html-pipeline 2.14.3 → 3.0.2

data/lib/html/pipeline/@team_mention_filter.rb

@@ -1,99 +0,0 @@
-# frozen_string_literal: true
-
-require 'set'
-
-module HTML
-  class Pipeline
-    # HTML filter that replaces @org/team mentions with links. Mentions within
-    # <pre>, <code>, <a>, <style>, and <script> elements are ignored.
-    #
-    # Context options:
-    #   :base_url - Used to construct links to team profile pages for each
-    #               mention.
-    #   :team_pattern - Used to provide a custom regular expression to
-    #                       identify team names
-    #
-    class TeamMentionFilter < Filter
-      # Public: Find @org/team mentions in text.  See
-      # TeamMentionFilter#team_mention_link_filter.
-      #
-      #   TeamMentionFilter.mentioned_teams_in(text) do |match, org, team|
-      #     "<a href=...>#{team}</a>"
-      #   end
-      #
-      # text - String text to search.
-      #
-      # Yields the String match, org name, and team name.  The yield's
-      # return replaces the match in the original text.
-      #
-      # Returns a String replaced with the return of the block.
-      def self.mentioned_teams_in(text, team_pattern = TeamPattern)
-        text.gsub team_pattern do |match|
-          org = $1
-          team = $2
-          yield match, org, team
-        end
-      end
-
-      # Default pattern used to extract team names from text. The value can be
-      # overridden by providing the team_pattern variable in the context. To
-      # properly link the mention, should be in the format of /@(1)\/(2)/.
-      TeamPattern = /
-        (?<=^|\W)                  # beginning of string or non-word char
-        @([a-z0-9][a-z0-9-]*)      # @organization
-          \/                       # dividing slash
-          ([a-z0-9][a-z0-9\-_]*)   # team
-          \b
-      /ix
-
-      # Don't look for mentions in text nodes that are children of these elements
-      IGNORE_PARENTS = %w[pre code a style script].to_set
-
-      def call
-        result[:mentioned_teams] ||= []
-
-        doc.search('.//text()').each do |node|
-          content = node.to_html
-          next unless content.include?('@')
-          next if has_ancestor?(node, IGNORE_PARENTS)
-          html = mention_link_filter(content, base_url, team_pattern)
-          next if html == content
-          node.replace(html)
-        end
-        doc
-      end
-
-      def team_pattern
-        context[:team_pattern] || TeamPattern
-      end
-
-      # Replace @org/team mentions in text with links to the mentioned team's
-      # page.
-      #
-      # text      - String text to replace @mention team names in.
-      # base_url  - The base URL used to construct team page URLs.
-      # team_pattern  - Regular expression used to identify teams in text
-      #
-      # Returns a string with @team mentions replaced with links. All links have a
-      # 'team-mention' class name attached for styling.
-      def mention_link_filter(text, _base_url = '/', team_pattern = TeamPattern)
-        self.class.mentioned_teams_in(text, team_pattern) do |match, org, team|
-          link = link_to_mentioned_team(org, team)
-
-          link ? match.sub("@#{org}/#{team}", link) : match
-        end
-      end
-
-      def link_to_mentioned_team(org, team)
-        result[:mentioned_teams] |= [team]
-
-        url = base_url.dup
-        url << '/' unless url =~ /[\/~]\z/
-        
-        "<a href='#{url << org}/#{team}' class='team-mention'>" \
-          "@#{org}/#{team}" \
-          '</a>'
-      end
-    end
-  end
-end

data/lib/html/pipeline/absolute_source_filter.rb

@@ -1,52 +0,0 @@
-# frozen_string_literal: true
-
-require 'uri'
-
-module HTML
-  class Pipeline
-    class AbsoluteSourceFilter < Filter
-      # HTML Filter for replacing relative and root relative image URLs with
-      # fully qualified URLs
-      #
-      # This is useful if an image is root relative but should really be going
-      # through a cdn, or if the content for the page assumes the host is known
-      # i.e. scraped webpages and some RSS feeds.
-      #
-      # Context options:
-      #   :image_base_url - Base URL for image host for root relative src.
-      #   :image_subpage_url - For relative src.
-      #
-      # This filter does not write additional information to the context.
-      # This filter would need to be run before CamoFilter.
-      def call
-        doc.search('img').each do |element|
-          next if element['src'].nil? || element['src'].empty?
-          src = element['src'].strip
-          next if src.start_with? 'http'
-          base = if src.start_with? '/'
-                   image_base_url
-                 else
-                   image_subpage_url
-                 end
-
-          begin
-            element['src'] = URI.join(base, src).to_s
-          rescue Exception
-            next
-          end
-        end
-        doc
-      end
-
-      # Private: the base url you want to use
-      def image_base_url
-        context[:image_base_url] || raise("Missing context :image_base_url for #{self.class.name}")
-      end
-
-      # Private: the relative url you want to use
-      def image_subpage_url
-        context[:image_subpage_url] || raise("Missing context :image_subpage_url for #{self.class.name}")
-      end
-    end
-  end
-end

data/lib/html/pipeline/autolink_filter.rb

@@ -1,34 +0,0 @@
-# frozen_string_literal: true
-
-HTML::Pipeline.require_dependency('rinku', 'AutolinkFilter')
-
-module HTML
-  class Pipeline
-    # HTML Filter for auto_linking urls in HTML.
-    #
-    # Context options:
-    #   :autolink  - boolean whether to autolink urls
-    #   :link_mode - :all, :urls or :email_addresses
-    #   :link_attr - HTML attributes for the link that will be generated
-    #   :skip_tags - HTML tags inside which autolinking will be skipped.
-    #                See Rinku.skip_tags
-    #   :flags     - additional Rinku flags. See https://github.com/vmg/rinku
-    #
-    # This filter does not write additional information to the context.
-    class AutolinkFilter < Filter
-      def call
-        return html if context[:autolink] == false
-
-        skip_tags = context[:skip_tags]
-        flags = 0
-        flags |= context[:flags] if context[:flags]
-
-        Rinku.auto_link(html, link_mode, context[:link_attr], skip_tags, flags)
-      end
-
-      def link_mode
-        context[:link_mode] || :urls
-      end
-    end
-  end
-end

data/lib/html/pipeline/body_content.rb

@@ -1,44 +0,0 @@
-# frozen_string_literal: true
-
-module HTML
-  class Pipeline
-    # Public: Runs a String of content through an HTML processing pipeline,
-    # providing easy access to a generated DocumentFragment.
-    class BodyContent
-      attr_reader :result
-
-      # Public: Initialize a BodyContent.
-      #
-      # body     - A String body.
-      # context  - A Hash of context options for the filters.
-      # pipeline - A HTML::Pipeline object with one or more Filters.
-      def initialize(body, context, pipeline)
-        @body = body
-        @context = context
-        @pipeline = pipeline
-      end
-
-      # Public: Gets the memoized result of the body content as it passed through
-      # the Pipeline.
-      #
-      # Returns a Hash, or something similar as defined by @pipeline.result_class.
-      def result
-        @result ||= @pipeline.call @body, @context
-      end
-
-      # Public: Gets the updated body from the Pipeline result.
-      #
-      # Returns a String or DocumentFragment.
-      def output
-        @output ||= result[:output]
-      end
-
-      # Public: Parses the output into a DocumentFragment.
-      #
-      # Returns a DocumentFragment.
-      def document
-        @document ||= HTML::Pipeline.parse output
-      end
-    end
-  end
-end

