/*
 * 949_valstruct_subsize_run — runtime + byte-id net for #254: a sub-8
 * (non-8-multiple) nested value-struct must size its zero-init extent
 * from the type table's natural ABI size (cstage lu->size), NOT the
 * slot-padded register-struct width.
 *
 * Root: wwstage conflated SLOT-size (round-to-8, for frame layout) with
 * ABI-size (true). A nested value-struct field was sized via fieldsize()
 * (cgenutil.ww TY_STRUCT -> ti.slotsize = 8), poisoning structabisize +
 * registerstruct si.totsize to 8 for a struct whose true ABI size is 4.
 * Two emission sites then over-sized:
 *   D1 (local): cglet zsz = structabisize = 8 hit the `zsz == 8` zero
 *       arm (cgenstmt.ww #213) -> a stray `MOVQ $0, off(BP)` that cstage
 *       (ABI 4 is sub-8 -> left uninit per the shared no-rhs policy)
 *       never emits.
 *   D2 (global): emitletdataw struct arm wrote si.totsize = 8 zero bytes
 *       of DATAW; cstage cg_let_emit_size returns u->size = 4.
 * Both were SILENT cs!=ww divergences (gate-blind: a standalone wwstage
 * is self-consistent; only the cs==ww .s cmp catches it).
 *
 * Fix (rule-13 SSoT): both sites source the extent from tinfo.size
 * (peeling TY_NAMED), the same value cstage reads. fieldsize /
 * registerstruct / frame slot-padding stay UNTOUCHED — moving the fix
 * into the size helpers would shift nested-struct field offsets and
 * re-diverge other byte-id.
 *
 * Rows cover the whole sub-8 class (ABI size 1/2/4) in both the local
 * (D1) and global (D2) emission contexts, plus a >8 NEGATIVE control
 * proving the fix didn't disable legitimate multi-word zero-init. Each
 * row: cstage `ww build` + run for the exit code (correctness) AND
 * w6c vs w6c_ww `.s` cmp for rule-10 byte-id (the silent-divergence net).
 */
#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[] = {
	/* D1 local, ABI size 4 (inner {[4]u8}). Pre-fix wwstage emitted a
	 * stray MOVQ $0 cstage didn't -> .s differ. Write+read a byte so
	 * the exit is deterministic (sub-8 is left uninit by BOTH stages,
	 * matching cstage's no-rhs policy). */
	{ "d1_local_4",
	  "package main;\n"
	  "type inner = struct { m: [4]u8 };\n"
	  "type outv = struct { i: inner };\n"
	  "export fn main() i32 = {\n"
	  "	let o: outv;\n"
	  "	o.i.m[0] = 66u8;\n"
	  "	return o.i.m[0]: i32;\n"
	  "};\n", 66 },
	/* D1 local, ABI size 2 ([2]u8). */
	{ "d1_local_2",
	  "package main;\n"
	  "type inner = struct { m: [2]u8 };\n"
	  "type outv = struct { i: inner };\n"
	  "export fn main() i32 = {\n"
	  "	let o: outv;\n"
	  "	o.i.m[1] = 55u8;\n"
	  "	return o.i.m[1]: i32;\n"
	  "};\n", 55 },
	/* D1 local, ABI size 1 ([1]u8) — the tightest sub-8 case. */
	{ "d1_local_1",
	  "package main;\n"
	  "type inner = struct { m: [1]u8 };\n"
	  "type outv = struct { i: inner };\n"
	  "export fn main() i32 = {\n"
	  "	let o: outv;\n"
	  "	o.i.m[0] = 44u8;\n"
	  "	return o.i.m[0]: i32;\n"
	  "};\n", 44 },
	/* D2 global, ABI size 4. Pre-fix wwstage emitted DATAW of 8 zero
	 * bytes vs cstage's 4 -> .s differ. */
	{ "d2_global_4",
	  "package main;\n"
	  "type inner = struct { m: [4]u8 };\n"
	  "type outv = struct { i: inner };\n"
	  "let g: outv;\n"
	  "export fn main() i32 = {\n"
	  "	g.i.m[0] = 66u8;\n"
	  "	return g.i.m[0]: i32;\n"
	  "};\n", 66 },
	/* D2 global, ABI size 2. */
	{ "d2_global_2",
	  "package main;\n"
	  "type inner = struct { m: [2]u8 };\n"
	  "type outv = struct { i: inner };\n"
	  "let g: outv;\n"
	  "export fn main() i32 = {\n"
	  "	g.i.m[1] = 55u8;\n"
	  "	return g.i.m[1]: i32;\n"
	  "};\n", 55 },
	/* D2 global, ABI size 1. */
	{ "d2_global_1",
	  "package main;\n"
	  "type inner = struct { m: [1]u8 };\n"
	  "type outv = struct { i: inner };\n"
	  "let g: outv;\n"
	  "export fn main() i32 = {\n"
	  "	g.i.m[0] = 44u8;\n"
	  "	return g.i.m[0]: i32;\n"
	  "};\n", 44 },
	/* NEGATIVE control — a >8 (multi-word) value-struct still zero-
	 * inits. Read an UNWRITTEN byte: a working multi-word zero-init
	 * fill makes it 0. If the fix had wrongly suppressed the >8 zero
	 * arm, this would read stack garbage (and byte-id would diff
	 * against the still-zeroing cstage). Local + global both proven. */
	{ "ctl_local_16",
	  "package main;\n"
	  "type inner = struct { m: [16]u8 };\n"
	  "type outv = struct { i: inner };\n"
	  "export fn main() i32 = {\n"
	  "	let o: outv;\n"
	  "	return o.i.m[7]: i32;\n"
	  "};\n", 0 },
	{ "ctl_global_16",
	  "package main;\n"
	  "type inner = struct { m: [16]u8 };\n"
	  "type outv = struct { i: inner };\n"
	  "let g: outv;\n"
	  "export fn main() i32 = {\n"
	  "	return g.i.m[7]: i32;\n"
	  "};\n", 0 },
	{ 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, "valstruct_subsize: w6c_ww missing — cannot run "
		    "the cs==ww byte-id gate (the whole point of this test)\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/wwvss_%d_%d.ww", getpid(), i);
		FILE *f = fopen(src, "wb");
		if (f == NULL) { fail++; continue; }
		fputs(rows[i].src, f);
		fclose(f);

		char tmpdir[64];
		snprintf(tmpdir, sizeof tmpdir, "/tmp/wwvss_%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);

		char cs_s[64], ws_s[64];
		snprintf(cs_s, sizeof cs_s, "/tmp/wwvss_%d_%d_cs.s",
		    getpid(), i);
		snprintf(ws_s, sizeof ws_s, "/tmp/wwvss_%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 valstruct-subsize tests failed\n",
		    fail, n);
		return 1;
	}
	printf("valstruct_subsize: %d/%d ok (cstage run + cs==ww byte-id)\n",
	    n, n);
	return 0;
}