/*
 * 949_f9_float_run — F9 argument widen/drain ABI (float) cluster.
 *
 * The cgcall push/drain handling of a CONCRETE arg widened into a
 * tagged-union parameter slot, where a float is involved:
 *
 *   #30 + #48 (align-UP, wwstage-only): the cgcall DRAIN loop had no
 *       widen-first pop branch. A concrete arg widened into a tagged param
 *       was pushed as slotsize/8 GP words (tag + payload), but the drain
 *       classified per the ARG's source type:
 *         #30 — a float arg AFTER a widened (i64|void) arg: the widened
 *               box under-drained by one GP word, so `MOVSD (SP),X0` for
 *               the following f64 read the box's leftover payload word.
 *         #48 — the widened arg IS an f64 source: source-type=f64 hit the
 *               float arm, so `MOVSD (SP),X0` ate the TAG word into X0 and
 *               the payload landed in DI as the tag → callee fell through.
 *       Both are one missing branch — a widen-first GP pop placed BEFORE
 *       the float check, draining slotsize/8 words into the integer arg
 *       cursor (DI=tag, SI=payload). cstage already does this (precomputed
 *       widen[i]); this aligns wwstage UP and the rows pin cs==ww byte-id.
 *
 * REGISTER-CURSOR INVARIANT (rob): a lucky-but-wrong float shuffle can pass
 * exit codes, so the run rows use values that only survive if the tag/
 * payload land in the right GP regs AND the float in the right XMM:
 *   #30 returns 0 iff f's b (the f64 arg following the widen) == 1.5;
 *   #48 returns 2 iff the (i64|f64) box's tag selects the f64 arm (DI=tag).
 * Both also assert cstage/wwstage .s byte-identical.
 *
 * NNN<950, self-contained (/tmp, no imports; #30 returns i32 rather than
 * importing os, so the asm byte-id row can run w6c/w6c_ww directly).
 */
#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
#define K_BUILDERR 1

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

static const struct row rows[] = {
	/* #30: a widened (i64|void) arg FOLLOWED by an f64 arg. Pre-fix the
	 * f64 drain (MOVSD (SP),X0) read the widened box's leftover payload
	 * word (int 7) instead of 1.5, so r != 1.5 → 1. */
	{ "widen_then_float",
	  "package main;\n"
	  "fn f(a: (i64 | void), b: f64) f64 = { return b; };\n"
	  "export fn main() i32 = {\n"
	  "	let r: f64 = f(7, 1.5);\n"
	  "	if (r == 1.5) { return 0; };\n"
	  "	return 1;\n"
	  "};\n", 0, K_RUN, NULL },
	/* #48: the widened arg IS an f64 source (i64|f64). Pre-fix the float
	 * arm ate the tag word into X0 and the payload landed in DI as the
	 * tag, so the match fell through both arms → 9. Correct = 2 (f64). */
	{ "float_source_widen",
	  "package main;\n"
	  "fn g(v: (i64 | f64)) i32 = {\n"
	  "	match (v) {\n"
	  "	case let n: i64 =>\n"
	  "		return 1;\n"
	  "	case let d: f64 =>\n"
	  "		return 2;\n"
	  "	};\n"
	  "	return 9;\n"
	  "};\n"
	  "export fn main() i32 = {\n"
	  "	let d: f64 = 3.5;\n"
	  "	return g(d);\n"
	  "};\n", 2, K_RUN, NULL },
	/* #49 (#263 both-stages): a RUNTIME f64 producer (mk) feeds a value
	 * widened into (f64|void), and the f64 arm READS the payload
	 * (d == 2.5). Pre-fix the widen-PUSH did `PUSHQ AX` for the payload
	 * while the f64 sat in X0, so d read stale bits → 1 (cs) / 3 (ww,
	 * the #48 pop divergence compounding). #48's arm dodged this by not
	 * reading the payload; this one catches the stale-AX push. Both
	 * stages now spill X0 → 0. (After the c4 drain fix the two stages
	 * already agree on the pop; this push fix closes the shared bug.) */
	{ "runtime_float_widen_payload",
	  "package main;\n"
	  "type fv = (f64 | void);\n"
	  "fn mk(x: f64) f64 = { return x + 1.5; };\n"
	  "fn take(v: fv) i32 = {\n"
	  "	match (v) {\n"
	  "	case let d: f64 => {\n"
	  "		if (d == 2.5) { return 0; };\n"
	  "		return 1;\n"
	  "	};\n"
	  "	case void => { return 2; };\n"
	  "	};\n"
	  "	return 3;\n"
	  "};\n"
	  "export fn main() i32 = {\n"
	  "	let d: f64 = mk(1.0);\n"
	  "	return take(d);\n"
	  "};\n", 0, K_RUN, NULL },
};

static int
run_driver(const char *driver, const struct row *r, int i)
{
	char tmpdir[96], src[128], outbin[128], errf[128], rmcmd[160], cmd[1024];
	snprintf(tmpdir, sizeof tmpdir, "/tmp/f9f_%d_d_%d", getpid(), i);
	mkdir(tmpdir, 0755);
	snprintf(src, sizeof src, "%s/f9f_%d_%d.ww", tmpdir, getpid(), i);
	snprintf(outbin, sizeof outbin, "%s/f9f_%d_%d", tmpdir, getpid(), i);
	snprintf(errf, sizeof errf, "%s/err", tmpdir);
	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>%s",
	    driver, outbin, src, errf);
	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;
}

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/f9f_asm_%d_%d.ww", getpid(), i);
	snprintf(cs,  sizeof cs,  "/tmp/f9f_asm_%d_%d_c.s", getpid(), i);
	snprintf(ws,  sizeof ws,  "/tmp/f9f_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, "f9_float: %d/%d checks failed\n",
		    fail, total);
		return 1;
	}
	printf("f9_float: %d/%d ok\n", total, total);
	return 0;
}