def markDocumentComplete(self, documentId):
err = None
dynamodb = AwsHelper().getResource("dynamodb")
table = dynamodb.Table(self._documentsTableName)
try:
table.update_item(
Key = { 'documentId': documentId },
UpdateExpression = 'SET documentStatus= :documentstatusValue, documentCompletedOn = :documentCompletedOnValue',
ConditionExpression = 'attribute_exists(documentId)',
ExpressionAttributeValues = {
':documentstatusValue': "SUCCEEDED",
':documentCompletedOnValue': str(datetime.datetime.utcnow())
}
)
except ClientError as e:
if e.response['Error']['Code'] == "ConditionalCheckFailedException":
print(e.response['Error']['Message'])
err = {'Error' : 'Document does not exist.'}
else:
raise
return err
def queryByIndexBothKeys(self, indexPartitionKey, indexSortKey):
"""List the data from database based on index partition key and index sort key
Args:
indexPartitionKey(str): partition key value of index
indexSortKey(str): sort key value of index
Returns:
List of data from database based on partition key and sort key
"""
response = {'Items': []}
if self._databaseName == 'dynamodb':
dynamodb = AwsHelper().getResource(self._databaseName,
self._awsRegion)
table = dynamodb.Table(self._tableName)
try:
response = table.query(
IndexName=self._indexName,
KeyConditionExpression=Key(
self._indexPartitionKeyName).eq(indexPartitionKey)
& Key(self._indexSortKeyName).eq(indexSortKey))
except ParamValidationError as e:
print("Parameter validation error: %s" % e)
except ClientError as e:
print("Unexpected error: %s" % e)
return response['Items']
def getDocumentCount(self):
dynamodb = AwsHelper().getResource("dynamodb")
table = dynamodb.Table(self._documentsTableName)
return table.item_count
def createDocument(self, documentId, bucketName, objectName):
err = None
dynamodb = AwsHelper().getResource("dynamodb")
table = dynamodb.Table(self._documentsTableName)
try:
table.update_item(
Key={"documentId": documentId},
UpdateExpression=
"SET bucketName = :bucketNameValue, objectName = :objectNameValue, documentStatus = :documentstatusValue, documentCreatedOn = :documentCreatedOnValue",
ConditionExpression="attribute_not_exists(documentId)",
ExpressionAttributeValues={
":bucketNameValue": bucketName,
":objectNameValue": objectName,
":documentstatusValue": "IN_PROGRESS",
":documentCreatedOnValue": str(datetime.datetime.utcnow()),
},
)
except ClientError as e:
print(e)
if e.response["Error"][
"Code"] == "ConditionalCheckFailedException":
print(e.response["Error"]["Message"])
err = {"Error": "Document already exist."}
else:
raise
return err
def markDocumentComplete(self, documentId):
err = None
dynamodb = AwsHelper().getResource("dynamodb")
table = dynamodb.Table(self._documentsTableName)
try:
table.update_item(
Key={"documentId": documentId},
UpdateExpression=
"SET documentStatus= :documentstatusValue, documentCompletedOn = :documentCompletedOnValue",
ConditionExpression="attribute_exists(documentId)",
ExpressionAttributeValues={
":documentstatusValue": "SUCCEEDED",
":documentCompletedOnValue":
str(datetime.datetime.utcnow()),
},
)
except ClientError as e:
if e.response["Error"][
"Code"] == "ConditionalCheckFailedException":
print(e.response["Error"]["Message"])
err = {"Error": "Document does not exist."}
else:
raise
return err
def callTextract(bucketName, objectName, detectText, detectForms, detectTables):
textract = AwsHelper().getClient('textract')
if(not detectForms and not detectTables):
response = textract.detect_document_text(
Document={
'S3Object': {
'Bucket': bucketName,
'Name': objectName
}
}
)
else:
features = []
if(detectTables):
features.append("TABLES")
if(detectForms):
features.append("FORMS")
response = textract.analyze_document(
Document={
'S3Object': {
'Bucket': bucketName,
'Name': objectName
}
},
FeatureTypes=features
)
return response
def save(self, info):
"""Store the data into database
Args:
info(dict): information to store
Returns:
None
"""
response = {'status': 'OK'}
if self._databaseName == 'dynamodb':
dynamodb = AwsHelper().getResource(self._databaseName,
self._awsRegion)
table = dynamodb.Table(self._tableName)
for key in info:
if not info[key]:
response['status'] = 'BAD'
response['error'] = key + ' should not be empty.'
print(response['error'])
return response
try:
table.put_item(Item=info)
except ParamValidationError as e:
print("Parameter validation error: %s" % e)
except ClientError as e:
print("Unexpected error: %s" % e)
return response
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 updateDocumentStatus(self, documentId, documentStatus, jobId=None):
err = None
dynamodb = AwsHelper().getResource("dynamodb")
table = dynamodb.Table(self._documentsTableName)
try:
table.update_item(
Key={'documentId': documentId},
UpdateExpression=
'SET documentStatus= :documentstatusValue, jobId= :jobIdValue',
ConditionExpression='attribute_exists(documentId)',
ExpressionAttributeValues={
':documentstatusValue': documentStatus,
':jobIdValue': jobId
})
except ClientError as e:
if e.response['Error'][
'Code'] == "ConditionalCheckFailedException":
print(e.response['Error']['Message'])
err = {'Error': 'Document does not exist.'}
else:
raise
return err
def createDocument(self, documentId, bucketName, objectName):
err = None
dynamodb = AwsHelper().getResource("dynamodb")
table = dynamodb.Table(self._documentsTableName)
try:
table.update_item(
Key = { "documentId": documentId },
UpdateExpression = 'SET bucketName = :bucketNameValue, objectName = :objectNameValue, documentStatus = :documentstatusValue, documentCreatedOn = :documentCreatedOnValue',
ConditionExpression = 'attribute_not_exists(documentId)',
ExpressionAttributeValues = {
':bucketNameValue': bucketName,
':objectNameValue': objectName,
':documentstatusValue': 'IN_PROGRESS',
':documentCreatedOnValue': str(datetime.datetime.utcnow())
}
)
except ClientError as e:
print(e)
if e.response['Error']['Code'] == "ConditionalCheckFailedException":
print(e.response['Error']['Message'])
err = {'Error' : 'Document already exist.'}
else:
raise
return err
def getDocument(self, documentId):
dynamodb = AwsHelper().getClient("dynamodb")
ddbGetItemResponse = dynamodb.get_item(
Key={"documentId": {
"S": documentId
}},
TableName=self._documentsTableName)
itemToReturn = None
if "Item" in ddbGetItemResponse:
itemToReturn = {
"documentId":
ddbGetItemResponse["Item"]["documentId"]["S"],
"bucketName":
ddbGetItemResponse["Item"]["bucketName"]["S"],
"objectName":
ddbGetItemResponse["Item"]["objectName"]["S"],
"documentStatus":
ddbGetItemResponse["Item"]["documentStatus"]["S"],
}
return itemToReturn
def getDocument(self, documentId):
dynamodb = AwsHelper().getClient("dynamodb")
ddbGetItemResponse = dynamodb.get_item(
Key={'documentId': {
'S': documentId
}},
TableName=self._documentsTableName)
itemToReturn = None
if ('Item' in ddbGetItemResponse):
itemToReturn = {
'documentId':
ddbGetItemResponse['Item']['documentId']['S'],
'bucketName':
ddbGetItemResponse['Item']['bucketName']['S'],
'objectName':
ddbGetItemResponse['Item']['objectName']['S'],
'documentStatus':
ddbGetItemResponse['Item']['documentStatus']['S'],
}
return itemToReturn
def _startJob(self):
response = None
client = AwsHelper().getClient('textract',
self.inputParameters.awsRegion)
if (not self.inputParameters.detectForms
and not self.inputParameters.detectTables):
response = client.start_document_text_detection(
DocumentLocation={
'S3Object': {
'Bucket': self.inputParameters.bucketName,
'Name': self.inputParameters.documentPath
}
})
else:
features = []
if (self.inputParameters.detectTables):
features.append("TABLES")
if (self.inputParameters.detectForms):
features.append("FORMS")
response = client.start_document_analysis(DocumentLocation={
'S3Object': {
'Bucket': self.inputParameters.bucketName,
'Name': self.inputParameters.documentPath
}
},
FeatureTypes=features)
return response["JobId"]
def getDocuments(self, nextToken=None):
dynamodb = AwsHelper().getResource("dynamodb")
table = dynamodb.Table(self._opsTableName)
pageSize = 25
if(nextToken):
response = table.scan(ExclusiveStartKey={ "documentId" : nextToken}, Limit=pageSize)
else:
response = table.scan(Limit=pageSize)
print("response: {}".format(response))
data = []
if('Items' in response):
data = response['Items']
documents = {
"documents" : data
}
if 'LastEvaluatedKey' in response:
nextToken = response['LastEvaluatedKey']['documentId']
print("nexToken: {}".format(nextToken))
documents["nextToken"] = nextToken
return documents
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 read_from_s3(aws_env):
bucket_name = aws_env['bucketName']
s3_file_name = aws_env['objectName']
aws_region = aws_env['awsRegion']
s3 = AwsHelper().getResource('s3', aws_region)
obj = s3.Object(bucket_name, s3_file_name)
encoding = "utf-8"
try:
content = obj.get()['Body'].read()
except Exception as e:
print(e)
return
try:
encoding = chardet.detect(content)['encoding']
print("Trying to decode with {}".format(encoding))
content_decoded = content.decode(encoding)
return content_decoded
except UnicodeDecodeError as e:
print("Failing to decode with encoding {0}: {1}".format(encoding, e))
try:
print("Trying by removing the last character")
content_without_last_char = content[:-1].decode(encoding)
return content_without_last_char
except UnicodeDecodeError as e:
print("Failing to decode: {}".format(e))
print("Returning content in bytes")
return content
def callTextract(bucketName, objectName):
textract = AwsHelper().getClient('textract')
response = textract.detect_document_text(
Document={'S3Object': {
'Bucket': bucketName,
'Name': objectName
}})
return response
def lambda_handler(event, context):
if (event['status'] <= 0):
return {**event, "errorMessage": "Status isnt positive"}
aws_env = {
**event,
"bucketName": os.environ.get('DOCUMENTS_BUCKET'),
"awsRegion": 'eu-west-1',
"tmpJsonOutput": "/tmp/tmp_result.json",
"tmpTxtOutput": "/tmp/tmp_result.txt",
"outputBucket": os.environ.get('DOCUMENTS_BUCKET'),
"outputNameJson": get_bbox_filename(event['objectName'], ".json"),
"outputNameTxt": get_bbox_filename(event['objectName'], ".txt"),
"textractOnly": os.environ.get('TEXTRACT_ONLY'),
"minCharNeeded": int(os.environ.get('MIN_CHAR_NEEDED')),
"extract_pdf_lines": os.environ.get('EXTRACT_PDF_LINES'),
}
status = {"statusCode": 200, "body": "All right"}
extract_pdf_lines = aws_env['extract_pdf_lines']
textract_only = aws_env['textractOnly']
tmp_folder = "/tmp/pdfToBbox"
pdf_tmp_path = copy_pdf_to_tmp(tmp_folder, aws_env)
print("==> aws_env: ", aws_env)
if textract_only == "false" and is_pdf_has_enough_characters(
pdf_tmp_path, aws_env['minCharNeeded']) is True:
print("=> Extracting bounding box with pdfplumber")
if extract_pdf_lines == "true":
print("=> Extracting pdf lines bbox")
pdf = Pdf(pdf_tmp_path, aws_env['tmpJsonOutput'],
aws_env['tmpTxtOutput'])
pdf.parse_pdf()
pdf.save_in_json()
pdf.save_in_txt()
write_bbox_to_s3(aws_env)
else:
print("=> Extracting pdf words bbox")
if execute_pdf_to_bbox(pdf_tmp_path, aws_env['tmpJsonOutput']):
print("=> Error while trying to get pdf information")
aws_env["status"] = -1
aws_env["errorMessage"] = "PDF format not supported."
