fix document split bug

Signed-off-by: Tim Schopf <tim.schopf@t-online.de>
TimSchopf · May 2, 2024 · 9267fdd · 9267fdd
1 parent 5e28116
commit 9267fdd
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/keyphrase_vectorizers/keyphrase_vectorizer_mixin.py b/keyphrase_vectorizers/keyphrase_vectorizer_mixin.py
@@ -442,7 +442,7 @@ def _get_pos_keyphrases(self, document_list: List[str], stop_words: Union[str, L
         stop_words_list.add(doc_delimiter)
 
         # split processed documents by delimiter
-        processed_docs = list(filter(None, [doc.strip() for doc in processed_docs.split(doc_delimiter)]))
+        processed_docs = [doc.strip() for doc in processed_docs.split(doc_delimiter)][1:]
 
         if extract_keyphrases:
             # extract keyphrases that match the NLTK RegexpParser filter