data/lib/html/pipeline/camo_filter.rb

@@ -1,105 +0,0 @@
-# frozen_string_literal: true
-
-require 'openssl'
-require 'uri'
-
-module HTML
-  class Pipeline
-    # HTML Filter for replacing http image URLs with camo versions. See:
-    #
-    # https://github.com/atmos/camo
-    #
-    # All images provided in user content should be run through this
-    # filter so that http image sources do not cause mixed-content warnings
-    # in browser clients.
-    #
-    # Context options:
-    #   :asset_proxy (required) - Base URL for constructed asset proxy URLs.
-    #   :asset_proxy_secret_key (required) - The shared secret used to encode URLs.
-    #   :asset_proxy_allowlist - Array of host Strings or Regexps to skip
-    #                            src rewriting.
-    #
-    # This filter does not write additional information to the context.
-    class CamoFilter < Filter
-      # Hijacks images in the markup provided, replacing them with URLs that
-      # go through the github asset proxy.
-      def call
-        return doc unless asset_proxy_enabled?
-
-        doc.search('img').each do |element|
-          original_src = element['src']
-          next unless original_src
-
-          begin
-            uri = URI.parse(original_src)
-          rescue Exception
-            next
-          end
-
-          next if uri.host.nil?
-          next if asset_host_allowed?(uri.host)
-
-          element['src'] = asset_proxy_url(original_src)
-          element['data-canonical-src'] = original_src
-        end
-        doc
-      end
-
-      # Implementation of validate hook.
-      # Errors should raise exceptions or use an existing validator.
-      def validate
-        needs :asset_proxy, :asset_proxy_secret_key
-      end
-
-      # The camouflaged URL for a given image URL.
-      def asset_proxy_url(url)
-        "#{asset_proxy_host}/#{asset_url_hash(url)}/#{hexencode(url)}"
-      end
-
-      # Private: calculate the HMAC digest for a image source URL.
-      def asset_url_hash(url)
-        OpenSSL::HMAC.hexdigest('sha1', asset_proxy_secret_key, url)
-      end
-
-      # Private: Return true if asset proxy filter should be enabled
-      def asset_proxy_enabled?
-        !context[:disable_asset_proxy]
-      end
-
-      # Private: the host to use for generated asset proxied URLs.
-      def asset_proxy_host
-        context[:asset_proxy]
-      end
-
-      def asset_proxy_secret_key
-        context[:asset_proxy_secret_key]
-      end
-
-      def asset_proxy_whitelist
-        warn "[DEPRECATION] 'asset_proxy_whitelist' is deprecated. Please use 'asset_proxy_allowlist' instead."
-        asset_proxy_allowlist
-      end
-
-      def asset_proxy_allowlist
-        context[:asset_proxy_allowlist] || context[:asset_proxy_whitelist] || []
-      end
-
-      def asset_host_whitelisted?(host)
-        warn "[DEPRECATION] 'asset_host_whitelisted?' is deprecated. Please use 'asset_host_allowed?' instead."
-        asset_host_allowed?(host)
-      end
-
-      def asset_host_allowed?(host)
-        asset_proxy_allowlist.any? do |test|
-          test.is_a?(String) ? host == test : test.match(host)
-        end
-      end
-
-      # Private: helper to hexencode a string. Each byte ends up encoded into
-      # two characters, zero padded value in the range [0-9a-f].
-      def hexencode(str)
-        str.unpack('H*').first
-      end
-    end
-  end
-end

data/lib/html/pipeline/email_reply_filter.rb

@@ -1,69 +0,0 @@
-# frozen_string_literal: true
-
-HTML::Pipeline.require_dependency('escape_utils', 'EmailReplyFilter')
-HTML::Pipeline.require_dependency('email_reply_parser', 'EmailReplyFilter')
-
-module HTML
-  class Pipeline
-    # HTML Filter that converts email reply text into an HTML DocumentFragment.
-    # It must be used as the first filter in a pipeline.
-    #
-    # Context options:
-    #   None
-    #
-    # This filter does not write any additional information to the context hash.
-    class EmailReplyFilter < TextFilter
-      include EscapeUtils
-
-      EMAIL_HIDDEN_HEADER    = %(<span class="email-hidden-toggle"><a href="#">&hellip;</a></span><div class="email-hidden-reply" style="display:none">).freeze
-      EMAIL_QUOTED_HEADER    = %(<div class="email-quoted-reply">).freeze
-      EMAIL_SIGNATURE_HEADER = %(<div class="email-signature-reply">).freeze
-      EMAIL_FRAGMENT_HEADER  = %(<div class="email-fragment">).freeze
-      EMAIL_HEADER_END       = '</div>'.freeze
-      EMAIL_REGEX            = /[^@\s.][^@\s]*@\[?[a-z0-9.-]+\]?/
-      HIDDEN_EMAIL_PATTERN   = '***@***.***'.freeze
-
-      # Scans an email body to determine which bits are quoted and which should
-      # be hidden. EmailReplyParser is used to split the comment into an Array
-      # of quoted or unquoted Blocks. Now, we loop through them and attempt to
-      # add <div> tags around them so we can hide the hidden blocks, and style
-      # the quoted blocks differently. Since multiple blocks may be hidden, be
-      # sure to keep the "email-hidden-reply" <div>s around "email-quoted-reply"
-      # <div> tags. Call this on each comment of a visible thread in the order
-      # that they are displayed. Note: all comments are processed so we can
-      # maintain a Set of SHAs of paragraphs. Only plaintext comments skip the
-      # markdown step.
-      #
-      # Returns the email comment HTML as a String
-      def call
-        found_hidden = nil
-        paragraphs = EmailReplyParser.read(text.dup).fragments.map do |fragment|
-          pieces = [CGI.escapeHTML(fragment.to_s.strip).gsub(/^\s*(>|&gt;)/, '')]
-
-          if fragment.quoted?
-            if context[:hide_quoted_email_addresses]
-              pieces.map! do |piece|
-                piece.gsub(EMAIL_REGEX, HIDDEN_EMAIL_PATTERN)
-              end
-            end
-            pieces.unshift EMAIL_QUOTED_HEADER
-            pieces << EMAIL_HEADER_END
-          elsif fragment.signature?
-            pieces.unshift EMAIL_SIGNATURE_HEADER
-            pieces << EMAIL_HEADER_END
-          else
-            pieces.unshift EMAIL_FRAGMENT_HEADER
-            pieces << EMAIL_HEADER_END
-          end
-          if fragment.hidden? && !found_hidden
-            found_hidden = true
-            pieces.unshift EMAIL_HIDDEN_HEADER
-          end
-          pieces.join
-        end
-        paragraphs << EMAIL_HEADER_END if found_hidden
-        paragraphs.join("\n")
-      end
-    end
-  end
-end

data/lib/html/pipeline/filter.rb

@@ -1,165 +0,0 @@
-# frozen_string_literal: true
-
-module HTML
-  class Pipeline
-    # Base class for user content HTML filters. Each filter takes an
-    # HTML string or Nokogiri::HTML::DocumentFragment, performs
-    # modifications and/or writes information to the result hash. Filters must
-    # return a DocumentFragment (typically the same instance provided to the call
-    # method) or a String with HTML markup.
-    #
-    # Example filter that replaces all images with trollface:
-    #
-    #   class FuuuFilter < HTML::Pipeline::Filter
-    #     def call
-    #       doc.search('img').each do |img|
-    #         img['src'] = "http://paradoxdgn.com/junk/avatars/trollface.jpg"
-    #       end
-    #     end
-    #   end
-    #
-    # The context Hash passes options to filters and should not be changed in
-    # place.  A Result Hash allows filters to make extracted information
-    # available to the caller and is mutable.
-    #
-    # Common context options:
-    #   :base_url   - The site's base URL
-    #   :repository - A Repository providing context for the HTML being processed
-    #
-    # Each filter may define additional options and output values. See the class
-    # docs for more info.
-    class Filter
-      class InvalidDocumentException < StandardError; end
-
-      def initialize(doc, context = nil, result = nil)
-        if doc.is_a?(String)
-          @html = doc.to_str
-          @doc = nil
-        else
-          @doc = doc
-          @html = nil
-        end
-        @context = context || {}
-        @result = result || {}
-        validate
-      end
-
-      # Public: Returns a simple Hash used to pass extra information into filters
-      # and also to allow filters to make extracted information available to the
-      # caller.
-      attr_reader :context
-
-      # Public: Returns a Hash used to allow filters to pass back information
-      # to callers of the various Pipelines.  This can be used for
-      # #mentioned_users, for example.
-      attr_reader :result
-
-      # The Nokogiri::HTML::DocumentFragment to be manipulated. If the filter was
-      # provided a String, parse into a DocumentFragment the first time this
-      # method is called.
-      def doc
-        @doc ||= parse_html(html)
-      end
-
-      # The String representation of the document. If a DocumentFragment was
-      # provided to the Filter, it is serialized into a String when this method is
-      # called.
-      def html
-        raise InvalidDocumentException if @html.nil? && @doc.nil?
-        @html || doc.to_html
-      end
-
-      # The main filter entry point. The doc attribute is guaranteed to be a
-      # Nokogiri::HTML::DocumentFragment when invoked. Subclasses should modify
-      # this document in place or extract information and add it to the context
-      # hash.
-      def call
-        raise NotImplementedError
-      end
-
-      # Make sure the context has everything we need. Noop: Subclasses can override.
-      def validate; end
-
-      # The Repository object provided in the context hash, or nil when no
-      # :repository was specified.
-      #
-      # It's assumed that the repository context has already been checked
-      # for permissions
-      def repository
-        context[:repository]
-      end
-
-      # The User object provided in the context hash, or nil when no user
-      # was specified
-      def current_user
-        context[:current_user]
-      end
-
-      # The site's base URL provided in the context hash, or '/' when no
-      # base URL was specified.
-      def base_url
-        context[:base_url] || '/'
-      end
-
-      # Ensure the passed argument is a DocumentFragment. When a string is
-      # provided, it is parsed and returned; otherwise, the DocumentFragment is
-      # returned unmodified.
-      def parse_html(html)
-        HTML::Pipeline.parse(html)
-      end
-
-      # Helper method for filter subclasses used to determine if any of a node's
-      # ancestors have one of the tag names specified.
-      #
-      # node - The Node object to check.
-      # tags - An array of tag name strings to check. These should be downcase.
-      #
-      # Returns true when the node has a matching ancestor.
-      def has_ancestor?(node, tags)
-        while node = node.parent
-          break true if tags.include?(node.name.downcase)
-        end
-      end
-
-      # Perform a filter on doc with the given context.
-      #
-      # Returns a HTML::Pipeline::DocumentFragment or a String containing HTML
-      # markup.
-      def self.call(doc, context = nil, result = nil)
-        new(doc, context, result).call
-      end
-
-      # Like call but guarantees that a DocumentFragment is returned, even when
-      # the last filter returns a String.
-      def self.to_document(input, context = nil)
-        html = call(input, context)
-        HTML::Pipeline.parse(html)
-      end
-
-      # Like call but guarantees that a string of HTML markup is returned.
-      def self.to_html(input, context = nil)
-        output = call(input, context)
-        if output.respond_to?(:to_html)
-          output.to_html
-        else
-          output.to_s
-        end
-      end
-
-      # Validator for required context. This will check that anything passed in
-      # contexts exists in @contexts
-      #
-      # If any errors are found an ArgumentError will be raised with a
-      # message listing all the missing contexts and the filters that
-      # require them.
-      def needs(*keys)
-        missing = keys.reject { |key| context.include? key }
-
-        if missing.any?
-          raise ArgumentError,
-                "Missing context keys for #{self.class.name}: #{missing.map(&:inspect).join ', '}"
-        end
-      end
-    end
-  end
-end

data/lib/html/pipeline/https_filter.rb

@@ -1,29 +0,0 @@
-# frozen_string_literal: true
-
-module HTML
-  class Pipeline
-    # HTML Filter for replacing http references to :http_url with https versions.
-    # Subdomain references are not rewritten.
-    #
-    # Context options:
-    #   :http_url - The HTTP url to force HTTPS. Falls back to :base_url
-    class HttpsFilter < Filter
-      def call
-        doc.css(%(a[href^="#{http_url}"])).each do |element|
-          element['href'] = element['href'].sub(/^http:/, 'https:')
-        end
-        doc
-      end
-
-      # HTTP url to replace. Falls back to :base_url
-      def http_url
-        context[:http_url] || context[:base_url]
-      end
-
-      # Raise error if :http_url undefined
-      def validate
-        needs :http_url unless http_url
-      end
-    end
-  end
-end

data/lib/html/pipeline/image_max_width_filter.rb

@@ -1,37 +0,0 @@
-# frozen_string_literal: true
-
-module HTML
-  class Pipeline
-    # This filter rewrites image tags with a max-width inline style and also wraps
-    # the image in an <a> tag that causes the full size image to be opened in a
-    # new tab.
-    #
-    # The max-width inline styles are especially useful in HTML email which
-    # don't use a global stylesheets.
-    class ImageMaxWidthFilter < Filter
-      def call
-        doc.search('img').each do |element|
-          # Skip if there's already a style attribute. Not sure how this
-          # would happen but we can reconsider it in the future.
-          next if element['style']
-
-          # Bail out if src doesn't look like a valid http url. trying to avoid weird
-          # js injection via javascript: urls.
-          next if element['src'].to_s.strip =~ /\Ajavascript/i
-
-          element['style'] = 'max-width:100%;'
-
-          link_image element unless has_ancestor?(element, %w[a])
-        end
-
-        doc
-      end
-
-      def link_image(element)
-        link = doc.document.create_element('a', href: element['src'], target: '_blank')
-        link.add_child(element.dup)
-        element.replace(link)
-      end
-    end
-  end
-end

data/lib/html/pipeline/markdown_filter.rb

@@ -1,56 +0,0 @@
-# frozen_string_literal: true
-
-HTML::Pipeline.require_dependency('commonmarker', 'MarkdownFilter')
-
-module HTML
-  class Pipeline
-    # HTML Filter that converts Markdown text into HTML and converts into a
-    # DocumentFragment. This is different from most filters in that it can take a
-    # non-HTML as input. It must be used as the first filter in a pipeline.
-    #
-    # Context options:
-    #   :gfm      => false    Disable GFM line-end processing
-    #   :commonmarker_extensions => [ :table, :strikethrough,
-    #      :tagfilter, :autolink ] Commonmarker extensions to include
-    #
-    # This filter does not write any additional information to the context hash.
-    class MarkdownFilter < TextFilter
-      DEFAULT_COMMONMARKER_EXTENSIONS = %i[table strikethrough tagfilter autolink].freeze
-
-      def initialize(text, context = nil, result = nil)
-        super text, context, result
-        @text = @text.delete "\r"
-      end
-
-      # Convert Markdown to HTML using the best available implementation
-      # and convert into a DocumentFragment.
-      def call
-        extensions = context.fetch(
-          :commonmarker_extensions,
-          DEFAULT_COMMONMARKER_EXTENSIONS
-        )
-        html = if (renderer = context[:commonmarker_renderer])
-          unless renderer < CommonMarker::HtmlRenderer
-            raise ArgumentError, "`commonmark_renderer` must be derived from `CommonMarker::HtmlRenderer`"
-          end
-          parse_options = :DEFAULT
-          parse_options = [:UNSAFE] if context[:unsafe]
-
-          render_options = [:GITHUB_PRE_LANG]
-          render_options << :HARDBREAKS if context[:gfm] != false
-          render_options << :UNSAFE if context[:unsafe]
-
-          doc = CommonMarker.render_doc(@text, parse_options, extensions)
-          renderer.new(options: render_options, extensions: extensions).render(doc)
-        else
-          options = [:GITHUB_PRE_LANG]
-          options << :HARDBREAKS if context[:gfm] != false
-          options << :UNSAFE if context[:unsafe]
-          CommonMarker.render_html(@text, options, extensions)
-        end
-        html.rstrip!
-        html
-      end
-    end
-  end
-end