ww/test/wcc/947_inferred_scalar_global_run.c

/*
 * 947_inferred_scalar_global_run — runtime + byte-id net for #66(b-i): an
 * INFERRED int-literal module-global `let s = 42;` (no type annotation) was
 * wwstage SILENT-WRONG. The checker stamps such a global with an
 * N_TNAME("untyped_int") annotation; letemitsize / emitletdataw / the cgident
 * global-read arm key on that annotation's name, which letscalarprim doesn't
 * recognise — so the global was dropped from collectlets (no DATAW emitted)
 * AND the read fell to the silent module-leaf (no `MOVQ main.s(SB)`), leaving
 * `MOVSXD` to sign-extend a STALE AX. cstage instead type_default's the untyped
 * int to the 8B machine word before emit, so it produced the correct
 * `DATAW main.s` + `MOVQ main.s(SB), AX` (exit 42). cs≠ww, ww silent-wrong.
 *
 * Fix (wwstage only, cgen.ww defaultinferredlets, one choke-point before
 * collectlets): rewrite the untyped_int annotation to the concrete machine
 * word `int` — NOT i32 (that's the #108 truncation trap, opposite polarity) —
 * so all three consumers resolve it as an 8B int global. The emitted DATAW +
 * MOVQ then match cstage byte-for-byte (align ww UP). Guarded to N_INTLIT rhs
 * ONLY: a const-EXPR inferred global (`let s = 7*6`) is #66(b-ii), a SEPARATE
 * loud both-stage no-DATA gap, and must stay on its loud route.
 *
 * Each row carries (a) a cstage `ww build` + run asserting the exit code (R1
 * pre-fix: wwstage exit 136 / asm differs), and (b) a w6c vs w6c_ww `.s` cmp
 * (rule-10 byte-id). R2 is the typed-annotation control (already cs==ww/42),
 * locking no regression on the annotated path.
 */
#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;
}

struct row { const char *label; const char *src; int want_exit; int want_err; };

static const struct row rows[] = {
	/* R1 — the #66(b-i) repro: inferred int-literal module-global, read
	 * back from main. Pre-fix wwstage emitted neither the DATAW nor the
	 * MOVQ → MOVSXD on stale AX → exit 136. Post-fix cs==ww, exit 42. */
	{ "inferred",
	  "package main;\n"
	  "let s = 42;\n"
	  "export fn main() i32 = {\n"
	  "	return s: i32;\n"
	  "};\n", 42, 0 },
	/* R2 — typed-annotation control: `let s: i64 = 42;` already worked
	 * (cs==ww, DATA emitted). Regression guard for the annotated path. */
	{ "typed_ctrl",
	  "package main;\n"
	  "let s: i64 = 42;\n"
	  "export fn main() i32 = {\n"
	  "	return s: i32;\n"
	  "};\n", 42, 0 },
	/* R3 — #134 neg leg: inferred unary-over-int-literal module-global
	 * `let s = -42;` (rhs N_UN(TK_MINUS) over N_INTLIT). Pre-fix wwstage
	 * emitted neither DATAW nor MOVQ (un-defaulted untyped_int annotation)
	 * → exit 168 (garbage). cstage folds the unary, emits DATAW + load
	 * (exit 214 = -42 low-8). Post-fix defaultinferredlets peels the unary
	 * and defaults to `int`, so cs==ww and both run -42 (exit 214). */
	{ "neg_inferred",
	  "package main;\n"
	  "let s = -42;\n"
	  "export fn main() i32 = {\n"
	  "	return s: i32;\n"
	  "};\n", 214, 0 },
	/* R4 — #134 neg typed control: `let s: int = -42;` (TYPED). Already
	 * cs==ww today (concrete annotation → letscalarprim fires). Locks the
	 * construction proof: R3's emitted .s is byte-identical to this typed
	 * control (the inferred decl IS the typed decl after defaulting). */
	{ "neg_typed_ctrl",
	  "package main;\n"
	  "let s: int = -42;\n"
	  "export fn main() i32 = {\n"
	  "	return s: i32;\n"
	  "};\n", 214, 0 },
	/* #133 — const-EXPR scalar module-global. The let pass-2 arm now
	 * const-folds an N_BIN / unary-over-N_BIN / def-ref rhs and stamps it
	 * to an N_INTLIT (mirroring the N_DEF arm), so cgen's literal-only
	 * DATA emitter lays the row in BOTH stages. Pre-fix: cstage LINK-FAILed
	 * (`undefined main.s` — read emitted, no DATA word) and wwstage was
	 * SILENT-WRONG (no DATA, no load, MOVSXD on stale AX → exit 152). */

	/* C1 — inferred const-expr `let s = 7*6;` → 42 (N_BIN rhs). */
	{ "const_inferred",
	  "package main;\n"
	  "let s = 7 * 6;\n"
	  "export fn main() i32 = {\n"
	  "	return s: i32;\n"
	  "};\n", 42, 0 },
	/* C2 — typed const-expr (b-ii) `let s: i64 = 7*6;` → 42. Pre-fix this
	 * LINK-FAILed BOTH stages (annotation-independent no-DATA gap); the
	 * same stamp supplies the foldable value. */
	{ "const_typed",
	  "package main;\n"
	  "let s: i64 = 7 * 6;\n"
	  "export fn main() i32 = {\n"
	  "	return s: i32;\n"
	  "};\n", 42, 0 },
	/* C3 — def-ref through let `def K: int = 6; let s = K*7;` → 42. Proves
	 * eval_def_const's N_IDENT def-resolution reaches through the new let
	 * hook. */
	{ "const_defref",
	  "package main;\n"
	  "def K: int = 6;\n"
	  "let s = K * 7;\n"
	  "export fn main() i32 = {\n"
	  "	return s: i32;\n"
	  "};\n", 42, 0 },
	/* C4 — unary-over-binop `let s = -(2*3);` → -6 (low byte 250). Proves
	 * the N_UN ∘ N_BIN composition folds through eval_def_const. */
	{ "const_unary_binop",
	  "package main;\n"
	  "let s = -(2 * 3);\n"
	  "export fn main() i32 = {\n"
	  "	return s: i32;\n"
	  "};\n", 250, 0 },
	/* C5 — loud guard: a div-by-zero const-expr module-global init stays a
	 * compile ERROR in BOTH stages, NOT silently zeroed. Asserts the
	 * eval_def_const error path is preserved through the let hook. */
	{ "const_divzero",
	  "package main;\n"
	  "let s = 7 / 0;\n"
	  "export fn main() i32 = {\n"
	  "	return s: i32;\n"
	  "};\n", 0, 1 },
	{ NULL, NULL, 0, 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, "infglobal: 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/wwisg_%d_d_%d",
		    getpid(), i);
		mkdir(tmpdir, 0755);

		char src[128], rmcmd[160];
		snprintf(src, sizeof src, "%s/wwisg_%d_%d.ww",
		    tmpdir, getpid(), i);
		snprintf(rmcmd, sizeof rmcmd, "rm -rf %s", tmpdir);
		FILE *f = fopen(src, "wb");
		if (f == NULL) { runwait(rmcmd); fail++; continue; }
		fputs(rows[i].src, f);
		fclose(f);

		char cs_s[128], ws_s[128];
		snprintf(cs_s, sizeof cs_s, "%s/wwisg_%d_%d_cs.s",
		    tmpdir, getpid(), i);
		snprintf(ws_s, sizeof ws_s, "%s/wwisg_%d_%d_ww.s",
		    tmpdir, getpid(), i);

		/* Loud-guard rows (#133 R5): both stages must REJECT the
		 * source at compile (e.g. a div-by-zero const-expr init). No
		 * value to run / no byte-id — only the error-path preservation
		 * matters. Assert raw w6c AND w6c_ww both emit non-zero. */
		if (rows[i].want_err) {
			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 accepted a source "
				    "that must be rejected (loud guard)\n",
				    rows[i].label);
				fail++;
			}
			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 accepted a "
				    "source that must be rejected (loud "
				    "guard)\n", rows[i].label);
				fail++;
			}
			runwait(rmcmd);
			continue;
		}

		/* (a) cstage build + run. */
		char outbin[128];
		snprintf(outbin, sizeof outbin, "%s/wwisg_%d_%d",
		    tmpdir, getpid(), i);

		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. */
		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 inferred-scalar-global tests failed\n",
		    fail, n);
		return 1;
	}
	printf("infglobal: %d/%d ok (cstage run + cs==ww byte-id)\n", n, n);
	return 0;
}