Every // ---- section banner dies (132 -> 0): names carry the WHAT. Narration deleted (filename restatements, run-with lines, what-the- next-line-does); every ref/hare cite, task cite, divergence, ABI/ layout contract, and ownership qualifier kept (borrowed-view lines restored where the sweep over-cut). Comment-only proven: all 442 walk-workdir .s and 32 import-probe .s byte-identical before/after; libbyteid 56-roster all-ID.
63 lines
2.1 KiB
Plaintext
63 lines
2.1 KiB
Plaintext
// Vectors mirror ref/hare/encoding/utf8/rune.ha. A failing row aborts
|
|
// via the assert/abort builtin (task #5 @test conversion).
|
|
|
|
package utf8_test;
|
|
|
|
import encoding.utf8;
|
|
|
|
// ref/hare/encoding/utf8/rune.ha:5. Boundaries: 0x7F → 1, 0x80 → 2,
|
|
// 0x7FF → 2, 0x800 → 3, 0xFFFF → 3, 0x10000 → 4, 0x10FFFF → 4.
|
|
|
|
@test fn runesz_ranges() void = {
|
|
assert(!(utf8.runesz(0u32: rune) != 1));
|
|
assert(!(utf8.runesz(0x7Fu32: rune) != 1));
|
|
assert(!(utf8.runesz(0x80u32: rune) != 2));
|
|
assert(!(utf8.runesz(0x7FFu32: rune) != 2));
|
|
assert(!(utf8.runesz(0x800u32: rune) != 3));
|
|
assert(!(utf8.runesz(0xFFFFu32: rune) != 3));
|
|
assert(!(utf8.runesz(0x10000u32: rune) != 4));
|
|
assert(!(utf8.runesz(0x10FFFFu32: rune) != 4));
|
|
};
|
|
|
|
// ref/hare/encoding/utf8/rune.ha:15. ASCII → 1; legal multibyte
|
|
// leads → 2/3/4; continuation and >0xF7 → invalid.
|
|
|
|
@test fn utf8sz_classify() void = {
|
|
match (utf8.utf8sz(0u8)) {
|
|
case let n: i32 => { assert(!(n != 1)); };
|
|
case let e: utf8.invalid => { abort(); };
|
|
};
|
|
match (utf8.utf8sz(0x7Fu8)) {
|
|
case let n: i32 => { assert(!(n != 1)); };
|
|
case let e: utf8.invalid => { abort(); };
|
|
};
|
|
match (utf8.utf8sz(0x80u8)) { // continuation
|
|
case let n: i32 => { abort(); };
|
|
case let e: utf8.invalid => void;
|
|
};
|
|
match (utf8.utf8sz(0xC1u8)) { // overlong 2-byte lead
|
|
case let n: i32 => { abort(); };
|
|
case let e: utf8.invalid => void;
|
|
};
|
|
match (utf8.utf8sz(0xC2u8)) {
|
|
case let n: i32 => { assert(!(n != 2)); };
|
|
case let e: utf8.invalid => { abort(); };
|
|
};
|
|
match (utf8.utf8sz(0xE0u8)) {
|
|
case let n: i32 => { assert(!(n != 3)); };
|
|
case let e: utf8.invalid => { abort(); };
|
|
};
|
|
match (utf8.utf8sz(0xF0u8)) {
|
|
case let n: i32 => { assert(!(n != 4)); };
|
|
case let e: utf8.invalid => { abort(); };
|
|
};
|
|
match (utf8.utf8sz(0xF8u8)) { // 5-byte lead — illegal in modern UTF-8
|
|
case let n: i32 => { abort(); };
|
|
case let e: utf8.invalid => void;
|
|
};
|
|
match (utf8.utf8sz(0xFFu8)) {
|
|
case let n: i32 => { abort(); };
|
|
case let e: utf8.invalid => void;
|
|
};
|
|
};
|