html2doc 1.1.0 → 1.1.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f1d55301cebf98f75ddfd8966237d19c39bae1c9c8b4b01a39f124ca5da8e588
-  data.tar.gz: a84cd4d87e2cf1c9f107300c883b6b6b85496e2067e76d7f0a282feecf6550c1
+  metadata.gz: b9ed3f5d01d7910a104f86dfe54090ffc3ddf56730f5885293801b3848b24735
+  data.tar.gz: 98428b2016bba38f17cb66226e2fb8d96a28c6ad28bd47a3bc0b998ea1c81228
 SHA512:
-  metadata.gz: 2ef21ec975f624420db8ee706ab1997ab7941bb7e9f75bfaecdde056346a08f73842cd151ad6f5c7a9711a0616ccc61177bd24f17693f8c31c6db70e7aa78088
-  data.tar.gz: c204dfcb3f27a24f86908195d47287c74daaaa41d02de5f28fbb99167b17895f7b46e27971ae533c18874f09ed2d32d4205c6dcd9c6ee6b9e045a9dc06656bfa
+  metadata.gz: ede857348aa47a2f09df5c0c1929056251729b358815130ed6c7823f14e9a49cbb1439d43eb45104cb6be2104f47b4dda15b156680dfefd687c4d6439e162c89
+  data.tar.gz: 4027da3d313f7efb834efc96666d6aedfa509d3b2fc7335b367259833a0050e29b13da92e40514b2afee76b9f84420b81951d1fb9d577643a077643823dcf23c

data/.github/workflows/rake.yml

@@ -16,19 +16,9 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        ruby: [ '2.7', '2.6', '2.5', '2.4' ]
+        ruby: [ '3.0', '2.7', '2.6', '2.5' ]
         os: [ ubuntu-latest, windows-latest, macos-latest ]
         experimental: [ false ]
-        include:
-          - ruby: '3.0'
-            os: 'ubuntu-latest'
-            experimental: true
-          - ruby: '3.0'
-            os: 'windows-latest'
-            experimental: true
-          - ruby: '3.0'
-            os: 'macos-latest'
-            experimental: true
     steps:
       - uses: actions/checkout@v2
         with:

data/.hound.yml

@@ -1,3 +1,5 @@
+# Auto-generated by Cimas: Do not edit it manually!
+# See https://github.com/metanorma/cimas
 ruby:
-  Enabled: true
+  enabled: true
   config_file: .rubocop.yml

data/.rubocop.yml

@@ -1,14 +1,10 @@
-# This project follows the Ribose OSS style guide.
-# https://github.com/riboseinc/oss-guides
-# All project-specific additions and overrides should be specified in this file.
+# Auto-generated by Cimas: Do not edit it manually!
+# See https://github.com/metanorma/cimas
 inherit_from:
   - https://raw.githubusercontent.com/riboseinc/oss-guides/master/ci/rubocop.yml
 
 # local repo-specific modifications
+# ...
 
 AllCops:
-  DisplayCopNames: false
-  StyleGuideCopsOnly: false
-  TargetRubyVersion: 2.4
-Rails:
-  Enabled: true
+  TargetRubyVersion: 2.5

data/Gemfile

@@ -10,6 +10,6 @@ end
 
 gemspec
 
-if File.exist? 'Gemfile.devel'
-  eval File.read('Gemfile.devel'), nil, 'Gemfile.devel' # rubocop:disable Security/Eval
+if File.exist? "Gemfile.devel"
+  eval File.read("Gemfile.devel"), nil, "Gemfile.devel" # rubocop:disable Security/Eval
 end

data/Rakefile

@@ -3,4 +3,4 @@ require "rspec/core/rake_task"
 
 RSpec::Core::RakeTask.new(:spec)
 
-task :default => :spec
+task default: :spec

data/bin/html2doc

@@ -21,9 +21,8 @@ if ARGV.length < 1
 end
 
 Html2Doc.process(
-  File.read(ARGV[0], encoding: "utf-8"), 
+  File.read(ARGV[0], encoding: "utf-8"),
   filename: ARGV[0].gsub(/\.html?$/, ""),
   stylesheet: options[:stylesheet],
   header: options[:header],
 )
-                 

data/bin/rspec

@@ -1,5 +1,5 @@
 #!/usr/bin/env ruby
-  
+
 # This file was generated by Bundler.
 #
 # The application 'rspec' is installed as part of a gem, and

data/html2doc.gemspec

@@ -1,5 +1,4 @@
-
-lib = File.expand_path("../lib", __FILE__)
+lib = File.expand_path("lib", __dir__)
 $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 require "html2doc/version"
 
