fix(pdf): convert CMYK images before vision analysis (#6917)

src/document_processor.py

@@ -142,7 +142,10 @@ def _process_pdf(
                         with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as tmp:
                             temp_img_path = tmp.name
                         try:
-                            img.image.save(temp_img_path, "PNG")  # pypdf -> PIL image
+                            image = img.image
+                            if image.mode == "CMYK":
+                                image = image.convert("RGB")
+                            image.save(temp_img_path, "PNG")
                             ocr_text = analyze_image_with_vl(temp_img_path, owner=owner)
                             if ocr_text and "unavailable" not in ocr_text.lower():
                                 pdf_text += f"\n\n[Page {page_num + 1} image {img_index + 1} text]: {ocr_text}"

tests/test_pdf_cmyk_image_analysis.py

@@ -0,0 +1,98 @@
+"""Actual embedded PDF images must reach vision as a decodable PNG."""
+from pathlib import Path
+
+from PIL import Image
+from pypdf import PdfReader, PdfWriter
+from pypdf.generic import DecodedStreamObject, DictionaryObject, NameObject, NumberObject
+import pytest
+
+from src import document_processor as dp
+
+
+def make_pdf(tmp_path, mode):
+    colors = {"CMYK": (0, 255, 255, 0), "RGB": (255, 0, 0), "L": 127}
+    path = tmp_path / (mode + ".pdf")
+    image = Image.new(mode, (128, 96), colors[mode])
+    if mode == "CMYK":
+        # A raw DeviceCMYK XObject avoids JPEG/Adobe inversion differences in
+        # Pillow-generated PDFs; the extracted color samples are unambiguous.
+        writer = PdfWriter()
+        page = writer.add_blank_page(width=128, height=96)
+        stream = DecodedStreamObject()
+        stream.set_data(image.tobytes())
+        stream.update({NameObject(key): value for key, value in {
+            "/Type": NameObject("/XObject"), "/Subtype": NameObject("/Image"),
+            "/ColorSpace": NameObject("/DeviceCMYK"), "/BitsPerComponent": NumberObject(8),
+            "/Width": NumberObject(128), "/Height": NumberObject(96),
+        }.items()})
+        page[NameObject("/Resources")] = DictionaryObject({NameObject("/XObject"):
+            DictionaryObject({NameObject("/Im0"): writer._add_object(stream)})})
+        content = DecodedStreamObject()
+        content.set_data(b"q 128 0 0 96 0 0 cm /Im0 Do Q")
+        page[NameObject("/Contents")] = writer._add_object(content)
+        writer.write(path)
+    else:
+        image.save(path, "PDF")
+    assert PdfReader(path).pages[0].images[0].image.mode == mode
+    return path
+
+
+@pytest.mark.parametrize("mode,expected", [("CMYK", "RGB"), ("RGB", "RGB"), ("L", "L")])
+def test_pdf_image_reaches_vision_with_owner_and_png_pixels(tmp_path, monkeypatch, mode, expected):
+    pdf = make_pdf(tmp_path, mode)
+    calls = []
+    def analyze(path, owner=None):
+        with Image.open(path) as image:
+            image.load()
+            assert image.format == "PNG" and image.mode == expected
+            assert image.size == (128, 96)
+            if mode == "CMYK":
+                red, green, blue = image.getpixel((64, 48))
+                assert red > 250 and green < 5 and blue < 5
+            calls.append((Path(path), owner))
+        return "Synthetic OCR result"
+    monkeypatch.setattr(dp, "analyze_image_with_vl", analyze)
+    output = dp._process_pdf(str(pdf), owner="alice")
+    assert "[Page 1 image 1 text]: Synthetic OCR result" in output
+    assert len(calls) == 1 and calls[0][1] == "alice"
+    assert not calls[0][0].exists(), "Temporary PNG must be removed after analysis"
+    assert PdfReader(pdf).pages[0].images[0].image.mode == mode, "Source PDF is unchanged"
+
+
+def test_mixed_pdf_keeps_images_on_both_pages(tmp_path, monkeypatch):
+    writer = PdfWriter()
+    for mode in ("CMYK", "RGB"):
+        writer.append(str(make_pdf(tmp_path, mode)))
+    pdf = tmp_path / "mixed.pdf"
+    writer.write(pdf)
+    calls = []
+    def analyze(path, owner=None):
+        with Image.open(path) as image:
+            image.load()
+            calls.append(image.mode)
+        return "Image content"
+    monkeypatch.setattr(dp, "analyze_image_with_vl", analyze)
+    output = dp._process_pdf(str(pdf), owner="alice")
+    assert calls == ["RGB", "RGB"]
+    assert "Page 1 image 1 text" in output and "Page 2 image 1 text" in output
+
+
+def test_text_only_extraction_does_not_enable_vision(tmp_path, monkeypatch):
+    pdf = make_pdf(tmp_path, "CMYK")
+    def unexpected(*args, **kwargs):
+        pytest.fail("Text-only extraction must not call vision")
+    monkeypatch.setattr(dp, "analyze_image_with_vl", unexpected)
+    assert "no readable content" in dp.extract_local_document(str(pdf), owner="alice")
+
+
+def test_vision_failure_still_removes_converted_png(tmp_path, monkeypatch):
+    pdf = make_pdf(tmp_path, "CMYK")
+    paths = []
+    def unavailable(path, owner=None):
+        paths.append(Path(path))
+        with Image.open(path) as image:
+            assert image.mode == "RGB" and image.format == "PNG"
+        raise RuntimeError("Synthetic unavailable vision endpoint")
+    monkeypatch.setattr(dp, "analyze_image_with_vl", unavailable)
+    assert "no readable content" in dp._process_pdf(str(pdf), owner="alice")
+    assert len(paths) == 1 and not paths[0].exists()