viirya commented on code in PR #226:
URL: https://github.com/apache/datafusion-comet/pull/226#discussion_r1575674292
##########
core/src/execution/datafusion/expressions/scalar_funcs.rs:
##########
@@ -629,3 +622,72 @@ fn spark_decimal_div(
let result = result.with_data_type(DataType::Decimal128(p3, s3));
Ok(ColumnarValue::Array(Arc::new(result)))
}
+
+fn spark_murmur3_hash(args: &[ColumnarValue]) -> Result<ColumnarValue,
DataFusionError> {
+ let length = args.len();
+ let seed = &args[length - 1];
+ match seed {
+ ColumnarValue::Scalar(ScalarValue::Int32(Some(seed))) => {
+ // iterate over the arguments to find out the length of the array
+ let num_rows = args[0..args.len() - 1]
+ .iter()
+ .find_map(|arg| match arg {
+ ColumnarValue::Array(array) => Some(array.len()),
+ ColumnarValue::Scalar(_) => None,
+ })
+ .unwrap_or(1);
+ let mut hashes: Vec<u32> = vec![0_u32; num_rows];
+ hashes.fill(*seed as u32);
+ let arrays = args[0..args.len() - 1]
+ .iter()
+ .map(|arg| match arg {
+ ColumnarValue::Array(array) => array.clone(),
+ ColumnarValue::Scalar(scalar) => {
+ scalar.clone().to_array_of_size(num_rows).unwrap()
+ }
+ })
+ .collect::<Vec<ArrayRef>>();
+ create_hashes(&arrays, &mut hashes)?;
+ if num_rows == 1 {
+ Ok(ColumnarValue::Scalar(ScalarValue::Int32(Some(
+ hashes[0] as i32,
+ ))))
+ } else {
+ let hashes: Vec<i32> = hashes.into_iter().map(|x| x as
i32).collect();
+ Ok(ColumnarValue::Array(Arc::new(Int32Array::from(hashes))))
+ }
+ }
+ _ => internal_err!("Unsupported data type for function murmur3_hash"),
Review Comment:
```suggestion
_ => internal_err!("The seed of function murmur3_hash must be a
scalar value."),
```
--
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
