def post(self):
log_info("Resource Pdf2HtmlConversion", "pdf2html 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 Pdf2HtmlConversion", "pdf2html api response completed", None)
return jsonify(response)
except FormatError as e:
log_error("Resource Pdf2HtmlConversion", "Input json format is not correct or dict_key is missing", None, e)
return Status.ERR_request_input_format.value
def post(self):
log_info("Resource Pdf2HtmlConversionWF", "pdf2html service started", None)
task_id = str("PDF2HTML-" + 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 Pdf2HtmlConversionWF", "pdf2html api response completed", None)
return jsonify(response)
except FormatError as e:
log_error("Resource Pdf2HtmlConversionWF", "Input json format is not correct or dict_key is missing", None, e)
return Status.ERR_request_input_format.value
def post(self):
task_id = str("TOK-" + str(time.time()).replace('.', '')[0:13])
task_starttime = eval(str(time.time()).replace('.', '')[0:13])
json_data = request.get_json(force=True)
log_info("Resource BlockTokenize : data from api request received",
json_data)
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_block_tokeniser(
task_id, task_starttime)
log_info(
"Resource BlockTokenize : Tokenisation api response completed",
json_data)
return jsonify(response)
except FormatError as e:
log_error(
"Resource BlockTokenize : Input json format is not correct or dict_key is missing",
json_data, e)
return Status.ERR_request_input_format.value
def nonwf_response(self):
log_info("non workflow response", "started the response generation",
None)
input_files = self.json_data['files']
error_validator = ValidationResponse(self.DOWNLOAD_FOLDER)
pdf_html_service = Pdf2HtmlService(self.DOWNLOAD_FOLDER)
try:
error_validator.inputfile_list_empty(input_files)
output_file_response = list()
for item in input_files:
input_filename, in_file_type, in_locale = file_ops.accessing_files(
item)
output_htmlfiles_path, output_pngfiles_path = pdf_html_service.pdf2html(
self.DOWNLOAD_FOLDER, input_filepath)
file_res = file_ops.one_filename_response(
input_filename, output_htmlfiles_path,
output_pngfiles_path, in_locale, in_file_type)
output_file_response.append(file_res)
response_true = Status.SUCCESS.value
response_true['output'] = output_file_response
log_info("non workflow_response",
"successfully generated response for rest server", None)
return response_true
except FileErrors as e:
response_custom = Status.ERR_STATUS.value
response_custom['message'] = e.message
response = file_ops.error_handler(response_custom, e.code, False)
log_exception("non workflow_response",
"some error occured while validating file", None, e)
return response
except ServiceError as e:
response_custom = Status.ERR_STATUS.value
response_custom['message'] = str(e)
response = file_ops.error_handler(response_custom, "SERVICE_ERROR",
False)
log_exception(
"non workflow_response",
"Something went wrong during pdf to html conversion.", None, e)
return response
def workflow_response_block_tokeniser(self, task_id, task_starttime):
input_key, workflow_id, jobid, tool_name, step_order, user_id = file_ops.json_input_format(self.json_data)
log_info("workflow_response : started the block tokenisation response generation", self.json_data)
error_validator = ValidationResponse(self.DOWNLOAD_FOLDER)
tokenisation = Tokenisation(self.DOWNLOAD_FOLDER, self.json_data)
try:
error_validator.wf_keyerror(jobid, workflow_id, tool_name, step_order)
error_validator.inputfile_list_empty(input_key)
blocks_list, record_id, model_id, in_locale = file_ops.get_input_values_for_block_tokenise(input_key)
input_key = tokenisation.adding_tokenised_text_blockmerger(input_key, in_locale, 0)
task_endtime = eval(str(time.time()).replace('.', '')[0:13])
response_true = CustomResponse(Status.SUCCESS.value, jobid, task_id)
response_success = response_true.success_response(workflow_id, task_starttime, task_endtime, tool_name, step_order, input_key)
response = copy.deepcopy(response_success)
log_info("workflow_response : successfully generated response for workflow", self.json_data)
return response
except WorkflowkeyError as e:
response_custom = self.json_data
response_custom['taskID'] = task_id
response_custom['message'] = str(e)
response = file_ops.error_handler(response_custom, "WORKFLOWKEY-ERROR", True)
log_exception("workflow_response : workflow key error: key value missing", self.json_data, e)
response = copy.deepcopy(response)
return response
except FileErrors as e:
response_custom = self.json_data
response_custom['taskID'] = task_id
response_custom['message'] = e.message
response = file_ops.error_handler(response_custom, e.code, True)
log_exception("workflow_response : some error occured while validating file", self.json_data, e)
response = copy.deepcopy(response)
return response
except ServiceError as e:
response_custom = self.json_data
response_custom['taskID'] = task_id
response_custom['message'] = str(e)
response = file_ops.error_handler(response_custom, "SERVICE_ERROR", True)
log_exception("workflow_response : Error occured during tokenisation or file writing", self.json_data, e)
response = copy.deepcopy(response)
return response
except Exception as e:
response_custom = self.json_data
response_custom['taskID'] = task_id
response_custom['message'] = str(e)
response = file_ops.error_handler(response_custom, "SERVICE_ERROR", True)
log_exception("workflow_response : Any random exception", self.json_data, e)
response = copy.deepcopy(response)
return response
def nonwf_response(self):
log_info("non workflow response : started the response generation", None)
error_validator = ValidationResponse(self.DOWNLOAD_FOLDER)
tokenisation = Tokenisation(self.DOWNLOAD_FOLDER, self.json_data)
try:
if 'files' in self.json_data.keys():
input_files = self.json_data['files']
error_validator.inputfile_list_empty(input_files)
output_file_response = list()
for i, item in enumerate(input_files):
input_filename, in_file_type, in_locale = file_ops.accessing_files(item)
input_file_data = file_ops.read_txt_file(input_filename)
error_validator.file_encoding_error(input_file_data)
output_filename = tokenisation.tokenisation_response(input_file_data, in_locale, i)
file_res = file_ops.one_filename_response(input_filename, output_filename, in_locale, in_file_type)
output_file_response.append(file_res)
else:
input_paragraphs = self.json_data['text']
input_locale = self.json_data['locale']
tokenised_sentences = [tokenisation.tokenisation_core([input_paragraph], input_locale) for input_paragraph in input_paragraphs]
output_list_text = [{"inputText" : x, "tokenisedSentences" : y} for x, y in zip(input_paragraphs, tokenised_sentences)]
output_file_response = {'tokenisedText' : output_list_text, 'locale':input_locale}
response_true = Status.SUCCESS.value
response_true['output'] = output_file_response
log_info("non workflow_response : successfully generated response for rest server", None)
return response_true
except FileErrors as e:
response_custom = Status.ERR_STATUS.value
response_custom['message'] = e.message
response = file_ops.error_handler(response_custom, e.code, False)
log_exception("non workflow_response : some error occured while validating file", None, e)
return response
except FileEncodingError as e:
response_custom = Status.ERR_STATUS.value
response_custom['message'] = str(e)
response = file_ops.error_handler(response_custom, "ENCODING_ERROR", False)
log_exception("non workflow_response : service supports only utf-16 encoded file", None, e)
return response
except ServiceError as e:
response_custom = Status.ERR_STATUS.value
response_custom['message'] = str(e)
response = file_ops.error_handler(response_custom, "SERVICE_ERROR", False)
log_exception("non workflow_response : Error occured during tokenisation or file writing", None, e)
return response
def workflow_response(self, task_id, task_starttime):
input_key, workflow_id, jobid, tool_name, step_order = file_ops.json_input_format(
self.json_data)
log_info("workflow_response : started the response generation",
self.json_data)
error_validator = ValidationResponse(self.DOWNLOAD_FOLDER)
tokenisation = Tokenisation(self.DOWNLOAD_FOLDER, self.json_data)
try:
error_validator.wf_keyerror(jobid, workflow_id, tool_name,
step_order)
error_validator.inputfile_list_empty(input_key)
if 'files' in input_key.keys():
output_file_response = list()
for i, item in enumerate(input_key['files']):
input_filename, in_file_type, in_locale = file_ops.accessing_files(
item)
if in_file_type == "txt":
input_file_data = file_ops.read_txt_file(
input_filename)
error_validator.file_encoding_error(input_file_data)
output_filename = tokenisation.tokenisation_response(
input_file_data, in_locale, i)
elif in_file_type == "json":
input_jsonfile_data = file_ops.read_json_file(
input_filename)
input_jsonfile_data['result'] = [
tokenisation.adding_tokenised_text_blockmerger(
item, in_locale, page_id) for page_id, item in
enumerate(input_jsonfile_data['result'])
]
output_filename = tokenisation.writing_json_file_blockmerger(
i, input_jsonfile_data)
file_res = file_ops.one_filename_response(
input_filename, output_filename, in_locale,
in_file_type)
output_file_response.append(file_res)
else:
input_paragraphs = input_key['text']
input_locale = input_key['locale']
tokenised_sentences = [
tokenisation.tokenisation_core([input_paragraph],
input_locale)
for input_paragraph in input_paragraphs
]
output_list_text = [{
"inputText": x,
"tokenisedSentences": y
} for x, y in zip(input_paragraphs, tokenised_sentences)]
output_file_response = {
'tokenisedText': output_list_text,
'locale': input_locale
}
task_endtime = str(time.time()).replace('.', '')
response_true = CustomResponse(Status.SUCCESS.value, jobid,
task_id)
response_success = response_true.success_response(
workflow_id, task_starttime, task_endtime, tool_name,
step_order, output_file_response)
response = copy.deepcopy(response_success)
log_info(
"workflow_response : successfully generated response for workflow",
self.json_data)
return response
except WorkflowkeyError as e:
response_custom = self.json_data
response_custom['taskID'] = task_id
response_custom['message'] = str(e)
response = file_ops.error_handler(response_custom,
"WORKFLOWKEY-ERROR", True)
log_exception(
"workflow_response : workflow key error: key value missing",
self.json_data, e)
response = copy.deepcopy(response)
return response
except FileErrors as e:
response_custom = self.json_data
response_custom['taskID'] = task_id
response_custom['message'] = e.message
response = file_ops.error_handler(response_custom, e.code, True)
log_exception(
"workflow_response : some error occured while validating file",
self.json_data, e)
response = copy.deepcopy(response)
return response
except FileEncodingError as e:
response_custom = self.json_data
response_custom['taskID'] = task_id
response_custom['message'] = str(e)
response = file_ops.error_handler(response_custom,
"ENCODING_ERROR", True)
log_exception(
"workflow_response : service supports only utf-16 encoded file",
self.json_data, e)
response = copy.deepcopy(response)
return response
except ServiceError as e:
response_custom = self.json_data
response_custom['taskID'] = task_id
response_custom['message'] = str(e)
response = file_ops.error_handler(response_custom, "SERVICE_ERROR",
True)
log_exception(
"workflow_response : Error occured during tokenisation or file writing",
self.json_data, e)
response = copy.deepcopy(response)
return response
def workflow_response(self, task_id, task_starttime):
input_key, workflow_id, jobid, tool_name, step_order, user_id = file_ops.json_input_format(
self.json_data)
log_info("workflow_response : started the response generation",
self.json_data)
error_validator = ValidationResponse(self.DOWNLOAD_FOLDER)
tokenisation = Tokenisation(self.DOWNLOAD_FOLDER, self.json_data)
try:
error_validator.wf_keyerror(
jobid, workflow_id, tool_name,
step_order) # Validating Workflow key-values
error_validator.inputfile_list_empty(
input_key
) # Validating Input key for files input and only text input
# input key is a dictionary data for files input, "files" as a key
if not isinstance(input_key, list):
if 'files' in input_key.keys():
output_file_response = list()
for i, item in enumerate(input_key['files']):
input_filename, in_file_type, in_locale = file_ops.accessing_files(
item)
if in_file_type == "txt":
input_file_data = file_ops.read_txt_file(
input_filename)
error_validator.file_encoding_error(
input_file_data)
output_filename = tokenisation.tokenisation_response(
input_file_data, in_locale, i)
elif in_file_type == "json":
input_jsonfile_data, file_write = file_ops.read_json_file(
input_filename)
# input_jsonfile_data['result'] = tokenisation.getting_incomplete_text_merging_blocks(input_jsonfile_data['result'])
input_jsonfile_data['result'] = [
tokenisation.adding_tokenised_text_blockmerger(
item, in_locale, page_id) for page_id, item
in enumerate(input_jsonfile_data['result'])
]
input_jsonfile_data[
'result'] = tokenisation.getting_incomplete_text_merging_blocks(
input_jsonfile_data['result'])
input_jsonfile_data['file_locale'] = in_locale
#tokenisation.sending_data_to_content_handler(jobid, user_id, input_jsonfile_data)
json_data_write = json.dumps(input_jsonfile_data)
file_write.seek(0)
file_write.truncate()
file_write.write(json_data_write)
output_filename = input_filename
file_res = file_ops.one_filename_response(
input_filename, output_filename, in_locale,
in_file_type)
output_file_response.append(file_res)
# input key is a list data of objects, object contain text and language code
else:
output_file_response = []
for paragraph in input_key:
input_paragraphs = paragraph['text']
input_locale = paragraph['locale']
tokenised_sentences = [
tokenisation.tokenisation_core([input_paragraph],
input_locale)
for input_paragraph in input_paragraphs
]
output_list_text = [{
"inputText": x,
"tokenisedSentences": y
} for x, y in zip(input_paragraphs, tokenised_sentences)]
output_per_para = {
'tokenisedText': output_list_text,
'locale': input_locale
}
output_file_response.append(output_per_para)
task_endtime = eval(str(time.time()).replace('.', '')[0:13])
response_true = CustomResponse(Status.SUCCESS.value, jobid,
task_id)
