add metadata fixture

test/unit_tests/conftest.py

@@ -10,12 +10,15 @@ from image_prediction.estimator.adapter.adapters.keras import KerasEstimatorAdap
 from image_prediction.estimator.adapter.adapters.mock import EstimatorMock, EstimatorAdapterMock
 from image_prediction.exceptions import UnknownEstimatorAdapter, UnknownImageExtractor
 from image_prediction.image_extractor.extractors.mock import ImageExtractorMock
+from image_prediction.image_extractor.extractors.parsable import ParsablePDFImageExtractor
 
 
 @pytest.fixture
 def image_extractor(extractor_type):
     if extractor_type == "mock":
         return ImageExtractorMock()
+    elif extractor_type == "parsable_pdf":
+        return ParsablePDFImageExtractor()
     else:
         raise UnknownImageExtractor(f"No image extractor for type {extractor_type} was specified.")
 
@@ -119,3 +122,29 @@ def classes():
 
 def map_labels(numeric_labels, classes):
     return [classes[nl] for nl in numeric_labels]
+
+
+@pytest.fixture
+def metadata(images):
+    def build_image_metadata(image):
+        width, height = image.size
+        page_width = 595.32
+        page_height = 842.04
+        x1 = random.uniform(0, page_width - width)
+        x2 = x1 + width
+        y1 = random.uniform(0, page_height)
+        y2 = y1 - height
+
+        metadata = {
+            "page_width": page_width,
+            "page_height": page_height,
+            "page_idx": 0,
+            "width": width,
+            "height": height,
+            "x1": x1,
+            "x2": x2,
+            "y1": y1,
+            "y2": y2
+        }
+
+        return map(build_image_metadata, images)

test/unit_tests/image_extractor_test.py

@@ -6,3 +6,11 @@ import pytest
 def test_image_extractor_mock(image_extractor, images):
     images_extracted, metadata = map(list, zip(*image_extractor(images)))
     assert images_extracted == images
+
+
+@pytest.mark.parametrize("extractor_type", ["parsable_pdf"])
+@pytest.mark.parametrize("batch_size", [1, 2, 4])
+def test_parsable_pdf_image_extractor(image_extractor, pdf, images, metadata):
+    images_extracted, metadata_extracted = map(list, zip(*image_extractor(images)))
+    assert images_extracted == images
+    assert metadata_extracted == metadata