app.py

import sys
import os
sys.path.insert(0, os.path.abspath(os.path.dirname(__file__)))
from paddleocr import PaddleOCR
import cv2
import numpy as np  
import pandas as pd




from doctr.models import ocr_predictor
from torch.utils.data import DataLoader
from doctr.io import DocumentFile


import math
from typing import Tuple, Union

import cv2
import numpy as np
import os

from deskew import determine_skew




print(sys.version)
ocr = PaddleOCR(lang='en')
model = ocr_predictor(pretrained=True)

ocr = PaddleOCR(lang='en')



def find_surr_keys(unassigned_key, known_keys):
    # Sort known keys
    print(known_keys)
    known_keys = sorted(known_keys)
    # Initialize distances and closest keys
    closest_keys = []
    for k in known_keys:
         closest_keys.append((abs(int(k) - int(unassigned_key)), k))
    # Sort by distance
    closest_keys.sort()
    # Return the two closest known keys
    if(closest_keys[0][1]<unassigned_key and closest_keys[0][1]>unassigned_key):
        return [closest_keys[0][1], closest_keys[1][1]]
    else:
        raise ValueError(f"No closest keys found for unassigned key: {unassigned_key}")

def label_text(text):
    # Define the two lists
    list1 = ['t', 'r', 'u', 'T', 'R', 'U']
    list2 = ['f', 'a', 'l', 's', 'F', 'A', 'L', 'S']
    
    # Count the matches for each list
    count1 = sum(text.count(char) for char in list1)
    count2 = sum(text.count(char) for char in list2)
    
    # Determine the label based on the counts
    if count1 > count2:
        return True
    elif count1!=0 or count2!=0:
        return False


def percentMatch(text1,text2):
    list = ['t', 'r', 'u', 'T', 'R', 'U','f', 'a', 'l', 's', 'F', 'A', 'L', 'S']

    if(text1):
        count1 = sum(text1.count(char) for char in list)
       
        
        count2 = sum(text2.count(char) for char in list)

        if(count1==3 and count2==4 or count1==4 and count2==3 ):  #if one says true and other says false then priority given to 2nd
            print("true and false collision so given priority to text2 which is the incoming text")
            return 2

        if(count1>count2):
            print("text1 i.e the prev text is the winner")
            return 1
        else:
            print("text2 i.e the incoming text is the winner")
            return 2
    else:
        print("text1 not there so text2 is the winner")
        return 2

def count_true_false(d): #in a dictionary to check how many T/F are there.
    true_count = sum(1 for v in d.values() if v is True)
    false_count = sum(1 for v in d.values() if v is False)
    return true_count, false_count

def merge_dicts(dict1, dict2): 
    true_count1, false_count1 = count_true_false(dict1)
    true_count2, false_count2 = count_true_false(dict2)
    
    if (true_count1 + false_count1) >= (true_count2 + false_count2):
        final_dict = dict1.copy()
        y_dirn_gap=False
    else:
        final_dict = dict2.copy()
        y_dirn_gap=True

    return final_dict,y_dirn_gap


def assign_true_false_or_unknown(true_list, false_list, question_dict,total_questions):
    # Initialize the final dictionary
    final_dict = {str(i): 'UNASSIGNED' for i in range(1, total_questions+1)}
    unassigned_keys=[]
    assigned_keys=[]
    
    # Iterate over each question and its y-coordinate
    for question, y in question_dict.items():
        # compute diff with true list such that we sub t/f box from s/n box
        # true_differences= [y - ty for ty in true_list]
        # Compute absolute differences with true list
        true_abs_differences = [abs(y - ty) for ty in true_list]
        # Compute absolute differences with false list
        # false_differences= [y - ty for ty in false_list]
        false_abs_differences = [abs(y - fy) for fy in false_list]


        # Find the minimum differences
  
        # min_true_diff = min((diff for diff in true_differences if diff > 0), default=float('inf'))
        # min_false_diff = min((diff for diff in false_differences if diff > 0), default=float('inf'))

        
        min_true_abs_diff=min(true_abs_differences) if true_abs_differences else float('inf')
        min_false_abs_diff=min(false_abs_differences) if false_abs_differences else float('inf')

        # Determine the smallest difference
        # min_diff = min(min_true_diff, min_false_diff)
        min_abs_diff=min(min_true_abs_diff,min_false_abs_diff)


        # Assign the value based on the smallest difference
        # if min_diff < 360:
        #     if min_true_diff < min_false_diff:
        #         final_dict[question] = True
        #         true_list.pop(true_differences.index(min_true_diff))
        #     else:
        #         final_dict[question] = False
        #         false_list.pop(false_differences.index(min_false_diff))
        # else:
            # checking the abs diff option if nothing can find in positive diff option
        if min_abs_diff < 300:
            if min_true_abs_diff < min_false_abs_diff:
                final_dict[question] = True
                true_list.pop(true_abs_differences.index(min_true_abs_diff))
            else:
                final_dict[question] = False
                false_list.pop(false_abs_differences.index(min_false_abs_diff))
            
        else:
            final_dict[question] = 'NULL'
   

    
    
   

                         
    return final_dict


def assign_true_false_or_unknown_rotated(true_list,false_list,true_list_x,false_list_x,question_dict,question_dict_x,total_questions):
    final_dict = {str(i): 'UNASSIGNED' for i in range(1, total_questions+1)}
    unassigned_keys=[]
    assigned_keys=[]
    final_dict_y={str(i): 'UNASSIGNED' for i in range(1, total_questions+1)}
    final_dict_x={str(i): 'UNASSIGNED' for i in range(1, total_questions+1)}

    # Iterate over each question and its y-coordinate
    for question, y in question_dict.items():
        # Compute absolute differences with true list
        true_differences= [y - ty for ty in true_list]
        true_abs_differences = [abs(y - ty) for ty in true_list]
        # Compute absolute differences with false list
        false_differences= [y - fy for fy in false_list]
        false_abs_differences = [abs(y - fy) for fy in false_list]


        # Find the minimum differences
  
        min_true_diff = min((diff for diff in true_differences if diff > 0), default=float('inf'))
        min_false_diff = min((diff for diff in false_differences if diff > 0), default=float('inf'))

        
        min_true_abs_diff=min(true_abs_differences) if true_abs_differences else float('inf')
        min_false_abs_diff=min(false_abs_differences) if false_abs_differences else float('inf')

        # Determine the smallest difference
        min_diff = min(min_true_diff, min_false_diff)
        min_abs_diff=min(min_true_abs_diff,min_false_abs_diff)

        # print("the question number is :",question)
        # print("the min dist is :",min_diff)
        # print("the min abs_diff is :",min_abs_diff)
        # print("the false abs diff",false_abs_differences)
        


        # Assign the value based on the smallest difference first going with abs diff as for upside down it will favour abs
        if min_abs_diff < 310:
            if min_true_abs_diff < min_false_abs_diff:
                final_dict_y[question] = True
                true_list.pop(true_abs_differences.index(min_true_abs_diff))
            else:
                final_dict_y[question] = False
                false_list.pop(false_abs_differences.index(min_false_abs_diff))
        else:
            # checking the postive diff option if nothing can find in abs diff option
            if min_diff < 310:
                print(question)
                if min_true_diff < min_false_diff:

                    final_dict_y[question] = True
                    true_list.pop(true_differences.index(min_true_diff))
                else:
                    final_dict_y[question] = False
                    false_list.pop(false_differences.index(min_false_diff))
            
            else:
                final_dict_y[question] = 'NULL'
   



    for question,x in question_dict_x.items():
    
        # Compute absolute differences with true list
        true_differences= [x - tx for tx in true_list_x]
        true_abs_differences = [abs(x - tx) for tx in true_list_x]
        # Compute absolute differences with false list
        false_differences= [x - fy for fy in false_list_x]
        false_abs_differences = [abs(x - fy) for fy in false_list_x]


        # Find the minimum differences
  
        min_true_diff = min((diff for diff in true_differences if diff > 0), default=float('inf'))
        min_false_diff = min((diff for diff in false_differences if diff > 0), default=float('inf'))

        
        min_true_abs_diff=min(true_abs_differences) if true_abs_differences else float('inf')
        min_false_abs_diff=min(false_abs_differences) if false_abs_differences else float('inf')

