Hojun-Cho/ww
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

lib/bytes+test: Hare port (equal / index / rindex / contains / has{prefix,suffix} / reverse / zero)

Browse Source 
Mirrors ref/hare/bytes/{equal,index,contains,reverse,zero}.ha for
the in-tree subset used by lib/encoding, lib/bufio, lib/memio;
converts 4 hextest sites from local beq to bytes.equal and drops
the now-dead beq in utf8test.

Surface:
  - equal(a, b: []u8) bool
  - index(s: []u8, needle: (u8 | []u8)) (i32 | void)
  - rindex(s: []u8, needle: (u8 | []u8)) (i32 | void)
  - contains(s: []u8, needle: (u8 | []u8)) bool
  - hasprefix(s, pre: []u8) bool
  - hassuffix(s, suf: []u8) bool
  - reverse(s: []u8) void  (already present, citation added)
  - zero(s: []u8) void  (already present, citation added)

Two documented Hare-fidelity gaps (cited in lib/bytes/bytes.ww
header, no in-tree caller demands them yet):
  - index_slice / rindex_slice use naive O(n·m). Hare specialises
    2/3/4-byte needles + falls back to Crochemore-Perrin two-way
    (ref/hare/bytes/two_way.ha). Correctness equivalent.
  - contains takes a single needle. Hare uses variadic
    needle: (u8 | []u8)... (ref/hare/bytes/contains.ha:5).

Tests: 967_bytes_run drives lib/bytes/bytestest.ww via ww run.
Eight @test fns × table-driven row sets: equal (5), index_byte
(5), index_slice (10), rindex_byte (3), rindex_slice (3),
contains (4), hasprefix (6 verbatim from contains.ha:25),
hassuffix (6 verbatim from contains.ha:40).

Call-site conversions in the same commit (the conversions are
the proof the API is wired): lib/encoding/hex/hextest.ww drops
the local beq helper and 4 callers switch to bytes.equal;
lib/encoding/utf8/utf8test.ww drops the dead beq helper.

91/91 ok. 995_self_rebuild stays green (ww2==ww3==ww4 byte-id).
This commit is contained in:
Hojun-Cho
2026-05-18 00:48:14 +09:00
parent a7700f201b
commit a6abac22d8
6 changed files with 336 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
lib/bytes/bytes.ww
View File

@@ -1,18 +1,31 @@
// bytes — slice operations over []u8.
// bytes — slice operations over []u8. Mirrors Hare's bytes module
// (ref/hare/bytes/) for the in-tree subset: search/equality/prefix
// helpers used by lib/encoding, lib/bufio, lib/memio.
//
// Documented divergences from Hare:
// - index_slice / rindex_slice use naive O(n·m); Hare specialises
// 2/3/4-byte needles and falls back to two_way (Crochemore-Perrin)
// for longer (ref/hare/bytes/index.ha:61, ref/hare/bytes/two_way.ha).
// Correctness equivalent.
// - contains takes a single needle; Hare's contains is variadic
// `(u8 | []u8)...` (ref/hare/bytes/contains.ha:5). No caller needs
// the variadic shape yet; graduate when one does.
// equal — true iff `a` and `b` have the same length and contents.
// ref/hare/bytes/equal.ha:9.
export fn equal(a: []u8, b: []u8) bool = {
if (a.len != b.len) { return false; };
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;
return true;
};
// 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.
// index — first offset of `needle` in `s`. u8 needle scans for the
// byte; []u8 needle scans for the substring. void if absent.
// ref/hare/bytes/index.ha:6.
export fn index(s: []u8, needle: (u8 | []u8)) (i32 | void) = {
match (needle) {
case let c: u8 => {
@@ -44,8 +57,9 @@ export fn index(s: []u8, needle: (u8 | []u8)) (i32 | void) = {
return;
};
// rindex — last index of `needle` in `s`. Mirrors Hare's bytes::rindex.
// Empty []u8 needle matches at s.len.
// rindex — last offset of `needle` in `s`. Empty []u8 needle returns
// s.len (ref/hare/bytes/index.ha:103 — Hare's loop yields r-0 at i=0).
// ref/hare/bytes/index.ha:86.
export fn rindex(s: []u8, needle: (u8 | []u8)) (i32 | void) = {
match (needle) {
case let c: u8 => {
@@ -76,18 +90,18 @@ export fn rindex(s: []u8, needle: (u8 | []u8)) (i32 | void) = {
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) {
// contains — true iff `needle` (byte or sub-slice) appears in `s`.
// ref/hare/bytes/contains.ha:5 (variadic subset; see header note).
export fn contains(s: []u8, needle: (u8 | []u8)) bool = {
match (index(s, needle)) {
case let i: i32 => return true;
case void => return false;
};
return false;
};
// hasprefix — `s` starts with `pre`. Mirrors Hare's bytes::hasprefix.
// hasprefix — true iff `s` starts with `pre`.
// ref/hare/bytes/contains.ha:21.
export fn hasprefix(s: []u8, pre: []u8) bool = {
if (pre.len > s.len) { return false; };
let i: i32 = 0;
@@ -98,7 +112,8 @@ export fn hasprefix(s: []u8, pre: []u8) bool = {
return true;
};
// hassuffix — `s` ends with `suf`. Mirrors Hare's bytes::hassuffix.
// hassuffix — true iff `s` ends with `suf`.
// ref/hare/bytes/contains.ha:35.
export fn hassuffix(s: []u8, suf: []u8) bool = {
if (suf.len > s.len) { return false; };
let off: i32 = s.len - suf.len;
@@ -110,7 +125,7 @@ export fn hassuffix(s: []u8, suf: []u8) bool = {
return true;
};
// reverse — in-place reverse of `s`. Mirrors Hare's bytes::reverse.
// reverse — in-place reverse of `s`. ref/hare/bytes/reverse.ha:5.
export fn reverse(s: []u8) void = {
let i: i32 = 0;
let j: i32 = s.len - 1;
@@ -123,7 +138,7 @@ export fn reverse(s: []u8) void = {
};
};
// zero — set every byte of `s` to 0. Mirrors Hare's bytes::zero.
// zero — set every byte of `s` to 0. ref/hare/bytes/zero.ha:5.
export fn zero(s: []u8) void = {
let i: i32 = 0;
for (i < s.len) {