comparison sra.py @ 0:cdcc400dcafc draft

Migrated separate tools fastq_dump, sam_dump, and sra_fetch to this repository for further development.
author matt-shirley <mdshw5@gmail.com>
date Tue, 27 Nov 2012 13:31:09 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:cdcc400dcafc
1 """
2 Sra class
3 """
4
5 import galaxy.datatypes.binary
6 from galaxy.datatypes.binary import Binary
7 import data, logging, binascii
8 from galaxy.datatypes.metadata import MetadataElement
9 from galaxy.datatypes import metadata
10 from galaxy.datatypes.sniff import *
11 from galaxy import eggs
12 import pkg_resources
13 pkg_resources.require( "bx-python" )
14 import os, subprocess, tempfile
15 import struct
16
17 class Sra( Binary ):
18 """ Sequence Read Archive (SRA) """
19 file_ext = "sra"
20
21 def __init__( self, **kwd ):
22 Binary.__init__( self, **kwd )
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
25 # about the format, see http://www.ncbi.nlm.nih.gov/books/n/helpsra/SRA_Overview_BK/#SRA_Overview_BK.4_SRA_Data_Structure
26 try:
27 header = open( filename ).read(8)
28 if binascii.b2a_hex( header ) == binascii.hexlify( 'NCBI.sra' ):
29 return True
30 return False
31 except:
32 return False
33 def set_peek( self, dataset, is_multi_byte=False ):
34 if not dataset.dataset.purged:
35 dataset.peek = "Binary sra file"
36 dataset.blurb = data.nice_size( dataset.get_size() )
37 else:
38 dataset.peek = 'file does not exist'
39 dataset.blurb = 'file purged from disk'
40 def display_peek( self, dataset ):
41 try:
42 return dataset.peek
43 except:
44 return "Binary sra file (%s)" % ( data.nice_size( dataset.get_size() ) )
45
46 Binary.register_sniffable_binary_format("sra", "sra", Sra)