main
 1from dataclasses import dataclass
 2import json
 3import sys
 4
 5
 6# Script to check that the `fields.json` file that Claude creates when analyzing PDFs
 7# does not have overlapping bounding boxes. See forms.md.
 8
 9
10@dataclass
11class RectAndField:
12    rect: list[float]
13    rect_type: str
14    field: dict
15
16
17# Returns a list of messages that are printed to stdout for Claude to read.
18def get_bounding_box_messages(fields_json_stream) -> list[str]:
19    messages = []
20    fields = json.load(fields_json_stream)
21    messages.append(f"Read {len(fields['form_fields'])} fields")
22
23    def rects_intersect(r1, r2):
24        disjoint_horizontal = r1[0] >= r2[2] or r1[2] <= r2[0]
25        disjoint_vertical = r1[1] >= r2[3] or r1[3] <= r2[1]
26        return not (disjoint_horizontal or disjoint_vertical)
27
28    rects_and_fields = []
29    for f in fields["form_fields"]:
30        rects_and_fields.append(RectAndField(f["label_bounding_box"], "label", f))
31        rects_and_fields.append(RectAndField(f["entry_bounding_box"], "entry", f))
32
33    has_error = False
34    for i, ri in enumerate(rects_and_fields):
35        # This is O(N^2); we can optimize if it becomes a problem.
36        for j in range(i + 1, len(rects_and_fields)):
37            rj = rects_and_fields[j]
38            if ri.field["page_number"] == rj.field["page_number"] and rects_intersect(ri.rect, rj.rect):
39                has_error = True
40                if ri.field is rj.field:
41                    messages.append(f"FAILURE: intersection between label and entry bounding boxes for `{ri.field['description']}` ({ri.rect}, {rj.rect})")
42                else:
43                    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})")
44                if len(messages) >= 20:
45                    messages.append("Aborting further checks; fix bounding boxes and try again")
46                    return messages
47        if ri.rect_type == "entry":
48            if "entry_text" in ri.field:
49                font_size = ri.field["entry_text"].get("font_size", 14)
50                entry_height = ri.rect[3] - ri.rect[1]
51                if entry_height < font_size:
52                    has_error = True
53                    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.")
54                    if len(messages) >= 20:
55                        messages.append("Aborting further checks; fix bounding boxes and try again")
56                        return messages
57
58    if not has_error:
59        messages.append("SUCCESS: All bounding boxes are valid")
60    return messages
61
62if __name__ == "__main__":
63    if len(sys.argv) != 2:
64        print("Usage: check_bounding_boxes.py [fields.json]")
65        sys.exit(1)
66    # Input file should be in the `fields.json` format described in forms.md.
67    with open(sys.argv[1]) as f:
68        messages = get_bounding_box_messages(f)
69    for msg in messages:
70        print(msg)