"""
Custom Chess Tokenizer - Final Fix
"""
from __future__ import annotations
import json
import os
import shutil
import re
from typing import Dict, List, Optional
from transformers import PreTrainedTokenizer

MOVE_RE = re.compile(r"([a-h][1-8])([a-h][1-8])")
PROMO_RE = re.compile(r"=([NBRQ])")

def normalize_move(tok: str) -> str:
    if tok.startswith("["): return tok
    m = MOVE_RE.search(tok)
    if not m: return tok 
    fr, to = m.group(1), m.group(2)
    promo = ""
    pm = PROMO_RE.search(tok)
    if pm: promo = "=" + pm.group(1)
    prefix = tok[:2] if len(tok) >= 2 else "WP"
    return f"{prefix}{fr}{to}{promo}"

class ChessTokenizer(PreTrainedTokenizer):
    model_input_names = ["input_ids", "attention_mask"]
    vocab_files_names = {"vocab_file": "vocab.json"}
    
    PAD_TOKEN = "[PAD]"
    BOS_TOKEN = "[BOS]"
    EOS_TOKEN = "[EOS]"
    UNK_TOKEN = "[UNK]"
    
    def __init__(self, vocab_file=None, vocab=None, **kwargs):
        self._pad_token = self.PAD_TOKEN
        self._bos_token = self.BOS_TOKEN
        self._eos_token = self.EOS_TOKEN
        self._unk_token = self.UNK_TOKEN

        for t in ["pad_token", "bos_token", "eos_token", "unk_token"]: kwargs.pop(t, None)
            
        if vocab is None:
            if vocab_file is None:
                vocab_file = os.path.join(os.path.dirname(__file__), "vocab.json")
            self.vocab_file = vocab_file
            if os.path.exists(vocab_file):
                with open(vocab_file, "r", encoding="utf-8") as f: self._vocab = json.load(f)
            else: self._vocab = self._create_default_vocab()
        else:
            self._vocab = vocab
            self.vocab_file = vocab_file

        self._ids_to_tokens = {v: k for k, v in self._vocab.items()}
        super().__init__(pad_token=self.PAD_TOKEN, bos_token=self.BOS_TOKEN, eos_token=self.EOS_TOKEN, unk_token=self.UNK_TOKEN, **kwargs)


    def save_pretrained(self, save_directory: str, **kwargs):
        super().save_pretrained(save_directory, **kwargs)
        src_path = os.path.abspath(__file__)
        dst_path = os.path.join(save_directory, "tokenizer.py")
        if src_path != dst_path: shutil.copy(src_path, dst_path)
        
        config_path = os.path.join(save_directory, "tokenizer_config.json")
        if os.path.exists(config_path):
            with open(config_path, "r") as f: cfg = json.load(f)
            cfg["auto_map"] = {"AutoTokenizer": "tokenizer.ChessTokenizer"}
            with open(config_path, "w") as f: json.dump(cfg, f, indent=2)

    def _create_default_vocab(self):
        return {t: i for i, t in enumerate([self.PAD_TOKEN, self.BOS_TOKEN, self.EOS_TOKEN, self.UNK_TOKEN])}
    
    @classmethod
    def build_vocab_from_dataset(cls, dataset_name, split="train", column="text", min_frequency=2, max_vocab_size=1700, max_samples=100000):
        from datasets import load_dataset
        from collections import Counter
        
        ds = load_dataset(dataset_name, split=split, streaming=True)
        ds = ds.take(max_samples)
        
        counter = Counter()
        for ex in ds:
            # On normalise
            moves = [normalize_move(t) for t in ex[column].split()]
            counter.update(moves)
            
        special = [cls.PAD_TOKEN, cls.BOS_TOKEN, cls.EOS_TOKEN, cls.UNK_TOKEN]
        most_common = counter.most_common(max_vocab_size - len(special))
        
        vocab = {t: i for i, t in enumerate(special + [t for t, c in most_common])}
        return cls(vocab=vocab)
    
    @property
    def vocab_size(self): return len(self._vocab)
    def get_vocab(self): return dict(self._vocab)
    
    def _tokenize(self, text): return [normalize_move(t) for t in text.strip().split()]
    def _convert_token_to_id(self, token): return self._vocab.get(token, self._vocab.get(self.UNK_TOKEN))
    def _convert_id_to_token(self, index): return self._ids_to_tokens.get(index, self.UNK_TOKEN)
    def convert_tokens_to_string(self, tokens): return " ".join(t for t in tokens if t not in [self.PAD_TOKEN, self.BOS_TOKEN, self.EOS_TOKEN, self.UNK_TOKEN])
    
    def save_vocabulary(self, save_directory, filename_prefix=None):
        if not os.path.isdir(save_directory): os.makedirs(save_directory, exist_ok=True)
        path = os.path.join(save_directory, (filename_prefix + "-" if filename_prefix else "") + "vocab.json")
        with open(path, "w", encoding="utf-8") as f: json.dump(self._vocab, f, ensure_ascii=False, indent=2)
        return (path,)