folia2stam: do not include leading whitespace in token/structure offsets

proycon · Mar 19, 2024 · 406f279 · 406f279
1 parent 1f7d6d7
commit 406f279
Showing 1 changed file with 2 additions and 0 deletions.
diff --git a/foliatools/folia2stam.py b/foliatools/folia2stam.py
@@ -89,8 +89,10 @@ def convert_tokens(doc: folia.Document, annotationstore: stam.AnnotationStore, *
                if delimiters:
                    delimiters.sort(key= lambda x: len(x), reverse=True)
                    text += delimiters[0]
+                   textstart += len(delimiters[0])
                elif prevword.space:
                    text += " "
+                   textstart += 1
         try:
             text += word.text()
         except folia.NoSuchText: