Address more review comments

ESCOMP · Nov 6, 2023 · 28f9892 · 28f9892
1 parent 7eb7a6f
commit 28f9892
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 15 deletions.
diff --git a/tools/check_name_rules.py b/tools/check_name_rules.py
@@ -1,13 +1,12 @@
 #!/usr/bin/env python3
 
 """
-Remove duplicates from a metadata standard-name XML library file.
+Check standard names database file for violations of standard name character rules
 """
 
 import argparse
 import sys
 import os.path
-import copy
 import re
 
 ################################################
@@ -50,20 +49,20 @@ def main():
             validate_xml_file(stdname_file, schema_name, version, None,
                             schema_path=schema_root, error_on_noxmllint=True)
         except ValueError:
-            raise ValueError("Invalid standard names file, {}".format(stdname_file))
+            raise ValueError(f"Invalid standard names file, {stdname_file}")
     else:
-        raise ValueError(
-            'Cannot find schema file, {}, for version {}'.format(schema_name, version)
-        )
+        raise ValueError(f'Cannot find schema file, {schema_name}, for {version=}')
 
     #Parse list of standard names and see if any names violate one or more rules
     violators = {}
+    legal_first_char = re.compile('[a-z]')
+    valid_chars = re.compile('[a-z0-9_]')
     for name in root.findall('./section/standard_name'):
         sname = name.attrib['name']
         violations = []
-        if re.sub('[a-z]', '', sname[0]):
+        if legal_first_char.sub('', sname[0]):
             violations.append('First character is not a lowercase letter')
-        testchars = re.sub('[a-z0-9_]', '', sname)
+        testchars = valid_chars.sub('', sname)
         if testchars:
             violations.append(f'Invalid characters are present: "{testchars}"')
 

diff --git a/tools/check_xml_unique.py b/tools/check_xml_unique.py
@@ -59,11 +59,9 @@ def main_func():
             validate_xml_file(stdname_file, schema_name, version, None,
                             schema_path=schema_root, error_on_noxmllint=True)
         except ValueError:
-            raise ValueError("Invalid standard names file, {}".format(stdname_file))
+            raise ValueError(f"Invalid standard names file, {stdname_file}")
     else:
-        raise ValueError(
-            'Cannot find schema file, {}, for version {}'.format(schema_name, version)
-        )
+        raise ValueError(f'Cannot find schema file, {schema_name}, for {version=}')
 
     #get list of all standard names
     all_std_names = []
@@ -87,8 +85,8 @@ def main_func():
             print('The following duplicate standard names were found:')
             for dup in dup_std_names:
                 rm_elements = root.findall('./section/standard_name[@name="%s"]'%dup)[1:]
-                print("{0}, ({1} duplicate(s))".format(dup, len(rm_elements)))
-            print('Removing duplicates and overwriting {}'.format(stdname_file))
+                print("{dup}, ({len(rm_elements)} duplicate(s))")
+            print('Removing duplicates and overwriting {stdname_file}')
             for dup in dup_std_names:
                 first_use = True #Logical that indicates the first use of the duplicated name
                 rm_parents = root.findall('./section/standard_name[@name="%s"]..'%dup)
@@ -110,7 +108,7 @@ def main_func():
             print('The following duplicate standard names were found:')
             for dup in dup_std_names:
                 rm_elements = root.findall('./section/standard_name[@name="%s"]'%dup)[1:]
-                print("{0}, ({1} duplicate(s))".format(dup, len(rm_elements)))
+                print("{dup}, ({len(rm_elements)} duplicate(s))")
             sys.exit(1)
         else:
             print('No duplicate standard names were found.')