mirror of
https://github.com/ilri/csv-metadata-quality.git
synced 2024-11-10 16:25:45 +01:00
Alan Orth
232d28e13e
This makes it cleaner for introducing checks, fixes, tests, docs, and tests in the future. Currently can be run like this: python -m csv_metadata_quality CSV input and output paths are still hard coded. See: https://dev.to/codemouse92/dead-simple-python-project-structure-and-imports-38c6
43 lines
982 B
Python
Executable File
43 lines
982 B
Python
Executable File
import pandas as pd
|
|
import re
|
|
|
|
def alan():
|
|
print('Alan')
|
|
|
|
|
|
def whitespace(field):
|
|
"""Fix whitespace issues.
|
|
|
|
Return string with leading, trailing, and consecutive whitespace trimmed.
|
|
"""
|
|
|
|
|
|
# Skip fields with missing values
|
|
if pd.isna(field):
|
|
return
|
|
|
|
# Initialize an empty list to hold the cleaned values
|
|
values = list()
|
|
|
|
# Try to split multi-value field on "||" separator
|
|
for value in field.split('||'):
|
|
# Strip leading and trailing whitespace
|
|
value = value.strip()
|
|
|
|
# Replace excessive whitespace (>2) with one space
|
|
pattern = re.compile(r'\s{2,}')
|
|
match = re.findall(pattern, value)
|
|
|
|
if len(match) > 0:
|
|
print('DEBUG: Excessive whitespace')
|
|
value = re.sub(pattern, ' ', value)
|
|
|
|
# Save cleaned value
|
|
values.append(value)
|
|
|
|
# Create a new field consisting of all values joined with "||"
|
|
new_field = '||'.join(values)
|
|
|
|
return new_field
|
|
|