adamfisher commented on a change in pull request #3317: NIFI-6047 Add DetectDuplicateRecord Processor URL: https://github.com/apache/nifi/pull/3317#discussion_r259598661
########## File path: nifi-nar-bundles/nifi-standard-bundle/nifi-standard-processors/src/main/java/org/apache/nifi/processors/standard/DetectDuplicateRecord.java ########## @@ -0,0 +1,620 @@ +/* + * 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.standard; + +import com.google.common.base.Joiner; +import com.google.common.hash.BloomFilter; +import com.google.common.hash.Funnels; +import org.apache.commons.codec.binary.Hex; +import org.apache.commons.codec.digest.DigestUtils; +import org.apache.commons.codec.digest.MessageDigestAlgorithms; +import org.apache.nifi.annotation.behavior.*; +import org.apache.nifi.annotation.behavior.InputRequirement.Requirement; +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.*; +import org.apache.nifi.distributed.cache.client.Deserializer; +import org.apache.nifi.distributed.cache.client.DistributedMapCacheClient; +import org.apache.nifi.distributed.cache.client.Serializer; +import org.apache.nifi.distributed.cache.client.exception.DeserializationException; +import org.apache.nifi.distributed.cache.client.exception.SerializationException; +import org.apache.nifi.expression.AttributeExpression.ResultType; +import org.apache.nifi.expression.ExpressionLanguageScope; +import org.apache.nifi.flowfile.FlowFile; +import org.apache.nifi.flowfile.attributes.CoreAttributes; +import org.apache.nifi.logging.ComponentLog; +import org.apache.nifi.processor.*; +import org.apache.nifi.processor.exception.ProcessException; +import org.apache.nifi.processor.util.StandardValidators; +import org.apache.nifi.record.path.RecordPath; +import org.apache.nifi.record.path.RecordPathResult; +import org.apache.nifi.record.path.util.RecordPathCache; +import org.apache.nifi.record.path.validation.RecordPathPropertyNameValidator; +import org.apache.nifi.record.path.validation.RecordPathValidator; +import org.apache.nifi.schema.access.SchemaNotFoundException; +import org.apache.nifi.serialization.*; +import org.apache.nifi.serialization.record.Record; +import org.apache.nifi.serialization.record.RecordSchema; + +import java.io.*; +import java.nio.charset.Charset; +import java.nio.charset.StandardCharsets; +import java.security.MessageDigest; +import java.util.*; +import java.util.concurrent.TimeUnit; +import java.util.stream.Collectors; + +import static java.util.stream.Collectors.toList; +import static org.apache.commons.codec.binary.StringUtils.getBytesUtf8; +import static org.apache.commons.lang3.StringUtils.*; + +@EventDriven +@SupportsBatching +@InputRequirement(Requirement.INPUT_REQUIRED) +@SystemResourceConsideration(resource = SystemResource.MEMORY, + description = "Caches records from each incoming FlowFile and determines if the cached record has " + + "already been seen. The name of user-defined properties determines the RecordPath values used to " + + "determine if a record is unique. If no user-defined properties are present, the entire record is " + + "used as the input to determine uniqueness. All duplicate records are routed to 'duplicate'. " + + "If the record is not determined to be a duplicate, the Processor routes the record to 'non-duplicate'.") +@Tags({"text", "record", "update", "change", "replace", "modify", "distinct", "unique", + "filter", "hash", "dupe", "duplicate", "dedupe"}) +@CapabilityDescription("Caches records from each incoming FlowFile and determines if the cached record has " + + "already been seen. The name of user-defined properties determines the RecordPath values used to " + + "determine if a record is unique. If no user-defined properties are present, the entire record is " + + "used as the input to determine uniqueness. All duplicate records are routed to 'duplicate'. " + + "If the record is not determined to be a duplicate, the Processor routes the record to 'non-duplicate'." +) +@ReadsAttributes({@ReadsAttribute(attribute="", description="")}) +@WritesAttributes({ + @WritesAttribute(attribute = "record.count", description = "The number of records in the FlowFile") +}) +@DynamicProperty( + name = "RecordPath", + value = "User-defined property values are ignored", + description = "The name of each user-defined property must be a valid RecordPath.") +@SeeAlso(classNames = { + "org.apache.nifi.distributed.cache.client.DistributedMapCacheClientService", + "org.apache.nifi.distributed.cache.server.map.DistributedMapCacheServer", + "org.apache.nifi.processors.standard.DetectDuplicate" +}) +public class DetectDuplicateRecord extends AbstractProcessor { + + private volatile RecordPathCache recordPathCache; + private volatile List<String> recordPaths; + + // VALUES + + static final AllowableValue MD5_ALGORITHM_VALUE = new AllowableValue(MessageDigestAlgorithms.MD5, "MD5", + "The MD5 message-digest algorithm."); + static final AllowableValue SHA1_ALGORITHM_VALUE = new AllowableValue(MessageDigestAlgorithms.SHA_1, "SHA-1", + "The SHA-1 cryptographic hash algorithm."); + static final AllowableValue SHA256_ALGORITHM_VALUE = new AllowableValue(MessageDigestAlgorithms.SHA3_256, "SHA-256", + "The SHA-256 cryptographic hash algorithm."); + static final AllowableValue SHA512_ALGORITHM_VALUE = new AllowableValue(MessageDigestAlgorithms.SHA3_512, "SHA-512", + "The SHA-512 cryptographic hash algorithm."); + +// static final AllowableValue ENTIRE_RECORD_VALUE = new AllowableValue("entire-record", "Entire Record", +// "All field values of a record are used in the order they are listed in the incoming FlowFile to determine if two records are equal."); +// static final AllowableValue RECORD_PATH_VALUE = new AllowableValue("entire-record", "Entire Record", +// "The user-defined RecordPath properties are used in the specified order to determine whether two records are equal. " + +// "If the value of a RecordPath is modified or the ordering of the user-defined RecordPath properties change " + +// "after processing one or more FlowFiles, duplicate detection is effectively reset."); + + static final AllowableValue HASH_SET_VALUE = new AllowableValue("hash-set", "HashSet", + "Exactly matches records seen before with 100% accuracy at the expense of more memory usage. " + + "This is not ideal for large files since a hash of each record is held in memory."); + static final AllowableValue BLOOM_FILTER_VALUE = new AllowableValue("bloom-filter", "BloomFilter", + "Space-efficient data structure ideal for large data sets uses probability to determine if a record was seen before. " + + "False positive matches are possible, but false negatives are not – in other words, a query returns either \"possibly in set\" or \"definitely not in set\". " + + "You should use this option if the FlowFile content is large and you can tolerate some duplication in the data."); + + + // PROPERTIES + + static final PropertyDescriptor RECORD_READER = new PropertyDescriptor.Builder() + .name("record-reader") + .displayName("Record Reader") + .description("Specifies the Controller Service to use for reading incoming data") + .identifiesControllerService(RecordReaderFactory.class) + .required(true) + .build(); + + static final PropertyDescriptor RECORD_WRITER = new PropertyDescriptor.Builder() + .name("record-writer") + .displayName("Record Writer") + .description("Specifies the Controller Service to use for writing out the records") + .identifiesControllerService(RecordSetWriterFactory.class) + .required(true) + .build(); + + static final PropertyDescriptor INCLUDE_ZERO_RECORD_FLOWFILES = new PropertyDescriptor.Builder() + .name("include-zero-record-flowfiles") + .displayName("Include Zero Record FlowFiles") + .description("When converting an incoming FlowFile, if the conversion results in no data, " + + "this property specifies whether or not a FlowFile will be sent to the corresponding relationship") + .expressionLanguageSupported(ExpressionLanguageScope.NONE) + .allowableValues("true", "false") + .defaultValue("true") + .required(true) + .build(); + + static final PropertyDescriptor CACHE_IDENTIFIER = new PropertyDescriptor.Builder() + .name("Cache The Entry Identifier") Review comment: Sounds good. It should be noted this was copied from the `DetectDuplicate` processor since there is overlap in the properties offered so this issue is also present in that processor. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
