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 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')
