Mercurial > repos > devteam > subtract_query

comparison subtract_query.py @ 1:df4bce472400 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 33927a87ba2eee9bf0ecdd376a66241b17b3d734
author devteam
date Tue, 13 Oct 2015 12:51:35 -0400
parents 8a3448727cec
children f58ba0382c26
comparison
equal deleted inserted replaced
0:8a3448727cec 1:df4bce472400
4 """ 4 """
5 Subtract an entire query from another query 5 Subtract an entire query from another query
6 usage: %prog in_file_1 in_file_2 begin_col end_col output 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 7 --ignore-empty-end-cols: ignore empty end columns when subtracting
8 """ 8 """
9 import sys, re 9 import sys
10 from bx.cookbook import doc_optparse 10 from bx.cookbook import doc_optparse
11 11
12 # Older py compatibility 12 # Older py compatibility
13 try: 13 try:
14 set() 14 set()
15 except: 15 except:
16 from sets import Set as set 16 from sets import Set as set
17 17
18 assert sys.version_info[:2] >= ( 2, 4 ) 18 assert sys.version_info[:2] >= ( 2, 4 )
19
19 20
20 def get_lines(fname, begin_col='', end_col='', ignore_empty_end_cols=False): 21 def get_lines(fname, begin_col='', end_col='', ignore_empty_end_cols=False):
21 lines = set([]) 22 lines = set([])
22 i = 0 23 i = 0
23 for i, line in enumerate(file(fname)): 24 for i, line in enumerate(file(fname)):
25 if line and not line.startswith('#'): 26 if line and not line.startswith('#'):
26 if begin_col and end_col: 27 if begin_col and end_col:
27 """Both begin_col and end_col must be integers at this point.""" 28 """Both begin_col and end_col must be integers at this point."""
28 try: 29 try:
29 line = line.split('\t') 30 line = line.split('\t')
30 line = '\t'.join([line[j] for j in range(begin_col-1, end_col)]) 31 line = '\t'.join([line[j] for j in range(begin_col - 1, end_col)])
31 if ignore_empty_end_cols: 32 if ignore_empty_end_cols:
32 # removing empty fields, we do not compare empty fields at the end of a line. 33 # removing empty fields, we do not compare empty fields at the end of a line.
33 line = line.rstrip() 34 line = line.rstrip()
34 lines.add( line ) 35 lines.add( line )
35 except: pass 36 except:
37 pass
36 else: 38 else:
37 if ignore_empty_end_cols: 39 if ignore_empty_end_cols:
38 # removing empty fields, we do not compare empty fields at the end of a line. 40 # removing empty fields, we do not compare empty fields at the end of a line.
39 line = line.rstrip() 41 line = line.rstrip()
40 lines.add( line ) 42 lines.add( line )
41 if i: return (i+1, lines) 43 if i:
42 else: return (i, lines) 44 return (i + 1, lines)
45 else:
46 return (i, lines)
47
43 48
44 def main(): 49 def main():
45
46 # Parsing Command Line here 50 # Parsing Command Line here
47 options, args = doc_optparse.parse( __doc__ ) 51 options, args = doc_optparse.parse( __doc__ )
48 52
49 try: 53 try:
50 inp1_file, inp2_file, begin_col, end_col, out_file = args 54 inp1_file, inp2_file, begin_col, end_col, out_file = args
51 except: 55 except:
52 doc_optparse.exception() 56 doc_optparse.exception()
53 57
54 begin_col = begin_col.strip() 58 begin_col = begin_col.strip()
55 end_col = end_col.strip() 59 end_col = end_col.strip()
56 60
57 if begin_col != 'None' or end_col != 'None': 61 if begin_col != 'None' or end_col != 'None':
58 """ 62 """
59 The user selected columns for restriction. We'll allow default 63 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 64 values for both begin_col and end_col as long as the user selected
61 at least one of them for restriction. 65 at least one of them for restriction.
73 begin_col = tmp_col 77 begin_col = tmp_col
74 else: 78 else:
75 begin_col = end_col = '' 79 begin_col = end_col = ''
76 80
77 try: 81 try:
78 fo = open(out_file,'w') 82 fo = open(out_file, 'w')
79 except: 83 except:
80 print >> sys.stderr, "Unable to open output file" 84 print >> sys.stderr, "Unable to open output file"
81 sys.exit() 85 sys.exit()
82 86
83 """ 87 """
86 diff1 is the number of duplicate lines removed from inp1_file 90 diff1 is the number of duplicate lines removed from inp1_file
87 """ 91 """
88 len1, lines1 = get_lines(inp1_file, begin_col, end_col, options.ignore_empty_end_cols) 92 len1, lines1 = get_lines(inp1_file, begin_col, end_col, options.ignore_empty_end_cols)
89 diff1 = len1 - len(lines1) 93 diff1 = len1 - len(lines1)
90 len2, lines2 = get_lines(inp2_file, begin_col, end_col, options.ignore_empty_end_cols) 94 len2, lines2 = get_lines(inp2_file, begin_col, end_col, options.ignore_empty_end_cols)
91 95
92 lines1.difference_update(lines2) 96 lines1.difference_update(lines2)
93 """lines1 is now the set of unique lines in inp1_file - the set of unique lines in inp2_file""" 97 """lines1 is now the set of unique lines in inp1_file - the set of unique lines in inp2_file"""
94 98
95 for line in lines1: 99 for line in lines1:
96 print >> fo, line 100 print >> fo, line
97 101
98 fo.close() 102 fo.close()
99 103
100 info_msg = 'Subtracted %d lines. ' %((len1 - diff1) - len(lines1)) 104 info_msg = 'Subtracted %d lines. ' % ((len1 - diff1) - len(lines1))
101 105
102 if begin_col and end_col: 106 if begin_col and end_col:
103 info_msg += 'Restricted to columns c' + str(begin_col) + ' thru c' + str(end_col) + '. ' 107 info_msg += 'Restricted to columns c' + str(begin_col) + ' thru c' + str(end_col) + '. '
104 108
105 if diff1 > 0: 109 if diff1 > 0:
106 info_msg += 'Eliminated %d duplicate/blank/comment/invalid lines from first query.' %diff1 110 info_msg += 'Eliminated %d duplicate/blank/comment/invalid lines from first query.' % diff1
107 111
108 print info_msg 112 print info_msg
109 113
110 if __name__ == "__main__": 114 if __name__ == "__main__":
111 main() 115 main()