Go through a bunch of exported MindMup .mup files looking for text

search_mup.py

"""
Iterates through a directory of exported MindMup .mup files and prints the title of each file that matches the given
regular expression, as well as the matched node contents.

MindMup is a mind mapping tool which represents the Directed Acyclic Graph (DAG) of a mind map as a nested dictionary encoded as JSON.
"""

import argparse
import json
from pathlib import Path
import re
from typing import Generator


def nested_dict_iter(nested: dict) -> Generator[tuple[str, str], None, None]:
    """
    Iterates through a nested dictionary yielding any top-level (no children/nesting) keys and values.
    """
    for key, value in nested.items():
        if isinstance(value, dict):
            for inner_key, inner_value in nested_dict_iter(value):
                yield inner_key, inner_value
        else:
            yield key, value


if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("directory", help="the directory to search")
    parser.add_argument("regex", help="the regular expression to use")
    args = parser.parse_args()

    exp = re.compile(args.regex)
    search_dir = Path(args.directory)

    assert search_dir.is_dir()

    # Could instead read from stdin to enable piping from other commands
    for mup in search_dir.glob("*.mup"):
        with mup.open("r") as fi:
            jmup = json.load(fi)

        file_printed = False

        for key, val in nested_dict_iter(jmup):
            # node text contents are stored in the "title" key
            if key == "title" and exp.search(val) is not None:
                if not file_printed:
                    file_printed = True
                    print()
                    print(mup)

                print(val)