zhjwpku commented on code in PR #1045:
URL: https://github.com/apache/iceberg-cpp/pull/1045#discussion_r4324703689
##########
src/iceberg/util/base64.cc:
##########
@@ -30,28 +30,42 @@ namespace {
// When `pad` is true, the output is padded with '=' to a multiple of 4
characters.
std::string Base64EncodeWithAlphabet(std::string_view input, std::string_view
alphabet,
bool pad) {
- std::string output;
- output.reserve((input.size() + 2) / 3 * 4);
+ const size_t full_blocks = input.size() / 3;
+ const size_t remainder = input.size() % 3;
+ const size_t output_size =
+ full_blocks * 4 + (remainder == 0 ? 0 : (pad ? 4 : remainder + 1));
+ std::string output(output_size, '\0');
+
+ const auto* bytes = reinterpret_cast<const uint8_t*>(input.data());
+ size_t out = 0;
+ for (size_t i = 0; i < full_blocks * 3; i += 3) {
+ const uint32_t block = (static_cast<uint32_t>(bytes[i]) << 16) |
+ (static_cast<uint32_t>(bytes[i + 1]) << 8) |
+ static_cast<uint32_t>(bytes[i + 2]);
+ output[out++] = alphabet[(block >> 18) & 0x3F];
+ output[out++] = alphabet[(block >> 12) & 0x3F];
+ output[out++] = alphabet[(block >> 6) & 0x3F];
+ output[out++] = alphabet[block & 0x3F];
+ }
- uint32_t buffer = 0;
- int bits_collected = 0;
- for (unsigned char byte : input) {
- buffer = (buffer << 8) | byte;
- bits_collected += 8;
- while (bits_collected >= 6) {
- bits_collected -= 6;
- output.push_back(alphabet[(buffer >> bits_collected) & 0x3F]);
+ if (remainder > 0) {
+ const size_t i = full_blocks * 3;
+ uint32_t block = static_cast<uint32_t>(bytes[i]) << 16;
+ if (remainder == 2) {
+ block |= static_cast<uint32_t>(bytes[i + 1]) << 8;
}
- }
- if (bits_collected > 0) {
- // Pad the remaining bits on the right to form the final 6-bit group.
- output.push_back(alphabet[(buffer << (6 - bits_collected)) & 0x3F]);
- }
- if (pad) {
- while (output.size() % 4 != 0) {
- output.push_back('=');
+ output[out++] = alphabet[(block >> 18) & 0x3F];
+ output[out++] = alphabet[(block >> 12) & 0x3F];
+ if (remainder == 2) {
+ output[out++] = alphabet[(block >> 6) & 0x3F];
+ }
+ if (pad) {
Review Comment:
nit: seems we can delete this condition wrapper since the output_size is
exact.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
