feedtools 0.2.4 → 0.2.5

data/CHANGELOG

@@ -1,3 +1,8 @@
+== FeedTools 0.2.5
+ * fixed multiple rows being created in the cache after a 301 redirection
+ * fixed broken table creation for postgresql and sqlite
+ * testing against non-standard feeds
+ * removed the 'comment_link' method in favor of the 'comments' method
 == FeedTools 0.2.4
  * fixed bug in the sqlite table creation query
  * greatly improved image support

data/lib/feed_tools.rb

@@ -25,7 +25,7 @@ FEED_TOOLS_ENV = ENV['FEED_TOOLS_ENV'] ||
                  ENV['RAILS_ENV'] ||
                  'production' # :nodoc:
 
-FEED_TOOLS_VERSION = "0.2.4"
+FEED_TOOLS_VERSION = "0.2.5"
 
 $:.unshift(File.dirname(__FILE__))
 $:.unshift(File.dirname(__FILE__) + "/../../activerecord/lib")
@@ -182,7 +182,7 @@ module FeedTools
             'link'            VARCHAR(255) DEFAULT NULL,
             'xml_data'        TEXT DEFAULT NULL,
             'http_headers'    TEXT DEFAULT NULL,
-            'last_retrieved'  DATETIME DEFAULT NULL,
+            'last_retrieved'  DATETIME DEFAULT NULL
           );
         SQL_END
         feeds_psql = <<-SQL_END
@@ -193,7 +193,7 @@ module FeedTools
             link              varchar(255) default NULL,
             xml_data          text default NULL,
             http_headers      text default NULL,
-            last_retrieved    datetime default NULL,
+            last_retrieved    timestamp default NULL
           );
         SQL_END
         table_creation_sql = nil
@@ -489,7 +489,7 @@ module FeedTools
     if url.nil? || url == ""
       return nil
     end
-    normalized_url = url
+    normalized_url = url.strip
     
     # if a url begins with the '/' character, it only makes sense that they
     # meant to be using a file:// url.  Fix it for them.
@@ -900,6 +900,8 @@ module FeedTools
               # redirections, and see if we need to update the url.
               for redirected_response in response_chain
                 if redirected_response.last.code.to_i == 301
+                  # Reset the cache object or we may get duplicate entries
+                  self.cache_object = nil
                   self.url = redirected_response.last['location']
                 else
                   # Jump out as soon as we hit anything that isn't a
@@ -1483,42 +1485,43 @@ module FeedTools
     #
     # This method uses the url from the link field in order to avoid grabbing
     # the favicon for services like feedburner.
-    def icon_link
-      if @icon_link.nil?
-        @icon_link = XPath.first(channel_node,
-          "link[@rel='icon']/@href").to_s
-        if @icon_link == ""
-          @icon_link = XPath.first(channel_node,
-            "link[@rel='shortcut icon']/@href").to_s
+    def icon
+      if @icon.nil?
+        icon_node = XPath.first(channel_node, "link[@rel='icon']")
+        if icon_node.nil?
+          icon_node = XPath.first(channel_node, "link[@rel='shortcut icon']")
         end
-        if @icon_link == ""
-          @icon_link = XPath.first(channel_node,
-            "link[@type='image/x-icon']/@href").to_s
+        if icon_node.nil?
+          icon_node = XPath.first(channel_node, "link[@type='image/x-icon']")
         end
-        if @icon_link == ""
-          @icon_link = XPath.first(channel_node,
-            "icon/@href").to_s
+        if icon_node.nil?
+          icon_node = XPath.first(channel_node, "icon")
         end
-        if @icon_link == ""
-          @icon_link = XPath.first(channel_node,
-            "icon/text()").to_s
+        if icon_node.nil?
+          icon_node = XPath.first(channel_node, "logo[@style='icon']")
         end
-        if @icon_link == ""
-          @icon_link = XPath.first(channel_node,
-            "logo[@style='icon']/@href").to_s
+        if icon_node.nil?
+          icon_node = XPath.first(channel_node, "LOGO[@STYLE='ICON']")
         end
-        if @icon_link == ""
-          @icon_link = XPath.first(channel_node,
-            "LOGO[@STYLE='ICON']/@HREF").to_s
-        end
-        if @icon_link == "" && self.link != nil && self.link != ""
-          link_uri = URI.parse(FeedTools.normalize_url(self.link))
-          @icon_link =
-            link_uri.scheme + "://" + link_uri.host + "/favicon.ico"
+        unless icon_node.nil?
+          @icon = FeedTools.unescape_entities(
+            XPath.first(icon_node, "@href").to_s)
+          if @icon == ""
+            @icon = FeedTools.unescape_entities(
+              XPath.first(icon_node, "text()").to_s)
+            unless FeedTools.is_url? @icon
+              @icon = ""
+            end
+          end
+          if @icon == "" && self.link != nil && self.link != ""
+            link_uri = URI.parse(FeedTools.normalize_url(self.link))
+            @icon =
+              link_uri.scheme + "://" + link_uri.host + "/favicon.ico"
+          end
+          @icon = nil if @icon == ""
         end
-        icon_link = nil if icon_link == ""
       end
-      return @icon_link
+      return @icon
     end
 
     # Returns the feed author
@@ -1526,70 +1529,83 @@ module FeedTools
       if @author.nil?
         @author = FeedTools::Feed::Author.new
 
-        # Set the author name
-        @author.name = FeedTools.unescape_entities(
-          XPath.first(channel_node, "author/name/text()").to_s)
-
-        @author.raw = FeedTools.unescape_entities(
-          XPath.first(channel_node, "author/text()").to_s)
-        if @author.raw == ""
-          @author.raw = FeedTools.unescape_entities(
-            XPath.first(channel_node, "dc:creator/text()").to_s)
+        author_node = XPath.first(channel_node, "author")
+        if author_node.nil?
+          author_node = XPath.first(channel_node, "managingEditor")
         end
-        if @author.raw == ""
-          @author.raw = FeedTools.unescape_entities(
-            XPath.first(channel_node, "dc:author/text()").to_s)
+        if author_node.nil?
+          author_node = XPath.first(channel_node, "dc:author")
         end
-        if @author.raw == ""
-          @author.raw = FeedTools.unescape_entities(
-            XPath.first(channel_node, "managingEditor/text()").to_s)
+        if author_node.nil?
+          author_node = XPath.first(channel_node, "dc:creator")
         end
-        unless @author.raw == ""
-          raw_scan = @author.raw.scan(
-            /(.*)\((\b[A-Z0-9._%-\+]+@[A-Z0-9._%-]+\.[A-Z]{2,4}\b)\)/i)
-          if raw_scan.nil? || raw_scan.size == 0
+        if author_node.nil?
+          author_node = XPath.first(channel_node, "atom:author")
+        end
+        unless author_node.nil?
+          @author.raw = FeedTools.unescape_entities(
+            XPath.first(author_node, "text()").to_s)
+          @author.raw = nil if @author.raw == ""
+          unless @author.raw.nil?
             raw_scan = @author.raw.scan(
-              /(\b[A-Z0-9._%-\+]+@[A-Z0-9._%-]+\.[A-Z]{2,4}\b)\s*\((.*)\)/i)
-            author_raw_pair = raw_scan.first.reverse unless raw_scan.size == 0
-          else
-            author_raw_pair = raw_scan.first
-          end
-          if raw_scan.nil? || raw_scan.size == 0
-            email_scan = @author.raw.scan(
-              /\b[A-Z0-9._%-\+]+@[A-Z0-9._%-]+\.[A-Z]{2,4}\b/i)
-            if email_scan != nil && email_scan.size > 0
-              @author.email = email_scan.first.strip
+              /(.*)\((\b[A-Z0-9._%-\+]+@[A-Z0-9._%-]+\.[A-Z]{2,4}\b)\)/i)
+            if raw_scan.nil? || raw_scan.size == 0
+              raw_scan = @author.raw.scan(
+                /(\b[A-Z0-9._%-\+]+@[A-Z0-9._%-]+\.[A-Z]{2,4}\b)\s*\((.*)\)/i)
+              author_raw_pair = raw_scan.first.reverse unless raw_scan.size == 0
+            else
+              author_raw_pair = raw_scan.first
             end
-          end
-          unless author_raw_pair.nil? || author_raw_pair.size == 0
-            @author.name = author_raw_pair.first.strip
-            @author.email = author_raw_pair.last.strip
-          else
-            unless @author.raw.include?("@")
-              # We can be reasonably sure we are looking at something
-              # that the creator didn't intend to contain an email address if
-              # it got through the preceeding regexes and it doesn't
-              # contain the tell-tale '@' symbol.
-              @author.name = @author.raw
+            if raw_scan.nil? || raw_scan.size == 0
+              email_scan = @author.raw.scan(
+                /\b[A-Z0-9._%-\+]+@[A-Z0-9._%-]+\.[A-Z]{2,4}\b/i)
+              if email_scan != nil && email_scan.size > 0
+                @author.email = email_scan.first.strip
+              end
+            end
+            unless author_raw_pair.nil? || author_raw_pair.size == 0
+              @author.name = author_raw_pair.first.strip
+              @author.email = author_raw_pair.last.strip
+            else
+              unless @author.raw.include?("@")
+                # We can be reasonably sure we are looking at something
+                # that the creator didn't intend to contain an email address if
+                # it got through the preceeding regexes and it doesn't
+                # contain the tell-tale '@' symbol.
+                @author.name = @author.raw
+              end
             end
           end
+          @author.name = "" if @author.name.nil?
+          if @author.name == ""
+            @author.name = FeedTools.unescape_entities(
+              XPath.first(author_node, "name/text()").to_s)
+          end
+          if @author.name == ""
+            @author.name = FeedTools.unescape_entities(
+              XPath.first(author_node, "@name").to_s)
+          end
+          if @author.email == ""
+            @author.email = FeedTools.unescape_entities(
+              XPath.first(author_node, "email/text()").to_s)
+          end
+          if @author.email == ""
+            @author.email = FeedTools.unescape_entities(
+              XPath.first(author_node, "@email").to_s)
+          end
+          if @author.url == ""
+            @author.url = FeedTools.unescape_entities(
+              XPath.first(author_node, "url/text()").to_s)
+          end
+          if @author.url == ""
+            @author.url = FeedTools.unescape_entities(
+              XPath.first(author_node, "@url").to_s)
+          end
+          @author.name = nil if @author.name == ""
+          @author.raw = nil if @author.raw == ""
+          @author.email = nil if @author.email == ""
+          @author.url = nil if @author.url == ""
         end
-
-        @author.name = nil if @author.name == ""
-        @author.raw = nil if @author.raw == ""
-
-        # Set the author email
-        if @author.email == ""
-          @author.email = FeedTools.unescape_entities(
-            XPath.first(channel_node, "author/email/text()").to_s)
-        end
-        @author.email = nil if @author.email == ""
-
-        # Set the author url
-        @author.url = FeedTools.unescape_entities(
-          XPath.first(channel_node, "author/url/text()").to_s)
-        @author.url = nil if @author.url == ""
-        
         # Fallback on the itunes module if we didn't find an author name
         begin
           @author.name = self.itunes_author if @author.name.nil?
@@ -1822,6 +1838,9 @@ module FeedTools
         if @copyright == ""
           @copyright = XPath.first(channel_node, "dc:rights/text()").to_s
         end
+        if @copyright == ""
+          @copyright = XPath.first(channel_node, "copyrights/text()").to_s
+        end
         @copyright = FeedTools.sanitize_html(@copyright, :strip)
         @copyright = nil if @copyright == ""
       end
@@ -1841,60 +1860,93 @@ module FeedTools
         if update_frequency != ""
           update_period = XPath.first(channel_node, "syn:updatePeriod/text()").to_s
           if update_period == "daily"
-            @time_to_live = update_frequency.to_i * 24
+            @time_to_live = update_frequency.to_i.day
           elsif update_period == "weekly"
-            @time_to_live = update_frequency.to_i * 24 * 7
+            @time_to_live = update_frequency.to_i.week
           elsif update_period == "monthly"
-            @time_to_live = update_frequency.to_i * 24 * 30
+            @time_to_live = update_frequency.to_i.month
           elsif update_period == "yearly"
-            @time_to_live = update_frequency.to_i * 24 * 365
+            @time_to_live = update_frequency.to_i.year
           else
             # hourly
-            @time_to_live = update_frequency.to_i
+            @time_to_live = update_frequency.to_i.hour
           end
         end
       end
       if @time_to_live.nil?
-        # expressed in minutes
+        # usually expressed in minutes
         update_frequency = XPath.first(channel_node, "ttl/text()").to_s
         if update_frequency != ""
-          @time_to_live = (update_frequency.to_i / 60)
+          update_span = XPath.first(channel_node, "ttl/@span").to_s
+          if update_span == "seconds"
+            @time_to_live = update_frequency.to_i
+          elsif update_span == "minutes"
+            @time_to_live = update_frequency.to_i.minute
+          elsif update_span == "hours"
+            @time_to_live = update_frequency.to_i.hour
+          elsif update_span == "days"
+            @time_to_live = update_frequency.to_i.day
+          elsif update_span == "weeks"
+            @time_to_live = update_frequency.to_i.week
+          elsif update_span == "months"
+            @time_to_live = update_frequency.to_i.month
+          elsif update_span == "years"
+            @time_to_live = update_frequency.to_i.year
+          elsif update_frequency.to_i >= 3000
+            # Normally, this should default to minutes, but realistically,
+            # if they meant minutes, you're rarely going to see a value higher
+            # than 120.  If we see >= 3000, we're either dealing with a stupid
+            # pseudo-spec that decided to use seconds, or we're looking at
+            # someone who only has weekly updated content.  Worst case, we
+            # misreport the time, and we update too often.  Best case, we
+            # avoid accidentally updating the feed only once a year.  In the
+            # interests of being pragmatic, and since the problem we avoid
+            # is a far greater one than the one we cause, just run the check
+            # and hope no one actually gets hurt.
+            @time_to_live = update_frequency.to_i
+          else
+            @time_to_live = update_frequency.to_i.minute
+          end
         end
       end
       if @time_to_live.nil?
         @time_to_live = 0
-        update_frequency_days = XPath.first(channel_node, "schedule/intervaltime/@days").to_s
-        update_frequency_hours = XPath.first(channel_node, "schedule/intervaltime/@hour").to_s
-        update_frequency_minutes = XPath.first(channel_node, "schedule/intervaltime/@min").to_s
-        update_frequency_seconds = XPath.first(channel_node, "schedule/intervaltime/@sec").to_s
+        update_frequency_days =
+          XPath.first(channel_node, "schedule/intervaltime/@days").to_s
+        update_frequency_hours =
+          XPath.first(channel_node, "schedule/intervaltime/@hour").to_s
+        update_frequency_minutes =
+          XPath.first(channel_node, "schedule/intervaltime/@min").to_s
+        update_frequency_seconds =
+          XPath.first(channel_node, "schedule/intervaltime/@sec").to_s
         if update_frequency_days != ""
-          @time_to_live = @time_to_live + update_frequency_days.to_i * 24
+          @time_to_live = @time_to_live + update_frequency_days.to_i.day
         end
         if update_frequency_hours != ""
-          @time_to_live = @time_to_live + update_frequency_hours.to_i * 1
+          @time_to_live = @time_to_live + update_frequency_hours.to_i.hour
         end
         if update_frequency_minutes != ""
-          @time_to_live = @time_to_live + update_frequency_minutes.to_i / 60
+          @time_to_live = @time_to_live + update_frequency_minutes.to_i.minute
         end
         if update_frequency_seconds != ""
-          @time_to_live = @time_to_live + update_frequency_seconds.to_i / 3600
+          @time_to_live = @time_to_live + update_frequency_seconds.to_i
         end
         if @time_to_live == 0
-          @time_to_live = nil
+          @time_to_live = 1.hour
         end
       end
       if @time_to_live.nil? || @time_to_live == 0
         # Default to one hour
-        @time_to_live = 1
+        @time_to_live = 1.hour
       end
       @time_to_live = @time_to_live.round
-      return @time_to_live.hour
+      return @time_to_live
     end
 
