Update GNP Reader version(s) to avoid exception with empty zones.

PMID37632434 has a complete empty abstract section: <AbstractText Label="INTRODUCTION" NlmCategory="BACKGROUND"/> and no text in the abstract at all. That caused an exception when checking for empty text because `getCoveredtext()` failed.
JULIELab · Feb 13, 2024 · 4cd8ff6 · 4cd8ff6
1 parent e75cbd1
commit 4cd8ff6
Show file tree

Hide file tree

Showing 15 changed files with 79 additions and 74 deletions.
diff --git a/jcore-biosem-ae/component.meta b/jcore-biosem-ae/component.meta
@@ -14,7 +14,7 @@
     "maven-artifact": {
         "artifactId": "jcore-biosem-ae",
         "groupId": "de.julielab",
-        "version": "2.6.1"
+        "version": "2.6.2"
     },
     "name": "JCoRe BioSem Event Annotator"
 }
diff --git a/jcore-db-checkpoint-ae/component.meta b/jcore-db-checkpoint-ae/component.meta
@@ -19,7 +19,7 @@
     "maven-artifact": {
         "artifactId": "jcore-db-checkpoint-ae",
         "groupId": "de.julielab",
-        "version": "2.6.1"
+        "version": "2.6.3"
     },
     "name": "JCoRe Database Checkpoint AE"
 }
diff --git a/jcore-db-reader/component.meta b/jcore-db-reader/component.meta
@@ -14,7 +14,7 @@
     "maven-artifact": {
         "artifactId": "jcore-db-reader",
         "groupId": "de.julielab",
-        "version": "2.6.1"
+        "version": "2.6.3"
     },
     "name": "JCoRe Database Reader"
 }
diff --git a/jcore-elasticsearch-consumer/component.meta b/jcore-elasticsearch-consumer/component.meta
@@ -18,7 +18,7 @@
     "maven-artifact": {
         "artifactId": "jcore-elasticsearch-consumer",
         "groupId": "de.julielab",
-        "version": "2.6.1"
+        "version": "2.6.3"
     },
     "name": "JCoRe ElasticSearch Consumer"
 }
diff --git a/jcore-gnormplus-ae/component.meta b/jcore-gnormplus-ae/component.meta
@@ -31,7 +31,7 @@
     "maven-artifact": {
         "artifactId": "jcore-gnormplus-ae",
         "groupId": "de.julielab",
-        "version": "2.6.1"
+        "version": "2.6.8-SNAPSHOT"
     },
     "name": "JCoRe GNormPlus Annotator"
 }
diff --git a/jcore-gnormplus-ae/pom.xml b/jcore-gnormplus-ae/pom.xml
@@ -13,7 +13,7 @@
         <version>2.6.1</version>
     </parent>
 
-    <version>2.6.7</version>
+    <version>2.6.8-SNAPSHOT</version>
 
     <dependencies>
         <dependency>
@@ -24,12 +24,12 @@
         <dependency>
             <groupId>de.julielab</groupId>
             <artifactId>jcore-gnp-bioc-writer</artifactId>
-            <version>2.6.3</version>
+            <version>[2.6.3,2.7)</version>
         </dependency>
         <dependency>
             <groupId>de.julielab</groupId>
             <artifactId>jcore-gnp-bioc-reader</artifactId>
-            <version>2.6.3</version>
+            <version>[2.6.3, 2.7)</version>
         </dependency>
         <dependency>
             <groupId>de.julielab</groupId>

diff --git a/jcore-gnp-bioc-reader/component.meta b/jcore-gnp-bioc-reader/component.meta
@@ -19,7 +19,7 @@
     "maven-artifact": {
         "artifactId": "jcore-gnp-bioc-reader",
         "groupId": "de.julielab",
-        "version": "2.6.1"
+        "version": "2.6.3"
     },
     "name": "JCoRe GNormPlus BioC Reader"
 }
diff --git a/jcore-gnp-bioc-writer/component.meta b/jcore-gnp-bioc-writer/component.meta
@@ -14,7 +14,7 @@
     "maven-artifact": {
         "artifactId": "jcore-gnp-bioc-writer",
         "groupId": "de.julielab",
-        "version": "2.6.1"
+        "version": "2.6.4-SNAPSHOT"
     },
     "name": "JCoRe GNormPlus BioC Writer"
 }
diff --git a/jcore-gnp-bioc-writer/pom.xml b/jcore-gnp-bioc-writer/pom.xml
@@ -12,7 +12,7 @@
         <artifactId>jcore-base</artifactId>
         <version>2.6.1</version>
     </parent>
-    <version>2.6.3</version>
+    <version>2.6.4-SNAPSHOT</version>
     <dependencies>
         <dependency>
             <groupId>ch.qos.logback</groupId>

diff --git a/...e-gnp-bioc-writer/src/main/java/de/julielab/jcore/consumer/gnp/BioCDocumentPopulator.java b/...e-gnp-bioc-writer/src/main/java/de/julielab/jcore/consumer/gnp/BioCDocumentPopulator.java
@@ -34,66 +34,71 @@ public BioCDocument populate(JCas jCas) {
         AnnotationIndex<Zone> zoneIndex = jCas.getAnnotationIndex(Zone.type);
         int annotationId = 0;
         for (Zone z : zoneIndex) {
-            // skip empty zones
-            if (z.getCoveredText().isBlank())
-                continue;
-            BioCPassage p = null;
-            if (z instanceof Title) {
-                Title t = (Title) z;
-                String titleType;
-                String titleTypeString = t.getTitleType();
-                if (titleTypeString == null)
-                    titleTypeString = "other";
-                switch (titleTypeString) {
-                    case "document":
-                        titleType = "title";
-                        break;
-                    case "section":
-                        titleType = "section_title";
-                        break;
-                    case "figure":
-                        titleType = "figure_title";
-                        break;
-                    case "table":
-                        titleType = "table_title";
-                        break;
-                    case "abstractSection":
-                        // abstract sections are part of the AbstractText which is handled below
-                        titleType = "null";
-                        break;
-                    case "other":
-                        titleType = "other_title";
-                        break;
-                    default:
-                        log.debug("Unhandled title type {}", titleTypeString);
-                        titleType = "other_title";
-                        break;
-                }
-                if (titleType != null) {
-                    p = getPassageForAnnotation(t);
-                    p.putInfon("type", titleType);
+            try {
+                // skip empty zones
+                if (z.getEnd() - z.getBegin() <= 0 || z.getCoveredText().isBlank())
+                    continue;
+                BioCPassage p = null;
+                if (z instanceof Title) {
+                    Title t = (Title) z;
+                    String titleType;
+                    String titleTypeString = t.getTitleType();
+                    if (titleTypeString == null)
+                        titleTypeString = "other";
+                    switch (titleTypeString) {
+                        case "document":
+                            titleType = "title";
+                            break;
+                        case "section":
+                            titleType = "section_title";
+                            break;
+                        case "figure":
+                            titleType = "figure_title";
+                            break;
+                        case "table":
+                            titleType = "table_title";
+                            break;
+                        case "abstractSection":
+                            // abstract sections are part of the AbstractText which is handled below
+                            titleType = "null";
+                            break;
+                        case "other":
+                            titleType = "other_title";
+                            break;
+                        default:
+                            log.debug("Unhandled title type {}", titleTypeString);
+                            titleType = "other_title";
+                            break;
+                    }
+                    if (titleType != null) {
+                        p = getPassageForAnnotation(t);
+                        p.putInfon("type", titleType);
+                        doc.addPassage(p);
+                    }
+                } else if (z instanceof AbstractText) {
+                    AbstractText at = (AbstractText) z;
+                    p = getPassageForAnnotation(at);
+                    p.putInfon("type", "abstract");
+                    doc.addPassage(p);
+                } else if (z instanceof Paragraph) {
+                    Paragraph pa = (Paragraph) z;
+                    p = getPassageForAnnotation(pa);
+                    p.putInfon("type", "paragraph");
+                    doc.addPassage(p);
+                } else if (z instanceof Caption) {
+                    Caption c = (Caption) z;
+                    p = getPassageForAnnotation(c);
+                    if (c.getCaptionType() == null)
+                        throw new IllegalArgumentException("The captionType feature is null for " + c);
+                    p.putInfon("type", c.getCaptionType());
                     doc.addPassage(p);
                 }
-            } else if (z instanceof AbstractText) {
-                AbstractText at = (AbstractText) z;
-                p = getPassageForAnnotation(at);
-                p.putInfon("type", "abstract");
-                doc.addPassage(p);
-            } else if (z instanceof Paragraph) {
-                Paragraph pa = (Paragraph) z;
-                p = getPassageForAnnotation(pa);
-                p.putInfon("type", "paragraph");
-                doc.addPassage(p);
-            } else if (z instanceof Caption) {
-                Caption c = (Caption) z;
-                p = getPassageForAnnotation(c);
-                if (c.getCaptionType() == null)
-                    throw new IllegalArgumentException("The captionType feature is null for " + c);
-                p.putInfon("type", c.getCaptionType());
-                doc.addPassage(p);
-            }
-            if (addGenes) {
-                annotationId = addGenesToPassage(jCas, z, p, annotationId);
+                if (addGenes) {
+                    annotationId = addGenesToPassage(jCas, z, p, annotationId);
+                }
+            } catch (Exception e) {
+                log.error("Exception occurred with Zone annotation {}", z);
+                throw e;
             }
         }
         return doc;

