"""VTX-TTS Configuration & Text Processing System.

Defines VTXConfig and text symbol tokenization.
"""
from __future__ import annotations

import json
from dataclasses import dataclass
from pathlib import Path
from typing import Any, Dict


# Symbol definitions for VTX-TTS phoneme tokenization
_pad = "_"
_punctuation = ";:,.!?¡¿—…\"«»“” "
_letters = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
_letters_ipa = "ɑɐɒæɓʙβɔɕçɗɖðʤəɘɚɛɜɝɞɟʄɡɠɢʛɦɧħɥʜɨɪʝɭɬɫɮʟɱɯɰŋɳɲɴøɵɸθœɶʘɹɺɾɻʀʁɽʂʃʈʧʉʊʋⱱʌɣɤʍχʎʏʑʐʒʔʡʕʢǀǁǂǃˈˌːˑʼʴʰʱʲʷˠˤ˞↓↑→↗↘'̩'ᵻ"

symbols = [_pad] + list(_punctuation) + list(_letters) + list(_letters_ipa)
_symbol_to_id = {s: i for i, s in enumerate(symbols)}


def cleaned_text_to_sequence(cleaned_text: str) -> list[int]:
    """Converts a string of text to a sequence of IDs corresponding to the symbols in the text."""
    sequence = []
    for symbol in cleaned_text:
        if symbol in _symbol_to_id:
            sequence.append(_symbol_to_id[symbol])
    return sequence


class HParams:
    def __init__(self, **kwargs):
        for k, v in kwargs.items():
            if isinstance(v, dict):
                v = HParams(**v)
            self[k] = v

    def __getitem__(self, key):
        return getattr(self, key)

    def __setitem__(self, key, value):
        return setattr(self, key, value)

    def __contains__(self, key):
        return hasattr(self, key)

    def __repr__(self):
        return self.__dict__.__repr__()


def get_hparams_from_file(config_path: str | Path) -> HParams:
    with open(config_path, "r", encoding="utf-8") as f:
        data = f.read()
    config = json.loads(data)
    return HParams(**config)