Merge pull request #1049 from shawntanzk/doi-wikiversioned-extractor

Add DOI and WikipediaVersioned Extractor

protege-editor-owl/src/main/java/org/protege/editor/owl/ui/renderer/DOILinkExtractor.java

@@ -0,0 +1,20 @@
+package org.protege.editor.owl.ui.renderer;
+
+import java.util.regex.Pattern;
+
+/**
+ * A RegEx based link extractor for the 'DOI:' prefix. 
+ * 25 Mar 2022
+ */
+public class DOILinkExtractor {
+
+    public static final Pattern DOI_ID_PATTERN = Pattern.compile("DOI:\\s*([^\\s]+)", Pattern.CASE_INSENSITIVE);
+
+    public static final String DOI_URL_BASE = "https://doi.org/";
+
+    public static final String replacementString = DOI_URL_BASE + "$1";
+
+    public static RegExBasedLinkExtractor createExtractor() {
+        return new RegExBasedLinkExtractor("DOI", DOI_ID_PATTERN, replacementString);
+    }
+}

protege-editor-owl/src/main/java/org/protege/editor/owl/ui/renderer/OMIMLinkExtractor.java

@@ -0,0 +1,20 @@
+package org.protege.editor.owl.ui.renderer;
+
+import java.util.regex.Pattern;
+
+/**
+ * A RegEx based link extractor for the 'OMIM:' prefix. 
+ * 25 Mar 2022
+ */
+public class OMIMLinkExtractor {
+
+    public static final Pattern OMIM_ID_PATTERN = Pattern.compile("OMIM:\\s*(\\d+)", Pattern.CASE_INSENSITIVE);
+
+    public static final String OMIM_URL_BASE = "https://omim.org/entry/";
+
+    public static final String replacementString = OMIM_URL_BASE + "$1";
+
+    public static RegExBasedLinkExtractor createExtractor() {
+        return new RegExBasedLinkExtractor("OMIM", OMIM_ID_PATTERN, replacementString);
+    }
+}

protege-editor-owl/src/main/java/org/protege/editor/owl/ui/renderer/OMIMPSLinkExtractor.java

@@ -0,0 +1,20 @@
+package org.protege.editor.owl.ui.renderer;
+
+import java.util.regex.Pattern;
+
+/**
+ * A RegEx based link extractor for the 'OMIMPS:' prefix. 
+ * 25 Mar 2022
+ */
+public class OMIMPSLinkExtractor {
+
+    public static final Pattern OMIMPS_ID_PATTERN = Pattern.compile("OMIMPS:\\s*(\\d+)", Pattern.CASE_INSENSITIVE);
+
+    public static final String OMIMPS_URL_BASE = "https://www.omim.org/phenotypicSeries/";
+
+    public static final String replacementString = OMIMPS_URL_BASE + "$1";
+
+    public static RegExBasedLinkExtractor createExtractor() {
+        return new RegExBasedLinkExtractor("OMIMPS", OMIMPS_ID_PATTERN, replacementString);
+    }
+}

protege-editor-owl/src/main/java/org/protege/editor/owl/ui/renderer/ORCIDLinkExtractor.java

@@ -0,0 +1,20 @@
+package org.protege.editor.owl.ui.renderer;
+
+import java.util.regex.Pattern;
+
+/**
+ * A RegEx based link extractor for the 'ORCID:' prefix. 
+ * 25 Mar 2022
+ */
+public class ORCIDLinkExtractor {
+
+    public static final Pattern ORCID_ID_PATTERN = Pattern.compile("ORCID:\\s*([^\\s]+)", Pattern.CASE_INSENSITIVE);
+
+    public static final String ORCID_URL_BASE = "https://orcid.org/";
+
+    public static final String replacementString = ORCID_URL_BASE + "$1";
+
+    public static RegExBasedLinkExtractor createExtractor() {
+        return new RegExBasedLinkExtractor("ORCID", ORCID_ID_PATTERN, replacementString);
+    }
+}

protege-editor-owl/src/main/java/org/protege/editor/owl/ui/renderer/OWLAnnotationCellRenderer2.java

@@ -54,8 +54,14 @@ public class OWLAnnotationCellRenderer2 extends PageCellRenderer {
 
     private final List<LinkExtractor> linkExtractors = Arrays.asList(
             PubMedLinkExtractor.createExtractor(),
+            OrphanetLinkExtractor.createExtractor(),
+            OMIMLinkExtractor.createExtractor(),
+            OMIMPSLinkExtractor.createExtractor(),
             ISBN10LinkExtractor.createExtractor(),
             WikipediaLinkExtractor.createExtractor(),
+            WikipediaVersionedLinkExtractor.createExtractor(),
+            DOILinkExtractor.createExtractor(),
+            ORCIDLinkExtractor.createExtractor(),
             IdentifiersDotOrgLinkExtractor.createExtractor(),
             OboFoundryLinkExtractor.createLinkExtractor());
 

protege-editor-owl/src/main/java/org/protege/editor/owl/ui/renderer/OrphanetLinkExtractor.java

@@ -0,0 +1,20 @@
+package org.protege.editor.owl.ui.renderer;
+
+import java.util.regex.Pattern;
+
+/**
+ * A RegEx based link extractor for the 'Orphanet:' prefix. 
+ * 25 Mar 2022
+ */
+public class OrphanetLinkExtractor {
+
+    public static final Pattern ORPHANET_ID_PATTERN = Pattern.compile("Orphanet:\\s*(\\d+)", Pattern.CASE_INSENSITIVE);
+
+    public static final String ORPHANET_URL_BASE = "https://www.orpha.net/consor/www/cgi-bin/OC_Exp.php?Expert=";
+
+    public static final String replacementString = ORPHANET_URL_BASE + "$1";
+
+    public static RegExBasedLinkExtractor createExtractor() {
+        return new RegExBasedLinkExtractor("Orphanet", ORPHANET_ID_PATTERN, replacementString);
+    }
+}

protege-editor-owl/src/main/java/org/protege/editor/owl/ui/renderer/WikipediaVersionedLinkExtractor.java

@@ -0,0 +1,20 @@
+package org.protege.editor.owl.ui.renderer;
+
+import java.util.regex.Pattern;
+
+/**
+ * A RegEx based link extractor for the 'WikipediaVersioned:' prefix. 
+ * 25 Mar 2022
+ */
+public class WikipediaVersionedLinkExtractor {
+
+    private static final Pattern WIKI_VERSIONED_PATTERN = Pattern.compile("WikipediaVersioned:([^\\s]+)", Pattern.CASE_INSENSITIVE);
+
+    public static final String WIKI_VERSIONED_URL_BASE = "https://wikipedia.org/wiki/index.php?title=";
+
+    public static final String WIKI_VERSIONED_REPLACEMENT = WIKI_VERSIONED_URL_BASE + "$1";
+
+    public static RegExBasedLinkExtractor createExtractor() {
+        return new RegExBasedLinkExtractor("WikipediaVersioned", WIKI_VERSIONED_PATTERN, WIKI_VERSIONED_REPLACEMENT);
+    }
+}

protege-editor-owl/src/test/java/org/protege/editor/owl/ui/renderer/DOILinkExtractor_TestCase.java

@@ -0,0 +1,65 @@
+package org.protege.editor.owl.ui.renderer;
+
+import org.junit.Before;
+import org.junit.Test;
+
+import java.util.Optional;
+
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.Is.is;
+
+/**
+ * Unit tests for the DOI link extraction.
+ * 25 Mar 2022
+ */
+public class DOILinkExtractor_TestCase {
+
+    private RegExBasedLinkExtractor extractor;
+
+    @Before
+    public void setUp()  {
+        extractor = DOILinkExtractor.createExtractor();
+    }
+
+    @Test
+    public void shouldExtractId() {
+        String id = "DOI:10.1101/2021.10.10.463703";
+        Optional<String> extractedId = extractor.extractLinkLiteral(id);
+        assertThat(extractedId, is(Optional.of(DOILinkExtractor.DOI_URL_BASE + "10.1101/2021.10.10.463703")));
+    }
+
+    @Test
+    public void shouldIgnoreCase_AllLowerCase() {
+        String id = "doi:10.1101/2021.10.10.463703";
+        Optional<String> extractedId = extractor.extractLinkLiteral(id);
+        assertThat(extractedId, is(Optional.of(DOILinkExtractor.DOI_URL_BASE + "10.1101/2021.10.10.463703")));
+    }
+
+    @Test
+    public void shouldIgnoreCase_MixedCase() {
+        String id = "DoI:10.1101/2021.10.10.463703";
+        Optional<String> extractedId = extractor.extractLinkLiteral(id);
+        assertThat(extractedId, is(Optional.of(DOILinkExtractor.DOI_URL_BASE + "10.1101/2021.10.10.463703")));
+    }
+
+    @Test
+    public void shouldNotExtractIdInCaseOfMissingPrefix() {
+        String id = "10.1101/2021.10.10.463703";
+        Optional<String> extractedId = extractor.extractLinkLiteral(id);
+        assertThat(extractedId.isPresent(), is(false));
+    }
+
+    @Test
+    public void shouldAllowWhiteSpaceAfterPrefix() {
+        String id = "doi: 10.1101/2021.10.10.463703";
+        Optional<String> extractedId = extractor.extractLinkLiteral(id);
+        assertThat(extractedId, is(Optional.of(DOILinkExtractor.DOI_URL_BASE + "10.1101/2021.10.10.463703")));
+    }
+
+    @Test
+    public void shouldNotExtractIdInCaseOfWhiteSpace() {
+        String id = "doi:123 456";
+        Optional<String> extractedId = extractor.extractLinkLiteral(id);
+        assertThat(extractedId.isPresent(), is(false));
+    }
+}

protege-editor-owl/src/test/java/org/protege/editor/owl/ui/renderer/OMIMLinkExtractor_TestCase.java

@@ -0,0 +1,65 @@
+package org.protege.editor.owl.ui.renderer;
+
+import org.junit.Before;
+import org.junit.Test;
+
+import java.util.Optional;
+
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.Is.is;
+
+/**
+ * Unit tests for the OMIM link extraction.
+ * 25 Mar 2022
+ */
+public class OMIMLinkExtractor_TestCase {
+
+    private RegExBasedLinkExtractor extractor;
+
+    @Before
+    public void setUp()  {
+        extractor = OMIMLinkExtractor.createExtractor();
+    }
+
+    @Test
+    public void shouldExtractId() {
+        String id = "OMIM:300376";
+        Optional<String> extractedId = extractor.extractLinkLiteral(id);
+        assertThat(extractedId, is(Optional.of(OMIMLinkExtractor.OMIM_URL_BASE + "300376")));
+    }
+
+    @Test
+    public void shouldIgnoreCase_AllLowerCase() {
+        String id = "omim:300376";
+        Optional<String> extractedId = extractor.extractLinkLiteral(id);
+        assertThat(extractedId, is(Optional.of(OMIMLinkExtractor.OMIM_URL_BASE + "300376")));
+    }
+
+    @Test
+    public void shouldIgnoreCase_MixedCase() {
+        String id = "OMim:300376";
+        Optional<String> extractedId = extractor.extractLinkLiteral(id);
+        assertThat(extractedId, is(Optional.of(OMIMLinkExtractor.OMIM_URL_BASE + "300376")));
+    }
+
+    @Test
+    public void shouldNotExtractIdInCaseOfMissingPrefix() {
+        String id = "300376";
+        Optional<String> extractedId = extractor.extractLinkLiteral(id);
+        assertThat(extractedId.isPresent(), is(false));
+    }
+
+    @Test
+    public void shouldAllowWhiteSpaceAfterPrefix() {
+        String id = "OMIM: 300376";
+        Optional<String> extractedId = extractor.extractLinkLiteral(id);
+        assertThat(extractedId, is(Optional.of(OMIMLinkExtractor.OMIM_URL_BASE + "300376")));
+    }
+
+    @Test
+    public void shouldNotExtractIdInCaseOfWhiteSpace() {
+        String id = "OMIM:300 376";
+        Optional<String> extractedId = extractor.extractLinkLiteral(id);
+        assertThat(extractedId.isPresent(), is(false));
+    }
+}

protege-editor-owl/src/test/java/org/protege/editor/owl/ui/renderer/OMIMPSLinkExtractor_TestCase.java

@@ -0,0 +1,65 @@
+package org.protege.editor.owl.ui.renderer;
+
+import org.junit.Before;
+import org.junit.Test;
+
+import java.util.Optional;
+
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.Is.is;
+
+/**
+ * Unit tests for the OMIMPS link extraction.
+ * 25 Mar 2022
+ */
+public class OMIMPSLinkExtractor_TestCase {
+
+    private RegExBasedLinkExtractor extractor;
+
+    @Before
+    public void setUp()  {
+        extractor = OMIMPSLinkExtractor.createExtractor();
+    }
+
+    @Test
+    public void shouldExtractId() {
+        String id = "OMIMPS:236100";
+        Optional<String> extractedId = extractor.extractLinkLiteral(id);
+        assertThat(extractedId, is(Optional.of(OMIMPSLinkExtractor.OMIMPS_URL_BASE + "236100")));
+    }
+
+    @Test
+    public void shouldIgnoreCase_AllLowerCase() {
+        String id = "omimps:236100";
+        Optional<String> extractedId = extractor.extractLinkLiteral(id);
+        assertThat(extractedId, is(Optional.of(OMIMPSLinkExtractor.OMIMPS_URL_BASE + "236100")));
+    }
+
+    @Test
+    public void shouldIgnoreCase_MixedCase() {
+        String id = "OmimPS:236100";
+        Optional<String> extractedId = extractor.extractLinkLiteral(id);
+        assertThat(extractedId, is(Optional.of(OMIMPSLinkExtractor.OMIMPS_URL_BASE + "236100")));
+    }
+
+    @Test
+    public void shouldNotExtractIdInCaseOfMissingPrefix() {
+        String id = "236100";
+        Optional<String> extractedId = extractor.extractLinkLiteral(id);
+        assertThat(extractedId.isPresent(), is(false));
+    }
+
+    @Test
+    public void shouldAllowWhiteSpaceAfterPrefix() {
+        String id = "OMIMPS: 236100";
+        Optional<String> extractedId = extractor.extractLinkLiteral(id);
+        assertThat(extractedId, is(Optional.of(OMIMPSLinkExtractor.OMIMPS_URL_BASE + "236100")));
+    }
+
+    @Test
+    public void shouldNotExtractIdInCaseOfWhiteSpace() {
+        String id = "OMIMPS:236 100";
+        Optional<String> extractedId = extractor.extractLinkLiteral(id);
+        assertThat(extractedId.isPresent(), is(false));
+    }
+}