BIDI_ML_INFO_EXTRACTION/BiddingKG/dl/interface/extract.py

'''
Created on 2019年1月4日

@author: User
'''

from bs4 import BeautifulSoup, Comment
import copy
import re
import sys
import os
import codecs
import requests
import time

_time1 = time.time()
sys.path.append(os.path.abspath("../.."))
from BiddingKG.dl.common.Utils import *
import BiddingKG.dl.interface.predictor as predictor
import BiddingKG.dl.interface.Preprocessing as Preprocessing
import BiddingKG.dl.interface.getAttributes as getAttributes
import BiddingKG.dl.entityLink.entityLink as entityLink
import BiddingKG.dl.complaint.punish_predictor as punish_rule
import json



''''''
codeNamePredict = predictor.CodeNamePredict()
premPredict = predictor.PREMPredict()
epcPredict = predictor.EPCPredict()
roleRulePredict = predictor.RoleRulePredictor()
timePredict = predictor.TimePredictor()
punish = punish_rule.Punish_Extract()
productPredict = predictor.ProductPredictor()

#自定义jsonEncoder
class MyEncoder(json.JSONEncoder):
    def default(self, obj):
        if isinstance(obj, np.ndarray):
            return obj.tolist()
        elif isinstance(obj, bytes):
            return str(obj, encoding='utf-8')
        elif isinstance(obj, (np.float_, np.float16, np.float32,
                              np.float64)):
            return float(obj)
        elif isinstance(obj,str):
            return obj
        return json.JSONEncoder.default(self, obj)

def predict(doc_id,text,title=""):
    list_articles,list_sentences,list_entitys,_ = Preprocessing.get_preprocessed([[doc_id,text,"","",title]],useselffool=True)

    codeName = codeNamePredict.predict(list_sentences,list_entitys=list_entitys)

    premPredict.predict(list_sentences,list_entitys)
    productPredict.predict(list_sentences,list_entitys)

    roleRulePredict.predict(list_articles,list_sentences, list_entitys,codeName)
    epcPredict.predict(list_sentences,list_entitys)
    timePredict.predict(list_sentences, list_entitys)
    entityLink.link_entitys(list_entitys)
    prem = getAttributes.getPREMs(list_sentences,list_entitys,list_articles)
    list_punish_dic = punish.get_punish_extracts(list_articles,list_sentences, list_entitys)

    return json.dumps(Preprocessing.union_result(Preprocessing.union_result(codeName, prem),list_punish_dic)[0],cls=MyEncoder,sort_keys=True,indent=4,ensure_ascii=False)


def test(name,content):
    user = {
        "content": content,
        "id":name
    }
    myheaders = {'Content-Type': 'application/json'}
    _resp = requests.post("http://192.168.2.101:15015" + '/article_extract', json=user, headers=myheaders, verify=True)
    resp_json = _resp.content.decode("utf-8")
    print(resp_json)
    return resp_json


if __name__=="__main__":
    pass