make array_union/array_except/array_intersect handle empty/null arrays rightly
#8269
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -228,10 +228,10 @@ fn compute_array_dims(arr: Option<ArrayRef>) -> Result<Option<Vec<Option<u64>>>> | |
|
|
||
| fn check_datatypes(name: &str, args: &[&ArrayRef]) -> Result<()> { | ||
| let data_type = args[0].data_type(); | ||
| if !args.iter().all(|arg| { | ||
| arg.data_type().equals_datatype(data_type) | ||
| || arg.data_type().equals_datatype(&DataType::Null) | ||
|
There was a problem hiding this comment. @Veeupup Why do we need Null checking here, which function failed without this? There was a problem hiding this comment. when it comes to handle multi arrays functions,their input types maybe like |
||
| }) { | ||
| let types = args.iter().map(|arg| arg.data_type()).collect::<Vec<_>>(); | ||
| return plan_err!("{name} received incompatible types: '{types:?}'."); | ||
| } | ||
|
|
@@ -1512,19 +1512,29 @@ pub fn array_union(args: &[ArrayRef]) -> Result<ArrayRef> { | |
| match (array1.data_type(), array2.data_type()) { | ||
| (DataType::Null, _) => Ok(array2.clone()), | ||
| (_, DataType::Null) => Ok(array1.clone()), | ||
| (DataType::List(l_field_ref), DataType::List(r_field_ref)) => { | ||
| match (l_field_ref.data_type(), r_field_ref.data_type()) { | ||
| (DataType::Null, _) => Ok(array2.clone()), | ||
| (_, DataType::Null) => Ok(array1.clone()), | ||
| (_, _) => { | ||
| let list1 = array1.as_list::<i32>(); | ||
| let list2 = array2.as_list::<i32>(); | ||
| let result = union_generic_lists::<i32>(list1, list2, l_field_ref)?; | ||
| Ok(Arc::new(result)) | ||
| } | ||
| } | ||
| } | ||
| (DataType::LargeList(l_field_ref), DataType::LargeList(r_field_ref)) => { | ||
| match (l_field_ref.data_type(), r_field_ref.data_type()) { | ||
| (DataType::Null, _) => Ok(array2.clone()), | ||
| (_, DataType::Null) => Ok(array1.clone()), | ||
| (_, _) => { | ||
| let list1 = array1.as_list::<i64>(); | ||
| let list2 = array2.as_list::<i64>(); | ||
| let result = union_generic_lists::<i64>(list1, list2, l_field_ref)?; | ||
| Ok(Arc::new(result)) | ||
| } | ||
| } | ||
| } | ||
| _ => { | ||
| internal_err!( | ||
|
|
@@ -1998,55 +2008,66 @@ pub fn string_to_array<T: OffsetSizeTrait>(args: &[ArrayRef]) -> Result<ArrayRef | |
| pub fn array_intersect(args: &[ArrayRef]) -> Result<ArrayRef> { | ||
| assert_eq!(args.len(), 2); | ||
|
|
||
| let first_array = &args[0]; | ||
| let second_array = &args[1]; | ||
|
|
||
| match (first_array.data_type(), second_array.data_type()) { | ||
| (DataType::Null, _) => Ok(second_array.clone()), | ||
| (_, DataType::Null) => Ok(first_array.clone()), | ||
| _ => { | ||
| let first_array = as_list_array(&first_array)?; | ||
| let second_array = as_list_array(&second_array)?; | ||
|
|
||
| if first_array.value_type() != second_array.value_type() { | ||
| return internal_err!("array_intersect is not implemented for '{first_array:?}' and '{second_array:?}'"); | ||
| } | ||
|
|
||
| let dt = first_array.value_type(); | ||
|
|
||
| let mut offsets = vec![0]; | ||
| let mut new_arrays = vec![]; | ||
|
|
||
| let converter = RowConverter::new(vec![SortField::new(dt.clone())])?; | ||
| for (first_arr, second_arr) in first_array.iter().zip(second_array.iter()) { | ||
| if let (Some(first_arr), Some(second_arr)) = (first_arr, second_arr) { | ||
| let l_values = converter.convert_columns(&[first_arr])?; | ||
| let r_values = converter.convert_columns(&[second_arr])?; | ||
|
|
||
| let values_set: HashSet<_> = l_values.iter().collect(); | ||
| let mut rows = Vec::with_capacity(r_values.num_rows()); | ||
| for r_val in r_values.iter().sorted().dedup() { | ||
| if values_set.contains(&r_val) { | ||
| rows.push(r_val); | ||
| } | ||
| } | ||
|
|
||
| let last_offset: i32 = match offsets.last().copied() { | ||
| Some(offset) => offset, | ||
| None => return internal_err!("offsets should not be empty"), | ||
| }; | ||
| offsets.push(last_offset + rows.len() as i32); | ||
| let arrays = converter.convert_rows(rows)?; | ||
| let array = match arrays.get(0) { | ||
| Some(array) => array.clone(), | ||
| None => { | ||
| return internal_err!( | ||
| "array_intersect: failed to get array from rows" | ||
| ) | ||
| } | ||
| }; | ||
| new_arrays.push(array); | ||
| } | ||
| } | ||
|
|
||
| let field = Arc::new(Field::new("item", dt, true)); | ||
| let offsets = OffsetBuffer::new(offsets.into()); | ||
| let new_arrays_ref = | ||
| new_arrays.iter().map(|v| v.as_ref()).collect::<Vec<_>>(); | ||
| let values = compute::concat(&new_arrays_ref)?; | ||
| let arr = Arc::new(ListArray::try_new(field, offsets, values, None)?); | ||
| Ok(arr) | ||
| } | ||
| } | ||
| } | ||
|
|
||
| #[cfg(test)] | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
yes!