bliss 0.0.7 → 0.0.9

data/lib/hash_extension.rb

@@ -20,4 +20,20 @@ class Hash
     chain.pop
     return self.value_at_chain(chain)
   end
+
+  def recurse(include_root=false, depth=[], &block)
+    self.each_pair { |k,v|
+      if v.is_a? Hash
+        if include_root
+          block.call(depth + [k], v)
+        end
+        depth.push k
+        v.recurse(include_root, depth, &block)
+      else
+        block.call(depth + [k], v)
+        #return "#{depth + [k]}: #{v.inspect}"
+      end
+    }
+    depth.pop
+  end
 end

data/spec.yml

@@ -0,0 +1,23 @@
+# TODO content_type = url
+---
+root:
+  ads:
+    tag_name_values: [ ads, jobs, job ]
+    ad:
+      id:
+        content_type: numeric
+      description:
+        tag_name_values: [ description, content ]
+        content_type: string
+      pictures:
+        tag_name_required: false
+        picture:
+          tag_name_required: false
+          url:
+            tag_name_required: true
+            content_type: string
+            content_format: /http:\/\/\w+/
+      url:
+        content_format: /http:\/\/\w+/
+      date:
+        content_type: date

data/spec/format_spec.rb

@@ -0,0 +1,63 @@
+require 'spec_helper'
+#require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
+#require_dependency 'xmlrpc/client'
+
+describe Bliss::Format do
+  before do
+    #@openx_banner = mock(OpenX::Services::Banner)
+    @format = Bliss::Format.new
+  end
+
+  describe '.constraints' do
+    #before do
+    #end
+    
+    it 'should do it' do
+      @format.constraints.size.should == 8
+    end
+  end
+
+  #describe '.traffic' do
+  #  before do
+  #    @openx_banner.stub(:statistics) { YAML.load_file('spec/fixtures/openx_banner_statistics.yml') }
+  #    OpenX::Services::Banner.should_receive(:find).with(1).and_return(@openx_banner)
+  #    @banner = Banner.new(1)
+  #  end
+
+  #  it 'should return statistics' do
+  #    @banner.traffic(Date.today, Date.today).should be_kind_of(Hash)
+  #  end
+  #end
+
+  # describe '.created' do
+  #   context 'when last creation is less than 2 days ago' do
+  #     before do
+  #       @site.stub(:last_creation_day_in_week) { Date.today - 1 }
+  #     end
+
+  #     it 'should be ok' do
+  #       @site_evaluation.created[@site.id]['created'][0].should == 'ok'
+  #     end
+  #   end
+
+  #   context 'when last creation is between 2 and 7 days ago' do
+  #     before do
+  #       @site.stub(:last_creation_day_in_week) { Date.today - 3 }
+  #     end
+
+  #     it 'should be a warning' do
+  #       @site_evaluation.created[@site.id]['created'][0].should == 'warning'
+  #     end
+  #   end
+
+  #   context 'when last creation is more than 7 days ago' do
+  #     before do
+  #       @site.stub(:last_creation_day_in_week) { Date.today - 8 }
+  #     end
+
+  #     it 'should be an alert' do
+  #       @site_evaluation.created[@site.id]['created'][0].should == 'alert'
+  #     end
+  #   end
+  # end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,16 @@
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'rspec'
+
+require 'bundler'
+Bundler.require(:default, :development)
+
+Dir["#{File.dirname(__FILE__)}/../lib/**/*.rb"].each {|f| require f}
+
+# Requires supporting files with custom matchers and macros, etc,
+# in ./support/ and its subdirectories.
+Dir["#{File.dirname(__FILE__)}/support/**/*.rb"].each {|f| require f}
+
+RSpec.configure do |config|
+  
+end

data/test.rb

@@ -1,5 +1,47 @@
 require 'rubygems'
 require 'bliss'
 
-p = Bliss::ParserMachine.new('dummy')
-p.parse
+p = Bliss::Parser.new('', 'output.xml')
+p.wait_tag_close('ad')
+#p.on_max_unhandled_bytes(20000) {
+#  puts 'Reached Max Unhandled Bytes'
+#  p.close
+#}
+
+@count = 0
+@makes = 0
+
+p.on_tag_close('ad') { |hash, depth|
+  if hash.has_key?('make')
+    @makes += 1
+  end
+  @count += 1
+
+  if @count == 600
+    p.close
+  end
+}
+
+=begin
+p.on_tag_close('ad') { |hash|
+  count += 1
+
+  dict = {"make"=>"name"}
+  only_in_dict = false
+  hash = hash.inject({}) { |h,v| key = dict.invert[v[0]]; key ||= v[0] unless only_in_dict; h[key] = v[1] if key; h }
+  
+  #puts hash.keys.inspect
+  if count == 100
+    p.close
+  end
+}
+=end
+
+begin
+  p.parse
+rescue Bliss::EncodingError
+  puts "Encoding Error!"
+end
+
+puts @count
+puts @makes

