Mercurial > repos > iuc > msa_datatypes

comparison msa.py @ 0:70227007b991 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Imported from capsule None
author iuc
date Tue, 22 Apr 2014 13:55:42 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:70227007b991
1 # -*- coding: utf-8 -*-
2
3 from galaxy.datatypes.data import Text
4 from galaxy.datatypes.sniff import get_headers, get_test_fname
5 from galaxy.datatypes.data import get_file_peek
6 import subprocess
7 import os
8
9 from galaxy.datatypes.metadata import MetadataElement
10 from galaxy.datatypes import metadata
11
12 def count_special_lines( word, filename, invert = False ):
13 """
14 searching for special 'words' using the grep tool
15 grep is used to speed up the searching and counting
16 The number of hits is returned.
17 """
18 try:
19 cmd = ["grep", "-c"]
20 if invert:
21 cmd.append('-v')
22 cmd.extend([word, filename])
23 out = subprocess.Popen(cmd, stdout=subprocess.PIPE)
24 return int(out.communicate()[0].split()[0])
25 except:
26 pass
27 return 0
28
29 class Stockholm_1_0( Text ):
30 file_ext = "stockholm"
31
32 MetadataElement( name="number_of_alignments", default=0, desc="Number of multiple alignments", readonly=True, visible=True, optional=True, no_value=0 )
33
34 def set_peek( self, dataset, is_multi_byte=False ):
35 if not dataset.dataset.purged:
36 dataset.peek = get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
37 if (dataset.metadata.number_of_models == 1):
38 dataset.blurb = "1 alignment"
39 else:
40 dataset.blurb = "%s alignments" % dataset.metadata.number_of_models
41 dataset.peek = data.get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
42 else:
43 dataset.peek = 'file does not exist'
44 dataset.blurb = 'file purged from disc'
45
46 def sniff( self, filename ):
47 if count_special_lines('^#[[:space:]+]STOCKHOLM[[:space:]+]1.0', filename) > 0:
48 return True
49 else:
50 return False
51
52 def set_meta( self, dataset, **kwd ):
53 """
54
55 Set the number of models in dataset.
56 """
57 dataset.metadata.number_of_models = count_special_lines('^#[[:space:]+]STOCKHOLM[[:space:]+]1.0', dataset.file_name)
58
59 def split( cls, input_datasets, subdir_generator_function, split_params):
60 """
61
62 Split the input files by model records.
63 """
64 if split_params is None:
65 return None
66
67 if len(input_datasets) > 1:
68 raise Exception("STOCKHOLM-file splitting does not support multiple files")
69 input_files = [ds.file_name for ds in input_datasets]
70
71 chunk_size = None
72 if split_params['split_mode'] == 'number_of_parts':
73 raise Exception('Split mode "%s" is currently not implemented for STOCKHOLM-files.' % split_params['split_mode'])
74 elif split_params['split_mode'] == 'to_size':
75 chunk_size = int(split_params['split_size'])
76 else:
77 raise Exception('Unsupported split mode %s' % split_params['split_mode'])
78
79 def _read_stockholm_records( filename ):
80 lines = []
81 with open(filename) as handle:
82 for line in handle:
83 lines.append( line )
84 if line.strip() == '//':
85 yield lines
86 lines = []
87
88 def _write_part_stockholm_file( accumulated_lines ):
89 part_dir = subdir_generator_function()
90 part_path = os.path.join( part_dir, os.path.basename( input_files[0] ) )
91 part_file = open( part_path, 'w' )
92 part_file.writelines( accumulated_lines )
93 part_file.close()
94
95 try:
96
97 stockholm_records = _read_stockholm_records( input_files[0] )
98 stockholm_lines_accumulated = []
99 for counter, stockholm_record in enumerate( stockholm_records, start = 1):
100 stockholm_lines_accumulated.extend( stockholm_record )
101 if counter % chunk_size == 0:
102 _write_part_stockholm_file( stockholm_lines_accumulated )
103 stockholm_lines_accumulated = []
104 if stockholm_lines_accumulated:
105 _write_part_stockholm_file( stockholm_lines_accumulated )
106 except Exception, e:
107 log.error('Unable to split files: %s' % str(e))
108 raise
109 split = classmethod(split)
110