BaseDataMaintenance/BaseDataMaintenance/common/Utils.py

'''
Created on 2018年12月20日

@author: User
'''

import numpy as np
import re
import gensim

import os

from threading import RLock

# from pai_tf_predict_proto import tf_predict_pb2
import requests

import time
from bs4 import BeautifulSoup


model_w2v = None
lock_model_w2v = RLock()

USE_PAI_EAS = False

Lazy_load = False

ILLEGAL_CHARACTERS_RE = re.compile(r'[\000-\010]|[\013-\014]|[\016-\037]')

import smtplib
from email.mime.application import MIMEApplication
from email.mime.multipart import MIMEMultipart
from email.utils import formataddr

ILLEGAL_CHARACTERS_RE = re.compile(r'[\000-\010]|[\013-\014]|[\016-\037]')

def getLegal_str(_str):
    if _str is not None:
        return ILLEGAL_CHARACTERS_RE.sub("",str(_str))

import traceback
dict_server = {}

def getServer(host,username,password,reconnect=False):
    key = "%s-%s-%s"%(host,username,password)
    if key in dict_server:
        server = dict_server[key]
        if reconnect:
            server = smtplib.SMTP_SSL(host, 465)
            server.login(username,password)
    else:
        server = smtplib.SMTP_SSL(host, 465)
        server.login(username,password)
        dict_server[key] = server
    return server
from email.mime.text import MIMEText
def sendEmail(host,username,password,receivers,subject="数据导出",content="",attachs=[]):
    try:
        #处理附件
        msg = MIMEMultipart()
        msg["From"] = formataddr(["广州比地数据科技有限公司",username])
        msg["To"] = formataddr(["客户",receivers[0]])
        msg["Subject"] = subject
        message = MIMEText(content, 'plain', 'utf-8')
        for at in attachs:
            xlsfile = MIMEApplication(open(at,"rb").read())
            xlsfile.add_header("Content-Disposition","attachment",filename=('gbk', '', at.split("/")[-1]))
            log(at.split("/")[-1])
            msg.attach(xlsfile)
        server = getServer(host,username,password)
        server.sendmail(username,receivers,msg.as_string())
        log("发送邮件成功%s"%str(attachs))

    except smtplib.SMTPServerDisconnected as e:
        server = getServer(host,username,password,reconnect=True)
        server.sendmail(username,receivers,msg.as_string())
        log("发送邮件成功%s"%str(attachs))

    except Exception as e:
        traceback.print_exc()
        log("发送邮件错误%s"%str(e))
    finally:
        server.close()

mobile_pattern = re.compile("^1\d{10}$")
def recog_likeType(phone):
    if re.search(mobile_pattern,phone) is not None:
        return "mobile"
    else:
        return "phone"

def article_limit(soup,limit_words=30000):
    sub_space = re.compile("\s+")
    def soup_limit(_soup,_count,max_count=30000,max_gap=500):
        """
        :param _soup: soup
        :param _count: 当前字数
        :param max_count: 字数最大限制
        :param max_gap: 超过限制后的最大误差
        :return:
        """
        _gap = _count - max_count
        _is_skip = False
        next_soup = None
        while len(_soup.find_all(recursive=False)) == 1 and \
                _soup.get_text(strip=True) == _soup.find_all(recursive=False)[0].get_text(strip=True):
            _soup = _soup.find_all(recursive=False)[0]
        if len(_soup.find_all(recursive=False)) == 0:
            _soup.string = str(_soup.get_text())[:max_count-_count]
            _count += len(re.sub(sub_space, "", _soup.string))
            _gap = _count - max_count
            next_soup = None
        else:
            for _soup_part in _soup.find_all(recursive=False):
                if not _is_skip:
                    _count += len(re.sub(sub_space, "", _soup_part.get_text()))
                    if _count >= max_count:
                        _gap = _count - max_count
                        if _gap <= max_gap:
                            _is_skip = True
                        else:
                            _is_skip = True
                            next_soup = _soup_part
                            _count -= len(re.sub(sub_space, "", _soup_part.get_text()))
                            continue
                else:
                    _soup_part.decompose()
        return _count,_gap,next_soup

    text_count = 0
    have_attachment = False
    attachment_part = None
    for child in soup.find_all(recursive=True):
        if child.name == 'div' and 'class' in child.attrs:
            if "richTextFetch" in child['class']:
                child.insert_before("##attachment##")
                attachment_part = child
                have_attachment = True
                break
    if not have_attachment:
        # 无附件
        if len(re.sub(sub_space, "", soup.get_text())) > limit_words:
            text_count,gap,n_soup = soup_limit(soup,text_count,max_count=limit_words,max_gap=500)
            while n_soup:
                text_count, gap, n_soup = soup_limit(n_soup, text_count, max_count=limit_words, max_gap=500)

    else:
        # 有附件
        _text = re.sub(sub_space, "", soup.get_text())
        _text_split = _text.split("##attachment##")
        if len(_text_split[0])>limit_words:
            main_soup = attachment_part.parent
            main_text = main_soup.find_all(recursive=False)[0]
            text_count, gap, n_soup = soup_limit(main_text, text_count, max_count=limit_words, max_gap=500)
            while n_soup:
                text_count, gap, n_soup = soup_limit(n_soup, text_count, max_count=limit_words, max_gap=500)
        if len(_text_split[1])>limit_words:
            # attachment_html纯文本，无子结构
            if len(attachment_part.find_all(recursive=False))==0:
                attachment_part.string = str(attachment_part.get_text())[:limit_words]
            else:
                attachment_text_nums = 0
                attachment_skip = False
                for part in attachment_part.find_all(recursive=False):
                    if not attachment_skip:
                        last_attachment_text_nums = attachment_text_nums
                        attachment_text_nums = attachment_text_nums + len(re.sub(sub_space, "", part.get_text()))
                        if attachment_text_nums>=limit_words:
                            part.string = str(part.get_text())[:limit_words-last_attachment_text_nums]
                            attachment_skip = True
                    else:
                        part.decompose()
    soup = str(soup).replace("##attachment##","")
    return soup

def soup_limit(_soup,_count,max_count=30000,max_gap=500,sub_space = re.compile("\s+")):
    """
    :param _soup: soup
    :param _count: 当前字数
    :param max_count: 字数最大限制
    :param max_gap: 超过限制后的最大误差
    :return:
    """
    _gap = _count - max_count
    _is_skip = False
    next_soup = None
    while len(_soup.find_all(recursive=False)) == 1 and \
            _soup.get_text(strip=True) == _soup.find_all(recursive=False)[0].get_text(strip=True):
        _soup = _soup.find_all(recursive=False)[0]
    if len(_soup.find_all(recursive=False)) == 0:
        _soup.string = str(_soup.get_text())[:max_count-_count]
        _count += len(re.sub(sub_space, "", _soup.string))
        _gap = _count - max_count
        next_soup = None
    else:
        for _soup_part in _soup.find_all(recursive=False):
            if not _is_skip:
                _count += len(re.sub(sub_space, "", _soup_part.get_text()))
                if _count >= max_count:
                    _gap = _count - max_count
                    if _gap <= max_gap:
                        _is_skip = True
                    else:
                        _is_skip = True
                        next_soup = _soup_part
                        _count -= len(re.sub(sub_space, "", _soup_part.get_text()))
                        continue
            else:
                _soup_part.decompose()
    return _count,_gap,next_soup

def cut_str(text_list, only_text_list, max_bytes_length=2000000):
    try:

        # 计算有格式总字节数
        bytes_length = 0
        for text in text_list:
            bytes_length += len(bytes(text, encoding='utf-8'))


        # 小于直接返回
        if bytes_length < max_bytes_length:
            return text_list

        # 全部文件连接，重新计算无格式字节数
        all_text = ""
        bytes_length = 0
        for text in only_text_list:
            bytes_length += len(bytes(text, encoding='utf-8'))
            all_text += text

        # 小于直接返回
        if bytes_length < max_bytes_length:
            return only_text_list

        # 截取字符
        all_text = all_text[:max_bytes_length//3]

        return [all_text]
    except Exception as e:
        logging.info("cut_str " + str(e))
        return text_list

def getLegal_str(_str):
    if _str is not None:
        return ILLEGAL_CHARACTERS_RE.sub("",str(_str))

def getRow_ots_primary(row):
    _dict = dict()
    if row is None:
        return None
    for part in row.attribute_columns:
        _dict[part[0]] = part[1]
    for part in row.primary_key:
        _dict[part[0]] = part[1]
    return _dict

def timeAdd(_time,days,format="%Y-%m-%d",minutes=0):
    a = time.mktime(time.strptime(_time,format))+86400*days+60*minutes

    _time1 = time.strftime(format,time.localtime(a))
    return _time1

def getRow_ots(rows):
    list_dict = []
    for row in rows:
        _dict = dict()
        for part in row:
            for v in part:
                _dict[v[0]] = v[1]
        list_dict.append(_dict)
    return list_dict

def getw2vfilepath():
    w2vfile = os.path.dirname(__file__)+"/../wiki_128_word_embedding_new.vector"
    if os.path.exists(w2vfile):
        return w2vfile
    return "wiki_128_word_embedding_new.vector"

def getLazyLoad():
    global Lazy_load
    return Lazy_load

def get_file_name(url, headers):
    filename = ''
    if 'Content-Disposition' in headers and headers['Content-Disposition']:
        disposition_split = headers['Content-Disposition'].split(';')
        if len(disposition_split) > 1:
            if disposition_split[1].strip().lower().startswith('filename='):
                file_name = disposition_split[1].split('=')
                if len(file_name) > 1:
                    filename = file_name[1]
    if not filename and os.path.basename(url):
        filename = os.path.basename(url).split("?")[0]
    if not filename:
        return time.time()
    return filename

model_word_file = os.path.dirname(__file__)+"/../singlew2v_model.vector"
model_word = None
lock_model_word = RLock()

from decimal import Decimal
import logging
logging.basicConfig(level = logging.INFO,format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)
import pickle
import os

import json

#自定义jsonEncoder
class MyEncoder(json.JSONEncoder):

    def __init__(self):
        import numpy as np
        global np

    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,(np.int64,np.int32)):
            return int(obj)
        return json.JSONEncoder.default(self, obj)

vocab_word = None
vocab_words = None

file_vocab_word = "vocab_word.pk"
file_vocab_words = "vocab_words.pk"

selffool_authorization = "NjlhMWFjMjVmNWYyNzI0MjY1OGQ1M2Y0ZmY4ZGY0Mzg3Yjc2MTVjYg=="
selffool_url = "http://pai-eas-vpc.cn-beijing.aliyuncs.com/api/predict/selffool_gpu"
selffool_seg_authorization = "OWUwM2Q0ZmE3YjYxNzU4YzFiMjliNGVkMTA3MzJkNjQ2MzJiYzBhZg=="
selffool_seg_url = "http://pai-eas-vpc.cn-beijing.aliyuncs.com/api/predict/selffool_seg_gpu"
codename_authorization = "Y2M5MDUxMzU1MTU4OGM3ZDk2ZmEzYjkxYmYyYzJiZmUyYTgwYTg5NA=="
codename_url = "http://pai-eas-vpc.cn-beijing.aliyuncs.com/api/predict/codename_gpu"

form_item_authorization = "ODdkZWY1YWY0NmNhNjU2OTI2NWY4YmUyM2ZlMDg1NTZjOWRkYTVjMw=="
form_item_url = "http://pai-eas-vpc.cn-beijing.aliyuncs.com/api/predict/form"
person_authorization = "N2I2MDU2N2Q2MGQ0ZWZlZGM3NDkyNTA1Nzc4YmM5OTlhY2MxZGU1Mw=="
person_url = "http://pai-eas-vpc.cn-beijing.aliyuncs.com/api/predict/person"
role_authorization = "OWM1ZDg5ZDEwYTEwYWI4OGNjYmRlMmQ1NzYwNWNlZGZkZmRmMjE4OQ=="
role_url = "http://pai-eas-vpc.cn-beijing.aliyuncs.com/api/predict/role"
money_authorization = "MDQyNjc2ZDczYjBhYmM4Yzc4ZGI4YjRmMjc3NGI5NTdlNzJiY2IwZA=="
money_url = "http://pai-eas-vpc.cn-beijing.aliyuncs.com/api/predict/money"
codeclasses_authorization = "MmUyNWIxZjQ2NjAzMWJlMGIzYzkxMjMzNWY5OWI3NzJlMWQ1ZjY4Yw=="
codeclasses_url = "http://pai-eas-vpc.cn-beijing.aliyuncs.com/api/predict/codeclasses"

def viterbi_decode(score, transition_params):
    """Decode the highest scoring sequence of tags outside of TensorFlow.

    This should only be used at test time.

    Args:
      score: A [seq_len, num_tags] matrix of unary potentials.
      transition_params: A [num_tags, num_tags] matrix of binary potentials.

    Returns:
      viterbi: A [seq_len] list of integers containing the highest scoring tag
          indices.
      viterbi_score: A float containing the score for the Viterbi sequence.
    """
    trellis = np.zeros_like(score)
    backpointers = np.zeros_like(score, dtype=np.int32)
    trellis[0] = score[0]

    for t in range(1, score.shape[0]):
        v = np.expand_dims(trellis[t - 1], 1) + transition_params
        trellis[t] = score[t] + np.max(v, 0)
        backpointers[t] = np.argmax(v, 0)

    viterbi = [np.argmax(trellis[-1])]
    for bp in reversed(backpointers[1:]):
        viterbi.append(bp[viterbi[-1]])
    viterbi.reverse()

    viterbi_score = np.max(trellis[-1])
    return viterbi, viterbi_score

import ctypes
import inspect

def _async_raise(tid, exctype):
    """raises the exception, performs cleanup if needed"""
    tid = ctypes.c_long(tid)
    if not inspect.isclass(exctype):
        exctype = type(exctype)
    res = ctypes.pythonapi.PyThreadState_SetAsyncExc(tid, ctypes.py_object(exctype))
    if res == 0:
        raise ValueError("invalid thread id")
    elif res != 1:
        ctypes.pythonapi.PyThreadState_SetAsyncExc(tid, None)
        raise SystemError("PyThreadState_SetAsyncExc failed")

def stop_thread(thread):
    _async_raise(thread.ident, SystemExit)

def limitRun(sess,list_output,feed_dict,MAX_BATCH=1024):
    len_sample = 0
    if len(feed_dict.keys())>0:
        len_sample = len(feed_dict[list(feed_dict.keys())[0]])
    if len_sample>MAX_BATCH:
        list_result = [[] for _ in range(len(list_output))]
        _begin = 0
        while(_begin<len_sample):
            new_dict = dict()
            for _key in feed_dict.keys():
                new_dict[_key] = feed_dict[_key][_begin:_begin+MAX_BATCH]
            _output = sess.run(list_output,feed_dict=new_dict)
            for _index in range(len(list_output)):
                list_result[_index].extend(_output[_index])
            _begin += MAX_BATCH
    else:
        list_result = sess.run(list_output,feed_dict=feed_dict)
    return list_result



def get_values(response,output_name):
        """
        Get the value of a specified output tensor
        :param output_name: name of the output tensor
        :return: the content of the output tensor
        """
        output = response.outputs[output_name]
        if output.dtype == tf_predict_pb2.DT_FLOAT:
            _value = output.float_val
        elif output.dtype == tf_predict_pb2.DT_INT8 or output.dtype == tf_predict_pb2.DT_INT16 or \
                output.dtype == tf_predict_pb2.DT_INT32:
            _value = output.int_val
        elif output.dtype == tf_predict_pb2.DT_INT64:
            _value = output.int64_val
        elif output.dtype == tf_predict_pb2.DT_DOUBLE:
            _value = output.double_val
        elif output.dtype == tf_predict_pb2.DT_STRING:
            _value = output.string_val
        elif output.dtype == tf_predict_pb2.DT_BOOL:
            _value = output.bool_val
        return np.array(_value).reshape(response.outputs[output_name].array_shape.dim)

def vpc_requests(url,authorization,request_data,list_outputs):
    
    
    headers = {"Authorization": authorization}
    dict_outputs = dict()
    
    response = tf_predict_pb2.PredictResponse()
    resp = requests.post(url, data=request_data, headers=headers)
    
    
    if resp.status_code != 200:
        print(resp.status_code,resp.content)
        log("调用pai-eas接口出错,authorization:"+str(authorization))
        return None
    else:
        response = tf_predict_pb2.PredictResponse()
        response.ParseFromString(resp.content)
        for _output in list_outputs:
            dict_outputs[_output] = get_values(response, _output)
        return dict_outputs

def encodeInput(data,word_len,word_flag=True,userFool=False):
    result = []
    out_index = 0
    for item in data:
        if out_index in [0]:
            list_word = item[-word_len:]
        else:
            list_word = item[:word_len]
        temp = []
        if word_flag:
            for word in list_word:
                if userFool:
                    temp.append(getIndexOfWord_fool(word))
                else:
                    temp.append(getIndexOfWord(word))
            list_append = []
            temp_len = len(temp)
            while(temp_len<word_len):
                if userFool:
                    list_append.append(0)
                else:
                    list_append.append(getIndexOfWord("<pad>"))
                temp_len += 1
            if out_index in [0]:
                temp = list_append+temp
            else:
                temp = temp+list_append
        else:
            for words in list_word:
                temp.append(getIndexOfWords(words))
                
            list_append = []
            temp_len = len(temp)
            while(temp_len<word_len):
                list_append.append(getIndexOfWords("<pad>"))
                temp_len += 1
            if out_index in [0,1]:
                temp = list_append+temp
            else:
                temp = temp+list_append
        result.append(temp)
        out_index += 1
    return result

def encodeInput_form(input,MAX_LEN=30):
    x = np.zeros([MAX_LEN])
    for i in range(len(input)):
        if i>=MAX_LEN:
            break
        x[i] = getIndexOfWord(input[i])
    return x
    

def getVocabAndMatrix(model,Embedding_size = 60):
    '''
    @summary:获取子向量的词典和子向量矩阵
    '''
    vocab = ["<pad>"]+model.index2word
    
    embedding_matrix = np.zeros((len(vocab),Embedding_size))
    for i in range(1,len(vocab)):
        embedding_matrix[i] = model[vocab[i]]
    
    return vocab,embedding_matrix

def getIndexOfWord(word):
    global vocab_word,file_vocab_word
    if vocab_word is None:
        if os.path.exists(file_vocab_word):
            vocab = load(file_vocab_word)
            vocab_word = dict((w, i) for i, w in enumerate(np.array(vocab)))
        else:
            model = getModel_word()
            vocab,_ = getVocabAndMatrix(model, Embedding_size=60)
            vocab_word = dict((w, i) for i, w in enumerate(np.array(vocab)))
            save(vocab,file_vocab_word)
    if word in vocab_word.keys():
        return vocab_word[word]
    else:
        return vocab_word['<pad>']
        
def getIndexOfWords(words):
    global vocab_words,file_vocab_words
    if vocab_words is None:
        if os.path.exists(file_vocab_words):
            vocab = load(file_vocab_words)
            vocab_words = dict((w, i) for i, w in enumerate(np.array(vocab)))
        else:
            model = getModel_w2v()
            vocab,_ = getVocabAndMatrix(model, Embedding_size=128)
            vocab_words = dict((w, i) for i, w in enumerate(np.array(vocab)))
            save(vocab,file_vocab_words)
    if words in vocab_words.keys():
        return vocab_words[words]
    else:
        return vocab_words["<pad>"]

def isCellphone(phone):
    if phone is not None and re.search("^1\d{10}$",str(phone)) is not None:
        return True
    return False

def popNoneFromDict(_dict):
    list_pop = []
    for k,v in _dict.items():
        if v is None or v=="":
            list_pop.append(k)
    for k in list_pop:
        _dict.pop(k)
    return _dict


pattern_attachment = re.compile("\.(?P<attachment>jpg|jpeg|png|swf|tif|pdf|doc|docx|xls|xlsx|zip|rar|tar|7z|wim)$")
def getAttachmentTypeFromUrl(url):
    _match = re.search(pattern_attachment,url)
    if _match is not None:
        return _match.groupdict().get("attachment")
    return None

def getAttachmentUrls(sourceHtml):
    list_urls = []
    _soup = BeautifulSoup(sourceHtml,"lxml")
    set_types = set()
    list_a = _soup.find_all("a")
    for _a in list_a:
        _url = _a.attrs.get("href","")
        _type = getAttachmentTypeFromUrl(_url)
        if _type is not None:
            list_urls.append({"url":_url,"type":_type})
    list_img = _soup.find_all("img")
    for _img in list_img:
        _url = _img.attrs.get("src","")
        _type = getAttachmentTypeFromUrl(_url)
        if _type is not None:
            list_urls.append({"url":_url,"type":_type})
    return list_urls

def getCurrent_date(format="%Y-%m-%d %H:%M:%S"):
    _time = time.strftime(format,time.localtime())
    return _time

def log_tofile(filename):
    logging.basicConfig(filename=filename,level = logging.INFO,format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s')
    logger = logging.getLogger(__name__)

def log(msg):
    '''
    @summary:打印信息
    '''
    logger.info(msg)

def debug(msg):
    '''
    @summary:打印信息
    '''
    logger.debug(msg)


def save(object_to_save, path):
    '''
    保存对象
    @Arugs:
        object_to_save: 需要保存的对象

    @Return:
        保存的路径
    '''
    with open(path, 'wb') as f:
        pickle.dump(object_to_save, f)

def load(path):
    '''
    读取对象
    @Arugs:
        path: 读取的路径

    @Return:
        读取的对象
    '''
    with open(path, 'rb') as f:
        object1 = pickle.load(f)
        return object1
    

def getIndexOfWord_fool(word):
    
    if word in fool_char_to_id.keys():
        return fool_char_to_id[word]
    else:
        return fool_char_to_id["[UNK]"]


def find_index(list_tofind,text):
    '''
    @summary: 查找所有词汇在字符串中第一次出现的位置
    @param:
        list_tofind:待查找词汇
        text:字符串
    @return: list,每个词汇第一次出现的位置
    
