Github user jfrazee commented on a diff in the pull request: https://github.com/apache/nifi/pull/1312#discussion_r102492802 --- Diff: nifi-nar-bundles/nifi-ccda-bundle/nifi-ccda-processors/src/main/java/org/apache/nifi/processors/ccda/ExtractCCDAAttributes.java --- @@ -0,0 +1,383 @@ +/* + * 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.ccda; + +import java.io.IOException; +import java.io.InputStream; +import java.io.OutputStream; +import java.util.ArrayList; +import java.util.HashMap; +import java.util.HashSet; +import java.util.LinkedHashMap; +import java.util.List; +import java.util.Map; +import java.util.Map.Entry; +import java.util.Properties; +import java.util.Set; +import java.util.TreeMap; + +import org.apache.commons.jexl3.JexlBuilder; +import org.apache.commons.jexl3.JexlContext; +import org.apache.commons.jexl3.JexlEngine; +import org.apache.commons.jexl3.JexlExpression; +import org.apache.commons.jexl3.MapContext; +import org.apache.commons.lang3.StringUtils; +import org.apache.nifi.annotation.behavior.InputRequirement; +import org.apache.nifi.annotation.behavior.InputRequirement.Requirement; +import org.apache.nifi.annotation.behavior.SideEffectFree; +import org.apache.nifi.annotation.behavior.SupportsBatching; +import org.apache.nifi.annotation.documentation.CapabilityDescription; +import org.apache.nifi.annotation.documentation.Tags; +import org.apache.nifi.components.PropertyDescriptor; +import org.apache.nifi.flowfile.FlowFile; +import org.apache.nifi.flowfile.attributes.CoreAttributes; +import org.apache.nifi.processor.AbstractProcessor; +import org.apache.nifi.processor.ProcessContext; +import org.apache.nifi.processor.ProcessSession; +import org.apache.nifi.processor.ProcessorInitializationContext; +import org.apache.nifi.processor.Relationship; +import org.apache.nifi.processor.exception.ProcessException; +import org.apache.nifi.processor.io.OutputStreamCallback; +import org.apache.nifi.processor.util.StandardValidators; +import org.eclipse.emf.common.util.Diagnostic; +import org.openhealthtools.mdht.uml.cda.CDAPackage; +import org.openhealthtools.mdht.uml.cda.ClinicalDocument; +import org.openhealthtools.mdht.uml.cda.ccd.CCDPackage; +import org.openhealthtools.mdht.uml.cda.consol.ConsolPackage; +import org.openhealthtools.mdht.uml.cda.hitsp.HITSPPackage; +import org.openhealthtools.mdht.uml.cda.ihe.IHEPackage; +import org.openhealthtools.mdht.uml.cda.util.CDAUtil; +import org.openhealthtools.mdht.uml.cda.util.CDAUtil.ValidationHandler; + +import com.google.gson.Gson; +import com.google.gson.GsonBuilder; + +@SideEffectFree +@SupportsBatching +@InputRequirement(Requirement.INPUT_REQUIRED) +@Tags({"CCDA", "healthcare", "extract", "JSON", "attributes"}) +@CapabilityDescription("Extracts information from an Consolidated CDA formatted FlowFile and provides JSON as FlowFile content " + + "and individual attributes as FlowFile attributes. The attributes are named as <Parent> <dot> <Key>. " + + "If the Parent is repeating, the naming will be <Parent> <underscore> <Parent Index> <dot> <Key>. " + + "For example, section.act_07.observation.name=Essential hypertension") +public class ExtractCCDAAttributes extends AbstractProcessor { + + private static final String APPLICATION_JSON = "application/json"; + private static final char FIELD_SEPARATOR = '@'; + private static final char KEY_VALUE_SEPARATOR = '#'; + + private Map<String, Map<String, String>> processMap = new LinkedHashMap<String, Map<String, String>>(); // stores mapping data for Parser + private List<String> timingStats = new ArrayList<String>(); // stores timing statistics + private Map<String, String> attributes = new TreeMap<String, String>(); // stores CDA attributes + private JexlEngine jexl = null; // JEXL Engine to execute code for mapping + private JexlContext jexlCtx = null; // JEXL Context to hold element being processed + + private List<PropertyDescriptor> properties; + private Set<Relationship> relationships; + + /** + * SKIP_VALIDATION - Indicates whether to validate the CDA document after loading. + * if true and the document is not valid, then ProcessException will be thrown + */ + public static final PropertyDescriptor SKIP_VALIDATION = new PropertyDescriptor.Builder().name("skip-validation") + .displayName("Skip Validation").description("Whether or not to validate CDA message values").required(true) + .allowableValues("true", "false").defaultValue("true").addValidator(StandardValidators.BOOLEAN_VALIDATOR) + .build(); + + /** + * PRETTY_PRINTING - Choice of whether generated JSON in the FileFlow content is + * pretty printed with new line and tabs or just a continuous string of characters + */ + public static final PropertyDescriptor PRETTY_PRINTING = new PropertyDescriptor.Builder().name("pretty-printing") + .displayName("Pretty Printing").description("Whether or not to Pretty Print JSON output").required(true) + .allowableValues("true", "false").defaultValue("false").addValidator(StandardValidators.BOOLEAN_VALIDATOR) + .build(); + + /** + * REL_SUCCESS - Value to be returned in case the processor succeeds + */ + public static final Relationship REL_SUCCESS = new Relationship.Builder() + .name("success") + .description("A FlowFile is routed to this relationship if it is properly parsed as CDA and its content stored in FlowFile") + .build(); + + /** + * REL_FAILURE - Value to be returned in case the processor fails + */ + public static final Relationship REL_FAILURE = new Relationship.Builder() + .name("failure") + .description("A FlowFile is routed to this relationship if it cannot be parse CDA and store content to FlowFile.") + .build(); + + @Override + protected List<PropertyDescriptor> getSupportedPropertyDescriptors() { + return properties; + } + + @Override + public Set<Relationship> getRelationships() { + return relationships; + } + + @Override + protected void init(final ProcessorInitializationContext context) { + getLogger().info("Loading packages"); + + relationships = new HashSet<>(); + relationships.add(REL_SUCCESS); + relationships.add(REL_FAILURE); + + properties = new ArrayList<>(); + properties.add(SKIP_VALIDATION); + properties.add(PRETTY_PRINTING); + + long start = System.currentTimeMillis(); + + // Load required MDHT packages + System.setProperty( "org.eclipse.emf.ecore.EPackage.Registry.INSTANCE", --- End diff -- Setup like this is usually put in a method with the @onScheduled annotation and init(). See [ScanAttribute.java](https://github.com/apache/nifi/blob/master/nifi-nar-bundles/nifi-standard-bundle/nifi-standard-processors/src/main/java/org/apache/nifi/processors/standard/ScanAttribute.java#L144) for an example.
--- 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. ---