Ted-Jiang commented on code in PR #3780:
URL: https://github.com/apache/arrow-datafusion/pull/3780#discussion_r995599914
##########
datafusion/core/src/physical_plan/file_format/parquet.rs:
##########
@@ -749,6 +811,61 @@ macro_rules! get_null_count_values {
}};
}
+// Extract the min or max value calling `func` from page idex
+macro_rules! get_min_max_values_form_page_index {
+ ($self:expr, $column:expr, $func:ident) => {{
+ if let Some((col_id_index, _field)) =
+ $self.parquet_schema.column_with_name(&$column.name)
+ {
+ if let Some(page_index) = $self.page_indexes.get(col_id_index) {
+ match page_index {
+ Index::NONE => None,
+ Index::INT32(index) => {
+ let vec = &index.indexes;
+ Some(Arc::new(Int32Array::from_iter(
+ vec.iter().map(|x| x.$func().cloned()),
+ )))
+ }
+ Index::INT64(index) => {
+ let vec = &index.indexes;
+ Some(Arc::new(Int64Array::from_iter(
+ vec.iter().map(|x| x.$func().cloned()),
+ )))
+ }
+ Index::FLOAT(index) => {
+ let vec = &index.indexes;
+ Some(Arc::new(Float32Array::from_iter(
+ vec.iter().map(|x| x.$func().cloned()),
+ )))
+ }
+ Index::DOUBLE(index) => {
+ let vec = &index.indexes;
+ Some(Arc::new(Float64Array::from_iter(
+ vec.iter().map(|x| x.$func().cloned()),
+ )))
+ }
+ Index::BOOLEAN(index) => {
+ let vec = &index.indexes;
+ Some(Arc::new(BooleanArray::from_iter(
+ vec.iter().map(|x| x.$func().cloned()),
+ )))
+ }
+ Index::INT96(_)
+ | Index::BYTE_ARRAY(_)
+ | Index::FIXED_LEN_BYTE_ARRAY(_) => {
+ //Todo support these type
Review Comment:
file
##########
datafusion/core/src/physical_plan/file_format/parquet.rs:
##########
@@ -749,6 +811,61 @@ macro_rules! get_null_count_values {
}};
}
+// Extract the min or max value calling `func` from page idex
+macro_rules! get_min_max_values_form_page_index {
+ ($self:expr, $column:expr, $func:ident) => {{
+ if let Some((col_id_index, _field)) =
+ $self.parquet_schema.column_with_name(&$column.name)
+ {
+ if let Some(page_index) = $self.page_indexes.get(col_id_index) {
+ match page_index {
+ Index::NONE => None,
+ Index::INT32(index) => {
+ let vec = &index.indexes;
+ Some(Arc::new(Int32Array::from_iter(
+ vec.iter().map(|x| x.$func().cloned()),
+ )))
+ }
+ Index::INT64(index) => {
+ let vec = &index.indexes;
+ Some(Arc::new(Int64Array::from_iter(
+ vec.iter().map(|x| x.$func().cloned()),
+ )))
+ }
+ Index::FLOAT(index) => {
+ let vec = &index.indexes;
+ Some(Arc::new(Float32Array::from_iter(
+ vec.iter().map(|x| x.$func().cloned()),
+ )))
+ }
+ Index::DOUBLE(index) => {
+ let vec = &index.indexes;
+ Some(Arc::new(Float64Array::from_iter(
+ vec.iter().map(|x| x.$func().cloned()),
+ )))
+ }
+ Index::BOOLEAN(index) => {
+ let vec = &index.indexes;
+ Some(Arc::new(BooleanArray::from_iter(
+ vec.iter().map(|x| x.$func().cloned()),
+ )))
+ }
+ Index::INT96(_)
+ | Index::BYTE_ARRAY(_)
+ | Index::FIXED_LEN_BYTE_ARRAY(_) => {
+ //Todo support these type
Review Comment:
file https://github.com/apache/arrow-datafusion/issues/3833#issue-1409121339
--
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]