java-topology/defects/raylib/unit/test_raylib_0001.py

"""
Unit test for raylib-0001: GetGlyphIndex O(T×G) linear scan per character.

Tests:
1. Correctness: both implementations return the same glyph index
2. Performance: O(G) linear scan vs O(1) hash map lookup ratio
"""
import time
import random


# ---- Minimal glyph stub ----

class GlyphInfo:
    def __init__(self, codepoint, advance_x=8):
        self.value = codepoint
        self.advance_x = advance_x


def make_font(codepoints):
    """Build a fake Font-like object with glyphs in arbitrary order."""
    glyphs = [GlyphInfo(cp) for cp in codepoints]
    random.shuffle(glyphs)
    return glyphs


# ---- BEFORE: defective implementation (linear scan) ----

def get_glyph_index_before(glyphs, codepoint):
    """O(G) linear scan — mirrors raylib src/rtext.c GetGlyphIndex."""
    index = 0
    fallback_index = 0
    for i, g in enumerate(glyphs):
        if g.value == 63:   # '?' fallback
            fallback_index = i
        if g.value == codepoint:
            return i
    if glyphs[0].value != codepoint:
        return fallback_index
    return index


def measure_text_before(glyphs, text_codepoints):
    """Simulate MeasureTextEx: calls get_glyph_index_before per character."""
    total = 0
    for cp in text_codepoints:
        idx = get_glyph_index_before(glyphs, cp)
        total += glyphs[idx].advance_x
    return total


# ---- AFTER: fixed implementation (hash map) ----

def build_glyph_hashmap(glyphs):
    """Build codepoint→index hash map once at font load time."""
    return {g.value: i for i, g in enumerate(glyphs)}


def get_glyph_index_after(glyph_map, glyphs, codepoint):
    """O(1) hash map lookup."""
    if codepoint in glyph_map:
        return glyph_map[codepoint]
    # fallback to '?'
    if 63 in glyph_map:
        return glyph_map[63]
    return 0


def measure_text_after(glyph_map, glyphs, text_codepoints):
    """Simulate MeasureTextEx with hash map — O(T) total."""
    total = 0
    for cp in text_codepoints:
        idx = get_glyph_index_after(glyph_map, glyphs, cp)
        total += glyphs[idx].advance_x
    return total


# ---- Tests ----

def test_correctness_ascii():
    """Both implementations return the same index for ASCII glyphs."""
    codepoints = list(range(32, 127))  # 95 ASCII glyphs
    glyphs = make_font(codepoints)
    glyph_map = build_glyph_hashmap(glyphs)
    for cp in codepoints:
        before = get_glyph_index_before(glyphs, cp)
        after = get_glyph_index_after(glyph_map, glyphs, cp)
        assert before == after, (
            f"Mismatch for codepoint {cp}: before={before} after={after}"
        )
    print("PASS test_correctness_ascii")


def test_correctness_unicode():
    """Both implementations agree on a mixed Unicode glyph set."""
    codepoints = list(range(32, 127)) + list(range(0x4E00, 0x4E00 + 200))  # ASCII + CJK
    glyphs = make_font(codepoints)
    glyph_map = build_glyph_hashmap(glyphs)
    sample = random.sample(codepoints, 50)
    for cp in sample:
        before = get_glyph_index_before(glyphs, cp)
        after = get_glyph_index_after(glyph_map, glyphs, cp)
        assert before == after, (
            f"Mismatch for codepoint {cp}: before={before} after={after}"
        )
    print("PASS test_correctness_unicode")


def test_correctness_measure_text():
    """MeasureText returns the same width before and after the fix."""
    codepoints = list(range(32, 127))
    glyphs = make_font(codepoints)
    glyph_map = build_glyph_hashmap(glyphs)
    text = [ord(c) for c in "Hello, World! raylib text rendering."]
    w_before = measure_text_before(glyphs, text)
    w_after = measure_text_after(glyph_map, glyphs, text)
    assert w_before == w_after, f"Width mismatch: {w_before} vs {w_after}"
    print("PASS test_correctness_measure_text")


def test_performance_ratio():
    """O(G) linear scan is dramatically slower than O(1) hash lookup."""
    G = 1000   # glyph count (extended Latin + symbols)
    T = 500    # characters per render call
    ITERS = 100

    codepoints = list(range(32, 32 + G))
    glyphs = make_font(codepoints)
    glyph_map = build_glyph_hashmap(glyphs)
    text = [codepoints[i % len(codepoints)] for i in range(T)]

    t0 = time.perf_counter()
    for _ in range(ITERS):
        measure_text_before(glyphs, text)
    t_before = time.perf_counter() - t0

    t0 = time.perf_counter()
    for _ in range(ITERS):
        measure_text_after(glyph_map, glyphs, text)
    t_after = time.perf_counter() - t0

    ratio = t_before / t_after if t_after > 0 else float('inf')
    print(f"PERF raylib-0001: G={G} T={T} ITERS={ITERS} "
          f"before={t_before*1000:.1f}ms after={t_after*1000:.1f}ms ratio={ratio:.1f}x")

    assert ratio >= 50, (
        f"Expected >= 50x speedup for G={G} T={T}, got {ratio:.1f}x"
    )
    print("PASS test_performance_ratio")


def test_performance_large_unicode_font():
    """With a large Unicode font (G=4000) the pathology is severe."""
    G = 4000
    T = 200
    ITERS = 20

    codepoints = list(range(0x4E00, 0x4E00 + G))  # CJK range
    glyphs = make_font(codepoints)
    glyph_map = build_glyph_hashmap(glyphs)
    text = [codepoints[i % len(codepoints)] for i in range(T)]

    t0 = time.perf_counter()
    for _ in range(ITERS):
        measure_text_before(glyphs, text)
    t_before = time.perf_counter() - t0

    t0 = time.perf_counter()
    for _ in range(ITERS):
        measure_text_after(glyph_map, glyphs, text)
    t_after = time.perf_counter() - t0

    ratio = t_before / t_after if t_after > 0 else float('inf')
    print(f"PERF raylib-0001 (unicode): G={G} T={T} ITERS={ITERS} "
          f"before={t_before*1000:.1f}ms after={t_after*1000:.1f}ms ratio={ratio:.1f}x")

    assert ratio >= 500, (
        f"Expected >= 500x speedup for G={G} T={T}, got {ratio:.1f}x"
    )
    print("PASS test_performance_large_unicode_font")


if __name__ == "__main__":
    random.seed(42)
    test_correctness_ascii()
    test_correctness_unicode()
    test_correctness_measure_text()
    test_performance_ratio()
    test_performance_large_unicode_font()
    print("\nAll raylib-0001 tests PASSED")