     # Sets the feed time to live
     def time_to_live=(new_time_to_live)
-      @time_to_live = (new_time_to_live / 3600).round
-      @time_to_live = 1 if @time_to_live < 1
+      @time_to_live = new_time_to_live.round
+      @time_to_live = 1.hour if @time_to_live < 1.hour
     end
 
     # Returns the feed's cloud
@@ -2735,13 +2787,16 @@ module FeedTools
         if @link != ""
           @link = FeedTools.unescape_entities(@link)
         end
-        if @link != "" && (@link =~ /http:\/\//) != 0 && (@link =~ /https:\/\//) != 0
-          if (feed.base[-1..-1] == "/" && @link[0..0] == "/")
-            @link = @link[1..-1]
-          end
-          # prepend the base to the link since they seem to have used a relative path
-          @link = feed.base + @link
-        end
+# TODO: Actually implement proper relative url resolving instead of this crap
+# ===========================================================================
+# 
+#        if @link != "" && (@link =~ /http:\/\//) != 0 && (@link =~ /https:\/\//) != 0
+#          if (feed.base[-1..-1] == "/" && @link[0..0] == "/")
+#            @link = @link[1..-1]
+#          end
+#          # prepend the base to the link since they seem to have used a relative path
+#          @link = feed.base + @link
+#        end
         @link = FeedTools.normalize_url(@link)
       end
       return @link
@@ -2751,25 +2806,7 @@ module FeedTools
     def link=(new_link)
       @link = new_link
     end
-    
-    # Returns the feed item comment link
-    def comment_link
-      if @comment_link.nil?
-        # get the feed comment link from the xml document
-        @comment_link = XPath.first(root_node, "comments/text()").to_s
-        if @comment_link == ""
-          @comment_link = self.link
-        end
-        @comment_link = FeedTools.normalize_url(@comment_link)
-      end
-      return @comment_link
-    end
-
-    # Sets the feed item comment link
-    def comment_link=(new_comment_link)
-      @comment_link = new_comment_link
-    end
-    
+        
     # Returns a list of the feed item's categories
     def categories
       if @categories.nil?
@@ -3291,70 +3328,83 @@ module FeedTools
       if @author.nil?
         @author = FeedTools::Feed::Author.new
 
-        # Set the author name
-        @author.name = FeedTools.unescape_entities(
-          XPath.first(root_node, "author/name/text()").to_s)
-
-        @author.raw = FeedTools.unescape_entities(
-          XPath.first(root_node, "author/text()").to_s)
-        if @author.raw == ""
-          @author.raw = FeedTools.unescape_entities(
-            XPath.first(root_node, "dc:creator/text()").to_s)
+        author_node = XPath.first(root_node, "author")
+        if author_node.nil?
+          author_node = XPath.first(root_node, "managingEditor")
         end
-        if @author.raw == ""
-          @author.raw = FeedTools.unescape_entities(
-            XPath.first(root_node, "dc:author/text()").to_s)
+        if author_node.nil?
+          author_node = XPath.first(root_node, "dc:author")
         end
-        if @author.raw == ""
-          @author.raw = FeedTools.unescape_entities(
-            XPath.first(root_node, "managingEditor/text()").to_s)
+        if author_node.nil?
+          author_node = XPath.first(root_node, "dc:creator")
         end
-        unless @author.raw == ""
-          raw_scan = @author.raw.scan(
-            /(.*)\((\b[A-Z0-9._%-\+]+@[A-Z0-9._%-]+\.[A-Z]{2,4}\b)\)/i)
-          if raw_scan.nil? || raw_scan.size == 0
+        if author_node.nil?
+          author_node = XPath.first(root_node, "atom:author")
+        end
+        unless author_node.nil?
+          @author.raw = FeedTools.unescape_entities(
+            XPath.first(author_node, "text()").to_s)
+          @author.raw = nil if @author.raw == ""
+          unless @author.raw.nil?
             raw_scan = @author.raw.scan(
-              /(\b[A-Z0-9._%-\+]+@[A-Z0-9._%-]+\.[A-Z]{2,4}\b)\s*\((.*)\)/i)
-            author_raw_pair = raw_scan.first.reverse unless raw_scan.size == 0
-          else
-            author_raw_pair = raw_scan.first
-          end
-          if raw_scan.nil? || raw_scan.size == 0
-            email_scan = @author.raw.scan(
-              /\b[A-Z0-9._%-\+]+@[A-Z0-9._%-]+\.[A-Z]{2,4}\b/i)
-            if email_scan != nil && email_scan.size > 0
-              @author.email = email_scan.first.strip
+              /(.*)\((\b[A-Z0-9._%-\+]+@[A-Z0-9._%-]+\.[A-Z]{2,4}\b)\)/i)
+            if raw_scan.nil? || raw_scan.size == 0
+              raw_scan = @author.raw.scan(
+                /(\b[A-Z0-9._%-\+]+@[A-Z0-9._%-]+\.[A-Z]{2,4}\b)\s*\((.*)\)/i)
+              author_raw_pair = raw_scan.first.reverse unless raw_scan.size == 0
+            else
+              author_raw_pair = raw_scan.first
             end
-          end
-          unless author_raw_pair.nil? || author_raw_pair.size == 0
-            @author.name = author_raw_pair.first.strip
-            @author.email = author_raw_pair.last.strip
-          else
-            unless @author.raw.include?("@")
-              # We can be reasonably sure we are looking at something
-              # that the creator didn't intend to contain an email address if
-              # it got through the preceeding regexes and it doesn't
-              # contain the tell-tale '@' symbol.
-              @author.name = @author.raw
+            if raw_scan.nil? || raw_scan.size == 0
+              email_scan = @author.raw.scan(
+                /\b[A-Z0-9._%-\+]+@[A-Z0-9._%-]+\.[A-Z]{2,4}\b/i)
+              if email_scan != nil && email_scan.size > 0
+                @author.email = email_scan.first.strip
+              end
+            end
+            unless author_raw_pair.nil? || author_raw_pair.size == 0
+              @author.name = author_raw_pair.first.strip
+              @author.email = author_raw_pair.last.strip
+            else
+              unless @author.raw.include?("@")
+                # We can be reasonably sure we are looking at something
+                # that the creator didn't intend to contain an email address if
+                # it got through the preceeding regexes and it doesn't
+                # contain the tell-tale '@' symbol.
+                @author.name = @author.raw
+              end
             end
           end
+          @author.name = "" if @author.name.nil?
+          if @author.name == ""
+            @author.name = FeedTools.unescape_entities(
+              XPath.first(author_node, "name/text()").to_s)
+          end
+          if @author.name == ""
+            @author.name = FeedTools.unescape_entities(
+              XPath.first(author_node, "@name").to_s)
+          end
+          if @author.email == ""
+            @author.email = FeedTools.unescape_entities(
+              XPath.first(author_node, "email/text()").to_s)
+          end
+          if @author.email == ""
+            @author.email = FeedTools.unescape_entities(
+              XPath.first(author_node, "@email").to_s)
+          end
+          if @author.url == ""
+            @author.url = FeedTools.unescape_entities(
+              XPath.first(author_node, "url/text()").to_s)
+          end
+          if @author.url == ""
+            @author.url = FeedTools.unescape_entities(
+              XPath.first(author_node, "@url").to_s)
+          end
+          @author.name = nil if @author.name == ""
+          @author.raw = nil if @author.raw == ""
+          @author.email = nil if @author.email == ""
+          @author.url = nil if @author.url == ""
         end
-
-        @author.name = nil if @author.name == ""
-        @author.raw = nil if @author.raw == ""
-
-        # Set the author email
-        if @author.email == ""
-          @author.email = FeedTools.unescape_entities(
-            XPath.first(root_node, "author/email/text()").to_s)
-        end
-        @author.email = nil if @author.email == ""
-
-        # Set the author url
-        @author.url = FeedTools.unescape_entities(
-          XPath.first(root_node, "author/url/text()").to_s)
-        @author.url = nil if @author.url == ""
-
         # Fallback on the itunes module if we didn't find an author name
         begin
           @author.name = self.itunes_author if @author.name.nil?
@@ -3522,7 +3572,8 @@ module FeedTools
     # Returns the url for posting comments
     def comments
       if @comments.nil?
-        @comments = XPath.first(root_node, "comments/text()").to_s
+        @comments = FeedTools.normalize_url(
+          XPath.first(root_node, "comments/text()").to_s)
         @comments = nil if @comments == ""
       end
       return @comments
@@ -3791,4 +3842,4 @@ begin
     FeedTools.feed_cache.initialize_cache
   end
 rescue
-end
+end

data/rakefile

@@ -7,7 +7,7 @@ require 'rake/gempackagetask'
 require 'rake/contrib/rubyforgepublisher'
 
