ww/test/wcc/947_tuple_index_read_run.c

/*
 * 947_tuple_index_read_run — #121: const-slice tuple-element READ.
 *
 * Three legs of indexed-tuple read off a `const [](str,*fn)` (fold-6's
 * charclass_map shape), all sharing the &tbl[i] place-spine (#116):
 *
 *   (a) FIELD `tbl[i].N` (bound) — was LOUD both stages ("unsupported
 *       field-read shape": the tuple-field dispatch fired only for an
 *       N_IDENT base; an N_INDEX base fell to the read-resolver fatal).
 *       Now resolved via cgplaceaddr + the per-element-kind arms
 *       (str-triple / fn-8B). align-loud→both-accept-correct.
 *
 *   (b) WHOLE `let e = tbl[i]` then read e.N — was SILENT both-wrong-
 *       IDENTICAL (#263, word0-only: the in-cap tuple receive read a
 *       register cursor the N_INDEX load never filled past word0, so
 *       str.len→0 and the *fn word was garbage). Now fills all gptotal
 *       cursor words from &tbl[i]. align-both-correct.
 *
 *   (c) for-range over a module-global slice — LOUD-STOP both stages
 *       (the for-range spine has no global-base resolution; pre-fix it
 *       read saved-BP → SEGV with divergent cs≠ww asm). Filed as a #121
 *       sibling; loud is byte-id-neutral + a pure improvement.
 *
 * POLARITY: leg (a) cstage is the byte-id ref (align-loud→accept); leg
 * (b) byte-id is BLIND (#263) — both stages were identically truncated,
 * so the runtime READ-BACK with DISTINCT-per-row values (str lengths
 * differ; fns fa↔'a'/fz↔'z' differ) is the only net: a wrong/truncated
 * word is CAUGHT, not masked.
 *
 * MUST use `[](str,*fn)`, NOT `[](str,int)` — the latter is #120
 * wwstage-checker-rejected ("let: not assignable") BEFORE the read runs.
 *
 * NNN<950, self-contained (/tmp, no imports) — rule-14's selfhost-sibling
 * race does not apply (941/944/945/946 precedent). Every K_RUN row also
 * pins cstage/wwstage asm byte-id.
 */
#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;
}

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	/* build+run both drivers, exit==want, + cs==ww byte-id */
#define K_BUILDERR 1	/* build must FAIL with experr on BOTH drivers (rule 7) */

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

static int
errlog_has(const char *path, const char *needle)
{
	FILE *f = fopen(path, "rb");
	if (!f) return 0;
	char buf[8192];
	size_t got = fread(buf, 1, sizeof buf - 1, f);
	fclose(f);
	buf[got] = '\0';
	return strstr(buf, needle) != NULL;
}

static const struct row rows[] = {
	/* leg (a): direct `tbl[i].N` field read, bound then observed.
	 * str field (distinct lengths 2 vs 4) + fn field (distinct fns,
	 * each called back). Was LOUD both stages at base 761cfa4. */
	{ "field_read",
	  "package main;\n"
	  "fn fa(c: rune) bool = { return c == 'a'; };\n"
	  "fn fz(c: rune) bool = { return c == 'z'; };\n"
	  "const tbl: [](str, *fn(c: rune) bool) = "
	  "[(\"ab\", &fa), (\"cdef\", &fz)];\n"
	  "export fn main() i32 = {\n"
	  "	let s1 = tbl[1].0;\n"
	  "	let s0 = tbl[0].0;\n"
	  "	if (len(s1) != 4) { return 1; };\n"
	  "	if (len(s0) != 2) { return 2; };\n"
	  "	let f1 = tbl[1].1;\n"
	  "	if (!(*f1)('z')) { return 3; };\n"
	  "	if ((*f1)('a')) { return 4; };\n"
	  "	let f0 = tbl[0].1;\n"
	  "	if (!(*f0)('a')) { return 5; };\n"
	  "	if ((*f0)('z')) { return 6; };\n"
	  "	return 0;\n"
	  "};\n", 0, K_RUN, NULL },
	/* leg (b): whole-element bind then read e.0 (str.len, catches the
	 * w1→0 truncation) + e.1 (the *fn word, catches w3 garbage).
	 * DISTINCT per row — a truncated/wrong word is caught not masked.
	 * Was SILENT both-wrong-identical (#263) at base 761cfa4. */
	{ "whole_element",
	  "package main;\n"
	  "fn fa(c: rune) bool = { return c == 'a'; };\n"
	  "fn fz(c: rune) bool = { return c == 'z'; };\n"
	  "const tbl: [](str, *fn(c: rune) bool) = "
	  "[(\"ab\", &fa), (\"cdef\", &fz)];\n"
	  "export fn main() i32 = {\n"
	  "	let e = tbl[1];\n"
	  "	if (len(e.0) != 4) { return 1; };\n"
	  "	if (!(*e.1)('z')) { return 2; };\n"
	  "	if ((*e.1)('a')) { return 3; };\n"
	  "	let e0 = tbl[0];\n"
	  "	if (len(e0.0) != 2) { return 4; };\n"
	  "	if (!(*e0.1)('a')) { return 5; };\n"
	  "	if ((*e0.1)('z')) { return 6; };\n"
	  "	return 0;\n"
	  "};\n", 0, K_RUN, NULL },
	/* write-face of leg (b): a tuple-LITERAL store into an indexed
	 * element `a[i] = (3,4)`, read back whole. DISTINCT words per row
	 * (3≠4, 7≠9) so the pre-fix word0-only store (cgen.c:6249 fell to
	 * the scalar tail) is CAUGHT — t.1 would read 0. Both faces (this
	 * store + the leg-b read) must be correct or the round-trip fails;
	 * the read alone was green by stale-register luck (809 tuple_elem). */
	{ "store_roundtrip",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "	let a: [2](u64, u64);\n"
	  "	a[1] = (3u64, 4u64);\n"
	  "	a[0] = (7u64, 9u64);\n"
	  "	let t = a[1];\n"
	  "	if (t.0 != 3) { return 1; };\n"
	  "	if (t.1 != 4) { return 2; };\n"
	  "	let s = a[0];\n"
	  "	if (s.0 != 7) { return 3; };\n"
	  "	if (s.1 != 9) { return 4; };\n"
	  "	return 0;\n"
	  "};\n", 0, K_RUN, NULL },
	/* leg (c): for-range over a module-global slice LOUD-STOPS,
	 * symmetric both stages (segfault→compile-error, byte-id-neutral).
	 * `n += 1` (not len()) sidesteps the #26 len-vs-int checker reject
	 * so the cgen loud is what fires, on BOTH stages. */
	{ "forrange_global_loud",
	  "package main;\n"
	  "fn fa(c: rune) bool = { return c == 'a'; };\n"
	  "const tbl: [](str, *fn(c: rune) bool) = "
	  "[(\"ab\", &fa), (\"cdef\", &fa)];\n"
	  "export fn main() i32 = {\n"
	  "	let n: int = 0;\n"
	  "	for (let e .. tbl) { n += 1; };\n"
	  "	return n: i32;\n"
	  "};\n", 0, K_BUILDERR,
	  "for-range over a module-global" },
};

static int
run_driver(const char *driver, const struct row *r, int i)
{
	char tmpdir[96], src[160], errf[160], outbin[160], rmcmd[176], cmd[1024];
	snprintf(tmpdir, sizeof tmpdir, "/tmp/tir_%d_d_%d", getpid(), i);
	mkdir(tmpdir, 0755);
	snprintf(src, sizeof src, "%s/tir_%d_%d.ww", tmpdir, getpid(), i);
	snprintf(errf, sizeof errf, "%s/tir_%d_e_%d", tmpdir, getpid(), i);
	snprintf(outbin, sizeof outbin, "%s/tir_%d_%d", tmpdir, getpid(), i);
	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 (r->kind == K_BUILDERR) {
		int ok = (brc != 0)
		    && (r->experr == NULL || errlog_has(errf, r->experr));
		if (!ok)
			fprintf(stderr, "row[%s]: %s expected loud builderr "
			    "\"%s\" (brc=%d)\n", r->label, driver,
			    r->experr ? r->experr : "", brc);
		runwait(rmcmd);
		return ok ? 0 : 1;
	}
	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/tir_asm_%d_%d.ww", getpid(), i);
	snprintf(cs,  sizeof cs,  "/tmp/tir_asm_%d_%d_c.s", getpid(), i);
	snprintf(ws,  sizeof ws,  "/tmp/tir_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, "tuple_index_read: %d/%d checks failed\n",
		    fail, total);
		return 1;
	}
	printf("tuple_index_read: %d/%d ok\n", total, total);
	return 0;
}