import

import os
import csv

path = "/media/ltphen/Ulife/LTPhen von Ulife/tools/dataset/emails"
emailsContent = []

def read_file(path):
    f = open(path, "r", encoding = "ISO-8859-1")
    return f.read()

def write_in_csv(content):
    with open("result.csv", "w+") as out:
        csv_file = csv.writer(out)
        csv_file.writerow(["content", "spam"])
        for item in content:
            csv_file.writerow(item)

for i in range(1,7):
    for label in ["ham", "spam"]:
        pathName = path+"/"+"enron"+str(i)+"/"+label
        for _, _, files in os.walk(pathName):
            for file in files:
                filePath = os.path.join(pathName, file)
                content = read_file(filePath)
                emailsContent.append((content.replace("Subject:", "").replace("\n", ""), label == "spam"))
                write_in_csv(emailsContent)