def processImage(documentId, bucketName, objectName, callerId):
response = callTextract(bucketName, objectName)
print("Generating output for documentId: {}".format(documentId))
opg = OutputGenerator(documentId=documentId,
response=response,
bucketName=textractBucketName,
objectName=objectName,
forms=False,
tables=False)
tagging = "documentId={}".format(documentId)
opg.writeTextractOutputs(taggingStr=tagging)
lineage_client.recordLineage({
"documentId": documentId,
"callerId": callerId,
"sourceBucketName": bucketName,
"targetBucketName": textractBucketName,
"sourceFileName": objectName,
"targetFileName": objectName
})
def processRequest(request):
output = ""
status = request['jobStatus']
jobId = request['jobId']
jobTag = request['jobTag']
jobAPI = request['jobAPI']
bucketName = request['bucketName']
objectName = request['objectName']
pipeline_client.body = {
"documentId": jobTag,
"bucketName": bucketName,
"objectName": objectName,
"stage": PIPELINE_STAGE
}
if status == 'FAILED':
pipeline_client.stageFailed(
"Textract Analysis didn't complete successfully")
raise Exception(
"Textract job for document ID {}; bucketName {} fileName {}; failed during Textract analysis. Please double check the document quality"
.format(jobTag, bucketName, objectName))
pipeline_client.stageInProgress()
try:
pages = getJobResults(jobAPI, jobId)
except Exception as e:
pipeline_client.stageFailed()
raise (e)
print("Result pages received: {}".format(len(pages)))
detectForms = False
detectTables = False
if (jobAPI == "StartDocumentAnalysis"):
detectForms = True
detectTables = True
try:
opg = OutputGenerator(documentId=jobTag,
response=pages,
bucketName=textractBucketName,
objectName=objectName,
forms=detectForms,
tables=detectTables)
except Exception as e:
pipeline_client.stageFailed(
"Could not convert results from Textract into processable object. Try uploading again."
)
raise (e)
tagging = "documentId={}".format(jobTag)
opg.writeTextractOutputs(taggingStr=tagging)
lineage_client.recordLineage({
"documentId": jobTag,
"callerId": request["callerId"],
"sourceBucketName": bucketName,
"targetBucketName": textractBucketName,
"sourceFileName": objectName,
"targetFileName": objectName
})
output = "Processed -> Document: {}, Object: {}/{} processed.".format(
jobTag, bucketName, objectName)
pipeline_client.stageSucceeded()
print(output)
return {'statusCode': 200, 'body': output}
