resync-client 0.1.0

data/lib/resync/client/zip_package.rb

@@ -0,0 +1,66 @@
+require 'rexml/document'
+require 'zip'
+require_relative 'bitstream'
+
+module Resync
+  # A ZIP package of resources or changes, providing access to individual
+  # bitstreams based on the included manifest file.
+  #
+  class ZipPackage
+
+    # ------------------------------------------------------------
+    # Attributes
+
+    # @return [Zip::File] the ZIP file wrapped by this package
+    attr_reader :zipfile
+
+    # @return [ResourceDumpManifest, ChangeDumpManifest] the manifest
+    #   for the ZIP package
+    attr_reader :manifest
+
+    # ------------------------------------------------------------
+    # Initializer
+
+    # Creates a new +ZipPackage+ for the specified file.
+    #
+    # @param zipfile [Zip::File, String] the ZIP file, or a path to it.
+    def initialize(zipfile)
+      self.zipfile = zipfile
+    end
+
+    # ------------------------------------------------------------
+    # Public methods
+
+    # Gets the bitstream for the specified resource. (Note that this
+    # does no validation; if the resource is not in the manifest, or
+    # the corresponding entry is not in the ZIP file, the behavior of
+    # the returned {Bitstream} is undefined.)
+    #
+    # @return [Bitstream] a bitstream wrapping the ZIP entry for the
+    #   specified resource.
+    def bitstream_for(resource)
+      Bitstream.new(zipfile: @zipfile, resource: resource)
+    end
+
+    # Gets all bitstreams declared in the package manifest.
+    # @return [Array<Bitstream>] a list of all bitstreams in the package
+    def bitstreams
+      manifest.resources.map { |r| bitstream_for(r) }
+    end
+
+    # ------------------------------------------------------------
+    # Private methods
+
+    private
+
+    def zipfile=(value)
+      zipfile = value.is_a?(Zip::File) ? value : Zip::File.open(value)
+      manifest_entry = zipfile.find_entry('manifest.xml')
+      fail "No manifest.xml found in zipfile #{zipfile.name}" unless manifest_entry
+      manifest_stream = manifest_entry.get_input_stream
+      @manifest = XMLParser.parse(manifest_stream)
+      @zipfile = zipfile
+    end
+
+  end
+end

data/lib/resync/client.rb

@@ -0,0 +1,3 @@
+require 'resync'
+
+Dir.glob(File.expand_path('../client/*.rb', __FILE__), &method(:require))

data/resync-client.gemspec

@@ -0,0 +1,35 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+
+require 'resync/client/version'
+require 'uri'
+
+Gem::Specification.new do |spec|
+  spec.name = 'resync-client'
+  spec.version = Resync::Client::VERSION
+  spec.authors = ['David Moles']
+  spec.email = ['david.moles@ucop.edu']
+  spec.summary = 'Client library for ResourceSync'
+  spec.description = 'A Ruby client for the ResourceSync web synchronization framework'
+  spec.license = 'MIT'
+
+  origin_uri = URI(`git config --get remote.origin.url`.chomp)
+  spec.homepage = URI::HTTP.build(host: origin_uri.host, path: origin_uri.path.chomp('.git')).to_s
+
+  spec.files = `git ls-files -z`.split("\x0")
+  spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ['lib']
+
+  spec.add_dependency 'resync', '~> 0.1.0'
+  spec.add_dependency 'rubyzip', '~> 1.1.7'
+
+  spec.add_development_dependency 'equivalent-xml', '~> 0.6.0'
+  spec.add_development_dependency 'rake', '~> 10.4'
+  spec.add_development_dependency 'rspec', '~> 3.2'
+  spec.add_development_dependency 'rubocop', '~> 0.29.1'
+  spec.add_development_dependency 'simplecov', '~> 0.9.2'
+  spec.add_development_dependency 'simplecov-console', '~> 0.2.0'
+  spec.add_development_dependency 'yard', '~> 0.8'
+end

data/spec/data/examples/capability-list.xml

@@ -0,0 +1,25 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+        xmlns:rs="http://www.openarchives.org/rs/terms/">
+  <rs:ln rel="describedby"
+         href="http://example.com/info_about_set1_of_resources.xml"/>
+  <rs:ln rel="up"
+         href="http://example.com/resourcesync_description.xml"/>
+  <rs:md capability="capabilitylist"/>
+  <url>
+    <loc>http://example.com/dataset1/resourcelist.xml</loc>
+    <rs:md capability="resourcelist"/>
+  </url>
+  <url>
+    <loc>http://example.com/dataset1/resourcedump.xml</loc>
+    <rs:md capability="resourcedump"/>
+  </url>
+  <url>
+    <loc>http://example.com/dataset1/changelist.xml</loc>
+    <rs:md capability="changelist"/>
+  </url>
+  <url>
+    <loc>http://example.com/dataset1/changedump.xml</loc>
+    <rs:md capability="changedump"/>
+  </url>
+</urlset>

