advancedxy commented on code in PR #424: URL: https://github.com/apache/datafusion-comet/pull/424#discussion_r1620141162
########## core/src/execution/datafusion/expressions/scalar_funcs.rs: ########## @@ -672,6 +676,49 @@ fn spark_murmur3_hash(args: &[ColumnarValue]) -> Result<ColumnarValue, DataFusio } } +fn spark_xxhash64(args: &[ColumnarValue]) -> Result<ColumnarValue, DataFusionError> { + let length = args.len(); + let seed = &args[length - 1]; + match seed { + ColumnarValue::Scalar(ScalarValue::Int64(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<u64> = vec![0_u64; num_rows]; + hashes.fill(*seed as u64); + 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>>(); Review Comment: hmm. I think we have to compute `num_rows` first? ########## core/src/execution/datafusion/spark_hash.rs: ########## @@ -244,111 +283,214 @@ fn create_hashes_dictionary<K: ArrowDictionaryKeyType>( /// /// The number of rows to hash is determined by `hashes_buffer.len()`. /// `hashes_buffer` should be pre-sized appropriately -pub fn create_hashes<'a>( - arrays: &[ArrayRef], - hashes_buffer: &'a mut [u32], -) -> Result<&'a mut [u32]> { - for (i, col) in arrays.iter().enumerate() { - let first_col = i == 0; - match col.data_type() { - DataType::Boolean => { - hash_array_boolean!(BooleanArray, col, i32, hashes_buffer); - } - DataType::Int8 => { - hash_array_primitive!(Int8Array, col, i32, hashes_buffer); - } - DataType::Int16 => { - hash_array_primitive!(Int16Array, col, i32, hashes_buffer); - } - DataType::Int32 => { - hash_array_primitive!(Int32Array, col, i32, hashes_buffer); - } - DataType::Int64 => { - hash_array_primitive!(Int64Array, col, i64, hashes_buffer); - } - DataType::Float32 => { - hash_array_primitive_float!(Float32Array, col, f32, i32, hashes_buffer); - } - DataType::Float64 => { - hash_array_primitive_float!(Float64Array, col, f64, i64, hashes_buffer); - } - DataType::Timestamp(TimeUnit::Second, _) => { - hash_array_primitive!(TimestampSecondArray, col, i64, hashes_buffer); - } - DataType::Timestamp(TimeUnit::Millisecond, _) => { - hash_array_primitive!(TimestampMillisecondArray, col, i64, hashes_buffer); - } - DataType::Timestamp(TimeUnit::Microsecond, _) => { - hash_array_primitive!(TimestampMicrosecondArray, col, i64, hashes_buffer); - } - DataType::Timestamp(TimeUnit::Nanosecond, _) => { - hash_array_primitive!(TimestampNanosecondArray, col, i64, hashes_buffer); - } - DataType::Date32 => { - hash_array_primitive!(Date32Array, col, i32, hashes_buffer); - } - DataType::Date64 => { - hash_array_primitive!(Date64Array, col, i64, hashes_buffer); - } - DataType::Utf8 => { - hash_array!(StringArray, col, hashes_buffer); - } - DataType::LargeUtf8 => { - hash_array!(LargeStringArray, col, hashes_buffer); - } - DataType::Binary => { - hash_array!(BinaryArray, col, hashes_buffer); - } - DataType::LargeBinary => { - hash_array!(LargeBinaryArray, col, hashes_buffer); - } - DataType::FixedSizeBinary(_) => { - hash_array!(FixedSizeBinaryArray, col, hashes_buffer); - } - DataType::Decimal128(_, _) => { - hash_array_decimal!(Decimal128Array, col, hashes_buffer); - } - DataType::Dictionary(index_type, _) => match **index_type { +/// +/// `hash_method` is the hash function to use. +/// `create_dictionary_hash_method` is the function to create hashes for dictionary arrays input. +macro_rules! create_hashes_internal { + ($arrays: ident, $hashes_buffer: ident, $hash_method: ident, $create_dictionary_hash_method: ident) => { + for (i, col) in $arrays.iter().enumerate() { + let first_col = i == 0; + match col.data_type() { + DataType::Boolean => { + hash_array_boolean!(BooleanArray, col, i32, $hashes_buffer, $hash_method); + } Review Comment: hmm, let me give it a try. I will report back if it's too hard to do that. -- 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