replaced usages of .id with .pk, fixed filename issue in exporter

src/documents/classifier.py

@@ -75,16 +75,16 @@ class DocumentClassifier(object):
             y = -1
             if doc.document_type:
                 if doc.document_type.matching_algorithm == MatchingModel.MATCH_AUTO:
-                    y = doc.document_type.id
+                    y = doc.document_type.pk
             labels_document_type.append(y)
 
             y = -1
             if doc.correspondent:
                 if doc.correspondent.matching_algorithm == MatchingModel.MATCH_AUTO:
-                    y = doc.correspondent.id
+                    y = doc.correspondent.pk
             labels_correspondent.append(y)
 
-            tags = [tag.id for tag in doc.tags.filter(
+            tags = [tag.pk for tag in doc.tags.filter(
                 matching_algorithm=MatchingModel.MATCH_AUTO
             )]
             labels_tags.append(tags)

src/documents/index.py

@@ -69,7 +69,7 @@ def open_index(recreate=False):
 def update_document(writer, doc):
     logging.getLogger(__name__).debug("Updating index with document{}".format(str(doc)))
     writer.update_document(
-        id=doc.id,
+        id=doc.pk,
         title=doc.title,
         content=doc.content
     )
@@ -87,7 +87,7 @@ def remove_document_from_index(sender, instance, **kwargs):
     logging.getLogger(__name__).debug("Removing document {} from index".format(str(instance)))
     ix = open_index()
     with AsyncWriter(ix) as writer:
-        writer.delete_by_term('id', instance.id)
+        writer.delete_by_term('id', instance.pk)
 
 
 def autocomplete(ix, term, limit=10):

src/documents/management/commands/document_exporter.py

@@ -64,12 +64,14 @@ class Command(Renderable, BaseCommand):
 
             document = document_map[document_dict["pk"]]
 
-            file_target = os.path.join(self.target, document.file_name)
+            unique_filename = "{:07}_{}".format(document.pk, document.file_name)
 
-            thumbnail_name = document.file_name + "-thumbnail.png"
+            file_target = os.path.join(self.target, unique_filename)
+
+            thumbnail_name = unique_filename + "-thumbnail.png"
             thumbnail_target = os.path.join(self.target, thumbnail_name)
 
-            document_dict[EXPORTER_FILE_NAME] = document.file_name
+            document_dict[EXPORTER_FILE_NAME] = unique_filename
             document_dict[EXPORTER_THUMBNAIL_NAME] = thumbnail_name
 
             print("Exporting: {}".format(file_target))

src/documents/matching.py

@@ -9,7 +9,7 @@ def match_correspondents(document_content, classifier):
     correspondents = Correspondent.objects.all()
     predicted_correspondent_id = classifier.predict_correspondent(document_content) if classifier else None
 
-    matched_correspondents = [o for o in correspondents if matches(o, document_content) or o.id == predicted_correspondent_id]
+    matched_correspondents = [o for o in correspondents if matches(o, document_content) or o.pk == predicted_correspondent_id]
     return matched_correspondents
 
 
@@ -17,7 +17,7 @@ def match_document_types(document_content, classifier):
     document_types = DocumentType.objects.all()
     predicted_document_type_id = classifier.predict_document_type(document_content) if classifier else None
 
-    matched_document_types = [o for o in document_types if matches(o, document_content) or o.id == predicted_document_type_id]
+    matched_document_types = [o for o in document_types if matches(o, document_content) or o.pk == predicted_document_type_id]
     return matched_document_types
 
 
@@ -25,7 +25,7 @@ def match_tags(document_content, classifier):
     objects = Tag.objects.all()
     predicted_tag_ids = classifier.predict_tags(document_content) if classifier else []
 
-    matched_tags = [o for o in objects if matches(o, document_content) or o.id in predicted_tag_ids]
+    matched_tags = [o for o in objects if matches(o, document_content) or o.pk in predicted_tag_ids]
     return matched_tags
 
 

src/documents/signals/handlers.py

@@ -134,7 +134,7 @@ def run_post_consume_script(sender, document, **kwargs):
 
     Popen((
         settings.POST_CONSUME_SCRIPT,
-        str(document.id),
+        str(document.pk),
         document.file_name,
         document.source_path,
         document.thumbnail_path,
@@ -166,7 +166,7 @@ def set_log_entry(sender, document=None, logging_group=None, **kwargs):
         action_flag=ADDITION,
         action_time=timezone.now(),
         content_type=ct,
-        object_id=document.id,
+        object_id=document.pk,
         user=user,
         object_repr=document.__str__(),
     )