[
https://issues.apache.org/jira/browse/NIFI-1156?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15094274#comment-15094274
]
ASF GitHub Bot commented on NIFI-1156:
--------------------------------------
Github user markap14 commented on a diff in the pull request:
https://github.com/apache/nifi/pull/124#discussion_r49480952
--- Diff:
nifi-nar-bundles/nifi-html-bundle/nifi-html-processors/src/main/java/org/apache/nifi/PutHTMLElement.java
---
@@ -0,0 +1,150 @@
+/*
+ * 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;
+
+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.components.PropertyDescriptor;
+import org.apache.nifi.flowfile.FlowFile;
+import org.apache.nifi.processor.ProcessContext;
+import org.apache.nifi.processor.ProcessSession;
+import org.apache.nifi.processor.Relationship;
+import org.apache.nifi.processor.ProcessorInitializationContext;
+import org.apache.nifi.processor.exception.ProcessException;
+import org.apache.nifi.processor.io.StreamCallback;
+import org.apache.nifi.processor.util.StandardValidators;
+import org.jsoup.nodes.Document;
+import org.jsoup.nodes.Element;
+import org.jsoup.select.Elements;
+
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.OutputStream;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Set;
+import java.util.HashSet;
+import java.util.Collections;
+
+@Tags({"put", "html", "dom", "css", "element"})
+@CapabilityDescription("Creates a new HTML element in the input HTML")
+@SeeAlso({GetHTMLElement.class, ModifyHTMLElement.class})
+public class PutHTMLElement extends AbstractHTMLProcessor {
+
+ public static final String APPEND_ELEMENT = "append-html";
+ public static final String PREPEND_ELEMENT = "prepend-html";
+
+ public static final PropertyDescriptor PUT_LOCATION_TYPE = new
PropertyDescriptor.Builder()
+ .name("Element Insert Location Type")
+ .description("Controls whether the new element is prepended or
appended to the children of the " +
+ "Element located by the CSS selector. EX: prepended
value '<b>Hi</b>' inside of " +
+ "Element (using CSS Selector 'p') '<p>There</p>' would
result in " +
+ "'<p><b>Hi</b>There</p>'. Appending the value would
result in '<p>There<b>Hi</b></p>'")
+ .required(true)
+ .allowableValues(APPEND_ELEMENT, PREPEND_ELEMENT)
+ .defaultValue(APPEND_ELEMENT)
+ .build();
+
+ public static final PropertyDescriptor PUT_VALUE = new
PropertyDescriptor.Builder()
+ .name("Put Value")
+ .description("Value used when creating the new Element. Value
should be a valid HTML element. " +
+ "The text should be supplied unencoded: characters
like '<', '>', etc will be properly HTML " +
+ "encoded in the output.")
+ .required(true)
+ .addValidator(StandardValidators.NON_EMPTY_VALIDATOR)
+ .expressionLanguageSupported(true)
+ .build();
+
+ private List<PropertyDescriptor> descriptors;
+
+ private Set<Relationship> relationships;
+
+ @Override
+ protected void init(final ProcessorInitializationContext context) {
+ final List<PropertyDescriptor> descriptors = new
ArrayList<PropertyDescriptor>();
+ descriptors.add(URL);
+ descriptors.add(CSS_SELECTOR);
+ descriptors.add(HTML_CHARSET);
+ descriptors.add(PUT_LOCATION_TYPE);
+ descriptors.add(PUT_VALUE);
+ this.descriptors = Collections.unmodifiableList(descriptors);
+
+ final Set<Relationship> relationships = new
HashSet<Relationship>();
+ relationships.add(REL_ORIGINAL);
+ relationships.add(REL_SUCCESS);
+ relationships.add(REL_FAILURE);
+ relationships.add(REL_INVALID_HTML);
+ this.relationships = Collections.unmodifiableSet(relationships);
+ }
+
+ @Override
+ public Set<Relationship> getRelationships() {
+ return this.relationships;
+ }
+
+ @Override
+ public final List<PropertyDescriptor>
getSupportedPropertyDescriptors() {
+ return descriptors;
+ }
+
+ @Override
+ public void onTrigger(final ProcessContext context, final
ProcessSession session) throws ProcessException {
+ final FlowFile flowFile = session.get();
+ if (flowFile == null) {
+ return;
+ }
+
+ try {
+ final Document doc = parseHTMLDocumentFromFlowfile(flowFile,
context, session);
+ final Elements eles =
doc.select(context.getProperty(CSS_SELECTOR).evaluateAttributeExpressions().getValue());
+
+ if (eles == null || eles.size() == 0) {
+ //No element found
+ session.transfer(flowFile, REL_NOT_FOUND);
+ } else {
+ for (Element ele : eles) {
+ switch
(context.getProperty(PUT_LOCATION_TYPE).getValue()) {
+ case APPEND_ELEMENT:
+
ele.append(context.getProperty(PUT_VALUE).evaluateAttributeExpressions().getValue());
--- End diff --
This should call evaluateAttributeExpressions(flowFile) so that we can take
into account FlowFile Attributes.
> HTML Parsing Processors Bundle
> ------------------------------
>
> Key: NIFI-1156
> URL: https://issues.apache.org/jira/browse/NIFI-1156
> Project: Apache NiFi
> Issue Type: New Feature
> Components: Core Framework
> Reporter: Jeremy Dyer
> Priority: Minor
>
> NiFi provides the ability to ingest HTML but lacks the convenience to easily
> interact with that HTML once it has entered the flow. There should be a HTML
> Processing Bundle that provides mechanisms for manipulating and interacting
> with HTML data once it has entered the flow. Jsoup http://jsoup.org/ seems
> like a logical tool to use since it is mature and has a MIT license which
> would allow it to be incorporated into NiFi.
> “GetHTMLElement” should use the CSS selector-syntax
> (http://www.w3schools.com/cssref/css_selectors.asp) built into Jsoup to
> extract 0-N HTML elements from the original HTML input. This processor should
> support a delimited string of selectors allowing the user to build compound
> HTML element output. Each HTML element (or compound element result) extracted
> will create a new Flowfile where the element will be in either the Flowfile
> content or an attribute depending on the user configuration.
> “ModifyHTMLElement” should provide the ability to modify the original input
> HTML and overwrite any existing element values. The HTML element that will be
> modified can be selected by using the CSS selector-syntax
> “PutHTMLElement” should provide the ability to put a new HTML element
> anywhere in the original input HTML using CSS selector-syntax to indicate the
> position that the new HTML element should be placed.
> There seems to be a potential for adding more processors but this seems like
> a good start. Since there is a dependency on Jsoup and a potential for more
> processors to come I think it makes sense to add this logic as its own nar
> bundle but I could be wrong.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
