Release v5.0.5 -- part Deux (#3479)

* bumping to v5.0.5

* relaxing rugged version requirement

.gitignore

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

.gitmodules

@@ -130,9 +130,6 @@
 [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
@@ -247,9 +244,6 @@
 [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
@@ -443,9 +437,6 @@
 [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
@@ -623,9 +614,6 @@
 [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
@@ -809,4 +797,24 @@
 [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

CONTRIBUTING.md

@@ -17,7 +17,7 @@ To add support for a new extension:
 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. 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.
 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.
 
 
@@ -36,7 +36,7 @@ To add support for a new language:
 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. 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.
 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.
 
 Remember, the goal here is to try and avoid false positives!
@@ -80,7 +80,6 @@ Here's our current build status: [![Build Status](https://api.travis-ci.org/gith
 Linguist is maintained with :heart: by:
 
 - **@Alhadis**
-- **@arfon**
 - **@brandonblack** (GitHub staff)
 - **@larsbrinkhoff**
 - **@lildude** (GitHub staff)

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

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

@@ -1,30 +1,38 @@
 #!/usr/bin/env ruby
 
-# linguist — detect language type for a file, or, given a directory, determine language breakdown
+$LOAD_PATH[0, 0] = File.join(File.dirname(__FILE__), '..', 'lib')
-#     usage: linguist <path> [<--breakdown>]
+
-#
 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)
+  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
     file_breakdown = repo.breakdown_by_file
@@ -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 directory, 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'

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:
@@ -113,7 +113,9 @@ 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
@@ -178,8 +180,15 @@ vendor/grammars/atom-language-1c-bsl:
 - source.sdbl
 vendor/grammars/atom-language-clean:
 - source.clean
+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:
@@ -225,8 +234,6 @@ 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
@@ -360,6 +367,8 @@ 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:
@@ -384,8 +393,6 @@ 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:
@@ -408,6 +415,10 @@ vendor/grammars/language-povray:
 vendor/grammars/language-python:
 - text.python.console
 - text.python.traceback
+vendor/grammars/language-regexp:
+- source.regexp
+- source.regexp.comment
+- source.regexp.extended
 vendor/grammars/language-renpy:
 - source.renpy
 vendor/grammars/language-restructuredtext:
@@ -436,6 +447,8 @@ 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:
@@ -513,10 +526,6 @@ 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:
@@ -541,6 +550,8 @@ vendor/grammars/r.tmbundle:
 - text.tex.latex.rd
 vendor/grammars/rascal-syntax-highlighting:
 - source.rascal
+vendor/grammars/reason:
+- source.reason
 vendor/grammars/ruby-slim.tmbundle:
 - text.slim
 vendor/grammars/ruby.tmbundle:
@@ -608,8 +619,6 @@ 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

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/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?
@@ -275,6 +279,17 @@ module Linguist
       return lines[0].include?("Generated by the protocol buffer compiler.  DO NOT EDIT!")
     end
 
+    # 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?
@@ -311,7 +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?
@@ -333,7 +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?
@@ -433,5 +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

@@ -260,7 +260,7 @@ 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"]
@@ -278,7 +278,7 @@ 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"]]
@@ -326,7 +326,7 @@ 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"]

lib/linguist/language.rb

@@ -215,7 +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
@@ -265,7 +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
@@ -283,9 +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]
 
@@ -437,12 +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
     #
@@ -557,7 +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

@@ -499,6 +499,7 @@ C++:
   - ".inc"
   - ".inl"
   - ".ipp"
+  - ".re"
   - ".tcc"
   - ".tpp"
   language_id: 43
@@ -1120,6 +1121,7 @@ Emacs Lisp:
   - ".gnus"
   - ".spacemacs"
   - ".viper"
+  - Cask
   - Project.ede
   - _emacs
   - abbrev_defs
@@ -1154,6 +1156,7 @@ Erlang:
   - ".xrl"
   - ".yrl"
   filenames:
+  - Emakefile
   - rebar.config
   - rebar.config.lock
   - rebar.lock
@@ -1384,6 +1387,14 @@ 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:
@@ -1595,7 +1606,7 @@ HTML:
   ace_mode: html
   codemirror_mode: htmlmixed
   codemirror_mime_type: text/html
-  color: "#e44b23"
+  color: "#e34c26"
   aliases:
   - xhtml
   extensions:
@@ -1754,7 +1765,7 @@ Hy:
   - ".hy"
   aliases:
   - hylang
-  tm_scope: source.hy
+  tm_scope: none
   language_id: 159
 HyPhy:
   type: programming
@@ -2281,6 +2292,8 @@ LookML:
   color: "#652B81"
   extensions:
   - ".lookml"
+  - ".model.lkml"
+  - ".view.lkml"
   tm_scope: source.yaml
   language_id: 211
 LoomScript:
@@ -3216,6 +3229,7 @@ PowerBuilder:
   language_id: 292
 PowerShell:
   type: programming
+  color: "#012456"
   ace_mode: powershell
   codemirror_mode: powershell
   codemirror_mime_type: application/x-powershell
@@ -3548,6 +3562,19 @@ 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"
@@ -3578,6 +3605,17 @@ 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:
@@ -3790,6 +3828,7 @@ SQL:
   - ".cql"
   - ".ddl"
   - ".inc"
+  - ".mysql"
   - ".prc"
   - ".tab"
   - ".udf"
@@ -4274,12 +4313,16 @@ 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
@@ -4566,6 +4609,15 @@ 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
@@ -4759,6 +4811,7 @@ YAML:
   - ".syntax"
   - ".yaml"
   - ".yaml-tmlanguage"
+  - ".yml.mysql"
   filenames:
   - ".clang-format"
   ace_mode: yaml

lib/linguist/vendor.yml

@@ -238,6 +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 = "5.0.0"
+  VERSION = "5.0.5"
 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/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/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/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/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/R/import.Rd

@@ -0,0 +1,72 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/hello.R
+\name{import}
+\alias{import}
+\title{Import a module into the current scope}
+\usage{
+import(module, attach, attach_operators = TRUE)
+}
+\arguments{
+\item{module}{an identifier specifying the full module path}
+
+\item{attach}{if \code{TRUE}, attach the newly loaded module to the object
+search path (see \code{Details})}
+
+\item{attach_operators}{if \code{TRUE}, attach operators of module to the
+object search path, even if \code{attach} is \code{FALSE}}
+}
+\value{
+the loaded module environment (invisible)
+}
+\description{
+\code{module = import('module')} imports a specified module and makes its
+code available via the environment-like object it returns.
+}
+\details{
+Modules are loaded in an isolated environment which is returned, and
+optionally attached to the object search path of the current scope (if
+argument \code{attach} is \code{TRUE}).
+\code{attach} defaults to \code{FALSE}. However, in interactive code it is
+often helpful to attach packages by default. Therefore, in interactive code
+invoked directly from the terminal only (i.e. not within modules),
+\code{attach} defaults to the value of \code{options('import.attach')}, which
+can be set to \code{TRUE} or \code{FALSE} depending on the user’s preference.
+
+\code{attach_operators} causes \emph{operators} to be attached by default,
+because operators can only be invoked in R if they re found in the search
+path. Not attaching them therefore drastically limits a module’s usefulness.
+
+Modules are searched in the module search path \code{options('import.path')}.
+This is a vector of paths to consider, from the highest to the lowest
+priority. The current directory is \emph{always} considered first. That is,
+if a file \code{a.r} exists both in the current directory and in a module
+search path, the local file \code{./a.r} will be loaded.
+
+Module names can be fully qualified to refer to nested paths. See
+\code{Examples}.
+}
+\note{
+Unlike for packages, attaching happens \emph{locally}: if
+\code{import} is executed in the global environment, the effect is the same.
+Otherwise, the imported module is inserted as the parent of the current
+\code{environment()}. When used (globally) \emph{inside} a module, the newly
+imported module is only available inside the module’s search path, not
+outside it (nor in other modules which might be loaded).
+}
+\examples{
+# `a.r` is a file in the local directory containing a function `f`.
+a = import('a')
+a$f()
+
+# b/c.r is a file in path `b`, containing a function `g`.
+import('b/c', attach = TRUE)
+g() # No module name qualification necessary
+
+}
+\seealso{
+\code{unload}
+
+\code{reload}
+
+\code{module_name}
+}

samples/Reason/JSX.re

@@ -0,0 +1,483 @@
+type component = {displayName: string};
+
+let module Bar = {
+  let createElement c::c=? children => {
+    displayName: "test"
+  };
+};
+
+let module Nesting = {
+  let createElement children => {
+    displayName: "test"
+  };
+};
+
+let module Much = {
+  let createElement children => {
+    displayName: "test"
+  };
+};
+
+let module Foo = {
+  let createElement a::a=? b::b=? children => {
+    displayName: "test"
+  };
+};
+
+let module One = {
+  let createElement
+      test::test=?
+      foo::foo=?
+      children => {
+    displayName: "test"
+  };
+  let createElementobvioustypo
+      test::test
+      children => {
+    displayName: "test"
+  };
+};
+
+let module Two = {
+  let createElement foo::foo=? children => {
+    displayName: "test"
+  };
+};
+
+let module Sibling = {
+  let createElement
+      foo::foo=?
+      (children: list component) => {
+    displayName: "test"
+  };
+};
+
+let module Test = {
+  let createElement yo::yo=? children => {
+    displayName: "test"
+  };
+};
+
+let module So = {
+  let createElement children => {
+    displayName: "test"
+  };
+};
+
+let module Foo2 = {
+  let createElement children => {
+    displayName: "test"
+  };
+};
+
+let module Text = {
+  let createElement children => {
+    displayName: "test"
+  };
+};
+
+let module Exp = {
+  let createElement children => {
+    displayName: "test"
+  };
+};
+
+let module Pun = {
+  let createElement intended::intended=? children => {
+    displayName: "test"
+  };
+};
+
+let module Namespace = {
+  let module Foo = {
+    let createElement
+        intended::intended=?
+        anotherOptional::x=100
+        children => {
+      displayName: "test"
+    };
+  };
+};
+
+let module LotsOfArguments = {
+  let createElement
+      argument1::argument1=?
+      argument2::argument2=?
+      argument3::argument3=?
+      argument4::argument4=?
+      argument5::argument5=?
+      argument6::argument6=?
+      children => {
+    displayName: "test"
+  };
+};
+
+let div argument1::argument1=? children => {
+  displayName: "test"
+};
+
+let module List1 = {
+  let createElement children => {
+    displayName: "test"
+  };
+};
+
+let module List2 = {
+  let createElement children => {
+    displayName: "test"
+  };
+};
+
+let module List3 = {
+  let createElement children => {
+    displayName: "test"
+  };
+};
+
+let (/><) a b => a + b;
+
+let (><) a b => a + b;
+
+let (/>) a b => a + b;
+
+let (><\/) a b => a + b;
+
+let tag1 = 5 />< 6;
+
+let tag2 = 5 >< 7;
+
+let tag3 = 5 /> 7;
+
+let tag4 = 5 ><\/ 7;
+
+let b = 2;
+
+let selfClosing = <Foo />;
+
+let selfClosing2 = <Foo a=1 b=true />;
+
+let selfClosing3 =
+  <Foo
+    a="really long values that should"
+    b="cause the entire thing to wrap"
+  />;
+
+let a = <Foo> <Bar c=(fun a => a + 2) /> </Foo>;
+
+let a3 = <So> <Much> <Nesting /> </Much> </So>;
+
+let a4 =
+  <Sibling>
+    <One test=true foo=b />
+    <Two foo=b />
+  </Sibling>;
+
+let a5 = <Foo> "testing a string here" </Foo>;
+
+let a6 =
+  <Foo2>
+    <Text> "testing a string here" </Text>
+    <Test yo=1 />
+    <Text> "another string" </Text>
+    <Bar />
+    <Exp> (2 + 4) </Exp>
+  </Foo2>;
+
+let intended = true;
+
+let punning = <Pun intended />;
+
+let namespace = <Namespace.Foo />;
+
+let c = <Foo />;
+
+let d = <Foo />;
+
+let spaceBefore =
+  <So> <Much> <Nesting /> </Much> </So>;
+
+let spaceBefore2 = <So> <Much /> </So>;
+
+let siblingNotSpaced =
+  <So> <Much /> <Much /> </So>;
+
+let jsxInList = [<Foo />];
+
+let jsxInList2 = [<Foo />];
+
+let jsxInListA = [<Foo />];
+
+let jsxInListB = [<Foo />];
+
+let jsxInListC = [<Foo />];
+
+let jsxInListD = [<Foo />];
+
+let jsxInList3 = [<Foo />, <Foo />, <Foo />];
+
+let jsxInList4 = [<Foo />, <Foo />, <Foo />];
+
+let jsxInList5 = [<Foo />, <Foo />];
+
+let jsxInList6 = [<Foo />, <Foo />];
+
+let jsxInList7 = [<Foo />, <Foo />];
+
+let jsxInList8 = [<Foo />, <Foo />];
+
+let testFunc b => b;
+
+let jsxInFnCall = testFunc <Foo />;
+
+let lotsOfArguments =
+  <LotsOfArguments
+    argument1=1
+    argument2=2
+    argument3=3
+    argument4=4
+    argument5=5
+    argument6="test">
+    <Namespace.Foo />
+  </LotsOfArguments>;
+
+let lowerCase = <div argument1=1 />;
+
+let b = 0;
+
+let d = 0;
+
+/*
+ * Should pun the first example:
+ */
+let a = <Foo a> 5 </Foo>;
+
+let a = <Foo a=b> 5 </Foo>;
+
+let a = <Foo a=b b=d> 5 </Foo>;
+
+let a = <Foo a> 0.55 </Foo>;
+
+let a = Foo.createElement "" [@JSX];
+
+let ident = <Foo> a </Foo>;
+
+let fragment1 = <> <Foo /> <Foo /> </>;
+
+let fragment2 = <> <Foo /> <Foo /> </>;
+
+let fragment3 = <> <Foo /> <Foo /> </>;
+
+let fragment4 = <> <Foo /> <Foo /> </>;
+
+let fragment5 = <> <Foo /> <Foo /> </>;
+
+let fragment6 = <> <Foo /> <Foo /> </>;
+
+let fragment7 = <> <Foo /> <Foo /> </>;
+
+let fragment8 = <> <Foo /> <Foo /> </>;
+
+let fragment9 = <> 2 2 2 2 </>;
+
+let fragment10 = <> 2.2 3.2 4.6 1.2 </>;
+
+let fragment11 = <> "str" </>;
+
+let fragment12 = <> (6 + 2) (6 + 2) (6 + 2) </>;
+
+let fragment13 = <> fragment11 fragment11 </>;
+
+let listOfItems1 = <List1> 1 2 3 4 5 </List1>;
+
+let listOfItems2 =
+  <List2> 1.0 2.8 3.8 4.0 5.1 </List2>;
+
+let listOfItems3 =
+  <List3> fragment11 fragment11 </List3>;
+
+/*
+ * Several sequential simple jsx expressions must be separated with a space.
+ */
+let thisIsRight a b => ();
+
+let tagOne children => ();
+
+let tagTwo children => ();
+
+/* thisIsWrong <tagOne /><tagTwo />; */
+thisIsRight <tagOne /> <tagTwo />;
+
+/* thisIsWrong <tagOne> </tagOne><tagTwo> </tagTwo>; */
+thisIsRight <tagOne /> <tagTwo />;
+
+let a children => ();
+
+let b children => ();
+
+let thisIsOkay =
+  <List1> <a /> <b /> <a /> <b /> </List1>;
+
+let thisIsAlsoOkay =
+  <List1> <a /> <b /> </List1>;
+
+/* Doesn't make any sense, but suppose you defined an
+   infix operator to compare jsx */
+<a /> < <b />;
+
+<a /> > <b />;
+
+<a /> < <b />;
+
+<a /> > <b />;
+
+let listOfListOfJsx = [<> </>];
+
+let listOfListOfJsx = [<> <Foo /> </>];
+
+let listOfListOfJsx = [
+  <> <Foo /> </>,
+  <> <Bar /> </>
+];
+
+let listOfListOfJsx = [
+  <> <Foo /> </>,
+  <> <Bar /> </>,
+  ...listOfListOfJsx
+];
+
+let sameButWithSpaces = [<> </>];
+
+let sameButWithSpaces = [<> <Foo /> </>];
+
+let sameButWithSpaces = [
+  <> <Foo /> </>,
+  <> <Bar /> </>
+];
+
+let sameButWithSpaces = [
+  <> <Foo /> </>,
+  <> <Bar /> </>,
+  ...sameButWithSpaces
+];
+
+/*
+ * Test named tag right next to an open bracket.
+ */
+let listOfJsx = [];
+
+let listOfJsx = [<Foo />];
+
+let listOfJsx = [<Foo />, <Bar />];
+
+let listOfJsx = [<Foo />, <Bar />, ...listOfJsx];
+
+let sameButWithSpaces = [];
+
+let sameButWithSpaces = [<Foo />];
+
+let sameButWithSpaces = [<Foo />, <Bar />];
+
+let sameButWithSpaces = [
+  <Foo />,
+  <Bar />,
+  ...sameButWithSpaces
+];
+
+
+/**
+ * Test no conflict with polymorphic variant types.
+ */
+type thisType = [ | `Foo | `Bar];
+
+type t 'a = [< thisType] as 'a;
+
+let asd =
+  <One test=true foo=2> "a" "b" </One> [@foo];
+
+let asd2 =
+  One.createElementobvioustypo
+  test::false
+  ["a", "b"]
+  [@JSX]
+  [@foo];
+
+let span
+    test::(test: bool)
+    foo::(foo: int)
+    children => 1;
+
+let asd =
+  <span test=true foo=2> "a" "b" </span> [@foo];
+
+/* "video" call doesn't end with a list, so the expression isn't converted to JSX */
+let video test::(test: bool) children => children;
+
+let asd2 = video test::false 10 [@JSX] [@foo];
+
+let div children => 1;
+
+((fun () => div) ()) [] [@JSX];
+
+let myFun () =>
+  <>
+    <Namespace.Foo
+      intended=true
+      anotherOptional=200
+    />
+    <Namespace.Foo
+      intended=true
+      anotherOptional=200
+    />
+    <Namespace.Foo
+      intended=true anotherOptional=200>
+      <Foo />
+      <Foo />
+      <Foo />
+      <Foo />
+      <Foo />
+      <Foo />
+      <Foo />
+    </Namespace.Foo>
+  </>;
+
+let myFun () => <> </>;
+
+let myFun () =>
+  <>
+    <Namespace.Foo
+      intended=true
+      anotherOptional=200
+    />
+    <Namespace.Foo
+      intended=true
+      anotherOptional=200
+    />
+    <Namespace.Foo
+      intended=true anotherOptional=200>
+      <Foo />
+      <Foo />
+      <Foo />
+      <Foo />
+      <Foo />
+      <Foo />
+      <Foo />
+    </Namespace.Foo>
+  </>;
+
+
+/**
+ * Children should wrap without forcing attributes to.
+ */
+<Foo a=10 b=0>
+  <Bar />
+  <Bar />
+  <Bar />
+  <Bar />
+</Foo>;
+/**
+ * Failing test cases:
+ */
+/* let res = <Foo a=10 b=(<Foo a=200 />) > */
+/*   <Bar /> */
+/* </Foo>; */
+/* let res = <Foo a=10 b=(<Foo a=200 />) />; */

