Don't unnecessarily rewrite DataFrames for checks

By using df[column] = df[column].apply(check...) we were re-writing
the DataFrame every time we returned from a check. We don't actuall
y need to return a value at all, as the point of checks is to print
a warning to the screen. In Python a "return" statement without a v
ariable returns None.

I haven't measured the impact of this, but I assume it will mean we
are faster and use less memory.

csv_metadata_quality/app.py

@@ -105,7 +105,7 @@ def run(argv):
         df[column] = df[column].apply(fix.unnecessary_unicode)
 
         # Check: suspicious characters
-        df[column] = df[column].apply(check.suspicious_characters, field_name=column)
+        df[column].apply(check.suspicious_characters, field_name=column)
 
         # Fix: invalid and unnecessary multi-value separators
         df[column] = df[column].apply(fix.separators, field_name=column)
@@ -120,36 +120,36 @@ def run(argv):
             # Identify fields the user wants to validate against AGROVOC
             for field in args.agrovoc_fields.split(","):
                 if column == field:
-                    df[column] = df[column].apply(check.agrovoc, field_name=column)
+                    df[column].apply(check.agrovoc, field_name=column)
 
         # Check: invalid language
         match = re.match(r"^.*?language.*$", column)
         if match is not None:
-            df[column] = df[column].apply(check.language)
+            df[column].apply(check.language)
 
         # Check: invalid ISSN
         match = re.match(r"^.*?issn.*$", column)
         if match is not None:
-            df[column] = df[column].apply(check.issn)
+            df[column].apply(check.issn)
 
         # Check: invalid ISBN
         match = re.match(r"^.*?isbn.*$", column)
         if match is not None:
-            df[column] = df[column].apply(check.isbn)
+            df[column].apply(check.isbn)
 
         # Check: invalid date
         match = re.match(r"^.*?(date|dcterms\.issued).*$", column)
         if match is not None:
-            df[column] = df[column].apply(check.date, field_name=column)
+            df[column].apply(check.date, field_name=column)
 
         # Check: filename extension
         if column == "filename":
-            df[column] = df[column].apply(check.filename_extension)
+            df[column].apply(check.filename_extension)
 
         # Check: SPDX license identifier
         match = re.match(r"dcterms\.license.*$", column)
         if match is not None:
-            df[column] = df[column].apply(check.spdx_license_identifier)
+            df[column].apply(check.spdx_license_identifier)
 
     ##
     # Perform some checks on rows so we can consider items as a whole rather

csv_metadata_quality/check.py

@@ -32,7 +32,7 @@ def issn(field):
         if not stdnum_issn.is_valid(value):
             print(f"{Fore.RED}Invalid ISSN: {Fore.RESET}{value}")
 
-    return field
+    return
 
 
 def isbn(field):
@@ -55,7 +55,7 @@ def isbn(field):
         if not stdnum_isbn.is_valid(value):
             print(f"{Fore.RED}Invalid ISBN: {Fore.RESET}{value}")
 
-    return field
+    return
 
 
 def date(field, field_name):
@@ -83,13 +83,13 @@ def date(field, field_name):
             f"{Fore.RED}Multiple dates not allowed ({field_name}): {Fore.RESET}{field}"
         )
 
-        return field
+        return
 
     try:
         # Check if date is valid YYYY format
         datetime.strptime(field, "%Y")
 
-        return field
+        return
     except ValueError:
         pass
 
@@ -97,7 +97,7 @@ def date(field, field_name):
         # Check if date is valid YYYY-MM format
         datetime.strptime(field, "%Y-%m")
 
-        return field
+        return
     except ValueError:
         pass
 
@@ -105,7 +105,7 @@ def date(field, field_name):
         # Check if date is valid YYYY-MM-DD format
         datetime.strptime(field, "%Y-%m-%d")
 
-        return field
+        return
     except ValueError:
         pass
 
@@ -113,11 +113,11 @@ def date(field, field_name):
         # Check if date is valid YYYY-MM-DDTHH:MM:SSZ format
         datetime.strptime(field, "%Y-%m-%dT%H:%M:%SZ")
 
-        return field
+        return
     except ValueError:
         print(f"{Fore.RED}Invalid date ({field_name}): {Fore.RESET}{field}")
 
-        return field
+        return
 
 
 def suspicious_characters(field, field_name):
@@ -151,7 +151,7 @@ def suspicious_characters(field, field_name):
             suspicious_character_msg = f"{Fore.YELLOW}Suspicious character ({field_name}): {Fore.RESET}{field_subset}"
             print(f"{suspicious_character_msg:1.80}")
 
-    return field
+    return
 
 
 def language(field):
@@ -184,7 +184,7 @@ def language(field):
         else:
             print(f"{Fore.RED}Invalid language: {Fore.RESET}{value}")
 
-    return field
+    return
 
 
 def agrovoc(field, field_name):
@@ -230,7 +230,7 @@ def agrovoc(field, field_name):
             if len(data["results"]) == 0:
                 print(f"{Fore.RED}Invalid AGROVOC ({field_name}): {Fore.RESET}{value}")
 
-    return field
+    return
 
 
 def filename_extension(field):
@@ -281,7 +281,7 @@ def filename_extension(field):
         if filename_extension_match is False:
             print(f"{Fore.YELLOW}Filename with uncommon extension: {Fore.RESET}{value}")
 
-    return field
+    return
 
 
 def spdx_license_identifier(field):
@@ -301,4 +301,4 @@ def spdx_license_identifier(field):
 
             pass
 
-    return field
+    return

csv_metadata_quality/experimental.py

@@ -94,4 +94,4 @@ def correct_language(row):
         )
 
     else:
-        return language
+        return