At least partially working for the tesseract parser

src/documents/consumer.py

@@ -420,7 +420,7 @@ class Consumer(LoggingMixin):
 
         document_parser: DocumentParser = parser_class(
             self.logging_group,
-            progress_callback,
+            progress_callback=progress_callback,
         )
 
         self.log.debug(f"Parser: {type(document_parser).__name__}")

src/documents/parsers.py

@@ -125,8 +125,10 @@ def get_parser_class_for_mime_type(mime_type: str) -> Optional[type["DocumentPar
     if not options:
         return None
 
+    best_parser = sorted(options, key=lambda _: _["weight"], reverse=True)[0]
+
     # Return the parser with the highest weight.
-    return sorted(options, key=lambda _: _["weight"], reverse=True)[0]["parser"]
+    return best_parser["parser"]
 
 
 def run_convert(
@@ -318,6 +320,7 @@ class DocumentParser(LoggingMixin):
     def __init__(self, logging_group, progress_callback=None):
         super().__init__()
         self.logging_group = logging_group
+        self.parser_settings = self.get_settings()
         os.makedirs(settings.SCRATCH_DIR, exist_ok=True)
         self.tempdir = tempfile.mkdtemp(prefix="paperless-", dir=settings.SCRATCH_DIR)
 
@@ -330,6 +333,10 @@ class DocumentParser(LoggingMixin):
         if self.progress_callback:
             self.progress_callback(current_progress, max_progress)
 
+    def get_settings(self):
+        # return None
+        raise NotImplementedError
+
     def read_file_handle_unicode_errors(self, filepath: Path) -> str:
         """
         Helper utility for reading from a file, and handling a problem with its