feedutils 0.3.2 → 0.4.0

data/README.md

@@ -6,6 +6,8 @@ feedutils gems - web feed parser and normalizer (RSS 2.0, Atom, etc.)
 * bugs  :: [github.com/rubylibs/feedutils/issues](https://github.com/rubylibs/feedutils/issues)
 * gem   :: [rubygems.org/gems/feedutils](https://rubygems.org/gems/feedutils)
 * rdoc  :: [rubydoc.info/gems/feedutils](http://rubydoc.info/gems/feedutils)
+* forum :: [groups.google.com/group/feedreader](http://groups.google.com/group/feedreader)
+
 
 ## Usage
 
@@ -13,8 +15,13 @@ TBD
 
 ## Alternatives
 
+- [`syndication`](http://syndication.rubyforge.org) [(Source)](https://github.com/lpar/syndication) - by Mathew (aka lpar);  RSS 1.0, 2.0, Atom, and understands namespaces; optional support for Dublin Core, iTunes/podcast feeds, and RSS 1.0 Syndication and Content modules
+- [`simple-rss`](http://rubyforge.org/projects/simple-rss)
+- [`feedtools`](http://rubyforge.org/projects/feedtools)
+
 TBD
 
+
 ## License
 
 The `feedutils` scripts are dedicated to the public domain.

data/Rakefile

@@ -11,7 +11,7 @@ Hoe.spec 'feedutils' do
   self.urls    = ['https://github.com/rubylibs/feedutils']
 
   self.author  = 'Gerald Bauer'
-  self.email   = 'webslideshow@googlegroups.com'
+  self.email   = 'feedreader@googlegroups.com'
 
   # switch extension to .markdown for gihub formatting
   self.readme_file  = 'README.md'

data/lib/feedutils.rb

@@ -23,7 +23,7 @@ require 'feedutils/parser'
 module FeedUtils
 
   def self.banner
-    "feedutils #{VERSION} on Ruby #{RUBY_VERSION} (#{RUBY_RELEASE_DATE}) [#{RUBY_PLATFORM}]"
+    "feedutils/#{VERSION} (with stdlib rss/#{RSS::VERSION}) on Ruby #{RUBY_VERSION} (#{RUBY_RELEASE_DATE}) [#{RUBY_PLATFORM}]"
   end
 
 =begin

data/lib/feedutils/builder/atom.rb

@@ -21,10 +21,11 @@ class AtomFeedBuilder
 
   def build_feed( atom_feed )
     feed = Feed.new
-    feed.object = atom_feed
+    ## feed.object = atom_feed  # not use for now
     feed.format = 'atom'
 
     feed.title  = atom_feed.title.content
+    logger.debug "  atom | title.content  >#{atom_feed.title.content}< : #{atom_feed.title.content.class.name}"
 
     if atom_feed.updated
       # NOTE: empty updated.content e.g.  used by google groups feed
@@ -39,6 +40,12 @@ class AtomFeedBuilder
     if atom_feed.generator
       feed.generator =  atom_feed.generator.content
       logger.debug "  atom | generator.content  >#{atom_feed.generator.content}< : #{atom_feed.generator.content.class.name}"
+
+      # pp atom_feed.generator
+      feed.generator_version = atom_feed.generator.version
+      feed.generator_uri     = atom_feed.generator.uri
+      logger.debug "  atom | generator.version  >#{atom_feed.generator.version}< : #{atom_feed.generator.version.class.name}"
+      logger.debug "  atom | generator.uri      >#{atom_feed.generator.uri}< : #{atom_feed.generator.uri.class.name}"
     end
 
     if atom_feed.subtitle
@@ -58,7 +65,7 @@ class AtomFeedBuilder
 
   def build_feed_item( atom_item )
     item = Item.new   # Item.new
-    item.object = atom_item
+    ## item.object = atom_item  # not used for now
 
     item.title     = atom_item.title.content
     item.url       = atom_item.link.href
@@ -68,36 +75,26 @@ class AtomFeedBuilder
 
 
     if atom_item.updated
-      ## convert from time to to_datetime  (avoid errors on windows w/ builtin rss lib)
-
-      item.updated    =  atom_item.updated.content.nil? ? nil : atom_item.updated.content.to_datetime   #  .utc.strftime( "%Y-%m-%d %H:%M" )
-
       ## change time to utc if present? why? why not?
+      #  --  .utc.strftime( "%Y-%m-%d %H:%M" )
+
+      ## convert from time to to_datetime  (avoid errors on windows w/ builtin rss lib)
 
+      item.updated    =  atom_item.updated.content.nil? ? nil : atom_item.updated.content.to_datetime
       logger.debug "  atom | item.updated.content  >#{atom_item.updated.content}< : #{atom_item.updated.content.class.name}"
     end
-    
+
     if atom_item.published
       ## convert from time to to_datetime  (avoid errors on windows w/ builtin rss lib)
 
-      item.published   =  atom_item.published.content.nil? ? nil : atom_item.published.content.to_datetime   #  .utc.strftime( "%Y-%m-%d %H:%M" )
+      item.published   =  atom_item.published.content.nil? ? nil : atom_item.published.content.to_datetime
       logger.debug "  atom | item.published.content  >#{atom_item.published.content}< : #{atom_item.published.content.class.name}"
     end
 
-    # - todo/check: does it exist in atom format?
-    # item.published  =  item.updated  # fix: check if publshed set
 
     item.guid       =  atom_item.id.content
-
     logger.debug "  atom | item.id.content: >#{atom_item.id.content}< : #{atom_item.id.content.class.name}"
 
-    # todo: move logic to updater or something
-    #  - not part of normalize
-
-
-    ## fix/todo:
-    #  also save/include full content in content
-
     if atom_item.content
       item.content = atom_item.content.content
     end
@@ -106,14 +103,6 @@ class AtomFeedBuilder
       item.summary = atom_item.summary.content
     end
 
-#  let client deal w/ missing summary - move to attic - delete
-#        text  = atom_item.content.content
-#        ## strip all html tags
-#        text = text.gsub( /<[^>]+>/, '' )
-#        text = text[ 0..400 ] # get first 400 chars
-#        ## todo: check for length if > 400 add ... at the end???
-#        item.summary = text
-
     item
   end # method build_feed_item
 

data/lib/feedutils/builder/rss.rb

@@ -24,7 +24,7 @@ class RssFeedBuilder
 
   def build_feed( rss_feed )
     feed = Feed.new
-    feed.object = rss_feed
+    ## feed.object = rss_feed   # not use for now
     feed.format = "rss #{rss_feed.rss_version}"
 
     feed.title     = rss_feed.channel.title           # required
@@ -65,11 +65,14 @@ class RssFeedBuilder
   def build_feed_item( rss_item )
 
     item = Item.new
-    item.object = rss_item
+    ## item.object = rss_item  # not use for now
 
     item.title     = rss_item.title
     item.url       = rss_item.link
 
+    logger.debug "  rss | item.title: >#{rss_item.title}< : #{rss_item.title.class.name}"
+    logger.debug "  rss | item.link: >#{rss_item.link}< : #{rss_item.link.class.name}"
+
 ## todo:
 ##  check if feedburner:origLink present - if yes, use it for url/link
 ##  example: use
@@ -80,8 +83,10 @@ class RssFeedBuilder
 
     item.summary   = rss_item.description
 
-    logger.debug "  rss | item.title: >#{rss_item.title}< : #{rss_item.title.class.name}"
-    logger.debug "  rss | item.link: >#{rss_item.link}< : #{rss_item.link.class.name}"
+    # check for <content:encoded>
+    # -- using RSS 1.0 content module in RSS 2.0
+    item.content = rss_item.content_encoded
+    logger.debug "  rss | item.content_encoded[0..40]: >#{rss_item.content_encoded ? rss_item.content_encoded[0..40] : ''}< : #{rss_item.content_encoded.class.name}"
 
     # NOTE:
     # All date-times in RSS conform
@@ -94,15 +99,7 @@ class RssFeedBuilder
     item.published = rss_item.pubDate.nil? ? nil : rss_item.pubDate.to_datetime    # .utc.strftime( "%Y-%m-%d %H:%M" )
 
     logger.debug "  rss | item.pubDate: >#{rss_item.pubDate}< : #{rss_item.pubDate.class.name}"
- 
-    ## fix/todo: add
-    ## check for <content:encoded>
-    ##   full content  (example use e.g. in sitepoint/ruby/feed/)
-    # content:  item.content_encoded,
-  
-    # if item.content_encoded.nil?
-    # puts " using description for content"
-    # end
+
 
     ## fix/todo: check if rss_item.guid present? !!!!
     ##

data/lib/feedutils/feed.rb

@@ -1,7 +1,7 @@
 module FeedUtils
 
 class Feed
-  attr_accessor :object
+  ### attr_accessor :object  # not use for now
 
   attr_accessor :format   # e.g. atom|rss 2.0|etc.
   attr_accessor :title
@@ -11,29 +11,15 @@ class Feed
   attr_accessor :items
 
   def summary?()  @summary.nil? == false;  end
-  # no summary? try/return title2
-  def summary()  summary?  ?  @summary : @title2;  end
-  attr_writer :summary        # e.g. description (rss)
-
+  attr_accessor :summary        # e.g. description (rss)
   attr_accessor :summary_type   # e.g. text|html|html-escaped
 
   def title2?()  @title2.nil? == false;  end
   attr_accessor :title2         # e.g. subtitle (atom)
-
   attr_accessor :title2_type    # e.g. text|html|html-escaped
 
   def published?()  @published.nil? == false;  end
-  # no published date? try/return updated or built
-  def published
-    if published?
-      @published
-    elsif updated?
-      @updated
-    else
-      @built
-    end
-  end
-  attr_writer :published
+  attr_accessor :published
 
   def updated?()  @updated.nil? == false;  end
   attr_accessor :updated
@@ -42,11 +28,13 @@ class Feed
   attr_accessor :built
 
   attr_accessor :generator
-
+  attr_accessor :generator_version  # e.g. @version (atom)
+  attr_accessor :generator_uri      # e.g. @uri     (atom) - use alias url/link ???
 
   ## fix:
   #  add pretty printer/inspect (exclude object)
 
+
 end  # class Feed
 
 end # module FeedUtils

data/lib/feedutils/item.rb

@@ -1,35 +1,27 @@
 module FeedUtils
 
 class Item
-  attr_accessor :object   # orginal object (e.g RSS item or ATOM entry etc.)
+  ## attr_accessor :object   # not used for now -- orginal object (e.g RSS item or ATOM entry etc.)
 
   attr_accessor :title
   attr_accessor :title_type    # optional for now (text|html|html-escaped) - not yet set
   attr_accessor :url      # todo: rename to link (use alias) ??
 
 
-  # no content? try/return summary
-  def content()  content? ? @content : @summary;  end
   def content?()  @content.nil? == false;  end
-  attr_writer   :content
+  attr_accessor  :content
+  attr_accessor  :content_type  # optional for now (text|html|html-escaped|binary-base64) - not yet set
 
-  attr_accessor :content_type  # optional for now (text|html|html-escaped|binary-base64) - not yet set
-
-  # no summary? try/return content
-  def summary()  summary? ? @summary : @content;  end
   def summary?()  @summary.nil? == false;  end
-  attr_writer   :summary
-
-  attr_accessor :summary_type  # optional for now (text|html|html-escaped) - not yet set
+  attr_accessor   :summary
+  attr_accessor   :summary_type  # optional for now (text|html|html-escaped) - not yet set
 
 ## todo: add summary (alias description)  ???
 ## todo: add author/authors
 ## todo: add category/categories
 
-  # no published date? try/return updated
-  def published()  published? ? @published : @updated;  end
   def published?()  @published.nil? == false;  end
-  attr_writer :published
+  attr_accessor :published
 
   def updated?()  @updated.nil? == false;  end
   attr_accessor :updated

data/lib/feedutils/parser.rb

@@ -15,8 +15,10 @@ class Parser
   def initialize( xml )
     @xml = xml
   end
-    
+
   def parse
+    logger.debug "using stdlib rss/#{RSS::VERSION}"
+
     parser = RSS::Parser.new( @xml )
     parser.do_validate            = false
     parser.ignore_unknown_element = true

data/lib/feedutils/version.rb

@@ -1,4 +1,4 @@
 
 module FeedUtils
-   VERSION = '0.3.2'
+  VERSION = '0.4.0'
 end

data/test/test_atom.rb

@@ -10,17 +10,30 @@ class TestAtom < MiniTest::Unit::TestCase
 
   def test_rubyonrails
     feed = parse_feed( 'http://weblog.rubyonrails.org/feed/atom.xml' )
-    assert( feed.format == 'atom' )
+    
+    assert_equal 'atom', feed.format
   end
 
   def test_railstutorial
     feed = parse_feed( 'http://feeds.feedburner.com/railstutorial?format=xml' )
-    assert( feed.format == 'atom' )
+    
+    assert_equal 'atom', feed.format
   end
 
   def test_googlegroup
     feed = parse_feed( 'https://groups.google.com/forum/feed/beerdb/topics/atom.xml?num=15' )
-    assert( feed.format == 'atom' )
+
+    assert_equal 'atom', feed.format
+  end
+
+
+  def test_headius
+    feed = parse_feed( 'http://blog.headius.com/feeds/posts/default' )
+
+    assert_equal 'atom',    feed.format
+    assert_equal 'Blogger', feed.generator
+    assert_equal 'Headius', feed.title
+    assert_equal 'Helping the JVM Into the 21st Century', feed.title2  # aka subtitle in atom
   end
 
 end

data/test/test_rss.rb

@@ -11,18 +11,28 @@ class TestRss < MiniTest::Unit::TestCase
 
   def test_rubyflow
     feed = parse_feed( 'http://feeds.feedburner.com/Rubyflow?format=xml' )
-    assert( feed.format == 'rss 2.0' )
+    
+    assert_equal 'rss 2.0', feed.format
   end
 
   def test_sitepointruby
     feed = parse_feed( 'http://www.sitepoint.com/ruby/feed/' )
-    assert( feed.format == 'rss 2.0' )
+
+    assert_equal 'rss 2.0', feed.format
   end
 
   def test_lambdatheultimate
     ## check - has no item.guid - will use item.link for guid
     feed = parse_feed( 'http://lambda-the-ultimate.org/rss.xml' )
-    assert( feed.format == 'rss 2.0' )
+
+    assert_equal 'rss 2.0', feed.format
+  end
+
+  def test_rubymine
+    # includes item/content:encoded
+    feed = parse_feed( 'http://feeds.feedburner.com/jetbrains_rubymine?format=xml' )
+    
+    assert_equal 'rss 2.0', feed.format
   end
 
-end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: feedutils
 version: !ruby/object:Gem::Version
-  version: 0.3.2
+  version: 0.4.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-09-28 00:00:00.000000000 Z
+date: 2013-10-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: logutils
-  requirement: &82615740 !ruby/object:Gem::Requirement
+  requirement: &74494180 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,10 +21,10 @@ dependencies:
         version: '0.5'
   type: :runtime
   prerelease: false
-  version_requirements: *82615740
+  version_requirements: *74494180
 - !ruby/object:Gem::Dependency
   name: rdoc
-  requirement: &82615490 !ruby/object:Gem::Requirement
+  requirement: &74493890 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -32,10 +32,10 @@ dependencies:
         version: '3.10'
   type: :development
   prerelease: false
-  version_requirements: *82615490
+  version_requirements: *74493890
 - !ruby/object:Gem::Dependency
   name: hoe
-  requirement: &82615190 !ruby/object:Gem::Requirement
+  requirement: &74493660 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -43,9 +43,9 @@ dependencies:
         version: '3.3'
   type: :development
   prerelease: false
-  version_requirements: *82615190
+  version_requirements: *74493660
 description: feedutils - web feed parser and normalizer (RSS 2.0, Atom, etc.)
-email: webslideshow@googlegroups.com
+email: feedreader@googlegroups.com
 executables: []
 extensions: []
 extra_rdoc_files: