advancedxy commented on code in PR #449: URL: https://github.com/apache/datafusion-comet/pull/449#discussion_r1608635628
########## core/src/execution/datafusion/expressions/scalar_funcs/hex.rs: ########## @@ -0,0 +1,191 @@ +// Licensed to the Apache Software Foundation (ASF) under one +// or more contributor license agreements. See the NOTICE file +// distributed with this work for additional information +// regarding copyright ownership. The ASF licenses this file +// to you under the Apache License, Version 2.0 (the +// "License"); you may not use this file except in compliance +// with the License. You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, +// software distributed under the License is distributed on an +// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +// KIND, either express or implied. See the License for the +// specific language governing permissions and limitations +// under the License. + +use std::sync::Arc; + +use arrow::array::as_string_array; +use arrow_array::StringArray; +use arrow_schema::DataType; +use datafusion::logical_expr::ColumnarValue; +use datafusion_common::{ + cast::{as_binary_array, as_int64_array}, + exec_err, DataFusionError, ScalarValue, +}; +use std::fmt::Write; + +fn hex_bytes(bytes: &[u8]) -> Vec<u8> { + let length = bytes.len(); + let mut value = vec![0; length * 2]; + let mut i = 0; + while i < length { + value[i * 2] = (bytes[i] & 0xF0) >> 4; + value[i * 2 + 1] = bytes[i] & 0x0F; + i += 1; + } + value +} + +fn hex_int64(num: i64) -> String { + if num >= 0 { + format!("{:X}", num) + } else { + format!("{:016X}", num as u64) + } +} + +fn hex_string(s: &str) -> Vec<u8> { + hex_bytes(s.as_bytes()) +} + +fn hex_bytes_to_string(bytes: &[u8]) -> Result<String, std::fmt::Error> { + let mut hex_string = String::with_capacity(bytes.len() * 2); + for byte in bytes { + write!(&mut hex_string, "{:01X}", byte)?; Review Comment: I think I can move sha2/md5 related to scalar_funcs in a follow-up pr. It’s indeed a better place. For the hex_encode, maybe we need to extract it to hex_utils or simply in hex.rs, and make that crate public. I don’t think it’s a blocker to this PR. Just saying it so that it can be addressed later. -- 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: github-unsubscr...@datafusion.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org For additional commands, e-mail: github-h...@datafusion.apache.org
