import os
import re
import torch
from pdf2image import convert_from_path
from helpers import majority_vote_dicts, limit_pagenumbers
from transformers import DonutProcessor, VisionEncoderDecoderModel

os.environ["TOKENIZERS_PARALLELISM"] = "false"
model_name = "harish3110/donut-quandri-all-data"
processor = DonutProcessor.from_pretrained(model_name)
model = VisionEncoderDecoderModel.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model.to(device)

def process_pdf(pdf_file, cut_off=20):
    limit_pagenumbers(pdf_file.name)
    images = convert_from_path(pdf_file.name)
    results = []
    # cut pdf to 20 pages
    if len(images) > cut_off:
        images = images[:cut_off]
    for image in images:
        result = process_document(image)
        results.append(result)
    return majority_vote_dicts(results)

def process_document(image):
    # prepare encoder inputs
    pixel_values = processor(image, return_tensors="pt").pixel_values
    
    # prepare decoder inputs
    task_prompt = "<s_cord-v2>"
    decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt").input_ids
          
    # generate answer
    outputs = model.generate(
        pixel_values.to(device),
        decoder_input_ids=decoder_input_ids.to(device),
        max_length=model.decoder.config.max_position_embeddings,
        early_stopping=True,
        pad_token_id=processor.tokenizer.pad_token_id,
        eos_token_id=processor.tokenizer.eos_token_id,
        use_cache=True,
        num_beams=1,
        bad_words_ids=[[processor.tokenizer.unk_token_id]],
        return_dict_in_generate=True,
    )
    
    # postprocess
    sequence = processor.batch_decode(outputs.sequences)[0]
    sequence = sequence.replace(processor.tokenizer.eos_token, "").replace(processor.tokenizer.pad_token, "")
    sequence = re.sub(r"<.*?>", "", sequence, count=1).strip()  # remove first task start token
    return processor.token2json(sequence)