Merge pull request #1 from pchaigno/pythonmultiline

Multiline comments for Python during tokenization

.gitignore

@@ -1,4 +1,4 @@
-Gemfile.lock
+/Gemfile.lock
 .bundle/
 benchmark/
 lib/linguist/samples.json

.travis.yml

@@ -2,6 +2,7 @@ before_install:
   - git fetch origin master:master
   - git fetch origin v2.0.0:v2.0.0
   - git fetch origin test/attributes:test/attributes
+  - git fetch origin test/master:test/master
   - sudo apt-get install libicu-dev -y
 rvm:
   - 1.9.3

CONTRIBUTING.md

@@ -0,0 +1,31 @@
+## Contributing
+
+The majority of contributions won't need to touch any Ruby code at all. The [master language list][languages] is just a YAML configuration file.
+
+Almost all bug fixes or new language additions should come with some additional code samples. Just drop them under [`samples/`][samples] in the correct subdirectory and our test suite will automatically test them. In most cases you shouldn't need to add any new assertions.
+
+### My code is detected as the wrong language
+
+This can usually be solved either by adding a new filename or file name extension to the language's entry in [`languages.yml`][languages] or adding more [samples][samples] for your language to the repository to make Linguist's classifier smarter.
+
+### Syntax highlighting looks wrong
+
+Assuming your code is being detected as the right language (see above), in most cases this is due to a bug in the language grammar rather than a bug in Linguist. [`grammars.yml`][grammars] lists all the grammars we use for syntax highlighting on github.com. Find the one corresponding to your code's programming language and submit a bug report upstream.
+
+You can also try to fix the bug yourself and submit a Pull Request. [This piece from TextMate's documentation](http://manual.macromates.com/en/language_grammars) offers a good introduction on how to work with TextMate-compatible grammars.
+
+Once the bug has been fixed upstream, please let us know and we'll pick it up for GitHub.
+
+### I want to add support for the `X` programming language
+
+Great! You'll need to:
+
+0. Add an entry for your language to [`languages.yml`][languages].
+0. Add a grammar for your language to [`grammars.yml`][grammars] by running `script/download-grammars --add URL`. Please only add grammars that have a license that permits redistribution.
+0. Add samples for your language to the [samples directory][samples].
+
+We try only to add languages once they have some usage on GitHub, so please note in-the-wild usage examples in your pull request. In most cases we prefer that languages already be in use in hundreds of repositories before supporting them in Linguist.
+
+[grammars]: /grammars.yml
+[languages]: /lib/linguist/languages.yml
+[samples]: /samples

README.md

@@ -2,6 +2,8 @@
 
 We use this library at GitHub to detect blob languages, ignore binary files, suppress generated files in diffs, and generate language breakdown graphs.
 
+Tips for filing issues and creating pull requests can be found in [`CONTRIBUTING.md`](/CONTRIBUTING.md).
+
 ## Features
 
 ### Language detection
@@ -26,15 +28,7 @@ See [lib/linguist/language.rb](https://github.com/github/linguist/blob/master/li
 
 Syntax highlighting in GitHub is performed using TextMate-compatible grammars. These are the same grammars that TextMate, Sublime Text and Atom use.
 
-Every language in `languages.yml` is mapped to its corresponding TM `scope`. This scope will be used when picking up a grammar for highlighting. **When adding a new language to Linguist, please add its corrsponding scope too (assuming there's an existing TextMate bundle) so syntax highlighting works for it**.
+Every language in `languages.yml` is mapped to its corresponding TM `scope`. This scope will be used when picking up a grammar for highlighting. **When adding a new language to Linguist, please add its corresponding scope too (assuming there's an existing TextMate bundle, Sublime Text package, or Atom package) so syntax highlighting works for it**.
-
-#### I found a bug!
-
-The `grammars.yml` file contains the list of all the repositories where we fetch TextMate grammars for highlighting. If you find a bug in the highlighting for any given language, please consult this Grammars list to find the source of the grammar, and submit the bug report upstream.
-
-You can also try to fix the bug yourself and submit a Pull Request. [This piece from TextMate's documentation](http://manual.macromates.com/en/language_grammars) offers a good introduction on how to work with TextMate-compatible grammars.
-
-Once the bug has been fixed upstream, please let us know and we'll pick it up for GitHub.
 
 ### Stats
 
@@ -153,14 +147,6 @@ To run the tests:
 
     bundle exec rake test
 
-## Contributing
-
-The majority of contributions won't need to touch any Ruby code at all. The [master language list](https://github.com/github/linguist/blob/master/lib/linguist/languages.yml) is just a YAML configuration file.
-
-We try to only add languages once they have some usage on GitHub, so please note in-the-wild usage examples in your pull request.
-
-Almost all bug fixes or new language additions should come with some additional code samples. Just drop them under [`samples/`](https://github.com/github/linguist/tree/master/samples) in the correct subdirectory and our test suite will automatically test them. In most cases you shouldn't need to add any new assertions.
-
 ### A note on language extensions
 
 Linguist has a number of methods available to it for identifying the language of a particular file. The initial lookup is based upon the extension of the file, possible file extensions are defined in an array called `extensions`. Take a look at this example for example for `Perl`:

github-linguist.gemspec

@@ -15,8 +15,8 @@ Gem::Specification.new do |s|
 
   s.add_dependency 'charlock_holmes', '~> 0.7.3'
   s.add_dependency 'escape_utils',    '~> 1.0.1'
-  s.add_dependency 'mime-types',      '~> 1.19'
+  s.add_dependency 'mime-types',      '>= 1.19'
-  s.add_dependency 'rugged',          '~> 0.21.1b2'
+  s.add_dependency 'rugged',          '~> 0.22.0b4'
 
   s.add_development_dependency 'mocha'
   s.add_development_dependency 'pry'

grammars.yml

@@ -1,6 +1,4 @@
 ---
-http://hww3.riverweb.com/dist/Pike_TextMate.tar.gz:
-- source.pike
 http://svn.edgewall.org/repos/genshi/contrib/textmate/Genshi.tmbundle/Syntaxes/Markup%20Template%20%28XML%29.tmLanguage:
 - text.xml.genshi
 http://svn.textmate.org/trunk/Review/Bundles/BlitzMax.tmbundle:
@@ -40,10 +38,14 @@ https://github.com/Drako/SublimeBrainfuck/raw/master/Brainfuck.tmLanguage:
 - source.bf
 https://github.com/JohnNilsson/awk-sublime/raw/master/AWK.tmLanguage:
 - source.awk
+https://github.com/JonBons/Sublime-SQF-Language:
+- source.sqf
 https://github.com/MarioRicalde/SCSS.tmbundle:
 - source.scss
 https://github.com/Oldes/Sublime-REBOL:
 - source.rebol
+https://github.com/PogiNate/Sublime-Inform:
+- source.Inform7
 https://github.com/Red-Nova-Technologies/autoitv3-tmbundle:
 - source.autoit.3
 https://github.com/SalGnt/Sublime-VimL:
@@ -70,6 +72,8 @@ https://github.com/aroben/ruby.tmbundle@4636a3023153c3034eb6ffc613899ba9cf33b41f
 - text.html.erb
 https://github.com/asbjornenge/Docker.tmbundle:
 - source.dockerfile
+https://github.com/atom/language-clojure:
+- source.clojure
 https://github.com/atom/language-coffee-script:
 - source.coffee
 - source.litcoffee
@@ -95,6 +99,8 @@ https://github.com/bholt/chapel-tmbundle:
 - source.chapel
 https://github.com/brandonwamboldt/sublime-nginx:
 - source.nginx
+https://github.com/bro/bro-sublime:
+- source.bro
 https://github.com/carsonoid/sublime_man_page_support/raw/master/man-groff.tmLanguage:
 - text.groff
 https://github.com/ccreutzig/sublime-MuPAD:
@@ -135,6 +141,8 @@ https://github.com/guillermooo/dart-sublime-bundle/raw/master/Dart.tmLanguage:
 - source.dart
 https://github.com/harrism/sublimetext-cuda-cpp/raw/master/cuda-c%2B%2B.tmLanguage:
 - source.cuda-c++
+https://github.com/hww3/pike-textmate:
+- source.pike
 https://github.com/jeancharles-roger/ceylon-sublimetext/raw/master/Ceylon.tmLanguage:
 - source.ceylon
 https://github.com/jfairbank/Sublime-Text-2-OpenEdge-ABL:
@@ -211,16 +219,11 @@ https://github.com/slavapestov/factor/raw/master/misc/Factor.tmbundle/Syntaxes/F
 - source.factor
 https://github.com/slim-template/ruby-slim.tmbundle:
 - text.slim
-https://github.com/smiledawgg/Bro.tmbundle:
-- source.bro
-- source.bro.sig
 https://github.com/staltz/SublimeXtend:
 - source.xtend
 https://github.com/statatmbundle/Stata.tmbundle:
 - source.mata
 - source.stata
-https://github.com/swannodette/textmate-clojure:
-- source.clojure
 https://github.com/technosophos/Vala-TMBundle:
 - source.vala
 https://github.com/textmate/ant.tmbundle:
@@ -240,6 +243,7 @@ https://github.com/textmate/bison.tmbundle:
 https://github.com/textmate/c.tmbundle:
 - source.c
 - source.c++
+- source.c.platform
 https://github.com/textmate/capnproto.tmbundle:
 - source.capnp
 https://github.com/textmate/cmake.tmbundle:
@@ -277,8 +281,6 @@ https://github.com/textmate/haskell.tmbundle:
 - text.tex.latex.haskell
 https://github.com/textmate/html.tmbundle:
 - text.html.basic
-https://github.com/textmate/inform.tmbundle:
-- source.inform
 https://github.com/textmate/ini.tmbundle:
 - source.ini
 https://github.com/textmate/io.tmbundle:
@@ -327,6 +329,7 @@ https://github.com/textmate/ninja.tmbundle:
 https://github.com/textmate/objective-c.tmbundle:
 - source.objc
 - source.objc++
+- source.objc.platform
 - source.strings
 https://github.com/textmate/ocaml.tmbundle:
 - source.camlp4.ocaml

lib/linguist/blob_helper.rb

@@ -146,6 +146,13 @@ module Linguist
       end
     end
 
+    # Public: Is the blob empty?
+    #
+    # Return true or false
+    def empty?
+      data.nil? || data == ""
+    end
+
     # Public: Is the blob text?
     #
     # Return true or false

lib/linguist/generated.rb

@@ -51,21 +51,20 @@ module Linguist
     #
     # Return true or false
     def generated?
-      name == 'Gemfile.lock' ||
+      minified_files? ||
-        minified_files? ||
+      compiled_coffeescript? ||
-        compiled_coffeescript? ||
+      xcode_file? ||
-        xcode_file? ||
+      generated_parser? ||
-        generated_parser? ||
+      generated_net_docfile? ||
-        generated_net_docfile? ||
+      generated_net_designer_file? ||
-        generated_net_designer_file? ||
+      generated_postscript? ||
-        generated_postscript? ||
+      generated_protocol_buffer? ||
-        generated_protocol_buffer? ||
+      generated_jni_header? ||
-        generated_jni_header? ||
+      composer_lock? ||
-        composer_lock? ||
+      node_modules? ||
-        node_modules? ||
+      godeps? ||
-        godeps? ||
+      vcr_cassette? ||
-        vcr_cassette? ||
+      generated_by_zephir?
-        generated_by_zephir?
     end
 
     # Internal: Is the blob an Xcode file?
@@ -265,4 +264,3 @@ module Linguist
     end
   end
 end
-

lib/linguist/heuristics.rb

@@ -13,26 +13,31 @@ module Linguist
     # Returns an array of Languages or []
     def self.find_by_heuristics(data, languages)
       if active?
+        result = []
+
         if languages.all? { |l| ["Perl", "Prolog"].include?(l) }
-          result = disambiguate_pl(data, languages)
+          result = disambiguate_pl(data)
         end
         if languages.all? { |l| ["ECL", "Prolog"].include?(l) }
-          result = disambiguate_ecl(data, languages)
+          result = disambiguate_ecl(data)
         end
         if languages.all? { |l| ["IDL", "Prolog"].include?(l) }
-          result = disambiguate_pro(data, languages)
+          result = disambiguate_pro(data)
         end
         if languages.all? { |l| ["Common Lisp", "OpenCL"].include?(l) }
-          result = disambiguate_cl(data, languages)
+          result = disambiguate_cl(data)
         end
         if languages.all? { |l| ["Hack", "PHP"].include?(l) }
-          result = disambiguate_hack(data, languages)
+          result = disambiguate_hack(data)
         end
         if languages.all? { |l| ["Scala", "SuperCollider"].include?(l) }
-          result = disambiguate_sc(data, languages)
+          result = disambiguate_sc(data)
         end
         if languages.all? { |l| ["AsciiDoc", "AGS Script"].include?(l) }
-          result = disambiguate_asc(data, languages)
+          result = disambiguate_asc(data)
+        end
+        if languages.all? { |l| ["FORTRAN", "Forth"].include?(l) }
+          result = disambiguate_f(data)
         end
         return result
       end
@@ -42,28 +47,37 @@ module Linguist
     # We want to shortcut look for Objective-C _and_ now C++ too!
     #
     # Returns an array of Languages or []
-    def self.disambiguate_c(data, languages)
+    def self.disambiguate_c(data)
       matches = []
-      matches << Language["Objective-C"] if data.include?("@interface")
+      if data.include?("@interface")
-      matches << Language["C++"] if data.include?("#include <cstdint>")
+        matches << Language["Objective-C"]
+      elsif data.include?("#include <cstdint>")
+        matches << Language["C++"]
+      end
       matches
     end
 
-    def self.disambiguate_pl(data, languages)
+    def self.disambiguate_pl(data)
       matches = []
-      matches << Language["Prolog"] if data.include?(":-")
+      if data.include?("use strict")
-      matches << Language["Perl"] if data.include?("use strict")
+        matches << Language["Perl"]
+      elsif data.include?(":-")
+        matches << Language["Prolog"]
+      end
       matches
     end
 
-    def self.disambiguate_ecl(data, languages)
+    def self.disambiguate_ecl(data)
       matches = []
-      matches << Language["Prolog"] if data.include?(":-")
+      if data.include?(":-")
-      matches << Language["ECL"] if data.include?(":=")
+        matches << Language["Prolog"]
+      elsif data.include?(":=")
+        matches << Language["ECL"]
+      end
       matches
     end
 
-    def self.disambiguate_pro(data, languages)
+    def self.disambiguate_pro(data)
       matches = []
       if (data.include?(":-"))
         matches << Language["Prolog"]
@@ -73,7 +87,7 @@ module Linguist
       matches
     end
 
-    def self.disambiguate_ts(data, languages)
+    def self.disambiguate_ts(data)
       matches = []
       if (data.include?("</translation>"))
         matches << Language["XML"]
@@ -83,21 +97,24 @@ module Linguist
       matches
     end
 
-    def self.disambiguate_cl(data, languages)
+    def self.disambiguate_cl(data)
       matches = []
-      matches << Language["Common Lisp"] if data.include?("(defun ")
+      if data.include?("(defun ")
-      matches << Language["OpenCL"] if /\/\* |\/\/ |^\}/.match(data)
+        matches << Language["Common Lisp"]
+      elsif /\/\* |\/\/ |^\}/.match(data)
+        matches << Language["OpenCL"]
+      end
       matches
     end
 
-    def self.disambiguate_r(data, languages)
+    def self.disambiguate_r(data)
       matches = []
       matches << Language["Rebol"] if /\bRebol\b/i.match(data)
       matches << Language["R"] if data.include?("<-")
       matches
     end
 
-    def self.disambiguate_hack(data, languages)
+    def self.disambiguate_hack(data)
       matches = []
       if data.include?("<?hh")
         matches << Language["Hack"]
@@ -107,7 +124,7 @@ module Linguist
       matches
     end
 
-    def self.disambiguate_sc(data, languages)
+    def self.disambiguate_sc(data)
       matches = []
       if (/\^(this|super)\./.match(data) || /^\s*(\+|\*)\s*\w+\s*{/.match(data) || /^\s*~\w+\s*=\./.match(data))
         matches << Language["SuperCollider"]
@@ -118,12 +135,22 @@ module Linguist
       matches
     end
 
-    def self.disambiguate_asc(data, languages)
+    def self.disambiguate_asc(data)
       matches = []
       matches << Language["AsciiDoc"] if /^=+(\s|\n)/.match(data)
       matches
     end
 
+    def self.disambiguate_f(data)
+      matches = []
+      if /^: /.match(data)
+        matches << Language["Forth"]
+      elsif /^([c*][^a-z]|      subroutine\s)/i.match(data)
+        matches << Language["FORTRAN"]
+      end
+      matches
+    end
+
     def self.active?
       !!ACTIVE
     end

lib/linguist/language.rb

@@ -100,12 +100,8 @@ module Linguist
     def self.detect(blob)
       name = blob.name.to_s
 
-      # Check if the blob is possibly binary and bail early; this is a cheap
+      # Bail early if the blob is binary or empty.
-      # test that uses the extension name to guess a binary binary mime type.
+      return nil if blob.likely_binary? || blob.binary? || blob.empty?
-      #
-      # We'll perform a more comprehensive test later which actually involves
-      # looking for binary characters in the blob
-      return nil if blob.likely_binary? || blob.binary?
 
       # A bit of an elegant hack. If the file is executable but extensionless,
       # append a "magic" extension so it can be classified with other
@@ -124,16 +120,18 @@ module Linguist
       if possible_languages.length > 1
         data = blob.data
         possible_language_names = possible_languages.map(&:name)
+        heuristic_languages = Heuristics.find_by_heuristics(data, possible_language_names)
+
+        if heuristic_languages.size > 1
+          possible_language_names = heuristic_languages.map(&:name)
+        end
 
-        # Don't bother with binary contents or an empty file
-        if data.nil? || data == ""
-          nil
         # Check if there's a shebang line and use that as authoritative
-        elsif (result = find_by_shebang(data)) && !result.empty?
+        if (result = find_by_shebang(data)) && !result.empty?
           result.first
         # No shebang. Still more work to do. Try to find it with our heuristics.
-        elsif (determined = Heuristics.find_by_heuristics(data, possible_language_names)) && !determined.empty?
+        elsif heuristic_languages.size == 1
-          determined.first
+          heuristic_languages.first
         # Lastly, fall back to the probabilistic classifier.
         elsif classified = Classifier.classify(Samples.cache, data, possible_language_names).first
           # Return the actual Language object based of the string language name (i.e., first element of `#classify`)
@@ -433,11 +431,6 @@ module Linguist
     # Returns the extensions Array
     attr_reader :filenames
 
-    # Public: Return all possible extensions for language
-    def all_extensions
-      (extensions + [primary_extension]).uniq
-    end
-
     # Deprecated: Get primary extension
     #
     # Defaults to the first extension but can be overridden
@@ -595,9 +588,9 @@ module Linguist
       :ace_mode          => options['ace_mode'],
       :wrap              => options['wrap'],
       :group_name        => options['group'],
-      :searchable        => options.key?('searchable') ? options['searchable'] : true,
+      :searchable        => options.fetch('searchable', true),
       :search_term       => options['search_term'],
-      :extensions        => [options['extensions'].first] + options['extensions'][1..-1].sort,
+      :extensions        => Array(options['extensions']),
       :interpreters      => options['interpreters'].sort,
       :filenames         => options['filenames'],
       :popular           => popular.include?(name)

lib/linguist/languages.yml

@@ -12,6 +12,10 @@
 # search_term       - Deprecated: Some languages maybe indexed under a
 #                     different alias. Avoid defining new exceptions.
 # color             - CSS hex color to represent the language.
+# tm_scope          - The TextMate scope that represents this programming
+#                     language. This should match one of the scopes listed in
+#                     the grammars.yml file. Use "none" if there is no grammar
+#                     for this language.
 #
 # Any additions or modifications (even trivial) should have corresponding
 # test change in `test/test_blob.rb`.
@@ -33,15 +37,6 @@ AGS Script:
   - .ash
   tm_scope: source.c++
 
-Ant Build System:
-  type: data
-  tm_scope: text.xml.ant
-  extensions:
-  - .ant.xml
-  filenames:
-  - build.xml
-  - ant.xml
-
 ANTLR:
   type: programming
   color: "#9DC3FF"
@@ -54,6 +49,7 @@ APL:
   extensions:
   - .apl
   - .dyalog
+  tm_scope: none
 
 ASP:
   type: programming
@@ -117,6 +113,13 @@ Alloy:
   extensions:
   - .als
 
+Ant Build System:
+  type: data
+  tm_scope: text.xml.ant
+  filenames:
+  - ant.xml
+  - build.xml
+
 ApacheConf:
   type: markup
   aliases:
@@ -148,6 +151,7 @@ Arc:
   color: "#ca2afe"
   extensions:
   - .arc
+  tm_scope: none
 
 Arduino:
   type: programming
@@ -164,12 +168,14 @@ AsciiDoc:
   - .asciidoc
   - .adoc
   - .asc
+  tm_scope: none
 
 AspectJ:
   type: programming
   color: "#1957b0"
   extensions:
   - .aj
+  tm_scope: none
 
 Assembly:
   type: programming
@@ -187,6 +193,7 @@ Augeas:
   type: programming
   extensions:
   - .aug
+  tm_scope: none
 
 AutoHotkey:
   type: programming
@@ -196,6 +203,7 @@ AutoHotkey:
   extensions:
   - .ahk
   - .ahkl
+  tm_scope: none
 
 AutoIt:
   type: programming
@@ -288,6 +296,7 @@ Brightscript:
   type: programming
   extensions:
   - .brs
+  tm_scope: none
 
 Bro:
   type: programming
@@ -361,6 +370,7 @@ CLIPS:
   type: programming
   extensions:
   - .clp
+  tm_scope: none
 
 CMake:
   extensions:
@@ -423,6 +433,7 @@ Clean:
   extensions:
   - .icl
   - .dcl
+  tm_scope: none
 
 Clojure:
   type: programming
@@ -451,6 +462,7 @@ CoffeeScript:
   extensions:
   - .coffee
   - ._coffee
+  - .cjsx
   - .cson
   - .iced
   filenames:
@@ -539,6 +551,7 @@ Creole:
   wrap: true
   extensions:
   - .creole
+  tm_scope: none
 
 Crystal:
   type: programming
@@ -606,6 +619,7 @@ Darcs Patch:
   extensions:
   - .darcspatch
   - .dpatch
+  tm_scope: none
 
 Dart:
   type: programming
@@ -633,6 +647,7 @@ Dogescript:
   color: "#cca760"
   extensions:
   - .djs
+  tm_scope: none
 
 Dylan:
   type: programming
@@ -648,13 +663,7 @@ E:
   color: "#ccce35"
   extensions:
   - .E
-
+  tm_scope: none
-Ecere Projects:
-  type: data
-  group: JavaScript
-  extensions:
-  - .epj
-  tm_scope: source.json
 
 ECL:
   type: programming
@@ -662,6 +671,7 @@ ECL:
   extensions:
   - .ecl
   - .eclxml
+  tm_scope: none
 
 Eagle:
   type: markup
@@ -671,6 +681,13 @@ Eagle:
   - .brd
   tm_scope: text.xml
 
+Ecere Projects:
+  type: data
+  group: JavaScript
+  extensions:
+  - .epj
+  tm_scope: source.json
+
 Eiffel:
   type: programming
   color: "#946d57"
@@ -738,6 +755,7 @@ FLUX:
   extensions:
   - .fx
   - .flux
+  tm_scope: none
 
 FORTRAN:
   type: programming
@@ -767,8 +785,8 @@ Factor:
   extensions:
   - .factor
   filenames:
-    - .factor-rc
     - .factor-boot-rc
+    - .factor-rc
 
 Fancy:
   type: programming
@@ -792,6 +810,9 @@ Forth:
   extensions:
   - .fth
   - .4th
+  - .F
+  - .f
+  - .for
   - .forth
   - .frt
 
@@ -808,18 +829,13 @@ G-code:
   - .g
   - .gco
   - .gcode
-
+  tm_scope: none
-Game Maker Language:
-  type: programming
-  color: "#8ad353"
-  extensions:
-  - .gml
-  tm_scope: source.js
 
 GAMS:
   type: programming
   extensions:
   - .gms
+  tm_scope: none
 
 GAP:
   type: programming
@@ -828,6 +844,7 @@ GAP:
   - .gap
   - .gd
   - .gi
+  tm_scope: none
 
 GAS:
   type: programming
@@ -841,6 +858,7 @@ GDScript:
   type: programming
   extensions:
   - .gd
+  tm_scope: none
 
 GLSL:
   group: C
@@ -860,6 +878,13 @@ GLSL:
   - .vrx
   - .vshader
 
+Game Maker Language:
+  type: programming
+  color: "#8ad353"
+  extensions:
+  - .gml
+  tm_scope: source.js
+
 Genshi:
   extensions:
   - .kid
@@ -918,6 +943,7 @@ Golo:
   color: "#f6a51f"
   extensions:
   - .golo
+  tm_scope: none
 
 Gosu:
   type: programming
@@ -933,6 +959,7 @@ Grace:
   type: programming
   extensions:
   - .grace
+  tm_scope: none
 
 Grammatical Framework:
   type: programming
@@ -949,6 +976,7 @@ Graph Modeling Language:
   type: data
   extensions:
   - .gml
+  tm_scope: none
 
 Graphviz (DOT):
   type: data
@@ -1003,6 +1031,7 @@ HTML:
   - .html
   - .htm
   - .st
+  - .xht
   - .xhtml
 
 HTML+Django:
@@ -1038,6 +1067,7 @@ HTTP:
   type: data
   extensions:
   - .http
+  tm_scope: none
 
 Hack:
   type: programming
@@ -1045,6 +1075,7 @@ Hack:
   extensions:
   - .hh
   - .php
+  tm_scope: none
 
 Haml:
   group: HTML
@@ -1067,6 +1098,7 @@ Harbour:
   color: "#0e60e3"
   extensions:
   - .hb
+  tm_scope: none
 
 Haskell:
   type: programming
@@ -1092,6 +1124,7 @@ Hy:
   - .hy
   aliases:
   - hylang
+  tm_scope: none
 
 IDL:
   type: programming
@@ -1107,6 +1140,7 @@ IGOR Pro:
   aliases:
   - igor
   - igorpro
+  tm_scope: none
 
 INI:
   type: data
@@ -1119,9 +1153,15 @@ INI:
   aliases:
   - dosini
 
-Inno Setup:
+IRC log:
+  search_term: irc
+  aliases:
+  - irc
+  - irc logs
   extensions:
-  - .iss
+  - .irclog
+  - .weechatlog
+  tm_scope: none
 
 Idris:
   type: programming
@@ -1135,7 +1175,7 @@ Inform 7:
   extensions:
   - .ni
   - .i7x
-  tm_scope: source.inform
+  tm_scope: source.Inform7
   aliases:
   - i7
   - inform7
@@ -1143,15 +1183,7 @@ Inform 7:
 Inno Setup:
   extensions:
   - .iss
-
+  tm_scope: none
-IRC log:
-  search_term: irc
-  aliases:
-  - irc
-  - irc logs
-  extensions:
-  - .irclog
-  - .weechatlog
 
 Io:
   type: programming
@@ -1170,11 +1202,13 @@ Isabelle:
   color: "#fdcd00"
   extensions:
   - .thy
+  tm_scope: none
 
 J:
   type: programming
   extensions:
   - .ijs
+  tm_scope: none
 
 JSON:
   type: data
@@ -1282,6 +1316,7 @@ KRL:
   color: "#f5c800"
   extensions:
   - .krl
+  tm_scope: none
 
 Kit:
   type: markup
@@ -1315,6 +1350,7 @@ LOLCODE:
   extensions:
   - .lol
   color: "#cc9900"
+  tm_scope: none
 
 LSL:
   type: programming
@@ -1329,6 +1365,7 @@ LabVIEW:
   type: programming
   extensions:
   - .lvproj
+  tm_scope: none
 
 Lasso:
   type: programming
@@ -1367,12 +1404,14 @@ Liquid:
   type: markup
   extensions:
   - .liquid
+  tm_scope: none
 
 Literate Agda:
   type: programming
   group: Agda
   extensions:
   - .lagda
+  tm_scope: none
 
 Literate CoffeeScript:
   type: programming
@@ -1462,6 +1501,7 @@ MTML:
   tm_scope: text.html.basic
 
 Makefile:
+  type: programming
   aliases:
   - bsdmake
   - make
@@ -1470,9 +1510,9 @@ Makefile:
   - .mak
   - .mk
   filenames:
-  - makefile
-  - Makefile
   - GNUmakefile
+  - Makefile
+  - makefile
   interpreters:
   - make
 
@@ -1525,8 +1565,6 @@ Matlab:
 Maven POM:
   type: data
   tm_scope: text.xml.pom
-  extensions:
-  - .pom.xml
   filenames:
   - pom.xml
 
@@ -1550,6 +1588,7 @@ MediaWiki:
   wrap: true
   extensions:
   - .mediawiki
+  tm_scope: none
 
 Mercury:
   type: programming
@@ -1564,6 +1603,7 @@ MiniD: # Legacy
   searchable: false
   extensions:
   - .minid # Dummy extension
+  tm_scope: none
 
 Mirah:
   type: programming
@@ -1585,6 +1625,7 @@ Moocode:
   type: programming
   extensions:
   - .moo
+  tm_scope: none
 
 MoonScript:
   type: programming
@@ -1596,6 +1637,7 @@ MoonScript:
 Myghty:
   extensions:
   - .myt
+  tm_scope: none
 
 NSIS:
   extensions:
@@ -1641,6 +1683,7 @@ Nit:
   color: "#0d8921"
   extensions:
   - .nit
+  tm_scope: none
 
 Nix:
   type: programming
@@ -1648,6 +1691,7 @@ Nix:
   - .nix
   aliases:
   - nixos
+  tm_scope: none
 
 Nu:
   type: programming
@@ -1666,6 +1710,7 @@ NumPy:
   - .numpy
   - .numpyw
   - .numsc
+  tm_scope: none
 
 OCaml:
   type: programming
@@ -1726,6 +1771,7 @@ Omgrofl:
   extensions:
   - .omgrofl
   color: "#cabbff"
+  tm_scope: none
 
 Opa:
   type: programming
@@ -1737,6 +1783,7 @@ Opal:
   color: "#f7ede0"
   extensions:
   - .opal
+  tm_scope: none
 
 OpenCL:
   type: programming
@@ -1761,12 +1808,14 @@ OpenSCAD:
   type: programming
   extensions:
   - .scad
+  tm_scope: none
 
 Org:
   type: prose
   wrap: true
   extensions:
   - .org
+  tm_scope: none
 
 Ox:
   type: programming
@@ -1774,12 +1823,14 @@ Ox:
   - .ox
   - .oxh
   - .oxo
+  tm_scope: none
 
 Oxygene:
   type: programming
   color: "#5a63a3"
   extensions:
   - .oxygene
+  tm_scope: none
 
 PAWN:
   type: programming
@@ -1815,18 +1866,30 @@ Pan:
   color: '#cc0000'
   extensions:
   - .pan
+  tm_scope: none
 
 Papyrus:
   type: programming
   color: "#6600cc"
   extensions:
   - .psc
+  tm_scope: none
 
 Parrot:
   type: programming
   color: "#f3ca0a"
   extensions:
   - .parrot # Dummy extension
+  tm_scope: none
+
+Parrot Assembly:
+  group: Parrot
+  type: programming
+  aliases:
+  - pasm
+  extensions:
+  - .pasm
+  tm_scope: none
 
 Parrot Internal Representation:
   group: Parrot
@@ -1837,14 +1900,6 @@ Parrot Internal Representation:
   extensions:
   - .pir
 
-Parrot Assembly:
-  group: Parrot
-  type: programming
-  aliases:
-  - pasm
-  extensions:
-  - .pasm
-
 Pascal:
   type: programming
   color: "#b0ce4e"
@@ -1886,12 +1941,14 @@ Perl6:
   - .p6m
   - .pl6
   - .pm6
+  tm_scope: none
 
 PigLatin:
   type: programming
   color: "#fcd7de"
   extensions:
   - .pig
+  tm_scope: none
 
 Pike:
   type: programming
@@ -1906,12 +1963,14 @@ Pod:
   wrap: true
   extensions:
   - .pod
+  tm_scope: none
 
 PogoScript:
   type: programming
   color: "#d80074"
   extensions:
   - .pogo
+  tm_scope: none
 
 PostScript:
   type: markup
@@ -1952,6 +2011,7 @@ Propeller Spin:
   color: "#2b446d"
   extensions:
   - .spin
+  tm_scope: none
 
 Protocol Buffer:
   type: markup
@@ -1975,6 +2035,7 @@ Pure Data:
   color: "#91de79"
   extensions:
   - .pd
+  tm_scope: none
 
 PureScript:
   type: programming
@@ -2001,10 +2062,10 @@ Python:
   - .wsgi
   - .xpy
   filenames:
-  - wscript
-  - SConstruct
-  - SConscript
   - BUILD
+  - SConscript
+  - SConstruct
+  - wscript
   interpreters:
   - python
 
@@ -2070,7 +2131,7 @@ RHTML:
   group: HTML
   extensions:
   - .rhtml
-  tm_scope: text.html.ruby
+  tm_scope: text.html.erb
   aliases:
   - html+ruby
 
@@ -2081,6 +2142,7 @@ RMarkdown:
   extensions:
   - .rmd
   - .Rmd
+  tm_scope: none
 
 Racket:
   type: programming
@@ -2100,6 +2162,7 @@ Ragel in Ruby Host:
   aliases:
   - ragel-rb
   - ragel-ruby
+  tm_scope: none
 
 Raw token data:
   search_term: raw
@@ -2107,6 +2170,7 @@ Raw token data:
   - raw
   extensions:
   - .raw
+  tm_scope: none
 
 Rebol:
   type: programming
@@ -2126,10 +2190,12 @@ Red:
   - .reds
   aliases:
   - red/system
+  tm_scope: none
 
 Redcode:
   extensions:
   - .cw
+  tm_scope: none
 
 RobotFramework:
   type: programming
@@ -2203,6 +2269,7 @@ SAS:
   color: "#1E90FF"
   extensions:
   - .sas
+  tm_scope: none
 
 SCSS:
   type: markup
@@ -2218,7 +2285,7 @@ SQF:
   extensions:
   - .sqf
   - .hqf
-  tm_scope: source.c++
+  tm_scope: source.sqf
 
 SQL:
   type: data
@@ -2296,6 +2363,7 @@ Self:
   color: "#0579aa"
   extensions:
   - .self
+  tm_scope: none
 
 Shell:
   type: programming
@@ -2334,6 +2402,7 @@ Shen:
   color: "#120F14"
   extensions:
   - .shen
+  tm_scope: none
 
 Slash:
   type: programming
@@ -2404,6 +2473,7 @@ Stylus:
   group: CSS
   extensions:
   - .styl
+  tm_scope: none
 
 SuperCollider:
   type: programming
@@ -2411,6 +2481,7 @@ SuperCollider:
   extensions:
   - .scd
   - .sc
+  tm_scope: none
 
 Swift:
   type: programming
@@ -2436,6 +2507,7 @@ TXL:
   type: programming
   extensions:
   - .txl
+  tm_scope: none
 
 Tcl:
   type: programming
@@ -2492,6 +2564,7 @@ Textile:
   wrap: true
   extensions:
   - .textile
+  tm_scope: none
 
 Thrift:
   type: programming
@@ -2505,6 +2578,7 @@ Turing:
   extensions:
   - .t
   - .tu
+  tm_scope: none
 
 Twig:
   type: markup
@@ -2584,8 +2658,8 @@ VimL:
   filenames:
   - .vimrc
   - _vimrc
-  - vimrc
   - gvimrc
+  - vimrc
 
 Visual Basic:
   type: programming
@@ -2687,12 +2761,12 @@ XML:
   filenames:
   - .classpath
   - .project
+  - Web.Debug.config
+  - Web.Release.config
+  - Web.config
   - build.xml.dist
   - packages.config
   - phpunit.xml.dist
-  - Web.config
-  - Web.Debug.config
-  - Web.Release.config
 
 XProc:
   type: programming
@@ -2765,6 +2839,7 @@ Zimpl:
   - .zimpl
   - .zmpl
   - .zpl
+  tm_scope: none
 
 eC:
   type: programming
@@ -2772,6 +2847,7 @@ eC:
   extensions:
   - .ec
   - .eh
+  tm_scope: none
 
 edn:
   type: data
@@ -2786,6 +2862,7 @@ fish:
   group: Shell
   extensions:
   - .fish
+  tm_scope: none
 
 mupad:
   extensions:
@@ -2826,3 +2903,4 @@ xBase:
   color: "#3a4040"
   extensions:
   - .prg
+  tm_scope: none

lib/linguist/vendor.yml

@@ -110,6 +110,12 @@
 # MathJax
 - (^|/)MathJax/
 
+# Chart.js
+- (^|/)Chart\.js$
+
+# Codemirror
+- (^|/)[Cc]ode[Mm]irror/(lib|mode|theme|addon|keymap)
+
 # SyntaxHighlighter - http://alexgorbatchev.com/
 - (^|/)shBrush([^.]*)\.js$
 - (^|/)shCore\.js$

lib/linguist/version.rb

@@ -1,3 +1,3 @@
 module Linguist
-  VERSION = "4.0.0"
+  VERSION = "4.0.3"
 end

samples/Ant Build System/filenames/ant.xml

@@ -0,0 +1,110 @@
+<?xml version="1.0" encoding="iso-8859-1"?>
+<project name="WebBuild">
+
+    <!-- generate timestamps -->
+    <tstamp />
+
+    <!-- Debugging Macro -->
+    <import file="echopath.xml" />
+
+    <!-- JS build files macro -->
+    <import file="rhinoscript.xml" />
+
+    <!-- Component Build Files -->
+    <import file="setup.xml" />
+    <import file="clean.xml" />
+    <import file="copy.xml" />
+    <import file="file.transform.xml" />
+    <import file="external.tools.xml" />
+    <import file="rename.xml" />
+    <import file="js.xml" />
+    <import file="css.xml" />
+    <import file="img.xml" />
+    <import file="png8.xml" />
+    <import file="yui.xml" />
+    <import file="cdn.xml" />
+    <import file="datauri.xml" />
+    <import file="devlive.xml" />
+
+    <!-- This dirname is the only complete path we know for sure, everything builds off of it -->
+    <dirname property="dir.build" file="${ant.file.WebBuild}" />
+
+    <!-- get name for newly built folder -->
+    <basename property="app.name"       file="${basedir}" />
+
+    <!-- read global properties file -->
+    <property file="${dir.build}\build.properties" />
+
+    <!-- Build Directories -->
+    <property name="dir.build.js"   location="${dir.build}/js" />
+
+    <!-- App Directories -->
+    <property name="dir.app"        location="${dir.result}/${app.name}" />
+    <property name="dir.app.temp"   location="${dir.temp}/${app.name}" />
+    <property name="dir.app.files"  location="${dir.app.temp}/${dir.files}" />
+
+    <!-- Files -->
+    <property name="mapping.js"     location="${dir.app.temp}/${mapping.file.js}" />
+    <property name="mapping.css"    location="${dir.app.temp}/${mapping.file.css}" />
+    <property name="mapping.img"    location="${dir.app.temp}/${mapping.file.img}" />
+    <property name="mapping.swf"    location="${dir.app.temp}/${mapping.file.swf}" />
+    <property name="mapping.fonts"  location="${dir.app.temp}/${mapping.file.fonts}" />
+
+    <!-- Tool Directories -->
+    <property name="dir.bin"    location="${dir.build}/Bin" />
+    <property name="dir.jar"    location="${dir.bin}/jar" />
+
+    <!-- Tool Files -->
+	<property name="tools.compressor"     location="${dir.jar}/${tools.file.compressor}" />
+	<property name="tools.cssembed"       location="${dir.jar}/${tools.file.cssembed}" />
+    <property name="tools.filetransform"  location="${dir.jar}/${tools.file.filetransform}" />
+    <property name="tools.optipng"        location="${dir.bin}/${tools.file.optipng}" />
+    <property name="tools.jpegtran"       location="${dir.bin}/${tools.file.jpegtran}" />
+
+
+    <!-- BUILD TARGETS -->
+
+    <!-- low level utility build targets -->
+
+    <!-- Build the tools -->
+    <target name="-setup.build.tools"
+            depends="-define.filetransform, -define.cssembed, -define.yuicompressor, -define.jsclasspath"
+    />
+
+    <!-- set up filesystem properties -->
+    <target
+        name="-setup"
+        depends="-setup.mode, -setup.conditions, -setup.js, -setup.css, -setup.swf, -setup.img, -setup.fonts, -setup.yui"
+    />
+
+    <!-- utility-ish targets -->
+    <target name="copy"         depends="clean, tools, -copy" />
+    <target name="tools"        depends="-setup.build.tools" />
+    <target name="finalize"     depends="copy, -finalize" />
+    <target name="-prepare"     depends="copy, -setup" />
+
+    <!-- individual component build targets (empty descriptions are to make sure they show in "ant -p") -->
+    <target name="devlive"      depends="-prepare, -devlive"            description="" />
+    <target name="js"           depends="-prepare, -js"                 description="" />
+    <target name="css"          depends="-prepare, -css"                description="" />
+    <target name="rename"       depends="-prepare, -rename"             description="" />
+    <target name="yui"          depends="-prepare, rename, -yui"        description="" />
+    <target name="cdn"          depends="-prepare, -cdn"                description="" />
+
+    <!-- high level build targets (Excluding of images is on purpose here, it's slow) -->
+    <target name="core"
+            depends="devlive, js, css, cdn, rename, yui, -js.inline"
+            description="Core build work"
+    />
+
+    <target name="prod"
+            depends="core, finalize"
+            description="Full Production Build"
+    />
+
+    <!-- debug target -->
+    <target name="debug" depends="-setup">
+        <echoproperties/>
+    </target>
+
+</project>

samples/Ant Build System/filenames/build.xml

@@ -0,0 +1 @@
+ant.xml

samples/CoffeeScript/example.cjsx

@@ -0,0 +1,40 @@
+###* @cjsx React.DOM ###
+define 'myProject.ReactExampleComponent', [
+  'React'
+  'myProject.ExampleStore'
+  'myProject.ExampleActions'
+  'myProject.ReactExampleTable'
+], (React, ExampleStore, ExampleActions, ReactExampleTable ) ->
+
+  ReactExampleComponent = React.createClass
+    mixins: [ListenMixin]
+
+    getInitialState: ->
+      rows: ExampleStore.getRows()
+      meta: ExampleStore.getMeta()
+
+    componentWillMount: ->
+      @listenTo ExampleStore
+
+    componentDidMount: ->
+      ExampleActions.getExampleData()
+
+    onStoreChange: ->
+      if this.isMounted()
+        @setState
+          rows: ExampleStore.getRows()
+          meta: ExampleStore.getMeta()
+
+    componentWillUnmount: ->
+      @stopListening ExampleStore
+
+    render: ->
+      <div className="page-wrap">
+          <header>
+            <strong> {@state.title} </strong>
+          <header>
+            <ReactExampleTable
+              rows={@state.rows},
+              meta={@state.meta}
+            />
+      </div>

samples/FORTRAN/sample1.f

@@ -0,0 +1,25 @@
+c comment
+* comment
+
+      program main
+
+      end
+
+      subroutine foo( i, x, b )
+      INTEGER            i
+      REAL               x
+      LOGICAL            b
+
+      if( i.ne.0 ) then
+         call bar( -i )
+      end if
+
+      return
+      end
+
+      double complex function baz()
+
+      baz = (0.0d0,0.0d0)
+
+      return 
+      end

samples/FORTRAN/sample1.for

@@ -0,0 +1,25 @@
+c comment
+* comment
+
+      program main
+
+      end
+
+      subroutine foo( i, x, b )
+      INTEGER            i
+      REAL               x
+      LOGICAL            b
+
+      if( i.ne.0 ) then
+         call bar( -i )
+      end if
+
+      return
+      end
+
+      double complex function baz()
+
+      baz = (0.0d0,0.0d0)
+
+      return 
+      end

samples/FORTRAN/sample2.f

@@ -0,0 +1,25 @@
+      PROGRAM MAIN
+
+      END
+
+C comment
+* comment
+
+      SUBROUTINE foo( i, x, b )
+      INTEGER            i
+      REAL               x
+      LOGICAL            b
+
+      IF( i.NE.0 ) THEN
+         CALL bar( -i )
+      END IF
+
+      RETURN
+      END
+
+      DOUBLE COMPLEX FUNCTION baz()
+
+      baz = (0.0d0,0.0d0)
+
+      RETURN 
+      END

samples/FORTRAN/sample3.F

@@ -0,0 +1,25 @@
+c comment
+* comment
+
+      program main
+
+      end
+
+      subroutine foo( i, x, b )
+      INTEGER            i
+      REAL               x
+      LOGICAL            b
+
+      if( i.ne.0 ) then
+         call bar( -i )
+      end if
+
+      return
+      end
+
+      double complex function baz()
+
+      baz = (0.0d0,0.0d0)
+
+      return 
+      end

