Split Markdown rendering & reference gathering

This splits the Markdown rendering and reference extraction phases into
two distinct code bases. The reference extraction phase no longer relies
on the html-pipeline Gem (and any related code) and allows for
extracting of references from multiple HTML nodes in a single pass. This
means that if you want to extract user references from 200 comments you
no longer need to run 200 times N number of queries, instead only a
handful of queries may be needed.

10 files changed, 477 insertions, 0 deletions

diff --git a/lib/banzai/reference_parser/base_parser.rb b/lib/banzai/reference_parser/base_parser.rb
new file mode 100644
index 00000000000..3d7b9c4a024
--- /dev/null
+++ b/lib/banzai/reference_parser/base_parser.rb
@@ -0,0 +1,204 @@
+module Banzai
+  module ReferenceParser
+    # Base class for reference parsing classes.
+    #
+    # Each parser should also specify its reference type by calling
+    # `self.reference_type = ...` in the body of the class. The value of this
+    # method should be a symbol such as `:issue` or `:merge_request`. For
+    # example:
+    #
+    #     class IssueParser < BaseParser
+    #       self.reference_type = :issue
+    #     end
+    #
+    # The reference type is used to determine what nodes to pass to the
+    # `referenced_by` method.
+    #
+    # Parser classes should either implement the instance method
+    # `references_relation` or overwrite `referenced_by`. The
+    # `references_relation` method is supposed to return an
+    # ActiveRecord::Relation used as a base relation for retrieving the objects
+    # referenced in a set of HTML nodes.
+    #
+    # Each class can implement two additional methods:
+    #
+    # * `nodes_user_can_reference`: returns an Array of nodes the given user can
+    #   refer to.
+    # * `nodes_visible_to_user`: returns an Array of nodes that are visible to
+    #   the given user.
+    #
+    # You only need to overwrite these methods if you want to tweak who can see
+    # which references. For example, the IssueParser class defines its own
+    # `nodes_visible_to_user` method so it can ensure users can only see issues
+    # they have access to.
+    class BaseParser
+      class << self
+        attr_accessor :reference_type
+      end
+
+      # Returns the attribute name containing the value for every object to be
+      # parsed by the current parser.
+      #
+      # For example, for a parser class that returns "Animal" objects this
+      # attribute would be "data-animal".
+      def self.data_attribute
+        @data_attribute ||= "data-#{reference_type.to_s.dasherize}"
+      end
+
+      def initialize(project = nil, current_user = nil)
+        @project = project
+        @current_user = current_user
+      end
+
+      # Returns all the nodes containing references that the user can refer to.
+      def nodes_user_can_reference(user, nodes)
+        nodes
+      end
+
+      # Returns all the nodes that are visible to the given user.
+      def nodes_visible_to_user(user, nodes)
+        projects = lazy { projects_for_nodes(nodes) }
+        project_attr = 'data-project'
+
+        nodes.select do |node|
+          if node.has_attribute?(project_attr)
+            node_id = node.attr(project_attr).to_i
+
+            if project && project.id == node_id
+              true
+            else
+              can?(user, :read_project, projects[node_id])
+            end
+          else
+            true
+          end
+        end
+      end
+
+      # Returns an Array of objects referenced by any of the given HTML nodes.
+      def referenced_by(nodes)
+        ids = unique_attribute_values(nodes, self.class.data_attribute)
+
+        references_relation.where(id: ids)
+      end
+
+      # Returns the ActiveRecord::Relation to use for querying references in the
+      # DB.
+      def references_relation
+        raise NotImplementedError,
+          "#{self.class} does not implement #{__method__}"
+      end
+
+      # Returns a Hash containing attribute values per project ID.
+      #
+      # The returned Hash uses the following format:
+      #
+      #     { project id => [value1, value2, ...] }
+      #
+      # nodes - An Array of HTML nodes to process.
+      # attribute - The name of the attribute (as a String) for which to gather
+      #             values.
+      #
+      # Returns a Hash.
