/*
 * 953_f64crossmod_run — runtime + byte-id regression net for the
 * cross-module f64-return codegen bug, one root with two symptoms:
 *   #101 — `mod.g(): i32` where g returns f64 must CVTTSD2SI X0->AX
 *          (f64->int convert), NOT MOVSXD (integer sign-extend).
 *   #98  — `dbl(mod.g())` forwarding an imported f64 call-result as an
 *          f64 arg must MOVSD-spill it, NOT integer PUSHQ AX / POPQ DI.
 *
 * Root: wwstage exprfloatkind's N_CALL arm only resolved an N_IDENT
 * callee's return type; a module-qualified N_DOT callee (`mod.g()`)
 * never reached fnretlookup and fell through to integer kind 0. cgcast
 * (#101) and pushargsrev (#98) then both took the integer path for an
 * imported f64-returning fn. Fixed in cgenutil.ww by routing the N_DOT
 * callee through fnretlookupmod (cstage cg_isfloat reads the resolved
 * call result type directly — cmd/w6c/cgen.c:117,155 — and is correct
 * for both cases).
 *
 * THIS TEST MUST CATCH A WWSTAGE-ONLY REGRESSION. cstage is correct
 * before and after the fix, so a cstage-only probe (like
 * 951_f64cgen_run) is gate-blind to a wwstage-only divergence. Each row
 * therefore carries BOTH dimensions:
 *   (a) cstage `ww build` + run, asserting the exit code — pins that
 *       the asm both stages converge on is the runtime-correct one.
 *   (b) w6c vs w6c_ww `.s` cmp — FAILS if the stages diverge. On master
 *       6f8b658 (pre-fix) this diverges (#101 ~2 lines MOVSXD vs
 *       CVTTSD2SI, #98 ~6 lines PUSHQ/POPQ vs MOVSD-spill); post-fix it
 *       is byte-identical.
 *
 * Single-file multi-package form (like 728_match_4arm_cross_module):
 * `package myf; ... package main; import myf; ...` in one source, so
 * w6c/w6c_ww see the cross-module call without -I path plumbing.
 */
#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[] = {
	/* #101 basic: g() returns -7.0, cast to i32 -> -7, exit u8 249. */
	{ "x101_neg",
	  "package myf;\n"
	  "export fn g() f64 = { return -7.0; };\n"
	  "package main;\n"
	  "import myf;\n"
	  "export fn main() i32 = { return myf.g(): i32; };\n", 249 },
	/* #101 truncation toward zero, positive: 3.9 -> 3. */
	{ "x101_trunc_pos",
	  "package myf;\n"
	  "export fn g() f64 = { return 3.9; };\n"
	  "package main;\n"
	  "import myf;\n"
	  "export fn main() i32 = { return myf.g(): i32; };\n", 3 },
	/* #101 truncation toward zero, negative: -3.9 -> -3, exit u8 253. */
	{ "x101_trunc_neg",
	  "package myf;\n"
	  "export fn g() f64 = { return -3.9; };\n"
	  "package main;\n"
	  "import myf;\n"
	  "export fn main() i32 = { return myf.g(): i32; };\n", 253 },
	/* #98 nested f64-call-as-f64-arg: dbl(myf.g()) = -7.0*2 = -14,
	 * cast to i32 -> -14, exit u8 242. The imported call-result is
	 * forwarded as an f64 arg, exercising pushargsrev's float spill. */
	{ "x98_nested_arg",
	  "package myf;\n"
	  "export fn g() f64 = { return -7.0; };\n"
	  "package main;\n"
	  "import myf;\n"
	  "fn dbl(x: f64) f64 = { return x * 2.0; };\n"
	  "export fn main() i32 = { return dbl(myf.g()): i32; };\n", 242 },
	/* #98 XMM-pressure: myf.g() forwarded as the first of three f64
	 * args; pushargsrev must MOVSD-spill the imported call-result into
	 * X2 while two more f64 args are live — a distinct path from the
	 * basic single-arg X0 spill above. sum3(-7,10.5,4.5)=8.0 -> i32 8. */
	{ "x98_xmm_pressure",
	  "package myf;\n"
	  "export fn g() f64 = { return -7.0; };\n"
	  "package main;\n"
	  "import myf;\n"
	  "fn sum3(a: f64, b: f64, c: f64) f64 = { return a + b + c; };\n"
	  "export fn main() i32 = { return sum3(myf.g(), 10.5, 4.5): i32; };\n", 8 },
	{ 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, "f64crossmod: 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/wwf64x_%d_%d.ww", getpid(), i);
		FILE *f = fopen(src, "wb");
		if (f == NULL) { fail++; continue; }
		fputs(rows[i].src, f);
		fclose(f);

		/* (a) cstage build + run. Build cwd is a scratch dir so the
		 * output binary (and any intermediates) land there. */
		char tmpdir[64];
		snprintf(tmpdir, sizeof tmpdir, "/tmp/wwf64x_%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);

		/* (b) cs==ww byte-id gate: emit .s from both stages, cmp.
		 * FAILS on the pre-fix wwstage divergence. */
		char cs_s[64], ws_s[64];
		snprintf(cs_s, sizeof cs_s, "/tmp/wwf64x_%d_%d_cs.s",
		    getpid(), i);
		snprintf(ws_s, sizeof ws_s, "/tmp/wwf64x_%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 f64 cross-module tests failed\n",
		    fail, n);
		return 1;
	}
	printf("f64crossmod: %d/%d ok (cstage run + cs==ww byte-id)\n", n, n);
	return 0;
}