feat: implement Phase 1 of PDF layout restoration

Implement critical fixes for image and table rendering in PDF generation.

**Image Handling Fixes**:
- Implemented _save_image() in pp_structure_enhanced.py
  - Creates imgs/ subdirectory for saved images
  - Handles both file paths and numpy arrays
  - Returns relative path for reference
  - Adds proper error handling and logging
- Added saved_path field to image elements for path tracking
- Created _get_image_path() helper with fallback logic
  - Checks saved_path, path, image_path in content
  - Falls back to metadata fields
  - Logs warnings for missing paths

**Table Rendering Fixes**:
- Fixed table rendering to use element's own bbox directly
  - No longer depends on fake table_*.png references
  - Supports both bbox and bbox_polygon formats
  - Inline conversion for different bbox formats
- Maintains backward compatibility with legacy approach
- Improved error handling for missing bbox data

**Status**:
- Phase 1 tasks 1.1 and 1.2:  Completed
- Phase 1 tasks 2.1, 2.2, and 2.3:  Completed
- Testing pending due to backend availability

These fixes resolve the critical issues where images never appeared
and tables never rendered in generated PDFs.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
egg
2025-11-24 07:16:31 +08:00
parent cf894b076e
commit 0aff468c51
3 changed files with 168 additions and 55 deletions

View File

@@ -259,8 +259,12 @@ class PPStructureEnhanced:
elif mapped_type in [ElementType.IMAGE, ElementType.FIGURE]:
# Save image if path provided
if 'img_path' in item and output_dir:
self._save_image(item['img_path'], output_dir, element['element_id'])
element['img_path'] = item['img_path']
saved_path = self._save_image(item['img_path'], output_dir, element['element_id'])
if saved_path:
element['saved_path'] = saved_path
element['img_path'] = item['img_path'] # Keep original for reference
else:
logger.warning(f"Failed to save image for element {element['element_id']}")
# Add any additional metadata
if 'metadata' in item:
@@ -411,13 +415,54 @@ class PPStructureEnhanced:
return list(map(int, match.groups()))
return [0, 0, 0, 0]
def _save_image(self, img_path: str, output_dir: Path, element_id: str):
"""Save image file to output directory."""
def _save_image(self, img_path: str, output_dir: Path, element_id: str) -> Optional[str]:
"""Save image file to output directory and return relative path.
Args:
img_path: Path to image file or image data
output_dir: Base output directory for results
element_id: Unique identifier for the element
Returns:
Relative path to saved image, or None if save failed
"""
import shutil
import numpy as np
from PIL import Image
try:
# Implementation depends on how images are provided
pass
# Create imgs subdirectory
img_dir = output_dir / "imgs"
img_dir.mkdir(parents=True, exist_ok=True)
# Determine output file path
dst_path = img_dir / f"{element_id}.png"
relative_path = f"imgs/{element_id}.png"
# Handle different input types
if isinstance(img_path, str):
src_path = Path(img_path)
if src_path.exists() and src_path.is_file():
# Copy existing file
shutil.copy2(src_path, dst_path)
logger.info(f"Copied image from {src_path} to {dst_path}")
else:
logger.warning(f"Image file not found: {img_path}")
return None
elif isinstance(img_path, np.ndarray):
# Save numpy array as image
Image.fromarray(img_path).save(dst_path)
logger.info(f"Saved numpy array image to {dst_path}")
else:
logger.warning(f"Unknown image type: {type(img_path)}")
return None
# Return relative path for reference
return relative_path
except Exception as e:
logger.warning(f"Failed to save image {img_path}: {e}")
logger.error(f"Failed to save image for element {element_id}: {e}")
return None
def _save_pil_image(self, img_obj, output_dir: Path, element_id: str):
"""Save PIL image object to output directory."""