/*
 * 940_overcap_tuple_field_store_run — project #234: storing the result of an
 * over-capacity tuple-returning call (sret: > 4 GP / > 2 SSE eightbytes,
 * e.g. ([]u8,[]u8) = 6 GP) into a struct field or an indexed lvalue.
 *
 * The receive end (project #10 Fold B) wired single-var-let / destructure /
 * reassign / return-forward, but a FIELD or INDEXED dest stayed unwired: the
 * store dropped the callee's sret body (a truncated MOVQ through a stale
 * RDI), a SILENT miscompile gate-blind because the bootstrap never field-
 * stores a wide tuple. The fix points the callee's hidden sret dest (RDI)
 * straight at the destination slot when it is a LOCAL (BP-relative), so the
 * callee writes the WHOLE tuple there:
 *   - LOCAL struct field   `s.f = wide();`   dest = s.off + field.off.
 *   - INDEXED local array   `arr[i] = wide();` with a CONSTANT index — dest
 *                           = arr.off + idx*esz (the only indexed form whose
 *                           dest is a static BP offset).
 * Every other dest — via_ptr field (`p.f`), global field (`g.f`), runtime /
 * slice / pointer index — needs a runtime RDI-pointer dest (deferred to
 * #234-tail) and HARD-ERRORS LOUD, never a silent truncating store (rule 7).
 *
 * Both stages emit byte-identically (rule 10); the wwstage struct-field slot
 * is correctly sized only with #237 underneath (a tuple struct field's slot
 * width), committed first in this branch.
 *
 * Rows (cap != len in every wide element so a dropped len OR cap is caught):
 *   A indexed_local   `arr[1] = wide()`, arr: [2]([]u8,[]u8). RUN both stages
 *                     + cs==ww byte-id. Readback via `(&arr[1]):*int` p[i]
 *                     (a tuple-element READ `arr[1].N` is a SEPARATE gap,
 *                     filed #238) — len0=1,cap0=5,len1=2,cap1=6.
 *   B struct_field    `s.f = wide()`, S = struct { hdr:int, f:([]u8,[]u8) }.
 *                     foff!=0 (after hdr) + hdr-uncorrupted check. RUN both
 *                     stages + cs==ww byte-id, pointer readback `(&s.f):*int`.
 *   C via_ptr_be      `p.f = wide()` (p:*S) — BUILDERR, loud #234-tail on
 *                     BOTH drivers.
 *   D global_be       `g.f = wide()` (g a struct global) — BUILDERR, loud.
 *   E rtindex_be      `arr[idx()] = wide()` (runtime index) — BUILDERR, loud.
 *   F ndot_index_be   `s.arr[1] = wide()` (N_DOT-base index, array field of a
 *                     local) — BUILDERR, loud. Regression witness: this form
 *                     shipped SILENT on wwstage when the N_INDEX arm keyed its
 *                     entry on sretretsize(elemtn) — elemtn is a value node for
 *                     an N_DOT base, so the gate returned 0 and fell through to
 *                     the truncating store. Re-keying on callsretsize(rhs)
 *                     (callee-return SSoT) fires the base-shape loud-stop.
 *   G chained_index_be `a[0][1] = wide()` (chained N_INDEX base) — same class,
 *                     BUILDERR, loud on both stages.
 *
 * GATE POLARITY: A/B must build+run exit 0 on BOTH stages AND be cs==ww
 * byte-identical; C/D/E must FAIL the build with the cited #234-tail
 * diagnostic on BOTH stages (rule 7 — loud, not an incidental error).
 * NNN<950, self-contained (/tmp, no imports), so rule-14's selfhost-sibling
 * race does not apply (945/799 precedent).
 */
#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
file_contains(const char *path, const char *needle)
{
	FILE *f = fopen(path, "rb");
	if (!f) return 0;
	char buf[8192];
	size_t n = fread(buf, 1, sizeof buf - 1, f);
	fclose(f);
	buf[n] = '\0';
	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), 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 */

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

static const struct row rows[] = {
	{ "indexed_local",
	  "package main;\n"
	  "fn wide() ([]u8, []u8) = {\n"
	  "	let a: []u8; a.len = 1; a.cap = 5;\n"
	  "	let b: []u8; b.len = 2; b.cap = 6;\n"
	  "	return (a, b);\n"
	  "};\n"
	  "export fn main() i32 = {\n"
	  "	let arr: [2]([]u8, []u8);\n"
	  "	arr[1] = wide();\n"
	  "	let p: *int = (&arr[1]): *int;\n"
	  "	if (p[1] != 1) { return 1; };\n"
	  "	if (p[2] != 5) { return 2; };\n"
	  "	if (p[4] != 2) { return 3; };\n"
	  "	if (p[5] != 6) { return 4; };\n"
	  "	return 0;\n"
	  "};\n", K_RUN, 0, NULL },
	{ "struct_field",
	  "package main;\n"
	  "fn wide() ([]u8, []u8) = {\n"
	  "	let a: []u8; a.len = 1; a.cap = 5;\n"
	  "	let b: []u8; b.len = 2; b.cap = 6;\n"
	  "	return (a, b);\n"
	  "};\n"
	  "type S = struct { hdr: int, f: ([]u8, []u8) };\n"
	  "export fn main() i32 = {\n"
	  "	let s: S;\n"
	  "	s.hdr = 99;\n"
	  "	s.f = wide();\n"
	  "	if (s.hdr != 99) { return 9; };\n"
	  "	let p: *int = (&s.f): *int;\n"
	  "	if (p[1] != 1) { return 1; };\n"
	  "	if (p[2] != 5) { return 2; };\n"
	  "	if (p[4] != 2) { return 3; };\n"
	  "	if (p[5] != 6) { return 4; };\n"
	  "	return 0;\n"
	  "};\n", K_RUN, 0, NULL },
	{ "via_ptr_be",
	  "package main;\n"
	  "fn wide() ([]u8, []u8) = {\n"
	  "	let a: []u8; a.len = 1; let b: []u8; b.len = 2;\n"
	  "	return (a, b);\n"
	  "};\n"
	  "type S = struct { f: ([]u8, []u8) };\n"
	  "export fn main() i32 = {\n"
	  "	let s: S;\n"
	  "	let p: *S = &s;\n"
	  "	p.f = wide();\n"
	  "	return 0;\n"
	  "};\n", K_BUILDERR, 0, "#234-tail" },
	{ "global_be",
	  "package main;\n"
	  "fn wide() ([]u8, []u8) = {\n"
	  "	let a: []u8; a.len = 1; let b: []u8; b.len = 2;\n"
	  "	return (a, b);\n"
	  "};\n"
	  "type S = struct { f: ([]u8, []u8) };\n"
	  "let g: S;\n"
	  "export fn main() i32 = {\n"
	  "	g.f = wide();\n"
	  "	return 0;\n"
	  "};\n", K_BUILDERR, 0, "#234-tail" },
	{ "rtindex_be",
	  "package main;\n"
	  "fn wide() ([]u8, []u8) = {\n"
	  "	let a: []u8; a.len = 1; let b: []u8; b.len = 2;\n"
	  "	return (a, b);\n"
	  "};\n"
	  "fn ix() int = { return 0; };\n"
	  "export fn main() i32 = {\n"
	  "	let arr: [2]([]u8, []u8);\n"
	  "	arr[ix()] = wide();\n"
	  "	return 0;\n"
	  "};\n", K_BUILDERR, 0, "#234-tail" },
	/* N_DOT-base index `s.arr[1] = wide()`: array-field-of-local. The
	 * dest is a static BP offset but the N_INDEX arm only wires a plain
	 * N_IDENT base, so this is a deferred form — MUST loud-stop. Witness
	 * for the gap that shipped silently on wwstage when the arm was keyed
	 * on sretretsize(elemtn) (a value node for an N_DOT base → 0 → fell
	 * through to the truncating store); now keyed on callsretsize(rhs). */
	{ "ndot_index_be",
	  "package main;\n"
	  "fn wide() ([]u8, []u8) = {\n"
	  "	let a: []u8; a.len = 1; let b: []u8; b.len = 2;\n"
	  "	return (a, b);\n"
	  "};\n"
	  "type S = struct { arr: [2]([]u8, []u8) };\n"
	  "export fn main() i32 = {\n"
	  "	let s: S;\n"
	  "	s.arr[1] = wide();\n"
	  "	return 0;\n"
	  "};\n", K_BUILDERR, 0, "#234-tail" },
	/* Chained index `a[0][1] = wide()`: N_INDEX base, same deferred class
	 * — loud-stop on both stages. */
	{ "chained_index_be",
	  "package main;\n"
	  "fn wide() ([]u8, []u8) = {\n"
	  "	let a: []u8; a.len = 1; let b: []u8; b.len = 2;\n"
	  "	return (a, b);\n"
	  "};\n"
	  "export fn main() i32 = {\n"
	  "	let a: [2][2]([]u8, []u8);\n"
	  "	a[0][1] = wide();\n"
	  "	return 0;\n"
	  "};\n", K_BUILDERR, 0, "#234-tail" },
};

/* 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 src[96], tmpdir[96], errf[96], cmd[1024];
	snprintf(src, sizeof src, "/tmp/ocf_%d_%d.ww", getpid(), i);
	snprintf(tmpdir, sizeof tmpdir, "/tmp/ocf_%d_d_%d", getpid(), i);
	snprintf(errf, sizeof errf, "/tmp/ocf_%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 (r->kind == K_BUILDERR) {
		int ok = (brc != 0)
		    && (r->experr == NULL || file_contains(errf, r->experr));
		if (!ok)
			fprintf(stderr, "row[%s]: %s expected loud #234-tail "
			    "builderr (brc=%d)\n", r->label, driver, brc);
		unlink(src); unlink(errf); rmdir(tmpdir);
		return ok ? 0 : 1;
	}

	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;
}

/* cs==ww .s byte-id (rule 10) for a K_RUN row. */
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/ocf_bi_%d_%d.ww", getpid(), i);
	snprintf(cs_s, sizeof cs_s, "/tmp/ocf_bi_%d_%d_cs.s", getpid(), i);
	snprintf(ws_s, sizeof ws_s, "/tmp/ocf_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;
	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 "
			    "(rule-10 byte-id)\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, "overcap_tuple_field_store: 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++;
		}
	}

	/* cs==ww byte-id for the K_RUN rows. */
	if (access(w6c_ww, X_OK) == 0) {
		for (int i = 0; i < n; i++) {
			if (rows[i].kind != K_RUN) continue;
			total++;
			if (byteid(w6c, w6c_ww, &rows[i], i) != 0) fail++;
		}
	}

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