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

Output field name for more fixes and checks

Browse Source 
This helps identify which field has the error.
This commit is contained in:
Alan Orth
2020-01-16 12:35:11 +02:00
parent 40ba9bae6c
commit 28b5996aa6
5 changed files with 35 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
csv_metadata_quality/app.py
View File

@ -82,7 +82,7 @@ def run(argv):
continue
# Fix: whitespace
df[column] = df[column].apply(fix.whitespace)
df[column] = df[column].apply(fix.whitespace, field_name=column)
# Fix: newlines
if args.unsafe_fixes:
@ -104,19 +104,19 @@ def run(argv):
df[column] = df[column].apply(fix.unnecessary_unicode)
# Check: invalid multi-value separator
df[column] = df[column].apply(check.separators)
df[column] = df[column].apply(check.separators, field_name=column)
# Check: suspicious characters
df[column] = df[column].apply(check.suspicious_characters, field_name=column)
# Fix: invalid multi-value separator
if args.unsafe_fixes:
df[column] = df[column].apply(fix.separators)
df[column] = df[column].apply(fix.separators, field_name=column)
# Run whitespace fix again after fixing invalid separators
df[column] = df[column].apply(fix.whitespace)
df[column] = df[column].apply(fix.whitespace, field_name=column)
# Fix: duplicate metadata values
df[column] = df[column].apply(fix.duplicates)
df[column] = df[column].apply(fix.duplicates, field_name=column)
# Check: invalid AGROVOC subject
if args.agrovoc_fields: