alanorth/csv-metadata-quality
1
0
Fork 0
mirror of https://github.com/ilri/csv-metadata-quality.git synced 2024-12-21 19:52:18 +01:00
Code Releases Activity

Add field name to fix.newlines output

Browse Source
This commit is contained in:
Alan Orth 2021-10-08 14:36:23 +03:00
parent 82261f7fe0
commit 787fa9e8d9
Signed by: alanorth
GPG Key ID: 0FB860CC9C45B1B9
3 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
csv_metadata_quality/app.py
View File

@ -89,7 +89,7 @@ def run(argv):
# Fix: newlines
if args.unsafe_fixes:
df[column] = df[column].apply(fix.newlines)
df[column] = df[column].apply(fix.newlines, field_name=column)
# Fix: missing space after comma. Only run on author and citation
# fields for now, as this problem is mostly an issue in names.

4
csv_metadata_quality/fix.py
View File

@ -180,7 +180,7 @@ def duplicates(field, field_name):
return new_field
def newlines(field):
def newlines(field, field_name):
"""Fix newlines.
Single metadata values should not span multiple lines because this is not
@ -205,7 +205,7 @@ def newlines(field):
match = re.findall(r"\n", field)
if match:
print(f"{Fore.GREEN}Removing newline: {Fore.RESET}{field}")
print(f"{Fore.GREEN}Removing newline ({field_name}): {Fore.RESET}{field}")
field = field.replace("\n", "")
return field

3
tests/test_fix.py
View File

@ -76,8 +76,9 @@ def test_fix_newlines():
value = """Ken
ya"""
field_name = "dcterms.subject"
assert fix.newlines(value) == "Kenya"
assert fix.newlines(value, field_name) == "Kenya"
def test_fix_comma_space():