Skip to content

Deprecates the standard filter #33468

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Sep 7, 2018
Merged

Deprecates the standard filter #33468

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
433f924
Deprecates the standard filter
jimczi Sep 6, 2018
14656d0
remove mentions of the standard filter in tests and docs. Add depreca…
jimczi Sep 7, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion docs/plugins/analysis-phonetic.asciidoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,6 @@ PUT phonetic_sample
"my_analyzer": {
"tokenizer": "standard",
"filter": [
"standard",
"lowercase",
"my_metaphone"
]
Expand Down
1 change: 0 additions & 1 deletion docs/reference/analysis/analyzers/standard-analyzer.asciidoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -292,7 +292,6 @@ PUT /standard_example
"rebuilt_standard": {
"tokenizer": "standard",
"filter": [
"standard",
"lowercase" <1>
]
}
Expand Down
4 changes: 2 additions & 2 deletions docs/reference/analysis/tokenfilters/asciifolding-tokenfilter.asciidoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ PUT /asciifold_example
"analyzer" : {
"default" : {
"tokenizer" : "standard",
"filter" : ["standard", "asciifolding"]
"filter" : ["asciifolding"]
}
}
}
Expand All @@ -37,7 +37,7 @@ PUT /asciifold_example
"analyzer" : {
"default" : {
"tokenizer" : "standard",
"filter" : ["standard", "my_ascii_folding"]
"filter" : ["my_ascii_folding"]
}
},
"filter" : {
Expand Down
2 changes: 1 addition & 1 deletion docs/reference/analysis/tokenfilters/elision-tokenfilter.asciidoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ PUT /elision_example
"analyzer" : {
"default" : {
"tokenizer" : "standard",
"filter" : ["standard", "elision"]
"filter" : ["elision"]
}
},
"filter" : {
Expand Down
4 changes: 2 additions & 2 deletions docs/reference/analysis/tokenfilters/keep-types-tokenfilter.asciidoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ PUT /keep_types_example
"analyzer" : {
"my_analyzer" : {
"tokenizer" : "standard",
"filter" : ["standard", "lowercase", "extract_numbers"]
"filter" : ["lowercase", "extract_numbers"]
}
},
"filter" : {
Expand Down Expand Up @@ -87,7 +87,7 @@ PUT /keep_types_exclude_example
"analyzer" : {
"my_analyzer" : {
"tokenizer" : "standard",
"filter" : ["standard", "lowercase", "remove_numbers"]
"filter" : ["lowercase", "remove_numbers"]
}
},
"filter" : {
Expand Down
4 changes: 2 additions & 2 deletions docs/reference/analysis/tokenfilters/keep-words-tokenfilter.asciidoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,11 +27,11 @@ PUT /keep_words_example
"analyzer" : {
"example_1" : {
"tokenizer" : "standard",
"filter" : ["standard", "lowercase", "words_till_three"]
"filter" : ["lowercase", "words_till_three"]
},
"example_2" : {
"tokenizer" : "standard",
"filter" : ["standard", "lowercase", "words_in_file"]
"filter" : ["lowercase", "words_in_file"]
}
},
"filter" : {
Expand Down
2 changes: 1 addition & 1 deletion docs/reference/analysis/tokenfilters/snowball-tokenfilter.asciidoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ PUT /my_index
"analyzer" : {
"my_analyzer" : {
"tokenizer" : "standard",
"filter" : ["standard", "lowercase", "my_snow"]
"filter" : ["lowercase", "my_snow"]
}
},
"filter" : {
Expand Down
7 changes: 4 additions & 3 deletions docs/reference/analysis/tokenfilters/standard-tokenfilter.asciidoc
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,11 @@
[[analysis-standard-tokenfilter]]
=== Standard Token Filter

deprecated[6.5.0, This filter is deprecated and will be removed in the next
major version.]

A token filter of type `standard` that normalizes tokens extracted with
the
<<analysis-standard-tokenizer,Standard
Tokenizer>>.
the <<analysis-standard-tokenizer,Standard Tokenizer>>.

[TIP]
==================================================
Expand Down
2 changes: 1 addition & 1 deletion docs/reference/analysis/tokenfilters/stemmer-tokenfilter.asciidoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ PUT /my_index
"analyzer" : {
"my_analyzer" : {
"tokenizer" : "standard",
"filter" : ["standard", "lowercase", "my_stemmer"]
"filter" : ["lowercase", "my_stemmer"]
}
},
"filter" : {
Expand Down
3 changes: 0 additions & 3 deletions docs/reference/mapping/types/percolator.asciidoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -446,7 +446,6 @@ PUT my_queries1
"type": "custom",
"tokenizer": "standard",
"filter": [
"standard",
"lowercase",
"wildcard_edge_ngram"
]
Expand Down Expand Up @@ -597,7 +596,6 @@ PUT my_queries2
"type": "custom",
"tokenizer": "standard",
"filter": [
"standard",
"lowercase",
"reverse",
"wildcard_edge_ngram"
Expand All @@ -607,7 +605,6 @@ PUT my_queries2
"type": "custom",
"tokenizer": "standard",
"filter": [
"standard",
"lowercase",
"reverse"
]
Expand Down
6 changes: 5 additions & 1 deletion docs/reference/migration/migrate_6_0/analysis.asciidoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,4 +20,8 @@ To protect against this, the maximum number of characters that to be analyzed wi
limited to 1000000 in the next major Elastic version. For this version, by default the limit
is not set. A deprecation warning will be issued when an analyzed text exceeds 1000000.
The limit can be set for a particular index with the index setting
`index.highlight.max_analyzed_offset`.
`index.highlight.max_analyzed_offset`.

==== `standard` filter has been deprecated
The `standard` token filter has been deprecated because it doesn't change anything in
the stream. It will be removed in the next major version.
4 changes: 2 additions & 2 deletions docs/reference/search/suggesters/phrase-suggest.asciidoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,12 +33,12 @@ PUT test
"trigram": {
"type": "custom",
"tokenizer": "standard",
"filter": ["standard", "shingle"]
"filter": ["shingle"]
},
"reverse": {
"type": "custom",
"tokenizer": "standard",
"filter": ["standard", "reverse"]
"filter": ["reverse"]
}
},
"filter": {
Expand Down
2 changes: 1 addition & 1 deletion plugins/analysis-icu/src/test/resources/rest-api-spec/test/analysis_icu/20_search.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@
analyzer:
my_analyzer:
tokenizer: standard
filter: ["standard", "lowercase", "my_collator"]
filter: ["lowercase", "my_collator"]
filter:
my_collator:
type: icu_collation
Expand Down
2 changes: 1 addition & 1 deletion ...nalysis-phonetic/src/test/resources/rest-api-spec/test/analysis_phonetic/10_metaphone.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@
analyzer:
my_analyzer:
tokenizer: standard
filter: ["standard", "lowercase", "my_metaphone"]
filter: ["lowercase", "my_metaphone"]
filter:
my_metaphone:
type: phonetic
Expand Down
2 changes: 1 addition & 1 deletion ...-phonetic/src/test/resources/rest-api-spec/test/analysis_phonetic/20_double_metaphone.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@
analyzer:
my_analyzer:
tokenizer: standard
filter: ["standard", "lowercase", "my_metaphone"]
filter: ["lowercase", "my_metaphone"]
filter:
my_metaphone:
type: phonetic
Expand Down
2 changes: 1 addition & 1 deletion ...ysis-phonetic/src/test/resources/rest-api-spec/test/analysis_phonetic/30_beider_morse.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@
analyzer:
my_analyzer:
tokenizer: standard
filter: ["standard", "lowercase", "beider_morse"]
filter: ["lowercase", "beider_morse"]
filter:
beider_morse:
type: phonetic
Expand Down
2 changes: 1 addition & 1 deletion ...s/analysis-phonetic/src/test/resources/rest-api-spec/test/analysis_phonetic/40_search.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@
analyzer:
my_analyzer:
tokenizer: standard
filter: ["standard", "lowercase", "my_metaphone"]
filter: ["lowercase", "my_metaphone"]
filter:
my_metaphone:
type: phonetic
Expand Down
2 changes: 1 addition & 1 deletion ...s-phonetic/src/test/resources/rest-api-spec/test/analysis_phonetic/50_daitch_mokotoff.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@
analyzer:
my_analyzer:
tokenizer: standard
filter: ["standard", "lowercase", "daitch_mokotoff"]
filter: ["lowercase", "daitch_mokotoff"]
filter:
daitch_mokotoff:
type: phonetic
Expand Down
39 changes: 0 additions & 39 deletions server/src/main/java/org/elasticsearch/index/analysis/StandardTokenFilterFactory.java
View file
Open in desktop

This file was deleted.

26 changes: 22 additions & 4 deletions server/src/main/java/org/elasticsearch/indices/analysis/AnalysisModule.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,14 +19,17 @@

package org.elasticsearch.indices.analysis;

import org.apache.logging.log4j.LogManager;
import org.apache.lucene.analysis.LowerCaseFilter;
import org.apache.lucene.analysis.standard.StandardFilter;
import org.apache.lucene.analysis.TokenStream;
import org.elasticsearch.Version;
import org.elasticsearch.cluster.metadata.IndexMetaData;
import org.elasticsearch.common.NamedRegistry;
import org.elasticsearch.common.logging.DeprecationLogger;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.env.Environment;
import org.elasticsearch.index.IndexSettings;
import org.elasticsearch.index.analysis.AbstractTokenFilterFactory;
import org.elasticsearch.index.analysis.AnalysisRegistry;
import org.elasticsearch.index.analysis.AnalyzerProvider;
import org.elasticsearch.index.analysis.CharFilterFactory;
Expand All @@ -39,7 +42,6 @@
import org.elasticsearch.index.analysis.ShingleTokenFilterFactory;
import org.elasticsearch.index.analysis.SimpleAnalyzerProvider;
import org.elasticsearch.index.analysis.StandardAnalyzerProvider;
import org.elasticsearch.index.analysis.StandardTokenFilterFactory;
import org.elasticsearch.index.analysis.StandardTokenizerFactory;
import org.elasticsearch.index.analysis.StopAnalyzerProvider;
import org.elasticsearch.index.analysis.StopTokenFilterFactory;
Expand Down Expand Up @@ -69,6 +71,8 @@ public final class AnalysisModule {

private static final IndexSettings NA_INDEX_SETTINGS;

private static final DeprecationLogger DEPRECATION_LOGGER = new DeprecationLogger(LogManager.getLogger(AnalysisModule.class));

private final HunspellService hunspellService;
private final AnalysisRegistry analysisRegistry;

Expand Down Expand Up @@ -116,7 +120,16 @@ private NamedRegistry<AnalysisProvider<TokenFilterFactory>> setupTokenFilters(Li
hunspellService) {
NamedRegistry<AnalysisProvider<TokenFilterFactory>> tokenFilters = new NamedRegistry<>("token_filter");
tokenFilters.register("stop", StopTokenFilterFactory::new);
tokenFilters.register("standard", StandardTokenFilterFactory::new);
tokenFilters.register("standard", (indexSettings, environment, name, settings) -> {
DEPRECATION_LOGGER.deprecatedAndMaybeLog("standard_deprecation",
"The [standard] token filter name is deprecated and will be removed in a future version.");
return new AbstractTokenFilterFactory(indexSettings, name, settings) {
@Override
public TokenStream create(TokenStream tokenStream) {
return tokenStream;
}
};
});
tokenFilters.register("shingle", ShingleTokenFilterFactory::new);
tokenFilters.register("hunspell", requiresAnalysisSettings((indexSettings, env, name, settings) -> new HunspellTokenFilterFactory
(indexSettings, name, settings, hunspellService)));
Expand Down Expand Up @@ -153,7 +166,12 @@ static Map<String, PreConfiguredTokenFilter> setupPreConfiguredTokenFilters(List

// Add filters available in lucene-core
preConfiguredTokenFilters.register("lowercase", PreConfiguredTokenFilter.singleton("lowercase", true, LowerCaseFilter::new));
preConfiguredTokenFilters.register("standard", PreConfiguredTokenFilter.singleton("standard", false, StandardFilter::new));
preConfiguredTokenFilters.register( "standard",
PreConfiguredTokenFilter.singletonWithVersion("standard", false, (reader, version) -> {
DEPRECATION_LOGGER.deprecatedAndMaybeLog("standard_deprecation",
"The [standard] token filter is deprecated and will be removed in a future version.");
return reader;
}));
/* Note that "stop" is available in lucene-core but it's pre-built
* version uses a set of English stop words that are in
* lucene-analyzers-common so "stop" is defined in the analysis-common
Expand Down
13 changes: 13 additions & 0 deletions server/src/test/java/org/elasticsearch/indices/analysis/AnalysisModuleTests.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -435,6 +435,19 @@ public Map<String, Dictionary> getHunspellDictionaries() {
assertSame(dictionary, module.getHunspellService().getDictionary("foo"));
}

public void testStandardFilterDeprecation() throws IOException {
Version version = VersionUtils.randomVersionBetween(random(), Version.V_5_0_0, Version.CURRENT);
Settings settings = Settings.builder()
.put("index.analysis.analyzer.my_standard.tokenizer", "standard")
.put("index.analysis.analyzer.my_standard.filter", "standard")
.put(Environment.PATH_HOME_SETTING.getKey(), createTempDir().toString())
.put(IndexMetaData.SETTING_VERSION_CREATED, version)
.build();
IndexAnalyzers analyzers = getIndexAnalyzers(settings);
assertTokenStreamContents(analyzers.get("my_standard").tokenStream("", "test"), new String[]{"test"});
assertWarnings("The [standard] token filter is deprecated and will be removed in a future version.");
}

// Simple char filter that appends text to the term
public static class AppendCharFilter extends CharFilter {

Expand Down
3 changes: 1 addition & 2 deletions test/framework/src/main/java/org/elasticsearch/indices/analysis/AnalysisFactoryTestCase.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,6 @@
import org.elasticsearch.index.analysis.PreConfiguredTokenFilter;
import org.elasticsearch.index.analysis.PreConfiguredTokenizer;
import org.elasticsearch.index.analysis.ShingleTokenFilterFactory;
import org.elasticsearch.index.analysis.StandardTokenFilterFactory;
import org.elasticsearch.index.analysis.StandardTokenizerFactory;
import org.elasticsearch.index.analysis.StopTokenFilterFactory;
import org.elasticsearch.index.analysis.SynonymGraphTokenFilterFactory;
Expand Down Expand Up @@ -167,7 +166,7 @@ private static String toCamelCase(String s) {
.put("soraninormalization", MovedToAnalysisCommon.class)
.put("soranistem", MovedToAnalysisCommon.class)
.put("spanishlightstem", MovedToAnalysisCommon.class)
.put("standard", StandardTokenFilterFactory.class)
.put("standard", Deprecated.class)
.put("stemmeroverride", MovedToAnalysisCommon.class)
.put("stop", StopTokenFilterFactory.class)
.put("swedishlightstem", MovedToAnalysisCommon.class)
Expand Down
2 changes: 1 addition & 1 deletion test/framework/src/main/resources/org/elasticsearch/analysis/common/test1.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@
},
"czechAnalyzerWithStemmer":{
"tokenizer":"standard",
"filter":["standard", "lowercase", "stop", "czech_stem"]
"filter":["lowercase", "stop", "czech_stem"]
},
"decompoundingAnalyzer":{
"tokenizer":"standard",
Expand Down