[Remove] Analyzer Deprecations (#1741)

This commit removes deprecated analyzer instantiation that is no longer permitted in OpenSearch 2.0.0. Signed-off-by: Nicholas Walter Knize <[email protected]>
opensearch-project · Dec 16, 2021 · 5550f8d · 5550f8d
1 parent 5966cc0
commit 5550f8d
Show file tree

Hide file tree

Showing 21 changed files with 22 additions and 834 deletions.
diff --git a/.../analysis-common/src/main/java/org/opensearch/analysis/common/CJKBigramFilterFactory.java b/.../analysis-common/src/main/java/org/opensearch/analysis/common/CJKBigramFilterFactory.java
@@ -35,8 +35,6 @@
 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.analysis.cjk.CJKBigramFilter;
 import org.apache.lucene.analysis.miscellaneous.DisableGraphAttribute;
-import org.opensearch.LegacyESVersion;
-import org.opensearch.common.logging.DeprecationLogger;
 import org.opensearch.common.settings.Settings;
 import org.opensearch.env.Environment;
 import org.opensearch.index.IndexSettings;
@@ -63,9 +61,6 @@
  * In all cases, all non-CJK input is passed thru unmodified.
  */
 public final class CJKBigramFilterFactory extends AbstractTokenFilterFactory {
-
-    private static final DeprecationLogger DEPRECATION_LOGGER = DeprecationLogger.getLogger(CJKBigramFilterFactory.class);
-
     private final int flags;
     private final boolean outputUnigrams;
 
@@ -110,14 +105,7 @@ public TokenStream create(TokenStream tokenStream) {
     @Override
     public TokenFilterFactory getSynonymFilter() {
         if (outputUnigrams) {
-            if (indexSettings.getIndexVersionCreated().onOrAfter(LegacyESVersion.V_7_0_0)) {
-                throw new IllegalArgumentException("Token filter [" + name() + "] cannot be used to parse synonyms");
-            } else {
-                DEPRECATION_LOGGER.deprecate(
-                    name() + "_synonym_tokenfilters",
-                    "Token filter [" + name() + "] will not be usable to parse synonyms after v7.0"
-                );
-            }
+            throw new IllegalArgumentException("Token filter [" + name() + "] cannot be used to parse synonyms");
         }
         return this;
     }

diff --git a/...es/analysis-common/src/main/java/org/opensearch/analysis/common/CommonAnalysisPlugin.java b/...es/analysis-common/src/main/java/org/opensearch/analysis/common/CommonAnalysisPlugin.java
@@ -200,9 +200,6 @@ public List<ScriptContext<?>> getContexts() {
     public Map<String, AnalysisProvider<AnalyzerProvider<? extends Analyzer>>> getAnalyzers() {
         Map<String, AnalysisProvider<AnalyzerProvider<? extends Analyzer>>> analyzers = new TreeMap<>();
         analyzers.put("fingerprint", FingerprintAnalyzerProvider::new);
-
-        // TODO remove in 8.0
-        analyzers.put("standard_html_strip", StandardHtmlStripAnalyzerProvider::new);
         analyzers.put("pattern", PatternAnalyzerProvider::new);
         analyzers.put("snowball", SnowballAnalyzerProvider::new);
 
@@ -265,7 +262,6 @@ public Map<String, AnalysisProvider<TokenFilterFactory>> getTokenFilters() {
             requiresAnalysisSettings((i, e, n, s) -> new ScriptedConditionTokenFilterFactory(i, n, s, scriptService.get()))
         );
         filters.put("decimal_digit", DecimalDigitFilterFactory::new);
-        filters.put("delimited_payload_filter", LegacyDelimitedPayloadTokenFilterFactory::new);
         filters.put("delimited_payload", DelimitedPayloadTokenFilterFactory::new);
         filters.put("dictionary_decompounder", requiresAnalysisSettings(DictionaryCompoundWordTokenFilterFactory::new));
         filters.put("dutch_stem", DutchStemTokenFilterFactory::new);
@@ -388,14 +384,6 @@ public Map<String, AnalysisProvider<TokenizerFactory>> getTokenizers() {
     @Override
     public List<PreBuiltAnalyzerProviderFactory> getPreBuiltAnalyzerProviderFactories() {
         List<PreBuiltAnalyzerProviderFactory> analyzers = new ArrayList<>();
-        // TODO remove in 8.0
-        analyzers.add(
-            new PreBuiltAnalyzerProviderFactory(
-                "standard_html_strip",
-                CachingStrategy.OPENSEARCH,
-                () -> new StandardHtmlStripAnalyzer(CharArraySet.EMPTY_SET)
-            )
-        );
         analyzers.add(
             new PreBuiltAnalyzerProviderFactory(
                 "pattern",
@@ -462,16 +450,6 @@ public List<PreBuiltAnalyzerProviderFactory> getPreBuiltAnalyzerProviderFactorie
     public List<PreConfiguredCharFilter> getPreConfiguredCharFilters() {
         List<PreConfiguredCharFilter> filters = new ArrayList<>();
         filters.add(PreConfiguredCharFilter.singleton("html_strip", false, HTMLStripCharFilter::new));
-        filters.add(PreConfiguredCharFilter.openSearchVersion("htmlStrip", false, (reader, version) -> {
-            if (version.onOrAfter(LegacyESVersion.V_6_3_0)) {
-                deprecationLogger.deprecate(
-                    "htmlStrip_deprecation",
-                    "The [htmpStrip] char filter name is deprecated and will be removed in a future version. "
-                        + "Please change the filter name to [html_strip] instead."
-                );
-            }
-            return new HTMLStripCharFilter(reader);
-        }));
         return filters;
     }
 
@@ -492,18 +470,6 @@ public List<PreConfiguredTokenFilter> getPreConfiguredTokenFilters() {
         );
         filters.add(PreConfiguredTokenFilter.singleton("czech_stem", false, CzechStemFilter::new));
         filters.add(PreConfiguredTokenFilter.singleton("decimal_digit", true, DecimalDigitFilter::new));
-        filters.add(PreConfiguredTokenFilter.openSearchVersion("delimited_payload_filter", false, (input, version) -> {
-            if (version.onOrAfter(LegacyESVersion.V_7_0_0)) {
-                throw new IllegalArgumentException(
-                    "[delimited_payload_filter] is not supported for new indices, use [delimited_payload] instead"
-                );
-            }
-            return new DelimitedPayloadTokenFilter(
-                input,
-                DelimitedPayloadTokenFilterFactory.DEFAULT_DELIMITER,
-                DelimitedPayloadTokenFilterFactory.DEFAULT_ENCODER
-            );
-        }));
         filters.add(
             PreConfiguredTokenFilter.singleton(
                 "delimited_payload",

diff --git a/...is-common/src/main/java/org/opensearch/analysis/common/CommonGramsTokenFilterFactory.java b/...is-common/src/main/java/org/opensearch/analysis/common/CommonGramsTokenFilterFactory.java
@@ -36,8 +36,6 @@
 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.analysis.commongrams.CommonGramsFilter;
 import org.apache.lucene.analysis.commongrams.CommonGramsQueryFilter;
-import org.opensearch.LegacyESVersion;
-import org.opensearch.common.logging.DeprecationLogger;
 import org.opensearch.common.settings.Settings;
 import org.opensearch.env.Environment;
 import org.opensearch.index.IndexSettings;
@@ -46,9 +44,6 @@
 import org.opensearch.index.analysis.TokenFilterFactory;
 
 public class CommonGramsTokenFilterFactory extends AbstractTokenFilterFactory {
-
-    private static final DeprecationLogger DEPRECATION_LOGGER = DeprecationLogger.getLogger(CommonGramsTokenFilterFactory.class);
-
     private final CharArraySet words;
 
     private final boolean ignoreCase;
@@ -80,15 +75,6 @@ public TokenStream create(TokenStream tokenStream) {
 
     @Override
     public TokenFilterFactory getSynonymFilter() {
-        if (indexSettings.getIndexVersionCreated().onOrAfter(LegacyESVersion.V_7_0_0)) {
-            throw new IllegalArgumentException("Token filter [" + name() + "] cannot be used to parse synonyms");
-        } else {
-            DEPRECATION_LOGGER.deprecate(
-                name() + "_synonym_tokenfilters",
-                "Token filter [" + name() + "] will not be usable to parse synonyms after v7.0"
-            );
-        }
-
-        return this;
+        throw new IllegalArgumentException("Token filter [" + name() + "] cannot be used to parse synonyms");
     }
 }
diff --git a/...ysis-common/src/main/java/org/opensearch/analysis/common/EdgeNGramTokenFilterFactory.java b/...ysis-common/src/main/java/org/opensearch/analysis/common/EdgeNGramTokenFilterFactory.java
@@ -35,18 +35,13 @@
 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.analysis.ngram.EdgeNGramTokenFilter;
 import org.apache.lucene.analysis.reverse.ReverseStringFilter;
-import org.opensearch.LegacyESVersion;
-import org.opensearch.common.logging.DeprecationLogger;
 import org.opensearch.common.settings.Settings;
 import org.opensearch.env.Environment;
 import org.opensearch.index.IndexSettings;
 import org.opensearch.index.analysis.AbstractTokenFilterFactory;
 import org.opensearch.index.analysis.TokenFilterFactory;
 
 public class EdgeNGramTokenFilterFactory extends AbstractTokenFilterFactory {
-
-    private static final DeprecationLogger DEPRECATION_LOGGER = DeprecationLogger.getLogger(EdgeNGramTokenFilterFactory.class);
-
     private final int minGram;
 
     private final int maxGram;
@@ -102,14 +97,6 @@ public boolean breaksFastVectorHighlighter() {
 
     @Override
     public TokenFilterFactory getSynonymFilter() {
-        if (indexSettings.getIndexVersionCreated().onOrAfter(LegacyESVersion.V_7_0_0)) {
-            throw new IllegalArgumentException("Token filter [" + name() + "] cannot be used to parse synonyms");
-        } else {
-            DEPRECATION_LOGGER.deprecate(
-                name() + "_synonym_tokenfilters",
-                "Token filter [" + name() + "] will not be usable to parse synonyms after v7.0"
-            );
-            return this;
-        }
+        throw new IllegalArgumentException("Token filter [" + name() + "] cannot be used to parse synonyms");
     }
 }
diff --git a/...is-common/src/main/java/org/opensearch/analysis/common/FingerprintTokenFilterFactory.java b/...is-common/src/main/java/org/opensearch/analysis/common/FingerprintTokenFilterFactory.java
@@ -34,8 +34,6 @@
 
 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.analysis.miscellaneous.FingerprintFilter;
-import org.opensearch.LegacyESVersion;
-import org.opensearch.common.logging.DeprecationLogger;
 import org.opensearch.common.settings.Settings;
 import org.opensearch.env.Environment;
 import org.opensearch.index.IndexSettings;
@@ -46,9 +44,6 @@
 import static org.opensearch.analysis.common.FingerprintAnalyzerProvider.MAX_OUTPUT_SIZE;
 
 public class FingerprintTokenFilterFactory extends AbstractTokenFilterFactory {
-
-    private static final DeprecationLogger DEPRECATION_LOGGER = DeprecationLogger.getLogger(FingerprintTokenFilterFactory.class);
-
     private final char separator;
     private final int maxOutputSize;
 
@@ -67,15 +62,7 @@ public TokenStream create(TokenStream tokenStream) {
 
     @Override
     public TokenFilterFactory getSynonymFilter() {
-        if (indexSettings.getIndexVersionCreated().onOrAfter(LegacyESVersion.V_7_0_0)) {
-            throw new IllegalArgumentException("Token filter [" + name() + "] cannot be used to parse synonyms");
-        } else {
-            DEPRECATION_LOGGER.deprecate(
-                name() + "_synonym_tokenfilters",
-                "Token filter [" + name() + "] will not be usable to parse synonyms after v7.0"
-            );
-            return this;
-        }
+        throw new IllegalArgumentException("Token filter [" + name() + "] cannot be used to parse synonyms");
     }
 
 }
diff --git a/...rc/main/java/org/opensearch/analysis/common/LegacyDelimitedPayloadTokenFilterFactory.java b/...rc/main/java/org/opensearch/analysis/common/LegacyDelimitedPayloadTokenFilterFactory.java
diff --git a/...is-common/src/main/java/org/opensearch/analysis/common/MultiplexerTokenFilterFactory.java b/...is-common/src/main/java/org/opensearch/analysis/common/MultiplexerTokenFilterFactory.java
@@ -37,9 +37,7 @@
 import org.apache.lucene.analysis.miscellaneous.ConditionalTokenFilter;
 import org.apache.lucene.analysis.miscellaneous.RemoveDuplicatesTokenFilter;
 import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
-import org.opensearch.LegacyESVersion;
 import org.opensearch.common.Strings;
-import org.opensearch.common.logging.DeprecationLogger;
 import org.opensearch.common.settings.Settings;
 import org.opensearch.env.Environment;
 import org.opensearch.index.IndexSettings;
@@ -55,9 +53,6 @@
 import java.util.function.Function;
 
 public class MultiplexerTokenFilterFactory extends AbstractTokenFilterFactory {
-
-    private static final DeprecationLogger DEPRECATION_LOGGER = DeprecationLogger.getLogger(MultiplexerTokenFilterFactory.class);
-
     private List<String> filterNames;
     private final boolean preserveOriginal;
 
@@ -74,20 +69,7 @@ public TokenStream create(TokenStream tokenStream) {
 
     @Override
     public TokenFilterFactory getSynonymFilter() {
-        if (indexSettings.getIndexVersionCreated().onOrAfter(LegacyESVersion.V_7_0_0)) {
-            throw new IllegalArgumentException("Token filter [" + name() + "] cannot be used to parse synonyms");
-        } else {
-            if (preserveOriginal) {
-                DEPRECATION_LOGGER.deprecate(
-                    name() + "_synonym_tokenfilters",
-                    "Token filter [" + name() + "] will not be usable to parse synonyms after v7.0"
-                );
-                return IDENTITY_FILTER;
-            }
-            throw new IllegalArgumentException(
-                "Token filter [" + name() + "] cannot be used to parse synonyms unless [preserve_original] is [true]"
-            );
-        }
+        throw new IllegalArgumentException("Token filter [" + name() + "] cannot be used to parse synonyms");
     }
 
     @Override
@@ -142,20 +124,7 @@ public TokenStream create(TokenStream tokenStream) {
 
             @Override
             public TokenFilterFactory getSynonymFilter() {
-                if (indexSettings.getIndexVersionCreated().onOrAfter(LegacyESVersion.V_7_0_0)) {
-                    throw new IllegalArgumentException("Token filter [" + name() + "] cannot be used to parse synonyms");
-                } else {
-                    if (preserveOriginal) {
-                        DEPRECATION_LOGGER.deprecate(
-                            name() + "_synonym_tokenfilters",
-                            "Token filter [" + name() + "] will not be usable to parse synonyms after v7.0"
-                        );
-                        return IDENTITY_FILTER;
-                    }
-                    throw new IllegalArgumentException(
-                        "Token filter [" + name() + "] cannot be used to parse synonyms unless [preserve_original] is [true]"
-                    );
-                }
+                throw new IllegalArgumentException("Token filter [" + name() + "] cannot be used to parse synonyms");
             }
 
             @Override

diff --git a/...analysis-common/src/main/java/org/opensearch/analysis/common/NGramTokenFilterFactory.java b/...analysis-common/src/main/java/org/opensearch/analysis/common/NGramTokenFilterFactory.java
@@ -35,17 +35,13 @@
 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.analysis.ngram.NGramTokenFilter;
 import org.opensearch.LegacyESVersion;
-import org.opensearch.common.logging.DeprecationLogger;
 import org.opensearch.common.settings.Settings;
 import org.opensearch.env.Environment;
 import org.opensearch.index.IndexSettings;
 import org.opensearch.index.analysis.AbstractTokenFilterFactory;
 import org.opensearch.index.analysis.TokenFilterFactory;
 
 public class NGramTokenFilterFactory extends AbstractTokenFilterFactory {
-
-    private static final DeprecationLogger DEPRECATION_LOGGER = DeprecationLogger.getLogger(NGramTokenFilterFactory.class);
-
     private final int minGram;
     private final int maxGram;
     private final boolean preserveOriginal;
@@ -88,14 +84,6 @@ public TokenStream create(TokenStream tokenStream) {
 
     @Override
     public TokenFilterFactory getSynonymFilter() {
-        if (indexSettings.getIndexVersionCreated().onOrAfter(LegacyESVersion.V_7_0_0)) {
-            throw new IllegalArgumentException("Token filter [" + name() + "] cannot be used to parse synonyms");
-        } else {
-            DEPRECATION_LOGGER.deprecate(
-                name() + "_synonym_tokenfilters",
-                "Token filter [" + name() + "] will not be usable to parse synonyms after v7.0"
-            );
-            return this;
-        }
+        throw new IllegalArgumentException("Token filter [" + name() + "] cannot be used to parse synonyms");
     }
 }