Handle TokenizerFactory TODOs (#32063)

original-brownbear · web-flow · commit ed3b44fb4cd6 · 2018-07-17T14:14:02.000+02:00
* Don't replace Replace TokenizerFactory with Supplier, this approach was rejected in #32063 * Remove unused parameter from constructor
diff --git a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/CharGroupTokenizerFactory.java b/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) {
diff --git a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/ClassicTokenizerFactory.java b/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/ClassicTokenizerFactory.java
@@ -35,7 +35,7 @@ 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);
     }
 
diff --git a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/EdgeNGramTokenizerFactory.java b/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/EdgeNGramTokenizerFactory.java
@@ -36,7 +36,7 @@ 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"));
diff --git a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/KeywordTokenizerFactory.java b/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/KeywordTokenizerFactory.java
@@ -31,7 +31,7 @@ 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);
     }
 
diff --git a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/LetterTokenizerFactory.java b/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/LetterTokenizerFactory.java
@@ -29,7 +29,7 @@
 public class LetterTokenizerFactory extends AbstractTokenizerFactory {
 
     LetterTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
     }
 
     @Override
diff --git a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/LowerCaseTokenizerFactory.java b/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/LowerCaseTokenizerFactory.java
@@ -30,7 +30,7 @@
 public class LowerCaseTokenizerFactory extends AbstractTokenizerFactory implements MultiTermAwareComponent {
 
     LowerCaseTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
     }
 
     @Override
diff --git a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/NGramTokenizerFactory.java b/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);
diff --git a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/PathHierarchyTokenizerFactory.java b/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) {
diff --git a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/PatternTokenizerFactory.java b/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) {
diff --git a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/SimplePatternSplitTokenizerFactory.java b/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/SimplePatternSplitTokenizerFactory.java
@@ -31,7 +31,7 @@ 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", "");
     }
diff --git a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/SimplePatternTokenizerFactory.java b/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/SimplePatternTokenizerFactory.java
@@ -31,7 +31,7 @@ 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", "");
     }
diff --git a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/ThaiTokenizerFactory.java b/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/ThaiTokenizerFactory.java
@@ -32,7 +32,7 @@
 public class ThaiTokenizerFactory extends AbstractTokenizerFactory {
 
     ThaiTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
     }
 
     @Override
diff --git a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/UAX29URLEmailTokenizerFactory.java b/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/UAX29URLEmailTokenizerFactory.java
@@ -32,7 +32,7 @@ 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);
     }
 
diff --git a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/WhitespaceTokenizerFactory.java b/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/WhitespaceTokenizerFactory.java
@@ -34,7 +34,7 @@ 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);
     }
 
diff --git a/plugins/analysis-icu/src/main/java/org/elasticsearch/index/analysis/IcuTokenizerFactory.java b/plugins/analysis-icu/src/main/java/org/elasticsearch/index/analysis/IcuTokenizerFactory.java
@@ -47,7 +47,7 @@ public class IcuTokenizerFactory extends AbstractTokenizerFactory {
     private static final String RULE_FILES = "rule_files";
 
     public IcuTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
         config = getIcuConfig(environment, settings);
     }
 
diff --git a/plugins/analysis-kuromoji/src/main/java/org/elasticsearch/index/analysis/KuromojiTokenizerFactory.java b/plugins/analysis-kuromoji/src/main/java/org/elasticsearch/index/analysis/KuromojiTokenizerFactory.java
@@ -45,7 +45,7 @@ public class KuromojiTokenizerFactory extends AbstractTokenizerFactory {
     private boolean discartPunctuation;
 
     public KuromojiTokenizerFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
         mode = getMode(settings);
         userDictionary = getUserDictionary(env, settings);
         discartPunctuation = settings.getAsBoolean("discard_punctuation", true);
diff --git a/plugins/analysis-nori/src/main/java/org/elasticsearch/index/analysis/NoriTokenizerFactory.java b/plugins/analysis-nori/src/main/java/org/elasticsearch/index/analysis/NoriTokenizerFactory.java
@@ -38,7 +38,7 @@ public class NoriTokenizerFactory extends AbstractTokenizerFactory {
     private final KoreanTokenizer.DecompoundMode decompoundMode;
 
