added parsing of SSSOM to eval client

documentation/release_notes.md

@@ -17,6 +17,7 @@
 - [Wikidata tests are fixed](https://github.com/dwslab/melt/commit/ae824d9#diff-471d5bfa39673c940c5c7c2f7450ffe61545c052efd6ccf85080e0e589cbd7c9) because Wikidata entry for `EU` changed 
 - [Testcasevalidation is more memory friendly](https://github.com/dwslab/melt/commit/fe6915287637895c3fee63eec2e28934218ba0bd)
 - fixed macro F1 computation (it is **not** the harmonic mean of macro averaged precision and recall but now the macro averaged f1 scores)
+- track `Popconference[0-100]` works now because this track has no reference alignments (see [commit 1f9b601](https://github.com/dwslab/melt/commit/1f9b60102c14131a97228f6d84cf84ffe29df024) )
 
 **New Tracks**
 - [pgx Track](http://oaei.ontologymatching.org/2023/pharmacogenomics/index.html)

examples/SSSOMMatcher/pom.xml

@@ -0,0 +1,113 @@
+<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>
+    <groupId>de.uni-mannheim.informatik.dws.melt</groupId>
+    <artifactId>SSSOMMatcher</artifactId><!-- id used as matcher id in descriptor file of seals package -->
+    <packaging>jar</packaging>
+    <version>1.0</version><!-- version appearing in descriptor file of seals package -->
+    <description>simple SSSOM Matcher</description><!-- description appearing in descriptor file of seals package -->
+
+    <properties>
+        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
+        <maven.compiler.source>1.8</maven.compiler.source>
+        <maven.compiler.target>1.8</maven.compiler.target>
+
+        <oaei.mainClass>de.uni_mannheim.informatik.dws.melt.demomatcher.SSSOMMatcher</oaei.mainClass><!-- mandatory: this class has to implement IOntologyMatchingToolBridge -->
+
+        <oaei.copyright>(C) Mannheim, 2019</oaei.copyright> <!--optional copyright appearing in the seals descriptor file -->
+        <oaei.license>GNU Lesser General Public License 2.1 or above</oaei.license> <!--optional license appearing in the seals descriptor file -->
+
+        <matching.version>3.4-SNAPSHOT</matching.version> <!-- version for all matching related packages -->
+    </properties>
+
+    <!-- Accessing the resources:
+    - all files in "oaei-resources" folder are stored in the current working directory and can be accessed with 
+          Files.readAllLines(Paths.get("oaei-resources", "configuration_oaei.txt"));
+    - all files in "src/main/resources" folder are compiled to the resulting jar and can be accessed with
+          getClass().getClassLoader().getResourceAsStream("configuration_jar.txt");
+    -->
+
+    <dependencies>
+        <!-- dependency for jena matchers - for other matchers you can replace it with artifactId: matching-base -->
+        <dependency>
+            <groupId>de.uni-mannheim.informatik.dws.melt</groupId>
+            <artifactId>matching-jena</artifactId>
+            <version>${matching.version}</version>
+        </dependency>
+
+        <!-- This dependency is necessary for seals_external. It contains the cli wrapper. -->
+        <dependency>
+            <groupId>de.uni-mannheim.informatik.dws.melt</groupId>
+            <artifactId>receiver-cli</artifactId>
+            <version>${matching.version}</version>
+        </dependency>
+
+        <dependency>
+            <groupId>de.uni-mannheim.informatik.dws.melt</groupId>
+            <artifactId>matching-eval</artifactId>
+            <version>${matching.version}</version>
+            <scope>test</scope>
+            <!-- only in test scope, can only be used when running tests. 
+                 You can also remove the scope but then remove the whole dependency when packaging the matcher.
+                 Otherwise you get a lot of unused dependencies in your matcher.-->
+        </dependency>
+
+        <dependency>
+            <groupId>org.slf4j</groupId>
+            <artifactId>slf4j-log4j12</artifactId>
+            <version>1.7.36</version>
+        </dependency>
+
+
+        <dependency>
+            <groupId>org.junit.jupiter</groupId>
+            <artifactId>junit-jupiter-api</artifactId>
+            <version>5.9.0</version>
+            <scope>test</scope>
+        </dependency>
+
+        <dependency>
+            <groupId>org.junit.jupiter</groupId>
+            <artifactId>junit-jupiter-engine</artifactId>
+            <version>5.9.0</version>
+            <scope>test</scope>
+        </dependency>
+
+    </dependencies>
+
+    <build>
+        <plugins>
+
+            <!-- the following plugin will generate a seals assembly -->
+            <plugin>
+                <artifactId>maven-assembly-plugin</artifactId>
+                <version>3.4.2</version>
+                <dependencies>
+                    <dependency>
+                        <groupId>de.uni-mannheim.informatik.dws.melt</groupId>
+                        <artifactId>matching-assembly</artifactId>
+                        <version>${matching.version}</version>
+                    </dependency>
+                </dependencies>
+                <executions>
+                    <execution>
+                        <phase>package</phase>
+                        <goals><goal>single</goal></goals>
+                        <!-- there exists three descriptors:
+                        1) "seals" - removes all dependencies available in seals client regardless of their version.
+                        2) "seals_all_deps" - adds all dependencies of your project (please note that this can cause problems when using jena for example)
+                        3) "seals_external" - creates a wrapper around the matcher so that no inference with seals happens(the matcher has to log to std err only).-->
+                        <configuration><descriptorRefs><descriptorRef>seals_external</descriptorRef></descriptorRefs></configuration>
+                    </execution>
+                </executions>
+            </plugin>
+
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-surefire-plugin</artifactId>
+                <version>3.0.0-M7</version>
+            </plugin>
+        </plugins>
+    </build>
+
+</project>

examples/SSSOMMatcher/src/main/java/de/uni_mannheim/informatik/dws/melt/demomatcher/SSSOMMatcher.java

@@ -0,0 +1,91 @@
+package de.uni_mannheim.informatik.dws.melt.demomatcher;
+
+import de.uni_mannheim.informatik.dws.melt.matching_base.MatcherURL;
+import de.uni_mannheim.informatik.dws.melt.matching_jena.OntologyCacheJena;
+import de.uni_mannheim.informatik.dws.melt.yet_another_alignment_api.Alignment;
+import de.uni_mannheim.informatik.dws.melt.yet_another_alignment_api.DefaultExtensions.SSSOM;
+import de.uni_mannheim.informatik.dws.melt.yet_another_alignment_api.SSSOMSerializer;
+import java.io.File;
+import java.net.URL;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.Set;
+import org.apache.jena.ontology.OntModel;
+import org.apache.jena.ontology.OntResource;
+import org.apache.jena.rdf.model.NodeIterator;
+import org.apache.jena.rdf.model.RDFNode;
+import org.apache.jena.util.iterator.ExtendedIterator;
+import org.apache.jena.vocabulary.RDFS;
+
+/**
+ * A very simple SSSOM matcher.
+ */
+public class SSSOMMatcher extends MatcherURL {
+
+    @Override
+    public URL match(URL sourceURL, URL targetURL, URL inputAlignment) throws Exception {
+
+        OntModel source = OntologyCacheJena.get(sourceURL, OntologyCacheJena.DEFAULT_JENA_ONT_MODEL_SPEC);
+        OntModel target = OntologyCacheJena.get(targetURL, OntologyCacheJena.DEFAULT_JENA_ONT_MODEL_SPEC);
+
+        Alignment alignment = new Alignment();
+        matchResources(source.listClasses(), target.listClasses(), alignment);//match only classes
+
+        File alignmentFile = File.createTempFile("alignment", ".rdf");
+
+        alignment.addExtensionValue(SSSOM.MAPPING_SET_TITLE, "A simple SSSOM mapping.");
+
+        SSSOMSerializer.serialize(alignment, alignmentFile);
+        return alignmentFile.toURI().toURL();
+    }
+
+
+    private void matchResources(ExtendedIterator<? extends OntResource> sourceResources, ExtendedIterator<? extends OntResource> targetResources, Alignment alignment) {
+        HashMap<String, String> text2URI = new HashMap<>();
+        while (sourceResources.hasNext()) {
+            OntResource source = sourceResources.next();
+            for(String s : getStringRepresentation(source))
+                text2URI.put(s, source.getURI());
+        }
+        while (targetResources.hasNext()) {
+            OntResource target = targetResources.next();
+            for(String s : getStringRepresentation(target)){
+                String sourceURI = text2URI.get(s);
+                if(sourceURI != null){
+                    alignment.add(sourceURI, target.getURI());
+                }
+            }
+        }
+    }
+
+    private Set<String> getStringRepresentation(OntResource resource) {
+        Set<String> texts = new HashSet<>();
+        String uri = resource.getURI();
+        if(uri == null)
+            return texts;
+        NodeIterator labelIterator = resource.listPropertyValues(RDFS.label);
+        while(labelIterator.hasNext()){
+            RDFNode label = labelIterator.next();
+            if(label.isLiteral()){
+                texts.add(label.asLiteral().getLexicalForm().toLowerCase());
+            }
+        }
+        String fragment = getUriFragment(resource.getURI());
+        if(fragment != null)
+            texts.add(fragment.toLowerCase().replace("_", " "));
+        return texts;
+    }
+
+    public static String getUriFragment(String uri){
+        int lastIndex = uri.lastIndexOf("#");
+        if(lastIndex >= 0){
+            return uri.substring(lastIndex + 1);
+        }
+        lastIndex = uri.lastIndexOf("/");
+        if(lastIndex >= 0){
+            return uri.substring(lastIndex + 1);
+        }
+        return null;
+    }
+}
+

examples/SSSOMMatcher/src/main/resources/log4j.properties

@@ -0,0 +1,8 @@
+# Root logger option
+log4j.rootLogger=INFO, stdout
+
+# Direct log messages to stdout
+log4j.appender.stdout=org.apache.log4j.ConsoleAppender
+log4j.appender.stdout.Target=System.out
+log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
+log4j.appender.stdout.layout.ConversionPattern=%d{yyyy-MM-dd HH:mm:ss} %-5p [%-30.30t] %-4L in %-20.20c{1} - %m%n

examples/SSSOMMatcher/src/test/java/de/uni_mannheim/informatik/dws/melt/demomatcher/EvaluateMatcher.java

@@ -0,0 +1,18 @@
+package de.uni_mannheim.informatik.dws.melt.demomatcher;
+
+import de.uni_mannheim.informatik.dws.melt.matching_data.TrackRepository;
+import de.uni_mannheim.informatik.dws.melt.matching_eval.ExecutionResult;
+import de.uni_mannheim.informatik.dws.melt.matching_eval.ExecutionResultSet;
+import de.uni_mannheim.informatik.dws.melt.matching_eval.Executor;
+import org.junit.jupiter.api.Test;
+
+
+public class EvaluateMatcher {
+
+    @Test
+    public void evalSimpleMatcher(){        
+        ExecutionResultSet result = Executor.run(TrackRepository.Anatomy.Default, new SSSOMMatcher());
+        ExecutionResult r = result.iterator().next();
+        System.out.print(r.getSystemAlignment());
+    }
+}

examples/SSSOMMatcher/src/test/java/de/uni_mannheim/informatik/dws/melt/demomatcher/TestPackage.java

@@ -0,0 +1,26 @@
+package de.uni_mannheim.informatik.dws.melt.demomatcher;
+
+import de.uni_mannheim.informatik.dws.melt.matching_base.external.seals.MatcherSeals;
+import de.uni_mannheim.informatik.dws.melt.matching_data.TrackRepository;
+import de.uni_mannheim.informatik.dws.melt.matching_eval.ExecutionResult;
+import de.uni_mannheim.informatik.dws.melt.matching_eval.Executor;
+import java.io.File;
+import java.nio.file.Paths;
+
+/**
+ * This class tests the generated seals package.
+ * The exit code is important because it used in the continuouns integration 
+ * pipeline (CI) in github to test the package.
+ */
+public class TestPackage {
+    public static void main(String[] args) {        
+        // cache seals client in CI (thus the location .m2 because it is cache already)
+        File sealsClient = Paths.get(System.getProperty("user.home"), ".m2", "seals_client.jar").toFile(); 
+        MatcherSeals sealsMatcher = new MatcherSeals(new File("target/simpleSealsMatcher-1.0-seals_external.zip"), sealsClient);
+        ExecutionResult result = Executor.runSingle(TrackRepository.Anatomy.Default.getFirstTestCase(), sealsMatcher);
+
+        if(result.getSystemAlignment().isEmpty()){
+            System.exit(1);
+        }
+    }
+}

matching-eval-client/src/main/java/de/uni_mannheim/informatik/dws/melt/matching_eval_client/Main.java

@@ -51,7 +51,7 @@ public static void main(String[] args) {
         // help option
         if (cmd.hasOption(HELP_OPTION_STRING)) {
             HelpFormatter helpFormatter = new HelpFormatter();
-            helpFormatter.printHelp("ant", options);
+            helpFormatter.printHelp("java -jar matching-eval-client-latest.jar", options);
             return;
         }
 

matching-eval/src/main/java/de/uni_mannheim/informatik/dws/melt/matching_eval/ExecutionResult.java

@@ -8,12 +8,15 @@
 import de.uni_mannheim.informatik.dws.melt.matching_eval.refinement.Refiner;
 import de.uni_mannheim.informatik.dws.melt.yet_another_alignment_api.Alignment;
 import de.uni_mannheim.informatik.dws.melt.yet_another_alignment_api.AlignmentParser;
+import de.uni_mannheim.informatik.dws.melt.yet_another_alignment_api.SSSOMFormatException;
+import de.uni_mannheim.informatik.dws.melt.yet_another_alignment_api.SSSOMParser;
 import java.io.*;
 import java.net.URL;
 import java.util.Comparator;
 import java.util.HashSet;
 import java.util.Objects;
 import java.util.Set;
+import java.util.logging.Level;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 import org.xml.sax.SAXException;
@@ -152,14 +155,22 @@ private static Set<Refiner> addRefinementToNewSet(Set<Refiner> initialRefinement
      * @param url url which represents the alignment
      * @return Parsed alignment.
      */
-    private static Alignment silentlyParseAlignment(URL url){
+    private static Alignment silentlyParseAlignment(URL url) {
         try {
             return AlignmentParser.parse(url);
         }catch(FileNotFoundException ex){
             LOGGER.error("The system alignment file with URL {} does not exist. Returning empty system alignment.", url);
-        }
-        catch (SAXException | IOException | NullPointerException ex) {
-            LOGGER.error("The system alignment given by following URL could not be parsed: " + url.toString(), ex);
+        }catch(IOException | NullPointerException ex){
+            LOGGER.error("The system alignment given by following URL could not be parsed with Alignment Format: " + url.toString(), ex);
+        }catch(SAXException ex){
+            try {
+                return SSSOMParser.parse(AlignmentParser.getInputStreamFromURL(url));
+            } catch (IOException ex1) {
+                LOGGER.error("The system alignment given by following URL could not be parsed with SSSOM: " + url.toString(), ex);
+            } catch (SSSOMFormatException ex1) {
+                LOGGER.error("The system alignment given by URL {} could not be parsed as alignemntFormat and SSSOM: error from alignment: {} error from SSSOM: {} ",
+                        url.toString(), ex.getMessage(), ex1.getMessage());
+            }
         }
         return new Alignment();
     }

yet-another-alignment-api/src/main/java/de/uni_mannheim/informatik/dws/melt/yet_another_alignment_api/Alignment.java

@@ -560,7 +560,7 @@ public Alignment cut(double threshold){
         Alignment m = new Alignment(this, false);
         ResultSet<Correspondence> result = this.retrieve(QueryFactory.greaterThanOrEqualTo(Correspondence.CONFIDENCE, threshold));
         for(Correspondence c : result){
-            m.add(c);
+            m.add(new Correspondence(c));
         }
         return m;
     }

yet-another-alignment-api/src/main/java/de/uni_mannheim/informatik/dws/melt/yet_another_alignment_api/SSSOMFormatException.java

@@ -0,0 +1,19 @@
+package de.uni_mannheim.informatik.dws.melt.yet_another_alignment_api;
+
+/**
+ * Exception representing a error when data does not fit to SSSOM schema
+ */
+public class SSSOMFormatException extends Exception {
+
+    private static final long serialVersionUID = 5451825154955645498L;
+
+
+    public SSSOMFormatException(String msg) {
+        super(msg);
+    }
+
+    public SSSOMFormatException(String msg, Throwable inner) {
+        super(msg, inner);
+    }
+
+}

yet-another-alignment-api/src/main/java/de/uni_mannheim/informatik/dws/melt/yet_another_alignment_api/SSSOMParser.java

@@ -34,7 +34,7 @@ public class SSSOMParser {
 
     private static final Logger LOGGER = LoggerFactory.getLogger(SSSOMParser.class);
 
-    public static Alignment parse(InputStream s) throws IOException {
+    public static Alignment parse(InputStream s) throws IOException, SSSOMFormatException {
 
         Alignment a = new Alignment();        
         BufferedReader reader = new BufferedReader(new InputStreamReader(s, StandardCharsets.UTF_8));
@@ -69,6 +69,10 @@ public static Alignment parse(InputStream s) throws IOException {
         } // else no metadata found and skipping it
 
         try(CSVParser csvParser = CSVFormat.DEFAULT.withDelimiter('\t').withFirstRecordAsHeader().parse(reader)){
+            if(csvParser.getHeaderNames().contains("subject_id") == false || csvParser.getHeaderNames().contains("object_id") == false){
+                throw new SSSOMFormatException("SSSOM header does not contain subject_id and/or object_id");
+            }
+
             Set<String> usedKeys = new HashSet<>(Arrays.asList("subject_id", "object_id", "predicate_id", "confidence"));
             for (CSVRecord record : csvParser) {
                 String source;

yet-another-alignment-api/src/test/java/de/uni_mannheim/informatik/dws/melt/yet_another_alignment_api/SSSOMParserTest.java

@@ -11,7 +11,7 @@
 class SSSOMParserTest {
 
     @Test
-    public void SSSOMParserTest() throws IOException{
+    public void SSSOMParserTest() throws IOException, SSSOMFormatException{
         InputStream i = this.getClass().getClassLoader().getResourceAsStream("mp_hp_mgi_all.sssom.tsv");
         Alignment a = SSSOMParser.parse(i);
 
@@ -44,4 +44,13 @@ public void SSSOMParserTest() throws IOException{
         assertEquals(LocalDate.parse("2022-09-02"), mappingDate);
     }
 
+
+    @Test
+    public void SSSOMParserWithInvalidInput() throws IOException{
+        InputStream i = this.getClass().getClassLoader().getResourceAsStream("LogMap-cmt-conference.rdf");
+        assertThrows(SSSOMFormatException.class, ()->{
+            Alignment a = SSSOMParser.parse(i);
+        });
+    }
+
 }