samples/Reason/Machine.re

@@ -0,0 +1,344 @@
+open Format;
+
+let module Endo = {
+  type t 'a = 'a => 'a;
+};
+
+let module Syntax = {
+  let module Var = {
+    type t = int;
+  };
+  let module Term = {
+    type t =
+      | App t t
+      | Lam t
+      | Var Var.t
+      ;
+  };
+  let module Sub = {
+    type t 'a =
+      | Cmp (t 'a) (t 'a)
+      | Dot 'a (t 'a)
+      | Id
+      | Shift
+      ;
+
+    let map f sgm => {
+      let rec go = fun
+      | Cmp sgm0 sgm1 => Cmp (go sgm0) (go sgm1)
+      | Dot a sgm => Dot (f a) (go sgm)
+      | Id => Id
+      | Shift => Shift
+      ;
+      go sgm;
+    };
+
+    let rec apply sgm e =>
+      switch (sgm, e) {
+      | (sgm, Term.App e0 e1) => Term.App (apply sgm e0) (apply sgm e1)
+      | (sgm, Term.Lam e) => Term.Lam (apply (Dot (Term.Var 0) (Cmp sgm Shift)) e)
+      | (Dot e _, Term.Var 0) => e
+      | (Dot _ sgm, Term.Var i) => apply sgm (Term.Var (i - 1))
+      | (Id, Term.Var i) => Term.Var i
+      | (Shift, Term.Var i) => Term.Var (i + 1)
+      | (Cmp rho sgm, e) => apply sgm (apply rho e)
+      };
+  };
+};
+
+let module Zip = {
+  open Syntax;
+  type t 'a =
+    | App0 (t 'a) 'a
+    | App1 'a (t 'a)
+    | Halt
+    | Lam (t 'a)
+    ;
+
+  let map f sgm => {
+    let rec go = fun
+    | App0 zip e1 => App0 (go zip) (f e1)
+    | App1 e0 zip => App1 (f e0) (go zip)
+    | Halt => Halt
+    | Lam zip => Lam (go zip)
+    ;
+    go sgm;
+  };
+
+  let rec apply zip acc => switch zip {
+    | App0 zip e1 => apply zip (Term.App acc e1)
+    | App1 e0 zip => apply zip (Term.App e0 acc)
+    | Halt => acc
+    | Lam zip => apply zip (Term.Lam acc)
+  };
+};
+
+let module Clo = {
+  open Syntax;
+  type t =
+    | Clo Term.t (Sub.t t);
+  let rec from (Clo term sgm) => Sub.apply (Sub.map from sgm) term;
+};
+
+let module Pretty = {
+  let module Delim = {
+    type t = string;
+    let pp prev next fmt token => if (prev < next) { fprintf fmt "%s" token };
+  };
+  let module Prec = {
+    type t = int;
+    open Syntax.Term;
+    let calc = fun
+      | App _ _ => 1
+      | Lam _ => 2
+      | Var _ => 0
+      ;
+  };
+  let module Name = {
+    type t = string;
+
+    let suffix = {
+      let script = fun
+        | 0 => "₀"
+        | 1 => "₁"
+        | 2 => "₂"
+        | 3 => "₃"
+        | 4 => "₄"
+        | 5 => "₅"
+        | 6 => "₆"
+        | 7 => "₇"
+        | 8 => "₈"
+        | 9 => "₉"
+        | _ => failwith "bad subscript";
+      let rec go acc => fun
+        | 0 => acc
+        | n => go (script (n mod 10) ^ acc) (n / 10);
+      go ""
+    };
+
+    let gen = {
+      let offset = 97;
+      let width = 26;
+      fun () i => {
+        let code = i mod width + offset;
+        let char = Char.chr code;
+        let prime = i / width;
+        let suffix = suffix prime;
+        let name = Char.escaped char ^ suffix;
+        Some name;
+      }
+    };
+  };
+
+  let module Env = {
+    type t = {
+      used: list Name.t,
+      rest: Stream.t Name.t,
+    };
+    let mk () => {
+      let used = [];
+      let rest = Stream.from @@ Name.gen ();
+      { used, rest };
+    };
+  };
+
+  type printer 'a = Env.t => Prec.t => formatter => 'a => unit;
+
+  let module Term = {
+    open Syntax.Term;
+    let rec pp ({ Env.used: used, rest } as env) prev fmt e => {
+      let next = Prec.calc e;
+      switch e {
+      | App e0 e1 =>
+        fprintf fmt "@[%a%a@ %a%a@]"
+          (Delim.pp prev next) "("
+          (pp env 1) e0
+          (pp env 0) e1
+          (Delim.pp prev next) ")"
+      | Lam e =>
+        let name = Stream.next rest;
+        let env = { ...env, Env.used: [name, ...used] };
+        fprintf fmt "%aλ%a.%a%a"
+          (Delim.pp prev next) "("
+          (pp_print_string) name
+          (pp env next) e
+          (Delim.pp prev next) ")"
+      | Var index =>
+        fprintf fmt "%s" @@ try (List.nth used index) {
+          | _ => "#" ^ string_of_int index
+          }
+      }
+    };
+  };
+
+  let module Sub = {
+    open Syntax.Sub;
+    let rec pp pp_elem env prev fmt => fun
+    | Cmp sgm1 sgm0 =>
+      fprintf fmt "@[%a;@ %a@]"
+        (pp pp_elem env prev) sgm1
+        (pp pp_elem env prev) sgm0
+    | Dot e sgm =>
+      fprintf fmt "@[%a@ ·@ %a@]"
+        (pp_elem env prev) e
+        (pp pp_elem env prev) sgm
+    | Id =>
+      fprintf fmt "ι"
+    | Shift =>
+      fprintf fmt "↑"
+    ;
+  };
+
+  let module Clo = {
+    let rec pp env prev fmt (Clo.Clo e sgm) => {
+      let next = Prec.calc e;
+      fprintf fmt "@[%a%a%a[%a]@]"
+        (Delim.pp prev next) "("
+        (Term.pp env next) e
+        (Delim.pp prev next) ")"
+        (Sub.pp pp env next) sgm
+    };
+  };
+
+  let module Zip = {
+    open Zip;
+    let rec pp pp_elem env prev fmt => fun
+    | App0 zip elem =>
+      fprintf fmt "inl@[<v -1>⟨@,%a@,%a⟩@]"
+        (pp pp_elem env prev) zip
+        (pp_elem env prev) elem
+    | App1 elem zip =>
+      fprintf fmt "inr@[<v -1>⟨@,%a@,%a⟩@]"
+        (pp_elem env prev) elem
+        (pp pp_elem env prev) zip
+    | Halt =>
+      fprintf fmt "halt"
+    | Lam zip =>
+      fprintf fmt "lam@[<v -1>⟨@,%a⟩@]"
+        (pp pp_elem env prev) zip
+    ;
+  };
+};
+
+let module Machine = {
+  type t = {
+    clo: Clo.t,
+    ctx: Zip.t Clo.t,
+  };
+
+  let into e => {
+    open Clo;
+    open Syntax.Sub;
+    let clo = Clo e Id;
+    let ctx = Zip.Halt;
+    { clo, ctx }
+  };
+
+  let from { clo, ctx } => Zip.apply (Zip.map Clo.from ctx) (Clo.from clo);
+
+  let pp fmt rule state => {
+    fprintf fmt "@[<v>ctx  ::@[<v -5>@,%a@]@,clo  ::@[<v -5>@,%a@]@,rule ::@[<v -5>@,%a@]@,term ::@[<v -5>@,%a@]@]@."
+      (Pretty.Zip.pp Pretty.Clo.pp (Pretty.Env.mk ()) 2) state.ctx
+                    (Pretty.Clo.pp (Pretty.Env.mk ()) 2) state.clo
+                                       (pp_print_string) rule
+                   (Pretty.Term.pp (Pretty.Env.mk ()) 2) (from state)
+  };
+
+  let halted state => {
+    open Clo;
+    open Syntax.Sub;
+    open Syntax.Term;
+    switch state {
+    | { clo: Clo (Var _) Id, _ } => true
+    | _ => false
+    } [@warning "-4"];
+  };
+
+  let step state => {
+    open Clo;
+    open Syntax.Sub;
+    open Syntax.Term;
+    let rule = ref "";
+    let state = switch state {
+    /* left */
+    | { clo: Clo (App e0 e1) sgm, ctx } =>
+      let clo = Clo e0 sgm;
+      let ctx = Zip.App0 ctx (Clo e1 sgm);
+      rule := "LEFT";
+      { clo, ctx };
+    /* beta */
+    | { clo: Clo (Lam e) sgm, ctx: Zip.App0 ctx c0 } =>
+      let clo = Clo e (Cmp (Dot c0 sgm) Id);
+      rule := "BETA";
+      { clo, ctx };
+    /* lambda */
+    | { clo: Clo (Lam e) sgm, ctx } =>
+      let clo = Clo e (Cmp (Dot (Clo (Var 0) Id) (Cmp sgm Shift)) Id);
+      let ctx = Zip.Lam ctx;
+      rule := "LAMBDA";
+      { clo, ctx };
+    /* associate */
+    | { clo: Clo (Var n) (Cmp (Cmp pi rho) sgm), ctx } =>
+      let clo = Clo (Var n) (Cmp pi (Cmp rho sgm));
+      rule := "ASSOCIATE";
+      { clo, ctx };
+    /* head */
+    | { clo: Clo (Var 0) (Cmp (Dot (Clo e pi) _) sgm), ctx } =>
+      let clo = Clo e (Cmp pi sgm);
+      rule := "HEAD";
+      { clo, ctx };
+    /* tail */
+    | { clo: Clo (Var n) (Cmp (Dot (Clo _ _) rho) sgm), ctx } =>
+      let clo = Clo (Var (n - 1)) (Cmp rho sgm);
+      rule := "TAIL";
+      { clo, ctx };
+    /* shift */
+    | { clo: Clo (Var n) (Cmp Shift sgm), ctx } =>
+      let clo = Clo (Var (n + 1)) sgm;
+      rule := "SHIFT";
+      { clo, ctx };
+    /* id */
+    | { clo: Clo (Var n) (Cmp Id sgm), ctx } =>
+      let clo = Clo (Var n) sgm;
+      rule := "ID";
+      { clo, ctx };
+    | _ =>
+      pp std_formatter !rule state;
+      failwith "bad state";
+    } [@warning "-4"];
+    pp std_formatter !rule state;
+    state;
+  };
+
+  let norm e => {
+    let count = ref 0;
+    let state = ref (into e);
+    while (not (halted !state)) {
+      fprintf std_formatter "@\n--- step[%d] ---@\n" !count;
+      incr count;
+      state := step !state;
+    };
+    from !state;
+  };
+};
+
+let module Test = {
+  open Syntax.Term;
+  let l e => Lam e;
+  let ( *@ ) e0 e1 => App e0 e1;
+  let ff = l (l (Var 1));
+  let tt = l (l (Var 0));
+  let zero = l (l (Var 1));
+  let succ = l (l (l (Var 0 *@ Var 2)));
+  let one = succ *@ zero;
+  let two = succ *@ one;
+  let three = succ *@ two;
+  let const = l (l (Var 1));
+  let fix = l (l (Var 1 *@ (Var 0 *@ Var 0)) *@ l (Var 1 *@ (Var 0 *@ Var 0)));
+  let add = fix *@ l (l (l (Var 1 *@ Var 0 *@ l (succ *@ Var 3 *@ Var 0 *@ Var 1))));
+  let init = l (l (Var 0) *@ l (l (Var 1)));
+};
+
+let module Run = {
+  let go () => Machine.norm Test.init;
+};

samples/Reason/SuperMerlin.re

@@ -0,0 +1,308 @@
+/*
+ * Copyright (c) 2015-present, Facebook, Inc.
+ * All rights reserved.
+ *
+ */
+let startedMerlin: ref (option Js.Unsafe.any) = {contents: None};
+
+let fixedEnv = Js.Unsafe.js_expr "require('../lib/fixedEnv')";
+
+/* This and the subsequent big js blocks are copied over from Nuclide. More convenient for now. */
+let findNearestMerlinFile' = Js.Unsafe.js_expr {|
+  function findNearestMerlinFile(beginAtFilePath) {
+    var path = require('path');
+    var fs = require('fs');
+    var fileDir = path.dirname(beginAtFilePath);
+    var currentPath = path.resolve(fileDir);
+    do {
+      var fileToFind = path.join(currentPath, '.merlin');
+      var hasFile = fs.existsSync(fileToFind);
+      if (hasFile) {
+        return path.dirname(currentPath);
+      }
+
+      if (path.dirname(currentPath) === currentPath) {
+        // Bail
+        return '.';
+      }
+      currentPath = path.dirname(currentPath);
+    } while (true);
+  }
+|};
+
+let findNearestMerlinFile beginAtFilePath::path => {
+  let result = Js.Unsafe.fun_call findNearestMerlinFile' [|Js.Unsafe.inject (Js.string path)|];
+  Js.to_string result
+};
+
+let createMerlinReaderFnOnce' = Js.Unsafe.js_expr {|
+  function(ocamlMerlinPath, ocamlMerlinFlags, dotMerlinDir, fixedEnv) {
+    var spawn = require('child_process').spawn;
+    // To split while stripping out any leading/trailing space, we match on all
+    // *non*-whitespace.
+    var items = ocamlMerlinFlags === '' ? [] : ocamlMerlinFlags.split(/\s+/);
+    var merlinProcess = spawn(ocamlMerlinPath, items, {cwd: dotMerlinDir});
+    merlinProcess.stderr.on('data', function(d) {
+      console.error('Ocamlmerlin: something wrong happened:');
+      console.error(d.toString());
+    });
+
+    merlinProcess.stdout.on('close', function(d) {
+      console.error('Ocamlmerlin: closed.');
+    });
+
+    var cmdQueue = [];
+    var hasStartedReading = false;
+
+    var readline = require('readline');
+    var reader = readline.createInterface({
+      input: merlinProcess.stdout,
+      terminal: false,
+    });
+
+    return function(cmd, resolve, reject) {
+      cmdQueue.push([resolve, reject]);
+
+      if (!hasStartedReading) {
+        hasStartedReading = true;
+        reader.on('line', function(line) {
+          var response;
+          try {
+            response = JSON.parse(line);
+          } catch (err) {
+            response = null;
+          }
+          var resolveReject = cmdQueue.shift();
+          var resolve = resolveReject[0];
+          var reject = resolveReject[1];
+
+          if (!response || !Array.isArray(response) || response.length !== 2) {
+            reject(new Error('Unexpected ocamlmerlin output format: ' + line));
+            return;
+          }
+
+          var status = response[0];
+          var content = response[1];
+
+          var errorResponses = {
+            'failure': true,
+            'error': true,
+            'exception': true,
+          };
+
+          if (errorResponses[status]) {
+            reject(new Error('Ocamlmerlin returned an error: ' + line));
+            return;
+          }
+
+          resolve(content);
+        });
+      }
+
+      merlinProcess.stdin.write(JSON.stringify(cmd));
+    };
+  }
+|};
+
+let createMerlinReaderFnOnce
+    pathToMerlin::pathToMerlin
+    merlinFlags::merlinFlags
+    dotMerlinPath::dotMerlinPath =>
+  Js.Unsafe.fun_call
+    createMerlinReaderFnOnce'
+    [|
+      Js.Unsafe.inject (Js.string pathToMerlin),
+      Js.Unsafe.inject (Js.string merlinFlags),
+      Js.Unsafe.inject (Js.string dotMerlinPath),
+      Js.Unsafe.inject fixedEnv
+    |];
+
+let startMerlinProcess path::path =>
+  switch startedMerlin.contents {
+  | Some readerFn => ()
+  | None =>
+    let atomReasonPathToMerlin = Atom.Config.get "atom-reason.pathToMerlin";
+    let atomReasonMerlinFlags = Atom.Config.get "atom-reason.merlinFlags";
+    let atomReasonMerlinLogFile = Atom.Config.get "atom-reason.merlinLogFile";
+    switch atomReasonMerlinLogFile {
+    | JsonString "" => ()
+    | JsonString s => Atom.Env.setEnvVar "MERLIN_LOG" s
+    | _ => ()
+    };
+    let readerFn =
+      createMerlinReaderFnOnce
+        pathToMerlin::(Atom.JsonValue.unsafeExtractString atomReasonPathToMerlin)
+        merlinFlags::(Atom.JsonValue.unsafeExtractString atomReasonMerlinFlags)
+        dotMerlinPath::(findNearestMerlinFile beginAtFilePath::path);
+    startedMerlin.contents = Some readerFn
+  };
+
+let readOneLine cmd::cmd resolve reject =>
+  switch startedMerlin.contents {
+  | None => raise Not_found
+  | Some readerFn =>
+    Js.Unsafe.fun_call
+      readerFn
+      [|
+        Js.Unsafe.inject cmd,
+        Js.Unsafe.inject (Js.wrap_callback resolve),
+        Js.Unsafe.inject (Js.wrap_callback reject)
+      |]
+  };
+
+/* contextify is important for avoiding different buffers calling the backing merlin at the same time. */
+/* https://github.com/the-lambda-church/merlin/blob/d98a08d318ca14d9c702bbd6eeadbb762d325ce7/doc/dev/PROTOCOL.md#contextual-commands */
+let contextify query::query path::path => Js.Unsafe.obj [|
+  ("query", Js.Unsafe.inject query),
+  ("context", Js.Unsafe.inject (Js.array [|Js.string "auto", Js.string path|]))
+|];
+
+let prepareCommand text::text path::path query::query resolve reject => {
+  startMerlinProcess path;
+  /* These two commands should be run before every main command. */
+  readOneLine
+    cmd::(
+      contextify
+        /* The protocol command tells Merlin which API version we want to use. (2 for us) */
+        query::(
+          Js.array [|
+            Js.Unsafe.inject (Js.string "protocol"),
+            Js.Unsafe.inject (Js.string "version"),
+            Js.Unsafe.inject (Js.number_of_float 2.)
+          |]
+        )
+        path::path
+    )
+    (
+      fun _ =>
+        readOneLine
+          cmd::(
+            contextify
+              /* The tell command allows us to synchronize our text with Merlin's internal buffer. */
+              query::(
+                Js.array [|Js.string "tell", Js.string "start", Js.string "end", Js.string text|]
+              )
+              path::path
+          )
+          (fun _ => readOneLine cmd::(contextify query::query path::path) resolve reject)
+          reject
+    )
+    reject
+};
+
+let positionToJsMerlinPosition (line, col) => Js.Unsafe.obj [|
+  /* lines (rows) are 1-based for merlin, not 0-based, like for Atom */
+  ("line", Js.Unsafe.inject (Js.number_of_float (float_of_int (line + 1)))),
+  ("col", Js.Unsafe.inject (Js.number_of_float (float_of_int col)))
+|];
+
+/* Actual merlin commands we'll use. */
+let getTypeHint path::path text::text position::position resolve reject =>
+  prepareCommand
+    text::text
+    path::path
+    query::(
+      Js.array [|
+        Js.Unsafe.inject (Js.string "type"),
+        Js.Unsafe.inject (Js.string "enclosing"),
+        Js.Unsafe.inject (Js.string "at"),
+        Js.Unsafe.inject (positionToJsMerlinPosition position)
+      |]
+    )
+    resolve
+    reject;
+
+let getAutoCompleteSuggestions
+    path::path
+    text::text
+    position::position
+    prefix::prefix
+    resolve
+    reject =>
+  prepareCommand
+    text::text
+    path::path
+    query::(
+      Js.array [|
+        Js.Unsafe.inject (Js.string "complete"),
+        Js.Unsafe.inject (Js.string "prefix"),
+        Js.Unsafe.inject (Js.string prefix),
+        Js.Unsafe.inject (Js.string "at"),
+        Js.Unsafe.inject (positionToJsMerlinPosition position),
+        Js.Unsafe.inject (Js.string "with"),
+        Js.Unsafe.inject (Js.string "doc")
+      |]
+    )
+    resolve
+    reject;
+
+let getDiagnostics path::path text::text resolve reject =>
+  prepareCommand
+    text::text
+    path::path
+    query::(Js.array [|Js.Unsafe.inject (Js.string "errors")|])
+    resolve
+    reject;
+
+let locate path::path text::text extension::extension position::position resolve reject =>
+  prepareCommand
+    text::text
+    path::path
+    query::(
+      Js.array [|
+        Js.Unsafe.inject (Js.string "locate"),
+        Js.Unsafe.inject (Js.string ""),
+        Js.Unsafe.inject (Js.string extension),
+        Js.Unsafe.inject (Js.string "at"),
+        Js.Unsafe.inject (positionToJsMerlinPosition position)
+      |]
+    )
+    resolve
+    reject;
+
+/* reject */
+let getOccurrences path::path text::text position::position resolve reject =>
+  prepareCommand
+    text::text
+    path::path
+    query::(
+      Js.array [|
+        Js.Unsafe.inject (Js.string "occurrences"),
+        Js.Unsafe.inject (Js.string "ident"),
+        Js.Unsafe.inject (Js.string "at"),
+        Js.Unsafe.inject (positionToJsMerlinPosition position)
+      |]
+    )
+    resolve
+    reject;
+
+let destruct
+    path::path
+    text::text
+    startPosition::startPosition
+    endPosition::endPosition
+    resolve
+    reject =>
+  prepareCommand
+    text::text
+    path::path
+    query::(
+      Js.array [|
+        Js.Unsafe.inject (Js.string "case"),
+        Js.Unsafe.inject (Js.string "analysis"),
+        Js.Unsafe.inject (Js.string "from"),
+        Js.Unsafe.inject (positionToJsMerlinPosition startPosition),
+        Js.Unsafe.inject (Js.string "to"),
+        Js.Unsafe.inject (positionToJsMerlinPosition endPosition)
+      |]
+    )
+    resolve
+    reject;
+
+let getOutline path::path text::text resolve reject =>
+  prepareCommand
+    text::text
+    path::path
+    query::(Js.array [|Js.Unsafe.inject (Js.string "outline")|])
+    resolve
+    reject;

samples/Reason/Syntax.re

@@ -0,0 +1,989 @@
+/* Copyright (c) 2015-present, Facebook, Inc. All rights reserved. */
+[@@@autoFormat let wrap = 80; let shift = 2];
+
+Modules.run ();
+
+Polymorphism.run ();
+
+Variants.run ();
+
+BasicStructures.run ();
+
+TestUtils.printSection "General Syntax";
+
+/* Won't work! */
+/* let matchingFunc a = match a with */
+/*   `Thingy x => (print_string "matched thingy x"); x */
+/*   | `Other x => (print_string "matched other x"); x;; */
+/*  */
+let matchingFunc a =>
+  switch a {
+  | `Thingy x =>
+    print_string "matched thingy x";
+    let zz = 10;
+    zz
+  | `Other x =>
+    print_string "matched other x";
+    x
+  };
+
+type firstTwoShouldBeGroupedInParens =
+  (int => int) => int => int;
+
+type allParensCanBeRemoved =
+  int => int => int => int;
+
+type firstTwoShouldBeGroupedAndFirstThree =
+  ((int => int) => int) => int;
+
+/* Same thing now but with type constructors instead of each int */
+type firstTwoShouldBeGroupedInParens =
+  (list int => list int) => list int => list int;
+
+type allParensCanBeRemoved =
+  list int => list int => list int => list int;
+
+type firstTwoShouldBeGroupedAndFirstThree =
+  ((list int => list int) => list int) =>
+  list int;
+
+type myRecordType = {
+  firstTwoShouldBeGroupedInParens:
+    (int => int) => int => int,
+  allParensCanBeRemoved:
+    int => int => int => int,
+  firstTwoShouldBeGroupedAndFirstThree:
+    ((int => int) => int) => int
+};
+
+type firstNamedArgShouldBeGroupedInParens =
+  first::(int => int) => second::int => int;
+
+type allParensCanBeRemoved =
+  first::int => second::int => third::int => int;
+
+type firstTwoShouldBeGroupedAndFirstThree =
+  first::((int => int) => int) => int;
+
+/* Same thing now, but with type constructors instead of int */
+type firstNamedArgShouldBeGroupedInParens =
+  first::(list int => list int) =>
+  second::list int =>
+  list int;
+
+type allParensCanBeRemoved =
+  first::list int =>
+  second::list int =>
+  third::list int =>
+  list int;
+
+type firstTwoShouldBeGroupedAndFirstThree =
+  first::((list int => list int) => list int) =>
+  list int;
+
+type firstNamedArgShouldBeGroupedInParens =
+  first::(int => int)? =>
+  second::int list? =>
+  int;
+
+/* The arrow necessitates parens around the next two args. The ? isn't what
+ * makes the parens necessary. */
+type firstNamedArgShouldBeGroupedInParensAndSecondNamedArg =
+  first::(int => int)? =>
+  second::(int => int)? =>
+  int;
+
+type allParensCanBeRemoved =
+  first::int? =>
+  second::int? =>
+  third::int? =>
+  int;
+
+type firstTwoShouldBeGroupedAndFirstThree =
+  first::((int => int) => int) => int;
+
+type noParens =
+  one::int => int => int => two::int => int;
+
+type noParensNeeded =
+  one::int => int => int => two::int => int;
+
+type firstNamedArgNeedsParens =
+  one::(int => int => int) => two::int => int;
+
+/* Now, let's try type aliasing */
+/* Unless wrapped in parens, types between arrows may not be aliased, may not
+ * themselves be arrows. */
+type parensRequiredAroundFirstArg =
+  (list int as 'a) => int as 'a;
+
+type parensRequiredAroundReturnType =
+  (list int as 'a) => (int as 'a);
+
+type parensRequiredAroundReturnType =
+  (list int as 'a) => (int as 'a) as 'b;
+
+type noParensNeededWhenInTuple =
+  (list int as 'a, list int as 'b) as 'entireThing;
+
+type myTypeDef 'a = list 'a;
+
+type instatiatedTypeDef = myTypeDef int => int;
+
+/* Test a type attribute for good measure */
+/* We should clean up all of the attribute tagging eventually, but for now,
+ * let's make it super ugly to get out of the way of all the formatting/parsing
+ * implementations (fewer conflicts during parsing, fewer edge cases during
+ * printing).
+ */
+type something = (
+  int,
+  int [@lookAtThisAttribute]
+);
+
+type longWrappingTypeDefinitionExample =
+  M_RK__G.Types.instance
+    (TGRecognizer.tGFields unit unit)
+    (TGRecognizer.tGMethods unit unit);
+
+type semiLongWrappingTypeDefinitionExample =
+  M_RK__Gesture.Types.instance
+    TGRecognizerFinal.tGFields
+    TGRecognizerFinal.tGMethods;
+
+type semiLongWrappingTypeWithConstraint =
+  M_RK__Gesture.Types.instance
+    'a
+    TGRecognizerFinal.tGFields
+    TGRecognizerFinal.tGMethods
+constraint 'a = (unit, unit);
+
+type onelineConstrain = 'a constraint 'a = int;
+
+/* This must be in trunk but not in this branch of OCaml */
+/* type withNestedRecords = MyConstructor {myField: int} */
+type colors =
+  | Red int
+  | Black int
+  | Green int;
+
+/* Another approach is to require declared variants to wrap any record */
+/* type myRecord = MyRecord {name: int}; */
+/* let myValue = MyRecord {name: int}; */
+/* This would force importing of the module */
+/* This would also lend itself naturally to pattern matching - and avoid having
+   to use `.` operator at all since you normally destructure. */
+type nameBlahType = {nameBlah: int};
+
+let myRecord = {nameBlah: 20};
+
+let myRecordName = myRecord.nameBlah;
+
+let {nameBlah}: nameBlahType = {nameBlah: 20};
+
+print_int nameBlah;
+
+let {nameBlah: aliasedToThisVar}: nameBlahType = {
+  nameBlah: 20
+};
+
+print_int aliasedToThisVar;
+
+let desiredFormattingForWrappedLambda:
+  int => int => int => nameBlahType =
+  /*
+
+   fun is
+   pre-   /firstarg\
+   fix   /-coupled--\
+    |-\ /-to-prefix--\       */
+  fun curriedArg anotherArg lastArg => {
+    nameBlah: 10
+  };
+
+type longerInt = int;
+
+let desiredFormattingForWrappedLambdaWrappedArrow:
+  longerInt =>
+  longerInt =>
+  longerInt =>
+  nameBlahType =
+  /*
+
+   fun is
+   pre-   /firstarg\
+   fix   /-coupled--\
+    |-\ /-to-prefix--\       */
+  fun curriedArg anotherArg lastArg => {
+    nameBlah: 10
+  };
+
+let desiredFormattingForWrappedLambdaReturnOnNewLine
+    /*
+
+     fun is
+     pre-   /firstarg\
+     fix   /-coupled--\
+      |-\ /-to-prefix--\       */
+    curriedArg
+    anotherArg
+    lastArg => {
+  nameBlah: 10
+};
+
+/*
+ let is
+ pre-
+ fix    /-function binding name---\
+ |-\   / is coupled to prefix      \   */
+let desiredFormattingForWrappedSugar
+    curriedArg
+    anotherArg
+    lastArg => {
+  nameBlah: 10
+};
+
+/*
+ let is
+ pre-
+ fix    /-function binding name---\
+ |-\   / is coupled to prefix      \   */
+let desiredFormattingForWrappedSugarReturnOnNewLine
+    curriedArg
+    anotherArg
+    lastArg => {
+  nameBlah: 10
+};
+
+/*
+   let  : type t1 t2. t1 * t2 list -> t1 = ...
+   let rec f : 't1 't2. 't1 * 't2 list -> 't1 =
+     fun (type t1) (type t2) -> (... : t1 * t2 list -> t1)
+ */
+type point = {x: int, y: int};
+
+type point3D = {x: int, y: int, z: int};
+
+let point2D = {x: 20, y: 30};
+
+let point3D: point3D = {
+  x: 10,
+  y: 11,
+  z: 80 /* Optional Comma */
+};
+
+let printPoint (p: point) => {
+  print_int p.x;
+  print_int p.y
+};
+
+let addPoints (p1: point, p2: point) => {
+  x: p1.x + p2.x,
+  y: p1.y + p2.y
+};
+
+let res1 = printPoint point2D;
+
+let res2 =
+  printPoint {x: point3D.x, y: point3D.y};
+
+/*
+    When () were used to indicate sequences, the parser used seq_expr not only
+    for grouping sequences, but also to form standard precedences.
+                          /------- sequence_expr ------\
+    let res3 = printPoint (addPoints (point2D, point3D));
+
+    Interestingly, it knew that tuples aren't sequences.
+
+    To move towards semi delimited, semi-terminated, braces-grouped sequences:
+    while allowing any non-sequence expression to be grouped on parens, we make
+    an explicit rule that allows one single non-semi ended expression to be
+    grouped in parens.
+
+    Actually: We will allow an arbitrary number of semi-delimited expressions to
+    be wrapped in parens, but the braces grouped semi delimited (sequence)
+    expressions must *also* be terminated with a semicolon.
+
+    This allows the parser to distinguish between
+
+        let x = {a};    /* Record {a:a} */
+        let x = {a;};   /* Single item sequence returning identifier {a} */
+ */
+let res3 =
+  printPoint (
+    addPoints (
+      point2D,
+      {x: point3D.x, y: point3D.y}
+    )
+  );
+
+type person = {age: int, name: string};
+
+type hiredPerson = {
+  age: string,
+  name: string,
+  dateHired: int
+};
+
+let o: person = {name: "bob", age: 10};
+
+/* Parens needed? Nope! */
+let o: person = {name: "bob", age: 10};
+
+let printPerson (p: person) => {
+  let q: person = p;
+  p.name ^ p.name
+};
+
+/* let dontParseMeBro x y:int = x = y;*/
+/* With this unification, anywhere eyou see `= fun` you can just ommit it */
+let blah a => a; /* Done */
+
+let blah a => a; /* Done (almost) */
+
+let blah a b => a; /* Done */
+
+let blah a b => a; /* Done (almost) */
+
+/* More than one consecutive pattern must have a single case */
+type blah = {blahBlah: int};
+
+let blah a {blahBlah} => a;
+
+let blah a {blahBlah} => a;
+
+let module TryToExportTwice = {
+  let myVal = "hello";
+};
+
+/*
+   Unifying top level module syntax with local module syntax is probably a bad
+   idea at the moment because it makes it more difficult to continue to support
+   `let .. in` bindings. We can distinguish local modules for `let..in` that
+   just happen to be defined at the top level (but not exported).
+
+     let MyModule = {let myVal = 20;} in
+     MyModule.x
+
+   Wait, where would this ever be valid, even if we continued to support
+   `let..in`?
+ */
+let onlyDoingThisTopLevelLetToBypassTopLevelSequence = {
+  let x = {
+    print_int 1;
+    print_int 20 /* Missing trailing SEMI */
+  };
+  let x = {
+    print_int 1;
+    print_int 20; /* Ensure missing middle SEMI reported well */
+    print_int 20
+  };
+  let x = {
+    print_int 1;
+    print_int 20;
+    10
+    /* Comment in final position */
+  }; /* Missing final SEMI */
+  x + x
+};
+
+type hasA = {a: int};
+
+let a = 10;
+
+let returnsASequenceExpressionWithASingleIdentifier
+    () => a;
+
+let thisReturnsA () => a;
+
+let thisReturnsAAsWell () => a;
+
+let recordVal: int = (thisReturnsARecord ()).a;
+
+Printf.printf
+  "\nproof that thisReturnsARecord: %n\n"
+  recordVal;
+
+Printf.printf
+  "\nproof that thisReturnsA: %n\n"
+  (thisReturnsA ());
+
+/* Pattern matching */
+let blah arg =>
+  switch arg {
+  /* Comment before Bar */
+  | /* Comment between bar/pattern */ Red _ => 1
+  /* Comment Before non-first bar */
+  | /* Comment betwen bar/pattern */ Black _ => 0
+  | Green _ => 0
+  };
+
+/* Any function that pattern matches a multicase match is interpretted as a
+ * single arg that is then matched on. Instead of the above `blah` example:*/
+let blah =
+  fun
+  | Red _ => 1
+  | Black _ => 0
+  | Green _ => 1;
+
+/* `fun a => a` is read as "a function that maps a to a". Then the */
+/* above example is read: "a function that 'either maps' Red to.. or maps .." */
+/* Thc00f564e first bar is read as "either maps" */
+/* Curried form is not supported:
+      let blah x | Red _ => 1 | Black _ => 0;
+      Theres no sugar rule for dropping => fun, only = fun
+   */
+/* let blahCurriedX x => fun  /* See, nothing says we can drop the => fun */ */
+/*   |(Red x | Black x | Green x) => 1     /* With some effort, we can ammend the sugar rule that would */ */
+/*   | Black x => 0                       /* Allow us to drop any => fun.. Just need to make pattern matching */ */
+/*   | Green x => 0;                      /* Support that */ */
+/*  */
+let blahCurriedX x =>
+  fun
+  | Red x
+  | Black x
+  | Green x =>
+    1 /* With some effort, we can ammend the sugar rule that would */
+  | Black x => 0 /* Allow us to drop any => fun.. Just need to make pattern matching */
+  | Green x => 0; /* Support that */
+
+let sameThingInLocal = {
+  let blahCurriedX x =>
+    fun
+    | Red x
+    | Black x
+    | Green x =>
+      1 /* With some effort, we can ammend the sugar rule that would */
+    | Black x => 0 /* Allow us to drop any => fun.. Just need to make pattern matching */
+    | Green x => 0; /* Support that */
+  blahCurriedX
+};
+
+/* This should be parsed/printed exactly as the previous */
+let blahCurriedX x =>
+  fun
+  | Red x
+  | Black x
+  | Green x => 1
