Add dry run

arkindex/documents/importer.py

@@ -284,6 +284,9 @@ class ManifestsImporter(ABC):
 
     def save_transcriptions(self):
         """To optimize transcription parsing, saving and indexing is done in bulk."""
+        if len(self.images_transcription_data) < 1:
+            return
+
         total_zones, total_transcriptions, total_indexes = 0, 0, 0
 
         for (image, page), data in self.images_transcription_data.items():

arkindex/documents/management/commands/import_annotations.py

@@ -18,6 +18,12 @@ class Command(BaseCommand):
             help='Folder to recursively search for index files',
             default='.'
         )
+        parser.add_argument(
+            '--dry-run',
+            help='Only show the associated images found for all index files, without importing anything',
+            action='store_true',
+            default=False,
+        )
 
     def handle(self, *args, **options):
         # Handle verbosity level
@@ -26,4 +32,8 @@ class Command(BaseCommand):
         if verbosity > 1:
             root_logger.setLevel(logging.DEBUG)
 
-        IndexImporter(options['index_folder']).run()
+        importer = IndexImporter(options['index_folder'])
+        if options['dry_run']:
+            importer.dry_run()
+        else:
+            importer.run()

arkindex/images/importer.py

@@ -169,6 +169,25 @@ class IndexImporter(object):
     def run(self):
         for index_path in self.get_index_paths():
             logger.info("Parsing index file {}".format(index_path))
-            image = self.get_image(index_path)
-            page = self.get_page(image)
-            import_indexes(image, page, index_path)
+            try:
+                image = self.get_image(index_path)
+                page = self.get_page(image)
+                import_indexes(image, page, index_path)
+            except Image.DoesNotExist:
+                logger.warning("No associated image found for file {}".format(index_path))
+            except Page.DoesNotExist:
+                logger.warning("No associated page found for file {}".format(index_path))
+            except Image.MultipleObjectsReturned:
+                logger.warning("Multiple associated images found for file {}".format(index_path))
+
+    def dry_run(self):
+        image = None
+        for index_path in self.get_index_paths():
+            try:
+                image = self.get_image(index_path)
+            except (Image.DoesNotExist, Image.MultipleObjectsReturned):
+                pass
+            if image is None:
+                print("{}\tFAIL".format(index_path))
+            else:
+                print("{}\t{}".format(index_path, image.path))