File size: 2,926 Bytes
5120311 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 |
from entity import Docs, Cluster, Preprocess, SummaryInput
from fastapi import FastAPI
import time
import hashlib
import json
from fastapi.middleware.cors import CORSMiddleware
from iclibs.ic_rabbit import ICRabbitMQ
from get_config import config_params
app = FastAPI()
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
def get_hash_id(item: Docs):
str_hash = ""
for it in item.response["docs"]:
str_hash += it["url"]
str_hash += str(item.top_cluster)
str_hash += str(item.top_sentence)
str_hash += str(item.topn_summary)
str_hash += str(item.top_doc)
str_hash += str(item.threshold)
if item.sorted_field.strip():
str_hash += str(item.sorted_field)
return hashlib.sha224(str_hash.encode("utf-8")).hexdigest()
try:
with open("log_mnews/log.txt") as f:
data_dict = json.load(f)
except Exception as ve:
print(ve)
data_dict = {}
def init_rabbit_queue(usr, passw, host, vir_host, queue_name, durable, max_priority, exchange=""):
connection = ICRabbitMQ(host, vir_host, usr, passw)
connection.init_connection()
channel = connection.init_queue(
queue_name, exchange=exchange, durable=durable, max_priority=max_priority)
return channel, connection, queue_name
@app.post("/mnews/topic_clustering")
async def topic_clustering_v2(item: Docs):
print("command id: ", item.command_id)
docs = item.response["docs"]
meta = item.response.get('meta', {})
# threshold = item.threshold
print("start ")
print("len doc: ", len(docs))
st_time = time.time()
top_cluster = item.top_cluster
top_sentence = item.top_sentence
topn_summary = item.topn_summary
hash_str = get_hash_id(item)
# threshold = 0.1
# item.threshold = threshold
# with open("log/input_{0}.txt".format(st_time), "w+") as f:
# f.write(json.dumps({"docs": docs, "key": item.keyword}))
data_push = {
"threshold": item.threshold,
"top_cluster": top_cluster,
"top_sentence": top_sentence,
"topn_summary": topn_summary,
"hash_str": hash_str,
"st_time": st_time,
"command_id": item.command_id,
"docs": docs,
"meta": meta
}
params = config_params['queue_topic_clustering_mnews']
usr_name = params["usr_name"]
password = str(params["password"])
host = params["host"]
virtual_host = params["virtual_host"]
queue_name = params["queue_name"]
channel_consumer, rb_consumer, queue_consumer = init_rabbit_queue(usr_name, password, host, virtual_host, queue_name, True, 10)
ICRabbitMQ.publish_message(channel_consumer, queue_consumer, data_push, priority= 1,delivery_mode=2, exchange='')
return {"message":"success"}
|