Merge pull request #39 from mvdbeek/bam_unsorted

Fix tests and revert additional sorting of converters

config/datatypes_conf.xml.sample

@@ -288,8 +288,8 @@
     <datatype extension="qual454" type="galaxy.datatypes.qualityscore:QualityScore454" display_in_upload="true"/>
     <datatype extension="roadmaps" type="galaxy.datatypes.assembly:Roadmaps" display_in_upload="false"/>
     <datatype extension="sam" type="galaxy.datatypes.tabular:Sam" display_in_upload="true">
-        <converter file="sam_to_bam.xml" target_datatype="bam"/>
         <converter file="sam_to_bam_native.xml" target_datatype="bam_native"/>
+        <converter file="sam_to_bam.xml" target_datatype="bam"/>
         <converter file="sam_to_bigwig_converter.xml" target_datatype="bigwig"/>
     </datatype>
     <datatype extension="scf" type="galaxy.datatypes.binary:Scf" mimetype="application/octet-stream" display_in_upload="true" description="A binary sequence file in 'scf' format with a '.scf' file extension.  You must manually select this 'File Format' when uploading the file." description_url="https://wiki.galaxyproject.org/Learn/Datatypes#Scf"/>

lib/galaxy/datatypes/converters/sam_to_bam_native.xml

@@ -6,6 +6,7 @@
     <command><![CDATA[
         samtools view
             -b
+            -h
             -@ \${GALAXY_SLOTS:-2}
             -o '${output}'
             '$input'

lib/galaxy/datatypes/registry.py

@@ -798,34 +798,19 @@ class Registry(object):
                 tabular.CSV()
             ]
 
-    def get_converters_by_datatype(self, ext, priority_formats=None):
-        """
-            Returns available converters by source type.
-            `priority_formats` will contain a list of format extensions that should
-            be handled with priority. This means they will end up infront of the
-            returned ordered dictionary.
-        """
+    def get_converters_by_datatype(self, ext):
+        """Returns available converters by source type"""
         if ext not in self._converters_by_datatype:
             converters = odict()
-            prio_converters = odict()
             source_datatype = type(self.get_datatype_by_extension(ext))
             for ext2, converters_dict in self.datatype_converters.items():
                 converter_datatype = type(self.get_datatype_by_extension(ext2))
                 if issubclass(source_datatype, converter_datatype):
-                    for k, v in converters_dict.items():
-                        if k in priority_formats:
-                            prio_converters[k] = v
-                        else:
-                            converters[k] = v
+                    converters.update(converters_dict)
             # Ensure ext-level converters are present
             if ext in self.datatype_converters.keys():
-                for k, v in self.datatype_converters[ext].items():
-                    if k in priority_formats:
-                        prio_converters[k] = v
-                    else:
-                        converters[k] = v
-            prio_converters.update(converters)
-            self._converters_by_datatype[ext] = prio_converters
+                converters.update(self.datatype_converters[ext])
+            self._converters_by_datatype[ext] = converters
         return self._converters_by_datatype[ext]
 
     def get_converter_by_target_type(self, source_ext, target_ext):
@@ -837,10 +822,7 @@ class Registry(object):
 
     def find_conversion_destination_for_dataset_by_extensions(self, dataset, accepted_formats, converter_safe=True):
         """Returns ( target_ext, existing converted dataset )"""
-
-        converters = self.get_converters_by_datatype(dataset.ext, [k.file_ext for k in accepted_formats])
-
-        for convert_ext in converters:
+        for convert_ext in self.get_converters_by_datatype(dataset.ext):
             convert_ext_datatype = self.get_datatype_by_extension(convert_ext)
             if convert_ext_datatype is None:
                 self.log.warning("Datatype class not found for extension '%s', which is used as target for conversion from datatype '%s'" % (convert_ext, dataset.ext))

test/functional/tools/sam_to_bam_native.xml

@@ -6,31 +6,41 @@
     #if $input1:
         samtools view
             -b
+            -h
             -@ \${GALAXY_SLOTS:-2}
-            -o '${output}'
+            -o '$bam_native_output'
             '$input1'
-    #else
-        cp '$input2' '$output'
+    #elif $input2:
+        cp '$input2' '$bam_native_output'
+    #elif $input3:
+        cp '$input3' '$bam_output'
     #end if
     ]]>
     </command>
     <inputs>
         <param name="input1" type="data" format="sam" label="SAM file" optional="true"/>
         <param name="input2" type="data" format="bam_native" label="Unsorted BAM file" optional="true"/>
+        <param name="input3" type="data" format="bam" label="Sorted BAM file" optional="true"/>
     </inputs>
     <outputs>
-        <data name="output" format="bam_native"/>
+        <data name="bam_native_output" format="bam_native"/>
+        <data name="bam_output" format="bam"/>
     </outputs>
     <tests>
         <!-- Test that bam native output won't be sorted-->
         <test>
             <param name="input1" value="sam_with_header.sam" ftype="sam"/>
-            <output name="output" file="bam_native_from_sam.bam" ftype="bam_native"/>
+            <output name="bam_native_output" file="bam_native_from_sam.bam" ftype="bam_native"/>
         </test>
         <!-- Test that sam input is properly converted to bam native -->
         <test>
             <param name="input2" value="sam_with_header.sam" ftype="sam"/>
-            <output name="output" file="bam_native_from_sam.bam" ftype="bam_native"/>
+            <output name="bam_native_output" file="bam_native_from_sam.bam" ftype="bam_native"/>
+        </test>
+        <!-- Test that sam input is properly converted to bam -->
+        <test>
+            <param name="input3" value="sam_with_header.sam" ftype="sam"/>
+            <output name="bam_output" file="bam_from_sam.bam" ftype="bam"/>
         </test>
     </tests>
     <help>