response_success = response_true.success_response(
workflow_id, task_starttime, task_endtime, tool_name,
step_order, output_file_response)
response = copy.deepcopy(response_success)
log_info(
"workflow_response : successfully generated response for workflow",
self.json_data)
return response
# exceptions for workflow key error
except WorkflowkeyError as e:
response_custom = self.json_data
response_custom['taskID'] = task_id
response_custom['message'] = str(e)
response = file_ops.error_handler(response_custom,
"WORKFLOWKEY-ERROR", True)
log_exception(
"workflow_response : workflow key error: key value missing",
self.json_data, e)
response = copy.deepcopy(response)
return response
# exceptions for input key data validation
except FileErrors as e:
response_custom = self.json_data
response_custom['taskID'] = task_id
response_custom['message'] = e.message
response = file_ops.error_handler(response_custom, e.code, True)
log_exception(
"workflow_response : some error occured while validating file",
self.json_data, e)
response = copy.deepcopy(response)
return response
# checking filedata unicodes and null data
except FileEncodingError as e:
response_custom = self.json_data
response_custom['taskID'] = task_id
response_custom['message'] = str(e)
response = file_ops.error_handler(response_custom,
"ENCODING_ERROR", True)
log_exception(
"workflow_response : service supports only utf-16 encoded file",
self.json_data, e)
response = copy.deepcopy(response)
return response
# exceptions for tokenisation core logic and file writing of tokenised output
except ServiceError as e:
response_custom = self.json_data
response_custom['taskID'] = task_id
response_custom['message'] = str(e)
response = file_ops.error_handler(response_custom, "SERVICE_ERROR",
True)
log_exception(
"workflow_response : Error occured during tokenisation or file writing",
self.json_data, e)
response = copy.deepcopy(response)
return response
# any other exception i.e. not covered in above exceptions
except Exception as e:
response_custom = self.json_data
response_custom['taskID'] = task_id
response_custom['message'] = str(e)
response = file_ops.error_handler(response_custom, "SERVICE_ERROR",
True)
log_exception("workflow_response : Any random exception",
self.json_data, e)
response = copy.deepcopy(response)
return response
def workflow_response(self, task_id, task_starttime):
input_files, workflow_id, jobid, tool_name, step_order = file_ops.json_input_format(
self.json_data)
log_info("workflow_response", "started the response generation", jobid)
error_validator = ValidationResponse(self.DOWNLOAD_FOLDER)
pdf_html_service = Pdf2HtmlService(self.DOWNLOAD_FOLDER)
try:
error_validator.wf_keyerror(jobid, workflow_id, tool_name,
step_order)
error_validator.inputfile_list_error(input_files)
output_file_response = list()
for item in input_files:
input_filename, in_file_type, in_locale = file_ops.accessing_files(
item)
input_filepath = file_ops.input_path(input_filename)
output_htmlfiles_path, output_pngfiles_path = pdf_html_service.pdf2html(
input_filepath, jobid)
file_res = file_ops.one_filename_response(
input_filename, output_htmlfiles_path,
output_pngfiles_path, in_locale, in_file_type)
output_file_response.append(file_res)
task_endtime = str(time.time()).replace('.', '')
response_true = CustomResponse(Status.SUCCESS.value, jobid,
task_id)
response_success = response_true.success_response(
workflow_id, task_starttime, task_endtime, tool_name,
step_order, output_file_response)
response = copy.deepcopy(response_success)
log_info("workflow_response",
"successfully generated response for workflow", jobid)
return response
except WorkflowkeyError as e:
response_custom = CustomResponse(Status.ERR_STATUS.value, jobid,
task_id)
response_custom.status_code['message'] = str(e)
response = file_ops.error_handler(response_custom.status_code,
"WORKFLOWKEY-ERROR", True)
log_exception("workflow_response",
"workflow key error: key value missing", jobid, e)
response = copy.deepcopy(response)
return response
except FileErrors as e:
response_custom = CustomResponse(Status.ERR_STATUS.value, jobid,
task_id)
response_custom.status_code['message'] = e.message
response = file_ops.error_handler(response_custom.status_code,
e.code, True)
log_exception("workflow_response",
"some error occured while validating file", jobid, e)
response = copy.deepcopy(response)
return response
except ServiceError as e:
response_custom = CustomResponse(Status.ERR_STATUS.value, jobid,
task_id)
response_custom.status_code['message'] = str(e)
response = file_ops.error_handler(response_custom.status_code,
"SERVICE_ERROR", True)
log_exception(
"workflow_response",
"Something went wrong during pdf to html conversion.", jobid,
e)
response = copy.deepcopy(response)
return response