code icon Code

PDF Validation Image

Creates validation images with rectangles for bounding box visualization

Source Code

#!/usr/bin/env python3
"""Creates validation images with rectangles for bounding box visualization.
Used to verify bounding box information when adding text annotations to PDFs. See forms.md."""

metadata = {
    "id": "code:document.pdf.validation_image",
    "name": "PDF Validation Image",
    "description": "Creates validation images with rectangles for bounding box visualization",
    "language": "python",
    "packages": ["pillow"],
    "args": [
        {"name": "page_number", "type": "number", "description": "Page number to validate", "position": 0},
        {"name": "fields_json", "type": "string", "description": "JSON file with field bounding boxes", "position": 1},
        {"name": "input_image", "type": "string", "description": "Input image path", "position": 2},
        {"name": "output_image", "type": "string", "description": "Output image path", "position": 3}
    ]
}

import json
import sys

from PIL import Image, ImageDraw


# Creates "validation" images with rectangles for the bounding box information that
# Claude creates when determining where to add text annotations in PDFs. See forms.md.


def create_validation_image(page_number, fields_json_path, input_path, output_path):
    # Input file should be in the `fields.json` format described in forms.md.
    with open(fields_json_path, 'r') as f:
        data = json.load(f)

        img = Image.open(input_path)
        draw = ImageDraw.Draw(img)
        num_boxes = 0

        for field in data["form_fields"]:
            if field["page_number"] == page_number:
                entry_box = field['entry_bounding_box']
                label_box = field['label_bounding_box']
                # Draw red rectangle over entry bounding box and blue rectangle over the label.
                draw.rectangle(entry_box, outline='red', width=2)
                draw.rectangle(label_box, outline='blue', width=2)
                num_boxes += 2

        img.save(output_path)
        print(f"Created validation image at {output_path} with {num_boxes} bounding boxes")


if __name__ == "__main__":
    if len(sys.argv) != 5:
        print("Usage: create_validation_image.py [page number] [fields.json file] [input image path] [output image path]")
        sys.exit(1)
    page_number = int(sys.argv[1])
    fields_json_path = sys.argv[2]
    input_image_path = sys.argv[3]
    output_image_path = sys.argv[4]
    create_validation_image(page_number, fields_json_path, input_image_path, output_image_path)