@@ -16,23 +15,23 @@ Gem::Specification.new do |spec|
     This gem is in active development.
   DESCRIPTION
 
-  spec.homepage      = "https://github.com/metanorma/html2doc"
-  spec.licenses       = ["CC-BY-SA-3.0", "BSD-2-Clause"]
+  spec.homepage = "https://github.com/metanorma/html2doc"
+  spec.licenses = ["CC-BY-SA-3.0", "BSD-2-Clause"]
 
   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(">= 2.4.0")
+  spec.required_ruby_version = Gem::Requirement.new(">= 2.5.0")
 
+  spec.add_dependency "asciimath", "~> 2.0.2"
   spec.add_dependency "htmlentities", "~> 4.3.4"
   spec.add_dependency "image_size"
   spec.add_dependency "mime-types"
-  spec.add_dependency "nokogiri", "~> 1.10.4"
+  spec.add_dependency "nokogiri", "~> 1.12"
+  spec.add_dependency "plane1converter", "~> 0.0.1"
   spec.add_dependency "thread_safe"
   spec.add_dependency "uuidtools"
-  spec.add_dependency "asciimath", "~> 2.0.2"
-  spec.add_dependency "plane1converter", "~> 0.0.1"
 
   spec.add_development_dependency "byebug", "~> 9.1"
   spec.add_development_dependency "equivalent-xml", "~> 0.6"
@@ -40,8 +39,8 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "guard-rspec", "~> 4.7"
   spec.add_development_dependency "rake", "~> 12.0"
   spec.add_development_dependency "rspec", "~> 3.6"
+  spec.add_development_dependency "rspec-match_fuzzy", "~> 0.1.3"
   spec.add_development_dependency "rubocop", "~> 1.5.2"
   spec.add_development_dependency "simplecov", "~> 0.15"
   spec.add_development_dependency "timecop", "~> 0.9"
-  spec.add_development_dependency "rspec-match_fuzzy", "~> 0.1.3"
 end

data/lib/html2doc/base.rb

@@ -2,8 +2,6 @@ require "uuidtools"
 require "asciimath"
 require "htmlentities"
 require "nokogiri"
-#require "xml/xslt"
-require "pp"
 require "fileutils"
 
 module Html2Doc
@@ -19,15 +17,17 @@ module Html2Doc
 
   def self.process_header(headerfile, hash)
     return if headerfile.nil?
+
     doc = File.read(headerfile, encoding: "utf-8")
-    doc = header_image_cleanup(doc, hash[:dir1], hash[:filename], File.dirname(hash[:filename]))
+    doc = header_image_cleanup(doc, hash[:dir1], hash[:filename],
+                               File.dirname(hash[:filename]))
     File.open("#{hash[:dir1]}/header.html", "w:UTF-8") { |f| f.write(doc) }
   end
 
   def self.clear_dir(dir)
     Dir.foreach(dir) do |f|
       fn = File.join(dir, f)
-      File.delete(fn) if f != '.' && f != '..'
+      File.delete(fn) if f != "." && f != ".."
     end
     dir
   end
@@ -72,7 +72,7 @@ module Html2Doc
 
   def self.to_xhtml(xml)
     xml.gsub!(/<\?xml[^>]*>/, "")
-    unless /<!DOCTYPE /.match xml
+    unless /<!DOCTYPE /.match? xml
       xml = '<!DOCTYPE html SYSTEM
           "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">' + xml
     end
@@ -84,34 +84,35 @@ module Html2Doc
   DOCTYPE
 
   def self.from_xhtml(xml)
-    xml.to_xml.sub(%{ xmlns="http://www.w3.org/1999/xhtml"}, "").
-      sub(DOCTYPE, "").
-      gsub(%{ />}, "/>")
+    xml.to_xml.sub(%{ xmlns="http://www.w3.org/1999/xhtml"}, "")
+      .sub(DOCTYPE, "")
+      .gsub(%{ />}, "/>")
   end
 
-  def self.msword_fix(r)
+  def self.msword_fix(doc)
     # brain damage in MSWord parser
-    r.gsub!(%r{<span style="mso-special-character:footnote"/>},
-            '<span style="mso-special-character:footnote"></span>')
-    r.gsub!(%r{<div style="mso-element:footnote-list"></div>},
-            '<div style="mso-element:footnote-list"/>')
-    r.gsub!(%r{(<a style="mso-comment-reference:[^>/]+)/>}, "\\1></a>")
-    r.gsub!(%r{<link rel="File-List"}, "<link rel=File-List")
-    r.gsub!(%r{<meta http-equiv="Content-Type"},
-            "<meta http-equiv=Content-Type")
-    r.gsub!(%r{></m:jc>}, "/>")
-    r.gsub!(%r{></v:stroke>}, "/>")
-    r.gsub!(%r{></v:f>}, "/>")
-    r.gsub!(%r{></v:path>}, "/>")
-    r.gsub!(%r{></o:lock>}, "/>")
-    r.gsub!(%r{></v:imagedata>}, "/>")
-    r.gsub!(%r{></w:wrap>}, "/>")
-    r.gsub!(%r{&tab;|&amp;tab;}, '<span style="mso-tab-count:1">&#xA0; </span>')
-    r = r.split(%r{(<m:oMath>|</m:oMath>)}).each_slice(4).map do |a|
+    doc.gsub!(%r{<span style="mso-special-character:footnote"/>},
+              '<span style="mso-special-character:footnote"></span>')
+    doc.gsub!(%r{<div style="mso-element:footnote-list"></div>},
+              '<div style="mso-element:footnote-list"/>')
+    doc.gsub!(%r{(<a style="mso-comment-reference:[^>/]+)/>}, "\\1></a>")
+    doc.gsub!(%r{<link rel="File-List"}, "<link rel=File-List")
+    doc.gsub!(%r{<meta http-equiv="Content-Type"},
+              "<meta http-equiv=Content-Type")
+    doc.gsub!(%r{></m:jc>}, "/>")
+    doc.gsub!(%r{></v:stroke>}, "/>")
+    doc.gsub!(%r{></v:f>}, "/>")
+    doc.gsub!(%r{></v:path>}, "/>")
+    doc.gsub!(%r{></o:lock>}, "/>")
+    doc.gsub!(%r{></v:imagedata>}, "/>")
+    doc.gsub!(%r{></w:wrap>}, "/>")
+    doc.gsub!(%r{<(/)?m:(span|em)\b}, "<\\1\\2")
+    doc.gsub!(%r{&tab;|&amp;tab;},
+              '<span style="mso-tab-count:1">&#xA0; </span>')
+    doc.split(%r{(<m:oMath>|</m:oMath>)}).each_slice(4).map do |a|
       a.size > 2 and a[2] = a[2].gsub(/>\s+</, "><")
       a
     end.join
-    r
   end
 
   PRINT_VIEW = <<~XML.freeze
@@ -127,30 +128,30 @@ module Html2Doc
     <meta http-equiv=Content-Type content="text/html; charset=utf-8"/>
   XML
 
-  def self.define_head1(docxml, dir)
+  def self.define_head1(docxml, _dir)
     docxml.xpath("//*[local-name() = 'head']").each do |h|
       h.children.first.add_previous_sibling <<~XML
-      #{PRINT_VIEW}
-        <link rel="File-List" href="cid:filelist.xml"/>
+        #{PRINT_VIEW}
+          <link rel="File-List" href="cid:filelist.xml"/>
       XML
     end
   end
 
-  def self.filename_substitute(stylesheet, header_filename, filename)
-    if header_filename.nil?
-      stylesheet
-    else
-      stylesheet.gsub(/url\("[^"]+"\)/) do |m|
-        /FILENAME/.match(m) ? "url(cid:header.html)" : m
+  def self.filename_substitute(head, header_filename)
+    return if header_filename.nil?
+
+    head.xpath(".//*[local-name() = 'style']").each do |s|
+      s1 = s.to_xml.gsub(/url\("[^"]+"\)/) do |m|
+        /FILENAME/.match?(m) ? "url(cid:header.html)" : m
       end
+      s.replace(s1)
     end
   end
 
