ww/test/wcc/814_def_arr_infer_len.c

/*
 * 814_def_arr_infer_len — cstage and wwstage agree, byte-for-byte and at
 * runtime, that a `def NAME: [_]T = [...]` array infers its length from
 * the initialiser's element count — the `def` twin of the `let` path
 * pinned by 684 (task #11 / #5; #7 wired only the let decl path).
 *
 * The bug (BOTH stages, byte-id identical): the `[_]` infer sentinel
 * (alen=0 / nil length-child) was stamped on the `let` decl path but NOT
 * on the `def` decl path. A `def [_]int = [10,20,30]` stayed sized 0,
 * emitted no/short DATA, and indexed reads (`TAB[1]`) / `.len` returned
 * garbage with no diagnostic (rule-7 silent miscompile).
 *
 * The fix (CHECKER ONLY — cgen already keys stride/length/DATA off the
 * stamped length, so `def [3]int` works today):
 *   - cstage cmd/wcc/check.c N_DEF pass-2: mirror the module N_LET path —
 *     if d->type is `[_]T` (TY_ARRAY, alen==0), chase the rhs type,
 *     rebuild type_array(.., iu->alen), and re-point BOTH d->type AND the
 *     installed SK_DEF Sym (an indexed read resolves the def through its
 *     Sym, so the Sym repoint is required).
 *   - wwstage selfhost/cmd/wcc/check.ww N_DEF arm: call inferarraylen(c,d)
 *     BEFORE resolvewalk stamps d.lhs's tinfo (the N_TARRAY AST is the
 *     SSoT; no Sym repoint needed). A `def [_]T` whose init is not an
 *     array literal can't infer → LOUD error, never a silent length-0.
 *
 * `def` is MODULE-SCOPE ONLY in both stages, so there is exactly one def
 * site per stage and every element type rides the single inference arm
 * (it is gated only on TY_ARRAY+alen==0, agnostic to the element type).
 *
 * SCOPE (corrected at impl-probe — the inference is complete, but two
 * adjacent shapes hit SEPARATE PRE-EXISTING cgen gaps that fail the SAME
 * way on an explicit-length `def [N]T`, so they are NOT #11 and are
 * excluded here; each is filed as its own task):
 *   - `def`-array `.len`/`.ptr` on wwstage falls to the SB fallback and
 *     emits `MOVQ len(SB)` (w6l: undefined reference). cstage handles it
 *     (so cstage vs wwstage asm also DIVERGES) — the wwstage cgdot
 *     def-array arm is missing, the def twin of #7's let-global cgdot
 *     fix. Every `.len` row is dropped for this reason.
 *   - `def [_]str` / `def [N]str` emit no DATA symbol (w6l: undefined
 *     reference, BOTH stages) — the #270 / str-slice-array-element DATA
 *     lineage. Every str row is dropped for this reason.
 * The pin therefore exercises INDEX reads across int / u8 / multi-dim,
 * which is exactly the shape #11 corrupts and is mutation-sensitive
 * (a collapse-to-0 def lays no DATA row, so the indexed read strikes
 * garbage / segv).
 *
 * The NEG row (`def [_]int = 5`, non-array init) proves the loud-error
 * arm fires (rule-7: never a silent zero-length array).
 *
 *   row           | shape                                      | want
 *   --------------+--------------------------------------------+-----
 *   def_int_i1    | def [_]int=[10,20,30], TAB[1]  (ken oracle)| 20
 *   def_int_last  | def [_]int=[10,20,30], TAB[2]  (full len)  | 30
 *   def_one_elem  | def [_]int=[7], A[0]  (1-elem edge)        | 7
 *   def_u8_first  | def [_]u8=[1..5], B[0]  (narrow stride)    | 1
 *   def_u8_last   | def [_]u8=[1..5], B[4]                     | 5
 *   def_2d_first  | def [_][2]int=[[1,2],[3,4],[5,6]], D[0][0] | 1
 *   def_2d_last   | def [_][2]int=[..], D[2][1]                | 6
 * NEG def_noarr   | def [_]int = 5;  (non-array init)          | BUILD FAIL
 */
#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; };

static const struct row rows[] = {
	/* INDEX reads only — the shape #11 corrupts. Reading the LAST
	 * element of an N-element def proves the inference stamped the full
	 * length: a collapse-to-0 lays no DATA row at that offset, so the
	 * read strikes garbage / segv. This is mutation-sensitive without
	 * `.len` (whose def-array codegen is a SEPARATE pre-existing gap —
	 * see the header). */
	{ "def_int_i1",
	  "package main;\n"
	  "def TAB: [_]int = [10, 20, 30];\n"
	  "export fn main() i32 = {\n"
	  "\treturn TAB[1]: i32;\n"
	  "};\n",
	  20 },

