|
| 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 | +use iceberg::{Error, ErrorKind, Result}; |
| 19 | +use serde_derive::{Deserialize, Serialize}; |
| 20 | + |
| 21 | +#[derive(Debug, PartialEq, Eq, Serialize, Deserialize, Clone, Copy)] |
| 22 | +#[serde(rename_all = "lowercase")] |
| 23 | +#[derive(Default)] |
| 24 | +pub enum CompressionCodec { |
| 25 | + /** No compression */ |
| 26 | + #[default] |
| 27 | + None, |
| 28 | + /** LZ4 single compression frame with content size present */ |
| 29 | + Lz4, |
| 30 | + /** Zstandard single compression frame with content size present */ |
| 31 | + Zstd, |
| 32 | +} |
| 33 | + |
| 34 | +impl CompressionCodec { |
| 35 | + pub(crate) fn decompress(&self, bytes: Vec<u8>) -> Result<Vec<u8>> { |
| 36 | + match self { |
| 37 | + CompressionCodec::None => Ok(bytes), |
| 38 | + CompressionCodec::Lz4 => Err(Error::new( |
| 39 | + ErrorKind::FeatureUnsupported, |
| 40 | + "LZ4 decompression is not supported currently", |
| 41 | + )), |
| 42 | + CompressionCodec::Zstd => { |
| 43 | + let decompressed = zstd::stream::decode_all(&bytes[..])?; |
| 44 | + Ok(decompressed) |
| 45 | + } |
| 46 | + } |
| 47 | + } |
| 48 | + |
| 49 | + pub(crate) fn compress(&self, bytes: Vec<u8>) -> Result<Vec<u8>> { |
| 50 | + match self { |
| 51 | + CompressionCodec::None => Ok(bytes), |
| 52 | + CompressionCodec::Lz4 => Err(Error::new( |
| 53 | + ErrorKind::FeatureUnsupported, |
| 54 | + "LZ4 compression is not supported currently", |
| 55 | + )), |
| 56 | + CompressionCodec::Zstd => { |
| 57 | + let writer = Vec::<u8>::new(); |
| 58 | + let mut encoder = zstd::stream::Encoder::new(writer, 3)?; |
| 59 | + encoder.include_checksum(true)?; |
| 60 | + encoder.set_pledged_src_size(Some(bytes.len().try_into()?))?; |
| 61 | + std::io::copy(&mut &bytes[..], &mut encoder)?; |
| 62 | + let compressed = encoder.finish()?; |
| 63 | + Ok(compressed) |
| 64 | + } |
| 65 | + } |
| 66 | + } |
| 67 | + |
| 68 | + pub(crate) fn is_none(&self) -> bool { |
| 69 | + matches!(self, CompressionCodec::None) |
| 70 | + } |
| 71 | +} |
| 72 | + |
| 73 | +#[cfg(test)] |
| 74 | +mod tests { |
| 75 | + use crate::compression::CompressionCodec; |
| 76 | + |
| 77 | + #[tokio::test] |
| 78 | + async fn test_compression_codec_none() { |
| 79 | + let compression_codec = CompressionCodec::None; |
| 80 | + let bytes_vec = [0_u8; 100].to_vec(); |
| 81 | + |
| 82 | + let compressed = compression_codec.compress(bytes_vec.clone()).unwrap(); |
| 83 | + assert_eq!(bytes_vec, compressed); |
| 84 | + |
| 85 | + let decompressed = compression_codec.decompress(compressed.clone()).unwrap(); |
| 86 | + assert_eq!(compressed, decompressed) |
| 87 | + } |
| 88 | + |
| 89 | + #[tokio::test] |
| 90 | + async fn test_compression_codec_lz4() { |
| 91 | + let compression_codec = CompressionCodec::Lz4; |
| 92 | + let bytes_vec = [0_u8; 100].to_vec(); |
| 93 | + |
| 94 | + assert_eq!( |
| 95 | + compression_codec |
| 96 | + .compress(bytes_vec.clone()) |
| 97 | + .unwrap_err() |
| 98 | + .to_string(), |
| 99 | + "FeatureUnsupported => LZ4 compression is not supported currently", |
| 100 | + ); |
| 101 | + |
| 102 | + assert_eq!( |
| 103 | + compression_codec |
| 104 | + .decompress(bytes_vec.clone()) |
| 105 | + .unwrap_err() |
| 106 | + .to_string(), |
| 107 | + "FeatureUnsupported => LZ4 decompression is not supported currently", |
| 108 | + ) |
| 109 | + } |
| 110 | + |
| 111 | + #[tokio::test] |
| 112 | + async fn test_compression_codec_zstd() { |
| 113 | + let compression_codec = CompressionCodec::Zstd; |
| 114 | + let bytes_vec = [0_u8; 100].to_vec(); |
| 115 | + |
| 116 | + let compressed = compression_codec.compress(bytes_vec.clone()).unwrap(); |
| 117 | + assert!(compressed.len() < bytes_vec.len()); |
| 118 | + |
| 119 | + let decompressed = compression_codec.decompress(compressed.clone()).unwrap(); |
| 120 | + assert_eq!(decompressed, bytes_vec) |
| 121 | + } |
| 122 | +} |
0 commit comments