ww/test/wcc/835_nested_union_int_box.c

/*
 * 835_nested_union_int_box — two reject-align fixes in the nested-union /
 * widen-subset family. Both close SILENT wwstage miscompiles by aligning
 * ww DOWN to cstage's existing loud.
 *
 * #23 (drew spec .ai/drew-23-spec.md) — a bare untyped-int return/assign
 * into a tagged union with NO DIRECT variant able to hold an int (the int
 * is reachable only via a NESTED union, or no slot exists at all). ww's
 * isuntypedint tagged sub-loop fell through to a permissive `*confident=
 * false; return true;` so the caller never flagged it — ww silently built
 * a tag=0/payload box with no inner-tag wrapper (malformed). The fix:
 * confident-reject when no direct variant is numeric-or-enum (mirror
 * cstage type.c:343 `return 0`), routing through errnotassign. An ENUM
 * variant is kept ACCEPTED (new N_TENUM check, mirrors cstage type_isnum
 * (enum)=true) — A3 is the trap: dropping it would flip an enum-variant
 * union to reject while cstage accepts. wwstage-ONLY; check.c unchanged.
 *
 * S1 / #35 (ken census .ai/miscompile-census.md) — a widen-SUBSET cast in
 * a tagged construct: `return true: inner` where inner=(int|bool) boxed
 * into outer=(int|bool|str). The cast target is a TAGGED union that is NOT
 * dst, and the inner-variant tag is never remapped to dst's index, so ww
 * cgen's scalar arm emitted tag=0 — running the int arm on a bool value
 * (census S1 returned 70, expected 11). cstage loud-stops at cgen.c:2721-
 * 2723 (#35). wwstage gains the twin in cgwidentaggedstorebp (cgenutil.ww).
 * A 2ND-VARIANT value (bool) is mandatory: `5:inner` is benign (int is
 * variant 0 in both, tag 0 coincidentally right). Faithful inner->outer
 * tag remap = the #23/#40 widen-subset feature, deferred post-CSP.
 *
 *   neg row      | shape                                          | gate
 *   -------------+------------------------------------------------+------
 *   R1_nested    | inner=(int|bool); outer=(inner|str); ret 5     | FAIL
 *   R2_noslot    | u=(str|bool); ret 5                            | FAIL
 *   R3_struct    | A=struct{v:int}; u=(A|str); ret 5             | FAIL
 *   S1_subcast   | return true: inner (inner=(int|bool)->outer)   | FAIL
 *
 *   pos row      | shape                                          | want
 *   -------------+------------------------------------------------+------
 *   A1_direct    | u=(int|str); ret 5; match int -> n             | 5
 *   A2_aliased   | myint=int; u=(myint|str); ret 5                | 0
 *   A3_enum      | col=enum{RED,GREEN}; u=(col|str); ret 5 [trap] | 0
 *   A4_unionsrc  | outer=(inner|str); mk(x:inner) outer = x       | 0
 *   A5_subset    | sub=(int|uint); sup=(int|uint|str); ret x      | 0
 *
 * Diagnostic TEXT is byte-id-blind (#23 routes through errnotassign "not
 * assignable"; S1 emits the #35 line); both stages REJECT and emit no asm.
 * selfhost has no such construct, so 990-997 byte-id is untouched.
 */
#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;
}

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

static const struct row rows[] = {
	/* A1 — direct numeric variant; live runtime proof the accept path
	 * still builds a correct box (match int -> return 5). */
	{ "A1_direct",
	  "package main;\n"
	  "type u = (int | str);\n"
	  "fn mk() u = { return 5; };\n"
	  "export fn main() i32 = {\n"
	  "\tlet v = mk();\n"
	  "\tmatch (v) {\n"
	  "\tcase let n: int => return n: i32;\n"
	  "\tcase str => return 1;\n"
	  "\t};\n"
	  "\treturn 9;\n"
	  "};\n",
	  5 },

	/* A2 — aliased numeric variant (resolvealias -> int). Compile-only:
	 * main returns 0; the accept is proven by the build succeeding. */
	{ "A2_aliased",
	  "package main;\n"
	  "type myint = int;\n"
	  "type u = (myint | str);\n"
	  "fn mk() u = { return 5; };\n"
	  "export fn main() i32 = { return 0; };\n",
	  0 },

	/* A3 — enum variant (the trap): the N_TENUM accept keeps this legal,
	 * mirroring cstage type_isnum(enum). Compile-only. */
	{ "A3_enum",
	  "package main;\n"
	  "type col = enum { RED, GREEN };\n"
	  "type u = (col | str);\n"
	  "fn mk() u = { return 5; };\n"
	  "export fn main() i32 = { return 0; };\n",
	  0 },

	/* A4 — src is a UNION (inner), not an untyped int -> never enters the
	 * int arm; tagged->tagged direct-variant accept. Compile-only. */
	{ "A4_unionsrc",
	  "package main;\n"
	  "type inner = (int | bool);\n"
	  "type outer = (inner | str);\n"
	  "fn mk(x: inner) outer = { return x; };\n"
	  "export fn main() i32 = { return 0; };\n",
	  0 },

	/* A5 — proper-subset union widen, src union. Compile-only. */
	{ "A5_subset",
	  "package main;\n"
	  "type sub = (int | uint);\n"
	  "type sup = (int | uint | str);\n"
	  "fn w(x: sub) sup = { return x; };\n"
	  "export fn main() i32 = { return 0; };\n",
	  0 },
};

/* Each neg must FAIL the build on both stages (loud reject). */
static const char *neg[] = {
	/* R1 — #23 canonical: int reachable only via a NESTED union. */
	"package main;\n"
	"type inner = (int | bool);\n"
	"type outer = (inner | str);\n"
	"fn mk() outer = { return 5; };\n"
	"export fn main() i32 = { return 0; };\n",
	/* R2 — no slot for an int at all (same fallthrough). */
	"package main;\n"
	"type u = (str | bool);\n"
	"fn mk() u = { return 5; };\n"
	"export fn main() i32 = { return 0; };\n",
	/* R3 — int fits no variant (struct | str). */
	"package main;\n"
	"type A = struct { v: int };\n"
	"type u = (A | str);\n"
	"fn mk() u = { return 5; };\n"
	"export fn main() i32 = { return 0; };\n",
	/* S1 / #35 — widen-SUBSET cast in a RETURN, 2nd-variant (bool) value
	 * (census sx4). ww cgen's cgreturn formerly skipped the widener for an
	 * N_CAST-tagged source (needswiden=false) -> plain cgexpr -> tag=0
	 * SILENT (ran the int arm -> 70, want 11). Now the genuine-widening
	 * (ru!=fnret) needswiden arm routes it through cgwidentaggedstore ->
	 * the #35 widen-subset loud-stop. Both stages reject. */
	"package main;\n"
	"type inner = (int | bool);\n"
	"type outer = (int | bool | str);\n"
	"fn mk() outer = { return true: inner; };\n"
	"export fn main() i32 = {\n"
	"\tlet v = mk();\n"
	"\tmatch (v) {\n"
	"\tcase let n: int => return 70;\n"
	"\tcase let b: bool => return 11;\n"
	"\tcase let s: str => return 22;\n"
	"\t};\n"
	"\treturn 99;\n"
	"};\n",
};

static int
run_driver(const char *driver, const struct row *r, int i)
{
	char tmpdir[64], src[128], outbin[128], rmcmd[160], cmd[1024];
	snprintf(tmpdir, sizeof tmpdir, "/tmp/nui_%d_d_%d", getpid(), i);
	mkdir(tmpdir, 0755);
	snprintf(src, sizeof src, "%s/nui_%d_%d.ww", tmpdir, getpid(), i);
	snprintf(outbin, sizeof outbin, "%s/nui_%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 2>/dev/null",
	    driver, outbin, src);
	if (runwait(cmd) != 0) {
		fprintf(stderr, "row[%s]: build via %s failed\n",
		    r->label, driver);
		runwait(rmcmd);
		return -1;
	}

	int got = runwait(outbin);

	runwait(rmcmd);
	return got;
}

/* build_should_fail — the construct must error on `driver`; returns 0 when
 * the build correctly FAILS, non-zero when it wrongly succeeded. */
static int
build_should_fail(const char *driver, const char *src, int i)
{
	char tmpdir[64], s[128], outbin[128], rmcmd[160], cmd[1024];
	snprintf(tmpdir, sizeof tmpdir, "/tmp/nuin_%d_d_%d", getpid(), i);
	mkdir(tmpdir, 0755);
	snprintf(s, sizeof s, "%s/nuin_%d_%d.ww", tmpdir, getpid(), i);
	snprintf(outbin, sizeof outbin, "%s/nuin_%d_%d", tmpdir, getpid(), i);
	snprintf(rmcmd, sizeof rmcmd, "rm -rf %s", tmpdir);

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

	snprintf(cmd, sizeof cmd, "%s build -o %s %s 2>/dev/null",
	    driver, outbin, s);
	int rc = runwait(cmd);
	runwait(rmcmd);
	return rc == 0 ? -1 : 0;	/* build must NOT succeed */
}

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 cdrv[1024];
	snprintf(cdrv, sizeof cdrv, "%s/ww", bin);
	char wdrv[1024];
	snprintf(wdrv, sizeof wdrv, "%s/ww_ww", bin);

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

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

	for (int d = 0; drivers[d].name; d++) {
		if (drivers[d].gated_on_existence
		    && access(drivers[d].path, X_OK) != 0) {
			fprintf(stderr, "nested_union_int_box: skip %s (no %s)\n",
			    drivers[d].name, drivers[d].path);
			continue;
		}
		for (int i = 0; i < n; i++) {
			int got = run_driver(drivers[d].path, &rows[i], i);
			total++;
			if (got != rows[i].want) {
				fprintf(stderr,
				    "nested_union_int_box[%s][%s]: exit=%d want=%d\n",
				    drivers[d].name, rows[i].label,
				    got, rows[i].want);
				fail++;
			}
		}
		for (int i = 0; i < nn; i++) {
			total++;
			if (build_should_fail(drivers[d].path, neg[i],
			    100 + i) != 0) {
				fprintf(stderr,
				    "nested_union_int_box[%s][neg%d]: built ok, "
				    "expected a loud reject\n",
				    drivers[d].name, i);
				fail++;
			}
		}
	}

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