stash-sword 0.1.0

data/notes/service-document.xml

@@ -0,0 +1,15 @@
+<service xmlns="http://www.w3.org/2007/app" xmlns:atom="http://www.w3.org/2005/Atom">
+  <workspace>
+    <atom:title type="text">Merritt</atom:title>
+    <collection href="http://merritt.cdlib.org/sword/v2/dash_ucb">
+      <atom:title type="text">UCB Dash</atom:title>
+      <accept>*/*</accept>
+      <accept alternate="multipart-related">*/*</accept>
+      <mediation xmlns="http://purl.org/net/sword/terms/">true</mediation>
+      <acceptPackaging xmlns="http://purl.org/net/sword/terms/">http://purl.org/net/sword/package/SimpleZip</acceptPackaging>
+    </collection>
+  </workspace>
+  <generator xmlns="http://www.w3.org/2005/Atom" uri="http://www.swordapp.org/" version="2.0" />
+  <version xmlns="http://purl.org/net/sword/terms/">2.0</version>
+  <maxUploadSize xmlns="http://purl.org/net/sword/terms/">10000000</maxUploadSize>
+</service>

data/spec/.rubocop.yml

@@ -0,0 +1,10 @@
+inherit_from: ../.rubocop.yml
+
+Metrics/MethodLength:
+  Enabled: false
+
+Metrics/ModuleLength:
+  Enabled: false
+
+Metrics/ClassLength:
+  Enabled: false

data/spec/data/deposit_receipt_merritt.xml

@@ -0,0 +1,25 @@
+<entry xmlns="http://www.w3.org/2005/Atom">
+    <author>
+        <name>ucop_dash_submitter</name>
+    </author>
+    <title type="text">doi:10.5072/FK1465406644</title>
+    <id>http://n2t.net/ark:/99999/fk47h1tz4k</id>
+    <updated>2016-06-08T17:24:12.643Z</updated>
+    <generator uri="http://www.swordapp.org/" version="2.0"/>
+    <link
+            href="http://sword-aws-dev.cdlib.org:39001/mrtsword/edit/dash_cdl/doi%3A10.5072%2FFK1465406644"
+            rel="edit"
+    />
+    <link
+            href="http://sword-aws-dev.cdlib.org:39001/mrtsword/edit/dash_cdl/doi%3A10.5072%2FFK1465406644"
+            rel="http://purl.org/net/sword/terms/add"
+    />
+    <link
+            href="http://merritt-dev.cdlib.org/d/ark%3A%2F99999%2Ffk47h1tz4k"
+            rel="edit-media"
+    />
+    <treatment xmlns="http://purl.org/net/sword/terms/">no treatment information available</treatment>
+    <link
+            href="http://n2t.net/ark:/99999/fk47h1tz4k" rel="alternate"
+    />
+</entry>

