html2doc 1.4.2.1 → 1.4.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8c9737d99ed7f4eaa814bd07e97e5b11b54f1f27a07c628b97e21216b9a3a816
-  data.tar.gz: 7778c03a49a8223a873f139fda9722a451700d6c39df1003dde40bf8cb8e6bfb
+  metadata.gz: '0519bc0cdea11bd73e5ef3c07236793fc46ade0f08e7c36258e8fe0918808907'
+  data.tar.gz: 919f5ee2632c524b30a72f5eb9f1c647c386eda1946aab89ea7f74e603e90aa1
 SHA512:
-  metadata.gz: b9b0479132c6115e69449fec5797c3e30007790940c9530f59cb74c5bf8598f1d01b6c180c42a9bc87880c86636cf9719f4e704036f2afe8adb264312867d1eb
-  data.tar.gz: 616429b25b5cd9d59db066f5085fb19a5d79d308d38cb0f4360ec66e85a3dc1163d5707de433155226e72cb86b065dbe03e9e07c9f1eb6dae66300a0169846e5
+  metadata.gz: 1c3c6b592ebff133758628ef1cd664a9c7e13390bd63551026c785992f0c6ae770d7593aa5052477e1aa08fedd033d749056857a9bb73b1e5babd4aa2e657ff4
+  data.tar.gz: 907db4fb0ae7c64168c5b8436b1d2162591f05d9785928cb393d5e7ea4e7fddc086c96534a81e5d3f42df1c048df5c00b313e08f96dbb91a88b0dd95d3ee6774

data/html2doc.gemspec

@@ -20,9 +20,11 @@ Gem::Specification.new do |spec|
 
   spec.bindir        = "bin"
   spec.require_paths = ["lib"]
-  spec.files         = `git ls-files`.split("\n")
-  spec.test_files    = `git ls-files -- {spec}/*`.split("\n")
-  spec.required_ruby_version = Gem::Requirement.new(">= 2.5.0")
+  spec.files         = `git ls-files -z`.split("\x0").reject do |f|
+    f.match(%r{^(test|spec|features|bin|.github)/}) \
+    || f.match(%r{Rakefile|bin/rspec})
+  end
+  spec.required_ruby_version = Gem::Requirement.new(">= 2.7.0")
 
   spec.add_dependency "asciimath", "~> 2.0.2"
   spec.add_dependency "htmlentities", "~> 4.3.4"

data/lib/html2doc/base.rb

@@ -15,6 +15,7 @@ class Html2Doc
     @debug = hash[:debug]
     @liststyles = hash[:liststyles]
     @stylesheet = hash[:stylesheet]
+    @c = HTMLEntities.new
     @xsltemplate =
       Nokogiri::XSLT(File.read(File.join(File.dirname(__FILE__), "mml2omml.xsl"),
                                encoding: "utf-8"))
@@ -49,7 +50,7 @@ class Html2Doc
   def create_dir(filename, dir)
     dir and return clear_dir(dir)
     dir = "#{filename}_files"
-    Dir.mkdir(dir) unless File.exists?(dir)
+    FileUtils.mkdir_p(dir)
     clear_dir(dir)
   end
 

data/lib/html2doc/math.rb

@@ -5,24 +5,26 @@ require "nokogiri"
 require "plane1converter"
 
 class Html2Doc
-  def asciimath_to_mathml1(expr)
-    AsciiMath::MathMLBuilder.new(msword: true).append_expression(
-      AsciiMath.parse(HTMLEntities.new.decode(expr)).ast,
-    ).to_s
-      .gsub(/<math>/, "<math xmlns='http://www.w3.org/1998/Math/MathML'>")
+  def asciimath_to_mathml1(expr, retain_asciimath)
+    ret = AsciiMath::MathMLBuilder.new(msword: true).append_expression(
+      AsciiMath.parse(@c.decode(expr)).ast,
+    ).to_s.gsub(/<math>/, "<math xmlns='http://www.w3.org/1998/Math/MathML'>")
+    retain_asciimath and
+      ret += "<asciimath>#{@c.encode(@c.decode(expr), :basic)}</asciimath>"
+    ret
   rescue StandardError => e
     puts "parsing: #{expr}"
     puts e.message
     raise e
   end
 
-  def asciimath_to_mathml(doc, delims)
+  def asciimath_to_mathml(doc, delims, retain_asciimath: false)
     return doc if delims.nil? || delims.size < 2
 
     m = doc.split(/(#{Regexp.escape(delims[0])}|#{Regexp.escape(delims[1])})/)
     m.each_slice(4).map.with_index do |(*a), i|
       progress_conv(i, 500, (m.size / 4).floor, 1000, "AsciiMath")
-      a[2].nil? || a[2] = asciimath_to_mathml1(a[2])
+      a[2].nil? or a[2] = asciimath_to_mathml1(a[2], retain_asciimath)
       a.size > 1 ? a[0] + a[2] : a[0]
     end.join
   end
@@ -122,7 +124,7 @@ class Html2Doc
     xml.traverse do |n|
       next unless n.text?
 
-      n.replace(Plane1Converter.conv(HTMLEntities.new.decode(n.text), font))
+      n.replace(Plane1Converter.conv(@c.decode(n.text), font))
     end
     xml
   end

data/lib/html2doc/mime.rb

@@ -67,22 +67,23 @@ class Html2Doc
   end
 
   def contentid(mhtml)
-    mhtml.gsub %r{(<img[^>]*?src=")([^\"']+)(['"])}m do |m|
+    mhtml.gsub %r{(<img[^>]*?src=")([^"']+)(['"])}m do |m|
       repl = "#{$1}cid:#{File.basename($2)}#{$3}"
-      /^data:|^https?:/.match($2) ? m : repl
-    end.gsub %r{(<v:imagedata[^>]*?src=")([^\"']+)(['"])}m do |m|
+      /^data:|^https?:/ =~ $2 ? m : repl
+    end.gsub %r{(<v:imagedata[^>]*?src=")([^"']+)(['"])}m do |m|
       repl = "#{$1}cid:#{File.basename($2)}#{$3}"
-      /^data:|^https?:/.match($2) ? m : repl
+      /^data:|^https?:/ =~ $2 ? m : repl
     end
   end
 
   # max width for Word document is 400, max height is 680
   def image_resize(img, path, maxheight, maxwidth)
-    realsize = ImageSize.path(path).size
-    s = [img["width"].to_i, img["height"].to_i]
-    s = realsize if s[0].zero? && s[1].zero?
-    return [nil, nil] if realsize.nil? || realsize[0].nil? || realsize[1].nil?
+    s, realsize = get_image_size(img, path)
+    return s if s[0] == nil && s[1] == nil
 
+    if img.name == "svg" && !img["viewBox"]
+      img["viewBox"] = "0 0 #{s[0]} #{s[1]}"
+    end
     s[1] = s[0] * realsize[1] / realsize[0] if s[1].zero? && !s[0].zero?
     s[0] = s[1] * realsize[0] / realsize[1] if s[0].zero? && !s[1].zero?
     s = [(s[0] * maxheight / s[1]).ceil, maxheight] if s[1] > maxheight
@@ -90,6 +91,16 @@ class Html2Doc
     s
   end
 
+  def get_image_size(img, path)
+    realsize = ImageSize.path(path).size # does not support emf
+    s = [img["width"].to_i, img["height"].to_i]
+    return [s, s] if /\.emf$/.match?(path)
+
+    s = realsize if s[0].zero? && s[1].zero?
+    s = [nil, nil]  if realsize.nil? || realsize[0].nil? || realsize[1].nil?
+    [s, realsize]
+  end
+
   IMAGE_PATH = "//*[local-name() = 'img' or local-name() = 'imagedata']".freeze
 
   def mkuuid

data/lib/html2doc/version.rb

@@ -1,3 +1,3 @@
 class Html2Doc
-  VERSION = "1.4.2.1".freeze
+  VERSION = "1.4.4".freeze
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html2doc
 version: !ruby/object:Gem::Version
-  version: 1.4.2.1
+  version: 1.4.4
 platform: ruby
 authors:
 - Ribose Inc.
-autorequire:
+autorequire: 
 bindir: bin
 cert_chain: []
-date: 2022-07-04 00:00:00.000000000 Z
+date: 2022-11-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: asciimath
@@ -273,7 +273,6 @@ extensions: []
 extra_rdoc_files: []
 files:
 - ".gitattributes"
-- ".github/workflows/rake.yml"
 - ".gitignore"
 - ".hound.yml"
 - ".oss-guides.rubocop.yml"
@@ -283,11 +282,6 @@ files:
 - Gemfile
 - LICENSE
 - README.adoc
-- Rakefile
-- bin/console
-- bin/html2doc
-- bin/rspec
-- bin/setup
 - html2doc.gemspec
 - lib/html2doc.rb
 - lib/html2doc/base.rb
@@ -298,28 +292,12 @@ files:
 - lib/html2doc/notes.rb
 - lib/html2doc/version.rb
 - lib/html2doc/wordstyle.css
-- spec/19160-6.png
-- spec/19160-7.gif
-- spec/19160-8.jpg
-- spec/examples/header.html
-- spec/examples/rice.doc
-- spec/examples/rice.html
-- spec/examples/rice_images/rice_image1.gif
-- spec/examples/rice_images/rice_image1.png
-- spec/examples/rice_images/rice_image2.png
-- spec/examples/rice_images/rice_image3_1.png
-- spec/examples/rice_images/rice_image3_2.png
-- spec/examples/rice_images/rice_image3_3.png
-- spec/header.html
-- spec/header_img.html
-- spec/html2doc_spec.rb
-- spec/spec_helper.rb
 homepage: https://github.com/metanorma/html2doc
 licenses:
 - CC-BY-SA-3.0
 - BSD-2-Clause
 metadata: {}
-post_install_message:
+post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
@@ -327,15 +305,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.5.0
+      version: 2.7.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.16
-signing_key:
+rubygems_version: 3.1.6
+signing_key: 
 specification_version: 4
 summary: Convert HTML document to Microsoft Word document
 test_files: []

data/.github/workflows/rake.yml

@@ -1,15 +0,0 @@
-# Auto-generated by Cimas: Do not edit it manually!
-# See https://github.com/metanorma/cimas
-name: rake
-
-on:
-  push:
-    branches: [ master, main ]
-    tags: [ v* ]
-  pull_request:
-
-jobs:
-  rake:
-    uses: metanorma/metanorma-build-scripts/.github/workflows/generic-rake.yml@main
-    secrets:
-      pat_token: ${{ secrets.METANORMA_CI_PAT_TOKEN }}

data/Rakefile

@@ -1,6 +0,0 @@
-require "bundler/gem_tasks"
-require "rspec/core/rake_task"
-
-RSpec::Core::RakeTask.new(:spec)
-
-task default: :spec

data/bin/console

@@ -1,14 +0,0 @@
-#!/usr/bin/env ruby
-
-require "bundler/setup"
-require "html2doc"
-
-# You can add fixtures and/or initialization code here to make experimenting
-# with your gem easier. You can also use a different console, if you like.
-
-# (If you use this, don't forget to add pry to your Gemfile!)
-# require "pry"
-# Pry.start
-
-require "irb"
-IRB.start(__FILE__)

data/bin/html2doc

@@ -1,27 +0,0 @@
-#!/usr/bin/env ruby
-
-require "html2doc"
-require "optparse"
-
-options = {}
-OptionParser.new do |opts|
-  opts.banner = "Usage: bin/html2doc filename [options]"
-
-  opts.on("--stylesheet FILE.CSS", "Use the provided stylesheet") do |v|
-    options[:stylesheet] = v
-  end
-  opts.on("--header HEADER.HTML", "Use the provided stylesheet") do |v|
-    options[:header] = v
-  end
-end.parse!
-
-if ARGV.length < 1
-  puts "Usage: bin/html2doc filename [options]"
-  exit
-end
-
-Html2Doc.process(
-  filename: ARGV[0].gsub(/\.html?$/, ""),
-  stylesheet: options[:stylesheet],
-  header: options[:header],
-).process(File.read(ARGV[0], encoding: "utf-8"))

data/bin/rspec

@@ -1,18 +0,0 @@
-#!/usr/bin/env ruby
-
-# This file was generated by Bundler.
-#
-# The application 'rspec' is installed as part of a gem, and
-# this file is here to facilitate running it.
-#
-
-require "pathname"
-ENV["BUNDLE_GEMFILE"] ||= File.expand_path(
-  "../../Gemfile", Pathname.new(__FILE__).realpath
-)
-
-require "rubygems"
-require "bundler/setup"
-
-load Gem.bin_path("rspec-core", "rspec")
-

data/bin/setup

@@ -1,8 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-IFS=$'\n\t'
-set -vx
-
-bundle install
-
-# Do any other automated setup that you need to do here

data/spec/examples/header.html

@@ -1,184 +0,0 @@
-<html xmlns:v="urn:schemas-microsoft-com:vml"
-xmlns:o="urn:schemas-microsoft-com:office:office"
-xmlns:w="urn:schemas-microsoft-com:office:word"
-xmlns:m="http://schemas.microsoft.com/office/2004/12/omml"
-xmlns:mv="http://macVmlSchemaUri" xmlns="http://www.w3.org/TR/REC-html40">
-
-<head>
-<meta name=Title content="">
-<meta name=Keywords content="">
-<meta http-equiv=Content-Type content="text/html; charset=utf-8">
-<meta name=ProgId content=Word.Document>
-<meta name=Generator content="Microsoft Word 15">
-<meta name=Originator content="Microsoft Word 15">
-<link id=Main-File rel=Main-File href="../rice.html">
-<!--[if gte mso 9]><xml>
- <o:shapedefaults v:ext="edit" spidmax="2049"/>
-</xml><![endif]-->
-</head>
-
-<body lang=EN link=blue vlink="#954F72">
-
-<div style='mso-element:footnote-separator' id=fs>
-
-<p class=MsoNormal style='margin-bottom:0cm;margin-bottom:.0001pt;line-height:
-normal'><span lang=EN-GB><span style='mso-special-character:footnote-separator'><![if !supportFootnotes]>
-
-<hr align=left size=1 width="33%">
-
-<![endif]></span></span></p>
-
-</div>
-
-<div style='mso-element:footnote-continuation-separator' id=fcs>
-
-<p class=MsoNormal style='margin-bottom:0cm;margin-bottom:.0001pt;line-height:
-normal'><span lang=EN-GB><span style='mso-special-character:footnote-continuation-separator'><![if !supportFootnotes]>
-
-<hr align=left size=1>
-
-<![endif]></span></span></p>
-
-</div>
-
-<div style='mso-element:endnote-separator' id=es>
-
-<p class=MsoNormal style='margin-bottom:0cm;margin-bottom:.0001pt;line-height:
-normal'><span lang=EN-GB><span style='mso-special-character:footnote-separator'><![if !supportFootnotes]>
-
-<hr align=left size=1 width="33%">
-
-<![endif]></span></span></p>
-
-</div>
-
-<div style='mso-element:endnote-continuation-separator' id=ecs>
-
-<p class=MsoNormal style='margin-bottom:0cm;margin-bottom:.0001pt;line-height:
-normal'><span lang=EN-GB><span style='mso-special-character:footnote-continuation-separator'><![if !supportFootnotes]>
-
-<hr align=left size=1>
-
-<![endif]></span></span></p>
-
-</div>
-
-<div style='mso-element:header' id=eh1>
-
-<p class=MsoHeader align=left style='text-align:left;line-height:12.0pt;
-mso-line-height-rule:exactly'><span lang=EN-GB>ISO/IEC&nbsp;CD 17301-1:2016(E)</span></p>
-
-</div>
-
-<div style='mso-element:header' id=h1>
-
-<p class=MsoHeader style='margin-bottom:18.0pt'><span lang=EN-GB
-style='font-size:10.0pt;mso-bidi-font-size:11.0pt;font-weight:normal'>©
-ISO/IEC&nbsp;2016&nbsp;– All rights reserved</span><span lang=EN-GB
-style='font-weight:normal'><o:p></o:p></span></p>
-
-</div>
-
-<div style='mso-element:footer' id=ef1>
-
-<p class=MsoFooter style='margin-top:12.0pt;line-height:12.0pt;mso-line-height-rule:
-exactly'><!--[if supportFields]><b style='mso-bidi-font-weight:normal'><span
-lang=EN-GB style='font-size:10.0pt;mso-bidi-font-size:11.0pt'><span
-style='mso-element:field-begin'></span><span
-style='mso-spacerun:yes'> </span>PAGE<span style='mso-spacerun:yes'>  
-</span>\* MERGEFORMAT <span style='mso-element:field-separator'></span></span></b><![endif]--><b
-style='mso-bidi-font-weight:normal'><span lang=EN-GB style='font-size:10.0pt;
-mso-bidi-font-size:11.0pt'><span style='mso-no-proof:yes'>2</span></span></b><!--[if supportFields]><b
-style='mso-bidi-font-weight:normal'><span lang=EN-GB style='font-size:10.0pt;
-mso-bidi-font-size:11.0pt'><span style='mso-element:field-end'></span></span></b><![endif]--><span
-lang=EN-GB style='font-size:10.0pt;mso-bidi-font-size:11.0pt'><span
-style='mso-tab-count:1'>                                                                                                                                                                           </span>©
-ISO/IEC&nbsp;2016&nbsp;– All rights reserved<o:p></o:p></span></p>
-
-</div>
-
-<div style='mso-element:header' id=eh2>
-
-<p class=MsoHeader align=left style='text-align:left;line-height:12.0pt;
-mso-line-height-rule:exactly'><span lang=EN-GB>ISO/IEC&nbsp;CD 17301-1:2016(E)</span></p>
-
-</div>
-
-<div style='mso-element:header' id=h2>
-
-<p class=MsoHeader align=right style='text-align:right;line-height:12.0pt;
-mso-line-height-rule:exactly'><span lang=EN-GB>ISO/IEC&nbsp;CD 17301-1:2016(E)</span></p>
-
-</div>
-
-<div style='mso-element:footer' id=ef2>
-
-<p class=MsoFooter style='line-height:12.0pt;mso-line-height-rule:exactly'><!--[if supportFields]><span
-lang=EN-GB style='font-size:10.0pt;mso-bidi-font-size:11.0pt'><span
-style='mso-element:field-begin'></span><span
-style='mso-spacerun:yes'> </span>PAGE<span style='mso-spacerun:yes'>  
-</span>\* MERGEFORMAT <span style='mso-element:field-separator'></span></span><![endif]--><span
-lang=EN-GB style='font-size:10.0pt;mso-bidi-font-size:11.0pt'><span
-style='mso-no-proof:yes'>ii</span></span><!--[if supportFields]><span
-lang=EN-GB style='font-size:10.0pt;mso-bidi-font-size:11.0pt'><span
-style='mso-element:field-end'></span></span><![endif]--><span lang=EN-GB
-style='font-size:10.0pt;mso-bidi-font-size:11.0pt'><span style='mso-tab-count:
-1'>                                                                                                                                                                           </span>©
-ISO/IEC&nbsp;2016&nbsp;– All rights reserved<o:p></o:p></span></p>
-
-</div>
-
-<div style='mso-element:footer' id=f2>
-
-<p class=MsoFooter style='line-height:12.0pt'><span lang=EN-GB
-style='font-size:10.0pt;mso-bidi-font-size:11.0pt'>© ISO/IEC&nbsp;2016&nbsp;– All
-rights reserved<span style='mso-tab-count:1'>                                                                                                                                                                          </span></span><!--[if supportFields]><span
-lang=EN-GB style='font-size:10.0pt;mso-bidi-font-size:11.0pt'><span
-style='mso-element:field-begin'></span> PAGE<span style='mso-spacerun:yes'>  
-</span>\* MERGEFORMAT <span style='mso-element:field-separator'></span></span><![endif]--><span
-lang=EN-GB style='font-size:10.0pt;mso-bidi-font-size:11.0pt'><span
-style='mso-no-proof:yes'>iii</span></span><!--[if supportFields]><span
-lang=EN-GB style='font-size:10.0pt;mso-bidi-font-size:11.0pt'><span
-style='mso-element:field-end'></span></span><![endif]--><span lang=EN-GB
-style='font-size:10.0pt;mso-bidi-font-size:11.0pt'><o:p></o:p></span></p>
-
-</div>
-
-<div style='mso-element:footer' id=ef3>
-
-<p class=MsoFooter style='margin-top:12.0pt;line-height:12.0pt;mso-line-height-rule:
-exactly'><!--[if supportFields]><b style='mso-bidi-font-weight:normal'><span
-lang=EN-GB style='font-size:10.0pt;mso-bidi-font-size:11.0pt'><span
-style='mso-element:field-begin'></span><span
-style='mso-spacerun:yes'> </span>PAGE<span style='mso-spacerun:yes'>  
-</span>\* MERGEFORMAT <span style='mso-element:field-separator'></span></span></b><![endif]--><b
-style='mso-bidi-font-weight:normal'><span lang=EN-GB style='font-size:10.0pt;
-mso-bidi-font-size:11.0pt'><span style='mso-no-proof:yes'>2</span></span></b><!--[if supportFields]><b
-style='mso-bidi-font-weight:normal'><span lang=EN-GB style='font-size:10.0pt;
-mso-bidi-font-size:11.0pt'><span style='mso-element:field-end'></span></span></b><![endif]--><span
-lang=EN-GB style='font-size:10.0pt;mso-bidi-font-size:11.0pt'><span
-style='mso-tab-count:1'>                                                                                                                                                                           </span>©
-ISO/IEC&nbsp;2016&nbsp;– All rights reserved<o:p></o:p></span></p>
-
-</div>
-
-<div style='mso-element:footer' id=f3>
-
-<p class=MsoFooter style='line-height:12.0pt'><span lang=EN-GB
-style='font-size:10.0pt;mso-bidi-font-size:11.0pt'>© ISO/IEC&nbsp;2016&nbsp;– All
-rights reserved<span style='mso-tab-count:1'>                                                                                                                                                                           </span></span><!--[if supportFields]><b
-style='mso-bidi-font-weight:normal'><span lang=EN-GB style='font-size:10.0pt;
-mso-bidi-font-size:11.0pt'><span style='mso-element:field-begin'></span>
-PAGE<span style='mso-spacerun:yes'>   </span>\* MERGEFORMAT <span
-style='mso-element:field-separator'></span></span></b><![endif]--><b
-style='mso-bidi-font-weight:normal'><span lang=EN-GB style='font-size:10.0pt;
-mso-bidi-font-size:11.0pt'><span style='mso-no-proof:yes'>3</span></span></b><!--[if supportFields]><b
-style='mso-bidi-font-weight:normal'><span lang=EN-GB style='font-size:10.0pt;
-mso-bidi-font-size:11.0pt'><span style='mso-element:field-end'></span></span></b><![endif]--><span
-lang=EN-GB style='font-size:10.0pt;mso-bidi-font-size:11.0pt'><o:p></o:p></span></p>
-
-</div>
-
-</body>
-
-</html>