wp2txt 0.5.4 → 0.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 07ab0b6030dcc43512ef8f17504519dc06f72a25
-  data.tar.gz: 915a4ea67ab2bfbe7b465d3d6d718c30a02b463f
+  metadata.gz: c05af7e5c72b073f18b53eca8619212f0928aaa1
+  data.tar.gz: 02dc116458041b096fd811b3fec6ffb6e6ff3ee7
 SHA512:
-  metadata.gz: f2d66c66a8e87dc8d35c7627729e44dc3a9d6c93624a3055e925ad293fbf21aff3e012dfd4e00d14b815e9b8ee7f303b704430555a7525bb497d8ae11f390968
-  data.tar.gz: 75f6245efe1b55dfcb0612b49d8b2fd7e96cf3fb2dbe729abbcc3761f6d7431f2e9408c8970bf310e96626819e884ce681bfb9685462df3461ca0f494e0d483d
+  metadata.gz: 26479a43e8e3ccebfb6578562d62b7b6d2234e924838774a11d143c8fad7e1952db0278526d202a77aad680926b96baa25c8da9e0c23f916d95ccf614d5e82a3
+  data.tar.gz: 8959c9b51efb18386cf556c67439332fc43723d8de8abfc014745d0d0ad1f89ba56b6222b6f8d2a33748343e2dbef93752ee104c8a54c57e01fe21bee7e2f892

data/.gitignore

@@ -9,7 +9,7 @@ _yardoc
 coverage
 doc/
 lib/bundler/man
-pkg
+pkg/
 rdoc
 spec/reports
 test/tmp

data/README.md

@@ -2,8 +2,6 @@
 
 Wikipedia dump file to text converter
 
-     CAUTION: This software is on an experimental stage. Use with care!
-
 ### About ###
 
 WP2TXT extracts plain text data from Wikipedia dump file (encoded in XML/compressed with Bzip2) stripping all the MediaWiki markups and other metadata. It is originally intended to be useful for researchers who look for an easy way to obtain open-source multi-lingual corpora, but may be handy for other purposes.
@@ -14,15 +12,19 @@ WP2TXT extracts plain text data from Wikipedia dump file (encoded in XML/compres
 * Create output files of specified size.
 * Allow users to specify text elements to be extracted/converted (page titles, section titles, lists, and tables).
 
-WP2TXT before version 0.4.0 came with Mac/Windows GUI. Now it's become a pure command-line application--Sorry GUI folks, but there seems more demand for an easy-to-hack CUI package than a not-very-flexible GUI app.
-
 ### Installation
     
     $ gem install wp2txt
 
+It is highly recommended you also install bz2-ruby gem. See the following for the details about bz2-ruby gem:
+
+[https://github.com/brianmario/bzip2-ruby](https://github.com/brianmario/bzip2-ruby)
+
+When the above gem is not found, wp2txt will try to use bzip2 program in your command line environment.  Supposedly he former option is more reliable as well as fast.
+
 ### Usage
 
-Obtain a Wikipedia dump file (see the link below) with a file name such as:
+Obtain a Wikipedia dump file (from [here](http://dumps.wikimedia.org/backup-index.html)) with a file name such as:
 
     xxwiki-yyyymmdd-pages-articles.xml.bz2
 
@@ -30,24 +32,31 @@ where `xx` is language code such as "en (English)" or "ja (Japanese)", and  `yyy
 
 Command line options are as follows:
 
-    Usage: wp2txt [options]
-    where [options] are:
-                         --input-file, -i:   Wikipedia dump file with .bz2 (compressed) or .txt (uncompressed) format
-                     --output-dir, -o <s>:   Output directory (default: Present working directory)
-                        --convert-off, -c:   Output XML (without converting to plain text)
-                           --list-off, -l:   Exclude list items from output
-                        --heading-off, -d:   Exclude section titles from output
-                          --title-off, -t:   Exclude page titles from output
-          --table-off, --no-table-off, -a:   Exclude page titles from output (default: true)
-    --template-off, --no-template-off, -e:   Remove template notations from output (default: true)
-                       --redirect-off, -r:   Not show redirect destination
-                       --strip-marker, -s:   Remove symbols prefixed to list items, definitions, etc.
-                       --category-off, -g:   Not show article category information
-                      --file-size, -f <i>:   Approximate size (in MB) of each output file (default: 10)
-                            --version, -v:   Print version and exit
-                               --help, -h:   Show this message
-
-### Limitations ###
+*CAUTION:* command line options in the current version have been drastically changed from those in versions 0.5!
+
+      Usage: wp2txt [options]
+      where [options] are:
+               --input-file, -i:   Wikipedia dump file with .bz2 (compressed) or
+                                   .txt (uncompressed) format
+           --output-dir, -o <s>:   Output directory (default:
+                                   /Users/yohasebe/Dropbox/code/wp2txt)
+    --convert, --no-convert, -c:   Output in plain text (converting from XML)
+                                   (default: true)
+          --list, --no-list, -l:   Show list items in output (default: true)
+    --heading, --no-heading, -d:   Show section titles in output (default: true)
+        --title, --no-title, -t:   Show page titles in output (default: true)
+                    --table, -a:   Show table source code in output
+                 --template, -e:   Show template specifications in output
+                 --redirect, -r:   Show redirect destination
+      --marker, --no-marker, -m:   Show symbols prefixed to list items,
+                                   definitions, etc. (Default: true)
+                 --category, -g:   Show article category information
+            --file-size, -f <i>:   Approximate size (in MB) of each output file
+                                   (default: 10)
+                  --version, -v:   Print version and exit
+                     --help, -h:   Show this message
+
+### Caveats ###
 
 * Certain types of data such as mathematical equations and computer source code are not be properly converted.  Please remember this software is originally intended for correcting “sentences” for linguistic studies.
 * Extraction of normal text data could sometimes fail for various reasons (e.g. illegal matching of begin/end tags, language-specific conventions of formatting, etc). 

data/bin/wp2txt

@@ -26,15 +26,15 @@ EOS
 
   opt :input_file,  "Wikipedia dump file with .bz2 (compressed) or .txt (uncompressed) format", :required => true
   opt :output_dir,  "Output directory", :default => Dir::pwd, :type => String
-  opt :convert_off, "Output XML (without converting to plain text)", :default => false
-  opt :list_off,    "Exclude list items from output", :default => false
-  opt :heading_off, "Exclude section titles from output", :default => false, :short => "-d"
-  opt :title_off,   "Exclude page titles from output", :default => false
-  opt :table_off,   "Exclude page titles from output", :default => true
-  opt :template_off, "Remove template notations from output", :default => true
-  opt :redirect_off, "Not show redirect destination", :default => false
-  opt :strip_marker, "Remove symbols prefixed to list items, definitions, etc.", :default => false
-  opt :category_off, "Not show article category information", :default => false
+  opt :convert,     "Output in plain text (converting from XML)", :default => true
+  opt :list,    "Show list items in output", :default => true
+  opt :heading, "Show section titles in output", :default => true, :short => "-d"
+  opt :title,   "Show page titles in output", :default => true
+  opt :table,   "Show table source code in output", :default => false
+  opt :template, "Show template specifications in output", :default => false
+  opt :redirect, "Show redirect destination", :default => false
+  opt :marker, "Show symbols prefixed to list items, definitions, etc.", :default => true
+  opt :category, "Show article category information", :default => false
   opt :file_size,   "Approximate size (in MB) of each output file", :default => 10  
 end
 Trollop::die :size, "must be larger than 0" unless opts[:file_size] >= 0
@@ -43,9 +43,9 @@ Trollop::die :output_dir, "must exist" unless File.exist?(opts[:output_dir])
 input_file = ARGV[0]
 output_dir = opts[:output_dir]
 tfile_size = opts[:file_size]
-convert_off = opts[:convert_off]
-strip_tmarker = opts[:strip_marker]
-opt_array = [:title_off, :list_off, :heading_off, :table_off, :template_off, :redirect_off]
+convert = opts[:convert]
+strip_tmarker = opts[:marker] ? false : true
+opt_array = [:title_off, :list, :heading, :table, :template, :redirect]
 config = {}
 opt_array.each do |opt|
   config[opt] = opts[opt]
@@ -54,13 +54,13 @@ end
 # a "parent" is either commandline progress bar or 
 # a gui window (not available for now)
 parent = Wp2txt::CmdProgbar.new
-wpconv = Wp2txt::Runner.new(parent, input_file, output_dir, tfile_size, convert_off, strip_tmarker)
+wpconv = Wp2txt::Runner.new(parent, input_file, output_dir, tfile_size, convert, strip_tmarker)
 
 wpconv.extract_text do |article|
   title = format_wiki article.title
   title = "[[#{title}]]\n"
 
-  if !opts[:category_off] && !article.categories.empty?
+  if opts[:category] && !article.categories.empty?
     contents = "\nCATEGORIES: "
     contents += article.categories.join(", ")
     contents += "\n\n"
@@ -71,31 +71,31 @@ wpconv.extract_text do |article|
   article.elements.each do |e|
     case e.first
     when :mw_heading
-      next if config[:heading_off]
+      next if !config[:heading]
       line = format_wiki(e.last)
       line += "+HEADING+" if $DEBUG_MODE
     when :mw_paragraph
-      next if config[:paragraph_off]
+      # next if !config[:paragraph]
       line = format_wiki(e.last)
       line += "+PARAGRAPH+" if $DEBUG_MODE
     when :mw_table, :mw_htable
-      next if config[:table_off]
+      next if !config[:table]
       line = format_wiki(e.last)
       line += "+TABLE+" if $DEBUG_MODE
     when :mw_pre
-      next if config[:pre_off]
+      next if !config[:pre]
       line = e.last
       line += "+PRE+" if $DEBUG_MODE
     when :mw_quote
-      next if config[:quote_off]
+      # next if !config[:quote]
       line = format_wiki(e.last)
       line += "+QUOTE+" if $DEBUG_MODE
     when :mw_unordered, :mw_ordered, :mw_definition
-      next if config[:list_off]
+      next if !config[:list]
       line = format_wiki(e.last)
       line += "+LIST+" if $DEBUG_MODE
     when :mw_redirect
-      next if config[:redirect_off]
+      next if !config[:redirect]
       line = format_wiki(e.last)
       line += "+REDIRECT+" if $DEBUG_MODE
       line += "\n\n"
@@ -108,14 +108,14 @@ wpconv.extract_text do |article|
       end
     end
     contents += line
-    contents = remove_templates(contents) if config[:template_off]
+    contents = remove_templates(contents) unless config[:template]
   end
     
   ##### cleanup #####
   if /\A\s*\z/m =~ contents
     result = ""
   else
-    result = config[:title_off] ? contents : title + "\n" + contents
+    result = config[:title] ? title + "\n" + contents : contents
   end
   result = result.gsub(/\[ref\]\s*\[\/ref\]/m){""}
   result = result.gsub(/\n\n\n+/m){"\n\n"} + "\n"  

data/lib/wp2txt/version.rb

@@ -1,3 +1,3 @@
 module Wp2txt
-  VERSION = "0.5.4"
+  VERSION = "0.6.0"
 end

data/lib/wp2txt.rb

@@ -25,16 +25,16 @@ module Wp2txt
 
     include Wp2txt
 
-    # attr_accessor :pause_flag, :stop_flag, :outfiles, :convert_off
+    # attr_accessor :pause_flag, :stop_flag, :outfiles, :convert
 
-    def initialize(parent, input_file, output_dir = ".", tfile_size = 10, convert_off = false, strip_tmarker = false)
+    def initialize(parent, input_file, output_dir = ".", tfile_size = 10, convert = true, strip_tmarker = false)
       @parent = parent
       @fp = nil
       
       @input_file = input_file
       @output_dir = output_dir
       @tfile_size = tfile_size
-      @convert_off = convert_off
+      @convert = convert
       @strip_tmarker = strip_tmarker
     end
     
@@ -213,16 +213,15 @@ module Wp2txt
     # call this method to do the job
     def extract_text(&block)
       prepare            
-      # output the original xml only split to files of the specified size
-      if @convert_off
-        extract
-        # convert xml to plain text
-      else
+      if @convert
         if block
           extract_and_convert(&block)
         else
           extract_and_convert
         end
+      else
+        # output the original xml only split to files of the specified size
+        extract
       end
     end
     

data/spec/utils_spec.rb

@@ -23,7 +23,7 @@ describe "Wp2txt" do
       str_processed = process_nested_structure(scanner, "[[", "]]") do |content|
         "<<" + content + ">>"
       end
-      str_processed.should == str_after
+      expect(str_processed).to eq str_after
       
       str_before = "#* {{quote-book|1503|year_published=1836|chapter=19 Henry VII. c. 5: Coin||A Collection of Statutes Connected with the General Administration of the Law|page=158|url=http://books.google.com/books?id=QtYuAAAAIAAJ
       |passage={{...}} every of them, being gold, whole and weight, shall '''go''' and be current in payment throughout this his realm for the sum that they were coined for.}}"
@@ -33,7 +33,9 @@ describe "Wp2txt" do
       str_processed = process_nested_structure(scanner, "{{", "}}") do |content|
         "<<" + content + ">>"
       end
-      str_processed.should == str_after
+      #str_processed.should == str_after
+      expect(str_processed).to eq str_after
+      
     end
   end
   
@@ -41,7 +43,7 @@ describe "Wp2txt" do
     it "replaces character references with real characters" do
       str_before = "&nbsp; &lt; &gt; &amp; &quot;"
       str_after  = "  < > & \""
-      special_chr(str_before).should == str_after
+      expect(special_chr(str_before)).to eq str_after
     end    
   end
   
@@ -49,7 +51,7 @@ describe "Wp2txt" do
     it "replaces character references with real characters" do
       str_before = "&#x266A;"
       str_after  = "♪"
-      chrref_to_utf(str_before).should == str_after
+      expect(chrref_to_utf(str_before)).to eq str_after
     end
   end
   
@@ -57,7 +59,7 @@ describe "Wp2txt" do
     it "replaces {mdash}, {ndash}, or {–} with '–'" do
       str_before = "{mdash} {ndash} {–}"
       str_after  = "– – –"
-      mndash(str_before).should == str_after
+      expect(mndash(str_before)).to eq str_after
     end
   end
 
@@ -65,7 +67,7 @@ describe "Wp2txt" do
     it "replaces \\r\\n and <br /> inside [ref] ... [/ref] to ' '" do
       str_before = "[ref]...\r\n...<br />...[/ref]"
       str_after  = "... ... ..."
-      format_ref(str_before).should == str_after
+      expect(format_ref(str_before)).to eq str_after
     end    
   end
   
@@ -73,7 +75,7 @@ describe "Wp2txt" do
     it "replaces <ref> tag with [ref]" do
       str_before = "<ref> ... <br /> ... </ref> \n <ref />"
       str_after  = "[ref] ... \n ... [/ref] \n "
-      make_reference(str_before).should == str_after
+      expect(make_reference(str_before)).to eq str_after
     end    
   end
   
@@ -81,7 +83,7 @@ describe "Wp2txt" do
     it "removes table formated parts" do
       str_before = "{| ... \n{| ... \n ...|}\n ...|}"
       str_after  = ""
-      remove_table(str_before).should == str_after
+      expect(remove_table(str_before)).to eq str_after
     end    
   end
 
@@ -89,7 +91,7 @@ describe "Wp2txt" do
     it "removes clade formated parts" do
       str_before = "\{\{clade ... \n ... \n ... \n\}\}"
       str_after  = ""
-      remove_clade(str_before).should == str_after
+      expect(remove_clade(str_before)).to eq str_after
     end    
   end
   
@@ -97,7 +99,7 @@ describe "Wp2txt" do
     it "removes horizontal lines" do
       str_before = "\n----\n--\n--\n"
       str_after  = "\n\n"
-      remove_hr(str_before).should == str_after
+      expect(remove_hr(str_before)).to eq str_after
     end    
   end
 
