blob: e452892812a401dbca0b482aef27f9bfd535499d (
plain)
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
|
#!/usr/bin/python
# Copyright 2006-2007 Nanorex, Inc. See LICENSE file for details.
# usage:
#
# merge.parameters.py existingParameterFile newParameterFiles...
#
# creates existingParameterFile.new
#
import sys
import re
leadingWhitespacePattern = re.compile(r"^\s*")
trailingWhitespacePattern = re.compile(r"\s*$")
idPattern = re.compile(r"(\$Id\:.*\$)")
commentPattern = re.compile("#")
firstField = re.compile(r"^(\S+)\s+(.*)")
parameterPattern = re.compile(r"^([^=]+)\s*\=\s*(\S+)\s*(.*)")
existing = sys.argv[1]
allfiles = sys.argv[1:]
print "existing parameter file: " + existing
newfile = open(existing + ".new", 'w')
# accumulates canonicalized lines for each unique "bond hybridization" pair
results = {}
for f in allfiles:
print "processing " + f
lines = open(f).readlines();
for l in lines:
# remove leading and trailing whitespace
l = leadingWhitespacePattern.sub('', l)
l = trailingWhitespacePattern.sub('', l)
# find RCSID
if f == existing and idPattern.search(l):
newfile.write("#\n" + l + "\n#\n\n")
continue
# ignore comments and blank lines
if commentPattern.match(l): continue
if len(l) == 0: continue
m = firstField.match(l)
if m:
bond = m.group(1)
rest = m.group(2)
canonical = bond + " "
hybrid = "sp3"
m = parameterPattern.match(rest)
while m:
key = m.group(1)
value = m.group(2)
rest = m.group(3)
if key == "CenterHybridization":
hybrid = value
canonical += key + "=" + value + " "
m = parameterPattern.match(rest)
sortfield = bond + " " + hybrid
results[sortfield] = canonical
bondkeys = results.keys()
bondkeys.sort()
for key in bondkeys:
newfile.write(results[key] + "\n")
|
