test: enable mypy typing checks for test/components/converters/image (#12750)

pyproject.toml

@@ -150,7 +150,7 @@ all = 'pytest {args:test}'
 e2e = 'pytest {args:e2e}'
 
 # TODO We want to eventually type the whole test folder
-types = "mypy --install-types --non-interactive --cache-dir=.mypy_cache/ {args:haystack test/core/ test/marshal/ test/testing/ test/tracing/ test/tools/ test/hooks/budget/ test/hooks/human_in_the_loop test/hooks/tool_result_offloading/ test/hooks/test_from_function.py test/hooks/test_invocation.py test/hooks/test_utils.py test/evaluation test/document_stores test/dataclasses test/utils/ test/fuzz/ test/skill_stores/ test/token_counters/ test/components/agents/test_state_class.py test/components/agents/test_agent_hooks.py test/components/agents/test_agent_hitl.py test/components/builders/ test/components/caching/ test/components/converters/test_csv_to_document.py test/components/converters/test_textfile_to_document.py test/components/converters/test_utils.py test/components/embedders/ test/components/evaluators/ test/components/extractors/ test/components/fetchers/ test/components/generators/ test/components/joiners/ test/components/preprocessors/ test/components/query/ test/components/rankers/ test/components/retrievers/ test/components/routers/ test/components/samplers/ test/components/validators/ test/components/writers/}"
+types = "mypy --install-types --non-interactive --cache-dir=.mypy_cache/ {args:haystack test/core/ test/marshal/ test/testing/ test/tracing/ test/tools/ test/hooks/budget/ test/hooks/human_in_the_loop test/hooks/tool_result_offloading/ test/hooks/test_from_function.py test/hooks/test_invocation.py test/hooks/test_utils.py test/evaluation test/document_stores test/dataclasses test/utils/ test/fuzz/ test/skill_stores/ test/token_counters/ test/components/agents/test_state_class.py test/components/agents/test_agent_hooks.py test/components/agents/test_agent_hitl.py test/components/builders/ test/components/caching/ test/components/converters/image/ test/components/converters/test_csv_to_document.py test/components/converters/test_textfile_to_document.py test/components/converters/test_utils.py test/components/embedders/ test/components/evaluators/ test/components/extractors/ test/components/fetchers/ test/components/generators/ test/components/joiners/ test/components/preprocessors/ test/components/query/ test/components/rankers/ test/components/retrievers/ test/components/routers/ test/components/samplers/ test/components/validators/ test/components/writers/}"
 
 [project.urls]
 "CI: GitHub" = "https://github.com/deepset-ai/haystack/actions"

test/components/converters/image/test_document_to_image_content.py

@@ -68,13 +68,13 @@ class TestDocumentToImageContent:
         with pytest.raises(ValueError, match="has an unsupported MIME type"):
             _ = converter.run(documents=[docx_doc])
 
-    def test_run_with_invalid_file_path(self, caplog) -> None:
+    def test_run_with_invalid_file_path(self, caplog: pytest.LogCaptureFixture) -> None:
         converter = DocumentToImageContent()
         pdf_doc = Document(content="test", meta={"file_path": "wrong_name.jpg"})
         with pytest.raises(ValueError, match="has an invalid file path 'wrong_name.jpg'"):
             _ = converter.run(documents=[pdf_doc])
 
-    def test_run_with_pdf_missing_page_number(self, caplog) -> None:
+    def test_run_with_pdf_missing_page_number(self, caplog: pytest.LogCaptureFixture) -> None:
         converter = DocumentToImageContent()
         pdf_doc = Document(content="test", meta={"file_path": "test/test_files/pdf/sample_pdf_1.pdf"})
         with pytest.raises(ValueError, match="is missing the 'page_number' key"):
@@ -85,17 +85,18 @@ class TestDocumentToImageContent:
         image_doc = Document(content="test", meta={"file_path": "apple.jpg"})
         results = converter.run(documents=[image_doc])
         assert len(results["image_contents"]) == 1
-        assert results["image_contents"][0].meta == {"file_path": "apple.jpg"}
+        image_content = results["image_contents"][0]
+        assert image_content is not None
+        assert image_content.meta == {"file_path": "apple.jpg"}
 
     def test_run_with_pdf_documents(self) -> None:
         converter = DocumentToImageContent()
         pdf_doc = Document(content="test", meta={"file_path": "test/test_files/pdf/sample_pdf_1.pdf", "page_number": 1})
         results = converter.run(documents=[pdf_doc])
         assert len(results["image_contents"]) == 1
-        assert results["image_contents"][0].meta == {
-            "file_path": "test/test_files/pdf/sample_pdf_1.pdf",
-            "page_number": 1,
-        }
+        image_content = results["image_contents"][0]
+        assert image_content is not None
+        assert image_content.meta == {"file_path": "test/test_files/pdf/sample_pdf_1.pdf", "page_number": 1}
 
     def test_run_with_mixed_document_types(self) -> None:
         converter = DocumentToImageContent(root_path="test/test_files")

test/components/converters/image/test_file_to_document.py

@@ -55,12 +55,13 @@ class TestImageFileToDocument:
         assert len(results["documents"]) == 0
         assert results == {"documents": []}
 
-    def test_run_with_invalid_source_type(self, caplog) -> None:
+    def test_run_with_invalid_source_type(self, caplog: pytest.LogCaptureFixture) -> None:
         converter = ImageFileToDocument()
-        converter.run(sources=[123])  # Invalid source type
+        # The invalid source type is what this test exercises.
+        converter.run(sources=[123])  # type: ignore[list-item]
         assert "Could not read" in caplog.text
 
-    def test_run_with_non_existent_file(self, caplog) -> None:
+    def test_run_with_non_existent_file(self, caplog: pytest.LogCaptureFixture) -> None:
         converter = ImageFileToDocument()
         converter.run(sources=["./non_existent_file.png"])
         assert "Could not read" in caplog.text

test/components/converters/image/test_file_to_image.py

@@ -65,12 +65,13 @@ class TestImageFileToImageContent:
         assert len(results["image_contents"]) == 0
         assert results == {"image_contents": []}
 
-    def test_run_with_invalid_source_type(self, caplog) -> None:
+    def test_run_with_invalid_source_type(self, caplog: pytest.LogCaptureFixture) -> None:
         converter = ImageFileToImageContent()
-        converter.run(sources=[123])  # Invalid source type
+        # The invalid source type is what this test exercises.
+        converter.run(sources=[123])  # type: ignore[list-item]
         assert "Could not read" in caplog.text
 
-    def test_run_with_non_existent_file(self, caplog) -> None:
+    def test_run_with_non_existent_file(self, caplog: pytest.LogCaptureFixture) -> None:
         converter = ImageFileToImageContent()
         converter.run(sources=["./non_existent_file.png"])
         assert "Could not read" in caplog.text

test/components/converters/image/test_image_utils.py

@@ -51,9 +51,11 @@ class TestConvertPdfToImages:
         pages_images = _convert_pdf_to_images(bytestream=bytestream, page_range=[1], size=(100, 100))
 
         assert len(pages_images) == 1
-        assert pages_images[0][0] == 1
-        assert pages_images[0][1].width <= 100
-        assert pages_images[0][1].height <= 100
+        page_number, image = pages_images[0]
+        assert page_number == 1
+        assert isinstance(image, Image.Image)
+        assert image.width <= 100
+        assert image.height <= 100
 
     def test_convert_pdf_to_images_invalid_page(self, caplog: LogCaptureFixture) -> None:
         bytestream = get_bytestream_from_source(Path("test/test_files/pdf/sample_pdf_1.pdf"))

test/components/converters/image/test_pdf_to_image.py

@@ -4,6 +4,8 @@
 
 from pathlib import Path
 
+import pytest
+
 from haystack.components.converters.image.image_utils import _convert_pdf_to_images
 from haystack.components.converters.image.pdf_to_image import PDFToImageContent
 from haystack.core.serialization import component_from_dict, component_to_dict
@@ -60,12 +62,13 @@ class TestPDFToImageContent:
         assert len(results["image_contents"]) == 0
         assert results == {"image_contents": []}
 
-    def test_run_with_invalid_source_type(self, caplog) -> None:
+    def test_run_with_invalid_source_type(self, caplog: pytest.LogCaptureFixture) -> None:
         converter = PDFToImageContent()
-        converter.run(sources=[123])  # Invalid source type
+        # The invalid source type is what this test exercises.
+        converter.run(sources=[123])  # type: ignore[list-item]
         assert "Could not read" in caplog.text
 
-    def test_run_with_non_existent_file(self, caplog) -> None:
+    def test_run_with_non_existent_file(self, caplog: pytest.LogCaptureFixture) -> None:
         converter = PDFToImageContent()
         converter.run(sources=["./non_existent_file.png"])
         assert "Could not read" in caplog.text