Convert Adobe Prelude subclip markers exported as CSV to a better format.

pltosheets.py

"""Convert subclip marker CSV file exported from Prelude to a more user-friendly format."""

import argparse
import csv
import platform

# Add your category abbreviations here
CATS = {
    'ha': 'Haastis',
    'fi': 'Fiilis',
    'yl': 'Yleiskuva',
    'to': 'Toiminta',
    'yk': 'Yksityiskohta',
    'il': 'Ilmakuva'
}

# Use OS-specific path delimiter
PATH_DELIMITER = '\\' if platform.system() == 'Windows' else '/'

def main():
    """Main function"""

    # Argument parsing and --help feature
    parser = argparse.ArgumentParser(
        description="""Convert subclip marker CSV file exported from Prelude
                    to a more user-friendly format. USAGE: Takes in subclip markers only.
                    The marker name should be in format note/category/rating, delimited
                    by forward slashes. For the category, use abbreviations specified
                    in the beginning of the script file
                    (by default 2 first letters of the word in lowercase).""")
    parser.add_argument('-d', '--depth',
                        dest='depth',
                        default=1,
                        type=int,
                        help="""Depth of path that you want to retain,
                             1 = only the file name  itself (default)""",
                        metavar='depth')
    parser.add_argument('inputfile',
                        type=str,
                        help='Path to the file',
                        metavar='inputfile')
    parser.add_argument('outputfile',
                        type=str,
                        help="""Path to the output file
                             that will be created""", metavar='outputfile')

    args = parser.parse_args()

    # Initialize result table (list of lists)
    table = []

    with open(args.inputfile, 'r', encoding='utf-16', newline=None) as original:
        reader = csv.reader((row.replace('\0', '') for row in original), delimiter='\t')
        for row in reader:
            # Each row from marker data is now
            # [filepath, intimecode, outtimecode, category (empty), rating (empty), name]
            table.append([row[9], row[4], row[5], '', '', row[0]])

        original.close()

    # Remove column headers, We'll add those back later
    table.pop(0)

    row_note = []
    row_filename = []
    parsed_filename = ''

    for row_data in table:
        row_note = row_data[5].split('/') # Split marker name to list
        row_filename = row_data[0].split(PATH_DELIMITER) # Split file path to list

        # Place just the file name to parsed_filename
        parsed_filename = row_filename[-1]

        # Iterate and add parts of path in reverse order if required by -d parameter
        end = max(0, len(row_filename) - 1 - args.depth)
        for i in range(len(row_filename) - 2, end, -1):
            parsed_filename = row_filename[i] + PATH_DELIMITER + parsed_filename

        # Final file name
        row_data[0] = parsed_filename

        # Category
        try:
            row_data[3] = CATS[row_note[1]]
        except KeyError:
            # Abbreviation not found in CATS
            row_data[3] = row_note[1]
        except IndexError:
            # No category marked
            pass

        # Rating
        try:
            row_data[4] = row_note[2]
        except IndexError:
            pass

        # Note
        row_data[5] = row_note[0]

    # Add column names back
    table.insert(0, ['File', 'In', 'Out', 'Category', 'Rating', 'Note'])

    # Write result table to a CSV file
    with open(args.outputfile, 'w+', encoding='utf-16', newline='') as output:
        writer = csv.writer(output, delimiter='\t')
        writer.writerows(table)

        output.close()

if __name__ == "__main__":
    main()