56 lines
2.1 KiB
Python
56 lines
2.1 KiB
Python
import json
|
|
import sys
|
|
|
|
from PIL import Image, ImageDraw
|
|
from pathlib import Path
|
|
|
|
|
|
def safe_user_path(path_value, base_dir="."):
|
|
"""Resolve a CLI path under the current workspace."""
|
|
if base_dir != ".":
|
|
raise ValueError("Custom base directories are not supported for CLI paths")
|
|
base_path = Path.cwd().resolve()
|
|
resolved_path = Path(path_value).expanduser().resolve()
|
|
try:
|
|
resolved_path.relative_to(base_path)
|
|
except ValueError as exc:
|
|
raise ValueError(f"Path escapes allowed directory: {path_value}") from exc
|
|
return resolved_path
|
|
|
|
|
|
# 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 = safe_user_path(sys.argv[2])
|
|
input_image_path = safe_user_path(sys.argv[3])
|
|
output_image_path = safe_user_path(sys.argv[4])
|
|
create_validation_image(page_number, fields_json_path, input_image_path, output_image_path)
|