data/spec/data/examples/change-dump-manifest.xml

@@ -0,0 +1,41 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+        xmlns:rs="http://www.openarchives.org/rs/terms/">
+  <rs:ln rel="up"
+         href="http://example.com/dataset1/capabilitylist.xml"/>
+  <rs:md capability="changedump-manifest"
+         from="2013-01-02T00:00:00Z"
+         until="2013-01-03T00:00:00Z"/>
+  <url>
+    <loc>http://example.com/res7.html</loc>
+    <lastmod>2013-01-02T12:00:00Z</lastmod>
+    <rs:md change="created"
+           hash="md5:1c1b0e264fa9b7e1e9aa6f9db8d6362b"
+           length="4339"
+           type="text/html"
+           path="/changes/res7.html"/>
+  </url>
+  <url>
+    <loc>http://example.com/res9.pdf</loc>
+    <lastmod>2013-01-02T13:00:00Z</lastmod>
+    <rs:md change="updated"
+           hash="md5:f906610c3d4aa745cb2b986f25b37c5a"
+           length="38297"
+           type="application/pdf"
+           path="/changes/res9.pdf"/>
+  </url>
+  <url>
+    <loc>http://example.com/res5.tiff</loc>
+    <lastmod>2013-01-02T19:00:00Z</lastmod>
+    <rs:md change="deleted"/>
+  </url>
+  <url>
+    <loc>http://example.com/res7.html</loc>
+    <lastmod>2013-01-02T20:00:00Z</lastmod>
+    <rs:md change="updated"
+           hash="md5:0988647082c8bc51778894a48ec3b576"
+           length="5426"
+           type="text/html"
+           path="/changes/res7-v2.html"/>
+  </url>
+</urlset>

data/spec/data/examples/change-dump.xml

@@ -0,0 +1,41 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+        xmlns:rs="http://www.openarchives.org/rs/terms/">
+  <rs:ln rel="up"
+         href="http://example.com/dataset1/capabilitylist.xml"/>
+  <rs:md capability="changedump"
+         from="2013-01-01T00:00:00Z"/>
+  <url>
+    <loc>http://example.com/20130101-changedump.zip</loc>
+    <lastmod>2013-01-01T23:59:59Z</lastmod>
+    <rs:md type="application/zip"
+           length="3109"
+           from="2013-01-01T00:00:00Z"
+           until="2013-01-02T00:00:00Z"/>
+    <rs:ln rel="contents"
+           href="http://example.com/20130101-changedump-manifest.xml"
+           type="application/xml"/>
+  </url>
+  <url>
+    <loc>http://example.com/20130102-changedump.zip</loc>
+    <lastmod>2013-01-02T23:59:59Z</lastmod>
+    <rs:md type="application/zip"
+           length="6629"
+           from="2013-01-02T00:00:00Z"
+           until="2013-01-03T00:00:00Z"/>
+    <rs:ln rel="contents"
+           href="http://example.com/20130102-changedump-manifest.xml"
+           type="application/xml"/>
+  </url>
+  <url>
+    <loc>http://example.com/20130103-changedump.zip</loc>
+    <lastmod>2013-01-03T23:59:59Z</lastmod>
+    <rs:md type="application/zip"
+           length="8124"
+           from="2013-01-03T00:00:00Z"
+           until="2013-01-04T00:00:00Z"/>
+    <rs:ln rel="contents"
+           href="http://example.com/20130103-changedump-manifest.xml"
+           type="application/xml"/>
+  </url>
+</urlset>

data/spec/data/examples/change-list-index.xml

@@ -0,0 +1,22 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+              xmlns:rs="http://www.openarchives.org/rs/terms/">
+  <rs:ln rel="up"
+         href="http://example.com/dataset1/capabilitylist.xml"/>
+  <rs:md capability="changelist"
+         from="2013-01-01T00:00:00Z"/>
+  <sitemap>
+    <loc>http://example.com/20130101-changelist.xml</loc>
+    <rs:md from="2013-01-01T00:00:00Z"
+           until="2013-01-02T00:00:00Z"/>
+  </sitemap>
+  <sitemap>
+    <loc>http://example.com/20130102-changelist.xml</loc>
+    <rs:md from="2013-01-02T00:00:00Z"
+           until="2013-01-03T00:00:00Z"/>
+  </sitemap>
+  <sitemap>
+    <loc>http://example.com/20130103-changelist.xml</loc>
+    <rs:md from="2013-01-03T00:00:00Z"/>
+  </sitemap>
+</sitemapindex>

