rosetta-ruby 0.0.0

data/lib/rosetta/tokens/link.rb

@@ -0,0 +1,66 @@
+# frozen_string_literal: true
+
+require './lib/rosetta/tokens/basic_token'
+
+# Handles logic for Link tokens
+class Link < BasicToken
+  def self.matches?(text)
+    # Naive check for link.
+    return false unless text.start_with?('[')
+
+    closing_bracket_index = text.index(']')
+    return false if closing_bracket_index.nil?
+
+    return false if text[closing_bracket_index + 1] != '('
+
+    text[closing_bracket_index + 1..].include?(')')
+  end
+
+  def self.consume(text)
+    closing_index = text.rindex(')')
+    source = text[0..closing_index]
+
+    new(source)
+  end
+
+  def to_s
+    "<Token type='#{type}' value='#{value}' url='#{url}'>"
+  end
+
+  def node_representation
+    "<#{type} value='#{value}' url='#{url}'>"
+  end
+
+  def type
+    :LINK
+  end
+
+  def value
+    final_bracket_index = url_beginning_index - 1
+
+    # We want the value inside brackets, and should exclude the brackets themselves.
+    @source_text[1...final_bracket_index]
+  end
+
+  def url
+    # We want the value inside the parenthesis, and should exclude the the parens themselves.
+    @source_text[url_beginning_index + 1...-1]
+  end
+
+  private
+
+  def url_beginning_index
+    open_bracket_count = 0
+
+    @url_beginning_index ||= @source_text.each_char.with_index do |character, index|
+      case character
+      when '['
+        open_bracket_count += 1
+      when ']'
+        open_bracket_count -= 1
+      end
+
+      return index + 1 if open_bracket_count.zero?
+    end
+  end
+end

data/lib/rosetta/tokens/new_line.rb

@@ -0,0 +1,20 @@
+# frozen_string_literal: true
+
+require './lib/rosetta/tokens/basic_token'
+
+# Handles logic for New Line tokens
+class NewLine < BasicToken
+  def self.matches?(text)
+    text == ''
+  end
+
+  def initialize; end
+
+  def type
+    :NEW_LINE
+  end
+
+  def value
+    nil
+  end
+end

data/lib/rosetta/tokens/numbered_list.rb

@@ -0,0 +1,10 @@
+# frozen_string_literal: true
+
+require './lib/rosetta/tokens/block_token'
+
+# Handles logic for Paragraph tokens
+class NumberedList < BlockToken
+  def type
+    :NUMBERED_LIST
+  end
+end

data/lib/rosetta/tokens/numbered_list_item.rb

@@ -0,0 +1,25 @@
+# frozen_string_literal: true
+
+require './lib/rosetta/tokens/basic_token'
+
+# Handles logic for Header tokens
+class NumberedListItem < BasicToken
+  def self.matches?(text)
+    return false unless number?(text[0])
+
+    text[1..2] == '. '
+  end
+
+  def type
+    :NUMBERED_LIST_ITEM
+  end
+
+  def value
+    # If the code reaches here we know the first 3 chars are the list delimiter.
+    @source_text[3..-1]
+  end
+
+  def self.number?(object)
+    object.to_s == object.to_i.to_s
+  end
+end

data/lib/rosetta/tokens/paragraph.rb

@@ -0,0 +1,10 @@
+# frozen_string_literal: true
+
+require './lib/rosetta/tokens/block_token'
+
+# Handles logic for Paragraph tokens
+class Paragraph < BlockToken
+  def type
+    :PARAGRAPH
+  end
+end

data/lib/rosetta/tokens/quote.rb

@@ -0,0 +1,24 @@
+# frozen_string_literal: true
+
+require './lib/rosetta/tokens/basic_token'
+
+# Handles logic for Header tokens
+class Quote < BasicToken
+  def self.matches?(text)
+    text.start_with?('> ')
+  end
+
+  def type
+    :QUOTE
+  end
+
+  def value
+    @value ||= extract_value_from_text
+  end
+
+  private
+
+  def extract_value_from_text
+    @source_text.delete_prefix('> ')
+  end
+end

data/lib/rosetta/tokens/shared/inline_tokens.rb

@@ -0,0 +1,30 @@
+# frozen_string_literal: true
+
+module Shared
+  # Handles logic for class methods for Inline Tokens.
+  module InlineTokens
+    def delimiter_length
+      delimiter_token.length
+    end
+
+    def matches?(text)
+      text.start_with?(delimiter_token) && valid_delimiter?(text[delimiter_length..])
+    end
+
+    def valid_delimiter?(text)
+      delimiter_index = text.index(delimiter_token)
+      !delimiter_index.nil?
+    end
+
+    def consume(text)
+      delimiter_index = text[delimiter_length..].index(delimiter_token) + delimiter_length
+
+      source = text[0..delimiter_index]
+      new(source)
+    end
+
+    def delimiter_token
+      const_get('DELIMITER_TOKEN')
+    end
+  end
+end

data/lib/rosetta/tokens/strikethrough.rb

@@ -0,0 +1,29 @@
+# frozen_string_literal: true
+
+require './lib/rosetta/tokens/basic_token'
+require './lib/rosetta/tokens/shared/inline_tokens'
+
+# Handles logic for Strikethrough tokens
+class Strikethrough < BasicToken
+  extend Shared::InlineTokens
+
+  DELIMITER_TOKEN = '~~'
+
+  def self.consume(raw_text)
+    # Add an extra 1 to offset the extra delimiter length (because strikethrough).
+    delimiter_index = raw_text[delimiter_length..].index(DELIMITER_TOKEN) + delimiter_length + 1
+
+    source = raw_text[0..delimiter_index]
+    new(source)
+  end
+
+  def type
+    :STRIKETHROUGH
+  end
+
+  def value
+    return DELIMITER_TOKEN * 2 if @source_text == DELIMITER_TOKEN * 2
+
+    @source_text[self.class.delimiter_length...-self.class.delimiter_length]
+  end
+end

data/lib/rosetta/tokens/text.rb

@@ -0,0 +1,14 @@
+# frozen_string_literal: true
+
+require './lib/rosetta/tokens/basic_token'
+
+# Handles logic for Text tokens.
+class Text < BasicToken
+  def type
+    :TEXT
+  end
+
+  def value
+    @source_text
+  end
+end

data/lib/rosetta-ruby.rb

@@ -0,0 +1,15 @@
+# frozen_string_literal: true
+
+require './lib/rosetta/abstract_syntax_tree'
+require './lib/rosetta/formatters/html/html_writer'
+require './lib/rosetta/services/input_scanner'
+
+# Entry point for rosetta-ruby gem.
+class Rosetta
+  def self.markdown_to_html(markdown_source)
+    source_tokens = InputScanner.call(markdown_source)
+    abstract_syntax_tree = AbstractSyntaxTree.new(source_tokens)
+
+    HTMLWriter.call(abstract_syntax_tree.token_tree)
+  end
+end

data/main.rb

@@ -0,0 +1,21 @@
+# frozen_string_literal: true
+
+require './lib/rosetta/abstract_syntax_tree'
+require './lib/rosetta/formatters/html/html_writer'
+require './lib/rosetta/services/input_scanner'
+
+# We ignore the issue of large file sizes for now.
+# TODO: Optimise file reading, i.e. stream input for large source files.
+
+puts 'Correct usage: ruby main.rb <source_filename>' if ARGV.length != 1
+
+source_filename = ARGV[0]
+source_file = File.read(source_filename)
+
+source_tokens = InputScanner.call(source_file)
+
+abstract_syntax_tree = AbstractSyntaxTree.new(source_tokens)
+
+html_output = HTMLWriter.call(abstract_syntax_tree.token_tree)
+
+puts html_output

data/rosetta-ruby.gemspec

@@ -0,0 +1,16 @@
+# frozen_string_literal: true
+
+Gem::Specification.new do |spec|
+  spec.name        = 'rosetta-ruby'
+  spec.version     = '0.0.0'
+  spec.summary     = 'Rosetta'
+  spec.description = 'Simple Markdown to HTML transformation.'
+  spec.authors     = ['Matt Craig']
+  spec.email       = 'mattcraig365@gmail.com'
+  spec.files       = `git ls-files`.split("\n")
+  spec.homepage    = 'https://rubygems.org/gems/rosetta-ruby'
+  spec.license     = 'MIT'
+  spec.required_ruby_version = '>= 3.0.0'
+
+  # spec.add_development_dependency ['rspec', 'byebug']
+end

data/samples/all.md

@@ -0,0 +1,50 @@
+# Testing all block features
+
+## Code Blocks
+
+```
+def test
+  return true
+end
+```
+
+This is *bold text*!
+*But* should all be part of the same paragraph.
+
+This is _italicized text_!
+
+This is ~~struck through~~!
+
+This is an [inline) link](https://mattcraig.me)!
+
+This is `inline code`!
+
+## Links
+
+[A link.](https://example.com)
+
+## Quotes
+
+> I'd rather be eating tacos.
+> And writing quotes, of course.
+
+In the middle of everything, some text!
+
+## Bullet List
+
+- Thing 1
+- Thing 2
+- Thing 3
+
+## Another Bullet List
+
+- A simple list
+- With two items
+
+More text!
+
+## Ordered List
+
+1. Order one
+2. Order two
+3. Order three

data/samples/bold.md

@@ -0,0 +1 @@
+*This is* too.

