|
0
|
1 #!/usr/bin/env python
|
|
|
2 # Greg Von Kuster
|
|
|
3
|
|
|
4 """
|
|
|
5 Subtract an entire query from another query
|
|
|
6 usage: %prog in_file_1 in_file_2 begin_col end_col output
|
|
|
7 --ignore-empty-end-cols: ignore empty end columns when subtracting
|
|
|
8 """
|
|
|
9 import sys, re
|
|
|
10 from galaxy import eggs
|
|
|
11 import pkg_resources; pkg_resources.require( "bx-python" )
|
|
|
12 from bx.cookbook import doc_optparse
|
|
|
13
|
|
|
14 # Older py compatibility
|
|
|
15 try:
|
|
|
16 set()
|
|
|
17 except:
|
|
|
18 from sets import Set as set
|
|
|
19
|
|
|
20 assert sys.version_info[:2] >= ( 2, 4 )
|
|
|
21
|
|
|
22 def get_lines(fname, begin_col='', end_col='', ignore_empty_end_cols=False):
|
|
|
23 lines = set([])
|
|
|
24 i = 0
|
|
|
25 for i, line in enumerate(file(fname)):
|
|
|
26 line = line.rstrip('\r\n')
|
|
|
27 if line and not line.startswith('#'):
|
|
|
28 if begin_col and end_col:
|
|
|
29 """Both begin_col and end_col must be integers at this point."""
|
|
|
30 try:
|
|
|
31 line = line.split('\t')
|
|
|
32 line = '\t'.join([line[j] for j in range(begin_col-1, end_col)])
|
|
|
33 if ignore_empty_end_cols:
|
|
|
34 # removing empty fields, we do not compare empty fields at the end of a line.
|
|
|
35 line = line.rstrip()
|
|
|
36 lines.add( line )
|
|
|
37 except: pass
|
|
|
38 else:
|
|
|
39 if ignore_empty_end_cols:
|
|
|
40 # removing empty fields, we do not compare empty fields at the end of a line.
|
|
|
41 line = line.rstrip()
|
|
|
42 lines.add( line )
|
|
|
43 if i: return (i+1, lines)
|
|
|
44 else: return (i, lines)
|
|
|
45
|
|
|
46 def main():
|
|
|
47
|
|
|
48 # Parsing Command Line here
|
|
|
49 options, args = doc_optparse.parse( __doc__ )
|
|
|
50
|
|
|
51 try:
|
|
|
52 inp1_file, inp2_file, begin_col, end_col, out_file = args
|
|
|
53 except:
|
|
|
54 doc_optparse.exception()
|
|
|
55
|
|
|
56 begin_col = begin_col.strip()
|
|
|
57 end_col = end_col.strip()
|
|
|
58
|
|
|
59 if begin_col != 'None' or end_col != 'None':
|
|
|
60 """
|
|
|
61 The user selected columns for restriction. We'll allow default
|
|
|
62 values for both begin_col and end_col as long as the user selected
|
|
|
63 at least one of them for restriction.
|
|
|
64 """
|
|
|
65 if begin_col == 'None':
|
|
|
66 begin_col = end_col
|
|
|
67 elif end_col == 'None':
|
|
|
68 end_col = begin_col
|
|
|
69 begin_col = int(begin_col)
|
|
|
70 end_col = int(end_col)
|
|
|
71 """Make sure that begin_col <= end_col (switch if not)"""
|
|
|
72 if begin_col > end_col:
|
|
|
73 tmp_col = end_col
|
|
|
74 end_col = begin_col
|
|
|
75 begin_col = tmp_col
|
|
|
76 else:
|
|
|
77 begin_col = end_col = ''
|
|
|
78
|
|
|
79 try:
|
|
|
80 fo = open(out_file,'w')
|
|
|
81 except:
|
|
|
82 print >> sys.stderr, "Unable to open output file"
|
|
|
83 sys.exit()
|
|
|
84
|
|
|
85 """
|
|
|
86 len1 is the number of lines in inp1_file
|
|
|
87 lines1 is the set of unique lines in inp1_file
|
|
|
88 diff1 is the number of duplicate lines removed from inp1_file
|
|
|
89 """
|
|
|
90 len1, lines1 = get_lines(inp1_file, begin_col, end_col, options.ignore_empty_end_cols)
|
|
|
91 diff1 = len1 - len(lines1)
|
|
|
92 len2, lines2 = get_lines(inp2_file, begin_col, end_col, options.ignore_empty_end_cols)
|
|
|
93
|
|
|
94 lines1.difference_update(lines2)
|
|
|
95 """lines1 is now the set of unique lines in inp1_file - the set of unique lines in inp2_file"""
|
|
|
96
|
|
|
97 for line in lines1:
|
|
|
98 print >> fo, line
|
|
|
99
|
|
|
100 fo.close()
|
|
|
101
|
|
|
102 info_msg = 'Subtracted %d lines. ' %((len1 - diff1) - len(lines1))
|
|
|
103
|
|
|
104 if begin_col and end_col:
|
|
|
105 info_msg += 'Restricted to columns c' + str(begin_col) + ' thru c' + str(end_col) + '. '
|
|
|
106
|
|
|
107 if diff1 > 0:
|
|
|
108 info_msg += 'Eliminated %d duplicate/blank/comment/invalid lines from first query.' %diff1
|
|
|
109
|
|
|
110 print info_msg
|
|
|
111
|
|
|
112 if __name__ == "__main__":
|
|
|
113 main()
|
