(datafusion) branch main updated: Improve `ScalarUDFImpl` docs (#14248)

[al...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

alamb pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/datafusion.git


The following commit(s) were added to refs/heads/main by this push:
     new 27db82fe39 Improve `ScalarUDFImpl` docs (#14248)
27db82fe39 is described below

commit 27db82fe396f43077b5056bab4b20b084c8f6948
Author: Andrew Lamb <an...@nerdnetworks.org>
AuthorDate: Thu Jan 23 10:45:29 2025 -0500

    Improve `ScalarUDFImpl` docs (#14248)
    
    * Improve `ScalarUDFImpl` docs
    
    * fix clippy
---
 datafusion/expr/src/udf.rs | 39 ++++++++++++++++++++++++++-------------
 1 file changed, 26 insertions(+), 13 deletions(-)

diff --git a/datafusion/expr/src/udf.rs b/datafusion/expr/src/udf.rs
index bb5a405a93..aa6a5cddad 100644
--- a/datafusion/expr/src/udf.rs
+++ b/datafusion/expr/src/udf.rs
@@ -193,6 +193,9 @@ impl ScalarUDF {
         self.inner.return_type_from_exprs(args, schema, arg_types)
     }
 
+    /// Return the datatype this function returns given the input argument types.
+    ///
+    /// See [`ScalarUDFImpl::return_type_from_args`] for more details.
     pub fn return_type_from_args(&self, args: ReturnTypeArgs) -> Result<ReturnInfo> {
         self.inner.return_type_from_args(args)
     }
@@ -433,7 +436,6 @@ impl ReturnInfo {
 /// # use datafusion_expr::{col, ColumnarValue, Documentation, ScalarFunctionArgs, Signature, Volatility};
 /// # use datafusion_expr::{ScalarUDFImpl, ScalarUDF};
 /// # use datafusion_expr::scalar_doc_sections::DOC_SECTION_MATH;
-///
 /// /// This struct for a simple UDF that adds one to an int32
 /// #[derive(Debug)]
 /// struct AddOne {
@@ -494,7 +496,12 @@ pub trait ScalarUDFImpl: Debug + Send + Sync {
     /// Returns this function's name
     fn name(&self) -> &str;
 
-    /// Returns the user-defined display name of the UDF given the arguments
+    /// Returns the user-defined display name of function, given the arguments
+    ///
+    /// This can be used to customize the output column name generated by this
+    /// function.
+    ///
+    /// Defaults to `name(args[0], args[1], ...)`
     fn display_name(&self, args: &[Expr]) -> Result<String> {
         let names: Vec<String> = args.iter().map(ToString::to_string).collect();
         // TODO: join with ", " to standardize the formatting of Vec<Expr>, <https://github.com/apache/datafusion/issues/10364>
@@ -522,7 +529,7 @@ pub trait ScalarUDFImpl: Debug + Send + Sync {
     /// # Notes
     ///
     /// If you provide an implementation for [`Self::return_type_from_args`],
-    /// DataFusion will not call `return_type` (this function). In this case it
+    /// DataFusion will not call `return_type` (this function). In such cases
     /// is recommended to return [`DataFusionError::Internal`].
     ///
     /// [`DataFusionError::Internal`]: datafusion_common::DataFusionError::Internal
@@ -538,18 +545,24 @@ pub trait ScalarUDFImpl: Debug + Send + Sync {
         self.return_type(arg_types)
     }
 
-    /// What [`DataType`] will be returned by this function, given the
-    /// arguments?
-    ///
-    /// Note most UDFs should implement [`Self::return_type`] and not this
-    /// function. The output type for most functions only depends on the types
-    /// of their inputs (e.g. `sqrt(f32)` is always `f32`).
+    /// What type will be returned by this function, given the arguments?
     ///
     /// By default, this function calls [`Self::return_type`] with the
     /// types of each argument.
     ///
-    /// This method can be overridden for functions that return different
-    /// *types* based on the *values* of their arguments.
+    /// # Notes
+    ///
+    /// Most UDFs should implement [`Self::return_type`] and not this
+    /// function as the output type for most functions only depends on the types
+    /// of their inputs (e.g. `sqrt(f32)` is always `f32`).
+    ///
+    /// This function can be used for more advanced cases such as:
+    ///
+    /// 1. specifying nullability
+    /// 2. return types based on the **values** of the arguments (rather than
+    ///    their **types**.
+    ///
+    /// # Output Type based on Values
     ///
     /// For example, the following two function calls get the same argument
     /// types (something and a `Utf8` string) but return different types based
@@ -558,9 +571,9 @@ pub trait ScalarUDFImpl: Debug + Send + Sync {
     /// * `arrow_cast(x, 'Int16')` --> `Int16`
     /// * `arrow_cast(x, 'Float32')` --> `Float32`
     ///
-    /// # Notes:
+    /// # Requirements
     ///
-    /// This function must consistently return the same type for the same
+    /// This function **must** consistently return the same type for the same
     /// logical input even if the input is simplified (e.g. it must return the same
     /// value for `('foo' | 'bar')` as it does for ('foobar').
     fn return_type_from_args(&self, args: ReturnTypeArgs) -> Result<ReturnInfo> {


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@datafusion.apache.org
For additional commands, e-mail: commits-help@datafusion.apache.org