automatic 14.12.2 → 26.08

data/plugins/custom_feed/svn_log.rb

@@ -1,55 +1,96 @@
 # -*- coding: utf-8 -*-
-# Name::      Automatic::Plugin::CustomFeed::SVNLog
-# Author::    kzgs
-# Created::   Feb 29, 2012
-# Updated::   Mar  3, 2012
-# Copyright:: Copyright (c) 2012-2013 Automatic Ruby Developers.
-# License::   Licensed under the GNU GENERAL PUBLIC LICENSE, Version 3.0.
+# Name::        Automatic::Plugin::CustomFeed::SVNLog
+# Author:       kzgs
+# Source Code:: https://github.com/id774/automaticruby
+# License::     The GPL version 3, or LGPL version 3 (Dual License).
+# Contact::     idnanashi@gmail.com
+# Created::     Feb 29, 2012
+# Updated::     Aug 15, 2026
+# Copyright::   Copyright (c) 2012-2026 Automatic Ruby Developers.
 
+require 'rexml/document'
 require 'rss/maker'
+require 'time'
 
 module Automatic::Plugin
   class CustomFeedSVNLog
-    require 'xmlsimple'
+    DEFAULT_FETCH_ITEMS = 30
 
-    def initialize(config, pipeline=[])
-      @config = config
+    def initialize(config, pipeline = [])
+      @config   = config || {}
       @pipeline = pipeline
     end
 
     def run
-      revisions = XmlSimple.xml_in(`svn log #{svn_log_argument}`)["logentry"]
-      @pipeline << RSS::Maker.make("1.0") {|maker|
-        maker.channel.title = @config["title"] || ""
-        maker.channel.about = ""
-        maker.channel.description = ""
-        maker.channel.link = base_url
-        revisions.each {|rev|
-          item = maker.items.new_item
-          item.title = "#{rev["msg"]} by #{rev["author"]}"
-          item.link = base_url+"/!svn/bc/#{rev["revision"]}"
-          item.date = Time.parse(rev["date"][0])
-        }
-      }
-      return @pipeline
+      entries = revisions
+      if entries.empty?
+        # RSS 1.0 has no representation for a channel with no items, and a
+        # repository with no revisions in the window asked for is an ordinary
+        # answer rather than a failure.
+        Automatic::Log.puts('warn', "No revisions returned by svn log for #{base_url}")
+        return @pipeline
+      end
+
+      @pipeline << feed(entries)
+      @pipeline
     end
 
     private
 
-    def base_url
-      return @config['target'].gsub(/\/$/, "")
+    def feed(revisions)
+      RSS::Maker.make('1.0') do |maker|
+        maker.channel.title       = @config['title'].to_s
+        maker.channel.about       = ''
+        maker.channel.description = ''
+        maker.channel.link        = base_url
+
+        revisions.each do |revision|
+          item       = maker.items.new_item
+          item.title = "#{revision['msg']} by #{revision['author']}"
+          item.link  = "#{base_url}/!svn/bc/#{revision['revision']}"
+          item.date  = Time.parse(revision['date'])
+        end
+      end
+    end
+
+    # `svn log --xml` as REXML sees it. REXML is a runtime dependency of this
+    # framework already -- the OPML parser uses it -- so this plugin needs the
+    # svn command and no gem of its own.
+    def revisions
+      REXML::Document.new(svn_log).elements.to_a('/log/logentry').map do |entry|
+        {
+          'revision' => entry.attributes['revision'].to_s,
+          'author'   => text(entry, 'author'),
+          'msg'      => text(entry, 'msg'),
+          'date'     => text(entry, 'date')
+        }
+      end
     end
 
-    def svn_log_argument
-      return [
-        base_url,
-        "--xml",
-        "--limit=#{limit}"
-      ].join(" ")
+    def text(entry, name)
+      element = entry.elements[name]
+      element.nil? ? '' : element.text.to_s
+    end
+
+    # The command is run as an argument vector rather than through a shell, so
+    # a repository URL cannot become part of a command line. Point `target` at
+    # a repository you control regardless: svn itself will do what the URL
+    # tells it to.
+    def svn_log
+      output = IO.popen(['svn', 'log', base_url, '--xml', "--limit=#{limit}"],
+                        err: File::NULL, &:read)
+      raise "svn log failed for #{base_url}" unless $?.success?
+
+      output
+    end
+
+    def base_url
+      @base_url ||= @config['target'].to_s.sub(%r{/\z}, '')
     end
 
     def limit
-      return @config['fetch_items'] || 30
+      value = @config['fetch_items'].to_i
+      value.positive? ? value : DEFAULT_FETCH_ITEMS
     end
   end
 end

data/plugins/custom_feed/web.rb

@@ -0,0 +1,348 @@
+# -*- coding: utf-8 -*-
+# Name::        Automatic::Plugin::CustomFeed::Web
+# Description:: Build a feed from the article links of an HTML index page.
+# 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::     Aug 17, 2026
+# Updated::     Aug 17, 2026
+# Copyright::   Copyright (c) 2012-2026 Automatic Ruby Developers.
+#
+# One page in, one feed out. The pages named in the Recipe are fetched, their
+# article links are taken with CSS selectors, and each page becomes a feed of
+# what it currently lists. Nothing else is fetched: the links are not
+# followed, no article body is read, and no page beyond the ones named is
+# visited, so a run costs one request per site.
+#
+# It keeps no state of its own, deliberately. What was published last time is
+# StorePermalink's question, and the Recipe that answers it puts StorePermalink
+# after this plugin. See doc/PLUGINS.md section 6.2.
+
+require 'rss/maker'
+require 'set'
+require 'time'
+require 'uri'
+
+module Automatic::Plugin
+  class CustomFeedWeb
+    Automatic.require_optional('nokogiri', needed_by: 'CustomFeedWeb')
+
+    DEFAULT_FETCH_ITEMS = 100
+
+    # What an article link is, where the Recipe does not say. Every mode ends
+    # at an `<a href>`, because a permalink is what a feed item needs.
+    DEFAULT_LINK_SELECTOR = 'a[href]'
+
+    # A link in a page is written by whoever wrote the page. `mailto:`,
+    # `javascript:` and `file:` links are ordinary in a navigation bar and are
+    # not articles.
+    SCHEMES = %w[http https].freeze
+
+    # One article as the page presents it, before it becomes an item. Internal
+    # to this plugin: what leaves here is the pipeline value of section 3.4.
+    Candidate = Struct.new(:title, :url, :description, :date, keyword_init: true)
+
+    def initialize(config, pipeline = [])
+      @config   = config || {}
+      @pipeline = pipeline
+      @seen     = Set.new
+    end
+
+    def run
+      sites.each do |site|
+        feed = feed_for(site)
+        @pipeline << feed unless feed.nil?
+      end
+      @pipeline
+    end
+
+    private
+
+    # Every site, checked before anything is fetched.
+    #
+    # A Recipe this plugin cannot carry out -- a site that is not a mapping, a
+    # URL that cannot be fetched, a pattern that is not a regular expression,
+    # a selector combination that names no article -- is the operator's
+    # mistake, and it will be the same mistake after a retry and a wait. It is
+    # refused here, where no request has been made yet, rather than inside the
+    # retry loop, which is for a host that did not answer.
+    def sites
+      @sites ||= Array(@config['sites']).each { |site| validate(site) }
+    end
+
+    def validate(site)
+      unless site.is_a?(Hash)
+        raise ArgumentError,
+              'CustomFeedWeb takes a mapping with a url key for each site, ' \
+              "not #{site.inspect}"
+      end
+
+      source(site)
+      patterns(site, 'include')
+      patterns(site, 'exclude')
+      article_unit(site)
+    end
+
+    # The page URL as this plugin will fetch and resolve against it.
+    # Automatic::Http is what says which URLs those are.
+    def source(site)
+      Automatic::Http.uri(site['url'])
+    rescue ArgumentError, URI::InvalidURIError => e
+      raise ArgumentError, "CustomFeedWeb needs a url for each site: #{e.message}"
+    end
+
+    def patterns(site, key)
+      Array(site[key]).map { |pattern| Regexp.new(pattern.to_s) }
+    rescue RegexpError => e
+      raise ArgumentError,
+            "CustomFeedWeb was given an invalid #{key} pattern for " \
+            "#{site['url']}: #{e.message}"
+    end
+
+    # `title_selector`, `description_selector` and `date_selector` are read
+    # inside one article's node, and `item_selector` is what says where an
+    # article begins and ends. Without it there is no node to read them in,
+    # and a page of anchors cannot be divided into articles by guessing.
+    def article_unit(site)
+      return if presence(site['item_selector'])
+
+      named = %w[title_selector description_selector date_selector].
+              select { |key| presence(site[key]) }
+      return if named.empty?
+
+      raise ArgumentError,
+            "CustomFeedWeb needs item_selector to use #{named.join(', ')}: " \
+            "#{site['url']}"
+    end
+
+    def feed_for(site)
+      base     = source(site)
+      document = fetch(site)
+      return nil if document.nil?
+
+      articles = entries(document, site, base)
+      if articles.empty?
+        # A list page with nothing on it that this Recipe recognises is an
+        # ordinary answer rather than a failure, and an empty feed would only
+        # give the rest of the pipeline something to skip.
+        Automatic::Log.puts('warn', "No article links found on #{base}")
+        return nil
+      end
+
+      Automatic::Log.puts('info', "Web feed: #{articles.size} items from #{base}")
+      feed(site, document, base, articles)
+    end
+
+    # The page, or nil where it could not be read after its retries. One site
+    # that is down does not take the rest of the Recipe with it.
+    #
+    # The parser is given the stream rather than a decoded string, so that it
+    # reads the document's own meta charset instead of the encoding open-uri
+    # settled on. See doc/PLUGINS.md section 3.8.1.
+    def fetch(site)
+      url       = site['url']
+      retries   = 0
+      retry_max = @config['retry'].to_i
+      begin
+        Automatic::Log.puts('info', "Parsing Web page: #{url}")
+        document = Automatic::Http.open(url) { |io| Nokogiri::HTML(io) }
+        sleep(@config['interval'].to_i)
+        document
+      rescue StandardError => e
+        retries += 1
+        Automatic::Log.puts('error',
+                            "ErrorCount: #{retries}, Fault in fetching: #{url}, #{e.message}")
+        if retries > retry_max
+          Automatic::Log.puts('warn', "Skipping #{url}")
+          return nil
+        end
+
+        sleep(@config['interval'].to_i)
+        retry
+      end
+    end
+
+    # The candidates that survive, in the order the page lists them, up to
+    # `fetch_items`. A list page's own order is the only ordering information
+    # it carries, so nothing here sorts.
+    def entries(document, site, base)
+      includes = patterns(site, 'include')
+      excludes = patterns(site, 'exclude')
+      limit    = fetch_items(site)
+
+      candidates(document, site).each_with_object([]) do |candidate, kept|
+        next if candidate.title.empty?
+
+        url = permalink(candidate.url, base, site, includes, excludes)
+        next if url.nil?
+
+        candidate.url = url
+        kept << candidate
+        break kept if kept.size >= limit
+      end
+    end
+
+    # The three ways a page is read, and the only three: every anchor, the
+    # anchors a selector names, or an article node with its parts inside it.
+    def candidates(document, site)
+      item_selector = presence(site['item_selector'])
+      return anchors(document, site) if item_selector.nil?
+
+      document.css(item_selector).filter_map { |node| article(node, site) }
+    end
+
+    def anchors(document, site)
+      selector = presence(site['link_selector']) || DEFAULT_LINK_SELECTOR
+      document.css(selector).filter_map { |node|
+        next if node['href'].nil?
+
+        Candidate.new(title: normalize(node.text), url: node['href'], description: '')
+      }
+    end
+
+    def article(node, site)
+      link = node.at_css(presence(site['link_selector']) || DEFAULT_LINK_SELECTOR)
+      return nil if link.nil? || link['href'].nil?
+
+      Candidate.new(
+        title:       title(node, site, link),
+        url:         link['href'],
+        description: description(node, site),
+        date:        date(node, site)
+      )
+    end
+
+    # A `title_selector` that selects nothing in this particular article falls
+    # back to the link's own text rather than dropping the article: one entry
+    # laid out differently from the rest of a list is ordinary.
+    def title(node, site, link)
+      selector = presence(site['title_selector'])
+      found    = selector.nil? ? nil : node.at_css(selector)
+      normalize((found || link).text)
+    end
+
+    # The summary the list page prints, as text. Not the article: this plugin
+    # does not fetch one.
+    def description(node, site)
+      selector = presence(site['description_selector'])
+      return '' if selector.nil?
+
+      found = node.at_css(selector)
+      found.nil? ? '' : normalize(found.text)
+    end
+
+    # `<time datetime="2026-08-17T09:00:00+09:00">yesterday</time>` is the
+    # reason the attribute is preferred: it is written for a machine, and the
+    # text beside it is written for a reader.
+    def date(node, site)
+      selector = presence(site['date_selector'])
+      return nil if selector.nil?
+
+      found = node.at_css(selector)
+      return nil if found.nil?
+
+      published(found.name == 'time' && found['datetime'] ? found['datetime'] : found.text)
+    end
+
+    # A date that cannot be read costs the article its date and not its place
+    # in the feed. Nothing is substituted for it: the time this ran is when
+    # the page was fetched, which is not when the article was published.
+    def published(value)
+      Time.parse(value.to_s)
+    rescue ArgumentError => e
+      Automatic::Log.puts('warn', "Unreadable date #{value.to_s.strip.inspect}: #{e.message}")
+      nil
+    end
+
+    # The judgements a candidate URL passes, in this order: it is resolved
+    # against the page it was found on, then it is one this framework fetches,
+    # then it is not the page itself, then the host, then include, then
+    # exclude, and only what has survived all of them is recorded as seen.
+    def permalink(href, base, site, includes, excludes)
+      uri = absolute(href, base)
+      return nil if uri.nil? || !SCHEMES.include?(uri.scheme)
+
+      url = uri.to_s
+      return nil if url == base.to_s
+      return nil if same_host?(site) && !same_host_as?(uri, base)
+      return nil if includes.any? && includes.none? { |pattern| pattern.match?(url) }
+      return nil if excludes.any? { |pattern| pattern.match?(url) }
+
+      # Within one run only. Whether a URL was published last week is
+      # StorePermalink's record, not this plugin's.
+      @seen.add?(url).nil? ? nil : url
+    end
+
+    # Resolved against the page it was found on, so that `/articles/42`,
+    # `../42` and `//example.com/42` all become the URL a reader would follow.
+    # The fragment goes, because two links differing only in their anchor are
+    # one article. The query string stays, because `?id=42` is frequently the
+    # whole of what identifies one, and no canonical form is guessed.
+    def absolute(href, base)
+      uri = base.merge(href.to_s.strip)
+      uri.fragment = nil
+      uri
+    rescue URI::Error, ArgumentError
+      nil
+    end
+
+    def same_host?(site)
+      value = site['same_host']
+      value.nil? ? true : value
+    end
+
+    # An exact host match, and nothing cleverer. `www.example.com` and
+    # `blog.example.com` are one organisation and are not one site, and which
+    # of them a Recipe wants is the Recipe's to say.
+    def same_host_as?(uri, base)
+      uri.host.to_s.downcase == base.host.to_s.downcase
+    end
+
+    def fetch_items(site)
+      value = site['fetch_items'].to_i
+      value.positive? ? value : DEFAULT_FETCH_ITEMS
+    end
+
+    def feed(site, document, base, entries)
+      RSS::Maker.make('2.0') do |maker|
+        maker.channel.title       = channel_title(site, document, base)
+        maker.channel.link        = base.to_s
+        maker.channel.description = "Web page items from #{base}"
+        # The page's order is kept. RSS::Maker sorts its items by date when it
+        # is asked to, and an article the page listed first is first for a
+        # reason a date does not carry.
+        maker.items.do_sort = false
+
+        entries.each do |entry|
+          item             = maker.items.new_item
+          item.title       = entry.title
+          item.link        = entry.url
+          item.description = entry.description
+          item.date        = entry.date unless entry.date.nil?
+        end
+      end
+    end
+
+    # `name`, then what the page calls itself, then the host it came from.
+    def channel_title(site, document, base)
+      name = presence(site['name'])
+      return name unless name.nil?
+
+      title = normalize(document.title.to_s)
+      title.empty? ? base.host.to_s : title
+    end
+
+    # "  Ruby\n   4.0\t released  " is "Ruby 4.0 released". A title in a list
+    # page is laid out for a browser, and the line breaks and indentation of
+    # the markup are not part of it.
+    def normalize(text)
+      text.to_s.gsub(/[[:space:]]+/, ' ').strip
+    end
+
+    def presence(value)
+      string = value.to_s.strip
+      string.empty? ? nil : string
+    end
+  end
+end

data/plugins/filter/absolute_uri.rb

@@ -1,44 +1,60 @@
 # -*- coding: utf-8 -*-
-# Name::      Automatic::Plugin::Filter::AbsoluteURI
-# Author::    774 <http://id774.net>
-# Created::   Jun 20, 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::Filter::AbsoluteURI
+# 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::     Jun 20, 2012
+# Updated::     Aug 15, 2026
+# Copyright::   Copyright (c) 2012-2026 Automatic Ruby Developers.
 
 module Automatic::Plugin
   class FilterAbsoluteURI
+    require 'uri'
 
-    def initialize(config, pipeline=[])
-      @config = config
+    # Anything already carrying a scheme is left alone. The earlier spelling
+    # of this test matched `http://` only, so an https link was treated as
+    # relative and had the base prepended to it.
+    ABSOLUTE = %r{\A[a-zA-Z][a-zA-Z0-9+.\-]*://}
+
+    # URI::Parser became the RFC 3986 parser in Ruby 3.4, which reports #escape
+    # as obsolete. The RFC 2396 parser is what this was always reaching and is
+    # spelled the same way on every supported Ruby.
+    ESCAPER = URI::RFC2396_Parser.new
+
+    def initialize(config, pipeline = [])
+      @config   = config || {}
       @pipeline = pipeline
+      @base     = base_url
     end
 
     def run
-      @return_feeds = []
-      @pipeline.each {|feeds|
-        unless feeds.nil?
-          feeds.items.each {|feed|
-            feed.link = rewrite(feed.link) unless feed.link.nil?
-          }
-          @return_feeds << feeds
+      @pipeline.each_with_object([]) do |feeds, returned|
+        next if feeds.nil?
+
+        feeds.items.each do |item|
+          item.link = rewrite(item.link) unless item.link.nil?
         end
-      }
-      @return_feeds
+        returned << feeds
+      end
     end
 
     private
-    def rewrite(string)
-      if /^http:\/\/.*$/ =~ string
-        return string
-      end
 
-      if /[^\/]$/ =~ @config['url']
-        @config['url'] = @config['url'] + '/'
-      end
-      string = @config['url'] + string.sub(/^\./,'').sub(/^\//,'')
-      string = URI::Parser.new.escape(string)
-      return string
+    # Read once, in the constructor: the earlier version appended the trailing
+    # slash to the Recipe's own config mapping, which is the plugin's input
+    # rather than its state.
+    def base_url
+      url = @config['url'].to_s
+      return url if url.empty? || url.end_with?('/')
+
+      "#{url}/"
+    end
+
+    def rewrite(link)
+      return link if ABSOLUTE.match?(link)
+
+      ESCAPER.escape(@base + link.sub(/\A\./, '').sub(%r{\A/}, ''))
     end
   end
 end

data/plugins/filter/accept.rb

@@ -1,62 +1,55 @@
 # -*- coding: utf-8 -*-
-# Name::      Automatic::Plugin::Filter::Accept
-# Author::    soramugi <http://soramugi.net>
-#             774 <http://id774.net>
-# Created::   Jun  4, 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::Filter::Accept
+# 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::     Jun  4, 2013
+# Updated::     Aug 15, 2026
+# Copyright::   Copyright (c) 2012-2026 Automatic Ruby Developers.
 
 module Automatic::Plugin
   class FilterAccept
-    def initialize(config, pipeline=[])
-      @config   = config
+    FIELDS = %i[title link description].freeze
+
+    def initialize(config, pipeline = [])
+      @config   = config || {}
       @pipeline = pipeline
     end
 
+    # The complement of FilterIgnore: keeps only the items that match. Matching
+    # is a substring test, so an empty keyword matches everything.
     def run
-      @return_feeds = []
-      @pipeline.each {|feeds|
-        new_feeds = []
-        unless feeds.nil?
-          feeds.items.each {|items|
-            new_feeds << items if contain(items) == true
-          }
-        end
-        @return_feeds << Automatic::FeedMaker.create_pipeline(new_feeds) if new_feeds.length > 0
-      }
-      @return_feeds
+      @pipeline.each_with_object([]) do |feeds, returned|
+        kept = feeds.nil? ? [] : feeds.items.select { |item| contain?(item) }
+        returned << Automatic::FeedMaker.create_pipeline(kept) unless kept.empty?
+      end
     end
 
     private
 
-    def contain(items)
-      detection = false
-      unless @config['title'].nil?
-        @config['title'].each {|e|
-          if items.title.include?(e.chomp)
-            detection = true
-            Automatic::Log.puts("info", "Contain by title: #{items.link}")
-          end
-        }
-      end
-      unless @config['link'].nil?
-        @config['link'].each {|e|
-          if items.link.include?(e.chomp)
-            detection = true
-            Automatic::Log.puts("info", "Contain by link: #{items.link}")
-          end
-        }
+    def contain?(item)
+      FIELDS.any? do |field|
+        Array(@config[field.to_s]).any? do |keyword|
+          matched?(item, field, keyword.to_s.chomp)
+        end
       end
-      unless @config['description'].nil?
-        @config['description'].each {|e|
-          if items.description.include?(e.chomp)
-            detection = true
-            Automatic::Log.puts("info", "Contain by description: #{items.link}")
-          end
-        }
+    end
+
+    # An item whose field is missing is not matched, and says so. The earlier
+    # version called #include? on it and ended the run with a NoMethodError,
+    # which is not what the complementary filter does with the same item.
+    def matched?(item, field, keyword)
+      value = item.send(field)
+      unless value.respond_to?(:include?)
+        Automatic::Log.puts('warn', "Invalid feed detected in accept process with #{field}")
+        return false
       end
-      detection
+
+      return false unless value.include?(keyword)
+
+      Automatic::Log.puts('info', "Contain by #{field}: #{item.link}")
+      true
     end
   end
 end