el/lang/tests/native/test_lexer_scaling.el

import "../../runtime/eltest.el"
import "../../runtime/elbench.el"

// test_lexer_scaling.el — THE ARMED GATE.
//
// This is the regression test that would have caught el #132.
//
// #132 was a strlen() inside str_char_code() and str_slice(). The lexer walks
// source one character at a time, so every character access rescanned the whole
// remaining input: O(n) per character over n characters = O(n^2). It shipped for
// months. It was found by a geometric sweep, not by reading code.
//
// So this test IS a geometric sweep. It scans a string of length n, character by
// character, at four doubling sizes, and asserts the cost is linear. If anyone
// reintroduces a per-character rescan — in str_char_code, in str_slice, in any
// accessor the lexer leans on — the measured curve becomes O(n^2) and this fails.
//
// The value is in it being ARMED, not in it currently failing. It passes today
// because #132 is fixed. That is the correct state for a regression gate.
//
// Note the deliberate `let c: Int = str_char_code(...)` binding in the scan loop.
// Inlining it as `total + str_char_code(s, i)` lowers to el_str_concat() on
// integers — the Plus arm of the operator-typing family, still open at the time
// of writing. Binding first is the safe form.

// _mk_string — build a string of length >= n by DOUBLING.
//
// Deliberately not `s = s + "x"` n times: that is itself quadratic in bytes and
// would contaminate the very measurement this test exists to take. Doubling
// allocates ~2n total.
fn _mk_string(n: Int) -> String {
    let s: String = "abcdefgh"
    while str_len(s) < n {
        let s = s + s
    }
    return s
}

// _scan — walk the string one character at a time, REPS times.
//
// This is the lexer's access pattern reduced to its essential shape. The
// repetitions lift the measurement clear of timer resolution; without them the
// smaller sizes land in noise and the classifier correctly reports
// INDETERMINATE rather than guessing.
fn _scan(s: String, n: Int, reps: Int) -> Int {
    let total: Int = 0
    let r: Int = 0
    while r < reps {
        let i: Int = 0
        while i < n {
            let c: Int = str_char_code(s, i)
            let total = total + c
            let i = i + 1
        }
        let r = r + 1
    }
    return total
}

// _measure_scan — microseconds for a full scan sweep point.
fn _measure_scan(n: Int, reps: Int) -> Int {
    let s: String = _mk_string(n)
    // WARMUP, discarded. Without it the small-n end of the sweep is dominated
    // by cold caches and reads as superlinear on genuinely linear work --
    // measured ratios 3.37 2.92 1.76 1.65 on exactly this workload.
    let w: Int = _scan(s, n, 2)
    let wj: Int = el_black_box(w)
    let t0: Int = el_now_instant()
    let got: Int = _scan(s, n, reps)
    let t1: Int = el_now_instant()
    // Feed the result through the barrier so the scan cannot be elided.
    let sink: Int = el_black_box(got)
    if sink == 0 { println("") }
    return (t1 - t0) / 1000
}

fn _series4(a: Int, b: Int, c: Int, d: Int) -> [Int] {
    let l: [Int] = native_list_empty()
    let l = native_list_append(l, a)
    let l = native_list_append(l, b)
    let l = native_list_append(l, c)
    let l = native_list_append(l, d)
    return l
}

test "character scan is LINEAR in time -- regression gate for el #132" {
    let reps: Int = 40
    let t1: Int = _measure_scan(16384, reps)
    let t2: Int = _measure_scan(32768, reps)
    let t3: Int = _measure_scan(65536, reps)
    let t4: Int = _measure_scan(131072, reps)
    let series: [Int] = _series4(t1, t2, t3, t4)

    let verdict: Int = elb_gate(series, 2, 50)
    let measured: Int = elb_measured_curve(series, 50)

    // Report the actual numbers regardless of outcome. A gate that fires
    // without showing its evidence is just an assertion.
    println("      scan us: " + int_to_str(t1) + " " + int_to_str(t2) + " "
        + int_to_str(t3) + " " + int_to_str(t4)
        + "  -> " + elb_curve_name(measured) + " [" + elb_verdict_name(verdict) + "]")

    // PASS (0) or BETTER (4) are both acceptable. FAIL (1) means someone
    // reintroduced superlinear per-character cost. REFUSED (3) or
    // INDETERMINATE (2) mean the measurement is untrustworthy -- which is
    // also a failure of this test, deliberately: a gate that cannot measure
    // must not report success.
    assert verdict == 0 || verdict == 4, "character scan must measure O(n) or better"
}

test "string building by doubling stays linear in allocated bytes" {
    let b1: Int = el_alloc_bytes()
    let s1: String = _mk_string(8192)
    let b2: Int = el_alloc_bytes()
    let s2: String = _mk_string(16384)
    let b3: Int = el_alloc_bytes()
    let s3: String = _mk_string(32768)
    let b4: Int = el_alloc_bytes()
    let s4: String = _mk_string(65536)
    let b5: Int = el_alloc_bytes()

    let series: [Int] = _series4(b2 - b1, b3 - b2, b4 - b3, b5 - b4)
    let verdict: Int = elb_gate(series, 2, 1000)
    let measured: Int = elb_measured_curve(series, 1000)
    println("      bytes: " + int_to_str(b2 - b1) + " " + int_to_str(b3 - b2) + " "
        + int_to_str(b4 - b3) + " " + int_to_str(b5 - b4)
        + "  -> " + elb_curve_name(measured) + " [" + elb_verdict_name(verdict) + "]")

    assert verdict == 0 || verdict == 4, "doubling build must be O(n) in bytes"
    assert str_len(s4) >= 65536, "final string reached the requested size"
}

// _scan_quadratic — a DELIBERATELY quadratic scan: for each position, rescan
// from the start. This is precisely what el #132 did — strlen() from offset 0
// on every character access — reproduced here so the gate can be proven to
// FIRE, not merely to pass on healthy code. An unproven gate is decoration.
fn _scan_quadratic(s: String, n: Int) -> Int {
    let total: Int = 0
    let i: Int = 0
    while i < n {
        let j: Int = 0
        while j < i {
            let c: Int = str_char_code(s, j)
            let total = total + c
            let j = j + 1
        }
        let i = i + 1
    }
    return total
}

fn _measure_quadratic(n: Int) -> Int {
    let s: String = _mk_string(n)
    let w: Int = _scan_quadratic(s, 64)
    let wj: Int = el_black_box(w)
    let t0: Int = el_now_instant()
    let got: Int = _scan_quadratic(s, n)
    let t1: Int = el_now_instant()
    let sink: Int = el_black_box(got)
    return (t1 - t0) / 1000
}

test "the gate FIRES on a live quadratic scan -- proves it is armed" {
    let q1: Int = _measure_quadratic(1024)
    let q2: Int = _measure_quadratic(2048)
    let q3: Int = _measure_quadratic(4096)
    let q4: Int = _measure_quadratic(8192)
    let series: [Int] = _series4(q1, q2, q3, q4)

    let verdict: Int = elb_gate(series, 2, 50)
    let measured: Int = elb_measured_curve(series, 50)
    println("      quad us: " + int_to_str(q1) + " " + int_to_str(q2) + " "
        + int_to_str(q3) + " " + int_to_str(q4)
        + "  -> " + elb_curve_name(measured) + " [" + elb_verdict_name(verdict) + "]")

    assert measured == 4, "a rescan-from-zero workload must classify O(n^2)"
    assert verdict == 1, "declared O(n) against measured O(n^2) must FAIL the gate"
}