Created
September 9, 2020 10:50
-
-
Save AndrewOwenMartin/906a3eefb9fa27fc0353b40a444fe678 to your computer and use it in GitHub Desktop.
A reader for the concordance DAT file format
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import collections | |
import logging, pathlib | |
import csv | |
log = logging.getLogger(__name__) | |
def read_dat(path): | |
with path.open("r", encoding="latin1") as f: | |
csv_reader = csv.reader(f, delimiter="\x14", quotechar="\xfe") | |
header_row = list(next(csv_reader)) | |
DatRow = collections.namedtuple("DatRow", header_row) | |
yield from (DatRow(*row) for row in csv_reader) | |
def main(): | |
path = pathlib.Path("example.dat") | |
row_gen = read_dat(path) | |
for num, row in enumerate(row_gen): | |
log.info("%s: %s", num, row) | |
if num > 10: | |
break | |
if __name__ == "__main__": | |
logging.basicConfig( | |
level=logging.INFO, | |
datefmt="%Y-%m-%d %H:%M:%S", | |
format="%(asctime)s %(levelname)-4s %(name)s %(message)s", | |
style="%", | |
) | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment