rfeedreader 0.1.0

data/History.txt

@@ -0,0 +1,3 @@
+== 0.1.0 2007-09-01
+
+* Initial release

data/License.txt

@@ -0,0 +1,20 @@
+Copyright (c) 2007 Alexandre Girard
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/Manifest.txt

@@ -0,0 +1,16 @@
+History.txt
+License.txt
+Manifest.txt
+README.txt
+Rakefile
+lib/rfeedreader.rb
+lib/rfeedreader/version.rb
+scripts/txt2html
+setup.rb
+test/test_helper.rb
+test/test_rfeedreader.rb
+website/index.html
+website/index.txt
+website/javascripts/rounded_corners_lite.inc.js
+website/stylesheets/screen.css
+website/template.rhtml

data/README.txt

@@ -0,0 +1,5 @@
+README for rfeedreader
+======================
+
+Feed parser to read feed and return first posts of this feed.
+Special parsing from sources like Flickr, Jumcut, Google video, ...

data/Rakefile

@@ -0,0 +1,132 @@
+require 'rubygems'
+require 'rake'
+require 'rake/clean'
+require 'rake/testtask'
+require 'rake/packagetask'
+require 'rake/gempackagetask'
+require 'rake/rdoctask'
+require 'rake/contrib/rubyforgepublisher'
+require 'fileutils'
+require 'hoe'
+
+include FileUtils
+require File.join(File.dirname(__FILE__), 'lib', 'rfeedreader', 'version')
+
+AUTHOR = 'Alexandre Girard'  # can also be an array of Authors
+EMAIL = "alx.girard@gmail.com"
+DESCRIPTION = "Feed parser to read feed and return first posts of this feed. Special parsing from sources like Flickr, Jumcut, Google video, ..."
+GEM_NAME = 'rfeedreader' # what ppl will type to install your gem
+
+@config_file = "~/.rubyforge/user-config.yml"
+@config = nil
+def rubyforge_username
+  unless @config
+    begin
+      @config = YAML.load(File.read(File.expand_path(@config_file)))
+    rescue
+      puts <<-EOS
+ERROR: No rubyforge config file found: #{@config_file}"
+Run 'rubyforge setup' to prepare your env for access to Rubyforge
+ - See http://newgem.rubyforge.org/rubyforge.html for more details
+      EOS
+      exit
+    end
+  end
+  @rubyforge_username ||= @config["username"]
+end
+
+RUBYFORGE_PROJECT = 'rfeedreader' # The unix name for your project
+HOMEPATH = "http://#{RUBYFORGE_PROJECT}.rubyforge.org"
+DOWNLOAD_PATH = "http://rubyforge.org/projects/#{RUBYFORGE_PROJECT}"
+
+NAME = "rfeedreader"
+REV = nil 
+# UNCOMMENT IF REQUIRED: 
+# REV = `svn info`.each {|line| if line =~ /^Revision:/ then k,v = line.split(': '); break v.chomp; else next; end} rescue nil
+VERS = Rfeedreader::VERSION::STRING + (REV ? ".#{REV}" : "")
+CLEAN.include ['**/.*.sw?', '*.gem', '.config', '**/.DS_Store']
+RDOC_OPTS = ['--quiet', '--title', 'rfeedreader documentation',
+    "--opname", "index.html",
+    "--line-numbers", 
+    "--main", "README",
+    "--inline-source"]
+
+class Hoe
+  def extra_deps 
+    @extra_deps.reject { |x| Array(x).first == 'hoe' } 
+  end 
+end
+
+# Generate all the Rake tasks
+# Run 'rake -T' to see list of generated tasks (from gem root directory)
+hoe = Hoe.new(GEM_NAME, VERS) do |p|
+  p.author = AUTHOR 
+  p.description = DESCRIPTION
+  p.email = EMAIL
+  p.summary = DESCRIPTION
+  p.url = HOMEPATH
+  p.rubyforge_name = RUBYFORGE_PROJECT if RUBYFORGE_PROJECT
+  p.test_globs = ["test/**/test_*.rb"]
+  p.clean_globs |= CLEAN  #An array of file patterns to delete on clean.
+  
+  # == Optional
+  p.changes = p.paragraphs_of("History.txt", 0..1).join("\n\n")
+  #p.extra_deps = []     # An array of rubygem dependencies [name, version], e.g. [ ['active_support', '>= 1.3.1'] ]
+  #p.spec_extras = {}    # A hash of extra values to set in the gemspec.
+end
+
+CHANGES = hoe.paragraphs_of('History.txt', 0..1).join("\n\n")
+PATH    = (RUBYFORGE_PROJECT == GEM_NAME) ? RUBYFORGE_PROJECT : "#{RUBYFORGE_PROJECT}/#{GEM_NAME}"
+hoe.remote_rdoc_dir = File.join(PATH.gsub(/^#{RUBYFORGE_PROJECT}\/?/,''), 'rdoc')
+
+desc 'Generate website files'
+task :website_generate do
+  Dir['website/**/*.txt'].each do |txt|
+    sh %{ ruby scripts/txt2html #{txt} > #{txt.gsub(/txt$/,'html')} }
+  end
+end
+
+desc 'Upload website files to rubyforge'
+task :website_upload do
+  host = "#{rubyforge_username}@rubyforge.org"
+  remote_dir = "/var/www/gforge-projects/#{PATH}/"
+  local_dir = 'website'
+  sh %{rsync -aCv #{local_dir}/ #{host}:#{remote_dir}}
+end
+
+desc 'Generate and upload website files'
+task :website => [:website_generate, :website_upload, :publish_docs]
+
+desc 'Release the website and new gem version'
+task :deploy => [:check_version, :website, :release] do
+  puts "Remember to create SVN tag:"
+  puts "svn copy svn+ssh://#{rubyforge_username}@rubyforge.org/var/svn/#{PATH}/trunk " +
+    "svn+ssh://#{rubyforge_username}@rubyforge.org/var/svn/#{PATH}/tags/REL-#{VERS} "
+  puts "Suggested comment:"
+  puts "Tagging release #{CHANGES}"
+end
+
+desc 'Runs tasks website_generate and install_gem as a local deployment of the gem'
+task :local_deploy => [:website_generate, :install_gem]
+
+task :check_version do
+  unless ENV['VERSION']
+    puts 'Must pass a VERSION=x.y.z release version'
+    exit
+  end
+  unless ENV['VERSION'] == VERS
+    puts "Please update your version.rb to match the release version, currently #{VERS}"
+    exit
+  end
+end
+
+rule "" do |t|
+  # test:file:method
+  if /test:(.*)(:([^.]+))?$/.match(t.name)
+    arguments = t.name.split(":")[1..-1]
+    test_name = arguments.first
+    run_file_name = "test_rfeedreader.rb" 
+    
+    sh "ruby -Ilib:test test/#{run_file_name} -n /#{test_name}/" 
+  end
+end

data/lib/rfeedreader.rb

@@ -0,0 +1,194 @@
+require 'net/http'
+require 'rubygems'
+require 'open-uri'
+require 'hpricot'
+require 'timeout'
+require 'rfeedfinder'
+require 'helper/texty_helper'
+require 'helper/html_entities'
+
+module Rfeedreader
+  module_function
+  
+  class Feed
+    attr_accessor :title, :link, :charset, :entries
+    
+    def initialize(link, hpricot_doc)
+      @link = link
+      read_title hpricot_doc
+      read_charset hpricot_doc
+      @entries = []
+    end
+    
+    def parse_entries(hpricot_doc, nb_posts=10)
+      @entries = []
+      type = self.source_type
+      
+      # Parse each item
+      (hpricot_doc/"item|entry")[0..nb_posts - 1].each do |item|
+        case type
+          when "source_flickr"
+            @entries<<Entry_Flickr.new(item, self.charset)
+          when "source_fotolog"
+            @entries<<Entry_Fotolog.new(item, self.charset)
+          when "source_google_video"
+            @entries<<Entry_Google_Video.new(item, self.charset)
+          when "source_jumpcut"
+            @entries<<Entry_Jumpcut.new(item, self.charset)
+          when "source_picasa"
+            @entries<<Entry_Picasa.new(item, self.charset)
+          else
+            @entries<<Entry.new(item, self.charset)
+        end
+      end
+    end
+    
+    def to_s
+      "Feed: title: #{title} - charset: #{charset}\n\rlink: #{link} - Entries: #{entries.size}"
+    end
+    
+    def display_entries
+      i = 0
+      @entries.each do |entry|
+        i += 1
+        puts "#{i} - #{entry}"
+      end
+    end
+    
+    protected
+    
+    def read_charset(hpricot_doc)
+      @charset = hpricot_doc.to_s.scan(/encoding=['"]?([^'"]*)['" ]/)
+      @charset = @charset[0] if @charset.is_a? Array
+      @charset = @charset.to_s.downcase
+    end
+    
+    def read_title(hpricot_doc)
+      @title = (hpricot_doc/"//title:first").text
+    end
+
+    def source_type
+      return "source_flickr" if link =~ /http:\/\/api\.flickr\.com/
+      return "source_fotolog" if link =~ /\.fotolog\.com/
+      return "source_google_video" if link =~ /http:\/\/video\.google\.com/
+      return "source_jumpcut" if link =~ /http:\/\/rss\.jumpcut\.com/
+      return "source_picasa" if link =~ /http:\/\/picasaweb\.google\.com/
+      return ""
+    end
+  end
+  
+  class Entry
+    attr_accessor :title, :link, :description, :charset
+    
+    def initialize(item, charset)
+      @charset = charset
+      @link = read_link item
+      @title = read_title item
+      @description = read_description item
+    end
+    
+    # Return the rss item link
+    def read_link(item)
+      post_url = nil
+      if link = item.search("link:first")
+        post_url = link.text
+        post_url = link.to_s.scan(/href=['"]?([^'"]*)['" ]/).to_s if (post_url.nil? or post_url.empty?)
+      end
+      return post_url
+    end
+    
+    def read_title(item)
+      return TextyHelper::convertEncoding((item/:title).text, @charset).downcase
+    end
+    
+    def read_description(item)
+      description = (item/"description|summary|content|[@type='text']").text
+     if description.include? "&lt;"
+        description = HTMLEntities.decode_entities(description)
+      else
+        description = HTMLEntities.encode_entities(description, :named, :decimal) if @charset == 'utf-8'
+      end
+      description = TextyHelper::clean(TextyHelper::convertEncoding(description, @charset), 200) unless description.empty?
+      description.gsub!(/((https?):\/\/([^\/]+)\/(.*))/, '[<a href=\'\1\'>link</a>]') unless description.empty?
+      return description.strip
+    end
+    
+    def to_s
+      "Entry: title: #{title} - link: #{link}\n\rdescription: #{description}"
+    end
+  end
+  
+  class Entry_Flickr<Entry
+    def read_description(item)
+      image = item.search("media:thumbnail").to_s.scan(/url=['"]?([^'"]*)['" ]/).to_s
+      image = item.search("content|description").text.scan(/(http:\/\/farm.*_.\.jpg)/).to_s if image.nil? or image.empty?
+      image.gsub!(/_.\.jpg/,"_t.jpg")
+      return "<a href='#{@link}' class='image_link'><img src='#{image}' class='flickr_image'/></a><br/>"
+    end
+  end
+  
+  class Entry_Fotolog<Entry
+    def read_description(item)
+      image = item.search("media:thumbnail").to_s.scan(/url=['"]?([^'"]*)['" ]/).to_s
+      return "<a href='#{@link}' class='image_link'><img src='#{image}' class='post_image'/></a>"
+    end
+  end
+  
+  class Entry_Google_Video<Entry
+    def read_description(item)
+      image = item.search("media:thumbnail").to_s.scan(/url=['"]?([^'"]*)['" ]/).to_s.gsub(/&amp;/, '&')
+      return "<a href='#{@link}' class='image_link'><img src='#{image}' class='google_video_image' width='160px' height='160px'/></a><br/>"
+    end
+  end
+  
+  class Entry_Jumpcut<Entry
+    def read_description(item)
+      image = item.search("description").to_s.scan(/src=['"]?([^'"]*)['" ]/).to_s
+      return "<a href='#{@link}' class='image_link'><img src='#{image}' class='jumpcut_image' width='160px' height='120px'/></a><br/>"
+    end
+  end
+  
+  class Entry_Picasa<Entry
+    def read_description(item)
+      image = item.search("media:thumbnail").to_s.scan(/url=['"]?([^'"]*)['" ]/).to_s
+      return "<a href='#{@link}' class='image_link'><img src='#{image}' class='picasa_image'/></a>"
+    end
+  end
+  
+  def read(uri, nb_posts=10)
+    
+    link = Rfeedfinder::feed(uri)
+    doc = open_doc(link)
+    
+    unless doc.nil?
+      feed = Feed.new(link, doc)
+      entries = feed.parse_entries(doc, nb_posts)
+    end
+    
+    return feed
+  end
+  
+  def read_first(uri)
+    return read(uri, nb_post=1)
+  end
+  
+  def open_doc(link)
+    begin
+      data = Hpricot(open(link,
+            "User-Agent" => "Ruby/#{RUBY_VERSION} - Rfeedreader",
+            "From" => "rfeedreader@googlegroups.com",
+            "Referer" => "http://rfeedreader.rubyforge.org/"), :xml => true)
+    rescue Timeout::Error
+      return nil
+    rescue OpenURI::HTTPError
+      html = Net::HTTP.get(URI.parse(link))
+      data = Hpricot(html, :xml => true)
+    rescue => err
+      puts "Error while opening #{link} with Hpricot: #{err.class} " << $!
+      return nil
+    end
+    return data
+  end
+end
+
+require 'rfeedreader/version'

data/lib/rfeedreader/version.rb

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

data/scripts/txt2html

@@ -0,0 +1,67 @@
+#!/usr/bin/env ruby
+
+require 'rubygems'
+require 'redcloth'
+require 'syntax/convertors/html'
+require 'erb'
+require File.dirname(__FILE__) + '/../lib/rfeedreader/version.rb'
+
+version  = Rfeedreader::VERSION::STRING
+download = 'http://rubyforge.org/projects/rfeedreader'
+
+class Fixnum
+  def ordinal
+    # teens
+    return 'th' if (10..19).include?(self % 100)
+    # others
+    case self % 10
+    when 1: return 'st'
+    when 2: return 'nd'
+    when 3: return 'rd'
+    else    return 'th'
+    end
+  end
+end
+
+class Time
+  def pretty
+    return "#{mday}#{mday.ordinal} #{strftime('%B')} #{year}"
+  end
+end
+
+def convert_syntax(syntax, source)
+  return Syntax::Convertors::HTML.for_syntax(syntax).convert(source).gsub(%r!^<pre>|</pre>$!,'')
+end
+
+if ARGV.length >= 1
+  src, template = ARGV
+  template ||= File.dirname(__FILE__) + '/../website/template.rhtml'
+  
+else
+  puts("Usage: #{File.split($0).last} source.txt [template.rhtml] > output.html")
+  exit!
+end
+
+template = ERB.new(File.open(template).read)
+
+title = nil
+body = nil
+File.open(src) do |fsrc|
+  title_text = fsrc.readline
+  body_text = fsrc.read
+  syntax_items = []
+  body_text.gsub!(%r!<(pre|code)[^>]*?syntax=['"]([^'"]+)[^>]*>(.*?)</
>!m){
+    ident = syntax_items.length
+    element, syntax, source = $1, $2, $3
+    syntax_items << "<#{element} class='syntax'>#{convert_syntax(syntax, source)}</#{element}>"
+    "syntax-temp-#{ident}"
+  }
+  title = RedCloth.new(title_text).to_html.gsub(%r!<.*?>!,'').strip
+  body = RedCloth.new(body_text).to_html
+  body.gsub!(%r!(?:<pre><code>)?syntax-temp-(d+)(?:</code></pre>)?!){ syntax_items[$1.to_i] }
+end
+stat = File.stat(src)
+created = stat.ctime
+modified = stat.mtime
+
+$stdout << template.result(binding)