Explore \index{} elements in your LaTeX aborescence

parse_index.py

import sys
from collections import defaultdict
from itertools import repeat
from pathlib import Path
from typing import DefaultDict, Iterator, List, Optional, Tuple

import click
import regex as re
from rich import print


help_msg = """
This script helps you find all occurrences of \\index{} commands matching one
or several patterns

Example:

$ python parse_index.py foo bar 'regex[-like]?'"
"""


def get_lines() -> Iterator[Tuple[Path, Tuple[int, str]]]:
    if False:
        yield from sys.stdin.readlines()
    else:
        for file in Path(".").glob("**/*.tex"):
            yield from zip(
                repeat(file), enumerate(file.read_text().split("\n"), 1)
            )


@click.command(help=help_msg)
@click.argument("pattern", default=None, nargs=-1)
def main(pattern: List[str]):
    indexes: DefaultDict[str, List[Tuple[Path, int]]] = defaultdict(list)
    for file, (nb, line) in get_lines():
        regex = r"\{((?:[^\}\{]+|(?R))*+)\}"  # match balanced {}
        for m in re.finditer(r"\\index\{", line):
            for elt in re.finditer(regex, line[m.span()[1] - 1 :], re.VERSION1):
                indexes[elt.group(1)].append((file, nb))
                break

    for kwd in sorted(indexes):
        match = list(next(re.finditer(p, kwd), None) for p in pattern)
        if len(match) == 0 or any(match):
            first_match = next(m for m in match if m is not None)
            start, stop = first_match.span()
            for file, nb in indexes[kwd]:
                print(
                    f"{file}:{nb}: {kwd[:start]}"
                    f"[bold red]{kwd[start:stop]}[/bold red]{kwd[stop:]}"
                )


if __name__ == "__main__":
    main()