You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by rm...@apache.org on 2014/09/28 16:36:02 UTC
svn commit: r1628070 [1/3] - in /lucene/dev/branches/lucene5969:
lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/
lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene41/
lucene/backward-codecs/src/java/org/apache/lucene/cod...
Author: rmuir
Date: Sun Sep 28 14:36:00 2014
New Revision: 1628070
URL: http://svn.apache.org/r1628070
Log:
LUCENE-5969: fix compile/javadocs, tighten up backwards codecs, add more safety to 5.x fields/vectors
Modified:
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/BitVector.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40Codec.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40DocValuesFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40DocValuesReader.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40FieldInfosFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40FieldInfosReader.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40LiveDocsFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40NormsFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40NormsReader.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40PostingsBaseFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40PostingsFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40PostingsReader.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40SegmentInfoFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40SegmentInfoReader.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40SkipListReader.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40StoredFieldsFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40StoredFieldsReader.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40TermVectorsFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40TermVectorsReader.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene41/Lucene41Codec.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene41/Lucene41StoredFieldsFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene41/Lucene41StoredFieldsIndexReader.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene410/Lucene410Codec.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene42/Lucene42Codec.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene42/Lucene42DocValuesFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene42/Lucene42DocValuesProducer.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene42/Lucene42FieldInfosFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene42/Lucene42FieldInfosReader.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene42/Lucene42NormsFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene42/Lucene42NormsProducer.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene42/Lucene42TermVectorsReader.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene45/Lucene45Codec.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene45/Lucene45DocValuesConsumer.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene45/Lucene45DocValuesFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene45/Lucene45DocValuesProducer.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene46/Lucene46Codec.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene46/Lucene46FieldInfosFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene46/Lucene46FieldInfosReader.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene46/Lucene46FieldInfosWriter.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene46/Lucene46SegmentInfoFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene46/Lucene46SegmentInfoReader.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene49/Lucene49Codec.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene49/Lucene49DocValuesConsumer.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene49/Lucene49DocValuesFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene49/Lucene49DocValuesProducer.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene40/Lucene40DocValuesWriter.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene40/Lucene40FieldInfosWriter.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene40/Lucene40PostingsWriter.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene40/Lucene40RWCodec.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene40/Lucene40RWDocValuesFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene40/Lucene40RWNormsFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene40/Lucene40RWPostingsFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene40/Lucene40RWSegmentInfoFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene40/Lucene40RWStoredFieldsFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene40/Lucene40RWTermVectorsFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene40/Lucene40SegmentInfoWriter.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene40/Lucene40SkipListWriter.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene40/Lucene40StoredFieldsWriter.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene40/Lucene40TermVectorsWriter.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene40/TestBitVector.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene40/TestLucene40StoredFieldsFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene40/TestLucene40TermVectorsFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene41/Lucene41RWCodec.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene41/Lucene41RWStoredFieldsFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene41/Lucene41StoredFieldsIndexWriter.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene41/Lucene41StoredFieldsWriter.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene42/Lucene42DocValuesConsumer.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene42/Lucene42FieldInfosWriter.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene42/Lucene42NormsConsumer.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene42/Lucene42RWCodec.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene42/Lucene42RWDocValuesFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene42/Lucene42RWNormsFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene42/Lucene42RWTermVectorsFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene42/Lucene42TermVectorsWriter.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene45/Lucene45RWCodec.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene45/Lucene45RWDocValuesFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene45/TestLucene45DocValuesFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene46/Lucene46RWCodec.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene46/Lucene46RWSegmentInfoFormat.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene46/Lucene46SegmentInfoWriter.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene49/Lucene49RWCodec.java
lucene/dev/branches/lucene5969/lucene/backward-codecs/src/test/org/apache/lucene/codecs/lucene49/Lucene49RWDocValuesFormat.java
lucene/dev/branches/lucene5969/lucene/core/src/java/org/apache/lucene/codecs/compressing/CompressingStoredFieldsReader.java
lucene/dev/branches/lucene5969/lucene/core/src/java/org/apache/lucene/codecs/compressing/CompressingTermVectorsReader.java
lucene/dev/branches/lucene5969/lucene/core/src/java/org/apache/lucene/codecs/compressing/MatchingReaders.java
lucene/dev/branches/lucene5969/lucene/core/src/java/org/apache/lucene/index/MergeState.java
lucene/dev/branches/lucene5969/solr/core/src/java/org/apache/solr/update/SolrIndexConfig.java
lucene/dev/branches/lucene5969/solr/core/src/test/org/apache/solr/update/SolrIndexConfigTest.java
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/BitVector.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/BitVector.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/BitVector.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/BitVector.java Sun Sep 28 14:36:00 2014
@@ -31,19 +31,11 @@ import org.apache.lucene.store.IndexOutp
import org.apache.lucene.util.BitUtil;
import org.apache.lucene.util.MutableBits;
-/** Optimized implementation of a vector of bits. This is more-or-less like
- * java.util.BitSet, but also includes the following:
- * <ul>
- * <li>a count() method, which efficiently computes the number of one bits;</li>
- * <li>optimized read from and write to disk;</li>
- * <li>inlinable get() method;</li>
- * <li>store and load, as bit set or d-gaps, depending on sparseness;</li>
- * </ul>
- *
- * @lucene.internal
+/**
+ * Bitset for support of 4.x live documents
+ * @deprecated only for old 4.x segments
*/
-// pkg-private: if this thing is generally useful then it can go back in .util,
-// but the serialization must be here underneath the codec.
+@Deprecated
final class BitVector implements Cloneable, MutableBits {
private byte[] bits;
@@ -52,7 +44,7 @@ final class BitVector implements Cloneab
private int version;
/** Constructs a vector capable of holding <code>n</code> bits. */
- public BitVector(int n) {
+ BitVector(int n) {
size = n;
bits = new byte[getNumBytes(size)];
count = 0;
@@ -90,27 +82,6 @@ final class BitVector implements Cloneab
count = -1;
}
- /** Sets the value of <code>bit</code> to true, and
- * returns true if bit was already set */
- public final boolean getAndSet(int bit) {
- if (bit >= size) {
- throw new ArrayIndexOutOfBoundsException("bit=" + bit + " size=" + size);
- }
- final int pos = bit >> 3;
- final int v = bits[pos];
- final int flag = 1 << (bit & 7);
- if ((flag & v) != 0)
- return true;
- else {
- bits[pos] = (byte) (v | flag);
- if (count != -1) {
- count++;
- assert count <= size;
- }
- return false;
- }
- }
-
/** Sets the value of <code>bit</code> to zero. */
@Override
public final void clear(int bit) {
@@ -121,25 +92,6 @@ final class BitVector implements Cloneab
count = -1;
}
- public final boolean getAndClear(int bit) {
- if (bit >= size) {
- throw new ArrayIndexOutOfBoundsException(bit);
- }
- final int pos = bit >> 3;
- final int v = bits[pos];
- final int flag = 1 << (bit & 7);
- if ((flag & v) == 0) {
- return false;
- } else {
- bits[pos] &= ~flag;
- if (count != -1) {
- count--;
- assert count >= 0;
- }
- return true;
- }
- }
-
/** Returns <code>true</code> if <code>bit</code> is one and
<code>false</code> if it is zero. */
@Override
@@ -150,7 +102,7 @@ final class BitVector implements Cloneab
/** Returns the number of bits in this vector. This is also one greater than
the number of the largest valid bit number. */
- public final int size() {
+ final int size() {
return size;
}
@@ -162,7 +114,7 @@ final class BitVector implements Cloneab
/** Returns the total number of one bits in this vector. This is efficiently
computed and cached, so that, if the vector is not changed, no
recomputation is done for repeated calls. */
- public final int count() {
+ final int count() {
// if the vector has been modified
if (count == -1) {
int c = 0;
@@ -177,7 +129,7 @@ final class BitVector implements Cloneab
}
/** For testing */
- public final int getRecomputedCount() {
+ final int getRecomputedCount() {
int c = 0;
int end = bits.length;
for (int i = 0; i < end; i++) {
@@ -191,29 +143,29 @@ final class BitVector implements Cloneab
private static String CODEC = "BitVector";
// Version before version tracking was added:
- public final static int VERSION_PRE = -1;
+ final static int VERSION_PRE = -1;
// First version:
- public final static int VERSION_START = 0;
+ final static int VERSION_START = 0;
// Changed DGaps to encode gaps between cleared bits, not
// set:
- public final static int VERSION_DGAPS_CLEARED = 1;
+ final static int VERSION_DGAPS_CLEARED = 1;
// added checksum
- public final static int VERSION_CHECKSUM = 2;
+ final static int VERSION_CHECKSUM = 2;
// Increment version to change it:
- public final static int VERSION_CURRENT = VERSION_CHECKSUM;
+ final static int VERSION_CURRENT = VERSION_CHECKSUM;
- public int getVersion() {
+ int getVersion() {
return version;
}
/** Writes this vector to the file <code>name</code> in Directory
<code>d</code>, in a format that can be read by the constructor {@link
#BitVector(Directory, String, IOContext)}. */
- public final void write(Directory d, String name, IOContext context) throws IOException {
+ final void write(Directory d, String name, IOContext context) throws IOException {
assert !(d instanceof CompoundFileDirectory);
try (IndexOutput output = d.createOutput(name, context)) {
output.writeInt(-2);
@@ -230,7 +182,7 @@ final class BitVector implements Cloneab
}
/** Invert all bits */
- public void invertAll() {
+ void invertAll() {
if (count != -1) {
count = size - count;
}
@@ -254,13 +206,6 @@ final class BitVector implements Cloneab
}
}
- /** Set all bits */
- public void setAll() {
- Arrays.fill(bits, (byte) 0xff);
- clearUnusedBits();
- count = size;
- }
-
/** Write as a bit set */
private void writeBits(IndexOutput output) throws IOException {
output.writeInt(size()); // write size
@@ -325,7 +270,7 @@ final class BitVector implements Cloneab
/** Constructs a bit vector from the file <code>name</code> in Directory
<code>d</code>, as written by the {@link #write} method.