data/spec/data/deposit_receipt_spec.xml

@@ -0,0 +1,58 @@
+<entry xmlns="http://www.w3.org/2005/Atom"
+       xmlns:sword="http://purl.org/net/sword/"
+       xmlns:dcterms="http://purl.org/dc/terms/">
+
+    <title>My Deposit</title>
+    <id>info:something:1</id>
+    <updated>2008-08-18T14:27:08Z</updated>
+    <summary type="text">A summary</summary>
+    <generator uri="http://www.myrepository.ac.uk/sword-plugin" version="1.0"/>
+
+    <!-- the item's metadata -->
+    <dcterms:abstract>The abstract</dcterms:abstract>
+    <dcterms:accessRights>Access Rights</dcterms:accessRights>
+    <dcterms:alternative>Alternative Title</dcterms:alternative>
+    <dcterms:available>Date Available</dcterms:available>
+    <dcterms:bibliographicCitation>Bibliographic Citation</dcterms:bibliographicCitation>
+    <dcterms:contributor>Contributor</dcterms:contributor>
+    <dcterms:description>Description</dcterms:description>
+    <dcterms:hasPart>Has Part</dcterms:hasPart>
+    <dcterms:hasVersion>Has Version</dcterms:hasVersion>
+    <dcterms:identifier>Identifier</dcterms:identifier>
+    <dcterms:isPartOf>Is Part Of</dcterms:isPartOf>
+    <dcterms:publisher>Publisher</dcterms:publisher>
+    <dcterms:references>References</dcterms:references>
+    <dcterms:rightsHolder>Rights Holder</dcterms:rightsHolder>
+    <dcterms:source>Source</dcterms:source>
+    <dcterms:title>Title</dcterms:title>
+    <dcterms:type>Type</dcterms:type>
+
+    <sword:verboseDescription>Verbose description</sword:verboseDescription>
+    <sword:treatment>Unpacked. JPEG contents converted to JPEG2000.</sword:treatment>
+
+    <link rel="alternate" href="http://www.swordserver.ac.uk/col1/mydeposit.html"/>
+    <content type="application/zip" src="http://www.swordserver.ac.uk/col1/mydeposit"/>
+    <link rel="edit-media" href="http://www.swordserver.ac.uk/col1/mydeposit"/>
+    <link rel="edit" href="http://www.swordserver.ac.uk/col1/mydeposit.atom" />
+    <link rel="http://purl.org/net/sword/terms/add" href="http://www.swordserver.ac.uk/col1/mydeposit.atom" />
+    <sword:packaging>http://purl.org/net/sword/package/BagIt</sword:packaging>
+
+    <link rel="http://purl.org/net/sword/terms/originalDeposit"
+          type="application/zip"
+          href="http://www.swordserver.ac.uk/col1/mydeposit/package.zip"/>
+    <link rel="http://purl.org/net/sword/terms/derivedResource"
+          type="application/pdf"
+          href="http://www.swordserver.ac.uk/col1/mydeposit/file1.pdf"/>
+    <link rel="http://purl.org/net/sword/terms/derivedResource"
+          type="application/pdf"
+          href="http://www.swordserver.ac.uk/col1/mydeposit/file2.pdf"/>
+
+    <link rel="http://purl.org/net/sword/terms/statement"
+          type="application/atom+xml;type=feed"
+          href="http://www.swordserver.ac.uk/col1/mydeposit.feed"/>
+    <link rel="http://purl.org/net/sword/terms/statement"
+          type="application/rdf+xml"
+          href="http://www.swordserver.ac.uk/col1/mydeposit.rdf"/>
+
+
+</entry>

