Optimize ASCII lowercase conversion performance - #15203

from statistics import median
from timeit import repeat

ASCII_UPPERCASE_START = ord("A")
ASCII_UPPERCASE_END = ord("Z")
ASCII_CASE_OFFSET = ord("a") - ord("A")


def old_lower(word: str) -> str:
    """
    Will convert the entire string to lowercase letters

    >>> old_lower("wow")
    'wow'
    >>> old_lower("HellZo")
    'hellzo'
    >>> old_lower("WHAT")
    'what'
    >>> old_lower("wh[]32")
    'wh[]32'
    >>> old_lower("whAT")
    'what'
    """

    # Converting to ASCII value, obtaining the integer representation
    # and checking to see if the character is a capital letter.
    # If it is a capital letter, it is shifted by 32, making it a lowercase letter.
    return "".join(chr(ord(char) + 32) if "A" <= char <= "Z" else char for char in word)


def new_lower(word: str) -> str:
    """
    Convert ASCII uppercase letters in a string to lowercase.

    >>> new_lower("wow")
    'wow'
    >>> new_lower("HellZo")
    'hellzo'
    >>> new_lower("WHAT")
    'what'
    >>> new_lower("wh[]32")
    'wh[]32'
    >>> new_lower("whAT")
    'what'
    """
    result = []

    for char in word:
        code = ord(char)
        if ASCII_UPPERCASE_START <= code <= ASCII_UPPERCASE_END:
            char = chr(code + ASCII_CASE_OFFSET)
        result.append(char)

    return "".join(result)


def benchmark(
    text: str,
    number: int = 1_000,
    repeats: int = 10,
) -> None:
    """Benchmark the old and new implementations."""
    assert old_lower(text) == new_lower(text)

    old_times = repeat(
        lambda: old_lower(text),
        number=number,
        repeat=repeats,
    )
    new_times = repeat(
        lambda: new_lower(text),
        number=number,
        repeat=repeats,
    )

    old_min = min(old_times)
    old_median = median(old_times)
    old_max = max(old_times)

    new_min = min(new_times)
    new_median = median(new_times)
    new_max = max(new_times)

    speedup = old_median / new_median
    improvement = (1 - new_median / old_median) * 100

    print(f"Input length: {len(text):,}")
    print(f"Iterations:   {number:,}")
    print(f"Repeats:      {repeats}")
    print()
    print(f"Old: min={old_min:.6f}s, median={old_median:.6f}s, " f"max={old_max:.6f}s")
    print(f"New: min={new_min:.6f}s, median={new_median:.6f}s, " f"max={new_max:.6f}s")
    print()
    print(f"Median speedup:     {speedup:.2f}x")
    print(f"Median improvement: {improvement:.2f}%")
    print("-" * 70)


if __name__ == "__main__":
    sample = "Hello WORLD 123! "

    for multiplier in (10, 100, 1_000, 10_000):
        benchmark(sample * multiplier)