+      def gather_attributes_per_project(nodes, attribute)
+        per_project = Hash.new { |hash, key| hash[key] = Set.new }
+
+        nodes.each do |node|
+          project_id = node.attr('data-project').to_i
+          id = node.attr(attribute)
+
+          per_project[project_id] << id if id
+        end
+
+        per_project
+      end
+
+      # Returns a Hash containing objects for an attribute grouped per their
+      # IDs.
+      #
+      # The returned Hash uses the following format:
+      #
+      #     { id value => row }
+      #
+      # nodes - An Array of HTML nodes to process.
+      #
+      # collection - The model or ActiveRecord relation to use for retrieving
+      #              rows from the database.
+      #
+      # attribute - The name of the attribute containing the primary key values
+      #             for every row.
+      #
+      # Returns a Hash.
+      def grouped_objects_for_nodes(nodes, collection, attribute)
+        return {} if nodes.empty?
+
+        ids = unique_attribute_values(nodes, attribute)
+
+        collection.where(id: ids).each_with_object({}) do |row, hash|
+          hash[row.id] = row
+        end
+      end
+
+      # Returns an Array containing all unique values of an attribute of the
+      # given nodes.
+      def unique_attribute_values(nodes, attribute)
+        values = Set.new
+
+        nodes.each do |node|
+          if node.has_attribute?(attribute)
+            values << node.attr(attribute)
+          end
+        end
+
+        values.to_a
+      end
+
+      # Processes the list of HTML documents and returns an Array containing all
+      # the references.
+      def process(documents)
+        type = self.class.reference_type
+
+        nodes = documents.flat_map do |document|
+          Querying.css(document, "a[data-reference-type='#{type}'].gfm").to_a
+        end
+
+        gather_references(nodes)
+      end
+
+      # Gathers the references for the given HTML nodes.
+      def gather_references(nodes)
+        nodes = nodes_user_can_reference(current_user, nodes)
+        nodes = nodes_visible_to_user(current_user, nodes)
+
+        referenced_by(nodes)
+      end
+
+      # Returns a Hash containing the projects for a given list of HTML nodes.
+      #
+      # The returned Hash uses the following format:
+      #
+      #     { project ID => project }
+      #
+      def projects_for_nodes(nodes)
+        @projects_for_nodes ||=
+          grouped_objects_for_nodes(nodes, Project, 'data-project')
+      end
+
+      def can?(user, permission, subject)
+        Ability.abilities.allowed?(user, permission, subject)
+      end
+
+      def find_projects_for_hash_keys(hash)
+        Project.where(id: hash.keys)
+      end
+
+      private
+
+      attr_reader :current_user, :project
+
+      def lazy(&block)
+        Gitlab::Lazy.new(&block)
+      end
+    end
+  end
+end
diff --git a/lib/banzai/reference_parser/commit_parser.rb b/lib/banzai/reference_parser/commit_parser.rb
new file mode 100644
index 00000000000..0fee9d267de
--- /dev/null
+++ b/lib/banzai/reference_parser/commit_parser.rb
@@ -0,0 +1,34 @@
+module Banzai
+  module ReferenceParser
+    class CommitParser < BaseParser
+      self.reference_type = :commit
+
+      def referenced_by(nodes)
+        commit_ids = commit_ids_per_project(nodes)
+        projects = find_projects_for_hash_keys(commit_ids)
+
+        projects.flat_map do |project|
+          find_commits(project, commit_ids[project.id])
+        end
+      end
+
+      def commit_ids_per_project(nodes)
+        gather_attributes_per_project(nodes, self.class.data_attribute)
+      end
+
+      def find_commits(project, ids)
+        commits = []
+
+        return commits unless project.valid_repo?
+
+        ids.each do |id|
+          commit = project.commit(id)
+
+          commits << commit if commit
+        end
+
+        commits
+      end
+    end
+  end
+end
diff --git a/lib/banzai/reference_parser/commit_range_parser.rb b/lib/banzai/reference_parser/commit_range_parser.rb
new file mode 100644
index 00000000000..69d01f8db15
--- /dev/null
+++ b/lib/banzai/reference_parser/commit_range_parser.rb
@@ -0,0 +1,38 @@
+module Banzai
+  module ReferenceParser
+    class CommitRangeParser < BaseParser
+      self.reference_type = :commit_range
+
+      def referenced_by(nodes)
+        range_ids = commit_range_ids_per_project(nodes)
+        projects = find_projects_for_hash_keys(range_ids)
+
+        projects.flat_map do |project|
+          find_ranges(project, range_ids[project.id])
+        end
+      end
+
+      def commit_range_ids_per_project(nodes)
+        gather_attributes_per_project(nodes, self.class.data_attribute)
+      end
+
+      def find_ranges(project, range_ids)
+        ranges = []
+
+        range_ids.each do |id|
+          range = find_object(project, id)
+
+          ranges << range if range
+        end
+
+        ranges
+      end
+
+      def find_object(project, id)
+        range = CommitRange.new(id, project)
+
+        range.valid_commits? ? range : nil
+      end
+    end
+  end
+end
diff --git a/lib/banzai/reference_parser/external_issue_parser.rb b/lib/banzai/reference_parser/external_issue_parser.rb
new file mode 100644
index 00000000000..a1264db2111
--- /dev/null
+++ b/lib/banzai/reference_parser/external_issue_parser.rb
@@ -0,0 +1,25 @@
+module Banzai
+  module ReferenceParser
+    class ExternalIssueParser < BaseParser
+      self.reference_type = :external_issue
+
+      def referenced_by(nodes)
+        issue_ids = issue_ids_per_project(nodes)
+        projects = find_projects_for_hash_keys(issue_ids)
+        issues = []
+
+        projects.each do |project|
+          issue_ids[project.id].each do |id|
+            issues << ExternalIssue.new(id, project)
+          end
+        end
+
+        issues
+      end
+
+      def issue_ids_per_project(nodes)
+        gather_attributes_per_project(nodes, self.class.data_attribute)
+      end
+    end
+  end
+end
diff --git a/lib/banzai/reference_parser/issue_parser.rb b/lib/banzai/reference_parser/issue_parser.rb
new file mode 100644
index 00000000000..24076e3d9ec
--- /dev/null
+++ b/lib/banzai/reference_parser/issue_parser.rb
@@ -0,0 +1,40 @@
+module Banzai
+  module ReferenceParser
+    class IssueParser < BaseParser
+      self.reference_type = :issue
+
+      def nodes_visible_to_user(user, nodes)
+        # It is not possible to check access rights for external issue trackers
+        return nodes if project && project.external_issue_tracker
+
+        issues = issues_for_nodes(nodes)
+
+        nodes.select do |node|
+          issue = issue_for_node(issues, node)
+
+          issue ? can?(user, :read_issue, issue) : false
+        end
+      end
+
+      def referenced_by(nodes)
+        issues = issues_for_nodes(nodes)
+
+        nodes.map { |node| issue_for_node(issues, node) }.uniq
+      end
+
+      def issues_for_nodes(nodes)
+        @issues_for_nodes ||= grouped_objects_for_nodes(
+          nodes,
+          Issue.all.includes(:author, :assignee, :project),
+          self.class.data_attribute
+        )
+      end
+
+      private
+
+      def issue_for_node(issues, node)
+        issues[node.attr(self.class.data_attribute).to_i]
+      end
+    end
+  end
+end
diff --git a/lib/banzai/reference_parser/label_parser.rb b/lib/banzai/reference_parser/label_parser.rb
new file mode 100644
index 00000000000..e5d1eb11d7f
--- /dev/null
+++ b/lib/banzai/reference_parser/label_parser.rb
@@ -0,0 +1,11 @@
+module Banzai
+  module ReferenceParser
+    class LabelParser < BaseParser
+      self.reference_type = :label
+
+      def references_relation
+        Label
+      end
+    end
+  end
+end
diff --git a/lib/banzai/reference_parser/merge_request_parser.rb b/lib/banzai/reference_parser/merge_request_parser.rb
new file mode 100644
index 00000000000..c9a9ca79c09
--- /dev/null