	{ "def_int_last",
	  "package main;\n"
	  "def TAB: [_]int = [10, 20, 30];\n"
	  "export fn main() i32 = {\n"
	  "\treturn TAB[2]: i32;\n"
	  "};\n",
	  30 },

	/* 1-element edge — the minimal non-empty count. */
	{ "def_one_elem",
	  "package main;\n"
	  "def A: [_]int = [7];\n"
	  "export fn main() i32 = {\n"
	  "\treturn A[0]: i32;\n"
	  "};\n",
	  7 },

	{ "def_u8_first",
	  "package main;\n"
	  "def B: [_]u8 = [1u8, 2u8, 3u8, 4u8, 5u8];\n"
	  "export fn main() i32 = {\n"
	  "\treturn B[0]: i32;\n"
	  "};\n",
	  1 },

	/* narrow (1B) stride — the last element of 5 proves both the stride
	 * and the inferred length. */
	{ "def_u8_last",
	  "package main;\n"
	  "def B: [_]u8 = [1u8, 2u8, 3u8, 4u8, 5u8];\n"
	  "export fn main() i32 = {\n"
	  "\treturn B[4]: i32;\n"
	  "};\n",
	  5 },

	/* multi-dim: outer `[_]` infers 3 from the row count, element type
	 * is the explicit `[2]int`. The def static-init DATA path lays the
	 * full 3x2 aggregate (the `let` runtime-store path for this shape is
	 * separately #270-1c-blocked, so this is def-only today). */
	{ "def_2d_first",
	  "package main;\n"
	  "def D: [_][2]int = [[1, 2], [3, 4], [5, 6]];\n"
	  "export fn main() i32 = {\n"
	  "\treturn D[0][0]: i32;\n"
	  "};\n",
	  1 },

	{ "def_2d_last",
	  "package main;\n"
	  "def D: [_][2]int = [[1, 2], [3, 4], [5, 6]];\n"
	  "export fn main() i32 = {\n"
	  "\treturn D[2][1]: i32;\n"
	  "};\n",
	  6 },
};

/* `def [_]T` whose initialiser is not an array literal can't infer its
 * length — both stages must FAIL the build (loud diagnostic, not a silent
 * zero-length array). `def` requires an `= value` init (parser), so the
 * no-init case can't reach the checker; the non-array init is the only
 * negative shape. */
static const char *neg[] = {
	/* non-array initialiser */
	"package main;\n"
	"def TAB: [_]int = 5;\n"
	"export fn main() i32 = { return 0; };\n",
};

/* Per-neg expected diagnostic body (parallel to neg[]); shared by both
 * stages (cstage prepends file:line:col, wwstage does not — #20). */
static const char *neg_diag[] = {
	"[_]T needs an array-literal initialiser",
};

static int
run_driver(const char *driver, const struct row *r, int i)
{
	char src[64], tmpdir[64], cmd[1024];
	snprintf(src, sizeof src, "/tmp/dail_%d_%d.ww", getpid(), i);
	snprintf(tmpdir, sizeof tmpdir, "/tmp/dail_%d_d_%d", getpid(), i);

	FILE *f = fopen(src, "wb");
	if (!f) return -1;
	fputs(r->src, f);
	fclose(f);

	mkdir(tmpdir, 0755);
	snprintf(cmd, sizeof cmd, "cd %s && %s build %s 2>/dev/null",
	    tmpdir, driver, src);
	if (runwait(cmd) != 0) {
		fprintf(stderr, "row[%s]: build via %s failed\n",
		    r->label, driver);
		unlink(src); rmdir(tmpdir);
		return -1;
	}

	const char *base = strrchr(src, '/');
	base = base ? base + 1 : src;
	char outbin[128];
	snprintf(outbin, sizeof outbin, "%s/%s", tmpdir, base);
	char *dot = strrchr(outbin, '.');
	if (dot && strcmp(dot, ".ww") == 0) *dot = '\0';
	int got = runwait(outbin);

	unlink(src); unlink(outbin); rmdir(tmpdir);
	return got;
}

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

/* build_should_fail — a `def [_]T` that can't infer must error on
 * `driver`; returns 0 when the build FAILS *and* emits `diag`. A crash
 * (segfault) wraps as a nonzero "w6c failed" with no diagnostic, so the
 * substring check distinguishes it from a clean reject (#20). */
static int
build_should_fail(const char *driver, const char *src, const char *diag,
    int i)
{
	char s[64], tmpdir[64], cmd[1024], errf[64];
	snprintf(s, sizeof s, "/tmp/dailn_%d_%d.ww", getpid(), i);
	snprintf(tmpdir, sizeof tmpdir, "/tmp/dailn_%d_d_%d", getpid(), i);
	snprintf(errf, sizeof errf, "/tmp/dailn_%d_e_%d.txt", getpid(), i);

	FILE *f = fopen(s, "wb");
	if (!f) return -1;
	fputs(src, f);
	fclose(f);

	mkdir(tmpdir, 0755);
	snprintf(cmd, sizeof cmd, "cd %s && %s build %s >/dev/null 2>%s",
	    tmpdir, driver, s, errf);
	int rc = runwait(cmd);
	int hasmsg = filehas(errf, diag);
	unlink(s);
	unlink(errf);
	/* clean any emitted binary */
	const char *base = strrchr(s, '/');
	base = base ? base + 1 : s;
	char outbin[128];
	snprintf(outbin, sizeof outbin, "%s/%s", tmpdir, base);
	char *dot = strrchr(outbin, '.');
	if (dot && strcmp(dot, ".ww") == 0) *dot = '\0';
	unlink(outbin);
	rmdir(tmpdir);
	/* build must NOT succeed AND must emit its diagnostic. */
	return (rc != 0 && hasmsg) ? 0 : -1;
}

/* asm_byte_identical — w6c vs w6c_ww .s for the same source must match.
 * The bug is byte-id-BLIND (both stages emitted identical wrong asm), so
 * this is a rule-10 convergence invariant, not a mutation detector. */
static int
asm_byte_identical(const char *bin, const struct row *r, int i)
{
	char src[64], cs[64], ws[64], cmd[1024];
	snprintf(src, sizeof src, "/tmp/dail_asm_%d_%d.ww", getpid(), i);
	snprintf(cs,  sizeof cs,  "/tmp/dail_asm_%d_%d_c.s", getpid(), i);
	snprintf(ws,  sizeof ws,  "/tmp/dail_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;
	}

	FILE *fc = fopen(cs, "rb");
	FILE *fw = fopen(ws, "rb");
	int rc = 0;
	if (!fc || !fw) {
		rc = -1;
	} else {
		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);
	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[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];
	snprintf(cdrv, sizeof cdrv, "%s/ww", bin);
	char wdrv[1024];
	snprintf(wdrv, sizeof wdrv, "%s/ww_ww", bin);

	struct { const char *name; const char *path; int gated_on_existence; }
	drivers[] = {
		{ "cstage",  cdrv, 0 },
		{ "wwstage", wdrv, 1 },
		{ NULL, NULL, 0 },
	};

	int n = (int)(sizeof rows / sizeof rows[0]);
	int nn = (int)(sizeof neg / sizeof neg[0]);
	int total = 0, fail = 0;

	for (int d = 0; drivers[d].name; d++) {
		if (drivers[d].gated_on_existence
		    && access(drivers[d].path, X_OK) != 0) {
			fprintf(stderr, "def_arr_infer_len: skip %s (no %s)\n",
			    drivers[d].name, drivers[d].path);
			continue;
		}
		for (int i = 0; i < n; i++) {
			int got = run_driver(drivers[d].path, &rows[i], i);
			total++;
			if (got != rows[i].want) {
				fprintf(stderr,
				    "def_arr_infer_len[%s][%s]: exit=%d want=%d\n",
				    drivers[d].name, rows[i].label,
				    got, rows[i].want);
				fail++;
			}
		}
		for (int i = 0; i < nn; i++) {
			total++;
			if (build_should_fail(drivers[d].path, neg[i],
			    neg_diag[i], 100 + i) != 0) {
				fprintf(stderr,
				    "def_arr_infer_len[%s][neg%d]: built ok, "
				    "expected a loud error\n",
				    drivers[d].name, i);
				fail++;
			}
		}
	}

	if (access(wdrv, X_OK) == 0) {
		for (int i = 0; i < n; i++) {
			total++;
			if (asm_byte_identical(bin, &rows[i], i) != 0)
				fail++;
		}
	}

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