Cleans up the reprocess task and generally reduces duplicate of classes

src/documents/consumer.py

@@ -459,13 +459,20 @@ class ConsumerPlugin(
             progress_callback=progress_callback,
         )
 
+        parser_is_new_style = isinstance(
+            document_parser,
+            (
+                MailDocumentParser,
+                RemoteDocumentParser,
+                TextDocumentParser,
+                TikaDocumentParser,
+            ),
+        )
+
         # New-style parsers use __enter__/__exit__ for resource management.
         # _parser_cleanup (below) handles __exit__; call __enter__ here.
         # TODO(stumpylog): Remove me in the future
-        if isinstance(
-            document_parser,
-            (TextDocumentParser, RemoteDocumentParser, TikaDocumentParser),
-        ):
+        if parser_is_new_style:
             document_parser.__enter__()
 
         self.log.debug(f"Parser: {type(document_parser).__name__}")
@@ -488,15 +495,7 @@ class ConsumerPlugin(
             self.log.debug(f"Parsing {self.filename}...")
 
             # TODO(stumpylog): Remove me in the future when all parsers use new protocol
-            if isinstance(
-                document_parser,
-                (
-                    MailDocumentParser,
-                    RemoteDocumentParser,
-                    TextDocumentParser,
-                    TikaDocumentParser,
-                ),
-            ):
+            if parser_is_new_style:
                 document_parser.configure(
                     ParserContext(mailrule_id=self.input_doc.mailrule_id),
                 )
@@ -513,15 +512,7 @@ class ConsumerPlugin(
                 ConsumerStatusShortMessage.GENERATING_THUMBNAIL,
             )
             # TODO(stumpylog): Remove me in the future when all parsers use new protocol
-            if isinstance(
-                document_parser,
-                (
-                    MailDocumentParser,
-                    RemoteDocumentParser,
-                    TextDocumentParser,
-                    TikaDocumentParser,
-                ),
-            ):
+            if parser_is_new_style:
                 thumbnail = document_parser.get_thumbnail(self.working_copy, mime_type)
             else:
                 thumbnail = document_parser.get_thumbnail(

src/documents/tasks.py

@@ -67,6 +67,7 @@ from documents.workflows.utils import get_workflows_for_trigger
 from paperless.config import AIConfig
 from paperless.parsers import ParserContext
 from paperless.parsers.mail import MailDocumentParser
+from paperless.parsers.remote import RemoteDocumentParser
 from paperless.parsers.text import TextDocumentParser
 from paperless.parsers.tika import TikaDocumentParser
 from paperless_ai.indexing import llm_index_add_or_update_document
@@ -319,16 +320,23 @@ def update_document_content_maybe_archive_file(document_id) -> None:
 
     parser: DocumentParser = parser_class(logging_group=uuid.uuid4())
 
+    parser_is_new_style = isinstance(
+        parser,
+        (
+            MailDocumentParser,
+            RemoteDocumentParser,
+            TextDocumentParser,
+            TikaDocumentParser,
+        ),
+    )
+
     # TODO(stumpylog): Remove branch in the future when all parsers use new protocol
-    if isinstance(parser, (TextDocumentParser, TikaDocumentParser)):
+    if parser_is_new_style:
         parser.__enter__()
 
     try:
         # TODO(stumpylog): Remove branch in the future when all parsers use new protocol
-        if isinstance(
-            parser,
-            (MailDocumentParser, TextDocumentParser, TikaDocumentParser),
-        ):
+        if parser_is_new_style:
             parser.configure(ParserContext())
             parser.parse(document.source_path, mime_type)
         else:
@@ -339,10 +347,7 @@ def update_document_content_maybe_archive_file(document_id) -> None:
             )
 
         # TODO(stumpylog): Remove branch in the future when all parsers use new protocol
-        if isinstance(
-            parser,
-            (MailDocumentParser, TextDocumentParser, TikaDocumentParser),
-        ):
+        if parser_is_new_style:
             thumbnail = parser.get_thumbnail(document.source_path, mime_type)
         else:
             thumbnail = parser.get_thumbnail(