Mercurial > repos > matt-shirley > ncbi_sra_toolkit

changeset 6:e4c21444a3ba

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Add sniffer, clean up imports, register sniffable datatype.
author Matt Shirley <mdshw5@gmail.com>
date Thu, 13 Mar 2014 15:30:54 -0400
parents 76c7d617cd56
children e724bff23fb6
files datatypes_conf.xml sra.py
diffstat 2 files changed, 15 insertions(+), 13 deletions(-) [+]
line wrap: on
line diff
--- a/datatypes_conf.xml	Mon Oct 07 10:13:06 2013 -0400
+++ b/datatypes_conf.xml	Thu Mar 13 15:30:54 2014 -0400
@@ -4,6 +4,9 @@
     <datatype_file name="sra.py"/>
   </datatype_files>
   <registration>
-    <datatype extension="sra" type="galaxy.datatypes.sra:sra" display_in_upload="true"/>
+    <datatype extension="sra" type="galaxy.datatypes.binary:Sra" mimetype="application/octet-stream" display_in_upload="true"/>
   </registration>
+  <sniffers>
+    <sniffer type="galaxy.datatypes.binary:Sra"/>
+  </sniffers>
 </datatypes>
--- a/sra.py	Mon Oct 07 10:13:06 2013 -0400
+++ b/sra.py	Thu Mar 13 15:30:54 2014 -0400
@@ -3,23 +3,21 @@
 """
 import logging
 import binascii
-from galaxy.datatypes.data import *
-from galaxy.datatypes.sniff import *
-from galaxy.datatypes.binary import *
-from galaxy.datatypes.metadata import *
+from galaxy.datatypes.data import nice_size
+from galaxy.datatypes.binary import Binary
 
 log = logging.getLogger(__name__)
 
-class sra( Binary ):
+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 'NCIB.sra', and the file is binary. EBI and DDBJ files may differ, though EBI and DDBJ 
-        submissions through NCBI (ERR and DRR accessions) read 'NCBI.sra'.
-        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 
+        """ 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)
@@ -29,18 +27,19 @@
                 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 = data.nice_size(dataset.get_size())
+            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)' % ( data.nice_size(dataset.get_size()))
+            return 'Binary sra file (%s)' % (nice_size(dataset.get_size()))
 
-if hasattr(Binary, 'register_sniffable_binary_format'):
-    Binary.register_sniffable_binary_format('sra', 'sra', sra)
\ No newline at end of file
+Binary.register_sniffable_binary_format('sra', 'sra', 'Sra')