tokenizer.py

from __future__ import annotations
import json
import os
import re
from pathlib import Path
from typing import Dict, List, Optional, Tuple
from transformers import PreTrainedTokenizer

_MOVE_RE = re.compile(
    r"^(?P<side>[WB])"
    r"(?P<piece>[PNBRQK])"
    r"(?P<src>[a-h][1-8])"
    r"(?P<dst>[a-h][1-8])"
    r"(?P<suffix>.*)$"
)

# Promotions like "=Q" or "=q"
_PROMO_RE = re.compile(r"=([QRBNqrbn])")

def _parse_suffix(suffix: str) -> Tuple[bool, bool, bool, Optional[str], Optional[str]]:
    
    if not suffix:
        return False, False, False, None, None
    suf = suffix.strip()
    is_capture = "x" in suf
    is_check = "+" in suf
    is_mate = "*" in suf
    castle_kind = None
    if "(O)" in suf:
        castle_kind = "q"
    elif "(o)" in suf:
        castle_kind = "k"
    promo_piece = None
    m = _PROMO_RE.search(suf)
    if m:
        promo_piece = m.group(1).lower()
    return is_capture, is_check, is_mate, castle_kind, promo_piece

def _reindex_vocab(vocab: Dict[str, int]) -> Dict[str, int]:
    # sort by old id for stability
    items = sorted(vocab.items(), key=lambda kv: kv[1])
    return {tok: new_id for new_id, (tok, _) in enumerate(items)}

class ChessTokenizer(PreTrainedTokenizer):
    
    model_input_names = ["input_ids", "attention_mask"]
    vocab_files_names = {"vocab_file": "vocab.json"}
    
    # Special tokens
    PAD_TOKEN = "[PAD]"
    BOS_TOKEN = "[BOS]"
    EOS_TOKEN = "[EOS]"
    UNK_TOKEN = "[UNK]" 
    
    SIDE_TOKENS = ("[W]", "[B]")
    PIECE_TOKENS = ("[P]", "[N]", "[B]", "[R]", "[Q]", "[K]")
    
    FLAG_TOKENS = (
        "[x]",       # capture
        "[+]",       # check
        "[#]",       # mate
        "[O-O]",     # kingside castle marker (not required by evaluator)
        "[O-O-O]",   # queenside castle marker
        "[=q]", "[=r]", "[=b]", "[=n]",
    )
    
    def __init__(
        self,
        vocab_file: Optional[str] = None,
        vocab: Optional[Dict[str, int]] = 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
        
        kwargs.pop("pad_token", None)
        kwargs.pop("bos_token", None)
        kwargs.pop("eos_token", None)
        kwargs.pop("unk_token", None)
        
        if vocab is not None:
            self._vocab = vocab
        elif vocab_file is not None and 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()
        
        self._vocab = _reindex_vocab(self._vocab)
        
        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 _create_default_vocab(self) -> Dict[str, int]:
        
        tokens: List[str] = [self.PAD_TOKEN, self.BOS_TOKEN, self.EOS_TOKEN, self.UNK_TOKEN]
        tokens += list(self.SIDE_TOKENS)
        tokens += list(self.PIECE_TOKENS)
        for file in "abcdefgh":
            for rank in "12345678":
                tokens.append(f"[{file}{rank}]")
        tokens += list(self.FLAG_TOKENS)
        return {tok: idx for idx, tok in enumerate(tokens)}
    
    @classmethod
    def build_vocab_from_iterator(
        cls,
        iterator,
        min_frequency: int = 1,
    ) -> "ChessTokenizer":
        return cls()
    
    @classmethod
    def build_vocab_from_dataset(
        cls,
        dataset_name: str = "dlouapre/lichess_2025-01_1M",
        split: str = "train",
        column: str = "text",
        min_frequency: int = 500,
        max_samples: Optional[int] = 100000,
    ) -> "ChessTokenizer":
        return cls()
    
    @property
    def vocab_size(self) -> int:
        return len(self._vocab)
    
    def get_vocab(self) -> Dict[str, int]:
        return dict(self._vocab)
    
    def _tokenize(self, text: str) -> List[str]:
      
        text = (text or "").strip()
        if not text:
            return []
        
        chunks = text.split()
        out: List[str] = []
        
        for chunk in chunks:
            if re.fullmatch(r"[a-h][1-8][a-h][1-8][qrbn]?", chunk):
                src = chunk[0:2]
                dst = chunk[2:4]                
                out.append(f"[{src}]")
                out.append(f"[{dst}]")
                if len(chunk) == 5 and chunk[4] in "qrbn":
                    out.append(f"[={chunk[4]}]")
                continue
            
            m = _MOVE_RE.match(chunk)
            if not m:
                out.append(self.UNK_TOKEN)
                continue
            
            side = "[W]" if m.group("side") == "W" else "[BL]"
            piece = m.group("piece")
            src = m.group("src")
            dst = m.group("dst")
            suffix = m.group("suffix") or ""
            
            out.append(side)
            out.append(f"[{piece}]")
            out.append(f"[{src}]")
            out.append(f"[{dst}]")
            
            is_cap, is_chk, is_mate, castle_kind, promo = _parse_suffix(suffix)
            
            if castle_kind == "k":
                out.append("[O-O]")
            elif castle_kind == "q":
                out.append("[O-O-O]")
            
            if is_cap:
                out.append("[x]")
            
            if is_mate:
                out.append("[#]")
            elif is_chk:
                out.append("[+]")
            
            if promo in ("q", "r", "b", "n"):
                out.append(f"[={promo}]")
        return out
    
    def _convert_token_to_id(self, token: str) -> int:
        return self._vocab.get(token, self._vocab.get(self.UNK_TOKEN, 0))
    
    def _convert_id_to_token(self, index: int) -> str:
        return self._ids_to_tokens.get(index, self.UNK_TOKEN)
    
    def convert_tokens_to_string(self, tokens: List[str]) -> str:
        """Convert a list of tokens back to a string."""
        # Filter out special tokens for cleaner output
        special = {self.PAD_TOKEN, self.BOS_TOKEN, self.EOS_TOKEN, self.UNK_TOKEN}
        return " ".join(t for t in tokens if t not in special)
    
    def save_vocabulary(
        self,
        save_directory: str,
        filename_prefix: Optional[str] = None,
    ) -> tuple:
        
        if not os.path.isdir(save_directory):
            os.makedirs(save_directory, exist_ok=True)
        
        vocab_file = os.path.join(
            save_directory,
            (filename_prefix + "-" if filename_prefix else "") + "vocab.json",
        )
        
        with open(vocab_file, "w", encoding="utf-8") as f:
            json.dump(self._vocab, f, ensure_ascii=False, indent=2)
        
        return (vocab_file,)
    
    def build_inputs_with_special_tokens(self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None) -> List[int]:
        bos = [self.bos_token_id] if self.bos_token_id is not None else [1]
        return bos + token_ids_0

def count_vocab_from_dataset(
    dataset_name: str = "dlouapre/lichess_2025-01_1M",
    split: str = "train",
    column: str = "text",
    max_samples: Optional[int] = 10000,
) -> Dict[str, int]:
    """
    Count token frequencies in a dataset (useful for vocabulary analysis).
    """
    from collections import Counter
    from datasets import load_dataset
    
    ds = load_dataset(dataset_name, split=split)
    if max_samples is not None:
        ds = ds.select(range(min(max_samples, len(ds))))
    
    tok = ChessTokenizer()
    counts = Counter()
    for ex in ds:
        counts.update(tok._tokenize(ex[column]))
    return dict(counts)