Merge pull request #6 from lcdhoffman/master

Merge lcdhoffman repo into master repo
archivesspace-deprecated · Jan 10, 2014 · a5f90fc · a5f90fc
2 parents bab9d3a + ba0fc39
commit a5f90fc
Show file tree

Hide file tree

Showing 12 changed files with 443 additions and 163 deletions.
diff --git a/Gemfile b/Gemfile
@@ -6,7 +6,7 @@ gem 'execjs'
 gem 'jsmin'
 gem 'json'
 gem 'json-schema', '= 1.0.10'
-gem 'lrucache'
+gem 'rufus-lru'
 gem 'mime-types'
 gem 'minitest'
 gem 'multi_json'
@@ -15,9 +15,8 @@ gem 'puma'
 gem 'rack'
 gem 'rack-protection'
 gem 'rack-test'
-gem 'rdoc'
 gem 'rspec'
 gem 'rubyzip'
 gem 'sinatra'
 gem 'sinatra-assetpack'
-gem 'zip'
+gem 'tilt', '= 1.4.1'
diff --git a/Gemfile.lock b/Gemfile.lock
@@ -0,0 +1,65 @@
+GEM
+  remote: https://rubygems.org/
+  specs:
+    atomic (1.1.14-java)
+    diff-lcs (1.2.5)
+    execjs (2.0.2)
+    jsmin (1.0.1)
+    json (1.8.1-java)
+    json-schema (1.0.10)
+    mime-types (2.0)
+    minitest (5.2.0)
+    multi_json (1.8.2)
+    net-http-persistent (2.9)
+    puma (2.7.1-java)
+      rack (>= 1.1, < 2.0)
+    rack (1.5.2)
+    rack-protection (1.5.1)
+      rack
+    rack-test (0.6.2)
+      rack (>= 1.0)
+    rspec (2.14.1)
+      rspec-core (~> 2.14.0)
+      rspec-expectations (~> 2.14.0)
+      rspec-mocks (~> 2.14.0)
+    rspec-core (2.14.7)
+    rspec-expectations (2.14.4)
+      diff-lcs (>= 1.1.3, < 2.0)
+    rspec-mocks (2.14.4)
+    rubyzip (1.1.0)
+    rufus-lru (1.0.5)
+    sinatra (1.4.4)
+      rack (~> 1.4)
+      rack-protection (~> 1.4)
+      tilt (~> 1.3, >= 1.3.4)
+    sinatra-assetpack (0.3.1)
+      jsmin
+      rack-test
+      sinatra
+      tilt (>= 1.3.0)
+    tilt (1.4.1)
+
+PLATFORMS
+  java
+
+DEPENDENCIES
+  atomic
+  bundler
+  execjs
+  jsmin
+  json
+  json-schema (= 1.0.10)
+  mime-types
+  minitest
+  multi_json
+  net-http-persistent
+  puma
+  rack
+  rack-protection
+  rack-test
+  rspec
+  rubyzip
+  rufus-lru
+  sinatra
+  sinatra-assetpack
+  tilt (= 1.4.1)
diff --git a/README.md b/README.md
@@ -2,96 +2,32 @@ Archon2ArchivesSpace README
 ================
 # System Requirements
 
-You will need to have Ruby 1.9.3 installed to run this service
+You will need to have java installed to run this service. Example:
 
-	ruby --version
-    # example output: ruby 1.9.3p429 (2013-05-15 revision 40747)
+    java -version
+    -> Java(TM) SE Runtime Environment (build 1.7.0_17-b02)
+    -> Java HotSpot(TM) 64-Bit Server VM (build 23.7-b01, mixed mode)
 
-If your system has a different version of Ruby installed, the simplest way to
-leave your system intact and get 1.9.3 is to install RVM (https://rvm.io/).
+# Running the service
 
-# Installing the service
+Download the .war file from the Releases page: https://github.com/lcdhoffman/archon-migration/releases
 
-Download a release or just checkout the project from Github:
+To run the service:
 
-    git clone https://github.com/lcdhoffman/archon-migration.git
-    cd archon-migration
-
-Run a script to download the necessary ArchivesSpace libraries:
-
-	./scripts/import\_client\_libs.sh v1.0.0RC1
-
-This will attempt to download the ArchivesSpace source code for ArchivesSpace v1.0.0RC1.
-*Note: the service ships with libraries for ArchivesSpace 1.0.0, so you can skip this step
-if you are targeting 1.0.0.
-
-Install the application dependencies listed in the Gemfile:
-
-    gem install bundler
-    bundle install
-
-Now run the application:
-
-    ruby app/main.rb
-
-The service runs on port 4568 by default. To change this:
-
-	touch config/config_local.rb
-    echo "Appdata.port_number YOUR_FAVORITE_PORT_HERE" >> config/config_local.rb
-
-# Daemonizing the Service
-
-The service can be daemonized in several ways. One option is to install a native
-ruby solution such as the Daemonize gem (http://daemons.rubyforge.org/). However,
-since the service is intended to be short-lived, it may be easiest to simply
-send the process to the background and disown it.
-
-# Using the Service
+    java -jar archon-migration.war [--httpPort=XXXX]
 
-The service is designed to be used in a browser window. Make sure you have a 
-running Archon instance and a running ArchiveSpace instance. You will also need 
-account credentials for each service. It is recommended that you create a 
-separate account called 'migration_user' and assign this user the required 
-permissions in each application.
+This will start the application within an embedded webserver. The default port of the webserver is 8080.
 
-Point your browser to, e.g.,  http://localhost:4568 and fill out the web form. 
+# Building the distribution
 
-# Configuration Options
+You can build a distribution by cloning the source code:
 
-The best way to configure the application is to create a local config file:
-
-    touch config/config_local.rb
-
-To change, for example, the version of the ArchivesSpace target, add the following
-line
-
-	Appdata.aspace_version 'v1.0.1'
-
-If Archon response times become slow due to network latency or large datasets, it is
-possible to speed up successive tests by turning on database caching. Note that you must manually delete
-the database if you point the migration tool at a new Archon instance.
-
-	Appdata.use_dbcache  true
-
-*Note: this feature is not complete and should be left off by default.
-
-# Notes
-
-A typical migration can take several hours and could cause ArchivesSpace's 
-indexer to get backed up. Migrated records may not appear right away in browse or search results in ArchivesSpace. Consider running ArchivesSpace with the indexer
-turned off to speed up the migration process, or upgrading to a later version of ArchivesSpace.
-
-Do not run a migration process against an ArchivesSpace instance that already
-contains data.
-
-Do not allow Archon users to create or edit data while the migration is running.
-
-Do not allow ArchivesSpace users to create or edit data while the migration is
-running.
+    git clone https://github.com/lcdhoffman/archon-migration.git
+    cd archon-migration
 
-You can optimize the performance of the migration tool by adjusting the number of
-pages of Archon data that are cached. For example, if your largest Archon collection contains 50,000 Content records, and you are running the migration tool in an environment that can afford around 300MB of memory, you might want to add this line to your config_local.rb file:
+and using warbler to build a web application archive:
 
-    Appdata.archon_page_cache_size 500
+    gem install warbler
+    warble executable war
 
-There's no (or little) advantage to setting the page cache size to a value larger than the number of Content records in the largest Collection, divided by 100. There is a significant disadvantage to keeping your page cache size smaller than the number of pages of items in your largest collection.
+Now visit your application at http://localhost:8080
diff --git a/README_MRI.md b/README_MRI.md
@@ -0,0 +1,97 @@
+Archon2ArchivesSpace README
+================
+# System Requirements
+
+You will need to have Ruby 1.9.3 installed to run this service
+
+	ruby --version
+    # example output: ruby 1.9.3p429 (2013-05-15 revision 40747)
+
+If your system has a different version of Ruby installed, the simplest way to
+leave your system intact and get 1.9.3 is to install RVM (https://rvm.io/).
+
+# Installing the service
+
+Download a release or just checkout the project from Github:
+
+    git clone https://github.com/lcdhoffman/archon-migration.git
+    cd archon-migration
+
+Run a script to download the necessary ArchivesSpace libraries:
+
+	./scripts/import\_client\_libs.sh v1.0.0RC1
+
+This will attempt to download the ArchivesSpace source code for ArchivesSpace v1.0.0RC1.
+*Note: the service ships with libraries for ArchivesSpace 1.0.0, so you can skip this step
+if you are targeting 1.0.0.
+
+Install the application dependencies listed in the Gemfile:
+
+    gem install bundler
+    bundle install
+
+Now run the application:
+
+    ruby app/main.rb
+
+The service runs on port 4568 by default. To change this:
+
+	touch config/config_local.rb
+    echo "Appdata.port_number YOUR_FAVORITE_PORT_HERE" >> config/config_local.rb
+
+# Daemonizing the Service
+
+The service can be daemonized in several ways. One option is to install a native
+ruby solution such as the Daemonize gem (http://daemons.rubyforge.org/). However,
+since the service is intended to be short-lived, it may be easiest to simply
+send the process to the background and disown it.
+
+# Using the Service
+
+The service is designed to be used in a browser window. Make sure you have a 
+running Archon instance and a running ArchiveSpace instance. You will also need 
+account credentials for each service. It is recommended that you create a 
+separate account called 'migration_user' and assign this user the required 
+permissions in each application.
+
+Point your browser to, e.g.,  http://localhost:4568 and fill out the web form. 
+
+# Configuration Options
+
+The best way to configure the application is to create a local config file:
+
+    touch config/config_local.rb
+
+To change, for example, the version of the ArchivesSpace target, add the following
+line
+
+	Appdata.aspace_version 'v1.0.1'
+
+If Archon response times become slow due to network latency or large datasets, it is
+possible to speed up successive tests by turning on database caching. Note that you must manually delete
+the database if you point the migration tool at a new Archon instance.
+
+	Appdata.use_dbcache  true
+
+*Note: this feature is not complete and should be left off by default.
+
+# Notes
+
+A typical migration can take several hours and could cause ArchivesSpace's 
+indexer to get backed up. Migrated records may not appear right away in browse or search results in ArchivesSpace. Consider running ArchivesSpace with the indexer
+turned off to speed up the migration process, or upgrading to a later version of ArchivesSpace.
+
+Do not run a migration process against an ArchivesSpace instance that already
+contains data.
+
+Do not allow Archon users to create or edit data while the migration is running.
+
+Do not allow ArchivesSpace users to create or edit data while the migration is
+running.
+
+You can optimize the performance of the migration tool by adjusting the number of
+pages of Archon data that are cached. For example, if your largest Archon collection contains 50,000 Content records, and you are running the migration tool in an environment that can afford around 300MB of memory, you might want to add this line to your config_local.rb file:
+
+    Appdata.archon_page_cache_size 500
+
+There's no (or little) advantage to setting the page cache size to a value larger than the number of Content records in the largest Collection, divided by 100. There is a significant disadvantage to keeping your page cache size smaller than the number of pages of items in your largest collection.
diff --git a/app/lib/archon_client.rb b/app/lib/archon_client.rb
@@ -2,7 +2,7 @@
 require_relative 'startup'
 require 'net/http/persistent'
 require 'json'
-require 'lrucache'
+require 'rufus-lru'
 
 module Archon
 
@@ -102,7 +102,7 @@ def get_container_type(id)
   class ArchonRecord
     include RecordSetupHelpers
     include EnumLookupHelpers
-    @@cache = LRUCache.new(:max_size => 300, :default => false, :ttl => 600)
+    @@cache = Rufus::Lru::Hash.new(300)
 
     def self.each(instantiate=true)
       raise NoArchonClientException unless Thread.current[:archon_client]
@@ -200,7 +200,7 @@ def self.unfound(id = '0')
 
     def self.find(id)
       import_id = import_id_for(id)
-      if @@cache[import_id].nil?
+      if @@cache.has_key?(import_id) && @@cache[import_id].nil?
         return unfound(id)
       end
 
@@ -354,9 +354,7 @@ def http
 
 
     def get_json(endpoint, usecache=true)
-      @http_cache ||= LRUCache.new(
-                                   :max_size => Appdata.archon_page_cache_size, 
-                                   :default => false)
+      @http_cache ||= Rufus::Lru::Hash.new(Appdata.archon_page_cache_size)
 
       # look at in-memory cache
       if @http_cache[endpoint]

diff --git a/app/lib/migrate.rb b/app/lib/migrate.rb
@@ -2,7 +2,7 @@
 require_relative 'archon_client'
 require_relative 'archivesspace_client'
 require_relative 'migration_helpers'
-require 'zip/zip'
+require 'zip'
 
 
 class MigrationJob
@@ -24,11 +24,6 @@ def initialize(params = {})
 
     Archon.record_type(:digitalfile).base_url = @args[:do_baseurl]
 
-    # 1 job per thread
-    raise "Job thread occupied." if Thread.current[:archon_migration_job]
-    Thread.current[:archon_migration_job] = self
-
-
     @aspace = ArchivesSpace::Client.new(
                                         :url => @args[:aspace_url],
                                         :user => @args[:aspace_user],
@@ -503,7 +498,7 @@ def package_digital_files
     directory = Dir.tmpdir + "/archon_bitstreams/"
     zipfile_name = File.join(File.dirname(__FILE__), '../', 'public', 'bitstreams.zip')
 
-    Zip::ZipFile.open(zipfile_name, Zip::ZipFile::CREATE) do |zipfile|
+    Zip::File.open(zipfile_name, Zip::File::CREATE) do |zipfile|
       Dir.glob("#{directory}*.*").each do |file|
         zipfile.add(file.sub(directory, ''), file)
       end