a couple fixes and more supported image files

src/documents/signals/handlers.py

@@ -268,8 +268,9 @@ def update_filename_and_move_files(sender, instance, **kwargs):
         logging.getLogger(__name__).debug(
             f"Moved file {old_source_path} to {new_source_path}.")
 
-        logging.getLogger(__name__).debug(
-            f"Moved file {old_archive_path} to {new_archive_path}.")
+        if instance.archive_checksum:
+            logging.getLogger(__name__).debug(
+                f"Moved file {old_archive_path} to {new_archive_path}.")
 
     except OSError as e:
         instance.filename = old_filename

src/paperless_tesseract/parsers.py

@@ -65,7 +65,10 @@ class RasterisedDocumentParser(DocumentParser):
     def is_image(self, mime_type):
         return mime_type in [
             "image/png",
-            "image/jpeg"
+            "image/jpeg",
+            "image/tiff",
+            "image/bmp",
+            "image/gif",
         ]
 
     def get_dpi(self, image):

src/paperless_tesseract/signals.py

@@ -8,6 +8,9 @@ def tesseract_consumer_declaration(sender, **kwargs):
         "mime_types": {
             "application/pdf": ".pdf",
             "image/jpeg": ".jpg",
-            "image/png": ".png"
+            "image/png": ".png",
+            "image/tiff": ".tif",
+            "image/gif": ".gif",
+            "image/bmp": ".bmp",
         }
     }

src/paperless_tesseract/tests/test_parser.py

@@ -247,3 +247,33 @@ class TestParser(DirectoriesMixin, TestCase):
         parser.parse(os.path.join(self.SAMPLE_FILES, "multi-page-images.pdf"), "application/pdf")
         self.assertTrue(os.path.join(parser.archive_path))
         self.assertContainsStrings(parser.get_text().lower(), ["page 1", "page 2", "page 3"])
+
+
+class TestParserFileTypes(DirectoriesMixin, TestCase):
+
+    SAMPLE_FILES = os.path.join(os.path.dirname(__file__), "samples")
+
+    def test_bmp(self):
+        parser = RasterisedDocumentParser(None)
+        parser.parse(os.path.join(self.SAMPLE_FILES, "simple.bmp"), "image/bmp")
+        self.assertTrue(os.path.isfile(parser.archive_path))
+        self.assertTrue("this is a test document" in parser.get_text().lower())
+
+    def test_jpg(self):
+        parser = RasterisedDocumentParser(None)
+        parser.parse(os.path.join(self.SAMPLE_FILES, "simple.jpg"), "image/jpeg")
+        self.assertTrue(os.path.isfile(parser.archive_path))
+        self.assertTrue("this is a test document" in parser.get_text().lower())
+
+    @override_settings(OCR_IMAGE_DPI=200)
+    def test_gif(self):
+        parser = RasterisedDocumentParser(None)
+        parser.parse(os.path.join(self.SAMPLE_FILES, "simple.gif"), "image/gif")
+        self.assertTrue(os.path.isfile(parser.archive_path))
+        self.assertTrue("this is a test document" in parser.get_text().lower())
+
+    def test_tiff(self):
+        parser = RasterisedDocumentParser(None)
+        parser.parse(os.path.join(self.SAMPLE_FILES, "simple.tif"), "image/tiff")
+        self.assertTrue(os.path.isfile(parser.archive_path))
+        self.assertTrue("this is a test document" in parser.get_text().lower())