import gradio as gr
from transformers import TrOCRProcessor, VisionEncoderDecoderModel
import requests
from PIL import Image
from craft_text_detector import (
    read_image,
    load_craftnet_model,
    load_refinenet_model,
    get_prediction,
    export_detected_regions,
    export_extra_results,
    empty_cuda_cache
)
from craft_text_detector import Craft
import torch
import numpy as np

processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-handwritten")
model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-handwritten")
craft = Craft(output_dir=None, 
              crop_type="poly",
              export_extra=False,
              link_threshold=0.1,
              text_threshold=0.3,
              cuda=torch.cuda.is_available())


# load image examples from the IAM database
urls = ['https://cdn.shopify.com/s/files/1/0275/6457/2777/files/Penwritten_2048x.jpg']
for idx, url in enumerate(urls):
  image = Image.open(requests.get(url, stream=True).raw)
  image.save(f"image_{idx}.png")

def process_image(image):
    img = np.array(image)
    prediction_result = craft.detect_text(img)
    text = []
    for i,j in enumerate(prediction_result['boxes']): 
      roi = img[int(prediction_result['boxes'][i][0][1]): int(prediction_result['boxes'][i][2][1]), 
                int(prediction_result['boxes'][i][0][0]): int(prediction_result['boxes'][i][2][0])]
      image = Image.fromarray(roi).convert("RGB")
      pixel_values = processor(image, return_tensors="pt").pixel_values
      generated_ids = model.generate(pixel_values)
      generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
      text.append(generated_text)
      print('line ' + str(i) + ' has been recoginized')

    generated_text = ('\n').join(text)


    # # prepare image
    # pixel_values = processor(image, return_tensors="pt").pixel_values

    # # generate (no beam search)
    # generated_ids = model.generate(pixel_values)

    # # decode
    # generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]

    return generated_text

title = "Interactive demo: TrOCR"
description = "Demo for Microsoft's TrOCR, an encoder-decoder model consisting of an image Transformer encoder and a text Transformer decoder for state-of-the-art optical character recognition (OCR) on single-text line images. This particular model is fine-tuned on IAM, a dataset of annotated handwritten images. To use it, simply upload an image or use the example image below and click 'submit'. Results will show up in a few seconds."
article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2109.10282'>TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models</a> | <a href='https://github.com/microsoft/unilm/tree/master/trocr'>Github Repo</a></p>"
examples =[["image_0.png"]]

iface = gr.Interface(fn=process_image, 
                     inputs=gr.inputs.Image(type="pil"), 
                     outputs=gr.outputs.Textbox(),
                     title=title,
                     description=description,
                     article=article,
                     examples=examples)
iface.launch(debug=True)