data/spec/data/examples/change-list.xml

@@ -0,0 +1,36 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+        xmlns:rs="http://www.openarchives.org/rs/terms/">
+  <rs:ln rel="up"
+         href="http://example.com/dataset1/capabilitylist.xml"/>
+  <rs:md capability="changelist"
+         from="2013-01-03T00:00:00Z"/>
+  <url>
+    <loc>http://example.com/res4</loc>
+    <lastmod>2013-01-03T17:00:00Z</lastmod>
+    <rs:md change="updated"
+           hash="sha-256:f4OxZX_x_DFGFDgghgdfb6rtSx-iosjf6735432nklj"
+           length="56778"
+           type="application/json"/>
+    <rs:ln rel="http://www.openarchives.org/rs/terms/patch"
+           href="http://example.com/res4-json-patch"
+           modified="2013-01-03T17:00:00Z"
+           hash="sha-256:y66dER_t_HWEIKpesdkeb7rtSc-ippjf9823742opld"
+           length="73"
+           type="application/json-patch"/>
+  </url>
+  <url>
+    <loc>http://example.com/res5-full.tiff</loc>
+    <lastmod>2013-01-03T18:00:00Z</lastmod>
+    <rs:md change="updated"
+           hash="sha-256:f4OxZX_x_FO5LcGBSKHWXfwtSx-j1ncoSt3SABJtkGk"
+           length="9788456778"
+           type="image/tiff"/>
+    <rs:ln rel="http://www.openarchives.org/rs/terms/patch"
+           href="http://example.com/res5-diff"
+           modified="2013-01-03T18:00:00Z"
+           hash="sha-256:h986gT_t_87HTkjHYE76G558hY-jdfgy76t55sadJUYT"
+           length="4533"
+           type="application/x-tiff-diff"/>
+  </url>
+</urlset>

data/spec/data/examples/resource-dump-manifest.xml

@@ -0,0 +1,25 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+        xmlns:rs="http://www.openarchives.org/rs/terms/">
+  <rs:ln rel="up"
+         href="http://example.com/dataset1/capabilitylist.xml"/>
+  <rs:md capability="resourcedump-manifest"
+         at="2013-01-03T09:00:00Z"
+         completed="2013-01-03T09:02:00Z"/>
+  <url>
+    <loc>http://example.com/res1</loc>
+    <lastmod>2013-01-02T13:00:00Z</lastmod>
+    <rs:md hash="md5:1584abdf8ebdc9802ac0c6a7402c03b6"
+           length="8876"
+           type="text/html"
+           path="/resources/res1"/>
+  </url>
+  <url>
+    <loc>http://example.com/res2</loc>
+    <lastmod>2013-01-02T14:00:00Z</lastmod>
+    <rs:md hash="md5:1e0d5cb8ef6ba40c99b14c0237be735e sha-256:854f61290e2e197a11bc91063afce22e43f8ccc655237050ace766adc68dc784"
+           length="14599"
+           type="application/pdf"
+           path="/resources/res2"/>
+  </url>
+</urlset>

data/spec/data/examples/resource-dump.xml

@@ -0,0 +1,39 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+        xmlns:rs="http://www.openarchives.org/rs/terms/">
+  <rs:ln rel="up"
+         href="http://example.com/dataset1/capabilitylist.xml"/>
+  <rs:md capability="resourcedump"
+         at="2013-01-03T09:00:00Z"
+         completed="2013-01-03T09:04:00Z"/>
+  <url>
+    <loc>http://example.com/resourcedump-part1.zip</loc>
+    <rs:md type="application/zip"
+           length="4765"
+           at="2013-01-03T09:00:00Z"
+           completed="2013-01-03T09:02:00Z"/>
+    <rs:ln rel="contents"
+           href="http://example.com/resourcedump_manifest-part1.xml"
+           type="application/xml"/>
+  </url>
+  <url>
+    <loc>http://example.com/resourcedump-part2.zip</loc>
+    <rs:md type="application/zip"
+           length="9875"
+           at="2013-01-03T09:01:00Z"
+           completed="2013-01-03T09:03:00Z"/>
+    <rs:ln rel="contents"
+           href="http://example.com/resourcedump_manifest-part2.xml"
+           type="application/xml"/>
+  </url>
+  <url>
+    <loc>http://example.com/resourcedump-part3.zip</loc>
+    <rs:md type="application/zip"
+           length="2298"
+           at="2013-01-03T09:03:00Z"
+           completed="2013-01-03T09:04:00Z"/>
+    <rs:ln rel="contents"
+           href="http://example.com/resourcedump_manifest-part3.xml"
+           type="application/xml"/>
+  </url>
+</urlset>

