exceptionfactory commented on code in PR #6589: URL: https://github.com/apache/nifi/pull/6589#discussion_r1064920895
########## nifi-nar-bundles/nifi-aws-bundle/nifi-aws-processors/src/main/java/org/apache/nifi/processors/aws/ml/textract/GetAwsTextractJobStatus.java: ########## @@ -0,0 +1,131 @@ +/* + * 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.aws.ml.textract; + +import com.amazonaws.ClientConfiguration; +import com.amazonaws.auth.AWSCredentialsProvider; +import com.amazonaws.services.textract.AmazonTextractClient; +import com.amazonaws.services.textract.model.GetDocumentAnalysisRequest; +import com.amazonaws.services.textract.model.GetDocumentTextDetectionRequest; +import com.amazonaws.services.textract.model.GetExpenseAnalysisRequest; +import com.amazonaws.services.textract.model.JobStatus; +import java.util.Collections; +import java.util.List; +import java.util.stream.Collectors; +import java.util.stream.Stream; +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.expression.ExpressionLanguageScope; +import org.apache.nifi.flowfile.FlowFile; +import org.apache.nifi.processor.ProcessContext; +import org.apache.nifi.processor.ProcessSession; +import org.apache.nifi.processor.exception.ProcessException; +import org.apache.nifi.processor.util.StandardValidators; +import org.apache.nifi.processors.aws.ml.AwsMachineLearningJobStatusProcessor; + +@Tags({"Amazon", "AWS", "ML", "Machine Learning", "Textract"}) +@CapabilityDescription("Retrieves the current status of an AWS Textract job.") +@SeeAlso({StartAwsTextractJob.class}) +public class GetAwsTextractJobStatus extends AwsMachineLearningJobStatusProcessor<AmazonTextractClient> { + public static final String DOCUMENT_ANALYSIS = "Document Analysis"; + public static final String DOCUMENT_TEXT_DETECTION = "Document Text Detection"; + public static final String EXPENSE_ANALYSIS = "Expense Analysis"; + public static final PropertyDescriptor TEXTRACT_TYPE = new PropertyDescriptor.Builder() + .name("textract-type") + .displayName("Textract Type") + .required(true) + .description("Supported values: \"Document Analysis\", \"Document Text Detection\", \"Expense Analysis\"") + .expressionLanguageSupported(ExpressionLanguageScope.FLOWFILE_ATTRIBUTES) + .defaultValue(DOCUMENT_ANALYSIS) + .addValidator(StandardValidators.NON_EMPTY_VALIDATOR) + .build(); + private static final List<PropertyDescriptor> TEXTRACT_PROPERTIES = + Collections.unmodifiableList(Stream.concat(PROPERTIES.stream(), Stream.of(TEXTRACT_TYPE)).collect(Collectors.toList())); + + @Override + public List<PropertyDescriptor> getSupportedPropertyDescriptors() { + return TEXTRACT_PROPERTIES; + } + + @Override + protected AmazonTextractClient createClient(ProcessContext context, AWSCredentialsProvider credentialsProvider, ClientConfiguration config) { + return (AmazonTextractClient) AmazonTextractClient.builder() + .withRegion(context.getProperty(REGION).getValue()) + .withCredentials(credentialsProvider) + .build(); + } + + @Override + public void onTrigger(ProcessContext context, ProcessSession session) throws ProcessException { + FlowFile flowFile = session.get(); + if (flowFile == null) { + return; + } + String textractType = context.getProperty(TEXTRACT_TYPE).evaluateAttributeExpressions(flowFile).getValue(); + + String awsTaskId = flowFile.getAttribute(AWS_TASK_ID_PROPERTY); Review Comment: This approach has an implicit contract on input FlowFiles having the `awsTaskId` property. Although this aligns with the output of the start Processors, it would be better to make this explicit. All of the Get-Status Processors could have a `Task ID` property that supports Expression Language, and the default value would be `${awsTaskId}`, which would provide the same basic behavior, but support alternative configuration