Hojun-Cho
7ca32432b1
`[_]T = [...]` (canonical Hare array-length inference) silently miscompiled to a zero-length array: the parser already left the array type's length child nil as the infer sentinel — distinct from an explicit [N] — but neither checker stamped the real count, so `len(x)` returned 0 with no diagnostic (rule-7 silent miscompile). Module-level was worse on wwstage, where `x.len` on ANY global array (even an explicit [N]) fell to the SB fallback and mis-emitted `MOVQ len(SB), AX` (linker: undefined reference to len). The length lives in the stamped TYPE and cgen already keys stride / length / data-emission off it, so stamping the inferred count at the one checker inference point closes it permanently (rob's #7 ruling): - check.c clet + module-level N_LET pass-2: count the initializer's elements and patch the array type's length (the Sym too, so a later x.len reads the inferred alen). No-init / non-array init can't infer -> loud error, never a silent zero-length array. - check.ww inferarraylen: the wwstage twin — stamp a synthesized N_INTLIT length child before resolvewalk caches the array tinfo; same loud-error rule. Idempotent for the module-level double-call. - cgenexpr.ww cgdot: the missing wwstage arm for a top-level [N]T global's .len / .ptr (cstage cgen.c:8011 already had it). - cgenutil.ww letslotsize: drop the now-redundant [_] slot-size intercept — a workaround for this very bug; the stamped length flows through the general slotsize path (rule 7). Both stages converge byte-identical; new table-driven test 684 covers [_]int/[_]str/[_]u8 local + module-level, len + element read-back, dual-stage runtime + asm byte-id, plus three negative no-infer rows.
350 lines
9.6 KiB
C
350 lines
9.6 KiB
C
/*
|
|
* 684_arr_infer_len — cstage and wwstage agree, byte-for-byte and at
|
|
* runtime, that a `[_]T = [...]` array infers its length from the
|
|
* initialiser's element count (task #7, a canonical Hare form).
|
|
*
|
|
* The bug: `[_]T` silently miscompiled to a zero-length array. The
|
|
* parser already left the array type's length child nil as the infer
|
|
* sentinel (distinct from an explicit `[N]`), but neither checker
|
|
* stamped the real count — so `len(x)` / `x.len` returned 0 with no
|
|
* diagnostic (rule-7 silent miscompile). Module-level was worse on
|
|
* wwstage: `x.len` on ANY global array (even explicit `[N]`) fell to
|
|
* the SB fallback and mis-emitted `MOVQ len(SB), AX` (linker:
|
|
* undefined reference to len).
|
|
*
|
|
* The fix (BOTH stages, converged byte-identical):
|
|
* - checker (cmd/wcc/check.c clet + module-level N_LET;
|
|
* selfhost/cmd/wcc/check.ww inferarraylen): count the array-literal
|
|
* elements and stamp the length onto the array TYPE. cgen already
|
|
* keys stride/length/data off the stamped length, so it "just
|
|
* works" (rob's #7 ruling). A `[_]T` with no array-literal init
|
|
* can't infer → LOUD error, never a silent zero-length array.
|
|
* - cgen (selfhost/cmd/wcc/cgenexpr.ww cgdot): a top-level `[N]T`
|
|
* global's `.len` / `.ptr` pseudo-fields, the wwstage arm that was
|
|
* missing (cstage cgen.c:8011 already handled it).
|
|
*
|
|
* Coverage: `[_]int` / `[_]str` / `[_]u8`, both local and module-level,
|
|
* `len` read-back and element read-back, dual-stage runtime + asm
|
|
* byte-id. Mutation-sanity: the old collapse-to-0 fails every `*_len`
|
|
* row (len would be 0, not the count). Plus three negative rows where
|
|
* `[_]T` can't infer (no init / non-array init) — both stages must
|
|
* FAIL the build.
|
|
*
|
|
* row | shape | want
|
|
* ----------------+--------------------------------------+------
|
|
* local_int_len | local [_]int=[10,20,30,40], x.len | 4
|
|
* local_int_elem | local, x[2] | 30
|
|
* mod_int_len | global [_]int=[..], x.len | 4
|
|
* mod_int_elem | global, x[2] | 30
|
|
* local_str_len | local [_]str=["a","b","c"], x.len | 3
|
|
* local_str_elem | local [_]str=["ab","cde"], x[0].len | 2
|
|
* mod_str_len | global [_]str=["a","b","c"], x.len | 3
|
|
* local_u8_len | local [_]u8=[1..5], x.len | 5
|
|
* local_u8_elem | local, x[4] | 5
|
|
*/
|
|
#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[] = {
|
|
{ "local_int_len",
|
|
"package main;\n"
|
|
"export fn main() i32 = {\n"
|
|
"\tlet x: [_]int = [10, 20, 30, 40];\n"
|
|
"\treturn x.len: i32;\n"
|
|
"};\n",
|
|
4 },
|
|
|
|
{ "local_int_elem",
|
|
"package main;\n"
|
|
"export fn main() i32 = {\n"
|
|
"\tlet x: [_]int = [10, 20, 30, 40];\n"
|
|
"\treturn x[2]: i32;\n"
|
|
"};\n",
|
|
30 },
|
|
|
|
{ "mod_int_len",
|
|
"package main;\n"
|
|
"let x: [_]int = [10, 20, 30, 40];\n"
|
|
"export fn main() i32 = {\n"
|
|
"\treturn x.len: i32;\n"
|
|
"};\n",
|
|
4 },
|
|
|
|
{ "mod_int_elem",
|
|
"package main;\n"
|
|
"let x: [_]int = [10, 20, 30, 40];\n"
|
|
"export fn main() i32 = {\n"
|
|
"\treturn x[2]: i32;\n"
|
|
"};\n",
|
|
30 },
|
|
|
|
{ "local_str_len",
|
|
"package main;\n"
|
|
"export fn main() i32 = {\n"
|
|
"\tlet x: [_]str = [\"a\", \"b\", \"c\"];\n"
|
|
"\treturn x.len: i32;\n"
|
|
"};\n",
|
|
3 },
|
|
|
|
{ "local_str_elem",
|
|
"package main;\n"
|
|
"export fn main() i32 = {\n"
|
|
"\tlet x: [_]str = [\"ab\", \"cde\"];\n"
|
|
"\treturn x[0].len: i32;\n"
|
|
"};\n",
|
|
2 },
|
|
|
|
{ "mod_str_len",
|
|
"package main;\n"
|
|
"let x: [_]str = [\"a\", \"b\", \"c\"];\n"
|
|
"export fn main() i32 = {\n"
|
|
"\treturn x.len: i32;\n"
|
|
"};\n",
|
|
3 },
|
|
|
|
{ "local_u8_len",
|
|
"package main;\n"
|
|
"export fn main() i32 = {\n"
|
|
"\tlet x: [_]u8 = [1u8, 2u8, 3u8, 4u8, 5u8];\n"
|
|
"\treturn x.len: i32;\n"
|
|
"};\n",
|
|
5 },
|
|
|
|
{ "local_u8_elem",
|
|
"package main;\n"
|
|
"export fn main() i32 = {\n"
|
|
"\tlet x: [_]u8 = [1u8, 2u8, 3u8, 4u8, 5u8];\n"
|
|
"\treturn x[4]: i32;\n"
|
|
"};\n",
|
|
5 },
|
|
};
|
|
|
|
/* `[_]T` that can't infer its length — both stages must FAIL the build
|
|
* (loud diagnostic, not a silent zero-length array). */
|
|
static const char *neg[] = {
|
|
/* no init, local */
|
|
"package main;\n"
|
|
"export fn main() i32 = {\n"
|
|
"\tlet x: [_]str;\n"
|
|
"\treturn 0;\n"
|
|
"};\n",
|
|
/* no init, module-level */
|
|
"package main;\n"
|
|
"let x: [_]int;\n"
|
|
"export fn main() i32 = { return 0; };\n",
|
|
/* non-array initialiser */
|
|
"package main;\n"
|
|
"export fn main() i32 = {\n"
|
|
"\tlet x: [_]int = 5;\n"
|
|
"\treturn 0;\n"
|
|
"};\n",
|
|
};
|
|
|
|
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/ail_%d_%d.ww", getpid(), i);
|
|
snprintf(tmpdir, sizeof tmpdir, "/tmp/ail_%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;
|
|
}
|
|
|
|
/* build_should_fail — a `[_]T` that can't infer must error on `driver`;
|
|
* returns 0 when the build correctly FAILS, non-zero when it wrongly
|
|
* succeeded. */
|
|
static int
|
|
build_should_fail(const char *driver, const char *src, int i)
|
|
{
|
|
char s[64], tmpdir[64], cmd[1024];
|
|
snprintf(s, sizeof s, "/tmp/ailn_%d_%d.ww", getpid(), i);
|
|
snprintf(tmpdir, sizeof tmpdir, "/tmp/ailn_%d_d_%d", 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 2>/dev/null",
|
|
tmpdir, driver, s);
|
|
int rc = runwait(cmd);
|
|
unlink(s);
|
|
/* 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);
|
|
return rc == 0 ? -1 : 0; /* build must NOT succeed */
|
|
}
|
|
|
|
/* asm_byte_identical — w6c vs w6c_ww .s for the same source must match. */
|
|
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/ail_asm_%d_%d.ww", getpid(), i);
|
|
snprintf(cs, sizeof cs, "/tmp/ail_asm_%d_%d_c.s", getpid(), i);
|
|
snprintf(ws, sizeof ws, "/tmp/ail_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, "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,
|
|
"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],
|
|
100 + i) != 0) {
|
|
fprintf(stderr,
|
|
"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,
|
|
"arr_infer_len: %d/%d fixtures failed\n", fail, total);
|
|
return 1;
|
|
}
|
|
printf("arr_infer_len: %d/%d ok\n", total, total);
|
|
return 0;
|
|
}
|