X-Git-Url: https://git.netwichtig.de/gitweb/?a=blobdiff_plain;f=lib%2Frbot%2Fcore%2Futils%2Fextends.rb;h=7b733994b74d323b010db0bc2ee6d66dad1f598d;hb=a209adb0e00e2a335333c1cb696d5807a47072c6;hp=e0c781b194cba78910028f156c2ea735b80f1fe0;hpb=abdbe1adcd085a131c301bb5f40c053b96b47638;p=user%2Fhenk%2Fcode%2Fruby%2Frbot.git

diff --git a/lib/rbot/core/utils/extends.rb b/lib/rbot/core/utils/extends.rb
index e0c781b1..7b733994 100644
--- a/lib/rbot/core/utils/extends.rb
+++ b/lib/rbot/core/utils/extends.rb
@@ -137,6 +137,10 @@ class ::String
     txt.gsub!(/<sub>(.*?)<\/sub>/, '_{\1}')
     txt.gsub!(/(^|_)\{(.)\}/, '\1\2')
 
+    # List items are converted to *). We don't have special support for
+    # nested or ordered lists.
+    txt.gsub!(/<li>/, ' *) ')
+
     # All other tags are just removed
     txt.gsub!(/<[^>]+>/, '')
 
@@ -144,6 +148,14 @@ class ::String
     # such as &nbsp;
     txt = Utils.decode_html_entities(txt)
 
+    # Keep unbreakable spaces or conver them to plain spaces?
+    case val = opts[:nbsp]
+    when :space, ' '
+      txt.gsub!([160].pack('U'), ' ')
+    else
+      warning "unknown :nbsp option #{val} passed to ircify_html" if val
+    end
+
     # Remove double formatting options, since they only waste bytes
     txt.gsub!(/#{Bold}(\s*)#{Bold}/, '\1')
     txt.gsub!(/#{Underline}(\s*)#{Underline}/, '\1')
@@ -178,6 +190,23 @@ class ::String
   def riphtml
     self.gsub(/<[^>]+>/, '').gsub(/&amp;/,'&').gsub(/&quot;/,'"').gsub(/&lt;/,'<').gsub(/&gt;/,'>').gsub(/&ellip;/,'...').gsub(/&apos;/, "'").gsub("\n",'')
   end
+
+  # This method tries to find an HTML title in the string,
+  # and returns it if found
+  def get_html_title
+    if defined? ::Hpricot
+      Hpricot(self).at("title").inner_html
+    else
+      return unless Irc::Utils::TITLE_REGEX.match(self)
+      $1
+    end
+  end
+
+  # This method returns the IRC-formatted version of an
+  # HTML title found in the string
+  def ircify_html_title
+    self.get_html_title.ircify_html rescue nil
+  end
 end