datafusion_catalog/
streaming.rs

1// Licensed to the Apache Software Foundation (ASF) under one
2// or more contributor license agreements.  See the NOTICE file
3// distributed with this work for additional information
4// regarding copyright ownership.  The ASF licenses this file
5// to you under the Apache License, Version 2.0 (the
6// "License"); you may not use this file except in compliance
7// with the License.  You may obtain a copy of the License at
8//
9//   http://www.apache.org/licenses/LICENSE-2.0
10//
11// Unless required by applicable law or agreed to in writing,
12// software distributed under the License is distributed on an
13// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
14// KIND, either express or implied.  See the License for the
15// specific language governing permissions and limitations
16// under the License.
17
18//! A simplified [`TableProvider`] for streaming partitioned datasets
19
20use std::any::Any;
21use std::sync::Arc;
22
23use crate::Session;
24use crate::TableProvider;
25
26use arrow::datatypes::SchemaRef;
27use datafusion_common::{plan_err, DFSchema, Result};
28use datafusion_expr::{Expr, SortExpr, TableType};
29use datafusion_physical_expr::{create_physical_sort_exprs, LexOrdering};
30use datafusion_physical_plan::streaming::{PartitionStream, StreamingTableExec};
31use datafusion_physical_plan::ExecutionPlan;
32
33use async_trait::async_trait;
34use log::debug;
35
36/// A [`TableProvider`] that streams a set of [`PartitionStream`]
37#[derive(Debug)]
38pub struct StreamingTable {
39    schema: SchemaRef,
40    partitions: Vec<Arc<dyn PartitionStream>>,
41    infinite: bool,
42    sort_order: Vec<SortExpr>,
43}
44
45impl StreamingTable {
46    /// Try to create a new [`StreamingTable`] returning an error if the schema is incorrect
47    pub fn try_new(
48        schema: SchemaRef,
49        partitions: Vec<Arc<dyn PartitionStream>>,
50    ) -> Result<Self> {
51        for x in partitions.iter() {
52            let partition_schema = x.schema();
53            if !schema.contains(partition_schema) {
54                debug!(
55                    "target schema does not contain partition schema. \
56                        Target_schema: {schema:?}. Partition Schema: {partition_schema:?}"
57                );
58                return plan_err!("Mismatch between schema and batches");
59            }
60        }
61
62        Ok(Self {
63            schema,
64            partitions,
65            infinite: false,
66            sort_order: vec![],
67        })
68    }
69
70    /// Sets streaming table can be infinite.
71    pub fn with_infinite_table(mut self, infinite: bool) -> Self {
72        self.infinite = infinite;
73        self
74    }
75
76    /// Sets the existing ordering of streaming table.
77    pub fn with_sort_order(mut self, sort_order: Vec<SortExpr>) -> Self {
78        self.sort_order = sort_order;
79        self
80    }
81}
82
83#[async_trait]
84impl TableProvider for StreamingTable {
85    fn as_any(&self) -> &dyn Any {
86        self
87    }
88
89    fn schema(&self) -> SchemaRef {
90        Arc::clone(&self.schema)
91    }
92
93    fn table_type(&self) -> TableType {
94        TableType::View
95    }
96
97    async fn scan(
98        &self,
99        state: &dyn Session,
100        projection: Option<&Vec<usize>>,
101        _filters: &[Expr],
102        limit: Option<usize>,
103    ) -> Result<Arc<dyn ExecutionPlan>> {
104        let physical_sort = if !self.sort_order.is_empty() {
105            let df_schema = DFSchema::try_from(Arc::clone(&self.schema))?;
106            let eqp = state.execution_props();
107
108            create_physical_sort_exprs(&self.sort_order, &df_schema, eqp)?
109        } else {
110            vec![]
111        };
112
113        Ok(Arc::new(StreamingTableExec::try_new(
114            Arc::clone(&self.schema),
115            self.partitions.clone(),
116            projection,
117            LexOrdering::new(physical_sort),
118            self.infinite,
119            limit,
120        )?))
121    }
122}
datafusion_catalog/streaming.rs

datafusion_catalog/
streaming.rs
