From 68b01d794dcf145fb11603a238c647b7ca998f84 Mon Sep 17 00:00:00 2001 From: Jose Colon Rodriguez Date: Fri, 1 Mar 2024 20:49:49 -0400 Subject: Added canonical caseless match to Caser --- src/Normalizer.zig | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'src/Normalizer.zig') diff --git a/src/Normalizer.zig b/src/Normalizer.zig index 3ff157c..b5a54d1 100644 --- a/src/Normalizer.zig +++ b/src/Normalizer.zig @@ -343,6 +343,31 @@ test "nfkd !ASCII / alloc" { try testing.expectEqualStrings("He\u{301}llo World! \u{3a5}\u{301}", result.slice); } +pub fn nfdCodePoints( + self: Self, + allocator: mem.Allocator, + cps: []const u21, +) ![]u21 { + var dcp_list = std.ArrayList(u21).init(allocator); + defer dcp_list.deinit(); + + var dc_buf: [18]u21 = undefined; + + for (cps) |cp| { + const dc = self.decompose(cp, .nfd, &dc_buf); + + if (dc.form == .same) { + try dcp_list.append(cp); + } else { + try dcp_list.appendSlice(dc.cps); + } + } + + self.canonicalSort(dcp_list.items); + + return try dcp_list.toOwnedSlice(); +} + pub fn nfkdCodePoints( self: Self, allocator: mem.Allocator, -- cgit v1.2.3