data/samples/code_blocks.md

@@ -0,0 +1,5 @@
+```
+def test
+  return true
+end
+```

data/samples/headers.md

@@ -0,0 +1,11 @@
+# Header One
+
+## Header Two
+
+### Header Three
+
+#### Header Four
+
+##### Header Five
+
+###### Header Six

data/samples/link.md

@@ -0,0 +1,3 @@
+This line contains [a link](https://example.com) to a website.
+
+[A link.](https://example.com)

data/samples/lists.md

@@ -0,0 +1,10 @@
+1. Number one
+2. Number two
+3. Three
+4. And so on..
+
+- A simple list
+- With two items
+
+* Another simple list
+* with two items

data/samples/quotes.md

@@ -0,0 +1,6 @@
+# Paragraph One
+This is a line of text.
+> This is a quote
+This is not a quote
+
+>This is a quote again.

data/samples/text.md

@@ -0,0 +1,5 @@
+# Paragraph One
+This is a line of text.
+This is another one.
+
+This is yet another one.

metadata

@@ -0,0 +1,91 @@
+--- !ruby/object:Gem::Specification
+name: rosetta-ruby
+version: !ruby/object:Gem::Version
+  version: 0.0.0
+platform: ruby
+authors:
+- Matt Craig
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2021-08-30 00:00:00.000000000 Z
+dependencies: []
+description: Simple Markdown to HTML transformation.
+email: mattcraig365@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".DS_Store"
+- ".gitignore"
+- ".rubocop.yml"
+- ".vscode/settings.json"
+- Gemfile
+- Gemfile.lock
+- README.md
+- TODOS.md
+- lib/rosetta-ruby.rb
+- lib/rosetta/abstract_syntax_tree.rb
+- lib/rosetta/formatters/html/html_generator.rb
+- lib/rosetta/formatters/html/html_writer.rb
+- lib/rosetta/service_base.rb
+- lib/rosetta/services/inline_token_resolver.rb
+- lib/rosetta/services/input_scanner.rb
+- lib/rosetta/services/token_resolver.rb
+- lib/rosetta/services/tree_parser.rb
+- lib/rosetta/tokens/basic_list.rb
+- lib/rosetta/tokens/basic_list_item.rb
+- lib/rosetta/tokens/basic_token.rb
+- lib/rosetta/tokens/block_quote.rb
+- lib/rosetta/tokens/block_token.rb
+- lib/rosetta/tokens/bold.rb
+- lib/rosetta/tokens/break.rb
+- lib/rosetta/tokens/code_block.rb
+- lib/rosetta/tokens/code_block_delimiter.rb
+- lib/rosetta/tokens/header.rb
+- lib/rosetta/tokens/inline_code.rb
+- lib/rosetta/tokens/italics.rb
+- lib/rosetta/tokens/line_break.rb
+- lib/rosetta/tokens/link.rb
+- lib/rosetta/tokens/new_line.rb
+- lib/rosetta/tokens/numbered_list.rb
+- lib/rosetta/tokens/numbered_list_item.rb
+- lib/rosetta/tokens/paragraph.rb
+- lib/rosetta/tokens/quote.rb
+- lib/rosetta/tokens/shared/inline_tokens.rb
+- lib/rosetta/tokens/strikethrough.rb
+- lib/rosetta/tokens/text.rb
+- main.rb
+- rosetta-ruby.gemspec
+- samples/all.md
+- samples/bold.md
+- samples/code_blocks.md
+- samples/headers.md
+- samples/link.md
+- samples/lists.md
+- samples/quotes.md
+- samples/text.md
+homepage: https://rubygems.org/gems/rosetta-ruby
+licenses:
+- MIT
+metadata: {}
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 3.0.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.2.3
+signing_key:
+specification_version: 4
+summary: Rosetta
+test_files: []