+  | Black x => 0
+  | Green x => 0;
+
+/* Any time there are multiple match cases we require a leading BAR */
+let v = Red 10;
+
+let Black x | Red x | Green x = v; /* So this NON-function still parses */
+
+/* This doesn't parse, however (and it doesn't in OCaml either):
+     let | Black x | Red x | Green x = v;
+   */
+print_int x;
+
+/* Scoping: Let sequences. Familiar syntax for lexical ML style scope and
+   sequences. */
+let res = {
+  let a = "a starts out as";
+  {
+    print_string a;
+    let a = 20;
+    print_int a
+  };
+  print_string a
+};
+
+let res = {
+  let a = "first its a string";
+  let a = 20;
+  print_int a;
+  print_int a;
+  print_int a
+};
+
+let res = {
+  let a = "a is always a string";
+  print_string a;
+  let b = 30;
+  print_int b
+};
+
+/* let result = LyList.map (fun | [] => true | _ => false) []; */
+/* OTHERWISE: You cannot tell if a is the first match case falling through or
+ * a curried first arg */
+/* let blah = fun a | patt => 0 | anotherPatt => 1; */
+/* let blah a patt => 0 | anotherPatt => 1; */
+/*simple pattern  EQUALGREATER      expr */
+let blah a {blahBlah} => a;
+
+/*            match_case             */
+/*     pattern EQUALGREATER  expr */
+let blah =
+  fun
+  | Red _ => 1
+  | Black _ => 0
+  | Green _ => 0;
+
+/* Won't work! */
+/* let arrowFunc = fun a b => print_string "returning aplusb from arrow"; a + b;;  */
+let arrowFunc a b => {
+  print_string "returning aplusb from arrow";
+  a + b
+};
+
+let add a b => {
+  let extra = {
+    print_string "adding";
+    0
+  };
+  let anotherExtra = 0;
+  extra + a + b + anotherExtra
+};
+
+print_string (string_of_int (add 4 34));
+
+let dummy _ => 10;
+
+dummy res1;
+
+dummy res2;
+
+dummy res3;
+
+/* Some edge cases */
+let myFun firstArg (Red x | Black x | Green x) =>
+  firstArg + x;
+
+let matchesWithWhen a =>
+  switch a {
+  | Red x when 1 > 0 => 10
+  | Red _ => 10
+  | Black x => 10
+  | Green x => 10
+  };
+
+let matchesWithWhen =
+  fun
+  | Red x when 1 > 0 => 10
+  | Red _ => 10
+  | Black x => 10
+  | Green x => 10;
+
+let matchesOne (`Red x) => 10;
+
+/*
+ Typical OCaml would make you *wrap the functions in parens*! This is because it
+ can't tell if a semicolon is a sequence operator. Even if we had records use
+ commas to separate fields,
+ */
+type adders = {
+  addTwoNumbers: int => int => int,
+  addThreeNumbers: int => int => int => int,
+  addThreeNumbersTupled: (int, int, int) => int
+};
+
+let myRecordWithFunctions = {
+  addTwoNumbers: fun a b => a + b,
+  addThreeNumbers: fun a b c => a + b + c,
+  addThreeNumbersTupled: fun (a, b, c) =>
+    a + b + c
+};
+
+let result =
+  myRecordWithFunctions.addThreeNumbers 10 20 30;
+
+let result =
+  myRecordWithFunctions.addThreeNumbersTupled (
+    10,
+    20,
+    30
+  );
+
+let lookTuplesRequireParens = (1, 2);
+
+/* let thisDoesntParse = 1, 2;  */
+let tupleInsideAParenSequence = {
+  print_string "look, a tuple inside a sequence";
+  let x = 10;
+  (x, x)
+};
+
+let tupleInsideALetSequence = {
+  print_string "look, a tuple inside a sequence";
+  let x = 10;
+  (x, x)
+};
+
+/* We *require* that function return types be wrapped in
+   parenthesis. In this example, there's no ambiguity */
+let makeIncrementer (delta: int) :(int => int) =>
+  fun a => a + delta;
+
+/* We could even force that consistency with let bindings - it's allowed
+      currently but not forced.
+   */
+let myAnnotatedValBinding: int = 10;
+
+/* Class functions (constructors) and methods are unified in the same way */
+class classWithNoArg = {
+  method x = 0;
+  method y = 0;
+};
+
+/* This parses but doesn't type check
+     class myClass init => object
+       method x => init
+       method y => init
+     end;
+   */
+let myFunc (a: int) (b: int) :(int, int) => (
+  a,
+  b
+);
+
+let myFunc (a: int) (b: int) :list int => [1];
+
+let myFunc (a: int) (b: int) :point => {
+  x: a,
+  y: b
+};
+
+let myFunc (a: int, b: int) :point => {
+  x: a,
+  y: b
+};
+
+type myThing = (int, int);
+
+type stillARecord = {name: string, age: int};
+
+/* Rebase latest OCaml to get the following: And fixup
+   `generalized_constructor_arguments` according to master. */
+/* type ('a, 'b) myOtherThing = Leaf {first:'a, second: 'b} | Null; */
+type branch 'a 'b = {first: 'a, second: 'b};
+
+type myOtherThing 'a 'b =
+  | Leaf (branch 'a 'b)
+  | Null;
+
+type yourThing = myOtherThing int int;
+
+/* Conveniently - this parses exactly how you would intend! No *need* to wrap
+   in an extra [], but it doesn't hurt */
+/* FIXME type lookAtThesePolyVariants = list [`Red] ; */
+/* FIXME type bracketsGroupMultipleParamsAndPrecedence = list (list (list [`Red])); */
+/* FIXME type youCanWrapExtraIfYouWant = (list [`Red]); */
+/* FIXME type hereAreMultiplePolyVariants = list [`Red | `Black]; */
+/* FIXME type hereAreMultiplePolyVariantsWithOptionalWrapping = list ([`Red | `Black]); */
+/*
+   /* Proposal: ES6 style lambdas: */
+
+   /* Currying */
+   let lookES6Style = (`Red x) (`Black y) => { };
+   let lookES6Style (`Red x) (`Black y) => { };
+
+   /* Matching the single argument */
+   let lookES6Style = oneArg => match oneArg with
+     | `Red x => x
+     | `Black x => x;
+
+   /* The "trick" to currying that we already have is basically the same - we just
+    * have to reword it a bit:
+    * From:
+    * "Any time you see [let x = fun ...] just replace it with [let x ...]"
+    * To:
+    * "Any time you see [let x = ... => ] just replace it with [let x ... => ]"
+    */
+   let lookES6Style oneArg => match oneArg with
+     | `Red x => x
+     | `Black x => x;
+
+ */
+
+/** Current OCaml Named Arguments. Any aliasing is more than just aliasing!
+    OCaml allows full on pattern matching of named args. */
+/*
+ A: let named              ~a    ~b                = aa + bb in
+ B: let namedAlias         ~a:aa ~b:bb             = aa + bb in
+ C: let namedAnnot         ~(a:int) ~(b:int)       = a + b in
+ D: let namedAliasAnnot    ~a:(aa:int) ~b:(bb:int) = aa + bb in
+ E: let optional           ?a    ?b                              = 10 in
+ F: let optionalAlias      ?a:aa ?b:bb                           = 10 in
+ G: let optionalAnnot      ?(a:int option) ?(b:int option)       = 10 in
+ H: let optionalAliasAnnot ?a:(aa:int option) ?b:(bb:int option) = 10 in
+ /*
+ Look! When a default is provided, annotation causes inferred type of argument
+ to not be "option" since it's automatically destructured (because we know it
+ will always be available one way or another.)
+ */
+ I: let defOptional           ?(a=10)    ?(b=10)                 = 10 in
+ J: let defOptionalAlias      ?a:(aa=10) ?b:(bb=10)              = 10 in
+ K: let defOptionalAnnot      ?(a:int=10) ?(b:int=10)            = 10 in
+                             \       \
+                              \label_let_pattern opt_default: no longer needed in SugarML
+
+ L: let defOptionalAliasAnnot ?a:(aa:int=10) ?b:(bb:int=10)      = 10 in
+                               \        \
+                                \let_pattern: still a useful syntactic building block in SugarML
+ */
+
+/**
+ * In Reason, the syntax for named args uses double semicolon, since
+ * the syntax for lists uses ES6 style [], freeing up the ::.
+ */
+let a = 10;
+
+let b = 20;
+
+/*A*/
+let named a::a b::b => a + b;
+
+type named = a::int => b::int => int;
+
+/*B*/
+let namedAlias a::aa b::bb => aa + bb;
+
+let namedAlias a::aa b::bb => aa + bb;
+
+type namedAlias = a::int => b::int => int;
+
+/*C*/
+let namedAnnot a::(a: int) b::(b: int) => 20;
+
+/*D*/
+let namedAliasAnnot a::(aa: int) b::(bb: int) => 20;
+
+/*E*/
+let myOptional a::a=? b::b=? () => 10;
+
+type named = a::int? => b::int? => unit => int;
+
+/*F*/
+let optionalAlias a::aa=? b::bb=? () => 10;
+
+/*G*/
+let optionalAnnot a::(a: int)=? b::(b: int)=? () => 10;
+
+/*H*/
+let optionalAliasAnnot
+    a::(aa: int)=?
+    b::(bb: int)=?
+    () => 10;
+
+/*I: */
+let defOptional a::a=10 b::b=10 () => 10;
+
+type named = a::int? => b::int? => unit => int;
+
+/*J*/
+let defOptionalAlias a::aa=10 b::bb=10 () => 10;
+
+/*K*/
+let defOptionalAnnot
+    a::(a: int)=10
+    b::(b: int)=10
+    () => 10;
+
+/*L*/
+let defOptionalAliasAnnot
+    a::(aa: int)=10
+    b::(bb: int)=10
+    () => 10;
+
+/*M: Invoking them - Punned */
+let resNotAnnotated = named a::a b::b;
+
+/*N:*/
+let resAnnotated: int = named a::a b::b;
+
+/*O: Invoking them */
+let resNotAnnotated = named a::a b::b;
+
+/*P: Invoking them */
+let resAnnotated: int = named a::a b::b;
+
+/*Q: Here's why "punning" doesn't work!  */
+/* Is b:: punned with a final non-named arg, or is b:: supplied b as one named arg? */
+let b = 20;
+
+let resAnnotated = named a::a b::b;
+
+/*R: Proof that there are no ambiguities with return values being annotated */
+let resAnnotated: ty = named a::a b;
+
+/*S: Explicitly passed optionals are a nice way to say "use the default value"*/
+let explictlyPassed =
+  myOptional a::?None b::?None;
+
+/*T: Annotating the return value of the entire function call */
+let explictlyPassedAnnotated: int =
+  myOptional a::?None b::?None;
+
+/*U: Explicitly passing optional with identifier expression */
+let a = None;
+
+let explictlyPassed = myOptional a::?a b::?None;
+
+let explictlyPassedAnnotated: int =
+  myOptional a::?a b::?None;
+
+let nestedLet = {
+  let _ = 1;
+  ()
+};
+
+let nestedLet = {
+  let _ = 1;
+  ()
+};
+
+let nestedLet = {
+  let _ = 1;
+  ()
+};
+
+let nestedLet = {
+  let _ = 1;
+  2
+};
+
+/*
+ * Showing many combinations of type annotations and named arguments.
+ */
+type typeWithNestedNamedArgs =
+  outerOne::(
+    innerOne::int => innerTwo::int => int
+  ) =>
+  outerTwo::int =>
+  int;
+
+type typeWithNestedOptionalNamedArgs =
+  outerOne::
+    (innerOne::int => innerTwo::int => int)? =>
+  outerTwo::int? =>
+  int;
+
+type typeWithNestedOptionalNamedArgs =
+  outerOne::list string? => outerTwo::int? => int;
+
+let x =
+  callSomeFunction
+    withArg::10 andOtherArg::wrappedArg;
+
+let res = {
+  (constraintedSequenceItem: string);
+  (dontKnowWheYoudWantToActuallyDoThis: string)
+};
+
+let res = {
+  (
+    butTheyWillBePrintedWithAppropriateSpacing: string
+  );
+  (soAsToInstillBestDevelopmentPractices: string)
+};
+
+let x = [
+  (eachItemInListCanBeAnnotated: int),
+  (typeConstraints: float),
+  (
+    tupleConstraints: int,
+    andNotFunctionInvocations: int
+  )
+];
+
+let x = [
+  (butWeWillPrint: int),
+  (themAsSpaceSeparated: float),
+  (toInfluenceYour: int, developmentHabbits: int)
+];
+
+let newRecord = {
+  ...(annotatedSpreadRecord: someRec),
+  x: y
+};
+
+let newRecord = {
+  ...(annotatedSpreadRecord: someRec),
+  blah: 0,
+  foo: 1
+};
+
+let newRecord = {
+  ...(
+    youCanEvenCallMethodsHereAndAnnotate them: someRec
+  ),
+  blah: 0,
+  foo: 1
+};
+
+let newRecord = {
+  ...(
+    youCanEvenCallMethodsHereAndAnnotate
+      them named::10: someRec
+  ),
+  blah: 0,
+  foo: 1
+};
+
+let something: thing blah = aTypeAnnotation;
+
+let something: thing blah = thisIsANamedArg;
+
+let something: thing blah = aTypeAnnotation;
+
+let something: blah = thisIsANamedArg thing;
+
+let something: blah = typeAnnotation thing;
+
+let newRecord = {
+  ...(
+    heresAFunctionWithNamedArgs argOne::i: annotatedResult
+  ),
+  soAsToInstill: 0,
+  developmentHabbits: 1
+};
+
+[@@@thisIsAThing];
+
+let x = 10;
+
+/* Ensure that the parenthesis are preserved here because they are
+ * important:
+ */
+let something =
+  fun
+  | None => (
+      fun
+      | [] => "emptyList"
+      | [_, ..._] => "nonEmptyList"
+    )
+  | Some _ => (
+      fun
+      | [] => "emptyList"
+      | [_, ..._] => "nonEmptyList"
+    );
+
+/*  A | B = X; */
+let A | B = X;
+
+/*  A | (B | C) = X; */
+let A | (B | C) = X;
+
+/* (A | B) | (C | D) = X; */
+let A | B | (C | D) = X;
+
+/*  A | B | (C | D) = X; */
+let A | B | (C | D) = X;
+
+/* (A | B) | C = X; */
+let A | B | C = X;
+
+/*  A | B | C = X; */
+let A | B | C = X;
+
+
+/** External function declaration
+ *
+ */
+external f : int => int = "foo";
+
+let x = {contents: 0};
+
+let unitVal = x.contents = 210;

samples/Regular Expression/modeline-emacs.regexp

@@ -0,0 +1,19 @@
+-\*-
+(?:
+	\s*
+	(?= [^:;\s]+ \s* -\*-)
+	|
+	(?:
+		.*?[;\s]
+		|
+		(?<=-\*-)
+	)
+	mode\s*:\s*
+)
+([^:;\s]+)
+
+(?=
+	[\s;] | (?<![-*]) -\*-
+)
+.*?
+-\*-

samples/Regular Expression/modeline-vim.regexp

@@ -0,0 +1,27 @@
+(?:
+	(?:\s|^)
+	vi
+	(?:m[<=>]?\d+|m)?
+	|
+	[\t\x20]
+	ex
+)
+(?=
+	: (?=\s* set? \s [^\n:]+ :) |
+	: (?!\s* set? \s)
+)
+
+(?:
+	(?:\s|\s*:\s*)
+	\w*
+	(?:
+		\s*=
+		(?:[^\n\\\s]|\\.)*
+	)?
+)*
+
+[\s:]
+(?:filetype|ft|syntax)
+\s*=
+(MODE_NAME_HERE)
+(?=\s|:|$)

samples/Regular Expression/ordinal.regex

@@ -0,0 +1 @@
+\b(\d*1[1-3]th|\d*0th|(?:(?!11st)\d)*1st|\d*2nd|(?:(?!13rd)\d*)3rd|\d*[4-9]th)\b

samples/Regular Expression/url.regex

@@ -0,0 +1 @@
+/^([^\/#\?]*:?\/\/)?(\/?(?:[^\/#\?]+\/)*)?([^\/#\?]+)?(?:\/(?=$))?(\?[^#]*)?(#.*)?$/

samples/Text/filenames/COPYING.regex

@@ -0,0 +1,54 @@
+$OpenBSD: COPYRIGHT,v 1.3 2003/06/02 20:18:36 millert Exp $
+
+Copyright 1992, 1993, 1994 Henry Spencer.  All rights reserved.
+This software is not subject to any license of the American Telephone
+and Telegraph Company or of the Regents of the University of California.
+
+Permission is granted to anyone to use this software for any purpose on
+any computer system, and to alter it and redistribute it, subject
+to the following restrictions:
+
+1. The author is not responsible for the consequences of use of this
+   software, no matter how awful, even if they arise from flaws in it.
+
+2. The origin of this software must not be misrepresented, either by
+   explicit claim or by omission.  Since few users ever read sources,
+   credits must appear in the documentation.
+
+3. Altered versions must be plainly marked as such, and must not be
+   misrepresented as being the original software.  Since few users
+   ever read sources, credits must appear in the documentation.
+
+4. This notice may not be removed or altered.
+
+=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+/*-
+ * Copyright (c) 1994
+ *	The Regents of the University of California.  All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of the University nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ *	@(#)COPYRIGHT	8.1 (Berkeley) 3/16/94
+ */

samples/Text/filenames/LICENSE.mysql

@@ -0,0 +1,339 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
+ 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users.  This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it.  (Some other Free Software Foundation software is covered by
+the GNU Lesser General Public License instead.)  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have.  You must make sure that they, too, receive or can get the
+source code.  And you must show them these terms so they know their
+rights.
+
+  We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+  Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software.  If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+  Finally, any free program is threatened constantly by software
+patents.  We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary.  To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                    GNU GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License.  The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language.  (Hereinafter, translation is included without limitation in
+the term "modification".)  Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+  1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+  2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) You must cause the modified files to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    b) You must cause any work that you distribute or publish, that in
+    whole or in part contains or is derived from the Program or any
+    part thereof, to be licensed as a whole at no charge to all third
+    parties under the terms of this License.
+
+    c) If the modified program normally reads commands interactively
+    when run, you must cause it, when started running for such
+    interactive use in the most ordinary way, to print or display an
+    announcement including an appropriate copyright notice and a
+    notice that there is no warranty (or else, saying that you provide
+    a warranty) and that users may redistribute the program under
+    these conditions, and telling the user how to view a copy of this
+    License.  (Exception: if the Program itself is interactive but
+    does not normally print such an announcement, your work based on
+    the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+    a) Accompany it with the complete corresponding machine-readable
+    source code, which must be distributed under the terms of Sections
+    1 and 2 above on a medium customarily used for software interchange; or,
+
+    b) Accompany it with a written offer, valid for at least three
+    years, to give any third party, for a charge no more than your
+    cost of physically performing source distribution, a complete
+    machine-readable copy of the corresponding source code, to be
+    distributed under the terms of Sections 1 and 2 above on a medium
+    customarily used for software interchange; or,
+
+    c) Accompany it with the information you received as to the offer
+    to distribute corresponding source code.  (This alternative is
+    allowed only for noncommercial distribution and only if you
+    received the program in object code or executable form with such
+    an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it.  For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable.  However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License.  Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+  5. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Program or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+  6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+  7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded.  In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+  9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation.  If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+  10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission.  For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this.  Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+                            NO WARRANTY
+
+  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License along
+    with this program; if not, write to the Free Software Foundation, Inc.,
+    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+    Gnomovision version 69, Copyright (C) year name of author
+    Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+  `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+  <signature of Ty Coon>, 1 April 1989
+  Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs.  If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.

samples/Text/filenames/README.mysql

@@ -0,0 +1,24 @@
+README for users interested in using MySQL as a triplestore backend
+===================================================================
+
+The KiWi Triple Store used by Apache Marmotta supports different database
+backends, including H2, PostgreSQL and MySQL. However, for legal reasons,
+we are not allowed to distribute the MySQL connector library together with
+the Apache Marmotta source code or binaries, as it is licensed under GPL
+license.
+
+Nonetheless, it is possible to use MySQL by downloading and installing the
+connector manually:
+    1.  download and unpack the MySQL Connector/J from
+        http://dev.mysql.com/downloads/connector/j/
+    2.  copy the mysql-connector-java-5.x.x.jar file to
+        a. the library directory of the application server
+           (e.g. $TOMCAT_HOME/lib)
+        -- OR --
+        b. the library directory of the Apache Marmotta Web application
+           (e.g. $TOMCAT_HOME/webapps/marmotta/WEB-INF/lib)
+    3.  restart the application server
+
+Apache Marmotta will then automatically be able to use the MySQL connector
+to connect to a MySQL database. Please note that Marmotta requires at least
+MySQL 5.x, because it makes use of nested queries and foreign keys.

samples/YAML/database.yml.mysql

@@ -0,0 +1,42 @@
+#
+# PRODUCTION
+#
+production:
+  adapter: mysql2
+  encoding: utf8mb4
+  collation: utf8mb4_general_ci
+  reconnect: false
+  database: gitlabhq_production
+  pool: 10
+  username: git
+  password: "secure password"
+  # host: localhost
+  # socket: /tmp/mysql.sock
+
+#
+# Development specific
+#
+development:
+  adapter: mysql2
+  encoding: utf8mb4
+  collation: utf8mb4_general_ci
+  reconnect: false
+  database: gitlabhq_development
+  pool: 5
+  username: root
+  password: "secure password"
+  # socket: /tmp/mysql.sock
+
+# Warning: The database defined as "test" will be erased and
+# re-generated from your development database when you run "rake".
+# Do not set this db to the same as development or production.
+test: &test
+  adapter: mysql2
+  encoding: utf8mb4
+  collation: utf8mb4_general_ci
+  reconnect: false
+  database: gitlabhq_test
+  pool: 5
+  username: root
+  password:
+  # socket: /tmp/mysql.sock

script/add-grammar

@@ -84,6 +84,7 @@ if repo_old
   log "Deregistering: #{repo_old}"
   `git submodule deinit #{repo_old}`
   `git rm -rf #{repo_old}`
+  `script/convert-grammars`
 end
 
 log "Registering new submodule: #{repo_new}"
@@ -92,7 +93,11 @@ exit 1 if $?.exitstatus > 0
 `script/convert-grammars --add #{repo_new}`
 
 log "Confirming license"
-`script/licensed --module "#{repo_new}"`
+if repo_old
+  `script/licensed`
+else
+  `script/licensed --module "#{repo_new}"`
+end
 
 log "Updating grammar documentation in vendor/REAEDME.md"
 `bundle exec rake samples`

script/convert-grammars

@@ -174,6 +174,7 @@ end
 def load_grammars(tmp_dir, source, all_scopes)
   is_url = source.start_with?("http:", "https:")
   return [] if is_url && !$options[:remote]
+  return [] if !is_url && !File.exist?(source)
 
   p = if !is_url
         if File.directory?(source)

script/fast-submodule-update

@@ -51,7 +51,7 @@ SUBMODULES.partition { |submodule| SLOW_SUBMODULES.include?(submodule) }.flatten
   submodules.push(submodule)
 end
 
-8.times do
+(ARGV.first || 8).to_i.times do
   Thread.new { run_thread(submodules, results) }
 end
 

script/list-grammars

@@ -71,7 +71,7 @@ class GrammarList
       when "https://bitbucket.org/Clams/sublimesystemverilog/get/default.tar.gz"
         short_url = "bitbucket:Clams/sublimesystemverilog"
         long_url  = "https://bitbucket.org/Clams/sublimesystemverilog"
-      when "http://svn.edgewall.org/repos/genshi/contrib/textmate/Genshi.tmbundle/Syntaxes/Markup%20Template%20%28XML%29.tmLanguage"
+      when "https://svn.edgewall.org/repos/genshi/contrib/textmate/Genshi.tmbundle/Syntaxes/Markup%20Template%20%28XML%29.tmLanguage"
         short_url = "genshi.edgewall.org/query"
         long_url  = "https://genshi.edgewall.org/query"
       when "vendor/grammars/oz-tmbundle/Syntaxes/Oz.tmLanguage"

test/fixtures/Data/yarn.lock

@@ -0,0 +1,9 @@
+# THIS IS AN AUTOGENERATED FILE. DO NOT EDIT THIS FILE DIRECTLY.
+# yarn lockfile v1
+abab@^1.0.0:
+  version "1.0.3"
+  resolved "https://registry.yarnpkg.com/abab/-/abab-1.0.3.tgz#b81de5f7274ec4e756d797cd834f303642724e5d"
+
+abbrev@1, abbrev@1.0.x:
+  version "1.0.9"
+  resolved "https://registry.yarnpkg.com/abbrev/-/abbrev-1.0.9.tgz#91b4792588a7738c25f35dd6f63752a2f8776135"

test/test_blob.rb

@@ -187,6 +187,9 @@ class TestBlob < Minitest::Test
     assert sample_blob_memory("JavaScript/intro.js").generated?
     assert sample_blob_memory("JavaScript/classes.js").generated?
 
+    assert sample_blob_memory("JavaScript/ccalc-lex.js").generated?
+    assert sample_blob_memory("JavaScript/ccalc-parse.js").generated?
+
     # Protocol Buffer generated code
     assert sample_blob_memory("C++/protocol-buffer.pb.h").generated?
     assert sample_blob_memory("C++/protocol-buffer.pb.cc").generated?
@@ -194,6 +197,7 @@ class TestBlob < Minitest::Test
     assert sample_blob_memory("Python/protocol_buffer_pb2.py").generated?
     assert sample_blob_memory("Go/api.pb.go").generated?
     assert sample_blob_memory("Go/embedded.go").generated?
+    assert sample_blob_memory("JavaScript/proto.js").generated?
 
     # Apache Thrift generated code
     assert sample_blob_memory("Python/gen-py-linguist-thrift.py").generated?

test/test_classifier.rb

@@ -53,4 +53,8 @@ class TestClassifier < Minitest::Test
       assert_equal language.name, results.first[0], "#{sample[:path]}\n#{results.inspect}"
     end
   end
+
+  def test_classify_empty_languages
+    assert_equal [], Classifier.classify(Samples.cache, fixture("Ruby/foo.rb"), [])
+  end
 end

test/test_generated.rb

@@ -79,6 +79,9 @@ class TestGenerated < Minitest::Test
     generated_fixture_loading_data("Data/sourcemap.v3.map")
     generated_fixture_loading_data("Data/sourcemap.v1.map")
 
+    # Yarn locfile
+    generated_fixture_loading_data("Data/yarn.lock")
+
     # Specflow
     generated_fixture_without_loading_data("Features/BindingCulture.feature.cs")
 
@@ -87,5 +90,8 @@ class TestGenerated < Minitest::Test
 
     # GrammarKit
     generated_sample_loading_data("Java/GrammarKit.java")
+
+    # roxygen2
+    generated_sample_loading_data("R/import.Rd")
   end
 end

test/test_grammars.rb

@@ -21,7 +21,7 @@ class TestGrammars < Minitest::Test
     "b5432a1e1055de7eeede2dddf91e009480651fd6", # jasmin-sublime
     "74143c4d2a5649eb179105afcb37f466558c22ce", # language-clojure
     "760471435f5ab0b9dc99a628203cd8f9156d28ce", # language-coffee-script
-    "330e6d465e26bdd232aafcd3f5dba6a1d098a20e", # language-csharp
+    "94fbd554ec1837fb7c508fd7425326639c3f4103", # language-csharp
     "70fb557a431891c2d634c33fa7367feab5066fd6", # language-javascript
     "e0528c23cd967f999e058f1408ccb5b7237daaba", # language-python
     "8653305b358375d0fced85dc24793b99919b11ef", # language-shellscript
@@ -36,11 +36,13 @@ class TestGrammars < Minitest::Test
     "c78ec142ac3126cf639cfd67bd646ed8226d8b74", # atom-language-purescript
     "341d7f66806fc41d081133d6e51ade856352e056", # FreeMarker.tmbundle
     "15a394f6bc43400946570b299aee8ae264a1e3ff", # language-renpy
-    "c9118c370411f2f049c746c0fd096554e877aea2", # perl6fe
     "8ccf886749c32fb7e65d4d1316a7ed0479c93dc9", # language-less
     "2f03492b52d7dd83b4e7472f01b87c6121e5b1a4", # monkey
     "241e5ddbb4423d792216783e9f668bd670b026e4", # ant.tmbundle
-    "bdab9fdc21e6790b479ccb5945b78bc0f6ce2493"  # language-blade
+    "bdab9fdc21e6790b479ccb5945b78bc0f6ce2493", # language-blade
+    "81711c69aa40135de7266c88b2f6ab28dbc1d81e", # atom-language-perl6
+    "808e27f5e44167113198d277f47926c5d482eac8", # atom-language-rust
+    "304be6184f7f344d44a1d13bddf511019624fd22", # language-css
   ].freeze
 
   # List of allowed SPDX license names

test/test_language.rb

@@ -460,4 +460,8 @@ class TestLanguage < Minitest::Test
       assert !language.color, "Unused colour assigned to #{language.name}"
     end
   end
+
+  def test_non_crash_on_comma
+    assert_nil Language[',']
+  end
 end

vendor/README.md

@@ -76,8 +76,7 @@ This is a list of grammars that Linguist selects to provide syntax highlighting
 - **Csound:** [nwhetsell/language-csound](https://github.com/nwhetsell/language-csound)
 - **Csound Document:** [nwhetsell/language-csound](https://github.com/nwhetsell/language-csound)
 - **Csound Score:** [nwhetsell/language-csound](https://github.com/nwhetsell/language-csound)
-- **CSS:** [textmate/css.tmbundle](https://github.com/textmate/css.tmbundle)
+- **CSS:** [atom/language-css](https://github.com/atom/language-css)
-- **Cucumber:** [cucumber/cucumber-tmbundle](https://github.com/cucumber/cucumber-tmbundle)
 - **Cuda:** [harrism/sublimetext-cuda-cpp](https://github.com/harrism/sublimetext-cuda-cpp)
 - **Cycript:** [atom/language-javascript](https://github.com/atom/language-javascript)
 - **Cython:** [textmate/cython.tmbundle](https://github.com/textmate/cython.tmbundle)
@@ -109,13 +108,12 @@ This is a list of grammars that Linguist selects to provide syntax highlighting
 - **Fancy:** [fancy-lang/fancy-tmbundle](https://github.com/fancy-lang/fancy-tmbundle)
 - **fish:** [l15n/fish-tmbundle](https://github.com/l15n/fish-tmbundle)
 - **Forth:** [textmate/forth.tmbundle](https://github.com/textmate/forth.tmbundle)
-- **FORTRAN:** [textmate/fortran.tmbundle](https://github.com/textmate/fortran.tmbundle)
+- **Fortran:** [textmate/fortran.tmbundle](https://github.com/textmate/fortran.tmbundle)
 - **FreeMarker:** [freemarker/FreeMarker.tmbundle](https://github.com/freemarker/FreeMarker.tmbundle)
 - **Frege:** [atom-haskell/language-haskell](https://github.com/atom-haskell/language-haskell)
 - **G-code:** [robotmaster/sublime-text-syntax-highlighting](https://github.com/robotmaster/sublime-text-syntax-highlighting)
 - **Game Maker Language:** [textmate/c.tmbundle](https://github.com/textmate/c.tmbundle)
 - **GAP:** [dhowden/gap-tmbundle](https://github.com/dhowden/gap-tmbundle)
-- **GAS:** [Nessphoro/sublimeassembly](https://github.com/Nessphoro/sublimeassembly)
 - **GCC Machine Description:** [textmate/lisp.tmbundle](https://github.com/textmate/lisp.tmbundle)
 - **GDB:** [quarnster/SublimeGDB](https://github.com/quarnster/SublimeGDB)
 - **GDScript:** [beefsack/GDScript-sublime](https://github.com/beefsack/GDScript-sublime)
@@ -123,6 +121,7 @@ This is a list of grammars that Linguist selects to provide syntax highlighting
 - **Gentoo Ebuild:** [atom/language-shellscript](https://github.com/atom/language-shellscript)
 - **Gentoo Eclass:** [atom/language-shellscript](https://github.com/atom/language-shellscript)
 - **Gettext Catalog:** [textmate/gettext.tmbundle](https://github.com/textmate/gettext.tmbundle)
+- **Gherkin:** [cucumber/cucumber-tmbundle](https://github.com/cucumber/cucumber-tmbundle)
 - **GLSL:** [euler0/sublime-glsl](https://github.com/euler0/sublime-glsl)
 - **Glyph:** [textmate/tcl.tmbundle](https://github.com/textmate/tcl.tmbundle)
 - **GN:** [devoncarew/language-gn](https://github.com/devoncarew/language-gn)
@@ -135,7 +134,6 @@ This is a list of grammars that Linguist selects to provide syntax highlighting
 - **Grammatical Framework:** [atom-haskell/language-haskell](https://github.com/atom-haskell/language-haskell)
 - **GraphQL:** [rmosolgo/language-graphql](https://github.com/rmosolgo/language-graphql)
 - **Graphviz (DOT):** [textmate/graphviz.tmbundle](https://github.com/textmate/graphviz.tmbundle)
-- **Groff:** [Alhadis/language-roff](https://github.com/Alhadis/language-roff)
 - **Groovy:** [textmate/groovy.tmbundle](https://github.com/textmate/groovy.tmbundle)
 - **Groovy Server Pages:** [textmate/java.tmbundle](https://github.com/textmate/java.tmbundle)
 - **Hack:** [textmate/php.tmbundle](https://github.com/textmate/php.tmbundle)
@@ -152,7 +150,6 @@ This is a list of grammars that Linguist selects to provide syntax highlighting
 - **HTML+ERB:** [aroben/ruby.tmbundle](https://github.com/aroben/ruby.tmbundle)
 - **HTML+PHP:** [textmate/php.tmbundle](https://github.com/textmate/php.tmbundle)
 - **HTTP:** [httpspec/sublime-highlighting](https://github.com/httpspec/sublime-highlighting)
-- **Hy:** [rwtolbert/language-hy](https://github.com/rwtolbert/language-hy)
 - **IDL:** [mgalloy/idl.tmbundle](https://github.com/mgalloy/idl.tmbundle)
 - **Idris:** [idris-hackers/idris-sublime](https://github.com/idris-hackers/idris-sublime)
 - **Inform 7:** [erkyrath/language-inform7](https://github.com/erkyrath/language-inform7)
@@ -162,7 +159,6 @@ This is a list of grammars that Linguist selects to provide syntax highlighting
 - **Isabelle:** [lsf37/Isabelle.tmbundle](https://github.com/lsf37/Isabelle.tmbundle)
 - **Isabelle ROOT:** [lsf37/Isabelle.tmbundle](https://github.com/lsf37/Isabelle.tmbundle)
 - **J:** [bcj/JSyntax](https://github.com/bcj/JSyntax)
-- **Jade:** [davidrios/jade-tmbundle](https://github.com/davidrios/jade-tmbundle)
 - **Jasmin:** [atmarksharp/jasmin-sublime](https://github.com/atmarksharp/jasmin-sublime)
 - **Java:** [textmate/java.tmbundle](https://github.com/textmate/java.tmbundle)
 - **Java Server Pages:** [textmate/java.tmbundle](https://github.com/textmate/java.tmbundle)
@@ -224,7 +220,7 @@ This is a list of grammars that Linguist selects to provide syntax highlighting
 - **NetLogo:** [textmate/lisp.tmbundle](https://github.com/textmate/lisp.tmbundle)
 - **NewLisp:** [textmate/lisp.tmbundle](https://github.com/textmate/lisp.tmbundle)
 - **Nginx:** [brandonwamboldt/sublime-nginx](https://github.com/brandonwamboldt/sublime-nginx)
-- **Nimrod:** [Varriount/NimLime](https://github.com/Varriount/NimLime)
+- **Nim:** [Varriount/NimLime](https://github.com/Varriount/NimLime)
 - **Ninja:** [khyo/language-ninja](https://github.com/khyo/language-ninja)
 - **Nit:** [R4PaSs/Sublime-Nit](https://github.com/R4PaSs/Sublime-Nit)
 - **Nix:** [wmertens/sublime-nix](https://github.com/wmertens/sublime-nix)
@@ -249,7 +245,7 @@ This is a list of grammars that Linguist selects to provide syntax highlighting
 - **Pascal:** [textmate/pascal.tmbundle](https://github.com/textmate/pascal.tmbundle)
 - **PAWN:** [Southclaw/pawn-sublime-language](https://github.com/Southclaw/pawn-sublime-language)
 - **Perl:** [textmate/perl.tmbundle](https://github.com/textmate/perl.tmbundle)
-- **Perl6:** [MadcapJake/language-perl6fe](https://github.com/MadcapJake/language-perl6fe)
+- **Perl6:** [perl6/atom-language-perl6](https://github.com/perl6/atom-language-perl6)
 - **PHP:** [textmate/php.tmbundle](https://github.com/textmate/php.tmbundle)
 - **Pic:** [Alhadis/language-roff](https://github.com/Alhadis/language-roff)
 - **PicoLisp:** [textmate/lisp.tmbundle](https://github.com/textmate/lisp.tmbundle)
@@ -265,6 +261,7 @@ This is a list of grammars that Linguist selects to provide syntax highlighting
 - **Prolog:** [alnkpa/sublimeprolog](https://github.com/alnkpa/sublimeprolog)
 - **Propeller Spin:** [bitbased/sublime-spintools](https://github.com/bitbased/sublime-spintools)
 - **Protocol Buffer:** [michaeledgar/protobuf-tmbundle](https://github.com/michaeledgar/protobuf-tmbundle)
+- **Pug:** [davidrios/jade-tmbundle](https://github.com/davidrios/jade-tmbundle)
 - **Puppet:** [russCloak/SublimePuppet](https://github.com/russCloak/SublimePuppet)
 - **PureScript:** [purescript-contrib/atom-language-purescript](https://github.com/purescript-contrib/atom-language-purescript)
 - **Python:** [MagicStack/MagicPython](https://github.com/MagicStack/MagicPython)
@@ -275,21 +272,25 @@ This is a list of grammars that Linguist selects to provide syntax highlighting
 - **R:** [textmate/r.tmbundle](https://github.com/textmate/r.tmbundle)
 - **Racket:** [soegaard/racket-highlight-for-github](https://github.com/soegaard/racket-highlight-for-github)
 - **RAML:** [atom/language-yaml](https://github.com/atom/language-yaml)
+- **Rascal:** [usethesource/rascal-syntax-highlighting](https://github.com/usethesource/rascal-syntax-highlighting)
 - **RDoc:** [joshaven/RDoc.tmbundle](https://github.com/joshaven/RDoc.tmbundle)
 - **REALbasic:** [angryant0007/VBDotNetSyntax](https://github.com/angryant0007/VBDotNetSyntax)
+- **Reason:** [facebook/reason](https://github.com/facebook/reason)
 - **Rebol:** [Oldes/Sublime-REBOL](https://github.com/Oldes/Sublime-REBOL)
 - **Red:** [Oldes/Sublime-Red](https://github.com/Oldes/Sublime-Red)
+- **Regular Expression:** [Alhadis/language-regexp](https://github.com/Alhadis/language-regexp)
 - **Ren'Py:** [williamd1k0/language-renpy](https://github.com/williamd1k0/language-renpy)
 - **reStructuredText:** [Lukasa/language-restructuredtext](https://github.com/Lukasa/language-restructuredtext)
 - **REXX:** [mblocker/rexx-sublime](https://github.com/mblocker/rexx-sublime)
 - **RHTML:** [aroben/ruby.tmbundle](https://github.com/aroben/ruby.tmbundle)
 - **RMarkdown:** [atom/language-gfm](https://github.com/atom/language-gfm)
 - **RobotFramework:** [shellderp/sublime-robot-plugin](https://github.com/shellderp/sublime-robot-plugin)
+- **Roff:** [Alhadis/language-roff](https://github.com/Alhadis/language-roff)
 - **Rouge:** [atom/language-clojure](https://github.com/atom/language-clojure)
 - **RPM Spec:** [waveclaw/language-rpm-spec](https://github.com/waveclaw/language-rpm-spec)
 - **Ruby:** [aroben/ruby.tmbundle](https://github.com/aroben/ruby.tmbundle)
 - **RUNOFF:** [Alhadis/language-roff](https://github.com/Alhadis/language-roff)
-- **Rust:** [jhasse/sublime-rust](https://github.com/jhasse/sublime-rust)
+- **Rust:** [zargony/atom-language-rust](https://github.com/zargony/atom-language-rust)
 - **Sage:** [MagicStack/MagicPython](https://github.com/MagicStack/MagicPython)
 - **SaltStack:** [saltstack/atom-salt](https://github.com/saltstack/atom-salt)
 - **SAS:** [rpardee/sas.tmbundle](https://github.com/rpardee/sas.tmbundle)
@@ -341,6 +342,7 @@ This is a list of grammars that Linguist selects to provide syntax highlighting
 - **TypeScript:** [Microsoft/TypeScript-Sublime-Plugin](https://github.com/Microsoft/TypeScript-Sublime-Plugin)
 - **Unified Parallel C:** [textmate/c.tmbundle](https://github.com/textmate/c.tmbundle)
 - **Unity3D Asset:** [atom/language-yaml](https://github.com/atom/language-yaml)
+- **Unix Assembly:** [Nessphoro/sublimeassembly](https://github.com/Nessphoro/sublimeassembly)
 - **Uno:** [atom/language-csharp](https://github.com/atom/language-csharp)
 - **UnrealScript:** [textmate/java.tmbundle](https://github.com/textmate/java.tmbundle)
 - **UrWeb:** [gwalborn/UrWeb-Language-Definition](https://github.com/gwalborn/UrWeb-Language-Definition)
@@ -348,7 +350,7 @@ This is a list of grammars that Linguist selects to provide syntax highlighting
 - **VCL:** [brandonwamboldt/sublime-varnish](https://github.com/brandonwamboldt/sublime-varnish)
 - **Verilog:** [textmate/verilog.tmbundle](https://github.com/textmate/verilog.tmbundle)
 - **VHDL:** [textmate/vhdl.tmbundle](https://github.com/textmate/vhdl.tmbundle)
-- **VimL:** [Alhadis/language-viml](https://github.com/Alhadis/language-viml)
+- **Vim script:** [Alhadis/language-viml](https://github.com/Alhadis/language-viml)
 - **Visual Basic:** [angryant0007/VBDotNetSyntax](https://github.com/angryant0007/VBDotNetSyntax)
 - **Volt:** [textmate/d.tmbundle](https://github.com/textmate/d.tmbundle)
 - **Vue:** [vuejs/vue-syntax-highlight](https://github.com/vuejs/vue-syntax-highlight)
@@ -361,6 +363,7 @@ This is a list of grammars that Linguist selects to provide syntax highlighting
 - **X10:** [x10-lang/x10-highlighting](https://github.com/x10-lang/x10-highlighting)
 - **xBase:** [hernad/atom-language-harbour](https://github.com/hernad/atom-language-harbour)
 - **XC:** [graymalkin/xc.tmbundle](https://github.com/graymalkin/xc.tmbundle)
+- **XCompose:** [samcv/language-xcompose](https://github.com/samcv/language-xcompose)
 - **XML:** [textmate/xml.tmbundle](https://github.com/textmate/xml.tmbundle)
 - **Xojo:** [angryant0007/VBDotNetSyntax](https://github.com/angryant0007/VBDotNetSyntax)
 - **XProc:** [textmate/xml.tmbundle](https://github.com/textmate/xml.tmbundle)

vendor/licenses/grammar/SublimeEthereum.txt

@@ -1,8 +1,10 @@
 ---
 type: grammar
-name: sublime-rust
+name: SublimeEthereum
 license: mit
 ---
+Copyright (c) 2015+ uniqpath
+
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal
 in the Software without restriction, including without limitation the rights
@@ -19,4 +21,4 @@ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
-THE SOFTWARE.
+THE SOFTWARE..