├── src └── main │ ├── resources │ └── es-plugin.properties │ ├── java │ └── com │ │ └── ubervu │ │ ├── river │ │ └── github │ │ │ ├── GitHubRiverModule.java │ │ │ └── GitHubRiver.java │ │ └── plugin │ │ └── river │ │ └── github │ │ └── GitHubRiverPlugin.java │ └── assemblies │ └── plugin.xml ├── .gitignore ├── README.md ├── pom.xml └── LICENSE /src/main/resources/es-plugin.properties: -------------------------------------------------------------------------------- 1 | plugin=com.ubervu.plugin.river.github.GitHubRiverPlugin 2 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | *.class 2 | 3 | # Package Files # 4 | *.jar 5 | *.war 6 | *.ear 7 | 8 | target/ 9 | 10 | settings.xml 11 | -------------------------------------------------------------------------------- /src/main/java/com/ubervu/river/github/GitHubRiverModule.java: -------------------------------------------------------------------------------- 1 | package com.ubervu.river.github; 2 | 3 | import org.elasticsearch.common.inject.AbstractModule; 4 | import org.elasticsearch.river.River; 5 | 6 | /** 7 | * 8 | */ 9 | public class GitHubRiverModule extends AbstractModule { 10 | 11 | @Override 12 | protected void configure() { 13 | bind(River.class).to(GitHubRiver.class).asEagerSingleton(); 14 | } 15 | } 16 | 17 | -------------------------------------------------------------------------------- /src/main/java/com/ubervu/plugin/river/github/GitHubRiverPlugin.java: -------------------------------------------------------------------------------- 1 | package com.ubervu.plugin.river.github; 2 | 3 | import org.elasticsearch.common.inject.Inject; 4 | import org.elasticsearch.plugins.AbstractPlugin; 5 | import org.elasticsearch.river.RiversModule; 6 | import com.ubervu.river.github.GitHubRiverModule; 7 | 8 | /** 9 | * 10 | */ 11 | public class GitHubRiverPlugin extends AbstractPlugin { 12 | 13 | @Inject 14 | public GitHubRiverPlugin() { 15 | } 16 | 17 | @Override 18 | public String name() { 19 | return "river-github"; 20 | } 21 | 22 | @Override 23 | public String description() { 24 | return "GitHub River Plugin"; 25 | } 26 | 27 | public void onModule(RiversModule module) { 28 | module.registerRiver("github", GitHubRiverModule.class); 29 | } 30 | } 31 | -------------------------------------------------------------------------------- /src/main/assemblies/plugin.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | plugin 4 | 5 | zip 6 | 7 | false 8 | 9 | 10 | / 11 | true 12 | true 13 | 14 | org.elasticsearch:elasticsearch 15 | 16 | 17 | 18 | / 19 | true 20 | true 21 | 22 | org.eclipse.mylyn.github:org.eclipse.egit.github.core 23 | com.google.gson:com.google.gson 24 | 25 | 26 | 27 | 28 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | elasticsearch-river-github 2 | ========================== 3 | 4 | Elasticsearch river for GitHub data. Fetches all of the following for 5 | a given GitHub repo: 6 | 7 | * [events](http://developer.github.com/v3/activity/events/) 8 | * [issues](http://developer.github.com/v3/issues/#list-issues-for-a-repository) 9 | * [open pull requests](http://developer.github.com/v3/pulls/#list-pull-requests) 10 | * [open milestones](http://developer.github.com/v3/issues/milestones/) 11 | * [labels](http://developer.github.com/v3/issues/labels/) 12 | * [collaborators](http://developer.github.com/v3/repos/collaborators/#list) 13 | 14 | Works for private repos as well if you provide authentication. 15 | 16 | ##Easy install 17 | 18 | Assuming you have elasticsearch's `bin` folder in your `PATH`: 19 | 20 | ``` 21 | plugin -i com.ubervu/elasticsearch-river-github/1.7.1 22 | ``` 23 | 24 | Otherwise, you have to find the directory yourself. It should be 25 | `/usr/share/elasticsearch/bin` on Ubuntu. 26 | 27 | ##Adding the river 28 | 29 | ```bash 30 | curl -XPUT localhost:9200/_river/my_gh_river/_meta -d '{ 31 | "type": "github", 32 | "github": { 33 | "owner": "gabrielfalcao", 34 | "repository": "lettuce", 35 | "interval": 60, 36 | "authentication": { 37 | "username": "MYUSER", # or token 38 | "password": "MYPASSWORD" # or x-oauth-basic when using a token 39 | } 40 | "endpoint": "https://api.somegithub.com" # optional, use it only for non github.com 41 | } 42 | }' 43 | ``` 44 | 45 | _interval_ is optional, given in seconds and changes how often the river looks for new data. Since 1.7.1 the default value has been reduced to one minute as we now only load issues and events that has changed, which should decrease API calls and improve the time to update quite significantly. The actual polling interval will be affected by GitHub's minimum allowed polling interval, which is normally 60 seconds, but may increase when servers are busy. 46 | 47 | _authentication_ is optional and helps with the API rate limit (5000 requests/hour instead of 60 requests/hour) and when accessing private data. You can use your own GitHub credentials or a token. When using a token, fill in the token as the username and `x-oauth-basic` as the password, as the [docs](http://developer.github.com/v3/auth/#basic-authentication) mention. 48 | 49 | If you do not use _authentication_, you may want to set _interval_ to a higher value, like 900 (every 15 minutes), as the GitHub rate limit will probably be breached when using low values. This is __not__ recommended if you require the GitHub events without holes, as Github only allows access to the last 300 events. In that case, authenticating is highly recommended. _This will probably change in a later version, at least for repositories without too much traffic, as we should be able to check for changes before loading most types of entries._ 50 | 51 | ##Deleting the river 52 | 53 | ``` 54 | curl -XDELETE localhost:9200/_river/my_gh_river 55 | ``` 56 | 57 | ##Indexes and types 58 | 59 | The data will be stored in an index of format "%s&%s" % (owner, repo), i.e. 60 | `gabrielfalcao&lettuce`. 61 | 62 | For every API event type, there will be an elasticsearch type of the same name - 63 | i.e. `ForkEvent`. 64 | 65 | Issue data will be stored with the `IssueData` type. Pull request data will be stored 66 | with the `PullRequestData` type. Milestone data will be stored with the `MilestoneData` 67 | type. 68 | 69 | -------------------------------------------------------------------------------- /pom.xml: -------------------------------------------------------------------------------- 1 | 2 | 5 | elasticsearch-river-github 6 | 4.0.0 7 | com.ubervu 8 | elasticsearch-river-github 9 | 1.7.1 10 | jar 11 | Github River for ElasticSearch 12 | 2014 13 | 14 | 15 | The Apache Software License, Version 2.0 16 | http://www.apache.org/licenses/LICENSE-2.0.txt 17 | repo 18 | 19 | 20 | 21 | scm:git:git@github.com:ubervu/elasticsearch-river-github.git 22 | scm:git:git@github.com:ubervu/elasticsearch-river-github.git 23 | http://github.com/ubervu/elasticsearch-river-github 24 | 25 | 26 | 27 | org.sonatype.oss 28 | oss-parent 29 | 7 30 | 31 | 32 | 33 | 1.0.1 34 | 35 | 36 | 37 | 38 | sonatype 39 | http://oss.sonatype.org/content/repositories/releases/ 40 | 41 | 42 | 43 | 44 | 45 | org.elasticsearch 46 | elasticsearch 47 | ${elasticsearch.version} 48 | compile 49 | 50 | 51 | 52 | log4j 53 | log4j 54 | 1.2.16 55 | runtime 56 | 57 | 58 | 59 | commons-io 60 | commons-io 61 | 2.4 62 | 63 | 64 | 65 | commons-codec 66 | commons-codec 67 | 1.6 68 | 69 | 70 | 71 | com.google.code.gson 72 | gson 73 | 2.2.2 74 | 75 | 76 | 77 | 78 | 79 | 80 | 81 | 82 | org.apache.maven.plugins 83 | maven-gpg-plugin 84 | 85 | 86 | sign-artifacts 87 | verify 88 | 89 | sign 90 | 91 | 92 | 93 | 94 | 95 | org.apache.maven.plugins 96 | maven-compiler-plugin 97 | 2.3.2 98 | 99 | 1.6 100 | 1.6 101 | 102 | 103 | 104 | org.apache.maven.plugins 105 | maven-surefire-plugin 106 | 2.11 107 | 108 | 109 | **/*Tests.java 110 | 111 | 112 | 113 | 114 | org.apache.maven.plugins 115 | maven-javadoc-plugin 116 | 117 | 118 | attach-javadocs 119 | 120 | jar 121 | 122 | 123 | 124 | 125 | 126 | org.apache.maven.plugins 127 | maven-source-plugin 128 | 2.1.2 129 | 130 | 131 | attach-sources 132 | 133 | jar 134 | 135 | 136 | 137 | 138 | 139 | maven-assembly-plugin 140 | 2.3 141 | 142 | false 143 | ${project.build.directory}/releases/ 144 | 145 | ${basedir}/src/main/assemblies/plugin.xml 146 | 147 | 148 | 149 | 150 | package 151 | 152 | single 153 | 154 | 155 | 156 | 157 | 158 | 159 | 160 | 161 | sonatype 162 | https://oss.sonatype.org/service/local/staging/deploy/maven2 163 | 164 | 165 | 166 | -------------------------------------------------------------------------------- /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 | 203 | -------------------------------------------------------------------------------- /src/main/java/com/ubervu/river/github/GitHubRiver.java: -------------------------------------------------------------------------------- 1 | package com.ubervu.river.github; 2 | 3 | import com.google.gson.JsonArray; 4 | import com.google.gson.JsonElement; 5 | import com.google.gson.JsonObject; 6 | import com.google.gson.JsonStreamParser; 7 | import org.apache.commons.codec.digest.DigestUtils; 8 | import org.elasticsearch.action.bulk.BulkProcessor; 9 | import org.elasticsearch.action.bulk.BulkRequest; 10 | import org.elasticsearch.action.bulk.BulkResponse; 11 | import org.elasticsearch.action.index.IndexRequest; 12 | import org.elasticsearch.action.search.SearchResponse; 13 | import org.elasticsearch.client.Client; 14 | import org.elasticsearch.common.Base64; 15 | import org.elasticsearch.common.inject.Inject; 16 | import org.elasticsearch.common.settings.ImmutableSettings; 17 | import org.elasticsearch.common.settings.Settings; 18 | import org.elasticsearch.common.xcontent.support.XContentMapValues; 19 | import org.elasticsearch.index.query.FilterBuilders; 20 | import org.elasticsearch.index.query.FilteredQueryBuilder; 21 | import org.elasticsearch.index.query.QueryBuilders; 22 | import org.elasticsearch.indices.IndexAlreadyExistsException; 23 | import org.elasticsearch.river.AbstractRiverComponent; 24 | import org.elasticsearch.river.River; 25 | import org.elasticsearch.river.RiverName; 26 | import org.elasticsearch.river.RiverSettings; 27 | import org.elasticsearch.search.sort.FieldSortBuilder; 28 | import org.elasticsearch.search.sort.SortBuilders; 29 | import org.elasticsearch.search.sort.SortOrder; 30 | 31 | import java.io.IOException; 32 | import java.io.InputStream; 33 | import java.io.InputStreamReader; 34 | import java.net.HttpURLConnection; 35 | import java.net.URL; 36 | import java.net.URLConnection; 37 | import java.util.HashMap; 38 | import java.util.Map; 39 | import java.util.regex.Matcher; 40 | import java.util.regex.Pattern; 41 | 42 | import static org.elasticsearch.index.query.QueryBuilders.matchAllQuery; 43 | import static org.elasticsearch.index.query.QueryBuilders.termQuery; 44 | 45 | 46 | public class GitHubRiver extends AbstractRiverComponent implements River { 47 | 48 | private final Client client; 49 | private final String index; 50 | private final String repository; 51 | private final String owner; 52 | private final int userRequestedInterval; 53 | private final String endpoint; 54 | 55 | private String password; 56 | private String username; 57 | private DataStream dataStream; 58 | private String eventETag = null; 59 | private int pollInterval = 60; 60 | 61 | @SuppressWarnings({"unchecked"}) 62 | @Inject 63 | public GitHubRiver(RiverName riverName, RiverSettings settings, Client client) { 64 | super(riverName, settings); 65 | this.client = client; 66 | 67 | if (!settings.settings().containsKey("github")) { 68 | throw new IllegalArgumentException("Need river settings - owner and repository."); 69 | } 70 | 71 | // get settings 72 | Map githubSettings = (Map) settings.settings().get("github"); 73 | owner = XContentMapValues.nodeStringValue(githubSettings.get("owner"), null); 74 | repository = XContentMapValues.nodeStringValue(githubSettings.get("repository"), null); 75 | 76 | index = String.format("%s&%s", owner, repository); 77 | userRequestedInterval = XContentMapValues.nodeIntegerValue(githubSettings.get("interval"), 60); 78 | 79 | // auth (optional) 80 | username = null; 81 | password = null; 82 | if (githubSettings.containsKey("authentication")) { 83 | Map auth = (Map) githubSettings.get("authentication"); 84 | username = XContentMapValues.nodeStringValue(auth.get("username"), null); 85 | password = XContentMapValues.nodeStringValue(auth.get("password"), null); 86 | } 87 | 88 | // endpoint (optional - default to github.com) 89 | endpoint = XContentMapValues.nodeStringValue(githubSettings.get("endpoint"), "https://api.github.com"); 90 | 91 | logger.info("Created GitHub river."); 92 | } 93 | 94 | @Override 95 | public void start() { 96 | // create the index explicitly so we can use the whitespace tokenizer 97 | // because there are usernames like "user-name" and we want those 98 | // to be treated as just one term 99 | try { 100 | Settings indexSettings = ImmutableSettings.settingsBuilder().put("analysis.analyzer.default.tokenizer", "whitespace").build(); 101 | client.admin().indices().prepareCreate(index).setSettings(indexSettings).execute().actionGet(); 102 | logger.info("Created index."); 103 | } catch (IndexAlreadyExistsException e) { 104 | logger.info("Index already created"); 105 | } catch (Exception e) { 106 | logger.error("Exception creating index.", e); 107 | } 108 | dataStream = new DataStream(); 109 | dataStream.start(); 110 | logger.info("Started GitHub river."); 111 | } 112 | 113 | @Override 114 | public void close() { 115 | dataStream.setRunning(false); 116 | dataStream.interrupt(); 117 | logger.info("Stopped GitHub river."); 118 | } 119 | 120 | private class DataStream extends Thread { 121 | private volatile boolean isRunning; 122 | 123 | @Inject 124 | public DataStream() { 125 | super("DataStream thread"); 126 | isRunning = true; 127 | } 128 | 129 | private boolean checkAndUpdateETag(HttpURLConnection conn) throws IOException { 130 | if (eventETag != null) { 131 | conn.setRequestProperty("If-None-Match", eventETag); 132 | } 133 | 134 | String xPollInterval = conn.getHeaderField("X-Poll-Interval"); 135 | if (xPollInterval != null) { 136 | logger.debug("Next GitHub specified minimum polling interval is {} s", xPollInterval); 137 | pollInterval = Integer.parseInt(xPollInterval); 138 | } 139 | 140 | if (conn.getResponseCode() == 304) { 141 | logger.debug("304 {}", conn.getResponseMessage()); 142 | return false; 143 | } 144 | 145 | String eTag = conn.getHeaderField("ETag"); 146 | if (eTag != null) { 147 | logger.debug("New eTag: {}", eTag); 148 | eventETag = eTag; 149 | } 150 | 151 | return true; 152 | } 153 | 154 | private boolean indexResponse(HttpURLConnection conn, String type) { 155 | InputStream input; 156 | try { 157 | input = conn.getInputStream(); 158 | } catch (IOException e) { 159 | logger.info("Exception encountered (403 usually is rate limit exceeded): ", e); 160 | return false; 161 | } 162 | JsonStreamParser jsp = new JsonStreamParser(new InputStreamReader(input)); 163 | 164 | JsonArray array = (JsonArray) jsp.next(); 165 | 166 | BulkProcessor bp = BulkProcessor.builder(client, new BulkProcessor.Listener() { 167 | @Override 168 | public void beforeBulk(long executionId, BulkRequest request) { 169 | } 170 | 171 | @Override 172 | public void afterBulk(long executionId, BulkRequest request, BulkResponse response) { 173 | } 174 | 175 | @Override 176 | public void afterBulk(long executionId, BulkRequest request, Throwable failure) { 177 | } 178 | }).build(); 179 | 180 | boolean continueIndexing = true; 181 | 182 | IndexRequest req = null; 183 | for (JsonElement e: array) { 184 | if (type.equals("event")) { 185 | req = indexEvent(e); 186 | if (req == null) { 187 | continueIndexing = false; 188 | logger.debug("Found existing event, all remaining events has already been indexed"); 189 | break; 190 | } 191 | } else if (type.equals("issue")) { 192 | req = indexOther(e, "IssueData", true); 193 | } else if (type.equals("pullreq")) { 194 | req = indexOther(e, "PullRequestData"); 195 | } else if (type.equals("milestone")) { 196 | req = indexOther(e, "MilestoneData"); 197 | } else if (type.equals("label")) { 198 | req = indexOther(e, "LabelData"); 199 | } else if (type.equals("collaborator")) { 200 | req = indexOther(e, "CollaboratorData"); 201 | } 202 | bp.add(req); 203 | } 204 | bp.close(); 205 | 206 | try { 207 | input.close(); 208 | } catch (IOException e) { 209 | logger.warn("Couldn't close connection?", e); 210 | } 211 | 212 | return continueIndexing; 213 | } 214 | 215 | private boolean isEventIndexed(String id) { 216 | return client.prepareGet(index, null, id).get().isExists(); 217 | } 218 | 219 | private IndexRequest indexEvent(JsonElement e) { 220 | JsonObject obj = e.getAsJsonObject(); 221 | String type = obj.get("type").getAsString(); 222 | String id = obj.get("id").getAsString(); 223 | 224 | if (isEventIndexed(id)) { 225 | return null; 226 | } 227 | 228 | IndexRequest req = new IndexRequest(index) 229 | .type(type) 230 | .id(id).create(false) // we want to overwrite old items 231 | .source(e.toString()); 232 | return req; 233 | } 234 | 235 | private IndexRequest indexOther(JsonElement e, String type, boolean overwrite) { 236 | JsonObject obj = e.getAsJsonObject(); 237 | 238 | // handle objects that don't have IDs (i.e. labels) 239 | // set the ID to the MD5 hash of the string representation 240 | String id; 241 | if (obj.has("id")) { 242 | id = obj.get("id").getAsString(); 243 | } else { 244 | id = DigestUtils.md5Hex(e.toString()); 245 | } 246 | 247 | IndexRequest req = new IndexRequest(index) 248 | .type(type) 249 | .id(id).create(!overwrite) 250 | .source(e.toString()); 251 | return req; 252 | } 253 | 254 | private IndexRequest indexOther(JsonElement e, String type) { 255 | return indexOther(e, type, false); 256 | } 257 | 258 | private HashMap parseHeader(String header) { 259 | // inspired from https://github.com/uberVU/elasticboard/blob/4ccdfd8c8e772c1dda49a29a7487d14b8d820762/data_processor/github.py#L73 260 | Pattern p = Pattern.compile("\\<([a-z/0-9:\\.\\?_&=]+page=([0-9]+))\\>;\\s*rel=\\\"([a-z]+)\\\".*"); 261 | Matcher m = p.matcher(header); 262 | 263 | if (!m.matches()) { 264 | return null; 265 | } 266 | 267 | HashMap data = new HashMap(); 268 | data.put("url", m.group(1)); 269 | data.put("page", m.group(2)); 270 | data.put("rel", m.group(3)); 271 | 272 | return data; 273 | } 274 | 275 | private boolean morePagesAvailable(URLConnection response) { 276 | String link = response.getHeaderField("link"); 277 | if (link == null || link.length() == 0) { 278 | return false; 279 | } 280 | 281 | HashMap headerData = parseHeader(response.getHeaderField("link")); 282 | if (headerData == null) { 283 | return false; 284 | } 285 | 286 | String rel = headerData.get("rel"); 287 | return rel.equals("next"); 288 | } 289 | 290 | private String nextPageURL(URLConnection response) { 291 | HashMap headerData = parseHeader(response.getHeaderField("link")); 292 | if (headerData == null) { 293 | return null; 294 | } 295 | return headerData.get("url"); 296 | } 297 | 298 | private void addAuthHeader(URLConnection connection) { 299 | if (username == null || password == null) { 300 | return; 301 | } 302 | String auth = String.format("%s:%s", username, password); 303 | String encoded = Base64.encodeBytes(auth.getBytes()); 304 | connection.setRequestProperty("Authorization", "Basic " + encoded); 305 | } 306 | 307 | private boolean getData(String fmt, String type) { 308 | return getData(fmt, type, null); 309 | } 310 | 311 | private boolean getData(String fmt, String type, String since) { 312 | try { 313 | URL url; 314 | if (since != null) { 315 | url = new URL(String.format(fmt, owner, repository, since)); 316 | } else { 317 | url = new URL(String.format(fmt, owner, repository)); 318 | } 319 | HttpURLConnection connection = (HttpURLConnection) url.openConnection(); 320 | addAuthHeader(connection); 321 | if (type.equals("event")) { 322 | boolean modified = checkAndUpdateETag(connection); 323 | if (!modified) { 324 | return false; 325 | } 326 | } 327 | boolean continueIndexing = indexResponse(connection, type); 328 | 329 | while (continueIndexing && morePagesAvailable(connection)) { 330 | url = new URL(nextPageURL(connection)); 331 | connection = (HttpURLConnection) url.openConnection(); 332 | addAuthHeader(connection); 333 | continueIndexing = indexResponse(connection, type); 334 | } 335 | } catch (Exception e) { 336 | logger.error("Exception in getData", e); 337 | } 338 | 339 | return true; 340 | } 341 | 342 | private void deleteByType(String type) { 343 | client.prepareDeleteByQuery(index) 344 | .setQuery(termQuery("_type", type)) 345 | .execute() 346 | .actionGet(); 347 | } 348 | 349 | /** 350 | * Gets the creation data of the single newest entry. 351 | * 352 | * @return ISO8601 formatted time of most recent entry, or null on empty or error. 353 | */ 354 | private String getMostRecentEntry() { 355 | long totalEntries = client.prepareCount(index).setQuery(matchAllQuery()).execute().actionGet().getCount(); 356 | if (totalEntries > 0) { 357 | FilteredQueryBuilder updatedAtQuery = QueryBuilders 358 | .filteredQuery(QueryBuilders.matchAllQuery(), FilterBuilders.existsFilter("created_at")); 359 | FieldSortBuilder updatedAtSort = SortBuilders.fieldSort("created_at").order(SortOrder.DESC); 360 | 361 | SearchResponse response = client.prepareSearch(index) 362 | .setQuery(updatedAtQuery) 363 | .addSort(updatedAtSort) 364 | .setSize(1) 365 | .execute() 366 | .actionGet(); 367 | 368 | String createdAt = (String) response.getHits().getAt(0).getSource().get("created_at"); 369 | logger.debug("Most recent event was created at {}", createdAt); 370 | return createdAt; 371 | } else { 372 | // getData will get all data on a null. 373 | logger.info("No existing entries, assuming first run"); 374 | return null; 375 | } 376 | } 377 | 378 | @Override 379 | public void run() { 380 | while (isRunning) { 381 | // Must be read before getting new events. 382 | String mostRecentEntry = getMostRecentEntry(); 383 | 384 | logger.debug("Checking for events"); 385 | if (getData(endpoint + "/repos/%s/%s/events?per_page=1000", 386 | "event")) { 387 | logger.debug("First run or new events found, fetching rest of the data"); 388 | if (mostRecentEntry != null) { 389 | getData(endpoint + "/repos/%s/%s/issues?state=all&per_page=1000&since=%s", 390 | "issue", mostRecentEntry); 391 | } else { 392 | getData(endpoint + "/repos/%s/%s/issues?state=all&per_page=1000", 393 | "issue"); 394 | } 395 | // delete pull req data - we are only storing open pull reqs 396 | // and when a pull request is closed we have no way of knowing; 397 | // this is why we have to delete them and reindex "fresh" ones 398 | deleteByType("PullRequestData"); 399 | getData(endpoint + "/repos/%s/%s/pulls", "pullreq"); 400 | 401 | // same for milestones 402 | deleteByType("MilestoneData"); 403 | getData(endpoint + "/repos/%s/%s/milestones?per_page=1000", "milestone"); 404 | 405 | // collaborators 406 | deleteByType("CollaboratorData"); 407 | getData(endpoint + "/repos/%s/%s/collaborators?per_page=1000", "collaborator"); 408 | 409 | // and for labels - they have IDs based on the MD5 of the contents, so 410 | // if a property changes, we get a "new" document 411 | deleteByType("LabelData"); 412 | getData(endpoint + "/repos/%s/%s/labels?per_page=1000", "label"); 413 | } else { 414 | logger.debug("No new events found"); 415 | } 416 | try { 417 | int waitTime = Math.max(pollInterval, userRequestedInterval) * 1000; 418 | logger.debug("Waiting {} ms before polling for new events", waitTime); 419 | Thread.sleep(waitTime); // needs milliseconds 420 | } catch (InterruptedException e) { 421 | logger.info("Wait interrupted, river was probably stopped"); 422 | } 423 | } 424 | } 425 | 426 | public void setRunning(boolean running) { 427 | isRunning = running; 428 | } 429 | } 430 | } 431 | --------------------------------------------------------------------------------