rubyBHL 0.1.0

data/Manifest

@@ -0,0 +1,7 @@
+Manifest
+README.rdoc
+Rakefile
+init.rb
+lib/rubyBHL.rb
+test/helper.rb
+test/rubyBHL_test.rb

data/README.rdoc

@@ -0,0 +1,16 @@
+= RubyBHL
+
+A very simple Ruby hook to the BHL.
+
+== Install 
+
+  gem install mjy-RubyBHL --source http://gems.github.com
+
+== Usage
+
+See tests.
+
+== Todo
+
+Lots.
+

data/Rakefile

@@ -0,0 +1,18 @@
+# follows Bate's screencast 135
+
+require 'rubygems'
+require 'rake'
+require 'echoe'
+
+Echoe.new('rubyBHL', '0.1.0') do |p|
+  p.description = "Hook to the Biodiversity Heritage Library API plus some screen scraping for OCR."
+  p.url = "http://github.com/mjy/rubyBHL"
+  p.author = "Yoder & Seltmann"
+  p.email = "diapriid@gmail.com"
+  p.ignore_pattern = ["tmp/*", "script/*"]
+  p.development_dependencies = []
+end
+
+Dir["#{File.dirname(__FILE__)}/tasks/*.rake"].sort.each {|ext| load ext}
+
+  

data/init.rb

@@ -0,0 +1 @@
+#require 'ruby_BHL'

data/lib/rubyBHL.rb

@@ -0,0 +1,116 @@
+module RubyBHL
+  
+ # Some quick hacks, only configured for json right now.
+
+ require 'net/http'
+ # require 'json'
+ require 'json/add/rails'
+
+ class RbhlError < StandardError
+ end
+
+ class Rbhl
+   
+ # some notes   
+ #http://www.biodiversitylibrary.org/openurl?url_ver=Z39.88-2004&ctx_ver=Z39.88-2004
+ #rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook
+ #rft.btitle
+ #rft.jtitle
+ #rft.au
+ #rft.aufirst
+ #rft.aulast
+ #rft.publisher
+ #rft.pub
+ #rft.place
+ #rft.date
+ #rft.issn
+ #rft.isbn
+ # rft.coden
+ # rft.stitle
+ # rft.volume
+ # rft.issue
+ # rft.spage
+ # rft_id=info:oclcnum/XXXX
+ # rft_id=info:lccn/XXXX
+ # rft_id=http://www.biodiversitylibrary.org/bibliography/XXXX
+ # rft_id=http://www.biodiversitylibrary.org/page/XXXX
+  
+  # "constants" (defaults really)
+  SEARCH_URL =  'http://www.biodiversitylibrary.org/openurl?' 
+  FORMAT = 'json'
+  #  METHOD = '' # openURL0.1, openURL1.0 
+
+  PARAMETERS = [
+                  :title,
+                  :au,
+                  :aufirst,
+                  :aulast,
+                  :publisher,
+                  :date,
+                  :issn,
+                  :isbn,
+                  :coden,
+                  :stitle,
+                  :volume,
+                  :issue,
+                  :spage]
+  
+  # created from response
+  attr_reader(:json_data)
+  attr_reader(:citations)
+  attr :search_url
+
+ def initialize(options = {}) 
+   @opt = {
+    #  :method => METHOD,
+      :format => FORMAT,
+      :params => {}
+   }.merge!(options)
+   
+   # check for legal parameters
+   @opt[:params].keys.each do |p|
+      raise RbhlError, "#{p} is not a valid parameter" if !PARAMETERS.include?(p)
+   end 
+     
+   @json_data = {}
+     
+   @search_url = SEARCH_URL + 
+       @opt[:params].keys.sort{|a,b| a.to_s <=> b.to_s}.collect{|k| "#{k}=#{@opt[:params][k].gsub(/\s/, "+")}"}.join("&") +
+      '&format=' + @opt[:format]       
+       
+   @json_data = JSON.parse(Net::HTTP.get_response(URI.parse(@search_url)).body)
+   @citations = @json_data['citations'] if @json_data['Status'] == 1 # a simpler reference
+   
+   true
+ end
+
+ # this works on a redirect
+ def OCR_text(citation_index)
+   return nil if !citation_index
+   fetch(OCR_url(citation_index))
+ end
+ 
+ # from the ruby doc
+ def fetch(uri_string, limit = 10)
+   return nil if !uri_string
+   limit = 10 # Justin Case we get in some redirect loop
+   raise RbhlError, 'HTTP redirect too deep' if limit == 0 # should tweak
+   response = Net::HTTP.get_response(URI.parse(uri_string))
+   case response
+   when Net::HTTPSuccess then response.body
+   when Net::HTTPRedirection then fetch(response['location'], limit - 1)
+   else
+     response.error!
+    end
+  end
+
+ # Since the API doesn't return a link to the OCR we screen scrape it the URL
+ def OCR_url(citation_index)
+   Net::HTTP.get_response(URI.parse(@citations[citation_index]["Url"])).body =~ /http:\/\/.*?\.txt/
+   return $& # the matched results
+ end
+
+end
+
+
+end

data/rubyBHL.gemspec

@@ -0,0 +1,31 @@
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{rubyBHL}
+  s.version = "0.1.0"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 1.2") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Yoder & Seltmann"]
+  s.date = %q{2009-10-19}
+  s.description = %q{Hook to the Biodiversity Heritage Library API plus some screen scraping for OCR.}
+  s.email = %q{diapriid@gmail.com}
+  s.extra_rdoc_files = ["README.rdoc", "lib/rubyBHL.rb"]
+  s.files = ["Manifest", "README.rdoc", "Rakefile", "init.rb", "lib/rubyBHL.rb", "test/helper.rb", "test/rubyBHL_test.rb", "rubyBHL.gemspec"]
+  s.homepage = %q{http://github.com/mjy/rubyBHL}
+  s.rdoc_options = ["--line-numbers", "--inline-source", "--title", "rubyBHL", "--main", "README.rdoc"]
+  s.require_paths = ["lib"]
+  s.rubyforge_project = %q{rubybhl}
+  s.rubygems_version = %q{1.3.5}
+  s.summary = %q{Hook to the Biodiversity Heritage Library API plus some screen scraping for OCR.}
+  s.test_files = ["test/rubyBHL_test.rb"]
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
+    else
+    end
+  else
+  end
+end

data/test/helper.rb

@@ -0,0 +1,3 @@
+require 'test/unit'
+require 'rubygems'
+require 'ruby-debug'

data/test/rubyBHL_test.rb

@@ -0,0 +1,36 @@
+require File.expand_path(File.join(File.dirname(__FILE__), 'helper'))
+require File.expand_path(File.join(File.dirname(__FILE__), '../lib/rubyBHL'))
+
+class RubyBHLTest < Test::Unit::TestCase
+
+  def setup
+  end
+
+  def test_foo_is_not_a_legal_param
+    assert_raise(RubyBHL::RbhlError) {RubyBHL::Rbhl.new(:params => {:foo => "BAR!"}) }   
+  end
+  
+  def test_search_url_for_default_url_is_properly_formed
+    @bhl = RubyBHL::Rbhl.new(:params => {:title => "BAR!", :volume => "2"})
+    assert_equal "http://www.biodiversitylibrary.org/openurl?title=BAR!&volume=2&format=json", @bhl.search_url 
+  end
+  
+  def test_search_url_convert_space_to_plus
+    @bhl = RubyBHL::Rbhl.new(:params => {:title => "BAR FOO"})
+    assert_equal "http://www.biodiversitylibrary.org/openurl?title=BAR+FOO&format=json", @bhl.search_url 
+  end
+  
+  def test_basic_response_is_returned
+   # this is a crummy test, we need a reference to the status codes.
+   @bhl = RubyBHL::Rbhl.new(:params => {:title => "BAR FOO"}) # should match nothing, I hope
+   assert @bhl.json_data["Status"] == 1
+   assert @bhl.json_data["citations"].size == 0
+  end
+  
+  def test_response_with_citations_is_returned
+   # this is a crummy test, we need a reference to the status codes.
+   @bhl = RubyBHL::Rbhl.new(:params => {:title => "Manual of North American Diptera"}) # should match nothing, I hope
+   assert @bhl.json_data["citations"].size > 0
+  end
+
+end

metadata

@@ -0,0 +1,68 @@
+--- !ruby/object:Gem::Specification 
+name: rubyBHL
+version: !ruby/object:Gem::Version 
+  version: 0.1.0
+platform: ruby
+authors: 
+- Yoder & Seltmann
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-10-19 00:00:00 -04:00
+default_executable: 
+dependencies: []
+
+description: Hook to the Biodiversity Heritage Library API plus some screen scraping for OCR.
+email: diapriid@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- README.rdoc
+- lib/rubyBHL.rb
+files: 
+- Manifest
+- README.rdoc
+- Rakefile
+- init.rb
+- lib/rubyBHL.rb
+- test/helper.rb
+- test/rubyBHL_test.rb
+- rubyBHL.gemspec
+has_rdoc: true
+homepage: http://github.com/mjy/rubyBHL
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --line-numbers
+- --inline-source
+- --title
+- rubyBHL
+- --main
+- README.rdoc
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "1.2"
+  version: 
+requirements: []
+
+rubyforge_project: rubybhl
+rubygems_version: 1.3.5
+signing_key: 
+specification_version: 3
+summary: Hook to the Biodiversity Heritage Library API plus some screen scraping for OCR.
+test_files: 
+- test/rubyBHL_test.rb