lib/strings+test: port dupall from Hare
ref/hare/strings/dup.ha:26-35. Returns ([]str | nomem); duplicates every str in the input slice via the now-graduated alloc-slice builtin (#45 unblocked `let s: []str = alloc([], n)?`). Loop body uses appendstr because `[]str` element is 16B and the bare `append` builtin truncates (#11) — pre-allocated cap=s.len means rt_ensure's grow branch never fires. Defer-rollback omitted: with `dup()` still unchecked (graduation tracked by #46), the only nomem source is the initial slice alloc, so there is no partial state to roll back. Will revisit when #46 lands. Empty-input early-return short-circuits via {nil,0,0} because rt_alloc(0) is an mmap of 0 bytes which the kernel rejects with -EINVAL — Hare hands back a sentinel. Localized at the call site pending #47. Tests assert independent allocations at every index of multi-element inputs, including a multibyte row.
This commit is contained in:
@@ -77,6 +77,42 @@ export fn dup(s: str) str = {
|
||||
return r;
|
||||
};
|
||||
|
||||
// dupall — fresh `[]str` whose elements are independent copies of
|
||||
// `s`'s elements. Caller releases via [[freeall]].
|
||||
// ref/hare/strings/dup.ha:26 (#6).
|
||||
//
|
||||
// Hare gates the per-element dup behind `?` and rolls back via
|
||||
// `defer if (!ok) freeall(newsl)`. ww has no `defer if`; more
|
||||
// importantly, ww's [[dup]] is still unchecked (returns plain `str`,
|
||||
// aborts via os.alloc on OOM — see top-of-file divergence note),
|
||||
// so the only nomem propagation point is the initial slice alloc.
|
||||
// With no inner failure path, the rollback is structurally a no-op
|
||||
// and is omitted; it returns once dup graduates to `(str | nomem)`
|
||||
// (#46). The pre-allocated slice has `cap == s.len`, so appendstr's
|
||||
// rt_ensure call never reaches the grow branch.
|
||||
//
|
||||
// Empty input bypasses the alloc: rt_alloc(0) is an mmap of 0 bytes
|
||||
// which returns -EINVAL, and the alloc-slice `?` shortcut routes
|
||||
// that through nomem — Hare's heap allocator hands back a sentinel
|
||||
// instead (#47). Return `{nil, 0, 0}` directly so callers get the
|
||||
// Hare-observable shape (len==0, freeall is a no-op via cap==0).
|
||||
export fn dupall(s: []str) ([]str | nomem) = {
|
||||
if (s.len == 0) {
|
||||
let r: []str;
|
||||
r.ptr = nil: *str;
|
||||
r.len = 0;
|
||||
r.cap = 0;
|
||||
return r;
|
||||
};
|
||||
let newsl: []str = alloc([], s.len)?;
|
||||
let i: i32 = 0;
|
||||
for (i < s.len) {
|
||||
appendstr(&newsl, dup(s[i]));
|
||||
i += 1;
|
||||
};
|
||||
return newsl;
|
||||
};
|
||||
|
||||
// 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.
|
||||
|
||||
@@ -45,6 +45,93 @@ fn streq(a: str, b: str) bool = {
|
||||
defer os.free(m.ptr: *void, m.len: u64);
|
||||
};
|
||||
|
||||
// ---- dupall -----------------------------------------------------------
|
||||
// ref/hare/strings/dup.ha:55 (#6). Per-row `signalled` bump narrows a
|
||||
// failure exit code; element reads go through `&toks.ptr[i]: *str`
|
||||
// per the splitn cases (16B element copy gap, cgen.c:6515).
|
||||
|
||||
@test fn dupall_cases() void = {
|
||||
// Empty input — empty result, mirrors Hare's `payload = []`.
|
||||
signalled = 1800;
|
||||
let empty: []str;
|
||||
empty.ptr = nil: *str;
|
||||
empty.len = 0;
|
||||
empty.cap = 0;
|
||||
match (strings.dupall(empty)) {
|
||||
case let r: []str => {
|
||||
if (r.len != 0) { fail(); };
|
||||
strings.freeall(r);
|
||||
};
|
||||
case nomem => { fail(); };
|
||||
};
|
||||
|
||||
// Two-element ASCII — each output element is a fresh allocation
|
||||
// independent of the input (ptr differs from the borrowed source).
|
||||
signalled = 1801;
|
||||
let in2: [2]str;
|
||||
in2[0] = "hello";
|
||||
in2[1] = "world";
|
||||
let src2: []str;
|
||||
src2.ptr = &in2[0];
|
||||
src2.len = 2;
|
||||
src2.cap = 2;
|
||||
match (strings.dupall(src2)) {
|
||||
case let r: []str => {
|
||||
if (r.len != 2) { fail(); };
|
||||
expect_str(r, 0, "hello");
|
||||
expect_str(r, 1, "world");
|
||||
let p0: *str = &r.ptr[0];
|
||||
if (p0.ptr == in2[0].ptr) { fail(); };
|
||||
let p1: *str = &r.ptr[1];
|
||||
if (p1.ptr == in2[1].ptr) { fail(); };
|
||||
strings.freeall(r);
|
||||
};
|
||||
case nomem => { fail(); };
|
||||
};
|
||||
|
||||
// Singleton — `only` rune-equivalent of Hare's `["only"]`.
|
||||
signalled = 1802;
|
||||
let in1: [1]str;
|
||||
in1[0] = "only";
|
||||
let src1: []str;
|
||||
src1.ptr = &in1[0];
|
||||
src1.len = 1;
|
||||
src1.cap = 1;
|
||||
match (strings.dupall(src1)) {
|
||||
case let r: []str => {
|
||||
if (r.len != 1) { fail(); };
|
||||
expect_str(r, 0, "only");
|
||||
strings.freeall(r);
|
||||
};
|
||||
case nomem => { fail(); };
|
||||
};
|
||||
|
||||
// Multibyte — UTF-8 bytes (5-byte and 15-byte) round-trip.
|
||||
signalled = 1803;
|
||||
let inm: [2]str;
|
||||
inm[0] = "héllo";
|
||||
inm[1] = "こんにちは";
|
||||
let srcm: []str;
|
||||
srcm.ptr = &inm[0];
|
||||
srcm.len = 2;
|
||||
srcm.cap = 2;
|
||||
match (strings.dupall(srcm)) {
|
||||
case let r: []str => {
|
||||
if (r.len != 2) { fail(); };
|
||||
expect_str(r, 0, "héllo");
|
||||
expect_str(r, 1, "こんにちは");
|
||||
let p0: *str = &r.ptr[0];
|
||||
if (p0.len != 6) { fail(); }; // é is 2 bytes
|
||||
if (p0.ptr == inm[0].ptr) { fail(); };
|
||||
let p1: *str = &r.ptr[1];
|
||||
if (p1.len != 15) { fail(); }; // each kana is 3 bytes
|
||||
if (p1.ptr == inm[1].ptr) { fail(); };
|
||||
strings.freeall(r);
|
||||
};
|
||||
case nomem => { fail(); };
|
||||
};
|
||||
};
|
||||
|
||||
// ---- concat -----------------------------------------------------------
|
||||
// ref/hare/strings/concat.ha:18. Rows mirror Hare's vectors (0/1/2/3-arg,
|
||||
// empty-mid, 2-empty) plus empty-first / empty-last / multibyte. The
|
||||
@@ -1441,6 +1528,7 @@ fn expect_str(toks: []str, i: i32, want: str) void = {
|
||||
|
||||
export fn main() i32 = {
|
||||
signalled = 1; dup_cases();
|
||||
signalled = 42; dupall_cases();
|
||||
signalled = 2; concat_cases();
|
||||
signalled = 30; join_cases();
|
||||
signalled = 3; hasprefix_cases();
|
||||
|
||||
Reference in New Issue
Block a user