reverse_adoc 0.2.3 → 0.2.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8003d7dcf58a0561295e898bbcc93ce2c4f6168f5b9e2bcb17791fc183a48d04
-  data.tar.gz: 1229e27b2b00ce61d1004bf3348552b8c3749d3b15f0490c3ab85d63bec94964
+  metadata.gz: eb34effa1c1af2e72ef8df7b6b1553c7c2574bcca9608e02cfaf561ed8a2bfec
+  data.tar.gz: e18b3b9cf2d936a48fdf2e6d5f265aa5c945c9493bd232a4d8fb311df780e81f
 SHA512:
-  metadata.gz: 5e162c8c8a83ca274faed8247ff8fde809118e1a2fa02e3cfaf75f1804d9163d6019ee5bd79a33fe3b2dd00aee2780e8809f2139ffbc118899a8985689feedf8
-  data.tar.gz: d8c715a4ccb49082a832590f89b4b434b1502e1d7c2bcc9539fb0c5b47ddc09afb8b87236a48913ebe8dbecb02f848ffa20d83f9b7f2100bc3ed57355309bb25
+  metadata.gz: ca8454b96ad3064c16018f09198f8450f9a15e6525c1df6e63b7a0e3dd3254f66f2bee56e69e8c7088087962911480513f3608c759f955489b2e602dc2251890
+  data.tar.gz: 49c2198645f22b9ac26ea78aa36e1073a27807dca8364ad076250dccfc6b307055775894962d70d6400d7c8ec6b3dfa02cb31c84c922c60d8c18cbbf5ee55171

data/.github/workflows/macos.yml

@@ -1,14 +1,18 @@
-# Auto-generated !!! Do not edit it manually
-# use ci-master https://github.com/metanorma/metanorma-build-scripts
+# Auto-generated by Cimas: Do not edit it manually!
+# See https://github.com/metanorma/cimas
 name: macos
 
-on: [push]
+on:
+  push:
+    branches: [ master ]
+  pull_request:
 
 jobs:
   test-macos:
     name: Test on Ruby ${{ matrix.ruby }} macOS
     runs-on: macos-latest
     strategy:
+      fail-fast: false
       matrix:
         ruby: [ '2.6', '2.5', '2.4' ]
     steps:
@@ -20,7 +24,7 @@ jobs:
           architecture: 'x64'
       - name: Update gems
         run: |
-          sudo gem install bundler -v "~> 2" --force
+          sudo gem install bundler --force
           bundle install --jobs 4 --retry 3
       - name: Run specs
         run: |

data/.github/workflows/ubuntu.yml

@@ -1,14 +1,18 @@
-# Auto-generated !!! Do not edit it manually
-# use ci-master https://github.com/metanorma/metanorma-build-scripts
+# Auto-generated by Cimas: Do not edit it manually!
+# See https://github.com/metanorma/cimas
 name: ubuntu
 
-on: [push]
+on:
+  push:
+    branches: [ master ]
+  pull_request:
 
 jobs:
   test-linux:
     name: Test on Ruby ${{ matrix.ruby }} Ubuntu
     runs-on: ubuntu-latest
     strategy:
+      fail-fast: false
       matrix:
         ruby: [ '2.6', '2.5', '2.4' ]
     steps:
@@ -18,9 +22,11 @@ jobs:
         with:
           ruby-version: ${{ matrix.ruby }}
           architecture: 'x64'
+      - name: Install LibreOffice
+        run: sudo apt-get -y --no-install-recommends install libreoffice
       - name: Update gems
         run: |
-          gem install bundler -v "~> 2"
+          gem install bundler
           bundle install --jobs 4 --retry 3
       - name: Run specs
         run: |

data/.github/workflows/windows.yml

@@ -1,14 +1,18 @@
-# Auto-generated !!! Do not edit it manually
-# use ci-master https://github.com/metanorma/metanorma-build-scripts
+# Auto-generated by Cimas: Do not edit it manually!
+# See https://github.com/metanorma/cimas
 name: windows
 
