def processRequest()

in code/document_classifier/document_classifier.py [0:0]

• 18 lines of code
• 7 McCabe index (conditional complexity)

def processRequest(newImage):
    documentMetadata = newImage.get("documentMetadata")
    documentId = newImage.get("documentId")
    bucketName = newImage.get("bucketName")
    objectName = newImage.get("documentName")
    
    if documentMetadata and documentId and bucketName and objectName:
        print("Valid document item to classify!")
    else:
        raise ValueError("Invalid document item! Please check the incoming dynamoDB record stream")
    
    print("DocumentId: {}, BucketName: {}, ObjectName: {}".format(documentId, bucketName, objectName))
    
    ### This is logic to determine whether or not the document should be sent to NLP processing pipeline
    ### Could be anything; we just determined this could be easy to implement based on document metadata
    print(documentMetadata)
    if documentMetadata['class'] in documentTypes['NLP_VALID']:
        return startNLPProcessing(bucketName, objectName, documentId)
    else:
        return {
            'statusCode': 200,
            'message': "Document {} not eligible for NLP Processing".format(documentId)
        }