#coding=utf-8
import os
import jieba
import sys
import re
import time
import jieba.posseg as pseg

sys.path.append("../")
jieba.load_userdict("../Database/userdict.txt") # 載入自定義分詞詞典

'''
title：利用結巴分詞進行文字語料處理：單文字處理器、批量檔案處理器
    1 首先對文字進行遍歷查詢
    2 建立原始文字的儲存結構
    3 對原文字進行結巴分詞和停用詞處理
    4 對預處理結果進行標準化格式，並儲存原檔案結構路徑
author：白寧超
myblog：http://www.cnblogs.com/baiboy/
time：2017年4月28日10:03:09
'''


'''
分詞.詞性標註以及去停用詞
stopwordspath： 停用詞路徑
dealpath：中文資料預處理檔案的路徑
savepath：中文資料預處理結果的儲存路徑
'''
def cutTxtWord(dealpath,savepath,stopwordspath):
    stopwords = {}.fromkeys([ line.rstrip() for line in open(stopwordspath,"r",encoding='utf-8')]) # 停用詞表
    with open(dealpath,"r",encoding='utf-8') as f:
        txtlist=f.read() # 讀取待處理的文字
    words =pseg.cut(txtlist) # 帶詞性標註的分詞結果
    cutresult=""# 獲取去除停用詞後的分詞結果
    for word, flag in words:
        if word not in stopwords:
            cutresult += word+"/"+flag+" " #去停用詞
            getFlag(cutresult,savepath) #



'''
分詞.詞性標註以及去停用詞
stopwordspath： 停用詞路徑
read_folder_path ：中文資料預處理檔案的路徑
write_folder_path ：中文資料預處理結果的儲存路徑
filescount=300 #設定資料夾下檔案最多多少個
'''

def cutFileWord(read_folder_path,write_folder_path,stopwordspath):
    # 停用詞表
    stopwords = {}.fromkeys([ line.rstrip() for line in open(stopwordspath,"r",encoding='utf-8')])

    # 獲取待處理根目錄下的所有類別
    folder_list = os.listdir(read_folder_path)
    # 類間迴圈
    for folder in folder_list:
        #某類下的路徑
        new_folder_path = os.path.join(read_folder_path, folder)

        # 建立儲存檔案目錄
        path=write_folder_path+folder #儲存檔案的子檔案
        isExists=os.path.exists(path)
        if not isExists:
            os.makedirs(path)
            print(path+' 建立成功')
        else: pass
        save_folder_path = os.path.join(write_folder_path, folder)#某類下的儲存路徑
        print('--> 請稍等，正在處理中...')

        # 類內迴圈
        files = os.listdir(new_folder_path)
        j = 1
        for file in files:
            if j > len(files): break
            dealpath = os.path.join(new_folder_path, file) #處理單個檔案的路徑
            with open(dealpath,"r",encoding='utf-8') as f:
                txtlist=f.read()
                # python 過濾中文、英文標點特殊符號
                # txtlist1 = re.sub("[\s+\.\!\/_,$%^*(+\"\']+|[+——！，。？、
 
[email protected]#￥%……&*（）]+", "",txtlist)
            words =pseg.cut(txtlist) # 帶詞性標註的分詞結果
            cutresult="" # 單個文字：分詞後經停用詞處理後的結果
            for word, flag in words:
                if word not in stopwords:
                    cutresult += word+"/"+flag+" " #去停用詞
            savepath = os.path.join(save_folder_path,file)
            getFlag(cutresult,savepath)
            j += 1

'''
做詞性篩選
cutresult：str型別，初切分的結果
savepath： 儲存檔案路徑
'''
def getFlag(cutresult,savepath):
    txtlist=[] #過濾掉的詞性後的結果
    #詞列表為自己定義要過濾掉的詞性
    cixing=["/x","/zg","/uj","/ul","/e","/d","/uz","/y"]
    for line in cutresult.split('\n'):
        line_list2=re.split('[ ]', line)
        line_list2.append("\n") # 保持原段落格式存在
        line_list=line_list2[:]
        for segs in line_list2:
            for K in cixing:
                if K in segs:
                    line_list.remove(segs)
                    break
                else:
                    pass
        txtlist.extend(line_list)

    # 去除詞性標籤
    resultlist=txtlist[:]
    flagresult=""
    for v in txtlist:
        if "/" in v:
            slope=v.index("/")
            letter=v[0:slope]+" "
            flagresult+= letter
        else:
            flagresult+= v
    standdata(flagresult,savepath)

'''
標準化處理，去除空行，空白字元等。
flagresult:篩選過的結果
'''
def standdata(flagresult,savepath):
    f2=open(savepath,"w",encoding='utf-8')
    for line in flagresult.split('\n'):
        if len(line)>=2:
            line_clean="/ ".join(line.split())
            lines=line_clean+" "+"\n"
            f2.write(lines)
        else: pass
    f2.close()


if __name__ == '__main__' :
    t1=time.time()


    # 測試單個檔案
    dealpath="../Database/SogouC/FileTest/1.txt"
    savepath="../Database/SogouCCut/FileTest/1.txt"

    stopwordspath='../Database/stopwords/CH_stopWords.txt'
    stopwordspath1='../Database/stopwords/HG_stopWords.txt' # 哈工大停用詞表

    # 批量處理資料夾下的檔案
    # rfolder_path = '../Database/SogouC/Sample/'
    rfolder_path = '../Database/SogouC/FileNews/'
    # 分詞處理後儲存根路徑
    wfolder_path = '../Database/SogouCCut/'

    # 中文語料前處理器
    # cutTxtWord(dealpath,savepath,stopwordspath) # 單文字前處理器
    cutFileWord(rfolder_path,wfolder_path,stopwordspath) # 多文字前處理器


    t2=time.time()
    print("中文語料語處理完成，耗時："+str(t2-t1)+"秒。") #反饋結果