[ 
https://issues.apache.org/jira/browse/NIFI-1899?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15367880#comment-15367880
 ] 

ASF GitHub Bot commented on NIFI-1899:
--------------------------------------

Github user JPercivall commented on a diff in the pull request:

    https://github.com/apache/nifi/pull/483#discussion_r70097725
  
    --- Diff: 
nifi-nar-bundles/nifi-email-bundle/nifi-email-processors/src/main/java/org/apache/nifi/processors/email/ExtractEmailAttachments.java
 ---
    @@ -0,0 +1,201 @@
    +/*
    + * 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.email;
    +
    +import java.io.IOException;
    +import java.io.InputStream;
    +import java.io.OutputStream;
    +import java.util.ArrayList;
    +import java.util.Collections;
    +import java.util.HashMap;
    +import java.util.HashSet;
    +import java.util.List;
    +import java.util.Map;
    +import java.util.Properties;
    +import java.util.Set;
    +import java.util.Date;
    +
    +import javax.activation.DataSource;
    +import javax.mail.Address;
    +import javax.mail.MessagingException;
    +import javax.mail.Session;
    +import javax.mail.internet.MimeMessage;
    +
    +import org.apache.commons.io.IOUtils;
    +import org.apache.commons.lang3.StringUtils;
    +import org.apache.commons.mail.util.MimeMessageParser;
    +
    +
    +import org.apache.nifi.annotation.behavior.EventDriven;
    +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.WritesAttribute;
    +import org.apache.nifi.annotation.behavior.WritesAttributes;
    +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.logging.ComponentLog;
    +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.io.InputStreamCallback;
    +import org.apache.nifi.processor.io.OutputStreamCallback;
    +import org.apache.nifi.stream.io.BufferedInputStream;
    +
    +
    +
    +
    +@EventDriven
    +@SideEffectFree
    +@Tags({"split", "email"})
    +@InputRequirement(Requirement.INPUT_REQUIRED)
    +@CapabilityDescription("Extract attachments from a mime formatted email 
file, splitting them into individual flowfiles.")
    +@WritesAttributes({
    +        @WritesAttribute(attribute = "filename ", description = "The 
filename of the attachment"),
    +        @WritesAttribute(attribute = "email.attachment.parent.filename ", 
description = "The filename of the parent FlowFile"),
    +        @WritesAttribute(attribute = "email.attachment.parent.uuid", 
description = "The UUID of the original FlowFile."),
    +        @WritesAttribute(attribute = "mime.type", description = "The mime 
type of the attachment.")})
    +
    +public class ExtractEmailAttachments extends AbstractProcessor {
    +    public static final String ATTACHMENT_ORIGINAL_FILENAME = 
"email.attachment.parent.filename";
    +    public static final String ATTACHMENT_ORIGINAL_UUID = 
"email.attachment.parent.uuid";
    +
    +    public static final Relationship REL_ATTACHMENTS = new 
Relationship.Builder()
    +            .name("attachments")
    +            .description("Each individual attachment will be routed to the 
attachments relationship")
    +            .build();
    +    public static final Relationship REL_ORIGINAL = new 
Relationship.Builder()
    +            .name("original")
    +            .description("The original file")
    +            .build();
    +    public static final Relationship REL_FAILURE = new 
Relationship.Builder()
    +            .name("failure")
    +            .description("Flowfiles that could not be parsed")
    +            .build();
    +    private Set<Relationship> relationships;
    +    private List<PropertyDescriptor> descriptors;
    +
    +
    +    @Override
    +    protected void init(final ProcessorInitializationContext context) {
    +        final Set<Relationship> relationships = new HashSet<>();
    +        relationships.add(REL_ATTACHMENTS);
    +        relationships.add(REL_ORIGINAL);
    +        relationships.add(REL_FAILURE);
    +        this.relationships = Collections.unmodifiableSet(relationships);
    +
    +        final List<PropertyDescriptor> descriptors = new ArrayList<>();
    +
    +        this.descriptors = Collections.unmodifiableList(descriptors);
    +    }
    +
    +    @Override
    +    public void onTrigger(final ProcessContext context, final 
ProcessSession session) {
    +        final ComponentLog logger = getLogger();
    +        final FlowFile originalFlowFile = session.get();
    +        if (originalFlowFile == null) {
    +            return;
    +        }
    +        final List<FlowFile> attachmentsList = new ArrayList<>();
    +        final List<FlowFile> invalidFlowFilesList = new ArrayList<>();
    +        final List<FlowFile> originalFlowFilesList = new ArrayList<>();
    +
    +        session.read(originalFlowFile, new InputStreamCallback() {
    +                @Override
    +                public void process(final InputStream rawIn) throws 
IOException {
    +                    try (final InputStream in = new 
BufferedInputStream(rawIn)) {
    +                        Properties props = new Properties();
    +                        Session mailSession = 
Session.getDefaultInstance(props, null);
    +                        MimeMessage originalMessage = new 
MimeMessage(mailSession, in);
    +                        MimeMessageParser parser = new 
MimeMessageParser(originalMessage).parse();
    +                        // RFC-2822 determines that a message must have a 
"From:" header
    +                        // if a message lacks the field, it is flagged as 
invalid
    +                        Address[] from = originalMessage.getFrom();
    +                        Date sentDate = originalMessage.getSentDate();
    +                        if (from == null || sentDate == null ) {
    +                            // See ya later my friend...
    +                            throw new MessagingException("Message failed 
RFC2822 validation");
    +                        }
    +                        if (parser.hasAttachments()) {
    +                            final String originalFlowFileName = 
originalFlowFile.getAttribute(CoreAttributes.FILENAME.key());
    +                            for (final DataSource data : 
parser.getAttachmentList()) {
    +                                FlowFile split = 
session.create(originalFlowFile);
    --- End diff --
    
    If an error occurs in this block (after a split has been created) this 
error[1] will get thrown. This is because all FlowFiles need to be handled even 
if they were just created. What is probably best is to have another try/catch 
which covers the contents of this for loop and removes the newly created split 
flowfile if it fails. 
    
    Also this would allow for potentially extracting some splits and fail to 
split others. This may require a property to determine what to do. Of course, 
in the event of a failure you could just remove all the splits and transfer the 
original to failure.
    
    [1] FlowFileHandlingException: Cannot commit session because the following 
FlowFiles have not been removed or transferred: ...


> Create ListenSMTP & ExtractEmailAttachment processors
> -----------------------------------------------------
>
>                 Key: NIFI-1899
>                 URL: https://issues.apache.org/jira/browse/NIFI-1899
>             Project: Apache NiFi
>          Issue Type: New Feature
>            Reporter: Andre
>




--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Reply via email to