coradoc 1.0.0 → 1.1.1

data/utils/parser_analyzer.rb

@@ -0,0 +1,66 @@
+require "rubocop"
+
+def ast_from(string)
+  RuboCop::ProcessedSource.new(string, RUBY_VERSION.to_f).ast
+end
+
+def is_def?(arr)
+  if Array === arr
+    if arr[0] == :def
+      $defs << arr
+    else
+      arr.each do |e|
+        is_def?(e)
+      end
+    end
+  end
+end
+
+path = "lib/coradoc/parser/asciidoc/"
+class_files = Dir.entries(path).select{|x| File.file?(path+x)}
+
+$all_defs = {}
+
+class_files.each do |cf|
+  a = ast_from(File.open(path+cf).read)
+  next if a.nil?
+  sexp = a.to_sexp_array
+  $defs = []
+  is_def?(sexp)
+  $all_defs[cf] = $defs
+end;
+
+relevant_names = $all_defs.map{|fn, defs| defs.map{|d| d[1]}}.flatten;
+
+require 'graphviz'
+
+g = GraphViz.new( :G, :type => :digraph );
+
+g[:fontsize] = 8
+g[:rankdir] = "LR"
+g[:overlap] = false
+g[:splines] = false
+
+nodes = {}
+
+$all_defs.each do |file_name, defs|
+
+  defs.each do |ast_def|
+    calls = ast_def[2..-1].flatten & relevant_names
+    node_name = ast_def[1]
+    nodes[node_name] = g.add_nodes( "#{node_name}\n#{file_name}" )
+  end
+end;
+
+$all_defs.each do |file_name, defs|
+  defs.each do |ast_def|
+    calls = ast_def[2..-1].flatten & relevant_names
+    node_name = ast_def[1]
+    calls.each do |cl|
+      w = g.add_edges(nodes[node_name], nodes[cl])
+      w[:weight] = 1.5
+    end
+  end
+end;
+
+g.output( :png => "utils/parser_graph.png_#{Time.now.to_i}" );

data/utils/round_trip.rb

@@ -0,0 +1,37 @@
+$LOAD_PATH.unshift("../coradoc/lib")
+
+require "coradoc"
+require "coradoc/input/html"
+
+
+rice_path = "../mn-samples-iso/sources/international-standard/rice-2023/"
+
+if !Dir.exist?(rice_path)
+  puts "pleas set path to rice-2023"
+  exit
+end
+
+adoc_files = Dir.glob("#{rice_path}**/*adoc")
+
+adoc_files.each do |file_path|
+  puts file_path
+  file_path_rt = "#{file_path}.roundtrip"
+  file_path_diff = "#{file_path}.roundtrip.diff"
+  FileUtils.rm(file_path_rt) if File.exist?(file_path_rt)
+  FileUtils.rm(file_path_diff) if File.exist?(file_path_diff)
+  # begin
+    adoc_file = File.open(file_path).read
+    next if adoc_file.size == 0
+    puts "parsing..."
+    ast = Coradoc::Parser::Base.new.parse(adoc_file)
+    puts "transforming..."
+    doc = Coradoc::Transformer.transform(ast[:document])
+    puts "generating..."
+    generated_adoc = Coradoc::Generator.gen_adoc(doc)
+    cleaned_adoc = Coradoc::Input::HTML.cleaner.tidy(generated_adoc)
+    File.open("#{file_path}.roundtrip","w"){|f| f.write(cleaned_adoc)}
+    `diff -B #{file_path} #{file_path}.roundtrip > #{file_path}.roundtrip.diff`
+  # rescue
+    # puts "unsuccessful..."
+  # end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: coradoc
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.1.1
 platform: ruby
 authors:
 - Ribose Inc.
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2024-06-01 00:00:00.000000000 Z
+date: 2024-09-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: marcel
@@ -109,6 +109,34 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: base64
+  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: thor
+  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: codeclimate-test-reporter
   requirement: !ruby/object:Gem::Requirement
@@ -226,31 +254,33 @@ email:
 - open.source@ribose.com
 - abunashir@gmail.com
 executables:
+- coradoc
 - reverse_adoc
 - w2a
 extensions: []
 extra_rdoc_files: []
 files:
-- ".docker/Dockerfile"
-- ".docker/Makefile"
-- ".docker/docker-compose.yml"
-- ".docker/readme.md"
 - ".editorconfig"
 - ".hound.yml"
 - ".pryrc.sample"
 - ".rubocop.yml"
 - CHANGELOG.md
 - CODE_OF_CONDUCT.md
+- Dockerfile
 - Gemfile
 - LICENSE.txt
 - Makefile
-- README.md
+- README.Docker.adoc
+- README.adoc
 - Rakefile
 - coradoc.gemspec
 - docker-compose.yml
+- exe/coradoc
 - exe/reverse_adoc
 - exe/w2a
 - lib/coradoc.rb
+- lib/coradoc/cli.rb
+- lib/coradoc/converter.rb
 - lib/coradoc/document.rb
 - lib/coradoc/element/admonition.rb
 - lib/coradoc/element/attribute.rb
@@ -258,23 +288,31 @@ files:
 - lib/coradoc/element/audio.rb
 - lib/coradoc/element/author.rb
 - lib/coradoc/element/base.rb
+- lib/coradoc/element/bibliography.rb
+- lib/coradoc/element/bibliography_entry.rb
 - lib/coradoc/element/block.rb
 - lib/coradoc/element/block/core.rb
 - lib/coradoc/element/block/example.rb
 - lib/coradoc/element/block/literal.rb
+- lib/coradoc/element/block/pass.rb
 - lib/coradoc/element/block/quote.rb
+- lib/coradoc/element/block/reviewer_comment.rb
 - lib/coradoc/element/block/side.rb
 - lib/coradoc/element/block/sourcecode.rb
 - lib/coradoc/element/break.rb
+- lib/coradoc/element/comment_block.rb
+- lib/coradoc/element/comment_line.rb
 - lib/coradoc/element/document_attributes.rb
 - lib/coradoc/element/header.rb
 - lib/coradoc/element/image.rb
 - lib/coradoc/element/image/block_image.rb
 - lib/coradoc/element/image/core.rb
 - lib/coradoc/element/image/inline_image.rb
+- lib/coradoc/element/include.rb
 - lib/coradoc/element/inline.rb
 - lib/coradoc/element/inline/anchor.rb
 - lib/coradoc/element/inline/bold.rb
+- lib/coradoc/element/inline/citation.rb
 - lib/coradoc/element/inline/cross_reference.rb
 - lib/coradoc/element/inline/hard_line_break.rb
 - lib/coradoc/element/inline/highlight.rb
@@ -295,70 +333,91 @@ files:
 - lib/coradoc/element/revision.rb
 - lib/coradoc/element/section.rb
 - lib/coradoc/element/table.rb
+- lib/coradoc/element/tag.rb
+- lib/coradoc/element/term.rb
 - lib/coradoc/element/text_element.rb
 - lib/coradoc/element/title.rb
 - lib/coradoc/element/video.rb
 - lib/coradoc/generator.rb
+- lib/coradoc/input.rb
+- lib/coradoc/input/adoc.rb
+- lib/coradoc/input/docx.rb
+- lib/coradoc/input/html.rb
+- lib/coradoc/input/html/LICENSE.txt
+- lib/coradoc/input/html/README.adoc
+- lib/coradoc/input/html/cleaner.rb
+- lib/coradoc/input/html/config.rb
+- lib/coradoc/input/html/converters.rb
+- lib/coradoc/input/html/converters/a.rb
+- lib/coradoc/input/html/converters/aside.rb
+- lib/coradoc/input/html/converters/audio.rb
+- lib/coradoc/input/html/converters/base.rb
+- lib/coradoc/input/html/converters/blockquote.rb
+- lib/coradoc/input/html/converters/br.rb
+- lib/coradoc/input/html/converters/bypass.rb
+- lib/coradoc/input/html/converters/code.rb
+- lib/coradoc/input/html/converters/div.rb
+- lib/coradoc/input/html/converters/dl.rb
+- lib/coradoc/input/html/converters/drop.rb
+- lib/coradoc/input/html/converters/em.rb
+- lib/coradoc/input/html/converters/figure.rb
+- lib/coradoc/input/html/converters/h.rb
+- lib/coradoc/input/html/converters/head.rb
+- lib/coradoc/input/html/converters/hr.rb
+- lib/coradoc/input/html/converters/ignore.rb
+- lib/coradoc/input/html/converters/img.rb
+- lib/coradoc/input/html/converters/li.rb
+- lib/coradoc/input/html/converters/mark.rb
+- lib/coradoc/input/html/converters/markup.rb
+- lib/coradoc/input/html/converters/math.rb
+- lib/coradoc/input/html/converters/ol.rb
+- lib/coradoc/input/html/converters/p.rb
+- lib/coradoc/input/html/converters/pass_through.rb
+- lib/coradoc/input/html/converters/pre.rb
+- lib/coradoc/input/html/converters/q.rb
+- lib/coradoc/input/html/converters/strong.rb
+- lib/coradoc/input/html/converters/sub.rb
+- lib/coradoc/input/html/converters/sup.rb
+- lib/coradoc/input/html/converters/table.rb
+- lib/coradoc/input/html/converters/td.rb
+- lib/coradoc/input/html/converters/text.rb
+- lib/coradoc/input/html/converters/th.rb
+- lib/coradoc/input/html/converters/tr.rb
+- lib/coradoc/input/html/converters/video.rb
+- lib/coradoc/input/html/errors.rb
+- lib/coradoc/input/html/html_converter.rb
+- lib/coradoc/input/html/plugin.rb
+- lib/coradoc/input/html/plugins/plateau.rb
+- lib/coradoc/input/html/postprocessor.rb
 - lib/coradoc/legacy_parser.rb
 - lib/coradoc/oscal.rb
+- lib/coradoc/output.rb
+- lib/coradoc/output/adoc.rb
+- lib/coradoc/output/coradoc_tree_debug.rb
 - lib/coradoc/parser.rb
+- lib/coradoc/parser/asciidoc/admonition.rb
+- lib/coradoc/parser/asciidoc/attribute_list.rb
 - lib/coradoc/parser/asciidoc/base.rb
+- lib/coradoc/parser/asciidoc/bibliography.rb
+- lib/coradoc/parser/asciidoc/block.rb
+- lib/coradoc/parser/asciidoc/citation.rb
 - lib/coradoc/parser/asciidoc/content.rb
 - lib/coradoc/parser/asciidoc/document_attributes.rb
 - lib/coradoc/parser/asciidoc/header.rb
+- lib/coradoc/parser/asciidoc/inline.rb
+- lib/coradoc/parser/asciidoc/list.rb
+- lib/coradoc/parser/asciidoc/paragraph.rb
 - lib/coradoc/parser/asciidoc/section.rb
+- lib/coradoc/parser/asciidoc/table.rb
+- lib/coradoc/parser/asciidoc/term.rb
 - lib/coradoc/parser/base.rb
-- lib/coradoc/reverse_adoc.rb
-- lib/coradoc/reverse_adoc/LICENSE.txt
-- lib/coradoc/reverse_adoc/README.adoc
-- lib/coradoc/reverse_adoc/cleaner.rb
-- lib/coradoc/reverse_adoc/config.rb
-- lib/coradoc/reverse_adoc/converters.rb
-- lib/coradoc/reverse_adoc/converters/a.rb
-- lib/coradoc/reverse_adoc/converters/aside.rb
-- lib/coradoc/reverse_adoc/converters/audio.rb
-- lib/coradoc/reverse_adoc/converters/base.rb
-- lib/coradoc/reverse_adoc/converters/blockquote.rb
-- lib/coradoc/reverse_adoc/converters/br.rb
-- lib/coradoc/reverse_adoc/converters/bypass.rb
-- lib/coradoc/reverse_adoc/converters/code.rb
-- lib/coradoc/reverse_adoc/converters/div.rb
-- lib/coradoc/reverse_adoc/converters/dl.rb
-- lib/coradoc/reverse_adoc/converters/drop.rb
-- lib/coradoc/reverse_adoc/converters/em.rb
-- lib/coradoc/reverse_adoc/converters/figure.rb
-- lib/coradoc/reverse_adoc/converters/h.rb
-- lib/coradoc/reverse_adoc/converters/head.rb
-- lib/coradoc/reverse_adoc/converters/hr.rb
-- lib/coradoc/reverse_adoc/converters/ignore.rb
-- lib/coradoc/reverse_adoc/converters/img.rb
-- lib/coradoc/reverse_adoc/converters/li.rb
-- lib/coradoc/reverse_adoc/converters/mark.rb
-- lib/coradoc/reverse_adoc/converters/markup.rb
-- lib/coradoc/reverse_adoc/converters/math.rb
-- lib/coradoc/reverse_adoc/converters/ol.rb
-- lib/coradoc/reverse_adoc/converters/p.rb
-- lib/coradoc/reverse_adoc/converters/pass_through.rb
-- lib/coradoc/reverse_adoc/converters/pre.rb
-- lib/coradoc/reverse_adoc/converters/q.rb
-- lib/coradoc/reverse_adoc/converters/strong.rb
-- lib/coradoc/reverse_adoc/converters/sub.rb
-- lib/coradoc/reverse_adoc/converters/sup.rb
-- lib/coradoc/reverse_adoc/converters/table.rb
-- lib/coradoc/reverse_adoc/converters/td.rb
-- lib/coradoc/reverse_adoc/converters/text.rb
-- lib/coradoc/reverse_adoc/converters/th.rb
-- lib/coradoc/reverse_adoc/converters/tr.rb
-- lib/coradoc/reverse_adoc/converters/video.rb
-- lib/coradoc/reverse_adoc/errors.rb
-- lib/coradoc/reverse_adoc/html_converter.rb
-- lib/coradoc/reverse_adoc/plugin.rb
-- lib/coradoc/reverse_adoc/plugins/plateau.rb
-- lib/coradoc/reverse_adoc/postprocessor.rb
 - lib/coradoc/transformer.rb
+- lib/coradoc/util.rb
 - lib/coradoc/version.rb
 - lib/reverse_adoc.rb
 - todo.md
+- utils/parser_analyzer.rb
+- utils/round_trip.rb
 homepage: https://www.metanorma.org
 licenses:
 - MIT

data/.docker/Makefile

@@ -1,35 +0,0 @@
-export SPEC ?= spec
-SPEC_FILE = $(subst ../,, $(SPEC))
-export RUBY_IMAGE ?= ruby:3.1.2-slim
-
-.PHONY: up
-up:
-	docker-compose up
-
-.PHONY: down
-down:
-	docker-compose down
-
-.PHONY: test
-test: rspec
-
-.PHONY: ssh
-ssh:
-	docker-compose run lib bash
-
-.PHONY: install
-install:
-	docker-compose run lib bin/setup
-
-.PHONY: console
-console:
-	docker-compose run lib bin/console
-
-.PHONY: rspec
-rspec:
-	docker-compose run lib bin/rspec ${SPEC_FILE}
-
-.PHONY: setup
-setup:
-	docker-compose build --build-arg RUBY_IMAGE=${RUBY_IMAGE}
-	docker-compose run lib bin/setup

data/.docker/docker-compose.yml

@@ -1,14 +0,0 @@
-version: "3"
-
-services:
-  lib:
-    build:
-      context: .
-      dockerfile: ./.docker/Dockerfile
-
-    volumes:
-      - .:/workspace:z
-      - bundle:/bundle:z
-
-volumes:
-  bundle:

data/Makefile

@@ -1 +0,0 @@
-.docker/Makefile

data/README.md

@@ -1,73 +0,0 @@
-# Coradoc
-
-Coradoc is a modern Parser for Asciidoc document. It defines a grammar for
-AsciiDoc, and then build the Parser for that grammar.
-
-Once the document is parsed, it provides a pure ruby object `Coradoc::Document`,
-which can used to customize the document in easiest way.
-
-## Installation
-
-Add this line to your application's Gemfile:
-
-```ruby
-gem "coradoc"
-```
-
-And then execute:
-
-```sh
-bundle install
-```
-
-Or install it yourself as:
-
-```sh
-gem install coradoc
-```
-
-## Development
-
-We are following Sandi Metz's Rules for this gem, you can read the
-[description of the rules here][sandi-metz] All new code should follow these
-rules. If you make changes in a pre-existing file that violates these rules you
-should fix the violations as part of your contribution.
-
-### Setup
-
-Clone the repository.
-
-```sh
-git clone https://github.com/metanorma/coradoc.git
-```
-
-Setup your environment in docker
-
-```sh
-make setup
-```
-
-Run the test suite
-
-```sh
-make test
-```
-
-
-## Usages
-
-### Parsing a document
-
-To parse any AsciiDoc, we can use the following:
-
-```ruby
-Coradoc::Parser.parse(sample_asciidoc)
-```
-
-This interface will return the abstract syntax tree.
-
-### Converting from HTML to AsciiDoc (reverse_adoc)
-
-See: [reverse_adoc README](https://github.com/metanorma/coradoc/blob/main/lib/coradoc/reverse_adoc/README.adoc)
-
-[sandi-metz]: http://robots.thoughtbot.com/post/50655960596/sandi-metz-rules-for-developers

data/docker-compose.yml

@@ -1 +0,0 @@
-.docker/docker-compose.yml

data/lib/coradoc/reverse_adoc/config.rb

@@ -1,73 +0,0 @@
-require "tmpdir"
-
-module Coradoc::ReverseAdoc
-  class Config
-    def initialize
-      @unknown_tags     = :pass_through
-      @input_format     = :html
-      @mathml2asciimath = false
-      @external_images  = false
-
-      # Destination to save file and images
-      @destination      = nil
-
-      # Source of HTML
-      # @sourcedir        = nil
-
-      # Image counter, assuming there are max 999 images
-      @image_counter = 1
-      # pad with 0s
-      @image_counter_pattern = "%03d"
-
-      @em_delimiter     = "_".freeze
-      @strong_delimiter = "*".freeze
-      @inline_options   = {}
-      @tag_border       = " ".freeze
-
-      @split_sections   = nil
-
-      # Document width - used to compute table sizes.
-      # This is an assumption for screen size in input document.
-      # If column widths are specified in absolute values, then we
-      # have to convert them to relative values, as AsciiDoc only
-      # supports those.
-      @doc_width        = 1000
-
-      # Plugin system
-      @plugins          = []
-
-      # Debugging options
-      @track_time       = false
-    end
-
-    def with(options = {})
-      old_options = @inline_options
-      @inline_options = options
-      result = yield
-      @inline_options = old_options
-      result
-    end
-
-    def self.declare_option(option)
-      define_method(option) do
-        @inline_options[option] || instance_variable_get(:"@#{option}")
-      end
-
-      attr_writer option
-    end
-
-    declare_option :unknown_tags
-    declare_option :tag_border
-    declare_option :mathml2asciimath
-    declare_option :external_images
-    declare_option :destination
-    declare_option :sourcedir
-    declare_option :image_counter
-    declare_option :image_counter_pattern
-    declare_option :input_format
-    declare_option :split_sections
-    declare_option :doc_width
-    declare_option :plugins
-    declare_option :track_time
-  end
-end

data/lib/coradoc/reverse_adoc/converters.rb

@@ -1,53 +0,0 @@
-module Coradoc::ReverseAdoc
-  module Converters
-    def self.register(tag_name, converter)
-      @@converters ||= {}
-      @@converters[tag_name.to_sym] = converter
-    end
-
-    def self.unregister(tag_name)
-      @@converters.delete(tag_name.to_sym)
-    end
-
-    def self.lookup(tag_name)
-      @@converters[tag_name.to_sym] or default_converter(tag_name)
-    end
-
-    # Note: process won't run plugin hooks
-    def self.process(node, state)
-      node = node.to_a if node.is_a? Nokogiri::XML::NodeSet
-      return node.map { |i| process(i, state) }.join if node.is_a? Array
-
-      lookup(node.name).convert(node, state)
-    end
-
-    def self.process_coradoc(node, state)
-      node = node.to_a if node.is_a? Nokogiri::XML::NodeSet
-      return node.map { |i| process_coradoc(i, state) } if node.is_a? Array
-
-      plugins = state[:plugin_instances] || {}
-      process = proc { lookup(node.name).to_coradoc(node, state) }
-      plugins.each do |i|
-        prev_process = process
-        process = proc { i.html_tree_run_hooks(node, state, &prev_process) }
-      end
-      process.(node, state)
-    end
-
-    def self.default_converter(tag_name)
-      case Coradoc::ReverseAdoc.config.unknown_tags.to_sym
-      when :pass_through
-        Coradoc::ReverseAdoc::Converters::PassThrough.new
-      when :drop
-        Coradoc::ReverseAdoc::Converters::Drop.new
-      when :bypass
-        Coradoc::ReverseAdoc::Converters::Bypass.new
-      when :raise
-        raise UnknownTagError, "unknown tag: #{tag_name}"
-      else
-        raise InvalidConfigurationError,
-              "unknown value #{Coradoc::ReverseAdoc.config.unknown_tags.inspect} for Coradoc::ReverseAdoc.config.unknown_tags"
-      end
-    end
-  end
-end

data/lib/coradoc/reverse_adoc/errors.rb

@@ -1,10 +0,0 @@
-module Coradoc::ReverseAdoc
-  class Error < StandardError
-  end
-
-  class UnknownTagError < Error
-  end
-
-  class InvalidConfigurationError < Error
-  end
-end

data/lib/coradoc/reverse_adoc.rb

@@ -1,30 +0,0 @@
-# frozen_string_literal: true
-
-require "digest"
-require "nokogiri"
-require_relative "../coradoc"
-require_relative "reverse_adoc/errors"
-require_relative "reverse_adoc/cleaner"
-require_relative "reverse_adoc/config"
-require_relative "reverse_adoc/converters"
-require_relative "reverse_adoc/converters/base"
-require_relative "reverse_adoc/html_converter"
-require_relative "reverse_adoc/plugin"
-require_relative "reverse_adoc/postprocessor"
-
-
-module Coradoc::ReverseAdoc
-  def self.convert(input, options = {})
-    Coradoc::ReverseAdoc::HtmlConverter.convert(input, options)
-  end
-
-  def self.config
-    @config ||= Config.new
-    yield @config if block_given?
-    @config
-  end
-
-  def self.cleaner
-    @cleaner ||= Cleaner.new
-  end
-end