Replace TokenizerFactory with Supplier

modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/CharGroupTokenizerFactory.java

@@ -39,7 +39,7 @@ public class CharGroupTokenizerFactory extends AbstractTokenizerFactory{
     private boolean tokenizeOnSymbol = false;
 
     public CharGroupTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
 
         for (final String c : settings.getAsList("tokenize_on_chars")) {
             if (c == null || c.length() == 0) {
@@ -109,7 +109,7 @@ private char parseEscapedChar(final String s) {
     }
 
     @Override
-    public Tokenizer create() {
+    public Tokenizer get() {
         return new CharTokenizer() {
             @Override
             protected boolean isTokenChar(int c) {

modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/ClassicTokenizerFactory.java

@@ -35,12 +35,12 @@ public class ClassicTokenizerFactory extends AbstractTokenizerFactory {
     private final int maxTokenLength;
 
     ClassicTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
         maxTokenLength = settings.getAsInt("max_token_length", StandardAnalyzer.DEFAULT_MAX_TOKEN_LENGTH);
     }
 
     @Override
-    public Tokenizer create() {
+    public Tokenizer get() {
         ClassicTokenizer tokenizer = new ClassicTokenizer();
         tokenizer.setMaxTokenLength(maxTokenLength);
         return tokenizer;

modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/CommonAnalysisPlugin.java

@@ -24,6 +24,7 @@
 import org.apache.lucene.analysis.LowerCaseFilter;
 import org.apache.lucene.analysis.StopFilter;
 import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.Tokenizer;
 import org.apache.lucene.analysis.ar.ArabicAnalyzer;
 import org.apache.lucene.analysis.ar.ArabicNormalizationFilter;
 import org.apache.lucene.analysis.ar.ArabicStemFilter;
@@ -122,7 +123,6 @@
 import org.elasticsearch.index.analysis.PreConfiguredTokenizer;
 import org.elasticsearch.index.analysis.SoraniNormalizationFilterFactory;
 import org.elasticsearch.index.analysis.TokenFilterFactory;
-import org.elasticsearch.index.analysis.TokenizerFactory;
 import org.elasticsearch.indices.analysis.AnalysisModule.AnalysisProvider;
 import org.elasticsearch.indices.analysis.PreBuiltCacheFactory.CachingStrategy;
 import org.elasticsearch.plugins.AnalysisPlugin;
@@ -134,6 +134,7 @@
 import java.util.List;
 import java.util.Map;
 import java.util.TreeMap;
+import java.util.function.Supplier;
 
 import static org.elasticsearch.plugins.AnalysisPlugin.requiresAnalysisSettings;
 
@@ -262,8 +263,8 @@ public Map<String, AnalysisProvider<CharFilterFactory>> getCharFilters() {
     }
 
     @Override
-    public Map<String, AnalysisProvider<TokenizerFactory>> getTokenizers() {
-        Map<String, AnalysisProvider<TokenizerFactory>> tokenizers = new TreeMap<>();
+    public Map<String, AnalysisProvider<Supplier<Tokenizer>>> getTokenizers() {
+        Map<String, AnalysisProvider<Supplier<Tokenizer>>> tokenizers = new TreeMap<>();
         tokenizers.put("simple_pattern", SimplePatternTokenizerFactory::new);
         tokenizers.put("simple_pattern_split", SimplePatternSplitTokenizerFactory::new);
         tokenizers.put("thai", ThaiTokenizerFactory::new);

modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/EdgeNGramTokenizerFactory.java

@@ -36,14 +36,14 @@ public class EdgeNGramTokenizerFactory extends AbstractTokenizerFactory {
     private final CharMatcher matcher;
 
     EdgeNGramTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
         this.minGram = settings.getAsInt("min_gram", NGramTokenizer.DEFAULT_MIN_NGRAM_SIZE);
         this.maxGram = settings.getAsInt("max_gram", NGramTokenizer.DEFAULT_MAX_NGRAM_SIZE);
         this.matcher = parseTokenChars(settings.getAsList("token_chars"));
     }
 
     @Override
-    public Tokenizer create() {
+    public Tokenizer get() {
         if (matcher == null) {
             return new EdgeNGramTokenizer(minGram, maxGram);
         } else {

modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/KeywordTokenizerFactory.java

@@ -31,12 +31,12 @@ public class KeywordTokenizerFactory extends AbstractTokenizerFactory {
     private final int bufferSize;
 
     KeywordTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
         bufferSize = settings.getAsInt("buffer_size", 256);
     }
 
     @Override
-    public Tokenizer create() {
+    public Tokenizer get() {
         return new KeywordTokenizer(bufferSize);
     }
 }

modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/LetterTokenizerFactory.java

@@ -29,11 +29,11 @@
 public class LetterTokenizerFactory extends AbstractTokenizerFactory {
 
     LetterTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
     }
 
     @Override
-    public Tokenizer create() {
+    public Tokenizer get() {
         return new LetterTokenizer();
     }
 }

modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/LowerCaseTokenizerFactory.java

@@ -30,11 +30,11 @@
 public class LowerCaseTokenizerFactory extends AbstractTokenizerFactory implements MultiTermAwareComponent {
 
     LowerCaseTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
     }
 
     @Override
-    public Tokenizer create() {
+    public Tokenizer get() {
         return new LowerCaseTokenizer();
     }
 

modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/NGramTokenizerFactory.java

@@ -85,7 +85,7 @@ static CharMatcher parseTokenChars(List<String> characterClasses) {
     }
 
     NGramTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
         int maxAllowedNgramDiff = indexSettings.getMaxNgramDiff();
         this.minGram = settings.getAsInt("min_gram", NGramTokenizer.DEFAULT_MIN_NGRAM_SIZE);
         this.maxGram = settings.getAsInt("max_gram", NGramTokenizer.DEFAULT_MAX_NGRAM_SIZE);
@@ -105,7 +105,7 @@ static CharMatcher parseTokenChars(List<String> characterClasses) {
     }
 
     @Override
-    public Tokenizer create() {
+    public Tokenizer get() {
         if (matcher == null) {
             return new NGramTokenizer(minGram, maxGram);
         } else {

modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/PathHierarchyTokenizerFactory.java

@@ -37,7 +37,7 @@ public class PathHierarchyTokenizerFactory extends AbstractTokenizerFactory {
     private final boolean reverse;
 
     PathHierarchyTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
         bufferSize = settings.getAsInt("buffer_size", 1024);
         String delimiter = settings.get("delimiter");
         if (delimiter == null) {
@@ -61,7 +61,7 @@ public class PathHierarchyTokenizerFactory extends AbstractTokenizerFactory {
     }
 
     @Override
-    public Tokenizer create() {
+    public Tokenizer get() {
         if (reverse) {
             return new ReversePathHierarchyTokenizer(bufferSize, delimiter, replacement, skip);
         }

modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/PatternTokenizerFactory.java

@@ -35,7 +35,7 @@ public class PatternTokenizerFactory extends AbstractTokenizerFactory {
     private final int group;
 
     PatternTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
 
         String sPattern = settings.get("pattern", "\\W+" /*PatternAnalyzer.NON_WORD_PATTERN*/);
         if (sPattern == null) {
@@ -47,7 +47,7 @@ public class PatternTokenizerFactory extends AbstractTokenizerFactory {
     }
 
     @Override
-    public Tokenizer create() {
+    public Tokenizer get() {
         return new PatternTokenizer(pattern, group);
     }
 }

modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/SimplePatternSplitTokenizerFactory.java

@@ -31,13 +31,13 @@ public class SimplePatternSplitTokenizerFactory extends AbstractTokenizerFactory
     private final String pattern;
 
     public SimplePatternSplitTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
 
         pattern = settings.get("pattern", "");
     }
 
     @Override
-    public Tokenizer create() {
+    public Tokenizer get() {
         return new SimplePatternSplitTokenizer(pattern);
     }
 }

modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/SimplePatternTokenizerFactory.java

@@ -31,13 +31,13 @@ public class SimplePatternTokenizerFactory extends AbstractTokenizerFactory {
     private final String pattern;
 
     public SimplePatternTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
 
         pattern = settings.get("pattern", "");
     }
 
     @Override
-    public Tokenizer create() {
+    public Tokenizer get() {
         return new SimplePatternTokenizer(pattern);
     }
 }

modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/ThaiTokenizerFactory.java

@@ -32,11 +32,11 @@
 public class ThaiTokenizerFactory extends AbstractTokenizerFactory {
 
     ThaiTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
     }
 
     @Override
-    public Tokenizer create() {
+    public Tokenizer get() {
         return new ThaiTokenizer();
     }
 }

modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/UAX29URLEmailTokenizerFactory.java

@@ -32,12 +32,12 @@ public class UAX29URLEmailTokenizerFactory extends AbstractTokenizerFactory {
     private final int maxTokenLength;
 
     UAX29URLEmailTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
         maxTokenLength = settings.getAsInt("max_token_length", StandardAnalyzer.DEFAULT_MAX_TOKEN_LENGTH);
     }
 
     @Override
-    public Tokenizer create() {
+    public Tokenizer get() {
         UAX29URLEmailTokenizer tokenizer = new UAX29URLEmailTokenizer();
         tokenizer.setMaxTokenLength(maxTokenLength);
         return tokenizer;

modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/WhitespaceTokenizerFactory.java

@@ -34,12 +34,12 @@ public class WhitespaceTokenizerFactory extends AbstractTokenizerFactory {
     private Integer maxTokenLength;
 
     WhitespaceTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
         maxTokenLength = settings.getAsInt(MAX_TOKEN_LENGTH, StandardAnalyzer.DEFAULT_MAX_TOKEN_LENGTH);
     }
 
     @Override
-    public Tokenizer create() {
+    public Tokenizer get() {
         return new WhitespaceTokenizer(TokenStream.DEFAULT_TOKEN_ATTRIBUTE_FACTORY, maxTokenLength);
     }
 }

modules/analysis-common/src/test/java/org/elasticsearch/analysis/common/CharGroupTokenizerFactoryTests.java

@@ -43,7 +43,7 @@ public void testParseTokenChars() {
                 new String[] { "commas" },
                 new String[] { "a", "b", "c", "\\$" })) {
             final Settings settings = newAnalysisSettingsBuilder().putList("tokenize_on_chars", conf).build();
-            expectThrows(RuntimeException.class, () -> new CharGroupTokenizerFactory(indexProperties, null, name, settings).create());
+            expectThrows(RuntimeException.class, () -> new CharGroupTokenizerFactory(indexProperties, null, name, settings).get());
         }
 
         for (String[] conf : Arrays.asList(
@@ -56,7 +56,7 @@ public void testParseTokenChars() {
                 new String[] { "\\r" },
                 new String[] { "f", "o", "o", "symbol" })) {
             final Settings settings = newAnalysisSettingsBuilder().putList("tokenize_on_chars", Arrays.asList(conf)).build();
-            new CharGroupTokenizerFactory(indexProperties, null, name, settings).create();
+            new CharGroupTokenizerFactory(indexProperties, null, name, settings).get();
             // no exception
         }
     }
@@ -67,7 +67,7 @@ public void testTokenization() throws IOException {
         final Settings indexSettings = newAnalysisSettingsBuilder().build();
         final Settings settings = newAnalysisSettingsBuilder().putList("tokenize_on_chars", "whitespace", ":", "\\u0024").build();
         Tokenizer tokenizer = new CharGroupTokenizerFactory(IndexSettingsModule.newIndexSettings(index, indexSettings),
-                null, name, settings).create();
+                null, name, settings).get();
         tokenizer.setReader(new StringReader("foo bar $34 test:test2"));
         assertTokenStreamContents(tokenizer, new String[] {"foo", "bar", "34", "test", "test2"});
     }

modules/analysis-common/src/test/java/org/elasticsearch/analysis/common/NGramTokenizerFactoryTests.java

@@ -51,7 +51,7 @@ public void testParseTokenChars() {
             final Settings settings = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 3)
                 .put("token_chars", tokenChars).build();
             try {
-                new NGramTokenizerFactory(indexProperties, null, name, settings).create();
+                new NGramTokenizerFactory(indexProperties, null, name, settings).get();
                 fail();
             } catch (IllegalArgumentException expected) {
                 // OK
@@ -62,7 +62,7 @@ public void testParseTokenChars() {
                 .put("token_chars", tokenChars).build();
             indexProperties = IndexSettingsModule.newIndexSettings(index, indexSettings);
 
-            new NGramTokenizerFactory(indexProperties, null, name, settings).create();
+            new NGramTokenizerFactory(indexProperties, null, name, settings).get();
             // no exception
         }
     }
@@ -75,7 +75,7 @@ public void testNoTokenChars() throws IOException {
         final Settings settings = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 4)
             .putList("token_chars", new String[0]).build();
         Tokenizer tokenizer = new NGramTokenizerFactory(IndexSettingsModule.newIndexSettings(index, indexSettings), null, name, settings)
-            .create();
+            .get();
         tokenizer.setReader(new StringReader("1.34"));
         assertTokenStreamContents(tokenizer, new String[] {"1.", "1.3", "1.34", ".3", ".34", "34"});
     }
@@ -88,13 +88,13 @@ public void testPreTokenization() throws IOException {
         Settings settings = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 3)
             .put("token_chars", "letter,digit").build();
         Tokenizer tokenizer = new NGramTokenizerFactory(IndexSettingsModule.newIndexSettings(index, indexSettings), null, name, settings)
-            .create();
+            .get();
         tokenizer.setReader(new StringReader("Åbc déf g\uD801\uDC00f "));
         assertTokenStreamContents(tokenizer,
                 new String[] {"Åb", "Åbc", "bc", "dé", "déf", "éf", "g\uD801\uDC00", "g\uD801\uDC00f", "\uD801\uDC00f"});
         settings = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 3)
             .put("token_chars", "letter,digit,punctuation,whitespace,symbol").build();
-        tokenizer = new NGramTokenizerFactory(IndexSettingsModule.newIndexSettings(index, indexSettings), null, name, settings).create();
+        tokenizer = new NGramTokenizerFactory(IndexSettingsModule.newIndexSettings(index, indexSettings), null, name, settings).get();
         tokenizer.setReader(new StringReader(" a!$ 9"));
         assertTokenStreamContents(tokenizer,
             new String[] {" a", " a!", "a!", "a!$", "!$", "!$ ", "$ ", "$ 9", " 9"});
@@ -107,14 +107,14 @@ public void testPreTokenizationEdge() throws IOException {
         final Settings indexSettings = newAnalysisSettingsBuilder().build();
         Settings settings = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 3).put("token_chars", "letter,digit").build();
         Tokenizer tokenizer =
-            new EdgeNGramTokenizerFactory(IndexSettingsModule.newIndexSettings(index, indexSettings), null, name, settings).create();
+            new EdgeNGramTokenizerFactory(IndexSettingsModule.newIndexSettings(index, indexSettings), null, name, settings).get();
         tokenizer.setReader(new StringReader("Åbc déf g\uD801\uDC00f "));
         assertTokenStreamContents(tokenizer,
                 new String[] {"Åb", "Åbc", "dé", "déf", "g\uD801\uDC00", "g\uD801\uDC00f"});
         settings = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 3)
             .put("token_chars", "letter,digit,punctuation,whitespace,symbol").build();
         tokenizer = new EdgeNGramTokenizerFactory(IndexSettingsModule.newIndexSettings(index, indexSettings), null, name, settings)
-            .create();
+            .get();
         tokenizer.setReader(new StringReader(" a!$ 9"));
         assertTokenStreamContents(tokenizer,
                 new String[] {" a", " a!"});
@@ -163,7 +163,7 @@ public void testMaxNGramDiffException() throws Exception{
 
         final Settings settings = newAnalysisSettingsBuilder().put("min_gram", min_gram).put("max_gram", max_gram).build();
         IllegalArgumentException ex = expectThrows(IllegalArgumentException.class, () ->
-            new NGramTokenizerFactory(indexProperties, null, name, settings).create());
+            new NGramTokenizerFactory(indexProperties, null, name, settings).get());
         assertEquals(
             "The difference between max_gram and min_gram in NGram Tokenizer must be less than or equal to: ["
                 + maxAllowedNgramDiff + "] but was [" + ngramDiff + "]. This limit can be set by changing the ["