1from dataclasses import dataclass
2import json
3import sys
4 
5 
6 
7 
8@dataclass
9class RectAndField:
10    rect: list[float]
11    rect_type: str
12    field: dict
13 
14 
15def get_bounding_box_messages(fields_json_stream) -> list[str]:
16    messages = []
17    fields = json.load(fields_json_stream)
18    messages.append(f"Read {len(fields['form_fields'])} fields")
19 
20    def rects_intersect(r1, r2):
21        disjoint_horizontal = r1[0] >= r2[2] or r1[2] <= r2[0]
22        disjoint_vertical = r1[1] >= r2[3] or r1[3] <= r2[1]
23        return not (disjoint_horizontal or disjoint_vertical)
24 
25    rects_and_fields = []
26    for f in fields["form_fields"]:
27        rects_and_fields.append(RectAndField(f["label_bounding_box"], "label", f))
28        rects_and_fields.append(RectAndField(f["entry_bounding_box"], "entry", f))
29 
30    has_error = False
31    for i, ri in enumerate(rects_and_fields):
32        for j in range(i + 1, len(rects_and_fields)):
33            rj = rects_and_fields[j]
34            if ri.field["page_number"] == rj.field["page_number"] and rects_intersect(ri.rect, rj.rect):
35                has_error = True
36                if ri.field is rj.field:
37                    messages.append(f"FAILURE: intersection between label and entry bounding boxes for `{ri.field['description']}` ({ri.rect}, {rj.rect})")
38                else:
39                    messages.append(f"FAILURE: intersection between {ri.rect_type} bounding box for `{ri.field['description']}` ({ri.rect}) and {rj.rect_type} bounding box for `{rj.field['description']}` ({rj.rect})")
40                if len(messages) >= 20:
41                    messages.append("Aborting further checks; fix bounding boxes and try again")
42                    return messages
43        if ri.rect_type == "entry":
44            if "entry_text" in ri.field:
45                font_size = ri.field["entry_text"].get("font_size", 14)
46                entry_height = ri.rect[3] - ri.rect[1]
47                if entry_height < font_size:
48                    has_error = True
49                    messages.append(f"FAILURE: entry bounding box height ({entry_height}) for `{ri.field['description']}` is too short for the text content (font size: {font_size}). Increase the box height or decrease the font size.")
50                    if len(messages) >= 20:
51                        messages.append("Aborting further checks; fix bounding boxes and try again")
52                        return messages
53 
54    if not has_error:
55        messages.append("SUCCESS: All bounding boxes are valid")
56    return messages
57 
58if __name__ == "__main__":
59    if len(sys.argv) != 2:
60        print("Usage: check_bounding_boxes.py [fields.json]")
61        sys.exit(1)
62    with open(sys.argv[1]) as f:
63        messages = get_bounding_box_messages(f)
64    for msg in messages:
65        print(msg)
66