libis-workflow 2.0.25 → 2.0.28

data/lib/libis/workflow/base/logging.rb

@@ -1,67 +1,67 @@
-module Libis
-  module Workflow
-    module Base
-      module Logging
-
-        # Add a structured message to the log history. The message text can be submitted as an integer or text. If an
-        # integer is submitted, it will be used to look up the text in the MessageRegistry. The message text will be
-        # passed to the % operator with the args parameter. If that failes (e.g. because the format string is not correct)
-        # the args value is appended to the message.
-        #
-        # @param [Symbol] severity
-        # @param [Hash] msg should contain message text as :id or :text and the hierarchical name of the task as :task
-        # @param [Array] args string format values
-        def log_message(severity, msg, *args)
-          # Prepare info from msg struct for use with string substitution
-          message_id, message_text = if msg[:id]
-                                       [msg[:id], MessageRegistry.instance.get_message(msg[:id])]
-                                     elsif msg[:text]
-                                       [0, msg[:text]]
-                                     else
-                                       [0, '']
-                                     end
-          task = msg[:task] || ''
-          message_text = (message_text % args rescue "#{message_text} - #{args}")
-
-          run_id = self.get_run.id rescue nil
-
-          self.add_log severity: severity, id: message_id.to_i, text: message_text, task: task, run_id: run_id
-        end
-
-        # Helper function for the WorkItems to add a log entry to the log_history.
-        #
-        # The supplied message structure is expected to contain the following fields:
-        # - :severity : ::Logger::Severity value
-        # - :id : optional message id
-        # - :text : message text
-        # - :task : list of tasks names (task hierarchy) that submits the message
-        #
-        # @param [Hash] message
-        def add_log(message = {})
-          msg = message_struct(message)
-          add_log_entry(msg)
-          self.save!
-        end
-
-        def <=(message = {})
-          self.add_log(message)
-        end
-
-        protected
-
-        # create and return a proper message structure
-        # @param [Hash] opts
-        def message_struct(opts = {})
-          opts.reverse_merge!(severity: :info, code: nil, text: '')
-          {
-              severity: ::Logging::levelify(opts[:severity]).upcase,
-              task: opts[:task],
-              code: opts[:code],
-              message: opts[:text]
-          }.cleanup
-        end
-
-      end
-    end
-  end
+module Libis
+  module Workflow
+    module Base
+      module Logging
+
+        # Add a structured message to the log history. The message text can be submitted as an integer or text. If an
+        # integer is submitted, it will be used to look up the text in the MessageRegistry. The message text will be
+        # passed to the % operator with the args parameter. If that failes (e.g. because the format string is not correct)
+        # the args value is appended to the message.
+        #
+        # @param [Symbol] severity
+        # @param [Hash] msg should contain message text as :id or :text and the hierarchical name of the task as :task
+        # @param [Array] args string format values
+        def log_message(severity, msg, *args)
+          # Prepare info from msg struct for use with string substitution
+          message_id, message_text = if msg[:id]
+                                       [msg[:id], MessageRegistry.instance.get_message(msg[:id])]
+                                     elsif msg[:text]
+                                       [0, msg[:text]]
+                                     else
+                                       [0, '']
+                                     end
+          task = msg[:task] || ''
+          message_text = (message_text % args rescue "#{message_text} - #{args}")
+
+          run_id = self.get_run.id rescue nil
+
+          self.add_log severity: severity, id: message_id.to_i, text: message_text, task: task, run_id: run_id
+        end
+
+        # Helper function for the WorkItems to add a log entry to the log_history.
+        #
+        # The supplied message structure is expected to contain the following fields:
+        # - :severity : ::Logger::Severity value
+        # - :id : optional message id
+        # - :text : message text
+        # - :task : list of tasks names (task hierarchy) that submits the message
+        #
+        # @param [Hash] message
+        def add_log(message = {})
+          msg = message_struct(message)
+          add_log_entry(msg)
+          self.save!
+        end
+
+        def <=(message = {})
+          self.add_log(message)
+        end
+
+        protected
+
+        # create and return a proper message structure
+        # @param [Hash] opts
+        def message_struct(opts = {})
+          opts.reverse_merge!(severity: :info, code: nil, text: '')
+          {
+              severity: ::Logging::levelify(opts[:severity]).upcase,
+              task: opts[:task],
+              code: opts[:code],
+              message: opts[:text]
+          }.cleanup
+        end
+
+      end
+    end
+  end
 end

data/lib/libis/workflow/base/run.rb

@@ -1,95 +1,97 @@
-require 'fileutils'
-
-require 'libis/workflow/base/work_item'
-require 'libis/workflow/task_runner'
-
-module Libis
-  module Workflow
-    module Base
-
-      # Base module for all workflow runs. It is created by an associated workflow when the workflow is executed.
-      #
-      # This module lacks the implementation for the data attributes. It functions as an interface that describes the
-      # common functionality regardless of the storage implementation. These attributes require some implementation:
-      #
-      # - start_date: [Time] the timestamp of the execution of the run
-      # - job: [Object] a reference to the Job this Run belongs to
-      # - id: [String] (Optional) a unique run number
-      #
-      # Note that ::Libis::Workflow::Base::WorkItem is a parent module and therefore requires implementation of the
-      # attributes of that module too.
-      #
-      # A simple in-memory implementation can be found in ::Libis::Workflow::Run
-      module Run
-        include ::Libis::Workflow::Base::WorkItem
-
-        attr_accessor :tasks, :action
-
-        def work_dir
-          # noinspection RubyResolve
-          dir = File.join(Libis::Workflow::Config.workdir, self.name)
-          FileUtils.mkpath dir unless Dir.exist?(dir)
-          dir
-        end
-
-        def name
-          self.job.run_name(self.start_date)
-        end
-
-        def names
-          Array.new
-        end
-
-        def namepath
-          self.name
-        end
-
-        def workflow
-          self.job.workflow
-        end
-
-        def logger
-          self.properties['logger'] || self.job.logger rescue ::Libis::Workflow::Config.logger
-        end
-
-        # Execute the workflow.
-        #
-        # The action parameter defines how the execution of the tasks will behave:
-        #  - With the default :run action each task will be executed regardsless how the task performed on the item
-        #    previously.
-        #  - When using the :retry action a task will not perform on an item if it was successful the last time. This
-        #    allows you to retry a run when an temporary error (e.g. asynchronous wait or halt) occured.
-        #
-        # @param [Symbol] action the type of action to take during this run. :run or :retry
-        def run(action = :run)
-          self.action = action
-
-          self.start_date = Time.now unless action == :retry
-
-          self.options = workflow.prepare_input(self.options)
-
-          self.tasks = workflow.tasks
-          configure_tasks self.options
-
-          self.save!
-
-          runner = Libis::Workflow::TaskRunner.new nil
-
-          self.tasks.each do |task|
-            runner << task
-          end
-
-          runner.run self
-
-        end
-
-        protected
-
-        def configure_tasks(opts)
-          self.tasks.each { |task| task.apply_options opts }
-        end
-
-      end
-    end
-  end
-end
+require 'fileutils'
+
+require 'libis/workflow/base/work_item'
+require 'libis/workflow/task_runner'
+
+module Libis
+  module Workflow
+    module Base
+
+      # Base module for all workflow runs. It is created by an associated workflow when the workflow is executed.
+      #
+      # This module lacks the implementation for the data attributes. It functions as an interface that describes the
+      # common functionality regardless of the storage implementation. These attributes require some implementation:
+      #
+      # - start_date: [Time] the timestamp of the execution of the run
+      # - job: [Object] a reference to the Job this Run belongs to
+      # - id: [String] (Optional) a unique run number
+      #
+      # Note that ::Libis::Workflow::Base::WorkItem is a parent module and therefore requires implementation of the
+      # attributes of that module too.
+      #
+      # A simple in-memory implementation can be found in ::Libis::Workflow::Run
+      module Run
+        include ::Libis::Workflow::Base::WorkItem
+
+        attr_accessor :tasks, :action
+
+        def work_dir
+          # noinspection RubyResolve
+          dir = File.join(Libis::Workflow::Config.workdir, self.name)
+          FileUtils.mkpath dir unless Dir.exist?(dir)
+          dir
+        end
+
+        def name
+          self.job.run_name(self.start_date)
+        end
+
+        def names
+          Array.new
+        end
+
+        def namepath
+          self.name
+        end
+
+        def workflow
+          self.job.workflow
+        end
+
+        def logger
+          self.properties['logger'] || self.job.logger rescue ::Libis::Workflow::Config.logger
+        end
+
+        # Execute the workflow.
