umlaut 3.0.0alpha1

data/lib/umlaut_http.rb

@@ -0,0 +1,100 @@
+# Helper module for service adaptors making HTTP requests, as most do.
+# Eventually this may include some HTTP request wrapper methods that
+# set timeout appropriately, and perhaps even do some HTTP level cacheing.
+#
+# Right now, just a helper method for generating headers for proxy-like requests.
+
+module UmlautHttp
+  require 'net/http'
+  require 'net/https'
+  require 'uri'
+
+  # Generate headers for a proxy-like request, so a service adaptor
+  # can make a request to a foreign service that appears to be HTTP-proxied
+  # from the original client browser, instead of just originating from
+  # Umlaut. This in some cases helps get around service traffic limiting,
+  # and in general is more honest and gives the service some good information
+  # about the actual end user.
+  #
+  # Not generally neccesary for accessing actual APIs, but sometimes useful
+  # for screen scraping, or for an API intended to be client-side JS only.
+  #
+  # request is an Umlaut Request, which has in it information about
+  # original client request and ip. host is optional, and is the
+  # ultimate destination you will be sending the proxy-like request to.
+  # if supplied, a not entirely honest X-Forwarded-Host header will be
+  # added. 
+  def proxy_like_headers(request, host = nil)
+    orig_env = request.http_env
+    if (request.http_env.nil? || ! request.http_env.kind_of?(Hash))
+      Rails.logger.warn("proxy_like_headers: orig_env arg is missing, proxy-like headers will be flawed. request id: #{request.id}. ")
+      orig_env = {}
+    end
+
+    header = {}
+
+    # Bunch of headers we proxy as-is from the original client request,
+    # supplying reasonable defaults. 
+    
+    header["User-Agent"] = orig_env['HTTP_USER_AGENT'] || 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9) Gecko/2008061015 Firefox/3.0'
+    header['Accept'] = orig_env['HTTP_ACCEPT'] || 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'
+    header['Accept-Language'] = orig_env['HTTP_ACCEPT_LANGUAGE'] || 'en-us,en;q=0.5'
+    header['Accept-Encoding'] = orig_env['HTTP_ACCEPT_ENCODING'] || ''
+    header["Accept-Charset"] = orig_env['HTTP_ACCEPT_CHARSET'] || 'UTF-8,*'
+
+    # Set referrer to be, well, an Umlaut page, like the one we are
+    # currently generating would be best. That is, the resolve link. 
+    
+    header["Referer"] = "http://#{orig_env['HTTP_HOST']}#{orig_env['REQUEST_URI']}"
+
+    # Proxy X-Forwarded headers. 
+
+    # The original Client's ip, most important and honest. Look for
+    # and add on to any existing x-forwarded-for, if neccesary, as per
+    # x-forwarded-for convention. 
+
+    header['X-Forwarded-For'] =  (orig_env['HTTP_X_FORWARDED_FOR']) ?
+       (orig_env['HTTP_X_FORWARDED_FOR'].to_s + ', ' + request.client_ip_addr.to_s) :
+       request.client_ip_addr.to_s
+       
+    #Theoretically the original host requested by the client in the Host HTTP request header. We're disembling a bit.  
+    header['X-Forwarded-Host'] = host if host
+    # The proxy server: That is, Umlaut, us. 
+    header['X-Forwarded-Server'] = orig_env['SERVER_NAME'] || '' 
+    
+    return header
+    
+  end
+
+  # Right now the main thing this will do for you is (sort of, stupidly) 
+  # maintain cookies given in redirects. 
+  # Later it might do other cooler things. Returns a Net::HTTP::Response
+  def http_fetch(uri, options = {})
+    options[:max_redirects] ||= 8
+    options[:redirects_left] ||= options[:max_redirects]
+    options[:raise_on_http_error_code] = true unless options.has_key?(:raise_on_http_error_code)
+
+      uri = URI.parse(uri) unless uri.kind_of?(URI)
+      http = Net::HTTP.new(uri.host, uri.port)
+      http.use_ssl = true if uri.scheme == "https"
+      headers = options[:headers] || {}
+      headers["Cookie"] = options[:cookies] if options[:cookies]
+
+      response = http.request_get(uri.request_uri, headers)
+            
+      if ( response.kind_of?(Net::HTTPRedirection))
+         raise ArgumentError, "HTTP redirect too deep (max #{options[:max_redirects]})" if options[:redirects_left] <= 0
+
+         options[:cookies] = response['Set-Cookie']
+         
+         options[:redirects_left] = options[:redirects_left] - 1
+         
+         return http_fetch(response['location'], options)
+      else
+        response.value if options[:raise_on_http_error_code]        
+        return response
+      end
+  end
+  
+  
+end

data/lib/xml_schema_helper.rb

@@ -0,0 +1,109 @@
+module XmlSchemaHelper
+  def self.xml_ns
+    {
+      "dlf" => "http://diglib.org/ilsdi/1.1",
+      "marc" => "http://www.loc.gov/MARC21/slim",
+      "daia" => "http://ws.gbv.de/daia/",
+      "atom" => "http://www.w3.org/2005/Atom",
+      "opensearch" => "http://a9.com/-/spec/opensearch/1.1/"
+    }
+  end
+  def xml_ns ; XmlSchemaHelper.xml_ns ; end
+
+  
+  # Meant for use with "dlf_expanded" responses, but really of wide
+  # applicability. The input is a list of Nokogiri elements. Each element
+  # should contain as children 0-to-N recognized XML schema formats
+  # representing holdings data. XML nodes should be properly
+  # namespaced. (Cause that's how we'll recognize them.).  Method will
+  # Create Umlaut 'holding' ServiceResponses for each one, taking what
+  # info it can get from the metadata.
+  #
+  # Note that when taking from an dlf_expanded doc, this means the
+  # the individual xml elements passed in can be dlf:item OR dlf:holdingsrec
+  #
+  # Recognized metadata formats:
+  # * dlf:simpleavailability from namespace: http://diglib.org/ilsdi/1.1
+  # * marc holdings, marc:record with type="Holdings" from namespace: http://www.loc.gov/MARC21/slim
+  # * daia from namespace: http://ws.gbv.de/daia/
+  #
+  # Method uses it's own logic for precedence when the same data element
+  # is found in multiple places.
+  #
+  # NOTE: Does NOT add a :url key, caller will want to add that themselves. 
+  def xml_to_holdings(xml)
+ 
+    data = {}
+
+    data[:call_number] = xml_choose_first(xml,
+      marc_xpath("852", "h"))
+
+    data[:status] = xml_choose_first(xml,    
+      "dlf:simpleavailability/dlf:availabilitymsg")
+                
+    data[:location] = xml_choose_first(xml,
+      [ marc_xpath("852", "b"),
+        "daia:daia/daia:document/daia:item/daia:department"
+      ])
+    
+    data[:source_name] = data[:collection_str] = xml_choose_first(xml,
+      [ marc_xpath(852, "c"),
+        "daia:daia/daia:document/daia:item/daia:storage"
+      ])
+
+    data[:copy_str] = xml_choose_first(xml, marc_xpath(852, "i"))
+
+    # get coverage strings from mfhd 866, 867, 868
+    data[:coverage_str_array] = []    
+    xml.xpath("marc:record/marc:datafield[@tag='866' or @tag='867' or @tag='868']", xml_ns).each do |field|
+      value = ""  
+      value += mfhd_coverage_prefix( field.attributes["tag"].text )
+      value +=  field.xpath("marc:subfield[@code='a']", xml_ns).text
+      if ( (notes = field.xpath("marc:subfield[@code='z']", xml_ns)).length > 0)
+        value += " -- #{notes.text}"
+      end
+      data[:coverage_str_array] << value
+    end    
+    data[:coverage_str] = data[:coverage_str_array].join(" ")
+    
+    data[:notes] = xml.xpath(marc_xpath(852, "z"), xml_ns).collect {|sf| sf.text.to_s}.join("\n")
+        
+    data[:request_url] = xml_choose_first(xml, "daia:daia/daia:document/daia:item/daia:available/attribute::href")
+
+    if (data[:collection_str].blank? && data[:location].blank? && data[:call_number].blank? )
+      data[:collection_str] = xml_choose_first(xml, "dlf:simpleavailability/dlf:location")
+    end
+
+    # Add a display_text to be a good generic Umlaut service response
+    data[:display_text] = "#{data[:location]} #{data[:collection_str]} #{data[:call_number]} #{data[:copy_str]}"
+            
+    # edition_str
+    return data
+  end
+
+  protected
+  def marc_xpath(tag, sf_code)
+    "marc:record/marc:datafield[@tag='#{tag}']/marc:subfield[@code='#{sf_code}']"
+  end
+  def xml_choose_first(xml, path_array)
+    path_array = [path_array] if path_array.kind_of?(String)
+    
+    path_array.each do |path|
+      candidate = xml.xpath(path, xml_ns)[0]
+      unless candidate.nil?
+        return candidate.text
+      end
+    end
+    return nil
+  end
+
+  # Translates from marc mfhd tags 866, 867, 868 to a prefix label
+  def mfhd_coverage_prefix(tag_str)
+    { 
+      "866" => "",
+      "867" => "Supplements: ", 
+      "868" => "Indexes: "
+    }[tag_str].to_s
+  end
+  
+end

data/test/dummy/Rakefile

@@ -0,0 +1,7 @@
+#!/usr/bin/env rake
+# Add your own tasks in files placed in lib/tasks ending in .rake,
+# for example lib/tasks/capistrano.rake, and they will automatically be available to Rake.
+
+require File.expand_path('../config/application', __FILE__)
+
+Dummy::Application.load_tasks

data/test/dummy/app/assets/javascripts/application.js

@@ -0,0 +1,13 @@
+
+ // Umlaut javascript required for proper functionality. The 'umlaut' file
+ // also forces require of jquery and jquery-ui, dependencies. 
+ //= require 'umlaut'          
+          // This is a manifest file that'll be compiled into including all the files listed below.
+// Add new JavaScript/Coffee code in separate files in this directory and they'll automatically
+// be included in the compiled file accessible from http://example.com/assets/application.js
+// It's not advisable to add code directly here, but if you do, it'll appear at the bottom of the
+// the compiled file.
+//
+//= require jquery
+//= require jquery_ujs
+//= require_tree .

data/test/dummy/app/assets/stylesheets/application.css

@@ -0,0 +1,15 @@
+/* 
+ * The base Umlaut styles:
+ *= require 'umlaut'         
+          
+ * This is a manifest file that'll automatically include all the stylesheets available in this directory
+ * and any sub-directories. You're free to add application-wide styles to this file and they'll appear at
+ * the top of the compiled file, but it's generally better to create a new file per style scope.
+ *= require_self
+ *= require_tree . 
+*/
+          
+  /* Umlaut needs a jquery-ui theme CSS. Here's an easy way to get one,
+     you can replace with another theme. */
+  @import url(http://ajax.googleapis.com/ajax/libs/jqueryui/1.8.16/themes/ui-lightness/jquery-ui.css);
+          

data/test/dummy/app/controllers/application_controller.rb

@@ -0,0 +1,3 @@
+class ApplicationController < ActionController::Base
+  protect_from_forgery
+end

data/test/dummy/app/controllers/umlaut_controller.rb

@@ -0,0 +1,112 @@
+require 'umlaut'
+require 'umlaut_configurable'
+
+# Superclass for all Umlaut controllers, to hold default behavior,
+# also hold global configuration. It's a superclass rather than a module,
+# so we can use Rails 3 hieararchical superclass view lookup too if we want,
+# for general umlaut views. And also so local app can over-ride
+# methods here once, and have it apply to all Umlaut controllers.
+# But there's not much magic in here or anything, the
+# common behavior is ordinary methods available to be called, mostly. 
+#
+# This class is copied into the local app -- the default implementation
+# does nothing but 'include Umlaut::ControllerBehavior'
+#
+# You will ordinarily set config here, and can also over-ride
+# methods from Umlaut::ControllerBehavior if desired. Or add
+# additional helpers to over-ride Umlaut helpers if needed. 
+class UmlautController < ApplicationController
+    include Umlaut::ControllerBehavior
+        
+    # Some suggested configuration. More config keys
+    # are available, see UmlautConfigurable.set_default_configuration!
+    # implementation for list. Configuration actually uses
+    # a Confstruct object. 
+    
+    umlaut_config.configure do 
+      # app_name 'Find It'
+      
+      # URL to image to use for link resolver in some self-links, 
+      # OR name of image asset in local app. 
+      #link_img_url "http//something"
+      
+      # Sometimes Umlaut sends out email, what email addr should it be from?
+      # from_email_addr 'no_reply@umlaut.example.com'
+      
+      # Local layout for UmlautController's, instead of
+      # built in 'umlaut' layout?
+      # layout "application"
+      
+      # A help url used on error page and a few other places.
+      # help_url  "http://www.library.jhu.edu/services/askalib/index.html"
+
+      # If OpenURL came from manual entry of title/ISSN, and no match is found in
+      # link resolver knowledge base, display a warning to the user of potential
+      # typo?
+      # entry_not_in_kb_warning true
+      
+      # rfr_ids used for umlaut generated pages.
+      # rfr_ids do
+      #   opensearch  "info:sid/umlaut.code4lib.org:opensearch"
+      #  citation    "info:sid/umlaut.code4lib.org:citation"
+      #   azlist      'info:sid/umlaut.code4lib.org:azlist'
+      # end
+      
+      # Referent filters. Sort of like SFX source parsers.
+      # hash, key is regexp to match a sid, value is filter object
+      # (see lib/referent_filters )        
+      # add_referent_filters!( :match => /.*/, :filter => DissertationCatch.new ) 
+    
+      # How many seconds between updates of the background updater for background
+      # services?
+      # poll_wait_seconds 4
+      
+      # Configuration for the 'search' functions -- A-Z lookup
+      # and citation entry. 
+      search do
+        # Is your SFX database connection, defined in database.yml under
+        # sfx_db and used for A-Z searches, Sfx3 or Sfx4?  Other SearchMethods
+        # in addition to SFX direct db may be provided later. 
+        #az_search_method  SearchMethods::Sfx4
+        #az_search_method  SearchMethods::Sfx3
+        
+        # When talking directly to the SFX A-Z list database, you may
+        # need to set this, if you have multiple A-Z profiles configured
+        # and don't want to use the 'default.
+        # sfx_az_profile "default"    
+                
+        # can set to "_blank" etc. 
+        # result_link_target nil        
+      end
+      
+      # config only relevant to SFX use  
+      sfx do      
+        # base sfx url to use for search actions, error condition backup,
+        # and some other purposes. For search actions (A-Z), direct database
+        # connection to your SFX db also needs to be defined in database.yml
+        # sfx_base_url  'http://sfx.library.jhu.edu:8000/jhu_sfx?'
+        # 
+  
+        
+        
+        # Umlaut tries to figure out from the SFX knowledge base
+        # which hosts are "SFX controlled", to avoid duplicating SFX
+        # urls with urls from catalog. But sometimes it misses some, or
+        # alternate hostnames for some. Regexps matching against
+        # urls can be included here. Eg,
+        # AppConfig::Base.additional_sfx_controlled_urls = [
+        #    %r{^http://([^\.]\.)*pubmedcentral\.com}
+        #  ]    
+        # additional_sfx_controlled_urls = []
+        
+        
+      end
+      
+      # Advanced topic, you can declaratively configure
+      # what sections of the resolve page are output where
+      # and how using resolve_sections and add_resolve_sections!            
+      
+    end
+    
+    
+end

data/test/dummy/app/helpers/application_helper.rb

@@ -0,0 +1,2 @@
+module ApplicationHelper
+end

data/test/dummy/app/views/layouts/application.html.erb

@@ -0,0 +1,14 @@
+<!DOCTYPE html>
+<html>
+<head>
+  <title>Dummy</title>
+  <%= stylesheet_link_tag    "application" %>
+  <%= javascript_include_tag "application" %>
+  <%= csrf_meta_tags %>
+</head>
+<body>
+
+<%= yield %>
+
+</body>
+</html>

data/test/dummy/config/application.rb

@@ -0,0 +1,45 @@
+require File.expand_path('../boot', __FILE__)
+
+require 'rails/all'
+
+Bundler.require
+require "umlaut"
+
+module Dummy
+  class Application < Rails::Application
+    # Settings in config/environments/* take precedence over those specified here.
+    # Application configuration should go into files in config/initializers
+    # -- all .rb files in that directory are automatically loaded.
+
+    # Custom directories with classes and modules you want to be autoloadable.
+    # config.autoload_paths += %W(#{config.root}/extras)
+
+    # Only load the plugins named here, in the order given (default is alphabetical).
+    # :all can be used as a placeholder for all plugins not explicitly named.
+    # config.plugins = [ :exception_notification, :ssl_requirement, :all ]
+
+    # Activate observers that should always be running.
+    # config.active_record.observers = :cacher, :garbage_collector, :forum_observer
+
+    # Set Time.zone default to the specified zone and make Active Record auto-convert to this zone.
+    # Run "rake -D time" for a list of tasks for finding time zone names. Default is UTC.
+    # config.time_zone = 'Central Time (US & Canada)'
+
+    # The default locale is :en and all translations from config/locales/*.rb,yml are auto loaded.
+    # config.i18n.load_path += Dir[Rails.root.join('my', 'locales', '*.{rb,yml}').to_s]
+    # config.i18n.default_locale = :de
+
+    # Configure the default encoding used in templates for Ruby 1.9.
+    config.encoding = "utf-8"
+
+    # Configure sensitive parameters which will be filtered from the log file.
+    config.filter_parameters += [:password]
+
+    # Enable the asset pipeline
+    config.assets.enabled = true
+
+    # Version of your assets, change this if you want to expire all your assets
+    config.assets.version = '1.0'
+  end
+end
+

data/test/dummy/config/boot.rb

@@ -0,0 +1,10 @@
+require 'rubygems'
+gemfile = File.expand_path('../../../../Gemfile', __FILE__)
+
+if File.exist?(gemfile)
+  ENV['BUNDLE_GEMFILE'] = gemfile
+  require 'bundler'
+  Bundler.setup
+end
+
+$:.unshift File.expand_path('../../../../lib', __FILE__)