resync 0.2.1 → 0.2.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 8c504db116de3859b95c4acea4ea950fb2a37a48
-  data.tar.gz: 1f0c7ef67cb41ca6dcdbf87ef943aa64b38b16d7
+  metadata.gz: 30958a3d136a05395b75151c4396cc3a396d8dc0
+  data.tar.gz: 1380f44a55d5305a1cf46988cbbc604f6672ad8f
 SHA512:
-  metadata.gz: 8b4ae0258fe913c876274be50963832f0022a2a71fee6d0c9cb9ad40e7cb2e83e97cba776eba0a7194e631177b16e19aab8e80ce89a4343c862572c7f3c1fb87
-  data.tar.gz: 3e04a2227d2434fda5c8628a484027542a9d7bf713f742a3c062d87a5836339037b0c520363dc348b59487eebb2d6fb801a9f41e7f7e0f21e548fac352bfa71f
+  metadata.gz: 2262fa5a7028254fb4144772ec3cfe44982596a1cd69f8114afad7a4c9f1db5de0f2de0de7d0f25990ce6cf8c0a3d16fb35eaeb504c3f877fe6a6f2ab31660de
+  data.tar.gz: 885631b5db2dae906e938f2a125c75f7f020d98dfbe2b964bd8ea6fe68ff3e3ba684137fd34ab2ff635ed94639e5c8b482eba457440de410d7830abc6d1c26a3

data/CHANGES.md

@@ -1,3 +1,8 @@
+## 0.2.2
+
+- Added `#changes` method to `ChangeList` and `ChangeDumpManifest`, allowing filtering by change type and modified time
+- Added `#change_lists` method to `ChangeListIndex`, `ChangeDumpIndex`, and `ChangeDump`, allowing filtering by from and until times
+
 ## 0.2.1
 
 - Fixed issue where extra whitespace in `<loc/>` tags could prevent URI parsing.

data/lib/resync/change_dump.rb

@@ -1,11 +1,11 @@
-require_relative 'shared/sorted_resource_list'
+require_relative 'shared/base_change_index'
 require_relative 'xml'
 
 module Resync
   # A change dump. See section 13.1,
   # "{http://www.openarchives.org/rs/1.0/resourcesync#ChangeDump Change Dump}",
   # in the ResourceSync specification.
-  class ChangeDump < SortedResourceList
+  class ChangeDump < BaseChangeIndex
     include ::XML::Mapping
 
     # The capability provided by this type.

data/lib/resync/change_dump_index.rb

@@ -1,11 +1,11 @@
-require_relative 'shared/sorted_resource_list'
+require_relative 'shared/base_change_index'
 require_relative 'shared/sitemap_index'
 
 module Resync
   # A change dump index. See under section 13.1,
   # "{http://www.openarchives.org/rs/1.0/resourcesync#ChangeDumpIndex Change Dump}",
   # in the ResourceSync specification.
-  class ChangeDumpIndex < SortedResourceList
+  class ChangeDumpIndex < BaseChangeIndex
     include ::XML::Mapping
     include SitemapIndex
 

data/lib/resync/change_dump_manifest.rb

@@ -1,11 +1,11 @@
-require_relative 'shared/sorted_resource_list'
+require_relative 'shared/base_change_list'
 require_relative 'xml'
 
 module Resync
   # A change dump manifest. See section 13.2,
   # "{http://www.openarchives.org/rs/1.0/resourcesync#ChangeDumpManifest Change Dump Manifest}",
   # in the ResourceSync specification.
-  class ChangeDumpManifest < SortedResourceList
+  class ChangeDumpManifest < BaseChangeList
     include ::XML::Mapping
 
     # The capability provided by this type.

data/lib/resync/change_list.rb

@@ -1,11 +1,11 @@
-require_relative 'shared/sorted_resource_list'
+require_relative 'shared/base_change_list'
 require_relative 'xml'
 
 module Resync
   # A change list. See section 12.1,
   # "{http://www.openarchives.org/rs/1.0/resourcesync#ChangeList Change List}",
   # in the ResourceSync specification.
-  class ChangeList < SortedResourceList
+  class ChangeList < BaseChangeList
     include ::XML::Mapping
 
     # The capability provided by this type.

data/lib/resync/change_list_index.rb

@@ -1,11 +1,11 @@
-require_relative 'shared/sorted_resource_list'
+require_relative 'shared/base_change_index'
 require_relative 'shared/sitemap_index'
 
 module Resync
   # A change list index. See section 12.2,
   # "{http://www.openarchives.org/rs/1.0/resourcesync#ChangeListIndex Change List Index}",
   # in the ResourceSync specification.
-  class ChangeListIndex < SortedResourceList
+  class ChangeListIndex < BaseChangeIndex
     include ::XML::Mapping
     include SitemapIndex
 

data/lib/resync/metadata.rb

@@ -48,7 +48,7 @@ module Resync
     #   a change list (including change list indices, change dumps, etc.)
     # @param until_time [Time] the end of the time range represented by
     #   a change list (including change list indices, change dumps, etc.)
-    # @param completed_time the datetime at which assembling a resource list
+    # @param completed_time [Time] the datetime at which assembling a resource list
     #   ended (including resource list indices, resource dumps, etc.)
     # @param modified_time [Time] The date and time when the referenced resource was last modified.
     # @param length [Integer] The content length of the referenced resource.

data/lib/resync/shared/augmented.rb

@@ -73,21 +73,44 @@ module Resync
       links.find { |l| l.rel == rel }
     end
 
+    # Convenience accessor for the +at_time+ metadata attribute
+    # @return [Time] the datetime at which assembling a resource list
+    #   began (including resource list indices, resource dumps, etc.)
+    # @see Metadata#at_time
     def at_time
       metadata.at_time if metadata
     end
 
+    # Convenience accessor for the +from_time+ metadata attribute
+    # @return [Time] the beginning of the time range represented by
+    #   a change list (including change list indices, change dumps, etc.)
+    # @see Metadata#from_time
     def from_time
       metadata.from_time if metadata
     end
 
+    # Convenience accessor for the +until_time+ metadata attribute
+    # @return [Time] the end of the time range represented by
+    #   a change list (including change list indices, change dumps, etc.)
+    # @see Metadata#until_time
     def until_time
       metadata.until_time if metadata
     end
 
+    # Convenience accessor for the +completed_time+ metadata attribute
+    # @return [Time] the datetime at which assembling a resource list
+    #   ended (including resource list indices, resource dumps, etc.)
+    # @see Metadata#completed_time
     def completed_time
       metadata.completed_time if metadata
     end
 
+    # Convenience accessor for the +change+ metadata attribute
+    # @return [Change] the type of change to a resource reported in
+    #   a change list (including change list indices, change dumps, etc.)
+    # @see Metadata#change
+    def change
+      metadata.change if metadata
+    end
   end
 end

data/lib/resync/shared/base_change_index.rb

@@ -0,0 +1,35 @@
+require_relative 'sorted_resource_list'
+
+module Resync
+  # Adds useful methods to {ChangeListIndex}, {ChangeDumpIndex}, and {ChangeDump}.
+  class BaseChangeIndex < SortedResourceList
+    # Filters the list of change lists by from/until time. The filter can be *strict*, in which
+    # case only those change lists provably in the range are included, or *non-strict*, in which
+    # case only those change lists provably *not* in the range are *excluded*. (This is particularly
+    # useful for {ChangeDump}s, where the +from_time+ and +until_time+ attributes on the individual
+    # bitstream packages are optional.)
+    #
+    # @param in_range [Range<Time>] the range of times to filter by
+    # @param strict [Boolean] +true+ if resources without +from_time+ or +until_time+ should be
+    #   excluded, +false+ if they should be included.
+    # @return [Enumerator::Lazy<Resource>] those change lists whose +from_time+ *or* +until_time+
+    #   falls within +in_range+
+    def change_lists(in_range:, strict: true)
+      resources.select do |r|
+        strict ? strictly(in_range, r) : loosely(in_range, r)
+      end
+    end
+
+    private
+
+    def strictly(in_range, resource)
+      from_in_range = resource.from_time ? in_range.cover?(resource.from_time) : false
+      until_in_range = resource.until_time ? in_range.cover?(resource.until_time) : false
+      from_in_range || until_in_range
+    end
+
+    def loosely(in_range, resource)
+      (resource.from_time || resource.until_time) ? strictly(in_range, resource) : true
+    end
+  end
+end

data/lib/resync/shared/base_change_list.rb

@@ -0,0 +1,19 @@
+require_relative 'sorted_resource_list'
+
+module Resync
+  # Adds useful methods to {ChangeList} and {ChangeDumpManifest}.
+  class BaseChangeList < SortedResourceList
+    # Filters the list of changes by change type, modification time, or both.
+    # @param of_type [Types::Change] the change type
+    # @param in_range [Range<Time>] the range of modification times
+    # @return [Enumerator::Lazy<Resource>] the matching changes, or all changes
+    #   if neither +of_type+ nor +in_range+ is specified.
+    def changes(of_type: nil, in_range: nil)
+      resources.select do |r|
+        is_of_type = of_type ? r.change == of_type : true
+        is_in_range = in_range ? in_range.cover?(r.modified_time) : true
+        is_of_type && is_in_range
+      end
+    end
+  end
+end

data/lib/resync/version.rb

@@ -1,4 +1,4 @@
 module Resync
   # The version of this gem.
-  VERSION = '0.2.1'
+  VERSION = '0.2.2'
 end

data/spec/unit/resync/change_dump_index_spec.rb

@@ -1,8 +1,8 @@
-require_relative 'shared/sorted_list_examples'
+require_relative 'shared/base_change_index_examples'
 
 module Resync
   describe ChangeDumpIndex do
-    it_behaves_like SortedResourceList
+    it_behaves_like BaseChangeIndex
 
     describe 'XML conversion' do
       describe '#from_xml' do

data/spec/unit/resync/change_dump_manifest_spec.rb

@@ -1,8 +1,8 @@
-require_relative 'shared/sorted_list_examples'
+require_relative 'shared/base_change_list_examples'
 
 module Resync
   describe ChangeDumpManifest do
-    it_behaves_like SortedResourceList
+    it_behaves_like BaseChangeList
     describe 'XML conversion' do
       describe '#from_xml' do
         it 'parses an XML string' do

data/spec/unit/resync/change_dump_spec.rb

@@ -1,8 +1,8 @@
-require_relative 'shared/sorted_list_examples'
+require_relative 'shared/base_change_index_examples'
 
 module Resync
   describe ChangeDump do
-    it_behaves_like SortedResourceList
+    it_behaves_like BaseChangeIndex
 
     describe 'XML conversion' do
       describe '#from_xml' do

data/spec/unit/resync/change_list_index_spec.rb

@@ -1,8 +1,8 @@
-require_relative 'shared/sorted_list_examples'
+require_relative 'shared/base_change_index_examples'
 
 module Resync
   describe ChangeListIndex do
-    it_behaves_like SortedResourceList
+    it_behaves_like BaseChangeIndex
 
     describe 'XML conversion' do
       describe '#from_xml' do

data/spec/unit/resync/change_list_spec.rb

@@ -1,8 +1,8 @@
-require_relative 'shared/sorted_list_examples'
+require_relative 'shared/base_change_list_examples'
 
 module Resync
   describe ChangeList do
-    it_behaves_like SortedResourceList
+    it_behaves_like BaseChangeList
 
     describe 'XML conversion' do
       describe '#from_xml' do

data/spec/unit/resync/shared/base_change_index_examples.rb

@@ -0,0 +1,66 @@
+require_relative 'sorted_list_examples'
+
+module Resync
+  RSpec.shared_examples BaseChangeIndex do
+    it_behaves_like SortedResourceList
+
+    describe '#change_lists' do
+      it 'filters by time range' do
+        resources = []
+        resources[0] = Resource.new(uri: 'http://example.org/changes-0', metadata: Metadata.new(until_time: Time.utc(2000)))
+        resources[1] = Resource.new(uri: 'http://example.org/changes-1', metadata: Metadata.new(from_time: Time.utc(2000), until_time: Time.utc(2001)))
+        resources[2] = Resource.new(uri: 'http://example.org/changes-2', metadata: Metadata.new(from_time: Time.utc(2001), until_time: Time.utc(2002)))
+        resources[3] = Resource.new(uri: 'http://example.org/changes-3', metadata: Metadata.new(from_time: Time.utc(2002)))
+        index = ChangeListIndex.new(resources: resources)
+
+        changes = index.change_lists(in_range: Time.utc(1999)..Time.utc(2000, 7, 1)).to_a
+        expect(changes.size).to eq(2)
+        expect(changes).to include(resources[0])
+        expect(changes).to include(resources[1])
+
+        changes = index.change_lists(in_range: Time.utc(2000, 7, 1)..Time.utc(2001, 7, 1)).to_a
+        expect(changes.size).to eq(2)
+        expect(changes).to include(resources[1])
+        expect(changes).to include(resources[2])
+
+        changes = index.change_lists(in_range: Time.utc(2001, 7, 1)..Time.utc(2003, 7, 1)).to_a
+        expect(changes.size).to eq(2)
+        expect(changes).to include(resources[2])
+        expect(changes).to include(resources[3])
+      end
+
+      it 'ignores resources with neither from nor until time' do
+        resources = []
+        resources[0] = Resource.new(uri: 'http://example.org/changes-0', metadata: Metadata.new(until_time: Time.utc(2000)))
+        resources[1] = Resource.new(uri: 'http://example.org/changes-1', metadata: Metadata.new(from_time: Time.utc(2000), until_time: Time.utc(2001)))
+        resources[2] = Resource.new(uri: 'http://example.org/changes-2', metadata: Metadata.new(from_time: Time.utc(2001), until_time: Time.utc(2002)))
+        resources[3] = Resource.new(uri: 'http://example.org/changes-3', metadata: Metadata.new(from_time: Time.utc(2002)))
+        resources[4] = Resource.new(uri: 'http://example.org/changes-4')
+        resources[5] = Resource.new(uri: 'http://example.org/changes-5')
+        index = ChangeListIndex.new(resources: resources)
+        changes = index.change_lists(in_range: Time.utc(2000, 7, 1)..Time.utc(2001, 7, 1)).to_a
+        expect(changes.size).to eq(2)
+        expect(changes).to include(resources[1])
+        expect(changes).to include(resources[2])
+      end
+
+      it 'includes resources with neither from nor until time when in non-strict mode' do
+        resources = []
+        resources[0] = Resource.new(uri: 'http://example.org/changes-0', metadata: Metadata.new(until_time: Time.utc(2000)))
+        resources[1] = Resource.new(uri: 'http://example.org/changes-1', metadata: Metadata.new(from_time: Time.utc(2000), until_time: Time.utc(2001)))
+        resources[2] = Resource.new(uri: 'http://example.org/changes-2', metadata: Metadata.new(from_time: Time.utc(2001), until_time: Time.utc(2002)))
+        resources[3] = Resource.new(uri: 'http://example.org/changes-3', metadata: Metadata.new(from_time: Time.utc(2002)))
+        resources[4] = Resource.new(uri: 'http://example.org/changes-4')
+        resources[5] = Resource.new(uri: 'http://example.org/changes-5')
+        index = ChangeListIndex.new(resources: resources)
+        changes = index.change_lists(in_range: Time.utc(2000, 7, 1)..Time.utc(2001, 7, 1), strict: false).to_a
+        expect(changes.size).to eq(4)
+        expect(changes).to include(resources[1])
+        expect(changes).to include(resources[2])
+        expect(changes).to include(resources[4])
+        expect(changes).to include(resources[5])
+      end
+    end
+
+  end
+end

data/spec/unit/resync/shared/base_change_list_examples.rb

@@ -0,0 +1,69 @@
+require_relative 'sorted_list_examples'
+
+module Resync
+  RSpec.shared_examples BaseChangeList do
+
+    # ------------------------------------------------------
+    # Superclass conformance
+
+    it_behaves_like SortedResourceList
+
+    def new_instance(**args)
+      required_args = (defined? required_arguments) ? required_arguments : {}
+      args = required_args.merge(args)
+      described_class.new(**args)
+    end
+
+    # ------------------------------------------------------
+    # Tests
+
+    describe '#changes' do
+
+      it 'returns all changes if called without arguments' do
+        resource0 = Resource.new(uri: 'http://example.org', modified_time: Time.utc(1997, 7, 16, 19, 20, 30.45))
+        resource1 = Resource.new(uri: 'http://example.org', modified_time: Time.utc(1998, 7, 16, 19, 20, 30.45))
+        resource2 = Resource.new(uri: 'http://example.org', modified_time: Time.utc(1998, 8, 16, 19, 20, 30.45))
+        resource3 = Resource.new(uri: 'http://example.org', modified_time: Time.utc(1999, 1, 16, 19, 20, 30.45))
+        list = new_instance(resources: [resource1, resource3, resource2, resource0])
+        expect(list.changes.to_a).to eq([resource0, resource1, resource2, resource3])
+      end
+
+      it 'filters on change type' do
+        resource0 = Resource.new(uri: 'http://example.org', metadata: Metadata.new(change: Types::Change::CREATED), modified_time: Time.utc(1997, 7, 16, 19, 20, 30.45))
+        resource1 = Resource.new(uri: 'http://example.org', metadata: Metadata.new(change: Types::Change::UPDATED), modified_time: Time.utc(1998, 7, 16, 19, 20, 30.45))
+        resource2 = Resource.new(uri: 'http://example.org', metadata: Metadata.new(change: Types::Change::UPDATED), modified_time: Time.utc(1998, 8, 16, 19, 20, 30.45))
+        resource3 = Resource.new(uri: 'http://example.org', metadata: Metadata.new(change: Types::Change::DELETED), modified_time: Time.utc(1999, 1, 16, 19, 20, 30.45))
+        list = new_instance(resources: [resource0, resource1, resource2, resource3])
+        changes = list.changes(of_type: Types::Change::UPDATED)
+        expect(changes.to_a).to eq([resource1, resource2])
+      end
+
+      it 'filters on modified time' do
+        resource0 = Resource.new(uri: 'http://example.org', modified_time: Time.utc(1997, 7, 16, 19, 20, 30.45))
+        resource1 = Resource.new(uri: 'http://example.org', modified_time: Time.utc(1998, 7, 16, 19, 20, 30.45))
+        resource2 = Resource.new(uri: 'http://example.org', modified_time: Time.utc(1998, 8, 16, 19, 20, 30.45))
+        resource3 = Resource.new(uri: 'http://example.org', modified_time: Time.utc(1999, 1, 16, 19, 20, 30.45))
+        list = new_instance(resources: [resource0, resource1, resource2, resource3])
+        range = Time.utc(1998, 1, 1)...Time.utc(1999, 1, 1)
+        changes = list.changes(in_range: range)
+        expect(changes.to_a).to eq([resource1, resource2])
+      end
+
+      it 'filters on combinations' do
+        resources = []
+        resources[0] = Resource.new(uri: 'http://example.org/', modified_time: Time.utc(1999, 1, 1), metadata: Metadata.new(change: Types::Change::CREATED))
+        resources[1] = Resource.new(uri: 'http://example.org/', modified_time: Time.utc(2000, 1, 1), metadata: Metadata.new(change: Types::Change::CREATED))
+        resources[2] = Resource.new(uri: 'http://example.org/', modified_time: Time.utc(1999, 3, 1), metadata: Metadata.new(change: Types::Change::UPDATED))
+        resources[3] = Resource.new(uri: 'http://example.org/', modified_time: Time.utc(1999, 6, 1), metadata: Metadata.new(change: Types::Change::UPDATED))
+        resources[4] = Resource.new(uri: 'http://example.org/', modified_time: Time.utc(2000, 3, 1), metadata: Metadata.new(change: Types::Change::UPDATED))
+        resources[5] = Resource.new(uri: 'http://example.org/', modified_time: Time.utc(2000, 6, 1), metadata: Metadata.new(change: Types::Change::UPDATED))
+        resources[6] = Resource.new(uri: 'http://example.org/', modified_time: Time.utc(1999, 9, 1), metadata: Metadata.new(change: Types::Change::DELETED))
+        resources[7] = Resource.new(uri: 'http://example.org/', modified_time: Time.utc(2000, 9, 1), metadata: Metadata.new(change: Types::Change::DELETED))
+        list = new_instance(resources: resources)
+        changes = list.changes(of_type: Types::Change::UPDATED, in_range: Time.utc(1999, 4, 1)..Time.utc(2000, 4, 1))
+        expect(changes.to_a).to eq([resources[3], resources[4]])
+      end
+    end
+
+  end
+end

data/spec/unit/resync/shared/sorted_list_examples.rb

@@ -31,11 +31,11 @@ module Resync
           resource0 = Resource.new(uri: 'http://example.org', modified_time: Time.utc(1997, 7, 16, 19, 20, 30.45))
           resource1 = Resource.new(uri: 'http://example.org', modified_time: Time.utc(1998, 7, 16, 19, 20, 30.45))
           resource2 = Resource.new(uri: 'http://example.org', modified_time: Time.utc(1998, 7, 16, 19, 20, 30.45))
-          resource4 = Resource.new(uri: 'http://example.org', modified_time: Time.utc(1998, 1, 16, 19, 20, 30.45))
-          list = new_instance(resources: [resource1, resource4, resource2, resource0])
+          resource3 = Resource.new(uri: 'http://example.org', modified_time: Time.utc(1998, 1, 16, 19, 20, 30.45))
+          list = new_instance(resources: [resource1, resource3, resource2, resource0])
           resources = list.resources.to_a
           expect(resources[0]).to be(resource0)
-          expect(resources[1]).to be(resource4)
+          expect(resources[1]).to be(resource3)
           expect(resources).to include(resource1)
           expect(resources).to include(resource2)
         end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: resync
 version: !ruby/object:Gem::Version
-  version: 0.2.1
+  version: 0.2.2
 platform: ruby
 authors:
 - David Moles
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-06-09 00:00:00.000000000 Z
+date: 2015-06-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: mime-types
@@ -183,6 +183,8 @@ files:
 - lib/resync/resource_list.rb
 - lib/resync/resource_list_index.rb
 - lib/resync/shared/augmented.rb
+- lib/resync/shared/base_change_index.rb
+- lib/resync/shared/base_change_list.rb
 - lib/resync/shared/base_resource_list.rb
 - lib/resync/shared/descriptor.rb
 - lib/resync/shared/sitemap_index.rb
@@ -252,6 +254,8 @@ files:
 - spec/unit/resync/resource_list_spec.rb
 - spec/unit/resync/resource_spec.rb
 - spec/unit/resync/shared/augmented_examples.rb
+- spec/unit/resync/shared/base_change_index_examples.rb
+- spec/unit/resync/shared/base_change_list_examples.rb
 - spec/unit/resync/shared/base_resource_list_examples.rb
 - spec/unit/resync/shared/descriptor_examples.rb
 - spec/unit/resync/shared/descriptor_spec.rb
@@ -342,6 +346,8 @@ test_files:
 - spec/unit/resync/resource_list_spec.rb
 - spec/unit/resync/resource_spec.rb
 - spec/unit/resync/shared/augmented_examples.rb
+- spec/unit/resync/shared/base_change_index_examples.rb
+- spec/unit/resync/shared/base_change_list_examples.rb
 - spec/unit/resync/shared/base_resource_list_examples.rb
 - spec/unit/resync/shared/descriptor_examples.rb
 - spec/unit/resync/shared/descriptor_spec.rb