add a puppet sample with includes-only since they are often misclassified as pascal

* Revert "Switch the PHP grammar to the upstream repo (#3575)"

Manually reverting this as it breaks PHP syntax highlighting on
github.com.

* Update submodule ref

.gitignore

@@ -1,3 +1,4 @@
+*.gem
 /Gemfile.lock
 .bundle/
 .idea

.gitmodules

@@ -67,9 +67,6 @@
 [submodule "vendor/grammars/language-javascript"]
 	path = vendor/grammars/language-javascript
 	url = https://github.com/atom/language-javascript
-[submodule "vendor/grammars/language-python"]
-	path = vendor/grammars/language-python
-	url = https://github.com/atom/language-python
 [submodule "vendor/grammars/language-shellscript"]
 	path = vendor/grammars/language-shellscript
 	url = https://github.com/atom/language-shellscript
@@ -130,9 +127,6 @@
 [submodule "vendor/grammars/Sublime-Text-2-OpenEdge-ABL"]
 	path = vendor/grammars/Sublime-Text-2-OpenEdge-ABL
 	url = https://github.com/jfairbank/Sublime-Text-2-OpenEdge-ABL
-[submodule "vendor/grammars/sublime-rust"]
-	path = vendor/grammars/sublime-rust
-	url = https://github.com/jhasse/sublime-rust
 [submodule "vendor/grammars/sublime-befunge"]
 	path = vendor/grammars/sublime-befunge
 	url = https://github.com/johanasplund/sublime-befunge
@@ -180,7 +174,7 @@
 	url = https://github.com/mokus0/Agda.tmbundle
 [submodule "vendor/grammars/Julia.tmbundle"]
 	path = vendor/grammars/Julia.tmbundle
-	url = https://github.com/nanoant/Julia.tmbundle
+	url = https://github.com/JuliaEditorSupport/Julia.tmbundle
 [submodule "vendor/grammars/ooc.tmbundle"]
 	path = vendor/grammars/ooc.tmbundle
 	url = https://github.com/nilium/ooc.tmbundle
@@ -247,9 +241,6 @@
 [submodule "vendor/grammars/cpp-qt.tmbundle"]
 	path = vendor/grammars/cpp-qt.tmbundle
 	url = https://github.com/textmate/cpp-qt.tmbundle
-[submodule "vendor/grammars/css.tmbundle"]
-	path = vendor/grammars/css.tmbundle
-	url = https://github.com/textmate/css.tmbundle
 [submodule "vendor/grammars/d.tmbundle"]
 	path = vendor/grammars/d.tmbundle
 	url = https://github.com/textmate/d.tmbundle
@@ -325,9 +316,6 @@
 [submodule "vendor/grammars/nemerle.tmbundle"]
 	path = vendor/grammars/nemerle.tmbundle
 	url = https://github.com/textmate/nemerle.tmbundle
-[submodule "vendor/grammars/ninja.tmbundle"]
-	path = vendor/grammars/ninja.tmbundle
-	url = https://github.com/textmate/ninja.tmbundle
 [submodule "vendor/grammars/objective-c.tmbundle"]
 	path = vendor/grammars/objective-c.tmbundle
 	url = https://github.com/textmate/objective-c.tmbundle
@@ -342,7 +330,7 @@
 	url = https://github.com/textmate/php-smarty.tmbundle
 [submodule "vendor/grammars/php.tmbundle"]
 	path = vendor/grammars/php.tmbundle
-	url = https://github.com/textmate/php.tmbundle
+	url = https://github.com/brandonblack/php.tmbundle
 [submodule "vendor/grammars/postscript.tmbundle"]
 	path = vendor/grammars/postscript.tmbundle
 	url = https://github.com/textmate/postscript.tmbundle
@@ -355,9 +343,6 @@
 [submodule "vendor/grammars/r.tmbundle"]
 	path = vendor/grammars/r.tmbundle
 	url = https://github.com/textmate/r.tmbundle
-[submodule "vendor/grammars/ruby-haml.tmbundle"]
-	path = vendor/grammars/ruby-haml.tmbundle
-	url = https://github.com/textmate/ruby-haml.tmbundle
 [submodule "vendor/grammars/scheme.tmbundle"]
 	path = vendor/grammars/scheme.tmbundle
 	url = https://github.com/textmate/scheme.tmbundle
@@ -449,9 +434,6 @@
 [submodule "vendor/grammars/Sublime-Nit"]
 	path = vendor/grammars/Sublime-Nit
 	url = https://github.com/R4PaSs/Sublime-Nit
-[submodule "vendor/grammars/language-hy"]
-	path = vendor/grammars/language-hy
-	url = https://github.com/rwtolbert/language-hy
 [submodule "vendor/grammars/Racket"]
 	path = vendor/grammars/Racket
 	url = https://github.com/soegaard/racket-highlight-for-github
@@ -629,9 +611,6 @@
 [submodule "vendor/grammars/language-yang"]
 	path = vendor/grammars/language-yang
 	url = https://github.com/DzonyKalafut/language-yang.git
-[submodule "vendor/grammars/perl6fe"]
-	path = vendor/grammars/perl6fe
-	url = https://github.com/MadcapJake/language-perl6fe.git
 [submodule "vendor/grammars/language-less"]
 	path = vendor/grammars/language-less
 	url = https://github.com/atom/language-less.git
@@ -776,9 +755,6 @@
 [submodule "vendor/grammars/vhdl"]
 	path = vendor/grammars/vhdl
 	url = https://github.com/textmate/vhdl.tmbundle
-[submodule "vendor/grammars/xquery"]
-	path = vendor/grammars/xquery
-	url = https://github.com/textmate/xquery.tmbundle
 [submodule "vendor/grammars/language-rpm-spec"]
 	path = vendor/grammars/language-rpm-spec
 	url = https://github.com/waveclaw/language-rpm-spec
@@ -803,3 +779,63 @@
 [submodule "vendor/grammars/EBNF.tmbundle"]
 	path = vendor/grammars/EBNF.tmbundle
 	url = https://github.com/sanssecours/EBNF.tmbundle
+[submodule "vendor/grammars/language-haml"]
+	path = vendor/grammars/language-haml
+	url = https://github.com/ezekg/language-haml
+[submodule "vendor/grammars/language-ninja"]
+	path = vendor/grammars/language-ninja
+	url = https://github.com/khyo/language-ninja
+[submodule "vendor/grammars/language-fontforge"]
+	path = vendor/grammars/language-fontforge
+	url = https://github.com/Alhadis/language-fontforge
+[submodule "vendor/grammars/language-gn"]
+	path = vendor/grammars/language-gn
+	url = https://github.com/devoncarew/language-gn
+[submodule "vendor/grammars/rascal-syntax-highlighting"]
+	path = vendor/grammars/rascal-syntax-highlighting
+	url = https://github.com/usethesource/rascal-syntax-highlighting
+[submodule "vendor/grammars/atom-language-perl6"]
+	path = vendor/grammars/atom-language-perl6
+	url = https://github.com/perl6/atom-language-perl6
+[submodule "vendor/grammars/reason"]
+	path = vendor/grammars/reason
+	url = https://github.com/facebook/reason
+[submodule "vendor/grammars/language-xcompose"]
+	path = vendor/grammars/language-xcompose
+	url = https://github.com/samcv/language-xcompose
+[submodule "vendor/grammars/SublimeEthereum"]
+	path = vendor/grammars/SublimeEthereum
+	url = https://github.com/davidhq/SublimeEthereum.git
+[submodule "vendor/grammars/atom-language-rust"]
+	path = vendor/grammars/atom-language-rust
+	url = https://github.com/zargony/atom-language-rust
+[submodule "vendor/grammars/language-css"]
+	path = vendor/grammars/language-css
+	url = https://github.com/atom/language-css
+[submodule "vendor/grammars/language-regexp"]
+	path = vendor/grammars/language-regexp
+	url = https://github.com/Alhadis/language-regexp
+[submodule "vendor/grammars/Terraform.tmLanguage"]
+	path = vendor/grammars/Terraform.tmLanguage
+	url = https://github.com/alexlouden/Terraform.tmLanguage
+[submodule "vendor/grammars/shaders-tmLanguage"]
+	path = vendor/grammars/shaders-tmLanguage
+	url = https://github.com/tgjones/shaders-tmLanguage
+[submodule "vendor/grammars/language-meson"]
+	path = vendor/grammars/language-meson
+	url = https://github.com/TingPing/language-meson
+[submodule "vendor/grammars/atom-language-p4"]
+	path = vendor/grammars/atom-language-p4
+	url = https://github.com/TakeshiTseng/atom-language-p4
+[submodule "vendor/grammars/language-jison"]
+	path = vendor/grammars/language-jison
+	url = https://github.com/cdibbs/language-jison
+[submodule "vendor/grammars/openscad.tmbundle"]
+	path = vendor/grammars/openscad.tmbundle
+	url = https://github.com/tbuser/openscad.tmbundle
+[submodule "vendor/grammars/marko-tmbundle"]
+	path = vendor/grammars/marko-tmbundle
+	url = https://github.com/marko-js/marko-tmbundle
+[submodule "vendor/grammars/language-jolie"]
+	path = vendor/grammars/language-jolie
+	url = https://github.com/fmontesi/language-jolie

.travis.yml

@@ -1,20 +1,33 @@
 language: ruby
 sudo: false
+
 addons:
   apt:
     packages:
     - libicu-dev
     - libicu48
+
 before_install: script/travis/before_install
+
 script:
   - bundle exec rake
   - script/licensed verify
+
 rvm:
-  - 2.0.0
   - 2.1
   - 2.2
+  - 2.3.3
+  - 2.4.0
+
+matrix:
+  allow_failures:
+  - rvm: 2.4.0
+
 notifications:
   disabled: true
+
 git:
   submodules: false
+  depth: 3
+
 cache: bundler

CONTRIBUTING.md

@@ -10,15 +10,15 @@ We try only to add new extensions once they have some usage on GitHub. In most c
 
 To add support for a new extension:
 
-0. Add your extension to the language entry in [`languages.yml`][languages], keeping the extensions in alphabetical order.
-0. Add at least one sample for your extension to the [samples directory][samples] in the correct subdirectory.
-0. Open a pull request, linking to a [GitHub search result](https://github.com/search?utf8=%E2%9C%93&q=extension%3Aboot+NOT+nothack&type=Code&ref=searchresults) showing in-the-wild usage.
+1. Add your extension to the language entry in [`languages.yml`][languages], keeping the extensions in alphabetical order.
+1. Add at least one sample for your extension to the [samples directory][samples] in the correct subdirectory.
+1. Open a pull request, linking to a [GitHub search result](https://github.com/search?utf8=%E2%9C%93&q=extension%3Aboot+NOT+nothack&type=Code&ref=searchresults) showing in-the-wild usage.
 
 In addition, if this extension is already listed in [`languages.yml`][languages] then sometimes a few more steps will need to be taken:
 
-0. Make sure that example `.yourextension` files are present in the [samples directory][samples] for each language that uses `.yourextension`.
-0. Test the performance of the Bayesian classifier with a relatively large number (1000s) of sample `.yourextension` files. (ping **@arfon** or **@bkeepers** to help with this) to ensure we're not misclassifying files.
-0. If the Bayesian classifier does a bad job with the sample `.yourextension` files then a [heuristic](https://github.com/github/linguist/blob/master/lib/linguist/heuristics.rb) may need to be written to help.
+1. Make sure that example `.yourextension` files are present in the [samples directory][samples] for each language that uses `.yourextension`.
+1. Test the performance of the Bayesian classifier with a relatively large number (1000s) of sample `.yourextension` files. (ping **@bkeepers** to help with this) to ensure we're not misclassifying files.
+1. If the Bayesian classifier does a bad job with the sample `.yourextension` files then a [heuristic](https://github.com/github/linguist/blob/master/lib/linguist/heuristics.rb) may need to be written to help.
 
 
 ## Adding a language
@@ -27,17 +27,17 @@ We try only to add languages once they have some usage on GitHub. In most cases
 
 To add support for a new language:
 
-0. Add an entry for your language to [`languages.yml`][languages]. Omit the `language_id` field for now.
-0. Add a grammar for your language: `script/add-grammar https://github.com/JaneSmith/MyGrammar`. Please only add grammars that have [one of these licenses][licenses].
-0. Add samples for your language to the [samples directory][samples] in the correct subdirectory.
-0. Add a `language_id` for your language using `script/set-language-ids`. **You should only ever need to run `script/set-language-ids --update`. Anything other than this risks breaking GitHub search :cry:**
-0. Open a pull request, linking to a [GitHub search result](https://github.com/search?utf8=%E2%9C%93&q=extension%3Aboot+NOT+nothack&type=Code&ref=searchresults) showing in-the-wild usage.
+1. Add an entry for your language to [`languages.yml`][languages]. Omit the `language_id` field for now.
+1. Add a grammar for your language: `script/add-grammar https://github.com/JaneSmith/MyGrammar`. Please only add grammars that have [one of these licenses][licenses].
+1. Add samples for your language to the [samples directory][samples] in the correct subdirectory.
+1. Add a `language_id` for your language using `script/set-language-ids`. **You should only ever need to run `script/set-language-ids --update`. Anything other than this risks breaking GitHub search :cry:**
+1. Open a pull request, linking to a [GitHub search result](https://github.com/search?utf8=%E2%9C%93&q=extension%3Aboot+NOT+nothack&type=Code&ref=searchresults) showing in-the-wild usage.
 
 In addition, if your new language defines an extension that's already listed in [`languages.yml`][languages] (such as `.foo`) then sometimes a few more steps will need to be taken:
 
-0. Make sure that example `.foo` files are present in the [samples directory][samples] for each language that uses `.foo`.
-0. Test the performance of the Bayesian classifier with a relatively large number (1000s) of sample `.foo` files. (ping **@arfon** or **@bkeepers** to help with this) to ensure we're not misclassifying files.
-0. If the Bayesian classifier does a bad job with the sample `.foo` files then a [heuristic](https://github.com/github/linguist/blob/master/lib/linguist/heuristics.rb) may need to be written to help.
+1. Make sure that example `.foo` files are present in the [samples directory][samples] for each language that uses `.foo`.
+1. Test the performance of the Bayesian classifier with a relatively large number (1000s) of sample `.foo` files. (ping **@bkeepers** to help with this) to ensure we're not misclassifying files.
+1. If the Bayesian classifier does a bad job with the sample `.foo` files then a [heuristic](https://github.com/github/linguist/blob/master/lib/linguist/heuristics.rb) may need to be written to help.
 
 Remember, the goal here is to try and avoid false positives!
 
@@ -79,10 +79,15 @@ Here's our current build status: [![Build Status](https://api.travis-ci.org/gith
 
 Linguist is maintained with :heart: by:
 
-- **@arfon** (GitHub Staff)
 - **@Alhadis**
+- **@BenEddy** (GitHub staff)
+- **@Caged** (GitHub staff)
+- **@grantr** (GitHub staff)
 - **@larsbrinkhoff**
+- **@lildude** (GitHub staff)
 - **@pchaigno**
+- **@rafer** (GitHub staff)
+- **@shreyasjoshis** (GitHub staff)
 
 As Linguist is a production dependency for GitHub we have a couple of workflow restrictions:
 
@@ -93,21 +98,21 @@ As Linguist is a production dependency for GitHub we have a couple of workflow r
 
 If you are the current maintainer of this gem:
 
-0. Create a branch for the release: `git checkout -b cut-release-vxx.xx.xx`
-0. Make sure your local dependencies are up to date: `script/bootstrap`
-0. If grammar submodules have not been updated recently, update them: `git submodule update --remote && git commit -a`
-0. Ensure that samples are updated: `bundle exec rake samples`
-0. Ensure that tests are green: `bundle exec rake test`
-0. Bump gem version in `lib/linguist/version.rb`, [like this](https://github.com/github/linguist/commit/8d2ea90a5ba3b2fe6e1508b7155aa4632eea2985).
-0. Make a PR to github/linguist, [like this](https://github.com/github/linguist/pull/1238).
-0. Build a local gem: `bundle exec rake build_gem`
-0. Test the gem:
-  0. Bump the Gemfile and Gemfile.lock versions for an app which relies on this gem
-  0. Install the new gem locally
-  0. Test behavior locally, branch deploy, whatever needs to happen
-0. Merge github/linguist PR
-0. Tag and push: `git tag vx.xx.xx; git push --tags`
-0. Push to rubygems.org -- `gem push github-linguist-3.0.0.gem`
+1. Create a branch for the release: `git checkout -b cut-release-vxx.xx.xx`
+1. Make sure your local dependencies are up to date: `script/bootstrap`
+1. If grammar submodules have not been updated recently, update them: `git submodule update --remote && git commit -a`
+1. Ensure that samples are updated: `bundle exec rake samples`
+1. Ensure that tests are green: `bundle exec rake test`
+1. Bump gem version in `lib/linguist/version.rb`, [like this](https://github.com/github/linguist/commit/8d2ea90a5ba3b2fe6e1508b7155aa4632eea2985).
+1. Make a PR to github/linguist, [like this](https://github.com/github/linguist/pull/1238).
+1. Build a local gem: `bundle exec rake build_gem`
+1. Test the gem:
+  1. Bump the Gemfile and Gemfile.lock versions for an app which relies on this gem
+  1. Install the new gem locally
+  1. Test behavior locally, branch deploy, whatever needs to happen
+1. Merge github/linguist PR
+1. Tag and push: `git tag vx.xx.xx; git push --tags`
+1. Push to rubygems.org -- `gem push github-linguist-3.0.0.gem`
 
 [grammars]: /grammars.yml
 [languages]: /lib/linguist/languages.yml

LICENSE

@@ -1,4 +1,4 @@
-Copyright (c) 2011-2016 GitHub, Inc.
+Copyright (c) 2017 GitHub, Inc.
 
 Permission is hereby granted, free of charge, to any person
 obtaining a copy of this software and associated documentation

README.md

@@ -15,10 +15,10 @@ See [Troubleshooting](#troubleshooting) and [`CONTRIBUTING.md`](/CONTRIBUTING.md
 
 The Language stats bar displays languages percentages for the files in the repository. The percentages are calculated based on the bytes of code for each language as reported by the [List Languages](https://developer.github.com/v3/repos/#list-languages) API. If the bar is reporting a language that you don't expect:
 
-0. Click on the name of the language in the stats bar to see a list of the files that are identified as that language.
-0. If you see files that you didn't write, consider moving the files into one of the [paths for vendored  code](/lib/linguist/vendor.yml), or use the [manual overrides](#overrides) feature to ignore them.
-0. If the files are being misclassified, search for [open issues][issues] to see if anyone else has already reported the issue. Any information you can add, especially links to public repositories, is helpful.
-0. If there are no reported issues of this misclassification, [open an issue][new-issue] and include a link to the repository or a sample of the code that is being misclassified.
+1. Click on the name of the language in the stats bar to see a list of the files that are identified as that language.
+1. If you see files that you didn't write, consider moving the files into one of the [paths for vendored  code](/lib/linguist/vendor.yml), or use the [manual overrides](#overrides) feature to ignore them.
+1. If the files are being misclassified, search for [open issues][issues] to see if anyone else has already reported the issue. Any information you can add, especially links to public repositories, is helpful.
+1. If there are no reported issues of this misclassification, [open an issue][new-issue] and include a link to the repository or a sample of the code that is being misclassified.
 
 ### There's a problem with the syntax highlighting of a file
 
@@ -32,13 +32,15 @@ Linguist supports a number of different custom overrides strategies for language
 
 ### Using gitattributes
 
-Add a `.gitattributes` file to your project and use standard git-style path matchers for the files you want to override to set `linguist-documentation`, `linguist-language`, and `linguist-vendored`. `.gitattributes` will be used to determine language statistics, but will not be used to syntax highlight files. To manually set syntax highlighting, use [Vim or Emacs modelines](#using-emacs-or-vim-modelines).
+Add a `.gitattributes` file to your project and use standard git-style path matchers for the files you want to override to set `linguist-documentation`, `linguist-language`, `linguist-vendored`, and `linguist-generated`. `.gitattributes` will be used to determine language statistics and will be used to syntax highlight files. You can also manually set syntax highlighting using [Vim or Emacs modelines](#using-emacs-or-vim-modelines).
 
 ```
 $ cat .gitattributes
 *.rb linguist-language=Java
 ```
 
+#### Vendored code
+
 Checking code you didn't write, such as JavaScript libraries, 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. By default, Linguist treats all of the paths defined in [lib/linguist/vendor.yml](https://github.com/github/linguist/blob/master/lib/linguist/vendor.yml) as vendored and therefore doesn't include them in the language statistics for a repository.
 
 Use the `linguist-vendored` attribute to vendor or un-vendor paths.
@@ -49,6 +51,8 @@ special-vendored-path/* linguist-vendored
 jquery.js linguist-vendored=false
 ```
 
+#### Documentation
+
 Just like vendored files, Linguist excludes documentation files from your project's language stats. [lib/linguist/documentation.yml](lib/linguist/documentation.yml) lists common documentation paths and excludes them from the language statistics for your repository.
 
 Use the `linguist-documentation` attribute to mark or unmark paths as documentation.
@@ -59,19 +63,18 @@ project-docs/* linguist-documentation
 docs/formatter.rb linguist-documentation=false
 ```
 
-#### Generated file detection
+#### Generated code
 
 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 added bonus, unlike vendored and documentation files, these files are suppressed in diffs.
 
-```ruby
-Linguist::FileBlob.new("underscore.min.js").generated? # => true
 ```
-
-See [Linguist::Generated#generated?](https://github.com/github/linguist/blob/master/lib/linguist/generated.rb).
+$ cat .gitattributes
+Api.elm linguist-generated=true
+```
 
 ### Using Emacs or Vim modelines
 
-Alternatively, you can use Vim or Emacs style modelines to set the language for a single file. Modelines can be placed anywhere within a file and are respected when determining how to syntax-highlight a file on GitHub.com
+If you do not want to use `.gitattributes` to override the syntax highlighting used on GitHub.com, you can use Vim or Emacs style modelines to set the language for a single file. Modelines can be placed anywhere within a file and are respected when determining how to syntax-highlight a file on GitHub.com
 
 ##### Vim
 ```

Rakefile

@@ -4,6 +4,7 @@ require 'rake/testtask'
 require 'yaml'
 require 'yajl'
 require 'open-uri'
+require 'json'
 
 task :default => :test
 

bin/git-linguist

@@ -1,5 +1,7 @@
 #!/usr/bin/env ruby
 
+$LOAD_PATH[0, 0] = File.join(File.dirname(__FILE__), '..', 'lib')
+
 require 'linguist'
 require 'rugged'
 require 'optparse'
@@ -102,10 +104,16 @@ def git_linguist(args)
   commit = nil
 
   parser = OptionParser.new do |opts|
-    opts.banner = "Usage: git-linguist [OPTIONS] stats|breakdown|dump-cache|clear|disable"
+    opts.banner = <<-HELP
+    Linguist v#{Linguist::VERSION}
+    Detect language type and determine language breakdown for a given Git repository.
+
+    Usage:
+    git-linguist [OPTIONS] stats|breakdown|dump-cache|clear|disable"
+    HELP
 
     opts.on("-f", "--force", "Force a full rescan") { incremental = false }
-    opts.on("--commit=COMMIT", "Commit to index") { |v| commit = v}
+    opts.on("-c", "--commit=COMMIT", "Commit to index") { |v| commit = v}
   end
 
   parser.parse!(args)

bin/linguist

@@ -1,29 +1,37 @@
 #!/usr/bin/env ruby
 
-# linguist — detect language type for a file, or, given a directory, determine language breakdown
-#     usage: linguist <path> [<--breakdown>]
-#
+$LOAD_PATH[0, 0] = File.join(File.dirname(__FILE__), '..', 'lib')
+
 require 'linguist'
 require 'rugged'
+require 'json'
+require 'optparse'
 
 path = ARGV[0] || Dir.pwd
 
-# special case if not given a directory but still given the --breakdown option
+# special case if not given a directory
+# but still given the --breakdown or --json options/
 if path == "--breakdown"
   path = Dir.pwd
   breakdown = true
+elsif path == "--json"
+  path = Dir.pwd
+  json_breakdown = true
 end
 
 ARGV.shift
 breakdown = true if ARGV[0] == "--breakdown"
+json_breakdown = true if ARGV[0] == "--json"
 
 if File.directory?(path)
   rugged = Rugged::Repository.new(path)
   repo = Linguist::Repository.new(rugged, rugged.head.target_id)
-  repo.languages.sort_by { |_, size| size }.reverse.each do |language, size|
-    percentage = ((size / repo.size.to_f) * 100)
-    percentage = sprintf '%.2f' % percentage
-    puts "%-7s %s" % ["#{percentage}%", language]
+  if !json_breakdown
+    repo.languages.sort_by { |_, size| size }.reverse.each do |language, size|
+      percentage = ((size / repo.size.to_f) * 100)
+      percentage = sprintf '%.2f' % percentage
+      puts "%-7s %s" % ["#{percentage}%", language]
+    end
   end
   if breakdown
     puts
@@ -35,6 +43,8 @@ if File.directory?(path)
       end
       puts
     end
+  elsif json_breakdown
+    puts JSON.dump(repo.breakdown_by_file)
   end
 elsif File.file?(path)
   blob = Linguist::FileBlob.new(path, Dir.pwd)
@@ -63,5 +73,12 @@ elsif File.file?(path)
     puts "  appears to be a vendored file"
   end
 else
-  abort "usage: linguist <path>"
+  abort <<-HELP
+  Linguist v#{Linguist::VERSION}
+  Detect language type for a file, or, given a repository, determine language breakdown.
+
+  Usage: linguist <path>
+         linguist <path> [--breakdown] [--json]
+         linguist [--breakdown] [--json]
+  HELP
 end

github-linguist.gemspec

@@ -16,7 +16,7 @@ Gem::Specification.new do |s|
   s.add_dependency 'charlock_holmes', '~> 0.7.3'
   s.add_dependency 'escape_utils',    '~> 1.1.0'
   s.add_dependency 'mime-types',      '>= 1.19'
-  s.add_dependency 'rugged',          '>= 0.23.0b'
+  s.add_dependency 'rugged',          '>= 0.25.1'
 
   s.add_development_dependency 'minitest', '>= 5.0'
   s.add_development_dependency 'mocha'
@@ -26,6 +26,5 @@ Gem::Specification.new do |s|
   s.add_development_dependency 'yajl-ruby'
   s.add_development_dependency 'color-proximity', '~> 0.2.1'
   s.add_development_dependency 'licensed'
-  s.add_development_dependency 'licensee', '>= 8.6.0'
-
+  s.add_development_dependency 'licensee', '~> 8.8.0'
 end

grammars.yml

@@ -1,9 +1,9 @@
 ---
-http://svn.edgewall.org/repos/genshi/contrib/textmate/Genshi.tmbundle/Syntaxes/Markup%20Template%20%28XML%29.tmLanguage:
-- text.xml.genshi
 https://bitbucket.org/Clams/sublimesystemverilog/get/default.tar.gz:
 - source.systemverilog
 - source.ucfconstraints
+https://svn.edgewall.org/repos/genshi/contrib/textmate/Genshi.tmbundle/Syntaxes/Markup%20Template%20%28XML%29.tmLanguage:
+- text.xml.genshi
 vendor/grammars/ABNF.tmbundle:
 - source.abnf
 vendor/grammars/Agda.tmbundle:
@@ -56,6 +56,8 @@ vendor/grammars/MQL5-sublime:
 vendor/grammars/MagicPython:
 - source.python
 - source.regexp.python
+- text.python.console
+- text.python.traceback
 vendor/grammars/Modelica:
 - source.modelica
 vendor/grammars/NSIS:
@@ -113,7 +115,9 @@ vendor/grammars/SublimeBrainfuck:
 - source.bf
 vendor/grammars/SublimeClarion:
 - source.clarion
-vendor/grammars/SublimeGDB:
+vendor/grammars/SublimeEthereum:
+- source.solidity
+vendor/grammars/SublimeGDB/:
 - source.disasm
 - source.gdb
 - source.gdb.session
@@ -128,6 +132,8 @@ vendor/grammars/TLA:
 - source.tla
 vendor/grammars/TXL:
 - source.txl
+vendor/grammars/Terraform.tmLanguage:
+- source.terraform
 vendor/grammars/Textmate-Gosu-Bundle:
 - source.gosu.2
 vendor/grammars/UrWeb-Language-Definition:
@@ -178,8 +184,18 @@ vendor/grammars/atom-language-1c-bsl:
 - source.sdbl
 vendor/grammars/atom-language-clean:
 - source.clean
+- text.restructuredtext.clean
+vendor/grammars/atom-language-p4:
+- source.p4
+vendor/grammars/atom-language-perl6:
+- source.meta-info
+- source.perl6fe
+- source.quoting.perl6fe
+- source.regexp.perl6fe
 vendor/grammars/atom-language-purescript:
 - source.purescript
+vendor/grammars/atom-language-rust:
+- source.rust
 vendor/grammars/atom-language-srt:
 - text.srt
 vendor/grammars/atom-language-stan:
@@ -211,7 +227,6 @@ vendor/grammars/capnproto.tmbundle:
 vendor/grammars/carto-atom:
 - source.css.mss
 vendor/grammars/ceylon-sublimetext:
-- module.ceylon
 - source.ceylon
 vendor/grammars/chapel-tmbundle:
 - source.chapel
@@ -225,8 +240,6 @@ vendor/grammars/cpp-qt.tmbundle:
 - source.qmake
 vendor/grammars/creole:
 - text.html.creole
-vendor/grammars/css.tmbundle:
-- source.css
 vendor/grammars/cucumber-tmbundle:
 - source.ruby.rspec.cucumber.steps
 - text.gherkin.feature
@@ -360,12 +373,23 @@ vendor/grammars/language-csound:
 - source.csound
 - source.csound-document
 - source.csound-score
+vendor/grammars/language-css:
+- source.css
 vendor/grammars/language-emacs-lisp:
 - source.emacs.lisp
+vendor/grammars/language-fontforge:
+- source.fontforge
+- source.opentype
+- text.sfd
 vendor/grammars/language-gfm:
 - source.gfm
+vendor/grammars/language-gn:
+- source.gn
 vendor/grammars/language-graphql:
 - source.graphql
+vendor/grammars/language-haml:
+- text.haml
+- text.hamlc
 vendor/grammars/language-haskell:
 - hint.haskell
 - hint.message.haskell
@@ -375,15 +399,19 @@ vendor/grammars/language-haskell:
 - source.haskell
 - source.hsc2hs
 - text.tex.latex.haskell
-vendor/grammars/language-hy:
-- source.hy
 vendor/grammars/language-inform7:
 - source.inform7
 vendor/grammars/language-javascript:
 - source.js
-- source.js.embedded.html
 - source.js.regexp
 - source.js.regexp.replacement
+- source.jsdoc
+vendor/grammars/language-jison:
+- source.jison
+- source.jisonlex
+- source.jisonlex-injection
+vendor/grammars/language-jolie:
+- source.jolie
 vendor/grammars/language-jsoniq:
 - source.jq
 - source.xq
@@ -391,18 +419,24 @@ vendor/grammars/language-less:
 - source.css.less
 vendor/grammars/language-maxscript:
 - source.maxscript
+vendor/grammars/language-meson:
+- source.meson
 vendor/grammars/language-ncl:
 - source.ncl
+vendor/grammars/language-ninja:
+- source.ninja
 vendor/grammars/language-povray:
 - source.pov-ray sdl
-vendor/grammars/language-python:
-- text.python.console
-- text.python.traceback
+vendor/grammars/language-regexp:
+- source.regexp
+- source.regexp.extended
 vendor/grammars/language-renpy:
 - source.renpy
 vendor/grammars/language-restructuredtext:
 - text.restructuredtext
 vendor/grammars/language-roff:
+- source.ditroff
+- source.ditroff.desc
 - source.ideal
 - source.pic
 - text.roff
@@ -426,6 +460,8 @@ vendor/grammars/language-wavefront:
 - source.wavefront.obj
 vendor/grammars/language-xbase:
 - source.harbour
+vendor/grammars/language-xcompose:
+- config.xcompose
 vendor/grammars/language-yaml:
 - source.yaml
 vendor/grammars/language-yang:
@@ -455,6 +491,8 @@ vendor/grammars/make.tmbundle:
 - source.makefile
 vendor/grammars/mako-tmbundle:
 - text.html.mako
+vendor/grammars/marko-tmbundle:
+- text.marko
 vendor/grammars/mathematica-tmbundle:
 - source.mathematica
 vendor/grammars/matlab.tmbundle:
@@ -474,8 +512,6 @@ vendor/grammars/nemerle.tmbundle:
 - source.nemerle
 vendor/grammars/nesC:
 - source.nesc
-vendor/grammars/ninja.tmbundle:
-- source.ninja
 vendor/grammars/nix:
 - source.nix
 vendor/grammars/nu.tmbundle:
@@ -494,6 +530,8 @@ vendor/grammars/ooc.tmbundle:
 - source.ooc
 vendor/grammars/opa.tmbundle:
 - source.opa
+vendor/grammars/openscad.tmbundle:
+- source.scad
 vendor/grammars/oz-tmbundle/Syntaxes/Oz.tmLanguage:
 - source.oz
 vendor/grammars/parrot:
@@ -505,10 +543,6 @@ vendor/grammars/pawn-sublime-language:
 vendor/grammars/perl.tmbundle:
 - source.perl
 - source.perl.6
-vendor/grammars/perl6fe:
-- source.meta-info
-- source.perl6fe
-- source.regexp.perl6fe
 vendor/grammars/php-smarty.tmbundle:
 - text.html.smarty
 vendor/grammars/php.tmbundle:
@@ -531,8 +565,10 @@ vendor/grammars/python-django.tmbundle:
 vendor/grammars/r.tmbundle:
 - source.r
 - text.tex.latex.rd
-vendor/grammars/ruby-haml.tmbundle:
-- text.haml
+vendor/grammars/rascal-syntax-highlighting:
+- source.rascal
+vendor/grammars/reason:
+- source.reason
 vendor/grammars/ruby-slim.tmbundle:
 - text.slim
 vendor/grammars/ruby.tmbundle:
@@ -552,6 +588,9 @@ vendor/grammars/scilab.tmbundle:
 - source.scilab
 vendor/grammars/secondlife-lsl:
 - source.lsl
+vendor/grammars/shaders-tmLanguage:
+- source.hlsl
+- source.shaderlab
 vendor/grammars/smali-sublime:
 - source.smali
 vendor/grammars/smalltalk-tmbundle:
@@ -600,8 +639,6 @@ vendor/grammars/sublime-rexx:
 - source.rexx
 vendor/grammars/sublime-robot-plugin:
 - text.robot
-vendor/grammars/sublime-rust:
-- source.rust
 vendor/grammars/sublime-spintools:
 - source.regexp.spin
 - source.spin
@@ -653,7 +690,5 @@ vendor/grammars/xc.tmbundle:
 vendor/grammars/xml.tmbundle:
 - text.xml
 - text.xml.xsl
-vendor/grammars/xquery:
-- source.xquery
 vendor/grammars/zephir-sublime:
 - source.php.zephir

lib/linguist.rb

@@ -15,9 +15,9 @@ class << Linguist
   #       see Linguist::LazyBlob and Linguist::FileBlob for examples
   #
   # Returns Language or nil.
-  def detect(blob)
+  def detect(blob, allow_empty: false)
     # Bail early if the blob is binary or empty.
-    return nil if blob.likely_binary? || blob.binary? || blob.empty?
+    return nil if blob.likely_binary? || blob.binary? || (!allow_empty && blob.empty?)
 
     Linguist.instrument("linguist.detection", :blob => blob) do
       # Call each strategy until one candidate is returned.
@@ -59,8 +59,9 @@ class << Linguist
   # Strategies are called in turn until a single Language is returned.
   STRATEGIES = [
     Linguist::Strategy::Modeline,
-    Linguist::Shebang,
     Linguist::Strategy::Filename,
+    Linguist::Shebang,
+    Linguist::Strategy::Extension,
     Linguist::Heuristics,
     Linguist::Classifier
   ]
@@ -73,7 +74,7 @@ class << Linguist
   #       end
   #     end
   #
-  #     Linguist.instrumenter = CustomInstrumenter
+  #     Linguist.instrumenter = CustomInstrumenter.new
   #
   # The instrumenter must conform to the `ActiveSupport::Notifications`
   # interface, which defines `#instrument` and accepts:

lib/linguist/blob.rb

@@ -63,7 +63,7 @@ module Linguist
     #
     # Returns an Array
     def extensions
-      _, *segments = name.downcase.split(".")
+      _, *segments = name.downcase.split(".", -1)
 
       segments.map.with_index do |segment, index|
         "." + segments[index..-1].join(".")

lib/linguist/classifier.rb

@@ -95,7 +95,7 @@ module Linguist
     # 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?
+      return [] if tokens.nil? || languages.empty?
       tokens = Tokenizer.tokenize(tokens) if tokens.is_a?(String)
       scores = {}
 

lib/linguist/documentation.yml

@@ -9,11 +9,12 @@
 
 ## Documentation directories ##
 
-- ^docs?/
+- ^[Dd]ocs?/
 - (^|/)[Dd]ocumentation/
-- (^|/)javadoc/
-- ^man/
+- (^|/)[Jj]avadoc/
+- ^[Mm]an/
 - ^[Ee]xamples/
+- ^[Dd]emos?/
 
 ## Documentation files ##
 
@@ -27,4 +28,4 @@
 - (^|/)[Rr]eadme(\.|$)
 
 # Samples folders
-- ^[Ss]amples/
+- ^[Ss]amples?/

lib/linguist/generated.rb

@@ -3,7 +3,7 @@ module Linguist
     # Public: Is the blob a generated file?
     #
     # name - String filename
-    # data - String blob data. A block also maybe passed in for lazy
+    # data - String blob data. A block also may be passed in for lazy
     #        loading. This behavior is deprecated and you should always
     #        pass in a String.
     #
@@ -70,6 +70,7 @@ module Linguist
       compiled_cython_file? ||
       generated_go? ||
       generated_protocol_buffer? ||
+      generated_javascript_protocol_buffer? ||
       generated_apache_thrift? ||
       generated_jni_header? ||
       vcr_cassette? ||
@@ -77,7 +78,10 @@ module Linguist
       generated_unity3d_meta? ||
       generated_racc? ||
       generated_jflex? ||
-      generated_grammarkit?
+      generated_grammarkit? ||
+      generated_roxygen2? ||
+      generated_jison? ||
+      generated_yarn_lock?
     end
 
     # Internal: Is the blob an Xcode file?
@@ -275,16 +279,25 @@ module Linguist
       return lines[0].include?("Generated by the protocol buffer compiler.  DO NOT EDIT!")
     end
 
-    APACHE_THRIFT_EXTENSIONS = ['.rb', '.py', '.go', '.js', '.m', '.java', '.h', '.cc', '.cpp']
+    # Internal: Is the blob a Javascript source file generated by the
+    # Protocol Buffer compiler?
+    #
+    # Returns true of false.
+    def generated_javascript_protocol_buffer?
+      return false unless extname == ".js"
+      return false unless lines.count > 6
+
+      return lines[5].include?("GENERATED CODE -- DO NOT EDIT!")
+    end
+
+    APACHE_THRIFT_EXTENSIONS = ['.rb', '.py', '.go', '.js', '.m', '.java', '.h', '.cc', '.cpp', '.php']
 
     # Internal: Is the blob generated by Apache Thrift compiler?
     #
     # Returns true or false
     def generated_apache_thrift?
       return false unless APACHE_THRIFT_EXTENSIONS.include?(extname)
-      return false unless lines.count > 1
-
-      return lines[0].include?("Autogenerated by Thrift Compiler") || lines[1].include?("Autogenerated by Thrift Compiler")
+      return lines.first(6).any? { |l| l.include?("Autogenerated by Thrift Compiler") }
     end
 
     # Internal: Is the blob a C/C++ header generated by the Java JNI tool javah?
@@ -313,7 +326,7 @@ module Linguist
       !!name.match(/vendor\/((?!-)[-0-9A-Za-z]+(?<!-)\.)+(com|edu|gov|in|me|net|org|fm|io)/)
     end
 
-    # Internal: Is the blob a generated npm shrinkwrap file.
+    # Internal: Is the blob a generated npm shrinkwrap file?
     #
     # Returns true or false.
     def npm_shrinkwrap?
@@ -335,7 +348,7 @@ module Linguist
       !!name.match(/composer\.lock/)
     end
 
-    # Internal: Is the blob a generated by Zephir
+    # Internal: Is the blob generated by Zephir?
     #
     # Returns true or false.
     def generated_by_zephir?
@@ -435,5 +448,46 @@ module Linguist
       return false unless lines.count > 1
       return lines[0].start_with?("// This is a generated file. Not intended for manual editing.")
     end
+
+    # Internal: Is this a roxygen2-generated file?
+    #
+    # A roxygen2-generated file typically contain:
+    # % Generated by roxygen2: do not edit by hand
+    # on the first line.
+    #
+    # Return true or false
+    def generated_roxygen2?
+      return false unless extname == '.Rd'
+      return false unless lines.count > 1
+
+      return lines[0].include?("% Generated by roxygen2: do not edit by hand")
+    end
+
+    # Internal: Is this a Jison-generated file?
+    #
+    # Jison-generated parsers typically contain:
+    # /* parser generated by jison
+    # on the first line.
+    #
+    # Jison-generated lexers typically contain:
+    # /* generated by jison-lex
+    # on the first line.
+    #
+    # Return true or false
+    def generated_jison?
+      return false unless extname == '.js'
+      return false unless lines.count > 1
+      return lines[0].start_with?("/* parser generated by jison ") ||
+             lines[0].start_with?("/* generated by jison-lex ")
+    end
+
+    # Internal: Is the blob a generated yarn lockfile?
+    #
+    # Returns true or false.
+    def generated_yarn_lock?
+      return false unless name.match(/yarn\.lock/)
+      return false unless lines.count > 0
+      return lines[0].include?("# THIS IS AN AUTOGENERATED FILE")
+    end
   end
 end

lib/linguist/heuristics.rb

@@ -110,6 +110,12 @@ module Linguist
       end
     end
 
+    disambiguate ".cls" do |data|
+      if /\\\w+{/.match(data)
+        Language["TeX"]
+      end
+    end
+
     disambiguate ".cs" do |data|
       if /![\w\s]+methodsFor: /.match(data)
         Language["Smalltalk"]
@@ -119,11 +125,18 @@ module Linguist
     end
 
     disambiguate ".d" do |data|
-      if /^module /.match(data)
+      # see http://dlang.org/spec/grammar
+      # ModuleDeclaration | ImportDeclaration | FuncDeclaration | unittest
+      if /^module\s+[\w.]*\s*;|import\s+[\w\s,.:]*;|\w+\s+\w+\s*\(.*\)(?:\(.*\))?\s*{[^}]*}|unittest\s*(?:\(.*\))?\s*{[^}]*}/.match(data)
         Language["D"]
-      elsif /^((dtrace:::)?BEGIN|provider |#pragma (D (option|attributes)|ident)\s)/.match(data)
+      # see http://dtrace.org/guide/chp-prog.html, http://dtrace.org/guide/chp-profile.html, http://dtrace.org/guide/chp-opt.html
+      elsif /^(\w+:\w*:\w*:\w*|BEGIN|END|provider\s+|(tick|profile)-\w+\s+{[^}]*}|#pragma\s+D\s+(option|attributes|depends_on)\s|#pragma\s+ident\s)/.match(data)
         Language["DTrace"]
-      elsif /(\/.*:( .* \\)$| : \\$|^ : |: \\$)/.match(data)
+      # path/target : dependency \
+      # target : \
+      #  : dependency
+      # path/file.ext1 : some/path/../file.ext2
+      elsif /([\/\\].*:\s+.*\s\\$|: \\$|^ : |^[\w\s\/\\.]+\w+\.\w+\s*:\s+[\w\s\/\\.]+\w+\.\w+)/.match(data)
         Language["Makefile"]
       end
     end
@@ -152,7 +165,7 @@ module Linguist
       elsif data.include?("flowop")
         Language["Filebench WML"]
       elsif fortran_rx.match(data)
-        Language["FORTRAN"]
+        Language["Fortran"]
       end
     end
 
@@ -160,7 +173,7 @@ module Linguist
       if /^: /.match(data)
         Language["Forth"]
       elsif fortran_rx.match(data)
-        Language["FORTRAN"]
+        Language["Fortran"]
       end
     end
 
@@ -213,7 +226,7 @@ module Linguist
       elsif /^(%[%{}]xs|<.*>)/.match(data)
         Language["Lex"]
       elsif /^\.[a-z][a-z](\s|$)/i.match(data)
-        Language["Groff"]
+        Language["Roff"]
       elsif /^\((de|class|rel|code|data|must)\s/.match(data)
         Language["PicoLisp"]
       end
@@ -254,10 +267,12 @@ module Linguist
     end
 
     disambiguate ".md" do |data|
-      if /(^[-a-z0-9=#!\*\[|])|<\//i.match(data) || data.empty?
+      if /(^[-a-z0-9=#!\*\[|>])|<\//i.match(data) || data.empty?
         Language["Markdown"]
       elsif /^(;;|\(define_)/.match(data)
-        Language["GCC machine description"]
+        Language["GCC Machine Description"]
+      else
+        Language["Markdown"]
       end
     end
 
@@ -272,7 +287,7 @@ module Linguist
     disambiguate ".mod" do |data|
       if data.include?('<!ENTITY ')
         Language["XML"]
-      elsif /MODULE\s\w+\s*;/i.match(data) || /^\s*END \w+;$/i.match(data)
+      elsif /^\s*MODULE [\w\.]+;/i.match(data) || /^\s*END [\w\.]+;/i.match(data)
         Language["Modula-2"]
       else
         [Language["Linux Kernel Module"], Language["AMPL"]]
@@ -281,9 +296,9 @@ module Linguist
 
     disambiguate ".ms" do |data|
       if /^[.'][a-z][a-z](\s|$)/i.match(data)
-        Language["Groff"]
+        Language["Roff"]
       elsif /(?<!\S)\.(include|globa?l)\s/.match(data) || /(?<!\/\*)(\A|\n)\s*\.[A-Za-z]/.match(data.gsub(/"([^\\"]|\\.)*"|'([^\\']|\\.)*'|\\\s*(?:--.*)?\n/, ""))
-        Language["GAS"]
+        Language["Unix Assembly"]
       else
         Language["MAXScript"]
       end
@@ -291,7 +306,7 @@ module Linguist
 
     disambiguate ".n" do |data|
       if /^[.']/.match(data)
-        Language["Groff"]
+        Language["Roff"]
       elsif /^(module|namespace|using)\s/.match(data)
         Language["Nemerle"]
       end
@@ -320,7 +335,7 @@ module Linguist
     end
 
     disambiguate ".pl" do |data|
-      if /^[^#]+:-/.match(data)
+      if /^[^#]*:-/.match(data)
         Language["Prolog"]
       elsif /use strict|use\s+v?5\./.match(data)
         Language["Perl"]
@@ -329,16 +344,16 @@ module Linguist
       end
     end
 
-    disambiguate ".pm", ".t" do |data|
-      if /use strict|use\s+v?5\./.match(data)
-        Language["Perl"]
-      elsif /^(use v6|(my )?class|module)/.match(data)
+    disambiguate ".pm" do |data|
+      if /^\s*(?:use\s+v6\s*;|(?:\bmy\s+)?class|module)\b/.match(data)
         Language["Perl6"]
+      elsif /\buse\s+(?:strict\b|v?5\.)/.match(data)
+        Language["Perl"]
       end
     end
 
     disambiguate ".pod" do |data|
-      if /^=\w+$/.match(data)
+      if /^=\w+\b/.match(data)
         Language["Pod"]
       else
         Language["Perl"]
@@ -377,7 +392,7 @@ module Linguist
       if /^\.!|^\.end lit(?:eral)?\b/i.match(data)
         Language["RUNOFF"]
       elsif /^\.\\" /.match(data)
-        Language["Groff"]
+        Language["Roff"]
       end
     end
 
@@ -428,10 +443,12 @@ module Linguist
     end
     
     disambiguate ".t" do |data|
-      if /^\s*%|^\s*var\s+\w+\s*:\s*\w+/.match(data)
+      if /^\s*%[ \t]+|^\s*var\s+\w+\s*:=\s*\w+/.match(data)
         Language["Turing"]
-      elsif /^\s*use\s+v6\s*;/.match(data)
+      elsif /^\s*(?:use\s+v6\s*;|\bmodule\b|\b(?:my\s+)?class\b)/.match(data)
         Language["Perl6"]
+      elsif /\buse\s+(?:strict\b|v?5\.)/.match(data)
+        Language["Perl"]
       end
     end
     
@@ -459,5 +476,13 @@ module Linguist
         Language["Scilab"]
       end
     end
+
+    disambiguate ".tsx" do |data|
+      if /^\s*(import.+(from\s+|require\()['"]react|\/\/\/\s*<reference\s)/.match(data)
+        Language["TypeScript"]
+      elsif /^\s*<\?xml\s+version/i.match(data)
+        Language["XML"]
+      end
+    end
   end
 end

lib/linguist/language.rb

@@ -11,6 +11,7 @@ require 'linguist/samples'
 require 'linguist/file_blob'
 require 'linguist/blob_helper'
 require 'linguist/strategy/filename'
+require 'linguist/strategy/extension'
 require 'linguist/strategy/modeline'
 require 'linguist/shebang'
 
@@ -90,17 +91,6 @@ module Linguist
       language
     end
 
-    # Public: Detects the Language of the blob.
-    #
-    # blob - an object that includes the Linguist `BlobHelper` interface;
-    #       see Linguist::LazyBlob and Linguist::FileBlob for examples
-    #
-    # Returns Language or nil.
-    def self.detect(blob)
-      warn "[DEPRECATED] `Linguist::Language.detect` is deprecated. Use `Linguist.detect`. #{caller[0]}"
-      Linguist.detect(blob)
-    end
-
     # Public: Get all Languages
     #
     # Returns an Array of Languages
@@ -140,46 +130,46 @@ module Linguist
 
     # Public: Look up Languages by filename.
     #
+    # The behaviour of this method recently changed.
+    # See the second example below.
+    #
     # filename - The path String.
     #
     # Examples
     #
+    #   Language.find_by_filename('Cakefile')
+    #   # => [#<Language name="CoffeeScript">]
     #   Language.find_by_filename('foo.rb')
-    #   # => [#<Language name="Ruby">]
+    #   # => []
     #
     # Returns all matching Languages or [] if none were found.
     def self.find_by_filename(filename)
       basename = File.basename(filename)
-
-      # find the first extension with language definitions
-      extname = FileBlob.new(filename).extensions.detect do |e|
-        !@extension_index[e].empty?
-      end
-
-      (@filename_index[basename] + @extension_index[extname]).compact.uniq
+      @filename_index[basename]
     end
 
     # Public: Look up Languages by file extension.
     #
-    # extname - The extension String.
+    # The behaviour of this method recently changed.
+    # See the second example below.
+    #
+    # filename - The path String.
     #
     # Examples
     #
-    #   Language.find_by_extension('.rb')
+    #   Language.find_by_extension('dummy.rb')
     #   # => [#<Language name="Ruby">]
-    #
     #   Language.find_by_extension('rb')
-    #   # => [#<Language name="Ruby">]
+    #   # => []
     #
     # Returns all matching Languages or [] if none were found.
-    def self.find_by_extension(extname)
-      extname = ".#{extname}" unless extname.start_with?(".")
-      @extension_index[extname.downcase]
-    end
+    def self.find_by_extension(filename)
+      # find the first extension with language definitions
+      extname = FileBlob.new(filename.downcase).extensions.detect do |e|
+        !@extension_index[e].empty?
+      end
 
-    # DEPRECATED
-    def self.find_by_shebang(data)
-      @interpreter_index[Shebang.interpreter(data)]
+      @extension_index[extname]
     end
 
     # Public: Look up Languages by interpreter.
@@ -225,7 +215,14 @@ module Linguist
     # Returns the Language or nil if none was found.
     def self.[](name)
       return nil if name.to_s.empty?
-      name && (@index[name.downcase] || @index[name.split(',').first.downcase])
+
+      lang = @index[name.downcase]
+      return lang if lang
+
+      name = name.split(',').first
+      return nil if name.to_s.empty?
+
+      @index[name.downcase]
     end
 
     # Public: A List of popular languages
@@ -259,18 +256,6 @@ module Linguist
       @colors ||= all.select(&:color).sort_by { |lang| lang.name.downcase }
     end
 
-    # Public: A List of languages compatible with Ace.
-    #
-    # TODO: Remove this method in a 5.x release. Every language now needs an ace_mode
-    # key, so this function isn't doing anything unique anymore.
-    #
-    # Returns an Array of Languages.
-    def self.ace_modes
-      warn "This method will be deprecated in a future 5.x release. Every language now has an `ace_mode` set."
-      warn caller
-      @ace_modes ||= all.select(&:ace_mode).sort_by { |lang| lang.name.downcase }
-    end
-
     # Internal: Initialize a new Language
     #
     # attributes - A hash of attributes
@@ -287,7 +272,7 @@ module Linguist
       @color = attributes[:color]
 
       # Set aliases
-      @aliases = [default_alias_name] + (attributes[:aliases] || [])
+      @aliases = [default_alias] + (attributes[:aliases] || [])
 
       # Load the TextMate scope name or try to guess one
       @tm_scope = attributes[:tm_scope] || begin
@@ -305,9 +290,6 @@ module Linguist
       @codemirror_mime_type = attributes[:codemirror_mime_type]
       @wrap = attributes[:wrap] || false
 
-      # Set legacy search term
-      @search_term = attributes[:search_term] || default_alias_name
-
       # Set the language_id
       @language_id = attributes[:language_id]
 
@@ -362,17 +344,6 @@ module Linguist
     # Returns an Array of String names
     attr_reader :aliases
 
-    # Deprecated: Get code search term
-    #
-    # Examples
-    #
-    #   # => "ruby"
-    #   # => "python"
-    #   # => "perl"
-    #
-    # Returns the name String
-    attr_reader :search_term
-
     # Public: Get language_id (used in GitHub search)
     #
     # Examples
@@ -457,22 +428,6 @@ module Linguist
     # Returns the extensions Array
     attr_reader :filenames
 
-    # Deprecated: Get primary extension
-    #
-    # Defaults to the first extension but can be overridden
-    # in the languages.yml.
-    #
-    # The primary extension can not be nil. Tests should verify this.
-    #
-    # This method is only used by app/helpers/gists_helper.rb for creating
-    # the language dropdown. It really should be using `name` instead.
-    # Would like to drop primary extension.
-    #
-    # Returns the extension String.
-    def primary_extension
-      extensions.first
-    end
-
     # Public: Get URL escaped name.
     #
     # Examples
@@ -486,12 +441,13 @@ module Linguist
       EscapeUtils.escape_url(name).gsub('+', '%20')
     end
 
-    # Internal: Get default alias name
+    # Public: Get default alias name
     #
     # Returns the alias name String
-    def default_alias_name
+    def default_alias
       name.downcase.gsub(/\s/, '-')
     end
+    alias_method :default_alias_name, :default_alias
 
     # Public: Get Language group
     #
@@ -606,7 +562,6 @@ module Linguist
       :wrap              => options['wrap'],
       :group_name        => options['group'],
       :searchable        => options.fetch('searchable', true),
-      :search_term       => options['search_term'],
       :language_id       => options['language_id'],
       :extensions        => Array(options['extensions']),
       :interpreters      => options['interpreters'].sort,

lib/linguist/languages.yml

@@ -2,7 +2,8 @@
 #
 # type              - Either data, programming, markup, prose, or nil
 # aliases           - An Array of additional aliases (implicitly
-#                     includes name.downcase)
+#                     includes the lowercase name with spaces replaced
+#                     by dashes)
 # ace_mode          - A String name of the Ace Mode used for highlighting whenever
 #                     a file is edited. This must match one of the filenames in http://git.io/3XO_Cg.
 #                     Use "text" if a mode does not exist.
@@ -14,12 +15,10 @@
 #                     listed alphabetically)
 # interpreters      - An Array of associated interpreters
 # searchable        - Boolean flag to enable searching (defaults to true)
-# search_term       - Deprecated: Some languages may be indexed under a
-#                     different alias. Avoid defining new exceptions.
 # language_id       - Integer used as a language-name-independent indexed field so that we can rename
 #                     languages in Linguist without reindexing all the code on GitHub. Must not be
 #                     changed for existing languages without the explicit permission of GitHub staff.
-# color             - CSS hex color to represent the language. Only used if type is "programming" or "prose"
+# color             - CSS hex color to represent the language. Only used if type is "programming" or "prose".
 # tm_scope          - The TextMate scope that represents this programming
 #                     language. This should match one of the scopes listed in
 #                     the grammars.yml file. Use "none" if there is no grammar
@@ -121,7 +120,6 @@ ASN.1:
 ASP:
   type: programming
   color: "#6a40fd"
-  search_term: aspx-vb
   tm_scope: text.html.asp
   aliases:
   - aspx
@@ -154,7 +152,6 @@ ActionScript:
   type: programming
   tm_scope: source.actionscript.3
   color: "#882B0F"
-  search_term: as3
   aliases:
   - actionscript 3
   - actionscript3
@@ -291,7 +288,6 @@ AspectJ:
 Assembly:
   type: programming
   color: "#6E4C13"
-  search_term: nasm
   aliases:
   - nasm
   extensions:
@@ -349,7 +345,6 @@ Awk:
   language_id: 28
 Batchfile:
   type: programming
-  search_term: bat
   aliases:
   - bat
   - batch
@@ -474,7 +469,6 @@ C#:
   codemirror_mode: clike
   codemirror_mime_type: text/x-csharp
   tm_scope: source.cs
-  search_term: csharp
   color: "#178600"
   aliases:
   - csharp
@@ -489,7 +483,6 @@ C++:
   ace_mode: c_cpp
   codemirror_mode: clike
   codemirror_mime_type: text/x-c++src
-  search_term: cpp
   color: "#f34b7d"
   aliases:
   - cpp
@@ -507,6 +500,7 @@ C++:
   - ".inc"
   - ".inl"
   - ".ipp"
+  - ".re"
   - ".tcc"
   - ".tpp"
   language_id: 43
@@ -719,7 +713,6 @@ ColdFusion:
   type: programming
   ace_mode: coldfusion
   color: "#ed2cd6"
-  search_term: cfm
   aliases:
   - cfm
   - cfml
@@ -733,7 +726,6 @@ ColdFusion CFC:
   type: programming
   group: ColdFusion
   ace_mode: coldfusion
-  search_term: cfc
   aliases:
   - cfc
   extensions:
@@ -854,16 +846,6 @@ Csound Score:
   tm_scope: source.csound-score
   ace_mode: text
   language_id: 75
-Cucumber:
-  type: programming
-  extensions:
-  - ".feature"
-  tm_scope: text.gherkin.feature
-  aliases:
-  - gherkin
-  ace_mode: text
-  color: "#5B2063"
-  language_id: 76
 Cuda:
   type: programming
   extensions:
@@ -956,7 +938,6 @@ DTrace:
   language_id: 85
 Darcs Patch:
   type: data
-  search_term: dpatch
   aliases:
   - dpatch
   extensions:
@@ -1141,9 +1122,10 @@ Emacs Lisp:
   - ".gnus"
   - ".spacemacs"
   - ".viper"
-  - "Project.ede"
-  - "_emacs"
-  - "abbrev_defs"
+  - Cask
+  - Project.ede
+  - _emacs
+  - abbrev_defs
   extensions:
   - ".el"
   - ".emacs"
@@ -1175,6 +1157,7 @@ Erlang:
   - ".xrl"
   - ".yrl"
   filenames:
+  - Emakefile
   - rebar.config
   - rebar.config.lock
   - rebar.lock
@@ -1187,7 +1170,6 @@ Erlang:
 F#:
   type: programming
   color: "#b845fc"
-  search_term: fsharp
   aliases:
   - fsharp
   extensions:
@@ -1208,23 +1190,6 @@ FLUX:
   tm_scope: none
   ace_mode: text
   language_id: 106
-FORTRAN:
-  type: programming
-  color: "#4d41b1"
-  extensions:
-  - ".f90"
-  - ".f"
-  - ".f03"
-  - ".f08"
-  - ".f77"
-  - ".f95"
-  - ".for"
-  - ".fpp"
-  tm_scope: source.fortran.modern
-  ace_mode: text
-  codemirror_mode: fortran
-  codemirror_mime_type: text/x-fortran
-  language_id: 107
 Factor:
   type: programming
   color: "#636746"
@@ -1294,6 +1259,23 @@ Forth:
   codemirror_mode: forth
   codemirror_mime_type: text/x-forth
   language_id: 114
+Fortran:
+  type: programming
+  color: "#4d41b1"
+  extensions:
+  - ".f90"
+  - ".f"
+  - ".f03"
+  - ".f08"
+  - ".f77"
+  - ".f95"
+  - ".for"
+  - ".fpp"
+  tm_scope: source.fortran.modern
+  ace_mode: text
+  codemirror_mode: fortran
+  codemirror_mime_type: text/x-fortran
+  language_id: 107
 FreeMarker:
   type: programming
   color: "#0050b2"
@@ -1339,15 +1321,6 @@ GAP:
   tm_scope: source.gap
   ace_mode: text
   language_id: 119
-GAS:
-  type: programming
-  group: Assembly
-  extensions:
-  - ".s"
-  - ".ms"
-  tm_scope: source.assembly
-  ace_mode: assembly_x86
-  language_id: 120
 GCC Machine Description:
   type: programming
   extensions:
@@ -1393,6 +1366,18 @@ GLSL:
   - ".vshader"
   ace_mode: glsl
   language_id: 124
+GN:
+  type: data
+  extensions:
+  - ".gn"
+  - ".gni"
+  interpreters:
+  - gn
+  tm_scope: source.gn
+  ace_mode: python
+  codemirror_mode: python
+  codemirror_mime_type: text/x-python
+  language_id: 302957008
 Game Maker Language:
   type: programming
   color: "#8fb200"
@@ -1403,6 +1388,14 @@ Game Maker Language:
   codemirror_mode: clike
   codemirror_mime_type: text/x-c++src
   language_id: 125
+Genie:
+  type: programming
+  ace_mode: text
+  extensions:
+  - ".gs"
+  color: "#fb855d"
+  tm_scope: none
+  language_id: 792408528
 Genshi:
   type: programming
   extensions:
@@ -1437,7 +1430,6 @@ Gentoo Eclass:
   language_id: 128
 Gettext Catalog:
   type: prose
-  search_term: pot
   searchable: false
   aliases:
   - pot
@@ -1447,6 +1439,16 @@ Gettext Catalog:
   tm_scope: source.po
   ace_mode: text
   language_id: 129
+Gherkin:
+  type: programming
+  extensions:
+  - ".feature"
+  tm_scope: text.gherkin.feature
+  aliases:
+  - cucumber
+  ace_mode: text
+  color: "#5B2063"
+  language_id: 76
 Glyph:
   type: programming
   color: "#e4cc98"
@@ -1473,6 +1475,8 @@ Gnuplot:
 Go:
   type: programming
   color: "#375eab"
+  aliases:
+  - golang
   extensions:
   - ".go"
   ace_mode: golang
@@ -1548,45 +1552,6 @@ Graphviz (DOT):
   - ".gv"
   ace_mode: text
   language_id: 140
-Groff:
-  type: markup
-  color: "#ecdebe"
-  extensions:
-  - ".man"
-  - ".1"
-  - ".1in"
-  - ".1m"
-  - ".1x"
-  - ".2"
-  - ".3"
-  - ".3in"
-  - ".3m"
-  - ".3qt"
-  - ".3x"
-  - ".4"
-  - ".5"
-  - ".6"
-  - ".7"
-  - ".8"
-  - ".9"
-  - ".l"
-  - ".me"
-  - ".ms"
-  - ".n"
-  - ".rno"
-  - ".roff"
-  - ".tmac"
-  filenames:
-  - mmn
-  - mmt
-  tm_scope: text.roff
-  aliases:
-  - nroff
-  - troff
-  ace_mode: text
-  codemirror_mode: troff
-  codemirror_mime_type: text/troff
-  language_id: 141
 Groovy:
   type: programming
   ace_mode: groovy
@@ -1624,17 +1589,18 @@ HCL:
   ace_mode: ruby
   codemirror_mode: ruby
   codemirror_mime_type: text/x-ruby
-  tm_scope: source.ruby
+  tm_scope: source.terraform
   language_id: 144
 HLSL:
   type: programming
   extensions:
   - ".hlsl"
+  - ".cginc"
   - ".fx"
   - ".fxh"
   - ".hlsli"
   ace_mode: text
-  tm_scope: none
+  tm_scope: source.hlsl
   language_id: 145
 HTML:
   type: markup
@@ -1642,7 +1608,7 @@ HTML:
   ace_mode: html
   codemirror_mode: htmlmixed
   codemirror_mime_type: text/html
-  color: "#e44b23"
+  color: "#e34c26"
   aliases:
   - xhtml
   extensions:
@@ -1659,13 +1625,16 @@ HTML+Django:
   tm_scope: text.html.django
   group: HTML
   extensions:
-  - ".mustache"
   - ".jinja"
+  - ".mustache"
+  - ".njk"
   aliases:
   - django
   - html+django/jinja
   - html+jinja
   - htmldjango
+  - njk
+  - nunjucks
   ace_mode: django
   codemirror_mode: django
   codemirror_mime_type: text/x-django
@@ -1798,7 +1767,7 @@ Hy:
   - ".hy"
   aliases:
   - hylang
-  tm_scope: source.hy
+  tm_scope: none
   language_id: 159
 HyPhy:
   type: programming
@@ -1844,7 +1813,6 @@ INI:
   language_id: 163
 IRC log:
   type: data
-  search_term: irc
   aliases:
   - irc
   - irc logs
@@ -1959,6 +1927,8 @@ JSON5:
   type: data
   extensions:
   - ".json5"
+  filenames:
+  - ".babelrc"
   tm_scope: source.js
   ace_mode: javascript
   codemirror_mode: javascript
@@ -1992,17 +1962,6 @@ JSX:
   codemirror_mode: jsx
   codemirror_mime_type: text/jsx
   language_id: 178
-Jade:
-  group: HTML
-  type: markup
-  extensions:
-  - ".jade"
-  - ".pug"
-  tm_scope: text.jade
-  ace_mode: jade
-  codemirror_mode: pug
-  codemirror_mime_type: text/x-pug
-  language_id: 179
 Jasmin:
   type: programming
   ace_mode: java
@@ -2022,7 +1981,6 @@ Java:
 Java Server Pages:
   type: programming
   group: Java
-  search_term: jsp
   aliases:
   - jsp
   extensions:
@@ -2067,6 +2025,33 @@ JavaScript:
   interpreters:
   - node
   language_id: 183
+Jison:
+  type: programming
+  group: Yacc
+  extensions:
+  - ".jison"
+  tm_scope: source.jison
+  ace_mode: text
+  language_id: 284531423
+Jison Lex:
+  type: programming
+  group: Lex
+  extensions:
+  - ".jisonlex"
+  tm_scope: source.jisonlex
+  ace_mode: text
+  language_id: 406395330
+Jolie:
+  type: programming
+  extensions:
+  - ".ol"
+  - ".iol"
+  interpreters:
+  - jolie
+  color: "#843179"
+  ace_mode: text
+  tm_scope: source.jolie
+  language_id: 998078858
 Julia:
   type: programming
   extensions:
@@ -2279,7 +2264,6 @@ Literate CoffeeScript:
   group: CoffeeScript
   ace_mode: text
   wrap: true
-  search_term: litcoffee
   aliases:
   - litcoffee
   extensions:
@@ -2288,7 +2272,6 @@ Literate CoffeeScript:
 Literate Haskell:
   type: programming
   group: Haskell
-  search_term: lhs
   aliases:
   - lhaskell
   - lhs
@@ -2338,6 +2321,8 @@ LookML:
   color: "#652B81"
   extensions:
   - ".lookml"
+  - ".model.lkml"
+  - ".view.lkml"
   tm_scope: source.yaml
   language_id: 211
 LoomScript:
@@ -2484,6 +2469,8 @@ Mako:
   language_id: 221
 Markdown:
   type: prose
+  aliases:
+  - pandoc
   ace_mode: markdown
   codemirror_mode: gfm
   codemirror_mime_type: text/x-gfm
@@ -2491,12 +2478,27 @@ Markdown:
   extensions:
   - ".md"
   - ".markdown"
+  - ".mdown"
+  - ".mdwn"
   - ".mkd"
   - ".mkdn"
   - ".mkdown"
   - ".ron"
+  - ".workbook"
   tm_scope: source.gfm
   language_id: 222
+Marko:
+  group: HTML
+  type: markup
+  tm_scope: text.marko
+  extensions:
+  - ".marko"
+  aliases:
+  - markojs
+  ace_mode: text
+  codemirror_mode: htmlmixed
+  codemirror_mime_type: text/html
+  language_id: 932782397
 Mask:
   type: markup
   color: "#f97732"
@@ -2550,7 +2552,6 @@ Max:
   aliases:
   - max/msp
   - maxmsp
-  search_term: max/msp
   extensions:
   - ".maxpat"
   - ".maxhelp"
@@ -2582,6 +2583,15 @@ Mercury:
   - ".moo"
   tm_scope: source.mercury
   language_id: 229
+Meson:
+  type: programming
+  color: "#007800"
+  filenames:
+  - meson.build
+  - meson_options.txt
+  tm_scope: source.meson
+  ace_mode: text
+  language_id: 799141244
 Metal:
   type: programming
   color: "#8f14e9"
@@ -2602,7 +2612,6 @@ MiniD:
   language_id: 231
 Mirah:
   type: programming
-  search_term: mirah
   color: "#c7a938"
   extensions:
   - ".druby"
@@ -2759,7 +2768,7 @@ Nginx:
   codemirror_mime_type: text/x-nginx-conf
   color: "#9469E9"
   language_id: 248
-Nimrod:
+Nim:
   type: programming
   color: "#37775b"
   extensions:
@@ -2951,9 +2960,18 @@ OpenSCAD:
   type: programming
   extensions:
   - ".scad"
-  tm_scope: none
+  tm_scope: source.scad
   ace_mode: scad
   language_id: 266
+OpenType Feature File:
+  type: data
+  aliases:
+  - AFDKO
+  extensions:
+  - ".fea"
+  tm_scope: source.opentype
+  ace_mode: text
+  language_id: 374317347
 Org:
   type: prose
   wrap: true
@@ -2989,6 +3007,14 @@ Oz:
   codemirror_mode: oz
   codemirror_mime_type: text/x-oz
   language_id: 270
+P4:
+  type: programming
+  color: "#7055b5"
+  extensions:
+  - ".p4"
+  tm_scope: source.p4
+  ace_mode: text
+  language_id: 348895984
 PAWN:
   type: programming
   color: "#dbb284"
@@ -3017,6 +3043,8 @@ PHP:
   - ".phps"
   - ".phpt"
   filenames:
+  - ".php_cs"
+  - ".php_cs.dist"
   - Phakefile
   interpreters:
   - php
@@ -3032,12 +3060,21 @@ PLSQL:
   color: "#dad8d8"
   extensions:
   - ".pls"
+  - ".bdy"
+  - ".ddl"
+  - ".fnc"
   - ".pck"
   - ".pkb"
   - ".pks"
   - ".plb"
   - ".plsql"
+  - ".prc"
+  - ".spc"
   - ".sql"
+  - ".tpb"
+  - ".tps"
+  - ".trg"
+  - ".vw"
   language_id: 273
 PLpgSQL:
   type: programming
@@ -3171,8 +3208,8 @@ Perl6:
   language_id: 283
 Pic:
   type: markup
-  group: Groff
-  tm_scope: "source.pic"
+  group: Roff
+  tm_scope: source.pic
   extensions:
   - ".pic"
   - ".chem"
@@ -3264,6 +3301,7 @@ PowerBuilder:
   language_id: 292
 PowerShell:
   type: programming
+  color: "#012456"
   ace_mode: powershell
   codemirror_mode: powershell
   codemirror_mime_type: application/x-powershell
@@ -3325,6 +3363,17 @@ Public Key:
   codemirror_mode: asciiarmor
   codemirror_mime_type: application/pgp
   language_id: 298
+Pug:
+  group: HTML
+  type: markup
+  extensions:
+  - ".jade"
+  - ".pug"
+  tm_scope: text.jade
+  ace_mode: jade
+  codemirror_mode: pug
+  codemirror_mime_type: text/x-pug
+  language_id: 179
 Puppet:
   type: programming
   color: "#302B6D"
@@ -3376,8 +3425,11 @@ Python:
   - ".cgi"
   - ".fcgi"
   - ".gyp"
+  - ".gypi"
   - ".lmi"
+  - ".py3"
   - ".pyde"
+  - ".pyi"
   - ".pyp"
   - ".pyt"
   - ".pyw"
@@ -3387,11 +3439,13 @@ Python:
   - ".wsgi"
   - ".xpy"
   filenames:
+  - ".gclient"
   - BUCK
   - BUILD
   - SConscript
   - SConstruct
   - Snakefile
+  - WORKSPACE
   - wscript
   interpreters:
   - python
@@ -3554,7 +3608,7 @@ Racket:
   tm_scope: source.racket
   ace_mode: lisp
   language_id: 316
-Ragel in Ruby Host:
+Ragel:
   type: programming
   color: "#9d5200"
   extensions:
@@ -3565,9 +3619,16 @@ Ragel in Ruby Host:
   tm_scope: none
   ace_mode: text
   language_id: 317
+Rascal:
+  type: programming
+  color: "#fffaa0"
+  extensions:
+  - ".rsc"
+  tm_scope: source.rascal
+  ace_mode: text
+  language_id: 173616037
 Raw token data:
   type: data
-  search_term: raw
   aliases:
   - raw
   extensions:
@@ -3575,6 +3636,19 @@ Raw token data:
   tm_scope: none
   ace_mode: text
   language_id: 318
+Reason:
+  type: programming
+  group: OCaml
+  ace_mode: rust
+  codemirror_mode: rust
+  codemirror_mime_type: text/x-rustsrc
+  extensions:
+  - ".re"
+  - ".rei"
+  interpreters:
+  - ocaml
+  tm_scope: source.reason
+  language_id: 869538413
 Rebol:
   type: programming
   color: "#358a5b"
@@ -3605,6 +3679,17 @@ Redcode:
   tm_scope: none
   ace_mode: text
   language_id: 321
+Regular Expression:
+  type: data
+  extensions:
+  - ".regexp"
+  - ".regex"
+  aliases:
+  - regexp
+  - regex
+  ace_mode: text
+  tm_scope: source.regexp
+  language_id: 363378884
 Ren'Py:
   type: programming
   aliases:
@@ -3630,6 +3715,44 @@ RobotFramework:
   tm_scope: text.robot
   ace_mode: text
   language_id: 324
+Roff:
+  type: markup
+  color: "#ecdebe"
+  extensions:
+  - ".man"
+  - ".1"
+  - ".1in"
+  - ".1m"
+  - ".1x"
+  - ".2"
+  - ".3"
+  - ".3in"
+  - ".3m"
+  - ".3qt"
+  - ".3x"
+  - ".4"
+  - ".5"
+  - ".6"
+  - ".7"
+  - ".8"
+  - ".9"
+  - ".l"
+  - ".me"
+  - ".ms"
+  - ".n"
+  - ".rno"
+  - ".roff"
+  - ".tmac"
+  filenames:
+  - mmn
+  - mmt
+  tm_scope: text.roff
+  aliases:
+  - nroff
+  ace_mode: text
+  codemirror_mode: troff
+  codemirror_mime_type: text/troff
+  language_id: 141
 Rouge:
   type: programming
   ace_mode: clojure
@@ -3655,10 +3778,10 @@ Ruby:
   extensions:
   - ".rb"
   - ".builder"
+  - ".eye"
   - ".fcgi"
   - ".gemspec"
   - ".god"
-  - ".irbrc"
   - ".jbuilder"
   - ".mspec"
   - ".pluginspec"
@@ -3680,11 +3803,13 @@ Ruby:
   - jruby
   - rbx
   filenames:
+  - ".irbrc"
   - ".pryrc"
   - Appraisals
   - Berksfile
   - Brewfile
   - Buildfile
+  - Dangerfile
   - Deliverfile
   - Fastfile
   - Gemfile
@@ -3694,6 +3819,7 @@ Ruby:
   - Mavenfile
   - Podfile
   - Puppetfile
+  - Rakefile
   - Snapfile
   - Thorfile
   - Vagrantfile
@@ -3778,6 +3904,7 @@ SQL:
   - ".cql"
   - ".ddl"
   - ".inc"
+  - ".mysql"
   - ".prc"
   - ".tab"
   - ".udf"
@@ -3911,9 +4038,15 @@ Self:
   tm_scope: none
   ace_mode: text
   language_id: 345
+ShaderLab:
+  type: programming
+  extensions:
+  - ".shader"
+  ace_mode: text
+  tm_scope: source.shaderlab
+  language_id: 664257356
 Shell:
   type: programming
-  search_term: bash
   color: "#89e051"
   aliases:
   - sh
@@ -4026,6 +4159,13 @@ SourcePawn:
   tm_scope: source.sp
   ace_mode: text
   language_id: 354
+Spline Font Database:
+  type: data
+  extensions:
+  - ".sfd"
+  tm_scope: text.sfd
+  ace_mode: yaml
+  language_id: 767169629
 Squirrel:
   type: programming
   color: "#800000"
@@ -4256,11 +4396,16 @@ Text:
   - ".no"
   filenames:
   - COPYING
+  - COPYRIGHT.regex
+  - FONTLOG
   - INSTALL
+  - INSTALL.mysql
   - LICENSE
+  - LICENSE.mysql
   - NEWS
   - README.1ST
   - README.me
+  - README.mysql
   - click.me
   - delete.me
   - keep.me
@@ -4351,6 +4496,15 @@ Unity3D Asset:
   - ".unity"
   tm_scope: source.yaml
   language_id: 380
+Unix Assembly:
+  type: programming
+  group: Assembly
+  extensions:
+  - ".s"
+  - ".ms"
+  tm_scope: source.assembly
+  ace_mode: assembly_x86
+  language_id: 120
 Uno:
   type: programming
   extensions:
@@ -4423,13 +4577,13 @@ Verilog:
   codemirror_mode: verilog
   codemirror_mime_type: text/x-verilog
   language_id: 387
-VimL:
+Vim script:
   type: programming
   color: "#199f4b"
-  search_term: vim
   tm_scope: source.viml
   aliases:
   - vim
+  - viml
   - nvim
   extensions:
   - ".vim"
@@ -4538,6 +4692,15 @@ XC:
   codemirror_mode: clike
   codemirror_mime_type: text/x-csrc
   language_id: 398
+XCompose:
+  type: data
+  filenames:
+  - ".XCompose"
+  - XCompose
+  - xcompose
+  tm_scope: config.xcompose
+  ace_mode: text
+  language_id: 225167241
 XML:
   type: data
   ace_mode: xml
@@ -4549,6 +4712,8 @@ XML:
   - wsdl
   extensions:
   - ".xml"
+  - ".adml"
+  - ".admx"
   - ".ant"
   - ".axml"
   - ".builds"
@@ -4576,6 +4741,7 @@ XML:
   - ".kml"
   - ".launch"
   - ".mdpolicy"
+  - ".mjml"
   - ".mm"
   - ".mod"
   - ".mxml"
@@ -4614,8 +4780,11 @@ XML:
   - ".ux"
   - ".vbproj"
   - ".vcxproj"
+  - ".vsixmanifest"
   - ".vssettings"
+  - ".vstemplate"
   - ".vxml"
+  - ".wixproj"
   - ".wsdl"
   - ".wsf"
   - ".wxi"
@@ -4731,6 +4900,7 @@ YAML:
   - ".syntax"
   - ".yaml"
   - ".yaml-tmlanguage"
+  - ".yml.mysql"
   filenames:
   - ".clang-format"
   ace_mode: yaml
@@ -4782,7 +4952,6 @@ desktop:
 eC:
   type: programming
   color: "#913960"
-  search_term: ec
   extensions:
   - ".ec"
   - ".eh"
@@ -4832,7 +5001,6 @@ ooc:
 reStructuredText:
   type: prose
   wrap: true
-  search_term: rst
   aliases:
   - rst
   extensions:

lib/linguist/popular.yml

@@ -26,4 +26,4 @@
 - Shell
 - Swift
 - TeX
-- VimL
+- Vim script

lib/linguist/strategy/extension.rb

@@ -0,0 +1,10 @@
+module Linguist
+  module Strategy
+    # Detects language based on extension
+    class Extension
+      def self.call(blob, _)
+        Language.find_by_extension(blob.name.to_s)
+      end
+    end
+  end
+end

lib/linguist/strategy/filename.rb

@@ -1,9 +1,10 @@
 module Linguist
   module Strategy
-    # Detects language based on filename and/or extension
+    # Detects language based on filename
     class Filename
       def self.call(blob, _)
-        Language.find_by_filename(blob.name.to_s)
+        name = blob.name.to_s
+        Language.find_by_filename(name)
       end
     end
   end

lib/linguist/vendor.yml

@@ -50,6 +50,9 @@
 # Go dependencies
 - Godeps/_workspace/
 
+# GNU indent profiles
+- .indent.pro
+
 # Minified JavaScript and CSS
 - (\.|-)min\.(js|css)$
 
@@ -235,6 +238,12 @@
 # BuddyBuild
 - BuddyBuildSDK.framework/
 
+# Realm
+- Realm.framework
+
+# RealmSwift
+- RealmSwift.framework
+
 # git config files
 - gitattributes$
 - gitignore$

lib/linguist/version.rb

@@ -1,3 +1,3 @@
 module Linguist
-  VERSION = "4.8.16"
+  VERSION = "5.0.9"
 end

samples/C++/bug1163046.--skeleton.re

@@ -0,0 +1,46 @@
+#include <iostream>
+
+#define YYCTYPE unsigned char
+#define YYCURSOR cursor
+#define YYLIMIT cursor
+#define YYMARKER marker
+#define YYFILL(n)
+
+bool scan(const char *text)
+{
+	YYCTYPE *start = (YYCTYPE *)text;
+	YYCTYPE *cursor = (YYCTYPE *)text;
+	YYCTYPE *marker = (YYCTYPE *)text;
+next:
+	YYCTYPE *token = cursor;
+/*!re2c
+'(This file must be converted with BinHex 4.0)'
+	{
+		if (token == start || *(token - 1) == '\n')
+		return true; else goto next;
+	}
+[\001-\377]
+	{ goto next; }
+[\000]
+	{ return false; }
+*/
+	return false;
+}
+
+#define do_scan(str, expect) \
+	res = scan(str) == expect ? 0 : 1; \
+	std::cerr << str << "\t-\t" << (res ? "fail" : "ok") << std::endl; \
+	result += res
+
+/*!max:re2c */
+
+int main(int,void**)
+{
+	int res, result = 0;
+	do_scan("(This file must be converted with BinHex 4.0)", 1);
+	do_scan("x(This file must be converted with BinHex 4.0)", 0);
+	do_scan("(This file must be converted with BinHex 4.0)x", 1);
+	do_scan("x(This file must be converted with BinHex 4.0)x", 0);
+	
+	return result;
+}

samples/C++/cnokw.re

@@ -0,0 +1,239 @@
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+
+#define	ADDEQ	257
+#define	ANDAND	258
+#define	ANDEQ	259
+#define	ARRAY	260
+#define	ASM	261
+#define	AUTO	262
+#define	BREAK	263
+#define	CASE	264
+#define	CHAR	265
+#define	CONST	266
+#define	CONTINUE	267
+#define	DECR	268
+#define	DEFAULT	269
+#define	DEREF	270
+#define	DIVEQ	271
+#define	DO	272
+#define	DOUBLE	273
+#define	ELLIPSIS	274
+#define	ELSE	275
+#define	ENUM	276
+#define	EQL	277
+#define	EXTERN	278
+#define	FCON	279
+#define	FLOAT	280
+#define	FOR	281
+#define	FUNCTION	282
+#define	GEQ	283
+#define	GOTO	284
+#define	ICON	285
+#define	ID	286
+#define	IF	287
+#define	INCR	288
+#define	INT	289
+#define	LEQ	290
+#define	LONG	291
+#define	LSHIFT	292
+#define	LSHIFTEQ	293
+#define	MODEQ	294
+#define	MULEQ	295
+#define	NEQ	296
+#define	OREQ	297
+#define	OROR	298
+#define	POINTER	299
+#define	REGISTER	300
+#define	RETURN	301
+#define	RSHIFT	302
+#define	RSHIFTEQ	303
+#define	SCON	304
+#define	SHORT	305
+#define	SIGNED	306
+#define	SIZEOF	307
+#define	STATIC	308
+#define	STRUCT	309
+#define	SUBEQ	310
+#define	SWITCH	311
+#define	TYPEDEF	312
+#define	UNION	313
+#define	UNSIGNED	314
+#define	VOID	315
+#define	VOLATILE	316
+#define	WHILE	317
+#define	XOREQ	318
+#define	EOI	319
+
+typedef unsigned int uint;
+typedef unsigned char uchar;
+
+#define	BSIZE	8192
+
+#define	YYCTYPE		uchar
+#define	YYCURSOR	cursor
+#define	YYLIMIT		s->lim
+#define	YYMARKER	s->ptr
+#define	YYFILL(n)	{cursor = fill(s, cursor);}
+
+#define	RET(i)	{s->cur = cursor; return i;}
+
+typedef struct Scanner {
+    int			fd;
+    uchar		*bot, *tok, *ptr, *cur, *pos, *lim, *top, *eof;
+    uint		line;
+} Scanner;
+
+uchar *fill(Scanner *s, uchar *cursor){
+    if(!s->eof){
+	uint cnt = s->tok - s->bot;
+	if(cnt){
+	    memcpy(s->bot, s->tok, s->lim - s->tok);
+	    s->tok = s->bot;
+	    s->ptr -= cnt;
+	    cursor -= cnt;
+	    s->pos -= cnt;
+	    s->lim -= cnt;
+	}
+	if((s->top - s->lim) < BSIZE){
+	    uchar *buf = (uchar*) malloc(((s->lim - s->bot) + BSIZE)*sizeof(uchar));
+	    memcpy(buf, s->tok, s->lim - s->tok);
+	    s->tok = buf;
+	    s->ptr = &buf[s->ptr - s->bot];
+	    cursor = &buf[cursor - s->bot];
+	    s->pos = &buf[s->pos - s->bot];
+	    s->lim = &buf[s->lim - s->bot];
+	    s->top = &s->lim[BSIZE];
+	    free(s->bot);
+	    s->bot = buf;
+	}
+	if((cnt = read(s->fd, (char*) s->lim, BSIZE)) != BSIZE){
+	    s->eof = &s->lim[cnt]; *(s->eof)++ = '\n';
+	}
+	s->lim += cnt;
+    }
+    return cursor;
+}
+
+int scan(Scanner *s){
+	uchar *cursor = s->cur;
+std:
+	s->tok = cursor;
+/*!re2c
+any	= [\000-\377];
+O	= [0-7];
+D	= [0-9];
+L	= [a-zA-Z_];
+H	= [a-fA-F0-9];
+E	= [Ee] [+-]? D+;
+FS	= [fFlL];
+IS	= [uUlL]*;
+ESC	= [\\] ([abfnrtv?'"\\] | "x" H+ | O+);
+*/
+
+/*!re2c
+	"/*"			{ goto comment; }
+	
+	L (L|D)*		{ RET(ID); }
+	
+	("0" [xX] H+ IS?) | ("0" D+ IS?) | (D+ IS?) |
+	(['] (ESC|any\[\n\\'])* ['])
+				{ RET(ICON); }
+	
+	(D+ E FS?) | (D* "." D+ E? FS?) | (D+ "." D* E? FS?)
+				{ RET(FCON); }
+	
+	(["] (ESC|any\[\n\\"])* ["])
+				{ RET(SCON); }
+	
+	"..."                   { RET(ELLIPSIS); }
+	">>="			{ RET(RSHIFTEQ); }
+	"<<="			{ RET(LSHIFTEQ); }
+	"+="			{ RET(ADDEQ); }
+	"-="			{ RET(SUBEQ); }
+	"*="			{ RET(MULEQ); }
+	"/="			{ RET(DIVEQ); }
+	"%="			{ RET(MODEQ); }
+	"&="			{ RET(ANDEQ); }
+	"^="			{ RET(XOREQ); }
+	"|="			{ RET(OREQ); }
+	">>"			{ RET(RSHIFT); }
+	"<<"			{ RET(LSHIFT); }
+	"++"			{ RET(INCR); }
+	"--"			{ RET(DECR); }
+	"->"			{ RET(DEREF); }
+	"&&"			{ RET(ANDAND); }
+	"||"			{ RET(OROR); }
+	"<="			{ RET(LEQ); }
+	">="			{ RET(GEQ); }
+	"=="			{ RET(EQL); }
+	"!="			{ RET(NEQ); }
+	";"			{ RET(';'); }
+	"{"			{ RET('{'); }
+	"}"			{ RET('}'); }
+	","			{ RET(','); }
+	":"			{ RET(':'); }
+	"="			{ RET('='); }
+	"("			{ RET('('); }
+	")"			{ RET(')'); }
+	"["			{ RET('['); }
+	"]"			{ RET(']'); }
+	"."			{ RET('.'); }
+	"&"			{ RET('&'); }
+	"!"			{ RET('!'); }
+	"~"			{ RET('~'); }
+	"-"			{ RET('-'); }
+	"+"			{ RET('+'); }
+	"*"			{ RET('*'); }
+	"/"			{ RET('/'); }
+	"%"			{ RET('%'); }
+	"<"			{ RET('<'); }
+	">"			{ RET('>'); }
+	"^"			{ RET('^'); }
+	"|"			{ RET('|'); }
+	"?"			{ RET('?'); }
+
+
+	[ \t\v\f]+		{ goto std; }
+
+	"\n"
+	    {
+		if(cursor == s->eof) RET(EOI);
+		s->pos = cursor; s->line++;
+		goto std;
+	    }
+
+	any
+	    {
+		printf("unexpected character: %c\n", *s->tok);
+		goto std;
+	    }
+*/
+
+comment:
+/*!re2c
+	"*/"			{ goto std; }
+	"\n"
+	    {
+		if(cursor == s->eof) RET(EOI);
+		s->tok = s->pos = cursor; s->line++;
+		goto comment;
+	    }
+        any			{ goto comment; }
+*/
+}
+
+main(){
+    Scanner in;
+    int t;
+    memset((char*) &in, 0, sizeof(in));
+    in.fd = 0;
+    while((t = scan(&in)) != EOI){
+/*
+	printf("%d\t%.*s\n", t, in.cur - in.tok, in.tok);
+	printf("%d\n", t);
+*/
+    }
+    close(in.fd);
+}

samples/C++/cvsignore.re

@@ -0,0 +1,63 @@
+
+#define YYFILL(n) if (cursor >= limit) break;
+#define YYCTYPE char
+#define YYCURSOR cursor
+#define YYLIMIT limit
+#define YYMARKER marker
+
+/*!re2c
+any     = (.|"\n");
+value	= (":" (.\"$")+)?;
+cvsdat	= "Date";
+cvsid	= "Id";
+cvslog	= "Log";
+cvsrev	= "Revision";
+cvssrc	= "Source";
+*/
+
+#define APPEND(text) \
+	append(output, outsize, text, sizeof(text) - sizeof(YYCTYPE))
+
+inline void append(YYCTYPE *output, size_t & outsize, const YYCTYPE * text, size_t len)
+{
+	memcpy(output + outsize, text, len);
+	outsize += (len / sizeof(YYCTYPE));
+}
+
+void scan(YYCTYPE *pText, size_t *pSize, int *pbChanged)
+{
+	// rule
+	// scan lines
+	// find $ in lines
+	//   compact $<keyword>: .. $ to $<keyword>$
+  
+	YYCTYPE *output;
+	const YYCTYPE *cursor, *limit, *marker;
+
+	cursor = marker = output = *pText;
+
+	size_t insize = *pSize;
+	size_t outsize = 0;
+
+	limit = cursor + insize;
+
+	while(1) {
+loop:
+/*!re2c
+
+"$" cvsdat value "$"	{ APPEND(L"$" L"Date$"); goto loop; }
+"$" cvsid  value "$"	{ APPEND(L"$" L"Id$"); goto loop; }
+"$" cvslog value "$"	{ APPEND(L"$" L"Log$"); goto loop; }
+"$" cvsrev value "$"	{ APPEND(L"$" L"Revision$"); goto loop; }
+"$" cvssrc value "$"	{ APPEND(L"$" L"Source$"); goto loop; }
+any						{ output[outsize++] = cursor[-1]; if (cursor >= limit) break; goto loop; }
+
+*/
+	}
+	output[outsize] = '\0';
+
+	// set the new size
+	*pSize = outsize;
+	
+	*pbChanged = (insize == outsize) ? 0 : 1;
+}

samples/C++/simple.re

@@ -0,0 +1,13 @@
+#define	NULL		((char*) 0)
+char *scan(char *p){
+char *q;
+#define	YYCTYPE		char
+#define	YYCURSOR	p
+#define	YYLIMIT		p
+#define	YYMARKER	q
+#define	YYFILL(n)
+/*!re2c
+	[0-9]+		{return YYCURSOR;}
+	[\000-\377]	{return NULL;}
+*/
+}

samples/D/aa.d

@@ -0,0 +1,440 @@
+/**
+ * Implementation of associative arrays.
+ *
+ * Copyright: Martin Nowak 2015 -.
+ * License:   $(LINK2 http://www.boost.org/LICENSE_1_0.txt, Boost License 1.0)
+ * Authors:   Martin Nowak
+ */
+module core.aa;
+
+import core.memory : GC;
+
+private
+{
+    // grow threshold
+    enum GROW_NUM = 4;
+    enum GROW_DEN = 5;
+    // shrink threshold
+    enum SHRINK_NUM = 1;
+    enum SHRINK_DEN = 8;
+    // grow factor
+    enum GROW_FAC = 4;
+    // growing the AA doubles it's size, so the shrink threshold must be
+    // smaller than half the grow threshold to have a hysteresis
+    static assert(GROW_FAC * SHRINK_NUM * GROW_DEN < GROW_NUM * SHRINK_DEN);
+    // initial load factor (for literals), mean of both thresholds
+    enum INIT_NUM = (GROW_DEN * SHRINK_NUM + GROW_NUM * SHRINK_DEN) / 2;
+    enum INIT_DEN = SHRINK_DEN * GROW_DEN;
+
+    // magic hash constants to distinguish empty, deleted, and filled buckets
+    enum HASH_EMPTY = 0;
+    enum HASH_DELETED = 0x1;
+    enum HASH_FILLED_MARK = size_t(1) << 8 * size_t.sizeof - 1;
+}
+
+enum INIT_NUM_BUCKETS = 8;
+
+struct AA(Key, Val)
+{
+    this(size_t sz)
+    {
+        impl = new Impl(nextpow2(sz));
+    }
+
+    @property bool empty() const pure nothrow @safe @nogc
+    {
+        return !length;
+    }
+
+    @property size_t length() const pure nothrow @safe @nogc
+    {
+        return impl is null ? 0 : impl.length;
+    }
+
+    void opIndexAssign(Val val, in Key key)
+    {
+        // lazily alloc implementation
+        if (impl is null)
+            impl = new Impl(INIT_NUM_BUCKETS);
+
+        // get hash and bucket for key
+        immutable hash = calcHash(key);
+
+        // found a value => assignment
+        if (auto p = impl.findSlotLookup(hash, key))
+        {
+            p.entry.val = val;
+            return;
+        }
+
+        auto p = findSlotInsert(hash);
+        if (p.deleted)
+            --deleted;
+        // check load factor and possibly grow
+        else if (++used * GROW_DEN > dim * GROW_NUM)
+        {
+            grow();
+            p = findSlotInsert(hash);
+            assert(p.empty);
+        }
+
+        // update search cache and allocate entry
+        firstUsed = min(firstUsed, cast(uint)(p - buckets.ptr));
+        p.hash = hash;
+        p.entry = new Impl.Entry(key, val); // TODO: move
+        return;
+    }
+
+    ref inout(Val) opIndex(in Key key) inout @trusted
+    {
+        auto p = opIn_r(key);
+        assert(p !is null);
+        return *p;
+    }
+
+    inout(Val)* opIn_r(in Key key) inout @trusted
+    {
+        if (empty)
+            return null;
+
+        immutable hash = calcHash(key);
+        if (auto p = findSlotLookup(hash, key))
+            return &p.entry.val;
+        return null;
+    }
+
+    bool remove(in Key key)
+    {
+        if (empty)
+            return false;
+
+        immutable hash = calcHash(key);
+        if (auto p = findSlotLookup(hash, key))
+        {
+            // clear entry
+            p.hash = HASH_DELETED;
+            p.entry = null;
+
+            ++deleted;
+            if (length * SHRINK_DEN < dim * SHRINK_NUM)
+                shrink();
+
+            return true;
+        }
+        return false;
+    }
+
+    Val get(in Key key, lazy Val val)
+    {
+        auto p = opIn_r(key);
+        return p is null ? val : *p;
+    }
+
+    ref Val getOrSet(in Key key, lazy Val val)
+    {
+        // lazily alloc implementation
+        if (impl is null)
+            impl = new Impl(INIT_NUM_BUCKETS);
+
+        // get hash and bucket for key
+        immutable hash = calcHash(key);
+
+        // found a value => assignment
+        if (auto p = impl.findSlotLookup(hash, key))
+            return p.entry.val;
+
+        auto p = findSlotInsert(hash);
+        if (p.deleted)
+            --deleted;
+        // check load factor and possibly grow
+        else if (++used * GROW_DEN > dim * GROW_NUM)
+        {
+            grow();
+            p = findSlotInsert(hash);
+            assert(p.empty);
+        }
+
+        // update search cache and allocate entry
+        firstUsed = min(firstUsed, cast(uint)(p - buckets.ptr));
+        p.hash = hash;
+        p.entry = new Impl.Entry(key, val);
+        return p.entry.val;
+    }
+
+    /**
+       Convert the AA to the type of the builtin language AA.
+     */
+    Val[Key] toBuiltinAA() pure nothrow
+    {
+        return cast(Val[Key]) _aaFromCoreAA(impl, rtInterface);
+    }
+
+private:
+
+    private this(inout(Impl)* impl) inout
+    {
+        this.impl = impl;
+    }
+
+    ref Val getLValue(in Key key)
+    {
+        // lazily alloc implementation
+        if (impl is null)
+            impl = new Impl(INIT_NUM_BUCKETS);
+
+        // get hash and bucket for key
+        immutable hash = calcHash(key);
+
+        // found a value => assignment
+        if (auto p = impl.findSlotLookup(hash, key))
+            return p.entry.val;
+
+        auto p = findSlotInsert(hash);
+        if (p.deleted)
+            --deleted;
+        // check load factor and possibly grow
+        else if (++used * GROW_DEN > dim * GROW_NUM)
+        {
+            grow();
+            p = findSlotInsert(hash);
+            assert(p.empty);
+        }
+
+        // update search cache and allocate entry
+        firstUsed = min(firstUsed, cast(uint)(p - buckets.ptr));
+        p.hash = hash;
+        p.entry = new Impl.Entry(key); // TODO: move
+        return p.entry.val;
+    }
+
+    static struct Impl
+    {
+        this(size_t sz)
+        {
+            buckets = allocBuckets(sz);
+        }
+
+        @property size_t length() const pure nothrow @nogc
+        {
+            assert(used >= deleted);
+            return used - deleted;
+        }
+
+        @property size_t dim() const pure nothrow @nogc
+        {
+            return buckets.length;
+        }
+
+        @property size_t mask() const pure nothrow @nogc
+        {
+            return dim - 1;
+        }
+
+        // find the first slot to insert a value with hash
+        inout(Bucket)* findSlotInsert(size_t hash) inout pure nothrow @nogc
+        {
+            for (size_t i = hash & mask, j = 1;; ++j)
+            {
+                if (!buckets[i].filled)
+                    return &buckets[i];
+                i = (i + j) & mask;
+            }
+        }
+
+        // lookup a key
+        inout(Bucket)* findSlotLookup(size_t hash, in Key key) inout
+        {
+            for (size_t i = hash & mask, j = 1;; ++j)
+            {
+                if (buckets[i].hash == hash && key == buckets[i].entry.key)
+                    return &buckets[i];
+                else if (buckets[i].empty)
+                    return null;
+                i = (i + j) & mask;
+            }
+        }
+
+        void grow()
+        {
+            // If there are so many deleted entries, that growing would push us
+            // below the shrink threshold, we just purge deleted entries instead.
+            if (length * SHRINK_DEN < GROW_FAC * dim * SHRINK_NUM)
+                resize(dim);
+            else
+                resize(GROW_FAC * dim);
+        }
+
+        void shrink()
+        {
+            if (dim > INIT_NUM_BUCKETS)
+                resize(dim / GROW_FAC);
+        }
+
+        void resize(size_t ndim) pure nothrow
+        {
+            auto obuckets = buckets;
+            buckets = allocBuckets(ndim);
+
+            foreach (ref b; obuckets)
+                if (b.filled)
+                    *findSlotInsert(b.hash) = b;
+
+            firstUsed = 0;
+            used -= deleted;
+            deleted = 0;
+            GC.free(obuckets.ptr); // safe to free b/c impossible to reference
+        }
+
+        static struct Entry
+        {
+            Key key;
+            Val val;
+        }
+
+        static struct Bucket
+        {
+            size_t hash;
+            Entry* entry;
+
+            @property bool empty() const
+            {
+                return hash == HASH_EMPTY;
+            }
+
+            @property bool deleted() const
+            {
+                return hash == HASH_DELETED;
+            }
+
+            @property bool filled() const
+            {
+                return cast(ptrdiff_t) hash < 0;
+            }
+        }
+
+        Bucket[] allocBuckets(size_t dim) @trusted pure nothrow
+        {
+            enum attr = GC.BlkAttr.NO_INTERIOR;
+            immutable sz = dim * Bucket.sizeof;
+            return (cast(Bucket*) GC.calloc(sz, attr))[0 .. dim];
+        }
+
+        Bucket[] buckets;
+        uint used;
+        uint deleted;
+        uint firstUsed;
+    }
+
+    RTInterface* rtInterface()() pure nothrow @nogc
+    {
+        static size_t aaLen(in void* pimpl) pure nothrow @nogc
+        {
+            auto aa = const(AA)(cast(const(Impl)*) pimpl);
+            return aa.length;
+        }
+
+        static void* aaGetY(void** pimpl, in void* pkey)
+        {
+            auto aa = AA(cast(Impl*)*pimpl);
+            auto res = &aa.getLValue(*cast(const(Key*)) pkey);
+            *pimpl = aa.impl; // might have changed
+            return res;
+        }
+
+        static inout(void)* aaInX(inout void* pimpl, in void* pkey)
+        {
+            auto aa = inout(AA)(cast(inout(Impl)*) pimpl);
+            return aa.opIn_r(*cast(const(Key*)) pkey);
+        }
+
+        static bool aaDelX(void* pimpl, in void* pkey)
+        {
+            auto aa = AA(cast(Impl*) pimpl);
+            return aa.remove(*cast(const(Key*)) pkey);
+        }
+
+        static immutable vtbl = RTInterface(&aaLen, &aaGetY, &aaInX, &aaDelX);
+        return cast(RTInterface*)&vtbl;
+    }
+
+    static size_t calcHash(in ref Key key)
+    {
+        return hashOf(key) | HASH_FILLED_MARK;
+    }
+
+    Impl* impl;
+    alias impl this;
+}
+
+package extern (C) void* _aaFromCoreAA(void* impl, RTInterface* rtIntf) pure nothrow;
+
+private:
+
+struct RTInterface
+{
+    alias AA = void*;
+
+    size_t function(in AA aa) pure nothrow @nogc len;
+    void* function(AA* aa, in void* pkey) getY;
+    inout(void)* function(inout AA aa, in void* pkey) inX;
+    bool function(AA aa, in void* pkey) delX;
+}
+
+unittest
+{
+    AA!(int, int) aa;
+    assert(aa.length == 0);
+    aa[0] = 1;
+    assert(aa.length == 1 && aa[0] == 1);
+    aa[1] = 2;
+    assert(aa.length == 2 && aa[1] == 2);
+    import core.stdc.stdio;
+
+    int[int] rtaa = aa.toBuiltinAA();
+    assert(rtaa.length == 2);
+    puts("length");
+    assert(rtaa[0] == 1);
+    assert(rtaa[1] == 2);
+    rtaa[2] = 3;
+
+    assert(aa[2] == 3);
+}
+
+unittest
+{
+    auto aa = AA!(int, int)(3);
+    aa[0] = 0;
+    aa[1] = 1;
+    aa[2] = 2;
+    assert(aa.length == 3);
+}
+
+//==============================================================================
+// Helper functions
+//------------------------------------------------------------------------------
+
+size_t nextpow2(in size_t n) pure nothrow @nogc
+{
+    import core.bitop : bsr;
+
+    if (n < 2)
+        return 1;
+    return size_t(1) << bsr(n - 1) + 1;
+}
+
+pure nothrow @nogc unittest
+{
+    //                            0, 1, 2, 3, 4, 5, 6, 7, 8,  9
+    foreach (const n, const pow2; [1, 1, 2, 4, 4, 8, 8, 8, 8, 16])
+        assert(nextpow2(n) == pow2);
+}
+
+T min(T)(T a, T b) pure nothrow @nogc
+{
+    return a < b ? a : b;
+}
+
+T max(T)(T a, T b) pure nothrow @nogc
+{
+    return b < a ? a : b;
+}

samples/D/arrayops.d

@@ -0,0 +1,187 @@
+/**
+ * Benchmark for array ops.
+ *
+ * Copyright: Copyright Martin Nowak 2016 -.
+ * License:   $(LINK2 http://www.boost.org/LICENSE_1_0.txt, Boost License 1.0)
+ * Authors:   Martin Nowak
+ */
+import core.cpuid, std.algorithm, std.datetime, std.meta, std.stdio, std.string,
+    std.range;
+
+float[6] getLatencies(T, string op)()
+{
+    enum N = (64 * (1 << 6) + 64) * T.sizeof;
+    auto a = Array!T(N), b = Array!T(N), c = Array!T(N);
+    float[6] latencies = float.max;
+    foreach (i, ref latency; latencies)
+    {
+        auto len = 1 << i;
+        foreach (_; 1 .. 32)
+        {
+            a[] = 24;
+            b[] = 4;
+            c[] = 2;
+            auto sw = StopWatch(AutoStart.yes);
+            foreach (off; size_t(0) .. size_t(64))
+            {
+                off = off * len + off;
+                enum op = op.replace("const", "2").replace("a",
+                        "a[off .. off + len]").replace("b",
+                        "b[off .. off + len]").replace("c", "c[off .. off + len]");
+                mixin(op ~ ";");
+            }
+            latency = min(latency, sw.peek.nsecs);
+        }
+    }
+    float[6] res = latencies[] / 1024;
+    return res;
+}
+
+float[4] getThroughput(T, string op)()
+{
+    enum N = (40 * 1024 * 1024 + 64 * T.sizeof) / T.sizeof;
+    auto a = Array!T(N), b = Array!T(N), c = Array!T(N);
+    float[4] latencies = float.max;
+    size_t[4] lengths = [
+        8 * 1024 / T.sizeof, 32 * 1024 / T.sizeof, 512 * 1024 / T.sizeof, 32 * 1024 * 1024 / T
+        .sizeof
+    ];
+    foreach (i, ref latency; latencies)
+    {
+        auto len = lengths[i] / 64;
+        foreach (_; 1 .. 4)
+        {
+            a[] = 24;
+            b[] = 4;
+            c[] = 2;
+            auto sw = StopWatch(AutoStart.yes);
+            foreach (off; size_t(0) .. size_t(64))
+            {
+                off = off * len + off;
+                enum op = op.replace("const", "2").replace("a",
+                        "a[off .. off + len]").replace("b",
+                        "b[off .. off + len]").replace("c", "c[off .. off + len]");
+                mixin(op ~ ";");
+            }
+            immutable nsecs = sw.peek.nsecs;
+            runMasked({latency = min(latency, nsecs);});
+        }
+    }
+    float[4] throughputs = void;
+    runMasked({throughputs = T.sizeof * lengths[] / latencies[];});
+    return throughputs;
+}
+
+string[] genOps()
+{
+    string[] ops;
+    foreach (op1; ["+", "-", "*", "/"])
+    {
+        ops ~= "a " ~ op1 ~ "= b";
+        ops ~= "a " ~ op1 ~ "= const";
+        foreach (op2; ["+", "-", "*", "/"])
+        {
+            ops ~= "a " ~ op1 ~ "= b " ~ op2 ~ " c";
+            ops ~= "a " ~ op1 ~ "= b " ~ op2 ~ " const";
+        }
+    }
+    return ops;
+}
+
+void runOp(string op)()
+{
+    foreach (T; AliasSeq!(ubyte, ushort, uint, ulong, byte, short, int, long, float,
+            double))
+        writefln("%s, %s, %(%.2f, %), %(%s, %)", T.stringof, op,
+            getLatencies!(T, op), getThroughput!(T, op));
+}
+
+struct Array(T)
+{
+    import core.stdc.stdlib : free, malloc;
+
+    this(size_t n)
+    {
+        ary = (cast(T*) malloc(T.sizeof * n))[0 .. n];
+    }
+
+    ~this()
+    {
+        free(ary.ptr);
+    }
+
+    T[] ary;
+    alias ary this;
+}
+
+version (X86)
+    version = SSE;
+else version (X86_64)
+    version = SSE;
+else
+    static assert(0, "unimplemented");
+
+version (SSE)
+{
+    uint mxcsr()
+    {
+        uint ret = void;
+        asm
+        {
+            stmxcsr ret;
+        }
+        return ret;
+    }
+
+    void mxcsr(uint val)
+    {
+        asm
+        {
+            ldmxcsr val;
+        }
+    }
+
+    // http://softpixel.com/~cwright/programming/simd/sse.php
+    enum FPU_EXCEPTION_MASKS = 1 << 12 | 1 << 11 | 1 << 10 | 1 << 9 | 1 << 8 | 1 << 7;
+    enum FPU_EXCEPTION_FLAGS = 1 << 5 | 1 << 4 | 1 << 3 | 1 << 2 | 1 << 1 | 1 << 0;
+
+    void maskFPUExceptions()
+    {
+        mxcsr = mxcsr | FPU_EXCEPTION_MASKS;
+    }
+
+    void unmaskFPUExceptions()
+    {
+        mxcsr = mxcsr & ~FPU_EXCEPTION_MASKS;
+    }
+
+    uint FPUExceptionFlags()
+    {
+        return mxcsr & FPU_EXCEPTION_FLAGS;
+    }
+
+    void clearFPUExceptionFlags()
+    {
+        mxcsr = mxcsr & ~FPU_EXCEPTION_FLAGS;
+    }
+}
+
+void runMasked(scope void delegate() dg)
+{
+    assert(FPUExceptionFlags == 0);
+    maskFPUExceptions;
+    dg();
+    clearFPUExceptionFlags;
+    unmaskFPUExceptions;
+}
+
+void main()
+{
+    unmaskFPUExceptions;
+
+    writefln("type, op, %(latency%s, %), %-(throughput%s, %)", iota(6)
+        .map!(i => 1 << i), ["8KB", "32KB", "512KB", "32MB"]);
+    foreach (op; mixin("AliasSeq!(%(%s, %))".format(genOps)))
+        runOp!op;
+    maskFPUExceptions;
+}

samples/D/function.d

@@ -0,0 +1,3 @@
+void foo()
+{
+}

samples/D/hello_world.d

@@ -0,0 +1,6 @@
+import std.stdio;
+
+void main()
+{
+    writeln("Hello World");
+}

samples/D/template.d

@@ -0,0 +1,7 @@
+template Fib(size_t N)
+{
+    static if (N < 2)
+        enum Fib = size_t(1);
+    else
+        enum Fib = Fib!(N - 2) + Fib!(N - 1);
+}

samples/D/template_function.d

@@ -0,0 +1,3 @@
+void bar(T)(T t)
+{
+}

samples/D/unittest1.d

@@ -0,0 +1,3 @@
+unittest
+{
+}

samples/D/unittest2.d

@@ -0,0 +1,3 @@
+unittest("optional name")
+{
+}

samples/Emacs Lisp/filenames/Cask

@@ -0,0 +1,9 @@
+(package "composer" "0.0.7" "Interface to PHP Composer")
+(source "melpa" "https://melpa.org/packages/")
+
+(package-file "composer.el")
+
+(depends-on "f")
+(depends-on "s")
+(depends-on "request")
+(depends-on "seq")

samples/Erlang/filenames/Emakefile

@@ -0,0 +1,7 @@
+{"src/*", [
+   report, 
+   verbose, 
+   {i, "include"}, 
+   {outdir, "ebin"},
+   debug_info 
+]}.

samples/GLSL/SyLens.shader

@@ -0,0 +1,161 @@
+#version 120
+
+/*
+  Original Lens Distortion Algorithm from SSontech (Syntheyes)
+  http://www.ssontech.com/content/lensalg.htm
+  
+  r2 is radius squared.
+  
+  r2 = image_aspect*image_aspect*u*u + v*v
+  f = 1 + r2*(k + kcube*sqrt(r2))
+  u' = f*u
+  v' = f*v
+
+*/
+
+// Controls
+uniform float kCoeff, kCube, uShift, vShift;
+uniform float chroma_red, chroma_green, chroma_blue;
+uniform bool apply_disto;
+
+// Uniform inputs
+uniform sampler2D input1;
+uniform float adsk_input1_w, adsk_input1_h, adsk_input1_aspect, adsk_input1_frameratio;
+uniform float adsk_result_w, adsk_result_h;
+
+float distortion_f(float r) {
+    float f = 1 + (r*r)*(kCoeff + kCube * r);
+    return f;
+}
+
+
+float inverse_f(float r)
+{
+    
+    // Build a lookup table on the radius, as a fixed-size table.
+    // We will use a vec3 since we will store the multipled number in the Z coordinate.
+    // So to recap: x will be the radius, y will be the f(x) distortion, and Z will be x * y;
+    vec3[48] lut;
+    
+    // Since out LUT is shader-global check if it's been computed alrite
+    // Flame has no overflow bbox so we can safely max out at the image edge, plus some cushion
+    float max_r = sqrt((adsk_input1_frameratio * adsk_input1_frameratio) + 1) + 0.1;
+    float incr = max_r / 48;
+    float lut_r = 0;
+    float f;
+    for(int i=0; i < 48; i++) {
+        f = distortion_f(lut_r);
+        lut[i] = vec3(lut_r, f, lut_r * f);
+        lut_r += incr;
+    }
+    
+    float t;
+    // Now find the nehgbouring elements
+    // only iterate to 46 since we will need
+    // 47 as i+1
+    for(int i=0; i < 47; i++) {
+        if(lut[i].z < r && lut[i+1].z > r) {
+            // BAM! our value is between these two segments
+            // get the T interpolant and mix
+            t = (r - lut[i].z) / (lut[i+1].z - lut[i]).z;
+            return mix(lut[i].y, lut[i+1].y, t );
+        }
+    }
+}
+
+float aberrate(float f, float chroma)
+{
+   return f + (f * chroma);
+}
+
+vec3 chromaticize_and_invert(float f)
+{
+   vec3 rgb_f = vec3(aberrate(f, chroma_red), aberrate(f, chroma_green), aberrate(f, chroma_blue));
+   // We need to DIVIDE by F when we redistort, and x / y == x * (1 / y)
+   if(apply_disto) {
+      rgb_f = 1 / rgb_f;
+   }
+   return rgb_f;
+}
+
+void main(void)
+{
+   vec2 px, uv;
+   float f = 1;
+   float r = 1;
+   
+   px = gl_FragCoord.xy;
+   
+   // Make sure we are still centered
+   px.x -= (adsk_result_w - adsk_input1_w) / 2;
+   px.y -= (adsk_result_h - adsk_input1_h) / 2;
+   
+   // Push the destination coordinates into the [0..1] range
+   uv.x = px.x / adsk_input1_w;
+   uv.y = px.y / adsk_input1_h;
+   
+       
+   // And to Syntheyes UV which are [1..-1] on both X and Y
+   uv.x = (uv.x *2 ) - 1;
+   uv.y = (uv.y *2 ) - 1;
+   
+   // Add UV shifts
+   uv.x += uShift;
+   uv.y += vShift;
+   
+   // Make the X value the aspect value, so that the X coordinates go to [-aspect..aspect]
+   uv.x = uv.x * adsk_input1_frameratio;
+   
+   // Compute the radius
+   r = sqrt(uv.x*uv.x + uv.y*uv.y);
+   
+   // If we are redistorting, account for the oversize plate in the input, assume that
+   // the input aspect is the same
+   if(apply_disto) {
+       r = r / (float(adsk_input1_w) / float(adsk_result_w));
+   }
+   
+   // Apply or remove disto, per channel honoring chromatic aberration
+   if(apply_disto) {
+      f = inverse_f(r);
+   } else {
+      f = distortion_f(r);
+   }
+   
+   vec2[3] rgb_uvs = vec2[](uv, uv, uv);
+   
+   // Compute distortions per component
+   vec3 rgb_f = chromaticize_and_invert(f);
+   
+   // Apply the disto coefficients, per component
+   rgb_uvs[0] = rgb_uvs[0] * rgb_f.rr;
+   rgb_uvs[1] = rgb_uvs[1] * rgb_f.gg;
+   rgb_uvs[2] = rgb_uvs[2] * rgb_f.bb;
+   
+   // Convert all the UVs back to the texture space, per color component
+   for(int i=0; i < 3; i++) {
+       uv = rgb_uvs[i];
+       
+       // Back from [-aspect..aspect] to [-1..1]
+       uv.x = uv.x / adsk_input1_frameratio;
+       
+       // Remove UV shifts
+       uv.x -= uShift;
+       uv.y -= vShift;
+       
+       // Back to OGL UV
+       uv.x = (uv.x + 1) / 2;
+       uv.y = (uv.y + 1) / 2;
+       
+       rgb_uvs[i] = uv;
+   }
+   
+   // Sample the input plate, per component
+   vec4 sampled;
+   sampled.r = texture2D(input1, rgb_uvs[0]).r;
+   sampled.g = texture2D(input1, rgb_uvs[1]).g;
+   sampled.b = texture2D(input1, rgb_uvs[2]).b;
+   
+   // and assign to the output
+   gl_FragColor.rgba = vec4(sampled.rgb, 1.0 );
+}

samples/GLSL/islandScene.shader

@@ -0,0 +1,630 @@
+//// High quality (Some browsers may freeze or crash)
+//#define HIGHQUALITY
+
+//// Medium quality (Should be fine on all systems, works on Intel HD2000 on Win7 but quite slow)
+//#define MEDIUMQUALITY
+
+//// Defaults
+//#define REFLECTIONS
+#define SHADOWS
+//#define GRASS
+//#define SMALL_WAVES
+#define RAGGED_LEAVES
+//#define DETAILED_NOISE
+//#define LIGHT_AA // 2 sample SSAA
+//#define HEAVY_AA // 2x2 RG SSAA
+//#define TONEMAP
+
+//// Configurations
+#ifdef MEDIUMQUALITY
+	#define SHADOWS
+	#define SMALL_WAVES
+	#define RAGGED_LEAVES
+	#define TONEMAP
+#endif
+
+#ifdef HIGHQUALITY
+	#define REFLECTIONS
+	#define SHADOWS
+	//#define GRASS
+	#define SMALL_WAVES
+	#define RAGGED_LEAVES
+	#define DETAILED_NOISE
+	#define LIGHT_AA
+	#define TONEMAP
+#endif
+
+// Constants
+const float eps = 1e-5;
+const float PI = 3.14159265359;
+
+const vec3 sunDir = vec3(0.79057,-0.47434, 0.0);
+const vec3 skyCol = vec3(0.3, 0.5, 0.8);
+const vec3 sandCol = vec3(0.9, 0.8, 0.5);
+const vec3 treeCol = vec3(0.8, 0.65, 0.3);
+const vec3 grassCol = vec3(0.4, 0.5, 0.18);
+const vec3 leavesCol = vec3(0.3, 0.6, 0.2);
+const vec3 leavesPos = vec3(-5.1,13.4, 0.0);
+
+#ifdef TONEMAP
+const vec3 sunCol = vec3(1.8, 1.7, 1.6);
+#else
+const vec3 sunCol = vec3(0.9, 0.85, 0.8);
+#endif
+
+const float exposure = 1.1; // Only used when tonemapping
+
+// Description : Array and textureless GLSL 2D/3D/4D simplex
+// noise functions.
+// Author : Ian McEwan, Ashima Arts.
+// License : Copyright (C) 2011 Ashima Arts. All rights reserved.
+// Distributed under the MIT License. See LICENSE file.
+// https://github.com/ashima/webgl-noise
+vec3 mod289(vec3 x) {
+  return x - floor(x * (1.0 / 289.0)) * 289.0;
+}
+
+vec4 mod289(vec4 x) {
+  return x - floor(x * (1.0 / 289.0)) * 289.0;
+}
+
+vec4 permute(vec4 x) {
+     return mod289(((x*34.0)+1.0)*x);
+}
+
+vec4 taylorInvSqrt(vec4 r) {
+  return 1.79284291400159 - 0.85373472095314 * r;
+}
+
+float snoise(vec3 v) {
+  const vec2 C = vec2(1.0/6.0, 1.0/3.0) ;
+  const vec4 D = vec4(0.0, 0.5, 1.0, 2.0);
+
+// First corner
+  vec3 i = floor(v + dot(v, C.yyy) );
+  vec3 x0 = v - i + dot(i, C.xxx) ;
+
+// Other corners
+  vec3 g = step(x0.yzx, x0.xyz);
+  vec3 l = 1.0 - g;
+  vec3 i1 = min( g.xyz, l.zxy );
+  vec3 i2 = max( g.xyz, l.zxy );
+
+  // x0 = x0 - 0.0 + 0.0 * C.xxx;
+  // x1 = x0 - i1 + 1.0 * C.xxx;
+  // x2 = x0 - i2 + 2.0 * C.xxx;
+  // x3 = x0 - 1.0 + 3.0 * C.xxx;
+  vec3 x1 = x0 - i1 + C.xxx;
+  vec3 x2 = x0 - i2 + C.yyy; // 2.0*C.x = 1/3 = C.y
+  vec3 x3 = x0 - D.yyy; // -1.0+3.0*C.x = -0.5 = -D.y
+
+// Permutations
+  i = mod289(i);
+  vec4 p = permute( permute( permute(
+             i.z + vec4(0.0, i1.z, i2.z, 1.0 ))
+           + i.y + vec4(0.0, i1.y, i2.y, 1.0 ))
+           + i.x + vec4(0.0, i1.x, i2.x, 1.0 ));
+
+// Gradients: 7x7 points over a square, mapped onto an octahedron.
+// The ring size 17*17 = 289 is close to a multiple of 49 (49*6 = 294)
+  float n_ = 0.142857142857; // 1.0/7.0
+  vec3 ns = n_ * D.wyz - D.xzx;
+
+  vec4 j = p - 49.0 * floor(p * ns.z * ns.z); // mod(p,7*7)
+
+  vec4 x_ = floor(j * ns.z);
+  vec4 y_ = floor(j - 7.0 * x_ ); // mod(j,N)
+
+  vec4 x = x_ *ns.x + ns.yyyy;
+  vec4 y = y_ *ns.x + ns.yyyy;
+  vec4 h = 1.0 - abs(x) - abs(y);
+
+  vec4 b0 = vec4( x.xy, y.xy );
+  vec4 b1 = vec4( x.zw, y.zw );
+
+  //vec4 s0 = vec4(lessThan(b0,0.0))*2.0 - 1.0;
+  //vec4 s1 = vec4(lessThan(b1,0.0))*2.0 - 1.0;
+  vec4 s0 = floor(b0)*2.0 + 1.0;
+  vec4 s1 = floor(b1)*2.0 + 1.0;
+  vec4 sh = -step(h, vec4(0.0));
+
+  vec4 a0 = b0.xzyw + s0.xzyw*sh.xxyy ;
+  vec4 a1 = b1.xzyw + s1.xzyw*sh.zzww ;
+
+  vec3 p0 = vec3(a0.xy,h.x);
+  vec3 p1 = vec3(a0.zw,h.y);
+  vec3 p2 = vec3(a1.xy,h.z);
+  vec3 p3 = vec3(a1.zw,h.w);
+
+//Normalise gradients
+  vec4 norm = taylorInvSqrt(vec4(dot(p0,p0), dot(p1,p1), dot(p2, p2), dot(p3,p3)));
+  p0 *= norm.x;
+  p1 *= norm.y;
+  p2 *= norm.z;
+  p3 *= norm.w;
+
+// Mix final noise value
+  vec4 m = max(0.6 - vec4(dot(x0,x0), dot(x1,x1), dot(x2,x2), dot(x3,x3)), 0.0);
+  m = m * m;
+  return 42.0 * dot( m*m, vec4( dot(p0,x0), dot(p1,x1),
+                                dot(p2,x2), dot(p3,x3) ) );
+}
+
+
+
+// Main
+float fbm(vec3 p)
+{
+	float final = snoise(p); 
+	p *= 1.94; final += snoise(p) * 0.5;
+	#ifdef DETAILED_NOISE
+	p *= 3.75; final += snoise(p) * 0.25;
+	return final / 1.75;
+	#else
+	return final / 1.5;
+	#endif
+}
+
+float waterHeight(vec3 p)
+{
+	float d = length(p.xz);
+	float h = sin(d * 1.5 + iGlobalTime * 3.0) * 12.0 / d; // Island waves
+	#ifdef SMALL_WAVES
+	h += fbm(p*0.5); // Other waves
+	#endif
+	return h;
+}
+
+vec3 bump(vec3 pos, vec3 rayDir)
+{
+	float s = 2.0;
+	
+	// Fade out waves to reduce aliasing
+	float dist = dot(pos, rayDir);
+	s *= dist < 2.0 ? 1.0 : 1.4142 / sqrt(dist);
+	
+	// Calculate normal from heightmap
+	vec2 e = vec2(1e-2, 0.0);
+	vec3 p = vec3(pos.x, iGlobalTime*0.5, pos.z)*0.7;
+	float m = waterHeight(p)*s;
+	return normalize(vec3(
+		waterHeight(p+e.xyy)*s-m,
+		1.0,
+		waterHeight(p+e.yxy)*s-m
+	));
+}
+
+// Ray intersections
+vec4 intersectSphere(vec3 rpos, vec3 rdir, vec3 pos, float rad)
+{
+	vec3 op = pos - rpos;
+	float b = dot(op, rdir); 
+	float det = b*b - dot(op, op) + rad*rad; 
+		
+	if (det > 0.0)
+	{
+		det = sqrt(det);
+		float t = b - det;
+		if (t > eps)
+			return vec4(-normalize(rpos+rdir*t-pos), t);
+	}
+	
+	return vec4(0.0);
+}
+
+vec4 intersectCylinder(vec3 rpos, vec3 rdir, vec3 pos, float rad)
+{
+	vec3 op = pos - rpos;
+	vec2 rdir2 = normalize(rdir.yz);
+	float b = dot(op.yz, rdir2);
+	float det = b*b - dot(op.yz, op.yz) + rad*rad; 
+	
+	if (det > 0.0)
+	{
+		det = sqrt(det);
+		float t = b - det;
+		if (t > eps)
+			return vec4(-normalize(rpos.yz+rdir2*t-pos.yz), 0.0, t);
+		t = b + det;
+		if (t > eps)
+			return vec4(-normalize(rpos.yz+rdir2*t-pos.yz), 0.0, t);
+	}
+	
+	return vec4(0.0);
+}
+
+vec4 intersectPlane(vec3 rayPos, vec3 rayDir, vec3 n, float d)
+{
+	float t = -(dot(rayPos, n) + d) / dot(rayDir, n);
+	return vec4(n * sign(dot(rayDir, n)), t);
+}
+
+// Helper functions
+vec3 rotate(vec3 p, float theta)
+{
+	float c = cos(theta), s = sin(theta);
+	return vec3(p.x * c + p.z * s, p.y,
+				p.z * c - p.x * s);
+}
+
+float impulse(float k, float x) // by iq
+{
+    float h = k*x;
+    return h * exp(1.0 - h);
+}
+
+// Raymarched parts of scene
+float grass(vec3 pos)
+{
+	float h = length(pos - vec3(0.0, -7.0, 0.0)) - 8.0;
+	
+	if (h > 2.0) return h; // Optimization (Avoid noise if too far away)
+	
+	return h + snoise(pos * 3.0) * 0.1 + pos.y * 0.9;
+}
+
+float tree(vec3 pos)
+{
+	pos.y -= 0.5;
+	float s = sin(pos.y*0.03);
+	float c = cos(pos.y*0.03);
+	mat2 m = mat2(c, -s, s, c);
+	vec3 p = vec3(m*pos.xy, pos.z);
+	
+	float width = 1.0 - pos.y * 0.02 - clamp(sin(pos.y * 8.0) * 0.1, 0.05, 0.1);
+	
+	return max(length(p.xz) - width, pos.y - 12.5);
+}
+
+vec2 scene(vec3 pos)
+{
+	float vtree = tree(pos);
+	#ifdef GRASS
+	float vgrass = grass(pos);
+	float v = min(vtree, vgrass);
+	#else
+	float v = vtree;
+	#endif
+	return vec2(v, v == vtree ? 2.0 : 1.0);
+}
+
+vec3 normal(vec3 pos)
+{
+	vec2 eps = vec2(1e-3, 0.0);
+	float h = scene(pos).x;
+	return normalize(vec3(
+		scene(pos-eps.xyy).x-h,
+		scene(pos-eps.yxy).x-h,
+		scene(pos-eps.yyx).x-h
+	));
+}
+
+float plantsShadow(vec3 rayPos, vec3 rayDir)
+{
+	// Soft shadow taken from iq
+	float k = 6.0;
+	float t = 0.0;
+	float s = 1.0;	
+	for (int i = 0; i < 30; i++)
+	{
+		vec3 pos = rayPos+rayDir*t;	
+		vec2 res = scene(pos);		
+		if (res.x < 0.001) return 0.0;
+		s = min(s, k*res.x/t); 
+		t += max(res.x, 0.01);
+	}
+	
+	return s*s*(3.0 - 2.0*s);
+}
+
+// Ray-traced parts of scene
+vec4 intersectWater(vec3 rayPos, vec3 rayDir)
+{
+	float h = sin(20.5 + iGlobalTime * 2.0) * 0.03;
+	float t = -(rayPos.y + 2.5 + h) / rayDir.y;
+	return vec4(0.0, 1.0, 0.0, t);
+}
+
+vec4 intersectSand(vec3 rayPos, vec3 rayDir)
+{
+	return intersectSphere(rayPos, rayDir, vec3(0.0,-24.1,0.0), 24.1);
+}
+
+vec4 intersectTreasure(vec3 rayPos, vec3 rayDir)
+{
+	return vec4(0.0);
+}
+
+vec4 intersectLeaf(vec3 rayPos, vec3 rayDir, float openAmount)
+{	
+	vec3 dir = normalize(vec3(0.0, 1.0, openAmount));
+	float offset = 0.0;
+			
+	vec4 res = intersectPlane(rayPos, rayDir, dir, 0.0);
+	vec3 pos = rayPos+rayDir*res.w;
+	#ifdef RAGGED_LEAVES
+	offset = snoise(pos*0.8) * 0.3;
+	#endif
+	if (pos.y > 0.0 || length(pos * vec3(0.9, 2.0, 1.0)) > 4.0 - offset) res.w = 0.0;
+	
+	vec4 res2 = intersectPlane(rayPos, rayDir, vec3(dir.xy, -dir.z), 0.0);
+	pos = rayPos+rayDir*res2.w;
+	#ifdef RAGGED_LEAVES
+	offset = snoise(pos*0.8) * 0.3;
+	#endif
+	if (pos.y > 0.0 || length(pos * vec3(0.9, 2.0, 1.0)) > 4.0 - offset) res2.w = 0.0;
+	
+	if (res2.w > 0.0 && res2.w < res.w || res.w <= 0.0)
+		res = res2;
+		
+	return res;
+}
+
+vec4 leaves(vec3 rayPos, vec3 rayDir)
+{
+	float t = 1e20;
+	vec3 n = vec3(0.0);
+	
+	rayPos -= leavesPos;
+	
+	float sway = impulse(15.0, fract(iGlobalTime / PI * 0.125));
+	float upDownSway = sway * -sin(iGlobalTime) * 0.06;
+	float openAmount = sway * max(-cos(iGlobalTime) * 0.4, 0.0);
+	
+	float angleOffset = -0.1;	
+	for (float k = 0.0; k < 6.2; k += 0.75)
+	{
+		// Left-right
+		float alpha = k + (k - PI) * sway * 0.015;
+		vec3 p = rotate(rayPos, alpha);
+		vec3 d = rotate(rayDir, alpha);
+		
+		// Up-down
+		angleOffset *= -1.0;
+		float theta = -0.4 + 
+			angleOffset + 
+			cos(k) * 0.35 + 
+			upDownSway + 
+			sin(iGlobalTime+k*10.0) * 0.03 * (sway + 0.2);
+		
+		p = rotate(p.xzy, theta).xzy;
+		d = rotate(d.xzy, theta).xzy;
+	
+		// Shift
+		p -= vec3(5.4, 0.0, 0.0);
+		
+		// Intersect individual leaf
+		vec4 res = intersectLeaf(p, d, 1.0+openAmount);
+		if (res.w > 0.0 && res.w < t)
+		{
+			t = res.w;
+			n = res.xyz;
+		}
+	}
+	
+	return vec4(n, t);
+}
+
+// Lighting
+float shadow(vec3 rayPos, vec3 rayDir)
+{	
+	float s = 1.0;
+	
+	// Intersect sand
+	//vec4 resSand = intersectSand(rayPos, rayDir);
+	//if (resSand.w > 0.0) return 0.0;
+	
+	// Intersect plants
+	s = min(s, plantsShadow(rayPos, rayDir));
+	if (s < 0.0001) return 0.0;
+	
+	// Intersect leaves
+	vec4 resLeaves = leaves(rayPos, rayDir);
+	if (resLeaves.w > 0.0 && resLeaves.w < 1e7) return 0.0;
+	
+	return s;
+}
+
+vec3 light(vec3 p, vec3 n)
+{
+	float s = 1.0;
+	
+	#ifdef SHADOWS
+	s = shadow(p-sunDir*0.01, -sunDir);
+	#endif
+	
+	vec3 col = sunCol * min(max(dot(n, sunDir), 0.0), s);
+	col += skyCol * (-n.y * 0.5 + 0.5) * 0.3;
+	return col;
+}
+
+vec3 lightLeaves(vec3 p, vec3 n)
+{
+	float s = 1.0;
+	
+	#ifdef SHADOWS
+	s = shadow(p-sunDir*0.01, -sunDir);
+	#endif
+	
+	float ao = min(length(p - leavesPos) * 0.1, 1.0);
+	
+	float ns = dot(n, sunDir);
+	float d = sqrt(max(ns, 0.0));
+	vec3 col = sunCol * min(d, s);
+	col += sunCol * max(-ns, 0.0) * vec3(0.3, 0.3, 0.1) * ao;
+	col += skyCol * (-n.y * 0.5 + 0.5) * 0.3 * ao;
+	return col;
+}
+
+vec3 sky(vec3 n)
+{
+	return skyCol * (1.0 - n.y * 0.8);
+}
+
+// Ray-marching
+vec4 plants(vec3 rayPos, vec3 rayDir)
+{
+	float t = 0.0;
+	
+	for (int i = 0; i < 40; i++)
+	{
+		vec3 pos = rayPos+rayDir*t;	
+		vec2 res = scene(pos);
+		float h = res.x;
+		
+		if (h < 0.001)
+		{
+			vec3 col = res.y == 2.0 ? treeCol : grassCol;
+			float uvFact = res.y == 2.0 ? 1.0 : 10.0;
+			
+			vec3 n = normal(pos);
+			vec2 uv = vec2(n.x, pos.y * 0.5) * 0.2 * uvFact;
+			vec3 tex = texture2D(iChannel0, uv).rgb * 0.6 + 0.4;
+			float ao = min(length(pos - leavesPos) * 0.1, 1.0);
+			return vec4(col * light(pos, n) * ao * tex, t);
+		}
+		
+		t += h;
+	}
+	
+	return vec4(sky(rayDir), 1e8);
+}
+
+// Final combination
+vec3 traceReflection(vec3 rayPos, vec3 rayDir)
+{
+	vec3 col = vec3(0.0);
+	float t = 1e20;
+			
+	// Intersect plants
+	vec4 resPlants = plants(rayPos, rayDir);
+	if (resPlants.w > 0.0 && resPlants.w < t)
+	{
+		t = resPlants.w;
+		col = resPlants.xyz;
+	}
+	
+	// Intersect leaves
+	vec4 resLeaves = leaves(rayPos, rayDir);
+	if (resLeaves.w > 0.0 && resLeaves.w < t)
+	{
+		vec3 pos = rayPos + rayDir * resLeaves.w;
+		vec2 uv = (pos.xz - leavesPos.xz) * 0.3;
+		float tex = texture2D(iChannel0, uv).r * 0.6 + 0.5;
+		
+		t = resLeaves.w;
+		col = leavesCol * lightLeaves(pos, resLeaves.xyz) * tex;
+	}
+		
+	if (t > 1e7) return sky(rayDir);
+	
+	return col;
+}
+
+vec3 trace(vec3 rayPos, vec3 rayDir)
+{
+	vec3 col = vec3(0.0);
+	float t = 1e20;
+	
+	// Intersect sand
+	vec4 resSand = intersectSand(rayPos, rayDir);
+	if (resSand.w > 0.0)
+	{
+		vec3 pos = rayPos + rayDir * resSand.w;
+		t = resSand.w;
+
+		col = sandCol * light(pos, resSand.xyz);
+	}
+	
+	// Intersect treasure chest
+	vec4 resTreasure = intersectTreasure(rayPos, rayDir);
+	if (resTreasure.w > 0.0 && resTreasure.w < t)
+	{
+		vec3 pos = rayPos + rayDir * resTreasure.w;
+		t = resTreasure.w;
+		col = leavesCol * light(pos, resTreasure.xyz);
+	}
+	
+	// Intersect leaves
+	vec4 resLeaves = leaves(rayPos, rayDir);
+	if (resLeaves.w > 0.0 && resLeaves.w < t)
+	{
+		vec3 pos = rayPos + rayDir * resLeaves.w;
+		vec2 uv = (pos.xz - leavesPos.xz) * 0.3;
+		float tex = texture2D(iChannel0, uv).r * 0.6 + 0.5;
+		
+		t = resLeaves.w;
+		col = leavesCol * lightLeaves(pos, resLeaves.xyz) * tex;
+	}
+	
+	// Intersect plants
+	vec4 resPlants = plants(rayPos, rayDir);
+	if (resPlants.w > 0.0 && resPlants.w < t)
+	{
+		t = resPlants.w;
+		col = resPlants.xyz;
+	}
+		
+	// Intersect water	
+	vec4 resWater = intersectWater(rayPos, rayDir);
+	if (resWater.w > 0.0 && resWater.w < t)
+	{
+		vec3 pos = rayPos + rayDir * resWater.w;
+		float dist = t - resWater.w;
+		vec3 n = bump(pos, rayDir);
+		
+		float ct = -min(dot(n,rayDir), 0.0);
+		float fresnel = 0.9 - 0.9 * pow(1.0 - ct, 5.0);
+		
+		vec3 trans = col * exp(-dist * vec3(1.0, 0.7, 0.4) * 3.0);
+		vec3 reflDir = normalize(reflect(rayDir, n));
+		vec3 refl = sky(reflDir);
+		
+		#ifdef REFLECTIONS
+		if (dot(pos, rayDir) < -2.0)
+			refl = traceReflection(pos, reflDir).rgb;
+		#endif
+				
+		t = resWater.t;
+		col = mix(refl, trans, fresnel);
+	}
+	
+	if (t > 1e7) return sky(rayDir);
+	
+	return col;
+}
+
+// Ray-generation
+vec3 camera(vec2 px)
+{
+	vec2 rd = (px / iResolution.yy - vec2(iResolution.x/iResolution.y*0.5-0.5, 0.0)) * 2.0 - 1.0;
+	float t = sin(iGlobalTime * 0.1) * 0.2;
+	vec3 rayDir = normalize(vec3(rd.x, rd.y, 1.0));
+	vec3 rayPos = vec3(0.0, 3.0, -18.0);
+	return trace(rayPos, rayDir);
+}
+
+void main(void)
+{
+	#ifdef HEAVY_AA
+		vec3 col = camera(gl_FragCoord.xy+vec2(0.0,0.5))*0.25;
+		col += camera(gl_FragCoord.xy+vec2(0.25,0.0))*0.25;
+		col += camera(gl_FragCoord.xy+vec2(0.5,0.75))*0.25;
+		col += camera(gl_FragCoord.xy+vec2(0.75,0.25))*0.25;
+	#else
+		vec3 col = camera(gl_FragCoord.xy);
+		#ifdef LIGHT_AA
+			col = col * 0.5 + camera(gl_FragCoord.xy+vec2(0.5,0.5))*0.5;
+		#endif
+	#endif
+	
+	#ifdef TONEMAP
+	// Optimized Haarm-Peter Duiker’s curve
+	vec3 x = max(vec3(0.0),col*exposure-0.004);
+	col = (x*(6.2*x+.5))/(x*(6.2*x+1.7)+0.06);
+	#else
+	col = pow(col, vec3(0.4545));
+	#endif
+	
+	gl_FragColor = vec4(col, 1.0);
+}

samples/GN/BUILD.2.gn

@@ -0,0 +1,59 @@
+# Copyright 2016 the V8 project authors. All rights reserved.
+# Use of this source code is governed by a BSD-style license that can be
+# found in the LICENSE file.
+
+import("../gni/isolate.gni")
+
+group("gn_all") {
+  testonly = true
+
+  if (v8_test_isolation_mode != "noop") {
+    deps = [
+      ":check-static-initializers_run",
+      ":jsfunfuzz_run",
+      ":run-deopt-fuzzer_run",
+      ":run-gcmole_run",
+      ":run-valgrind_run",
+    ]
+  }
+}
+
+v8_isolate_run("check-static-initializers") {
+  deps = [
+    "..:d8_run",
+  ]
+
+  isolate = "check-static-initializers.isolate"
+}
+
+v8_isolate_run("jsfunfuzz") {
+  deps = [
+    "..:d8_run",
+  ]
+
+  isolate = "jsfunfuzz/jsfunfuzz.isolate"
+}
+
+v8_isolate_run("run-deopt-fuzzer") {
+  deps = [
+    "..:d8_run",
+  ]
+
+  isolate = "run-deopt-fuzzer.isolate"
+}
+
+v8_isolate_run("run-gcmole") {
+  deps = [
+    "..:d8_run",
+  ]
+
+  isolate = "gcmole/run-gcmole.isolate"
+}
+
+v8_isolate_run("run-valgrind") {
+  deps = [
+    "..:d8_run",
+  ]
+
+  isolate = "run-valgrind.isolate"
+}

samples/GN/clang.gni

@@ -0,0 +1,13 @@
+# Copyright 2014 The Chromium Authors. All rights reserved.
+# Use of this source code is governed by a BSD-style license that can be
+# found in the LICENSE file.
+
+import("//build/toolchain/toolchain.gni")
+
+declare_args() {
+  # Indicates if the build should use the Chrome-specific plugins for enforcing
+  # coding guidelines, etc. Only used when compiling with Clang.
+  clang_use_chrome_plugins = is_clang && !is_nacl && !use_xcode_clang
+
+  clang_base_path = "//third_party/llvm-build/Release+Asserts"
+}

samples/GN/filenames/.gn

@@ -0,0 +1,25 @@
+# This file is used by the GN meta build system to find the root of the source
+# tree and to set startup options. For documentation on the values set in this
+# file, run "gn help dotfile" at the command line.
+
+import("//build/dotfile_settings.gni")
+
+# The location of the build configuration file.
+buildconfig = "//build/config/BUILDCONFIG.gn"
+
+# The secondary source root is a parallel directory tree where
+# GN build files are placed when they can not be placed directly
+# in the source tree, e.g. for third party source trees.
+secondary_source = "//build/secondary/"
+
+# These are the targets to check headers for by default. The files in targets
+# matching these patterns (see "gn help label_pattern" for format) will have
+# their includes checked for proper dependencies when you run either
+# "gn check" or "gn gen --check".
+check_targets = []
+
+# These are the list of GN files that run exec_script. This whitelist exists
+# to force additional review for new uses of exec_script, which is strongly
+# discouraged except for gypi_to_gn calls.
+exec_script_whitelist =
+    build_dotfile_settings.exec_script_whitelist + [ "//test/test262/BUILD.gn" ]

samples/GN/gcc_toolchain.gni

@@ -0,0 +1,503 @@
+# Copyright (c) 2013 The Chromium Authors. All rights reserved.
+# Use of this source code is governed by a BSD-style license that can be
+# found in the LICENSE file.
+
+import("//build/config/android/config.gni")
+import("//build/config/clang/clang.gni")
+import("//build/config/nacl/config.gni")
+import("//build/config/sanitizers/sanitizers.gni")
+import("//build/config/v8_target_cpu.gni")
+import("//build/toolchain/cc_wrapper.gni")
+import("//build/toolchain/goma.gni")
+import("//build/toolchain/toolchain.gni")
+
+# This template defines a toolchain for something that works like gcc
+# (including clang).
+#
+# It requires the following variables specifying the executables to run:
+#  - ar
+#  - cc
+#  - cxx
+#  - ld
+#
+# Optional parameters that control the tools:
+#
+#  - extra_cflags
+#      Extra flags to be appended when compiling C files (but not C++ files).
+#  - extra_cppflags
+#      Extra flags to be appended when compiling both C and C++ files. "CPP"
+#      stands for "C PreProcessor" in this context, although it can be
+#      used for non-preprocessor flags as well. Not to be confused with
+#      "CXX" (which follows).
+#  - extra_cxxflags
+#      Extra flags to be appended when compiling C++ files (but not C files).
+#  - extra_ldflags
+#      Extra flags to be appended when linking
+#
+#  - libs_section_prefix
+#  - libs_section_postfix
+#      The contents of these strings, if specified, will be placed around
+#      the libs section of the linker line. It allows one to inject libraries
+#      at the beginning and end for all targets in a toolchain.
+#  - solink_libs_section_prefix
+#  - solink_libs_section_postfix
+#      Same as libs_section_{pre,post}fix except used for solink instead of link.
+#  - link_outputs
+#      The content of this array, if specified, will be added to the list of
+#      outputs from the link command. This can be useful in conjunction with
+#      the post_link parameter.
+#  - post_link
+#      The content of this string, if specified, will be run as a separate
+#      command following the the link command.
+#  - deps
+#      Just forwarded to the toolchain definition.
+#  - executable_extension
+#      If this string is specified it will be used for the file extension
+#      for an executable, rather than using no extension; targets will
+#      still be able to override the extension using the output_extension
+#      variable.
+#  - rebuild_define
+#      The contents of this string, if specified, will be passed as a #define
+#      to the toolchain. It can be used to force recompiles whenever a
+#      toolchain is updated.
+#  - shlib_extension
+#      If this string is specified it will be used for the file extension
+#      for a shared library, rather than default value specified in
+#      toolchain.gni
+#  - strip
+#      Location of the strip executable. When specified, strip will be run on
+#      all shared libraries and executables as they are built. The pre-stripped
+#      artifacts will be put in lib.unstripped/ and exe.unstripped/.
+template("gcc_toolchain") {
+  toolchain(target_name) {
+    assert(defined(invoker.ar), "gcc_toolchain() must specify a \"ar\" value")
+    assert(defined(invoker.cc), "gcc_toolchain() must specify a \"cc\" value")
+    assert(defined(invoker.cxx), "gcc_toolchain() must specify a \"cxx\" value")
+    assert(defined(invoker.ld), "gcc_toolchain() must specify a \"ld\" value")
+
+    # This define changes when the toolchain changes, forcing a rebuild.
+    # Nothing should ever use this define.
+    if (defined(invoker.rebuild_define)) {
+      rebuild_string = "-D" + invoker.rebuild_define + " "
+    } else {
+      rebuild_string = ""
+    }
+
+    # GN's syntax can't handle more than one scope dereference at once, like
+    # "invoker.toolchain_args.foo", so make a temporary to hold the toolchain
+    # args so we can do "invoker_toolchain_args.foo".
+    assert(defined(invoker.toolchain_args),
+           "Toolchains must specify toolchain_args")
+    invoker_toolchain_args = invoker.toolchain_args
+    assert(defined(invoker_toolchain_args.current_cpu),
+           "toolchain_args must specify a current_cpu")
+    assert(defined(invoker_toolchain_args.current_os),
+           "toolchain_args must specify a current_os")
+
+    # When invoking this toolchain not as the default one, these args will be
+    # passed to the build. They are ignored when this is the default toolchain.
+    toolchain_args = {
+      # Populate toolchain args from the invoker.
+      forward_variables_from(invoker_toolchain_args, "*")
+
+      # The host toolchain value computed by the default toolchain's setup
+      # needs to be passed through unchanged to all secondary toolchains to
+      # ensure that it's always the same, regardless of the values that may be
+      # set on those toolchains.
+      host_toolchain = host_toolchain
+
+      if (!defined(invoker_toolchain_args.v8_current_cpu)) {
+        v8_current_cpu = invoker_toolchain_args.current_cpu
+      }
+    }
+
+    # When the invoker has explicitly overridden use_goma or cc_wrapper in the
+    # toolchain args, use those values, otherwise default to the global one.
+    # This works because the only reasonable override that toolchains might
+    # supply for these values are to force-disable them.
+    if (defined(toolchain_args.use_goma)) {
+      toolchain_uses_goma = toolchain_args.use_goma
+    } else {
+      toolchain_uses_goma = use_goma
+    }
+    if (defined(toolchain_args.cc_wrapper)) {
+      toolchain_cc_wrapper = toolchain_args.cc_wrapper
+    } else {
+      toolchain_cc_wrapper = cc_wrapper
+    }
+
+    # Compute the compiler prefix.
+    if (toolchain_uses_goma) {
+      assert(toolchain_cc_wrapper == "",
+             "Goma and cc_wrapper can't be used together.")
+      compiler_prefix = "$goma_dir/gomacc "
+    } else if (toolchain_cc_wrapper != "") {
+      compiler_prefix = toolchain_cc_wrapper + " "
+    } else {
+      compiler_prefix = ""
+    }
+
+    cc = compiler_prefix + invoker.cc
+    cxx = compiler_prefix + invoker.cxx
+    ar = invoker.ar
+    ld = invoker.ld
+    if (defined(invoker.readelf)) {
+      readelf = invoker.readelf
+    } else {
+      readelf = "readelf"
+    }
+    if (defined(invoker.nm)) {
+      nm = invoker.nm
+    } else {
+      nm = "nm"
+    }
+
+    if (defined(invoker.shlib_extension)) {
+      default_shlib_extension = invoker.shlib_extension
+    } else {
+      default_shlib_extension = shlib_extension
+    }
+
+    if (defined(invoker.executable_extension)) {
+      default_executable_extension = invoker.executable_extension
+    } else {
+      default_executable_extension = ""
+    }
+
+    # Bring these into our scope for string interpolation with default values.
+    if (defined(invoker.libs_section_prefix)) {
+      libs_section_prefix = invoker.libs_section_prefix
+    } else {
+      libs_section_prefix = ""
+    }
+
+    if (defined(invoker.libs_section_postfix)) {
+      libs_section_postfix = invoker.libs_section_postfix
+    } else {
+      libs_section_postfix = ""
+    }
+
+    if (defined(invoker.solink_libs_section_prefix)) {
+      solink_libs_section_prefix = invoker.solink_libs_section_prefix
+    } else {
+      solink_libs_section_prefix = ""
+    }
+
+    if (defined(invoker.solink_libs_section_postfix)) {
+      solink_libs_section_postfix = invoker.solink_libs_section_postfix
+    } else {
+      solink_libs_section_postfix = ""
+    }
+
+    if (defined(invoker.extra_cflags) && invoker.extra_cflags != "") {
+      extra_cflags = " " + invoker.extra_cflags
+    } else {
+      extra_cflags = ""
+    }
+
+    if (defined(invoker.extra_cppflags) && invoker.extra_cppflags != "") {
+      extra_cppflags = " " + invoker.extra_cppflags
+    } else {
+      extra_cppflags = ""
+    }
+
+    if (defined(invoker.extra_cxxflags) && invoker.extra_cxxflags != "") {
+      extra_cxxflags = " " + invoker.extra_cxxflags
+    } else {
+      extra_cxxflags = ""
+    }
+
+    if (defined(invoker.extra_ldflags) && invoker.extra_ldflags != "") {
+      extra_ldflags = " " + invoker.extra_ldflags
+    } else {
+      extra_ldflags = ""
+    }
+
+    # These library switches can apply to all tools below.
+    lib_switch = "-l"
+    lib_dir_switch = "-L"
+
+    # Object files go in this directory.
+    object_subdir = "{{target_out_dir}}/{{label_name}}"
+
+    tool("cc") {
+      depfile = "{{output}}.d"
+      command = "$cc -MMD -MF $depfile ${rebuild_string}{{defines}} {{include_dirs}} {{cflags}} {{cflags_c}}${extra_cppflags}${extra_cflags} -c {{source}} -o {{output}}"
+      depsformat = "gcc"
+      description = "CC {{output}}"
+      outputs = [
+        # The whitelist file is also an output, but ninja does not
+        # currently support multiple outputs for tool("cc").
+        "$object_subdir/{{source_name_part}}.o",
+      ]
+      if (enable_resource_whitelist_generation) {
+        compile_wrapper =
+            rebase_path("//build/toolchain/gcc_compile_wrapper.py",
+                        root_build_dir)
+        command = "$python_path \"$compile_wrapper\" --resource-whitelist=\"{{output}}.whitelist\" $command"
+      }
+    }
+
+    tool("cxx") {
+      depfile = "{{output}}.d"
+      command = "$cxx -MMD -MF $depfile ${rebuild_string}{{defines}} {{include_dirs}} {{cflags}} {{cflags_cc}}${extra_cppflags}${extra_cxxflags} -c {{source}} -o {{output}}"
+      depsformat = "gcc"
+      description = "CXX {{output}}"
+      outputs = [
+        # The whitelist file is also an output, but ninja does not
+        # currently support multiple outputs for tool("cxx").
+        "$object_subdir/{{source_name_part}}.o",
+      ]
+      if (enable_resource_whitelist_generation) {
+        compile_wrapper =
+            rebase_path("//build/toolchain/gcc_compile_wrapper.py",
+                        root_build_dir)
+        command = "$python_path \"$compile_wrapper\" --resource-whitelist=\"{{output}}.whitelist\" $command"
+      }
+    }
+
+    tool("asm") {
+      # For GCC we can just use the C compiler to compile assembly.
+      depfile = "{{output}}.d"
+      command = "$cc -MMD -MF $depfile ${rebuild_string}{{defines}} {{include_dirs}} {{asmflags}} -c {{source}} -o {{output}}"
+      depsformat = "gcc"
+      description = "ASM {{output}}"
+      outputs = [
+        "$object_subdir/{{source_name_part}}.o",
+      ]
+    }
+
+    tool("alink") {
+      rspfile = "{{output}}.rsp"
+      whitelist_flag = " "
+      if (enable_resource_whitelist_generation) {
+        whitelist_flag = " --resource-whitelist=\"{{output}}.whitelist\""
+      }
+
+      # This needs a Python script to avoid using simple sh features in this
+      # command, in case the host does not use a POSIX shell (e.g. compiling
+      # POSIX-like toolchains such as NaCl on Windows).
+      ar_wrapper =
+          rebase_path("//build/toolchain/gcc_ar_wrapper.py", root_build_dir)
+      command = "$python_path \"$ar_wrapper\"$whitelist_flag --output={{output}} --ar=\"$ar\" {{arflags}} rcsD @\"$rspfile\""
+      description = "AR {{output}}"
+      rspfile_content = "{{inputs}}"
+      outputs = [
+        "{{output_dir}}/{{target_output_name}}{{output_extension}}",
+      ]
+
+      # Shared libraries go in the target out directory by default so we can
+      # generate different targets with the same name and not have them collide.
+      default_output_dir = "{{target_out_dir}}"
+      default_output_extension = ".a"
+      output_prefix = "lib"
+    }
+
+    tool("solink") {
+      soname = "{{target_output_name}}{{output_extension}}"  # e.g. "libfoo.so".
+      sofile = "{{output_dir}}/$soname"  # Possibly including toolchain dir.
+      rspfile = sofile + ".rsp"
+      pool = "//build/toolchain:link_pool($default_toolchain)"
+      whitelist_flag = " "
+      if (enable_resource_whitelist_generation) {
+        whitelist_file = "$sofile.whitelist"
+        whitelist_flag = " --resource-whitelist=\"$whitelist_file\""
+      }
+
+      if (defined(invoker.strip)) {
+        unstripped_sofile = "{{root_out_dir}}/lib.unstripped/$soname"
+      } else {
+        unstripped_sofile = sofile
+      }
+
+      # These variables are not built into GN but are helpers that
+      # implement (1) linking to produce a .so, (2) extracting the symbols
+      # from that file (3) if the extracted list differs from the existing
+      # .TOC file, overwrite it, otherwise, don't change it.
+      tocfile = sofile + ".TOC"
+
+      link_command = "$ld -shared {{ldflags}}${extra_ldflags} -o \"$unstripped_sofile\" -Wl,-soname=\"$soname\" @\"$rspfile\""
+
+      assert(defined(readelf), "to solink you must have a readelf")
+      assert(defined(nm), "to solink you must have an nm")
+      strip_switch = ""
+      if (defined(invoker.strip)) {
+        strip_switch = "--strip=${invoker.strip}"
+      }
+
+      # This needs a Python script to avoid using a complex shell command
+      # requiring sh control structures, pipelines, and POSIX utilities.
+      # The host might not have a POSIX shell and utilities (e.g. Windows).
+      solink_wrapper = rebase_path("//build/toolchain/gcc_solink_wrapper.py")
+      command = "$python_path \"$solink_wrapper\" --readelf=\"$readelf\" --nm=\"$nm\" $strip_switch --sofile=\"$unstripped_sofile\" --tocfile=\"$tocfile\" --output=\"$sofile\"$whitelist_flag -- $link_command"
+
+      rspfile_content = "-Wl,--whole-archive {{inputs}} {{solibs}} -Wl,--no-whole-archive $solink_libs_section_prefix {{libs}} $solink_libs_section_postfix"
+
+      description = "SOLINK $sofile"
+
+      # Use this for {{output_extension}} expansions unless a target manually
+      # overrides it (in which case {{output_extension}} will be what the target
+      # specifies).
+      default_output_extension = default_shlib_extension
+
+      default_output_dir = "{{root_out_dir}}"
+      if (shlib_subdir != ".") {
+        default_output_dir += "/$shlib_subdir"
+      }
+
+      output_prefix = "lib"
+
+      # Since the above commands only updates the .TOC file when it changes, ask
+      # Ninja to check if the timestamp actually changed to know if downstream
+      # dependencies should be recompiled.
+      restat = true
+
+      # Tell GN about the output files. It will link to the sofile but use the
+      # tocfile for dependency management.
+      outputs = [
+        sofile,
+        tocfile,
+      ]
+      if (enable_resource_whitelist_generation) {
+        outputs += [ whitelist_file ]
+      }
+      if (sofile != unstripped_sofile) {
+        outputs += [ unstripped_sofile ]
+      }
+      link_output = sofile
+      depend_output = tocfile
+    }
+
+    tool("solink_module") {
+      soname = "{{target_output_name}}{{output_extension}}"  # e.g. "libfoo.so".
+      sofile = "{{output_dir}}/$soname"
+      rspfile = sofile + ".rsp"
+      pool = "//build/toolchain:link_pool($default_toolchain)"
+
+      if (defined(invoker.strip)) {
+        unstripped_sofile = "{{root_out_dir}}/lib.unstripped/$soname"
+      } else {
+        unstripped_sofile = sofile
+      }
+
+      command = "$ld -shared {{ldflags}}${extra_ldflags} -o \"$unstripped_sofile\" -Wl,-soname=\"$soname\" @\"$rspfile\""
+
+      if (defined(invoker.strip)) {
+        strip_command = "${invoker.strip} --strip-unneeded -o \"$sofile\" \"$unstripped_sofile\""
+        command += " && " + strip_command
+      }
+      rspfile_content = "-Wl,--whole-archive {{inputs}} {{solibs}} -Wl,--no-whole-archive $solink_libs_section_prefix {{libs}} $solink_libs_section_postfix"
+
+      description = "SOLINK_MODULE $sofile"
+
+      # Use this for {{output_extension}} expansions unless a target manually
+      # overrides it (in which case {{output_extension}} will be what the target
+      # specifies).
+      if (defined(invoker.loadable_module_extension)) {
+        default_output_extension = invoker.loadable_module_extension
+      } else {
+        default_output_extension = default_shlib_extension
+      }
+
+      default_output_dir = "{{root_out_dir}}"
+      if (shlib_subdir != ".") {
+        default_output_dir += "/$shlib_subdir"
+      }
+
+      output_prefix = "lib"
+
+      outputs = [
+        sofile,
+      ]
+      if (sofile != unstripped_sofile) {
+        outputs += [ unstripped_sofile ]
+      }
+    }
+
+    tool("link") {
+      exename = "{{target_output_name}}{{output_extension}}"
+      outfile = "{{output_dir}}/$exename"
+      rspfile = "$outfile.rsp"
+      unstripped_outfile = outfile
+      pool = "//build/toolchain:link_pool($default_toolchain)"
+
+      # Use this for {{output_extension}} expansions unless a target manually
+      # overrides it (in which case {{output_extension}} will be what the target
+      # specifies).
+      default_output_extension = default_executable_extension
+
+      default_output_dir = "{{root_out_dir}}"
+
+      if (defined(invoker.strip)) {
+        unstripped_outfile = "{{root_out_dir}}/exe.unstripped/$exename"
+      }
+
+      command = "$ld {{ldflags}}${extra_ldflags} -o \"$unstripped_outfile\" -Wl,--start-group @\"$rspfile\" {{solibs}} -Wl,--end-group $libs_section_prefix {{libs}} $libs_section_postfix"
+      if (defined(invoker.strip)) {
+        link_wrapper =
+            rebase_path("//build/toolchain/gcc_link_wrapper.py", root_build_dir)
+        command = "$python_path \"$link_wrapper\" --strip=\"${invoker.strip}\" --unstripped-file=\"$unstripped_outfile\" --output=\"$outfile\" -- $command"
+      }
+      description = "LINK $outfile"
+      rspfile_content = "{{inputs}}"
+      outputs = [
+        outfile,
+      ]
+      if (outfile != unstripped_outfile) {
+        outputs += [ unstripped_outfile ]
+      }
+      if (defined(invoker.link_outputs)) {
+        outputs += invoker.link_outputs
+      }
+    }
+
+    # These two are really entirely generic, but have to be repeated in
+    # each toolchain because GN doesn't allow a template to be used here.
+    # See //build/toolchain/toolchain.gni for details.
+    tool("stamp") {
+      command = stamp_command
+      description = stamp_description
+    }
+    tool("copy") {
+      command = copy_command
+      description = copy_description
+    }
+
+    forward_variables_from(invoker, [ "deps" ])
+  }
+}
+
+# This is a shorthand for gcc_toolchain instances based on the Chromium-built
+# version of Clang. Only the toolchain_cpu and toolchain_os variables need to
+# be specified by the invoker, and optionally toolprefix if it's a
+# cross-compile case. Note that for a cross-compile case this toolchain
+# requires a config to pass the appropriate -target option, or else it will
+# actually just be doing a native compile. The invoker can optionally override
+# use_gold too.
+template("clang_toolchain") {
+  if (defined(invoker.toolprefix)) {
+    toolprefix = invoker.toolprefix
+  } else {
+    toolprefix = ""
+  }
+
+  gcc_toolchain(target_name) {
+    prefix = rebase_path("$clang_base_path/bin", root_build_dir)
+    cc = "$prefix/clang"
+    cxx = "$prefix/clang++"
+    ld = cxx
+
+    readelf = "${toolprefix}readelf"
+    ar = "${toolprefix}ar"
+    nm = "${toolprefix}nm"
+
+    forward_variables_from(invoker, [ "strip" ])
+
+    toolchain_args = {
+      if (defined(invoker.toolchain_args)) {
+        forward_variables_from(invoker.toolchain_args, "*")
+      }
+      is_clang = true
+    }
+  }
+}

samples/GN/icu.gn

@@ -0,0 +1,235 @@
+# Copyright 2016 The Chromium Authors. All rights reserved.
+# Use of this source code is governed by a BSD-style license that can be
+# found in the LICENSE file.
+
+import("//build/config/linux/pkg_config.gni")
+import("//build/shim_headers.gni")
+
+group("icu") {
+  public_deps = [
+    ":icui18n",
+    ":icuuc",
+  ]
+}
+
+config("icu_config") {
+  defines = [
+    "USING_SYSTEM_ICU=1",
+    "ICU_UTIL_DATA_IMPL=ICU_UTIL_DATA_STATIC",
+  ]
+}
+
+pkg_config("system_icui18n") {
+  packages = [ "icu-i18n" ]
+}
+
+pkg_config("system_icuuc") {
+  packages = [ "icu-uc" ]
+}
+
+source_set("icui18n") {
+  deps = [
+    ":icui18n_shim",
+  ]
+  public_configs = [
+    ":icu_config",
+    ":system_icui18n",
+  ]
+}
+
+source_set("icuuc") {
+  deps = [
+    ":icuuc_shim",
+  ]
+  public_configs = [
+    ":icu_config",
+    ":system_icuuc",
+  ]
+}
+
+shim_headers("icui18n_shim") {
+  root_path = "source/i18n"
+  headers = [
+    # This list can easily be updated using the command below:
+    # find third_party/icu/source/i18n/unicode \
+    # -iname '*.h' -printf '"%p",\n' | \
+    # sed -e 's|third_party/icu/i18n/common/||' | sort -u
+    "unicode/alphaindex.h",
+    "unicode/basictz.h",
+    "unicode/calendar.h",
+    "unicode/choicfmt.h",
+    "unicode/coleitr.h",
+    "unicode/coll.h",
+    "unicode/compactdecimalformat.h",
+    "unicode/curramt.h",
+    "unicode/currpinf.h",
+    "unicode/currunit.h",
+    "unicode/datefmt.h",
+    "unicode/dcfmtsym.h",
+    "unicode/decimfmt.h",
+    "unicode/dtfmtsym.h",
+    "unicode/dtitvfmt.h",
+    "unicode/dtitvinf.h",
+    "unicode/dtptngen.h",
+    "unicode/dtrule.h",
+    "unicode/fieldpos.h",
+    "unicode/fmtable.h",
+    "unicode/format.h",
+    "unicode/fpositer.h",
+    "unicode/gender.h",
+    "unicode/gregocal.h",
+    "unicode/locdspnm.h",
+    "unicode/measfmt.h",
+    "unicode/measunit.h",
+    "unicode/measure.h",
+    "unicode/msgfmt.h",
+    "unicode/numfmt.h",
+    "unicode/numsys.h",
+    "unicode/plurfmt.h",
+    "unicode/plurrule.h",
+    "unicode/rbnf.h",
+    "unicode/rbtz.h",
+    "unicode/regex.h",
+    "unicode/region.h",
+    "unicode/reldatefmt.h",
+    "unicode/scientificnumberformatter.h",
+    "unicode/search.h",
+    "unicode/selfmt.h",
+    "unicode/simpletz.h",
+    "unicode/smpdtfmt.h",
+    "unicode/sortkey.h",
+    "unicode/stsearch.h",
+    "unicode/tblcoll.h",
+    "unicode/timezone.h",
+    "unicode/tmunit.h",
+    "unicode/tmutamt.h",
+    "unicode/tmutfmt.h",
+    "unicode/translit.h",
+    "unicode/tzfmt.h",
+    "unicode/tznames.h",
+    "unicode/tzrule.h",
+    "unicode/tztrans.h",
+    "unicode/ucal.h",
+    "unicode/ucol.h",
+    "unicode/ucoleitr.h",
+    "unicode/ucsdet.h",
+    "unicode/ucurr.h",
+    "unicode/udat.h",
+    "unicode/udateintervalformat.h",
+    "unicode/udatpg.h",
+    "unicode/udisplaycontext.h",
+    "unicode/ufieldpositer.h",
+    "unicode/uformattable.h",
+    "unicode/ugender.h",
+    "unicode/uldnames.h",
+    "unicode/ulocdata.h",
+    "unicode/umsg.h",
+    "unicode/unirepl.h",
+    "unicode/unum.h",
+    "unicode/unumsys.h",
+    "unicode/upluralrules.h",
+    "unicode/uregex.h",
+    "unicode/uregion.h",
+    "unicode/usearch.h",
+    "unicode/uspoof.h",
+    "unicode/utmscale.h",
+    "unicode/utrans.h",
+    "unicode/vtzone.h",
+  ]
+}
+
+shim_headers("icuuc_shim") {
+  root_path = "source/common"
+  headers = [
+    # This list can easily be updated using the command below:
+    # find third_party/icu/source/common/unicode \
+    # -iname '*.h' -printf '"%p",\n' | \
+    # sed -e 's|third_party/icu/source/common/||' | sort -u
+    "unicode/appendable.h",
+    "unicode/brkiter.h",
+    "unicode/bytestream.h",
+    "unicode/bytestrie.h",
+    "unicode/bytestriebuilder.h",
+    "unicode/caniter.h",
+    "unicode/chariter.h",
+    "unicode/dbbi.h",
+    "unicode/docmain.h",
+    "unicode/dtintrv.h",
+    "unicode/enumset.h",
+    "unicode/errorcode.h",
+    "unicode/filteredbrk.h",
+    "unicode/icudataver.h",
+    "unicode/icuplug.h",
+    "unicode/idna.h",
+    "unicode/listformatter.h",
+    "unicode/localpointer.h",
+    "unicode/locid.h",
+    "unicode/messagepattern.h",
+    "unicode/normalizer2.h",
+    "unicode/normlzr.h",
+    "unicode/parseerr.h",
+    "unicode/parsepos.h",
+    "unicode/platform.h",
+    "unicode/ptypes.h",
+    "unicode/putil.h",
+    "unicode/rbbi.h",
+    "unicode/rep.h",
+    "unicode/resbund.h",
+    "unicode/schriter.h",
+    "unicode/std_string.h",
+    "unicode/strenum.h",
+    "unicode/stringpiece.h",
+    "unicode/stringtriebuilder.h",
+    "unicode/symtable.h",
+    "unicode/ubidi.h",
+    "unicode/ubrk.h",
+    "unicode/ucasemap.h",
+    "unicode/ucat.h",
+    "unicode/uchar.h",
+    "unicode/ucharstrie.h",
+    "unicode/ucharstriebuilder.h",
+    "unicode/uchriter.h",
+    "unicode/uclean.h",
+    "unicode/ucnv.h",
+    "unicode/ucnv_cb.h",
+    "unicode/ucnv_err.h",
+    "unicode/ucnvsel.h",
+    "unicode/uconfig.h",
+    "unicode/udata.h",
+    "unicode/uenum.h",
+    "unicode/uidna.h",
+    "unicode/uiter.h",
+    "unicode/ulistformatter.h",
+    "unicode/uloc.h",
+    "unicode/umachine.h",
+    "unicode/umisc.h",
+    "unicode/unifilt.h",
+    "unicode/unifunct.h",
+    "unicode/unimatch.h",
+    "unicode/uniset.h",
+    "unicode/unistr.h",
+    "unicode/unorm.h",
+    "unicode/unorm2.h",
+    "unicode/uobject.h",
+    "unicode/urename.h",
+    "unicode/urep.h",
+    "unicode/ures.h",
+    "unicode/uscript.h",
+    "unicode/uset.h",
+    "unicode/usetiter.h",
+    "unicode/ushape.h",
+    "unicode/usprep.h",
+    "unicode/ustring.h",
+    "unicode/ustringtrie.h",
+    "unicode/utext.h",
+    "unicode/utf.h",
+    "unicode/utf16.h",
+    "unicode/utf32.h",
+    "unicode/utf8.h",
+    "unicode/utf_old.h",
+    "unicode/utrace.h",
+    "unicode/utypes.h",
+    "unicode/uvernum.h",
+    "unicode/uversion.h",
+  ]
+}

samples/GN/isolate.gni

@@ -0,0 +1,193 @@
+# Copyright 2016 the V8 project authors. All rights reserved.
+# Use of this source code is governed by a BSD-style license that can be
+# found in the LICENSE file.
+
+import("//build/config/sanitizers/sanitizers.gni")
+import("//third_party/icu/config.gni")
+import("v8.gni")
+
+declare_args() {
+  # Sets the test isolation mode (noop|prepare|check).
+  v8_test_isolation_mode = "noop"
+}
+
+template("v8_isolate_run") {
+  forward_variables_from(invoker,
+                         "*",
+                         [
+                           "deps",
+                           "isolate",
+                         ])
+
+  # Remember target name as within the action scope the target name will be
+  # different.
+  name = target_name
+
+  assert(defined(invoker.deps))
+  assert(defined(invoker.isolate))
+
+  if (name != "" && v8_test_isolation_mode != "noop") {
+    action(name + "_run") {
+      testonly = true
+
+      deps = invoker.deps
+
+      script = "//tools/isolate_driver.py"
+
+      sources = [
+        invoker.isolate,
+      ]
+
+      inputs = [
+        # Files that are known to be involved in this step.
+        "//tools/swarming_client/isolate.py",
+        "//tools/swarming_client/run_isolated.py",
+      ]
+
+      if (v8_test_isolation_mode == "prepare") {
+        outputs = [
+          "$root_out_dir/$name.isolated.gen.json",
+        ]
+      } else if (v8_test_isolation_mode == "check") {
+        outputs = [
+          "$root_out_dir/$name.isolated",
+          "$root_out_dir/$name.isolated.state",
+        ]
+      }
+
+      # Translate gn to gyp variables.
+      if (is_asan) {
+        asan = "1"
+      } else {
+        asan = "0"
+      }
+      if (is_msan) {
+        msan = "1"
+      } else {
+        msan = "0"
+      }
+      if (is_tsan) {
+        tsan = "1"
+      } else {
+        tsan = "0"
+      }
+      if (is_cfi) {
+        cfi_vptr = "1"
+      } else {
+        cfi_vptr = "0"
+      }
+      if (target_cpu == "x86") {
+        target_arch = "ia32"
+      } else {
+        target_arch = target_cpu
+      }
+      if (is_debug) {
+        configuration_name = "Debug"
+      } else {
+        configuration_name = "Release"
+      }
+      if (is_component_build) {
+        component = "shared_library"
+      } else {
+        component = "static_library"
+      }
+      if (icu_use_data_file) {
+        icu_use_data_file_flag = "1"
+      } else {
+        icu_use_data_file_flag = "0"
+      }
+      if (v8_enable_inspector) {
+        enable_inspector = "1"
+      } else {
+        enable_inspector = "0"
+      }
+      if (v8_use_external_startup_data) {
+        use_external_startup_data = "1"
+      } else {
+        use_external_startup_data = "0"
+      }
+      if (v8_use_snapshot) {
+        use_snapshot = "true"
+      } else {
+        use_snapshot = "false"
+      }
+      if (v8_has_valgrind) {
+        has_valgrind = "1"
+      } else {
+        has_valgrind = "0"
+      }
+      if (v8_gcmole) {
+        gcmole = "1"
+      } else {
+        gcmole = "0"
+      }
+
+      # Note, all paths will be rebased in isolate_driver.py to be relative to
+      # the isolate file.
+      args = [
+        v8_test_isolation_mode,
+        "--isolated",
+        rebase_path("$root_out_dir/$name.isolated", root_build_dir),
+        "--isolate",
+        rebase_path(invoker.isolate, root_build_dir),
+
+        # Path variables are used to replace file paths when loading a .isolate
+        # file
+        "--path-variable",
+        "DEPTH",
+        rebase_path("//", root_build_dir),
+        "--path-variable",
+        "PRODUCT_DIR",
+        rebase_path(root_out_dir, root_build_dir),
+
+        # TODO(machenbach): Set variables for remaining features.
+        "--config-variable",
+        "CONFIGURATION_NAME=$configuration_name",
+        "--config-variable",
+        "OS=$target_os",
+        "--config-variable",
+        "asan=$asan",
+        "--config-variable",
+        "cfi_vptr=$cfi_vptr",
+        "--config-variable",
+        "gcmole=$gcmole",
+        "--config-variable",
+        "has_valgrind=$has_valgrind",
+        "--config-variable",
+        "icu_use_data_file_flag=$icu_use_data_file_flag",
+        "--config-variable",
+        "is_gn=1",
+        "--config-variable",
+        "msan=$msan",
+        "--config-variable",
+        "tsan=$tsan",
+        "--config-variable",
+        "coverage=0",
+        "--config-variable",
+        "sanitizer_coverage=0",
+        "--config-variable",
+        "component=$component",
+        "--config-variable",
+        "target_arch=$target_arch",
+        "--config-variable",
+        "v8_enable_inspector=$enable_inspector",
+        "--config-variable",
+        "v8_use_external_startup_data=$use_external_startup_data",
+        "--config-variable",
+        "v8_use_snapshot=$use_snapshot",
+      ]
+
+      if (is_win) {
+        args += [
+          "--config-variable",
+          "msvs_version=2015",
+        ]
+      } else {
+        args += [
+          "--config-variable",
+          "msvs_version=0",
+        ]
+      }
+    }
+  }
+}

samples/Genie/Class.gs

@@ -0,0 +1,12 @@
+init
+	new Demo( "Demonstration class" ).run()
+
+class Demo
+	_message:string = ""
+
+	construct ( message:string = "Optional argument - no message passed in constructor" )
+		_message = message
+
+	def run()
+		print( _message )
+		

samples/Genie/Hello.gs

@@ -0,0 +1,2 @@
+init
+	print( "Hello, World!" )

samples/HCL/main.tf

@@ -0,0 +1,135 @@
+resource "aws_security_group" "elb_sec_group" {
+  description = "Allow traffic from the internet to ELB port 80"
+  vpc_id = "${var.vpc_id}"
+
+  ingress {
+      from_port = 80
+      to_port = 80
+      protocol = "tcp"
+      cidr_blocks = ["${split(",", var.allowed_cidr_blocks)}"]
+  }
+
+  egress {
+      from_port = 0
+      to_port = 0
+      protocol = "-1"
+      cidr_blocks = ["0.0.0.0/0"]
+  }
+}
+
+resource "aws_security_group" "dokku_allow_ssh_from_internal" {
+  description = "Allow git access over ssh from the private subnet"
+  vpc_id = "${var.vpc_id}"
+
+  ingress {
+      from_port = 22
+      to_port = 22
+      protocol = "tcp"
+      cidr_blocks = ["${var.private_subnet_cidr}"]
+  }
+
+  egress {
+      from_port = 0
+      to_port = 0
+      protocol = "-1"
+      cidr_blocks = ["0.0.0.0/0"]
+  }
+}
+
+resource "aws_security_group" "allow_from_elb_to_instance" {
+  description = "Allow traffic from the ELB to the private instance"
+  vpc_id = "${var.vpc_id}"
+
+  ingress {
+      security_groups = ["${aws_security_group.elb_sec_group.id}"]
+      from_port = 80
+      to_port = 80
+      protocol = "tcp"
+  }
+
+  egress {
+      from_port = 0
+      to_port = 0
+      protocol = "-1"
+      cidr_blocks = ["0.0.0.0/0"]
+  }
+}
+
+resource "aws_instance" "dokku" {
+  ami = "ami-47a23a30"
+  instance_type = "${var.instance_type}"
+  associate_public_ip_address = false
+  key_name = "${var.key_name}"
+  subnet_id = "${var.private_subnet_id}"
+  vpc_security_group_ids = [
+    "${var.bastion_sec_group_id}",
+    "${aws_security_group.allow_from_elb_to_instance.id}",
+    "${aws_security_group.dokku_allow_ssh_from_internal.id}"
+  ]
+  tags {
+    Name = "${var.name}"
+  }
+  connection {
+    user = "ubuntu"
+    private_key = "${var.private_key}"
+    bastion_host = "${var.bastion_host}"
+    bastion_port = "${var.bastion_port}"
+    bastion_user = "${var.bastion_user}"
+    bastion_private_key = "${var.bastion_private_key}"
+  }
+  provisioner "file" {
+    source = "${path.module}/../scripts/install-dokku.sh"
+    destination = "/home/ubuntu/install-dokku.sh"
+  }
+  provisioner "remote-exec" {
+    inline = [
+      "chmod +x /home/ubuntu/install-dokku.sh",
+      "HOSTNAME=${var.hostname} /home/ubuntu/install-dokku.sh"
+    ]
+  }
+}
+
+resource "aws_elb" "elb_dokku" {
+  name = "elb-dokku-${var.name}"
+  subnets = ["${var.public_subnet_id}"]
+  security_groups = ["${aws_security_group.elb_sec_group.id}"]
+
+  listener {
+    instance_port = 80
+    instance_protocol = "http"
+    lb_port = 80
+    lb_protocol = "http"
+  }
+
+  health_check {
+    healthy_threshold = 2
+    unhealthy_threshold = 2
+    timeout = 3
+    target = "HTTP:80/"
+    interval = 30
+  }
+
+  instances = ["${aws_instance.dokku.id}"]
+  cross_zone_load_balancing = false
+  idle_timeout = 400
+
+  tags {
+    Name = "elb-dokku-${var.name}"
+  }
+}
+
+resource "aws_route53_record" "dokku-deploy" {
+   zone_id = "${var.zone_id}"
+   name = "deploy.${var.hostname}"
+   type = "A"
+   ttl = "300"
+   records = ["${aws_instance.dokku.private_ip}"]
+}
+
+resource "aws_route53_record" "dokku-wildcard" {
+   zone_id = "${var.zone_id}"
+   name = "*.${var.hostname}"
+   type = "CNAME"
+   ttl = "300"
+   records = ["${aws_elb.elb_dokku.dns_name}"]
+}

samples/HLSL/bloom.cginc

@@ -0,0 +1,89 @@
+// From https://github.com/Unity-Technologies/PostProcessing/blob/master/PostProcessing/Resources/Shaders/Bloom.cginc
+// Licensed under the MIT license
+
+#ifndef __BLOOM__
+#define __BLOOM__
+
+#include "Common.cginc"
+
+// Brightness function
+half Brightness(half3 c)
+{
+    return Max3(c);
+}
+
+// 3-tap median filter
+half3 Median(half3 a, half3 b, half3 c)
+{
+    return a + b + c - min(min(a, b), c) - max(max(a, b), c);
+}
+
+// Downsample with a 4x4 box filter
+half3 DownsampleFilter(sampler2D tex, float2 uv, float2 texelSize)
+{
+    float4 d = texelSize.xyxy * float4(-1.0, -1.0, 1.0, 1.0);
+
+    half3 s;
+    s = DecodeHDR(tex2D(tex, uv + d.xy));
+    s += DecodeHDR(tex2D(tex, uv + d.zy));
+    s += DecodeHDR(tex2D(tex, uv + d.xw));
+    s += DecodeHDR(tex2D(tex, uv + d.zw));
+
+    return s * (1.0 / 4.0);
+}
+
+// Downsample with a 4x4 box filter + anti-flicker filter
+half3 DownsampleAntiFlickerFilter(sampler2D tex, float2 uv, float2 texelSize)
+{
+    float4 d = texelSize.xyxy * float4(-1.0, -1.0, 1.0, 1.0);
+
+    half3 s1 = DecodeHDR(tex2D(tex, uv + d.xy));
+    half3 s2 = DecodeHDR(tex2D(tex, uv + d.zy));
+    half3 s3 = DecodeHDR(tex2D(tex, uv + d.xw));
+    half3 s4 = DecodeHDR(tex2D(tex, uv + d.zw));
+
+    // Karis's luma weighted average (using brightness instead of luma)
+    half s1w = 1.0 / (Brightness(s1) + 1.0);
+    half s2w = 1.0 / (Brightness(s2) + 1.0);
+    half s3w = 1.0 / (Brightness(s3) + 1.0);
+    half s4w = 1.0 / (Brightness(s4) + 1.0);
+    half one_div_wsum = 1.0 / (s1w + s2w + s3w + s4w);
+
+    return (s1 * s1w + s2 * s2w + s3 * s3w + s4 * s4w) * one_div_wsum;
+}
+
+half3 UpsampleFilter(sampler2D tex, float2 uv, float2 texelSize, float sampleScale)
+{
+#if MOBILE_OR_CONSOLE
+    // 4-tap bilinear upsampler
+    float4 d = texelSize.xyxy * float4(-1.0, -1.0, 1.0, 1.0) * (sampleScale * 0.5);
+
+    half3 s;
+    s =  DecodeHDR(tex2D(tex, uv + d.xy));
+    s += DecodeHDR(tex2D(tex, uv + d.zy));
+    s += DecodeHDR(tex2D(tex, uv + d.xw));
+    s += DecodeHDR(tex2D(tex, uv + d.zw));
+
+    return s * (1.0 / 4.0);
+#else
+    // 9-tap bilinear upsampler (tent filter)
+    float4 d = texelSize.xyxy * float4(1.0, 1.0, -1.0, 0.0) * sampleScale;
+
+    half3 s;
+    s =  DecodeHDR(tex2D(tex, uv - d.xy));
+    s += DecodeHDR(tex2D(tex, uv - d.wy)) * 2.0;
+    s += DecodeHDR(tex2D(tex, uv - d.zy));
+
+    s += DecodeHDR(tex2D(tex, uv + d.zw)) * 2.0;
+    s += DecodeHDR(tex2D(tex, uv))        * 4.0;
+    s += DecodeHDR(tex2D(tex, uv + d.xw)) * 2.0;
+
+    s += DecodeHDR(tex2D(tex, uv + d.zy));
+    s += DecodeHDR(tex2D(tex, uv + d.wy)) * 2.0;
+    s += DecodeHDR(tex2D(tex, uv + d.xy));
+
+    return s * (1.0 / 16.0);
+#endif
+}
+
+#endif // __BLOOM__

samples/HTML+Django/nunjucks.njk

@@ -0,0 +1,48 @@
+{% from "forms.html" import label as description %}
+
+
+{% macro field(name, value='', type='text') %}
+    <div class="field">
+        <input type="{{ type }}" name="{{ name }}"
+                value="{{ value | escape }}" />
+    </div>
+{% endmacro %}
+
+<html>
+<head>
+    {% extends "head.html" %}
+</head>
+<body>
+{% if horse %}
+    Chuck Norris once kicked a horse in the chin. Its descendants are known today as Giraffes.
+{% elif optimus %}
+    Chuck Norris once urinated in a semi truck's gas tank as a joke....that truck is now known as Optimus Prime.
+{% else %}
+    Chuck Norris threw a grenade and killed 50 people, then the grenade exploded.
+{% endif %}
+
+{% block left %}
+    This is the left side!
+{% endblock %}
+
+{% block right %}
+    This is the right side!
+{% endblock %}
+
+{{ description('Username') }}
+{{ field('user') }}
+{{ field('pass', type='password') }}
+
+<h1>Posts</h1>
+<ul>
+    {% for item in items %}
+        <li>{{ item.title }}</li>
+    {% else %}
+        <li>This would display if the 'item' collection were empty</li>
+    {% endfor %}
+</ul>
+
+{# Don't escape foo #}
+{{ foo | safe }}
+</body>
+</html>

samples/JSON5/filenames/.babelrc

@@ -0,0 +1,6 @@
+{
+  "presets": [
+    "es2015",
+    "es2016"
+  ]
+}

samples/JavaScript/ccalc-lex.js

@@ -0,0 +1,923 @@
+/* generated by jison-lex 0.3.4-159 */
+var ccalcLex = (function () {
+// See also:
+// http://stackoverflow.com/questions/1382107/whats-a-good-way-to-extend-error-in-javascript/#35881508
+// but we keep the prototype.constructor and prototype.name assignment lines too for compatibility
+// with userland code which might access the derived class in a 'classic' way.
+function JisonLexerError(msg, hash) {
+    Object.defineProperty(this, 'name', {
+        enumerable: false,
+        writable: false,
+        value: 'JisonLexerError'
+    });
+
+    if (msg == null) msg = '???';
+
+    Object.defineProperty(this, 'message', {
+        enumerable: false,
+        writable: true,
+        value: msg
+    });
+
+    this.hash = hash;
+
+    var stacktrace;
+    if (hash && hash.exception instanceof Error) {
+        var ex2 = hash.exception;
+        this.message = ex2.message || msg;
+        stacktrace = ex2.stack;
+    }
+    if (!stacktrace) {
+        if (Error.hasOwnProperty('captureStackTrace')) { // V8
+            Error.captureStackTrace(this, this.constructor);
+        } else {
+            stacktrace = (new Error(msg)).stack;
+        }
+    }
+    if (stacktrace) {
+        Object.defineProperty(this, 'stack', {
+            enumerable: false,
+            writable: false,
+            value: stacktrace
+        });
+    }
+}
+
+if (typeof Object.setPrototypeOf === 'function') {
+    Object.setPrototypeOf(JisonLexerError.prototype, Error.prototype);
+} else {
+    JisonLexerError.prototype = Object.create(Error.prototype);
+}
+JisonLexerError.prototype.constructor = JisonLexerError;
+JisonLexerError.prototype.name = 'JisonLexerError';
+
+
+var lexer = {
+    EOF: 1,
+    ERROR: 2,
+
+    // JisonLexerError: JisonLexerError,        // <-- injected by the code generator
+
+    // options: {},                             // <-- injected by the code generator
+
+    // yy: ...,                                 // <-- injected by setInput()
+
+    __currentRuleSet__: null,                   // <-- internal rule set cache for the current lexer state
+
+    __error_infos: [],                          // INTERNAL USE ONLY: the set of lexErrorInfo objects created since the last cleanup
+
+    __decompressed: false,                      // INTERNAL USE ONLY: mark whether the lexer instance has been 'unfolded' completely and is now ready for use
+
+    done: false,                                // INTERNAL USE ONLY
+    _backtrack: false,                          // INTERNAL USE ONLY
+    _input: '',                                 // INTERNAL USE ONLY
+    _more: false,                               // INTERNAL USE ONLY
+    _signaled_error_token: false,               // INTERNAL USE ONLY
+
+    conditionStack: [],                         // INTERNAL USE ONLY; managed via `pushState()`, `popState()`, `topState()` and `stateStackSize()`
+
+    match: '',                                  // READ-ONLY EXTERNAL ACCESS - ADVANCED USE ONLY: tracks input which has been matched so far for the lexer token under construction. `match` is identical to `yytext` except that this one still contains the matched input string after `lexer.performAction()` has been invoked, where userland code MAY have changed/replaced the `yytext` value entirely!
+    matched: '',                                // READ-ONLY EXTERNAL ACCESS - ADVANCED USE ONLY: tracks entire input which has been matched so far
+    matches: false,                             // READ-ONLY EXTERNAL ACCESS - ADVANCED USE ONLY: tracks RE match result for last (successful) match attempt
+    yytext: '',                                 // ADVANCED USE ONLY: tracks input which has been matched so far for the lexer token under construction; this value is transferred to the parser as the 'token value' when the parser consumes the lexer token produced through a call to the `lex()` API.
+    offset: 0,                                  // READ-ONLY EXTERNAL ACCESS - ADVANCED USE ONLY: tracks the 'cursor position' in the input string, i.e. the number of characters matched so far
+    yyleng: 0,                                  // READ-ONLY EXTERNAL ACCESS - ADVANCED USE ONLY: length of matched input for the token under construction (`yytext`)
+    yylineno: 0,                                // READ-ONLY EXTERNAL ACCESS - ADVANCED USE ONLY: 'line number' at which the token under construction is located
+    yylloc: null,                               // READ-ONLY EXTERNAL ACCESS - ADVANCED USE ONLY: tracks location info (lines + columns) for the token under construction
+
+    // INTERNAL USE: construct a suitable error info hash object instance for `parseError`.
+    constructLexErrorInfo: function lexer_constructLexErrorInfo(msg, recoverable) {
+        var pei = {
+            errStr: msg,
+            recoverable: !!recoverable,
+            text: this.match,           // This one MAY be empty; userland code should use the `upcomingInput` API to obtain more text which follows the 'lexer cursor position'...
+            token: null,
+            line: this.yylineno,
+            loc: this.yylloc,
+            yy: this.yy,
+            lexer: this,
+
+            // and make sure the error info doesn't stay due to potential
+            // ref cycle via userland code manipulations.
+            // These would otherwise all be memory leak opportunities!
+            //
+            // Note that only array and object references are nuked as those
+            // constitute the set of elements which can produce a cyclic ref.
+            // The rest of the members is kept intact as they are harmless.
+            destroy: function destructLexErrorInfo() {
+                // remove cyclic references added to error info:
+                // info.yy = null;
+                // info.lexer = null;
+                // ...
+                var rec = !!this.recoverable;
+                for (var key in this) {
+                    if (this.hasOwnProperty(key) && typeof key === 'object') {
+                        this[key] = undefined;
+                    }
+                }
+                this.recoverable = rec;
+            }
+        };
+        // track this instance so we can `destroy()` it once we deem it superfluous and ready for garbage collection!
+        this.__error_infos.push(pei);
+        return pei;
+    },
+
+    parseError: function lexer_parseError(str, hash) {
+        if (this.yy.parser && typeof this.yy.parser.parseError === 'function') {
+            return this.yy.parser.parseError(str, hash) || this.ERROR;
+        } else if (typeof this.yy.parseError === 'function') {
+            return this.yy.parseError.call(this, str, hash) || this.ERROR;
+        } else {
+            throw new this.JisonLexerError(str);
+        }
+    },
+
+    // final cleanup function for when we have completed lexing the input; 
+    // make it an API so that external code can use this one once userland
+    // code has decided it's time to destroy any lingering lexer error
+    // hash object instances and the like: this function helps to clean
+    // up these constructs, which *may* carry cyclic references which would
+    // otherwise prevent the instances from being properly and timely
+    // garbage-collected, i.e. this function helps prevent memory leaks!
+    cleanupAfterLex: function lexer_cleanupAfterLex(do_not_nuke_errorinfos) {
+        var rv;
+
+        // prevent lingering circular references from causing memory leaks:
+        this.setInput('', {});
+
+        // nuke the error hash info instances created during this run.
+        // Userland code must COPY any data/references
+        // in the error hash instance(s) it is more permanently interested in.
+        if (!do_not_nuke_errorinfos) {
+            for (var i = this.__error_infos.length - 1; i >= 0; i--) {
+                var el = this.__error_infos[i];
+                if (el && typeof el.destroy === 'function') {
+                    el.destroy();
+                }
+            }
+            this.__error_infos.length = 0;
+        }
+
+        return this;
+    },
+
+    // clear the lexer token context; intended for internal use only
+    clear: function lexer_clear() {
+        this.yytext = '';
+        this.yyleng = 0;
+        this.match = '';
+        this.matches = false;
+        this._more = false;
+        this._backtrack = false;
+    },
+
+    // resets the lexer, sets new input
+    setInput: function lexer_setInput(input, yy) {
+        this.yy = yy || this.yy || {};
+
+        // also check if we've fully initialized the lexer instance,
+        // including expansion work to be done to go from a loaded
+        // lexer to a usable lexer:
+        if (!this.__decompressed) {
+          // step 1: decompress the regex list:
+          var rules = this.rules;
+          for (var i = 0, len = rules.length; i < len; i++) {
+            var rule_re = rules[i];
+
+            // compression: is the RE an xref to another RE slot in the rules[] table?
+            if (typeof rule_re === 'number') {
+              rules[i] = rules[rule_re];
+            }
+          }
+
+          // step 2: unfold the conditions[] set to make these ready for use:
+          var conditions = this.conditions;
+          for (var k in conditions) {
+            var spec = conditions[k];
+
+            var rule_ids = spec.rules;
+
+            var len = rule_ids.length;
+            var rule_regexes = new Array(len + 1);            // slot 0 is unused; we use a 1-based index approach here to keep the hottest code in `lexer_next()` fast and simple!
+            var rule_new_ids = new Array(len + 1);
+
+            if (this.rules_prefix1) {
+                var rule_prefixes = new Array(65536);
+                var first_catch_all_index = 0;
+
+                for (var i = 0; i < len; i++) {
+                  var idx = rule_ids[i];
+                  var rule_re = rules[idx];
+                  rule_regexes[i + 1] = rule_re;
+                  rule_new_ids[i + 1] = idx;
+
+                  var prefix = this.rules_prefix1[idx];
+                  // compression: is the PREFIX-STRING an xref to another PREFIX-STRING slot in the rules_prefix1[] table?
+                  if (typeof prefix === 'number') {
+                    prefix = this.rules_prefix1[prefix];
+                  }
+                  // init the prefix lookup table: first come, first serve...
+                  if (!prefix) {
+                    if (!first_catch_all_index) {
+                      first_catch_all_index = i + 1;
+                    }
+                  } else {
+                    for (var j = 0, pfxlen = prefix.length; j < pfxlen; j++) {
+                      var pfxch = prefix.charCodeAt(j);
+                      // first come, first serve:
+                      if (!rule_prefixes[pfxch]) {
+                        rule_prefixes[pfxch] = i + 1;
+                      }  
+                    }
+                  }
+                }
+
+                // if no catch-all prefix has been encountered yet, it means all
+                // rules have limited prefix sets and it MAY be that particular
+                // input characters won't be recognized by any rule in this 
+                // condition state.
+                // 
+                // To speed up their discovery at run-time while keeping the
+                // remainder of the lexer kernel code very simple (and fast),
+                // we point these to an 'illegal' rule set index *beyond*
+                // the end of the rule set.
+                if (!first_catch_all_index) {
+                  first_catch_all_index = len + 1;
+                }
+
+                for (var i = 0; i < 65536; i++) {
+                  if (!rule_prefixes[i]) {
+                    rule_prefixes[i] = first_catch_all_index; 
+                  }
+                }
+
+                spec.__dispatch_lut = rule_prefixes;
+            } else {
+                for (var i = 0; i < len; i++) {
+                  var idx = rule_ids[i];
+                  var rule_re = rules[idx];
+                  rule_regexes[i + 1] = rule_re;
+                  rule_new_ids[i + 1] = idx;
+                }
+            }
+
+            spec.rules = rule_new_ids;
+            spec.__rule_regexes = rule_regexes;
+            spec.__rule_count = len;
+          }
+
+          this.__decompressed = true;
+        }
+
+        this._input = input || '';
+        this.clear();
+        this._signaled_error_token = false;
+        this.done = false;
+        this.yylineno = 0;
+        this.matched = '';
+        this.conditionStack = ['INITIAL'];
+        this.__currentRuleSet__ = null;
+        this.yylloc = {
+            first_line: 1,
+            first_column: 0,
+            last_line: 1,
+            last_column: 0
+        };
+        if (this.options.ranges) {
+            this.yylloc.range = [0, 0];
+        }
+        this.offset = 0;
+        return this;
+    },
+
+    // consumes and returns one char from the input
+    input: function lexer_input() {
+        if (!this._input) {
+            this.done = true;
+            return null;
+        }
+        var ch = this._input[0];
+        this.yytext += ch;
+        this.yyleng++;
+        this.offset++;
+        this.match += ch;
+        this.matched += ch;
+        // Count the linenumber up when we hit the LF (or a stand-alone CR).
+        // On CRLF, the linenumber is incremented when you fetch the CR or the CRLF combo
+        // and we advance immediately past the LF as well, returning both together as if
+        // it was all a single 'character' only.
+        var slice_len = 1;
+        var lines = false;
+        if (ch === '\n') {
+            lines = true;
+        } else if (ch === '\r') {
+            lines = true;
+            var ch2 = this._input[1];
+            if (ch2 === '\n') {
+                slice_len++;
+                ch += ch2;
+                this.yytext += ch2;
+                this.yyleng++;
+                this.offset++;
+                this.match += ch2;
+                this.matched += ch2;
+                if (this.options.ranges) {
+                    this.yylloc.range[1]++;
+                }
+            }
+        }
+        if (lines) {
+            this.yylineno++;
+            this.yylloc.last_line++;
+        } else {
+            this.yylloc.last_column++;
+        }
+        if (this.options.ranges) {
+            this.yylloc.range[1]++;
+        }
+
+        this._input = this._input.slice(slice_len);
+        return ch;
+    },
+
+    // unshifts one char (or a string) into the input
+    unput: function lexer_unput(ch) {
+        var len = ch.length;
+        var lines = ch.split(/(?:\r\n?|\n)/g);
+
+        this._input = ch + this._input;
+        this.yytext = this.yytext.substr(0, this.yytext.length - len);
+        //this.yyleng -= len;
+        this.offset -= len;
+        var oldLines = this.match.split(/(?:\r\n?|\n)/g);
+        this.match = this.match.substr(0, this.match.length - len);
+        this.matched = this.matched.substr(0, this.matched.length - len);
+
+        if (lines.length - 1) {
+            this.yylineno -= lines.length - 1;
+        }
+
+        this.yylloc.last_line = this.yylineno + 1;
+        this.yylloc.last_column = (lines ?
+                (lines.length === oldLines.length ? this.yylloc.first_column : 0)
+                + oldLines[oldLines.length - lines.length].length - lines[0].length :
+                this.yylloc.first_column - len);
+
+        if (this.options.ranges) {
+            this.yylloc.range[1] = this.yylloc.range[0] + this.yyleng - len;
+        }
+        this.yyleng = this.yytext.length;
+        this.done = false;
+        return this;
+    },
+
+    // When called from action, caches matched text and appends it on next action
+    more: function lexer_more() {
+        this._more = true;
+        return this;
+    },
+
+    // When called from action, signals the lexer that this rule fails to match the input, so the next matching rule (regex) should be tested instead.
+    reject: function lexer_reject() {
+        if (this.options.backtrack_lexer) {
+            this._backtrack = true;
+        } else {
+            // when the parseError() call returns, we MUST ensure that the error is registered.
+            // We accomplish this by signaling an 'error' token to be produced for the current
+            // .lex() run.
+            var p = this.constructLexErrorInfo('Lexical error on line ' + (this.yylineno + 1) + '. You can only invoke reject() in the lexer when the lexer is of the backtracking persuasion (options.backtrack_lexer = true).\n' + this.showPosition(), false);
+            this._signaled_error_token = (this.parseError(p.errStr, p) || this.ERROR);
+        }
+        return this;
+    },
+
+    // retain first n characters of the match
+    less: function lexer_less(n) {
+        return this.unput(this.match.slice(n));
+    },
+
+    // return (part of the) already matched input, i.e. for error messages.
+    // Limit the returned string length to `maxSize` (default: 20).
+    // Limit the returned string to the `maxLines` number of lines of input (default: 1).
+    // Negative limit values equal *unlimited*.
+    pastInput: function lexer_pastInput(maxSize, maxLines) {
+        var past = this.matched.substring(0, this.matched.length - this.match.length);
+        if (maxSize < 0)
+            maxSize = past.length;
+        else if (!maxSize)
+            maxSize = 20;
+        if (maxLines < 0)
+            maxLines = past.length;         // can't ever have more input lines than this!
+        else if (!maxLines)
+            maxLines = 1;
+        // `substr` anticipation: treat \r\n as a single character and take a little
+        // more than necessary so that we can still properly check against maxSize
+        // after we've transformed and limited the newLines in here:
+        past = past.substr(-maxSize * 2 - 2);
+        // now that we have a significantly reduced string to process, transform the newlines
+        // and chop them, then limit them:
+        var a = past.replace(/\r\n|\r/g, '\n').split('\n');
+        a = a.slice(-maxLines);
+        past = a.join('\n');
+        // When, after limiting to maxLines, we still have too much to return, 
+        // do add an ellipsis prefix...
+        if (past.length > maxSize) {
+            past = '...' + past.substr(-maxSize);
+        }
+        return past;
+    },
+
+    // return (part of the) upcoming input, i.e. for error messages.
+    // Limit the returned string length to `maxSize` (default: 20).
+    // Limit the returned string to the `maxLines` number of lines of input (default: 1).
+    // Negative limit values equal *unlimited*.
+    upcomingInput: function lexer_upcomingInput(maxSize, maxLines) {
+        var next = this.match;
+        if (maxSize < 0)
+            maxSize = next.length + this._input.length;
+        else if (!maxSize)
+            maxSize = 20;
+        if (maxLines < 0)
+            maxLines = maxSize;         // can't ever have more input lines than this!
+        else if (!maxLines)
+            maxLines = 1;
+        // `substring` anticipation: treat \r\n as a single character and take a little
+        // more than necessary so that we can still properly check against maxSize
+        // after we've transformed and limited the newLines in here:
+        if (next.length < maxSize * 2 + 2) {
+            next += this._input.substring(0, maxSize * 2 + 2);  // substring is faster on Chrome/V8
+        }
+        // now that we have a significantly reduced string to process, transform the newlines
+        // and chop them, then limit them:
+        var a = next.replace(/\r\n|\r/g, '\n').split('\n');
+        a = a.slice(0, maxLines);
+        next = a.join('\n');
+        // When, after limiting to maxLines, we still have too much to return, 
+        // do add an ellipsis postfix...
+        if (next.length > maxSize) {
+            next = next.substring(0, maxSize) + '...';
+        }
+        return next;
+    },
+
+    // return a string which displays the character position where the lexing error occurred, i.e. for error messages
+    showPosition: function lexer_showPosition(maxPrefix, maxPostfix) {
+        var pre = this.pastInput(maxPrefix).replace(/\s/g, ' ');
+        var c = new Array(pre.length + 1).join('-');
+        return pre + this.upcomingInput(maxPostfix).replace(/\s/g, ' ') + '\n' + c + '^';
+    },
+
+    // helper function, used to produce a human readable description as a string, given
+    // the input `yylloc` location object. 
+    // Set `display_range_too` to TRUE to include the string character index position(s)
+    // in the description if the `yylloc.range` is available. 
+    describeYYLLOC: function lexer_describe_yylloc(yylloc, display_range_too) {
+        var l1 = yylloc.first_line;
+        var l2 = yylloc.last_line;
+        var o1 = yylloc.first_column;
+        var o2 = yylloc.last_column - 1;
+        var dl = l2 - l1;
+        var d_o = (dl === 0 ? o2 - o1 : 1000);
+        var rv;
+        if (dl === 0) {
+            rv = 'line ' + l1 + ', ';
+            if (d_o === 0) {
+                rv += 'column ' + o1;
+            } else {
+                rv += 'columns ' + o1 + ' .. ' + o2;
+            }
+        } else {
+            rv = 'lines ' + l1 + '(column ' + o1 + ') .. ' + l2 + '(column ' + o2 + ')';
+        }
+        if (yylloc.range && display_range_too) {
+            var r1 = yylloc.range[0];
+            var r2 = yylloc.range[1] - 1;
+            if (r2 === r1) {
+                rv += ' {String Offset: ' + r1 + '}';
+            } else {
+                rv += ' {String Offset range: ' + r1 + ' .. ' + r2 + '}';
+            }
+        }
+        return rv;
+        // return JSON.stringify(yylloc);
+    },
+
+    // test the lexed token: return FALSE when not a match, otherwise return token.
+    //
+    // `match` is supposed to be an array coming out of a regex match, i.e. `match[0]`
+    // contains the actually matched text string.
+    //
+    // Also move the input cursor forward and update the match collectors:
+    // - yytext
+    // - yyleng
+    // - match
+    // - matches
+    // - yylloc
+    // - offset
+    test_match: function lexer_test_match(match, indexed_rule) {
+        var token,
+            lines,
+            backup,
+            match_str;
+
+        if (this.options.backtrack_lexer) {
+            // save context
+            backup = {
+                yylineno: this.yylineno,
+                yylloc: {
+                    first_line: this.yylloc.first_line,
+                    last_line: this.last_line,
+                    first_column: this.yylloc.first_column,
+                    last_column: this.yylloc.last_column
+                },
+                yytext: this.yytext,
+                match: this.match,
+                matches: this.matches,
+                matched: this.matched,
+                yyleng: this.yyleng,
+                offset: this.offset,
+                _more: this._more,
+                _input: this._input,
+                yy: this.yy,
+                conditionStack: this.conditionStack.slice(0),
+                done: this.done
+            };
+            if (this.options.ranges) {
+                backup.yylloc.range = this.yylloc.range.slice(0);
+            }
+        }
+
+        match_str = match[0];
+        lines = match_str.match(/(?:\r\n?|\n).*/g);
+        if (lines) {
+            this.yylineno += lines.length;
+        }
+        this.yylloc = {
+            first_line: this.yylloc.last_line,
+            last_line: this.yylineno + 1,
+            first_column: this.yylloc.last_column,
+            last_column: lines ?
+                         lines[lines.length - 1].length - lines[lines.length - 1].match(/\r?\n?/)[0].length :
+                         this.yylloc.last_column + match_str.length
+        };
+        this.yytext += match_str;
+        this.match += match_str;
+        this.matches = match;
+        this.yyleng = this.yytext.length;
+        if (this.options.ranges) {
+            this.yylloc.range = [this.offset, this.offset + this.yyleng];
+        }
+        // previous lex rules MAY have invoked the `more()` API rather than producing a token:
+        // those rules will already have moved this `offset` forward matching their match lengths,
+        // hence we must only add our own match length now:
+        this.offset += match_str.length;
+        this._more = false;
+        this._backtrack = false;
+        this._input = this._input.slice(match_str.length);
+        this.matched += match_str;
+
+        // calling this method: 
+        //
+        //   function lexer__performAction(yy, yy_, $avoiding_name_collisions, YY_START) {...}
+        token = this.performAction.call(this, this.yy, this, indexed_rule, this.conditionStack[this.conditionStack.length - 1] /* = YY_START */);
+        // otherwise, when the action codes are all simple return token statements:
+        //token = this.simpleCaseActionClusters[indexed_rule];
+
+        if (this.done && this._input) {
+            this.done = false;
+        }
+        if (token) {
+            return token;
+        } else if (this._backtrack) {
+            // recover context
+            for (var k in backup) {
+                this[k] = backup[k];
+            }
+            this.__currentRuleSet__ = null;
+            return false; // rule action called reject() implying the next rule should be tested instead.
+        } else if (this._signaled_error_token) {
+            // produce one 'error' token as .parseError() in reject() did not guarantee a failure signal by throwing an exception!
+            token = this._signaled_error_token;
+            this._signaled_error_token = false;
+            return token;
+        }
+        return false;
+    },
+
+    // return next match in input
+    next: function lexer_next() {
+        if (this.done) {
+            this.clear();
+            return this.EOF;
+        }
+        if (!this._input) {
+            this.done = true;
+        }
+
+        var token,
+            match,
+            tempMatch,
+            index;
+        if (!this._more) {
+            this.clear();
+        }
+        var spec = this.__currentRuleSet__;
+        if (!spec) {
+            // Update the ruleset cache as we apparently encountered a state change or just started lexing.
+            // The cache is set up for fast lookup -- we assume a lexer will switch states much less often than it will
+            // invoke the `lex()` token-producing API and related APIs, hence caching the set for direct access helps
+            // speed up those activities a tiny bit.
+            spec = this.__currentRuleSet__ = this._currentRules();
+        }
+
+        var rule_ids = spec.rules;
+//        var dispatch = spec.__dispatch_lut;
+        var regexes = spec.__rule_regexes;
+        var len = spec.__rule_count;
+
+//        var c0 = this._input[0];
+
+        // Note: the arrays are 1-based, while `len` itself is a valid index, 
+        // hence the non-standard less-or-equal check in the next loop condition!
+        // 
+        // `dispatch` is a lookup table which lists the *first* rule which matches the 1-char *prefix* of the rule-to-match.
+        // By using that array as a jumpstart, we can cut down on the otherwise O(n*m) behaviour of this lexer, down to
+        // O(n) ideally, where:
+        // 
+        // - N is the number of input particles -- which is not precisely characters 
+        //   as we progress on a per-regex-match basis rather than on a per-character basis
+        //   
+        // - M is the number of rules (regexes) to test in the active condition state.
+        //  
+        for (var i = 1 /* (dispatch[c0] || 1) */ ; i <= len; i++) {
+            tempMatch = this._input.match(regexes[i]);
+            if (tempMatch && (!match || tempMatch[0].length > match[0].length)) {
+                match = tempMatch;
+                index = i;
+                if (this.options.backtrack_lexer) {
+                    token = this.test_match(tempMatch, rule_ids[i]);
+                    if (token !== false) {
+                        return token;
+                    } else if (this._backtrack) {
+                        match = undefined;
+                        continue; // rule action called reject() implying a rule MISmatch.
+                    } else {
+                        // else: this is a lexer rule which consumes input without producing a token (e.g. whitespace)
+                        return false;
+                    }
+                } else if (!this.options.flex) {
+                    break;
+                }
+            }
+        }
+        if (match) {
+            token = this.test_match(match, rule_ids[index]);
+            if (token !== false) {
+                return token;
+            }
+            // else: this is a lexer rule which consumes input without producing a token (e.g. whitespace)
+            return false;
+        }
+        if (this._input === '') {
+            this.done = true;
+            return this.EOF;
+        } else {
+            var p = this.constructLexErrorInfo('Lexical error on line ' + (this.yylineno + 1) + '. Unrecognized text.\n' + this.showPosition(), this.options.lexer_errors_are_recoverable);
+            token = (this.parseError(p.errStr, p) || this.ERROR);
+            if (token === this.ERROR) {
+                // we can try to recover from a lexer error that parseError() did not 'recover' for us, by moving forward at least one character at a time:
+                if (!this.match.length) {
+                    this.input();
+                }
+            }
+            return token;
+        }
+    },
+
+    // return next match that has a token
+    lex: function lexer_lex() {
+        var r;
+        // allow the PRE/POST handlers set/modify the return token for maximum flexibility of the generated lexer:
+        if (typeof this.options.pre_lex === 'function') {
+            r = this.options.pre_lex.call(this);
+        }
+        while (!r) {
+            r = this.next();
+        }
+        if (typeof this.options.post_lex === 'function') {
+            // (also account for a userdef function which does not return any value: keep the token as is)
+            r = this.options.post_lex.call(this, r) || r;
+        }
+        return r;
+    },
+
+    // backwards compatible alias for `pushState()`;
+    // the latter is symmetrical with `popState()` and we advise to use
+    // those APIs in any modern lexer code, rather than `begin()`.
+    begin: function lexer_begin(condition) {
+        return this.pushState(condition);
+    },
+
+    // activates a new lexer condition state (pushes the new lexer condition state onto the condition stack)
+    pushState: function lexer_pushState(condition) {
+        this.conditionStack.push(condition);
+        this.__currentRuleSet__ = null;
+        return this;
+    },
+
+    // pop the previously active lexer condition state off the condition stack
+    popState: function lexer_popState() {
+        var n = this.conditionStack.length - 1;
+        if (n > 0) {
+            this.__currentRuleSet__ = null;
+            return this.conditionStack.pop();
+        } else {
+            return this.conditionStack[0];
+        }
+    },
+
+    // return the currently active lexer condition state; when an index argument is provided it produces the N-th previous condition state, if available
+    topState: function lexer_topState(n) {
+        n = this.conditionStack.length - 1 - Math.abs(n || 0);
+        if (n >= 0) {
+            return this.conditionStack[n];
+        } else {
+            return 'INITIAL';
+        }
+    },
+
+    // (internal) determine the lexer rule set which is active for the currently active lexer condition state
+    _currentRules: function lexer__currentRules() {
+        if (this.conditionStack.length && this.conditionStack[this.conditionStack.length - 1]) {
+            return this.conditions[this.conditionStack[this.conditionStack.length - 1]];
+        } else {
+            return this.conditions['INITIAL'];
+        }
+    },
+
+    // return the number of states currently on the stack
+    stateStackSize: function lexer_stateStackSize() {
+        return this.conditionStack.length;
+    },
+options: {},
+JisonLexerError: JisonLexerError,
+performAction: function lexer__performAction(yy, yy_, $avoiding_name_collisions, YY_START) {
+
+var YYSTATE = YY_START;
+switch($avoiding_name_collisions) {
+case 0 : 
+/*! Conditions:: INITIAL */ 
+/*! Rule::       [ \t\r\n]+ */ 
+ 
+    /* eat up whitespace */
+    BeginToken(yy_.yytext); 
+     
+break;
+case 1 : 
+/*! Conditions:: INITIAL */ 
+/*! Rule::       {DIGIT}+ */ 
+ 
+    BeginToken(yy_.yytext); 
+    yylval.value = atof(yy_.yytext);
+    return VALUE;
+     
+break;
+case 2 : 
+/*! Conditions:: INITIAL */ 
+/*! Rule::       {DIGIT}+\.{DIGIT}* */ 
+ 
+    BeginToken(yy_.yytext);
+    yylval.value = atof(yy_.yytext);
+    return VALUE;
+     
+break;
+case 3 : 
+/*! Conditions:: INITIAL */ 
+/*! Rule::       {DIGIT}+[eE]["+""-"]?{DIGIT}* */ 
+ 
+    BeginToken(yy_.yytext);
+    yylval.value = atof(yy_.yytext);
+    return VALUE;
+     
+break;
+case 4 : 
+/*! Conditions:: INITIAL */ 
+/*! Rule::       {DIGIT}+\.{DIGIT}*[eE]["+""-"]?{DIGIT}* */ 
+ 
+    BeginToken(yy_.yytext);
+    yylval.value = atof(yy_.yytext);
+    return VALUE;
+     
+break;
+case 5 : 
+/*! Conditions:: INITIAL */ 
+/*! Rule::       {ID} */ 
+ 
+    BeginToken(yy_.yytext);
+    yylval.string = malloc(strlen(yy_.yytext)+1);
+    strcpy(yylval.string, yy_.yytext);
+    return IDENTIFIER;
+     
+break;
+case 6 : 
+/*! Conditions:: INITIAL */ 
+/*! Rule::       \+ */ 
+  BeginToken(yy_.yytext); return ADD;  
+break;
+case 7 : 
+/*! Conditions:: INITIAL */ 
+/*! Rule::       - */ 
+  BeginToken(yy_.yytext); return SUB;  
+break;
+case 8 : 
+/*! Conditions:: INITIAL */ 
+/*! Rule::       \* */ 
+  BeginToken(yy_.yytext); return MULT;  
+break;
+case 9 : 
+/*! Conditions:: INITIAL */ 
+/*! Rule::       \/ */ 
+  BeginToken(yy_.yytext); return DIV;  
+break;
+case 10 : 
+/*! Conditions:: INITIAL */ 
+/*! Rule::       \( */ 
+  BeginToken(yy_.yytext); return LBRACE;  
+break;
+case 11 : 
+/*! Conditions:: INITIAL */ 
+/*! Rule::       \) */ 
+  BeginToken(yy_.yytext); return RBRACE;  
+break;
+case 12 : 
+/*! Conditions:: INITIAL */ 
+/*! Rule::       ; */ 
+  BeginToken(yy_.yytext); return SEMICOLON;  
+break;
+case 13 : 
+/*! Conditions:: INITIAL */ 
+/*! Rule::       = */ 
+  BeginToken(yy_.yytext); return ASSIGN;  
+break;
+case 14 : 
+/*! Conditions:: INITIAL */ 
+/*! Rule::       . */ 
+ 
+    BeginToken(yy_.yytext);
+    return yy_.yytext[0];
+     
+break;
+default:
+  return this.simpleCaseActionClusters[$avoiding_name_collisions];
+}
+},
+simpleCaseActionClusters: {
+
+},
+rules: [
+/^(?:[ \t\r\n]+)/,
+/^(?:(\d)+)/,
+/^(?:(\d)+\.(\d)*)/,
+/^(?:(\d)+[Ee]["+]?(\d)*)/,
+/^(?:(\d)+\.(\d)*[Ee]["+]?(\d)*)/,
+/^(?:([^\W\d]\w*))/,
+/^(?:\+)/,
+/^(?:-)/,
+/^(?:\*)/,
+/^(?:\/)/,
+/^(?:\()/,
+/^(?:\))/,
+/^(?:;)/,
+/^(?:=)/,
+/^(?:.)/
+],
+conditions: {
+  "INITIAL": {
+    rules: [
+      0,
+      1,
+      2,
+      3,
+      4,
+      5,
+      6,
+      7,
+      8,
+      9,
+      10,
+      11,
+      12,
+      13,
+      14
+    ],
+    inclusive: true
+  }
+}
+};
+
+/*--------------------------------------------------------------------
+ * lex.l
+ *------------------------------------------------------------------*/;
+return lexer;
+})();

