word-to-markdown 1.1.4 → 1.1.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 2ebb72caa54bd03cd393646e9458f228a47d4bb6
-  data.tar.gz: 9a11db1413481a4abd7a04f38b4fe9b31f765f7e
+  metadata.gz: 9de91d876eb8b4dd4b895c3a36240cb270891592
+  data.tar.gz: 7a671dd33ed9faa1cab5e14cef87da8be3a34f61
 SHA512:
-  metadata.gz: 330dc12f0a9b438bc5485f702594690131a0a0e6306a12e75996017d4dddbbf5591d8d35ea2450fbf54b9e4bf67420d18940901025d1c730dc58d3e8563e46ce
-  data.tar.gz: 929e165957b4dbdce0becfb614539df57b0b7748ee204ee258bda450e68c4f0d55a112e09f308415f100d0d335275ab7a8ba8932865b49ce8ac81eb1eb626bc0
+  metadata.gz: 220ba6079d8383d369601a84ab32f278deb63ec498317b1b77c60208e8fa16ae9317ed57ce6bb9db9164ecc85ac759eeabe0dc95239e4b993dd777ba32c79c12
+  data.tar.gz: 34a838bfb0f659c3cc6a70b3488d01fba8f4b5f69097ba760c06ead8df31e50c05095f0d2e1a178ea9b5eedcff8551a32a1ff8ccb6e421016db21367df5b690a

data/bin/w2m

@@ -9,7 +9,7 @@ end
 
 if ARGV[0] == "--version"
   puts "WordToMarkdown v#{WordToMarkdown::VERSION}"
-  puts "LibreOffice #{WordToMarkdown.soffice_version}"
+  puts "LibreOffice v#{WordToMarkdown.soffice.version}"
 else
   doc = WordToMarkdown.new ARGV[0]
   puts doc.to_s

data/lib/cliver/dependency_ext.rb

@@ -0,0 +1,31 @@
+require 'sys/proctable'
+
+module Cliver
+  class Dependency
+
+    include Sys
+
+    # Memoized shortcut for detect
+    # Returns the path to the detected dependency
+    # Raises an error if the dependency was not satisfied
+    def path
+      @detected_path ||= detect!
+    end
+
+    # Is the detected dependency currently open?
+    def open?
+      ProcTable.ps.any? { |p| p.comm == path }
+    end
+
+    # Returns the version of the resolved dependency
+    def version
+      return @detected_version if defined? @detected_version
+      version = installed_versions.find { |p, v| p == path }
+      @detected_version = version.nil? ? nil : version[1]
+    end
+
+    def major_version
+      version.split(".").first
+    end
+  end
+end

data/lib/word-to-markdown.rb

@@ -1,22 +1,22 @@
 require 'descriptive_statistics'
 require 'reverse_markdown'
 require 'nokogiri-styles'
-require 'sys/proctable'
 require 'premailer'
 require 'rbconfig'
 require 'nokogiri'
+require 'logger'
 require 'tmpdir'
+require 'cliver'
 require 'open3'
 
 require_relative 'word-to-markdown/version'
 require_relative 'word-to-markdown/document'
 require_relative 'word-to-markdown/converter'
 require_relative 'nokogiri/xml/element'
+require_relative 'cliver/dependency_ext'
 
 class WordToMarkdown
 
-  include Sys
-
   attr_reader :document, :converter
 
   REVERSE_MARKDOWN_OPTIONS = {
@@ -24,6 +24,15 @@ class WordToMarkdown
     github_flavored: true
   }
 
+  SOFFICE_VERSION_REQUIREMENT = '> 4.0'
+
+  PATHS = [
+    "~/Applications/LibreOffice.app/Contents/MacOS",
+    "/Applications/LibreOffice.app/Contents/MacOS",
+    "/C/Program Files (x86)/LibreOffice 5/program",
+    "/C/Program Files (x86)/LibreOffice 4/program"
+  ]
+
   # Create a new WordToMarkdown object
   #
   # input - a HTML string or path to an HTML file
@@ -35,59 +44,36 @@ class WordToMarkdown
     converter.convert!
   end
 
-  # source: https://stackoverflow.com/questions/11784109/detecting-operating-systems-in-ruby
-  def self.os
-    @os ||= (
-    host_os = RbConfig::CONFIG['host_os']
-    case host_os
-    when /mswin|msys|mingw|cygwin|bccwin|wince|emc/
-      :windows
-    when /darwin|mac os/
-      :macosx
-    when /linux/
-      :linux
-    when /solaris|bsd/
-      :unix
-    else
-      raise Error::WebDriverError, "unknown os: #{host_os.inspect}"
-    end
-    )
-  end
-
-  def self.soffice_path
-    case os
-    when :macosx
-      %w[~/Applications /Applications]
-        .map  { |f| File.expand_path(File.join(f, "/LibreOffice.app/Contents/MacOS/soffice")) }
-        .find { |f| File.file?(f) }
-    when :windows
-      'C:\Program Files (x86)\LibreOffice 4\program\soffice.exe'
-    else
-      "soffice"
-    end
-  end
-
-  def self.soffice?
-    @soffice ||= !(soffice_path.nil? || soffice_version.nil?)
-  end
-
-  def self.soffice_open?
-    ProcTable.ps.any? { |p| p.exe == soffice_path }
-  end
-
   def self.run_command(*args)
-    raise "LibreOffice executable not found" unless soffice?
-    raise "LibreOffice already running" if soffice_open?
+    raise "LibreOffice already running" if soffice.open?
 
-    output, status = Open3.capture2e(soffice_path, *args)
-    raise "Command `#{soffice_path} #{args.join(" ")}` failed: #{output}" if status != 0
+    output, status = Open3.capture2e(soffice.path, *args)
+    logger.debug output
+    raise "Command `#{soffice_path} #{args.join(" ")}` failed: #{output}" if status.exitstatus != 0
     output
   end
 
-  def self.soffice_version
-    return if soffice_path.nil?
-    output, status = Open3.capture2e(soffice_path, "--version")
-    output.strip.sub "LibreOffice ", "" if status == 0
+  # Returns a Cliver::Dependency object representing our soffice dependency
+  #
+  # Attempts to resolve by looking at PATH followed by paths in the PATHS constant
+  #
+  # Methods used internally:
+  #   path    - returns the resolved path. Raises an error if not satisfied
+  #   version - returns the resolved version
+  #   open    - is the dependency currently open/running?
+  def self.soffice
+    @@soffice_dependency ||= Cliver::Dependency.new(
+      "soffice", SOFFICE_VERSION_REQUIREMENT,
+      :path => "*:" + PATHS.join(":")
+    )
+  end
+
+  def self.logger
+    @@logger ||= begin
+      logger = Logger.new(STDOUT)
+      logger.level = Logger::ERROR unless ENV["DEBUG"]
+      logger
+    end
   end
 
   # Pretty print the class in console

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

@@ -7,7 +7,7 @@ class WordToMarkdown
     HEADING_DEPTH = 6 # Number of headings to guess, e.g., h6
     HEADING_STEP = 100/HEADING_DEPTH
     MIN_HEADING_SIZE = 20
-    UNICODE_BULLETS = ["○", "o", "●", "\uF0B7", "\u2022", "\uF0A7"]
+    UNICODE_BULLETS = ["○", "o", "●", "\u2022", "\\p{C}"]
 
     def initialize(document)
       @document = document
@@ -93,13 +93,15 @@ class WordToMarkdown
     end
 
     def remove_unicode_bullets_from_list_items!
-      @document.tree.search("li span").each do |span|
+      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("")}]+)/, ""
       end
     end
 
     def remove_numbering_from_list_items!
-      @document.tree.search("li span").each do |span|
+      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 /^[a-zA-Z0-9]+\./m, ""
       end
     end

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

@@ -2,6 +2,7 @@
 class WordToMarkdown
   class Document
     class NotFoundError < StandardError; end
+    class ConverstionError < StandardError; end
 
     attr_reader :path, :raw_html, :tmpdir
 
@@ -87,11 +88,20 @@ class WordToMarkdown
 
     def raw_html
       @raw_html ||= begin
-        WordToMarkdown::run_command '--headless', '--convert-to', 'html', path, '--outdir', tmpdir
+        WordToMarkdown::run_command '--headless', '--convert-to', filter, path, '--outdir', tmpdir
+        raise ConverstionError, "Failed to convert #{path}" unless File.exists?(dest_path)
         html = File.read dest_path
         File.delete dest_path
         html
       end
     end
+
+    def filter
+      if WordToMarkdown.soffice.major_version == "5"
+        "html:XHTML Writer File:UTF8"
+      else
+        "html"
+      end
+    end
   end
 end

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

@@ -1,3 +1,3 @@
 class WordToMarkdown
-  VERSION = "1.1.4"
+  VERSION = "1.1.5"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: word-to-markdown
 version: !ruby/object:Gem::Version
-  version: 1.1.4
+  version: 1.1.5
 platform: ruby
 authors:
 - Ben Balter
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-08-05 00:00:00.000000000 Z
+date: 2015-09-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: reverse_markdown
@@ -80,6 +80,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.9'
+- !ruby/object:Gem::Dependency
+  name: cliver
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.3'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.3'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -156,14 +170,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '4.7'
+        version: '5.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '4.7'
+        version: '5.0'
 description: Ruby Gem to convert Word documents to markdown.
 email: ben.balter@github.com
 executables:
@@ -172,6 +186,7 @@ extensions: []
 extra_rdoc_files: []
 files:
 - bin/w2m
+- lib/cliver/dependency_ext.rb
 - lib/nokogiri/xml/element.rb
 - lib/word-to-markdown.rb
 - lib/word-to-markdown/converter.rb
@@ -197,7 +212,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.0
+rubygems_version: 2.4.8
 signing_key: 
 specification_version: 4
 summary: Ruby Gem to convert Word documents to markdown