Chore: Consolidate test sample files (#14430)

Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>

src/paperless/tests/parsers/conftest.py

@@ -432,30 +432,6 @@ def tesseract_samples_dir(parser_samples_dir: Path) -> Path:
     return parser_samples_dir / "tesseract"
 
 
-@pytest.fixture(scope="session")
-def multi_page_images_pdf_file(tesseract_samples_dir: Path) -> Path:
-    """Path to a multi-page PDF with images.
-
-    Returns
-    -------
-    Path
-        Absolute path to ``tesseract/multi-page-images.pdf``.
-    """
-    return tesseract_samples_dir / "multi-page-images.pdf"
-
-
-@pytest.fixture(scope="session")
-def simple_digital_pdf_file(tesseract_samples_dir: Path) -> Path:
-    """Path to a simple digital PDF sample file.
-
-    Returns
-    -------
-    Path
-        Absolute path to ``tesseract/simple-digital.pdf``.
-    """
-    return tesseract_samples_dir / "simple-digital.pdf"
-
-
 @pytest.fixture(scope="session")
 def simple_no_dpi_png_file(tesseract_samples_dir: Path) -> Path:
     """Path to a simple PNG without DPI information.
@@ -480,6 +456,18 @@ def simple_png_file(tesseract_samples_dir: Path) -> Path:
     return tesseract_samples_dir / "simple.png"
 
 
+@pytest.fixture(scope="session")
+def rotated_pdf_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a landscape (rotated) PDF sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/rotated.pdf``.
+    """
+    return tesseract_samples_dir / "rotated.pdf"
+
+
 # ------------------------------------------------------------------
 # Tesseract parser instance and settings helpers
 # ------------------------------------------------------------------

src/paperless/tests/parsers/test_tesseract_parser.py

@@ -161,11 +161,11 @@ class TestGetPageCount:
     def test_single_page_pdf(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
         assert (
             tesseract_parser.get_page_count(
-                tesseract_samples_dir / "simple-digital.pdf",
+                simple_digital_pdf_file,
                 "application/pdf",
             )
             == 1
@@ -188,7 +188,7 @@ class TestGetPageCount:
         self,
         mocker: MockerFixture,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        simple_digital_pdf_file: Path,
         caplog,
     ) -> None:
         """
@@ -204,7 +204,7 @@ class TestGetPageCount:
 
         with caplog.at_level(logging.WARNING):
             page_count = tesseract_parser.get_page_count(
-                tesseract_samples_dir / "simple-digital.pdf",
+                simple_digital_pdf_file,
                 "application/pdf",
             )
         assert page_count is None
@@ -273,26 +273,26 @@ class TestGetThumbnail:
     def test_thumbnail_is_file(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
         thumb = tesseract_parser.get_thumbnail(
-            tesseract_samples_dir / "simple-digital.pdf",
+            simple_digital_pdf_file,
             "application/pdf",
         )
         assert thumb.is_file()
 
     @pytest.mark.parametrize(
-        ("filename", "expected_height"),
+        ("sample_fixture", "expected_height"),
         [
-            pytest.param("simple-digital.pdf", 647, id="portrait-letter"),
-            pytest.param("rotated.pdf", 386, id="landscape"),
+            pytest.param("simple_digital_pdf_file", 647, id="portrait-letter"),
+            pytest.param("rotated_pdf_file", 386, id="landscape"),
         ],
     )
     def test_thumbnail_is_correct_format_and_size(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
-        filename: str,
+        request: pytest.FixtureRequest,
+        sample_fixture: str,
         expected_height: int,
     ) -> None:
         """
@@ -304,7 +304,7 @@ class TestGetThumbnail:
             - A 500px wide WebP keeping the page's aspect ratio
         """
         thumb = tesseract_parser.get_thumbnail(
-            tesseract_samples_dir / filename,
+            request.getfixturevalue(sample_fixture),
             "application/pdf",
         )
         with Image.open(thumb) as im:
@@ -316,7 +316,7 @@ class TestGetThumbnail:
         self,
         mocker: MockerFixture,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
         """
         GIVEN:
@@ -326,7 +326,7 @@ class TestGetThumbnail:
         THEN:
             - The PDF is repaired with qpdf and a real thumbnail is rendered
         """
-        original = tesseract_samples_dir / "simple-digital.pdf"
+        original = simple_digital_pdf_file
 
         def _fail_on_original(in_path: Path, out_path: Path, **kwargs) -> None:
             if in_path == original:
@@ -368,11 +368,11 @@ class TestExtractText:
     def test_extract_text_from_digital_pdf(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
         text = tesseract_parser.extract_text(
             None,
-            tesseract_samples_dir / "simple-digital.pdf",
+            simple_digital_pdf_file,
         )
         assert text is not None
         assert "This is a test document." in text.strip()
@@ -387,7 +387,7 @@ class TestParsePdf:
     def test_simple_digital_creates_archive(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        multi_page_digital_pdf_file: Path,
     ) -> None:
         """
         GIVEN:
@@ -401,7 +401,7 @@ class TestParsePdf:
             - Text is extracted
         """
         tesseract_parser.parse(
-            tesseract_samples_dir / "multi-page-digital.pdf",
+            multi_page_digital_pdf_file,
             "application/pdf",
         )
         assert tesseract_parser.archive_path is not None
@@ -416,10 +416,10 @@ class TestParsePdf:
     def test_with_form_default(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        with_form_pdf_file: Path,
     ) -> None:
         tesseract_parser.parse(
-            tesseract_samples_dir / "with-form.pdf",
+            with_form_pdf_file,
             "application/pdf",
         )
         assert tesseract_parser.archive_path is not None
@@ -432,11 +432,11 @@ class TestParsePdf:
     def test_with_form_redo_no_archive_when_not_requested(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        with_form_pdf_file: Path,
     ) -> None:
         tesseract_parser.settings.mode = ModeChoices.REDO
         tesseract_parser.parse(
-            tesseract_samples_dir / "with-form.pdf",
+            with_form_pdf_file,
             "application/pdf",
             produce_archive=False,
         )
@@ -449,11 +449,11 @@ class TestParsePdf:
     def test_with_form_force(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        with_form_pdf_file: Path,
     ) -> None:
         tesseract_parser.settings.mode = ModeChoices.FORCE
         tesseract_parser.parse(
-            tesseract_samples_dir / "with-form.pdf",
+            with_form_pdf_file,
             "application/pdf",
         )
         assert_ordered_substrings(
@@ -494,7 +494,7 @@ class TestParsePdf:
         self,
         mocker: MockerFixture,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
         mocker.patch(
             "ocrmypdf.ocr",
@@ -502,7 +502,7 @@ class TestParsePdf:
         )
         with pytest.raises(ParseError):
             tesseract_parser.parse(
-                tesseract_samples_dir / "simple-digital.pdf",
+                simple_digital_pdf_file,
                 "application/pdf",
             )
 
@@ -578,10 +578,10 @@ class TestParseMultiPage:
     def test_multi_page_digital(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        multi_page_digital_pdf_file: Path,
     ) -> None:
         tesseract_parser.parse(
-            tesseract_samples_dir / "multi-page-digital.pdf",
+            multi_page_digital_pdf_file,
             "application/pdf",
         )
         assert tesseract_parser.archive_path is not None
@@ -605,12 +605,12 @@ class TestParseMultiPage:
         self,
         mode: str,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        multi_page_digital_pdf_file: Path,
     ) -> None:
         tesseract_parser.settings.pages = 2
         tesseract_parser.settings.mode = mode
         tesseract_parser.parse(
-            tesseract_samples_dir / "multi-page-digital.pdf",
+            multi_page_digital_pdf_file,
             "application/pdf",
         )
         assert tesseract_parser.archive_path is not None
@@ -624,11 +624,11 @@ class TestParseMultiPage:
     def test_multi_page_images_skip(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        multi_page_images_pdf_file: Path,
     ) -> None:
         tesseract_parser.settings.mode = ModeChoices.AUTO
         tesseract_parser.parse(
-            tesseract_samples_dir / "multi-page-images.pdf",
+            multi_page_images_pdf_file,
             "application/pdf",
         )
         assert tesseract_parser.archive_path is not None
@@ -642,7 +642,7 @@ class TestParseMultiPage:
     def test_multi_page_images_redo_pages_2(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        multi_page_images_pdf_file: Path,
     ) -> None:
         """
         GIVEN:
@@ -657,7 +657,7 @@ class TestParseMultiPage:
         tesseract_parser.settings.pages = 2
         tesseract_parser.settings.mode = ModeChoices.REDO
         tesseract_parser.parse(
-            tesseract_samples_dir / "multi-page-images.pdf",
+            multi_page_images_pdf_file,
             "application/pdf",
         )
         assert tesseract_parser.archive_path is not None
@@ -670,7 +670,7 @@ class TestParseMultiPage:
     def test_multi_page_images_force_page_1(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        multi_page_images_pdf_file: Path,
     ) -> None:
         """
         GIVEN:
@@ -685,7 +685,7 @@ class TestParseMultiPage:
         tesseract_parser.settings.pages = 1
         tesseract_parser.settings.mode = ModeChoices.FORCE
         tesseract_parser.parse(
-            tesseract_samples_dir / "multi-page-images.pdf",
+            multi_page_images_pdf_file,
             "application/pdf",
         )
         assert tesseract_parser.archive_path is not None
@@ -781,7 +781,7 @@ class TestSkipArchive:
     def test_skip_noarchive_with_text_layer(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        multi_page_digital_pdf_file: Path,
     ) -> None:
         """
         GIVEN:
@@ -795,7 +795,7 @@ class TestSkipArchive:
         """
         tesseract_parser.settings.mode = ModeChoices.AUTO
         tesseract_parser.parse(
-            tesseract_samples_dir / "multi-page-digital.pdf",
+            multi_page_digital_pdf_file,
             "application/pdf",
             produce_archive=False,
         )
@@ -810,7 +810,7 @@ class TestSkipArchive:
     def test_skip_noarchive_image_only_creates_archive(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        multi_page_images_pdf_file: Path,
     ) -> None:
         """
         GIVEN:
@@ -823,7 +823,7 @@ class TestSkipArchive:
         """
         tesseract_parser.settings.mode = ModeChoices.AUTO
         tesseract_parser.parse(
-            tesseract_samples_dir / "multi-page-images.pdf",
+            multi_page_images_pdf_file,
             "application/pdf",
         )
         assert tesseract_parser.archive_path is not None
@@ -835,29 +835,29 @@ class TestSkipArchive:
         )
 
     @pytest.mark.parametrize(
-        ("produce_archive", "filename", "expect_archive"),
+        ("produce_archive", "sample_fixture", "expect_archive"),
         [
             pytest.param(
                 True,
-                "multi-page-digital.pdf",
+                "multi_page_digital_pdf_file",
                 True,
                 id="produce-archive-with-text",
             ),
             pytest.param(
                 True,
-                "multi-page-images.pdf",
+                "multi_page_images_pdf_file",
                 True,
                 id="produce-archive-no-text",
             ),
             pytest.param(
                 False,
-                "multi-page-digital.pdf",
+                "multi_page_digital_pdf_file",
                 False,
                 id="no-archive-with-text-layer",
             ),
             pytest.param(
                 False,
-                "multi-page-images.pdf",
+                "multi_page_images_pdf_file",
                 False,
                 id="no-archive-no-text-layer",
             ),
@@ -866,10 +866,10 @@ class TestSkipArchive:
     def test_produce_archive_flag(
         self,
         produce_archive: bool,  # noqa: FBT001
-        filename: str,
+        sample_fixture: str,
         expect_archive: bool,  # noqa: FBT001
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        request: pytest.FixtureRequest,
     ) -> None:
         """
         GIVEN:
@@ -882,8 +882,9 @@ class TestSkipArchive:
             - Text is always extracted
         """
         tesseract_parser.settings.mode = ModeChoices.AUTO
+        sample = request.getfixturevalue(sample_fixture)
         tesseract_parser.parse(
-            tesseract_samples_dir / filename,
+            sample,
             "application/pdf",
             produce_archive=produce_archive,
         )
@@ -900,7 +901,7 @@ class TestSkipArchive:
         self,
         mocker: MockerFixture,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
         """
         GIVEN:
@@ -916,7 +917,7 @@ class TestSkipArchive:
         tesseract_parser.settings.mode = ModeChoices.AUTO
         mock_ocr = mocker.patch("ocrmypdf.ocr")
         tesseract_parser.parse(
-            tesseract_samples_dir / "simple-digital.pdf",
+            simple_digital_pdf_file,
             "application/pdf",
             produce_archive=False,
         )
@@ -955,7 +956,7 @@ class TestSkipArchive:
     def test_tagged_pdf_produces_pdfa_archive_without_ocr(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
         """
         GIVEN:
@@ -970,7 +971,7 @@ class TestSkipArchive:
         """
         tesseract_parser.settings.mode = ModeChoices.AUTO
         tesseract_parser.parse(
-            tesseract_samples_dir / "simple-digital.pdf",
+            simple_digital_pdf_file,
             "application/pdf",
             produce_archive=True,
         )

src/paperless/tests/samples/mail/sample.html

@@ -1,19 +0,0 @@
- <html>
-    <head>
-      <meta http-equiv="content-type" content="text/html; charset=UTF-8">
-    </head>
-    <body>
-      <p>Some Text</p>
-      <p>
-				<img src="cid:part1.pNdUSz0s.D3NqVtPg@example.de" alt="Has to be rewritten to work..">
-				<img src="http://localhost:8080/assets/logo_full_white.svg" alt="This image should not be shown.">
-			</p>
-
-      <p>and an embedded image.<br>
-      </p>
-      <p id="changeme">Paragraph unchanged.</p>
-      <scRipt>
-          document.getElementById("changeme").innerHTML = "Paragraph changed via Java Script.";
-      </script>
-    </body>
-  </html>

src/paperless/tests/test_parser_utils.py

@@ -18,8 +18,6 @@ from paperless.parsers.utils import read_file_handle_unicode_errors
 if TYPE_CHECKING:
     from pytest_mock import MockerFixture
 
-SAMPLES = Path(__file__).parent / "samples" / "tesseract"
-
 
 class TestReadFileHandleUnicodeErrors:
     def test_plain_utf8(self, tmp_path: Path) -> None:
@@ -57,11 +55,11 @@ class TestReadFileHandleUnicodeErrors:
 
 
 class TestIsTaggedPdf:
-    def test_tagged_pdf_returns_true(self) -> None:
-        assert is_tagged_pdf(SAMPLES / "simple-digital.pdf") is True
+    def test_tagged_pdf_returns_true(self, simple_digital_pdf_file: Path) -> None:
+        assert is_tagged_pdf(simple_digital_pdf_file) is True
 
-    def test_untagged_pdf_returns_false(self) -> None:
-        assert is_tagged_pdf(SAMPLES / "multi-page-images.pdf") is False
+    def test_untagged_pdf_returns_false(self, multi_page_images_pdf_file: Path) -> None:
+        assert is_tagged_pdf(multi_page_images_pdf_file) is False
 
     def test_nonexistent_path_returns_false(self) -> None:
         assert is_tagged_pdf(Path("/nonexistent/file.pdf")) is False
@@ -95,7 +93,7 @@ class TestGetPdfFirstPageSizePoints:
         pdf.save(path)
         return path
 
-    def test_letter_sample(self) -> None:
+    def test_letter_sample(self, simple_digital_pdf_file: Path) -> None:
         """
         GIVEN:
             - A US Letter sample PDF with no CropBox and no rotation
@@ -104,7 +102,7 @@ class TestGetPdfFirstPageSizePoints:
         THEN:
             - The MediaBox size in points is returned
         """
-        assert get_pdf_first_page_size_points(SAMPLES / "simple-digital.pdf") == (
+        assert get_pdf_first_page_size_points(simple_digital_pdf_file) == (
             612.0,
             792.0,
         )
@@ -199,6 +197,7 @@ class TestGetPdfFirstPageSizePoints:
     def test_pdfinfo_not_installed_returns_none(
         self,
         mocker: MockerFixture,
+        simple_digital_pdf_file: Path,
     ) -> None:
         """
         GIVEN:
@@ -209,7 +208,7 @@ class TestGetPdfFirstPageSizePoints:
             - None is returned and nothing is raised
         """
         mocker.patch("subprocess.run", side_effect=FileNotFoundError("pdfinfo"))
-        assert get_pdf_first_page_size_points(SAMPLES / "simple-digital.pdf") is None
+        assert get_pdf_first_page_size_points(simple_digital_pdf_file) is None
 
     def test_degenerate_box_returns_none(self, tmp_path: Path) -> None:
         """
@@ -251,7 +250,7 @@ class TestGetPdfFirstPageSizePoints:
         bad.write_bytes(b"not a pdf")
         assert get_pdf_first_page_size_points(bad) is None
 
-    def test_encrypted_pdf_returns_none(self) -> None:
+    def test_encrypted_pdf_returns_none(self, parser_samples_dir: Path) -> None:
         """
         GIVEN:
             - A password protected PDF
@@ -260,7 +259,8 @@ class TestGetPdfFirstPageSizePoints:
         THEN:
             - None is returned and nothing is raised
         """
-        assert get_pdf_first_page_size_points(SAMPLES / "encrypted.pdf") is None
+        encrypted = parser_samples_dir / "tesseract" / "encrypted.pdf"
+        assert get_pdf_first_page_size_points(encrypted) is None
 
 
 class TestPostProcessText: