mirror of
https://github.com/ilri/csv-metadata-quality.git
synced 2024-12-23 04:32:21 +01:00
Alan Orth
49e3543878
This will check all strings for un-normalized Unicode characters. Normalization is done using NFC. This includes tests and updated sample data (data/test.csv). See: https://withblue.ink/2019/03/11/why-you-need-to-normalize-unicode-strings.html
91 lines
1.9 KiB
Python
91 lines
1.9 KiB
Python
import csv_metadata_quality.fix as fix
|
||
|
||
|
||
def test_fix_leading_whitespace():
|
||
"""Test fixing leading whitespace."""
|
||
|
||
value = " Alan"
|
||
|
||
assert fix.whitespace(value) == "Alan"
|
||
|
||
|
||
def test_fix_trailing_whitespace():
|
||
"""Test fixing trailing whitespace."""
|
||
|
||
value = "Alan "
|
||
|
||
assert fix.whitespace(value) == "Alan"
|
||
|
||
|
||
def test_fix_excessive_whitespace():
|
||
"""Test fixing excessive whitespace."""
|
||
|
||
value = "Alan Orth"
|
||
|
||
assert fix.whitespace(value) == "Alan Orth"
|
||
|
||
|
||
def test_fix_invalid_separators():
|
||
"""Test fixing invalid multi-value separators."""
|
||
|
||
value = "Alan|Orth"
|
||
|
||
assert fix.separators(value) == "Alan||Orth"
|
||
|
||
|
||
def test_fix_unnecessary_unicode():
|
||
"""Test fixing unnecessary Unicode."""
|
||
|
||
value = "Alan Orth"
|
||
|
||
assert fix.unnecessary_unicode(value) == "Alan Orth"
|
||
|
||
|
||
def test_fix_duplicates():
|
||
"""Test fixing duplicate metadata values."""
|
||
|
||
value = "Kenya||Kenya"
|
||
|
||
assert fix.duplicates(value) == "Kenya"
|
||
|
||
|
||
def test_fix_newlines():
|
||
"""Test fixing newlines."""
|
||
|
||
value = """Ken
|
||
ya"""
|
||
|
||
assert fix.newlines(value) == "Kenya"
|
||
|
||
|
||
def test_fix_comma_space():
|
||
"""Test adding space after comma."""
|
||
|
||
value = "Orth,Alan S."
|
||
|
||
field_name = "dc.contributor.author"
|
||
|
||
assert fix.comma_space(value, field_name) == "Orth, Alan S."
|
||
|
||
|
||
def test_fix_normalized_unicode():
|
||
"""Test fixing a string that is already in its normalized (NFC) Unicode form."""
|
||
|
||
# string using the normalized canonical form of é
|
||
value = "Ouédraogo, Mathieu"
|
||
|
||
field_name = "dc.contributor.author"
|
||
|
||
assert fix.normalize_unicode(value, field_name) == "Ouédraogo, Mathieu"
|
||
|
||
|
||
def test_fix_decomposed_unicode():
|
||
"""Test fixing a string that contains Unicode string."""
|
||
|
||
# string using the decomposed form of é
|
||
value = "Ouédraogo, Mathieu"
|
||
|
||
field_name = "dc.contributor.author"
|
||
|
||
assert fix.normalize_unicode(value, field_name) == "Ouédraogo, Mathieu"
|