vaibhawvipul commented on code in PR #627:
URL: https://github.com/apache/datafusion-comet/pull/627#discussion_r1675535745
##########
native/core/src/execution/datafusion/expressions/scalar_funcs/hex.rs:
##########
@@ -118,65 +118,36 @@ pub(super) fn spark_hex(args: &[ColumnarValue]) ->
Result<ColumnarValue, DataFus
Ok(ColumnarValue::Array(Arc::new(hexed)))
}
- DataType::Dictionary(_, value_type) if matches!(**value_type,
DataType::Int64) => {
+ DataType::Dictionary(_, value_type) => {
let dict = as_dictionary_array::<Int32Type>(&array);
- let hexed_values = as_int64_array(dict.values())?;
- let values = hexed_values
+ let values = match **value_type {
+ DataType::Int64 => as_int64_array(dict.values())?
+ .iter()
+ .map(|v| v.map(hex_int64))
+ .collect::<Vec<_>>(),
+ DataType::Utf8 => as_string_array(dict.values())
+ .iter()
+ .map(|v| v.map(hex_bytes).transpose())
+ .collect::<Result<_, _>>()?,
+ DataType::Binary => as_binary_array(dict.values())?
+ .iter()
+ .map(|v| v.map(hex_bytes).transpose())
+ .collect::<Result<_, _>>()?,
+ _ => exec_err!(
+ "hex got an unexpected argument type: {:?}",
+ array.data_type()
+ )?,
+ };
+
+ let new_values: Vec<Option<String>> = dict
+ .keys()
.iter()
- .map(|v| v.map(hex_int64))
- .collect::<Vec<_>>();
+ .map(|key| key.map(|k| values[k as
usize].clone()).unwrap_or(None))
+ .collect();
- let keys = dict.keys().clone();
- let mut new_keys = Vec::with_capacity(values.len());
+ let string_array_values = StringArray::from(new_values);
Review Comment:
did a small benchmark by timing `hex` testcase in CometExpressionSuite.
Old code - 3600 ms
New code - 2950ms
--
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
