Merge pull request #804 from jplag/develop

jplag · Nov 17, 2022 · 7d17ab1 · 7d17ab1
2 parents 6fc9f77 + 60f9634
commit 7d17ab1
Show file tree

Hide file tree

Showing 69 changed files with 1,038 additions and 889 deletions.
diff --git a/.github/pull_request_template.md b/.github/pull_request_template.md
@@ -0,0 +1,6 @@
+<!--
+Pull requests regarding major or minor updates need to target the `develop` branch.
+Pull requests regarding patch updates need to target the `main` branch.
+Please make sure to select the appropriate branch while creating the pull request.
+For a reference on semantic versioning, see https://semver.org.
+-->
diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml
@@ -1,20 +1,19 @@
-name: Deploy to Maven Central
+name: Deploy to Maven Central & GitHub
 on:
   workflow_dispatch:
   release:
     types: [created]
 jobs:
-  publish:
+  publish-maven-central:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
-      - name: Set up Maven Central Repository
-        uses: actions/setup-java@v3
+      - uses: actions/setup-java@v3
         with:
           java-version: '17'
           distribution: 'temurin'
       - name: Set maven settings.xml
-        uses: whelk-io/maven-settings-xml-action@v20
+        uses: whelk-io/maven-settings-xml-action@v21
         with:
           servers: '[{ "id": "ossrh", "username": "jplag", "password": "${{ secrets.OSSRH_TOKEN }}" }]'
       - name: Import GPG key
@@ -26,3 +25,21 @@ jobs:
         run: mvn -P deployment -U -B deploy
         env:
           GPG_PASSPHRASE: ${{ secrets.PGP_PW }}
+
+  publish-release-artifact:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-java@v3
+        with:
+          java-version: '17'
+          distribution: 'temurin'
+      - name: Build JPlag
+        run: mvn -U -B clean package assembly:single
+
+      - name: Attach CLI to Release on GitHub
+        uses: softprops/action-gh-release@v1
+        if: startsWith(github.ref, 'refs/tags/')
+        with:
+          files: jplag.cli/target/jplag-*-jar-with-dependencies.jar
+          fail_on_unmatched_files: true
diff --git a/cli/pom.xml b/cli/pom.xml
@@ -8,6 +8,8 @@
     </parent>
     <artifactId>cli</artifactId>
     <dependencies>
+        <!-- IMPORTANT: For Coverage testing, you have to add dependencies to the coverage-report project ! -->
+
         <dependency>
             <groupId>de.jplag</groupId>
             <artifactId>jplag</artifactId>
@@ -103,7 +105,7 @@
                 <configuration>
                     <archive>
                         <manifest>
-                            <mainClass>de.jplag.CLI</mainClass>
+                            <mainClass>de.jplag.cli.CLI</mainClass>
                             <packageName>jplag</packageName>
                         </manifest>
                     </archive>
@@ -117,7 +119,7 @@
                     </descriptors>
                     <archive>
                         <manifest>
-                            <mainClass>de.jplag.CLI</mainClass>
+                            <mainClass>de.jplag.cli.CLI</mainClass>
                             <packageName>jplag</packageName>
                             <addDefaultImplementationEntries>true</addDefaultImplementationEntries>
                             <addDefaultSpecificationEntries>true</addDefaultSpecificationEntries>
@@ -126,19 +128,6 @@
                     <finalName>jplag-${project.version}</finalName>
                 </configuration>
             </plugin>
-            <plugin>
-                <groupId>org.jacoco</groupId>
-                <artifactId>jacoco-maven-plugin</artifactId>
-                <executions>
-                    <execution>
-                        <id>report-aggregate</id>
-                        <goals>
-                            <goal>report-aggregate</goal>
-                        </goals>
-                        <phase>verify</phase>
-                    </execution>
-                </executions>
-            </plugin>
         </plugins>
     </build>
 </project>
diff --git a/cli/src/main/java/de/jplag/CLI.java → cli/src/main/java/de/jplag/cli/CLI.java b/cli/src/main/java/de/jplag/CLI.java → cli/src/main/java/de/jplag/cli/CLI.java
@@ -1,32 +1,32 @@
-package de.jplag;
-
-import static de.jplag.CommandLineArgument.BASE_CODE;
-import static de.jplag.CommandLineArgument.CLUSTER_AGGLOMERATIVE_INTER_CLUSTER_SIMILARITY;
-import static de.jplag.CommandLineArgument.CLUSTER_AGGLOMERATIVE_THRESHOLD;
-import static de.jplag.CommandLineArgument.CLUSTER_ALGORITHM;
-import static de.jplag.CommandLineArgument.CLUSTER_DISABLE;
-import static de.jplag.CommandLineArgument.CLUSTER_METRIC;
-import static de.jplag.CommandLineArgument.CLUSTER_PREPROCESSING_CDF;
-import static de.jplag.CommandLineArgument.CLUSTER_PREPROCESSING_NONE;
-import static de.jplag.CommandLineArgument.CLUSTER_PREPROCESSING_PERCENTILE;
-import static de.jplag.CommandLineArgument.CLUSTER_PREPROCESSING_THRESHOLD;
-import static de.jplag.CommandLineArgument.CLUSTER_SPECTRAL_BANDWIDTH;
-import static de.jplag.CommandLineArgument.CLUSTER_SPECTRAL_KMEANS_ITERATIONS;
-import static de.jplag.CommandLineArgument.CLUSTER_SPECTRAL_MAX_RUNS;
-import static de.jplag.CommandLineArgument.CLUSTER_SPECTRAL_MIN_RUNS;
-import static de.jplag.CommandLineArgument.CLUSTER_SPECTRAL_NOISE;
-import static de.jplag.CommandLineArgument.DEBUG;
-import static de.jplag.CommandLineArgument.EXCLUDE_FILE;
-import static de.jplag.CommandLineArgument.LANGUAGE;
-import static de.jplag.CommandLineArgument.MIN_TOKEN_MATCH;
-import static de.jplag.CommandLineArgument.NEW_DIRECTORY;
-import static de.jplag.CommandLineArgument.OLD_DIRECTORY;
-import static de.jplag.CommandLineArgument.RESULT_FOLDER;
-import static de.jplag.CommandLineArgument.ROOT_DIRECTORY;
-import static de.jplag.CommandLineArgument.SHOWN_COMPARISONS;
-import static de.jplag.CommandLineArgument.SIMILARITY_THRESHOLD;
-import static de.jplag.CommandLineArgument.SUBDIRECTORY;
-import static de.jplag.CommandLineArgument.SUFFIXES;
+package de.jplag.cli;
+
+import static de.jplag.cli.CommandLineArgument.BASE_CODE;
+import static de.jplag.cli.CommandLineArgument.CLUSTER_AGGLOMERATIVE_INTER_CLUSTER_SIMILARITY;
+import static de.jplag.cli.CommandLineArgument.CLUSTER_AGGLOMERATIVE_THRESHOLD;
+import static de.jplag.cli.CommandLineArgument.CLUSTER_ALGORITHM;
+import static de.jplag.cli.CommandLineArgument.CLUSTER_DISABLE;
+import static de.jplag.cli.CommandLineArgument.CLUSTER_METRIC;
+import static de.jplag.cli.CommandLineArgument.CLUSTER_PREPROCESSING_CDF;
+import static de.jplag.cli.CommandLineArgument.CLUSTER_PREPROCESSING_NONE;
+import static de.jplag.cli.CommandLineArgument.CLUSTER_PREPROCESSING_PERCENTILE;
+import static de.jplag.cli.CommandLineArgument.CLUSTER_PREPROCESSING_THRESHOLD;
+import static de.jplag.cli.CommandLineArgument.CLUSTER_SPECTRAL_BANDWIDTH;
+import static de.jplag.cli.CommandLineArgument.CLUSTER_SPECTRAL_KMEANS_ITERATIONS;
+import static de.jplag.cli.CommandLineArgument.CLUSTER_SPECTRAL_MAX_RUNS;
+import static de.jplag.cli.CommandLineArgument.CLUSTER_SPECTRAL_MIN_RUNS;
+import static de.jplag.cli.CommandLineArgument.CLUSTER_SPECTRAL_NOISE;
+import static de.jplag.cli.CommandLineArgument.DEBUG;
+import static de.jplag.cli.CommandLineArgument.EXCLUDE_FILE;
+import static de.jplag.cli.CommandLineArgument.LANGUAGE;
+import static de.jplag.cli.CommandLineArgument.MIN_TOKEN_MATCH;
+import static de.jplag.cli.CommandLineArgument.NEW_DIRECTORY;
+import static de.jplag.cli.CommandLineArgument.OLD_DIRECTORY;
+import static de.jplag.cli.CommandLineArgument.RESULT_FOLDER;
+import static de.jplag.cli.CommandLineArgument.ROOT_DIRECTORY;
+import static de.jplag.cli.CommandLineArgument.SHOWN_COMPARISONS;
+import static de.jplag.cli.CommandLineArgument.SIMILARITY_THRESHOLD;
+import static de.jplag.cli.CommandLineArgument.SUBDIRECTORY;
+import static de.jplag.cli.CommandLineArgument.SUFFIXES;
 
 import java.io.File;
 import java.security.SecureRandom;
@@ -45,10 +45,12 @@
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
+import de.jplag.JPlag;
+import de.jplag.JPlagResult;
+import de.jplag.cli.logger.CollectedLoggerFactory;
 import de.jplag.clustering.ClusteringOptions;
 import de.jplag.clustering.Preprocessing;
 import de.jplag.exceptions.ExitException;
-import de.jplag.logger.CollectedLoggerFactory;
 import de.jplag.options.JPlagOptions;
 import de.jplag.reporting.reportobject.ReportObjectFactory;
 
@@ -58,7 +60,7 @@
  */
 public final class CLI {
 
-    private static final Logger logger = LoggerFactory.getLogger("JPlag");
+    private static final Logger logger = LoggerFactory.getLogger(CLI.class);
 
     private static final Random RANDOM = new SecureRandom();
 

diff --git a/...rc/main/java/de/jplag/CliGroupHelper.java → ...ain/java/de/jplag/cli/CliGroupHelper.java b/...rc/main/java/de/jplag/CliGroupHelper.java → ...ain/java/de/jplag/cli/CliGroupHelper.java
@@ -1,4 +1,4 @@
-package de.jplag;
+package de.jplag.cli;
 
 import java.util.HashMap;
 import java.util.Map;

diff --git a/...in/java/de/jplag/CommandLineArgument.java → ...ava/de/jplag/cli/CommandLineArgument.java b/...in/java/de/jplag/CommandLineArgument.java → ...ava/de/jplag/cli/CommandLineArgument.java
@@ -1,7 +1,7 @@
-package de.jplag;
+package de.jplag.cli;
 
-import static de.jplag.CLI.ADVANCED_GROUP;
-import static de.jplag.CLI.CLUSTERING_GROUP_NAME;
+import static de.jplag.cli.CLI.ADVANCED_GROUP;
+import static de.jplag.cli.CLI.CLUSTERING_GROUP_NAME;
 import static de.jplag.options.JPlagOptions.DEFAULT_SHOWN_COMPARISONS;
 import static de.jplag.options.JPlagOptions.DEFAULT_SIMILARITY_THRESHOLD;
 import static net.sourceforge.argparse4j.impl.Arguments.append;
@@ -20,6 +20,9 @@
 import net.sourceforge.argparse4j.inf.FeatureControl;
 import net.sourceforge.argparse4j.inf.Namespace;
 
+import de.jplag.Language;
+import de.jplag.Messages;
+import de.jplag.NumberOfArgumentValues;
 import de.jplag.clustering.ClusteringAlgorithm;
 import de.jplag.clustering.ClusteringOptions;
 import de.jplag.clustering.algorithm.InterClusterSimilarity;
@@ -34,7 +37,7 @@ public enum CommandLineArgument {
     NEW_DIRECTORY(new Builder("-new", String.class).nargs(NumberOfArgumentValues.ONE_OR_MORE_VALUES)),
     OLD_DIRECTORY(new Builder("-old", String.class).nargs(NumberOfArgumentValues.ONE_OR_MORE_VALUES)),
     LANGUAGE(
-            new Builder("-l", String.class).defaultsTo(de.jplag.java.Language.IDENTIFIER)
+            new Builder("-l", String.class).defaultsTo(new de.jplag.java.Language().getIdentifier())
                     .choices(LanguageLoader.getAllAvailableLanguageIdentifiers())),
     BASE_CODE("-bc", String.class),
 
@@ -82,7 +85,7 @@ public enum CommandLineArgument {
      * The identifier of the default {@link Language}.
      * @see Language#getIdentifier()
      */
-    public static final String DEFAULT_LANGUAGE_IDENTIFIER = de.jplag.java.Language.IDENTIFIER;
+    public static final String DEFAULT_LANGUAGE_IDENTIFIER = new de.jplag.java.Language().getIdentifier();
 
     private final String flag;
     private final NumberOfArgumentValues numberOfValues;
@@ -126,7 +129,7 @@ public String flag() {
      * @return the flag name of the command line argument without leading dashes and inner dashes replaced with underscores.
      */
     public String flagWithoutDash() {
-        return flag.replaceAll("^-+", "").replaceAll("-", "_");
+        return flag.replaceAll("^-+", "").replace("-", "_");
     }
 
     /**

diff --git a/...rc/main/java/de/jplag/LanguageLoader.java → ...ain/java/de/jplag/cli/LanguageLoader.java b/...rc/main/java/de/jplag/LanguageLoader.java → ...ain/java/de/jplag/cli/LanguageLoader.java
@@ -1,4 +1,4 @@
-package de.jplag;
+package de.jplag.cli;
 
 import java.util.Collections;
 import java.util.Map;
@@ -11,12 +11,14 @@
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
+import de.jplag.Language;
+
 /**
  * This class contains methods to load {@link Language Languages}.
  * @author Dominik Fuchss
  */
 public final class LanguageLoader {
-    private static final Logger logger = LoggerFactory.getLogger("JPlag");
+    private static final Logger logger = LoggerFactory.getLogger(LanguageLoader.class);
 
     private static Map<String, Language> cachedLanguageInstances = null;
 

diff --git a/...java/de/jplag/logger/CollectedLogger.java → .../de/jplag/cli/logger/CollectedLogger.java b/...java/de/jplag/logger/CollectedLogger.java → .../de/jplag/cli/logger/CollectedLogger.java
@@ -1,4 +1,4 @@
-package de.jplag.logger;
+package de.jplag.cli.logger;
 
 import java.io.PrintStream;
 import java.io.Serial;
@@ -27,7 +27,12 @@ public final class CollectedLogger extends MarkerIgnoringBase {
     private static final int LOG_LEVEL_WARN = LocationAwareLogger.WARN_INT;
     private static final int LOG_LEVEL_ERROR = LocationAwareLogger.ERROR_INT;
 
-    private final int currentLogLevel = LOG_LEVEL_INFO;
+    /**
+     * The default log level that shall be used for external libraries (like Stanford Core NLP)
+     */
+    private static final int LOG_LEVEL_FOR_EXTERNAL_LIBRARIES = LOG_LEVEL_ERROR;
+
+    private static final int CURRENT_LOG_LEVEL = LOG_LEVEL_INFO;
 
     /**
      * The short name of this simple log instance
@@ -117,7 +122,11 @@ private String computeShortName() {
     }
 
     private boolean isLevelEnabled(int logLevel) {
-        return logLevel >= currentLogLevel;
+        return logLevel >= (isJPlagLog() ? CURRENT_LOG_LEVEL : LOG_LEVEL_FOR_EXTERNAL_LIBRARIES);
+    }
+
+    private boolean isJPlagLog() {
+        return this.name.startsWith("de.jplag.");
     }
 
     private String renderLevel(int level) {

diff --git a/.../jplag/logger/CollectedLoggerFactory.java → ...ag/cli/logger/CollectedLoggerFactory.java b/.../jplag/logger/CollectedLoggerFactory.java → ...ag/cli/logger/CollectedLoggerFactory.java
@@ -1,4 +1,4 @@
-package de.jplag.logger;
+package de.jplag.cli.logger;
 
 import java.util.ArrayList;
 import java.util.List;

diff --git a/...ogger/CollectedLoggerServiceProvider.java → ...ogger/CollectedLoggerServiceProvider.java b/...ogger/CollectedLoggerServiceProvider.java → ...ogger/CollectedLoggerServiceProvider.java
@@ -1,4 +1,4 @@
-package de.jplag.logger;
+package de.jplag.cli.logger;
 
 import org.kohsuke.MetaInfServices;
 import org.slf4j.ILoggerFactory;

diff --git a/...src/main/java/de/jplag/logger/Triple.java → ...main/java/de/jplag/cli/logger/Triple.java b/...src/main/java/de/jplag/logger/Triple.java → ...main/java/de/jplag/cli/logger/Triple.java
@@ -1,4 +1,4 @@
-package de.jplag.logger;
+package de.jplag.cli.logger;
 
 public record Triple<A, B, C> (A first, B second, C third) {
 }
diff --git a/cli/src/test/java/de/jplag/cli/BaseCodeOptionTest.java b/cli/src/test/java/de/jplag/cli/BaseCodeOptionTest.java
@@ -5,8 +5,6 @@
 
 import org.junit.jupiter.api.Test;
 
-import de.jplag.CommandLineArgument;
-
 class BaseCodeOptionTest extends CommandLineInterfaceTest {
 
     private static final String NAME = "BaseCodeName";

diff --git a/cli/src/test/java/de/jplag/cli/ClusteringTest.java b/cli/src/test/java/de/jplag/cli/ClusteringTest.java
@@ -4,7 +4,6 @@
 
 import org.junit.jupiter.api.Test;
 
-import de.jplag.CommandLineArgument;
 import de.jplag.clustering.Preprocessing;
 
 class ClusteringTest extends CommandLineInterfaceTest {

diff --git a/cli/src/test/java/de/jplag/cli/CommandLineInterfaceTest.java b/cli/src/test/java/de/jplag/cli/CommandLineInterfaceTest.java
@@ -1,14 +1,12 @@
 package de.jplag.cli;
 
-import static de.jplag.CommandLineArgument.ROOT_DIRECTORY;
+import static de.jplag.cli.CommandLineArgument.ROOT_DIRECTORY;
 import static java.util.stream.Collectors.toSet;
 
 import java.util.Arrays;
 
 import net.sourceforge.argparse4j.inf.Namespace;
 
-import de.jplag.CLI;
-import de.jplag.CommandLineArgument;
 import de.jplag.options.JPlagOptions;
 
 /**

diff --git a/cli/src/test/java/de/jplag/cli/LanguageTest.java b/cli/src/test/java/de/jplag/cli/LanguageTest.java
@@ -9,9 +9,7 @@
 import org.junit.jupiter.api.Assertions;
 import org.junit.jupiter.api.Test;
 
-import de.jplag.CommandLineArgument;
 import de.jplag.Language;
-import de.jplag.LanguageLoader;
 
 class LanguageTest extends CommandLineInterfaceTest {
 

diff --git a/cli/src/test/java/de/jplag/cli/MinTokenMatchTest.java b/cli/src/test/java/de/jplag/cli/MinTokenMatchTest.java
@@ -6,8 +6,6 @@
 
 import org.junit.jupiter.api.Test;
 
-import de.jplag.CommandLineArgument;
-
 class MinTokenMatchTest extends CommandLineInterfaceTest {
 
     @Test

diff --git a/cli/src/test/java/de/jplag/cli/SimiliarityThresholdTest.java b/cli/src/test/java/de/jplag/cli/SimiliarityThresholdTest.java
@@ -5,7 +5,6 @@
 
 import org.junit.jupiter.api.Test;
 
-import de.jplag.CommandLineArgument;
 import de.jplag.options.JPlagOptions;
 
 class SimiliarityThresholdTest extends CommandLineInterfaceTest {

diff --git a/cli/src/test/java/de/jplag/cli/StoredMatchesTest.java b/cli/src/test/java/de/jplag/cli/StoredMatchesTest.java
@@ -5,7 +5,6 @@
 
 import org.junit.jupiter.api.Test;
 
-import de.jplag.CommandLineArgument;
 import de.jplag.options.JPlagOptions;
 
 class StoredMatchesTest extends CommandLineInterfaceTest {

diff --git a/core/src/main/java/de/jplag/JPlagResult.java b/core/src/main/java/de/jplag/JPlagResult.java
@@ -141,8 +141,7 @@ private int[] calculateDistributionFor(List<JPlagComparison> comparisons, ToDoub
             int index = (int) (similarity * SIMILARITY_DISTRIBUTION_SIZE); // divide similarity by bucket size to find index of correct bucket.
             index = Math.min(index, SIMILARITY_DISTRIBUTION_SIZE - 1);// index is out of bounds when similarity is 1.0. decrease by one to count
                                                                       // towards the highest value bucket
-            similarityDistribution[SIMILARITY_DISTRIBUTION_SIZE - 1 - index]++; // count comparison towards its determined bucket. bucket order is
-            // reversed, so that the highest value bucket has the lowest index
+            similarityDistribution[index]++; // count comparison towards its determined bucket.
         }
         return similarityDistribution;
     }
-Original file line number
+Diff line change
@@ Expand Up / @@ -6,8 +6,6 @@ @@
     import org.junit.jupiter.api.Test;
-    import de.jplag.CommandLineArgument;
     class MinTokenMatchTest extends CommandLineInterfaceTest {
         @Test
@@ Expand Down @@