word-to-markdown 1.1.8 → 1.1.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3febb4398acdc4eacedcc62e09f4beeaee625858043a27e6df7e597fee1e0d17
-  data.tar.gz: 7a76057aeca2db8f321282bc309a835f282ea921343b28c8bce6d83cd0fc4582
+  metadata.gz: f2b816a2ad9402eb1c45f74f806482502608337ac9127d072647bd4f1f97cd39
+  data.tar.gz: ff35f5c9f2e89c0e781ea864552f6f20bafd23083301c4d72c5c95c7aae4f38c
 SHA512:
-  metadata.gz: ee2340688c2d5f3f21c7e47f85220bebc88201e28200a682146041fa7f5a47e89c56d687b4f6565a95d7d3e7f4c70fb1551894ad297620e7bd49cef520975e18
-  data.tar.gz: 44d405387990ee9a09cb33572a1d7843461c0817789c92a08df6d3542082ffc837bbd39d544a2e6a734a0772c67da3afed77049dc96b0ace0d562473515816e1
+  metadata.gz: e74c055913709cd0fa871ba95cf22b22a86089bb18fd9e88cd27d1dec3ec3b4927708fc9a591ba278b3e5cdc98150178cd17547ba76579702893645554370c83
+  data.tar.gz: 9b01d816e8f95d43fb19dc828213e3db4f7b0897957c6e3eba42b4f4fe888d3564db3b3730b416f9eb10837ca4911fd7083c73b3556c3313dd12cefe2f8ae597

data/README.md

@@ -2,7 +2,7 @@
 
 A Ruby gem to liberate content from [the jail that is Word documents](http://ben.balter.com/2012/10/19/we-ve-been-trained-to-make-paper/#jailbreaking-content)
 
-[![Build Status](https://travis-ci.org/benbalter/word-to-markdown.svg?branch=master)](https://travis-ci.org/benbalter/word-to-markdown) [![Gem Version](https://badge.fury.io/rb/word-to-markdown.png)](http://badge.fury.io/rb/word-to-markdown) [![Inline docs](http://inch-ci.org/github/benbalter/word-to-markdown.png)](http://inch-ci.org/github/benbalter/word-to-markdown) [![Build status](https://ci.appveyor.com/api/projects/status/x2gnsfvli3q47a2e/branch/master?svg=true)](https://ci.appveyor.com/project/benbalter/word-to-markdown/branch/master)
+[![CI](https://github.com/benbalter/word-to-markdown/actions/workflows/ci.yml/badge.svg)](https://github.com/benbalter/word-to-markdown/actions/workflows/ci.yml) [![Gem Version](https://badge.fury.io/rb/word-to-markdown.png)](http://badge.fury.io/rb/word-to-markdown) [![Inline docs](http://inch-ci.org/github/benbalter/word-to-markdown.png)](http://inch-ci.org/github/benbalter/word-to-markdown) [![Build status](https://ci.appveyor.com/api/projects/status/x2gnsfvli3q47a2e/branch/master?svg=true)](https://ci.appveyor.com/project/benbalter/word-to-markdown/branch/master) [![Maintainability](https://api.codeclimate.com/v1/badges/aae0d67ea7db185f1595/maintainability)](https://codeclimate.com/github/benbalter/word-to-markdown/maintainability) [![Test Coverage](https://api.codeclimate.com/v1/badges/aae0d67ea7db185f1595/test_coverage)](https://codeclimate.com/github/benbalter/word-to-markdown/test_coverage)
 
 ## The problem
 
@@ -14,7 +14,9 @@ A Ruby gem to liberate content from [the jail that is Word documents](http://ben
 
 **[Read more](http://ben.balter.com/2014/03/31/word-versus-markdown-more-than-mere-semantics/)**
 
-**[Demo](http://word-to-markdown.herokuapp.com/)**
+## Just want to convert a Microsoft Word (or Google) document to Markdown?
+
+You can use this **[hosted service](https://word2md.com/)** (or check out [its source](https://github.com/benbalter/word-to-markdown-server)).
 
 ## Install
 
@@ -71,8 +73,22 @@ Word-to-markdown requires `soffice` a command line interface to LibreOffice that
 script/cibuild
 ```
 
-## Server
+## Docker
+
+First, create the `Gemfile.lock` by installing the dependencies:
+
+```
+bundle install
+```
+
+Everything you need to run the executable locally:
+
+```
+docker-compose build
+docker-compose run --rm app bundle exec w2m --help
+docker-compose run --rm app bundle exec w2m test/fixtures/em.docx
+```
 
-[Word-to-markdown-demo](https://github.com/benbalter/word-to-markdown-demo) contains a lightweight server for converting Word Documents as a service.
+## Hosted service
 
-A live version runs at [word-to-markdown.herokuapp.com](http://word-to-markdown.herokuapp.com).
+[Word-to-markdown-server](https://github.com/benbalter/word-to-markdown-server) contains a lightweight server for converting Word Documents as a service. A live version runs at [word2md.com](https://word2md.com).

data/lib/cliver/dependency_ext.rb

@@ -24,14 +24,15 @@ module Cliver
 
     # Returns the version of the resolved dependency
     def version
-      return @detected_version if defined? @detected_version
+      return @version if defined? @version
       return if Gem.win_platform?
+
       version = installed_versions.find { |p, _v| p == path }
-      @detected_version = version.nil? ? nil : version[1]
+      @version = version.nil? ? nil : version[1]
     end
 
     def major_version
-      version.split('.').first if version
+      version&.split('.')&.first
     end
   end
 end

data/lib/word-to-markdown/converter.rb

@@ -58,7 +58,7 @@ class WordToMarkdown
         @document.tree.css('[style]').each do |element|
           sizes.push element.font_size.round(-1) unless element.font_size.nil?
         end
-        sizes.uniq.sort
+        sizes.uniq.sort.extend(DescriptiveStatistics)
       end
     end
 
@@ -68,6 +68,7 @@ class WordToMarkdown
     # @return [String, nil] the heading tag (e.g., H1), or nil
     def guess_heading(node)
       return nil if node.font_size.nil?
+
       [*1...HEADING_DEPTH].each do |heading|
         return "h#{heading}" if node.font_size >= h(heading)
       end
@@ -109,7 +110,7 @@ class WordToMarkdown
     def remove_unicode_bullets_from_list_items!
       path = WordToMarkdown.soffice.major_version == '5' ? 'li span span' : 'li span'
       @document.tree.search(path).each do |span|
-        span.inner_html = span.inner_html.gsub(/^([#{UNICODE_BULLETS.join("")}]+)/, '')
+        span.inner_html = span.inner_html.gsub(/^([#{UNICODE_BULLETS.join}]+)/, '')
       end
     end
 

data/lib/word-to-markdown/document.rb

@@ -3,6 +3,7 @@
 class WordToMarkdown
   class Document
     class NotFoundError < StandardError; end
+
     class ConversionError < StandardError; end
 
     attr_reader :path, :tmpdir
@@ -44,7 +45,7 @@ class WordToMarkdown
     #
     # @return [String] the encoding, defaulting to "UTF-8"
     def encoding
-      match = raw_html.encode('UTF-8', invalid: :replace, replace: '').match(/charset=([^\"]+)/)
+      match = raw_html.encode('UTF-8', invalid: :replace, replace: '').match(/charset=([^"]+)/)
       if match
         match[1].sub('macintosh', 'MacRoman')
       else
@@ -81,6 +82,7 @@ class WordToMarkdown
       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.gsub!(/\*\*\ +(?!\*|_)([[:punct:]])/, '**\1') # Remove extra space after bold
       string
     end
 
@@ -95,6 +97,7 @@ class WordToMarkdown
       @raw_html ||= begin
         WordToMarkdown.run_command '--headless', '--convert-to', filter, path, '--outdir', tmpdir
         raise ConversionError, "Failed to convert #{path}" unless File.exist?(dest_path)
+
         html = File.read dest_path
         File.delete dest_path
         html

data/lib/word-to-markdown/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 class WordToMarkdown
-  VERSION = '1.1.8'.freeze
+  VERSION = '1.1.9'
 end

data/lib/word-to-markdown.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-require 'descriptive_statistics'
+require 'descriptive_statistics/safe'
 require 'reverse_markdown'
 require 'nokogiri-styles'
 require 'premailer'
@@ -22,12 +22,12 @@ class WordToMarkdown
 
   # Options to be passed to Reverse Markdown
   REVERSE_MARKDOWN_OPTIONS = {
-    unknown_tags:    :bypass,
+    unknown_tags: :bypass,
     github_flavored: true
   }.freeze
 
   # Minimum version of LibreOffice Required
-  SOFFICE_VERSION_REQUIREMENT = '> 4.0'.freeze
+  SOFFICE_VERSION_REQUIREMENT = '> 4.0'
 
   # Paths to look for LibreOffice, in order of preference
   PATHS = [
@@ -66,6 +66,7 @@ class WordToMarkdown
       output, status = Open3.capture2e(soffice.path, *args)
       logger.debug output
       raise "Command `#{soffice.path} #{args.join(' ')}` failed: #{output}" if status.exitstatus != 0
+
       output
     end
 
@@ -85,7 +86,7 @@ class WordToMarkdown
     # @return Logger instance
     def logger
       @logger ||= begin
-        logger = Logger.new(STDOUT)
+        logger = Logger.new($stdout)
         logger.level = Logger::ERROR unless ENV['DEBUG']
         logger
       end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: word-to-markdown
 version: !ruby/object:Gem::Version
-  version: 1.1.8
+  version: 1.1.9
 platform: ruby
 authors:
 - Ben Balter
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2018-08-01 00:00:00.000000000 Z
+date: 2025-01-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: cliver
@@ -70,16 +70,22 @@ dependencies:
   name: reverse_markdown
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.0'
+        version: '1'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '3'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.0'
+        version: '1'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '3'
 - !ruby/object:Gem::Dependency
   name: sys-proctable
   requirement: !ruby/object:Gem::Requirement
@@ -94,20 +100,6 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.0'
-- !ruby/object:Gem::Dependency
-  name: bundler
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.6'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.6'
 - !ruby/object:Gem::Dependency
   name: minitest
   requirement: !ruby/object:Gem::Requirement
@@ -156,42 +148,70 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.4'
+        version: '13.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.4'
+        version: '13.0'
 - !ruby/object:Gem::Dependency
   name: rubocop
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.49'
+        version: '1.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: rubocop-minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.3'
+- !ruby/object:Gem::Dependency
+  name: rubocop-performance
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.5'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.49'
+        version: '1.5'
 - !ruby/object:Gem::Dependency
   name: shoulda
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.5'
+        version: '4.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.5'
+        version: '4.0'
 description: Ruby Gem to convert Word documents to markdown.
 email: ben.balter@github.com
 executables:
@@ -211,8 +231,9 @@ files:
 homepage: https://github.com/benbalter/word-to-markdown
 licenses:
 - MIT
-metadata: {}
-post_install_message: 
+metadata:
+  rubygems_mfa_required: 'true'
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -227,9 +248,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.6
-signing_key: 
+rubygems_version: 3.5.16
+signing_key:
 specification_version: 4
 summary: Ruby Gem to convert Word documents to markdown
 test_files: []