samples/Forth/core.f

@@ -0,0 +1,252 @@
+: immediate   lastxt @ dup c@ negate swap c! ;
+
+: \   source nip >in ! ; immediate \ Copyright 2004, 2012 Lars Brinkhoff
+
+: char \ ( "word" -- char )
+    bl-word here 1+ c@ ;
+
+: ahead  here 0 , ;
+
+: resolve   here swap ! ;
+
+: '   bl-word here find 0branch [ ahead ] exit [ resolve ] 0 ;
+
+: postpone-nonimmediate   [ ' literal , ' compile, ] literal , ;
+
+: create   dovariable_code header, reveal ;
+
+create postponers
+    ' postpone-nonimmediate ,
+    ' abort ,
+    ' , ,
+
+: word \ ( char "<chars>string<char>" -- caddr )
+    drop bl-word here ;
+
+: postpone \ ( C: "word" -- )
+    bl word find 1+ cells  postponers + @ execute ; immediate
+
+: unresolved \ ( C: "word" -- orig )
+    postpone postpone  postpone ahead ; immediate
+
+: chars \ ( n1 -- n2 )
+    ;
+
+: else \ ( -- ) ( C: orig1 -- orig2 )
+    unresolved branch swap resolve ; immediate
+
+: if \ ( flag -- ) ( C: -- orig )
+    unresolved 0branch ; immediate
+
+: then \ ( -- ) ( C: orig -- )
+    resolve ; immediate
+
+: [char] \ ( "word" -- )
+    char  postpone literal ; immediate
+
+: (does>)   lastxt @ dodoes_code over >code ! r> swap >does ! ;
+
+: does>   postpone (does>) ; immediate
+
+: begin \ ( -- ) ( C: -- dest )
+    here ; immediate
+
+: while \ ( x -- ) ( C: dest -- orig dest )
+    unresolved 0branch swap ; immediate
+
+: repeat \ ( -- ) ( C: orig dest -- )
+    postpone branch ,  resolve ; immediate
+
+: until \ ( x -- ) ( C: dest -- )
+    postpone 0branch , ; immediate
+
+: recurse   lastxt @ compile, ; immediate
+
+: pad \ ( -- addr )
+    here 1024 + ;
+
+: parse \ ( char "string<char>" -- addr n )
+    pad >r  begin
+	source? if <source 2dup <> else 0 0 then
+    while
+	r@ c!  r> 1+ >r
+    repeat  2drop  pad r> over - ;
+
+: ( \ ( "string<paren>" -- )
+    [ char ) ] literal parse 2drop ; immediate
+    \ TODO: If necessary, refill and keep parsing.
+
+: string, ( addr n -- )
+    here over allot align  swap cmove ;
+
+: (s") ( -- addr n ) ( R: ret1 -- ret2 )
+    r> dup @ swap cell+ 2dup + aligned >r swap ;
+
+create squote   128 allot
+
+: s" ( "string<quote>" -- addr n )
+    state @ if
+	postpone (s")  [char] " parse  dup ,  string,
+    else
+	[char] " parse  >r squote r@ cmove  squote r>
+    then ; immediate
+
+: (abort") ( ... addr n -- ) ( R: ... -- )
+    cr type cr abort ;
+
+: abort" ( ... x "string<quote>" -- ) ( R: ... -- )
+    postpone if  postpone s"  postpone (abort")  postpone then ; immediate
+
+\ ----------------------------------------------------------------------
+
+( Core words. )
+
+\ TODO: #
+\ TODO: #>
+\ TODO: #s
+
+: and  ( x y -- x&y )   nand invert ;
+
+: *   1 2>r 0 swap begin r@ while
+         r> r> swap 2dup dup + 2>r and if swap over + swap then dup +
+      repeat r> r> 2drop drop ;
+
+\ TODO: */mod
+
+: +loop ( -- ) ( C: nest-sys -- )
+    postpone (+loop)  postpone 0branch  ,  postpone unloop ; immediate
+
+: space   bl emit ;
+
+: ?.-  dup 0 < if [char] - emit negate then ;
+
+: digit   [char] 0 + emit ;
+
+: (.)   base @ /mod  ?dup if recurse then  digit ;
+
+: ." ( "string<quote>" -- )   postpone s"  postpone type ; immediate
+
+: . ( x -- )   ?.- (.) space ;
+
+: postpone-number ( caddr -- )
+    0 0 rot count >number dup 0= if
+	2drop nip
+	postpone (literal)  postpone (literal)  postpone ,
+	postpone literal  postpone ,
+    else
+	." Undefined: " type cr abort
+    then ;
+
+' postpone-number  postponers cell+  !
+
+: / ( x y -- x/y )   /mod nip ;
+
+: 0< ( n -- flag )   0 < ;
+
+: 1- ( n -- n-1 )   -1 + ;
+
+: 2! ( x1 x2 addr -- )   swap over ! cell+ ! ;
+
+: 2* ( n -- 2n )   dup + ;
+
+\ Kernel: 2/
+
+: 2@ ( addr -- x1 x2 )   dup cell+ @ swap @ ;
+
+\ Kernel: 2drop
+\ Kernel: 2dup
+
+\ TODO: 2over ( x1 x2 x3 x4 -- x1 x2 x3 x4 x1 x2 )
+\           3 pick 3 pick ;
+
+\ TODO: 2swap
+
+\ TODO: <#
+
+: abs ( n -- |n| )
+    dup 0< if negate then ;
+
+\ TODO: accept
+
+: c, ( n -- )
+    here c!  1 chars allot ;
+
+: char+ ( n1 -- n2 )
+    1+ ;
+
+: constant   create , does> @ ;
+
+: decimal ( -- )
+    10 base ! ;
+
+: depth ( -- n )
+    data_stack 100 cells +  'SP @  - /cell /  2 - ;
+
+: do ( n1 n2 -- ) ( R: -- loop-sys ) ( C: -- do-sys )
+    postpone 2>r  here ; immediate
+
+\ TODO: environment?
+\ TODO: evaluate
+\ TODO: fill
+\ TODO: fm/mod )
+\ TODO: hold
+
+: j ( -- x1 ) ( R: x1 x2 x3 -- x1 x2 x3 )
+    'RP @ 3 cells + @ ;
+
+\ TODO: leave
+
+: loop ( -- ) ( C: nest-sys -- )
+    postpone 1  postpone (+loop)
+    postpone 0branch  ,
+    postpone unloop ; immediate
+
+: lshift   begin ?dup while 1- swap dup + swap repeat ;
+
+: rshift   1 begin over while dup + swap 1- swap repeat nip
+           2>r 0 1 begin r@ while
+              r> r> 2dup swap dup + 2>r and if swap over + swap then dup +
+           repeat r> r> 2drop drop ;
+
+: max ( x y -- max[x,y] )
+    2dup > if drop else nip then ;
+
+\ Kernel: min
+\ TODO:   mod
+\ TODO:   move
+
+: (quit) ( R: ... -- )
+    return_stack 100 cells + 'RP !
+    0 'source-id !  tib ''source !  #tib ''#source !
+    postpone [
+    begin
+	refill
+    while
+	interpret  state @ 0= if ." ok" cr then
+    repeat
+    bye ;
+
+' (quit)  ' quit >body cell+  !
+
+\ TODO: s>d
+\ TODO: sign
+\ TODO: sm/rem
+
+: spaces ( n -- )
+    0 do space loop ;
+
+\ TODO: u.
+
+: signbit ( -- n )   -1 1 rshift invert ;
+
+: xor ( x y -- x^y )    2dup nand >r r@ nand swap r> nand nand ;
+
+: u<  ( x y -- flag )  signbit xor swap signbit xor > ;
+
+\ TODO: um/mod
+
+: variable ( "word" -- )
+    create /cell allot ;
+
+: ['] \ ( C: "word" -- )
+    ' postpone literal ; immediate

samples/Forth/core.for

@@ -0,0 +1,252 @@
+: immediate   lastxt @ dup c@ negate swap c! ;
+
+: \   source nip >in ! ; immediate \ Copyright 2004, 2012 Lars Brinkhoff
+
+: char \ ( "word" -- char )
+    bl-word here 1+ c@ ;
+
+: ahead  here 0 , ;
+
+: resolve   here swap ! ;
+
+: '   bl-word here find 0branch [ ahead ] exit [ resolve ] 0 ;
+
+: postpone-nonimmediate   [ ' literal , ' compile, ] literal , ;
+
+: create   dovariable_code header, reveal ;
+
+create postponers
+    ' postpone-nonimmediate ,
+    ' abort ,
+    ' , ,
+
+: word \ ( char "<chars>string<char>" -- caddr )
+    drop bl-word here ;
+
+: postpone \ ( C: "word" -- )
+    bl word find 1+ cells  postponers + @ execute ; immediate
+
+: unresolved \ ( C: "word" -- orig )
+    postpone postpone  postpone ahead ; immediate
+
+: chars \ ( n1 -- n2 )
+    ;
+
+: else \ ( -- ) ( C: orig1 -- orig2 )
+    unresolved branch swap resolve ; immediate
+
+: if \ ( flag -- ) ( C: -- orig )
+    unresolved 0branch ; immediate
+
+: then \ ( -- ) ( C: orig -- )
+    resolve ; immediate
+
+: [char] \ ( "word" -- )
+    char  postpone literal ; immediate
+
+: (does>)   lastxt @ dodoes_code over >code ! r> swap >does ! ;
+
+: does>   postpone (does>) ; immediate
+
+: begin \ ( -- ) ( C: -- dest )
+    here ; immediate
+
+: while \ ( x -- ) ( C: dest -- orig dest )
+    unresolved 0branch swap ; immediate
+
+: repeat \ ( -- ) ( C: orig dest -- )
+    postpone branch ,  resolve ; immediate
+
+: until \ ( x -- ) ( C: dest -- )
+    postpone 0branch , ; immediate
+
+: recurse   lastxt @ compile, ; immediate
+
+: pad \ ( -- addr )
+    here 1024 + ;
+
+: parse \ ( char "string<char>" -- addr n )
+    pad >r  begin
+	source? if <source 2dup <> else 0 0 then
+    while
+	r@ c!  r> 1+ >r
+    repeat  2drop  pad r> over - ;
+
+: ( \ ( "string<paren>" -- )
+    [ char ) ] literal parse 2drop ; immediate
+    \ TODO: If necessary, refill and keep parsing.
+
+: string, ( addr n -- )
+    here over allot align  swap cmove ;
+
+: (s") ( -- addr n ) ( R: ret1 -- ret2 )
+    r> dup @ swap cell+ 2dup + aligned >r swap ;
+
+create squote   128 allot
+
+: s" ( "string<quote>" -- addr n )
+    state @ if
+	postpone (s")  [char] " parse  dup ,  string,
+    else
+	[char] " parse  >r squote r@ cmove  squote r>
+    then ; immediate
+
+: (abort") ( ... addr n -- ) ( R: ... -- )
+    cr type cr abort ;
+
+: abort" ( ... x "string<quote>" -- ) ( R: ... -- )
+    postpone if  postpone s"  postpone (abort")  postpone then ; immediate
+
+\ ----------------------------------------------------------------------
+
+( Core words. )
+
+\ TODO: #
+\ TODO: #>
+\ TODO: #s
+
+: and  ( x y -- x&y )   nand invert ;
+
+: *   1 2>r 0 swap begin r@ while
+         r> r> swap 2dup dup + 2>r and if swap over + swap then dup +
+      repeat r> r> 2drop drop ;
+
+\ TODO: */mod
+
+: +loop ( -- ) ( C: nest-sys -- )
+    postpone (+loop)  postpone 0branch  ,  postpone unloop ; immediate
+
+: space   bl emit ;
+
+: ?.-  dup 0 < if [char] - emit negate then ;
+
+: digit   [char] 0 + emit ;
+
+: (.)   base @ /mod  ?dup if recurse then  digit ;
+
+: ." ( "string<quote>" -- )   postpone s"  postpone type ; immediate
+
+: . ( x -- )   ?.- (.) space ;
+
+: postpone-number ( caddr -- )
+    0 0 rot count >number dup 0= if
+	2drop nip
+	postpone (literal)  postpone (literal)  postpone ,
+	postpone literal  postpone ,
+    else
+	." Undefined: " type cr abort
+    then ;
+
+' postpone-number  postponers cell+  !
+
+: / ( x y -- x/y )   /mod nip ;
+
+: 0< ( n -- flag )   0 < ;
+
+: 1- ( n -- n-1 )   -1 + ;
+
+: 2! ( x1 x2 addr -- )   swap over ! cell+ ! ;
+
+: 2* ( n -- 2n )   dup + ;
+
+\ Kernel: 2/
+
+: 2@ ( addr -- x1 x2 )   dup cell+ @ swap @ ;
+
+\ Kernel: 2drop
+\ Kernel: 2dup
+
+\ TODO: 2over ( x1 x2 x3 x4 -- x1 x2 x3 x4 x1 x2 )
+\           3 pick 3 pick ;
+
+\ TODO: 2swap
+
+\ TODO: <#
+
+: abs ( n -- |n| )
+    dup 0< if negate then ;
+
+\ TODO: accept
+
+: c, ( n -- )
+    here c!  1 chars allot ;
+
+: char+ ( n1 -- n2 )
+    1+ ;
+
+: constant   create , does> @ ;
+
+: decimal ( -- )
+    10 base ! ;
+
+: depth ( -- n )
+    data_stack 100 cells +  'SP @  - /cell /  2 - ;
+
+: do ( n1 n2 -- ) ( R: -- loop-sys ) ( C: -- do-sys )
+    postpone 2>r  here ; immediate
+
+\ TODO: environment?
+\ TODO: evaluate
+\ TODO: fill
+\ TODO: fm/mod )
+\ TODO: hold
+
+: j ( -- x1 ) ( R: x1 x2 x3 -- x1 x2 x3 )
+    'RP @ 3 cells + @ ;
+
+\ TODO: leave
+
+: loop ( -- ) ( C: nest-sys -- )
+    postpone 1  postpone (+loop)
+    postpone 0branch  ,
+    postpone unloop ; immediate
+
+: lshift   begin ?dup while 1- swap dup + swap repeat ;
+
+: rshift   1 begin over while dup + swap 1- swap repeat nip
+           2>r 0 1 begin r@ while
+              r> r> 2dup swap dup + 2>r and if swap over + swap then dup +
+           repeat r> r> 2drop drop ;
+
+: max ( x y -- max[x,y] )
+    2dup > if drop else nip then ;
+
+\ Kernel: min
+\ TODO:   mod
+\ TODO:   move
+
+: (quit) ( R: ... -- )
+    return_stack 100 cells + 'RP !
+    0 'source-id !  tib ''source !  #tib ''#source !
+    postpone [
+    begin
+	refill
+    while
+	interpret  state @ 0= if ." ok" cr then
+    repeat
+    bye ;
+
+' (quit)  ' quit >body cell+  !
+
+\ TODO: s>d
+\ TODO: sign
+\ TODO: sm/rem
+
+: spaces ( n -- )
+    0 do space loop ;
+
+\ TODO: u.
+
+: signbit ( -- n )   -1 1 rshift invert ;
+
+: xor ( x y -- x^y )    2dup nand >r r@ nand swap r> nand nand ;
+
+: u<  ( x y -- flag )  signbit xor swap signbit xor > ;
+
+\ TODO: um/mod
+
+: variable ( "word" -- )
+    create /cell allot ;
+
+: ['] \ ( C: "word" -- )
+    ' postpone literal ; immediate

samples/Forth/core1.F

@@ -0,0 +1,252 @@
+: immediate   lastxt @ dup c@ negate swap c! ;
+
+: \   source nip >in ! ; immediate \ Copyright 2004, 2012 Lars Brinkhoff
+
+: char \ ( "word" -- char )
+    bl-word here 1+ c@ ;
+
+: ahead  here 0 , ;
+
+: resolve   here swap ! ;
+
+: '   bl-word here find 0branch [ ahead ] exit [ resolve ] 0 ;
+
+: postpone-nonimmediate   [ ' literal , ' compile, ] literal , ;
+
+: create   dovariable_code header, reveal ;
+
+create postponers
+    ' postpone-nonimmediate ,
+    ' abort ,
+    ' , ,
+
+: word \ ( char "<chars>string<char>" -- caddr )
+    drop bl-word here ;
+
+: postpone \ ( C: "word" -- )
+    bl word find 1+ cells  postponers + @ execute ; immediate
+
+: unresolved \ ( C: "word" -- orig )
+    postpone postpone  postpone ahead ; immediate
+
+: chars \ ( n1 -- n2 )
+    ;
+
+: else \ ( -- ) ( C: orig1 -- orig2 )
+    unresolved branch swap resolve ; immediate
+
+: if \ ( flag -- ) ( C: -- orig )
+    unresolved 0branch ; immediate
+
+: then \ ( -- ) ( C: orig -- )
+    resolve ; immediate
+
+: [char] \ ( "word" -- )
+    char  postpone literal ; immediate
+
+: (does>)   lastxt @ dodoes_code over >code ! r> swap >does ! ;
+
+: does>   postpone (does>) ; immediate
+
+: begin \ ( -- ) ( C: -- dest )
+    here ; immediate
+
+: while \ ( x -- ) ( C: dest -- orig dest )
+    unresolved 0branch swap ; immediate
+
+: repeat \ ( -- ) ( C: orig dest -- )
+    postpone branch ,  resolve ; immediate
+
+: until \ ( x -- ) ( C: dest -- )
+    postpone 0branch , ; immediate
+
+: recurse   lastxt @ compile, ; immediate
+
+: pad \ ( -- addr )
+    here 1024 + ;
+
+: parse \ ( char "string<char>" -- addr n )
+    pad >r  begin
+	source? if <source 2dup <> else 0 0 then
+    while
+	r@ c!  r> 1+ >r
+    repeat  2drop  pad r> over - ;
+
+: ( \ ( "string<paren>" -- )
+    [ char ) ] literal parse 2drop ; immediate
+    \ TODO: If necessary, refill and keep parsing.
+
+: string, ( addr n -- )
+    here over allot align  swap cmove ;
+
+: (s") ( -- addr n ) ( R: ret1 -- ret2 )
+    r> dup @ swap cell+ 2dup + aligned >r swap ;
+
+create squote   128 allot
+
+: s" ( "string<quote>" -- addr n )
+    state @ if
+	postpone (s")  [char] " parse  dup ,  string,
+    else
+	[char] " parse  >r squote r@ cmove  squote r>
+    then ; immediate
+
+: (abort") ( ... addr n -- ) ( R: ... -- )
+    cr type cr abort ;
+
+: abort" ( ... x "string<quote>" -- ) ( R: ... -- )
+    postpone if  postpone s"  postpone (abort")  postpone then ; immediate
+
+\ ----------------------------------------------------------------------
+
+( Core words. )
+
+\ TODO: #
+\ TODO: #>
+\ TODO: #s
+
+: and  ( x y -- x&y )   nand invert ;
+
+: *   1 2>r 0 swap begin r@ while
+         r> r> swap 2dup dup + 2>r and if swap over + swap then dup +
+      repeat r> r> 2drop drop ;
+
+\ TODO: */mod
+
+: +loop ( -- ) ( C: nest-sys -- )
+    postpone (+loop)  postpone 0branch  ,  postpone unloop ; immediate
+
+: space   bl emit ;
+
+: ?.-  dup 0 < if [char] - emit negate then ;
+
+: digit   [char] 0 + emit ;
+
+: (.)   base @ /mod  ?dup if recurse then  digit ;
+
+: ." ( "string<quote>" -- )   postpone s"  postpone type ; immediate
+
+: . ( x -- )   ?.- (.) space ;
+
+: postpone-number ( caddr -- )
+    0 0 rot count >number dup 0= if
+	2drop nip
+	postpone (literal)  postpone (literal)  postpone ,
+	postpone literal  postpone ,
+    else
+	." Undefined: " type cr abort
+    then ;
+
+' postpone-number  postponers cell+  !
+
+: / ( x y -- x/y )   /mod nip ;
+
+: 0< ( n -- flag )   0 < ;
+
+: 1- ( n -- n-1 )   -1 + ;
+
+: 2! ( x1 x2 addr -- )   swap over ! cell+ ! ;
+
+: 2* ( n -- 2n )   dup + ;
+
+\ Kernel: 2/
+
+: 2@ ( addr -- x1 x2 )   dup cell+ @ swap @ ;
+
+\ Kernel: 2drop
+\ Kernel: 2dup
+
+\ TODO: 2over ( x1 x2 x3 x4 -- x1 x2 x3 x4 x1 x2 )
+\           3 pick 3 pick ;
+
+\ TODO: 2swap
+
+\ TODO: <#
+
+: abs ( n -- |n| )
+    dup 0< if negate then ;
+
+\ TODO: accept
+
+: c, ( n -- )
+    here c!  1 chars allot ;
+
+: char+ ( n1 -- n2 )
+    1+ ;
+
+: constant   create , does> @ ;
+
+: decimal ( -- )
+    10 base ! ;
+
+: depth ( -- n )
+    data_stack 100 cells +  'SP @  - /cell /  2 - ;
+
+: do ( n1 n2 -- ) ( R: -- loop-sys ) ( C: -- do-sys )
+    postpone 2>r  here ; immediate
+
+\ TODO: environment?
+\ TODO: evaluate
+\ TODO: fill
+\ TODO: fm/mod )
+\ TODO: hold
+
+: j ( -- x1 ) ( R: x1 x2 x3 -- x1 x2 x3 )
+    'RP @ 3 cells + @ ;
+
+\ TODO: leave
+
+: loop ( -- ) ( C: nest-sys -- )
+    postpone 1  postpone (+loop)
+    postpone 0branch  ,
+    postpone unloop ; immediate
+
+: lshift   begin ?dup while 1- swap dup + swap repeat ;
+
+: rshift   1 begin over while dup + swap 1- swap repeat nip
+           2>r 0 1 begin r@ while
+              r> r> 2dup swap dup + 2>r and if swap over + swap then dup +
+           repeat r> r> 2drop drop ;
+
+: max ( x y -- max[x,y] )
+    2dup > if drop else nip then ;
+
+\ Kernel: min
+\ TODO:   mod
+\ TODO:   move
+
+: (quit) ( R: ... -- )
+    return_stack 100 cells + 'RP !
+    0 'source-id !  tib ''source !  #tib ''#source !
+    postpone [
+    begin
+	refill
+    while
+	interpret  state @ 0= if ." ok" cr then
+    repeat
+    bye ;
+
+' (quit)  ' quit >body cell+  !
+
+\ TODO: s>d
+\ TODO: sign
+\ TODO: sm/rem
+
+: spaces ( n -- )
+    0 do space loop ;
+
+\ TODO: u.
+
+: signbit ( -- n )   -1 1 rshift invert ;
+
+: xor ( x y -- x^y )    2dup nand >r r@ nand swap r> nand nand ;
+
+: u<  ( x y -- flag )  signbit xor swap signbit xor > ;
+
+\ TODO: um/mod
+
+: variable ( "word" -- )
+    create /cell allot ;
+
+: ['] \ ( C: "word" -- )
+    ' postpone literal ; immediate

samples/HTML/example.xht

@@ -0,0 +1,17 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml">
+    <head>
+        <title>This is a XHTML sample file</title>
+        <style type="text/css"><![CDATA[
+            #example {
+                background-color: yellow;
+            }
+        ]]></style>
+    </head>
+    <body>
+        <div id="example">
+            Just a simple <strong>XHTML</strong> test page.
+        </div>
+    </body>
+</html>
+

