"""
Micro-benchmark for the Python UTF-8 decoder. Run it with:

./python.orig benchmark.py script bench_str.py --file=orig
./python.patched benchmark.py script bench_str.py --file=patched
./python.patched benchmark.py compare_to orig patched

Download benchmark.py from:

https://bitbucket.org/haypo/misc/raw/tip/python/benchmark.py
"""
def run_benchmark(bench):
    bench.start_group('valid UTF-8 (strict)')
    for length in ('10**1', '10**3', '10**2', '10**4'):
        bench.timeit(setup='data = (b"a" * 100) * %s' % length,
                     stmt='data.decode("utf-8")',
                     name='100 x %s bytes' % length)

    for error_handler in ('ignore', 'replace', 'surrogateescape', 'backslashreplace'):
        bench.start_group(error_handler)
        for length in ('10**1', '10**3', '10**2', '10**4'):
            bench.timeit(setup=r'data = (b"a" * 99 + b"\x80\xff") * %s' % length,
                         stmt='data.decode("utf-8", "%s")' % error_handler,
                         name='100 x %s bytes' % length)