Github user markap14 commented on a diff in the pull request: https://github.com/apache/nifi/pull/1108#discussion_r83227771 --- Diff: nifi-nar-bundles/nifi-standard-bundle/nifi-standard-processors/src/main/java/org/apache/nifi/processors/standard/GrokParser.java --- @@ -0,0 +1,243 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.nifi.processors.standard; + +import com.fasterxml.jackson.databind.ObjectMapper; +import oi.thekraken.grok.api.Grok; +import oi.thekraken.grok.api.Match; +import oi.thekraken.grok.api.exception.GrokException; +import org.apache.nifi.annotation.behavior.ReadsAttribute; +import org.apache.nifi.annotation.behavior.ReadsAttributes; +import org.apache.nifi.annotation.behavior.WritesAttribute; +import org.apache.nifi.annotation.behavior.WritesAttributes; +import org.apache.nifi.annotation.documentation.CapabilityDescription; +import org.apache.nifi.annotation.documentation.SeeAlso; +import org.apache.nifi.annotation.documentation.Tags; +import org.apache.nifi.annotation.lifecycle.OnScheduled; +import org.apache.nifi.components.PropertyDescriptor; +import org.apache.nifi.flowfile.attributes.CoreAttributes; +import org.apache.nifi.flowfile.FlowFile; + +import org.apache.nifi.processor.AbstractProcessor; +import org.apache.nifi.processor.DataUnit; +import org.apache.nifi.processor.ProcessorInitializationContext; +import org.apache.nifi.processor.Relationship; +import org.apache.nifi.processor.ProcessContext; +import org.apache.nifi.processor.ProcessSession; +import org.apache.nifi.processor.exception.ProcessException; +import org.apache.nifi.processor.io.InputStreamCallback; +import org.apache.nifi.processor.io.StreamCallback; +import org.apache.nifi.processor.util.StandardValidators; +import org.apache.nifi.stream.io.BufferedOutputStream; +import org.apache.nifi.stream.io.StreamUtils; +import java.io.IOException; +import java.io.InputStream; +import java.io.OutputStream; +import java.nio.charset.Charset; +import java.util.List; +import java.util.Map; +import java.util.HashMap; +import java.util.Set; +import java.util.HashSet; +import java.util.ArrayList; +import java.util.Collections; + + +@Tags({"Grok Processor"}) +@CapabilityDescription("Use Grok expression ,a la logstash, to parse data.") +@SeeAlso({}) +@ReadsAttributes({@ReadsAttribute(attribute="", description="")}) +@WritesAttributes({@WritesAttribute(attribute="", description="")}) +public class GrokParser extends AbstractProcessor { + + + public static final String DESTINATION_ATTRIBUTE = "flowfile-attribute"; + public static final String DESTINATION_CONTENT = "flowfile-content"; + private static final String APPLICATION_JSON = "application/json"; + + public static final PropertyDescriptor GROK_EXPRESSION = new PropertyDescriptor + .Builder().name("Grok Expression") + .description("Grok expression") + .required(true) + .addValidator(StandardValidators.NON_EMPTY_VALIDATOR) + .build(); + + public static final PropertyDescriptor GROK_PATTERN_FILE = new PropertyDescriptor + .Builder().name("Grok Pattern file") + .description("Grok Pattern file definition") + .required(false) + .addValidator(StandardValidators.FILE_EXISTS_VALIDATOR) + .build(); + + public static final PropertyDescriptor DESTINATION = new PropertyDescriptor.Builder() + .name("Destination") + .description("Control if Grok output value is written as a new flowfile attribute " + + "or written in the flowfile content. Writing to flowfile content will overwrite any " + + "existing flowfile content.") + .required(true) + .allowableValues(DESTINATION_ATTRIBUTE, DESTINATION_CONTENT) + .defaultValue(DESTINATION_ATTRIBUTE) + .build(); + + public static final PropertyDescriptor CHARACTER_SET = new PropertyDescriptor + .Builder().name("Character Set") + .description("The Character Set in which the file is encoded") + .required(true) + .addValidator(StandardValidators.CHARACTER_SET_VALIDATOR) + .defaultValue("UTF-8") + .build(); + + public static final PropertyDescriptor MAX_BUFFER_SIZE = new PropertyDescriptor + .Builder().name("Maximum Buffer Size") + .description("Specifies the maximum amount of data to buffer (per file) in order to apply the Grok expressions. Files larger than the specified maximum will not be fully evaluated.") + .required(true) + .addValidator(StandardValidators.DATA_SIZE_VALIDATOR) + .addValidator(StandardValidators.createDataSizeBoundsValidator(0, Integer.MAX_VALUE)) + .defaultValue("1 MB") + .build(); + + public static final Relationship REL_MATCH = new Relationship.Builder() + .name("matched") + .description("FlowFiles are routed to this relationship when the Grok Expression is successfully evaluated and the FlowFile is modified as a result") + .build(); + + public static final Relationship REL_NO_MATCH = new Relationship.Builder() + .name("unmatched") + .description("FlowFiles are routed to this relationship when no provided Grok Expression matches the content of the FlowFile") + .build(); + + private List<PropertyDescriptor> descriptors; + + private Set<Relationship> relationships; + + private static final ObjectMapper objectMapper = new ObjectMapper(); + + private Grok grok; --- End diff -- These member variables are not thread-safe. They should be defined inline where needed, or properly protected via Java's concurrency mechanisms.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. ---