Merge pull request #3381 from jmchilton/rename_improvements

Test cases & small enhancement to workflow renaming PJAs.

lib/galaxy/jobs/actions/post.py

@@ -142,6 +142,15 @@ class RenameDatasetAction(DefaultJobAction):
                     if input_assoc.name == input_file_var:
                         replacement = input_assoc.dataset.name
 
+                # Ditto for collections...
+                for input_assoc in job.input_dataset_collections:
+                    if input_assoc.name == input_file_var:
+                        if input_assoc.dataset_collection:
+                            hdca = input_assoc.dataset_collection
+                            replacement = hdca.name
+
+                # In case name was None.
+                replacement = replacement or ''
                 #  Do operations on replacement
                 #  Any control that is not defined will be ignored.
                 #  This should be moved out to a class or module function

lib/galaxy/model/__init__.py

@@ -593,8 +593,8 @@ class Job( object, JobLike, Dictifiable ):
     def add_output_dataset( self, name, dataset ):
         self.output_datasets.append( JobToOutputDatasetAssociation( name, dataset ) )
 
-    def add_input_dataset_collection( self, name, dataset ):
-        self.input_dataset_collections.append( JobToInputDatasetCollectionAssociation( name, dataset ) )
+    def add_input_dataset_collection( self, name, dataset_collection ):
+        self.input_dataset_collections.append( JobToInputDatasetCollectionAssociation( name, dataset_collection ) )
 
     def add_output_dataset_collection( self, name, dataset_collection_instance ):
         self.output_dataset_collection_instances.append( JobToOutputDatasetCollectionAssociation( name, dataset_collection_instance ) )
@@ -924,9 +924,9 @@ class JobToOutputDatasetAssociation( object ):
 
 
 class JobToInputDatasetCollectionAssociation( object ):
-    def __init__( self, name, dataset ):
+    def __init__( self, name, dataset_collection ):
         self.name = name
-        self.dataset = dataset
+        self.dataset_collection = dataset_collection
 
 
 # Many jobs may map to one HistoryDatasetCollection using these for a given

lib/galaxy/model/mapping.py

@@ -2026,8 +2026,7 @@ mapper( model.JobToOutputDatasetAssociation, model.JobToOutputDatasetAssociation
 mapper( model.JobToInputDatasetCollectionAssociation, model.JobToInputDatasetCollectionAssociation.table, properties=dict(
     job=relation( model.Job ),
     dataset_collection=relation( model.HistoryDatasetCollectionAssociation,
-        lazy=False,
-        backref="dependent_jobs" )
+        lazy=False )
 ) )
 
 mapper( model.JobToOutputDatasetCollectionAssociation, model.JobToOutputDatasetCollectionAssociation.table, properties=dict(

test/api/helpers.py

@@ -349,7 +349,7 @@ class LibraryPopulator( object ):
 
 class BaseDatasetCollectionPopulator( object ):
 
-    def create_list_from_pairs( self, history_id, pairs ):
+    def create_list_from_pairs( self, history_id, pairs, name="Dataset Collection from pairs" ):
         element_identifiers = []
         for i, pair in enumerate( pairs ):
             element_identifiers.append( dict(
@@ -363,6 +363,7 @@ class BaseDatasetCollectionPopulator( object ):
             history_id=history_id,
             element_identifiers=json.dumps(element_identifiers),
             collection_type="list:paired",
+            name=name,
         )
         return self.__create( payload )
 
@@ -401,6 +402,9 @@ class BaseDatasetCollectionPopulator( object ):
         if "element_identifiers" not in kwds:
             kwds[ "element_identifiers" ] = json.dumps( identifiers_func( history_id, contents=contents ) )
 
+        if "name" not in kwds:
+            kwds["name"] = "Test Dataset Collection"
+
         payload = dict(
             history_id=history_id,
             collection_type=collection_type,

test/api/test_workflows.py

@@ -201,12 +201,15 @@ class BaseWorkflowsApiTestCase( api.ApiTestCase, ImporterGalaxyInterface ):
                     elements.append( ( identifier, content ) )
                 # TODO: make this collection_type
                 collection_type = value["type"]
+                new_collection_kwds = {}
+                if "name" in value:
+                    new_collection_kwds["name"] = value["name"]
                 if collection_type == "list:paired":
-                    hdca = self.dataset_collection_populator.create_list_of_pairs_in_history( history_id ).json()
+                    hdca = self.dataset_collection_populator.create_list_of_pairs_in_history( history_id, **new_collection_kwds ).json()
                 elif collection_type == "list":
-                    hdca = self.dataset_collection_populator.create_list_in_history( history_id, contents=elements ).json()
+                    hdca = self.dataset_collection_populator.create_list_in_history( history_id, contents=elements, **new_collection_kwds ).json()
                 else:
-                    hdca = self.dataset_collection_populator.create_pair_in_history( history_id, contents=elements ).json()
+                    hdca = self.dataset_collection_populator.create_pair_in_history( history_id, contents=elements, **new_collection_kwds ).json()
                 label_map[key] = self._ds_entry( hdca )
                 inputs[key] = hdca
                 has_uploads = True
@@ -214,7 +217,14 @@ class BaseWorkflowsApiTestCase( api.ApiTestCase, ImporterGalaxyInterface ):
                 input_type = value["type"]
                 if input_type == "File":
                     content = read_test_data(value)
-                    hda = self.dataset_populator.new_dataset( history_id, content=content )
+                    new_dataset_kwds = {
+                        "content": content
+                    }
+                    if "name" in value:
+                        new_dataset_kwds["name"] = value["name"]
+                    if "file_type" in value:
+                        new_dataset_kwds["file_type"] = value["file_type"]
+                    hda = self.dataset_populator.new_dataset( history_id, **new_dataset_kwds )
                     label_map[key] = self._ds_entry( hda )
                     has_uploads = True
                 elif input_type == "raw":
@@ -1251,6 +1261,147 @@ test_data:
         content = self.dataset_populator.get_history_dataset_details( history_id, wait=True, assert_ok=True )
         assert content[ "name" ] == "foo was replaced"
 
+    @skip_without_tool( "cat" )
+    def test_run_rename_based_on_input( self ):
+        history_id = self.dataset_populator.new_history()
+        self._run_jobs("""
+class: GalaxyWorkflow
+inputs:
+  - id: input1
+steps:
+  - tool_id: cat
+    label: first_cat
+    state:
+      input1:
+        $link: input1
+    outputs:
+      out_file1:
+        rename: "#{input1 | basename} suffix"
+test_data:
+  input1:
+    value: 1.fasta
+    type: File
+    name: fasta1
+""", history_id=history_id)
+        content = self.dataset_populator.get_history_dataset_details( history_id, wait=True, assert_ok=True )
+        name = content[ "name" ]
+        assert name == "fasta1 suffix", name
+
+    @skip_without_tool( "cat" )
+    def test_run_rename_based_on_input_repeat( self ):
+        history_id = self.dataset_populator.new_history()
+        self._run_jobs("""
+class: GalaxyWorkflow
+inputs:
+  - id: input1
+  - id: input2
+steps:
+  - tool_id: cat
+    label: first_cat
+    state:
+      input1:
+        $link: input1
+      queries:
+        - input2:
+            $link: input2
+    outputs:
+      out_file1:
+        rename: "#{queries_0.input2| basename} suffix"
+test_data:
+  input1:
+    value: 1.fasta
+    type: File
+    name: fasta1
+  input2:
+    value: 1.fasta
+    type: File
+    name: fasta2
+""", history_id=history_id)
+        content = self.dataset_populator.get_history_dataset_details( history_id, wait=True, assert_ok=True )
+        name = content[ "name" ]
+        assert name == "fasta2 suffix", name
+
+    @skip_without_tool( "mapper2" )
+    def test_run_rename_based_on_input_conditional( self ):
+        history_id = self.dataset_populator.new_history()
+        self._run_jobs("""
+class: GalaxyWorkflow
+inputs:
+  - id: fasta_input
+  - id: fastq_input
+steps:
+  - tool_id: mapper2
+    state:
+      fastq_input:
+        fastq_input_selector: single
+        fastq_input1:
+          $link: fastq_input
+      reference:
+        $link: fasta_input
+    outputs:
+      out_file1:
+        # Wish it was qualified for conditionals but it doesn't seem to be. -John
+        # rename: "#{fastq_input.fastq_input1 | basename} suffix"
+        rename: "#{fastq_input1 | basename} suffix"
+test_data:
+  fasta_input:
+    value: 1.fasta
+    type: File
+    name: fasta1
+    file_type: fasta
+  fastq_input:
+    value: 1.fastqsanger
+    type: File
+    name: fastq1
+    file_type: fastqsanger
+""", history_id=history_id)
+        content = self.dataset_populator.get_history_dataset_details( history_id, wait=True, assert_ok=True )
+        name = content[ "name" ]
+        assert name == "fastq1 suffix", name
+
+    @skip_without_tool( "mapper2" )
+    def test_run_rename_based_on_input_collection( self ):
+        history_id = self.dataset_populator.new_history()
+        self._run_jobs("""
+class: GalaxyWorkflow
+inputs:
+  - id: fasta_input
+  - id: fastq_inputs
+steps:
+  - tool_id: mapper2
+    state:
+      fastq_input:
+        fastq_input_selector: paired_collection
+        fastq_input1:
+          $link: fastq_inputs
+      reference:
+        $link: fasta_input
+    outputs:
+      out_file1:
+        # Wish it was qualified for conditionals but it doesn't seem to be. -John
+        # rename: "#{fastq_input.fastq_input1 | basename} suffix"
+        rename: "#{fastq_input1} suffix"
+test_data:
+  fasta_input:
+    value: 1.fasta
+    type: File
+    name: fasta1
+    file_type: fasta
+  fastq_inputs:
+    type: list
+    name: the_dataset_pair
+    elements:
+      - identifier: forward
+        value: 1.fastq
+        type: File
+      - identifier: reverse
+        value: 1.fastq
+        type: File
+""", history_id=history_id)
+        content = self.dataset_populator.get_history_dataset_details( history_id, wait=True, assert_ok=True )
+        name = content[ "name" ]
+        assert name == "the_dataset_pair suffix", name
+
     @skip_without_tool( "cat1" )
     def test_run_with_runtime_pja( self ):
         workflow = self.workflow_populator.load_workflow( name="test_for_pja_runtime" )

test/functional/tools/for_workflows/mapper2.xml

@@ -0,0 +1,33 @@
+<tool id="mapper2" name="mapper2" version="0.1.0">
+    <command>
+        cp $__tool_directory__/1.bam $out_file1
+    </command>
+    <inputs>
+        <!-- Conditional input block loosely based on bwa-mem. -->
+        <conditional name="fastq_input">
+          <param name="fastq_input_selector" type="select" label="Single or Paired-end reads">
+            <option value="paired">Paired</option>
+            <option value="single">Single</option>
+            <option value="paired_collection">Paired Collection</option>
+            <option value="paired_iv">Paired Interleaved</option>
+          </param>
+          <when value="paired">
+            <param name="fastq_input1" type="data" format="fastq" label="Select first set of reads" />
+            <param name="fastq_input2" type="data" format="fastq" label="Select second set of reads" />
+          </when>
+          <when value="single">
+            <param name="fastq_input1" type="data" format="fastq" label="Select fastq dataset"/>
+          </when>
+          <when value="paired_collection">
+            <param name="fastq_input1" format="fastq" type="data_collection" collection_type="paired" label="Select a paired collection" />
+          </when>
+          <when value="paired_iv">
+            <param name="fastq_input1" type="data" format="fastq" label="Select fastq dataset" />
+          </when>
+        </conditional>
+        <param name="reference" type="data" format="fasta" label="Fasta Input"/>
+    </inputs>
+    <outputs>
+        <data name="out_file1" format="bam" />
+    </outputs>
+</tool>

test/functional/tools/samples_tool_conf.xml

@@ -114,6 +114,7 @@
   <tool file="for_workflows/cat_interleave.xml" />
   <tool file="for_workflows/pileup.xml" />
   <tool file="for_workflows/mapper.xml" />
+  <tool file="for_workflows/mapper2.xml" />
   <tool file="for_workflows/split.xml" />
   <tool file="for_workflows/create_input_collection.xml" />