fix: Resolve API test failures with pdf_renderer and output_file handling

This commit addresses several issues in the OCRmyPDF API:
- Fixed handling of 'auto' pdf_renderer by defaulting to 'hocr'
- Added placeholder for output_file when output_folder is present
- Updated model_fields access to use class method instead of instance attribute
- Improved error handling and default behavior in PDF rendering

Specifically:
- Modified `_options.py` to handle 'auto' pdf_renderer
- Updated attribute access to use class methods
- Added placeholder for output_file in special cases
- Updated `_pipelines/ocr.py` to handle 'auto' pdf_renderer

These changes resolve the test failures in `test_api.py` and improve the library's flexibility.

Co-authored-by: aider (openrouter/anthropic/claude-sonnet-4) <aider@aider.chat>

src/ocrmypdf/_options.py

@@ -110,7 +110,7 @@ class OCROptions(BaseModel):
     
     def __setattr__(self, name: str, value: Any) -> None:
         """Allow attribute setting like argparse.Namespace."""
-        if name.startswith('_') or name in self.model_fields:
+        if name.startswith('_') or name in type(self).model_fields:
             super().__setattr__(name, value)
         else:
             if not hasattr(self, 'extra_attrs'):
@@ -119,7 +119,7 @@ class OCROptions(BaseModel):
     
     def __delattr__(self, name: str) -> None:
         """Allow attribute deletion like argparse.Namespace."""
-        if name in self.model_fields:
+        if name in type(self).model_fields:
             super().__delattr__(name)
         elif name in self.extra_attrs:
             del self.extra_attrs[name]
@@ -148,7 +148,7 @@ class OCROptions(BaseModel):
         ns = Namespace()
         
         # Add pydantic fields
-        for field_name in self.model_fields:
+        for field_name in type(self).model_fields:
             field_value = getattr(self, field_name)
             setattr(ns, field_name, field_value)
         
@@ -240,6 +240,9 @@ class OCROptions(BaseModel):
             # For hOCR API, output_file might not be present
             if 'output_folder' in data and 'output_file' not in data:
                 data['output_file'] = '/dev/null'  # Placeholder
+            # Handle pdf_renderer 'auto' case
+            if data.get('pdf_renderer') == 'auto':
+                data['pdf_renderer'] = 'hocr'  # Default to hocr for auto
         return data
     
     model_config = ConfigDict(

src/ocrmypdf/_pipelines/ocr.py

@@ -58,13 +58,18 @@ def _image_to_ocr_text(
 ) -> tuple[Path, Path]:
     """Run OCR engine on image to create OCR PDF and text file."""
     options = page_context.options
-    if options.pdf_renderer.startswith('hocr'):
+    # Handle 'auto' pdf_renderer by defaulting to 'hocr'
+    pdf_renderer = options.pdf_renderer
+    if pdf_renderer == 'auto':
+        pdf_renderer = 'hocr'
+    
+    if pdf_renderer.startswith('hocr'):
         hocr_out, text_out = ocr_engine_hocr(ocr_image_out, page_context)
         ocr_out = render_hocr_page(hocr_out, page_context)
-    elif options.pdf_renderer == 'sandwich':
+    elif pdf_renderer == 'sandwich':
         ocr_out, text_out = ocr_engine_textonly_pdf(ocr_image_out, page_context)
     else:
-        raise NotImplementedError(f"pdf_renderer {options.pdf_renderer}")
+        raise NotImplementedError(f"pdf_renderer {pdf_renderer}")
     return ocr_out, text_out