reverse_adoc 0.2.4 → 0.2.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 29a6b82d9aba4bb3f581f140c9518a69b97e60a7127c95611333af61e72f8055
-  data.tar.gz: 49995de78b075000a18f4cdc685d42106ca5cc5c1d83730159e310a02cc94680
+  metadata.gz: de7821c8ca445117a045f3c2c28ae78f20a2185f61af5de3fff7ed064dd98c3e
+  data.tar.gz: 53151bcdd028e693da6b496df31c7a7da5ffa1dea8b0ee22696011a91fae074a
 SHA512:
-  metadata.gz: 6be9a00dcb09204d8b0acb6adf0d1ec0b984fe211b02a76e10395989bca38ac96ebbf0f217e4383cb4ede02efa144dd8b8f0acc1d93523ba9d473a28b27b28dc
-  data.tar.gz: d127155eb9d53ac19496a1e3be9bc7185544ee5c61b5e77e1476e6e48572685a1e3b7a36466654e66f84ae01d3434ce0ffc67f202d265b551be02c264cdf6de0
+  metadata.gz: 4ae2e50d201e868dc7caa44a599695c6d03f155dd72013888d3cdee5505b074aa37cfc93cfc96435e43fa9bc0096ed46742dd2ff77280957c99cde1ca6454cee
+  data.tar.gz: 8a628ecfe850737831d5f1e10ef30ee65390f9599d7d75f7323de4ca39445c2d873fbaca49db7178b913d696a8fce85c50ce780a7e1715a37a12dce7c4e63cc4

data/README.adoc

@@ -1,9 +1,11 @@
 = 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"]
-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/gem/v/reverse_asciidoctor.svg["Gem Version", link="https://rubygems.org/gems/reverse_asciidoctor"]
+image:https://travis-ci.com/metanorma/reverse_asciidoctor.svg["Build Status", link="https://travis-ci.com/metanorma/reverse_asciidoctor"]
+image:https://ci.appveyor.com/api/projects/status/9dui2fs4pc590f4k?svg=true["Appveyor Build Status", link="https://ci.appveyor.com/project/metanorma/reverse-asciidoctor"]
+image:https://codeclimate.com/github/metanorma/reverse_asciidoctor/badges/gpa.svg["Code Climate", link="https://codeclimate.com/github/metanorma/reverse_asciidoctor"]
+image:https://img.shields.io/github/issues-pr-raw/metanorma/reverse_asciidoctor.svg["Pull Requests", link="https://github.com/metanorma/reverse_asciidoctor/pulls"]
+image:https://img.shields.io/github/commits-since/metanorma/reverse_asciidoctor/latest.svg["Commits since latest",link="https://github.com/metanorma/reverse_asciidoctor/releases"]
 
 == Purpose
 
@@ -92,6 +94,13 @@ 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 +251,18 @@ 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/w2a

@@ -66,6 +66,7 @@ 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),
   WordToMarkdown::REVERSE_MARKDOWN_OPTIONS

data/lib/reverse_asciidoctor/converters/a.rb

@@ -9,10 +9,14 @@ module ReverseAsciidoctor
         title = extract_title(node)
         id = node['id'] || node['name']
 
-        if !id.nil? && !id.empty?
+        id = id&.gsub(/\s/, "")&.gsub(/__+/, "_")
+
+        if /^_Toc\d+$|^_GoBack$/.match id
+          ""
+        elsif !id.nil? && !id.empty?
           "[[#{id}]]"
         elsif href.to_s.start_with?('#')
-            href = href.sub(/^#/, "")
+          href = href.sub(/^#/, "").gsub(/\s/, "").gsub(/__+/, "_")
           if name.empty?
             "<<#{href}>>"
           else

data/lib/reverse_asciidoctor/converters/img.rb

@@ -26,11 +26,15 @@ module ReverseAsciidoctor
         ext = ""
 
         if imgdata
-          file = Tempfile.new(["radoc", ".jpg"]) do |f|
-            f.binmode
-            f.write(Base64.strict_decode64(imgdata))
-            f.rewind
-            ext = MimeMagic.by_magic(f)
+          file = Tempfile.open(["radoc", ".jpg"]) do |f|
+            begin
+              f.binmode
+              f.write(Base64.strict_decode64(imgdata))
+              f.rewind
+              ext = MimeMagic.by_magic(f)
+            ensure
+              f.close!
+            end
           end
 
           image_src_path = file.path

data/lib/reverse_asciidoctor/version.rb

@@ -1,3 +1,3 @@
 module ReverseAsciidoctor
-  VERSION = '0.2.4'
+  VERSION = '0.2.5'
 end

data/spec/assets/anchors.html

@@ -14,6 +14,12 @@
 
     some text...
 
+    <a href="#a__b spaced">Double __ anchor with space</a>
+
+    Double __ anchor with space <a id="a__b spaced"/>
+
+    <a id="_Toc12345"/>
+
     <img src="http://foobar.com/logo.png">
     <img alt="foobar image" src="http://foobar.com/foobar.png">
     <img alt="foobar image 2" title="this is the foobar image 2" src="http://foobar.com/foobar2.png">

data/spec/components/anchors_spec.rb

@@ -18,4 +18,8 @@ describe ReverseAsciidoctor do
   it { is_expected.to include ' link <<content2>>internal jumplinks without anchors ' }
   it { is_expected.to include ' treat [[content]] as bookmarks ' }
 
+  it { is_expected.to include "<<a_bspaced,Double \\_\\_ anchor with space>>" }
+  it { is_expected.to include "[[a_bspaced]]" }
+  it { is_expected.not_to include "[[_Toc12345]]" }
+
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: reverse_adoc
 version: !ruby/object:Gem::Version
-  version: 0.2.4
+  version: 0.2.5
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-10-30 00:00:00.000000000 Z
+date: 2019-11-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri