Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion arrow-avro/Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,7 @@ small_decimals = []
avro_custom_types = ["dep:arrow-select"]

# Enable async APIs
async = ["futures", "tokio"]
async = ["futures", "tokio", "tokio-util", "async-stream"]
# Enable object_store integration
object_store = ["dep:object_store", "async"]

Expand Down Expand Up @@ -77,6 +77,8 @@ rand = "0.9"
md5 = { version = "0.8", optional = true }
sha2 = { version = "0.11", optional = true }
tokio = { version = "1.0", optional = true, default-features = false, features = ["macros", "rt", "io-util"] }
tokio-util = { version = "0.7.18", default-features = false, features = ["io"], optional = true }
async-stream = { version = "0.3.6", optional = true }

Comment thread
ariel-miculas marked this conversation as resolved.
[dev-dependencies]
arrow-data = { workspace = true }
Expand Down
34 changes: 33 additions & 1 deletion arrow-avro/src/reader/async_reader/async_file_reader.rs
Original file line number Diff line number Diff line change
Expand Up @@ -17,11 +17,13 @@

use crate::errors::AvroError;
use bytes::Bytes;
use futures::FutureExt;
use futures::future::BoxFuture;
use futures::stream::BoxStream;
use futures::{FutureExt, StreamExt, TryStreamExt};
use std::io::SeekFrom;
use std::ops::Range;
use tokio::io::{AsyncRead, AsyncReadExt, AsyncSeek, AsyncSeekExt};
use tokio_util::io::ReaderStream;

/// The asynchronous interface used by [`super::AsyncAvroFileReader`] to read avro files
///
Expand All @@ -40,6 +42,12 @@ pub trait AsyncFileReader: Send {
/// Retrieve the bytes in `range`
fn get_bytes(&mut self, range: Range<u64>) -> BoxFuture<'_, Result<Bytes, AvroError>>;

/// Retrieve a range of bytes as a stream
fn get_stream(
&mut self,
range: Range<u64>,
) -> BoxFuture<'_, Result<BoxStream<'_, Result<Bytes, AvroError>>, AvroError>>;

/// Retrieve multiple byte ranges. The default implementation will call `get_bytes` sequentially
fn get_byte_ranges(
&mut self,
Expand All @@ -61,6 +69,13 @@ pub trait AsyncFileReader: Send {

/// This allows Box<dyn AsyncFileReader + '_> to be used as an AsyncFileReader,
impl AsyncFileReader for Box<dyn AsyncFileReader + '_> {
fn get_stream(
&mut self,
range: Range<u64>,
) -> BoxFuture<'_, Result<BoxStream<'_, Result<Bytes, AvroError>>, AvroError>> {
self.as_mut().get_stream(range)
}

fn get_bytes(&mut self, range: Range<u64>) -> BoxFuture<'_, Result<Bytes, AvroError>> {
self.as_mut().get_bytes(range)
}
Expand All @@ -74,6 +89,23 @@ impl AsyncFileReader for Box<dyn AsyncFileReader + '_> {
}

impl<T: AsyncRead + AsyncSeek + Unpin + Send> AsyncFileReader for T {
fn get_stream(
&mut self,
range: Range<u64>,
) -> BoxFuture<'_, Result<BoxStream<'_, Result<Bytes, AvroError>>, AvroError>> {
async move {
self.seek(SeekFrom::Start(range.start)).await?;

let ranged_reader = self.take(range.end - range.start);
let stream = ReaderStream::new(ranged_reader)
.map_err(AvroError::from)
.boxed();

Ok(stream)
}
.boxed()
}

fn get_bytes(&mut self, range: Range<u64>) -> BoxFuture<'_, Result<Bytes, AvroError>> {
async move {
self.seek(SeekFrom::Start(range.start)).await?;
Expand Down
15 changes: 4 additions & 11 deletions arrow-avro/src/reader/async_reader/builder.rs
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,6 @@

use crate::codec::{AvroFieldBuilder, Tz};
use crate::errors::AvroError;
use crate::reader::async_reader::ReaderState;
use crate::reader::header::{Header, HeaderDecoder, HeaderInfo};
use crate::reader::record::RecordDecoder;
use crate::reader::{AsyncAvroFileReader, AsyncFileReader, Decoder};
Expand Down Expand Up @@ -183,7 +182,7 @@ where
.ok_or_else(|| AvroError::EOF("Unexpected EOF while reading Avro header".into()))
}

impl<R: AsyncFileReader> ReaderBuilder<R> {
impl<R: AsyncFileReader + Unpin + Send + 'static> ReaderBuilder<R> {
/// Build the asynchronous Avro reader with the provided parameters.
/// This reads the header first to initialize the reader state.
pub async fn try_build(mut self) -> Result<AsyncAvroFileReader<R>, AvroError> {
Expand Down Expand Up @@ -273,24 +272,18 @@ impl<R: AsyncFileReader> ReaderBuilder<R> {

// Determine if there is actually data to fetch, note that we subtract the header len from range.start,
// so we need to check if range.end == header_len to see if there's no data after the header
let reader_state = if range.start == range.end || header_len == range.end {
ReaderState::Finished
} else {
ReaderState::Idle {
reader: self.reader,
}
};

let finished = range.start == range.end || header_len == range.end;
let codec = header_info.compression()?;
let sync_marker = header_info.sync();

Ok(AsyncAvroFileReader::new(
self.reader,
range,
self.file_size,
decoder,
codec,
sync_marker,
reader_state,
finished,
))
}
}
Loading
Loading