def handler()

in lambda/comprehend.py [0:0]

• 47 lines of code
• 8 McCabe index (conditional complexity)

def handler(event, context):
    print("Received event: " + json.dumps(event, indent=2))
    
    # Get the object from the event and show its content type
    bucket = event['Records'][0]['s3']['bucket']['name']
    key = unquote_plus(event['Records'][0]['s3']['object']['key'])
    print("key is"+key)
    print("bucket is"+bucket)
    text=""
    textvalues=[]
    textvalues_entity={}
    try:
        s3.Bucket(bucket).download_file(Key=key,Filename='/tmp/{}')
        # Read document content
        with open('/tmp/{}', 'rb') as document:
            imageBytes = bytearray(document.read())
        print("Object downloaded")
        response = textract.analyze_document(Document={'Bytes': imageBytes},FeatureTypes=["TABLES", "FORMS"])
        document = Document(response)
        table=[]
        forms=[]
        #print(document)
        for page in document.pages:
                table = outputTable(page)
                forms = outputForm(page)
        print(table)
        blocks=response['Blocks']
        for block in blocks:
            if block['BlockType'] == 'LINE':
                text += block['Text']+"\n"
        print(text)
        # Extracting Key Phrases
        keyphrase_response = comprehend.detect_key_phrases(Text=text, LanguageCode='en')
        KeyPhraseList=keyphrase_response.get("KeyPhrases")
        for s in KeyPhraseList:
              textvalues.append(s.get("Text"))
                    
        detect_entity= comprehend.detect_entities(Text=text, LanguageCode='en')
        EntityList=detect_entity.get("Entities")
        for s in EntityList:
                textvalues_entity.update([(s.get("Type").strip('\t\n\r'),s.get("Text").strip('\t\n\r'))])

        s3url= 'https://s3.console.aws.amazon.com/s3/object/'+bucket+'/'+key+'?region='+region
        
        searchdata={'s3link':s3url,'KeyPhrases':textvalues,'Entity':textvalues_entity,'text':text, 'table':table, 'forms':forms}
        print(searchdata)
        print("connecting to ES")
        es=connectES()
        #es.index(index="resume-search", doc_type="_doc", body=searchdata)
        es.index(index="document", doc_type="_doc", body=searchdata)
        print("data uploaded to Elasticsearch")
        return 'keyphrases Successfully Uploaded'
    except Exception as e:
        print(e)
        print('Error: ')
        raise e