diff --git a/src/paperless/tests/parsers/conftest.py b/src/paperless/tests/parsers/conftest.py index a484f02c8..8747ac9bd 100644 --- a/src/paperless/tests/parsers/conftest.py +++ b/src/paperless/tests/parsers/conftest.py @@ -90,35 +90,6 @@ def text_parser() -> Generator[TextDocumentParser, None, None]: yield parser -# ------------------------------------------------------------------ -# Remote parser sample files -# ------------------------------------------------------------------ - - -@pytest.fixture(scope="session") -def remote_samples_dir(samples_dir: Path) -> Path: - """Absolute path to the remote parser sample files directory. - - Returns - ------- - Path - ``/remote/`` - """ - return samples_dir / "remote" - - -@pytest.fixture(scope="session") -def sample_pdf_file(remote_samples_dir: Path) -> Path: - """Path to a simple digital PDF sample file. - - Returns - ------- - Path - Absolute path to ``remote/simple-digital.pdf``. - """ - return remote_samples_dir / "simple-digital.pdf" - - # ------------------------------------------------------------------ # Remote parser instance # ------------------------------------------------------------------ diff --git a/src/paperless/tests/parsers/test_remote_parser.py b/src/paperless/tests/parsers/test_remote_parser.py index 69199a6e8..892915bb5 100644 --- a/src/paperless/tests/parsers/test_remote_parser.py +++ b/src/paperless/tests/parsers/test_remote_parser.py @@ -277,20 +277,20 @@ class TestRemoteParserParse: def test_parse_returns_text_from_azure( self, remote_parser: RemoteDocumentParser, - sample_pdf_file: Path, + simple_digital_pdf_file: Path, azure_client: Mock, ) -> None: - remote_parser.parse(sample_pdf_file, "application/pdf") + remote_parser.parse(simple_digital_pdf_file, "application/pdf") assert remote_parser.get_text() == _DEFAULT_TEXT def test_parse_sets_archive_path( self, remote_parser: RemoteDocumentParser, - sample_pdf_file: Path, + simple_digital_pdf_file: Path, azure_client: Mock, ) -> None: - remote_parser.parse(sample_pdf_file, "application/pdf") + remote_parser.parse(simple_digital_pdf_file, "application/pdf") archive = remote_parser.get_archive_path() assert archive is not None @@ -300,11 +300,11 @@ class TestRemoteParserParse: def test_parse_closes_client_on_success( self, remote_parser: RemoteDocumentParser, - sample_pdf_file: Path, + simple_digital_pdf_file: Path, azure_client: Mock, ) -> None: remote_parser.configure(ParserContext()) - remote_parser.parse(sample_pdf_file, "application/pdf") + remote_parser.parse(simple_digital_pdf_file, "application/pdf") azure_client.close.assert_called_once() @@ -312,9 +312,9 @@ class TestRemoteParserParse: def test_parse_sets_empty_text_when_not_configured( self, remote_parser: RemoteDocumentParser, - sample_pdf_file: Path, + simple_digital_pdf_file: Path, ) -> None: - remote_parser.parse(sample_pdf_file, "application/pdf") + remote_parser.parse(simple_digital_pdf_file, "application/pdf") assert remote_parser.get_text() == "" assert remote_parser.get_archive_path() is None @@ -328,10 +328,10 @@ class TestRemoteParserParse: def test_get_date_always_none( self, remote_parser: RemoteDocumentParser, - sample_pdf_file: Path, + simple_digital_pdf_file: Path, azure_client: Mock, ) -> None: - remote_parser.parse(sample_pdf_file, "application/pdf") + remote_parser.parse(simple_digital_pdf_file, "application/pdf") assert remote_parser.get_date() is None @@ -345,33 +345,33 @@ class TestRemoteParserParseError: def test_parse_returns_none_on_azure_error( self, remote_parser: RemoteDocumentParser, - sample_pdf_file: Path, + simple_digital_pdf_file: Path, failing_azure_client: Mock, ) -> None: - remote_parser.parse(sample_pdf_file, "application/pdf") + remote_parser.parse(simple_digital_pdf_file, "application/pdf") assert remote_parser.get_text() is None def