From d73f7b54b1c477bdc956034c04ddac2a9c430340 Mon Sep 17 00:00:00 2001 From: Alan Orth Date: Mon, 29 Jul 2019 16:24:35 +0300 Subject: [PATCH] csv_metadata_quality/app.py: Improve comments --- csv_metadata_quality/app.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/csv_metadata_quality/app.py b/csv_metadata_quality/app.py index caade1c..1695673 100644 --- a/csv_metadata_quality/app.py +++ b/csv_metadata_quality/app.py @@ -22,29 +22,29 @@ def main(argv): df = pd.read_csv(args.input_file, dtype=str) for column in df.columns.values.tolist(): - # Run whitespace fix on all columns + # Fix: whitespace df[column] = df[column].apply(fix.whitespace) - # Run invalid multi-value separator check on all columns + # Check: invalid multi-value separator df[column] = df[column].apply(check.separators) - # Run invalid multi-value separator fix on all columns + # Fix: invalid multi-value separator if args.unsafe_fixes: df[column] = df[column].apply(fix.separators) # Run whitespace fix again after fixing invalid separators df[column] = df[column].apply(fix.whitespace) - # check if column is an issn column like dc.identifier.issn + # Check: invalid ISSN match = re.match(r'^.*?issn.*$', column) if match is not None: df[column] = df[column].apply(check.issn) - # check if column is an isbn column like dc.identifier.isbn + # Check: invalid ISBN match = re.match(r'^.*?isbn.*$', column) if match is not None: df[column] = df[column].apply(check.isbn) - # check if column is a date column like dc.date.issued + # Check: invalid date match = re.match(r'^.*?date.*$', column) if match is not None: df[column] = df[column].apply(check.date)