def mark_story_as_read(request):
story_ids = request.REQUEST.getlist("story_id")
feed_id = int(request.REQUEST["feed_id"])
try:
usersub = UserSubscription.objects.select_related("feed").get(user=request.user, feed=feed_id)
except Feed.DoesNotExist:
duplicate_feed = DuplicateFeed.objects.filter(duplicate_feed_id=feed_id)
if duplicate_feed:
try:
usersub = UserSubscription.objects.get(user=request.user, feed=duplicate_feed[0].feed)
except Feed.DoesNotExist:
return dict(code=-1)
if not usersub.needs_unread_recalc:
usersub.needs_unread_recalc = True
usersub.save()
data = dict(code=0, payload=story_ids)
if len(story_ids) > 1:
logging.info(" ---> [%s] ~FYRead %s stories in feed: %s" % (request.user, len(story_ids), usersub.feed))
else:
logging.info(" ---> [%s] ~FYRead story in feed: %s" % (request.user, usersub.feed))
for story_id in story_ids:
story = MStory.objects(story_feed_id=feed_id, story_guid=story_id)[0]
now = datetime.datetime.utcnow()
m = MUserStory(story=story, user_id=request.user.pk, feed_id=feed_id, read_date=now)
try:
m.save()
except OperationError:
logging.info(" ---> [%s] ~BRMarked story as read: Duplicate Story -> %s" % (request.user, story_id))
return data
def bootstrap_userstories():
print "Mongo DB userstories: %s" % MUserStory.objects().count()
# db.userstories.drop()
print "Dropped! Mongo DB userstories: %s" % MUserStory.objects().count()
print "UserStories: %s" % UserStory.objects.all().count()
pprint(db.userstories.index_information())
userstories = UserStory.objects.all().values()
for userstory in userstories:
try:
story = Story.objects.get(pk=userstory['story_id'])
except Story.DoesNotExist:
continue
try:
userstory['story'] = MStory.objects(story_feed_id=story.story_feed.pk, story_guid=story.story_guid)[0]
except:
print '!',
continue
print '.',
del userstory['id']
del userstory['opinion']
del userstory['story_id']
try:
MUserStory(**userstory).save()
except:
print '\n\n!\n\n'
continue
print "\nMongo DB userstories: %s" % MUserStory.objects().count()
def mark_story_as_read(request):
story_ids = request.REQUEST.getlist('story_id')
feed_id = int(request.REQUEST['feed_id'])
usersub = UserSubscription.objects.select_related('feed').get(user=request.user, feed=feed_id)
if not usersub.needs_unread_recalc:
usersub.needs_unread_recalc = True
usersub.save()
data = dict(code=0, payload=story_ids)
if len(story_ids) > 1:
logging.debug(" ---> [%s] Read %s stories in feed: %s" % (request.user, len(story_ids), usersub.feed))
else:
logging.debug(" ---> [%s] Read story in feed: %s" % (request.user, usersub.feed))
for story_id in story_ids:
story = MStory.objects(story_feed_id=feed_id, story_guid=story_id)[0]
now = datetime.datetime.utcnow()
m = MUserStory(story=story, user_id=request.user.pk, feed_id=feed_id, read_date=now)
try:
m.save()
except OperationError:
logging.info(' ---> [%s] *** Marked story as read: Duplicate Story -> %s' % (request.user, story_id))
return data
def bootstrap_userstories():
print "Mongo DB userstories: %s" % MUserStory.objects().count()
# db.userstories.drop()
print "Dropped! Mongo DB userstories: %s" % MUserStory.objects().count()
print "UserStories: %s" % UserStory.objects.all().count()
pprint(db.userstories.index_information())
userstories = UserStory.objects.all().values()
for userstory in userstories:
try:
story = Story.objects.get(pk=userstory['story_id'])
except Story.DoesNotExist:
continue
try:
userstory['story'] = MStory.objects(
story_feed_id=story.story_feed.pk,
story_guid=story.story_guid)[0]
except:
print '!',
continue
print '.',
del userstory['id']
del userstory['opinion']
del userstory['story_id']
try:
MUserStory(**userstory).save()
except:
print '\n\n!\n\n'
continue
print "\nMongo DB userstories: %s" % MUserStory.objects().count()
def delete_feed(request):
feed_id = int(request.POST['feed_id'])
user_sub = get_object_or_404(UserSubscription, user=request.user, feed=feed_id)
user_sub.delete()
MUserStory.objects(user_id=request.user.pk, feed_id=feed_id).delete()
def _find_feed_in_folders(old_folders):
new_folders = []
for k, folder in enumerate(old_folders):
if isinstance(folder, int):
if folder == feed_id:
logging.info(" ---> [%s] Delete folder: %s'th item: %s folders/feeds" % (
request.user, k, len(old_folders)
))
# folders.remove(folder)
else:
new_folders.append(folder)
elif isinstance(folder, dict):
for f_k, f_v in folder.items():
new_folders.append({f_k: _find_feed_in_folders(f_v)})
return new_folders
user_sub_folders_object = UserSubscriptionFolders.objects.get(user=request.user)
user_sub_folders = json.decode(user_sub_folders_object.folders)
user_sub_folders = _find_feed_in_folders(user_sub_folders)
user_sub_folders_object.folders = json.encode(user_sub_folders)
user_sub_folders_object.save()
return dict(code=1)
def process_feed_wrapper(self, feed_queue):
delta = None
current_process = multiprocessing.current_process()
identity = "X"
if current_process._identity:
identity = current_process._identity[0]
for feed_id in feed_queue:
ret_entries = {
ENTRY_NEW: 0,
ENTRY_UPDATED: 0,
ENTRY_SAME: 0,
ENTRY_ERR: 0
}
start_time = datetime.datetime.utcnow()
try:
feed = self.refresh_feed(feed_id)
ffeed = FetchFeed(feed_id, self.options)
ret_feed, fetched_feed = ffeed.fetch()
if ((fetched_feed and ret_feed == FEED_OK)
or self.options['force']):
pfeed = ProcessFeed(feed_id, fetched_feed, self.options)
ret_feed, ret_entries = pfeed.process()
feed = self.refresh_feed(feed_id)
if ret_entries.get(ENTRY_NEW) or self.options[
'force'] or not feed.fetched_once:
if not feed.fetched_once:
feed.fetched_once = True
feed.save()
MUserStory.delete_old_stories(feed_id=feed.pk)
try:
self.count_unreads_for_subscribers(feed)
except TimeoutError:
logging.debug(
' ---> [%-30s] Unread count took too long...'
% (unicode(feed)[:30], ))
cache.delete('feed_stories:%s-%s-%s' % (feed.id, 0, 25))
# if ret_entries.get(ENTRY_NEW) or ret_entries.get(ENTRY_UPDATED) or self.options['force']:
# feed.get_stories(force=True)
except KeyboardInterrupt:
break
except urllib2.HTTPError, e:
feed.save_feed_history(e.code, e.msg, e.fp.read())
fetched_feed = None
except Feed.DoesNotExist, e:
logging.debug(' ---> [%-30s] Feed is now gone...' %
(unicode(feed_id)[:30]))
continue
def process_feed_wrapper(self, feed_queue):
""" wrapper for ProcessFeed
"""
UNREAD_CUTOFF = datetime.datetime.utcnow() - datetime.timedelta(days=settings.DAYS_OF_UNREAD)
delta = None
current_process = multiprocessing.current_process()
identity = "X"
if current_process._identity:
identity = current_process._identity[0]
for feed_id in feed_queue:
ret_entries = {ENTRY_NEW: 0, ENTRY_UPDATED: 0, ENTRY_SAME: 0, ENTRY_ERR: 0}
start_time = datetime.datetime.utcnow()
feed = self.refresh_feed(feed_id)
try:
ffeed = FetchFeed(feed_id, self.options)
ret_feed, fetched_feed = ffeed.fetch()
if (fetched_feed and ret_feed == FEED_OK) or self.options["force"]:
pfeed = ProcessFeed(feed_id, fetched_feed, self.options)
ret_feed, ret_entries = pfeed.process()
feed = self.refresh_feed(feed_id)
if ret_entries.get(ENTRY_NEW) or self.options["force"] or not feed.fetched_once:
if not feed.fetched_once:
feed.fetched_once = True
feed.save()
MUserStory.delete_old_stories(feed_id=feed.pk)
user_subs = UserSubscription.objects.filter(feed=feed)
logging.debug(
u" ---> [%-30s] Computing scores for all feed subscribers: %s subscribers"
% (unicode(feed)[:30], user_subs.count())
)
stories_db = MStory.objects(story_feed_id=feed.pk, story_date__gte=UNREAD_CUTOFF)
for sub in user_subs:
cache.delete("usersub:%s" % sub.user_id)
silent = False if self.options["verbose"] >= 2 else True
sub.calculate_feed_scores(silent=silent, stories_db=stories_db)
cache.delete("feed_stories:%s-%s-%s" % (feed.id, 0, 25))
# if ret_entries.get(ENTRY_NEW) or ret_entries.get(ENTRY_UPDATED) or self.options['force']:
# feed.get_stories(force=True)
except KeyboardInterrupt:
break
except urllib2.HTTPError, e:
feed.save_feed_history(e.code, e.msg, e.fp.read())
fetched_feed = None
except Feed.DoesNotExist, e:
logging.debug(" ---> [%-30s] Feed is now gone..." % (unicode(feed)[:30]))
return
def process_feed_wrapper(self, feed_queue):
delta = None
current_process = multiprocessing.current_process()
identity = "X"
if current_process._identity:
identity = current_process._identity[0]
for feed_id in feed_queue:
ret_entries = {
ENTRY_NEW: 0,
ENTRY_UPDATED: 0,
ENTRY_SAME: 0,
ENTRY_ERR: 0
}
start_time = time.time()
ret_feed = FEED_ERREXC
try:
feed = self.refresh_feed(feed_id)
if self.options.get('fake'):
logging.debug(' ---> [%-30s] ~BGFaking fetch, skipping...' % (unicode(feed)[:30],))
continue
ffeed = FetchFeed(feed_id, self.options)
ret_feed, fetched_feed = ffeed.fetch()
if ((fetched_feed and ret_feed == FEED_OK) or self.options['force']):
pfeed = ProcessFeed(feed_id, fetched_feed, self.options)
ret_feed, ret_entries = pfeed.process()
feed = self.refresh_feed(feed_id)
if ret_entries.get(ENTRY_NEW) or self.options['force']:
if not feed.known_good:
feed.known_good = True
feed.save()
MUserStory.delete_old_stories(feed_id=feed.pk)
try:
self.count_unreads_for_subscribers(feed)
except TimeoutError:
logging.debug(' ---> [%-30s] Unread count took too long...' % (unicode(feed)[:30],))
cache.delete('feed_stories:%s-%s-%s' % (feed.id, 0, 25))
# if ret_entries.get(ENTRY_NEW) or ret_entries.get(ENTRY_UPDATED) or self.options['force']:
# feed.get_stories(force=True)
except KeyboardInterrupt:
break
except urllib2.HTTPError, e:
feed.save_feed_history(e.code, e.msg, e.fp.read())
fetched_feed = None
except Feed.DoesNotExist, e:
logging.debug(' ---> [%-30s] Feed is now gone...' % (unicode(feed_id)[:30]))
continue
def mark_feed_as_read(request):
feed_id = int(request.REQUEST['feed_id'])
feed = Feed.objects.get(id=feed_id)
code = 0
us = UserSubscription.objects.get(feed=feed, user=request.user)
try:
us.mark_feed_read()
except IntegrityError:
code = -1
else:
code = 1
logging.info(" ---> [%s] Marking feed as read: %s" % (request.user, feed,))
MUserStory.objects(user_id=request.user.pk, feed_id=feed_id).delete()
return dict(code=code)
def trim_feed(self):
from apps.reader.models import MUserStory
trim_cutoff = 500
if self.active_subscribers <= 1:
trim_cutoff = 50
elif self.active_subscribers <= 3:
trim_cutoff = 100
elif self.active_subscribers <= 5:
trim_cutoff = 150
elif self.active_subscribers <= 10:
trim_cutoff = 250
elif self.active_subscribers <= 25:
trim_cutoff = 350
stories = MStory.objects(story_feed_id=self.pk).order_by("-story_date")
if stories.count() > trim_cutoff:
# print 'Found %s stories in %s. Trimming...' % (stories.count(), self),
story_trim_date = stories[trim_cutoff].story_date
extra_stories = MStory.objects(story_feed_id=self.pk, story_date__lte=story_trim_date)
extra_stories.delete()
# print "Deleted stories, %s left." % MStory.objects(story_feed_id=self.pk).count()
userstories = MUserStory.objects(feed_id=self.pk, read_date__lte=story_trim_date)
if userstories.count():
# print "Found %s user stories. Deleting..." % userstories.count()
userstories.delete()
def mark_story_as_unread(request):
story_id = request.POST['story_id']
feed_id = int(request.POST['feed_id'])
try:
usersub = UserSubscription.objects.select_related('feed').get(user=request.user, feed=feed_id)
except Feed.DoesNotExist:
duplicate_feed = DuplicateFeed.objects.filter(duplicate_feed_id=feed_id)
if duplicate_feed:
try:
usersub = UserSubscription.objects.get(user=request.user,
feed=duplicate_feed[0].feed)
except Feed.DoesNotExist:
return dict(code=-1)
if not usersub.needs_unread_recalc:
usersub.needs_unread_recalc = True
usersub.save()
data = dict(code=0, payload=dict(story_id=story_id))
logging.user(request, "~FY~SBUnread~SN story in feed: %s" % (usersub.feed))
story = MStory.objects(story_feed_id=feed_id, story_guid=story_id)[0]
m = MUserStory.objects(story=story, user_id=request.user.pk, feed_id=feed_id)
m.delete()
return data
def mark_story_as_unread(request):
story_id = request.POST['story_id']
feed_id = int(request.POST['feed_id'])
try:
usersub = UserSubscription.objects.select_related('feed').get(user=request.user, feed=feed_id)
except Feed.DoesNotExist:
duplicate_feed = DuplicateFeed.objects.filter(duplicate_feed_id=feed_id)
if duplicate_feed:
try:
usersub = UserSubscription.objects.get(user=request.user,
feed=duplicate_feed[0].feed)
except Feed.DoesNotExist:
return dict(code=-1)
if not usersub.needs_unread_recalc:
usersub.needs_unread_recalc = True
usersub.save()
data = dict(code=0, payload=dict(story_id=story_id))
logging.user(request.user, "~FY~SBUnread~SN story in feed: %s" % (usersub.feed))
story = MStory.objects(story_feed_id=feed_id, story_guid=story_id)[0]
m = MUserStory.objects(story=story, user_id=request.user.pk, feed_id=feed_id)
m.delete()
return data
def trim_feed(self, verbose=False):
from apps.reader.models import MUserStory
trim_cutoff = 500
if self.active_subscribers <= 1:
trim_cutoff = 50
elif self.active_subscribers <= 3:
trim_cutoff = 100
elif self.active_subscribers <= 5:
trim_cutoff = 150
elif self.active_subscribers <= 10:
trim_cutoff = 250
elif self.active_subscribers <= 25:
trim_cutoff = 350
stories = MStory.objects(
story_feed_id=self.pk, ).order_by('-story_date')
if stories.count() > trim_cutoff:
if verbose:
print 'Found %s stories in %s. Trimming to %s...' % (
stories.count(), self, trim_cutoff)
story_trim_date = stories[trim_cutoff].story_date
extra_stories = MStory.objects(story_feed_id=self.pk,
story_date__lte=story_trim_date)
extra_stories.delete()
# print "Deleted stories, %s left." % MStory.objects(story_feed_id=self.pk).count()
userstories = MUserStory.objects(feed_id=self.pk,
read_date__lte=story_trim_date)
if userstories.count():
# print "Found %s user stories. Deleting..." % userstories.count()
userstories.delete()
def mark_story_as_unread(request):
story_id = request.POST['story_id']
feed_id = int(request.POST['feed_id'])
usersub = UserSubscription.objects.select_related('feed').get(user=request.user, feed=feed_id)
if not usersub.needs_unread_recalc:
usersub.needs_unread_recalc = True
usersub.save()
data = dict(code=0, payload=dict(story_id=story_id))
logging.user(request, "~FY~SBUnread~SN story in feed: %s" % (usersub.feed))
story = MStory.objects(story_feed_id=feed_id, story_guid=story_id)[0]
if story.story_date < usersub.mark_read_date:
# Story is outside the mark as read range, so invert all stories before.
newer_stories = MStory.objects(story_feed_id=story.story_feed_id,
story_date__gte=story.story_date,
story_date__lte=usersub.mark_read_date
).only('story_guid')
newer_stories = [s.story_guid for s in newer_stories]
usersub.mark_read_date = story.story_date - datetime.timedelta(minutes=1)
usersub.needs_unread_recalc = True
usersub.save()
# Mark stories as read only after the mark_read_date has been moved, otherwise
# these would be ignored.
data = usersub.mark_story_ids_as_read(newer_stories, request=request)
m = MUserStory.objects(story_id=story_id, user_id=request.user.pk, feed_id=feed_id)
m.delete()
return data
def mark_story_as_unread(request):
story_id = request.POST['story_id']
feed_id = int(request.POST['feed_id'])
usersub = UserSubscription.objects.select_related('feed').get(user=request.user, feed=feed_id)
if not usersub.needs_unread_recalc:
usersub.needs_unread_recalc = True
usersub.save()
data = dict(code=0, payload=dict(story_id=story_id))
logging.user(request, "~FY~SBUnread~SN story in feed: %s" % (usersub.feed))
story = MStory.objects(story_feed_id=feed_id, story_guid=story_id)[0]
if story.story_date < usersub.mark_read_date:
# Story is outside the mark as read range, so invert all stories before.
newer_stories = MStory.objects(story_feed_id=story.story_feed_id,
story_date__gte=story.story_date,
story_date__lte=usersub.mark_read_date
).only('story_guid')
newer_stories = [s.story_guid for s in newer_stories]
usersub.mark_read_date = story.story_date - datetime.timedelta(minutes=1)
usersub.needs_unread_recalc = True
usersub.save()
# Mark stories as read only after the mark_read_date has been moved, otherwise
# these would be ignored.
data = usersub.mark_story_ids_as_read(newer_stories, request=request)
m = MUserStory.objects(story_id=story_id, user_id=request.user.pk, feed_id=feed_id)
m.delete()
return data
def calculate_metrics():
from apps.rss_feeds.models import MStory
from apps.reader.models import MUserStory
return {
'stories': MStory.objects().count(),
'read_stories': MUserStory.objects().count(),
}
def calculate_metrics(self):
from apps.rss_feeds.models import MStory
from apps.reader.models import MUserStory
return {
'stories': MStory.objects().count(),
'read_stories': MUserStory.objects().count(),
}
def mark_story_as_read(request):
story_ids = request.REQUEST.getlist('story_id')
feed_id = int(request.REQUEST['feed_id'])
try:
usersub = UserSubscription.objects.select_related('feed').get(
user=request.user, feed=feed_id)
except (UserSubscription.DoesNotExist, Feed.DoesNotExist):
duplicate_feed = DuplicateFeed.objects.filter(
duplicate_feed_id=feed_id)
if duplicate_feed:
try:
usersub = UserSubscription.objects.get(
user=request.user, feed=duplicate_feed[0].feed)
except (UserSubscription.DoesNotExist, Feed.DoesNotExist):
return dict(code=-1)
else:
return dict(code=-1)
if not usersub.needs_unread_recalc:
usersub.needs_unread_recalc = True
usersub.save()
data = dict(code=0, payload=story_ids)
if len(story_ids) > 1:
logging.user(
request.user,
"~FYRead %s stories in feed: %s" % (len(story_ids), usersub.feed))
else:
logging.user(request.user,
"~FYRead story in feed: %s" % (usersub.feed))
for story_id in story_ids:
try:
story = MStory.objects(story_feed_id=feed_id,
story_guid=story_id)[0]
except IndexError:
# Story has been deleted, probably by feed_fetcher.
continue
now = datetime.datetime.utcnow()
date = now if now > story.story_date else story.story_date # For handling future stories
m = MUserStory(story=story,
user_id=request.user.pk,
feed_id=feed_id,
read_date=date)
try:
m.save()
except OperationError:
logging.user(
request.user,
"~BRMarked story as read: Duplicate Story -> %s" % (story_id))
m = MUserStory.objects.get(story=story,
user_id=request.user.pk,
feed_id=feed_id)
m.read_date = date
m.save()
return data
def mark_feed_as_read(request):
feed_ids = [int(f) for f in request.REQUEST.getlist('feed_id') if f]
code = 0
for feed_id in feed_ids:
try:
feed = Feed.objects.get(id=feed_id)
except Feed.DoesNotExist:
continue
code = 0
us = UserSubscription.objects.get(feed=feed, user=request.user)
try:
us.mark_feed_read()
except IntegrityError:
code = -1
else:
code = 1
logging.user(request.user, "~FMMarking feed as read: ~SB%s" % (feed,))
MUserStory.objects(user_id=request.user.pk, feed_id=feed_id).delete()
return dict(code=code)
def mark_story_as_read(request):
story_ids = request.REQUEST.getlist('story_id')
feed_id = int(request.REQUEST['feed_id'])
try:
usersub = UserSubscription.objects.select_related('feed').get(user=request.user, feed=feed_id)
except (UserSubscription.DoesNotExist, Feed.DoesNotExist):
duplicate_feed = DuplicateFeed.objects.filter(duplicate_feed_id=feed_id)
if duplicate_feed:
try:
usersub = UserSubscription.objects.get(user=request.user,
feed=duplicate_feed[0].feed)
except (UserSubscription.DoesNotExist, Feed.DoesNotExist):
return dict(code=-1)
else:
return dict(code=-1)
if not usersub.needs_unread_recalc:
usersub.needs_unread_recalc = True
usersub.save()
data = dict(code=0, payload=story_ids)
if len(story_ids) > 1:
logging.user(request, "~FYRead %s stories in feed: %s" % (len(story_ids), usersub.feed))
else:
logging.user(request, "~FYRead story in feed: %s" % (usersub.feed))
for story_id in story_ids:
try:
story = MStory.objects.get(story_feed_id=feed_id, story_guid=story_id)
except MStory.DoesNotExist:
# Story has been deleted, probably by feed_fetcher.
continue
now = datetime.datetime.utcnow()
date = now if now > story.story_date else story.story_date # For handling future stories
m = MUserStory(story=story, user_id=request.user.pk, feed_id=feed_id, read_date=date, story_id=story_id)
try:
m.save()
except OperationError:
logging.user(request, "~BRMarked story as read: Duplicate Story -> %s" % (story_id))
logging.user(request, "~BRRead now date: %s, story_date: %s, story_id: %s." % (m.read_date, story.story_date, story.story_guid))
logging.user(request, "~BRSubscription mark_read_date: %s, oldest_unread_story_date: %s" % (
usersub.mark_read_date, usersub.oldest_unread_story_date))
m = MUserStory.objects.get(story=story, user_id=request.user.pk, feed_id=feed_id)
logging.user(request, "~BROriginal read date: %s, story id: %s, story.id: %s" % (m.read_date, m.story_id, m.story.id))
m.story_id = story_id
m.read_date = date
m.save()
return data
def load_river_stories(request):
user = get_user(request)
feed_ids = [int(feed_id) for feed_id in request.POST.getlist("feeds")]
offset = int(request.REQUEST.get("offset", 0))
limit = int(request.REQUEST.get("limit", 25))
page = int(request.REQUEST.get("page", 0)) + 1
read_stories = int(request.REQUEST.get("read_stories", 0))
# if page: offset = limit * page
if page:
limit = limit * page - read_stories
def feed_qvalues(feed_id):
feed = UserSubscription.objects.get(feed__pk=feed_id, user=user)
return Q(story_feed_id=feed_id) & Q(story_date__gte=feed.mark_read_date)
feed_last_reads = map(feed_qvalues, feed_ids)
qs = reduce(lambda q1, q2: q1 | q2, feed_last_reads)
read_stories = MUserStory.objects(user_id=user.pk, feed_id__in=feed_ids).only("story")
read_stories = [rs.story.id for rs in read_stories]
mstories = MStory.objects(Q(id__nin=read_stories) & qs)[offset : offset + limit]
stories = Feed.format_stories(mstories)
starred_stories = MStarredStory.objects(user_id=user.pk, story_feed_id__in=feed_ids).only(
"story_guid", "starred_date"
)
starred_stories = dict([(story.story_guid, story.starred_date) for story in starred_stories])
for story in stories:
story_date = localtime_for_timezone(story["story_date"], user.profile.timezone)
story["short_parsed_date"] = format_story_link_date__short(story_date)
story["long_parsed_date"] = format_story_link_date__long(story_date)
story["read_status"] = 0
if story["id"] in starred_stories:
story["starred"] = True
starred_date = localtime_for_timezone(starred_stories[story["id"]], user.profile.timezone)
story["starred_date"] = format_story_link_date__long(starred_date)
story["intelligence"] = {"feed": 0, "author": 0, "tags": 0, "title": 0}
logging.info(
" ---> [%s] ~FCLoading river stories: ~SB%s stories ~SN(%s feeds)" % (request.user, len(stories), len(feed_ids))
)
return dict(stories=stories)
# Switch to original feed for the user subscription
logging.info(" ===> %s " % user_sub.user)
user_sub.feed = original_feed
user_sub.needs_unread_recalc = True
try:
user_sub.save()
folders = json.decode(user_sub_folders.folders)
folders = rewrite_folders(folders, original_feed, duplicate_feed)
user_sub_folders.folders = json.encode(folders)
user_sub_folders.save()
except (IntegrityError, OperationError):
logging.info(" !!!!> %s already subscribed" % user_sub.user)
user_sub.delete()
# Switch read stories
user_stories = MUserStory.objects(feed_id=duplicate_feed.pk)
logging.info(" ---> %s read stories" % user_stories.count())
for user_story in user_stories:
user_story.feed_id = original_feed.pk
duplicate_story = user_story.story
story_guid = duplicate_story.story_guid if hasattr(duplicate_story, "story_guid") else duplicate_story.id
original_story = MStory.objects(story_feed_id=original_feed.pk, story_guid=story_guid)
if original_story:
user_story.story = original_story[0]
try:
user_story.save()
except OperationError:
# User read the story in the original feed, too. Ugh, just ignore it.
pass
else:
#!/usr/bin/env python
from utils.munin.base import MuninGraph
from apps.rss_feeds.models import MStory
from apps.reader.models import MUserStory
graph_config = {
'graph_category': 'NewsBlur',
'graph_title': 'NewsBlur Stories',
'graph_vlabel': 'Stories',
'stories.label': 'stories',
'tags.label': 'tags',
'authors.label': 'authors',
'read_stories.label': 'read_stories',
}
metrics = {
'stories': MStory.objects().count(),
'read_stories': MUserStory.objects().count(),
}
if __name__ == '__main__':
MuninGraph(graph_config, metrics).run()
if ((fetched_feed and ret_feed == FEED_OK) or self.options['force']):
pfeed = ProcessFeed(feed_id, fetched_feed, self.options)
ret_feed, ret_entries = pfeed.process()
feed = pfeed.feed
feed_process_duration = time.time() - start_duration
if ret_entries['new'] or self.options['force']:
start = time.time()
if not feed.known_good or not feed.fetched_once:
feed.known_good = True
feed.fetched_once = True
feed = feed.save()
if random.random() <= 0.02:
feed.sync_redis()
MUserStory.delete_old_stories(feed_id=feed.pk)
MUserStory.sync_all_redis(feed_id=feed.pk)
try:
self.count_unreads_for_subscribers(feed)
except TimeoutError:
logging.debug(' ---> [%-30s] Unread count took too long...' % (feed.title[:30],))
if self.options['verbose']:
logging.debug(u' ---> [%-30s] ~FBTIME: unread count in ~FM%.4ss' % (
feed.title[:30], time.time() - start))
<<<<<<< HEAD
cache.delete('feed_stories:%s-%s-%s' % (feed.id, 0, 25))
# if ret_entries['new'] or ret_entries['updated'] or self.options['force']:
=======
# if ret_entries.get(ENTRY_NEW) or ret_entries.get(ENTRY_UPDATED) or self.options['force']:
>>>>>>> Cleaning up RSS feed header for shared stories feeds.
# feed.get_stories(force=True)
def load_single_feed(request, feed_id):
start = time.time()
user = get_user(request)
offset = int(request.REQUEST.get('offset', 0))
limit = int(request.REQUEST.get('limit', 12))
page = int(request.REQUEST.get('page', 1))
dupe_feed_id = None
userstories_db = None
if page: offset = limit * (page-1)
if not feed_id: raise Http404
try:
feed = Feed.objects.get(id=feed_id)
except Feed.DoesNotExist:
feed_address = request.REQUEST.get('feed_address')
dupe_feed = DuplicateFeed.objects.filter(duplicate_address=feed_address)
if dupe_feed:
feed = dupe_feed[0].feed
dupe_feed_id = feed_id
else:
raise Http404
stories = feed.get_stories(offset, limit)
# Get intelligence classifier for user
classifier_feeds = list(MClassifierFeed.objects(user_id=user.pk, feed_id=feed_id))
classifier_authors = list(MClassifierAuthor.objects(user_id=user.pk, feed_id=feed_id))
classifier_titles = list(MClassifierTitle.objects(user_id=user.pk, feed_id=feed_id))
classifier_tags = list(MClassifierTag.objects(user_id=user.pk, feed_id=feed_id))
checkpoint1 = time.time()
usersub = UserSubscription.objects.get(user=user, feed=feed)
userstories = []
if usersub and stories:
story_ids = [story['id'] for story in stories]
userstories_db = MUserStory.objects(user_id=user.pk,
feed_id=feed.pk,
story_id__in=story_ids).only('story_id')
starred_stories = MStarredStory.objects(user_id=user.pk,
story_feed_id=feed_id,
story_guid__in=story_ids).only('story_guid', 'starred_date')
starred_stories = dict([(story.story_guid, story.starred_date) for story in starred_stories])
userstories = set(us.story_id for us in userstories_db)
checkpoint2 = time.time()
for story in stories:
story_date = localtime_for_timezone(story['story_date'], user.profile.timezone)
now = localtime_for_timezone(datetime.datetime.now(), user.profile.timezone)
story['short_parsed_date'] = format_story_link_date__short(story_date, now)
story['long_parsed_date'] = format_story_link_date__long(story_date, now)
if usersub:
if story['id'] in userstories:
story['read_status'] = 1
elif not story.get('read_status') and story['story_date'] < usersub.mark_read_date:
story['read_status'] = 1
elif not story.get('read_status') and story['story_date'] > usersub.last_read_date:
story['read_status'] = 0
if story['id'] in starred_stories:
story['starred'] = True
starred_date = localtime_for_timezone(starred_stories[story['id']], user.profile.timezone)
story['starred_date'] = format_story_link_date__long(starred_date, now)
else:
story['read_status'] = 1
story['intelligence'] = {
'feed': apply_classifier_feeds(classifier_feeds, feed),
'author': apply_classifier_authors(classifier_authors, story),
'tags': apply_classifier_tags(classifier_tags, story),
'title': apply_classifier_titles(classifier_titles, story),
}
checkpoint3 = time.time()
# Intelligence
feed_tags = json.decode(feed.data.popular_tags) if feed.data.popular_tags else []
feed_authors = json.decode(feed.data.popular_authors) if feed.data.popular_authors else []
classifiers = get_classifiers_for_user(user, feed_id, classifier_feeds,
classifier_authors, classifier_titles, classifier_tags)
if usersub:
usersub.feed_opens += 1
usersub.save()
diff1 = checkpoint1-start
diff2 = checkpoint2-start
diff3 = checkpoint3-start
timediff = time.time()-start
last_update = relative_timesince(feed.last_update)
logging.user(request, "~FYLoading feed: ~SB%s%s ~SN(%.4s seconds, ~SB%.4s/%.4s(%s)/%.4s~SN)" % (
feed.feed_title[:32], ('~SN/p%s' % page) if page > 1 else '', timediff,
diff1, diff2, userstories_db and userstories_db.count() or '~SN0~SB', diff3))
FeedLoadtime.objects.create(feed=feed, loadtime=timediff)
data = dict(stories=stories,
feed_tags=feed_tags,
feed_authors=feed_authors,
classifiers=classifiers,
last_update=last_update,
feed_id=feed.pk)
if dupe_feed_id: data['dupe_feed_id'] = dupe_feed_id
if not usersub:
data.update(feed.canonical())
return data
def load_river_stories(request):
limit = 18
offset = 0
start = datetime.datetime.utcnow()
user = get_user(request)
feed_ids = [int(feed_id) for feed_id in request.REQUEST.getlist('feeds') if feed_id]
original_feed_ids = list(feed_ids)
page = int(request.REQUEST.get('page', 1))
read_stories_count = int(request.REQUEST.get('read_stories_count', 0))
new_flag = request.REQUEST.get('new_flag', False)
bottom_delta = datetime.timedelta(days=settings.DAYS_OF_UNREAD)
if not feed_ids:
logging.user(request, "~FCLoading empty river stories: page %s" % (page))
return dict(stories=[])
# Fetch all stories at and before the page number.
# Not a single page, because reading stories can move them up in the unread order.
# `read_stories_count` is an optimization, works best when all 25 stories before have been read.
limit = limit * page - read_stories_count
# Read stories to exclude
read_stories = MUserStory.objects(user_id=user.pk, feed_id__in=feed_ids).only('story_id')
read_stories = [rs.story_id for rs in read_stories]
