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

Ignore subregion field for missing region checks
All checks were successful
continuous-integration/drone/push Build is passing
Details

Browse Source 
Due to a sloppy regex I was sometimes matching the subregion field
when checking for missing UN M.49 regions in the region field.
This commit is contained in:
Alan Orth
2022-12-07 23:18:47 +01:00
parent 58e956360a
commit 051777bcec
4 changed files with 46 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
csv_metadata_quality/check.py
View File

@ -512,9 +512,9 @@ def countries_match_regions(row, exclude):
if match is not None:
country_column_name = label
# Find the name of the region column
# Find the name of the region column, but make sure it's not subregion!
match = re.match(r"^.*?region.*$", label)
if match is not None:
if match is not None and "sub" not in label:
region_column_name = label
# Find the name of the title column

4
csv_metadata_quality/fix.py
View File

@ -327,9 +327,9 @@ def countries_match_regions(row, exclude):
if match is not None:
country_column_name = label
# Find the name of the region column
# Find the name of the region column, but make sure it's not subregion!
match = re.match(r"^.*?region.*$", label)
if match is not None:
if match is not None and "sub" not in label:
region_column_name = label
# Find the name of the title column