    '''
    result = []
    for item in list_tofind:
        index = text.find(item)
        if index>=0:
            result.append(index)
        else:
            result.append(-1)
    return result


def combine(list1,list2):
    '''
    @summary:将两个list中的字符串两两拼接
    @param:
        list1:字符串list
        list2:字符串list
    @return:拼接结果list
    '''
    result = []
    for item1 in list1:
        for item2 in list2:
            result.append(str(item1)+str(item2))
    return result


def getDigitsDic(unit):
    '''
    @summary:拿到中文对应的数字
    '''
    DigitsDic = {"零":0, "壹":1, "贰":2, "叁":3, "肆":4, "伍":5, "陆":6, "柒":7, "捌":8, "玖":9,
                 "〇":0, "一":1, "二":2, "三":3, "四":4, "五":5, "六":6, "七":7, "八":8, "九":9}
    return DigitsDic.get(unit)

def getMultipleFactor(unit):
    '''
    @summary:拿到单位对应的值
    '''
    MultipleFactor = {"兆":Decimal(1000000000000),"亿":Decimal(100000000),"万":Decimal(10000),"仟":Decimal(1000),"千":Decimal(1000),"佰":Decimal(100),"百":Decimal(100),"拾":Decimal(10),"十":Decimal(10),"元":Decimal(1),"角":round(Decimal(0.1),1),"分":round(Decimal(0.01),2)}
    return MultipleFactor.get(unit)

def getUnifyMoney(money):
    '''
    @summary:将中文金额字符串转换为数字金额
    @param:
        money:中文金额字符串
    @return: decimal,数据金额
    '''


    MAX_NUM = 12
    #去掉逗号
    money = re.sub("[，,]","",money)
    money = re.sub("[^0-9.零壹贰叁肆伍陆柒捌玖拾佰仟萬億〇一二三四五六七八九十百千万亿元角分]","",money)
    result = Decimal(0)
    chnDigits = ["零", "壹", "贰", "叁", "肆", "伍", "陆", "柒", "捌", "玖"]
    chnFactorUnits = ["兆", "亿", "万", "仟", "佰", "拾","元","角","分"]

    LowMoneypattern = re.compile("^[\d,]+(\.\d+)?$")
    BigMoneypattern = re.compile("^零?(?P<BigMoney>[%s])$"%("".join(chnDigits)))
    if re.search(LowMoneypattern,money) is not None:
        return Decimal(money)
    elif re.search(BigMoneypattern,money) is not None:
        return getDigitsDic(re.search(BigMoneypattern,money).group("BigMoney"))
    for factorUnit in chnFactorUnits:
        if re.search(re.compile(".*%s.*"%(factorUnit)),money) is not None:
            subMoneys = re.split(re.compile("%s(?!.*%s.*)"%(factorUnit,factorUnit)),money)
            if re.search(re.compile("^(\d+(,)?)+(\.\d+)?$"),subMoneys[0]) is not None:
                result += Decimal(subMoneys[0])*(getMultipleFactor(factorUnit))
            elif len(subMoneys[0])==1:
                if re.search(re.compile("^[%s]$"%("".join(chnDigits))),subMoneys[0]) is not None:
                    result += Decimal(getDigitsDic(subMoneys[0]))*(getMultipleFactor(factorUnit))
            else:
                result += Decimal(getUnifyMoney(subMoneys[0]))*(getMultipleFactor(factorUnit))

            if len(subMoneys)>1:
                if re.search(re.compile("^(\d+(,)?)+(\.\d+)?[百千万亿]?\s?(元)?$"),subMoneys[1]) is not None:
                    result += Decimal(subMoneys[1])
                elif len(subMoneys[1])==1:
                    if re.search(re.compile("^[%s]$"%("".join(chnDigits))),subMoneys[1]) is not None:
                        result += Decimal(getDigitsDic(subMoneys[1]))
                else:
                    result += Decimal(getUnifyMoney(subMoneys[1]))
            break
    return result




def getModel_w2v():
    '''
    @summary:加载词向量
    '''
    global model_w2v,lock_model_w2v
    with lock_model_w2v:
        if model_w2v is None:
            model_w2v = gensim.models.KeyedVectors.load_word2vec_format(getw2vfilepath(),binary=True)
        return model_w2v

def getModel_word():
    '''
    @summary:加载字向量
    '''

    global model_word,lock_model_w2v
    with lock_model_word:
        if model_word is None:
            model_word = gensim.models.KeyedVectors.load_word2vec_format(model_word_file,binary=True)
        return model_word

# getModel_w2v()
# getModel_word()

def formatArea(area):
    if area is not None and len(area)>=3:
        return re.sub("[省市区县]","",area)
    return area

def findAllIndex(substr,wholestr):
    '''
    @summary: 找到字符串的子串的所有begin_index
    @param:
        substr:子字符串
        wholestr:子串所在完整字符串
    @return: list,字符串的子串的所有begin_index
    '''
    copystr = wholestr
    result = []
    indexappend = 0
    while(True):
        index = copystr.find(substr)
        if index<0:
            break
        else:
            result.append(indexappend+index)
            indexappend += index+len(substr)
            copystr = copystr[index+len(substr):]
    return result
    
  
def spanWindow(tokens,begin_index,end_index,size,center_include=False,word_flag = False,use_text = False,text = None):
    '''
    @summary:取得某个实体的上下文词汇
    @param:
        tokens:句子分词list
        begin_index:实体的开始index
        end_index:实体的结束index
        size:左右两边各取多少个词
        center_include:是否包含实体
        word_flag:词/字,默认是词
    @return: list,实体的上下文词汇
    '''  
    if use_text:
        assert text is not None
    length_tokens = len(tokens)
    if begin_index>size:
        begin = begin_index-size
    else:
        begin = 0
    if end_index+size<length_tokens:
        end = end_index+size+1
    else:
        end = length_tokens
    result = []
    if not word_flag:
        result.append(tokens[begin:begin_index])
        if center_include:
            if use_text:
                result.append(text)
            else:
                result.append(tokens[begin_index:end_index+1])
        result.append(tokens[end_index+1:end])
    else:
        result.append("".join(tokens[begin:begin_index]))
        if center_include:
            if use_text:
                result.append(text)
            else:
                result.append("".join(tokens[begin_index:end_index+1]))
        result.append("".join(tokens[end_index+1:end]))
    #print(result)
    return result

#根据规则补全编号或名称两边的符号
def fitDataByRule(data):
    symbol_dict = {"(":")",
                   "（":"）",
                   "[":"]",
                   "【":"】",
                   ")":"(",
                   "）":"（",
                   "]":"[",
                   "】":"【"}
    leftSymbol_pattern = re.compile("[\(（\[【]")
    rightSymbol_pattern = re.compile("[\)）\]】]")
    leftfinds = re.findall(leftSymbol_pattern,data)
    rightfinds = re.findall(rightSymbol_pattern,data)
    result = data
    if len(leftfinds)+len(rightfinds)==0:
        return data
    elif len(leftfinds)==len(rightfinds):
        return data
    elif abs(len(leftfinds)-len(rightfinds))==1:
        if len(leftfinds)>len(rightfinds):
            if symbol_dict.get(data[0]) is not None:
                result = data[1:]
            else:
                #print(symbol_dict.get(leftfinds[0]))
                result = data+symbol_dict.get(leftfinds[0])
        else:
            if symbol_dict.get(data[-1]) is not None:
                result = data[:-1]
            else:
                result = symbol_dict.get(rightfinds[0])+data
    result = re.sub("[。]","",result)
    return  result

def embedding(datas,shape):
    '''
    @summary:查找词汇对应的词向量
    @param:
        datas:词汇的list
        shape:结果的shape
    @return: array,返回对应shape的词嵌入
    '''
    model_w2v = getModel_w2v()
    embed = np.zeros(shape)
    length = shape[1]
    out_index = 0
    #print(datas)
    for data in datas:
        index = 0
        for item in data:
            item_not_space = re.sub("\s*","",item)
            if index>=length:
                break
            if item_not_space in model_w2v.vocab:
                embed[out_index][index] = model_w2v[item_not_space]
                index += 1
            else:
                #embed[out_index][index] = model_w2v['unk']
                index += 1
        out_index += 1
    return embed

def embedding_word(datas,shape):
    '''
    @summary:查找词汇对应的词向量
    @param:
        datas:词汇的list
        shape:结果的shape
    @return: array,返回对应shape的词嵌入
    '''
    model_w2v = getModel_word()
    embed = np.zeros(shape)
    length = shape[1]
    out_index = 0
    #print(datas)
    for data in datas:
        index = 0
        for item in str(data)[-shape[1]:]:
            if index>=length:
                break
            if item in model_w2v.vocab:
                embed[out_index][index] = model_w2v[item]
                index += 1
            else:
                # embed[out_index][index] = model_w2v['unk']
                index += 1
        out_index += 1
    return embed

def formEncoding(text,shape=(100,60),expand=False):
    embedding = np.zeros(shape)
    word_model = getModel_word()
    for i in range(len(text)):
        if i>=shape[0]:
            break
        if text[i] in word_model.vocab:
            embedding[i] = word_model[text[i]]
    if expand:
        embedding = np.expand_dims(embedding,0)
    return embedding

def partMoney(entity_text,input2_shape = [7]):
    '''
    @summary:对金额分段
    @param:
        entity_text:数值金额
        input2_shape:分类数
    @return: array,分段之后的独热编码
    '''
    money = float(entity_text)
    parts = np.zeros(input2_shape)
    if money<100:
        parts[0] = 1
    elif money<1000:
        parts[1] = 1
    elif money<10000:
        parts[2] = 1
    elif money<100000:
        parts[3] = 1
    elif money<1000000:
        parts[4] = 1
    elif money<10000000:
        parts[5] = 1
    else:
        parts[6] = 1
    return parts

def recall(y_true, y_pred):
    from keras import backend as K
    '''
    计算召回率
    @Argus:
        y_true: 正确的标签
        y_pred: 模型预测的标签

    @Return
        召回率
    '''
    c1 = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
    c3 = K.sum(K.round(K.clip(y_true, 0, 1)))
    if c3 == 0:
        return 0
    recall = c1 / c3
    return recall


def f1_score(y_true, y_pred):
    from keras import backend as K
    '''
    计算F1

    @Argus:
        y_true: 正确的标签
        y_pred: 模型预测的标签

    @Return
        F1值
    '''

    c1 = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
    c2 = K.sum(K.round(K.clip(y_pred, 0, 1)))
    c3 = K.sum(K.round(K.clip(y_true, 0, 1)))
    precision = c1 / c2
    if c3 == 0:
        recall = 0
    else:
        recall = c1 / c3
    f1_score = 2 * (precision * recall) / (precision + recall)
    return f1_score


def precision(y_true, y_pred):
    from keras import backend as K
    '''
    计算精确率

    @Argus:
        y_true: 正确的标签
        y_pred: 模型预测的标签

    @Return
        精确率
    '''
    c1 = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
    c2 = K.sum(K.round(K.clip(y_pred, 0, 1)))
    precision = c1 / c2
    return precision

# def print_metrics(history):
#     '''
#     制作每次迭代的各metrics变化图片
#
#     @Arugs:
#         history: 模型训练迭代的历史记录
#     '''
#     import matplotlib.pyplot as plt
#
#     # loss图
#     loss = history.history['loss']
#     val_loss = history.history['val_loss']
#     epochs = range(1, len(loss) + 1)
#     plt.subplot(2, 2, 1)
#     plt.plot(epochs, loss, 'bo', label='Training loss')
#     plt.plot(epochs, val_loss, 'b', label='Validation loss')
#     plt.title('Training and validation loss')
#     plt.xlabel('Epochs')
#     plt.ylabel('Loss')
#     plt.legend()
#
#     # f1图
#     f1 = history.history['f1_score']
#     val_f1 = history.history['val_f1_score']
#     plt.subplot(2, 2, 2)
#     plt.plot(epochs, f1, 'bo', label='Training f1')
#     plt.plot(epochs, val_f1, 'b', label='Validation f1')
#     plt.title('Training and validation f1')
#     plt.xlabel('Epochs')
#     plt.ylabel('F1')
#     plt.legend()
#
#     # precision图
#     prec = history.history['precision']
#     val_prec = history.history['val_precision']
#     plt.subplot(2, 2, 3)
#     plt.plot(epochs, prec, 'bo', label='Training precision')
#     plt.plot(epochs, val_prec, 'b', label='Validation pecision')
#     plt.title('Training and validation precision')
#     plt.xlabel('Epochs')
#     plt.ylabel('Precision')
#     plt.legend()
#
#     # recall图
#     recall = history.history['recall']
#     val_recall = history.history['val_recall']
#     plt.subplot(2, 2, 4)
#     plt.plot(epochs, recall, 'bo', label='Training recall')
#     plt.plot(epochs, val_recall, 'b', label='Validation recall')
#     plt.title('Training and validation recall')
#     plt.xlabel('Epochs')
#     plt.ylabel('Recall')
#     plt.legend()
#
#     plt.show()


if __name__=="__main__":
    print(fool_char_to_id[">"])
    # model = getModel_w2v()
    # vocab,matrix = getVocabAndMatrix(model, Embedding_size=128)
    # save([vocab,matrix],"vocabMatrix_words.pk")