drop old style Lucene compression support - but allow older configs to still work

git-svn-id: https://svn.apache.org/repos/asf/lucene/solr/branches/solr@923411 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Mark Robert Miller 2010-03-15 19:56:25 +00:00
parent 6be973b1a4
commit b0f25360bf
9 changed files with 22 additions and 99 deletions

View File

@ -45,7 +45,7 @@
that avoids logging every request that avoids logging every request
--> -->
<schema name="example" version="1.2"> <schema name="example" version="1.3">
<!-- attribute "name" is the name of this schema and is only used for display purposes. <!-- attribute "name" is the name of this schema and is only used for display purposes.
Applications should change this to reflect the nature of the search collection. Applications should change this to reflect the nature of the search collection.
version="1.2" is Solr's version number for the schema syntax and semantics. It should version="1.2" is Solr's version number for the schema syntax and semantics. It should
@ -53,6 +53,7 @@
1.0: multiValued attribute did not exist, all fields are multiValued by nature 1.0: multiValued attribute did not exist, all fields are multiValued by nature
1.1: multiValued attribute introduced, false by default 1.1: multiValued attribute introduced, false by default
1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields. 1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields.
1.3: removed optional field compress feature
--> -->
<types> <types>
@ -64,11 +65,7 @@
org.apache.solr.analysis package. org.apache.solr.analysis package.
--> -->
<!-- The StrField type is not analyzed, but indexed/stored verbatim. <!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
- StrField and TextField support an optional compressThreshold which
limits compression (if enabled in the derived fields) to values which
exceed a certain size (in characters).
-->
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/> <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
<!-- boolean type: "true" or "false" --> <!-- boolean type: "true" or "false" -->
@ -436,9 +433,6 @@
<types> section <types> section
indexed: true if this field should be indexed (searchable or sortable) indexed: true if this field should be indexed (searchable or sortable)
stored: true if this field should be retrievable stored: true if this field should be retrievable
compressed: [false] if this field should be stored using gzip compression
(this will only apply if the field type is compressable; among
the standard field types, only TextField and StrField are)
multiValued: true if this field may contain multiple values per document multiValued: true if this field may contain multiple values per document
omitNorms: (expert) set to true to omit the norms associated with omitNorms: (expert) set to true to omit the norms associated with
this field (this disables length normalization and index-time this field (this disables length normalization and index-time

View File

@ -33,7 +33,6 @@ public enum FieldFlag {
OMIT_TF('F', "Omit Tf"), OMIT_TF('F', "Omit Tf"),
LAZY('L', "Lazy"), LAZY('L', "Lazy"),
BINARY('B', "Binary"), BINARY('B', "Binary"),
COMPRESSED('C', "Compressed"),
SORT_MISSING_FIRST('f', "Sort Missing First"), SORT_MISSING_FIRST('f', "Sort Missing First"),
SORT_MISSING_LAST('l', "Sort Missing Last"); SORT_MISSING_LAST('l', "Sort Missing Last");

View File

@ -172,8 +172,6 @@ public class LukeRequestHandler extends RequestHandlerBase
flags.append( (f != null && f.getOmitNorms()) ? FieldFlag.OMIT_NORMS.getAbbreviation() : '-' ); flags.append( (f != null && f.getOmitNorms()) ? FieldFlag.OMIT_NORMS.getAbbreviation() : '-' );
flags.append( (f != null && f.isLazy()) ? FieldFlag.LAZY.getAbbreviation() : '-' ); flags.append( (f != null && f.isLazy()) ? FieldFlag.LAZY.getAbbreviation() : '-' );
flags.append( (f != null && f.isBinary()) ? FieldFlag.BINARY.getAbbreviation() : '-' ); flags.append( (f != null && f.isBinary()) ? FieldFlag.BINARY.getAbbreviation() : '-' );
//nocommit: handle compressed
//flags.append( (f != null && f.isCompressed()) ? FieldFlag.COMPRESSED.getAbbreviation() : '-' );
flags.append( (false) ? FieldFlag.SORT_MISSING_FIRST.getAbbreviation() : '-' ); // SchemaField Specific flags.append( (false) ? FieldFlag.SORT_MISSING_FIRST.getAbbreviation() : '-' ); // SchemaField Specific
flags.append( (false) ? FieldFlag.SORT_MISSING_LAST.getAbbreviation() : '-' ); // SchemaField Specific flags.append( (false) ? FieldFlag.SORT_MISSING_LAST.getAbbreviation() : '-' ); // SchemaField Specific
return flags.toString(); return flags.toString();
@ -202,7 +200,6 @@ public class LukeRequestHandler extends RequestHandlerBase
flags.append( (f != null && f.omitTf()) ? FieldFlag.OMIT_TF.getAbbreviation() : '-' ); flags.append( (f != null && f.omitTf()) ? FieldFlag.OMIT_TF.getAbbreviation() : '-' );
flags.append( (lazy) ? FieldFlag.LAZY.getAbbreviation() : '-' ); flags.append( (lazy) ? FieldFlag.LAZY.getAbbreviation() : '-' );
flags.append( (binary) ? FieldFlag.BINARY.getAbbreviation() : '-' ); flags.append( (binary) ? FieldFlag.BINARY.getAbbreviation() : '-' );
flags.append( (f != null && f.isCompressed()) ? FieldFlag.COMPRESSED.getAbbreviation() : '-' );
flags.append( (f != null && f.sortMissingFirst() ) ? FieldFlag.SORT_MISSING_FIRST.getAbbreviation() : '-' ); flags.append( (f != null && f.sortMissingFirst() ) ? FieldFlag.SORT_MISSING_FIRST.getAbbreviation() : '-' );
flags.append( (f != null && f.sortMissingLast() ) ? FieldFlag.SORT_MISSING_LAST.getAbbreviation() : '-' ); flags.append( (f != null && f.sortMissingLast() ) ? FieldFlag.SORT_MISSING_LAST.getAbbreviation() : '-' );
return flags.toString(); return flags.toString();
@ -224,7 +221,6 @@ public class LukeRequestHandler extends RequestHandlerBase
key.add( String.valueOf(FieldFlag.OMIT_NORMS.getAbbreviation()), FieldFlag.OMIT_NORMS.getDisplay() ); key.add( String.valueOf(FieldFlag.OMIT_NORMS.getAbbreviation()), FieldFlag.OMIT_NORMS.getDisplay() );
key.add( String.valueOf(FieldFlag.LAZY.getAbbreviation()), FieldFlag.LAZY.getDisplay() ); key.add( String.valueOf(FieldFlag.LAZY.getAbbreviation()), FieldFlag.LAZY.getDisplay() );
key.add( String.valueOf(FieldFlag.BINARY.getAbbreviation()), FieldFlag.BINARY.getDisplay() ); key.add( String.valueOf(FieldFlag.BINARY.getAbbreviation()), FieldFlag.BINARY.getDisplay() );
key.add( String.valueOf(FieldFlag.COMPRESSED.getAbbreviation()), FieldFlag.COMPRESSED.getDisplay() );
key.add( String.valueOf(FieldFlag.SORT_MISSING_FIRST.getAbbreviation()), FieldFlag.SORT_MISSING_FIRST.getDisplay() ); key.add( String.valueOf(FieldFlag.SORT_MISSING_FIRST.getAbbreviation()), FieldFlag.SORT_MISSING_FIRST.getDisplay() );
key.add( String.valueOf(FieldFlag.SORT_MISSING_LAST.getAbbreviation()), FieldFlag.SORT_MISSING_LAST.getDisplay() ); key.add( String.valueOf(FieldFlag.SORT_MISSING_LAST.getAbbreviation()), FieldFlag.SORT_MISSING_LAST.getDisplay() );
return key; return key;

View File

@ -1,68 +0,0 @@
/**
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.solr.schema;
import org.apache.lucene.document.Field;
import org.apache.solr.common.params.MapSolrParams;
import org.apache.solr.common.params.SolrParams;
import java.util.Map;
/** <code>CompressableField</code> is an abstract field type which enables a
* field to be compressed (by specifying <code>compressed="true"</code> at the
* field definition level) and provides optional support for specifying a
* threshold at which compression is enabled.
*
* Optional settings:
* <ul>
* <li><code>compressThreshold</code>: length, in characters, at which point the
* field contents should be compressed [default: 0]</li>
* </ul></p>
*
* TODO: Enable compression level specification (not yet in lucene)
*
* @version $Id$
*/
public abstract class CompressableField extends FieldType {
/* if field size (in characters) is greater than this threshold, the field
will be stored compressed */
public static int DEFAULT_COMPRESS_THRESHOLD = 0;
int compressThreshold;
private static String CT = "compressThreshold";
protected void init(IndexSchema schema, Map<String,String> args) {
SolrParams p = new MapSolrParams(args);
compressThreshold = p.getInt(CT, DEFAULT_COMPRESS_THRESHOLD);
args.remove(CT);
super.init(schema, args);
}
/* Helpers for field construction */
protected Field.Store getFieldStore(SchemaField field,
String internalVal) {
/* compress field if length exceeds threshold */
if(field.isCompressed()) {
// nocommit: handle compression
//return internalVal.length() >= compressThreshold ?
// Field.Store.COMPRESS : Field.Store.YES;
return Field.Store.YES;
} else
return super.getFieldStore(field, internalVal);
}
}

View File

@ -33,23 +33,22 @@ abstract class FieldProperties {
final static int TOKENIZED = 0x00000002; final static int TOKENIZED = 0x00000002;
final static int STORED = 0x00000004; final static int STORED = 0x00000004;
final static int BINARY = 0x00000008; final static int BINARY = 0x00000008;
final static int COMPRESSED = 0x00000010; final static int OMIT_NORMS = 0x00000010;
final static int OMIT_NORMS = 0x00000020; final static int OMIT_TF_POSITIONS = 0x00000020;
final static int OMIT_TF_POSITIONS = 0x00000040; final static int STORE_TERMVECTORS = 0x00000040;
final static int STORE_TERMVECTORS = 0x00000080; final static int STORE_TERMPOSITIONS = 0x00000080;
final static int STORE_TERMPOSITIONS = 0x00000100; final static int STORE_TERMOFFSETS = 0x00000100;
final static int STORE_TERMOFFSETS = 0x00000200;
final static int MULTIVALUED = 0x00000400; final static int MULTIVALUED = 0x00000200;
final static int SORT_MISSING_FIRST = 0x00000800; final static int SORT_MISSING_FIRST = 0x00000400;
final static int SORT_MISSING_LAST = 0x00001000; final static int SORT_MISSING_LAST = 0x00000800;
final static int REQUIRED = 0x00002000; final static int REQUIRED = 0x00001000;
static final String[] propertyNames = { static final String[] propertyNames = {
"indexed", "tokenized", "stored", "indexed", "tokenized", "stored",
"binary", "compressed", "omitNorms", "omitTermFreqAndPositions", "binary", "omitNorms", "omitTermFreqAndPositions",
"termVectors", "termPositions", "termOffsets", "termVectors", "termPositions", "termOffsets",
"multiValued", "multiValued",
"sortMissingFirst","sortMissingLast","required" "sortMissingFirst","sortMissingLast","required"

View File

@ -127,8 +127,12 @@ public abstract class FieldType extends FieldProperties {
void setArgs(IndexSchema schema, Map<String,String> args) { void setArgs(IndexSchema schema, Map<String,String> args) {
// default to STORED, INDEXED, OMIT_TF_POSITIONS and MULTIVALUED depending on schema version // default to STORED, INDEXED, OMIT_TF_POSITIONS and MULTIVALUED depending on schema version
properties = (STORED | INDEXED); properties = (STORED | INDEXED);
if (schema.getVersion()< 1.1f) properties |= MULTIVALUED; float schemaVersion = schema.getVersion();
if (schema.getVersion()> 1.1f) properties |= OMIT_TF_POSITIONS; if (schemaVersion < 1.1f) properties |= MULTIVALUED;
if (schemaVersion > 1.1f) properties |= OMIT_TF_POSITIONS;
if (schemaVersion < 1.3) {
args.remove("compressThreshold");
}
this.args=args; this.args=args;
Map<String,String> initArgs = new HashMap<String,String>(args); Map<String,String> initArgs = new HashMap<String,String>(args);

View File

@ -83,7 +83,6 @@ public final class SchemaField extends FieldProperties {
public boolean multiValued() { return (properties & MULTIVALUED)!=0; } public boolean multiValued() { return (properties & MULTIVALUED)!=0; }
public boolean sortMissingFirst() { return (properties & SORT_MISSING_FIRST)!=0; } public boolean sortMissingFirst() { return (properties & SORT_MISSING_FIRST)!=0; }
public boolean sortMissingLast() { return (properties & SORT_MISSING_LAST)!=0; } public boolean sortMissingLast() { return (properties & SORT_MISSING_LAST)!=0; }
public boolean isCompressed() { return (properties & COMPRESSED)!=0; }
public boolean isRequired() { return required; } public boolean isRequired() { return required; }
// things that should be determined by field type, not set as options // things that should be determined by field type, not set as options
@ -166,7 +165,7 @@ public final class SchemaField extends FieldProperties {
// that depend on that. // that depend on that.
// //
if (on(falseProps,STORED)) { if (on(falseProps,STORED)) {
int pp = STORED | BINARY | COMPRESSED; int pp = STORED | BINARY;
if (on(pp,trueProps)) { if (on(pp,trueProps)) {
throw new RuntimeException("SchemaField: " + name + " conflicting stored field options:" + props); throw new RuntimeException("SchemaField: " + name + " conflicting stored field options:" + props);
} }

View File

@ -33,7 +33,7 @@ import java.io.IOException;
/** /**
* @version $Id$ * @version $Id$
*/ */
public class StrField extends CompressableField { public class StrField extends FieldType {
protected void init(IndexSchema schema, Map<String,String> args) { protected void init(IndexSchema schema, Map<String,String> args) {
super.init(schema, args); super.init(schema, args);
} }

View File

@ -45,7 +45,7 @@ import java.io.StringReader;
* Analyzers for field types using this implementation should be defined in the schema. * Analyzers for field types using this implementation should be defined in the schema.
* @version $Id$ * @version $Id$
*/ */
public class TextField extends CompressableField { public class TextField extends FieldType {
protected void init(IndexSchema schema, Map<String,String> args) { protected void init(IndexSchema schema, Map<String,String> args) {
properties |= TOKENIZED; properties |= TOKENIZED;
if (schema.getVersion()> 1.1f) properties &= ~OMIT_TF_POSITIONS; if (schema.getVersion()> 1.1f) properties &= ~OMIT_TF_POSITIONS;