Version 0.4.1

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

CHANGELOG.md

@@ -4,6 +4,11 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.4.1] - 2020-01-15
+### Changed
+- Reduce minimum Python version to 3.6 by working around the `is_normalized()`
+that only works in Python >= 3.8
+
 ## [0.4.0] - 2020-01-15
 ### Added
 - Unicode normalization (enable with `--unsafe-fixes`, see README.md)

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)

csv_metadata_quality/version.py

@@ -1 +1 @@
-VERSION = "0.4.0"
+VERSION = "0.4.1"

setup.py

@@ -14,7 +14,7 @@ install_requires = [
 
 setuptools.setup(
     name="csv-metadata-quality",
-    version="0.4.0",
+    version="0.4.1",
     author="Alan Orth",
     author_email="aorth@mjanja.ch",
     description="A simple, but opinionated CSV quality checking and fixing pipeline for CSVs in the DSpace ecosystem.",
@@ -23,6 +23,8 @@ setuptools.setup(
     long_description_content_type="text/markdown",
     url="https://github.com/alanorth/csv-metadata-quality",
     classifiers=[
+        "Programming Language :: Python :: 3.6",
+        "Programming Language :: Python :: 3.7",
         "Programming Language :: Python :: 3.8",
         "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
         "Operating System :: OS Independent",