wp2txt 0.7.5 → 0.7.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 911e08e181a6bedb664b797d49183d0988daeba5
-  data.tar.gz: 076d1349a8aa8cf454dac42bdce7b89a82f3fca0
+  metadata.gz: b4dff862e52128851fb4db35a59a1f4e3e9e473f
+  data.tar.gz: e38612ada2785a2fed1e975460451b0d0a703e5e
 SHA512:
-  metadata.gz: 4ebc035e4f1635f150294d8b79eb474457a280707a416688f3e7712bb7788d15888b6718bfd6f4e3a790e6fb8a7623e1415255fde913bfe658dd237fa7f599cd
-  data.tar.gz: ccee00a9e1b85186d52d0b3c07b52c04fff1ecd133ff245010943312cf37e279874b5f3a757880c005ad877e957df6a4176af2269f40b3c3210951530eb4c511
+  metadata.gz: 19159a3706d0dfb687c239f3200ac3685916e63a4e3ec292d3e47acf4e8787c5ed728837bdf4b5586691adacdc75decddc1b2c7937ad483ca15a3663213d32c9
+  data.tar.gz: 8d956611e29eb4fa0d058ab6459bd96167352fdb5ee44b1819fe4688983a8ebf146cc2413e609029558d845bf9e93f9e27eaca9a35f34bf4644c234a4809146c

data/bin/wp2txt

@@ -127,8 +127,9 @@ wpconv.extract_text do |article|
   if /\A\s*\z/m =~ contents
     result = ""
   else
-    result = config[:title] ? title + "\n" + contents : 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"  
+  result.gsub!(/\[ref\]\s*\[\/ref\]/m){""}
+  result.gsub!(/\n\n\n+/m){"\n\n"}
+  result << "\n"  
 end

data/lib/wp2txt/utils.rb

@@ -68,8 +68,6 @@ $list_marks_regex = Regexp.new('\A[\*\#\;\:\ ]+')
 $pre_marks_regex = Regexp.new('\A\^\ ')
 $def_marks_regex = Regexp.new('\A[\;\:\ ]+')
 $onset_bar_regex = Regexp.new('\A[^\|]+\z')
-# $remove_table_regex = Regexp.new('\{\|[^\{\|\}]*?\|\}', Regexp::MULTILINE)
-# $remove_clade_regex = Regexp.new('\{\{(?:C|c)lade[^\{\}]*\}\}', Regexp::MULTILINE)
 
 $category_patterns = ["Category", "Categoria"].join("|")
 $category_regex = Regexp.new('[\{\[\|\b](?:' + $category_patterns + ')\:(.*?)[\}\]\|\b]', Regexp::IGNORECASE)
@@ -340,44 +338,7 @@ module Wp2txt
     end
   end
   
-  #################### methods currently unused ####################
-
-  # def process_template(str)
-  #   scanner = StringScanner.new(str)
-  #   result = process_nested_structure(scanner, "{{", "}}", $limit_recur) do |contents|
-  #     parts = contents.split("|")
-  #     case parts.size
-  #     when 0
-  #       ""
-  #     when 1
-  #       parts.first || ""
-  #     else
-  #       if parts.last.split("=").size > 1
-  #         parts.first || ""
-  #       else
-  #         parts.last || ""
-  #       end
-  #     end
-  #   end
-  #   result
-  # end
-
-  # def remove_table(str)
-  #   new_str = str.gsub($remove_table_regex, "")
-  #   if str != new_str
-  #     new_str = remove_table(new_str)
-  #   end
-  #   new_str = remove_table(new_str) unless str == new_str
-  #   return new_str
-  # end
-  
-  # def remove_clade(page)
-  #   new_page = page.gsub($remove_clade_regex, "")
-  #   new_page = remove_clade(new_page) unless page == new_page
-  #   new_page
-  # end
-
-  #################### file related utilities ####################
+#################### file related utilities ####################
 
   # collect filenames recursively
   def collect_files(str, regex = nil)

data/lib/wp2txt/version.rb

@@ -1,3 +1,3 @@
 module Wp2txt
-  VERSION = "0.7.5"
+  VERSION = "0.7.6"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: wp2txt
 version: !ruby/object:Gem::Version
-  version: 0.7.5
+  version: 0.7.6
 platform: ruby
 authors:
 - Yoichiro Hasebe
@@ -99,7 +99,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: wp2txt
-rubygems_version: 2.4.4
+rubygems_version: 2.4.3
 signing_key: 
 specification_version: 4
 summary: Wikipedia dump to text converter