datafusion_functions/string/
repeat.rsuse std::any::Any;
use std::sync::Arc;
use crate::utils::{make_scalar_function, utf8_to_str_type};
use arrow::array::{
ArrayRef, AsArray, GenericStringArray, GenericStringBuilder, Int64Array,
OffsetSizeTrait, StringArrayType, StringViewArray,
};
use arrow::datatypes::DataType;
use arrow::datatypes::DataType::{LargeUtf8, Utf8, Utf8View};
use datafusion_common::cast::as_int64_array;
use datafusion_common::types::{logical_int64, logical_string};
use datafusion_common::{exec_err, Result};
use datafusion_expr::{ColumnarValue, Documentation, Volatility};
use datafusion_expr::{ScalarUDFImpl, Signature};
use datafusion_expr_common::signature::TypeSignatureClass;
use datafusion_macros::user_doc;
#[user_doc(
doc_section(label = "String Functions"),
description = "Returns a string with an input string repeated a specified number.",
syntax_example = "repeat(str, n)",
sql_example = r#"```sql
> select repeat('data', 3);
+-------------------------------+
| repeat(Utf8("data"),Int64(3)) |
+-------------------------------+
| datadatadata |
+-------------------------------+
```"#,
standard_argument(name = "str", prefix = "String"),
argument(
name = "n",
description = "Number of times to repeat the input string."
)
)]
#[derive(Debug)]
pub struct RepeatFunc {
signature: Signature,
}
impl Default for RepeatFunc {
fn default() -> Self {
Self::new()
}
}
impl RepeatFunc {
pub fn new() -> Self {
Self {
signature: Signature::coercible(
vec![
TypeSignatureClass::Native(logical_string()),
TypeSignatureClass::Native(logical_int64()),
],
Volatility::Immutable,
),
}
}
}
impl ScalarUDFImpl for RepeatFunc {
fn as_any(&self) -> &dyn Any {
self
}
fn name(&self) -> &str {
"repeat"
}
fn signature(&self) -> &Signature {
&self.signature
}
fn return_type(&self, arg_types: &[DataType]) -> Result<DataType> {
utf8_to_str_type(&arg_types[0], "repeat")
}
fn invoke_batch(
&self,
args: &[ColumnarValue],
_number_rows: usize,
) -> Result<ColumnarValue> {
make_scalar_function(repeat, vec![])(args)
}
fn documentation(&self) -> Option<&Documentation> {
self.doc()
}
}
fn repeat(args: &[ArrayRef]) -> Result<ArrayRef> {
let number_array = as_int64_array(&args[1])?;
match args[0].data_type() {
Utf8View => {
let string_view_array = args[0].as_string_view();
repeat_impl::<i32, &StringViewArray>(string_view_array, number_array)
}
Utf8 => {
let string_array = args[0].as_string::<i32>();
repeat_impl::<i32, &GenericStringArray<i32>>(string_array, number_array)
}
LargeUtf8 => {
let string_array = args[0].as_string::<i64>();
repeat_impl::<i64, &GenericStringArray<i64>>(string_array, number_array)
}
other => exec_err!(
"Unsupported data type {other:?} for function repeat. \
Expected Utf8, Utf8View or LargeUtf8."
),
}
}
fn repeat_impl<'a, T, S>(string_array: S, number_array: &Int64Array) -> Result<ArrayRef>
where
T: OffsetSizeTrait,
S: StringArrayType<'a>,
{
let mut builder: GenericStringBuilder<T> = GenericStringBuilder::new();
string_array
.iter()
.zip(number_array.iter())
.for_each(|(string, number)| match (string, number) {
(Some(string), Some(number)) if number >= 0 => {
builder.append_value(string.repeat(number as usize))
}
(Some(_), Some(_)) => builder.append_value(""),
_ => builder.append_null(),
});
let array = builder.finish();
Ok(Arc::new(array) as ArrayRef)
}
#[cfg(test)]
mod tests {
use arrow::array::{Array, StringArray};
use arrow::datatypes::DataType::Utf8;
use datafusion_common::Result;
use datafusion_common::ScalarValue;
use datafusion_expr::{ColumnarValue, ScalarUDFImpl};
use crate::string::repeat::RepeatFunc;
use crate::utils::test::test_function;
#[test]
fn test_functions() -> Result<()> {
test_function!(
RepeatFunc::new(),
vec![
ColumnarValue::Scalar(ScalarValue::Utf8(Some(String::from("Pg")))),
ColumnarValue::Scalar(ScalarValue::Int64(Some(4))),
],
Ok(Some("PgPgPgPg")),
&str,
Utf8,
StringArray
);
test_function!(
RepeatFunc::new(),
vec![
ColumnarValue::Scalar(ScalarValue::Utf8(None)),
ColumnarValue::Scalar(ScalarValue::Int64(Some(4))),
],
Ok(None),
&str,
Utf8,
StringArray
);
test_function!(
RepeatFunc::new(),
vec![
ColumnarValue::Scalar(ScalarValue::Utf8(Some(String::from("Pg")))),
ColumnarValue::Scalar(ScalarValue::Int64(None)),
],
Ok(None),
&str,
Utf8,
StringArray
);
test_function!(
RepeatFunc::new(),
vec![
ColumnarValue::Scalar(ScalarValue::Utf8View(Some(String::from("Pg")))),
ColumnarValue::Scalar(ScalarValue::Int64(Some(4))),
],
Ok(Some("PgPgPgPg")),
&str,
Utf8,
StringArray
);
test_function!(
RepeatFunc::new(),
vec![
ColumnarValue::Scalar(ScalarValue::Utf8View(None)),
ColumnarValue::Scalar(ScalarValue::Int64(Some(4))),
],
Ok(None),
&str,
Utf8,
StringArray
);
test_function!(
RepeatFunc::new(),
vec![
ColumnarValue::Scalar(ScalarValue::Utf8View(Some(String::from("Pg")))),
ColumnarValue::Scalar(ScalarValue::Int64(None)),
],
Ok(None),
&str,
Utf8,
StringArray
);
Ok(())
}
}