[SL-7546] add name to fast dataset metadata loading

pbcommand/models/common.py

@@ -24,7 +24,7 @@
 REGISTERED_FILE_TYPES = {}
 
 # Light weight Dataset metatadata. Use pbcore for full dataset functionality
-DataSetMetaData = namedtuple("DataSetMetaData", 'uuid metatype')
+DataSetMetaData = namedtuple("DataSetMetaData", 'uuid metatype name')
 
 
 class PacBioNamespaces:

pbcommand/utils.py

@@ -470,16 +470,17 @@ def get_dataset_metadata(path):
     :raises: ValueError
     :return: DataSetMetaData
     """
-    uuid = mt = None
+    uuid = mt = name = None
     for event, element in ET.iterparse(path, events=("start",)):
         uuid = element.get("UniqueId")
         mt = element.get("MetaType")
+        name = element.get("Name")
         break
     else:
         raise ValueError(
             'Did not find events=("start",) in XML path={}'.format(path))
     if mt in FileTypes.ALL_DATASET_TYPES().keys():
-        return DataSetMetaData(uuid, mt)
+        return DataSetMetaData(uuid, mt, name)
     else:
         raise ValueError("Unsupported dataset type '{t}'".format(t=mt))
 

setup.py

@@ -15,7 +15,7 @@
 
 setup(
     name='pbcommand',
-    version='2.3.1',
+    version='2.3.2',
     author='Pacific Biosciences',
     author_email='devnet@pacificbiosciences.com',
     description='Library and Tools for interfacing with PacBio® data CLI tools',

tests/test_utils.py

@@ -105,6 +105,7 @@ def test_get_dataset_metadata(self):
         import pbtestdata
         md = get_dataset_metadata(pbtestdata.get_file("subreads-xml"))
         assert md.metatype == "PacBio.DataSet.SubreadSet"
+        assert md.name == "subreads-xml"
 
         from pbcore.io import SubreadSet
         ds = SubreadSet(pbtestdata.get_file("subreads-xml"))