Mercurial > repos > peterjc > seq_filter_by_id

comparison tools/seq_filter_by_id/seq_filter_by_id.py @ 7:fb1313d79396 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded v0.2.5, ignore blank names in tabular files (based on contribution from Gildas Le Corguille)
author peterjc
date Fri, 04 Nov 2016 08:11:08 -0400
parents 03e134cae41a
children 2d4537dbf0bc
comparison
equal deleted inserted replaced
6:03e134cae41a 7:fb1313d79396
72 help="Show version and quit") 72 help="Show version and quit")
73 73
74 options, args = parser.parse_args() 74 options, args = parser.parse_args()
75 75
76 if options.version: 76 if options.version:
77 print "v0.2.3" 77 print "v0.2.5"
78 sys.exit(0) 78 sys.exit(0)
79 79
80 in_file = options.input 80 in_file = options.input
81 seq_format = options.format 81 seq_format = options.format
82 out_positive_file = options.output_positive 82 out_positive_file = options.output_positive
91 if seq_format is None: 91 if seq_format is None:
92 sys.exit("Missing sequence format") 92 sys.exit("Missing sequence format")
93 if logic not in ["UNION", "INTERSECTION"]: 93 if logic not in ["UNION", "INTERSECTION"]:
94 sys.exit("Logic agrument should be 'UNION' or 'INTERSECTION', not %r" % logic) 94 sys.exit("Logic agrument should be 'UNION' or 'INTERSECTION', not %r" % logic)
95 if options.id_list and args: 95 if options.id_list and args:
96 sys.exit("Cannot accepted IDs via both -t and as tabular files") 96 sys.exit("Cannot accept IDs via both -t in the command line, and as tabular files")
97 elif not options.id_list and not args: 97 elif not options.id_list and not args:
98 sys.exit("Expected matched pairs of tabular files and columns (or -t given)") 98 sys.exit("Expected matched pairs of tabular files and columns (or -t given)")
99 if len(args) % 2: 99 if len(args) % 2:
100 sys.exit("Expected matched pairs of tabular files and columns, not: %r" % args) 100 sys.exit("Expected matched pairs of tabular files and columns, not: %r" % args)
101 101
179 '@': '__at__', 179 '@': '__at__',
180 '\n': '__cn__', 180 '\n': '__cn__',
181 '\r': '__cr__', 181 '\r': '__cr__',
182 '\t': '__tc__', 182 '\t': '__tc__',
183 '#': '__pd__', 183 '#': '__pd__',
184 } 184 }
185 185
186 # Read tabular file(s) and record all specified identifiers 186 # Read tabular file(s) and record all specified identifiers
187 ids = None # Will be a set 187 ids = None # Will be a set
188 if options.id_list: 188 if options.id_list:
189 assert not identifiers 189 assert not identifiers
204 if line.startswith("#"): 204 if line.startswith("#"):
205 # Ignore comments 205 # Ignore comments
206 continue 206 continue
207 parts = line.rstrip("\n").split("\t") 207 parts = line.rstrip("\n").split("\t")
208 for col in columns: 208 for col in columns:
209 file_ids.add(clean_name(parts[col])) 209 name = clean_name(parts[col])
210 if name:
211 file_ids.add(name)
210 else: 212 else:
211 # Single column, special case speed up 213 # Single column, special case speed up
212 col = columns[0] 214 col = columns[0]
213 for line in handle: 215 for line in handle:
214 if not line.strip(): #skip empty lines 216 if not line.strip(): # skip empty lines
215 continue 217 continue
216 if not line.startswith("#"): 218 if not line.startswith("#"):
217 file_ids.add(clean_name(line.rstrip("\n").split("\t")[col])) 219 name = clean_name(line.rstrip("\n").split("\t")[col])
220 if name:
221 file_ids.add(name)
218 print "Using %i IDs from column %s in tabular file" % (len(file_ids), ", ".join(str(col + 1) for col in columns)) 222 print "Using %i IDs from column %s in tabular file" % (len(file_ids), ", ".join(str(col + 1) for col in columns))
219 if ids is None: 223 if ids is None:
220 ids = file_ids 224 ids = file_ids
221 if logic == "UNION": 225 if logic == "UNION":
222 ids.update(file_ids) 226 ids.update(file_ids)