Function list_to_tree

pageindex/utils.py:324–370

(data)

def list_to_tree(data):
    def get_parent_structure(structure):
        """Helper function to get the parent structure code"""
        if not structure:
            return None
        parts = str(structure).split('.')
        return '.'.join(parts[:-1]) if len(parts) > 1 else None
    
    # First pass: Create nodes and track parent-child relationships
    nodes = {}
    root_nodes = []
    
    for item in data:
        structure = item.get('structure')
        node = {
            'title': item.get('title'),
            'start_index': item.get('start_index'),
            'end_index': item.get('end_index'),
            'nodes': []
        }
        
        nodes[structure] = node
        
        # Find parent
        parent_structure = get_parent_structure(structure)
        
        if parent_structure:
            # Add as child to parent if parent exists
            if parent_structure in nodes:
                nodes[parent_structure]['nodes'].append(node)
            else:
                root_nodes.append(node)
        else:
            # No parent, this is a root node
            root_nodes.append(node)
    
    # Helper function to clean empty children arrays
    def clean_node(node):
        if not node['nodes']:
            del node['nodes']
        else:
            for child in node['nodes']:
                clean_node(child)
        return node
    
    # Clean and return the tree
    return [clean_node(node) for node in root_nodes]

def add_preface_if_needed(data):
    if not isinstance(data, list) or not data: