each document that has term vectors
{@link org.apache.lucene.codecs.lucene50.Lucene50TermVectorsFormat Term Vector Fields}.tvfThe field level info about term vectors
{@link org.apache.lucene.codecs.lucene50.Lucene50LiveDocsFormat Live Documents}.livInfo about what files are live
- *
- * - *

Lock File

- * 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. - * - *

History

- *

Compatibility notes are provided in this document, describing how file - * formats have changed from prior versions:

- *
    - *
  • 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.
    • - *
  • 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).
    • - *
  • In version 2.4, Strings are now written as true UTF-8 byte sequence, not - * Java's modified UTF-8. See - * LUCENE-510 for details.
    • - *
  • 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 - * LUCENE-1382 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 - * LUCENE-1654 for details.
    • - *
  • 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 LUCENE-1960 - * for details.
    • - *
  • In version 3.1, segments records the code version that created them. See - * LUCENE-2720 for details. - * Additionally segments track explicitly whether or not they have term vectors. - * See LUCENE-2811 - * for details.
    • - *
  • In version 3.2, numeric fields are written as natively to stored fields - * file, previously they were stored in text format only.
    • - *
  • In version 3.4, fields can omit position data while still indexing term - * frequencies.
    • - *
  • 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.
    • - *
  • 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.
    • - *
  • 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.
    • - *
  • In version 4.5, DocValues were extended to explicitly represent missing values.
    • - *
  • In version 4.6, FieldInfos were extended to support per-field DocValues generation, to - * allow updating NumericDocValues fields.
    • - *
  • 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.
    • - *
  • In version 4.9, DocValues has a new multi-valued numeric type (SortedNumeric) - * that is suitable for faceting/sorting/analytics. - *
    • - *
- * - *

Limitations

- *
- *

Lucene uses a Java int to refer to - * document numbers, and the index file format uses an Int32 - * 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 UInt64 values, or - * better yet, {@link org.apache.lucene.store.DataOutput#writeVInt VInt} values which have no limit.

- *
+ * Components from the Lucene 5.0 index format + * See {@link org.apache.lucene.codecs.lucene53} for an overview + * of the index format. */ package org.apache.lucene.codecs.lucene50; diff --git a/lucene/core/src/java/org/apache/lucene/codecs/lucene53/Lucene53Codec.java b/lucene/core/src/java/org/apache/lucene/codecs/lucene53/Lucene53Codec.java new file mode 100644 index 00000000000..d5c49fb5476 --- /dev/null +++ b/lucene/core/src/java/org/apache/lucene/codecs/lucene53/Lucene53Codec.java @@ -0,0 +1,169 @@ +package org.apache.lucene.codecs.lucene53; + +/* + * 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.util.Objects; + +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.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.Lucene50FieldInfosFormat; +import org.apache.lucene.codecs.lucene50.Lucene50LiveDocsFormat; +import org.apache.lucene.codecs.lucene50.Lucene50SegmentInfoFormat; +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.perfield.PerFieldDocValuesFormat; +import org.apache.lucene.codecs.perfield.PerFieldPostingsFormat; + +/** + * Implements the Lucene 5.3 index format, with configurable per-field postings + * and docvalues formats. + *

+ * If you want to reuse functionality of this codec in another codec, extend + * {@link FilterCodec}. + * + * @see org.apache.lucene.codecs.lucene53 package documentation for file format details. + * @lucene.experimental + */ +public class Lucene53Codec extends Codec { + private final TermVectorsFormat vectorsFormat = new Lucene50TermVectorsFormat(); + private final FieldInfosFormat fieldInfosFormat = new Lucene50FieldInfosFormat(); + private final SegmentInfoFormat segmentInfosFormat = new Lucene50SegmentInfoFormat(); + private final LiveDocsFormat liveDocsFormat = new Lucene50LiveDocsFormat(); + private final CompoundFormat compoundFormat = new Lucene50CompoundFormat(); + + private final PostingsFormat postingsFormat = new PerFieldPostingsFormat() { + @Override + public PostingsFormat getPostingsFormatForField(String field) { + return Lucene53Codec.this.getPostingsFormatForField(field); + } + }; + + private final DocValuesFormat docValuesFormat = new PerFieldDocValuesFormat() { + @Override + public DocValuesFormat getDocValuesFormatForField(String field) { + return Lucene53Codec.this.getDocValuesFormatForField(field); + } + }; + + private final StoredFieldsFormat storedFieldsFormat; + + /** + * Instantiates a new codec. + */ + public Lucene53Codec() { + this(Mode.BEST_SPEED); + } + + /** + * Instantiates a new codec, specifying the stored fields compression + * mode to use. + * @param mode stored fields compression mode to use for newly + * flushed/merged segments. + */ + public Lucene53Codec(Mode mode) { + super("Lucene53"); + this.storedFieldsFormat = new Lucene50StoredFieldsFormat(Objects.requireNonNull(mode)); + } + + @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; + } + + /** Returns the postings format that should be used for writing + * new segments of field. + * + * The default implementation always returns "Lucene50". + *

+ * WARNING: if you subclass, you are responsible for index + * backwards compatibility: future version of Lucene are only + * guaranteed to be able to read the default implementation. + */ + public PostingsFormat getPostingsFormatForField(String field) { + return defaultFormat; + } + + /** Returns the docvalues format that should be used for writing + * new segments of field. + * + * The default implementation always returns "Lucene50". + *

+ * WARNING: if you subclass, you are responsible for index + * backwards compatibility: future version of Lucene are only + * guaranteed to be able to read the default implementation. + */ + public DocValuesFormat getDocValuesFormatForField(String field) { + return defaultDVFormat; + } + + @Override + public final DocValuesFormat docValuesFormat() { + return docValuesFormat; + } + + private final PostingsFormat defaultFormat = PostingsFormat.forName("Lucene50"); + private final DocValuesFormat defaultDVFormat = DocValuesFormat.forName("Lucene50"); + + private final NormsFormat normsFormat = new Lucene53NormsFormat(); + + @Override + public final NormsFormat normsFormat() { + return normsFormat; + } +} diff --git a/lucene/core/src/java/org/apache/lucene/codecs/lucene53/Lucene53NormsConsumer.java b/lucene/core/src/java/org/apache/lucene/codecs/lucene53/Lucene53NormsConsumer.java new file mode 100644 index 00000000000..88c04e3c533 --- /dev/null +++ b/lucene/core/src/java/org/apache/lucene/codecs/lucene53/Lucene53NormsConsumer.java @@ -0,0 +1,153 @@ +package org.apache.lucene.codecs.lucene53; + +/* + * 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.NormsConsumer; +import org.apache.lucene.index.FieldInfo; +import org.apache.lucene.index.IndexFileNames; +import org.apache.lucene.index.SegmentWriteState; +import org.apache.lucene.store.IndexOutput; +import org.apache.lucene.util.IOUtils; + +import static org.apache.lucene.codecs.lucene53.Lucene53NormsFormat.VERSION_CURRENT; + +/** + * Writer for {@link Lucene53NormsFormat} + */ +class Lucene53NormsConsumer extends NormsConsumer { + IndexOutput data, meta; + final int maxDoc; + + Lucene53NormsConsumer(SegmentWriteState state, String dataCodec, String dataExtension, String metaCodec, String metaExtension) throws IOException { + boolean success = false; + try { + String dataName = IndexFileNames.segmentFileName(state.segmentInfo.name, state.segmentSuffix, dataExtension); + data = state.directory.createOutput(dataName, state.context); + CodecUtil.writeIndexHeader(data, dataCodec, VERSION_CURRENT, state.segmentInfo.getId(), state.segmentSuffix); + String metaName = IndexFileNames.segmentFileName(state.segmentInfo.name, state.segmentSuffix, metaExtension); + meta = state.directory.createOutput(metaName, state.context); + CodecUtil.writeIndexHeader(meta, metaCodec, VERSION_CURRENT, state.segmentInfo.getId(), state.segmentSuffix); + maxDoc = state.segmentInfo.maxDoc(); + success = true; + } finally { + if (!success) { + IOUtils.closeWhileHandlingException(this); + } + } + } + + @Override + public void addNormsField(FieldInfo field, Iterable values) throws IOException { + meta.writeVInt(field.number); + long minValue = Long.MAX_VALUE; + long maxValue = Long.MIN_VALUE; + int count = 0; + + for (Number nv : values) { + if (nv == null) { + throw new IllegalStateException("illegal norms data for field " + field.name + ", got null for value: " + count); + } + final long v = nv.longValue(); + minValue = Math.min(minValue, v); + maxValue = Math.max(maxValue, v); + count++; + } + + if (count != maxDoc) { + throw new IllegalStateException("illegal norms data for field " + field.name + ", expected count=" + maxDoc + ", got=" + count); + } + + if (minValue == maxValue) { + addConstant(minValue); + } else if (minValue >= Byte.MIN_VALUE && maxValue <= Byte.MAX_VALUE) { + addByte1(values); + } else if (minValue >= Short.MIN_VALUE && maxValue <= Short.MAX_VALUE) { + addByte2(values); + } else if (minValue >= Integer.MIN_VALUE && maxValue <= Integer.MAX_VALUE) { + addByte4(values); + } else { + addByte8(values); + } + } + + private void addConstant(long constant) throws IOException { + meta.writeByte((byte) 0); + meta.writeLong(constant); + } + + private void addByte1(Iterable values) throws IOException { + meta.writeByte((byte) 1); + meta.writeLong(data.getFilePointer()); + + for (Number value : values) { + data.writeByte(value.byteValue()); + } + } + + private void addByte2(Iterable values) throws IOException { + meta.writeByte((byte) 2); + meta.writeLong(data.getFilePointer()); + + for (Number value : values) { + data.writeShort(value.shortValue()); + } + } + + private void addByte4(Iterable values) throws IOException { + meta.writeByte((byte) 4); + meta.writeLong(data.getFilePointer()); + + for (Number value : values) { + data.writeInt(value.intValue()); + } + } + + private void addByte8(Iterable values) throws IOException { + meta.writeByte((byte) 8); + meta.writeLong(data.getFilePointer()); + + for (Number value : values) { + data.writeLong(value.longValue()); + } + } + + @Override + public void close() throws IOException { + boolean success = false; + try { + if (meta != null) { + meta.writeVInt(-1); // write EOF marker + CodecUtil.writeFooter(meta); // write checksum + } + if (data != null) { + CodecUtil.writeFooter(data); // write checksum + } + success = true; + } finally { + if (success) { + IOUtils.close(data, meta); + } else { + IOUtils.closeWhileHandlingException(data, meta); + } + meta = data = null; + } + } +} diff --git a/lucene/core/src/java/org/apache/lucene/codecs/lucene53/Lucene53NormsFormat.java b/lucene/core/src/java/org/apache/lucene/codecs/lucene53/Lucene53NormsFormat.java new file mode 100644 index 00000000000..91faf5d64be --- /dev/null +++ b/lucene/core/src/java/org/apache/lucene/codecs/lucene53/Lucene53NormsFormat.java @@ -0,0 +1,91 @@ +package org.apache.lucene.codecs.lucene53; + +/* + * 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.NormsConsumer; +import org.apache.lucene.codecs.NormsFormat; +import org.apache.lucene.codecs.NormsProducer; +import org.apache.lucene.index.SegmentReadState; +import org.apache.lucene.index.SegmentWriteState; +import org.apache.lucene.store.DataOutput; + +/** + * Lucene 5.3 Score normalization format. + *

+ * Encodes normalization values by encoding each value with the minimum + * number of bytes needed to represent the range (which can be zero). + *

+ * Files: + *

    + *
  1. .nvd: Norms data
    2. + *
  2. .nvm: Norms metadata
    3. + *
+ *
    + *
  1. + *

    The Norms metadata or .nvm file.

    + *

    For each norms field, this stores metadata, such as the offset into the + * Norms data (.nvd)

    + *

    Norms metadata (.dvm) --> Header,<Entry>NumFields,Footer

    + *
      + *
    • Header --> {@link CodecUtil#writeIndexHeader IndexHeader}
      • + *
    • Entry --> FieldNumber,BytesPerValue, Address
      • + *
    • FieldNumber --> {@link DataOutput#writeVInt vInt}
      • + *
    • BytesPerValue --> {@link DataOutput#writeByte byte}
      • + *
    • Offset --> {@link DataOutput#writeLong Int64}
      • + *
    • Footer --> {@link CodecUtil#writeFooter CodecFooter}
      • + *
    + *

    FieldNumber of -1 indicates the end of metadata.

    + *

    Offset is the pointer to the start of the data in the norms data (.nvd), or the singleton value + * when BytesPerValue = 0

    + *
  2. + *

    The Norms data or .nvd file.

    + *

    For each Norms field, this stores the actual per-document data (the heavy-lifting)

    + *

    Norms data (.nvd) --> Header,< Data >NumFields,Footer

    + *
      + *
    • Header --> {@link CodecUtil#writeIndexHeader IndexHeader}
      • + *
    • Data --> {@link DataOutput#writeByte(byte) byte}MaxDoc * BytesPerValue
      • + *
    • Footer --> {@link CodecUtil#writeFooter CodecFooter}
      • + *
    + *
+ * @lucene.experimental + */ +public class Lucene53NormsFormat extends NormsFormat { + + /** Sole Constructor */ + public Lucene53NormsFormat() {} + + @Override + public NormsConsumer normsConsumer(SegmentWriteState state) throws IOException { + return new Lucene53NormsConsumer(state, DATA_CODEC, DATA_EXTENSION, METADATA_CODEC, METADATA_EXTENSION); + } + + @Override + public NormsProducer normsProducer(SegmentReadState state) throws IOException { + return new Lucene53NormsProducer(state, DATA_CODEC, DATA_EXTENSION, METADATA_CODEC, METADATA_EXTENSION); + } + + private static final String DATA_CODEC = "Lucene53NormsData"; + private static final String DATA_EXTENSION = "nvd"; + private static final String METADATA_CODEC = "Lucene53NormsMetadata"; + private static final String METADATA_EXTENSION = "nvm"; + static final int VERSION_START = 0; + static final int VERSION_CURRENT = VERSION_START; +} diff --git a/lucene/core/src/java/org/apache/lucene/codecs/lucene53/Lucene53NormsProducer.java b/lucene/core/src/java/org/apache/lucene/codecs/lucene53/Lucene53NormsProducer.java new file mode 100644 index 00000000000..de79b07cacb --- /dev/null +++ b/lucene/core/src/java/org/apache/lucene/codecs/lucene53/Lucene53NormsProducer.java @@ -0,0 +1,208 @@ +package org.apache.lucene.codecs.lucene53; + +/* + * 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 static org.apache.lucene.codecs.lucene53.Lucene53NormsFormat.VERSION_CURRENT; +import static org.apache.lucene.codecs.lucene53.Lucene53NormsFormat.VERSION_START; + +import java.io.IOException; +import java.util.HashMap; +import java.util.Map; + +import org.apache.lucene.codecs.CodecUtil; +import org.apache.lucene.codecs.NormsProducer; +import org.apache.lucene.index.CorruptIndexException; +import org.apache.lucene.index.FieldInfo; +import org.apache.lucene.index.FieldInfos; +import org.apache.lucene.index.IndexFileNames; +import org.apache.lucene.index.NumericDocValues; +import org.apache.lucene.index.SegmentReadState; +import org.apache.lucene.store.ChecksumIndexInput; +import org.apache.lucene.store.IndexInput; +import org.apache.lucene.store.RandomAccessInput; +import org.apache.lucene.util.IOUtils; + +/** + * Reader for {@link Lucene53NormsFormat} + */ +class Lucene53NormsProducer extends NormsProducer { + // metadata maps (just file pointers and minimal stuff) + private final Map norms = new HashMap<>(); + private final IndexInput data; + private final int maxDoc; + + Lucene53NormsProducer(SegmentReadState state, String dataCodec, String dataExtension, String metaCodec, String metaExtension) throws IOException { + maxDoc = state.segmentInfo.maxDoc(); + String metaName = IndexFileNames.segmentFileName(state.segmentInfo.name, state.segmentSuffix, metaExtension); + int version = -1; + + // read in the entries from the metadata file. + try (ChecksumIndexInput in = state.directory.openChecksumInput(metaName, state.context)) { + Throwable priorE = null; + try { + version = CodecUtil.checkIndexHeader(in, metaCodec, VERSION_START, VERSION_CURRENT, state.segmentInfo.getId(), state.segmentSuffix); + readFields(in, state.fieldInfos); + } catch (Throwable exception) { + priorE = exception; + } finally { + CodecUtil.checkFooter(in, priorE); + } + } + + String dataName = IndexFileNames.segmentFileName(state.segmentInfo.name, state.segmentSuffix, dataExtension); + data = state.directory.openInput(dataName, state.context); + boolean success = false; + try { + final int version2 = CodecUtil.checkIndexHeader(data, dataCodec, VERSION_START, VERSION_CURRENT, state.segmentInfo.getId(), state.segmentSuffix); + if (version != version2) { + throw new CorruptIndexException("Format versions mismatch: meta=" + version + ",data=" + version2, data); + } + + // NOTE: data file is too costly to verify checksum against all the bytes on open, + // but for now we at least verify proper structure of the checksum footer: which looks + // for FOOTER_MAGIC + algorithmID. This is cheap and can detect some forms of corruption + // such as file truncation. + CodecUtil.retrieveChecksum(data); + + success = true; + } finally { + if (!success) { + IOUtils.closeWhileHandlingException(this.data); + } + } + } + + private void readFields(IndexInput meta, FieldInfos infos) throws IOException { + int fieldNumber = meta.readVInt(); + while (fieldNumber != -1) { + FieldInfo info = infos.fieldInfo(fieldNumber); + if (info == null) { + throw new CorruptIndexException("Invalid field number: " + fieldNumber, meta); + } else if (!info.hasNorms()) { + throw new CorruptIndexException("Invalid field: " + info.name, meta); + } + NormsEntry entry = new NormsEntry(); + entry.bytesPerValue = meta.readByte(); + switch (entry.bytesPerValue) { + case 0: case 1: case 2: case 4: case 8: + break; + default: + throw new CorruptIndexException("Invalid bytesPerValue: " + entry.bytesPerValue + ", field: " + info.name, meta); + } + entry.offset = meta.readLong(); + norms.put(info.number, entry); + fieldNumber = meta.readVInt(); + } + } + + @Override + public NumericDocValues getNorms(FieldInfo field) throws IOException { + final NormsEntry entry = norms.get(field.number); + + if (entry.bytesPerValue == 0) { + final long value = entry.offset; + return new NumericDocValues() { + @Override + public long get(int docID) { + return value; + } + }; + } + + RandomAccessInput slice; + synchronized (data) { + switch (entry.bytesPerValue) { + case 1: + slice = data.randomAccessSlice(entry.offset, maxDoc); + return new NumericDocValues() { + @Override + public long get(int docID) { + try { + return slice.readByte(docID); + } catch (IOException e) { + throw new RuntimeException(e); + } + } + }; + case 2: + slice = data.randomAccessSlice(entry.offset, maxDoc * 2L); + return new NumericDocValues() { + @Override + public long get(int docID) { + try { + return slice.readShort(((long)docID) << 1L); + } catch (IOException e) { + throw new RuntimeException(e); + } + } + }; + case 4: + slice = data.randomAccessSlice(entry.offset, maxDoc * 4L); + return new NumericDocValues() { + @Override + public long get(int docID) { + try { + return slice.readInt(((long)docID) << 2L); + } catch (IOException e) { + throw new RuntimeException(e); + } + } + }; + case 8: + slice = data.randomAccessSlice(entry.offset, maxDoc * 8L); + return new NumericDocValues() { + @Override + public long get(int docID) { + try { + return slice.readLong(((long)docID) << 3L); + } catch (IOException e) { + throw new RuntimeException(e); + } + } + }; + default: + throw new AssertionError(); + } + } + } + + @Override + public void close() throws IOException { + data.close(); + } + + @Override + public long ramBytesUsed() { + return 64L * norms.size(); // good enough + } + + @Override + public void checkIntegrity() throws IOException { + CodecUtil.checksumEntireFile(data); + } + + static class NormsEntry { + byte bytesPerValue; + long offset; + } + + @Override + public String toString() { + return getClass().getSimpleName() + "(fields=" + norms.size() + ")"; + } +} diff --git a/lucene/core/src/java/org/apache/lucene/codecs/lucene53/package-info.java b/lucene/core/src/java/org/apache/lucene/codecs/lucene53/package-info.java new file mode 100644 index 00000000000..3509738d1a5 --- /dev/null +++ b/lucene/core/src/java/org/apache/lucene/codecs/lucene53/package-info.java @@ -0,0 +1,401 @@ +/* + * 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 5.3 file format. + * + *

Apache Lucene - Index File Formats

+ * + * + *

Introduction

+ *
+ *

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 + * docs/ that was distributed with + * the version you are using.

+ *

Apache Lucene is written in Java, but several efforts are underway to write + * versions of + * Lucene in other programming languages. If these versions are to remain + * compatible with Apache Lucene, then a language-independent definition of the + * Lucene index format is required. This document thus attempts to provide a + * complete and independent definition of the Apache Lucene file formats.

+ *

As Lucene evolves, this document should evolve. Versions of Lucene in + * different programming languages should endeavor to agree on file formats, and + * generate new versions of this document.

+ *
+ * + *

Definitions

+ *
+ *

The fundamental concepts in Lucene are index, document, field and term.

+ *

An index contains a sequence of documents.

+ *
    + *
  • A document is a sequence of fields.
    • + *
  • A field is a named sequence of terms.
    • + *
  • A term is a sequence of bytes.
    • + *
+ *

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.

+ * + *

Inverted Indexing

+ *

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 + * inverted index. 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.

+ * + *

Types of Fields

+ *

In Lucene, fields may be stored, in which case their text is stored + * in the index literally, in a non-inverted manner. Fields that are inverted are + * called indexed. A field may be both stored and indexed.

+ *

The text of a field may be tokenized 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.

+ *

See the {@link org.apache.lucene.document.Field Field} + * java docs for more information on Fields.

+ * + *

Segments

+ *

Lucene indexes may be composed of multiple sub-indexes, or segments. + * Each segment is a fully independent index, which could be searched separately. + * Indexes evolve by:

+ *
    + *
  1. Creating new segments for newly added documents.
    2. + *
  2. Merging existing segments.
    3. + *
+ *

Searches may involve multiple segments and/or multiple indexes, each index + * potentially composed of a set of segments.

+ * + *

Document Numbers

+ *

Internally, Lucene refers to documents by an integer document number. + * The first document added to an index is numbered zero, and each subsequent + * document added gets a number one greater than the previous.

+ *

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:

+ *
    + *
  • + *

    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 base 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.

    + *
    • + *
  • + *

    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.

    + *
    • + *
+ *
+ * + *

Index Structure Overview

+ *
+ *

Each segment index maintains the following:

+ *
    + *
  • + * {@link org.apache.lucene.codecs.lucene50.Lucene50SegmentInfoFormat Segment info}. + * This contains metadata about a segment, such as the number of documents, + * what files it uses, + *
    • + *
  • + * {@link org.apache.lucene.codecs.lucene50.Lucene50FieldInfosFormat Field names}. + * This contains the set of field names used in the index. + *
    • + *
  • + * {@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. + *
    • + *
  • + * {@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. + *
    • + *
  • + * {@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) + *
    • + *
  • + * {@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. + *
    • + *
  • + * {@link org.apache.lucene.codecs.lucene53.Lucene53NormsFormat Normalization factors}. + * For each field in each document, a value is stored + * that is multiplied into the score for hits on that field. + *
    • + *
  • + * {@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 + *
    • + *
  • + * {@link org.apache.lucene.codecs.lucene50.Lucene50DocValuesFormat 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. + *
    • + *
  • + * {@link org.apache.lucene.codecs.lucene50.Lucene50LiveDocsFormat Live documents}. + * An optional file indicating which documents are live. + *
    • + *
+ *

Details on each of these are provided in their linked pages.

+ *
+ * + *

File Naming

+ *
+ *

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 in 1.4 and greater) 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)

+ *

Typically, all segments in an index are stored in a single directory, + * although this is not required.

+ *

As of version 2.1 (lock-less commits), 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.

+ *
+ * + *

Summary of File Extensions

+ *
+ *

The following table summarizes the names and extensions of the files in + * Lucene:

+ * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + * + *
NameExtensionBrief Description
{@link org.apache.lucene.index.SegmentInfos Segments File}segments_NStores information about a commit point
Lock Filewrite.lockThe Write lock prevents multiple IndexWriters from writing to the same + * file.
{@link org.apache.lucene.codecs.lucene50.Lucene50SegmentInfoFormat Segment Info}.siStores metadata about a segment
{@link org.apache.lucene.codecs.lucene50.Lucene50CompoundFormat Compound File}.cfs, .cfeAn optional "virtual" file consisting of all the other index files for + * systems that frequently run out of file handles.
{@link org.apache.lucene.codecs.lucene50.Lucene50FieldInfosFormat Fields}.fnmStores information about the fields
{@link org.apache.lucene.codecs.lucene50.Lucene50StoredFieldsFormat Field Index}.fdxContains pointers to field data
{@link org.apache.lucene.codecs.lucene50.Lucene50StoredFieldsFormat Field Data}.fdtThe stored fields for documents
{@link org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat Term Dictionary}.timThe term dictionary, stores term info
{@link org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat Term Index}.tipThe index into the Term Dictionary
{@link org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat Frequencies}.docContains the list of docs which contain each term along with frequency
{@link org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat Positions}.posStores position information about where a term occurs in the index
{@link org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat Payloads}.payStores additional per-position metadata information such as character offsets and user payloads
{@link org.apache.lucene.codecs.lucene53.Lucene53NormsFormat Norms}.nvd, .nvmEncodes length and boost factors for docs and fields
{@link org.apache.lucene.codecs.lucene50.Lucene50DocValuesFormat Per-Document Values}.dvd, .dvmEncodes additional scoring factors or other per-document information.
{@link org.apache.lucene.codecs.lucene50.Lucene50TermVectorsFormat Term Vector Index}.tvxStores offset into the document data file
{@link org.apache.lucene.codecs.lucene50.Lucene50TermVectorsFormat Term Vector Documents}.tvdContains information about each document that has term vectors
{@link org.apache.lucene.codecs.lucene50.Lucene50TermVectorsFormat Term Vector Fields}.tvfThe field level info about term vectors
{@link org.apache.lucene.codecs.lucene50.Lucene50LiveDocsFormat Live Documents}.livInfo about what files are live
+ *
+ * + *

Lock File

+ * 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. + * + *

History

+ *

Compatibility notes are provided in this document, describing how file + * formats have changed from prior versions:

+ *
    + *
  • 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.
    • + *
  • 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).
    • + *
  • In version 2.4, Strings are now written as true UTF-8 byte sequence, not + * Java's modified UTF-8. See + * LUCENE-510 for details.
    • + *
  • 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 + * LUCENE-1382 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 + * LUCENE-1654 for details.
    • + *
  • 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 LUCENE-1960 + * for details.
    • + *
  • In version 3.1, segments records the code version that created them. See + * LUCENE-2720 for details. + * Additionally segments track explicitly whether or not they have term vectors. + * See LUCENE-2811 + * for details.
    • + *
  • In version 3.2, numeric fields are written as natively to stored fields + * file, previously they were stored in text format only.
    • + *
  • In version 3.4, fields can omit position data while still indexing term + * frequencies.
    • + *
  • 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.
    • + *
  • 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.
    • + *
  • 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.
    • + *
  • In version 4.5, DocValues were extended to explicitly represent missing values.
    • + *
  • In version 4.6, FieldInfos were extended to support per-field DocValues generation, to + * allow updating NumericDocValues fields.
    • + *
  • 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.
    • + *
  • In version 4.9, DocValues has a new multi-valued numeric type (SortedNumeric) + * that is suitable for faceting/sorting/analytics. + *
    • + *
+ * + *

Limitations

+ *
+ *

Lucene uses a Java int to refer to + * document numbers, and the index file format uses an Int32 + * 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 UInt64 values, or + * better yet, {@link org.apache.lucene.store.DataOutput#writeVInt VInt} values which have no limit.

+ *
+ */ +package org.apache.lucene.codecs.lucene53; diff --git a/lucene/core/src/java/org/apache/lucene/store/ByteBufferIndexInput.java b/lucene/core/src/java/org/apache/lucene/store/ByteBufferIndexInput.java index dac15932010..b29b06a19d7 100644 --- a/lucene/core/src/java/org/apache/lucene/store/ByteBufferIndexInput.java +++ b/lucene/core/src/java/org/apache/lucene/store/ByteBufferIndexInput.java @@ -54,7 +54,7 @@ abstract class ByteBufferIndexInput extends IndexInput implements RandomAccessIn if (buffers.length == 1) { return new SingleBufferImpl(resourceDescription, buffers[0], length, chunkSizePower, cleaner, clones); } else { - return new DefaultImpl(resourceDescription, buffers, length, chunkSizePower, cleaner, clones); + return new MultiBufferImpl(resourceDescription, buffers, 0, length, chunkSizePower, cleaner, clones); } } @@ -301,9 +301,7 @@ abstract class ByteBufferIndexInput extends IndexInput implements RandomAccessIn newBuffers[0].position(offset); return new SingleBufferImpl(newResourceDescription, newBuffers[0].slice(), length, chunkSizePower, this.cleaner, this.clones); } else { - return (offset == 0) ? - new DefaultImpl(newResourceDescription, newBuffers, length, chunkSizePower, cleaner, clones) : - new WithOffsetImpl(newResourceDescription, newBuffers, offset, length, chunkSizePower, cleaner, clones); + return new MultiBufferImpl(newResourceDescription, newBuffers, offset, length, chunkSizePower, cleaner, clones); } } @@ -388,21 +386,6 @@ abstract class ByteBufferIndexInput extends IndexInput implements RandomAccessIn void freeBuffer(ByteBufferIndexInput parent, ByteBuffer b) throws IOException; } - /** Default implementation of ByteBufferIndexInput, supporting multiple buffers, but no offset. */ - static final class DefaultImpl extends ByteBufferIndexInput { - - DefaultImpl(String resourceDescription, ByteBuffer[] buffers, long length, int chunkSizePower, - BufferCleaner cleaner, WeakIdentityMap clones) { - super(resourceDescription, buffers, length, chunkSizePower, cleaner, clones); - try { - seek(0L); - } catch (IOException ioe) { - throw new AssertionError(ioe); - } - } - - } - /** Optimization of ByteBufferIndexInput for when there is only one buffer */ static final class SingleBufferImpl extends ByteBufferIndexInput { @@ -502,10 +485,10 @@ abstract class ByteBufferIndexInput extends IndexInput implements RandomAccessIn } /** This class adds offset support to ByteBufferIndexInput, which is needed for slices. */ - static final class WithOffsetImpl extends ByteBufferIndexInput { + static final class MultiBufferImpl extends ByteBufferIndexInput { private final int offset; - WithOffsetImpl(String resourceDescription, ByteBuffer[] buffers, int offset, long length, int chunkSizePower, + MultiBufferImpl(String resourceDescription, ByteBuffer[] buffers, int offset, long length, int chunkSizePower, BufferCleaner cleaner, WeakIdentityMap clones) { super(resourceDescription, buffers, length, chunkSizePower, cleaner, clones); this.offset = offset; @@ -518,10 +501,7 @@ abstract class ByteBufferIndexInput extends IndexInput implements RandomAccessIn @Override public void seek(long pos) throws IOException { - // necessary in case offset != 0 and pos < 0, but pos >= -offset - if (pos < 0L) { - throw new IllegalArgumentException("Seeking to negative position: " + this); - } + assert pos >= 0L; super.seek(pos + offset); } diff --git a/lucene/core/src/resources/META-INF/services/org.apache.lucene.codecs.Codec b/lucene/core/src/resources/META-INF/services/org.apache.lucene.codecs.Codec index 2d066a7234c..db60db6e42b 100644 --- a/lucene/core/src/resources/META-INF/services/org.apache.lucene.codecs.Codec +++ b/lucene/core/src/resources/META-INF/services/org.apache.lucene.codecs.Codec @@ -13,4 +13,4 @@ # See the License for the specific language governing permissions and # limitations under the License. -org.apache.lucene.codecs.lucene50.Lucene50Codec +org.apache.lucene.codecs.lucene53.Lucene53Codec diff --git a/lucene/core/src/test/org/apache/lucene/codecs/lucene50/TestLucene50StoredFieldsFormatHighCompression.java b/lucene/core/src/test/org/apache/lucene/codecs/lucene50/TestLucene50StoredFieldsFormatHighCompression.java index 371e309298e..b7026c5c965 100644 --- a/lucene/core/src/test/org/apache/lucene/codecs/lucene50/TestLucene50StoredFieldsFormatHighCompression.java +++ b/lucene/core/src/test/org/apache/lucene/codecs/lucene50/TestLucene50StoredFieldsFormatHighCompression.java @@ -19,6 +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.lucene53.Lucene53Codec; import org.apache.lucene.document.Document; import org.apache.lucene.document.StoredField; import org.apache.lucene.index.BaseStoredFieldsFormatTestCase; @@ -33,7 +34,7 @@ import com.carrotsearch.randomizedtesting.generators.RandomPicks; public class TestLucene50StoredFieldsFormatHighCompression extends BaseStoredFieldsFormatTestCase { @Override protected Codec getCodec() { - return new Lucene50Codec(Mode.BEST_COMPRESSION); + return new Lucene53Codec(Mode.BEST_COMPRESSION); } /** @@ -44,7 +45,7 @@ public class TestLucene50StoredFieldsFormatHighCompression extends BaseStoredFie Directory dir = newDirectory(); for (int i = 0; i < 10; i++) { IndexWriterConfig iwc = newIndexWriterConfig(); - iwc.setCodec(new Lucene50Codec(RandomPicks.randomFrom(random(), Mode.values()))); + iwc.setCodec(new Lucene53Codec(RandomPicks.randomFrom(random(), Mode.values()))); IndexWriter iw = new IndexWriter(dir, newIndexWriterConfig()); Document doc = new Document(); doc.add(new StoredField("field1", "value1")); @@ -71,7 +72,7 @@ public class TestLucene50StoredFieldsFormatHighCompression extends BaseStoredFie public void testInvalidOptions() throws Exception { try { - new Lucene50Codec(null); + new Lucene53Codec(null); fail("didn't hit exception"); } catch (NullPointerException expected) { // expected diff --git a/lucene/core/src/test/org/apache/lucene/codecs/lucene53/TestLucene53NormsFormat.java b/lucene/core/src/test/org/apache/lucene/codecs/lucene53/TestLucene53NormsFormat.java new file mode 100644 index 00000000000..e086c70667d --- /dev/null +++ b/lucene/core/src/test/org/apache/lucene/codecs/lucene53/TestLucene53NormsFormat.java @@ -0,0 +1,34 @@ +package org.apache.lucene.codecs.lucene53; + +/* + * 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 org.apache.lucene.codecs.Codec; +import org.apache.lucene.index.BaseNormsFormatTestCase; + +/** + * Tests Lucene53NormsFormat + */ +public class TestLucene53NormsFormat extends BaseNormsFormatTestCase { + private final Codec codec = new Lucene53Codec(); + + @Override + protected Codec getCodec() { + return codec; + } + +} diff --git a/lucene/core/src/test/org/apache/lucene/index/Test2BTerms.java b/lucene/core/src/test/org/apache/lucene/index/Test2BTerms.java index 997459bd9e0..49df315e4ee 100644 --- a/lucene/core/src/test/org/apache/lucene/index/Test2BTerms.java +++ b/lucene/core/src/test/org/apache/lucene/index/Test2BTerms.java @@ -51,7 +51,7 @@ import com.carrotsearch.randomizedtesting.annotations.TimeoutSuite; // disk (but, should run successfully). Best to run w/ // -Dtests.codec=, and w/ plenty of RAM, eg: // -// ant test -Dtests.monster=true -Dtests.heapsize=8g -Dtests.codec=Lucene50 -Dtestcase=Test2BTerms +// ant test -Dtests.monster=true -Dtests.heapsize=8g -Dtests.codec=Lucene53 -Dtestcase=Test2BTerms // @SuppressCodecs({ "SimpleText", "Memory", "Direct" }) @Monster("very slow, use 5g minimum heap") diff --git a/lucene/core/src/test/org/apache/lucene/store/TestMultiMMap.java b/lucene/core/src/test/org/apache/lucene/store/TestMultiMMap.java index bfff86f8d61..1abbe7c90c2 100644 --- a/lucene/core/src/test/org/apache/lucene/store/TestMultiMMap.java +++ b/lucene/core/src/test/org/apache/lucene/store/TestMultiMMap.java @@ -386,7 +386,7 @@ public class TestMultiMMap extends BaseDirectoryTestCase { ii.seek(0L); // check impl (we must check size < chunksize: currently, if size==chunkSize, we get 2 buffers, the second one empty: - assertTrue((size < chunkSize) ? (ii instanceof ByteBufferIndexInput.SingleBufferImpl) : (ii instanceof ByteBufferIndexInput.DefaultImpl)); + assertTrue((size < chunkSize) ? (ii instanceof ByteBufferIndexInput.SingleBufferImpl) : (ii instanceof ByteBufferIndexInput.MultiBufferImpl)); // clone tests: assertSame(ii.getClass(), ii.clone().getClass()); @@ -394,7 +394,7 @@ public class TestMultiMMap extends BaseDirectoryTestCase { // slice test (offset 0) int sliceSize = random().nextInt(size); IndexInput slice = ii.slice("slice", 0, sliceSize); - assertTrue((sliceSize < chunkSize) ? (slice instanceof ByteBufferIndexInput.SingleBufferImpl) : (slice instanceof ByteBufferIndexInput.DefaultImpl)); + assertTrue((sliceSize < chunkSize) ? (slice instanceof ByteBufferIndexInput.SingleBufferImpl) : (slice instanceof ByteBufferIndexInput.MultiBufferImpl)); // slice test (offset > 0 ) int offset = random().nextInt(size - 1) + 1; @@ -403,10 +403,8 @@ public class TestMultiMMap extends BaseDirectoryTestCase { //System.out.println(offset + "/" + sliceSize + " chunkSize=" + chunkSize + " " + slice.getClass()); if (offset % chunkSize + sliceSize < chunkSize) { assertTrue(slice instanceof ByteBufferIndexInput.SingleBufferImpl); - } else if (offset % chunkSize == 0) { - assertTrue(slice instanceof ByteBufferIndexInput.DefaultImpl); } else { - assertTrue(slice instanceof ByteBufferIndexInput.WithOffsetImpl); + assertTrue(slice instanceof ByteBufferIndexInput.MultiBufferImpl); } ii.close(); diff --git a/lucene/sandbox/src/test/org/apache/lucene/bkdtree/TestBKDTree.java b/lucene/sandbox/src/test/org/apache/lucene/bkdtree/TestBKDTree.java index 1ebe75876a5..8a0d64b687b 100644 --- a/lucene/sandbox/src/test/org/apache/lucene/bkdtree/TestBKDTree.java +++ b/lucene/sandbox/src/test/org/apache/lucene/bkdtree/TestBKDTree.java @@ -19,7 +19,7 @@ package org.apache.lucene.bkdtree; import org.apache.lucene.codecs.Codec; import org.apache.lucene.codecs.DocValuesFormat; -import org.apache.lucene.codecs.lucene50.Lucene50Codec; +import org.apache.lucene.codecs.lucene53.Lucene53Codec; import org.apache.lucene.document.Document; import org.apache.lucene.document.Field; import org.apache.lucene.document.NumericDocValuesField; @@ -369,7 +369,7 @@ public class TestBKDTree extends LuceneTestCase { iwc.setMaxBufferedDocs(lats.length/100); } final DocValuesFormat dvFormat = new BKDTreeDocValuesFormat(maxPointsInLeaf, maxPointsSortInHeap); - Codec codec = new Lucene50Codec() { + Codec codec = new Lucene53Codec() { @Override public DocValuesFormat getDocValuesFormatForField(String field) { if (field.equals("point")) { diff --git a/lucene/suggest/src/test/org/apache/lucene/search/suggest/document/TestSuggestField.java b/lucene/suggest/src/test/org/apache/lucene/search/suggest/document/TestSuggestField.java index 4e915280a7d..6d7d9388321 100644 --- a/lucene/suggest/src/test/org/apache/lucene/search/suggest/document/TestSuggestField.java +++ b/lucene/suggest/src/test/org/apache/lucene/search/suggest/document/TestSuggestField.java @@ -30,7 +30,7 @@ import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.MockAnalyzer; import org.apache.lucene.codecs.Codec; import org.apache.lucene.codecs.PostingsFormat; -import org.apache.lucene.codecs.lucene50.Lucene50Codec; +import org.apache.lucene.codecs.lucene53.Lucene53Codec; import org.apache.lucene.document.Document; import org.apache.lucene.document.Field; import org.apache.lucene.document.IntField; @@ -626,7 +626,7 @@ public class TestSuggestField extends LuceneTestCase { static IndexWriterConfig iwcWithSuggestField(Analyzer analyzer, final Set suggestFields) { IndexWriterConfig iwc = newIndexWriterConfig(random(), analyzer); iwc.setMergePolicy(newLogMergePolicy()); - Codec filterCodec = new Lucene50Codec() { + Codec filterCodec = new Lucene53Codec() { PostingsFormat postingsFormat = new Completion50PostingsFormat(); @Override diff --git a/lucene/test-framework/src/java/org/apache/lucene/util/TestRuleSetupAndRestoreClassEnv.java b/lucene/test-framework/src/java/org/apache/lucene/util/TestRuleSetupAndRestoreClassEnv.java index 69b00df85d1..03f5afbd1f2 100644 --- a/lucene/test-framework/src/java/org/apache/lucene/util/TestRuleSetupAndRestoreClassEnv.java +++ b/lucene/test-framework/src/java/org/apache/lucene/util/TestRuleSetupAndRestoreClassEnv.java @@ -34,8 +34,8 @@ import org.apache.lucene.codecs.asserting.AssertingDocValuesFormat; 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.Lucene50Codec; import org.apache.lucene.codecs.lucene50.Lucene50StoredFieldsFormat; +import org.apache.lucene.codecs.lucene53.Lucene53Codec; import org.apache.lucene.codecs.mockrandom.MockRandomPostingsFormat; import org.apache.lucene.codecs.simpletext.SimpleTextCodec; import org.apache.lucene.index.RandomCodec; @@ -184,8 +184,8 @@ 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 ("Lucene50".equals(TEST_CODEC) || ("random".equals(TEST_CODEC) && randomVal == 5 && !shouldAvoidCodec("Lucene50"))) { - codec = new Lucene50Codec(RandomPicks.randomFrom(random, Lucene50StoredFieldsFormat.Mode.values())); + } else if ("Lucene53".equals(TEST_CODEC) || ("random".equals(TEST_CODEC) && randomVal == 5 && !shouldAvoidCodec("Lucene53"))) { + codec = new Lucene53Codec(RandomPicks.randomFrom(random, Lucene50StoredFieldsFormat.Mode.values())); } else if (!"random".equals(TEST_CODEC)) { codec = Codec.forName(TEST_CODEC); } else if ("random".equals(TEST_POSTINGSFORMAT)) { diff --git a/lucene/test-framework/src/java/org/apache/lucene/util/TestUtil.java b/lucene/test-framework/src/java/org/apache/lucene/util/TestUtil.java index a66c6beb411..7c948b5d490 100644 --- a/lucene/test-framework/src/java/org/apache/lucene/util/TestUtil.java +++ b/lucene/test-framework/src/java/org/apache/lucene/util/TestUtil.java @@ -54,9 +54,9 @@ import org.apache.lucene.codecs.PostingsFormat; 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.Lucene50Codec; import org.apache.lucene.codecs.lucene50.Lucene50DocValuesFormat; import org.apache.lucene.codecs.lucene50.Lucene50PostingsFormat; +import org.apache.lucene.codecs.lucene53.Lucene53Codec; import org.apache.lucene.codecs.perfield.PerFieldDocValuesFormat; import org.apache.lucene.codecs.perfield.PerFieldPostingsFormat; import org.apache.lucene.document.BinaryDocValuesField; @@ -881,7 +881,7 @@ public final class TestUtil { * This may be different than {@link Codec#getDefault()} because that is randomized. */ public static Codec getDefaultCodec() { - return new Lucene50Codec(); + return new Lucene53Codec(); } /** diff --git a/solr/core/src/java/org/apache/solr/core/SchemaCodecFactory.java b/solr/core/src/java/org/apache/solr/core/SchemaCodecFactory.java index 8b523ef5efc..4b285ff887c 100644 --- a/solr/core/src/java/org/apache/solr/core/SchemaCodecFactory.java +++ b/solr/core/src/java/org/apache/solr/core/SchemaCodecFactory.java @@ -3,7 +3,7 @@ package org.apache.solr.core; import org.apache.lucene.codecs.Codec; import org.apache.lucene.codecs.DocValuesFormat; import org.apache.lucene.codecs.PostingsFormat; -import org.apache.lucene.codecs.lucene50.Lucene50Codec; +import org.apache.lucene.codecs.lucene53.Lucene53Codec; import org.apache.solr.common.util.NamedList; import org.apache.solr.schema.SchemaField; import org.apache.solr.util.plugin.SolrCoreAware; @@ -51,7 +51,7 @@ public class SchemaCodecFactory extends CodecFactory implements SolrCoreAware { @Override public void init(NamedList args) { super.init(args); - codec = new Lucene50Codec() { + codec = new Lucene53Codec() { @Override public PostingsFormat getPostingsFormatForField(String field) { final SchemaField schemaField = core.getLatestSchema().getFieldOrNull(field);