Add ISSN and ISBN checks using python-stdnum

csv_metadata_quality/app.py

@@ -1,3 +1,4 @@
+import csv_metadata_quality.check as check
 import csv_metadata_quality.fix as fix
 import pandas as pd
 
@@ -13,5 +14,11 @@ def run():
 
         df[column] = df[column].apply(fix.whitespace)
 
+        if column == 'dc.identifier.issn':
+            df[column] = df[column].apply(check.issn)
+
+        if column == 'dc.identifier.isbn':
+            df[column] = df[column].apply(check.isbn)
+
     # Write
     df.to_csv('/tmp/omg.fixed.csv', index=False)

csv_metadata_quality/check.py

@@ -0,0 +1,42 @@
+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}')
+
+
+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
+
+    # Try to split multi-value field on "||" separator
+    for value in field.split('||'):
+
+        if not isbn.is_valid(value):
+            print(f'Invalid ISBN: {value}')