-  def self.stylesheet(filename, header_filename, fn)
-    (fn.nil? || fn.empty?) &&
+  def self.stylesheet(_filename, _header_filename, fn)
+    (fn.nil? || fn.empty?) and
       fn = File.join(File.dirname(__FILE__), "wordstyle.css")
     stylesheet = File.read(fn, encoding: "UTF-8")
-    stylesheet = filename_substitute(stylesheet, header_filename, filename)
     xml = Nokogiri::XML("<style/>")
     xml.children.first << Nokogiri::XML::Comment.new(xml, "\n#{stylesheet}\n")
     xml.root.to_s
@@ -161,6 +162,7 @@ module Html2Doc
     head = docxml.at("//*[local-name() = 'head']")
     css = stylesheet(hash[:filename], hash[:header_file], hash[:stylesheet])
     add_stylesheet(head, title, css)
+    filename_substitute(head, hash[:header_file])
     define_head1(docxml, hash[:dir1])
     rootnamespace(docxml.root)
   end
@@ -189,13 +191,13 @@ module Html2Doc
   end
 
   def self.bookmarks(docxml)
-    docxml.xpath("//*[@id][not(@name)][not(@style = 'mso-element:footnote')]").each do |x|
-      next if x["id"].empty?
-      next if %w(shapetype v:shapetype shape v:shape).include? x.name
-      if x.children.empty?
-        x.add_child("<a name='#{x["id"]}'></a>")
-      else
-        x.children.first.previous = "<a name='#{x["id"]}'></a>"
+    docxml.xpath("//*[@id][not(@name)][not(@style = 'mso-element:footnote')]")
+      .each do |x|
+      next if x["id"].empty? ||
+        %w(shapetype v:shapetype shape v:shape).include?(x.name)
+
+      if x.children.empty? then x.add_child("<a name='#{x['id']}'></a>")
+      else x.children.first.previous = "<a name='#{x['id']}'></a>"
       end
       x.delete("id")
     end

data/lib/html2doc/lists.rb

@@ -2,83 +2,87 @@ require "uuidtools"
 require "asciimath"
 require "htmlentities"
 require "nokogiri"
-require "uuidtools"
 
 module Html2Doc
-  def self.style_list(li, level, liststyle, listnumber)
+  def self.style_list(elem, level, liststyle, listnumber)
     return unless liststyle
-    if li["style"]
-      li["style"] += ";"
+
+    if elem["style"]
+      elem["style"] += ";"
     else
-      li["style"] = ""
+      elem["style"] = ""
     end
-    li["style"] += "mso-list:#{liststyle} level#{level} lfo#{listnumber};"
+    elem["style"] += "mso-list:#{liststyle} level#{level} lfo#{listnumber};"
   end
 
-  def self.list_add1(li, liststyles, listtype, level)
-    if [:ul, :ol].include? listtype
-          list_add(li.xpath(".//ul") - li.xpath(".//ul//ul | .//ol//ul"),
-                   liststyles, :ul, level + 1)
-          list_add(li.xpath(".//ol") - li.xpath(".//ul//ol | .//ol//ol"),
-                   liststyles, :ol, level + 1)
-        else
-          list_add(li.xpath(".//ul") - li.xpath(".//ul//ul | .//ol//ul"),
-                   liststyles, listtype, level + 1)
-          list_add(li.xpath(".//ol") - li.xpath(".//ul//ol | .//ol//ol"),
-                   liststyles, listtype, level + 1)
-        end
+  def self.list_add1(elem, liststyles, listtype, level)
+    if %i[ul ol].include? listtype
+      list_add(elem.xpath(".//ul") - elem.xpath(".//ul//ul | .//ol//ul"),
+               liststyles, :ul, level + 1)
+      list_add(elem.xpath(".//ol") - elem.xpath(".//ul//ol | .//ol//ol"),
+               liststyles, :ol, level + 1)
+    else
+      list_add(elem.xpath(".//ul") - elem.xpath(".//ul//ul | .//ol//ul"),
+               liststyles, listtype, level + 1)
+      list_add(elem.xpath(".//ol") - elem.xpath(".//ul//ol | .//ol//ol"),
+               liststyles, listtype, level + 1)
+    end
   end
 
