saxerator 0.0.3 → 0.1.0

data/.travis.yml

@@ -0,0 +1,14 @@
+language: ruby
+bundler_args: --without coverage benchmark
+rvm:
+  - 1.8.7
+  - 1.9.2
+  - 1.9.3
+  - jruby-18mode
+  - jruby-19mode
+  - rbx-18mode
+  - rbx-19mode
+matrix:
+  allow_failures:
+    - rvm: jruby-18mode
+    - rvm: jruby-19mode

data/Gemfile

@@ -2,3 +2,11 @@ source "http://rubygems.org"
 
 # Specify your gem's dependencies in saxerator.gemspec
 gemspec
+
+group :benchmark do
+  gem 'ipsum'
+end
+
+group :coverage do
+  gem 'simplecov'
+end

data/README.md

@@ -1,4 +1,4 @@
-Saxerator
+Saxerator [![Build Status](https://secure.travis-ci.org/soulcutter/saxerator.png?branch=master)](http://travis-ci.org/soulcutter/saxerator)
 =========
 
 Saxerator is a SAX-based xml-to-hash parser designed for parsing very large files into manageable chunks. Rather than
@@ -10,6 +10,12 @@ Each xml chunk is parsed into a JSON-like Ruby Hash structure for consumption.
 
 Examples
 --------
+You can parse any valid xml in 3 simple steps.
+
+1. Initialize the parser
+1. Tell it which tag you care about
+1. Perform your work in an 'each' block, or using any [Enumerable](http://apidock.com/ruby/Enumerable)
+method
 
 ```ruby
 parser = Saxerator.parser(File.new("rss.xml"))
@@ -24,25 +30,24 @@ end
 puts "First title: #{parser.for_tag(:title).first}"
 ```
 
-```ruby
-# attributes are stored as a part of the Hash or String object they relate to
+Attributes are stored as a part of the Hash or String object they relate to
 
-# author behaves like a String here, but also responds to .attributes
+```ruby
+# author is a String here, but also responds to .attributes
 primary_authors = parser.for_tag(:author).select { |author| author.attributes['type'] == 'primary' }
-puts "Primary authors: #{primary_authors.join(", ")}"
-
-# item behaves like a Hash, but also responds to .attributes
-favorite_items = parser.for_tag(:item).select { |item| item.attributes['favorite'] }
-puts "First favorite title: #{favorite_items[0]['title']}"
 ```
 
-Compatibility
--------------
-Known compatible rubies:
+You can combine predicates to isolate just the tags you want.
 
-* MRI 1.9.3-p125
-* MRI 1.9.2-p318
-* JRuby 1.6.7 (with JRUBY_OPTS=--1.9)
+```ruby
+parser.for_tag(:name).each { |x| all_the_names_in_a_document << x }
+parser.for_tag(:name).at_depth(2).each { |x| names_nested_under_document_root << x }
+```
+
+Known Issues
+------------
+* JRuby closes the file stream at the end of parsing, therefor to perform multiple operations
+  which parse a file you will need to instantiate a new parser with a new File object.
 
 FAQ
 ---
@@ -64,4 +69,7 @@ Why not DOM parsing?
 
 ### Acknowledgements ###
 Saxerator was inspired by [Nori](https://github.com/rubiii/nori) and [Gregory Brown](http://majesticseacreature.com/)'s
-[Practicing Ruby](http://practicingruby.com/)
+[Practicing Ruby](http://practicingruby.com/)
+
+#### Legal Stuff ####
+Copyright © Bradley Schaefer. MIT License (see LICENSE file).

data/Rakefile

@@ -1,4 +1,5 @@
-require "bundler/gem_tasks"
+require 'rake/dsl_definition'
+require 'bundler/gem_tasks'
 require 'rspec/core/rake_task'
 
 RSpec::Core::RakeTask.new(:spec)

data/lib/saxerator.rb

@@ -1,16 +1,21 @@
-require "saxerator/version"
-require 'saxerator/configuration'
+require 'nokogiri'
 
+require "saxerator/version"
+require 'saxerator/document'
 require 'saxerator/string_with_attributes'
 require 'saxerator/hash_with_attributes'
-
 require 'saxerator/xml_node'
-require 'saxerator/parser/nokogiri'
+
+require 'saxerator/parser/accumulator'
+require 'saxerator/parser/document_latch'
+require 'saxerator/parser/element_name_latch'
+require 'saxerator/parser/depth_latch'
+require 'saxerator/parser/latched_accumulator'
 
 module Saxerator
   extend self
 
   def parser(xml)
-    Saxerator::Configuration.new(xml)
+    Saxerator::Document.new(xml)
   end
 end

data/lib/saxerator/document.rb

@@ -0,0 +1,29 @@
+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 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

data/lib/saxerator/parser/accumulator.rb

@@ -0,0 +1,30 @@
+module Saxerator
+  module Parser
+    class Accumulator < ::Nokogiri::XML::SAX::Document
+      def initialize(config, block)
+        @stack = []
+        @config = config
+        @block = block
+      end
+
+      def start_element(name, attrs = [])
+        @stack.push XmlNode.new(@config, name, Hash[*attrs.flatten])
+      end
+
+      def end_element(_)
+        if @stack.size > 1
+          last = @stack.pop
+          @stack.last.add_node last
+        else
+          @block.call(@stack.pop.to_hash)
+        end
+      end
+
+      def characters(string)
+        @stack.last.add_node(string) unless string.strip.length == 0
+      end
+
+      alias cdata_block characters
+    end
+  end
+end

data/lib/saxerator/parser/depth_latch.rb

@@ -0,0 +1,21 @@
+module Saxerator
+  module Parser
+    class DepthLatch < DocumentLatch
+      def initialize(depth)
+        @depth = depth
+        @actual_depth = 0
+      end
+
+      def start_element name, attrs = []
+        @actual_depth += 1
+        if @actual_depth == @depth
+          open
+        end
+      end
+
+      def end_element name
+        @actual_depth -= 1
+      end
+    end
+  end
+end

data/lib/saxerator/parser/document_latch.rb

@@ -0,0 +1,21 @@
+module Saxerator
+  module Parser
+    class DocumentLatch < ::Nokogiri::XML::SAX::Document
+      def open
+        @open = true
+      end
+
+      def close
+        @open = false
+      end
+
+      def open?
+        @open
+      end
+
+      def reset
+        close
+      end
+    end
+  end
+end

data/lib/saxerator/parser/element_name_latch.rb

@@ -0,0 +1,15 @@
+module Saxerator
+  module Parser
+    class ElementNameLatch < DocumentLatch
+      def initialize(name)
+        @name = name
+      end
+
+      def start_element(name, _)
+        if name == @name
+          open
+        end
+      end
+    end
+  end
+end

data/lib/saxerator/parser/latched_accumulator.rb

@@ -0,0 +1,75 @@
+module Saxerator
+  module Parser
+    class LatchedAccumulator < ::Nokogiri::XML::SAX::Document
+      def initialize(config, latches, block)
+        @latches = latches
+        block_and_reset = Proc.new do |x|
+          block.call(x)
+          reset_latches
+        end
+        @accumulator = Accumulator.new(config, block_and_reset)
+      end
+
+      def reset_latches
+        @latches.each(&:reset)
+      end
+
+      def check_latches_and_passthrough(method, *args)
+        @latches.each { |latch| latch.send(method, *args) }
+        if @latches.all?(&:open?)
+          @accumulator.send(method, *args)
+        else
+          reset_latches
+        end
+      end
+
+      def xmldecl version, encoding, standalone
+        check_latches_and_passthrough(:xmldecl, version, encoding, standalone)
+      end
+
+      def start_document
+        check_latches_and_passthrough(:start_document)
+      end
+
+      def end_document
+        check_latches_and_passthrough(:end_document)
+      end
+
+      def start_element name, attrs = []
+        check_latches_and_passthrough(:start_element, name, attrs)
+      end
+
+      def end_element name
+        check_latches_and_passthrough(:end_element, name)
+      end
+
+      def start_element_namespace name, attrs = [], prefix = nil, uri = nil, ns = []
+        check_latches_and_passthrough(:start_element_namespace, name, attrs, prefix, uri, ns)
+      end
+
+      def end_element_namespace name, prefix = nil, uri = nil
+        check_latches_and_passthrough(:end_element_namespace, name, prefix, uri)
+      end
+
+      def characters string
+        check_latches_and_passthrough(:characters, string)
+      end
+
+      def comment string
+        check_latches_and_passthrough(:comment, string)
+      end
+
+      def warning string
+        check_latches_and_passthrough(:warning, string)
+      end
+
+      def error string
+        check_latches_and_passthrough(:error, string)
+      end
+
+      def cdata_block string
+        check_latches_and_passthrough(:cdata_block, string)
+      end
+    end
+  end
+end

data/lib/saxerator/version.rb

@@ -1,3 +1,3 @@
 module Saxerator
-  VERSION = "0.0.3"
+  VERSION = "0.1.0"
 end

data/lib/saxerator/xml_node.rb

@@ -1,23 +1,23 @@
 module Saxerator
   class XmlNode
-    attr_accessor :name, :attributes, :children, :type
+    attr_reader :name
 
     def initialize(config, name, attributes)
       @config = config
-      self.name = name
-      self.attributes = attributes
-      self.children = []
+      @name = name
+      @attributes = attributes
+      @children = []
       @text = false
     end
 
     def add_node(node)
       @text = true if node.is_a? String
-      children << node
+      @children << node
     end
 
     def to_s
-      string = StringWithAttributes.new(@text ? children.join : children.to_s)
-      string.attributes = attributes
+      string = StringWithAttributes.new(@children.join)
+      string.attributes = @attributes
       string
     end
 
@@ -26,7 +26,7 @@ module Saxerator
         to_s
       else
         out = HashWithAttributes.new
-        out.attributes = attributes
+        out.attributes = @attributes
 
         @children.each do |child|
           name = child.name

data/saxerator.gemspec

@@ -1,7 +1,6 @@
 # -*- encoding: utf-8 -*-
 $:.push File.expand_path('../lib', __FILE__)
 require 'saxerator/version'
-require 'rake' # for FileList
 
 Gem::Specification.new do |s|
   s.name        = 'saxerator'
@@ -20,26 +19,25 @@ Gem::Specification.new do |s|
 
   s.rubyforge_project = 'saxerator'
 
-  s.files = FileList[
+  s.files = [
     'LICENSE',
     'README.md',
     'saxerator.gemspec',
-    'lib/**/*.rb',
-    'spec/**/*.*',
-    'benchmark/**/*.rb',
     'Gemfile',
     'Rakefile',
     '.rvmrc',
-    '.gitignore'
-  ]
-  s.test_files    = FileList['spec/**/*.*']
+    '.gitignore',
+    '.travis.yml'
+  ] +
+    Dir.glob('lib/**/*.rb') +
+    Dir.glob('spec/**/*.*') +
+    Dir.glob('benchmark/**/*.rb')
+  s.test_files    = Dir.glob('spec/**/*.*')
   s.executables   = []
   s.require_paths = ['lib']
 
-  s.add_runtime_dependency 'nokogiri'
+  s.add_runtime_dependency 'nokogiri', '>= 1.4.0'
 
   s.add_development_dependency 'rake'
   s.add_development_dependency 'rspec'
-  s.add_development_dependency 'simplecov'
-  s.add_development_dependency 'ipsum'
 end

data/spec/lib/saxerator_spec.rb

@@ -32,6 +32,43 @@ describe Saxerator do
       end
     end
 
+    context "with a string with an element at multiple depths" do
+      let(:xml) do
+        <<-eos
+          <books>
+            <book>
+              <name>How to eat an airplane</name>
+              <author>
+                <name>Leviticus Alabaster</name>
+                <name>Eunice Diesel</name>
+              </author>
+            </book>
+            <book>
+              <name>To wallop a horse in the face</name>
+              <author>
+                <name>Jeanne Clarewood</name>
+              </author>
+            </book>
+          </books>
+        eos
+      end
+
+      it "should only parse the requested tag depth" do
+        results = []
+        subject.at_depth(3).each { |x| results << x }
+        results.should == [
+          'How to eat an airplane', {'name' => ['Leviticus Alabaster', 'Eunice Diesel']},
+          'To wallop a horse in the face', {'name' => 'Jeanne Clarewood'}
+        ]
+      end
+
+      it "should only parse the requested tag depth and tag" do
+        results = []
+        subject.at_depth(3).for_tag(:name).each { |x| results << x }
+        results.should == ['How to eat an airplane', 'To wallop a horse in the face']
+      end
+    end
+
     context "with a file with blurbs" do
       let(:xml) { fixture_file('flat_blurbs.xml') }
 
@@ -47,7 +84,6 @@ describe Saxerator do
         subject.for_tag(:blurb).first.should == 'one'
         subject.for_tag(:blurb).first.should == 'one'
       end
-
     end
 
     context "with a file with nested elements" do

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: saxerator
 version: !ruby/object:Gem::Version
-  version: 0.0.3
+  version: 0.1.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-04-12 00:00:00.000000000 Z
+date: 2012-04-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -18,7 +18,7 @@ dependencies:
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 1.4.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -26,7 +26,7 @@ dependencies:
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 1.4.0
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -59,38 +59,6 @@ dependencies:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: simplecov
-  requirement: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: ipsum
-  requirement: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
 description: ! "    Saxerator is a SAX-based xml-to-hash parser designed for parsing
   very large files into manageable chunks. Rather than\n    dealing directly with
   SAX callback methods, Saxerator gives you Enumerable access to chunks of an xml
@@ -105,9 +73,18 @@ files:
 - LICENSE
 - README.md
 - saxerator.gemspec
-- lib/saxerator/configuration.rb
+- Gemfile
+- Rakefile
+- .rvmrc
+- .gitignore
+- .travis.yml
+- lib/saxerator/document.rb
 - lib/saxerator/hash_with_attributes.rb
-- lib/saxerator/parser/nokogiri.rb
+- lib/saxerator/parser/accumulator.rb
+- lib/saxerator/parser/depth_latch.rb
+- lib/saxerator/parser/document_latch.rb
+- lib/saxerator/parser/element_name_latch.rb
+- lib/saxerator/parser/latched_accumulator.rb
 - lib/saxerator/string_with_attributes.rb
 - lib/saxerator/version.rb
 - lib/saxerator/xml_node.rb
@@ -118,10 +95,6 @@ files:
 - spec/spec_helper.rb
 - benchmark/benchmark.rb
 - benchmark/generate_sample_file.rb
-- Gemfile
-- Rakefile
-- .rvmrc
-- .gitignore
 homepage: https://github.com/soulcutter/saxerator
 licenses:
 - MIT

data/lib/saxerator/configuration.rb

@@ -1,13 +0,0 @@
-module Saxerator
-  class Configuration
-    attr_reader :source
-
-    def initialize(source)
-      @source = source
-    end
-
-    def for_tag(tag)
-      Saxerator::Parser::Nokogiri.new(self, source, tag.to_s)
-    end
-  end
-end

data/lib/saxerator/parser/nokogiri.rb

@@ -1,58 +0,0 @@
-require 'nokogiri'
-
-module Saxerator
-  module Parser
-    class Nokogiri
-      include Enumerable
-
-      def initialize(config, source, tag)
-        @config = config
-        @source = source
-        @tag = tag
-      end
-
-      def each(&block)
-        document = Document.new(@config, @tag, 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
-
-      class Document < ::Nokogiri::XML::SAX::Document
-        attr_accessor :stack
-
-        def initialize(config, tag, block)
-          @config = config
-          @tag = tag
-          @stack = []
-          @block = block
-        end
-
-        def start_element(name, attrs = [])
-          if stack.size > 0 || name == @tag
-            stack.push XmlNode.new(@config, name, Hash[*attrs.flatten])
-          end
-        end
-
-        def end_element(name)
-          if stack.size > 1
-            last = stack.pop
-            stack.last.add_node last
-          elsif stack.size == 1
-            @block.yield(stack.pop.to_hash)
-          end
-        end
-
-        def characters(string)
-          stack.last.add_node(string) unless string.strip.length == 0 || stack.empty?
-        end
-
-        alias cdata_block characters
-
-      end
-    end
-  end
-end