data/spec/rspec_custom_matchers.rb

@@ -0,0 +1,118 @@
+require 'rspec/expectations'
+
+# Workaround for https://github.com/rspec/rspec-mocks/issues/1086
+class RSpec::Mocks::ErrorGenerator # rubocop:disable Style/ClassAndModuleChildren
+  unless respond_to?(:_default_error_message)
+    alias _default_error_message default_error_message
+
+    def default_error_message(expectation, expected_args, actual_args)
+      failures = [_default_error_message(expectation, expected_args, actual_args)]
+      expectation.expected_args.each do |expected|
+        if expected.respond_to?(:failure_message)
+          failures << expected.failure_message
+        end
+      end
+      failures.join("\n  ")
+    end
+  end
+end
+
+def value_for(key:, in_hash:)
+  matching_key = in_hash.keys.find { |k| k.to_s.casecmp(key.to_s.downcase).zero? }
+  in_hash[matching_key] if matching_key
+end
+
+def header?(key:, value:, in_hash:)
+  actual_values = value_for(key: key, in_hash: in_hash)
+  actual_values = [actual_values] unless actual_values.is_a?(Array)
+  actual_values.find do |actual_value|
+    if value.nil?
+      actual_value.nil?
+    elsif value.respond_to?(:match)
+      actual_value && value.match(actual_value)
+    else
+      value == actual_value
+    end
+  end
+end
+
+def all?(headers:, in_hash:)
+  headers.each do |k, v|
+    return false unless header?(key: k, value: v, in_hash: in_hash)
+  end
+  true
+end
+
+def basic_auth(username, password)
+  'Basic ' + ["#{username}:#{password}"].pack('m').delete("\r\n")
+end
+
+RSpec::Matchers.define :request do
+  match do |actual|
+    failures_for(actual).empty?
+  end
+
+  failure_message do |actual|
+    failures_for(actual).join('; ')
+  end
+
+  chain :with_method do |method|
+    @method = method
+  end
+
+  chain :with_uri do |expected_uri|
+    @expected_uri = expected_uri
+    # actual.uri == expected_uri
+  end
+
+  chain :with_headers do |expected_headers|
+    @expected_headers = expected_headers
+    # has_all(headers: expected_headers, in_hash: actual.to_hash).empty
+  end
+
+  chain :with_auth do |username, password|
+    @expected_auth = basic_auth(username, password)
+    # value_for(key: 'Authorization', in_hash: actual.to_hash) == @expected_auth ? true : false
+  end
+
+  def failures_for(actual) # rubocop:disable Metrics/AbcSize, Metrics/CyclomaticComplexity
+    return ["Expected Net::HTTPRequest, got: #{actual.class}"] unless actual.is_a?(Net::HTTPRequest)
+    failures = []
+    failures << "Expected method #{@method}, got: #{actual.method}" if bad_method(actual)
+    failures << "Expected uri #{@expected_uri}, got: #{actual.uri}" if bad_uri(actual)
+    failures << "Expected headers #{expected_headers}, got: #{actual.to_hash}" if bad_headers(actual)
+    failures << "Expected Authorization header #{@expected_auth}, got: #{value_for(key: 'Authorization', in_hash: actual.to_hash) || 'nil'}" if bad_auth(actual)
+    failures
+  end
+
+  def bad_method(actual)
+    actual.method != @method.to_s.upcase if @method
+  end
+
+  def bad_uri(actual)
+    actual.uri != @expected_uri if @expected_uri
+  end
+
+  def bad_headers(actual)
+    !all?(headers: @expected_headers, in_hash: actual.to_hash) if @expected_headers
+  end
+
+  def bad_auth(actual)
+    !header?(key: 'Authorization', value: @expected_auth, in_hash: actual.to_hash) if @expected_auth
+  end
+
+end
+
+RSpec::Matchers.define :include_header do |k, v|
+  def matching_key(k, actual)
+    actual.keys.find { |k2| k2.to_s.casecmp(k.to_s.downcase).zero? }
+  end
+
+  match do |actual|
+    all?(headers: { k => v }, in_hash: actual)
+  end
+
+  failure_message do |actual|
+    "expected #{k}: #{v} but found #{value_for(key: k, in_hash: actual) || 'nil'}"
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,33 @@
+# ------------------------------------------------------------
+# SimpleCov setup
+
+if ENV['COVERAGE']
+  require 'simplecov'
+  require 'simplecov-console'
+
+  SimpleCov.minimum_coverage 100
+  SimpleCov.start do
+    add_filter '/spec/'
+    SimpleCov.formatter = SimpleCov::Formatter::MultiFormatter[
+      SimpleCov::Formatter::HTMLFormatter,
+      SimpleCov::Formatter::Console,
+    ]
+  end
+end
+
+# ------------------------------------------------------------
+# Rspec configuration
+
+require 'rspec'
+
+RSpec.configure do |config|
+  config.raise_errors_for_deprecations!
+  config.mock_with :rspec
+end
+
+require 'rspec_custom_matchers'
+
+# ------------------------------------------------------------
+# Code under test
+
+require 'stash/sword'

data/spec/unit/stash/sword2/client_spec.rb

@@ -0,0 +1,110 @@
+require 'spec_helper'
+require 'webmock/rspec'
+
+module Stash
+  module Sword
+    describe Client do
+      attr_reader :username, :client, :password, :on_behalf_of, :zipfile, :doi, :collection_uri
+
+      before(:each) do
+        @username       = 'ucb_dash_submitter'
+        @password       = 'ucb_dash_password'
+        @collection_uri = 'http://uc3-mrtsword-dev.cdlib.org:39001/mrtsword/collection/dash_ucb'
+        @on_behalf_of   = 'ucb_dash_author'
+        @client         = Client.new(collection_uri: @collection_uri, username: @username, password: @password, on_behalf_of: @on_behalf_of)
+        @zipfile        = 'examples/uploads/example.zip'
+        @doi            = "doi:10.5072/FK#{Time.now.getutc.xmlschema.gsub(/[^0-9a-z]/i, '')}"
+      end
+
+      describe '#create' do
+        it 'POSTs with the correct headers' do
+          authorized_uri = collection_uri.sub('http://', "http://#{username}:#{password}@")
+
+          stub_request(:post, authorized_uri).to_return(
+            body: '<entry xmlns="http://www.w3.org/2005/Atom"><id>http://merritt.cdlib.org/sword/v2/object/ark:/99999/fk4t157x4p</id><author><name>ucb_dash_submitter</name></author><generator uri="http://www.swordapp.org/" version="2.0" /><link href="http://merritt.cdlib.org/sword/v2/object/ark:/99999/fk4t157x4p" rel="edit" /><link href="http://merritt.cdlib.org/sword/v2/object/ark:/99999/fk4t157x4p" rel="http://purl.org/net/sword/terms/add" /><link href="http://merritt.cdlib.org/sword/v2/object/ark:/99999/fk4t157x4p" rel="edit-media" /><treatment xmlns="http://purl.org/net/sword/terms/">no treatment information available</treatment></entry>'
+          )
+
+          client.create(zipfile: zipfile, doi: doi)
+
+          md5 = Digest::MD5.file(zipfile).to_s
+
+          actual_headers = nil
+          expect(a_request(:post, authorized_uri).with do |req|
+            actual_headers = req.headers
+          end).to have_been_made
+
+          aggregate_failures('request headers') do
+            {
+              'On-Behalf-Of' => on_behalf_of,
+              'Packaging' => 'http://purl.org/net/sword/package/SimpleZip',
+              'Slug' => doi,
+              'Content-Disposition' => 'attachment; filename=example.zip',
+              'Content-MD5' => md5,
+              'Content-Length' => /[0-9]+/,
+              'Content-Type' => 'application/zip'
+            }.each do |k, v|
+              expect(actual_headers).to include_header(k, v)
+            end
+          end
+        end
+
+        it 'returns the entry'
+        it "gets the entry from the Edit-IRI in the Location: header if it isn't returned in the body"
+        it 'forwards a success response'
+        it 'forwards a 4xx error'
+        it 'forwards a 5xx error'
+        it 'forwards an internal exception'
+      end
+
+      describe '#update' do
+        it 'PUTs with the correct headers' do
+          edit_iri = "http://merritt.cdlib.org/sword/v2/object/#{doi}"
+          authorized_uri = edit_iri.sub('http://', "http://#{username}:#{password}@")
+
+          stub_request(:put, authorized_uri)
+
+          client.update(edit_iri: edit_iri, zipfile: zipfile)
+
+          md5 = Digest::MD5.file(zipfile).to_s
+
+          actual_body = nil
+          actual_headers = nil
+          expect(a_request(:put, authorized_uri).with do |req|
+            actual_body = req.body
+            actual_headers = req.headers
+          end).to have_been_made
+
+          aggregate_failures('request headers') do
+            {
+              'Content-Length' => /[0-9]+/,
+              'Content-Type' => %r{multipart/related; type="application/atom\+xml"; boundary=.*},
+              'On-Behalf-Of' => on_behalf_of
+            }.each do |k, v|
+              expect(actual_headers).to include_header(k, v)
+            end
+          end
+
+          mime_headers = {
+            'Packaging' => 'http://purl.org/net/sword/package/SimpleZip',
+            'Content-Disposition' => 'attachment; name=payload; filename="example.zip"',
+            'Content-Type' => 'application/zip',
+            'Content-MD5' => md5
+          }
+
+          aggregate_failures('MIME headers') do
+            mime_headers.each do |k, v|
+              expect(actual_body).to include("#{k}: #{v}"), "expected #{k}: #{v}, closest match was #{actual_body[/#{k}[^\n]+/m]}"
+            end
+          end
+        end
+
+        it 'does something clever and asynchronous'
+        it 'forwards a success response'
+        it 'forwards a 4xx error'
+        it 'forwards a 5xx error'
+        it 'forwards an internal exception'
+      end
+
+    end
+  end
+end

data/spec/unit/stash/sword2/deposit_receipt_spec.rb

@@ -0,0 +1,48 @@
+require 'spec_helper'
+
+module Stash
+  module Sword
+    describe DepositReceipt do
+      describe '#parse_xml' do
+
+        it 'parses the response from the spec' do
+          xml = File.read('spec/data/deposit_receipt_spec.xml')
+          receipt = DepositReceipt.parse_xml(xml)
+          expect(receipt).to be_a(DepositReceipt)
+
+          em_iri = receipt.link(rel: 'edit-media')
+          expect(em_iri.href).to eq(URI('http://www.swordserver.ac.uk/col1/mydeposit'))
+
+          se_iri = receipt.link(rel: URI('http://purl.org/net/sword/terms/add'))
+          expect(se_iri.href).to eq(URI('http://www.swordserver.ac.uk/col1/mydeposit.atom'))
+
+          edit_iri = receipt.link(rel: 'edit')
+          expect(edit_iri.href).to eq(URI('http://www.swordserver.ac.uk/col1/mydeposit.atom'))
+
+          expect(receipt.em_iri).to eq(em_iri.href)
+          expect(receipt.se_iri).to eq(se_iri.href)
+          expect(receipt.edit_iri).to eq(edit_iri.href)
+        end
+
+        it 'parses a Merritt response' do
+          xml = File.read('spec/data/deposit_receipt_merritt.xml')
+          receipt = DepositReceipt.parse_xml(xml)
+          expect(receipt).to be_a(DepositReceipt)
+
+          em_iri = receipt.link(rel: 'edit-media')
+          expect(em_iri.href).to eq(URI('http://merritt-dev.cdlib.org/d/ark%3A%2F99999%2Ffk47h1tz4k'))
+
+          se_iri = receipt.link(rel: URI('http://purl.org/net/sword/terms/add'))
+          expect(se_iri.href).to eq(URI('http://sword-aws-dev.cdlib.org:39001/mrtsword/edit/dash_cdl/doi%3A10.5072%2FFK1465406644'))
+
+          edit_iri = receipt.link(rel: 'edit')
+          expect(edit_iri.href).to eq(URI('http://sword-aws-dev.cdlib.org:39001/mrtsword/edit/dash_cdl/doi%3A10.5072%2FFK1465406644'))
+
+          expect(receipt.em_iri).to eq(em_iri.href)
+          expect(receipt.se_iri).to eq(se_iri.href)
+          expect(receipt.edit_iri).to eq(edit_iri.href)
+        end
+      end
+    end
+  end
+end

data/spec/unit/stash/sword2/http_helper_get_spec.rb

@@ -0,0 +1,131 @@
+require 'spec_helper'
+
+module Stash
+  module Sword
+    describe HTTPHelper do
+
+      # ------------------------------------------------------------
+      # Fixture
+
+      attr_writer :user_agent
+
+      def user_agent
+        @user_agent ||= 'elvis'
+      end
+
+      attr_writer :helper
+
+      def helper
+        @helper ||= HTTPHelper.new(user_agent: user_agent)
+      end
+
+      # ------------------------------------------------------------
+      # Tests
+
+      describe '#get' do
+
+        # ------------------------------
+        # Fixture
+
+        before(:each) do
+          @http = instance_double(Net::HTTP)
+          allow(Net::HTTP).to receive(:new).and_return(@http)
+          allow(@http).to receive(:start).and_yield(@http)
+          @success = Net::HTTPOK.allocate
+          @body    = 'I am the body of the response'
+          allow(@success).to receive(:body).and_return(@body)
+        end
+
+        # ------------------------------
+        # Tests
+
+        it 'gets the specified URI' do
+          uri = URI('http://example.org/')
+          expect(@http).to receive(:request).with(request.with_method('GET').with_uri(uri)).and_yield(@success)
+          helper.get(uri: uri)
+        end
+
+        it 'gets a response' do
+          expect(@http).to receive(:request).and_yield(@success)
+          expect(helper.get(uri: URI('http://example.org/'))).to be(@body)
+        end
+
+        it 'sets the User-Agent header' do
+          agent  = 'Not Elvis'
+          helper = HTTPHelper.new(user_agent: agent)
+          expect(@http).to receive(:request).with(request.with_method('GET').with_headers('User-Agent' => agent)).and_yield(@success)
+          helper.get(uri: URI('http://example.org/'))
+        end
+
+        it 'sets Basic-Auth headers' do
+          uri = URI('http://example.org/')
+          expect(@http).to receive(:request).with(request.with_method('GET').with_uri(uri).with_auth('elvis', 'presley')).and_yield(@success)
+          helper = HTTPHelper.new(user_agent: user_agent, username: 'elvis', password: 'presley')
+          helper.get(uri: uri)
+        end
+
+        it 'uses SSL for https requests' do
+          uri = URI('https://example.org/')
+          expect(Net::HTTP).to receive(:start).with(uri.hostname, uri.port, use_ssl: true).and_call_original
+          expect(@http).to receive(:request).and_yield(@success)
+          helper.get(uri: uri)
+        end
+
+        it 're-requests on receiving a 1xx' do
+          uri   = URI('http://example.org/')
+          @info = Net::HTTPContinue.allocate
+
+          expected = [@info, @success]
+          expect(@http).to receive(:request).twice.with(request.with_method('GET').with_uri(uri).with_headers('User-Agent' => user_agent)) do |&block|
+            block.call(expected.shift)
+          end
+
+          expect(helper.get(uri: uri)).to be(@body)
+        end
+
+        it 'redirects on receiving a 3xx' do
+          uri       = URI('http://example.org/')
+          uri2      = URI('http://example.org/new')
+          @redirect = Net::HTTPMovedPermanently.allocate
+          allow(@redirect).to receive(:[]).with('location').and_return(uri2.to_s)
+          expect(@http).to receive(:request).with(request.with_method('GET').with_uri(uri).with_headers('User-Agent' => user_agent)).and_yield(@redirect)
+          expect(@http).to receive(:request).with(request.with_method('GET').with_uri(uri2).with_headers('User-Agent' => user_agent)).and_yield(@success)
+          expect(helper.get(uri: uri)).to be(@body)
+        end
+
+        it 'only redirects a limited number of times' do
+          uri       = URI('http://example.org/')
+          @redirect = Net::HTTPMovedPermanently.allocate
+          allow(@redirect).to receive(:[]).with('location').and_return(uri.to_s)
+          expect(@http).to receive(:request).with(request.with_method('GET').with_uri(uri).with_headers('User-Agent' => user_agent)).exactly(HTTPHelper::DEFAULT_MAX_REDIRECTS).times.and_yield(@redirect)
+          expect { helper.get(uri: uri) }.to raise_error do |e|
+            expect(e.message).to match(/Redirect limit.*exceeded.*#{uri.to_s}/)
+          end
+        end
+
+        it 'fails on a 4xx' do
+          @error = Net::HTTPForbidden
+          allow(@error).to receive(:code).and_return(403)
+          allow(@error).to receive(:message).and_return('Forbidden')
+          expect(@http).to receive(:request).and_yield(@error)
+          uri = URI('http://example.org/')
+          expect { helper.get(uri: uri) }.to raise_error do |e|
+            expect(e.message).to match(/403.*Forbidden.*#{uri.to_s}/)
+          end
+        end
+
+        it 'fails on a 5xx' do
+          @error = Net::HTTPServerError
+          allow(@error).to receive(:code).and_return(500)
+          allow(@error).to receive(:message).and_return('Internal Server Error')
+          expect(@http).to receive(:request).and_yield(@error)
+          uri = URI('http://example.org/')
+          expect { helper.get(uri: uri) }.to raise_error do |e|
+            expect(e.message).to match(/500.*Internal Server Error.*#{uri.to_s}/)
+          end
+        end
+      end
+
+    end
+  end
+end