Skip to main content

datafusion_functions/datetime/
to_unixtime.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
18use super::to_timestamp::ToTimestampSecondsFunc;
19use crate::datetime::common::*;
20use arrow::datatypes::{DataType, TimeUnit};
21use datafusion_common::{Result, exec_err};
22use datafusion_expr::{
23    ColumnarValue, Documentation, ScalarFunctionArgs, ScalarUDFImpl, Signature,
24    Volatility,
25};
26use datafusion_macros::user_doc;
27
28#[user_doc(
29    doc_section(label = "Time and Date Functions"),
30    description = r#"
31Converts a value to seconds since the unix epoch (`1970-01-01T00:00:00`).
32Supports strings, dates, timestamps, integer, unsigned integer, and float types as input.
33Strings are parsed as RFC3339 (e.g. '2023-07-20T05:44:00')
34if no [Chrono formats](https://docs.rs/chrono/latest/chrono/format/strftime/index.html) are provided.
35Integers, unsigned integers, and floats are interpreted as seconds since the unix epoch (`1970-01-01T00:00:00`)."#,
36    syntax_example = "to_unixtime(expression[, ..., format_n])",
37    sql_example = r#"
38```sql
39> select to_unixtime('2020-09-08T12:00:00+00:00');
40+------------------------------------------------+
41| to_unixtime(Utf8("2020-09-08T12:00:00+00:00")) |
42+------------------------------------------------+
43| 1599566400                                     |
44+------------------------------------------------+
45> select to_unixtime('01-14-2023 01:01:30+05:30', '%q', '%d-%m-%Y %H/%M/%S', '%+', '%m-%d-%Y %H:%M:%S%#z');
46+-----------------------------------------------------------------------------------------------------------------------------+
47| to_unixtime(Utf8("01-14-2023 01:01:30+05:30"),Utf8("%q"),Utf8("%d-%m-%Y %H/%M/%S"),Utf8("%+"),Utf8("%m-%d-%Y %H:%M:%S%#z")) |
48+-----------------------------------------------------------------------------------------------------------------------------+
49| 1673638290                                                                                                                  |
50+-----------------------------------------------------------------------------------------------------------------------------+
51```
52"#,
53    argument(
54        name = "expression",
55        description = "Expression to operate on. Can be a constant, column, or function, and any combination of arithmetic operators."
56    ),
57    argument(
58        name = "format_n",
59        description = "Optional [Chrono format](https://docs.rs/chrono/latest/chrono/format/strftime/index.html) strings to use to parse the expression. Formats will be tried in the order they appear with the first successful one being returned. If none of the formats successfully parse the expression an error will be returned."
60    )
61)]
62#[derive(Debug, PartialEq, Eq, Hash)]
63pub struct ToUnixtimeFunc {
64    signature: Signature,
65}
66
67impl Default for ToUnixtimeFunc {
68    fn default() -> Self {
69        Self::new()
70    }
71}
72
73impl ToUnixtimeFunc {
74    pub fn new() -> Self {
75        Self {
76            signature: Signature::variadic_any(Volatility::Immutable),
77        }
78    }
79}
80
81impl ScalarUDFImpl for ToUnixtimeFunc {
82    fn name(&self) -> &str {
83        "to_unixtime"
84    }
85
86    fn signature(&self) -> &Signature {
87        &self.signature
88    }
89
90    fn return_type(&self, _arg_types: &[DataType]) -> Result<DataType> {
91        Ok(DataType::Int64)
92    }
93
94    fn invoke_with_args(&self, args: ScalarFunctionArgs) -> Result<ColumnarValue> {
95        let arg_args = &args.args;
96        if arg_args.is_empty() {
97            return exec_err!("to_unixtime function requires 1 or more arguments, got 0");
98        }
99
100        // validate that any args after the first one are Utf8
101        if arg_args.len() > 1 {
102            // Format arguments only make sense for string inputs
103            match arg_args[0].data_type() {
104                DataType::Utf8View | DataType::LargeUtf8 | DataType::Utf8 => {
105                    validate_data_types(arg_args, "to_unixtime")?;
106                }
107                _ => {
108                    return exec_err!(
109                        "to_unixtime function only accepts format arguments with string input, got {} arguments",
110                        arg_args.len()
111                    );
112                }
113            }
114        }
115
116        match arg_args[0].data_type() {
117            DataType::Int8
118            | DataType::Int16
119            | DataType::Int32
120            | DataType::Int64
121            | DataType::UInt8
122            | DataType::UInt16
123            | DataType::UInt32
124            | DataType::UInt64
125            | DataType::Float16
126            | DataType::Float32
127            | DataType::Float64
128            | DataType::Null => arg_args[0].cast_to(&DataType::Int64, None),
129            DataType::Date64 | DataType::Date32 => arg_args[0]
130                .cast_to(&DataType::Timestamp(TimeUnit::Second, None), None)?
131                .cast_to(&DataType::Int64, None),
132            DataType::Timestamp(_, tz) => arg_args[0]
133                .cast_to(&DataType::Timestamp(TimeUnit::Second, tz), None)?
134                .cast_to(&DataType::Int64, None),
135            DataType::Utf8View | DataType::LargeUtf8 | DataType::Utf8 => {
136                ToTimestampSecondsFunc::new_with_config(args.config_options.as_ref())
137                    .invoke_with_args(args)?
138                    .cast_to(&DataType::Int64, None)
139            }
140            other => {
141                exec_err!("Unsupported data type {} for function to_unixtime", other)
142            }
143        }
144    }
145
146    fn documentation(&self) -> Option<&Documentation> {
147        self.doc()
148    }
149}