|
0
|
1 """
|
|
|
2 NCBI sra class
|
|
|
3 """
|
|
|
4 import logging
|
|
|
5 import binascii
|
|
|
6 from galaxy.datatypes.data import nice_size
|
|
|
7 from galaxy.datatypes.binary import Binary
|
|
|
8
|
|
|
9 log = logging.getLogger(__name__)
|
|
|
10
|
|
|
11 class Sra(Binary):
|
|
|
12 """ Sequence Read Archive (SRA) """
|
|
|
13 file_ext = 'sra'
|
|
|
14
|
|
|
15 def __init__( self, **kwd ):
|
|
|
16 Binary.__init__( self, **kwd )
|
|
|
17
|
|
|
18 def sniff( self, filename ):
|
|
|
19 """ The first 8 bytes of any NCBI sra file is 'NCBI.sra', and the file is binary.
|
|
|
20 For details about the format, see http://www.ncbi.nlm.nih.gov/books/n/helpsra/SRA_Overview_BK/#SRA_Overview_BK.4_SRA_Data_Structure
|
|
|
21 """
|
|
|
22 try:
|
|
|
23 header = open(filename).read(8)
|
|
|
24 if binascii.b2a_hex(header) == binascii.hexlify('NCBI.sra'):
|
|
|
25 return True
|
|
|
26 else:
|
|
|
27 return False
|
|
|
28 except:
|
|
|
29 return False
|
|
|
30
|
|
|
31 def set_peek(self, dataset, is_multi_byte=False):
|
|
|
32 if not dataset.dataset.purged:
|
|
|
33 dataset.peek = 'Binary sra file'
|
|
|
34 dataset.blurb = nice_size(dataset.get_size())
|
|
|
35 else:
|
|
|
36 dataset.peek = 'file does not exist'
|
|
|
37 dataset.blurb = 'file purged from disk'
|
|
|
38
|
|
|
39 def display_peek(self, dataset):
|
|
|
40 try:
|
|
|
41 return dataset.peek
|
|
|
42 except:
|
|
|
43 return 'Binary sra file (%s)' % (nice_size(dataset.get_size()))
|
