pluto 1.0.1 → 1.1.0

data/lib/pluto/schema.rb

@@ -1,139 +0,0 @@
-
-module Pluto
-
-class CreateDb < ActiveRecord::Migration
-
-  def up
-    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.
-
-      ############
-      # filters (site-wide)
-      t.string   :includes  # regex
-      t.string   :excludes  # regex
-
-      ######################
-      # for auto-update of feed list/site config
-
-      t.string   :url    # source url for auto-update (optional)
-
-      ## note: make sure to use same fields for update check as feed 
-
-      t.datetime :fetched   #  last fetched/checked date -- make not null ??
-      t.integer  :http_code   # last http status code e.g. 200,404,etc.
-      t.string   :http_etag    # last http header etag
-      ## note: save last-modified header as text (not datetime) - pass through as is
-      t.string   :http_last_modified   # last http header last-modified - note: save header as plain text!!! pass along in next request as-is
-      t.string   :http_server    # last http server header if present
-
-      # note: do NOT store body content (that is, text) and md5 digest
-      #   use git! and github! commit will be http_etag!!
-
-      t.datetime :fetched    # last fetched/checked date
-
-      #############
-      # more fields
-
-      t.timestamps  # created_at, updated_at
-    end
-
-    create_table :subscriptions do |t|   # has_many join table (sites/feeds)
-      t.references :site, :null => false
-      t.references :feed, :null => false
-      t.timestamps
-    end
-
-    create_table :feeds do |t|
-      t.string  :title        # user supplied title
-      t.string  :auto_title   # "fallback" - auto(fill) title from feed
-
-      t.string  :title2        # user supplied title2
-      t.string  :auto_title2   # "fallback" - auto(fill) title2 from feed e.g. subtitle (atom)
-
-      t.string  :url          # user supplied site url
-      t.string  :auto_url     # "fallback" - auto(fill) url from feed
-
-      t.string  :feed_url       # user supplied feed url
-      t.string  :auto_feed_url  # "fallback" - auto discovery feed url from (site) url
-
-      t.text    :summary    # e.g. description (rss)
-
-      t.string  :generator   # feed generator (e.g. wordpress, etc.)  from feed
-      
-      t.datetime :published  # from feed published(atom)+ pubDate(rss)
-      t.datetime :built      # from feed lastBuiltDate(rss)
-      t.datetime :touched    # from feed updated(atom)
-
-      ### extras (move to array for custom fields or similar??)
-      t.string   :github   # github handle  (optional)
-      t.string   :twitter  # twitter handle (optional)
-      t.string   :avatar   # gravator or hackergotchi handle (optional)
-
-      ### add class/kind field e.g.
-      # - personal feed/blog/site, that is, individual author
-      # - team blog/site
-      # - org (anization) or com(pany blog/site)
-      # - newsfeed (composite)
-      # - other  (link blog?, podcast?) - why? why not??
-
-      ############
-      # 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 :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.integer  :http_code   # last http status code e.g. 200,404,etc.
-      t.string   :http_etag    # last http header etag
-      ## note: save last-modified header as text (not datetime) - pass through as is
-      t.string   :http_last_modified   # last http header last-modified - note: save header as plain text!!! pass along in next request as-is
-      t.string   :http_server    # last http server header if present
-
-      t.string   :md5       # md5 hash of body
-      t.text     :body      # last http response body (complete feed!)
-
-      t.datetime :fetched    # last fetched/checked date
-
-      t.timestamps   # created_at, updated_at
-    end
-
-
-    create_table :items do |t|
-      t.string   :guid
-      t.string   :url
-
-      ## note: title may contain more than 255 chars!! use text for sure!
-      ## e.g. Rails Girls blog has massive titles in feed
-      
-      t.text     :title   # todo: add some :null => false ??
-      t.text     :summary  # e.g. description (rss), summary (atom)
-      t.text     :content
-      
-      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   # last fetched/check date
-      t.timestamps   # created_at, updated_at
-
-      ## t.string   :author
-      ## todo: add author/authors, category/categories
-    end
-
-  end
-    
-  def down
-    raise ActiveRecord::IrreversibleMigration
-  end
-    
-end  # class CreateDb
-   
-end  # module Pluto

data/lib/pluto/subscriber.rb

@@ -1,102 +0,0 @@
-module Pluto
-
-class Subscriber
-
-  include LogUtils::Logging
-
-  include Models
-
-  def debug=(value)  @debug = value;   end
-  def debug?()       @debug || false;  end
-
-
-  def update_subscriptions( config, opts={} )
-    # !!!! -- depreciated API - remove - do NOT use anymore
-    puts "*** warn - [Pluto::Subscriber] depreciated API -- use update_subscriptions_for( site_key )"
-    update_subscriptions_for( 'planet', config, opts )  # default to planet site_key
-  end
-
-
-  def update_subscriptions_for( site_key, config, opts={} )
-    site_attribs = {
-      title:  config['title'] || config['name'],   # support either title or name
-      url:    config['source'] || config['url']    # support source or url   for source url for auto-update (optional)
-    }
-
-    logger.debug "site_attribs: #{site_attribs.inspect}"
-
-    site_rec = Site.find_by_key( site_key )
-    if site_rec.nil?
-      site_rec             = Site.new
-      site_attribs[ :key ] = site_key
-
-      ## use object_id: site.id and object_type: Site
-      ## change - model/table/schema!!!
-      Activity.create!( text: "new site >#{site_key}< - #{site_attribs[ :title ]}" )
-    end
-    site_rec.update_attributes!( site_attribs )
-
-    # -- log update activity
-    Activity.create!( text: "update subscriptions >#{site_key}<" )
-
-    # clean out subscriptions and add again
-    logger.debug "before site.subscriptions.delete_all - count: #{site_rec.subscriptions.count}"
-    site_rec.subscriptions.destroy_all  # note: use destroy_all NOT delete_all (delete_all tries by default only nullify)
-    logger.debug "after site.subscriptions.delete_all - count: #{site_rec.subscriptions.count}"
-
-    config.each do |key, value|
-
-      ## todo: downcase key - why ??? why not???
-
-      # skip "top-level" feed keys e.g. title, etc. or planet planet sections (e.g. planet,defaults)
-      next if ['title','title2','name',
-               'source', 'url',
-               'include','includes','exclude','excludes',
-               'feeds',
-               'planet','defaults'].include?( key )
-
-      ### todo/check:
-      ##   check value - must be hash
-      #     check if url or feed_url present
-      #      that is, check for required props/key-value pairs
-
-      feed_key   = key.to_s.dup
-      feed_hash  = value
-
-      # 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' ],
-        includes: feed_hash[ 'includes' ] || feed_hash[ 'include' ],
-        excludes: feed_hash[ 'excludes' ] || feed_hash[ 'exclude' ]
-      }
-
-      puts "Updating feed subscription >#{feed_key}< - >#{feed_attribs[:feed_url]}<..."
-
-      feed_rec = Feed.find_by_key( feed_key )
-      if feed_rec.nil?
-        feed_rec             = Feed.new
-        feed_attribs[ :key ] = feed_key
-
-        ## use object_id: feed.id and object_type: Feed
-        ## change - model/table/schema!!!
-        ## todo: add parent_action_id - why? why not?
-        Activity.create!( text: "new feed >#{feed_key}< - #{feed_attribs[ :title ]}" )
-      end
-
-      feed_rec.update_attributes!( feed_attribs )
-
-      #  add subscription record
-      #   note: subscriptions get cleaned out on update first (see above)
-      site_rec.subscriptions.create!( feed_id: feed_rec.id )   
-    end
-
-  end # method update_subscriptions
-
-end # class Subscriber
-
-end # module Pluto

data/lib/pluto/tasks/env.rake

@@ -1,25 +0,0 @@
-
-
-task :env  do
-  LogUtils::Logger.root.level = :debug
-
-  Pluto.connect!
-end
-
-
-#########
-# for debugging
-
-desc 'pluto - debug site setup'
-task :site => :env do
-  site = Pluto::Models::Site.first      # FIX: for now assume one planet per DB (fix later; allow planet key or similar)
-  if site.present?
-    puts "site found:"
-    pp site
-  else
-    puts "no site found"
-  end
-end
-
-### todo: add new task :sites
-

data/lib/pluto/tasks/setup.rake

@@ -1,40 +0,0 @@
-
-
-desc 'pluto -=- setup/update feed subscriptions'
-task :setup => :env do
-
-  ## check if PLANET key passed in
-  if ENV['PLANET'].present?
-    key = ENV['PLANET']
-    puts "setup planet for key >#{key}<"
-  else
-    puts 'no PLANET=key passed along; try defaults'
-    # try pluto.yml or planet.yml if exist
-
-    if File.exists?( './pluto.ini' ) || File.exists?( './pluto.yml' ) # check if pluto.yml exists, if yes add/use it
-      key ='pluto'
-    elsif File.exists?( './planet.ini' ) || File.exists?( './planet.yml' ) # check if planet.yml exists, if yes add/use it
-      key = 'planet'
-    else
-      puts '*** note: no arg passed in; no pluto.ini|yml or planet.ini|yml found in working folder'
-    end
-  end
-
-
-  config_path = "./#{key}.ini"
-  if File.exists?( config_path )
-    config = INI.load_file( config_path )
-  else  ## assume .yml
-    config_path = "./#{key}.yml"
-    config = YAML.load_file( config_path )
-  end
-  
-
-  puts "dump planet setup settings >#{config_path}<:"
-  pp config
-
-  # note: allow multiple planets (sites) for a single install
-  Pluto::Subscriber.new.update_subscriptions_for( key, config )
-
-  puts 'Done.'
-end

data/lib/pluto/tasks/stats.rake

@@ -1,10 +0,0 @@
-
-
-desc 'pluto - show planet (feed) stats'
-task :stats => :env do
-  puts "stats:"
-  puts "  Feeds: #{Pluto::Models::Feed.count}"
-  puts "  Items: #{Pluto::Models::Item.count}"
-  puts "  Sites: #{Pluto::Models::Site.count}"
-  puts "  Subscriptions:  #{Pluto::Models::Subscription.count}"
-end

data/lib/pluto/tasks/update.rake

@@ -1,24 +0,0 @@
-
-
-desc 'pluto -=- update planet (site configs)'
-task :update_sites => :env do
-
-  Pluto.update_sites  # update all site configs if source (url) present/specified
-
-  puts 'Done (Update Sites).'
-end
-
-
-desc 'pluto -=- update planet (feeds)'
-task :update_feeds => :env do
-
-  Pluto.update_feeds
-  
-  puts 'Done (Update Feeds).'
-end
-
-
-desc 'pluto -=- update planet (site configs + feeds)'
-task :update => [:update_sites, :update_feeds] do
-  puts 'Done.'
-end

data/lib/pluto/updater.rb

@@ -1,50 +0,0 @@
-module Pluto
-
-class Updater
-
-  include LogUtils::Logging
-
-  ### fix!!!!!: change config    to text   - yes/no - why? why not??
-  #   or pass along struct
-  #      - with hash and text and format(e.g. ini/yml) as fields???
-  #
-  #   - why? - we need to get handle on md5 digest/hash plus on plain text, ideally to store in db
-  ##  - pass along unparsed text!! - not hash struct
-  #      - will get saved in db plus we need to generate md5 hash
-  #    - add filename e.g. ruby.ini|ruby.conf|ruby.yml as opt ??
-  #           or add config format as opt e.g. ini or yml?
-
-  def initialize( opts, config )
-    @opts    = opts
-    @config  = config
-  end
-
-  attr_reader :opts, :config
-
-  def run( arg )
-    arg = arg.downcase.gsub('.ini','').gsub('.yml','')  # remove file extension if present
-
-    update_for( arg )
-  end
-
-  def update_for( site_key )
-    ###################
-    # step 1) update subscriptions
-    subscriber = Subscriber.new
-
-    # pass along debug/verbose setting/switch
-    subscriber.debug = true    if opts.verbose?
-    subscriber.update_subscriptions_for( site_key, config )
-
-    ##############################
-    # step 2) update feeds
-    refresher = Refresher.new
-
-    # pass along debug/verbose setting/switch
-    refresher.debug = true    if opts.verbose?
-    refresher.update_feeds_for( site_key )
-  end # method run
-
-end # class Updater
-
-end # module Pluto

data/lib/pluto/version.rb

@@ -1,4 +0,0 @@
-
-module Pluto
-  VERSION = '1.0.1'
-end

data/test/helper.rb

@@ -1,18 +0,0 @@
-## $:.unshift(File.dirname(__FILE__))
-
-
-## minitest setup
-
-# require 'minitest/unit'
-require 'minitest/autorun'
-
-# include MiniTest::Unit  # lets us use TestCase instead of MiniTest::Unit::TestCase
-
-
-## our own code
-
-require 'pluto'
-
-
-LogUtils::Logger.root.level = :debug
-

data/test/test_helpers.rb

@@ -1,15 +0,0 @@
-# encoding: UTF-8
-
-###
-#  to run use
-#     ruby -I ./lib -I ./test test/test_rss.rb
-#  or better
-#     rake test
-
-require 'helper'
-
-class TestHelper < MiniTest::Unit::TestCase
-
-  ## add some tests; to be done
-
-end # class TestHelper