def get(self: Resource, args: typing.Dict) -> typing.Tuple[typing.Dict, int]:
items = MarkJobService().get_mark_job_data_by_ids(args["mark_job_ids"], args, doc_type_key="entity_doc_type", prefix='RE')
return {
"message": "请求成功",
"result": items,
"count": len(items),
}, 200
def post(self: Resource, args: typing.Dict) -> typing.Tuple[typing.Dict, int]:
MarkJobService().delete_mark_jobs(args["job_ids"])
return {
"message": "批量删除成功",
"result": args
}, 200
def post(self: Resource, args: typing.Dict) -> typing.Tuple[typing.Dict, int]:
"""
message queue回调统一入口
"""
message = args['message']
logger.info(f"receive callback info from mq. response is: {json.dumps(args)}")
if message['business'] in [
'label', # 实体预标注
'classify_label', # 分类预标注
'relation_label', # 实体关系预标注
'wordseg_label' # 分词预标注
]:
update_params = {}
if args.get("task_state"):
if args['task_state'] == 'success': # 如果mq预标注返回成功，则初试状态是unlabel
update_params.update(mark_task_status=int(StatusEnum.unlabel))
else: # 如果mq预标注返回失败，则初试状态是fail
update_params.update(mark_task_status=int(StatusEnum.fail))
if args.get("task_result"):
update_params.update(mark_task_result=args["task_result"])
mark_task, user_task_list = MarkJobService()\
.update_mark_task_and_user_task_by_mark_task_id(mark_task_id=message["task_id"], args=update_params)
MarkJobService().update_mark_job_status_by_mark_task(mark_task=mark_task)
result = UserTaskSchema(many=True).dump(user_task_list)
return {
"message": "更新成功",
"result": result,
}, 201
elif message['business'] in [
'extract', # 实体抽取
'classify_extract', # 分类抽取
'relation_extract', # 实体关系抽取
'wordseg_extract' # 分词抽取
]:
update_params = {}
if args.get("task_state"):
update_params.update(predict_task_status=status_str2int_mapper()[args["task_state"]])
if args.get("task_result"):
update_params.update(predict_task_result=args["task_result"])
predict_task = PredictService().update_predict_task_by_id(predict_task_id=message["task_id"], args=update_params)
result = PredictTaskSchema().dump(predict_task)
return {
"message": "更新成功",
"result": result,
}, 201
def post(self: Resource,
args: typing.Dict) -> typing.Tuple[typing.Dict, int]:
mark_job_ids = args['mark_job_ids'].split(',')
MarkJobService().re_pre_label_mark_job(mark_job_ids,
nlp_task=NlpTaskEnum.wordseg)
return {
"message": "请求成功",
}, 200
def get(self: Resource,
args: typing.Dict) -> typing.Tuple[typing.Dict, int]:
count, result = MarkJobService().get_mark_job_list_by_nlp_task(
args, NlpTaskEnum.relation)
return {
"message": "请求成功",
"result": result,
"count": count,
}, 200
def get(
self: Resource,
job_id: int
) -> typing.Tuple[typing.Dict, int]:
file_path = MarkJobService().export_mark_file(nlp_task_id=int(NlpTaskEnum.classify), mark_job_id=job_id)
return {
"message": "请求成功",
"file_path": file_path
}, 200
def post(self: Resource, args: typing.Dict):
files = args['files']
args['task_type'] = 'manual'
# validate file extensions
for f in files:
if get_ext(f.filename) not in ["txt"]:
abort(400, message="导入已标注序列标注数据仅支持txt格式。")
result = MarkJobService().import_mark_job(files, args, nlp_task=NlpTaskEnum.extract)
return {
"message": "创建成功",
"result": result
}, 201
def post(self: Resource,
args: typing.Dict) -> typing.Tuple[typing.Dict, int]:
files = args['files']
job_type = Common().check_job_type_by_files(files)
if not job_type:
abort(400, message='请上传全部纯文本文档（txt/csv）或者全部电子文档（pdf/word文档）')
else:
args['mark_job_type'] = job_type
result = MarkJobService().create_mark_job(files, NlpTaskEnum.relation,
args)
return {"message": "创建成功", "result": result}, 201
def post(
self: Resource,
args: typing.Dict
) -> typing.Tuple[typing.Dict, int]:
try:
file_path = MarkJobService().export_multi_mark_file(
nlp_task_id=int(NlpTaskEnum.classify), mark_job_id_list=args["job_ids"])
return {
"message": "请求成功",
"file_path": file_path
}, 200
except ValueError as e:
abort(400, message=e.args[0])
def post(self: Resource,
args: typing.Dict) -> typing.Tuple[typing.Dict, int]:
"""
上传已标注数据
"""
files = args['files']
# validate file extensions
for f in files:
if get_ext(f.filename) not in ["txt"]:
abort(400, message="上传已标注分词数据仅支持txt格式。")
result = MarkJobService().import_mark_job(files,
args,
nlp_task=NlpTaskEnum.wordseg)
return {"message": "创建成功", "result": result}, 201
def post(self: Resource,
args: typing.Dict) -> typing.Tuple[typing.Dict, int]:
files = args["files"]
assign_mode = args["assign_mode"]
if assign_mode == AssignModeEnum.together:
abort(400, message="不支持共同标注")
job_type = Common().check_job_type_by_files(files)
if job_type != "text":
abort(400, message="请上传纯文本文档（txt/csv）")
else:
args['mark_job_type'] = job_type
try:
result = MarkJobService().create_mark_job(files,
NlpTaskEnum.wordseg,
args)
return {"message": "创建成功", "result": result}, 201
except TypeError:
abort(400, message="上传文件类型错误")
def post(
self: Resource,
args: typing.Dict
) -> typing.Tuple[typing.Dict, int]:
files = args['files']
for f in files:
if get_ext(f.filename) not in ["csv"]:
abort(400, message="已标注分类数据仅支持csv格式。")
try:
result = MarkJobService().import_mark_job(files, args, nlp_task=NlpTaskEnum.classify)
return {
"message": "创建成功",
"result": result
}, 201
except UnicodeDecodeError:
abort(400, message="文件编码错误 请上传utf-8编码文件")
except KeyError:
abort(400, message="文件格式不合规 请查看csv文件模版")
def delete(self: Resource, job_id: int) -> typing.Tuple[typing.Dict, int]:
MarkJobService().delete_mark_job(job_id)
return {
"message": "删除成功",
}, 200
def post(self: Resource,
args: typing.Dict) -> typing.Tuple[typing.Dict, int]:
MarkJobService.delete_mark_jobs(args['job_ids'])
return {
"message": "删除成功",
}, 200