def processDocument(self, ips, i, document):
print("\nTextracting Document # {}: {}".format(i, document))
print('=' * (len(document) + 30))
# Get document textracted
dp = DocumentProcessor(ips["bucketName"], document, ips["awsRegion"],
ips["text"], ips["forms"], ips["tables"])
response = dp.run()
print("Recieved Textract response...")
#FileHelper.writeToFile("temp-response.json", json.dumps(response))
#Generate output files
print("Generating output...")
name, ext = FileHelper.getFileNameAndExtension(document)
opg = OutputGenerator(
response, os.path.join(ips["output"], "{}-{}".format(name, ext)),
ips["forms"], ips["tables"])
opg.run()
if (ips["insights"] or ips["medical-insights"] or ips["translate"]):
opg.generateInsights(ips["insights"], ips["medical-insights"],
ips["translate"], ips["awsRegion"])
print("{} textracted successfully.".format(document))
def processImage(
documentId, features, bucketName, objectName, outputTableName, documentsTableName
):
detectText = "Text" in features
detectForms = "Forms" in features
detectTables = "Tables" in features
response = callTextract(
bucketName, objectName, detectText, detectForms, detectTables
)
dynamodb = AwsHelper().getResource("dynamodb")
ddb = dynamodb.Table(outputTableName)
print("Generating output for DocumentId: {}".format(documentId))
opg = OutputGenerator(
documentId, response, bucketName, objectName, detectForms, detectTables, ddb
)
opg.run()
print("DocumentId: {}".format(documentId))
ds = datastore.DocumentStore(documentsTableName, outputTableName)
ds.markDocumentComplete(documentId)
def processRequest(request):
output = ""
print(request)
jobId = request['jobId']
jobTag = request['jobTag']
jobStatus = request['jobStatus']
jobAPI = request['jobAPI']
bucketName = request['bucketName']
objectName = request['objectName']
outputTable = request["outputTable"]
outputBucket = request["outputBucket"]
documentsTable = request["documentsTable"]
qUrl = request["elasticQueueUrl"]
pages = getJobResults(jobAPI, jobId)
print("Result pages recieved: {}".format(len(pages)))
dynamodb = AwsHelper().getResource("dynamodb")
ddb = dynamodb.Table(outputTable)
detectForms = False
detectTables = False
if (jobAPI == "StartDocumentAnalysis"):
detectForms = True
detectTables = True
opg = OutputGenerator(jobId, jobTag, pages, outputBucket, objectName,
detectForms, detectTables, ddb)
opg.run()
print("DocumentId: {}".format(jobTag))
ds = datastore.DocumentStore(documentsTable, outputTable)
ds.markDocumentComplete(jobTag, jobId)
jsonMessage = {
'documentId': jobTag,
'jobId': jobId,
'bucketName': outputBucket,
'objectName': objectName
}
client = AwsHelper().getClient('sqs')
postMessage(client, qUrl, jsonMessage)
output = "Processed -> Document: {}, Object: {}/{} processed.".format(
jobTag, bucketName, objectName)
print(output)
return {'statusCode': 200, 'body': output}
def processRequest(request):
output = ""
print(request)
jobId = request['jobId']
jobTag = request['jobTag']
jobStatus = request['jobStatus']
jobAPI = request['jobAPI']
bucketName = request['bucketName']
outputBucketName = request['outputBucketName']
objectName = request['objectName']
outputTable = request["outputTable"]
documentsTable = request["documentsTable"]
elasticsearchDomain = request["elasticsearchDomain"]
pages = getJobResults(jobAPI, jobId)
print("Result pages recieved: {}".format(len(pages)))
dynamodb = AwsHelper().getResource("dynamodb")
ddb = dynamodb.Table(outputTable)
detectForms = False
detectTables = False
if (jobAPI == "StartDocumentAnalysis"):
detectForms = True
detectTables = True
dynamodb = AwsHelper().getResource('dynamodb')
ddb = dynamodb.Table(outputTable)
opg = OutputGenerator(jobTag, pages, outputBucketName, objectName,
detectForms, detectTables, ddb, elasticsearchDomain)
opg.run()