+++ b/lib/banzai/reference_parser/merge_request_parser.rb
@@ -0,0 +1,11 @@
+module Banzai
+  module ReferenceParser
+    class MergeRequestParser < BaseParser
+      self.reference_type = :merge_request
+
+      def references_relation
+        MergeRequest.includes(:author, :assignee, :target_project)
+      end
+    end
+  end
+end
diff --git a/lib/banzai/reference_parser/milestone_parser.rb b/lib/banzai/reference_parser/milestone_parser.rb
new file mode 100644
index 00000000000..a000ac61e5c
--- /dev/null
+++ b/lib/banzai/reference_parser/milestone_parser.rb
@@ -0,0 +1,11 @@
+module Banzai
+  module ReferenceParser
+    class MilestoneParser < BaseParser
+      self.reference_type = :milestone
+
+      def references_relation
+        Milestone
+      end
+    end
+  end
+end
diff --git a/lib/banzai/reference_parser/snippet_parser.rb b/lib/banzai/reference_parser/snippet_parser.rb
new file mode 100644
index 00000000000..fa71b3c952a
--- /dev/null
+++ b/lib/banzai/reference_parser/snippet_parser.rb
@@ -0,0 +1,11 @@
+module Banzai
+  module ReferenceParser
+    class SnippetParser < BaseParser
+      self.reference_type = :snippet
+
+      def references_relation
+        Snippet
+      end
+    end
+  end
+end
diff --git a/lib/banzai/reference_parser/user_parser.rb b/lib/banzai/reference_parser/user_parser.rb
new file mode 100644
index 00000000000..a12b0d19560
--- /dev/null
+++ b/lib/banzai/reference_parser/user_parser.rb
@@ -0,0 +1,92 @@
+module Banzai
+  module ReferenceParser
+    class UserParser < BaseParser
+      self.reference_type = :user
+
+      def referenced_by(nodes)
+        group_ids = []
+        user_ids = []
+        project_ids = []
+
+        nodes.each do |node|
+          if node.has_attribute?('data-group')
+            group_ids << node.attr('data-group').to_i
+          elsif node.has_attribute?(self.class.data_attribute)
+            user_ids << node.attr(self.class.data_attribute).to_i
+          elsif node.has_attribute?('data-project')
+            project_ids << node.attr('data-project').to_i
+          end
+        end
+
+        find_users_for_groups(group_ids) | find_users(user_ids) |
+          find_users_for_projects(project_ids)
+      end
+
+      def nodes_visible_to_user(user, nodes)
+        group_attr = 'data-group'
+        groups = lazy { grouped_objects_for_nodes(nodes, Group, group_attr) }
+        visible = []
+        remaining = []
+
+        nodes.each do |node|
+          if node.has_attribute?(group_attr)
+            node_group = groups[node.attr(group_attr).to_i]
+
+            if node_group &&
+              can?(user, :read_group, node_group)
+              visible << node
+            end
+          # Remaining nodes will be processed by the parent class'
+          # implementation of this method.
+          else
+            remaining << node
+          end
+        end
+
+        visible + super(current_user, remaining)
+      end
+
+      def nodes_user_can_reference(current_user, nodes)
+        project_attr = 'data-project'
+        author_attr = 'data-author'
+
+        projects = lazy { projects_for_nodes(nodes) }
+        users = lazy { grouped_objects_for_nodes(nodes, User, author_attr) }
+
+        nodes.select do |node|
+          project_id = node.attr(project_attr)
+          user_id = node.attr(author_attr)
+
+          if project && project_id && project.id == project_id.to_i
+            true
+          elsif project_id && user_id
+            project = projects[project_id.to_i]
+            user = users[user_id.to_i]
+
+            project && user ? project.team.member?(user) : false
+          else
+            true
+          end
+        end
+      end
+
+      def find_users(ids)
+        return [] if ids.empty?
+
+        User.where(id: ids).to_a
+      end
+
+      def find_users_for_groups(ids)
+        return [] if ids.empty?
+
+        User.joins(:group_members).where(members: { source_id: ids }).to_a
+      end
+
+      def find_users_for_projects(ids)
+        return [] if ids.empty?
+
+        Project.where(id: ids).flat_map { |p| p.team.members.to_a }
+      end
+    end
+  end
+end