*/
- public BitVector(Directory d, String name, IOContext context) throws IOException {
+ BitVector(Directory d, String name, IOContext context) throws IOException {
try (ChecksumIndexInput input = d.openChecksumInput(name, context)) {
final int firstInt = input.readInt();
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40Codec.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40Codec.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40Codec.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40Codec.java Sun Sep 28 14:36:00 2014
@@ -19,7 +19,6 @@ package org.apache.lucene.codecs.lucene4
import org.apache.lucene.codecs.Codec;
import org.apache.lucene.codecs.FieldInfosFormat;
-import org.apache.lucene.codecs.FilterCodec;
import org.apache.lucene.codecs.LiveDocsFormat;
import org.apache.lucene.codecs.PostingsFormat;
import org.apache.lucene.codecs.SegmentInfoFormat;
@@ -30,17 +29,9 @@ import org.apache.lucene.codecs.TermVect
import org.apache.lucene.codecs.perfield.PerFieldPostingsFormat;
/**
- * Implements the Lucene 4.0 index format, with configurable per-field postings formats.
- * <p>
- * If you want to reuse functionality of this codec in another codec, extend
- * {@link FilterCodec}.
- *
- * @see org.apache.lucene.codecs.lucene40 package documentation for file format details.
+ * Reader for the 4.0 file format
* @deprecated Only for reading old 4.0 segments
*/
-// NOTE: if we make largish changes in a minor release, easier to just make Lucene42Codec or whatever
-// if they are backwards compatible or smallish we can probably do the backwards in the postingsreader
-// (it writes a minor version, etc).
@Deprecated
public class Lucene40Codec extends Codec {
private final StoredFieldsFormat fieldsFormat = new Lucene40StoredFieldsFormat();
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40DocValuesFormat.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40DocValuesFormat.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40DocValuesFormat.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40DocValuesFormat.java Sun Sep 28 14:36:00 2014
@@ -19,119 +19,22 @@ package org.apache.lucene.codecs.lucene4
import java.io.IOException;
-import org.apache.lucene.codecs.CodecUtil;
import org.apache.lucene.codecs.DocValuesConsumer;
import org.apache.lucene.codecs.DocValuesFormat;
import org.apache.lucene.codecs.DocValuesProducer;
import org.apache.lucene.index.IndexFileNames;
import org.apache.lucene.index.SegmentReadState;
import org.apache.lucene.index.SegmentWriteState;
-import org.apache.lucene.store.CompoundFileDirectory;
-import org.apache.lucene.store.DataOutput;
-import org.apache.lucene.util.packed.PackedInts;
/**
* Lucene 4.0 DocValues format.
- * <p>
- * Files:
- * <ul>
- * <li><tt>.dv.cfs</tt>: {@link CompoundFileDirectory compound container}</li>
- * <li><tt>.dv.cfe</tt>: {@link CompoundFileDirectory compound entries}</li>
- * </ul>
- * Entries within the compound file:
- * <ul>
- * <li><tt><segment>_<fieldNumber>.dat</tt>: data values</li>
- * <li><tt><segment>_<fieldNumber>.idx</tt>: index into the .dat for DEREF types</li>
- * </ul>
- * <p>
- * There are several many types of {@code DocValues} with different encodings.
- * From the perspective of filenames, all types store their values in <tt>.dat</tt>
- * entries within the compound file. In the case of dereferenced/sorted types, the <tt>.dat</tt>
- * actually contains only the unique values, and an additional <tt>.idx</tt> file contains
- * pointers to these unique values.
- * </p>
- * Formats:
- * <ul>
- * <li>{@code VAR_INTS} .dat --> Header, PackedType, MinValue,
- * DefaultValue, PackedStream</li>
- * <li>{@code FIXED_INTS_8} .dat --> Header, ValueSize,
- * {@link DataOutput#writeByte Byte}<sup>maxdoc</sup></li>
- * <li>{@code FIXED_INTS_16} .dat --> Header, ValueSize,
- * {@link DataOutput#writeShort Short}<sup>maxdoc</sup></li>
- * <li>{@code FIXED_INTS_32} .dat --> Header, ValueSize,
- * {@link DataOutput#writeInt Int32}<sup>maxdoc</sup></li>
- * <li>{@code FIXED_INTS_64} .dat --> Header, ValueSize,
- * {@link DataOutput#writeLong Int64}<sup>maxdoc</sup></li>
- * <li>{@code FLOAT_32} .dat --> Header, ValueSize, Float32<sup>maxdoc</sup></li>
- * <li>{@code FLOAT_64} .dat --> Header, ValueSize, Float64<sup>maxdoc</sup></li>
- * <li>{@code BYTES_FIXED_STRAIGHT} .dat --> Header, ValueSize,
- * ({@link DataOutput#writeByte Byte} * ValueSize)<sup>maxdoc</sup></li>
- * <li>{@code BYTES_VAR_STRAIGHT} .idx --> Header, TotalBytes, Addresses</li>
- * <li>{@code BYTES_VAR_STRAIGHT} .dat --> Header,
- ({@link DataOutput#writeByte Byte} * <i>variable ValueSize</i>)<sup>maxdoc</sup></li>
- * <li>{@code BYTES_FIXED_DEREF} .idx --> Header, NumValues, Addresses</li>
- * <li>{@code BYTES_FIXED_DEREF} .dat --> Header, ValueSize,
- * ({@link DataOutput#writeByte Byte} * ValueSize)<sup>NumValues</sup></li>
- * <li>{@code BYTES_VAR_DEREF} .idx --> Header, TotalVarBytes, Addresses</li>
- * <li>{@code BYTES_VAR_DEREF} .dat --> Header,
- * (LengthPrefix + {@link DataOutput#writeByte Byte} * <i>variable ValueSize</i>)<sup>NumValues</sup></li>
- * <li>{@code BYTES_FIXED_SORTED} .idx --> Header, NumValues, Ordinals</li>
- * <li>{@code BYTES_FIXED_SORTED} .dat --> Header, ValueSize,
- * ({@link DataOutput#writeByte Byte} * ValueSize)<sup>NumValues</sup></li>
- * <li>{@code BYTES_VAR_SORTED} .idx --> Header, TotalVarBytes, Addresses, Ordinals</li>
- * <li>{@code BYTES_VAR_SORTED} .dat --> Header,
- * ({@link DataOutput#writeByte Byte} * <i>variable ValueSize</i>)<sup>NumValues</sup></li>
- * </ul>
- * Data Types:
- * <ul>
- * <li>Header --> {@link CodecUtil#writeHeader CodecHeader}</li>
- * <li>PackedType --> {@link DataOutput#writeByte Byte}</li>
- * <li>MaxAddress, MinValue, DefaultValue --> {@link DataOutput#writeLong Int64}</li>
- * <li>PackedStream, Addresses, Ordinals --> {@link PackedInts}</li>
- * <li>ValueSize, NumValues --> {@link DataOutput#writeInt Int32}</li>
- * <li>Float32 --> 32-bit float encoded with {@link Float#floatToRawIntBits(float)}
- * then written as {@link DataOutput#writeInt Int32}</li>
- * <li>Float64 --> 64-bit float encoded with {@link Double#doubleToRawLongBits(double)}
- * then written as {@link DataOutput#writeLong Int64}</li>
- * <li>TotalBytes --> {@link DataOutput#writeVLong VLong}</li>
- * <li>TotalVarBytes --> {@link DataOutput#writeLong Int64}</li>
- * <li>LengthPrefix --> Length of the data value as {@link DataOutput#writeVInt VInt} (maximum
- * of 2 bytes)</li>
- * </ul>
- * Notes:
- * <ul>
- * <li>PackedType is a 0 when compressed, 1 when the stream is written as 64-bit integers.</li>
- * <li>Addresses stores pointers to the actual byte location (indexed by docid). In the VAR_STRAIGHT
- * case, each entry can have a different length, so to determine the length, docid+1 is
- * retrieved. A sentinel address is written at the end for the VAR_STRAIGHT case, so the Addresses
- * stream contains maxdoc+1 indices. For the deduplicated VAR_DEREF case, each length
- * is encoded as a prefix to the data itself as a {@link DataOutput#writeVInt VInt}
- * (maximum of 2 bytes).</li>
- * <li>Ordinals stores the term ID in sorted order (indexed by docid). In the FIXED_SORTED case,
- * the address into the .dat can be computed from the ordinal as
- * <code>Header+ValueSize+(ordinal*ValueSize)</code> because the byte length is fixed.
