1#! /usr/bin/python
2
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
7#%tmp.#, i.e. it now will remove %tmp.12.3.15 etc, additionally fixed a spelling error in
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.#
11import re
12import sys
13if( len(sys.argv) < 3 ):
14	print 'usage is: ./DSAclean <dot_file_to_be_cleaned> <out_put_file>'
15	sys.exit(1)
16#get a file object
17input = open(sys.argv[1], 'r')
18output = open(sys.argv[2], 'w')
19#we'll get this one line at a time...while we could just put the whole thing in a string
20#it would kill old computers
21buffer = input.readline()
22while buffer != '':
23	if re.compile("label(\s*)=(\s*)\"\s%tmp(.\w*)*(\s*)\"").search(buffer):
24		#skip next line, write neither this line nor the next
25		buffer = input.readline()
26	else:
27		#this isn't a tmp Node, we can write it
28		output.write(buffer)
29	#prepare for the next iteration
30	buffer = input.readline()
31input.close()
32output.close()
33