For Markdown documents, 'pages' are line numbers. Find nodes whose line_num falls within [min(page_nums), max(page_nums)] and return their text.
(doc_info: dict, page_nums: list[int])
| 54 | |
| 55 | |
| 56 | def _get_md_page_content(doc_info: dict, page_nums: list[int]) -> list[dict]: |
| 57 | """ |
| 58 | For Markdown documents, 'pages' are line numbers. |
| 59 | Find nodes whose line_num falls within [min(page_nums), max(page_nums)] and return their text. |
| 60 | """ |
| 61 | min_line, max_line = min(page_nums), max(page_nums) |
| 62 | results = [] |
| 63 | seen = set() |
| 64 | |
| 65 | def _traverse(nodes): |
| 66 | for node in nodes: |
| 67 | ln = node.get('line_num') |
| 68 | if ln and min_line <= ln <= max_line and ln not in seen: |
| 69 | seen.add(ln) |
| 70 | results.append({'page': ln, 'content': node.get('text', '')}) |
| 71 | if node.get('nodes'): |
| 72 | _traverse(node['nodes']) |
| 73 | |
| 74 | _traverse(doc_info.get('structure', [])) |
| 75 | results.sort(key=lambda x: x['page']) |
| 76 | return results |
| 77 | |
| 78 | |
| 79 | # ── Tool functions ──────────────────────────────────────────────────────────── |
no test coverage detected