├── .gitignore ├── src ├── main │ └── java │ │ └── pl │ │ └── schibsted │ │ └── flume │ │ └── interceptor │ │ └── json │ │ ├── JsonInterceptorSerializer.java │ │ ├── JsonInterceptorMillisecondFormatSerializer.java │ │ ├── JsonInterceptorPassThroughSerializer.java │ │ ├── JsonInterceptorDateTimeFormatSerializer.java │ │ ├── JsonInterceptorMillisSerializer.java │ │ └── JsonInterceptor.java └── test │ └── java │ └── pl │ └── schibsted │ └── flume │ └── interceptor │ └── json │ └── JsonInterceptorTest.java ├── README.md ├── pom.xml └── LICENSE /.gitignore: -------------------------------------------------------------------------------- 1 | # Created by .ignore support plugin (hsz.mobi) 2 | ### Java template 3 | *.class 4 | 5 | # Mobile Tools for Java (J2ME) 6 | .mtj.tmp/ 7 | 8 | # Package Files # 9 | *.jar 10 | *.war 11 | *.ear 12 | 13 | # virtual machine crash logs, see http://www.java.com/en/download/help/error_hotspot.xml 14 | hs_err_pid* 15 | 16 | 17 | ### Maven template 18 | target/ 19 | pom.xml.tag 20 | pom.xml.releaseBackup 21 | pom.xml.versionsBackup 22 | pom.xml.next 23 | release.properties 24 | dependency-reduced-pom.xml 25 | buildNumber.properties 26 | .mvn/timing.properties 27 | 28 | 29 | -------------------------------------------------------------------------------- /src/main/java/pl/schibsted/flume/interceptor/json/JsonInterceptorSerializer.java: -------------------------------------------------------------------------------- 1 | /* 2 | * Copyright 2015 Schibsted Tech Polska Sp. z o.o. 3 | * 4 | * Licensed under the Apache License, Version 2.0 (the "License"); 5 | * you may not use this file except in compliance with the License. 6 | * You may obtain a copy of the License at 7 | * 8 | * http://www.apache.org/licenses/LICENSE-2.0 9 | * 10 | * Unless required by applicable law or agreed to in writing, software 11 | * distributed under the License is distributed on an "AS IS" BASIS, 12 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | * See the License for the specific language governing permissions and 14 | * limitations under the License. 15 | */ 16 | package pl.schibsted.flume.interceptor.json; 17 | 18 | import org.apache.flume.conf.Configurable; 19 | import org.apache.flume.conf.ConfigurableComponent; 20 | 21 | public interface JsonInterceptorSerializer extends Configurable, 22 | ConfigurableComponent { 23 | 24 | String serialize(String value); 25 | } 26 | -------------------------------------------------------------------------------- /src/main/java/pl/schibsted/flume/interceptor/json/JsonInterceptorMillisecondFormatSerializer.java: -------------------------------------------------------------------------------- 1 | package pl.schibsted.flume.interceptor.json; 2 | 3 | import com.google.common.base.Preconditions; 4 | import org.apache.commons.lang.StringUtils; 5 | import org.apache.flume.Context; 6 | import org.apache.flume.conf.ComponentConfiguration; 7 | import org.joda.time.format.DateTimeFormat; 8 | import org.joda.time.format.DateTimeFormatter; 9 | 10 | public class JsonInterceptorMillisecondFormatSerializer implements JsonInterceptorSerializer { 11 | 12 | private DateTimeFormatter outputFormatter; 13 | 14 | @Override 15 | public void configure(Context context) { 16 | String outputPattern = context.getString("outputpattern"); 17 | Preconditions.checkArgument( 18 | !StringUtils.isEmpty(outputPattern), "Must configure with a valid outputpattern"); 19 | outputFormatter = DateTimeFormat.forPattern(outputPattern); 20 | } 21 | 22 | @Override 23 | public String serialize(String value) { 24 | Long millisecond = Long.valueOf(value); 25 | return outputFormatter.print(millisecond); 26 | } 27 | 28 | @Override 29 | public void configure(ComponentConfiguration componentConfiguration) { 30 | 31 | } 32 | } 33 | -------------------------------------------------------------------------------- /src/main/java/pl/schibsted/flume/interceptor/json/JsonInterceptorPassThroughSerializer.java: -------------------------------------------------------------------------------- 1 | /* 2 | * Copyright 2015 Schibsted Tech Polska Sp. z o.o. 3 | * 4 | * Licensed under the Apache License, Version 2.0 (the "License"); 5 | * you may not use this file except in compliance with the License. 6 | * You may obtain a copy of the License at 7 | * 8 | * http://www.apache.org/licenses/LICENSE-2.0 9 | * 10 | * Unless required by applicable law or agreed to in writing, software 11 | * distributed under the License is distributed on an "AS IS" BASIS, 12 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | * See the License for the specific language governing permissions and 14 | * limitations under the License. 15 | */ 16 | package pl.schibsted.flume.interceptor.json; 17 | 18 | import org.apache.flume.Context; 19 | import org.apache.flume.conf.ComponentConfiguration; 20 | 21 | public class JsonInterceptorPassThroughSerializer implements JsonInterceptorSerializer { 22 | 23 | 24 | @Override 25 | public String serialize(String value) { 26 | return value; 27 | } 28 | 29 | @Override 30 | public void configure(Context context) { 31 | } 32 | 33 | @Override 34 | public void configure(ComponentConfiguration conf) { 35 | } 36 | 37 | } 38 | -------------------------------------------------------------------------------- /src/main/java/pl/schibsted/flume/interceptor/json/JsonInterceptorDateTimeFormatSerializer.java: -------------------------------------------------------------------------------- 1 | package pl.schibsted.flume.interceptor.json; 2 | 3 | import org.apache.commons.lang.StringUtils; 4 | import org.apache.flume.Context; 5 | import org.apache.flume.conf.ComponentConfiguration; 6 | import org.joda.time.DateTime; 7 | import org.joda.time.format.DateTimeFormat; 8 | import org.joda.time.format.DateTimeFormatter; 9 | import com.google.common.base.Preconditions; 10 | 11 | public class JsonInterceptorDateTimeFormatSerializer implements 12 | JsonInterceptorSerializer { 13 | private DateTimeFormatter inputFormatter; 14 | private DateTimeFormatter outputFormatter; 15 | @Override 16 | public void configure(Context context) { 17 | String inputPattern = context.getString("inputpattern"); 18 | String outputPattern = context.getString("outputpattern"); 19 | Preconditions.checkArgument(!StringUtils.isEmpty(inputPattern), 20 | "Must configure with a valid inputpattern"); 21 | Preconditions.checkArgument(!StringUtils.isEmpty(outputPattern), 22 | "Must configure with a valid outputpattern"); 23 | inputFormatter = DateTimeFormat.forPattern(inputPattern); 24 | outputFormatter = DateTimeFormat.forPattern(outputPattern); 25 | } 26 | @Override 27 | public String serialize(String value) { 28 | DateTime dateTime = inputFormatter.parseDateTime(value); 29 | return outputFormatter.print(dateTime.getMillis()); 30 | } 31 | @Override 32 | public void configure(ComponentConfiguration conf) { 33 | } 34 | } 35 | -------------------------------------------------------------------------------- /src/main/java/pl/schibsted/flume/interceptor/json/JsonInterceptorMillisSerializer.java: -------------------------------------------------------------------------------- 1 | /* 2 | * Copyright 2015 Schibsted Tech Polska Sp. z o.o. 3 | * 4 | * Licensed under the Apache License, Version 2.0 (the "License"); 5 | * you may not use this file except in compliance with the License. 6 | * You may obtain a copy of the License at 7 | * 8 | * http://www.apache.org/licenses/LICENSE-2.0 9 | * 10 | * Unless required by applicable law or agreed to in writing, software 11 | * distributed under the License is distributed on an "AS IS" BASIS, 12 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | * See the License for the specific language governing permissions and 14 | * limitations under the License. 