Output sentence IDs too

OHNLP · Feb 15, 2023 · 05d00dd · 05d00dd
1 parent d1815f9
commit 05d00dd
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 1 deletion.
diff --git a/pom.xml b/pom.xml
@@ -6,7 +6,7 @@
 
     <groupId>org.ohnlp.medtagger</groupId>
     <artifactId>medtagger</artifactId>
-    <version>1.0.52</version>
+    <version>1.0.53</version>
     <description>The MedTagger biomedical information extraction pipeline</description>
 
 

diff --git a/src/main/java/org/ohnlp/medtagger/backbone/MedTaggerBackboneTransform.java b/src/main/java/org/ohnlp/medtagger/backbone/MedTaggerBackboneTransform.java
@@ -82,6 +82,7 @@ public Schema calculateOutputSchema(Schema schema) {
         fields.add(Schema.Field.of("status", Schema.FieldType.STRING));
         fields.add(Schema.Field.of("offset", Schema.FieldType.INT32));
         fields.add(Schema.Field.of("semgroups", Schema.FieldType.STRING).withNullable(true));
+        fields.add(Schema.Field.of("sentid", Schema.FieldType.STRING).withNullable(true));
         this.outputSchema = Schema.of(fields.toArray(new Schema.Field[0]));
         return this.outputSchema;
     }
@@ -287,6 +288,7 @@ private static List<Object> toRowObjects(
             ret.add(cm.getStatus());
             ret.add(cm.getBegin());
             ret.add(cm.getSemGroup());
+            ret.add(cm.getSentence().getId());
             return ret;
         }
     }