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.
 *
 * C5 SWEEP (#10 F2 + #41 FA2/FB1): the arm enumeration leaked FOUR
 * siblings over time (#235 → #19 → F2 → FA2/FB1) — every unhandled
 * operand shape fell to a bare cgexpr fallback returning the slice DATA
 * POINTER as the length, silent and byte-id-blind. The fix replaces the
 * fallback with ONE uniform header-place route (cgplaceaddr → .len at
 * place+8) in BOTH stages; non-place operands (string literal, slicing
 * expr, call result — all previously the same silent ptr-garbage) now
 * die LOUD (rule 7). Rows below pin: len(*p) param + local (FB1),
 * len(*p) on an EMPTY slice (a bare exit-code row can't pin this — the
 * garbage ptr's low byte masks to 0 — hence the branchy discriminator),
 * len(**pp) (chained deref, same resolver spine), len(xs[i].field)
 * (F2), len((*p)[i].field) incl. computed index, len(s.field) +
 * len(p.field) (struct-field cousins), the [N]T-const and ident-str
 * neutrality controls (global and tuple fast-paths have dedicated runs:
 * 797, 903), and reject rows with the exact rule-7 text. All
 * garbage/reject rows verified FAILING at the parent e481cb8 (the
 * per-row garbage exits below cite the d642017 probes; garbage is
 * frame-layout-dependent and drifts between commits — the FAILING
 * status is the pin, not the value).
 */
#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;
}

/* reject != NULL marks a build-reject row: both stages must refuse the
 * source LOUD and the diagnostic must contain that exact text. */
struct row { const char *label; const char *src; int want_exit;
	const char *reject; };

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 },

	/* ---- C5 sweep rows (#10 F2 + #41 FA2/FB1) ---- */

	/* FB1 exact repro: len(*p) through a *[]T PARAM loaded the slice
	 * header's word 0 (the data pointer) as the length — silent
	 * ptr-garbage (exit 48 at d642017), byte-id both stages. */
	{ "deref_param",
	  "package main;\n"
	  "fn n(p: *[]i64) i32 = { return len(*p): i32; };\n"
	  "export fn main() i32 = {\n"
	  "  let xs: []i64 = [10, 20, 30];\n"
	  "  return n(&xs);\n"
	  "};\n", 3, NULL },
	/* FB1, local-ptr variant (exit 64 at d642017). */
	{ "deref_local",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "  let xs: []i64 = [10, 20, 30];\n"
	  "  let p: *[]i64 = &xs;\n"
	  "  return len(*p): i32;\n"
	  "};\n", 3, NULL },
	/* EMPTY-slice deref: the off-by-header bug returns .ptr (nonzero),
	 * len() must say 0. A bare exit row can't pin it — the garbage
	 * ptr's low byte happens to mask to 0 (verified at e481cb8) — so
	 * branch on len()!=0 and return distinct codes. */
	{ "deref_empty",
	  "package main;\n"
	  "fn n(p: *[]i64) i32 = {\n"
	  "  if (len(*p) != 0) { return 9; };\n"
	  "  return 42;\n"
	  "};\n"
	  "export fn main() i32 = {\n"
	  "  let xs: []i64 = [1];\n"
	  "  let ys: []i64 = xs[0:0];\n"
	  "  return n(&ys);\n"
	  "};\n", 42, NULL },
	/* chained deref len(**pp) — the resolver spine must recurse through
	 * BOTH hops (exit 208 garbage at e481cb8). */
	{ "deref_chain",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "  let xs: []i64 = [10, 20, 30];\n"
	  "  let p: *[]i64 = &xs;\n"
	  "  let pp: **[]i64 = &p;\n"
	  "  return len(**pp): i32;\n"
	  "};\n", 3, NULL },
	/* F2 exact repro: len(xs[i].field) — N_DOT over an N_INDEX base
	 * matched no arm (the #235 arm requires an IDENT base) and fell to
	 * the ptr-garbage fallback (exit 147 at d642017). */
	{ "idx_field",
	  "package main;\n"
	  "type S = struct { pad: i64, name: str };\n"
	  "export fn main() i32 = {\n"
	  "  let xs: [2]S = [S{ pad = 1, name = \"a\" }, S{ pad = 2, name = \"bcde\" }];\n"
	  "  return len(xs[1].name): i32;\n"
	  "};\n", 4, NULL },
	/* full deref spine: len((*p)[i].field) (exit 10 at d642017). */
	{ "deref_idx_field",
	  "package main;\n"
	  "type S = struct { pad: i64, name: str };\n"
	  "fn n(p: *[]S, i: i64) i32 = { return len((*p)[i].name): i32; };\n"
	  "export fn main() i32 = {\n"
	  "  let arr: [2]S = [S{ pad = 1, name = \"a\" }, S{ pad = 2, name = \"bcde\" }];\n"
	  "  let xs: []S = arr;\n"
	  "  return n(&xs, 1);\n"
	  "};\n", 4, NULL },
	/* computed index through the spine — cgplaceaddr cgexpr's the index
	 * operand, so i+1 must resolve identically to a constant. */
	{ "deref_idx_field_computed",
	  "package main;\n"
	  "type S = struct { pad: i64, name: str };\n"
	  "fn n(p: *[]S, i: i64) i32 = { return len((*p)[i + 1].name): i32; };\n"
	  "export fn main() i32 = {\n"
	  "  let arr: [2]S = [S{ pad = 1, name = \"a\" }, S{ pad = 2, name = \"bcde\" }];\n"
	  "  let xs: []S = arr;\n"
	  "  return n(&xs, 0);\n"
	  "};\n", 4, NULL },
	/* struct-field cousins: len(s.field) (exit 75 at d642017) and
	 * len(p.field) through a *struct (exit 87 at d642017) — the #235
	 * arm's inner non-tuple fallback was the same ptr-garbage. */
	{ "dot_field",
	  "package main;\n"
	  "type S = struct { pad: i64, name: str };\n"
	  "export fn main() i32 = {\n"
	  "  let s: S = S{ pad = 7, name = \"abc\" };\n"
	  "  return len(s.name): i32;\n"
	  "};\n", 3, NULL },
	{ "ptr_field",
	  "package main;\n"
	  "type S = struct { pad: i64, name: str };\n"
	  "export fn main() i32 = {\n"
	  "  let s: S = S{ pad = 7, name = \"abc\" };\n"
	  "  let p: *S = &s;\n"
	  "  return len(p.name): i32;\n"
	  "};\n", 3, NULL },
	/* neutrality controls — already correct pre-sweep, pin that the
	 * enumerated fast-paths ([N]T const fold, ident str) still hold. */
	{ "neutral_array_const",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "  let a: [5]u8 = [1, 2, 3, 4, 5];\n"
	  "  return len(a): i32;\n"
	  "};\n", 5, NULL },
	{ "neutral_ident_str",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "  let s: str = \"abcd\";\n"
	  "  return len(s): i32;\n"
	  "};\n", 4, NULL },
	/* non-place operands: previously the same SILENT ptr-garbage
	 * (strlit exit 40, slice-expr exit 48, call-result exit 0 at
	 * master); now LOUD per rule 7 in both stages. */
	{ "reject_strlit",
	  "package main;\n"
	  "export fn main() i32 = { return len(\"abc\"): i32; };\n",
	  0, "#10/#41: len() operand shape not place-resolvable (rule-7)" },
	{ "reject_sliceexpr",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "  let xs: []i64 = [10, 20, 30, 40];\n"
	  "  return len(xs[1:3]): i32;\n"
	  "};\n",
	  0, "#10/#41: len() operand shape not place-resolvable (rule-7)" },
	{ "reject_callres",
	  "package main;\n"
	  "fn mk() []i64 = {\n"
	  "  let xs: []i64 = [10, 20, 30];\n"
	  "  return xs;\n"
	  "};\n"
	  "export fn main() i32 = { return len(mk()): i32; };\n",
	  0, "#10/#41: len() operand shape not place-resolvable (rule-7)" },
	{ NULL, NULL, 0, NULL }
};

static int
file_contains(const char *path, const char *needle)
{
	FILE *f = fopen(path, "rb");
	if (!f) return 0;
	char buf[8192];
	size_t got = fread(buf, 1, sizeof buf - 1, f);
	buf[got] = '\0';
	fclose(f);
	return strstr(buf, needle) != NULL;
}

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);

		/* reject rows: BOTH stages must refuse with the exact rule-7
		 * text — a silent accept means the ptr-garbage fallback is
		 * back. */
		if (rows[i].reject) {
			char errf[64], cmd2[2048];
			int bad = 0;
			snprintf(errf, sizeof errf, "/tmp/wwli_%d_%d.err",
			    getpid(), i);
			snprintf(cmd2, sizeof cmd2, "%s -o /dev/null %s 2>%s",
			    w6c, src, errf);
			if (runwait(cmd2) == 0) {
				fprintf(stderr, "row[%s]: w6c ACCEPTED a "
				    "reject row\n", rows[i].label);
				bad = 1;
			} else if (!file_contains(errf, rows[i].reject)) {
				fprintf(stderr, "row[%s]: w6c rejected but "
				    "without the rule-7 text\n",
				    rows[i].label);
				bad = 1;
			}
			snprintf(cmd2, sizeof cmd2, "%s -o /dev/null %s 2>%s",
			    w6c_ww, src, errf);
			if (runwait(cmd2) == 0) {
				fprintf(stderr, "row[%s]: w6c_ww ACCEPTED a "
				    "reject row\n", rows[i].label);
				bad = 1;
			} else if (!file_contains(errf, rows[i].reject)) {
				fprintf(stderr, "row[%s]: w6c_ww rejected but "
				    "without the rule-7 text\n",
				    rows[i].label);
				bad = 1;
			}
			if (bad) fail++;
			unlink(errf); unlink(src);
			continue;
		}

		/* (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;
}