html-renderer 0.0.2 → 0.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4d2be4cf32a612a0e2fa528a0d50e85df36f732e40c408ed3183b6a041c60558
-  data.tar.gz: 1500874bc627082bf07f2e0912ba5b2020cad6987cd9cd29c4add0abe0e5d0db
+  metadata.gz: d3c17a79e5d484dfafbdf2161683d28c8ee9d24b3ec099c7e392236fe167f547
+  data.tar.gz: 4c0cc61cc44691ab2e35b2c289f352fe17aec1d499cd01d86b6a01f4a3a9dab6
 SHA512:
-  metadata.gz: eda1c880bebd51ed462ca2c07fcec4abfcb80cc30cc9b16b2c7366d4abc46637f3d3f778d36689e3cb6472b60fa28fda2282fea64c49262f6a4246c45468d2d9
-  data.tar.gz: 26dec9aa2c27f6356101c92ed5aabf164249aaec89a99febbb55ecbd4aafe9db1e44d9e914344b49f4919f501cd01d568427f48e267db353d4d7952ba9f36b25
+  metadata.gz: 52f7781a488c72b42398dad8a8a10393a3ccc1eca7147696e94398d28633d57956133a05c026364c8125b5dfcdf333a6772ec44ee786ced02ceb130e2c6c1ce2
+  data.tar.gz: 228891adf55ef0e77c958399071c0eb2a4acbc2620e3681aa59b65b56bd47dc308e5cee5b968043603388cd92e44443b7906acf93963c69513d94cceafa3f0b4

data/.gemspec

@@ -12,9 +12,10 @@ Gem::Specification.new do |s|
   s.email       = "chris@ill-logic.com"
   s.authors     = ["epitron"]
 
-  s.files = `git ls`.lines.map(&:strip)
+  s.files            = `git ls`.lines.map(&:strip)
   s.extra_rdoc_files = ["README.md", "LICENSE"]
-  
-  s.add_dependency "oga", "~> 2"
-  s.add_development_dependency "ansi", "~> 1"
+
+  s.add_dependency "oga"
+  s.add_dependency "terminal-table", "~> 1.8"
+  s.add_dependency "term-ansicolor", "~> 1.7"
 end

data/.gitignore

@@ -0,0 +1 @@
+/pkg/

data/README.md

@@ -2,11 +2,29 @@
 
 ## Overview
 
-Allows you to subclass `HTMLRenderer::Base`, add some methods, and then parse HTML to generate custom output.
+An extensible HTML renderer.
 
-(Uses a similar API to the [RedCarpet](https://github.com/vmg/redcarpet) gem.)
+Comes with two built-in renderers:
+* `HTMLRenderer::ANSI` (outputs colored text to the termnial)
+* `HTMLRenderer::Text` (outputs plain text)
 
-## Examples
+## Usage
 
-* [HTML to Plain Text Renderer](https://github.com/epitron/html-renderer/blob/master/examples/plain_text_renderer.rb)
-* [HTML to ANSI Renderer](https://github.com/epitron/html-renderer/blob/master/examples/ansi_renderer.rb)
+Render to ANSI:
+```
+ansi_text = HTMLRenderer::ANSI.render("<b>hello html</b>")
+ansi_text = HTMLRenderer::ANSI.render(open("file.html"))
+```
+
+Render to plain text:
+```
+plain_text = HTMLRenderer::Text.render(open("file.html"))
+```
+
+## Extending it
+
+The API design uses the same philosophy as [RedCarpet](https://github.com/vmg/redcarpet).
+
+To create a new renderer, subclass `HTMLRenderer::Base`, then add a method to handle each type of element. Whatever the method returns is output by the renderer.
+
+Example renderer: [HTMLRenderer::ANSI](https://github.com/epitron/html-renderer/blob/master/lib/html-renderer/ansi.rb)

data/Rakefile

@@ -1,14 +1,13 @@
-pkgname = "html-renderer"
-gem_version = File.read("VERSION").strip
+gem = eval(File.read '.gemspec')
 
-gemfile = "#{pkgname}-#{gem_version}.gem"
+gemfile = "#{gem.name}-#{gem.version}.gem"
 
 task :build do
   system "gem build .gemspec"
   system "mkdir pkg/" unless File.directory? "pkg"
   system "mv #{gemfile} pkg/"
 end
- 
+
 task :release => :build do
   system "gem push pkg/#{gemfile}"
 end
@@ -18,3 +17,9 @@ task :gem => :build
 task :install => :build do
   system "gem install pkg/#{gemfile}"
 end
+
+task :test do
+  Dir.chdir "test"
+  $: << "../lib"
+  load "test.rb"
+end

data/TODO.md

@@ -0,0 +1,14 @@
+# TODO list
+
+## Base class
+
+! add HTMLRenderer.reflow_paragraph
+* #render takes options (and passes them to subclasses)
+* :debug option (hide parse errors unless 'true')
+
+## ANSI renderer
+
+* use HTMLRenderer.reflow_paragraph
+* :wrap option (with optional terminal width)
+* Better table renderer (with line-drawing)
+* Follow `<table>` style attributes when drawing tables (eg: borders)

data/VERSION

@@ -1 +1 @@
-0.0.2
+0.1.3

data/lib/html-renderer.rb

@@ -1 +1,6 @@
 require 'html-renderer/base'
+
+module HTMLRenderer
+  autoload :ANSI, 'html-renderer/ansi'
+  autoload :Text, 'html-renderer/text'
+end

data/{examples/ansi_renderer.rb → lib/html-renderer/ansi.rb}

@@ -1,16 +1,24 @@
 require 'html-renderer'
 require 'ansi/mixin'
 require 'terminal-table'
-require 'coderay'
 
-class String
-  include ANSI::Mixin
+###########################################################################
 
-  def grey; self.black.bold; end
+module ANSI::Mixin
+  def grey; ANSI::Code.bold { ANSI::Code.black { to_s } }; end
 end
 
+module HTMLRenderer::ANSIStrings
+  refine String do
+    include ANSI::Mixin
+  end
+end
+
+###########################################################################
+
+class HTMLRenderer::ANSI < HTMLRenderer::Base
 
-class ANSIRenderer < HTMLRenderer::Base
+  using HTMLRenderer::ANSIStrings
 
 private
 
@@ -32,6 +40,9 @@ private
     s&.downcase&.scan(/\w+/)&.join
   end
 
+  def subscript(s)
+    "[#{s}]"
+  end
 
 public
 
@@ -78,13 +89,7 @@ public
   end
 
   def block_code(code, language)
-    language ||= :ruby
-
-    language = language[1..-1] if language[0] == "."  # strip leading "."
-    language = :cpp if language == "C++"
-
-    require 'coderay'
-    "#{indent CodeRay.scan(code, language).term, 4}\n"
+    code.bold.cyan + "\n"
   end
 
   def block_quote(text)
@@ -102,7 +107,7 @@ public
       when 1 then title.bold.yellow
       when 2 then title.bold.cyan
       when 3 then title.bold.blue
-      else title.purple
+      else title.magenta
     end
 
     "#{bar}\n  #{title}\n#{bar}\n\n"
@@ -174,7 +179,8 @@ public
 
 end
 
+###########################################################################
 
 if __FILE__ == $0
-  puts ANSIRenderer.render(open(ARGV.first || "test.html"))
+  puts HTMLRenderer::ANSI.render(open(ARGV.first || "test.html"))
 end

data/lib/html-renderer/base.rb

@@ -1,30 +1,25 @@
 ######################################################################################
 require 'oga'
 ######################################################################################
-#
-# TODOs:
-# - Streaming output (yield every paragraph/div/header)
-# - Embed into 'c' tool (for rendering raw HTML blocks)
-#
-######################################################################################
-
-class String
 
-  def tighten
-    gsub(/\s+/, ' ').strip
-  end
+module HTMLRenderer
 
-  def blank?; !!self[/[^\s]/]; end
+  module STDLIBRefinements
+    refine String do
+      def tighten
+        gsub(/\s+/, ' ').strip
+      end
 
-end
+      def blank?; !!self[/[^\s]/]; end
+    end
 
-class NilClass
-  def blank?; true; end
-end
+    refine NilClass do
+      def blank?; true; end
+    end
+  end
 
-######################################################################################
+  using STDLIBRefinements
 
-module HTMLRenderer
 
   class State
     attr_accessor :list_order
@@ -65,14 +60,16 @@ private
           content.blank? ? normal_text(content) : nil
 
         when Oga::XML::Element
-          case node.name
+          case node.name.downcase
           when "a"
             url     = node["href"]
             title   = node["title"]
             name    = node["name"]
             content = render_children(node, state)
 
-            if name and not url
+            if title.blank? and url.blank? and name.blank?
+              content
+            elsif name and not url
               anchor(name, title, content)
             else
               link(url, title, content)
@@ -96,6 +93,8 @@ private
             emphasis(render_children(node, state))
           when "sup"
             superscript(render_children(node, state))
+          when "sub"
+            subscript(render_children(node, state))
           when "u"
             underline(render_children(node, state))
           when "br"
@@ -118,7 +117,7 @@ private
             list_item(render_children(node, state), state.list_order)
 
           when "code"
-            block_code(render_children(node, state))
+            block_code(render_children(node, state), nil)
           when "blockquote"
             block_quote(render_children(node, state))
 
@@ -149,20 +148,22 @@ private
             table(header, rows)
 
           when "html", "body", "nav", "span", "form", "label", "input", "button", "section", "fieldset",
-               "menu", "article", "header", "time", "aside", "footer", "nobr", "wbr", 
-               "table", "tr", "td", "th", "thead", "tbody", "noscript", "select",
-               "address"
+               "pre", "menu", "article", "header", "time", "aside", "footer", "nobr", "wbr",
+               "table", "tr", "td", "th", "tt", "thead", "tbody", "noscript", "select",
+               "address", "center", "small"
             render_children(node, state)
 
           when "head", "script", "link", "style"
-            # skip it
-
+            #
+            # don't render anything
+            #
           else
-            raise "Unrecognized HTML tag: #{node.name} -> #{node.inspect}"
+            # raise "Unrecognized HTML tag: #{node.name} -> #{node.inspect}"
+            $stderr.puts "Unrecognized HTML tag: #{node.name} -> #{node.inspect}"
+            render_children(node, state)
           end
 
-        when Oga::XML::Comment
-          # skip it
+        when Oga::XML::Comment, Oga::XML::Cdata
 
         else
           raise "Unhandled Oga node type: #{node.class}"

data/lib/html-renderer/debug.rb

@@ -0,0 +1,9 @@
+require 'html-renderer'
+
+class HTMLRenderer::DebugRenderer < HTMLRenderer::Base
+
+  def method_missing(meth, *args)
+    "#{meth}(#{args})"
+  end
+
+end

data/lib/html-renderer/html_parser.rb

@@ -0,0 +1,105 @@
+require 'strscan'
+
+class Stack < Array
+  alias_method :top, :last
+  alias_method :peek, :last
+end
+
+class String
+  def recursive_inspect(depth)
+    ("  "*depth)+inspect
+  end
+end
+
+class HTMLParser
+
+  OPEN_TAG_RE  = %r{<([^>]+)>}
+  CLOSE_TAG_RE = %r{</([^>]+)>}
+  TEXT_RE      = %r{[^<]+}
+  ATTR_RE      = %r{(\w+)=(?:"([^"]+)"|'([^']+)'|(\w+))}
+
+  class Tag
+
+    attr_accessor :name, :attrs, :children
+
+    def self.from_str(s)
+      name, rest = s.split(/\s+/, 2)
+      
+      if rest
+        attrs = rest.scan(HTMLParser::ATTR_RE).flatten.compact.each_slice(2).to_h
+      else
+        attrs = {}
+      end
+      new(name, attrs)
+    end
+
+    def initialize(name, attrs={}, children=[])
+      @name     = name
+      @attrs    = attrs
+      @children = children
+    end
+
+    def recursive_inspect(depth=0)
+      curdent = "  "*depth
+      indent = "  "*(depth+1)
+      "#{curdent}<#{name} #{attrs}>\n#{indent}#{children.map{|c| c.recursive_inspect(depth+1)}}\n#{curdent}</#{name}>"
+    end
+
+  end
+
+  def initialize(html)
+    @s = StringScanner.new(html)
+    # @s = html
+  end
+
+  def each_tag
+      until @s.eos?
+      if @s.scan(CLOSE_TAG_RE)
+        yield [:close_tag, @s.captures.first]
+      elsif @s.scan(OPEN_TAG_RE)
+        tag = Tag.from_str(@s.captures.first)
+        yield [:open_tag, tag]
+      elsif @s.scan(TEXT_RE)
+        yield [:text, @s.matched]
+      end
+    end
+  end
+
+  def as_tree
+    tree.map { |e| e.recursive_inspect }
+  end
+
+  def tree
+    stack = Stack.new
+    stack.push Tag.new("root")
+
+    each_tag do |type, elem|
+      case type
+      when :text
+        text = elem.strip
+        stack.top.children << text unless text.empty?
+      when :open_tag
+        stack.top.children << elem
+        stack.push elem
+      when :close_tag
+        stack.pop
+      else
+        raise "wat"
+      end
+    end
+
+    stack
+  end
+
+end
+
+unless file = ARGV.first
+  file = "test.html"
+end
+
+html = File.read(file)
+
+r = HTMLParser.new(html)
+r.each_tag{|t| p t}
+
+# puts r.as_tree

data/{examples/plain_text_renderer.rb → lib/html-renderer/text.rb}

@@ -1,9 +1,10 @@
 require 'html-renderer'
 
 #
-# Everything-stripping renderer.
+# Strips out everything but the plain text.
 #
-class PlainTextRenderer < HTMLRenderer::Base
+class HTMLRenderer::Text < HTMLRenderer::Base
+
   # Methods where the first argument is the text content
   [
     # block-level calls
@@ -65,8 +66,3 @@ class PlainTextRenderer < HTMLRenderer::Base
     content + "\t"
   end
 end
-
-
-if __FILE__ == $0
-  puts PlainTextRenderer.render(open("test.html"))
-end

data/test/test.rb

@@ -0,0 +1,15 @@
+require 'html-renderer'
+require 'html-renderer/debug'
+
+[
+  HTMLRenderer::ANSI,
+  HTMLRenderer::Text,
+  HTMLRenderer::DebugRenderer,
+].each do |renderer|
+  puts
+  puts "=== #{renderer} =============================="
+  puts
+  puts renderer.render(open("test.html"))
+  puts
+  puts
+end

metadata

@@ -1,43 +1,57 @@
 --- !ruby/object:Gem::Specification
 name: html-renderer
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.1.3
 platform: ruby
 authors:
 - epitron
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2018-05-22 00:00:00.000000000 Z
+date: 2020-07-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: oga
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: terminal-table
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2'
+        version: '1.8'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2'
+        version: '1.8'
 - !ruby/object:Gem::Dependency
-  name: ansi
+  name: term-ansicolor
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1'
-  type: :development
+        version: '1.7'
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1'
+        version: '1.7'
 description: Easily implement an HTML renderer by creating a subclass and adding some
   methods, similar to RedCarpet. (Examples are included for rendering HTML to ANSI
   and plain text.)
@@ -49,21 +63,25 @@ extra_rdoc_files:
 - LICENSE
 files:
 - ".gemspec"
+- ".gitignore"
 - LICENSE
 - README.md
 - Rakefile
+- TODO.md
 - VERSION
-- examples/ansi_renderer.rb
-- examples/debug_renderer.rb
-- examples/plain_text_renderer.rb
-- examples/test.html
 - lib/html-renderer.rb
+- lib/html-renderer/ansi.rb
 - lib/html-renderer/base.rb
+- lib/html-renderer/debug.rb
+- lib/html-renderer/html_parser.rb
+- lib/html-renderer/text.rb
+- test/test.html
+- test/test.rb
 homepage: http://github.com/epitron/html-renderer/
 licenses:
 - WTFPL
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -78,9 +96,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.6
-signing_key: 
+rubygems_version: 3.1.3
+signing_key:
 specification_version: 4
 summary: HTML Renderer
 test_files: []

data/examples/debug_renderer.rb

@@ -1,14 +0,0 @@
-require 'html-renderer'
-
-class DebugRenderer < HTMLRenderer::Base
- 
-  def method_missing(meth, *args)
-    "#{meth}(#{args})"
-  end
-
-end
-
-
-if __FILE__ == $0
-  puts DebugRenderer.render(open("test.html"))
-end