Github user jfrazee commented on a diff in the pull request:
https://github.com/apache/nifi/pull/1312#discussion_r102500181
--- 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",
+ "org.eclipse.emf.ecore.impl.EPackageRegistryImpl" );
+ CDAPackage.eINSTANCE.eClass();
+ HITSPPackage.eINSTANCE.eClass();
+ CCDPackage.eINSTANCE.eClass();
+ ConsolPackage.eINSTANCE.eClass();
+ IHEPackage.eINSTANCE.eClass();
+ timingStats.add(String.format("Loaded packages in %d ms",
System.currentTimeMillis() - start));
+
+ // Initialize JEXL
+ jexl = new
JexlBuilder().cache(1024).debug(false).silent(true).strict(false).create();
+ jexlCtx = new MapContext();
+
+ getLogger().info("Loading mappings");
+ loadMappings(); // Load CDA mappings for parser
+
+ }
+
+ @Override
+ public void onTrigger(final ProcessContext context, final
ProcessSession session) {
+ getLogger().info("Processing CCDA");
+
+ FlowFile flowFile = session.get();
+ if ( flowFile == null ) {
+ return;
+ }
+
+ if(processMap.isEmpty()) {
+ getLogger().error("Process Mapping is not loaded");
+ session.transfer(flowFile, REL_FAILURE);
+ return;
+ }
+
+ final Boolean skipValidation =
context.getProperty(SKIP_VALIDATION).asBoolean();
+ final Boolean prettyPrinting =
context.getProperty(PRETTY_PRINTING).asBoolean();
+
+ long start = System.currentTimeMillis(), total = start;
+
+ ClinicalDocument cd = loadDocument(session.read(flowFile),
skipValidation); // Load and optionally validate CDA document
+
+ start = System.currentTimeMillis();
+ getLogger().info("Processing elements");
+ Map<String, Object> elements = processElement(null, cd); //
Process CDA element using mapping data
+
+ start = System.currentTimeMillis();
+ getLogger().info("Generating JSON");
+
+ // Initialize GSON with optional pretty printing
+ Gson gson = prettyPrinting ? new
GsonBuilder().setPrettyPrinting().create() : new GsonBuilder().create();
+ String json = gson.toJson(elements);
+ timingStats.add(String.format("JSON created in %d ms",
System.currentTimeMillis() - start));
+ timingStats.add(String.format("CCDA Processed in %d ms",
System.currentTimeMillis() - total));
+
+ logDetails(json);
+
+ flowFile = session.write(flowFile, new OutputStreamCallback() {
+
+ @Override
+ public void process(OutputStream output) throws IOException {
+ output.write(json.getBytes("UTF-8"));
+ }
+ });
+ flowFile = session.putAttribute(flowFile,
CoreAttributes.MIME_TYPE.key(), APPLICATION_JSON);
+ flowFile = session.putAllAttributes(flowFile, attributes);
+
+ session.transfer(flowFile, REL_SUCCESS);
+
+ }
+
+ /**
+ * Process elements children based on the parser mapping.
+ * Any String values are added to attributes and JSON map
+ * For List, the processList method is called to iterate and process
+ * For an Object this method is called recursively
+ * While adding to the attributes the key is prefixed by parent
+ * @param parent Parent key for this element, used as a prefix for
attribute key
+ * @param element Element to be processed
+ * @return Map of processed data, value can contain String or
Map of Strings
+ */
+ protected Map<String, Object> processElement(String parent, Object
element) {
+ long start = System.currentTimeMillis();
+
+ Map<String, Object> map = new LinkedHashMap<String, Object>();
+ String name = element.getClass().getName();
+ Map<String, String> jexlMap = (HashMap<String, String>)
processMap.get(name); // get JEXL mappings for this element
+ getLogger().debug("Processing " + name);
+
+ if (jexlMap == null) {
+ getLogger().info("Missing mapping for element " + name);
--- End diff --
Seems like this should be a warn() or error(). What's the impact here/what
happens if this returns null? Seems like it'll mean addElement() never gets
called so no attributes will be added; i.e., if there's a single missing
mapping the processing short circuits but it still transfers to REL_SUCCESS. Is
this right?
---
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.
---
