Skip to main content

datafusion_functions_nested/
map_keys.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//! [`ScalarUDFImpl`] definitions for map_keys function.
19
20use crate::utils::{get_map_entry_field, make_scalar_function};
21use arrow::array::{Array, ArrayRef, ListArray};
22use arrow::datatypes::{DataType, Field};
23use datafusion_common::utils::take_function_args;
24use datafusion_common::{Result, cast::as_map_array, exec_err};
25use datafusion_expr::{
26    ArrayFunctionSignature, ColumnarValue, Documentation, ScalarFunctionArgs,
27    ScalarUDFImpl, Signature, TypeSignature, Volatility,
28};
29use datafusion_macros::user_doc;
30use std::sync::Arc;
31
32make_udf_expr_and_func!(
33    MapKeysFunc,
34    map_keys,
35    map,
36    "Return a list of all keys in the map.",
37    map_keys_udf
38);
39
40#[user_doc(
41    doc_section(label = "Map Functions"),
42    description = "Returns a list of all keys in the map.",
43    syntax_example = "map_keys(map)",
44    sql_example = r#"```sql
45SELECT map_keys(MAP {'a': 1, 'b': NULL, 'c': 3});
46----
47[a, b, c]
48
49SELECT map_keys(map([100, 5], [42, 43]));
50----
51[100, 5]
52```"#,
53    argument(
54        name = "map",
55        description = "Map expression. Can be a constant, column, or function, and any combination of map operators."
56    )
57)]
58#[derive(Debug, PartialEq, Eq, Hash)]
59pub struct MapKeysFunc {
60    signature: Signature,
61}
62
63impl Default for MapKeysFunc {
64    fn default() -> Self {
65        Self::new()
66    }
67}
68
69impl MapKeysFunc {
70    pub fn new() -> Self {
71        Self {
72            signature: Signature::new(
73                TypeSignature::ArraySignature(ArrayFunctionSignature::MapArray),
74                Volatility::Immutable,
75            ),
76        }
77    }
78}
79
80impl ScalarUDFImpl for MapKeysFunc {
81    fn name(&self) -> &str {
82        "map_keys"
83    }
84
85    fn signature(&self) -> &Signature {
86        &self.signature
87    }
88
89    fn return_type(&self, arg_types: &[DataType]) -> Result<DataType> {
90        let [map_type] = take_function_args(self.name(), arg_types)?;
91        let map_fields = get_map_entry_field(map_type)?;
92        // internal array nullability is true to be in sync with DuckDB
93        Ok(DataType::List(Arc::new(Field::new_list_field(
94            map_fields.first().unwrap().data_type().clone(),
95            true,
96        ))))
97    }
98
99    fn invoke_with_args(&self, args: ScalarFunctionArgs) -> Result<ColumnarValue> {
100        make_scalar_function(map_keys_inner)(&args.args)
101    }
102
103    fn documentation(&self) -> Option<&Documentation> {
104        self.doc()
105    }
106}
107
108fn map_keys_inner(args: &[ArrayRef]) -> Result<ArrayRef> {
109    let [map_arg] = take_function_args("map_keys", args)?;
110
111    let map_array = match map_arg.data_type() {
112        DataType::Map(_, _) => as_map_array(&map_arg)?,
113        _ => return exec_err!("Argument for map_keys should be a map"),
114    };
115
116    Ok(Arc::new(ListArray::new(
117        // internal array nullability is true to be in sync with DuckDB
118        Arc::new(Field::new_list_field(map_array.key_type().clone(), true)),
119        map_array.offsets().clone(),
120        Arc::clone(map_array.keys()),
121        map_array.nulls().cloned(),
122    )))
123}