pluto 0.8.5 → 0.8.6

data/README.md

@@ -197,6 +197,15 @@ For more samples, see [`nytimes.yml`](https://github.com/feedreader/pluto.sample
 [`beer.yml`](https://github.com/feedreader/pluto.samples/blob/master/beer.yml),
 [`football.yml`](https://github.com/feedreader/pluto.samples/blob/master/football.yml).
 
+
+## Template Packs
+
+- Blank - default templates; [more »](https://github.com/feedreader/pluto.blank)
+- News - 'river of news' style templates; [more »](https://github.com/feedreader/pluto.news)
+- Top -  Popurl-style templates; [more »](https://github.com/feedreader/pluto.top)
+- Classic -  Planet Planet-Style templates; [more »](https://github.com/feedreader/pluto.classic)
+
+
 ## Install
 
 Just install the gem:
@@ -222,7 +231,7 @@ Planet Mars by Sam Ruby [(Site)](https://github.com/rubys/mars) -  first draft o
 
 ### Python
 
-Planet Planet by Scott James Remnant n Jeff Waugh [(Site)](http://www.planetplanet.org)  - uses Mark Pilgrim's universal feed parser (RDF, RSS and Atom) and Tomas Styblo's templating engine; last release version 2.0 in 2006
+Planet Planet by Scott James Remnant ann Jeff Waugh [(Site)](http://www.planetplanet.org)  - uses Mark Pilgrim's universal feed parser (RDF, RSS and Atom) and Tomas Styblo's templating engine; last release version 2.0 in 2006
 
 Planet Venus by Sam Ruby [(Site)](https://github.com/rubys/venus) - cleaned up Planet Planet code; last change in 2010
 

data/lib/pluto/fetcher.rb

@@ -13,14 +13,48 @@ class Fetcher
   def debug?()       @debug || false;  end
 
 
+  def fetch_feed( url )
+    response = @worker.get( url )
+
+    if debug?
+      puts "http status #{response.code} #{response.message}"
+      
+      puts "http header - etag: #{response.header['etag']} - #{response.header['etag'].class.name}"
+      puts "http header - last-modified: #{response.header['last-modified']} - #{response.header['last-modified'].class.name}"
+    end
+
+    xml = response.body
+
+    ###
+    # NB: Net::HTTP will NOT set encoding UTF-8 etc.
+    # will mostly be ASCII
+    # - try to change encoding to UTF-8 ourselves
+    logger.debug "xml.encoding.name (before): #{xml.encoding.name}"
+
+    #####
+    # NB: ASCII-8BIT == BINARY == Encoding Unknown; Raw Bytes Here
+
+    ## NB:
+    # for now "hardcoded" to utf8 - what else can we do?
+    # - note: force_encoding will NOT change the chars only change the assumed encoding w/o translation
+    xml = xml.force_encoding( Encoding::UTF_8 )
+    logger.debug "xml.encoding.name (after): #{xml.encoding.name}"      
+
+    xml
+  end
+
+
   def feed_by_rec( feed_rec )
+    # simple feed fetcher; use for debugging (only/mostly)
+    #  -- will NOT change db records in any way
+
     feed_url = feed_rec.feed_url
     feed_key = feed_rec.key
-    
+
     feed_xml = fetch_feed( feed_url )
 
     logger.debug "feed_xml:"
-    logger.debug feed_xml[ 0..300 ] # get first 300 chars
+    logger.debug feed_xml[ 0..500 ] # get first 500 chars
 
     #  if opts.verbose?  # also write a copy to disk
     if debug?
@@ -41,16 +75,43 @@ class Fetcher
   end
 
 
-  def fetch_feed( url )
-    ### fix: use worker.get( url )  # check http response code etc.
+  def feed_by_rec_if_modified( feed_rec )   # try smart http update; will update db records
+    feed_url = feed_rec.feed_url
+    feed_key = feed_rec.key
+
+    ### todo/fix:
+    ##  add if available http_etag  machinery for smarter updates
+    ##    and http_last_modified headers
+    ##    and brute force body_old == body_new   etc.
+
+    response = @worker.get( feed_url )
+
+    feed_fetched = Time.now
+
+    if response.code != '200'   # note Net::HTTP response.code is a string in ruby
+
+      puts "*** error: fetching feed '#{feed_key}' - HTTP status #{response.code} #{response.message}"
+      
+      feed_attribs = {
+        http_code:          response.code.to_i,
+        http_etag:          nil,
+        http_last_modified: nil,
+        body:               nil,
+        fetched:            feed_fetched 
+      }
+      feed_rec.update_attributes!( feed_attribs )
+      return nil  #  sorry; no feed for parsing available
+    end
+    
     
-    xml = @worker.read( url )
+    puts "OK - fetching feed '#{feed_key}' - HTTP status #{response.code} #{response.message}"
 
+    feed_xml = response.body
     ###
     # NB: Net::HTTP will NOT set encoding UTF-8 etc.
     # will mostly be ASCII
     # - try to change encoding to UTF-8 ourselves
-    logger.debug "xml.encoding.name (before): #{xml.encoding.name}"
+    logger.debug "feed_xml.encoding.name (before): #{feed_xml.encoding.name}"
 
     #####
     # NB: ASCII-8BIT == BINARY == Encoding Unknown; Raw Bytes Here
@@ -58,10 +119,35 @@ class Fetcher
     ## NB:
     # for now "hardcoded" to utf8 - what else can we do?
     # - note: force_encoding will NOT change the chars only change the assumed encoding w/o translation
-    xml = xml.force_encoding( Encoding::UTF_8 )
-    logger.debug "xml.encoding.name (after): #{xml.encoding.name}"      
+    feed_xml = feed_xml.force_encoding( Encoding::UTF_8 )
+    logger.debug "feed_xml.encoding.name (after): #{feed_xml.encoding.name}"
+      
+    feed_attribs = {
+      http_code:          response.code.to_i,
+      http_etag:          response.header[ 'etag' ],
+      http_last_modified: response.header[ 'last-modified' ],
+      body:               feed_xml,
+      fetched:            feed_fetched
+    }
+    
+    if debug?
+      puts "http header - etag: #{response.header['etag']} - #{response.header['etag'].class.name}"
+      puts "http header - last-modified: #{response.header['last-modified']} - #{response.header['last-modified'].class.name}"
+    end
 
-    xml
+    feed_rec.update_attributes!( feed_attribs )
+
+    logger.debug "feed_xml:"
+    logger.debug feed_xml[ 0..300 ] # get first 300 chars
+      
+    puts "Before parsing feed >#{feed_key}<..."
+
+    ### move to feedutils
+    ### logger.debug "using stdlib RSS::VERSION #{RSS::VERSION}"
+
+    ## fix/todo: check for feed.nil?   -> error parsing!!!
+    #    or throw exception
+    feed = FeedUtils::Parser.parse( feed_xml )
   end
   
 end # class Fetcher

data/lib/pluto/models/feed.rb

@@ -15,9 +15,9 @@ class Feed < ActiveRecord::Base
     # note: order by first non-null datetime field
     #   coalesce - supported by sqlite (yes), postgres (yes)
 
-    # note: if not published_at,touched_at or built_at use hardcoded 1911-01-01 for now
-    ## order( "coalesce(published_at,touched_at,built_at,'1911-01-01') desc" )
-    order( "coalesce(latest_published_at,'1911-01-01') desc" )
+    # note: if not published, touched or built use hardcoded 1971-01-01 for now
+    ## order( "coalesce(published,touched,built,'1971-01-01') desc" )
+    order( "coalesce(last_published,'1971-01-01') desc" )
   end
 
   ##################################
@@ -27,6 +27,12 @@ class Feed < ActiveRecord::Base
   def link()        url;      end  # alias for url
   def feed()        feed_url; end  # alias for feed_url
 
+  def last_published_at() last_published; end # legay attrib reader - depreciated - remove!!
+  def fetched_at()        fetched;        end # legay attrib reader - depreciated - remove!!
+  def published_at()      published;      end # legay attrib reader - depreciated - remove!!
+  def touched_at()        touched;        end # legay attrib reader - depreciated - remove!!
+  def built_at()          built;          end # legay attrib reader - depreciated - remove!!
+
 
   def url?()           read_attribute(:url).present?;       end
   def title?()         read_attribute(:title).present?;     end
@@ -39,20 +45,74 @@ class Feed < ActiveRecord::Base
   def feed_url() read_attribute_w_fallbacks( :feed_url, :auto_feed_url ); end
 
 
-  def published_at?()  read_attribute(:published_at).present?;  end
-  def touched_at?()    read_attribute(:touched_at).present?;    end
+  def published?()  read_attribute(:published).present?;  end
+  def touched?()    read_attribute(:touched).present?;    end
+
 
-  def published_at
+  def published
     ## todo/fix: use a new name - do NOT squeeze convenience lookup into existing
     #    db backed attribute
 
     read_attribute_w_fallbacks(
-       :published_at,  # try touched_at (aka updated (ATOM))
-       :touched_at,    # try build_at (aka lastBuildDate (RSS))
-       :built_at
+       :published,  
+       :touched,     # try touched (aka updated (ATOM))
+       :built        # try build (aka lastBuildDate (RSS))
     )
   end
 
+
+  def debug=(value)  @debug = value;   end
+  def debug?()       @debug || false;  end
+
+  def save_from_struct!( data )
+
+    update_from_struct!( data )
+    
+    data.items.each do |item|
+
+      item_rec = Item.find_by_guid( item.guid )
+      if item_rec.nil?
+        item_rec  = Item.new
+        puts "** NEW | #{item.title}"
+      else
+        ## todo: check if any attribs changed
+        puts "UPDATE | #{item.title}"
+      end
+      
+      item_rec.debug = debug? ? true : false  # pass along debug flag
+      item_rec.update_from_struct!( self, item )
+
+    end  # each item
+  end
+
+
+  def update_from_struct!( data )
+    feed_attribs = {
+        format:       data.format,
+        published:    data.published? ? data.published : nil,
+        touched:      data.updated?   ? data.updated   : nil,
+        built:        data.built?     ? data.built     : nil,
+        summary:      data.summary?   ? data.summary   : nil,
+        ### todo/fix: add/use
+        # auto_title:     ???,
+        # auto_url:       ???,
+        # auto_feed_url:  ???,
+        auto_title2:  data.title2?    ? data.title2    : nil,
+        generator:    data.generator
+      }
+
+    if debug?
+        ## puts "*** dump feed_attribs:"
+        ## pp feed_attribs
+        puts "*** dump feed_attribs w/ class types:"
+        feed_attribs.each do |key,value|
+          puts "  #{key}: >#{value}< : #{value.class.name}"
+        end
+    end
+
+    update_attributes!( feed_attribs )
+  end
+
 end  # class Feed
 
 

data/lib/pluto/models/item.rb

@@ -14,27 +14,63 @@ class Item < ActiveRecord::Base
   def description() summary;  end  # alias for summary  -- also add descr shortcut??
   def link()        url;      end  # alias for url
 
+  def fetched_at()        fetched;        end # legay attrib reader - depreciated - remove!!
+  def published_at()      published;      end # legay attrib reader - depreciated - remove!!
+  def touched_at()        touched;        end # legay attrib reader - depreciated - remove!!
+
 
   def self.latest
     # note: order by first non-null datetime field
     #   coalesce - supported by sqlite (yes), postgres (yes)
 
-    # note: if not published_at,touched_at or built_at use hardcoded 1911-01-01 for now
-    order( "coalesce(published_at,touched_at,'1911-01-01') desc" )
+    # note: if not published,touched or built_at use hardcoded 1971-01-01 for now
+    order( "coalesce(published,touched,'1971-01-01') desc" )
   end
 
-  def published_at?()  read_attribute(:published_at).present?;  end
+  def published?()  read_attribute(:published).present?;  end
 
-  def published_at
+  def published
     ## todo/fix: use a new name - do NOT squeeze convenience lookup into existing
     #    db backed attribute
 
     read_attribute_w_fallbacks(
-      :published_at,
-      :touched_at      # try touched_at (aka updated)
+      :published,
+      :touched       # try touched (aka updated RSS/ATOM)
     )
   end
 
+
+
+  def debug=(value)  @debug = value;   end
+  def debug?()       @debug || false;  end
+
+  def update_from_struct!( feed_rec, data )
+    ## check: new item/record?  not saved?  add guid
+    #   otherwise do not add guid  - why? why not?
+
+    item_attribs = {
+      guid:         data.guid,   # todo: only add for new records???
+      title:        data.title,
+      url:          data.url,
+      summary:      data.summary?   ? data.summary   : nil,
+      content:      data.content?   ? data.content   : nil,
+      published:    data.published? ? data.published : nil,
+      touched:      data.updated?   ? data.updated   : nil,
+      feed_id:      feed_rec.id,    # add feed_id fk_ref
+      fetched:      feed_rec.fetched
+    }
+
+    if debug?
+      puts "*** dump item_attribs w/ class types:"
+      item_attribs.each do |key,value|
+        next if [:summary,:content].include?( key )   # skip summary n content
+        puts "  #{key}: >#{value}< : #{value.class.name}"
+      end
+    end
+
+    update_attributes!( item_attribs )
+  end
+
 end  # class Item
 
 

data/lib/pluto/models/site.rb

@@ -11,6 +11,7 @@ class Site < ActiveRecord::Base
   ##################################
   # attribute reader aliases
   def name()        title;    end  # alias for title
+  def fetched_at()  fetched;  end  # - legacy attrib reader -- remove!!!
 
 end
 

data/lib/pluto/models/utils.rb

@@ -8,16 +8,16 @@ class ItemCursor
   end
 
   def each
-    last_published_at = Time.local( 1911, 1, 1 )
+    last_published = Time.local( 1971, 1, 1 )
     last_feed_id      = -1     ## todo: use feed_key instead of id?? why? why not??
     
     @items.each do |item|
 
-      item_published_at = item.published_at  # cache published_at value ref
+      item_published = item.published  # cache published value ref
 
-      if last_published_at.year   == item_published_at.year  &&
-         last_published_at.month  == item_published_at.month &&
-         last_published_at.day    == item_published_at.day 
+      if last_published.year   == item_published.year  &&
+         last_published.month  == item_published.month &&
+         last_published.day    == item_published.day 
         new_date = false
       else
         new_date = true
@@ -31,8 +31,8 @@ class ItemCursor
 
       yield( item, new_date, new_feed )
       
-      last_published_at = item.published_at
-      last_feed_id      = item.feed.id
+      last_published = item.published
+      last_feed_id   = item.feed.id
     end
   end # method each
     

data/lib/pluto/refresher.rb

@@ -25,18 +25,23 @@ class Refresher
     Action.create!( title: 'update feeds' )
 
     #####
-    # -- update fetched_at  timestamps for all sites
-    feeds_fetched_at = Time.now
+    # -- update fetched  timestamps for all sites
+    feeds_fetched = Time.now
     Site.all.each do |site|
-      site.fetched_at = feeds_fetched_at
+      site.fetched = feeds_fetched
       site.save!
     end
 
     Feed.all.each do |feed_rec|
 
-      feed = @worker.feed_by_rec( feed_rec )
+      feed = @worker.feed_by_rec_if_modified( feed_rec )
+      
+      # on error or if http-not modified etc. skip update/processing
+      next  if feed.nil?
 
-      feed_fetched_at = Time.now
+      ## fix/todo: reload feed_red   - fetched date updated etc.
+      ##  check if needed for access to fetched date
+      
 
       ## todo/check: move feed_rec update to the end (after item updates??)
 
@@ -51,79 +56,21 @@ class Refresher
       #
       #  move to_datetime to feedutils!! if it works
       ##   todo: move this comments to feedutils??
-      
-      
-      feed_attribs = {
-        fetched_at:   feed_fetched_at,
-        format:       feed.format,
-        published_at: feed.published? ? feed.published : nil,
-        touched_at:   feed.updated?   ? feed.updated   : nil,
-        built_at:     feed.built?     ? feed.built     : nil,
-        summary:      feed.summary?   ? feed.summary   : nil,
-        ### todo/fix: add/use
-        # auto_title:     ???,
-        # auto_url:       ???,
-        # auto_feed_url:  ???,
-        auto_title2:  feed.title2?    ? feed.title2    : nil,
-        generator:    feed.generator
-      }
-
-      if debug?
-        ## puts "*** dump feed_attribs:"
-        ## pp feed_attribs
-        puts "*** dump feed_attribs w/ class types:"
-        feed_attribs.each do |key,value|
-          puts "  #{key}: >#{value}< : #{value.class.name}"
-        end
-      end
-
-      feed_rec.update_attributes!( feed_attribs )
 
 
-      feed.items.each do |item|
-
-        item_attribs = {
-          fetched_at:   feed_fetched_at,
-          title:        item.title,
-          url:          item.url,
-          summary:      item.summary?   ? item.summary   : nil,
-          content:      item.content?   ? item.content   : nil,
-          published_at: item.published? ? item.published : nil,
-          touched_at:   item.updated?   ? item.updated   : nil,
-          feed_id:      feed_rec.id    # add feed_id fk_ref
-        }
-
-        if debug?
-          puts "*** dump item_attribs w/ class types:"
-          item_attribs.each do |key,value|
-            next if [:summary,:content].include?( key )   # skip summary n content
-            puts "  #{key}: >#{value}< : #{value.class.name}"
-          end
-        end
-
-
-        rec = Item.find_by_guid( item.guid )
-        if rec.nil?
-          rec      = Item.new
-          item_attribs[ :guid ] = item.guid
-          puts "** NEW | #{item.title}"
-        else
-          ## todo: check if any attribs changed
-          puts "UPDATE | #{item.title}"
-        end
+      feed_rec.debug = debug? ? true : false    # pass along debug flag
+      ## fix/todo: pass debug flag as opts - debug: true|false !!!!!!
+      feed_rec.save_from_struct!( feed )  # todo: find a better name - why? why not??
 
-        rec.update_attributes!( item_attribs )
-      end  # each item
 
-      #  update  cached value latest published_at for item
-      item_recs = feed_rec.items.latest.limit(1).all
-      unless item_recs.empty?
-        if item_recs[0].published_at?
-          feed_rec.latest_published_at = item_recs[0].published_at
-        else # try touched_at
-          feed_rec.latest_published_at = item_recs[0].touched_at
+      #  update  cached value last published for item
+      last_item_rec = feed_rec.items.latest.limit(1).first  # note limit(1) will return relation/arrar - use first to get first element or nil from ary
+      if last_item_rec.present?
+        if last_item_rec.published?
+          feed_rec.update_attributes!( last_published: last_item_rec.published )
+        else # try touched
+          feed_rec.update_attributes!( last_published: last_item_rec.touched )
         end
-        feed_rec.save!
       end
 
     end # each feed

data/lib/pluto/schema.rb

@@ -7,7 +7,7 @@ class CreateDb < ActiveRecord::Migration
     create_table :sites do |t|
       t.string   :title,     :null => false    # e.g Planet Ruby, Planet JavaScript, etc.
       t.string   :key,       :null => false    # e.g. ruby, js, etc.
-      t.datetime :fetched_at   #  last fetched/checked date -- make not null ??
+      t.datetime :fetched   #  last fetched/checked date -- make not null ??
 
       t.timestamps  # created_at, updated_at
     end
@@ -35,17 +35,30 @@ class CreateDb < ActiveRecord::Migration
 
       t.string  :generator   # feed generator (e.g. wordpress, etc.)  from feed
       
-      t.datetime :published_at  # from feed published(atom)+ pubDate(rss)
-      t.datetime :built_at      # from feed lastBuiltDate(rss)
-      t.datetime :touched_at    # from feed updated(atom)
+      t.datetime :published  # from feed published(atom)+ pubDate(rss)
+      t.datetime :built      # from feed lastBuiltDate(rss)
+      t.datetime :touched    # from feed updated(atom)
+
+      ############
+      # filters
+      t.string   :includes  # regex
+      t.string   :excludes  # regex
+      # todo: add generic filter list e.g. t.string :filters  (comma,pipe or space separated method names?)
 
       # -- our own (meta) fields
-      t.datetime :latest_published_at # cache latest item published_at
+      t.datetime :last_published # cache last (latest) published for items
 
       t.string  :key,      :null => false
       t.string  :format      # e.g. atom (1.0), rss 2.0, rss 0.7 etc.
-      t.string  :etag      # last etag
-      t.datetime :fetched_at    # last fetched/checked date
+
+      t.integer  :http_code   # last http status code e.g. 200,404,etc.
+      t.string   :http_etag    # last http header etag
+      t.datetime :http_last_modified   # last http header last-modified
+
+      t.text    :body    # last http response body (complete feed!)
+
+      t.datetime :fetched    # last fetched/checked date
+
       t.timestamps   # created_at, updated_at
     end
 
@@ -56,15 +69,15 @@ class CreateDb < ActiveRecord::Migration
       t.text     :summary  # e.g. description (rss), summary (atom)
       t.text     :content
       
-      t.datetime :published_at   # from feed (published)  + pubDate(rss)
-      t.datetime :touched_at     # from feed updated (atom)
+      t.datetime :published   # from feed (published)  + pubDate(rss)
+      t.datetime :touched     # from feed updated (atom)
 
       ## todo: add :last_updated_at ??  (NOTE: updated_at already take by auto-timestamps)
       t.references :feed, :null => false
 
-      t.datetime :fetched_at   # last fetched/check date
+      t.datetime :fetched   # last fetched/check date
       t.timestamps   # created_at, updated_at
-      
+
       ## t.string   :author
       ## todo: add author/authors, category/categories
     end

data/lib/pluto/subscriber.rb

@@ -54,12 +54,16 @@ class Subscriber
       feed_key   = key.to_s.dup
       feed_hash  = value
 
-      # todo: use title from feed?
+      # todo/fix: use title from feed?
+      #  e.g. fill up auto_title, auto_url, etc.
+
       feed_attribs = {
         feed_url: feed_hash[ 'feed' ]  || feed_hash[ 'feed_url' ],
         url:      feed_hash[ 'link' ]  || feed_hash[ 'url' ],
         title:    feed_hash[ 'title' ] || feed_hash[ 'name' ],
-        title2:   feed_hash[ 'title2' ]
+        title2:   feed_hash[ 'title2' ],
+        includes: feed_hash[ 'includes' ] || feed_hash[ 'include' ],
+        excludes: feed_hash[ 'excludes' ] || feed_hash[ 'exclude' ]
       }
 
       puts "Updating feed subscription >#{feed_key}< - >#{feed_attribs[:feed_url]}<..."

data/lib/pluto/template_helpers.rb

@@ -5,16 +5,16 @@ module Pluto
 
 module TemplateHelper
 
-  def strip_tags( hy )
+  def strip_tags( ht )
     ### tobe done
     ## strip markup tags; return plain text
-    hy.gsub( /<[^>]+>/, '' )
+    ht.gsub( /<[^>]+>/, '' )
   end
 
 
-  def whitelist( hy, tags, opts={} )
+  def whitelist( ht, tags, opts={} )
 
-    # note: assumes properly escaped <> in hy/hypertext
+    # note: assumes properly escaped <> in ht/hypertext
 
     ###############################################
     # step one - save whitelisted tags use ‹tag›
@@ -25,38 +25,38 @@ module TemplateHelper
 
       # convert xml-style empty tags to simple html emtpty tags
       #  e.g. <br/> or <br /> becomses <br>
-      hy = hy.gsub( /<(#{tag})\s*\/>/i )       { |_| "‹#{$1.downcase}›" }   # eg. <br /> or <br/> becomes ‹br›
+      ht = ht.gsub( /<(#{tag})\s*\/>/i )       { |_| "‹#{$1.downcase}›" }   # eg. <br /> or <br/> becomes ‹br›
 
       # make sure we won't swall <br> for <b> for example, thus use \s+ before [^>]
-      hy = hy.gsub( /<(#{tag})(\s+[^>]*)?>/i ) { |_| "‹#{$1.downcase}›" }   # opening tag <p>
-      hy = hy.gsub( /<\/(#{tag})\s*>/i )       { |_| "‹/#{$1.downcase}›" }  # closing tag e.g. </p>
+      ht = ht.gsub( /<(#{tag})(\s+[^>]*)?>/i ) { |_| "‹#{$1.downcase}›" }   # opening tag <p>
+      ht = ht.gsub( /<\/(#{tag})\s*>/i )       { |_| "‹/#{$1.downcase}›" }  # closing tag e.g. </p>
     end
 
