Metadata will now be set on all output datasets when getting encode data.

tools/data_source/encode_import.py

@@ -9,76 +9,73 @@ from shutil import copyfile
 #tempfile, shutil
 BUFFER = 1048576
 
-uids = sys.argv[1].split(",")
-out_file1 = sys.argv[2]
+def stop_err( msg ):
+    sys.stderr.write( msg )
+    sys.exit()
 
-#remove NONE from uids
-have_none = True
-while have_none:
-    try:
-        uids.remove('None')
-    except:
-        have_none = False
-
-
-#create dictionary keyed by uid of tuples of (displayName,filePath,build) for all files
-available_files = {}
-try:
-    for line in open( "/depot/data2/galaxy/encode_datasets.loc" ):
-        if line[0:1] == "#" : continue
-        
-        fields = line.split('\t')
-        #read each line, if not enough fields, go to next line
+def main():
+    uids = sys.argv[1].split(",")
+    out_file1 = sys.argv[2]
+    file_name = "/depot/data2/galaxy/encode_datasets.loc"
+    
+    #remove NONE from uids
+    have_none = True
+    while have_none:
         try:
-            encode_group = fields[0]
-            build = fields[1]
-            description = fields[2]
-            uid = fields[3]
-            path = fields[4]
-            path = path.replace("\n","")
-            path = path.replace("\r","")
-            try:
-                file_type = fields[5]
-                #remove newlines from file type
-                file_type = file_type.replace("\n","")
-                file_type = file_type.replace("\r","")
-            except:
-                file_type = "bed"
-                
+            uids.remove('None')
+        except:
+            have_none = False
+    
+    #create dictionary keyed by uid of tuples of (displayName,filePath,build) for all files
+    available_files = {}
+    try:
+        for line in open( file_name ):
+            line = line.rstrip( '\r\n' )
+            if line and not line.startswith( '#' ):
+                fields = line.split( '\t' )
+                try:
+                    encode_group = fields[0].strip()
+                    build = fields[1].strip()
+                    description = fields[2].strip()
+                    uid = fields[3].strip()
+                    path = fields[4].strip()
+                    try:
+                        file_type = fields[5].strip()
+                    except:
+                        file_type = "bed"
+                except:
+                    continue
+                available_files[uid] = ( description, path, build, file_type )
+    except:
+        stop_err( "It appears that the configuration file for this tool is missing." )
+
+    #create list of tuples of ( displayName, FileName, build ) for desired files
+    desired_files = []
+    for uid in uids:
+        try:
+            desired_files.append( available_files[uid] )
         except:
             continue
-        available_files[uid]=(description,path,build,file_type)
-except:
-    print >>sys.stderr, "It appears that the configuration file for this tool is missing."
-
-#create list of tuples of (displayName,FileName,build) for desired files
-desired_files = []
-for uid in uids:
-    try:
-        desired_files.append(available_files[uid])
-    except:
-        continue
-
-#copy first file to contents of given output file
-file1_copied = False
-while not file1_copied:
-    try:
-        first_file = desired_files.pop(0)
-    except:
-        print >>sys.stderr, "There were no valid files requested."
-        sys.exit()
-    file1_desc, file1_path, file1_build, file1_type = first_file
-    try:
-        copyfile(file1_path,out_file1)
-        print "#File1\t"+file1_desc+"\t"+file1_build+"\t"+file1_type
-        file1_copied = True
-    except:
-        print >>sys.stderr, "The file specified is missing."
-        continue
-        #print >>sys.stderr, "The file specified is missing."
     
+    #copy first file to contents of given output file
+    file1_copied = False
+    while not file1_copied:
+        try:
+            first_file = desired_files.pop(0)
+        except:
+            stop_err( "There were no valid files requested." )
+        file1_desc, file1_path, file1_build, file1_type = first_file
+        try:
+            copyfile( file1_path, out_file1 )
+            print "#File1\t" + file1_desc + "\t" + file1_build + "\t" + file1_type
+            file1_copied = True
+        except:
+            #print "The file '%s' is missing." %str( file1_path )
+            continue
+        
+    #Tell post-process filter where remaining files reside
+    for extra_output in desired_files:
+        file_desc, file_path, file_build, file_type = extra_output
+        print "#NewFile\t" + file_desc + "\t" + file_build + "\t" + file_path + "\t" + file_type
 
-#Tell post-process filter where remaining files reside
-for extra_output in desired_files:
-    file_desc, file_path, file_build, file_type = extra_output
-    print "#NewFile\t"+file_desc+"\t"+file_build+"\t"+file_path+"\t"+file_type
+if __name__ == "__main__": main()

tools/data_source/encode_import_code.py

@@ -35,9 +35,7 @@ def exec_after_process(app, inp_data, out_data, param_dict, tool, stdout, stderr
             newdata = app.model.Dataset()
             newdata.extension = file_type
             newdata.name = basic_name + " (" + description + ")"
-            newdata.flush()
             history.add_dataset( newdata )
-            newdata.flush()
             app.model.flush()
             try:
                 copyfile(filepath,newdata.file_name)
@@ -47,7 +45,6 @@ def exec_after_process(app, inp_data, out_data, param_dict, tool, stdout, stderr
                 newdata.info = "The requested file is missing from the system."
                 newdata.state = jobs.JOB_ERROR
             newdata.dbkey = dbkey
-            newdata.init_meta()
+            newdata.set_meta()
             newdata.set_peek()
-            #
             app.model.flush()