automatic 14.12.2 → 26.08

data/plugins/subscription/link.rb

@@ -1,47 +1,46 @@
 # -*- coding: utf-8 -*-
-# Name::      Automatic::Plugin::Subscription::Link
-# Author::    774 <http://id774.net>
-# Created::   Sep 18, 2012
-# Updated::   Oct 29, 2014
-# Copyright:: Copyright (c) 2012-2014 Automatic Ruby Developers.
-# License::   Licensed under the GNU GENERAL PUBLIC LICENSE, Version 3.0.
+# Name::        Automatic::Plugin::Subscription::Link
+# Author:       id774 (More info: http://id774.net)
+# Source Code:: https://github.com/id774/automaticruby
+# License::     The GPL version 3, or LGPL version 3 (Dual License).
+# Contact::     idnanashi@gmail.com
+# Created::     Sep 18, 2012
+# Updated::     Aug 15, 2026
+# Copyright::   Copyright (c) 2012-2026 Automatic Ruby Developers.
 
 module Automatic::Plugin
   class SubscriptionLink
-    require 'open-uri'
-    require 'rss'
-
-    def initialize(config, pipeline=[])
-      @config = config
+    def initialize(config, pipeline = [])
+      @config   = config || {}
       @pipeline = pipeline
     end
 
+    # Returns only what it fetched, discarding any incoming pipeline.
     def run
-      @return_feeds = []
-      @config['urls'].each {|url|
-        retries = 0
-        retry_max = @config['retry'].to_i || 0
-        begin
-          create_rss(URI::Parser.new.escape(url))
-        rescue
-          retries += 1
-          Automatic::Log.puts("error", "ErrorCount: #{retries}, Fault in parsing: #{url}")
-          sleep ||= @config['interval'].to_i
-          retry if retries <= retry_max
-        end
-      }
-      @return_feeds
+      Array(@config['urls']).each_with_object([]) do |url, feeds|
+        rss = fetch(url)
+        feeds << rss unless rss.nil?
+      end
     end
 
     private
 
-    def create_rss(url)
-      Automatic::Log.puts("info", "Parsing Link: #{url}")
-      html = open(url).read
-      unless html.nil?
-        rss = Automatic::FeedParser.parse_html(html)
-        sleep ||= @config['interval'].to_i
-        @return_feeds << rss
+    def fetch(url)
+      retries   = 0
+      retry_max = @config['retry'].to_i
+      begin
+        Automatic::Log.puts('info', "Parsing Link: #{url}")
+        rss = Automatic::FeedParser.parse_html(Automatic::Http.read(url))
+        sleep(@config['interval'].to_i)
+        rss
+      rescue StandardError => e
+        retries += 1
+        Automatic::Log.puts('error',
+                            "ErrorCount: #{retries}, Fault in parsing: #{url}, #{e.message}")
+        return nil if retries > retry_max
+
+        sleep(@config['interval'].to_i)
+        retry
       end
     end
   end

data/plugins/subscription/text.rb

@@ -1,67 +1,53 @@
 # -*- coding: utf-8 -*-
-# Name::      Automatic::Plugin::Subscription::Text
-# Author::    soramugi <http://soramugi.net>
-#             774 <http://id774.net>
-# Created::   May  6, 2013
-# Updated::   Feb 21, 2014
-# Copyright:: Copyright (c) 2012-2014 Automatic Ruby Developers.
-# License::   Licensed under the GNU GENERAL PUBLIC LICENSE, Version 3.0.
+# Name::        Automatic::Plugin::Subscription::Text
+# Author:       soramugi (More info: http://soramugi.net)
+# Source Code:: https://github.com/id774/automaticruby
+# License::     The GPL version 3, or LGPL version 3 (Dual License).
+# Contact::     idnanashi@gmail.com
+# Created::     May  6, 2013
+# Updated::     Aug 15, 2026
+# Copyright::   Copyright (c) 2012-2026 Automatic Ruby Developers.
 
 module Automatic::Plugin
   class SubscriptionText
-    def initialize(config, pipeline=[])
-      @config   = config
+    # Columns of a TSV row, in order. A row with fewer columns leaves the rest
+    # unset, which is what makes a one-column file of titles a valid input.
+    COLUMNS = %w[title url description author comments].freeze
+
+    def initialize(config, pipeline = [])
+      @config   = config || {}
       @pipeline = pipeline
-      @return_feeds = []
     end
 