samples/JavaScript/empty.js

@@ -1,3 +0,0 @@
-(function() {
-
-}).call(this);

samples/Maven POM/filenames/pom.xml

@@ -0,0 +1,207 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+	xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
+	<modelVersion>4.0.0</modelVersion>
+	<groupId>renpengben</groupId>
+	<artifactId>spring4mvc-jpa</artifactId>
+	<packaging>war</packaging>
+	<version>0.0.1-SNAPSHOT</version>
+	<name>spring4mvc-jpa Maven Webapp</name>
+
+	<url>https://renpengben.github.io</url>
+
+	<description>spring4mvc-jpa</description>
+
+	<properties>
+		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
+		<java.version>1.7</java.version>
+		<junit.version>4.11</junit.version>
+		<slf4j.version>1.7.7</slf4j.version>
+		<log4j.version>1.2.17</log4j.version>
+
+		<spring.version>4.0.5.RELEASE</spring.version>
+		<spring.data.jpa.version>1.6.0.RELEASE</spring.data.jpa.version>
+		<cglib.version>2.1_3</cglib.version>
+
+		<mysql.version>5.1.31</mysql.version>
+		<hibernate.version>4.3.5.Final</hibernate.version>
+		<hibernate-validator.version>5.1.1.Final</hibernate-validator.version>
+		<druid-version>1.0.6</druid-version>
+
+	</properties>
+
+
+	<dependencies>
+
+		<dependency>
+			<groupId>junit</groupId>
+			<artifactId>junit</artifactId>
+			<version>${junit.version}</version>
+			<scope>test</scope>
+		</dependency>
+
+		<dependency>
+			<groupId>org.slf4j</groupId>
+			<artifactId>slf4j-api</artifactId>
+			<version>${slf4j.version}</version>
+		</dependency>
+		<dependency>
+			<groupId>org.slf4j</groupId>
+			<artifactId>slf4j-log4j12</artifactId>
+			<version>${slf4j.version}</version>
+		</dependency>
+		<dependency>
+			<groupId>log4j</groupId>
+			<artifactId>log4j</artifactId>
+			<version>${log4j.version}</version>
+		</dependency>
+
+
+		<!-- Spring -->
+		<dependency>
+			<groupId>org.springframework</groupId>
+			<artifactId>spring-core</artifactId>
+			<version>${spring.version}</version>
+			<exclusions>
+				<exclusion>
+					<groupId>commons-logging</groupId>
+					<artifactId>commons-logging</artifactId>
+				</exclusion>
+			</exclusions>
+		</dependency>
+
+		<dependency>
+			<groupId>org.springframework</groupId>
+			<artifactId>spring-beans</artifactId>
+			<version>${spring.version}</version>
+		</dependency>
+		<dependency>
+			<groupId>org.springframework</groupId>
+			<artifactId>spring-context</artifactId>
+			<version>${spring.version}</version>
+		</dependency>
+
+		<dependency>
+			<groupId>org.springframework</groupId>
+			<artifactId>spring-aop</artifactId>
+			<version>${spring.version}</version>
+		</dependency>
+
+		<dependency>
+			<groupId>org.springframework</groupId>
+			<artifactId>spring-expression</artifactId>
+			<version>${spring.version}</version>
+		</dependency>
+		<dependency>
+			<groupId>org.springframework</groupId>
+			<artifactId>spring-tx</artifactId>
+			<version>${spring.version}</version>
+		</dependency>
+
+
+		<dependency>
+			<groupId>org.springframework</groupId>
+			<artifactId>spring-aspects</artifactId>
+			<version>${spring.version}</version>
+		</dependency>
+		<dependency>
+			<groupId>org.springframework</groupId>
+			<artifactId>spring-context-support</artifactId>
+			<version>${spring.version}</version>
+		</dependency>
+		<dependency>
+			<groupId>org.springframework</groupId>
+			<artifactId>spring-jdbc</artifactId>
+			<version>${spring.version}</version>
+		</dependency>
+		<dependency>
+			<groupId>org.springframework</groupId>
+			<artifactId>spring-orm</artifactId>
+			<version>${spring.version}</version>
+		</dependency>
+
+		<dependency>
+			<groupId>org.springframework</groupId>
+			<artifactId>spring-web</artifactId>
+			<version>${spring.version}</version>
+		</dependency>
+		<dependency>
+			<groupId>org.springframework</groupId>
+			<artifactId>spring-webmvc</artifactId>
+			<version>${spring.version}</version>
+		</dependency>
+		<dependency>
+			<groupId>org.springframework</groupId>
+			<artifactId>spring-test</artifactId>
+			<version>${spring.version}</version>
+			<scope>test</scope>
+		</dependency>
+
+		<dependency>
+			<groupId>org.springframework.data</groupId>
+			<artifactId>spring-data-jpa</artifactId>
+			<version>${spring.data.jpa.version}</version>
+			<exclusions>
+				<exclusion>
+					<artifactId>junit-dep</artifactId>
+					<groupId>junit</groupId>
+				</exclusion>
+			</exclusions>
+		</dependency>
+		<dependency>
+			<groupId>cglib</groupId>
+			<artifactId>cglib-nodep</artifactId>
+			<version>${cglib.version}</version>
+		</dependency>
+
+
+
+		<!-- JPA -->
+
+		<dependency>
+			<groupId>org.hibernate</groupId>
+			<artifactId>hibernate-core</artifactId>
+			<version>${hibernate.version}</version>
+		</dependency>
+		<dependency>
+			<groupId>org.hibernate</groupId>
+			<artifactId>hibernate-entitymanager</artifactId>
+			<version>${hibernate.version}</version>
+		</dependency>
+		<dependency>
+			<groupId>org.hibernate</groupId>
+			<artifactId>hibernate-validator</artifactId>
+			<version>${hibernate-validator.version}</version>
+			<scope>compile</scope>
+
+		</dependency>
+
+
+		<dependency>
+			<groupId>mysql</groupId>
+			<artifactId>mysql-connector-java</artifactId>
+			<version>${mysql.version}</version>
+			<scope>runtime</scope>
+		</dependency>
+		<dependency>
+			<groupId>com.alibaba</groupId>
+			<artifactId>druid</artifactId>
+			<version>${druid-version}</version>
+		</dependency>
+
+
+	</dependencies>
+	<build>
+		<plugins>
+			<plugin>
+				<groupId>org.apache.maven.plugins</groupId>
+				<artifactId>maven-compiler-plugin</artifactId>
+				<version>2.0.2</version>
+				<configuration>
+					<source>1.7</source>
+					<target>1.7</target>
+				</configuration>
+			</plugin>
+		</plugins>
+	</build>
+</project>

samples/Ruby/filenames/Gemfile.lock

@@ -0,0 +1,42 @@
+PATH
+  remote: .
+  specs:
+    github-linguist (4.0.1)
+      charlock_holmes (~> 0.7.3)
+      escape_utils (~> 1.0.1)
+      mime-types (>= 1.19)
+      rugged (~> 0.22.0b1)
+    github-linguist-grammars (4.0.1)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    charlock_holmes (0.7.3)
+    coderay (1.1.0)
+    escape_utils (1.0.1)
+    metaclass (0.0.4)
+    method_source (0.8.2)
+    mime-types (2.4.3)
+    mocha (1.1.0)
+      metaclass (~> 0.0.1)
+    plist (3.1.0)
+    pry (0.10.1)
+      coderay (~> 1.1.0)
+      method_source (~> 0.8.1)
+      slop (~> 3.4)
+    rake (10.3.2)
+    rugged (0.22.0b1)
+    slop (3.6.0)
+    yajl-ruby (1.2.1)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  github-linguist!
+  github-linguist-grammars!
+  mocha
+  plist (~> 3.1)
+  pry
+  rake
+  yajl-ruby

test/test_blob.rb

@@ -193,8 +193,8 @@ class TestBlob < Test::Unit::TestCase
     assert blob("Binary/MainMenu.nib").generated?
     assert !blob("XML/project.pbxproj").generated?
 
-    # Gemfile.locks
+    # Gemfile.lock is NOT generated
-    assert blob("Gemfile.lock").generated?
+    assert !blob("Gemfile.lock").generated?
 
     # Generated .NET Docfiles
     assert blob("XML/net_docfile.xml").generated?
@@ -226,7 +226,6 @@ class TestBlob < Test::Unit::TestCase
     assert !blob("PostScript/sierpinski.ps").generated?
 
     # These examples are too basic to tell
-    assert !blob("JavaScript/empty.js").generated?
     assert !blob("JavaScript/hello.js").generated?
 
     assert blob("JavaScript/intro-old.js").generated?
@@ -298,6 +297,13 @@ class TestBlob < Test::Unit::TestCase
     assert blob("deps/http_parser/http_parser.c").vendored?
     assert blob("deps/v8/src/v8.h").vendored?
 
+    # Chart.js
+    assert blob("some/vendored/path/Chart.js").vendored?
+    assert !blob("some/vendored/path/chart.js").vendored?
+
+    # Codemirror deps
+    assert blob("codemirror/mode/blah.js").vendored?
+
     # Debian packaging
     assert blob("debian/cron.d").vendored?
 
@@ -469,4 +475,13 @@ class TestBlob < Test::Unit::TestCase
   def test_minified_files_not_safe_to_highlight
     assert !blob("JavaScript/jquery-1.6.1.min.js").safe_to_colorize?
   end
+
+  def test_empty
+    blob = Struct.new(:data) { include Linguist::BlobHelper }
+
+    assert blob.new("").empty?
+    assert blob.new(nil).empty?
+    refute blob.new(" ").empty?
+    refute blob.new("nope").empty?
+  end
 end

test/test_heuristics.rb

@@ -20,18 +20,18 @@ class TestHeuristcs < Test::Unit::TestCase
     Dir.glob("#{samples_path}/#{language_name}/#{file}")
   end
 
+  # Candidate languages = ["C++", "Objective-C"]
   def test_obj_c_by_heuristics
-    languages = ["C++", "Objective-C"]
     # Only calling out '.h' filenames as these are the ones causing issues
     all_fixtures("Objective-C", "*.h").each do |fixture|
-      results = Heuristics.disambiguate_c(fixture("Objective-C/#{File.basename(fixture)}"), languages)
+      results = Heuristics.disambiguate_c(fixture("Objective-C/#{File.basename(fixture)}"))
       assert_equal Language["Objective-C"], results.first
     end
   end
 
+  # Candidate languages = ["C++", "Objective-C"]
   def test_cpp_by_heuristics
-    languages = ["C++", "Objective-C"]
+    results = Heuristics.disambiguate_c(fixture("C++/render_adapter.cpp"))
-    results = Heuristics.disambiguate_c(fixture("C++/render_adapter.cpp"), languages)
     assert_equal Language["C++"], results.first
   end
 
@@ -41,57 +41,57 @@ class TestHeuristcs < Test::Unit::TestCase
     assert_equal Language["Objective-C"], match
   end
 
+  # Candidate languages = ["Perl", "Prolog"]
   def test_pl_prolog_by_heuristics
-    languages = ["Perl", "Prolog"]
+    results = Heuristics.disambiguate_pl(fixture("Prolog/turing.pl"))
-    results = Heuristics.disambiguate_pl(fixture("Prolog/turing.pl"), languages)
     assert_equal Language["Prolog"], results.first
   end
 
+  # Candidate languages = ["Perl", "Prolog"]
   def test_pl_perl_by_heuristics
-    languages = ["Perl", "Prolog"]
+    results = Heuristics.disambiguate_pl(fixture("Perl/perl-test.t"))
-    results = Heuristics.disambiguate_pl(fixture("Perl/perl-test.t"), languages)
     assert_equal Language["Perl"], results.first
   end
 
+  # Candidate languages = ["ECL", "Prolog"]
   def test_ecl_prolog_by_heuristics
-    languages = ["ECL", "Prolog"]
+    results = Heuristics.disambiguate_ecl(fixture("Prolog/or-constraint.ecl"))
-    results = Heuristics.disambiguate_ecl(fixture("Prolog/or-constraint.ecl"), languages)
     assert_equal Language["Prolog"], results.first
   end
 
+  # Candidate languages = ["ECL", "Prolog"]
   def test_ecl_ecl_by_heuristics
-    languages = ["ECL", "Prolog"]
+    results = Heuristics.disambiguate_ecl(fixture("ECL/sample.ecl"))
-    results = Heuristics.disambiguate_ecl(fixture("ECL/sample.ecl"), languages)
     assert_equal Language["ECL"], results.first
   end
 
+  # Candidate languages = ["IDL", "Prolog"]
   def test_pro_prolog_by_heuristics
-    languages = ["IDL", "Prolog"]
+    results = Heuristics.disambiguate_pro(fixture("Prolog/logic-problem.pro"))
-    results = Heuristics.disambiguate_pro(fixture("Prolog/logic-problem.pro"), languages)
     assert_equal Language["Prolog"], results.first
   end
 
+  # Candidate languages = ["IDL", "Prolog"]
   def test_pro_idl_by_heuristics
-    languages = ["IDL", "Prolog"]
+    results = Heuristics.disambiguate_pro(fixture("IDL/mg_acosh.pro"))
-    results = Heuristics.disambiguate_pro(fixture("IDL/mg_acosh.pro"), languages)
     assert_equal Language["IDL"], results.first
   end
 
+  # Candidate languages = ["AGS Script", "AsciiDoc"]
   def test_asc_asciidoc_by_heuristics
-    languages = ["AGS Script", "AsciiDoc"]
+    results = Heuristics.disambiguate_asc(fixture("AsciiDoc/list.asc"))
-    results = Heuristics.disambiguate_asc(fixture("AsciiDoc/list.asc"), languages)
     assert_equal Language["AsciiDoc"], results.first
   end
 
+  # Candidate languages = ["TypeScript", "XML"]
   def test_ts_typescript_by_heuristics
-    languages = ["TypeScript", "XML"]
+    results = Heuristics.disambiguate_ts(fixture("TypeScript/classes.ts"))
-    results = Heuristics.disambiguate_ts(fixture("TypeScript/classes.ts"), languages)
     assert_equal Language["TypeScript"], results.first
   end
 
+  # Candidate languages = ["TypeScript", "XML"]
   def test_ts_xml_by_heuristics
-    languages = ["TypeScript", "XML"]
+    results = Heuristics.disambiguate_ts(fixture("XML/pt_BR.xml"))
-    results = Heuristics.disambiguate_ts(fixture("XML/pt_BR.xml"), languages)
     assert_equal Language["XML"], results.first
   end
 
@@ -99,27 +99,37 @@ class TestHeuristcs < Test::Unit::TestCase
     languages = ["Common Lisp", "OpenCL"]
     languages.each do |language|
       all_fixtures(language).each do |fixture|
-        results = Heuristics.disambiguate_cl(fixture("#{language}/#{File.basename(fixture)}"), languages)
+        results = Heuristics.disambiguate_cl(fixture("#{language}/#{File.basename(fixture)}"))
         assert_equal Language[language], results.first
       end
     end
   end
 
+  def test_f_by_heuristics
+    languages = ["FORTRAN", "Forth"]
+    languages.each do |language|
+      all_fixtures(language).each do |fixture|
+        results = Heuristics.disambiguate_f(fixture("#{language}/#{File.basename(fixture)}"))
+        assert_equal Language[language], results.first
+      end
+    end
+  end
+
+  # Candidate languages = ["Hack", "PHP"]
   def test_hack_by_heuristics
-    languages = ["Hack", "PHP"]
+    results = Heuristics.disambiguate_hack(fixture("Hack/funs.php"))
-    results = Heuristics.disambiguate_hack(fixture("Hack/funs.php"), languages)
     assert_equal Language["Hack"], results.first
   end
 
+  # Candidate languages = ["Scala", "SuperCollider"]
   def test_sc_supercollider_by_heuristics
-    languages = ["Scala", "SuperCollider"]
+    results = Heuristics.disambiguate_sc(fixture("SuperCollider/WarpPreset.sc"))
-    results = Heuristics.disambiguate_sc(fixture("SuperCollider/WarpPreset.sc"), languages)
     assert_equal Language["SuperCollider"], results.first
   end
 
+  # Candidate languages = ["Scala", "SuperCollider"]
   def test_sc_scala_by_heuristics
-    languages = ["Scala", "SuperCollider"]
+    results = Heuristics.disambiguate_sc(fixture("Scala/node11.sc"))
-    results = Heuristics.disambiguate_sc(fixture("Scala/node11.sc"), languages)
     assert_equal Language["Scala"], results.first
   end
 end

test/test_language.rb

@@ -1,5 +1,6 @@
 require 'linguist/language'
 require 'test/unit'
+require 'yaml'
 
 class TestLanguage < Test::Unit::TestCase
   include Linguist
@@ -139,6 +140,7 @@ class TestLanguage < Test::Unit::TestCase
     assert_equal :programming, Language['Python'].type
     assert_equal :programming, Language['Ruby'].type
     assert_equal :programming, Language['TypeScript'].type
+    assert_equal :programming, Language['Makefile'].type
   end
 
   def test_markup
@@ -157,7 +159,6 @@ class TestLanguage < Test::Unit::TestCase
 
   def test_other
     assert_nil Language['Brainfuck'].type
-    assert_nil Language['Makefile'].type
   end
 
   def test_searchable
@@ -349,12 +350,6 @@ class TestLanguage < Test::Unit::TestCase
     assert_equal '.coffee', Language['CoffeeScript'].primary_extension
     assert_equal '.t', Language['Turing'].primary_extension
     assert_equal '.ts', Language['TypeScript'].primary_extension
-
-    # This is a nasty requirement, but there's some code in GitHub that
-    # expects this. Really want to drop this.
-    Language.all.each do |language|
-      assert language.primary_extension, "#{language} has no primary extension"
-    end
   end
 
   def test_eql
@@ -365,4 +360,15 @@ class TestLanguage < Test::Unit::TestCase
   def test_by_type
     assert !Language.by_type(:prose).nil?
   end
+
+  def test_all_languages_have_grammars
+    scopes = YAML.load(File.read(File.expand_path("../../grammars.yml", __FILE__))).values.flatten
+    missing = Language.all.reject { |language| language.tm_scope == "none" || scopes.include?(language.tm_scope) }
+    message = "The following languages' scopes are not listed in grammars.yml. Please add grammars for all new languages.\n"
+    message << "If no grammar exists for a language, mark the language with `tm_scope: none` in lib/linguist/languages.yml.\n"
+
+    width = missing.map { |language| language.name.length }.max
+    message << missing.map { |language| sprintf("%-#{width}s %s", language.name, language.tm_scope) }.sort.join("\n")
+    assert missing.empty?, message
+  end
 end

test/test_pedantic.rb

@@ -1,57 +1,30 @@
 require 'test/unit'
+require 'yaml'
 
 class TestPedantic < Test::Unit::TestCase
-  Lib = File.expand_path("../../lib/linguist", __FILE__)
+  filename = File.expand_path("../../lib/linguist/languages.yml", __FILE__)
-
+  LANGUAGES = YAML.load(File.read(filename))
-  def file(name)
-    File.read(File.join(Lib, name))
-  end
 
   def test_language_names_are_sorted
-    languages = []
+    assert_sorted LANGUAGES.keys
-    file("languages.yml").lines.each do |line|
-      if line =~ /^(\w+):$/
-        languages << $1
-      end
-    end
-    assert_sorted languages
   end
 
   def test_extensions_are_sorted
-    extensions = nil
+    LANGUAGES.each do |name, language|
-    file("languages.yml").lines.each do |line|
+      extensions = language['extensions']
-      if line =~ /^  extensions:$/
+      assert_sorted extensions[1..-1] if extensions && extensions.size > 1
-        extensions = []
-      elsif extensions && line =~ /^  - \.([\w\-\.]+)( *#.*)?$/
-        extensions << $1
-      else
-        assert_sorted extensions[1..-1] if extensions
-        extensions = nil
-      end
     end
   end
 
   def test_filenames_are_sorted
-    filenames = nil
+    LANGUAGES.each do |name, language|
-    file("languages.yml").lines.each do |line|
+      assert_sorted language['filenames'] if language['filenames']
-      if line =~ /^  filenames:$/
-        filenames = []
-      elsif filenames && line =~ /^  - \.(\w+)$/
-        filenames << $1
-      else
-        assert_sorted filenames if filenames
-        filenames = nil
-      end
     end
   end
 
   def assert_sorted(list)
-    previous = nil
+    list.each_cons(2) do |previous, item|
-    list.each do |item|
+      flunk "#{previous} should come after #{item}" if previous > item
-      if previous && previous > item
-        flunk "#{previous} should come after #{item}"
-      end
-      previous = item
     end
   end
 end

test/test_samples.rb

@@ -55,20 +55,28 @@ class TestSamples < Test::Unit::TestCase
   end
 
   # If a language extension isn't globally unique then make sure there are samples
-  def test_presence
+  Linguist::Language.all.each do |language|
-    Linguist::Language.all.each do |language|
+    define_method "test_#{language.name}_has_samples" do
-      language.all_extensions.each do |extension|
+      language.extensions.each do |extension|
-        language_matches = Language.find_by_filename("foo#{extension}")
+        language_matches = Language.find_by_extension(extension)
 
-        # If there is more than one language match for a given extension
+        # Check for samples if more than one language matches the given extension.
-        # then check that there are examples for that language with the extension
         if language_matches.length > 1
-          language_matches.each do |language|
+          language_matches.each do |match|
-            assert File.directory?("samples/#{language.name}"), "#{language.name} is missing a samples directory"
+            samples = "samples/#{match.name}/*#{extension}"
-            assert Dir.glob("samples/#{language.name}/*#{extension}").any?, "#{language.name} is missing samples for extension #{extension}"
+            assert Dir.glob(samples).any?, "Missing samples in #{samples.inspect}. See https://github.com/github/linguist/blob/master/CONTRIBUTING.md"
           end
         end
       end
+
+      language.filenames.each do |filename|
+        # Check for samples if more than one language matches the given filename
+        if Language.find_by_filename(filename).size > 1
+          sample = "samples/#{language.name}/filenames/#{filename}"
+          assert File.exists?(sample),
+            "Missing sample in #{sample.inspect}. See https://github.com/github/linguist/blob/master/CONTRIBUTING.md"
+        end
+      end
     end
   end
 end

test/test_tokenizer.rb

@@ -43,6 +43,8 @@ class TestTokenizer < Test::Unit::TestCase
     assert_equal %w(foo), tokenize("foo {- Comment -}")
     assert_equal %w(foo), tokenize("foo (* Comment *)")
     assert_equal %w(%), tokenize("2 % 10\n% Comment")
+    assert_equal %w(foo bar), tokenize("foo\n\"\"\"\nComment\n\"\"\"\nbar")
+    assert_equal %w(foo bar), tokenize("foo\n'''\nComment\n'''\nbar")
   end
 
   def test_sgml_tags