# coding=utf-8
from BeautifulSoup import BeautifulSoup, Tag, NavigableString
from SentenceSpliter import SentenceSpliter
from os.path import basename,dirname,isdir,isfile
from os import makedirs
from shutil import copyfile
import io
import time
import re

class build_tpl:
    def __init__(self,parse_file,build_tpl_name,cp_pic_dir,show_pic_dir,js_path,set_lang=2052):
        '''參數(shù)說明：解析文件名，模版名稱，保存圖片路徑，圖片顯示路徑，js路徑，當前語言（分句使用）'''

        #取得解析文件目錄路徑
        if len(dirname(parse_file))>1:
            self.cur_dir = dirname(parse_file)+"/";
        else:
            self.cur_dir ="./";

        #建立的模版文件文件名
        self.build_tpl_name = build_tpl_name;
        #圖片cp到得目錄
        self.cp_pic_dir = cp_pic_dir;
        #通過http展現(xiàn)圖片的目錄
        self.show_pic_dir = show_pic_dir;
        #加載js的路徑
        self.js_path = js_path;

        #句段組
        self.get_text_arr = [];
        #當前圖片名數(shù)組
        self.cur_pic_arr = [];

        #解析文件 取得soup 資源
        self.soup = self.get_soup(parse_file);
        #取得html文檔中，段文檔
        self.get_text_arr = self.soup.body.findAll(text=lambda(x): len(x.strip()) > 0);
        #取得句對
        self.get_sentence_arr = self.parse_text(self.get_text_arr,set_lang);
        #取得替換數(shù)組
        self.replace_list = self.get_replace_list(self.get_text_arr,set_lang);
        #取得圖片數(shù)組
        self.cur_pic_arr = self.soup.findAll('img');

        #self.write_file_by_list("no.txt",self.get_text_arr);
        #self.write_file_by_list("yes.txt",self.get_sentence_arr);

    #保存詞組到文件
    def save_data_file(self):
        file_name = self.build_tpl_name+".data";
        self.write_file_by_list(file_name,self.get_data());
    #取得詞組
    def get_data(self):
        return self.get_sentence_arr;
    #數(shù)組寫入到文檔
    def write_file_by_list(self,file_name,write_arr):
        file=io.FileIO(file_name,"w");
        file.write(('\n'.join(write_arr)).encode('utf-8'));
        file.close();
    #字符串寫入到文檔
    def write_file(self,file_name,file_contents):
        file=io.FileIO(file_name,"w");
        file.write(file_contents.encode('utf-8'));
        file.close();
    #建立圖片hash目錄
    def get_pic_hash(self):
        return time.strftime("%Y/%m/%d/");
    #建立模版文件
    def builder(self):
        #沒能發(fā)生替換的單詞
        bug_msg = [];
        #進行內(nèi)容模版替換
        for i in range(len(self.get_text_arr)):
            #替換
            rep_str = "$rep_arr[{0}]".format(i);
            try:
                self.soup.body.find(text=self.get_text_arr[i]).replaceWith(self.replace_list[i]);
            except AttributeError:
                bug_msg.append(self.get_text_arr[i]);

        #取得圖片hash路徑
        hash_dir = self.get_pic_hash();
        #構(gòu)造展示圖片路徑
        show_pic_dir = self.show_pic_dir+hash_dir;
        #構(gòu)造圖片保存路徑
        cp_pic_dir = self.cp_pic_dir+hash_dir;

        #判斷保存圖片的目錄是否存在 不存在建立
        if not isdir(cp_pic_dir):
            makedirs(cp_pic_dir);

        for pic_name in self.cur_pic_arr:
            #進行圖片路徑替換
            old_pic_src = pic_name['src'];
            pic_name['src'] = show_pic_dir+old_pic_src;
            #進行圖片拷貝
            cp_src_file = self.cur_dir+old_pic_src;
            cp_dis_file = cp_pic_dir+old_pic_src;
            copyfile(cp_src_file,cp_dis_file);

        #建立bug信息的文檔
        #self.write_file_by_list("bug.txt",bug_msg);

        #添加js
        tag = Tag(self.soup,"script");
        tag['type'] = "text/javascript";
        tag['src'] =self.js_path+"jquery.js";

        tag2 = Tag(self.soup,"script");
        tag2['type'] = "text/javascript";
        tag2['src'] =self.js_path+"init.js";

        self.soup.head.insert(2,tag2);
        self.soup.head.insert(2,tag);


        #建立模版
        self.write_file(self.build_tpl_name,self.soup);
    #取得替換的html文件    
    def get_replace_html(self,rep_id,rep_data=""):
        '''
        參數(shù)說明：替換id，替換內(nèi)容（為空的采用模版模式替換）
        '''
        if len(rep_data) > 0 :
            rep_str = rep_data;
        else:
            rep_str = "$rep_arr[{0}]".format(rep_id);
        return "<span sty=\"data\" id=\"rep_"+str(rep_id)+"\">"+rep_str+"</span>";
    #取得替換數(shù)組
    def get_replace_list(self,text_arr,set_lang):
        Sp = SentenceSpliter();
        Sp.SetLang(set_lang);
        temp_sentence = [];
        jump_i = 0;
        for text in text_arr:
            SList = Sp.Split(text);
            replace_temp = "";
            if SList != None:
                for item in SList:
                    replace_temp = replace_temp+self.get_replace_html(jump_i,item);
                    jump_i=jump_i+1;
            else:
                replace_temp = self.get_replace_html(jump_i,text);
                jump_i=jump_i+1;
            temp_sentence.append(replace_temp);
        return temp_sentence;
    #分句
    def parse_text(self,text_arr,set_lang):
        Sp = SentenceSpliter();
        Sp.SetLang(set_lang);
        temp_sentence = [];
        for text in text_arr:
            SList = Sp.Split(text);
            if SList != None:
                for item in SList:
                    temp_sentence.append(item);
            else:
                temp_sentence.append(text);

        return temp_sentence;

    #取得解析資源
    def get_soup(self,parse_file):
        try:
            file=io.FileIO(parse_file,"r");
            doc = file.readall();
            file.close();
        except IOError:
            print 'ERROR: %s file not found!' %parse_file;
            return False;
        #開始解析html文檔
        return BeautifulSoup(''.join(doc));

if __name__ == "__main__":
    from sys import argv, exit;

    if len(argv) < 3:
        print "USAGE: python %s <input-file> <output-file>" % argv[0]
        exit(255);

    if not isfile(argv[1]):
        print "no such input file: %s" % argv[1]
        exit(1)


    paser_file = argv[1];#"html/testpic.html";
    tpl_file = argv[2];
    save_pic_path = argv[3];
    show_pic_path = argv[4];
    load_js_path = argv[5];
    #解析開始 設置解析文件，模版名，圖片保存路徑，圖片顯示路徑
    so = build_tpl(paser_file,tpl_file,save_pic_path,show_pic_path,load_js_path);
    #建立模版
    so.builder();
    #保存分句的句對
    so.save_data_file();