alanorth/csv-metadata-quality
1
0
Fork 0
mirror of https://github.com/ilri/csv-metadata-quality.git synced 2025-05-09 14:46:00 +02:00
Code Releases Activity

Add "unsafe fixes" runtime option

Browse Source 
In this case it fixes occurences of invalid multi-value separators.
DSpace uses "||" to separate multiple values in one field, but our
editors sometimes give us files with mistakes like "|". We can fix
these to be correct multi-value separators if we are sure that the
metadata is not actually using "|" for some legitimate purpose.
This commit is contained in:
Alan Orth
2019-07-28 22:53:39 +03:00
parent a93b5b31c5
commit 40e77db713
4 changed files with 46 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
csv_metadata_quality/app.py
View File

@ -9,6 +9,7 @@ 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'))
parser.add_argument('--unsafe-fixes', '-u', help='Perform unsafe fixes.', action='store_true')
args = parser.parse_args()
return args
@ -28,6 +29,12 @@ def main(argv):
# Run invalid multi-value separator check on all columns
df[column] = df[column].apply(check.separators)
# Run invalid multi-value separator fix on all columns
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
match = re.match(r'^.*?issn.*$', column)
if match is not None: