risingwave_connector/sink/file_sink/
webhdfs.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;
19use opendal::services::Webhdfs;
20use serde::Deserialize;
21use serde_with::serde_as;
22use with_options::WithOptions;
23
24use super::opendal_sink::{BatchingStrategy, FileSink};
25use crate::sink::file_sink::opendal_sink::OpendalSinkBackend;
26use crate::sink::{Result, SINK_TYPE_APPEND_ONLY, SINK_TYPE_OPTION, SINK_TYPE_UPSERT, SinkError};
27use crate::source::UnknownFields;
28#[derive(Deserialize, Debug, Clone, WithOptions)]
29pub struct WebhdfsCommon {
30    #[serde(rename = "webhdfs.endpoint")]
31    pub endpoint: String,
32    /// The directory where the sink file is located.
33    #[serde(rename = "webhdfs.path")]
34    pub path: String,
35}
36
37#[serde_as]
38#[derive(Clone, Debug, Deserialize, WithOptions)]
39pub struct WebhdfsConfig {
40    #[serde(flatten)]
41    pub common: WebhdfsCommon,
42
43    #[serde(flatten)]
44    pub batching_strategy: BatchingStrategy,
45
46    pub r#type: String, // accept "append-only"
47
48    #[serde(flatten)]
49    pub unknown_fields: HashMap<String, String>,
50}
51
52pub const WEBHDFS_SINK: &str = "webhdfs";
53
54impl<S: OpendalSinkBackend> FileSink<S> {
55    pub fn new_webhdfs_sink(config: WebhdfsConfig) -> Result<Operator> {
56        // Create webhdfs backend builder.
57        let builder = Webhdfs::default()
58            .endpoint(&config.common.endpoint)
59            .root(&config.common.path);
60
61        let operator: Operator = Operator::new(builder)?
62            .layer(LoggingLayer::default())
63            .finish();
64
65        Ok(operator)
66    }
67}
68
69#[derive(Debug, Clone, Copy, PartialEq, Eq)]
70pub struct WebhdfsSink;
71
72impl UnknownFields for WebhdfsConfig {
73    fn unknown_fields(&self) -> HashMap<String, String> {
74        self.unknown_fields.clone()
75    }
76}
77
78impl OpendalSinkBackend for WebhdfsSink {
79    type Properties = WebhdfsConfig;
80
81    const SINK_NAME: &'static str = WEBHDFS_SINK;
82
83    fn from_btreemap(btree_map: BTreeMap<String, String>) -> Result<Self::Properties> {
84        let config =
85            serde_json::from_value::<WebhdfsConfig>(serde_json::to_value(btree_map).unwrap())
86                .map_err(|e| SinkError::Config(anyhow!(e)))?;
87        if config.r#type != SINK_TYPE_APPEND_ONLY && config.r#type != SINK_TYPE_UPSERT {
88            return Err(SinkError::Config(anyhow!(
89                "`{}` must be {}, or {}",
90                SINK_TYPE_OPTION,
91                SINK_TYPE_APPEND_ONLY,
92                SINK_TYPE_UPSERT
93            )));
94        }
95        Ok(config)
96    }
97
98    fn new_operator(properties: WebhdfsConfig) -> Result<Operator> {
99        FileSink::<WebhdfsSink>::new_webhdfs_sink(properties)
100    }
101
102    fn get_path(properties: Self::Properties) -> String {
103        properties.common.path
104    }
105
106    fn get_engine_type() -> super::opendal_sink::EngineType {
107        super::opendal_sink::EngineType::Webhdfs
108    }
109
110    fn get_batching_strategy(properties: Self::Properties) -> BatchingStrategy {
111        BatchingStrategy {
112            max_row_count: properties.batching_strategy.max_row_count,
113            rollover_seconds: properties.batching_strategy.rollover_seconds,
114            path_partition_prefix: properties.batching_strategy.path_partition_prefix,
115        }
116    }
117}
risingwave_connector/sink/file_sink/webhdfs.rs

risingwave_connector/sink/file_sink/
webhdfs.rs
