Mercurial > repos > devteam > column_maker

comparison column_maker.py @ 6:13b6f0007d9e draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/column_maker commit 35c79ccee143e8d178ebd24f6317888de3ca0187"
author devteam
date Mon, 25 Jan 2021 10:00:12 +0000
parents 9cd341095afd
children 427903d47026
comparison
equal deleted inserted replaced
5:9cd341095afd 6:13b6f0007d9e
7 """ 7 """
8 8
9 import argparse 9 import argparse
10 import json 10 import json
11 import re 11 import re
12 import sys
12 13
13 parser = argparse.ArgumentParser() 14 parser = argparse.ArgumentParser()
14 parser.add_argument('input', type=argparse.FileType('r'), help="input file") 15 parser.add_argument('input', type=argparse.FileType('r'), help="input file")
15 parser.add_argument('output', type=argparse.FileType('wt'), help="output file") 16 parser.add_argument('output', type=argparse.FileType('wt'), help="output file")
16 parser.add_argument('cond', nargs='?', type=str, help="expression") 17 parser.add_argument('cond', nargs='?', type=str, help="expression")
17 parser.add_argument('round', nargs='?', type=str, choices=['yes', 'no'],
18 help="round result")
19 parser.add_argument('columns', nargs='?', type=int, help="number of columns") 18 parser.add_argument('columns', nargs='?', type=int, help="number of columns")
20 parser.add_argument('column_types', nargs='?', type=str, help="comma separated list of column types") 19 parser.add_argument('column_types', nargs='?', type=str, help="comma separated list of column types")
21 parser.add_argument('avoid_scientific_notation', nargs='?', type=str, choices=['yes', 'no'], 20 parser.add_argument('--round', action="store_true",
21 help="round result")
22 parser.add_argument('--avoid_scientific_notation', action="store_true",
22 help="avoid scientific notation") 23 help="avoid scientific notation")
24 parser.add_argument('--header_new_column_name', default=None, type=str,
25 help="First line of input is a header line with column "
26 "names and this should become the name of the new "
27 "column")
23 parser.add_argument('--load_json', default=None, type=argparse.FileType('r'), 28 parser.add_argument('--load_json', default=None, type=argparse.FileType('r'),
24 help="overwrite parsed arguments from json file") 29 help="overwrite parsed arguments from json file")
25 args = parser.parse_args() 30 args = parser.parse_args()
26 31
27 argparse_dict = vars(args) 32 argparse_dict = vars(args)
31 36
32 fh = argparse_dict['input'] 37 fh = argparse_dict['input']
33 out = argparse_dict['output'] 38 out = argparse_dict['output']
34 expr = argparse_dict['cond'] 39 expr = argparse_dict['cond']
35 round_result = argparse_dict['round'] 40 round_result = argparse_dict['round']
41 avoid_scientific_notation = argparse_dict['avoid_scientific_notation']
42
43 if argparse_dict['header_new_column_name'] is not None:
44 header_line = fh.readline().strip('\n')
45 out.write(
46 '{0}\t{1}\n'.format(
47 header_line, argparse_dict['header_new_column_name']
48 )
49 )
36 try: 50 try:
37 in_columns = int(argparse_dict['columns']) 51 in_columns = int(argparse_dict['columns'])
52 if in_columns < 2:
53 # To be considered tabular, data must fulfill requirements of the sniff.is_column_based() method.
54 raise ValueError
38 except Exception: 55 except Exception:
39 exit("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.") 56 if not fh.readline():
40 if in_columns < 2: 57 # empty file content is ok and should produce empty output
41 # To be considered tabular, data must fulfill requirements of the sniff.is_column_based() method. 58 out.close()
42 exit("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.") 59 sys.exit()
60 sys.exit("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.")
43 try: 61 try:
44 in_column_types = argparse_dict['column_types'].split(',') 62 in_column_types = argparse_dict['column_types'].split(',')
45 except Exception: 63 except Exception:
46 exit("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.") 64 sys.exit("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.")
47 if len(in_column_types) != in_columns: 65 if len(in_column_types) != in_columns:
48 exit("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.") 66 sys.exit("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.")
49 avoid_scientific_notation = argparse_dict['avoid_scientific_notation']
50
51 # Unescape if input has been escaped
52 mapped_str = {
53 '__lt__': '<',
54 '__le__': '<=',
55 '__eq__': '==',
56 '__ne__': '!=',
57 '__gt__': '>',
58 '__ge__': '>=',
59 '__sq__': '\'',
60 '__dq__': '"',
61 }
62 for key, value in mapped_str.items():
63 expr = expr.replace(key, value)
64 67
65 operators = 'is|not|or|and' 68 operators = 'is|not|or|and'
66 builtin_and_math_functions = 'abs|all|any|bin|chr|cmp|complex|divmod|float|bool|hex|int|len|long|max|min|oct|ord|pow|range|reversed|round|sorted|str|sum|type|unichr|unicode|log|log10|exp|sqrt|ceil|floor' 69 builtin_and_math_functions = 'abs|all|any|bin|chr|cmp|complex|divmod|float|bool|hex|int|len|long|max|min|oct|ord|pow|range|reversed|round|sorted|str|sum|type|unichr|unicode|log|log10|exp|sqrt|ceil|floor'
67 string_and_list_methods = [name for name in dir('') + dir([]) if not name.startswith('_')] 70 string_and_list_methods = [name for name in dir('') + dir([]) if not name.startswith('_')]
68 whitelist = r"^([c0-9\+\-\*\/\(\)\.\'\"><=,:! ]|%s|%s|%s)*$" % (operators, builtin_and_math_functions, '|'.join(string_and_list_methods)) 71 whitelist = r"^([c0-9\+\-\*\/\(\)\.\'\"><=,:! ]|%s|%s|%s)*$" % (operators, builtin_and_math_functions, '|'.join(string_and_list_methods))
69 if not re.compile(whitelist).match(expr): 72 if not re.compile(whitelist).match(expr):
70 exit("Invalid expression") 73 sys.exit("Invalid expression")
71 if avoid_scientific_notation == "yes": 74 if avoid_scientific_notation:
72 expr = "format_float_positional(%s)" % expr 75 expr = "format_float_positional(%s)" % expr
73 76
74 # Prepare the column variable names and wrappers for column data types 77 # Prepare the column variable names and wrappers for column data types
75 cols, type_casts = [], [] 78 cols, type_casts = [], []
76 for col in range(1, in_columns + 1): 79 for col in range(1, in_columns + 1):
77 col_name = "c%d" % col 80 col_name = "c%d" % col
78 cols.append(col_name) 81 cols.append(col_name)
79 col_type = in_column_types[col - 1].strip() 82 col_type = in_column_types[col - 1].strip()
80 if round_result == 'no' and col_type == 'int': 83 if not round_result and col_type == 'int':
81 col_type = 'float' 84 col_type = 'float'
82 type_cast = "%s(%s)" % (col_type, col_name) 85 type_cast = "%s(%s)" % (col_type, col_name)
83 type_casts.append(type_cast) 86 type_casts.append(type_cast)
84 87
85 col_str = ', '.join(cols) # 'c1, c2, c3, c4' 88 col_str = ', '.join(cols) # 'c1, c2, c3, c4'
116 continue 119 continue
117 try: 120 try:
118 %s 121 %s
119 %s 122 %s
120 new_val = %s 123 new_val = %s
121 if round_result == "yes": 124 if round_result:
122 new_val = int(round(new_val)) 125 new_val = int(round(new_val))
123 new_line = line + '\\t' + str(new_val) + "\\n" 126 new_line = line + '\\t' + str(new_val) + "\\n"
124 out.write(new_line) 127 out.write(new_line)
125 lines_kept += 1 128 lines_kept += 1
126 except Exception: 129 except Exception:
136 exec(code) 139 exec(code)
137 except Exception as e: 140 except Exception as e:
138 out.close() 141 out.close()
139 if str(e).startswith('invalid syntax'): 142 if str(e).startswith('invalid syntax'):
140 valid_expr = False 143 valid_expr = False
141 exit('Expression "%s" likely invalid. See tool tips, syntax and examples.' % expr) 144 sys.exit('Expression "%s" likely invalid. See tool tips, syntax and examples.' % expr)
142 else: 145 else:
143 exit(str(e)) 146 sys.exit(str(e))
144 147
145 if valid_expr: 148 if valid_expr:
146 out.close() 149 out.close()
147 valid_lines = total_lines - skipped_lines 150 valid_lines = total_lines - skipped_lines
148 print('Creating column %d with expression %s' % (in_columns + 1, expr)) 151 print('Creating column %d with expression %s' % (in_columns + 1, expr))