samples/JavaScript/proto.js

@@ -0,0 +1,31 @@
+/**
+ * @fileoverview
+ * @enhanceable
+ * @public
+ */
+// GENERATED CODE -- DO NOT EDIT!
+
+goog.provide('proto.google.protobuf.Timestamp');
+
+goog.require('jspb.Message');
+
+/**
+ * Generated by JsPbCodeGenerator.
+ * @param {Array=} opt_data Optional initial data array, typically from a
+ * server response, or constructed directly in Javascript. The array is used
+ * in place and becomes part of the constructed object. It is not cloned.
+ * If no data is provided, the constructed object will be empty, but still
+ * valid.
+ * @extends {jspb.Message}
+ * @constructor
+ */
+proto.google.protobuf.Timestamp = function(opt_data) {
+  jspb.Message.initialize(this, opt_data, 0, -1, null, null);
+};
+goog.inherits(proto.google.protobuf.Timestamp, jspb.Message);
+if (goog.DEBUG && !COMPILED) {
+  proto.google.protobuf.Timestamp.displayName = 'proto.google.protobuf.Timestamp';
+}
+
+
+// Remainder elided

samples/Jison Lex/classy.jisonlex

@@ -0,0 +1,39 @@
+digit                       [0-9]
+id                          [a-zA-Z][a-zA-Z0-9]*
+
+%%
+"//".*                      /* ignore comment */
+"main"                      return 'MAIN';
+"class"                     return 'CLASS';
+"extends"                   return 'EXTENDS';
+"nat"                       return 'NATTYPE';
+"if"                        return 'IF';
+"else"                      return 'ELSE';
+"for"                       return 'FOR';
+"printNat"                  return 'PRINTNAT';
+"readNat"                   return 'READNAT';
+"this"                      return 'THIS';
+"new"                       return 'NEW';
+"var"                       return 'VAR';
+"null"                      return 'NUL';
+{digit}+                    return 'NATLITERAL';
+{id}                        return 'ID';
+"=="                        return 'EQUALITY';
+"="                         return 'ASSIGN';
+"+"                         return 'PLUS';
+"-"                         return 'MINUS';
+"*"                         return 'TIMES';
+">"                         return 'GREATER';
+"||"                        return 'OR';
+"!"                         return 'NOT';
+"."                         return 'DOT';
+"{"                         return 'LBRACE';
+"}"                         return 'RBRACE';
+"("                         return 'LPAREN';
+")"                         return 'RPAREN';
+";"                         return 'SEMICOLON';
+\s+                         /* skip whitespace */
+"."                         throw 'Illegal character';
+<<EOF>>                     return 'ENDOFFILE';
+
+

samples/Jison Lex/lex_grammar.jisonlex

@@ -0,0 +1,29 @@
+
+%%
+\n+                         {yy.freshLine = true;}
+\s+                         {yy.freshLine = false;}
+"y{"[^}]*"}"                {yytext = yytext.substr(2, yyleng - 3); return 'ACTION';}
+[a-zA-Z_][a-zA-Z0-9_-]*     {return 'NAME';}
+'"'([^"]|'\"')*'"'          {return 'STRING_LIT';}
+"'"([^']|"\'")*"'"          {return 'STRING_LIT';}
+"|"                         {return '|';}
+"["("\]"|[^\]])*"]"         {return 'ANY_GROUP_REGEX';}
+"("                         {return '(';}
+")"                         {return ')';}
+"+"                         {return '+';}
+"*"                         {return '*';}
+"?"                         {return '?';}
+"^"                         {return '^';}
+"/"                         {return '/';}
+"\\"[a-zA-Z0]               {return 'ESCAPE_CHAR';}
+"$"                         {return '$';}
+"<<EOF>>"                   {return '$';}
+"."                         {return '.';}
+"%%"                        {return '%%';}
+"{"\d+(","\s?\d+|",")?"}"   {return 'RANGE_REGEX';}
+/"{"                        %{if (yy.freshLine) { this.input('{'); return '{'; } else { this.unput('y'); }%}
+"}"                         %{return '}';%}
+"%{"(.|\n)*?"}%"            {yytext = yytext.substr(2, yyleng - 4); return 'ACTION';}
+.                           {/* ignore bad characters */}
+<<EOF>>                     {return 'EOF';}
+

samples/Jison/ansic.jison

@@ -0,0 +1,418 @@
+%token IDENTIFIER CONSTANT STRING_LITERAL SIZEOF
+%token PTR_OP INC_OP DEC_OP LEFT_OP RIGHT_OP LE_OP GE_OP EQ_OP NE_OP
+%token AND_OP OR_OP MUL_ASSIGN DIV_ASSIGN MOD_ASSIGN ADD_ASSIGN
+%token SUB_ASSIGN LEFT_ASSIGN RIGHT_ASSIGN AND_ASSIGN
+%token XOR_ASSIGN OR_ASSIGN TYPE_NAME
+
+%token TYPEDEF EXTERN STATIC AUTO REGISTER
+%token CHAR SHORT INT LONG SIGNED UNSIGNED FLOAT DOUBLE CONST VOLATILE VOID
+%token STRUCT UNION ENUM ELLIPSIS
+
+%token CASE DEFAULT IF ELSE SWITCH WHILE DO FOR GOTO CONTINUE BREAK RETURN
+
+%nonassoc IF_WITHOUT_ELSE
+%nonassoc ELSE
+
+%start translation_unit
+%%
+
+primary_expression
+    : IDENTIFIER
+    | CONSTANT
+    | STRING_LITERAL
+    | '(' expression ')'
+    ;
+
+postfix_expression
+    : primary_expression
+    | postfix_expression '[' expression ']'
+    | postfix_expression '(' ')'
+    | postfix_expression '(' argument_expression_list ')'
+    | postfix_expression '.' IDENTIFIER
+    | postfix_expression PTR_OP IDENTIFIER
+    | postfix_expression INC_OP
+    | postfix_expression DEC_OP
+    ;
+
+argument_expression_list
+    : assignment_expression
+    | argument_expression_list ',' assignment_expression
+    ;
+
+unary_expression
+    : postfix_expression
+    | INC_OP unary_expression
+    | DEC_OP unary_expression
+    | unary_operator cast_expression
+    | SIZEOF unary_expression
+    | SIZEOF '(' type_name ')'
+    ;
+
+unary_operator
+    : '&'
+    | '*'
+    | '+'
+    | '-'
+    | '~'
+    | '!'
+    ;
+
+cast_expression
+    : unary_expression
+    | '(' type_name ')' cast_expression
+    ;
+
+multiplicative_expression
+    : cast_expression
+    | multiplicative_expression '*' cast_expression
+    | multiplicative_expression '/' cast_expression
+    | multiplicative_expression '%' cast_expression
+    ;
+
+additive_expression
+    : multiplicative_expression
+    | additive_expression '+' multiplicative_expression
+    | additive_expression '-' multiplicative_expression
+    ;
+
+shift_expression
+    : additive_expression
+    | shift_expression LEFT_OP additive_expression
+    | shift_expression RIGHT_OP additive_expression
+    ;
+
+relational_expression
+    : shift_expression
+    | relational_expression '<' shift_expression
+    | relational_expression '>' shift_expression
+    | relational_expression LE_OP shift_expression
+    | relational_expression GE_OP shift_expression
+    ;
+
+equality_expression
+    : relational_expression
+    | equality_expression EQ_OP relational_expression
+    | equality_expression NE_OP relational_expression
+    ;
+
+and_expression
+    : equality_expression
+    | and_expression '&' equality_expression
+    ;
+
+exclusive_or_expression
+    : and_expression
+    | exclusive_or_expression '^' and_expression
+    ;
+
+inclusive_or_expression
+    : exclusive_or_expression
+    | inclusive_or_expression '|' exclusive_or_expression
+    ;
+
+logical_and_expression
+    : inclusive_or_expression
+    | logical_and_expression AND_OP inclusive_or_expression
+    ;
+
+logical_or_expression
+    : logical_and_expression
+    | logical_or_expression OR_OP logical_and_expression
+    ;
+
+conditional_expression
+    : logical_or_expression
+    | logical_or_expression '?' expression ':' conditional_expression
+    ;
+
+assignment_expression
+    : conditional_expression
+    | unary_expression assignment_operator assignment_expression
+    ;
+
+assignment_operator
+    : '='
+    | MUL_ASSIGN
+    | DIV_ASSIGN
+    | MOD_ASSIGN
+    | ADD_ASSIGN
+    | SUB_ASSIGN
+    | LEFT_ASSIGN
+    | RIGHT_ASSIGN
+    | AND_ASSIGN
+    | XOR_ASSIGN
+    | OR_ASSIGN
+    ;
+
+expression
+    : assignment_expression
+    | expression ',' assignment_expression
+    ;
+
+constant_expression
+    : conditional_expression
+    ;
+
+declaration
+    : declaration_specifiers ';'
+    | declaration_specifiers init_declarator_list ';'
+    ;
+
+declaration_specifiers
+    : storage_class_specifier
+    | storage_class_specifier declaration_specifiers
+    | type_specifier
+    | type_specifier declaration_specifiers
+    | type_qualifier
+    | type_qualifier declaration_specifiers
+    ;
+
+init_declarator_list
+    : init_declarator
+    | init_declarator_list ',' init_declarator
+    ;
+
+init_declarator
+    : declarator
+    | declarator '=' initializer
+    ;
+
+storage_class_specifier
+    : TYPEDEF
+    | EXTERN
+    | STATIC
+    | AUTO
+    | REGISTER
+    ;
+
+type_specifier
+    : VOID
+    | CHAR
+    | SHORT
+    | INT
+    | LONG
+    | FLOAT
+    | DOUBLE
+    | SIGNED
+    | UNSIGNED
+    | struct_or_union_specifier
+    | enum_specifier
+    | TYPE_NAME
+    ;
+
+struct_or_union_specifier
+    : struct_or_union IDENTIFIER '{' struct_declaration_list '}'
+    | struct_or_union '{' struct_declaration_list '}'
+    | struct_or_union IDENTIFIER
+    ;
+
+struct_or_union
+    : STRUCT
+    | UNION
+    ;
+
+struct_declaration_list
+    : struct_declaration
+    | struct_declaration_list struct_declaration
+    ;
+
+struct_declaration
+    : specifier_qualifier_list struct_declarator_list ';'
+    ;
+
+specifier_qualifier_list
+    : type_specifier specifier_qualifier_list
+    | type_specifier
+    | type_qualifier specifier_qualifier_list
+    | type_qualifier
+    ;
+
+struct_declarator_list
+    : struct_declarator
+    | struct_declarator_list ',' struct_declarator
+    ;
+
+struct_declarator
+    : declarator
+    | ':' constant_expression
+    | declarator ':' constant_expression
+    ;
+
+enum_specifier
+    : ENUM '{' enumerator_list '}'
+    | ENUM IDENTIFIER '{' enumerator_list '}'
+    | ENUM IDENTIFIER
+    ;
+
+enumerator_list
+    : enumerator
+    | enumerator_list ',' enumerator
+    ;
+
+enumerator
+    : IDENTIFIER
+    | IDENTIFIER '=' constant_expression
+    ;
+
+type_qualifier
+    : CONST
+    | VOLATILE
+    ;
+
+declarator
+    : pointer direct_declarator
+    | direct_declarator
+    ;
+
+direct_declarator
+    : IDENTIFIER
+    | '(' declarator ')'
+    | direct_declarator '[' constant_expression ']'
+    | direct_declarator '[' ']'
+    | direct_declarator '(' parameter_type_list ')'
+    | direct_declarator '(' identifier_list ')'
+    | direct_declarator '(' ')'
+    ;
+
+pointer
+    : '*'
+    | '*' type_qualifier_list
+    | '*' pointer
+    | '*' type_qualifier_list pointer
+    ;
+
+type_qualifier_list
+    : type_qualifier
+    | type_qualifier_list type_qualifier
+    ;
+
+
+parameter_type_list
+    : parameter_list
+    | parameter_list ',' ELLIPSIS
+    ;
+
+parameter_list
+    : parameter_declaration
+    | parameter_list ',' parameter_declaration
+    ;
+
+parameter_declaration
+    : declaration_specifiers declarator
+    | declaration_specifiers abstract_declarator
+    | declaration_specifiers
+    ;
+
+identifier_list
+    : IDENTIFIER
+    | identifier_list ',' IDENTIFIER
+    ;
+
+type_name
+    : specifier_qualifier_list
+    | specifier_qualifier_list abstract_declarator
+    ;
+
+abstract_declarator
+    : pointer
+    | direct_abstract_declarator
+    | pointer direct_abstract_declarator
+    ;
+
+direct_abstract_declarator
+    : '(' abstract_declarator ')'
+    | '[' ']'
+    | '[' constant_expression ']'
+    | direct_abstract_declarator '[' ']'
+    | direct_abstract_declarator '[' constant_expression ']'
+    | '(' ')'
+    | '(' parameter_type_list ')'
+    | direct_abstract_declarator '(' ')'
+    | direct_abstract_declarator '(' parameter_type_list ')'
+    ;
+
+initializer
+    : assignment_expression
+    | '{' initializer_list '}'
+    | '{' initializer_list ',' '}'
+    ;
+
+initializer_list
+    : initializer
+    | initializer_list ',' initializer
+    ;
+
+statement
+    : labeled_statement
+    | compound_statement
+    | expression_statement
+    | selection_statement
+    | iteration_statement
+    | jump_statement
+    ;
+
+labeled_statement
+    : IDENTIFIER ':' statement
+    | CASE constant_expression ':' statement
+    | DEFAULT ':' statement
+    ;
+
+compound_statement
+    : '{' '}'
+    | '{' statement_list '}'
+    | '{' declaration_list '}'
+    | '{' declaration_list statement_list '}'
+    ;
+
+declaration_list
+    : declaration
+    | declaration_list declaration
+    ;
+
+statement_list
+    : statement
+    | statement_list statement
+    ;
+
+expression_statement
+    : ';'
+    | expression ';'
+    ;
+
+selection_statement
+    : IF '(' expression ')' statement %prec IF_WITHOUT_ELSE
+    | IF '(' expression ')' statement ELSE statement
+    | SWITCH '(' expression ')' statement
+    ;
+
+iteration_statement
+    : WHILE '(' expression ')' statement
+    | DO statement WHILE '(' expression ')' ';'
+    | FOR '(' expression_statement expression_statement ')' statement
+    | FOR '(' expression_statement expression_statement expression ')' statement
+    ;
+
+jump_statement
+    : GOTO IDENTIFIER ';'
+    | CONTINUE ';'
+    | BREAK ';'
+    | RETURN ';'
+    | RETURN expression ';'
+    ;
+
+translation_unit
+    : external_declaration
+    | translation_unit external_declaration
+    ;
+
+external_declaration
+    : function_definition
+    | declaration
+    ;
+
+function_definition
+    : declaration_specifiers declarator declaration_list compound_statement
+    | declaration_specifiers declarator compound_statement
+    | declarator declaration_list compound_statement
+    | declarator compound_statement
+    ;

samples/Jison/classy.jison

@@ -0,0 +1,84 @@
+
+/* description: ClassyLang grammar. Very classy. */
+/*
+  To build parser:
+
+    $ ./bin/jison examples/classy.jison examples/classy.jisonlex
+
+*/
+
+
+/* author: Zach Carter */
+
+%right ASSIGN
+%left OR
+%nonassoc EQUALITY GREATER
+%left PLUS MINUS
+%left TIMES
+%right NOT
+%left DOT
+
+%%
+
+pgm
+    : cdl MAIN LBRACE vdl el RBRACE ENDOFFILE
+    ;
+
+cdl
+    : c cdl
+    |
+    ;
+
+c
+    : CLASS id EXTENDS id LBRACE vdl mdl RBRACE
+    ;
+
+vdl
+    : VAR t id SEMICOLON vdl
+    |
+    ;
+
+mdl
+    : t id LPAREN t id RPAREN LBRACE vdl el RBRACE mdl
+    |
+    ;
+
+t
+    : NATTYPE
+    | id
+    ;
+
+id
+    : ID
+    ;
+
+el
+    : e SEMICOLON el
+    | e SEMICOLON
+    ;
+
+e
+    : NATLITERAL
+    | NUL
+    | id
+    | NEW id
+    | THIS
+    | IF LPAREN e RPAREN LBRACE el RBRACE ELSE LBRACE el RBRACE
+    | FOR LPAREN e SEMICOLON e SEMICOLON e RPAREN LBRACE el RBRACE
+    | READNAT LPAREN RPAREN
+    | PRINTNAT LPAREN e RPAREN
+    | e PLUS e
+    | e MINUS e
+    | e TIMES e
+    | e EQUALITY e
+    | e GREATER e
+    | NOT e
+    | e OR e
+    | e DOT id
+    | id ASSIGN e
+    | e DOT id ASSIGN e
+    | id LPAREN e RPAREN
+    | e DOT id LPAREN e RPAREN
+    | LPAREN e RPAREN
+    ;
+

samples/Jison/lex.jison

@@ -0,0 +1,145 @@
+
+// `%nonassoc` tells the parser compiler (JISON) that these tokens cannot occur more than once,
+// i.e. input like '//a' (tokens '/', '/' and 'a') is not a legal input while '/a' (tokens '/' and 'a')
+// *is* legal input for this grammar.
+ 
+%nonassoc '/' '/!'
+
+// Likewise for `%left`: this informs the LALR(1) grammar compiler (JISON) that these tokens
+// *can* occur repeatedly, e.g. 'a?*' and even 'a**' are considered legal inputs given this
+// grammar!
+//
+// Token `RANGE_REGEX` may seem the odd one out here but really isn't: given the `regex_base`
+// choice/rule `regex_base range_regex`, which is recursive, this grammar tells JISON that 
+// any input matching a sequence like `regex_base range_regex range_regex` *is* legal.
+// If you do not want that to be legal, you MUST adjust the grammar rule set you match your
+// actual intent.
+
+%left '*' '+' '?' RANGE_REGEX
+
+
+%% 
+
+lex 
+    : definitions include '%%' rules '%%' EOF
+        {{ $$ = {macros: $1, rules: $4};
+          if ($2) $$.actionInclude = $2;
+          return $$; }}
+    | definitions include '%%' rules EOF
+        {{ $$ = {macros: $1, rules: $4};
+          if ($2) $$.actionInclude = $2;
+          return $$; }}
+    ;
+
+include
+    : action
+    |
+    ;
+
+definitions
+    : definitions definition
+        { $$ = $1; $$.concat($2); }
+    | definition
+        { $$ = [$1]; }
+    ;
+
+definition
+    : name regex
+        { $$ = [$1, $2]; }
+    ;
+
+name
+    : NAME
+        { $$ = yytext; }
+    ;
+
+rules
+    : rules rule
+        { $$ = $1; $$.push($2); }
+    | rule
+        { $$ = [$1]; }
+    ;
+
+rule
+    : regex action
+        { $$ = [$1, $2]; }
+    ;
+
+action
+    : ACTION 
+        { $$ = yytext; }
+    ;
+
+regex
+    : start_caret regex_list end_dollar
+        { $$ = $1+$2+$3; }
+    ;
+
+start_caret
+    : '^'
+        { $$ = '^'; }
+    |
+        { $$ = ''; }
+    ;
+
+end_dollar
+    : '$'
+        { $$ = '$'; }
+    |
+        { $$ = ''; }
+    ;
+
+regex_list
+    : regex_list '|' regex_chain
+        { $$ = $1+'|'+$3; }
+    | regex_chain
+    ;
+
+regex_chain
+    : regex_chain regex_base
+        { $$ = $1+$2;}
+    | regex_base
+        { $$ = $1;}
+    ;
+
+regex_base
+    : '(' regex_list ')'
+        { $$ = '('+$2+')'; }
+    | regex_base '+'
+        { $$ = $1+'+'; }
+    | regex_base '*'
+        { $$ = $1+'*'; }
+    | regex_base '?'
+        { $$ = $1+'?'; }
+    | '/' regex_base
+        { $$ = '(?=' + $regex_base + ')'; }
+    | '/!' regex_base
+        { $$ = '(?!' + $regex_base + ')'; }
+    | name_expansion
+    | regex_base range_regex
+        { $$ = $1+$2; }
+    | any_group_regex
+    | '.'
+        { $$ = '.'; }
+    | string
+    ;
+
+name_expansion
+    : '{' name '}'
+        {{ $$ = '{'+$2+'}'; }}
+    ;
+
+any_group_regex
+    : ANY_GROUP_REGEX
+        { $$ = yytext; }
+    ;
+
+range_regex
+    : RANGE_REGEX
+        { $$ = yytext; }
+    ;
+
+string
+    : STRING_LIT
+        { $$ = yy.prepareString(yytext.substr(1, yyleng-2)); }
+    ;

samples/Jolie/common.iol

@@ -0,0 +1,37 @@
+include "types/Binding.iol"
+
+constants {
+	Location_Exam = "socket://localhost:8000"
+}
+
+type StartExamRequest:void {
+	.examName:string
+	.studentName:string
+	.student:Binding
+}
+
+type MakeQuestionRequest:void {
+	.question:string
+	.examName:string
+	.studentName:string
+}
+
+type DecisionMessage:void {
+	.studentName:string
+	.examName:string
+}
+
+interface ExamInterface {
+OneWay:
+	startExam(StartExamRequest),
+	pass(DecisionMessage), fail(DecisionMessage)
+RequestResponse:
+	makeQuestion(MakeQuestionRequest)(int)
+}
+
+interface StudentInterface {
+OneWay:
+	sendMessage(string)
+RequestResponse:
+	makeQuestion(MakeQuestionRequest)(int)
+}

samples/Jolie/exam.ol

@@ -0,0 +1,39 @@
+include "common.iol"
+
+cset {
+studentName:
+	StartExamRequest.studentName
+	DecisionMessage.studentName
+	MakeQuestionRequest.studentName,
+examName:
+	StartExamRequest.examName
+	DecisionMessage.examName
+	MakeQuestionRequest.examName
+}
+
+execution { concurrent }
+
+outputPort Student {
+Interfaces: StudentInterface
+}
+
+inputPort ExamInput {
+Location: Location_Exam
+Protocol: sodep
+Interfaces: ExamInterface
+}
+
+main
+{
+	startExam( examRequest );
+	Student << examRequest.student;
+	makeQuestion( question )( answer ) {
+		makeQuestion@Student( question )( answer )
+	};
+	[ pass( message ) ] {
+		sendMessage@Student( "You passed!" )
+	}
+	[ fail( message ) ] {
+		sendMessage@Student( "You failed!" )
+	}
+}

samples/Jolie/examiner.ol

@@ -0,0 +1,26 @@
+include "common.iol"
+include "ui/swing_ui.iol"
+include "console.iol"
+
+outputPort Exam {
+Location: Location_Exam
+Protocol: sodep
+Interfaces: ExamInterface
+}
+
+main
+{
+	question.studentName = "John";
+	question.examName = "SPLG";
+	question.question = "Random question";
+	makeQuestion@Exam( question )( answer );
+	showYesNoQuestionDialog@SwingUI( "Do you want to accept answer " + answer + " ?" )( decision );
+
+	message.studentName = "John";
+	message.examName = "SPLG";
+	if ( decision == 0 ) {
+		pass@Exam( message )
+	} else {
+		fail@Exam( message )
+	}
+}

samples/Jolie/hanoi.ol

@@ -0,0 +1,84 @@
+// https://github.com/jolie/website/blob/master/docs/documentation/locations/code/local.ol
+
+include "runtime.iol"
+include "string_utils.iol"
+
+type HanoiRequest: void{
+  .src: string
+  .aux: string
+  .dst: string
+  .n: int
+  .sid?: string
+}
+
+type HanoiReponse: void {
+  .move?: string
+}
+
+interface LocalOperations{
+  RequestResponse:
+    hanoiSolver( HanoiRequest )( HanoiReponse )
+}
+
+interface ExternalOperations{
+  RequestResponse:
+    hanoi( HanoiRequest )( string )
+}
+
+outputPort Self{
+  Interfaces: LocalOperations
+}
+
+inputPort Self {
+  Location: "local"
+  Interfaces: LocalOperations
+}
+
+inputPort PowerService {
+  Location: "socket://localhost:8000"
+  Protocol: http{
+    .format = "html"
+  }
+  Interfaces: ExternalOperations
+}
+
+execution { concurrent }
+
+init
+{
+  getLocalLocation@Runtime()( Self.location )
+}
+
+main
+{
+  [ hanoi( request )( response ){
+    getRandomUUID@StringUtils()(request.sid);
+    hanoiSolver@Self( request )( subRes );
+    response = subRes.move
+  }]{ nullProcess }
+
+  [ hanoiSolver( request )( response ){
+    if ( request.n > 0 ){
+      subReq.n = request.n;
+      subReq.n--;
+      with( request ){
+        subReq.aux = .dst;
+        subReq.dst = .aux;
+        subReq.src = .src;
+        subReq.sid = .sid
+      };
+      hanoiSolver@Self( subReq )( response );
+      response.move +=  "<br>" + 
+                ++global.counters.(request.sid) + 
+                ") Move from " + request.src +
+                " to " + request.dst + ";";
+      with ( request ){
+        subReq.src = .aux;
+        subReq.aux = .src;
+        subReq.dst = .dst
+      };
+      hanoiSolver@Self( subReq )( subRes );
+      response.move += subRes.move
+    }
+  }]{ nullProcess }
+}

samples/Jolie/student.ol

@@ -0,0 +1,29 @@
+include "common.iol"
+include "ui/swing_ui.iol"
+include "console.iol"
+
+outputPort Exam {
+Location: Location_Exam
+Protocol: sodep
+Interfaces: ExamInterface
+}
+
+inputPort StudentInput {
+Location: "socket://localhost:8001/"
+Protocol: sodep
+Interfaces: StudentInterface
+}
+
+main
+{
+	request.studentName = "John";
+	request.examName = "SPLG";
+	request.student.location = "socket://localhost:8001/";
+	request.student.protocol = "sodep";
+	startExam@Exam( request );
+	makeQuestion( question )( answer ) {
+		showYesNoQuestionDialog@SwingUI( question.question )( answer )
+	};
+	sendMessage( message );
+	println@Console( message )()
+}

samples/LookML/example.model.lkml

@@ -0,0 +1,49 @@
+- label:          'desired label name'
+- connection:     connection_name
+- include:        filename_or_pattern
+  # Possibly more include declarations
+- persist_for:    N (seconds | minutes | hours)
+- case_sensitive: true | false
+- week_start_day: monday | tuesday | wednesday | thursday | friday | saturday | sunday
+- value_formats:
+  - name: desired_format_name
+    value_format: 'excel-style formatting string'
+  # Possibly more value formats
+
+- explore: view_name
+  label:  'desired label name'
+  description: 'description string'
+  symmetric_aggregates: true | false
+  hidden: true | false
+  fields: [field_or_set, field_or_set, …]
+
+  sql_always_where: SQL WHERE condition
+  always_filter:
+    field_name: 'looker filter expression'
+  conditionally_filter:
+    field_name: 'looker filter expression'
+    unless: [field_or_set, field_or_set, …]
+  access_filter_fields: [fully_scoped_field, fully_scoped_field, …]
+
+  always_join: [view_name, view_name, …]
+  joins:
+    - join: view_name
+      type: left_outer | full_outer | inner | cross
+      relationship: one_to_one | many_to_one | one_to_many | many_to_many
+      from: view_name
+      sql_table_name: table_name
+      view_label: 'desired label name'
+      fields: [field_or_set, field_or_set, …]
+      required_joins: [view_name, view_name, …]
+      foreign_key: dimension_name
+      sql_on: SQL ON clause
+    # Possibly more join declarations
+
+  persist_for: N (seconds | minutes | hours)
+  from: view_name
+  view: view_name
+  case_sensitive: true | false
+  sql_table_name: table_name
+  cancel_grouping_fields: [fully_scoped_field, fully_scoped_field, …]
+
+# Possibly more explore declarations

samples/LookML/example.view.lkml

@@ -0,0 +1,90 @@
+- view: view_name
+  sql_table_name: table_name
+  suggestions: true | false
+
+  derived_table:
+    sql: SQL query
+    persist_for: N (seconds | minutes | hours)
+    sql_trigger_value: SQL query
+    distribution: column_name
+    distribution_style: ALL | EVEN
+    sortkeys: [column_name, column_name, …]
+    indexes: [column_name, column_name, …]
+
+  sets:
+    set_name:
+      - field_or_set
+      - field_or_set
+      - …
+    # Possibly more set declarations
+
+  fields:
+  - (dimension | dimension_group | measure | filter): field_name
+    label: 'desired label name'
+    view_label: 'desired label name'
+    group_label: 'desired label name'
+    description: 'description string'
+    hidden: true | false
+    alias: [old_field_name, old_field_name, …]
+    value_format: 'excel-style formatting string'
+    value_format_name: format_name
+    html: HTML expression using Liquid template elements
+    sql: SQL expression to generate the field value
+    required_fields: [field_name, field_name, …]
+    drill_fields: [field_or_set, field_or_set, …]
+    can_filter: true | false
+    fanout_on: repeated_record_name
+
+    # DIMENSION SPECIFIC PARAMETERS
+
+    type: dimension_field_type
+    primary_key: true | false
+    sql_case:
+      value: SQL condition
+      value: SQL condition
+      # Possibly more sql_case statements
+    alpha_sort: true | false
+    tiers: [N, N, …]
+    style: classic | interval | integer | relational
+    sql_latitude: SQL expression to generate a latitude
+    sql_longitude: SQL expression to generate a longitude
+    suggestable: true | false
+    suggest_persist_for: N (seconds | minutes | hours)
+    suggest_dimension: dimension_name
+    suggest_explore: explore_name
+    suggestions: ['suggestion string', 'suggestion string', …]
+    bypass_suggest_restrictions: true | false
+    full_suggestions: true | false
+    skip_drill_filter: true | false
+    case_sensitive: true | false
+    order_by_field: dimension_name
+    map_layer: name_of_map_layer
+    links:
+      - label: 'desired label name'
+        url: desired_url
+        icon_url: url_of_an_ico_file
+      # Possibly more links
+
+    # DIMENSION GROUP SPECIFIC PARAMETERS
+
+    timeframes: [timeframe, timeframe, …]
+    convert_tz: true | false
+    datatype: epoch | timestamp | datetime | date | yyyymmdd
+
+    # MEASURE SPECIFIC PARAMETERS
+
+    type: measure_field_type
+    direction: row | column
+    approximate: true | false
+    approximate_threshold: N
+    sql_distinct_key: SQL expression to define repeated entities
+    list_field: dimension_name
+    filters:
+      dimension_name: 'looker filter expression'
+      # Possibly more filters statements
+
+    # FILTER SPECIFIC PARAMETERS
+
+    default_value: 'desired default value'
+
+  # Possibly more dimension or measure declarations

samples/Markdown/README.mdown

@@ -1,9 +1,14 @@
----
-type: grammar
-name: css.tmbundle
-license: permissive
-curated: true
----
+# Installation
+
+You can install this bundle in TextMate by opening the preferences and going to the bundles tab. After installation it will be automatically updated for you.
+
+# General
+
+* [Bundle Styleguide](http://kb.textmate.org/bundle_styleguide) — _before you make changes_
+* [Commit Styleguide](http://kb.textmate.org/commit_styleguide) — _before you send a pull request_
+* [Writing Bug Reports](http://kb.textmate.org/writing_bug_reports) — _before you report an issue_
+
+# License
 
 If not otherwise specified (see below), files in this repository fall under the following license:
 
@@ -12,4 +17,4 @@ If not otherwise specified (see below), files in this repository fall under the
 	express or implied warranty, and with no claim as to its
 	suitability for any purpose.
 
-An exception is made for files in readable text which contain their own license information, or files where an accompanying file exists (in the same directory) with a “-license” suffix added to the base-name name of the original file, and an extension of txt, html, or similar. For example “tidy” is accompanied by “tidy-license.txt”.
+An exception is made for files in readable text which contain their own license information, or files where an accompanying file exists (in the same directory) with a “-license” suffix added to the base-name name of the original file, and an extension of txt, html, or similar. For example “tidy” is accompanied by “tidy-license.txt”.

samples/Markdown/csharp6.workbook

@@ -0,0 +1,192 @@
+---
+uti: com.xamarin.workbook
+platforms:
+- Console
+---
+
+# Using C# 6
+
+Some examples from Xamarin's [intro to C# 6](https://developer.xamarin.com/guides/cross-platform/advanced/csharp_six/).
+
+* Null-conditional operator
+
+* String Interpolation
+
+* Expression-bodied Function Members
+
+* Auto-property Initialization
+
+* Index Initializers
+
+* using static
+
+## Null-conditional operator
+
+The `?.` operator automatically does a null-check before referencing the
+specified member. The example string array below has a `null` entry:
+
+```csharp
+var names = new string[] { "Foo", null };
+```
+
+In C# 5, a null-check is required before accessing the `.Length` property:
+
+```csharp
+// C# 5
+int secondLength = 0;
+if (names[1] != null)
+  secondLength = names[1].Length;
+```
+
+C# 6 allows the length to be queried in a single line; the entire
+statement returns `null` if any object is null.
+
+```csharp
+var length0 = names[0]?.Length; // 3
+var length1 = names[1]?.Length; // null
+```
+
+This can be used in conjunction with the `??` null coalescing operator
+to set a default value (such as `0`) in the example below:
+
+```csharp
+var lengths = names.Select (names => names?.Length ?? 0); //[3, 0]
+```
+
+## String Interpolation
+
+Previously strings were built in a number of different ways:
+
+```csharp
+var animal = "Monkeys";
+var food = "bananas";
+
+var out1 = String.Format ("{0} love to eat {1}", animal, food);
+var out2 = animal + " love to eat " + food;
+// or even StringBuilder
+```
+
+C# 6 provides a simple syntax where the fieldname can be
+embedded directly in the string:
+
+```csharp
+$"{animal} love to eat {food}"
+```
+
+String-formatting can also be done with this syntax:
+
+```csharp
+var values = new int[] { 1, 2, 3, 4, 12, 123456 };
+foreach (var s in values.Select (i => $"The value is {i,10:N2}.")) {
+   Console.WriteLine (s);
+}
+```
+
+## Expression-bodied Function Members
+
+The `ToString` override in the following class is an expression-bodied
+function - a more succinct declaration syntax.
+
+```csharp
+class Person
+{
+    public string FirstName { get; }
+    public string LastName { get; }
+    public Person (string firstname, string lastname)
+    {
+       FirstName = firstname;
+       LastName = lastname;
+    }
+    // note there is no explicit `return` keyword
+    public override string ToString () => $"{LastName}, {FirstName} {LastName}";
+}
+```
+
+`void` expression bodied functions are also allowed so long as
+the expression is a statement:
+
+```csharp
+public void Log(string message) => System.Console.WriteLine($"{DateTime.Now.ToString ("s", System.Globalization.CultureInfo.InvariantCulture )}: {message}");
+```
+
+This simple example calls these two methods:
+
+```csharp
+Log(new Person("James", "Bond").ToString())
+```
+
+## Auto-property Initialization
+
+Properties (ie. specified with `{get;set;}`) can be initialized inline
+with C# 6:
+
+```csharp
+class Todo
+{
+    public bool Done { get; set; } = false;
+    public DateTime Created { get; } = DateTime.Now;
+    public string Description { get; }
+
+    public Todo (string description)
+    {
+       this.Description = description; // can assign (only in constructor!)
+    }
+    public override string ToString () => $"'{Description}' was created on {Created}";
+}
+```
+
+```csharp
+new Todo("buy apples")
+```
+
+## Index Initializers
+
+Dictionary-style data structures let you specify key/value
+types with a simple object-initializer-like syntax:
+
+```csharp
+var userInfo = new Dictionary<string,object> {
+    ["Created"] = DateTime.Now,
+    ["Due"] = DateTime.Now.AddSeconds(60 * 60 * 24),
+    ["Task"] = "buy lettuce"
+};
+```
+
+## using static
+
+Enumerations, and certain classes such as System.Math, are primarily
+holders of static values and functions. In C# 6, you can import all
+static members of a type with a single using static statement:
+
+```csharp
+using static System.Math;
+```
+
+C# 6 code can then reference the static members directly, avoiding
+repetition of the class name (eg. `Math.PI` becomes `PI`):
+
+```csharp
+public class Location 
+{
+    public Location (double lat, double @long) {Latitude = lat; Longitude = @long;} 
+    public double Latitude = 0; public double Longitude = 0; 
+}
+static public double MilesBetween(Location loc1, Location loc2)
+{
+  double rlat1  = PI * loc1.Latitude / 180;
+  double rlat2  = PI * loc2.Latitude / 180;
+  double theta  = loc1.Longitude - loc2.Longitude;
+  double rtheta = PI * theta / 180;
+  double dist =
+      Sin(rlat1) * Sin(rlat2) + Cos(rlat1) *
+      Cos(rlat2) * Cos(rtheta);
+  dist = Acos(dist);
+  dist = dist*180/PI;
+  dist = dist*60*1.1515;
+  return dist; //miles
+}
+```
+
+```csharp
+MilesBetween (new Location(-12,22), new Location(-13,33))
+```

samples/Markdown/minimal.md

@@ -0,0 +1 @@
+_This_ is a **Markdown** readme.

samples/Marko/counter.marko

@@ -0,0 +1,26 @@
+class {
+    constructor() {
+        this.state = { count:0 };
+    }
+    increment() {
+        this.state.count++;
+    }
+}
+
+style {
+    .count {
+        color:#09c;
+        font-size:3em;
+    }
+    .example-button {
+        font-size:1em;
+        padding:0.5em;
+    }
+}
+
+<div.count>
+    ${state.count}
+</div>
+<button.example-button on-click('increment')>
+    Click me!
+</button>

samples/Marko/hello.marko

@@ -0,0 +1,15 @@
+$ var name = 'Frank';
+$ var colors = ['red', 'green', 'blue'];
+
+<h1>
+    Hello ${name}!
+</h1>
+
+<ul if(colors.length)>
+    <li style={color: color} for(color in colors)>
+        ${color}
+    </li>
+</ul>
+<div else>
+    No colors!
+</div>

samples/Marko/rgb-sliders.marko

@@ -0,0 +1,36 @@
+static const colors = ['red', 'green', 'blue'];
+static const defaultColor = [255, 0, 0];
+
+class {
+	onInput(input) {
+		this.state = { color: input.color || defaultColor };
+	}
+
+	updateColor() {
+    	this.state.color = colors.map((color) => {
+        	return parseInt(this.getEl(color + 'Input').value, 10);
+        });
+    }
+
+    getStyleColor() {
+    	return 'rgb(' + this.state.color.join(',') + ')';
+    }
+}
+
+<div.rgb-sliders>
+    <div.inputs>
+    	<for(i, color in colors)>
+        	<div>
+                <label for-key=color+"Input">
+                    ${color}:
+                </label>
+                <input type="range" max="255"
+                    key=color+"Input"
+                    on-input('updateColor')
+                    value=state.color[i] >
+            </div>
+        </for>
+    </div>
+    <div.color style={backgroundColor: component.getStyleColor()}>
+    </div>
+</div>

samples/Meson/filenames/meson.build

@@ -0,0 +1,51 @@
+project('test', ['c'],
+  version: '0.1.0'
+)
+
+# This is a comment test('foo')
+
+add_global_arguments(['-foo'])
+add_global_link_arguments(['-foo'])
+
+gnome = import('gnome') # As is this
+
+gnome.do_something('test')
+
+meson.source_root()
+
+foreach foo: bar
+  foreach baz : foo
+    message(baz)
+  endforeach
+endforeach
+
+blah = '''
+afjoakjflajf  # Test
+lflkasjf
+test\'test
+test\\\\test
+test\ntest
+'''
+
+foo = ''
+foo = ''''''
+foo = 'string'
+foo = '''string2'''
+foo = 12314
+foo = 1231.1231
+foo = true
+foo = false
+foo = ['te\'st', 1, 3.3, '''test''']
+foo += 1231
+foo = '@0@'.format('test')
+foo = include_directories('foo', kwarg: 'bar', include_directories: 'foo')
+foo = true ? 'true' : 'false'
+foo = 2 - 1 + 3 % 8 / 4 * 3
+
+if true and false
+elif false or true
+elif true not false
+elif foo == 12
+elif (foo != 124) and (foo <= 200)
+else
+endif

samples/Meson/filenames/meson_options.txt

@@ -0,0 +1,3 @@
+option('with-something', type: 'boolean',
+  value: true,
+)

samples/P4/l2.p4

@@ -0,0 +1,329 @@
+/*
+Copyright 2013-present Barefoot Networks, Inc. 
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+*/
+
+/*
+ * Layer-2 processing
+ */
+
+header_type l2_metadata_t {
+    fields {
+        lkp_pkt_type : 3;
+        lkp_mac_sa : 48;
+        lkp_mac_da : 48;
+        lkp_mac_type : 16;
+
+        l2_nexthop : 16;                       /* next hop from l2 */
+        l2_nexthop_type : 1;                   /* ecmp or nexthop */
+        l2_redirect : 1;                       /* l2 redirect action */
+        l2_src_miss : 1;                       /* l2 source miss */
+        l2_src_move : IFINDEX_BIT_WIDTH;       /* l2 source interface mis-match */
+        stp_group: 10;                         /* spanning tree group id */
+        stp_state : 3;                         /* spanning tree port state */
+        bd_stats_idx : 16;                     /* ingress BD stats index */
+        learning_enabled : 1;                  /* is learning enabled */
+        port_vlan_mapping_miss : 1;            /* port vlan mapping miss */
+        same_if_check : IFINDEX_BIT_WIDTH;     /* same interface check */
+    }
+}
+
+metadata l2_metadata_t l2_metadata;
+
+#ifndef L2_DISABLE
+/*****************************************************************************/
+/* Spanning tree lookup                                                      */
+/*****************************************************************************/
+action set_stp_state(stp_state) {
+    modify_field(l2_metadata.stp_state, stp_state);
+}
+
+table spanning_tree {
+    reads {
+        ingress_metadata.ifindex : exact;
+        l2_metadata.stp_group: exact;
+    }
+    actions {
+        set_stp_state;
+    }
+    size : SPANNING_TREE_TABLE_SIZE;
+}
+#endif /* L2_DISABLE */
+
+control process_spanning_tree {
+#ifndef L2_DISABLE
+    if (l2_metadata.stp_group != STP_GROUP_NONE) {
+        apply(spanning_tree);
+    }
+#endif /* L2_DISABLE */
+}
+
+#ifndef L2_DISABLE
+/*****************************************************************************/
+/* Source MAC lookup                                                         */
+/*****************************************************************************/
+action smac_miss() {
+    modify_field(l2_metadata.l2_src_miss, TRUE);
+}
+
+action smac_hit(ifindex) {
+    bit_xor(l2_metadata.l2_src_move, ingress_metadata.ifindex, ifindex);
+}
+
+table smac {
+    reads {
+        ingress_metadata.bd : exact;
+        l2_metadata.lkp_mac_sa : exact;
+    }
+    actions {
+        nop;
+        smac_miss;
+        smac_hit;
+    }
+    size : MAC_TABLE_SIZE;
+}
+
+/*****************************************************************************/
+/* Destination MAC lookup                                                    */
+/*****************************************************************************/
+action dmac_hit(ifindex) {
+    modify_field(ingress_metadata.egress_ifindex, ifindex);
+    bit_xor(l2_metadata.same_if_check, l2_metadata.same_if_check, ifindex);
+}
+
+action dmac_multicast_hit(mc_index) {
+    modify_field(intrinsic_metadata.mcast_grp, mc_index);
+#ifdef FABRIC_ENABLE
+    modify_field(fabric_metadata.dst_device, FABRIC_DEVICE_MULTICAST);
+#endif /* FABRIC_ENABLE */
+}
+
+action dmac_miss() {
+    modify_field(ingress_metadata.egress_ifindex, IFINDEX_FLOOD);
+#ifdef FABRIC_ENABLE
+    modify_field(fabric_metadata.dst_device, FABRIC_DEVICE_MULTICAST);
+#endif /* FABRIC_ENABLE */
+}
+
+action dmac_redirect_nexthop(nexthop_index) {
+    modify_field(l2_metadata.l2_redirect, TRUE);
+    modify_field(l2_metadata.l2_nexthop, nexthop_index);
+    modify_field(l2_metadata.l2_nexthop_type, NEXTHOP_TYPE_SIMPLE);
+}
+
+action dmac_redirect_ecmp(ecmp_index) {
+    modify_field(l2_metadata.l2_redirect, TRUE);
+    modify_field(l2_metadata.l2_nexthop, ecmp_index);
+    modify_field(l2_metadata.l2_nexthop_type, NEXTHOP_TYPE_ECMP);
+}
+
+action dmac_drop() {
+    drop();
+}
+
+table dmac {
+    reads {
+        ingress_metadata.bd : exact;
+        l2_metadata.lkp_mac_da : exact;
+    }
+    actions {
+#ifdef OPENFLOW_ENABLE
+        openflow_apply;
+        openflow_miss;
+#endif /* OPENFLOW_ENABLE */
+        nop;
+        dmac_hit;
+        dmac_multicast_hit;
+        dmac_miss;
+        dmac_redirect_nexthop;
+        dmac_redirect_ecmp;
+        dmac_drop;
+    }
+    size : MAC_TABLE_SIZE;
+    support_timeout: true;
+}
+#endif /* L2_DISABLE */
+
+control process_mac {
+#ifndef L2_DISABLE
+    apply(smac);
+    apply(dmac);
+#endif /* L2_DISABLE */
+}
+
+#ifndef L2_DISABLE
+/*****************************************************************************/
+/* MAC learn notification                                                    */
+/*****************************************************************************/
+field_list mac_learn_digest {
+    ingress_metadata.bd;
+    l2_metadata.lkp_mac_sa;
+    ingress_metadata.ifindex;
+}
+
+action generate_learn_notify() {
+    generate_digest(MAC_LEARN_RECEIVER, mac_learn_digest);
+}
+
+table learn_notify {
+    reads {
+        l2_metadata.l2_src_miss : ternary;
+        l2_metadata.l2_src_move : ternary;
+        l2_metadata.stp_state : ternary;
+    }
+    actions {
+        nop;
+        generate_learn_notify;
+    }
+    size : LEARN_NOTIFY_TABLE_SIZE;
+}
+#endif /* L2_DISABLE */
+
+control process_mac_learning {
+#ifndef L2_DISABLE
+    if (l2_metadata.learning_enabled == TRUE) {
+        apply(learn_notify);
+    }
+#endif /* L2_DISABLE */
+}
+
+
+/*****************************************************************************/
+/* Validate packet                                                           */
+/*****************************************************************************/
+action set_unicast() {
+    modify_field(l2_metadata.lkp_pkt_type, L2_UNICAST);
+}
+
+action set_unicast_and_ipv6_src_is_link_local() {
+    modify_field(l2_metadata.lkp_pkt_type, L2_UNICAST);
+    modify_field(ipv6_metadata.ipv6_src_is_link_local, TRUE);
+}
+
+action set_multicast() {
+    modify_field(l2_metadata.lkp_pkt_type, L2_MULTICAST);
+    add_to_field(l2_metadata.bd_stats_idx, 1);
+}
+
+action set_multicast_and_ipv6_src_is_link_local() {
+    modify_field(l2_metadata.lkp_pkt_type, L2_MULTICAST);
+    modify_field(ipv6_metadata.ipv6_src_is_link_local, TRUE);
+    add_to_field(l2_metadata.bd_stats_idx, 1);
+}
+
+action set_broadcast() {
+    modify_field(l2_metadata.lkp_pkt_type, L2_BROADCAST);
+    add_to_field(l2_metadata.bd_stats_idx, 2);
+}
+
+action set_malformed_packet(drop_reason) {
+    modify_field(ingress_metadata.drop_flag, TRUE);
+    modify_field(ingress_metadata.drop_reason, drop_reason);
+}
+
+table validate_packet {
+    reads {
+#ifndef __TARGET_BMV2__
+        l2_metadata.lkp_mac_sa mask 0x010000000000 : ternary;
+#else
+        l2_metadata.lkp_mac_sa : ternary;
+#endif
+        l2_metadata.lkp_mac_da : ternary;
+        l3_metadata.lkp_ip_type : ternary;
+        l3_metadata.lkp_ip_ttl : ternary;
+        l3_metadata.lkp_ip_version : ternary;
+#ifndef __TARGET_BMV2__
+        ipv4_metadata.lkp_ipv4_sa mask 0xFF000000 : ternary;
+#else
+        ipv4_metadata.lkp_ipv4_sa : ternary;
+#endif
+#ifndef IPV6_DISABLE
+#ifndef __TARGET_BMV2__
+        ipv6_metadata.lkp_ipv6_sa mask 0xFFFF0000000000000000000000000000 : ternary;
+#else
+        ipv6_metadata.lkp_ipv6_sa : ternary;
+#endif
+#endif /* IPV6_DISABLE */
+    }
+    actions {
+        nop;
+        set_unicast;
+        set_unicast_and_ipv6_src_is_link_local;
+        set_multicast;
+        set_multicast_and_ipv6_src_is_link_local;
+        set_broadcast;
+        set_malformed_packet;
+    }
+    size : VALIDATE_PACKET_TABLE_SIZE;
+}
+
+control process_validate_packet {
+    if (ingress_metadata.drop_flag == FALSE) {
+        apply(validate_packet);
+    }
+}
+
+
+/*****************************************************************************/
+/* Egress BD lookup                                                          */
+/*****************************************************************************/
+action set_egress_bd_properties() {
+}
+
+table egress_bd_map {
+    reads {
+        egress_metadata.bd : exact;
+    }
+    actions {
+        nop;
+        set_egress_bd_properties;
+    }
+    size : EGRESS_BD_MAPPING_TABLE_SIZE;
+}
+
+control process_egress_bd {
+    apply(egress_bd_map);
+}
+
+
+/*****************************************************************************/
+/* Egress VLAN decap                                                         */
+/*****************************************************************************/
+action remove_vlan_single_tagged() {
+    modify_field(ethernet.etherType, vlan_tag_[0].etherType);
+    remove_header(vlan_tag_[0]);
+}
+
+action remove_vlan_double_tagged() {
+    modify_field(ethernet.etherType, vlan_tag_[1].etherType);
+    remove_header(vlan_tag_[0]);
+    remove_header(vlan_tag_[1]);
+}
+
+table vlan_decap {
+    reads {
+        vlan_tag_[0] : valid;
+        vlan_tag_[1] : valid;
+    }
+    actions {
+        nop;
+        remove_vlan_single_tagged;
+        remove_vlan_double_tagged;
+    }
+    size: VLAN_DECAP_TABLE_SIZE;
+}
+
+control process_vlan_decap {
+    apply(vlan_decap);
+}

samples/P4/mirror_acl.p4

@@ -0,0 +1,39 @@
+// Copyright 2015, Barefoot Networks, Inc.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+action set_mirror_id(session_id) {
+    clone_ingress_pkt_to_egress(session_id);
+}
+
+table mirror_acl {
+    reads {
+        ingress_metadata.if_label : ternary;
+        ingress_metadata.bd_label : ternary;
+
+        /* ip acl */
+        ingress_metadata.lkp_ipv4_sa : ternary;
+        ingress_metadata.lkp_ipv4_da : ternary;
+        ingress_metadata.lkp_ip_proto : ternary;
+
+        /* mac acl */
+        ingress_metadata.lkp_mac_sa : ternary;
+        ingress_metadata.lkp_mac_da : ternary;
+        ingress_metadata.lkp_mac_type : ternary;
+    }
+    actions {
+        nop;
+        set_mirror_id;
+    }
+    size : INGRESS_MIRROR_ACL_TABLE_SIZE;
+}

samples/PHP/ThriftGenerated.php

@@ -0,0 +1,93 @@
+<?php
+namespace github\com;
+
+/**
+ * Autogenerated by Thrift Compiler (0.9.3)
+ *
+ * DO NOT EDIT UNLESS YOU ARE SURE THAT YOU KNOW WHAT YOU ARE DOING
+ *  @generated
+ */
+use Thrift\Base\TBase;
+use Thrift\Type\TType;
+use Thrift\Type\TMessageType;
+use Thrift\Exception\TException;
+use Thrift\Exception\TProtocolException;
+use Thrift\Protocol\TProtocol;
+use Thrift\Protocol\TBinaryProtocolAccelerated;
+use Thrift\Exception\TApplicationException;
+
+
+class PullRequest {
+  static $_TSPEC;
+
+  /**
+   * @var string
+   */
+  public $title = null;
+
+  public function __construct($vals=null) {
+    if (!isset(self::$_TSPEC)) {
+      self::$_TSPEC = array(
+        1 => array(
+          'var' => 'title',
+          'type' => TType::STRING,
+          ),
+        );
+    }
+    if (is_array($vals)) {
+      if (isset($vals['title'])) {
+        $this->title = $vals['title'];
+      }
+    }
+  }
+
+  public function getName() {
+    return 'PullRequest';
+  }
+
+  public function read($input)
+  {
+    $xfer = 0;
+    $fname = null;
+    $ftype = 0;
+    $fid = 0;
+    $xfer += $input->readStructBegin($fname);
+    while (true)
+    {
+      $xfer += $input->readFieldBegin($fname, $ftype, $fid);
+      if ($ftype == TType::STOP) {
+        break;
+      }
+      switch ($fid)
+      {
+        case 1:
+          if ($ftype == TType::STRING) {
+            $xfer += $input->readString($this->title);
+          } else {
+            $xfer += $input->skip($ftype);
+          }
+          break;
+        default:
+          $xfer += $input->skip($ftype);
+          break;
+      }
+      $xfer += $input->readFieldEnd();
+    }
+    $xfer += $input->readStructEnd();
+    return $xfer;
+  }
+
+  public function write($output) {
+    $xfer = 0;
+    $xfer += $output->writeStructBegin('PullRequest');
+    if ($this->title !== null) {
+      $xfer += $output->writeFieldBegin('title', TType::STRING, 1);
+      $xfer += $output->writeString($this->title);
+      $xfer += $output->writeFieldEnd();
+    }
+    $xfer += $output->writeFieldStop();
+    $xfer += $output->writeStructEnd();
+    return $xfer;
+  }
+
+}

samples/PHP/filenames/.php_cs

@@ -0,0 +1,37 @@
+<?php
+
+$header = <<<'EOF'
+This file is part of PHP CS Fixer.
+
+(c) Fabien Potencier <fabien@symfony.com>
+    Dariusz Rumiński <dariusz.ruminski@gmail.com>
+
+This source file is subject to the MIT license that is bundled
+with this source code in the file LICENSE.
+EOF;
+
+return PhpCsFixer\Config::create()
+    ->setRiskyAllowed(true)
+    ->setRules(array(
+        '@Symfony' => true,
+        '@Symfony:risky' => true,
+        'combine_consecutive_unsets' => true,
+        'header_comment' => array('header' => $header),
+        'array_syntax' => array('syntax' => 'long'),
+        'no_extra_consecutive_blank_lines' => array('break', 'continue', 'extra', 'return', 'throw', 'use', 'parenthesis_brace_block', 'square_brace_block', 'curly_brace_block'),
+        'no_useless_else' => true,
+        'no_useless_return' => true,
+        'ordered_class_elements' => true,
+        'ordered_imports' => true,
+        'php_unit_strict' => true,
+        'phpdoc_add_missing_param_annotation' => true,
+        'psr4' => true,
+        'strict_comparison' => true,
+        'strict_param' => true,
+    ))
+    ->setFinder(
+        PhpCsFixer\Finder::create()
+            ->exclude('tests/Fixtures')
+            ->in(__DIR__)
+    )
+;

samples/PHP/filenames/.php_cs.dist

@@ -0,0 +1,37 @@
+<?php
+
+$header = <<<'EOF'
+This file is part of PHP CS Fixer.
+
+(c) Fabien Potencier <fabien@symfony.com>
+    Dariusz Rumiński <dariusz.ruminski@gmail.com>
+
+This source file is subject to the MIT license that is bundled
+with this source code in the file LICENSE.
+EOF;
+
+return PhpCsFixer\Config::create()
+    ->setRiskyAllowed(true)
+    ->setRules(array(
+        '@Symfony' => true,
+        '@Symfony:risky' => true,
+        'combine_consecutive_unsets' => true,
+        'header_comment' => array('header' => $header),
+        'array_syntax' => array('syntax' => 'long'),
+        'no_extra_consecutive_blank_lines' => array('break', 'continue', 'extra', 'return', 'throw', 'use', 'parenthesis_brace_block', 'square_brace_block', 'curly_brace_block'),
+        'no_useless_else' => true,
+        'no_useless_return' => true,
+        'ordered_class_elements' => true,
+        'ordered_imports' => true,
+        'php_unit_strict' => true,
+        'phpdoc_add_missing_param_annotation' => true,
+        'psr4' => true,
+        'strict_comparison' => true,
+        'strict_param' => true,
+    ))
+    ->setFinder(
+        PhpCsFixer\Finder::create()
+            ->exclude('tests/Fixtures')
+            ->in(__DIR__)
+    )
+;

samples/PLSQL/print_bool.prc

@@ -0,0 +1,12 @@
+create or replace procedure print_bool(
+    p_bool in BOOLEAN,
+    p_true_value in varchar2 default 'TRUE',
+    p_false_value in varchar2 := 'FALSE'
+)
+as
+begin
+
+    dbms_output.put_line(case when p_bool then p_true_value else p_false_value end);
+
+end print_bool;
+/

samples/PLSQL/videodb.ddl

@@ -0,0 +1,48 @@
+CREATE TABLE users (
+   user_name varchar2(40),
+   first_name varchar2(40),
+   last_name varchar2(40),
+   email varchar2(40),
+   password varchar2(40),
+   created_date DATE,
+   total_credits NUMBER,
+   credit_change_date DATE,
+   PRIMARY KEY (user_name)
+);
+/
+
+CREATE TABLE users_videos (
+   video_id NUMBER,
+   video_name varchar2(40),
+   user_name varchar2(40),
+   description varchar2(512),
+   upload_date DATE,
+   PRIMARY KEY (video_id),
+   CONSTRAINT "USERS_VIDEOS_FK1" FOREIGN KEY ("USER_NAME") REFERENCES "USERS"("USER_NAME")
+);
+/
+
+create or replace procedure print_user_videos(
+    p_user_name in users.user_name%type
+)
+AUTHID DEFINER
+as
+    type t_user_videos is table of users_videos%rowtype
+        index by pls_integer;
+    l_videos t_user_videos;
+begin
+
+    select *
+    bulk collect into l_videos
+    from users_videos
+    where user_name = p_user_name;
+
+    for i in 1..l_videos.COUNT
+    loop
+
+        dbms_output.put_line(l_videos(i).video_name);
+
+    end loop;
+
+end print_user_videos;
+/

samples/Puppet/init.pp

@@ -0,0 +1,4 @@
+include docker
+include apt
+include ::something
+include foo::bar

samples/Python/argparse.pyi

@@ -0,0 +1,159 @@
+# Stubs for argparse (Python 3.4)
+
+from typing import (
+    Any, Callable, Iterable, List, IO, Optional, Sequence, Tuple, Type, Union,
+    TypeVar, overload
+)
+import sys
+
+_T = TypeVar('_T')
+
+if sys.version_info >= (3,):
+    _Text = str
+else:
+    _Text = Union[str, unicode]
+
+ONE_OR_MORE = ...  # type: str
+OPTIONAL = ...  # type: str
+PARSER = ...  # type: str
+REMAINDER = ...  # type: str
+SUPPRESS = ...  # type: str
+ZERO_OR_MORE = ...  # type: str
+
+class ArgumentError(Exception): ...
+
+class ArgumentParser:
+    if sys.version_info >= (3, 5):
+        def __init__(self,
+                     prog: Optional[str] = ...,
+                     usage: Optional[str] = ...,
+                     description: Optional[str] = ...,
+                     epilog: Optional[str] = ...,
+                     parents: Sequence[ArgumentParser] = ...,
+                     formatter_class: Type[HelpFormatter] = ...,
+                     prefix_chars: _Text = ...,
+                     fromfile_prefix_chars: Optional[str] = ...,
+                     argument_default: Optional[str] = ...,
+                     conflict_handler: _Text = ...,
+                     add_help: bool = ...,
+                     allow_abbrev: bool = ...) -> None: ...
+    else:
+        def __init__(self,
+                     prog: Optional[_Text] = ...,
+                     usage: Optional[_Text] = ...,
+                     description: Optional[_Text] = ...,
+                     epilog: Optional[_Text] = ...,
+                     parents: Sequence[ArgumentParser] = ...,
+                     formatter_class: Type[HelpFormatter] = ...,
+                     prefix_chars: _Text = ...,
+                     fromfile_prefix_chars: Optional[_Text] = ...,
+                     argument_default: Optional[_Text] = ...,
+                     conflict_handler: _Text = ...,
+                     add_help: bool = ...) -> None: ...
+    def add_argument(self,
+                     *name_or_flags: Union[_Text, Sequence[_Text]],
+                     action: Union[_Text, Type[Action]] = ...,
+                     nargs: Union[int, _Text] = ...,
+                     const: Any = ...,
+                     default: Any = ...,
+                     type: Union[Callable[[str], _T], FileType] = ...,
+                     choices: Iterable[_T] = ...,
+                     required: bool = ...,
+                     help: _Text = ...,
+                     metavar: Union[_Text, Tuple[_Text, ...]] = ...,
+                     dest: _Text = ...,
+                     version: _Text = ...) -> None: ...  # weirdly documented
+    def parse_args(self, args: Optional[Sequence[_Text]] = ...,
+                   namespace: Optional[Namespace] = ...) -> Namespace: ...
+    def add_subparsers(self, title: _Text = ...,
+                       description: Optional[_Text] = ...,
+                       prog: _Text = ...,
+                       parser_class: Type[ArgumentParser] = ...,
+                       action: Type[Action] = ...,
+                       option_string: _Text = ...,
+                       dest: Optional[_Text] = ...,
+                       help: Optional[_Text] = ...,
+                       metavar: Optional[_Text] = ...) -> _SubParsersAction: ...
+    def add_argument_group(self, title: Optional[_Text] = ...,
+                           description: Optional[_Text] = ...) -> _ArgumentGroup: ...
+    def add_mutually_exclusive_group(self, required: bool = ...) -> _MutuallyExclusiveGroup: ...
+    def set_defaults(self, **kwargs: Any) -> None: ...
+    def get_default(self, dest: _Text) -> Any: ...
+    def print_usage(self, file: Optional[IO[str]] = ...) -> None: ...
+    def print_help(self, file: Optional[IO[str]] = ...) -> None: ...
+    def format_usage(self) -> str: ...
+    def format_help(self) -> str: ...
+    def parse_known_args(self, args: Optional[Sequence[_Text]] = ...,
+                         namespace: Optional[Namespace] = ...) -> Tuple[Namespace, List[str]]: ...
+    def convert_arg_line_to_args(self, arg_line: _Text) -> List[str]: ...
+    def exit(self, status: int = ..., message: Optional[_Text] = ...) -> None: ...
+    def error(self, message: _Text) -> None: ...
+
+class HelpFormatter:
+    # not documented
+    def __init__(self, prog: _Text, indent_increment: int = ...,
+                 max_help_position: int = ...,
+                 width: Optional[int] = ...) -> None: ...
+class RawDescriptionHelpFormatter(HelpFormatter): ...
+class RawTextHelpFormatter(HelpFormatter): ...
+class ArgumentDefaultsHelpFormatter(HelpFormatter): ...
+if sys.version_info >= (3,):
+    class MetavarTypeHelpFormatter(HelpFormatter): ...
+
+class Action:
+    def __init__(self,
+                 option_strings: Sequence[_Text],
+                 dest: _Text = ...,
+                 nargs: Optional[Union[int, _Text]] = ...,
+                 const: Any = ...,
+                 default: Any = ...,
+                 type: Union[Callable[[str], _T], FileType, None] = ...,
+                 choices: Optional[Iterable[_T]] = ...,
+                 required: bool = ...,
+                 help: Optional[_Text] = ...,
+                 metavar: Union[_Text, Tuple[_Text, ...]] = ...) -> None: ...
+    def __call__(self, parser: ArgumentParser, namespace: Namespace,
+                 values: Union[_Text, Sequence[Any], None],
+                 option_string: _Text = ...) -> None: ...
+
+class Namespace:
+    def __getattr__(self, name: _Text) -> Any: ...
+    def __setattr__(self, name: _Text, value: Any) -> None: ...
+
+class FileType:
+    if sys.version_info >= (3, 4):
+        def __init__(self, mode: _Text = ..., bufsize: int = ...,
+                     encoding: Optional[_Text] = ...,
+                     errors: Optional[_Text] = ...) -> None: ...
+    elif sys.version_info >= (3,):
+        def __init__(self,
+                     mode: _Text = ..., bufsize: int = ...) -> None: ...
+    else:
+        def __init__(self,
+                     mode: _Text = ..., bufsize: Optional[int] = ...) -> None: ...
+    def __call__(self, string: _Text) -> IO[Any]: ...
+
+class _ArgumentGroup:
+    def add_argument(self,
+                     *name_or_flags: Union[_Text, Sequence[_Text]],
+                     action: Union[_Text, Type[Action]] = ...,
+                     nargs: Union[int, _Text] = ...,
+                     const: Any = ...,
+                     default: Any = ...,
+                     type: Union[Callable[[str], _T], FileType] = ...,
+                     choices: Iterable[_T] = ...,
+                     required: bool = ...,
+                     help: _Text = ...,
+                     metavar: Union[_Text, Tuple[_Text, ...]] = ...,
+                     dest: _Text = ...,
+                     version: _Text = ...) -> None: ...
+    def add_mutually_exclusive_group(self, required: bool = ...) -> _MutuallyExclusiveGroup: ...
+
+class _MutuallyExclusiveGroup(_ArgumentGroup): ...
+
+class _SubParsersAction:
+    # TODO: Type keyword args properly.
+    def add_parser(self, name: _Text, **kwargs: Any) -> ArgumentParser: ...
+
+# not documented
+class ArgumentTypeError(Exception): ...

samples/Python/filenames/.gclient

@@ -0,0 +1,9 @@
+solutions = [
+  {
+    "url": "https://chromium.googlesource.com/v8/v8.git",
+    "managed": False,
+    "name": "v8",
+    "deps_file": "DEPS",
+    "custom_deps": {},
+  },
+]

samples/Python/filenames/WORKSPACE

@@ -0,0 +1,12 @@
+# rules for scala
+# https://github.com/bazelbuild/rules_scala#getting-started
+# pull rule definitions from git
+git_repository(
+    name = "io_bazel_rules_scala",
+    remote = "https://github.com/bazelbuild/rules_scala.git",
+    commit = "73743b830ae98d13a946b25ad60cad5fee58e6d3", # update this as needed
+)
+
+# load the desired scala rules for this workspace
+load("@io_bazel_rules_scala//scala:scala.bzl", "scala_repositories")
+scala_repositories()

samples/Python/py3.py3

@@ -0,0 +1,20 @@
+import random
+
+guesses = 0
+
+number = random.randint(1, 20)
+
+print("Guess the number between 1 and 20! You have 6 tries.")
+while guesses < 6:
+    guess = int(input("Is it... "))
+
+    if guess == number:
+        print("Hooray! You guessed it right!")
+        break
+    elif guess < number:
+        print("It's bigger...")
+    elif guess > number:
+        print("It's not so big.")
+    guesses += 1
+if guesses == 6:
+    print("You've ran out of tries.")