|
0
|
1 #!/usr/bin/env python
|
|
|
2 # This tool takes a tab-delimited textfile as input and creates another column in the file which is the result of
|
|
|
3 # a computation performed on every row in the original file. The tool will skip over invalid lines within the file,
|
|
|
4 # informing the user about the number of lines skipped.
|
|
|
5 import sys, re, os.path
|
|
|
6 from galaxy import eggs
|
|
|
7 from galaxy.tools import validation
|
|
|
8 from galaxy.datatypes import metadata
|
|
|
9 from math import log,exp,sqrt,ceil,floor
|
|
|
10
|
|
|
11 assert sys.version_info[:2] >= ( 2, 4 )
|
|
|
12
|
|
|
13 def stop_err( msg ):
|
|
|
14 sys.stderr.write( msg )
|
|
|
15 sys.exit()
|
|
|
16
|
|
|
17 inp_file = sys.argv[1]
|
|
|
18 out_file = sys.argv[2]
|
|
|
19 expr = sys.argv[3]
|
|
|
20 round_result = sys.argv[4]
|
|
|
21 try:
|
|
|
22 in_columns = int( sys.argv[5] )
|
|
|
23 except:
|
|
|
24 stop_err( "Missing or invalid 'columns' metadata value, click the pencil icon in the history item and select the Auto-detect option to correct it. This tool can only be used with tab-delimited data." )
|
|
|
25 if in_columns < 2:
|
|
|
26 # To be considered tabular, data must fulfill requirements of the sniff.is_column_based() method.
|
|
|
27 stop_err( "Missing or invalid 'columns' metadata value, click the pencil icon in the history item and select the Auto-detect option to correct it. This tool can only be used with tab-delimited data." )
|
|
|
28 try:
|
|
|
29 in_column_types = sys.argv[6].split( ',' )
|
|
|
30 except:
|
|
|
31 stop_err( "Missing or invalid 'column_types' metadata value, click the pencil icon in the history item and select the Auto-detect option to correct it. This tool can only be used with tab-delimited data." )
|
|
|
32 if len( in_column_types ) != in_columns:
|
|
|
33 stop_err( "The 'columns' metadata setting does not conform to the 'column_types' metadata setting, click the pencil icon in the history item and select the Auto-detect option to correct it. This tool can only be used with tab-delimited data." )
|
|
|
34
|
|
|
35 # Unescape if input has been escaped
|
|
|
36 mapped_str = {
|
|
|
37 '__lt__': '<',
|
|
|
38 '__le__': '<=',
|
|
|
39 '__eq__': '==',
|
|
|
40 '__ne__': '!=',
|
|
|
41 '__gt__': '>',
|
|
|
42 '__ge__': '>=',
|
|
|
43 '__sq__': '\'',
|
|
|
44 '__dq__': '"',
|
|
|
45 }
|
|
|
46 for key, value in mapped_str.items():
|
|
|
47 expr = expr.replace( key, value )
|
|
|
48
|
|
|
49 # Prepare the column variable names and wrappers for column data types
|
|
|
50 cols, type_casts = [], []
|
|
|
51 for col in range( 1, in_columns + 1 ):
|
|
|
52 col_name = "c%d" % col
|
|
|
53 cols.append( col_name )
|
|
|
54 col_type = in_column_types[ col - 1 ].strip()
|
|
|
55 if round_result == 'no' and col_type == 'int':
|
|
|
56 col_type = 'float'
|
|
|
57 type_cast = "%s(%s)" % ( col_type, col_name )
|
|
|
58 type_casts.append( type_cast )
|
|
|
59
|
|
|
60 col_str = ', '.join( cols ) # 'c1, c2, c3, c4'
|
|
|
61 type_cast_str = ', '.join( type_casts ) # 'str(c1), int(c2), int(c3), str(c4)'
|
|
|
62 assign = "%s = line.split( '\\t' )" % col_str
|
|
|
63 wrap = "%s = %s" % ( col_str, type_cast_str )
|
|
|
64 skipped_lines = 0
|
|
|
65 first_invalid_line = 0
|
|
|
66 invalid_line = None
|
|
|
67 lines_kept = 0
|
|
|
68 total_lines = 0
|
|
|
69 out = open( out_file, 'wt' )
|
|
|
70
|
|
|
71 # Read input file, skipping invalid lines, and perform computation that will result in a new column
|
|
|
72 code = '''
|
|
|
73 for i, line in enumerate( file( inp_file ) ):
|
|
|
74 total_lines += 1
|
|
|
75 line = line.rstrip( '\\r\\n' )
|
|
|
76 if not line or line.startswith( '#' ):
|
|
|
77 skipped_lines += 1
|
|
|
78 if not invalid_line:
|
|
|
79 first_invalid_line = i + 1
|
|
|
80 invalid_line = line
|
|
|
81 continue
|
|
|
82 try:
|
|
|
83 %s
|
|
|
84 %s
|
|
|
85 new_val = %s
|
|
|
86 if round_result == "yes":
|
|
|
87 new_val = int( round( new_val ) )
|
|
|
88 new_line = line + '\\t' + str( new_val )
|
|
|
89 print >> out, new_line
|
|
|
90 lines_kept += 1
|
|
|
91 except:
|
|
|
92 skipped_lines += 1
|
|
|
93 if not invalid_line:
|
|
|
94 first_invalid_line = i + 1
|
|
|
95 invalid_line = line
|
|
|
96 ''' % ( assign, wrap, expr )
|
|
|
97
|
|
|
98 valid_expr = True
|
|
|
99 try:
|
|
|
100 exec code
|
|
|
101 except Exception, e:
|
|
|
102 out.close()
|
|
|
103 if str( e ).startswith( 'invalid syntax' ):
|
|
|
104 valid_expr = False
|
|
|
105 stop_err( 'Expression "%s" likely invalid. See tool tips, syntax and examples.' % expr )
|
|
|
106 else:
|
|
|
107 stop_err( str( e ) )
|
|
|
108
|
|
|
109 if valid_expr:
|
|
|
110 out.close()
|
|
|
111 valid_lines = total_lines - skipped_lines
|
|
|
112 print 'Creating column %d with expression %s' % ( in_columns + 1, expr )
|
|
|
113 if valid_lines > 0:
|
|
|
114 print 'kept %4.2f%% of %d lines.' % ( 100.0*lines_kept/valid_lines, total_lines )
|
|
|
115 else:
|
|
|
116 print 'Possible invalid expression "%s" or non-existent column referenced. See tool tips, syntax and examples.' % expr
|
|
|
117 if skipped_lines > 0:
|
|
|
118 print 'Skipped %d invalid lines starting at line #%d: "%s"' % ( skipped_lines, first_invalid_line, invalid_line )
|
