1// Licensed to the Apache Software Foundation (ASF) under one
2// or more contributor license agreements. See the NOTICE file
3// distributed with this work for additional information
4// regarding copyright ownership. The ASF licenses this file
5// to you under the Apache License, Version 2.0 (the
6// "License"); you may not use this file except in compliance
7// with the License. You may obtain a copy of the License at
8//
9// http://www.apache.org/licenses/LICENSE-2.0
10//
11// Unless required by applicable law or agreed to in writing,
12// software distributed under the License is distributed on an
13// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
14// KIND, either express or implied. See the License for the
15// specific language governing permissions and limitations
16// under the License.
1718use crate::arrow::array_reader::{read_records, skip_records, ArrayReader};
19use crate::arrow::record_reader::RecordReader;
20use crate::column::page::PageIterator;
21use crate::data_type::DataType;
22use crate::errors::Result;
23use crate::schema::types::ColumnDescPtr;
24use arrow_array::ArrayRef;
25use arrow_buffer::ArrowNativeType;
26use arrow_schema::DataType as ArrowType;
27use std::any::Any;
28use std::sync::Arc;
2930/// A NullArrayReader reads Parquet columns stored as null int32s with an Arrow
31/// NullArray type.
32pub struct NullArrayReader<T>
33where
34T: DataType,
35 T::T: ArrowNativeType,
36{
37 data_type: ArrowType,
38 pages: Box<dyn PageIterator>,
39 def_levels_buffer: Option<Vec<i16>>,
40 rep_levels_buffer: Option<Vec<i16>>,
41 record_reader: RecordReader<T>,
42}
4344impl<T> NullArrayReader<T>
45where
46T: DataType,
47 T::T: ArrowNativeType,
48{
49/// Construct null array reader.
50pub fn new(pages: Box<dyn PageIterator>, column_desc: ColumnDescPtr) -> Result<Self> {
51let record_reader = RecordReader::<T>::new(column_desc);
5253Ok(Self {
54 data_type: ArrowType::Null,
55 pages,
56 def_levels_buffer: None,
57 rep_levels_buffer: None,
58 record_reader,
59 })
60 }
61}
6263/// Implementation of primitive array reader.
64impl<T> ArrayReader for NullArrayReader<T>
65where
66T: DataType,
67 T::T: ArrowNativeType,
68{
69fn as_any(&self) -> &dyn Any {
70self
71}
7273/// Returns data type of primitive array.
74fn get_data_type(&self) -> &ArrowType {
75&self.data_type
76 }
7778fn read_records(&mut self, batch_size: usize) -> Result<usize> {
79 read_records(&mut self.record_reader, self.pages.as_mut(), batch_size)
80 }
8182fn consume_batch(&mut self) -> Result<ArrayRef> {
83// convert to arrays
84let array = arrow_array::NullArray::new(self.record_reader.num_values());
8586// save definition and repetition buffers
87self.def_levels_buffer = self.record_reader.consume_def_levels();
88self.rep_levels_buffer = self.record_reader.consume_rep_levels();
8990// Must consume bitmap buffer
91self.record_reader.consume_bitmap_buffer();
9293self.record_reader.reset();
94Ok(Arc::new(array))
95 }
9697fn skip_records(&mut self, num_records: usize) -> Result<usize> {
98 skip_records(&mut self.record_reader, self.pages.as_mut(), num_records)
99 }
100101fn get_def_levels(&self) -> Option<&[i16]> {
102self.def_levels_buffer.as_deref()
103 }
104105fn get_rep_levels(&self) -> Option<&[i16]> {
106self.rep_levels_buffer.as_deref()
107 }
108}