Update license scripts to support YAML frontmatter changes

AUTHORS.rst

@@ -79,6 +79,7 @@ The following organizations or individuals have contributed to ScanCode:
 - Sankha Das @sankha555
 - Saravanan G @SaravananOffl
 - Sarita Singh @itssingh
+- Sarthak Shubham @sarthak-shubham
 - Savino Sguera @savinos
 - Sebastian Roth @ened
 - Sebastian Schuberth @sschuberth

CHANGELOG.rst

@@ -8,6 +8,13 @@ Next release
   ``licensedcode-data``.
   https://github.com/aboutcode-org/scancode-toolkit/pull/5056
 
+- Fix ``report_license_rules.py`` and ``buildrules.py`` in
+  ``etc/scripts/licenses/`` to work correctly with the YAML frontmatter
+  fields added in #3100.
+  https://github.com/aboutcode-org/scancode-toolkit/pull/5259
+
+
+
 v33.0.0rc1 - 2026-05-14
 ------------------------
 

etc/scripts/licenses/buildrules.py

@@ -294,6 +294,7 @@ def cli(licenses_file, dump_to_file_on_errors=False):
     """
 
     rules_data = load_data(licenses_file)
+    click.echo("Loading existing rules to check for duplicates. This may take several minutes...")
     rule_by_tokens = all_rule_by_tokens()
 
     licenses_by_key = cache.get_licenses_db()

etc/scripts/licenses/report_license_rules.py

@@ -83,8 +83,8 @@
 
 def write_data_to_csv(data, output_csv, fieldnames):
 
-    with open(output_csv, "w") as f:
-        w = csv.DictWriter(f, fieldnames=fieldnames)
+    with open(output_csv, "w", encoding="utf-8") as f:
+        w = csv.DictWriter(f, fieldnames=fieldnames, extrasaction='ignore')
         w.writeheader()
         for entry in data:
             w.writerow(entry)
@@ -180,6 +180,7 @@ def cli(licenses, rules, category, license_key, with_text):
     licenses_output = []
     rules_output = []
 
+    click.echo("Loading licenses from the database...")
     licenses_data = load_licenses()
 
     if licenses:
@@ -208,8 +209,10 @@ def cli(licenses, rules, category, license_key, with_text):
         write_data_to_csv(data=licenses_output, output_csv=licenses, fieldnames=LICENSES_FIELDNAMES)
 
     if rules:
-        rules_data = list(load_rules())
-        for rule in rules_data:
+        click.echo("Loading 30,000+ rules from the database. This will take several minutes, so please be patient...")
+        for i, rule in enumerate(load_rules()):
+            if i > 0 and i % 5000 == 0:
+                click.echo(f"Processed {i} rules...")
             rule_data = rule.to_dict()
             rule_data["identifier"] = rule.identifier
             rule_data["referenced_filenames"] = rule.referenced_filenames
@@ -240,6 +243,9 @@ def cli(licenses, rules, category, license_key, with_text):
         rules_output = flatten_output(rules_output)
         write_data_to_csv(data=rules_output, output_csv=rules, fieldnames=RULES_FIELDNAMES)
 
+    if licenses or rules:
+        click.echo("Export complete! Check your CSV files.")
+
 
 if __name__ == "__main__":
     cli()