Hojun-Cho
cbeffea7d8
Close A.3's deferred shape-14 (nested array). (a) emit_array_lit_bytes gains a TY_ARRAY-element arm (mechanical clone of the TY_STRUCT-element arm — recurses; esz=etype->size, rule-13; ...-nested loud-reject). (b) double-index read tbl[i][j]: when the indexed element is TY_ARRAY, leave the sub-array ADDRESS in AX instead of dereferencing (sister of #135's N_DOT-base fix, on the N_INDEX path) — new elemisarrayc/tinfoisarray helpers, both stages. Storage + read = one 2D-end-to-end concern (A.2/A.3 storage+LOAD precedent). Unblocks strconv fold-4's powers_of_ten[596][2]u64 (direct double-index access). Bootstrap-NEUTRAL (new arms gate on TY_ARRAY-element; 1D consumers byte-identical, 990-997 green). Test 919 +2D rows + 3D + ...-nested-reject. Deferred siblings: #155 (sub-array bind / whole- aggregate copy), #160 (global-struct-field index base).
357 lines
13 KiB
C
357 lines
13 KiB
C
/*
|
||
* 919_array_static_init_run — runtime + byte-id net for #129 Phase
|
||
* A.3: module-level let/def with array initializer.
|
||
*
|
||
* Pre-A.3 state:
|
||
* - Int-element arrays (u8/i8/u16/u32/u64/i32 etc) already worked
|
||
* in both stages via fold_int_literal.
|
||
* - Float-element arrays ([N]f64, [N]f32) → undef-ref at link
|
||
* (emit_lets array arm fold_int_literal fails on FLOATLIT).
|
||
* - Array DEFs (def A: [N]T = [...]) → emit_defs no array arm
|
||
* (storage missing) AND cgindex broken (reads LEAQ (BP), BX —
|
||
* stack frame, not data section).
|
||
* - Array-in-struct field (`def D: dt = dt{tag=42, buf=[...]}`) →
|
||
* #129 A.2 rule-7 fatal "array field rhs not foldable" — the
|
||
* shape parked in A.2 awaiting A.3.
|
||
*
|
||
* Phase A.3 fix (mirror A.1/A.2 SSoT-helper precedent):
|
||
* - cstage: emit_array_data + emit_array_lit_bytes helpers with
|
||
* element-kind dispatch (int via fold_int_literal preserving
|
||
* bootstrap byte-id, float via inline bitcast + sign-XOR byte-
|
||
* loop mirror of A.1, struct via emit_struct_lit_bytes recursion
|
||
* mirror of A.2). Two-pass validate-then-emit avoids partial-byte
|
||
* corruption on rhs-fold-failure.
|
||
* - cstage: emit_lets array arm routes through helper; emit_defs
|
||
* gains array arm.
|
||
* - cstage: DefArray registry + def_isarraydef populated in
|
||
* let_collect; cgindex N_INDEX direct-ident `isglobal` gate
|
||
* widened to (let_islet || def_isarraydef).
|
||
* - cstage: emit_struct_lit_bytes (A.2 helper) gains TY_ARRAY field
|
||
* arm calling emit_array_lit_bytes recursively (closes A.2 parked
|
||
* shape 15).
|
||
* - wwstage: parallel emitarraydata + emitarraylitbytes; emitstruct
|
||
* litbytes TY_ARRAY arm; defvartnode helper; cgindex falls through
|
||
* to defvartnode after letvartnode nil.
|
||
*
|
||
* Bootstrap RISK: live consumers in lib/os, lib/bufio, lib/strings,
|
||
* lib/encoding/utf8 (dfa + masks), lib/strconv/stof_data
|
||
* (left_shift_table). All use typed-int-literal elements; the int-elem
|
||
* helper path is byte-for-byte preserved → bootstrap NEUTRAL.
|
||
*
|
||
* Rows (size strata 1B/2B/4B/8B × count strata 1/2/4 × int/float/struct/
|
||
* empty/no-rhs/def-variant, avoiding the 16B-evade pattern from A.2):
|
||
*
|
||
* - (a) `let A: [4]u8 = [1u8, 2u8, 3u8, 4u8]` — 1B regression
|
||
* - (b) `let A: [4]u32 = [1u32, 2u32, 3u32, 4u32]` — 4B regression
|
||
* - (c) `let A: [2]u64 = [1u64, 2u64]` — 8B regression
|
||
* - (d) `let A: [4]i32 = [-1, -2, -3, -4]` — N_UN peel regression
|
||
* - (e) `let A: [4]f64 = [1.5, -2.5, 3.5, -4.5]` — NEW float-elem
|
||
* - (f) `let A: [4]f32 = [1.5f32, -2.5f32, 3.5f32, -4.5f32]` — NEW
|
||
* f32 narrow + sign-XOR per element
|
||
* - (g) `def A: [4]u32 = [11u32, 22u32, 33u32, 44u32]` — NEW
|
||
* def-storage + LOAD-widening
|
||
* - (h) `def A: [4]f64 = [1.5, 2.5, 3.5, 4.5]` — NEW def-variant of
|
||
* float
|
||
* - (i) `def D: dt = dt{tag=42, buf=[1u8,2u8,3u8,4u8]}` — NEW
|
||
* closes A.2 shape 15 (struct-with-array-field)
|
||
* - (j) `let A: [4]u8 = [0u8, 0u8, 0u8, 0u8]` — explicit-zero
|
||
* regression
|
||
* - (k) `let A: [1]u8 = [0u8]` — single-elem (matches lib/os/
|
||
* emptypath pattern)
|
||
*
|
||
* Each row: cstage `ww build` + run asserting exit code + w6c vs
|
||
* w6c_ww `.s` cmp (rule-10 byte-id).
|
||
*
|
||
* #156 (PREREQ-1) extends this with 2D `[N][M]T` static-init (a) +
|
||
* double-index read (b) — the A.3 shape-14 capstone, consumer-driven by
|
||
* fold-4's powers_of_ten[596][2]u64. emit_array_lit_bytes gains a
|
||
* TY_ARRAY-element arm (recurse; esz=etype->size); cgindex leaves the
|
||
* sub-array ADDRESS for an array element (sister of #135). Rows
|
||
* let_2d_x, def_2d_u64 and let_struct_2d_field + the nested-`...`
|
||
* loud-reject (rule-7) below. The D.m[i][j] global-struct-field-array
|
||
* READ stays a
|
||
* pre-existing gap (#160, 1D+2D, cs≠ww) out of scope here.
|
||
*
|
||
* Deferred:
|
||
* - Pointer-element arrays `[N]*T = [&G, &H]` — needs DATAR per
|
||
* element (own task/fold).
|
||
* - `...` repeat with a nested-array element — loud-reject (#156
|
||
* rule-7); no consumer (powers_of_ten is fully enumerated).
|
||
* - Bare-int `[N]u8 = [1, 2, 3, 4]` — #130 (checker issue).
|
||
* - Partial init `[4]u8 = [1u8]` — checker rejects (parser/checker
|
||
* decision).
|
||
*/
|
||
#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[] = {
|
||
{ "let_u8_arr",
|
||
"package main;\n"
|
||
"let A: [4]u8 = [1u8, 2u8, 3u8, 4u8];\n"
|
||
"export fn main() i32 = { return A[0]: i32; };\n", 1 },
|
||
{ "let_u32_arr",
|
||
"package main;\n"
|
||
"let A: [4]u32 = [1u32, 2u32, 3u32, 4u32];\n"
|
||
"export fn main() i32 = { return A[0]: i32; };\n", 1 },
|
||
{ "let_u64_arr",
|
||
"package main;\n"
|
||
"let A: [2]u64 = [1u64, 2u64];\n"
|
||
"export fn main() i32 = { return A[0]: i32; };\n", 1 },
|
||
{ "let_i32_neg_arr",
|
||
"package main;\n"
|
||
"let A: [4]i32 = [-1, -2, -3, -4];\n"
|
||
"export fn main() i32 = { return A[0]; };\n", 255 /* -1 */ },
|
||
/* Float-element array — NEW in A.3. Includes both signs to exercise
|
||
* the sign-XOR byte-loop per element. */
|
||
{ "let_f64_arr",
|
||
"package main;\n"
|
||
"let A: [4]f64 = [1.5, -2.5, 3.5, -4.5];\n"
|
||
"export fn main() i32 = { return (A[0]: i32); };\n", 1 },
|
||
{ "let_f32_arr",
|
||
"package main;\n"
|
||
"let A: [4]f32 = [1.5f32, -2.5f32, 3.5f32, -4.5f32];\n"
|
||
"export fn main() i32 = { return (A[0]: i32); };\n", 1 },
|
||
/* def-variant exercises the LOAD-widening (def_isarraydef) at
|
||
* cgindex/cgident. Storage emit also new. */
|
||
{ "def_u32_arr",
|
||
"package main;\n"
|
||
"def A: [4]u32 = [11u32, 22u32, 33u32, 44u32];\n"
|
||
"export fn main() i32 = { return A[0]: i32; };\n", 11 },
|
||
{ "def_f64_arr",
|
||
"package main;\n"
|
||
"def A: [4]f64 = [1.5, 2.5, 3.5, 4.5];\n"
|
||
"export fn main() i32 = { return (A[0]: i32); };\n", 1 },
|
||
/* The A.2-parked shape-15 — closes via emit_struct_lit_bytes
|
||
* TY_ARRAY field arm. */
|
||
{ "let_struct_with_arr_field",
|
||
"package main;\n"
|
||
"type dt = struct { tag: i32, buf: [4]u8 };\n"
|
||
"let D: dt = dt{tag=42, buf=[1u8, 2u8, 3u8, 4u8]};\n"
|
||
"export fn main() i32 = { return D.tag; };\n", 42 },
|
||
{ "let_u8_zero_arr",
|
||
"package main;\n"
|
||
"let A: [4]u8 = [0u8, 0u8, 0u8, 0u8];\n"
|
||
"export fn main() i32 = { return A[0]: i32; };\n", 0 },
|
||
{ "let_u8_single",
|
||
"package main;\n"
|
||
"let A: [1]u8 = [7u8];\n"
|
||
"export fn main() i32 = { return A[0]: i32; };\n", 7 },
|
||
/* #156 (PREREQ-1): 2D [N][M]T static-init (a) + double-index read
|
||
* (b) — the A.3 shape-14 capstone, consumer-driven by fold-4's
|
||
* powers_of_ten[596][2]u64. emit_array_lit_bytes recurses on the
|
||
* TY_ARRAY element (esz=etype->size, rule-13); cgindex leaves the
|
||
* sub-array ADDRESS (not a value) for an array element so the outer
|
||
* index dereferences the right cell (sister of #135). */
|
||
{ "let_2d_u64",
|
||
"package main;\n"
|
||
"let A: [3][2]u64 = [[1u64,2u64],[3u64,4u64],[5u64,6u64]];\n"
|
||
"export fn main() i32 = { return A[1][0]: i32; };\n", 3 },
|
||
{ "def_2d_u64",
|
||
"package main;\n"
|
||
"def A: [3][2]u64 = [[1u64,2u64],[3u64,4u64],[5u64,6u64]];\n"
|
||
"export fn main() i32 = { return A[2][1]: i32; };\n", 6 },
|
||
/* variable-index read — the exact fold-4 access pattern
|
||
* (powers_of_ten[i][0]/[i][1]). 21 + 30 = 51. */
|
||
{ "let_2d_varidx",
|
||
"package main;\n"
|
||
"let A: [3][2]u64 = [[10u64,11u64],[20u64,21u64],[30u64,31u64]];\n"
|
||
"fn at(i: i32, j: i32) u64 = { return A[i][j]; };\n"
|
||
"export fn main() i32 = { return (at(1, 1) + at(2, 0)): i32; };\n",
|
||
51 },
|
||
/* 8-byte 2D: must NOT hit the sz==8 scalar short-circuit (the
|
||
* isarr8/N_TARRAY guard, #128 lesson) — routes to the array arm. */
|
||
{ "let_2d_u32_8byte",
|
||
"package main;\n"
|
||
"let A: [2][1]u32 = [[7u32],[9u32]];\n"
|
||
"export fn main() i32 = { return A[1][0]: i32; };\n", 9 },
|
||
/* 2D write to one cell, sum all four — verifies the lvalue address
|
||
* targets the exact cell with no neighbour clobber. 1+2+99+4=106. */
|
||
{ "let_2d_write",
|
||
"package main;\n"
|
||
"let A: [2][2]u64 = [[1u64,2u64],[3u64,4u64]];\n"
|
||
"export fn main() i32 = { A[1][0] = 99u64; return "
|
||
"(A[0][0]+A[0][1]+A[1][0]+A[1][1]): i32; };\n", 106 },
|
||
/* struct field that is itself a 2D array — static-init emit +
|
||
* layout (read D.tag). The D.m[i][j] field-array READ exercises a
|
||
* pre-existing global-struct-field-base bug (#137/#150 family,
|
||
* 1D+2D, cs≠ww) out of PREREQ-1 scope — the array bytes are
|
||
* covered by the cs==ww byte-id gate below. */
|
||
{ "let_struct_2d_field",
|
||
"package main;\n"
|
||
"type dt = struct { tag: i32, m: [2][2]u64 };\n"
|
||
"let D: dt = dt{tag=42, m=[[1u64,2u64],[3u64,4u64]]};\n"
|
||
"export fn main() i32 = { return D.tag; };\n", 42 },
|
||
/* 3D — locks recursion-depth>2 in both emit (nested TY_ARRAY arm
|
||
* recurses twice) and read (double-then-single index, two
|
||
* address-leaves). [[[1,2],[3,4]],[[5,6],[7,8]]]; A[1][1][0] = 7. */
|
||
{ "let_3d_u8",
|
||
"package main;\n"
|
||
"let A: [2][2][2]u8 = "
|
||
"[[[1u8,2u8],[3u8,4u8]],[[5u8,6u8],[7u8,8u8]]];\n"
|
||
"export fn main() i32 = { return A[1][1][0]: i32; };\n", 7 },
|
||
{ 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, "arrinit: w6c_ww missing — cannot run "
|
||
"the cs==ww byte-id gate (the whole point of this test)\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/wwari_%d_%d.ww", getpid(), i);
|
||
FILE *f = fopen(src, "wb");
|
||
if (f == NULL) { fail++; continue; }
|
||
fputs(rows[i].src, f);
|
||
fclose(f);
|
||
|
||
char tmpdir[64];
|
||
snprintf(tmpdir, sizeof tmpdir, "/tmp/wwari_%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);
|
||
|
||
char cs_s[64], ws_s[64];
|
||
snprintf(cs_s, sizeof cs_s, "/tmp/wwari_%d_%d_cs.s",
|
||
getpid(), i);
|
||
snprintf(ws_s, sizeof ws_s, "/tmp/wwari_%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);
|
||
}
|
||
|
||
/* #156 rule-7: a `...` repeat marker with a nested-array element is
|
||
* a loud reject in BOTH stages (no consumer needs it; powers_of_ten
|
||
* is fully enumerated). The compile must FAIL, not silently emit
|
||
* wrong bytes. Separate from the rows table (which asserts build
|
||
* success). */
|
||
{
|
||
char src[64];
|
||
snprintf(src, sizeof src, "/tmp/wwari_%d_rej.ww", getpid());
|
||
FILE *f = fopen(src, "wb");
|
||
if (f != NULL) {
|
||
fputs("package main;\n"
|
||
"let A: [4][2]u64 = [[1u64, 2u64]...];\n"
|
||
"export fn main() i32 = { return 0; };\n", f);
|
||
fclose(f);
|
||
}
|
||
char cmd[2048];
|
||
snprintf(cmd, sizeof cmd, "%s -o /dev/null %s 2>/dev/null",
|
||
w6c, src);
|
||
int rc_cs = runwait(cmd);
|
||
snprintf(cmd, sizeof cmd, "%s -o /dev/null %s 2>/dev/null",
|
||
w6c_ww, src);
|
||
int rc_ww = runwait(cmd);
|
||
n++;
|
||
if (rc_cs == 0 || rc_ww == 0) {
|
||
fprintf(stderr, "row[nested_ellipsis_reject]: expected "
|
||
"BOTH stages to reject (cs=%d ww=%d), want nonzero "
|
||
"(#156 rule-7)\n", rc_cs, rc_ww);
|
||
fail++;
|
||
}
|
||
unlink(src);
|
||
}
|
||
|
||
if (fail) {
|
||
fprintf(stderr, "%d/%d array-static-init tests failed\n", fail, n);
|
||
return 1;
|
||
}
|
||
printf("arrinit: %d/%d ok (cstage run + cs==ww byte-id)\n",
|
||
n, n);
|
||
return 0;
|
||
}
|