parquet/column/chunker/
mod.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//! Content-defined chunking (CDC) for Parquet data pages.
19//!
20//! CDC creates data page boundaries based on content rather than fixed sizes,
21//! enabling efficient deduplication in content-addressable storage (CAS) systems.
22//! See [`CdcOptions`](crate::file::properties::CdcOptions) for configuration.
23
24mod cdc;
25mod cdc_generated;
26
27pub(crate) use cdc::ContentDefinedChunker;
28
29/// A chunk of data with level and value offsets for record-shredded nested data.
30#[derive(Debug, Clone, Copy)]
31pub(crate) struct CdcChunk {
32    /// The start offset of this chunk inside the given levels.
33    pub level_offset: usize,
34    /// The start offset of this chunk inside the given values array.
35    pub value_offset: usize,
36    /// The number of levels in this chunk.
37    pub num_levels: usize,
38    /// The number of values (Arrow array elements) in this chunk.
39    pub num_values: usize,
40}
parquet/column/chunker/mod.rs

parquet/column/chunker/
mod.rs
