/*
 * 946_floatarr_run — runtime + byte-id net for #119: a float ARRAY
 * ELEMENT load must land in X0 (MOVSS/MOVSD), not the integer register
 * file (MOVQ → AX). cgindex's element-load sites ended in the integer
 * loadopsz, so `let a: [3]f64 = [...]; a[0] + a[1]` loaded the element
 * into AX while the consumer's ADDSD read a stale X0 → wrong sum. #119
 * adds a float-element branch (MOVSS f32 / MOVSD f64 into X0) at all
 * three wwstage cgindex sites (global, baselocal, fallback) and both
 * cstage N_INDEX element-load sites, deriving float-ness from the same
 * stamped element tinfo the esz already reads (elemisfloatc/elemisf32c
 * for ident bases, typeisfloat/typeisf32(n.type_) for N_DOT/N_INDEX
 * bases — never an unstamped node-stamp, dodging the #121 trap).
 *
 * #119 also required a wwstage exprfloatkind N_INDEX arm: the consumer
 * (cgbin / cgcast) classified an indexed float operand as INTEGER and
 * fell to PUSHQ/ADDQ/MOVSXD, while the cstage read the stamped operand
 * type and used ADDSD/CVTTSD2SI — a rule-10 divergence the load fix
 * exposed. The N_INDEX result type_ is checker-stamped (cgindex reads
 * it for esz), so this is not the unstamped-N_MLET case deferred under
 * #121.
 *
 * Each row carries (a) a cstage `ww build` + run asserting the exit
 * code, and (b) a w6c vs w6c_ww `.s` cmp (rule-10 byte-id). A row whose
 * want_exit is RUN_SKIP runs only the byte-id leg.
 *
 * #122 fixes the store-side twin the #119 commit deferred: the f32
 * array-element STORE wrote AX (the raw double low-bits) instead of the
 * CVTSD2SS-narrowed X0 single, so every f32 array slot read back garbage.
 * Both the array-literal-init store (cgen.c:6889 / cgenstmt:949) and the
 * arr[i]= index store (cgen.c:3818 / cgenexpr:4209) now route FROM X0 via
 * MOVSS/MOVSD, mirroring the scalar float store. The f32 rows below now
 * assert the runtime VALUE (not byte-id only) and add an arr[i]= store
 * plus a [v...] repeat-fill init (a distinct cgen arm #122 also fixed).
 */
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <sys/stat.h>
#include <sys/wait.h>

#define RUN_SKIP (-1)

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[] = {
	/* f64 element load + float add: 1.5 + 2.5 == 4.0. On the bug the
	 * elements loaded into AX and the ADDSD read a stale X0 -> != 4.0. */
	{ "f64_arith",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "	let a: [3]f64 = [1.5, 2.5, 9.0];\n"
	  "	if (a[0] + a[1] != 4.0) { return 1; };\n"
	  "	return 0;\n"
	  "};\n", 0 },
	/* f64 element -> i32 cast: 1.5 truncates to 1. On the bug the cast
	 * operand classified integer (MOVSXD on AX) not CVTTSD2SI on X0. */
	{ "f64_trunc",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "	let a: [3]f64 = [1.5, 2.5, 9.0];\n"
	  "	return a[0]: i32;\n"
	  "};\n", 1 },
	/* third element, non-adjacent index: a[2] == 9.0. */
	{ "f64_elem2",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "	let a: [3]f64 = [1.5, 2.5, 9.0];\n"
	  "	if (a[2] != 9.0) { return 1; };\n"
	  "	return 0;\n"
	  "};\n", 0 },
	/* f32 array-literal-init store + element load + add: suffixed
	 * literals so fold-1 narrows them. Pre-#122 the init store wrote
	 * MOVL AX (raw double low-bits) so the slots read garbage; #122
	 * routes the store from X0 via MOVSS, so 1.5 + 2.5 == 4.0. */
	{ "f32_arith",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "	let b: [2]f32 = [1.5f32, 2.5f32];\n"
	  "	if ((b[0] + b[1]): f64 != 4.0) { return 1; };\n"
	  "	return 0;\n"
	  "};\n", 0 },
	/* f32 arr[i]= index store (#122): assign each slot, read back.
	 * The index-store path popped the value to AX and wrote MOVL (raw
	 * double low-bits, garbage for f32); #122 stores from X0 via MOVSS.
	 * The [0.0f32,0.0f32] init also exercises the array-lit store. */
	{ "f32_index_store",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "	let b: [2]f32 = [0.0f32, 0.0f32];\n"
	  "	b[0] = 1.5f32;\n"
	  "	b[1] = 2.5f32;\n"
	  "	if ((b[0] + b[1]): f64 != 4.0) { return 1; };\n"
	  "	return 0;\n"
	  "};\n", 0 },
	/* f32 [v...] repeat-fill init store (#122): the repeat marker
	 * fills every slot from the last element's X0 single; pre-#122 the
	 * fill wrote MOVL AX (raw double low-bits) per slot so each read
	 * back garbage. Distinct cgen arm from the per-element list store.
	 * 1.5 * 3 == 4.5 (exact in IEEE). */
	{ "f32_repeat_fill",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "	let c: [3]f32 = [1.5f32...];\n"
	  "	if ((c[0] + c[1] + c[2]): f64 != 4.5) { return 1; };\n"
	  "	return 0;\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, "floatarr: 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 tmpdir[64];
		snprintf(tmpdir, sizeof tmpdir, "/tmp/wwfarr_%d_d_%d",
		    getpid(), i);
		mkdir(tmpdir, 0755);

		char src[128], outbin[128], cs_s[128], ws_s[128], rmcmd[160];
		snprintf(src, sizeof src, "%s/wwfarr_%d_%d.ww",
		    tmpdir, getpid(), i);
		snprintf(outbin, sizeof outbin, "%s/wwfarr_%d_%d",
		    tmpdir, getpid(), i);
		snprintf(cs_s, sizeof cs_s, "%s/wwfarr_%d_%d_cs.s",
		    tmpdir, getpid(), i);
		snprintf(ws_s, sizeof ws_s, "%s/wwfarr_%d_%d_ww.s",
		    tmpdir, getpid(), i);
		snprintf(rmcmd, sizeof rmcmd, "rm -rf %s", tmpdir);

		FILE *f = fopen(src, "wb");
		if (f == NULL) { fail++; runwait(rmcmd); continue; }
		fputs(rows[i].src, f);
		fclose(f);

		/* (a) cstage build + run (skipped for byte-id-only rows). */
		if (rows[i].want_exit != RUN_SKIP) {
			char cmd[2048];
			snprintf(cmd, sizeof cmd, "%s/ww build -o %s %s",
			    bin, outbin, src);
			if (runwait(cmd) != 0) {
				fprintf(stderr, "row[%s]: cstage build failed\n",
				    rows[i].label);
				fail++;
				runwait(rmcmd);
				continue;
			}

			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++;
			}
		}

		/* (b) cs==ww byte-id gate: emit .s from both stages, cmp. */
		char cmd[2048];
		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++; runwait(rmcmd); 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++; runwait(rmcmd); 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++;
		}
		runwait(rmcmd);
	}

	if (fail) {
		fprintf(stderr, "%d/%d float-array element tests failed\n",
		    fail, n);
		return 1;
	}
	printf("floatarr: %d/%d ok (cstage run + cs==ww byte-id)\n", n, n);
	return 0;
}