Support filtering feeds by author names, to pull only parts of a shared blog

without requiring use of specific tags/categories.

In passing, fix a number of error messages to throw the proper type of
exception.

Selena Deckelmann, with some polishing from me.


git-svn-id: file:///Users/dpage/pgweb/svn-repo/trunk@2367 8f5c7a92-453e-0410-a47f-ad33c8a6b003

5 files changed, 79 insertions, 14 deletions

diff --git a/planet/aggregator.py b/planet/aggregator.py
index dba6d176..182d0233 100755
--- a/planet/aggregator.py
+++ b/planet/aggregator.py
@@ -17,11 +17,12 @@ class Aggregator:
 	def __init__(self, db):
 		self.db = db
 		self.stored = 0
+		self.authorfilter = None
 		socket.setdefaulttimeout(20)
 		
 	def Update(self):
 		feeds = self.db.cursor()
-		feeds.execute('SELECT id,feedurl,name,lastget FROM planet.feeds')
+		feeds.execute('SELECT id,feedurl,name,lastget,authorfilter FROM planet.feeds')
 		for feed in feeds.fetchall():
 			try:
 				self.ParseFeed(feed)
@@ -43,7 +44,12 @@ class Aggregator:
 			print "Feed %s status %s" % (feedinfo[1], feed.status)
 			return
 
+		self.authorfilter = feedinfo[4]
+
 		for entry in feed.entries:
+			if not self.matches_filter(entry):
+				continue
+				
 			# Grab the entry. At least atom feeds from wordpress store what we
 			# want in entry.content[0].value and *also* has a summary that's
 			# much shorter. Other blog software store what we want in the summary
@@ -66,6 +72,20 @@ class Aggregator:
 		self.db.cursor().execute("UPDATE planet.feeds SET lastget=COALESCE((SELECT max(dat) FROM planet.posts WHERE planet.posts.feed=planet.feeds.id),'2000-01-01') WHERE planet.feeds.id=%(feed)s", {'feed': feedinfo[0]})
 		#self.db.cursor().execute('UPDATE planet.feeds SET lastget=%(lg)s WHERE id=%(feed)s', {'lg':parsestart, 'feed': feedinfo[0]})
 
+	def matches_filter(self, entry):
+		# For now, we only match against self.authorfilter. In the future,
+		# there may be more filters.
+		if self.authorfilter:
+			# Match against an author filter
+			
+			if entry.has_key('author_detail'):
+				return entry.author_detail.name == self.authorfilter
+			else: 
+				return False
+
+		# No filters, always return true
+		return True
+
 	def StoreEntry(self, feedid, guid, date, link, guidisperma, title, txt):
 		c = self.db.cursor()
 		c.execute("SELECT id FROM planet.posts WHERE feed=%(feed)s AND guid=%(guid)s", {'feed':feedid, 'guid':guid})
diff --git a/planet/planetadmin/register/models.py b/planet/planetadmin/register/models.py
index 94488577..85e0be49 100644
--- a/planet/planetadmin/register/models.py
+++ b/planet/planetadmin/register/models.py
@@ -9,6 +9,7 @@ class Blog(models.Model):
 	lastget = models.DateTimeField(default='2000-01-01')
 	userid = models.CharField(max_length=255, blank=False)
 	approved = models.BooleanField()
+	authorfilter = models.CharField(max_length=255,default='')
 
 	def __str__(self):
 		return self.feedurl
@@ -59,7 +60,6 @@ class AuditEntry(models.Model):
 	def __str__(self):
 		return "%s (%s): %s" % (self.logtime, self.user, self.logtxt)
 
-
 	class Meta:
 		db_table = 'planetadmin\".\"auditlog'
 		ordering = ['logtime']
diff --git a/planet/planetadmin/register/templates/index.html b/planet/planetadmin/register/templates/index.html
index 0fee79e2..edeb2632 100644
--- a/planet/planetadmin/register/templates/index.html
+++ b/planet/planetadmin/register/templates/index.html
@@ -34,7 +34,18 @@ We have the following blog(s) registered:
 {%endif%}
  </td>
  <td>{{blog.approved|yesno:"Yes,No"}}</td>
- <td>Feed: <a href="{{blog.feedurl}}">{{blog.feedurl}}</a><br/>Blog: <a href="{{blog.blogurl}}">{{blog.blogurl}}</a></td>
+ <td>Feed: <a href="{{blog.feedurl}}">{{blog.feedurl}}</a><br/>Blog: <a href="{{blog.blogurl}}">{{blog.blogurl}}</a><br/>
+OPTIONAL Author Filter:
+{%if user.is_superuser %}
+ <form method="post" action="modifyauthorfilter/{{blog.id}}/">
+ <input type="text" name="authorfilter" value="{{blog.authorfilter}}">
+ <input type="submit" value="Save Author Filter">
+ </form>
+{%else%}
+{{blog.authorfilter}}
+{%endif%}
+ </td>
+
  <td>{% if blog.approved  or user.is_superuser%}
   <a href="blogposts/{{blog.id}}/">Posts</a><br/>
 {%else%}
@@ -63,6 +74,7 @@ attachment is correct.
 </p>
 <form method="post" action="new/">
 <input type="text" name="feedurl"><br/>
+Filter by author (OPTIONAL): <input type="text" name="authorfilter"><br/>
 <input type="submit" value="New blog">
 </form>
 {%endif%}
@@ -73,6 +85,7 @@ way to do it :-P</p>
 <form method="post" action="new/">
 Blog url: <input type="text" name="feedurl"><br/>
 Userid (blank for yourself): <input type="text" name="userid"><br/>
+Filter by author (OPTIONAL): <input type="text" name="authorfilter"><br/>
 <input type="submit" value="New blog">
 </form>
 {%endif%}
diff --git a/planet/planetadmin/register/urls.py b/planet/planetadmin/register/urls.py
index fc61d2d7..6e5f05a7 100644
--- a/planet/planetadmin/register/urls.py
+++ b/planet/planetadmin/register/urls.py
@@ -15,6 +15,7 @@ urlpatterns = patterns('',
     (r'^detach/(\d+)/$', 'planetadmin.register.views.detach'),
     (r'^delete/(\d+)/$', 'planetadmin.register.views.delete'),
     (r'^modify/(\d+)/$', 'planetadmin.register.views.modify'),
+    (r'^modifyauthorfilter/(\d+)/$', 'planetadmin.register.views.modifyauthorfilter'),
 
     (r'^blogposts/(\d+)/$', 'planetadmin.register.views.blogposts'),
     (r'^blogposts/(\d+)/hide/(\d+)/$', 'planetadmin.register.views.blogpost_hide'),
diff --git a/planet/planetadmin/register/views.py b/planet/planetadmin/register/views.py
index 7885bc7a..f8bc95fb 100644
--- a/planet/planetadmin/register/views.py
+++ b/planet/planetadmin/register/views.py
@@ -31,23 +31,31 @@ def new(request):
 	if not request.method== 'POST':
 		raise pExcept('must be POST')
 	feedurl = request.POST['feedurl']
+	try: 
+		user = request.POST['userid']
+	except: 
+		user = request.user.username
+	authorfilter  = request.POST['authorfilter']
 	if not len(feedurl) > 1:
 		raise pExcept('must include blog url!')
 
 	# See if we can find the blog already
 	try:
-		blog = Blog.objects.get(feedurl=feedurl)
+		blog = Blog.objects.get(userid=userid)
 	except:
 		blog = None
 
 	if blog:
 		if blog.userid:
-			return HttpResponse("Specified blog is already registered to account '%s'" % (blog.userid))
+			raise pExcept("User %s has already registered blog %s." % (blog.userid, blog.feedurl))
+		# Rest of this is not really useful, but will be modified so that a single user can have multiple blogs in the future
 		# Found a match, so we're going to register this blog
 		# For safety reasons, we're going to require approval before we do it as well :-P
 		if not settings.NOTIFYADDR:
 			raise pExcept('Notify address not specified, cannot complete')
 		blog.userid = request.user.username
+		blog.feedurl = feedurl
+		blog.authorfilter = authorfilter
 		blog.approved = False
 		AuditEntry(request.user.username, 'Requested blog attachment for %s' % blog.feedurl).save()
 		send_mail('New blog assignment', """
@@ -60,8 +68,9 @@ So, head off to the admin interface and approve or reject this!
 		blog.save()
 		return HttpResponse('The blog has been attached to your account. For security reasons, it has been disapproved until a moderator has approved this connection.')
 
+	# TODO: add support for 'feed://' urls
 	if not feedurl.startswith('http://'):
-		return HttpResponse('Only http served blogs are accepted!')
+		raise pExcept('Only http served blogs are accepted!')
 
 	# Attempting to register a new blog. First let's see that we can download it
 	socket.setdefaulttimeout(20)
@@ -71,22 +80,32 @@ So, head off to the admin interface and approve or reject this!
 		lnk = feed.feed.link
 		l = len(feed.entries)
 		if l < 1:
-			return HttpResponse('Blog feed contains no entries.')
+			raise pExcept('Blog feed contains no entries.')
 	except Exception, e:
-		return HttpResponse('Failed to download blog feed')
+		raise pExcept('Failed to download blog feed')
 	if not status == 200:
-		return HttpResponse('Attempt to download blog feed returned status %s.' % (status))
+		raise pExcept('Attempt to download blog feed returned status %s.' % (status))
 	
 	if not settings.NOTIFYADDR:
 		raise pExcept('Notify address not specified, cannot complete')
 
 	blog = Blog()
-	blog.name = request.user.first_name
-	if request.user.is_superuser:
-		blog.userid = request.POST['userid']
+	if issuperuser(request.user):
+		blog.userid = request.POST['userid'] or request.user.username
+		# Try to guess who's name should go on this blog, default to the current
+		# users name if we can't find it in the feed.
+		blog.name = request.user.first_name
+		try:
+			e = feed.entries[0]
+			blog.name = e.author_detail.name or request.user.first_name
+		except:
+			pass
 	else:
-		blog.userid= request.user.username
+		blog.userid = request.user.username
+		blog.name = request.user.first_name
+
 	blog.feedurl = feedurl
+	blog.authorfilter = authorfilter
 	blog.blogurl = lnk
 	blog.approved = False
 	send_mail('New blog assignment', """
@@ -107,7 +126,7 @@ def delete(request, id):
 	blog = get_object_or_404(Blog, id=id)
 	if not request.user.is_superuser:
 		if not blog.userid == request.user.username:
-			return HttpResponse("You can only delete your own feeds! Don't try to hack!")
+			raise pError("You can only delete your own feeds! Don't try to hack!")
 	send_mail('Blog deleted', """
 The user '%s' has deleted the blog at
 %s (name %s)
@@ -116,6 +135,18 @@ The user '%s' has deleted the blog at
 	AuditEntry(request.user.username, 'Deleted blog %s' % blog.feedurl).save()
 	return HttpResponseRedirect('../..')
 
+@login_required
+@transaction.commit_on_success
+def modifyauthorfilter(request, id):
+	blog = get_object_or_404(Blog, id=id)
+	if not request.user.is_superuser:
+		if not blog.userid == request.user.username:
+			raise Exception("You can only update your own author filter! Don't try to hack!")
+	blog.authorfilter = request.POST['authorfilter']
+	blog.save()
+	AuditEntry(request.user.username, 'Changed author filter of blog %s' % blog.feedurl).save()
+	return HttpResponseRedirect('../..')
+
 @user_passes_test(issuperuser)
 @transaction.commit_on_success
 def modify(request, id):