concord_cacher 0.0.5 → 0.1.0

data/Rakefile

@@ -6,7 +6,7 @@ require 'spec/rake/spectask'
 require './lib/concord_cacher.rb'
 
 require 'echoe'
-Echoe.new('concord_cacher', '0.0.5') do |p|
+Echoe.new('concord_cacher', '0.1.0') do |p|
   p.description    = "concord_cacher provides support for locally caching a resource and all referenced resources in multiple different ways. It is intended for using with other Concord Consortium projects and not necessarily for outside projects."
   p.summary        = "Support for locally caching a resource and all referenced resources in multiple different ways"
   p.url            = "http://github.com/psndcsrv/concord_cacher"

data/concord_cacher.gemspec

@@ -2,12 +2,12 @@
 
 Gem::Specification.new do |s|
   s.name = %q{concord_cacher}
-  s.version = "0.0.5"
+  s.version = "0.1.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 1.2") if s.respond_to? :required_rubygems_version=
   s.authors = ["Aaron Unger"]
   s.cert_chain = ["/Users/aunger/gem-public_cert.pem"]
-  s.date = %q{2010-03-26}
+  s.date = %q{2010-04-05}
   s.description = %q{concord_cacher provides support for locally caching a resource and all referenced resources in multiple different ways. It is intended for using with other Concord Consortium projects and not necessarily for outside projects.}
   s.email = %q{aunger @nospam@ concord.org}
   s.extra_rdoc_files = ["README.textile", "lib/concord_cacher.rb", "lib/concord/cacher.rb", "lib/concord/diy_local_cacher.rb", "lib/concord/java_proxy_cacher.rb"]

data/lib/concord/cacher.rb

@@ -3,240 +3,65 @@ class ::Concord::Cacher
   require 'open-uri'
   require 'cgi'
   require 'rexml/document'
-  
-  DEBUG = false
 
-  #   scan for anything that matches (http://[^'"]+)
-  URL_REGEX = /(http[s]?:\/\/[^'"]+)/i
-  # the imageBytes can be referenced by a OTImage object
-  SRC_REGEX = /(?:src|href|imageBytes|authoredDataURL)[ ]?=[ ]?['"]([^'"]+)/i
-  NLOGO_REGEX = /import-drawing "([^"]+)"/i
-  MW_REGEX = /<resource>(.*?mml)<\/resource>/
-  ALWAYS_SKIP_REGEX = /^(mailto|jres)/i
-  RECURSE_ONCE_REGEX = /html$/i  # (resourceFile =~ /otml$/ || resourceFile =~ /html/)
-  RECURSE_FOREVER_REGEX = /(otml|cml|mml|nlogo)$/i
-  
-  attr_reader :otml_url, :cache_dir, :uuid, :errors
+  attr_reader :main_resource, :errors
   
