diff --git a/Makefile b/Makefile index f5c5484f..59a4fe95 100644 --- a/Makefile +++ b/Makefile @@ -259,6 +259,7 @@ TESTS = $(BIN)/test_smoke $(BIN)/test_lex $(BIN)/test_parse $(BIN)/test_check \ $(BIN)/test_overlong_arrlit \ $(BIN)/test_tuple_elem_overlong \ $(BIN)/test_tagged_arr_variant \ + $(BIN)/test_nested_union_int_box \ $(BIN)/test_inferred_array_global \ $(BIN)/test_slice_str_global_arg \ $(BIN)/test_slice_str_global_zero \ @@ -730,6 +731,12 @@ $(BIN)/test_tagged_arr_variant: test/wcc/834_tagged_arr_variant.c $(BIN)/ww \ $(LIB)/libwwrt.a | $(BIN) $(CC) $(CFLAGS) -o $@ $< +$(BIN)/test_nested_union_int_box: test/wcc/835_nested_union_int_box.c $(BIN)/ww \ + $(BIN)/w6c $(BIN)/w6a $(BIN)/w6l \ + $(BIN)/ww_ww $(BIN)/w6c_ww $(BIN)/w6a_ww $(BIN)/w6l_ww \ + $(LIB)/libwwrt.a | $(BIN) + $(CC) $(CFLAGS) -o $@ $< + $(BIN)/test_inferred_array_global: test/wcc/833_inferred_array_global.c $(BIN)/ww \ $(BIN)/w6c $(BIN)/w6a $(BIN)/w6l \ $(BIN)/ww_ww $(BIN)/w6c_ww $(BIN)/w6a_ww $(BIN)/w6l_ww \ diff --git a/selfhost/cmd/w6c/main.combined.ww b/selfhost/cmd/w6c/main.combined.ww index c300abb3..8b85015d 100644 --- a/selfhost/cmd/w6c/main.combined.ww +++ b/selfhost/cmd/w6c/main.combined.ww @@ -14084,11 +14084,27 @@ fn isassignable(c: *checker, dst: *node, src: *node, confident: *bool) bool = { let vu: *node = resolvealias(c, unwrapbang(v)); if (vu != nil) { if (isnumerictname(vu)) { return true; }; + // mirror cstage type_isnum(enum)=true (type.c:201 -> + // type_isint -> :178 TY_ENUM); an enum variant DOES + // accept an untyped int. Without this the #23 fix would + // flip an enum-variant union to reject while cstage + // accepts = a NEW divergence (A3 trap). + if (vu.kind == nkind.N_TENUM) { return true; }; }; v = v.next; }; - *confident = false; - return true; + // #23: no DIRECT variant accepts an untyped int -> confident + // reject (mirror cstage type.c:343 `return 0`). ww does NOT + // flatten a nested union variant (#199-alpha non-drill); an int + // reachable only via a nested union (e.g. (inner|str), + // inner=(int|bool)) would otherwise silently build tag=0/payload + // with no inner-tag wrapper = malformed box. *confident is + // already true (:3777, untouched on this path) so the caller + // sees ok=false,conf=true -> loud errnotassign. DEFERRED + // divergence (task #23 / #199b): both stages then over-reject + // valid Hare (expand_tagged flattens); faithful flatten+rebox + // is post-CSP nominal-identity work. + return false; }; // Known non-numeric primitive: confidently wrong. if (du.kind == nkind.N_TNAME) { diff --git a/selfhost/cmd/wcc/check.ww b/selfhost/cmd/wcc/check.ww index 7f6c449d..e43b306a 100644 --- a/selfhost/cmd/wcc/check.ww +++ b/selfhost/cmd/wcc/check.ww @@ -3803,11 +3803,27 @@ fn isassignable(c: *checker, dst: *node, src: *node, confident: *bool) bool = { let vu: *node = resolvealias(c, unwrapbang(v)); if (vu != nil) { if (isnumerictname(vu)) { return true; }; + // mirror cstage type_isnum(enum)=true (type.c:201 -> + // type_isint -> :178 TY_ENUM); an enum variant DOES + // accept an untyped int. Without this the #23 fix would + // flip an enum-variant union to reject while cstage + // accepts = a NEW divergence (A3 trap). + if (vu.kind == nkind.N_TENUM) { return true; }; }; v = v.next; }; - *confident = false; - return true; + // #23: no DIRECT variant accepts an untyped int -> confident + // reject (mirror cstage type.c:343 `return 0`). ww does NOT + // flatten a nested union variant (#199-alpha non-drill); an int + // reachable only via a nested union (e.g. (inner|str), + // inner=(int|bool)) would otherwise silently build tag=0/payload + // with no inner-tag wrapper = malformed box. *confident is + // already true (:3777, untouched on this path) so the caller + // sees ok=false,conf=true -> loud errnotassign. DEFERRED + // divergence (task #23 / #199b): both stages then over-reject + // valid Hare (expand_tagged flattens); faithful flatten+rebox + // is post-CSP nominal-identity work. + return false; }; // Known non-numeric primitive: confidently wrong. if (du.kind == nkind.N_TNAME) { diff --git a/selfhost/cmd/wwdump/main.combined.ww b/selfhost/cmd/wwdump/main.combined.ww index b08a3fe1..516adf28 100644 --- a/selfhost/cmd/wwdump/main.combined.ww +++ b/selfhost/cmd/wwdump/main.combined.ww @@ -14084,11 +14084,27 @@ fn isassignable(c: *checker, dst: *node, src: *node, confident: *bool) bool = { let vu: *node = resolvealias(c, unwrapbang(v)); if (vu != nil) { if (isnumerictname(vu)) { return true; }; + // mirror cstage type_isnum(enum)=true (type.c:201 -> + // type_isint -> :178 TY_ENUM); an enum variant DOES + // accept an untyped int. Without this the #23 fix would + // flip an enum-variant union to reject while cstage + // accepts = a NEW divergence (A3 trap). + if (vu.kind == nkind.N_TENUM) { return true; }; }; v = v.next; }; - *confident = false; - return true; + // #23: no DIRECT variant accepts an untyped int -> confident + // reject (mirror cstage type.c:343 `return 0`). ww does NOT + // flatten a nested union variant (#199-alpha non-drill); an int + // reachable only via a nested union (e.g. (inner|str), + // inner=(int|bool)) would otherwise silently build tag=0/payload + // with no inner-tag wrapper = malformed box. *confident is + // already true (:3777, untouched on this path) so the caller + // sees ok=false,conf=true -> loud errnotassign. DEFERRED + // divergence (task #23 / #199b): both stages then over-reject + // valid Hare (expand_tagged flattens); faithful flatten+rebox + // is post-CSP nominal-identity work. + return false; }; // Known non-numeric primitive: confidently wrong. if (du.kind == nkind.N_TNAME) { diff --git a/test/wcc/835_nested_union_int_box.c b/test/wcc/835_nested_union_int_box.c new file mode 100644 index 00000000..581403a9 --- /dev/null +++ b/test/wcc/835_nested_union_int_box.c @@ -0,0 +1,263 @@ +/* + * 835_nested_union_int_box — two reject-align fixes in the nested-union / + * widen-subset family. Both close SILENT wwstage miscompiles by aligning + * ww DOWN to cstage's existing loud. + * + * #23 (drew spec .ai/drew-23-spec.md) — a bare untyped-int return/assign + * into a tagged union with NO DIRECT variant able to hold an int (the int + * is reachable only via a NESTED union, or no slot exists at all). ww's + * isuntypedint tagged sub-loop fell through to a permissive `*confident= + * false; return true;` so the caller never flagged it — ww silently built + * a tag=0/payload box with no inner-tag wrapper (malformed). The fix: + * confident-reject when no direct variant is numeric-or-enum (mirror + * cstage type.c:343 `return 0`), routing through errnotassign. An ENUM + * variant is kept ACCEPTED (new N_TENUM check, mirrors cstage type_isnum + * (enum)=true) — A3 is the trap: dropping it would flip an enum-variant + * union to reject while cstage accepts. wwstage-ONLY; check.c unchanged. + * + * neg row | shape | gate + * -------------+------------------------------------------------+------ + * R1_nested | inner=(int|bool); outer=(inner|str); ret 5 | FAIL + * R2_noslot | u=(str|bool); ret 5 | FAIL + * R3_struct | A=struct{v:int}; u=(A|str); ret 5 | FAIL + * + * pos row | shape | want + * -------------+------------------------------------------------+------ + * A1_direct | u=(int|str); ret 5; match int -> n | 5 + * A2_aliased | myint=int; u=(myint|str); ret 5 | 0 + * A3_enum | col=enum{RED,GREEN}; u=(col|str); ret 5 [trap] | 0 + * A4_unionsrc | outer=(inner|str); mk(x:inner) outer = x | 0 + * A5_subset | sub=(int|uint); sup=(int|uint|str); ret x | 0 + * + * Diagnostic TEXT is byte-id-blind (#23 routes through errnotassign "not + * assignable"); both stages REJECT and emit no asm. + * selfhost has no such construct, so 990-997 byte-id is untouched. + */ +#include +#include +#include +#include +#include +#include + +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[] = { + /* A1 — direct numeric variant; live runtime proof the accept path + * still builds a correct box (match int -> return 5). */ + { "A1_direct", + "package main;\n" + "type u = (int | str);\n" + "fn mk() u = { return 5; };\n" + "export fn main() i32 = {\n" + "\tlet v = mk();\n" + "\tmatch (v) {\n" + "\tcase let n: int => return n: i32;\n" + "\tcase str => return 1;\n" + "\t};\n" + "\treturn 9;\n" + "};\n", + 5 }, + + /* A2 — aliased numeric variant (resolvealias -> int). Compile-only: + * main returns 0; the accept is proven by the build succeeding. */ + { "A2_aliased", + "package main;\n" + "type myint = int;\n" + "type u = (myint | str);\n" + "fn mk() u = { return 5; };\n" + "export fn main() i32 = { return 0; };\n", + 0 }, + + /* A3 — enum variant (the trap): the N_TENUM accept keeps this legal, + * mirroring cstage type_isnum(enum). Compile-only. */ + { "A3_enum", + "package main;\n" + "type col = enum { RED, GREEN };\n" + "type u = (col | str);\n" + "fn mk() u = { return 5; };\n" + "export fn main() i32 = { return 0; };\n", + 0 }, + + /* A4 — src is a UNION (inner), not an untyped int -> never enters the + * int arm; tagged->tagged direct-variant accept. Compile-only. */ + { "A4_unionsrc", + "package main;\n" + "type inner = (int | bool);\n" + "type outer = (inner | str);\n" + "fn mk(x: inner) outer = { return x; };\n" + "export fn main() i32 = { return 0; };\n", + 0 }, + + /* A5 — proper-subset union widen, src union. Compile-only. */ + { "A5_subset", + "package main;\n" + "type sub = (int | uint);\n" + "type sup = (int | uint | str);\n" + "fn w(x: sub) sup = { return x; };\n" + "export fn main() i32 = { return 0; };\n", + 0 }, +}; + +/* Each neg must FAIL the build on both stages (loud reject). */ +static const char *neg[] = { + /* R1 — #23 canonical: int reachable only via a NESTED union. */ + "package main;\n" + "type inner = (int | bool);\n" + "type outer = (inner | str);\n" + "fn mk() outer = { return 5; };\n" + "export fn main() i32 = { return 0; };\n", + /* R2 — no slot for an int at all (same fallthrough). */ + "package main;\n" + "type u = (str | bool);\n" + "fn mk() u = { return 5; };\n" + "export fn main() i32 = { return 0; };\n", + /* R3 — int fits no variant (struct | str). */ + "package main;\n" + "type A = struct { v: int };\n" + "type u = (A | str);\n" + "fn mk() u = { return 5; };\n" + "export fn main() i32 = { return 0; };\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/nui_%d_%d.ww", getpid(), i); + snprintf(tmpdir, sizeof tmpdir, "/tmp/nui_%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 — the construct 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/nuin_%d_%d.ww", getpid(), i); + snprintf(tmpdir, sizeof tmpdir, "/tmp/nuin_%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); + 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 */ +} + +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, "nested_union_int_box: 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, + "nested_union_int_box[%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, + "nested_union_int_box[%s][neg%d]: built ok, " + "expected a loud reject\n", + drivers[d].name, i); + fail++; + } + } + } + + if (fail) { + fprintf(stderr, + "nested_union_int_box: %d/%d fixtures failed\n", fail, total); + return 1; + } + printf("nested_union_int_box: %d/%d ok\n", total, total); + return 0; +}