/*
 * 766_star_fn_deref_call — root-cause lock for project #181, and the
 * live verification of the full deref-call c-cluster (#180 + #185 +
 * #181 working together end-to-end).
 *
 * Pre-#181 wwstage's checker bailed asserttyped on the N_CALL whose
 * callee was N_UN TK_STAR over a *fn — selfhost/cmd/wcc/check.ww
 * exprtype's N_CALL arm only resolved IDENT/DOT-named callees and
 * early-returned nil for any other shape, leaving e.type_ unstamped
 * so the post-checker invariant gate fired. With cgen post-#180+#185
 * already correct for the deref-call lowering, the safe fix was to
 * lift the asserttyped bail and route the callee through the
 * fn-VALUE fallback (autodereference + dealias to TY_FN, mirroring
 * harec check_autodereference at ref/harec/src/check.c:1566).
 *
 * Fix: selfhost/cmd/wcc/check.ww exprtype N_CALL arm — replace the
 * `if (nm.len == 0) return nil` early-bail with `if (nm.len > 0)
 * { name-lookup }`, so non-named callees fall through to the
 * existing fn-VALUE branch (peel TPTR, dealias to TFN, stamp the
 * result type). cstage check.c already worked because cexpr
 * recurses on the callee — TK_STAR's unop arm returns t->sub which
 * is TY_FN directly, no name path needed.
 *
 * Gate flip from 765: 765 was cstage-only because wwstage bailed
 * before reaching cgen. Post-#181 every row gates BOTH stages —
 * cstage runtime, wwstage runtime, AND cs.s == ww.s byte-id. This
 * is the runtime coverage 765 deferred plus the symmetry gate that
 * proves both stages emit identical asm for the deref-call shape.
 *
 * Coverage (same 5 rows as 765, now with STAGE_CS|STAGE_WW):
 *   1. minimal              — `let f = &add1; (*f)(7) == 8`
 *   2. branched_callee      — pick aa or bb by runtime cond
 *   3. alias_chain          — `let f = &fn; let g = f; (*g)(7)`
 *   4. fn_with_args         — multiple args, scalar + ptr mix
 *   5. fn_tuple_return      — (i32, i32) return shape; multi-reg
 *                             return ABI survives the deref-call
 *
 * Gates per row:
 *   a. cstage builds + runs, exit == expected (already worked
 *      post-#180+#185; kept for c-cluster regression coverage).
 *   b. wwstage builds + runs, exit == expected — the #181 lift
 *      gate; pre-fix this row's asserttyped bailed before cgen.
 *   c. cstage .s == wwstage .s byte-identical — rule-10 symmetry,
 *      proves the checker change doesn't perturb the codegen.
 *
 * GATE POLARITY: must stay GREEN. A red here means either the
 * checker N_CALL fn-VALUE route regressed, the cgen deref-call
 * lowering regressed (#180/#185), or stage symmetry drifted.
 */
#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;
}

#define STAGE_CS	1
#define STAGE_WW	2

struct row {
	const char *label;
	const char *src;
	int expected_exit;
	int stage_mask;
};

static const struct row rows[] = {
	{ "minimal",
	  "fn add1(x: i32) i32 = { return x + 1; };\n"
	  "export fn main() i32 = {\n"
	  "    let f: *fn(x: i32) i32 = &add1;\n"
	  "    return (*f)(7);\n"
	  "};\n",
	  8,
	  STAGE_CS | STAGE_WW },
	/* Branched-callee: the if-arm forces a runtime choice between
	 * two distinct fn addresses, defeating any constant-aliasing
	 * mask of the deref miscompile (#105 lesson). */
	{ "branched_callee",
	  "fn aa(x: i32) i32 = { return x; };\n"
	  "fn bb(x: i32) i32 = { return x + 100; };\n"
	  "export fn main() i32 = {\n"
	  "    let pick: i32 = 1;\n"
	  "    let f: *fn(x: i32) i32 = &aa;\n"
	  "    if (pick != 0) { f = &bb; };\n"
	  "    return (*f)(7);\n"
	  "};\n",
	  107,
	  STAGE_CS | STAGE_WW },
	{ "alias_chain",
	  "fn add1(x: i32) i32 = { return x + 1; };\n"
	  "export fn main() i32 = {\n"
	  "    let f: *fn(x: i32) i32 = &add1;\n"
	  "    let g: *fn(x: i32) i32 = f;\n"
	  "    return (*g)(7);\n"
	  "};\n",
	  8,
	  STAGE_CS | STAGE_WW },
	{ "fn_with_args",
	  "fn many(a: i32, b: i32, p: *i32) i32 = { return a + b + *p; };\n"
	  "export fn main() i32 = {\n"
	  "    let z: i32 = 5;\n"
	  "    let f: *fn(a: i32, b: i32, p: *i32) i32 = &many;\n"
	  "    return (*f)(3, 7, &z);\n"
	  "};\n",
	  15,
	  STAGE_CS | STAGE_WW },
	/* Tuple-return: exercises the multi-register return ABI through
	 * the deref-call. (i32, i32) keeps it simple while still covering
	 * the multi-reg path. */
	{ "fn_tuple_return",
	  "fn pair(x: i32) (i32, i32) = { return (x, x + 1); };\n"
	  "export fn main() i32 = {\n"
	  "    let f: *fn(x: i32) (i32, i32) = &pair;\n"
	  "    let a, b = (*f)(7);\n"
	  "    return a + b;\n"
	  "};\n",
	  15,
	  STAGE_CS | STAGE_WW },
};

static int
write_source(const char *src_path, const char *src)
{
	FILE *f = fopen(src_path, "wb");
	if (!f) return -1;
	fputs(src, f);
	fclose(f);
	return 0;
}

static void
cleanup_tmp(const char *tmpdir, const char *base)
{
	char p[512];
	snprintf(p, sizeof p, "%s/%s.ww", tmpdir, base); unlink(p);
	snprintf(p, sizeof p, "%s/%s.o",  tmpdir, base); unlink(p);
	snprintf(p, sizeof p, "%s/%s.combined.ww", tmpdir, base); unlink(p);
	snprintf(p, sizeof p, "%s/%s",    tmpdir, base); unlink(p);
	/* #93: the sep scratch dir + the tmpdir-pinned pkgcache. */
	snprintf(p, sizeof p, "rm -rf %s/%s.sepwork %s/pkgc", tmpdir, base, tmpdir);
	if (system(p)) {} /* best-effort */
	rmdir(tmpdir);
}

static int
build_via_driver(const char *driver, const char *tmpdir, const char *src)
{
	char cmd[1024];
	/* #93 sep layout: emit asm to <src-stem>.sepwork/__root.s; pin
	 * WW_PKGCACHE under tmpdir so out/.pkgcache is untouched. */
	snprintf(cmd, sizeof cmd,
	    "cd %s && b='%s'; WW_PKGCACHE=%s/pkgc timeout 180 %s build --sep "
	    "-o \"${b%%.ww}\" \"$b\" 2>/dev/null",
	    tmpdir, src, tmpdir, driver);
	return runwait(cmd);
}

/* run_row — build + run; returns the binary's exit code (-1 on
 * build failure). */
static int
run_row(const char *driver, const struct row *r, int seq)
{
	char tmpdir[256], src[256], base[64], outbin[512];
	snprintf(tmpdir, sizeof tmpdir, "/tmp/wcsfdc_%d_d_%d", getpid(), seq);
	snprintf(src,    sizeof src,    "%s/main766.ww", tmpdir);
	snprintf(base,   sizeof base,   "main766");
	mkdir(tmpdir, 0755);
	if (write_source(src, r->src) != 0) {
		cleanup_tmp(tmpdir, base);
		return -1;
	}
	int rc = -1;
	if (build_via_driver(driver, tmpdir, src) == 0) {
		snprintf(outbin, sizeof outbin, "%s/%s", tmpdir, base);
		rc = runwait(outbin);
	}
	cleanup_tmp(tmpdir, base);
	return rc;
}

/* asm_byte_identical — diff cstage vs wwstage .s. Parallel trees so
 * ww_ww writing intermediates next to the source doesn't clobber the
 * cstage .s (filed bug per CLAUDE.md rule 14 phase split). */
static int
asm_byte_identical(const char *cdrv, const char *wdrv,
    const struct row *r, int seq)
{
	char src[256], tdc[256], tdw[256], base[64], cs[512], ws[512];
	snprintf(tdc, sizeof tdc, "/tmp/wcsfdc_%d_c_%d", getpid(), seq);
	snprintf(tdw, sizeof tdw, "/tmp/wcsfdc_%d_w_%d", getpid(), seq);
	snprintf(base, sizeof base, "main766");
	mkdir(tdc, 0755);
	mkdir(tdw, 0755);
	snprintf(src, sizeof src, "%s/main766.ww", tdc);
	if (write_source(src, r->src) != 0) { cleanup_tmp(tdc, base); cleanup_tmp(tdw, base); return -1; }
	int rc = -1;
	if (build_via_driver(cdrv, tdc, src) != 0) goto out;
	snprintf(cs, sizeof cs, "%s/%s.sepwork/__root.s", tdc, base);

	snprintf(src, sizeof src, "%s/main766.ww", tdw);
	if (write_source(src, r->src) != 0) goto out;
	if (build_via_driver(wdrv, tdw, src) != 0) goto out;
	snprintf(ws, sizeof ws, "%s/%s.sepwork/__root.s", tdw, base);

	FILE *fc = fopen(cs, "rb");
	FILE *fw = fopen(ws, "rb");
	if (fc && fw) {
		rc = 0;
		for (;;) {
			int a = fgetc(fc);
			int b = fgetc(fw);
			if (a != b) { rc = -1; break; }
			if (a == EOF) break;
		}
	}
	if (fc) fclose(fc);
	if (fw) fclose(fw);
out:
	cleanup_tmp(tdc, base);
	cleanup_tmp(tdw, base);
	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 cdrv[1024], wdrv[1024];
	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;
	int wwpresent = (access(wdrv, X_OK) == 0);
	int seq = 0;

	for (int i = 0; i < n; i++) {
		if (rows[i].stage_mask & STAGE_CS) {
			total++;
			int got = run_row(cdrv, &rows[i], seq++);
			if (got != rows[i].expected_exit) {
				fprintf(stderr,
				    "star_fn_deref_call[cstage run][%s]: exit=%d want=%d\n",
				    rows[i].label, got, rows[i].expected_exit);
				fail++;
			}
		}
		if (wwpresent && (rows[i].stage_mask & STAGE_WW)) {
			total++;
			int got = run_row(wdrv, &rows[i], seq++);
			if (got != rows[i].expected_exit) {
				fprintf(stderr,
				    "star_fn_deref_call[wwstage run][%s]: exit=%d want=%d\n",
				    rows[i].label, got, rows[i].expected_exit);
				fail++;
			}
			total++;
			if (asm_byte_identical(cdrv, wdrv, &rows[i], seq++) != 0) {
				fprintf(stderr,
				    "star_fn_deref_call[byte-id][%s]: cstage vs wwstage asm differs\n",
				    rows[i].label);
				fail++;
			}
		}
	}

	if (!wwpresent)
		fprintf(stderr, "star_fn_deref_call: skip wwstage (no %s)\n", wdrv);

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