   def self.list_add(xpath, liststyles, listtype, level)
-    xpath.each_with_index do |list, i|
+    xpath.each_with_index do |l, _i|
       @listnumber += 1 if level == 1
-      list["seen"] = true if level == 1
-      list["id"] ||= UUIDTools::UUID.random_create
-      (list.xpath(".//li") - list.xpath(".//ol//li | .//ul//li")).each do |li|
+      l["seen"] = true if level == 1
+      l["id"] ||= UUIDTools::UUID.random_create
+      (l.xpath(".//li") - l.xpath(".//ol//li | .//ul//li")).each do |li|
         style_list(li, level, liststyles[listtype], @listnumber)
         list_add1(li, liststyles, listtype, level)
       end
-      list.xpath(".//ul[not(ancestor::li/ancestor::*/@id = '#{list['id']}')] | "\
-                 ".//ol[not(ancestor::li/ancestor::*/@id = '#{list['id']}')]").each do |li|
-        list_add1(li.parent, liststyles, listtype, level-1)
+      l.xpath(".//ul[not(ancestor::li/ancestor::*/@id = '#{l['id']}')] | "\
+              ".//ol[not(ancestor::li/ancestor::*/@id = '#{l['id']}')]")
+        .each do |li|
+        list_add1(li.parent, liststyles, listtype, level - 1)
       end
     end
   end
 
-  def self.list2para(u)
-    return if u.xpath("./li").empty?
-    u.xpath("./li").first["class"] ||= "MsoListParagraphCxSpFirst"
-    u.xpath("./li").last["class"] ||= "MsoListParagraphCxSpLast"
-    u.xpath("./li/p").each { |p| p["class"] ||= "MsoListParagraphCxSpMiddle" }
-    u.xpath("./li").each do |l|
+  def self.list2para(list)
+    return if list.xpath("./li").empty?
+
+    list.xpath("./li").first["class"] ||= "MsoListParagraphCxSpFirst"
+    list.xpath("./li").last["class"] ||= "MsoListParagraphCxSpLast"
+    list.xpath("./li/p").each { |p| p["class"] ||= "MsoListParagraphCxSpMiddle" }
+    list.xpath("./li").each do |l|
       l.name = "p"
       l["class"] ||= "MsoListParagraphCxSpMiddle"
       l&.first_element_child&.name == "p" and
         l.first_element_child.replace(l.first_element_child.children)
     end
-    u.replace(u.children)
+    list.replace(list.children)
   end
 
   TOPLIST = "[not(ancestor::ul) and not(ancestor::ol)]".freeze
 
-  def self.lists1(docxml, liststyles, k)
-    case k
+  def self.lists1(docxml, liststyles, style)
+    case style
     when :ul then list_add(docxml.xpath("//ul[not(@class)]#{TOPLIST}"),
-                            liststyles, :ul, 1)
+                           liststyles, :ul, 1)
     when :ol then list_add(docxml.xpath("//ol[not(@class)]#{TOPLIST}"),
                            liststyles, :ol, 1)
     else
-      list_add(docxml.xpath("//ol[@class = '#{k.to_s}']#{TOPLIST} | "\
-                            "//ul[@class = '#{k.to_s}']#{TOPLIST}"),
-      liststyles, k, 1)
+      list_add(docxml.xpath("//ol[@class = '#{style}']#{TOPLIST} | "\
+                            "//ul[@class = '#{style}']#{TOPLIST}"),
+      liststyles, style, 1)
     end
   end
 
   def self.lists_unstyled(docxml, liststyles)
-    list_add(docxml.xpath("//ul#{TOPLIST}[not(@seen)]"),
-             liststyles, :ul, 1) if liststyles.has_key?(:ul)
-    list_add(docxml.xpath("//ol#{TOPLIST}[not(@seen)]"),
-             liststyles, :ul, 1) if liststyles.has_key?(:ol)
+    liststyles.has_key?(:ul) and
+      list_add(docxml.xpath("//ul#{TOPLIST}[not(@seen)]"),
+               liststyles, :ul, 1)
+    liststyles.has_key?(:ol) and
+      list_add(docxml.xpath("//ol#{TOPLIST}[not(@seen)]"),
+               liststyles, :ul, 1)
     docxml.xpath("//ul[@seen] | //ol[@seen]").each do |l|
       l.delete("seen")
     end
@@ -86,6 +90,7 @@ module Html2Doc
 
   def self.lists(docxml, liststyles)
     return if liststyles.nil?
+
     @listnumber = 0
     liststyles.each_key { |k| lists1(docxml, liststyles, k) }
     lists_unstyled(docxml, liststyles)