Mercurial > repos > devteam > subtract_query
comparison subtract_query.py @ 0:8a3448727cec draft
Imported from capsule None
author | devteam |
---|---|
date | Tue, 01 Apr 2014 09:12:49 -0400 |
parents | |
children | df4bce472400 |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:8a3448727cec |
---|---|
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 bx.cookbook import doc_optparse | |
11 | |
12 # Older py compatibility | |
13 try: | |
14 set() | |
15 except: | |
16 from sets import Set as set | |
17 | |
18 assert sys.version_info[:2] >= ( 2, 4 ) | |
19 | |
20 def get_lines(fname, begin_col='', end_col='', ignore_empty_end_cols=False): | |
21 lines = set([]) | |
22 i = 0 | |
23 for i, line in enumerate(file(fname)): | |
24 line = line.rstrip('\r\n') | |
25 if line and not line.startswith('#'): | |
26 if begin_col and end_col: | |
27 """Both begin_col and end_col must be integers at this point.""" | |
28 try: | |
29 line = line.split('\t') | |
30 line = '\t'.join([line[j] for j in range(begin_col-1, end_col)]) | |
31 if ignore_empty_end_cols: | |
32 # removing empty fields, we do not compare empty fields at the end of a line. | |
33 line = line.rstrip() | |
34 lines.add( line ) | |
35 except: pass | |
36 else: | |
37 if ignore_empty_end_cols: | |
38 # removing empty fields, we do not compare empty fields at the end of a line. | |
39 line = line.rstrip() | |
40 lines.add( line ) | |
41 if i: return (i+1, lines) | |
42 else: return (i, lines) | |
43 | |
44 def main(): | |
45 | |
46 # Parsing Command Line here | |
47 options, args = doc_optparse.parse( __doc__ ) | |
48 | |
49 try: | |
50 inp1_file, inp2_file, begin_col, end_col, out_file = args | |
51 except: | |
52 doc_optparse.exception() | |
53 | |
54 begin_col = begin_col.strip() | |
55 end_col = end_col.strip() | |
56 | |
57 if begin_col != 'None' or end_col != 'None': | |
58 """ | |
59 The user selected columns for restriction. We'll allow default | |
60 values for both begin_col and end_col as long as the user selected | |
61 at least one of them for restriction. | |
62 """ | |
63 if begin_col == 'None': | |
64 begin_col = end_col | |
65 elif end_col == 'None': | |
66 end_col = begin_col | |
67 begin_col = int(begin_col) | |
68 end_col = int(end_col) | |
69 """Make sure that begin_col <= end_col (switch if not)""" | |
70 if begin_col > end_col: | |
71 tmp_col = end_col | |
72 end_col = begin_col | |
73 begin_col = tmp_col | |
74 else: | |
75 begin_col = end_col = '' | |
76 | |
77 try: | |
78 fo = open(out_file,'w') | |
79 except: | |
80 print >> sys.stderr, "Unable to open output file" | |
81 sys.exit() | |
82 | |
83 """ | |
84 len1 is the number of lines in inp1_file | |
85 lines1 is the set of unique lines in inp1_file | |
86 diff1 is the number of duplicate lines removed from inp1_file | |
87 """ | |
88 len1, lines1 = get_lines(inp1_file, begin_col, end_col, options.ignore_empty_end_cols) | |
89 diff1 = len1 - len(lines1) | |
90 len2, lines2 = get_lines(inp2_file, begin_col, end_col, options.ignore_empty_end_cols) | |
91 | |
92 lines1.difference_update(lines2) | |
93 """lines1 is now the set of unique lines in inp1_file - the set of unique lines in inp2_file""" | |
94 | |
95 for line in lines1: | |
96 print >> fo, line | |
97 | |
98 fo.close() | |
99 | |
100 info_msg = 'Subtracted %d lines. ' %((len1 - diff1) - len(lines1)) | |
101 | |
102 if begin_col and end_col: | |
103 info_msg += 'Restricted to columns c' + str(begin_col) + ' thru c' + str(end_col) + '. ' | |
104 | |
105 if diff1 > 0: | |
106 info_msg += 'Eliminated %d duplicate/blank/comment/invalid lines from first query.' %diff1 | |
107 | |
108 print info_msg | |
109 | |
110 if __name__ == "__main__": | |
111 main() |