def post(self):
json_data = request.get_json(force=True)
app_context.init()
app_context.application_context = json_data
log_info(
"Resource Layout_Detector_WF Layout_Detector service started",
app_context.application_context)
task_id = str("LD-" + str(time.time()).replace('.', '')[0:13])
task_starttime = eval(str(time.time()).replace('.', '')[0:13])
#json_data = request.get_json(force = True)
try:
error_validator = ValidationResponse(DOWNLOAD_FOLDER)
if error_validator.format_error(json_data) is True:
response_gen = Response(json_data, DOWNLOAD_FOLDER)
response = response_gen.workflow_response(
task_id, task_starttime)
log_info(
"Resource Layout_Detector_WF Layout_Detector api response completed",
app_context.application_context)
return jsonify(response)
except FormatError as e:
log_error(
"Resource Layout_Detector_WF Input json format is not correct or dict_key is missing",
app_context.application_context, e)
return Status.ERR_request_input_format.value
def processRequest(data):
file_ops = FileOperation()
producer_tok = Producer(config.bootstrap_server)
DOWNLOAD_FOLDER = file_ops.file_download(config.download_folder)
task_id = str("ANNO-" + str(time.time()).replace('.', ''))
task_starttime = str(time.time()).replace('.', '')
input_params, workflow_id, jobid, tool_name, step_order = file_ops.json_input_format(
data)
log_info("processing -- received message " + str(jobid), data)
try:
response_gen = Response(data, DOWNLOAD_FOLDER)
result_response = response_gen.workflow_response(
task_id, task_starttime)
if result_response != None:
if "errorID" not in result_response.keys():
push_output(producer_tok, config.output_topic, result_response,
jobid, task_id, data)
log_info(
"processing completed successfully, published at %s" %
(config.output_topic), data)
else:
log_info("processing failed, informed WFM", data)
except Exception as e:
log_exception("exception encountered ", LOG_WITHOUT_CONTEXT, e)
def vision_ocr_request_worker():
file_ops = FileOperation()
DOWNLOAD_FOLDER = file_ops.create_file_download_dir(config.download_folder)
producer_tok = Producer(config.bootstrap_server)
log_info("vision_ocr_request_worker : starting thread ", LOG_WITHOUT_CONTEXT)
while True:
data = processQueue.get(block=True)
#################
task_id = str("vision_ocr" + str(time.time()).replace('.', ''))
###################
task_starttime = str(time.time()).replace('.', '')
input_files, workflow_id, jobid, tool_name, step_order = file_ops.json_input_format(data)
log_info("vision_ocr_request_worker processing -- received message "+str(jobid), data)
try:
response_gen = Response(data, DOWNLOAD_FOLDER)
file_value_response = response_gen.workflow_response(task_id, task_starttime, False)
if file_value_response != None:
if "errorID" not in file_value_response.keys():
push_output(producer_tok, config.output_topic, file_value_response, jobid, task_id,data)
log_info("vision_ocr_request_worker : response send to topic %s"%(config.output_topic), LOG_WITHOUT_CONTEXT)
else:
log_info("vision_ocr_request_worker : error send to error handler", data)
log_info('vision_ocr_request_worker - request in internal queue {}'.format(Queue.qsize()), data)
processQueue.task_done()
except Exception as e:
log_exception("vision_ocr_request_worker ", LOG_WITHOUT_CONTEXT, e)
controlQueue.put(1)
def word_detector_request_worker():
file_ops = FileOperation()
DOWNLOAD_FOLDER = file_ops.create_file_download_dir(config.download_folder)
producer_tok = Producer(config.bootstrap_server)
log_info("word_detector_request_worker : starting thread ",
LOG_WITHOUT_CONTEXT)
while True:
data = Queue.get(block=True)
#################
task_id = str("word_detector" + str(time.time()).replace('.', ''))
###################
task_starttime = str(time.time()).replace('.', '')
input_files, workflow_id, jobid, tool_name, step_order = file_ops.json_input_format(
data)
log_info(
"word_detector_request_worker processing -- received message " +
str(jobid), data)
try:
response_gen = Response(data, DOWNLOAD_FOLDER)
file_value_response = response_gen.workflow_response(
task_id, task_starttime, False)
if file_value_response != None:
push_output(producer_tok, config.output_topic,
file_value_response, jobid, task_id, data)
log_info(
"word_detector_request_worker : response send to topic %s"
% (config.output_topic), LOG_WITHOUT_CONTEXT)
else:
erro_obj = {
'code': 400,
'jobID': jobid,
'message': "Word detector failed"
}
producer_tok.push_data_to_queue(
config.KAFKA_ANUVAAD_ETL_WF_ERROR_TOPIC, erro_obj)
log_info(
"word_detector_request_worker : error send to error handler",
data)
log_info(
'word_detector_request_worker - request in internal queue {}'.
format(Queue.qsize()), data)
Queue.task_done()
except Exception as e:
log_exception("word_detector_request_worker ", LOG_WITHOUT_CONTEXT,
e)
def post(self):
json_data = request.get_json(force=True)
app_context.init()
app_context.application_context = json_data
log_info("Resource Vision_OCR service started", app_context.application_context)
try:
error_validator = ValidationResponse(DOWNLOAD_FOLDER)
if error_validator.format_error(json_data) is True:
response_gen = Response(json_data, DOWNLOAD_FOLDER)
response = response_gen.nonwf_response()
log_info("Resource Vision_OCR api response completed", app_context.application_context)
return jsonify(response)
except FormatError as e:
log_error("Resource Vision_OCR Input json format is not correct or dict_key is missing", app_context.application_context, e)
return Status.ERR_request_input_format.value
def post(self):
log_info("Resource BlockMerger", "Block-merger service started", None)
json_data = request.get_json(force=True)
try:
error_validator = ValidationResponse(DOWNLOAD_FOLDER)
if error_validator.format_error(json_data) is True:
response_gen = Response(json_data, DOWNLOAD_FOLDER)
response = response_gen.nonwf_response()
log_info("Resource BlockMerger",
"Block-merger api response completed", None)
return jsonify(response)
except FormatError as e:
log_error(
"Resource BlockMerger",
"Input json format is not correct or dict_key is missing",
None, e)
return Status.ERR_request_input_format.value
def process_merger_kf():
file_ops = FileOperation()
DOWNLOAD_FOLDER = file_ops.create_file_download_dir(config.download_folder)
task_id = str("BM-" + str(time.time()).replace('.', ''))
task_starttime = str(time.time()).replace('.', '')
# instatiation of consumer for respective topic
try:
consumer_class = Consumer(config.input_topic, config.bootstrap_server)
consumer = consumer_class.consumer_instantiate()
log_info("process_merger_kf", "trying to receive value from consumer",
None)
thread_instance = 0
for msg in consumer:
try:
data = msg.value
task_id = str("BM-" + str(time.time()).replace('.', ''))
task_starttime = str(time.time()).replace('.', '')
input_files, workflow_id, jobid, tool_name, step_order = file_ops.json_input_format(
data)
log_info("process_merger_kf", "kafka request arrived ", jobid)
response_gen = Response(data, DOWNLOAD_FOLDER)
t1 = threading.Thread(
target=response_gen.multi_thred_block_merger,
args=(task_id, task_starttime, jobid),
name='BM-thread-' + str(thread_instance))
t1.start()
thread_instance += 1
log_info("multithread", "block-merger running on multithread",
None)
'''
file_value_response = response_gen.workflow_response(task_id, task_starttime)
if "errorID" not in file_value_response.keys():
producer = Producer()
producer.push_data_to_queue(config.output_topic, file_value_response, jobid, task_id)
else:
log_info("process_merger_kf", "error send to error handler", jobid)'''
except Exception as e:
log_exception("process_pdf_kf",
"exception while consuming the records", jobid,
e)
except KafkaConsumerError as e:
response_custom = CustomResponse(Status.ERR_STATUS.value, None, None)
response_custom.status_code['message'] = str(e)
file_ops.error_handler(response_custom.status_code,
"KAFKA_CONSUMER_ERROR", True)
log_exception("process_pdf_kf", "Consumer didn't instantiate", None, e)
except KafkaProducerError as e:
response_custom = e.code
response_custom['message'] = e.message
file_ops.error_handler(response_custom, "KAFKA_PRODUCER_ERROR", True)
log_exception("process_pdf_kf",
"response send to topic %s" % (config.output_topic),
response_custom['jobID'], e)
def post(self):
log_info("Resource BlockMergerWF", "Block-merger service started",
None)
task_id = str("BM-" + str(time.time()).replace('.', ''))
task_starttime = str(time.time()).replace('.', '')
json_data = request.get_json(force=True)
try:
error_validator = ValidationResponse(DOWNLOAD_FOLDER)
if error_validator.format_error(json_data) is True:
response_gen = Response(json_data, DOWNLOAD_FOLDER)
response = response_gen.workflow_response(
task_id, task_starttime)
log_info("Resource BlockMergerWF",
"Block-merger api response completed", None)
return jsonify(response)
except FormatError as e:
log_error(
"Resource BlockMergerWF",
"Input json format is not correct or dict_key is missing",
None, e)
return Status.ERR_request_input_format.value
def block_merger_request_worker():
file_ops = FileOperation()
DOWNLOAD_FOLDER = file_ops.create_file_download_dir(config.download_folder)
producer_tok = Producer(config.bootstrap_server)
while True:
data = blockMergerQueue.get(block=True)
task_id = str("BM-" + str(time.time()).replace('.', ''))
task_starttime = str(time.time()).replace('.', '')
input_files, workflow_id, jobid, tool_name, step_order = file_ops.json_input_format(
data)
log_info(
"block_merger_request_worker processing -- received message " +
str(jobid), data)
response_gen = Response(data, DOWNLOAD_FOLDER)
file_value_response = response_gen.workflow_response(
task_id, task_starttime, False)
if file_value_response != None:
if "errorID" not in file_value_response.keys():
push_output(producer_tok, config.output_topic,
file_value_response, jobid, task_id)
log_info(
"process_block_merger_kf : response send to topic %s" %
(config.output_topic), None)
else:
log_info(
"process_block_merger_kf : error send to error handler",
jobid)
log_info(
'block_merger_request_worker - request in internal queue {}'.
format(blockMergerQueue.qsize()), jobid)
blockMergerQueue.task_done()
