From: Trenton H <797416+stumpylog@users.noreply.github.com>
Date: Tue, 3 Jan 2023 16:21:23 +0000 (-0800)
Subject: Adds testing coverage of multipage TIFF with alpha, without and with alpha/sRGB
X-Git-Tag: v1.12.0-beta.rc0~79
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=0fd51e35e1345f8ec381cc511d473079812c2a43;p=thirdparty%2Fpaperless-ngx.git

Adds testing coverage of multipage TIFF with alpha, without and with alpha/sRGB
---

diff --git a/src/paperless_tesseract/tests/samples/multi-page-images-alpha-rgb.tiff b/src/paperless_tesseract/tests/samples/multi-page-images-alpha-rgb.tiff
new file mode 100644
index 0000000000..3111b7c4cc
Binary files /dev/null and b/src/paperless_tesseract/tests/samples/multi-page-images-alpha-rgb.tiff differ
diff --git a/src/paperless_tesseract/tests/samples/multi-page-images-alpha.tiff b/src/paperless_tesseract/tests/samples/multi-page-images-alpha.tiff
new file mode 100644
index 0000000000..c612cf4bae
Binary files /dev/null and b/src/paperless_tesseract/tests/samples/multi-page-images-alpha.tiff differ
diff --git a/src/paperless_tesseract/tests/samples/multi-page-images.tiff b/src/paperless_tesseract/tests/samples/multi-page-images.tiff
new file mode 100644
index 0000000000..0e62b60106
Binary files /dev/null and b/src/paperless_tesseract/tests/samples/multi-page-images.tiff differ
diff --git a/src/paperless_tesseract/tests/test_parser.py b/src/paperless_tesseract/tests/test_parser.py
index 4d6890653d..28af8dec18 100644
--- a/src/paperless_tesseract/tests/test_parser.py
+++ b/src/paperless_tesseract/tests/test_parser.py
@@ -542,6 +542,69 @@ class TestParser(DirectoriesMixin, TestCase):
             ],
         )
 
+    def test_multi_page_tiff(self):
+        """
+        GIVEN:
+            - Multi-page TIFF image
+        WHEN:
+            - Image is parsed
+        THEN:
+            - Text from all pages extracted
+        """
+        parser = RasterisedDocumentParser(None)
+        parser.parse(
+            os.path.join(self.SAMPLE_FILES, "multi-page-images.tiff"),
+            "image/tiff",
+        )
+        self.assertTrue(os.path.isfile(parser.archive_path))
+        self.assertContainsStrings(
+            parser.get_text().lower(),
+            ["page 1", "page 2", "page 3"],
+        )
+
+    def test_multi_page_tiff_alpha(self):
+        """
+        GIVEN:
+            - Multi-page TIFF image
+            - Image include an alpha channel
+        WHEN:
+            - Image is parsed
+        THEN:
+            - Text from all pages extracted
+        """
+        parser = RasterisedDocumentParser(None)
+        parser.parse(
+            os.path.join(self.SAMPLE_FILES, "multi-page-images-alpha.tiff"),
+            "image/tiff",
+        )
+        self.assertTrue(os.path.isfile(parser.archive_path))
+        self.assertContainsStrings(
+            parser.get_text().lower(),
+            ["page 1", "page 2", "page 3"],
+        )
+
+    def test_multi_page_tiff_alpha_srgb(self):
+        """
+        GIVEN:
+            - Multi-page TIFF image
+            - Image include an alpha channel
+            - Image is srgb colorspace
+        WHEN:
+            - Image is parsed
+        THEN:
+            - Text from all pages extracted
+        """
+        parser = RasterisedDocumentParser(None)
+        parser.parse(
+            os.path.join(self.SAMPLE_FILES, "multi-page-images-alpha-rgb.tiff"),
+            "image/tiff",
+        )
+        self.assertTrue(os.path.isfile(parser.archive_path))
+        self.assertContainsStrings(
+            parser.get_text().lower(),
+            ["page 1", "page 2", "page 3"],
+        )
+
     def test_ocrmypdf_parameters(self):
         parser = RasterisedDocumentParser(None)
         params = parser.construct_ocrmypdf_parameters(