Fix #2030 : all new from createComponents()

oracle · Feb 17, 2020 · 9cd38b9 · 9cd38b9
1 parent 5050c4d
commit 9cd38b9
Show file tree

Hide file tree

Showing 41 changed files with 124 additions and 115 deletions.
diff --git a/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/AbstractAnalyzer.java b/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/AbstractAnalyzer.java
@@ -20,14 +20,16 @@
 /*
  * Copyright (c) 2005, 2019, Oracle and/or its affiliates. All rights reserved.
  * Use is subject to license terms.
- * Portions Copyright (c) 2017-2019, Chris Fraire <cfraire@me.com>.
+ * Portions Copyright (c) 2017-2020, Chris Fraire <cfraire@me.com>.
  */
 package org.opengrok.indexer.analysis;
 
 import java.io.IOException;
 import java.io.Reader;
 import java.io.StringReader;
 import java.io.Writer;
+import java.util.function.Supplier;
+
 import org.apache.lucene.analysis.Analyzer;
 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.document.Document;
@@ -40,8 +42,7 @@ public abstract class AbstractAnalyzer extends Analyzer {
 
     public static final Reader DUMMY_READER = new StringReader("");
     protected AnalyzerFactory factory;
-    // you analyzer HAS to override this to get proper symbols in results
-    protected JFlexTokenizer symbolTokenizer;
+    protected Supplier<JFlexTokenizer> symbolTokenizerFactory;
     protected Project project;
     protected Ctags ctags;
     protected boolean scopesEnabled;

diff --git a/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/FileAnalyzer.java b/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/FileAnalyzer.java
@@ -20,13 +20,14 @@
 /*
  * Copyright (c) 2005, 2019, Oracle and/or its affiliates. All rights reserved.
  * Use is subject to license terms.
- * Portions Copyright (c) 2017-2019, Chris Fraire <cfraire@me.com>.
+ * Portions Copyright (c) 2017-2020, Chris Fraire <cfraire@me.com>.
  */
 package org.opengrok.indexer.analysis;
 
 import java.io.IOException;
 import java.io.Writer;
 import java.util.Locale;
+import java.util.function.Supplier;
 import java.util.logging.Level;
 import java.util.logging.Logger;
 import org.apache.lucene.analysis.Analyzer;
@@ -44,7 +45,7 @@
  *
  * An Analyzer for a filetype provides
  * <ol>
- * <li>the file extentions and magic numbers it analyzes</li>
+ * <li>the file extensions and magic numbers it analyzes</li>
  * <li>a lucene document listing the fields it can support</li>
  * <li>TokenStreams for each of the field it said requires tokenizing in 2</li>
  * <li>cross reference in HTML format</li>
@@ -100,27 +101,27 @@ public FileAnalyzer(AnalyzerFactory factory) {
             throw new IllegalArgumentException("`factory' is null");
         }
         this.factory = factory;
-        this.symbolTokenizer = createPlainSymbolTokenizer();
+        this.symbolTokenizerFactory = this::createPlainSymbolTokenizer;
     }
 
     /**
      * Creates a new instance of {@link FileAnalyzer}.
      *
      * @param factory defined instance for the analyzer
-     * @param symbolTokenizer a defined instance relevant for the file
+     * @param symbolTokenizerFactory a defined instance relevant for the file
      */
     protected FileAnalyzer(AnalyzerFactory factory,
-            JFlexTokenizer symbolTokenizer) {
+            Supplier<JFlexTokenizer> symbolTokenizerFactory) {
 
         super(Analyzer.PER_FIELD_REUSE_STRATEGY);
         if (factory == null) {
             throw new IllegalArgumentException("`factory' is null");
         }
-        if (symbolTokenizer == null) {
-            throw new IllegalArgumentException("`symbolTokenizer' is null");
+        if (symbolTokenizerFactory == null) {
+            throw new IllegalArgumentException("symbolTokenizerFactory is null");
         }
         this.factory = factory;
-        this.symbolTokenizer = symbolTokenizer;
+        this.symbolTokenizerFactory = symbolTokenizerFactory;
     }
 
     /**
@@ -185,7 +186,7 @@ protected TokenStreamComponents createComponents(String fieldName) {
                 return new HistoryAnalyzer().createComponents(fieldName);
             //below is set by PlainAnalyzer to workaround #1376 symbols search works like full text search 
             case QueryBuilder.REFS: {
-                return new TokenStreamComponents(symbolTokenizer);
+                return new TokenStreamComponents(symbolTokenizerFactory.get());
             }
             case QueryBuilder.DEFS:
                 return new TokenStreamComponents(createPlainSymbolTokenizer());

diff --git a/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/TextAnalyzer.java b/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/TextAnalyzer.java
@@ -19,14 +19,16 @@
 
 /*
  * Copyright (c) 2005, 2018, Oracle and/or its affiliates. All rights reserved.
- * Portions Copyright (c) 2017-2018, Chris Fraire <cfraire@me.com>.
+ * Portions Copyright (c) 2017-2018, 2020, Chris Fraire <cfraire@me.com>.
  */
 package org.opengrok.indexer.analysis;
 
 import java.io.IOException;
 import java.io.InputStream;
 import java.io.Reader;
 import java.nio.charset.StandardCharsets;
+import java.util.function.Supplier;
+
 import org.opengrok.indexer.util.IOUtils;
 
 public abstract class TextAnalyzer extends FileAnalyzer {
@@ -42,11 +44,11 @@ protected TextAnalyzer(AnalyzerFactory factory) {
     /**
      * Creates a new instance of {@link TextAnalyzer}.
      * @param factory defined instance for the analyzer
-     * @param symbolTokenizer defined instance for the analyzer
+     * @param symbolTokenizerFactory defined instance for the analyzer
      */
     protected TextAnalyzer(AnalyzerFactory factory,
-        JFlexTokenizer symbolTokenizer) {
-        super(factory, symbolTokenizer);
+            Supplier<JFlexTokenizer> symbolTokenizerFactory) {
+        super(factory, symbolTokenizerFactory);
     }
 
     /**

diff --git a/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/ada/AdaAnalyzer.java b/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/ada/AdaAnalyzer.java
@@ -19,7 +19,7 @@
 
 /*
  * Copyright (c) 2010, 2018, Oracle and/or its affiliates. All rights reserved.
- * Portions Copyright (c) 2017-2019, Chris Fraire <cfraire@me.com>.
+ * Portions Copyright (c) 2017-2020, Chris Fraire <cfraire@me.com>.
  */
 package org.opengrok.indexer.analysis.ada;
 
@@ -43,7 +43,7 @@ public class AdaAnalyzer extends AbstractSourceCodeAnalyzer {
      * @param factory defined instance for the analyzer
      */
     protected AdaAnalyzer(AnalyzerFactory factory) {
-        super(factory, new JFlexTokenizer(new AdaSymbolTokenizer(
+        super(factory, () -> new JFlexTokenizer(new AdaSymbolTokenizer(
                 AbstractAnalyzer.DUMMY_READER)));
     }
 

diff --git a/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/asm/AsmAnalyzer.java b/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/asm/AsmAnalyzer.java
@@ -18,7 +18,7 @@
  */
 
 /*
- * Copyright (c) 2017-2019, Chris Fraire <cfraire@me.com>.
+ * Copyright (c) 2017-2020, Chris Fraire <cfraire@me.com>.
  */
 
 package org.opengrok.indexer.analysis.asm;
@@ -41,7 +41,8 @@ public class AsmAnalyzer extends AbstractSourceCodeAnalyzer {
      * @param factory instance
      */
     protected AsmAnalyzer(AnalyzerFactory factory) {
-        super(factory, new JFlexTokenizer(new AsmSymbolTokenizer(AbstractAnalyzer.DUMMY_READER)));
+        super(factory, () -> new JFlexTokenizer(new AsmSymbolTokenizer(
+                AbstractAnalyzer.DUMMY_READER)));
     }
 
     /**

diff --git a/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/c/CAnalyzer.java b/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/c/CAnalyzer.java
@@ -19,7 +19,7 @@
 
 /*
  * Copyright (c) 2005, 2018, Oracle and/or its affiliates. All rights reserved.
- * Portions Copyright (c) 2017-2019, Chris Fraire <cfraire@me.com>.
+ * Portions Copyright (c) 2017-2020, Chris Fraire <cfraire@me.com>.
  */
 package org.opengrok.indexer.analysis.c;
 
@@ -44,7 +44,7 @@ public class CAnalyzer extends AbstractSourceCodeAnalyzer {
      * @param factory defined instance for the analyzer
      */
     protected CAnalyzer(AnalyzerFactory factory) {
-        super(factory, new JFlexTokenizer(new CSymbolTokenizer(
+        super(factory, () -> new JFlexTokenizer(new CSymbolTokenizer(
                 AbstractAnalyzer.DUMMY_READER)));
     }
 

diff --git a/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/c/CxxAnalyzer.java b/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/c/CxxAnalyzer.java
@@ -19,7 +19,7 @@
 
 /*
  * Copyright (c) 2008, 2018, Oracle and/or its affiliates. All rights reserved.
- * Portions Copyright (c) 2017-2019, Chris Fraire <cfraire@me.com>.
+ * Portions Copyright (c) 2017-2020, Chris Fraire <cfraire@me.com>.
  */
 package org.opengrok.indexer.analysis.c;
 
@@ -42,7 +42,7 @@ public class CxxAnalyzer extends AbstractSourceCodeAnalyzer {
      * @param factory defined instance for the analyzer
      */
     protected CxxAnalyzer(AnalyzerFactory factory) {
-        super(factory, new JFlexTokenizer(new CxxSymbolTokenizer(
+        super(factory, () -> new JFlexTokenizer(new CxxSymbolTokenizer(
                 AbstractAnalyzer.DUMMY_READER)));
     }
 

diff --git a/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/clojure/ClojureAnalyzer.java b/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/clojure/ClojureAnalyzer.java
@@ -19,7 +19,7 @@
 
 /*
  * Copyright (c) 2015, 2018, Oracle and/or its affiliates. All rights reserved.
- * Portions Copyright (c) 2017-2019, Chris Fraire <cfraire@me.com>.
+ * Portions Copyright (c) 2017-2020, Chris Fraire <cfraire@me.com>.
  */
 package org.opengrok.indexer.analysis.clojure;
 
@@ -33,7 +33,7 @@
 public class ClojureAnalyzer extends AbstractSourceCodeAnalyzer {
 
     protected ClojureAnalyzer(AnalyzerFactory factory) {
-        super(factory, new JFlexTokenizer(new ClojureSymbolTokenizer(
+        super(factory, () -> new JFlexTokenizer(new ClojureSymbolTokenizer(
                 AbstractAnalyzer.DUMMY_READER)));
     }
 

diff --git a/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/csharp/CSharpAnalyzer.java b/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/csharp/CSharpAnalyzer.java
@@ -19,7 +19,7 @@
 
 /*
  * Copyright (c) 2008, 2018, Oracle and/or its affiliates. All rights reserved.
- * Portions Copyright (c) 2017-2019, Chris Fraire <cfraire@me.com>.
+ * Portions Copyright (c) 2017-2020, Chris Fraire <cfraire@me.com>.
  */
 package org.opengrok.indexer.analysis.csharp;
 
@@ -37,7 +37,7 @@
 public class CSharpAnalyzer extends AbstractSourceCodeAnalyzer {
 
     protected CSharpAnalyzer(AnalyzerFactory factory) {
-        super(factory, new JFlexTokenizer(new CSharpSymbolTokenizer(
+        super(factory, () -> new JFlexTokenizer(new CSharpSymbolTokenizer(
                 AbstractAnalyzer.DUMMY_READER)));
     }
 

diff --git a/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/document/MandocAnalyzer.java b/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/document/MandocAnalyzer.java
@@ -19,7 +19,7 @@
 
 /*
  * Copyright (c) 2005, 2018, Oracle and/or its affiliates. All rights reserved.
- * Portions Copyright (c) 2017-2019, Chris Fraire <cfraire@me.com>.
+ * Portions Copyright (c) 2017-2020, Chris Fraire <cfraire@me.com>.
  */
 package org.opengrok.indexer.analysis.document;
 
@@ -47,7 +47,7 @@ public class MandocAnalyzer extends TextAnalyzer {
      * @param factory defined instance for the analyzer
      */
     protected MandocAnalyzer(AnalyzerFactory factory) {
-        super(factory, new JFlexTokenizer(new TroffFullTokenizer(
+        super(factory, () -> new JFlexTokenizer(new TroffFullTokenizer(
                 AbstractAnalyzer.DUMMY_READER)));
     }
 
@@ -77,9 +77,9 @@ public void analyze(Document doc, StreamSource src, Writer xrefOut)
 
         // this is to explicitly use appropriate analyzers tokenstream to
         // workaround #1376 symbols search works like full text search
-        this.symbolTokenizer.setReader(getReader(src.getStream()));
-        OGKTextField full = new OGKTextField(QueryBuilder.FULL,
-            symbolTokenizer);
+        JFlexTokenizer symbolTokenizer = symbolTokenizerFactory.get();
+        symbolTokenizer.setReader(getReader(src.getStream()));
+        OGKTextField full = new OGKTextField(QueryBuilder.FULL, symbolTokenizer);
         doc.add(full);
 
         if (xrefOut != null) {

diff --git a/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/document/TroffAnalyzer.java b/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/document/TroffAnalyzer.java
@@ -19,7 +19,7 @@
 
 /*
  * Copyright (c) 2005, 2018, Oracle and/or its affiliates. All rights reserved.
- * Portions Copyright (c) 2017-2019, Chris Fraire <cfraire@me.com>.
+ * Portions Copyright (c) 2017-2020, Chris Fraire <cfraire@me.com>.
  */
 package org.opengrok.indexer.analysis.document;
 
@@ -50,7 +50,7 @@ public class TroffAnalyzer extends TextAnalyzer {
      * @param factory defined instance for the analyzer
      */
     protected TroffAnalyzer(AnalyzerFactory factory) {
-        super(factory, new JFlexTokenizer(new TroffFullTokenizer(
+        super(factory, () -> new JFlexTokenizer(new TroffFullTokenizer(
                 AbstractAnalyzer.DUMMY_READER)));
     }
 
@@ -75,10 +75,10 @@ protected int getSpecializedVersionNo() {
 
     @Override
     public void analyze(Document doc, StreamSource src, Writer xrefOut) throws IOException {        
-        //this is to explicitly use appropriate analyzers tokenstream to workaround #1376 symbols search works like full text search 
-        this.symbolTokenizer.setReader(getReader(src.getStream()));
-        OGKTextField full = new OGKTextField(QueryBuilder.FULL,
-            symbolTokenizer);
+        //this is to explicitly use appropriate analyzers tokenstream to workaround #1376 symbols search works like full text search
+        JFlexTokenizer symbolTokenizer = symbolTokenizerFactory.get();
+        symbolTokenizer.setReader(getReader(src.getStream()));
+        OGKTextField full = new OGKTextField(QueryBuilder.FULL, symbolTokenizer);
         doc.add(full);
 
         if (xrefOut != null) {

diff --git a/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/eiffel/EiffelAnalyzer.java b/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/eiffel/EiffelAnalyzer.java
@@ -18,7 +18,7 @@
  */
 
 /*
- * Copyright (c) 2017-2019, Chris Fraire <cfraire@me.com>.
+ * Copyright (c) 2017-2020, Chris Fraire <cfraire@me.com>.
  */
 
 package org.opengrok.indexer.analysis.eiffel;
@@ -40,7 +40,7 @@ public class EiffelAnalyzer extends AbstractSourceCodeAnalyzer {
      * @param factory instance
      */
     protected EiffelAnalyzer(AnalyzerFactory factory) {
-        super(factory, new JFlexTokenizer(new EiffelSymbolTokenizer(
+        super(factory, () -> new JFlexTokenizer(new EiffelSymbolTokenizer(
                 AbstractAnalyzer.DUMMY_READER)));
     }
 

diff --git a/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/erlang/ErlangAnalyzer.java b/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/erlang/ErlangAnalyzer.java
@@ -19,7 +19,7 @@
 
