221
|
1 #!/usr/bin/env python
|
150
|
2
|
252
|
3 # changelog:
|
|
4 # 10/13/2005b: replaced the # in tmp(.#*)* with alphanumeric and _, this will then remove
|
|
5 # nodes such as %tmp.1.i and %tmp._i.3
|
|
6 # 10/13/2005: exntended to remove variables of the form %tmp(.#)* rather than just
|
150
|
7 #%tmp.#, i.e. it now will remove %tmp.12.3.15 etc, additionally fixed a spelling error in
|
252
|
8 # the comments
|
|
9 # 10/12/2005: now it only removes nodes and edges for which the label is %tmp.# rather
|
|
10 # than removing all lines for which the lable CONTAINS %tmp.#
|
150
|
11
|
|
12 from __future__ import print_function
|
|
13
|
|
14 import re
|
|
15 import sys
|
252
|
16
|
|
17 if len(sys.argv) < 3:
|
|
18 print("usage is: ./DSAclean <dot_file_to_be_cleaned> <out_put_file>")
|
|
19 sys.exit(1)
|
|
20 # get a file object
|
|
21 input = open(sys.argv[1], "r")
|
|
22 output = open(sys.argv[2], "w")
|
|
23 # we'll get this one line at a time...while we could just put the whole thing in a string
|
|
24 # it would kill old computers
|
150
|
25 buffer = input.readline()
|
252
|
26 while buffer != "":
|
|
27 if re.compile('label(\s*)=(\s*)"\s%tmp(.\w*)*(\s*)"').search(buffer):
|
|
28 # skip next line, write neither this line nor the next
|
|
29 buffer = input.readline()
|
|
30 else:
|
|
31 # this isn't a tmp Node, we can write it
|
|
32 output.write(buffer)
|
|
33 # prepare for the next iteration
|
|
34 buffer = input.readline()
|
150
|
35 input.close()
|
|
36 output.close()
|