Fix string split mechanism for section tagging

OHNLP · Oct 7, 2024 · be085ec · be085ec
1 parent 8ffc4ea
commit be085ec
Show file tree

Hide file tree

Showing 2 changed files with 13 additions and 8 deletions.
diff --git a/pom.xml b/pom.xml
@@ -6,7 +6,7 @@
 
     <groupId>org.ohnlp.medtagger</groupId>
     <artifactId>medtagger</artifactId>
-    <version>1.0.80</version>
+    <version>1.0.81</version>
     <description>The MedTagger biomedical information extraction pipeline</description>
 
 

diff --git a/src/main/java/org/ohnlp/medtagger/sectag/RulebasedSectionAnnotator.java b/src/main/java/org/ohnlp/medtagger/sectag/RulebasedSectionAnnotator.java
@@ -125,13 +125,18 @@ public void process(JCas jCas) throws AnalysisEngineProcessException {
 	private Segment SecIndicator(Sentence sen, JCas jcas) {
 		String str=sen.getCoveredText();
 		Segment cSeg=null;
-		int pos=str.indexOf(":");
-		String secStr;
-		if(pos < 0 || pos >=100)
-			secStr=str;
-		else {
-			secStr=str.substring(0,pos);
-		}
+		int pos = -1;
+		int colonPos=str.indexOf(":");
+		int senPos = pos= str.indexOf("\n");
+		if (colonPos == -1) {
+			pos = senPos;
+		} else if (senPos == -1) {
+			pos = colonPos;
+		} else {
+			pos = Math.min(senPos, colonPos);
+		};
+		if(pos < 0 || pos >=100) return null;
+		String secStr = str.substring(0, pos);
 		if(sectionMap.containsKey(lvg.getNorm(secStr))){
 			sen.removeFromIndexes(jcas);
 		    String cSegment=sectionMap.get(lvg.getNorm(secStr));