oai 0.0.13 → 0.1.0

data/Rakefile

@@ -1,42 +1,21 @@
-RUBY_OAI_VERSION = '0.0.13'
 
 require 'rubygems'
 require 'rake'
+begin
+  require 'bundler/setup'
+rescue LoadError
+  puts 'You must `gem install bundler` and `bundle install` to run rake tasks'
+end
+
+Bundler::GemHelper.install_tasks
+
 require 'rake/testtask'
-require 'rake/rdoctask'
-require 'rake/packagetask'
-require 'rake/gempackagetask'
+require 'rdoc/task'
 
 task :default => ["test"]
 
 task :test => ["test:client", "test:provider"]
 
-spec = Gem::Specification.new do |s|
-    s.name = 'oai'
-    s.version = RUBY_OAI_VERSION
-    s.author = 'Ed Summers'
-    s.email = 'ehs@pobox.com'
-    s.homepage = 'http://www.textualize.com/ruby_oai_0'
-    s.platform = Gem::Platform::RUBY
-    s.summary = 'A ruby library for working with the Open Archive Initiative Protocol for Metadata Harvesting (OAI-PMH)'
-    s.require_path = 'lib'
-    s.autorequire = 'oai'
-    s.bindir = 'bin'
-    s.executables = 'oai'
-
-    s.add_dependency('builder', '>=2.0.0')
-    
-    s.files = %w(README.md Rakefile) +
-      Dir.glob("{bin,test,lib}/**/*") + 
-      Dir.glob("examples/**/*.rb")
-end
-
-Rake::GemPackageTask.new(spec) do |pkg|
-  pkg.need_zip = true
-  pkg.need_tar = true
-  pkg.gem_spec = spec
-end
-
 namespace :test do
   Rake::TestTask.new('client') do |t|
     t.libs << ['lib', 'test/client']
@@ -62,13 +41,40 @@ namespace :test do
   task :coverage do
     rm_f "coverage"
     rm_f "coverage.data"
-    system("rcov --aggregate coverage.data --text-summary -Ilib:test/provider test/provider/tc_*.rb")
-    system("rcov --aggregate coverage.data --text-summary -Ilib:test/client test/client/tc_*.rb")
-    system("open coverage/index.html") if PLATFORM['darwin']
+    if RUBY_VERSION =~ /^1.8/
+      Rake::Task['rcov:client'].invoke
+      Rake::Task['rcov:provider'].invoke
+    else
+      ENV['COVERAGE'] = 'true'
+      Rake::Task['test:client'].invoke
+      Rake::Task['test:provider'].invoke
+    end
+
+    system("open coverage/index.html") if (PLATFORM['darwin'] if Kernel.const_defined? :PLATFORM) || (RUBY_PLATFORM =~ /darwin/ if Kernel.const_defined? :RUBY_PLATFORM)
   end
 
 end
 
+if RUBY_VERSION =~ /^1.8/
+  require 'rcov/rcovtask'
+  namespace :rcov do
+    Rcov::RcovTask.new do |t|
+      t.name = 'client'
+      t.libs << ['lib', 'test/client']
+      t.pattern = 'test/client/tc_*.rb'
+      t.verbose = true
+      t.rcov_opts = ['--aggregate coverage.data', '--text-summary']
+    end
+
+    Rcov::RcovTask.new('provider') do |t|
+      t.libs << ['lib', 'test/provider']
+      t.pattern = 'test/provider/tc_*.rb'
+      t.verbose = true
+      t.rcov_opts = ['--aggregate coverage.data', '--text-summary']
+    end
+  end
+end
+
 task 'test:activerecord_provider' => :create_database
 
 task :environment do 
@@ -104,7 +110,7 @@ task :load_fixtures => :create_database do
 end
   
 Rake::RDocTask.new('doc') do |rd|
-  rd.rdoc_files.include("lib/**/*.rb", "README")
-  rd.main = 'README'
+  rd.rdoc_files.include("lib/**/*.rb", "README.md")
+  rd.main = 'README.md'
   rd.rdoc_dir = 'doc'
 end

data/lib/oai/client.rb

@@ -1,6 +1,6 @@
 # External dependencies
 require 'uri'
-require 'net/http'
+require 'faraday'
 require 'cgi'
 require 'iconv'
 
@@ -67,6 +67,11 @@ module OAI
     # back XML::Node objects
     #
     #   client = OAI::Client.new 'http://example.com', :parser => 'libxml'
+    #   
+    # You can configure the Faraday HTTP client by providing an alternate 
+    # Faraday instance:
+    #
+    #   client = OAI::Client.new 'http://example.com', :http => Faraday.new { |c| }
     #
     # === HIGH PERFORMANCE
     #
@@ -77,7 +82,18 @@ module OAI
       @base = URI.parse base_url
       @debug = options.fetch(:debug, false)
       @parser = options.fetch(:parser, 'rexml')
+
       @follow_redirects = options.fetch(:redirects, true)
+      @http_client = options.fetch(:http, Faraday.new(@base))
+
+      if !options.key?(:http) and @follow_redirects
+
+        count = @folow_redirects if @folow_redirects.is_a? Fixnum
+        count ||= 5
+
+        require 'faraday_middleware'
+        @http_client.use FaradayMiddleware::FollowRedirects, :limit => count
+      end
       
       # load appropriate parser
       case @parser
@@ -98,7 +114,7 @@ module OAI
 
     # Equivalent to a Identify request. You'll get back a OAI::IdentifyResponse
     # object which is essentially just a wrapper around a REXML::Document 
-    # for the response. If you are created your client using the libxml 
+    # for the response. If you created your client using the libxml 
     # parser then you will get an XML::Node object instead.
     
     def identify
@@ -207,21 +223,8 @@ module OAI
 
     # Do the actual HTTP get, following any temporary redirects
     def get(uri)
-      response = Net::HTTP.get_response(uri)
-      case response
-      when Net::HTTPSuccess
-        return response.body
-      when Net::HTTPMovedPermanently
-        if @follow_redirects
-          response = get(URI.parse(response['location']))
-        else
-          raise ArgumentError, "Permanently Redirected to [#{response['location']}]"
-        end
-      when Net::HTTPTemporaryRedirect
-        response = get(URI.parse(response['location']))
-      else
-        raise ArgumentError, "#{response.code_type} [#{response.code}]"
-      end
+      response = @http_client.get uri
+      response.body
     end
 
     def debug(msg)

data/lib/oai/client/response.rb

@@ -1,4 +1,24 @@
 module OAI
+
+  # An OAI::Response contains entries and a resumption token. If a resumption token is present, 
+  # then you must use it to fetch the rest of the entries for your query. For example:
+  #   # List all records
+  #   i = 1
+  #   begin 
+  #     response = client.list_records
+  #     while response.entries.size > 0    
+  #       response.entries.each { |entry|
+  #         puts "<b>#{i}</b> #{entry.header.identifier}<br/>"
+  #         i +=1
+  #       }
+  #       token = response.resumption_token
+  #       response = client.list_records :resumption_token => token if token
+  #     end
+  #   rescue OAI::Exception => e
+  #     puts 'No records to process'
+  #   end
+  #   puts "Done processing #{i} records"
+
   class Response
     include OAI::XPath
     attr_reader :doc, :resumption_token

data/test/client/helpers/test_wrapper.rb

@@ -9,3 +9,10 @@ module Test::Unit
   end
   
 end
+
+unless $provider_server_already_started
+  $provider_server_already_started = true
+  ProviderServer.start(3333)
+  sleep 2
+end
+

data/test/client/tc_http_client.rb

@@ -0,0 +1,26 @@
+require 'test_helper'
+
+class HttpClientTest < Test::Unit::TestCase
+
+  def test_pluggable_http_client
+    oai_response = <<-eos
+    <Identify>
+      <repositoryName>Mock OAI Provider</repositoryName>
+      <baseURL>http://nowhere.example.com</baseURL> 
+    </Identify>
+eos
+
+    faraday_stub = Faraday.new do |builder|
+      builder.adapter :test do |stub|
+        stub.get('/oai?verb=Identify') { [200, {}, oai_response] }
+      end
+    end
+    client = OAI::Client.new 'http://localhost:3333/oai', :http => faraday_stub
+    response = client.identify
+
+    assert_kind_of OAI::IdentifyResponse, response
+    assert_equal 'Mock OAI Provider [http://nowhere.example.com]', response.to_s
+    
+  end
+end
+

data/test/client/tc_utf8_escaping.rb

@@ -5,6 +5,7 @@ class UTF8Test < Test::Unit::TestCase
   def test_escaping_invalid_utf_8_characters
     client = OAI::Client.new 'http://localhost:3333/oai' #, :parser => 'libxml'
     invalid_utf_8 = [2, 3, 4, 104, 5, 101, 6, 108, 66897, 108, 66535, 111, 1114112, 33, 55234123, 33].pack("U*")
+    invalid_utf_8 = invalid_utf_8.force_encoding("binary") if invalid_utf_8.respond_to? :force_encoding
     assert_equal("hello!!", client.send(:strip_invalid_utf_8_chars, invalid_utf_8).gsub(/\?/, ''))
   end
 

data/test/client/test_helper.rb

@@ -1,5 +1,13 @@
+if ENV['COVERAGE'] and RUBY_VERSION =~ /^1.9/
+  require 'simplecov'
+  require 'simplecov-rcov'
+
+  SimpleCov.formatter = SimpleCov::Formatter::RcovFormatter
+  SimpleCov.start
+end
+
 require 'oai'
 require 'test/unit'
 
 require File.dirname(__FILE__) + '/helpers/provider'
-require File.dirname(__FILE__) + '/helpers/test_wrapper'
+require File.dirname(__FILE__) + '/helpers/test_wrapper'

data/test/provider/models.rb

@@ -112,7 +112,7 @@ class TestModel < OAI::Provider::Model
   end
       
   def generate_records(number, timestamp = Time.now.utc.xmlschema, sets = [], deleted = false)
-    @earliest = timestamp.dup if @earliest.nil? || timestamp.to_s < @earliest
+    @earliest = timestamp.dup if @earliest.nil? || timestamp.to_s < @earliest.to_s
     @earliest = timestamp.dup if @earliest.nil?
     
     # Add any sets we don't already have

data/test/provider/tc_exceptions.rb

@@ -1,7 +1,6 @@
 require 'test_helper'
 
 class ProviderExceptions < Test::Unit::TestCase
-  include Singleton
   
   def setup
     @provider = ComplexProvider.new

metadata

@@ -1,161 +1,215 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: oai
-version: !ruby/object:Gem::Version 
-  hash: 5
+version: !ruby/object:Gem::Version
+  version: 0.1.0
   prerelease: 
-  segments: 
-  - 0
-  - 0
-  - 13
-  version: 0.0.13
 platform: ruby
-authors: 
+authors:
 - Ed Summers
 autorequire: oai
 bindir: bin
 cert_chain: []
-
-date: 2012-04-09 00:00:00 Z
-dependencies: 
-- !ruby/object:Gem::Dependency 
+date: 2012-06-01 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
   name: builder
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 2.0.0
+  type: :runtime
   prerelease: false
-  requirement: &id001 !ruby/object:Gem::Requirement 
+  version_requirements: !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        hash: 15
-        segments: 
-        - 2
-        - 0
-        - 0
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
         version: 2.0.0
+- !ruby/object:Gem::Dependency
+  name: faraday
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: faraday_middleware
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
   type: :runtime
-  version_requirements: *id001
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rdoc
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 description: 
 email: ehs@pobox.com
-executables: 
+executables:
 - oai
 extensions: []
-
 extra_rdoc_files: []
-
-files: 
+files:
 - README.md
 - Rakefile
 - bin/oai
-- test/client/tc_get_record.rb
-- test/client/tc_identify.rb
+- test/activerecord_provider/config/connection.rb
+- test/activerecord_provider/config/database.yml
+- test/activerecord_provider/database/ar_migration.rb
+- test/activerecord_provider/database/oaipmhtest
+- test/activerecord_provider/fixtures/dc.yml
+- test/activerecord_provider/helpers/providers.rb
+- test/activerecord_provider/helpers/set_provider.rb
+- test/activerecord_provider/models/dc_field.rb
+- test/activerecord_provider/models/dc_set.rb
+- test/activerecord_provider/models/oai_token.rb
+- test/activerecord_provider/tc_ar_provider.rb
+- test/activerecord_provider/tc_ar_sets_provider.rb
+- test/activerecord_provider/tc_caching_paging_provider.rb
+- test/activerecord_provider/tc_simple_paging_provider.rb
+- test/activerecord_provider/test_helper.rb
 - test/client/helpers/provider.rb
 - test/client/helpers/test_wrapper.rb
+- test/client/tc_exception.rb
+- test/client/tc_get_record.rb
+- test/client/tc_http_client.rb
+- test/client/tc_identify.rb
+- test/client/tc_libxml.rb
 - test/client/tc_list_identifiers.rb
-- test/client/tc_utf8_escaping.rb
-- test/client/tc_list_sets.rb
-- test/client/test_helper.rb
+- test/client/tc_list_metadata_formats.rb
 - test/client/tc_list_records.rb
-- test/client/tc_libxml.rb
+- test/client/tc_list_sets.rb
 - test/client/tc_low_resolution_dates.rb
-- test/client/tc_exception.rb
-- test/client/tc_list_metadata_formats.rb
+- test/client/tc_utf8_escaping.rb
 - test/client/tc_xpath.rb
-- test/provider/tc_simple_provider.rb
+- test/client/test_helper.rb
 - test/provider/models.rb
+- test/provider/tc_exceptions.rb
 - test/provider/tc_functional_tokens.rb
 - test/provider/tc_provider.rb
 - test/provider/tc_resumption_tokens.rb
+- test/provider/tc_simple_provider.rb
 - test/provider/test_helper.rb
-- test/provider/tc_exceptions.rb
 - test/test.xml
-- test/activerecord_provider/fixtures/dc.yml
-- test/activerecord_provider/helpers/providers.rb
-- test/activerecord_provider/helpers/set_provider.rb
-- test/activerecord_provider/tc_caching_paging_provider.rb
-- test/activerecord_provider/tc_ar_sets_provider.rb
-- test/activerecord_provider/models/oai_token.rb
-- test/activerecord_provider/models/dc_set.rb
-- test/activerecord_provider/models/dc_field.rb
-- test/activerecord_provider/test_helper.rb
-- test/activerecord_provider/tc_simple_paging_provider.rb
-- test/activerecord_provider/database/oaipmhtest
-- test/activerecord_provider/database/ar_migration.rb
-- test/activerecord_provider/tc_ar_provider.rb
-- test/activerecord_provider/config/connection.rb
-- test/activerecord_provider/config/database.yml
-- lib/oai/set.rb
-- lib/oai/xpath.rb
-- lib/oai/harvester/logging.rb
-- lib/oai/harvester/mailer.rb
-- lib/oai/harvester/harvest.rb
-- lib/oai/harvester/shell.rb
-- lib/oai/harvester/config.rb
-- lib/oai/client/list_identifiers.rb
-- lib/oai/client/list_records.rb
+- lib/oai/client/get_record.rb
 - lib/oai/client/header.rb
 - lib/oai/client/identify.rb
-- lib/oai/client/record.rb
-- lib/oai/client/get_record.rb
-- lib/oai/client/response.rb
-- lib/oai/client/metadata_format.rb
+- lib/oai/client/list_identifiers.rb
 - lib/oai/client/list_metadata_formats.rb
+- lib/oai/client/list_records.rb
 - lib/oai/client/list_sets.rb
-- lib/oai/provider/model.rb
+- lib/oai/client/metadata_format.rb
+- lib/oai/client/record.rb
+- lib/oai/client/response.rb
+- lib/oai/client.rb
+- lib/oai/constants.rb
+- lib/oai/exception.rb
+- lib/oai/harvester/config.rb
+- lib/oai/harvester/harvest.rb
+- lib/oai/harvester/logging.rb
+- lib/oai/harvester/mailer.rb
+- lib/oai/harvester/shell.rb
+- lib/oai/harvester.rb
+- lib/oai/provider/metadata_format/oai_dc.rb
+- lib/oai/provider/metadata_format.rb
 - lib/oai/provider/model/activerecord_caching_wrapper.rb
 - lib/oai/provider/model/activerecord_wrapper.rb
-- lib/oai/provider/response/list_identifiers.rb
-- lib/oai/provider/response/list_records.rb
-- lib/oai/provider/response/record_response.rb
-- lib/oai/provider/response/identify.rb
+- lib/oai/provider/model.rb
+- lib/oai/provider/partial_result.rb
 - lib/oai/provider/response/error.rb
 - lib/oai/provider/response/get_record.rb
+- lib/oai/provider/response/identify.rb
+- lib/oai/provider/response/list_identifiers.rb
 - lib/oai/provider/response/list_metadata_formats.rb
+- lib/oai/provider/response/list_records.rb
 - lib/oai/provider/response/list_sets.rb
-- lib/oai/provider/metadata_format/oai_dc.rb
-- lib/oai/provider/resumption_token.rb
+- lib/oai/provider/response/record_response.rb
 - lib/oai/provider/response.rb
-- lib/oai/provider/partial_result.rb
-- lib/oai/provider/metadata_format.rb
-- lib/oai/constants.rb
-- lib/oai/client.rb
+- lib/oai/provider/resumption_token.rb
 - lib/oai/provider.rb
-- lib/oai/harvester.rb
-- lib/oai/exception.rb
-- lib/test.rb
+- lib/oai/set.rb
+- lib/oai/xpath.rb
 - lib/oai.rb
-- examples/providers/dublin_core.rb
+- lib/test.rb
 - examples/models/file_model.rb
-homepage: http://www.textualize.com/ruby_oai_0
+- examples/providers/dublin_core.rb
+homepage: http://github.com/code4lib/ruby-oai
 licenses: []
-
 post_install_message: 
 rdoc_options: []
-
-require_paths: 
+require_paths:
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement 
+required_ruby_version: !ruby/object:Gem::Requirement
   none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      hash: 3
-      segments: 
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+      segments:
       - 0
-      version: "0"
-required_rubygems_version: !ruby/object:Gem::Requirement 
+      hash: -1260822851612593558
+required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      hash: 3
-      segments: 
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+      segments:
       - 0
-      version: "0"
+      hash: -1260822851612593558
 requirements: []
-
 rubyforge_project: 
-rubygems_version: 1.7.2
+rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
-summary: A ruby library for working with the Open Archive Initiative Protocol for Metadata Harvesting (OAI-PMH)
+summary: A ruby library for working with the Open Archive Initiative Protocol for
+  Metadata Harvesting (OAI-PMH)
 test_files: []
-