eldenmoon commented on code in PR #21866:
URL: https://github.com/apache/doris/pull/21866#discussion_r1266102314
##########
be/src/vec/exec/format/json/new_json_reader.cpp:
##########
@@ -1475,15 +1476,18 @@ Status
NewJsonReader::_simdjson_write_data_to_column(simdjson::ondemand::value&
break;
}
default: {
- auto str_view = simdjson::to_json_string(value).value();
if (value.type() == simdjson::ondemand::json_type::string) {
+ uint8_t* unescape_buffer =
+
reinterpret_cast<uint8_t*>(&_simdjson_ondemand_unscape_padding_buffer[0]);
+ std::string_view unescaped_value =
+
_ondemand_json_parser->unescape(value.get_raw_json_string(), unescape_buffer);
nullable_column->get_null_map_data().push_back(0);
- // trim
- column_string->insert_data(str_view.data() + 1, str_view.length()
- 2);
+ column_string->insert_data(unescaped_value.data(),
unescaped_value.length());
Review Comment:
unescape has no side effect, so it does not impact the original string, but
it could impact a little bit performance
--
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]
