import fitz  # PyMuPDF
from PIL import Image
import os
import convert_from_path
from itertools import islice
from collections import namedtuple
import pytesseract
import argparse
import imutils
import cv2
import shutil
import os
import gradio as gr


def cleanup_text(text):
	return "".join([c if ord(c) < 128 else "" for c in text]).strip()




def detectarCatastro(pdf):
    if pdf.endswith(".pdf"):
        images = []
        pdf =  fitz.open("pdf",pdf)
        # Iterar sobre cada página del PDF
        for page_num in range(len(pdf)):
            page = pdf.load_page(page_num)
            pix = page.get_pixmap()
            images.append(pix)


        aligned_images = []
        template = cv2.imread('alignImage1.png')
        aligned_image = align_images(images[0], template, debug=True)
        aligned_images.append(aligned_image)

        template = cv2.imread('alignImage2.png')
        aligned_image = align_images(images[1], template, debug=True)
        aligned_images.append(aligned_image)

        filtered_image = cv2.bilateralFilter(aligned_images[0], 9, 75, 75)
        
        alignedImage = filtered_image
        alignedImage = cv2.resize(alignedImage, None, fx=1, fy=1, interpolation=cv2.INTER_LINEAR)

        OCRLocation = namedtuple("OCRLocation", ["id", "bbox", "filter_keywords"])

        OCR_LOCATIONS = [
            OCRLocation("Numero de la parcela", (385, 33, 225, 20), ["numero", "de", "la", "parcela"]),
        ]
        
        mostrar = "Numero de la parcela: "
        
        for loc in OCR_LOCATIONS:
            (x, y, w, h) = loc.bbox
            roi = alignedImage[y:y + h, x:x + w]
        
            rgb = cv2.cvtColor(roi, cv2.COLOR_BGR2RGB)
            text = pytesseract.image_to_string(rgb)

        mostrar = mostrar + text + " | Cultivos: "


        filtered_image = cv2.bilateralFilter(aligned_images[1], 9, 75, 75)
        
        alignedImage = filtered_image
        alignedImage = cv2.resize(alignedImage, None, fx=1, fy=1, interpolation=cv2.INTER_LINEAR)
        
     
        

        OCR_LOCATIONS = [
            OCRLocation("Cultivos", (75, 58, 180, 190), ["cultivos", "y", "aprovechamientos"]),
        ]
        

        
        
        for loc in OCR_LOCATIONS:
         
            (x, y, w, h) = loc.bbox
            roi = alignedImage[y:y + h, x:x + w]
            
            rgb = cv2.cvtColor(roi, cv2.COLOR_BGR2RGB)
            text = pytesseract.image_to_string(rgb)
        mostrar = mostrar + text

        return mostrar


pdf = gr.File(label="Input PDF", value="ejemplo.pdf")
method = gr.Radio(["PaddleOCR","EasyOCR", "KerasOCR"],value="PaddleOCR")
output = gr.Textbox(label="Output")

demo = gr.Interface(
    detectarCatastro,
    [pdf],
    output,
    title="DetectorCatastro",
    css=".gradio-container {background-color: lightgray} #radio_div {background-color: #FFD8B4; font-size: 40px;}",
    article = """<p style='text-align: center;'>Feel free to give us your thoughts on this demo and please contact us at 
                    <a href="mailto:letstalk@pragnakalp.com" target="_blank">letstalk@pragnakalp.com</a> 
                    <p style='text-align: center;'>Developed by: <a href="https://www.pragnakalp.com/" target="_blank">Pragnakalp Techlabs</a></p>"""


)
demo.launch()