xudong963 commented on code in PR #16362: URL: https://github.com/apache/datafusion/pull/16362#discussion_r2161147718
########## datafusion/optimizer/src/simplify_predicates.rs: ########## @@ -0,0 +1,194 @@ +// 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 datafusion_common::{Column, Result, ScalarValue}; +use datafusion_expr::{BinaryExpr, Cast, Expr, Operator}; +use std::collections::BTreeMap; + +pub(crate) fn simplify_predicates(predicates: Vec<Expr>) -> Result<Vec<Expr>> { + // Early return for simple cases + if predicates.len() <= 1 { + return Ok(predicates); + } + + // Group predicates by their column reference + let mut column_predicates: BTreeMap<Column, Vec<Expr>> = BTreeMap::new(); + let mut other_predicates = Vec::new(); + + for pred in predicates { + match &pred { + Expr::BinaryExpr(BinaryExpr { + left, + op: + Operator::Gt + | Operator::GtEq + | Operator::Lt + | Operator::LtEq + | Operator::Eq, + right, + }) => { + let left_col = extract_column_from_expr(left); + let right_col = extract_column_from_expr(right); + let left_lit = left.is_literal(); + let right_lit = right.is_literal(); + if let (Some(col), true) = (&left_col, right_lit) { + column_predicates.entry(col.clone()).or_default().push(pred); + } else if let (true, Some(col)) = (left_lit, &right_col) { + column_predicates.entry(col.clone()).or_default().push(pred); + } else { + other_predicates.push(pred); + } + } + _ => other_predicates.push(pred), + } + } + + // Process each column's predicates to remove redundancies + let mut result = other_predicates; + for (_, preds) in column_predicates { + let simplified = simplify_column_predicates(preds)?; + result.extend(simplified); + } + + Ok(result) +} + +fn simplify_column_predicates(predicates: Vec<Expr>) -> Result<Vec<Expr>> { Review Comment: Yes, I'll open an issue to track the general way, it may involve more discussion, such as 1. A new physical rule? Or leverage the current physical filter push down 2. Some filters, such as partition columns related predicates, will be fully pushed down scan, that is, we don't have such predicates in some FilterExec. How to capture this? 3. TBD -- 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