+        #
+        # The action parameter defines how the execution of the tasks will behave:
+        #  - With the default :run action each task will be executed regardsless how the task performed on the item
+        #    previously.
+        #  - When using the :retry action a task will not perform on an item if it was successful the last time. This
+        #    allows you to retry a run when an temporary error (e.g. asynchronous wait or halt) occured.
+        #
+        # @param [Symbol] action the type of action to take during this run. :run or :retry
+        def run(action = :run)
+          self.action = action
+
+          unless action == :retry
+            self.start_date = Time.now
+            self.options = workflow.prepare_input(self.options)
+          end
+
+
+          self.tasks = workflow.tasks
+          configure_tasks self.options
+
+          self.save!
+
+          runner = Libis::Workflow::TaskRunner.new nil
+
+          self.tasks.each do |task|
+            runner << task
+          end
+
+          runner.run self
+
+        end
+
+        protected
+
+        def configure_tasks(opts)
+          self.tasks.each { |task| task.apply_options opts }
+        end
+
+      end
+    end
+  end
+end

data/lib/libis/workflow/base/work_item.rb

@@ -1,173 +1,173 @@
-require 'backports/rails/hash'
-require 'libis/tools/extend/hash'
-
-require 'libis/workflow/config'
-require 'libis/workflow/status'
-require_relative 'logging'
-
-module Libis
-  module Workflow
-    module Base
-
-      # Base module for all work items.
-      #
-      # This module lacks the implementation for the data attributes. It functions as an interface that describes the
-      # common functionality regardless of the storage implementation. These attributes require some implementation:
-      #
-      # - parent: [Object|nil] a link to a parent work item. Work items can be organized in any hierarchy you think is
-      #     relevant for your workflow (e.g. directory[/directory...]/file/line or library/section/book/page). Of course
-      #     hierarchies are not mandatory.
-      # - items: [Array] a list of child work items. see above.
-      # - options: [Hash] a set of options for the task chain on how to deal with this work item. This attribute can be
-      #     used to fine-tune the behaviour of tasks for a particular work item.
-      # - properties: [Hash] a set of properties, typically collected during the workflow processing and used to store
-      #     final or intermediate resulst of tasks. The ::Lias::Ingester::FileItem module uses this attribute to store the
-      #     properties (e.g. size, checksum, ...) of the file it represents.
-      # - status_log: [Array] a list of all status changes the work item went through.
-      # - summary: [Hash] collected statistics about the ingest for the work item and its children. This structure will
-      #     be filled in by the included task ::Lias::Ingester::Tasks::Analyzer wich is appended to the workflow by default.
-      #
-      # The module is created so that it is possible to implement an ActiveRecord/Datamapper/... implementation easily.
-      # A simple in-memory implementation would require:
-      #
-      # attr_accessor :parent
-      # attr_accessor :items
-      # attr_accessor :options, :properties
-      # attr_accessor :status_log
-      # attr_accessor :summary
-      #
-      # def initialize
-      #   self.parent = nil
-      #   self.items = []
-      #   self.options = {}
-      #   self.properties = {}
-      #   self.status_log = []
-      #   self.summary = {}
-      # end
-      #
-      # protected
-      #
-      # ## Method below should be adapted to match the implementation of the status array
-      #
-      # def add_status_log(info)
-      #   self.status_log << info
-      # end
-      #
-      #
-      module WorkItem
-        include Enumerable
-        include Libis::Workflow::Status
-        include Libis::Workflow::Base::Logging
-
-        # String representation of the identity of the work item.
-        #
-        # You may want to overwrite this method as it tries the :name property or whatever #inspect returns if that
-        # failes. Typically this should return the key value, file name or id number. If that's what your :name property
-        # contains, you're fine.
-        #
-        # @return [String] string identification for this work item.
-        def name
-          # noinspection RubyResolve
-          self.properties['name'] || self.inspect
-        end
-
-        def to_s;
-          self.name;
-        end
-
-        def names
-          (self.parent.names rescue Array.new).push(name).compact
-        end
-
-        def namepath;
-          self.names.join('/');
-        end
-
-        # File name safe version of the to_s output.
-        #
-        # The output should be safe to use as a file name to store work item
-        # data. Typical use is when extra file items are created by a task and need to be stored on disk. The default
-        # implementation URL-encodes (%xx) all characters except alphanumeric, '.' and '-'.
-        #
-        # @return [String] file name
-        def to_filename
-          self.to_s.gsub(/[^\w.-]/) { |s| '%%%02x' % s.ord }
-        end
-
-        # Iterates over the work item clients and invokes code on each of them.
-        def each(&block)
-          self.items.each(&block)
-        end
-
-        def size
-          self.items.size
-        end
-
-        alias_method :count, :size
-
-        # Add a child work item
-        #
-        # @param [WorkItem] item to be added to the child list :items
-        def add_item(item)
-          return self unless item and item.is_a?(Libis::Workflow::Base::WorkItem)
-          self.items << item
-          item.parent = self
-          self.save!
-          item.save!
-          self
-        end
-
-        alias_method :<<, :add_item
-
-        # Get list of items.
-        #
-        # This method should return a list of items that can be accessed during long processing times.
-        def get_items
-          self.items
-        end
-
-        # Get list of items.
-        #
-        # This method should return a list of items that is safe to iterate over while it is being altered.
-        def get_item_list
-          self.items.dup
-        end
-
-        # Return item's parent
-        # @return [Libis::Workflow::Base::WorkItem]
-        def get_parent
-          self.parent
-        end
-
-        # go up the hierarchy and return the topmost work item
-        #
-        # @return [Libis::Workflow::Base::WorkItem]
-        def get_root
-          self.get_parent && self.get_parent.is_a?(Libis::Workflow::Base::WorkItem) && self.get_parent.get_root || self
-        end
-
-        # Get the top
-        #
-        # @return [Libis::Workflow::Base::Run]
-        def get_run
-          return self if self.is_a?(Libis::Workflow::Base::Run)
-          self.get_parent && self.get_parent.get_run || nil
-        end
-
-        # Dummy method. It is a placeholder for DB backed implementations. Wherever appropriate WorkItem#save will be
-        # called to save the current item's state. If state needs to persisted, you should override this method or make
-        # sure your persistence layer implements it in your class.
-        def save
-        end
-
-        # Dummy method. It is a placeholder for DB backed implementations. Wherever appropriate WorkItem#save will be
-        # called to save the current item's state. If state needs to persisted, you should override this method or make
-        # sure your persistence layer implements it in your class.
-        def save!
-        end
-
-      end
-
-    end
-  end
-end
+require 'backports/rails/hash'
+require 'libis/tools/extend/hash'
+
+require 'libis/workflow/config'
+require 'libis/workflow/status'
+require_relative 'logging'
+
+module Libis
+  module Workflow
+    module Base
+
+      # Base module for all work items.
+      #
+      # This module lacks the implementation for the data attributes. It functions as an interface that describes the
+      # common functionality regardless of the storage implementation. These attributes require some implementation:
+      #
+      # - parent: [Object|nil] a link to a parent work item. Work items can be organized in any hierarchy you think is
+      #     relevant for your workflow (e.g. directory[/directory...]/file/line or library/section/book/page). Of course
+      #     hierarchies are not mandatory.
+      # - items: [Array] a list of child work items. see above.
+      # - options: [Hash] a set of options for the task chain on how to deal with this work item. This attribute can be
+      #     used to fine-tune the behaviour of tasks for a particular work item.
+      # - properties: [Hash] a set of properties, typically collected during the workflow processing and used to store
+      #     final or intermediate resulst of tasks. The ::Lias::Ingester::FileItem module uses this attribute to store the
+      #     properties (e.g. size, checksum, ...) of the file it represents.
+      # - status_log: [Array] a list of all status changes the work item went through.
+      # - summary: [Hash] collected statistics about the ingest for the work item and its children. This structure will
+      #     be filled in by the included task ::Lias::Ingester::Tasks::Analyzer wich is appended to the workflow by default.
+      #
+      # The module is created so that it is possible to implement an ActiveRecord/Datamapper/... implementation easily.
+      # A simple in-memory implementation would require:
+      #
+      # attr_accessor :parent
+      # attr_accessor :items
+      # attr_accessor :options, :properties
+      # attr_accessor :status_log
+      # attr_accessor :summary
+      #
+      # def initialize
+      #   self.parent = nil
+      #   self.items = []
+      #   self.options = {}
+      #   self.properties = {}
+      #   self.status_log = []
+      #   self.summary = {}
+      # end
+      #
+      # protected
+      #
+      # ## Method below should be adapted to match the implementation of the status array
+      #
+      # def add_status_log(info)
+      #   self.status_log << info
+      # end
+      #
+      #
+      module WorkItem
+        include Enumerable
+        include Libis::Workflow::Status
+        include Libis::Workflow::Base::Logging
+
+        # String representation of the identity of the work item.
+        #
+        # You may want to overwrite this method as it tries the :name property or whatever #inspect returns if that
+        # failes. Typically this should return the key value, file name or id number. If that's what your :name property
+        # contains, you're fine.
+        #
+        # @return [String] string identification for this work item.
+        def name
+          # noinspection RubyResolve
+          self.properties['name'] || self.inspect
+        end
+
+        def to_s;
+          self.name;
+        end
+
+        def names
+          (self.parent.names rescue Array.new).push(name).compact
+        end
+
+        def namepath;
+          self.names.join('/');
+        end
+
+        # File name safe version of the to_s output.
+        #
+        # The output should be safe to use as a file name to store work item
+        # data. Typical use is when extra file items are created by a task and need to be stored on disk. The default
+        # implementation URL-encodes (%xx) all characters except alphanumeric, '.' and '-'.
+        #
+        # @return [String] file name
+        def to_filename
+          self.to_s.gsub(/[^\w.-]/) { |s| '%%%02x' % s.ord }
+        end
+
+        # Iterates over the work item clients and invokes code on each of them.
+        def each(&block)
+          self.items.each(&block)
+        end
+
+        def size
+          self.items.size
+        end
+
+        alias_method :count, :size
+
+        # Add a child work item
+        #
+        # @param [WorkItem] item to be added to the child list :items
+        def add_item(item)
+          return self unless item and item.is_a?(Libis::Workflow::Base::WorkItem)
+          self.items << item
+          item.parent = self
+          self.save!
+          item.save!
+          self
+        end
+
+        alias_method :<<, :add_item
+
+        # Get list of items.
+        #
+        # This method should return a list of items that can be accessed during long processing times.
+        def get_items
+          self.items
+        end
+
+        # Get list of items.
+        #
+        # This method should return a list of items that is safe to iterate over while it is being altered.
+        def get_item_list
+          self.items.dup
+        end
+
+        # Return item's parent
+        # @return [Libis::Workflow::Base::WorkItem]
+        def get_parent
+          self.parent
+        end
+
+        # go up the hierarchy and return the topmost work item
+        #
+        # @return [Libis::Workflow::Base::WorkItem]
+        def get_root
+          self.get_parent && self.get_parent.is_a?(Libis::Workflow::Base::WorkItem) && self.get_parent.get_root || self
+        end
+
+        # Get the top
+        #
+        # @return [Libis::Workflow::Base::Run]
+        def get_run
+          return self if self.is_a?(Libis::Workflow::Base::Run)
+          self.get_parent && self.get_parent.get_run || nil
+        end
+
+        # Dummy method. It is a placeholder for DB backed implementations. Wherever appropriate WorkItem#save will be
+        # called to save the current item's state. If state needs to persisted, you should override this method or make
+        # sure your persistence layer implements it in your class.
+        def save
+        end
+
+        # Dummy method. It is a placeholder for DB backed implementations. Wherever appropriate WorkItem#save will be
+        # called to save the current item's state. If state needs to persisted, you should override this method or make
+        # sure your persistence layer implements it in your class.
+        def save!
+        end
+
+      end
+
+    end
+  end
+end