preparemoodle.py

#!/usr/bin/env python

import csv
import os
import shutil  # copyfile, make_archive
import argparse, sys


def find_file(pattern, path):
  if os.name == "posix":
    import subprocess

    result = [line[2:] for line in subprocess.check_output(
        "find " + path + " -type f -name " + pattern, 
        shell=True).splitlines()]
    result = [tmp.decode("utf-8") for tmp in result]

  else: 
    import fnmatch

    result = []
    for root, _, files in os.walk(path):
      for name in files:
        if fnmatch.fnmatch(name, pattern):
          result.append(os.path.join(root, name))

  return result

if __name__ == '__main__':

  parser = argparse.ArgumentParser(description='''
  prepares batch upload to Moodle via assignment module. 
  PDFs in folder 'in' are moved to folder 'tmp' with a certain folder structure and finally zipped to 'out'. 
  Attention: zip-archive 'out' will be overwritten in the following!

  ''')
  parser.add_argument("-i", "--infolder", default="./pdfs/encrypted", 
    help="Input folder with PDFs. Default: ./pdfs/encrypted")
  parser.add_argument("-c", "--csv", default="./Bewertungen.csv",
    help="Moodle grading CSV file, needed to construct the folder names. Default: ./Bewertungen.csv")
  parser.add_argument("-o", "--outzip", default="./moodle_feedbacks.zip",
    help="Output zip archive. Default: ./moodle_feedbacks.zip")
  parser.add_argument("-d", "--dry", action='store_true', 
    help="Flag for dry run, displays only the folder structure inside the archive moodle_feedbacks.zip")
  parser.add_argument("-t", "--tmp", default="./tmp",
    help="temporary folder Default: ./tmp")
  parser.add_argument("--nowarn", action='store_true', 
    help="Disables warnings")

  args = parser.parse_args()
  infolder = args.infolder
  csvfilename = args.csv
  outzip = args.outzip
  tmpfolder = args.tmp
  dry = args.dry
  nowarn = args.nowarn

  numlines = 0
  with open(csvfilename, newline='') as csvfile:
    numlines = sum(1 for line in csvfile)

  print('''Preparing for moodle upload
  Processing {} lines
  '''.format(numlines))

  if dry:
    print("Dry run\n")
    dryoutput=""
  else:
    for root, dirs, files in os.walk(tmpfolder):
      for f in files:
          os.unlink(os.path.join(root, f))
      for d in dirs:
          shutil.rmtree(os.path.join(root, d))

    if os.path.exists(outzip): os.remove(outzip)


  with open(csvfilename, newline='') as csvfile:
    
    # Loop over all lines in CSV file
    numfoundpdfs = 0
    cnt = 0
    print("Start iterating...", sep='', end='', flush=True)

    reader = csv.reader(csvfile, delimiter=',', quotechar='"')
    next(reader)  # skip first row in CSV file since this should be the header
    for row in reader:
      # parse the required fields from the csv file
      id = row[0]
      id = id.replace("Teilnehmer/in", "")
      name = row[1]
      matnum = row[2]

      # if a pdf file for current student exists, create a directory and copy
      # the pdf file to it. The resulting directories can be uploaded to moodle
      longpdffile = ''
      paths = find_file(matnum + "*.pdf", infolder)

      if len(paths) > 0:
        longpdffile = paths[0]
      if len(paths) > 1:  # TODO: implement second loop for enabling distribution of multiple files
        raise Exception("More than one PDFs starting with matnum {} found!".format(matnum)) 
      
      
      if os.path.isfile(longpdffile):
        numfoundpdfs += 1
        pdffile = os.path.basename(longpdffile)
        folder = "{}_{}_assignsubmission_file_".format(name, id)
        longfolder = os.path.join(tmpfolder, folder)

        if not dry:
          os.mkdir(longfolder)
          shutil.copyfile(longpdffile, os.path.join(longfolder, pdffile))
        else:
          dryoutput += "\n{}".format(os.path.join(folder, pdffile))
      else:
          if not nowarn:
            print("Warning: PDF corresponding to matriculation number {} (id={}, name={}) not available.".format(
              matnum, id, name
            ))
      
      # Progress
      if not (cnt % round(numlines/10)): 
        print(".", sep=' ', end='', flush=True)
      cnt += 1
      
  print("done.\n")

  print("Found {} PDFs (CSV had {} entries)\n".format(numfoundpdfs, numlines))

  print("Searching for matriculation numbers not present in CSV but in PDF input folder:")

  # Check for PDFs which are not reflected in CSV (student not registered in Moodle)
  numnotfoundmatnums = 0
  notfoundmatnums = ""

  for root, dirs, files in os.walk(infolder):
      for pdffile in files:
          if pdffile.endswith(".pdf"):
            # Get matriculation number from file
            matnum = pdffile[0:6]
            
            # Search in CSV
            with open(csvfilename, 'r') as csvfile:
              notfound = True
              for line in csvfile:
                  if matnum in line:
                    notfound = False

            if notfound:
              numnotfoundmatnums += 1
              notfoundmatnums += matnum + ", "
              if not nowarn:
                print("Warning: Could not find {} in CSV".format(matnum))

  if numnotfoundmatnums > 0:
    print('''I could not find the following {} matriculation numbers in CSV:
      {}'''.format(numnotfoundmatnums, notfoundmatnums))

  print("Done.")

  # Zipping
  if not dry:
    print("Zipping")

    shutil.make_archive(os.path.splitext(outzip)[0], 'zip', tmpfolder)

  else:
    print("\nResults from dry ryn:\n{}".format(dryoutput))


  print("\nDone.\n")