Convert tabular data to a forest.

tree.py

# First row is child, second row is parent.
rows = [
    ('h', 'd'),
    ('f', 'c'),
    ('e', 'b'),
    ('b', 'a'),
    ('d', 'b'),
    ('c', 'a'),
    ('g', 'c'),
    ('i', 'd'),
    ('j', 'd'),
]

# Posible roots are intersection of parents and children
children = set(map(lambda row: row[0], rows))
parents = set(map(lambda row: row[1], rows))
roots = parents - children
for root in roots:
    rows.append((root, root))

# Create nodes dictionary
nodes = {}
for i in rows:
    id, parent_id = i
    nodes[id] = { 'id': id }

# Create trees and parent-child relations
forest = []
for i in rows:
    id, parent_id = i
    node = nodes[id]

    # Either make the node a new tree or link it to its parent
    if id == parent_id:
        # Start a new tree in the forest
        forest.append(node)
    else:
        # Add new_node as child to parent
        parent = nodes[parent_id]
        if not 'children' in parent:
            # Ensure parent has a 'children' field
            parent['children'] = []
        children = parent['children']
        children.append(node)

print(forest)