saxerator 0.1.2 → 0.1.4

data/README.md

@@ -45,6 +45,12 @@ parser.for_tag(:name).at_depth(2).each { |x| names_nested_under_document_root <<
 parser.for_tag(:name).within(:author).each { |x| author_names << x }
 ```
 
+Don't care about memory/streaming, you just want your xml in one big hash? Saxerator can do that too.
+
+```ruby
+parser.all # big, giant hash
+```
+
 Known Issues
 ------------
 * JRuby closes the file stream at the end of parsing, therefor to perform multiple operations

data/benchmark/benchmark.rb

@@ -9,10 +9,15 @@ if !File.exists?(file)
 end
 file = File.new(file)
 
-tag = ARGV.shift || :artist
-
-count = 0
+count = count2 = count3 = count4 = 0
 Benchmark.bm do |x|
-  x.report { Saxerator.parser(file).for_tag(tag).each { count = count + 1 } }
+  x.report('for_tag') { Saxerator.parser(file).for_tag(:artist).each { count = count + 1 } }
+  x.report('at_depth') { Saxerator.parser(file).at_depth(2).each { count2 = count2 + 1 } }
+  x.report('within') { Saxerator.parser(file).within(:artists).each { count3 = count3 + 1 } }
+  x.report('composite') { Saxerator.parser(file).for_tag(:name).within(:artist).at_depth(3).each { count4 = count4 + 1} }
 end
-puts "#{count} #{tag} elements parsed"
+
+puts "for_tag:   #{count} artist elements parsed"
+puts "at_depth:  #{count2} elements parsed"
+puts "within:    #{count3} artists children parsed"
+puts "composite: #{count4} names within artist nested 3 tags deep parsed"

data/benchmark/profile.rb

@@ -0,0 +1,21 @@
+$:.push File.expand_path('../../lib', __FILE__)
+require 'saxerator'
+require 'ruby-prof'
+
+file = ARGV.shift
+if !File.exists?(file)
+  puts "Cannot find file #{file}"
+  exit 1
+end
+file = File.new(file)
+
+count = 0
+RubyProf.start
+
+Saxerator.parser(file).for_tag(:artist).each { count = count + 1 }
+
+result = RubyProf.stop
+printer = RubyProf::FlatPrinter.new(result)
+printer.print(STDOUT)
+
+puts "for_tag:   #{count} artist elements parsed"

data/lib/saxerator.rb

@@ -1,13 +1,14 @@
 require 'nokogiri'
 
-require "saxerator/version"
-require 'saxerator/document'
+require 'saxerator/version'
+
+require 'saxerator/full_document'
+require 'saxerator/document_fragment'
 require 'saxerator/string_with_attributes'
 require 'saxerator/hash_with_attributes'
 require 'saxerator/xml_node'
 
 require 'saxerator/parser/accumulator'
-require 'saxerator/parser/document_latch'
 require 'saxerator/parser/element_name_latch'
 require 'saxerator/parser/depth_latch'
 require 'saxerator/parser/within_element_latch'
@@ -17,6 +18,6 @@ module Saxerator
   extend self
 
   def parser(xml)
-    Saxerator::Document.new(xml)
+    Saxerator::FullDocument.new(xml)
   end
 end

data/lib/saxerator/document_fragment.rb

@@ -0,0 +1,24 @@
+require 'saxerator/dsl'
+
+module Saxerator
+  class DocumentFragment
+    include Enumerable
+    include DSL
+
+    def initialize(source, config = nil, latches = [])
+      @source = source
+      @latches = latches
+      @config = config
+    end
+
+    def each(&block)
+      reader = Parser::LatchedAccumulator.new(@config, @latches, block)
+      parser = ::Nokogiri::XML::SAX::Parser.new(reader)
+
+      # Always have to start at the beginning of a File
+      @source.rewind if(@source.is_a?(File))
+
+      parser.parse(@source)
+    end
+  end
+end

data/lib/saxerator/dsl.rb

@@ -0,0 +1,15 @@
+module Saxerator
+  module DSL
+    def for_tag(tag)
+      DocumentFragment.new(@source, @config, @latches + [Parser::ElementNameLatch.new(tag.to_s)])
+    end
+
+    def at_depth(depth)
+      DocumentFragment.new(@source, @config, @latches + [Parser::DepthLatch.new(depth.to_i)])
+    end
+
+    def within(tag)
+      DocumentFragment.new(@source, @config, @latches + [Parser::WithinElementLatch.new(tag.to_s)])
+    end
+  end
+end

data/lib/saxerator/full_document.rb

@@ -0,0 +1,17 @@
+require 'saxerator/dsl'
+
+module Saxerator
+  class FullDocument
+    include DSL
+
+    def initialize(source, config = nil)
+      @source = source
+      @config = config
+      @latches = []
+    end
+
+    def all
+      DocumentFragment.new(@source, @config, @latches).first
+    end
+  end
+end

data/lib/saxerator/parser/depth_latch.rb

@@ -1,3 +1,5 @@
+require 'saxerator/parser/document_latch'
+
 module Saxerator
   module Parser
     class DepthLatch < DocumentLatch

data/lib/saxerator/parser/element_name_latch.rb

@@ -1,3 +1,5 @@
+require 'saxerator/parser/document_latch'
+
 module Saxerator
   module Parser
     class ElementNameLatch < DocumentLatch

data/lib/saxerator/parser/within_element_latch.rb

@@ -1,3 +1,5 @@
+require 'saxerator/parser/document_latch'
+
 module Saxerator
   module Parser
     class WithinElementLatch < DocumentLatch

data/lib/saxerator/version.rb

@@ -1,3 +1,3 @@
 module Saxerator
-  VERSION = "0.1.2"
+  VERSION = "0.1.4"
 end

data/spec/lib/saxerator_spec.rb

@@ -20,6 +20,10 @@ describe Saxerator do
         results.should == ['one', 'two', 'three']
       end
 
+      it "should allow you to parse an entire document" do
+        subject.all.should == {'blurb' => ['one', 'two', 'three']}
+      end
+
       context "and one non-blurb" do
         let(:xml) { "<blurbs><blurb>one</blurb><blurb>two</blurb><blurb>three</blurb><notablurb>four</notablurb></blurbs>" }
         it "should only parse the requested tag" do

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: saxerator
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.1.4
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-04-14 00:00:00.000000000 Z
+date: 2012-04-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -78,7 +78,9 @@ files:
 - .rvmrc
 - .gitignore
 - .travis.yml
-- lib/saxerator/document.rb
+- lib/saxerator/document_fragment.rb
+- lib/saxerator/dsl.rb
+- lib/saxerator/full_document.rb
 - lib/saxerator/hash_with_attributes.rb
 - lib/saxerator/parser/accumulator.rb
 - lib/saxerator/parser/depth_latch.rb
@@ -96,6 +98,7 @@ files:
 - spec/spec_helper.rb
 - benchmark/benchmark.rb
 - benchmark/generate_sample_file.rb
+- benchmark/profile.rb
 homepage: https://github.com/soulcutter/saxerator
 licenses:
 - MIT

data/lib/saxerator/document.rb

@@ -1,33 +0,0 @@
-module Saxerator
-  class Document
-    include Enumerable
-
-    def initialize(source, config = nil, latches = [])
-      @source = source
-      @latches = latches
-      @config = config
-    end
-
-    def for_tag(tag)
-      Document.new(@source, @config, @latches + [Parser::ElementNameLatch.new(tag.to_s)])
-    end
-
-    def at_depth(depth)
-      Document.new(@source, @config, @latches + [Parser::DepthLatch.new(depth.to_i)])
-    end
-
-    def within(tag)
-      Document.new(@source, @config, @latches + [Parser::WithinElementLatch.new(tag.to_s)])
-    end
-
-    def each(&block)
-      document = Parser::LatchedAccumulator.new(@config, @latches, block)
-      parser = ::Nokogiri::XML::SAX::Parser.new document
-
-      # Always have to start at the beginning of a File
-      @source.rewind if(@source.is_a?(File))
-
-      parser.parse(@source)
-    end
-  end
-end