data/spec/data/examples/resource-list-index.xml

@@ -0,0 +1,21 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+              xmlns:rs="http://www.openarchives.org/rs/terms/">
+  <rs:ln rel="up"
+         href="http://example.com/dataset1/capabilitylist.xml"/>
+  <rs:md capability="resourcelist"
+         at="2013-01-03T09:00:00Z"
+         completed="2013-01-03T09:10:00Z"/>
+  <sitemap>
+    <loc>http://example.com/resourcelist1.xml</loc>
+    <rs:md at="2013-01-03T09:00:00Z"/>
+  </sitemap>
+  <sitemap>
+    <loc>http://example.com/resourcelist2.xml</loc>
+    <rs:md at="2013-01-03T09:03:00Z"/>
+  </sitemap>
+  <sitemap>
+    <loc>http://example.com/resourcelist3.xml</loc>
+    <rs:md at="2013-01-03T09:07:00Z"/>
+  </sitemap>
+</sitemapindex>

data/spec/data/examples/resource-list.xml

@@ -0,0 +1,24 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+        xmlns:rs="http://www.openarchives.org/rs/terms/">
+  <rs:ln rel="up"
+         href="http://example.com/dataset1/capabilitylist.xml"/>
+  <rs:ln rel="index"
+         href="http://example.com/dataset1/resourcelist-index.xml"/>
+  <rs:md capability="resourcelist"
+         at="2013-01-03T09:00:00Z"/>
+  <url>
+    <loc>http://example.com/res3</loc>
+    <lastmod>2013-01-02T13:00:00Z</lastmod>
+    <rs:md hash="md5:1584abdf8ebdc9802ac0c6a7402c8753"
+           length="4385"
+           type="application/pdf"/>
+  </url>
+  <url>
+    <loc>http://example.com/res4</loc>
+    <lastmod>2013-01-02T14:00:00Z</lastmod>
+    <rs:md hash="md5:4556abdf8ebdc9802ac0c6a7402c9881"
+           length="883"
+           type="image/png"/>
+  </url>
+</urlset>

data/spec/data/examples/source-description.xml

@@ -0,0 +1,25 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+        xmlns:rs="http://www.openarchives.org/rs/terms/">
+  <rs:ln rel="describedby"
+         href="http://example.com/info_about_source.xml"/>
+  <rs:md capability="description"/>
+  <url>
+    <loc>http://example.com/capabilitylist1.xml</loc>
+    <rs:md capability="capabilitylist"/>
+    <rs:ln rel="describedby"
+           href="http://example.com/info_about_set1_of_resources.xml"/>
+  </url>
+  <url>
+    <loc>http://example.com/capabilitylist2.xml</loc>
+    <rs:md capability="capabilitylist"/>
+    <rs:ln rel="describedby"
+           href="http://example.com/info_about_set2_of_resources.xml"/>
+  </url>
+  <url>
+    <loc>http://example.com/capabilitylist3.xml</loc>
+    <rs:md capability="capabilitylist"/>
+    <rs:ln rel="describedby"
+           href="http://example.com/info_about_set3_of_resources.xml"/>
+  </url>
+</urlset>

data/spec/data/resourcedump/manifest.xml

@@ -0,0 +1,18 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+        xmlns:rs="http://www.openarchives.org/rs/terms/">
+  <rs:md capability="resourcedump-manifest"
+         at="2015-05-05T16:19:25Z"/>
+  <url>
+    <loc>http://example.com/res1</loc>
+    <lastmod>2015-05-22T16:14:55Z</lastmod>
+    <rs:md hash="md5:51b99b46c9980623b36b27e06a7e4a46"
+           path="/resources/res1"/>
+  </url>
+  <url>
+    <loc>http://example.com/res2</loc>
+    <lastmod>2015-05-22T16:16:04Z</lastmod>
+    <rs:md hash="md5:6205d276e0c120eb4bac47c14a8297d8"
+           path="/resources/res2"/>
+  </url>
+</urlset>