 /*
  * Copyright (c) 2015, 2018 Oracle and/or its affiliates. All rights reserved.
- * Portions Copyright (c) 2017-2019, Chris Fraire <cfraire@me.com>.
+ * Portions Copyright (c) 2017-2020, Chris Fraire <cfraire@me.com>.
  */
 
 package org.opengrok.indexer.analysis.erlang;
@@ -38,7 +38,7 @@ public class ErlangAnalyzer extends AbstractSourceCodeAnalyzer {
      * @param factory defined instance for the analyzer
      */
     protected ErlangAnalyzer(AnalyzerFactory factory) {
-        super(factory, new JFlexTokenizer(new ErlangSymbolTokenizer(
+        super(factory, () -> new JFlexTokenizer(new ErlangSymbolTokenizer(
                 AbstractAnalyzer.DUMMY_READER)));
     }
 

diff --git a/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/fortran/FortranAnalyzer.java b/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/fortran/FortranAnalyzer.java
@@ -19,7 +19,7 @@
 
 /*
  * Copyright (c) 2008, 2018, Oracle and/or its affiliates. All rights reserved.
- * Portions Copyright (c) 2017-2019, Chris Fraire <cfraire@me.com>.
+ * Portions Copyright (c) 2017-2020, Chris Fraire <cfraire@me.com>.
  */
 package org.opengrok.indexer.analysis.fortran;
 
@@ -37,7 +37,7 @@
 public class FortranAnalyzer extends AbstractSourceCodeAnalyzer {
 
     FortranAnalyzer(FortranAnalyzerFactory factory) {
-        super(factory, new JFlexTokenizer(new FortranSymbolTokenizer(
+        super(factory, () -> new JFlexTokenizer(new FortranSymbolTokenizer(
                 AbstractAnalyzer.DUMMY_READER)));
     }
 

diff --git a/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/golang/GolangAnalyzer.java b/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/golang/GolangAnalyzer.java
@@ -19,7 +19,7 @@
 
 /*
  * Copyright (c) 2015, 2018 Oracle and/or its affiliates. All rights reserved.
- * Portions Copyright (c) 2017-2019, Chris Fraire <cfraire@me.com>.
+ * Portions Copyright (c) 2017-2020, Chris Fraire <cfraire@me.com>.
  */
 
 package org.opengrok.indexer.analysis.golang;
@@ -42,7 +42,7 @@ public class GolangAnalyzer extends AbstractSourceCodeAnalyzer {
      * @param factory defined instance for the analyzer
      */
     protected GolangAnalyzer(AnalyzerFactory factory) {
-        super(factory, new JFlexTokenizer(new GolangSymbolTokenizer(
+        super(factory, () -> new JFlexTokenizer(new GolangSymbolTokenizer(
                 AbstractAnalyzer.DUMMY_READER)));
     }
 

diff --git a/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/haskell/HaskellAnalyzer.java b/opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/haskell/HaskellAnalyzer.java
@@ -19,7 +19,7 @@
 
 /*
  * Copyright (c) 2015, 2018, Oracle and/or its affiliates. All rights reserved.
- * Portions Copyright (c) 2017-2019, Chris Fraire <cfraire@me.com>.
+ * Portions Copyright (c) 2017-2020, Chris Fraire <cfraire@me.com>.
  */
 
 package org.opengrok.indexer.analysis.haskell;
@@ -41,7 +41,7 @@ public class HaskellAnalyzer extends AbstractSourceCodeAnalyzer {
      * @param factory defined instance for the analyzer
      */
     protected HaskellAnalyzer(AnalyzerFactory factory) {
-        super(factory, new JFlexTokenizer(new HaskellSymbolTokenizer(
+        super(factory, () -> new JFlexTokenizer(new HaskellSymbolTokenizer(
                 AbstractAnalyzer.DUMMY_READER)));
     }