andygrove commented on code in PR #19627: URL: https://github.com/apache/datafusion/pull/19627#discussion_r2817734384
########## datafusion/spark/src/function/hash/xxhash64.rs: ########## @@ -0,0 +1,391 @@ +// 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::any::Any; +use std::sync::Arc; + +use arrow::array::{ + Array, ArrayRef, AsArray, BinaryArray, BooleanArray, Date32Array, Date64Array, + Decimal128Array, Float32Array, Float64Array, Int8Array, Int16Array, Int32Array, + Int64Array, LargeBinaryArray, LargeStringArray, StringArray, + TimestampMicrosecondArray, TimestampMillisecondArray, TimestampNanosecondArray, + TimestampSecondArray, +}; +use arrow::datatypes::{DataType, TimeUnit}; +use datafusion_common::{Result, ScalarValue, exec_err, internal_err}; +use datafusion_expr::{ + ColumnarValue, ScalarFunctionArgs, ScalarUDFImpl, Signature, Volatility, +}; +use twox_hash::XxHash64; + +const DEFAULT_SEED: i64 = 42; + +/// Spark-compatible xxhash64 function. +/// <https://spark.apache.org/docs/latest/api/sql/index.html#xxhash64> +#[derive(Debug, PartialEq, Eq, Hash)] +pub struct SparkXxhash64 { + signature: Signature, +} + +impl Default for SparkXxhash64 { + fn default() -> Self { + Self::new() + } +} + +impl SparkXxhash64 { + pub fn new() -> Self { + Self { + signature: Signature::variadic_any(Volatility::Immutable), + } + } +} + +impl ScalarUDFImpl for SparkXxhash64 { + fn as_any(&self) -> &dyn Any { + self + } + + fn name(&self) -> &str { + "xxhash64" + } + + fn signature(&self) -> &Signature { + &self.signature + } + + fn return_type(&self, _arg_types: &[DataType]) -> Result<DataType> { + Ok(DataType::Int64) + } + + fn invoke_with_args(&self, args: ScalarFunctionArgs) -> Result<ColumnarValue> { + if args.args.is_empty() { + return exec_err!("xxhash64 requires at least one argument"); + } + + // Determine number of rows from the first array argument + let num_rows = args + .args + .iter() + .find_map(|arg| match arg { + ColumnarValue::Array(array) => Some(array.len()), + ColumnarValue::Scalar(_) => None, + }) + .unwrap_or(1); + + // Initialize hashes with seed + let mut hashes: Vec<u64> = vec![DEFAULT_SEED as u64; num_rows]; + + // Convert all arguments to arrays + let arrays: Vec<ArrayRef> = args + .args + .iter() + .map(|arg| match arg { + ColumnarValue::Array(array) => Arc::clone(array), + ColumnarValue::Scalar(scalar) => scalar + .to_array_of_size(num_rows) + .expect("Failed to convert scalar to array"), + }) + .collect(); + + // Hash each column + for col in &arrays { + hash_column_xxhash64(col, &mut hashes)?; + } + + // Convert to Int64 + let result: Vec<i64> = hashes.into_iter().map(|h| h as i64).collect(); + let result_array = Int64Array::from(result); + + if num_rows == 1 { + Ok(ColumnarValue::Scalar(ScalarValue::Int64(Some( + result_array.value(0), + )))) + } else { + Ok(ColumnarValue::Array(Arc::new(result_array))) + } + } +} + +#[inline] +fn spark_compatible_xxhash64<T: AsRef<[u8]>>(data: T, seed: u64) -> u64 { + XxHash64::oneshot(seed, data.as_ref()) +} Review Comment: I took a look at this, and it may make the code a little cleaner, but also increases the size of the diff on this PR. Perhaps we could consider this as a follow-on cleanup? -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
