right_scraper 3.2.6 → 5.0.1

data/lib/right_scraper/scanners/union.rb

@@ -1,5 +1,5 @@
 #--
-# Copyright: Copyright (c) 2010-2011 RightScale, Inc.
+# Copyright: Copyright (c) 2010-2013 RightScale, Inc.
 #
 # Permission is hereby granted, free of charge, to any person obtaining
 # a copy of this software and associated documentation files (the
@@ -21,69 +21,72 @@
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 #++
 
-module RightScraper
-  module Scanners
-    # Union scanner, to permit running multiple scanners while only
-    # walking the fs once.
-    class Union
-      # Create a new union scanner.  Recognizes no new options.
-      #
-      # === Parameters
-      # classes(List):: List of Scanner classes to run
-      # options(Hash):: scanner options
-      def initialize(classes, options={})
-        @subscanners = classes.map {|klass| klass.new(options)}
-      end
+# ancestor
+require 'right_scraper/scanners'
 
-      # Notify subscanners that all scans have completed.
-      def finish
-        @subscanners.each {|scanner| scanner.finish}
-      end
+module RightScraper::Scanners
 
-      # Begin a scan for the given resource.
-      #
-      # === Parameters
-      # resource(RightScraper::Resource::Base):: resource to scan
-      def begin(resource)
-        @subscanners.each {|scanner| scanner.begin(resource)}
-      end
+  # Union scanner, to permit running multiple scanners while only
+  # walking the fs once.
+  class Union
 
-      # Finish a scan for the given resource.
-      #
-      # === Parameters
-      # resource(RightScraper::Resource::Base):: resource that just finished scanning
-      def end(resource)
-        @subscanners.each {|scanner| scanner.end(resource)}
-      end
+    # Create a new union scanner.  Recognizes no new options.
+    #
+    # === Parameters
+    # classes(List):: List of Scanner classes to run
+    # options(Hash):: scanner options
+    def initialize(classes, options={})
+      @subscanners = classes.map {|klass| klass.new(options)}
+    end
+
+    # Notify subscanners that all scans have completed.
+    def finish
+      @subscanners.each {|scanner| scanner.finish}
+    end
+
+    # Begin a scan for the given resource.
+    #
+    # === Parameters
+    # resource(RightScraper::Resource::Base):: resource to scan
+    def begin(resource)
+      @subscanners.each {|scanner| scanner.begin(resource)}
+    end
+
+    # Finish a scan for the given resource.
+    #
+    # === Parameters
+    # resource(RightScraper::Resource::Base):: resource that just finished scanning
+    def end(resource)
+      @subscanners.each {|scanner| scanner.end(resource)}
+    end
 
-      # Notice a file during scanning.
-      #
-      # === Block
-      # Return the data for this file.  We use a block because it may
-      # not always be necessary to read the data.
-      #
-      # === Parameters
-      # relative_position(String):: relative pathname for the file from the root of resource
-      def notice(relative_position)
-        data = nil
-        @subscanners.each {|scanner| scanner.notice(relative_position) {
-            data = yield if data.nil?
-            data
-          }
+    # Notice a file during scanning.
+    #
+    # === Block
+    # Return the data for this file.  We use a block because it may
+    # not always be necessary to read the data.
+    #
+    # === Parameters
+    # relative_position(String):: relative pathname for the file from the root of resource
+    def notice(relative_position)
+      data = nil
+      @subscanners.each {|scanner| scanner.notice(relative_position) {
+          data = yield if data.nil?
+          data
         }
-      end
+      }
+    end
 
-      # Notice a directory during scanning.  Returns true if any of the
-      # subscanners report that they should recurse into the directory.
-      #
-      # === Parameters
-      # relative_position(String):: relative pathname for directory from root of resource
-      #
-      # === Returns
-      # Boolean:: should the scanning recurse into the directory
-      def notice_dir(relative_position)
-        @subscanners.any? {|scanner| scanner.notice_dir(relative_position)}
-      end
+    # Notice a directory during scanning.  Returns true if any of the
+    # subscanners report that they should recurse into the directory.
+    #
+    # === Parameters
+    # relative_position(String):: relative pathname for directory from root of resource
+    #
+    # === Returns
+    # Boolean:: should the scanning recurse into the directory
+    def notice_dir(relative_position)
+      @subscanners.any? {|scanner| scanner.notice_dir(relative_position)}
     end
   end
 end

data/lib/right_scraper/scanners/workflow_manifest.rb

@@ -1,5 +1,5 @@
 #--
-# Copyright: Copyright (c) 2010-2011 RightScale, Inc.
+# Copyright: Copyright (c) 2010-2013 RightScale, Inc.
 #
 # Permission is hereby granted, free of charge, to any person obtaining
 # a copy of this software and associated documentation files (the
@@ -21,66 +21,67 @@
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 #++
 
-require File.expand_path(File.join(File.dirname(__FILE__), 'base'))
+# ancestor
+require 'right_scraper/scanners'
+
 require 'digest/sha1'
 
-module RightScraper
-  module Scanners
-    # Build manifests from a filesystem.
-    class WorkflowManifest < Base
-      # Create a new manifest scanner.  Does not accept any new arguments.
-      def initialize(*args)
-        super
-        @manifest = {}
-      end
+module RightScraper::Scanners
 
-      # Retrieve relative workflow files positions
-      #
-      # === Parameters
-      # workflow(Resources::Workflow):: Workflow whose manifest is being built
-      def begin(workflow)
-        @workflow = workflow
-        @metadata_filename = File.basename(@workflow.metadata_path)
-        @definition_filename = File.basename(@workflow.definition_path)
-      end
+  # Build manifests from a filesystem.
+  class WorkflowManifest < ::RightScraper::Scanners::Base
+    # Create a new manifest scanner.  Does not accept any new arguments.
+    def initialize(*args)
+      super
+      @manifest = {}
+    end
 
-      # Complete a scan for the given resource.
-      #
-      # === Parameters ===
-      # resource(RightScraper::Resources::Base):: resource to scan
-      def end(resource)
-        resource.manifest = @manifest
-        @manifest = {}
-      end
+    # Retrieve relative workflow files positions
+    #
+    # === Parameters
+    # workflow(Resources::Workflow):: Workflow whose manifest is being built
+    def begin(workflow)
+      @workflow = workflow
+      @metadata_filename = File.basename(@workflow.metadata_path)
+      @definition_filename = File.basename(@workflow.definition_path)
+    end
 
-      # Notice a file during scanning.
-      #
-      # === Block ===
-      # Return the data for this file.  We use a block because it may
-      # not always be necessary to read the data.
-      #
-      # === Parameters ===
-      # relative_position(String):: relative pathname for file from root of resource
-      def notice(relative_position)
-        if [ @metadata_filename, @definition_filename ].include?(relative_position)
-          @manifest[relative_position] = Digest::SHA1.hexdigest(yield)
-        end
-      end
+    # Complete a scan for the given resource.
+    #
+    # === Parameters ===
+    # resource(RightScraper::Resources::Base):: resource to scan
+    def end(resource)
+      resource.manifest = @manifest
+      @manifest = {}
+    end
 
-      # Notice a directory during scanning.  Since the workflow definition and
-      # metadata live in the root directory we don't need to recurse,
-      # but we do need to go into the first directory (identified by
-      # +relative_position+ being +nil+).
-      #
-      # === Parameters
-      # relative_position(String):: relative pathname for the directory from root of workflow
-      #
-      # === Returns
-      # Boolean:: should the scanning recurse into the directory
-      def notice_dir(relative_position)
-        relative_position == nil
+    # Notice a file during scanning.
+    #
+    # === Block ===
+    # Return the data for this file.  We use a block because it may
+    # not always be necessary to read the data.
+    #
+    # === Parameters ===
+    # relative_position(String):: relative pathname for file from root of resource
+    def notice(relative_position)
+      if [ @metadata_filename, @definition_filename ].include?(relative_position)
+        @manifest[relative_position] = Digest::SHA1.hexdigest(yield)
       end
- 
     end
+
+    # Notice a directory during scanning.  Since the workflow definition and
+    # metadata live in the root directory we don't need to recurse,
+    # but we do need to go into the first directory (identified by
+    # +relative_position+ being +nil+).
+    #
+    # === Parameters
+    # relative_position(String):: relative pathname for the directory from root of workflow
+    #
+    # === Returns
+    # Boolean:: should the scanning recurse into the directory
+    def notice_dir(relative_position)
+      relative_position == nil
+    end
+
   end
 end

data/lib/right_scraper/scanners/workflow_metadata.rb

@@ -1,5 +1,5 @@
 #--
-# Copyright: Copyright (c) 2010-2011 RightScale, Inc.
+# Copyright: Copyright (c) 2010-2013 RightScale, Inc.
 #
 # Permission is hereby granted, free of charge, to any person obtaining
 # a copy of this software and associated documentation files (the
@@ -21,50 +21,52 @@
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 #++
 
+# ancestor
+require 'right_scraper/scanners'
+
 require 'json'
 
-module RightScraper
-  module Scanners
-    # Load workflow metadata from a filesystem.
-    class WorkflowMetadata < Base
-      # Begin a scan for the given workflow.
-      #
-      # === Parameters
-      # workflow(RightScraper::Resources::Workflow):: workflow to scan
-      def begin(workflow)
-        @workflow = workflow
-        @metadata_filename = File.basename(workflow.metadata_path)
-      end
+module RightScraper::Scanners
+
+  # Load workflow metadata from a filesystem.
+  class WorkflowMetadata < ::RightScraper::Scanners::Base
+    # Begin a scan for the given workflow.
+    #
+    # === Parameters
+    # workflow(RightScraper::Resources::Workflow):: workflow to scan
+    def begin(workflow)
+      @workflow = workflow
+      @metadata_filename = File.basename(workflow.metadata_path)
+    end
 
-      # Notice a file during scanning.
-      #
-      # === Block
-      # Return the data for this file.  We use a block because it may
-      # not always be necessary to read the data.
-      #
-      # === Parameters
-      # relative_position(String):: relative pathname for the file from root of workflow
-      def notice(relative_position)
-        if relative_position == @metadata_filename
-          @logger.operation(:metadata_parsing) do
-            @workflow.metadata = JSON.parse(yield)
-          end
+    # Notice a file during scanning.
+    #
+    # === Block
+    # Return the data for this file.  We use a block because it may
+    # not always be necessary to read the data.
+    #
+    # === Parameters
+    # relative_position(String):: relative pathname for the file from root of workflow
+    def notice(relative_position)
+      if relative_position == @metadata_filename
+        @logger.operation(:metadata_parsing) do
+          @workflow.metadata = JSON.parse(yield)
         end
       end
+    end
 
-      # Notice a directory during scanning.  Since the workflow definition and
-      # metadata live in the root directory we don't need to recurse,
-      # but we do need to go into the first directory (identified by
-      # +relative_position+ being +nil+).
-      #
-      # === Parameters
-      # relative_position(String):: relative pathname for the directory from root of workflow
-      #
-      # === Returns
-      # Boolean:: should the scanning recurse into the directory
-      def notice_dir(relative_position)
-        relative_position == nil
-      end
+    # Notice a directory during scanning.  Since the workflow definition and
+    # metadata live in the root directory we don't need to recurse,
+    # but we do need to go into the first directory (identified by
+    # +relative_position+ being +nil+).
+    #
+    # === Parameters
+    # relative_position(String):: relative pathname for the directory from root of workflow
+    #
+    # === Returns
+    # Boolean:: should the scanning recurse into the directory
+    def notice_dir(relative_position)
+      relative_position == nil
     end
   end
 end

data/lib/right_scraper/scanners/workflow_s3_upload.rb

@@ -1,5 +1,5 @@
 #--
-# Copyright: Copyright (c) 2010-2011 RightScale, Inc.
+# Copyright: Copyright (c) 2010-2013 RightScale, Inc.
 #
 # Permission is hereby granted, free of charge, to any person obtaining
 # a copy of this software and associated documentation files (the
@@ -20,65 +20,69 @@
 # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 #++
+
+# ancestor
+require 'right_scraper/scanners'
+
 require 'right_aws'
 require 'json'
 
-module RightScraper
-  module Scanners
-    # Upload workflow definition and metadata to an S3 bucket.
-    class WorkflowS3Upload < Base
-      # Create a new S3Upload.  In addition to the options recognized
-      # by Scanner, this class recognizes <tt>:s3_key</tt>,
-      # <tt>:s3_secret</tt>, and <tt>:s3_bucket</tt> and requires all
-      # of those.
-      #
-      # === Options
-      # <tt>:s3_key</tt>:: Required.  S3 access key.
-      # <tt>:s3_secret</tt>:: Required.  S3 secret key.
-      # <tt>:s3_bucket</tt>:: Required.  Bucket to upload workflows to.
-      #
-      # === Parameters
-      # options(Hash):: scanner options
-      def initialize(options={})
-        super
-        s3_key = options.fetch(:s3_key)
-        s3_secret = options.fetch(:s3_secret)
-        s3 = RightAws::S3.new(aws_access_key_id=s3_key,
-                              aws_secret_access_key=s3_secret,
-                              :logger => Logger.new)
-        @bucket = s3.bucket(options.fetch(:s3_bucket))
-        raise "Need an actual, existing S3 bucket!" if @bucket.nil?
-      end
+module RightScraper::Scanners
 
-      # Upon ending a scan for a workflows, upload the workflows
-      # contents to S3.
-      #
-      # === Parameters
-      # workflows(RightScraper::Workflows):: Workflow to scan
-      def end(workflow)
-        @bucket.put(File.join('Workflows', workflow.resource_hash),
-                    {
-                      :metadata => workflow.metadata,
-                      :manifest => workflow.manifest
-                    }.to_json)
-      end
+  # Upload workflow definition and metadata to an S3 bucket.
+  class WorkflowS3Upload < ::RightScraper::Scanners::Base
+
+    # Create a new S3Upload.  In addition to the options recognized
+    # by Scanner, this class recognizes <tt>:s3_key</tt>,
+    # <tt>:s3_secret</tt>, and <tt>:s3_bucket</tt> and requires all
+    # of those.
+    #
+    # === Options
+    # <tt>:s3_key</tt>:: Required.  S3 access key.
+    # <tt>:s3_secret</tt>:: Required.  S3 secret key.
+    # <tt>:s3_bucket</tt>:: Required.  Bucket to upload workflows to.
+    #
+    # === Parameters
+    # options(Hash):: scanner options
+    def initialize(options={})
+      super
+      s3_key = options.fetch(:s3_key)
+      s3_secret = options.fetch(:s3_secret)
+      s3 = RightAws::S3.new(aws_access_key_id=s3_key,
+                            aws_secret_access_key=s3_secret,
+                            :logger => @logger)
+      @bucket = s3.bucket(options.fetch(:s3_bucket))
+      raise "Need an actual, existing S3 bucket!" if @bucket.nil?
+    end
+
+    # Upon ending a scan for a workflows, upload the workflows
+    # contents to S3.
+    #
+    # === Parameters
+    # workflows(RightScraper::Workflows):: Workflow to scan
+    def end(workflow)
+      @bucket.put(File.join('Workflows', workflow.resource_hash),
+                  {
+                    :metadata => workflow.metadata,
+                    :manifest => workflow.manifest
+                  }.to_json)
+    end
 
-      # Upload a file during scanning.
-      #
-      # === Block
-      # Return the data for this file.  We use a block because it may
-      # not always be necessary to read the data.
-      #
-      # === Parameters
-      # relative_position(String):: relative pathname for file from root of cookbook
-      def notice(relative_position)
-        # TBD: Only uplad definition and metadata, will there be more files?
-        contents = yield
-        name = Digest::SHA1.hexdigest(contents)
-        path = File.join('Files', name)
-        unless @bucket.key(path).exists?
-          @bucket.put(path, contents)
-        end
+    # Upload a file during scanning.
+    #
+    # === Block
+    # Return the data for this file.  We use a block because it may
+    # not always be necessary to read the data.
+    #
+    # === Parameters
+    # relative_position(String):: relative pathname for file from root of cookbook
+    def notice(relative_position)
+      # TBD: Only uplad definition and metadata, will there be more files?
+      contents = yield
+      name = Digest::SHA1.hexdigest(contents)
+      path = File.join('Files', name)
+      unless @bucket.key(path).exists?
+        @bucket.put(path, contents)
       end
     end
   end