oai_talia 0.0.13

data/README

@@ -0,0 +1,81 @@
+= ruby-oai
+
+== DESCRIPTION
+
+ruby-oai is a Open Archives Protocol for Metadata Harvesting (OAI-PMH[http://openarchives.org]) 
+library for Ruby. If you're not familiar with OAI-PMH[http://openarchives.org] it is the most used 
+protocol for sharing metadata between digital library repositories.
+
+The OAI-PMH[http://openarchives.org] spec defines six verbs (Identify, ListIdentifiers, ListRecords, 
+GetRecords, ListSets, ListMetadataFormat) used for discovery and sharing of
+metadata.
+
+The ruby-oai gem includes a client library, a server/provider library and
+a interactive harvesting shell.
+
+=== client
+
+The OAI client library is used for harvesting metadata from repositories. 
+For example to initiate a ListRecords request to pubmed you can:
+
+  require 'oai'
+  client = OAI::Client.new 'http://www.pubmedcentral.gov/oai/oai.cgi'
+  for record in client.list_records
+    puts record.metadata
+  end
+
+See OAI::Client for more details
+
+=== provider
+
+The OAI provider library handles serving local content to other clients.
+
+Setting up a simple provider:
+
+  class MyProvider < Oai::Provider
+    repository_name 'My little OAI provider'
+    repository_url  'http://localhost/provider'
+    record_prefix 'oai:localhost'
+    admin_email 'root@localhost'   # String or Array
+    source_model MyModel.new       # Subclass of OAI::Provider::Model
+  end
+
+See OAI::Provider for more details
+
+=== interactive harvester
+
+The OAI-PMH[http://openarchives.org] client shell allows OAI Harvesting to be configured in
+an interactive manner.  Typing 'oai' on the command line starts the
+shell.
+
+After initial configuration, the shell can be used to manage harvesting
+operations.
+
+See OAI::Harvester::Shell for more details
+
+== INSTALLATION
+
+Normally the best way to install oai is from rubyforge using the gem
+command line tool:
+
+  % gem install oai
+
+If you're reading this you've presumably got the tarball or zip distribution.
+So you'll need to:
+
+  % rake package
+  % gem install pkg/oai-x.y.z.gem 
+
+Where x.y.z is the version of the gem that was generated.
+
+== TODO
+
+* consolidate response classes used by provider and client
+* automatic validation of metadata schemas
+* email the authors with your suggestions
+
+== AUTHORS
+
+- Ed Summers <ehs@pobox.com>
+- William Groppe <will.groppe@gmail.com>
+- Terry Reese <terry.reese@oregonstate.edu>

data/Rakefile

@@ -0,0 +1,127 @@
+RUBY_OAI_VERSION = '0.0.12'
+
+require 'rubygems'
+require 'rake'
+require 'rake/testtask'
+require 'rake/rdoctask'
+require 'rake/packagetask'
+require 'rake/gempackagetask'
+
+task :default => ["test"]
+
+task :test => ["test:client", "test:provider"]
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |s|
+    s.name = "oai_talia"
+    s.summary = "A ruby library for working with the Open Archive Initiative Protocol for Metadata Harvesting (OAI-PMH)"
+    s.email = "ghub@limitedcreativity.org"
+    s.homepage = "http://trac.talia.discovery-project.eu/"
+    s.description = "A ruby library for working with the Open Archive Initiative Protocol for Metadata Harvesting (OAI-PMH). Fork of the original version by Ed Summers, aims for best standards compatibility (test with http://re.cs.uct.ac.za/)"
+    s.required_ruby_version = '>= 1.8.6'
+    s.authors = ["Ed Summers", "Daniel Hahn"]
+    s.homepage = 'http://github.com/net7/ruby-oai-talia/'
+    s.platform = Gem::Platform::RUBY
+    s.require_path = 'lib'
+    s.autorequire = 'oai'
+    s.has_rdoc = true
+    s.bindir = 'bin'
+    s.executables = 'oai'
+
+    s.add_dependency('builder', '>=2.0.0')
+    
+    s.files = %w(README Rakefile) +
+      Dir.glob("{bin,test,lib}/**/*") + 
+      Dir.glob("examples/**/*.rb")
+  end
+  Jeweler::GemcutterTasks.new
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
+end
+
+namespace :test do
+  Rake::TestTask.new('client') do |t|
+    t.libs += ['lib', 'test/client']
+    t.pattern = 'test/client/tc_*.rb'
+    t.verbose = true
+  end
+
+  Rake::TestTask.new('provider') do |t|
+    t.libs += ['lib', 'test/provider']
+    t.pattern = 'test/provider/tc_*.rb'
+    t.verbose = true
+  end
+
+  desc "Active Record base Provider Tests"
+  Rake::TestTask.new('activerecord_provider') do |t|
+    t.libs += ['lib', 'test/activerecord_provider']
+    t.pattern = 'test/activerecord_provider/tc_*.rb'
+    t.verbose = true
+  end
+
+  desc 'Measures test coverage'
+  # borrowed from here: http://clarkware.com/cgi/blosxom/2007/01/05#RcovRakeTask
+  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']
+  end
+
+end
+
+desc "Run all unit tests"
+task :test => ['test:client', 'test:provider', 'test:activerecord_provider']
+
+task 'test:activerecord_provider' => :create_database
+
+task :environment do 
+  unless defined? OAI_PATH
+    OAI_PATH = File.dirname(__FILE__) + '/lib/oai'
+    $LOAD_PATH << OAI_PATH
+    $LOAD_PATH << File.dirname(__FILE__) + '/test'
+  end
+end
+
+task :drop_database => :environment do
+  %w{rubygems active_record yaml}.each { |lib| require lib }
+  require 'activerecord_provider/database/ar_migration'
+  require 'activerecord_provider/config/connection'
+  begin
+    OAIPMHTables.down
+  rescue
+  end
+end
+
+task :create_database => :drop_database do
+  OAIPMHTables.up
+end
+
+task :load_fixtures => :create_database do
+  require 'test/activerecord_provider/models/dc_field'
+  fixtures = YAML.load_file(
+    File.join('test', 'activerecord_provider', 'fixtures', 'dc.yml')
+  )
+  fixtures.keys.sort.each do |key|
+    DCField.create(fixtures[key])
+  end
+end
+  
+Rake::RDocTask.new('doc') do |rd|
+  rd.rdoc_files.include("lib/**/*.rb", "README")
+  rd.main = 'README'
+  rd.rdoc_dir = 'doc'
+end
+
+begin
+  require 'gokdok'
+  Gokdok::Dokker.new do |gd|
+    gd.remote_path = ''
+    gd.rdoc_task = :doc
+    gd.doc_home = 'doc'
+  end
+rescue LoadError
+  puts "Gokdoc not available. Install it with: gem install gokdok"
+end

data/bin/oai

@@ -0,0 +1,68 @@
+#!/usr/bin/env ruby -rubygems
+#
+#  Created by William Groppe on 2006-11-05.
+#  Copyright (c) 2006. All rights reserved.
+
+require 'optparse'
+
+DIRECTORY_LAYOUT = "%Y/%m".freeze
+
+require 'oai/harvester'
+
+include OAI::Harvester
+
+conf = OAI::Harvester::Config.load
+
+startup = :interactive
+
+rexml = false
+
+opts = OptionParser.new do |opts|
+  opts.banner = "Usage: oai ..."
+  opts.define_head "#{File.basename($0)}, a OAI harvester shell."
+  opts.separator ""
+  opts.separator "Options:"
+  
+  opts.on("-D", "--daemon", "Non-interactive mode, to be called via scheduler") { startup = :daemon }
+  opts.on("-R", "--rexml", "Use rexml even if libxml is available") { rexml = true }
+  opts.on("-?", "--help", "Show this message") do
+    puts opts
+    exit
+  end
+  
+  # Another typical switch to print the version.
+  opts.on_tail("-v", "--version", "Show version") do
+      class << Gem; attr_accessor :loaded_specs; end
+      puts Gem.loaded_specs['oai'].version
+      exit
+  end
+end
+
+begin
+  opts.parse! ARGV
+rescue
+  puts opts
+  exit
+end
+
+unless rexml
+  begin # Try to load libxml to speed up harvesting
+    require 'xml/libxml'
+  rescue LoadError
+  end
+end
+
+case startup
+when :interactive
+  shell = Shell.new(conf)
+  shell.start
+when :daemon
+  if conf.storage
+    harvest = Harvest.new(conf)
+    harvest.start(harvestable_sites(conf))
+  else
+    puts "Missing or corrupt configuration file, cannot continue."
+    exit(-1)
+  end
+end
+  

data/examples/models/file_model.rb

@@ -0,0 +1,63 @@
+#!/usr/bin/env ruby
+#
+# Created by William Groppe on 2007-02-01.
+#
+# Simple file based Model.  Basically just serves a directory of xml files to the
+# Provider.
+#
+class File
+  def id
+    File.basename(self.path)
+  end
+  
+  def to_oai_dc
+    self.read
+  end
+end
+    
+class FileModel < OAI::Provider::Model
+  include OAI::Provider
+  
+  def initialize(directory = 'data')
+    # nil specifies no partial results aka resumption tokens, and 'mtime' is the
+    # method that the provider will call for determining the timestamp
+    super(nil, 'mtime')
+    @directory = directory
+  end
+  
+  def earliest
+    e = Dir["#{@directory}/*.xml"].min { |a,b| File.stat(a).mtime <=> File.stat(b).mtime }
+    File.stat(e).mtime.utc.xmlschema
+  end
+  
+  def latest
+    e = Dir["#{@directory}/*.xml"].max { |a,b| File.stat(a).mtime <=> File.stat(b).mtime }
+    File.stat(e).mtime.utc.xmlschema
+  end
+
+  def sets
+    nil
+  end
+  
+  def find(selector, opts={})
+    return nil unless selector
+
+    case selector
+    when :all
+      records = Dir["#{@directory}/*.xml"].sort.collect do |file|
+        File.new(file) unless File.stat(file).mtime.utc < opts[:from] or
+          File.stat(file).mtime.utc > opts[:until]
+      end
+      records
+    else
+      Find.find("#{@directory}/#{selector}") rescue nil
+    end
+  end
+  
+end
+
+# == Example Usage:
+# class FileProvider < OAI::Provider::Base
+#   repository_name 'XML File Provider'
+#   source_model FileModel.new('/tmp')
+# end