From 6bc9499e689bab0f301f8f04522af8024b9ef7a3 Mon Sep 17 00:00:00 2001
From: "James R. Barlow" <james@purplerock.ca>
Date: Fri, 5 Jun 2026 01:07:27 -0700
Subject: [PATCH] feat: recognize pngmonod device in pypdfium rasterizer
 (#1688)

---
 src/ocrmypdf/builtin_plugins/pypdfium.py | 21 ++++++++++++++----
 tests/test_rasterizer.py                 | 28 ++++++++++++++++++++++++
 2 files changed, 45 insertions(+), 4 deletions(-)

diff --git a/src/ocrmypdf/builtin_plugins/pypdfium.py b/src/ocrmypdf/builtin_plugins/pypdfium.py
index 8edab8f3..973b40c9 100644
--- a/src/ocrmypdf/builtin_plugins/pypdfium.py
+++ b/src/ocrmypdf/builtin_plugins/pypdfium.py
@@ -96,7 +96,12 @@ def _render_page_to_bitmap(
     # Render the page to a bitmap
     # The scale parameter controls the resolution
     # Render in grayscale for mono and gray devices (better input for 1-bit conversion)
-    grayscale = raster_device.lower() in ('pngmono', 'pnggray', 'jpeggray')
+    grayscale = raster_device.lower() in (
+        'pngmono',
+        'pngmonod',
+        'pnggray',
+        'jpeggray',
+    )
 
     # Default (use_cropbox=False) renders MediaBox for consistency with Ghostscript
     if not use_cropbox:
@@ -157,8 +162,8 @@ def _process_image_for_output(
     # This ensures pypdfium output matches Ghostscript's native device output
     raster_device_lower = raster_device.lower()
 
-    if raster_device_lower == 'pngmono':
-        # Convert to 1-bit black and white (matches Ghostscript pngmono device)
+    if raster_device_lower in ('pngmono', 'pngmonod'):
+        # Convert to 1-bit black and white (matches Ghostscript pngmono/pngmonod)
         if pil_image.mode != '1':
             if pil_image.mode not in ('L', '1'):
                 pil_image = pil_image.convert('L')
@@ -184,7 +189,15 @@ def _process_image_for_output(
     # pngalpha: keep RGBA as-is
 
     # Determine output format based on raster_device
-    png_devices = ('png', 'pngmono', 'pnggray', 'png256', 'png16m', 'pngalpha')
+    png_devices = (
+        'png',
+        'pngmono',
+        'pngmonod',
+        'pnggray',
+        'png256',
+        'png16m',
+        'pngalpha',
+    )
     if raster_device_lower in png_devices:
         format_name = 'PNG'
     elif raster_device_lower in ('jpeg', 'jpeggray', 'jpg'):
diff --git a/tests/test_rasterizer.py b/tests/test_rasterizer.py
index dec805c1..56e79593 100644
--- a/tests/test_rasterizer.py
+++ b/tests/test_rasterizer.py
@@ -213,6 +213,34 @@ class TestRasterizerHookDirect:
         assert result == img
         assert img.exists()
 
+    @pytest.mark.skipif(not PYPDFIUM_AVAILABLE, reason="pypdfium2 not installed")
+    def test_pypdfium_pngmonod_produces_1bit(self, resources, tmp_path):
+        """Pngmonod is treated like pngmono by pypdfium: it yields a 1-bit PNG."""
+        pm = get_plugin_manager([])
+        options = OcrOptions(
+            input_file=resources / 'graph.pdf',
+            output_file=tmp_path / 'out.pdf',
+            rasterizer='pypdfium',
+        )
+
+        img = tmp_path / 'pngmonod_test.png'
+        result = pm.rasterize_pdf_page(
+            input_file=resources / 'graph.pdf',
+            output_file=img,
+            raster_device='pngmonod',
+            raster_dpi=Resolution(50, 50),
+            page_dpi=Resolution(50, 50),
+            pageno=1,
+            rotation=0,
+            filter_vector=False,
+            stop_on_soft_error=True,
+            options=options,
+            use_cropbox=False,
+        )
+        assert result == img
+        with Image.open(img) as im:
+            assert im.mode == '1'
+
 
 def _create_gradient_image(width: int, height: int) -> Image.Image:
     """Create an image with multiple gradients to detect rasterization errors.