树状转XML
将程序日志中的树状结构的报文，转换为XML格式的报文。
输入样式为
1 ├─0.COMMON_INFO(utype) 2 │ ├─0.PROVINCE_GROUP(string):10017 3 │ ├─1.SESSION_ID(string):Dj32QgQQlzjD2MFRn1JKcLlffXL6xfFRKn313Bnyr8SwfGV12dQS!903836304!1348468960414 4 │ ├─2.SER_NAME(string): 5 │ ├─3.ROUND_AUDIT(string):Y 6 │ ├─4.DEST_IP(string):172.21.0.123 7 │ ├─5.DEST_PORT(string):11001 8 │ ├─6.SRC_PORT(string):56284 9 │ ├─7.APP_NAME(string):NGBOSS 10 │ ├─8.APP_ID(string):2000 11 │ └─9.FROM_SYS(string):BOSS 12 ├─1.BILL_TYPE(int):1 13 ├─2.START_TIME(string):20120903000000 14 ├─3.END_TIME(string):20120924235959 15 ├─4.ELECTRIC_FLAG(string):N 16 ├─5.LOGIN_NO(string):M00000SYS 17 └─6.PAGINATION_INFO(utype) 18 ├─0.LINE_COUNT(int):20 19 └─1.PAGE_NUM(int):1
输出样式为
1 <COMMON_INFO> 2 <PROVINCE_GROUP type="string">10017</PROVINCE_GROUP> 3 <SESSION_ID type="string">Dj32QgQQlzjD2MFRn1JKcLlffXL6xfFRKn313Bnyr8SwfGV12dQS!903836304!1348468960414</SESSION_ID> 4 <SER_NAME type="string"></SER_NAME> 5 <ROUND_AUDIT type="string">Y</ROUND_AUDIT> 6 <DEST_IP type="string">172.21.0.123</DEST_IP> 7 <DEST_PORT type="string">11001</DEST_PORT> 8 <SRC_PORT type="string">56284</SRC_PORT> 9 <APP_NAME type="string">NGBOSS</APP_NAME> 10 <APP_ID type="string">2000</APP_ID> 11 <FROM_SYS type="string">BOSS</FROM_SYS> 12 </COMMON_INFO> 13 <BILL_TYPE type="int">1</BILL_TYPE> 14 <START_TIME type="string">20120903000000</START_TIME> 15 <END_TIME type="string">20120924235959</END_TIME> 16 <ELECTRIC_FLAG type="string">N</ELECTRIC_FLAG> 17 <LOGIN_NO type="string">M00000SYS</LOGIN_NO> 18 <PAGINATION_INFO> 19 <LINE_COUNT type="int">20</LINE_COUNT> 20 <PAGE_NUM type="int">1</PAGE_NUM> 21 </PAGINATION_INFO>
python代码
1 # -*- coding:gb2312 -*- 2 # To change this template, choose Tools | Templates 3 # and open the template in the editor. 4 5 __author__="Shawn" 6 __date__ ="$2012-11-18 15:28:40$" 7 8 9 if __name__ == "__main__": 10 curr_line="" 11 pre_level=0 12 f=open("in.txt","r") 13 p=open("out.txt","w") 14 alist=[] 15 alist_level=[] 16 17 for eachLine in f: 18 curr_line=eachLine 19 dot_index=curr_line.index(".") 20 left_quote_index=curr_line.index("(") 21 right_quote_index=curr_line.index(")") 22 level_index=0 23 if(curr_line.find("├")!=-1): 24 level_index=curr_line.index("├") 25 if(curr_line.find("└")!=-1): 26 level_index=curr_line.index("└") 27 blank_num=curr_line.count(" ", 0, dot_index) 28 level=int((level_index-blank_num/2)/2) 29 if(level<pre_level): 30 begin_level=level 31 for i in range(level,pre_level): 32 begin_level=begin_level-1 33 buffer=" "*alist_level.pop()+"</"+alist.pop()+">" 34 p.writelines(buffer+'\n') 35 type=curr_line[left_quote_index+1:right_quote_index] 36 node_name=curr_line[dot_index+1:left_quote_index] 37 if(type!="utype"): 38 node_value=curr_line[curr_line.index(":")+1:] 39 buffer=" "*level+"<"+node_name+" type=\""+type+"\">"+node_value.rstrip()+"</"+node_name+">" 40 p.writelines(buffer+'\n') 41 else: 42 buffer=" "*level+"<"+node_name+">" 43 p.writelines(buffer+'\n') 44 alist.append(node_name) 45 alist_level.append(level) 46 node_value="" 47 pre_level=level 48 while(alist.__len__()!=0): 49 buffer=" "*alist_level.pop()+"</"+alist.pop()+">" 50 p.writelines(buffer+'\n') 51 f.close() 52 p.close()
