#!/usr/bin/env python

"""Rename scanned PDFs assuming scan order equal to alphabetical order of
students in Moodle grading sheet.

Renames scans accordingly to info in Moodle grading sheet, such that the
file name starts with the matriculation number. This only works if exams were
scanned in alphabetical order.
Optionally, each scanned PDF is searched for barcodes/QRs containing the
matriculation number to double check.

Attention: Contents in output folder will be overwritten in the following!
"""

__author__ = "Amrita Deb (deb@itc.rwth-aachen.de), " +\
    "Christian Rohlfing (rohlfing@ient.rwth-aachen.de)"


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

import utils.moodle as moodle
import utils.matnum as matnum_utils
import utils.qr as qr_utils


def _make_parser():
    csv_parser = moodle.get_moodle_csv_parser()
    parser = argparse.ArgumentParser(
        parents=[csv_parser],
        description=__doc__,
        formatter_class=argparse.ArgumentDefaultsHelpFormatter)

    parser.add_argument(
        "infolder", help="Input folder with PDFs.")
    parser.add_argument(
        "csv", help="Moodle grading sheet.")
    parser.add_argument(
        "outfolder", help="Output folder with renamed scans.")

    parser.add_argument(
        "--filenameformat", default="{matnum}_{fullname[0]}",
        help="File name format. Available keywords: " +
        "{matnum}, {fullname}, {lastname}, {firstname}. " +
        "Default: '{matnum}_{fullname[0]}'")
    parser.add_argument(
        "-q", "--checkqr", action='store_true',
        help="Flag for additional QR code match.")
    parser.add_argument(
        "-d", "--dry", action='store_true', help="Flag for dry run.")

    return parser


# Create argument parser with default values
_parser = _make_parser()
__doc__ += _parser.format_help()


def main(args):
    """Main routine
    """

    # Parse input arguments
    args = _parser.parse_args(args)
    infolder = args.infolder
    sheet_csv = args.csv
    outfolder = args.outfolder
    file_format = args.filenameformat
    dry = args.dry
    csv_delim = args.csvdelim
    csv_quote = args.csvquote
    csv_enc = args.csvenc
    check_qr = args.checkqr

    # Print status with total number of lines
    starttime = time.time()
    dryout = ""
    if dry:
        print("Dry run")
    print("Preparing renaming of scans")

    # Only PDF files are considered
    pdf_folder = os.listdir(infolder)
    pdf_files = [_ for _ in pdf_folder
                 if _.lower().endswith(".pdf")]
    # Sort list alphabetically
    # Most scanners are putting timestamps in the file names
    # This information is more important than the OS time stamp
    pdf_files.sort()

    # Get number of CSV entries
    num_students = moodle.get_student_number(sheet_csv=sheet_csv,
                                             csv_enc=csv_enc)
    if len(pdf_files) != num_students:
        raise Exception("Error: Not as many CSV lines as scans!")

    # Parse grading infos from CSV file
    infos = moodle.extract_info(sheet_csv=sheet_csv, csv_delim=csv_delim,
                                csv_quote=csv_quote, csv_enc=csv_enc)

    # Loop over grading infos
    pdfs_no_qrs = []
    print("Renaming", sep=' ', end='', flush=True)
    for cnt, pdf_file in enumerate(pdf_files):
        # Extract matriculation number and lastname from grading info
        info = infos[cnt]
        matnum_csv = info['matnum']

        # Destination PDF file name
        dest_pdf = file_format.format(
            matnum=matnum_csv, fullname=info['fullname'],
            lastname=info['lastname'], firstname=info['firstname'])
        # Add extension
        _, ext = os.path.splitext(pdf_file)
        dest_pdf = dest_pdf + ext
        in_pdf_full = os.path.join(infolder, pdf_file)

        # Sanity check
        if check_qr:
            # Search for first QR code in PDF
            qr = qr_utils.first_qr_from_first_pdf_page(pdf_file=in_pdf_full)

            # Extract matnum from QR code
            if qr:
                # Assumed QR format:
                # "something-before-the-matnum-{matnum}-{pagenum}"
                matnum_qr = qr.split('-')[-2]
                if not matnum_utils.check_matnum(matnum_qr):
                    raise Exception("{} no valid matnum!".format(matnum_qr))

                # Halt if matnum of QR and CSV differ
                if matnum_qr != info['matnum']:
                    raise Exception("{}: QR with {} but CSV with matnum {}"
                                    .format(pdf_file, matnum_csv, matnum_qr))
            else:
                pdfs_no_qrs.append(pdf_file)

        # Copy
        if not dry:
            dest_pdf_full = os.path.join(outfolder, dest_pdf)
            shutil.copyfile(in_pdf_full, dest_pdf_full)
        else:
            dryout += "\n{} -> {}".format(pdf_file, dest_pdf)

        # Print for-loop progress
        if not (cnt % max(1, round(num_students/10))):
            print(".", sep=' ', end='', flush=True)

    # Print results
    print("done.")

    # Dry run
    if dry:
        print("\nDry run results:{}".format(dryout))

    if check_qr and pdfs_no_qrs:
        print("\nCouldn't read QRs in the following PDFs\n- {}"
              .format("\n- ".join(pdfs_no_qrs)))

    # Print time
    endtime = time.time()
    print("Time taken: {:.2f}".format(endtime-starttime))


# Main routine
if __name__ == '__main__':
    main(sys.argv[1:])