rfeedreader 0.9.20 → 1.0.0

data/History.txt

@@ -1,3 +1,12 @@
+== 1.0.0 2007-11-08
+
+* Added feed.contains_entries?
+* Solved truncated UTF-8
+* Solved truncated html in title
+* Solved empty titles, CDATA issue
+* Solved multiple space inside description
+* Solved Hpricot issue with Nil and inner_text
+
 == 0.9.20 2007-10-29
 
 * Update license

data/lib/rfeedreader.rb

@@ -13,33 +13,32 @@ module Rfeedreader
   module_function
   
   class TextyHelper
-    def TextyHelper.clean(html, length = 45)
-      return html if html.empty?
-      if html.index("<")
-        html.gsub!(/(<[^>]*>)|\n|\t/s) {" "}
-
+    def TextyHelper.clean(text, length = 45)
+      return text if text.empty?
+      
+      if text.index("<")
+        # Strip html tags, tabs and new lines
+        text.gsub!(/(<[^>]*>)/s, " ")
         # strip any comments, and if they have a newline at the end (ie. line with
         # only a comment) strip that too
-        truncate(html.gsub(/<!--(.*?)-->[\n]?/m, ""), length)
-      else
-        truncate(html, length) # already plain text
-      end 
+        text.gsub!(/<!--(.*?)-->[\n]?/m, "")
+      end
+      text.gsub!(/\s{2,}|\n|\t/, ' ')
+      truncate(HTMLEntities.encode_entities(text, :named, :decimal), length) 
     end
 
-    def TextyHelper.truncate(text, length = 45, truncate_string = "...")
-      if text.nil? then
-         return
-      end
+    def TextyHelper.truncate(text="", length = 45, truncate_string = "...")
+      return if text.empty?
+      
       l = length - truncate_string.length
-      if text.length > length 
-        text = text[0...l]
-        # Avoid html entity truncation
-        if text =~ /(&#\d+[^;])$/
-          text.delete!($1)
-        end
-        text = text + truncate_string
-      end
-      text
+      truncated_text = text[0...l]
+      
+      # Avoid html entity truncation
+      truncated_text.gsub!(/(&\S+[^;])$/,  '')
+      
+      truncated_text << truncate_string if text.length > length
+      
+      return truncated_text
     end
 
     def TextyHelper.convertEncoding(text, encoding='utf-8')
@@ -154,6 +153,10 @@ module Rfeedreader
       end
     end
     
+    def contains_entries?
+      return @entries.size > 0
+    end
+    
     protected
     
     def read_charset(hpricot_doc)
@@ -164,20 +167,28 @@ module Rfeedreader
     end
     
     def read_title(hpricot_doc)
-      @title = (hpricot_doc/"//title:first").text
+      begin
+        @title = (hpricot_doc/"//title:first").text
+      rescue
+        @title = ""
+      end
     end
     
     def read_link(hpricot_doc)
-      @link = (hpricot_doc/"link").first.inner_text
-      
-      if @link.empty?
-        element = (hpricot_doc/"link[@rel=alternate]").first
-        @link = element[:href] unless element.nil?
-      end
-      
-      if @link.empty?
-        element = (hpricot_doc/"link").first
-        @link = element[:href] unless element.nil?
+      begin
+        @link = (hpricot_doc/"link").first.inner_text
+
+        if @link.empty?
+          element = (hpricot_doc/"link[@rel=alternate]").first
+          @link = element[:href] unless element.nil?
+        end
+
+        if @link.empty?
+          element = (hpricot_doc/"link").first
+          @link = element[:href] unless element.nil?
+        end
+      rescue
+        @link = ""
       end
     end
 
@@ -213,7 +224,13 @@ module Rfeedreader
     end
     
     def read_title
-      @title = TextyHelper.convertEncoding(TextyHelper.clean((@hpricot_item/:title).to_s), @charset)
+      preformatted_title = (@hpricot_item/:title).text
+      if preformatted_title.index("CDATA")
+        preformatted_title.gsub!(/<\/*title>/, '')
+        preformatted_title.gsub!(/<\!\[CDATA\[/, '')
+        preformatted_title.gsub!(/\]\]>/, '')
+      end
+      @title = TextyHelper.convertEncoding(TextyHelper.clean(preformatted_title), @charset)
     end
     
     def read_description
@@ -229,15 +246,13 @@ module Rfeedreader
       
       unless @description.empty?
         @description = TextyHelper.clean(@description, 200)
-        
-        @description = HTMLEntities.encode_entities(@description, :named, :decimal)
         @description = TextyHelper.convertEncoding(@description, @charset)
         
         @description.gsub!("&#10;", "")
         @description.gsub!("&#13;", "")
         @description.strip!
           
-        @description.gsub!(/((https?):\/\/([^\/]+)\/(.*))/, '[<a href=\'\1\'>link</a>]')
+        @description.gsub!(/((https?):\/\/([^\/]+)\/(\S*))/, '[<a href=\'\1\'>link</a>]')
         @description.strip!
       end
     end

data/lib/rfeedreader/version.rb

@@ -1,8 +1,8 @@
 module Rfeedreader #:nodoc:
   module VERSION #:nodoc:
-    MAJOR = 0
-    MINOR = 9
-    TINY  = 20
+    MAJOR = 1
+    MINOR = 0
+    TINY  = 0
 
     STRING = [MAJOR, MINOR, TINY].join('.')
   end

data/test/test_helper.rb

@@ -10,7 +10,28 @@ end
 def read_first(feed_url)
   puts "Read first from #{feed_url}"
   feed = Rfeedreader.read_first feed_url
-  assert_not_nil feed
-  assert_equal 1, feed.entries.size
-  feed.display_entries
+  unless feed.nil?
+    feed.display_entries
+  else
+    puts "+++WARNING+++ nil feed"
+  end
+end
+
+def read_opml(filename)
+  puts "Read OPML from #{filename}"
+  doc = Hpricot(open(filename))
+  feeds = (doc/"outline[@htmlurl]")
+  nb_feeds = feeds.size
+  current_feed = 1
+  feeds.each do |url|
+    if current_feed > 117
+      puts "Feed #{current_feed}/#{nb_feeds}"
+      unless url[:xmlurl].nil?
+        read_first(url[:xmlurl]) 
+      else
+        read_first(url[:htmlurl]) 
+      end
+    end
+    current_feed += 1
+  end
 end

data/test/test_rfeedreader.rb

@@ -32,13 +32,19 @@ class TestRfeedreader < Test::Unit::TestCase
   def test_read_teketen_problem
     # 
     feed = Rfeedreader.read("http://www.eitb24.com/rss/rss-eitb24-kultura-eu.xml")
-    puts feed
-    feed.display_entries
-
+    assert_not_nil feed
+    unless feed.nil?
+      puts feed
+      feed.display_entries
+    end
+    
     # 412 problem in rfeedfinder
     feed = Rfeedreader.read("http://www.arteleku.net/4.1/blog/laburrak/?feed=rss2")
-    puts feed
-    feed.display_entries
+    assert_not_nil feed
+    unless feed.nil?
+      puts feed
+      feed.display_entries
+    end
   end
 
   def test_read_from_feevy
@@ -177,4 +183,37 @@ class TestRfeedreader < Test::Unit::TestCase
   def test_inquirer
     read_first "http://theinquirer.es/feed/"
   end
+  
+  def test_imified
+    read_first "http://feeds.feedburner.com/imified"
+  end
+  
+  def test_pere_opml
+    read_opml File.dirname(__FILE__) + '/pere.opml'
+  end
+  
+  def test_encoding_with_amp
+    read_first " http://abladias.blogspot.com/feeds/posts/default"
+  end
+  
+  def test_lot_of_space
+    read_first "http://igandekoa.wordpress.com/feed/"
+  end
+  
+  def test_wrongly_formatted_link
+    read_first "http://snippets.dzone.com/rss/tag/R"
+  end
+  
+  def test_title_truncate
+    read_first "http://corankeando.zoomblog.com/rss.xml"
+  end
+  
+  def test_bad_title_encoding
+    read_first "http://www.esperanto.de/dej/aktualajhoj/rss.php?lingvo=eo"
+  end
+  
+  def test_unrecognized_feed
+    read_first "http://www.gobmenorca.com/noticies/RSS"
+    #read_first "http://www.liberafolio.org/search_rss?SearchableText=&Title=&Description=&portal_type:list=News+Item&portal_type:list=Link&portal_type:list=Document&Creator=&submit=Search&sort_on=created&sort_order=reverse&review_s"
+  end
 end

data/website/index.html

@@ -33,7 +33,7 @@
     <h1>rfeedreader</h1>
     <div id="version" class="clickable" onclick='document.location = "http://rubyforge.org/projects/rfeedreader"; return false'>
       <p>Get Version</p>
-      <a href="http://rubyforge.org/projects/rfeedreader" class="numbers">0.9.20</a>
+      <a href="http://rubyforge.org/projects/rfeedreader" class="numbers">1.0.0</a>
     </div>
     <h2>What</h2>
 
@@ -81,7 +81,7 @@ Rfeedfinder.read('http://blog.alexgirard.com/feed/', nb_posts=3)
 	<h2>License</h2>
 
 
-	<p>This code is free to use under the terms of the <span class="caps">MIT</span> license.</p>
+	<p>This code is free to use under the terms of the Creative Commons <span class="caps">GNU GPL</span>.</p>
 
 
 	<h2>Contact</h2>
@@ -89,7 +89,7 @@ Rfeedfinder.read('http://blog.alexgirard.com/feed/', nb_posts=3)
 
 	<p>Comments are welcome. Send an email to <a href="mailto:alx.girard@gmail.com">Alexandre Girard</a>.</p>
     <p class="coda">
-      <a href="mailto:drnicwilliams@gmail.com">Dr Nic</a>, 1st September 2007<br>
+      <a href="mailto:drnicwilliams@gmail.com">Dr Nic</a>, 29th October 2007<br>
       Theme extended from <a href="http://rb2js.rubyforge.org/">Paul Battley</a>
     </p>
 </div>

data/website/index.txt

@@ -36,7 +36,7 @@ The trunk repository is <code>svn://rubyforge.org/var/svn/rfeedreader/trunk</cod
 
 h2. License
 
-This code is free to use under the terms of the MIT license. 
+This code is free to use under the terms of the Creative Commons GNU GPL. 
 
 h2. Contact
 

metadata

@@ -3,8 +3,8 @@ rubygems_version: 0.9.4
 specification_version: 1
 name: rfeedreader
 version: !ruby/object:Gem::Version 
-  version: 0.9.20
-date: 2007-10-29 00:00:00 +01:00
+  version: 1.0.0
+date: 2007-11-09 00:00:00 +01:00
 summary: Feed parser to read feed and return first posts of this feed. Special parsing from sources like Flickr, Jumcut, Google video, ...
 require_paths: 
 - lib