1
0
mirror of https://github.com/ilri/csv-metadata-quality.git synced 2024-11-18 20:17:04 +01:00
csv-metadata-quality/csv_metadata_quality/check.py
Alan Orth fa4fa3491b
Add check for "suspicious" characters
These standalone characters often indicate issues with encoding or
copy/paste in languages with accents like French and Spanish. For
example: foreˆt should be forêt.

It is not possible to fix these issues automatically, but this will
print a warning so you can notify the owner of the data.
2019-07-29 17:08:49 +03:00

150 lines
3.4 KiB
Python
Executable File
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import pandas as pd
def issn(field):
"""Check if an ISSN is valid.
Prints the ISSN if invalid.
stdnum's is_valid() function never raises an exception.
See: https://arthurdejong.org/python-stdnum/doc/1.11/index.html#stdnum.module.is_valid
"""
from stdnum import issn
# Skip fields with missing values
if pd.isna(field):
return
# Try to split multi-value field on "||" separator
for value in field.split('||'):
if not issn.is_valid(value):
print(f'Invalid ISSN: {value}')
return field
def isbn(field):
"""Check if an ISBN is valid.
Prints the ISBN if invalid.
stdnum's is_valid() function never raises an exception.
See: https://arthurdejong.org/python-stdnum/doc/1.11/index.html#stdnum.module.is_valid
"""
from stdnum import isbn
# Skip fields with missing values
if pd.isna(field):
return
# Try to split multi-value field on "||" separator
for value in field.split('||'):
if not isbn.is_valid(value):
print(f'Invalid ISBN: {value}')
return field
def separators(field):
"""Check for invalid multi-value separators (ie "|" or "|||").
Prints the field with the invalid multi-value separator.
"""
import re
# Skip fields with missing values
if pd.isna(field):
return
# Try to split multi-value field on "||" separator
for value in field.split('||'):
# After splitting, see if there are any remaining "|" characters
match = re.findall(r'^.*?\|.*$', value)
if match:
print(f'Invalid multi-value separator: {field}')
return field
def date(field):
"""Check if a date is valid.
In DSpace the issue date is usually 1990, 1990-01, or 1990-01-01, but it
could technically even include time as long as it is ISO8601.
Also checks for other invalid cases like missing and multiple dates.
Prints the date if invalid.
"""
from datetime import datetime
if pd.isna(field):
print(f'Missing date.')
return
# Try to split multi-value field on "||" separator
multiple_dates = field.split('||')
# We don't allow multi-value date fields
if len(multiple_dates) > 1:
print(f'Multiple dates not allowed: {field}')
return field
try:
# Check if date is valid YYYY format
datetime.strptime(field, '%Y')
return field
except ValueError:
pass
try:
# Check if date is valid YYYY-MM format
datetime.strptime(field, '%Y-%m')
return field
except ValueError:
pass
try:
# Check if date is valid YYYY-MM-DD format
datetime.strptime(field, '%Y-%m-%d')
return field
except ValueError:
print(f'Invalid date: {field}')
def suspicious_characters(field):
"""Warn about suspicious characters.
Look for standalone characters that could indicate encoding or copy/paste
errors for languages with accents. For example: foreˆt should be forêt.
"""
# Skip fields with missing values
if pd.isna(field):
return
# List of suspicious characters, for example: ́ˆ~`
suspicious_characters = ['\u00B4', '\u02C6', '\u007E', '\u0060']
for character in suspicious_characters:
character_set = set(character)
if character_set.issubset(field):
print(f'Suspicious character: {field}')
return field