feat: add benchmark

.gitignore

@@ -12,6 +12,7 @@ venv
 result.txt
 testing/main.c
 */*compile_commands.json
+testing/benchmark_results.txt
 
 # Ignore Python wheel packages (clang-format, clang-tidy)
 clang-tidy-1*

docs/benchmark.md

@@ -0,0 +1,18 @@
+# Benchmarking
+
+This document outlines the benchmarking process for comparing the performance of cpp-linter-hooks and mirrors-clang-format.
+
+## Running the Benchmark
+
+```bash
+python3 testing/benchmark_hooks.py
+```
+
+## Results
+
+The results of the benchmarking process will be saved to `testing/benchmark_results.txt`.
+
+## To Do
+
+- Run benchmark against a larger codebase, such as [TheAlgorithms/C-Plus-Plus](https://github.com/TheAlgorithms/C-Plus-Plus).
+- Run benchmark with GitHub Actions for continuous integration.

testing/benchmark_hooks.py

@@ -0,0 +1,95 @@
+#!/usr/bin/env python3
+"""
+Benchmark script to compare performance of cpp-linter-hooks vs mirrors-clang-format.
+
+Usage:
+ python benchmark_hooks.py
+
+Requirements:
+- pre-commit must be installed and available in PATH
+- Two config files:
+ - testing/pre-commit-config-cpp-linter-hooks.yaml
+ - testing/pre-commit-config-mirrors-clang-format.yaml
+- Target files: testing/main.c (or adjust as needed)
+"""
+
+import subprocess
+import time
+import statistics
+import glob
+
+HOOKS = [
+ {
+ "name": "cpp-linter-hooks",
+ "config": "testing/pre-commit-config-cpp-linter-hooks.yaml",
+ },
+ {
+ "name": "mirrors-clang-format",
+ "config": "testing/pre-commit-config-mirrors-clang-format.yaml",
+ },
+]
+
+# Automatically find all C/C++ files in testing/ (and optionally src/, include/)
+TARGET_FILES = (
+ glob.glob("testing/**/*.c", recursive=True)
+ + glob.glob("testing/**/*.cpp", recursive=True)
+ + glob.glob("testing/**/*.h", recursive=True)
+ + glob.glob("testing/**/*.hpp", recursive=True)
+)
+
+REPEATS = 5
+RESULTS_FILE = "testing/benchmark_results.txt"
+
+
+def run_hook(config, files):
+ cmd = ["pre-commit", "run", "--config", config, "--files"] + files
+ start = time.perf_counter()
+ try:
+ subprocess.run(cmd, check=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+ except subprocess.CalledProcessError:
+ # Still record time even if hook fails
+ pass
+ end = time.perf_counter()
+ return end - start
+
+
+def benchmark():
+ results = {}
+ for hook in HOOKS:
+ times = []
+ print(f"Benchmarking {hook['name']}...")
+ for i in range(REPEATS):
+ # Clean up any changes before each run
+ subprocess.run(["git", "restore"] + TARGET_FILES)
+ subprocess.run(["pre-commit", "clean"])
+ t = run_hook(hook["config"], TARGET_FILES)
+ print(f" Run {i + 1}: {t:.3f} seconds")
+ times.append(t)
+ results[hook["name"]] = times
+ return results
+
+
+def report(results):
+ lines = []
+ for name, times in results.items():
+ avg = statistics.mean(times)
+ std = statistics.stdev(times) if len(times) > 1 else 0.0
+ min_t = min(times)
+ max_t = max(times)
+ lines.append(
+ f"{name}: avg={avg:.3f}s, std={std:.3f}s, min={min_t:.3f}s, max={max_t:.3f}s, runs={len(times)}"
+ )
+ print("\nBenchmark Results:")
+ print("\n".join(lines))
+ with open(RESULTS_FILE, "w") as f:
+ f.write("\n".join(lines) + "\n")
+ print(f"Results saved to {RESULTS_FILE}")
+
+
+def main():
+ results = benchmark()
+ report(results)
+
+
+if __name__ == "__main__":
+ main()