from modeling import MT5ForConditionalGeneration
from transformers import AutoTokenizer
import os


class ChemicalConverter:
    def __init__(self, mode: str):
        self.mode = mode
        model_directory = os.path.abspath("models")
        model_path = os.path.join(model_directory, mode)
        if not os.path.exists(model_path):
            raise ValueError(f"Model path does not exist: {model_path}")
        self.model = MT5ForConditionalGeneration.from_pretrained(model_path)
        self.smiles_tokenizer = AutoTokenizer.from_pretrained("BioMike/smiles")
        self.iupac_tokenizer = AutoTokenizer.from_pretrained("BioMike/iupac")
        self.smiles_max_len = 128
        self.iupac_max_len = 156

    def convert(self, input):
        if self.mode == "SMILES2IUPAC":
            tokenizer = self.smiles_tokenizer
            reverse_tokenizer = self.iupac_tokenizer
            max_length = self.smiles_max_len
        else:
            tokenizer = self.iupac_tokenizer
            reverse_tokenizer = self.smiles_tokenizer
            max_length = self.iupac_max_len

        encoding = tokenizer(input,
                             return_tensors='pt',
                             padding="max_length",
                             truncation=True,
                             max_length=max_length)
        # Move the input tensor to GPU
        encoding = {key: value.to(self.model.device) for key, value in encoding.items()}

        # Generate  names
        output = self.model.generate(input_ids=encoding['input_ids'],
                                     attention_mask=encoding['attention_mask'],
                                     max_new_tokens=156,
                                     num_beams=1,
                                     num_return_sequences=1)

        # Decode names
        output = [reverse_tokenizer.decode(ids, skip_special_tokens=True) for ids in output]

        return output[0]