saxerator 0.1.4 → 0.2.0

data/.gitignore

@@ -5,4 +5,4 @@ pkg/*
 .DS_Store
 .idea/
 coverage/
-
+.rvmrc

data/.travis.yml

@@ -1,5 +1,5 @@
 language: ruby
-bundler_args: --without coverage benchmark
+bundler_args: --without coverage
 rvm:
   - 1.8.7
   - 1.9.2

data/Gemfile

@@ -3,10 +3,6 @@ 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

@@ -40,9 +40,26 @@ primary_authors = parser.for_tag(:author).select { |author| author.attributes['t
 You can combine predicates to isolate just the tags you want.
 
 ```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 }
-parser.for_tag(:name).within(:author).each { |x| author_names << x }
+require 'saxerator'
+
+parser = Saxerator.parser(bookshelf_xml)
+
+# You can chain predicates
+parser.for_tag(:name).within(:book).each { |book_name| puts book_name }
+
+# You can re-use intermediary predicates
+bookshelf_contents = parser.within(:bookshelf)
+
+books = bookshelf_contents.for_tag(:book)
+magazines = bookshelf_contents.for_tag(:magazine)
+
+books.each do |book|
+  # Some processing on a book
+end
+
+magazines.each do |magazine|
+  # Do some work with a magazine
+end
 ```
 
 Don't care about memory/streaming, you just want your xml in one big hash? Saxerator can do that too.
@@ -75,7 +92,7 @@ Why not DOM parsing?
   > document is very large, this can be an important consideration.
 
 ### Acknowledgements ###
-Saxerator was inspired by [Nori](https://github.com/rubiii/nori) and [Gregory Brown](http://majesticseacreature.com/)'s
+Saxerator was inspired by - but not affiliated with - [nori](https://github.com/rubiii/nori) and [Gregory Brown](http://majesticseacreature.com/)'s
 [Practicing Ruby](http://practicingruby.com/)
 
 #### Legal Stuff ####

data/benchmark/generate_sample_file.rb

@@ -1,5 +1,4 @@
-require 'ipsum'
-
+#!/usr/bin/env ruby
 filename = ARGV.shift
 
 unless filename
@@ -14,7 +13,7 @@ element = <<-eos
   <artist id="%i">
     <name>Rock Star %i</name>
     <active>true</active>
-    <description>%s</description>
+    <description>...</description>
     <genre>Rock,Metal</genre>
   </artist>
 eos
@@ -25,7 +24,7 @@ File.open(filename, 'w') do |f|
   f.puts '<?xml version="1.0" encoding="UTF-8"?>'
   f.puts '<artists>'
   num_records.times do |count|
-    f.puts(element % [count, count, 5.sentences])
+    f.puts(element % [count, count])
   end
   f.puts '</artists>'
 end

data/lib/saxerator.rb

@@ -1,5 +1,3 @@
-require 'nokogiri'
-
 require 'saxerator/version'
 
 require 'saxerator/full_document'
@@ -13,6 +11,7 @@ require 'saxerator/parser/element_name_latch'
 require 'saxerator/parser/depth_latch'
 require 'saxerator/parser/within_element_latch'
 require 'saxerator/parser/latched_accumulator'
+require 'saxerator/parser/child_of_latch'
 
 module Saxerator
   extend self

data/lib/saxerator/document_fragment.rb

@@ -1,4 +1,5 @@
 require 'saxerator/dsl'
+require 'nokogiri'
 
 module Saxerator
   class DocumentFragment
@@ -13,10 +14,10 @@ module Saxerator
 
     def each(&block)
       reader = Parser::LatchedAccumulator.new(@config, @latches, block)
-      parser = ::Nokogiri::XML::SAX::Parser.new(reader)
+      parser = Nokogiri::XML::SAX::Parser.new(reader)
 
       # Always have to start at the beginning of a File
-      @source.rewind if(@source.is_a?(File))
+      @source.rewind if @source.respond_to?(:rewind)
 
       parser.parse(@source)
     end

data/lib/saxerator/dsl.rb

@@ -1,15 +1,24 @@
 module Saxerator
   module DSL
     def for_tag(tag)
-      DocumentFragment.new(@source, @config, @latches + [Parser::ElementNameLatch.new(tag.to_s)])
+      specify(Parser::ElementNameLatch.new(tag.to_s))
     end
 
     def at_depth(depth)
-      DocumentFragment.new(@source, @config, @latches + [Parser::DepthLatch.new(depth.to_i)])
+      specify(Parser::DepthLatch.new(depth.to_i))
     end
 
     def within(tag)
-      DocumentFragment.new(@source, @config, @latches + [Parser::WithinElementLatch.new(tag.to_s)])
+      specify(Parser::WithinElementLatch.new(tag.to_s))
+    end
+
+    def child_of(tag)
+      specify(Parser::ChildOfLatch.new(tag.to_s))
+    end
+
+    private
+    def specify(predicate)
+      DocumentFragment.new(@source, @config, @latches + [predicate])
     end
   end
 end

data/lib/saxerator/parser/accumulator.rb

@@ -1,6 +1,8 @@
+require 'nokogiri'
+
 module Saxerator
   module Parser
-    class Accumulator < ::Nokogiri::XML::SAX::Document
+    class Accumulator < Nokogiri::XML::SAX::Document
       def initialize(config, block)
         @stack = []
         @config = config
@@ -25,6 +27,10 @@ module Saxerator
       end
 
       alias cdata_block characters
+
+      def accumulating?
+        @stack.size > 0
+      end
     end
   end
 end

data/lib/saxerator/parser/child_of_latch.rb

@@ -0,0 +1,47 @@
+require 'saxerator/parser/document_latch'
+
+module Saxerator
+  module Parser
+    class ChildOfLatch < DocumentLatch
+      def initialize(name)
+        @name = name
+        @depths = []
+        @depth_within_element = 0
+      end
+
+      def start_element name, _
+        if depth_within_element > 0
+          increment_depth(1)
+          resolve_open_status
+        end
+        if @name == name
+          @depths.push 1
+        end
+      end
+
+      def end_element _
+        if depth_within_element > 0
+          increment_depth(-1)
+          @depths.pop if @depths.last == 0
+          resolve_open_status
+        end
+      end
+
+      def increment_depth(amount)
+        @depths.map! { |depth| depth + amount }
+      end
+
+      def depth_within_element
+        @depths.size > 0 ? @depths.last : 0
+      end
+
+      def resolve_open_status
+        if depth_within_element == 2
+          open
+        else
+          close
+        end
+      end
+    end
+  end
+end

data/lib/saxerator/parser/depth_latch.rb

@@ -4,19 +4,20 @@ module Saxerator
   module Parser
     class DepthLatch < DocumentLatch
       def initialize(depth)
-        @depth = depth
-        @actual_depth = 0
+        @target_depth = depth
+        @current_depth = 0
       end
 
       def start_element(_, __)
-        @actual_depth += 1
-        if @actual_depth == @depth
-          open
-        end
+        @current_depth += 1
       end
 
       def end_element(_)
-        @actual_depth -= 1
+        @current_depth -= 1
+      end
+
+      def open?
+        @current_depth == @target_depth
       end
     end
   end

data/lib/saxerator/parser/document_latch.rb

@@ -1,6 +1,8 @@
+require 'nokogiri'
+
 module Saxerator
   module Parser
-    class DocumentLatch < ::Nokogiri::XML::SAX::Document
+    class DocumentLatch < Nokogiri::XML::SAX::Document
       def open
         @open = true
       end
@@ -12,10 +14,6 @@ module Saxerator
       def open?
         @open
       end
-
-      def reset
-        close
-      end
     end
   end
 end

data/lib/saxerator/parser/element_name_latch.rb

@@ -7,10 +7,12 @@ module Saxerator
         @name = name
       end
 
-      def start_element(name, _)
-        if name == @name
-          open
-        end
+      def start_element name, _
+        name == @name ? open : close
+      end
+
+      def end_element name
+        close if name == @name
       end
     end
   end

data/lib/saxerator/parser/latched_accumulator.rb

@@ -1,25 +1,18 @@
+require 'nokogiri'
+
 module Saxerator
   module Parser
-    class LatchedAccumulator < ::Nokogiri::XML::SAX::Document
+    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 { |latch| latch.reset }
+        @accumulator = Accumulator.new(config, block)
       end
 
       def check_latches_and_passthrough(method, *args)
         @latches.each { |latch| latch.send(method, *args) }
-        if @latches.all? { |latch| latch.open? }
+        if @accumulator.accumulating? ||
+            @latches.all? { |latch| latch.open? }
           @accumulator.send(method, *args)
-        else
-          reset_latches
         end
       end
 

data/lib/saxerator/parser/within_element_latch.rb

@@ -5,28 +5,22 @@ module Saxerator
     class WithinElementLatch < DocumentLatch
       def initialize(name)
         @name = name
-        @inner_depth = 0
+        @depth_within_element = 0
       end
 
