bugfix

src/documents/index.py

@@ -82,6 +82,10 @@ def open_index(recreate=False):
 
 
 def update_document(writer, doc):
+    # TODO: this line caused many issues all around, since:
+    #  We need to make sure that this method does not get called with
+    #  deserialized documents (i.e, document objects that don't come from
+    #  Django's ORM interfaces directly.
     logger.debug("Indexing {}...".format(doc))
     tags = ",".join([t.name for t in doc.tags.all()])
     writer.update_document(
@@ -98,6 +102,7 @@ def update_document(writer, doc):
 
 
 def remove_document(writer, doc):
+    # TODO: see above.
     logger.debug("Removing {} from index...".format(doc))
     writer.delete_by_term('id', doc.pk)
 

src/documents/management/commands/document_archiver.py

@@ -23,7 +23,9 @@ from ...parsers import get_parser_class_for_mime_type
 logger = logging.getLogger(__name__)
 
 
-def handle_document(document):
+def handle_document(document_id):
+    document = Document.objects.get(id=document_id)
+
     mime_type = document.mime_type
 
     parser_class = get_parser_class_for_mime_type(mime_type)
@@ -98,9 +100,12 @@ class Command(Renderable, BaseCommand):
         else:
             documents = Document.objects.all()
 
-        documents_to_process = list(filter(
-            lambda d: overwrite or not d.archive_checksum,
-            documents
+        document_ids = list(map(
+            lambda doc: doc.id,
+            filter(
+                lambda d: overwrite or not d.archive_checksum,
+                documents
+            )
         ))
 
         logging.getLogger().handlers[0].level = logging.ERROR
@@ -108,7 +113,7 @@ class Command(Renderable, BaseCommand):
             list(tqdm.tqdm(
                 pool.imap_unordered(
                     handle_document,
-                    documents_to_process
+                    document_ids
                 ),
-                total=len(documents_to_process)
+                total=len(document_ids)
             ))

src/documents/tests/test_management_archiver.py

@@ -32,7 +32,7 @@ class TestArchiver(DirectoriesMixin, TestCase):
         shutil.copy(sample_file, os.path.join(self.dirs.originals_dir, "0000001.pdf"))
         self.make_models()
 
-        handle_document(self.d1)
+        handle_document(self.d1.pk)
 
         doc = Document.objects.get(id=self.d1.id)