Add descriptor for modules with empty XML data.

This allows a more general approach to modules such as word_cloud and
video which have no XML data (it's all store in metadata), but use
XmlDescriptor for backwards compatibility. They now generate an empty
tag on export, and clear out empty tags on import.

Also a small change to the video module as a result -- if it's asked
to parse empty XML data, it won't try to parse anything.

cms/djangoapps/contentstore/tests/test_contentstore.py

@@ -883,6 +883,40 @@ class ContentStoreToyCourseTest(ModuleStoreTestCase):
 
         shutil.rmtree(root_dir)
 
+    def test_empty_data_roundtrip(self):
+        """
+        Test that an empty `data` field is preserved through
+        export/import.
+        """
+        module_store = modulestore('direct')
+        draft_store = modulestore('draft')
+        content_store = contentstore()
+
+        import_from_xml(module_store, 'common/test/data/', ['toy'])
+        location = CourseDescriptor.id_to_location('edX/toy/2012_Fall')
+
+        verticals = module_store.get_items(['i4x', 'edX', 'toy', 'vertical', None, None])
+
+        self.assertGreater(len(verticals), 0)
+
+        parent = verticals[0]
+
+        # Create a module, and ensure that its `data` field is empty
+        word_cloud = ItemFactory.create(parent_location=parent.location, category="word_cloud", display_name="untitled")
+        del word_cloud.data
+        self.assertEquals(word_cloud.data, '')
+
+        # Export the course
+        root_dir = path(mkdtemp_clean())
+        export_to_xml(module_store, content_store, location, root_dir, 'test_roundtrip', draft_modulestore=draft_store)
+
+        # Reimport and get the video back
+        import_from_xml(module_store, root_dir)
+        imported_word_cloud = module_store.get_item(Location(['i4x', 'edX', 'toy', 'word_cloud', 'untitled', None]))
+
+        # It should now contain empty data
+        self.assertEquals(imported_word_cloud.data, '')
+
     def test_course_handouts_rewrites(self):
         module_store = modulestore('direct')
 

common/lib/xmodule/xmodule/raw_module.py

@@ -20,8 +20,6 @@ class RawDescriptor(XmlDescriptor, XMLEditingDescriptor):
         return {'data': etree.tostring(xml_object, pretty_print=True, encoding='unicode')}, []
 
     def definition_to_xml(self, resource_fs):
-        if not self.data:
-            return etree.fromstring('<{0} />'.format(self.category))
         try:
             return etree.fromstring(self.data)
         except etree.XMLSyntaxError as err:
@@ -34,3 +32,22 @@ class RawDescriptor(XmlDescriptor, XMLEditingDescriptor):
                    context=lines[line - 1][offset - 40:offset + 40],
                    loc=self.location))
             raise Exception, msg, sys.exc_info()[2]
+
+
+class EmptyDataRawDescriptor(XmlDescriptor, XMLEditingDescriptor):
+    """
+    Version of RawDescriptor for modules which may have no XML data,
+    but use XMLEditingDescriptor for import/export handling.
+    """
+    data = String(default='', scope=Scope.content)
+
+    @classmethod
+    def definition_from_xml(cls, xml_object, system):
+        if len(xml_object) == 0 and len(xml_object.items()) == 0:
+            return {'data': ''}, []
+        return {'data': etree.tostring(xml_object, pretty_print=True, encoding='unicode')}, []
+
+    def definition_to_xml(self, resource_fs):
+        if self.data:
+            return etree.fromstring(self.data)
+        return etree.Element(self.category)

common/lib/xmodule/xmodule/video_module.py

@@ -12,7 +12,7 @@ import time
 from django.http import Http404
 
 from xmodule.x_module import XModule
-from xmodule.raw_module import RawDescriptor
+from xmodule.raw_module import EmptyDataRawDescriptor
 from xmodule.editing_module import MetadataOnlyEditingDescriptor
 from xblock.core import Integer, Scope, String, Float, Boolean
 
@@ -97,7 +97,7 @@ class VideoModule(VideoFields, XModule):
 
 class VideoDescriptor(VideoFields,
                       MetadataOnlyEditingDescriptor,
-                      RawDescriptor):
+                      EmptyDataRawDescriptor):
     module_class = VideoModule
 
     def __init__(self, *args, **kwargs):
@@ -136,6 +136,9 @@ def _parse_video_xml(video, xml_data):
     Parse video fields out of xml_data. The fields are set if they are
     present in the XML.
     """
+    if not xml_data:
+        return
+
     xml = etree.fromstring(xml_data)
 
     display_name = xml.get('display_name')

common/lib/xmodule/xmodule/word_cloud_module.py

@@ -10,7 +10,7 @@ import json
 import logging
 
 from pkg_resources import resource_string
-from xmodule.raw_module import RawDescriptor
+from xmodule.raw_module import EmptyDataRawDescriptor
 from xmodule.editing_module import MetadataOnlyEditingDescriptor
 from xmodule.x_module import XModule
 
@@ -240,7 +240,7 @@ class WordCloudModule(WordCloudFields, XModule):
         return self.content
 
 
-class WordCloudDescriptor(WordCloudFields, MetadataOnlyEditingDescriptor, RawDescriptor):
+class WordCloudDescriptor(WordCloudFields, MetadataOnlyEditingDescriptor, EmptyDataRawDescriptor):
     """Descriptor for WordCloud Xmodule."""
     module_class = WordCloudModule
     template_dir_name = 'word_cloud'