       def start_element name, _
-        if @inner_depth == 0
-          if name == @name
-            @inner_depth += 1
-          end
-        else
-          open if @inner_depth == 1
-          @inner_depth += 1
+        if name == @name || @depth_within_element > 0
+          @depth_within_element += 1
+          open if @depth_within_element == 2
         end
       end
 
       def end_element _
-        if @inner_depth > 0
-          @inner_depth -= 1
-          close if @inner_depth == 0
+        if @depth_within_element > 0
+          @depth_within_element -= 1
+          close if @depth_within_element == 1
         end
       end
-
-      def reset; end
     end
   end
 end

data/lib/saxerator/version.rb

@@ -1,3 +1,3 @@
 module Saxerator
-  VERSION = "0.1.4"
+  VERSION = "0.2.0"
 end

data/lib/saxerator/xml_node.rb

@@ -31,6 +31,7 @@ module Saxerator
         @children.each do |child|
           name = child.name
           element = child.to_hash
+
           if out[name]
             if !out[name].is_a?(Array)
               out[name] = [out[name]]
@@ -40,6 +41,7 @@ module Saxerator
             out[name] = element
           end
         end
+
         out
       end
     end

data/saxerator.gemspec

@@ -25,7 +25,6 @@ Gem::Specification.new do |s|
     'saxerator.gemspec',
     'Gemfile',
     'Rakefile',
-    '.rvmrc',
     '.gitignore',
     '.travis.yml'
   ] +

data/spec/lib/saxerator_spec.rb

@@ -11,28 +11,28 @@ describe Saxerator do
     subject { parser }
     let(:parser) { Saxerator.parser(xml) }
 
-    context "with a string with blurbs" do
-      let(:xml) { "<blurbs><blurb>one</blurb><blurb>two</blurb><blurb>three</blurb></blurbs>" }
+    context "with a string with blurbs and one non-blurb" do
+      let(:xml) do
+        <<-eos
+          <blurbs>
+            <blurb>one</blurb>
+            <blurb>two</blurb>
+            <blurb>three</blurb>
+            <notablurb>four</notablurb>
+          </blurbs>
+        eos
+      end
 
       it "should parse simple strings" do
-        results = []
-        subject.for_tag(:blurb).each { |x| results << x }
-        results.should == ['one', 'two', 'three']
+        subject.for_tag(:blurb).inject([], :<<).should == ['one', 'two', 'three']
       end
 
-      it "should allow you to parse an entire document" do
-        subject.all.should == {'blurb' => ['one', 'two', 'three']}
+      it "should only parse the requested tag" do
+        subject.for_tag(:notablurb).inject([], :<<).should == ['four']
       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
-          results = []
-          subject.for_tag(:blurb).each { |x| results << x }
-          results.should == ['one', 'two', 'three']
-          subject.for_tag(:notablurb).each { |x| results << x }
-          results.should == ['one', 'two', 'three', 'four']
-        end
+      it "should allow you to parse an entire document" do
+        subject.all.should == {'blurb' => ['one', 'two', 'three'], 'notablurb' => 'four'}
       end
     end
 
@@ -64,9 +64,7 @@ describe Saxerator do
       end
 
       it "should only parse the requested tag depth" do
-        results = []
-        subject.at_depth(3).each { |x| results << x }
-        results.should == [
+        subject.at_depth(3).inject([], :<<).should == [
           'How to eat an airplane', { 'name' => ['Leviticus Alabaster', 'Eunice Diesel'] },
           'To wallop a horse in the face', { 'name' => 'Jeanne Clarewood' },
           'Is our children learning?', { 'name' => 'Hazel Nutt' }
@@ -74,21 +72,58 @@ describe Saxerator do
       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', 'Is our children learning?']
+        subject.at_depth(3).for_tag(:name).inject([], :<<).should == [
+            'How to eat an airplane',
+            'To wallop a horse in the face',
+            'Is our children learning?'
+        ]
       end
 
       it "should only parse tags nested inside the specified tag" do
-        results = []
-        subject.within(:article).each { |x| results << x }
-        results.should == ['Is our children learning?', { 'name' => 'Hazel Nutt' }]
+        subject.within(:article).inject([], :<<).should == [
+            'Is our children learning?',
+            { 'name' => 'Hazel Nutt' }
+        ]
+      end
+
+      it "should combine #for_tag and #within to parse the specified elements" do
+        subject.for_tag(:name).within(:article).inject([], :<<).should == [
+            'Is our children learning?',
+            'Hazel Nutt'
+        ]
+      end
+    end
+
+    context "with a grand child" do
+      let(:xml) do
+         <<-eos
+        <root>
+          <children>
+            <name>Rudy McMannis</name>
+            <children>
+              <name>Tom McMannis</name>
+            </children>
+            <grandchildren>
+              <name>Mildred Marston</name>
+            </grandchildren>
+            <name>Anne Welsh</name>
+          </children>
+        </root>
+        eos
       end
 
-      it "should only parse specified tags nested inside a specified tag" do
-        results = []
-        subject.for_tag(:name).within(:article).each { |x| results << x }
-        results.should == ['Is our children learning?', 'Hazel Nutt'  ]
+      it "should only parse children of the specified tag" do
+        subject.child_of(:grandchildren).inject([], :<<).should == [
+            'Mildred Marston'
+        ]
+      end
+
+      it "should combine #for_tag and #child_of" do
+        subject.for_tag(:name).child_of(:children).inject([], :<<).should == [
+            'Rudy McMannis',
+            'Tom McMannis',
+            'Anne Welsh'
+        ]
       end
     end
 
@@ -96,9 +131,7 @@ describe Saxerator do
       let(:xml) { fixture_file('flat_blurbs.xml') }
 
       it "should parse simple strings" do
-        results = []
-        subject.for_tag(:blurb).each { |x| results << x }
-        results.should == ['one', 'two', 'three']
+        subject.for_tag(:blurb).inject([], :<<).should == ['one', 'two', 'three']
       end
 
       it "should allow multiple operations on the same parser" do

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: saxerator
 version: !ruby/object:Gem::Version
-  version: 0.1.4
+  version: 0.2.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-04-17 00:00:00.000000000 Z
+date: 2012-08-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -75,7 +75,6 @@ files:
 - saxerator.gemspec
 - Gemfile
 - Rakefile
-- .rvmrc
 - .gitignore
 - .travis.yml
 - lib/saxerator/document_fragment.rb
@@ -83,6 +82,7 @@ files:
 - lib/saxerator/full_document.rb
 - lib/saxerator/hash_with_attributes.rb
 - lib/saxerator/parser/accumulator.rb
+- lib/saxerator/parser/child_of_latch.rb
 - lib/saxerator/parser/depth_latch.rb
 - lib/saxerator/parser/document_latch.rb
 - lib/saxerator/parser/element_name_latch.rb
@@ -98,7 +98,6 @@ files:
 - spec/spec_helper.rb
 - benchmark/benchmark.rb
 - benchmark/generate_sample_file.rb
-- benchmark/profile.rb
 homepage: https://github.com/soulcutter/saxerator
 licenses:
 - MIT
@@ -120,7 +119,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: saxerator
-rubygems_version: 1.8.21
+rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
 summary: A SAX-based XML-to-hash parser for parsing large files into manageable chunks

data/.rvmrc

@@ -1,38 +0,0 @@
-#!/usr/bin/env bash
-
-# This is an RVM Project .rvmrc file, used to automatically load the ruby
-# development environment upon cd'ing into the directory
-
-# First we specify our desired <ruby>[@<gemset>], the @gemset name is optional.
-environment_id="1.9.3@saxerator"
-
-#
-# First we attempt to load the desired environment directly from the environment
-# file. This is very fast and efficient compared to running through the entire
-# CLI and selector. If you want feedback on which environment was used then
-# insert the word 'use' after --create as this triggers verbose mode.
-#
-if [[ -d "${rvm_path:-$HOME/.rvm}/environments" \
-  && -s "${rvm_path:-$HOME/.rvm}/environments/$environment_id" ]]
-then
-  \. "${rvm_path:-$HOME/.rvm}/environments/$environment_id"
-
-  if [[ -s "${rvm_path:-$HOME/.rvm}/hooks/after_use" ]]
-  then
-    . "${rvm_path:-$HOME/.rvm}/hooks/after_use"
-  fi
-else
-  # If the environment file has not yet been created, use the RVM CLI to select.
-  if ! rvm --create  "$environment_id"
-  then
-    echo "Failed to create RVM environment '${environment_id}'."
-    return 1
-  fi
-fi
-
-if [[ $- == *i* ]] # check for interactive shells
-then
-    echo "Using: $(tput setaf 2)$GEM_HOME$(tput sgr0)" # show the user the ruby and gemset they are using in green
-else 
-	echo "Using: $GEM_HOME" # don't use colors in interactive shells
-fi

data/benchmark/profile.rb

@@ -1,21 +0,0 @@
-$:.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"