ww/test/wcc/802_lenidx_run.c

/*
 * 802_lenidx_run — BUG #19. Runtime + cs==ww byte-id net for the
 * `len()` builtin applied to an INDEXED str/slice element (`len(xs[i])`).
 *
 * THE BUG (cstage == wwstage, BOTH wrong — shared gap, NOT rule-10):
 *   `len(t[i])` over a `[N]str` / `[]str` returned the element's .ptr,
 *   not its length. The len() builtin (cgen.c / cgenexpr.ww) had arms for
 *   an N_IDENT slice/str operand (.len at BP+off+8), a tuple-element N_DOT
 *   (#235), and a whole TY_ARRAY (→ alen) — but NOT an N_INDEX element.
 *   So `len(xs[i])` fell to the bare `cgexpr(arg)` fallback, which loads
 *   the str/slice element header via cgslicehdr leaving AX=.ptr, BX=.len,
 *   CX=.cap — and len() then returned AX (the ptr) AS the length. Same
 *   family as #14 (literal `.len` returned ptr) and #18 (shared static-init
 *   gap). byte-id was BLIND: no bootstrap source uses len(indexed-element)
 *   — the corpus indexes-then-reads .len explicitly or hardcodes lengths.
 *   CONTRAST (controls, all already correct): `t[i].len` pseudo-field,
 *   `t[i].ptr`, and scalar `len(s)` over a bare str variable.
 *
 * THE FIX (#19): add an N_INDEX arm to the len() builtin in BOTH stages —
 * `cgexpr(arg)` to materialise the element, then `MOVQ BX, AX` to shuffle
 * the len word (already in BX after cgslicehdr) into the result reg. The
 * same MOVQ BX,AX shape as #14's `.len` pseudo-field fix. Covers str AND
 * slice elements (both are 24B headers loaded by cgslicehdr).
 *
 * EACH ROW CARRIES BOTH DIMENSIONS (801 model):
 *   (a) cstage `ww build` + run, asserting the exit — pins that the
 *       converged asm is runtime-correct (real lengths, not ptr bytes).
 *   (b) w6c vs w6c_ww `.s` cmp — FAILS if the stages diverge (rule-10).
 *
 * GATE POLARITY: must stay GREEN. A wrong exit means len(indexed-element)
 * regressed back to returning the ptr; a byte-id FAIL means the stages
 * diverged.
 *
 * SCOPE NOTE: the []T (slice-of-slice) ELEMENT len shares the identical
 * codegen path (cgslicehdr → BX=len → MOVQ BX,AX) and is byte-id-clean in
 * isolation, but a clean runtime row for it is blocked by a SEPARATE
 * pre-existing bug — the `[2][]u8` array-literal → slice coercion emits a
 * divergent frame offset (cstage -24(BP) vs wwstage -40(BP)). That gap is
 * unrelated to len() (it reproduces with the `.len` pseudo-field too) and
 * is filed separately; these rows stay on str elements to avoid it.
 */
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <sys/stat.h>
#include <sys/wait.h>

static int
runwait(const char *cmd)
{
	int rc = system(cmd);
	if (rc == -1) return -1;
	if (WIFEXITED(rc)) return WEXITSTATUS(rc);
	return -1;
}

struct row { const char *label; const char *src; int want_exit; };

static const struct row rows[] = {
	/* the exact #19 repro: a [3]str table, len(t[1]) == 3. Pre-fix this
	 * returned a ptr low-byte (58), not 3. */
	{ "arrtab_mid",
	  "package main;\n"
	  "let t: [3]str = [\"a\", \"bcd\", \"\"];\n"
	  "export fn main() i32 = { return len(t[1]): i32; };\n", 3 },
	/* empty-string element edge: len(t[2]) == 0 (a ptr would be nonzero). */
	{ "arrtab_empty",
	  "package main;\n"
	  "let t: [3]str = [\"a\", \"bcd\", \"\"];\n"
	  "export fn main() i32 = { return len(t[2]): i32; };\n", 0 },
	/* first element: len(t[0]) == 1 — guards an off-by-one in the index
	 * scale (a ptr or the wrong element would not be 1). */
	{ "arrtab_first",
	  "package main;\n"
	  "let t: [3]str = [\"a\", \"bcd\", \"\"];\n"
	  "export fn main() i32 = { return len(t[0]): i32; };\n", 1 },
	/* []str slice parameter — the callee-side shape: len(xs[i]) over a
	 * slice arg, summing all three lengths (1 + 3 + 0 == 4). */
	{ "slice_param_sum",
	  "package main;\n"
	  "fn slen(xs: []str, i: i64) i32 = { return len(xs[i]): i32; };\n"
	  "export fn main() i32 = {\n"
	  "  let arr: [3]str = [\"a\", \"bcd\", \"\"];\n"
	  "  let xs: []str = arr;\n"
	  "  return slen(xs, 0) + slen(xs, 1) + slen(xs, 2);\n"
	  "};\n", 4 },
	/* NEGATIVE CONTROL: the `.len` pseudo-field on the same indexed
	 * element must agree with len() (both == 3), AND `.ptr` must still
	 * deref to the first byte ('b' == 98) — proving the fix left the
	 * already-correct .len/.ptr field paths untouched. Returns 3 only if
	 * len()==.len AND *.ptr=='b'. */
	{ "neg_control_field_agree",
	  "package main;\n"
	  "let t: [3]str = [\"a\", \"bcd\", \"\"];\n"
	  "export fn main() i32 = {\n"
	  "  if (len(t[1]) != t[1].len) { return 91; };\n"
	  "  let p: *u8 = t[1].ptr;\n"
	  "  if (*p != 'b') { return 92; };\n"
	  "  return len(t[1]): i32;\n"
	  "};\n", 3 },
	{ NULL, NULL, 0 }
};

static int
slurp_eq(const char *a, const char *b)
{
	FILE *fa = fopen(a, "rb");
	FILE *fb = fopen(b, "rb");
	if (!fa || !fb) { if (fa) fclose(fa); if (fb) fclose(fb); return -1; }
	int rc = 0;
	for (;;) {
		int ca = fgetc(fa);
		int cb = fgetc(fb);
		if (ca != cb) { rc = -1; break; }
		if (ca == EOF) break;
	}
	fclose(fa); fclose(fb);
	return rc;
}

int
main(void)
{
	const char *bin = getenv("BIN");
	if (!bin) bin = "out/bin";
	char absbin[1024];
	if (bin[0] != '/') {
		char cwd[1024];
		if (getcwd(cwd, sizeof cwd) == NULL) return 1;
		snprintf(absbin, sizeof absbin, "%s/%s", cwd, bin);
		bin = absbin;
	}

	char w6c[1100], w6c_ww[1100];
	snprintf(w6c, sizeof w6c, "%s/w6c", bin);
	snprintf(w6c_ww, sizeof w6c_ww, "%s/w6c_ww", bin);
	if (access(w6c_ww, X_OK) != 0) {
		fprintf(stderr, "lenidx: w6c_ww missing — cannot run the "
		    "cs==ww byte-id gate\n");
		return 1;
	}

	int n = 0, fail = 0;
	for (int i = 0; rows[i].src; i++, n++) {
		char src[64];
		snprintf(src, sizeof src, "/tmp/wwli_%d_%d.ww", getpid(), i);
		FILE *f = fopen(src, "wb");
		if (f == NULL) { fail++; continue; }
		fputs(rows[i].src, f);
		fclose(f);

		/* (a) cstage build + run in a scratch dir. */
		char tmpdir[64];
		snprintf(tmpdir, sizeof tmpdir, "/tmp/wwli_%d_d_%d", getpid(), i);
		mkdir(tmpdir, 0755);

		char cmd[2048];
		snprintf(cmd, sizeof cmd, "cd %s && %s/ww build %s",
		    tmpdir, bin, src);
		if (runwait(cmd) != 0) {
			fprintf(stderr, "row[%s]: cstage build failed\n",
			    rows[i].label);
			fail++;
			unlink(src); rmdir(tmpdir);
			continue;
		}

		char outbin[128];
		const char *base = strrchr(src, '/');
		base = base ? base + 1 : src;
		snprintf(outbin, sizeof outbin, "%s/%s", tmpdir, base);
		char *dot = strrchr(outbin, '.');
		if (dot && strcmp(dot, ".ww") == 0) *dot = '\0';

		int got = runwait(outbin);
		if (got != rows[i].want_exit) {
			fprintf(stderr, "row[%s]: cstage exit %d, want %d\n",
			    rows[i].label, got, rows[i].want_exit);
			fail++;
		}
		unlink(outbin); rmdir(tmpdir);

		/* (b) cs==ww byte-id gate. */
		char cs_s[64], ws_s[64];
		snprintf(cs_s, sizeof cs_s, "/tmp/wwli_%d_%d_cs.s", getpid(), i);
		snprintf(ws_s, sizeof ws_s, "/tmp/wwli_%d_%d_ww.s", getpid(), i);

		snprintf(cmd, sizeof cmd, "%s -o %s %s 2>/dev/null", w6c, cs_s, src);
		if (runwait(cmd) != 0) {
			fprintf(stderr, "row[%s]: w6c failed\n", rows[i].label);
			fail++; unlink(src); continue;
		}
		snprintf(cmd, sizeof cmd, "%s -o %s %s 2>/dev/null",
		    w6c_ww, ws_s, src);
		if (runwait(cmd) != 0) {
			fprintf(stderr, "row[%s]: w6c_ww failed\n", rows[i].label);
			fail++; unlink(src); unlink(cs_s); continue;
		}
		if (slurp_eq(cs_s, ws_s) != 0) {
			fprintf(stderr, "row[%s]: cstage/wwstage .s DIFFER "
			    "(rule-10 byte-id violation)\n", rows[i].label);
			fail++;
		}
		unlink(src); unlink(cs_s); unlink(ws_s);
	}

	if (fail) {
		fprintf(stderr, "%d/%d lenidx tests failed\n", fail, n);
		return 1;
	}
	printf("lenidx: %d/%d ok (cstage run + cs==ww byte-id)\n", n, n);
	return 0;
}