risingwave_connector/sink/file_sink/
fs.rs

1// Copyright 2025 RisingWave Labs
2//
3// Licensed under the Apache License, Version 2.0 (the "License");
4// you may not use this file except in compliance with the License.
5// You may obtain a copy of the License at
6//
7//     http://www.apache.org/licenses/LICENSE-2.0
8//
9// Unless required by applicable law or agreed to in writing, software
10// distributed under the License is distributed on an "AS IS" BASIS,
11// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12// See the License for the specific language governing permissions and
13// limitations under the License.
14use std::collections::{BTreeMap, HashMap};
15
16use anyhow::anyhow;
17use opendal::Operator;
18use opendal::layers::{LoggingLayer, RetryLayer};
19use opendal::services::Fs;
20use serde::Deserialize;
21use serde_with::serde_as;
22use with_options::WithOptions;
23
24use super::opendal_sink::BatchingStrategy;
25use crate::sink::file_sink::opendal_sink::{FileSink, OpendalSinkBackend};
26use crate::sink::{Result, SINK_TYPE_APPEND_ONLY, SINK_TYPE_OPTION, SINK_TYPE_UPSERT, SinkError};
27use crate::source::UnknownFields;
28
29#[derive(Deserialize, Debug, Clone, WithOptions)]
30pub struct FsCommon {
31    /// The directory where the sink file is located.
32    #[serde(rename = "fs.path")]
33    pub path: String,
34}
35
36#[serde_as]
37#[derive(Clone, Debug, Deserialize, WithOptions)]
38pub struct FsConfig {
39    #[serde(flatten)]
40    pub common: FsCommon,
41    #[serde(flatten)]
42    pub batching_strategy: BatchingStrategy,
43
44    pub r#type: String, // accept "append-only"
45
46    #[serde(flatten)]
47    pub unknown_fields: HashMap<String, String>,
48}
49
50impl UnknownFields for FsConfig {
51    fn unknown_fields(&self) -> HashMap<String, String> {
52        self.unknown_fields.clone()
53    }
54}
55
56pub const FS_SINK: &str = "fs";
57
58impl<S: OpendalSinkBackend> FileSink<S> {
59    pub fn new_fs_sink(config: FsConfig) -> Result<Operator> {
60        // Create fs builder.
61        let builder = Fs::default().root(&config.common.path);
62        let operator: Operator = Operator::new(builder)?
63            .layer(LoggingLayer::default())
64            .layer(RetryLayer::default())
65            .finish();
66        Ok(operator)
67    }
68}
69
70#[derive(Debug, Clone, Copy, PartialEq, Eq)]
71pub struct FsSink;
72
73impl OpendalSinkBackend for FsSink {
74    type Properties = FsConfig;
75
76    const SINK_NAME: &'static str = FS_SINK;
77
78    fn from_btreemap(btree_map: BTreeMap<String, String>) -> Result<Self::Properties> {
79        let config = serde_json::from_value::<FsConfig>(serde_json::to_value(btree_map).unwrap())
80            .map_err(|e| SinkError::Config(anyhow!(e)))?;
81        if config.r#type != SINK_TYPE_APPEND_ONLY && config.r#type != SINK_TYPE_UPSERT {
82            return Err(SinkError::Config(anyhow!(
83                "`{}` must be {}, or {}",
84                SINK_TYPE_OPTION,
85                SINK_TYPE_APPEND_ONLY,
86                SINK_TYPE_UPSERT
87            )));
88        }
89        Ok(config)
90    }
91
92    fn new_operator(properties: FsConfig) -> Result<Operator> {
93        FileSink::<FsSink>::new_fs_sink(properties)
94    }
95
96    fn get_path(properties: Self::Properties) -> String {
97        properties.common.path
98    }
99
100    fn get_engine_type() -> super::opendal_sink::EngineType {
101        super::opendal_sink::EngineType::Fs
102    }
103
104    fn get_batching_strategy(properties: Self::Properties) -> BatchingStrategy {
105        BatchingStrategy {
106            max_row_count: properties.batching_strategy.max_row_count,
107            rollover_seconds: properties.batching_strategy.rollover_seconds,
108            path_partition_prefix: properties.batching_strategy.path_partition_prefix,
109        }
110    }
111}
risingwave_connector/sink/file_sink/fs.rs

risingwave_connector/sink/file_sink/
fs.rs