+    # Reaches no network, which is what makes this the plugin to test a
+    # Recipe's later half with. Any combination of the four keys may be given.
     def run
-      create_feed
-      @pipeline << Automatic::FeedMaker.create_pipeline(@return_feeds) if @return_feeds.length > 0
+      items = titles + urls + feeds + files
+      @pipeline << Automatic::FeedMaker.create_pipeline(items) unless items.empty?
       @pipeline
     end
 
     private
 
-    def create_feed
-      unless @config.nil?
-        @dummyfeeds = []
-        unless @config['titles'].nil?
-          @config['titles'].each {|title|
-            feed = {}
-            feed['title'] = title
-            @return_feeds << Automatic::FeedMaker.generate_feed(feed)
-          }
-        end
+    def titles
+      Array(@config['titles']).map { |title| Automatic::FeedMaker.generate_feed('title' => title) }
+    end
 
-        unless @config['urls'].nil?
-          @config['urls'].each {|url|
-            feed = {}
-            feed['url'] = url
-            @return_feeds << Automatic::FeedMaker.generate_feed(feed)
-          }
-        end
+    def urls
+      Array(@config['urls']).map { |url| Automatic::FeedMaker.generate_feed('url' => url) }
+    end
 
-        unless @config['feeds'].nil?
-          @config['feeds'].each {|feed|
-            @return_feeds << Automatic::FeedMaker.generate_feed(feed)
-          }
-        end
+    def feeds
+      Array(@config['feeds']).map { |feed| Automatic::FeedMaker.generate_feed(feed) }
+    end
 
-        unless @config['files'].nil?
-          @config['files'].each {|f|
-            open(File.expand_path(f)) do |file|
-              file.each_line do |line|
-                feed = {}
-                feed['title'], feed['url'], feed['description'], feed['author'],
-                feed['comments'] = line.force_encoding("utf-8").strip.split("\t")
-                @return_feeds << Automatic::FeedMaker.generate_feed(feed)
-              end
-            end
-          }
+    # Tab separated, read as UTF-8, and `~` expanded.
+    def files
+      Array(@config['files']).flat_map do |path|
+        File.foreach(File.expand_path(path), encoding: 'UTF-8').map do |line|
+          Automatic::FeedMaker.generate_feed(COLUMNS.zip(line.strip.split("\t")).to_h)
         end
       end
     end
-
   end
 end

data/plugins/subscription/tumblr.rb

@@ -1,59 +1,70 @@
 # -*- coding: utf-8 -*-
-# Name::      Automatic::Plugin::Subscription::Tumblr
-# Author::    774 <http://id774.net>
-# Created::   Oct 16, 2012
-# Updated::   Feb 21, 2014
-# Copyright:: Copyright (c) 2012-2014 Automatic Ruby Developers.
-# License::   Licensed under the GNU GENERAL PUBLIC LICENSE, Version 3.0.
+# Name::        Automatic::Plugin::Subscription::Tumblr
+# Author:       id774 (More info: http://id774.net)
+# Source Code:: https://github.com/id774/automaticruby
+# License::     The GPL version 3, or LGPL version 3 (Dual License).
+# Contact::     idnanashi@gmail.com
+# Created::     Oct 16, 2012
+# Updated::     Aug 15, 2026
+# Copyright::   Copyright (c) 2012-2026 Automatic Ruby Developers.
 
 module Automatic::Plugin
   class SubscriptionTumblr
-    require 'open-uri'
-
-    def initialize(config, pipeline=[])
-      @config = config
+    def initialize(config, pipeline = [])
+      @config   = config || {}
       @pipeline = pipeline
     end
 
+    # Reads HTML written for a browser, so what it finds depends on the theme
+    # a given blog uses. Verify against the blog you mean to follow before
+    # putting it in cron, and set `interval`.
     def run
-      @return_feeds = []
-      @config['urls'].each {|url|
-        retries = 0
-        retry_max = @config['retry'].to_i || 0
-        begin
-          create_rss(url)
-          unless @config['pages'].nil?
-            @config['pages'].times {|i|
-              if i > 0
-                old_url = url + "/page/" + (i+1).to_s
-                create_rss(old_url)
-              end
-            }
-          end
-        rescue
-          retries += 1
-          Automatic::Log.puts("error", "ErrorCount: #{retries}, Fault in parsing: #{url}")
-          sleep ||= @config['interval'].to_i
-          retry if retries <= retry_max
+      Array(@config['urls']).each_with_object([]) do |url, feeds|
+        pages(url).each do |page|
+          rss = fetch(page, url)
+          feeds << rss unless rss.nil?
         end
-      }
-      @return_feeds
+      end
     end
 
     private
-    def create_rss(url)
-      Automatic::Log.puts("info", "Parsing Tumblr: #{url}")
-      html = open(url).read
-      unless html.nil?
-        uri = URI.parse(url)
-        rss = Automatic::FeedParser.parse_html(html)
-        rss.items.each {|item|
-           unless item.link =~ Regexp.new(uri.host)
-             item.link = nil
-           end
-        }
-        sleep ||= @config['interval'].to_i
-        @return_feeds << rss
+
+    # The blog's own page, then /page/2 and onward.
+    def pages(url)
+      count = @config['pages'].to_i
+      return [url] if count < 2
+
+      [url] + (2..count).map { |number| "#{url}/page/#{number}" }
+    end
+
+    def fetch(url, blog_url)
+      retries   = 0
+      retry_max = @config['retry'].to_i
+      begin
+        Automatic::Log.puts('info', "Parsing Tumblr: #{url}")
+        rss = Automatic::FeedParser.parse_html(Automatic::Http.read(url))
+        drop_offsite_links(rss, blog_url)
+        sleep(@config['interval'].to_i)
+        rss
+      rescue StandardError => e
+        retries += 1
+        Automatic::Log.puts('error',
+                            "ErrorCount: #{retries}, Fault in parsing: #{url}, #{e.message}")
+        return nil if retries > retry_max
+
+        sleep(@config['interval'].to_i)
+        retry
+      end
+    end
+
+    # A theme's page carries the blog's own posts and a great deal else. A
+    # link that leaves the blog's host is blanked rather than removed, which
+    # is the pipeline's way of saying "not applicable"; the plugins after this
+    # one skip an item whose link is nil.
+    def drop_offsite_links(rss, blog_url)
+      host = Automatic::Http.uri(blog_url).host.to_s
+      rss.items.each do |item|
+        item.link = nil unless item.link.to_s.include?(host)
       end
     end
   end

data/plugins/subscription/xml.rb

@@ -1,53 +1,57 @@
 # -*- coding: utf-8 -*-
-# Name::      Automatic::Plugin::Subscription::Xml
-# Author::    774 <http://id774.net>
-# Created::   Jul 12, 2013
-# Updated::   Oct 29, 2014
-# Copyright:: Copyright (c) 2012-2014 Automatic Ruby Developers.
-# License::   Licensed under the GNU GENERAL PUBLIC LICENSE, Version 3.0.
+# Name::        Automatic::Plugin::Subscription::Xml
+# Author:       id774 (More info: http://id774.net)
+# Source Code:: https://github.com/id774/automaticruby
+# License::     The GPL version 3, or LGPL version 3 (Dual License).
+# Contact::     idnanashi@gmail.com
+# Created::     Jul 12, 2013
+# Updated::     Aug 15, 2026
+# Copyright::   Copyright (c) 2012-2026 Automatic Ruby Developers.
 
 module Automatic::Plugin
   class SubscriptionXml
-    require 'open-uri'
-    require 'active_support'
-    require 'active_support/core_ext'
-    require 'active_support/deprecation'
-    require 'rss'
+    require 'active_support/core_ext/hash/conversions'
+    require 'json'
 
-    def initialize(config, pipeline=[])
-      @config = config
+    def initialize(config, pipeline = [])
+      @config   = config || {}
       @pipeline = pipeline
     end
 
     def run
-      @return_feeds = []
-      @config['urls'].each {|url|
-        retries = 0
-        retry_max = @config['retry'].to_i || 0
-        begin
-          create_rss(URI::Parser.new.escape(url))
-        rescue
-          retries += 1
-          Automatic::Log.puts("error", "ErrorCount: #{retries}, Fault in parsing: #{url}")
-          sleep ||= @config['interval'].to_i
-          retry if retries <= retry_max
-        end
-      }
-      @return_feeds
+      Array(@config['urls']).each_with_object([]) do |url, feeds|
+        rss = fetch(url)
+        feeds << rss unless rss.nil?
+      end
     end
 
     private
 
-    def create_rss(url)
-      Automatic::Log.puts("info", "Parsing XML: #{url}")
-      hash = Hash.from_xml(open(url).read)
-      json = hash.to_json
-      data = ActiveSupport::JSON.decode(json)
-      unless data.nil?
-        rss = Automatic::FeedMaker.content_provide(url, data)
-        sleep ||= @config['interval'].to_i
-        @return_feeds << rss
+    def fetch(url)
+      retries   = 0
+      retry_max = @config['retry'].to_i
+      begin
+        Automatic::Log.puts('info', "Parsing XML: #{url}")
+        rss = Automatic::FeedMaker.content_provide(url, document(url))
+        sleep(@config['interval'].to_i)
+        rss
+      rescue StandardError => e
+        retries += 1
+        Automatic::Log.puts('error',
+                            "ErrorCount: #{retries}, Fault in parsing: #{url}, #{e.message}")
+        return nil if retries > retry_max
+
+        sleep(@config['interval'].to_i)
+        retry
       end
     end
+
+    # The document as plain hashes, arrays and strings. The round trip through
+    # JSON is what flattens what Hash.from_xml returns -- dates, times and
+    # ActiveSupport's own string subclasses -- into the values a consumer such
+    # as ProvideFluentd can serialize.
+    def document(url)
+      JSON.parse(Hash.from_xml(Automatic::Http.read(url)).to_json)
+    end
   end
 end