/*
 * 949_f6_header_run — F6 24B str/slice header partial-load/store cluster.
 *
 * Three members of the cat-A drain F6 sub-train, each a 24B-header
 * (ptr,len,cap) materialize choke-point that dropped one or more words:
 *
 *   #19 (align-UP, wwstage-only): a str→[]u8 cast from a NON-LOCAL
 *       source (global ident / struct field / call result) missed the
 *       cap=len synth (`MOVQ BX, CX`) — wwstage gated the synth on a
 *       local-ident source only, leaving CX = the str's stale word-16
 *       garbage cap. cstage was already type-keyed (TY_STR→TY_SLICE) and
 *       correct, so this aligns wwstage UP; the rows pin cs==ww byte-id.
 *
 *   #28 (#263 both-stages): a tuple slice-element read `t.0` over a
 *       `([]u8, i64)` loaded only the ptr word — the str arm handled str
 *       but a SLICE element fell to the scalar tail, so len/cap took
 *       stale registers (a clobber() call between build and read leaves
 *       junk in BX/CX). Both stages were byte-id-WRONG; fixed together.
 *
 *   #29 (#263 both-stages): a chained-dot str leaf `o.i.s` (depth-2)
 *       emitted only (ptr,len) — the cap word was dropped, so a junk
 *       strlit before the chain left CX stale. Both stages byte-id-WRONG.
 *
 * POLARITY: #19 cstage is the byte-id ref (align wwstage UP). #28/#29 are
 * #263 (both byte-id-WRONG) — the fix lands BOTH halves together, so the
 * rows assert both-stages-CORRECT post-fix (no residual rows); the
 * runtime read-back with DISTINCT values (cap=3/len=5/cap=5) is the net
 * a byte-id gate alone was blind to.
 *
 * NNN<950, self-contained (/tmp, no imports) — rule-14's selfhost-sibling
 * race does not apply (941/944/945/947 precedent). Every K_RUN row also
 * pins cstage/wwstage asm byte-id.
 */
#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;
}

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 */
#define K_BUILDERR 1	/* build must FAIL with experr on BOTH drivers (rule 7) */

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

static const struct row rows[] = {
	/* #19: str→[]u8 cast from a GLOBAL ident source, threaded through a
	 * call return. cap must == len == 3. Pre-fix wwstage left CX = the
	 * str's stale word-16 (rc=120). */
	{ "global_str_cap",
	  "package main;\n"
	  "let G: str = \"abc\";\n"
	  "fn f() []u8 = { return G: []u8; };\n"
	  "export fn main() i32 = {\n"
	  "	let s: []u8 = f();\n"
	  "	return s.cap: i32;\n"
	  "};\n", 3, K_RUN, NULL },
	/* #19 sibling: str→[]u8 cast from a struct FIELD source. Same
	 * type-keyed synth path; distinct len (5) catches a dropped cap. */
	{ "field_str_cap",
	  "package main;\n"
	  "type box = struct { s: str, x: i64 };\n"
	  "export fn main() i32 = {\n"
	  "	let b: box = box { s = \"hello\", x = 0 };\n"
	  "	let v: []u8 = b.s: []u8;\n"
	  "	return v.cap: i32;\n"
	  "};\n", 5, K_RUN, NULL },
	/* #19 control: LOCAL str source (the pre-fix-covered shape) still
	 * emits the synth — guards against a regression of the common case. */
	{ "local_str_cap",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "	let s: str = \"abcd\";\n"
	  "	let v: []u8 = s: []u8;\n"
	  "	return v.cap: i32;\n"
	  "};\n", 4, K_RUN, NULL },
	/* #28 (#263 both-stages): tuple slice-element read `t.0` over a
	 * ([]u8, i64). A clobber() call between the tuple build and the
	 * read leaves junk in BX/CX; pre-fix the str-only arm fell to the
	 * scalar tail (ptr word only), so ys.len read stale BX. Reads len
	 * == 5 (distinct from any stale value) → 0. */
	{ "tuple_slice_elem",
	  "package main;\n"
	  "fn clobber() i64 = {\n"
	  "	let a: i64 = 111;\n"
	  "	let b: i64 = 222;\n"
	  "	return a + b;\n"
	  "};\n"
	  "export fn main() i32 = {\n"
	  "	let xs: []u8 = [1u8, 2u8, 3u8, 4u8, 5u8];\n"
	  "	let t: ([]u8, i64) = (xs, 7);\n"
	  "	let junk: i64 = clobber();\n"
	  "	let ys: []u8 = t.0;\n"
	  "	if (ys.len == 5) { return 0; };\n"
	  "	return 1;\n"
	  "};\n", 0, K_RUN, NULL },
	/* #28 sibling: the slice element sits at tuple position 1 (foff != 0:
	 * an i64 occupies slot 0, the []u8 header starts at +8). Exercises the
	 * widened arm's offset arithmetic, which the position-0 row leaves
	 * untested. Same clobber()-between-build-and-read trigger; len == 6. */
	{ "tuple_slice_elem_pos1",
	  "package main;\n"
	  "fn clobber() i64 = {\n"
	  "	let a: i64 = 111;\n"
	  "	let b: i64 = 222;\n"
	  "	return a + b;\n"
	  "};\n"
	  "export fn main() i32 = {\n"
	  "	let xs: []u8 = [1u8, 2u8, 3u8, 4u8, 5u8, 6u8];\n"
	  "	let t: (i64, []u8) = (9, xs);\n"
	  "	let junk: i64 = clobber();\n"
	  "	let ys: []u8 = t.1;\n"
	  "	if (ys.len == 6) { return 0; };\n"
	  "	return 1;\n"
	  "};\n", 0, K_RUN, NULL },
	/* #29 (#263 both-stages): chained-dot str leaf `o.i.s` (depth-2)
	 * dropped the cap word — a junk strlit before the chain left CX
	 * stale, so t.cap read 2 (the junk's cap) instead of 5. Now the
	 * str leaf loads all three header words like the slice arm. */
	{ "chained_str_cap",
	  "package main;\n"
	  "type inner = struct { s: str, x: i64 };\n"
	  "type outer = struct { i: inner, y: i64 };\n"
	  "export fn main() i32 = {\n"
	  "	let iv: inner = inner { s = \"hello\", x = 0 };\n"
	  "	let o: outer = outer { i = iv, y = 0 };\n"
	  "	let junk: str = \"ab\";\n"
	  "	let t: str = o.i.s;\n"
	  "	return t.cap: i32;\n"
	  "};\n", 5, K_RUN, NULL },
	/* #29 sibling: the str leaf sits at a NON-ZERO field offset within the
	 * inner struct (a leading i64 pad pushes `s` to +8, so totaloff != 0).
	 * Exercises the chained-leaf offset arithmetic the offset-0 row leaves
	 * untested. Junk strlit before the chain; cap == len == 7. */
	{ "chained_str_cap_offset",
	  "package main;\n"
	  "type inner = struct { pad: i64, s: str };\n"
	  "type outer = struct { i: inner, y: i64 };\n"
	  "export fn main() i32 = {\n"
	  "	let iv: inner = inner { pad = 0, s = \"worldly\" };\n"
	  "	let o: outer = outer { i = iv, y = 0 };\n"
	  "	let junk: str = \"ab\";\n"
	  "	let t: str = o.i.s;\n"
	  "	return t.cap: i32;\n"
	  "};\n", 7, K_RUN, NULL },
};

static int
run_driver(const char *driver, const struct row *r, int i)
{
	char src[96], tmpdir[96], errf[96], cmd[1024];
	snprintf(src, sizeof src, "/tmp/f6h_%d_%d.ww", getpid(), i);
	snprintf(tmpdir, sizeof tmpdir, "/tmp/f6h_%d_d_%d", getpid(), i);
	snprintf(errf, sizeof errf, "/tmp/f6h_%d_e_%d", getpid(), i);

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

	mkdir(tmpdir, 0755);
	snprintf(cmd, sizeof cmd, "cd %s && %s build %s >/dev/null 2>%s",
	    tmpdir, driver, src, errf);
	int brc = runwait(cmd);
	if (brc != 0) {
		fprintf(stderr, "row[%s]: build via %s failed\n",
		    r->label, driver);
		unlink(src); unlink(errf); rmdir(tmpdir);
		return -1;
	}

	const char *base = strrchr(src, '/');
	base = base ? base + 1 : src;
	char outbin[256];
	snprintf(outbin, sizeof outbin, "%s/%s", tmpdir, base);
	char *dot = strrchr(outbin, '.');
	if (dot && strcmp(dot, ".ww") == 0) *dot = '\0';
	int got = runwait(outbin);

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

static int
asm_byte_identical(const char *bin, const struct row *r, int i)
{
	char src[96], cs[96], ws[96], cmd[1024];
	snprintf(src, sizeof src, "/tmp/f6h_asm_%d_%d.ww", getpid(), i);
	snprintf(cs,  sizeof cs,  "/tmp/f6h_asm_%d_%d_c.s", getpid(), i);
	snprintf(ws,  sizeof ws,  "/tmp/f6h_asm_%d_%d_w.s", getpid(), i);

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

	snprintf(cmd, sizeof cmd, "%s/w6c -o %s %s 2>/dev/null", bin, cs, src);
	if (runwait(cmd) != 0) {
		fprintf(stderr, "row[%s]: w6c errored\n", r->label);
		unlink(src);
		return -1;
	}
	snprintf(cmd, sizeof cmd, "%s/w6c_ww -o %s %s 2>/dev/null",
	    bin, ws, src);
	if (runwait(cmd) != 0) {
		fprintf(stderr, "row[%s]: w6c_ww errored\n", r->label);
		unlink(src); unlink(cs);
		return -1;
	}
	int rc = slurp_eq(cs, ws);
	if (rc != 0)
		fprintf(stderr, "row[%s]: cstage vs wwstage asm differs\n",
		    r->label);
	unlink(src); unlink(cs); unlink(ws);
	return rc;
}

int
main(void)
{
	const char *bin = getenv("BIN");
	if (!bin) bin = "out/bin";
	char absbin[2080];
	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[2120], wdrv[2120];
	snprintf(cdrv, sizeof cdrv, "%s/ww", bin);
	snprintf(wdrv, sizeof wdrv, "%s/ww_ww", bin);

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

	for (int i = 0; i < n; i++) {
		total++;
		if (run_driver(cdrv, &rows[i], i) != 0) fail++;
	}
	if (access(wdrv, X_OK) == 0) {
		for (int i = 0; i < n; i++) {
			total++;
			if (run_driver(wdrv, &rows[i], i) != 0) fail++;
		}
		for (int i = 0; i < n; i++) {
			if (rows[i].kind == K_BUILDERR)
				continue;
			total++;
			if (asm_byte_identical(bin, &rows[i], i) != 0) fail++;
		}
	}

	if (fail) {
		fprintf(stderr, "f6_header: %d/%d checks failed\n",
		    fail, total);
		return 1;
	}
	printf("f6_header: %d/%d ok\n", total, total);
	return 0;
}