Update easymatcher_worker.py

src/easymatcher_worker.py

@@ -47,9 +47,9 @@ class EasymatcherWorker(nlp_ws.NLPWorker):
                 with open(document_path, "r", encoding="utf-8") as _df:
                     for line in _df:
                         line_data = json.loads(line)
-                        document['text'] = line_data['text']
+                        # document['text'] = line_data['text'] 
                         # document['label'] = []
-                        _f.write(json.dumps(document) + "\n")
+                        _f.write(json.dumps(line_data) + "\n")
         else:
             with open(document_path, "r", encoding="utf-8") as _df:
                 document["text"] = _df.read()
@@ -107,5 +107,7 @@ class EasymatcherWorker(nlp_ws.NLPWorker):
         os.unlink(tmpf.name)
 
         with open(output_path, "w", encoding="utf-8") as _f:
-            for out_document in out_documents:
-                _f.write(json.dumps(out_document) + "\n")
+            for out_document, document in zip(out_documents, documents):
+                # We want to keep content of the original labeled documents
+                document['label'] = out_document['label']
+                _f.write(json.dumps(document) + "\n")