ww/test/wcc/944_nonlit_tuple_widen_run.c

/*
 * 944_nonlit_tuple_widen_run — project #116: a NON-LITERAL tuple source
 * widened into a tagged box (cg_widen_tagged_store / cgwidentaggedstore).
 *
 * Pre-#116 only a bare/cast tuple LITERAL (N_TUPLE / N_CAST-of-N_TUPLE)
 * carried a full payload into the union box; every ADDRESSABLE non-literal
 * tuple source — a tuple IDENT var, a slice/array INDEX `tbl[i]`, a DEREF
 * `*p` — hit the `else fatal` ("tuple-typed source shape unwired"), LOUD and
 * IDENTICAL on both stages. This blocked fold-6's
 * `append(charsets[...], charclass_map[cc_idx])` (the INDEX shape).
 *
 * THE FIX (align-BOTH; both stages were loud, so there is NO runtime
 * reference and byte-id is BLIND — #263). A new arm resolves the source
 * ADDRESS through the existing place-address spine (cgplaceaddr — the same
 * one &base[i] / *p / ident use) into SI, then BLOCK-COPIES sum(tuple_eslot)
 * bytes (== the tuple type's table size under the 8B-slot layout) from the
 * source address into the box payload (write_off+8), and stamps the variant
 * tag. The source-tuple-in-memory layout already EQUALS the box-payload
 * layout (same tuple_eslot strides the literal loop fills), so it is a flat
 * address block-copy — no re-slotting, and a tagged element rides over as
 * its already-built box. One mechanism closes the addressable trio.
 *
 * SCOPE (kept loud, out of #116): a CALL/sret tuple result (the tuple sits
 * at the sret address, #40-kin) and struct-field / array-literal-element
 * tuple sources (loud EARLIER at their construction, #49 / #270-1c).
 *
 * Because byte-id is blind here, the RUNTIME read-back is the correctness
 * net (rob's obligation): EACH covered shape (ident / index / deref) builds
 * the box from its non-literal tuple source, match-extracts the variant, and
 * ASSERTS the payload survived — `len(x.0)` proves the str header rode over,
 * `(*x.1)(arg)` indirect-calls the fn-ptr element and checks its result
 * (drew's P3/P4 read-back). The tuple-LITERAL row is the already-green
 * regression guard. All four rows confirmed to LOUD on base da30f10.
 *
 * The read-back deliberately avoids `str !=` (a pre-existing cs!=ww
 * comparison-codegen divergence, rt_streq vs inline CMPQ — unrelated to
 * #116) so the K_RUN byte-id check isolates the widen arm.
 *
 * NNN<950, self-contained (/tmp, no imports), so rule-14's selfhost-sibling
 * race does not apply (903/940/945 precedent).
 */
#include <stdio.h>
#include <stdlib.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;
}

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), cb = fgetc(fb);
		if (ca != cb) { rc = -1; break; }
		if (ca == EOF) break;
	}
	fclose(fa); fclose(fb);
	return rc;
}

#define K_RUN 0	/* build+run both drivers, exit==want, + cs==ww byte-id */

struct row { const char *label; const char *src; int kind; int want; };

static const struct row rows[] = {
	/* control (already green pre-#116): a CAST tuple LITERAL. Regression
	 * guard — the literal arm must keep emitting the same fill. */
	{ "literal",
	  "package main;\n"
	  "fn fa(c: rune) bool = { return c == 'a'; };\n"
	  "type ci = (str, *fn(c: rune) bool);\n"
	  "type u = (rune | ci);\n"
	  "export fn main() i32 = {\n"
	  "	let nm: str = \"ww\";\n"
	  "	let cf: *fn(c: rune) bool = &fa;\n"
	  "	let s: []u = [];\n"
	  "	append(s, ((nm, cf): ci));\n"
	  "	match (s[0]) {\n"
	  "	case let r: rune => { return 90; };\n"
	  "	case let x: ci => {\n"
	  "		if ((len(x.0): i32) != 2) { return 1; };\n"
	  "		if (!(*x.1)('a')) { return 2; };\n"
	  "		return 0;\n"
	  "	};\n"
	  "	};\n"
	  "	return 4;\n"
	  "};\n", K_RUN, 0 },
	/* IDENT: a tuple-typed local var as the widen source. */
	{ "ident",
	  "package main;\n"
	  "fn fb(c: rune) bool = { return c == 'b'; };\n"
	  "type ci = (str, *fn(c: rune) bool);\n"
	  "type u = (rune | ci);\n"
	  "export fn main() i32 = {\n"
	  "	let nm: str = \"zz\";\n"
	  "	let cf: *fn(c: rune) bool = &fb;\n"
	  "	let t: ci = (nm, cf);\n"
	  "	let s: []u = [];\n"
	  "	append(s, t);\n"
	  "	match (s[0]) {\n"
	  "	case let r: rune => { return 90; };\n"
	  "	case let x: ci => {\n"
	  "		if ((len(x.0): i32) != 2) { return 1; };\n"
	  "		if (!(*x.1)('b')) { return 2; };\n"
	  "		if ((*x.1)('a')) { return 3; };\n"
	  "		return 0;\n"
	  "	};\n"
	  "	};\n"
	  "	return 4;\n"
	  "};\n", K_RUN, 0 },
	/* INDEX: `tbl[i]` — the fold-6 shape. The array is filled by tuple-
	 * ident element stores (the foldable construction at HEAD), then the
	 * indexed element is the widen source. */
	{ "index",
	  "package main;\n"
	  "fn fb(c: rune) bool = { return c == 'b'; };\n"
	  "fn fa(c: rune) bool = { return c == 'a'; };\n"
	  "type ci = (str, *fn(c: rune) bool);\n"
	  "type u = (rune | ci);\n"
	  "export fn main() i32 = {\n"
	  "	let n0: str = \"aa\"; let c0: *fn(c: rune) bool = &fa;\n"
	  "	let n1: str = \"zzz\"; let c1: *fn(c: rune) bool = &fb;\n"
	  "	let t0: ci = (n0, c0);\n"
	  "	let t1: ci = (n1, c1);\n"
	  "	let tbl: [2]ci = [];\n"
	  "	tbl[0] = t0;\n"
	  "	tbl[1] = t1;\n"
	  "	let s: []u = [];\n"
	  "	append(s, tbl[1]);\n"
	  "	match (s[0]) {\n"
	  "	case let r: rune => { return 90; };\n"
	  "	case let x: ci => {\n"
	  "		if ((len(x.0): i32) != 3) { return 1; };\n"
	  "		if (!(*x.1)('b')) { return 2; };\n"
	  "		if ((*x.1)('a')) { return 3; };\n"
	  "		return 0;\n"
	  "	};\n"
	  "	};\n"
	  "	return 4;\n"
	  "};\n", K_RUN, 0 },
	/* DEREF: `*p` — a pointer to a tuple var as the widen source. */
	{ "deref",
	  "package main;\n"
	  "fn fa(c: rune) bool = { return c == 'a'; };\n"
	  "type ci = (str, *fn(c: rune) bool);\n"
	  "type u = (rune | ci);\n"
	  "export fn main() i32 = {\n"
	  "	let nm: str = \"qqq\";\n"
	  "	let cf: *fn(c: rune) bool = &fa;\n"
	  "	let t: ci = (nm, cf);\n"
	  "	let p: *ci = &t;\n"
	  "	let s: []u = [];\n"
	  "	append(s, *p);\n"
	  "	match (s[0]) {\n"
	  "	case let r: rune => { return 90; };\n"
	  "	case let x: ci => {\n"
	  "		if ((len(x.0): i32) != 3) { return 1; };\n"
	  "		if (!(*x.1)('a')) { return 2; };\n"
	  "		if ((*x.1)('b')) { return 3; };\n"
	  "		return 0;\n"
	  "	};\n"
	  "	};\n"
	  "	return 4;\n"
	  "};\n", K_RUN, 0 },
};

/* build+run via a driver (ww / ww_ww); returns 0 pass, nonzero fail. */
static int
run_driver(const char *driver, const struct row *r, int i)
{
	char tmpdir[96], src[128], outbin[128], rmcmd[160], cmd[1024];
	snprintf(tmpdir, sizeof tmpdir, "/tmp/ntw_%d_d_%d", getpid(), i);
	mkdir(tmpdir, 0755);
	snprintf(src, sizeof src, "%s/ntw_%d_%d.ww", tmpdir, getpid(), i);
	snprintf(outbin, sizeof outbin, "%s/ntw_%d_%d", tmpdir, getpid(), i);
	snprintf(rmcmd, sizeof rmcmd, "rm -rf %s", tmpdir);