 PKG_NAME      = 'feedtools'
-PKG_VERSION   = '0.2.4'
+PKG_VERSION   = '0.2.5'
 PKG_FILE_NAME = "#{PKG_NAME}-#{PKG_VERSION}"
 
 RELEASE_NAME  = "REL #{PKG_VERSION}"

data/test/nonstandard_test.rb

@@ -0,0 +1,147 @@
+require 'test/unit'
+require 'feed_tools'
+
+class NonStandardTest < Test::Unit::TestCase
+  def setup
+    FeedTools.tidy_enabled = false
+  end
+  
+  def test_xss_strict
+    feed = FeedTools::Feed.new
+    feed.xml_data = <<-FEED
+      <?xml version="1.0" encoding="iso-8859-1"?>
+      <rss version="2.0/XSS-strict">
+        <channel>
+          <title>tima thinking outloud.</title>
+          <link>http://www.timaoutloud.org/</link>
+          <description>The personal weblog of Timothy Appnel</description>
+          <item>
+            <link>http://www.timaoutloud.org/archives/000415.html</link>
+            <title>OSCON Wrap-Up.</title>
+            <description>
+              It&apos;s been a week since OSCON ended and I&apos;m just
+              beginning to recover. This uber post records my notes and
+              personal views as a speaker and attendee.
+            </description>
+          </item>
+          <item>
+            <link>http://www.timaoutloud.org/archives/000414.html</link>
+            <title>Write For The People Who Support You.</title>
+            <description>
+              Hooray! Mena is back. Ben too. Anil is celebrating
+              6 years of blogging.
+            </description>
+          </item>
+          <item>
+            <link>http://www.timaoutloud.org/archives/000413.html</link>
+            <title>tima@OSCON</title>
+            <description>
+              Ben Hammersley and I will be presenting 45 syndication hacks
+              in 45 minutes. Will I be able to keep pace with the madness?
+            </description>
+          </item>
+        </channel>
+      </rss>
+    FEED
+    assert_equal("tima thinking outloud.", feed.title)
+    assert_equal("http://www.timaoutloud.org/", feed.link)
+    assert_equal("The personal weblog of Timothy Appnel", feed.description)
+
+    assert_equal("OSCON Wrap-Up.", feed.items[0].title)
+    assert_equal("http://www.timaoutloud.org/archives/000415.html",
+      feed.items[0].link)
+    assert_equal(false, feed.items[0].description == nil)
+
+    assert_equal("Write For The People Who Support You.", feed.items[1].title)
+    assert_equal("http://www.timaoutloud.org/archives/000414.html",
+      feed.items[1].link)
+    assert_equal(false, feed.items[1].description == nil)
+
+    assert_equal("tima@OSCON", feed.items[2].title)
+    assert_equal("http://www.timaoutloud.org/archives/000413.html",
+      feed.items[2].link)
+    assert_equal(false, feed.items[2].description == nil)
+  end
+  
+  def test_rss_30_lite
+    # Delusions of grandeur...
+    feed = FeedTools::Feed.new
+    feed.xml_data = <<-FEED
+      <?xml version="1.0" encoding="UTF-8"?>
+      <rss version="3.0" type="lite"
+           source="http://www.rss3.org/files/liteSample.rss">
+        <channel>
+          <title>RSS Version 3</title>
+          <link>http://www.rss3.org/</link>
+          <description>This is a sample RSS 3 Lite-type feed</description>
+
+          <lastBuildDate>Sun, 14 Aug 2005 09:53:59 +0000</lastBuildDate>
+          <generator name="RSS3Maker">http://no.address/</generator>
+          <language rel="both">en</language>
+          <icon>http://www.rss3.org/files/r1.ico</icon>
+          <copyright>Jonathan Avidan 2005 (c)</copyright>
+          <managingEditor name="Jonathan Avidan">
+            editor@rss3.org
+          </managingEditor>
+          <webMaster name="Jonathan Avidan">webmaster@rss3.org</webMaster>
+          <ttl span="days">7</ttl>
+          <docs>http://www.rss3.org/rss3lite.html</docs>
+          <item>
+            <title>RSS 3 Lite First Draft Now Available</title>
+            <link>
+              http://www.rss3.org/archive/rss3lite/first_draft.html
+            </link>
+            <description>
+              The RSS 3 Lite-type specification first publicly
+              available version
+            </description>
+            <pubDate>Sun, 18 Aug 2005 09:53:59 +0000</pubDate>
+            <author name="Jonathan Avidan">jonathan@rss3.org</author>
+            <guid type="code">6457894357689</guid>
+          </item>
+          <item isUpdated="true" updateNum="1">
+            <title>Welcome to the RSS 3 Official Blog!</title>
+            <link>http://www.rss3.org/official_blog/?p=2</link>
+            <description>The RSS 3 Official Blog welcome message</description>
+            <comments type="both">
+              http://www.rss3.org/official_blog/?p=2#comments
+            </comments>
+            <pubDate>Wed, 27 Jul 2005 14:34:51 +0000</pubDate>
+            <author name="Jonathan Avidan" type="writer">
+              jonathan@rss3.org
+            </author>
+            <guid type="link">http://www.rss3.org/official_blog/?p=2</guid>
+          </item>
+        </channel>
+      </rss>
+    FEED
+    assert_equal("RSS Version 3", feed.title)
+    assert_equal("http://www.rss3.org/", feed.link)
+    assert_equal("This is a sample RSS 3 Lite-type feed", feed.description)
+    assert_equal("http://no.address/", feed.generator)
+    assert_equal("en", feed.language)
+    assert_equal("http://www.rss3.org/files/r1.ico", feed.icon)
+    assert_equal("Jonathan Avidan 2005 (c)", feed.copyright)
+    assert_equal(7.day, feed.ttl)
+    assert_equal("http://www.rss3.org/rss3lite.html", feed.docs)
+    
+    assert_equal("RSS 3 Lite First Draft Now Available", feed.items[0].title)
+    assert_equal("http://www.rss3.org/archive/rss3lite/first_draft.html",
+      feed.items[0].link)
+    assert_equal(false, feed.items[0].description == nil)
+    assert_equal(Time.utc(2005, "Aug", 18, 9, 53, 59), feed.items[0].time)
+    assert_equal("Jonathan Avidan", feed.items[0].author.name)
+    assert_equal("jonathan@rss3.org", feed.items[0].author.email)
+    assert_equal("6457894357689", feed.items[0].guid)
+    
+    assert_equal("Welcome to the RSS 3 Official Blog!", feed.items[1].title)
+    assert_equal("http://www.rss3.org/official_blog/?p=2", feed.items[1].link)
+    assert_equal(false, feed.items[1].description == nil)
+    assert_equal("http://www.rss3.org/official_blog/?p=2#comments",
+      feed.items[1].comments)
+    assert_equal(Time.utc(2005, "Jul", 27, 14, 34, 51), feed.items[1].time)
+    assert_equal("Jonathan Avidan", feed.items[1].author.name)
+    assert_equal("jonathan@rss3.org", feed.items[1].author.email)
+    assert_equal("http://www.rss3.org/official_blog/?p=2", feed.items[1].guid)
+  end
+end

metadata

@@ -1,10 +1,10 @@
 --- !ruby/object:Gem::Specification 
-rubygems_version: 0.8.10
+rubygems_version: 0.8.11
 specification_version: 1
 name: feedtools
 version: !ruby/object:Gem::Version 
-  version: 0.2.4
-date: 2005-08-16
+  version: 0.2.5
+date: 2005-08-19 00:00:00 -04:00
 summary: "Parsing, generation, and caching system for xml news feeds."
 require_paths: 
   - lib
@@ -24,6 +24,8 @@ required_ruby_version: !ruby/object:Gem::Version::Requirement
         version: 0.0.0
   version: 
 platform: ruby
+signing_key: 
+cert_chain: 
 authors: 
   - Bob Aman
 files: 
@@ -73,6 +75,7 @@ files:
   - test/cache_test.rb
   - test/cdf_test.rb
   - test/helper_test.rb
+  - test/nonstandard_test.rb
   - test/rss_test.rb
 test_files: []
 rdoc_options: