Within the vmfeed extension module there is a RepoFeed class that represents an installed repository. The RepoFeed.update_cache() method is responsible for reading the feed XML, and updating the database with each entry that is found. Here is what the ECP 2.1 version of the method looks like.
#ECP 2.1 version of RepoFeed.update_cache()
def update_cache(self):
"""This method will update the cache (the RepoEntry rows) with the new
versions of all of the data in the database.
@param self: The method class.
@type self: L{vmfeed.model.RepoFeed}
@return: None
@rtype: None
@raise None: No exceptions are raised by this method.
@status: Stable
@see: L{vmfeed.model.RepoFeed.validate_enclosure}"""
if not self.cache:
return False
self.retrieved_on=datetime.datetime.now()
feed=ET.fromstring(self.cache)
e2_log('Got a good feed %s'%feed, location=__name__)
feedname=None
feedname=feed.find('channel/title')
if feedname!=None and feedname.text.strip()!="":
e2_log('Updating feed name to %s'%feedname, location=__name__)
self.name=feedname.text.strip()
description=None
description=feed.find('channel/description')
if description!=None and description.text.strip()!="":
e2_log('Updating description to %s'%description,\
location=__name__)
self.description=description.text.strip()
items=feed.findall('channel/item')
if not len(items):
return 0
for i in items:
name=i.find('title').text.strip()
description=i.find('title').text.strip()
try:
description=i.find('description').text.strip()
except:
pass
U=None
U=i.find('uuid')
if U!=None:
U=U.text.strip().lower()
else:
U=gen_uuid()
enclosure=None
enclosures=i.findall('enclosure')
#Only the first enclosure matters, unless it is an egg, in which
#case we need to look at ALL of them and get the matching python
#release version.
#This should all get refactored actually...
for enclosure in enclosures:
e2_log('Enclosure is %s'%enclosure.attrib,\
location=__name__)
if enclosure!=None:
mime=self.enclosure_2_mime(enclosure)
if not mime:
enclosure=None
continue
elif not self.validate_enclosure(enclosure,mime):
enclosure=None
continue #Only known mime types get stored.
else:
break;
if enclosure!=None:
#mime=self.enclosure_2_mime(enclosure)
if not mime:
continue #Only known mime types get stored.
e2_log('Found an enclosure %s'%enclosure.attrib['url'],\
location=__name__)
url=enclosure.attrib['url']
url=self.normalize_url(url)
try:
if U:
re=RepoEntry.by_uuid(U)
else:
re=RepoEntry.by_url(url)
except:
re=RepoEntry(url=url,\
name=name,\
description=description,\
feed=self)
re.set(description=description,\
name=name,\
url=url,\
retrieved_on=datetime.datetime.now(),\
mime=mime,\
uuid=U,\
)
re.sync()
#re.retrieved_on=datetime.datetime.now()
#re.description=description
#re.mime=mime
#re.uuid=U
else:
e2_log('No enclosures found in entry %s'%name,\
location=__name__)
if enclosure:
e2_log('Enclosure had attribs %s'%enclosure.attrib,\
location=__name__)
return 1
The main problem the ECP development team found with this method is that it is not very cohesive. The responsibilities of this method are very broad:
- Parse XML
- Initialize repository entry parameters
- Iterate through item elements (while performing XML operations)
- Iterate through enclosure elements (while performing XML operations)
- Check if the repository entry exists and create it if not.
Here is a taste what what the ECP 2.2 version of the same method will look like.
#ECP 2.2 version of RepoFeed.update_cache()
def update_cache(self, tx=None):
"""This method will update the cache (the RepoEntry rows) with the new
versions of all of the data in the database.
@param self: The method class.
@type self: L{vmfeed.model.RepoFeed}
@return: None
@rtype: None
@raise None: No exceptions are raised by this method.
@status: Stable
@see: L{vmfeed.model.RepoFeed.validate_enclosure}"""
self.retrieved_on=datetime.datetime.now()
feed_xml=get_element(self.cache)
try:
name=get_element_text(feed_xml, element='channel/title')
self.name=name.strip()
except AttributeError:
pass
try:
desc=get_element_text(feed_xml, element='channel/description')
self.description=desc.strip()
except AttributeError:
pass
for item in VMFeedTools.get_items_xml(feed_xml):
try:
name=get_element_text(item, element='title')
name=name.strip()
except AttributeError:
name=None
try:
desc=get_element_text(item, element='description')
desc=desc.strip()
except AttributeError:
desc=None
try:
item_uuid=get_element_text(item, element='uuid')
item_uuid=item_uuid.strip().lower()
except AttributeError:
item_uuid=gen_uuid()
enclosure=VMFeedTools.get_valid_enclosure_xml(item)
url=get_element_property(enclosure, None, 'url')
mime=VMFeedTools.enclosure_2_mime(enclosure)
try:
entry_obj=VMFeedTools.get_repo_entry(item_uuid)
except RepoEntryNotFound, e:
e.store_traceback()
entry_obj=RepoEntry(uuid=item_uuid,\
url=url,\
name=name,\
description=desc,\
retrieved_on=datetime.datetime.now(),\
mime=mime,\
feed=self)
else:
entry_obj.set(uuid=item_uuid,\
url=url,\
name=name,\
description=desc,\
retrieved_on=datetime.datetime.now(),\
mime=mime)
entry_obj.sync()