Merge pull request #1122 from jplag/feature/reafactorLangaugeModules

Changed all language class names and added READMEs where they where missing

README.md

@@ -12,6 +12,7 @@
 [![Report Viewer](https://img.shields.io/badge/report%20viewer-online-b80025)](https://jplag.github.io/JPlag/)
 [![Java Version](https://img.shields.io/badge/java-SE%2017-yellowgreen)](#download-and-installation)
 
+
 JPlag is a system that finds similarities among multiple sets of source code files. This way it can detect software plagiarism and collusion in software development. JPlag currently supports various programming languages, EMF metamodels, and natural language text.
 
 ## Supported Languages
@@ -167,7 +168,7 @@ The new API makes it easy to integrate JPlag's plagiarism detection into externa
 <!-- To assure that the code example is always correct, it must be kept in sync
 with [`ReadmeCodeExampleTest#testReadmeCodeExample`](core/src/test/java/de/jplag/special/ReadmeCodeExampleTest.java). -->
 ```java
-Language language = new de.jplag.java.Language();
+JavaLanguage language = new JavaLanguage();
 language.getOptions(); //Use the object returned by this to set language options(same as language specific arguments above).
 Set<File> submissionDirectories = Set.of(new File("/path/to/rootDir"));
 File baseCode = new File("/path/to/baseCode");

cli/src/main/java/de/jplag/cli/CliOptions.java

@@ -6,6 +6,7 @@
 import de.jplag.clustering.ClusteringAlgorithm;
 import de.jplag.clustering.ClusteringOptions;
 import de.jplag.clustering.algorithm.InterClusterSimilarity;
+import de.jplag.java.JavaLanguage;
 import de.jplag.options.JPlagOptions;
 import de.jplag.options.SimilarityMetric;
 
@@ -16,7 +17,7 @@
 
 @CommandLine.Command(name = "jplag", description = "", usageHelpAutoWidth = true, abbreviateSynopsis = true)
 public class CliOptions implements Runnable {
-    public static final Language defaultLanguage = new de.jplag.java.Language();
+    public static final Language defaultLanguage = new JavaLanguage();
 
     @Parameters(paramLabel = "root-dirs", description = "Root-directory with submissions to check for plagiarism%n", split = ",")
     public File[] rootDirectory = new File[0];

core/src/test/java/de/jplag/TestBase.java

@@ -9,6 +9,7 @@
 import java.util.stream.Collectors;
 
 import de.jplag.exceptions.ExitException;
+import de.jplag.java.JavaLanguage;
 import de.jplag.options.JPlagOptions;
 
 /**
@@ -104,7 +105,7 @@ protected JPlagOptions getOptions(List<String> newPaths, Function<JPlagOptions,
     protected JPlagOptions getOptions(List<String> newPaths, List<String> oldPaths, Function<JPlagOptions, JPlagOptions> customization) {
         var newFiles = newPaths.stream().map(File::new).collect(Collectors.toSet());
         var oldFiles = oldPaths.stream().map(File::new).collect(Collectors.toSet());
-        JPlagOptions options = new JPlagOptions(new de.jplag.java.Language(), newFiles, oldFiles);
+        JPlagOptions options = new JPlagOptions(new JavaLanguage(), newFiles, oldFiles);
         return customization.apply(options);
     }
 

core/src/test/java/de/jplag/special/ReadmeCodeExampleTest.java

@@ -10,6 +10,7 @@
 import de.jplag.JPlagResult;
 import de.jplag.Language;
 import de.jplag.exceptions.ExitException;
+import de.jplag.java.JavaLanguage;
 import de.jplag.options.JPlagOptions;
 import de.jplag.reporting.reportobject.ReportObjectFactory;
 
@@ -25,7 +26,7 @@ class ReadmeCodeExampleTest {
      */
     @Test
     void testReadmeCodeExample() {
-        Language language = new de.jplag.java.Language();
+        Language language = new JavaLanguage();
         Set<File> submissionDirectories = Set.of(new File("/path/to/rootDir"));
         File baseCode = new File("/path/to/baseCode");
         JPlagOptions options = new JPlagOptions(language, submissionDirectories, Set.of()).withBaseCodeSubmissionDirectory(baseCode);

docs/1.-How-to-Use-JPlag.md

@@ -110,7 +110,7 @@ The new API makes it easy to integrate JPlag's plagiarism detection into externa
 **Example:**
 
 ```java
-Language language = new de.jplag.java.Language();
+JavaLanguage language = new JavaLanguage();
 language.getOptions(); //Use this to set language specific options, same as language specific arguments above.
 Set<File> submissionDirectories = Set.of(new File("/path/to/rootDir"));
 File baseCode = new File("/path/to/baseCode");

languages/csharp/README.md

@@ -0,0 +1,68 @@
+# CSharp langauge module
+
+Extracts token from CSharp source using the ANTRL Grammar from the official [ANTLR repository](https://github.com/antlr/grammars-v4/tree/master/csharp)
+
+## Tokens
+
+- INVOCATION
+- OBJECT_CREATION
+- ARRAY_CREATION
+- ASSIGNMENT
+- FIELD
+- CONSTANT
+- LOCAL_VARIABLE
+- IF
+- SWITCH_BEGIN
+- SWITCH_END
+- CASE
+- DO
+- WHILE
+- FOR
+- FOREACH
+- BREAK
+- CONTINUE
+- GOTO
+- RETURN
+- THROW
+- CHECKED
+- UNCHECKED
+- LOCK
+- USING
+- TRY
+- CATCH
+- FINALLY
+- NAMESPACE_BEGIN
+- NAMESPACE_END
+- USING_DIRECTIVE
+- CLASS_BEGIN
+- CLASS_END
+- METHOD
+- PROPERTY
+- EVENT
+- INDEXER
+- OPERATOR
+- CONSTRUCTOR
+- DESTRUCTOR
+- STRUCT_BEGIN
+- STRUCT_END
+- INTERFACE_BEGIN
+- INTERFACE_END
+- ENUM
+- DELEGATE
+- ATTRIBUTE
+- IF_END
+- UNSAFE
+- FIXED
+- METHOD_BEGIN
+- METHOD_END
+- STRUCT
+- IF_BEGIN
+- CLASS
+- INTERFACE
+- ENUM_BEGIN
+- ENUM_END
+- ENUMERAL
+- ACCESSORS_BEGIN
+- ACCESSORS_END
+- ACCESSOR_BEGIN
+- ACCESSOR_END

languages/csharp/src/main/java/de/jplag/csharp/Language.java → languages/csharp/src/main/java/de/jplag/csharp/CSharpLanguage.java

@@ -14,15 +14,15 @@
  * @author Timur Saglam
  */
 @MetaInfServices(de.jplag.Language.class)
-public class Language implements de.jplag.Language {
+public class CSharpLanguage implements de.jplag.Language {
     private static final String NAME = "C# 6 Parser";
     private static final String IDENTIFIER = "csharp";
     private static final String[] FILE_ENDINGS = new String[] {".cs", ".CS"};
     private static final int DEFAULT_MIN_TOKEN_MATCH = 8;
 
     private final CSharpParserAdapter parser;
 
-    public Language() {
+    public CSharpLanguage() {
         parser = new CSharpParserAdapter();
     }
 

languages/csharp/src/test/java/de/jplag/csharp/MinimalCSharpTest.java

@@ -50,7 +50,7 @@ class MinimalCSharpTest {
 
     @BeforeEach
     public void setUp() {
-        language = new Language();
+        language = new CSharpLanguage();
         baseDirectory = BASE_PATH.toFile();
         assertTrue(baseDirectory.exists(), "Could not find base directory!");
     }

languages/emf-metamodel-dynamic/README.md

@@ -9,7 +9,7 @@ This module is based on the EMF dependencies available on maven central. These m
 For the token extraction, we visit the containment tree of the metamodel and extract tokens for all metamodel elements based on their concrete metaclass. In this module, we thus extract tokens based on a dynamic token set.
 
 ### Usage
-To use this module, add the `-l emf-metamodel-dynamic` flag in the CLI, or use a `JPlagOption` object with `new de.jplag.emf.dynamic.Language()` as `language` in the Java API as described in the usage information in the [readme of the main project](https://github.com/jplag/JPlag#usage) and [in the wiki](https://github.com/jplag/JPlag/wiki/1.-How-to-Use-JPlag).
+To use this module, add the `-l emf-metamodel-dynamic` flag in the CLI, or use a `JPlagOption` object with `new DynamicEmfLanguage()` as `language` in the Java API as described in the usage information in the [readme of the main project](https://github.com/jplag/JPlag#usage) and [in the wiki](https://github.com/jplag/JPlag/wiki/1.-How-to-Use-JPlag).
 
 ### More Info
 More information can be found in the paper [*"Token-based Plagiarism Detection for Metamodels" (MODELS-C'22)*](https://dl.acm.org/doi/10.1145/3550356.3556508).

languages/emf-metamodel-dynamic/src/main/java/de/jplag/emf/dynamic/Language.java → languages/emf-metamodel-dynamic/src/main/java/de/jplag/emf/dynamic/DynamicEmfLanguage.java

@@ -1,5 +1,6 @@
 package de.jplag.emf.dynamic;
 
+import de.jplag.emf.EmfLanguage;
 import de.jplag.emf.dynamic.parser.DynamicEcoreParser;
 import de.jplag.emf.parser.EcoreParser;
 
@@ -8,7 +9,7 @@
  * created token set instead of a hand-picked one.
  * @author Timur Saglam
  */
-public class Language extends de.jplag.emf.Language { // currently not included in the CLI
+public class DynamicEmfLanguage extends EmfLanguage { // currently not included in the CLI
     private static final String NAME = "EMF metamodels (dynamically created token set)";
     private static final String IDENTIFIER = "emf-dynamic";
 
@@ -17,14 +18,14 @@ public class Language extends de.jplag.emf.Language { // currently not included
     /**
      * Creates an EMF language instance with a dynamic token parser.
      */
-    public Language() {
+    public DynamicEmfLanguage() {
         super(new DynamicEcoreParser());
     }
 
     /**
      * Creates an EMF language instance with a custom token parser.
      */
-    public Language(EcoreParser parser) {
+    public DynamicEmfLanguage(EcoreParser parser) {
         super(parser);
     }
 

languages/emf-metamodel-dynamic/src/test/java/de/jplag/emf/dynamic/MinimalDynamicMetamodelTest.java

@@ -37,7 +37,7 @@ class MinimalDynamicMetamodelTest {
 
     @BeforeEach
     public void setUp() {
-        language = new Language();
+        language = new DynamicEmfLanguage();
         baseDirectory = BASE_PATH.toFile();
         FileUtil.assertDirectory(baseDirectory, TEST_SUBJECTS);
     }
@@ -48,8 +48,8 @@ void testBookstoreMetamodels() throws ParsingException {
         List<File> testFiles = Arrays.stream(TEST_SUBJECTS).map(path -> new File(BASE_PATH.toFile(), path)).toList();
         List<Token> result = language.parse(new HashSet<>(testFiles));
         List<TokenType> tokenTypes = result.stream().map(Token::getType).toList();
-        logger.debug(TokenPrinter.printTokens(result, baseDirectory, Optional.of(Language.VIEW_FILE_SUFFIX)));
-        logger.info("parsed token types: " + tokenTypes.stream().map(TokenType::getDescription).toList().toString());
+        logger.debug(TokenPrinter.printTokens(result, baseDirectory, Optional.of(DynamicEmfLanguage.VIEW_FILE_SUFFIX)));
+        logger.info("parsed token types: " + tokenTypes.stream().map(TokenType::getDescription).toList());
         assertEquals(94, tokenTypes.size());
         assertEquals(7, new HashSet<>(tokenTypes.stream().filter(DynamicMetamodelTokenType.class::isInstance).toList()).size());
 
@@ -64,6 +64,6 @@ void testBookstoreMetamodels() throws ParsingException {
 
     @AfterEach
     public void tearDown() {
-        FileUtil.clearFiles(new File(BASE_PATH.toString()), Language.VIEW_FILE_SUFFIX);
+        FileUtil.clearFiles(new File(BASE_PATH.toString()), DynamicEmfLanguage.VIEW_FILE_SUFFIX);
     }
 }

languages/emf-metamodel/README.md

@@ -9,7 +9,7 @@ This module is based on the EMF dependencies available on maven central. These m
 For the token extraction, we visit the containment tree of the metamodel and extract tokens for certain metamodel elements based on their metaclass. In this module, we extract tokens based on a [handcrafted token set](https://github.com/jplag/JPlag/blob/master/languages/emf-metamodel/src/main/java/de/jplag/emf/MetamodelTokenType.java). Note that not for all concrete metaclasses tokens are extracted. `EFactory`, `EGenericType`, and `EObject` are ignored. Moreover, for some metaclasses, multiple token types are extracted. Finally, some references are also used for token extraction.
 
 ### Usage
-To use this module, add the `-l emf-metamodel` flag in the CLI, or use a `JPlagOption` object with `new de.jplag.emf.Language()` as `language` in the Java API as described in the usage information in the [readme of the main project](https://github.com/jplag/JPlag#usage) and [in the wiki](https://github.com/jplag/JPlag/wiki/1.-How-to-Use-JPlag).
+To use this module, add the `-l emf-metamodel` flag in the CLI, or use a `JPlagOption` object with `new EmfLanguage()` as `language` in the Java API as described in the usage information in the [readme of the main project](https://github.com/jplag/JPlag#usage) and [in the wiki](https://github.com/jplag/JPlag/wiki/1.-How-to-Use-JPlag).
 
 ### More Info
 More information can be found in the paper [*"Token-based Plagiarism Detection for Metamodels" (MODELS-C'22)*](https://dl.acm.org/doi/10.1145/3550356.3556508).

languages/emf-metamodel/src/main/java/de/jplag/emf/Language.java → languages/emf-metamodel/src/main/java/de/jplag/emf/EmfLanguage.java

@@ -16,7 +16,7 @@
  * @author Timur Saglam
  */
 @MetaInfServices(de.jplag.Language.class)
-public class Language implements de.jplag.Language {
+public class EmfLanguage implements de.jplag.Language {
     public static final String VIEW_FILE_SUFFIX = ".emfatic";
     public static final String FILE_ENDING = "." + EcorePackage.eNAME;
 
@@ -26,11 +26,11 @@ public class Language implements de.jplag.Language {
 
     protected final EcoreParser parser;
 
-    public Language() {
+    public EmfLanguage() {
         this(new EcoreParser());
     }
 
-    protected Language(EcoreParser parser) {
+    protected EmfLanguage(EcoreParser parser) {
         this.parser = parser;
     }
 

languages/emf-metamodel/src/main/java/de/jplag/emf/parser/EcoreParser.java

@@ -12,7 +12,7 @@
 import de.jplag.ParsingException;
 import de.jplag.Token;
 import de.jplag.TokenType;
-import de.jplag.emf.Language;
+import de.jplag.emf.EmfLanguage;
 import de.jplag.emf.MetamodelToken;
 import de.jplag.emf.normalization.ModelSorter;
 import de.jplag.emf.util.AbstractMetamodelVisitor;
@@ -74,7 +74,7 @@ protected void parseModelFile(File file) throws ParsingException {
      * @return the correct view file suffix for the model view. Can be overriden in subclasses for alternative views.
      */
     protected String getCorrespondingViewFileSuffix() {
-        return Language.VIEW_FILE_SUFFIX;
+        return EmfLanguage.VIEW_FILE_SUFFIX;
     }
 
     /**

languages/emf-metamodel/src/test/java/de/jplag/emf/AbstractEmfTest.java

@@ -35,14 +35,14 @@ public abstract class AbstractEmfTest {
 
     @BeforeEach
     protected void setUp() {
-        language = new Language();
+        language = new EmfLanguage();
         baseDirectory = BASE_PATH.toFile();
         FileUtil.assertDirectory(baseDirectory, TEST_SUBJECTS);
     }
 
     @AfterEach
     protected void tearDown() {
-        FileUtil.clearFiles(new File(BASE_PATH.toString()), Language.VIEW_FILE_SUFFIX);
+        FileUtil.clearFiles(new File(BASE_PATH.toString()), EmfLanguage.VIEW_FILE_SUFFIX);
     }
 
     /**

languages/emf-metamodel/src/test/java/de/jplag/emf/MinimalMetamodelTest.java

@@ -30,9 +30,9 @@ void testBookstoreMetamodels() throws ParsingException {
         List<File> testFiles = Arrays.stream(TEST_SUBJECTS).map(path -> new File(BASE_PATH.toFile(), path)).toList();
         List<Token> result = language.parse(new HashSet<>(testFiles));
 
