OPENNLP-385: Add unit tests for OpenNLP UIMA component (#748)

- adapts and reactivates AnnotatorsInitializationTest by T. Teofili, originally provided in JIRA issue, to execute for all xml descriptors - converts AnnotatorsInitializationTest to several integration tests executed via Maven failsafe plugin - adds Parser.xml to 'test-descriptors' - adds more test classes - configures Maven resource filtering for xml 'test-descriptors' - moves 'ci' profile to upper-level pom.xml for re-use in opennlp-uima component - adds simplelogger.properties to test resources to avoid log spam during build caused by internal UIMA logger config
apache · Feb 14, 2025 · 9d1dfa9 · 9d1dfa9
1 parent ac73a5c
commit 9d1dfa9
Show file tree

Hide file tree

Showing 60 changed files with 2,165 additions and 235 deletions.
diff --git a/opennlp-tools/pom.xml b/opennlp-tools/pom.xml
@@ -136,25 +136,12 @@
       <plugin>
         <groupId>org.apache.maven.plugins</groupId>
         <artifactId>maven-failsafe-plugin</artifactId>
-        <version>${maven.failsafe.plugin}</version>
-        <configuration>
-          <argLine>-DOPENNLP_DOWNLOAD_HOME=${opennlp.download.home}</argLine>
-        </configuration>
       </plugin>
+
     </plugins>
   </build>
 
-  <properties>
-    <opennlp.download.home>${user.home}</opennlp.download.home>
-  </properties>
-
   <profiles>
-    <profile>
-      <id>ci</id>
-      <properties>
-        <opennlp.download.home>${project.build.directory}</opennlp.download.home>
-      </properties>
-    </profile>
     <profile>
       <id>jmh</id>
       <dependencies>

diff --git a/opennlp-uima/pom.xml b/opennlp-uima/pom.xml
@@ -79,6 +79,12 @@
 			<scope>test</scope>
 		</dependency>
 
+		<dependency>
+			<groupId>org.junit.jupiter</groupId>
+			<artifactId>junit-jupiter-params</artifactId>
+			<scope>test</scope>
+		</dependency>
+
 		<dependency>
 			<groupId>org.slf4j</groupId>
 			<artifactId>slf4j-simple</artifactId>
@@ -87,11 +93,35 @@
 	</dependencies>
 
 	<build>
+		<testResources>
+			<testResource>
+				<directory>src/test/resources</directory>
+				<filtering>true</filtering>
+			</testResource>
+		</testResources>
+
 		<plugins>
+			<plugin>
+				<groupId>org.apache.maven.plugins</groupId>
+				<artifactId>maven-surefire-plugin</artifactId>
+				<configuration>
+					<argLine>-Xmx2048m -DOPENNLP_DOWNLOAD_HOME=${opennlp.download.home}</argLine>
+					<forkCount>${opennlp.forkCount}</forkCount>
+					<failIfNoSpecifiedTests>false</failIfNoSpecifiedTests>
+					<excludes>
+						<exclude>**/*IT.java</exclude>
+					</excludes>
+				</configuration>
+			</plugin>
+
+			<plugin>
+				<groupId>org.apache.maven.plugins</groupId>
+				<artifactId>maven-failsafe-plugin</artifactId>
+			</plugin>
+
 			<plugin>
 				<groupId>org.apache.maven.plugins</groupId>
 				<artifactId>maven-dependency-plugin</artifactId>
-				<version>3.8.1</version>
 				<executions>
 					<execution>
 						<id>copy-dependencies</id>
@@ -100,7 +130,7 @@
 							<goal>copy-dependencies</goal>
 						</goals>
 						<configuration>
-							<excludeScope>provided</excludeScope>
+							<includeScope>runtime</includeScope>
 							<stripVersion>true</stripVersion>
 						</configuration>
 					</execution>

diff --git a/opennlp-uima/src/main/java/opennlp/uima/chunker/Chunker.java b/opennlp-uima/src/main/java/opennlp/uima/chunker/Chunker.java
@@ -109,8 +109,8 @@ public void initialize(UimaContext context)
 
     Logger mLogger = context.getLogger();
 
-    if (mLogger.isLoggable(Level.INFO)) {
-      mLogger.log(Level.INFO, "Initializing the OpenNLP Chunker annotator.");
+    if (mLogger.isLoggable(Level.DEBUG)) {
+      mLogger.log(Level.DEBUG, "Initializing the OpenNLP Chunker annotator.");
     }
 
     ChunkerModel model;
@@ -172,8 +172,7 @@ public void process(CAS tcas) {
 
     String[] tokens = new String[tokenAnnotationIndex.size()];
     String[] pos = new String[tokenAnnotationIndex.size()];
-    AnnotationFS[] tokenAnnotations = new AnnotationFS[tokenAnnotationIndex
-        .size()];
+    AnnotationFS[] tokenAnnotations = new AnnotationFS[tokenAnnotationIndex.size()];
 
     int index = 0;
 

diff --git a/opennlp-uima/src/main/java/opennlp/uima/doccat/AbstractDocumentCategorizer.java b/opennlp-uima/src/main/java/opennlp/uima/doccat/AbstractDocumentCategorizer.java
@@ -50,6 +50,7 @@ abstract class AbstractDocumentCategorizer extends CasAnnotator_ImplBase {
 
   private Type mTokenType;
 
+  @Override
   public void initialize(UimaContext context)
       throws ResourceInitializationException {
 
@@ -59,8 +60,8 @@ public void initialize(UimaContext context)
 
     Logger mLogger = context.getLogger();
 
-    if (mLogger.isLoggable(Level.INFO)) {
-      mLogger.log(Level.INFO, "Initializing the OpenNLP Categorizer.");
+    if (mLogger.isLoggable(Level.DEBUG)) {
+      mLogger.log(Level.DEBUG, "Initializing the OpenNLP Categorizer.");
     }
 
     DoccatModel model;

diff --git a/opennlp-uima/src/main/java/opennlp/uima/doccat/DocumentCategorizer.java b/opennlp-uima/src/main/java/opennlp/uima/doccat/DocumentCategorizer.java
@@ -36,7 +36,7 @@ public class DocumentCategorizer extends AbstractDocumentCategorizer {
 
   private Feature mCategoryFeature;
 
-
+  @Override
   public void typeSystemInit(TypeSystem typeSystem)
       throws AnalysisEngineProcessException {
 
@@ -55,7 +55,7 @@ protected void setBestCategory(CAS tcas, String bestCategory) {
 
     AnnotationFS categoryAnnotation;
 
-    if (categoryIndex.size() > 0) {
+    if (!categoryIndex.isEmpty()) {
       categoryAnnotation = categoryIndex.iterator().next();
     } else {
       categoryAnnotation = tcas.createAnnotation(mCategoryType, 0,

diff --git a/opennlp-uima/src/main/java/opennlp/uima/namefind/AbstractNameFinder.java b/opennlp-uima/src/main/java/opennlp/uima/namefind/AbstractNameFinder.java
@@ -77,8 +77,8 @@ public final void initialize(UimaContext context) throws ResourceInitializationE
 
     mLogger = context.getLogger();
 
-    if (mLogger.isLoggable(Level.INFO)) {
-      mLogger.log(Level.INFO, "Initializing the " + name + ".");
+    if (mLogger.isLoggable(Level.DEBUG)) {
+      mLogger.log(Level.DEBUG, "Initializing the " + name + ".");
     }
 
     isRemoveExistingAnnotations = AnnotatorUtil.getOptionalBooleanParameter(
@@ -133,21 +133,19 @@ public void typeSystemInit(TypeSystem typeSystem)
       mNameTypeMapping = Collections.unmodifiableMap(nameTypeMap);
     }
 
-    if (mNameType == null && mNameTypeMapping.size() == 0) {
+    if (mNameType == null && mNameTypeMapping.isEmpty()) {
       throw new AnalysisEngineProcessException(
           new Exception("No name type or valid name type mapping configured!"));
     }
   }
 
-  protected void postProcessAnnotations(Span[] detectedNames,
-      AnnotationFS[] nameAnnotations) {
-  }
+  protected abstract void postProcessAnnotations(Span[] detectedNames,
+      AnnotationFS[] nameAnnotations);
 
   /**
    * Called if the current document is completely processed.
    */
-  protected void documentDone(CAS cas) {
-  }
+  protected abstract void documentDone(CAS cas);
 
   protected abstract Span[] find(CAS cas, String[] tokens);
 

diff --git a/opennlp-uima/src/main/java/opennlp/uima/namefind/DictionaryNameFinder.java b/opennlp-uima/src/main/java/opennlp/uima/namefind/DictionaryNameFinder.java
@@ -18,9 +18,9 @@
 package opennlp.uima.namefind;
 
 import java.io.IOException;
-import java.io.InputStream;
 
 import org.apache.uima.cas.CAS;
+import org.apache.uima.cas.text.AnnotationFS;
 import org.apache.uima.resource.ResourceAccessException;
 import org.apache.uima.resource.ResourceInitializationException;
 
@@ -66,24 +66,31 @@ public void initialize() throws ResourceInitializationException {
         String modelName = AnnotatorUtil.getRequiredStringParameter(context,
             UimaUtil.DICTIONARY_PARAMETER);
 
-        InputStream inModel = AnnotatorUtil.getResourceAsStream(context,
-            modelName);
-
-        nameFinderDictionary = new Dictionary(inModel);
+        nameFinderDictionary = new Dictionary(
+                AnnotatorUtil.getResourceAsStream(context, modelName));
 
       } catch (IOException ie) {
         throw new ResourceInitializationException(
             ExceptionMessages.MESSAGE_CATALOG,
             ExceptionMessages.IO_ERROR_DICTIONARY_READING,
             new Object[] {ie.getMessage()});
       }
-
     }
 
     mNameFinder = new opennlp.tools.namefind.DictionaryNameFinder(
         nameFinderDictionary);
   }
 
+  @Override
+  protected void postProcessAnnotations(Span[] detectedNames, AnnotationFS[] nameAnnotations) {
+    // nothing to do
+  }
+
+  @Override
+  protected void documentDone(CAS cas) {
+    // nothing to do
+  }
+
   @Override
   protected Span[] find(CAS cas, String[] tokens) {
     return mNameFinder.find(tokens);

diff --git a/opennlp-uima/src/main/java/opennlp/uima/namefind/NameFinder.java b/opennlp-uima/src/main/java/opennlp/uima/namefind/NameFinder.java
@@ -113,8 +113,7 @@ public NameFinder() {
    * Note: Do all initialization in this method, do not use the constructor.
    */
   @Override
-  public void initialize()
-      throws ResourceInitializationException {
+  public void initialize() throws ResourceInitializationException {
 
     super.initialize();
 
@@ -136,13 +135,12 @@ public void initialize()
    * Initializes the type system.
    */
   @Override
-  public void typeSystemInit(TypeSystem typeSystem)
-      throws AnalysisEngineProcessException {
+  public void typeSystemInit(TypeSystem typeSystem) throws AnalysisEngineProcessException {
 
     super.typeSystemInit(typeSystem);
 
     probabilityFeature = AnnotatorUtil.getOptionalFeatureParameter(context, mNameType,
-        UimaUtil.PROBABILITY_FEATURE_PARAMETER, CAS.TYPE_NAME_DOUBLE);
+            UimaUtil.PROBABILITY_FEATURE_PARAMETER, CAS.TYPE_NAME_DOUBLE);
 
     documentConfidenceType = AnnotatorUtil.getOptionalTypeParameter(context, typeSystem,
         "opennlp.uima.DocumentConfidenceType");
@@ -160,7 +158,6 @@ protected Span[] find(CAS cas, String[] tokens) {
     Span[] names = mNameFinder.find(tokens);
 
     double[] probs = mNameFinder.probs();
-
     for (double prob : probs) {
       documentConfidence.add(prob);
     }

diff --git a/opennlp-uima/src/main/java/opennlp/uima/normalizer/Normalizer.java b/opennlp-uima/src/main/java/opennlp/uima/normalizer/Normalizer.java
@@ -43,7 +43,7 @@
 
 /**
  * The Normalizer tries the structure annotations. The structured value
- * is than assigned to a field of the annotation.
+ * is then assigned to a field of the annotation.
  * <p>
  * The process depends on the
  * <p>
@@ -108,6 +108,7 @@ private Normalizer() {
    *
    * @implNote Do all initialization in this method, do not use the constructor.
    */
+  @Override
   public void initialize(UimaContext context) throws ResourceInitializationException {
 
     super.initialize(context);
@@ -116,8 +117,8 @@ public void initialize(UimaContext context) throws ResourceInitializationExcepti
 
     mLogger = context.getLogger();
 
-    if (mLogger.isLoggable(Level.INFO)) {
-      mLogger.log(Level.INFO, "Initializing the OpenNLP Normalizer annotator.");
+    if (mLogger.isLoggable(Level.DEBUG)) {
+      mLogger.log(Level.DEBUG, "Initializing the OpenNLP Normalizer annotator.");
     }
 
     try {
@@ -141,6 +142,7 @@ public void initialize(UimaContext context) throws ResourceInitializationExcepti
    * Initializes the type system.
    * @param typeSystem type system to initialize
    */
+  @Override
   public void typeSystemInit(TypeSystem typeSystem)
       throws AnalysisEngineProcessException {
 
@@ -165,6 +167,7 @@ public void typeSystemInit(TypeSystem typeSystem)
     }
   }
 
+  @Override
   public void process(CAS tcas) {
 
     FSIndex<AnnotationFS> sentenceIndex = tcas.getAnnotationIndex(mNameType);
@@ -203,8 +206,8 @@ public void process(CAS tcas) {
         try {
           number = NumberUtil.parse(text, language);
         } catch (ParseException e) {
-          if (mLogger.isLoggable(Level.INFO)) {
-            mLogger.log(Level.INFO, "Invalid number format: " + text);
+          if (mLogger.isLoggable(Level.WARN)) {
+            mLogger.log(Level.WARN, "Invalid number format: " + text);
           }
           continue;
         }

diff --git a/opennlp-uima/src/main/java/opennlp/uima/normalizer/StringDictionary.java b/opennlp-uima/src/main/java/opennlp/uima/normalizer/StringDictionary.java
@@ -43,6 +43,7 @@ public StringDictionary() {
    * @throws IOException Thrown if IO errors occurred.
    */
   public StringDictionary(InputStream in) throws IOException {
+    this();
     DictionaryEntryPersistor.create(in, entry -> {
       String valueString = entry.attributes().getValue("value");
       put(entry.tokens(), valueString);

diff --git a/opennlp-uima/src/main/java/opennlp/uima/parser/Parser.java b/opennlp-uima/src/main/java/opennlp/uima/parser/Parser.java
@@ -145,6 +145,7 @@ public void typeSystemInit(TypeSystem typeSystem)
   /**
    * Performs parsing on the given {@link CAS} object.
    */
+  @Override
   public void process(CAS cas) {
     FSIndex<AnnotationFS> sentences = cas.getAnnotationIndex(mSentenceType);
 

diff --git a/opennlp-uima/src/main/java/opennlp/uima/sentdetect/AbstractSentenceDetector.java b/opennlp-uima/src/main/java/opennlp/uima/sentdetect/AbstractSentenceDetector.java
@@ -57,8 +57,8 @@ public void initialize(UimaContext context)
 
     logger = context.getLogger();
 
-    if (logger.isLoggable(Level.INFO)) {
-      logger.log(Level.INFO, "Initializing the OpenNLP Sentence annotator.");
+    if (logger.isLoggable(Level.DEBUG)) {
+      logger.log(Level.DEBUG, "Initializing the OpenNLP Sentence annotator.");
     }
 
     isRemoveExistingAnnotations = AnnotatorUtil.getOptionalBooleanParameter(

diff --git a/opennlp-uima/src/main/java/opennlp/uima/sentdetect/SentenceDetector.java b/opennlp-uima/src/main/java/opennlp/uima/sentdetect/SentenceDetector.java
@@ -76,6 +76,7 @@ public SentenceDetector() {
    * <p>
    * Note: Do all initialization in this method, do not use the constructor.
    */
+  @Override
   public void initialize(UimaContext context)
       throws ResourceInitializationException {
 
@@ -98,14 +99,14 @@ public void initialize(UimaContext context)
   /**
    * Initializes the type system.
    */
+  @Override
   public void typeSystemInit(TypeSystem typeSystem)
       throws AnalysisEngineProcessException {
 
     super.typeSystemInit(typeSystem);
 
     probabilityFeature = AnnotatorUtil.getOptionalFeatureParameter(context,
-        sentenceType, UimaUtil.PROBABILITY_FEATURE_PARAMETER,
-        CAS.TYPE_NAME_DOUBLE);
+        sentenceType, UimaUtil.PROBABILITY_FEATURE_PARAMETER, CAS.TYPE_NAME_DOUBLE);
   }
 
   @Override
@@ -128,6 +129,7 @@ protected void postProcessAnnotations(AnnotationFS[] sentences) {
   /**
    * Releases allocated resources.
    */
+  @Override
   public void destroy() {
     // dereference model to allow garbage collection
     sentenceDetector = null;

diff --git a/opennlp-uima/src/main/java/opennlp/uima/sentdetect/SentenceModelResourceImpl.java b/opennlp-uima/src/main/java/opennlp/uima/sentdetect/SentenceModelResourceImpl.java
@@ -26,6 +26,7 @@
 public class SentenceModelResourceImpl extends AbstractModelResource<SentenceModel>
     implements SentenceModelResource {
 
+  @Override
   public SentenceModel getModel() {
     return model;
   }