Function wtf8ToUtf8LossyAllocZ [src]

Prototype

pub fn wtf8ToUtf8LossyAllocZ(allocator: mem.Allocator, wtf8: []const u8) error{ InvalidWtf8, OutOfMemory }![:0]u8

Parameters

allocator: mem.Allocatorwtf8: []const u8

Possible Errors

InvalidWtf8

OutOfMemory

Example

 test wtf8ToUtf8LossyAllocZ {
    const invalid_utf8 = "\xff";
    try testing.expectError(error.InvalidWtf8, wtf8ToUtf8LossyAllocZ(testing.allocator, invalid_utf8));

    {
        const ascii = "abcd";
        const utf8 = try wtf8ToUtf8LossyAllocZ(testing.allocator, ascii);
        defer testing.allocator.free(utf8);
        try testing.expectEqualStrings("abcd", utf8);
    }

    {
        const surrogate_half = "ab\xed\xa0\xbdcd";
        const utf8 = try wtf8ToUtf8LossyAllocZ(testing.allocator, surrogate_half);
        defer testing.allocator.free(utf8);
        try testing.expectEqualStrings("ab\u{FFFD}cd", utf8);
    }

    {
        // If the WTF-8 is not well-formed, each surrogate half is converted into a separate
        // replacement character instead of being interpreted as a surrogate pair.
        const encoded_surrogate_pair = "ab\xed\xa0\xbd\xed\xb2\xa9cd";
        const utf8 = try wtf8ToUtf8LossyAllocZ(testing.allocator, encoded_surrogate_pair);
        defer testing.allocator.free(utf8);
        try testing.expectEqualStrings("ab\u{FFFD}\u{FFFD}cd", utf8);
    }
}

Source

  pub fn wtf8ToUtf8LossyAllocZ(allocator: mem.Allocator, wtf8: []const u8) error{ InvalidWtf8, OutOfMemory }![:0]u8 {
    const utf8 = try allocator.allocSentinel(u8, wtf8.len, 0);
    errdefer allocator.free(utf8);

    try wtf8ToUtf8Lossy(utf8, wtf8);

    return utf8;
}  