reviewer/helpers.py

import csv
import sys
import os
import shutil
import datetime
import tkinter as tk
from tkinter import messagebox
import hashlib
import pickle
import filters.ieeeFilter as IEEE, filters.scopusFilter as Scopus, filters.webScienceFilter as WebOfScience
# titulo, abstract, autores, arquivo&linha, DOI, palavras-chave,palavras-chave extras

FINAL_CSV_HEADERS = ['titulo', 'abstract', 'autores', 'doi', 'keywords','extra_keywords', 'fonte']

def loadFiles (files):
  loadedFiles = []
  for file in files:
    loadedFiles.append((csv.DictReader(open(file['path']), delimiter=file['separator']), file))
  return loadedFiles

def saveAcceptedCSV (data):
  doBackup('accepted.csv')
  file = open('./accepted.csv', mode='w')
  headers = data['header']
  writer = csv.writer(file, delimiter=',')
  writer.writerow(headers)
  data.pop('header')
  for row in data.values():
    writer.writerow(row)
  data['header'] = headers
  file.flush()
  file.close()

def saveRejectedCSV (data):
  doBackup('rejected.csv')
  file = open('./rejected.csv', mode='w')
  headers = data['header']
  writer = csv.writer(file, delimiter=',')
  writer.writerow(headers)
  data.pop('header')
  for row in data.values():
    writer.writerow(row)
  data['header'] = headers
  file.flush()
  file.close()

def writeFinalLog (data):
  file = open("./log.txt", mode='w')
  file.write("accepted: {0}\nrejected: {1}\nduplicated: {2}\n".format(data['accepted'],data['rejected'],data['duplicate']))
  file.flush()
  file.close()

def removeStateFile ():
  try:
    os.remove('./.csvstate')
  except Exception:
    pass

def saveState (data):
  doBackup(".csvstate")
  file = open('./.csvstate', mode='wb')
  pickle.dump(data, file)
  file.close()

def doBackup (fileName):
  filePath = './bak/{0}'.format(fileName)
  shutil.copy('./{0}'.format(fileName), "{0}.{1}.bak".format(filePath, datetime.datetime.now()))

def loadState (root):
  try:
    file = open('./.csvstate', mode='rb')
    answer = tk.messagebox.askyesno("State lading","Load last session state?")
    if answer:
      data = pickle.load(file)
      file.close()
      return data
  except Exception:
    pass
  return {'file_index':0, 'row_index':0, 'accepted':0, 'rejected':0, 'duplicate': 0}

def loadConfigFile ():
  files = list()
  try:
    file = open('./csvconfig.txt')
    rawData = file.read()
    lines = rawData.split('\n')
    for line in lines:
      parameters = line.split(':')
      separator = parameters[2].encode('utf-8').decode("unicode_escape")
      fileConfig = {'path': parameters[0], 'filter': parameters[1], 'separator': separator}
      files.append(fileConfig)
    file.close()
    return files
  except FileNotFoundError:
    return list()

def getFilter (file):
  if file['filter'] == 'ieee':
    return IEEE.IEEEFilter()
  elif file['filter'] == 'scopus':
    return Scopus.ScopusFilter()
  elif file['filter'] == 'webscience':
    return WebOfScience.WebScience()
  else:
    raise Exception('Undefined filter '+file['filter'])

def restoreAcceptedCSV ():
  try:
    file = open('./accepted.csv')
    rows = list(csv.reader(file))
    data = {}
    if len(rows) == 0:
      return data
    data['header'] = rows[0]
    for i in range(1,len(rows)):
      digest = hashlib.sha256(str.encode(rows[i][0])).hexdigest()
      data[digest] = rows[i]
    return data
  except FileNotFoundError:
    return {}

def restoreRejectedCSV ():
  try:
    file = open('./rejected.csv')
    rows = list(csv.reader(file))
    data = {}
    if len(rows) == 0:
      return data
    data['header'] = rows[0]
    for i in range(1,len(rows)):
      digest = hashlib.sha256(str.encode(rows[i][0])).hexdigest()
      data[digest] = rows[i]
    return data
  except FileNotFoundError:
    return {}