diff --git a/jcore-neo4j-relations-consumer/component.meta b/jcore-neo4j-relations-consumer/component.meta
@@ -14,7 +14,7 @@
     "maven-artifact": {
         "artifactId": "jcore-neo4j-relations-consumer",
         "groupId": "de.julielab",
-        "version": "2.6.1"
+        "version": "2.6.2"
     },
     "name": "JCoRe Neo4j Relations Consumer"
 }
diff --git a/jcore-pmc-db-reader/component.meta b/jcore-pmc-db-reader/component.meta
@@ -19,7 +19,7 @@
     "maven-artifact": {
         "artifactId": "jcore-pmc-db-reader",
         "groupId": "de.julielab",
-        "version": "2.6.1"
+        "version": "2.6.3"
     },
     "name": "JCoRe PubMed Central DB Reader"
 }
diff --git a/jcore-xmi-db-reader/component.meta b/jcore-xmi-db-reader/component.meta
@@ -23,7 +23,7 @@
     "maven-artifact": {
         "artifactId": "jcore-xmi-db-reader",
         "groupId": "de.julielab",
-        "version": "2.6.1"
+        "version": "2.6.3"
     },
     "name": "JCoRe XMI Database Reader"
 }
diff --git a/jcore-xmi-db-writer/component.meta b/jcore-xmi-db-writer/component.meta
@@ -14,7 +14,7 @@
     "maven-artifact": {
         "artifactId": "jcore-xmi-db-writer",
         "groupId": "de.julielab",
-        "version": "2.6.1"
+        "version": "2.6.3"
     },
     "name": "JCoRe XMI Database Writer"
 }
diff --git a/jcore-xml-db-reader/component.meta b/jcore-xml-db-reader/component.meta
@@ -14,7 +14,7 @@
     "maven-artifact": {
         "artifactId": "jcore-xml-db-reader",
         "groupId": "de.julielab",
-        "version": "2.6.1"
+        "version": "2.6.3"
     },
     "name": "JCoRe XML Database Reader"
 }