     ############################
     # step two - clean tags
 
     #   strip images - special treatment for debugging
-    hy = hy.gsub( /<img[^>]*>/i, '♦' )   # for debugging use black diamond e.g. ♦
-    hy = hy.gsub( /<\/img>/i, '' )   # should not exists
+    ht = ht.gsub( /<img[^>]*>/i, '♦' )   # for debugging use black diamond e.g. ♦
+    ht = ht.gsub( /<\/img>/i, '' )   # should not exists
 
     # strip all remaining tags
-    hy = hy.gsub( /<[^>]+>/, '' )
+    ht = ht.gsub( /<[^>]+>/, '' )
     
-    pp hy  # fix: debugging indo - remove
+    pp ht  # fix: debugging indo - remove
     
     ############################################
     # step three - restore whitelisted tags
 
-    return hy if opts[:skip_restore].present?   # skip step 3 for debugging
+    return ht if opts[:skip_restore].present?   # skip step 3 for debugging
 
     tags.each do |tag|
-#      hy = hy.gsub( /‹(#{tag})›/, "<\1>" )  # opening tag e.g. <p>
-#      hy = hy.gsub( /‹\/(#{tag})›/, "<\/\1>" )  # closing tag e.g. </p>
-      hy = hy.gsub( /‹(#{tag})›/ )   { |_| "<#{$1}>" }
-      hy = hy.gsub( /‹\/(#{tag})›/ ) { |_| "<\/#{$1}>" }  # closing tag e.g. </p>
+#      ht = ht.gsub( /‹(#{tag})›/, "<\1>" )  # opening tag e.g. <p>
+#      ht = ht.gsub( /‹\/(#{tag})›/, "<\/\1>" )  # closing tag e.g. </p>
+      ht = ht.gsub( /‹(#{tag})›/ )   { |_| "<#{$1}>" }
+      ht = ht.gsub( /‹\/(#{tag})›/ ) { |_| "<\/#{$1}>" }  # closing tag e.g. </p>
     end
 
-    hy
+    ht
   end  # method whitelist
 
 
@@ -95,37 +95,37 @@ module TemplateHelper
 
   
 
-  def textify( hy, opts={} )   # hy -> hypertext
+  def textify( ht, opts={} )   # ht -> hypertext
     ## turn into text
     # todo: add options for
     #   keep links, images, lists (?too), code, codeblocks
 
-    hy = whitelist( hy, [:br, :p, :ul, :ol, :li, :pre, :code, :blockquote, :q, :cite], opts )
+    ht = whitelist( ht, [:br, :p, :ul, :ol, :li, :pre, :code, :blockquote, :q, :cite], opts )
 
    # strip bold
-#    hy = hy.gsub( /<b[^>]*>/, '**' )  # fix: will also swallow bxxx tags - add b space
-#    hy = hy.gsub( /<\/b>/, '**' )
+#    ht = ht.gsub( /<b[^>]*>/, '**' )  # fix: will also swallow bxxx tags - add b space
+#    ht = ht.gsub( /<\/b>/, '**' )
 
     # strip em
-#   hy = hy.gsub( /<em[^>]*>/, '__' )
-#   hy = hy.gsub( /<\/em>/, '__' )
+#   ht = ht.gsub( /<em[^>]*>/, '__' )
+#   ht = ht.gsub( /<\/em>/, '__' )
 
     # clean (prettify) literal urls (strip protocoll) 
-    hy = hy.gsub( /(http|https):\/\//, '' )
+    ht = ht.gsub( /(http|https):\/\//, '' )
 
-#    hy = hy.gsub( /&nbsp;/, ' ' )
+#    ht = ht.gsub( /&nbsp;/, ' ' )
 
 #    # try to cleanup whitespaces
 #    # -- keep no more than two spaces
-#    hy = hy.gsub( /[ \t]{3,}/, '  ' )
+#    ht = ht.gsub( /[ \t]{3,}/, '  ' )
 #    # -- keep no more than two new lines
-#    hy = hy.gsub( /\n{2,}/m, "\n\n" ) 
+#    ht = ht.gsub( /\n{2,}/m, "\n\n" ) 
 #    # -- remove all trailing spaces
-#    hy = hy.gsub( /[ \t\n]+$/m, '' )
+#    ht = ht.gsub( /[ \t\n]+$/m, '' )
 #    # -- remove all leading spaces
-#    hy = hy.gsub( /^[ \t\n]+/m, '' ) 
+#    ht = ht.gsub( /^[ \t\n]+/m, '' ) 
 
-    hy
+    ht
   end
 
 

data/lib/pluto/version.rb

@@ -1,4 +1,4 @@
 
 module Pluto
-  VERSION = '0.8.5'
+  VERSION = '0.8.6'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: pluto
 version: !ruby/object:Gem::Version
-  version: 0.8.5
+  version: 0.8.6
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-10-02 00:00:00.000000000 Z
+date: 2013-10-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: pakman
-  requirement: &80642240 !ruby/object:Gem::Requirement
+  requirement: &75090920 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,10 +21,10 @@ dependencies:
         version: '0.5'
   type: :runtime
   prerelease: false
-  version_requirements: *80642240
+  version_requirements: *75090920
 - !ruby/object:Gem::Dependency
   name: fetcher
-  requirement: &80642000 !ruby/object:Gem::Requirement
+  requirement: &75090620 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -32,10 +32,10 @@ dependencies:
         version: '0.3'
   type: :runtime
   prerelease: false
-  version_requirements: *80642000
+  version_requirements: *75090620
 - !ruby/object:Gem::Dependency
   name: logutils
-  requirement: &80641710 !ruby/object:Gem::Requirement
+  requirement: &75090350 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -43,10 +43,10 @@ dependencies:
         version: '0.6'
   type: :runtime
   prerelease: false
-  version_requirements: *80641710
+  version_requirements: *75090350
 - !ruby/object:Gem::Dependency
   name: feedutils
-  requirement: &80641470 !ruby/object:Gem::Requirement
+  requirement: &75090050 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -54,10 +54,10 @@ dependencies:
         version: 0.3.2
   type: :runtime
   prerelease: false
-  version_requirements: *80641470
+  version_requirements: *75090050
 - !ruby/object:Gem::Dependency
   name: props
-  requirement: &80641170 !ruby/object:Gem::Requirement
+  requirement: &75089760 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -65,10 +65,10 @@ dependencies:
         version: 1.0.2
   type: :runtime
   prerelease: false
-  version_requirements: *80641170
+  version_requirements: *75089760
 - !ruby/object:Gem::Dependency
   name: textutils
-  requirement: &80640910 !ruby/object:Gem::Requirement
+  requirement: &75089460 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -76,10 +76,10 @@ dependencies:
         version: 0.6.8
   type: :runtime
   prerelease: false
-  version_requirements: *80640910
+  version_requirements: *75089460
 - !ruby/object:Gem::Dependency
   name: gli
-  requirement: &80640610 !ruby/object:Gem::Requirement
+  requirement: &75089160 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -87,10 +87,10 @@ dependencies:
         version: 2.5.6
   type: :runtime
   prerelease: false
-  version_requirements: *80640610
+  version_requirements: *75089160
 - !ruby/object:Gem::Dependency
   name: rdoc
-  requirement: &80640330 !ruby/object:Gem::Requirement
+  requirement: &75088910 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -98,10 +98,10 @@ dependencies:
         version: '3.10'
   type: :development
   prerelease: false
-  version_requirements: *80640330
+  version_requirements: *75088910
 - !ruby/object:Gem::Dependency
   name: hoe
-  requirement: &80640060 !ruby/object:Gem::Requirement
+  requirement: &75088620 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -109,7 +109,7 @@ dependencies:
         version: '3.3'
   type: :development
   prerelease: false
-  version_requirements: *80640060
+  version_requirements: *75088620
 description: pluto - Another Planet Generator (Lets You Build Web Pages from Published
   Web Feeds)
 email: feedreader@googlegroups.com