reverse_adoc 0.2.4 → 0.2.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 29a6b82d9aba4bb3f581f140c9518a69b97e60a7127c95611333af61e72f8055
-  data.tar.gz: 49995de78b075000a18f4cdc685d42106ca5cc5c1d83730159e310a02cc94680
+  metadata.gz: 906cadff19bcc530a5aa527f3a7cb87bd80050163638ce87d052d3615e82c68d
+  data.tar.gz: ffaf10410be78e4971c80a7c45c946aa4d4803546102b90c0c5bc01342dd962d
 SHA512:
-  metadata.gz: 6be9a00dcb09204d8b0acb6adf0d1ec0b984fe211b02a76e10395989bca38ac96ebbf0f217e4383cb4ede02efa144dd8b8f0acc1d93523ba9d473a28b27b28dc
-  data.tar.gz: d127155eb9d53ac19496a1e3be9bc7185544ee5c61b5e77e1476e6e48572685a1e3b7a36466654e66f84ae01d3434ce0ffc67f202d265b551be02c264cdf6de0
+  metadata.gz: 1436a34f5bd46e9c73d41028562f9edd78970bc5c88acf3cf815c6b76975c228045266c32e6cbc63ffcef3fc9d05101f51de446476f10ace57d565cc306d8629
+  data.tar.gz: 78e5514b5d5e01e5407d12644db5deda0d73e9d62f274932a2dee50de098dd65e36ddd96ef0a523726ec1915d80e42ab847d6227e8d927b5a85e229f53aaff86

data/.github/workflows/macos.yml

@@ -1,26 +1,37 @@
-# 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:
+    paths-ignore:
+      - .github/workflows/ubuntu.yml
+      - .github/workflows/windows.yml
 
 jobs:
   test-macos:
     name: Test on Ruby ${{ matrix.ruby }} macOS
     runs-on: macos-latest
+    continue-on-error: ${{ matrix.experimental }}
     strategy:
+      fail-fast: false
       matrix:
         ruby: [ '2.6', '2.5', '2.4' ]
+        experimental: [false]
+        include:
+          - ruby: '2.7'
+            experimental: true
     steps:
       - uses: actions/checkout@master
       - name: Use Ruby
         uses: actions/setup-ruby@v1
         with:
           ruby-version: ${{ matrix.ruby }}
-          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

@@ -1,26 +1,39 @@
-# 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:
+    paths-ignore:
+      - .github/workflows/macos.yml
+      - .github/workflows/windows.yml
 
 jobs:
   test-linux:
     name: Test on Ruby ${{ matrix.ruby }} Ubuntu
     runs-on: ubuntu-latest
+    continue-on-error: ${{ matrix.experimental }}
     strategy:
+      fail-fast: false
       matrix:
         ruby: [ '2.6', '2.5', '2.4' ]
+        experimental: [false]
+        include:
+          - ruby: '2.7'
+            experimental: true
     steps:
       - uses: actions/checkout@master
       - name: Use Ruby
         uses: actions/setup-ruby@v1
         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

@@ -1,29 +1,43 @@
-# 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:
+    paths-ignore:
+      - .github/workflows/macos.yml
+      - .github/workflows/ubuntu.yml
 
 jobs:
   test-windows:
     name: Test on Ruby ${{ matrix.ruby }} Windows
     runs-on: windows-latest
+    continue-on-error: ${{ matrix.experimental }}
     strategy:
+      fail-fast: false
       matrix:
         ruby: [ '2.6', '2.5', '2.4' ]
+        experimental: [false]
+        include:
+          - ruby: '2.7'
+            experimental: true
     steps:
       - uses: actions/checkout@master
       - name: Use Ruby
         uses: actions/setup-ruby@v1
         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

@@ -1,8 +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
+# Specify your gem's dependencies in reverse_adoc.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
@@ -226,7 +247,7 @@ The gem does not support:
 === MathML support
 
 If you are using this gem in the context of https://www.metanorma.com[Metanorma],
-Metanorma Asciidoctor accepts MathML as a native mathematical format. So you do not need
+Metanorma AsciiDoc accepts MathML as a native mathematical format. So you do not need
 to convert the MathML to AsciiMath.
 
 The gem will optionally invoke the https://github.com/metanorma/mathml2asciimath
@@ -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 AsciiDoc.
+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
 
@@ -251,7 +284,7 @@ Simple to use.
 
 [source,ruby]
 ----
-result = ReverseAsciidoctor.convert input
+result = ReverseAdoc.convert input
 result.inspect # " *feelings* "
 ----
 
@@ -261,7 +294,7 @@ Just pass your chosen configuration options in after the input. The given option
 
 [source,ruby]
 ----
-ReverseAsciidoctor.convert(input, unknown_tags: :raise, mathml2asciimath: true)
+ReverseAdoc.convert(input, unknown_tags: :raise, mathml2asciimath: true)
 ----
 
 
@@ -271,7 +304,7 @@ Or configure it block style on a initializer level. These configurations will la
 
 [source,ruby]
 ----
-ReverseAsciidoctor.config do |config|
+ReverseAdoc.config do |config|
   config.unknown_tags      = :bypass
   config.mathml2asciimath  = true
   config.tag_border  = ''

data/Rakefile

@@ -10,5 +10,5 @@ task :default => :spec
 
 desc 'Open an irb session preloaded with this library'
 task :console do
-  sh 'irb -rubygems -I lib -r reverse_asciidoctor.rb'
+  sh 'irb -rubygems -I lib -r reverse_adoc.rb'
 end

data/bin/reverse_adoc

@@ -1,31 +1,38 @@
 #!/usr/bin/env ruby
-# Usage: reverse_asciidoctor [FILE]...
-# Usage: cat FILE | reverse_asciidoctor
-require 'reverse_asciidoctor'
+# Usage: reverse_adoc [FILE]...
+# Usage: cat FILE | reverse_adoc
+require 'rubygems'
+require 'bundler/setup'
+
+require 'reverse_adoc'
 require 'optparse'
 require 'fileutils'
 
 OptionParser.new do |opts|
   opts.banner = "Usage: reverse_adoc [options] <file>"
   opts.on('-m', '--mathml2asciimath', 'Convert MathML to AsciiMath') do |v|
-    ReverseAsciidoctor.config.mathml2asciimath = true
+    ReverseAdoc.config.mathml2asciimath = true
   end
 
   opts.on('-oFILENAME', '--output=FILENAME', 'Output file to write to') do |v|
-    ReverseAsciidoctor.config.destination = File.expand_path(v)
-    # puts "output goes to #{ReverseAsciidoctor.config.destination}"
+    ReverseAdoc.config.destination = File.expand_path(v)
+    # puts "output goes to #{ReverseAdoc.config.destination}"
   end
 
   opts.on('-e', '--external-images', 'Export images if data URI') do |v|
-    ReverseAsciidoctor.config.external_images = true
+    ReverseAdoc.config.external_images = true
+  end
+
+  opts.on('-f', '--input_format [html, smrl_description]', 'Unknown input format (default: html)') do |v|
+    ReverseAdoc.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
+    ReverseAdoc.config.unknown_tags = v
   end
 
   opts.on('-v', '--version', 'Version information') do |v|
-    puts "reverse_adoc: v#{ReverseAsciidoctor::VERSION}"
+    puts "reverse_adoc: v#{ReverseAdoc::VERSION}"
     exit
   end
 
@@ -38,30 +45,30 @@ end.parse!
 
 if filename = ARGV.pop
   input_content = IO.read(filename)
-  ReverseAsciidoctor.config.sourcedir = File.dirname(File.expand_path(filename))
+  ReverseAdoc.config.sourcedir = File.dirname(File.expand_path(filename))
 else
-  if ReverseAsciidoctor.config.external_images
+  if ReverseAdoc.config.external_images
     raise "The -e | --external-images feature cannot be used with STDIN input. Exiting."
   end
 
   input_content = ARGF.read
 end
 
-if ReverseAsciidoctor.config.external_images && ReverseAsciidoctor.config.destination.nil?
+if ReverseAdoc.config.external_images && ReverseAdoc.config.destination.nil?
   raise "The -e | --external-images feature must be used with -o | --output. Exiting."
 end
 
 # Read from STDIN
-adoc_content = ReverseAsciidoctor.convert(input_content)
+adoc_content = ReverseAdoc.convert(input_content)
 
 # Print to STDOUT
-unless ReverseAsciidoctor.config.destination
+unless ReverseAdoc.config.destination
   puts adoc_content
   exit
 end
 
-# Write output to ReverseAsciidoctor.config.destination
-FileUtils.mkdir_p(File.dirname(ReverseAsciidoctor.config.destination))
-File.open(ReverseAsciidoctor.config.destination, "w") do |file|
+# Write output to ReverseAdoc.config.destination
+FileUtils.mkdir_p(File.dirname(ReverseAdoc.config.destination))
+File.open(ReverseAdoc.config.destination, "w") do |file|
   file.write(adoc_content)
 end

data/bin/w2a

@@ -1,44 +1,32 @@
 #!/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!(/ |\ |\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
-  # 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
+require 'reverse_adoc'
 
 ARGV.push('-h') if ARGV.empty?
 
 OptionParser.new do |opts|
   opts.banner = "Usage: w2a [options] <file>"
   opts.on('-m', '--mathml2asciimath', 'Convert MathML to AsciiMath') do |v|
-    ReverseAsciidoctor.config.mathml2asciimath = true
+    ReverseAdoc.config.mathml2asciimath = true
   end
 
   opts.on('-oFILENAME', '--output=FILENAME', 'Output file to write to') do |v|
-    ReverseAsciidoctor.config.destination = File.expand_path(v)
-    # puts "output goes to #{ReverseAsciidoctor.config.destination}"
+    ReverseAdoc.config.destination = File.expand_path(v)
+    # puts "output goes to #{ReverseAdoc.config.destination}"
   end
 
   opts.on('-e', '--external-images', 'Export images if data URI') do |v|
-    ReverseAsciidoctor.config.external_images = true
+    ReverseAdoc.config.external_images = true
   end
 
   opts.on('-v', '--version', 'Version information') do |v|
-    puts "reverse_adoc: v#{ReverseAsciidoctor::VERSION}"
+    puts "reverse_adoc: v#{ReverseAdoc::VERSION}"
     puts "[dependency] WordToMarkdown: v#{WordToMarkdown::VERSION}"
     unless Gem.win_platform?
       puts "[dependency] LibreOffice: v#{WordToMarkdown.soffice.version}"
@@ -58,28 +46,28 @@ end.parse!
 filename = ARGV.pop
 raise "Please provide an input file to process. Exiting." unless filename
 
-if ReverseAsciidoctor.config.external_images && ReverseAsciidoctor.config.destination.nil?
+if ReverseAdoc.config.external_images && ReverseAdoc.config.destination.nil?
   raise "The -e | --external-images feature must be used with -o | --output. Exiting."
 end
 
-ReverseAsciidoctor.config.sourcedir = Dir.mktmpdir
-# puts "ReverseAsciidoctor.config.sourcedir #{ReverseAsciidoctor.config.sourcedir}"
+ReverseAdoc.config.sourcedir = Dir.mktmpdir
 
-doc = WordToMarkdown.new(filename, ReverseAsciidoctor.config.sourcedir)
-adoc_content = ReverseAsciidoctor.convert(
-  scrub_whitespace(doc.document.html),
+doc = WordToMarkdown.new(filename, ReverseAdoc.config.sourcedir)
+#File.open("test.html", "w:UTF-8") { |f| f.write doc.document.html }
+adoc_content = ReverseAdoc.convert(
+  ReverseAdoc.cleaner.preprocess_word_html(doc.document.html),
   WordToMarkdown::REVERSE_MARKDOWN_OPTIONS
 )
 # puts scrub_whitespace(doc.document.html)
 
 # Print to STDOUT
-unless ReverseAsciidoctor.config.destination
+unless ReverseAdoc.config.destination
   puts adoc_content
   exit
 end
 
-# Write output to ReverseAsciidoctor.config.destination
-FileUtils.mkdir_p(File.dirname(ReverseAsciidoctor.config.destination))
-File.open(ReverseAsciidoctor.config.destination, "w") do |file|
+# Write output to ReverseAdoc.config.destination
+FileUtils.mkdir_p(File.dirname(ReverseAdoc.config.destination))
+File.open(ReverseAdoc.config.destination, "w") do |file|
   file.write(adoc_content)
 end