Commit de5c25420b05aab47346a7cd4c8d9def85b9d0f9 | zig

author	nyx-xyn <nyx-xyn@nyru.xyz> 2026-07-28 21:01:34+02:00
committer	Ryan Liptak <squeek502@hotmail.com> 2026-07-28 21:01:34+02:00
log	de5c25420b05aab47346a7cd4c8d9def85b9d0f9
tree	f3b756c1f561b1c88e65dc468004a4ce99ba5a62
parent	4e5ce9909a7a008ca6a4a4fb9c45c473f95c9a8c

std.unicode: add peekCodepoint (#31038)

Adds peekCodepoint() to Utf8Iterator and Wtf8Iterator.

Reviewed-on: https://codeberg.org/ziglang/zig/pulls/31038
Reviewed-by: Ryan Liptak <squeek502@noreply.codeberg.org>

1 files changed, 35 insertions(+), 0 deletions(-)

lib
- std
  - unicode.zig

lib/std/unicode.zig+35

...	@@ -425,6 +425,15 @@ pub const Utf8Iterator = struct {	...	@@ -425,6 +425,15 @@ pub const Utf8Iterator = struct {
425		425
426	return it.bytes[original_i..end_ix];	426	return it.bytes[original_i..end_ix];
427	}	427	}
		428
		429	/// Look ahead at the next codepoint without advancing the iterator.
		430	/// If no codepoints exist, then returns null.
		431	pub fn peekCodepoint(it: *Utf8Iterator) ?u21 {
		432	const original_i = it.i;
		433	defer it.i = original_i;
		434
		435	return it.nextCodepoint();
		436	}
428	};	437	};
429		438
430	pub fn utf16IsHighSurrogate(c: u16) bool {	439	pub fn utf16IsHighSurrogate(c: u16) bool {
...	@@ -768,6 +777,9 @@ fn testMiscInvalidUtf8() !void {	...	@@ -768,6 +777,9 @@ fn testMiscInvalidUtf8() !void {
768	test "utf8 iterator peeking" {	777	test "utf8 iterator peeking" {
769	try comptime testUtf8Peeking();	778	try comptime testUtf8Peeking();
770	try testUtf8Peeking();	779	try testUtf8Peeking();
		780
		781	comptime try testUtf8PeekCodepoint();
		782	try testUtf8PeekCodepoint();
771	}	783	}
772		784
773	fn testUtf8Peeking() !void {	785	fn testUtf8Peeking() !void {
...	@@ -790,6 +802,20 @@ fn testUtf8Peeking() !void {	...	@@ -790,6 +802,20 @@ fn testUtf8Peeking() !void {
790	try testing.expect(mem.eql(u8, &[_]u8{}, it.peek(1)));	802	try testing.expect(mem.eql(u8, &[_]u8{}, it.peek(1)));
791	}	803	}
792		804
		805	fn testUtf8PeekCodepoint() !void {
		806	const s = Utf8View.initComptime("東京市");
		807	var it = s.iterator();
		808
		809	try testing.expect(it.peekCodepoint().? == 0x6771);
		810	try testing.expect(it.peekCodepoint().? == 0x6771);
		811	_ = it.nextCodepoint();
		812	try testing.expect(it.peekCodepoint().? == 0x4eac);
		813	_ = it.nextCodepoint();
		814	try testing.expect(it.peekCodepoint().? == 0x5e02);
		815	_ = it.nextCodepoint();
		816	try testing.expect(it.peekCodepoint() == null);
		817	}
		818
793	fn testError(bytes: []const u8, expected_err: anyerror) !void {	819	fn testError(bytes: []const u8, expected_err: anyerror) !void {
794	try testing.expectError(expected_err, testDecode(bytes));	820	try testing.expectError(expected_err, testDecode(bytes));
795	}	821	}
...	@@ -1758,6 +1784,15 @@ pub const Wtf8Iterator = struct {	...	@@ -1758,6 +1784,15 @@ pub const Wtf8Iterator = struct {
1758		1784
1759	return it.bytes[original_i..end_ix];	1785	return it.bytes[original_i..end_ix];
1760	}	1786	}
		1787
		1788	/// Look ahead at the next codepoint without advancing the iterator.
		1789	/// If no codepoints exist, then returns null.
		1790	pub fn peekCodepoint(it: *Wtf8Iterator) ?u21 {
		1791	const original_i = it.i;
		1792	defer it.i = original_i;
		1793
		1794	return it.nextCodepoint();
		1795	}
1761	};	1796	};
1762		1797
1763	pub fn wtf16LeToWtf8ArrayList(result: *std.array_list.Managed(u8), utf16le: []const u16) Allocator.Error!void {	1798	pub fn wtf16LeToWtf8ArrayList(result: *std.array_list.Managed(u8), utf16le: []const u16) Allocator.Error!void {