risingwave_connector/sink/file_sink/
webhdfs.rs

1// Copyright 2024 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.
14
15use std::collections::{BTreeMap, HashMap};
16
17use anyhow::anyhow;
18use opendal::Operator;
19use opendal::layers::LoggingLayer;
20use opendal::services::Webhdfs;
21use serde::Deserialize;
22use serde_with::serde_as;
23use with_options::WithOptions;
24
25use super::opendal_sink::{BatchingStrategy, FileSink};
26use crate::sink::file_sink::opendal_sink::OpendalSinkBackend;
27use crate::sink::{Result, SINK_TYPE_APPEND_ONLY, SINK_TYPE_OPTION, SINK_TYPE_UPSERT, SinkError};
28use crate::source::UnknownFields;
29#[derive(Deserialize, Debug, Clone, WithOptions)]
30pub struct WebhdfsCommon {
31    #[serde(rename = "webhdfs.endpoint")]
32    pub endpoint: String,
33    /// The directory where the sink file is located.
34    #[serde(rename = "webhdfs.path")]
35    pub path: String,
36}
37
38#[serde_as]
39#[derive(Clone, Debug, Deserialize, WithOptions)]
40pub struct WebhdfsConfig {
41    #[serde(flatten)]
42    pub common: WebhdfsCommon,
43
44    #[serde(flatten)]
45    pub batching_strategy: BatchingStrategy,
46
47    pub r#type: String, // accept "append-only"
48
49    #[serde(flatten)]
50    pub unknown_fields: HashMap<String, String>,
51}
52
53pub const WEBHDFS_SINK: &str = "webhdfs";
54
55impl<S: OpendalSinkBackend> FileSink<S> {
56    pub fn new_webhdfs_sink(config: WebhdfsConfig) -> Result<Operator> {
57        // Create webhdfs backend builder.
58        let builder = Webhdfs::default()
59            .endpoint(&config.common.endpoint)
60            .root(&config.common.path);
61
62        let operator: Operator = Operator::new(builder)?
63            .layer(LoggingLayer::default())
64            .finish();
65
66        Ok(operator)
67    }
68}
69
70#[derive(Debug, Clone, Copy, PartialEq, Eq)]
71pub struct WebhdfsSink;
72
73impl UnknownFields for WebhdfsConfig {
74    fn unknown_fields(&self) -> HashMap<String, String> {
75        self.unknown_fields.clone()
76    }
77}
78
79crate::impl_sink_unknown_fields!(WebhdfsConfig);
80
81impl OpendalSinkBackend for WebhdfsSink {
82    type Properties = WebhdfsConfig;
83
84    const SINK_NAME: &'static str = WEBHDFS_SINK;
85
86    fn from_btreemap(btree_map: BTreeMap<String, String>) -> Result<Self::Properties> {
87        let config =
88            serde_json::from_value::<WebhdfsConfig>(serde_json::to_value(btree_map).unwrap())
89                .map_err(|e| SinkError::Config(anyhow!(e)))?;
90        if config.r#type != SINK_TYPE_APPEND_ONLY && config.r#type != SINK_TYPE_UPSERT {
91            return Err(SinkError::Config(anyhow!(
92                "`{}` must be {}, or {}",
93                SINK_TYPE_OPTION,
94                SINK_TYPE_APPEND_ONLY,
95                SINK_TYPE_UPSERT
96            )));
97        }
98        Ok(config)
99    }
100
101    fn new_operator(properties: WebhdfsConfig) -> Result<Operator> {
102        FileSink::<WebhdfsSink>::new_webhdfs_sink(properties)
103    }
104
105    fn get_path(properties: Self::Properties) -> String {
106        properties.common.path
107    }
108
109    fn get_engine_type() -> super::opendal_sink::EngineType {
110        super::opendal_sink::EngineType::Webhdfs
111    }
112
113    fn get_batching_strategy(properties: Self::Properties) -> BatchingStrategy {
114        BatchingStrategy {
115            max_row_count: properties.batching_strategy.max_row_count,
116            rollover_seconds: properties.batching_strategy.rollover_seconds,
117            path_partition_prefix: properties.batching_strategy.path_partition_prefix,
118        }
119    }
120}
risingwave_connector/sink/file_sink/webhdfs.rs

risingwave_connector/sink/file_sink/
webhdfs.rs
