parquet_opendal/
lib.rs

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.
17
18//! parquet_opendal provides parquet IO utilities.
19//!
20//! ```no_run
21//! use std::sync::Arc;
22//! use arrow::array::{ArrayRef, Int64Array, RecordBatch};
23//!
24//! use futures::StreamExt;
25//! use opendal::{services::S3Config, Operator};
26//! use parquet::arrow::{AsyncArrowWriter, ParquetRecordBatchStreamBuilder};
27//! use parquet_opendal::{AsyncReader, AsyncWriter};
28//!
29//! #[tokio::main]
30//! async fn main() {
31//!     let mut cfg = S3Config::default();
32//!     cfg.access_key_id = Some("my_access_key".to_string());
33//!     cfg.secret_access_key = Some("my_secret_key".to_string());
34//!     cfg.endpoint = Some("my_endpoint".to_string());
35//!     cfg.region = Some("my_region".to_string());
36//!     cfg.bucket = "my_bucket".to_string();
37//!
38//!     // Create a new operator
39//!     let operator = Operator::from_config(cfg).unwrap().finish();
40//!     let path = "/path/to/file.parquet";
41//!
42//!     // Create an async writer
43//!     let writer = AsyncWriter::new(
44//!         operator
45//!             .writer_with(path)
46//!             .chunk(32 * 1024 * 1024)
47//!             .concurrent(8)
48//!             .await
49//!             .unwrap(),
50//!     );
51//!
52//!     let col = Arc::new(Int64Array::from_iter_values([1, 2, 3])) as ArrayRef;
53//!     let to_write = RecordBatch::try_from_iter([("col", col)]).unwrap();
54//!     let mut writer = AsyncArrowWriter::try_new(writer, to_write.schema(), None).unwrap();
55//!     writer.write(&to_write).await.unwrap();
56//!     writer.close().await.unwrap();
57//!
58//!     // gap: Allow the underlying reader to merge small IOs
59//!     // when the gap between multiple IO ranges is less than the threshold.
60//!     let reader = operator
61//!         .reader_with(path)
62//!         .gap(512 * 1024)
63//!         .chunk(16 * 1024 * 1024)
64//!         .concurrent(16)
65//!         .await
66//!         .unwrap();
67//!     let content_len = operator.stat(path).await.unwrap().content_length();
68//!     let reader = AsyncReader::new(reader, content_len).with_prefetch_footer_size(512 * 1024);
69//!     let mut stream = ParquetRecordBatchStreamBuilder::new(reader)
70//!         .await
71//!         .unwrap()
72//!         .build()
73//!         .unwrap();
74//!     let read = stream.next().await.unwrap().unwrap();
75//!     assert_eq!(to_write, read);
76//! }
77//! ```
78
79mod async_reader;
80mod async_writer;
81
82pub use async_reader::AsyncReader;
83pub use async_writer::AsyncWriter;
parquet_opendal/lib.rs

parquet_opendal/
lib.rs
