Improve Ruby/RDoc scraper

lib/docs/filters/rdoc/entries.rb

@@ -23,14 +23,16 @@ module Docs
         return [] if root_page?
         require 'cgi'
 
-        css('.method-detail').map do |node|
+        css('.method-detail').inject [] do |entries, node|
           name = node['id'].dup
           name.sub! %r{\A\w+?\-.}, ''
           name.sub! %r{\A-(?!\d)}, ''
           name.gsub! '-', '%'
           name = CGI.unescape(name)
           name.prepend self.name + (node['id'] =~ /\A\w+-c-/ ? '::' : '#')
-          [name, node['id']]
+
+          entries << [name, node['id']] unless entries.any? { |entry| entry[0] == name }
+          entries
         end
       end
     end

lib/docs/scrapers/rdoc/ruby.rb

@@ -1,38 +1,24 @@
 module Docs
   class Ruby < Rdoc
     # Generated with:
-    # rdoc \
+    # find \
-    #   --format=darkfish \
-    #   --no-line-numbers \
-    #   --op=rdoc \
-    #   --visibility=public \
     #   *.c \
-    #   lib/**/*.rb \
+    #   lib \
-    #   lib/*.rb \
+    #   ext/bigdecimal \
-    #   ext/bigdecimal/*.c \
+    #   ext/date \
-    #   ext/bigdecimal/lib/*.rb \
+    #   ext/digest \
-    #   ext/bigdecimal/lib/**/*.rb \
+    #   ext/json \
-    #   ext/date/*.c \
+    #   ext/pathname \
-    #   ext/date/lib/*.rb \
+    #   ext/psych \
-    #   ext/date/lib/**/*.rb \
+    #   ext/readline \
-    #   ext/digest/*.c \
+    #   ext/ripper \
-    #   ext/digest/**/*.c \
+    #   ext/socket \
-    #   ext/digest/**/*.rb \
+    #   ext/stringio \
-    #   ext/json/lib/**/*.rb \
+    #   ext/zlib \
-    #   ext/pathname/*.c \
+    #   \( -name '*.c' -or -name '*.rb' \) \
-    #   ext/pathname/lib/*.rb \
+    #   -not -wholename '*sample/*' \
-    #   ext/psych/*.c \
+    # | xargs \
-    #   ext/psych/lib/*.rb \
+    #   rdoc --format=darkfish --no-line-numbers --op=rdoc --visibility=public
-    #   ext/psych/lib/**/*.rb \
-    #   ext/readline/*.c \
-    #   ext/ripper/*.c \
-    #   ext/ripper/lib/*.rb \
-    #   ext/ripper/lib/**/*.rb \
-    #   ext/socket/*.c \
-    #   ext/socket/lib/*.rb \
-    #   ext/socket/lib/**/*.rb \
-    #   ext/stringio/*.c \
-    #   ext/zlib/*.c
 
     self.version = '2.0.0'
     self.dir = '/Users/Thibaut/DevDocs/Docs/RDoc/Ruby'
@@ -44,36 +30,48 @@ module Docs
     options[:skip] += %w(
       fatal.html
       unknown.html
+      CompositePublisher.html
       Data.html
       E2MM.html
       English.html
       Exception2MessageMapper.html
+      EXCEPTION_TYPE.html
       GServer.html
+      Logging.html
       MakeMakefile.html
       ParallelEach.html
       Requirement.html
+      SshDirPublisher.html
+      SshFilePublisher.html
+      SshFreshDirPublisher.html
+      Sys.html
       YAML/DBM.html)
 
     options[:skip_patterns] = [
       /\AComplex/,
+      /\AJSON\/Ext/,
       /\AGem/,
-      /\AHttpServer/,
+      /\AHTTP/i,
       /\AIRB/,
       /\AMiniTest/i,
+      /\ANet\/(?!HTTP)/,
       /\ANQXML/,
       /\AOpenSSL/,
+      /\AOptionParser\//,
       /\APride/,
+      /\APsych\//,
       /\ARacc/,
       /\ARake/,
       /\ARbConfig/,
       /\ARDoc/,
       /\AREXML/,
       /\ARSS/,
+      /\AShell\//,
+      /\ASocket\//,
       /\ATest/,
       /\AWEBrick/,
       /\AXML/,
-      /\AXMP/
+      /\AXMP/]
-    ]
 
     options[:attribution] = <<-HTML
       Ruby Core &copy; 1993&ndash;2013 Yukihiro Matsumoto<br>