Files
ww/lib/strings/strings.ww
Hojun-Cho a651883c14 lib/strings+test: Hare port (dup/concat/trim/index/contains/has{pre,suf}fix/compare/utf8)
Hare-faithful index/predicate family per ref/hare/strings/{dup,
concat,trim,index,suffix,contains,compare,utf8}.ha. Non-variadic
subset (concat 2-arg, trim single-rune, contains single-needle)
pending task #16 — cstage variadic-pack drops .len on multi-field
element types; ship the Hare-faithful single-arg shape now, file
the variadic upgrade as follow-up. `sub` follow-up filed as #29
(commit 2 with iterator + utf8.chars relocation).

Surface: dup, concat, trim/trimprefix/trimsuffix (single rune),
hasprefix, hassuffix (both with (str|rune) sum needle),
byteindex, rbyteindex (both with (str|rune) sum needle),
contains (single str needle), compare, toutf8, fromutf8_unsafe,
runebytes helper. (str|rune) match arms route the rune via
utf8.encoderune into a [4]u8 scratch then bytes.index/rindex —
drew-devault's directive for clean Hare-fidelity over invented
ASCII-only rune-byte arms.

byteindex / rbyteindex rune-arm semantic correction —
corpus-coverage-blind unmask. Pre-existing impl scanned for
`r: u8` (broken for all rune values >0x7F since strings.ww first
landed; no caller exercised it). Replaced with utf8.encoderune-
based scan via runebytes helper. Severity-marker: silent
wrong-result for any non-ASCII rune needle, masked by zero
in-tree callers until lib/strings + utf8 chain pulled the shape
in.

Build-system propagation: lib/strings depends transitively on
lib/encoding/utf8 (via byteindex's rune arm). cmd/ww driver's
locate_import_in (cmd/ww/main.c:85) walks `<dir>/<name>.ww` and
`<dir>/<name>/<name>.ww` only — `use utf8;` doesn't find
lib/encoding/utf8/utf8.ww without explicit `-I lib/encoding/utf8`.
Propagated through 5 wwstage-tool Makefile targets + 7 test
wrappers + test/wcc/995_self_rebuild.c sprintf lines. Task #17
filed for the principled resolver fix (subdir walk vs Hare's
qualified `use encoding::utf8;` notation).

This commit chain (#15 strings) surfaced 7 cgen bugs during
landing: #16 cstage variadic-pack, #17 resolver nested-paths,
#27 aliaslookup leaf-collision, #22 zero-init !void/void-alias
let-decl, #15-cstage retscr SSoT name, #24 composite CALL return
as composite arg, #28 N_DOT calleeparams. All blocking ones
fixed (#16/#17 deferred-with-stopgap, others fixed in their
respective commits). Pre-flight + stop-and-surface discipline
held throughout — no workarounds shipped in stdlib.

Tests:
  - 966_strings_run drives lib/strings/stringstest.ww via ww run.
    15 @test fns: dup (alloc, multibyte), concat (empty, lopsided,
    multibyte), trim/ltrim/rtrim incl. 4-byte rune U+1D68A,
    hasprefix/hassuffix with (str|rune) incl. multibyte,
    byteindex/rbyteindex both arms 1/2/3/4-byte rune coverage,
    compare. Cited from ref/hare/strings/+test.ha where vectors
    apply.

100/100 ok. 995_self_rebuild stays green (ww2==ww3==ww4 byte-id).
2026-05-18 10:28:44 +09:00

271 lines
8.3 KiB
Plaintext

// strings — operations over str ({ptr,len}). Hare port; see
// ref/hare/strings/.
//
// Documented divergences from Hare:
//
// - `concat(a, b)` is 2-arg. Hare ships `concat(strs: str...)`
// (ref/hare/strings/concat.ha:5). Blocks on task #16 (cstage
// variadic-pack drops .len of multi-field element type). Cite
// reverts on fix.
// - `trim` / `ltrim` / `rtrim` take a single rune. Hare's are
// `(exclude: rune...)` (ref/hare/strings/trim.ha:54). Same
// blocker as concat. Hare's no-rune branch (strip whitespace)
// is also dropped — depends on a rune set.
// - `contains` is non-variadic. Hare's is
// `contains(haystack, needles: (str | rune)...)`
// (ref/hare/strings/contains.ha:9). Same blocker.
// - `byteindex` / `rbyteindex` rune arms encode via
// `utf8.encoderune`; the legacy impls scanned for `r: u8` (an
// undocumented ASCII-only restriction that silently dropped
// to the wrong byte for U+80..U+7FF and higher).
// - `dup(s: str) str` — Hare returns `(str | nomem)`. ww's
// `os.alloc` aborts on OOM (no `nomem` type), so we return plain
// `str`. Empty input returns `{nil, 0}`; Hare returns the static
// empty string — same observable result.
use bytes;
use utf8;
use os;
// toutf8 — borrowed []u8 view of `s`. ref/hare/strings/utf8.ha:29.
// `cap` equals `len`; the slice does not own a separate allocation.
export fn toutf8(s: str) []u8 = {
let r: []u8;
r.ptr = s.ptr;
r.len = s.len;
r.cap = s.len;
return r;
};
// fromutf8_unsafe — borrowed str view of `in`. Does not validate.
// ref/hare/strings/utf8.ha:10.
export fn fromutf8_unsafe(in: []u8) str = {
let r: str;
r.ptr = in.ptr;
r.len = in.len;
return r;
};
// compare — three-way bytewise codepoint-order comparison.
// ref/hare/strings/compare.ha:12.
export fn compare(a: str, b: str) i32 = {
let n: i32 = a.len;
if (b.len < n) { n = b.len; };
let i: i32 = 0;
for (i < n) {
if (a[i] != b[i]) { return (a[i]: i32) - (b[i]: i32); };
i += 1;
};
return a.len - b.len;
};
// dup — allocate a fresh copy of `s`. Caller releases with
// `os.free(r.ptr, r.len: u64)`. ref/hare/strings/dup.ha:7.
export fn dup(s: str) str = {
let r: str;
r.ptr = nil;
r.len = 0;
if (s.len == 0) { return r; };
let buf: *u8 = os.alloc(s.len: u64): *u8;
let i: i32 = 0;
for (i < s.len) { buf[i] = s[i]; i += 1; };
r.ptr = buf;
r.len = s.len;
return r;
};
// freeall — release each element + the slice header. The natural
// disposer for any `[]str` of dup'd elements (e.g. shlex.split).
// ref/hare/strings/dup.ha:38.
//
// Empty elements (`{nil, 0}` from a zero-length dup) are skipped:
// os.free on a nil pointer at len 0 tickles the rt_free guard. The
// slice header itself is freed at `cap * 16` (one str = 16B); a
// never-grown slice (cap == 0) skips the header free.
export fn freeall(s: []str) void = {
let i: i32 = 0;
for (i < s.len) {
if (s[i].len > 0) {
os.free(s[i].ptr: *void, s[i].len: u64);
};
i += 1;
};
if (s.cap > 0) {
os.free(s.ptr: *void, (s.cap: u64) * 16u64);
};
};
// concat — fresh allocation containing `a` then `b`. Caller releases
// with `os.free(r.ptr, r.len: u64)`. ref/hare/strings/concat.ha:5
// (subset: Hare's `(strs: str...)` blocks on task #16).
export fn concat(a: str, b: str) str = {
let total: i32 = a.len + b.len;
let buf: *u8 = os.alloc(total: u64): *u8;
let i: i32 = 0;
for (i < a.len) { buf[i] = a[i]; i += 1; };
let j: i32 = 0;
for (j < b.len) { buf[a.len + j] = b[j]; j += 1; };
let r: str;
r.ptr = buf;
r.len = total;
return r;
};
// sub — borrowed `s[start..end]`. ref/hare/strings/sub.ha:30 is
// rune-wise; this ww form is byte-wise (no rune iterator yet, planned
// for commit 2). Clamps out-of-range silently where Hare aborts —
// retained for the existing getopt caller; will graduate when the
// rune-wise form lands.
export fn sub(s: str, start: i32, end: i32) str = {
let lo: i32 = start;
let hi: i32 = end;
if (lo < 0) { lo = 0; };
if (hi > s.len) { hi = s.len; };
if (hi < lo) { hi = lo; };
let r: str;
r.ptr = s.ptr + (lo: u64);
r.len = hi - lo;
return r;
};
// runebytes — encode `r` into caller's `scratch` (must hold 4 bytes)
// and return the borrowed slice trimmed to the encoded length. Hare
// inlines the same shape at ref/hare/strings/index.ha:132.
fn runebytes(scratch: []u8, r: rune) []u8 = {
let n: i32 = utf8.encoderune(scratch, r);
let s: []u8;
s.ptr = scratch.ptr;
s.len = n;
s.cap = n;
return s;
};
// hasprefix — true iff `in` begins with `prefix`.
// ref/hare/strings/suffix.ha:8.
export fn hasprefix(in: str, prefix: (str | rune)) bool = {
let scratch: [4]u8;
let p: []u8 = match (prefix) {
case let s: str => yield toutf8(s);
case let r: rune => yield runebytes(scratch[0:4], r);
};
return bytes.hasprefix(toutf8(in), p);
};
// hassuffix — true iff `in` ends with `suff`.
// ref/hare/strings/suffix.ha:26.
export fn hassuffix(in: str, suff: (str | rune)) bool = {
let scratch: [4]u8;
let s: []u8 = match (suff) {
case let v: str => yield toutf8(v);
case let r: rune => yield runebytes(scratch[0:4], r);
};
return bytes.hassuffix(toutf8(in), s);
};
// byteindex — byte-wise offset of `needle` in `haystack`, or void if
// absent. ref/hare/strings/index.ha:127. Rune arm encodes via
// utf8.encoderune (Hare passes the encoded slice straight to
// bytes::index).
export fn byteindex(haystack: str, needle: (str | rune)) (i32 | void) = {
let scratch: [4]u8;
let n: []u8 = match (needle) {
case let s: str => yield toutf8(s);
case let r: rune => yield runebytes(scratch[0:4], r);
};
return bytes.index(toutf8(haystack), n);
};
// rbyteindex — byte-wise offset of the last `needle` in `haystack`.
// ref/hare/strings/index.ha:138.
export fn rbyteindex(haystack: str, needle: (str | rune)) (i32 | void) = {
let scratch: [4]u8;
let n: []u8 = match (needle) {
case let s: str => yield toutf8(s);
case let r: rune => yield runebytes(scratch[0:4], r);
};
return bytes.rindex(toutf8(haystack), n);
};
// contains — true iff `needle` occurs in `haystack`.
// ref/hare/strings/contains.ha:9 (subset: Hare's variadic form
// `(needles: (str | rune)...)` blocks on task #16).
export fn contains(haystack: str, needle: (str | rune)) bool = {
match (byteindex(haystack, needle)) {
case let i: i32 => return true;
case void => return false;
};
return false;
};
// trimprefix — `s` with `prefix` stripped from the front, or `s`
// unchanged if it doesn't start with `prefix`. Borrowed view.
// ref/hare/strings/trim.ha:60.
export fn trimprefix(input: str, prefix: str) str = {
if (!hasprefix(input, prefix)) { return input; };
let r: str;
r.ptr = input.ptr + (prefix.len: u64);
r.len = input.len - prefix.len;
return r;
};
// trimsuffix — symmetric. ref/hare/strings/trim.ha:69.
export fn trimsuffix(input: str, suffix: str) str = {
if (!hassuffix(input, suffix)) { return input; };
let r: str;
r.ptr = input.ptr;
r.len = input.len - suffix.len;
return r;
};
// ltrim — strip occurrences of `exclude` (encoded as UTF-8) from the
// front. Borrowed view. ref/hare/strings/trim.ha:11 (subset: single
// rune; Hare's `(trim: rune...)` blocks on task #16). The no-rune
// strip-whitespace branch is omitted for the same reason.
export fn ltrim(input: str, exclude: rune) str = {
let scratch: [4]u8;
let pat: []u8 = runebytes(scratch[0:4], exclude);
let i: i32 = 0;
for (i + pat.len <= input.len) {
let j: i32 = 0;
let ok: bool = true;
for (j < pat.len) {
if (input[i + j] != pat[j]) { ok = false; j = pat.len; }
else { j += 1; };
};
if (!ok) { break; };
i += pat.len;
};
let r: str;
r.ptr = input.ptr + (i: u64);
r.len = input.len - i;
return r;
};
// rtrim — strip occurrences of `exclude` from the end. Borrowed view.
// ref/hare/strings/trim.ha:32 (same subset note).
export fn rtrim(input: str, exclude: rune) str = {
let scratch: [4]u8;
let pat: []u8 = runebytes(scratch[0:4], exclude);
let n: i32 = input.len;
for (n >= pat.len) {
let off: i32 = n - pat.len;
let j: i32 = 0;
let ok: bool = true;
for (j < pat.len) {
if (input[off + j] != pat[j]) { ok = false; j = pat.len; }
else { j += 1; };
};
if (!ok) { break; };
n -= pat.len;
};
let r: str;
r.ptr = input.ptr;
r.len = n;
return r;
};
// trim — strip from both ends. ref/hare/strings/trim.ha:54.
export fn trim(input: str, exclude: rune) str = {
return ltrim(rtrim(input, exclude), exclude);
};