viirya commented on code in PR #226:
URL: https://github.com/apache/datafusion-comet/pull/226#discussion_r1575678310
##########
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"),
+ }
+}
+
+#[inline]
+fn hex_encode<T: AsRef<[u8]>>(data: T) -> String {
+ let mut s = String::with_capacity(data.as_ref().len() * 2);
+ for b in data.as_ref() {
+ // Writing to a string never errors, so we can unwrap here.
+ write!(&mut s, "{b:02x}").unwrap();
+ }
+ s
+}
+
+fn wrap_digest_result_as_hex_string(
+ args: &[ColumnarValue],
+ digest: ScalarFunctionImplementation,
+) -> Result<ColumnarValue, DataFusionError> {
+ let value = digest(args)?;
+ Ok(match value {
+ ColumnarValue::Array(array) => {
+ let binary_array = as_binary_array(&array)?;
+ let string_array: StringArray = binary_array
+ .iter()
+ .map(|opt| opt.map(hex_encode::<_>))
+ .collect();
+ ColumnarValue::Array(Arc::new(string_array))
+ }
+ ColumnarValue::Scalar(ScalarValue::Binary(opt)) => {
+ ColumnarValue::Scalar(ScalarValue::Utf8(opt.map(hex_encode::<_>)))
+ }
+ _ => return exec_err!("Impossibly got invalid results from digest"),
Review Comment:
```suggestion
_ => return exec_err!(format!("sha function should return binary
value but got: {:?}", value.data_type())),
```
--
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
