guileless 0.1.0

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    YTk5NzVjNzdhY2JhMGVlNGQzYjY3OWQyYjdiY2VjNTJhM2Y5YTI0NQ==
+  data.tar.gz: !binary |-
+    YTcxMzkzNGIwODYxZTkzZWRiMDdkY2Q4ZTY3NWMwYTZiMjY5MjFjOQ==
+SHA512:
+  metadata.gz: !binary |-
+    MTY5N2UwYzg3YTQ0Yzk4OGJlMDQwZWQ1ZGM3NGY4YjE1MjBjNTRhZDBiODM3
+    YmIwMWI1MzY4ZGRkMDE5ZDE4ZTQwNDgwYWFlZDFiMTVlZThiZTk1ODhjOTUw
+    NTdkZmJlMjY4MTJhMDE5NjdkYTM0MzExZTVhMGEzZWMyNTQzNDQ=
+  data.tar.gz: !binary |-
+    YzgwYWY1ZWY2M2U2OTBmYTkyNTI5NTUwMzk0MDAwMTNmM2Q2ZDViOThjNDlj
+    YTU3YjNiYWJiODAxNjk5ZjBhZDVhZjg1NjgxMDhjZjAxYmQ5MDZkZjVlN2Q4
+    NDIxYmRmMTY3MjIyZjVmZWIxN2RiMGQwYmRmZDQwMDg5ODA3Nzk=

data/.gitignore

@@ -0,0 +1 @@
+*.gem

data/.rspec

@@ -0,0 +1,2 @@
+--color
+--format progress

data/.travis.yml

@@ -0,0 +1,6 @@
+language: ruby
+rvm:
+  - 1.9.3
+  - 2.0.0
+script:
+  - bundle exec rspec spec

data/Gemfile

@@ -0,0 +1,3 @@
+source 'https://rubygems.org'
+
+gem 'rspec'

data/Gemfile.lock

@@ -0,0 +1,17 @@
+GEM
+  specs:
+    diff-lcs (1.2.4)
+    rspec (2.14.1)
+      rspec-core (~> 2.14.0)
+      rspec-expectations (~> 2.14.0)
+      rspec-mocks (~> 2.14.0)
+    rspec-core (2.14.5)
+    rspec-expectations (2.14.3)
+      diff-lcs (>= 1.1.3, < 2.0)
+    rspec-mocks (2.14.3)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  rspec

data/LICENSE

@@ -0,0 +1,19 @@
+Copyright (c) 2013 Inge Jørgensen
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/README.md

@@ -0,0 +1,42 @@
+# Guileless [![Build Status](https://travis-ci.org/elektronaut/guileless.png)](https://travis-ci.org/elektronaut/guileless) [![Code Climate](https://codeclimate.com/github/elektronaut/guileless.png)](https://codeclimate.com/github/elektronaut/guileless)
+
+Guileless is a naive HTML preprocessor. It does three things:
+
+1. Single line breaks are converted to `<br>`
+2. Several consecutive line breaks are treated as paragraphs and wrapped in `<p>`
+3. Converts stray `<`, `>`, and `&`s to HTML entities.
+
+Why is this more useful than, say, Rails' built in `simple_format`?
+
+Well, it's actually a real (if simplistic) HTML parser. It understands nested
+tags, and will happily format text nodes inside `div`s and `blockquote`s.
+
+However, it does **NOT** do any sanitation on the input.
+
+## Usage
+
+```ruby
+Guileless.format("<div>foo</div>") # => "<div><p>foo</p></div>"
+```
+
+## License
+
+Copyright (c) 2013 Inge Jørgensen
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/guileless.gemspec

@@ -0,0 +1,24 @@
+# encoding: utf-8
+
+$:.push File.expand_path("../lib", __FILE__)
+require "guileless/version"
+
+Gem::Specification.new do |s|
+  s.name        = 'guileless'
+  s.version     = Guileless::VERSION
+  s.date        = '2013-10-20'
+  s.summary     = "Naive HTML preprocessor"
+  s.description = "Naive HTML preprocessor"
+  s.authors     = ["Inge Jørgensen"]
+  s.email       = 'inge@elektronaut.no'
+  s.files       = ["lib/hola.rb"]
+  s.homepage    = 'http://github.com/elektronaut/guileless'
+  s.license     = 'MIT'
+  s.required_ruby_version = Gem::Requirement.new(">= 1.9.2")
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+
+end

data/lib/guileless.rb

@@ -0,0 +1,15 @@
+require "guileless/input_stream"
+require "guileless/output_buffer"
+require "guileless/parse_methods"
+require "guileless/state_machine"
+require "guileless/tag_library"
+require "guileless/parser"
+require "guileless/version"
+
+module Guileless
+  class << self
+    def format(str)
+      Parser.new(str).to_html
+    end
+  end
+end

data/lib/guileless/input_stream.rb

@@ -0,0 +1,43 @@
+module Guileless
+  class InputStream
+    def initialize(input)
+      @buffer = input.chars.to_a
+    end
+
+    def reinject(char)
+      @buffer.unshift(char)
+    end
+
+    def empty?
+      @buffer.length == 0
+    end
+
+    def fetch
+      @buffer.shift
+    end
+
+    def discard(count=1)
+      count.times { @buffer.shift }
+    end
+
+    def strip_whitespace
+      @buffer.shift while @buffer.first == "\n"
+    end
+
+    def peek?(patterns)
+      match = false
+      Array(patterns).each do |pattern|
+        if pattern.kind_of?(Regexp)
+          match = true if self.to_s =~ pattern
+        elsif pattern.kind_of?(String)
+          match = true if self.to_s[0...(pattern.length)] == pattern
+        end
+      end
+      match
+    end
+
+    def to_s
+      @buffer.join
+    end
+  end
+end

data/lib/guileless/output_buffer.rb

@@ -0,0 +1,33 @@
+module Guileless
+  class OutputBuffer
+    def initialize
+      @output_buffer = []
+      @output = []
+    end
+
+    def add(str)
+      str = str.chars.to_a if str.kind_of?(String)
+      @output_buffer += Array(str)
+      str
+    end
+
+    def buffered?
+      @output_buffer.length > 0
+    end
+
+    def flush
+      @output += @output_buffer
+      @output_buffer = []
+    end
+
+    def wrap(prefix, postfix)
+      prefix = prefix.chars.to_a if prefix.kind_of?(String)
+      postfix = postfix.chars.to_a if postfix.kind_of?(String)
+      @output_buffer = Array(prefix) + @output_buffer + Array(postfix)
+    end
+
+    def to_s
+      @output.join
+    end
+  end
+end

data/lib/guileless/parse_methods.rb

@@ -0,0 +1,158 @@
+module Guileless
+  module ParseMethods
+
+    def parse_attribute_name(char)
+      case
+      when char !=~ /[\w\-]/
+        stream.reinject char
+        [false, :tag]
+      when char == "=" && stream.peek?("'")
+        stream.discard
+        ["='", :attribute_value_single_quote]
+      when char == "=" && stream.peek?("\"")
+        stream.discard
+        ["=\"", :attribute_value_double_quote]
+      when char == "="
+        [char, :attribute_value]
+      end
+    end
+
+    def parse_attribute_value(char)
+      case
+      when char !=~ /[\w\d]/
+        stream.reinject char
+        [false, :tag]
+      end
+    end
+
+    def parse_attribute_value_single_quote(char)
+      case
+      when char == "'"
+        [char, :tag]
+      end
+    end
+
+    def parse_attribute_value_double_quote(char)
+      case
+      when char == "\""
+        [char, :tag]
+      end
+    end
+
+    def parse_comment(char)
+      case
+      when char == "-" && stream.peek?("->")
+        stream.discard(2)
+        ["-->", :text]
+      end
+    end
+
+    def parse_tag(char)
+      case
+      when char =~ /\w/
+        [char, :attribute_name]
+      when char == ">"
+        [char, :text]
+      end
+    end
+
+    def parse_closing_tag(char)
+      case
+      when char == ">"
+        [char, :text]
+      end
+    end
+
+    def parse_tag_name(char)
+      case
+      when char =~ /\w/
+        @tag_name += char
+        char
+      else
+        stream.reinject char
+        [false, :tag]
+      end
+    end
+
+    def parse_closing_tag_name(char)
+      case
+      when char =~ /\w/
+        @tag_name += char
+        char
+      else
+        stream.reinject char
+        [false, :closing_tag]
+      end
+    end
+
+    def parse_left_angled_quote(char)
+      case
+
+      # Comment
+      when stream.peek?("!--")
+        stream.discard(3)
+        ["<!--", :comment]
+
+      # Opening block tag
+      when stream.peek?(block_level_tags)
+        flush_buffer
+        [char, :tag_name]
+
+      # Opening tag
+      when stream.peek?(html_tags)
+        [char, :tag_name]
+
+      # Closing block level tag
+      when stream.peek?(closing(block_level_tags))
+        flush_buffer
+        stream.discard
+        ["</", :closing_tag_name]
+
+      # Closing tag
+      when stream.peek?(closing(html_tags))
+        stream.discard
+        ["</", :closing_tag_name]
+
+      # Escape left angled bracket
+      else
+        @char_count += 4
+        "&lt;"
+      end
+    end
+
+    def parse_text(char)
+      case
+
+      # Comment
+      when char == "<"
+        parse_left_angled_quote(char)
+
+      # Escape right angled bracket
+      when char == ">"
+        @char_count += 4
+        "&gt;"
+
+      # Escape ampersands
+      when char == "&" && !stream.peek?("amp;")
+        @char_count += 5
+        "&amp;"
+
+      # Paragraph break
+      when char == "\n" && stream.peek?("\n")
+        flush_buffer
+        stream.strip_whitespace
+        false
+
+      # Line break
+      when char == "\n"
+        "<br>"
+
+      when char !=~ /\s/
+        @char_count += 1
+        char
+
+      end
+    end
+
+  end
+end

data/lib/guileless/parser.rb

@@ -0,0 +1,96 @@
+module Guileless
+  class Parser < Guileless::StateMachine
+    include Guileless::TagLibrary
+    include Guileless::ParseMethods
+
+    attr_reader :input, :stream, :tag_stack, :buffer, :tag_name, :char_count
+
+    before_transition :reset_tag_name,   [:tag_name, :closing_tag_name]
+    before_transition :add_tag_to_stack, :text, from: [:tag]
+    before_transition :close_tag,        :text, from: [:closing_tag]
+    before_transition :finish_tag,       :text, from: [:tag, :closing_tag]
+    before_transition :flush_buffer,     :end
+
+    def initialize(input)
+      @input = input
+    end
+
+    def to_html
+      parse!
+      buffer.to_s
+    end
+
+    def parse!
+      reset!
+      read while !stream.empty?
+      transition(:end)
+    end
+
+    def read
+      char = stream.fetch
+      value, next_state = Array(self.send("parse_#{state}".to_sym, char))
+
+      if value === nil
+        buffer.add char
+      elsif value
+        buffer.add value
+      end
+
+      transition(next_state) if next_state
+    end
+
+    def wrap_in_paragraph?
+      state == :text &&
+      char_count > 0 &&
+      buffer.buffered? &&
+      (!last_block_level_tag || paragraph_container_tags.include?(last_block_level_tag))
+    end
+
+    def flush_buffer
+      if wrap_in_paragraph?
+        if buffer.buffered? && char_count > 0
+          buffer.wrap("<p>", "</p>")
+        end
+      end
+      @char_count = 0
+      buffer.flush
+    end
+
+    def finish_tag
+      if block_level_tags.include?(tag_name)
+        flush_buffer
+      end
+    end
+
+    def add_tag_to_stack
+      @tag_stack << tag_name
+    end
+
+    def close_tag
+      unwind_tag_stack(tag_name)
+    end
+
+    def unwind_tag_stack(tag)
+      if tag_stack.include?(tag)
+        last_tag = tag_stack.pop while last_tag != tag
+      end
+    end
+
+    def last_block_level_tag
+      tag_stack.reverse.select{|t| block_level_tags.include?(t) }.first
+    end
+
+    def reset_tag_name
+      @tag_name = ""
+    end
+
+    def reset!
+      @char_count = 0
+      @buffer = Guileless::OutputBuffer.new
+      @stream = Guileless::InputStream.new(input)
+      @tag_stack = []
+      reset_tag_name
+      @state = :text
+    end
+  end
+end

data/lib/guileless/state_machine.rb

@@ -0,0 +1,33 @@
+module Guileless
+  class StateMachine
+    class NoStateError < StandardError; end
+
+    class << self
+      def transitions
+        @transitions ||= []
+      end
+
+      def before_transition(name, states, options={})
+        transitions << [name, Array(states), options]
+      end
+    end
+
+    def state
+      raise NoStateError unless @state
+      @state
+    end
+
+    def transition(new_state)
+      self.class.transitions.each do |callback, callback_states, options|
+        if callback_states.include?(new_state)
+          if !options[:from] || options[:from].include?(state)
+            self.send("#{callback}".to_sym)
+          end
+        end
+      end
+
+      @state = new_state
+    end
+
+  end
+end

data/lib/guileless/tag_library.rb

@@ -0,0 +1,33 @@
+module Guileless
+  module TagLibrary
+    def closing(tags)
+      tags.map{|t| "/#{t}" }
+    end
+
+    def html_tags
+      %w{
+        a abbr address area article aside audio b base bdi bdo blockquote
+        body br button canvas caption cite code col colgroup data datalist
+        dd del details dfn div dl dt em embed fieldset figcaption figure
+        footer form h1 h2 h3 h4 h5 h6 head header hr html i iframe img
+        input ins kbd keygen label legend li link main map mark math menu
+        menuitem meta meter nav noscript object ol optgroup option output
+        p param pre progress q rp rt ruby s samp section select small source
+        span strong style sub summary svg table tbody td textarea tfoot th
+        thead time title tr track u ul var video wbr
+      }
+    end
+
+    def block_level_tags
+      %w{
+        address article aside audio blockquote canvas dd div dl fieldset
+        figcaption figure footer form h1 h2 h3 h4 h5 h6 header hgroup hr
+        noscript ol output p pre section table tfoot ul video
+      }
+    end
+
+    def paragraph_container_tags
+      %w{article aside blockquote div footer header}
+    end
+  end
+end

data/lib/guileless/version.rb

@@ -0,0 +1,5 @@
+module Guileless
+  unless Guileless.const_defined?('VERSION')
+    VERSION = "0.1.0"
+  end
+end

data/spec/guileless_spec.rb

@@ -0,0 +1,69 @@
+require 'spec_helper'
+
+describe Guileless do
+  describe ".format" do
+    it "allows comments" do
+      Guileless.format("foo <!-- <b>comment</b> --> bar").should == "<p>foo <!-- <b>comment</b> --> bar</p>"
+    end
+
+    it "doesn't wrap comments" do
+      Guileless.format("<!-- <b>comment</b> -->").should == "<!-- <b>comment</b> -->"
+    end
+
+    it "doesn't wrap empty block tags" do
+      Guileless.format("<div></div>").should == "<div></div>"
+    end
+
+    it "ignores empty tags" do
+      Guileless.format("<b></b>").should == "<b></b>"
+    end
+
+    it "converts single breaks to <br>" do
+      Guileless.format("foo\nbar").should == "<p>foo<br>bar</p>"
+    end
+
+    it "converts double breaks to <br>" do
+      Guileless.format("foo\n\nbar").should == "<p>foo</p><p>bar</p>"
+    end
+
+    it "escapes left angled brackets" do
+      Guileless.format("<").should == "<p>&lt;</p>"
+    end
+
+    it "escapes right angled brackets" do
+      Guileless.format(">").should == "<p>&gt;</p>"
+    end
+
+    it "escapes ampersands" do
+      Guileless.format("&").should == "<p>&amp;</p>"
+    end
+
+    it "doesn't escape already escaped ampersands" do
+      Guileless.format("&amp;").should == "<p>&amp;</p>"
+    end
+
+    it "understands empty attributes" do
+      Guileless.format("<blockquote data-foo>stuff</blockquote>").should == "<blockquote data-foo><p>stuff</p></blockquote>"
+    end
+
+    it "understands single quoted attributes" do
+      Guileless.format("<blockquote data-foo='bar'>stuff</blockquote>").should == "<blockquote data-foo='bar'><p>stuff</p></blockquote>"
+    end
+
+    it "understands double quoted attributes" do
+      Guileless.format("<blockquote data-foo=\"bar\">stuff</blockquote>").should == "<blockquote data-foo=\"bar\"><p>stuff</p></blockquote>"
+    end
+
+    it "ignores non-closed tags" do
+      Guileless.format("<blockquote><b>stuff</blockquote>").should == "<blockquote><p><b>stuff</p></blockquote>"
+    end
+
+    it "nests tags properly" do
+      Guileless.format("foo<blockquote>bar</blockquote>baz").should == "<p>foo</p><blockquote><p>bar</p></blockquote><p>baz</p>"
+    end
+
+    it "doesn't wrap existing paragraphs" do
+      Guileless.format("<p>foo</p>").should == "<p>foo</p>"
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,20 @@
+# This file was generated by the `rspec --init` command. Conventionally, all
+# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
+# Require this file using `require "spec_helper"` to ensure that it is only
+# loaded once.
+#
+# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
+
+require_relative '../lib/guileless'
+
+RSpec.configure do |config|
+  config.treat_symbols_as_metadata_keys_with_true_values = true
+  config.run_all_when_everything_filtered = true
+  config.filter_run :focus
+
+  # Run specs in random order to surface order dependencies. If you find an
+  # order dependency and want to debug it, you can fix the order by providing
+  # the seed, which is printed after each run.
+  #     --seed 1234
+  config.order = 'random'
+end

metadata

@@ -0,0 +1,64 @@
+--- !ruby/object:Gem::Specification
+name: guileless
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Inge Jørgensen
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-10-20 00:00:00.000000000 Z
+dependencies: []
+description: Naive HTML preprocessor
+email: inge@elektronaut.no
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- .rspec
+- .travis.yml
+- Gemfile
+- Gemfile.lock
+- LICENSE
+- README.md
+- guileless.gemspec
+- lib/guileless.rb
+- lib/guileless/input_stream.rb
+- lib/guileless/output_buffer.rb
+- lib/guileless/parse_methods.rb
+- lib/guileless/parser.rb
+- lib/guileless/state_machine.rb
+- lib/guileless/tag_library.rb
+- lib/guileless/version.rb
+- spec/guileless_spec.rb
+- spec/spec_helper.rb
+homepage: http://github.com/elektronaut/guileless
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: 1.9.2
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.1.4
+signing_key: 
+specification_version: 4
+summary: Naive HTML preprocessor
+test_files:
+- spec/guileless_spec.rb
+- spec/spec_helper.rb
+has_rdoc: