datafusion_common/
lib.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#![doc(
19    html_logo_url = "https://raw.githubusercontent.com/apache/datafusion/19fe44cf2f30cbdd63d4a4f52c74055163c6cc38/docs/logos/standalone_logo/logo_original.svg",
20    html_favicon_url = "https://raw.githubusercontent.com/apache/datafusion/19fe44cf2f30cbdd63d4a4f52c74055163c6cc38/docs/logos/standalone_logo/logo_original.svg"
21)]
22#![cfg_attr(docsrs, feature(doc_auto_cfg))]
23// Make sure fast / cheap clones on Arc are explicit:
24// https://github.com/apache/datafusion/issues/11143
25#![deny(clippy::clone_on_ref_ptr)]
26
27mod column;
28mod dfschema;
29mod functional_dependencies;
30mod join_type;
31mod param_value;
32#[cfg(feature = "pyarrow")]
33mod pyarrow;
34mod schema_reference;
35mod table_reference;
36mod unnest;
37
38pub mod alias;
39pub mod cast;
40pub mod config;
41pub mod cse;
42pub mod diagnostic;
43pub mod display;
44pub mod encryption;
45pub mod error;
46pub mod file_options;
47pub mod format;
48pub mod hash_utils;
49pub mod instant;
50pub mod nested_struct;
51mod null_equality;
52pub mod parsers;
53pub mod pruning;
54pub mod rounding;
55pub mod scalar;
56pub mod spans;
57pub mod stats;
58pub mod test_util;
59pub mod tree_node;
60pub mod types;
61pub mod utils;
62
63/// Reexport arrow crate
64pub use arrow;
65pub use column::Column;
66pub use dfschema::{
67    qualified_name, DFSchema, DFSchemaRef, ExprSchema, SchemaExt, ToDFSchema,
68};
69pub use diagnostic::Diagnostic;
70pub use error::{
71    field_not_found, unqualified_field_not_found, DataFusionError, Result, SchemaError,
72    SharedResult,
73};
74pub use file_options::file_type::{
75    GetExt, DEFAULT_ARROW_EXTENSION, DEFAULT_AVRO_EXTENSION, DEFAULT_CSV_EXTENSION,
76    DEFAULT_JSON_EXTENSION, DEFAULT_PARQUET_EXTENSION,
77};
78pub use functional_dependencies::{
79    aggregate_functional_dependencies, get_required_group_by_exprs_indices,
80    get_target_functional_dependencies, Constraint, Constraints, Dependency,
81    FunctionalDependence, FunctionalDependencies,
82};
83use hashbrown::hash_map::DefaultHashBuilder;
84pub use join_type::{JoinConstraint, JoinSide, JoinType};
85pub use null_equality::NullEquality;
86pub use param_value::ParamValues;
87pub use scalar::{ScalarType, ScalarValue};
88pub use schema_reference::SchemaReference;
89pub use spans::{Location, Span, Spans};
90pub use stats::{ColumnStatistics, Statistics};
91pub use table_reference::{ResolvedTableReference, TableReference};
92pub use unnest::{RecursionUnnestOption, UnnestOptions};
93pub use utils::project_schema;
94
95// These are hidden from docs purely to avoid polluting the public view of what this crate exports.
96// These are just re-exports of macros by the same name, which gets around the 'cannot refer to
97// macro-expanded macro_export macros by their full path' error.
98// The design to get around this comes from this comment:
99// https://github.com/rust-lang/rust/pull/52234#issuecomment-976702997
100#[doc(hidden)]
101pub use error::{
102    _config_datafusion_err, _exec_datafusion_err, _internal_datafusion_err,
103    _not_impl_datafusion_err, _plan_datafusion_err, _resources_datafusion_err,
104    _substrait_datafusion_err,
105};
106
107// The HashMap and HashSet implementations that should be used as the uniform defaults
108pub type HashMap<K, V, S = DefaultHashBuilder> = hashbrown::HashMap<K, V, S>;
109pub type HashSet<T, S = DefaultHashBuilder> = hashbrown::HashSet<T, S>;
110
111/// Downcast an Arrow Array to a concrete type, return an `DataFusionError::Internal` if the cast is
112/// not possible. In normal usage of DataFusion the downcast should always succeed.
113///
114/// Example: `let array = downcast_value!(values, Int32Array)`
115#[macro_export]
116macro_rules! downcast_value {
117    ($Value: expr, $Type: ident) => {{
118        use $crate::__private::DowncastArrayHelper;
119        $Value.downcast_array_helper::<$Type>()?
120    }};
121    ($Value: expr, $Type: ident, $T: tt) => {{
122        use $crate::__private::DowncastArrayHelper;
123        $Value.downcast_array_helper::<$Type<$T>>()?
124    }};
125}
126
127// Not public API.
128#[doc(hidden)]
129pub mod __private {
130    use crate::error::_internal_datafusion_err;
131    use crate::Result;
132    use arrow::array::Array;
133    use std::any::{type_name, Any};
134
135    #[doc(hidden)]
136    pub trait DowncastArrayHelper {
137        fn downcast_array_helper<U: Any>(&self) -> Result<&U>;
138    }
139
140    impl<T: Array + ?Sized> DowncastArrayHelper for T {
141        fn downcast_array_helper<U: Any>(&self) -> Result<&U> {
142            self.as_any().downcast_ref().ok_or_else(|| {
143                let actual_type = self.data_type();
144                let desired_type_name = type_name::<U>();
145                _internal_datafusion_err!(
146                    "could not cast array of type {} to {}",
147                    actual_type,
148                    desired_type_name
149                )
150            })
151        }
152    }
153}
154
155#[cfg(test)]
156mod tests {
157    use arrow::array::{ArrayRef, Int32Array, UInt64Array};
158    use std::any::{type_name, type_name_of_val};
159    use std::sync::Arc;
160
161    #[test]
162    fn test_downcast_value() -> crate::Result<()> {
163        let boxed: ArrayRef = Arc::new(Int32Array::from(vec![1, 2, 3]));
164        let array = downcast_value!(&boxed, Int32Array);
165        assert_eq!(type_name_of_val(&array), type_name::<&Int32Array>());
166
167        let expected: Int32Array = vec![1, 2, 3].into_iter().map(Some).collect();
168        assert_eq!(array, &expected);
169        Ok(())
170    }
171
172    #[test]
173    fn test_downcast_value_err_message() {
174        let boxed: ArrayRef = Arc::new(Int32Array::from(vec![1, 2, 3]));
175        let error: crate::DataFusionError = (|| {
176            downcast_value!(&boxed, UInt64Array);
177            Ok(())
178        })()
179        .err()
180        .unwrap();
181
182        assert_starts_with(
183            error.to_string(),
184            "Internal error: could not cast array of type Int32 to arrow_array::array::primitive_array::PrimitiveArray<arrow_array::types::UInt64Type>"
185        );
186    }
187
188    // `err.to_string()` depends on backtrace being present (may have backtrace appended)
189    // `err.strip_backtrace()` also depends on backtrace being present (may have "This was likely caused by ..." stripped)
190    fn assert_starts_with(actual: impl AsRef<str>, expected_prefix: impl AsRef<str>) {
191        let actual = actual.as_ref();
192        let expected_prefix = expected_prefix.as_ref();
193        assert!(
194            actual.starts_with(expected_prefix),
195            "Expected '{actual}' to start with '{expected_prefix}'"
196        );
197    }
198}
datafusion_common/lib.rs

datafusion_common/
lib.rs
