neilconway commented on code in PR #21131:
URL: https://github.com/apache/datafusion/pull/21131#discussion_r2977623054


##########
datafusion/functions-nested/src/string.rs:
##########
@@ -530,271 +782,6 @@ where
     Ok(())
 }
 
-/// String_to_array SQL function
-/// Splits string at occurrences of delimiter and returns an array of parts
-/// string_to_array('abc~@~def~@~ghi', '~@~') = '["abc", "def", "ghi"]'
-fn string_to_array_inner<T: OffsetSizeTrait>(args: &[ArrayRef]) -> 
Result<ArrayRef> {
-    if args.len() < 2 || args.len() > 3 {
-        return exec_err!("string_to_array expects two or three arguments");
-    }
-
-    match args[0].data_type() {
-        Utf8 => {
-            let string_array = args[0].as_string::<T>();
-            let builder = StringBuilder::with_capacity(
-                string_array.len(),
-                string_array.get_buffer_memory_size(),
-            );
-            string_to_array_inner_2::<&GenericStringArray<T>, StringBuilder>(
-                args,
-                &string_array,
-                builder,
-            )
-        }
-        Utf8View => {
-            let string_array = args[0].as_string_view();
-            let builder = StringViewBuilder::with_capacity(string_array.len());
-            string_to_array_inner_2::<&StringViewArray, StringViewBuilder>(
-                args,
-                &string_array,
-                builder,
-            )
-        }
-        LargeUtf8 => {
-            let string_array = args[0].as_string::<T>();
-            let builder = LargeStringBuilder::with_capacity(
-                string_array.len(),
-                string_array.get_buffer_memory_size(),
-            );
-            string_to_array_inner_2::<&GenericStringArray<T>, 
LargeStringBuilder>(
-                args,
-                &string_array,
-                builder,
-            )
-        }
-        other => exec_err!(
-            "unsupported type for first argument to string_to_array function 
as {other:?}"
-        ),
-    }
-}
-
-fn string_to_array_inner_2<'a, StringArrType, StringBuilderType>(
-    args: &'a [ArrayRef],
-    string_array: &StringArrType,
-    string_builder: StringBuilderType,
-) -> Result<ArrayRef>
-where
-    StringArrType: StringArrayType<'a>,
-    StringBuilderType: StringArrayBuilderType,
-{
-    match args[1].data_type() {
-        Utf8 => {
-            let delimiter_array = args[1].as_string::<i32>();
-            if args.len() == 2 {
-                string_to_array_impl::<
-                    StringArrType,
-                    &GenericStringArray<i32>,
-                    &StringViewArray,
-                    StringBuilderType,
-                >(string_array, &delimiter_array, None, string_builder)
-            } else {
-                string_to_array_inner_3::<
-                    StringArrType,
-                    &GenericStringArray<i32>,
-                    StringBuilderType,
-                >(args, string_array, &delimiter_array, string_builder)
-            }
-        }
-        Utf8View => {
-            let delimiter_array = args[1].as_string_view();
-
-            if args.len() == 2 {
-                string_to_array_impl::<
-                    StringArrType,
-                    &StringViewArray,
-                    &StringViewArray,
-                    StringBuilderType,
-                >(string_array, &delimiter_array, None, string_builder)
-            } else {
-                string_to_array_inner_3::<
-                    StringArrType,
-                    &StringViewArray,
-                    StringBuilderType,
-                >(args, string_array, &delimiter_array, string_builder)
-            }
-        }
-        LargeUtf8 => {
-            let delimiter_array = args[1].as_string::<i64>();
-            if args.len() == 2 {
-                string_to_array_impl::<
-                    StringArrType,
-                    &GenericStringArray<i64>,
-                    &StringViewArray,
-                    StringBuilderType,
-                >(string_array, &delimiter_array, None, string_builder)
-            } else {
-                string_to_array_inner_3::<
-                    StringArrType,
-                    &GenericStringArray<i64>,
-                    StringBuilderType,
-                >(args, string_array, &delimiter_array, string_builder)
-            }
-        }
-        other => exec_err!(
-            "unsupported type for second argument to string_to_array function 
as {other:?}"
-        ),
-    }
-}
-
-fn string_to_array_inner_3<'a, StringArrType, DelimiterArrType, 
StringBuilderType>(
-    args: &'a [ArrayRef],
-    string_array: &StringArrType,
-    delimiter_array: &DelimiterArrType,
-    string_builder: StringBuilderType,
-) -> Result<ArrayRef>
-where
