1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547
// 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.
#![warn(missing_docs, clippy::needless_borrow)]
//! [DataFusion] is an extensible query engine written in Rust that
//! uses [Apache Arrow] as its in-memory format. DataFusion's many [use
//! cases] help developers build very fast and feature rich database
//! and analytic systems, customized to particular workloads.
//!
//! "Out of the box," DataFusion quickly runs complex [SQL] and
//! [`DataFrame`] queries using a sophisticated query planner, a columnar,
//! multi-threaded, vectorized execution engine, and partitioned data
//! sources (Parquet, CSV, JSON, and Avro).
//!
//! DataFusion is designed for easy customization such as supporting
//! additional data sources, query languages, functions, custom
//! operators and more. See the [Architecture] section for more details.
//!
//! [DataFusion]: https://arrow.apache.org/datafusion/
//! [Apache Arrow]: https://arrow.apache.org
//! [use cases]: https://arrow.apache.org/datafusion/user-guide/introduction.html#use-cases
//! [SQL]: https://arrow.apache.org/datafusion/user-guide/sql/index.html
//! [`DataFrame`]: dataframe::DataFrame
//! [Architecture]: #architecture
//!
//! # Examples
//!
//! The main entry point for interacting with DataFusion is the
//! [`SessionContext`]. [`Expr`]s represent expressions such as `a + b`.
//!
//! [`SessionContext`]: execution::context::SessionContext
//!
//! ## DataFrame
//!
//! To execute a query against data stored
//! in a CSV file using a [`DataFrame`]:
//!
//! ```rust
//! # use datafusion::prelude::*;
//! # use datafusion::error::Result;
//! # use datafusion::arrow::record_batch::RecordBatch;
//!
//! # #[tokio::main]
//! # async fn main() -> Result<()> {
//! let ctx = SessionContext::new();
//!
//! // create the dataframe
//! let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
//!
//! // create a plan
//! let df = df.filter(col("a").lt_eq(col("b")))?
//! .aggregate(vec![col("a")], vec![min(col("b"))])?
//! .limit(0, Some(100))?;
//!
//! // execute the plan
//! let results: Vec<RecordBatch> = df.collect().await?;
//!
//! // format the results
//! let pretty_results = arrow::util::pretty::pretty_format_batches(&results)?
//! .to_string();
//!
//! let expected = vec![
//! "+---+----------------+",
//! "| a | MIN(?table?.b) |",
//! "+---+----------------+",
//! "| 1 | 2 |",
//! "+---+----------------+"
//! ];
//!
//! assert_eq!(pretty_results.trim().lines().collect::<Vec<_>>(), expected);
//! # Ok(())
//! # }
//! ```
//!
//! ## SQL
//!
//! To execute a query against a CSV file using [SQL]:
//!
//! ```
//! # use datafusion::prelude::*;
//! # use datafusion::error::Result;
//! # use datafusion::arrow::record_batch::RecordBatch;
//!
//! # #[tokio::main]
//! # async fn main() -> Result<()> {
//! let ctx = SessionContext::new();
//!
//! ctx.register_csv("example", "tests/data/example.csv", CsvReadOptions::new()).await?;
//!
//! // create a plan
//! let df = ctx.sql("SELECT a, MIN(b) FROM example WHERE a <= b GROUP BY a LIMIT 100").await?;
//!
//! // execute the plan
//! let results: Vec<RecordBatch> = df.collect().await?;
//!
//! // format the results
//! let pretty_results = arrow::util::pretty::pretty_format_batches(&results)?
//! .to_string();
//!
//! let expected = vec![
//! "+---+----------------+",
//! "| a | MIN(example.b) |",
//! "+---+----------------+",
//! "| 1 | 2 |",
//! "+---+----------------+"
//! ];
//!
//! assert_eq!(pretty_results.trim().lines().collect::<Vec<_>>(), expected);
//! # Ok(())
//! # }
//! ```
//!
//! ## More Examples
//!
//! There are many additional annotated examples of using DataFusion in the [datafusion-examples] directory.
//!
//! [datafusion-examples]: https://github.com/apache/arrow-datafusion/tree/main/datafusion-examples
//!
//! ## Customization and Extension
//!
//! DataFusion is a "disaggregated" query engine. This
//! means developers can start with a working, full featured engine, and then
//! extend the areas they need to specialize for their usecase. For example,
//! some projects may add custom [`ExecutionPlan`] operators, or create their own
//! query language that directly creates [`LogicalPlan`] rather than using the
//! built in SQL planner, [`SqlToRel`].
//!
//! In order to achieve this, DataFusion supports extension at many points:
//!
//! * read from any datasource ([`TableProvider`])
//! * define your own catalogs, schemas, and table lists ([`CatalogProvider`])
//! * build your own query language or plans ([`LogicalPlanBuilder`])
//! * declare and use user-defined functions ([`ScalarUDF`], and [`AggregateUDF`], [`WindowUDF`])
//! * add custom plan rewrite passes ([`AnalyzerRule`], [`OptimizerRule`] and [`PhysicalOptimizerRule`])
//! * extend the planner to use user-defined logical and physical nodes ([`QueryPlanner`])
//!
//! You can find examples of each of them in the [datafusion-examples] directory.
//!
//! [`TableProvider`]: crate::datasource::TableProvider
//! [`CatalogProvider`]: crate::catalog::CatalogProvider
//! [`LogicalPlanBuilder`]: datafusion_expr::logical_plan::builder::LogicalPlanBuilder
//! [`ScalarUDF`]: crate::logical_expr::ScalarUDF
//! [`AggregateUDF`]: crate::logical_expr::AggregateUDF
//! [`WindowUDF`]: crate::logical_expr::WindowUDF
//! [`QueryPlanner`]: execution::context::QueryPlanner
//! [`OptimizerRule`]: datafusion_optimizer::optimizer::OptimizerRule
//! [`AnalyzerRule`]: datafusion_optimizer::analyzer::AnalyzerRule
//! [`PhysicalOptimizerRule`]: crate::physical_optimizer::optimizer::PhysicalOptimizerRule
//!
//! # Architecture
//!
//! <!-- NOTE: The goal of this section is to provide a high level
//! overview of how DataFusion is organized and then link to other
//! sections of the docs with more details -->
//!
//! ## Overview Presentations
//!
//! The following presentations offer high level overviews of the
//! different components and how they interact together.
//!
//! - [Apr 2023]: The Apache Arrow DataFusion Architecture talks
//! - _Query Engine_: [recording](https://youtu.be/NVKujPxwSBA) and [slides](https://docs.google.com/presentation/d/1D3GDVas-8y0sA4c8EOgdCvEjVND4s2E7I6zfs67Y4j8/edit#slide=id.p)
//! - _Logical Plan and Expressions_: [recording](https://youtu.be/EzZTLiSJnhY) and [slides](https://docs.google.com/presentation/d/1ypylM3-w60kVDW7Q6S99AHzvlBgciTdjsAfqNP85K30)
//! - _Physical Plan and Execution_: [recording](https://youtu.be/2jkWU3_w6z0) and [slides](https://docs.google.com/presentation/d/1cA2WQJ2qg6tx6y4Wf8FH2WVSm9JQ5UgmBWATHdik0hg)
//! - [July 2022]: DataFusion and Arrow: Supercharge Your Data Analytical Tool with a Rusty Query Engine: [recording](https://www.youtube.com/watch?v=Rii1VTn3seQ) and [slides](https://docs.google.com/presentation/d/1q1bPibvu64k2b7LPi7Yyb0k3gA1BiUYiUbEklqW1Ckc/view#slide=id.g11054eeab4c_0_1165)
//! - [March 2021]: The DataFusion architecture is described in _Query Engine Design and the Rust-Based DataFusion in Apache Arrow_: [recording](https://www.youtube.com/watch?v=K6eCAVEk4kU) (DataFusion content starts [~ 15 minutes in](https://www.youtube.com/watch?v=K6eCAVEk4kU&t=875s)) and [slides](https://www.slideshare.net/influxdata/influxdb-iox-tech-talks-query-engine-design-and-the-rustbased-datafusion-in-apache-arrow-244161934)
//! - [February 2021]: How DataFusion is used within the Ballista Project is described in _Ballista: Distributed Compute with Rust and Apache Arrow_: [recording](https://www.youtube.com/watch?v=ZZHQaOap9pQ)
//!
//! ## Query Planning and Execution Overview
//!
//! ### SQL
//!
//! ```text
//! Parsed with SqlToRel creates
//! sqlparser initial plan
//! ┌───────────────┐ ┌─────────┐ ┌─────────────┐
//! │ SELECT * │ │Query { │ │Project │
//! │ FROM ... │──────────▶│.. │────────────▶│ TableScan │
//! │ │ │} │ │ ... │
//! └───────────────┘ └─────────┘ └─────────────┘
//!
//! SQL String sqlparser LogicalPlan
//! AST nodes
//! ```
//!
//! 1. The query string is parsed to an Abstract Syntax Tree (AST)
//! [`Statement`] using [sqlparser].
//!
//! 2. The AST is converted to a [`LogicalPlan`] and logical
//! expressions [`Expr`]s to compute the desired result by the
//! [`SqlToRel`] planner.
//!
//! [`Statement`]: https://docs.rs/sqlparser/latest/sqlparser/ast/enum.Statement.html
//!
//! ### DataFrame
//!
//! When executing plans using the [`DataFrame`] API, the process is
//! identical as with SQL, except the DataFrame API builds the
//! [`LogicalPlan`] directly using [`LogicalPlanBuilder`]. Systems
//! that have their own custom query languages typically also build
//! [`LogicalPlan`] directly.
//!
//! ### Planning
//!
//! ```text
//! AnalyzerRules and PhysicalPlanner PhysicalOptimizerRules
//! OptimizerRules creates ExecutionPlan improve performance
//! rewrite plan
//! ┌─────────────┐ ┌─────────────┐ ┌───────────────┐ ┌───────────────┐
//! │Project │ │Project(x, y)│ │ProjectExec │ │ProjectExec │
//! │ TableScan │──...──▶│ TableScan │─────▶│ ... │──...──▶│ ... │
//! │ ... │ │ ... │ │ ParquetExec│ │ ParquetExec│
//! └─────────────┘ └─────────────┘ └───────────────┘ └───────────────┘
//!
//! LogicalPlan LogicalPlan ExecutionPlan ExecutionPlan
//! ```
//!
//! To process large datasets with many rows as efficiently as
//! possible, significant effort is spent planning and
//! optimizing, in the following manner:
//!
//! 1. The [`LogicalPlan`] is checked and rewritten to enforce
//! semantic rules, such as type coercion, by [`AnalyzerRule`]s
//!
//! 2. The [`LogicalPlan`] is rewritten by [`OptimizerRule`]s, such as
//! projection and filter pushdown, to improve its efficiency.
//!
//! 3. The [`LogicalPlan`] is converted to an [`ExecutionPlan`] by a
//! [`PhysicalPlanner`]
//!
//! 4. The [`ExecutionPlan`] is rewritten by
//! [`PhysicalOptimizerRule`]s, such as sort and join selection, to
//! improve its efficiency.
//!
//! ## Data Sources
//!
//! ```text
//! Planning │
//! requests │ TableProvider::scan
//! information │ creates an
//! such as schema │ ExecutionPlan
//! │
//! ▼
//! ┌─────────────────────────┐ ┌──────────────┐
//! │ │ │ │
//! │impl TableProvider │────────▶│ParquetExec │
//! │ │ │ │
//! └─────────────────────────┘ └──────────────┘
//! TableProvider
//! (built in or user provided) ExecutionPlan
//! ```
//!
//! DataFusion includes several built in data sources for common use
//! cases, and can be extended by implementing the [`TableProvider`]
//! trait. A [`TableProvider`] provides information for planning and
//! an [`ExecutionPlan`]s for execution.
//!
//! 1. [`ListingTable`]: Reads data from Parquet, JSON, CSV, or AVRO
//! files. Supports single files or multiple files with HIVE style
//! partitioning, optional compression, directly reading from remote
//! object store and more.
//!
//! 2. [`MemTable`]: Reads data from in memory [`RecordBatch`]es.
//!
//! 3. [`StreamingTable`]: Reads data from potentially unbounded inputs.
//!
//! [`ListingTable`]: crate::datasource::listing::ListingTable
//! [`MemTable`]: crate::datasource::memory::MemTable
//! [`StreamingTable`]: crate::datasource::streaming::StreamingTable
//!
//! ## Plan Representations
//!
//! ### Logical Plans
//! Logical planning yields [`LogicalPlan`] nodes and [`Expr`]
//! representing expressions which are [`Schema`] aware and represent statements
//! independent of how they are physically executed.
//! A [`LogicalPlan`] is a Directed Acyclic Graph (DAG) of other
//! [`LogicalPlan`]s, each potentially containing embedded [`Expr`]s.
//!
//! [`Expr`]s can be rewritten using the [`TreeNode`] API and simplified using
//! [`ExprSimplifier`]. Examples of working with and executing `Expr`s can be found in the
//! [`expr_api`.rs] example
//!
//! [`TreeNode`]: datafusion_common::tree_node::TreeNode
//! [`ExprSimplifier`]: crate::optimizer::simplify_expressions::ExprSimplifier
//! [`expr_api`.rs]: https://github.com/apache/arrow-datafusion/blob/main/datafusion-examples/examples/expr_api.rs
//!
//! ### Physical Plans
//!
//! An [`ExecutionPlan`] (sometimes referred to as a "physical plan")
//! is a plan that can be executed against data. It a DAG of other
//! [`ExecutionPlan`]s each potentially containing expressions that implement the
//! [`PhysicalExpr`] trait.
//!
//! Compared to a [`LogicalPlan`], an [`ExecutionPlan`] has additional concrete
//! information about how to perform calculations (e.g. hash vs merge
//! join), and how data flows during execution (e.g. partitioning and
//! sortedness).
//!
//! [cp_solver] performs range propagation analysis on [`PhysicalExpr`]s and
//! [`PruningPredicate`] can prove certain boolean [`PhysicalExpr`]s used for
//! filtering can never be `true` using additional statistical information.
//!
//! [cp_solver]: crate::physical_expr::intervals::cp_solver
//! [`PruningPredicate`]: crate::physical_optimizer::pruning::PruningPredicate
//! [`PhysicalExpr`]: crate::physical_plan::PhysicalExpr
//!
//! ## Execution
//!
//! ```text
//! ExecutionPlan::execute Calling next() on the
//! produces a stream stream produces the data
//!
//! ┌───────────────┐ ┌─────────────────────────┐ ┌────────────┐
//! │ProjectExec │ │impl │ ┌───▶│RecordBatch │
//! │ ... │─────▶│SendableRecordBatchStream│────┤ └────────────┘
//! │ ParquetExec│ │ │ │ ┌────────────┐
//! └───────────────┘ └─────────────────────────┘ ├───▶│RecordBatch │
//! ▲ │ └────────────┘
//! ExecutionPlan │ │ ...
//! │ │
//! │ │ ┌────────────┐
//! PhysicalOptimizerRules ├───▶│RecordBatch │
//! request information │ └────────────┘
//! such as partitioning │ ┌ ─ ─ ─ ─ ─ ─
//! └───▶ None │
//! └ ─ ─ ─ ─ ─ ─
//! ```
//!
//! [`ExecutionPlan`]s process data using the [Apache Arrow] memory
//! format, making heavy use of functions from the [arrow]
//! crate. Values are represented with [`ColumnarValue`], which are either
//! [`ScalarValue`] (single constant values) or [`ArrayRef`] (Arrow
//! Arrays).
//!
//! Calling [`execute`] produces 1 or more partitions of data,
//! as a [`SendableRecordBatchStream`], which implements a pull based execution
//! API. Calling `.next().await` will incrementally compute and return the next
//! [`RecordBatch`]. Balanced parallelism is achieved using [Volcano style]
//! "Exchange" operations implemented by [`RepartitionExec`].
//!
//! While some recent research such as [Morsel-Driven Parallelism] describes challenges
//! with the pull style Volcano execution model on NUMA architectures, in practice DataFusion achieves
//! similar scalability as systems that use morsel driven approach such as DuckDB.
//! See the [DataFusion paper submitted to SIGMOD] for more details.
//!
//! [`execute`]: physical_plan::ExecutionPlan::execute
//! [`SendableRecordBatchStream`]: crate::physical_plan::SendableRecordBatchStream
//! [`ColumnarValue`]: datafusion_expr::ColumnarValue
//! [`ScalarValue`]: crate::scalar::ScalarValue
//! [`ArrayRef`]: arrow::array::ArrayRef
//! [`Stream`]: futures::stream::Stream
//!
//! See the [implementors of `ExecutionPlan`] for a list of physical operators available.
//!
//! [`RepartitionExec`]: https://docs.rs/datafusion/latest/datafusion/physical_plan/repartition/struct.RepartitionExec.html
//! [Volcano style]: https://w6113.github.io/files/papers/volcanoparallelism-89.pdf
//! [Morsel-Driven Parallelism]: https://db.in.tum.de/~leis/papers/morsels.pdf
//! [DataFusion paper submitted SIGMOD]: https://github.com/apache/arrow-datafusion/files/13874720/DataFusion_Query_Engine___SIGMOD_2024.pdf
//! [implementors of `ExecutionPlan`]: https://docs.rs/datafusion/latest/datafusion/physical_plan/trait.ExecutionPlan.html#implementors
//!
//! ## Thread Scheduling
//!
//! DataFusion incrementally computes output from a [`SendableRecordBatchStream`]
//! with `target_partitions` threads. Parallelism is implementing using multiple
//! [Tokio] [`task`]s, which are executed by threads managed by a tokio Runtime.
//! While tokio is most commonly used
//! for asynchronous network I/O, its combination of an efficient, work-stealing
//! scheduler, first class compiler support for automatic continuation generation,
//! and exceptional performance makes it a compelling choice for CPU intensive
//! applications as well. This is explained in more detail in [Using Rustlang’s Async Tokio
//! Runtime for CPU-Bound Tasks].
//!
//! [Tokio]: https://tokio.rs
//! [`task`]: tokio::task
//! [Using Rustlang’s Async Tokio Runtime for CPU-Bound Tasks]: https://thenewstack.io/using-rustlangs-async-tokio-runtime-for-cpu-bound-tasks/
//!
//! ## State Management and Configuration
//!
//! [`ConfigOptions`] contain options to control DataFusion's
//! execution.
//!
//! [`ConfigOptions`]: datafusion_common::config::ConfigOptions
//!
//! The state required to execute queries is managed by the following
//! structures:
//!
//! 1. [`SessionContext`]: State needed for create [`LogicalPlan`]s such
//! as the table definitions, and the function registries.
//!
//! 2. [`TaskContext`]: State needed for execution such as the
//! [`MemoryPool`], [`DiskManager`], and [`ObjectStoreRegistry`].
//!
//! 3. [`ExecutionProps`]: Per-execution properties and data (such as
//! starting timestamps, etc).
//!
//! [`SessionContext`]: crate::execution::context::SessionContext
//! [`TaskContext`]: crate::execution::context::TaskContext
//! [`ExecutionProps`]: crate::execution::context::ExecutionProps
//!
//! ### Resource Management
//!
//! The amount of memory and temporary local disk space used by
//! DataFusion when running a plan can be controlled using the
//! [`MemoryPool`] and [`DiskManager`]. Other runtime options can be
//! found on [`RuntimeEnv`].
//!
//! [`DiskManager`]: crate::execution::DiskManager
//! [`MemoryPool`]: crate::execution::memory_pool::MemoryPool
//! [`RuntimeEnv`]: crate::execution::runtime_env::RuntimeEnv
//! [`ObjectStoreRegistry`]: crate::datasource::object_store::ObjectStoreRegistry
//!
//! ## Crate Organization
//!
//! DataFusion is organized into multiple crates to enforce modularity
//! and improve compilation times. The crates are:
//!
//! * [datafusion_common]: Common traits and types
//! * [datafusion_expr]: [`LogicalPlan`], [`Expr`] and related logical planning structure
//! * [datafusion_execution]: State and structures needed for execution
//! * [datafusion_optimizer]: [`OptimizerRule`]s and [`AnalyzerRule`]s
//! * [datafusion_physical_expr]: [`PhysicalExpr`] and related expressions
//! * [datafusion_sql]: SQL planner ([`SqlToRel`])
//!
//! [sqlparser]: https://docs.rs/sqlparser/latest/sqlparser
//! [`SqlToRel`]: sql::planner::SqlToRel
//! [`Expr`]: datafusion_expr::Expr
//! [`LogicalPlan`]: datafusion_expr::LogicalPlan
//! [`AnalyzerRule`]: datafusion_optimizer::analyzer::AnalyzerRule
//! [`OptimizerRule`]: optimizer::optimizer::OptimizerRule
//! [`ExecutionPlan`]: physical_plan::ExecutionPlan
//! [`PhysicalPlanner`]: physical_planner::PhysicalPlanner
//! [`PhysicalOptimizerRule`]: datafusion::physical_optimizer::optimizer::PhysicalOptimizerRule
//! [`Schema`]: arrow::datatypes::Schema
//! [`PhysicalExpr`]: physical_plan::PhysicalExpr
//! [`AggregateExpr`]: physical_plan::AggregateExpr
//! [`RecordBatch`]: arrow::record_batch::RecordBatch
//! [`RecordBatchReader`]: arrow::record_batch::RecordBatchReader
//! [`Array`]: arrow::array::Array
/// DataFusion crate version
pub const DATAFUSION_VERSION: &str = env!("CARGO_PKG_VERSION");
extern crate core;
extern crate sqlparser;
pub mod catalog;
pub mod dataframe;
pub mod datasource;
pub mod error;
pub mod execution;
pub mod physical_optimizer;
pub mod physical_planner;
pub mod prelude;
pub mod scalar;
pub mod variable;
// re-export dependencies from arrow-rs to minimize version maintenance for crate users
pub use arrow;
#[cfg(feature = "parquet")]
pub use parquet;
// re-export DataFusion sub-crates at the top level. Use `pub use *`
// so that the contents of the subcrates appears in rustdocs
// for details, see https://github.com/apache/arrow-datafusion/issues/6648
/// re-export of [`datafusion_common`] crate
pub mod common {
pub use datafusion_common::*;
/// re-export of [`datafusion_common_runtime`] crate
pub mod runtime {
pub use datafusion_common_runtime::*;
}
}
// Backwards compatibility
pub use common::config;
// NB datafusion execution is re-exported in the `execution` module
/// re-export of [`datafusion_expr`] crate
pub mod logical_expr {
pub use datafusion_expr::*;
}
/// re-export of [`datafusion_optimizer`] crate
pub mod optimizer {
pub use datafusion_optimizer::*;
}
/// re-export of [`datafusion_physical_expr`] crate
pub mod physical_expr {
pub use datafusion_physical_expr::*;
}
/// re-export of [`datafusion_physical_plan`] crate
pub mod physical_plan {
pub use datafusion_physical_plan::*;
}
// Reexport testing macros for compatibility
pub use datafusion_common::assert_batches_eq;
pub use datafusion_common::assert_batches_sorted_eq;
/// re-export of [`datafusion_sql`] crate
pub mod sql {
pub use datafusion_sql::*;
}
/// re-export of [`datafusion_functions`] crate
pub mod functions {
pub use datafusion_functions::*;
}
/// re-export of [`datafusion_functions_array`] crate, if "array_expressions" feature is enabled
pub mod functions_array {
#[cfg(feature = "array_expressions")]
pub use datafusion_functions_array::*;
}
#[cfg(test)]
pub mod test;
pub mod test_util;
#[cfg(doctest)]
doc_comment::doctest!("../../../README.md", readme_example_test);
#[cfg(doctest)]
doc_comment::doctest!(
"../../../docs/source/user-guide/example-usage.md",
user_guid_example_tests
);