test_parse_closes_client_on_error( self, remote_parser: RemoteDocumentParser, - sample_pdf_file: Path, + simple_digital_pdf_file: Path, failing_azure_client: Mock, ) -> None: - remote_parser.parse(sample_pdf_file, "application/pdf") + remote_parser.parse(simple_digital_pdf_file, "application/pdf") failing_azure_client.close.assert_called_once() def test_parse_logs_error_on_azure_failure( self, remote_parser: RemoteDocumentParser, - sample_pdf_file: Path, + simple_digital_pdf_file: Path, failing_azure_client: Mock, mocker: MockerFixture, ) -> None: mock_log = mocker.patch("paperless.parsers.remote.logger") - remote_parser.parse(sample_pdf_file, "application/pdf") + remote_parser.parse(simple_digital_pdf_file, "application/pdf") mock_log.error.assert_called_once() assert "Azure AI Vision parsing failed" in mock_log.error.call_args[0][0] @@ -386,18 +386,18 @@ class TestRemoteParserPageCount: def test_page_count_for_pdf( self, remote_parser: RemoteDocumentParser, - sample_pdf_file: Path, + simple_digital_pdf_file: Path, ) -> None: - count = remote_parser.get_page_count(sample_pdf_file, "application/pdf") + count = remote_parser.get_page_count(simple_digital_pdf_file, "application/pdf") assert isinstance(count, int) assert count >= 1 def test_page_count_returns_none_for_image_mime( self, remote_parser: RemoteDocumentParser, - sample_pdf_file: Path, + simple_digital_pdf_file: Path, ) -> None: - count = remote_parser.get_page_count(sample_pdf_file, "image/png") + count = remote_parser.get_page_count(simple_digital_pdf_file, "image/png") assert count is None def test_page_count_returns_none_for_invalid_pdf( @@ -420,25 +420,31 @@ class TestRemoteParserMetadata: def test_extract_metadata_non_pdf_returns_empty( self, remote_parser: RemoteDocumentParser, - sample_pdf_file: Path, + simple_digital_pdf_file: Path, ) -> None: - result = remote_parser.extract_metadata(sample_pdf_file, "image/png") + result = remote_parser.extract_metadata(simple_digital_pdf_file, "image/png") assert result == [] def test_extract_metadata_pdf_returns_list( self, remote_parser: RemoteDocumentParser, - sample_pdf_file: Path, + simple_digital_pdf_file: Path, ) -> None: - result = remote_parser.extract_metadata(sample_pdf_file, "application/pdf") + result = remote_parser.extract_metadata( + simple_digital_pdf_file, + "application/pdf", + ) assert isinstance(result, list) def test_extract_metadata_pdf_entries_have_required_keys( self, remote_parser: RemoteDocumentParser, - sample_pdf_file: Path, + simple_digital_pdf_file: Path, ) -> None: - result = remote_parser.extract_metadata(sample_pdf_file, "application/pdf") + result = remote_parser.extract_metadata( + simple_digital_pdf_file, + "application/pdf", + ) for entry in result: assert "namespace" in entry assert "prefix" in entry diff --git a/src/paperless/tests/parsers/test_tika_parser.py b/src/paperless/tests/parsers/test_tika_parser.py index 010969259..560527934 100644 --- a/src/paperless/tests/parsers/test_tika_parser.py +++ b/src/paperless/tests/parsers/test_tika_parser.py @@ -77,10 +77,10 @@ class TestTikaParserRegistryInterface: def test_get_page_count_returns_int_with_pdf_archive( self, tika_parser: TikaDocumentParser, - sample_pdf_file: Path, + simple_digital_pdf_file: Path, ) -> None: - tika_parser._archive_path = sample_pdf_file - count = tika_parser.get_page_count(sample_pdf_file, "application/pdf") + tika_parser._archive_path = simple_digital_pdf_file + count = tika_parser.get_page_count(simple_digital_pdf_file, "application/pdf") assert isinstance(count, int) assert count > 0 diff --git a/src/paperless/tests/samples/remote/simple-digital.pdf b/src/paperless/tests/samples/remote/simple-digital.pdf deleted file mode 100644 index e450de482..000000000 Binary files a/src/paperless/tests/samples/remote/simple-digital.pdf and /dev/null differ