ww/test/wcc/919_strarray_static_run.c

/*
 * 919_strarray_static_run — BUG #18. Runtime + cs==ww byte-id net for a
 * module-level `let xs: [N]str = ["a","b",…];` static table.
 *
 * THE BUG (BOTH stages dropped it — shared-logic gap, not rule-10):
 *   A module-level [N]str static init emitted NO .data at all. The
 *   per-element str header carries a ptr→rodata relocation (not just
 *   bytes), so it can't ride emit_array_lit_bytes (byte-only): the str-
 *   element case fell through to fold_int_literal, returned 0, and
 *   emit_lets zero-init'd / skipped — leaving `main.<tab>` undefined.
 *   `w6l: undefined reference` at link. Function-LOCAL [N]str worked
 *   (runtime element stores); only the module-level STATIC DATA form was
 *   broken.
 *
 * THE FIX (#18): emit_strarray_data / emitstrarraydata apply the scalar-
 * str-global pattern (DATAW header with a zero ptr placeholder + inline
 * LE len, then a per-element `DATAR sym+idx*esz(SB),_S_n(SB)`) at each
 * element offset. let_pre_intern / letpreintern pre-intern each element
 * strlit so the _S_ rodata rows precede the DATAR references. Scoped to
 * the DATAW (`let`) directive — A_DATAR requires a DATAW holder.
 *
 * EACH ROW CARRIES BOTH DIMENSIONS (801 model):
 *   (a) cstage `ww build` + run, asserting the exit — proves the table's
 *       .len bytes are correct AND each element's .ptr relocation
 *       resolves to the right rodata label (the rows deref a NON-zero
 *       element's first byte, so a dropped/wrong reloc gives a wrong
 *       char — built-in negative control).
 *   (b) w6c vs w6c_ww `.s` cmp — FAILS if the stages diverge.
 *
 * GATE POLARITY: must stay GREEN. A wrong exit means the static table
 * relocations regressed; a byte-id FAIL means the stages diverged.
 *
 * NB: the rows read elements via the `.ptr`/`.len` pseudo-fields, NOT
 * the `len()` builtin — `len(xs[i])` on an indexed str element is a
 * separate pre-existing read-side miscompile (returns the ptr; filed
 * alongside #18), orthogonal to the emission fix under test here.
 */
#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[] = {
	/* .len bytes: 2+3+1 == 6. A dropped table would fail to link. */
	{ "strtab_len",
	  "package main;\n"
	  "let t: [3]str = [\"ab\",\"cde\",\"f\"];\n"
	  "export fn main() i32 = { return (t[0].len + t[1].len + t[2].len): i32; };\n",
	  6 },
	/* element-2 .ptr reloc: *(t[2].ptr) == 'C' (67), NOT 'A' — proves
	 * the +2*esz relocation resolves to "C", not element 0. */
	{ "strtab_ptr_elem2",
	  "package main;\n"
	  "let t: [3]str = [\"A\",\"B\",\"C\"];\n"
	  "export fn main() i32 = { let p: *u8 = t[2].ptr; return (*p): i32; };\n",
	  67 },
	/* runtime-indexed .ptr: i=1, *(t[i].ptr) == 'y' (121) — the
	 * LEAQ tab(SB)+i*esz addressing reaches the right element's reloc. */
	{ "strtab_ptr_varindex",
	  "package main;\n"
	  "let t: [3]str = [\"xx\",\"yyy\",\"z\"];\n"
	  "export fn main() i32 = { let i: i32 = 1; let p: *u8 = t[i].ptr; "
	  "return (*p): i32; };\n",
	  121 },
	/* empty-element (no reloc, len 0) followed by a real element: t[0]
	 * len==0, *(t[1].ptr) == 'Z' (90) — the empty slot must not shift
	 * the following element's reloc offset. */
	{ "strtab_empty_then_ptr",
	  "package main;\n"
	  "let t: [2]str = [\"\",\"Z\"];\n"
	  "export fn main() i32 = { if (t[0].len != 0) { return 88; }; "
	  "let p: *u8 = t[1].ptr; return (*p): i32; };\n",
	  90 },
	/* repeat suffix `[X, Y...]` — the trailing `...` fills the rest of
	 * [3]str with the last explicit element ("Y"). t[2] is a repeat-
	 * filled slot: *(t[2].ptr) == 'Y' (89), NOT 'X' — proves the +48
	 * fill row's DATAR resolves to last_ev ("Y"), exercising the
	 * repeat branch (its own len-fill + DATAR loop) the other rows skip. */
	{ "strtab_repeat_suffix",
	  "package main;\n"
	  "let t: [3]str = [\"X\",\"Y\"...];\n"
	  "export fn main() i32 = { let p: *u8 = t[2].ptr; return (*p): i32; };\n",
	  89 },
	{ 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, "strarray_static: w6c_ww missing — cannot run "
		    "the cs==ww byte-id gate\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/wwsas_%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 in a scratch dir. */
		char tmpdir[64];
		snprintf(tmpdir, sizeof tmpdir, "/tmp/wwsas_%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. */
		char cs_s[64], ws_s[64];
		snprintf(cs_s, sizeof cs_s, "/tmp/wwsas_%d_%d_cs.s", getpid(), i);
		snprintf(ws_s, sizeof ws_s, "/tmp/wwsas_%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 strarray static-init tests failed\n",
		    fail, n);
		return 1;
	}
	printf("strarray_static: %d/%d ok (cstage run + cs==ww byte-id)\n",
	    n, n);
	return 0;
}