     public NoriTokenizerFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
         decompoundMode = getMode(settings);
         userDictionary = getUserDictionary(env, settings);
     }
diff --git a/plugins/analysis-smartcn/src/main/java/org/elasticsearch/index/analysis/SmartChineseTokenizerTokenizerFactory.java b/plugins/analysis-smartcn/src/main/java/org/elasticsearch/index/analysis/SmartChineseTokenizerTokenizerFactory.java
@@ -28,7 +28,7 @@
 public class SmartChineseTokenizerTokenizerFactory extends AbstractTokenizerFactory {
 
     public SmartChineseTokenizerTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
     }
 
     @Override
diff --git a/server/src/main/java/org/elasticsearch/index/analysis/AbstractTokenizerFactory.java b/server/src/main/java/org/elasticsearch/index/analysis/AbstractTokenizerFactory.java
@@ -27,8 +27,7 @@
 public abstract class AbstractTokenizerFactory extends AbstractIndexComponent implements TokenizerFactory {
     protected final Version version;
 
-    // TODO drop `String ignored` in a followup
-    public AbstractTokenizerFactory(IndexSettings indexSettings, String ignored, Settings settings) {
+    public AbstractTokenizerFactory(IndexSettings indexSettings, Settings settings) {
         super(indexSettings);
         this.version = Analysis.parseAnalysisVersion(this.indexSettings.getSettings(), settings, logger);
     }
diff --git a/server/src/main/java/org/elasticsearch/index/analysis/StandardTokenizerFactory.java b/server/src/main/java/org/elasticsearch/index/analysis/StandardTokenizerFactory.java
@@ -31,7 +31,7 @@ public class StandardTokenizerFactory extends AbstractTokenizerFactory {
     private final int maxTokenLength;
 
     public StandardTokenizerFactory(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);
     }
 
diff --git a/server/src/main/java/org/elasticsearch/index/analysis/TokenizerFactory.java b/server/src/main/java/org/elasticsearch/index/analysis/TokenizerFactory.java
@@ -21,6 +21,6 @@
 
 import org.apache.lucene.analysis.Tokenizer;
 
-public interface TokenizerFactory { // TODO replace with Supplier<Tokenizer>
+public interface TokenizerFactory {
     Tokenizer create();
 }
diff --git a/x-pack/plugin/ml/src/main/java/org/elasticsearch/xpack/ml/job/categorization/MlClassicTokenizerFactory.java b/x-pack/plugin/ml/src/main/java/org/elasticsearch/xpack/ml/job/categorization/MlClassicTokenizerFactory.java
@@ -20,7 +20,7 @@
 public class MlClassicTokenizerFactory extends AbstractTokenizerFactory {
 
     public MlClassicTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(indexSettings, settings);
     }
 
     @Override

Original file line number	Diff line number	Diff line change
`@@ -35,7 +35,7 @@ public class ClassicTokenizerFactory extends AbstractTokenizerFactory {`
`35`	`35`	`private final int maxTokenLength;`
`36`	`36`
`37`	`37`	`ClassicTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {`
`38`		`- super(indexSettings, name, settings);`
	`38`	`+ super(indexSettings, settings);`
`39`	`39`	`maxTokenLength = settings.getAsInt("max_token_length", StandardAnalyzer.DEFAULT_MAX_TOKEN_LENGTH);`
`40`	`40`	`}`
`41`	`41`
Original file line number	Diff line number	Diff line change
`@@ -31,7 +31,7 @@ public class KeywordTokenizerFactory extends AbstractTokenizerFactory {`
`31`	`31`	`private final int bufferSize;`
`32`	`32`
`33`	`33`	`KeywordTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {`
`34`		`- super(indexSettings, name, settings);`
	`34`	`+ super(indexSettings, settings);`
`35`	`35`	`bufferSize = settings.getAsInt("buffer_size", 256);`
`36`	`36`	`}`
`37`	`37`
Original file line number	Diff line number	Diff line change
`@@ -29,7 +29,7 @@`
`29`	`29`	`public class LetterTokenizerFactory extends AbstractTokenizerFactory {`
`30`	`30`
`31`	`31`	`LetterTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {`
`32`		`- super(indexSettings, name, settings);`
	`32`	`+ super(indexSettings, settings);`
`33`	`33`	`}`
`34`	`34`
`35`	`35`	`@Override`
Original file line number	Diff line number	Diff line change
`@@ -30,7 +30,7 @@`
`30`	`30`	`public class LowerCaseTokenizerFactory extends AbstractTokenizerFactory implements MultiTermAwareComponent {`
`31`	`31`
`32`	`32`	`LowerCaseTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {`
`33`		`- super(indexSettings, name, settings);`
	`33`	`+ super(indexSettings, settings);`
`34`	`34`	`}`
`35`	`35`
`36`	`36`	`@Override`
Original file line number	Diff line number	Diff line change
`@@ -85,7 +85,7 @@ static CharMatcher parseTokenChars(List<String> characterClasses) {`
`85`	`85`	`}`
`86`	`86`
`87`	`87`	`NGramTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {`
`88`		`- super(indexSettings, name, settings);`
	`88`	`+ super(indexSettings, settings);`
`89`	`89`	`int maxAllowedNgramDiff = indexSettings.getMaxNgramDiff();`
`90`	`90`	`this.minGram = settings.getAsInt("min_gram", NGramTokenizer.DEFAULT_MIN_NGRAM_SIZE);`
`91`	`91`	`this.maxGram = settings.getAsInt("max_gram", NGramTokenizer.DEFAULT_MAX_NGRAM_SIZE);`
Original file line number	Diff line number	Diff line change
`@@ -31,7 +31,7 @@ public class SimplePatternSplitTokenizerFactory extends AbstractTokenizerFactory`
`31`	`31`	`private final String pattern;`
`32`	`32`
`33`	`33`	`public SimplePatternSplitTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {`
`34`		`- super(indexSettings, name, settings);`
	`34`	`+ super(indexSettings, settings);`
`35`	`35`
`36`	`36`	`pattern = settings.get("pattern", "");`
`37`	`37`	`}`
Original file line number	Diff line number	Diff line change
`@@ -32,7 +32,7 @@`
`32`	`32`	`public class ThaiTokenizerFactory extends AbstractTokenizerFactory {`
`33`	`33`
`34`	`34`	`ThaiTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {`
`35`		`- super(indexSettings, name, settings);`
	`35`	`+ super(indexSettings, settings);`
`36`	`36`	`}`
`37`	`37`
`38`	`38`	`@Override`
Original file line number	Diff line number	Diff line change
`@@ -32,7 +32,7 @@ public class UAX29URLEmailTokenizerFactory extends AbstractTokenizerFactory {`
`32`	`32`	`private final int maxTokenLength;`
`33`	`33`
`34`	`34`	`UAX29URLEmailTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {`
`35`		`- super(indexSettings, name, settings);`
	`35`	`+ super(indexSettings, settings);`
`36`	`36`	`maxTokenLength = settings.getAsInt("max_token_length", StandardAnalyzer.DEFAULT_MAX_TOKEN_LENGTH);`
`37`	`37`	`}`
`38`	`38`
Original file line number	Diff line number	Diff line change
`@@ -34,7 +34,7 @@ public class WhitespaceTokenizerFactory extends AbstractTokenizerFactory {`
`34`	`34`	`private Integer maxTokenLength;`
`35`	`35`
`36`	`36`	`WhitespaceTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {`
`37`		`- super(indexSettings, name, settings);`
	`37`	`+ super(indexSettings, settings);`
`38`	`38`	`maxTokenLength = settings.getAsInt(MAX_TOKEN_LENGTH, StandardAnalyzer.DEFAULT_MAX_TOKEN_LENGTH);`
`39`	`39`	`}`
`40`	`40`
Original file line number	Diff line number	Diff line change
`@@ -47,7 +47,7 @@ public class IcuTokenizerFactory extends AbstractTokenizerFactory {`
`47`	`47`	`private static final String RULE_FILES = "rule_files";`
`48`	`48`
`49`	`49`	`public IcuTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {`
`50`		`- super(indexSettings, name, settings);`
	`50`	`+ super(indexSettings, settings);`
`51`	`51`	`config = getIcuConfig(environment, settings);`
`52`	`52`	`}`
`53`	`53`