data/spec/data/resourcedump/resourcedump.xml

@@ -0,0 +1,16 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+        xmlns:rs="http://www.openarchives.org/rs/terms/">
+  <rs:ln rel="up"
+         href="http://example.com/capabilitylist.xml"/>
+  <rs:md capability="resourcedump"
+         at="2015-05-22T16:06:04Z"
+         completed="2015-05-05T16:23:20Z"/>
+  <url>
+    <loc>http://example.com/resourcedump.zip</loc>
+    <rs:md type="application/zip"
+           length="1334"
+           at="2015-05-22T16:06:04Z"
+           completed="2015-05-05T16:23:20Z"/>
+  </url>
+ </urlset>

data/spec/data/resourcedump/resources/res1

@@ -0,0 +1,7 @@
+Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do
+eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad
+minim veniam, quis nostrud exercitation ullamco laboris nisi ut
+aliquip ex ea commodo consequat. Duis aute irure dolor in
+reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla
+pariatur. Excepteur sint occaecat cupidatat non proident, sunt in
+culpa qui officia deserunt mollit anim id est laborum.

data/spec/data/resourcedump/resources/res2

@@ -0,0 +1,7 @@
+Quo usque tandem abutere, Catilina, patientia nostra? quam diu etiam
+furor iste tuus nos eludet? quem ad finem sese effrenata iactabit
+audacia? Nihilne te nocturnum praesidium Palati, nihil urbis vigiliae,
+nihil timor populi, nihil concursus bonorum omnium, nihil hic
+munitissimus habendi senatus locus, nihil horum ora voltusque
+moverunt? Patere tua consilia non sentis, constrictam iam horum omnium
+scientia teneri coniurationem tuam non vides?

data/spec/rspec_custom_matchers.rb

@@ -0,0 +1,11 @@
+require 'rspec/expectations'
+
+RSpec::Matchers.define :request_for do |h|
+  match do |actual|
+    begin
+      !h.key?(:uri) || actual.uri == h[:uri] &&
+        !h.key?(:method) || actual.method == h[:method] &&
+          !h.key?(:headers) || actual.to_hash == h[:headers]
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,31 @@
+# ------------------------------------------------------------
+# 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
+
+RSpec.configure do |config|
+  config.raise_errors_for_deprecations!
+  config.mock_with :rspec
+end
+
+require 'rspec_custom_matchers'
+
+# ------------------------------------------------------------
+# resync-client
+
+require 'resync/client'

data/spec/todo.rb

@@ -0,0 +1,65 @@
+require 'rspec/core'
+require 'resync/client'
+
+# List of TODO items in spec form
+module Resync
+  describe Client do
+    describe 'discovery' do
+      it 'retrieves a Source Description from a URI'
+    end
+
+    describe 'capability lists' do
+      it 'retrieves a Capability List from a URI'
+    end
+
+    describe 'resource lists' do
+      it 'retrieves a Resource List from a URI'
+    end
+
+    describe 'resource list indices' do
+      it 'retrieves a Resource List Index from a URI'
+    end
+
+    describe 'resource dumps' do
+      it 'retrieves a Resource Dump from a URI'
+      describe 'bitstream packages' do
+        it 'can download and cache a bitstream package'
+        it 'can extract a resource dump manifest from a ZIP bitstream package'
+        it 'can extract a resource from a ZIP bitstream package based on a path in a manifest'
+      end
+    end
+
+    describe 'resource dump manifests' do
+      it 'retrieves a Resource Dump Manifest from a URI'
+    end
+
+    describe 'change lists' do
+      it 'retrieves a Change List from a URI'
+    end
+
+    describe 'change list indices' do
+      it 'retrieves a Change List Index from a URI'
+    end
+
+    describe 'change dumps' do
+      it 'retrieves a Change Dump from a URI'
+      describe 'bitstream packages' do
+        it 'gets the "contents" link URI for the change dump manifest, if present'
+        it 'can download and cache a bitstream package'
+        it 'can extract a change dump manifest from a ZIP bitstream package'
+        it 'can extract a resource from a ZIP bitstream package based on a path in a manifest'
+      end
+    end
+
+    describe 'change dump manifests' do
+      it 'retrieves a Change Dump Manifest from a URI'
+    end
+
+    describe 'error handling' do
+      it 'handles server errors gracefully'
+    end
+
+    it 'does something clever for mirrors, alternate representations, and related resources'
+
+  end
+end