Some internal refactorings in AnalysisRegistry (#40609)

Reducing some methods scope and marking them as static where possible. Removing
"alias" support from AnalysisRegistry#produceAnalyze and changing that method to
return a NamedAnalyzer instead of having a side effect on the analyzer map passed in.
Also, CustomAnalyzerProvider doesn't seem to need the `environment` field.

Author: Christoph Büscher

server/src/main/java/org/elasticsearch/index/analysis/AnalysisRegistry.java

@@ -293,13 +293,13 @@ private <T> Map<String, T> buildMapping(Component component, IndexSettings setti
                 T factory = null;
                 if (typeName == null) {
                     if (currentSettings.get("tokenizer") != null) {
-                        factory = (T) new CustomAnalyzerProvider(settings, name, currentSettings, environment);
+                        factory = (T) new CustomAnalyzerProvider(settings, name, currentSettings);
                     } else {
                         throw new IllegalArgumentException(component + " [" + name + "] " +
                             "must specify either an analyzer type, or a tokenizer");
                     }
                 } else if (typeName.equals("custom")) {
-                    factory = (T) new CustomAnalyzerProvider(settings, name, currentSettings, environment);
+                    factory = (T) new CustomAnalyzerProvider(settings, name, currentSettings);
                 }
                 if (factory != null) {
                     factories.put(name, factory);
@@ -430,8 +430,10 @@ public IndexAnalyzers build(IndexSettings indexSettings,
         Map<String, NamedAnalyzer> normalizers = new HashMap<>();
         Map<String, NamedAnalyzer> whitespaceNormalizers = new HashMap<>();
         for (Map.Entry<String, AnalyzerProvider<?>> entry : analyzerProviders.entrySet()) {
-            processAnalyzerFactory(indexSettings, entry.getKey(), entry.getValue(), analyzers,
-                tokenFilterFactoryFactories, charFilterFactoryFactories, tokenizerFactoryFactories);
+            analyzers.merge(entry.getKey(), produceAnalyzer(entry.getKey(), entry.getValue(), tokenFilterFactoryFactories,
+                    charFilterFactoryFactories, tokenizerFactoryFactories), (k, v) -> {
+                        throw new IllegalStateException("already registered analyzer with name: " + entry.getKey());
+                    });
         }
         for (Map.Entry<String, AnalyzerProvider<?>> entry : normalizerProviders.entrySet()) {
             processNormalizerFactory(entry.getKey(), entry.getValue(), normalizers, "keyword",
@@ -441,9 +443,9 @@ public IndexAnalyzers build(IndexSettings indexSettings,
         }
 
         if (!analyzers.containsKey("default")) {
-            processAnalyzerFactory(indexSettings, "default", new StandardAnalyzerProvider(indexSettings, null,
-                    "default", Settings.Builder.EMPTY_SETTINGS),
-                analyzers, tokenFilterFactoryFactories, charFilterFactoryFactories, tokenizerFactoryFactories);
+            NamedAnalyzer defaultAnalyzer = produceAnalyzer("default", new StandardAnalyzerProvider(indexSettings, null, "default",
+                    Settings.Builder.EMPTY_SETTINGS), tokenFilterFactoryFactories, charFilterFactoryFactories, tokenizerFactoryFactories);
+            analyzers.put("default", defaultAnalyzer);
         }
         if (!analyzers.containsKey("default_search")) {
             analyzers.put("default_search", analyzers.get("default"));
@@ -473,11 +475,9 @@ public IndexAnalyzers build(IndexSettings indexSettings,
                 whitespaceNormalizers);
     }
 
-    private void processAnalyzerFactory(IndexSettings indexSettings,
-                                        String name,
-                                        AnalyzerProvider<?> analyzerFactory,
-                                        Map<String, NamedAnalyzer> analyzers, Map<String, TokenFilterFactory> tokenFilters,
-                                        Map<String, CharFilterFactory> charFilters, Map<String, TokenizerFactory> tokenizers) {
+    private static NamedAnalyzer produceAnalyzer(String name, AnalyzerProvider<?> analyzerFactory,
+            Map<String, TokenFilterFactory> tokenFilters, Map<String, CharFilterFactory> charFilters,
+            Map<String, TokenizerFactory> tokenizers) {
         /*
          * Lucene defaults positionIncrementGap to 0 in all analyzers but
          * Elasticsearch defaults them to 0 only before version 2.0
@@ -511,15 +511,7 @@ private void processAnalyzerFactory(IndexSettings indexSettings,
         } else {
             analyzer = new NamedAnalyzer(name, analyzerFactory.scope(), analyzerF, overridePositionIncrementGap);
         }
-        if (analyzers.containsKey(name)) {
-            throw new IllegalStateException("already registered analyzer with name: " + name);
-        }
-        analyzers.put(name, analyzer);
-        // TODO: remove alias support completely when we no longer support pre 5.0 indices
-        final String analyzerAliasKey = "index.analysis.analyzer." + analyzerFactory.name() + ".alias";
-        if (indexSettings.getSettings().get(analyzerAliasKey) != null) {
-            throw new IllegalArgumentException("setting [" + analyzerAliasKey + "] is not supported");
-        }
+        return analyzer;
     }
 
     private void processNormalizerFactory(

server/src/main/java/org/elasticsearch/index/analysis/CustomAnalyzerProvider.java

@@ -20,7 +20,6 @@
 package org.elasticsearch.index.analysis;
 
 import org.elasticsearch.common.settings.Settings;
-import org.elasticsearch.env.Environment;
 import org.elasticsearch.index.IndexSettings;
 import org.elasticsearch.index.mapper.TextFieldMapper;
 
@@ -35,18 +34,16 @@
 public class CustomAnalyzerProvider extends AbstractIndexAnalyzerProvider<CustomAnalyzer> {
 
     private final Settings analyzerSettings;
-    private final Environment environment;
 
     private CustomAnalyzer customAnalyzer;
 
     public CustomAnalyzerProvider(IndexSettings indexSettings,
-                                  String name, Settings settings, Environment environment) {
+                                  String name, Settings settings) {
         super(indexSettings, name, settings);
         this.analyzerSettings = settings;
-        this.environment = environment;
     }
 
-    public void build(final Map<String, TokenizerFactory> tokenizers, final Map<String, CharFilterFactory> charFilters,
+    void build(final Map<String, TokenizerFactory> tokenizers, final Map<String, CharFilterFactory> charFilters,
                       final Map<String, TokenFilterFactory> tokenFilters) {
         String tokenizerName = analyzerSettings.get("tokenizer");
         if (tokenizerName == null) {

server/src/test/java/org/elasticsearch/indices/analysis/AnalysisModuleTests.java

@@ -131,19 +131,6 @@ public void testSimpleConfigurationYaml() throws IOException {
         testSimpleConfiguration(settings);
     }
 
-    public void testAnalyzerAliasNotAllowedPost5x() throws IOException {
-        Settings settings = Settings.builder()
-            .put("index.analysis.analyzer.foobar.type", "standard")
-            .put("index.analysis.analyzer.foobar.alias","foobaz")
-            // analyzer aliases were removed in v5.0.0 alpha6
-            .put(IndexMetaData.SETTING_VERSION_CREATED, VersionUtils.randomVersionBetween(random(), Version.V_6_0_0, null))
-            .put(Environment.PATH_HOME_SETTING.getKey(), createTempDir().toString())
-            .build();
-        AnalysisRegistry registry = getNewRegistry(settings);
-        IllegalArgumentException e = expectThrows(IllegalArgumentException.class, () -> getIndexAnalyzers(registry, settings));
-        assertEquals("setting [index.analysis.analyzer.foobar.alias] is not supported", e.getMessage());
-    }
-
     public void testVersionedAnalyzers() throws Exception {
         String yaml = "/org/elasticsearch/index/analysis/test1.yml";
         Settings settings2 = Settings.builder()