Convert Avid ALE files to CSV

ale2csv.py

#!/usr/bin/env python
from collections import OrderedDict
from itertools import dropwhile, izip
import csv
import argparse
import os.path

argparser = argparse.ArgumentParser()
argparser.add_argument("ale_file", metavar="ALE", type=argparse.FileType(mode="rb"))
argparser.add_argument("csv_file", metavar="CSV", type=argparse.FileType(mode="wb"), nargs="?", default=None)


def main():
    args = argparser.parse_args()

    columns, data = convert_ale_to_dict(args.ale_file)
    args.ale_file.close()

    if args.csv_file is not None:
        csv_file = args.csv_file
    else:
        pre, ext = os.path.splitext(args.ale_file.name)
        csv_path = pre + ".csv"
        csv_file = open(csv_path, mode="wb")

    dump_csv(csv_file, columns, data)
    csv_file.close()


def convert_ale_to_dict(f):
    f_iter = iter(f)

    f_iter = dropwhile(lambda line: line != "Column\n", f_iter)
    column_line = next_or_none(f_iter)
    if column_line is None:
        raise Exception("No columns found")

    column_names_line = next_or_none(f_iter)
    if column_names_line is None:
        raise Exception("No values for columns")

    columns = column_names_line.replace("\n", "").split("\t")

    f_iter = dropwhile(lambda line: line != "Data\n", f_iter)
    data_line = next_or_none(f_iter)
    if data_line is None:
        raise Exception("No data found")

    data = []
    for data_values_line in f_iter:
        values = data_values_line.replace("\n", "").split("\t")
        values_dict = OrderedDict(izip(columns, values))

        data.append(values_dict)

    return (columns, data)


def dump_csv(f, columns, data):
    dw = csv.DictWriter(f, fieldnames=columns)

    dw.writeheader()

    dw.writerows(data)


def next_or_none(iter):
    try:
        return next(iter)
    except StopIteration:
        return None


if __name__ == "__main__":
    main()

This is just a script that I threw together to more easily read ALE files so the error handling is not that great.

An ALE looks something like this:

Column
Name Tracks Start End Duration KN Start KN End KN Duration Mark IN Mark OUT Mark Duration KN Mark IN KN Mark OUT KN IN-OUT Scene Take Shoot date Aux TC1 Camera Camroll FPS Film TC Labroll Perf Pullin

Data
19B-1 VA1A2 06:19:34:20 06:24:35:25 EJ634018-5413+15 19B 1.00 Thu Mar 6 2008 A A17 24.00 180310.00 A

What that exception means is that there was no Column string found in the file.

Line 33 goes through the file until it finds a line that reads Column. Then it will read the name of the columns from the line after in code line 34. If it does not find the Column line or there is there is no next line it will throw this exception

@simonwagner
@casausg
I updated the script to work properly in Python 3

• updated the import from itertools to only import dropwhile since izip is now just zip natively in Python 3
• changed the read and write by removing the "b" to accommodate for all strings being unicode in Python 3
• changed the dropwhile to detect regardless of which newline character to make sure source ALE files can be written by any OS.
• updated line to use zip instead of izip

...
from itertools import dropwhile
...
argparser.add_argument("ale_file", metavar="ALE", type=argparse.FileType(mode="r"))
argparser.add_argument("csv_file", metavar="CSV", type=argparse.FileType(mode="w"), nargs="?", default=None)
...
f_iter = dropwhile(lambda line: "Column" not in line.rstrip(), f_iter)
...
f_iter = dropwhile(lambda line: "Data" not in line.rstrip(), f_iter)
...
values_dict = OrderedDict(zip(columns, values))
...

Thanks Simon, this has been very useful. I've forked it and added the ability to iterate through multiple ALEs and handle Avid ALEs

Howdy y'all! I enhanced this code and have if convert stuff from Alexa camera's to CSV for Resolve! Check it out:
https://github.com/jaminmc/ale2ResolveCSV

It also runs on the latest Python