options. ########## nifi-nar-bundles/nifi-aws-bundle/nifi-aws-processors/src/main/java/org/apache/nifi/processors/aws/ml/AwsMachineLearningJobStarter.java: ########## @@ -0,0 +1,171 @@ +/* + * 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.aws.ml; + +import static org.apache.nifi.flowfile.attributes.CoreAttributes.MIME_TYPE; + +import com.amazonaws.AmazonWebServiceClient; +import com.amazonaws.AmazonWebServiceRequest; +import com.amazonaws.AmazonWebServiceResult; +import com.amazonaws.ClientConfiguration; +import com.amazonaws.auth.AWSCredentials; +import com.amazonaws.regions.Regions; +import com.fasterxml.jackson.core.JsonProcessingException; +import com.fasterxml.jackson.databind.MapperFeature; +import com.fasterxml.jackson.databind.ObjectMapper; +import com.fasterxml.jackson.databind.json.JsonMapper; +import java.io.IOException; +import java.io.InputStream; +import java.util.Arrays; +import java.util.Collections; +import java.util.HashSet; +import java.util.List; +import java.util.Set; +import org.apache.commons.io.IOUtils; +import org.apache.nifi.components.PropertyDescriptor; +import org.apache.nifi.expression.ExpressionLanguageScope; +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.exception.ProcessException; +import org.apache.nifi.processor.util.StandardValidators; +import org.apache.nifi.processors.aws.AbstractAWSCredentialsProviderProcessor; + +public abstract class AwsMachineLearningJobStarter<T extends AmazonWebServiceClient, REQUEST extends AmazonWebServiceRequest, RESPONSE extends AmazonWebServiceResult> + extends AbstractAWSCredentialsProviderProcessor<T> { + public static final PropertyDescriptor JSON_PAYLOAD = new PropertyDescriptor.Builder() + .name("json-payload") + .displayName("JSON Payload") + .description("JSON request for AWS Machine Learning services. The Processor will use FlowFile content for the request when this property is not specified.") + .expressionLanguageSupported(ExpressionLanguageScope.FLOWFILE_ATTRIBUTES) + .required(false) + .addValidator(StandardValidators.NON_EMPTY_VALIDATOR) + .build(); + public static final PropertyDescriptor MANDATORY_AWS_CREDENTIALS_PROVIDER_SERVICE = + new PropertyDescriptor.Builder().fromPropertyDescriptor(AWS_CREDENTIALS_PROVIDER_SERVICE) + .required(true) + .build(); + public static final PropertyDescriptor REGION = new PropertyDescriptor.Builder() + .displayName("Region") + .name("aws-region") + .required(true) + .allowableValues(getAvailableRegions()) + .defaultValue(createAllowableValue(Regions.DEFAULT_REGION).getValue()) + .build(); + public static final Relationship REL_ORIGINAL = new Relationship.Builder() + .name("original") + .description("Upon successful completion, the original FlowFile will be routed to this relationship.") + .autoTerminateDefault(true) + .build(); + protected static final List<PropertyDescriptor> PROPERTIES = Collections.unmodifiableList(Arrays.asList( + JSON_PAYLOAD, + MANDATORY_AWS_CREDENTIALS_PROVIDER_SERVICE, + REGION, + TIMEOUT, + SSL_CONTEXT_SERVICE, + ENDPOINT_OVERRIDE)); + protected static final String AWS_TASK_ID_PROPERTY = "awsTaskId"; + private final static ObjectMapper MAPPER = JsonMapper.builder() + .configure(MapperFeature.ACCEPT_CASE_INSENSITIVE_PROPERTIES, true) + .build(); + private static final Set<Relationship> relationships = Collections.unmodifiableSet(new HashSet<>(Arrays.asList( + REL_ORIGINAL, + REL_SUCCESS, + REL_FAILURE + ))); + + @Override + public Set<Relationship> getRelationships() { + return relationships; + } + + @Override + public List<PropertyDescriptor> getSupportedPropertyDescriptors() { + return PROPERTIES; + } + + @Override + public void onTrigger(final ProcessContext context, final ProcessSession session) { + FlowFile flowFile = session.get(); + if (flowFile == null && !context.getProperty(JSON_PAYLOAD).isSet()) { + return; + } + final RESPONSE response; + FlowFile childFlowFile; + try { + response = sendRequest(buildRequest(session, context, flowFile), context, flowFile); + childFlowFile = writeToFlowFile(session, flowFile, response); + postProcessFlowFile(context, session, childFlowFile, response); + session.transfer(childFlowFile, REL_SUCCESS); + } catch (Exception e) { + if (context.getProperty(JSON_PAYLOAD).isSet()) { + session.transfer(flowFile, REL_FAILURE); + } + getLogger().error("Sending AWS ML Request failed", e); + return; + } + if (flowFile != null) { + session.transfer(flowFile, REL_ORIGINAL); + } + + } + + protected void postProcessFlowFile(ProcessContext context, ProcessSession session, FlowFile flowFile, RESPONSE response) { + session.putAttribute(flowFile, AWS_TASK_ID_PROPERTY, getAwsTaskId(context, response, flowFile)); + session.putAttribute(flowFile, MIME_TYPE.key(), "application/json"); Review Comment: These calls need to return an updated instance of `FlowFile` for subsequent processing. ########## nifi-nar-bundles/nifi-aws-bundle/nifi-aws-processors/src/main/java/org/apache/nifi/processors/aws/ml/AwsMachineLearningJobStarter.java: ########## @@ -0,0 +1,171 @@ +/* + * 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.aws.ml; + +import static org.apache.nifi.flowfile.attributes.CoreAttributes.MIME_TYPE; + +import com.amazonaws.AmazonWebServiceClient; +import com.amazonaws.AmazonWebServiceRequest; +import com.amazonaws.AmazonWebServiceResult; +import com.amazonaws.ClientConfiguration; +import com.amazonaws.auth.AWSCredentials; +import com.amazonaws.regions.Regions; +import com.fasterxml.jackson.core.JsonProcessingException; +import com.fasterxml.jackson.databind.MapperFeature; +import com.fasterxml.jackson.databind.ObjectMapper; +import com.fasterxml.jackson.databind.json.JsonMapper; +import java.io.IOException; +import java.io.InputStream; +import java.util.Arrays; +import java.util.Collections; +import java.util.HashSet; +import java.util.List; +import java.util.Set; +import org.apache.commons.io.IOUtils; +import org.apache.nifi.components.PropertyDescriptor; +import org.apache.nifi.expression.ExpressionLanguageScope; +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.exception.ProcessException; +import org.apache.nifi.processor.util.StandardValidators; +import org.apache.nifi.processors.aws.AbstractAWSCredentialsProviderProcessor; + +public abstract class AwsMachineLearningJobStarter<T extends AmazonWebServiceClient, REQUEST extends AmazonWebServiceRequest, RESPONSE extends AmazonWebServiceResult> + extends AbstractAWSCredentialsProviderProcessor<T> { + public static final PropertyDescriptor JSON_PAYLOAD = new PropertyDescriptor.Builder() + .name("json-payload") + .displayName("JSON Payload") + .description("JSON request for AWS Machine Learning services. The Processor will use FlowFile content for the request when this property is not specified.") + .expressionLanguageSupported(ExpressionLanguageScope.FLOWFILE_ATTRIBUTES) + .required(false) + .addValidator(StandardValidators.NON_EMPTY_VALIDATOR) + .build(); + public static final PropertyDescriptor MANDATORY_AWS_CREDENTIALS_PROVIDER_SERVICE = + new PropertyDescriptor.Builder().fromPropertyDescriptor(AWS_CREDENTIALS_PROVIDER_SERVICE) + .required(true) + .build(); + public static final PropertyDescriptor REGION = new PropertyDescriptor.Builder() + .displayName("Region") + .name("aws-region") + .required(true) + .allowableValues(getAvailableRegions()) + .defaultValue(createAllowableValue(Regions.DEFAULT_REGION).getValue()) + .build(); + public static final Relationship REL_ORIGINAL = new Relationship.Builder() + .name("original") + .description("Upon successful completion, the original FlowFile will be routed to this