generatePdf(jobTag, bucketName, objectName, outputBucketName)
print("DocumentId: {}".format(jobTag))
ds = datastore.DocumentStore(documentsTable, outputTable)
ds.markDocumentComplete(jobTag)
output = "Processed -> Document: {}, Object: {}/{} processed.".format(
jobTag, bucketName, objectName)
print(output)
return {'statusCode': 200, 'body': output}
def processRequest(request):
output = ""
print(request)
jobId = request["jobId"]
jobTag = request["jobTag"]
jobStatus = request["jobStatus"]
jobAPI = request["jobAPI"]
bucketName = request["bucketName"]
objectName = request["objectName"]
outputTable = request["outputTable"]
documentsTable = request["documentsTable"]
pages = getJobResults(jobAPI, jobId)
print("Result pages recieved: {}".format(len(pages)))
dynamodb = AwsHelper().getResource("dynamodb")
ddb = dynamodb.Table(outputTable)
detectForms = False
detectTables = False
if jobAPI == "StartDocumentAnalysis":
detectForms = True
detectTables = True
dynamodb = AwsHelper().getResource("dynamodb")
ddb = dynamodb.Table(outputTable)
opg = OutputGenerator(
jobTag, pages, bucketName, objectName, detectForms, detectTables, ddb
)
opg.run()
print("DocumentId: {}".format(jobTag))
ds = datastore.DocumentStore(documentsTable, outputTable)
ds.markDocumentComplete(jobTag)
output = "Processed -> Document: {}, Object: {}/{} processed.".format(
jobTag, bucketName, objectName
)
print(output)
return {"statusCode": 200, "body": output}
def processImage(documentId, features, bucketName, outputBucketName,
objectName, outputTableName, documentsTableName,
elasticsearchDomain):
detectText = "Text" in features
detectForms = "Forms" in features
detectTables = "Tables" in features
response = callTextract(bucketName, objectName, detectText, detectForms,
detectTables)
dynamodb = AwsHelper().getResource("dynamodb")
ddb = dynamodb.Table(outputTableName)
outputPath = '{}{}/{}'.format(PUBLIC_PATH_S3_PREFIX, documentId,
SERVICE_OUTPUT_PATH_S3_PREFIX)
print("Generating output for DocumentId: {} and storing in {}".format(
documentId, outputPath))
opg = OutputGenerator(documentId, response, outputBucketName, objectName,
detectForms, detectTables, ddb, outputPath,
elasticsearchDomain)
opg_output = opg.run()
generatePdf(documentId, bucketName, objectName, outputBucketName,
outputPath)
# generate Comprehend and ComprehendMedical entities in S3
comprehendOutputPath = "{}{}".format(outputPath, COMPREHEND_PATH_S3_PREFIX)
print("Comprehend output path: " + comprehendOutputPath)
maxPages = 100
comprehendClient = ComprehendHelper()
responseDocumentName = "{}{}response.json".format(outputPath,
TEXTRACT_PATH_S3_PREFIX)
comprehendAndMedicalEntities = comprehendClient.processComprehend(
outputBucketName, responseDocumentName, comprehendOutputPath, maxPages)
# if Kendra is available then let it index the document
# index the searchable pdf in Kendra
if 'KENDRA_INDEX_ID' in os.environ:
kendraClient = KendraHelper()
fileName = os.path.basename(objectName).split(".")[0]
fileExtension = os.path.basename(objectName).split(".")[1]
outputDocumentName = "{}{}-searchable.pdf".format(outputPath, fileName)
kendraClient.indexDocument(os.environ['KENDRA_INDEX_ID'],
os.environ['KENDRA_ROLE_ARN'],
outputBucketName, outputDocumentName,
documentId, fileExtension)
print("Processed Comprehend data for document: {}".format(documentId))
for key, val in opg_output[KVPAIRS].items():
if key not in comprehendAndMedicalEntities:
comprehendAndMedicalEntities[key] = val
else:
comprehendAndMedicalEntities[key].add(val)
opg.indexDocument(opg_output[DOCTEXT], comprehendAndMedicalEntities)
ds = datastore.DocumentStore(documentsTableName, outputTableName)
ds.markDocumentComplete(documentId)
def processImage(documentId, features, bucketName, outputBucketName,
objectName, outputTableName, documentsTableName,
elasticsearchDomain):
detectText = "Text" in features
detectForms = "Forms" in features
detectTables = "Tables" in features
response = callTextract(bucketName, objectName, detectText, detectForms,
detectTables)
dynamodb = AwsHelper().getResource("dynamodb")
ddb = dynamodb.Table(outputTableName)
outputPath = '{}{}/{}'.format(PUBLIC_PATH_S3_PREFIX, documentId,
SERVICE_OUTPUT_PATH_S3_PREFIX)
print("Generating output for DocumentId: {} and storing in {}".format(
documentId, outputPath))
opg = OutputGenerator(documentId, response, outputBucketName, objectName,
detectForms, detectTables, ddb, outputPath,
elasticsearchDomain)
opg_output = opg.run()
generatePdf(documentId, bucketName, objectName, outputBucketName,
outputPath)
# generate Comprehend and ComprehendMedical entities in S3
comprehendOutputPath = "{}{}".format(outputPath, COMPREHEND_PATH_S3_PREFIX)
print("Comprehend output path: " + comprehendOutputPath)
maxPages = 100
comprehendClient = ComprehendHelper()
responseDocumentName = "{}{}response.json".format(outputPath,
TEXTRACT_PATH_S3_PREFIX)
comprehendAndMedicalEntities = comprehendClient.processComprehend(
outputBucketName, responseDocumentName, comprehendOutputPath, maxPages)
print("DocumentId: {}".format(documentId))
print("Processed Comprehend data: {}".format(comprehendAndMedicalEntities))
for key, val in opg_output[KVPAIRS].items():
if key not in comprehendAndMedicalEntities:
comprehendAndMedicalEntities[key] = val
else:
comprehendAndMedicalEntities[key].add(val)
opg.indexDocument(opg_output[DOCTEXT], comprehendAndMedicalEntities)
ds = datastore.DocumentStore(documentsTableName, outputTableName)
ds.markDocumentComplete(documentId)
def processImage(documentId, features, bucketName, outputBucketName,
objectName, outputTableName, documentsTableName,
elasticsearchDomain):
detectText = "Text" in features
detectForms = "Forms" in features
detectTables = "Tables" in features
response = callTextract(bucketName, objectName, detectText, detectForms,
detectTables)
dynamodb = AwsHelper().getResource("dynamodb")
ddb = dynamodb.Table(outputTableName)
print("Generating output for DocumentId: {}".format(documentId))
opg = OutputGenerator(documentId, response, outputBucketName, objectName,
detectForms, detectTables, ddb, elasticsearchDomain)
opg_output = opg.run()
generatePdf(documentId, bucketName, objectName, outputBucketName)
# generate Comprehend and ComprehendMedical entities in S3
path = objectName + "-analysis" + "/" + documentId + "/"
print("path: " + path)
maxPages = 100
comprehendClient = ComprehendHelper()
comprehendAndMedicalEntities = comprehendClient.processComprehend(
outputBucketName, 'response.json', path, maxPages)
print("DocumentId: {}".format(documentId))
print("Processed Comprehend data: {}".format(comprehendAndMedicalEntities))
for key, val in opg_output[KVPAIRS].items():
if key not in comprehendAndMedicalEntities:
comprehendAndMedicalEntities[key] = val
else:
comprehendAndMedicalEntities[key].add(val)
opg.indexDocument(opg_output[DOCTEXT], comprehendAndMedicalEntities)
ds = datastore.DocumentStore(documentsTableName, outputTableName)
ds.markDocumentComplete(documentId)
def processImage(features, bucket_name, object_name):
detectTables = "detectTables" in features
detectText = "detectText" in features
response = callTextract(bucket_name, object_name, detectText, detectTables)
print("Generating output for DocumentId: {}".format(object_name))
#print(json.dumps(response))
#get page metadata
metadata = get_page_metadata(bucket_name=bucket_name, object_name=object_name)
opg = OutputGenerator(response, bucketName=bucket_name, objectName=object_name, tables=detectTables,
metadata=metadata)
output = opg.run()
print("DocumentId: {}".format(object_name))
return output
def generateOutput(filePath, response):
print("Generating output...")
name, ext = FileHelper.getFileNameAndExtension(filePath)
opg = OutputGenerator(response, "{}-v2-{}".format(name, ext), True, True)
opg.run()
opg.generateInsights(True, True, 'es', 'us-east-1')
def processRequest(request):
output = ""
print(request)
jobId = request['jobId']
jobTag = request['jobTag']
jobStatus = request['jobStatus']
jobAPI = request['jobAPI']
bucketName = request['bucketName']
outputBucketName = request['outputBucketName']
objectName = request['objectName']
outputTable = request["outputTable"]
documentsTable = request["documentsTable"]
elasticsearchDomain = request["elasticsearchDomain"]
pages = getJobResults(jobAPI, jobId)
print("Result pages recieved: {}".format(len(pages)))
dynamodb = AwsHelper().getResource("dynamodb")
ddb = dynamodb.Table(outputTable)
detectForms = False
detectTables = False
if (jobAPI == "StartDocumentAnalysis"):
detectForms = True
detectTables = True
dynamodb = AwsHelper().getResource('dynamodb')
ddb = dynamodb.Table(outputTable)
opg = OutputGenerator(jobTag, pages, outputBucketName, objectName,
detectForms, detectTables, ddb, elasticsearchDomain)
opg_output = opg.run()
generatePdf(jobTag, bucketName, objectName, outputBucketName)
# generate Comprehend and ComprehendMedical entities
path = objectName + "-analysis" + "/" + jobTag + "/"
print("path: " + path)
maxPages = 100
comprehendClient = ComprehendHelper()
comprehendAndMedicalEntities = comprehendClient.processComprehend(
outputBucketName, 'response.json', path, maxPages)
print("DocumentId: {}".format(jobTag))
# index document once the comprehend entities and KVPairs have been extracted
for key, val in opg_output[KVPAIRS].items():
if key not in comprehendAndMedicalEntities:
comprehendAndMedicalEntities[key] = val
else:
comprehendAndMedicalEntities[key].add(val)
opg.indexDocument(opg_output[DOCTEXT], comprehendAndMedicalEntities)
ds = datastore.DocumentStore(documentsTable, outputTable)
ds.markDocumentComplete(jobTag)
output = "Processed -> Document: {}, Object: {}/{} processed.".format(
jobTag, bucketName, objectName)
return {'statusCode': 200, 'body': output}
def processRequest(request):
output = ""
print("Request : {}".format(request))
jobId = request['jobId']
documentId = request['jobTag']
jobStatus = request['jobStatus']
jobAPI = request['jobAPI']
bucketName = request['bucketName']
outputBucketName = request['outputBucketName']
objectName = request['objectName']
outputTable = request["outputTable"]
documentsTable = request["documentsTable"]
elasticsearchDomain = request["elasticsearchDomain"]
pages = getJobResults(jobAPI, jobId)
print("Result pages recieved: {}".format(len(pages)))
dynamodb = AwsHelper().getResource("dynamodb")
ddb = dynamodb.Table(outputTable)
detectForms = False
detectTables = False
if (jobAPI == "StartDocumentAnalysis"):
detectForms = True
detectTables = True
dynamodb = AwsHelper().getResource('dynamodb')
ddb = dynamodb.Table(outputTable)
outputPath = '{}{}/{}'.format(PUBLIC_PATH_S3_PREFIX, documentId,
SERVICE_OUTPUT_PATH_S3_PREFIX)
print("Generating output for DocumentId: {} and storing in {}".format(
documentId, outputPath))
opg = OutputGenerator(documentId, pages, outputBucketName, objectName,
detectForms, detectTables, ddb, outputPath,
elasticsearchDomain)
opg_output = opg.run()
generatePdf(documentId, bucketName, objectName, outputBucketName,
outputPath)
# generate Comprehend and ComprehendMedical entities
comprehendOutputPath = "{}{}".format(outputPath, COMPREHEND_PATH_S3_PREFIX)
print("Comprehend output path: " + comprehendOutputPath)
maxPages = 100
comprehendClient = ComprehendHelper()
responseDocumentName = "{}{}response.json".format(outputPath,
TEXTRACT_PATH_S3_PREFIX)
comprehendAndMedicalEntities = comprehendClient.processComprehend(
outputBucketName, responseDocumentName, comprehendOutputPath, maxPages)
# if Kendra is available then let it index the document
if 'KENDRA_INDEX_ID' in os.environ:
kendraClient = KendraHelper()
fileName = os.path.basename(objectName).split(".")[0]
fileExtension = os.path.basename(objectName).split(".")[1]
outputDocumentName = "{}{}-searchable.pdf".format(outputPath, fileName)
kendraClient.indexDocument(os.environ['KENDRA_INDEX_ID'],
os.environ['KENDRA_ROLE_ARN'], bucketName,
outputDocumentName, documentId,
fileExtension)
print("DocumentId: {}".format(documentId))
print("Processed Comprehend data: {}".format(comprehendAndMedicalEntities))
# index document once the comprehend entities and KVPairs have been extracted
for key, val in opg_output[KVPAIRS].items():
if key not in comprehendAndMedicalEntities:
comprehendAndMedicalEntities[key] = val
else:
comprehendAndMedicalEntities[key].add(val)
opg.indexDocument(opg_output[DOCTEXT], comprehendAndMedicalEntities)
ds = datastore.DocumentStore(documentsTable, outputTable)
ds.markDocumentComplete(documentId)
output = "Processed -> Document: {}, Object: {}/{} processed.".format(
documentId, bucketName, objectName)
return {'statusCode': 200, 'body': output}
