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 process_block_segmenter_kf():
file_ops = FileOperation()
DOWNLOAD_FOLDER = file_ops.create_file_download_dir(config.download_folder)
producer_tok = Producer(config.bootstrap_server)
# instatiation of consumer for respective topic
try:
consumer = consumer_validator()
log_info(
"process_document_segmenter_kf : trying to receive value from consumer ",
LOG_WITHOUT_CONTEXT)
for msg in consumer:
if Consumer.get_json_data(msg.value) == None:
log_info(
'process_document_segmenter_kf - received invalid data {}'.
format(msg.value), None)
continue
data = Consumer.get_json_data(msg.value)
jobid = data['jobID']
log_info(
'process_document_segmenter_kf - received message from kafka, dumping into internal queue',
data)
input_files, workflow_id, jobid, tool_name, step_order = file_ops.json_input_format(
data)
#if input_files[0]['locale'] == 'en':
#############
####################################
Queue.put(data)
log_info(
'process_document_segmenter_kf - request in internal queue {}'.
format(Queue.qsize()), data)
########################################
# else:
# blockMergerOCRQueue.put(data)
# log_info('process_block_merger_kf - request in internal OCR queue {}'.format(blockMergerOCRQueue.qsize()), data)
# We should reject kafka request if internal queue size become too-much.
#
except KafkaConsumerError as e:
response_custom = {}
response_custom['message'] = str(e)
file_ops.error_handler(response_custom, "KAFKA_CONSUMER_ERROR", True)
log_exception(
"process_layout_detector_kf : Consumer didn't instantiate", None,
e)
except KafkaProducerError as e:
response_custom = {}
response_custom['message'] = e.message
file_ops.error_handler(response_custom, "KAFKA_PRODUCER_ERROR", True)
log_exception(
"process_layout_detector_kf : response send to topic %s" %
(config.output_topic), None, e)
def process_vision_ocr_kf():
file_ops = FileOperation()
DOWNLOAD_FOLDER = file_ops.create_file_download_dir(config.download_folder)
producer_tok = Producer(config.bootstrap_server)
# instatiation of consumer for respective topic
try:
consumer = consumer_validator()
log_info("process_vision_ocr_kf : trying to receive value from consumer ", LOG_WITHOUT_CONTEXT)
while True:
wait_for_control = controlQueue.get(block=True)
for msg in consumer:
if Consumer.get_json_data(msg.value) == None:
log_info('process_vision_ocr_kf - received invalid data {}'.format(msg.value), None)
continue
data = Consumer.get_json_data(msg.value)
consumer.commit() # <--- This is what we need
# Optionally, To check if everything went good
print('New Kafka offset: %s' % consumer.committed(TopicPartition(config.input_topic, msg.partition)))
jobid = data['jobID']
log_info('process_vision_ocr_kf - received message from kafka, dumping into internal queue', data)
input_files, workflow_id, jobid, tool_name, step_order = file_ops.json_input_format(data)
#if input_files[0]['locale'] == 'en':
#############
####################################
processQueue.put(data)
log_info('process_vision_ocr_kf - request in internal queue {}'.format(Queue.qsize()),
data)
break
########################################
# else:
# blockMergerOCRQueue.put(data)
# log_info('process_block_merger_kf - request in internal OCR queue {}'.format(blockMergerOCRQueue.qsize()), data)
# We should reject kafka request if internal queue size become too-much.
#
except KafkaConsumerError as e:
response_custom = {}
response_custom['message'] = str(e)
file_ops.error_handler(response_custom, "KAFKA_CONSUMER_ERROR", True)
log_exception("process_vision_ocr_kf : Consumer didn't instantiate", None, e)
except KafkaProducerError as e:
response_custom = {}
response_custom['message'] = e.message
file_ops.error_handler(response_custom, "KAFKA_PRODUCER_ERROR", True)
log_exception("process_vision_ocr_kf : response send to topic %s"%(config.output_topic), None, e)
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 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 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()
from flask.json import jsonify
from flask import request
from src.utilities.utils import FileOperation
from src.resources.response_gen import Response
from src.errors.error_validator import ValidationResponse
from src.errors.errors_exception import FormatError
from src.utilities.model_response import Status
from anuvaad_auditor.loghandler import log_info
from anuvaad_auditor.loghandler import log_error
import config
import time
import src.utilities.app_context as app_context
# sentence block merging
file_ops = FileOperation()
DOWNLOAD_FOLDER = file_ops.create_file_download_dir(config.download_folder)
# rest request for block merging workflow service
class Tesseract_OCR_WF(Resource):
# reading json request and reurnung final response
def post(self):
json_data = request.get_json(force=True)
app_context.init()
app_context.application_context = json_data
log_info("Resource Tesseract_OCR_WF Tesseract_OCR service started",
app_context.application_context)
task_id = str("TESSOCR-" + str(time.time()).replace('.', '')[0:13])
task_starttime = eval(str(time.time()).replace('.', '')[0:13])
#json_data = request.get_json(force = True)
def process_vision_ocr_kf():
file_ops = FileOperation()
DOWNLOAD_FOLDER = file_ops.create_file_download_dir(config.download_folder)
producer_tok = Producer(config.bootstrap_server)