relationship.") + .autoTerminateDefault(true) + .build(); + protected static final List<PropertyDescriptor> PROPERTIES = Collections.unmodifiableList(Arrays.asList( + JSON_PAYLOAD, + MANDATORY_AWS_CREDENTIALS_PROVIDER_SERVICE, + REGION, + TIMEOUT, + SSL_CONTEXT_SERVICE, + ENDPOINT_OVERRIDE)); + protected static final String AWS_TASK_ID_PROPERTY = "awsTaskId"; + private final static ObjectMapper MAPPER = JsonMapper.builder() + .configure(MapperFeature.ACCEPT_CASE_INSENSITIVE_PROPERTIES, true) + .build(); + private static final Set<Relationship> relationships = Collections.unmodifiableSet(new HashSet<>(Arrays.asList( + REL_ORIGINAL, + REL_SUCCESS, + REL_FAILURE + ))); + + @Override + public Set<Relationship> getRelationships() { + return relationships; + } + + @Override + public List<PropertyDescriptor> getSupportedPropertyDescriptors() { + return PROPERTIES; + } + + @Override + public void onTrigger(final ProcessContext context, final ProcessSession session) { + FlowFile flowFile = session.get(); + if (flowFile == null && !context.getProperty(JSON_PAYLOAD).isSet()) { + return; + } + final RESPONSE response; + FlowFile childFlowFile; + try { + response = sendRequest(buildRequest(session, context, flowFile), context, flowFile); + childFlowFile = writeToFlowFile(session, flowFile, response); + postProcessFlowFile(context, session, childFlowFile, response); + session.transfer(childFlowFile, REL_SUCCESS); + } catch (Exception e) { + if (context.getProperty(JSON_PAYLOAD).isSet()) { Review Comment: It looks like the logic should be reversed, or for clarity, this conditional should be changed to look for a defined `flowFile`: ```suggestion if (flowFile != null) { ``` ########## nifi-nar-bundles/nifi-aws-bundle/nifi-aws-processors/src/main/java/org/apache/nifi/processors/aws/ml/textract/GetAwsTextractJobStatus.java: ########## @@ -0,0 +1,131 @@ +/* + * 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.aws.ml.textract; + +import com.amazonaws.ClientConfiguration; +import com.amazonaws.auth.AWSCredentialsProvider; +import com.amazonaws.services.textract.AmazonTextractClient; +import com.amazonaws.services.textract.model.GetDocumentAnalysisRequest; +import com.amazonaws.services.textract.model.GetDocumentTextDetectionRequest; +import com.amazonaws.services.textract.model.GetExpenseAnalysisRequest; +import com.amazonaws.services.textract.model.JobStatus; +import java.util.Collections; +import java.util.List; +import java.util.stream.Collectors; +import java.util.stream.Stream; +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.expression.ExpressionLanguageScope; +import org.apache.nifi.flowfile.FlowFile; +import org.apache.nifi.processor.ProcessContext; +import org.apache.nifi.processor.ProcessSession; +import org.apache.nifi.processor.exception.ProcessException; +import org.apache.nifi.processor.util.StandardValidators; +import org.apache.nifi.processors.aws.ml.AwsMachineLearningJobStatusProcessor; + +@Tags({"Amazon", "AWS", "ML", "Machine Learning", "Textract"}) +@CapabilityDescription("Retrieves the current status of an AWS Textract job.") +@SeeAlso({StartAwsTextractJob.class}) +public class GetAwsTextractJobStatus extends AwsMachineLearningJobStatusProcessor<AmazonTextractClient> { + public static final String DOCUMENT_ANALYSIS = "Document Analysis"; + public static final String DOCUMENT_TEXT_DETECTION = "Document Text Detection"; + public static final String EXPENSE_ANALYSIS = "Expense Analysis"; + public static final PropertyDescriptor TEXTRACT_TYPE = new PropertyDescriptor.Builder() + .name("textract-type") + .displayName("Textract Type") + .required(true) + .description("Supported values: \"Document Analysis\", \"Document Text Detection\", \"Expense Analysis\"") + .expressionLanguageSupported(ExpressionLanguageScope.FLOWFILE_ATTRIBUTES) + .defaultValue(DOCUMENT_ANALYSIS) + .addValidator(StandardValidators.NON_EMPTY_VALIDATOR) + .build(); + private static final List<PropertyDescriptor> TEXTRACT_PROPERTIES = + Collections.unmodifiableList(Stream.concat(PROPERTIES.stream(), Stream.of(TEXTRACT_TYPE)).collect(Collectors.toList())); + + @Override + public List<PropertyDescriptor> getSupportedPropertyDescriptors() { + return TEXTRACT_PROPERTIES; + } + + @Override + protected AmazonTextractClient createClient(ProcessContext context, AWSCredentialsProvider credentialsProvider, ClientConfiguration config) { + return (AmazonTextractClient) AmazonTextractClient.builder() + .withRegion(context.getProperty(REGION).getValue()) + .withCredentials(credentialsProvider) + .build(); + } + + @Override + public void onTrigger(ProcessContext context, ProcessSession session) throws ProcessException { + FlowFile flowFile = session.get(); + if (flowFile == null) { + return; + } + String textractType = context.getProperty(TEXTRACT_TYPE).evaluateAttributeExpressions(flowFile).getValue(); + + String awsTaskId = flowFile.getAttribute(AWS_TASK_ID_PROPERTY); + JobStatus jobStatus = getTaskStatus(textractType, getClient(), awsTaskId); Review Comment: The `getTaskStatus` method can throw an exception that `onTrigger` does not catch, causing the input FlowFile to remaining in the input queue. The `GetAwsPollyJobStatus` Processor has a try-catch around that status call, so it seems like that approach should be implemented in this and other status retrieval Processors. ########## nifi-nar-bundles/nifi-aws-bundle/nifi-aws-processors/src/main/java/org/apache/nifi/processors/aws/ml/textract/GetAwsTextractJobStatus.java: ########## @@ -0,0 +1,131 @@ +/* + * 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.aws.ml.textract; + +import com.amazonaws.ClientConfiguration; +import com.amazonaws.auth.AWSCredentialsProvider; +import com.amazonaws.services.textract.AmazonTextractClient; +import com.amazonaws.services.textract.model.GetDocumentAnalysisRequest; +import com.amazonaws.services.textract.model.GetDocumentTextDetectionRequest; +import com.amazonaws.services.textract.model.GetExpenseAnalysisRequest; +import com.amazonaws.services.textract.model.JobStatus; +import java.util.Collections; +import java.util.List; +import java.util.stream.Collectors; +import java.util.stream.Stream; +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.expression.ExpressionLanguageScope; +import org.apache.nifi.flowfile.FlowFile; +import org.apache.nifi.processor.ProcessContext; +import org.apache.nifi.processor.ProcessSession; +import org.apache.nifi.processor.exception.ProcessException; +import org.apache.nifi.processor.util.StandardValidators; +import org.apache.nifi.processors.aws.ml.AwsMachineLearningJobStatusProcessor; + +@Tags({"Amazon", "AWS", "ML", "Machine Learning", "Textract"}) +@CapabilityDescription("Retrieves the current status of an AWS Textract job.") +@SeeAlso({StartAwsTextractJob.class}) +public class GetAwsTextractJobStatus extends AwsMachineLearningJobStatusProcessor<AmazonTextractClient> { + public static final String DOCUMENT_ANALYSIS = "Document Analysis"; + public static final String DOCUMENT_TEXT_DETECTION = "Document Text Detection"; + public static final String EXPENSE_ANALYSIS = "Expense Analysis"; + public static final PropertyDescriptor TEXTRACT_TYPE = new PropertyDescriptor.Builder() + .name("textract-type") + .displayName("Textract Type") + .required(true) + .description("Supported values: \"Document Analysis\", \"Document Text Detection\", \"Expense Analysis\"") Review Comment: It seems like these supported values should be defined using the `allowableValues()` property descriptor setting. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@nifi.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