	FILE *f = fopen(src, "wb");
	if (!f) { runwait(rmcmd); return -1; }
	fputs(r->src, f);
	fclose(f);

	snprintf(cmd, sizeof cmd, "%s build -o %s %s >/dev/null 2>&1",
	    driver, outbin, src);
	int brc = runwait(cmd);
	if (brc != 0) {
		fprintf(stderr, "row[%s]: build via %s failed\n",
		    r->label, driver);
		runwait(rmcmd);
		return -1;
	}

	int got = runwait(outbin);

	runwait(rmcmd);
	if (got != r->want) {
		fprintf(stderr, "row[%s]: %s exit %d, want %d\n",
		    r->label, driver, got, r->want);
		return 1;
	}
	return 0;
}

/* cs==ww .s byte-id (rule 10). */
static int
byteid(const char *w6c, const char *w6c_ww, const struct row *r, int i)
{
	char src[96], cs_s[96], ws_s[96], cmd[1024];
	snprintf(src, sizeof src, "/tmp/ntw_bi_%d_%d.ww", getpid(), i);
	snprintf(cs_s, sizeof cs_s, "/tmp/ntw_bi_%d_%d_cs.s", getpid(), i);
	snprintf(ws_s, sizeof ws_s, "/tmp/ntw_bi_%d_%d_ww.s", getpid(), i);

	FILE *f = fopen(src, "wb");
	if (!f) return -1;
	fputs(r->src, f);
	fclose(f);

	int rc = 0;
	/* Single-file package — w6c compiles the .ww source directly (no
	 * imports, no combined.ww amalgam needed); diff the two emissions. */
	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", r->label);
		rc = 1;
	} else {
		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", r->label);
			rc = 1;
		} else if (slurp_eq(cs_s, ws_s) != 0) {
			fprintf(stderr, "row[%s]: cstage/wwstage .s DIFFER "
			    "(#116 non-literal tuple widen regression)\n",
			    r->label);
			rc = 1;
		}
	}
	unlink(src); unlink(cs_s); unlink(ws_s);
	return rc;
}

int
main(void)
{
	const char *bin = getenv("BIN");
	if (!bin) bin = "out/bin";
	char absbin[512];
	if (bin[0] != '/') {
		char cwd[256];
		if (getcwd(cwd, sizeof cwd) == NULL) return 1;
		snprintf(absbin, sizeof absbin, "%s/%s", cwd, bin);
		bin = absbin;
	}

	char cdrv[640], wdrv[640], w6c[640], w6c_ww[640];
	snprintf(cdrv, sizeof cdrv, "%s/ww", bin);
	snprintf(wdrv, sizeof wdrv, "%s/ww_ww", bin);
	snprintf(w6c, sizeof w6c, "%s/w6c", bin);
	snprintf(w6c_ww, sizeof w6c_ww, "%s/w6c_ww", bin);

	struct { const char *name; const char *path; int gated; }
	drivers[] = {
		{ "cstage",  cdrv, 0 },
		{ "wwstage", wdrv, 1 },
		{ NULL, NULL, 0 },
	};

	int n = (int)(sizeof rows / sizeof rows[0]);
	int total = 0, fail = 0;

	for (int d = 0; drivers[d].name; d++) {
		if (drivers[d].gated && access(drivers[d].path, X_OK) != 0) {
			fprintf(stderr, "nonlit_tuple_widen: skip %s (no %s)\n",
			    drivers[d].name, drivers[d].path);
			continue;
		}
		for (int i = 0; i < n; i++) {
			total++;
			if (run_driver(drivers[d].path, &rows[i], i) != 0) fail++;
		}
	}

	if (access(w6c_ww, X_OK) == 0) {
		for (int i = 0; i < n; i++) {
			total++;
			if (byteid(w6c, w6c_ww, &rows[i], i) != 0) fail++;
		}
	}

	if (fail) {
		fprintf(stderr, "nonlit_tuple_widen: %d/%d checks failed\n",
		    fail, total);
		return 1;
	}
	printf("nonlit_tuple_widen: %d/%d ok\n", total, total);
	return 0;
}