tustvold commented on a change in pull request #1180: URL: https://github.com/apache/arrow-rs/pull/1180#discussion_r787045887
########## File path: parquet/src/arrow/array_reader/byte_array_dictionary.rs ########## @@ -0,0 +1,515 @@ +// Licensed to the Apache Software Foundation (ASF) under one +// or more contributor license agreements. See the NOTICE file +// distributed with this work for additional information +// regarding copyright ownership. The ASF licenses this file +// to you under the Apache License, Version 2.0 (the +// "License"); you may not use this file except in compliance +// with the License. You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, +// software distributed under the License is distributed on an +// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +// KIND, either express or implied. See the License for the +// specific language governing permissions and limitations +// under the License. + +use std::any::Any; +use std::marker::PhantomData; +use std::ops::Range; +use std::sync::Arc; + +use arrow::array::{ArrayData, ArrayDataBuilder, ArrayRef, OffsetSizeTrait}; +use arrow::buffer::Buffer; +use arrow::datatypes::{ArrowNativeType, DataType as ArrowType}; + +use crate::arrow::array_reader::dictionary_buffer::DictionaryBuffer; +use crate::arrow::array_reader::{ + byte_array::{ByteArrayDecoder, ByteArrayDecoderPlain}, + offset_buffer::OffsetBuffer, +}; +use crate::arrow::array_reader::{read_records, ArrayReader}; +use crate::arrow::record_reader::buffer::{BufferQueue, ScalarValue}; +use crate::arrow::record_reader::GenericRecordReader; +use crate::arrow::schema::parquet_to_arrow_field; +use crate::basic::{ConvertedType, Encoding}; +use crate::column::page::PageIterator; +use crate::column::reader::decoder::ColumnValueDecoder; +use crate::encodings::rle::RleDecoder; +use crate::errors::{ParquetError, Result}; +use crate::schema::types::ColumnDescPtr; +use crate::util::bit_util::FromBytes; +use crate::util::memory::ByteBufferPtr; + +/// A macro to reduce verbosity of [`make_byte_array_dictionary_reader`] +macro_rules! make_reader { + ( + ($pages:expr, $column_desc:expr, $data_type:expr, $null_mask_only:expr) => match ($k:expr, $v:expr) { + $(($key_arrow:pat, $value_arrow:pat) => ($key_type:ty, $value_type:ty),)+ + } + ) => { + match (($k, $v)) { + $( + ($key_arrow, $value_arrow) => { + let reader = GenericRecordReader::new_with_options( + $column_desc, + $null_mask_only, + ); + Ok(Box::new(ByteArrayDictionaryReader::<$key_type, $value_type>::new( + $pages, $data_type, reader, + ))) + } + )+ + _ => Err(general_err!( + "unsupported data type for byte array dictionary reader - {}", + $data_type + )), + } + } +} + +/// Returns an [`ArrayReader`] that decodes the provided byte array column +/// +/// This will attempt to preserve any dictionary encoding present in the parquet data +/// +/// It will be unable to preserve the dictionary encoding if: +/// +/// * A single read spans across multiple column chunks +/// * A column chunk contains non-dictionary encoded pages +/// +/// It is therefore recommended that if `pages` contains data from multiple column chunks, +/// that the batch size used is a divisor of the row group size +/// +pub fn make_byte_array_dictionary_reader( + pages: Box<dyn PageIterator>, + column_desc: ColumnDescPtr, + arrow_type: Option<ArrowType>, + null_mask_only: bool, +) -> Result<Box<dyn ArrayReader>> { + // Check if Arrow type is specified, else create it from Parquet type + let data_type = match arrow_type { + Some(t) => t, + None => parquet_to_arrow_field(column_desc.as_ref())? + .data_type() + .clone(), + }; + + match &data_type { + ArrowType::Dictionary(key_type, value_type) => { + make_reader! { + (pages, column_desc, data_type, null_mask_only) => match (key_type.as_ref(), value_type.as_ref()) { + (ArrowType::UInt8, ArrowType::Binary | ArrowType::Utf8) => (u8, i32), Review comment: Many of these aren't properly supported by the arrow compute kernels, but I figured better to be thorough -- 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: github-unsubscr...@arrow.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