- * In the VAR_SORTED case, there is double indirection (docid -> ordinal -> address), but
- * an additional sentinel ordinal+address is always written (so there are NumValues+1 ordinals). To
- * determine the length, ord+1's address is looked up as well.</li>
- * <li>{@code BYTES_VAR_STRAIGHT BYTES_VAR_STRAIGHT} in contrast to other straight
- * variants uses a <tt>.idx</tt> file to improve lookup perfromance. In contrast to
- * {@code BYTES_VAR_DEREF BYTES_VAR_DEREF} it doesn't apply deduplication of the document values.
- * </li>
- * </ul>
- * <p>
- * Limitations:
- * <ul>
- * <li> Binary doc values can be at most {@link #MAX_BINARY_FIELD_LENGTH} in length.
- * </ul>
* @deprecated Only for reading old 4.0 and 4.1 segments
*/
@Deprecated
-// NOTE: not registered in SPI, doesnt respect segment suffix, etc
-// for back compat only!
public class Lucene40DocValuesFormat extends DocValuesFormat {
/** Maximum length for each binary doc values field. */
- public static final int MAX_BINARY_FIELD_LENGTH = (1 << 15) - 2;
+ static final int MAX_BINARY_FIELD_LENGTH = (1 << 15) - 2;
/** Sole constructor. */
public Lucene40DocValuesFormat() {
@@ -144,7 +47,7 @@ public class Lucene40DocValuesFormat ext
}
@Override
- public DocValuesProducer fieldsProducer(SegmentReadState state) throws IOException {
+ public final DocValuesProducer fieldsProducer(SegmentReadState state) throws IOException {
String filename = IndexFileNames.segmentFileName(state.segmentInfo.name,
"dv",
IndexFileNames.COMPOUND_FILE_EXTENSION);
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40DocValuesReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40DocValuesReader.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40DocValuesReader.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40DocValuesReader.java Sun Sep 28 14:36:00 2014
@@ -48,7 +48,6 @@ import org.apache.lucene.util.packed.Pac
/**
* Reads the 4.0 format of norms/docvalues
- * @lucene.experimental
* @deprecated Only for reading old 4.0 and 4.1 segments
*/
@Deprecated
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40FieldInfosFormat.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40FieldInfosFormat.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40FieldInfosFormat.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40FieldInfosFormat.java Sun Sep 28 14:36:00 2014
@@ -19,79 +19,12 @@ package org.apache.lucene.codecs.lucene4
import java.io.IOException;
-import org.apache.lucene.codecs.CodecUtil;
import org.apache.lucene.codecs.FieldInfosFormat;
import org.apache.lucene.codecs.FieldInfosReader;
import org.apache.lucene.codecs.FieldInfosWriter;
-import org.apache.lucene.store.DataOutput; // javadoc
/**
* Lucene 4.0 Field Infos format.
- * <p>
- * <p>Field names are stored in the field info file, with suffix <tt>.fnm</tt>.</p>
- * <p>FieldInfos (.fnm) --> Header,FieldsCount, <FieldName,FieldNumber,
- * FieldBits,DocValuesBits,Attributes> <sup>FieldsCount</sup></p>
- * <p>Data types:
- * <ul>
- * <li>Header --> {@link CodecUtil#checkHeader CodecHeader}</li>
- * <li>FieldsCount --> {@link DataOutput#writeVInt VInt}</li>
- * <li>FieldName --> {@link DataOutput#writeString String}</li>
- * <li>FieldBits, DocValuesBits --> {@link DataOutput#writeByte Byte}</li>
- * <li>FieldNumber --> {@link DataOutput#writeInt VInt}</li>
- * <li>Attributes --> {@link DataOutput#writeStringStringMap Map<String,String>}</li>
- * </ul>
- * </p>
- * Field Descriptions:
- * <ul>
- * <li>FieldsCount: the number of fields in this file.</li>
- * <li>FieldName: name of the field as a UTF-8 String.</li>
- * <li>FieldNumber: the field's number. Note that unlike previous versions of
- * Lucene, the fields are not numbered implicitly by their order in the
- * file, instead explicitly.</li>
- * <li>FieldBits: a byte containing field options.
- * <ul>
- * <li>The low-order bit is one for indexed fields, and zero for non-indexed
- * fields.</li>
- * <li>The second lowest-order bit is one for fields that have term vectors
- * stored, and zero for fields without term vectors.</li>
- * <li>If the third lowest order-bit is set (0x4), offsets are stored into
- * the postings list in addition to positions.</li>
- * <li>Fourth bit is unused.</li>
- * <li>If the fifth lowest-order bit is set (0x10), norms are omitted for the
- * indexed field.</li>
- * <li>If the sixth lowest-order bit is set (0x20), payloads are stored for the
- * indexed field.</li>
- * <li>If the seventh lowest-order bit is set (0x40), term frequencies and
- * positions omitted for the indexed field.</li>
- * <li>If the eighth lowest-order bit is set (0x80), positions are omitted for the
- * indexed field.</li>
- * </ul>
- * </li>
- * <li>DocValuesBits: a byte containing per-document value types. The type
- * recorded as two four-bit integers, with the high-order bits representing
- * <code>norms</code> options, and the low-order bits representing
- * {@code DocValues} options. Each four-bit integer can be decoded as such:
- * <ul>
- * <li>0: no DocValues for this field.</li>
- * <li>1: variable-width signed integers. ({@code Type#VAR_INTS VAR_INTS})</li>
- * <li>2: 32-bit floating point values. ({@code Type#FLOAT_32 FLOAT_32})</li>
- * <li>3: 64-bit floating point values. ({@code Type#FLOAT_64 FLOAT_64})</li>
- * <li>4: fixed-length byte array values. ({@code Type#BYTES_FIXED_STRAIGHT BYTES_FIXED_STRAIGHT})</li>
- * <li>5: fixed-length dereferenced byte array values. ({@code Type#BYTES_FIXED_DEREF BYTES_FIXED_DEREF})</li>
- * <li>6: variable-length byte array values. ({@code Type#BYTES_VAR_STRAIGHT BYTES_VAR_STRAIGHT})</li>
- * <li>7: variable-length dereferenced byte array values. ({@code Type#BYTES_VAR_DEREF BYTES_VAR_DEREF})</li>
- * <li>8: 16-bit signed integers. ({@code Type#FIXED_INTS_16 FIXED_INTS_16})</li>
- * <li>9: 32-bit signed integers. ({@code Type#FIXED_INTS_32 FIXED_INTS_32})</li>
- * <li>10: 64-bit signed integers. ({@code Type#FIXED_INTS_64 FIXED_INTS_64})</li>
- * <li>11: 8-bit signed integers. ({@code Type#FIXED_INTS_8 FIXED_INTS_8})</li>
- * <li>12: fixed-length sorted byte array values. ({@code Type#BYTES_FIXED_SORTED BYTES_FIXED_SORTED})</li>
- * <li>13: variable-length sorted byte array values. ({@code Type#BYTES_VAR_SORTED BYTES_VAR_SORTED})</li>
- * </ul>
- * </li>
- * <li>Attributes: a key-value map of codec-private attributes.</li>
- * </ul>
- *
- * @lucene.experimental
* @deprecated Only for reading old 4.0 and 4.1 segments
*/
@Deprecated
@@ -103,7 +36,7 @@ public class Lucene40FieldInfosFormat ex
}
@Override
- public FieldInfosReader getFieldInfosReader() throws IOException {
+ public final FieldInfosReader getFieldInfosReader() throws IOException {
return reader;
}
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40FieldInfosReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40FieldInfosReader.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40FieldInfosReader.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40FieldInfosReader.java Sun Sep 28 14:36:00 2014
@@ -37,13 +37,10 @@ import org.apache.lucene.util.IOUtils;
/**
* Lucene 4.0 FieldInfos reader.