   def initialize(opts = {})
-    defaults = {:rewrite_urls => false, :verbose => false, :cache_headers => true, :create_map => true}
-    opts = defaults.merge(opts)
     raise ArgumentError, "Must include :url, and :cache_dir in the options hash." unless opts[:url] && opts[:cache_dir]
-    @rewrite_urls = opts[:rewrite_urls]
-    @cache_dir = opts[:cache_dir]
-    @verbose = opts[:verbose]
-    @cache_headers = opts[:cache_headers]
-    @create_map = opts[:create_map]
-    url = opts[:url]
-    @filename = File.basename(url, ".otml")
-    @content = ""
-    open(url) do |r|
-      @content_headers = r.respond_to?("meta") ? r.meta : {}
-      @content_headers['_http_version'] = "HTTP/1.1 #{r.respond_to?("status") ? r.status.join(" ") : "200 OK"}"
-      @content = r.read
-    end
-    @uuid = generate_uuid
-    if (URI.parse(url).kind_of?(URI::HTTP))
-      @otml_url = url
+    
+    @main_resource = Concord::Resource.new
+    @main_resource.url = opts.delete(:url)
+    @main_resource.cache_dir = opts.delete(:cache_dir)
+    @main_resource.extras = opts
+    @main_resource.uri = URI.parse(@main_resource.url)
+    @main_resource.load
+    
+    calculate_main_file_absolute_url
+	end
+	
+	def calculate_main_file_absolute_url
+	  orig_uri = @main_resource.uri
+	  codebase = ''
+	  if ((orig_uri.kind_of?(URI::HTTP) || orig_uri.kind_of?(URI::HTTPS)) && orig_uri.absolute?)
+      @main_resource.uri = orig_uri
     else
       # this probably references something on the local fs. we need to extract the document's codebase, if there is ony
-      if @content =~ /<otrunk[^>]+codebase[ ]?=[ ]?['"]([^'"]+)/
-        # @otml_url = "#{$1}/#{@filename}.otml"
-        @otml_url = "#{$1}"
-        @content.sub!(/codebase[ ]?=[ ]?['"][^'"]+['"]/,"")
+      if @main_resource.content =~ /<otrunk[^>]+codebase[ ]?=[ ]?['"]([^'"]+)/
+        codebase = "#{$1}"
+        @main_resource.content.sub!(/codebase[ ]?=[ ]?['"][^'"]+['"]/,"")
+        codebase.sub!(/\/$/,'')
+        codebase = "#{codebase}/#{@main_resource.remote_filename}" unless codebase =~ /otml$/
+        @main_resource.uri = URI.parse(codebase)
       else
-        @otml_url = url
+        @main_resource.uri = orig_uri
       end
     end
     
-    @otml_url.sub!(/[^\/]+$/,"")
-
-  	@errors = {}
-  	
-  	@url_to_hash_map = {}
-	end
+    if @main_resource.uri.relative?
+      # we need the main URI to be absolute so that we can use it to resolve references
+      file_root = URI.parse("file:///")
+      @main_resource.uri = file_root.merge(@main_resource.uri)
+    end
+  end
 	
 	def cache
 	  copy_otml_to_local_cache
-  	
-  	write_url_to_hash_map if @create_map
-	end
-	
-	def generate_main_filename
-	  raise NotImplementedError, "You should be using this class through one of its sub-classes!"
+	  print_errors if ::Concord::Resource.verbose
 	end
-	
-	def generate_filename(opts = {})
-	  raise NotImplementedError, "You should be using this class through one of its sub-classes!"
-  end
-  
-  def generate_uuid
-    raise NotImplementedError, "You should be using this class through one of its sub-classes!"
-  end
   
   def copy_otml_to_local_cache
     # save the file in the local server directories
-    filename = generate_main_filename
-
-    # open the otml file from the specified url or grab the embedded content
-    uri = URI.parse(@otml_url)
-    if uri.relative?
-      # we need the main URI to be absolute so that we can use it to resolve references
-      file_root = URI.parse("file:///")
-      uri = file_root.merge(uri)
-    end
-    @content = parse_file("#{@cache_dir}#{@filename}", @content, @cache_dir, uri, true)
-    
-    write_resource(@cache_dir + filename, @content)
-    write_property_map(@cache_dir + filename + ".hdrs", @content_headers) if @cache_headers
-    @url_to_hash_map[@otml_url + @filename + ".otml"] = filename
-
-    puts "\nThere were #{@errors.length} artifacts with errors.\n" if @verbose
-    @errors.each do |k,v|
-    	puts "In #{k}:" if @verbose
-    	v.uniq.each do |e|
-        puts "    #{e}" if @verbose
-      end
-    end
-  end
-  
-  def parse_file(orig_filename, content, cache_dir, parent_url, recurse)
-    short_filename = /\/([^\/]+)$/.match(orig_filename)[1]
-    print "\n#{short_filename}: " if @verbose
-    processed_lines = []
-    lines = content.split("\n")
-    lines.each do |line|
-      line = CGI.unescapeHTML(line)
-      match_indexes = []
-      while (
-        ( match = (
-            URL_REGEX.match(line) ||
-            SRC_REGEX.match(line) ||
-            (/.*\.nlogo/.match(short_filename) ? NLOGO_REGEX.match(line) : nil) ||
-            (/.*\.(:?cml|mml)/.match(short_filename) ? MW_REGEX.match(line) : nil)
-          )
-        ) && (! match_indexes.include?(match.begin(1)))
-      )
-        print "\nMatched url: #{match[1]}: " if DEBUG
-        match_indexes << match.begin(1)
-        #   get the resource from that location, save it locally
-        # match_url = match[1].gsub(/\s+/,"").gsub(/[\?\#&;=\+,<>"\{\}\|\\\^\[\]].*$/,"")
-        match_url = match[1]
-        # puts("pre: #{match[1]}, post: #{match_url}") if DEBUG
-        begin
-          resource_url = URI.parse(CGI.unescapeHTML(match_url))
-        rescue
-          @errors[parent_url] ||= []
-        @errors[parent_url] << "Bad URL: '#{CGI.unescapeHTML(match_url)}', skipping."
-          print 'x' if @verbose
-          next
-        end
-        if (resource_url.relative?)
-          # relative URL's need to have their parent document's codebase appended before trying to download
-          resource_url = parent_url.merge(resource_url.to_s)
-        end
-        resourceFile = match_url
-        resourceFile = resourceFile.gsub(/http[s]?:\/\//,"")
-        resourceFile = resourceFile.gsub(/\/$/,"")
-
-        if (resourceFile.length < 1) || ALWAYS_SKIP_REGEX.match(resourceFile)
-          print "S" if @verbose
-          next
-        end
-        
-      	begin
-          resource_content = ""
-          resource_headers = {}
-          open(resource_url.scheme == 'file' ? resource_url.path : resource_url.to_s) do |r|
-            resource_headers = r.respond_to?("meta") ? r.meta : {}
-            resource_headers['_http_version'] = "HTTP/1.1 #{r.respond_to?("status") ? r.status.join(" ") : "200 OK"}"
-            resource_content = r.read
-          end
-				rescue OpenURI::HTTPError, Timeout::Error, Errno::ENOENT => e
-          @errors[parent_url] ||= []
-          @errors[parent_url] << "Problem getting file: #{resource_url.to_s},   Error: #{e}"
-          print 'X' if @verbose
-					next
-				end
-
-        localFile = generate_filename(:content => resource_content, :url => resource_url)
-        @url_to_hash_map[resource_url.to_s] = localFile
-        line.sub!(match_url.to_s,localFile.to_s) if @rewrite_urls
-        
-        
-        # skip downloading already existing files.
-        # because we're working with sha1 hashes we can be reasonably certain the content is a complete match
-        if File.exists?(cache_dir + localFile)
-          print 's' if @verbose
-        else
-          # if it's an otml/html file, we should parse it too (only one level down)
-          if (recurse && (RECURSE_ONCE_REGEX.match(resourceFile) || RECURSE_FOREVER_REGEX.match(resourceFile)))
-							puts "recursively parsing '#{resource_url.to_s}'" if DEBUG
-							recurse_further = false
-							if RECURSE_FOREVER_REGEX.match(resourceFile)
-							  recurse_further = true
-						  end
-							begin
-							  write_resource(cache_dir + localFile, "") # touch the file so that we avoid recursion
-                resource_content = parse_file(cache_dir + resourceFile, resource_content, cache_dir, resource_url, recurse_further)
-							rescue OpenURI::HTTPError => e
-                @errors[parent_url] ||= []
-                @errors[parent_url] << "Problem getting or writing file: #{resource_url.to_s},   Error: #{e}"
-                print 'X' if @verbose
-								next
-							end
-          end
-          begin
-            write_resource(cache_dir + localFile, resource_content)
-            write_property_map(cache_dir + localFile + ".hdrs", resource_headers) if @cache_headers
-            print "." if @verbose
-          rescue Exception => e
-            @errors[parent_url] ||= []
-            @errors[parent_url] << "Problem getting or writing file: #{resource_url.to_s},   Error: #{e}"
-            print 'X' if @verbose
-          end
-        end
-      end
-      processed_lines << line
-    end
-
-    print ".\n" if @verbose
-    return processed_lines.join("\n")
-  end
-  
-  def write_resource(filename, content)
-    f = File.new(filename, "w")
-    f.write(content)
-    f.flush
-    f.close
+    @main_resource.should_recurse = true
+    @main_resource.process
+    @main_resource.write
   end
   
-  def write_url_to_hash_map
-    load_existing_map if (File.exists?(@cache_dir + "url_map.xml"))
-    write_property_map(@cache_dir + "url_map.xml", @url_to_hash_map)
-  end
-    
-  def write_property_map(filename, hash_map)
-    File.open(filename, "w") do |f|
-      f.write('<?xml version="1.0" encoding="UTF-8"?>' + "\n")
-      f.write('<!DOCTYPE properties SYSTEM "http://java.sun.com/dtd/properties.dtd">' + "\n")
-      f.write('<properties>' + "\n")
-      hash_map.each do |url,hash|
-        f.write("<entry key='#{CGI.escapeHTML(url)}'>#{hash}</entry>\n")
-      end
-      f.write('</properties>' + "\n")
-      f.flush
-    end
-  end
-  
-  def load_existing_map
-    map_content = ::REXML::Document.new(File.new(@cache_dir + "url_map.xml")).root
-    map_content.elements.each("entry") do |entry|
-      k = entry.attributes["key"]
-      if ! (@url_to_hash_map.include? k)
-        val = entry.text
-        @url_to_hash_map[k] = val
-        # puts "Adding previously defined url: #{k}  =>  #{val}" if DEBUG
+  def print_errors
+    puts "\nThere were #{@errors.length} artifacts with errors.\n"
+    ::Concord::Resource.errors.each do |k,v|
+    	puts "In #{k}:"
+    	v.uniq.each do |e|
+        puts "    #{e}"
       end
     end
   end

data/lib/concord/diy_local_cacher.rb

@@ -1,35 +1,15 @@
+require 'concord/cacher'
+
 class ::Concord::DiyLocalCacher < ::Concord::Cacher
-  require 'uri'
-  require 'digest/sha1'
-  require 'fileutils'
+  require 'concord/resource'
+  require 'concord/filename_generators/diy_generator'
   
   def initialize(opts = {})
-    raise InvalidArgumentError, "Must include :activity in the options hash." unless opts[:activity]
-    @activity = opts[:activity]
-    opts[:cache_headers] ||= false
-    opts[:create_map] ||= false
-    opts[:rewrite_urls] ||= true
+    raise ::ArgumentError, "Must include :activity in the options hash." unless opts[:activity]
+    ::Concord::Resource.cache_headers = false
+    ::Concord::Resource.rewrite_urls = true
+    ::Concord::Resource.create_map = false
+    ::Concord::Resource.filename_generator = ::Concord::FilenameGenerators::DiyGenerator
     super
   end
-  
-  def generate_main_filename
-    "#{generate_uuid}.otml"
-  end
-  
-  def generate_uuid
-    @activity.uuid
-  end
-  
-  def generate_filename(opts = {})
-    raise InvalidArgumentError, "Must include :url key in opts" unless opts[:url]
-    raise InvalidArgumentError, ":url value must be an instance of URI" unless opts[:url].kind_of?(::URI)
-    uri = opts[:url]
-    uri_path = uri.path.split('/')
-    uri_path = ["","index.html"] if uri_path.size == 0
-    uri_path.unshift("") if uri_path.size == 1
-    file_ext = uri_path[-1].split('.')[-1]
-    file = ::Digest::SHA1.hexdigest(uri.to_s)
-    file += ".#{file_ext}" if file_ext
-    return file
-  end
 end

data/lib/concord/java_proxy_cacher.rb

@@ -1,16 +1,40 @@
+require 'concord/cacher'
+
 class ::Concord::JavaProxyCacher < ::Concord::Cacher
   require 'digest/sha1'
+  require 'concord/helper'
+  require 'concord/resource'
+  require 'concord/filename_generators/java_proxy_generator'
   
-  def generate_main_filename
-    generate_filename(:content => @content)
+  include ::Concord::Helper
+  
+  def initialize(opts = {})
+    ::Concord::Resource.create_map = true
+    ::Concord::Resource.cache_headers = true
+    ::Concord::Resource.rewrite_urls = false
+    ::Concord::Resource.filename_generator = ::Concord::FilenameGenerators::JavaProxyGenerator
+    super
+  end
+  
+  def cache
+    super
+  	write_url_to_hash_map
   end
   
-  def generate_uuid
-    generate_filename(:content => @content)
+  def write_url_to_hash_map
+    load_existing_map if (File.exists?(@main_resource.cache_dir + "url_map.xml"))
+    write_property_map(@main_resource.cache_dir + "url_map.xml", ::Concord::Resource.url_map)
   end
   
-  def generate_filename(opts = {})
-    raise InvalidArgumentError, "Must include :content key in opts" unless opts[:content]
-    ::Digest::SHA1.hexdigest(opts[:content])
+  def load_existing_map
+    map_content = ::REXML::Document.new(File.new(@main_resource.cache_dir + "url_map.xml")).root
+    map_content.elements.each("entry") do |entry|
+      k = entry.attributes["key"]
+      if ! (::Concord::Resource.url_map.include? k)
+        val = entry.text
+        ::Concord::Resource.url_map[k] = val
+        # puts "Adding previously defined url: #{k}  =>  #{val}" if DEBUG
+      end
+    end
   end
 end

data/lib/concord_cacher.rb

@@ -2,7 +2,7 @@ $:.unshift(File.dirname(__FILE__)) unless
   $:.include?(File.dirname(__FILE__)) || $:.include?(File.expand_path(File.dirname(__FILE__)))
 
 module Concord
-  require 'concord/cacher'
+  require 'concord/filename_generators'
   require 'concord/diy_local_cacher'
   require 'concord/java_proxy_cacher'
 end

data/spec/data/element_reference.otml

@@ -7,7 +7,7 @@
       <root>
         <OTText>
           <!-- Absolute references -->
-          <a href="http://loops.diy.concord.org/">Visit the Concord Website</a>
+          <a href="http://www.concord.org/~aunger/">Visit the Concord Website</a>
           <img src="http://portal.concord.org/images/icons/chart_bar.png" />
           <OTBlob imageBytes="http://portal.concord.org/images/icons/chart_pie.png" />
           

data/spec/diy_local_cacher_spec.rb

@@ -10,31 +10,20 @@ require 'fileutils'
 
 include FileUtils
 
-require 'openssl'
-module OpenSSL
-  module SSL
-	  remove_const :VERIFY_PEER
-	end
-end
-OpenSSL::SSL::VERIFY_PEER = OpenSSL::SSL::VERIFY_NONE
-
 SPEC_ROOT = File.expand_path(File.dirname(__FILE__))
 
-$\ = "<br/>\n"
-
 describe 'DIY Local Cacher' do
   include CacheHelper
   
   before(:each) do
     @klass = Concord::DiyLocalCacher
     @cache = File.join(SPEC_ROOT, '..', 'tmp','diy_local')
-    rm_rf(@cache)
     mkdir_p(@cache)
     @cache += '/'
   end
   
   after(:each) do
-    # rm_rf(@cache)
+    rm_rf(@cache)
   end
   
   def mockup(file)
@@ -68,7 +57,6 @@ describe 'DIY Local Cacher' do
     end
   
     it 'should create a cached file of the original url' do
-      url = File.join(SPEC_ROOT,'data','empty.otml')
       cache('empty.otml', :activity => mockup('empty.otml'))
       exists?('hash.otml')
     end
@@ -79,6 +67,13 @@ describe 'DIY Local Cacher' do
       cache('empty.otml', :activity => mockup('empty.otml'))
       does_not_exist?("#{expected_filename}.hdrs")
     end
+    
+    it 'should strip the codebase from the otrunk element' do
+      cache('codebase.otml', :activity => mockup('codebase.otml'))
+      
+      file_content = File.read(File.join(@cache,'hash.otml'))
+      file_content.should_not match(/<otrunk.*?codebase=.*?>/)
+    end
   end
   
   describe 'standard uri syntax' do
@@ -113,7 +108,7 @@ describe 'DIY Local Cacher' do
     it 'should cache 6 referenced files' do
       expected_files = []
       expected_files << 'hash.otml' # element_reference.otml
-      expected_files << filename_for('http://loops.diy.concord.org/')
+      expected_files << filename_for('http://www.concord.org/~aunger/')
       expected_files << filename_for('http://portal.concord.org/images/icons/chart_bar.png')
       expected_files << filename_for('http://portal.concord.org/images/icons/chart_pie.png')
       expected_files << filename_for('resources/text.txt', File.join(SPEC_ROOT,'data','element_reference.otml'))
@@ -131,7 +126,7 @@ describe 'DIY Local Cacher' do
     it 'should rewrite the urls in the main otml file' do
       expected_urls = []
       unexpected_urls = []
-      unexpected_urls << 'http://loops.diy.concord.org/'
+      unexpected_urls << 'http://www.concord.org/~aunger/'
       unexpected_urls << 'http://portal.concord.org/images/icons/chart_bar.png'
       unexpected_urls << 'http://portal.concord.org/images/icons/chart_pie.png'
       unexpected_urls << File.join('resources','text.txt')
@@ -248,18 +243,59 @@ describe 'DIY Local Cacher' do
   end
   
   describe 'embedded nlogo files' do
+    it 'should download absolute referenced nlogo files' do
+      expected_files = []
+      expected_files << filename_for('http://otrunk.concord.org/examples/LOOPS/models/Spaceship.1D.docking.nlogo')
+      
+      cache('nlogo_absolute.otml', :activity => mockup('nlogo_absolute.otml'))
+      
+      expected_files.each do |f|
+        exists?(f)
+      end
+    end
+    
+    it 'should download relative referenced nlogo files' do
+      expected_files = []
+      expected_files << filename_for('resources/nlogo/SpaceRescue.Practice1.nlogo', File.join(SPEC_ROOT,'data','nlogo_relative.otml'))
+      
+      cache('nlogo_relative.otml', :activity => mockup('nlogo_relative.otml'))
+      
+      expected_files.each do |f|
+        exists?(f)
+      end
+    end
+    
     it 'should correctly download resources referenced from within netlogo model files'
   end
   
   describe 'embedded mw files' do
-    it 'should download absolute referenced cml files'
-    it 'should download relative referenced cml files'
+    it 'should download absolute referenced cml files' do
+      expected_files = []
+      expected_files << filename_for('http://otrunk.concord.org/examples/LOOPS/models/statesofmatter/statesOfMatterPage1.cml')
+      
+      cache('mw_model_absolute.otml', :activity => mockup('mw_model_absolute.otml'))
+      
+      expected_files.each do |f|
+        exists?(f)
+      end
+    end
+    
+    it 'should download relative referenced cml files' do
+      expected_files = []
+      expected_files << filename_for('resources/statesofmatter/statesOfMatterPage1.cml', File.join(SPEC_ROOT,'data','mw_model_relative.otml'))
+      
+      cache('mw_model_relative.otml', :activity => mockup('mw_model_relative.otml'))
+      
+      expected_files.each do |f|
+        exists?(f)
+      end
+    end
     
     it 'should correctly download mmls referenced from within mw cml files' do
       expected_files = []
       expected_files << filename_for('http://otrunk.concord.org/examples/LOOPS/models/statesofmatter/statesOfMatterPage1$0.mml')
       
-      cache('mw_model.otml', :activity => mockup('mw_model.otml'), :verbose => true)
+      cache('mw_model_absolute.otml', :activity => mockup('mw_model_absolute.otml'))
       
       expected_files.each do |f|
         exists?(f)
@@ -271,7 +307,12 @@ describe 'DIY Local Cacher' do
   end
   
   describe 'never cache' do
-    it 'should always skip mailto and jres references'
+    it 'should always skip some references' do
+      url = File.join(SPEC_ROOT,'data','always_skip.otml')
+      expected_filename = 'hash.otml'
+      cache('always_skip.otml', :activity => mockup('always_skip.otml'))
+      cache_size.should == 1
+    end
   end
   
   describe 'recursion limits' do

data/spec/helpers/cache_helper.rb

@@ -1,6 +1,6 @@
 module CacheHelper
   def cache(file, opts = {})
-    options = {:url => File.join(SPEC_ROOT,'data',file), :cache_dir => @cache, :verbose => false}.merge(opts)
+    options = {:url => File.join(SPEC_ROOT,'data',file), :cache_dir => @cache}.merge(opts)
     cacher = @klass.new(options)
     cacher.cache
   end
@@ -19,4 +19,12 @@ module CacheHelper
   def cache_size
     Dir.glob(@cache + "/**/*").select{|f| File.file?(f) }.size
   end
-end
+end
+
+require 'openssl'
+module OpenSSL
+  module SSL
+	  remove_const :VERIFY_PEER
+	end
+end
+OpenSSL::SSL::VERIFY_PEER = OpenSSL::SSL::VERIFY_NONE

data/spec/java_proxy_cacher_spec.rb

@@ -10,14 +10,6 @@ require 'fileutils'
 
 include FileUtils
 
-require 'openssl'
-module OpenSSL
-  module SSL
-	  remove_const :VERIFY_PEER
-	end
-end
-OpenSSL::SSL::VERIFY_PEER = OpenSSL::SSL::VERIFY_NONE
-
 SPEC_ROOT = File.expand_path(File.dirname(__FILE__))
 
 
@@ -74,6 +66,20 @@ describe 'Java Proxy Cacher' do
       does_not_exist?('8f0ebcb45d7ba71a541d4781329f4a6900c7ee65') # http://portal.concord.org/images/icons/delete.png
     end
     
+    it 'should handle a url with trailing spaces gracefully' do
+      url = File.join(SPEC_ROOT,'data','url_with_space.otml')
+      expected_filename = ::Digest::SHA1.hexdigest(File.read(url))
+      
+      lambda {
+        cache('url_with_space.otml')
+      }.should_not raise_error
+      
+      cache_size.should == 5
+      
+      exists?(expected_filename)
+      exists?('d1cea238486aeeba9215d56bf71efc243754fe48') # http://portal.concord.org/images/icons/chart_line.png
+    end
+    
     it 'should handle an empty url gracefully' do
       url = File.join(SPEC_ROOT,'data','empty_url.otml')
       expected_filename = ::Digest::SHA1.hexdigest(File.read(url))
@@ -120,8 +126,8 @@ describe 'Java Proxy Cacher' do
   describe 'element references syntax' do
     it 'should cache 6 referenced files' do
       expected_files = []
-      expected_files << '9f945e576290efa874842b4ee07ab437d9d94a67' # element_reference.otml
-      expected_files << 'd9a2565586307e2924c953dfe788154749e93799' # http://loops.diy.concord.org/
+      expected_files << '836ba09d9d7288cf735f555e7a9b9b314ad2f6ef' # element_reference.otml
+      expected_files << '20e89b62dda582d80e1832050f4998d64c801c03' # http://www.concord.org/~aunger/
       expected_files << '4e9576a56db3d142113b8905d7aa93e31c9f441b' # http://portal.concord.org/images/icons/chart_bar.png
       expected_files << '41f082b7e69a399679a47acfdcd7e7a204e49745' # http://portal.concord.org/images/icons/chart_pie.png
       expected_files << 'cbe7ac86926fd3b8aa8659842a1d8c299d8966a7' # resources/text.txt
@@ -191,7 +197,12 @@ describe 'Java Proxy Cacher' do
   end
   
   describe 'never cache' do
-    it 'should always skip mailto and jres references'
+    it 'should always skip some references' do
+      url = File.join(SPEC_ROOT,'data','always_skip.otml')
+      expected_filename = ::Digest::SHA1.hexdigest(File.read(url))
+      cache('always_skip.otml')
+      cache_size.should == 3
+    end
   end
   
   describe 'recursion limits' do

metadata

@@ -4,9 +4,9 @@ version: !ruby/object:Gem::Version
   prerelease: false
   segments: 
   - 0
+  - 1
   - 0
-  - 5
-  version: 0.0.5
+  version: 0.1.0
 platform: ruby
 authors: 
 - Aaron Unger
@@ -35,7 +35,7 @@ cert_chain:
   8kT2T2VF
   -----END CERTIFICATE-----
 
-date: 2010-03-26 00:00:00 -04:00
+date: 2010-04-05 00:00:00 -04:00
 default_executable: 
 dependencies: []