15 | */ 16 | package pl.schibsted.flume.interceptor.json; 17 | 18 | import org.apache.commons.lang.StringUtils; 19 | import org.apache.flume.Context; 20 | import org.apache.flume.conf.ComponentConfiguration; 21 | import org.joda.time.DateTime; 22 | import org.joda.time.format.DateTimeFormat; 23 | import org.joda.time.format.DateTimeFormatter; 24 | import com.google.common.base.Preconditions; 25 | 26 | public class JsonInterceptorMillisSerializer implements 27 | JsonInterceptorSerializer { 28 | private DateTimeFormatter formatter; 29 | @Override 30 | public void configure(Context context) { 31 | String pattern = context.getString("pattern"); 32 | Preconditions.checkArgument(!StringUtils.isEmpty(pattern), 33 | "Must configure with a valid pattern"); 34 | formatter = DateTimeFormat.forPattern(pattern); 35 | } 36 | @Override 37 | public String serialize(String value) { 38 | DateTime dateTime = formatter.parseDateTime(value); 39 | return Long.toString(dateTime.getMillis()); 40 | } 41 | @Override 42 | public void configure(ComponentConfiguration conf) { 43 | } 44 | } 45 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # flume-json-interceptor 2 | 3 | Flume JSON Interceptor Plugin extend Flume NG - now you can add headers getted from JSON document throught JSONPath. 4 | 5 | JSONPath is XPath for JSON. Specyfication: http://goessner.net/articles/JsonPath/ 6 | 7 | ## Compilation 8 | 9 | You can compile these using Maven (which you have to install first) by running 10 | 11 | ``` 12 | mvn clean package 13 | ``` 14 | 15 | from your command prompt. 16 | 17 | ## Installation 18 | 19 | Extract file `flume-json-interceptor-x.y.z-flume-plugin.tar` to directory: `plugins.d/flume-json-interceptor/`. 20 | 21 | If you use Cloudera Distrybution Hadoop, this will probably be `/usr/lib/flume-ng/plugins.d/plugins.d/flume-json-interceptor/`. 22 | 23 | ## Configuration 24 | 25 | Simple configuration to get element from `action` property and put it as header `action`. 26 | 27 | Example: 28 | 29 | ``` 30 | a1.sources.s1.interceptors = i1 31 | a1.sources.s1.interceptors.i1.type = pl.schibsted.flume.interceptor.json.JsonInterceptor$Builder 32 | a1.sources.s1.interceptors.i1.name = action 33 | a1.sources.s1.interceptors.i1.jsonpath = $.action 34 | ``` 35 | 36 | Configuration to get element from `published` property and put it as header `timestamp` throught serializer. 37 | 38 | Example: 39 | 40 | ``` 41 | a1.sources.s1.interceptors = i2 42 | a1.sources.s1.interceptors.i2.type = pl.schibsted.flume.interceptor.json.JsonInterceptor$Builder 43 | a1.sources.s1.interceptors.i2.name = timestamp 44 | a1.sources.s1.interceptors.i2.jsonpath = $.published 45 | a1.sources.s1.interceptors.i2.serializers = dt 46 | a1.sources.s1.interceptors.i2.serializers.dt.type=pl.schibsted.flume.interceptor.json.JsonInterceptorMillisSerializer 47 | a1.sources.s1.interceptors.i2.serializers.dt.pattern=yyyy-MM-dd'T'HH:mm:ssZ 48 | a1.sources.s1.interceptors.i2.serializers.dt.name=timestamp 49 | ``` 50 | 51 | Example JSON document: 52 | 53 | ``` 54 | { 55 | action: "pageview", 56 | published: "2015-05-06T12:34:54+02:00" 57 | } 58 | ``` 59 | 60 | ## Error handling 61 | 62 | 1. If specified JSONPath element not exists, event is passed without modifications. 63 | 64 | 2. If JSON is malformed, event is passed without modifications. 