- *
- * @lucene.experimental
- * @see Lucene40FieldInfosFormat
* @deprecated Only for reading old 4.0 and 4.1 segments
*/
@Deprecated
-class Lucene40FieldInfosReader extends FieldInfosReader {
+final class Lucene40FieldInfosReader extends FieldInfosReader {
/** Sole constructor. */
public Lucene40FieldInfosReader() {
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40LiveDocsFormat.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40LiveDocsFormat.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40LiveDocsFormat.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40LiveDocsFormat.java Sun Sep 28 14:36:00 2014
@@ -20,12 +20,10 @@ package org.apache.lucene.codecs.lucene4
import java.io.IOException;
import java.util.Collection;
-import org.apache.lucene.codecs.CodecUtil;
import org.apache.lucene.codecs.LiveDocsFormat;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexFileNames;
import org.apache.lucene.index.SegmentCommitInfo;
-import org.apache.lucene.store.DataOutput; // javadocs
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.IOContext;
import org.apache.lucene.util.Bits;
@@ -33,37 +31,10 @@ import org.apache.lucene.util.MutableBit
/**
* Lucene 4.0 Live Documents Format.
- * <p>
- * <p>The .del file is optional, and only exists when a segment contains
- * deletions.</p>
- * <p>Although per-segment, this file is maintained exterior to compound segment
- * files.</p>
- * <p>Deletions (.del) --> Format,Header,ByteCount,BitCount, Bits | DGaps (depending
- * on Format)</p>
- * <ul>
- * <li>Format,ByteSize,BitCount --> {@link DataOutput#writeInt Uint32}</li>
- * <li>Bits --> <{@link DataOutput#writeByte Byte}> <sup>ByteCount</sup></li>
- * <li>DGaps --> <DGap,NonOnesByte> <sup>NonzeroBytesCount</sup></li>
- * <li>DGap --> {@link DataOutput#writeVInt VInt}</li>
- * <li>NonOnesByte --> {@link DataOutput#writeByte Byte}</li>
- * <li>Header --> {@link CodecUtil#writeHeader CodecHeader}</li>
- * </ul>
- * <p>Format is 1: indicates cleared DGaps.</p>
- * <p>ByteCount indicates the number of bytes in Bits. It is typically
- * (SegSize/8)+1.</p>
- * <p>BitCount indicates the number of bits that are currently set in Bits.</p>
- * <p>Bits contains one bit for each document indexed. When the bit corresponding
- * to a document number is cleared, that document is marked as deleted. Bit ordering
- * is from least to most significant. Thus, if Bits contains two bytes, 0x00 and
- * 0x02, then document 9 is marked as alive (not deleted).</p>
- * <p>DGaps represents sparse bit-vectors more efficiently than Bits. It is made
- * of DGaps on indexes of nonOnes bytes in Bits, and the nonOnes bytes themselves.
- * The number of nonOnes bytes in Bits (NonOnesBytesCount) is not stored.</p>
- * <p>For example, if there are 8000 bits and only bits 10,12,32 are cleared, DGaps
- * would be used:</p>
- * <p>(VInt) 1 , (byte) 20 , (VInt) 3 , (Byte) 1</p>
+ * @deprecated Only for reading old 4.x segments
*/
-public class Lucene40LiveDocsFormat extends LiveDocsFormat {
+@Deprecated
+public final class Lucene40LiveDocsFormat extends LiveDocsFormat {
/** Extension of deletes */
static final String DELETES_EXTENSION = "del";
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40NormsFormat.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40NormsFormat.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40NormsFormat.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40NormsFormat.java Sun Sep 28 14:36:00 2014
@@ -25,21 +25,9 @@ import org.apache.lucene.codecs.NormsPro
import org.apache.lucene.index.IndexFileNames;
import org.apache.lucene.index.SegmentReadState;
import org.apache.lucene.index.SegmentWriteState;
-import org.apache.lucene.store.CompoundFileDirectory;
/**
* Lucene 4.0 Norms Format.
- * <p>
- * Files:
- * <ul>
- * <li><tt>.nrm.cfs</tt>: {@link CompoundFileDirectory compound container}</li>
- * <li><tt>.nrm.cfe</tt>: {@link CompoundFileDirectory compound entries}</li>
- * </ul>
- * Norms are implemented as DocValues, so other than file extension, norms are
- * written exactly the same way as {@link Lucene40DocValuesFormat DocValues}.
- *
- * @see Lucene40DocValuesFormat
- * @lucene.experimental
* @deprecated Only for reading old 4.0 and 4.1 segments
*/
@Deprecated
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40NormsReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40NormsReader.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40NormsReader.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40NormsReader.java Sun Sep 28 14:36:00 2014
@@ -27,14 +27,13 @@ import org.apache.lucene.util.Accountabl
/**
* Reads 4.0/4.1 norms.
- * Implemented the same as docvalues, but with a different filename.
* @deprecated Only for reading old 4.0 and 4.1 segments
*/
@Deprecated
-class Lucene40NormsReader extends NormsProducer {
+final class Lucene40NormsReader extends NormsProducer {
private final Lucene40DocValuesReader impl;
- public Lucene40NormsReader(SegmentReadState state, String filename) throws IOException {
+ Lucene40NormsReader(SegmentReadState state, String filename) throws IOException {
impl = new Lucene40DocValuesReader(state, filename, Lucene40FieldInfosReader.LEGACY_NORM_TYPE_KEY);
}
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40PostingsBaseFormat.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40PostingsBaseFormat.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40PostingsBaseFormat.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40PostingsBaseFormat.java Sun Sep 28 14:36:00 2014
@@ -26,17 +26,13 @@ import org.apache.lucene.index.SegmentRe
import org.apache.lucene.index.SegmentWriteState;
/**
- * Provides a {@link PostingsReaderBase} and {@link
- * PostingsWriterBase}.
- *
+ * PostingsReaderBase for 4.0 segments
* @deprecated Only for reading old 4.0 segments */
-
-// TODO: should these also be named / looked up via SPI?
@Deprecated
-public final class Lucene40PostingsBaseFormat extends PostingsBaseFormat {
+final class Lucene40PostingsBaseFormat extends PostingsBaseFormat {
/** Sole constructor. */
- public Lucene40PostingsBaseFormat() {
+ Lucene40PostingsBaseFormat() {
super("Lucene40");
}
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40PostingsFormat.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40PostingsFormat.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40PostingsFormat.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40PostingsFormat.java Sun Sep 28 14:36:00 2014
@@ -19,226 +19,25 @@ package org.apache.lucene.codecs.lucene4
import java.io.IOException;
-import org.apache.lucene.codecs.CodecUtil;
import org.apache.lucene.codecs.FieldsConsumer;
import org.apache.lucene.codecs.FieldsProducer;
import org.apache.lucene.codecs.PostingsFormat;
import org.apache.lucene.codecs.PostingsReaderBase;
-import org.apache.lucene.codecs.PostingsWriterBase; // javadocs
import org.apache.lucene.codecs.blocktree.BlockTreeTermsReader;
-import org.apache.lucene.codecs.blocktree.BlockTreeTermsWriter;
-import org.apache.lucene.index.DocsEnum; // javadocs
-import org.apache.lucene.index.FieldInfo.IndexOptions; // javadocs
-import org.apache.lucene.index.FieldInfos; // javadocs
import org.apache.lucene.index.SegmentReadState;
import org.apache.lucene.index.SegmentWriteState;
-import org.apache.lucene.store.DataOutput; // javadocs
-import org.apache.lucene.util.fst.FST; // javadocs
/**
* Lucene 4.0 Postings format.
- * <p>
- * Files:
- * <ul>
- * <li><tt>.tim</tt>: <a href="#Termdictionary">Term Dictionary</a></li>
- * <li><tt>.tip</tt>: <a href="#Termindex">Term Index</a></li>
- * <li><tt>.frq</tt>: <a href="#Frequencies">Frequencies</a></li>
- * <li><tt>.prx</tt>: <a href="#Positions">Positions</a></li>
- * </ul>
- * </p>
- * <p>
- * <a name="Termdictionary" id="Termdictionary"></a>
- * <h3>Term Dictionary</h3>
- *
- * <p>The .tim file contains the list of terms in each
- * field along with per-term statistics (such as docfreq)
- * and pointers to the frequencies, positions and
- * skip data in the .frq and .prx files.
- * See {@link BlockTreeTermsWriter} for more details on the format.
- * </p>
- *
- * <p>NOTE: The term dictionary can plug into different postings implementations:
- * the postings writer/reader are actually responsible for encoding
- * and decoding the Postings Metadata and Term Metadata sections described here:</p>
- * <ul>
- * <li>Postings Metadata --> Header, SkipInterval, MaxSkipLevels, SkipMinimum</li>
- * <li>Term Metadata --> FreqDelta, SkipDelta?, ProxDelta?
- * <li>Header --> {@link CodecUtil#writeHeader CodecHeader}</li>
- * <li>SkipInterval,MaxSkipLevels,SkipMinimum --> {@link DataOutput#writeInt Uint32}</li>
- * <li>SkipDelta,FreqDelta,ProxDelta --> {@link DataOutput#writeVLong VLong}</li>
- * </ul>
- * <p>Notes:</p>
- * <ul>
- * <li>Header is a {@link CodecUtil#writeHeader CodecHeader} storing the version information
- * for the postings.</li>
- * <li>SkipInterval is the fraction of TermDocs stored in skip tables. It is used to accelerate
- * {@link DocsEnum#advance(int)}. Larger values result in smaller indexes, greater
- * acceleration, but fewer accelerable cases, while smaller values result in bigger indexes,
- * less acceleration (in case of a small value for MaxSkipLevels) and more accelerable cases.
