Created
April 13, 2020 22:11
-
-
Save drkane/f74fd325e1e193f5b9817b31be2a968d to your computer and use it in GitHub Desktop.
Script for generating test Charity Commission zip files
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 io | |
from zipfile import ZipFile, ZIP_DEFLATED | |
import random | |
import bcp | |
import click | |
import tqdm | |
@click.command() | |
@click.argument('infile') | |
def create_data(infile): | |
delimiter = '@**@' | |
lineterminator = '*@@*' | |
print(infile) | |
output_data = {} | |
with ZipFile(infile, 'r') as inzip: | |
charities = set() | |
with inzip.open('extract_charity.bcp', 'r') as infile: | |
reader = bcp.reader(io.TextIOWrapper( | |
infile, encoding='latin1')) | |
for r in reader: | |
charities.add(r[0]) | |
random_charities = random.sample(charities, 500) | |
print(random_charities) | |
# with open | |
for f in inzip.namelist(): | |
print(f) | |
rows = [] | |
with inzip.open(f, 'r') as infile: | |
reader = bcp.reader(io.TextIOWrapper( | |
infile, encoding='latin1')) | |
for r in tqdm.tqdm(reader): | |
if r[0] in random_charities: | |
rows.append(r) | |
if rows: | |
output_data[f] = lineterminator.join([ | |
delimiter.join(r) for r in rows | |
]) | |
print(f"Found {:,.0f} sample rows") | |
else: | |
with inzip.open(f, 'r') as infile: | |
output_data[f] = infile.read() | |
with ZipFile('RegPlusExtract_TESTDATA.zip', 'w', compression=ZIP_DEFLATED) as outzip: | |
for f, contents in output_data.items(): | |
outzip.writestr(f, contents) | |
if __name__ == '__main__': | |
create_data() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment