comparison sra.py @ 1:28fda7631857 draft

minor fixes
author Matt Shirley <mdshw5@gmail.com>
date Wed, 29 May 2013 22:08:19 -0400
parents ffdd41766195
children b77840618b8f
comparison
equal deleted inserted replaced
0:ffdd41766195 1:28fda7631857
8 from galaxy.datatypes.metadata import MetadataElement 8 from galaxy.datatypes.metadata import MetadataElement
9 from galaxy.datatypes import metadata 9 from galaxy.datatypes import metadata
10 from galaxy.datatypes.sniff import * 10 from galaxy.datatypes.sniff import *
11 from galaxy import eggs 11 from galaxy import eggs
12 import pkg_resources 12 import pkg_resources
13 pkg_resources.require( "bx-python" ) 13 pkg_resources.require( 'bx-python' )
14 import os, subprocess, tempfile 14 import os, subprocess, tempfile
15 import struct 15 import struct
16 16
17 class Sra( Binary ): 17 class Sra( Binary ):
18 """ Sequence Read Archive (SRA) """ 18 """ Sequence Read Archive (SRA) """
19 file_ext = "sra" 19 file_ext = 'sra'
20 20
21 def __init__( self, **kwd ): 21 def __init__( self, **kwd ):
22 Binary.__init__( self, **kwd ) 22 Binary.__init__( self, **kwd )
23 def sniff( self, filename ): 23 def sniff( self, filename ):
24 # The first 8 bytes of any NCBI sra file is 'NCIB.sra', and the file is binary. EBI and DDBJ files may differ. For details 24 """ The first 8 bytes of any NCBI sra file is 'NCIB.sra', and the file is binary. Not sure if EBI and DDBJ files may differ.
25 # about the format, see http://www.ncbi.nlm.nih.gov/books/n/helpsra/SRA_Overview_BK/#SRA_Overview_BK.4_SRA_Data_Structure 25 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
26 """
26 try: 27 try:
27 header = open( filename ).read(8) 28 header = open(filename).read(8)
28 if binascii.b2a_hex( header ) == binascii.hexlify( 'NCBI.sra' ): 29 if binascii.b2a_hex(header) == binascii.hexlify('NCBI.sra'):
29 return True 30 return True
30 return False 31 return False
31 except: 32 except:
32 return False 33 return False
33 def set_peek( self, dataset, is_multi_byte=False ): 34 def set_peek(self, dataset, is_multi_byte=False):
34 if not dataset.dataset.purged: 35 if not dataset.dataset.purged:
35 dataset.peek = "Binary sra file" 36 dataset.peek = 'Binary sra file'
36 dataset.blurb = data.nice_size( dataset.get_size() ) 37 dataset.blurb = data.nice_size(dataset.get_size())
37 else: 38 else:
38 dataset.peek = 'file does not exist' 39 dataset.peek = 'file does not exist'
39 dataset.blurb = 'file purged from disk' 40 dataset.blurb = 'file purged from disk'
40 def display_peek( self, dataset ): 41 def display_peek(self, dataset):
41 try: 42 try:
42 return dataset.peek 43 return dataset.peek
43 except: 44 except:
44 return "Binary sra file (%s)" % ( data.nice_size( dataset.get_size() ) ) 45 return 'Binary sra file (%s)' % ( data.nice_size(dataset.get_size()))
45 46
46 Binary.register_sniffable_binary_format("sra", "sra", Sra) 47 Binary.register_sniffable_binary_format('sra', 'sra', Sra)