#!/usr/bin/evn python
from __future__ import annotations

from typing import Final, override
import bisect


filename: Final[str] = "taxonomie.csv"


class Taxonomy:
    def __init__(self, niveau: int, name: str):
        self._niveau = niveau
        self._name = name
        self._id = (niveau, name)
        self._words = []
        self._sorted_fmt_words = []
        self._max_width = 0

    def add(self, word: str):
        if word not in self._words:
            bisect.insort(self._words, word, key=lambda w: w.lower())
            if (new_width := len(word)) > self._max_width:
                self._max_width = new_width

    def __getitem__(self, item):
        word = self._words[item] if item < len(self._words) else " "
        return word.ljust(self._max_width)

    def name(self):
        plain_name = f" {self._name} "
        return plain_name.center(self._max_width, "#")

    def __len__(self):
        return len(self._words)

    def __contains__(self, item):
        return item in self._words

    @override
    def __repr__(self):
        if len(self._words) < 3:
            repr_word = f"{self._words}"
        else:
            chosen_words = []
            wc = 0
            before_idx = 3
            after_idx = len(self._words) - 3
            for w in self._words:
                wc += 1
                if wc < before_idx or wc > after_idx:
                    chosen_words.append(w)
                if wc == before_idx:
                    chosen_words.append("...")
            repr_word = f"{chosen_words}"
        return f"{self._id} {repr_word} ({len(self._words)})"

    def __gt__(self, other):
        return self._niveau >= other._niveau


def group_term(line: str, data: dict[str, Taxonomy]) -> None:
    terms = tuple(t.strip() for t in line.split(";"))
    key = (int(terms[1]), terms[2])
    niveau = data.get(key, Taxonomy(key[0], key[1]))
    niveau.add(terms[0])
    if key not in data:
        data[key] = niveau


def print_taxonomy(data: dict[str, Taxonomy]) -> None:
    wc = (len(t) for t in data.values() )
    longest_taxonomie = max(wc)
    taxonomie = sorted(data.values())
    names = [t.name() for t in taxonomie]
    sep_str = " ; "
    print(sep_str.join(names))
    for i in range(0, longest_taxonomie):
        terms = []
        for t in taxonomie:
            terms.append(t[i])
        print(sep_str.join(terms))




if __name__ == "__main__":
    terms = {}
    with open(filename) as file:
        for line in file:
            group_term(line, terms)

    print_taxonomy(terms)