Files
ww/lib/bytes/bytes.ww
Hojun-Cho 46edb8db4a w6c+selfhost+lib: cgen quality batch + lib Hare-shape graduation
Six fixes across the toolchain, surfaced by lib/lisp porting work.

  1. f64 compound assigns (`acc += d`, `-=`, `*=`, `/=`). Both stages
     load slot → X1, OP X0 into X1, store back (ADDSD/SUBSD/MULSD/
     DIVSD are reg-reg only). Previous MOVSD-overwrite dropped the
     OP. Locals and top-level lets.

  2. Top-level `[N]u8` arrays + `&arr[i]`. let_emit_size grows a
     TY_ARRAY branch so zero-init DATAW lands; cgindex / N_INDEX
     store / `&base[i]` all detect a global array base and use
     LEAQ name(SB) instead of LEAQ (BP). TK_AMP no longer pre-
     evaluates the operand as a value-load — `&base[i]` computes
     base + i*esz directly. Unblocks Hare's static-buffer pattern:
     strconv.{u64,i64,f64}tos graduate to module-level `*_buf`
     arrays and return owned views.

  3. Cross-module `pkg.Enum.MEMBER`. Nested N_DOT chains that
     don't fold to a known shape now emit `MOVQ <leaf>(SB), AX`
     (mirrors the bare-IDENT unresolved fallback), so isolation
     probes — and the test 990 cgen-match floor — stay consistent
     across stages. strconv exposes `base` as a real `enum i32`;
     callers updated. The `main` exemption (linker entry-point
     keeps bare name even when not exported) mirrors C-side
     collectmods into selfhost cgendecl.

  4. Sum-typed parameter ABI. lib/bytes.{index,rindex} take
     `(u8 | []u8)` needle; lib/strings.byteindex / rbyteindex take
     `(str | rune)` needle (Hare-shaped; the byte-wise misnomer
     `index` is dropped). tagged_arg_size cap bumps to 48 (6 int
     regs), with a new partial-fit branch on the callee: when an
     N-word tagged arg overflows remaining regs, fill what fits and
     stitch the rest from positive BP offsets. scanlocals MCASE
     handles slice binds (24B) and walks each arm with a saved /
     restored seenmark set so two arms naming the same local each
     get their own slot — matches cstage's per-arm scope reset.

  5. 4-reg tagged-return ABI (AX=tag, DX=word0, CX=word1, R8=word2),
     up from 3 regs. Slice-payload variants (`([]T | E)`, slot 32B)
     round-trip ptr/len/cap end-to-end. Every receive site updates:
     let-init via cgwidentaggedstore, match scrutinee spill, cgindex
     tagged-element load (both N_IDENT and fallback bases),
     pushargsrev tagged-ident arg (reads word count from slot size),
     cgreturn slice variant in the shuffle path.

  6. `expr: TaggedAlias` is a widening, not a re-interpret. C cgen +
     selfhost cgwidentaggedstore peel an N_CAST whose destination IS
     the union — so cgexpr's natural shape (str: AX=ptr, BX=len;
     slice: AX=ptr, BX=len, CX=cap) is consumed by the matching
     concrete-variant branch instead of being misread as a tagged
     AX/DX/CX triple. Inner casts to a concrete variant (`7: i32`)
     keep their type for proper tag lookup. `[N]Alias` arrays
     resolve element size via slotsize + aliaslookup, and aliaslookup
     strips a `pkg.` prefix so cross-module references work.

lib/fmt grows `formattable = (i64 | str | bool | rune)` plus
`printv` / `printlnv` taking an explicit `[]formattable` slice (the
receive side of Hare's `args: formattable...`). Call-site variadic
gather isn't wired — callers either hand-build the slice or compose
strconv.i64tos + strings.concat.

700_e2e: 114 → 123 rows (f64 compound, top-level u8 arrays + `&buf[i]`,
pkg.Enum.MEMBER, sum-typed (str|rune) and (u8|[]u8) params, 4-reg
slice-return ABI, formattable array). 26/26 tests, bootstrap stable
through ww4.
2026-05-13 08:05:01 +09:00

134 lines
2.9 KiB
Plaintext

// bytes — slice operations over []u8.
export fn equal(a: []u8, b: []u8) bool = {
let i: i32 = 0;
for (i < a.len) {
if (i >= b.len) { return false; };
if (a[i] != b[i]) { return false; };
i += 1;
};
return i == b.len;
};
// index — first index of `needle` in `s`. Mirrors Hare's bytes::index:
// `u8` needle scans for the byte, `[]u8` needle scans for the
// substring. Returns void if absent.
export fn index(s: []u8, needle: (u8 | []u8)) (i32 | void) = {
match (needle) {
case let c: u8 => {
let i: i32 = 0;
for (i < s.len) {
if (s[i] == c) { return i; };
i += 1;
};
return;
};
case let sub: []u8 => {
if (sub.len == 0) { return 0; };
if (sub.len > s.len) { return; };
let last: i32 = s.len - sub.len;
let i: i32 = 0;
for (i <= last) {
let j: i32 = 0;
let ok: bool = true;
for (j < sub.len) {
if (s[i + j] != sub[j]) { ok = false; j = sub.len; }
else { j += 1; };
};
if (ok) { return i; };
i += 1;
};
return;
};
};
return;
};
// rindex — last index of `needle` in `s`. Mirrors Hare's bytes::rindex.
// Empty []u8 needle matches at s.len.
export fn rindex(s: []u8, needle: (u8 | []u8)) (i32 | void) = {
match (needle) {
case let c: u8 => {
let i: i32 = s.len - 1;
for (i >= 0) {
if (s[i] == c) { return i; };
i -= 1;
};
return;
};
case let sub: []u8 => {
if (sub.len == 0) { return s.len; };
if (sub.len > s.len) { return; };
let i: i32 = s.len - sub.len;
for (i >= 0) {
let j: i32 = 0;
let ok: bool = true;
for (j < sub.len) {
if (s[i + j] != sub[j]) { ok = false; j = sub.len; }
else { j += 1; };
};
if (ok) { return i; };
i -= 1;
};
return;
};
};
return;
};
// contains — true iff `sub` appears in `s`. Mirrors Hare's
// bytes::contains for the slice case.
export fn contains(s: []u8, sub: []u8) bool = {
let r: (i32 | void) = index(s, sub);
match (r) {
case let i: i32 => return true;
case void => return false;
};
return false;
};
// hasprefix — `s` starts with `pre`. Mirrors Hare's bytes::hasprefix.
export fn hasprefix(s: []u8, pre: []u8) bool = {
if (pre.len > s.len) { return false; };
let i: i32 = 0;
for (i < pre.len) {
if (s[i] != pre[i]) { return false; };
i += 1;
};
return true;
};
// hassuffix — `s` ends with `suf`. Mirrors Hare's bytes::hassuffix.
export fn hassuffix(s: []u8, suf: []u8) bool = {
if (suf.len > s.len) { return false; };
let off: i32 = s.len - suf.len;
let i: i32 = 0;
for (i < suf.len) {
if (s[off + i] != suf[i]) { return false; };
i += 1;
};
return true;
};
// reverse — in-place reverse of `s`. Mirrors Hare's bytes::reverse.
export fn reverse(s: []u8) void = {
let i: i32 = 0;
let j: i32 = s.len - 1;
for (i < j) {
let t: u8 = s[i];
s[i] = s[j];
s[j] = t;
i += 1;
j -= 1;
};
};
// zero — set every byte of `s` to 0. Mirrors Hare's bytes::zero.
export fn zero(s: []u8) void = {
let i: i32 = 0;
for (i < s.len) {
s[i] = 0u8;
i += 1;
};
};