Convert rank / dense_rank and percent_rank builtin functions to UDWF
#12718
+687
−469
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,200 @@ | ||
| // 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. | ||
|
|
||
| //! Defines physical expression for `dense_rank` that can evaluated at runtime during query execution | ||
|
There was a problem hiding this comment. Technically speaking this module contains the I have this PR checked out to resolve some logical conflicts anyways, so I will pushed a commit to change it in this PR too |
||
|
|
||
| use std::any::Any; | ||
| use std::fmt::Debug; | ||
| use std::iter; | ||
| use std::ops::Range; | ||
| use std::sync::Arc; | ||
|
|
||
| use crate::define_udwf_and_expr; | ||
| use crate::rank::RankState; | ||
| use datafusion_common::arrow::array::ArrayRef; | ||
| use datafusion_common::arrow::array::UInt64Array; | ||
| use datafusion_common::arrow::compute::SortOptions; | ||
| use datafusion_common::arrow::datatypes::DataType; | ||
| use datafusion_common::arrow::datatypes::Field; | ||
| use datafusion_common::utils::get_row_at_idx; | ||
| use datafusion_common::{Result, ScalarValue}; | ||
| use datafusion_expr::{PartitionEvaluator, Signature, Volatility, WindowUDFImpl}; | ||
| use datafusion_functions_window_common::field; | ||
| use field::WindowUDFFieldArgs; | ||
|
|
||
| define_udwf_and_expr!( | ||
| DenseRank, | ||
| dense_rank, | ||
| "Returns rank of the current row without gaps. This function counts peer groups" | ||
| ); | ||
|
|
||
| /// dense_rank expression | ||
| #[derive(Debug)] | ||
| pub struct DenseRank { | ||
| signature: Signature, | ||
| } | ||
|
|
||
| impl DenseRank { | ||
| /// Create a new `dense_rank` function | ||
| pub fn new() -> Self { | ||
| Self { | ||
| signature: Signature::any(0, Volatility::Immutable), | ||
| } | ||
| } | ||
| } | ||
|
|
||
| impl Default for DenseRank { | ||
| fn default() -> Self { | ||
| Self::new() | ||
| } | ||
| } | ||
|
|
||
| impl WindowUDFImpl for DenseRank { | ||
| fn as_any(&self) -> &dyn Any { | ||
| self | ||
| } | ||
|
|
||
| fn name(&self) -> &str { | ||
| "dense_rank" | ||
| } | ||
|
|
||
| fn signature(&self) -> &Signature { | ||
| &self.signature | ||
| } | ||
|
|
||
| fn partition_evaluator(&self) -> Result<Box<dyn PartitionEvaluator>> { | ||
| Ok(Box::<DenseRankEvaluator>::default()) | ||
| } | ||
|
|
||
| fn field(&self, field_args: WindowUDFFieldArgs) -> Result<Field> { | ||
| Ok(Field::new(field_args.name(), DataType::UInt64, false)) | ||
| } | ||
|
|
||
| fn sort_options(&self) -> Option<SortOptions> { | ||
| Some(SortOptions { | ||
| descending: false, | ||
| nulls_first: false, | ||
| }) | ||
| } | ||
| } | ||
|
|
||
| /// State for the `dense_rank` built-in window function. | ||
| #[derive(Debug, Default)] | ||
| struct DenseRankEvaluator { | ||
| state: RankState, | ||
| } | ||
|
|
||
| impl PartitionEvaluator for DenseRankEvaluator { | ||
| fn is_causal(&self) -> bool { | ||
| // The dense_rank function doesn't need "future" values to emit results: | ||
| true | ||
| } | ||
|
|
||
| fn evaluate( | ||
| &mut self, | ||
| values: &[ArrayRef], | ||
| range: &Range<usize>, | ||
| ) -> Result<ScalarValue> { | ||
| let row_idx = range.start; | ||
| // There is no argument, values are order by column values (where rank is calculated) | ||
| let range_columns = values; | ||
| let last_rank_data = get_row_at_idx(range_columns, row_idx)?; | ||
| let new_rank_encountered = | ||
| if let Some(state_last_rank_data) = &self.state.last_rank_data { | ||
| // if rank data changes, new rank is encountered | ||
| state_last_rank_data != &last_rank_data | ||
| } else { | ||
| // First rank seen | ||
| true | ||
| }; | ||
|
|
||
| if new_rank_encountered { | ||
| self.state.last_rank_data = Some(last_rank_data); | ||
| self.state.last_rank_boundary += self.state.current_group_count; | ||
| self.state.current_group_count = 1; | ||
| self.state.n_rank += 1; | ||
| } else { | ||
| // data is still in the same rank | ||
| self.state.current_group_count += 1; | ||
| } | ||
|
|
||
| Ok(ScalarValue::UInt64(Some(self.state.n_rank as u64))) | ||
| } | ||
|
|
||
| fn evaluate_all_with_rank( | ||
| &self, | ||
| _num_rows: usize, | ||
| ranks_in_partition: &[Range<usize>], | ||
| ) -> Result<ArrayRef> { | ||
| let result = Arc::new(UInt64Array::from_iter_values( | ||
| ranks_in_partition | ||
| .iter() | ||
| .zip(1u64..) | ||
| .flat_map(|(range, rank)| { | ||
| let len = range.end - range.start; | ||
| iter::repeat(rank).take(len) | ||
| }), | ||
| )); | ||
|
|
||
| Ok(result) | ||
| } | ||
|
|
||
| fn supports_bounded_execution(&self) -> bool { | ||
| true | ||
| } | ||
|
|
||
| fn include_rank(&self) -> bool { | ||
| true | ||
| } | ||
| } | ||
|
|
||
| #[cfg(test)] | ||
| mod tests { | ||
| use super::*; | ||
| use datafusion_common::cast::as_uint64_array; | ||
|
|
||
| fn test_with_rank(expr: &DenseRank, expected: Vec<u64>) -> Result<()> { | ||
| test_i32_result(expr, vec![0..2, 2..3, 3..6, 6..7, 7..8], expected) | ||
| } | ||
|
|
||
| #[allow(clippy::single_range_in_vec_init)] | ||
| fn test_without_rank(expr: &DenseRank, expected: Vec<u64>) -> Result<()> { | ||
| test_i32_result(expr, vec![0..8], expected) | ||
| } | ||
|
|
||
| fn test_i32_result( | ||
| expr: &DenseRank, | ||
| ranks: Vec<Range<usize>>, | ||
| expected: Vec<u64>, | ||
| ) -> Result<()> { | ||
| let result = expr | ||
| .partition_evaluator()? | ||
| .evaluate_all_with_rank(8, &ranks)?; | ||
| let result = as_uint64_array(&result)?; | ||
| let result = result.values(); | ||
| assert_eq!(expected, *result); | ||
| Ok(()) | ||
| } | ||
|
|
||
| #[test] | ||
| fn test_dense_rank() -> Result<()> { | ||
| let r = DenseRank::default(); | ||
| test_without_rank(&r, vec![1; 8])?; | ||
| test_with_rank(&r, vec![1, 1, 2, 3, 3, 3, 4, 5])?; | ||
| Ok(()) | ||
| } | ||
| } | ||
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
the expr function have written docs for the percent_rank,
but when I try to import the percent_rank from datafusion_functions_window workspace,
its throwing error related to the circular depency
how to handle such cases ?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
There are a couple of ways to get around this. But here I noticed that the
first_valuefunction is a mock and not the realfirst_valuewindow function.So you can consider doing the same for
percent_rank. Then you don't have to import anything. This is alright because the test is not testing the functionality ofpercent_rankin the doc test.Another advantage of mocking in this specific case is that the change remains local to the doc test which I believe is good.