-        logger.debug(TokenPrinter.printTokens(result, baseDirectory, Optional.of(Language.VIEW_FILE_SUFFIX)));
+        logger.debug(TokenPrinter.printTokens(result, baseDirectory, Optional.of(EmfLanguage.VIEW_FILE_SUFFIX)));
         List<TokenType> tokenTypes = result.stream().map(Token::getType).toList();
-        logger.info("Parsed token types: " + tokenTypes.stream().map(TokenType::getDescription).toList().toString());
+        logger.info("Parsed token types: " + tokenTypes.stream().map(TokenType::getDescription).toList());
         assertEquals(80, tokenTypes.size());
         assertEquals(12, new HashSet<>(tokenTypes).size());
 

languages/emf-metamodel/src/test/java/de/jplag/emf/util/EmfaticModelViewTest.java

@@ -11,7 +11,7 @@
 
 import de.jplag.ParsingException;
 import de.jplag.emf.AbstractEmfTest;
-import de.jplag.emf.Language;
+import de.jplag.emf.EmfLanguage;
 
 class EmfaticModelViewTest extends AbstractEmfTest {
 
@@ -31,9 +31,9 @@ void testEmfaticViewFiles(String modelName) throws ParsingException {
 
         // Generate emfatic view:
         EmfaticModelView view = new EmfaticModelView(modelFile, modelResource);
-        view.writeToFile(Language.VIEW_FILE_SUFFIX);
+        view.writeToFile(EmfLanguage.VIEW_FILE_SUFFIX);
 
         // Compare expected vs. actual view file:
-        assertViewFilesMatch(modelFile, Language.VIEW_FILE_SUFFIX, EXPECTED_VIEW_FOLDER);
+        assertViewFilesMatch(modelFile, EmfLanguage.VIEW_FILE_SUFFIX, EXPECTED_VIEW_FOLDER);
     }
 }

languages/emf-model/src/main/java/de/jplag/emf/model/Language.java → languages/emf-model/src/main/java/de/jplag/emf/model/EmfModelLanguage.java

@@ -6,6 +6,7 @@
 
 import org.kohsuke.MetaInfServices;
 
+import de.jplag.emf.dynamic.DynamicEmfLanguage;
 import de.jplag.emf.model.parser.DynamicModelParser;
 
 /**
@@ -14,13 +15,13 @@
  * @author Timur Saglam
  */
 @MetaInfServices(de.jplag.Language.class)
-public class Language extends de.jplag.emf.dynamic.Language {
+public class EmfModelLanguage extends DynamicEmfLanguage {
     private static final String NAME = "EMF models (dynamically created token set)";
     private static final String IDENTIFIER = "emf-model";
 
     public static final String VIEW_FILE_SUFFIX = ".treeview";
 
-    public Language() {
+    public EmfModelLanguage() {
         super(new DynamicModelParser());
     }
 

languages/emf-model/src/main/java/de/jplag/emf/model/parser/DynamicModelParser.java

@@ -9,8 +9,9 @@
 import org.eclipse.emf.ecore.resource.Resource;
 
 import de.jplag.ParsingException;
+import de.jplag.emf.EmfLanguage;
 import de.jplag.emf.dynamic.parser.DynamicEcoreParser;
-import de.jplag.emf.model.Language;
+import de.jplag.emf.model.EmfModelLanguage;
 import de.jplag.emf.util.AbstractModelView;
 import de.jplag.emf.util.EMFUtil;
 import de.jplag.emf.util.MetamodelTreeView;
@@ -37,9 +38,9 @@ public DynamicModelParser() {
     @Override
     protected void parseModelFile(File file) throws ParsingException {
         // implicit assumption: Metamodel gets parsed first!
-        if (file.getName().endsWith(de.jplag.emf.Language.FILE_ENDING)) {
+        if (file.getName().endsWith(EmfLanguage.FILE_ENDING)) {
             parseMetamodelFile(file);
-        } else if (file.getName().endsWith(Language.VIEW_FILE_SUFFIX)) {
+        } else if (file.getName().endsWith(EmfModelLanguage.VIEW_FILE_SUFFIX)) {
             logger.warn(VIEW_FILE_WARNING, file.getName());
         } else {
             if (metapackages.isEmpty()) {
@@ -51,7 +52,7 @@ protected void parseModelFile(File file) throws ParsingException {
 
     @Override
     protected String getCorrespondingViewFileSuffix() {
-        return Language.VIEW_FILE_SUFFIX;
+        return EmfModelLanguage.VIEW_FILE_SUFFIX;
     }
 
     @Override