Completed project

.rspec

@@ -0,0 +1,3 @@
+--color
+--require spec_helper
+--format doc

Gemfile

@@ -0,0 +1,6 @@
+# Gemfile
+
+source 'https://rubygems.org'
+
+gem 'rspec', '~> 3.5.0'
+gem 'guard-rspec', '~> 4.7.3', require: false

Gemfile.lock

@@ -0,0 +1,65 @@
+GEM
+  remote: https://rubygems.org/
+  specs:
+    coderay (1.1.1)
+    diff-lcs (1.3)
+    ffi (1.9.18)
+    formatador (0.2.5)
+    guard (2.14.1)
+      formatador (>= 0.2.4)
+      listen (>= 2.7, < 4.0)
+      lumberjack (~> 1.0)
+      nenv (~> 0.1)
+      notiffany (~> 0.0)
+      pry (>= 0.9.12)
+      shellany (~> 0.0)
+      thor (>= 0.18.1)
+    guard-compat (1.2.1)
+    guard-rspec (4.7.3)
+      guard (~> 2.1)
+      guard-compat (~> 1.1)
+      rspec (>= 2.99.0, < 4.0)
+    listen (3.1.5)
+      rb-fsevent (~> 0.9, >= 0.9.4)
+      rb-inotify (~> 0.9, >= 0.9.7)
+      ruby_dep (~> 1.2)
+    lumberjack (1.0.11)
+    method_source (0.8.2)
+    nenv (0.3.0)
+    notiffany (0.1.1)
+      nenv (~> 0.1)
+      shellany (~> 0.0)
+    pry (0.10.4)
+      coderay (~> 1.1.0)
+      method_source (~> 0.8.1)
+      slop (~> 3.4)
+    rb-fsevent (0.9.8)
+    rb-inotify (0.9.8)
+      ffi (>= 0.5.0)
+    rspec (3.5.0)
+      rspec-core (~> 3.5.0)
+      rspec-expectations (~> 3.5.0)
+      rspec-mocks (~> 3.5.0)
+    rspec-core (3.5.4)
+      rspec-support (~> 3.5.0)
+    rspec-expectations (3.5.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.5.0)
+    rspec-mocks (3.5.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.5.0)
+    rspec-support (3.5.0)
+    ruby_dep (1.5.0)
+    shellany (0.0.1)
+    slop (3.6.0)
+    thor (0.19.4)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  guard-rspec (~> 4.7.3)
+  rspec (~> 3.5.0)
+
+BUNDLED WITH
+   1.14.4

Guardfile

@@ -0,0 +1,70 @@
+# A sample Guardfile
+# More info at https://github.com/guard/guard#readme
+
+## Uncomment and set this to only include directories you want to watch
+# directories %w(app lib config test spec features) \
+#  .select{|d| Dir.exists?(d) ? d : UI.warning("Directory #{d} does not exist")}
+
+## Note: if you are using the `directories` clause above and you are not
+## watching the project directory ('.'), then you will want to move
+## the Guardfile to a watched dir and symlink it back, e.g.
+#
+#  $ mkdir config
+#  $ mv Guardfile config/
+#  $ ln -s config/Guardfile .
+#
+# and, you'll have to watch "config/Guardfile" instead of "Guardfile"
+
+# Note: The cmd option is now required due to the increasing number of ways
+#       rspec may be run, below are examples of the most common uses.
+#  * bundler: 'bundle exec rspec'
+#  * bundler binstubs: 'bin/rspec'
+#  * spring: 'bin/rspec' (This will use spring if running and you have
+#                          installed the spring binstubs per the docs)
+#  * zeus: 'zeus rspec' (requires the server to be started separately)
+#  * 'just' rspec: 'rspec'
+
+guard :rspec, cmd: "bundle exec rspec" do
+  require "guard/rspec/dsl"
+  dsl = Guard::RSpec::Dsl.new(self)
+
+  # Feel free to open issues for suggestions and improvements
+
+  # RSpec files
+  rspec = dsl.rspec
+  watch(rspec.spec_helper) { rspec.spec_dir }
+  watch(rspec.spec_support) { rspec.spec_dir }
+  watch(rspec.spec_files)
+
+  # Ruby files
+  ruby = dsl.ruby
+  dsl.watch_spec_files_for(ruby.lib_files)
+
+  # Rails files
+  rails = dsl.rails(view_extensions: %w(erb haml slim))
+  dsl.watch_spec_files_for(rails.app_files)
+  dsl.watch_spec_files_for(rails.views)
+
+  watch(rails.controllers) do |m|
+    [
+      rspec.spec.call("routing/#{m[1]}_routing"),
+      rspec.spec.call("controllers/#{m[1]}_controller"),
+      rspec.spec.call("acceptance/#{m[1]}")
+    ]
+  end
+
+  # Rails config changes
+  watch(rails.spec_helper)     { rspec.spec_dir }
+  watch(rails.routes)          { "#{rspec.spec_dir}/routing" }
+  watch(rails.app_controller)  { "#{rspec.spec_dir}/controllers" }
+
+  # Capybara features specs
+  watch(rails.view_dirs)     { |m| rspec.spec.call("features/#{m[1]}") }
+  watch(rails.layouts)       { |m| rspec.spec.call("features/#{m[1]}") }
+
+  # Turnip features and steps
+  watch(%r{^spec/acceptance/(.+)\.feature$})
+  watch(%r{^spec/acceptance/steps/(.+)_steps\.rb$}) do |m|
+    Dir[File.join("**/#{m[1]}.feature")][0] || "spec/acceptance"
+  end
+end

README.md

@@ -2,3 +2,21 @@
 Like leaves on the wind
 
 [A data structures, algorithms, file I/O, ruby and regular expression (regex) project from the Viking Code School](http://www.vikingcodeschool.com)
+
+Worked on by [Roy Chen](https://github.com/roychen25)
+
+## Getting Started
+
+To run this program, fork and clone this repository.
+
+In the cloned directory, run this command:
+
+```
+ruby example.rb
+```
+
+The output includes:
+
+1. Printing information about the root node of the DOM tree created
+
+2. Rebuilding the DOM tree into its original format

example.rb

@@ -0,0 +1,15 @@
+if $0 == __FILE__
+  require_relative './lib/dom_reader'
+  require_relative './lib/node_renderer'
+  require_relative './lib/dom_rebuilder'
+
+  dom_reader = DOMReader.new
+
+  tree = dom_reader.build_tree('./test.html')
+
+  node_renderer = NodeRenderer.new(tree)
+  node_renderer.render
+
+  dom_rebuilder = DOMRebuilder.new(tree)
+  dom_rebuilder.print_tree
+end

lib/dom_reader.rb

@@ -0,0 +1,113 @@
+require_relative './dom_tree'
+
+class DOMReader
+  def initialize; end
+
+  def build_tree(filename)
+    # break file into tokens
+    tokens = tokenize_file(filename)
+
+    # exit if we have no tokens
+    return nil if tokens.empty?
+
+    # remove doctype declaration, if any
+    tokens = remove_doctype(tokens)
+
+    # initialize the tree
+    tree = DOMTree.new
+    current_node = tree.document
+
+    # set current depth of the tree
+    current_depth = 0
+
+    # create tree's root node if it does not exist yet
+    if tree.document.nil?
+      token = tokens.shift
+      tree.document = Node.new(token_type(token), token, current_depth, nil, [])
+      current_node = tree.document
+    end
+
+    # process remaining tokens
+    until tokens.empty?
+      token = tokens.shift
+      token_type = token_type(token)
+
+      node = Node.new(token_type, token, current_depth, current_node, [])
+      current_node.children << node
+
+      case token_type
+      when :open_tag
+        current_node = node
+        current_depth += 1
+      when :text
+        next
+      when :close_tag
+        current_node = current_node.parent unless current_node == tree.document
+        current_depth -= 1 unless current_depth == 0
+      when :unknown
+        # ignore unknown tag for now
+        next
+      end
+    end
+
+    tree
+  end
+
+  def read_file(filename)
+    raise "The file to be read does not exist." unless File.exist?(filename)
+
+    File.readlines(filename)
+  end
+
+  def tokenize_file(filename)
+    lines = read_file(filename)
+    tokens = []
+    lines.each { |line| tokens << tokenize(line) }
+    tokens.flatten!
+  end
+
+  def tokenize(text)
+    regex = /(<.+?>|[^<>]+|<\/\w+?>)/
+    tokens = text.scan(regex).flatten
+
+    tokens
+  end
+
+  def remove_doctype(tokens)
+    tokens.delete_at(0) if is_doctype_tag?(tokens[0])
+    tokens
+  end
+
+  def token_type(token)
+    return :unknown unless token.is_a?(String)
+
+    return :open_tag if is_open_tag?(token)
+
+    return :close_tag if is_close_tag?(token)
+
+    return :text if is_text?(token)
+
+    :unknown
+  end
+
+  def is_doctype_tag?(text)
+    regex = /<!doctype html>/i
+    !text.match(regex).nil?
+  end
+
+  def is_open_tag?(text)
+    # regex = /^<(\w+)>$/
+    regex = /^<(\w+)\s*(.+)*>$/
+    !text.match(regex).nil?
+  end
+
+  def is_close_tag?(text)
+    regex = /^<(\/\w+)>$/
+    !text.match(regex).nil?
+  end
+
+  def is_text?(text)
+    regex = /^[^<>\/]+$/
+    !text.match(regex).nil?
+  end
+end

lib/dom_rebuilder.rb

@@ -0,0 +1,30 @@
+class DOMRebuilder
+  attr_reader :tree
+
+  def initialize(tree = nil)
+    @tree = tree
+  end
+
+  # print out the DOM tree using DFS
+  def print_tree(start_node = nil)
+    output = ""
+
+    start_node = self.tree.document if start_node.nil?
+
+    stack = []
+    stack.push(start_node)
+
+    until stack.empty?
+      current_node = stack.pop
+
+      output << current_node.content
+
+      # it's important to reverse the child nodes first before
+      # pushing onto the stack, so that they'll be printed out
+      # in the right order
+      current_node.children.reverse.each { |child| stack.push(child) }
+    end
+
+    puts output
+  end
+end

lib/dom_tree.rb

@@ -0,0 +1,50 @@
+Node = Struct.new(:type, :content, :depth, :parent, :children)
+
+class DOMTree
+  attr_accessor :document
+
+  def initialize(document = nil)
+    # root node of tree
+    @document = document
+  end
+
+  # methods for traversing tree to be added here
+
+  def num_nodes_below(node = nil)
+    return 0 if node.nil? || node.children.empty?
+
+    count = 0
+    queue = []
+    node.children.each { |child| queue << child }
+
+    until queue.empty?
+      current_node = queue.shift
+      count += 1
+      current_node.children.each { |child| queue << child unless child.nil? }
+    end
+
+    count
+  end
+
+  def node_types_below(node = nil)
+    return {} if node.nil? || node.children.empty?
+
+    node_types = {}
+
+    queue = []
+    node.children.each { |child| queue << child }
+
+    until queue.empty?
+      current_node = queue.shift
+      current_node.children.each { |child| queue << child unless child.nil? }
+
+      if node_types.keys.include?(current_node.type)
+        node_types[current_node.type] += 1
+      else
+        node_types[current_node.type] = 1
+      end
+    end
+
+    node_types
+  end
+end