# coding: utf-8

# In[ ]:

import os

import os.path, time

import errno

import pandas as pd

import numpy as np

import re

from shutil import *

from PIL import Image

data = pd.read_csv('/Users/mayankajha/Documents/Dispute Soft/mayanka.jha/data.csv')

COLUMN_NAMES=['Repository Path','Copy Path','Corrected File Path','File Size','Date of File Creation','Line / Pixel Count']

result = pd.DataFrame(index = range(0,len(data)), columns=COLUMN_NAMES) //creating an empty dataframe called result to store the required columns

os.chdir('/Users/mayankajha/Documents/Dispute Soft/mayanka.jha/') //changing the working directory

#To extract the file from repository answering Programming Task 1.1

for index, row in data.iterrows():

directory = os.path.dirname(row["copy path"])

if not os.path.exists(directory):

os.makedirs(directory)

copy2(row["repository path"], row["copy path"])

#To check the extension label and store the corrected ones in a different column: Programming Task 1.1

for i in range(0,len(data)):

file_path = data.iloc[i][1]

#print(file_path)

result.iloc[i][0]= file_path

result.iloc[i][1]= data.iloc[i][1]

filename, file_extension = splitext(file_path)

try:

file_object = open(file_path)

file_object.read()

#x = file_object.read()

#print(file_object.tell())

#print(time.ctime(os.path.getctime(file_path))

#print("This is a text file")

if(file_extension!= 'txt'):

new_filename = filename+'.txt'

result.iloc[i][2] = new_filename

else:

result.iloc[i][2] = file_path

#for i in range(0,len(data)):

#file_path1 = data.iloc[i][1]

#file_object1 = open(file_path1)

#y = file_object1.read()

#if(file_path1!=file_path):

#if (x==y):

#print("Duplicate detected"+file_path1)

result.iloc[i][3]=file_object.tell() #file size: Programming Task 1.3

result.iloc[i][4] = time.ctime(os.path.getctime(file_path)) #create Date: Programming Task 1.4

result.iloc[i][5] = sum(1 for line in open(file_path)) #no of line in text file: Programming Task 1.5

except UnicodeDecodeError:

#print ("Failed to open file")

if(file_extension!= 'jpg'):

#print('error')

new_filename = filename+'.jpg'

result.iloc[i][3] = new_filename

else:

result.iloc[i][2] = file_path

result.iloc[i][3]=os.path.getsize(file_path) # file size: Programming Task 1.3

result.iloc[i][4] = time.ctime(os.path.getctime(file_path)) #create Date: Programming Task 1.4

result.iloc[i][5]= Image.open(file_path).size #Pixel count: // create Date: Programming Task 1.5

result.to_csv('Results.csv', encoding='utf-8', index=False)