# Determine mark_as_read dates for all feeds to ignore all stories before this date.
# max_feed_count = 0
feed_counts = {}
feed_last_reads = {}
for feed_id in feed_ids:
try:
usersub = UserSubscription.objects.get(feed__pk=feed_id, user=user)
except UserSubscription.DoesNotExist:
continue
if not usersub: continue
feed_counts[feed_id] = (usersub.unread_count_negative * 1 +
usersub.unread_count_neutral * 10 +
usersub.unread_count_positive * 20)
# if feed_counts[feed_id] > max_feed_count:
# max_feed_count = feed_counts[feed_id]
feed_last_reads[feed_id] = int(time.mktime(usersub.mark_read_date.timetuple()))
feed_counts = sorted(feed_counts.items(), key=itemgetter(1))[:50]
feed_ids = [f[0] for f in feed_counts]
feed_last_reads = dict([(str(feed_id), feed_last_reads[feed_id]) for feed_id in feed_ids
if feed_id in feed_last_reads])
feed_counts = dict(feed_counts)
# After excluding read stories, all that's left are stories
# past the mark_read_date. Everything returned is guaranteed to be unread.
mstories = MStory.objects(
story_guid__nin=read_stories,
story_feed_id__in=feed_ids,
# story_date__gte=start - bottom_delta
).map_reduce("""function() {
var d = feed_last_reads[this[~story_feed_id]];
if (this[~story_date].getTime()/1000 > d) {
emit(this[~id], this);
}
}""",
"""function(key, values) {
return values[0];
}""",
output='inline',
scope={
'feed_last_reads': feed_last_reads
}
)
mstories = [story.value for story in mstories if story and story.value]
mstories = sorted(mstories, cmp=lambda x, y: cmp(story_score(y, bottom_delta), story_score(x, bottom_delta)))
# story_feed_counts = defaultdict(int)
# mstories_pruned = []
# for story in mstories:
# print story['story_title'], story_feed_counts[story['story_feed_id']]
# if story_feed_counts[story['story_feed_id']] >= 3: continue
# mstories_pruned.append(story)
# story_feed_counts[story['story_feed_id']] += 1
stories = []
for i, story in enumerate(mstories):
if i < offset: continue
if i >= offset + limit: break
stories.append(bunch(story))
stories = Feed.format_stories(stories)
found_feed_ids = list(set([story['story_feed_id'] for story in stories]))
# Find starred stories
starred_stories = MStarredStory.objects(
user_id=user.pk,
story_feed_id__in=found_feed_ids
).only('story_guid', 'starred_date')
starred_stories = dict([(story.story_guid, story.starred_date)
for story in starred_stories])
# Intelligence classifiers for all feeds involved
def sort_by_feed(classifiers):
feed_classifiers = defaultdict(list)
for classifier in classifiers:
feed_classifiers[classifier.feed_id].append(classifier)
return feed_classifiers
classifier_feeds = sort_by_feed(MClassifierFeed.objects(user_id=user.pk, feed_id__in=found_feed_ids))
classifier_authors = sort_by_feed(MClassifierAuthor.objects(user_id=user.pk, feed_id__in=found_feed_ids))
classifier_titles = sort_by_feed(MClassifierTitle.objects(user_id=user.pk, feed_id__in=found_feed_ids))
classifier_tags = sort_by_feed(MClassifierTag.objects(user_id=user.pk, feed_id__in=found_feed_ids))
classifiers = {}
for feed_id in found_feed_ids:
classifiers[feed_id] = get_classifiers_for_user(user, feed_id, classifier_feeds[feed_id],
classifier_authors[feed_id],
classifier_titles[feed_id],
classifier_tags[feed_id])
# Just need to format stories
for story in stories:
story_date = localtime_for_timezone(story['story_date'], user.profile.timezone)
now = localtime_for_timezone(datetime.datetime.now(), user.profile.timezone)
story['short_parsed_date'] = format_story_link_date__short(story_date, now)
story['long_parsed_date'] = format_story_link_date__long(story_date, now)
story['read_status'] = 0
if story['id'] in starred_stories:
story['starred'] = True
starred_date = localtime_for_timezone(starred_stories[story['id']], user.profile.timezone)
story['starred_date'] = format_story_link_date__long(starred_date, now)
story['intelligence'] = {
'feed': apply_classifier_feeds(classifier_feeds[story['story_feed_id']], story['story_feed_id']),
'author': apply_classifier_authors(classifier_authors[story['story_feed_id']], story),
'tags': apply_classifier_tags(classifier_tags[story['story_feed_id']], story),
'title': apply_classifier_titles(classifier_titles[story['story_feed_id']], story),
}
diff = datetime.datetime.utcnow() - start
timediff = float("%s.%.2s" % (diff.seconds, (diff.microseconds / 1000)))
logging.user(request, "~FCLoading river stories: page %s - ~SB%s/%s "
"stories ~SN(%s/%s/%s feeds) ~FB(%s seconds)" %
(page, len(stories), len(mstories), len(found_feed_ids),
len(feed_ids), len(original_feed_ids), timediff))
if new_flag:
return dict(stories=stories, classifiers=classifiers)
else:
logging.user(request, "~BR~FCNo new flag on river")
return dict(stories=stories)
def process_feed_wrapper(self, feed_queue):
delta = None
current_process = multiprocessing.current_process()
identity = "X"
feed = None
if current_process._identity:
identity = current_process._identity[0]
for feed_id in feed_queue:
start_duration = time.time()
feed_fetch_duration = None
feed_process_duration = None
page_duration = None
icon_duration = None
feed_code = None
ret_entries = None
start_time = time.time()
ret_feed = FEED_ERREXC
try:
feed = self.refresh_feed(feed_id)
skip = False
if self.options.get('fake'):
skip = True
weight = "-"
quick = "-"
rand = "-"
elif (self.options.get('quick') and not self.options['force'] and
feed.known_good and feed.fetched_once and not feed.is_push):
weight = feed.stories_last_month * feed.num_subscribers
random_weight = random.randint(1, max(weight, 1))
quick = float(self.options.get('quick', 0))
rand = random.random()
if random_weight < 100 and rand < quick:
skip = True
if skip:
logging.debug(' ---> [%-30s] ~BGFaking fetch, skipping (%s/month, %s subs, %s < %s)...' % (
feed.title[:30],
weight,
feed.num_subscribers,
rand, quick))
continue
ffeed = FetchFeed(feed_id, self.options)
ret_feed, fetched_feed = ffeed.fetch()
feed_fetch_duration = time.time() - start_duration
if ((fetched_feed and ret_feed == FEED_OK) or self.options['force']):
pfeed = ProcessFeed(feed_id, fetched_feed, self.options)
ret_feed, ret_entries = pfeed.process()
feed = pfeed.feed
feed_process_duration = time.time() - start_duration
if ret_entries['new'] or self.options['force']:
start = time.time()
if not feed.known_good or not feed.fetched_once:
feed.known_good = True
feed.fetched_once = True
feed = feed.save()
if random.random() <= 0.02:
feed.sync_redis()
MUserStory.delete_old_stories(feed_id=feed.pk)
MUserStory.sync_all_redis(feed_id=feed.pk)
try:
self.count_unreads_for_subscribers(feed)
except TimeoutError:
logging.debug(' ---> [%-30s] Unread count took too long...' % (feed.title[:30],))
if self.options['verbose']:
logging.debug(u' ---> [%-30s] ~FBTIME: unread count in ~FM%.4ss' % (
feed.title[:30], time.time() - start))
except KeyboardInterrupt:
break
except urllib2.HTTPError, e:
logging.debug(' ---> [%-30s] ~FRFeed throws HTTP error: ~SB%s' % (unicode(feed_id)[:30], e.fp.read()))
feed.save_feed_history(e.code, e.msg, e.fp.read())
fetched_feed = None
except Feed.DoesNotExist, e:
logging.debug(' ---> [%-30s] ~FRFeed is now gone...' % (unicode(feed_id)[:30]))
continue
def process_feed_wrapper(self, feed_queue):
delta = None
current_process = multiprocessing.current_process()
identity = "X"
feed = None
if current_process._identity:
identity = current_process._identity[0]
for feed_id in feed_queue:
start_duration = time.time()
feed_fetch_duration = None
feed_process_duration = None
page_duration = None
icon_duration = None
feed_code = None
ret_entries = None
start_time = time.time()
ret_feed = FEED_ERREXC
try:
feed = self.refresh_feed(feed_id)
skip = False
if self.options.get('fake'):
skip = True
weight = "-"
quick = "-"
rand = "-"
elif (self.options.get('quick') and not self.options['force']
and feed.known_good and feed.fetched_once
and not feed.is_push):
weight = feed.stories_last_month * feed.num_subscribers
random_weight = random.randint(1, max(weight, 1))
quick = float(self.options.get('quick', 0))
rand = random.random()
if random_weight < 100 and rand < quick:
skip = True
if skip:
logging.debug(
' ---> [%-30s] ~BGFaking fetch, skipping (%s/month, %s subs, %s < %s)...'
% (feed.title[:30], weight, feed.num_subscribers, rand,
quick))
continue
ffeed = FetchFeed(feed_id, self.options)
ret_feed, fetched_feed = ffeed.fetch()
feed_fetch_duration = time.time() - start_duration
if ((fetched_feed and ret_feed == FEED_OK)
or self.options['force']):
pfeed = ProcessFeed(feed_id, fetched_feed, self.options)
ret_feed, ret_entries = pfeed.process()
feed = pfeed.feed
feed_process_duration = time.time() - start_duration
if ret_entries['new'] or self.options['force']:
start = time.time()
if not feed.known_good or not feed.fetched_once:
feed.known_good = True
feed.fetched_once = True
feed = feed.save()
if random.random() <= 0.02:
feed.sync_redis()
MUserStory.delete_old_stories(feed_id=feed.pk)
MUserStory.sync_all_redis(feed_id=feed.pk)
try:
self.count_unreads_for_subscribers(feed)
except TimeoutError:
logging.debug(
' ---> [%-30s] Unread count took too long...'
% (feed.title[:30], ))
if self.options['verbose']:
logging.debug(
u' ---> [%-30s] ~FBTIME: unread count in ~FM%.4ss'
% (feed.title[:30], time.time() - start))
except KeyboardInterrupt:
break
except urllib2.HTTPError, e:
logging.debug(
' ---> [%-30s] ~FRFeed throws HTTP error: ~SB%s' %
(unicode(feed_id)[:30], e.fp.read()))
feed.save_feed_history(e.code, e.msg, e.fp.read())
fetched_feed = None
except Feed.DoesNotExist, e:
logging.debug(' ---> [%-30s] ~FRFeed is now gone...' %
(unicode(feed_id)[:30]))
continue
# Switch to original feed for the user subscription
logging.info(" ===> %s " % user_sub.user)
user_sub.feed = original_feed
user_sub.needs_unread_recalc = True
try:
user_sub.save()
folders = json.decode(user_sub_folders.folders)
folders = rewrite_folders(folders, original_feed, duplicate_feed)
user_sub_folders.folders = json.encode(folders)
user_sub_folders.save()
except (IntegrityError, OperationError):
logging.info(" !!!!> %s already subscribed" % user_sub.user)
user_sub.delete()
# Switch read stories
user_stories = MUserStory.objects(feed_id=duplicate_feed.pk)
logging.info(" ---> %s read stories" % user_stories.count())
for user_story in user_stories:
user_story.feed_id = original_feed.pk
duplicate_story = user_story.story
story_guid = duplicate_story.story_guid if hasattr(
duplicate_story, 'story_guid') else duplicate_story.id
original_story = MStory.objects(story_feed_id=original_feed.pk,
story_guid=story_guid)
if original_story:
user_story.story = original_story[0]
try:
user_story.save()
except OperationError:
# User read the story in the original feed, too. Ugh, just ignore it.
def load_single_feed(request):
user = get_user(request)
offset = int(request.REQUEST.get('offset', 0))
limit = int(request.REQUEST.get('limit', 30))
page = int(request.REQUEST.get('page', 0))
if page:
offset = limit * page
feed_id = int(request.REQUEST['feed_id'])
feed = Feed.objects.get(id=feed_id)
force_update = request.GET.get('force_update', False)
now = datetime.datetime.now()
stories = feed.get_stories(offset, limit)
if force_update:
feed.update(force_update)
# Get intelligence classifier for user
classifier_feeds = MClassifierFeed.objects(user_id=user.pk, feed_id=feed_id)
classifier_authors = MClassifierAuthor.objects(user_id=user.pk, feed_id=feed_id)
classifier_titles = MClassifierTitle.objects(user_id=user.pk, feed_id=feed_id)
classifier_tags = MClassifierTag.objects(user_id=user.pk, feed_id=feed_id)
try:
usersub = UserSubscription.objects.get(user=user, feed=feed)
except UserSubscription.DoesNotExist:
# FIXME: Why is this happening for `conesus` when logged into another account?!
logging.info(" ***> [%s] UserSub DNE, creating: %s" % (user, feed))
usersub = UserSubscription.objects.create(user=user, feed=feed)
userstories = MUserStory.objects(user_id=user.pk,
feed_id=feed.pk,
read_date__gte=usersub.mark_read_date)
userstories = [us.story.id for us in userstories]
for story in stories:
classifier_feeds.rewind()
classifier_authors.rewind()
classifier_tags.rewind()
classifier_titles.rewind()
if story.get('id') in userstories:
story['read_status'] = 1
elif not story.get('read_status') and story['story_date'] < usersub.mark_read_date:
story['read_status'] = 1
elif not story.get('read_status') and story['story_date'] > usersub.last_read_date:
story['read_status'] = 0
story['intelligence'] = {
'feed': apply_classifier_feeds(classifier_feeds, feed),
'author': apply_classifier_authors(classifier_authors, story),
'tags': apply_classifier_tags(classifier_tags, story),
'title': apply_classifier_titles(classifier_titles, story),
}
# Intelligence
feed_tags = json.decode(feed.popular_tags) if feed.popular_tags else []
feed_authors = json.decode(feed.popular_authors) if feed.popular_authors else []
classifiers = get_classifiers_for_user(user, feed_id, classifier_feeds,
classifier_authors, classifier_titles, classifier_tags)
usersub.feed_opens += 1
usersub.save()
diff = datetime.datetime.now()-now
logging.info(" ---> [%s] Loading feed: %s (%s.%s seconds)" % (request.user, feed,
diff.seconds,
diff.microseconds / 1000))
data = dict(stories=stories,
feed_tags=feed_tags,
feed_authors=feed_authors,
classifiers=classifiers)
return data
def load_river_stories(request):
limit = 18
offset = 0
start = datetime.datetime.utcnow()
user = get_user(request)
feed_ids = [int(feed_id) for feed_id in request.REQUEST.getlist('feeds') if feed_id]
original_feed_ids = list(feed_ids)
page = int(request.REQUEST.get('page', 0))+1
read_stories_count = int(request.REQUEST.get('read_stories_count', 0))
bottom_delta = datetime.timedelta(days=settings.DAYS_OF_UNREAD)
if not feed_ids:
logging.user(request.user, "~FCLoading empty river stories: page %s" % (page))
return dict(stories=[])
# Fetch all stories at and before the page number.
# Not a single page, because reading stories can move them up in the unread order.
# `read_stories_count` is an optimization, works best when all 25 stories before have been read.
limit = limit * page - read_stories_count
# Read stories to exclude
read_stories = MUserStory.objects(user_id=user.pk, feed_id__in=feed_ids).only('story')
read_stories = [rs.story.id for rs in read_stories]
# Determine mark_as_read dates for all feeds to ignore all stories before this date.
# max_feed_count = 0
feed_counts = {}
feed_last_reads = {}
for feed_id in feed_ids:
try:
usersub = UserSubscription.objects.get(feed__pk=feed_id, user=user)
except UserSubscription.DoesNotExist:
continue
if not usersub: continue
feed_counts[feed_id] = (usersub.unread_count_negative * 1 +
usersub.unread_count_neutral * 10 +
usersub.unread_count_positive * 20)
# if feed_counts[feed_id] > max_feed_count:
# max_feed_count = feed_counts[feed_id]
feed_last_reads[feed_id] = int(time.mktime(usersub.mark_read_date.timetuple()))
feed_counts = sorted(feed_counts.items(), key=itemgetter(1))[:50]
feed_ids = [f[0] for f in feed_counts]
feed_last_reads = dict([(str(feed_id), feed_last_reads[feed_id]) for feed_id in feed_ids])
feed_counts = dict(feed_counts)
# After excluding read stories, all that's left are stories
# past the mark_read_date. Everything returned is guaranteed to be unread.
mstories = MStory.objects(
id__nin=read_stories,
story_feed_id__in=feed_ids,
story_date__gte=start - bottom_delta
).map_reduce("""function() {
var d = feed_last_reads[this[~story_feed_id]];
if (this[~story_date].getTime()/1000 > d) {
emit(this[~id], this);
}
}""",
"""function(key, values) {
return values[0];
}""",
output='inline',
scope={
'feed_last_reads': feed_last_reads
}
)
mstories = [story.value for story in mstories]
mstories = sorted(mstories, cmp=lambda x, y: cmp(story_score(y, bottom_delta), story_score(x, bottom_delta)))
# story_feed_counts = defaultdict(int)
# mstories_pruned = []
# for story in mstories:
# print story['story_title'], story_feed_counts[story['story_feed_id']]
# if story_feed_counts[story['story_feed_id']] >= 3: continue
# mstories_pruned.append(story)
# story_feed_counts[story['story_feed_id']] += 1
stories = []
for i, story in enumerate(mstories):
if i < offset: continue
if i >= offset + limit: break
stories.append(bunch(story))
stories = Feed.format_stories(stories)
found_feed_ids = list(set([story['story_feed_id'] for story in stories]))
# Find starred stories
starred_stories = MStarredStory.objects(
user_id=user.pk,
story_feed_id__in=found_feed_ids
).only('story_guid', 'starred_date')
starred_stories = dict([(story.story_guid, story.starred_date)
for story in starred_stories])
# Intelligence classifiers for all feeds involved
def sort_by_feed(classifiers):
feed_classifiers = defaultdict(list)
for classifier in classifiers:
feed_classifiers[classifier.feed_id].append(classifier)
return feed_classifiers
classifier_feeds = sort_by_feed(MClassifierFeed.objects(user_id=user.pk, feed_id__in=found_feed_ids))
classifier_authors = sort_by_feed(MClassifierAuthor.objects(user_id=user.pk, feed_id__in=found_feed_ids))
classifier_titles = sort_by_feed(MClassifierTitle.objects(user_id=user.pk, feed_id__in=found_feed_ids))
classifier_tags = sort_by_feed(MClassifierTag.objects(user_id=user.pk, feed_id__in=found_feed_ids))
# Just need to format stories
for story in stories:
story_date = localtime_for_timezone(story['story_date'], user.profile.timezone)
now = localtime_for_timezone(datetime.datetime.now(), user.profile.timezone)
story['short_parsed_date'] = format_story_link_date__short(story_date, now)
story['long_parsed_date'] = format_story_link_date__long(story_date, now)
story['read_status'] = 0
if story['id'] in starred_stories:
story['starred'] = True
starred_date = localtime_for_timezone(starred_stories[story['id']], user.profile.timezone)
story['starred_date'] = format_story_link_date__long(starred_date, now)
story['intelligence'] = {
'feed': apply_classifier_feeds(classifier_feeds[story['story_feed_id']], story['story_feed_id']),
'author': apply_classifier_authors(classifier_authors[story['story_feed_id']], story),
'tags': apply_classifier_tags(classifier_tags[story['story_feed_id']], story),
'title': apply_classifier_titles(classifier_titles[story['story_feed_id']], story),
}
diff = datetime.datetime.utcnow() - start
timediff = float("%s.%.2s" % (diff.seconds, (diff.microseconds / 1000)))
logging.user(request.user, "~FCLoading river stories: page %s - ~SB%s/%s "
"stories ~SN(%s/%s/%s feeds) ~FB(%s seconds)" %
(page, len(stories), len(mstories), len(found_feed_ids),
len(feed_ids), len(original_feed_ids), timediff))
return dict(stories=stories)
def load_social_stories(request, user_id, username=None):
start = time.time()
user = get_user(request)
social_user_id = int(user_id)
social_user = get_object_or_404(User, pk=social_user_id)
offset = int(request.REQUEST.get('offset', 0))
limit = int(request.REQUEST.get('limit', 6))
page = request.REQUEST.get('page')
order = request.REQUEST.get('order', 'newest')
read_filter = request.REQUEST.get('read_filter', 'all')
stories = []
if page: offset = limit * (int(page) - 1)
now = localtime_for_timezone(datetime.datetime.now(), user.profile.timezone)
UNREAD_CUTOFF = datetime.datetime.utcnow() - datetime.timedelta(days=settings.DAYS_OF_UNREAD)
social_profile = MSocialProfile.get_user(social_user.pk)
try:
socialsub = MSocialSubscription.objects.get(user_id=user.pk, subscription_user_id=social_user_id)
except MSocialSubscription.DoesNotExist:
socialsub = None
mstories = MSharedStory.objects(user_id=social_user.pk).order_by('-shared_date')[offset:offset+limit]
stories = Feed.format_stories(mstories)
if socialsub and (read_filter == 'unread' or order == 'oldest'):
story_ids = socialsub.get_stories(order=order, read_filter=read_filter, offset=offset, limit=limit)
story_date_order = "%sshared_date" % ('' if order == 'oldest' else '-')
if story_ids:
mstories = MSharedStory.objects(user_id=social_user.pk,
story_db_id__in=story_ids).order_by(story_date_order)
stories = Feed.format_stories(mstories)
else:
mstories = MSharedStory.objects(user_id=social_user.pk).order_by('-shared_date')[offset:offset+limit]
stories = Feed.format_stories(mstories)
if not stories:
return dict(stories=[])
checkpoint1 = time.time()
stories, user_profiles = MSharedStory.stories_with_comments_and_profiles(stories, user.pk, check_all=True)
story_feed_ids = list(set(s['story_feed_id'] for s in stories))
usersubs = UserSubscription.objects.filter(user__pk=user.pk, feed__pk__in=story_feed_ids)
usersubs_map = dict((sub.feed_id, sub) for sub in usersubs)
unsub_feed_ids = list(set(story_feed_ids).difference(set(usersubs_map.keys())))
unsub_feeds = Feed.objects.filter(pk__in=unsub_feed_ids)
unsub_feeds = [feed.canonical(include_favicon=False) for feed in unsub_feeds]
date_delta = UNREAD_CUTOFF
if socialsub and date_delta < socialsub.mark_read_date:
date_delta = socialsub.mark_read_date
# Get intelligence classifier for user
classifier_feeds = list(MClassifierFeed.objects(user_id=user.pk, social_user_id=social_user_id))
classifier_authors = list(MClassifierAuthor.objects(user_id=user.pk, social_user_id=social_user_id))
classifier_titles = list(MClassifierTitle.objects(user_id=user.pk, social_user_id=social_user_id))
classifier_tags = list(MClassifierTag.objects(user_id=user.pk, social_user_id=social_user_id))
# Merge with feed specific classifiers
classifier_feeds = classifier_feeds + list(MClassifierFeed.objects(user_id=user.pk, feed_id__in=story_feed_ids))
classifier_authors = classifier_authors + list(MClassifierAuthor.objects(user_id=user.pk, feed_id__in=story_feed_ids))
classifier_titles = classifier_titles + list(MClassifierTitle.objects(user_id=user.pk, feed_id__in=story_feed_ids))
classifier_tags = classifier_tags + list(MClassifierTag.objects(user_id=user.pk, feed_id__in=story_feed_ids))
checkpoint2 = time.time()
story_ids = [story['id'] for story in stories]
userstories_db = MUserStory.objects(user_id=user.pk,
feed_id__in=story_feed_ids,
story_id__in=story_ids).only('story_id')
userstories = set(us.story_id for us in userstories_db)
starred_stories = MStarredStory.objects(user_id=user.pk,
story_feed_id__in=story_feed_ids,
story_guid__in=story_ids).only('story_guid', 'starred_date')
shared_stories = MSharedStory.objects(user_id=user.pk,
story_feed_id__in=story_feed_ids,
story_guid__in=story_ids)\
.only('story_guid', 'shared_date', 'comments')
starred_stories = dict([(story.story_guid, story.starred_date) for story in starred_stories])
shared_stories = dict([(story.story_guid, dict(shared_date=story.shared_date, comments=story.comments))
for story in shared_stories])
for story in stories:
story['social_user_id'] = social_user_id
story_feed_id = story['story_feed_id']
# story_date = localtime_for_timezone(story['story_date'], user.profile.timezone)
shared_date = localtime_for_timezone(story['shared_date'], user.profile.timezone)
story['short_parsed_date'] = format_story_link_date__short(shared_date, now)
story['long_parsed_date'] = format_story_link_date__long(shared_date, now)
if not socialsub:
story['read_status'] = 1
elif story['id'] in userstories:
story['read_status'] = 1
elif story['shared_date'] < date_delta:
story['read_status'] = 1
elif not usersubs_map.get(story_feed_id):
story['read_status'] = 0
elif not story.get('read_status') and story['story_date'] < usersubs_map[story_feed_id].mark_read_date:
story['read_status'] = 1
elif not story.get('read_status') and story['shared_date'] < date_delta:
story['read_status'] = 1
# elif not story.get('read_status') and socialsub and story['shared_date'] > socialsub.last_read_date:
# story['read_status'] = 0
else:
story['read_status'] = 0
if story['id'] in starred_stories:
story['starred'] = True
starred_date = localtime_for_timezone(starred_stories[story['id']], user.profile.timezone)
story['starred_date'] = format_story_link_date__long(starred_date, now)
if story['id'] in shared_stories:
story['shared'] = True
shared_date = localtime_for_timezone(shared_stories[story['id']]['shared_date'],
user.profile.timezone)
story['shared_date'] = format_story_link_date__long(shared_date, now)
story['shared_comments'] = strip_tags(shared_stories[story['id']]['comments'])
story['intelligence'] = {
'feed': apply_classifier_feeds(classifier_feeds, story['story_feed_id'],
social_user_id=social_user_id),
'author': apply_classifier_authors(classifier_authors, story),
'tags': apply_classifier_tags(classifier_tags, story),
'title': apply_classifier_titles(classifier_titles, story),
}
classifiers = sort_classifiers_by_feed(user=user, feed_ids=story_feed_ids,
classifier_feeds=classifier_feeds,
classifier_authors=classifier_authors,
classifier_titles=classifier_titles,
classifier_tags=classifier_tags)
if socialsub:
socialsub.feed_opens += 1
socialsub.save()
diff1 = checkpoint1-start
diff2 = checkpoint2-start
logging.user(request, "~FYLoading ~FMshared stories~FY: ~SB%s%s ~SN(~SB%.4ss/%.4ss~SN)" % (
social_profile.title[:22], ('~SN/p%s' % page) if page > 1 else '', diff1, diff2))
return {
"stories": stories,
"user_profiles": user_profiles,
"feeds": unsub_feeds,
"classifiers": classifiers,
}
def load_single_feed(request, feed_id):
start = time.time()
user = get_user(request)
offset = int(request.REQUEST.get('offset', 0))
limit = int(request.REQUEST.get('limit', 12))
page = int(request.REQUEST.get('page', 1))
dupe_feed_id = None
userstories_db = None
if page: offset = limit * (page-1)
if not feed_id: raise Http404
try:
feed = Feed.objects.get(id=feed_id)
except Feed.DoesNotExist:
feed_address = request.REQUEST.get('feed_address')
dupe_feed = DuplicateFeed.objects.filter(duplicate_address=feed_address)
if dupe_feed:
feed = dupe_feed[0].feed
dupe_feed_id = feed_id
else:
raise Http404
stories = feed.get_stories(offset, limit)
# Get intelligence classifier for user
classifier_feeds = list(MClassifierFeed.objects(user_id=user.pk, feed_id=feed_id))
classifier_authors = list(MClassifierAuthor.objects(user_id=user.pk, feed_id=feed_id))
classifier_titles = list(MClassifierTitle.objects(user_id=user.pk, feed_id=feed_id))
classifier_tags = list(MClassifierTag.objects(user_id=user.pk, feed_id=feed_id))
checkpoint1 = time.time()
usersub = UserSubscription.objects.get(user=user, feed=feed)
userstories = []
if usersub:
userstories_db = MUserStory.objects(user_id=user.pk,
feed_id=feed.pk,
read_date__gte=usersub.mark_read_date)
starred_stories = MStarredStory.objects(user_id=user.pk, story_feed_id=feed_id).only('story_guid', 'starred_date')
starred_stories = dict([(story.story_guid, story.starred_date) for story in starred_stories])
for us in userstories_db:
if hasattr(us.story, 'story_guid') and isinstance(us.story.story_guid, unicode):
userstories.append(us.story.story_guid)
elif hasattr(us.story, 'id') and isinstance(us.story.id, unicode):
userstories.append(us.story.id) # TODO: Remove me after migration from story.id->guid
checkpoint2 = time.time()
for story in stories:
story_date = localtime_for_timezone(story['story_date'], user.profile.timezone)
now = localtime_for_timezone(datetime.datetime.now(), user.profile.timezone)
story['short_parsed_date'] = format_story_link_date__short(story_date, now)
story['long_parsed_date'] = format_story_link_date__long(story_date, now)
if usersub:
if story['id'] in userstories:
story['read_status'] = 1
elif not story.get('read_status') and story['story_date'] < usersub.mark_read_date:
story['read_status'] = 1
elif not story.get('read_status') and story['story_date'] > usersub.last_read_date:
story['read_status'] = 0
if story['id'] in starred_stories:
story['starred'] = True
starred_date = localtime_for_timezone(starred_stories[story['id']], user.profile.timezone)
story['starred_date'] = format_story_link_date__long(starred_date, now)
else:
story['read_status'] = 1
story['intelligence'] = {
'feed': apply_classifier_feeds(classifier_feeds, feed),
'author': apply_classifier_authors(classifier_authors, story),
'tags': apply_classifier_tags(classifier_tags, story),
'title': apply_classifier_titles(classifier_titles, story),
}
checkpoint3 = time.time()
# Intelligence
feed_tags = json.decode(feed.data.popular_tags) if feed.data.popular_tags else []
feed_authors = json.decode(feed.data.popular_authors) if feed.data.popular_authors else []
classifiers = get_classifiers_for_user(user, feed_id, classifier_feeds,
classifier_authors, classifier_titles, classifier_tags)
if usersub:
usersub.feed_opens += 1
usersub.save()
timediff = time.time()-start
last_update = relative_timesince(feed.last_update)
logging.user(request.user, "~FYLoading feed: ~SB%s%s ~SN(%.4s seconds)" % (
feed, ('~SN/p%s' % page) if page > 1 else '', timediff))
FeedLoadtime.objects.create(feed=feed, loadtime=timediff)
if timediff >= 1:
diff1 = checkpoint1-start
diff2 = checkpoint2-start
diff3 = checkpoint3-start
logging.user(request.user, "~FYSlow feed load: ~SB%.4s/%.4s(%s)/%.4s" % (
diff1, diff2, userstories_db and userstories_db.count(), diff3))
data = dict(stories=stories,
feed_tags=feed_tags,
feed_authors=feed_authors,
classifiers=classifiers,
last_update=last_update,
feed_id=feed.pk)
if dupe_feed_id: data['dupe_feed_id'] = dupe_feed_id
if not usersub:
data.update(feed.canonical())
return data
def load_single_feed(request):
user = get_user(request)
offset = int(request.REQUEST.get('offset', 0))
limit = int(request.REQUEST.get('limit', 30))
page = int(request.REQUEST.get('page', 0))
if page:
offset = limit * page
feed_id = int(request.REQUEST.get('feed_id', 0))
if feed_id == 0:
raise Http404
try:
feed = Feed.objects.get(id=feed_id)
except Feed.DoesNotExist:
feed_address = request.REQUEST.get('feed_address')
dupe_feed = DuplicateFeed.objects.filter(duplicate_address=feed_address)
if dupe_feed:
feed = dupe_feed[0].feed
else:
raise Http404
force_update = request.GET.get('force_update', False)
now = datetime.datetime.utcnow()
stories = feed.get_stories(offset, limit)
if force_update:
feed.update(force_update)
# Get intelligence classifier for user
classifier_feeds = MClassifierFeed.objects(user_id=user.pk, feed_id=feed_id)
classifier_authors = MClassifierAuthor.objects(user_id=user.pk, feed_id=feed_id)
classifier_titles = MClassifierTitle.objects(user_id=user.pk, feed_id=feed_id)
classifier_tags = MClassifierTag.objects(user_id=user.pk, feed_id=feed_id)
try:
usersub = UserSubscription.objects.get(user=user, feed=feed)
except UserSubscription.DoesNotExist:
# FIXME: Why is this happening for `conesus` when logged into another account?!
logging.info(" ***> [%s] UserSub DNE, creating: %s" % (user, feed))
usersub = UserSubscription.objects.create(user=user, feed=feed)
userstories = []
userstories_db = MUserStory.objects(user_id=user.pk,
feed_id=feed.pk,
read_date__gte=usersub.mark_read_date)
for us in userstories_db:
if hasattr(us.story, 'story_guid') and isinstance(us.story.story_guid, unicode):
userstories.append(us.story.story_guid)
elif hasattr(us.story, 'id') and isinstance(us.story.id, unicode):
userstories.append(us.story.id) # TODO: Remove me after migration from story.id->guid
for story in stories:
classifier_feeds.rewind()
classifier_authors.rewind()
classifier_tags.rewind()
classifier_titles.rewind()
if story['id'] in userstories:
story['read_status'] = 1
elif not story.get('read_status') and story['story_date'] < usersub.mark_read_date:
story['read_status'] = 1
elif not story.get('read_status') and story['story_date'] > usersub.last_read_date:
story['read_status'] = 0
story['intelligence'] = {
'feed': apply_classifier_feeds(classifier_feeds, feed),
'author': apply_classifier_authors(classifier_authors, story),
'tags': apply_classifier_tags(classifier_tags, story),
'title': apply_classifier_titles(classifier_titles, story),
}
# Intelligence
feed_tags = json.decode(feed.popular_tags) if feed.popular_tags else []
feed_authors = json.decode(feed.popular_authors) if feed.popular_authors else []
classifiers = get_classifiers_for_user(user, feed_id, classifier_feeds,
classifier_authors, classifier_titles, classifier_tags)
usersub.feed_opens += 1
usersub.save()
diff = datetime.datetime.utcnow()-now
timediff = float("%s.%s" % (diff.seconds, (diff.microseconds / 1000)))
logging.info(" ---> [%s] Loading feed: %s (%s seconds)" % (request.user, feed, timediff))
FeedLoadtime.objects.create(feed=feed, loadtime=timediff)
last_update = relative_timesince(feed.last_update)
data = dict(stories=stories,
feed_tags=feed_tags,
feed_authors=feed_authors,
classifiers=classifiers,
last_update=last_update,
feed_id=feed.pk)
return data
def process_feed_wrapper(self, feed_queue):
""" wrapper for ProcessFeed
"""
if not self.options['single_threaded']:
# Close the DB so the connection can be re-opened on a per-process basis
from django.db import connection
connection.close()
delta = None
MONGO_DB = settings.MONGO_DB
db = mongoengine.connection.connect(db=MONGO_DB['NAME'], host=MONGO_DB['HOST'], port=MONGO_DB['PORT'])
current_process = multiprocessing.current_process()
identity = "X"
if current_process._identity:
identity = current_process._identity[0]
for feed in feed_queue:
ret_entries = {
ENTRY_NEW: 0,
ENTRY_UPDATED: 0,
ENTRY_SAME: 0,
ENTRY_ERR: 0
}
start_time = datetime.datetime.now()
### Uncomment to test feed fetcher
# from random import randint
# if randint(0,10) < 10:
# continue
try:
ffeed = FetchFeed(feed, self.options)
ret_feed, fetched_feed = ffeed.fetch()
if ((fetched_feed and ret_feed == FEED_OK) or self.options['force']):
pfeed = ProcessFeed(feed, fetched_feed, db, self.options)
ret_feed, ret_entries = pfeed.process()
if ret_entries.get(ENTRY_NEW) or self.options['force'] or not feed.fetched_once:
if not feed.fetched_once:
feed.fetched_once = True
feed.save()
MUserStory.delete_old_stories(feed_id=feed.pk)
user_subs = UserSubscription.objects.filter(feed=feed)
logging.debug(u' ---> [%-30s] Computing scores for all feed subscribers: %s subscribers' % (unicode(feed)[:30], user_subs.count()))
stories_db = MStory.objects(story_feed_id=feed.pk,
story_date__gte=UNREAD_CUTOFF)
for sub in user_subs:
cache.delete('usersub:%s' % sub.user_id)
silent = False if self.options['verbose'] >= 2 else True
sub.calculate_feed_scores(silent=silent, stories_db=stories_db)
cache.delete('feed_stories:%s-%s-%s' % (feed.id, 0, 25))
# if ret_entries.get(ENTRY_NEW) or ret_entries.get(ENTRY_UPDATED) or self.options['force']:
# feed.get_stories(force=True)
except KeyboardInterrupt:
break
except urllib2.HTTPError, e:
feed.save_feed_history(e.code, e.msg, e.fp.read())
fetched_feed = None
except Exception, e:
logging.debug('[%d] ! -------------------------' % (feed.id,))
tb = traceback.format_exc()
logging.debug(tb)
logging.debug('[%d] ! -------------------------' % (feed.id,))
ret_feed = FEED_ERREXC
feed.save_feed_history(500, "Error", tb)
fetched_feed = None
def load_river_blurblog(request):
limit = 10
start = time.time()
user = get_user(request)
social_user_ids = [int(uid) for uid in request.REQUEST.getlist("social_user_ids") if uid]
original_user_ids = list(social_user_ids)
page = int(request.REQUEST.get("page", 1))
order = request.REQUEST.get("order", "newest")
read_filter = request.REQUEST.get("read_filter", "unread")
relative_user_id = request.REQUEST.get("relative_user_id", None)
now = localtime_for_timezone(datetime.datetime.now(), user.profile.timezone)
UNREAD_CUTOFF = datetime.datetime.utcnow() - datetime.timedelta(days=settings.DAYS_OF_UNREAD)
if not relative_user_id:
relative_user_id = get_user(request).pk
if not social_user_ids:
socialsubs = MSocialSubscription.objects.filter(user_id=user.pk)
social_user_ids = [s.subscription_user_id for s in socialsubs]
offset = (page - 1) * limit
limit = page * limit - 1
story_ids, story_dates = MSocialSubscription.feed_stories(
user.pk, social_user_ids, offset=offset, limit=limit, order=order, read_filter=read_filter
)
mstories = MStory.objects(id__in=story_ids)
story_id_to_dates = dict(zip(story_ids, story_dates))
def sort_stories_by_id(a, b):
return int(story_id_to_dates[str(b.id)]) - int(story_id_to_dates[str(a.id)])
sorted_mstories = sorted(mstories, cmp=sort_stories_by_id)
stories = Feed.format_stories(sorted_mstories)
for s, story in enumerate(stories):
story["story_date"] = datetime.datetime.fromtimestamp(story_dates[s])
stories, user_profiles = MSharedStory.stories_with_comments_and_profiles(stories, relative_user_id, check_all=True)
story_feed_ids = list(set(s["story_feed_id"] for s in stories))
usersubs = UserSubscription.objects.filter(user__pk=user.pk, feed__pk__in=story_feed_ids)
usersubs_map = dict((sub.feed_id, sub) for sub in usersubs)
unsub_feed_ids = list(set(story_feed_ids).difference(set(usersubs_map.keys())))
unsub_feeds = Feed.objects.filter(pk__in=unsub_feed_ids)
unsub_feeds = [feed.canonical(include_favicon=False) for feed in unsub_feeds]
# Find starred stories
if story_feed_ids:
story_ids = [story["id"] for story in stories]
starred_stories = MStarredStory.objects(user_id=user.pk, story_guid__in=story_ids).only(
"story_guid", "starred_date"
)
starred_stories = dict([(story.story_guid, story.starred_date) for story in starred_stories])
shared_stories = MSharedStory.objects(user_id=user.pk, story_guid__in=story_ids).only(
"story_guid", "shared_date", "comments"
)
shared_stories = dict(
[
(story.story_guid, dict(shared_date=story.shared_date, comments=story.comments))
for story in shared_stories
]
)
userstories_db = MUserStory.objects(user_id=user.pk, feed_id__in=story_feed_ids, story_id__in=story_ids).only(
"story_id"
)
userstories = set(us.story_id for us in userstories_db)
else:
starred_stories = {}
shared_stories = {}
userstories = []
# Intelligence classifiers for all feeds involved
if story_feed_ids:
classifier_feeds = list(MClassifierFeed.objects(user_id=user.pk, feed_id__in=story_feed_ids))
classifier_authors = list(MClassifierAuthor.objects(user_id=user.pk, feed_id__in=story_feed_ids))
classifier_titles = list(MClassifierTitle.objects(user_id=user.pk, feed_id__in=story_feed_ids))
classifier_tags = list(MClassifierTag.objects(user_id=user.pk, feed_id__in=story_feed_ids))
else:
classifier_feeds = []
classifier_authors = []
classifier_titles = []
classifier_tags = []
classifiers = sort_classifiers_by_feed(
user=user,
feed_ids=story_feed_ids,
classifier_feeds=classifier_feeds,
classifier_authors=classifier_authors,
classifier_titles=classifier_titles,
classifier_tags=classifier_tags,
)
# Just need to format stories
for story in stories:
if story["id"] in userstories:
story["read_status"] = 1
elif story["story_date"] < UNREAD_CUTOFF:
story["read_status"] = 1
else:
story["read_status"] = 0
story_date = localtime_for_timezone(story["story_date"], user.profile.timezone)
story["short_parsed_date"] = format_story_link_date__short(story_date, now)
story["long_parsed_date"] = format_story_link_date__long(story_date, now)
if story["id"] in starred_stories:
story["starred"] = True
starred_date = localtime_for_timezone(starred_stories[story["id"]], user.profile.timezone)
story["starred_date"] = format_story_link_date__long(starred_date, now)
story["intelligence"] = {
"feed": apply_classifier_feeds(classifier_feeds, story["story_feed_id"]),
"author": apply_classifier_authors(classifier_authors, story),
"tags": apply_classifier_tags(classifier_tags, story),
"title": apply_classifier_titles(classifier_titles, story),
}
if story["id"] in shared_stories:
story["shared"] = True
shared_date = localtime_for_timezone(shared_stories[story["id"]]["shared_date"], user.profile.timezone)
story["shared_date"] = format_story_link_date__long(shared_date, now)
story["shared_comments"] = strip_tags(shared_stories[story["id"]]["comments"])
diff = time.time() - start
timediff = round(float(diff), 2)
logging.user(
request,
"~FYLoading ~FCriver blurblogs stories~FY: ~SBp%s~SN (%s/%s "
"stories, ~SN%s/%s/%s feeds)"
% (page, len(stories), len(mstories), len(story_feed_ids), len(social_user_ids), len(original_user_ids)),
)
return {
"stories": stories,
"user_profiles": user_profiles,
"feeds": unsub_feeds,
"classifiers": classifiers,
"elapsed_time": timediff,
}
def load_river_stories(request):
limit = 18
offset = 0
start = time.time()
user = get_user(request)
feed_ids = [int(feed_id) for feed_id in request.REQUEST.getlist('feeds') if feed_id]
original_feed_ids = list(feed_ids)
page = int(request.REQUEST.get('page', 1))
read_stories_count = int(request.REQUEST.get('read_stories_count', 0))
bottom_delta = datetime.timedelta(days=settings.DAYS_OF_UNREAD)
if not feed_ids:
logging.user(request, "~FCLoading empty river stories: page %s" % (page))
return dict(stories=[])
# Fetch all stories at and before the page number.
# Not a single page, because reading stories can move them up in the unread order.
# `read_stories_count` is an optimization, works best when all 25 stories before have been read.
limit = limit * page - read_stories_count
# Read stories to exclude
read_stories = MUserStory.objects(user_id=user.pk, feed_id__in=feed_ids).only('story_id')
read_stories = [rs.story_id for rs in read_stories]
# Determine mark_as_read dates for all feeds to ignore all stories before this date.
# max_feed_count = 0
feed_counts = {}
feed_last_reads = {}
for feed_id in feed_ids:
try:
usersub = UserSubscription.objects.get(feed__pk=feed_id, user=user)
except UserSubscription.DoesNotExist:
continue
if not usersub: continue
feed_counts[feed_id] = (usersub.unread_count_negative * 1 +
usersub.unread_count_neutral * 10 +
usersub.unread_count_positive * 20)
# if feed_counts[feed_id] > max_feed_count:
# max_feed_count = feed_counts[feed_id]
feed_last_reads[feed_id] = int(time.mktime(usersub.mark_read_date.timetuple()))
feed_counts = sorted(feed_counts.items(), key=itemgetter(1))[:40]
feed_ids = [f[0] for f in feed_counts]
feed_last_reads = dict([(str(feed_id), feed_last_reads[feed_id]) for feed_id in feed_ids
if feed_id in feed_last_reads])
feed_counts = dict(feed_counts)
# After excluding read stories, all that's left are stories
# past the mark_read_date. Everything returned is guaranteed to be unread.
mstories = MStory.objects(
story_guid__nin=read_stories,
story_feed_id__in=feed_ids,
# story_date__gte=start - bottom_delta
).map_reduce("""function() {
var d = feed_last_reads[this[~story_feed_id]];
if (this[~story_date].getTime()/1000 > d) {
emit(this[~id], this);
}
}""",
"""function(key, values) {
return values[0];
}""",
output='inline',
scope={
'feed_last_reads': feed_last_reads
}
)
try:
mstories = [story.value for story in mstories if story and story.value]
except OperationFailure, e:
raise e
def load_single_feed(request, feed_id):
start = datetime.datetime.utcnow()
user = get_user(request)
offset = int(request.REQUEST.get('offset', 0))
limit = int(request.REQUEST.get('limit', 12))
page = int(request.REQUEST.get('page', 1))
if page:
offset = limit * (page-1)
dupe_feed_id = None
if not feed_id:
raise Http404
try:
feed = Feed.objects.get(id=feed_id)
except Feed.DoesNotExist:
feed_address = request.REQUEST.get('feed_address')
dupe_feed = DuplicateFeed.objects.filter(duplicate_address=feed_address)
if dupe_feed:
feed = dupe_feed[0].feed
dupe_feed_id = feed_id
else:
raise Http404
stories = feed.get_stories(offset, limit)
# Get intelligence classifier for user
classifier_feeds = MClassifierFeed.objects(user_id=user.pk, feed_id=feed_id)
classifier_authors = MClassifierAuthor.objects(user_id=user.pk, feed_id=feed_id)
classifier_titles = MClassifierTitle.objects(user_id=user.pk, feed_id=feed_id)
classifier_tags = MClassifierTag.objects(user_id=user.pk, feed_id=feed_id)
usersub = UserSubscription.objects.get(user=user, feed=feed)
userstories = []
if usersub:
userstories_db = MUserStory.objects(user_id=user.pk,
feed_id=feed.pk,
read_date__gte=usersub.mark_read_date)
starred_stories = MStarredStory.objects(user_id=user.pk, story_feed_id=feed_id).only('story_guid', 'starred_date')
starred_stories = dict([(story.story_guid, story.starred_date) for story in starred_stories])
for us in userstories_db:
if hasattr(us.story, 'story_guid') and isinstance(us.story.story_guid, unicode):
userstories.append(us.story.story_guid)
elif hasattr(us.story, 'id') and isinstance(us.story.id, unicode):
userstories.append(us.story.id) # TODO: Remove me after migration from story.id->guid
for story in stories:
[x.rewind() for x in [classifier_feeds, classifier_authors, classifier_tags, classifier_titles]]
story_date = localtime_for_timezone(story['story_date'], user.profile.timezone)
now = localtime_for_timezone(datetime.datetime.now(), user.profile.timezone)
story['short_parsed_date'] = format_story_link_date__short(story_date, now)
story['long_parsed_date'] = format_story_link_date__long(story_date, now)
if usersub:
if story['id'] in userstories:
story['read_status'] = 1
elif not story.get('read_status') and story['story_date'] < usersub.mark_read_date:
story['read_status'] = 1
elif not story.get('read_status') and story['story_date'] > usersub.last_read_date:
story['read_status'] = 0
if story['id'] in starred_stories:
story['starred'] = True
starred_date = localtime_for_timezone(starred_stories[story['id']], user.profile.timezone)
story['starred_date'] = format_story_link_date__long(starred_date, now)
else:
story['read_status'] = 1
story['intelligence'] = {
'feed': apply_classifier_feeds(classifier_feeds, feed),
'author': apply_classifier_authors(classifier_authors, story),
'tags': apply_classifier_tags(classifier_tags, story),
'title': apply_classifier_titles(classifier_titles, story),
}
# Intelligence
feed_tags = json.decode(feed.data.popular_tags) if feed.data.popular_tags else []
feed_authors = json.decode(feed.data.popular_authors) if feed.data.popular_authors else []
classifiers = get_classifiers_for_user(user, feed_id, classifier_feeds,
classifier_authors, classifier_titles, classifier_tags)
if usersub:
usersub.feed_opens += 1
usersub.save()
diff = datetime.datetime.utcnow()-start
timediff = float("%s.%.2s" % (diff.seconds, (diff.microseconds / 1000)))
last_update = relative_timesince(feed.last_update)
logging.user(request.user, "~FYLoading feed: ~SB%s%s ~SN(%s seconds)" % (
feed, ('~SN/p%s' % page) if page > 1 else '', timediff))
FeedLoadtime.objects.create(feed=feed, loadtime=timediff)
data = dict(stories=stories,
feed_tags=feed_tags,
feed_authors=feed_authors,
classifiers=classifiers,
last_update=last_update,
feed_id=feed.pk)
if dupe_feed_id: data['dupe_feed_id'] = dupe_feed_id
if not usersub:
data.update(feed.canonical())
return data
def load_river_stories(request):
limit = 18
offset = int(request.REQUEST.get('offset', 0))
start = time.time()
user = get_user(request)
feed_ids = [int(feed_id) for feed_id in request.REQUEST.getlist('feeds') if feed_id]
original_feed_ids = list(feed_ids)
page = int(request.REQUEST.get('page', 1))
read_stories_count = int(request.REQUEST.get('read_stories_count', 0))
days_to_keep_unreads = datetime.timedelta(days=settings.DAYS_OF_UNREAD)
if not feed_ids:
logging.user(request, "~FCLoading empty river stories: page %s" % (page))
return dict(stories=[])
# Fetch all stories at and before the page number.
# Not a single page, because reading stories can move them up in the unread order.
# `read_stories_count` is an optimization, works best when all 25 stories before have been read.
offset = (page-1) * limit - read_stories_count
limit = page * limit - read_stories_count
# Read stories to exclude
read_stories = MUserStory.objects(user_id=user.pk, feed_id__in=feed_ids).only('story_id')
read_stories = [rs.story_id for rs in read_stories]
# Determine mark_as_read dates for all feeds to ignore all stories before this date.
feed_counts = {}
feed_last_reads = {}
for feed_id in feed_ids:
try:
usersub = UserSubscription.objects.get(feed__pk=feed_id, user=user)
except UserSubscription.DoesNotExist:
continue
if not usersub: continue
feed_counts[feed_id] = (usersub.unread_count_negative * 1 +
usersub.unread_count_neutral * 10 +
usersub.unread_count_positive * 20)
feed_last_reads[feed_id] = int(time.mktime(usersub.mark_read_date.timetuple()))
feed_counts = sorted(feed_counts.items(), key=itemgetter(1))[:40]
feed_ids = [f[0] for f in feed_counts]
feed_last_reads = dict([(str(feed_id), feed_last_reads[feed_id]) for feed_id in feed_ids
if feed_id in feed_last_reads])
feed_counts = dict(feed_counts)
# After excluding read stories, all that's left are stories
# past the mark_read_date. Everything returned is guaranteed to be unread.
mstories = MStory.objects(
story_guid__nin=read_stories,
story_feed_id__in=feed_ids,
# story_date__gte=start - days_to_keep_unreads
).map_reduce("""function() {
var d = feed_last_reads[this[~story_feed_id]];
if (this[~story_date].getTime()/1000 > d) {
emit(this[~id], this);
}
}""",
"""function(key, values) {
return values[0];
}""",
output='inline',
scope={
'feed_last_reads': feed_last_reads
}
)
try:
mstories = [story.value for story in mstories if story and story.value]
except OperationFailure, e:
raise e
#!/usr/bin/env python
from utils.munin.base import MuninGraph
from apps.rss_feeds.models import MStory
from apps.reader.models import MUserStory
graph_config = {
'graph_category' : 'NewsBlur',
'graph_title' : 'NewsBlur Stories',
'graph_vlabel' : 'Stories',
'stories.label': 'stories',
'tags.label': 'tags',
'authors.label': 'authors',
'read_stories.label': 'read_stories',
}
metrics = {
'stories': MStory.objects().count(),
'read_stories': MUserStory.objects().count(),
}
if __name__ == '__main__':
MuninGraph(graph_config, metrics).run()
def load_single_feed(request):
user = get_user(request)
offset = int(request.REQUEST.get("offset", 0))
limit = int(request.REQUEST.get("limit", 30))
page = int(request.REQUEST.get("page", 0))
if page:
offset = limit * page
feed_id = int(request.REQUEST.get("feed_id", 0))
if feed_id == 0:
raise Http404
try:
feed = Feed.objects.get(id=feed_id)
except Feed.DoesNotExist:
feed_address = request.REQUEST.get("feed_address")
dupe_feed = DuplicateFeed.objects.filter(duplicate_address=feed_address)
if dupe_feed:
feed = dupe_feed[0].feed
else:
raise Http404
force_update = request.GET.get("force_update", False)
now = datetime.datetime.utcnow()
stories = feed.get_stories(offset, limit)
if force_update:
feed.update(force_update)
# Get intelligence classifier for user
classifier_feeds = MClassifierFeed.objects(user_id=user.pk, feed_id=feed_id)
classifier_authors = MClassifierAuthor.objects(user_id=user.pk, feed_id=feed_id)
classifier_titles = MClassifierTitle.objects(user_id=user.pk, feed_id=feed_id)
classifier_tags = MClassifierTag.objects(user_id=user.pk, feed_id=feed_id)
usersub = UserSubscription.objects.get(user=user, feed=feed)
userstories = []
userstories_db = MUserStory.objects(user_id=user.pk, feed_id=feed.pk, read_date__gte=usersub.mark_read_date)
starred_stories = MStarredStory.objects(user_id=user.pk, story_feed_id=feed_id).only("story_guid", "starred_date")
starred_stories = dict([(story.story_guid, story.starred_date) for story in starred_stories])
for us in userstories_db:
if hasattr(us.story, "story_guid") and isinstance(us.story.story_guid, unicode):
userstories.append(us.story.story_guid)
elif hasattr(us.story, "id") and isinstance(us.story.id, unicode):
userstories.append(us.story.id) # TODO: Remove me after migration from story.id->guid
for story in stories:
classifier_feeds.rewind()
classifier_authors.rewind()
classifier_tags.rewind()
classifier_titles.rewind()
story_date = localtime_for_timezone(story["story_date"], user.profile.timezone)
story["short_parsed_date"] = format_story_link_date__short(story_date)
story["long_parsed_date"] = format_story_link_date__long(story_date)
if story["id"] in userstories:
story["read_status"] = 1
elif not story.get("read_status") and story["story_date"] < usersub.mark_read_date:
story["read_status"] = 1
elif not story.get("read_status") and story["story_date"] > usersub.last_read_date:
story["read_status"] = 0
if story["id"] in starred_stories:
story["starred"] = True
starred_date = localtime_for_timezone(starred_stories[story["id"]], user.profile.timezone)
story["starred_date"] = format_story_link_date__long(starred_date)
story["intelligence"] = {
"feed": apply_classifier_feeds(classifier_feeds, feed),
"author": apply_classifier_authors(classifier_authors, story),
"tags": apply_classifier_tags(classifier_tags, story),
"title": apply_classifier_titles(classifier_titles, story),
}
# Intelligence
feed_tags = json.decode(feed.popular_tags) if feed.popular_tags else []
feed_authors = json.decode(feed.popular_authors) if feed.popular_authors else []
classifiers = get_classifiers_for_user(
user, feed_id, classifier_feeds, classifier_authors, classifier_titles, classifier_tags
)
usersub.feed_opens += 1
usersub.save()
diff = datetime.datetime.utcnow() - now
timediff = float("%s.%s" % (diff.seconds, (diff.microseconds / 1000)))
last_update = relative_timesince(feed.last_update)
logging.info(" ---> [%s] ~FYLoading feed: ~SB%s ~SN(%s seconds)" % (request.user, feed, timediff))
FeedLoadtime.objects.create(feed=feed, loadtime=timediff)
data = dict(
stories=stories,
feed_tags=feed_tags,
feed_authors=feed_authors,
classifiers=classifiers,
last_update=last_update,
feed_id=feed.pk,
)
return data
