XML-Parser-In-Python/tag_checker.py at master · ExtendSKE/XML-Parser-In-Python · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
import xml.etree.ElementTree as ET
import subprocess as SP
import file_search as FS
def predefine_tags():
    tag_file = open('tags.txt','r')
    tags = []
    for i in tag_file:
        i=i[:-1]
        if len(i) !=0:
            tags.append(i)
    tag_file.close()
    return tags

def finding_tags(root,tags,list_found_tag):  #finding all tags which are present in source-code
    if root is None:
        return list_found_tag
    for i in root:
        #print(i.tag)
        for j in tags:
            j = j[1:]
            j= j [:-1]
            index = i.tag.find(j)
            #print(index)
            if index!=-1:
                try:
                    index = list_found_tag.index(j)
                except ValueError:
                    index = -1
                #print(index)
                if index == -1:
                    list_found_tag.append(j)
        list_found_tag=finding_tags(i,tags,list_found_tag)
    return list_found_tag
def finding_tags_info(dict,data,list_found_tag,path):
    line_no = 0
    index1 = 0   #used for temporary storgae
    tmp_index =0
    for j in list_found_tag:
        tmp_list = []
        line_no =0
        #print(j)
        tmp_list.append(path)
        for i in data:
            i=i[:-1]
            #print(i)
            if len(i)!=0:
                line_no = line_no +1
                index = i.find(j)
                if index!=-1:
                    if i.find('<'+j)!=-1:
                        if i.find('>')==-1:
                            #print(j)
                            try :
                                index1 = data.index(i+"\n")
                                tmp_index = index1
                            except ValueError:
                                index1 =-1
                            flag =0
                            while index1!=len(data):
                                if data[index1].find('>')!=-1:
                                    if data[index1].find('/>')!=-1:
                                        flag =1
                                    break
                                else:
                                    index1 = index1+1;
                            #print(index1)
                            if flag == 1:
                                tmp_list.append("begin_line:"+str(line_no)+" begin_column:"+str(index)+", end_line:"+str(line_no+index1-tmp_index)+" end_column:"+str(data[index1].find('>')))
                            else:
                                tmp_list.append("begin_line:"+str(line_no)+" begin_column:"+str(index))
                        else:
                            if(i.find('/>')!=-1):
                                tmp_list.append("begin_line:"+str(line_no)+" begin_column:"+str(index)+", end_line:"+str(line_no)+" end_column:"+str(i.find('>')))
                            else:
                                tmp_list.append("begin_line:"+str(line_no)+" begin_column:"+str(index))
                    else:
                        if i.find('</'+j+'>')!=-1:
                            tmp_list.append("end_line:"+str(line_no)+" end_column:"+str(index))

        dict[j]=tmp_list
    #print(dict)
    return dict
if __name__ == "__main__":
    #tags = tag_finder()
    tags=predefine_tags()
    path = SP.getoutput('pwd')
    file_list = FS.directory_search(path,'*.bpel')
    for i in file_list:
        list_found_tag = []
        tree=ET.parse(i[0])
        root =tree.getroot()
        list_found_tag=finding_tags(root,tags,list_found_tag)
        #print(list_found_tag)
        source_code_file = open(i[0],'r') ##Reading SOurce-code Finding Starting & ending Line no. and column no.
        data = []
        for j in source_code_file:
            data.append(j)
        source_code_file.close()
        dict= {}
        dict=finding_tags_info(dict,data,list_found_tag,i[0])
        dict_out=open(i[0].replace('.bpel','.txt'),'w')     ##Writing dictionary in output file
        #dict_out.write("File_Path : "+i[0]+"\n")  #path of file
        for i in list_found_tag:
            dict_out.write(i+": "+str(dict[i])+"\n")
        dict_out.close()
    #print(found_tags)