-on: [push]
+on:
+  push:
+    branches: [ master ]
+  pull_request:
 
 jobs:
   test-windows:
     name: Test on Ruby ${{ matrix.ruby }} Windows
     runs-on: windows-latest
     strategy:
+      fail-fast: false
       matrix:
         ruby: [ '2.6', '2.5', '2.4' ]
     steps:
@@ -18,12 +22,15 @@ jobs:
         with:
           ruby-version: ${{ matrix.ruby }}
           architecture: 'x64'
+      - name: Install LibreOffice
+        run: |
+          choco install libreoffice-still
+          echo "::add-path::C:\Program Files\LibreOffice\program"
       - name: Update gems
         shell: pwsh
         run: |
-          gem install bundler -v "~> 2"
+          gem install bundler
           bundle config --local path vendor/bundle
-          bundle update
           bundle install --jobs 4 --retry 3
       - name: Run specs
         run: |

data/Gemfile

@@ -1,6 +1,8 @@
 source "https://rubygems.org"
-  
+
 git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
 
 # Specify your gem's dependencies in reverse_asciidoctor.gemspec
 gemspec
+
+gem "byebug"

data/Gemfile.lock

@@ -0,0 +1,84 @@
+PATH
+  remote: .
+  specs:
+    reverse_adoc (0.2.8)
+      mathml2asciimath
+      mimemagic
+      nokogiri (>= 1.10.4)
+      word-to-markdown
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    addressable (2.7.0)
+      public_suffix (>= 2.0.2, < 5.0)
+    byebug (11.1.1)
+    cliver (0.3.2)
+    codeclimate-test-reporter (1.0.7)
+      simplecov
+    css_parser (1.7.1)
+      addressable
+    descriptive_statistics (2.5.1)
+    diff-lcs (1.3)
+    docile (1.3.2)
+    ffi (1.13.1)
+    htmlentities (4.3.4)
+    mathml2asciimath (0.0.10)
+      htmlentities (~> 4.3.4)
+      nokogiri (>= 1.10.4)
+    mimemagic (0.3.5)
+    mini_portile2 (2.4.0)
+    nokogiri (1.10.9)
+      mini_portile2 (~> 2.4.0)
+    nokogiri-styles (0.1.2)
+      nokogiri
+    premailer (1.11.1)
+      addressable
+      css_parser (>= 1.6.0)
+      htmlentities (>= 4.0.0)
+    public_suffix (4.0.5)
+    rake (13.0.1)
+    redcarpet (3.5.0)
+    reverse_markdown (1.4.0)
+      nokogiri
+    rspec (3.9.0)
+      rspec-core (~> 3.9.0)
+      rspec-expectations (~> 3.9.0)
+      rspec-mocks (~> 3.9.0)
+    rspec-core (3.9.1)
+      rspec-support (~> 3.9.1)
+    rspec-expectations (3.9.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.9.0)
+    rspec-mocks (3.9.1)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.9.0)
+    rspec-support (3.9.2)
+    simplecov (0.18.5)
+      docile (~> 1.1)
+      simplecov-html (~> 0.11)
+    simplecov-html (0.12.1)
+    sys-proctable (1.2.5)
+      ffi
+    word-to-markdown (1.1.8)
+      cliver (~> 0.3)
+      descriptive_statistics (~> 2.5)
+      nokogiri-styles (~> 0.1)
+      premailer (~> 1.8)
+      reverse_markdown (~> 1.0)
+      sys-proctable (~> 1.0)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  byebug
+  codeclimate-test-reporter
+  rake
+  redcarpet
+  reverse_adoc!
+  rspec
+  simplecov
+
+BUNDLED WITH
+   2.0.2

data/README.adoc

@@ -1,9 +1,12 @@
 = AsciiDoc from HTML and Microsoft Word: reverse_adoc
 
-image:https://img.shields.io/gem/v/reverse_adoc.svg["Gem Version", link="https://rubygems.org/gems/reverse_adoc"]
-image:https://img.shields.io/travis/metanorma/reverse_adoc/master.svg["Build Status", link="https://travis-ci.org/metanorma/reverse_adoc"]
+https://github.com/metanorma/reverse_adoc[reverse_adoc] image:https://img.shields.io/gem/v/reverse_adoc.svg["Gem Version", link="https://rubygems.org/gems/reverse_adoc"]::
+image:https://github.com/metanorma/reverse_adoc/workflows/macos/badge.svg["Build Status", link="https://github.com/metanorma/reverse_adoc/actions?workflow=macos"]
+image:https://github.com/metanorma/reverse_adoc/workflows/windows/badge.svg["Build Status", link="https://github.com/metanorma/reverse_adoc/actions?workflow=windows"]
+image:https://github.com/metanorma/reverse_adoc/workflows/ubuntu/badge.svg["Build Status", link="https://github.com/metanorma/reverse_adoc/actions?workflow=ubuntu"]
 image:https://codeclimate.com/github/metanorma/reverse_adoc/badges/gpa.svg["Code Climate", link="https://codeclimate.com/github/metanorma/reverse_adoc"]
-image:https://ci.appveyor.com/api/projects/status/s4st0ft8moay90m6?svg=true["Appveyor Build Status", link="https://ci.appveyor.com/project/ribose/reverse-asciidoctor"]
+image:https://img.shields.io/github/issues-pr-raw/metanorma/reverse_adoc.svg["Pull Requests", link="https://github.com/metanorma/reverse_adoc/pulls"]
+image:https://img.shields.io/github/commits-since/metanorma/reverse_adoc/latest.svg["Commits since latest",link="https://github.com/metanorma/reverse_adoc/releases"]
 
 == Purpose
 
@@ -41,10 +44,21 @@ $ reverse_adoc file.html > file.adoc
 $ cat file.html | reverse_adoc > file.adoc
 ----
 
+=== XML smrl description to AsciiDoc: `reverse_adoc`
+
+Convert XML smrl description files to AsciiDoc:
+
+[source,console]
+----
+$ reverse_adoc -f smrl_description descriptions.xml > file.adoc
+$ cat descriptions.xml | reverse_adoc -f smrl_description > file.adoc
+----
+
 [source,console]
 ----
 $ reverse_adoc -h
 Usage: reverse_adoc [options] <file>
+    -f, --input_format               Supply input format to choose converter(html or smrl_description)
     -m, --mathml2asciimath           Convert MathML to AsciiMath
     -o, --output=FILENAME            Output file to write to
     -e, --external-images            Export images if data URI
@@ -92,6 +106,13 @@ document, and it may not cope with ordered lists or headings with customised app
 For best results, reset the styles in the document you're converting to those in
 the default `Normal.dot` template.
 
+NOTE: `w2a` requires the command-line version of LibreOffice, `soffice`. As it turns out,
+LibreOffice v6 appears to render formulae in HTML as images instead of MathML expressions;
+use LibreOffice v5. If you have both LibreOffice v5 and LibreOffice v6 installed, make sure
+that your OS path searches for the LibreOffice v5 version of `soffice` first; e.g. on Mac,
+include something like `/Applications/LibreOffice5.4.7.2.app/Contents/MacOS` in your PATH
+environment.
+
 NOTE: Some information in OOMML is not preserved in the export to MathML from LibreOffice;
 in particular, font shifts such as double-struck fonts.
 The LibreOffice exporter does seem to drop some text (possibly associated with
@@ -242,6 +263,18 @@ AsciiMath, and fail. But of course, MathJax has no problem with MathML, and some
 on the Asciidoctor output can ensure that the MathML is treated by MathJax (or whatever else
 uses the output) as such; so this is still much better than nothing for stem processing.
 
+=== Word cleanup
+
+This gem is routinely used in the Metanorma project to export Word documents to Asciidoctor.
+The HTML export from Word that the gem uses, from LibreOffice, is much cleaner than the
+native HTML 4 export from Word; but it has some infelicities which this gem cleans up:
+
+* The HTML export has trouble with subscripts, and routinely exports them as headings; the `w2a`
+script tries to clean them up.
+* The `w2a` cleans up spaces, but it does not strip them.
+* Spaces are removed from anchors and cross-references.
+* Double underscores are removed from anchors and cross-references.
+* Cross-references to `_GoBack` and to `_Toc` followed by numbers (used to construct tables of contents) are ignored.
 
 == Ruby library usage
 

data/bin/reverse_adoc

@@ -1,6 +1,9 @@
 #!/usr/bin/env ruby
 # Usage: reverse_asciidoctor [FILE]...
 # Usage: cat FILE | reverse_asciidoctor
+require 'rubygems'
+require 'bundler/setup'
+
 require 'reverse_asciidoctor'
 require 'optparse'
 require 'fileutils'
@@ -20,6 +23,10 @@ OptionParser.new do |opts|
     ReverseAsciidoctor.config.external_images = true
   end
 
+  opts.on('-f', '--input_format [html, smrl_description]', 'Unknown input format (default: html)') do |v|
+    ReverseAsciidoctor.config.input_format = v
+  end
+
   opts.on('-u', '--unknown_tags [pass_through, drop, bypass, raise]', 'Unknown tag handling (default: pass_through)') do |v|
     ReverseAsciidoctor.config.unknown_tags = v
   end

data/bin/w2a

@@ -1,25 +1,13 @@
 #!/usr/bin/env ruby
 # frozen_string_literal: true
 
+require 'rubygems'
+require 'bundler/setup'
+
 require 'word-to-markdown'
 require 'optparse'
 require 'reverse_asciidoctor'
 
-def scrub_whitespace(string)
-  string = string.dup
-  string.gsub!(' ', ' ')       # HTML encoded spaces
-  string.sub!(/\A[[:space:]]+/, '') # document leading whitespace
-  string.sub!(/[[:space:]]+\z/, '') # document trailing whitespace
-  string.gsub!(/([ ]+)$/, '')       # line trailing whitespace
-  string.gsub!(/\n\n\n\n/, "\n\n")  # Quadruple line breaks
-  string.delete!(' ')               # Unicode non-breaking spaces, injected as tabs
-  # following added by me
-  string.gsub!(%r{<h[1-9][^>]*></h1>}, " ") # I don't know why Libre Office is inserting them, but they need to go
-  string.gsub!(%r{<h1[^>]* style="vertical-align: super;[^>]*>([^<]+)</h1>},
-              "<sup>\\1</sup>")         # I absolutely don't know why Libre Office is rendering superscripts as h1
-  string
-end
-
 ARGV.push('-h') if ARGV.empty?
 
 OptionParser.new do |opts|
@@ -63,11 +51,11 @@ if ReverseAsciidoctor.config.external_images && ReverseAsciidoctor.config.destin
 end
 
 ReverseAsciidoctor.config.sourcedir = Dir.mktmpdir
-# puts "ReverseAsciidoctor.config.sourcedir #{ReverseAsciidoctor.config.sourcedir}"
 
 doc = WordToMarkdown.new(filename, ReverseAsciidoctor.config.sourcedir)
+#File.open("test.html", "w:UTF-8") { |f| f.write doc.document.html }
 adoc_content = ReverseAsciidoctor.convert(
-  scrub_whitespace(doc.document.html),
+  ReverseAsciidoctor.cleaner.preprocess_word_html(doc.document.html),
   WordToMarkdown::REVERSE_MARKDOWN_OPTIONS
 )
 # puts scrub_whitespace(doc.document.html)

data/lib/reverse_asciidoctor.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require 'digest'
 require 'nokogiri'
 require 'reverse_asciidoctor/version'
@@ -6,55 +8,14 @@ require 'reverse_asciidoctor/cleaner'
 require 'reverse_asciidoctor/config'
 require 'reverse_asciidoctor/converters'
 require 'reverse_asciidoctor/converters/base'
-require 'reverse_asciidoctor/converters/a'
-require 'reverse_asciidoctor/converters/aside'
-require 'reverse_asciidoctor/converters/audio'
-require 'reverse_asciidoctor/converters/blockquote'
-require 'reverse_asciidoctor/converters/br'
-require 'reverse_asciidoctor/converters/bypass'
-require 'reverse_asciidoctor/converters/code'
-require 'reverse_asciidoctor/converters/div'
-require 'reverse_asciidoctor/converters/drop'
-require 'reverse_asciidoctor/converters/em'
-require 'reverse_asciidoctor/converters/figure'
-require 'reverse_asciidoctor/converters/h'
-require 'reverse_asciidoctor/converters/head'
-require 'reverse_asciidoctor/converters/hr'
-require 'reverse_asciidoctor/converters/ignore'
-require 'reverse_asciidoctor/converters/img'
-require 'reverse_asciidoctor/converters/mark'
-require 'reverse_asciidoctor/converters/li'
-require 'reverse_asciidoctor/converters/ol'
-require 'reverse_asciidoctor/converters/p'
-require 'reverse_asciidoctor/converters/pass_through'
-require 'reverse_asciidoctor/converters/pre'
-require 'reverse_asciidoctor/converters/q'
-require 'reverse_asciidoctor/converters/strong'
-require 'reverse_asciidoctor/converters/sup'
-require 'reverse_asciidoctor/converters/sub'
-require 'reverse_asciidoctor/converters/table'
-require 'reverse_asciidoctor/converters/td'
-require 'reverse_asciidoctor/converters/th'
-require 'reverse_asciidoctor/converters/text'
-require 'reverse_asciidoctor/converters/tr'
-require 'reverse_asciidoctor/converters/video'
-require 'reverse_asciidoctor/converters/math'
 
 module ReverseAsciidoctor
-
   def self.convert(input, options = {})
-    root = case input
-      when String                  then Nokogiri::HTML(input).root
-      when Nokogiri::XML::Document then input.root
-      when Nokogiri::XML::Node     then input
-    end
-
-    root or return ''
-
-    config.with(options) do
-      result = ReverseAsciidoctor::Converters.lookup(root.name).convert(root)
-      cleaner.tidy(result)
-    end
+    type = config.input_format
+    name = "#{type}_converter"
+    require "reverse_asciidoctor/#{type}_converter"
+    constant = name.split('_').map(&:capitalize).join.to_s
+    ReverseAsciidoctor.const_get(constant).convert(input, options)
   end
 
   def self.config
@@ -66,5 +27,4 @@ module ReverseAsciidoctor
   def self.cleaner
     @cleaner ||= Cleaner.new
   end
-
 end

data/lib/reverse_asciidoctor/cleaner.rb

@@ -64,6 +64,29 @@ module ReverseAsciidoctor
       string.gsub(/(\*\*|~~|__)\s([\.!\?'"])/, "\\1".strip + "\\2")
     end
 
+     # preprocesses HTML, rather than postprocessing it
+    def preprocess_word_html(string)
+      clean_headings(scrub_whitespace(string.dup))
+    end
+
+    def scrub_whitespace(string)
+      string.gsub!(/ |\ |\u00a0/i, ' ')       # HTML encoded spaces
+      string.sub!(/^\A[[:space:]]+/m, '') # document leading whitespace
+      string.sub!(/[[:space:]]+\z$/m, '') # document trailing whitespace
+      string.gsub!(/([ ]+)$/, ' ')       # line trailing whitespace
+      string.gsub!(/\n\n\n\n/, "\n\n")  # Quadruple line breaks
+      #string.delete!('?| ')               # Unicode non-breaking spaces, injected as tabs
+      string
+    end
+
+    # following added by me
+    def clean_headings(string)
+      string.gsub!(%r{<h([1-9])[^>]*></h\1>}, " ") # I don't know why Libre Office is inserting them, but they need to go
+      string.gsub!(%r{<h([1-9])[^>]* style="vertical-align: super;[^>]*>(.+?)</h\1>},
+                   "<sup>\\2</sup>")         # I absolutely don't know why Libre Office is rendering superscripts as h1
+      string
+    end
+
     private
 
     def preserve_border_whitespaces(string, options = {}, &block)