alanorth/csv-metadata-quality
1
0
Fork 0
mirror of https://github.com/ilri/csv-metadata-quality.git synced 2025-05-09 22:56:01 +02:00
Code Releases Activity

Don't fix multi-value separators on citations

Browse Source
This commit is contained in:
Alan Orth
2023-03-10 16:12:30 +03:00
parent 47b03c49ba
commit 45a310387a
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
csv_metadata_quality/app.py
View File

@ -126,7 +126,7 @@ def run(argv):
# Fix: invalid and unnecessary multi-value separators. Skip the title
# and abstract fields because "|" is used to indicate something like
# a subtitle.
match = re.match(r"^.*?(abstract|title).*$", column)
match = re.match(r"^.*?(abstract|[Cc]itation|title).*$", column)
if match is None:
df[column] = df[column].apply(fix.separators, field_name=column)
# Run whitespace fix again after fixing invalid separators