Add text field support to archive indices #86591
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -50,6 +50,7 @@ | |
| import org.elasticsearch.common.lucene.Lucene; | ||
| import org.elasticsearch.common.lucene.search.AutomatonQueries; | ||
| import org.elasticsearch.common.lucene.search.MultiPhrasePrefixQuery; | ||
| import org.elasticsearch.common.unit.Fuzziness; | ||
| import org.elasticsearch.common.xcontent.support.XContentMapValues; | ||
| import org.elasticsearch.index.analysis.AnalyzerScope; | ||
| import org.elasticsearch.index.analysis.IndexAnalyzers; | ||
|
|
@@ -278,7 +279,8 @@ public Builder(String name, Version indexCreatedVersion, IndexAnalyzers indexAna | |
| this.analyzers = new TextParams.Analyzers( | ||
| indexAnalyzers, | ||
| m -> ((TextFieldMapper) m).indexAnalyzer, | ||
| m -> (((TextFieldMapper) m).positionIncrementGap), | ||
| indexCreatedVersion | ||
| ); | ||
| } | ||
|
|
||
|
|
@@ -329,7 +331,7 @@ protected List<Parameter<?>> getParameters() { | |
| ); | ||
| } | ||
|
|
||
| private TextFieldType buildFieldType(FieldType fieldType, MapperBuilderContext context, Version indexCreatedVersion) { | ||
| NamedAnalyzer searchAnalyzer = analyzers.getSearchAnalyzer(); | ||
| NamedAnalyzer searchQuoteAnalyzer = analyzers.getSearchQuoteAnalyzer(); | ||
| if (analyzers.positionIncrementGap.isConfigured()) { | ||
|
|
@@ -340,7 +342,12 @@ private TextFieldType buildFieldType(FieldType fieldType, MapperBuilderContext c | |
| } | ||
| } | ||
| TextSearchInfo tsi = new TextSearchInfo(fieldType, similarity.getValue(), searchAnalyzer, searchQuoteAnalyzer); | ||
| TextFieldType ft; | ||
| if (indexCreatedVersion.isLegacyIndexVersion()) { | ||
| ft = new ConstantScoreTextFieldType(context.buildFullName(name), index.getValue(), store.getValue(), tsi, meta.getValue()); | ||
| } else { | ||
| ft = new TextFieldType(context.buildFullName(name), index.getValue(), store.getValue(), tsi, meta.getValue()); | ||
| } | ||
| ft.eagerGlobalOrdinals = eagerGlobalOrdinals.getValue(); | ||
| if (fieldData.getValue()) { | ||
| ft.setFielddata(true, freqFilter.getValue()); | ||
|
|
@@ -430,7 +437,7 @@ public Map<String, NamedAnalyzer> indexAnalyzers(String name, SubFieldInfo phras | |
| @Override | ||
| public TextFieldMapper build(MapperBuilderContext context) { | ||
| FieldType fieldType = TextParams.buildFieldType(index, store, indexOptions, norms, termVectors); | ||
| TextFieldType tft = buildFieldType(fieldType, context, indexCreatedVersion); | ||
| SubFieldInfo phraseFieldInfo = buildPhraseInfo(fieldType, tft); | ||
| SubFieldInfo prefixFieldInfo = buildPrefixInfo(context, fieldType, tft); | ||
| MultiFields multiFields = multiFieldsBuilder.build(this, context); | ||
|
|
@@ -453,7 +460,12 @@ public TextFieldMapper build(MapperBuilderContext context) { | |
| } | ||
| } | ||
|
|
||
| private static final Version MINIMUM_COMPATIBILITY_VERSION = Version.fromString("5.0.0"); | ||
|
|
||
| public static final TypeParser PARSER = new TypeParser( | ||
| (n, c) -> new Builder(n, c.indexVersionCreated(), c.getIndexAnalyzers()), | ||
| MINIMUM_COMPATIBILITY_VERSION | ||
| ); | ||
|
|
||
| private static class PhraseWrappedAnalyzer extends AnalyzerWrapper { | ||
|
|
||
|
|
@@ -897,6 +909,78 @@ public IndexFieldData.Builder fielddataBuilder(String fullyQualifiedIndexName, S | |
|
|
||
| } | ||
|
|
||
| public static class ConstantScoreTextFieldType extends TextFieldType { | ||
|
|
||
| public ConstantScoreTextFieldType(String name, boolean indexed, boolean stored, TextSearchInfo tsi, Map<String, String> meta) { | ||
| super(name, indexed, stored, tsi, meta); | ||
| } | ||
|
|
||
| public ConstantScoreTextFieldType(String name) { | ||
| this( | ||
| name, | ||
| true, | ||
| false, | ||
| new TextSearchInfo(Defaults.FIELD_TYPE, null, Lucene.STANDARD_ANALYZER, Lucene.STANDARD_ANALYZER), | ||
| Collections.emptyMap() | ||
| ); | ||
| } | ||
|
|
||
| public ConstantScoreTextFieldType(String name, boolean indexed, boolean stored, Map<String, String> meta) { | ||
| this( | ||
| name, | ||
| indexed, | ||
| stored, | ||
| new TextSearchInfo(Defaults.FIELD_TYPE, null, Lucene.STANDARD_ANALYZER, Lucene.STANDARD_ANALYZER), | ||
| meta | ||
| ); | ||
| } | ||
|
|
||
| @Override | ||
| public Query termQuery(Object value, SearchExecutionContext context) { | ||
| // Disable scoring | ||
| return new ConstantScoreQuery(super.termQuery(value, context)); | ||
| } | ||
|
|
||
| @Override | ||
| public Query fuzzyQuery( | ||
| Object value, | ||
| Fuzziness fuzziness, | ||
| int prefixLength, | ||
| int maxExpansions, | ||
| boolean transpositions, | ||
| SearchExecutionContext context | ||
| ) { | ||
| // Disable scoring | ||
| return new ConstantScoreQuery(super.fuzzyQuery(value, fuzziness, prefixLength, maxExpansions, transpositions, context)); | ||
| } | ||
|
|
||
| @Override | ||
| public Query phraseQuery(TokenStream stream, int slop, boolean enablePosIncrements, SearchExecutionContext queryShardContext) | ||
| throws IOException { | ||
| // Disable scoring | ||
| return new ConstantScoreQuery(super.phraseQuery(stream, slop, enablePosIncrements, queryShardContext)); | ||
| } | ||
|
|
||
| @Override | ||
| public Query multiPhraseQuery( | ||
| TokenStream stream, | ||
| int slop, | ||
| boolean enablePositionIncrements, | ||
| SearchExecutionContext queryShardContext | ||
| ) throws IOException { | ||
| // Disable scoring | ||
| return new ConstantScoreQuery(super.multiPhraseQuery(stream, slop, enablePositionIncrements, queryShardContext)); | ||
| } | ||
|
|
||
| @Override | ||
| public Query phrasePrefixQuery(TokenStream stream, int slop, int maxExpansions, SearchExecutionContext queryShardContext) | ||
| throws IOException { | ||
| // Disable scoring | ||
| return new ConstantScoreQuery(super.phrasePrefixQuery(stream, slop, maxExpansions, queryShardContext)); | ||
| } | ||
|
|
||
|
There was a problem hiding this comment. Span prefix queries will do something weird here, won't they? But then span prefix queries are kind of weird in any case. I think they're enough of an edge case that we can override There was a problem hiding this comment. I agree that we don't need to support them. I've pushed 604d70c but I'm not sure how to add a test for it (I couldn't find existing tests that exercise this method). There was a problem hiding this comment. It looks as though the two places it would be used are 1) a prefix query wrapped in a span multiterm query, which can be replaced by an interval query; and 2) a match_phrase_prefix query that uses multiterm synonyms, which will get factored away when we rework things to use QueryBuilders properly. So I think we can happily just throw an exception here and not worry about it further :) |
||
| } | ||
|
|
||
| private final Version indexCreatedVersion; | ||
| private final boolean index; | ||
| private final boolean store; | ||
|
|
||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The changes in this class revert the changes made in #85059, as we now validate against a MapperService with all analyzers configured when restoring the legacy index in
RestoreService. The reason for doing it this way now is that it provides better error messages on restore, but also handles a tricky situation where the Mapping returned by these methods here would have their analyzer settings misconfigured as checkMappingsCompatibility would not create a proper environment with actual analyzers configured.