Merge pull request #1665 from lecorguille/zip_datatype

add a zip datatype which won't be extracted

config/datatypes_conf.xml.sample

@@ -145,6 +145,7 @@
     <datatype extension="pbm" type="galaxy.datatypes.images:Pbm" mimetype="image/pbm"/>
     <datatype extension="pgm" type="galaxy.datatypes.images:Pgm" mimetype="image/pgm"/>
     <datatype extension="rna_eps" type="galaxy.datatypes.sequence:RNADotPlotMatrix" mimetype="image/eps" display_in_upload="True"/>
+    <datatype extension="zip" type="galaxy.datatypes.binary:CompressedZipArchive" display_in_upload="True"/>
     <!-- Proteomics Datatypes -->
     <datatype extension="pepxml" type="galaxy.datatypes.proteomics:PepXml" mimetype="application/xml" display_in_upload="True"/>
     <datatype extension="raw_pepxml" type="galaxy.datatypes.proteomics:PepXml" mimetype="application/xml" subclass="True"/>

lib/galaxy/datatypes/binary.py

@@ -146,6 +146,31 @@ class CompressedArchive( Binary ):
 Binary.register_unsniffable_binary_ext("compressed_archive")
 
 
+class CompressedZipArchive( CompressedArchive ):
+    """
+        Class describing an compressed binary file
+        This class can be sublass'ed to implement archive filetypes that will not be unpacked by upload.py.
+    """
+    file_ext = "zip"
+
+    def set_peek( self, dataset, is_multi_byte=False ):
+        if not dataset.dataset.purged:
+            dataset.peek = "Compressed zip 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 "Compressed zip file (%s)" % ( nice_size( dataset.get_size() ) )
+
+
+Binary.register_unsniffable_binary_ext("zip")
+
+
 class GenericAsn1Binary( Binary ):
     """Class for generic ASN.1 binary format"""
     file_ext = "asn1-binary"