Mercurial > repos > matt-shirley > ncbi_sra_toolkit
view sra.py @ 23:b94593ba997b
Can't use concurrency.
author | Matt Shirley <mdshw5@gmail.com> |
---|---|
date | Mon, 30 Mar 2015 21:23:35 -0400 |
parents | 558a88cd49e4 |
children | ce2bb7841f17 |
line wrap: on
line source
""" NCBI sra class """ import logging import binascii from galaxy.datatypes.data import nice_size from galaxy.datatypes.binary import Binary log = logging.getLogger(__name__) class Sra(Binary): """ Sequence Read Archive (SRA) """ file_ext = 'sra' def __init__( self, **kwd ): Binary.__init__( self, **kwd ) def sniff( self, filename ): """ The first 8 bytes of any NCBI sra file is 'NCBI.sra', and the file is binary. 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 """ try: header = open(filename).read(8) if binascii.b2a_hex(header) == binascii.hexlify('NCBI.sra'): return True else: return False except: return False def set_peek(self, dataset, is_multi_byte=False): if not dataset.dataset.purged: dataset.peek = 'Binary sra file' dataset.blurb = nice_size(dataset.get_size()) else: dataset.peek = 'file does not exist' dataset.blurb = 'file purged from disk' def display_peek(self, dataset): try: return dataset.peek except: return 'Binary sra file (%s)' % (nice_size(dataset.get_size()))