Function _traverse

pageindex/retrieve.py:65–72

(nodes)

    seen = set()

    def _traverse(nodes):
        for node in nodes:
            ln = node.get('line_num')
            if ln and min_line <= ln <= max_line and ln not in seen:
                seen.add(ln)
                results.append({'page': ln, 'content': node.get('text', '')})
            if node.get('nodes'):
                _traverse(node['nodes'])

    _traverse(doc_info.get('structure', []))
    results.sort(key=lambda x: x['page'])