input) {
77 | return input.getKey() + ": " + input.getValue();
78 | }
79 | }
80 |
81 | /**
82 | * Options supported by {@link WordCount}.
83 | *
84 | * Inherits standard configuration options.
85 | */
86 | public interface Options extends PipelineOptions, FlinkPipelineOptions {
87 | @Description("Path of the file to read from")
88 | @Default.String("/tmp/kinglear.txt")
89 | String getInput();
90 | void setInput(String value);
91 |
92 | @Description("Path of the file to write to")
93 | @Default.String("/tmp/output.txt")
94 | String getOutput();
95 | void setOutput(String value);
96 | }
97 |
98 | public static void main(String[] args) {
99 |
100 | Options options = PipelineOptionsFactory.fromArgs(args).withValidation()
101 | .as(Options.class);
102 | options.setRunner(FlinkRunner.class);
103 |
104 | Pipeline p = Pipeline.create(options);
105 |
106 | p.apply("ReadLines", TextIO.Read.from(options.getInput()))
107 | .apply(new CountWords())
108 | .apply(MapElements.via(new FormatAsTextFn()))
109 | .apply("WriteCounts", TextIO.Write.to(options.getOutput()));
110 |
111 | p.run();
112 | }
113 |
114 | }
--------------------------------------------------------------------------------
/src/main/java/com/dataradiant/beam/examples/StreamWordCount.java:
--------------------------------------------------------------------------------
1 | /*
2 | * Licensed to the Apache Software Foundation (ASF) under one
3 | * or more contributor license agreements. See the NOTICE file
4 | * distributed with this work for additional information
5 | * regarding copyright ownership. The ASF licenses this file
6 | * to you under the Apache License, Version 2.0 (the
7 | * "License"); you may not use this file except in compliance
8 | * with the License. You may obtain a copy of the License at
9 | *
10 | * http://www.apache.org/licenses/LICENSE-2.0
11 | *
12 | * Unless required by applicable law or agreed to in writing, software
13 | * distributed under the License is distributed on an "AS IS" BASIS,
14 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15 | * See the License for the specific language governing permissions and
16 | * limitations under the License.
17 | */
18 | package com.dataradiant.beam.examples;
19 |
20 | import org.apache.beam.runners.flink.FlinkPipelineOptions;
21 | import org.apache.beam.runners.flink.FlinkRunner;
22 | import org.apache.beam.sdk.Pipeline;
23 | import org.apache.beam.sdk.io.TextIO;
24 | import org.apache.beam.sdk.io.kafka.KafkaIO;
25 | import org.apache.beam.sdk.options.Default;
26 | import org.apache.beam.sdk.options.Description;
27 | import org.apache.beam.sdk.options.PipelineOptions;
28 | import org.apache.beam.sdk.options.PipelineOptionsFactory;
29 | import org.apache.beam.sdk.transforms.*;
30 | import org.apache.beam.sdk.transforms.windowing.FixedWindows;
31 | import org.apache.beam.sdk.transforms.windowing.Window;
32 | import org.apache.beam.sdk.values.KV;
33 | import org.apache.beam.sdk.values.PCollection;
34 | import org.apache.beam.sdk.coders.StringUtf8Coder;
35 | import com.google.common.collect.ImmutableMap;
36 | import org.joda.time.Duration;
37 | import java.util.Arrays;
38 |
39 | public class StreamWordCount {
40 |
41 | public static class ExtractWordsFn extends DoFn {
42 | private final Aggregator emptyLines =
43 | createAggregator("emptyLines", new Sum.SumLongFn());
44 |
45 | @Override
46 | public void processElement(ProcessContext c) {
47 | if (c.element().trim().isEmpty()) {
48 | emptyLines.addValue(1L);
49 | }
50 |
51 | // Split the line into words.
52 | String[] words = c.element().split("[^a-zA-Z']+");
53 |
54 | // Output each word encountered into the output PCollection.
55 | for (String word : words) {
56 | if (!word.isEmpty()) {
57 | c.output(word);
58 | }
59 | }
60 | }
61 | }
62 |
63 | public static class CountWords extends PTransform,
64 | PCollection>> {
65 | @Override
66 | public PCollection> apply(PCollection lines) {
67 |
68 | // Convert lines of text into individual words.
69 | PCollection words = lines.apply(
70 | ParDo.of(new ExtractWordsFn()));
71 |
72 | // Count the number of times each word occurs.
73 | PCollection> wordCounts =
74 | words.apply(Count.perElement());
75 |
76 | return wordCounts;
77 | }
78 | }
79 |
80 | /** A SimpleFunction that converts a Word and Count into a printable string. */
81 | public static class FormatAsTextFn extends SimpleFunction, String> {
82 | @Override
83 | public String apply(KV input) {
84 | return input.getKey() + ": " + input.getValue();
85 | }
86 | }
87 |
88 | // public static class ValuesFn extends SimpleFunction, String> {
89 | // @Override
90 | // public String apply(KV input) {
91 | // return input.getValue();
92 | // }
93 | // }
94 |
95 | // public static class TrivialCountFn extends SimpleFunction> {
96 | // @Override
97 | // public KV apply(String input) {
98 | // return KV.of(input, 1L);
99 | // }
100 | // }
101 |
102 | /**
103 | * Options supported by {@link WordCount}.
104 | *
105 | * Inherits standard configuration options.
106 | */
107 | public interface Options extends PipelineOptions, FlinkPipelineOptions {
108 | @Description("Path of the file to read from")
109 | @Default.String("/tmp/kinglear.txt")
110 | String getInput();
111 | void setInput(String value);
112 |
113 | @Description("Path of the file to write to")
114 | @Default.String("/tmp/output.txt")
115 | String getOutput();
116 | void setOutput(String value);
117 |
118 | @Description("Fixed window duration, in minutes")
119 | @Default.Integer(1)
120 | Integer getWindowSize();
121 | void setWindowSize(Integer value);
122 | }
123 |
124 | public static void main(String[] args) throws Exception {
125 |
126 | Options options = PipelineOptionsFactory.fromArgs(args).withValidation()
127 | .as(Options.class);
128 | options.setRunner(FlinkRunner.class);
129 |
130 | Pipeline p = Pipeline.create(options);
131 |
132 | KafkaIO.Read kafkaIOReader = KafkaIO.read()
133 | .withBootstrapServers("192.168.99.100:32771")
134 | .withTopics(Arrays.asList("beam".split(",")))
135 | .updateConsumerProperties(ImmutableMap.of("auto.offset.reset", (Object)"earliest"))
136 | .withValueCoder(StringUtf8Coder.of());
137 |
138 | p.apply(kafkaIOReader.withoutMetadata())
139 | .apply(Values.create())
140 | .apply(Window.into(
141 | FixedWindows.of(Duration.standardMinutes(options.getWindowSize()))))
142 | .apply(new CountWords())
143 | .apply(MapElements.via(new FormatAsTextFn()))
144 | .apply("WriteCounts", TextIO.Write.to(options.getOutput()));
145 |
146 | p.run();
147 | }
148 |
149 | }
--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
1 | Apache License
2 | Version 2.0, January 2004
3 | http://www.apache.org/licenses/
4 |
5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6 |
7 | 1. Definitions.
8 |
9 | "License" shall mean the terms and conditions for use, reproduction,
10 | and distribution as defined by Sections 1 through 9 of this document.
11 |
12 | "Licensor" shall mean the copyright owner or entity authorized by
13 | the copyright owner that is granting the License.
14 |
15 | "Legal Entity" shall mean the union of the acting entity and all
16 | other entities that control, are controlled by, or are under common
17 | control with that entity. For the purposes of this definition,
18 | "control" means (i) the power, direct or indirect, to cause the
19 | direction or management of such entity, whether by contract or
20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the
21 | outstanding shares, or (iii) beneficial ownership of such entity.
22 |
23 | "You" (or "Your") shall mean an individual or Legal Entity
24 | exercising permissions granted by this License.
25 |
26 | "Source" form shall mean the preferred form for making modifications,
27 | including but not limited to software source code, documentation
28 | source, and configuration files.
29 |
30 | "Object" form shall mean any form resulting from mechanical
31 | transformation or translation of a Source form, including but
32 | not limited to compiled object code, generated documentation,
33 | and conversions to other media types.
34 |
35 | "Work" shall mean the work of authorship, whether in Source or
36 | Object form, made available under the License, as indicated by a
37 | copyright notice that is included in or attached to the work
38 | (an example is provided in the Appendix below).
39 |
40 | "Derivative Works" shall mean any work, whether in Source or Object
41 | form, that is based on (or derived from) the Work and for which the
42 | editorial revisions, annotations, elaborations, or other modifications
43 | represent, as a whole, an original work of authorship. For the purposes
44 | of this License, Derivative Works shall not include works that remain
45 | separable from, or merely link (or bind by name) to the interfaces of,
46 | the Work and Derivative Works thereof.
47 |
48 | "Contribution" shall mean any work of authorship, including
49 | the original version of the Work and any modifications or additions
50 | to that Work or Derivative Works thereof, that is intentionally
51 | submitted to Licensor for inclusion in the Work by the copyright owner
52 | or by an individual or Legal Entity authorized to submit on behalf of
53 | the copyright owner. For the purposes of this definition, "submitted"
54 | means any form of electronic, verbal, or written communication sent
55 | to the Licensor or its representatives, including but not limited to
56 | communication on electronic mailing lists, source code control systems,
57 | and issue tracking systems that are managed by, or on behalf of, the
58 | Licensor for the purpose of discussing and improving the Work, but
59 | excluding communication that is conspicuously marked or otherwise
60 | designated in writing by the copyright owner as "Not a Contribution."
61 |
62 | "Contributor" shall mean Licensor and any individual or Legal Entity
63 | on behalf of whom a Contribution has been received by Licensor and
64 | subsequently incorporated within the Work.
65 |
66 | 2. Grant of Copyright License. Subject to the terms and conditions of
67 | this License, each Contributor hereby grants to You a perpetual,
68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69 | copyright license to reproduce, prepare Derivative Works of,
70 | publicly display, publicly perform, sublicense, and distribute the
71 | Work and such Derivative Works in Source or Object form.
72 |
73 | 3. Grant of Patent License. Subject to the terms and conditions of
74 | this License, each Contributor hereby grants to You a perpetual,
75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76 | (except as stated in this section) patent license to make, have made,
77 | use, offer to sell, sell, import, and otherwise transfer the Work,
78 | where such license applies only to those patent claims licensable
79 | by such Contributor that are necessarily infringed by their
80 | Contribution(s) alone or by combination of their Contribution(s)
81 | with the Work to which such Contribution(s) was submitted. If You
82 | institute patent litigation against any entity (including a
83 | cross-claim or counterclaim in a lawsuit) alleging that the Work
84 | or a Contribution incorporated within the Work constitutes direct
85 | or contributory patent infringement, then any patent licenses
86 | granted to You under this License for that Work shall terminate
87 | as of the date such litigation is filed.
88 |
89 | 4. Redistribution. You may reproduce and distribute copies of the
90 | Work or Derivative Works thereof in any medium, with or without
91 | modifications, and in Source or Object form, provided that You
92 | meet the following conditions:
93 |
94 | (a) You must give any other recipients of the Work or
95 | Derivative Works a copy of this License; and
96 |
97 | (b) You must cause any modified files to carry prominent notices
98 | stating that You changed the files; and
99 |
100 | (c) You must retain, in the Source form of any Derivative Works
101 | that You distribute, all copyright, patent, trademark, and
102 | attribution notices from the Source form of the Work,
103 | excluding those notices that do not pertain to any part of
104 | the Derivative Works; and
105 |
106 | (d) If the Work includes a "NOTICE" text file as part of its
107 | distribution, then any Derivative Works that You distribute must
108 | include a readable copy of the attribution notices contained
109 | within such NOTICE file, excluding those notices that do not
110 | pertain to any part of the Derivative Works, in at least one
111 | of the following places: within a NOTICE text file distributed
112 | as part of the Derivative Works; within the Source form or
113 | documentation, if provided along with the Derivative Works; or,
114 | within a display generated by the Derivative Works, if and
115 | wherever such third-party notices normally appear. The contents
116 | of the NOTICE file are for informational purposes only and
117 | do not modify the License. You may add Your own attribution
118 | notices within Derivative Works that You distribute, alongside
119 | or as an addendum to the NOTICE text from the Work, provided
120 | that such additional attribution notices cannot be construed
121 | as modifying the License.
122 |
123 | You may add Your own copyright statement to Your modifications and
124 | may provide additional or different license terms and conditions
125 | for use, reproduction, or distribution of Your modifications, or
126 | for any such Derivative Works as a whole, provided Your use,
127 | reproduction, and distribution of the Work otherwise complies with
128 | the conditions stated in this License.
129 |
130 | 5. Submission of Contributions. Unless You explicitly state otherwise,
131 | any Contribution intentionally submitted for inclusion in the Work
132 | by You to the Licensor shall be under the terms and conditions of
133 | this License, without any additional terms or conditions.
134 | Notwithstanding the above, nothing herein shall supersede or modify
135 | the terms of any separate license agreement you may have executed
136 | with Licensor regarding such Contributions.
137 |
138 | 6. Trademarks. This License does not grant permission to use the trade
139 | names, trademarks, service marks, or product names of the Licensor,
140 | except as required for reasonable and customary use in describing the
141 | origin of the Work and reproducing the content of the NOTICE file.
142 |
143 | 7. Disclaimer of Warranty. Unless required by applicable law or
144 | agreed to in writing, Licensor provides the Work (and each
145 | Contributor provides its Contributions) on an "AS IS" BASIS,
146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147 | implied, including, without limitation, any warranties or conditions
148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149 | PARTICULAR PURPOSE. You are solely responsible for determining the
150 | appropriateness of using or redistributing the Work and assume any
151 | risks associated with Your exercise of permissions under this License.
152 |
153 | 8. Limitation of Liability. In no event and under no legal theory,
154 | whether in tort (including negligence), contract, or otherwise,
155 | unless required by applicable law (such as deliberate and grossly
156 | negligent acts) or agreed to in writing, shall any Contributor be
157 | liable to You for damages, including any direct, indirect, special,
158 | incidental, or consequential damages of any character arising as a
159 | result of this License or out of the use or inability to use the
160 | Work (including but not limited to damages for loss of goodwill,
161 | work stoppage, computer failure or malfunction, or any and all
162 | other commercial damages or losses), even if such Contributor
163 | has been advised of the possibility of such damages.
164 |
165 | 9. Accepting Warranty or Additional Liability. While redistributing
166 | the Work or Derivative Works thereof, You may choose to offer,
167 | and charge a fee for, acceptance of support, warranty, indemnity,
168 | or other liability obligations and/or rights consistent with this
169 | License. However, in accepting such obligations, You may act only
170 | on Your own behalf and on Your sole responsibility, not on behalf
171 | of any other Contributor, and only if You agree to indemnify,
172 | defend, and hold each Contributor harmless for any liability
173 | incurred by, or claims asserted against, such Contributor by reason
174 | of your accepting any such warranty or additional liability.
175 |
176 | END OF TERMS AND CONDITIONS
177 |
178 | APPENDIX: How to apply the Apache License to your work.
179 |
180 | To apply the Apache License to your work, attach the following
181 | boilerplate notice, with the fields enclosed by brackets "{}"
182 | replaced with your own identifying information. (Don't include
183 | the brackets!) The text should be enclosed in the appropriate
184 | comment syntax for the file format. We also recommend that a
185 | file or class name and description of purpose be included on the
186 | same "printed page" as the copyright notice for easier
187 | identification within third-party archives.
188 |
189 | Copyright {yyyy} {name of copyright owner}
190 |
191 | Licensed under the Apache License, Version 2.0 (the "License");
192 | you may not use this file except in compliance with the License.
193 | You may obtain a copy of the License at
194 |
195 | http://www.apache.org/licenses/LICENSE-2.0
196 |
197 | Unless required by applicable law or agreed to in writing, software
198 | distributed under the License is distributed on an "AS IS" BASIS,
199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200 | See the License for the specific language governing permissions and
201 | limitations under the License.
202 |
--------------------------------------------------------------------------------