md-noko 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 9fde11dc2fda8402592b512221cf66545b1d17a9fcb79183ae4cc299449685d8
+  data.tar.gz: ea5ac14c87fde2826ad792007a2f38df8be6c4890b93a3915700fefb94cf6efe
+SHA512:
+  metadata.gz: 80d7b6bbf6cf730a42780e8dcb2740f8e98b753303e736103734b38d7add4fa2d9cc4cb6911c7480e1b066cf279df6639b85469667d534c424c6ae9f9010c1d4
+  data.tar.gz: dad35e41c0a72f8af134896444f277bef50db97af43bfdacfa9484b9bf21753e2bb5578aeeff673387d1d585b72d17bb5bf7032003cbbb62a961eb61dde9241b

data/.gitignore

@@ -0,0 +1,13 @@
+syntax: glob
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+Gemfile.lock
+
+# rspec failure tracking
+.rspec_status

data/.rspec

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

data/.travis.yml

@@ -0,0 +1,5 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.5.1
+before_install: gem install bundler -v 1.16.1

data/Gemfile

@@ -0,0 +1,6 @@
+source "https://rubygems.org"
+
+git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in md-noko.gemspec
+gemspec

data/README.md

@@ -0,0 +1,73 @@
+# MD::Noko: in goes Markdown, out comes Nokogiri
+
+## Synopsis
+
+```ruby
+require 'md-noko'
+
+mdnk = MD::Noko.new
+doc  = mdnk.ingest File.open('lolwut.md')
+
+# or
+
+doc  = mdnk.ingest <<EOT
+# Hi
+
+Markdown here!
+
+![lulz](meme.jpeg)
+
+EOT
+
+# doc is a Nokogiri::XML::Document
+```
+
+## Description
+
+This is a simple module that encapsulates a set of desirable
+manipulations to the (X)HTML output
+of [Redcarpet](https://www.rubydoc.info/gems/redcarpet/). It exposes
+(for now) a single method, `ingest`, which returns a [`Nokogiri::XML::Document`](https://www.rubydoc.info/gems/nokogiri/Nokogiri/XML/Document), for further manipulation. In particular, this module:
+
+* Adds HTML preamble to produce a valid document,
+* Creates a `<base href=""/>` element which you can pass a URL,
+* Creates a hierarchy of `<section>` elements and places headings
+  and content inside,
+* If the document contains exactly one `<h1>` which is the very first
+  thing in the file, it is copied into the `<title>`, and removed from
+  the document body if determined to be redundant (i.e. unless it
+  contains markup elements and not strictly text),
+* A `<blockquote>` element containing exactly one nested
+  `<blockquote>` element is converted into a single `<aside role="note">`,
+* Images on their own paragraph are transformed into a `<figure>`,
+* Text nodes not descendants of `<pre>` are whitespace-normalized and
+  indentation is repaired.
+  
+The embedded `Redcarpet::Markdown` instance has the following flags set:
+
+* `:tables`
+* `:fenced_code_blocks`
+* `:quote`
+* `:highlight`
+
+These are currently not exposed.
+
+## Installation
+
+The usual:
+
+    $ gem install md-noko
+
+Or, [download it off rubygems.org](https://rubygems.org/gems/md-noko).
+
+## Contributing
+
+Bug reports and pull requests are welcome at
+[the GitHub repository](https://github.com/doriantaylor/rb-md-noko).
+
+## Copyright & License
+
+©2018 [Dorian Taylor](https://doriantaylor.com/)
+
+This software is provided under
+the [Apache License, 2.0](https://www.apache.org/licenses/LICENSE-2.0).

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "md/noko"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/lib/md-noko.rb

@@ -0,0 +1 @@
+require 'md/noko'

data/lib/md/noko.rb

@@ -0,0 +1,168 @@
+require 'md/noko/version'
+require 'redcarpet'
+require 'xml-mixup'
+
+class MD::Noko
+  include XML::Mixup
+
+  private
+
+  XHTML_BP = <<-BP
+<!DOCTYPE html>
+<html xmlns="http://www.w3.org/1999/xhtml">
+  <head>
+    <title/>
+    <base href="%s"/>
+  </head>
+  <body>
+%s
+  </body>
+</html>
+  BP
+
+  XPATH_NS = { html: 'http://www.w3.org/1999/xhtml' }.freeze
+
+  @@markdown = Redcarpet::Markdown.new(
+    Redcarpet::Render::XHTML.new(prettify: false),
+    tables: true, fenced_code_blocks: true, quote: true, highlight: true)
+
+  def h1_title body
+    heads = body.xpath('html:h1', XPATH_NS)
+
+    # set the title to the first and only h1 if it's the first element
+    if heads.length == 1 and not heads[0].previous_element
+      h1 = heads[0]
+
+      # assign document title to the header content
+      d = body.document
+      t = d.at_xpath('/html:html/html:head/html:title[1]', XPATH_NS)
+      t.content = h1.content
+
+      # unlink redundant h1 if it has no children (ie unformatted)
+      h1.unlink unless h1.at_xpath('*')
+      
+      # only do h2 through h6
+      return true
+    end
+
+    # otherwise do nothing
+    false
+  end
+
+  def make_sections node, ranks=1..6
+    raise 'fail range' if ranks.nil? or ranks.size < 1
+
+    h = "html:h#{ranks.first}"
+
+    ranks = Range.new(ranks.first + 1, ranks.last)
+
+    headers = node.xpath(h, XPATH_NS).to_a
+    if headers.empty?
+      return make_sections node, ranks if ranks.size > 0
+    else
+      headers.each_index do |i|
+        hdr = headers[i]
+        xp = "following-sibling::node()[not(self::#{h})]"
+        if i < headers.length - 1
+          # note that this is always 1 because all preceding
+          # siblings prior to that will have been removed
+          xp += "[following-sibling::#{h}" +
+            "[count(preceding-sibling::#{h}) = #{1}]]"
+        end
+
+        # duplicate and nuke these elements
+        siblings = hdr.xpath(xp, XPATH_NS).to_a.map do |s|
+          # note that :unlink returns the node, but with a
+          # garbaged-up set of namespaces
+          o = s.dup; s.unlink; o
+        end
+
+        # add the header to the front of the list
+        siblings.unshift hdr.dup
+        siblings.unshift "\n"
+
+        # now construct the section
+        section = markup replace: hdr, spec: { nil => :section }
+        markup after:  section, spec: "\n"
+        markup parent: section, spec: siblings
+
+        # now recurse
+        make_sections section, ranks
+      end
+    end
+  end
+
+  def bq_aside body
+    x = './/%s[not(parent::%s)][%s][count(*) = 1]' % (%w{html:blockquote} * 3)
+    body.xpath(x, XPATH_NS).each do |node|
+      fc = node.first_element_child
+      fc.name = 'aside'
+      fc[:role] = 'note'
+      node.replace fc
+    end
+  end
+
+  def img_figure body
+    body.xpath('.//html:p[html:img][count(*) = 1]', XPATH_NS).each do |node|
+      node.name = 'figure'
+    end
+  end
+
+  def prune_text body
+    doc = body.document
+    doc.xpath('//text()[not(ancestor::html:pre)]', XPATH_NS).each do |n|
+      n.content = n.content.gsub(/(?: |\t|\r|\n)+/, ' ')
+      # might as well fix the damn indentation while we're here
+      if n.content == ' '
+        a = n.ancestors.count - 1
+        if (p = n.previous_sibling)
+          # nth text node
+          if p.text? and p.content =~ /^\s+$/
+            n.unlink
+          else
+            a -= 1 unless n.next_sibling
+            n.content = "\n" + ('  ' * a)
+          end
+        else
+          # first text node
+          n.content = "\n" + ('  ' * a)
+        end
+      end
+    end
+  end
+
+  public
+
+  # Ingest a markdown file, with sensible defaults
+  #
+  # @param obj [String, IO] the content to be ingested
+  #
+  # @param uri [String, #to_s, nil] the document's base URI
+  #
+  # @return [Nokogiri::XML::Document]
+
+  def ingest obj, uri=nil
+    doc = obj.respond_to?(:read) ? obj.read : obj
+    doc = XHTML_BP % [uri ? uri.to_s : '', @@markdown.render(doc)]
+    doc = Nokogiri::XML.parse doc, uri
+
+    body = doc.at_xpath('/html:html/html:body[1]', XPATH_NS)
+
+    # default all six headers unless there's a lone h1
+    ranks = h1_title(body) ? 2..6 : 1..6
+
+    # markdown just makes a flat list of elements so let's plump it up
+    make_sections body, ranks
+
+    # redo double blockquotes as <aside role="note">
+    bq_aside body
+
+    # redo paragraphs containing only images as figures
+    img_figure body
+
+    # fix the damn text nodes
+    prune_text body
+
+    doc
+  end
+end

data/lib/md/noko/version.rb

@@ -0,0 +1,5 @@
+module MD
+  class Noko
+    VERSION = "0.1.0"
+  end
+end

data/md-noko.gemspec

@@ -0,0 +1,33 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'md/noko/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'md-noko'
+  spec.version       = MD::Noko::VERSION
+  spec.authors       = ['Dorian Taylor']
+  spec.email         = ['code@doriantaylor.com']
+  spec.license       = 'Apache-2.0'
+  spec.summary       = %q{In goes Markdown, out pops Nokogiri.}
+  spec.description   = <<-DESC
+This is a simple module that encapsulates a set of desirable
+manipulations to the (X)HTML output of Redcarpet, producing a
+Nokogiri::XML::Document which is amenable to further manipulation.
+  DESC
+  spec.homepage      = 'https://github.com/doriantaylor/rb-md-noko'
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.bindir        = 'exe'
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ['lib']
+
+  spec.required_ruby_version = '~> 2.0'
+
+  spec.add_development_dependency "bundler", "~> 1.11"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+
+  spec.add_runtime_dependency 'redcarpet', '~> 3.4.0'
+  spec.add_runtime_dependency 'xml-mixup', '~> 0.1.5'
+end

metadata

@@ -0,0 +1,129 @@
+--- !ruby/object:Gem::Specification
+name: md-noko
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Dorian Taylor
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2018-05-16 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.11'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.11'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: redcarpet
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.4.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.4.0
+- !ruby/object:Gem::Dependency
+  name: xml-mixup
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.1.5
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.1.5
+description: |
+  This is a simple module that encapsulates a set of desirable
+  manipulations to the (X)HTML output of Redcarpet, producing a
+  Nokogiri::XML::Document which is amenable to further manipulation.
+email:
+- code@doriantaylor.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- Gemfile
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- lib/md-noko.rb
+- lib/md/noko.rb
+- lib/md/noko/version.rb
+- md-noko.gemspec
+homepage: https://github.com/doriantaylor/rb-md-noko
+licenses:
+- Apache-2.0
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - "~>"
+    - !ruby/object:Gem::Version
+      version: '2.0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.7.6
+signing_key: 
+specification_version: 4
+summary: In goes Markdown, out pops Nokogiri.
+test_files: []