        # Determine the smallest difference
        min_diff = min(min_true_diff, min_false_diff)
        min_abs_diff=min(min_true_abs_diff,min_false_abs_diff)

        if min_diff < 310:
            if min_true_diff < min_false_diff:
                final_dict_x[question] = True
                true_list_x.pop(true_differences.index(min_true_diff))
            else:
                final_dict_x[question] = False
                false_list_x.pop(false_differences.index(min_false_diff))
        else:
            # checking the abs diff option if nothing can find in positive diff option
            if min_abs_diff < 310:
                if min_true_abs_diff < min_false_abs_diff:
                    final_dict_x[question] = True
                    true_list_x.pop(true_abs_differences.index(min_true_abs_diff))
                else:
                    final_dict_x[question] = False
                    false_list_x.pop(false_abs_differences.index(min_false_abs_diff))
            
            else:
                final_dict_x[question] = 'NULL'
    
    
    print("the final dict for y is: ")
    print(final_dict_y)
    print("the final dict for x is: ")
    print(final_dict_x)
    final_dict,y_dirn_gap=merge_dicts(final_dict_x,final_dict_y)

   
    if 'L' in final_dict:
        final_dict['7']=final_dict['L']
        del final_dict['L']
        
    if 'I' in final_dict:
        final_dict['1']=final_dict['I']
        del final_dict['I']
    
    if y_dirn_gap and '6' in final_dict and '9' in final_dict: #means image is inverted and 6 and 9 true and false value needs to swapped out
        temp=final_dict['6']
        final_dict['6']=final_dict['9']
        final_dict['9']=temp

    
    return final_dict

def process_using_paddleocr(image_path,output_folder,output_folder1,total_questions):
    
    ocr = PaddleOCR(lang='en')
    base_name = os.path.basename(image_path)
    image_cv = cv2.imread(image_path)
    print("!------------------------------start with paddleocr-----------------------------------!")
    print("Started processing of the image :",base_name)
    
    output = ocr.ocr(image_path)[0]


    
    texts = [line[1][0] for line in output]
   
 
    

    
    print("OCR detection done")

    boxes = [line[0] for line in output]
    # probabilities = [line[1][1] for line in output]



    image_boxes = image_cv.copy()



    # print("!------------------------------all coordinates-----------------------------------!")

    for box,text in zip(boxes,texts):
      cv2.rectangle(image_boxes,(int(box[0][0]),int(box[0][1])),(int(box[2][0]),int(box[2][1])),(0,0,255),5)  #needs top left and bottom right to draw bounding box
      cv2.putText(image_boxes,text,(int(box[0][0]),int(box[0][1])),cv2.FONT_HERSHEY_SIMPLEX,4,(222,0,0),3)
    
    




    alldet_file_name = f'detect_{base_name}'
    alldet_file_path = os.path.join(output_folder1, alldet_file_name)
    
    # Save the processed image
    cv2.imwrite(alldet_file_path, image_boxes)
  


    for box, text in zip(boxes, texts):
      if text=="SN" or text=="NS":
        num_l_x1=box[0][0]
        num_r_x1=box[2][0]+140
        num_l_y1=box[0][1]
        num_r_y1=box[2][1]+140
        print("left top x of SN:",num_l_x1)
        print("bottom right x of SN:",num_r_x1)
        print("left top y of SN:",num_l_y1)
        print("bottom right y of SN:",num_r_y1)




    cons_boxes_image=image_cv.copy()
    true_list=[]
    false_list=[]

    true_list_x=[]
    false_list_x=[]


    numbers_dict={}
    numbers_dict_x={}
    c=0
    prev_x=0
    prev_y=0


    # this is for s/n column
    try:
        for box, text in zip(boxes, texts):
            # print(f"the text is : {text}")

            
            box_top_left_x = int(box[0][0])
            box_top_left_y=int(box[0][1])
            box_bottom_right_x = int(box[2][0])
            box_bottom_right_y = int(box[2][1])
            box_width_x = box_bottom_right_x - box_top_left_x
            box_width_y = box_bottom_right_y - box_top_left_y
            if (num_l_x1 <= box_bottom_right_x <= num_r_x1 or num_l_y1<= box_bottom_right_y<=num_r_y1) and box_width_x <= 200 and box_width_y <= 200 and text!="SN" and text!="NS":
                # print("entered in the S/N column ")
                # print(text)
                # print(box)
                numbers_dict[text] = int(box[0][1])
                numbers_dict_x[text]=int(box[0][0])
            
                cv2.rectangle(cons_boxes_image, (int(box[0][0]), int(box[0][1])), (int(box[2][0]), int(box[2][1])), (0, 0, 255), 5)
                cv2.putText(cons_boxes_image, text, (int(box[0][0]), int(box[0][1])), cv2.FONT_HERSHEY_SIMPLEX, 4, (222, 0, 0), 1)





        
        
        
   
                       


    #error in detection of S/N column   
    except NameError:
        print("cant detect s/n column also so going with all detection using box width")
        c=0
        for box,text in zip(boxes,texts):
            box_top_left_x = int(box[0][0])
            box_top_left_y=int(box[0][1])
            box_bottom_right_x = int(box[2][0])
            box_bottom_right_y = int(box[2][1])
            box_width_x = box_bottom_right_x - box_top_left_x
            box_width_y = box_bottom_right_y - box_top_left_y
            
            
            if (box_width_x <= 80 and box_width_y <= 80):
                if text.isdigit():
                    number = int(text)
                    if 1 <= number <= total_questions+1:
                        # Store in dictionaries only if the number is between 1 and 10
                        numbers_dict[text] = int(box[0][1])
                        numbers_dict_x[text] = int(box[0][0])

                        # Visualize the rectangle and text on the image (optional)
                        cv2.rectangle(cons_boxes_image, (int(box[0][0]), int(box[0][1])), (int(box[1][0]), int(box[1][1])), (0, 0, 255), 5)
                        cv2.putText(cons_boxes_image, text, (int(box[0][0]), int(box[0][1])), cv2.FONT_HERSHEY_SIMPLEX, 4, (222, 0, 0), 1)

            if((box_width_x<=300 and box_width_y<=300) and ' ' not in text and label_text(text)==True):
                if(c==0):
                        print("first t/f detection")
                        print(text)
                        print(box)
                        prev_y=box[0][1]
                        prev_x=box[0][0]
                        true_list.append(int(box[0][1]))
                        true_list_x.append(int(box[0][0]))
                            
                else:
                            
                    if((abs(box[0][0]-prev_x)>160) or  abs(box[0][1]-prev_y)>160):
                        print(text)
                        print(box)
                        true_list.append(int(box[0][1]))
                        true_list_x.append(int(box[0][0]))
                        prev_y=box[0][1]
                        prev_x=box[0][0]
                        
                    c+=1

                cv2.rectangle(cons_boxes_image,(int(box[0][0]),int(box[0][1])),(int(box[2][0]),int(box[2][1])),(0,0,255),5)  
                cv2.putText(cons_boxes_image,text,(int(box[0][0]),int(box[0][1])),cv2.FONT_HERSHEY_SIMPLEX,4,(222,0,0),1)
                
            if((box_width_x<=300 and box_width_y<=300) and ' ' not in text and label_text(text)==False):
                if(c==0):
                        print("first t/f detection")
                        print(text)
                        print(box)
                        prev_y=box[0][1]
                        prev_x=box[0][0]

                        false_list.append(int(box[0][1]))
                        false_list_x.append(int(box[0][0]))
                else:
                            
                    if((abs(box[0][0]-prev_x)>160) or  abs(box[0][1]-prev_y)>160):
                        print(text)
                        print(box)
                        false_list.append(int(box[0][1]))
                        false_list_x.append(int(box[0][0]))
                        prev_y=box[0][1]
                        prev_x=box[0][0]
                    
                    c+=1
                
                cv2.rectangle(cons_boxes_image,(int(box[0][0]),int(box[0][1])),(int(box[2][0]),int(box[2][1])),(0,0,255),5)  
                cv2.putText(cons_boxes_image,text,(int(box[0][0]),int(box[0][1])),cv2.FONT_HERSHEY_SIMPLEX,4,(222,0,0),1)
        
        print("the number dict is: ",numbers_dict)
        print("the number dict x is: ",numbers_dict_x)
        print("the true list is ",true_list)
        print("the false list is ",false_list)
        print("the true list for xdirn",true_list_x)
        print("the false list for xdirn",false_list_x)

        final_dict=assign_true_false_or_unknown_rotated(true_list,false_list,true_list_x,false_list_x,numbers_dict,numbers_dict_x,total_questions)
            # Create a unique output file name
        output_file_name = f'final_tf_{base_name}'
        output_file_path = os.path.join(output_folder, output_file_name)

        # Save the processed image
        cv2.imwrite(output_file_path, cons_boxes_image)




    return final_dict

                  



def rotate(
        image: np.ndarray, angle: float, background: Union[int, Tuple[int, int, int]]
) -> np.ndarray:
    old_width, old_height = image.shape[:2]
    angle_radian = math.radians(angle)
    width = abs(np.sin(angle_radian) * old_height) + abs(np.cos(angle_radian) * old_width)
    height = abs(np.sin(angle_radian) * old_width) + abs(np.cos(angle_radian) * old_height)

    image_center = tuple(np.array(image.shape[1::-1]) / 2)
    rot_mat = cv2.getRotationMatrix2D(image_center, angle, 1.0)
    rot_mat[1, 2] += (width - old_width) / 2
    rot_mat[0, 2] += (height - old_height) / 2
    return cv2.warpAffine(image, rot_mat, (int(round(height)), int(round(width))), borderValue=background)

def process_using_doctr_less_row_gap(boxes,texts,numbers_dict,num_l_x2,num_r_x2,image_path,total_questions):
    print("the number dict in low gap",numbers_dict)
    cons_boxes_image = cv2.imread(image_path)
    true_list=[]
    false_list=[]
    c=0
    print("starting with low row gap")

    try:
        for box, text in zip(boxes, texts):
            box_bottom_right_x = int(box[1][0])
                
            
                
    
            # Draw the adjusted bounding box
            if (num_l_x2 <=  box_bottom_right_x <= num_r_x2):
                    # print("entered in the t/f column ")
                
                if label_text(text)==True and text!='TRUE/FALSE':
                    if(c==0):
                        print("first t/f detection")
                        print(text)
                        print(box)
                        prev=box[0][1]
                        prev_text=text
                        true_list.append(int(box[0][1]))
                    else:
                    
                        if(abs(box[0][1]-prev)>20):  #to avoid boxes in same row to overlap 
                            print(text)
                            print(box)
                            true_list.append(int(box[0][1]))
                            prev=box[0][1]
                            prev_text=text
                        else:
                            print(f"collision happend with box:{prev} and text:{prev_text} solving on the basis of percent match boxes")
                            print("the current box specification are")
                            print(text)
                            print(box)
                            ans=percentMatch(prev_text,text)
                            if(ans==2):

                                if(label_text(prev_text)==False):
                                    false_list.pop()
                            
                                elif(label_text(prev_text)==True):
                                    true_list.pop()
                            
                            
                                prev=box[0][1]
                                prev_text=text
                                true_list.append(int(prev))
                            
                            
                                    

                    c+=1
                    
                elif label_text(text)==False and text!='TRUE/FALSE':
                    if(c==0):
                        print("first t/f detection")
                        print(text)
                        print(box)
                        prev=box[0][1]
                        prev_text=text
                        false_list.append(int(box[0][1]))
                    else:
                        if(abs(box[0][1]-prev)>20):
                            print(text)
                            print(box)
                            false_list.append(int(box[0][1]))
                            prev=box[0][1]
                            prev_text=text
                        else:
                            print(f"collision happend with box:{prev} and text:{prev_text} solving on the basis of percent match boxes")
                            print("the current box specification are")
                            print(text)
                            print(box)
                            ans=percentMatch(prev_text,text)

                            if(ans==2):

                                if(label_text(prev_text)==False):
                                    false_list.pop()
                            
                                elif(label_text(prev_text)==True):
                                    true_list.pop()
                                
                                
                                prev=box[0][1]
                                prev_text=text
                                false_list.append(int(prev))
                    c+=1

                cv2.rectangle(cons_boxes_image,(int(box[0][0]),int(box[0][1])),(int(box[1][0]),int(box[1][1])),(0,0,255),5)  
                cv2.putText(cons_boxes_image,text,(int(box[0][0]),int(box[0][1])),cv2.FONT_HERSHEY_SIMPLEX,1,(222,0,0),1)
        
        
    

        final_dict=assign_true_false_or_unknown(true_list,false_list,numbers_dict,total_questions)
        
        return cons_boxes_image,final_dict
    except Exception as e:
        print("error occured")
        print(e)


def process_and_save_image(image_path,actual_ans_csv ,output_folder , output_folder1):

    base_name = os.path.basename(image_path)
    image_cv = cv2.imread(image_path)
    height = image_cv.shape[0]
    width = image_cv.shape[1]
    print("!------------------------------starting detection using doctr-----------------------------------!")
    print("Started processing of the image :",base_name)
    # print(image_width)
    # output = ocr.ocr(image_path)[0]

    # checking if header is there
    with open(actual_ans_csv, 'r') as file:
        first_line = file.readline().strip()

    
    # Check if the first column of the first line is numeric
    first_column_numeric = False
    try:
        first_value = float(first_line.split(',')[0])  # Assuming comma-separated values
        first_column_numeric = True
    except ValueError:
        pass  # If the first column cannot be converted to a float, it's not numeric

    
    # Read the CSV file based on the condition
    if first_column_numeric:
        actualAns_df = pd.read_csv(actual_ans_csv, header=None)
    else:
        actualAns_df = pd.read_csv(actual_ans_csv)
    
    total_questions = len(actualAns_df)

    #checking skewness
    grayscale = cv2.cvtColor(image_cv, cv2.COLOR_BGR2GRAY)
    angle = determine_skew(grayscale)
    image_cv = rotate(image_cv, angle, (0, 0, 0))
    cv2.imwrite(image_path, image_cv)


    single_img_doc = DocumentFile.from_images(image_path)
    result = model(single_img_doc)



 


    texts=[]
 
    for page in result.pages:
        for block in page.blocks:
            for line in block.lines:
                for word in line.words:
                    text = word.value
                    texts.append(text)
  


   
    #checking for rotation
    r_count=0

    while('TRUE/FALSE' not in texts):
        image_cv = cv2.rotate(image_cv, cv2.ROTATE_90_CLOCKWISE)
        print("rotation started")


        # Save the rotated image to a temporary path
        # temp_image_path = 'temp_rotated_image.jpg'
        cv2.imwrite(image_path, image_cv)

        # output=ocr.ocr(temp_image_path)[0]
        single_img_doc = DocumentFile.from_images(image_path)
        result=model(single_img_doc)
        texts=[]
        for page in result.pages:
            for block in page.blocks:
                for line in block.lines:
                    for word in line.words:
                        text = word.value
                        texts.append(text)

        print(texts)
        r_count+=1
        if r_count==4:  #reaching the same orientation
            break
    


    if(r_count>0 and r_count!=4):
        # cv2.imwrite(image_path,image_cv)
        print("rotation done for: ",base_name)
        print("Number of times rotation done:",r_count)

    height = image_cv.shape[0]
    width = image_cv.shape[1]
    
    print("OCR detection done with doctr")
    boxes=[]
    # boxes = [line[0] for line in output]4
    for page in result.pages:
        for block in page.blocks:
            for line in block.lines:
                for word in line.words:
                   
                    (x_min, y_min), (x_max, y_max) = word.geometry
                    
                    x_min_px = x_min * width
                    y_min_px = y_min * height
                    x_max_px = x_max * width
                    y_max_px = y_max * height
                    
                    bbox=(x_min_px, y_min_px), (x_max_px, y_max_px)

                  
                    boxes.append(bbox)

    image_boxes = image_cv.copy()



    # print("!------------------------------all coordinates-----------------------------------!")

    for box,text in zip(boxes,texts):
    #   print(text)
    #   print(box)
      cv2.rectangle(image_boxes,(int(box[0][0]),int(box[0][1])),(int(box[1][0]),int(box[1][1])),(0,0,255),5)  #needs top left and bottom right to draw bounding box
      cv2.putText(image_boxes,text,(int(box[0][0]),int(box[0][1])),cv2.FONT_HERSHEY_SIMPLEX,4,(222,0,0),3)
    
    
    # print("!------------------------------done with all coordinates-----------------------------------!")



    alldet_file_name = f'detect_{base_name}'
    alldet_file_path = os.path.join(output_folder1, alldet_file_name)
    
    # Save the processed image
    cv2.imwrite(alldet_file_path, image_boxes)
  


    for box, text in zip(boxes, texts):
      if text=="SN" or text=="NS":
        num_l_x1=box[0][0]-100
        num_r_x1=box[1][0]+140
    
        print("left top x of SN:",num_l_x1)
        print("bottom right x of SN:",num_r_x1)
       

      if text=="TRUE/FALSE":
        num_l_x2=box[0][0]-10
        num_r_x2=box[1][0]+200
       
      
        print("left top x of T/F:",num_l_x2)
        print("bottom right x of T/F:",num_r_x2)




    


    # Draw OCR bounding boxes within the final rectangle
    cons_boxes_image=image_cv.copy()
    true_list=[]
    false_list=[]



    numbers_dict={}
    numbers_dict_x={}
    c=0
   

    no_of_collisions=0
    
    try:

        # this is for s/n column
        for box, text in zip(boxes, texts):
            # print(f"the text is : {text}")

        
            box_top_left_x = int(box[0][0])
            box_top_left_y=int(box[0][1])
            box_bottom_right_x = int(box[1][0])
            box_bottom_right_y = int(box[1][1])
     

        
            # print(box_bottom_right_x)
            # print(box_bottom_right_y)
            # print(box_width_x)
            # print(box_width_y)

 
        
            if (num_l_x1 <=  box_bottom_right_x <= num_r_x1 ):
                if text.isdigit():
                    number = int(text)
                    if 1 <= number <= total_questions+1:
                        # Store in dictionaries only if the number is between 1 and 10
                        numbers_dict[text] = int(box[0][1])
                        print(text)
                        print(box)
                        # Visualize the rectangle and text on the image (optional)
                        cv2.rectangle(cons_boxes_image, (int(box[0][0]), int(box[0][1])), (int(box[1][0]), int(box[1][1])), (0, 0, 255), 5)
                        cv2.putText(cons_boxes_image, text, (int(box[0][0]), int(box[0][1])), cv2.FONT_HERSHEY_SIMPLEX, 1, (222, 0, 0), 1)


  



    
    
     
        
        prev=0

    
    
        for box, text in zip(boxes, texts):

            
        
            box_bottom_right_x = int(box[1][0])
    
            if(no_of_collisions>4):
                break
            
        # Draw the adjusted bounding box
            if (num_l_x2 <=  box_bottom_right_x <= num_r_x2):
                # print("entered in the t/f column ")
            
                if label_text(text)==True and text!='TRUE/FALSE':
                    if(c==0):
                        print("first t/f detection")
                        print(text)
                        print(box)
                        prev=box[0][1]
                        prev_text=text
                        true_list.append(int(box[0][1]))
                    else:
                    
                        if(abs(box[0][1]-prev)>200):  #to avoid boxes in same row to overlap 
                            print(text)
                            print(box)
                            true_list.append(int(box[0][1]))
                            prev=box[0][1]
                            prev_text=text
                        else:
                            print(f"collision happend with box:{prev} and text:{prev_text} solving on the basis of percent match boxes")
                            print("the current box specification are")
                            print(text)
                            print(box)
                            no_of_collisions+=1
                            ans=percentMatch(prev_text,text)
                            if(ans==2):

                                if(label_text(prev_text)==False):
                                    false_list.pop()
                            
                                elif(label_text(prev_text)==True):
                                    true_list.pop()
                            
                            
                                prev=box[0][1]
                                prev_text=text
                                true_list.append(int(prev))
                            
                            
                                

                    c+=1
                
                elif label_text(text)==False and text!='TRUE/FALSE':
                    if(c==0):
                        print("first t/f detection")
                        print(text)
                        print(box)
                        prev=box[0][1]
                        prev_text=text
                        false_list.append(int(box[0][1]))
                    else:
                        if(abs(box[0][1]-prev)>200):
                            print(text)
                            print(box)
                            false_list.append(int(box[0][1]))
                            prev=box[0][1]
                            prev_text=text
                        else:
                            print(f"collision happend with box:{prev} and text:{prev_text} solving on the basis of percent match boxes")
                            print("the current box specification are")
                            print(text)
                            print(box)
                            no_of_collisions+=1
                            ans=percentMatch(prev_text,text)

                            if(ans==2):

                                if(label_text(prev_text)==False):
                                    false_list.pop()
                            
                                elif(label_text(prev_text)==True):
                                    true_list.pop()
                            
                            
                                prev=box[0][1]
                                prev_text=text
                                false_list.append(int(prev))
                    c+=1

                cv2.rectangle(cons_boxes_image,(int(box[0][0]),int(box[0][1])),(int(box[1][0]),int(box[1][1])),(0,0,255),5)  
                cv2.putText(cons_boxes_image,text,(int(box[0][0]),int(box[0][1])),cv2.FONT_HERSHEY_SIMPLEX,1,(222,0,0),1)
    
            
        if(no_of_collisions<=4):
            final_dict=assign_true_false_or_unknown(true_list,false_list,numbers_dict,total_questions)
        
        else:
            print("going with doctr less gap")
            cons_boxes_image,final_dict=process_using_doctr_less_row_gap(boxes,texts,numbers_dict,num_l_x2,num_r_x2,image_path,total_questions)
            
        
    
        # Create a unique output file name
        output_file_name = f'final_tf_{base_name}'
        output_file_path = os.path.join(output_folder, output_file_name)
    
        # Save the processed image
        cv2.imwrite(output_file_path, cons_boxes_image)


        print("printing the number dict y_coordinate")
        print(numbers_dict)
     



    
    except NameError:

        print("TRUE/FALSE not detected. Skipping this part of processing.")
        print("going with paddleocr")

        final_dict=process_using_paddleocr(image_path,output_folder,output_folder1,total_questions)

                


    
        

   



    
    print("--------- Printing the final dict ------------")
    print(final_dict)

    df=pd.DataFrame(final_dict.items(),columns=['Q_No.','True/False'])

    
    # predcsv_file_name = f'answers_{base_name}.csv'

    # predcsv_file_path = os.path.join(output_folder, predcsv_file_name)
    # df.to_csv(predcsv_file_path,index=False)
    

    # print(f'DataFrame saved to {predcsv_file_path}')
   


        
        
    



    # predictions_file_path='pred_output.csv'
    # reading the answers and evaluting 
    
    
    marks=0
    w_ans=[]
    m_ans=[]

    for index, row in actualAns_df.iterrows():
        question_number = str(row.iloc[0])  # Accessing the first column by index
        answer = row.iloc[1]  # Accessing the second column by index
        # print(answer)
        if final_dict[question_number]==answer:
            marks += 1
        elif final_dict[question_number] not in ("NULL", "UNASSIGNED"):
            w_ans.append(question_number)
        else:
            m_ans.append(question_number)
            

    print("Total Marks:", marks)

    image_name = base_name #Replace this with the actual image name
    marks_df = pd.DataFrame({"Filename": [image_name], "Marks": [marks]})

    # Append the marks DataFrame to the predictions file
    # marks_df.to_csv(predictions_file_path, mode='a', header=False, index=False)
    output_text = f"Marks: {marks} out of {total_questions}"

    if w_ans:
        output_text += f" and the following were wrong_answers: {w_ans}"

    if m_ans and w_ans:
        output_text += f" and missed_questions: {m_ans}"
    
    if m_ans and len(w_ans)==0:
        output_text += f" and the following were missed_answers: {m_ans}"
    
    print(output_text)

    return output_text



import gradio as gr


output_folder = "test_gradio/output"
output_folder1 = "test_gradio/detection"

# actual_ans_csv = "test_gradio/ModelAnswer.csv"

demo_image_paths = [
    "test_gradio/samples/1zHXQVK.jpg",
    "test_gradio/samples/9X9qVWN.jpg",
    "test_gradio/samples/LRccyJJ.jpg"


]

demo_csv_path = "test_gradio/answerKey.csv"

# Define the Gradio interface
demo = gr.Interface(
    fn=lambda img_path, csv_path: process_and_save_image(img_path, csv_path, output_folder, output_folder1),
    inputs=[gr.Image(type='filepath',label="Upload Image of your answer_sheet"),
             gr.File(type='filepath',label="Upload the Answer Key in csv file")],
    outputs=[gr.Textbox(label=f"Predicted Marks")],
    title="AutoEval for True/False AnswerSheet",
    examples=[
        [demo_image_paths[0], demo_csv_path],
        [demo_image_paths[1], demo_csv_path],
        [demo_image_paths[2], demo_csv_path]
    ]
)   

# Launch the Gradio app
demo.launch()