Add calculation of most used rules

build-scripts/profile_tool.py

@@ -5,7 +5,7 @@
 import argparse
 
 try:
-    from utils.profile_tool import command_stats, command_sub
+    from utils.profile_tool import command_stats, command_sub, command_most_used_rules
 except ImportError:
     print("The ssg module could not be found.")
     print(
@@ -300,7 +300,11 @@ def parse_args():
     return args
 
 
-SUBCMDS = dict(stats=command_stats, sub=command_sub)
+SUBCMDS = {
+    "stats": command_stats,
+    "sub": command_sub,
+    "most-used-rules": command_most_used_rules,
+}
 
 
 def main():

utils/profile_tool/__init__.py

@@ -1,2 +1,3 @@
 from .sub import command_sub
 from .stats import command_stats
+from .most_used_rules import command_most_used_rules

utils/profile_tool/most_used_rules.py

@@ -0,0 +1,39 @@
+import json
+
+from ssg.build_profile import XCCDFBenchmark
+
+
+def _count_rules_per_profile(profile, rules):
+    for rule in profile.get("rules", []):
+        if rule in rules:
+            rules[rule] += 1
+        else:
+            rules[rule] = 1
+
+
+def _count_rules_per_benchmark(benchmark, rules):
+    benchmark = XCCDFBenchmark(benchmark)
+    for profile in benchmark.get_all_profile_stats():
+        _count_rules_per_profile(profile, rules)
+
+
+def command_most_used_rules(args):
+    rules = {}
+    for benchmark in args.benchmarks:
+        _count_rules_per_benchmark(benchmark, rules)
+
+    sorted_rules = {
+        k: v for k, v in sorted(rules.items(), key=lambda x: x[1], reverse=True)
+    }
+
+    f_string = "{}: {}"
+
+    if args.format == "json":
+        print(json.dumps(sorted_rules, indent=4))
+        return
+    elif args.format == "csv":
+        print("rule_id,count_of_profiles")
+        f_string = "{},{}"
+
+    for rule_id, rule_count in sorted_rules.items():
+        print(f_string.format(rule_id, rule_count))