-    StringArrType: StringArrayType<'a>,
-    DelimiterArrType: StringArrayType<'a>,
-    StringBuilderType: StringArrayBuilderType,
-{
-    match args[2].data_type() {
-        Utf8 => {
-            let null_type_array = Some(args[2].as_string::<i32>());
-            string_to_array_impl::<
-                StringArrType,
-                DelimiterArrType,
-                &GenericStringArray<i32>,
-                StringBuilderType,
-            >(
-                string_array,
-                delimiter_array,
-                null_type_array,
-                string_builder,
-            )
-        }
-        Utf8View => {
-            let null_type_array = Some(args[2].as_string_view());
-            string_to_array_impl::<
-                StringArrType,
-                DelimiterArrType,
-                &StringViewArray,
-                StringBuilderType,
-            >(
-                string_array,
-                delimiter_array,
-                null_type_array,
-                string_builder,
-            )
-        }
-        LargeUtf8 => {
-            let null_type_array = Some(args[2].as_string::<i64>());
-            string_to_array_impl::<
-                StringArrType,
-                DelimiterArrType,
-                &GenericStringArray<i64>,
-                StringBuilderType,
-            >(
-                string_array,
-                delimiter_array,
-                null_type_array,
-                string_builder,
-            )
-        }
-        other => {
-            exec_err!("unsupported type for string_to_array function as 
{other:?}")
-        }
-    }
-}
-
-fn string_to_array_impl<
-    'a,
-    StringArrType,
-    DelimiterArrType,
-    NullValueArrType,
-    StringBuilderType,
->(
-    string_array: &StringArrType,
-    delimiter_array: &DelimiterArrType,
-    null_value_array: Option<NullValueArrType>,
-    string_builder: StringBuilderType,
-) -> Result<ArrayRef>
-where
-    StringArrType: StringArrayType<'a>,
-    DelimiterArrType: StringArrayType<'a>,
-    NullValueArrType: StringArrayType<'a>,
-    StringBuilderType: StringArrayBuilderType,
-{
-    let mut list_builder = ListBuilder::new(string_builder);
-
-    match null_value_array {
-        None => {
-            string_array.iter().zip(delimiter_array.iter()).for_each(
-                |(string, delimiter)| {
-                    match (string, delimiter) {
-                        (Some(string), Some("")) => {
-                            list_builder.values().append_value(string);
-                            list_builder.append(true);
-                        }
-                        (Some(string), Some(delimiter)) => {
-                            string.split(delimiter).for_each(|s| {
-                                list_builder.values().append_value(s);
-                            });
-                            list_builder.append(true);
-                        }
-                        (Some(string), None) => {
-                            string.chars().map(|c| c.to_string()).for_each(|c| 
{
-                                list_builder.values().append_value(c.as_str());
-                            });
-                            list_builder.append(true);
-                        }
-                        _ => list_builder.append(false), // null value
-                    }
-                },
-            )
-        }
-        Some(null_value_array) => string_array
-            .iter()
-            .zip(delimiter_array.iter())
-            .zip(null_value_array.iter())
-            .for_each(|((string, delimiter), null_value)| {
-                match (string, delimiter) {
-                    (Some(string), Some("")) => {
-                        if Some(string) == null_value {
-                            list_builder.values().append_null();
-                        } else {
-                            list_builder.values().append_value(string);
-                        }
-                        list_builder.append(true);
-                    }
-                    (Some(string), Some(delimiter)) => {
-                        string.split(delimiter).for_each(|s| {
-                            if Some(s) == null_value {
-                                list_builder.values().append_null();
-                            } else {
-                                list_builder.values().append_value(s);
-                            }
-                        });
-                        list_builder.append(true);
-                    }
-                    (Some(string), None) => {
-                        string.chars().map(|c| c.to_string()).for_each(|c| {

Review Comment:
   This was the inefficient `NULL` delimiter handling mentioned in the PR 
summary.



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to