forked from confluentinc/examples
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathStreamsIngest.java
105 lines (79 loc) · 4.37 KB
/
StreamsIngest.java
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
/*
* Copyright 2017 Confluent Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package io.confluent.examples.connectandstreams.jdbcspecificavro;
import java.util.Properties;
import org.apache.kafka.common.serialization.Serdes;
import org.apache.kafka.clients.consumer.ConsumerConfig;
import org.apache.kafka.streams.KafkaStreams;
import org.apache.kafka.streams.StreamsConfig;
import org.apache.kafka.streams.kstream.KStream;
import org.apache.kafka.streams.kstream.KStreamBuilder;
import org.apache.kafka.streams.KeyValue;
import io.confluent.kafka.streams.serdes.avro.SpecificAvroSerializer;
import io.confluent.kafka.streams.serdes.avro.SpecificAvroSerde;
import io.confluent.kafka.serializers.AbstractKafkaAvroSerDeConfig;
import org.apache.kafka.common.serialization.Serde;
import io.confluent.examples.connectandstreams.avro.Location;
import java.util.Collections;
public class StreamsIngest {
static final String INPUT_TOPIC = "jdbcspecificavro-locations";
static final String DEFAULT_BOOTSTRAP_SERVERS = "localhost:9092";
static final String DEFAULT_SCHEMA_REGISTRY_URL = "http://localhost:8081";
static final String KEYS_STORE = "jdbcspecificavro-count-keys";
static final String SALES_STORE = "jdbcspecificavro-aggregate-sales";
public static void main(String[] args) throws Exception {
if (args.length > 2) {
throw new IllegalArgumentException("usage: ... " +
"[<bootstrap.servers> (optional, default: " + DEFAULT_BOOTSTRAP_SERVERS + ")] " +
"[<schema.registry.url> (optional, default: " + DEFAULT_SCHEMA_REGISTRY_URL + ")] ");
}
final String bootstrapServers = args.length > 0 ? args[0] : DEFAULT_BOOTSTRAP_SERVERS;
final String SCHEMA_REGISTRY_URL = args.length > 1 ? args[1] : DEFAULT_SCHEMA_REGISTRY_URL;
System.out.println("Connecting to Kafka cluster via bootstrap servers " + bootstrapServers);
System.out.println("Connecting to Confluent schema registry at " + SCHEMA_REGISTRY_URL);
final KStreamBuilder builder = new KStreamBuilder();
Properties streamsConfiguration = new Properties();
streamsConfiguration.put(StreamsConfig.APPLICATION_ID_CONFIG, "jdbcspecificavro");
streamsConfiguration.put(StreamsConfig.BOOTSTRAP_SERVERS_CONFIG, bootstrapServers);
streamsConfiguration.put(StreamsConfig.COMMIT_INTERVAL_MS_CONFIG, 1000);
streamsConfiguration.put(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest");
final Serde<Location> locationSerde = new SpecificAvroSerde<>();
final boolean isKeySerde = false;
locationSerde.configure(
Collections.singletonMap(AbstractKafkaAvroSerDeConfig.SCHEMA_REGISTRY_URL_CONFIG, SCHEMA_REGISTRY_URL),
isKeySerde);
KStream<String, Location> locationsNoKey = builder.stream(Serdes.String(), locationSerde, INPUT_TOPIC);
locationsNoKey.print();
KStream<Long, Location> locations = locationsNoKey.map((k, v) -> new KeyValue<Long, Location>((Long) v.get("id"), v ));
locations.print();
KStream<Long,Long> sales = locations.map((k, v) -> new KeyValue<Long, Long>(k, v.getSale()));
// Count occurrences of each key
KStream<Long, Long> countKeys = sales.groupByKey(Serdes.Long(), Serdes.Long())
.count(KEYS_STORE)
.toStream();
countKeys.print();
// Aggregate values by key
KStream<Long,Long> salesAgg = sales.groupByKey(Serdes.Long(), Serdes.Long())
.reduce(
(aggValue, newValue) -> aggValue + newValue, SALES_STORE)
.toStream();
salesAgg.print();
KafkaStreams streams = new KafkaStreams(builder, streamsConfiguration);
streams.start();
// Add shutdown hook to respond to SIGTERM and gracefully close Kafka Streams
Runtime.getRuntime().addShutdownHook(new Thread(streams::close));
}
}