just_inform 0.0.4 → 0.0.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 33226c88491ca873a4a890b6210b238d71d2303b
-  data.tar.gz: 3f4a35a9f074f03b5174652d339e6e620b581530
+  metadata.gz: ec2675e3a079ced6653676bdea664378f0e7bb1e
+  data.tar.gz: 3e68625e479cf8959c347d4b1bfe777ea64f2c3e
 SHA512:
-  metadata.gz: bf2bf9d4ef845106848dd4d29e42d0bf6cac9fe9f423a4fcb7b33d8188b7b1dfad96d0ec7e8c9d7ab4eb9489756ccd8eadc407a79b041a6ea42631c2a72c161a
-  data.tar.gz: a6d3abaa960709c01ea484c60e8b74d05b03d7bbe4c8aa10b888577011f1212552e0491debf210b2ddf6189cf4fa1302f0897f58012bd9add3d10a00417099b9
+  metadata.gz: 4726db2cd02fcb8f5b0cc698b2cfe05e6f35ad43504828d6393481d4b47fe6088a411190ebdc70be3c1efe8d034e51fdf86f6b2ef2c44074daf4969075743bd7
+  data.tar.gz: bd4bfa4acbb2a9271b296c037458adcc58215d6ef7465c16ddf3bba7e6f5265000c8757e3903732be0c85700cd439cda3b08b6c014de28f1dc632225e9ed4bac

data/README.md

@@ -4,15 +4,18 @@ Just Inform is a simple library to help parse the daily XML feed from [RegInfo.g
 
 ## Basic Usage
 
-#### Install the gem
-gem install just_inform
-
-#### Create a new parser instance
-parser = JustInform.new
-
-#### Return an array with the sort value (cost) and InformationCollectionRequest objects
-parser.top(10, :cost)  => 
-[["33,672,000,000", U.S. Individual Income Tax Return], ["8,190,000,004", Rule 10b-10 Confirmation of Securities Transactions (17 C.F.R. 240.10b-10)], ["2,857,465,000", Exchange Act  Form 10-K], ["2,727,479,226", America Invents Act Section 10 Patent Fee Adjustments], ["1,801,830,000", Application for a U.S. Passport], ["1,300,147,200", ASSIST Database], ["1,280,341,567", Form SD], ["910,000,000", Online Application for Nonimmigrant Visa], ["791,160,764", Rules for Patent Maintenance Fees], ["772,798,833", Initial Patent Applications]]
+    # Install the gem
+    gem install just_inform
+
+    # Load IRB
+    irb
+    
+    # Create a new parser instance (same as JustInform::Parser.new)
+    parser = JustInform.new
+
+    # Return an array with the sort value (cost) and InformationCollectionRequest objects
+    parser.top(10, :cost)  => 
+    [["33,672,000,000", U.S. Individual Income Tax Return], ["8,190,000,004", Rule 10b-10 Confirmation of Securities Transactions (17 C.F.R. 240.10b-10)], ["2,857,465,000", Exchange Act  Form 10-K], ["2,727,479,226", America Invents Act Section 10 Patent Fee Adjustments], ["1,801,830,000", Application for a U.S. Passport], ["1,300,147,200", ASSIST Database], ["1,280,341,567", Form SD], ["910,000,000", Online Application for Nonimmigrant Visa], ["791,160,764", Rules for Patent Maintenance Fees], ["772,798,833", Initial Patent Applications]]
 
 You can also sort by burden hours (:burden) and number of responses (:responses).
 

data/just_inform.gemspec

@@ -17,7 +17,6 @@ Gem::Specification.new do |s|
     "just_inform.gemspec",
     "LICENSE.md",
     "README.md",
-    'data',
     "lib/just_inform.rb",
     "lib/just_inform/downloader.rb",
     "lib/just_inform/information_collection.rb",

data/lib/just_inform.rb

@@ -1,27 +1,6 @@
-module JustInform; end
-
-module Nokogiri
-  module XML
-    class Node
-      
-      def inspect_attributes
-        [:name]
-      end
-      
-    end
-  end
-end
-
-module Nokogiri
-  module XML
-
-    class Document < Nokogiri::XML::Node
-
-      def inspect_attributes
-          [:name, :children]
-      end
-
-    end
+module JustInform
+  def self.new
+    Parser.new
   end
 end
 

data/lib/just_inform/downloader.rb

@@ -1,27 +1,48 @@
 module JustInform
   class Downloader
+    require 'tempfile' unless defined?(Tempfile)
     require 'fileutils' unless defined?(FileUtils)
-    require 'open-uri' unless defined?(OpenURI)
+    require 'net/http' unless defined?(Net::HTTP)
     
     def self.get_latest
       if self.current_file?
-        puts "Using downloaded file"
-        latest = File.open(File.join 'data', self.current_filename)
+        puts "Using downloaded file at #{File.join('/tmp', self.current_filename)} and parsing with Nokogiri"
+
+        latest = File.open(File.join('/tmp', self.current_filename), 'r')
       else
-        puts 'Downloading file, this could take a minute...'
-        latest = File.open(File.join('data',self.current_filename), 'wb') {|file| file << open('http://www.reginfo.gov/public/do/PRAXML?type=inventory').read}
-        latest = File.open(File.join 'data', self.current_filename)
+        thread = download
+
+        print "%.2f%% Complete\r" % thread[:progress].to_f until thread.join 1
+        latest = File.open(File.join('/tmp', self.current_filename), 'r')
+      end
+    end
+        
+    def self.download
+      Thread.new do
+        thread = Thread.current
+        body = thread[:body] = []
+
+        file = File.open(File.join('/tmp',self.current_filename), 'w+b')
+
+        Net::HTTP.new('www.reginfo.gov').request_get('/public/do/PRAXML?type=inventory') do |response|
+          length = thread[:length] = response['Content-Length'].to_i
+          file_size_in_mb = response['Content-Length'].to_i/1024/1024
+          puts "Downloading ~#{file_size_in_mb} MB of XML data and parsing with Nokogiri. This may take a few minutes depending on your processor and internet connection"
+          
+          response.read_body do |fragment|
+            file.write(fragment)
+            thread[:done] = (thread[:done] || 0) + fragment.length
+            thread[:progress] = thread[:done].quo(length) * 100
+          end
+          file.close
+        end
       end
     end
     
     private
     
     def self.current_file?
-      dir = 'data'
-      unless File.directory?(dir)
-        FileUtils.mkdir_p(dir)
-      end
-      true if File.exists?(File.join dir, self.current_filename)
+      true if File.exists?(File.join('/tmp', self.current_filename))
     end
     
     def self.current_filename

data/lib/just_inform/parser.rb

@@ -1,13 +1,17 @@
 module JustInform
   class Parser
     require 'nokogiri' unless defined?(Nokogiri)
-    
+    require 'pry'
     attr_accessor :doc
     
     def initialize
       load
     end
     
+    def inspect
+      "#{self.class} - #{self.doc.children.first.name}"
+    end
+    
     # Show top 10 forms, PRA.top(sort_by_symbol, number_of_results)
     # parser.top(:burden,2) => [<Nokogiri::XML::Element>, <Nokogiri::XML::Element>]
     def top(limit=10, attrib_name=:burden_hours)
@@ -56,9 +60,8 @@ module JustInform
     
     # load XML data into Nokogiri and set @doc instance variable
     def load
-      puts 'Loading >50 MB of XML data and parsing with Nokogiri, this could take awhile (e.g. 2-3m)'
       data = Downloader.get_latest
-      @doc = Nokogiri::XML(data)
+      @doc = ::Nokogiri::XML(data)
     end
     
 

data/lib/just_inform/version.rb

@@ -1,3 +1,3 @@
 module JustInform
-  VERSION = "0.0.4"
+  VERSION = "0.0.5"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: just_inform
 version: !ruby/object:Gem::Version
-  version: 0.0.4
+  version: 0.0.5
 platform: ruby
 authors:
 - Justin Grevich