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: bliss
 version: !ruby/object:Gem::Version
-  version: 0.0.7
+  version: 0.0.9
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-03-21 00:00:00.000000000 Z
+date: 2012-06-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
-  requirement: &10543860 !ruby/object:Gem::Requirement
+  requirement: &16900020 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,10 +21,10 @@ dependencies:
         version: 1.5.2
   type: :runtime
   prerelease: false
-  version_requirements: *10543860
+  version_requirements: *16900020
 - !ruby/object:Gem::Dependency
   name: eventmachine
-  requirement: &10543160 !ruby/object:Gem::Requirement
+  requirement: &16899520 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -32,10 +32,10 @@ dependencies:
         version: 1.0.0.beta.4
   type: :runtime
   prerelease: false
-  version_requirements: *10543160
+  version_requirements: *16899520
 - !ruby/object:Gem::Dependency
   name: em-http-request
-  requirement: &10542680 !ruby/object:Gem::Requirement
+  requirement: &16898800 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -43,32 +43,32 @@ dependencies:
         version: 1.0.2
   type: :runtime
   prerelease: false
-  version_requirements: *10542680
+  version_requirements: *16898800
 - !ruby/object:Gem::Dependency
-  name: shoulda
-  requirement: &10542100 !ruby/object:Gem::Requirement
+  name: rspec
+  requirement: &16898260 !ruby/object:Gem::Requirement
     none: false
     requirements:
-    - - ! '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 2.8.0
   type: :development
   prerelease: false
-  version_requirements: *10542100
+  version_requirements: *16898260
 - !ruby/object:Gem::Dependency
   name: bundler
-  requirement: &10541460 !ruby/object:Gem::Requirement
+  requirement: &16897260 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 1.0.0
+        version: 1.1.3
   type: :development
   prerelease: false
-  version_requirements: *10541460
+  version_requirements: *16897260
 - !ruby/object:Gem::Dependency
   name: jeweler
-  requirement: &10540780 !ruby/object:Gem::Requirement
+  requirement: &16895760 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -76,10 +76,10 @@ dependencies:
         version: 1.6.4
   type: :development
   prerelease: false
-  version_requirements: *10540780
+  version_requirements: *16895760
 - !ruby/object:Gem::Dependency
   name: simplecov
-  requirement: &10549040 !ruby/object:Gem::Requirement
+  requirement: &16911540 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -87,7 +87,7 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *10549040
+  version_requirements: *16911540
 description: streamed xml parsing tool
 email: krakatoa1987@gmail.com
 executables: []
@@ -97,6 +97,7 @@ extra_rdoc_files:
 - README.rdoc
 files:
 - .document
+- CHANGELOG.rdoc
 - Gemfile
 - Gemfile.lock
 - LICENSE.txt
@@ -104,13 +105,20 @@ files:
 - Rakefile
 - VERSION
 - bliss.gemspec
+- complete_test.rb
+- gzip_support.rb
 - hash.rb
 - http-machine.rb
 - lib/bliss.rb
+- lib/bliss/constraint.rb
+- lib/bliss/encoding_error.rb
+- lib/bliss/format.rb
 - lib/bliss/parser.rb
 - lib/bliss/parser_machine.rb
-- lib/bliss/sax_parser.rb
 - lib/hash_extension.rb
+- spec.yml
+- spec/format_spec.rb
+- spec/spec_helper.rb
 - test.rb
 - test/helper.rb
 - test/test_bliss.rb
@@ -129,7 +137,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -3966009882958368597
+      hash: 3727479071019105598
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -138,7 +146,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.15
+rubygems_version: 1.8.10
 signing_key: 
 specification_version: 3
 summary: streamed xml parsing tool

data/lib/bliss/sax_parser.rb

@@ -1,122 +0,0 @@
-module Bliss
-  class SaxParser < Nokogiri::XML::SAX::Document
-    def initialize
-      @depth = []
-      # @settings = {} # downcased
-
-      @root = nil
-      @nodes = {}
-      @current_node = {}
-
-      @on_root = nil
-      @on_tag_open = {}
-      @on_tag_close = {}
-
-      @closed = false
-
-    end
-
-    def on_root(&block)
-      @on_root = block
-    end
-
-    def on_tag_open(element, block)
-      @on_tag_open.merge!({element => block})
-    end
-
-    def on_tag_close(element, block)
-      @on_tag_close.merge!({element => block})
-    end
-
-    def close
-      @closed = true
-    end
-
-    def is_closed?
-      @closed
-    end
-
-    def start_element(element, attributes)
-      # element_transformation
-
-      if @root == nil
-        @root = element
-        if @on_root.is_a? Proc
-          @on_root.call(@root)
-        end
-      end
-
-      @depth.push(element) if @depth.last != element
-      
-      if @on_tag_open.has_key? element
-        @on_tag_open[element].call(@depth)
-      end
-
-      current = @nodes.pair_at_chain(@depth)
-
-      value_at = @nodes.value_at_chain(@depth)
-      
-      if current.is_a? Hash
-        if value_at.is_a? NilClass
-          current[element] = {}
-        elsif value_at.is_a? Hash
-          if current[element].is_a? Array
-            current[element].concat [{}]
-          else
-            current[element] = [current[element], {}]
-            #current = @nodes.pair_at_chain(@depth)
-          end
-        elsif value_at.is_a? Array
-          #puts @depth.inspect
-          #puts current[element].inspect
-          #puts current[element].inspect
-        end
-      elsif current.is_a? Array
-      end
-
-      @current_content = ''
-    end
-
-    def characters(string)
-      concat_content(string)
-    end
-
-    def cdata_block(string)
-      concat_content(string)
-    end
-
-    def end_element(element, attributes=[])
-      # element_transformation
-
-      current = @nodes.pair_at_chain(@depth)
-      value_at = @nodes.value_at_chain(@depth)
-
-      if value_at.is_a? Hash
-        current[element] = @current_content if @current_content.size > 0
-      elsif value_at.is_a? NilClass
-        if current.is_a? Array
-          current = current.last
-          current[element] = @current_content if @current_content.size > 0
-        end
-      end
-      @current_content = ''
-      
-      if @on_tag_close.has_key? element
-        @on_tag_close[element].call(value_at)
-      end
-
-      @depth.pop if @depth.last == element
-    end
-
-    def concat_content(string)
-      string.strip!
-      if string
-        @current_content << string
-      end
-    end
-
-    def end_document
-      puts @nodes.inspect
-    end
-  end
-end