mirror of
https://github.com/ilri/csv-metadata-quality.git
synced 2025-05-16 17:43:54 +02:00
Add support for validating languages
Will validate against ISO 639-2 or ISO 639-3 depending on how long the language field is. Otherwise will return that the language is invalid. Does not currently have any support for generic values like "Other".
This commit is contained in:
@ -43,6 +43,11 @@ def main(argv):
|
||||
# Fix: duplicate metadata values
|
||||
df[column] = df[column].apply(fix.duplicates)
|
||||
|
||||
# Check: invalid language
|
||||
match = re.match(r'^.*?language.*$', column)
|
||||
if match is not None:
|
||||
df[column] = df[column].apply(check.language)
|
||||
|
||||
# Check: invalid ISSN
|
||||
match = re.match(r'^.*?issn.*$', column)
|
||||
if match is not None:
|
||||
|
Reference in New Issue
Block a user