Merge pull request #38 from dkpro/refactoring/37-Upgrade-dependencies

#37 - Upgrade dependencies

.github/workflows/maven.yml

@@ -0,0 +1,46 @@
+# This workflow will build a Java project with Maven, and cache/restore any dependencies to improve the workflow execution time
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-java-with-maven
+
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+name: Java CI with Maven
+
+on:
+  push:
+    branches: [ "main", "release/**" ]
+  pull_request:
+    branches: [ "main", "release/**" ]
+
+jobs:
+  build:
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest]
+        jdk: [17]
+
+    runs-on: ${{ matrix.os }}
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+      with:
+        ref: ${{ github.head_ref || github.ref }}
+
+    - name: Set up JDK ${{ matrix.jdk }}
+      uses: actions/setup-java@v4
+      with:
+        java-version: ${{ matrix.jdk }}
+        distribution: 'temurin'
+        cache: maven
+
+    - name: Build with Maven
+      run: mvn --no-transfer-progress -B clean verify --file pom.xml
+
+    # Fails with error message - no idea why...
+    # Optional: Uploads the full dependency graph to GitHub to improve the quality of Dependabot alerts this repository can receive
+    # - name: Update dependency graph
+    #   uses: advanced-security/maven-dependency-submission-action@571e99aab1055c2e71a1e2309b9691de18d6b7d6

dkpro-statistics-agreement/pom.xml

@@ -16,7 +16,9 @@
   See the License for the specific language governing permissions and
   limitations under the License.
 -->
-<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+  xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+  xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
   <modelVersion>4.0.0</modelVersion>
 
   <artifactId>dkpro-statistics-agreement</artifactId>
@@ -35,11 +37,15 @@
       <distribution>repo</distribution>
     </license>
   </licenses>
-  
+
   <dependencies>
     <dependency>
-      <groupId>junit</groupId>
-      <artifactId>junit</artifactId>
+      <groupId>org.slf4j</groupId>
+      <artifactId>slf4j-api</artifactId>
+    </dependency>
+    <dependency>
+      <groupId>org.junit.jupiter</groupId>
+      <artifactId>junit-jupiter-api</artifactId>
       <scope>test</scope>
     </dependency>
     <dependency>

dkpro-statistics-agreement/src/main/java/org/dkpro/statistics/agreement/AgreementMeasure.java

@@ -20,8 +20,8 @@
 /**
  * Default implementation of the {@link IAgreementMeasure} interface providing computational hooks
  * for calculating the observed and the expected agreement. The values for observed and expected
- * agreement are combined using Scott's (1955) {@code (A_O - A_E) / (1.0 - A_E)} formula
- * (where A_O denotes the observed agreement and A_E denotes the expected agreement. See also
+ * agreement are combined using Scott's (1955) {@code (A_O - A_E) / (1.0 - A_E)} formula (where A_O
+ * denotes the observed agreement and A_E denotes the expected agreement. See also
  * {@link DisagreementMeasure} for the analogous definition of a measure based on the observed and
  * expected disagreement.<br>
  * <br>

dkpro-statistics-agreement/src/main/java/org/dkpro/statistics/agreement/AnnotationStudy.java

@@ -32,7 +32,7 @@ public abstract class AnnotationStudy
     implements IAnnotationStudy
 {
     private static final long serialVersionUID = -3596722258510421730L;
-    
+
     protected List<String> raters;
     protected Set<Object> categories;
 

dkpro-statistics-agreement/src/main/java/org/dkpro/statistics/agreement/AnnotationUnit.java

@@ -29,18 +29,18 @@ public class AnnotationUnit
     implements IAnnotationUnit
 {
     private static final long serialVersionUID = 4277733312128063453L;
-    
-    protected int raterIdx;
-    protected Object category;
+
+    protected final int raterIdx;
+    protected final Object category;
 
     /**
      * Initializes the annotation unit with the given category as the annotation by the rater with
      * the specified index.
      */
-    public AnnotationUnit(int raterIdx, final Object category)
+    public AnnotationUnit(int aRaterIdx, final Object aCategory)
     {
-        this.raterIdx = raterIdx;
-        this.category = category;
+        raterIdx = aRaterIdx;
+        category = aCategory;
     }
 
     @Override

dkpro-statistics-agreement/src/main/java/org/dkpro/statistics/agreement/DisagreementMeasure.java

@@ -17,11 +17,16 @@
  */
 package org.dkpro.statistics.agreement;
 
+import java.lang.invoke.MethodHandles;
+
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
 /**
  * Default implementation of the {@link IAgreementMeasure} interface providing computational hooks
  * for calculating the observed and the expected disagreement. The values for observed and expected
- * disagreement are combined using Krippendorff's (1980) {@code 1 - (D_O / D_E)} formula
- * (where D_O denotes the observed disagreement and D_E denotes the expected disagreement. See also
+ * disagreement are combined using Krippendorff's (1980) {@code 1 - (D_O / D_E)} formula (where D_O
+ * denotes the observed disagreement and D_E denotes the expected disagreement. See also
  * {@link AgreementMeasure} for the analogous definition of a measure based on the observed and
  * expected agreement.<br>
  * <br>
@@ -38,26 +43,31 @@
 public abstract class DisagreementMeasure
     implements IAgreementMeasure
 {
+    private static final Logger LOG = LoggerFactory.getLogger(MethodHandles.lookup().lookupClass());
+
     /**
      * Calculates the inter-rater agreement for the annotation study that was passed to the class
      * constructor and the currently assigned distance function.
      * 
-     * @throws NullPointerException if the study is null.
+     * @throws NullPointerException
+     *             if the study is null.
      * 
-     * @throws ArithmeticException if the study does not contain any item or the number of raters is
-     * smaller than 2.
+     * @throws ArithmeticException
+     *             if the study does not contain any item or the number of raters is smaller than 2.
      */
     @Override
     public double calculateAgreement()
     {
         double D_O = calculateObservedDisagreement();
         double D_E = calculateExpectedDisagreement();
+
+        LOG.trace("Disagreement -- observed: {} -- expected: {}", D_O, D_E);
+
         if (D_O == D_E) {
             return 0.0;
         }
-        else {
-            return 1.0 - (D_O / D_E);
-        }
+
+        return 1.0 - (D_O / D_E);
     }
 
     protected abstract double calculateObservedDisagreement();

dkpro-statistics-agreement/src/main/java/org/dkpro/statistics/agreement/IAnnotationItem.java

@@ -33,7 +33,8 @@
  * @see IAnnotationStudy
  * @author Christian M. Meyer
  */
-public interface IAnnotationItem extends Serializable
+public interface IAnnotationItem
+    extends Serializable
 {
 
 }

dkpro-statistics-agreement/src/main/java/org/dkpro/statistics/agreement/IAnnotationStudy.java

@@ -40,7 +40,7 @@ public interface IAnnotationStudy
 
     /** Returns the number of raters participating in this study. */
     int getRaterCount();
-    
+
     int findRater(final String name);
 
     // -- Categories --
@@ -63,7 +63,10 @@ public interface IAnnotationStudy
      * Returns true if, and only if, the categories defined by the study yield a dichotomy (i.e.,
      * there are exactly two categories).
      */
-    boolean isDichotomous();
+    default boolean isDichotomous()
+    {
+        return getCategoryCount() == 2;
+    }
 
     // -- Units --
 

dkpro-statistics-agreement/src/main/java/org/dkpro/statistics/agreement/IAnnotationUnit.java

@@ -33,15 +33,15 @@ public interface IAnnotationUnit
     extends Serializable
 {
     /**
-     * Returns the index of the rater who coded this unit (in case of a coding study) or defined the
-     * boundaries of this unit (in case of a unitizing study). The first rater has index 0.
+     * @return the index of the rater who coded this unit (in case of a coding study) or defined the
+     *         boundaries of this unit (in case of a unitizing study). The first rater has index 0.
      */
-    public int getRaterIdx();
+    int getRaterIdx();
 
     /**
-     * Returns the category assigned to this unit by one of the raters. The category might be null
-     * if, and only if, the unit represents a missing value (in case of a coding study) or a gap (in
-     * case of a unitizing study).
+     * @return the category assigned to this unit by one of the raters. The category might be null
+     *         if, and only if, the unit represents a missing value (in case of a coding study) or a
+     *         gap (in case of a unitizing study).
      */
-    public Object getCategory();
+    Object getCategory();
 }

dkpro-statistics-agreement/src/main/java/org/dkpro/statistics/agreement/coding/CodingAnnotationItem.java

@@ -36,7 +36,7 @@ public class CodingAnnotationItem
     implements ICodingAnnotationItem
 {
     private static final long serialVersionUID = 3447650373912260846L;
-    
+
     protected List<IAnnotationUnit> units;
     protected int nonNullCount;
 

dkpro-statistics-agreement/src/main/java/org/dkpro/statistics/agreement/coding/CodingAnnotationStudy.java

@@ -45,7 +45,7 @@ public class CodingAnnotationStudy
     implements ICodingAnnotationStudy, Cloneable, Serializable
 {
     private static final long serialVersionUID = -8242222160334337626L;
-    
+
     protected List<ICodingAnnotationItem> items;
 
     /**

dkpro-statistics-agreement/src/main/java/org/dkpro/statistics/agreement/unitizing/IUnitizingAnnotationUnit.java

@@ -34,23 +34,46 @@
 public interface IUnitizingAnnotationUnit
     extends IAnnotationUnit, Comparable<IUnitizingAnnotationUnit>
 {
+    /**
+     * @return the offset of the annotation unit (i.e., the start position of the identified
+     *         segment).
+     * @deprecated Use {@link #getBegin()}
+     */
+    @Deprecated
+    default long getOffset()
+    {
+        return getBegin();
+    }
 
     /**
-     * Returns the offset of the annotation unit (i.e., the start position of the identified
-     * segment).
+     * @return the length of the annotation unit (i.e., the difference between the end and start
+     *         position of the identified segment).
      */
-    public long getOffset();
+    default long getLength()
+    {
+        return getEnd() - getBegin();
+    }
 
     /**
-     * Returns the length of the annotation unit (i.e., the difference between the end and start
-     * position of the identified segment).
+     * @return the right delimiter of the annotation unit (i.e., the end position of the identified
+     *         segment). The method is a shorthand for {@link #getOffset()} + {@link #getLength()}.
+     * @deprecated Use {@link #getEnd()}
      */
-    public long getLength();
+    @Deprecated
+    default long getEndOffset()
+    {
+        return getEnd();
+    }
 
     /**
-     * Returns the right delimiter of the annotation unit (i.e., the end position of the identified
-     * segment). The method is a shorthand for {@link #getOffset()} + {@link #getLength()}.
+     * @return the offset of the annotation unit (i.e., the start position of the identified
+     *         segment).
      */
-    public long getEndOffset();
+    long getBegin();
 
+    /**
+     * @return the right delimiter of the annotation unit (i.e., the end position of the identified
+     *         segment). The method is a shorthand for {@link #getOffset()} + {@link #getLength()}.
+     */
+    long getEnd();
 }

dkpro-statistics-agreement/src/main/java/org/dkpro/statistics/agreement/unitizing/UnitizingAnnotationStudy.java

@@ -41,7 +41,7 @@ public class UnitizingAnnotationStudy
     implements IUnitizingAnnotationStudy, Serializable
 {
     private static final long serialVersionUID = 5877774485360119115L;
-    
+
     protected Set<IUnitizingAnnotationUnit> units;
     protected long begin;
     protected long length;
@@ -129,7 +129,7 @@ public Collection<IUnitizingAnnotationUnit> getUnits()
     {
         return units;
     }
-    
+
     @Override
     public long getUnitCount(int raterIdx)
     {

dkpro-statistics-agreement/src/main/java/org/dkpro/statistics/agreement/unitizing/UnitizingAnnotationUnit.java

@@ -35,21 +35,22 @@ public class UnitizingAnnotationUnit
     implements IUnitizingAnnotationUnit
 {
     private static final long serialVersionUID = -6716379300031576772L;
-    
-    protected long offset;
-    protected long length;
+
+    final protected long offset;
+    final protected long length;
 
     /**
      * Initializes the unit with the given offset and length as well as the category assigned to the
      * unit by the rater with the specified index. Normally, the method
      * {@link UnitizingAnnotationStudy#addUnit(long, long, int, Object)} should be used to define
      * the annotation units.
      */
-    protected UnitizingAnnotationUnit(long offset, long length, int raterIdx, final Object category)
+    protected UnitizingAnnotationUnit(long aOffset, long aLength, int aRaterIdx,
+            final Object aCategory)
     {
-        super(raterIdx, category);
-        this.offset = offset;
-        this.length = length;
+        super(aRaterIdx, aCategory);
+        offset = aOffset;
+        length = aLength;
     }
 
     @Override
@@ -70,6 +71,16 @@ public long getEndOffset()
         return offset + length;
     }
 
+    public long getBegin()
+    {
+        return getOffset();
+    }
+
+    public long getEnd()
+    {
+        return getEndOffset();
+    }
+
     @Override
     public int compareTo(final IUnitizingAnnotationUnit that)
     {

dkpro-statistics-agreement/src/main/java/org/dkpro/statistics/agreement/visualization/CoincidenceMatrixPrinter.java

@@ -120,7 +120,7 @@ protected void doPrint(final PrintStream out, final ICodingAnnotationStudy study
         out.printf(DIVIDER + DOUBLE_FORMAT, sum);
         out.println();
     }
-/*
+    /*
     public void printPercentage(final PrintStream out, final IItemAnnotationStudy study) {
         //TODO: measure length of cats. maybe cut them.
         Map<Object, Map<Object, Integer>> coincidence = 
@@ -175,5 +175,5 @@ public void printPercentage(final PrintStream out, final IItemAnnotationStudy st
         out.printf(DIVIDER + "%1.3f", sum);
         out.println();
     }
-    */
+     */
 }

dkpro-statistics-agreement/src/main/java/org/dkpro/statistics/agreement/visualization/ContingencyMatrixPrinter.java

@@ -30,7 +30,7 @@
  * of each combination of categories used by two raters. A contigency table
  * is only defined for coding studies with exactly two raters. For the example 
  * by Krippendorff (1980: p. 133), the implementation displays:
- * <pre>     
+ * <pre>
  *     0   1   Σ
  * 0   5   3   8
  * 1   1   1   2