Github user trixpan commented on a diff in the pull request: https://github.com/apache/nifi/pull/1619#discussion_r108918981 --- Diff: nifi-nar-bundles/nifi-cybersecurity-bundle/nifi-cybersecurity-processors/src/main/java/org/apache/nifi/processors/cybersecurity/FuzzyHashContent.java --- @@ -0,0 +1,192 @@ +/* + * 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.cybersecurity; + +import com.idealista.tlsh.TLSH; +import com.idealista.tlsh.exceptions.InsufficientComplexityException; +import info.debatty.java.spamsum.SpamSum; + +import org.apache.nifi.annotation.behavior.EventDriven; +import org.apache.nifi.annotation.behavior.InputRequirement; +import org.apache.nifi.annotation.behavior.SideEffectFree; +import org.apache.nifi.annotation.behavior.SupportsBatching; +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.AllowableValue; +import org.apache.nifi.components.PropertyDescriptor; +import org.apache.nifi.flowfile.FlowFile; +import org.apache.nifi.logging.ComponentLog; +import org.apache.nifi.processor.exception.ProcessException; +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.util.StandardValidators; +import org.apache.nifi.processors.standard.HashContent; + +import org.apache.nifi.stream.io.StreamUtils; + +import java.io.ByteArrayOutputStream; +import java.io.IOException; +import java.io.InputStream; +import java.util.ArrayList; +import java.util.Collections; +import java.util.HashSet; +import java.util.List; +import java.util.Set; +import java.util.concurrent.atomic.AtomicReference; + + +@EventDriven +@SideEffectFree +@SupportsBatching +@InputRequirement(InputRequirement.Requirement.INPUT_REQUIRED) +@Tags({"hashing", "fuzzy-hashing", "cyber-security"}) +@CapabilityDescription("Calculates a fuzzy/locality-sensitive hash value for the Content of a FlowFile and puts that " + + "hash value on the FlowFile as an attribute whose name is determined by the <Hash Attribute Name> property." + + "Note: this processor only offers non-criptographic hash algorithms. And it should be not be " + + "seen as a replacement to the HashContent processor") + +@SeeAlso({HashContent.class}) +@ReadsAttributes({@ReadsAttribute(attribute="", description="")}) +@WritesAttributes({@WritesAttribute(attribute = "<Hash Attribute Name>", description = "This Processor adds an attribute whose value is the result of Hashing the " + + "existing FlowFile content. The name of this attribute is specified by the <Hash Attribute Name> property")}) + +public class FuzzyHashContent extends AbstractProcessor { + + public static final AllowableValue allowableValueSSDEEP = new AllowableValue( + "ssdeep", + "ssdeep", + "Uses ssdeep / SpamSum 'context triggered piecewise hash'."); + public static final AllowableValue allowableValueTLSH = new AllowableValue( + "tlsh", + "tlsh", + "Uses TLSH (Trend 'Locality Sensitive Hash'). Note: FlowFile Content must be at least 512 characters long"); + + public static final PropertyDescriptor ATTRIBUTE_NAME = new PropertyDescriptor.Builder() + .name("ATTRIBUTE_NAME") + .displayName("Hash Attribute Name") + .description("The name of the FlowFile Attribute into which the Hash Value should be written. " + + "If the value already exists, it will be overwritten") + .required(true) + .addValidator(StandardValidators.NON_EMPTY_VALIDATOR) + .defaultValue("fuzzyhash.value") + .build(); + + public static final PropertyDescriptor HASH_ALGORITHM = new PropertyDescriptor.Builder() --- End diff -- I am mimicking the HashContent processor and IRRC we don't allow that over there.
--- 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. ---