Add utility function to check normalization

Python's built-in unicodedata library includes the is_normalized()
function starting with Python 3.8. This utility function allows us
to do the same thing with earlier Python versions.

See: https://docs.python.org/3/library/unicodedata.html

csv_metadata_quality/fix.py

@@ -212,7 +212,7 @@ def normalize_unicode(field, field_name):
     Return normalized string.
     """
 
-    from unicodedata import is_normalized
+    from csv_metadata_quality.util import is_nfc
     from unicodedata import normalize
 
     # Skip fields with missing values
@@ -220,7 +220,7 @@ def normalize_unicode(field, field_name):
         return
 
     # Check if the current string is using normalized Unicode (NFC)
-    if not is_normalized("NFC", field):
+    if not is_nfc(field):
         print(f"Normalizing Unicode ({field_name}): {field}")
         field = normalize("NFC", field)
 

csv_metadata_quality/util.py

@@ -0,0 +1,14 @@
+def is_nfc(field):
+    """Utility function to check whether a string is using normalized Unicode.
+    Python's built-in unicodedata library has the is_normalized() function, but
+    it was only introduced in Python 3.8. By using a simple utility function we
+    are able to run on Python >= 3.6 again.
+
+    See: https://docs.python.org/3/library/unicodedata.html
+
+    Return boolean.
+    """
+
+    from unicodedata import normalize
+
+    return field == normalize("NFC", field)