- * </li>
- * <li>MaxSkipLevels is the max. number of skip levels stored for each term in the .frq file. A
- * low value results in smaller indexes but less acceleration, a larger value results in
- * slightly larger indexes but greater acceleration. See format of .frq file for more
- * information about skip levels.</li>
- * <li>SkipMinimum is the minimum document frequency a term must have in order to write any
- * skip data at all.</li>
- * <li>FreqDelta determines the position of this term's TermFreqs within the .frq
- * file. In particular, it is the difference between the position of this term's
- * data in that file and the position of the previous term's data (or zero, for
- * the first term in the block).</li>
- * <li>ProxDelta determines the position of this term's TermPositions within the
- * .prx file. In particular, it is the difference between the position of this
- * term's data in that file and the position of the previous term's data (or zero,
- * for the first term in the block. For fields that omit position data, this will
- * be 0 since prox information is not stored.</li>
- * <li>SkipDelta determines the position of this term's SkipData within the .frq
- * file. In particular, it is the number of bytes after TermFreqs that the
- * SkipData starts. In other words, it is the length of the TermFreq data.
- * SkipDelta is only stored if DocFreq is not smaller than SkipMinimum.</li>
- * </ul>
- * <a name="Termindex" id="Termindex"></a>
- * <h3>Term Index</h3>
- * <p>The .tip file contains an index into the term dictionary, so that it can be
- * accessed randomly. See {@link BlockTreeTermsWriter} for more details on the format.</p>
- * <a name="Frequencies" id="Frequencies"></a>
- * <h3>Frequencies</h3>
- * <p>The .frq file contains the lists of documents which contain each term, along
- * with the frequency of the term in that document (except when frequencies are
- * omitted: {@link IndexOptions#DOCS_ONLY}).</p>
- * <ul>
- * <li>FreqFile (.frq) --> Header, <TermFreqs, SkipData?> <sup>TermCount</sup></li>
- * <li>Header --> {@link CodecUtil#writeHeader CodecHeader}</li>
- * <li>TermFreqs --> <TermFreq> <sup>DocFreq</sup></li>
- * <li>TermFreq --> DocDelta[, Freq?]</li>
- * <li>SkipData --> <<SkipLevelLength, SkipLevel>
- * <sup>NumSkipLevels-1</sup>, SkipLevel> <SkipDatum></li>
- * <li>SkipLevel --> <SkipDatum> <sup>DocFreq/(SkipInterval^(Level +
- * 1))</sup></li>
- * <li>SkipDatum -->
- * DocSkip,PayloadLength?,OffsetLength?,FreqSkip,ProxSkip,SkipChildLevelPointer?</li>
- * <li>DocDelta,Freq,DocSkip,PayloadLength,OffsetLength,FreqSkip,ProxSkip --> {@link DataOutput#writeVInt VInt}</li>
- * <li>SkipChildLevelPointer --> {@link DataOutput#writeVLong VLong}</li>
- * </ul>
- * <p>TermFreqs are ordered by term (the term is implicit, from the term dictionary).</p>
- * <p>TermFreq entries are ordered by increasing document number.</p>
- * <p>DocDelta: if frequencies are indexed, this determines both the document
- * number and the frequency. In particular, DocDelta/2 is the difference between
- * this document number and the previous document number (or zero when this is the
- * first document in a TermFreqs). When DocDelta is odd, the frequency is one.
- * When DocDelta is even, the frequency is read as another VInt. If frequencies
- * are omitted, DocDelta contains the gap (not multiplied by 2) between document
- * numbers and no frequency information is stored.</p>
- * <p>For example, the TermFreqs for a term which occurs once in document seven
- * and three times in document eleven, with frequencies indexed, would be the
- * following sequence of VInts:</p>
- * <p>15, 8, 3</p>
- * <p>If frequencies were omitted ({@link IndexOptions#DOCS_ONLY}) it would be this
- * sequence of VInts instead:</p>
- * <p>7,4</p>
- * <p>DocSkip records the document number before every SkipInterval <sup>th</sup>
- * document in TermFreqs. If payloads and offsets are disabled for the term's field, then
- * DocSkip represents the difference from the previous value in the sequence. If
- * payloads and/or offsets are enabled for the term's field, then DocSkip/2 represents the
- * difference from the previous value in the sequence. In this case when
- * DocSkip is odd, then PayloadLength and/or OffsetLength are stored indicating the length of
- * the last payload/offset before the SkipInterval<sup>th</sup> document in TermPositions.</p>
- * <p>PayloadLength indicates the length of the last payload.</p>
- * <p>OffsetLength indicates the length of the last offset (endOffset-startOffset).</p>
- * <p>
- * FreqSkip and ProxSkip record the position of every SkipInterval <sup>th</sup>
- * entry in FreqFile and ProxFile, respectively. File positions are relative to
- * the start of TermFreqs and Positions, to the previous SkipDatum in the
- * sequence.</p>
- * <p>For example, if DocFreq=35 and SkipInterval=16, then there are two SkipData
- * entries, containing the 15 <sup>th</sup> and 31 <sup>st</sup> document numbers
- * in TermFreqs. The first FreqSkip names the number of bytes after the beginning
- * of TermFreqs that the 16 <sup>th</sup> SkipDatum starts, and the second the
- * number of bytes after that that the 32 <sup>nd</sup> starts. The first ProxSkip
- * names the number of bytes after the beginning of Positions that the 16
- * <sup>th</sup> SkipDatum starts, and the second the number of bytes after that
- * that the 32 <sup>nd</sup> starts.</p>
- * <p>Each term can have multiple skip levels. The amount of skip levels for a
- * term is NumSkipLevels = Min(MaxSkipLevels,
- * floor(log(DocFreq/log(SkipInterval)))). The number of SkipData entries for a
- * skip level is DocFreq/(SkipInterval^(Level + 1)), whereas the lowest skip level
- * is Level=0.<br>
- * Example: SkipInterval = 4, MaxSkipLevels = 2, DocFreq = 35. Then skip level 0
- * has 8 SkipData entries, containing the 3<sup>rd</sup>, 7<sup>th</sup>,
- * 11<sup>th</sup>, 15<sup>th</sup>, 19<sup>th</sup>, 23<sup>rd</sup>,
- * 27<sup>th</sup>, and 31<sup>st</sup> document numbers in TermFreqs. Skip level
- * 1 has 2 SkipData entries, containing the 15<sup>th</sup> and 31<sup>st</sup>
- * document numbers in TermFreqs.<br>
- * The SkipData entries on all upper levels > 0 contain a SkipChildLevelPointer
- * referencing the corresponding SkipData entry in level-1. In the example has
- * entry 15 on level 1 a pointer to entry 15 on level 0 and entry 31 on level 1 a
- * pointer to entry 31 on level 0.
- * </p>
- * <a name="Positions" id="Positions"></a>
- * <h3>Positions</h3>
- * <p>The .prx file contains the lists of positions that each term occurs at
- * within documents. Note that fields omitting positional data do not store
- * anything into this file, and if all fields in the index omit positional data
- * then the .prx file will not exist.</p>
- * <ul>
- * <li>ProxFile (.prx) --> Header, <TermPositions> <sup>TermCount</sup></li>
- * <li>Header --> {@link CodecUtil#writeHeader CodecHeader}</li>
- * <li>TermPositions --> <Positions> <sup>DocFreq</sup></li>
- * <li>Positions --> <PositionDelta,PayloadLength?,OffsetDelta?,OffsetLength?,PayloadData?> <sup>Freq</sup></li>
- * <li>PositionDelta,OffsetDelta,OffsetLength,PayloadLength --> {@link DataOutput#writeVInt VInt}</li>
- * <li>PayloadData --> {@link DataOutput#writeByte byte}<sup>PayloadLength</sup></li>
- * </ul>
- * <p>TermPositions are ordered by term (the term is implicit, from the term dictionary).</p>
- * <p>Positions entries are ordered by increasing document number (the document
- * number is implicit from the .frq file).</p>
- * <p>PositionDelta is, if payloads are disabled for the term's field, the
- * difference between the position of the current occurrence in the document and
- * the previous occurrence (or zero, if this is the first occurrence in this
- * document). If payloads are enabled for the term's field, then PositionDelta/2
- * is the difference between the current and the previous position. If payloads
- * are enabled and PositionDelta is odd, then PayloadLength is stored, indicating
- * the length of the payload at the current term position.</p>
- * <p>For example, the TermPositions for a term which occurs as the fourth term in
- * one document, and as the fifth and ninth term in a subsequent document, would
- * be the following sequence of VInts (payloads disabled):</p>
- * <p>4, 5, 4</p>
- * <p>PayloadData is metadata associated with the current term position. If
- * PayloadLength is stored at the current position, then it indicates the length
- * of this payload. If PayloadLength is not stored, then this payload has the same
- * length as the payload at the previous position.</p>
- * <p>OffsetDelta/2 is the difference between this position's startOffset from the
- * previous occurrence (or zero, if this is the first occurrence in this document).
- * If OffsetDelta is odd, then the length (endOffset-startOffset) differs from the
- * previous occurrence and an OffsetLength follows. Offset data is only written for
- * {@link IndexOptions#DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS}.</p>
- *
- * @deprecated Only for reading old 4.0 segments */
-
-// TODO: this class could be created by wrapping
-// BlockTreeTermsDict around Lucene40PostingsBaseFormat; ie
-// we should not duplicate the code from that class here:
+ * @deprecated Only for reading old 4.0 segments
+ */
@Deprecated
public class Lucene40PostingsFormat extends PostingsFormat {
- /** minimum items (terms or sub-blocks) per block for BlockTree */
- protected final int minBlockSize;
- /** maximum items (terms or sub-blocks) per block for BlockTree */
- protected final int maxBlockSize;
-
/** Creates {@code Lucene40PostingsFormat} with default
* settings. */
public Lucene40PostingsFormat() {
- this(BlockTreeTermsWriter.DEFAULT_MIN_BLOCK_SIZE, BlockTreeTermsWriter.DEFAULT_MAX_BLOCK_SIZE);
- }
-
- /** Creates {@code Lucene40PostingsFormat} with custom
- * values for {@code minBlockSize} and {@code
- * maxBlockSize} passed to block terms dictionary.
- * @see BlockTreeTermsWriter#BlockTreeTermsWriter(SegmentWriteState,PostingsWriterBase,int,int) */
- private Lucene40PostingsFormat(int minBlockSize, int maxBlockSize) {
super("Lucene40");
- this.minBlockSize = minBlockSize;
- assert minBlockSize > 1;
- this.maxBlockSize = maxBlockSize;
}
@Override
@@ -247,7 +46,7 @@ public class Lucene40PostingsFormat exte
}
@Override
- public FieldsProducer fieldsProducer(SegmentReadState state) throws IOException {
+ public final FieldsProducer fieldsProducer(SegmentReadState state) throws IOException {
PostingsReaderBase postings = new Lucene40PostingsReader(state.directory, state.fieldInfos, state.segmentInfo, state.context, state.segmentSuffix);
boolean success = false;
@@ -276,6 +75,6 @@ public class Lucene40PostingsFormat exte
@Override
public String toString() {
- return getName() + "(minBlockSize=" + minBlockSize + " maxBlockSize=" + maxBlockSize + ")";
+ return getName();
}
}
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40PostingsReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40PostingsReader.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40PostingsReader.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40PostingsReader.java Sun Sep 28 14:36:00 2014
@@ -43,13 +43,10 @@ import org.apache.lucene.util.BytesRefBu
import org.apache.lucene.util.IOUtils;
/**
- * Concrete class that reads the 4.0 frq/prox
- * postings format.
- *
- * @see Lucene40PostingsFormat
- * @deprecated Only for reading old 4.0 segments */
+ * Reader for 4.0 postings format
+ * @deprecated Only for reading old 4.0 segments */
@Deprecated
-public class Lucene40PostingsReader extends PostingsReaderBase {
+final class Lucene40PostingsReader extends PostingsReaderBase {
final static String TERMS_CODEC = "Lucene40PostingsWriterTerms";
final static String FRQ_CODEC = "Lucene40PostingsWriterFrq";
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40SegmentInfoFormat.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40SegmentInfoFormat.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40SegmentInfoFormat.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40SegmentInfoFormat.java Sun Sep 28 14:36:00 2014
@@ -17,57 +17,14 @@ package org.apache.lucene.codecs.lucene4
* limitations under the License.
*/
-import org.apache.lucene.codecs.CodecUtil;
import org.apache.lucene.codecs.SegmentInfoFormat;
import org.apache.lucene.codecs.SegmentInfoReader;
import org.apache.lucene.codecs.SegmentInfoWriter;
-import org.apache.lucene.index.IndexWriter; // javadocs
-import org.apache.lucene.index.SegmentInfo; // javadocs
-import org.apache.lucene.index.SegmentInfos; // javadocs
-import org.apache.lucene.store.DataOutput; // javadocs
+import org.apache.lucene.index.SegmentInfo;
/**
* Lucene 4.0 Segment info format.
- * <p>
- * Files:
- * <ul>
- * <li><tt>.si</tt>: Header, SegVersion, SegSize, IsCompoundFile, Diagnostics, Attributes, Files
- * </ul>
- * </p>
- * Data types:
- * <p>
- * <ul>
- * <li>Header --> {@link CodecUtil#writeHeader CodecHeader}</li>
- * <li>SegSize --> {@link DataOutput#writeInt Int32}</li>
- * <li>SegVersion --> {@link DataOutput#writeString String}</li>
- * <li>Files --> {@link DataOutput#writeStringSet Set<String>}</li>
- * <li>Diagnostics, Attributes --> {@link DataOutput#writeStringStringMap Map<String,String>}</li>
- * <li>IsCompoundFile --> {@link DataOutput#writeByte Int8}</li>
- * </ul>
- * </p>
- * Field Descriptions:
- * <p>
- * <ul>
- * <li>SegVersion is the code version that created the segment.</li>
- * <li>SegSize is the number of documents contained in the segment index.</li>
- * <li>IsCompoundFile records whether the segment is written as a compound file or
- * not. If this is -1, the segment is not a compound file. If it is 1, the segment
- * is a compound file.</li>
- * <li>Checksum contains the CRC32 checksum of all bytes in the segments_N file up
- * until the checksum. This is used to verify integrity of the file on opening the
- * index.</li>
- * <li>The Diagnostics Map is privately written by {@link IndexWriter}, as a debugging aid,
- * for each segment it creates. It includes metadata like the current Lucene
- * version, OS, Java version, why the segment was created (merge, flush,
- * addIndexes), etc.</li>
- * <li>Attributes: a key-value map of codec-private attributes.</li>
- * <li>Files is a list of files referred to by this segment.</li>
- * </ul>
- * </p>
- *
- * @see SegmentInfos
- * @lucene.experimental
- * @deprecated Only for reading old 4.0-4.5 segments, and supporting IndexWriter.addIndexes
+ * @deprecated Only for reading old 4.0-4.5 segments
*/
@Deprecated
public class Lucene40SegmentInfoFormat extends SegmentInfoFormat {
@@ -78,7 +35,7 @@ public class Lucene40SegmentInfoFormat e
}
@Override
- public SegmentInfoReader getSegmentInfoReader() {
+ public final SegmentInfoReader getSegmentInfoReader() {
return reader;
}
@@ -88,7 +45,7 @@ public class Lucene40SegmentInfoFormat e
}
/** File extension used to store {@link SegmentInfo}. */
- public final static String SI_EXTENSION = "si";
+ static final String SI_EXTENSION = "si";
static final String CODEC_NAME = "Lucene40SegmentInfo";
static final int VERSION_START = 0;
static final int VERSION_CURRENT = VERSION_START;
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40SegmentInfoReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40SegmentInfoReader.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40SegmentInfoReader.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40SegmentInfoReader.java Sun Sep 28 14:36:00 2014
@@ -34,14 +34,11 @@ import org.apache.lucene.util.IOUtils;
import org.apache.lucene.util.Version;
/**
- * Lucene 4.0 implementation of {@link SegmentInfoReader}.
- *
- * @see Lucene40SegmentInfoFormat
- * @lucene.experimental
+ * Lucene 4.0 SI reader
* @deprecated Only for reading old 4.0-4.5 segments
*/
@Deprecated
-public class Lucene40SegmentInfoReader extends SegmentInfoReader {
+final class Lucene40SegmentInfoReader extends SegmentInfoReader {
/** Sole constructor. */
public Lucene40SegmentInfoReader() {
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40SkipListReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40SkipListReader.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40SkipListReader.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40SkipListReader.java Sun Sep 28 14:36:00 2014
@@ -24,14 +24,11 @@ import org.apache.lucene.codecs.MultiLev
import org.apache.lucene.store.IndexInput;
/**
- * Implements the skip list reader for the 4.0 posting list format
- * that stores positions and payloads.
- *
- * @see Lucene40PostingsFormat
+ * Lucene 4.0 skiplist reader
* @deprecated Only for reading old 4.0 segments
*/
@Deprecated
-public class Lucene40SkipListReader extends MultiLevelSkipListReader {
+final class Lucene40SkipListReader extends MultiLevelSkipListReader {
private boolean currentFieldStoresPayloads;
private boolean currentFieldStoresOffsets;
private long freqPointer[];
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40StoredFieldsFormat.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40StoredFieldsFormat.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40StoredFieldsFormat.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40StoredFieldsFormat.java Sun Sep 28 14:36:00 2014
@@ -19,66 +19,18 @@ package org.apache.lucene.codecs.lucene4
import java.io.IOException;
-import org.apache.lucene.codecs.CodecUtil;
import org.apache.lucene.codecs.StoredFieldsFormat;
import org.apache.lucene.codecs.StoredFieldsReader;
import org.apache.lucene.codecs.StoredFieldsWriter;
import org.apache.lucene.index.FieldInfos;
import org.apache.lucene.index.SegmentInfo;
-import org.apache.lucene.store.DataOutput; // javadocs
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.IOContext;
/**
* Lucene 4.0 Stored Fields Format.
- * <p>Stored fields are represented by two files:</p>
- * <ol>
- * <li><a name="field_index" id="field_index"></a>
- * <p>The field index, or <tt>.fdx</tt> file.</p>
- * <p>This is used to find the location within the field data file of the fields
- * of a particular document. Because it contains fixed-length data, this file may
- * be easily randomly accessed. The position of document <i>n</i> 's field data is
- * the {@link DataOutput#writeLong Uint64} at <i>n*8</i> in this file.</p>
- * <p>This contains, for each document, a pointer to its field data, as
- * follows:</p>
- * <ul>
- * <li>FieldIndex (.fdx) --> <Header>, <FieldValuesPosition> <sup>SegSize</sup></li>
- * <li>Header --> {@link CodecUtil#writeHeader CodecHeader}</li>
- * <li>FieldValuesPosition --> {@link DataOutput#writeLong Uint64}</li>
- * </ul>
- * </li>
- * <li>
- * <p><a name="field_data" id="field_data"></a>The field data, or <tt>.fdt</tt> file.</p>
- * <p>This contains the stored fields of each document, as follows:</p>
- * <ul>
- * <li>FieldData (.fdt) --> <Header>, <DocFieldData> <sup>SegSize</sup></li>
- * <li>Header --> {@link CodecUtil#writeHeader CodecHeader}</li>
- * <li>DocFieldData --> FieldCount, <FieldNum, Bits, Value>
- * <sup>FieldCount</sup></li>
- * <li>FieldCount --> {@link DataOutput#writeVInt VInt}</li>
- * <li>FieldNum --> {@link DataOutput#writeVInt VInt}</li>
- * <li>Bits --> {@link DataOutput#writeByte Byte}</li>
- * <ul>
- * <li>low order bit reserved.</li>
- * <li>second bit is one for fields containing binary data</li>
- * <li>third bit reserved.</li>
- * <li>4th to 6th bit (mask: 0x7<<3) define the type of a numeric field:
- * <ul>
- * <li>all bits in mask are cleared if no numeric field at all</li>
- * <li>1<<3: Value is Int</li>
- * <li>2<<3: Value is Long</li>
- * <li>3<<3: Value is Int as Float (as of {@link Float#intBitsToFloat(int)}</li>
- * <li>4<<3: Value is Long as Double (as of {@link Double#longBitsToDouble(long)}</li>
- * </ul>
- * </li>
- * </ul>
- * <li>Value --> String | BinaryValue | Int | Long (depending on Bits)</li>
- * <li>BinaryValue --> ValueSize, <{@link DataOutput#writeByte Byte}>^ValueSize</li>
- * <li>ValueSize --> {@link DataOutput#writeVInt VInt}</li>
- * </li>
- * </ul>
- * </ol>
- * @lucene.experimental */
+ * @deprecated only for reading 4.0 segments */
+@Deprecated
public class Lucene40StoredFieldsFormat extends StoredFieldsFormat {
/** Sole constructor. */
@@ -86,7 +38,7 @@ public class Lucene40StoredFieldsFormat
}
@Override
- public StoredFieldsReader fieldsReader(Directory directory, SegmentInfo si,
+ public final StoredFieldsReader fieldsReader(Directory directory, SegmentInfo si,
FieldInfos fn, IOContext context) throws IOException {
return new Lucene40StoredFieldsReader(directory, si, fn, context);
}
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40StoredFieldsReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40StoredFieldsReader.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40StoredFieldsReader.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40StoredFieldsReader.java Sun Sep 28 14:36:00 2014
@@ -40,14 +40,11 @@ import java.nio.charset.StandardCharsets
import java.util.Collections;
/**
- * Class responsible for access to stored document fields.
- * <p/>
- * It uses <segment>.fdt and <segment>.fdx; files.
- *
- * @see Lucene40StoredFieldsFormat
- * @lucene.internal
+ * Reader for 4.0 stored fields
+ * @deprecated only for reading 4.0 segments
*/
-public final class Lucene40StoredFieldsReader extends StoredFieldsReader implements Cloneable, Closeable {
+@Deprecated
+final class Lucene40StoredFieldsReader extends StoredFieldsReader implements Cloneable, Closeable {
// NOTE: bit 0 is free here! You can steal it!
static final int FIELD_IS_BINARY = 1 << 1;
@@ -76,10 +73,10 @@ public final class Lucene40StoredFieldsR
/** Extension of stored fields file */
- public static final String FIELDS_EXTENSION = "fdt";
+ static final String FIELDS_EXTENSION = "fdt";
/** Extension of stored fields index file */
- public static final String FIELDS_INDEX_EXTENSION = "fdx";
+ static final String FIELDS_INDEX_EXTENSION = "fdx";
private static final long RAM_BYTES_USED = RamUsageEstimator.shallowSizeOfInstance(Lucene40StoredFieldsReader.class);
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40TermVectorsFormat.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40TermVectorsFormat.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40TermVectorsFormat.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40TermVectorsFormat.java Sun Sep 28 14:36:00 2014
@@ -19,100 +19,19 @@ package org.apache.lucene.codecs.lucene4
import java.io.IOException;
-import org.apache.lucene.codecs.CodecUtil;
import org.apache.lucene.codecs.TermVectorsFormat;
import org.apache.lucene.codecs.TermVectorsReader;
import org.apache.lucene.codecs.TermVectorsWriter;
import org.apache.lucene.index.FieldInfos;
import org.apache.lucene.index.SegmentInfo;
-import org.apache.lucene.store.DataOutput; // javadocs
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.IOContext;
/**
* Lucene 4.0 Term Vectors format.
- * <p>Term Vector support is an optional on a field by field basis. It consists of
- * 3 files.</p>
- * <ol>
- * <li><a name="tvx" id="tvx"></a>
- * <p>The Document Index or .tvx file.</p>
- * <p>For each document, this stores the offset into the document data (.tvd) and
- * field data (.tvf) files.</p>
- * <p>DocumentIndex (.tvx) --> Header,<DocumentPosition,FieldPosition>
- * <sup>NumDocs</sup></p>
- * <ul>
- * <li>Header --> {@link CodecUtil#writeHeader CodecHeader}</li>
- * <li>DocumentPosition --> {@link DataOutput#writeLong UInt64} (offset in the .tvd file)</li>
- * <li>FieldPosition --> {@link DataOutput#writeLong UInt64} (offset in the .tvf file)</li>
- * </ul>
- * </li>
- * <li><a name="tvd" id="tvd"></a>
- * <p>The Document or .tvd file.</p>
- * <p>This contains, for each document, the number of fields, a list of the fields
- * with term vector info and finally a list of pointers to the field information
- * in the .tvf (Term Vector Fields) file.</p>
- * <p>The .tvd file is used to map out the fields that have term vectors stored
- * and where the field information is in the .tvf file.</p>
- * <p>Document (.tvd) --> Header,<NumFields, FieldNums,
- * FieldPositions> <sup>NumDocs</sup></p>
- * <ul>
- * <li>Header --> {@link CodecUtil#writeHeader CodecHeader}</li>
- * <li>NumFields --> {@link DataOutput#writeVInt VInt}</li>
- * <li>FieldNums --> <FieldNumDelta> <sup>NumFields</sup></li>
- * <li>FieldNumDelta --> {@link DataOutput#writeVInt VInt}</li>
- * <li>FieldPositions --> <FieldPositionDelta> <sup>NumFields-1</sup></li>
- * <li>FieldPositionDelta --> {@link DataOutput#writeVLong VLong}</li>
- * </ul>
- * </li>
- * <li><a name="tvf" id="tvf"></a>
- * <p>The Field or .tvf file.</p>
- * <p>This file contains, for each field that has a term vector stored, a list of
- * the terms, their frequencies and, optionally, position, offset, and payload
- * information.</p>
- * <p>Field (.tvf) --> Header,<NumTerms, Flags, TermFreqs>
- * <sup>NumFields</sup></p>
- * <ul>
- * <li>Header --> {@link CodecUtil#writeHeader CodecHeader}</li>
- * <li>NumTerms --> {@link DataOutput#writeVInt VInt}</li>
- * <li>Flags --> {@link DataOutput#writeByte Byte}</li>
- * <li>TermFreqs --> <TermText, TermFreq, Positions?, PayloadData?, Offsets?>
- * <sup>NumTerms</sup></li>
- * <li>TermText --> <PrefixLength, Suffix></li>
- * <li>PrefixLength --> {@link DataOutput#writeVInt VInt}</li>
- * <li>Suffix --> {@link DataOutput#writeString String}</li>
- * <li>TermFreq --> {@link DataOutput#writeVInt VInt}</li>
- * <li>Positions --> <PositionDelta PayloadLength?><sup>TermFreq</sup></li>
- * <li>PositionDelta --> {@link DataOutput#writeVInt VInt}</li>
- * <li>PayloadLength --> {@link DataOutput#writeVInt VInt}</li>
- * <li>PayloadData --> {@link DataOutput#writeByte Byte}<sup>NumPayloadBytes</sup></li>
- * <li>Offsets --> <{@link DataOutput#writeVInt VInt}, {@link DataOutput#writeVInt VInt}><sup>TermFreq</sup></li>
- * </ul>
- * <p>Notes:</p>
- * <ul>
- * <li>Flags byte stores whether this term vector has position, offset, payload.
- * information stored.</li>
- * <li>Term byte prefixes are shared. The PrefixLength is the number of initial
- * bytes from the previous term which must be pre-pended to a term's suffix
- * in order to form the term's bytes. Thus, if the previous term's text was "bone"
- * and the term is "boy", the PrefixLength is two and the suffix is "y".</li>
- * <li>PositionDelta is, if payloads are disabled for the term's field, the
- * difference between the position of the current occurrence in the document and
- * the previous occurrence (or zero, if this is the first occurrence in this
- * document). If payloads are enabled for the term's field, then PositionDelta/2
- * is the difference between the current and the previous position. If payloads
- * are enabled and PositionDelta is odd, then PayloadLength is stored, indicating
- * the length of the payload at the current term position.</li>
- * <li>PayloadData is metadata associated with a term position. If
- * PayloadLength is stored at the current position, then it indicates the length
- * of this payload. If PayloadLength is not stored, then this payload has the same
- * length as the payload at the previous position. PayloadData encodes the
- * concatenated bytes for all of a terms occurrences.</li>
- * <li>Offsets are stored as delta encoded VInts. The first VInt is the
- * startOffset, the second is the endOffset.</li>
- * </ul>
- * </li>
- * </ol>
+ * @deprecated only for reading 4.0 and 4.1 segments
*/
+@Deprecated
public class Lucene40TermVectorsFormat extends TermVectorsFormat {
/** Sole constructor. */
@@ -120,7 +39,7 @@ public class Lucene40TermVectorsFormat e
}
@Override
- public TermVectorsReader vectorsReader(Directory directory, SegmentInfo segmentInfo, FieldInfos fieldInfos, IOContext context) throws IOException {
+ public final TermVectorsReader vectorsReader(Directory directory, SegmentInfo segmentInfo, FieldInfos fieldInfos, IOContext context) throws IOException {
return new Lucene40TermVectorsReader(directory, segmentInfo, fieldInfos, context);
}
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40TermVectorsReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40TermVectorsReader.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40TermVectorsReader.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene40/Lucene40TermVectorsReader.java Sun Sep 28 14:36:00 2014
@@ -48,12 +48,10 @@ import org.apache.lucene.util.IOUtils;
/**
* Lucene 4.0 Term Vectors reader.
- * <p>
- * It reads .tvd, .tvf, and .tvx files.
- *
- * @see Lucene40TermVectorsFormat
+ * @deprecated only for reading 4.0 and 4.1 segments
*/
-public class Lucene40TermVectorsReader extends TermVectorsReader implements Closeable {
+@Deprecated
+final class Lucene40TermVectorsReader extends TermVectorsReader implements Closeable {
static final byte STORE_POSITIONS_WITH_TERMVECTOR = 0x1;
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene41/Lucene41Codec.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene41/Lucene41Codec.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene41/Lucene41Codec.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene41/Lucene41Codec.java Sun Sep 28 14:36:00 2014
@@ -19,7 +19,6 @@ package org.apache.lucene.codecs.lucene4
import org.apache.lucene.codecs.Codec;
import org.apache.lucene.codecs.FieldInfosFormat;
-import org.apache.lucene.codecs.FilterCodec;
import org.apache.lucene.codecs.LiveDocsFormat;
import org.apache.lucene.codecs.PostingsFormat;
import org.apache.lucene.codecs.SegmentInfoFormat;
@@ -36,14 +35,8 @@ import org.apache.lucene.codecs.lucene40
import org.apache.lucene.codecs.perfield.PerFieldPostingsFormat;
/**
- * Implements the Lucene 4.1 index format, with configurable per-field postings formats.
- * <p>
- * If you want to reuse functionality of this codec in another codec, extend
- * {@link FilterCodec}.
- *
- * @see org.apache.lucene.codecs.lucene41 package documentation for file format details.
- * @deprecated Only for reading old 4.0 segments
- * @lucene.experimental
+ * Implements the Lucene 4.1 index format
+ * @deprecated Only for reading old 4.1 segments
*/
@Deprecated
public class Lucene41Codec extends Codec {
@@ -65,7 +58,6 @@ public class Lucene41Codec extends Codec
super("Lucene41");
}
- // TODO: slightly evil
@Override
public StoredFieldsFormat storedFieldsFormat() {
return fieldsFormat;
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene41/Lucene41StoredFieldsFormat.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene41/Lucene41StoredFieldsFormat.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene41/Lucene41StoredFieldsFormat.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene41/Lucene41StoredFieldsFormat.java Sun Sep 28 14:36:00 2014
@@ -30,6 +30,7 @@ import org.apache.lucene.store.IOContext
/**
* Lucene 4.1 stored fields format.
+ * @deprecated only for reading old 4.x segments
*/
@Deprecated
public class Lucene41StoredFieldsFormat extends StoredFieldsFormat {
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene41/Lucene41StoredFieldsIndexReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene41/Lucene41StoredFieldsIndexReader.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene41/Lucene41StoredFieldsIndexReader.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene41/Lucene41StoredFieldsIndexReader.java Sun Sep 28 14:36:00 2014
@@ -34,7 +34,7 @@ import org.apache.lucene.util.RamUsageEs
import org.apache.lucene.util.packed.PackedInts;
/**
- * Random-access reader for {@code Lucene41CompressingStoredFieldsIndexWriter}.
+ * Reader for 4.x stored fields/term vectors index
* @deprecated only for reading old segments
*/
@Deprecated
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene410/Lucene410Codec.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene410/Lucene410Codec.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene410/Lucene410Codec.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene410/Lucene410Codec.java Sun Sep 28 14:36:00 2014
@@ -22,7 +22,6 @@ import java.io.IOException;
import org.apache.lucene.codecs.Codec;
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.NormsConsumer;
import org.apache.lucene.codecs.NormsFormat;
@@ -41,18 +40,10 @@ import org.apache.lucene.codecs.perfield
import org.apache.lucene.index.SegmentWriteState;
/**
- * Implements the Lucene 4.10 index format, with configurable per-field postings
- * and docvalues formats.
- * <p>
- * If you want to reuse functionality of this codec in another codec, extend
- * {@link FilterCodec}.
- *
- * @see org.apache.lucene.codecs.lucene410 package documentation for file format details.
- * @lucene.experimental
+ * Implements the Lucene 4.10 codec
+ * @deprecated only for reading old 4.10 segments
*/
-// NOTE: if we make largish changes in a minor release, easier to just make Lucene411Codec or whatever
-// if they are backwards compatible or smallish we can probably do the backwards in the postingsreader
-// (it writes a minor version, etc).
+@Deprecated
public class Lucene410Codec extends Codec {
private final StoredFieldsFormat fieldsFormat = new Lucene41StoredFieldsFormat();
private final TermVectorsFormat vectorsFormat = new Lucene42TermVectorsFormat();
Modified: lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene42/Lucene42Codec.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene42/Lucene42Codec.java?rev=1628070&r1=1628069&r2=1628070&view=diff
==============================================================================
--- lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene42/Lucene42Codec.java (original)
+++ lucene/dev/branches/lucene5969/lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene42/Lucene42Codec.java Sun Sep 28 14:36:00 2014
@@ -22,7 +22,6 @@ import java.io.IOException;
import org.apache.lucene.codecs.Codec;
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.NormsConsumer;
import org.apache.lucene.codecs.NormsFormat;
@@ -38,19 +37,9 @@ import org.apache.lucene.codecs.perfield
import org.apache.lucene.index.SegmentWriteState;
/**
- * Implements the Lucene 4.2 index format, with configurable per-field postings
- * and docvalues formats.
- * <p>
- * If you want to reuse functionality of this codec in another codec, extend
- * {@link FilterCodec}.
- *
- * @see org.apache.lucene.codecs.lucene42 package documentation for file format details.
- * @lucene.experimental
+ * Implements the Lucene 4.2 index format
* @deprecated Only for reading old 4.2 segments
*/
-// NOTE: if we make largish changes in a minor release, easier to just make Lucene43Codec or whatever
-// if they are backwards compatible or smallish we can probably do the backwards in the postingsreader
-// (it writes a minor version, etc).
@Deprecated
public class Lucene42Codec extends Codec {
private final StoredFieldsFormat fieldsFormat = new Lucene41StoredFieldsFormat();