Chess Challenge submission by mathispernin

README.md

@@ -0,0 +1,22 @@
+---
+library_name: transformers
+tags:
+- chess
+- llm-course
+- chess-challenge
+license: mit
+---
+
+## Chess model submitted to the LLM Course Chess Challenge.
+
+### Submission Info
+- **Submitted by**: [mathispernin](https://huggingface.co/mathispernin)
+- **Parameters**: 998,400
+- **Organization**: LLM-course
+
+### Model Details
+- **Architecture**: Chess Transformer (GPT-style)
+- **Vocab size**: 2383
+- **Embedding dim**: 128
+- **Layers**: 4
+- **Heads**: 4

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "ChessForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "model.ChessConfig",
+    "AutoModelForCausalLM": "model.ChessForCausalLM"
+  },
+  "bos_token_id": 1,
+  "dropout": 0.0,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "chess_transformer",
+  "n_ctx": 256,
+  "n_embd": 128,
+  "n_head": 4,
+  "n_inner": 384,
+  "n_layer": 4,
+  "norm_type": "rmsnorm",
+  "pad_token_id": 0,
+  "tie_weights": true,
+  "transformers_version": "4.57.3",
+  "vocab_size": 2383
+}

model.py

@@ -0,0 +1,463 @@
+"""
+Chess Transformer Model for the Chess Challenge.
+
+This module provides a simple GPT-style transformer architecture
+designed to fit within the 1M parameter constraint.
+
+Key components:
+- ChessConfig: Configuration class for model hyperparameters
+- ChessForCausalLM: The main model class for next-move prediction
+"""
+
+from __future__ import annotations
+
+import math
+from dataclasses import dataclass
+from typing import Optional, Tuple, Union
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from transformers import PretrainedConfig, PreTrainedModel
+from transformers.modeling_outputs import CausalLMOutputWithPast
+
+
+class ChessConfig(PretrainedConfig):
+    """
+    Configuration class for the Chess Transformer model.
+    
+    This configuration is designed for a ~1M parameter model.
+    Students can adjust these values to explore different architectures.
+    
+    Parameter budget breakdown (with default values):
+    - Embeddings (vocab): 1200 x 128 = 153,600
+    - Position Embeddings: 256 x 128 = 32,768
+    - Transformer Layers: 6 x ~120,000 = ~720,000
+    - LM Head (with weight tying): 0 (shared with embeddings)
+    - Total: ~906,000 parameters
+    
+    Attributes:
+        vocab_size: Size of the vocabulary (number of unique moves).
+        n_embd: Embedding dimension (d_model).
+        n_layer: Number of transformer layers.
+        n_head: Number of attention heads.
+        n_ctx: Maximum sequence length (context window).
+        n_inner: Feed-forward inner dimension (default: 3 * n_embd).
+        dropout: Dropout probability.
+        norm_type: Type of normalization ("layernorm" or "rmsnorm").
+        layer_norm_epsilon: Epsilon for layer normalization.
+        tie_weights: Whether to tie embedding and output weights.
+    """
+    
+    model_type = "chess_transformer"
+    
+    def __init__(
+        self,
+        vocab_size: int = 1200,
+        n_embd: int = 128,
+        n_layer: int = 6,
+        n_head: int = 4,
+        n_ctx: int = 256,
+        n_inner: Optional[int] = None,
+        dropout: float = 0.1,
+        norm_type: str = "rmsnorm",
+        layer_norm_epsilon: float = 1e-5,
+        tie_weights: bool = True,
+        pad_token_id: int = 0,
+        bos_token_id: int = 1,
+        eos_token_id: int = 2,
+        **kwargs,
+    ):
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            **kwargs,
+        )
+        
+        self.vocab_size = vocab_size
+        self.n_embd = n_embd
+        self.n_layer = n_layer
+        self.n_head = n_head
+        self.n_ctx = n_ctx
+        self.n_inner = n_inner if n_inner is not None else 3 * n_embd  # Reduced from 4x to 3x
+        self.dropout = dropout
+        self.norm_type = norm_type
+        self.layer_norm_epsilon = layer_norm_epsilon
+        self.tie_weights = tie_weights
+        # Inform HF base class about tying behavior
+        self.tie_word_embeddings = bool(tie_weights)
+
+class RMSNorm(nn.Module):
+    """
+    RMSNorm: normalize by RMS only (no mean subtraction).
+    Commonly used in modern LLMs.
+    """
+    def __init__(self, dim: int, eps: float = 1e-6):
+        super().__init__()
+        self.eps = eps
+        self.weight = nn.Parameter(torch.ones(dim))
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        rms = x.pow(2).mean(dim=-1, keepdim=True).add(self.eps).sqrt()
+        return (x / rms) * self.weight
+
+
+def make_norm(config: ChessConfig) -> nn.Module:
+    if getattr(config, "norm_type", "layernorm") == "rmsnorm":
+        return RMSNorm(config.n_embd, eps=config.layer_norm_epsilon)
+    return nn.LayerNorm(config.n_embd, eps=config.layer_norm_epsilon)
+
+
+class MultiHeadAttention(nn.Module):
+    """
+    Multi-head self-attention module.
+    
+    This is a standard scaled dot-product attention implementation
+    with causal masking for autoregressive generation.
+    """
+    
+    def __init__(self, config: ChessConfig):
+        super().__init__()
+        
+        assert config.n_embd % config.n_head == 0, \
+            f"n_embd ({config.n_embd}) must be divisible by n_head ({config.n_head})"
+        
+        self.n_head = config.n_head
+        self.n_embd = config.n_embd
+        self.head_dim = config.n_embd // config.n_head
+        
+        # Combined QKV projection for efficiency
+        self.c_attn = nn.Linear(config.n_embd, 3 * config.n_embd)
+        self.c_proj = nn.Linear(config.n_embd, config.n_embd)
+        
+        self.dropout = nn.Dropout(config.dropout)
+        
+        # Causal mask (will be created on first forward pass)
+        self.register_buffer(
+            "bias",
+            torch.tril(torch.ones(config.n_ctx, config.n_ctx)).view(
+                1, 1, config.n_ctx, config.n_ctx
+            ),
+            persistent=False,
+        )
+    
+    def forward(
+        self,
+        x: torch.Tensor,
+        attention_mask: Optional[torch.Tensor] = None,
+    ) -> torch.Tensor:
+        batch_size, seq_len, _ = x.size()
+        
+        # Compute Q, K, V
+        qkv = self.c_attn(x)
+        q, k, v = qkv.split(self.n_embd, dim=2)
+        
+        # Reshape for multi-head attention
+        q = q.view(batch_size, seq_len, self.n_head, self.head_dim).transpose(1, 2)
+        k = k.view(batch_size, seq_len, self.n_head, self.head_dim).transpose(1, 2)
+        v = v.view(batch_size, seq_len, self.n_head, self.head_dim).transpose(1, 2)
+        
+        # Scaled dot-product attention
+        attn_weights = torch.matmul(q, k.transpose(-2, -1)) / math.sqrt(self.head_dim)
+        
+        # Apply causal mask
+        causal_mask = self.bias[:, :, :seq_len, :seq_len]
+        attn_weights = attn_weights.masked_fill(causal_mask == 0, float("-inf"))
+        
+        # Apply attention mask (for padding)
+        if attention_mask is not None:
+            # attention_mask shape: (batch_size, seq_len) -> (batch_size, 1, 1, seq_len)
+            attention_mask = attention_mask.unsqueeze(1).unsqueeze(2)
+            attn_weights = attn_weights.masked_fill(attention_mask == 0, float("-inf"))
+        
+        attn_weights = F.softmax(attn_weights, dim=-1)
+        attn_weights = self.dropout(attn_weights)
+        
+        # Apply attention to values
+        attn_output = torch.matmul(attn_weights, v)
+        
+        # Reshape back
+        attn_output = attn_output.transpose(1, 2).contiguous().view(
+            batch_size, seq_len, self.n_embd
+        )
+        
+        # Output projection
+        attn_output = self.c_proj(attn_output)
+        
+        return attn_output
+
+
+class FeedForward(nn.Module):
+    """
+    Feed-forward network (MLP) module.
+    
+    Standard two-layer MLP with GELU activation.
+    """
+    
+    def __init__(self, config: ChessConfig):
+        super().__init__()
+        
+        self.c_fc = nn.Linear(config.n_embd, config.n_inner)
+        self.c_proj = nn.Linear(config.n_inner, config.n_embd)
+        self.dropout = nn.Dropout(config.dropout)
+    
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        x = self.c_fc(x)
+        x = F.gelu(x)
+        x = self.c_proj(x)
+        x = self.dropout(x)
+        return x
+
+
+class TransformerBlock(nn.Module):
+    """
+    A single transformer block with attention and feed-forward layers.
+    
+    Uses pre-normalization (LayerNorm before attention/FFN) for better
+    training stability.
+    """
+    
+    def __init__(self, config: ChessConfig):
+        super().__init__()
+        
+        self.ln_1 = make_norm(config)
+        self.attn = MultiHeadAttention(config)
+        self.ln_2 = make_norm(config)
+        self.mlp = FeedForward(config)
+    
+    def forward(
+        self,
+        x: torch.Tensor,
+        attention_mask: Optional[torch.Tensor] = None,
+    ) -> torch.Tensor:
+        # Pre-norm attention
+        x = x + self.attn(self.ln_1(x), attention_mask=attention_mask)
+        # Pre-norm FFN
+        x = x + self.mlp(self.ln_2(x))
+        return x
+
+
+class ChessForCausalLM(PreTrainedModel):
+    """
+    Chess Transformer for Causal Language Modeling (next-move prediction).
+    
+    This model is designed to predict the next chess move given a sequence
+    of previous moves. It uses a GPT-style architecture with:
+    - Token embeddings for chess moves
+    - Learned positional embeddings
+    - Stacked transformer blocks
+    - Linear head for next-token prediction
+    
+    The model supports weight tying between the embedding layer and the
+    output projection to save parameters.
+    
+    Example:
+        >>> config = ChessConfig(vocab_size=1200, n_embd=128, n_layer=6)
+        >>> model = ChessForCausalLM(config)
+        >>> inputs = {"input_ids": torch.tensor([[1, 42, 87]])}
+        >>> outputs = model(**inputs)
+        >>> next_move_logits = outputs.logits[:, -1, :]
+    """
+    
+    config_class = ChessConfig
+    base_model_prefix = "transformer"
+    supports_gradient_checkpointing = True
+    # Suppress missing-key warning for tied lm_head when loading
+    keys_to_ignore_on_load_missing = ["lm_head.weight"]
+    
+    def __init__(self, config: ChessConfig):
+        super().__init__(config)
+        
+        # Token and position embeddings
+        self.wte = nn.Embedding(config.vocab_size, config.n_embd)
+        self.wpe = nn.Embedding(config.n_ctx, config.n_embd)
+        
+        self.drop = nn.Dropout(config.dropout)
+        
+        # Transformer blocks
+        self.h = nn.ModuleList([
+            TransformerBlock(config) for _ in range(config.n_layer)
+        ])
+        
+        # Final layer norm
+        self.ln_f = make_norm(config)
+        
+        # Output head
+        self.lm_head = nn.Linear(config.n_embd, config.vocab_size, bias=False)
+        
+        # Declare tied weights for proper serialization
+        if config.tie_weights:
+            self._tied_weights_keys = ["lm_head.weight"]
+        
+        # Initialize weights
+        self.post_init()
+        
+        # Tie weights if configured
+        if config.tie_weights:
+            self.tie_weights()
+
+    def get_input_embeddings(self) -> nn.Module:
+        return self.wte
+
+    def set_input_embeddings(self, new_embeddings: nn.Module):
+        self.wte = new_embeddings
+        if getattr(self.config, "tie_weights", False):
+            self.tie_weights()
+
+    def get_output_embeddings(self) -> nn.Module:
+        return self.lm_head
+
+    def set_output_embeddings(self, new_embeddings: nn.Module):
+        self.lm_head = new_embeddings
+
+    def tie_weights(self):
+        # Use HF helper to tie or clone depending on config
+        if getattr(self.config, "tie_weights", False) or getattr(self.config, "tie_word_embeddings", False):
+            self._tie_or_clone_weights(self.lm_head, self.wte)
+    
+    def _init_weights(self, module: nn.Module):
+        """Initialize weights following GPT-2 style."""
+        if isinstance(module, nn.Linear):
+            torch.nn.init.normal_(module.weight, mean=0.0, std=0.02)
+            if module.bias is not None:
+                torch.nn.init.zeros_(module.bias)
+        elif isinstance(module, nn.Embedding):
+            torch.nn.init.normal_(module.weight, mean=0.0, std=0.02)
+        elif isinstance(module, nn.LayerNorm):
+            torch.nn.init.ones_(module.weight)
+            torch.nn.init.zeros_(module.bias)
+        elif isinstance(module, RMSNorm):
+            torch.nn.init.ones_(module.weight)
+    
+    def forward(
+        self,
+        input_ids: torch.LongTensor,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        labels: Optional[torch.LongTensor] = None,
+        return_dict: Optional[bool] = None,
+        **kwargs,
+    ) -> Union[Tuple, CausalLMOutputWithPast]:
+        """
+        Forward pass of the model.
+        
+        Args:
+            input_ids: Token IDs of shape (batch_size, seq_len).
+            attention_mask: Attention mask of shape (batch_size, seq_len).
+            position_ids: Position IDs of shape (batch_size, seq_len).
+            labels: Labels for language modeling loss.
+            return_dict: Whether to return a ModelOutput object.
+        
+        Returns:
+            CausalLMOutputWithPast containing loss (if labels provided) and logits.
+        """
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+        
+        batch_size, seq_len = input_ids.size()
+        device = input_ids.device
+        
+        # Create position IDs if not provided
+        if position_ids is None:
+            position_ids = torch.arange(seq_len, device=device).unsqueeze(0).expand(batch_size, -1)
+        
+        # Get embeddings
+        token_embeds = self.wte(input_ids)
+        position_embeds = self.wpe(position_ids)
+        hidden_states = self.drop(token_embeds + position_embeds)
+        
+        # Pass through transformer blocks
+        for block in self.h:
+            hidden_states = block(hidden_states, attention_mask=attention_mask)
+        
+        # Final layer norm
+        hidden_states = self.ln_f(hidden_states)
+        
+        # Get logits
+        logits = self.lm_head(hidden_states)
+        
+        # Compute loss if labels are provided
+        loss = None
+        if labels is not None:
+            # Shift logits and labels for next-token prediction
+            shift_logits = logits[..., :-1, :].contiguous()
+            shift_labels = labels[..., 1:].contiguous()
+            
+            # Flatten for cross-entropy
+            loss_fct = nn.CrossEntropyLoss(ignore_index=-100)
+            # loss_fct = nn.CrossEntropyLoss(ignore_index=self.config.pad_token_id)
+            loss = loss_fct(
+                shift_logits.view(-1, shift_logits.size(-1)),
+                shift_labels.view(-1),
+            )
+        
+        if not return_dict:
+            output = (logits,)
+            return ((loss,) + output) if loss is not None else output
+        
+        return CausalLMOutputWithPast(
+            loss=loss,
+            logits=logits,
+            past_key_values=None,
+            hidden_states=None,
+            attentions=None,
+        )
+    
+    @torch.no_grad()
+    def generate_move(
+        self,
+        input_ids: torch.LongTensor,
+        temperature: float = 1.0,
+        top_k: Optional[int] = None,
+        top_p: Optional[float] = None,
+    ) -> int:
+        """
+        Generate the next move given a sequence of moves.
+        
+        Args:
+            input_ids: Token IDs of shape (1, seq_len).
+            temperature: Sampling temperature (1.0 = no change).
+            top_k: If set, only sample from top k tokens.
+            top_p: If set, use nucleus sampling with this threshold.
+        
+        Returns:
+            The token ID of the predicted next move.
+        """
+        self.eval()
+        
+        # Get logits for the last position
+        outputs = self(input_ids)
+        logits = outputs.logits[:, -1, :] / temperature
+        
+        # Apply top-k filtering
+        if top_k is not None:
+            indices_to_remove = logits < torch.topk(logits, top_k)[0][..., -1, None]
+            logits[indices_to_remove] = float("-inf")
+        
+        # Apply top-p (nucleus) filtering
+        if top_p is not None:
+            sorted_logits, sorted_indices = torch.sort(logits, descending=True)
+            cumulative_probs = torch.cumsum(F.softmax(sorted_logits, dim=-1), dim=-1)
+            
+            # Remove tokens with cumulative probability above the threshold
+            sorted_indices_to_remove = cumulative_probs > top_p
+            sorted_indices_to_remove[..., 1:] = sorted_indices_to_remove[..., :-1].clone()
+            sorted_indices_to_remove[..., 0] = 0
+            
+            indices_to_remove = sorted_indices_to_remove.scatter(
+                dim=-1, index=sorted_indices, src=sorted_indices_to_remove
+            )
+            logits[indices_to_remove] = float("-inf")
+        
+        # Sample from the distribution
+        probs = F.softmax(logits, dim=-1)
+        next_token = torch.multinomial(probs, num_samples=1)
+        
+        return next_token.item()
+
+
+# Register the model with Auto classes for easy loading
+from transformers import AutoConfig, AutoModelForCausalLM
+
+AutoConfig.register("chess_transformer", ChessConfig)
+AutoModelForCausalLM.register(ChessConfig, ChessForCausalLM)

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bafd1b224a59c4849dee35cd3b76f9b69c5134f2e0a3eb1174890b58db379ff
+size 3997304

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "[BOS]",
+  "eos_token": "[EOS]",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer.py

@@ -0,0 +1,278 @@
+"""
+Custom Chess Tokenizer for the Chess Challenge.
+
+This tokenizer treats each move as a single token using the extended UCI notation
+from the Lichess dataset (e.g., WPe2e4, BNg8f6).
+
+The dataset format uses:
+- W/B prefix for White/Black
+- Piece letter: P=Pawn, N=Knight, B=Bishop, R=Rook, Q=Queen, K=King
+- Source and destination squares (e.g., e2e4)
+- Special suffixes: (x)=capture, (+)=check, (+*)=checkmate, (o)/(O)=castling
+"""
+
+from __future__ import annotations
+
+import json
+import os
+from pathlib import Path
+from typing import Dict, List, Optional
+
+from transformers import PreTrainedTokenizer
+
+
+class ChessTokenizer(PreTrainedTokenizer):
+    """
+    A custom tokenizer for chess moves using extended UCI notation.
+    
+    This tokenizer maps each possible chess move to a unique token ID.
+    The vocabulary is built from the training dataset to ensure all moves
+    encountered during training have a corresponding token.
+    
+    Example:
+        >>> tokenizer = ChessTokenizer()
+        >>> tokenizer.encode("WPe2e4 BPe7e5")
+        [1, 42, 87, 2]  # [BOS, e2e4, e7e5, EOS]
+    """
+    
+    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]"
+    
+    def __init__(
+        self,
+        vocab_file: Optional[str] = None,
+        vocab: Optional[Dict[str, int]] = None,
+        **kwargs,
+    ):
+        """
+        Initialize the chess tokenizer.
+        
+        Args:
+            vocab_file: Path to a JSON file containing the vocabulary mapping.
+            vocab: Dictionary mapping tokens to IDs (alternative to vocab_file).
+            **kwargs: Additional arguments passed to PreTrainedTokenizer.
+        """
+        # Initialize special tokens
+        self._pad_token = self.PAD_TOKEN
+        self._bos_token = self.BOS_TOKEN
+        self._eos_token = self.EOS_TOKEN
+        self._unk_token = self.UNK_TOKEN
+
+        # Remove any duplicate special-token entries passed through kwargs
+        # to avoid "multiple values for keyword" errors when loading from disk.
+        kwargs.pop("pad_token", None)
+        kwargs.pop("bos_token", None)
+        kwargs.pop("eos_token", None)
+        kwargs.pop("unk_token", None)
+        
+        # Load or create vocabulary
+        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:
+            # Create a minimal vocabulary with just special tokens
+            # The full vocabulary should be built from the dataset
+            self._vocab = self._create_default_vocab()
+        
+        # Create reverse mapping
+        self._ids_to_tokens = {v: k for k, v in self._vocab.items()}
+        
+        # Call parent init AFTER setting up vocab
+        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]:
+        """
+        Create a minimal default vocabulary with just special tokens.
+        
+        For the full vocabulary, use `build_vocab_from_dataset()`.
+        This minimal vocab is just a placeholder - you should build from data.
+        """
+        special_tokens = [self.PAD_TOKEN, self.BOS_TOKEN, self.EOS_TOKEN, self.UNK_TOKEN]
+        vocab = {token: idx for idx, token in enumerate(special_tokens)}
+        return vocab
+    
+    @classmethod
+    def build_vocab_from_iterator(
+        cls,
+        iterator,
+        min_frequency: int = 1,
+    ) -> "ChessTokenizer":
+        """
+        Build a tokenizer vocabulary from an iterator of game strings.
+        
+        Args:
+            iterator: An iterator yielding game strings (space-separated moves).
+            min_frequency: Minimum frequency for a token to be included.
+        
+        Returns:
+            A ChessTokenizer with the built vocabulary.
+        """
+        from collections import Counter
+        
+        token_counts = Counter()
+        
+        for game in iterator:
+            moves = game.strip().split()
+            token_counts.update(moves)
+        
+        # Filter by frequency
+        tokens = [
+            token for token, count in token_counts.items()
+            if count >= min_frequency
+        ]
+        
+        # Sort for reproducibility
+        tokens = sorted(tokens)
+        
+        # Build vocabulary
+        special_tokens = [cls.PAD_TOKEN, cls.BOS_TOKEN, cls.EOS_TOKEN, cls.UNK_TOKEN]
+        vocab = {token: idx for idx, token in enumerate(special_tokens + tokens)}
+        
+        return cls(vocab=vocab)
+    
+    @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":
+        """
+        Build a tokenizer vocabulary from a Hugging Face dataset.
+        
+        Args:
+            dataset_name: Name of the dataset on Hugging Face Hub.
+            split: Dataset split to use.
+            column: Column containing the game strings.
+            min_frequency: Minimum frequency for a token to be included (default: 500).
+            max_samples: Maximum number of samples to process (default: 100k).
+        
+        Returns:
+            A ChessTokenizer with the built vocabulary.
+        """
+        from datasets import load_dataset
+        
+        dataset = load_dataset(dataset_name, split=split)
+        
+        if max_samples is not None:
+            dataset = dataset.select(range(min(max_samples, len(dataset))))
+        
+        def game_iterator():
+            for example in dataset:
+                yield example[column]
+        
+        return cls.build_vocab_from_iterator(game_iterator(), min_frequency=min_frequency)
+    
+    @property
+    def vocab_size(self) -> int:
+        """Return the size of the vocabulary."""
+        return len(self._vocab)
+    
+    def get_vocab(self) -> Dict[str, int]:
+        """Return the vocabulary as a dictionary."""
+        return dict(self._vocab)
+    
+    def _tokenize(self, text: str) -> List[str]:
+        """
+        Tokenize a string of moves into a list of tokens.
+        
+        Args:
+            text: A string of space-separated moves.
+        
+        Returns:
+            List of move tokens.
+        """
+        return text.strip().split()
+    
+    def _convert_token_to_id(self, token: str) -> int:
+        """Convert a token to its ID."""
+        return self._vocab.get(token, self._vocab.get(self.UNK_TOKEN, 0))
+    
+    def _convert_id_to_token(self, index: int) -> str:
+        """Convert an ID to its token."""
+        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:
+        """
+        Save the vocabulary to a JSON file.
+        
+        Args:
+            save_directory: Directory to save the vocabulary.
+            filename_prefix: Optional prefix for the filename.
+        
+        Returns:
+            Tuple containing the path to the saved vocabulary file.
+        """
+        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 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).
+    
+    Args:
+        dataset_name: Name of the dataset on Hugging Face Hub.
+        split: Dataset split to use.
+        column: Column containing the game strings.
+        max_samples: Maximum number of samples to process.
+    
+    Returns:
+        Dictionary mapping tokens to their frequencies.
+    """
+    from collections import Counter
+    from datasets import load_dataset
+    
+    dataset = load_dataset(dataset_name, split=split)
+    
+    if max_samples is not None:
+        dataset = dataset.select(range(min(max_samples, len(dataset))))
+    
+    token_counts = Counter()
+    
+    for example in dataset:
+        moves = example[column].strip().split()
+        token_counts.update(moves)
+    
+    return dict(token_counts)

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[BOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[EOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenizer.ChessTokenizer",
+      null
+    ]
+  },
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "[EOS]",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "ChessTokenizer",
+  "unk_token": "[UNK]"
+}

vocab.json

@@ -0,0 +1,2385 @@
+{
+  "[PAD]": 0,
+  "[BOS]": 1,
+  "[EOS]": 2,
+  "[UNK]": 3,
+  "BBa5b6": 4,
+  "BBa5c7": 5,
+  "BBa6b7": 6,
+  "BBa6c4": 7,
+  "BBa6c4(x)": 8,
+  "BBa6c8": 9,
+  "BBa6d3(x)": 10,
+  "BBa6f1(x)": 11,
+  "BBb4a5": 12,
+  "BBb4c3": 13,
+  "BBb4c3(x)": 14,
+  "BBb4c3(x+)": 15,
+  "BBb4c5": 16,
+  "BBb4d2(x)": 17,
+  "BBb4d2(x+)": 18,
+  "BBb4d6": 19,
+  "BBb4e7": 20,
+  "BBb5c6": 21,
+  "BBb6a7": 22,
+  "BBb6c7": 23,
+  "BBb6d4(x)": 24,
+  "BBb6e3(x)": 25,
+  "BBb7a6": 26,
+  "BBb7a8": 27,
+  "BBb7c6": 28,
+  "BBb7c6(x)": 29,
+  "BBb7c8": 30,
+  "BBb7d5": 31,
+  "BBb7d5(x)": 32,
+  "BBb7e4": 33,
+  "BBb7e4(x)": 34,
+  "BBb7f3(x)": 35,
+  "BBb7g2(x)": 36,
+  "BBc4d5": 37,
+  "BBc5a7": 38,
+  "BBc5b4": 39,
+  "BBc5b4(+)": 40,
+  "BBc5b4(x)": 41,
+  "BBc5b6": 42,
+  "BBc5d4": 43,
+  "BBc5d4(x)": 44,
+  "BBc5d6": 45,
+  "BBc5e3(x)": 46,
+  "BBc5e3(x+)": 47,
+  "BBc5e7": 48,
+  "BBc5f2(x)": 49,
+  "BBc5f2(x+)": 50,
+  "BBc6b5": 51,
+  "BBc6b7": 52,
+  "BBc6d5": 53,
+  "BBc6d5(x)": 54,
+  "BBc6d7": 55,
+  "BBc6e4(x)": 56,
+  "BBc6f3(x)": 57,
+  "BBc7b6": 58,
+  "BBc8a6": 59,
+  "BBc8b7": 60,
+  "BBc8d7": 61,
+  "BBc8d7(x)": 62,
+  "BBc8e6": 63,
+  "BBc8e6(x)": 64,
+  "BBc8f5": 65,
+  "BBc8f5(x)": 66,
+  "BBc8g4": 67,
+  "BBc8g4(x)": 68,
+  "BBc8h3": 69,
+  "BBc8h3(x)": 70,
+  "BBd4b2(x)": 71,
+  "BBd4b6": 72,
+  "BBd4c3(x)": 73,
+  "BBd4c5": 74,
+  "BBd4e5": 75,
+  "BBd5c4": 76,
+  "BBd5c6": 77,
+  "BBd5e6": 78,
+  "BBd5f3(x)": 79,
+  "BBd6b4": 80,
+  "BBd6b8": 81,
+  "BBd6c5": 82,
+  "BBd6c5(+)": 83,
+  "BBd6c5(x)": 84,
+  "BBd6c7": 85,
+  "BBd6e5": 86,
+  "BBd6e5(x)": 87,
+  "BBd6e7": 88,
+  "BBd6f4": 89,
+  "BBd6f4(x)": 90,
+  "BBd6f8": 91,
+  "BBd6g3(x)": 92,
+  "BBd6h2(x+)": 93,
+  "BBd7a4": 94,
+  "BBd7a4(x)": 95,
+  "BBd7b5": 96,
+  "BBd7b5(x)": 97,
+  "BBd7c6": 98,
+  "BBd7c6(x)": 99,
+  "BBd7c8": 100,
+  "BBd7e6": 101,
+  "BBd7e6(x)": 102,
+  "BBd7e8": 103,
+  "BBd7f5": 104,
+  "BBd7f5(x)": 105,
+  "BBd7g4": 106,
+  "BBd7g4(x)": 107,
+  "BBd7h3(x)": 108,
+  "BBd8c7": 109,
+  "BBd8e7": 110,
+  "BBe4d5": 111,
+  "BBe4f3(x)": 112,
+  "BBe4f5": 113,
+  "BBe4g2(x)": 114,
+  "BBe4g6": 115,
+  "BBe5b2(x)": 116,
+  "BBe5c3(x)": 117,
+  "BBe5d4": 118,
+  "BBe5d6": 119,
+  "BBe5f6": 120,
+  "BBe5g7": 121,
+  "BBe6a2(x)": 122,
+  "BBe6b3(x)": 123,
+  "BBe6c4": 124,
+  "BBe6c4(x)": 125,
+  "BBe6c8": 126,
+  "BBe6d5": 127,
+  "BBe6d5(x)": 128,
+  "BBe6d7": 129,
+  "BBe6f5": 130,
+  "BBe6f5(x)": 131,
+  "BBe6f7": 132,
+  "BBe6g4": 133,
+  "BBe6g4(x)": 134,
+  "BBe6h3": 135,
+  "BBe6h3(x)": 136,
+  "BBe7a3(x)": 137,
+  "BBe7b4": 138,
+  "BBe7b4(x)": 139,
+  "BBe7c5": 140,
+  "BBe7c5(+)": 141,
+  "BBe7c5(x)": 142,
+  "BBe7d6": 143,
+  "BBe7d6(x)": 144,
+  "BBe7d8": 145,
+  "BBe7d8(x)": 146,
+  "BBe7f6": 147,
+  "BBe7f6(x)": 148,
+  "BBe7f8": 149,
+  "BBe7g5": 150,
+  "BBe7g5(x)": 151,
+  "BBe7h4": 152,
+  "BBe7h4(+)": 153,
+  "BBe7h4(x)": 154,
+  "BBf5b1(x)": 155,
+  "BBf5c2(x)": 156,
+  "BBf5d3": 157,
+  "BBf5d3(x)": 158,
+  "BBf5d7": 159,
+  "BBf5e4": 160,
+  "BBf5e4(x)": 161,
+  "BBf5e6": 162,
+  "BBf5g4": 163,
+  "BBf5g4(x)": 164,
+  "BBf5g6": 165,
+  "BBf5h7": 166,
+  "BBf6b2(x)": 167,
+  "BBf6c3(x)": 168,
+  "BBf6d4": 169,
+  "BBf6d4(x)": 170,
+  "BBf6e5": 171,
+  "BBf6e5(x)": 172,
+  "BBf6e7": 173,
+  "BBf6g5": 174,
+  "BBf6g5(x)": 175,
+  "BBf6g7": 176,
+  "BBf8a3(x)": 177,
+  "BBf8b4": 178,
+  "BBf8b4(+)": 179,
+  "BBf8b4(x)": 180,
+  "BBf8c5": 181,
+  "BBf8c5(+)": 182,
+  "BBf8c5(x)": 183,
+  "BBf8d6": 184,
+  "BBf8d6(x)": 185,
+  "BBf8e7": 186,
+  "BBf8e7(x)": 187,
+  "BBf8g7": 188,
+  "BBf8h6": 189,
+  "BBg4d1(x)": 190,
+  "BBg4d7": 191,
+  "BBg4e2(x)": 192,
+  "BBg4e6": 193,
+  "BBg4f3": 194,
+  "BBg4f3(x)": 195,
+  "BBg4f5": 196,
+  "BBg4h3": 197,
+  "BBg4h5": 198,
+  "BBg5f6": 199,
+  "BBg6d3(x)": 200,
+  "BBg6e4": 201,
+  "BBg6e4(x)": 202,
+  "BBg6f7": 203,
+  "BBg6h5": 204,
+  "BBg6h7": 205,
+  "BBg7a1(x)": 206,
+  "BBg7b2(x)": 207,
+  "BBg7c3(x)": 208,
+  "BBg7d4": 209,
+  "BBg7d4(x)": 210,
+  "BBg7e5": 211,
+  "BBg7e5(x)": 212,
+  "BBg7f6": 213,
+  "BBg7f6(x)": 214,
+  "BBg7f8": 215,
+  "BBg7h6": 216,
+  "BBg7h6(x)": 217,
+  "BBg7h8": 218,
+  "BBh3f1(x)": 219,
+  "BBh3g2(x)": 220,
+  "BBh3g4": 221,
+  "BBh4e7": 222,
+  "BBh4f6": 223,
+  "BBh4g5": 224,
+  "BBh5e2(x)": 225,
+  "BBh5f3(x)": 226,
+  "BBh5g6": 227,
+  "BBh6g7": 228,
+  "BKa6a5": 229,
+  "BKa6b7": 230,
+  "BKa7b6": 231,
+  "BKa7b8": 232,
+  "BKa8b8": 233,
+  "BKb4b3": 234,
+  "BKb4c3": 235,
+  "BKb4c5": 236,
+  "BKb5a4": 237,
+  "BKb5b4": 238,
+  "BKb5c4": 239,
+  "BKb5c5": 240,
+  "BKb5c6": 241,
+  "BKb6a5": 242,
+  "BKb6a6": 243,
+  "BKb6b5": 244,
+  "BKb6c5": 245,
+  "BKb6c6": 246,
+  "BKb6c7": 247,
+  "BKb7a6": 248,
+  "BKb7a7": 249,
+  "BKb7b6": 250,
+  "BKb7b8": 251,
+  "BKb7c6": 252,
+  "BKb7c7": 253,
+  "BKb7c8": 254,
+  "BKb8a7": 255,
+  "BKb8a8": 256,
+  "BKb8b7": 257,
+  "BKb8c7": 258,
+  "BKb8c8": 259,
+  "BKc4b3": 260,
+  "BKc4b4": 261,
+  "BKc4c3": 262,
+  "BKc4d3": 263,
+  "BKc4d5": 264,
+  "BKc5b4": 265,
+  "BKc5b5": 266,
+  "BKc5b6": 267,
+  "BKc5c4": 268,
+  "BKc5c6": 269,
+  "BKc5d4": 270,
+  "BKc5d5": 271,
+  "BKc5d6": 272,
+  "BKc6b5": 273,
+  "BKc6b6": 274,
+  "BKc6b7": 275,
+  "BKc6c5": 276,
+  "BKc6c7": 277,
+  "BKc6d5": 278,
+  "BKc6d6": 279,
+  "BKc6d7": 280,
+  "BKc7b6": 281,
+  "BKc7b7": 282,
+  "BKc7b8": 283,
+  "BKc7c6": 284,
+  "BKc7c8": 285,
+  "BKc7d6": 286,
+  "BKc7d7": 287,
+  "BKc7d8": 288,
+  "BKc8b7": 289,
+  "BKc8b8": 290,
+  "BKc8c7": 291,
+  "BKc8d7": 292,
+  "BKc8d8": 293,
+  "BKc8d8(x)": 294,
+  "BKd4c3": 295,
+  "BKd4c4": 296,
+  "BKd4c5": 297,
+  "BKd4d3": 298,
+  "BKd4e3": 299,
+  "BKd4e4": 300,
+  "BKd4e5": 301,
+  "BKd5c4": 302,
+  "BKd5c5": 303,
+  "BKd5c6": 304,
+  "BKd5d4": 305,
+  "BKd5d6": 306,
+  "BKd5e4": 307,
+  "BKd5e5": 308,
+  "BKd5e6": 309,
+  "BKd6c5": 310,
+  "BKd6c6": 311,
+  "BKd6c7": 312,
+  "BKd6d5": 313,
+  "BKd6d7": 314,
+  "BKd6e5": 315,
+  "BKd6e6": 316,
+  "BKd6e7": 317,
+  "BKd7c6": 318,
+  "BKd7c7": 319,
+  "BKd7c8": 320,
+  "BKd7d6": 321,
+  "BKd7d8": 322,
+  "BKd7e6": 323,
+  "BKd7e7": 324,
+  "BKd7e8": 325,
+  "BKd8c7": 326,
+  "BKd8c8": 327,
+  "BKd8d7": 328,
+  "BKd8e7": 329,
+  "BKd8e8": 330,
+  "BKe4d3": 331,
+  "BKe4d4": 332,
+  "BKe4d5": 333,
+  "BKe4e3": 334,
+  "BKe4f3": 335,
+  "BKe4f4": 336,
+  "BKe4f5": 337,
+  "BKe5d4": 338,
+  "BKe5d5": 339,
+  "BKe5d6": 340,
+  "BKe5e4": 341,
+  "BKe5e6": 342,
+  "BKe5f4": 343,
+  "BKe5f5": 344,
+  "BKe5f6": 345,
+  "BKe6d5": 346,
+  "BKe6d6": 347,
+  "BKe6d7": 348,
+  "BKe6e5": 349,
+  "BKe6e7": 350,
+  "BKe6f5": 351,
+  "BKe6f6": 352,
+  "BKe6f7": 353,
+  "BKe7d6": 354,
+  "BKe7d7": 355,
+  "BKe7d8": 356,
+  "BKe7e6": 357,
+  "BKe7e6(x)": 358,
+  "BKe7e8": 359,
+  "BKe7f6": 360,
+  "BKe7f7": 361,
+  "BKe7f8": 362,
+  "BKe8c8(O)": 363,
+  "BKe8d7": 364,
+  "BKe8d7(x)": 365,
+  "BKe8d8": 366,
+  "BKe8d8(x)": 367,
+  "BKe8e7": 368,
+  "BKe8e7(x)": 369,
+  "BKe8f7": 370,
+  "BKe8f7(x)": 371,
+  "BKe8f8": 372,
+  "BKe8g8(o)": 373,
+  "BKf4e3": 374,
+  "BKf4e4": 375,
+  "BKf4e5": 376,
+  "BKf4f3": 377,
+  "BKf4g3": 378,
+  "BKf4g4": 379,
+  "BKf4g5": 380,
+  "BKf5e4": 381,
+  "BKf5e5": 382,
+  "BKf5e6": 383,
+  "BKf5f4": 384,
+  "BKf5f6": 385,
+  "BKf5g4": 386,
+  "BKf5g5": 387,
+  "BKf5g6": 388,
+  "BKf6e5": 389,
+  "BKf6e6": 390,
+  "BKf6e7": 391,
+  "BKf6f5": 392,
+  "BKf6f7": 393,
+  "BKf6g5": 394,
+  "BKf6g6": 395,
+  "BKf6g7": 396,
+  "BKf7e6": 397,
+  "BKf7e7": 398,
+  "BKf7e8": 399,
+  "BKf7f6": 400,
+  "BKf7f8": 401,
+  "BKf7g6": 402,
+  "BKf7g7": 403,
+  "BKf7g8": 404,
+  "BKf8e7": 405,
+  "BKf8e8": 406,
+  "BKf8f7": 407,
+  "BKf8g7": 408,
+  "BKf8g8": 409,
+  "BKg4f3": 410,
+  "BKg4f4": 411,
+  "BKg4f5": 412,
+  "BKg4g3": 413,
+  "BKg4h3": 414,
+  "BKg5f4": 415,
+  "BKg5f5": 416,
+  "BKg5f6": 417,
+  "BKg5g4": 418,
+  "BKg5g6": 419,
+  "BKg5h4": 420,
+  "BKg5h5": 421,
+  "BKg5h6": 422,
+  "BKg6f5": 423,
+  "BKg6f6": 424,
+  "BKg6f7": 425,
+  "BKg6g5": 426,
+  "BKg6g7": 427,
+  "BKg6h5": 428,
+  "BKg6h6": 429,
+  "BKg6h7": 430,
+  "BKg7f6": 431,
+  "BKg7f6(x)": 432,
+  "BKg7f7": 433,
+  "BKg7f8": 434,
+  "BKg7g6": 435,
+  "BKg7g8": 436,
+  "BKg7h6": 437,
+  "BKg7h7": 438,
+  "BKg7h8": 439,
+  "BKg8f7": 440,
+  "BKg8f7(x)": 441,
+  "BKg8f8": 442,
+  "BKg8f8(x)": 443,
+  "BKg8g7": 444,
+  "BKg8g7(x)": 445,
+  "BKg8h7": 446,
+  "BKg8h7(x)": 447,
+  "BKg8h8": 448,
+  "BKh4h3": 449,
+  "BKh5g4": 450,
+  "BKh5g5": 451,
+  "BKh5g6": 452,
+  "BKh5h4": 453,
+  "BKh5h6": 454,
+  "BKh6g5": 455,
+  "BKh6g6": 456,
+  "BKh6g7": 457,
+  "BKh6h5": 458,
+  "BKh6h7": 459,
+  "BKh7g6": 460,
+  "BKh7g7": 461,
+  "BKh7g8": 462,
+  "BKh7h6": 463,
+  "BKh7h8": 464,
+  "BKh8g7": 465,
+  "BKh8g7(x)": 466,
+  "BKh8g8": 467,
+  "BKh8h7": 468,
+  "BNa2b4": 469,
+  "BNa5b3": 470,
+  "BNa5b3(x)": 471,
+  "BNa5b7": 472,
+  "BNa5c4": 473,
+  "BNa5c4(x)": 474,
+  "BNa5c6": 475,
+  "BNa6b4": 476,
+  "BNa6c5": 477,
+  "BNa6c7": 478,
+  "BNb2c4": 479,
+  "BNb4a2(x)": 480,
+  "BNb4a6": 481,
+  "BNb4c2": 482,
+  "BNb4c2(x)": 483,
+  "BNb4c6": 484,
+  "BNb4d3": 485,
+  "BNb4d3(x)": 486,
+  "BNb4d3(x+)": 487,
+  "BNb4d5": 488,
+  "BNb4d5(x)": 489,
+  "BNb6a4": 490,
+  "BNb6c4": 491,
+  "BNb6c4(x)": 492,
+  "BNb6d5": 493,
+  "BNb6d5(x)": 494,
+  "BNb6d7": 495,
+  "BNb8a6": 496,
+  "BNb8a6(x)": 497,
+  "BNb8c6": 498,
+  "BNb8c6(x)": 499,
+  "BNb8d7": 500,
+  "BNb8d7(x)": 501,
+  "BNc2a1(x)": 502,
+  "BNc2d4": 503,
+  "BNc3d5": 504,
+  "BNc3e2(+)": 505,
+  "BNc3e4": 506,
+  "BNc4b2(x)": 507,
+  "BNc4b6": 508,
+  "BNc4d2": 509,
+  "BNc4d6": 510,
+  "BNc4e3": 511,
+  "BNc4e3(x)": 512,
+  "BNc4e5": 513,
+  "BNc5a4": 514,
+  "BNc5b3(x)": 515,
+  "BNc5d3": 516,
+  "BNc5d3(x)": 517,
+  "BNc5d7": 518,
+  "BNc5e4": 519,
+  "BNc5e4(x)": 520,
+  "BNc5e6": 521,
+  "BNc6a5": 522,
+  "BNc6a5(x)": 523,
+  "BNc6a7": 524,
+  "BNc6b4": 525,
+  "BNc6b4(x)": 526,
+  "BNc6b8": 527,
+  "BNc6d4": 528,
+  "BNc6d4(+)": 529,
+  "BNc6d4(x)": 530,
+  "BNc6d8": 531,
+  "BNc6d8(x)": 532,
+  "BNc6e5": 533,
+  "BNc6e5(x)": 534,
+  "BNc6e7": 535,
+  "BNc6e7(x)": 536,
+  "BNc7d5": 537,
+  "BNc7e6": 538,
+  "BNd3b2(x)": 539,
+  "BNd3c5": 540,
+  "BNd3e5": 541,
+  "BNd3f4": 542,
+  "BNd4b3(x)": 543,
+  "BNd4c2": 544,
+  "BNd4c2(x)": 545,
+  "BNd4c2(x+)": 546,
+  "BNd4c6": 547,
+  "BNd4e2(+)": 548,
+  "BNd4e2(x)": 549,
+  "BNd4e2(x+)": 550,
+  "BNd4e6": 551,
+  "BNd4f3(+)": 552,
+  "BNd4f3(x)": 553,
+  "BNd4f3(x+)": 554,
+  "BNd4f5": 555,
+  "BNd5b4": 556,
+  "BNd5b4(x)": 557,
+  "BNd5b6": 558,
+  "BNd5c3": 559,
+  "BNd5c3(x)": 560,
+  "BNd5c7": 561,
+  "BNd5e3": 562,
+  "BNd5e3(x)": 563,
+  "BNd5e7": 564,
+  "BNd5f4": 565,
+  "BNd5f4(x)": 566,
+  "BNd5f6": 567,
+  "BNd6c4": 568,
+  "BNd6e4": 569,
+  "BNd6f5": 570,
+  "BNd7b6": 571,
+  "BNd7b8": 572,
+  "BNd7c5": 573,
+  "BNd7c5(x)": 574,
+  "BNd7e5": 575,
+  "BNd7e5(x)": 576,
+  "BNd7f6": 577,
+  "BNd7f6(x)": 578,
+  "BNd7f8": 579,
+  "BNd8c6": 580,
+  "BNd8e6": 581,
+  "BNe3f1(x)": 582,
+  "BNe4c3": 583,
+  "BNe4c3(x)": 584,
+  "BNe4c5": 585,
+  "BNe4c5(x)": 586,
+  "BNe4d2": 587,
+  "BNe4d2(x)": 588,
+  "BNe4d6": 589,
+  "BNe4f2(x)": 590,
+  "BNe4f6": 591,
+  "BNe4g3": 592,
+  "BNe4g3(x)": 593,
+  "BNe4g5": 594,
+  "BNe4g5(x)": 595,
+  "BNe5c4": 596,
+  "BNe5c4(x)": 597,
+  "BNe5c6": 598,
+  "BNe5d3": 599,
+  "BNe5d3(+)": 600,
+  "BNe5d3(x)": 601,
+  "BNe5d3(x+)": 602,
+  "BNe5d7": 603,
+  "BNe5f3(+)": 604,
+  "BNe5f3(x)": 605,
+  "BNe5f3(x+)": 606,
+  "BNe5f7": 607,
+  "BNe5g4": 608,
+  "BNe5g4(x)": 609,
+  "BNe5g6": 610,
+  "BNe6c5": 611,
+  "BNe6d4": 612,
+  "BNe6f4": 613,
+  "BNe6g5": 614,
+  "BNe7c6": 615,
+  "BNe7c6(x)": 616,
+  "BNe7c8": 617,
+  "BNe7d5": 618,
+  "BNe7d5(x)": 619,
+  "BNe7f5": 620,
+  "BNe7f5(x)": 621,
+  "BNe7g6": 622,
+  "BNe7g6(x)": 623,
+  "BNe7g8": 624,
+  "BNe8c7": 625,
+  "BNe8d6": 626,
+  "BNe8f6": 627,
+  "BNf2h1(x)": 628,
+  "BNf4d3": 629,
+  "BNf4d3(x)": 630,
+  "BNf4d5": 631,
+  "BNf4e2(+)": 632,
+  "BNf4e6": 633,
+  "BNf4g6": 634,
+  "BNf5d4": 635,
+  "BNf5d4(x)": 636,
+  "BNf5d6": 637,
+  "BNf5e3": 638,
+  "BNf5e3(x)": 639,
+  "BNf5e7": 640,
+  "BNf5g3(x)": 641,
+  "BNf5h4": 642,
+  "BNf5h6": 643,
+  "BNf6d5": 644,
+  "BNf6d5(x)": 645,
+  "BNf6d7": 646,
+  "BNf6d7(x)": 647,
+  "BNf6e4": 648,
+  "BNf6e4(+)": 649,
+  "BNf6e4(x)": 650,
+  "BNf6e8": 651,
+  "BNf6g4": 652,
+  "BNf6g4(+)": 653,
+  "BNf6g4(x)": 654,
+  "BNf6g8": 655,
+  "BNf6h5": 656,
+  "BNf6h5(x)": 657,
+  "BNf6h7": 658,
+  "BNf8d7": 659,
+  "BNf8e6": 660,
+  "BNf8g6": 661,
+  "BNg4e3": 662,
+  "BNg4e3(x)": 663,
+  "BNg4e5": 664,
+  "BNg4e5(x)": 665,
+  "BNg4f2(+)": 666,
+  "BNg4f2(x)": 667,
+  "BNg4f6": 668,
+  "BNg4h2(x)": 669,
+  "BNg4h6": 670,
+  "BNg5e4": 671,
+  "BNg5e6": 672,
+  "BNg6e5": 673,
+  "BNg6e5(x)": 674,
+  "BNg6e7": 675,
+  "BNg6f4": 676,
+  "BNg6f4(x)": 677,
+  "BNg6f8": 678,
+  "BNg6h4": 679,
+  "BNg8e7": 680,
+  "BNg8e7(x)": 681,
+  "BNg8f6": 682,
+  "BNg8f6(x)": 683,
+  "BNg8h6": 684,
+  "BNh4g6": 685,
+  "BNh5f4": 686,
+  "BNh5f4(x)": 687,
+  "BNh5f6": 688,
+  "BNh5g3": 689,
+  "BNh5g3(x)": 690,
+  "BNh5g7": 691,
+  "BNh6f5": 692,
+  "BNh6f7": 693,
+  "BNh6g4": 694,
+  "BNh7f6": 695,
+  "BNh7g5": 696,
+  "BPa2a1(Q)": 697,
+  "BPa3a2": 698,
+  "BPa4a3": 699,
+  "BPa4b3(x)": 700,
+  "BPa5a4": 701,
+  "BPa5b4(x)": 702,
+  "BPa6a5": 703,
+  "BPa6b5(x)": 704,
+  "BPa7a5": 705,
+  "BPa7a6": 706,
+  "BPa7b6(x)": 707,
+  "BPb2b1(Q)": 708,
+  "BPb3b2": 709,
+  "BPb4a3(x)": 710,
+  "BPb4b3": 711,
+  "BPb4c3(x)": 712,
+  "BPb5a4(x)": 713,
+  "BPb5b4": 714,
+  "BPb5c4(x)": 715,
+  "BPb6a5(x)": 716,
+  "BPb6b5": 717,
+  "BPb6c5(x)": 718,
+  "BPb7a6(x)": 719,
+  "BPb7b5": 720,
+  "BPb7b6": 721,
+  "BPb7c6(x)": 722,
+  "BPc2c1(Q)": 723,
+  "BPc3b2(x)": 724,
+  "BPc3c2": 725,
+  "BPc4b3(x)": 726,
+  "BPc4c3": 727,
+  "BPc4d3(x)": 728,
+  "BPc5b4(x)": 729,
+  "BPc5c4": 730,
+  "BPc5d4(x)": 731,
+  "BPc6b5(x)": 732,
+  "BPc6c5": 733,
+  "BPc6d5(x)": 734,
+  "BPc7b6(x)": 735,
+  "BPc7c5": 736,
+  "BPc7c6": 737,
+  "BPc7d6(x)": 738,
+  "BPd2d1(Q)": 739,
+  "BPd3d2": 740,
+  "BPd4c3(x)": 741,
+  "BPd4d3": 742,
+  "BPd4d3(+)": 743,
+  "BPd4e3(x)": 744,
+  "BPd5c4(x)": 745,
+  "BPd5d4": 746,
+  "BPd5e4(x)": 747,
+  "BPd6c5(x)": 748,
+  "BPd6d5": 749,
+  "BPd6e5(x)": 750,
+  "BPd7c6(x)": 751,
+  "BPd7d5": 752,
+  "BPd7d6": 753,
+  "BPd7e6(x)": 754,
+  "BPe2e1(Q)": 755,
+  "BPe3e2": 756,
+  "BPe4d3(x)": 757,
+  "BPe4e3": 758,
+  "BPe4e3(+)": 759,
+  "BPe4f3(x)": 760,
+  "BPe5d4(x)": 761,
+  "BPe5e4": 762,
+  "BPe5e4(+)": 763,
+  "BPe5f4(x)": 764,
+  "BPe6d5(x)": 765,
+  "BPe6e5": 766,
+  "BPe6f5(x)": 767,
+  "BPe7d6(x)": 768,
+  "BPe7e5": 769,
+  "BPe7e6": 770,
+  "BPe7f6(x)": 771,
+  "BPf2f1(Q)": 772,
+  "BPf3f2": 773,
+  "BPf4e3(x)": 774,
+  "BPf4f3": 775,
+  "BPf4f3(+)": 776,
+  "BPf4g3(x)": 777,
+  "BPf5e4(x)": 778,
+  "BPf5f4": 779,
+  "BPf5f4(+)": 780,
+  "BPf5g4(x)": 781,
+  "BPf6e5(x)": 782,
+  "BPf6f5": 783,
+  "BPf6g5(x)": 784,
+  "BPf7e6(x)": 785,
+  "BPf7f5": 786,
+  "BPf7f6": 787,
+  "BPf7g6(x)": 788,
+  "BPg2g1(Q)": 789,
+  "BPg3g2": 790,
+  "BPg4f3(x)": 791,
+  "BPg4g3": 792,
+  "BPg4h3(x)": 793,
+  "BPg5f4(x)": 794,
+  "BPg5g4": 795,
+  "BPg5g4(+)": 796,
+  "BPg5h4(x)": 797,
+  "BPg6f5(x)": 798,
+  "BPg6g5": 799,
+  "BPg6h5(x)": 800,
+  "BPg7f6(x)": 801,
+  "BPg7g5": 802,
+  "BPg7g6": 803,
+  "BPg7h6(x)": 804,
+  "BPh2h1(Q)": 805,
+  "BPh3h2": 806,
+  "BPh4g3(x)": 807,
+  "BPh4h3": 808,
+  "BPh5g4(x)": 809,
+  "BPh5h4": 810,
+  "BPh6g5(x)": 811,
+  "BPh6h5": 812,
+  "BPh7g6(x)": 813,
+  "BPh7h5": 814,
+  "BPh7h6": 815,
+  "BQa5a2(x)": 816,
+  "BQa5b6": 817,
+  "BQa5c3(x)": 818,
+  "BQa5c5(x)": 819,
+  "BQa5c7": 820,
+  "BQa5d8": 821,
+  "BQb2a2(x)": 822,
+  "BQb2a3": 823,
+  "BQb2c3(x)": 824,
+  "BQb4b2(x)": 825,
+  "BQb6a5": 826,
+  "BQb6a6": 827,
+  "BQb6b2(x)": 828,
+  "BQb6b3(x)": 829,
+  "BQb6b4": 830,
+  "BQb6b5": 831,
+  "BQb6c5": 832,
+  "BQb6c5(x)": 833,
+  "BQb6c6": 834,
+  "BQb6c7": 835,
+  "BQb6d4(x)": 836,
+  "BQb6d6": 837,
+  "BQb6d8": 838,
+  "BQc5b6": 839,
+  "BQc5d6": 840,
+  "BQc6b6": 841,
+  "BQc6c7": 842,
+  "BQc6d7": 843,
+  "BQc7a5": 844,
+  "BQc7b6": 845,
+  "BQc7b7": 846,
+  "BQc7b8": 847,
+  "BQc7c6": 848,
+  "BQc7c6(x)": 849,
+  "BQc7c8": 850,
+  "BQc7d6": 851,
+  "BQc7d6(x)": 852,
+  "BQc7d7": 853,
+  "BQc7d8": 854,
+  "BQc7e5": 855,
+  "BQc7e5(x)": 856,
+  "BQc7e7": 857,
+  "BQc7f4(x)": 858,
+  "BQc7f7": 859,
+  "BQc8d7": 860,
+  "BQd4b2(x)": 861,
+  "BQd5a5": 862,
+  "BQd5d6": 863,
+  "BQd5d7": 864,
+  "BQd5d8": 865,
+  "BQd5e5(+)": 866,
+  "BQd5e6": 867,
+  "BQd5e6(+)": 868,
+  "BQd6b4": 869,
+  "BQd6b6": 870,
+  "BQd6c5": 871,
+  "BQd6c6": 872,
+  "BQd6c7": 873,
+  "BQd6d5": 874,
+  "BQd6d7": 875,
+  "BQd6e5": 876,
+  "BQd6e5(x)": 877,
+  "BQd6e6": 878,
+  "BQd6e7": 879,
+  "BQd6f6": 880,
+  "BQd6g6": 881,
+  "BQd7b5": 882,
+  "BQd7c6": 883,
+  "BQd7c6(x)": 884,
+  "BQd7c7": 885,
+  "BQd7d5": 886,
+  "BQd7d5(x)": 887,
+  "BQd7d6": 888,
+  "BQd7d6(x)": 889,
+  "BQd7d8": 890,
+  "BQd7e6": 891,
+  "BQd7e6(x)": 892,
+  "BQd7e7": 893,
+  "BQd7e7(x)": 894,
+  "BQd7e8": 895,
+  "BQd7f5": 896,
+  "BQd7f5(x)": 897,
+  "BQd7f7": 898,
+  "BQd7g4": 899,
+  "BQd7h3(x)": 900,
+  "BQd8a5": 901,
+  "BQd8a5(+)": 902,
+  "BQd8a8(x)": 903,
+  "BQd8b6": 904,
+  "BQd8b6(+)": 905,
+  "BQd8b8": 906,
+  "BQd8c7": 907,
+  "BQd8c7(x)": 908,
+  "BQd8c8": 909,
+  "BQd8d1(x)": 910,
+  "BQd8d1(x+)": 911,
+  "BQd8d3(x)": 912,
+  "BQd8d4": 913,
+  "BQd8d4(x)": 914,
+  "BQd8d5": 915,
+  "BQd8d5(x)": 916,
+  "BQd8d6": 917,
+  "BQd8d6(x)": 918,
+  "BQd8d7": 919,
+  "BQd8d7(x)": 920,
+  "BQd8e7": 921,
+  "BQd8e7(+)": 922,
+  "BQd8e7(x)": 923,
+  "BQd8e8": 924,
+  "BQd8e8(x)": 925,
+  "BQd8f6": 926,
+  "BQd8f6(x)": 927,
+  "BQd8f8": 928,
+  "BQd8f8(x)": 929,
+  "BQd8g5": 930,
+  "BQd8g5(+)": 931,
+  "BQd8g5(x)": 932,
+  "BQd8h4": 933,
+  "BQd8h4(+)": 934,
+  "BQd8h4(x)": 935,
+  "BQe5d6": 936,
+  "BQe5f6": 937,
+  "BQe6d7": 938,
+  "BQe6f6": 939,
+  "BQe6g6": 940,
+  "BQe7b4": 941,
+  "BQe7b4(+)": 942,
+  "BQe7c5": 943,
+  "BQe7c5(x)": 944,
+  "BQe7c7": 945,
+  "BQe7d6": 946,
+  "BQe7d6(x)": 947,
+  "BQe7d7": 948,
+  "BQe7d8": 949,
+  "BQe7e4(x)": 950,
+  "BQe7e5": 951,
+  "BQe7e5(x)": 952,
+  "BQe7e6": 953,
+  "BQe7e6(x)": 954,
+  "BQe7e8": 955,
+  "BQe7f6": 956,
+  "BQe7f6(x)": 957,
+  "BQe7f7": 958,
+  "BQe7f8": 959,
+  "BQe7g5": 960,
+  "BQe7g7": 961,
+  "BQe7h4": 962,
+  "BQe8f7": 963,
+  "BQe8g6": 964,
+  "BQf6b2(x)": 965,
+  "BQf6d4(x)": 966,
+  "BQf6d6": 967,
+  "BQf6d8": 968,
+  "BQf6e5": 969,
+  "BQf6e5(x)": 970,
+  "BQf6e6": 971,
+  "BQf6e7": 972,
+  "BQf6f3(x)": 973,
+  "BQf6f4": 974,
+  "BQf6f5": 975,
+  "BQf6f7": 976,
+  "BQf6g5": 977,
+  "BQf6g6": 978,
+  "BQf6g7": 979,
+  "BQf6h4": 980,
+  "BQf6h6": 981,
+  "BQf7g6": 982,
+  "BQg5e7": 983,
+  "BQg5f6": 984,
+  "BQg5g6": 985,
+  "BQg6f6": 986,
+  "BQg6g5": 987,
+  "BQg6h5": 988,
+  "BQh4e7": 989,
+  "BQh4f6": 990,
+  "BQh4g5": 991,
+  "BQh4h3": 992,
+  "BQh4h5": 993,
+  "BQh5g6": 994,
+  "BRa2a1": 995,
+  "BRa2a1(+)": 996,
+  "BRa2a3": 997,
+  "BRa2a3(+)": 998,
+  "BRa2b2": 999,
+  "BRa2c2": 1000,
+  "BRa3a2": 1001,
+  "BRa3a2(+)": 1002,
+  "BRa8a1(x)": 1003,
+  "BRa8a2": 1004,
+  "BRa8a2(x)": 1005,
+  "BRa8a3": 1006,
+  "BRa8a3(x)": 1007,
+  "BRa8a4(x)": 1008,
+  "BRa8a5": 1009,
+  "BRa8a5(x)": 1010,
+  "BRa8a6": 1011,
+  "BRa8a6(x)": 1012,
+  "BRa8a7": 1013,
+  "BRa8a7(x)": 1014,
+  "BRa8b8": 1015,
+  "BRa8b8(x)": 1016,
+  "BRa8c8": 1017,
+  "BRa8c8(x)": 1018,
+  "BRa8d8": 1019,
+  "BRa8d8(+)": 1020,
+  "BRa8d8(x)": 1021,
+  "BRa8e8": 1022,
+  "BRa8e8(x)": 1023,
+  "BRa8f8": 1024,
+  "BRa8f8(x)": 1025,
+  "BRa8g8": 1026,
+  "BRa8h8": 1027,
+  "BRb2a2": 1028,
+  "BRb2a2(x)": 1029,
+  "BRb2b1(+)": 1030,
+  "BRb2b3": 1031,
+  "BRb2c2": 1032,
+  "BRb8a8": 1033,
+  "BRb8b2": 1034,
+  "BRb8b2(x)": 1035,
+  "BRb8b3(x)": 1036,
+  "BRb8b4": 1037,
+  "BRb8b4(x)": 1038,
+  "BRb8b5": 1039,
+  "BRb8b5(x)": 1040,
+  "BRb8b6": 1041,
+  "BRb8b7": 1042,
+  "BRb8b7(x)": 1043,
+  "BRb8c8": 1044,
+  "BRb8d8": 1045,
+  "BRb8e8": 1046,
+  "BRb8f8": 1047,
+  "BRc2a2(x)": 1048,
+  "BRc2b2(x)": 1049,
+  "BRc3c2": 1050,
+  "BRc7d7": 1051,
+  "BRc8a8": 1052,
+  "BRc8b8": 1053,
+  "BRc8c1(+)": 1054,
+  "BRc8c1(x)": 1055,
+  "BRc8c1(x+)": 1056,
+  "BRc8c2": 1057,
+  "BRc8c2(x)": 1058,
+  "BRc8c3": 1059,
+  "BRc8c3(x)": 1060,
+  "BRc8c4": 1061,
+  "BRc8c4(x)": 1062,
+  "BRc8c5": 1063,
+  "BRc8c5(x)": 1064,
+  "BRc8c6": 1065,
+  "BRc8c6(x)": 1066,
+  "BRc8c7": 1067,
+  "BRc8c7(x)": 1068,
+  "BRc8d8": 1069,
+  "BRc8d8(x)": 1070,
+  "BRc8e8": 1071,
+  "BRc8f8": 1072,
+  "BRd2a2(x)": 1073,
+  "BRd2b2(x)": 1074,
+  "BRd2c2(x)": 1075,
+  "BRd3d2": 1076,
+  "BRd4d2": 1077,
+  "BRd7c7": 1078,
+  "BRd7d6": 1079,
+  "BRd7d8": 1080,
+  "BRd7e7": 1081,
+  "BRd8a8": 1082,
+  "BRd8b8": 1083,
+  "BRd8c8": 1084,
+  "BRd8d1(+)": 1085,
+  "BRd8d1(x)": 1086,
+  "BRd8d1(x+)": 1087,
+  "BRd8d2": 1088,
+  "BRd8d2(+)": 1089,
+  "BRd8d2(x)": 1090,
+  "BRd8d3": 1091,
+  "BRd8d3(x)": 1092,
+  "BRd8d4": 1093,
+  "BRd8d4(x)": 1094,
+  "BRd8d5": 1095,
+  "BRd8d5(x)": 1096,
+  "BRd8d6": 1097,
+  "BRd8d6(x)": 1098,
+  "BRd8d7": 1099,
+  "BRd8d7(x)": 1100,
+  "BRd8e8": 1101,
+  "BRd8e8(x)": 1102,
+  "BRd8f8": 1103,
+  "BRd8g8": 1104,
+  "BRd8h8": 1105,
+  "BRe2b2(x)": 1106,
+  "BRe6f6": 1107,
+  "BRe6g6": 1108,
+  "BRe7d7": 1109,
+  "BRe7e6": 1110,
+  "BRe7e8": 1111,
+  "BRe7f7": 1112,
+  "BRe8a8": 1113,
+  "BRe8b8": 1114,
+  "BRe8c8": 1115,
+  "BRe8d8": 1116,
+  "BRe8d8(x)": 1117,
+  "BRe8e1(+)": 1118,
+  "BRe8e1(x)": 1119,
+  "BRe8e1(x+)": 1120,
+  "BRe8e2": 1121,
+  "BRe8e2(+)": 1122,
+  "BRe8e2(x)": 1123,
+  "BRe8e3": 1124,
+  "BRe8e3(x)": 1125,
+  "BRe8e4": 1126,
+  "BRe8e4(x)": 1127,
+  "BRe8e5": 1128,
+  "BRe8e5(x)": 1129,
+  "BRe8e6": 1130,
+  "BRe8e6(x)": 1131,
+  "BRe8e7": 1132,
+  "BRe8e7(x)": 1133,
+  "BRe8f8": 1134,
+  "BRe8g8": 1135,
+  "BRe8h8": 1136,
+  "BRf6e6": 1137,
+  "BRf6f7": 1138,
+  "BRf6g6": 1139,
+  "BRf7d7": 1140,
+  "BRf7e7": 1141,
+  "BRf7f6": 1142,
+  "BRf7f8": 1143,
+  "BRf7g7": 1144,
+  "BRf8a8": 1145,
+  "BRf8a8(x)": 1146,
+  "BRf8b8": 1147,
+  "BRf8c8": 1148,
+  "BRf8c8(x)": 1149,
+  "BRf8d8": 1150,
+  "BRf8d8(x)": 1151,
+  "BRf8e8": 1152,
+  "BRf8e8(+)": 1153,
+  "BRf8e8(x)": 1154,
+  "BRf8f1(x+)": 1155,
+  "BRf8f2": 1156,
+  "BRf8f2(x)": 1157,
+  "BRf8f3(x)": 1158,
+  "BRf8f4": 1159,
+  "BRf8f4(x)": 1160,
+  "BRf8f5": 1161,
+  "BRf8f5(x)": 1162,
+  "BRf8f6": 1163,
+  "BRf8f6(x)": 1164,
+  "BRf8f7": 1165,
+  "BRf8f7(x)": 1166,
+  "BRf8g8": 1167,
+  "BRf8h8": 1168,
+  "BRg8d8": 1169,
+  "BRg8e8": 1170,
+  "BRg8f8": 1171,
+  "BRg8g5": 1172,
+  "BRg8g6": 1173,
+  "BRg8g7": 1174,
+  "BRg8g7(x)": 1175,
+  "BRg8h8": 1176,
+  "BRh8b8": 1177,
+  "BRh8c8": 1178,
+  "BRh8d8": 1179,
+  "BRh8d8(x)": 1180,
+  "BRh8e8": 1181,
+  "BRh8f8": 1182,
+  "BRh8g8": 1183,
+  "BRh8h3(x)": 1184,
+  "BRh8h4(x)": 1185,
+  "BRh8h5": 1186,
+  "BRh8h5(x)": 1187,
+  "BRh8h6": 1188,
+  "BRh8h6(x)": 1189,
+  "BRh8h7": 1190,
+  "WBa2b1": 1191,
+  "WBa3b2": 1192,
+  "WBa3f8(x)": 1193,
+  "WBa4b3": 1194,
+  "WBa4c2": 1195,
+  "WBb2a3": 1196,
+  "WBb2c1": 1197,
+  "WBb2c3": 1198,
+  "WBb2c3(x)": 1199,
+  "WBb2d4": 1200,
+  "WBb2d4(x)": 1201,
+  "WBb2e5(x)": 1202,
+  "WBb2f6(x)": 1203,
+  "WBb2g7(x)": 1204,
+  "WBb3a2": 1205,
+  "WBb3a4": 1206,
+  "WBb3c2": 1207,
+  "WBb3c4": 1208,
+  "WBb3c4(x)": 1209,
+  "WBb3d5": 1210,
+  "WBb3d5(x)": 1211,
+  "WBb3e6(x)": 1212,
+  "WBb4c3": 1213,
+  "WBb5a4": 1214,
+  "WBb5c4": 1215,
+  "WBb5c6": 1216,
+  "WBb5c6(x)": 1217,
+  "WBb5c6(x+)": 1218,
+  "WBb5d3": 1219,
+  "WBb5d7(x)": 1220,
+  "WBb5d7(x+)": 1221,
+  "WBb5e2": 1222,
+  "WBc1a3": 1223,
+  "WBc1b2": 1224,
+  "WBc1b2(x)": 1225,
+  "WBc1d2": 1226,
+  "WBc1d2(x)": 1227,
+  "WBc1e3": 1228,
+  "WBc1e3(x)": 1229,
+  "WBc1f4": 1230,
+  "WBc1f4(x)": 1231,
+  "WBc1g5": 1232,
+  "WBc1g5(+)": 1233,
+  "WBc1g5(x)": 1234,
+  "WBc1h6": 1235,
+  "WBc1h6(x)": 1236,
+  "WBc2b3": 1237,
+  "WBc2d1": 1238,
+  "WBc2d3": 1239,
+  "WBc2e4": 1240,
+  "WBc2e4(x)": 1241,
+  "WBc3b2": 1242,
+  "WBc3b4": 1243,
+  "WBc3d2": 1244,
+  "WBc3d4": 1245,
+  "WBc3d4(x)": 1246,
+  "WBc3e5(x)": 1247,
+  "WBc3f6(x)": 1248,
+  "WBc4a2": 1249,
+  "WBc4a6(x)": 1250,
+  "WBc4b3": 1251,
+  "WBc4b5": 1252,
+  "WBc4b5(+)": 1253,
+  "WBc4b5(x)": 1254,
+  "WBc4d3": 1255,
+  "WBc4d5": 1256,
+  "WBc4d5(x)": 1257,
+  "WBc4e2": 1258,
+  "WBc4e6(x)": 1259,
+  "WBc4e6(x+)": 1260,
+  "WBc4f7(x)": 1261,
+  "WBc4f7(x+)": 1262,
+  "WBc5d4": 1263,
+  "WBc5e3": 1264,
+  "WBd1c2": 1265,
+  "WBd2a5(x)": 1266,
+  "WBd2b4": 1267,
+  "WBd2b4(x)": 1268,
+  "WBd2c1": 1269,
+  "WBd2c3": 1270,
+  "WBd2c3(x)": 1271,
+  "WBd2e1": 1272,
+  "WBd2e3": 1273,
+  "WBd2f4": 1274,
+  "WBd2f4(x)": 1275,
+  "WBd2g5": 1276,
+  "WBd2h6(x)": 1277,
+  "WBd3a6(x)": 1278,
+  "WBd3b1": 1279,
+  "WBd3b5": 1280,
+  "WBd3b5(+)": 1281,
+  "WBd3b5(x)": 1282,
+  "WBd3c2": 1283,
+  "WBd3c4": 1284,
+  "WBd3c4(+)": 1285,
+  "WBd3c4(x)": 1286,
+  "WBd3e2": 1287,
+  "WBd3e4": 1288,
+  "WBd3e4(x)": 1289,
+  "WBd3f1": 1290,
+  "WBd3f5": 1291,
+  "WBd3f5(x)": 1292,
+  "WBd3g6(x)": 1293,
+  "WBd3h7(x+)": 1294,
+  "WBd4c3": 1295,
+  "WBd4c5": 1296,
+  "WBd4e3": 1297,
+  "WBd4e5(x)": 1298,
+  "WBd4f6(x)": 1299,
+  "WBd4g7(x)": 1300,
+  "WBd5b3": 1301,
+  "WBd5b7(x)": 1302,
+  "WBd5c4": 1303,
+  "WBd5c6(x)": 1304,
+  "WBd5e4": 1305,
+  "WBe2a6(x)": 1306,
+  "WBe2b5": 1307,
+  "WBe2b5(x)": 1308,
+  "WBe2c4": 1309,
+  "WBe2c4(x)": 1310,
+  "WBe2d1": 1311,
+  "WBe2d3": 1312,
+  "WBe2d3(x)": 1313,
+  "WBe2f1": 1314,
+  "WBe2f3": 1315,
+  "WBe2f3(x)": 1316,
+  "WBe2g4": 1317,
+  "WBe2g4(x)": 1318,
+  "WBe2h5": 1319,
+  "WBe2h5(x)": 1320,
+  "WBe3a7(x)": 1321,
+  "WBe3b6": 1322,
+  "WBe3b6(x)": 1323,
+  "WBe3c1": 1324,
+  "WBe3c5": 1325,
+  "WBe3c5(x)": 1326,
+  "WBe3d2": 1327,
+  "WBe3d4": 1328,
+  "WBe3d4(x)": 1329,
+  "WBe3f2": 1330,
+  "WBe3f4": 1331,
+  "WBe3f4(x)": 1332,
+  "WBe3g5": 1333,
+  "WBe3g5(x)": 1334,
+  "WBe3h6": 1335,
+  "WBe3h6(x)": 1336,
+  "WBe4b7(x)": 1337,
+  "WBe4c6(x)": 1338,
+  "WBe4d3": 1339,
+  "WBe4d5(x)": 1340,
+  "WBe4f3": 1341,
+  "WBe4g2": 1342,
+  "WBe5d4": 1343,
+  "WBe5d6": 1344,
+  "WBe5f4": 1345,
+  "WBe5f6(x)": 1346,
+  "WBe5g3": 1347,
+  "WBe5g7(x)": 1348,
+  "WBf1a6(x)": 1349,
+  "WBf1b5": 1350,
+  "WBf1b5(+)": 1351,
+  "WBf1b5(x)": 1352,
+  "WBf1c4": 1353,
+  "WBf1c4(+)": 1354,
+  "WBf1c4(x)": 1355,
+  "WBf1d3": 1356,
+  "WBf1d3(x)": 1357,
+  "WBf1e2": 1358,
+  "WBf1e2(x)": 1359,
+  "WBf1g2": 1360,
+  "WBf1h3": 1361,
+  "WBf2g3": 1362,
+  "WBf3b7(x)": 1363,
+  "WBf3c6(x)": 1364,
+  "WBf3d5(x)": 1365,
+  "WBf3e2": 1366,
+  "WBf3e4": 1367,
+  "WBf3e4(x)": 1368,
+  "WBf3g2": 1369,
+  "WBf3g4": 1370,
+  "WBf4b8(x)": 1371,
+  "WBf4c7(x)": 1372,
+  "WBf4d2": 1373,
+  "WBf4d6": 1374,
+  "WBf4d6(x)": 1375,
+  "WBf4e3": 1376,
+  "WBf4e5": 1377,
+  "WBf4e5(x)": 1378,
+  "WBf4g3": 1379,
+  "WBf4g5": 1380,
+  "WBf4g5(x)": 1381,
+  "WBf4h2": 1382,
+  "WBf4h6": 1383,
+  "WBf4h6(x)": 1384,
+  "WBg2b7(x)": 1385,
+  "WBg2c6(x)": 1386,
+  "WBg2d5(x)": 1387,
+  "WBg2e4": 1388,
+  "WBg2e4(x)": 1389,
+  "WBg2f1": 1390,
+  "WBg2f3": 1391,
+  "WBg2f3(x)": 1392,
+  "WBg2h3": 1393,
+  "WBg3d6(x)": 1394,
+  "WBg3e5": 1395,
+  "WBg3e5(x)": 1396,
+  "WBg3f2": 1397,
+  "WBg3f4": 1398,
+  "WBg3f4(x)": 1399,
+  "WBg3h2": 1400,
+  "WBg3h4": 1401,
+  "WBg4f3": 1402,
+  "WBg5d2": 1403,
+  "WBg5d8(x)": 1404,
+  "WBg5e3": 1405,
+  "WBg5e7(x)": 1406,
+  "WBg5f4": 1407,
+  "WBg5f6": 1408,
+  "WBg5f6(x)": 1409,
+  "WBg5h4": 1410,
+  "WBg5h6": 1411,
+  "WBg5h6(x)": 1412,
+  "WBh3g2": 1413,
+  "WBh4e7(x)": 1414,
+  "WBh4f6(x)": 1415,
+  "WBh4g3": 1416,
+  "WBh5f3": 1417,
+  "WBh5g4": 1418,
+  "WBh6e3": 1419,
+  "WBh6f4": 1420,
+  "WBh6f8(x)": 1421,
+  "WBh6g5": 1422,
+  "WBh6g7(x)": 1423,
+  "WKa1b1": 1424,
+  "WKa2b1": 1425,
+  "WKb1a1": 1426,
+  "WKb1a2": 1427,
+  "WKb1b2": 1428,
+  "WKb1c1": 1429,
+  "WKb1c2": 1430,
+  "WKb2a3": 1431,
+  "WKb2b1": 1432,
+  "WKb2b3": 1433,
+  "WKb2c1": 1434,
+  "WKb2c2": 1435,
+  "WKb2c3": 1436,
+  "WKb3a3": 1437,
+  "WKb3a4": 1438,
+  "WKb3b4": 1439,
+  "WKb3c2": 1440,
+  "WKb3c3": 1441,
+  "WKb3c4": 1442,
+  "WKb4a5": 1443,
+  "WKb4b5": 1444,
+  "WKb4c3": 1445,
+  "WKb4c5": 1446,
+  "WKb5b6": 1447,
+  "WKb5c6": 1448,
+  "WKc1b1": 1449,
+  "WKc1b2": 1450,
+  "WKc1c2": 1451,
+  "WKc1d1": 1452,
+  "WKc1d1(x)": 1453,
+  "WKc1d2": 1454,
+  "WKc2b1": 1455,
+  "WKc2b2": 1456,
+  "WKc2b3": 1457,
+  "WKc2c1": 1458,
+  "WKc2c3": 1459,
+  "WKc2d1": 1460,
+  "WKc2d2": 1461,
+  "WKc2d3": 1462,
+  "WKc3b2": 1463,
+  "WKc3b3": 1464,
+  "WKc3b4": 1465,
+  "WKc3c2": 1466,
+  "WKc3c4": 1467,
+  "WKc3d2": 1468,
+  "WKc3d3": 1469,
+  "WKc3d4": 1470,
+  "WKc4b3": 1471,
+  "WKc4b4": 1472,
+  "WKc4b5": 1473,
+  "WKc4c3": 1474,
+  "WKc4c5": 1475,
+  "WKc4d3": 1476,
+  "WKc4d4": 1477,
+  "WKc4d5": 1478,
+  "WKc5b6": 1479,
+  "WKc5c6": 1480,
+  "WKc5d6": 1481,
+  "WKd1c1": 1482,
+  "WKd1c2": 1483,
+  "WKd1d2": 1484,
+  "WKd1e1": 1485,
+  "WKd1e2": 1486,
+  "WKd2c1": 1487,
+  "WKd2c2": 1488,
+  "WKd2c3": 1489,
+  "WKd2d1": 1490,
+  "WKd2d3": 1491,
+  "WKd2e1": 1492,
+  "WKd2e2": 1493,
+  "WKd2e3": 1494,
+  "WKd3c2": 1495,
+  "WKd3c3": 1496,
+  "WKd3c4": 1497,
+  "WKd3d2": 1498,
+  "WKd3d4": 1499,
+  "WKd3e2": 1500,
+  "WKd3e3": 1501,
+  "WKd3e4": 1502,
+  "WKd4c3": 1503,
+  "WKd4c4": 1504,
+  "WKd4c5": 1505,
+  "WKd4d3": 1506,
+  "WKd4d5": 1507,
+  "WKd4e3": 1508,
+  "WKd4e4": 1509,
+  "WKd4e5": 1510,
+  "WKd5c5": 1511,
+  "WKd5c6": 1512,
+  "WKd5d6": 1513,
+  "WKd5e4": 1514,
+  "WKd5e6": 1515,
+  "WKe1c1(O)": 1516,
+  "WKe1d1": 1517,
+  "WKe1d1(x)": 1518,
+  "WKe1d2": 1519,
+  "WKe1d2(x)": 1520,
+  "WKe1e2": 1521,
+  "WKe1e2(x)": 1522,
+  "WKe1f1": 1523,
+  "WKe1f2": 1524,
+  "WKe1f2(x)": 1525,
+  "WKe1g1(o)": 1526,
+  "WKe2d1": 1527,
+  "WKe2d2": 1528,
+  "WKe2d3": 1529,
+  "WKe2e1": 1530,
+  "WKe2e3": 1531,
+  "WKe2f1": 1532,
+  "WKe2f2": 1533,
+  "WKe2f3": 1534,
+  "WKe3d2": 1535,
+  "WKe3d3": 1536,
+  "WKe3d4": 1537,
+  "WKe3e2": 1538,
+  "WKe3e4": 1539,
+  "WKe3f2": 1540,
+  "WKe3f3": 1541,
+  "WKe3f4": 1542,
+  "WKe4d3": 1543,
+  "WKe4d4": 1544,
+  "WKe4d5": 1545,
+  "WKe4e3": 1546,
+  "WKe4e5": 1547,
+  "WKe4f3": 1548,
+  "WKe4f4": 1549,
+  "WKe4f5": 1550,
+  "WKe5d4": 1551,
+  "WKe5d5": 1552,
+  "WKe5d6": 1553,
+  "WKe5e6": 1554,
+  "WKe5f4": 1555,
+  "WKe5f5": 1556,
+  "WKe5f6": 1557,
+  "WKf1e1": 1558,
+  "WKf1e2": 1559,
+  "WKf1f2": 1560,
+  "WKf1g1": 1561,
+  "WKf1g2": 1562,
+  "WKf2e1": 1563,
+  "WKf2e2": 1564,
+  "WKf2e3": 1565,
+  "WKf2f1": 1566,
+  "WKf2f3": 1567,
+  "WKf2g1": 1568,
+  "WKf2g2": 1569,
+  "WKf2g3": 1570,
+  "WKf3e2": 1571,
+  "WKf3e3": 1572,
+  "WKf3e4": 1573,
+  "WKf3f2": 1574,
+  "WKf3f4": 1575,
+  "WKf3g2": 1576,
+  "WKf3g3": 1577,
+  "WKf3g4": 1578,
+  "WKf4e3": 1579,
+  "WKf4e4": 1580,
+  "WKf4e5": 1581,
+  "WKf4f3": 1582,
+  "WKf4f5": 1583,
+  "WKf4g3": 1584,
+  "WKf4g4": 1585,
+  "WKf4g5": 1586,
+  "WKf5e4": 1587,
+  "WKf5e5": 1588,
+  "WKf5e6": 1589,
+  "WKf5f6": 1590,
+  "WKf5g4": 1591,
+  "WKf5g5": 1592,
+  "WKf5g6": 1593,
+  "WKg1f1": 1594,
+  "WKg1f1(x)": 1595,
+  "WKg1f2": 1596,
+  "WKg1f2(x)": 1597,
+  "WKg1g2": 1598,
+  "WKg1g2(x)": 1599,
+  "WKg1h1": 1600,
+  "WKg1h2": 1601,
+  "WKg1h2(x)": 1602,
+  "WKg2f1": 1603,
+  "WKg2f2": 1604,
+  "WKg2f3": 1605,
+  "WKg2f3(x)": 1606,
+  "WKg2g1": 1607,
+  "WKg2g3": 1608,
+  "WKg2h1": 1609,
+  "WKg2h2": 1610,
+  "WKg2h3": 1611,
+  "WKg3f2": 1612,
+  "WKg3f3": 1613,
+  "WKg3f4": 1614,
+  "WKg3g2": 1615,
+  "WKg3g4": 1616,
+  "WKg3h2": 1617,
+  "WKg3h3": 1618,
+  "WKg3h4": 1619,
+  "WKg4f3": 1620,
+  "WKg4f4": 1621,
+  "WKg4f5": 1622,
+  "WKg4g3": 1623,
+  "WKg4g5": 1624,
+  "WKg4h3": 1625,
+  "WKg4h4": 1626,
+  "WKg4h5": 1627,
+  "WKg5f4": 1628,
+  "WKg5f5": 1629,
+  "WKg5f6": 1630,
+  "WKg5g6": 1631,
+  "WKg5h6": 1632,
+  "WKh1g1": 1633,
+  "WKh1g2": 1634,
+  "WKh1g2(x)": 1635,
+  "WKh1h2": 1636,
+  "WKh2g1": 1637,
+  "WKh2g2": 1638,
+  "WKh2g3": 1639,
+  "WKh2h1": 1640,
+  "WKh2h3": 1641,
+  "WKh3g2": 1642,
+  "WKh3g3": 1643,
+  "WKh3g4": 1644,
+  "WKh3h2": 1645,
+  "WKh3h4": 1646,
+  "WKh4g3": 1647,
+  "WKh4g4": 1648,
+  "WKh4g5": 1649,
+  "WKh4h3": 1650,
+  "WKh4h5": 1651,
+  "WKh5g4": 1652,
+  "WKh5g6": 1653,
+  "WKh5h6": 1654,
+  "WNa3b5": 1655,
+  "WNa3c2": 1656,
+  "WNa3c4": 1657,
+  "WNa4b6": 1658,
+  "WNa4b6(x)": 1659,
+  "WNa4c3": 1660,
+  "WNa4c5": 1661,
+  "WNa4c5(x)": 1662,
+  "WNa7b5": 1663,
+  "WNb1a3": 1664,
+  "WNb1c3": 1665,
+  "WNb1c3(x)": 1666,
+  "WNb1d2": 1667,
+  "WNb1d2(x)": 1668,
+  "WNb3a5": 1669,
+  "WNb3c5": 1670,
+  "WNb3c5(x)": 1671,
+  "WNb3d2": 1672,
+  "WNb3d4": 1673,
+  "WNb3d4(x)": 1674,
+  "WNb5a3": 1675,
+  "WNb5a7(x)": 1676,
+  "WNb5c3": 1677,
+  "WNb5c7": 1678,
+  "WNb5c7(+)": 1679,
+  "WNb5c7(x)": 1680,
+  "WNb5c7(x+)": 1681,
+  "WNb5d4": 1682,
+  "WNb5d4(x)": 1683,
+  "WNb5d6": 1684,
+  "WNb5d6(+)": 1685,
+  "WNb5d6(x)": 1686,
+  "WNb5d6(x+)": 1687,
+  "WNb7c5": 1688,
+  "WNc2e3": 1689,
+  "WNc3a2": 1690,
+  "WNc3a4": 1691,
+  "WNc3a4(x)": 1692,
+  "WNc3b1": 1693,
+  "WNc3b5": 1694,
+  "WNc3b5(x)": 1695,
+  "WNc3d1": 1696,
+  "WNc3d1(x)": 1697,
+  "WNc3d5": 1698,
+  "WNc3d5(+)": 1699,
+  "WNc3d5(x)": 1700,
+  "WNc3e2": 1701,
+  "WNc3e2(x)": 1702,
+  "WNc3e4": 1703,
+  "WNc3e4(x)": 1704,
+  "WNc4a5": 1705,
+  "WNc4b6(x)": 1706,
+  "WNc4d2": 1707,
+  "WNc4d6": 1708,
+  "WNc4d6(x)": 1709,
+  "WNc4e3": 1710,
+  "WNc4e5": 1711,
+  "WNc4e5(x)": 1712,
+  "WNc5a6(x)": 1713,
+  "WNc5b3": 1714,
+  "WNc5b7(x)": 1715,
+  "WNc5d3": 1716,
+  "WNc5d7": 1717,
+  "WNc5e4": 1718,
+  "WNc5e6": 1719,
+  "WNc5e6(x)": 1720,
+  "WNc6d4": 1721,
+  "WNc6e5": 1722,
+  "WNc6e7(+)": 1723,
+  "WNc7a8(x)": 1724,
+  "WNc7b5": 1725,
+  "WNc7d5": 1726,
+  "WNd1c3": 1727,
+  "WNd1e3": 1728,
+  "WNd2b1": 1729,
+  "WNd2b3": 1730,
+  "WNd2c4": 1731,
+  "WNd2c4(x)": 1732,
+  "WNd2e4": 1733,
+  "WNd2e4(x)": 1734,
+  "WNd2f1": 1735,
+  "WNd2f3": 1736,
+  "WNd2f3(x)": 1737,
+  "WNd3c5": 1738,
+  "WNd3e5": 1739,
+  "WNd3f4": 1740,
+  "WNd4b3": 1741,
+  "WNd4b5": 1742,
+  "WNd4b5(x)": 1743,
+  "WNd4c2": 1744,
+  "WNd4c6": 1745,
+  "WNd4c6(x)": 1746,
+  "WNd4e2": 1747,
+  "WNd4e6": 1748,
+  "WNd4e6(x)": 1749,
+  "WNd4f3": 1750,
+  "WNd4f5": 1751,
+  "WNd4f5(x)": 1752,
+  "WNd5b6(x)": 1753,
+  "WNd5c3": 1754,
+  "WNd5c7": 1755,
+  "WNd5c7(+)": 1756,
+  "WNd5c7(x)": 1757,
+  "WNd5c7(x+)": 1758,
+  "WNd5e3": 1759,
+  "WNd5e7(+)": 1760,
+  "WNd5e7(x)": 1761,
+  "WNd5e7(x+)": 1762,
+  "WNd5f4": 1763,
+  "WNd5f6(+)": 1764,
+  "WNd5f6(x)": 1765,
+  "WNd5f6(x+)": 1766,
+  "WNd6b7(x)": 1767,
+  "WNd6c4": 1768,
+  "WNd6c8(x)": 1769,
+  "WNd6e4": 1770,
+  "WNe1d3": 1771,
+  "WNe1f3": 1772,
+  "WNe2c1": 1773,
+  "WNe2c3": 1774,
+  "WNe2c3(x)": 1775,
+  "WNe2d4": 1776,
+  "WNe2d4(x)": 1777,
+  "WNe2f4": 1778,
+  "WNe2f4(x)": 1779,
+  "WNe2g1": 1780,
+  "WNe2g3": 1781,
+  "WNe3c4": 1782,
+  "WNe3d5": 1783,
+  "WNe3f5": 1784,
+  "WNe3g4": 1785,
+  "WNe4c3": 1786,
+  "WNe4c5": 1787,
+  "WNe4c5(x)": 1788,
+  "WNe4d2": 1789,
+  "WNe4d6": 1790,
+  "WNe4d6(+)": 1791,
+  "WNe4d6(x)": 1792,
+  "WNe4d6(x+)": 1793,
+  "WNe4f6": 1794,
+  "WNe4f6(+)": 1795,
+  "WNe4f6(x)": 1796,
+  "WNe4f6(x+)": 1797,
+  "WNe4g3": 1798,
+  "WNe4g5": 1799,
+  "WNe4g5(x)": 1800,
+  "WNe5c4": 1801,
+  "WNe5c4(x)": 1802,
+  "WNe5c6": 1803,
+  "WNe5c6(x)": 1804,
+  "WNe5d3": 1805,
+  "WNe5d7": 1806,
+  "WNe5d7(x)": 1807,
+  "WNe5f3": 1808,
+  "WNe5f7(+)": 1809,
+  "WNe5f7(x)": 1810,
+  "WNe5g4": 1811,
+  "WNe5g4(x)": 1812,
+  "WNe5g6": 1813,
+  "WNe5g6(x)": 1814,
+  "WNe6f8(x)": 1815,
+  "WNe6g7(x)": 1816,
+  "WNf1d2": 1817,
+  "WNf1e3": 1818,
+  "WNf1g3": 1819,
+  "WNf3d2": 1820,
+  "WNf3d2(x)": 1821,
+  "WNf3d4": 1822,
+  "WNf3d4(x)": 1823,
+  "WNf3e1": 1824,
+  "WNf3e5": 1825,
+  "WNf3e5(+)": 1826,
+  "WNf3e5(x)": 1827,
+  "WNf3g1": 1828,
+  "WNf3g5": 1829,
+  "WNf3g5(+)": 1830,
+  "WNf3g5(x)": 1831,
+  "WNf3h2": 1832,
+  "WNf3h4": 1833,
+  "WNf3h4(x)": 1834,
+  "WNf4d3": 1835,
+  "WNf4d5": 1836,
+  "WNf4d5(x)": 1837,
+  "WNf4e2": 1838,
+  "WNf4e6": 1839,
+  "WNf4e6(x)": 1840,
+  "WNf4g6(x)": 1841,
+  "WNf4h5": 1842,
+  "WNf5d6": 1843,
+  "WNf5e3": 1844,
+  "WNf5e7(+)": 1845,
+  "WNf5g3": 1846,
+  "WNf7h8(x)": 1847,
+  "WNg1e2": 1848,
+  "WNg1f3": 1849,
+  "WNg1f3(x)": 1850,
+  "WNg1h3": 1851,
+  "WNg3e2": 1852,
+  "WNg3e4": 1853,
+  "WNg3e4(x)": 1854,
+  "WNg3f1": 1855,
+  "WNg3f5": 1856,
+  "WNg3f5(x)": 1857,
+  "WNg3h5": 1858,
+  "WNg4e3": 1859,
+  "WNg4e5": 1860,
+  "WNg5e4": 1861,
+  "WNg5e4(x)": 1862,
+  "WNg5e6": 1863,
+  "WNg5e6(+)": 1864,
+  "WNg5e6(x)": 1865,
+  "WNg5f3": 1866,
+  "WNg5f7": 1867,
+  "WNg5f7(+)": 1868,
+  "WNg5f7(x)": 1869,
+  "WNg5h3": 1870,
+  "WNg5h7(x)": 1871,
+  "WNh2f3": 1872,
+  "WNh2g4": 1873,
+  "WNh3f2": 1874,
+  "WNh3f4": 1875,
+  "WNh3g5": 1876,
+  "WNh4f3": 1877,
+  "WNh4f5": 1878,
+  "WNh4f5(x)": 1879,
+  "WNh4g6": 1880,
+  "WNh4g6(x)": 1881,
+  "WNh5g3": 1882,
+  "WPa2a3": 1883,
+  "WPa2a4": 1884,
+  "WPa2b3(x)": 1885,
+  "WPa3a4": 1886,
+  "WPa3b4(x)": 1887,
+  "WPa4a5": 1888,
+  "WPa4b5(x)": 1889,
+  "WPa5a6": 1890,
+  "WPa5b6(x)": 1891,
+  "WPa6a7": 1892,
+  "WPa7a8(Q)": 1893,
+  "WPb2a3(x)": 1894,
+  "WPb2b3": 1895,
+  "WPb2b4": 1896,
+  "WPb2c3(x)": 1897,
+  "WPb3a4(x)": 1898,
+  "WPb3b4": 1899,
+  "WPb3c4(x)": 1900,
+  "WPb4a5(x)": 1901,
+  "WPb4b5": 1902,
+  "WPb4c5(x)": 1903,
+  "WPb5a6(x)": 1904,
+  "WPb5b6": 1905,
+  "WPb5c6(x)": 1906,
+  "WPb6b7": 1907,
+  "WPb7b8(Q)": 1908,
+  "WPc2b3(x)": 1909,
+  "WPc2c3": 1910,
+  "WPc2c4": 1911,
+  "WPc2d3(x)": 1912,
+  "WPc3b4(x)": 1913,
+  "WPc3c4": 1914,
+  "WPc3d4(x)": 1915,
+  "WPc4b5(x)": 1916,
+  "WPc4c5": 1917,
+  "WPc4d5(x)": 1918,
+  "WPc5b6(x)": 1919,
+  "WPc5c6": 1920,
+  "WPc5d6(x)": 1921,
+  "WPc6c7": 1922,
+  "WPc7c8(Q)": 1923,
+  "WPd2c3(x)": 1924,
+  "WPd2d3": 1925,
+  "WPd2d4": 1926,
+  "WPd3c4(x)": 1927,
+  "WPd3d4": 1928,
+  "WPd3e4(x)": 1929,
+  "WPd4c5(x)": 1930,
+  "WPd4d5": 1931,
+  "WPd4e5(x)": 1932,
+  "WPd5c6(x)": 1933,
+  "WPd5d6": 1934,
+  "WPd5d6(+)": 1935,
+  "WPd5e6(x)": 1936,
+  "WPd6d7": 1937,
+  "WPd7d8(Q)": 1938,
+  "WPe2e3": 1939,
+  "WPe2e4": 1940,
+  "WPe2f3(x)": 1941,
+  "WPe3d4(x)": 1942,
+  "WPe3e4": 1943,
+  "WPe3f4(x)": 1944,
+  "WPe4d5(x)": 1945,
+  "WPe4e5": 1946,
+  "WPe4e5(+)": 1947,
+  "WPe4f5(x)": 1948,
+  "WPe5d6(x)": 1949,
+  "WPe5d6(xE)": 1950,
+  "WPe5e6": 1951,
+  "WPe5e6(+)": 1952,
+  "WPe5f6(x)": 1953,
+  "WPe5f6(x+)": 1954,
+  "WPe5f6(xE)": 1955,
+  "WPe6e7": 1956,
+  "WPe6f7(x+)": 1957,
+  "WPe7e8(Q)": 1958,
+  "WPf2e3(x)": 1959,
+  "WPf2f3": 1960,
+  "WPf2f4": 1961,
+  "WPf2g3(x)": 1962,
