lib/display.rb in fastreader-1.0.1 vs lib/display.rb in fastreader-1.0.2

@@ -130,44 +130,44 @@
   def tags_to_text(html)
     doc = Hpricot(html)
 
     doc.search('//comment()').remove
 
-    doc.search('div') do |p|
-      p.swap( "\n\n" + p.inner_text.gsub("\n", ' ').squeeze(' ').strip + "\n\n" )
+    doc.search('p, div') do |p|
+      p.swap( "\n\n" + p.inner_html.gsub("\n", ' ').squeeze(' ').strip + "\n\n" )
     end
 
-    doc.search('p') do |p|
-      p.swap( "\n\n" + p.inner_text.gsub("\n", ' ').squeeze(' ').strip + "\n\n" )
-    end
-
-    doc.search('//blockquote') do |x|
+    doc.search('blockquote, pre') do |x|
       # compress extra spaces
       text = x.inner_text.squeeze(' ').strip
       # collapse the spacing in the text
       text.gsub!(/\s{2,}/, ' ')
       text = wrap_text(text, @width - 4).gsub(/^/, '    ') # indent 4 spaces
       x.swap("\n\n" + text + "\n\n")
     end
 
-    doc.search('h1,h2,h3,h4') do |p|
+    doc.search('big, h1,h2,h3,h4') do |p|
       p.swap( "\n\n= #{p.inner_text}\n\n" )
     end
     doc.search('//img') do |img|
       img.swap( "(img)" )
     end
     
-    doc.search('object').remove
+    doc.search('svg, object').remove
     doc.search('table').remove
     doc.search('script').remove
 
     doc.search('//br') do |p|
       p.swap( "\n" )
     end
 
-    doc.search('i, b') do |p|
+    doc.search('i, b, strong, em') do |p|
       p.swap( "*#{p.inner_text}*" )
     end
+    doc.search('abbr') do |p|
+      p.swap( "+#{p.inner_text}+" )
+    end
+    #
     # anchor tags are processed after real links 
     doc.search('a') do |p|
       p.swap( "#{p.inner_text}" )
     end
     doc.search('dt') do |x|