modify scripts

docker/paperless/plugins/parsers.py

@@ -335,6 +335,11 @@ class RasterisedDocumentParser(DocumentParser):
         os.environ["OMP_THREAD_LIMIT"] = "1"
         VALID_TEXT_LENGTH = 50
 
+        # skip ocr process entirely to save time.
+        self.text = "defautl text"
+        self.log.debug("skipping reading file entirely.")
+        return
+
         if mime_type == "application/pdf":
             text_original = self.extract_text(None, document_path)
             original_has_text = (