1
0
mirror of https://github.com/ilri/csv-metadata-quality.git synced 2024-06-09 13:25:08 +02:00

csv_metadata_quality/fix.py: Harmonize language in fix output

We should always say if we're removing or replacing something.
This commit is contained in:
Alan Orth 2019-10-01 17:09:23 +03:00
parent 85ae16d9b7
commit e55380b4d5
Signed by: alanorth
GPG Key ID: 0FB860CC9C45B1B9

View File

@ -26,7 +26,7 @@ def whitespace(field):
match = re.findall(pattern, value)
if match:
print(f"Excessive whitespace: {value}")
print(f"Removing excessive whitespace: {value}")
value = re.sub(pattern, " ", value)
# Save cleaned value
@ -140,7 +140,7 @@ def duplicates(field):
if value not in new_values:
new_values.append(value)
else:
print(f"Dropping duplicate value: {value}")
print(f"Removing duplicate value: {value}")
# Create a new field consisting of all values joined with "||"
new_field = "||".join(new_values)