Merge branch 'master' into 2.0.x

* master: #186 - Change artifactId to "dkpro-core-XXX" #1299 - Update to CoreNLP 3.9.2 #1337 - Connl2012 writer uses WordSense, but does not declare it #1299 - Update to CoreNLP 3.9.2 No issue. Fixed JavaDoc error. #1340 - Upgrade dependencies (1.11.0) #1358 - Improve error messages in TSV3 #1357 - Upgrade to ICU4J 64.2 #1340 - Upgrade dependencies (1.11.0) #1343 - Segmenter for Chinese #1343 - Segmenter for Chinese #1343 - Segmenter for Chinese #1343 - Segmenter for Chinese #1343 - Segmenter for Chinese #1340 - Upgrade dependencies % Conflicts: % dkpro-core-decompounding-asl/src/test/java/org/dkpro/core/decompounding/uima/annotator/CompoundAnnotatorTest.java % dkpro-core-io-lxf-asl/src/main/java/org/dkpro/core/io/lxf/internal/DKPro2Lxf.java
dkpro · May 31, 2019 · e4c4f5c · e4c4f5c
2 parents 751bcb3 + 70cfbb5
commit e4c4f5c
Show file tree

Hide file tree

Showing 33 changed files with 653 additions and 202 deletions.
diff --git a/dkpro-core-api-datasets-asl/pom.xml b/dkpro-core-api-datasets-asl/pom.xml
@@ -70,7 +70,7 @@
     <dependency>
       <groupId>com.github.junrar</groupId>
       <artifactId>junrar</artifactId>
-      <version>0.7</version>
+      <version>4.0.0</version>
       <exclusions>
         <exclusion>
           <groupId>org.apache.commons</groupId>

diff --git a/dkpro-core-api-resources-asl/pom.xml b/dkpro-core-api-resources-asl/pom.xml
@@ -96,8 +96,8 @@
       <scope>test</scope>
     </dependency>
     <dependency>
-      <groupId>org.hamcrest</groupId>
-      <artifactId>hamcrest-core</artifactId>
+      <groupId>org.assertj</groupId>
+      <artifactId>assertj-core</artifactId>
       <scope>test</scope>
     </dependency>
   </dependencies>

diff --git a/...-resources-asl/src/main/java/org/dkpro/core/api/resources/ResourceObjectProviderBase.java b/...-resources-asl/src/main/java/org/dkpro/core/api/resources/ResourceObjectProviderBase.java
@@ -142,6 +142,7 @@ public abstract class ResourceObjectProviderBase<M>
      * resolved when {@link #configure()} is called. (optional)
      */
     public static final String GROUP_ID = "groupId";
+    public static final String COMPONENT_GROUP_ID = "componentGroupId";
 
     /**
      * The artifact ID of the Maven artifact containing a resource. Variables in the location are
@@ -212,6 +213,7 @@ public abstract class ResourceObjectProviderBase<M>
     protected void init()
     {
         setDefault(GROUP_ID, "de.tudarmstadt.ukp.dkpro.core");
+        setDefault(COMPONENT_GROUP_ID, "org.dkpro.core");
         setDefault(ARTIFACT_URI,
                 "mvn:${" + GROUP_ID + "}:${" + ARTIFACT_ID + "}:${" + VERSION + "}");
     }
@@ -374,7 +376,7 @@ public void applyAutoOverrides(Object aObject)
         }
     }
 
-    protected List<URL> getPomUrlsForClass(String aModelGroup, String aModelArtifact,
+    protected List<URL> getPomUrlsForClass(String aComponentGroupId, String aModelArtifactId,
             Class<?> aClass)
         throws IOException
     {
@@ -418,7 +420,7 @@ protected List<URL> getPomUrlsForClass(String aModelGroup, String aModelArtifact
             Matcher matcher = pattern.matcher(base);
             if (matcher.matches()) {
                 String artifactIdAndVersion = matcher.group("ID");
-                String pomPattern = base + "META-INF/maven/" + aModelGroup + "/"
+                String pomPattern = base + "META-INF/maven/" + aComponentGroupId + "/"
                         + artifactIdAndVersion + "/pom.xml";
                 lookupPatterns.add(pomPattern);
                 ResourcePatternResolver resolver = new PathMatchingResourcePatternResolver();
@@ -434,9 +436,9 @@ protected List<URL> getPomUrlsForClass(String aModelGroup, String aModelArtifact
         // models from the StanfordNLP module).
         if (urls.isEmpty()) {
             // This is the default strategy supposed to look in the JAR
-            String moduleArtifactId = aModelArtifact.split("-")[0];
-            String pomPattern = base + "META-INF/maven/" + aModelGroup + "/" + moduleArtifactId +
-                    "*/pom.xml";
+            String moduleArtifactId = aModelArtifactId.split("-")[0];
+            String pomPattern = base + "META-INF/maven/" + aComponentGroupId + "/"
+                    + moduleArtifactId + "*/pom.xml";
             lookupPatterns.add(pomPattern);
             ResourcePatternResolver resolver = new PathMatchingResourcePatternResolver();
             Resource[] resources = resolver.getResources(pomPattern);
@@ -468,11 +470,11 @@ protected List<URL> getPomUrlsForClass(String aModelGroup, String aModelArtifact
      *             the POM, or if no context object was set.
      * @return the version of the required model.
      */
-    protected String getModelVersionFromMavenPom(String aModelGroup, String aModelArtifact,
-            Class<?> aClass)
+    protected String getModelVersionFromMavenPom(String aComponentGroupId, String aModelGroupId,
+            String aModelArtifactId, Class<?> aClass)
         throws IOException
     {
-        List<URL> urls = getPomUrlsForClass(aModelGroup, aModelArtifact, contextClass);
+        List<URL> urls = getPomUrlsForClass(aComponentGroupId, aModelArtifactId, contextClass);
 
         for (URL pomUrl : urls) {
             // Parse the POM
@@ -492,8 +494,8 @@ protected String getModelVersionFromMavenPom(String aModelGroup, String aModelAr
                 List<Dependency> deps = model.getDependencyManagement().getDependencies();
                 for (Dependency dep : deps) {
                     if (
-                            StringUtils.equals(dep.getGroupId(), aModelGroup) && 
-                            StringUtils.equals(dep.getArtifactId(), aModelArtifact)
+                            StringUtils.equals(dep.getGroupId(), aModelGroupId) && 
+                            StringUtils.equals(dep.getArtifactId(), aModelArtifactId)
                     ) {
                         return dep.getVersion();
                     }
@@ -790,12 +792,22 @@ private Properties resolveDependency(Properties aProps)
                 resolved.getProperty(ARTIFACT_URI, "").contains("${" + VERSION + "}") && 
                 isNull(resolved.getProperty(VERSION))
         ) {
-            String groupId = pph.replacePlaceholders(aProps.getProperty(GROUP_ID), resolved);
+            String modelGroupId = pph.replacePlaceholders(aProps.getProperty(GROUP_ID), resolved);
+            String componentGroupId;
+
+            if (aProps.getProperty(COMPONENT_GROUP_ID) != null) {
+                componentGroupId = pph.replacePlaceholders(aProps.getProperty(COMPONENT_GROUP_ID),
+                        resolved);
+            }
+            else {
+                componentGroupId = modelGroupId;
+            }
+
             String artifactId = pph.replacePlaceholders(aProps.getProperty(ARTIFACT_ID), resolved);
             try {
                 // If the version is to be auto-detected, then we must have a groupId and artifactId
-                resolved.put(VERSION,
-                        getModelVersionFromMavenPom(groupId, artifactId, contextClass));
+                resolved.put(VERSION, getModelVersionFromMavenPom(componentGroupId, modelGroupId,
+                        artifactId, contextClass));
             }
             catch (Throwable e) {
                 log.error("Unable to obtain version from POM", e);

diff --git a/...-core-api-resources-asl/src/test/java/org/dkpro/core/api/resources/ResourceUtilsTest.java b/...-core-api-resources-asl/src/test/java/org/dkpro/core/api/resources/ResourceUtilsTest.java
@@ -18,9 +18,8 @@
 package org.dkpro.core.api.resources;
 
 import static java.util.Arrays.asList;
-import static org.hamcrest.CoreMatchers.is;
+import static org.assertj.core.api.Assertions.assertThat;
 import static org.junit.Assert.assertEquals;
-import static org.junit.Assert.assertThat;
 import static org.junit.Assert.assertTrue;
 
 import java.io.File;
@@ -103,13 +102,13 @@ public void testGetUrlAsExecutable()
         URL url = new URL("jar:file:src/test/resources/testfiles.zip!/testfiles/"
                 + "FileSetCollectionReaderBase.class");
         File file = ResourceUtils.getUrlAsExecutable(url, false);
-        assertThat(file.getName().endsWith("temp"), is(true));
+
+        assertThat(file.getName()).endsWith("temp");
 
         URL url2 = new URL("jar:file:src/test/resources/testfiles.zip!/testfiles/"
                 + "ResourceCollectionReaderBase.class");
         file = ResourceUtils.getUrlAsExecutable(url2, true);
-        assertThat(file.getName().endsWith("temp"), is(true));
-
+
+        assertThat(file.getName()).endsWith("temp");
     }
-
 }
diff --git a/dkpro-core-api-segmentation-asl/pom.xml b/dkpro-core-api-segmentation-asl/pom.xml
@@ -56,8 +56,8 @@
       <scope>test</scope>
     </dependency>
     <dependency>
-      <groupId>org.hamcrest</groupId>
-      <artifactId>hamcrest-core</artifactId>
+      <groupId>org.assertj</groupId>
+      <artifactId>assertj-core</artifactId>
       <scope>test</scope>
     </dependency>
   </dependencies>

diff --git a/...core-api-segmentation-asl/src/test/java/org/dkpro/core/api/segmentation/CompoundTest.java b/...core-api-segmentation-asl/src/test/java/org/dkpro/core/api/segmentation/CompoundTest.java
@@ -17,8 +17,11 @@
  */
 package org.dkpro.core.api.segmentation;
 
-import static org.hamcrest.CoreMatchers.is;
-import static org.junit.Assert.assertThat;
+import static de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Compound.CompoundSplitLevel.ALL;
+import static de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Compound.CompoundSplitLevel.HIGHEST;
+import static de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Compound.CompoundSplitLevel.LOWEST;
+import static de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Compound.CompoundSplitLevel.NONE;
+import static org.assertj.core.api.Assertions.assertThat;
 
 import java.util.ArrayList;
 import java.util.List;
@@ -33,13 +36,11 @@
 import org.junit.Test;
 
 import de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Compound;
-import de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Compound.CompoundSplitLevel;
 import de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.CompoundPart;
 import de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Split;
 
 public class CompoundTest
 {
-
     private Compound compound;
 
     @Before
@@ -66,62 +67,39 @@ public void setUpCompound() throws UIMAException
         compound.setSplits(FSCollectionFactory.createFSArray(jcas, splits));
         compound.addToIndexes();
         jcasBuilder.close();
-
     }
 
     @Test
     public void testAll() throws UIMAException
     {
-
-        final String[] splitsList = new String[] { "getränk", "automat", "auto", "mat" };
-        assertThat(coveredTextArrayFromAnnotations(
-                compound.getSplitsWithoutMorpheme(CompoundSplitLevel.ALL)), is(splitsList));
-
+        assertThat(compound.getSplitsWithoutMorpheme(ALL))
+                .extracting(Annotation::getCoveredText)
+                .containsExactly("getränk", "automat", "auto", "mat");
     }
 
     @Test
     public void testLowest() throws UIMAException
     {
-
-        final String[] splitsList = new String[] { "getränk", "auto", "mat" };
-        assertThat(
-                coveredTextArrayFromAnnotations(
-                        compound.getSplitsWithoutMorpheme(CompoundSplitLevel.LOWEST)),
-                is(splitsList));
+        assertThat(compound.getSplitsWithoutMorpheme(LOWEST))
+                .extracting(Annotation::getCoveredText)
+                .containsExactly("getränk", "auto", "mat");
 
     }
 
     @Test
     public void testHighest() throws UIMAException
     {
-
-        final String[] splitsList = new String[] { "getränk", "automat" };
-        assertThat(
-                coveredTextArrayFromAnnotations(
-                        compound.getSplitsWithoutMorpheme(CompoundSplitLevel.HIGHEST)),
-                is(splitsList));
+        assertThat(compound.getSplitsWithoutMorpheme(HIGHEST))
+                .extracting(Annotation::getCoveredText)
+                .containsExactly("getränk", "automat");
 
     }
 
     @Test
     public void testNone() throws UIMAException
     {
-
-        final String[] splitsList = new String[] {};
-        assertThat(
-                coveredTextArrayFromAnnotations(
-                        compound.getSplitsWithoutMorpheme(CompoundSplitLevel.NONE)),
-                is(splitsList));
-
-    }
-
-    public <T extends Annotation> String[] coveredTextArrayFromAnnotations(final T[] annotations)
-    {
-        final List<String> list = new ArrayList<String>();
-        for (T annotation : annotations) {
-            list.add(annotation.getCoveredText());
-        }
-        return list.toArray(new String[list.size()]);
+        assertThat(compound.getSplitsWithoutMorpheme(NONE))
+                .extracting(Annotation::getCoveredText)
+                .isEmpty();
     }
-
 }
diff --git a/dkpro-core-asl/pom.xml b/dkpro-core-asl/pom.xml
@@ -620,6 +620,7 @@
     <module>../dkpro-core-ixa-asl</module>
     <module>../dkpro-core-jazzy-asl</module>
     <module>../dkpro-core-jtok-asl</module>
+    <module>../dkpro-core-jieba-asl</module>
     <module>../dkpro-core-languagetool-asl</module>
     <module>../dkpro-core-langdetect-asl</module>
     <module>../dkpro-core-ldweb1t-asl</module>

diff --git a/dkpro-core-corenlp-gpl/pom.xml b/dkpro-core-corenlp-gpl/pom.xml
@@ -33,7 +33,7 @@
   <name>DKPro Core GPL - Stanford CoreNLP Suite (v ${corenlp.version}) (GPL)</name>
   <url>https://dkpro.github.io/dkpro-core/</url>
   <properties>
-    <corenlp.version>3.9.1</corenlp.version>
+    <corenlp.version>3.9.2</corenlp.version>
   </properties>
   <dependencies>
     <dependency>
@@ -178,7 +178,7 @@
       <dependency>
         <groupId>de.tudarmstadt.ukp.dkpro.core</groupId>
         <artifactId>de.tudarmstadt.ukp.dkpro.core.stanfordnlp-model-coref-en-default</artifactId>
-        <version>20180227.1</version>
+        <version>20181005.1</version>
       </dependency>
       <dependency>
         <groupId>de.tudarmstadt.ukp.dkpro.core</groupId>
@@ -358,17 +358,17 @@
       <dependency>
         <groupId>de.tudarmstadt.ukp.dkpro.core</groupId>
         <artifactId>de.tudarmstadt.ukp.dkpro.core.stanfordnlp-model-tagger-en-bidirectional-distsim</artifactId>
-        <version>20140616.1</version>
+        <version>20181002.1</version>
       </dependency>
       <dependency>
         <groupId>de.tudarmstadt.ukp.dkpro.core</groupId>
         <artifactId>de.tudarmstadt.ukp.dkpro.core.stanfordnlp-model-tagger-en-left3words-distsim</artifactId>
-        <version>20140616.1</version>
+        <version>20181002.1</version>
       </dependency>
       <dependency>
         <groupId>de.tudarmstadt.ukp.dkpro.core</groupId>
         <artifactId>de.tudarmstadt.ukp.dkpro.core.stanfordnlp-model-tagger-en-caseless-left3words-distsim</artifactId>
-        <version>20140827.0</version>
+        <version>20181002.0</version>
       </dependency>
       <dependency>
         <groupId>de.tudarmstadt.ukp.dkpro.core</groupId>

diff --git a/...o-core-corenlp-gpl/src/main/java/org/dkpro/core/corenlp/CoreNlpNamedEntityRecognizer.java b/...o-core-corenlp-gpl/src/main/java/org/dkpro/core/corenlp/CoreNlpNamedEntityRecognizer.java
@@ -195,17 +195,6 @@ public class CoreNlpNamedEntityRecognizer
     // on, off, auto
     private boolean useSUTime = false; // = NumberSequenceClassifier.USE_SUTIME_DEFAULT;
 
-//    /**
-//     * Whether to read the default regular expression gazetteer.
-//     * 
-//     * @see edu.stanford.nlp.pipeline.DefaultPaths#DEFAULT_NER_GAZETTE_MAPPING
-//     */
-//    public static final String PARAM_AUGMENT_REGEX_NER = "augmentRegexNER";
-//    @ConfigurationParameter(name = PARAM_AUGMENT_REGEX_NER, mandatory = true, defaultValue = "false")
-    // Commented out since the default gazetter is currently only in the original Stanford model
-    // JARs
-    private boolean augmentRegexNER = false; // = NERClassifierCombiner.APPLY_GAZETTE_PROPERTY;
-
     private boolean verbose = false;
 
     private ModelProviderBase<NERCombinerAnnotator> annotatorProvider;
@@ -318,7 +307,7 @@ protected NERCombinerAnnotator produceResource(URL aUrl) throws IOException
             }
 
             NERClassifierCombiner combiner = new NERClassifierCombiner(applyNumericClassifiers,
-                    useSUTime, augmentRegexNER, classifier);
+                    useSUTime, classifier);
 
             NERCombinerAnnotator annotator = new NERCombinerAnnotator(combiner, verbose,
                     numThreads, maxTime, maxSentenceLength, false, false);

diff --git a/dkpro-core-corenlp-gpl/src/scripts/build.xml b/dkpro-core-corenlp-gpl/src/scripts/build.xml
@@ -27,12 +27,12 @@
     - Upstream versions - meta data versions are maintained per model below 
     -->
   <!-- http://nlp.stanford.edu/software/corenlp.shtml -->
-  <property name="core.arabic.date" value="2018-02-27"/>
-  <property name="core.chinese.date" value="2018-02-27"/>
-  <property name="core.english.date" value="2018-02-27"/>
-  <property name="core.french.date" value="2018-02-27"/>
-  <property name="core.german.date" value="2018-02-27"/>
-  <property name="core.spanish.date" value="2018-02-27"/>
+  <property name="core.arabic.date" value="2018-10-05"/>
+  <property name="core.chinese.date" value="2018-10-05"/>
+  <property name="core.english.date" value="2018-10-05"/>
+  <property name="core.french.date" value="2018-10-05"/>
+  <property name="core.german.date" value="2018-10-05"/>
+  <property name="core.spanish.date" value="2018-10-05"/>
 
   <!-- 
     - Output package configuration

diff --git a/...core-corenlp-gpl/src/test/java/org/dkpro/core/corenlp/CoreNlpCoreferenceResolverTest.java b/...core-corenlp-gpl/src/test/java/org/dkpro/core/corenlp/CoreNlpCoreferenceResolverTest.java
@@ -78,13 +78,14 @@ public void testTriggerReparse()
         JCas jcas = runTest("en", "'Let's go! I want to see the Don', he said.");
 
         String[][] ref = {
-                { "'Let's go" },
-                { "'Let's" },
+                { "'" },
+                { "Let's go" },
+                { "Let's" },
                 { "I" },
                 { "the Don'", "he" } };
 
         String[] pennTree = { 
-                "(ROOT (FRAG (NP (NP ('' ') (NNP Let) (POS 's)) (NN go)) (. !)))", 
+                "(ROOT (S (S (NP (POS ')) (NP (NP (NNP Let) (POS 's)) (NN go))) (. !)))", 
                 "(ROOT (S (S (NP (PRP I)) (VP (VBP want) (S (VP (TO to) (VP (VB see) (NP (DT the) "
                 + "(NX (NNP Don) (POS ')))))))) (, ,) (NP (PRP he)) (VP (VBD said)) (. .)))"
         };

diff --git a/dkpro-core-decompounding-asl/pom.xml b/dkpro-core-decompounding-asl/pom.xml
@@ -115,8 +115,8 @@
       <scope>test</scope>
     </dependency>
     <dependency>
-      <groupId>org.hamcrest</groupId>
-      <artifactId>hamcrest-core</artifactId>
+      <groupId>org.assertj</groupId>
+      <artifactId>assertj-core</artifactId>
       <scope>test</scope>
     </dependency>
     <dependency>