Merge pull request #728 from github/fix-dup-primary-extension-for-mumps

Ensure no two languages have the same primary extension

Gemfile

@@ -1,2 +1,2 @@
-source :rubygems
+source 'https://rubygems.org'
 gemspec

LICENSE

@@ -1,4 +1,4 @@
-Copyright (c) 2011 GitHub, Inc.
+Copyright (c) 2011-2013 GitHub, Inc.
 
 Permission is hereby granted, free of charge, to any person
 obtaining a copy of this software and associated documentation

README.md

@@ -8,13 +8,18 @@ We use this library at GitHub to detect blob languages, highlight code, ignore b
 
 Linguist defines the list of all languages known to GitHub in a [yaml file](https://github.com/github/linguist/blob/master/lib/linguist/languages.yml). In order for a file to be highlighted, a language and lexer must be defined there.
 
-Most languages are detected by their file extension. This is the fastest and most common situation. For script files, which are usually extensionless, we do "deep content inspection"™ and check the shebang of the file. Checking the file's contents may also be used for disambiguating languages. C, C++ and Obj-C all use `.h` files. Looking for common keywords, we are usually able to guess the correct language.
+Most languages are detected by their file extension. This is the fastest and most common situation.
+
+For disambiguating between files with common extensions, we use a [Bayesian classifier](https://github.com/github/linguist/blob/master/lib/linguist/classifier.rb). For an example, this helps us tell the difference between `.h` files which could be either C, C++, or Obj-C.
 
 In the actual GitHub app we deal with `Grit::Blob` objects. For testing, there is a simple `FileBlob` API.
 
-    Linguist::FileBlob.new("lib/linguist.rb").language.name #=> "Ruby"
+```ruby
 
-    Linguist::FileBlob.new("bin/linguist").language.name #=> "Ruby"
+Linguist::FileBlob.new("lib/linguist.rb").language.name #=> "Ruby"
+
+Linguist::FileBlob.new("bin/linguist").language.name #=> "Ruby"
+```
 
 See [lib/linguist/language.rb](https://github.com/github/linguist/blob/master/lib/linguist/language.rb) and [lib/linguist/languages.yml](https://github.com/github/linguist/blob/master/lib/linguist/languages.yml).
 
@@ -22,30 +27,19 @@ See [lib/linguist/language.rb](https://github.com/github/linguist/blob/master/li
 
 The actual syntax highlighting is handled by our Pygments wrapper, [pygments.rb](https://github.com/tmm1/pygments.rb). It also provides a [Lexer abstraction](https://github.com/tmm1/pygments.rb/blob/master/lib/pygments/lexer.rb) that determines which highlighter should be used on a file.
 
-We typically run on a prerelease version of Pygments to get early access to new lexers. The [lexers.yml](https://github.com/github/linguist/blob/master/lib/linguist/lexers.yml) file is a dump of the lexers we have available on our server. If there is a new lexer in pygments-main not on the list, [open an issue](https://github.com/github/linguist/issues) and we'll try to upgrade it soon.
-
-### MIME type detection
-
-Most of the MIME types handling is done by the Ruby [mime-types gem](https://github.com/halostatue/mime-types). But we have our own list of additions and overrides. To add or modify this list, see [lib/linguist/mimes.yml](https://github.com/github/linguist/blob/master/lib/linguist/mimes.yml).
-
-MIME types are used to set the Content-Type of raw binary blobs which are served from a special `raw.github.com` domain. However, all text blobs are served as `text/plain` regardless of their type to ensure they open in the browser rather than downloading.
-
-The MIME type also determines whether a blob is binary or plain text. So if you're seeing a blob that says "View Raw" and it is actually plain text, the mime type and encoding probably needs to be explicitly stated.
-
-    Linguist::FileBlob.new("linguist.zip").binary? #=> true
-
-See [lib/linguist/mimes.yml](https://github.com/github/linguist/blob/master/lib/linguist/mimes.yml).
+We typically run on a pre-release version of Pygments, [pygments.rb](https://github.com/tmm1/pygments.rb), to get early access to new lexers. The [languages.yml](https://github.com/github/linguist/blob/master/lib/linguist/languages.yml) file is a dump of the lexers we have available on our server.
 
 ### Stats
 
-The [Language Graph](https://github.com/github/linguist/graphs/languages) is built by aggregating the languages of all repo's blobs. The top language in the graph determines the project's primary language. Collectively, these stats make up the [Top Languages](https://github.com/languages) page.
+The Language Graph you see on every repository is built by aggregating the languages of all repo's blobs. The top language in the graph determines the project's primary language. Collectively, these stats make up the [Top Languages](https://github.com/languages) page.
 
 The repository stats API can be used on a directory:
 
-    project = Linguist::Repository.from_directory(".")
-    project.language.name  #=> "Ruby"
-    project.languages      #=> { "Ruby" => 0.98,
-                                 "Shell" => 0.02 }
+```ruby
+project = Linguist::Repository.from_directory(".")
+project.language.name  #=> "Ruby"
+project.languages      #=> { "Ruby" => 0.98, "Shell" => 0.02 }
+```
 
 These stats are also printed out by the binary. Try running `linguist` on itself:
 
@@ -56,21 +50,27 @@ These stats are also printed out by the binary. Try running `linguist` on itself
 
 Checking other code into your git repo is a common practice. But this often inflates your project's language stats and may even cause your project to be labeled as another language. We are able to identify some of these files and directories and exclude them.
 
-    Linguist::FileBlob.new("vendor/plugins/foo.rb").vendored? # => true
+```ruby
+Linguist::FileBlob.new("vendor/plugins/foo.rb").vendored? # => true
+```
 
 See [Linguist::BlobHelper#vendored?](https://github.com/github/linguist/blob/master/lib/linguist/blob_helper.rb) and [lib/linguist/vendor.yml](https://github.com/github/linguist/blob/master/lib/linguist/vendor.yml).
 
 #### Generated file detection
 
-Not all plain text files are true source files. Generated files like minified js and compiled CoffeeScript can be detected and excluded from language stats. As an extra bonus, these files are suppressed in Diffs.
+Not all plain text files are true source files. Generated files like minified js and compiled CoffeeScript can be detected and excluded from language stats. As an extra bonus, these files are suppressed in diffs.
 
-    Linguist::FileBlob.new("underscore.min.js").generated? # => true
+```ruby
+Linguist::FileBlob.new("underscore.min.js").generated? # => true
+```
 
-See [Linguist::BlobHelper#generated?](https://github.com/github/linguist/blob/master/lib/linguist/blob_helper.rb).
+See [Linguist::Generated#generated?](https://github.com/github/linguist/blob/master/lib/linguist/generated.rb).
 
 ## Installation
 
-To get it, clone the repo and run [Bundler](http://gembundler.com/) to install its dependencies.
+github.com is usually running the latest version of the `github-linguist` gem that is released on [RubyGems.org](http://rubygems.org/gems/github-linguist).
+
+But for development you are going to want to checkout out the source. To get it, clone the repo and run [Bundler](http://gembundler.com/) to install its dependencies.
 
     git clone https://github.com/github/linguist.git
     cd linguist/
@@ -80,17 +80,16 @@ To run the tests:
 
     bundle exec rake test
 
-*Since this code is specific to GitHub, is not published as a official rubygem.*
-
-If you are seeing errors like `StandardError: could not find any magic files!`, it means the CharlockHolmes gem didn’t install correctly. See the [installing section](https://github.com/brianmario/charlock_holmes/blob/master/README.md) of the CharlockHolmes README for more information.
-
 ## Contributing
 
-1. Fork it.
-2. Create a branch (`git checkout -b detect-foo-language`)
-3. Make your changes
-4. Run the tests (`bundle install` then `bundle exec rake`)
-5. Commit your changes (`git commit -am "Added detection for the new Foo language"`)
-6. Push to the branch (`git push origin detect-foo-language`)
-7. Create a [Pull Request](http://help.github.com/pull-requests/) from your branch.
-8. Promote it. Get others to drop in and +1 it.
+The majority of patches won't need to touch any Ruby code at all. The [master language list](https://github.com/github/linguist/blob/master/lib/linguist/languages.yml) is just a configuration file.
+
+We try to only add languages once they have some usage on GitHub, so please note in-the-wild usage examples in your pull request.
+
+Almost all bug fixes or new language additions should come with some additional code samples. Just drop them under [`samples/`](https://github.com/github/linguist/tree/master/samples) in the correct subdirectory and our test suite will automatically test them. In most cases you shouldn't need to add any new assertions.
+
+### Testing
+
+Sometimes getting the tests running can be too much work, especially if you don't have much Ruby experience. It's okay, be lazy and let our build bot [Travis](http://travis-ci.org/#!/github/linguist) run the tests for you. Just open a pull request and the bot will start cranking away.
+
+Here's our current build status, which is hopefully green: [![Build Status](https://secure.travis-ci.org/github/linguist.png?branch=master)](http://travis-ci.org/github/linguist)

Rakefile

@@ -3,27 +3,23 @@ require 'rake/testtask'
 
 task :default => :test
 
-Rake::TestTask.new do |t|
-  t.warning = true
+Rake::TestTask.new
+
+task :samples do
+  require 'linguist/samples'
+  require 'yajl'
+  data = Linguist::Samples.data
+  json = Yajl::Encoder.encode(data, :pretty => true)
+  File.open('lib/linguist/samples.json', 'w') { |io| io.write json }
 end
 
-
-file 'lib/linguist/classifier.yml' => Dir['test/fixtures/**/*'] do |f|
-  require 'linguist/sample'
-  classifier = Linguist::Sample.classifier
-  File.open(f.name, 'w') { |io| YAML.dump(classifier, io) }
-end
-
-CLOBBER.include 'lib/linguist/classifier.yml'
-
-task :classifier => ['lib/linguist/classifier.yml']
-
 namespace :classifier do
   LIMIT = 1_000
 
   desc "Run classifier against #{LIMIT} public gists"
   task :test do
     require 'linguist/classifier'
+    require 'linguist/samples'
 
     total, correct, incorrect = 0, 0, 0
     $stdout.sync = true
@@ -32,10 +28,10 @@ namespace :classifier do
       next if file_language.nil? || file_language == 'Text'
       begin
         data = open(file_url).read
-        guessed_language, score = Linguist::Classifier.instance.classify(data).first
+        guessed_language, score = Linguist::Classifier.classify(Linguist::Samples::DATA, data).first
 
         total += 1
-        guessed_language.name == file_language ? correct += 1 : incorrect += 1
+        guessed_language == file_language ? correct += 1 : incorrect += 1
 
         print "\r\e[0K%d:%d  %g%%" % [correct, incorrect, (correct.to_f/total.to_f)*100]
         $stdout.flush

bin/linguist

@@ -1,5 +1,9 @@
 #!/usr/bin/env ruby
 
+# linguist — detect language type for a file, or, given a directory, determine language breakdown
+#
+# usage: linguist <path>
+
 require 'linguist/file_blob'
 require 'linguist/repository'
 
@@ -23,12 +27,11 @@ elsif File.file?(path)
 
   puts "#{blob.name}: #{blob.loc} lines (#{blob.sloc} sloc)"
   puts "  type:      #{type}"
-  puts "  extension: #{blob.pathname.extname}"
   puts "  mime type: #{blob.mime_type}"
   puts "  language:  #{blob.language}"
 
   if blob.large?
-    puts "  blob is to large to be shown"
+    puts "  blob is too large to be shown"
   end
 
   if blob.generated?

github-linguist.gemspec

@@ -1,17 +1,20 @@
 Gem::Specification.new do |s|
   s.name    = 'github-linguist'
-  s.version = '2.0.1'
+  s.version = '2.9.5'
   s.summary = "GitHub Language detection"
 
-  s.authors = "GitHub"
+  s.authors  = "GitHub"
+  s.homepage = "https://github.com/github/linguist"
 
   s.files = Dir['lib/**/*']
   s.executables << 'linguist'
 
   s.add_dependency 'charlock_holmes', '~> 0.6.6'
-  s.add_dependency 'escape_utils',    '~> 0.2.3'
-  s.add_dependency 'mime-types',      '~> 1.18'
-  s.add_dependency 'pygments.rb',     '~> 0.2.13'
+  s.add_dependency 'escape_utils',    '~> 0.3.1'
+  s.add_dependency 'mime-types',      '~> 1.19'
+  s.add_dependency 'pygments.rb',     '~> 0.5.2'
+  s.add_development_dependency 'mocha'
   s.add_development_dependency 'json'
   s.add_development_dependency 'rake'
+  s.add_development_dependency 'yajl-ruby'
 end

lib/linguist.rb

@@ -1,5 +1,5 @@
 require 'linguist/blob_helper'
+require 'linguist/generated'
 require 'linguist/language'
-require 'linguist/mime'
-require 'linguist/pathname'
 require 'linguist/repository'
+require 'linguist/samples'

lib/linguist/blob_helper.rb

@@ -1,24 +1,22 @@
-require 'linguist/classifier'
+require 'linguist/generated'
 require 'linguist/language'
-require 'linguist/mime'
-require 'linguist/pathname'
 
 require 'charlock_holmes'
 require 'escape_utils'
+require 'mime/types'
 require 'pygments'
 require 'yaml'
 
 module Linguist
+  # DEPRECATED Avoid mixing into Blob classes. Prefer functional interfaces
+  # like `Language.detect` over `Blob#language`. Functions are much easier to
+  # cache and compose.
+  #
+  # Avoid adding additional bloat to this module.
+  #
   # BlobHelper is a mixin for Blobish classes that respond to "name",
   # "data" and "size" such as Grit::Blob.
   module BlobHelper
-    # Internal: Get a Pathname wrapper for Blob#name
-    #
-    # Returns a Pathname.
-    def pathname
-      Pathname.new(name || "")
-    end
-
     # Public: Get the extname of the path
     #
     # Examples
@@ -28,7 +26,23 @@ module Linguist
     #
     # Returns a String
     def extname
-      pathname.extname
+      File.extname(name.to_s)
+    end
+
+    # Internal: Lookup mime type for extension.
+    #
+    # Returns a MIME::Type
+    def _mime_type
+      if defined? @_mime_type
+        @_mime_type
+      else
+        guesses = ::MIME::Types.type_for(extname.to_s)
+
+        # Prefer text mime types over binary
+        @_mime_type = guesses.detect { |type| type.ascii? } ||
+          # Otherwise use the first guess
+          guesses.first
+      end
     end
 
     # Public: Get the actual blob mime type
@@ -40,7 +54,23 @@ module Linguist
     #
     # Returns a mime type String.
     def mime_type
-      @mime_type ||= pathname.mime_type
+      _mime_type ? _mime_type.to_s : 'text/plain'
+    end
+
+    # Internal: Is the blob binary according to its mime type
+    #
+    # Return true or false
+    def binary_mime_type?
+      _mime_type ? _mime_type.binary? : false
+    end
+
+    # Internal: Is the blob binary according to its mime type,
+    # overriding it if we have better data from the languages.yml
+    # database.
+    #
+    # Return true or false
+    def likely_binary?
+      binary_mime_type? && !Language.find_by_filename(name)
     end
 
     # Public: Get the Content-Type header value
@@ -72,7 +102,7 @@ module Linguist
       elsif name.nil?
         "attachment"
       else
-        "attachment; filename=#{EscapeUtils.escape_url(pathname.basename)}"
+        "attachment; filename=#{EscapeUtils.escape_url(File.basename(name))}"
       end
     end
 
@@ -91,15 +121,6 @@ module Linguist
       @detect_encoding ||= CharlockHolmes::EncodingDetector.new.detect(data) if data
     end
 
-    # Public: Is the blob binary according to its mime type
-    #
-    # Return true or false
-    def binary_mime_type?
-      if mime_type = Mime.lookup_mime_type_for(pathname.extname)
-        mime_type.binary?
-      end
-    end
-
     # Public: Is the blob binary?
     #
     # Return true or false
@@ -133,23 +154,28 @@ module Linguist
     #
     # Return true or false
     def image?
-      ['.png', '.jpg', '.jpeg', '.gif'].include?(extname)
+      ['.png', '.jpg', '.jpeg', '.gif'].include?(extname.downcase)
     end
 
-    # Public: Is the blob a possible drupal php file?
+    # Public: Is the blob a supported 3D model format?
     #
     # Return true or false
-    def drupal_extname?
-      ['.module', '.install', '.test', '.inc'].include?(extname)
+    def solid?
+      extname.downcase == '.stl'
     end
 
-    # Public: Is the blob likely to have a shebang?
+    # Public: Is this blob a CSV file?
     #
     # Return true or false
-    def shebang_extname?
-      extname.empty? &&
-        mode &&
-        (mode.to_i(8) & 05) == 05
+    def csv?
+      text? && extname.downcase == '.csv'
+    end
+
+    # Public: Is the blob a PDF?
+    #
+    # Return true or false
+    def pdf?
+      extname.downcase == '.pdf'
     end
 
     MEGABYTE = 1024 * 1024
@@ -163,14 +189,13 @@ module Linguist
 
     # Public: Is the blob safe to colorize?
     #
-    # We use Pygments.rb for syntax highlighting blobs, which
-    # has some quirks and also is essentially 'un-killable' via
-    # normal timeout.  To workaround this we try to
-    # carefully handling Pygments.rb anything it can't handle.
-    #
+    # We use Pygments for syntax highlighting blobs. Pygments
+    # can be too slow for very large blobs or for certain 
+    # corner-case blobs.
+    # 
     # Return true or false
     def safe_to_colorize?
-      text? && !large? && !high_ratio_of_long_lines?
+      !large? && text? && !high_ratio_of_long_lines?
     end
 
     # Internal: Does the blob have a ratio of long lines?
@@ -214,7 +239,12 @@ module Linguist
     #
     # Returns an Array of lines
     def lines
-      @lines ||= (viewable? && data) ? data.split("\n", -1) : []
+      @lines ||=
+        if viewable? && data
+          data.split(/\r\n|\r|\n/, -1)
+        else
+          []
+        end
     end
 
     # Public: Get number of lines of code
@@ -235,171 +265,16 @@ module Linguist
       lines.grep(/\S/).size
     end
 
-    # Internal: Compute average line length.
-    #
-    # Returns Integer.
-    def average_line_length
-      if lines.any?
-        lines.inject(0) { |n, l| n += l.length } / lines.length
-      else
-        0
-      end
-    end
-
     # Public: Is the blob a generated file?
     #
-    # Generated source code is supressed in diffs and is ignored by
+    # Generated source code is suppressed in diffs and is ignored by
     # language statistics.
     #
-    # Requires Blob#data
-    #
-    # Includes:
-    # - XCode project XML files
-    # - Minified JavaScript
-    # - Compiled CoffeeScript
-    # - PEG.js-generated parsers
-    #
-    # Please add additional test coverage to
-    # `test/test_blob.rb#test_generated` if you make any changes.
+    # May load Blob#data
     #
     # Return true or false
     def generated?
-      if name == 'Gemfile.lock' || minified_javascript? || compiled_coffeescript? ||
-      xcode_project_file? || generated_net_docfile? || generated_parser?
-        true
-      else
-        false
-      end
-    end
-
-    # Internal: Is the blob an XCode project file?
-    #
-    # Generated if the file extension is an XCode project
-    # file extension.
-    #
-    # Returns true of false.
-    def xcode_project_file?
-      ['.xib', '.nib', '.storyboard', '.pbxproj', '.xcworkspacedata', '.xcuserstate'].include?(extname)
-    end
-
-    # Internal: Is the blob minified JS?
-    #
-    # Consider JS minified if the average line length is
-    # greater then 100c.
-    #
-    # Returns true or false.
-    def minified_javascript?
-      return unless extname == '.js'
-      average_line_length > 100
-    end
-
-    # Internal: Is the blob of JS a parser generated by PEG.js?
-    #
-    # Requires Blob#data
-    #
-    # PEG.js-generated parsers are not meant to be consumed by humans.
-    #
-    # Return true or false
-    def generated_parser?
-      return false unless extname == '.js'
-
-      # PEG.js-generated parsers include a comment near the top  of the file
-      # that marks them as such.
-      if lines[0..4].join('') =~ /^(?:[^\/]|\/[^\*])*\/\*(?:[^\*]|\*[^\/])*Generated by PEG.js/
-        return true
-      end
-
-      false
-    end
-
-    # Internal: Is the blob of JS generated by CoffeeScript?
-    #
-    # Requires Blob#data
-    #
-    # CoffeScript is meant to output JS that would be difficult to
-    # tell if it was generated or not. Look for a number of patterns
-    # output by the CS compiler.
-    #
-    # Return true or false
-    def compiled_coffeescript?
-      return false unless extname == '.js'
-
-      # CoffeeScript generated by > 1.2 include a comment on the first line
-      if lines[0] =~ /^\/\/ Generated by /
-        return true
-      end
-
-      if lines[0] == '(function() {' &&     # First line is module closure opening
-          lines[-2] == '}).call(this);' &&  # Second to last line closes module closure
-          lines[-1] == ''                   # Last line is blank
-
-        score = 0
-
-        lines.each do |line|
-          if line =~ /var /
-            # Underscored temp vars are likely to be Coffee
-            score += 1 * line.gsub(/(_fn|_i|_len|_ref|_results)/).count
-
-            # bind and extend functions are very Coffee specific
-            score += 3 * line.gsub(/(__bind|__extends|__hasProp|__indexOf|__slice)/).count
-          end
-        end
-
-        # Require a score of 3. This is fairly arbitrary. Consider
-        # tweaking later.
-        score >= 3
-      else
-        false
-      end
-    end
-
-    # Internal: Is this a generated documentation file for a .NET assembly?
-    #
-    # Requires Blob#data
-    #
-    # .NET developers often check in the XML Intellisense file along with an
-    # assembly - however, these don't have a special extension, so we have to
-    # dig into the contents to determine if it's a docfile. Luckily, these files
-    # are extremely structured, so recognizing them is easy.
-    #
-    # Returns true or false
-    def generated_net_docfile?
-      return false unless extname.downcase == ".xml"
-      return false unless lines.count > 3
-
-      # .NET Docfiles always open with <doc> and their first tag is an
-      # <assembly> tag
-      return lines[1].include?("<doc>") &&
-        lines[2].include?("<assembly>") &&
-        lines[-2].include?("</doc>")
-    end
-
-    # Public: Should the blob be indexed for searching?
-    #
-    # Excluded:
-    # - Files over 0.1MB
-    # - Non-text files
-    # - Langauges marked as not searchable
-    # - Generated source files
-    #
-    # Please add additional test coverage to
-    # `test/test_blob.rb#test_indexable` if you make any changes.
-    #
-    # Return true or false
-    def indexable?
-      if binary?
-        false
-      elsif language.nil?
-        false
-      elsif !language.searchable?
-        false
-      elsif generated?
-        false
-      elsif size > 100 * 1024
-        false
-      else
-        true
-      end
+      @_generated ||= Generated.generated?(name, lambda { data })
     end
 
     # Public: Detects the Language of the blob.
@@ -408,33 +283,15 @@ module Linguist
     #
     # Returns a Language or nil if none is detected
     def language
-      if defined? @language
-        @language
+      return @language if defined? @language
+
+      if defined?(@data) && @data.is_a?(String)
+        data = @data
       else
-        @language = guess_language
+        data = lambda { (binary_mime_type? || binary?) ? "" : self.data }
       end
-    end
 
-    # Internal: Guess language
-    #
-    # Please add additional test coverage to
-    # `test/test_blob.rb#test_language` if you make any changes.
-    #
-    # Returns a Language or nil
-    def guess_language
-      return if binary_mime_type?
-
-      # Disambiguate between multiple language extensions
-      disambiguate_extension_language ||
-
-        # See if there is a Language for the extension
-        pathname.language ||
-
-        # Look for idioms in first line
-        first_line_language ||
-
-        # Try to detect Language from shebang line
-        shebang_language
+      @language = Language.detect(name.to_s, data, mode)
     end
 
     # Internal: Get the lexer of the blob.
@@ -444,247 +301,6 @@ module Linguist
       language ? language.lexer : Pygments::Lexer.find_by_name('Text only')
     end
 
-    # Internal: Disambiguates between multiple language extensions.
-    #
-    # Delegates to "guess_EXTENSION_language".
-    #
-    # Please add additional test coverage to
-    # `test/test_blob.rb#test_language` if you add another method.
-    #
-    # Returns a Language or nil.
-    def disambiguate_extension_language
-      if Language.ambiguous?(extname)
-        # name = "guess_#{extname.sub(/^\./, '')}_language"
-        # send(name) if respond_to?(name)
-
-        possible_languages = Language.all.select { |l| l.extensions.include?(extname) }
-        if possible_languages.any?
-          if result = Classifier.instance.classify(data, possible_languages).first
-            result[0]
-          end
-        end
-      end
-    end
-
-    # Internal: Guess language of .cls files
-    #
-    # Returns a Language.
-    def guess_cls_language
-      if lines.grep(/^(%|\\)/).any?
-        Language['TeX']
-      elsif lines.grep(/^\s*(CLASS|METHOD|INTERFACE).*:\s*/i).any? || lines.grep(/^\s*(USING|DEFINE)/i).any?
-        Language['OpenEdge ABL']
-      elsif lines.grep(/\{$/).any? || lines.grep(/\}$/).any?
-        Language['Apex']
-      elsif lines.grep(/^(\'\*|Attribute|Option|Sub|Private|Protected|Public|Friend)/i).any?
-        Language['Visual Basic']
-      else
-        # The most common language should be the fallback
-        Language['TeX']
-      end
-    end
-
-    # Internal: Guess language of header files (.h).
-    #
-    # Returns a Language.
-    def guess_h_language
-      if lines.grep(/^@(interface|property|private|public|end)/).any?
-        Language['Objective-C']
-      elsif lines.grep(/^class |^\s+(public|protected|private):/).any?
-        Language['C++']
-      else
-        Language['C']
-      end
-    end
-
-    # Internal: Guess language of .m files.
-    #
-    # Objective-C heuristics:
-    # * Keywords  ("#import", "#include", "#ifdef", #define, "@end") or "//" and opening "\*" comments
-    #
-    # Matlab heuristics:
-    # * Leading "function " of "classdef " keyword
-    # * "%" comments
-    #
-    # Note: All "#" keywords, e.g., "#import", are guaranteed to be Objective-C. Because the ampersand
-    # is used to created function handles and anonymous functions in Matlab, most "@" keywords are not
-    # safe heuristics. However, "end" is a reserved term in Matlab and can't be used to create a valid
-    # function handle. Because @end is required to close any @implementation, @property, @interface,
-    # @synthesize, etc. directive in Objective-C, only @end needs to be checked for.
-    #
-    # Returns a Language.
-    def guess_m_language
-      # Objective-C keywords or comments
-      if lines.grep(/^#(import|include|ifdef|define)|@end/).any? || lines.grep(/^\s*\/\//).any? || lines.grep(/^\s*\/\*/).any?
-        Language['Objective-C']
-
-      # Matlab file function or class or comments
-      elsif lines.any? && lines.first.match(/^\s*(function |classdef )/) || lines.grep(/^\s*%/).any?
-        Language['Matlab']
-
-      # Fallback to Objective-C, don't want any Matlab false positives
-      else
-        Language['Objective-C']
-      end
-    end
-
-    # Internal: Guess language of .pl files
-    #
-    # The rules for disambiguation are:
-    #
-    # 1. Many perl files begin with a shebang
-    # 2. Most Prolog source files have a rule somewhere (marked by the :- operator)
-    # 3. Default to Perl, because it is more popular
-    #
-    # Returns a Language.
-    def guess_pl_language
-      if shebang_script == 'perl'
-        Language['Perl']
-      elsif lines.grep(/:-/).any?
-        Language['Prolog']
-      else
-        Language['Perl']
-      end
-    end
-
-    # Internal: Guess language of .r files.
-    #
-    # Returns a Language.
-    def guess_r_language
-      if lines.grep(/(rebol|(:\s+func|make\s+object!|^\s*context)\s*\[)/i).any?
-        Language['Rebol']
-      else
-        Language['R']
-      end
-    end
-
-    # Internal: Guess language of .t files.
-    #
-    # Returns a Language.
-    def guess_t_language
-      score = 0
-      score += 1 if lines.grep(/^% /).any?
-      score += data.gsub(/ := /).count
-      score += data.gsub(/proc |procedure |fcn |function /).count
-      score += data.gsub(/var \w+: \w+/).count
-
-      # Tell-tale signs its gotta be Perl
-      if lines.grep(/^(my )?(sub |\$|@|%)\w+/).any?
-        score = 0
-      end
-
-      if score >= 3
-        Language['Turing']
-      else
-        Language['Perl']
-      end
-    end
-
-    # Internal: Guess language of .v files.
-    #
-    # Returns a Language
-    def guess_v_language
-      if lines.grep(/^(\/\*|\/\/|module|parameter|input|output|wire|reg|always|initial|begin|\`)/).any?
-        Language['Verilog']
-      else
-        Language['Coq']
-      end
-    end
-
-    # Internal: Guess language of .gsp files.
-    #
-    # Returns a Language.
-    def guess_gsp_language
-      if lines.grep(/<%|<%@|\$\{|<%|<g:|<meta name="layout"|<r:/).any?
-        Language['Groovy Server Pages']
-      else
-        Language['Gosu']
-      end
-    end
-
-    # Internal: Guess language from the first line.
-    #
-    # Look for leading "<?php" in Drupal files
-    #
-    # Returns a Language.
-    def first_line_language
-      # Only check files with drupal php extensions
-      return unless drupal_extname?
-
-      # Fail fast if blob isn't viewable?
-      return unless viewable?
-
-      if lines.first.to_s =~ /^<\?php/
-        Language['PHP']
-      end
-    end
-
-    # Internal: Extract the script name from the shebang line
-    #
-    # Requires Blob#data
-    #
-    # Examples
-    #
-    #   '#!/usr/bin/ruby'
-    #   # => 'ruby'
-    #
-    #   '#!/usr/bin/env ruby'
-    #   # => 'ruby'
-    #
-    #   '#!/usr/bash/python2.4'
-    #   # => 'python'
-    #
-    # Please add additional test coverage to
-    # `test/test_blob.rb#test_shebang_script` if you make any changes.
-    #
-    # Returns a script name String or nil
-    def shebang_script
-      # Fail fast if blob isn't viewable?
-      return unless viewable?
-
-      if lines.any? && (match = lines[0].match(/(.+)\n?/)) && (bang = match[0]) =~ /^#!/
-        bang.sub!(/^#! /, '#!')
-        tokens = bang.split(' ')
-        pieces = tokens.first.split('/')
-        if pieces.size > 1
-          script = pieces.last
-        else
-          script = pieces.first.sub('#!', '')
-        end
-
-        script = script == 'env' ? tokens[1] : script
-
-        # python2.4 => python
-        if script =~ /((?:\d+\.?)+)/
-          script.sub! $1, ''
-        end
-
-        # Check for multiline shebang hacks that exec themselves
-        #
-        #   #!/bin/sh
-        #   exec foo "$0" "$@"
-        #
-        if script == 'sh' &&
-            lines[0...5].any? { |l| l.match(/exec (\w+).+\$0.+\$@/) }
-          script = $1
-        end
-
-        script
-      end
-    end
-
-    # Internal: Get Language for shebang script
-    #
-    # Returns the Language or nil
-    def shebang_language
-      # Skip file extensions unlikely to have shebangs
-      return unless shebang_extname?
-
-      if script = shebang_script
-        Language[script]
-      end
-    end
-
     # Public: Highlight syntax of blob
     #
     # options - A Hash of options (defaults to {})
@@ -696,26 +312,5 @@ module Linguist
       options[:options][:encoding] ||= encoding
       lexer.highlight(data, options)
     end
-
-    # Public: Highlight syntax of blob without the outer highlight div
-    # wrapper.
-    #
-    # options - A Hash of options (defaults to {})
-    #
-    # Returns html String
-    def colorize_without_wrapper(options = {})
-      if text = colorize(options)
-        text[%r{<div class="highlight"><pre>(.*?)</pre>\s*</div>}m, 1]
-      else
-        ''
-      end
-    end
-
-    Language.overridden_extensions.each do |extension|
-      name = "guess_#{extension.sub(/^\./, '')}_language".to_sym
-      unless instance_methods.map(&:to_sym).include?(name)
-        raise NotImplementedError, "Language##{name} was not defined"
-      end
-    end
   end
 end

lib/linguist/classifier.rb

@@ -1,116 +1,101 @@
-require 'linguist/language'
 require 'linguist/tokenizer'
 
 module Linguist
   # Language bayesian classifier.
   class Classifier
-    # Internal: Path to persisted classifier db.
-    PATH = File.expand_path('../classifier.yml', __FILE__)
-
-    # Public: Check if persisted db exists on disk.
-    #
-    # Returns Boolean.
-    def self.exist?
-      File.exist?(PATH)
-    end
-
-    # Public: Get persisted Classifier instance.
-    #
-    # Returns Classifier.
-    def self.instance
-      @instance ||= YAML.load_file(PATH)
-    end
-
-    # Public: Initialize a Classifier.
-    def initialize
-      @tokens_total    = 0
-      @languages_total = 0
-      @tokens          = Hash.new { |h, k| h[k] = Hash.new(0) }
-      @language_tokens = Hash.new(0)
-      @languages       = Hash.new(0)
-    end
-
-    # Public: Compare Classifier objects.
-    #
-    # other - Classifier object to compare to.
-    #
-    # Returns Boolean.
-    def eql?(other)
-      # Lazy fast check counts only
-      other.is_a?(self.class) &&
-        @tokens_total == other.instance_variable_get(:@tokens_total) &&
-        @languages_total == other.instance_variable_get(:@languages_total)
-    end
-    alias_method :==, :eql?
-
     # Public: Train classifier that data is a certain language.
     #
-    # language - Language of data
+    # db       - Hash classifier database object
+    # language - String language of data
     # data     - String contents of file
     #
     # Examples
     #
-    #   train(Language['Ruby'], "def hello; end")
+    #   Classifier.train(db, 'Ruby', "def hello; end")
     #
     # Returns nothing.
-    def train(language, data)
-      language = language.name
-      tokens   = Tokenizer.new(data).tokens
+    #
+    # Set LINGUIST_DEBUG=1 or =2 to see probabilities per-token,
+    # per-language.  See also dump_all_tokens, below.
+    def self.train!(db, language, data)
+      tokens = Tokenizer.tokenize(data)
+
+      db['tokens_total'] ||= 0
+      db['languages_total'] ||= 0
+      db['tokens'] ||= {}
+      db['language_tokens'] ||= {}
+      db['languages'] ||= {}
 
       tokens.each do |token|
-        @tokens[language][token] += 1
-        @language_tokens[language] += 1
-        @tokens_total += 1
+        db['tokens'][language] ||= {}
+        db['tokens'][language][token] ||= 0
+        db['tokens'][language][token] += 1
+        db['language_tokens'][language] ||= 0
+        db['language_tokens'][language] += 1
+        db['tokens_total'] += 1
       end
-      @languages[language] += 1
-      @languages_total += 1
+      db['languages'][language] ||= 0
+      db['languages'][language] += 1
+      db['languages_total'] += 1
 
       nil
     end
 
-    # Public: Verify internal counts are consistent.
-    #
-    # Returns Boolean.
-    def verify
-      @languages.inject(0) { |n, (l, c)| n += c } == @languages_total &&
-        @language_tokens.inject(0) { |n, (l, c)| n += c } == @tokens_total &&
-        @tokens.inject(0) { |n, (l, ts)| n += ts.inject(0) { |m, (t, c)| m += c } } == @tokens_total
-    end
-
-    # Public: Prune infrequent tokens.
-    #
-    # Returns receiver Classifier instance.
-    def gc
-      self
-    end
-
     # Public: Guess language of data.
     #
+    # db        - Hash of classifier tokens database.
     # data      - Array of tokens or String data to analyze.
-    # languages - Array of Languages to restrict to.
+    # languages - Array of language name Strings to restrict to.
     #
     # Examples
     #
-    #   classify("def hello; end")
-    #   # => [ [Language['Ruby'], 0.90], [Language['Python'], 0.2], ... ]
+    #   Classifier.classify(db, "def hello; end")
+    #   # => [ 'Ruby', 0.90], ['Python', 0.2], ... ]
     #
     # Returns sorted Array of result pairs. Each pair contains the
-    # Language and a Float score.
-    def classify(tokens, languages = @languages.keys)
-      return [] if tokens.nil?
-      tokens = Tokenizer.new(tokens).tokens if tokens.is_a?(String)
-
-      scores = {}
-      languages.each do |language|
-        language_name = language.is_a?(Language) ? language.name : language
-        scores[language_name] = tokens_probability(tokens, language_name) +
-                                   language_probability(language_name)
-      end
-
-      scores.sort { |a, b| b[1] <=> a[1] }.map { |score| [Language[score[0]], score[1]] }
+    # String language name and a Float score.
+    def self.classify(db, tokens, languages = nil)
+      languages ||= db['languages'].keys
+      new(db).classify(tokens, languages)
     end
 
-    # Internal: Probably of set of tokens in a language occuring - P(D | C)
+    # Internal: Initialize a Classifier.
+    def initialize(db = {})
+      @tokens_total    = db['tokens_total']
+      @languages_total = db['languages_total']
+      @tokens          = db['tokens']
+      @language_tokens = db['language_tokens']
+      @languages       = db['languages']
+    end
+
+    # Internal: Guess language of data
+    #
+    # data      - Array of tokens or String data to analyze.
+    # languages - Array of language name Strings to restrict to.
+    #
+    # Returns sorted Array of result pairs. Each pair contains the
+    # String language name and a Float score.
+    def classify(tokens, languages)
+      return [] if tokens.nil?
+      tokens = Tokenizer.tokenize(tokens) if tokens.is_a?(String)
+
+      scores = {}
+      if verbosity >= 2
+        dump_all_tokens(tokens, languages)
+      end
+      languages.each do |language|
+        scores[language] = tokens_probability(tokens, language) +
+                                   language_probability(language)
+        if verbosity >= 1
+          printf "%10s = %10.3f + %7.3f = %10.3f\n",
+            language, tokens_probability(tokens, language), language_probability(language), scores[language]
+        end
+      end
+
+      scores.sort { |a, b| b[1] <=> a[1] }.map { |score| [score[0], score[1]] }
+    end
+
+    # Internal: Probably of set of tokens in a language occurring - P(D | C)
     #
     # tokens   - Array of String tokens.
     # language - Language to check.
@@ -122,7 +107,7 @@ module Linguist
       end
     end
 
-    # Internal: Probably of token in language occuring - P(F | C)
+    # Internal: Probably of token in language occurring - P(F | C)
     #
     # token    - String token.
     # language - Language to check.
@@ -136,7 +121,7 @@ module Linguist
       end
     end
 
-    # Internal: Probably of a language occuring - P(C)
+    # Internal: Probably of a language occurring - P(C)
     #
     # language - Language to check.
     #
@@ -145,40 +130,42 @@ module Linguist
       Math.log(@languages[language].to_f / @languages_total.to_f)
     end
 
-    # Public: Serialize classifier to YAML.
-    #
-    # opts - Hash of YAML options.
-    #
-    # Returns nothing.
-    def to_yaml(io)
-      data = "--- !ruby/object:Linguist::Classifier\n"
-
-      data << "languages_total: #{@languages_total}\n"
-      data << "tokens_total: #{@tokens_total}\n"
-
-      data << "languages:\n"
-      @languages.sort.each do |language, count|
-        data << "  #{{language => count}.to_yaml.lines.to_a[1]}"
+    private
+      def verbosity
+        @verbosity ||= (ENV['LINGUIST_DEBUG'] || 0).to_i
       end
 
-      data << "language_tokens:\n"
-      @language_tokens.sort.each do |language, count|
-        data << "  #{{language => count}.to_yaml.lines.to_a[1]}"
+      # Internal: show a table of probabilities for each <token,language> pair.
+      #
+      # The number in each table entry is the number of "points" that each
+      # token contributes toward the belief that the file under test is a
+      # particular language.  Points are additive.
+      #
+      # Points are the number of times a token appears in the file, times
+      # how much more likely (log of probability ratio) that token is to
+      # appear in one language vs. the least-likely language.  Dashes
+      # indicate the least-likely language (and zero points) for each token.
+      def dump_all_tokens(tokens, languages)
+        maxlen = tokens.map { |tok| tok.size }.max
+        
+        printf "%#{maxlen}s", ""
+        puts "    #" + languages.map { |lang| sprintf("%10s", lang) }.join
+        
+        tokmap = Hash.new(0)
+        tokens.each { |tok| tokmap[tok] += 1 }
+        
+        tokmap.sort.each { |tok, count|
+          arr = languages.map { |lang| [lang, token_probability(tok, lang)] }
+          min = arr.map { |a,b| b }.min
+          minlog = Math.log(min)
+          if !arr.inject(true) { |result, n| result && n[1] == arr[0][1] }
+            printf "%#{maxlen}s%5d", tok, count
+            
+            puts arr.map { |ent|
+              ent[1] == min ? "         -" : sprintf("%10.3f", count * (Math.log(ent[1]) - minlog))
+            }.join
+          end
+        }
       end
-
-      data << "tokens:\n"
-      @tokens.sort.each do |language, tokens|
-        data << "  #{{language => true}.to_yaml.lines.to_a[1].sub(/ true/, "")}"
-        tokens.sort.each do |token, count|
-          data << "    #{{token => count}.to_yaml.lines.to_a[1]}"
-        end
-      end
-
-      io.write data
-      nil
-    end
   end
-
-  # Eager load instance
-  Classifier.instance if Classifier.exist?
 end

lib/linguist/generated.rb

@@ -0,0 +1,185 @@
+module Linguist
+  class Generated
+    # Public: Is the blob a generated file?
+    #
+    # name - String filename
+    # data - String blob data. A block also maybe passed in for lazy
+    #        loading. This behavior is deprecated and you should always
+    #        pass in a String.
+    #
+    # Return true or false
+    def self.generated?(name, data)
+      new(name, data).generated?
+    end
+
+    # Internal: Initialize Generated instance
+    #
+    # name - String filename
+    # data - String blob data
+    def initialize(name, data)
+      @name = name
+      @extname = File.extname(name)
+      @_data = data
+    end
+
+    attr_reader :name, :extname
+
+    # Lazy load blob data if block was passed in.
+    #
+    # Awful, awful stuff happening here.
+    #
+    # Returns String data.
+    def data
+      @data ||= @_data.respond_to?(:call) ? @_data.call() : @_data
+    end
+
+    # Public: Get each line of data
+    #
+    # Returns an Array of lines
+    def lines
+      # TODO: data should be required to be a String, no nils
+      @lines ||= data ? data.split("\n", -1) : []
+    end
+
+    # Internal: Is the blob a generated file?
+    #
+    # Generated source code is suppressed in diffs and is ignored by
+    # language statistics.
+    #
+    # Please add additional test coverage to
+    # `test/test_blob.rb#test_generated` if you make any changes.
+    #
+    # Return true or false
+    def generated?
+      name == 'Gemfile.lock' ||
+        minified_files? ||
+        compiled_coffeescript? ||
+        xcode_project_file? ||
+        generated_parser? ||
+        generated_net_docfile? ||
+        generated_net_designer_file? ||
+        generated_protocol_buffer?
+    end
+
+    # Internal: Is the blob an XCode project file?
+    #
+    # Generated if the file extension is an XCode project
+    # file extension.
+    #
+    # Returns true of false.
+    def xcode_project_file?
+      ['.xib', '.nib', '.storyboard', '.pbxproj', '.xcworkspacedata', '.xcuserstate'].include?(extname)
+    end
+
+    # Internal: Is the blob minified files?
+    #
+    # Consider a file minified if it contains more than 5% spaces.
+    # Currently, only JS and CSS files are detected by this method.
+    #
+    # Returns true or false.
+    def minified_files?
+      return unless ['.js', '.css'].include? extname
+      if data && data.length > 200
+        (data.each_char.count{ |c| c <= ' ' } / data.length.to_f) < 0.05
+      else
+        false
+      end
+    end
+
+    # Internal: Is the blob of JS generated by CoffeeScript?
+    #
+    # CoffeeScript is meant to output JS that would be difficult to
+    # tell if it was generated or not. Look for a number of patterns
+    # output by the CS compiler.
+    #
+    # Return true or false
+    def compiled_coffeescript?
+      return false unless extname == '.js'
+
+      # CoffeeScript generated by > 1.2 include a comment on the first line
+      if lines[0] =~ /^\/\/ Generated by /
+        return true
+      end
+
+      if lines[0] == '(function() {' &&     # First line is module closure opening
+          lines[-2] == '}).call(this);' &&  # Second to last line closes module closure
+          lines[-1] == ''                   # Last line is blank
+
+        score = 0
+
+        lines.each do |line|
+          if line =~ /var /
+            # Underscored temp vars are likely to be Coffee
+            score += 1 * line.gsub(/(_fn|_i|_len|_ref|_results)/).count
+
+            # bind and extend functions are very Coffee specific
+            score += 3 * line.gsub(/(__bind|__extends|__hasProp|__indexOf|__slice)/).count
+          end
+        end
+
+        # Require a score of 3. This is fairly arbitrary. Consider
+        # tweaking later.
+        score >= 3
+      else
+        false
+      end
+    end
+
+    # Internal: Is this a generated documentation file for a .NET assembly?
+    #
+    # .NET developers often check in the XML Intellisense file along with an
+    # assembly - however, these don't have a special extension, so we have to
+    # dig into the contents to determine if it's a docfile. Luckily, these files
+    # are extremely structured, so recognizing them is easy.
+    #
+    # Returns true or false
+    def generated_net_docfile?
+      return false unless extname.downcase == ".xml"
+      return false unless lines.count > 3
+
+      # .NET Docfiles always open with <doc> and their first tag is an
+      # <assembly> tag
+      return lines[1].include?("<doc>") &&
+        lines[2].include?("<assembly>") &&
+        lines[-2].include?("</doc>")
+    end
+
+    # Internal: Is this a codegen file for a .NET project?
+    #
+    # Visual Studio often uses code generation to generate partial classes, and
+    # these files can be quite unwieldy. Let's hide them.
+    #
+    # Returns true or false
+    def generated_net_designer_file?
+      name.downcase =~ /\.designer\.cs$/
+    end
+
+    # Internal: Is the blob of JS a parser generated by PEG.js?
+    #
+    # PEG.js-generated parsers are not meant to be consumed by humans.
+    #
+    # Return true or false
+    def generated_parser?
+      return false unless extname == '.js'
+
+      # PEG.js-generated parsers include a comment near the top  of the file
+      # that marks them as such.
+      if lines[0..4].join('') =~ /^(?:[^\/]|\/[^\*])*\/\*(?:[^\*]|\*[^\/])*Generated by PEG.js/
+        return true
+      end
+
+      false
+    end
+
+    # Internal: Is the blob a C++, Java or Python source file generated by the
+    # Protocol Buffer compiler?
+    #
+    # Returns true of false.
+    def generated_protocol_buffer?
+      return false unless ['.py', '.java', '.h', '.cc', '.cpp'].include?(extname)
+      return false unless lines.count > 1
+
+      return lines[0].include?("Generated by the protocol buffer compiler.  DO NOT EDIT!")
+    end
+  end
+end

lib/linguist/language.rb

@@ -2,6 +2,9 @@ require 'escape_utils'
 require 'pygments'
 require 'yaml'
 
+require 'linguist/classifier'
+require 'linguist/samples'
+
 module Linguist
   # Language names that are recognizable by GitHub. Defined languages
   # can be highlighted, searched and listed under the Top Languages page.
@@ -9,28 +12,22 @@ module Linguist
   # Languages are defined in `lib/linguist/languages.yml`.
   class Language
     @languages       = []
-    @overrides       = {}
     @index           = {}
     @name_index      = {}
     @alias_index     = {}
-    @extension_index = {}
-    @filename_index  = {}
+
+    @extension_index          = Hash.new { |h,k| h[k] = [] }
+    @filename_index           = Hash.new { |h,k| h[k] = [] }
+    @primary_extension_index  = {}
 
     # Valid Languages types
     TYPES = [:data, :markup, :programming]
 
-    # Internal: Test if extension maps to multiple Languages.
+    # Names of non-programming languages that we will still detect
     #
-    # Returns true or false.
-    def self.ambiguous?(extension)
-      @overrides.include?(extension)
-    end
-
-    # Internal: Return overridden extensions.
-    #
-    # Returns extensions Array.
-    def self.overridden_extensions
-      @overrides.keys
+    # Returns an array
+    def self.detectable_markup
+      ["AsciiDoc", "CSS", "Creole", "Less", "Markdown", "MediaWiki", "Org", "RDoc", "Sass", "Textile", "reStructuredText"]
     end
 
     # Internal: Create a new Language object
@@ -65,34 +62,53 @@ module Linguist
           raise ArgumentError, "Extension is missing a '.': #{extension.inspect}"
         end
 
-        unless ambiguous?(extension)
-          # Index the extension with a leading ".": ".rb"
-          @extension_index[extension] = language
-
-          # Index the extension without a leading ".": "rb"
-          @extension_index[extension.sub(/^\./, '')] = language
-        end
+        @extension_index[extension] << language
       end
 
-      language.overrides.each do |extension|
-        if extension !~ /^\./
-          raise ArgumentError, "Extension is missing a '.': #{extension.inspect}"
-        end
-
-        if l = @overrides[extension]
-          raise ArgumentError, "#{extension} is already overridden by #{l.name}"
-        end
-
-        @overrides[extension] = language
+      if @primary_extension_index.key?(language.primary_extension)
+        raise ArgumentError, "Duplicate primary extension: #{language.primary_extension}"
       end
 
+      @primary_extension_index[language.primary_extension] = language
+
       language.filenames.each do |filename|
-        @filename_index[filename] = language
+        @filename_index[filename] << language
       end
 
       language
     end
 
+    # Public: Detects the Language of the blob.
+    #
+    # name - String filename
+    # data - String blob data. A block also maybe passed in for lazy
+    #        loading. This behavior is deprecated and you should always
+    #        pass in a String.
+    # mode - Optional String mode (defaults to nil)
+    #
+    # Returns Language or nil.
+    def self.detect(name, data, mode = nil)
+      # A bit of an elegant hack. If the file is executable but extensionless,
+      # append a "magic" extension so it can be classified with other
+      # languages that have shebang scripts.
+      if File.extname(name).empty? && mode && (mode.to_i(8) & 05) == 05
+        name += ".script!"
+      end
+
+      possible_languages = find_by_filename(name)
+
+      if possible_languages.length > 1
+        data = data.call() if data.respond_to?(:call)
+        if data.nil? || data == ""
+          nil
+        elsif result = Classifier.classify(Samples::DATA, data, possible_languages.map(&:name)).first
+          Language[result[0]]
+        end
+      else
+        possible_languages.first
+      end
+    end
+
     # Public: Get all Languages
     #
     # Returns an Array of Languages
@@ -128,33 +144,22 @@ module Linguist
       @alias_index[name]
     end
 
-    # Public: Look up Language by extension.
-    #
-    # extension - The extension String. May include leading "."
-    #
-    # Examples
-    #
-    #   Language.find_by_extension('.rb')
-    #   # => #<Language name="Ruby">
-    #
-    # Returns the Language or nil if none was found.
-    def self.find_by_extension(extension)
-      @extension_index[extension]
-    end
-
-    # Public: Look up Language by filename.
+    # Public: Look up Languages by filename.
     #
     # filename - The path String.
     #
     # Examples
     #
     #   Language.find_by_filename('foo.rb')
-    #   # => #<Language name="Ruby">
+    #   # => [#<Language name="Ruby">]
     #
-    # Returns the Language or nil if none was found.
+    # Returns all matching Languages or [] if none were found.
     def self.find_by_filename(filename)
       basename, extname = File.basename(filename), File.extname(filename)
-      @filename_index[basename] || @extension_index[extname]
+      langs = [@primary_extension_index[extname]] +
+              @filename_index[basename] +
+              @extension_index[extname]
+      langs.compact.uniq
     end
 
     # Public: Look up Language by its name or lexer.
@@ -235,16 +240,18 @@ module Linguist
         raise(ArgumentError, "#{@name} is missing lexer")
 
       @ace_mode = attributes[:ace_mode]
+      @wrap = attributes[:wrap] || false
 
       # Set legacy search term
       @search_term = attributes[:search_term] || default_alias_name
 
       # Set extensions or default to [].
       @extensions = attributes[:extensions] || []
-      @overrides  = attributes[:overrides]  || []
       @filenames  = attributes[:filenames]  || []
 
-      @primary_extension = attributes[:primary_extension] || default_primary_extension || extensions.first
+      unless @primary_extension = attributes[:primary_extension]
+        raise ArgumentError, "#{@name} is missing primary extension"
+      end
 
       # Prepend primary extension unless its already included
       if primary_extension && !extensions.include?(primary_extension)
@@ -324,6 +331,11 @@ module Linguist
     # Returns a String name or nil
     attr_reader :ace_mode
 
+    # Public: Should language lines be wrapped
+    #
+    # Returns true or false
+    attr_reader :wrap
+
     # Public: Get extensions
     #
     # Examples
@@ -335,7 +347,7 @@ module Linguist
 
     # Deprecated: Get primary extension
     #
-    # Defaults to the first extension but can be overriden
+    # Defaults to the first extension but can be overridden
     # in the languages.yml.
     #
     # The primary extension can not be nil. Tests should verify this.
@@ -347,11 +359,6 @@ module Linguist
     # Returns the extension String.
     attr_reader :primary_extension
 
-    # Internal: Get overridden extensions.
-    #
-    # Returns the extensions Array.
-    attr_reader :overrides
-
     # Public: Get filenames
     #
     # Examples
@@ -381,13 +388,6 @@ module Linguist
       name.downcase.gsub(/\s/, '-')
     end
 
-    # Internal: Get default primary extension.
-    #
-    # Returns the extension String.
-    def default_primary_extension
-      extensions.first
-    end
-
     # Public: Get Language group
     #
     # Returns a Language
@@ -451,9 +451,30 @@ module Linguist
     end
   end
 
+  extensions = Samples::DATA['extnames']
+  filenames = Samples::DATA['filenames']
   popular = YAML.load_file(File.expand_path("../popular.yml", __FILE__))
 
   YAML.load_file(File.expand_path("../languages.yml", __FILE__)).each do |name, options|
+    options['extensions'] ||= []
+    options['filenames'] ||= []
+
+    if extnames = extensions[name]
+      extnames.each do |extname|
+        if !options['extensions'].include?(extname)
+          options['extensions'] << extname
+        end
+      end
+    end
+
+    if fns = filenames[name]
+      fns.each do |filename|
+        if !options['filenames'].include?(filename)
+          options['filenames'] << filename
+        end
+      end
+    end
+
     Language.create(
       :name              => name,
       :color             => options['color'],
@@ -461,12 +482,12 @@ module Linguist
       :aliases           => options['aliases'],
       :lexer             => options['lexer'],
       :ace_mode          => options['ace_mode'],
+      :wrap              => options['wrap'],
       :group_name        => options['group'],
       :searchable        => options.key?('searchable') ? options['searchable'] : true,
       :search_term       => options['search_term'],
-      :extensions        => options['extensions'],
+      :extensions        => options['extensions'].sort,
       :primary_extension => options['primary_extension'],
-      :overrides         => options['overrides'],
       :filenames         => options['filenames'],
       :popular           => popular.include?(name)
     )

lib/linguist/md5.rb

@@ -0,0 +1,38 @@
+require 'digest/md5'
+
+module Linguist
+  module MD5
+    # Public: Create deep nested digest of value object.
+    #
+    # Useful for object comparison.
+    #
+    # obj - Object to digest.
+    #
+    # Returns String hex digest
+    def self.hexdigest(obj)
+      digest = Digest::MD5.new
+
+      case obj
+      when String, Symbol, Integer
+        digest.update "#{obj.class}"
+        digest.update "#{obj}"
+      when TrueClass, FalseClass, NilClass
+        digest.update "#{obj.class}"
+      when Array
+        digest.update "#{obj.class}"
+        for e in obj
+          digest.update(hexdigest(e))
+        end
+      when Hash
+        digest.update "#{obj.class}"
+        for e in obj.map { |(k, v)| hexdigest([k, v]) }.sort
+          digest.update(e)
+        end
+      else
+        raise TypeError, "can't convert #{obj.inspect} into String"
+      end
+
+      digest.hexdigest
+    end
+  end
+end

lib/linguist/mime.rb

@@ -1,91 +0,0 @@
-require 'mime/types'
-require 'yaml'
-
-class MIME::Type
-  attr_accessor :override
-end
-
-# Register additional mime type extensions
-#
-# Follows same format as mime-types data file
-#   https://github.com/halostatue/mime-types/blob/master/lib/mime/types.rb.data
-File.read(File.expand_path("../mimes.yml", __FILE__)).lines.each do |line|
-  # Regexp was cargo culted from mime-types lib
-  next unless line =~ %r{^
-    #{MIME::Type::MEDIA_TYPE_RE}
-    (?:\s@([^\s]+))?
-    (?:\s:(#{MIME::Type::ENCODING_RE}))?
-  }x
-
-  mediatype  = $1
-  subtype    = $2
-  extensions = $3
-  encoding   = $4
-
-  # Lookup existing mime type
-  mime_type = MIME::Types["#{mediatype}/#{subtype}"].first ||
-    # Or create a new instance
-    MIME::Type.new("#{mediatype}/#{subtype}")
-
-  if extensions
-    extensions.split(/,/).each do |extension|
-      mime_type.extensions << extension
-    end
-  end
-
-  if encoding
-    mime_type.encoding = encoding
-  end
-
-  mime_type.override = true
-
-  # Kind of hacky, but we need to reindex the mime type after making changes
-  MIME::Types.add_type_variant(mime_type)
-  MIME::Types.index_extensions(mime_type)
-end
-
-module Linguist
-  module Mime
-    # Internal: Look up mime type for extension.
-    #
-    # ext - The extension String. May include leading "."
-    #
-    # Examples
-    #
-    #   Mime.mime_for('.html')
-    #   # => 'text/html'
-    #
-    #   Mime.mime_for('txt')
-    #   # => 'text/plain'
-    #
-    # Return mime type String otherwise falls back to 'text/plain'.
-    def self.mime_for(ext)
-      mime_type = lookup_mime_type_for(ext)
-      mime_type ? mime_type.to_s : 'text/plain'
-    end
-
-    # Internal: Lookup mime type for extension or mime type
-    #
-    # ext_or_mime_type - A file extension ".txt" or mime type "text/plain".
-    #
-    # Returns a MIME::Type
-    def self.lookup_mime_type_for(ext_or_mime_type)
-      ext_or_mime_type ||= ''
-
-      if ext_or_mime_type =~ /\w+\/\w+/
-        guesses = ::MIME::Types[ext_or_mime_type]
-      else
-        guesses = ::MIME::Types.type_for(ext_or_mime_type)
-      end
-
-      # Use custom override first
-      guesses.detect { |type| type.override } ||
-
-        # Prefer text mime types over binary
-        guesses.detect { |type| type.ascii? } ||
-
-        # Otherwise use the first guess
-        guesses.first
-    end
-  end
-end

lib/linguist/mimes.yml

@@ -1,62 +0,0 @@
-# Additional types to add to MIME::Types
-#
-# MIME types are used to set the Content-Type of raw binary blobs. All text
-# blobs are served as text/plain regardless of their type to ensure they
-# open in the browser rather than downloading.
-#
-# The encoding helps determine whether a file should be treated as plain
-# text or binary. By default, a mime type's encoding is base64 (binary).
-# These types will show a "View Raw" link. To force a type to render as
-# plain text, set it to 8bit for UTF-8. text/* types will be treated as
-# text by default.
-#
-#   <type> @<extensions> :<encoding>
-#
-# type       - mediatype/subtype
-# extensions - comma seperated extension list
-# encoding   - base64 (binary), 7bit (ASCII), 8bit (UTF-8), or
-#              quoted-printable (Printable ASCII).
-#
-# Follows same format as mime-types data file
-#   https://github.com/halostatue/mime-types/blob/master/lib/mime/types.rb.data
-#
-# Any additions or modifications (even trivial) should have corresponding
-# test change in `test/test_mime.rb`.
-
-# TODO: Lookup actual types
-application/octet-stream @a,blend,gem,graffle,ipa,lib,mcz,nib,o,ogv,otf,pfx,pigx,plgx,psd,sib,spl,sqlite3,swc,ucode,xpi
-
-# Please keep this list alphabetized
-application/java-archive @ear,war
-application/netcdf :8bit
-application/ogg @ogg
-application/postscript :base64
-application/vnd.adobe.air-application-installer-package+zip @air
-application/vnd.mozilla.xul+xml :8bit
-application/vnd.oasis.opendocument.presentation @odp
-application/vnd.oasis.opendocument.spreadsheet @ods
-application/vnd.oasis.opendocument.text @odt
-application/vnd.openofficeorg.extension @oxt
-application/vnd.openxmlformats-officedocument.presentationml.presentation @pptx
-application/x-chrome-extension @crx
-application/x-iwork-keynote-sffkey @key
-application/x-iwork-numbers-sffnumbers @numbers
-application/x-iwork-pages-sffpages @pages
-application/x-ms-xbap @xbap :8bit
-application/x-parrot-bytecode @pbc
-application/x-shockwave-flash @swf
-application/x-silverlight-app @xap
-application/x-supercollider @sc :8bit
-application/x-troff-ms :8bit
-application/x-wais-source :8bit
-application/xaml+xml @xaml :8bit
-application/xslt+xml @xslt :8bit
-image/x-icns @icns
-text/cache-manifest @manifest
-text/plain @cu,cxx
-text/x-logtalk @lgt
-text/x-nemerle @n
-text/x-nimrod @nim
-text/x-ocaml @ml,mli,mll,mly,sig,sml
-text/x-rust @rs,rc
-text/x-scheme @rkt,scm,sls,sps,ss

lib/linguist/pathname.rb

@@ -1,92 +0,0 @@
-require 'linguist/language'
-require 'linguist/mime'
-require 'pygments'
-
-module Linguist
-  # Similar to ::Pathname, Linguist::Pathname wraps a path string and
-  # provides helpful query methods. Its useful when you only have a
-  # filename but not a blob and need to figure out the language of the file.
-  class Pathname
-    # Public: Initialize a Pathname
-    #
-    # path - A filename String. The file may or maybe actually exist.
-    #
-    # Returns a Pathname.
-    def initialize(path)
-      @path = path
-    end
-
-    # Public: Get the basename of the path
-    #
-    # Examples
-    #
-    #   Pathname.new('sub/dir/file.rb').basename
-    #   # => 'file.rb'
-    #
-    # Returns a String.
-    def basename
-      File.basename(@path)
-    end
-
-    # Public: Get the extname of the path
-    #
-    # Examples
-    #
-    #   Pathname.new('.rb').extname
-    #   # => '.rb'
-    #
-    #   Pathname.new('file.rb').extname
-    #   # => '.rb'
-    #
-    # Returns a String.
-    def extname
-      File.extname(@path)
-    end
-
-    # Public: Get the language of the path
-    #
-    # The path extension name is the only heuristic used to detect the
-    # language name.
-    #
-    # Examples
-    #
-    #   Pathname.new('file.rb').language
-    #   # => Language['Ruby']
-    #
-    # Returns a Language or nil if none was found.
-    def language
-      @language ||= Language.find_by_filename(@path)
-    end
-
-    # Internal: Get the lexer of the path
-    #
-    # Returns a Lexer.
-    def lexer
-      language ? language.lexer : Pygments::Lexer.find_by_name('Text only')
-    end
-
-    # Public: Get the mime type
-    #
-    # Examples
-    #
-    #   Pathname.new('index.html').mime_type
-    #   # => 'text/html'
-    #
-    # Returns a mime type String.
-    def mime_type
-      @mime_type ||= Mime.mime_for(extname)
-    end
-
-    # Public: Return self as String
-    #
-    # Returns a String
-    def to_s
-      @path.dup
-    end
-
-    def eql?(other)
-      other.is_a?(self.class) && @path == other.to_s
-    end
-    alias_method :==, :eql?
-  end
-end

lib/linguist/popular.yml

@@ -8,6 +8,8 @@
 - C#
 - C++
 - CSS
+- Clojure
+- CoffeeScript
 - Common Lisp
 - Diff
 - Emacs Lisp
@@ -25,5 +27,3 @@
 - SQL
 - Scala
 - Scheme
-- TeX
-- XML

lib/linguist/repository.rb

@@ -67,20 +67,20 @@ module Linguist
       return if @computed_stats
 
       @enum.each do |blob|
-        # Skip binary file extensions
-        next if blob.binary_mime_type?
+        # Skip files that are likely binary
+        next if blob.likely_binary?
 
         # Skip vendored or generated blobs
         next if blob.vendored? || blob.generated? || blob.language.nil?
 
-        # Only include programming languages
-        if blob.language.type == :programming
+        # Only include programming languages and acceptable markup languages
+        if blob.language.type == :programming || Language.detectable_markup.include?(blob.language.name)
           @sizes[blob.language.group] += blob.size
         end
       end
 
       # Compute total size
-      @size = @sizes.inject(0) { |s,(k,v)| s + v }
+      @size = @sizes.inject(0) { |s,(_,v)| s + v }
 
       # Get primary language
       if primary = @sizes.max_by { |(_, size)| size }

lib/linguist/sample.rb

@@ -1,74 +0,0 @@
-require 'linguist/classifier'
-require 'linguist/language'
-
-module Linguist
-  # Model for accessing classifier training data.
-  class Sample
-    # Samples live in test/ for now, we'll eventually move them out
-    PATH = File.expand_path("../../../test/fixtures", __FILE__)
-
-    # Public: Iterate over each Sample.
-    #
-    # &block - Yields Sample to block
-    #
-    # Returns nothing.
-    def self.each(&block)
-      Dir.entries(PATH).each do |category|
-        next if category == '.' || category == '..'
-
-        # Skip text and binary for now
-        # Possibly reconsider this later
-        next if category == 'text' || category == 'binary'
-
-        # Map directory name to a Language alias
-        language = Linguist::Language.find_by_alias(category)
-        raise "No language for #{category.inspect}" unless language
-
-        dirname = File.join(PATH, category)
-        Dir.entries(dirname).each do |filename|
-          next if filename == '.' || filename == '..'
-          yield new(File.join(dirname, filename), language)
-        end
-      end
-
-      nil
-    end
-
-    # Public: Build Classifier from all samples.
-    #
-    # Returns trained Classifier.
-    def self.classifier
-      classifier = Classifier.new
-      each { |sample| classifier.train(sample.language, sample.data) }
-      classifier.gc
-    end
-
-    # Internal: Initialize Sample.
-    #
-    # Samples should be initialized by Sample.each.
-    #
-    # path     - String full path to file.
-    # language - Language of sample.
-    def initialize(path, language)
-      @path     = path
-      @language = language
-    end
-
-    # Public: Get full path to file.
-    #
-    # Returns String.
-    attr_reader :path
-
-    # Public: Get sample language.
-    #
-    # Returns Language.
-    attr_reader :language
-
-    # Public: Read file contents.
-    #
-    # Returns String.
-    def data
-      File.read(path)
-    end
-  end
-end

lib/linguist/samples.rb

@@ -0,0 +1,98 @@
+require 'yaml'
+
+require 'linguist/md5'
+require 'linguist/classifier'
+
+module Linguist
+  # Model for accessing classifier training data.
+  module Samples
+    # Path to samples root directory
+    ROOT = File.expand_path("../../../samples", __FILE__)
+
+    # Path for serialized samples db
+    PATH = File.expand_path('../samples.json', __FILE__)
+
+    # Hash of serialized samples object
+    if File.exist?(PATH)
+      DATA = YAML.load_file(PATH)
+    end
+
+    # Public: Iterate over each sample.
+    #
+    # &block - Yields Sample to block
+    #
+    # Returns nothing.
+    def self.each(&block)
+      Dir.entries(ROOT).each do |category|
+        next if category == '.' || category == '..'
+
+        # Skip text and binary for now
+        # Possibly reconsider this later
+        next if category == 'Text' || category == 'Binary'
+
+        dirname = File.join(ROOT, category)
+        Dir.entries(dirname).each do |filename|
+          next if filename == '.' || filename == '..'
+
+          if filename == 'filenames'
+            Dir.entries(File.join(dirname, filename)).each do |subfilename|
+              next if subfilename == '.' || subfilename == '..'
+
+              yield({
+                :path    => File.join(dirname, filename, subfilename),
+                :language => category,
+                :filename => subfilename
+              })
+            end
+          else
+            if File.extname(filename) == ""
+              raise "#{File.join(dirname, filename)} is missing an extension, maybe it belongs in filenames/ subdir"
+            end
+
+            yield({
+              :path     => File.join(dirname, filename),
+              :language => category,
+              :extname  => File.extname(filename)
+            })
+          end
+        end
+      end
+
+      nil
+    end
+
+    # Public: Build Classifier from all samples.
+    #
+    # Returns trained Classifier.
+    def self.data
+      db = {}
+      db['extnames'] = {}
+      db['filenames'] = {}
+
+      each do |sample|
+        language_name = sample[:language]
+
+        if sample[:extname]
+          db['extnames'][language_name] ||= []
+          if !db['extnames'][language_name].include?(sample[:extname])
+            db['extnames'][language_name] << sample[:extname]
+            db['extnames'][language_name].sort!
+          end
+        end
+
+        if sample[:filename]
+          db['filenames'][language_name] ||= []
+          db['filenames'][language_name] << sample[:filename]
+          db['filenames'][language_name].sort!
+        end
+
+        data = File.read(sample[:path])
+        Classifier.train!(db, language_name, data)
+      end
+
+      db['md5'] = Linguist::MD5.hexdigest(db)
+
+      db
+    end
+  end
+end

lib/linguist/tokenizer.rb

@@ -1,3 +1,5 @@
+require 'strscan'
+
 module Linguist
   # Generic programming language tokenizer.
   #
@@ -5,25 +7,43 @@ module Linguist
   # It strips any data strings or comments and preserves significant
   # language symbols.
   class Tokenizer
-    # Public: Initialize a Tokenizer.
+    # Public: Extract tokens from data
     #
-    # data - String data to scan.
-    def initialize(data)
-      @data = data
-    end
-
-    # Public: Get source data.
-    #
-    # Returns String.
-    attr_reader :data
-
-    # Public: Extract tokens from data.
+    # data - String to tokenize
     #
     # Returns Array of token Strings.
-    def tokens
-      extract_tokens(data)
+    def self.tokenize(data)
+      new.extract_tokens(data)
     end
 
+    # Read up to 100KB
+    BYTE_LIMIT = 100_000
+
+    # Start state on token, ignore anything till the next newline
+    SINGLE_LINE_COMMENTS = [
+      '//', # C
+      '#',  # Ruby
+      '%',  # Tex
+    ]
+
+    # Start state on opening token, ignore anything until the closing
+    # token is reached.
+    MULTI_LINE_COMMENTS = [
+      ['/*', '*/'],    # C
+      ['<!--', '-->'], # XML
+      ['{-', '-}'],    # Haskell
+      ['(*', '*)'],    # Coq
+      ['"""', '"""']   # Python
+    ]
+
+    START_SINGLE_LINE_COMMENT =  Regexp.compile(SINGLE_LINE_COMMENTS.map { |c|
+      "\s*#{Regexp.escape(c)} "
+    }.join("|"))
+
+    START_MULTI_LINE_COMMENT =  Regexp.compile(MULTI_LINE_COMMENTS.map { |c|
+      Regexp.escape(c[0])
+    }.join("|"))
+
     # Internal: Extract generic tokens from data.
     #
     # data - String to scan.
@@ -39,54 +59,48 @@ module Linguist
 
       tokens = []
       until s.eos?
-        # Ruby single line comment
-        if token = s.scan(/# /)
-          tokens << "#"
+        break if s.pos >= BYTE_LIMIT
+
+        if token = s.scan(/^#!.+$/)
+          if name = extract_shebang(token)
+            tokens << "SHEBANG#!#{name}"
+          end
+
+        # Single line comment
+        elsif s.beginning_of_line? && token = s.scan(START_SINGLE_LINE_COMMENT)
+          # tokens << token.strip
           s.skip_until(/\n|\Z/)
 
-        # C style single line comment
-        elsif token = s.scan(/\/\/ /)
-          tokens << "//"
-          s.skip_until(/\n|\Z/)
-
-        # Leading Tex or Matlab comments
-        elsif token = s.scan(/\n%/)
-          tokens << "%"
-          s.skip_until(/\n|\Z/)
-
-        # C multiline comments
-        elsif token = s.scan(/\/\*/)
-          tokens << "/*"
-          s.skip_until(/\*\//)
-          tokens << "*/"
-
-        # Haskell multiline comments
-        elsif token = s.scan(/\{-/)
-          tokens << "{-"
-          s.skip_until(/-\}/)
-          tokens << "-}"
-
-        # XML multiline comments
-        elsif token = s.scan(/<!--/)
-          tokens << "<!--"
-          s.skip_until(/-->/)
-          tokens << "-->"
+        # Multiline comments
+        elsif token = s.scan(START_MULTI_LINE_COMMENT)
+          # tokens << token
+          close_token = MULTI_LINE_COMMENTS.assoc(token)[1]
+          s.skip_until(Regexp.compile(Regexp.escape(close_token)))
+          # tokens << close_token
 
         # Skip single or double quoted strings
         elsif s.scan(/"/)
-          s.skip_until(/[^\\]"/)
+          if s.peek(1) == "\""
+            s.getch
+          else
+            s.skip_until(/[^\\]"/)
+          end
         elsif s.scan(/'/)
-          s.skip_until(/[^\\]'/)
+          if s.peek(1) == "'"
+            s.getch
+          else
+            s.skip_until(/[^\\]'/)
+          end
 
         # Skip number literals
-        elsif s.scan(/(0x)?\d+/)
+        elsif s.scan(/(0x)?\d(\d|\.)*/)
 
         # SGML style brackets
         elsif token = s.scan(/<[^\s<>][^<>]*>/)
           extract_sgml_tokens(token).each { |t| tokens << t }
 
         # Common programming punctuation
-        elsif token = s.scan(/;|\{|\}|\(|\)/)
+        elsif token = s.scan(/;|\{|\}|\(|\)|\[|\]/)
           tokens << token
 
         # Regular token
@@ -105,6 +119,33 @@ module Linguist
       tokens
     end
 
+    # Internal: Extract normalized shebang command token.
+    #
+    # Examples
+    #
+    #   extract_shebang("#!/usr/bin/ruby")
+    #   # => "ruby"
+    #
+    #   extract_shebang("#!/usr/bin/env node")
+    #   # => "node"
+    #
+    # Returns String token or nil it couldn't be parsed.
+    def extract_shebang(data)
+      s = StringScanner.new(data)
+
+      if path = s.scan(/^#!\s*\S+/)
+        script = path.split('/').last
+        if script == 'env'
+          s.scan(/\s+/)
+          script = s.scan(/\S+/)
+        end
+        script = script[/[^\d]+/, 0] if script
+        return script
+      end
+
+      nil
+    end
+
     # Internal: Extract tokens from inside SGML tag.
     #
     # data - SGML tag String.

lib/linguist/vendor.yml

@@ -16,19 +16,32 @@
 #  https://github.com/joyent/node
 - ^deps/
 - ^tools/
+- (^|/)configure$
+- (^|/)configure.ac$
+- (^|/)config.guess$
+- (^|/)config.sub$
 
-# Node depedencies
+# Node dependencies
 - node_modules/
 
-# Vendored depedencies
+# Erlang bundles
+- ^rebar$
+
+# Vendored dependencies
 - vendor/
 
+# Debian packaging
+- ^debian/
 
 ## Commonly Bundled JavaScript frameworks ##
 
 # jQuery
 - (^|/)jquery([^.]*)(\.min)?\.js$
-- (^|/)jquery\-\d\.\d(\.\d)?(\.min)?\.js$
+- (^|/)jquery\-\d\.\d+(\.\d+)?(\.min)?\.js$
+
+# jQuery UI
+- (^|/)jquery\-ui(\-\d\.\d+(\.\d+)?)?(\.\w+)?(\.min)?\.(js|css)$
+- (^|/)jquery\.(ui|effects)\.([^.]*)(\.min)?\.(js|css)$
 
 # Prototype
 - (^|/)prototype(.*)\.js$
@@ -49,10 +62,6 @@
 - (^|/)yahoo-([^.]*)\.js$
 - (^|/)yui([^.]*)\.js$
 
-# LESS css
-- (^|/)less([^.]*)(\.min)?\.js$
-- (^|/)less\-\d+\.\d+\.\d+(\.min)?\.js$
-
 # WYS editors
 - (^|/)ckeditor\.js$
 - (^|/)tiny_mce([^.]*)\.js$
@@ -61,8 +70,16 @@
 # MathJax
 - (^|/)MathJax/
 
+# SyntaxHighlighter - http://alexgorbatchev.com/
+- (^|/)shBrush([^.]*)\.js$
+- (^|/)shCore\.js$
+- (^|/)shLegacy\.js$
+
 ## Python ##
 
+# django
+- (^|/)admin_media/
+
 # Fabric
 - ^fabfile\.py$
 
@@ -81,7 +98,8 @@
 - -vsdoc\.js$
 
 # jQuery validation plugin (MS bundles this with asp.net mvc)
-- (^|/)jquery([^.]*)\.validate(\.min)?\.js$
+- (^|/)jquery([^.]*)\.validate(\.unobtrusive)?(\.min)?\.js$
+- (^|/)jquery([^.]*)\.unobtrusive\-ajax(\.min)?\.js$
 
 # Microsoft Ajax
 - (^|/)[Mm]icrosoft([Mm]vc)?([Aa]jax|[Vv]alidation)(\.debug)?\.js$
@@ -94,3 +112,18 @@
 
 # Samples folders
 - ^[Ss]amples/
+
+# LICENSE, README, git config files
+- ^COPYING$
+- ^LICENSE$
+- gitattributes$
+- gitignore$
+- gitmodules$
+- ^README$
+- ^readme$
+
+# Test fixtures
+- ^[Tt]est/fixtures/
+
+# .DS_Store's
+- .[Dd][Ss]_[Ss]tore$

samples/ABAP/cl_csv_parser.abap

@@ -0,0 +1,219 @@
+*/**
+* The MIT License (MIT)
+* Copyright (c) 2012 René van Mil
+* 
+* Permission is hereby granted, free of charge, to any person obtaining
+* a copy of this software and associated documentation files (the
+* "Software"), to deal in the Software without restriction, including
+* without limitation the rights to use, copy, modify, merge, publish,
+* distribute, sublicense, and/or sell copies of the Software, and to
+* permit persons to whom the Software is furnished to do so, subject to
+* the following conditions:
+* 
+* The above copyright notice and this permission notice shall be
+* included in all copies or substantial portions of the Software.
+* 
+* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+* IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+* CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+* TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+* SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+*----------------------------------------------------------------------*
+*       CLASS CL_CSV_PARSER DEFINITION
+*----------------------------------------------------------------------*
+*
+*----------------------------------------------------------------------*
+class cl_csv_parser definition
+  public
+  inheriting from cl_object
+  final
+  create public .
+
+  public section.
+*"* public components of class CL_CSV_PARSER
+*"* do not include other source files here!!!
+
+    type-pools abap .
+    methods constructor
+      importing
+        !delegate type ref to if_csv_parser_delegate
+        !csvstring type string
+        !separator type c
+        !skip_first_line type abap_bool .
+    methods parse
+      raising
+        cx_csv_parse_error .
+  protected section.
+*"* protected components of class CL_CSV_PARSER
+*"* do not include other source files here!!!
+  private section.
+*"* private components of class CL_CSV_PARSER
+*"* do not include other source files here!!!
+
+    constants _textindicator type c value '"'.              "#EC NOTEXT
+    data _delegate type ref to if_csv_parser_delegate .
+    data _csvstring type string .
+    data _separator type c .
+    type-pools abap .
+    data _skip_first_line type abap_bool .
+
+    methods _lines
+      returning
+        value(returning) type stringtab .
+    methods _parse_line
+      importing
+        !line type string
+      returning
+        value(returning) type stringtab
+      raising
+        cx_csv_parse_error .
+endclass.                    "CL_CSV_PARSER DEFINITION
+
+
+
+*----------------------------------------------------------------------*
+*       CLASS CL_CSV_PARSER IMPLEMENTATION
+*----------------------------------------------------------------------*
+*
+*----------------------------------------------------------------------*
+class cl_csv_parser implementation.
+
+
+* <SIGNATURE>---------------------------------------------------------------------------------------+
+* | Instance Public Method CL_CSV_PARSER->CONSTRUCTOR
+* +-------------------------------------------------------------------------------------------------+
+* | [--->] DELEGATE                       TYPE REF TO IF_CSV_PARSER_DELEGATE
+* | [--->] CSVSTRING                      TYPE        STRING
+* | [--->] SEPARATOR                      TYPE        C
+* | [--->] SKIP_FIRST_LINE                TYPE        ABAP_BOOL
+* +--------------------------------------------------------------------------------------</SIGNATURE>
+  method constructor.
+    super->constructor( ).
+    _delegate = delegate.
+    _csvstring = csvstring.
+    _separator = separator.
+    _skip_first_line = skip_first_line.
+  endmethod.                    "constructor
+
+
+* <SIGNATURE>---------------------------------------------------------------------------------------+
+* | Instance Public Method CL_CSV_PARSER->PARSE
+* +-------------------------------------------------------------------------------------------------+
+* | [!CX!] CX_CSV_PARSE_ERROR
+* +--------------------------------------------------------------------------------------</SIGNATURE>
+  method parse.
+    data msg type string.
+    if _csvstring is initial.
+      message e002(csv) into msg.
+      raise exception type cx_csv_parse_error
+        exporting
+          message = msg.
+    endif.
+
+    " Get the lines
+    data is_first_line type abap_bool value abap_true.
+    data lines type standard table of string.
+    lines = _lines( ).
+    field-symbols <line> type string.
+    loop at lines assigning <line>.
+      " Should we skip the first line?
+      if _skip_first_line = abap_true and is_first_line = abap_true.
+        is_first_line = abap_false.
+        continue.
+      endif.
+      " Parse the line
+      data values type standard table of string.
+      values = _parse_line( <line> ).
+      " Send values to delegate
+      _delegate->values_found( values ).
+    endloop.
+  endmethod.                    "parse
+
+
+* <SIGNATURE>---------------------------------------------------------------------------------------+
+* | Instance Private Method CL_CSV_PARSER->_LINES
+* +-------------------------------------------------------------------------------------------------+
+* | [<-()] RETURNING                      TYPE        STRINGTAB
+* +--------------------------------------------------------------------------------------</SIGNATURE>
+  method _lines.
+    split _csvstring at cl_abap_char_utilities=>cr_lf into table returning.
+  endmethod.                    "_lines
+
+
+* <SIGNATURE>---------------------------------------------------------------------------------------+
+* | Instance Private Method CL_CSV_PARSER->_PARSE_LINE
+* +-------------------------------------------------------------------------------------------------+
+* | [--->] LINE                           TYPE        STRING
+* | [<-()] RETURNING                      TYPE        STRINGTAB
+* | [!CX!] CX_CSV_PARSE_ERROR
+* +--------------------------------------------------------------------------------------</SIGNATURE>
+  method _parse_line.
+    data msg type string.
+
+    data csvvalue type string.
+    data csvvalues type standard table of string.
+
+    data char type c.
+    data pos type i value 0.
+    data len type i.
+    len = strlen( line ).
+    while pos < len.
+      char = line+pos(1).
+      if char <> _separator.
+        if char = _textindicator.
+          data text_ended type abap_bool.
+          text_ended = abap_false.
+          while text_ended = abap_false.
+            pos = pos + 1.
+            if pos < len.
+              char = line+pos(1).
+              if char = _textindicator.
+                text_ended = abap_true.
+              else.
+                if char is initial. " Space
+                  concatenate csvvalue ` ` into csvvalue.
+                else.
+                  concatenate csvvalue char into csvvalue.
+                endif.
+              endif.
+            else.
+              " Reached the end of the line while inside a text value
+              " This indicates an error in the CSV formatting
+              text_ended = abap_true.
+              message e003(csv) into msg.
+              raise exception type cx_csv_parse_error
+                exporting
+                  message = msg.
+            endif.
+          endwhile.
+          " Check if next character is a separator, otherwise the CSV formatting is incorrect
+          data nextpos type i.
+          nextpos = pos + 1.
+          if nextpos < len and line+nextpos(1) <> _separator.
+            message e003(csv) into msg.
+            raise exception type cx_csv_parse_error
+              exporting
+                message = msg.
+          endif.
+        else.
+          if char is initial. " Space
+            concatenate csvvalue ` ` into csvvalue.
+          else.
+            concatenate csvvalue char into csvvalue.
+          endif.
+        endif.
+      else.
+        append csvvalue to csvvalues.
+        clear csvvalue.
+      endif.
+      pos = pos + 1.
+    endwhile.
+    append csvvalue to csvvalues. " Don't forget the last value
+
+    returning = csvvalues.
+  endmethod.                    "_parse_line
+endclass.                    "CL_CSV_PARSER IMPLEMENTATION

samples/ApacheConf/filenames/.htaccess

@@ -0,0 +1,26 @@
+ServerSignature Off
+RewriteCond %{REQUEST_METHOD} ^(HEAD|TRACE|DELETE|TRACK) [NC,OR]
+RewriteCond %{THE_REQUEST} (\\r|\\n|%0A|%0D) [NC,OR]
+
+RewriteCond %{HTTP_REFERER} (<|>|’|%0A|%0D|%27|%3C|%3E|%00) [NC,OR]
+RewriteCond %{HTTP_COOKIE} (<|>|’|%0A|%0D|%27|%3C|%3E|%00) [NC,OR]
+RewriteCond %{REQUEST_URI} ^/(,|;|:|<|>|”>|”<|/|\\\.\.\\).{0,9999} [NC,OR]
+
+RewriteCond %{HTTP_USER_AGENT} ^$ [OR]
+RewriteCond %{HTTP_USER_AGENT} ^(java|curl|wget) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (winhttp|HTTrack|clshttp|archiver|loader|email|harvest|extract|grab|miner) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (libwww-perl|curl|wget|python|nikto|scan) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (<|>|’|%0A|%0D|%27|%3C|%3E|%00) [NC,OR]
+
+#Block mySQL injects
+RewriteCond %{QUERY_STRING} (;|<|>|’|”|\)|%0A|%0D|%22|%27|%3C|%3E|%00).*(/\*|union|select|insert|cast|set|declare|drop|update|md5|benchmark) [NC,OR]
+
+RewriteCond %{QUERY_STRING} \.\./\.\. [OR]
+
+RewriteCond %{QUERY_STRING} (localhost|loopback|127\.0\.0\.1) [NC,OR]
+RewriteCond %{QUERY_STRING} \.[a-z0-9] [NC,OR]
+RewriteCond %{QUERY_STRING} (<|>|’|%0A|%0D|%27|%3C|%3E|%00) [NC]
+# Note: The final RewriteCond must NOT use the [OR] flag.
+
+# Return 403 Forbidden error.
+RewriteRule .* index.php [F]

samples/ApacheConf/filenames/apache2.conf

@@ -0,0 +1,470 @@
+# This is the main Apache HTTP server configuration file.  It contains the
+# configuration directives that give the server its instructions.
+# See <URL:http://httpd.apache.org/docs/2.2> for detailed information.
+# In particular, see
+# <URL:http://httpd.apache.org/docs/2.2/mod/directives.html>
+# for a discussion of each configuration directive.
+#
+# Do NOT simply read the instructions in here without understanding
+# what they do.  They're here only as hints or reminders.  If you are unsure
+# consult the online docs. You have been warned.
+#
+# Configuration and logfile names: If the filenames you specify for many
+# of the server's control files begin with "/" (or "drive:/" for Win32), the
+# server will use that explicit path.  If the filenames do *not* begin
+# with "/", the value of ServerRoot is prepended -- so "/var/log/apache2/foo.log"
+# with ServerRoot set to "" will be interpreted by the
+# server as "//var/log/apache2/foo.log".
+
+#
+# ServerRoot: The top of the directory tree under which the server's
+# configuration, error, and log files are kept.
+#
+# Do not add a slash at the end of the directory path.  If you point
+# ServerRoot at a non-local disk, be sure to point the LockFile directive
+# at a local disk.  If you wish to share the same ServerRoot for multiple
+# httpd daemons, you will need to change at least LockFile and PidFile.
+#
+ServerRoot ""
+
+#
+# Listen: Allows you to bind Apache to specific IP addresses and/or
+# ports, instead of the default. See also the <VirtualHost>
+# directive.
+#
+# Change this to Listen on specific IP addresses as shown below to
+# prevent Apache from glomming onto all bound IP addresses.
+#
+#Listen 12.34.56.78:80
+Listen 80
+
+#
+# Dynamic Shared Object (DSO) Support
+#
+# To be able to use the functionality of a module which was built as a DSO you
+# have to place corresponding `LoadModule' lines at this location so the
+# directives contained in it are actually available _before_ they are used.
+# Statically compiled modules (those listed by `httpd -l') do not need
+# to be loaded here.
+#
+# Example:
+# LoadModule foo_module modules/mod_foo.so
+#
+LoadModule authn_file_module /usr/lib/apache2/modules/mod_authn_file.so
+LoadModule authn_dbm_module /usr/lib/apache2/modules/mod_authn_dbm.so
+LoadModule authn_anon_module /usr/lib/apache2/modules/mod_authn_anon.so
+LoadModule authn_dbd_module /usr/lib/apache2/modules/mod_authn_dbd.so
+LoadModule authn_default_module /usr/lib/apache2/modules/mod_authn_default.so
+LoadModule authn_alias_module /usr/lib/apache2/modules/mod_authn_alias.so
+LoadModule authz_host_module /usr/lib/apache2/modules/mod_authz_host.so
+LoadModule authz_groupfile_module /usr/lib/apache2/modules/mod_authz_groupfile.so
+LoadModule authz_user_module /usr/lib/apache2/modules/mod_authz_user.so
+LoadModule authz_dbm_module /usr/lib/apache2/modules/mod_authz_dbm.so
+LoadModule authz_owner_module /usr/lib/apache2/modules/mod_authz_owner.so
+LoadModule authnz_ldap_module /usr/lib/apache2/modules/mod_authnz_ldap.so
+LoadModule authz_default_module /usr/lib/apache2/modules/mod_authz_default.so
+LoadModule auth_basic_module /usr/lib/apache2/modules/mod_auth_basic.so
+LoadModule auth_digest_module /usr/lib/apache2/modules/mod_auth_digest.so
+LoadModule file_cache_module /usr/lib/apache2/modules/mod_file_cache.so
+LoadModule cache_module /usr/lib/apache2/modules/mod_cache.so
+LoadModule disk_cache_module /usr/lib/apache2/modules/mod_disk_cache.so
+LoadModule mem_cache_module /usr/lib/apache2/modules/mod_mem_cache.so
+LoadModule dbd_module /usr/lib/apache2/modules/mod_dbd.so
+LoadModule dumpio_module /usr/lib/apache2/modules/mod_dumpio.so
+LoadModule ext_filter_module /usr/lib/apache2/modules/mod_ext_filter.so
+LoadModule include_module /usr/lib/apache2/modules/mod_include.so
+LoadModule filter_module /usr/lib/apache2/modules/mod_filter.so
+LoadModule charset_lite_module /usr/lib/apache2/modules/mod_charset_lite.so
+LoadModule deflate_module /usr/lib/apache2/modules/mod_deflate.so
+LoadModule ldap_module /usr/lib/apache2/modules/mod_ldap.so
+LoadModule log_forensic_module /usr/lib/apache2/modules/mod_log_forensic.so
+LoadModule env_module /usr/lib/apache2/modules/mod_env.so
+LoadModule mime_magic_module /usr/lib/apache2/modules/mod_mime_magic.so
+LoadModule cern_meta_module /usr/lib/apache2/modules/mod_cern_meta.so
+LoadModule expires_module /usr/lib/apache2/modules/mod_expires.so
+LoadModule headers_module /usr/lib/apache2/modules/mod_headers.so
+LoadModule ident_module /usr/lib/apache2/modules/mod_ident.so
+LoadModule usertrack_module /usr/lib/apache2/modules/mod_usertrack.so
+LoadModule unique_id_module /usr/lib/apache2/modules/mod_unique_id.so
+LoadModule setenvif_module /usr/lib/apache2/modules/mod_setenvif.so
+LoadModule version_module /usr/lib/apache2/modules/mod_version.so
+LoadModule proxy_module /usr/lib/apache2/modules/mod_proxy.so
+LoadModule proxy_connect_module /usr/lib/apache2/modules/mod_proxy_connect.so
+LoadModule proxy_ftp_module /usr/lib/apache2/modules/mod_proxy_ftp.so
+LoadModule proxy_http_module /usr/lib/apache2/modules/mod_proxy_http.so
+LoadModule proxy_ajp_module /usr/lib/apache2/modules/mod_proxy_ajp.so
+LoadModule proxy_balancer_module /usr/lib/apache2/modules/mod_proxy_balancer.so
+LoadModule ssl_module /usr/lib/apache2/modules/mod_ssl.so
+LoadModule mime_module /usr/lib/apache2/modules/mod_mime.so
+LoadModule dav_module /usr/lib/apache2/modules/mod_dav.so
+LoadModule status_module /usr/lib/apache2/modules/mod_status.so
+LoadModule autoindex_module /usr/lib/apache2/modules/mod_autoindex.so
+LoadModule asis_module /usr/lib/apache2/modules/mod_asis.so
+LoadModule info_module /usr/lib/apache2/modules/mod_info.so
+LoadModule suexec_module /usr/lib/apache2/modules/mod_suexec.so
+LoadModule cgid_module /usr/lib/apache2/modules/mod_cgid.so
+LoadModule cgi_module /usr/lib/apache2/modules/mod_cgi.so
+LoadModule dav_fs_module /usr/lib/apache2/modules/mod_dav_fs.so
+LoadModule dav_lock_module /usr/lib/apache2/modules/mod_dav_lock.so
+LoadModule vhost_alias_module /usr/lib/apache2/modules/mod_vhost_alias.so
+LoadModule negotiation_module /usr/lib/apache2/modules/mod_negotiation.so
+LoadModule dir_module /usr/lib/apache2/modules/mod_dir.so
+LoadModule imagemap_module /usr/lib/apache2/modules/mod_imagemap.so
+LoadModule actions_module /usr/lib/apache2/modules/mod_actions.so
+LoadModule speling_module /usr/lib/apache2/modules/mod_speling.so
+LoadModule userdir_module /usr/lib/apache2/modules/mod_userdir.so
+LoadModule alias_module /usr/lib/apache2/modules/mod_alias.so
+LoadModule rewrite_module /usr/lib/apache2/modules/mod_rewrite.so
+
+<IfModule !mpm_netware_module>
+#
+# If you wish httpd to run as a different user or group, you must run
+# httpd as root initially and it will switch.
+#
+# User/Group: The name (or #number) of the user/group to run httpd as.
+# It is usually good practice to create a dedicated user and group for
+# running httpd, as with most system services.
+#
+User daemon
+Group daemon
+</IfModule>
+
+# 'Main' server configuration
+#
+# The directives in this section set up the values used by the 'main'
+# server, which responds to any requests that aren't handled by a
+# <VirtualHost> definition.  These values also provide defaults for
+# any <VirtualHost> containers you may define later in the file.
+#
+# All of these directives may appear inside <VirtualHost> containers,
+# in which case these default settings will be overridden for the
+# virtual host being defined.
+#
+
+#
+# ServerAdmin: Your address, where problems with the server should be
+# e-mailed.  This address appears on some server-generated pages, such
+# as error documents.  e.g. admin@your-domain.com
+#
+ServerAdmin you@example.com
+
+#
+# ServerName gives the name and port that the server uses to identify itself.
+# This can often be determined automatically, but we recommend you specify
+# it explicitly to prevent problems during startup.
+#
+# If your host doesn't have a registered DNS name, enter its IP address here.
+#
+#ServerName www.example.com:80
+
+#
+# DocumentRoot: The directory out of which you will serve your
+# documents. By default, all requests are taken from this directory, but
+# symbolic links and aliases may be used to point to other locations.
+#
+DocumentRoot "/usr/share/apache2/default-site/htdocs"
+
+#
+# Each directory to which Apache has access can be configured with respect
+# to which services and features are allowed and/or disabled in that
+# directory (and its subdirectories).
+#
+# First, we configure the "default" to be a very restrictive set of
+# features.
+#
+<Directory />
+    Options FollowSymLinks
+    AllowOverride None
+    Order deny,allow
+    Deny from all
+</Directory>
+
+#
+# Note that from this point forward you must specifically allow
+# particular features to be enabled - so if something's not working as
+# you might expect, make sure that you have specifically enabled it
+# below.
+#
+
+#
+# This should be changed to whatever you set DocumentRoot to.
+#
+<Directory "/usr/share/apache2/default-site/htdocs">
+    #
+    # Possible values for the Options directive are "None", "All",
+    # or any combination of:
+    #   Indexes Includes FollowSymLinks SymLinksifOwnerMatch ExecCGI MultiViews
+    #
+    # Note that "MultiViews" must be named *explicitly* --- "Options All"
+    # doesn't give it to you.
+    #
+    # The Options directive is both complicated and important.  Please see
+    # http://httpd.apache.org/docs/2.2/mod/core.html#options
+    # for more information.
+    #
+    Options Indexes FollowSymLinks
+
+    #
+    # AllowOverride controls what directives may be placed in .htaccess files.
+    # It can be "All", "None", or any combination of the keywords:
+    #   Options FileInfo AuthConfig Limit
+    #
+    AllowOverride None
+
+    #
+    # Controls who can get stuff from this server.
+    #
+    Order allow,deny
+    Allow from all
+
+</Directory>
+
+#
+# DirectoryIndex: sets the file that Apache will serve if a directory
+# is requested.
+#
+<IfModule dir_module>
+    DirectoryIndex index.html
+</IfModule>
+
+#
+# The following lines prevent .htaccess and .htpasswd files from being
+# viewed by Web clients.
+#
+<FilesMatch "^\.ht">
+    Order allow,deny
+    Deny from all
+    Satisfy All
+</FilesMatch>
+
+#
+# ErrorLog: The location of the error log file.
+# If you do not specify an ErrorLog directive within a <VirtualHost>
+# container, error messages relating to that virtual host will be
+# logged here.  If you *do* define an error logfile for a <VirtualHost>
+# container, that host's errors will be logged there and not here.
+#
+ErrorLog /var/log/apache2/error_log
+
+#
+# LogLevel: Control the number of messages logged to the error_log.
+# Possible values include: debug, info, notice, warn, error, crit,
+# alert, emerg.
+#
+LogLevel warn
+
+<IfModule log_config_module>
+    #
+    # The following directives define some format nicknames for use with
+    # a CustomLog directive (see below).
+    #
+    LogFormat "%h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-Agent}i\"" combined
+    LogFormat "%h %l %u %t \"%r\" %>s %b" common
+
+    <IfModule logio_module>
+      # You need to enable mod_logio.c to use %I and %O
+      LogFormat "%h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-Agent}i\" %I %O" combinedio
+    </IfModule>
+
+    #
+    # The location and format of the access logfile (Common Logfile Format).
+    # If you do not define any access logfiles within a <VirtualHost>
+    # container, they will be logged here.  Contrariwise, if you *do*
+    # define per-<VirtualHost> access logfiles, transactions will be
+    # logged therein and *not* in this file.
+    #
+    CustomLog /var/log/apache2/access_log common
+
+    #
+    # If you prefer a logfile with access, agent, and referer information
+    # (Combined Logfile Format) you can use the following directive.
+    #
+    #CustomLog /var/log/apache2/access_log combined
+</IfModule>
+
+<IfModule alias_module>
+    #
+    # Redirect: Allows you to tell clients about documents that used to
+    # exist in your server's namespace, but do not anymore. The client
+    # will make a new request for the document at its new location.
+    # Example:
+    # Redirect permanent /foo http://www.example.com/bar
+
+    #
+    # Alias: Maps web paths into filesystem paths and is used to
+    # access content that does not live under the DocumentRoot.
+    # Example:
+    # Alias /webpath /full/filesystem/path
+    #
+    # If you include a trailing / on /webpath then the server will
+    # require it to be present in the URL.  You will also likely
+    # need to provide a <Directory> section to allow access to
+    # the filesystem path.
+
+    #
+    # ScriptAlias: This controls which directories contain server scripts.
+    # ScriptAliases are essentially the same as Aliases, except that
+    # documents in the target directory are treated as applications and
+    # run by the server when requested rather than as documents sent to the
+    # client.  The same rules about trailing "/" apply to ScriptAlias
+    # directives as to Alias.
+    #
+    ScriptAlias /cgi-bin/ "/usr/lib/cgi-bin/"
+
+</IfModule>
+
+<IfModule cgid_module>
+    #
+    # ScriptSock: On threaded servers, designate the path to the UNIX
+    # socket used to communicate with the CGI daemon of mod_cgid.
+    #
+    #Scriptsock /var/run/apache2/cgisock
+</IfModule>
+
+#
+# "/usr/lib/cgi-bin" should be changed to whatever your ScriptAliased
+# CGI directory exists, if you have that configured.
+#
+<Directory "/usr/lib/cgi-bin">
+    AllowOverride None
+    Options None
+    Order allow,deny
+    Allow from all
+</Directory>
+
+#
+# DefaultType: the default MIME type the server will use for a document
+# if it cannot otherwise determine one, such as from filename extensions.
+# If your server contains mostly text or HTML documents, "text/plain" is
+# a good value.  If most of your content is binary, such as applications
+# or images, you may want to use "application/octet-stream" instead to
+# keep browsers from trying to display binary files as though they are
+# text.
+#
+DefaultType text/plain
+
+<IfModule mime_module>
+    #
+    # TypesConfig points to the file containing the list of mappings from
+    # filename extension to MIME-type.
+    #
+    TypesConfig /etc/apache2/mime.types
+
+    #
+    # AddType allows you to add to or override the MIME configuration
+    # file specified in TypesConfig for specific file types.
+    #
+    #AddType application/x-gzip .tgz
+    #
+    # AddEncoding allows you to have certain browsers uncompress
+    # information on the fly. Note: Not all browsers support this.
+    #
+    #AddEncoding x-compress .Z
+    #AddEncoding x-gzip .gz .tgz
+    #
+    # If the AddEncoding directives above are commented-out, then you
+    # probably should define those extensions to indicate media types:
+    #
+    AddType application/x-compress .Z
+    AddType application/x-gzip .gz .tgz
+
+    #
+    # AddHandler allows you to map certain file extensions to "handlers":
+    # actions unrelated to filetype. These can be either built into the server
+    # or added with the Action directive (see below)
+    #
+    # To use CGI scripts outside of ScriptAliased directories:
+    # (You will also need to add "ExecCGI" to the "Options" directive.)
+    #
+    #AddHandler cgi-script .cgi
+
+    # For type maps (negotiated resources):
+    #AddHandler type-map var
+
+    #
+    # Filters allow you to process content before it is sent to the client.
+    #
+    # To parse .shtml files for server-side includes (SSI):
+    # (You will also need to add "Includes" to the "Options" directive.)
+    #
+    #AddType text/html .shtml
+    #AddOutputFilter INCLUDES .shtml
+</IfModule>
+
+#
+# The mod_mime_magic module allows the server to use various hints from the
+# contents of the file itself to determine its type.  The MIMEMagicFile
+# directive tells the module where the hint definitions are located.
+#
+#MIMEMagicFile /etc/apache2/magic
+
+#
+# Customizable error responses come in three flavors:
+# 1) plain text 2) local redirects 3) external redirects
+#
+# Some examples:
+#ErrorDocument 500 "The server made a boo boo."
+#ErrorDocument 404 /missing.html
+#ErrorDocument 404 "/cgi-bin/missing_handler.pl"
+#ErrorDocument 402 http://www.example.com/subscription_info.html
+#
+
+#
+# EnableMMAP and EnableSendfile: On systems that support it,
+# memory-mapping or the sendfile syscall is used to deliver
+# files.  This usually improves server performance, but must
+# be turned off when serving from networked-mounted
+# filesystems or if support for these functions is otherwise
+# broken on your system.
+#
+#EnableMMAP off
+#EnableSendfile off
+
+# Supplemental configuration
+#
+# The configuration files in the /etc/apache2/extra/ directory can be
+# included to add extra features or to modify the default configuration of
+# the server, or you may simply copy their contents here and change as
+# necessary.
+
+# Server-pool management (MPM specific)
+#Include /etc/apache2/extra/httpd-mpm.conf
+
+# Multi-language error messages
+#Include /etc/apache2/extra/httpd-multilang-errordoc.conf
+
+# Fancy directory listings
+#Include /etc/apache2/extra/httpd-autoindex.conf
+
+# Language settings
+#Include /etc/apache2/extra/httpd-languages.conf
+
+# User home directories
+#Include /etc/apache2/extra/httpd-userdir.conf
+
+# Real-time info on requests and configuration
+#Include /etc/apache2/extra/httpd-info.conf
+
+# Virtual hosts
+#Include /etc/apache2/extra/httpd-vhosts.conf
+
+# Local access to the Apache HTTP Server Manual
+#Include /etc/apache2/extra/httpd-manual.conf
+
+# Distributed authoring and versioning (WebDAV)
+#Include /etc/apache2/extra/httpd-dav.conf
+
+# Various default settings
+#Include /etc/apache2/extra/httpd-default.conf
+
+# Secure (SSL/TLS) connections
+#Include /etc/apache2/extra/httpd-ssl.conf
+#
+# Note: The following must must be present to support
+#       starting without SSL on platforms with no /dev/random equivalent
+#       but a statically compiled-in mod_ssl.
+#
+<IfModule ssl_module>
+SSLRandomSeed startup builtin
+SSLRandomSeed connect builtin
+</IfModule>

samples/ApacheConf/filenames/httpd.conf

@@ -0,0 +1,500 @@
+#
+# This is the main Apache HTTP server configuration file.  It contains the
+# configuration directives that give the server its instructions.
+# See <URL:http://httpd.apache.org/docs/2.2> for detailed information.
+# In particular, see 
+# <URL:http://httpd.apache.org/docs/2.2/mod/directives.html>
+# for a discussion of each configuration directive.
+#
+# Do NOT simply read the instructions in here without understanding
+# what they do.  They're here only as hints or reminders.  If you are unsure
+# consult the online docs. You have been warned.  
+#
+# Configuration and logfile names: If the filenames you specify for many
+# of the server's control files begin with "/" (or "drive:/" for Win32), the
+# server will use that explicit path.  If the filenames do *not* begin
+# with "/", the value of ServerRoot is prepended -- so "log/foo_log"
+# with ServerRoot set to "/usr" will be interpreted by the
+# server as "/usr/log/foo_log".
+
+#
+# ServerRoot: The top of the directory tree under which the server's
+# configuration, error, and log files are kept.
+#
+# Do not add a slash at the end of the directory path.  If you point
+# ServerRoot at a non-local disk, be sure to point the LockFile directive
+# at a local disk.  If you wish to share the same ServerRoot for multiple
+# httpd daemons, you will need to change at least LockFile and PidFile.
+#
+ServerRoot "/usr"
+
+#
+# Listen: Allows you to bind Apache to specific IP addresses and/or
+# ports, instead of the default. See also the <VirtualHost>
+# directive.
+#
+# Change this to Listen on specific IP addresses as shown below to 
+# prevent Apache from glomming onto all bound IP addresses.
+#
+#Listen 12.34.56.78:80
+Listen 80
+
+#
+# Dynamic Shared Object (DSO) Support
+#
+# To be able to use the functionality of a module which was built as a DSO you
+# have to place corresponding `LoadModule' lines at this location so the
+# directives contained in it are actually available _before_ they are used.
+# Statically compiled modules (those listed by `httpd -l') do not need
+# to be loaded here.
+#
+# Example:
+# LoadModule foo_module modules/mod_foo.so
+#
+LoadModule authn_file_module libexec/apache2/mod_authn_file.so
+LoadModule authn_dbm_module libexec/apache2/mod_authn_dbm.so
+LoadModule authn_anon_module libexec/apache2/mod_authn_anon.so
+LoadModule authn_dbd_module libexec/apache2/mod_authn_dbd.so
+LoadModule authn_default_module libexec/apache2/mod_authn_default.so
+LoadModule authz_host_module libexec/apache2/mod_authz_host.so
+LoadModule authz_groupfile_module libexec/apache2/mod_authz_groupfile.so
+LoadModule authz_user_module libexec/apache2/mod_authz_user.so
+LoadModule authz_dbm_module libexec/apache2/mod_authz_dbm.so
+LoadModule authz_owner_module libexec/apache2/mod_authz_owner.so
+LoadModule authz_default_module libexec/apache2/mod_authz_default.so
+LoadModule auth_basic_module libexec/apache2/mod_auth_basic.so
+LoadModule auth_digest_module libexec/apache2/mod_auth_digest.so
+LoadModule cache_module libexec/apache2/mod_cache.so
+LoadModule disk_cache_module libexec/apache2/mod_disk_cache.so
+LoadModule mem_cache_module libexec/apache2/mod_mem_cache.so
+LoadModule dbd_module libexec/apache2/mod_dbd.so
+LoadModule dumpio_module libexec/apache2/mod_dumpio.so
+LoadModule reqtimeout_module libexec/apache2/mod_reqtimeout.so
+LoadModule ext_filter_module libexec/apache2/mod_ext_filter.so
+LoadModule include_module libexec/apache2/mod_include.so
+LoadModule filter_module libexec/apache2/mod_filter.so
+LoadModule substitute_module libexec/apache2/mod_substitute.so
+LoadModule deflate_module libexec/apache2/mod_deflate.so
+LoadModule log_config_module libexec/apache2/mod_log_config.so
+LoadModule log_forensic_module libexec/apache2/mod_log_forensic.so
+LoadModule logio_module libexec/apache2/mod_logio.so
+LoadModule env_module libexec/apache2/mod_env.so
+LoadModule mime_magic_module libexec/apache2/mod_mime_magic.so
+LoadModule cern_meta_module libexec/apache2/mod_cern_meta.so
+LoadModule expires_module libexec/apache2/mod_expires.so
+LoadModule headers_module libexec/apache2/mod_headers.so
+LoadModule ident_module libexec/apache2/mod_ident.so
+LoadModule usertrack_module libexec/apache2/mod_usertrack.so
+#LoadModule unique_id_module libexec/apache2/mod_unique_id.so
+LoadModule setenvif_module libexec/apache2/mod_setenvif.so
+LoadModule version_module libexec/apache2/mod_version.so
+LoadModule proxy_module libexec/apache2/mod_proxy.so
+LoadModule proxy_connect_module libexec/apache2/mod_proxy_connect.so
+LoadModule proxy_ftp_module libexec/apache2/mod_proxy_ftp.so
+LoadModule proxy_http_module libexec/apache2/mod_proxy_http.so
+LoadModule proxy_scgi_module libexec/apache2/mod_proxy_scgi.so
+LoadModule proxy_ajp_module libexec/apache2/mod_proxy_ajp.so
+LoadModule proxy_balancer_module libexec/apache2/mod_proxy_balancer.so
+LoadModule ssl_module libexec/apache2/mod_ssl.so
+LoadModule mime_module libexec/apache2/mod_mime.so
+LoadModule dav_module libexec/apache2/mod_dav.so
+LoadModule status_module libexec/apache2/mod_status.so
+LoadModule autoindex_module libexec/apache2/mod_autoindex.so
+LoadModule asis_module libexec/apache2/mod_asis.so
+LoadModule info_module libexec/apache2/mod_info.so
+LoadModule cgi_module libexec/apache2/mod_cgi.so
+LoadModule dav_fs_module libexec/apache2/mod_dav_fs.so
+LoadModule vhost_alias_module libexec/apache2/mod_vhost_alias.so
+LoadModule negotiation_module libexec/apache2/mod_negotiation.so
+LoadModule dir_module libexec/apache2/mod_dir.so
+LoadModule imagemap_module libexec/apache2/mod_imagemap.so
+LoadModule actions_module libexec/apache2/mod_actions.so
+LoadModule speling_module libexec/apache2/mod_speling.so
+LoadModule userdir_module libexec/apache2/mod_userdir.so
+LoadModule alias_module libexec/apache2/mod_alias.so
+LoadModule rewrite_module libexec/apache2/mod_rewrite.so
+#LoadModule perl_module libexec/apache2/mod_perl.so
+#LoadModule php5_module libexec/apache2/libphp5.so
+#LoadModule hfs_apple_module libexec/apache2/mod_hfs_apple.so
+
+<IfModule !mpm_netware_module>
+<IfModule !mpm_winnt_module>
+#
+# If you wish httpd to run as a different user or group, you must run
+# httpd as root initially and it will switch.  
+#
+# User/Group: The name (or #number) of the user/group to run httpd as.
+# It is usually good practice to create a dedicated user and group for
+# running httpd, as with most system services.
+#
+User _www
+Group _www
+
+</IfModule>
+</IfModule>
+
+# 'Main' server configuration
+#
+# The directives in this section set up the values used by the 'main'
+# server, which responds to any requests that aren't handled by a
+# <VirtualHost> definition.  These values also provide defaults for
+# any <VirtualHost> containers you may define later in the file.
+#
+# All of these directives may appear inside <VirtualHost> containers,
+# in which case these default settings will be overridden for the
+# virtual host being defined.
+#
+
+#
+# ServerAdmin: Your address, where problems with the server should be
+# e-mailed.  This address appears on some server-generated pages, such
+# as error documents.  e.g. admin@your-domain.com
+#
+ServerAdmin you@example.com
+
+#
+# ServerName gives the name and port that the server uses to identify itself.
+# This can often be determined automatically, but we recommend you specify
+# it explicitly to prevent problems during startup.
+#
+# If your host doesn't have a registered DNS name, enter its IP address here.
+#
+#ServerName www.example.com:80
+
+#
+# DocumentRoot: The directory out of which you will serve your
+# documents. By default, all requests are taken from this directory, but
+# symbolic links and aliases may be used to point to other locations.
+#
+DocumentRoot "/Library/WebServer/Documents"
+
+#
+# Each directory to which Apache has access can be configured with respect
+# to which services and features are allowed and/or disabled in that
+# directory (and its subdirectories). 
+#
+# First, we configure the "default" to be a very restrictive set of 
+# features.  
+#
+<Directory />
+    Options FollowSymLinks
+    AllowOverride None
+    Order deny,allow
+    Deny from all
+</Directory>
+
+#
+# Note that from this point forward you must specifically allow
+# particular features to be enabled - so if something's not working as
+# you might expect, make sure that you have specifically enabled it
+# below.
+#
+
+#
+# This should be changed to whatever you set DocumentRoot to.
+#
+<Directory "/Library/WebServer/Documents">
+    #
+    # Possible values for the Options directive are "None", "All",
+    # or any combination of:
+    #   Indexes Includes FollowSymLinks SymLinksifOwnerMatch ExecCGI MultiViews
+    #
+    # Note that "MultiViews" must be named *explicitly* --- "Options All"
+    # doesn't give it to you.
+    #
+    # The Options directive is both complicated and important.  Please see
+    # http://httpd.apache.org/docs/2.2/mod/core.html#options
+    # for more information.
+    #
+    Options Indexes FollowSymLinks MultiViews
+
+    #
+    # AllowOverride controls what directives may be placed in .htaccess files.
+    # It can be "All", "None", or any combination of the keywords:
+    #   Options FileInfo AuthConfig Limit
+    #
+    AllowOverride None
+
+    #
+    # Controls who can get stuff from this server.
+    #
+    Order allow,deny
+    Allow from all
+
+</Directory>
+
+#
+# DirectoryIndex: sets the file that Apache will serve if a directory
+# is requested.
+#
+<IfModule dir_module>
+    DirectoryIndex index.html
+</IfModule>
+
+#
+# The following lines prevent .htaccess and .htpasswd files from being 
+# viewed by Web clients. 
+#
+<FilesMatch "^\.([Hh][Tt]|[Dd][Ss]_[Ss])">
+    Order allow,deny
+    Deny from all
+    Satisfy All
+</FilesMatch>
+
+#
+# Apple specific filesystem protection.
+#
+<Files "rsrc">
+    Order allow,deny
+    Deny from all
+    Satisfy All
+</Files>
+<DirectoryMatch ".*\.\.namedfork">
+    Order allow,deny
+    Deny from all
+    Satisfy All
+</DirectoryMatch>
+
+#
+# ErrorLog: The location of the error log file.
+# If you do not specify an ErrorLog directive within a <VirtualHost>
+# container, error messages relating to that virtual host will be
+# logged here.  If you *do* define an error logfile for a <VirtualHost>
+# container, that host's errors will be logged there and not here.
+#
+ErrorLog "/private/var/log/apache2/error_log"
+
+#
+# LogLevel: Control the number of messages logged to the error_log.
+# Possible values include: debug, info, notice, warn, error, crit,
+# alert, emerg.
+#
+LogLevel warn
+
+<IfModule log_config_module>
+    #
+    # The following directives define some format nicknames for use with
+    # a CustomLog directive (see below).
+    #
+    LogFormat "%h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-Agent}i\"" combined
+    LogFormat "%h %l %u %t \"%r\" %>s %b" common
+
+    <IfModule logio_module>
+      # You need to enable mod_logio.c to use %I and %O
+      LogFormat "%h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-Agent}i\" %I %O" combinedio
+    </IfModule>
+
+    #
+    # The location and format of the access logfile (Common Logfile Format).
+    # If you do not define any access logfiles within a <VirtualHost>
+    # container, they will be logged here.  Contrariwise, if you *do*
+    # define per-<VirtualHost> access logfiles, transactions will be
+    # logged therein and *not* in this file.
+    #
+    CustomLog "/private/var/log/apache2/access_log" common
+
+    #
+    # If you prefer a logfile with access, agent, and referer information
+    # (Combined Logfile Format) you can use the following directive.
+    #
+    #CustomLog "/private/var/log/apache2/access_log" combined
+</IfModule>
+
+<IfModule alias_module>
+    #
+    # Redirect: Allows you to tell clients about documents that used to 
+    # exist in your server's namespace, but do not anymore. The client 
+    # will make a new request for the document at its new location.
+    # Example:
+    # Redirect permanent /foo http://www.example.com/bar
+
+    #
+    # Alias: Maps web paths into filesystem paths and is used to
+    # access content that does not live under the DocumentRoot.
+    # Example:
+    # Alias /webpath /full/filesystem/path
+    #
+    # If you include a trailing / on /webpath then the server will
+    # require it to be present in the URL.  You will also likely
+    # need to provide a <Directory> section to allow access to
+    # the filesystem path.
+
+    #
+    # ScriptAlias: This controls which directories contain server scripts. 
+    # ScriptAliases are essentially the same as Aliases, except that
+    # documents in the target directory are treated as applications and
+    # run by the server when requested rather than as documents sent to the
+    # client.  The same rules about trailing "/" apply to ScriptAlias
+    # directives as to Alias.
+    #
+    ScriptAliasMatch ^/cgi-bin/((?!(?i:webobjects)).*$) "/Library/WebServer/CGI-Executables/$1"
+
+</IfModule>
+
+<IfModule cgid_module>
+    #
+    # ScriptSock: On threaded servers, designate the path to the UNIX
+    # socket used to communicate with the CGI daemon of mod_cgid.
+    #
+    #Scriptsock /private/var/run/cgisock
+</IfModule>
+
+#
+# "/Library/WebServer/CGI-Executables" should be changed to whatever your ScriptAliased
+# CGI directory exists, if you have that configured.
+#
+<Directory "/Library/WebServer/CGI-Executables">
+    AllowOverride None
+    Options None
+    Order allow,deny
+    Allow from all
+</Directory>
+
+#
+# DefaultType: the default MIME type the server will use for a document
+# if it cannot otherwise determine one, such as from filename extensions.
+# If your server contains mostly text or HTML documents, "text/plain" is
+# a good value.  If most of your content is binary, such as applications
+# or images, you may want to use "application/octet-stream" instead to
+# keep browsers from trying to display binary files as though they are
+# text.
+#
+DefaultType text/plain
+
+<IfModule mime_module>
+    #
+    # TypesConfig points to the file containing the list of mappings from
+    # filename extension to MIME-type.
+    #
+    TypesConfig /private/etc/apache2/mime.types
+
+    #
+    # AddType allows you to add to or override the MIME configuration
+    # file specified in TypesConfig for specific file types.
+    #
+    #AddType application/x-gzip .tgz
+    #
+    # AddEncoding allows you to have certain browsers uncompress
+    # information on the fly. Note: Not all browsers support this.
+    #
+    #AddEncoding x-compress .Z
+    #AddEncoding x-gzip .gz .tgz
+    #
+    # If the AddEncoding directives above are commented-out, then you
+    # probably should define those extensions to indicate media types:
+    #
+    AddType application/x-compress .Z
+    AddType application/x-gzip .gz .tgz
+
+    #
+    # AddHandler allows you to map certain file extensions to "handlers":
+    # actions unrelated to filetype. These can be either built into the server
+    # or added with the Action directive (see below)
+    #
+    # To use CGI scripts outside of ScriptAliased directories:
+    # (You will also need to add "ExecCGI" to the "Options" directive.)
+    #
+    #AddHandler cgi-script .cgi
+
+    # For type maps (negotiated resources):
+    #AddHandler type-map var
+
+    #
+    # Filters allow you to process content before it is sent to the client.
+    #
+    # To parse .shtml files for server-side includes (SSI):
+    # (You will also need to add "Includes" to the "Options" directive.)
+    #
+    #AddType text/html .shtml
+    #AddOutputFilter INCLUDES .shtml
+</IfModule>
+
+#
+# The mod_mime_magic module allows the server to use various hints from the
+# contents of the file itself to determine its type.  The MIMEMagicFile
+# directive tells the module where the hint definitions are located.
+#
+#MIMEMagicFile /private/etc/apache2/magic
+
+#
+# Customizable error responses come in three flavors:
+# 1) plain text 2) local redirects 3) external redirects
+#
+# Some examples:
+#ErrorDocument 500 "The server made a boo boo."
+#ErrorDocument 404 /missing.html
+#ErrorDocument 404 "/cgi-bin/missing_handler.pl"
+#ErrorDocument 402 http://www.example.com/subscription_info.html
+#
+
+#
+# MaxRanges: Maximum number of Ranges in a request before
+# returning the entire resource, or one of the special
+# values 'default', 'none' or 'unlimited'.
+# Default setting is to accept 200 Ranges.
+#MaxRanges unlimited
+
+#
+# EnableMMAP and EnableSendfile: On systems that support it, 
+# memory-mapping or the sendfile syscall is used to deliver
+# files.  This usually improves server performance, but must
+# be turned off when serving from networked-mounted 
+# filesystems or if support for these functions is otherwise
+# broken on your system.
+#
+#EnableMMAP off
+#EnableSendfile off
+
+# 6894961
+TraceEnable off
+
+# Supplemental configuration
+#
+# The configuration files in the /private/etc/apache2/extra/ directory can be 
+# included to add extra features or to modify the default configuration of 
+# the server, or you may simply copy their contents here and change as 
+# necessary.
+
+# Server-pool management (MPM specific)
+Include /private/etc/apache2/extra/httpd-mpm.conf
+
+# Multi-language error messages
+#Include /private/etc/apache2/extra/httpd-multilang-errordoc.conf
+
+# Fancy directory listings
+Include /private/etc/apache2/extra/httpd-autoindex.conf
+
+# Language settings
+Include /private/etc/apache2/extra/httpd-languages.conf
+
+# User home directories
+Include /private/etc/apache2/extra/httpd-userdir.conf
+
+# Real-time info on requests and configuration
+#Include /private/etc/apache2/extra/httpd-info.conf
+
+# Virtual hosts
+#Include /private/etc/apache2/extra/httpd-vhosts.conf
+
+# Local access to the Apache HTTP Server Manual
+Include /private/etc/apache2/extra/httpd-manual.conf
+
+# Distributed authoring and versioning (WebDAV)
+#Include /private/etc/apache2/extra/httpd-dav.conf
+
+# Various default settings
+#Include /private/etc/apache2/extra/httpd-default.conf
+
+# Secure (SSL/TLS) connections
+#Include /private/etc/apache2/extra/httpd-ssl.conf
+#
+# Note: The following must must be present to support
+#       starting without SSL on platforms with no /dev/random equivalent
+#       but a statically compiled-in mod_ssl.
+#
+<IfModule ssl_module>
+SSLRandomSeed startup builtin
+SSLRandomSeed connect builtin
+</IfModule>
+
+Include /private/etc/apache2/other/*.conf

samples/AppleScript/Convert To PDF.applescript

@@ -0,0 +1,87 @@
+(*
+Copyright 2003 Apple Computer, Inc.
+
+You may incorporate this Apple sample code into your program(s) without
+restriction.  This Apple sample code has been provided "AS IS" and the
+responsibility for its operation is yours.  You are not permitted to
+redistribute this Apple sample code as "Apple sample code" after having
+made changes.  If you're going to redistribute the code, we require
+that you make it clear that the code was descended from Apple sample
+code, but that you've made changes.
+*)
+
+property type_list : {"JPEG", "GIFf", "PICT", "TIFF", "PDF", "TEXT"}
+property extension_list : {"jpg", "gif", "pct", "tif", "pdf", "rtf"}
+--html is not currently handled
+
+on run {}
+	tell application "Finder" to set FinderSelection to the selection as alias list
+	
+	set FS to FinderSelection
+	--Ideally, this list could be passed to the open handler
+	
+	set SelectionCount to number of FS -- count	
+	if SelectionCount is 0 then
+		set FS to userPicksFolder()
+	else if the SelectionCount is 1 then
+		set MyPath to path to me
+		if MyPath is item 1 of FS then
+			--If I'm a droplet then I was double-clicked
+			set FS to userPicksFolder()
+		end if
+	else
+		--I'm not a double-clicked droplet
+	end if
+	open FS
+end run
+
+on userPicksFolder()
+	set these_items to {}
+	set these_items to (choose file with prompt "Select a file to convert to PDF:" of type {"JPEG", "GIFf", "PICT", "TIFF", "TEXT", "RTF"}) as list
+end userPicksFolder
+
+on open these_items
+	set thesefiles to {}
+	set the item_info to {}
+	repeat with i from 1 to the count of these_items
+		set this_item to (item i of these_items)
+		set the item_info to info for this_item
+		
+		if folder of the item_info is true then --if the item is a folder
+			processFolder(this_item)
+		else if ((folder of the item_info is false) and (alias of the item_info is false)) and (the file type of the item_info is in the type_list) or ((the name extension of the item_info) is in the extension_list) then
+			
+			set theFilePath to (item i of these_items as string)
+			set thePOSIXFilePath to POSIX path of theFilePath as string
+			processFile(thePOSIXFilePath)
+		end if
+	end repeat
+end open
+
+--process folders 
+on processFolder(theFolder)
+	set these_items to list folder theFolder without invisibles
+	repeat with i from 1 to the count of these_items
+		set this_item to alias ((theFolder as text) & (item i of these_items))
+		set the item_info to info for this_item
+		if folder of the item_info is true then
+			processFolder(this_item)
+		else if (alias of the item_info is false) and ((the file type of the item_info is in the type_list) or the name extension of the item_info is in the extension_list) then
+			set theFilePath to (this_item as string)
+			set thePOSIXFilePath to POSIX path of theFilePath as string
+			processFile(thePOSIXFilePath)
+		end if
+	end repeat
+end processFolder
+
+on processFile(thePOSIXFileName)
+	try
+		set terminalCommand to ""
+		set convertCommand to "/System/Library/Printers/Libraries/./convert "
+		set newFileName to thePOSIXFileName & ".pdf"
+		set terminalCommand to convertCommand & "-f " & "\"" & thePOSIXFileName & "\"" & " -o " & "\"" & newFileName & "\"" & " -j \"application/pdf\""
+		
+		do shell script terminalCommand
+	end try
+end processFile
+

samples/AppleScript/Convert To PostScript.applescript

@@ -0,0 +1,91 @@
+(*
+
+Copyright 2003 Apple Computer, Inc.
+
+You may incorporate this Apple sample code into your program(s) without
+restriction.  This Apple sample code has been provided "AS IS" and the
+responsibility for its operation is yours.  You are not permitted to
+redistribute this Apple sample code as "Apple sample code" after having
+made changes.  If you're going to redistribute the code, we require
+that you make it clear that the code was descended from Apple sample
+code, but that you've made changes.
+*)
+
+property type_list : {"JPEG", "GIFf", "PICT", "TIFF", "PDF", "TEXT"}
+property extension_list : {"jpg", "gif", "pct", "tif", "pdf", "rtf"}
+--html is not currently handled
+
+on run {}
+	tell application "Finder" to set FinderSelection to the selection as alias list
+	
+	set FS to FinderSelection
+	--Ideally, this list could be passed to the open handler
+	
+	set SelectionCount to number of FS -- count	
+	if SelectionCount is 0 then
+		set FS to userPicksFolder()
+	else if the SelectionCount is 1 then
+		set MyPath to path to me
+		if MyPath is item 1 of FS then
+			--If I'm a droplet then I was double-clicked
+			set FS to userPicksFolder()
+		end if
+	else
+		--I'm not a double-clicked droplet
+	end if
+	open FS
+end run
+
+on userPicksFolder()
+	set these_items to {}
+	set these_items to (choose file with prompt "Select a file to convert to PostScript:" of type {"JPEG", "GIFf", "PICT", "TIFF", "TEXT", "RTF"}) as list
+end userPicksFolder
+
+
+on open these_items
+	set thesefiles to {}
+	set the item_info to {}
+	repeat with i from 1 to the count of these_items
+		set this_item to (item i of these_items)
+		set the item_info to info for this_item
+		
+		if folder of the item_info is true then --if the item is a folder
+			processFolder(this_item)
+		else if ((folder of the item_info is false) and (alias of the item_info is false)) and (the file type of the item_info is in the type_list) or ((the name extension of the item_info) is in the extension_list) then
+			
+			set theFilePath to (item i of these_items as string)
+			set thePOSIXFilePath to POSIX path of theFilePath as string
+			processFile(thePOSIXFilePath)
+		end if
+	end repeat
+end open
+
+--process folders 
+on processFolder(theFolder)
+	set these_items to list folder theFolder without invisibles
+	repeat with i from 1 to the count of these_items
+		set this_item to alias ((theFolder as text) & (item i of these_items))
+		set the item_info to info for this_item
+		if folder of the item_info is true then
+			processFolder(this_item)
+		else if (alias of the item_info is false) and ((the file type of the item_info is in the type_list) or the name extension of the item_info is in the extension_list) then
+			set theFilePath to (this_item as string)
+			set thePOSIXFilePath to POSIX path of theFilePath as string
+			processFile(thePOSIXFilePath)
+		end if
+	end repeat
+end processFolder
+
+--need to pass the URL to Terminal
+on processFile(thePOSIXFileName)
+	try
+		set terminalCommand to ""
+		set convertCommand to "/System/Library/Printers/Libraries/./convert "
+		set newFileName to thePOSIXFileName & ".ps"
+		set terminalCommand to convertCommand & "-f " & "\"" & thePOSIXFileName & "\"" & " -o " & "\"" & newFileName & "\"" & " -j \"application/postscript\""
+		
+		do shell script terminalCommand
+	end try
+end processFile
+
+

samples/AppleScript/Count Messages in All Mailboxes.applescript

@@ -0,0 +1,80 @@
+(*
+Count Messages in All Mailboxes
+
+Copyright 2002-2012 Apple Inc. All rights reserved.
+
+You may incorporate this Apple sample code into your program(s) without
+restriction.  This Apple sample code has been provided "AS IS" and the
+responsibility for its operation is yours.  You are not permitted to
+redistribute this Apple sample code as "Apple sample code" after having
+made changes.  If you're going to redistribute the code, we require
+that you make it clear that the code was descended from Apple sample
+code, but that you've made changes.
+*)
+
+(*
+This script goes through each mailbox, gets the total message count and
+the unread count, then displays the final output in a new email message.
+*)
+
+tell application "Mail"
+	set localMailboxes to every mailbox
+	if (count of localMailboxes) is greater than 0 then
+		set messageCountDisplay to "Local mailboxes (On My Mac)" & return & my getMessageCountsForMailboxes(localMailboxes)
+	else
+		set messageCountDisplay to ""
+	end if
+	
+	set everyAccount to every account
+	repeat with eachAccount in everyAccount
+		set accountMailboxes to every mailbox of eachAccount
+		if (count of accountMailboxes) is greater than 0 then
+			set messageCountDisplay to messageCountDisplay & return & "Mailboxes for Account: " & name of eachAccount & return & my getMessageCountsForMailboxes(accountMailboxes)
+		end if
+	end repeat
+	
+	set outputMessage to make new outgoing message with properties {content:messageCountDisplay, subject:"Message counts for all my mailboxes", visible:true}
+	tell outputMessage
+		set font to "Courier"
+		set size to 12
+	end tell
+end tell
+
+on getMessageCountsForMailboxes(theMailboxes)
+	-- (list of mailboxes)
+	-- returns string
+	
+	set displayString to ""
+	
+	tell application "Mail"
+		repeat with eachMailbox in theMailboxes
+			set mailboxName to name of eachMailbox
+			set messageCount to (count of (messages of eachMailbox)) as string
+			set unreadCount to unread count of eachMailbox as string
+			
+			set displayString to displayString & "    " & my padString(mailboxName, 40) & "  " & messageCount & " (" & unreadCount & " unread)" & return
+		end repeat
+	end tell
+	
+	return displayString
+end getMessageCountsForMailboxes
+
+on padString(theString, fieldLength)
+	-- (string, integer)
+	-- returns string
+	
+	set stringLength to length of theString
+	
+	if stringLength is greater than fieldLength then
+		set paddedString to (text from character 1 to character (fieldLength - 3) of theString) & "..."
+	else -- stringLength is less than or equal to fieldLength
+		set paddedString to theString
+		
+		set paddingLength to fieldLength - stringLength
+		repeat paddingLength times
+			set paddedString to paddedString & space
+		end repeat
+	end if
+	
+	return paddedString
+end padString

samples/AppleScript/Crazy Message Text.applescript

@@ -0,0 +1,68 @@
+(*
+Crazy Message Text
+
+Copyright 2002-2012 Apple Inc. All rights reserved.
+
+You may incorporate this Apple sample code into your program(s) without
+restriction.  This Apple sample code has been provided "AS IS" and the
+responsibility for its operation is yours.  You are not permitted to
+redistribute this Apple sample code as "Apple sample code" after having
+made changes.  If you're going to redistribute the code, we require
+that you make it clear that the code was descended from Apple sample
+code, but that you've made changes.
+*)
+
+(*
+This script takes a string from the user and then makes a new message
+where each letter has a different font, size, and color.
+*)
+
+property lowFontSize : 36
+property highFontSize : 72
+property messageText : "Happy Birthday!"
+
+repeat
+	set userInput to display dialog "Enter some message text:" & return & return & "Minimum Character Size: " & (lowFontSize as string) & return & "Maximum Character Size: " & (highFontSize as string) default answer messageText buttons {"Cancel", "Set Prefs", "Continue"} default button 3
+	
+	if the button returned of userInput is "Set Prefs" then
+		set minimumFontSize to 9
+		
+		display dialog "Enter the minimum font size to use:" & return & return & "(Must be at least " & (minimumFontSize as string) & ")" default answer lowFontSize buttons {"OK"}
+		set newFontSize to text returned of the result as integer
+		if newFontSize is greater than or equal to minimumFontSize then
+			set lowFontSize to newFontSize
+		else
+			set lowFontSize to minimumFontSize
+		end if
+		
+		display dialog "Enter the maximum font size to use:" & return & return & "(Must be greater than " & (lowFontSize as string) & ")" default answer highFontSize buttons {"OK"}
+		set newFontSize to text returned of the result as integer
+		if newFontSize is greater than lowFontSize then
+			set highFontSize to newFontSize
+		else
+			set highFontSize to lowFontSize
+		end if
+		
+	else -- button returned of userInput is "Continue"
+		set theText to text returned of userInput
+		if theText is not "" then
+			set messageText to theText
+		end if
+		exit repeat
+	end if
+end repeat
+
+set fontList to {"American Typewriter", "American Typewriter Light", "American Typewriter Bold", "American Typewriter Condensed", "American Typewriter Condensed Light", "American Typewriter Condensed Bold", "Arial", "Arial Italic", "Arial Bold", "Arial Bold Italic", "Arial Black", "Baskerville", "Baskerville Italic", "Baskerville SemiBold", "Baskerville Bold", "Baskerville SemiBold Italic", "Baskerville Bold Italic", "Big Caslon Medium", "Comic Sans MS", "Comic Sans MS Bold", "Copperplate", "Copperplate Light", "Copperplate Bold", "Didot", "Didot Italic", "Didot Bold", "Futura Medium", "Futura Medium Italic", "Futura Condensed Medium", "Futura Condensed ExtraBold", "Geneva", "Gill Sans", "Gill Sans Italic", "Gill Sans Light", "Gill Sans Light Italic", "Gill Sans Bold", "Gill Sans Bold Italic", "Herculanum", "Lucida Grande", "Lucida Grande Bold", "Marker Felt Thin", "Marker Felt Wide", "Optima Regular", "Optima Italic", "Optima Bold", "Optima Bold Italic", "Optima ExtraBlack", "Papyrus", "Verdana", "Verdana Italic", "Verdana Bold", "Verdana Bold Italic", "Zapfino"}
+
+tell application "Mail"
+	activate
+	set crazyTextMessage to make new outgoing message with properties {content:messageText, visible:true}
+	
+	tell crazyTextMessage
+		repeat with eachCharacter in characters
+			set font of eachCharacter to (some item of fontList)
+			set size of eachCharacter to (random number from lowFontSize to highFontSize)
+			set color of eachCharacter to {random number from 0 to 65535, random number from 0 to 65535, random number from 0 to 65535}
+		end repeat
+	end tell
+end tell

samples/AppleScript/Get User Name.applescript

@@ -0,0 +1,41 @@
+(*
+Get User Name
+
+This script uses UI element scripting to get the name for the
+current user.
+
+If "Enable access for assistive devices" is not checked,
+this script will open the Universal Access System Preference and ask
+the user to check the checkbox.
+
+Copyright 2007 Apple Inc.
+
+You may incorporate this Apple sample code into your program(s) without
+restriction.  This Apple sample code has been provided "AS IS" and the
+responsibility for its operation is yours.  You are not permitted to
+redistribute this Apple sample code as "Apple sample code" after having
+made changes.  If you're going to redistribute the code, we require
+that you make it clear that the code was descended from Apple sample
+code, but that you've made changes.
+*)
+
+tell application "System Preferences"
+	activate
+	set current pane to pane "com.apple.preferences.users"
+end tell
+
+tell application "System Events"
+	if UI elements enabled then
+		tell tab group 1 of window "Accounts" of process "System Preferences"
+			click radio button 1
+			delay 2
+			get value of text field 1
+		end tell
+	else
+		tell application "System Preferences"
+			activate
+			set current pane to pane "com.apple.preference.universalaccess"
+			display dialog "UI element scripting is not enabled. Check \"Enable access for assistive devices\""
+		end tell
+	end if
+end tell

samples/AppleScript/Time Of Day.applescript

@@ -0,0 +1,75 @@
+(* 
+ Speaks the  date and time of day
+ 
+ Copyright 2008 Apple Inc. All rights reserved.
+ 
+ You may incorporate this Apple sample code into your program(s) without
+ restriction.  This Apple sample code has been provided "AS IS" and the
+ responsibility for its operation is yours.  You are not permitted to
+ redistribute this Apple sample code as "Apple sample code" after having
+ made changes.  If you're going to redistribute the code, we require
+ that you make it clear that the code was descended from Apple sample
+ code, but that you've made changes.
+ *)
+
+on isVoiceOverRunning()
+	set isRunning to false
+	tell application "System Events"
+		set isRunning to (name of processes) contains "VoiceOver"
+	end tell
+	return isRunning
+end isVoiceOverRunning
+
+on isVoiceOverRunningWithAppleScript()
+	if isVoiceOverRunning() then
+		set isRunningWithAppleScript to true
+		
+		-- is AppleScript enabled on VoiceOver --
+		tell application "VoiceOver"
+			try
+				set x to bounds of vo cursor
+			on error
+				set isRunningWithAppleScript to false
+			end try
+		end tell
+		return isRunningWithAppleScript
+	end if
+	return false
+end isVoiceOverRunningWithAppleScript
+
+set currentDate to current date
+set amPM to "AM"
+set currentHour to (currentDate's hours)
+set currentMinutes to currentDate's minutes
+
+if (currentHour > 12 and currentHour < 24) then
+	set amPM to "PM"
+else
+	set amPM to "AM"
+end if
+
+--  make minutes below 10 sound nice
+if currentMinutes < 10 then
+	set currentMinutes to ("0" & currentMinutes) as text
+end if
+
+--  ensure 0:nn gets set to 12:nn AM
+if currentHour is equal to 0 then
+	set currentHour to 12
+end if
+
+--  readjust for 12 hour time
+if (currentHour > 12) then
+	set currentHour to (currentHour - 12)
+end if
+
+set currentTime to ((currentDate's month) as text) & " " & ((currentDate's day) as text) & ", " & (currentHour as text) & ":" & ((currentMinutes) as text) & " " & amPM as text
+
+if isVoiceOverRunningWithAppleScript() then
+	tell application "VoiceOver"
+		output currentTime
+	end tell
+else
+	say currentTime
+	delay 2
+end if

samples/AsciiDoc/encoding.asciidoc

@@ -0,0 +1,13 @@
+Gregory Romé has written an AsciiDoc plugin for the Redmine project management application.
+
+https://github.com/foo-users/foo
+へと `vicmd` キーマップを足してみている試み、
+アニメーションgifです。
+
+tag::romé[]
+Gregory Romé has written an AsciiDoc plugin for the Redmine project management application.
+end::romé[]
+
+== Überschrift
+
+* Codierungen sind verrückt auf älteren Versionen von Ruby

samples/AsciiDoc/list.asc

@@ -0,0 +1,10 @@
+AsciiDoc Home Page
+==================
+
+Example Articles
+~~~~~~~~~~~~~~~~
+- Item 1
+
+- Item 2
+
+- Item 3

samples/AsciiDoc/sample.adoc

@@ -0,0 +1,25 @@
+Document Title
+==============
+Doc Writer <thedoc@asciidoctor.org>
+:idprefix: id_
+
+Preamble paragraph.
+
+NOTE: This is test, only a test.
+
+== Section A
+
+*Section A* paragraph.
+
+=== Section A Subsection
+
+*Section A* 'subsection' paragraph.
+
+== Section B
+
+*Section B* paragraph.
+
+.Section B list
+* Item 1
+* Item 2
+* Item 3

samples/Awk/test.awk

@@ -0,0 +1,121 @@
+#!/bin/awk -f
+
+BEGIN {
+  # It is not possible to define output file names here because
+  # FILENAME is not define in the BEGIN section
+  n = "";
+  printf "Generating data files ...";
+  network_max_bandwidth_in_byte = 10000000;
+  network_max_packet_per_second = 1000000;
+  last3 = 0;
+  last4 = 0;
+  last5 = 0;
+  last6 = 0;
+}
+{
+  if ($1 ~ /Average/)
+    { # Skip the Average values
+      n = "";
+      next;
+    }
+
+  if ($2 ~ /all/)
+    { # This is the cpu info
+      print $3 > FILENAME".cpu.user.dat";
+#	  print $4 > FILENAME".cpu.nice.dat";
+      print $5 > FILENAME".cpu.system.dat";
+#     print $6 > FILENAME".cpu.iowait.dat";
+      print $7 > FILENAME".cpu.idle.dat";
+      print 100-$7 > FILENAME".cpu.busy.dat";
+    }
+  if ($2 ~ /eth0/)
+    { # This is the eth0 network info
+      if ($3 > network_max_packet_per_second)
+	print last3 > FILENAME".net.rxpck.dat"; # Total number of packets received per second.
+      else
+	{
+	  last3 = $3;
+	  print $3 > FILENAME".net.rxpck.dat"; # Total number of packets received per second.
+	}
+      if ($4 > network_max_packet_per_second)
+	print last4 > FILENAME".net.txpck.dat"; # Total number of packets transmitted per second.
+      else
+	{
+	  last4 = $4;
+	  print $4 > FILENAME".net.txpck.dat"; # Total number of packets transmitted per second.
+	}
+      if ($5 > network_max_bandwidth_in_byte)
+	print last5 > FILENAME".net.rxbyt.dat"; # Total number of bytes received per second.
+      else
+	{
+	  last5 = $5;
+	  print $5 > FILENAME".net.rxbyt.dat"; # Total number of bytes received per second.
+	}
+      if ($6 > network_max_bandwidth_in_byte)
+	print last6 > FILENAME".net.txbyt.dat"; # Total number of bytes transmitted per second.
+      else
+	{
+	  last6 = $6;
+	  print $6 > FILENAME".net.txbyt.dat"; # Total number of bytes transmitted per second.
+	}
+#     print $7 > FILENAME".net.rxcmp.dat"; # Number of compressed packets received per second (for cslip etc.).
+#     print $8 > FILENAME".net.txcmp.dat"; # Number of compressed packets transmitted per second.
+#     print $9 > FILENAME".net.rxmcst.dat"; # Number of multicast packets received per second.
+    }
+
+  # Detect which is the next info to be parsed
+  if ($2 ~ /proc|cswch|tps|kbmemfree|totsck/)
+    {
+      n = $2;
+    }
+
+  # Only get lines with numbers (real data !)
+  if ($2 ~ /[0-9]/)
+    {
+      if (n == "proc/s")
+	{ # This is the proc/s info
+	  print $2 > FILENAME".proc.dat";
+#	  n = "";
+	}
+      if (n == "cswch/s")
+	{ # This is the context switches per second info
+	  print $2 > FILENAME".ctxsw.dat";
+#	  n = "";
+	}
+      if (n == "tps")
+	{ # This is the disk info
+	  print $2 > FILENAME".disk.tps.dat"; # total transfers per second
+	  print $3 > FILENAME".disk.rtps.dat"; # read requests per second
+	  print $4 > FILENAME".disk.wtps.dat"; # write requests per second
+	  print $5 > FILENAME".disk.brdps.dat"; # block reads per second
+	  print $6 > FILENAME".disk.bwrps.dat"; # block writes per second
+#	  n = "";
+	}
+      if (n == "kbmemfree")
+	{ # This is the mem info
+	  print $2 > FILENAME".mem.kbmemfree.dat"; # Amount of free memory available in kilobytes.
+	  print $3 > FILENAME".mem.kbmemused.dat"; # Amount of used memory in kilobytes. This does not take into account memory used by the kernel itself.
+	  print $4 > FILENAME".mem.memused.dat"; # Percentage of used memory.
+#         It appears the kbmemshrd has been removed from the sysstat output - ntolia
+#	  print $X > FILENAME".mem.kbmemshrd.dat"; # Amount of memory shared by the system in kilobytes.  Always zero with 2.4 kernels.
+#	  print $5 > FILENAME".mem.kbbuffers.dat"; # Amount of memory used as buffers by the kernel in kilobytes.
+	  print $6 > FILENAME".mem.kbcached.dat"; # Amount of memory used to cache data by the kernel in kilobytes.
+#	  print $7 > FILENAME".mem.kbswpfree.dat"; # Amount of free swap space in kilobytes.
+#	  print $8 > FILENAME".mem.kbswpused.dat"; # Amount of used swap space in kilobytes.
+	  print $9 > FILENAME".mem.swpused.dat"; # Percentage of used swap space.
+#	  n = "";
+ 	}
+      if (n == "totsck")
+	{ # This is the socket info
+	  print $2 > FILENAME".sock.totsck.dat"; # Total number of used sockets.
+	  print $3 > FILENAME".sock.tcpsck.dat"; # Number of TCP sockets currently in use.
+#	  print $4 > FILENAME".sock.udpsck.dat"; # Number of UDP sockets currently in use.
+#	  print $5 > FILENAME".sock.rawsck.dat"; # Number of RAW sockets currently in use.
+#	  print $6 > FILENAME".sock.ip-frag.dat"; # Number of IP fragments currently in use.
+#	  n = "";
+ 	}
+    }
+}
+END {
+  print " '" FILENAME "' done.";
+}

samples/C++/gdsdbreader.h

@@ -0,0 +1,69 @@
+#ifndef GDSDBREADER_H
+#define GDSDBREADER_H
+
+// This file contains core structures, classes and types for the entire gds app
+// WARNING: DO NOT MODIFY UNTIL IT'S STRICTLY NECESSARY
+
+#include <QDir>
+#include "diagramwidget/qgldiagramwidget.h"
+
+#define GDS_DIR "gdsdata"
+
+enum level {LEVEL_ONE, LEVEL_TWO, LEVEL_THREE};
+
+// The internal structure of the db to store information about each node (each level)
+// this will be serialized before being written to file
+class dbDataStructure
+{
+public:
+    QString label;
+    quint32 depth;
+    quint32 userIndex;
+    QByteArray data;    // This is COMPRESSED data, optimize ram and disk space, is decompressed
+                        // just when needed (to display the comments)
+
+    // The following ID is used to create second-third level files
+    quint64 uniqueID;
+    // All the next items linked to this one
+    QVector<dbDataStructure*> nextItems;
+    // Corresponding indices vector (used to store data)
+    QVector<quint32> nextItemsIndices;
+    // The father element (or NULL if it's root)
+    dbDataStructure* father;
+    // Corresponding indices vector (used to store data)
+    quint32 fatherIndex;
+    bool noFatherRoot; // Used to tell if this node is the root (so hasn't a father)
+
+    // These fields will be useful for levels 2 and 3
+    QString fileName; // Relative filename for the associated code file
+    QByteArray firstLineData; // Compressed first line data, this will be used with the line number to retrieve info
+    QVector<quint32> linesNumbers; // First and next lines (next are relative to the first) numbers
+
+    // -- Generic system data not to be stored on disk
+    void *glPointer; // GL pointer
+
+    // These operator overrides prevent the glPointer and other non-disk-necessary data serialization
+    friend QDataStream& operator<<(QDataStream& stream, const dbDataStructure& myclass)
+    // Notice: this function has to be "friend" because it cannot be a member function, member functions
+    // have an additional parameter "this" which isn't in the argument list of an operator overload. A friend
+    // function has full access to private data of the class without having the "this" argument
+    {
+        // Don't write glPointer and every pointer-dependent structure
+        return stream << myclass.label << myclass.depth << myclass.userIndex << qCompress(myclass.data)
+                         << myclass.uniqueID << myclass.nextItemsIndices << myclass.fatherIndex << myclass.noFatherRoot
+                            << myclass.fileName << qCompress(myclass.firstLineData) << myclass.linesNumbers;
+    }
+    friend QDataStream& operator>>(QDataStream& stream, dbDataStructure& myclass)
+    {
+        //Don't read it, either
+        stream >> myclass.label >> myclass.depth >> myclass.userIndex >> myclass.data
+                      >> myclass.uniqueID >> myclass.nextItemsIndices >> myclass.fatherIndex >> myclass.noFatherRoot
+                         >> myclass.fileName >> myclass.firstLineData >> myclass.linesNumbers;
+        myclass.data = qUncompress(myclass.data);
+        myclass.firstLineData = qUncompress(myclass.firstLineData);
+        return stream;
+    }
+
+};
+
+#endif // GDSDBREADER_H

samples/C++/protocol-buffer.pb.cc

@@ -0,0 +1,327 @@
+// Generated by the protocol buffer compiler.  DO NOT EDIT!
+// source: protocol-buffer.proto
+
+#define INTERNAL_SUPPRESS_PROTOBUF_FIELD_DEPRECATION
+#include "protocol-buffer.pb.h"
+
+#include <algorithm>
+
+#include <google/protobuf/stubs/common.h>
+#include <google/protobuf/stubs/once.h>
+#include <google/protobuf/io/coded_stream.h>
+#include <google/protobuf/wire_format_lite_inl.h>
+#include <google/protobuf/descriptor.h>
+#include <google/protobuf/generated_message_reflection.h>
+#include <google/protobuf/reflection_ops.h>
+#include <google/protobuf/wire_format.h>
+// @@protoc_insertion_point(includes)
+
+namespace persons {
+
+namespace {
+
+const ::google::protobuf::Descriptor* Person_descriptor_ = NULL;
+const ::google::protobuf::internal::GeneratedMessageReflection*
+  Person_reflection_ = NULL;
+
+}  // namespace
+
+
+void protobuf_AssignDesc_protocol_2dbuffer_2eproto() {
+  protobuf_AddDesc_protocol_2dbuffer_2eproto();
+  const ::google::protobuf::FileDescriptor* file =
+    ::google::protobuf::DescriptorPool::generated_pool()->FindFileByName(
+      "protocol-buffer.proto");
+  GOOGLE_CHECK(file != NULL);
+  Person_descriptor_ = file->message_type(0);
+  static const int Person_offsets_[1] = {
+    GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(Person, name_),
+  };
+  Person_reflection_ =
+    new ::google::protobuf::internal::GeneratedMessageReflection(
+      Person_descriptor_,
+      Person::default_instance_,
+      Person_offsets_,
+      GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(Person, _has_bits_[0]),
+      GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(Person, _unknown_fields_),
+      -1,
+      ::google::protobuf::DescriptorPool::generated_pool(),
+      ::google::protobuf::MessageFactory::generated_factory(),
+      sizeof(Person));
+}
+
+namespace {
+
+GOOGLE_PROTOBUF_DECLARE_ONCE(protobuf_AssignDescriptors_once_);
+inline void protobuf_AssignDescriptorsOnce() {
+  ::google::protobuf::GoogleOnceInit(&protobuf_AssignDescriptors_once_,
+                 &protobuf_AssignDesc_protocol_2dbuffer_2eproto);
+}
+
+void protobuf_RegisterTypes(const ::std::string&) {
+  protobuf_AssignDescriptorsOnce();
+  ::google::protobuf::MessageFactory::InternalRegisterGeneratedMessage(
+    Person_descriptor_, &Person::default_instance());
+}
+
+}  // namespace
+
+void protobuf_ShutdownFile_protocol_2dbuffer_2eproto() {
+  delete Person::default_instance_;
+  delete Person_reflection_;
+}
+
+void protobuf_AddDesc_protocol_2dbuffer_2eproto() {
+  static bool already_here = false;
+  if (already_here) return;
+  already_here = true;
+  GOOGLE_PROTOBUF_VERIFY_VERSION;
+
+  ::google::protobuf::DescriptorPool::InternalAddGeneratedFile(
+    "\n\025protocol-buffer.proto\022\007persons\"\026\n\006Pers"
+    "on\022\014\n\004name\030\001 \002(\t", 56);
+  ::google::protobuf::MessageFactory::InternalRegisterGeneratedFile(
+    "protocol-buffer.proto", &protobuf_RegisterTypes);
+  Person::default_instance_ = new Person();
+  Person::default_instance_->InitAsDefaultInstance();
+  ::google::protobuf::internal::OnShutdown(&protobuf_ShutdownFile_protocol_2dbuffer_2eproto);
+}
+
+// Force AddDescriptors() to be called at static initialization time.
+struct StaticDescriptorInitializer_protocol_2dbuffer_2eproto {
+  StaticDescriptorInitializer_protocol_2dbuffer_2eproto() {
+    protobuf_AddDesc_protocol_2dbuffer_2eproto();
+  }
+} static_descriptor_initializer_protocol_2dbuffer_2eproto_;
+
+// ===================================================================
+
+#ifndef _MSC_VER
+const int Person::kNameFieldNumber;
+#endif  // !_MSC_VER
+
+Person::Person()
+  : ::google::protobuf::Message() {
+  SharedCtor();
+}
+
+void Person::InitAsDefaultInstance() {
+}
+
+Person::Person(const Person& from)
+  : ::google::protobuf::Message() {
+  SharedCtor();
+  MergeFrom(from);
+}
+
+void Person::SharedCtor() {
+  _cached_size_ = 0;
+  name_ = const_cast< ::std::string*>(&::google::protobuf::internal::kEmptyString);
+  ::memset(_has_bits_, 0, sizeof(_has_bits_));
+}
+
+Person::~Person() {
+  SharedDtor();
+}
+
+void Person::SharedDtor() {
+  if (name_ != &::google::protobuf::internal::kEmptyString) {
+    delete name_;
+  }
+  if (this != default_instance_) {
+  }
+}
+
+void Person::SetCachedSize(int size) const {
+  GOOGLE_SAFE_CONCURRENT_WRITES_BEGIN();
+  _cached_size_ = size;
+  GOOGLE_SAFE_CONCURRENT_WRITES_END();
+}
+const ::google::protobuf::Descriptor* Person::descriptor() {
+  protobuf_AssignDescriptorsOnce();
+  return Person_descriptor_;
+}
+
+const Person& Person::default_instance() {
+  if (default_instance_ == NULL) protobuf_AddDesc_protocol_2dbuffer_2eproto();
+  return *default_instance_;
+}
+
+Person* Person::default_instance_ = NULL;
+
+Person* Person::New() const {
+  return new Person;
+}
+
+void Person::Clear() {
+  if (_has_bits_[0 / 32] & (0xffu << (0 % 32))) {
+    if (has_name()) {
+      if (name_ != &::google::protobuf::internal::kEmptyString) {
+        name_->clear();
+      }
+    }
+  }
+  ::memset(_has_bits_, 0, sizeof(_has_bits_));
+  mutable_unknown_fields()->Clear();
+}
+
+bool Person::MergePartialFromCodedStream(
+    ::google::protobuf::io::CodedInputStream* input) {
+#define DO_(EXPRESSION) if (!(EXPRESSION)) return false
+  ::google::protobuf::uint32 tag;
+  while ((tag = input->ReadTag()) != 0) {
+    switch (::google::protobuf::internal::WireFormatLite::GetTagFieldNumber(tag)) {
+      // required string name = 1;
+      case 1: {
+        if (::google::protobuf::internal::WireFormatLite::GetTagWireType(tag) ==
+            ::google::protobuf::internal::WireFormatLite::WIRETYPE_LENGTH_DELIMITED) {
+          DO_(::google::protobuf::internal::WireFormatLite::ReadString(
+                input, this->mutable_name()));
+          ::google::protobuf::internal::WireFormat::VerifyUTF8String(
+            this->name().data(), this->name().length(),
+            ::google::protobuf::internal::WireFormat::PARSE);
+        } else {
+          goto handle_uninterpreted;
+        }
+        if (input->ExpectAtEnd()) return true;
+        break;
+      }
+
+      default: {
+      handle_uninterpreted:
+        if (::google::protobuf::internal::WireFormatLite::GetTagWireType(tag) ==
+            ::google::protobuf::internal::WireFormatLite::WIRETYPE_END_GROUP) {
+          return true;
+        }
+        DO_(::google::protobuf::internal::WireFormat::SkipField(
+              input, tag, mutable_unknown_fields()));
+        break;
+      }
+    }
+  }
+  return true;
+#undef DO_
+}
+
+void Person::SerializeWithCachedSizes(
+    ::google::protobuf::io::CodedOutputStream* output) const {
+  // required string name = 1;
+  if (has_name()) {
+    ::google::protobuf::internal::WireFormat::VerifyUTF8String(
+      this->name().data(), this->name().length(),
+      ::google::protobuf::internal::WireFormat::SERIALIZE);
+    ::google::protobuf::internal::WireFormatLite::WriteString(
+      1, this->name(), output);
+  }
+
+  if (!unknown_fields().empty()) {
+    ::google::protobuf::internal::WireFormat::SerializeUnknownFields(
+        unknown_fields(), output);
+  }
+}
+
+::google::protobuf::uint8* Person::SerializeWithCachedSizesToArray(
+    ::google::protobuf::uint8* target) const {
+  // required string name = 1;
+  if (has_name()) {
+    ::google::protobuf::internal::WireFormat::VerifyUTF8String(
+      this->name().data(), this->name().length(),
+      ::google::protobuf::internal::WireFormat::SERIALIZE);
+    target =
+      ::google::protobuf::internal::WireFormatLite::WriteStringToArray(
+        1, this->name(), target);
+  }
+
+  if (!unknown_fields().empty()) {
+    target = ::google::protobuf::internal::WireFormat::SerializeUnknownFieldsToArray(
+        unknown_fields(), target);
+  }
+  return target;
+}
+
+int Person::ByteSize() const {
+  int total_size = 0;
+
+  if (_has_bits_[0 / 32] & (0xffu << (0 % 32))) {
+    // required string name = 1;
+    if (has_name()) {
+      total_size += 1 +
+        ::google::protobuf::internal::WireFormatLite::StringSize(
+          this->name());
+    }
+
+  }
+  if (!unknown_fields().empty()) {
+    total_size +=
+      ::google::protobuf::internal::WireFormat::ComputeUnknownFieldsSize(
+        unknown_fields());
+  }
+  GOOGLE_SAFE_CONCURRENT_WRITES_BEGIN();
+  _cached_size_ = total_size;
+  GOOGLE_SAFE_CONCURRENT_WRITES_END();
+  return total_size;
+}
+
+void Person::MergeFrom(const ::google::protobuf::Message& from) {
+  GOOGLE_CHECK_NE(&from, this);
+  const Person* source =
+    ::google::protobuf::internal::dynamic_cast_if_available<const Person*>(
+      &from);
+  if (source == NULL) {
+    ::google::protobuf::internal::ReflectionOps::Merge(from, this);
+  } else {
+    MergeFrom(*source);
+  }
+}
+
+void Person::MergeFrom(const Person& from) {
+  GOOGLE_CHECK_NE(&from, this);
+  if (from._has_bits_[0 / 32] & (0xffu << (0 % 32))) {
+    if (from.has_name()) {
+      set_name(from.name());
+    }
+  }
+  mutable_unknown_fields()->MergeFrom(from.unknown_fields());
+}
+
+void Person::CopyFrom(const ::google::protobuf::Message& from) {
+  if (&from == this) return;
+  Clear();
+  MergeFrom(from);
+}
+
+void Person::CopyFrom(const Person& from) {
+  if (&from == this) return;
+  Clear();
+  MergeFrom(from);
+}
+
+bool Person::IsInitialized() const {
+  if ((_has_bits_[0] & 0x00000001) != 0x00000001) return false;
+
+  return true;
+}
+
+void Person::Swap(Person* other) {
+  if (other != this) {
+    std::swap(name_, other->name_);
+    std::swap(_has_bits_[0], other->_has_bits_[0]);
+    _unknown_fields_.Swap(&other->_unknown_fields_);
+    std::swap(_cached_size_, other->_cached_size_);
+  }
+}
+
+::google::protobuf::Metadata Person::GetMetadata() const {
+  protobuf_AssignDescriptorsOnce();
+  ::google::protobuf::Metadata metadata;
+  metadata.descriptor = Person_descriptor_;
+  metadata.reflection = Person_reflection_;
+  return metadata;
+}
+
+
+// @@protoc_insertion_point(namespace_scope)
+
+}  // namespace persons
+
+// @@protoc_insertion_point(global_scope)

samples/C++/protocol-buffer.pb.h

@@ -0,0 +1,218 @@
+// Generated by the protocol buffer compiler.  DO NOT EDIT!
+// source: protocol-buffer.proto
+
+#ifndef PROTOBUF_protocol_2dbuffer_2eproto__INCLUDED
+#define PROTOBUF_protocol_2dbuffer_2eproto__INCLUDED
+
+#include <string>
+
+#include <google/protobuf/stubs/common.h>
+
+#if GOOGLE_PROTOBUF_VERSION < 2005000
+#error This file was generated by a newer version of protoc which is
+#error incompatible with your Protocol Buffer headers.  Please update
+#error your headers.
+#endif
+#if 2005000 < GOOGLE_PROTOBUF_MIN_PROTOC_VERSION
+#error This file was generated by an older version of protoc which is
+#error incompatible with your Protocol Buffer headers.  Please
+#error regenerate this file with a newer version of protoc.
+#endif
+
+#include <google/protobuf/generated_message_util.h>
+#include <google/protobuf/message.h>
+#include <google/protobuf/repeated_field.h>
+#include <google/protobuf/extension_set.h>
+#include <google/protobuf/unknown_field_set.h>
+// @@protoc_insertion_point(includes)
+
+namespace persons {
+
+// Internal implementation detail -- do not call these.
+void  protobuf_AddDesc_protocol_2dbuffer_2eproto();
+void protobuf_AssignDesc_protocol_2dbuffer_2eproto();
+void protobuf_ShutdownFile_protocol_2dbuffer_2eproto();
+
+class Person;
+
+// ===================================================================
+
+class Person : public ::google::protobuf::Message {
+ public:
+  Person();
+  virtual ~Person();
+
+  Person(const Person& from);
+
+  inline Person& operator=(const Person& from) {
+    CopyFrom(from);
+    return *this;
+  }
+
+  inline const ::google::protobuf::UnknownFieldSet& unknown_fields() const {
+    return _unknown_fields_;
+  }
+
+  inline ::google::protobuf::UnknownFieldSet* mutable_unknown_fields() {
+    return &_unknown_fields_;
+  }
+
+  static const ::google::protobuf::Descriptor* descriptor();
+  static const Person& default_instance();
+
+  void Swap(Person* other);
+
+  // implements Message ----------------------------------------------
+
+  Person* New() const;
+  void CopyFrom(const ::google::protobuf::Message& from);
+  void MergeFrom(const ::google::protobuf::Message& from);
+  void CopyFrom(const Person& from);
+  void MergeFrom(const Person& from);
+  void Clear();
+  bool IsInitialized() const;
+
+  int ByteSize() const;
+  bool MergePartialFromCodedStream(
+      ::google::protobuf::io::CodedInputStream* input);
+  void SerializeWithCachedSizes(
+      ::google::protobuf::io::CodedOutputStream* output) const;
+  ::google::protobuf::uint8* SerializeWithCachedSizesToArray(::google::protobuf::uint8* output) const;
+  int GetCachedSize() const { return _cached_size_; }
+  private:
+  void SharedCtor();
+  void SharedDtor();
+  void SetCachedSize(int size) const;
+  public:
+
+  ::google::protobuf::Metadata GetMetadata() const;
+
+  // nested types ----------------------------------------------------
+
+  // accessors -------------------------------------------------------
+
+  // required string name = 1;
+  inline bool has_name() const;
+  inline void clear_name();
+  static const int kNameFieldNumber = 1;
+  inline const ::std::string& name() const;
+  inline void set_name(const ::std::string& value);
+  inline void set_name(const char* value);
+  inline void set_name(const char* value, size_t size);
+  inline ::std::string* mutable_name();
+  inline ::std::string* release_name();
+  inline void set_allocated_name(::std::string* name);
+
+  // @@protoc_insertion_point(class_scope:persons.Person)
+ private:
+  inline void set_has_name();
+  inline void clear_has_name();
+
+  ::google::protobuf::UnknownFieldSet _unknown_fields_;
+
+  ::std::string* name_;
+
+  mutable int _cached_size_;
+  ::google::protobuf::uint32 _has_bits_[(1 + 31) / 32];
+
+  friend void  protobuf_AddDesc_protocol_2dbuffer_2eproto();
+  friend void protobuf_AssignDesc_protocol_2dbuffer_2eproto();
+  friend void protobuf_ShutdownFile_protocol_2dbuffer_2eproto();
+
+  void InitAsDefaultInstance();
+  static Person* default_instance_;
+};
+// ===================================================================
+
+
+// ===================================================================
+
+// Person
+
+// required string name = 1;
+inline bool Person::has_name() const {
+  return (_has_bits_[0] & 0x00000001u) != 0;
+}
+inline void Person::set_has_name() {
+  _has_bits_[0] |= 0x00000001u;
+}
+inline void Person::clear_has_name() {
+  _has_bits_[0] &= ~0x00000001u;
+}
+inline void Person::clear_name() {
+  if (name_ != &::google::protobuf::internal::kEmptyString) {
+    name_->clear();
+  }
+  clear_has_name();
+}
+inline const ::std::string& Person::name() const {
+  return *name_;
+}
+inline void Person::set_name(const ::std::string& value) {
+  set_has_name();
+  if (name_ == &::google::protobuf::internal::kEmptyString) {
+    name_ = new ::std::string;
+  }
+  name_->assign(value);
+}
+inline void Person::set_name(const char* value) {
+  set_has_name();
+  if (name_ == &::google::protobuf::internal::kEmptyString) {
+    name_ = new ::std::string;
+  }
+  name_->assign(value);
+}
+inline void Person::set_name(const char* value, size_t size) {
+  set_has_name();
+  if (name_ == &::google::protobuf::internal::kEmptyString) {
+    name_ = new ::std::string;
+  }
+  name_->assign(reinterpret_cast<const char*>(value), size);
+}
+inline ::std::string* Person::mutable_name() {
+  set_has_name();
+  if (name_ == &::google::protobuf::internal::kEmptyString) {
+    name_ = new ::std::string;
+  }
+  return name_;
+}
+inline ::std::string* Person::release_name() {
+  clear_has_name();
+  if (name_ == &::google::protobuf::internal::kEmptyString) {
+    return NULL;
+  } else {
+    ::std::string* temp = name_;
+    name_ = const_cast< ::std::string*>(&::google::protobuf::internal::kEmptyString);
+    return temp;
+  }
+}
+inline void Person::set_allocated_name(::std::string* name) {
+  if (name_ != &::google::protobuf::internal::kEmptyString) {
+    delete name_;
+  }
+  if (name) {
+    set_has_name();
+    name_ = name;
+  } else {
+    clear_has_name();
+    name_ = const_cast< ::std::string*>(&::google::protobuf::internal::kEmptyString);
+  }
+}
+
+
+// @@protoc_insertion_point(namespace_scope)
+
+}  // namespace persons
+
+#ifndef SWIG
+namespace google {
+namespace protobuf {
+
+
+}  // namespace google
+}  // namespace protobuf
+#endif  // SWIG
+
+// @@protoc_insertion_point(global_scope)
+
+#endif  // PROTOBUF_protocol_2dbuffer_2eproto__INCLUDED

samples/C++/qscicommand.h

@@ -0,0 +1,415 @@
+// This defines the interface to the QsciCommand class.
+//
+// Copyright (c) 2011 Riverbank Computing Limited <info@riverbankcomputing.com>
+// 
+// This file is part of QScintilla.
+// 
+// This file may be used under the terms of the GNU General Public
+// License versions 2.0 or 3.0 as published by the Free Software
+// Foundation and appearing in the files LICENSE.GPL2 and LICENSE.GPL3
+// included in the packaging of this file.  Alternatively you may (at
+// your option) use any later version of the GNU General Public
+// License if such license has been publicly approved by Riverbank
+// Computing Limited (or its successors, if any) and the KDE Free Qt
+// Foundation. In addition, as a special exception, Riverbank gives you
+// certain additional rights. These rights are described in the Riverbank
+// GPL Exception version 1.1, which can be found in the file
+// GPL_EXCEPTION.txt in this package.
+// 
+// If you are unsure which license is appropriate for your use, please
+// contact the sales department at sales@riverbankcomputing.com.
+// 
+// This file is provided AS IS with NO WARRANTY OF ANY KIND, INCLUDING THE
+// WARRANTY OF DESIGN, MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+
+
+#ifndef QSCICOMMAND_H
+#define QSCICOMMAND_H
+
+#ifdef __APPLE__
+extern "C++" {
+#endif
+
+#include <qstring.h>
+
+#include <Qsci/qsciglobal.h>
+#include <Qsci/qsciscintillabase.h>
+
+
+class QsciScintilla;
+
+
+//! \brief The QsciCommand class represents an internal editor command that may
+//! have one or two keys bound to it.
+//!
+//! Methods are provided to change the keys bound to the command and to remove
+//! a key binding.  Each command has a user friendly description of the command
+//! for use in key mapping dialogs.
+class QSCINTILLA_EXPORT QsciCommand
+{
+public:
+    //! This enum defines the different commands that can be assigned to a key.
+    enum Command {
+        //! Move down one line.
+        LineDown = QsciScintillaBase::SCI_LINEDOWN,
+
+        //! Extend the selection down one line.
+        LineDownExtend = QsciScintillaBase::SCI_LINEDOWNEXTEND,
+
+        //! Extend the rectangular selection down one line.
+        LineDownRectExtend = QsciScintillaBase::SCI_LINEDOWNRECTEXTEND,
+
+        //! Scroll the view down one line.
+        LineScrollDown = QsciScintillaBase::SCI_LINESCROLLDOWN,
+
+        //! Move up one line.
+        LineUp = QsciScintillaBase::SCI_LINEUP,
+
+        //! Extend the selection up one line.
+        LineUpExtend = QsciScintillaBase::SCI_LINEUPEXTEND,
+
+        //! Extend the rectangular selection up one line.
+        LineUpRectExtend = QsciScintillaBase::SCI_LINEUPRECTEXTEND,
+
+        //! Scroll the view up one line.
+        LineScrollUp = QsciScintillaBase::SCI_LINESCROLLUP,
+
+        //! Scroll to the start of the document.
+        ScrollToStart = QsciScintillaBase::SCI_SCROLLTOSTART,
+
+        //! Scroll to the end of the document.
+        ScrollToEnd = QsciScintillaBase::SCI_SCROLLTOEND,
+
+        //! Scroll vertically to centre the current line.
+        VerticalCentreCaret = QsciScintillaBase::SCI_VERTICALCENTRECARET,
+
+        //! Move down one paragraph.
+        ParaDown = QsciScintillaBase::SCI_PARADOWN,
+
+        //! Extend the selection down one paragraph.
+        ParaDownExtend = QsciScintillaBase::SCI_PARADOWNEXTEND,
+
+        //! Move up one paragraph.
+        ParaUp = QsciScintillaBase::SCI_PARAUP,
+
+        //! Extend the selection up one paragraph.
+        ParaUpExtend = QsciScintillaBase::SCI_PARAUPEXTEND,
+
+        //! Move left one character.
+        CharLeft = QsciScintillaBase::SCI_CHARLEFT,
+
+        //! Extend the selection left one character.
+        CharLeftExtend = QsciScintillaBase::SCI_CHARLEFTEXTEND,
+
+        //! Extend the rectangular selection left one character.
+        CharLeftRectExtend = QsciScintillaBase::SCI_CHARLEFTRECTEXTEND,
+
+        //! Move right one character.
+        CharRight = QsciScintillaBase::SCI_CHARRIGHT,
+
+        //! Extend the selection right one character.
+        CharRightExtend = QsciScintillaBase::SCI_CHARRIGHTEXTEND,
+
+        //! Extend the rectangular selection right one character.
+        CharRightRectExtend = QsciScintillaBase::SCI_CHARRIGHTRECTEXTEND,
+
+        //! Move left one word.
+        WordLeft = QsciScintillaBase::SCI_WORDLEFT,
+
+        //! Extend the selection left one word.
+        WordLeftExtend = QsciScintillaBase::SCI_WORDLEFTEXTEND,
+
+        //! Move right one word.
+        WordRight = QsciScintillaBase::SCI_WORDRIGHT,
+
+        //! Extend the selection right one word.
+        WordRightExtend = QsciScintillaBase::SCI_WORDRIGHTEXTEND,
+
+        //! Move to the end of the previous word.
+        WordLeftEnd = QsciScintillaBase::SCI_WORDLEFTEND,
+
+        //! Extend the selection to the end of the previous word.
+        WordLeftEndExtend = QsciScintillaBase::SCI_WORDLEFTENDEXTEND,
+
+        //! Move to the end of the next word.
+        WordRightEnd = QsciScintillaBase::SCI_WORDRIGHTEND,
+
+        //! Extend the selection to the end of the next word.
+        WordRightEndExtend = QsciScintillaBase::SCI_WORDRIGHTENDEXTEND,
+
+        //! Move left one word part.
+        WordPartLeft = QsciScintillaBase::SCI_WORDPARTLEFT,
+
+        //! Extend the selection left one word part.
+        WordPartLeftExtend = QsciScintillaBase::SCI_WORDPARTLEFTEXTEND,
+
+        //! Move right one word part.
+        WordPartRight = QsciScintillaBase::SCI_WORDPARTRIGHT,
+
+        //! Extend the selection right one word part.
+        WordPartRightExtend = QsciScintillaBase::SCI_WORDPARTRIGHTEXTEND,
+
+        //! Move to the start of the document line.
+        Home = QsciScintillaBase::SCI_HOME,
+
+        //! Extend the selection to the start of the document line.
+        HomeExtend = QsciScintillaBase::SCI_HOMEEXTEND,
+
+        //! Extend the rectangular selection to the start of the document line.
+        HomeRectExtend = QsciScintillaBase::SCI_HOMERECTEXTEND,
+
+        //! Move to the start of the displayed line.
+        HomeDisplay = QsciScintillaBase::SCI_HOMEDISPLAY,
+
+        //! Extend the selection to the start of the displayed line.
+        HomeDisplayExtend = QsciScintillaBase::SCI_HOMEDISPLAYEXTEND,
+
+        //! Move to the start of the displayed or document line.
+        HomeWrap = QsciScintillaBase::SCI_HOMEWRAP,
+
+        //! Extend the selection to the start of the displayed or document
+        //! line.
+        HomeWrapExtend = QsciScintillaBase::SCI_HOMEWRAPEXTEND,
+
+        //! Move to the first visible character in the document line.
+        VCHome = QsciScintillaBase::SCI_VCHOME,
+
+        //! Extend the selection to the first visible character in the document
+        //! line.
+        VCHomeExtend = QsciScintillaBase::SCI_VCHOMEEXTEND,
+
+        //! Extend the rectangular selection to the first visible character in
+        //! the document line.
+        VCHomeRectExtend = QsciScintillaBase::SCI_VCHOMERECTEXTEND,
+
+        //! Move to the first visible character of the displayed or document
+        //! line.
+        VCHomeWrap = QsciScintillaBase::SCI_VCHOMEWRAP,
+
+        //! Extend the selection to the first visible character of the
+        //! displayed or document line.
+        VCHomeWrapExtend = QsciScintillaBase::SCI_VCHOMEWRAPEXTEND,
+
+        //! Move to the end of the document line.
+        LineEnd = QsciScintillaBase::SCI_LINEEND,
+
+        //! Extend the selection to the end of the document line.
+        LineEndExtend = QsciScintillaBase::SCI_LINEENDEXTEND,
+
+        //! Extend the rectangular selection to the end of the document line.
+        LineEndRectExtend = QsciScintillaBase::SCI_LINEENDRECTEXTEND,
+
+        //! Move to the end of the displayed line.
+        LineEndDisplay = QsciScintillaBase::SCI_LINEENDDISPLAY,
+
+        //! Extend the selection to the end of the displayed line.
+        LineEndDisplayExtend = QsciScintillaBase::SCI_LINEENDDISPLAYEXTEND,
+
+        //! Move to the end of the displayed or document line.
+        LineEndWrap = QsciScintillaBase::SCI_LINEENDWRAP,
+
+        //! Extend the selection to the end of the displayed or document line.
+        LineEndWrapExtend = QsciScintillaBase::SCI_LINEENDWRAPEXTEND,
+
+        //! Move to the start of the document.
+        DocumentStart = QsciScintillaBase::SCI_DOCUMENTSTART,
+
+        //! Extend the selection to the start of the document.
+        DocumentStartExtend = QsciScintillaBase::SCI_DOCUMENTSTARTEXTEND,
+
+        //! Move to the end of the document.
+        DocumentEnd = QsciScintillaBase::SCI_DOCUMENTEND,
+
+        //! Extend the selection to the end of the document.
+        DocumentEndExtend = QsciScintillaBase::SCI_DOCUMENTENDEXTEND,
+
+        //! Move up one page.
+        PageUp = QsciScintillaBase::SCI_PAGEUP,
+
+        //! Extend the selection up one page.
+        PageUpExtend = QsciScintillaBase::SCI_PAGEUPEXTEND,
+
+        //! Extend the rectangular selection up one page.
+        PageUpRectExtend = QsciScintillaBase::SCI_PAGEUPRECTEXTEND,
+
+        //! Move down one page.
+        PageDown = QsciScintillaBase::SCI_PAGEDOWN,
+
+        //! Extend the selection down one page.
+        PageDownExtend = QsciScintillaBase::SCI_PAGEDOWNEXTEND,
+
+        //! Extend the rectangular selection down one page.
+        PageDownRectExtend = QsciScintillaBase::SCI_PAGEDOWNRECTEXTEND,
+
+        //! Stuttered move up one page.
+        StutteredPageUp = QsciScintillaBase::SCI_STUTTEREDPAGEUP,
+
+        //! Stuttered extend the selection up one page.
+        StutteredPageUpExtend = QsciScintillaBase::SCI_STUTTEREDPAGEUPEXTEND,
+
+        //! Stuttered move down one page.
+        StutteredPageDown = QsciScintillaBase::SCI_STUTTEREDPAGEDOWN,
+
+        //! Stuttered extend the selection down one page.
+        StutteredPageDownExtend = QsciScintillaBase::SCI_STUTTEREDPAGEDOWNEXTEND,
+
+        //! Delete the current character.
+        Delete = QsciScintillaBase::SCI_CLEAR,
+
+        //! Delete the previous character.
+        DeleteBack = QsciScintillaBase::SCI_DELETEBACK,
+
+        //! Delete the previous character if not at start of line.
+        DeleteBackNotLine = QsciScintillaBase::SCI_DELETEBACKNOTLINE,
+
+        //! Delete the word to the left.
+        DeleteWordLeft = QsciScintillaBase::SCI_DELWORDLEFT,
+
+        //! Delete the word to the right.
+        DeleteWordRight = QsciScintillaBase::SCI_DELWORDRIGHT,
+
+        //! Delete right to the end of the next word.
+        DeleteWordRightEnd = QsciScintillaBase::SCI_DELWORDRIGHTEND,
+
+        //! Delete the line to the left.
+        DeleteLineLeft = QsciScintillaBase::SCI_DELLINELEFT,
+
+        //! Delete the line to the right.
+        DeleteLineRight = QsciScintillaBase::SCI_DELLINERIGHT,
+
+        //! Delete the current line.
+        LineDelete = QsciScintillaBase::SCI_LINEDELETE,
+
+        //! Cut the current line to the clipboard.
+        LineCut = QsciScintillaBase::SCI_LINECUT,
+
+        //! Copy the current line to the clipboard.
+        LineCopy = QsciScintillaBase::SCI_LINECOPY,
+
+        //! Transpose the current and previous lines.
+        LineTranspose = QsciScintillaBase::SCI_LINETRANSPOSE,
+
+        //! Duplicate the current line.
+        LineDuplicate = QsciScintillaBase::SCI_LINEDUPLICATE,
+
+        //! Select the whole document.
+        SelectAll = QsciScintillaBase::SCI_SELECTALL,
+
+        //! Move the selected lines up one line.
+        MoveSelectedLinesUp = QsciScintillaBase::SCI_MOVESELECTEDLINESUP,
+
+        //! Move the selected lines down one line.
+        MoveSelectedLinesDown = QsciScintillaBase::SCI_MOVESELECTEDLINESDOWN,
+
+        //! Duplicate the selection.
+        SelectionDuplicate = QsciScintillaBase::SCI_SELECTIONDUPLICATE,
+
+        //! Convert the selection to lower case.
+        SelectionLowerCase = QsciScintillaBase::SCI_LOWERCASE,
+
+        //! Convert the selection to upper case.
+        SelectionUpperCase = QsciScintillaBase::SCI_UPPERCASE,
+
+        //! Cut the selection to the clipboard.
+        SelectionCut = QsciScintillaBase::SCI_CUT,
+
+        //! Copy the selection to the clipboard.
+        SelectionCopy = QsciScintillaBase::SCI_COPY,
+
+        //! Paste from the clipboard.
+        Paste = QsciScintillaBase::SCI_PASTE,
+
+        //! Toggle insert/overtype.
+        EditToggleOvertype = QsciScintillaBase::SCI_EDITTOGGLEOVERTYPE,
+
+        //! Insert a platform dependent newline.
+        Newline = QsciScintillaBase::SCI_NEWLINE,
+
+        //! Insert a formfeed.
+        Formfeed = QsciScintillaBase::SCI_FORMFEED,
+
+        //! Indent one level.
+        Tab = QsciScintillaBase::SCI_TAB,
+
+        //! De-indent one level.
+        Backtab = QsciScintillaBase::SCI_BACKTAB,
+
+        //! Cancel any current operation.
+        Cancel = QsciScintillaBase::SCI_CANCEL,
+
+        //! Undo the last command.
+        Undo = QsciScintillaBase::SCI_UNDO,
+
+        //! Redo the last command.
+        Redo = QsciScintillaBase::SCI_REDO,
+
+        //! Zoom in.
+        ZoomIn = QsciScintillaBase::SCI_ZOOMIN,
+
+        //! Zoom out.
+        ZoomOut = QsciScintillaBase::SCI_ZOOMOUT,
+    };
+
+    //! Return the command that will be executed by this instance.
+    Command command() const {return scicmd;}
+
+    //! Execute the command.
+    void execute();
+
+    //! Binds the key \a key to the command.  If \a key is 0 then the key
+    //! binding is removed.  If \a key is invalid then the key binding is
+    //! unchanged.  Valid keys are any visible or control character or any
+    //! of \c Key_Down, \c Key_Up, \c Key_Left, \c Key_Right, \c Key_Home,
+    //! \c Key_End, \c Key_PageUp, \c Key_PageDown, \c Key_Delete,
+    //! \c Key_Insert, \c Key_Escape, \c Key_Backspace, \c Key_Tab and
+    //! \c Key_Return.  Keys may be modified with any combination of \c SHIFT,
+    //! \c CTRL, \c ALT and \c META.
+    //!
+    //! \sa key(), setAlternateKey(), validKey()
+    void setKey(int key);
+
+    //! Binds the alternate key \a altkey to the command.  If \a key is 0
+    //! then the alternate key binding is removed.
+    //!
+    //! \sa alternateKey(), setKey(), validKey()
+    void setAlternateKey(int altkey);
+
+    //! The key that is currently bound to the command is returned.
+    //!
+    //! \sa setKey(), alternateKey()
+    int key() const {return qkey;}
+
+    //! The alternate key that is currently bound to the command is
+    //! returned.
+    //!
+    //! \sa setAlternateKey(), key()
+    int alternateKey() const {return qaltkey;}
+
+    //! If the key \a key is valid then true is returned.
+    static bool validKey(int key);
+
+    //! The user friendly description of the command is returned.
+    QString description() const;
+
+private:
+    friend class QsciCommandSet;
+
+    QsciCommand(QsciScintilla *qs, Command cmd, int key, int altkey,
+            const char *desc);
+
+    void bindKey(int key,int &qk,int &scik);
+
+    QsciScintilla *qsCmd;
+    Command scicmd;
+    int qkey, scikey, qaltkey, scialtkey;
+    const char *descCmd;
+
+    QsciCommand(const QsciCommand &);
+    QsciCommand &operator=(const QsciCommand &);
+};
+
+#ifdef __APPLE__
+}
+#endif
+
+#endif

samples/C++/qsciprinter.h

@@ -0,0 +1,116 @@
+// This module defines interface to the QsciPrinter class.
+//
+// Copyright (c) 2011 Riverbank Computing Limited <info@riverbankcomputing.com>
+// 
+// This file is part of QScintilla.
+// 
+// This file may be used under the terms of the GNU General Public
+// License versions 2.0 or 3.0 as published by the Free Software
+// Foundation and appearing in the files LICENSE.GPL2 and LICENSE.GPL3
+// included in the packaging of this file.  Alternatively you may (at
+// your option) use any later version of the GNU General Public
+// License if such license has been publicly approved by Riverbank
+// Computing Limited (or its successors, if any) and the KDE Free Qt
+// Foundation. In addition, as a special exception, Riverbank gives you
+// certain additional rights. These rights are described in the Riverbank
+// GPL Exception version 1.1, which can be found in the file
+// GPL_EXCEPTION.txt in this package.
+// 
+// If you are unsure which license is appropriate for your use, please
+// contact the sales department at sales@riverbankcomputing.com.
+// 
+// This file is provided AS IS with NO WARRANTY OF ANY KIND, INCLUDING THE
+// WARRANTY OF DESIGN, MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+
+
+#ifndef QSCIPRINTER_H
+#define QSCIPRINTER_H
+
+#ifdef __APPLE__
+extern "C++" {
+#endif
+
+#include <qprinter.h>
+
+#include <Qsci/qsciglobal.h>
+#include <Qsci/qsciscintilla.h>
+
+
+QT_BEGIN_NAMESPACE
+class QRect;
+class QPainter;
+QT_END_NAMESPACE
+
+class QsciScintillaBase;
+
+
+//! \brief The QsciPrinter class is a sub-class of the Qt QPrinter class that
+//! is able to print the text of a Scintilla document.
+//!
+//! The class can be further sub-classed to alter to layout of the text, adding
+//! headers and footers for example.
+class QSCINTILLA_EXPORT QsciPrinter : public QPrinter
+{
+public:
+    //! Constructs a printer paint device with mode \a mode.
+    QsciPrinter(PrinterMode mode = ScreenResolution);
+
+    //! Destroys the QsciPrinter instance.
+    virtual ~QsciPrinter();
+
+    //! Format a page, by adding headers and footers for example, before the
+    //! document text is drawn on it.  \a painter is the painter to be used to
+    //! add customised text and graphics.  \a drawing is true if the page is
+    //! actually being drawn rather than being sized.  \a painter drawing
+    //! methods must only be called when \a drawing is true.  \a area is the
+    //! area of the page that will be used to draw the text.  This should be
+    //! modified if it is necessary to reserve space for any customised text or
+    //! graphics.  By default the area is relative to the printable area of the
+    //! page.  Use QPrinter::setFullPage() because calling printRange() if you
+    //! want to try and print over the whole page.  \a pagenr is the number of
+    //! the page.  The first page is numbered 1.
+    virtual void formatPage(QPainter &painter, bool drawing, QRect &area,
+            int pagenr);
+
+    //! Return the number of points to add to each font when printing.
+    //!
+    //! \sa setMagnification()
+    int magnification() const {return mag;}
+
+    //! Sets the number of points to add to each font when printing to \a
+    //! magnification.
+    //!
+    //! \sa magnification()
+    virtual void setMagnification(int magnification);
+
+    //! Print a range of lines from the Scintilla instance \a qsb.  \a from is
+    //! the first line to print and a negative value signifies the first line
+    //! of text.  \a to is the last line to print and a negative value
+    //! signifies the last line of text.  true is returned if there was no
+    //! error.
+    virtual int printRange(QsciScintillaBase *qsb, int from = -1, int to = -1);
+
+    //! Return the line wrap mode used when printing.  The default is
+    //! QsciScintilla::WrapWord.
+    //!
+    //! \sa setWrapMode()
+    QsciScintilla::WrapMode wrapMode() const {return wrap;}
+
+    //! Sets the line wrap mode used when printing to \a wmode.
+    //!
+    //! \sa wrapMode()
+    virtual void setWrapMode(QsciScintilla::WrapMode wmode);
+
+private:
+    int mag;
+    QsciScintilla::WrapMode wrap;
+
+    QsciPrinter(const QsciPrinter &);
+    QsciPrinter &operator=(const QsciPrinter &);
+};
+
+#ifdef __APPLE__
+}
+#endif
+
+#endif