1
0
mirror of https://github.com/ilri/csv-metadata-quality.git synced 2024-11-17 19:47:03 +01:00
csv-metadata-quality/csv_metadata_quality/app.py
Alan Orth a93b5b31c5
Add support for command line arguments
Currently only supports specifying input and output files with -i
and -o. Eventually I'll add more options like dry run, debug, and
maybe things like forcing unsafe fixes.
2019-07-28 20:31:57 +03:00

48 lines
1.7 KiB
Python

import argparse
import csv_metadata_quality.check as check
import csv_metadata_quality.fix as fix
import pandas as pd
import re
def parse_args(argv):
parser = argparse.ArgumentParser(description='Metadata quality checker and fixer.')
parser.add_argument('--input-file', '-i', help='Path to input file. Can be UTF-8 CSV or Excel XLSX.', required=True, type=argparse.FileType('r', encoding='UTF-8'))
parser.add_argument('--output-file', '-o', help='Path to output file (always CSV).', required=True, type=argparse.FileType('w', encoding='UTF-8'))
args = parser.parse_args()
return args
def main(argv):
args = parse_args(argv)
# Read all fields as strings so dates don't get converted from 1998 to 1998.0
df = pd.read_csv(args.input_file, dtype=str)
# Fix whitespace in all columns
for column in df.columns.values.tolist():
# Run whitespace fix on all columns
df[column] = df[column].apply(fix.whitespace)
# Run invalid multi-value separator check on all columns
df[column] = df[column].apply(check.separators)
# check if column is an issn column like dc.identifier.issn
match = re.match(r'^.*?issn.*$', column)
if match is not None:
df[column] = df[column].apply(check.issn)
# check if column is an isbn column like dc.identifier.isbn
match = re.match(r'^.*?isbn.*$', column)
if match is not None:
df[column] = df[column].apply(check.isbn)
# check if column is a date column like dc.date.issued
match = re.match(r'^.*?date.*$', column)
if match is not None:
df[column] = df[column].apply(check.date)
# Write
df.to_csv(args.output_file, index=False)