Function utf8ToUtf16LeAllocZ [src]

Prototype

pub fn utf8ToUtf16LeAllocZ(allocator: mem.Allocator, utf8: []const u8) error{ InvalidUtf8, OutOfMemory }![:0]u16

Parameters

allocator: mem.Allocatorutf8: []const u8

Possible Errors

InvalidUtf8

OutOfMemory

Example

 test utf8ToUtf16LeAllocZ {
    {
        const utf16 = try utf8ToUtf16LeAllocZ(testing.allocator, "𐐷");
        defer testing.allocator.free(utf16);
        try testing.expectEqualSlices(u8, "\x01\xd8\x37\xdc", mem.sliceAsBytes(utf16));
        try testing.expect(utf16[2] == 0);
    }
    {
        const utf16 = try utf8ToUtf16LeAllocZ(testing.allocator, "\u{10FFFF}");
        defer testing.allocator.free(utf16);
        try testing.expectEqualSlices(u8, "\xff\xdb\xff\xdf", mem.sliceAsBytes(utf16));
        try testing.expect(utf16[2] == 0);
    }
    {
        const result = utf8ToUtf16LeAllocZ(testing.allocator, "\xf4\x90\x80\x80");
        try testing.expectError(error.InvalidUtf8, result);
    }
    {
        const utf16 = try utf8ToUtf16LeAllocZ(testing.allocator, "This string has been designed to test the vectorized implementat" ++
            "ion by beginning with one hundred twenty-seven ASCII characters¡");
        defer testing.allocator.free(utf16);
        try testing.expectEqualSlices(u8, &.{
            'T', 0, 'h', 0, 'i', 0, 's', 0, ' ', 0, 's', 0, 't', 0, 'r', 0, 'i', 0, 'n', 0, 'g', 0, ' ', 0, 'h', 0, 'a', 0, 's', 0, ' ',  0,
            'b', 0, 'e', 0, 'e', 0, 'n', 0, ' ', 0, 'd', 0, 'e', 0, 's', 0, 'i', 0, 'g', 0, 'n', 0, 'e', 0, 'd', 0, ' ', 0, 't', 0, 'o',  0,
            ' ', 0, 't', 0, 'e', 0, 's', 0, 't', 0, ' ', 0, 't', 0, 'h', 0, 'e', 0, ' ', 0, 'v', 0, 'e', 0, 'c', 0, 't', 0, 'o', 0, 'r',  0,
            'i', 0, 'z', 0, 'e', 0, 'd', 0, ' ', 0, 'i', 0, 'm', 0, 'p', 0, 'l', 0, 'e', 0, 'm', 0, 'e', 0, 'n', 0, 't', 0, 'a', 0, 't',  0,
            'i', 0, 'o', 0, 'n', 0, ' ', 0, 'b', 0, 'y', 0, ' ', 0, 'b', 0, 'e', 0, 'g', 0, 'i', 0, 'n', 0, 'n', 0, 'i', 0, 'n', 0, 'g',  0,
            ' ', 0, 'w', 0, 'i', 0, 't', 0, 'h', 0, ' ', 0, 'o', 0, 'n', 0, 'e', 0, ' ', 0, 'h', 0, 'u', 0, 'n', 0, 'd', 0, 'r', 0, 'e',  0,
            'd', 0, ' ', 0, 't', 0, 'w', 0, 'e', 0, 'n', 0, 't', 0, 'y', 0, '-', 0, 's', 0, 'e', 0, 'v', 0, 'e', 0, 'n', 0, ' ', 0, 'A',  0,
            'S', 0, 'C', 0, 'I', 0, 'I', 0, ' ', 0, 'c', 0, 'h', 0, 'a', 0, 'r', 0, 'a', 0, 'c', 0, 't', 0, 'e', 0, 'r', 0, 's', 0, '¡', 0,
        }, mem.sliceAsBytes(utf16));
    }
}

Source

  pub fn utf8ToUtf16LeAllocZ(allocator: mem.Allocator, utf8: []const u8) error{ InvalidUtf8, OutOfMemory }![:0]u16 {
    // optimistically guess that it will not require surrogate pairs
    var result = try std.ArrayList(u16).initCapacity(allocator, utf8.len + 1);
    errdefer result.deinit();

    try utf8ToUtf16LeArrayListImpl(&result, utf8, .cannot_encode_surrogate_half);
    return result.toOwnedSliceSentinel(0);
}  