Merge pull request #935 from jplag/develop

Merge develop into main
jplag · Feb 15, 2023 · 0c56723 · 0c56723
2 parents 1a7ca3c + 5534af2
commit 0c56723
Show file tree

Hide file tree

Showing 132 changed files with 25,674 additions and 15,271 deletions.
diff --git a/.github/workflows/report-viewer-dev.yml b/.github/workflows/report-viewer-dev.yml
@@ -0,0 +1,47 @@
+name: Report Viewer Deployment Workflow (Dev)
+
+on:
+ workflow_dispatch: # Use this to dispatch from the Actions Tab
+ push:
+    branches:
+      - develop
+
+jobs:
+  build-and-deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout 🛎️
+        uses: actions/checkout@v3
+
+      - uses: actions/setup-node@v3
+        with:
+          node-version: "16"
+
+      - name: Set version of Report Viewer
+        shell: bash
+        run: |
+          VERSION=$(grep "<revision>" pom.xml | grep -oPm1 "(?<=<revision>)[^-|<]+")
+          MAJOR=$(echo $VERSION | cut -d '.' -f 1)
+          MINOR=$(echo $VERSION | cut -d '.' -f 2)
+          PATCH=$(echo $VERSION | cut -d '.' -f 3)
+          sed -i "/major/s/.*/    \"major\": $MAJOR,/" report-viewer/src/version.json
+          sed -i "/minor/s/.*/    \"minor\": $MINOR,/" report-viewer/src/version.json
+          sed -i "/patch/s/.*/    \"patch\": $PATCH/" report-viewer/src/version.json
+          echo "Version of Report Viewer:"
+          cat report-viewer/src/version.json
+
+      - name: Install and Build 🔧
+        working-directory: report-viewer
+        run: |
+          npm install
+          npm run build
+
+      - name: Deploy 🚀
+        uses: JamesIves/[email protected]
+        with:
+          branch: gh-pages
+          folder: report-viewer/dist
+          repository-name: JPlag/JPlag-Dev
+          token: ${{ secrets.SDQ_DEV_DEPLOY_TOKEN }}
+          clean: true
+          single-commit: true
diff --git a/.github/workflows/report-viewer-test.yml b/.github/workflows/report-viewer-test.yml
@@ -28,7 +28,20 @@ jobs:
       - uses: actions/setup-node@v3
         with:
           node-version: "16"
-
+
+      - name: Set version of Report Viewer
+        shell: bash
+        run: |
+          VERSION=$(grep "<revision>" pom.xml | grep -oPm1 "(?<=<revision>)[^-|<]+")
+          MAJOR=$(echo $VERSION | cut -d '.' -f 1)
+          MINOR=$(echo $VERSION | cut -d '.' -f 2)
+          PATCH=$(echo $VERSION | cut -d '.' -f 3)
+          sed -i "/major/s/.*/    \"major\": $MAJOR,/" report-viewer/src/version.json
+          sed -i "/minor/s/.*/    \"minor\": $MINOR,/" report-viewer/src/version.json
+          sed -i "/patch/s/.*/    \"patch\": $PATCH/" report-viewer/src/version.json
+          echo "Version of Report Viewer:"
+          cat report-viewer/src/version.json
+
       - name: Install and Build 🔧
         working-directory: report-viewer
         run: |

diff --git a/.github/workflows/report-viewer.yml b/.github/workflows/report-viewer.yml
@@ -16,7 +16,20 @@ jobs:
       - uses: actions/setup-node@v3
         with:
           node-version: "16"
-
+
+      - name: Set version of Report Viewer
+        shell: bash
+        run: |
+          VERSION=$(grep "<revision>" pom.xml | grep -oPm1 "(?<=<revision>)[^-|<]+")
+          MAJOR=$(echo $VERSION | cut -d '.' -f 1)
+          MINOR=$(echo $VERSION | cut -d '.' -f 2)
+          PATCH=$(echo $VERSION | cut -d '.' -f 3)
+          sed -i "/major/s/.*/    \"major\": $MAJOR,/" report-viewer/src/version.json
+          sed -i "/minor/s/.*/    \"minor\": $MINOR,/" report-viewer/src/version.json
+          sed -i "/patch/s/.*/    \"patch\": $PATCH/" report-viewer/src/version.json
+          echo "Version of Report Viewer:"
+          cat report-viewer/src/version.json
+
       - name: Install and Build 🔧
         working-directory: report-viewer
         run: |

diff --git a/README.md b/README.md
@@ -9,30 +9,33 @@
 [![License](https://img.shields.io/github/license/jplag/jplag.svg)](https://github.com/jplag/jplag/blob/main/LICENSE)
 [![GitHub commit activity](https://img.shields.io/github/commit-activity/y/jplag/JPlag)](https://github.com/jplag/JPlag/pulse)
 [![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
 
 In the following, a list of all supported languages with their supported language version is provided. A language can be selected from the command line using the `-l <cli argument name>` argument.
 
-| Language                                                         | Version | CLI Argument Name     | [state](https://github.com/jplag/JPlag/wiki/3.-Language-Modules) | parser |
-|------------------------------------------------------------------|--------:|-----------------------| :---: | :---: |
-| [Java](https://www.java.com)                                     |      17 | java                  | mature | JavaC |
-| [C++](https://isocpp.org)                                        |      11 | cpp                   | legacy | JavaCC |
-| [C#](https://docs.microsoft.com/en-us/dotnet/csharp/)            |       8 | csharp                | beta | ANTLR 4 |
-| [Go](https://go.dev)                                             |    1.17 | golang                | beta | ANTLR 4 |
-| [Kotlin](https://kotlinlang.org)                                 |     1.3 | kotlin                | beta | ANTLR 4 |
-| [Python](https://www.python.org)                                 |     3.6 | python3               | legacy | ANTLR 4 |
-| [R](https://www.r-project.org/)                                  |   3.5.0 | rlang                 | beta | ANTLR 4 |
-| [Rust](https://www.rust-lang.org/)                               |  1.60.0 | rust                  | beta | ANTLR 4 |
-| [Scala](https://www.scala-lang.org)                              |  2.13.8 | scala                 | beta | Scalameta |
-| [Scheme](http://www.scheme-reports.org)                          |       ? | scheme                | unknown | JavaCC |
-| [Swift](https://www.swift.org)                                   |     5.4 | swift                 | beta | ANTLR 4 |
-| [EMF Metamodel](https://www.eclipse.org/modeling/emf/)           |  2.25.0 | emf                   | alpha | EMF |
-| Text (naive)                                                     |       - | text                  | legacy | CoreNLP |
+| Language                                               | Version | CLI Argument Name | [state](https://github.com/jplag/JPlag/wiki/3.-Language-Modules) |  parser   |
+|--------------------------------------------------------|--------:|-------------------|:----------------------------------------------------------------:|:---------:|
+| [Java](https://www.java.com)                           |      17 | java              |                              mature                              |   JavaC   |
+| [C++](https://isocpp.org)                              |      11 | cpp               |                              legacy                              |  JavaCC   |
+| [C#](https://docs.microsoft.com/en-us/dotnet/csharp/)  |       8 | csharp            |                               beta                               |  ANTLR 4  |
+| [Go](https://go.dev)                                   |    1.17 | golang            |                               beta                               |  ANTLR 4  |
+| [Kotlin](https://kotlinlang.org)                       |     1.3 | kotlin            |                               beta                               |  ANTLR 4  |
+| [Python](https://www.python.org)                       |     3.6 | python3           |                              legacy                              |  ANTLR 4  |
+| [R](https://www.r-project.org/)                        |   3.5.0 | rlang             |                               beta                               |  ANTLR 4  |
+| [Rust](https://www.rust-lang.org/)                     |  1.60.0 | rust              |                               beta                               |  ANTLR 4  |
+| [Scala](https://www.scala-lang.org)                    |  2.13.8 | scala             |                               beta                               | Scalameta |
+| [Scheme](http://www.scheme-reports.org)                |       ? | scheme            |                             unknown                              |  JavaCC   |
+| [Swift](https://www.swift.org)                         |     5.4 | swift             |                               beta                               |  ANTLR 4  |
+| [EMF Metamodel](https://www.eclipse.org/modeling/emf/) |  2.25.0 | emf               |                              alpha                               |    EMF    |
+| Text (naive)                                           |       - | text              |                              legacy                              |  CoreNLP  |
 
 ## Download and Installation
+You need Java SE 17 to run or build JPlag.
 
 ### Downloading a release
 * Download a [released version](https://github.com/jplag/jplag/releases).
@@ -51,7 +54,7 @@ JPlag is released on [Maven Central](https://search.maven.org/search?q=de.jplag)
 1. Download or clone the code from this repository.
 2. Run `mvn clean package` from the root of the repository to compile and build all submodules.
    Run `mvn clean package assembly:single` instead if you need the full jar which includes all dependencies.
-5. You will find the generated JARs in the subdirectory `jplag.cli/target`.
+5. You will find the generated JARs in the subdirectory `cli/target`.
 
 ## Usage
 JPlag can either be used via the CLI or directly via its Java API. For more information, see the [usage information in the wiki](https://github.com/jplag/JPlag/wiki/1.-How-to-Use-JPlag). If you are using the CLI, you can display your results via [jplag.github.io](https://jplag.github.io/JPlag/). No data will leave your computer!

diff --git a/cli/src/main/java/de/jplag/cli/CLI.java b/cli/src/main/java/de/jplag/cli/CLI.java
@@ -36,11 +36,6 @@
 import java.util.Random;
 import java.util.stream.Collectors;
 
-import net.sourceforge.argparse4j.ArgumentParsers;
-import net.sourceforge.argparse4j.inf.ArgumentParser;
-import net.sourceforge.argparse4j.inf.ArgumentParserException;
-import net.sourceforge.argparse4j.inf.Namespace;
-
 import org.slf4j.ILoggerFactory;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
@@ -54,6 +49,11 @@
 import de.jplag.options.JPlagOptions;
 import de.jplag.reporting.reportobject.ReportObjectFactory;
 
+import net.sourceforge.argparse4j.ArgumentParsers;
+import net.sourceforge.argparse4j.inf.ArgumentParser;
+import net.sourceforge.argparse4j.inf.ArgumentParserException;
+import net.sourceforge.argparse4j.inf.Namespace;
+
 /**
  * Command line interface class, allows using via command line.
  * @see CLI#main(String[])
@@ -82,6 +82,7 @@ public final class CLI {
      */
     public static void main(String[] args) {
         try {
+            logger.debug("Your version of JPlag is {}", JPlag.JPLAG_VERSION);
             CLI cli = new CLI();
             Namespace arguments = cli.parseArguments(args);
             JPlagOptions options = cli.buildOptionsFromArguments(arguments);

diff --git a/cli/src/main/java/de/jplag/cli/CommandLineArgument.java b/cli/src/main/java/de/jplag/cli/CommandLineArgument.java
@@ -12,14 +12,6 @@
 import java.util.List;
 import java.util.Optional;
 
-import net.sourceforge.argparse4j.impl.Arguments;
-import net.sourceforge.argparse4j.inf.Argument;
-import net.sourceforge.argparse4j.inf.ArgumentAction;
-import net.sourceforge.argparse4j.inf.ArgumentContainer;
-import net.sourceforge.argparse4j.inf.ArgumentParser;
-import net.sourceforge.argparse4j.inf.FeatureControl;
-import net.sourceforge.argparse4j.inf.Namespace;
-
 import de.jplag.Language;
 import de.jplag.Messages;
 import de.jplag.NumberOfArgumentValues;
@@ -28,6 +20,14 @@
 import de.jplag.clustering.algorithm.InterClusterSimilarity;
 import de.jplag.options.SimilarityMetric;
 
+import net.sourceforge.argparse4j.impl.Arguments;
+import net.sourceforge.argparse4j.inf.Argument;
+import net.sourceforge.argparse4j.inf.ArgumentAction;
+import net.sourceforge.argparse4j.inf.ArgumentContainer;
+import net.sourceforge.argparse4j.inf.ArgumentParser;
+import net.sourceforge.argparse4j.inf.FeatureControl;
+import net.sourceforge.argparse4j.inf.Namespace;
+
 /**
  * Command line arguments for the JPlag CLI. Each argument is defined through an enumeral.
  * @author Timur Saglam

diff --git a/cli/src/test/java/de/jplag/cli/CommandLineInterfaceTest.java b/cli/src/test/java/de/jplag/cli/CommandLineInterfaceTest.java
@@ -5,10 +5,10 @@
 
 import java.util.Arrays;
 
-import net.sourceforge.argparse4j.inf.Namespace;
-
 import de.jplag.options.JPlagOptions;
 
+import net.sourceforge.argparse4j.inf.Namespace;
+
 /**
  * Test base for tests regarding the {@link CLI} and any {@link CommandLineArgument}. Solely tests if the arguments set
  * via the command line interface are propagated correctly into options. JPlag is not executed for the different command

diff --git a/core/pom.xml b/core/pom.xml
@@ -74,4 +74,13 @@
             <scope>test</scope>
         </dependency>
     </dependencies>
+
+    <build>
+        <resources>
+            <resource>
+                <filtering>true</filtering>
+                <directory>src/main/resources</directory>
+            </resource>
+        </resources>
+    </build>
 </project>
diff --git a/core/src/main/java/de/jplag/JPlag.java b/core/src/main/java/de/jplag/JPlag.java
@@ -1,12 +1,15 @@
 package de.jplag;
 
+import java.util.ResourceBundle;
+
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
 import de.jplag.clustering.ClusteringFactory;
 import de.jplag.exceptions.ExitException;
 import de.jplag.exceptions.SubmissionException;
 import de.jplag.options.JPlagOptions;
+import de.jplag.reporting.reportobject.model.Version;
 import de.jplag.strategy.ComparisonStrategy;
 import de.jplag.strategy.ParallelComparisonStrategy;
 
@@ -16,6 +19,15 @@
 public class JPlag {
     private static final Logger logger = LoggerFactory.getLogger(JPlag.class);
 
+    public static final Version JPLAG_VERSION = loadVersion();
+
+    private static Version loadVersion() {
+        ResourceBundle versionProperties = ResourceBundle.getBundle("de.jplag.version");
+        String versionString = versionProperties.getString("version");
+        Version currentVersion = Version.parseVersion(versionString);
+        return currentVersion == null ? Version.DEVELOPMENT : currentVersion;
+    }
+
     private final JPlagOptions options;
 
     private final Language language;

diff --git a/core/src/main/java/de/jplag/clustering/ClusteringFactory.java b/core/src/main/java/de/jplag/clustering/ClusteringFactory.java
@@ -17,10 +17,17 @@
  * Runs the clustering according to an options object.
  */
 public class ClusteringFactory {
-    private static final String CLUSTER_PATTERN = " cluster strength: {}, avg similarity: {}%, members: {}";
+    private static final int MAX_LOGGED_MEMBERS = 5;
+    private static final String STRENGTH_FORMAT = "%,.5f";
+    private static final String SIMILARITY_FORMAT = "%,.1f%%";
+    private static final String CLOSING_BRACKET = "]";
+    private static final String DOTS = "...";
+
+    private static final String CLUSTER_PATTERN = "avg similarity: {}, strength: {}, {} members: {}";
     private static final String CLUSTERING_RESULT = "{} clusters were found:";
     private static final String CLUSTERING_PARAMETERS = "Calculating clusters via {} clustering with {} pre-processing...";
     private static final String CLUSTERING_DISABLED = "Cluster calculation disabled (as requested)!";
+
     private static final Logger logger = LoggerFactory.getLogger(ClusteringFactory.class);
 
     public static List<ClusteringResult<Submission>> getClusterings(Collection<JPlagComparison> comparisons, ClusteringOptions options) {
@@ -62,8 +69,22 @@ private static ClusteringResult<Submission> removeBadClusters(final ClusteringRe
 
     private static void logClusters(ClusteringResult<Submission> result) {
         var clusters = new ArrayList<>(result.getClusters());
-        clusters.sort((first, second) -> Double.compare(second.getCommunityStrength(), first.getCommunityStrength()));
+        clusters.sort((first, second) -> Double.compare(second.getAverageSimilarity(), first.getAverageSimilarity()));
         logger.info(CLUSTERING_RESULT, clusters.size());
-        clusters.forEach(it -> logger.info(CLUSTER_PATTERN, it.getCommunityStrength(), it.getAverageSimilarity(), it.getMembers()));
+        clusters.forEach(ClusteringFactory::logCluster);
+    }
+
+    private static void logCluster(Cluster<Submission> cluster) {
+        String members = membersToString(cluster.getMembers());
+        String similarity = String.format(SIMILARITY_FORMAT, cluster.getAverageSimilarity() * 100);
+        String strength = String.format(STRENGTH_FORMAT, cluster.getCommunityStrength());
+        logger.info(CLUSTER_PATTERN, similarity, strength, cluster.getMembers().size(), members);
+    }
+
+    private static String membersToString(Collection<Submission> members) {
+        if (members.size() > MAX_LOGGED_MEMBERS) {
+            return List.copyOf(members).subList(0, MAX_LOGGED_MEMBERS).toString().replace(CLOSING_BRACKET, DOTS);
+        }
+        return members.toString();
     }
 }
diff --git a/core/src/main/java/de/jplag/clustering/ClusteringOptions.java b/core/src/main/java/de/jplag/clustering/ClusteringOptions.java
@@ -59,7 +59,7 @@ public ClusteringOptions(SimilarityMetric similarityMetric, double spectralKerne
     }
 
     public ClusteringOptions() {
-        this(SimilarityMetric.MAX, 20.f, 0.05 * 0.05, 5, 50, 200, 0.2, Preprocessing.CUMULATIVE_DISTRIBUTION_FUNCTION, true,
+        this(SimilarityMetric.AVG, 20.f, 0.05 * 0.05, 5, 50, 200, 0.2, Preprocessing.CUMULATIVE_DISTRIBUTION_FUNCTION, true,
                 ClusteringAlgorithm.SPECTRAL, InterClusterSimilarity.AVERAGE, 0.2, 0.5);
     }
 

diff --git a/core/src/main/java/de/jplag/options/SimilarityMetric.java b/core/src/main/java/de/jplag/options/SimilarityMetric.java
@@ -5,14 +5,16 @@
 import de.jplag.JPlagComparison;
 
 public enum SimilarityMetric implements ToDoubleFunction<JPlagComparison> {
-    AVG(JPlagComparison::similarity),
-    MIN(JPlagComparison::minimalSimilarity),
-    MAX(JPlagComparison::maximalSimilarity),
-    INTERSECTION(it -> (double) it.getNumberOfMatchedTokens());
+    AVG("average similarity", JPlagComparison::similarity),
+    MIN("minimum similarity", JPlagComparison::minimalSimilarity),
+    MAX("maximal similarity", JPlagComparison::maximalSimilarity),
+    INTERSECTION("matched tokens", it -> (double) it.getNumberOfMatchedTokens());
 
     private final ToDoubleFunction<JPlagComparison> similarityFunction;
+    private final String description;
 
-    SimilarityMetric(ToDoubleFunction<JPlagComparison> similarityFunction) {
+    SimilarityMetric(String description, ToDoubleFunction<JPlagComparison> similarityFunction) {
+        this.description = description;
         this.similarityFunction = similarityFunction;
     }
 
@@ -24,4 +26,9 @@ public boolean isAboveThreshold(JPlagComparison comparison, double similarityThr
     public double applyAsDouble(JPlagComparison comparison) {
         return similarityFunction.applyAsDouble(comparison);
     }
+
+    @Override
+    public String toString() {
+        return description;
+    }
 }
diff --git a/core/src/main/java/de/jplag/reporting/jsonfactory/ComparisonReportWriter.java b/core/src/main/java/de/jplag/reporting/jsonfactory/ComparisonReportWriter.java
@@ -1,6 +1,7 @@
 package de.jplag.reporting.jsonfactory;
 
 import java.io.File;
+import java.nio.file.Path;
 import java.util.List;
 import java.util.Map;
 import java.util.concurrent.ConcurrentHashMap;
@@ -104,7 +105,10 @@ private Match convertMatchToReportMatch(JPlagComparison comparison, de.jplag.Mat
     }
 
     private String relativizedFilePath(File file, Submission submission) {
-        return submission.getRoot().toPath().relativize(file.toPath()).toString();
+        if (file.toPath().equals(submission.getRoot().toPath())) {
+            return Path.of(submissionToIdFunction.apply(submission), submission.getName()).toString();
+        }
+        return Path.of(submissionToIdFunction.apply(submission), submission.getRoot().toPath().relativize(file.toPath()).toString()).toString();
     }
 
 }