65 | 66 | 67 | 68 | 69 | -------------------------------------------------------------------------------- /pom.xml: -------------------------------------------------------------------------------- 1 | 2 | 5 | 4.0.0 6 | 7 | pl.schibsted.flume 8 | flume-json-interceptor 9 | 1.0.0 10 | jar 11 | 12 | Flume JSON Interceptor Plugin 13 | Flume JSON Interceptor Plugin 14 | 2015 15 | 16 | 17 | 1.5.2 18 | UTF-8 19 | 20 | 1.6 21 | 1.6 22 | 23 | true 24 | true 25 | 26 | 27 | 28 | scm:git:https://github.com/wojtekk/flume-json-interceptor.git 29 | scm:git:https://github.com/wojtekk/flume-json-interceptor.git 30 | scm:git:https://github.com/wojtekk/flume-json-interceptor.git 31 | 32 | 33 | 34 | GitHub 35 | https://github.com/wojtekk/flume-json-interceptor/issues 36 | 37 | 38 | 39 | 40 | The Apache Software License, Version 2.0 41 | http://www.apache.org/licenses/LICENSE-2.0.txt 42 | 43 | 44 | 45 | 46 | Schibsted Tech Polska 47 | http://www.schibsted.pl/ 48 | 49 | 50 | 51 | 52 | Wojciech Krawczyk 53 | wojtekk@gmail.com 54 | Schibsted Tech Polska 55 | 56 | 57 | 58 | 59 | 60 | 61 | org.apache.flume 62 | flume-parent 63 | ${flume.version} 64 | pom 65 | import 66 | 67 | 68 | 69 | 70 | 71 | 72 | org.apache.flume 73 | flume-ng-core 74 | 75 | 76 | junit 77 | junit-dep 78 | 4.10 79 | test 80 | 81 | 82 | com.nebhale.jsonpath 83 | jsonpath 84 | 1.2 85 | 86 | 87 | 88 | 89 | 90 | 91 | 92 | com.github.jrh3k5 93 | flume-plugin-maven-plugin 94 | 95 | 96 | build-project-plugin 97 | 98 | build-project-plugin 99 | 100 | 101 | 102 | 103 | 104 | org.pitest 105 | pitest-maven 106 | 1.1.5 107 | 108 | 109 | pl.schibsted.flume.interceptor.json* 110 | 111 | 112 | pl.schibsted.flume* 113 | 114 | 115 | 116 | 117 | 118 | 119 | 120 | -------------------------------------------------------------------------------- /src/main/java/pl/schibsted/flume/interceptor/json/JsonInterceptor.java: -------------------------------------------------------------------------------- 1 | /* 2 | * Copyright 2015 Schibsted Tech Polska Sp. z o.o. 3 | * 4 | * Licensed under the Apache License, Version 2.0 (the "License"); 5 | * you may not use this file except in compliance with the License. 6 | * You may obtain a copy of the License at 7 | * 8 | * http://www.apache.org/licenses/LICENSE-2.0 9 | * 10 | * Unless required by applicable law or agreed to in writing, software 11 | * distributed under the License is distributed on an "AS IS" BASIS, 12 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | * See the License for the specific language governing permissions and 14 | * limitations under the License. 15 | */ 16 | package pl.schibsted.flume.interceptor.json; 17 | 18 | import com.google.common.base.Preconditions; 19 | import com.google.common.base.Throwables; 20 | import com.google.common.base.Charsets; 21 | import com.nebhale.jsonpath.JsonPath; 22 | import org.apache.commons.lang.StringUtils; 23 | import org.apache.flume.Context; 24 | import org.apache.flume.Event; 25 | import org.apache.flume.interceptor.Interceptor; 26 | 27 | import java.util.ArrayList; 28 | import java.util.List; 29 | import java.util.Map; 30 | 31 | import org.slf4j.Logger; 32 | import org.slf4j.LoggerFactory; 33 | 34 | import static pl.schibsted.flume.interceptor.json.JsonInterceptor.Constants.CONFIG_SERIALIZERS; 35 | import static pl.schibsted.flume.interceptor.json.JsonInterceptor.Constants.CONFIG_HEADER_NAME; 36 | import static pl.schibsted.flume.interceptor.json.JsonInterceptor.Constants.CONFIG_HEADER_JSONPATH; 37 | import static pl.schibsted.flume.interceptor.json.JsonInterceptor.Constants.DEFAULT_SERIALIZER; 38 | import static pl.schibsted.flume.interceptor.json.JsonInterceptor.Constants.CONFIG_SERIALIZER_TYPE; 39 | import static pl.schibsted.flume.interceptor.json.JsonInterceptor.Constants.CONFIG_SERIALIZER_NAME; 40 | 41 | public class JsonInterceptor implements Interceptor { 42 | private static final Logger logger = 43 | LoggerFactory.getLogger(JsonInterceptor.class); 44 | 45 | private String headerName; 46 | private String headerJSONPath; 47 | private final JsonInterceptorSerializer serializer; 48 | 49 | public JsonInterceptor(String headerName, String headerJSONPath, JsonInterceptorSerializer serializer) { 50 | this.headerName = headerName; 51 | this.headerJSONPath = headerJSONPath; 52 | this.serializer = serializer; 53 | } 54 | 55 | @Override 56 | public void initialize() { 57 | } 58 | 59 | @Override 60 | public Event intercept(Event event) { 61 | try { 62 | 63 | String body = new String(event.getBody(), Charsets.UTF_8); 64 | Map headers = event.getHeaders(); 65 | //String value = JsonPath.read(body, headerJSONPath); 66 | JsonPath namePath = JsonPath.compile(headerJSONPath); 67 | String value = namePath.read(body,String.class); 68 | if (value != null) { 69 | headers.put(headerName, serializer.serialize(value)); 70 | } 71 | 72 | } catch (java.lang.ClassCastException e) { 73 | logger.warn("Skipping event due to: ClassCastException.", e); 74 | } catch (Exception e) { 75 | logger.warn("Skipping event due to: unknown error.", e); 76 | e.printStackTrace(); 77 | } 78 | return event; 79 | } 80 | 81 | @Override 82 | public List intercept(List events) { 83 | 84 | List interceptedEvents = new ArrayList(events.size()); 85 | for (Event event : events) { 86 | Event interceptedEvent = intercept(event); 87 | interceptedEvents.add(interceptedEvent); 88 | } 89 | 90 | return interceptedEvents; 91 | } 92 | 93 | @Override 94 | public void close() { 95 | } 96 | 97 | public static class Builder implements Interceptor.Builder { 98 | 99 | private String headerName; 100 | private String headerJSONPath; 101 | private JsonInterceptorSerializer serializer; 102 | private final JsonInterceptorSerializer defaultSerializer = new JsonInterceptorPassThroughSerializer(); 103 | 104 | @Override 105 | public void configure(Context context) { 106 | headerName = context.getString(CONFIG_HEADER_NAME); 107 | headerJSONPath = context.getString(CONFIG_HEADER_JSONPATH); 108 | 109 | configureSerializers(context); 110 | } 111 | 112 | @Override 113 | public JsonInterceptor build() { 114 | Preconditions.checkArgument(headerName != null, "Header name was misconfigured"); 115 | Preconditions.checkArgument(headerJSONPath != null, "Header JSONPath was misconfigured"); 116 | return new JsonInterceptor(headerName, headerJSONPath, serializer); 117 | } 118 | 119 | private void configureSerializers(Context context) { 120 | String serializerListStr = context.getString(CONFIG_SERIALIZERS); 121 | if (StringUtils.isEmpty(serializerListStr)) { 122 | serializer = defaultSerializer; 123 | return; 124 | } 125 | 126 | String[] serializerNames = serializerListStr.split("\\s+"); 127 | if (serializerNames.length > 1) { 128 | logger.warn("Only one serializer is supported."); 129 | } 130 | String serializerName = serializerNames[0]; 131 | 132 | Context serializerContexts = new Context(context.getSubProperties(CONFIG_SERIALIZERS + ".")); 133 | Context serializerContext = new Context(serializerContexts.getSubProperties(serializerName + ".")); 134 | 135 | String type = serializerContext.getString(CONFIG_SERIALIZER_TYPE, DEFAULT_SERIALIZER); 136 | String name = serializerContext.getString(CONFIG_SERIALIZER_NAME); 137 | 138 | Preconditions.checkArgument(!StringUtils.isEmpty(name), "Supplied name cannot be empty."); 139 | if (DEFAULT_SERIALIZER.equals(type)) { 140 | serializer = defaultSerializer; 141 | } else { 142 | serializer = getCustomSerializer(type, serializerContext); 143 | } 144 | 145 | } 146 | 147 | private JsonInterceptorSerializer getCustomSerializer(String clazzName, Context context) { 148 | try { 149 | JsonInterceptorSerializer serializer = (JsonInterceptorSerializer) Class 150 | .forName(clazzName).newInstance(); 151 | serializer.configure(context); 152 | return serializer; 153 | } catch (Exception e) { 154 | logger.error("Could not instantiate event serializer.", e); 155 | Throwables.propagate(e); 156 | } 157 | return defaultSerializer; 158 | } 159 | } 160 | 161 | 162 | public static class Constants { 163 | 164 | public static final String CONFIG_SERIALIZERS = "serializers"; 165 | public static final String DEFAULT_SERIALIZER = "DEFAULT"; 166 | public static final String CONFIG_HEADER_NAME = "name"; 167 | public static final String CONFIG_HEADER_JSONPATH = "jsonpath"; 168 | public static final String CONFIG_SERIALIZER_TYPE = "type"; 169 | public static final String CONFIG_SERIALIZER_NAME = "name"; 170 | } 171 | } 172 | -------------------------------------------------------------------------------- /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/test/java/pl/schibsted/flume/interceptor/json/JsonInterceptorTest.java: -------------------------------------------------------------------------------- 1 | /* 2 | * Copyright 2015 Schibsted Tech Polska Sp. z o.o. 3 | * 4 | * Licensed under the Apache License, Version 2.0 (the "License"); 5 | * you may not use this file except in compliance with the License. 6 | * You may obtain a copy of the License at 7 | * 8 | * http://www.apache.org/licenses/LICENSE-2.0 9 | * 10 | * Unless required by applicable law or agreed to in writing, software 11 | * distributed under the License is distributed on an "AS IS" BASIS, 12 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | * See the License for the specific language governing permissions and 14 | * limitations under the License. 15 | */ 16 | package pl.schibsted.flume.interceptor.json; 17 | 18 | import org.apache.flume.Context; 19 | import org.apache.flume.Event; 20 | import org.apache.flume.event.JSONEvent; 21 | 22 | import java.util.HashMap; 23 | import java.util.Map; 24 | 25 | import org.junit.Before; 26 | import org.junit.Test; 27 | import org.junit.runner.RunWith; 28 | import org.junit.runners.JUnit4; 29 | 30 | import static junit.framework.Assert.assertEquals; 31 | import static junit.framework.Assert.assertTrue; 32 | 33 | @RunWith(JUnit4.class) 34 | public class JsonInterceptorTest { 35 | 36 | @Before 37 | public void prepare() { 38 | } 39 | 40 | private JsonInterceptor getInterceptor(Context context) { 41 | JsonInterceptor.Builder interceptorBuilder = new JsonInterceptor.Builder(); 42 | interceptorBuilder.configure(context); 43 | 44 | JsonInterceptor interceptor = interceptorBuilder.build(); 45 | interceptor.initialize(); 46 | return interceptor; 47 | } 48 | 49 | private String getDefaultEventBody() { 50 | return "{ " + 51 | "\"pageViewId\":\"4eae0122-052d-41ff-ac5c-120279891184\"," + 52 | "\"published\":\"2015-04-23T01:37:09+00:00\"," + 53 | "\"finished\":\"1429753029000\"," + 54 | "\"params\": {" + 55 | "\"v1\":\"1\"," + 56 | "\"v2\":\"2\"," + 57 | "\"v3\":\"3\"" + 58 | "}" + 59 | " }"; 60 | } 61 | 62 | private String getInvalidEventBody() { 63 | return "{ \"pageViewId\":\"4eae0122-052d-41ff-ac5c-120279891184\","; 64 | } 65 | 66 | private Event getEvent(Map headers, String body) { 67 | Event event = new JSONEvent(); 68 | event.setBody(body.getBytes()); 69 | event.setHeaders(headers); 70 | return event; 71 | } 72 | 73 | private Context getDefaultContext(String headerName, String headerJSONPath) { 74 | Context context = new Context(); 75 | context.put("serializers", "s1"); 76 | context.put("serializers.s1.name", "s1"); 77 | if (!headerName.isEmpty()) { 78 | context.put("name", headerName); 79 | } 80 | if (!headerJSONPath.isEmpty()) { 81 | context.put("jsonpath", headerJSONPath); 82 | } 83 | return context; 84 | } 85 | 86 | @Test 87 | public void testBasicChecks() { 88 | 89 | String headerName = "testName"; 90 | String headerJSONPath = "$.published"; 91 | 92 | Map headers = new HashMap(1); 93 | headers.put("existingKey", "existingValue"); 94 | 95 | String body = getDefaultEventBody(); 96 | Event event = getEvent(headers, body); 97 | 98 | Context context = getDefaultContext(headerName, headerJSONPath); 99 | 100 | JsonInterceptor interceptor = getInterceptor(context); 101 | 102 | Event interceptedEvent = 103 | interceptor.intercept(event); 104 | 105 | assertEquals("Event body should not have been altered", 106 | body, 107 | new String(interceptedEvent.getBody())); 108 | 109 | assertTrue("Header should now contain " + headerName, 110 | interceptedEvent.getHeaders().containsKey(headerName)); 111 | 112 | String published = "2015-04-23T01:37:09+00:00"; 113 | 114 | assertEquals("Header's " + headerName + " should be correct", 115 | published, 116 | interceptedEvent.getHeaders().get(headerName)); 117 | 118 | } 119 | 120 | @Test 121 | public void testIncorrectJSONPathShoudNotChangeEvent() { 122 | 123 | String headerName = "testName"; 124 | String headerJSONPath = "$.notExists"; 125 | 126 | Map headers = new HashMap(1); 127 | headers.put("existingKey", "existingValue"); 128 | 129 | String body = getDefaultEventBody(); 130 | Event event = getEvent(headers, body); 131 | 132 | Context context = getDefaultContext(headerName, headerJSONPath); 133 | 134 | JsonInterceptor interceptor = getInterceptor(context); 135 | 136 | Event interceptedEvent = interceptor.intercept(event); 137 | 138 | assertEquals(interceptedEvent, event); 139 | } 140 | 141 | @Test 142 | public void testNonScalarResultShoudNotChangeEvent() { 143 | 144 | String headerName = "testName"; 145 | String headerJSONPath = "$.params"; 146 | 147 | Map headers = new HashMap(1); 148 | headers.put("existingKey", "existingValue"); 149 | 150 | String body = getDefaultEventBody(); 151 | Event event = getEvent(headers, body); 152 | 153 | Context context = getDefaultContext(headerName, headerJSONPath); 154 | 155 | JsonInterceptor interceptor = getInterceptor(context); 156 | 157 | Event interceptedEvent = interceptor.intercept(event); 158 | 159 | assertEquals(interceptedEvent, event); 160 | } 161 | 162 | @Test 163 | public void testInvalidEventBodyShoudNotChangeEvent() { 164 | 165 | String headerName = "testName"; 166 | String headerJSONPath = "$.published"; 167 | 168 | Map headers = new HashMap(1); 169 | headers.put("existingKey", "existingValue"); 170 | 171 | String body = getInvalidEventBody(); 172 | Event event = getEvent(headers, body); 173 | 174 | Context context = getDefaultContext(headerName, headerJSONPath); 175 | 176 | JsonInterceptor interceptor = getInterceptor(context); 177 | 178 | Event interceptedEvent = interceptor.intercept(event); 179 | 180 | assertEquals(interceptedEvent, event); 181 | } 182 | 183 | @Test(expected = java.lang.IllegalArgumentException.class) 184 | public void testMissedHeaderName() { 185 | 186 | String headerName = ""; 187 | String headerJSONPath = "$.published"; 188 | 189 | Map headers = new HashMap(1); 190 | headers.put("existingKey", "existingValue"); 191 | 192 | String body = getInvalidEventBody(); 193 | Event event = getEvent(headers, body); 194 | 195 | Context context = getDefaultContext(headerName, headerJSONPath); 196 | 197 | JsonInterceptor interceptor = getInterceptor(context); 198 | 199 | interceptor.intercept(event); 200 | } 201 | 202 | @Test(expected = java.lang.IllegalArgumentException.class) 203 | public void testMissedJSONPath() { 204 | 205 | String headerName = "testName"; 206 | String headerJSONPath = ""; 207 | 208 | Map headers = new HashMap(1); 209 | headers.put("existingKey", "existingValue"); 210 | 211 | String body = getInvalidEventBody(); 212 | Event event = getEvent(headers, body); 213 | 214 | Context context = getDefaultContext(headerName, headerJSONPath); 215 | 216 | JsonInterceptor interceptor = getInterceptor(context); 217 | 218 | interceptor.intercept(event); 219 | } 220 | 221 | @Test 222 | public void testMillisSerializer() { 223 | 224 | String headerName = "testName"; 225 | String headerJSONPath = "$.published"; 226 | 227 | Map headers = new HashMap(1); 228 | headers.put("existingKey", "existingValue"); 229 | 230 | String body = getDefaultEventBody(); 231 | Event event = getEvent(headers, body); 232 | 233 | Context context = getDefaultContext(headerName, headerJSONPath); 234 | context.put("serializers.s1.type", "pl.schibsted.flume.interceptor.json.JsonInterceptorMillisSerializer"); 235 | context.put("serializers.s1.pattern", "yyyy-MM-dd'T'HH:mm:ssZ"); 236 | 237 | JsonInterceptor interceptor = getInterceptor(context); 238 | 239 | Event interceptedEvent = interceptor.intercept(event); 240 | 241 | assertEquals("Event body should not have been altered", 242 | body, 243 | new String(interceptedEvent.getBody())); 244 | 245 | assertTrue("Header should now contain " + headerName, 246 | interceptedEvent.getHeaders().containsKey(headerName)); 247 | 248 | String published = "1429753029000"; // => 2015-04-23T01:37:09+00:00 249 | 250 | assertEquals("Header's " + headerName + " should be correct", 251 | published, 252 | interceptedEvent.getHeaders().get(headerName)); 253 | } 254 | 255 | @Test 256 | public void testDateTimeFormatSerializer() { 257 | 258 | String headerName = "testName"; 259 | String headerJSONPath = "$.published"; 260 | 261 | Map headers = new HashMap(1); 262 | headers.put("existingKey", "existingValue"); 263 | 264 | String body = getDefaultEventBody(); 265 | Event event = getEvent(headers, body); 266 | 267 | Context context = getDefaultContext(headerName, headerJSONPath); 268 | context.put("serializers.s1.type", "pl.schibsted.flume.interceptor.json.JsonInterceptorDateTimeFormatSerializer"); 269 | context.put("serializers.s1.inputpattern", "yyyy-MM-dd'T'HH:mm:ssZ"); 270 | context.put("serializers.s1.outputpattern", "yyyy-MM-dd HH:mm:ss"); 271 | 272 | JsonInterceptor interceptor = getInterceptor(context); 273 | 274 | Event interceptedEvent = interceptor.intercept(event); 275 | 276 | assertEquals("Event body should not have been altered", 277 | body, 278 | new String(interceptedEvent.getBody())); 279 | 280 | assertTrue("Header should now contain " + headerName, 281 | interceptedEvent.getHeaders().containsKey(headerName)); 282 | 283 | String published = "2015-04-22 20:37:09"; // => 2015-04-23T01:37:09+00:00 284 | 285 | assertEquals("Header's " + headerName + " should be correct", 286 | published, 287 | interceptedEvent.getHeaders().get(headerName)); 288 | } 289 | 290 | @Test 291 | public void testMillisecondFormatSerializer(){ 292 | String headerName = "testName"; 293 | String headerJSONPath = "$.finished"; 294 | 295 | Map headers = new HashMap(1); 296 | headers.put("existingKey", "existingValue"); 297 | 298 | String body = getDefaultEventBody(); 299 | Event event = getEvent(headers, body); 300 | 301 | Context context = getDefaultContext(headerName, headerJSONPath); 302 | context.put("serializers.s1.type", "pl.schibsted.flume.interceptor.json.JsonInterceptorMillisecondFormatSerializer"); 303 | context.put("serializers.s1.outputpattern", "yyyy-MM-dd HH:mm:ss"); 304 | 305 | JsonInterceptor interceptor = getInterceptor(context); 306 | 307 | Event interceptedEvent = interceptor.intercept(event); 308 | 309 | assertEquals("Event body should not have been altered", 310 | body, 311 | new String(interceptedEvent.getBody())); 312 | 313 | assertTrue("Header should now contain " + headerName, 314 | interceptedEvent.getHeaders().containsKey(headerName)); 315 | 316 | String finished = "2015-04-23 09:37:09"; 317 | 318 | assertEquals("Header's " + headerName + " should be correct", 319 | finished, 320 | interceptedEvent.getHeaders().get(headerName)); 321 | } 322 | 323 | } 324 | --------------------------------------------------------------------------------