+  "WPf3e4(x)": 1963,
+  "WPf3f4": 1964,
+  "WPf3g4(x)": 1965,
+  "WPf4e5(x)": 1966,
+  "WPf4f5": 1967,
+  "WPf4f5(+)": 1968,
+  "WPf4g5(x)": 1969,
+  "WPf5e6(x)": 1970,
+  "WPf5f6": 1971,
+  "WPf5f6(+)": 1972,
+  "WPf5g6(x)": 1973,
+  "WPf6f7": 1974,
+  "WPf6g7(x)": 1975,
+  "WPf7f8(Q)": 1976,
+  "WPg2f3(x)": 1977,
+  "WPg2g3": 1978,
+  "WPg2g4": 1979,
+  "WPg2h3(x)": 1980,
+  "WPg3f4(x)": 1981,
+  "WPg3g4": 1982,
+  "WPg3h4(x)": 1983,
+  "WPg4f5(x)": 1984,
+  "WPg4g5": 1985,
+  "WPg4g5(+)": 1986,
+  "WPg4h5(x)": 1987,
+  "WPg5f6(x)": 1988,
+  "WPg5g6": 1989,
+  "WPg5h6(x)": 1990,
+  "WPg6g7": 1991,
+  "WPg7g8(Q)": 1992,
+  "WPh2g3(x)": 1993,
+  "WPh2h3": 1994,
+  "WPh2h4": 1995,
+  "WPh3g4(x)": 1996,
+  "WPh3h4": 1997,
+  "WPh4g5(x)": 1998,
+  "WPh4h5": 1999,
+  "WPh5g6(x)": 2000,
+  "WPh5h6": 2001,
+  "WPh6h7": 2002,
+  "WPh7h8(Q)": 2003,
+  "WQa4b3": 2004,
+  "WQa4c2": 2005,
+  "WQa4d1": 2006,
+  "WQb3a4": 2007,
+  "WQb3b4": 2008,
+  "WQb3b7(x)": 2009,
+  "WQb3c2": 2010,
+  "WQb3c3": 2011,
+  "WQb3d1": 2012,
+  "WQb3d3": 2013,
+  "WQb3d5(x)": 2014,
+  "WQb5b7(x)": 2015,
+  "WQb7a7(x)": 2016,
+  "WQc2a4": 2017,
+  "WQc2b1": 2018,
+  "WQc2b2": 2019,
+  "WQc2b3": 2020,
+  "WQc2c3": 2021,
+  "WQc2c3(x)": 2022,
+  "WQc2d1": 2023,
+  "WQc2d2": 2024,
+  "WQc2d3": 2025,
+  "WQc2d3(x)": 2026,
+  "WQc2e2": 2027,
+  "WQc2e4": 2028,
+  "WQc2e4(x)": 2029,
+  "WQc2f2": 2030,
+  "WQc3d2": 2031,
+  "WQc4b3": 2032,
+  "WQc4d3": 2033,
+  "WQc4e2": 2034,
+  "WQd1a1(x)": 2035,
+  "WQd1a4": 2036,
+  "WQd1a4(+)": 2037,
+  "WQd1b1": 2038,
+  "WQd1b3": 2039,
+  "WQd1b3(+)": 2040,
+  "WQd1c1": 2041,
+  "WQd1c2": 2042,
+  "WQd1c2(x)": 2043,
+  "WQd1d2": 2044,
+  "WQd1d2(x)": 2045,
+  "WQd1d3": 2046,
+  "WQd1d3(x)": 2047,
+  "WQd1d4": 2048,
+  "WQd1d4(x)": 2049,
+  "WQd1d5": 2050,
+  "WQd1d5(x)": 2051,
+  "WQd1d6(x)": 2052,
+  "WQd1d8(x)": 2053,
+  "WQd1d8(x+)": 2054,
+  "WQd1e1": 2055,
+  "WQd1e1(x)": 2056,
+  "WQd1e2": 2057,
+  "WQd1e2(+)": 2058,
+  "WQd1e2(x)": 2059,
+  "WQd1f1": 2060,
+  "WQd1f3": 2061,
+  "WQd1f3(+)": 2062,
+  "WQd1f3(x)": 2063,
+  "WQd1g4": 2064,
+  "WQd1g4(+)": 2065,
+  "WQd1g4(x)": 2066,
+  "WQd1h5": 2067,
+  "WQd1h5(+)": 2068,
+  "WQd1h5(x)": 2069,
+  "WQd2c1": 2070,
+  "WQd2c2": 2071,
+  "WQd2c3": 2072,
+  "WQd2c3(x)": 2073,
+  "WQd2d1": 2074,
+  "WQd2d3": 2075,
+  "WQd2d3(x)": 2076,
+  "WQd2d4": 2077,
+  "WQd2d4(x)": 2078,
+  "WQd2e2": 2079,
+  "WQd2e3": 2080,
+  "WQd2e3(x)": 2081,
+  "WQd2f2": 2082,
+  "WQd2f4": 2083,
+  "WQd2f4(x)": 2084,
+  "WQd2g5": 2085,
+  "WQd2h6": 2086,
+  "WQd2h6(x)": 2087,
+  "WQd3b3": 2088,
+  "WQd3b5": 2089,
+  "WQd3c2": 2090,
+  "WQd3c3": 2091,
+  "WQd3c4": 2092,
+  "WQd3d2": 2093,
+  "WQd3d4": 2094,
+  "WQd3d4(x)": 2095,
+  "WQd3e2": 2096,
+  "WQd3e3": 2097,
+  "WQd3e4": 2098,
+  "WQd3e4(x)": 2099,
+  "WQd3f3": 2100,
+  "WQd3g3": 2101,
+  "WQd4d1": 2102,
+  "WQd4d2": 2103,
+  "WQd4d3": 2104,
+  "WQd4e3": 2105,
+  "WQe1f2": 2106,
+  "WQe1g3": 2107,
+  "WQe2b5": 2108,
+  "WQe2c2": 2109,
+  "WQe2c4": 2110,
+  "WQe2c4(x)": 2111,
+  "WQe2d1": 2112,
+  "WQe2d2": 2113,
+  "WQe2d3": 2114,
+  "WQe2d3(x)": 2115,
+  "WQe2e1": 2116,
+  "WQe2e3": 2117,
+  "WQe2e3(x)": 2118,
+  "WQe2e4": 2119,
+  "WQe2e4(x)": 2120,
+  "WQe2e5(x)": 2121,
+  "WQe2f1": 2122,
+  "WQe2f2": 2123,
+  "WQe2f3": 2124,
+  "WQe2f3(x)": 2125,
+  "WQe2g2": 2126,
+  "WQe2g4": 2127,
+  "WQe2h5": 2128,
+  "WQe3d2": 2129,
+  "WQe3d3": 2130,
+  "WQe3e2": 2131,
+  "WQe3f3": 2132,
+  "WQe3f4": 2133,
+  "WQe3g3": 2134,
+  "WQe4d3": 2135,
+  "WQe4e2": 2136,
+  "WQe4e3": 2137,
+  "WQe4f3": 2138,
+  "WQf2g3": 2139,
+  "WQf3b3": 2140,
+  "WQf3b7(x)": 2141,
+  "WQf3d1": 2142,
+  "WQf3d3": 2143,
+  "WQf3d5(x)": 2144,
+  "WQf3e2": 2145,
+  "WQf3e3": 2146,
+  "WQf3e4": 2147,
+  "WQf3e4(x)": 2148,
+  "WQf3f2": 2149,
+  "WQf3f4": 2150,
+  "WQf3f4(x)": 2151,
+  "WQf3f6(x)": 2152,
+  "WQf3f7(x+)": 2153,
+  "WQf3g2": 2154,
+  "WQf3g3": 2155,
+  "WQf3g4": 2156,
+  "WQf3h3": 2157,
+  "WQf3h5": 2158,
+  "WQf4g3": 2159,
+  "WQg3e3": 2160,
+  "WQg3f2": 2161,
+  "WQg3f3": 2162,
+  "WQg3g4": 2163,
+  "WQg3h3": 2164,
+  "WQg3h4": 2165,
+  "WQg4e2": 2166,
+  "WQg4f3": 2167,
+  "WQg4g3": 2168,
+  "WQg4g5": 2169,
+  "WQg4h4": 2170,
+  "WQg4h5": 2171,
+  "WQh3g3": 2172,
+  "WQh4g3": 2173,
+  "WQh5e2": 2174,
+  "WQh5f3": 2175,
+  "WQh5g4": 2176,
+  "WQh5h4": 2177,
+  "WQh5h6": 2178,
+  "WQh7h8(+)": 2179,
+  "WRa1a2": 2180,
+  "WRa1a2(x)": 2181,
+  "WRa1a3": 2182,
+  "WRa1a3(x)": 2183,
+  "WRa1a4": 2184,
+  "WRa1a4(x)": 2185,
+  "WRa1a5(x)": 2186,
+  "WRa1a6(x)": 2187,
+  "WRa1a7": 2188,
+  "WRa1a7(x)": 2189,
+  "WRa1a8(x)": 2190,
+  "WRa1b1": 2191,
+  "WRa1b1(x)": 2192,
+  "WRa1c1": 2193,
+  "WRa1c1(x)": 2194,
+  "WRa1d1": 2195,
+  "WRa1d1(+)": 2196,
+  "WRa1d1(x)": 2197,
+  "WRa1e1": 2198,
+  "WRa1e1(+)": 2199,
+  "WRa1e1(x)": 2200,
+  "WRa1f1": 2201,
+  "WRa1f1(x)": 2202,
+  "WRa1g1": 2203,
+  "WRa1h1": 2204,
+  "WRa6a7": 2205,
+  "WRa6a7(+)": 2206,
+  "WRa7a6": 2207,
+  "WRa7a8": 2208,
+  "WRa7a8(+)": 2209,
+  "WRa7b7": 2210,
+  "WRa7c7": 2211,
+  "WRb1a1": 2212,
+  "WRb1b2": 2213,
+  "WRb1b2(x)": 2214,
+  "WRb1b3": 2215,
+  "WRb1b4(x)": 2216,
+  "WRb1b5": 2217,
+  "WRb1b5(x)": 2218,
+  "WRb1b6(x)": 2219,
+  "WRb1b7": 2220,
+  "WRb1b7(x)": 2221,
+  "WRb1c1": 2222,
+  "WRb1d1": 2223,
+  "WRb1e1": 2224,
+  "WRb1f1": 2225,
+  "WRb7a7": 2226,
+  "WRb7a7(x)": 2227,
+  "WRb7b6": 2228,
+  "WRb7b8(+)": 2229,
+  "WRb7c7": 2230,
+  "WRc1a1": 2231,
+  "WRc1b1": 2232,
+  "WRc1c2": 2233,
+  "WRc1c2(x)": 2234,
+  "WRc1c3": 2235,
+  "WRc1c3(x)": 2236,
+  "WRc1c4": 2237,
+  "WRc1c4(x)": 2238,
+  "WRc1c5": 2239,
+  "WRc1c5(x)": 2240,
+  "WRc1c6": 2241,
+  "WRc1c6(x)": 2242,
+  "WRc1c7": 2243,
+  "WRc1c7(x)": 2244,
+  "WRc1c8(+)": 2245,
+  "WRc1c8(x)": 2246,
+  "WRc1c8(x+)": 2247,
+  "WRc1d1": 2248,
+  "WRc1e1": 2249,
+  "WRc1f1": 2250,
+  "WRc2d2": 2251,
+  "WRc6c7": 2252,
+  "WRc7a7(x)": 2253,
+  "WRc7b7(x)": 2254,
+  "WRd1a1": 2255,
+  "WRd1b1": 2256,
+  "WRd1c1": 2257,
+  "WRd1d2": 2258,
+  "WRd1d2(x)": 2259,
+  "WRd1d3": 2260,
+  "WRd1d3(x)": 2261,
+  "WRd1d4": 2262,
+  "WRd1d4(x)": 2263,
+  "WRd1d5": 2264,
+  "WRd1d5(x)": 2265,
+  "WRd1d6": 2266,
+  "WRd1d6(x)": 2267,
+  "WRd1d7": 2268,
+  "WRd1d7(+)": 2269,
+  "WRd1d7(x)": 2270,
+  "WRd1d8(+)": 2271,
+  "WRd1d8(x)": 2272,
+  "WRd1d8(x+)": 2273,
+  "WRd1e1": 2274,
+  "WRd1e1(+)": 2275,
+  "WRd1e1(x)": 2276,
+  "WRd1f1": 2277,
+  "WRd1g1": 2278,
+  "WRd1h1": 2279,
+  "WRd2c2": 2280,
+  "WRd2d1": 2281,
+  "WRd2d3": 2282,
+  "WRd2e2": 2283,
+  "WRd3d2": 2284,
+  "WRd3e3": 2285,
+  "WRd5d7": 2286,
+  "WRd6d7": 2287,
+  "WRd7a7(x)": 2288,
+  "WRd7b7(x)": 2289,
+  "WRd7c7(x)": 2290,
+  "WRe1a1": 2291,
+  "WRe1b1": 2292,
+  "WRe1c1": 2293,
+  "WRe1d1": 2294,
+  "WRe1d1(x)": 2295,
+  "WRe1e2": 2296,
+  "WRe1e2(x)": 2297,
+  "WRe1e3": 2298,
+  "WRe1e3(x)": 2299,
+  "WRe1e4": 2300,
+  "WRe1e4(x)": 2301,
+  "WRe1e5": 2302,
+  "WRe1e5(x)": 2303,
+  "WRe1e6": 2304,
+  "WRe1e6(x)": 2305,
+  "WRe1e7": 2306,
+  "WRe1e7(+)": 2307,
+  "WRe1e7(x)": 2308,
+  "WRe1e8(+)": 2309,
+  "WRe1e8(x)": 2310,
+  "WRe1e8(x+)": 2311,
+  "WRe1f1": 2312,
+  "WRe1g1": 2313,
+  "WRe1h1": 2314,
+  "WRe2c2": 2315,
+  "WRe2d2": 2316,
+  "WRe2e1": 2317,
+  "WRe2e3": 2318,
+  "WRe2f2": 2319,
+  "WRe3d3": 2320,
+  "WRe3e2": 2321,
+  "WRe3f3": 2322,
+  "WRe3g3": 2323,
+  "WRe6e7": 2324,
+  "WRe7b7(x)": 2325,
+  "WRf1a1": 2326,
+  "WRf1a1(x)": 2327,
+  "WRf1b1": 2328,
+  "WRf1c1": 2329,
+  "WRf1c1(x)": 2330,
+  "WRf1d1": 2331,
+  "WRf1d1(x)": 2332,
+  "WRf1e1": 2333,
+  "WRf1e1(+)": 2334,
+  "WRf1e1(x)": 2335,
+  "WRf1f2": 2336,
+  "WRf1f2(x)": 2337,
+  "WRf1f3": 2338,
+  "WRf1f3(x)": 2339,
+  "WRf1f4": 2340,
+  "WRf1f4(x)": 2341,
+  "WRf1f5": 2342,
+  "WRf1f5(x)": 2343,
+  "WRf1f6": 2344,
+  "WRf1f6(x)": 2345,
+  "WRf1f7": 2346,
+  "WRf1f7(+)": 2347,
+  "WRf1f7(x)": 2348,
+  "WRf1f8(x+)": 2349,
+  "WRf1g1": 2350,
+  "WRf1h1": 2351,
+  "WRf2d2": 2352,
+  "WRf2e2": 2353,
+  "WRf2f1": 2354,
+  "WRf2f3": 2355,
+  "WRf2g2": 2356,
+  "WRf3e3": 2357,
+  "WRf3f2": 2358,
+  "WRf3g3": 2359,
+  "WRf3h3": 2360,
+  "WRg1d1": 2361,
+  "WRg1e1": 2362,
+  "WRg1f1": 2363,
+  "WRg1g2": 2364,
+  "WRg1g3": 2365,
+  "WRg1g4": 2366,
+  "WRg1h1": 2367,
+  "WRg3f3": 2368,
+  "WRg3h3": 2369,
+  "WRh1b1": 2370,
+  "WRh1c1": 2371,
+  "WRh1d1": 2372,
+  "WRh1d1(x)": 2373,
+  "WRh1e1": 2374,
+  "WRh1f1": 2375,
+  "WRh1g1": 2376,
+  "WRh1h2": 2377,
+  "WRh1h3": 2378,
+  "WRh1h4": 2379,
+  "WRh1h5(x)": 2380,
+  "WRh1h6(x)": 2381,
+  "WRh3g3": 2382
+}