[Parquet] perf: Create StructArrays directly rather than use ArrayData

Author: alamb

parquet/src/arrow/array_reader/struct_array.rs

@@ -18,10 +18,10 @@
 use crate::arrow::array_reader::ArrayReader;
 use crate::errors::{ParquetError, Result};
 use arrow_array::{Array, ArrayRef, StructArray, builder::BooleanBufferBuilder};
-use arrow_data::{ArrayData, ArrayDataBuilder};
-use arrow_schema::DataType as ArrowType;
+use arrow_schema::{DataType as ArrowType, DataType};
 use std::any::Any;
 use std::sync::Arc;
+use arrow_buffer::NullBuffer;
 
 /// Implementation of struct array reader.
 pub struct StructArrayReader {
@@ -124,16 +124,13 @@ impl ArrayReader for StructArrayReader {
             return Err(general_err!("Not all children array length are the same!"));
         }
 
-        // Now we can build array data
-        let mut array_data_builder = ArrayDataBuilder::new(self.data_type.clone())
-            .len(children_array_len)
-            .child_data(
-                children_array
-                    .into_iter()
-                    .map(|x| x.into_data())
-                    .collect::<Vec<ArrayData>>(),
-            );
+        // Now we can build the struct array
 
+        let DataType::Struct(fields) = &self.data_type else {
+            return Err(general_err!("Internal error: StructArrayReader must have struct data type"));
+        };
+
+        let mut nulls = None;
         if self.nullable {
             // calculate struct def level data
 
@@ -169,11 +166,18 @@ impl ArrayReader for StructArrayReader {
                 return Err(general_err!("Failed to decode level data for struct array"));
             }
 
-            array_data_builder = array_data_builder.null_bit_buffer(Some(bitmap_builder.into()));
+            nulls = Some(NullBuffer::new(bitmap_builder.finish()));
+        }
+        // Safety: all children array data have same length and correct type
+        unsafe {
+            Ok(Arc::new(StructArray::new_unchecked_with_length(
+                fields.clone(), // cloning Fields is cheap (an Arc internally)
+                children_array,
+                nulls,
+                children_array_len
+            )))
         }
 
-        let array_data = unsafe { array_data_builder.build_unchecked() };
-        Ok(Arc::new(StructArray::from(array_data)))
     }
 
     fn skip_records(&mut self, num_records: usize) -> Result<usize> {