else:
write_bbox_to_s3(aws_env)
else:
print("Extracting bounding box with textract")
#send_to_textract(aws_env)
aws_env['size'] = S3Helper.getS3FileSize(aws_env['bucketName'],
aws_env['outputNameTxt'],
aws_env['awsRegion'])
aws_env["s3Url"] = get_new_s3_url(aws_env['s3Url'], "txt")
aws_env["status"] = status
aws_env["status"] = 1
aws_env["errorMessage"] = None
aws_env["contentType"] = "text/txt"
aws_env['objectName'] = aws_env['outputNameTxt']
aws_env["sourceUrl"] = aws_env["s3Url"]
AwsHelper.refreshTmpFolder(tmp_folder)
return update_event(aws_env, event)
def TranslateCaptions(self, translationContext, terminology_names=[]):
marker = "<span>"
sourceLanguageCode = translationContext["sourceLang"]
targetLanguageCodes = translationContext["targetLangList"]
translate_role = translationContext["roleArn"]
bucket = translationContext["bucket"]
inputPath = translationContext["inputLocation"]
outputPath = translationContext["outputlocation"]
jobPrefix = translationContext["jobPrefix"]
try:
translate_client = AwsHelper().getClient('translate')
targetLanguageCode = targetLanguageCodes[0]
self.logger.debug(
"Starting translation to {}".format(targetLanguageCode))
singletonTargetList = []
singletonTargetList.append(targetLanguageCode)
millis = int(round(time.time() * 1000))
job_name = jobPrefix + str(millis)
self.logger.debug("JobName: {}".format(job_name))
terminology_name = []
if len(terminology_names) > 0:
for item in terminology_names:
if targetLanguageCode in item['TargetLanguageCodes']:
terminology_name.append(item['Name'])
break
if len(terminology_name) == 0:
self.logger.debug(int("No custom terminology specified."))
else:
self.logger.debug(
"Using custom terminology {}".format(terminology_name))
# Save the delimited transcript text to S3
response = translate_client.start_text_translation_job(
JobName=job_name,
InputDataConfig={
'S3Uri': "s3://{}/{}".format(bucket, inputPath),
'ContentType': "text/html"
},
OutputDataConfig={
'S3Uri': "s3://{}/{}".format(bucket, outputPath)
},
DataAccessRoleArn=translate_role,
SourceLanguageCode=sourceLanguageCode,
TargetLanguageCodes=singletonTargetList,
TerminologyNames=terminology_name)
jobinfo = {
"JobId": response["JobId"],
"TargetLanguageCode": targetLanguageCode
}
return jobinfo
except Exception as e:
self.logger.error(e)
raise e
def deleteItem(self, itemId):
dynamodb = AwsHelper().getResource("dynamodb")
table = dynamodb.Table(self._itemsTableName)
table.delete_item(
Key={
'itemId': itemId
}
)
def deleteDocument(self, documentId):
dynamodb = AwsHelper().getResource("dynamodb")
table = dynamodb.Table(self._opsTableName)
table.delete_item(
Key={
'documentId': 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 updateDocumentStatus(self, documentId, status, stage, timestamp, message=None):
ret = None
dynamodb = AwsHelper().getResource("dynamodb")
table = dynamodb.Table(self._opsTableName)
try:
if message:
new_datapoint = {
"timestamp": timestamp,
"stage": stage,
"status": status,
"message": message
}
else:
new_datapoint = {
"timestamp": timestamp,
"stage": stage,
"status": status
}
table.update_item(
Key = {
'documentId': documentId
},
UpdateExpression = 'SET documentStatus = :documentStatus, documentStage = :documentStage, lastUpdate = :lastUpdate, timeline = list_append(timeline, :new_datapoint)',
ConditionExpression = 'attribute_exists(documentId)',
ExpressionAttributeValues = {
':documentStatus': status,
':documentStage': stage,
':lastUpdate': timestamp,
':new_datapoint': [new_datapoint]
}
)
ret = {
'Status': 200
}
except ClientError as e:
print(e)
ret = {
'Error' : e.response['Error']['Message'],
'Status': e.response['ResponseMetadata']['HTTPStatusCode']
}
except Exception as e:
print(e)
ret = {
'Error' : 'Updating document failed',
'Status': 400
}
return ret
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 queryDocumentId(self, targetBucketName, targetFileName, versionId=None):
ret = None
res = None
dynamodb = AwsHelper().getResource("dynamodb")
table = dynamodb.Table(self._lineageTableName)
documentSignature = "BUCKET:{}@FILE:{}".format(targetBucketName, targetFileName)
if versionId:
documentSignature += "@VERSION:{}".format(versionId)
try:
res = table.query(
KeyConditionExpression = Key('documentSignature').eq(documentSignature),
IndexName = self._lineageIndexName
)
except ClientError as e:
print(e)
ret = {
'Error': e.response['Error']['Message'],
'Status': e.response['ResponseMetadata']['HTTPStatusCode']
}
except Exception as e:
print(e)
ret = {
'Error': 'Unknown error occurred during querying the document Id',
'Status': 400
}
try:
items = res['Items']
print(items)
if len(items) == 0:
ret = {
'Status': 404,
'documentId': None
}
else:
items.sort(key=lambda item: datetime.fromisoformat(item['timestamp']))
ret = {
'Status': 200,
'documentId': items[0]['documentId']
}
except Exception as e:
print(e)
ret = {
'Error': 'Could not find the documentId for specified document Signature',
'Status': 400
}
return ret
def processRequest(request):
output = ""
print("request: {}".format(request))
itemId = request["itemId"]
bucketName = request["bucketName"]
objectName = request["objectName"]
print("Input Object: {}/{}".format(bucketName, objectName))
ext = FileHelper.getFileExtenstion(objectName.lower())
print("Extension: {}".format(ext))
if(ext and ext in ["jpg", "jpeg", "png"]):
qUrl = request['syncQueueUrl']
elif (ext in ["mov", "mp4"]):
qUrl = request['asyncQueueUrl']
if(qUrl):
jsonMessage = { 'itemId' : itemId,
'bucketName': bucketName,
'objectName' : objectName }
client = AwsHelper().getClient('sqs')
response = postMessage(client, qUrl, jsonMessage)
output = "Completed routing for itemId: {}, object: {}/{}".format(itemId, bucketName, objectName)
print(output)
return response
def processItems(qUrl, snsTopic, snsRole):
sqs = AwsHelper().getClient('sqs')
messages = getMessagesFromQueue(sqs, qUrl)
jc = 0
totalMessages = 0
hitLimit = False
limitException = None
if(messages):
totalMessages = len(messages)
print("Total messages: {}".format(totalMessages))
for message in messages:
receipt_handle = message['ReceiptHandle']
try:
if(hitLimit):
changeVisibility(sqs, qUrl, receipt_handle)
else:
print("starting job...")
processItem(message, snsTopic, snsRole)
print("started job...")
print('Deleting item from queue...')
# Delete received message from queue
sqs.delete_message(
QueueUrl=qUrl,
ReceiptHandle=receipt_handle
)
print('Deleted item from queue...')
jc += 1
except Exception as e:
print("Error while starting job or deleting from queue: {}".format(e))
changeVisibility(sqs, qUrl, receipt_handle)
if(e.__class__.__name__ == 'LimitExceededException'
or e.__class__.__name__ == "ProvisionedThroughputExceededException"):
hitLimit = True
limitException = e
if(hitLimit):
raise limitException
return totalMessages, jc
def startJob(bucketName, objectName, documentId, snsTopic, snsRole,
detectForms, detectTables):
print("Starting job with documentId: {}, bucketName: {}, objectName: {}".
format(documentId, bucketName, objectName))
response = None
client = AwsHelper().getClient('textract')
if (not detectForms and not detectTables):
response = client.start_document_text_detection(
ClientRequestToken=documentId,
DocumentLocation={
'S3Object': {
'Bucket': bucketName,
'Name': objectName
}
},
NotificationChannel={
"RoleArn": snsRole,
"SNSTopicArn": snsTopic
},
JobTag=documentId)
else:
features = []
if (detectTables):
features.append("TABLES")
if (detectForms):
features.append("FORMS")
response = client.start_document_analysis(
ClientRequestToken=documentId,
DocumentLocation={
'S3Object': {
'Bucket': bucketName,
'Name': objectName
}
},
FeatureTypes=features,
NotificationChannel={
"RoleArn": snsRole,
"SNSTopicArn": snsTopic
},
JobTag=documentId)
return response["JobId"]
def getComprehend(languageCode="en"):
ss = boto3.Session()
region = ss.region_name
client = AwsHelper().getClient('comprehend', region)
def entities(text):
return client.detect_entities(Text=text, LanguageCode=languageCode)
return {"entities": entities}
def startTranslationJob(bucketName, sourceCode, destCode, access_role):
translate = AwsHelper().getClient('translate')
try:
millis = int(round(time.time() * 1000))
response = translate.start_text_translation_job(
JobName="TranslateJob-json-{}".format(millis),
InputDataConfig={
'S3Uri': "s3://{}/xmlin/".format(bucketName),
'ContentType': 'text/html'
},
OutputDataConfig={'S3Uri': "s3://{}/xmlout/".format(bucketName)},
DataAccessRoleArn=access_role,
SourceLanguageCode=sourceCode,
TargetLanguageCodes=[destCode])
print(response["JobId"])
except ClientError as e:
logger.error("An error occured starting the Translate Batch Job: %s" %
e)