我想将一些文件内容加载到内存中,以便可以立即查询。
在齿轮工中,我正在加载文件并将其置于侦听模式。使用 gearman 客户端发出请求时,worker
只返回一次加载的内容,下次客户端收到None
工人:
class GetLexiconFiles(object):
def __init__(self):
self.gm_worker = gearman.GearmanWorker(['localhost:4730'])
self.loadFiles()
self.gm_worker.register_task('load_db', self.task_listener_reverse)
#self.loadFiles()
#self.gm_worker.work()
def task_listener_reverse(self, gearman_worker, gearman_job):
k=float('inf')
#print "Started loading file"
self.input_text = self.input_text.split('n')
print "Loading completed"
lexicon = defaultdict(list)
for i, line in enumerate(self.input_text):
#print "line is : ", line
if i >= k: break
#if i % 100000 == 0: print >>sys.stderr, i
try:
if line != '':
nl, dbs = line.split(' ', 1)
nl = int(nl)
dbs = self.str2obj(dbs)
lexicon[nl].append(dbs)
else:
pass
except:
print >>sys.stderr, 'could not parse line %r' % line
print traceback.format_exc()
continue
return json.dumps(lexicon)
if __name__ == '__main__':
GetLexiconFiles().gm_worker.work()
客户:
def check_request_status(job_request):
if job_request.complete:
#data = json.loads(job_request.result)
print "Job %s finished! Result: %s - %s" % (job_request.job.unique, job_request.state, job_request.result)
elif job_request.timed_out:
print "Job %s timed out!"
elif job_request.state == JOB_UNKNOWN:
print "Job %s connection failed!"
gm_client = gearman.GearmanClient(['localhost:4730'])
tasks = [{'task': 'load_lexicon', 'data': 'This is testing sentence'}, {'task': 'load_db', 'data': 'This is db testing'}]
submitted_requests = gm_client.submit_multiple_jobs(tasks, background=False, wait_until_complete=False)
completed_requests = gm_client.wait_until_jobs_completed(submitted_requests)
print completed_requests[1].result
for completed_job_request in completed_requests:
check_request_status(completed_job_request)
self.input_text = self.input_text.split('n')
使用这行代码,您将字符串转换为字符串列表。
由于您将结果保存回self.input_text下次调用该函数时self.input_text该函数已经是一个列表,并且会引发异常。