@@ -105,10 +107,10 @@ describe "Wp2txt" do
     it "removes tags" do
       str_before = "<tag>abc</tag>"
       str_after  = "abc"
-      remove_tag(str_before).should == str_after
+      expect(remove_tag(str_before)).to eq str_after
       str_before = "[tag]def[/tag]"
       str_after  = "def"
-      remove_tag(str_before, ['[', ']']).should == str_after
+      expect(remove_tag(str_before, ['[', ']'])).to eq str_after
     end    
   end
   
@@ -116,7 +118,7 @@ describe "Wp2txt" do
     it "removes directive" do
       str_before = "__abc__\n __def__"
       str_after  = "\n "
-      remove_directive(str_before).should == str_after
+      expect(remove_directive(str_before)).to eq str_after
     end    
   end
 
@@ -124,7 +126,7 @@ describe "Wp2txt" do
     it "removes directive" do
       str_before = "''abc''\n'''def'''"
       str_after  = "abc\ndef"
-      remove_emphasis(str_before).should == str_after
+      expect(remove_emphasis(str_before)).to eq str_after
     end    
   end
   
@@ -132,7 +134,7 @@ describe "Wp2txt" do
     it "replaces <nowiki>...</nowiki> with <nowiki-object_id>" do
       str_before = "<nowiki>[[abc]]</nowiki>def<nowiki>[[ghi]]</nowiki>"
       str_after  = Regexp.new("<nowiki-\\d+>def<nowiki-\\d+>")
-      escape_nowiki(str_before).should =~ str_after
+      expect(escape_nowiki(str_before)).to match str_after
     end
   end
 
@@ -141,24 +143,24 @@ describe "Wp2txt" do
       @nowikis = {123 => "[[abc]]", 124 => "[[ghi]]"}
       str_before = "<nowiki-123>def<nowiki-124>"
       str_after  = "[[abc]]def[[ghi]]"
-      unescape_nowiki(str_before).should == str_after
+      expect(unescape_nowiki(str_before)).to eq str_after
     end
   end
   
   describe "process_interwiki_links" do
     it "formats text link and remove brackets" do
-      process_interwiki_links("[[a b]]").should   == "a b"
-      process_interwiki_links("[[a b|c]]").should == "c"
-      process_interwiki_links("[[a|b|c]]").should == "b|c"
-      process_interwiki_links("[[硬口蓋鼻音|[ɲ], /J/]]").should == "[ɲ], /J/"
+      expect(process_interwiki_links("[[a b]]")).to eq "a b"
+      expect(process_interwiki_links("[[a b|c]]")).to eq "c"
+      expect(process_interwiki_links("[[a|b|c]]")).to eq "b|c"
+      expect(process_interwiki_links("[[硬口蓋鼻音|[ɲ], /J/]]")).to eq "[ɲ], /J/"
     end
   end
 
   describe "process_external_links" do
     it "formats text link and remove brackets" do
-      process_external_links("[http://yohasebe.com yohasebe.com]").should   == "yohasebe.com"
-      process_external_links("[http://yohasebe.com]").should   == "http://yohasebe.com"
-      process_external_links("* Turkish: {{t+|tr|köken bilimi}}]], {{t+|tr|etimoloji}}").should == "* Turkish: {{t+|tr|köken bilimi}}]], {{t+|tr|etimoloji}}"
+      expect(process_external_links("[http://yohasebe.com yohasebe.com]")).to eq "yohasebe.com"      
+      expect(process_external_links("[http://yohasebe.com]")).to eq "http://yohasebe.com"
+      expect(process_external_links("* Turkish: {{t+|tr|köken bilimi}}]], {{t+|tr|etimoloji}}")).to eq "* Turkish: {{t+|tr|köken bilimi}}]], {{t+|tr|etimoloji}}"
     end
   end
   
@@ -166,30 +168,30 @@ describe "Wp2txt" do
     it "removes brackets and leaving some text" do
       str_before = "{{}}"
       str_after = ""
-      process_template(str_before).should == str_after
+      expect(process_template(str_before)).to eq str_after
       str_before = "{{lang|en|Japan}}"
       str_after  = "Japan"
-      process_template(str_before).should == str_after
+      expect(process_template(str_before)).to eq str_after
       str_before = "{{a|b=c|d=f}}"
       str_after  = "a"
-      process_template(str_before).should == str_after
+      expect(process_template(str_before)).to eq str_after
       str_before = "{{a|b|{{c|d|e}}}}"
       str_after  = "e"
-      process_template(str_before).should == str_after
+      expect(process_template(str_before)).to eq str_after
     end
   end
   
-  describe "expand_template" do
-    it "gets data corresponding to a given template using mediawiki api" do 
-      uri = "http://en.wiktionary.org/w/api.php"
-      template = "{{en-verb}}"
-      word = "kick"
-      expanded = expand_template(uri, template, word)
-      html =<<EOD
-<span class=\"infl-inline\"><b class=\"Latn \" lang=\"en\">kick</b> (''third-person singular simple present'' <span class=\"form-of third-person-singular-form-of\">'''<span class=\"Latn \" lang=\"en\">[[kicks#English|kicks]]</span>'''</span>, ''present participle'' <span class=\"form-of present-participle-form-of\">'''<span class=\"Latn \" lang=\"en\">[[kicking#English|kicking]]</span>'''</span>, ''simple past and past participle'' <span class=\"form-of simple-past-and-participle-form-of\"> '''<span class=\"Latn \" lang=\"en\">[[kicked#English|kicked]]</span>'''</span>)</span>[[Category:English verbs|kick]]
-EOD
-      html.strip!
-      expanded.should == html
-    end
-  end
+#   describe "expand_template" do
+#     it "gets data corresponding to a given template using mediawiki api" do
+#       uri = "http://en.wiktionary.org/w/api.php"
+#       template = "{{en-verb}}"
+#       word = "kick"
+#       expanded = expand_template(uri, template, word)
+#       html =<<EOD
+# <span class=\"infl-inline\"><b class=\"Latn \" lang=\"en\">kick</b> (''third-person singular simple present'' <span class=\"form-of third-person-singular-form-of\">'''<span class=\"Latn \" lang=\"en\">[[kicks#English|kicks]]</span>'''</span>, ''present participle'' <span class=\"form-of present-participle-form-of\">'''<span class=\"Latn \" lang=\"en\">[[kicking#English|kicking]]</span>'''</span>, ''simple past and past participle'' <span class=\"form-of simple-past-and-participle-form-of\"> '''<span class=\"Latn \" lang=\"en\">[[kicked#English|kicked]]</span>'''</span>)</span>[[Category:English verbs|kick]]
+# EOD
+#       html.strip!
+#       expanded.should == html
+#     end
+#   end
 end

data/wp2txt.gemspec

@@ -24,10 +24,10 @@ Gem::Specification.new do |s|
 
   s.add_dependency "nokogiri"
   s.add_dependency "sanitize"
-  if RUBY_VERSION >= '2.0'
-    s.add_dependency "bzip2-ruby-rb20"
-  else
-    s.add_dependency "bzip2-ruby"
-  end
+  # if RUBY_VERSION >= '2.0'
+  #   s.add_dependency "bzip2-ruby-rb20"
+  # else
+  #   s.add_dependency "bzip2-ruby"
+  # end
   s.add_dependency "trollop"
 end

metadata

@@ -1,111 +1,97 @@
 --- !ruby/object:Gem::Specification
 name: wp2txt
 version: !ruby/object:Gem::Version
-  version: 0.5.4
+  version: 0.6.0
 platform: ruby
 authors:
 - Yoichiro Hasebe
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-12-11 00:00:00.000000000 Z
+date: 2014-10-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: sanitize
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: bzip2-ruby-rb20
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: trollop
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 description: WP2TXT extracts plain text data from Wikipedia dump file (encoded in
@@ -117,7 +103,7 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
-- .gitignore
+- ".gitignore"
 - Gemfile
 - LICENSE
 - README.md
@@ -142,17 +128,17 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: wp2txt
-rubygems_version: 2.1.11
+rubygems_version: 2.4.1
 signing_key: 
 specification_version: 4
 summary: Wikipedia dump to text converter