|| true so we can release with broken grammars

/cc @vmg

.gitignore

@@ -8,3 +8,6 @@ lib/linguist/samples.json
 /node_modules
 test/fixtures/ace_modes.json
 /vendor/gems/
+/tmp
+*.bundle
+*.so

.gitmodules

@@ -169,9 +169,6 @@
 [submodule "vendor/grammars/Agda.tmbundle"]
 	path = vendor/grammars/Agda.tmbundle
 	url = https://github.com/mokus0/Agda.tmbundle
-[submodule "vendor/grammars/Julia.tmbundle"]
-	path = vendor/grammars/Julia.tmbundle
-	url = https://github.com/JuliaEditorSupport/Julia.tmbundle
 [submodule "vendor/grammars/ooc.tmbundle"]
 	path = vendor/grammars/ooc.tmbundle
 	url = https://github.com/nilium/ooc.tmbundle
@@ -400,10 +397,6 @@
 [submodule "vendor/grammars/sublime_cobol"]
 	path = vendor/grammars/sublime_cobol
 	url = https://bitbucket.org/bitlang/sublime_cobol
-[submodule "vendor/grammars/ruby.tmbundle"]
-	path = vendor/grammars/ruby.tmbundle
-	url = https://github.com/aroben/ruby.tmbundle
-	branch = pl
 [submodule "vendor/grammars/IDL-Syntax"]
 	path = vendor/grammars/IDL-Syntax
 	url = https://github.com/andik/IDL-Syntax
@@ -446,9 +439,6 @@
 [submodule "vendor/grammars/sublime-golo"]
 	path = vendor/grammars/sublime-golo
 	url = https://github.com/TypeUnsafe/sublime-golo
-[submodule "vendor/grammars/JSyntax"]
-	path = vendor/grammars/JSyntax
-	url = https://github.com/bcj/JSyntax
 [submodule "vendor/grammars/TXL"]
 	path = vendor/grammars/TXL
 	url = https://github.com/MikeHoffert/Sublime-Text-TXL-syntax
@@ -569,9 +559,6 @@
 [submodule "vendor/grammars/sublime-aspectj"]
 	path = vendor/grammars/sublime-aspectj
 	url = https://github.com/pchaigno/sublime-aspectj
-[submodule "vendor/grammars/sublime-typescript"]
-	path = vendor/grammars/sublime-typescript
-	url = https://github.com/Microsoft/TypeScript-Sublime-Plugin
 [submodule "vendor/grammars/sublime-pony"]
 	path = vendor/grammars/sublime-pony
 	url = https://github.com/CausalityLtd/sublime-pony
@@ -866,3 +853,45 @@
 [submodule "vendor/grammars/language-reason"]
 	path = vendor/grammars/language-reason
 	url = https://github.com/reasonml-editor/language-reason
+[submodule "vendor/grammars/sublime-nearley"]
+	path = vendor/grammars/sublime-nearley
+	url = https://github.com/Hardmath123/sublime-nearley
+[submodule "vendor/grammars/data-weave-tmLanguage"]
+	path = vendor/grammars/data-weave-tmLanguage
+	url = https://github.com/mulesoft-labs/data-weave-tmLanguage
+[submodule "vendor/grammars/squirrel-language"]
+	path = vendor/grammars/squirrel-language
+	url = https://github.com/mathewmariani/squirrel-language
+[submodule "vendor/grammars/language-ballerina"]
+	path = vendor/grammars/language-ballerina
+	url = https://github.com/ballerinalang/plugin-vscode
+[submodule "vendor/grammars/language-yara"]
+	path = vendor/grammars/language-yara
+	url = https://github.com/blacktop/language-yara
+[submodule "vendor/grammars/language-ruby"]
+	path = vendor/grammars/language-ruby
+	url = https://github.com/atom/language-ruby
+[submodule "vendor/grammars/sublime-angelscript"]
+	path = vendor/grammars/sublime-angelscript
+	url = https://github.com/wronex/sublime-angelscript
+[submodule "vendor/grammars/TypeScript-TmLanguage"]
+	path = vendor/grammars/TypeScript-TmLanguage
+	url = https://github.com/Microsoft/TypeScript-TmLanguage
+[submodule "vendor/grammars/wdl-sublime-syntax-highlighter"]
+	path = vendor/grammars/wdl-sublime-syntax-highlighter
+	url = https://github.com/broadinstitute/wdl-sublime-syntax-highlighter
+[submodule "vendor/grammars/atom-language-julia"]
+	path = vendor/grammars/atom-language-julia
+	url = https://github.com/JuliaEditorSupport/atom-language-julia
+[submodule "vendor/grammars/language-cwl"]
+	path = vendor/grammars/language-cwl
+	url = https://github.com/manabuishii/language-cwl
+[submodule "vendor/grammars/Syntax-highlighting-for-PostCSS"]
+	path = vendor/grammars/Syntax-highlighting-for-PostCSS
+	url = https://github.com/hudochenkov/Syntax-highlighting-for-PostCSS
+[submodule "vendor/grammars/javadoc.tmbundle"]
+	path = vendor/grammars/javadoc.tmbundle
+	url = https://github.com/textmate/javadoc.tmbundle
+[submodule "vendor/grammars/JSyntax"]
+	path = vendor/grammars/JSyntax
+	url = https://github.com/tikkanz/JSyntax

.travis.yml

@@ -19,10 +19,6 @@ rvm:
   - 2.3.3
   - 2.4.0
 
-matrix:
-  allow_failures:
-  - rvm: 2.4.0
-
 notifications:
   disabled: true
 
@@ -32,3 +28,5 @@ git:
 
 cache: bundler
 dist: precise
+
+bundler_args: --without debug

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:
 
 1. Make sure that example `.yourextension` files are present in the [samples directory][samples] for each language that uses `.yourextension`.
-1. Test the performance of the Bayesian classifier with a relatively large number (1000s) of sample `.yourextension` files. (ping **@bkeepers** to help with this) to ensure we're not misclassifying files.
+1. Test the performance of the Bayesian classifier with a relatively large number (1000s) of sample `.yourextension` files. (ping **@lildude** to help with this) to ensure we're not misclassifying files.
 1. If the Bayesian classifier does a bad job with the sample `.yourextension` files then a [heuristic](https://github.com/github/linguist/blob/master/lib/linguist/heuristics.rb) may need to be written to help.
 
 
@@ -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:
 
 1. Make sure that example `.foo` files are present in the [samples directory][samples] for each language that uses `.foo`.
-1. Test the performance of the Bayesian classifier with a relatively large number (1000s) of sample `.foo` files. (ping **@bkeepers** to help with this) to ensure we're not misclassifying files.
+1. Test the performance of the Bayesian classifier with a relatively large number (1000s) of sample `.foo` files. (ping **@lildude** to help with this) to ensure we're not misclassifying files.
 1. If the Bayesian classifier does a bad job with the sample `.foo` files then a [heuristic](https://github.com/github/linguist/blob/master/lib/linguist/heuristics.rb) may need to be written to help.
 
 Remember, the goal here is to try and avoid false positives!
@@ -93,6 +93,7 @@ Linguist is maintained with :heart: by:
 - **@BenEddy** (GitHub staff)
 - **@Caged** (GitHub staff)
 - **@grantr** (GitHub staff)
+- **@kivikakk** (GitHub staff)
 - **@larsbrinkhoff**
 - **@lildude** (GitHub staff)
 - **@pchaigno**

Gemfile

@@ -1,3 +1,6 @@
 source 'https://rubygems.org'
 gemspec :name => "github-linguist"
-gem 'byebug' if RUBY_VERSION >= '2.0'
+
+group :debug do
+  gem 'byebug' if RUBY_VERSION >= '2.2'
+end

Rakefile

@@ -1,6 +1,7 @@
 require 'bundler/setup'
 require 'rake/clean'
 require 'rake/testtask'
+require 'rake/extensiontask'
 require 'yaml'
 require 'yajl'
 require 'open-uri'
@@ -10,8 +11,14 @@ task :default => :test
 
 Rake::TestTask.new
 
+gem_spec = Gem::Specification.load('github-linguist.gemspec')
+
+Rake::ExtensionTask.new('linguist', gem_spec) do |ext|
+  ext.lib_dir = File.join('lib', 'linguist')
+end
+
 # Extend test task to check for samples and fetch latest Ace modes
-task :test => [:check_samples, :fetch_ace_modes]
+task :test => [:compile, :check_samples, :fetch_ace_modes]
 
 desc "Check that we have samples.json generated"
 task :check_samples do
@@ -34,15 +41,22 @@ task :fetch_ace_modes do
   end
 end
 
-task :samples do
+task :samples => :compile do
   require 'linguist/samples'
   json = Yajl.dump(Linguist::Samples.data, :pretty => true)
   File.write 'lib/linguist/samples.json', json
 end
 
+task :flex do
+  if `flex -V` !~ /^flex \d+\.\d+\.\d+/
+    fail "flex not detected"
+  end
+  system "cd ext/linguist && flex tokenizer.l"
+end
+
 task :build_gem => :samples do
   rm_rf "grammars"
-  sh "script/convert-grammars"
+  sh "script/grammar-compiler compile -o grammars || true"
   languages = YAML.load_file("lib/linguist/languages.yml")
   File.write("lib/linguist/languages.json", Yajl.dump(languages))
   `gem build github-linguist.gemspec`

bin/git-linguist

@@ -117,9 +117,8 @@ def git_linguist(args)
   end
 
   parser.parse!(args)
-
   git_dir = `git rev-parse --git-dir`.strip
-  raise "git-linguist must be run in a Git repository (#{Dir.pwd})" unless $?.success?
+  raise "git-linguist must be run in a Git repository" unless $?.success?
   wrapper = GitLinguist.new(git_dir, commit, incremental)
 
   case args.pop
@@ -141,6 +140,10 @@ def git_linguist(args)
     $stderr.print(parser.help)
     exit 1
   end
+rescue Exception => e
+  $stderr.puts e.message
+  $stderr.puts e.backtrace
+  exit 1
 end
 
 git_linguist(ARGV)

ext/linguist/extconf.rb

@@ -0,0 +1,3 @@
+require 'mkmf'
+dir_config('linguist')
+create_makefile('linguist/linguist')

ext/linguist/lex.linguist_yy.h

@@ -0,0 +1,336 @@
+#ifndef linguist_yyHEADER_H
+#define linguist_yyHEADER_H 1
+#define linguist_yyIN_HEADER 1
+
+#line 6 "lex.linguist_yy.h"
+
+#define  YY_INT_ALIGNED short int
+
+/* A lexical scanner generated by flex */
+
+#define FLEX_SCANNER
+#define YY_FLEX_MAJOR_VERSION 2
+#define YY_FLEX_MINOR_VERSION 5
+#define YY_FLEX_SUBMINOR_VERSION 35
+#if YY_FLEX_SUBMINOR_VERSION > 0
+#define FLEX_BETA
+#endif
+
+/* First, we deal with  platform-specific or compiler-specific issues. */
+
+/* begin standard C headers. */
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <stdlib.h>
+
+/* end standard C headers. */
+
+/* flex integer type definitions */
+
+#ifndef FLEXINT_H
+#define FLEXINT_H
+
+/* C99 systems have <inttypes.h>. Non-C99 systems may or may not. */
+
+#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
+
+/* C99 says to define __STDC_LIMIT_MACROS before including stdint.h,
+ * if you want the limit (max/min) macros for int types. 
+ */
+#ifndef __STDC_LIMIT_MACROS
+#define __STDC_LIMIT_MACROS 1
+#endif
+
+#include <inttypes.h>
+typedef int8_t flex_int8_t;
+typedef uint8_t flex_uint8_t;
+typedef int16_t flex_int16_t;
+typedef uint16_t flex_uint16_t;
+typedef int32_t flex_int32_t;
+typedef uint32_t flex_uint32_t;
+typedef uint64_t flex_uint64_t;
+#else
+typedef signed char flex_int8_t;
+typedef short int flex_int16_t;
+typedef int flex_int32_t;
+typedef unsigned char flex_uint8_t; 
+typedef unsigned short int flex_uint16_t;
+typedef unsigned int flex_uint32_t;
+#endif /* ! C99 */
+
+/* Limits of integral types. */
+#ifndef INT8_MIN
+#define INT8_MIN               (-128)
+#endif
+#ifndef INT16_MIN
+#define INT16_MIN              (-32767-1)
+#endif
+#ifndef INT32_MIN
+#define INT32_MIN              (-2147483647-1)
+#endif
+#ifndef INT8_MAX
+#define INT8_MAX               (127)
+#endif
+#ifndef INT16_MAX
+#define INT16_MAX              (32767)
+#endif
+#ifndef INT32_MAX
+#define INT32_MAX              (2147483647)
+#endif
+#ifndef UINT8_MAX
+#define UINT8_MAX              (255U)
+#endif
+#ifndef UINT16_MAX
+#define UINT16_MAX             (65535U)
+#endif
+#ifndef UINT32_MAX
+#define UINT32_MAX             (4294967295U)
+#endif
+
+#endif /* ! FLEXINT_H */
+
+#ifdef __cplusplus
+
+/* The "const" storage-class-modifier is valid. */
+#define YY_USE_CONST
+
+#else	/* ! __cplusplus */
+
+/* C99 requires __STDC__ to be defined as 1. */
+#if defined (__STDC__)
+
+#define YY_USE_CONST
+
+#endif	/* defined (__STDC__) */
+#endif	/* ! __cplusplus */
+
+#ifdef YY_USE_CONST
+#define yyconst const
+#else
+#define yyconst
+#endif
+
+/* An opaque pointer. */
+#ifndef YY_TYPEDEF_YY_SCANNER_T
+#define YY_TYPEDEF_YY_SCANNER_T
+typedef void* yyscan_t;
+#endif
+
+/* For convenience, these vars (plus the bison vars far below)
+   are macros in the reentrant scanner. */
+#define yyin yyg->yyin_r
+#define yyout yyg->yyout_r
+#define yyextra yyg->yyextra_r
+#define yyleng yyg->yyleng_r
+#define yytext yyg->yytext_r
+#define yylineno (YY_CURRENT_BUFFER_LVALUE->yy_bs_lineno)
+#define yycolumn (YY_CURRENT_BUFFER_LVALUE->yy_bs_column)
+#define yy_flex_debug yyg->yy_flex_debug_r
+
+/* Size of default input buffer. */
+#ifndef YY_BUF_SIZE
+#define YY_BUF_SIZE 16384
+#endif
+
+#ifndef YY_TYPEDEF_YY_BUFFER_STATE
+#define YY_TYPEDEF_YY_BUFFER_STATE
+typedef struct yy_buffer_state *YY_BUFFER_STATE;
+#endif
+
+#ifndef YY_TYPEDEF_YY_SIZE_T
+#define YY_TYPEDEF_YY_SIZE_T
+typedef size_t yy_size_t;
+#endif
+
+#ifndef YY_STRUCT_YY_BUFFER_STATE
+#define YY_STRUCT_YY_BUFFER_STATE
+struct yy_buffer_state
+	{
+	FILE *yy_input_file;
+
+	char *yy_ch_buf;		/* input buffer */
+	char *yy_buf_pos;		/* current position in input buffer */
+
+	/* Size of input buffer in bytes, not including room for EOB
+	 * characters.
+	 */
+	yy_size_t yy_buf_size;
+
+	/* Number of characters read into yy_ch_buf, not including EOB
+	 * characters.
+	 */
+	yy_size_t yy_n_chars;
+
+	/* Whether we "own" the buffer - i.e., we know we created it,
+	 * and can realloc() it to grow it, and should free() it to
+	 * delete it.
+	 */
+	int yy_is_our_buffer;
+
+	/* Whether this is an "interactive" input source; if so, and
+	 * if we're using stdio for input, then we want to use getc()
+	 * instead of fread(), to make sure we stop fetching input after
+	 * each newline.
+	 */
+	int yy_is_interactive;
+
+	/* Whether we're considered to be at the beginning of a line.
+	 * If so, '^' rules will be active on the next match, otherwise
+	 * not.
+	 */
+	int yy_at_bol;
+
+    int yy_bs_lineno; /**< The line count. */
+    int yy_bs_column; /**< The column count. */
+    
+	/* Whether to try to fill the input buffer when we reach the
+	 * end of it.
+	 */
+	int yy_fill_buffer;
+
+	int yy_buffer_status;
+
+	};
+#endif /* !YY_STRUCT_YY_BUFFER_STATE */
+
+void linguist_yyrestart (FILE *input_file ,yyscan_t yyscanner );
+void linguist_yy_switch_to_buffer (YY_BUFFER_STATE new_buffer ,yyscan_t yyscanner );
+YY_BUFFER_STATE linguist_yy_create_buffer (FILE *file,int size ,yyscan_t yyscanner );
+void linguist_yy_delete_buffer (YY_BUFFER_STATE b ,yyscan_t yyscanner );
+void linguist_yy_flush_buffer (YY_BUFFER_STATE b ,yyscan_t yyscanner );
+void linguist_yypush_buffer_state (YY_BUFFER_STATE new_buffer ,yyscan_t yyscanner );
+void linguist_yypop_buffer_state (yyscan_t yyscanner );
+
+YY_BUFFER_STATE linguist_yy_scan_buffer (char *base,yy_size_t size ,yyscan_t yyscanner );
+YY_BUFFER_STATE linguist_yy_scan_string (yyconst char *yy_str ,yyscan_t yyscanner );
+YY_BUFFER_STATE linguist_yy_scan_bytes (yyconst char *bytes,yy_size_t len ,yyscan_t yyscanner );
+
+void *linguist_yyalloc (yy_size_t ,yyscan_t yyscanner );
+void *linguist_yyrealloc (void *,yy_size_t ,yyscan_t yyscanner );
+void linguist_yyfree (void * ,yyscan_t yyscanner );
+
+/* Begin user sect3 */
+
+#define yytext_ptr yytext_r
+
+#ifdef YY_HEADER_EXPORT_START_CONDITIONS
+#define INITIAL 0
+#define sgml 1
+#define c_comment 2
+#define xml_comment 3
+#define haskell_comment 4
+#define ocaml_comment 5
+#define python_dcomment 6
+#define python_scomment 7
+
+#endif
+
+#ifndef YY_NO_UNISTD_H
+/* Special case for "unistd.h", since it is non-ANSI. We include it way
+ * down here because we want the user's section 1 to have been scanned first.
+ * The user has a chance to override it with an option.
+ */
+#include <unistd.h>
+#endif
+
+#define YY_EXTRA_TYPE struct tokenizer_extra *
+
+int linguist_yylex_init (yyscan_t* scanner);
+
+int linguist_yylex_init_extra (YY_EXTRA_TYPE user_defined,yyscan_t* scanner);
+
+/* Accessor methods to globals.
+   These are made visible to non-reentrant scanners for convenience. */
+
+int linguist_yylex_destroy (yyscan_t yyscanner );
+
+int linguist_yyget_debug (yyscan_t yyscanner );
+
+void linguist_yyset_debug (int debug_flag ,yyscan_t yyscanner );
+
+YY_EXTRA_TYPE linguist_yyget_extra (yyscan_t yyscanner );
+
+void linguist_yyset_extra (YY_EXTRA_TYPE user_defined ,yyscan_t yyscanner );
+
+FILE *linguist_yyget_in (yyscan_t yyscanner );
+
+void linguist_yyset_in  (FILE * in_str ,yyscan_t yyscanner );
+
+FILE *linguist_yyget_out (yyscan_t yyscanner );
+
+void linguist_yyset_out  (FILE * out_str ,yyscan_t yyscanner );
+
+yy_size_t linguist_yyget_leng (yyscan_t yyscanner );
+
+char *linguist_yyget_text (yyscan_t yyscanner );
+
+int linguist_yyget_lineno (yyscan_t yyscanner );
+
+void linguist_yyset_lineno (int line_number ,yyscan_t yyscanner );
+
+/* Macros after this point can all be overridden by user definitions in
+ * section 1.
+ */
+
+#ifndef YY_SKIP_YYWRAP
+#ifdef __cplusplus
+extern "C" int linguist_yywrap (yyscan_t yyscanner );
+#else
+extern int linguist_yywrap (yyscan_t yyscanner );
+#endif
+#endif
+
+#ifndef yytext_ptr
+static void yy_flex_strncpy (char *,yyconst char *,int ,yyscan_t yyscanner);
+#endif
+
+#ifdef YY_NEED_STRLEN
+static int yy_flex_strlen (yyconst char * ,yyscan_t yyscanner);
+#endif
+
+#ifndef YY_NO_INPUT
+
+#endif
+
+/* Amount of stuff to slurp up with each read. */
+#ifndef YY_READ_BUF_SIZE
+#define YY_READ_BUF_SIZE 8192
+#endif
+
+/* Number of entries by which start-condition stack grows. */
+#ifndef YY_START_STACK_INCR
+#define YY_START_STACK_INCR 25
+#endif
+
+/* Default declaration of generated scanner - a define so the user can
+ * easily add parameters.
+ */
+#ifndef YY_DECL
+#define YY_DECL_IS_OURS 1
+
+extern int linguist_yylex (yyscan_t yyscanner);
+
+#define YY_DECL int linguist_yylex (yyscan_t yyscanner)
+#endif /* !YY_DECL */
+
+/* yy_get_previous_state - get the state just before the EOB char was reached */
+
+#undef YY_NEW_FILE
+#undef YY_FLUSH_BUFFER
+#undef yy_set_bol
+#undef yy_new_buffer
+#undef yy_set_interactive
+#undef YY_DO_BEFORE_ACTION
+
+#ifdef YY_DECL_IS_OURS
+#undef YY_DECL_IS_OURS
+#undef YY_DECL
+#endif
+
+#line 118 "tokenizer.l"
+
+
+#line 335 "lex.linguist_yy.h"
+#undef linguist_yyIN_HEADER
+#endif /* linguist_yyHEADER_H */

ext/linguist/linguist.c

@@ -0,0 +1,75 @@
+#include "ruby.h"
+#include "linguist.h"
+#include "lex.linguist_yy.h"
+
+// Anything longer is unlikely to be useful.
+#define MAX_TOKEN_LEN 32
+
+int linguist_yywrap(yyscan_t yyscanner) {
+	return 1;
+}
+
+static VALUE rb_tokenizer_extract_tokens(VALUE self, VALUE rb_data) {
+	YY_BUFFER_STATE buf;
+	yyscan_t scanner;
+	struct tokenizer_extra extra;
+	VALUE ary, s;
+	long len;
+	int r;
+
+	Check_Type(rb_data, T_STRING);
+
+	len = RSTRING_LEN(rb_data);
+	if (len > 100000)
+		len = 100000;
+
+	linguist_yylex_init_extra(&extra, &scanner);
+	buf = linguist_yy_scan_bytes(RSTRING_PTR(rb_data), (int) len, scanner);
+
+	ary = rb_ary_new();
+	do {
+		extra.type = NO_ACTION;
+		extra.token = NULL;
+		r = linguist_yylex(scanner);
+		switch (extra.type) {
+		case NO_ACTION:
+			break;
+		case REGULAR_TOKEN:
+			len = strlen(extra.token);
+			if (len <= MAX_TOKEN_LEN)
+				rb_ary_push(ary, rb_str_new(extra.token, len));
+			free(extra.token);
+			break;
+		case SHEBANG_TOKEN:
+			len = strlen(extra.token);
+			if (len <= MAX_TOKEN_LEN) {
+				s = rb_str_new2("SHEBANG#!");
+				rb_str_cat(s, extra.token, len);
+				rb_ary_push(ary, s);
+			}
+			free(extra.token);
+			break;
+		case SGML_TOKEN:
+			len = strlen(extra.token);
+			if (len <= MAX_TOKEN_LEN) {
+				s = rb_str_new(extra.token, len);
+				rb_str_cat2(s, ">");
+				rb_ary_push(ary, s);
+			}
+			free(extra.token);
+			break;
+		}
+	} while (r);
+
+	linguist_yy_delete_buffer(buf, scanner);
+	linguist_yylex_destroy(scanner);
+
+	return ary;
+}
+
+__attribute__((visibility("default"))) void Init_linguist() {
+	VALUE rb_mLinguist = rb_define_module("Linguist");
+	VALUE rb_cTokenizer = rb_define_class_under(rb_mLinguist, "Tokenizer", rb_cObject);
+
+	rb_define_method(rb_cTokenizer, "extract_tokens", rb_tokenizer_extract_tokens, 1);
+}

ext/linguist/linguist.h

@@ -0,0 +1,11 @@
+enum tokenizer_type {
+  NO_ACTION,
+  REGULAR_TOKEN,
+  SHEBANG_TOKEN,
+  SGML_TOKEN,
+};
+
+struct tokenizer_extra {
+  char *token;
+  enum tokenizer_type type;
+};

ext/linguist/tokenizer.l

@@ -0,0 +1,119 @@
+%{
+
+#include "linguist.h"
+
+#define feed_token(tok, typ) do { \
+    yyextra->token = (tok); \
+    yyextra->type = (typ); \
+  } while (0)
+
+#define eat_until_eol() do { \
+    int c; \
+    while ((c = input(yyscanner)) != '\n' && c != EOF && c); \
+    if (c == EOF || !c) \
+      return 0; \
+  } while (0)
+
+#define eat_until_unescaped(q) do { \
+    int c; \
+    while ((c = input(yyscanner)) != EOF && c) { \
+      if (c == '\n') \
+        break; \
+      if (c == '\\') { \
+        c = input(yyscanner); \
+        if (c == EOF || !c) \
+          return 0; \
+      } else if (c == q) \
+        break; \
+    } \
+    if (c == EOF || !c) \
+      return 0; \
+  } while (0)
+
+%}
+
+%option never-interactive yywrap reentrant nounput warn nodefault header-file="lex.linguist_yy.h" extra-type="struct tokenizer_extra *" prefix="linguist_yy"
+%x sgml c_comment xml_comment haskell_comment ocaml_comment python_dcomment python_scomment
+
+%%
+
+^#![ \t]*([[:alnum:]_\/]*\/)?env([ \t]+([^ \t=]*=[^ \t]*))*[ \t]+[[:alpha:]_]+ {
+    const char *off = strrchr(yytext, ' ');
+    if (!off)
+      off = yytext;
+    else
+      ++off;
+    feed_token(strdup(off), SHEBANG_TOKEN);
+    eat_until_eol();
+    return 1;
+  }
+
+^#![ \t]*[[:alpha:]_\/]+ {
+    const char *off = strrchr(yytext, '/');
+    if (!off)
+      off = yytext;
+    else
+      ++off;
+    if (strcmp(off, "env") == 0) {
+      eat_until_eol();
+    } else {
+      feed_token(strdup(off), SHEBANG_TOKEN);
+      eat_until_eol();
+      return 1;
+    }
+  }
+
+^[ \t]*(\/\/|--|\#|%|\")" ".*   { /* nothing */ }
+
+"/*"                              { BEGIN(c_comment); }
+  /* See below for xml_comment start. */
+"{-"                              { BEGIN(haskell_comment); }
+"(*"                              { BEGIN(ocaml_comment); }
+"\"\"\""                          { BEGIN(python_dcomment); }
+"'''"                             { BEGIN(python_scomment); }
+
+<c_comment,xml_comment,haskell_comment,ocaml_comment,python_dcomment,python_scomment>.|\n { /* nothing */ }
+<c_comment>"*/"                   { BEGIN(INITIAL); }
+<xml_comment>"-->"                { BEGIN(INITIAL); }
+<haskell_comment>"-}"             { BEGIN(INITIAL); }
+<ocaml_comment>"*)"               { BEGIN(INITIAL); }
+<python_dcomment>"\"\"\""         { BEGIN(INITIAL); }
+<python_scomment>"'''"            { BEGIN(INITIAL); }
+
+\"\"|''                           { /* nothing */ }
+\"                                { eat_until_unescaped('"'); }
+'                                 { eat_until_unescaped('\''); }
+(0x[0-9a-fA-F]([0-9a-fA-F]|\.)*|[0-9]([0-9]|\.)*)([uU][lL]{0,2}|([eE][-+][0-9]*)?[fFlL]*) { /* nothing */ }
+\<[[:alnum:]_!./?-]+              {
+    if (strcmp(yytext, "<!--") == 0) {
+     BEGIN(xml_comment);
+    } else {
+      feed_token(strdup(yytext), SGML_TOKEN);
+      BEGIN(sgml);
+      return 1;
+    }
+  }
+<sgml>[[:alnum:]_]+=\"            { feed_token(strndup(yytext, strlen(yytext) - 1), REGULAR_TOKEN); eat_until_unescaped('"'); return 1; }
+<sgml>[[:alnum:]_]+='             { feed_token(strndup(yytext, strlen(yytext) - 1), REGULAR_TOKEN); eat_until_unescaped('\''); return 1; }
+<sgml>[[:alnum:]_]+=[[:alnum:]_]* { feed_token(strdup(yytext), REGULAR_TOKEN); *(strchr(yyextra->token, '=') + 1) = 0; return 1; }
+<sgml>[[:alnum:]_]+               { feed_token(strdup(yytext), REGULAR_TOKEN); return 1; }
+<sgml>\>                          { BEGIN(INITIAL); }
+<sgml>.|\n                        { /* nothing */ }
+;|\{|\}|\(|\)|\[|\]               { feed_token(strdup(yytext), REGULAR_TOKEN); return 1; }
+[[:alnum:]_.@#/*]+                {
+    if (strncmp(yytext, "/*", 2) == 0) {
+      if (strlen(yytext) >= 4 && strcmp(yytext + strlen(yytext) - 2, "*/") == 0) {
+        /* nothing */
+      } else {
+        BEGIN(c_comment);
+      }
+    } else {
+      feed_token(strdup(yytext), REGULAR_TOKEN);
+      return 1;
+    }
+  }
+\<\<?|\+|\-|\*|\/|%|&&?|\|\|?     { feed_token(strdup(yytext), REGULAR_TOKEN); return 1; }
+.|\n                              { /* nothing */ }
+
+%%
+

github-linguist.gemspec

@@ -10,15 +10,17 @@ Gem::Specification.new do |s|
   s.homepage = "https://github.com/github/linguist"
   s.license  = "MIT"
 
-  s.files = Dir['lib/**/*'] + Dir['grammars/*'] + ['LICENSE']
+  s.files = Dir['lib/**/*'] + Dir['ext/**/*'] + Dir['grammars/*'] + ['LICENSE']
   s.executables = ['linguist', 'git-linguist']
+  s.extensions = ['ext/linguist/extconf.rb']
 
-  s.add_dependency 'charlock_holmes', '~> 0.7.3'
+  s.add_dependency 'charlock_holmes', '~> 0.7.5'
   s.add_dependency 'escape_utils',    '~> 1.1.0'
   s.add_dependency 'mime-types',      '>= 1.19'
   s.add_dependency 'rugged',          '>= 0.25.1'
 
   s.add_development_dependency 'minitest', '>= 5.0'
+  s.add_development_dependency 'rake-compiler', '~> 0.9'
   s.add_development_dependency 'mocha'
   s.add_development_dependency 'plist', '~>3.1'
   s.add_development_dependency 'pry'

grammars.yml

@@ -1,4 +1,3 @@
----
 https://bitbucket.org/Clams/sublimesystemverilog/get/default.tar.gz:
 - source.systemverilog
 - source.ucfconstraints
@@ -45,8 +44,6 @@ vendor/grammars/Isabelle.tmbundle:
 - source.isabelle.theory
 vendor/grammars/JSyntax:
 - source.j
-vendor/grammars/Julia.tmbundle:
-- source.julia
 vendor/grammars/Lean.tmbundle:
 - source.lean
 vendor/grammars/LiveScript.tmbundle:
@@ -130,6 +127,9 @@ vendor/grammars/SublimePuppet:
 - source.puppet
 vendor/grammars/SublimeXtend:
 - source.xtend
+vendor/grammars/Syntax-highlighting-for-PostCSS:
+- source.css.postcss.sugarss
+- source.postcss
 vendor/grammars/TLA:
 - source.tla
 vendor/grammars/TXL:
@@ -138,6 +138,11 @@ vendor/grammars/Terraform.tmLanguage:
 - source.terraform
 vendor/grammars/Textmate-Gosu-Bundle:
 - source.gosu.2
+vendor/grammars/TypeScript-TmLanguage:
+- source.ts
+- source.tsx
+- text.error-list
+- text.find-refs
 vendor/grammars/UrWeb-Language-Definition:
 - source.ur
 vendor/grammars/VBDotNetSyntax:
@@ -187,6 +192,9 @@ vendor/grammars/atom-language-1c-bsl:
 vendor/grammars/atom-language-clean:
 - source.clean
 - text.restructuredtext.clean
+vendor/grammars/atom-language-julia:
+- source.julia
+- source.julia.console
 vendor/grammars/atom-language-p4:
 - source.p4
 vendor/grammars/atom-language-perl6:
@@ -252,6 +260,8 @@ vendor/grammars/d.tmbundle:
 vendor/grammars/dartlang:
 - source.dart
 - source.yaml-ext
+vendor/grammars/data-weave-tmLanguage:
+- source.data-weave
 vendor/grammars/desktop.tmbundle:
 - source.desktop
 vendor/grammars/diff.tmbundle:
@@ -333,6 +343,8 @@ vendor/grammars/java.tmbundle:
 - source.java-properties
 - text.html.jsp
 - text.junit-test-report
+vendor/grammars/javadoc.tmbundle:
+- text.html.javadoc
 vendor/grammars/javascript-objective-j.tmbundle:
 - source.js.objj
 vendor/grammars/jflex.tmbundle:
@@ -350,6 +362,8 @@ vendor/grammars/language-asn1:
 vendor/grammars/language-babel:
 - source.js.jsx
 - source.regexp.babel
+vendor/grammars/language-ballerina:
+- source.ballerina
 vendor/grammars/language-batchfile:
 - source.batchfile
 vendor/grammars/language-blade:
@@ -377,6 +391,8 @@ vendor/grammars/language-csound:
 - source.csound-score
 vendor/grammars/language-css:
 - source.css
+vendor/grammars/language-cwl:
+- source.cwl
 vendor/grammars/language-emacs-lisp:
 - source.emacs.lisp
 vendor/grammars/language-fontforge:
@@ -394,6 +410,7 @@ vendor/grammars/language-haml:
 - text.haml
 - text.hamlc
 vendor/grammars/language-haskell:
+- annotation.liquidhaskell.haskell
 - hint.haskell
 - hint.message.haskell
 - hint.type.haskell
@@ -401,6 +418,7 @@ vendor/grammars/language-haskell:
 - source.cabal
 - source.haskell
 - source.hsc2hs
+- source.hsig
 - text.tex.latex.haskell
 vendor/grammars/language-inform7:
 - source.inform7
@@ -459,6 +477,10 @@ vendor/grammars/language-roff:
 vendor/grammars/language-rpm-spec:
 - source.changelogs.rpm-spec
 - source.rpm-spec
+vendor/grammars/language-ruby:
+- source.ruby
+- source.ruby.gemfile
+- text.html.erb
 vendor/grammars/language-shellscript:
 - source.shell
 - text.shell-session
@@ -485,6 +507,8 @@ vendor/grammars/language-yaml:
 - source.yaml
 vendor/grammars/language-yang:
 - source.yang
+vendor/grammars/language-yara:
+- source.yara
 vendor/grammars/latex.tmbundle:
 - text.bibtex
 - text.log.latex
@@ -551,7 +575,7 @@ vendor/grammars/opa.tmbundle:
 - source.opa
 vendor/grammars/openscad.tmbundle:
 - source.scad
-vendor/grammars/oz-tmbundle/Syntaxes/Oz.tmLanguage:
+vendor/grammars/oz-tmbundle:
 - source.oz
 vendor/grammars/parrot:
 - source.parrot.pir
@@ -588,9 +612,6 @@ vendor/grammars/rascal-syntax-highlighting:
 - source.rascal
 vendor/grammars/ruby-slim.tmbundle:
 - text.slim
-vendor/grammars/ruby.tmbundle:
-- source.ruby
-- text.html.erb
 vendor/grammars/sas.tmbundle:
 - source.SASLog
 - source.sas
@@ -616,6 +637,8 @@ vendor/grammars/sourcepawn:
 - source.sp
 vendor/grammars/sql.tmbundle:
 - source.sql
+vendor/grammars/squirrel-language:
+- source.nut
 vendor/grammars/st2-zonefile:
 - text.zone_file
 vendor/grammars/standard-ml.tmbundle:
@@ -623,6 +646,8 @@ vendor/grammars/standard-ml.tmbundle:
 - source.ml
 vendor/grammars/sublime-MuPAD:
 - source.mupad
+vendor/grammars/sublime-angelscript:
+- source.angelscript
 vendor/grammars/sublime-aspectj:
 - source.aspectj
 vendor/grammars/sublime-autoit:
@@ -644,6 +669,8 @@ vendor/grammars/sublime-golo:
 - source.golo
 vendor/grammars/sublime-mask:
 - source.mask
+vendor/grammars/sublime-nearley:
+- source.ne
 vendor/grammars/sublime-netlinx:
 - source.netlinx
 - source.netlinx.erb
@@ -669,11 +696,6 @@ vendor/grammars/sublime-terra:
 - source.terra
 vendor/grammars/sublime-text-ox:
 - source.ox
-vendor/grammars/sublime-typescript:
-- source.ts
-- source.tsx
-- text.error-list
-- text.find-refs
 vendor/grammars/sublime-varnish:
 - source.varnish.vcl
 vendor/grammars/sublime_cobol:
@@ -706,6 +728,8 @@ vendor/grammars/vhdl:
 - source.vhdl
 vendor/grammars/vue-syntax-highlight:
 - text.html.vue
+vendor/grammars/wdl-sublime-syntax-highlighter:
+- source.wdl
 vendor/grammars/xc.tmbundle:
 - source.xc
 vendor/grammars/xml.tmbundle:

lib/linguist/blob_helper.rb

@@ -275,10 +275,8 @@ module Linguist
           # also--importantly--without having to duplicate many (potentially
           # large) strings.
           begin
-            encoded_newlines = ["\r\n", "\r", "\n"].
-              map { |nl| nl.encode(ruby_encoding, "ASCII-8BIT").force_encoding(data.encoding) }
-
-            data.split(Regexp.union(encoded_newlines), -1)
+            
+            data.split(encoded_newlines_re, -1)
           rescue Encoding::ConverterNotFoundError
             # The data is not splittable in the detected encoding.  Assume it's
             # one big line.
@@ -289,6 +287,51 @@ module Linguist
         end
     end
 
+    def encoded_newlines_re
+      @encoded_newlines_re ||= Regexp.union(["\r\n", "\r", "\n"].
+                                              map { |nl| nl.encode(ruby_encoding, "ASCII-8BIT").force_encoding(data.encoding) })
+
+    end
+
+    def first_lines(n)
+      return lines[0...n] if defined? @lines
+      return [] unless viewable? && data
+
+      i, c = 0, 0
+      while c < n && j = data.index(encoded_newlines_re, i)
+        i = j + $&.length
+        c += 1
+      end
+      data[0...i].split(encoded_newlines_re, -1)
+    end
+
+    def last_lines(n)
+      if defined? @lines
+        if n >= @lines.length
+          @lines
+        else
+          lines[-n..-1]
+        end
+      end
+      return [] unless viewable? && data
+
+      no_eol = true
+      i, c = data.length, 0
+      k = i
+      while c < n && j = data.rindex(encoded_newlines_re, i - 1)
+        if c == 0 && j + $&.length == i
+          no_eol = false
+          n += 1
+        end
+        i = j
+        k = j + $&.length
+        c += 1
+      end
+      r = data[k..-1].split(encoded_newlines_re, -1)
+      r.pop if !no_eol
+      r
+    end
+
     # Public: Get number of lines of code
     #
     # Requires Blob#data

lib/linguist/classifier.rb

@@ -3,6 +3,8 @@ require 'linguist/tokenizer'
 module Linguist
   # Language bayesian classifier.
   class Classifier
+    CLASSIFIER_CONSIDER_BYTES = 50 * 1024
+
     # Public: Use the classifier to detect language of the blob.
     #
     # blob               - An object that quacks like a blob.
@@ -17,7 +19,7 @@ module Linguist
     # Returns an Array of Language objects, most probable first.
     def self.call(blob, possible_languages)
       language_names = possible_languages.map(&:name)
-      classify(Samples.cache, blob.data, language_names).map do |name, _|
+      classify(Samples.cache, blob.data[0...CLASSIFIER_CONSIDER_BYTES], language_names).map do |name, _|
         Language[name] # Return the actual Language objects
       end
     end

lib/linguist/file_blob.rb

@@ -23,21 +23,21 @@ module Linguist
     #
     # Returns a String like '100644'
     def mode
-      File.stat(@fullpath).mode.to_s(8)
+      @mode ||= File.stat(@fullpath).mode.to_s(8)
     end
 
     # Public: Read file contents.
     #
     # Returns a String.
     def data
-      File.read(@fullpath)
+      @data ||= File.read(@fullpath)
     end
 
     # Public: Get byte size
     #
     # Returns an Integer.
     def size
-      File.size(@fullpath)
+      @size ||= File.size(@fullpath)
     end
   end
 end

lib/linguist/generated.rb

@@ -52,6 +52,8 @@ module Linguist
     # Return true or false
     def generated?
       xcode_file? ||
+      cocoapods? ||
+      carthage_build? ||
       generated_net_designer_file? ||
       generated_net_specflow_feature_file? ||
       composer_lock? ||
@@ -95,6 +97,20 @@ module Linguist
       ['.nib', '.xcworkspacedata', '.xcuserstate'].include?(extname)
     end
 
+    # Internal: Is the blob part of Pods/, which contains dependencies not meant for humans in pull requests.
+    #
+    # Returns true or false.
+    def cocoapods?
+      !!name.match(/(^Pods|\/Pods)\//)
+    end
+
+    # Internal: Is the blob part of Carthage/Build/, which contains dependencies not meant for humans in pull requests.
+    #
+    # Returns true or false.
+    def carthage_build?
+      !!name.match(/(^|\/)Carthage\/Build\//)
+    end
+
     # Internal: Is the blob minified files?
     #
     # Consider a file minified if the average line length is

lib/linguist/heuristics.rb

@@ -1,6 +1,8 @@
 module Linguist
   # A collection of simple heuristics that can be used to better analyze languages.
   class Heuristics
+    HEURISTICS_CONSIDER_BYTES = 50 * 1024
+
     # Public: Use heuristics to detect language of the blob.
     #
     # blob               - An object that quacks like a blob.
@@ -14,7 +16,7 @@ module Linguist
     #
     # Returns an Array of languages, or empty if none matched or were inconclusive.
     def self.call(blob, candidates)
-      data = blob.data
+      data = blob.data[0...HEURISTICS_CONSIDER_BYTES]
 
       @heuristics.each do |heuristic|
         if heuristic.matches?(blob.name, candidates)
@@ -71,7 +73,25 @@ module Linguist
     end
 
     # Common heuristics
+    CPlusPlusRegex = Regexp.union(
+        /^\s*#\s*include <(cstdint|string|vector|map|list|array|bitset|queue|stack|forward_list|unordered_map|unordered_set|(i|o|io)stream)>/,
+        /^\s*template\s*</,
+        /^[ \t]*try/,
+        /^[ \t]*catch\s*\(/,
+        /^[ \t]*(class|(using[ \t]+)?namespace)\s+\w+/,
+        /^[ \t]*(private|public|protected):$/,
+        /std::\w+/)
     ObjectiveCRegex = /^\s*(@(interface|class|protocol|property|end|synchronised|selector|implementation)\b|#import\s+.+\.h[">])/
+    Perl5Regex = /\buse\s+(?:strict\b|v?5\.)/
+    Perl6Regex = /^\s*(?:use\s+v6\b|\bmodule\b|\b(?:my\s+)?class\b)/
+
+    disambiguate ".as" do |data|
+      if /^\s*(package\s+[a-z0-9_\.]+|import\s+[a-zA-Z0-9_\.]+;|class\s+[A-Za-z0-9_]+\s+extends\s+[A-Za-z0-9_]+)/.match(data)
+        Language["ActionScript"]
+      else
+        Language["AngelScript"]
+      end
+    end
 
     disambiguate ".asc" do |data|
       if /^(----[- ]BEGIN|ssh-(rsa|dss)) /.match(data)
@@ -211,8 +231,7 @@ module Linguist
     disambiguate ".h" do |data|
       if ObjectiveCRegex.match(data)
         Language["Objective-C"]
-      elsif (/^\s*#\s*include <(cstdint|string|vector|map|list|array|bitset|queue|stack|forward_list|unordered_map|unordered_set|(i|o|io)stream)>/.match(data) ||
-        /^\s*template\s*</.match(data) || /^[ \t]*try/.match(data) || /^[ \t]*catch\s*\(/.match(data) || /^[ \t]*(class|(using[ \t]+)?namespace)\s+\w+/.match(data) || /^[ \t]*(private|public|protected):$/.match(data) || /std::\w+/.match(data))
+      elsif CPlusPlusRegex.match(data)
         Language["C++"]
       end
     end
@@ -342,33 +361,25 @@ module Linguist
     disambiguate ".pl" do |data|
       if /^[^#]*:-/.match(data)
         Language["Prolog"]
-      elsif /use strict|use\s+v?5\./.match(data)
+      elsif Perl5Regex.match(data)
         Language["Perl"]
-      elsif /^(use v6|(my )?class|module)/.match(data)
+      elsif Perl6Regex.match(data)
         Language["Perl 6"]
       end
     end
 
     disambiguate ".pm" do |data|
-      if /^\s*(?:use\s+v6\s*;|(?:\bmy\s+)?class|module)\b/.match(data)
-        Language["Perl 6"]
-      elsif /\buse\s+(?:strict\b|v?5\.)/.match(data)
+      if Perl5Regex.match(data)
         Language["Perl"]
+      elsif Perl6Regex.match(data)
+        Language["Perl 6"]
       elsif /^\s*\/\* XPM \*\//.match(data)
         Language["XPM"]
       end
     end
 
-    disambiguate ".pod", "Pod", "Perl" do |data|
-      if /^=\w+\b/.match(data)
-        Language["Pod"]
-      else
-        Language["Perl"]
-      end
-    end
-
     disambiguate ".pro" do |data|
-      if /^[^#]+:-/.match(data)
+      if /^[^\[#]+:-/.match(data)
         Language["Prolog"]
       elsif data.include?("last_client=")
         Language["INI"]
@@ -450,12 +461,12 @@ module Linguist
     end
     
     disambiguate ".t" do |data|
-      if /^\s*%[ \t]+|^\s*var\s+\w+\s*:=\s*\w+/.match(data)
-        Language["Turing"]
-      elsif /^\s*(?:use\s+v6\s*;|\bmodule\b|\b(?:my\s+)?class\b)/.match(data)
-        Language["Perl 6"]
-      elsif /\buse\s+(?:strict\b|v?5\.)/.match(data)
+      if Perl5Regex.match(data)
         Language["Perl"]
+      elsif Perl6Regex.match(data)
+        Language["Perl 6"]
+      elsif /^\s*%[ \t]+|^\s*var\s+\w+\s*:=\s*\w+/.match(data)
+        Language["Turing"]
       end
     end
     
@@ -468,7 +479,7 @@ module Linguist
     end
 
     disambiguate ".ts" do |data|
-      if data.include?("<TS")
+      if /<TS\b/.match(data)
         Language["XML"]
       else
         Language["TypeScript"]
@@ -491,5 +502,14 @@ module Linguist
         Language["XML"]
       end
     end
+  
+    disambiguate ".w" do |data|
+      if (data.include?("&ANALYZE-SUSPEND _UIB-CODE-BLOCK _CUSTOM _DEFINITIONS"))
+        Language["OpenEdge ABL"]
+      elsif /^@(<|\w+\.)/.match(data)
+        Language["CWeb"]
+      end
+    end
+  
   end
 end

lib/linguist/language.rb

@@ -110,7 +110,7 @@ module Linguist
     # Returns the Language or nil if none was found.
     def self.find_by_name(name)
       return nil if !name.is_a?(String) || name.to_s.empty?
-      name && (@name_index[name.downcase] || @name_index[name.split(',').first.downcase])
+      name && (@name_index[name.downcase] || @name_index[name.split(',', 2).first.downcase])
     end
 
     # Public: Look up Language by one of its aliases.
@@ -125,7 +125,7 @@ module Linguist
     # Returns the Language or nil if none was found.
     def self.find_by_alias(name)
       return nil if !name.is_a?(String) || name.to_s.empty?
-      name && (@alias_index[name.downcase] || @alias_index[name.split(',').first.downcase])
+      name && (@alias_index[name.downcase] || @alias_index[name.split(',', 2).first.downcase])
     end
 
     # Public: Look up Languages by filename.
@@ -219,10 +219,7 @@ module Linguist
       lang = @index[name.downcase]
       return lang if lang
 
-      name = name.split(',').first
-      return nil if name.to_s.empty?
-
-      @index[name.downcase]
+      @index[name.split(',', 2).first.downcase]
     end
 
     # Public: A List of popular languages

lib/linguist/languages.yml

@@ -210,6 +210,17 @@ Alpine Abuild:
   codemirror_mode: shell
   codemirror_mime_type: text/x-sh
   language_id: 14
+AngelScript:
+  type: programming
+  color: "#C7D7DC"
+  extensions:
+  - ".as"
+  - ".angelscript"
+  tm_scope: source.angelscript
+  ace_mode: text
+  codemirror_mode: clike
+  codemirror_mime_type: text/x-c++src
+  language_id: 389477596
 Ant Build System:
   type: data
   tm_scope: text.xml.ant
@@ -221,7 +232,7 @@ Ant Build System:
   codemirror_mime_type: application/xml
   language_id: 15
 ApacheConf:
-  type: markup
+  type: data
   aliases:
   - aconf
   - apache
@@ -354,6 +365,14 @@ Awk:
   - nawk
   ace_mode: text
   language_id: 28
+Ballerina:
+  type: programming
+  extensions:
+  - ".bal"
+  tm_scope: source.ballerina
+  ace_mode: text
+  color: "#FF5000"
+  language_id: 720859680
 Batchfile:
   type: programming
   aliases:
@@ -625,8 +644,10 @@ CartoCSS:
   language_id: 53
 Ceylon:
   type: programming
+  color: "#dfa535"
   extensions:
   - ".ceylon"
+  tm_scope: source.ceylon
   ace_mode: text
   language_id: 54
 Chapel:
@@ -786,6 +807,19 @@ Common Lisp:
   codemirror_mode: commonlisp
   codemirror_mime_type: text/x-common-lisp
   language_id: 66
+Common Workflow Language:
+  alias: cwl
+  type: programming
+  ace_mode: yaml
+  codemirror_mode: yaml
+  codemirror_mime_type: text/x-yaml
+  extensions:
+  - ".cwl"
+  interpreters:
+  - cwl-runner
+  color: "#B5314C"
+  tm_scope: source.cwl
+  language_id: 988547172
 Component Pascal:
   type: programming
   color: "#B0CE4E"
@@ -855,7 +889,7 @@ Csound:
   - ".orc"
   - ".udo"
   tm_scope: source.csound
-  ace_mode: text
+  ace_mode: csound_orchestra
   language_id: 73
 Csound Document:
   type: programming
@@ -864,7 +898,7 @@ Csound Document:
   extensions:
   - ".csd"
   tm_scope: source.csound-document
-  ace_mode: text
+  ace_mode: csound_document
   language_id: 74
 Csound Score:
   type: programming
@@ -873,7 +907,7 @@ Csound Score:
   extensions:
   - ".sco"
   tm_scope: source.csound-score
-  ace_mode: text
+  ace_mode: csound_score
   language_id: 75
 Cuda:
   type: programming
@@ -986,6 +1020,14 @@ Dart:
   codemirror_mode: dart
   codemirror_mime_type: application/dart
   language_id: 87
+DataWeave:
+  type: programming
+  color: "#003a52"
+  extensions:
+  - ".dwl"
+  ace_mode: text
+  tm_scope: source.data-weave
+  language_id: 974514097
 Diff:
   type: data
   extensions:
@@ -1086,8 +1128,7 @@ EQ:
   codemirror_mime_type: text/x-csharp
   language_id: 96
 Eagle:
-  type: markup
-  color: "#814C05"
+  type: data
   extensions:
   - ".sch"
   - ".brd"
@@ -1116,6 +1157,15 @@ Ecere Projects:
   codemirror_mode: javascript
   codemirror_mime_type: application/json
   language_id: 98
+Edje Data Collection:
+  type: data
+  extensions:
+  - ".edc"
+  tm_scope: source.json
+  ace_mode: json
+  codemirror_mode: javascript
+  codemirror_mime_type: application/json
+  language_id: 342840478
 Eiffel:
   type: programming
   color: "#946d57"
@@ -1487,8 +1537,8 @@ Gerber Image:
   - ".gtp"
   - ".gts"
   interpreters:
-  - "gerbv"
-  - "gerbview"
+  - gerbv
+  - gerbview
   tm_scope: source.gerber
   ace_mode: text
   language_id: 404627610
@@ -1605,6 +1655,7 @@ GraphQL:
   type: data
   extensions:
   - ".graphql"
+  - ".gql"
   tm_scope: source.graphql
   ace_mode: text
   language_id: 139
@@ -1868,6 +1919,8 @@ INI:
   - ".prefs"
   - ".pro"
   - ".properties"
+  filenames:
+  - buildozer.spec
   tm_scope: source.ini
   aliases:
   - dosini
@@ -1890,6 +1943,7 @@ IRC log:
   language_id: 164
 Idris:
   type: programming
+  color: "#b30000"
   extensions:
   - ".idr"
   - ".lidr"
@@ -2078,6 +2132,7 @@ JavaScript:
   - ".jsfl"
   - ".jsm"
   - ".jss"
+  - ".mjs"
   - ".njs"
   - ".pac"
   - ".sjs"
@@ -2149,13 +2204,6 @@ KRL:
   tm_scope: none
   ace_mode: text
   language_id: 186
-KiCad Board:
-  type: data
-  extensions:
-  - ".brd"
-  tm_scope: source.pcb.board
-  ace_mode: text
-  language_id: 140848857
 KiCad Layout:
   type: data
   aliases:
@@ -2171,6 +2219,13 @@ KiCad Layout:
   codemirror_mode: commonlisp
   codemirror_mime_type: text/x-common-lisp
   language_id: 187
+KiCad Legacy Layout:
+  type: data
+  extensions:
+  - ".brd"
+  tm_scope: source.pcb.board
+  ace_mode: text
+  language_id: 140848857
 KiCad Schematic:
   type: data
   aliases:
@@ -2203,9 +2258,9 @@ Kotlin:
   language_id: 189
 LFE:
   type: programming
+  color: "#4C3023"
   extensions:
   - ".lfe"
-  group: Erlang
   tm_scope: source.lisp
   ace_mode: lisp
   codemirror_mode: commonlisp
@@ -2614,7 +2669,7 @@ Mathematica:
   language_id: 224
 Matlab:
   type: programming
-  color: "#bb92ac"
+  color: "#e16737"
   aliases:
   - octave
   extensions:
@@ -2741,6 +2796,7 @@ Monkey:
   type: programming
   extensions:
   - ".monkey"
+  - ".monkey2"
   ace_mode: text
   tm_scope: source.monkey
   language_id: 236
@@ -2790,6 +2846,15 @@ NSIS:
   codemirror_mode: nsis
   codemirror_mime_type: text/x-nsis
   language_id: 242
+Nearley:
+  type: programming
+  ace_mode: text
+  color: "#990000"
+  extensions:
+  - ".ne"
+  - ".nearley"
+  tm_scope: source.ne
+  language_id: 521429430
 Nemerle:
   type: programming
   color: "#3d3c6e"
@@ -2841,7 +2906,7 @@ NewLisp:
   codemirror_mime_type: text/x-common-lisp
   language_id: 247
 Nginx:
-  type: markup
+  type: data
   extensions:
   - ".nginxconf"
   - ".vhost"
@@ -2853,7 +2918,6 @@ Nginx:
   ace_mode: text
   codemirror_mode: nginx
   codemirror_mime_type: text/x-nginx-conf
-  color: "#9469E9"
   language_id: 248
 Nim:
   type: programming
@@ -3028,6 +3092,7 @@ OpenEdge ABL:
   extensions:
   - ".p"
   - ".cls"
+  - ".w"
   tm_scope: source.abl
   ace_mode: text
   language_id: 264
@@ -3271,7 +3336,6 @@ Perl:
   - ".ph"
   - ".plx"
   - ".pm"
-  - ".pod"
   - ".psgi"
   - ".t"
   filenames:
@@ -3376,6 +3440,14 @@ Pony:
   tm_scope: source.pony
   ace_mode: text
   language_id: 290
+PostCSS:
+  type: markup
+  tm_scope: source.postcss
+  group: CSS
+  extensions:
+  - ".pcss"
+  ace_mode: text
+  language_id: 262764437
 PostScript:
   type: markup
   color: "#da291c"
@@ -3442,7 +3514,7 @@ Propeller Spin:
   ace_mode: text
   language_id: 296
 Protocol Buffer:
-  type: markup
+  type: data
   aliases:
   - protobuf
   - Protocol Buffers
@@ -3487,8 +3559,7 @@ Puppet:
   tm_scope: source.puppet
   language_id: 299
 Pure Data:
-  type: programming
-  color: "#91de79"
+  type: data
   extensions:
   - ".pd"
   tm_scope: none
@@ -3542,6 +3613,7 @@ Python:
   - ".gclient"
   - BUCK
   - BUILD
+  - BUILD.bazel
   - SConscript
   - SConstruct
   - Snakefile
@@ -4363,6 +4435,14 @@ Sublime Text Config:
   - ".sublime_metrics"
   - ".sublime_session"
   language_id: 423
+SugarSS:
+  type: markup
+  tm_scope: source.css.postcss.sugarss
+  group: CSS
+  extensions:
+  - ".sss"
+  ace_mode: text
+  language_id: 826404698
 SuperCollider:
   type: programming
   color: "#46390b"
@@ -4660,8 +4740,8 @@ UrWeb:
   ace_mode: text
   language_id: 383
 VCL:
-  group: Perl
   type: programming
+  color: "#0298c3"
   extensions:
   - ".vcl"
   tm_scope: source.varnish.vcl
@@ -4773,8 +4853,7 @@ Wavefront Object:
   ace_mode: text
   language_id: 393
 Web Ontology Language:
-  type: markup
-  color: "#9cc9dd"
+  type: data
   extensions:
   - ".owl"
   tm_scope: text.xml
@@ -4855,12 +4934,16 @@ XML:
   - ".ant"
   - ".axml"
   - ".builds"
+  - ".ccproj"
   - ".ccxml"
   - ".clixml"
   - ".cproject"
+  - ".cscfg"
+  - ".csdef"
   - ".csl"
   - ".csproj"
   - ".ct"
+  - ".depproj"
   - ".dita"
   - ".ditamap"
   - ".ditaval"
@@ -4883,6 +4966,8 @@ XML:
   - ".mm"
   - ".mod"
   - ".mxml"
+  - ".natvis"
+  - ".ndproj"
   - ".nproj"
   - ".nuspec"
   - ".odd"
@@ -4890,6 +4975,7 @@ XML:
   - ".pkgproj"
   - ".plist"
   - ".pluginspec"
+  - ".proj"
   - ".props"
   - ".ps1xml"
   - ".psc1"
@@ -4900,6 +4986,7 @@ XML:
   - ".sch"
   - ".scxml"
   - ".sfproj"
+  - ".shproj"
   - ".srdf"
   - ".storyboard"
   - ".stTheme"
@@ -4961,11 +5048,11 @@ XPM:
   tm_scope: source.c
   language_id: 781846279
 XPages:
-  type: programming
+  type: data
   extensions:
   - ".xsp-config"
   - ".xsp.metadata"
-  tm_scope: none
+  tm_scope: text.xml
   ace_mode: xml
   codemirror_mode: xml
   codemirror_mime_type: text/xml
@@ -5050,6 +5137,7 @@ YAML:
   - ".yml.mysql"
   filenames:
   - ".clang-format"
+  - ".clang-tidy"
   ace_mode: yaml
   codemirror_mode: yaml
   codemirror_mime_type: text/x-yaml
@@ -5061,6 +5149,14 @@ YANG:
   tm_scope: source.yang
   ace_mode: text
   language_id: 408
+YARA:
+  type: data
+  ace_mode: text
+  extensions:
+  - ".yar"
+  - ".yara"
+  tm_scope: source.yara
+  language_id: 805122868
 Yacc:
   type: programming
   extensions:
@@ -5159,6 +5255,14 @@ reStructuredText:
   codemirror_mode: rst
   codemirror_mime_type: text/x-rst
   language_id: 419
+wdl:
+  type: programming
+  color: "#42f1f4"
+  extensions:
+  - ".wdl"
+  tm_scope: source.wdl
+  ace_mode: text
+  language_id: 374521672
 wisp:
   type: programming
   ace_mode: clojure

lib/linguist/strategy/modeline.rb

@@ -109,8 +109,8 @@ module Linguist
       # Returns an Array with one Language if the blob has a Vim or Emacs modeline
       # that matches a Language name or alias. Returns an empty array if no match.
       def self.call(blob, _ = nil)
-        header = blob.lines.first(SEARCH_SCOPE).join("\n")
-        footer = blob.lines.last(SEARCH_SCOPE).join("\n")
+        header = blob.first_lines(SEARCH_SCOPE).join("\n")
+        footer = blob.last_lines(SEARCH_SCOPE).join("\n")
         Array(Language.find_by_alias(modeline(header + footer)))
       end
 

lib/linguist/tokenizer.rb

@@ -1,4 +1,5 @@
 require 'strscan'
+require 'linguist/linguist'
 
 module Linguist
   # Generic programming language tokenizer.
@@ -15,191 +16,5 @@ module Linguist
     def self.tokenize(data)
       new.extract_tokens(data)
     end
-
-    # Read up to 100KB
-    BYTE_LIMIT = 100_000
-
-    # Start state on token, ignore anything till the next newline
-    SINGLE_LINE_COMMENTS = [
-      '//', # C
-      '--', # Ada, Haskell, AppleScript
-      '#',  # Ruby
-      '%',  # Tex
-      '"',  # Vim
-    ]
-
-    # Start state on opening token, ignore anything until the closing
-    # token is reached.
-    MULTI_LINE_COMMENTS = [
-      ['/*', '*/'],    # C
-      ['<!--', '-->'], # XML
-      ['{-', '-}'],    # Haskell
-      ['(*', '*)'],    # Coq
-      ['"""', '"""'],  # Python
-      ["'''", "'''"]   # Python
-    ]
-
-    START_SINGLE_LINE_COMMENT =  Regexp.compile(SINGLE_LINE_COMMENTS.map { |c|
-      "\s*#{Regexp.escape(c)} "
-    }.join("|"))
-
-    START_MULTI_LINE_COMMENT =  Regexp.compile(MULTI_LINE_COMMENTS.map { |c|
-      Regexp.escape(c[0])
-    }.join("|"))
-
-    # Internal: Extract generic tokens from data.
-    #
-    # data - String to scan.
-    #
-    # Examples
-    #
-    #   extract_tokens("printf('Hello')")
-    #   # => ['printf', '(', ')']
-    #
-    # Returns Array of token Strings.
-    def extract_tokens(data)
-      s = StringScanner.new(data)
-
-      tokens = []
-      until s.eos?
-        break if s.pos >= BYTE_LIMIT
-
-        if token = s.scan(/^#!.+$/)
-          if name = extract_shebang(token)
-            tokens << "SHEBANG#!#{name}"
-          end
-
-        # Single line comment
-        elsif s.beginning_of_line? && token = s.scan(START_SINGLE_LINE_COMMENT)
-          # tokens << token.strip
-          s.skip_until(/\n|\Z/)
-
-        # Multiline comments
-        elsif token = s.scan(START_MULTI_LINE_COMMENT)
-          # tokens << token
-          close_token = MULTI_LINE_COMMENTS.assoc(token)[1]
-          s.skip_until(Regexp.compile(Regexp.escape(close_token)))
-          # tokens << close_token
-
-        # Skip single or double quoted strings
-        elsif s.scan(/"/)
-          if s.peek(1) == "\""
-            s.getch
-          else
-            s.skip_until(/(?<!\\)"/)
-          end
-        elsif s.scan(/'/)
-          if s.peek(1) == "'"
-            s.getch
-          else
-            s.skip_until(/(?<!\\)'/)
-          end
-
-        # Skip number literals
-        elsif s.scan(/(0x\h(\h|\.)*|\d(\d|\.)*)([uU][lL]{0,2}|([eE][-+]\d*)?[fFlL]*)/)
-
-        # SGML style brackets
-        elsif token = s.scan(/<[^\s<>][^<>]*>/)
-          extract_sgml_tokens(token).each { |t| tokens << t }
-
-        # Common programming punctuation
-        elsif token = s.scan(/;|\{|\}|\(|\)|\[|\]/)
-          tokens << token
-
-        # Regular token
-        elsif token = s.scan(/[\w\.@#\/\*]+/)
-          tokens << token
-
-        # Common operators
-        elsif token = s.scan(/<<?|\+|\-|\*|\/|%|&&?|\|\|?/)
-          tokens << token
-
-        else
-          s.getch
-        end
-      end
-
-      tokens
-    end
-
-    # Internal: Extract normalized shebang command token.
-    #
-    # Examples
-    #
-    #   extract_shebang("#!/usr/bin/ruby")
-    #   # => "ruby"
-    #
-    #   extract_shebang("#!/usr/bin/env node")
-    #   # => "node"
-    #
-    #   extract_shebang("#!/usr/bin/env A=B foo=bar awk -f")
-    #   # => "awk"
-    #
-    # Returns String token or nil it couldn't be parsed.
-    def extract_shebang(data)
-      s = StringScanner.new(data)
-
-      if path = s.scan(/^#!\s*\S+/)
-        script = path.split('/').last
-        if script == 'env'
-          s.scan(/\s+/)
-          s.scan(/.*=[^\s]+\s+/)
-          script = s.scan(/\S+/)
-        end
-        script = script[/[^\d]+/, 0] if script
-        return script
-      end
-
-      nil
-    end
-
-    # Internal: Extract tokens from inside SGML tag.
-    #
-    # data - SGML tag String.
-    #
-    # Examples
-    #
-    #   extract_sgml_tokens("<a href='' class=foo>")
-    #   # => ["<a>", "href="]
-    #
-    # Returns Array of token Strings.
-    def extract_sgml_tokens(data)
-      s = StringScanner.new(data)
-
-      tokens = []
-
-      until s.eos?
-        # Emit start token
-        if token = s.scan(/<\/?[^\s>]+/)
-          tokens << "#{token}>"
-
-        # Emit attributes with trailing =
-        elsif token = s.scan(/\w+=/)
-          tokens << token
-
-          # Then skip over attribute value
-          if s.scan(/"/)
-            s.skip_until(/[^\\]"/)
-          elsif s.scan(/'/)
-            s.skip_until(/[^\\]'/)
-          else
-            s.skip_until(/\w+/)
-          end
-
-        # Emit lone attributes
-        elsif token = s.scan(/\w+/)
-          tokens << token
-
-        # Stop at the end of the tag
-        elsif s.scan(/>/)
-          s.terminate
-
-        else
-          s.getch
-        end
-      end
-
-      tokens
-    end
   end
 end

lib/linguist/vendor.yml

@@ -19,9 +19,7 @@
 - (^|/)dist/
 
 # C deps
-#  https://github.com/joyent/node
 - ^deps/
-- ^tools/
 - (^|/)configure$
 - (^|/)config.guess$
 - (^|/)config.sub$
@@ -65,6 +63,7 @@
 
 # Font Awesome
 - (^|/)font-awesome\.(css|less|scss|styl)$
+- (^|/)font-awesome/.*\.(css|less|scss|styl)$
 
 # Foundation css
 - (^|/)foundation\.(css|less|scss|styl)$
@@ -81,6 +80,9 @@
 # Animate.css
 - (^|/)animate\.(css|less|scss|styl)$
 
+# Select2
+- (^|/)select2/.*\.(css|scss|js)$
+
 # Vendored dependencies
 - third[-_]?party/
 - 3rd[-_]?party/
@@ -119,6 +121,15 @@
 # jQuery File Upload
 - (^|/)jquery\.fileupload(-\w+)?\.js$
 
+# jQuery dataTables
+- jquery.dataTables.js
+
+# bootboxjs
+- bootbox.js
+
+# pdf-worker
+- pdf.worker.js
+
 # Slick
 - (^|/)slick\.\w+.js$
 
@@ -135,6 +146,9 @@
 - .sublime-project
 - .sublime-workspace
 
+# VS Code workspace files
+- .vscode
+
 # Prototype
 - (^|/)prototype(.*)\.js$
 - (^|/)effects\.js$
@@ -227,10 +241,7 @@
 - \.imageset/
 
 # Carthage
-- ^Carthage/
-
-# Cocoapods
-- ^Pods/
+- (^|/)Carthage/
 
 # Sparkle
 - (^|/)Sparkle/

lib/linguist/version.rb

@@ -1,3 +1,3 @@
 module Linguist
-  VERSION = "5.2.0"
+  VERSION = "5.3.3"
 end

package.json

@@ -1,7 +0,0 @@
-{
-  "repository": "https://github.com/github/linguist",
-  "dependencies": {
-    "season": "~>5.4"
-  },
-  "license": "MIT"
-}

samples/ActionScript/FooBar.as

@@ -0,0 +1,35 @@
+// A sample for Actionscript.
+
+package foobar
+{
+	import flash.display.MovieClip;
+
+	class Bar
+	{
+		public function getNumber():Number
+		{
+			return 10;
+		}
+	}
+
+	class Foo extends Bar
+	{
+		private var ourNumber:Number = 25;
+
+		override public function getNumber():Number
+		{
+			return ourNumber;
+		}
+	}
+
+	class Main extends MovieClip
+	{
+		public function Main()
+		{
+			var x:Bar = new Bar();
+			var y:Foo = new Foo();
+			trace(x.getNumber());
+			trace(y.getNumber());
+		}
+	}
+}

samples/ActionScript/HelloWorld.as

@@ -0,0 +1,13 @@
+package mypackage
+{
+	public class Hello
+	{
+		/* Let's say hello!
+		 * This is just a test script for Linguist's Actionscript detection.
+		 */
+		public function sayHello():void
+		{
+			trace("Hello, world");
+		}
+	}
+}

samples/AngelScript/botmanager.as

@@ -0,0 +1,77 @@
+/*
+*	This is a sample script.
+*/
+
+#include "BotManagerInterface.acs"
+
+BotManager::BotManager g_BotManager( @CreateDumbBot );
+
+CConCommand@ m_pAddBot;
+
+void PluginInit()
+{
+	g_BotManager.PluginInit();
+	
+	@m_pAddBot = @CConCommand( "addbot", "Adds a new bot with the given name", @AddBotCallback );
+}
+
+void AddBotCallback( const CCommand@ args )
+{
+	if( args.ArgC() < 2 )
+	{
+		g_Game.AlertMessage( at_console, "Usage: addbot <name>" );
+		return;
+	}
+	
+	BotManager::BaseBot@ pBot = g_BotManager.CreateBot( args[ 1 ] );
+	
+	if( pBot !is null )
+	{
+		g_Game.AlertMessage( at_console, "Created bot " + args[ 1 ] + "\n" );
+	}
+	else
+	{
+		g_Game.AlertMessage( at_console, "Could not create bot\n" );
+	}
+}
+
+final class DumbBot : BotManager::BaseBot
+{	
+	DumbBot( CBasePlayer@ pPlayer )
+	{
+		super( pPlayer );
+	}
+	
+	void Think()
+	{
+		BotManager::BaseBot::Think();
+		
+		// If the bot is dead and can be respawned, send a button press
+		if( Player.pev.deadflag >= DEAD_RESPAWNABLE )
+		{
+			Player.pev.button |= IN_ATTACK;
+		}
+		else
+			Player.pev.button &= ~IN_ATTACK;
+		
+		KeyValueBuffer@ pInfoBuffer = g_EngineFuncs.GetInfoKeyBuffer( Player.edict() );
+		
+		pInfoBuffer.SetValue( "topcolor", Math.RandomLong( 0, 255 ) );
+		pInfoBuffer.SetValue( "bottomcolor", Math.RandomLong( 0, 255 ) );
+		
+		if( Math.RandomLong( 0, 100 ) > 10 )
+			Player.pev.button |= IN_ATTACK;
+		else
+			Player.pev.button &= ~IN_ATTACK;
+			
+		for( uint uiIndex = 0; uiIndex < 3; ++uiIndex )
+		{
+			m_vecVelocity[ uiIndex ] = Math.RandomLong( -50, 50 );
+		}
+	}
+}
+
+BotManager::BaseBot@ CreateDumbBot( CBasePlayer@ pPlayer )
+{
+	return @DumbBot( pPlayer );
+}

samples/AngelScript/payload.as

@@ -0,0 +1,396 @@
+// Sample script.
+// Source: https://github.com/codecat/ssbd-payload
+
+array<WorldScript::PayloadBeginTrigger@> g_payloadBeginTriggers;
+array<WorldScript::PayloadTeamForcefield@> g_teamForceFields;
+
+[GameMode]
+class Payload : TeamVersusGameMode
+{
+	[Editable]
+	UnitFeed PayloadUnit;
+
+	[Editable]
+	UnitFeed FirstNode;
+
+	[Editable default=10]
+	int PrepareTime;
+
+	[Editable default=300]
+	int TimeLimit;
+
+	[Editable default=90]
+	int TimeAddCheckpoint;
+
+	[Editable default=2]
+	float TimeOvertime;
+
+	[Editable default=1000]
+	int TimePayloadHeal;
+
+	[Editable default=1]
+	int PayloadHeal;
+
+	PayloadBehavior@ m_payload;
+
+	int m_tmStarting;
+	int m_tmStarted;
+	int m_tmLimitCustom;
+	int m_tmOvertime;
+	int m_tmInOvertime;
+
+	PayloadHUD@ m_payloadHUD;
+	PayloadClassSwitchWindow@ m_switchClass;
+
+	array<SValue@>@ m_switchedSidesData;
+
+	Payload(Scene@ scene)
+	{
+		super(scene);
+
+		m_tmRespawnCountdown = 5000;
+
+		@m_payloadHUD = PayloadHUD(m_guiBuilder);
+		@m_switchTeam = PayloadTeamSwitchWindow(m_guiBuilder);
+		@m_switchClass = PayloadClassSwitchWindow(m_guiBuilder);
+	}
+
+	void UpdateFrame(int ms, GameInput& gameInput, MenuInput& menuInput) override
+	{
+		TeamVersusGameMode::UpdateFrame(ms, gameInput, menuInput);
+
+		m_payloadHUD.Update(ms);
+
+		if (Network::IsServer())
+		{
+			uint64 tmNow = CurrPlaytimeLevel();
+
+			if (m_tmStarting == 0)
+			{
+				if (GetPlayersInTeam(0) > 0 && GetPlayersInTeam(1) > 0)
+				{
+					m_tmStarting = tmNow;
+					(Network::Message("GameStarting") << m_tmStarting).SendToAll();
+				}
+			}
+
+			if (m_tmStarting > 0 && m_tmStarted == 0 && tmNow - m_tmStarting > PrepareTime * 1000)
+			{
+				m_tmStarted = tmNow;
+				(Network::Message("GameStarted") << m_tmStarted).SendToAll();
+
+				for (uint i = 0; i < g_payloadBeginTriggers.length(); i++)
+				{
+					WorldScript@ ws = WorldScript::GetWorldScript(g_scene, g_payloadBeginTriggers[i]);
+					ws.Execute();
+				}
+			}
+		}
+
+		if (!m_ended && m_tmStarted > 0)
+			CheckTimeReached(ms);
+	}
+
+	string NameForTeam(int index) override
+	{
+		if (index == 0)
+			return "Defenders";
+		else if (index == 1)
+			return "Attackers";
+
+		return "Unknown";
+	}
+
+	void CheckTimeReached(int dt)
+	{
+		// Check if time limit is not reached yet
+		if (m_tmLimitCustom - (CurrPlaytimeLevel() - m_tmStarted) > 0)
+		{
+			// Don't need to continue checking
+			m_tmOvertime = 0;
+			m_tmInOvertime = 0;
+			return;
+		}
+
+		// Count how long we're in overtime for later time limit fixing when we reach a checkpoint
+		if (m_tmOvertime > 0)
+			m_tmInOvertime += dt;
+
+		// Check if there are any attackers still inside
+		if (m_payload.AttackersInside() > 0)
+		{
+			// We have overtime
+			m_tmOvertime = int(TimeOvertime * 1000);
+			return;
+		}
+
+		// If we have overtime
+		if (m_tmOvertime > 0)
+		{
+			// Decrease timer
+			m_tmOvertime -= dt;
+			if (m_tmOvertime <= 0)
+			{
+				// Overtime countdown reached, time limit reached
+				TimeReached();
+			}
+		}
+		else
+		{
+			// No overtime, so time limit is reached
+			TimeReached();
+		}
+	}
+
+	void TimeReached()
+	{
+		if (!Network::IsServer())
+			return;
+
+		(Network::Message("TimeReached")).SendToAll();
+		SetWinner(false);
+	}
+
+	bool ShouldFreezeControls() override
+	{
+		return m_switchClass.m_visible
+		    || TeamVersusGameMode::ShouldFreezeControls();
+	}
+
+	bool ShouldDisplayCursor() override
+	{
+		return m_switchClass.m_visible
+		    || TeamVersusGameMode::ShouldDisplayCursor();
+	}
+
+	bool CanSwitchTeams() override
+	{
+		return m_tmStarted == 0;
+	}
+
+	PlayerRecord@ CreatePlayerRecord() override
+	{
+		return PayloadPlayerRecord();
+	}
+
+	int GetPlayerClassCount(PlayerClass playerClass, TeamVersusScore@ team)
+	{
+		if (team is null)
+			return 0;
+
+		int ret = 0;
+		for (uint i = 0; i < team.m_players.length(); i++)
+		{
+			if (team.m_players[i].peer == 255)
+				continue;
+			auto record = cast<PayloadPlayerRecord>(team.m_players[i]);
+			if (record.playerClass == playerClass)
+				ret++;
+		}
+		return ret;
+	}
+
+	void PlayerClassesUpdated()
+	{
+		m_switchClass.PlayerClassesUpdated();
+	}
+
+	void SetWinner(bool attackers)
+	{
+		if (attackers)
+			print("Attackers win!");
+		else
+			print("Defenders win!");
+
+		m_payloadHUD.Winner(attackers);
+		EndMatch();
+	}
+
+	void DisplayPlayerName(int idt, SpriteBatch& sb, PlayerRecord@ record, PlayerHusk@ plr, vec2 pos) override
+	{
+		TeamVersusGameMode::DisplayPlayerName(idt, sb, record, plr, pos);
+
+		m_payloadHUD.DisplayPlayerName(idt, sb, cast<PayloadPlayerRecord>(record), plr, pos);
+	}
+
+	void RenderFrame(int idt, SpriteBatch& sb) override
+	{
+		Player@ player = GetLocalPlayer();
+		if (player !is null)
+		{
+			PlayerHealgun@ healgun = cast<PlayerHealgun>(player.m_currWeapon);
+			if (healgun !is null)
+				healgun.RenderMarkers(idt, sb);
+		}
+
+		TeamVersusGameMode::RenderFrame(idt, sb);
+	}
+
+	void RenderWidgets(PlayerRecord@ player, int idt, SpriteBatch& sb) override
+	{
+		m_payloadHUD.Draw(sb, idt);
+
+		TeamVersusGameMode::RenderWidgets(player, idt, sb);
+
+		m_switchClass.Draw(sb, idt);
+	}
+
+	void GoNextMap() override
+	{
+		if (m_switchedSidesData !is null)
+		{
+			TeamVersusGameMode::GoNextMap();
+			return;
+		}
+
+		ChangeLevel(GetCurrentLevelFilename());
+	}
+
+	void SpawnPlayers() override
+	{
+		if (m_switchedSidesData is null)
+		{
+			TeamVersusGameMode::SpawnPlayers();
+			return;
+		}
+
+		if (Network::IsServer())
+		{
+			for (uint i = 0; i < m_switchedSidesData.length(); i += 2)
+			{
+				uint peer = uint(m_switchedSidesData[i].GetInteger());
+				uint team = uint(m_switchedSidesData[i + 1].GetInteger());
+
+				TeamVersusScore@ joinScore = FindTeamScore(team);
+				if (joinScore is m_teamScores[0])
+					@joinScore = m_teamScores[1];
+				else
+					@joinScore = m_teamScores[0];
+
+				for (uint j = 0; j < g_players.length(); j++)
+				{
+					if (g_players[j].peer != peer)
+						continue;
+					SpawnPlayer(j, vec2(), 0, joinScore.m_team);
+					break;
+				}
+			}
+		}
+	}
+
+	void Save(SValueBuilder& builder) override
+	{
+		if (m_switchedSidesData is null)
+		{
+			builder.PushArray("teams");
+			for (uint i = 0; i < g_players.length(); i++)
+			{
+				if (g_players[i].peer == 255)
+					continue;
+				builder.PushInteger(g_players[i].peer);
+				builder.PushInteger(g_players[i].team);
+			}
+			builder.PopArray();
+		}
+
+		TeamVersusGameMode::Save(builder);
+	}
+
+	void Start(uint8 peer, SValue@ save, StartMode sMode) override
+	{
+		if (save !is null)
+			@m_switchedSidesData = GetParamArray(UnitPtr(), save, "teams", false);
+
+		TeamVersusGameMode::Start(peer, save, sMode);
+
+		m_tmLimit = 0; // infinite time limit as far as VersusGameMode is concerned
+		m_tmLimitCustom = TimeLimit * 1000; // 5 minutes by default
+
+		@m_payload = cast<PayloadBehavior>(PayloadUnit.FetchFirst().GetScriptBehavior());
+
+		if (m_payload is null)
+			PrintError("PayloadUnit is not a PayloadBehavior!");
+
+		UnitPtr unitFirstNode = FirstNode.FetchFirst();
+		if (unitFirstNode.IsValid())
+		{
+			auto node = cast<WorldScript::PayloadNode>(unitFirstNode.GetScriptBehavior());
+			if (node !is null)
+				@m_payload.m_targetNode = node;
+			else
+				PrintError("First target node is not a PayloadNode script!");
+		}
+		else
+			PrintError("First target node was not set!");
+
+		WorldScript::PayloadNode@ prevNode;
+
+		float totalDistance = 0.0f;
+
+		UnitPtr unitNode = unitFirstNode;
+		while (unitNode.IsValid())
+		{
+			auto node = cast<WorldScript::PayloadNode>(unitNode.GetScriptBehavior());
+			if (node is null)
+				break;
+
+			unitNode = node.NextNode.FetchFirst();
+
+			@node.m_prevNode = prevNode;
+			@node.m_nextNode = cast<WorldScript::PayloadNode>(unitNode.GetScriptBehavior());
+
+			if (prevNode !is null)
+				totalDistance += dist(prevNode.Position, node.Position);
+
+			@prevNode = node;
+		}
+
+		float currDistance = 0.0f;
+
+		auto distNode = cast<WorldScript::PayloadNode>(unitFirstNode.GetScriptBehavior());
+		while (distNode !is null)
+		{
+			if (distNode.m_prevNode is null)
+				distNode.m_locationFactor = 0.0f;
+			else
+			{
+				currDistance += dist(distNode.m_prevNode.Position, distNode.Position);
+				distNode.m_locationFactor = currDistance / totalDistance;
+			}
+
+			@distNode = distNode.m_nextNode;
+		}
+
+		m_payloadHUD.AddCheckpoints();
+	}
+
+	void SpawnPlayer(int i, vec2 pos = vec2(), int unitId = 0, uint team = 0) override
+	{
+		TeamVersusGameMode::SpawnPlayer(i, pos, unitId, team);
+
+		PayloadPlayerRecord@ record = cast<PayloadPlayerRecord>(g_players[i]);
+		record.HandlePlayerClass();
+
+		if (g_players[i].local)
+		{
+			//TODO: This doesn't work well
+			bool localAttackers = (team == HashString("player_1"));
+			for (uint j = 0; j < g_teamForceFields.length(); j++)
+			{
+				bool hasCollision = (localAttackers != g_teamForceFields[j].Attackers);
+
+				auto units = g_teamForceFields[j].Units.FetchAll();
+				for (uint k = 0; k < units.length(); k++)
+				{
+					PhysicsBody@ body = units[k].GetPhysicsBody();
+					if (body is null)
+					{
+						PrintError("PhysicsBody for unit " + units[k].GetDebugName() + "is null");
+						continue;
+					}
+					body.SetActive(hasCollision);
+				}
+			}
+		}
+	}
+}

samples/Ballerina/hello-world-service.bal

@@ -0,0 +1,16 @@
+import ballerina.lang.messages;
+import ballerina.net.http;
+import ballerina.doc;
+
+@doc:Description {value:"By default Ballerina assumes that the service is to be exposed via HTTP/1.1 using the system default port and that all requests coming to the HTTP server will be delivered to this service."}
+service<http> helloWorld {
+    @doc:Description {value:"All resources are invoked with an argument of type message, the built-in reference type representing a network invocation."}
+    resource sayHello (message m) {
+        // Creates an empty message.
+        message response = {};
+        // A util method that can be used to set string payload.
+        messages:setStringPayload(response, "Hello, World!");
+        // Reply keyword sends the response back to the client.
+        reply response;
+    }
+}

samples/Ballerina/hello-world.bal

@@ -0,0 +1,6 @@
+import ballerina.lang.system;
+
+function main (string[] args) {
+    system:println("Hello, World!");
+}
+

samples/Ballerina/json.bal

@@ -0,0 +1,31 @@
+import ballerina.lang.system;
+
+function main (string[] args) {
+    // JSON string value.
+    json j1 = "Apple";
+    system:println(j1);
+
+    // JSON number value.
+    json j2 = 5.36;
+    system:println(j2);
+
+    // JSON true value.
+    json j3 = true;
+    system:println(j3);
+
+    // JSON false value.
+    json j4 = false;
+    system:println(j4);
+
+    // JSON null value.
+    json j5 = null;
+
+    //JSON Objects.
+    json j6 = {name:"apple", color:"red", price:j2};
+    system:println(j6);
+
+    //JSON Arrays. They are arrays of any JSON value.
+    json j7 = [1, false, null, "foo",
+               {first:"John", last:"Pala"}];
+    system:println(j7);
+}

samples/Ballerina/var.bal

@@ -0,0 +1,28 @@
+import ballerina.lang.system;
+
+function divideBy10 (int d) (int, int) {
+    return d / 10, d % 10;
+}
+
+function main (string[] args) {
+    //Here the variable type is inferred type from the initial value. This is same as "int k = 5";
+    var k = 5;
+    system:println(10 + k);
+
+    //Here the type of the 'strVar' is 'string'.
+    var strVar = "Hello!";
+    system:println(strVar);
+
+    //Multiple assignment with 'var' allows you to define the variable then and there.
+    //Variable type is inferred from the right-hand side.
+    var q, r = divideBy10(6);
+    system:println("06/10: " + "quotient=" + q + " " +
+                   "remainder=" + r);
+
+    //To ignore a particular return value in a multiple assignment statement, use '_'.
+    var q1, _ = divideBy10(57);
+    system:println("57/10: " + "quotient=" + q1);
+
+    var _, r1 = divideBy10(9);
+    system:println("09/10: " + "remainder=" + r1);
+}

samples/Ballerina/xml.bal

@@ -0,0 +1,26 @@
+import ballerina.lang.system;
+
+function main (string[] args) {
+
+	// XML element. Can only have one root element.
+    xml x1 = xml `<book>The Lost World</book>`;
+    system:println(x1);
+
+    // XML text
+    xml x2 = xml `Hello, world!`;
+    system:println(x2);
+
+    // XML comment
+    xml x3 = xml `<!--I am a comment-->`;
+    system:println(x3);
+
+    // XML processing instruction
+    xml x4 = xml `<?target data?>`;
+    system:println(x4);
+
+    // Multiple XML items can be combined to form a sequence of XML. The resulting sequence is again an XML on its own.
+    xml x5 = x1 + x2 + x3 + x4;
+    system:println("\nResulting XML sequence:");
+    system:println(x5);
+
+}

samples/Common Workflow Language/trunk-peak-score.cwl

@@ -0,0 +1,36 @@
+#!/usr/bin/env cwl-runner
+# Originally from
+# https://github.com/Duke-GCB/GGR-cwl/blob/54e897263a702ff1074c8ac814b4bf7205d140dd/utils/trunk-peak-score.cwl
+# Released under the MIT License:
+# https://github.com/Duke-GCB/GGR-cwl/blob/54e897263a702ff1074c8ac814b4bf7205d140dd/LICENSE
+# Converted to CWL v1.0 syntax using
+# https://github.com/common-workflow-language/cwl-upgrader
+# and polished by Michael R. Crusoe <mrc@commonwl.org>
+# All modifications also released under the MIT License
+cwlVersion: v1.0
+class: CommandLineTool
+doc: Trunk scores in ENCODE bed6+4 files
+
+hints:
+  DockerRequirement:
+    dockerPull: dukegcb/workflow-utils
+
+inputs:
+  peaks:
+    type: File
+  sep:
+    type: string
+    default: \t
+
+outputs:
+  trunked_scores_peaks:
+    type: stdout
+
+baseCommand: awk
+
+arguments:
+- -F $(inputs.sep)
+- BEGIN{OFS=FS}$5>1000{$5=1000}{print}
+- $(inputs.peaks.path)
+
+stdout: $(inputs.peaks.nameroot).trunked_scores$(inputs.peaks.nameext)

samples/DataWeave/customInterpolator.dwl

@@ -0,0 +1,12 @@
+fun SQL(literals, parts) = ''
+---
+[
+  SQL `SELECT * FROM table WHERE id = $(1) AND name = $('a')`,
+  SQL `$('p')`,
+  SQL `$('a')$('b')`,
+  SQL `$('a')---$('b')`,
+  SQL `---$('a')---$('b')---`,
+  SQL `$('p')bbb`,
+  SQL `aaa$('p')`,
+  SQL `aaa$('p')bbb`
+]

samples/DataWeave/directives.dwl

@@ -0,0 +1,9 @@
+%dw 2.0
+var number = 1234
+fun foo(func,name="Mariano") = func(name)
+input payload application/test arg="value"
+output application/json
+---
+{
+  foo: "bar"
+}

samples/DataWeave/functions.dwl

@@ -0,0 +1,27 @@
+%dw 2.0
+var x=(param1, param2) -> { "$param1": param2 }
+var y=(param1, param2 = "c") -> { "$param1": param2 }
+var toUser = (user) -> { name: user.name,	lastName: user.lastName }
+fun z(param1, param2) = { "$param1": param2 }
+var a = { name: "Mariano" , toUser: ((param1, param2) -> { "$param1": param2 }) }
+var applyFirst =  (array, func) -> (func(array[0]) ++  array[1 to -1])
+
+var nested =  (array, func) -> (a) -> (b) -> (c) -> array map func(a ++ b ++ c)
+
+
+fun f2(a1, a2) = ""
+fun f3(a1:String, a2:Number):String = a1
+fun f4(a1:String, a2:(a:Number) -> Number):String = a1
+---
+result: {
+  a: x("a", "b"),
+  b: y("a"),
+  c: y("a", "b"),
+  users: { (in1 map ((user) -> { user: (toUser(user) ++ user) })) },
+  d: z("a", "b"),
+  e: a.toUser("name","Mariano"),
+  f: a.toUser("name","Mariano").name,
+  f: applyFirst("mariano", (s) -> upper(s) ),
+  g: [] map (s) -> upper(s),
+  h: 1 f2 2
+}

samples/DataWeave/literals.dwl

@@ -0,0 +1,36 @@
+%dw 2.0
+---
+{
+  "boolean":{
+    "true" : true,
+    "false": false
+  },
+  "Number": {
+    "int": 123,
+    "decimal": 123.23
+  },
+  "string": {
+    "singleQuote" : 'A String',
+    "doubleQuote" : "A String"
+  },
+  "regex": /foo/,
+  "date": {
+    a: |2003-10-01|,
+    b: |2005-045|,
+    c: |2003-W14-3|,
+    d: |23:57:59|,
+    e: |23:57:30.700|,
+    f: |23:50:30Z|,
+    g: |+13:00|,
+    h: |Z|,
+    i: |-02:00|,
+    j: |2005-06-02T15:10:16|,
+    k: |2005-06-02T15:10:16Z|,
+    l: |2005-06-02T15:10:16+03:00|,
+    m: |P12Y7M11D|,
+    n: |P12Y5M|,
+    o: |P45DT9H20M8S|,
+    p: |PT9H20M8S|
+  }
+}
+

samples/DataWeave/match.dwl

@@ -0,0 +1,33 @@
+{
+  // Regex Pattern Matching (Can be named or unnamed)
+  a: in0.phones map $ match {
+    case matches /\+(\d+)\s\((\d+)\)\s(\d+\-\d+)/ -> { country: $[0], area: $[1], number: $[2] }
+    case matches /\((\d+)\)\s(\d+\-\d+)/ -> { area: $[1], number: $[2] }
+    case phone matches /\((\d+)\)\s(\d+\-\d+)/ -> { area: phone[1], number: phone[2] }
+  },
+  // Type Pattern Matching (Can be named or unnamed)
+  b: in0.object match {
+    case is Object -> { object: $ }
+    case is Number -> { number: $ }
+    // This is how you name variables if needed
+    case y is Boolean -> { boolean: y }
+  },
+  // Literal Pattern Matching (Can be named or unnamed)
+  c: in0.value match {
+    case "Emiliano" -> { string: $ }
+    case 123 -> { number: $ }
+    // This is how you name variables if needed
+    case value: "Mariano" -> { name: value }
+  },
+  // Boolean Expression Pattern Matching (Always named)
+  d: in0.value match {
+    case x if x > 30 -> { biggerThan30: x }
+    case x if x == 9 -> { nine: x }
+  },
+  // Default matches
+  e: in0.value match {
+    case "Emiliano" -> "string"
+    case 3.14 -> number
+    else -> "1234"
+  }
+}

samples/INI/filenames/buildozer.spec

@@ -0,0 +1,227 @@
+[app]
+
+# (str) Title of your application
+title = Kivy Kazam
+
+# (str) Package name
+package.name = kivykazam
+
+# (str) Package domain (needed for android/ios packaging)
+package.domain = org.test
+
+# (str) Source code where the main.py live
+source.dir = .
+
+# (list) Source files to include (let empty to include all the files)
+source.include_exts = py,png,jpg,kv,atlas
+
+# (list) List of inclusions using pattern matching
+#source.include_patterns = assets/*,images/*.png
+
+# (list) Source files to exclude (let empty to not exclude anything)
+#source.exclude_exts = spec
+
+# (list) List of directory to exclude (let empty to not exclude anything)
+#source.exclude_dirs = tests, bin
+
+# (list) List of exclusions using pattern matching
+#source.exclude_patterns = license,images/*/*.jpg
+
+# (str) Application versioning (method 1)
+version = 0.1
+
+# (str) Application versioning (method 2)
+# version.regex = __version__ = ['"](.*)['"]
+# version.filename = %(source.dir)s/main.py
+
+# (list) Application requirements
+# comma seperated e.g. requirements = sqlite3,kivy
+requirements = kivy
+
+# (str) Custom source folders for requirements
+# Sets custom source for any requirements with recipes
+# requirements.source.kivy = ../../kivy
+
+# (list) Garden requirements
+#garden_requirements =
+
+# (str) Presplash of the application
+#presplash.filename = %(source.dir)s/data/presplash.png
+
+# (str) Icon of the application
+#icon.filename = %(source.dir)s/data/icon.png
+
+# (str) Supported orientation (one of landscape, portrait or all)
+orientation = all
+
+# (list) List of service to declare
+#services = NAME:ENTRYPOINT_TO_PY,NAME2:ENTRYPOINT2_TO_PY
+
+#
+# OSX Specific
+#
+
+#
+# author = © Copyright Info
+
+#
+# Android specific
+#
+
+# (bool) Indicate if the application should be fullscreen or not
+fullscreen = 1
+
+# (list) Permissions
+#android.permissions = INTERNET
+
+# (int) Android API to use
+#android.api = 19
+
+# (int) Minimum API required
+android.minapi = 13
+
+# (int) Android SDK version to use
+#android.sdk = 20
+
+# (str) Android NDK version to use
+#android.ndk = 9c
+
+# (bool) Use --private data storage (True) or --dir public storage (False)
+#android.private_storage = True
+
+# (str) Android NDK directory (if empty, it will be automatically downloaded.)
+#android.ndk_path =
+
+# (str) Android SDK directory (if empty, it will be automatically downloaded.)
+#android.sdk_path =
+
+# (str) ANT directory (if empty, it will be automatically downloaded.)
+#android.ant_path =
+
+# (str) python-for-android git clone directory (if empty, it will be automatically cloned from github)
+#android.p4a_dir =
+
+# (list) python-for-android whitelist
+#android.p4a_whitelist =
+
+# (bool) If True, then skip trying to update the Android sdk
+# This can be useful to avoid excess Internet downloads or save time
+# when an update is due and you just want to test/build your package
+# android.skip_update = False
+
+# (str) Android entry point, default is ok for Kivy-based app
+#android.entrypoint = org.renpy.android.PythonActivity
+
+# (list) List of Java .jar files to add to the libs so that pyjnius can access
+# their classes. Don't add jars that you do not need, since extra jars can slow
+# down the build process. Allows wildcards matching, for example:
+# OUYA-ODK/libs/*.jar
+#android.add_jars = foo.jar,bar.jar,path/to/more/*.jar
+
+# (list) List of Java files to add to the android project (can be java or a
+# directory containing the files)
+#android.add_src =
+
+# (str) python-for-android branch to use, if not master, useful to try
+# not yet merged features.
+#android.branch = master
+
+# (str) OUYA Console category. Should be one of GAME or APP
+# If you leave this blank, OUYA support will not be enabled
+#android.ouya.category = GAME
+
+# (str) Filename of OUYA Console icon. It must be a 732x412 png image.
+#android.ouya.icon.filename = %(source.dir)s/data/ouya_icon.png
+
+# (str) XML file to include as an intent filters in <activity> tag
+#android.manifest.intent_filters =
+
+# (list) Android additionnal libraries to copy into libs/armeabi
+#android.add_libs_armeabi = libs/android/*.so
+#android.add_libs_armeabi_v7a = libs/android-v7/*.so
+#android.add_libs_x86 = libs/android-x86/*.so
+#android.add_libs_mips = libs/android-mips/*.so
+
+# (bool) Indicate whether the screen should stay on
+# Don't forget to add the WAKE_LOCK permission if you set this to True
+#android.wakelock = False
+
+# (list) Android application meta-data to set (key=value format)
+#android.meta_data =
+
+# (list) Android library project to add (will be added in the
+# project.properties automatically.)
+#android.library_references =
+
+# (str) Android logcat filters to use
+#android.logcat_filters = *:S python:D
+
+# (bool) Copy library instead of making a libpymodules.so
+#android.copy_libs = 1
+
+#
+# iOS specific
+#
+
+# (str) Path to a custom kivy-ios folder
+#ios.kivy_ios_dir = ../kivy-ios
+
+# (str) Name of the certificate to use for signing the debug version
+# Get a list of available identities: buildozer ios list_identities
+#ios.codesign.debug = "iPhone Developer: <lastname> <firstname> (<hexstring>)"
+
+# (str) Name of the certificate to use for signing the release version
+#ios.codesign.release = %(ios.codesign.debug)s
+
+
+[buildozer]
+
+# (int) Log level (0 = error only, 1 = info, 2 = debug (with command output))
+log_level = 1
+
+# (int) Display warning if buildozer is run as root (0 = False, 1 = True)
+warn_on_root = 1
+
+# (str) Path to build artifact storage, absolute or relative to spec file
+# build_dir = ./.buildozer
+
+# (str) Path to build output (i.e. .apk, .ipa) storage
+# bin_dir = ./bin
+
+#    -----------------------------------------------------------------------------
+#    List as sections
+#
+#    You can define all the "list" as [section:key].
+#    Each line will be considered as a option to the list.
+#    Let's take [app] / source.exclude_patterns.
+#    Instead of doing:
+#
+#[app]
+#source.exclude_patterns = license,data/audio/*.wav,data/images/original/*
+#
+#    This can be translated into:
+#
+#[app:source.exclude_patterns]
+#license
+#data/audio/*.wav
+#data/images/original/*
+#
+
+
+#    -----------------------------------------------------------------------------
+#    Profiles
+#
+#    You can extend section / key with a profile
+#    For example, you want to deploy a demo version of your application without
+#    HD content. You could first change the title to add "(demo)" in the name
+#    and extend the excluded directories to remove the HD content.
+#
+#[app@demo]
+#title = My Application (demo)
+#
+#[app:source.exclude_patterns@demo]
+#images/hd/*
+#
+#    Then, invoke the command line with the "demo" profile:
+#
+#buildozer --profile demo android debug

samples/JavaScript/constant_fold.mjs

@@ -0,0 +1,955 @@
+// consumes <stdin> and performs constant folding
+// echo '"use strict";"_"[0],1+2;' | node constant_fold.js
+import _NodePath from '../NodePath';
+const {NodePath} = _NodePath;
+import _WalkCombinator from '../WalkCombinator';
+const {WalkCombinator} = _WalkCombinator;
+
+const $CONSTEXPR = Symbol.for('$CONSTEXTR');
+const $CONSTVALUE = Symbol.for('$CONSTVALUE');
+const IS_EMPTY = path => {
+  return (path.node.type === 'BlockStatement' && path.node.body.length === 0) ||
+    path.node.type === 'EmptyStatement';
+};
+const IN_PRAGMA_POS = path => {
+  if (path.parent && Array.isArray(path.parent.node)) {
+    const siblings = path.parent.node;
+    for (let i = 0; i < path.key; i++) {
+      // preceded by non-pragma
+      if (
+        siblings[i].type !== 'ExpressionStatement' ||
+        !IS_CONSTEXPR(siblings[i].expression) ||
+        typeof CONSTVALUE(siblings[i].expression) !== 'string'
+      ) {
+        return false;
+      }
+    }
+  }
+  return true;
+};
+const IS_PRAGMA = path => {
+  if (path.parent && Array.isArray(path.parent.node)) {
+    const siblings = path.parent.node;
+    for (let i = 0; i < path.key + 1; i++) {
+      // preceded by non-pragma
+      if (
+        siblings[i].type !== 'ExpressionStatement' ||
+        !IS_CONSTEXPR(siblings[i].expression) ||
+        typeof CONSTVALUE(siblings[i].expression) !== 'string'
+      ) {
+        return false;
+      }
+    }
+  }
+  return true;
+};
+// worst case is the completion value
+const IS_NOT_COMPLETION = path => {
+  while (true) {
+    if (!path.parent) {
+      return true;
+    }
+    if (
+      Array.isArray(path.parent.node) &&
+      path.key !== path.parent.node.length - 1
+    ) {
+      return true;
+    }
+    path = path.parent;
+    while (Array.isArray(path.node)) {
+      path = path.parent;
+    }
+    if (/Function/.test(path.node.type)) {
+      return true;
+    } else if (path.node.type === 'Program') {
+      return false;
+    }
+  }
+};
+const REMOVE_IF_EMPTY = path => {
+  if (IS_EMPTY(path)) REMOVE(path);
+  return null;
+};
+const REPLACE_IF_EMPTY = (path, folded) => {
+  if (IS_EMPTY(path)) return REPLACE(path, folded);
+  return path;
+};
+const REMOVE = path => {
+  if (Array.isArray(path.parent.node)) {
+    path.parent.node.splice(path.key, 1);
+  } else {
+    path.parent.node[path.key] = null;
+  }
+  return null;
+};
+const REPLACE = (path, folded) => {
+  const replacement = new NodePath(path.parent, folded, path.key);
+  path.parent.node[path.key] = folded;
+  return replacement;
+};
+// no mutation, this is an atomic value
+const NEG_ZERO = Object.freeze({
+  [$CONSTEXPR]: true,
+  type: 'UnaryExpression',
+  operator: '-',
+  argument: Object.freeze({
+    [$CONSTEXPR]: true,
+    type: 'Literal',
+    value: 0,
+  }),
+});
+const INFINITY = Object.freeze({
+  [$CONSTEXPR]: true,
+  type: 'BinaryExpression',
+  operator: '/',
+  left: Object.freeze({
+    [$CONSTEXPR]: true,
+    type: 'Literal',
+    value: 1,
+  }),
+  right: Object.freeze({
+    [$CONSTEXPR]: true,
+    type: 'Literal',
+    value: 0,
+  }),
+});
+const NEG_INFINITY = Object.freeze({
+  [$CONSTEXPR]: true,
+  type: 'BinaryExpression',
+  operator: '/',
+  left: Object.freeze({
+    [$CONSTEXPR]: true,
+    type: 'Literal',
+    value: 1,
+  }),
+  right: NEG_ZERO,
+});
+const EMPTY = Object.freeze({
+  [$CONSTEXPR]: true,
+  type: 'EmptyStatement',
+});
+const NULL = Object.freeze({
+  [$CONSTEXPR]: true,
+  type: 'Literal',
+  value: null,
+});
+const NAN = Object.freeze({
+  [$CONSTEXPR]: true,
+  type: 'BinaryExpression',
+  operator: '/',
+  left: Object.freeze({
+    [$CONSTEXPR]: true,
+    type: 'Literal',
+    value: 0,
+  }),
+  right: Object.freeze({
+    [$CONSTEXPR]: true,
+    type: 'Literal',
+    value: 0,
+  }),
+});
+const UNDEFINED = Object.freeze({
+  [$CONSTEXPR]: true,
+  type: 'UnaryExpression',
+  operator: 'void',
+  argument: Object.freeze({
+    [$CONSTEXPR]: true,
+    type: 'Literal',
+    value: 0,
+  }),
+});
+// ESTree doesn't like negative numeric literals
+// this also preserves -0
+const IS_UNARY_NEGATIVE = node => {
+  if (
+    node.type === 'UnaryExpression' &&
+    node.operator === '-' &&
+    typeof node.argument.value === 'number' &&
+    node.argument.value === node.argument.value &&
+    node.argument.type === 'Literal'
+  ) {
+    return true;
+  }
+  return false;
+};
+const IS_CONSTEXPR = node => {
+  if (typeof node !== 'object' || node === null) {
+    return false;
+  }
+  // DONT CALCULATE THINGS MULTIPLE TIMES!!@!@#
+  if (node[$CONSTEXPR]) return true;
+  if (node.type === 'ArrayExpression') {
+    for (let i = 0; i < node.elements.length; i++) {
+      const element = node.elements[i];
+      // hole == null
+      if (element !== null && !IS_CONSTEXPR(element)) {
+        return false;
+      }
+    }
+    return true;
+  }
+  if (node.type === 'ObjectExpression') {
+    for (let i = 0; i < node.properties.length; i++) {
+      const element = node.properties[i];
+      if (element.kind !== 'init') return false;
+      if (element.method) return false;
+      let key;
+      if (element.computed) {
+        // be sure {["y"]:1} works
+        if (!IS_CONSTEXPR(element.key)) {
+          return false;
+        }
+      }
+      if (!IS_CONSTEXPR(element.value)) return false;
+    }
+    return true;
+  }
+  if (node.type === 'Literal' || IS_UNDEFINED(node) || IS_NAN(node)) {
+    return true;
+  }
+  if (IS_UNARY_NEGATIVE(node)) {
+    return true;
+  }
+  return false;
+};
+const IS_NAN = node => {
+  return node === NAN;
+};
+const IS_UNDEFINED = node => {
+  return node === UNDEFINED;
+};
+const CONSTVALUE = node => {
+  if (node[$CONSTVALUE]) {
+    return node[$CONSTVALUE];
+  }
+  if (IS_UNDEFINED(node)) return void 0;
+  if (IS_NAN(node)) return +'_';
+  if (!IS_CONSTEXPR(node)) throw new Error('Not a CONSTEXPR');
+  if (node.type === 'ArrayExpression') {
+    let ret = [];
+    ret.length = node.elements.length;
+    for (let i = 0; i < node.elements.length; i++) {
+      if (node.elements[i] !== null) {
+        ret[i] = CONSTVALUE(node.elements[i]);
+      }
+    }
+    return ret;
+  }
+  if (node.type === 'ObjectExpression') {
+    let ret = Object.create(null);
+    for (let i = 0; i < node.properties.length; i++) {
+      const element = node.properties[i];
+      let key;
+      if (element.computed) {
+        key = `${CONSTVALUE(element.key)}`;
+      }
+      else {
+        key = element.key.name;
+      }
+      Object.defineProperty(ret, key, {
+        // duplicate keys...
+        configurable: true,
+        writable: true,
+        value: CONSTVALUE(element.value),
+        enumerable: true
+      });
+    }
+    Object.freeze(ret);
+    return ret;
+  }
+  if (IS_UNARY_NEGATIVE(node)) {
+    return -node.argument.value;
+  }
+  if (node.regex !== void 0) {
+    return new RegExp(node.regex.pattern, node.regex.flags);
+  }
+  return node.value;
+};
+const CONSTEXPRS = new Map();
+CONSTEXPRS.set(void 0, UNDEFINED);
+CONSTEXPRS.set(+'_', NAN);
+CONSTEXPRS.set(null, NULL);
+const TO_CONSTEXPR = value => {
+  if (value === -Infinity) {
+    return NEG_INFINITY;
+  }
+  if (value === Infinity) {
+    return INFINITY;
+  }
+  let is_neg_zero = 1 / value === -Infinity;
+  if (is_neg_zero) return NEG_ZERO;
+  if (CONSTEXPRS.has(value)) {
+    return CONSTEXPRS.get(value);
+  }
+  if (typeof value === 'number') {
+    if (value < 0) {
+      const CONSTEXPR = Object.freeze({
+        [$CONSTEXPR]: true,
+        [$CONSTVALUE]: value,
+        type: 'UnaryExpression',
+        operator: '-',
+        argument: Object.freeze({ type: 'Literal', value: -value }),
+      });
+      CONSTEXPRS.set(value, CONSTEXPR);
+      return CONSTEXPR;
+    }
+  }
+  if (
+    value === null ||
+    typeof value === 'number' ||
+    typeof value === 'boolean' ||
+    typeof value === 'string'
+  ) {
+    const CONSTEXPR = Object.freeze({
+      [$CONSTEXPR]: true,
+      [$CONSTVALUE]: value,
+      type: 'Literal',
+      value,
+    });
+    CONSTEXPRS.set(value, CONSTEXPR);
+    return CONSTEXPR;
+  }
+  // have to generate new one every time :-/
+  if (Array.isArray(value)) {
+    return Object.freeze({
+      [$CONSTEXPR]: true,
+      type: 'ArrayExpression',
+      elements: Object.freeze(value.map(TO_CONSTEXPR)),
+    });
+  }
+  if (typeof value === 'object' && Object.getPrototypeOf(value) === Object.getPrototypeOf({}) && [...Object.getOwnPropertySymbols(value)].length === 0) {
+    return Object.freeze({
+      [$CONSTEXPR]: true,
+      type: 'ObjectExpression',
+      properties: Object.freeze(
+        [...Object.getOwnPropertyKeys(value)].map(key => {
+          if (!('value' in Object.getOwnProperty(value, key))) {
+            throw Error('Not a CONSTVALUE (found a setter or getter?)');
+          }
+          return {
+            type: 'Property',
+            kind: 'init',
+            method: false,
+            shorthand: false,
+            computed: true,
+            key: {
+              type: 'Literal',
+              value: key
+            },
+            value: TO_CONSTEXPR(value[key])
+          }
+        })),
+      });
+  }
+  throw Error('Not a CONSTVALUE (did you pass a RegExp?)');
+};
+
+// THIS DOES NOT HANDLE NODE SPECIFIC CASES LIKE IfStatement
+const FOLD_EMPTY = function*(path) {
+  if (
+    path &&
+    path.node &&
+    path.parent &&
+    Array.isArray(path.parent.node) &&
+    IS_EMPTY(path)
+  ) {
+    REMOVE(path);
+    return yield;
+  }
+  return yield path;
+};
+
+// THIS DOES NOT HANDLE NODE SPECIFIC CASES LIKE IfStatement
+const FOLD_TEMPLATE = function*(path) {
+  if (
+    path &&
+    path.node &&
+    path.type === 'TemplateLiteral'
+  ) {
+    let updated = false;
+    for (let i = 0; i < path.node.exressions.length; i++) {
+      if (IS_CONSTEXPR(path.node.expressions[i])) {
+        //let 
+      }
+    }
+  }
+  return yield path;
+};
+const FOLD_EXPR_STMT = function*(path) {
+  // TODO: enforce completion value checking
+  if (path && path.node && path.node.type === 'ExpressionStatement') {
+    // merge all the adjacent expression statements into sequences
+    if (Array.isArray(path.parent.node)) {
+      // could have nodes after it
+      const siblings = path.parent.node;
+      if (!IS_PRAGMA(path)) {
+        if (path.key < siblings.length - 1) {
+          const mergeable = [path.node];
+          for (let needle = path.key + 1; needle < siblings.length; needle++) {
+            if (siblings[needle].type !== 'ExpressionStatement') {
+              break;
+            }
+            mergeable.push(siblings[needle]);
+          }
+          if (mergeable.length > 1) {
+            siblings.splice(path.key, mergeable.length, {
+              type: 'ExpressionStatement',
+              expression: {
+                type: 'SequenceExpression',
+                expressions: mergeable.reduce(
+                  (acc, es) => {
+                    if (es.expression.type == 'SequenceExpression') {
+                      return [...acc, ...es.expression.expressions];
+                    } else {
+                      return [...acc, es.expression];
+                    }
+                  },
+                  []
+                ),
+              },
+            });
+            return path;
+          }
+        }
+      }
+    }
+    if (IS_NOT_COMPLETION(path) && IS_CONSTEXPR(path.node.expression)) {
+      return REPLACE(path, EMPTY);
+    }
+  }
+  return yield path;
+};
+const FOLD_WHILE = function*(path) {
+  if (path && path.node) {
+    if (path.node.type === 'DoWhileStatement') {
+      console.error('FOLD_DOWHILE');
+      REPLACE_IF_EMPTY(path.get(['body']), EMPTY);
+    }
+    if (path.node.type === 'WhileStatement') {
+      console.error('FOLD_WHILE');
+      let { test, consequent, alternate } = path.node;
+      if (IS_CONSTEXPR(test)) {
+        test = CONSTVALUE(test);
+        if (!test) {
+          return REPLACE(path, EMPTY);
+        }
+      }
+      REPLACE_IF_EMPTY(path.get(['body']), EMPTY);
+    }
+    if (path.node.type === 'ForStatement') {
+      console.error('FOLD_FOR');
+      REPLACE_IF_EMPTY(path.get(['body']), EMPTY);
+      let { init, test, update } = path.node;
+      let updated = false;
+      if (init && IS_CONSTEXPR(init)) {
+        updated = true;
+        REPLACE(path.get(['init']), null);
+      }
+      if (test && IS_CONSTEXPR(test)) {
+        let current = CONSTVALUE(test);
+        let coerced = Boolean(current);
+        // remove the test if it is always true
+        if (coerced === true) {
+          updated = true;
+          REPLACE(path.get(['test']), null);
+        } else if (coerced !== current) {
+          updated = true;
+          REPLACE(path.get(['test']), TO_CONSTEXPR(coerced));
+        }
+      }
+      if (update && IS_CONSTEXPR(update)) {
+        updated = true;
+        REPLACE(path.get(['update']), null);
+      }
+      if (updated) {
+        return path;
+      }
+    }
+  }
+  return yield path;
+};
+const FOLD_IF = function*(path) {
+  if (path && path.node && path.node.type === 'IfStatement') {
+    let { test, consequent, alternate } = path.node;
+    const is_not_completion = IS_NOT_COMPLETION(path);
+    if (is_not_completion && !alternate) {
+      if (IS_EMPTY(path.get(['consequent']))) {
+        console.error('FOLD_IF_EMPTY_CONSEQUENT');
+        REPLACE(path, {
+          type: 'ExpressionStatement',
+          expression: test,
+        });
+        return path.parent;
+      }
+    }
+    if (alternate) {
+      if (alternate.type === consequent.type) {
+        if (consequent.type === 'ExpressionStatement') {
+          console.error('FOLD_IF_BOTH_EXPRSTMT');
+          REPLACE(path, {
+          type: 'ExpressionStatement', expression:
+          {
+            type: 'ConditionalExpression',
+            test: test,
+            consequent: consequent.expression,
+            alternate: alternate.expression,
+          }});
+          return path.parent;
+        }
+        else if (consequent.type === 'ReturnStatement' ||
+          consequent.type === 'ThrowStatement') {
+          console.error('FOLD_IF_BOTH_COMPLETIONS');
+          REPLACE(path, {
+          type: 'ExpressionStatement', expression:{
+            type: consequent.type,
+            argument: {
+              type: 'ConditionalExpression',
+              test: test,
+              consequent: consequent.argument,
+              alternate: alternate.argument,
+            }}
+          });
+          return path.parent;
+        }
+      }
+    }
+    else if (is_not_completion && consequent.type === 'ExpressionStatement') {
+      console.error('FOLD_IF_NON_COMPLETION_TO_&&');
+      REPLACE(path, {
+        type: 'ExpressionStatement',
+        expression: {
+          type: 'BinaryExpression',
+          operator: '&&',
+          left: test,
+          right: consequent.expression,
+        }
+      });
+      return path.parent;
+    }
+    if (IS_CONSTEXPR(test)) {
+      test = CONSTVALUE(test);
+      if (test) {
+        return REPLACE(path, consequent);
+      }
+      if (alternate) {
+        return REPLACE(path, alternate);
+      }
+      return REPLACE(path, EMPTY);
+    }
+    consequent = path.get(['consequent']);
+    let updated;
+    if (consequent.node !== EMPTY) {
+      REPLACE_IF_EMPTY(consequent, EMPTY);
+      if (consequent.parent.node[consequent.key] === EMPTY) {
+        updated = true;
+      }
+    }
+    if (alternate) {
+      alternate = path.get(['alternate']);
+      REMOVE_IF_EMPTY(alternate);
+      if (path.node.alternate === null) {
+        updated = true;
+      }
+    }
+    if (updated) {
+      return path;
+    }
+  }
+  return yield path;
+};
+const FOLD_SEQUENCE = function*(path) {
+  if (path && path.node && path.node.type === 'SequenceExpression') {
+    console.error('FOLD_SEQUENCE');
+    // never delete the last value
+    for (let i = 0; i < path.node.expressions.length - 1; i++) {
+      if (IS_CONSTEXPR(path.node.expressions[i])) {
+        path.node.expressions.splice(i, 1);
+        i--;
+      }
+    }
+    if (path.node.expressions.length === 1) {
+      return REPLACE(path, path.node.expressions[0]);
+    }
+  }
+  return yield path;
+};
+const FOLD_LOGICAL = function*(path) {
+  if (path && path.node && path.node.type === 'LogicalExpression') {
+    console.error('FOLD_LOGICAL');
+    let { left, right, operator } = path.node;
+    if (IS_CONSTEXPR(left)) {
+      left = CONSTVALUE(left);
+      if (operator === '||') {
+        if (left) {
+          return REPLACE(path, TO_CONSTEXPR(left));
+        }
+        return REPLACE(path, right);
+      } else if (operator === '&&') {
+        if (!left) {
+          return REPLACE(path, TO_CONSTEXPR(left));
+        }
+        return REPLACE(path, right);
+      }
+    }
+  }
+  return yield path;
+};
+const FOLD_SWITCH = function*(path) {
+  if (path && path.node && path.node.type === 'SwitchStatement') {
+    let { discriminant, cases } = path.node;
+    // if there are no cases, just become an expression
+    if (cases.length === 0 && IS_NOT_COMPLETION(path)) {
+      return REPLACE(path, {
+        type: 'ExpressionStatement',
+        expression: discriminant
+      });
+    }
+    // if the discriminant is static
+    //   remove any preceding non-matching static cases
+    //   fold any trailing cases into the matching case
+    if (cases.length > 1 && IS_CONSTEXPR(discriminant)) {
+      const discriminant_value = CONSTVALUE(discriminant);
+      for (var i = 0; i < cases.length; i++) {
+        const test = cases[i].test;
+        if (IS_CONSTEXPR(test)) {
+          let test_value = CONSTVALUE(test);
+          if (discriminant_value === test_value) {
+            let new_consequent = cases[i].consequent;
+            if (i < cases.length - 1) {
+              for (let fallthrough of cases.slice(i+1)) {
+                new_consequent.push(...fallthrough.consequent);
+              }
+            }
+            cases[i].consequent = new_consequent;
+            REPLACE(path.get(['cases']), [cases[i]]);
+            return path;
+          }
+        }
+        else {
+          // we had a dynamic case need to bail
+          break;
+        }
+      }
+    }
+  }
+  return yield path;
+};
+const FOLD_UNREACHABLE = function*(path) {
+  if (path && path.node && path.parent && Array.isArray(path.parent.node)) {
+    if (path.node.type === 'ReturnStatement' ||
+    path.node.type === 'ContinueStatement' ||
+    path.node.type === 'BreakStatement' ||
+    path.node.type === 'ThrowStatement') {
+      const next_key = path.key + 1;
+      path.parent.node.splice(next_key, path.parent.node.length - next_key);
+    }
+  }
+  return yield path;
+}
+const FOLD_CONDITIONAL = function*(path) {
+  if (path && path.node && path.node.type === 'ConditionalExpression') {
+    console.error('FOLD_CONDITIONAL');
+    let { test, consequent, alternate } = path.node;
+    if (IS_CONSTEXPR(test)) {
+      test = CONSTVALUE(test);
+      if (test) {
+        return REPLACE(path, consequent);
+      }
+      return REPLACE(path, alternate);
+    }
+  }
+  return yield path;
+};
+const FOLD_BINARY = function*(path) {
+  if (
+    path &&
+    path.node &&
+    path.node.type === 'BinaryExpression' &&
+    !IS_NAN(path.node)
+  ) {
+    console.error('FOLD_BINARY');
+    let { left, right, operator } = path.node;
+    if (operator === '==' || operator === '!=') {
+      let updated = false;
+      if (IS_UNDEFINED(left)) {
+        updated = true;
+        REPLACE(path.get(['left']), NULL);
+      }
+      if (IS_UNDEFINED(right)) {
+        updated = true;
+        REPLACE(path.get(['right']), NULL);
+      }
+      if (updated) {
+        return path;
+      }
+    }
+    if (path.node !== INFINITY && path.node !== NEG_INFINITY && IS_CONSTEXPR(left) && IS_CONSTEXPR(right)) {
+      left = CONSTVALUE(left);
+      right = CONSTVALUE(right);
+      let value;
+      if ((!left || typeof left !== 'object') && (!right || typeof right !== 'object')) {
+        if (operator === '+') {
+          value = left + right;
+        } else if (operator === '-') {
+          value = left - right;
+        } else if (operator === '*') {
+          value = left * right;
+        } else if (operator === '/') {
+          value = left / right;
+        } else if (operator === '%') {
+          value = left % right;
+        } else if (operator === '==') {
+          value = left == right;
+        } else if (operator === '!=') {
+          value = left != right;
+        } else if (operator === '===') {
+          value = left === right;
+        } else if (operator === '!==') {
+          value = left !== right;
+        } else if (operator === '<') {
+          value = left < right;
+        } else if (operator === '<=') {
+          value = left <= right;
+        } else if (operator === '>') {
+          value = left > right;
+        } else if (operator === '>=') {
+          value = left >= right;
+        } else if (operator === '<<') {
+          value = left << right;
+        } else if (operator === '>>') {
+          value = left >> right;
+        } else if (operator === '>>>') {
+          value = left >>> right;
+        } else if (operator === '|') {
+          value = left | right;
+        } else if (operator === '&') {
+          value = left & right;
+        } else if (operator === '^') {
+          value = left ^ right;
+        }
+      }
+      else {
+        if (operator === '==') value = false;
+        if (operator === '===') value = false;
+        if (operator === '!=') value = true;
+        if (operator === '!==') value = true;
+        if (operator === 'in' && typeof right === 'object' && right) {
+          value = Boolean(Object.getOwnPropertyDescriptor(right, left));
+        }
+      }
+      if (value !== void 0) {
+        if (typeof value === 'string' || typeof value === 'boolean' || value === null) {
+          return REPLACE(path, TO_CONSTEXPR(value));
+        }
+        if (typeof value === 'number') {
+          return REPLACE(path, TO_CONSTEXPR(value));
+        }
+      }
+    }
+  }
+  return yield path;
+};
+const FOLD_UNARY = function*(path) {
+  if (path && path.node && path.node.type === 'UnaryExpression') {
+    console.error('FOLD_UNARY');
+    if (IS_CONSTEXPR(path.node)) {
+      return yield path;
+    }
+    let { argument, operator } = path.node;
+    if (IS_CONSTEXPR(argument)) {
+      if (operator === 'void') {
+        return REPLACE(path, UNDEFINED);
+      }
+      let value = CONSTVALUE(argument);
+      if (operator === '-') {
+        value = -value;
+      } else if (operator === '+') {
+        value = +value;
+      } else if (operator === '~') {
+        value = ~value;
+      } else if (operator === '!') {
+        value = !value;
+      } else if (operator === 'typeof') {
+        value = typeof value;
+      } else if (operator === 'delete') {
+        value = true;
+      }
+      return REPLACE(path, TO_CONSTEXPR(value));
+    }
+  }
+  return yield path;
+};
+const FOLD_EVAL = function*(path) {
+  if (path && path.node && path.node.type === 'CallExpression' &&
+    path.node.callee.type === 'Identifier' && path.node.callee.name === 'eval') {
+    console.error('FOLD_EVAL');
+    if (path.node.arguments.length === 1 && path.node.arguments[0].type === 'Literal') {
+      let result = esprima.parse(`${
+        CONSTVALUE(path.node.arguments[0])
+      }`);
+      if (result.body.length === 1 && result.body[0].type === 'ExpressionStatement') {
+        return REPLACE(path, result.body[0].expression);
+      }
+    }
+  }
+  return yield path;
+}
+const FOLD_MEMBER = function*(path) {
+  if (path && path.node && path.node.type === 'MemberExpression') {
+    console.error('FOLD_MEMBER');
+    if (path.node.computed && path.node.property.type === 'Literal') {
+      const current = `${CONSTVALUE(path.node.property)}`;
+      if (typeof current === 'string' && /^[$_a-z][$_a-z\d]*$/i.test(current)) {
+        path.node.computed = false;
+        path.node.property = {
+          type: 'Identifier',
+          name: current,
+        };
+        return path;
+      }
+    }
+    if (IS_CONSTEXPR(path.node.object)) {
+      const value = CONSTVALUE(path.node.object);
+      if (typeof value === 'string' || Array.isArray(value) || (value && typeof value === 'object')) {
+        let key;
+        if (IS_CONSTEXPR(path.node.property)) {
+          key = `${CONSTVALUE(path.node.property)}`;
+        }
+        else if (!path.node.computed) {
+          key = path.node.property.name;
+        }
+        if (key !== void 0) {
+          const desc = Object.getOwnPropertyDescriptor(value, key);
+          if (desc) {
+            const folded = value[key];
+            console.error('FOLDING', JSON.stringify(folded));
+            if (IN_PRAGMA_POS(path) && typeof folded === 'string') {
+              if (value.length > 1) {
+                REPLACE(
+                  path.get(['object']),
+                  TO_CONSTEXPR(value.slice(key, key + 1))
+                );
+                REPLACE(path.get(['property']), TO_CONSTEXPR(0));
+                return path;
+              }
+            } else {
+              return REPLACE(path, TO_CONSTEXPR(value[key]));
+            }
+          }
+        }
+      }
+    }
+  }
+  return yield path;
+};
+
+const $MIN = Symbol();
+const MIN_TRUE = Object.freeze({
+  [$MIN]: true,
+  type: 'UnaryExpression',
+  operator: '!',
+  argument: Object.freeze({
+    [$MIN]: true,
+    type: 'Literal',
+    value: 0
+  })
+});
+const MIN_FALSE = Object.freeze({
+  [$MIN]: true,
+  type: 'UnaryExpression',
+  operator: '!',
+  argument: Object.freeze({
+    [$MIN]: true,
+    type: 'Literal',
+    value: 1
+  })
+});
+const MIN_REPLACEMENTS = new Map;
+MIN_REPLACEMENTS.set(true, MIN_TRUE);
+MIN_REPLACEMENTS.set(false, MIN_FALSE);
+const MIN_VALUES = function*(path) {
+  if (path && path.node && !path.node[$MIN] && IS_CONSTEXPR(path.node)) {
+    let value = CONSTVALUE(path.node);
+    if (MIN_REPLACEMENTS.has(value)) {
+      console.error('MIN_VALUE', value)
+      return REPLACE(path, MIN_REPLACEMENTS.get(value));
+    }
+  }
+  return yield path;
+}
+
+import esprima from 'esprima';
+import util from 'util';
+import escodegen from 'escodegen';
+const optimize = (src) => {
+    const ROOT = new NodePath(
+      null,
+      esprima.parse(
+        src,
+        {
+          // loc: true,
+          // source: '<stdin>',
+        }
+      ),
+      null
+    );
+    // all of these are things that could affect completion value positions
+    const walk_expressions = WalkCombinator.pipe(
+      ...[
+        WalkCombinator.DEPTH_FIRST,
+        {
+          // We never work on Arrays
+          *inputs(path) {
+            if (Array.isArray(path)) return;
+            return yield path;
+          },
+        },
+        { inputs: FOLD_UNREACHABLE },
+        { inputs: FOLD_IF },
+        { inputs: FOLD_SWITCH },
+        { inputs: FOLD_EXPR_STMT },
+        { inputs: FOLD_CONDITIONAL },
+        { inputs: FOLD_LOGICAL },
+        { inputs: FOLD_BINARY },
+        { inputs: FOLD_UNARY },
+        { inputs: FOLD_SEQUENCE },
+        { inputs: FOLD_MEMBER },
+        { inputs: FOLD_EMPTY },
+        { inputs: FOLD_WHILE },
+        { inputs: FOLD_EVAL },
+      ]
+    ).walk(ROOT);
+    for (const _ of walk_expressions) {
+    }
+    const minify = WalkCombinator.pipe(
+      ...[
+        WalkCombinator.DEPTH_FIRST,
+        {
+          // We never work on Arrays
+          *inputs(path) {
+            if (Array.isArray(path)) return;
+            return yield path;
+          },
+        },
+        { inputs: MIN_VALUES },
+      ]
+    ).walk(ROOT);
+    for (const _ of minify) {
+    }
+    return ROOT;
+}
+import mississippi from 'mississippi';
+process.stdin.pipe(
+  mississippi.concat(buff => {
+    const ROOT = optimize(`${buff}`)
+    console.error(
+      '%s',
+      util.inspect(ROOT.node, {
+        depth: null,
+        colors: true,
+      })
+    );
+    const out = escodegen.generate(ROOT.node);
+    console.log(out);
+  })
+);

samples/JavaScript/entry.mjs

@@ -0,0 +1,6 @@
+import bar from './module.mjs';
+function foo() {
+  return "I am foo";
+}
+export {foo};
+console.log(bar);

samples/JavaScript/module.mjs

@@ -0,0 +1,5 @@
+import {foo} from './entry.mjs';
+console.log(foo());
+
+const bar = "I am bar.";
+export {bar as default};

samples/Nearley/nearley-language-bootstrapped.ne

@@ -0,0 +1,106 @@
+# nearley grammar
+@builtin "string.ne"
+
+@{%
+
+function insensitive(sl) {
+    var s = sl.literal;
+    result = [];
+    for (var i=0; i<s.length; i++) {
+        var c = s.charAt(i);
+        if (c.toUpperCase() !== c || c.toLowerCase() !== c) {
+            result.push(new RegExp("[" + c.toLowerCase() + c.toUpperCase() + "]"));
+        } else {
+            result.push({literal: c});
+        }
+    }
+    return {subexpression: [{tokens: result, postprocess: function(d) {return d.join(""); }}]};
+}
+
+%}
+
+final -> whit? prog whit?  {% function(d) { return d[1]; } %}
+
+prog -> prod  {% function(d) { return [d[0]]; } %}
+      | prod whit prog  {% function(d) { return [d[0]].concat(d[2]); } %}
+
+prod -> word whit? ("-"|"="):+ ">" whit? expression+  {% function(d) { return {name: d[0], rules: d[5]}; } %}
+      | word "[" wordlist "]" whit? ("-"|"="):+ ">" whit? expression+ {% function(d) {return {macro: d[0], args: d[2], exprs: d[8]}} %}
+      | "@" whit? js  {% function(d) { return {body: d[2]}; } %}
+      | "@" word whit word  {% function(d) { return {config: d[1], value: d[3]}; } %}
+      | "@include"  whit? string {% function(d) {return {include: d[2].literal, builtin: false}} %}
+      | "@builtin"  whit? string {% function(d) {return {include: d[2].literal, builtin: true }} %}
+
+expression+ -> completeexpression
+             | expression+ whit? "|" whit? completeexpression  {% function(d) { return d[0].concat([d[4]]); } %}
+
+expressionlist -> completeexpression
+             | expressionlist whit? "," whit? completeexpression {% function(d) { return d[0].concat([d[4]]); } %}
+
+wordlist -> word
+            | wordlist whit? "," whit? word {% function(d) { return d[0].concat([d[4]]); } %}
+
+completeexpression -> expr  {% function(d) { return {tokens: d[0]}; } %}
+                    | expr whit? js  {% function(d) { return {tokens: d[0], postprocess: d[2]}; } %}
+
+expr_member ->
+      word {% id %}
+    | "$" word {% function(d) {return {mixin: d[1]}} %}
+    | word "[" expressionlist "]" {% function(d) {return {macrocall: d[0], args: d[2]}} %} 
+    | string "i":? {% function(d) { if (d[1]) {return insensitive(d[0]); } else {return d[0]; } } %}
+    | "%" word {% function(d) {return {token: d[1]}} %}
+    | charclass {% id %}
+    | "(" whit? expression+ whit? ")" {% function(d) {return {'subexpression': d[2]} ;} %}
+    | expr_member whit? ebnf_modifier {% function(d) {return {'ebnf': d[0], 'modifier': d[2]}; } %}
+
+ebnf_modifier -> ":+" {% id %} | ":*" {% id %} | ":?" {% id %}
+
+expr -> expr_member
+      | expr whit expr_member  {% function(d){ return d[0].concat([d[2]]); } %}
+
+word -> [\w\?\+]  {% function(d){ return d[0]; } %}
+      | word [\w\?\+]  {% function(d){ return d[0]+d[1]; } %}
+
+string -> dqstring {% function(d) {return { literal: d[0] }; } %}
+#string -> "\"" charset "\""  {% function(d) { return { literal: d[1].join("") }; } %}
+#
+#charset -> null
+#         | charset char  {% function(d) { return d[0].concat([d[1]]); } %}
+#
+#char -> [^\\"]  {% function(d) { return d[0]; } %}
+#      | "\\" .  {% function(d) { return JSON.parse("\""+"\\"+d[1]+"\""); } %}
+
+charclass -> "."  {% function(d) { return new RegExp("."); } %}
+           | "[" charclassmembers "]"  {% function(d) { return new RegExp("[" + d[1].join('') + "]"); } %}
+
+charclassmembers -> null
+                  | charclassmembers charclassmember  {% function(d) { return d[0].concat([d[1]]); } %}
+
+charclassmember -> [^\\\]]  {% function(d) { return d[0]; } %}
+                 | "\\" .  {% function(d) { return d[0] + d[1]; } %}
+
+js -> "{" "%" jscode "%" "}"  {% function(d) { return d[2]; } %}
+
+jscode -> null  {% function() {return "";} %}
+        | jscode [^%]  {% function(d) {return d[0] + d[1];} %}
+        | jscode "%" [^}] {% function(d) {return d[0] + d[1] + d[2]; } %}
+
+# Whitespace with a comment
+whit -> whitraw
+      | whitraw? comment whit?
+
+# Optional whitespace with a comment
+whit? -> null
+       | whit
+
+# Literally a string of whitespace
+whitraw -> [\s]
+         | whitraw [\s]
+
+# A string of whitespace OR the empty string
+whitraw? -> null
+          | whitraw
+
+comment -> "#" commentchars "\n"
+commentchars -> null
+              | commentchars [^\n]

samples/OpenEdge ABL/test-win.w

@@ -0,0 +1,230 @@
+&ANALYZE-SUSPEND _VERSION-NUMBER AB_v10r12 GUI
+&ANALYZE-RESUME
+&Scoped-define WINDOW-NAME C-Win
+&ANALYZE-SUSPEND _UIB-CODE-BLOCK _CUSTOM _DEFINITIONS C-Win 
+/*------------------------------------------------------------------------
+
+  File: 
+
+  Description: 
+
+  Input Parameters:
+      <none>
+
+  Output Parameters:
+      <none>
+
+  Author: 
+
+  Created: 
+
+------------------------------------------------------------------------*/
+/*          This .W file was created with the Progress AppBuilder.      */
+/*----------------------------------------------------------------------*/
+
+/* Create an unnamed pool to store all the widgets created 
+     by this procedure. This is a good default which assures
+     that this procedure's triggers and internal procedures 
+     will execute in this procedure's storage, and that proper
+     cleanup will occur on deletion of the procedure. */
+
+CREATE WIDGET-POOL.
+
+/* ***************************  Definitions  ************************** */
+
+/* Parameters Definitions ---                                           */
+
+/* Local Variable Definitions ---                                       */
+
+/* _UIB-CODE-BLOCK-END */
+&ANALYZE-RESUME
+
+
+&ANALYZE-SUSPEND _UIB-PREPROCESSOR-BLOCK 
+
+/* ********************  Preprocessor Definitions  ******************** */
+
+&Scoped-define PROCEDURE-TYPE Window
+&Scoped-define DB-AWARE no
+
+/* Name of designated FRAME-NAME and/or first browse and/or first query */
+&Scoped-define FRAME-NAME DEFAULT-FRAME
+
+/* Custom List Definitions                                              */
+/* List-1,List-2,List-3,List-4,List-5,List-6                            */
+
+/* _UIB-PREPROCESSOR-BLOCK-END */
+&ANALYZE-RESUME
+
+
+
+/* ***********************  Control Definitions  ********************** */
+
+/* Define the widget handle for the window                              */
+DEFINE VAR C-Win AS WIDGET-HANDLE NO-UNDO.
+
+/* ************************  Frame Definitions  *********************** */
+
+DEFINE FRAME DEFAULT-FRAME
+    WITH 1 DOWN NO-BOX KEEP-TAB-ORDER OVERLAY 
+         SIDE-LABELS NO-UNDERLINE THREE-D 
+         AT COL 1 ROW 1
+         SIZE 80 BY 16 WIDGET-ID 100.
+
+
+/* *********************** Procedure Settings ************************ */
+
+&ANALYZE-SUSPEND _PROCEDURE-SETTINGS
+/* Settings for THIS-PROCEDURE
+   Type: Window
+   Allow: Basic,Browse,DB-Fields,Window,Query
+   Other Settings: COMPILE
+ */
+&ANALYZE-RESUME _END-PROCEDURE-SETTINGS
+
+/* *************************  Create Window  ************************** */
+
+&ANALYZE-SUSPEND _CREATE-WINDOW
+IF SESSION:DISPLAY-TYPE = "GUI":U THEN
+  CREATE WINDOW C-Win ASSIGN
+         HIDDEN             = YES
+         TITLE              = "<insert window title>"
+         HEIGHT             = 16
+         WIDTH              = 80
+         MAX-HEIGHT         = 16
+         MAX-WIDTH          = 80
+         VIRTUAL-HEIGHT     = 16
+         VIRTUAL-WIDTH      = 80
+         RESIZE             = yes
+         SCROLL-BARS        = no
+         STATUS-AREA        = no
+         BGCOLOR            = ?
+         FGCOLOR            = ?
+         KEEP-FRAME-Z-ORDER = yes
+         THREE-D            = yes
+         MESSAGE-AREA       = no
+         SENSITIVE          = yes.
+ELSE {&WINDOW-NAME} = CURRENT-WINDOW.
+/* END WINDOW DEFINITION                                                */
+&ANALYZE-RESUME
+
+
+
+/* ***********  Runtime Attributes and AppBuilder Settings  *********** */
+
+&ANALYZE-SUSPEND _RUN-TIME-ATTRIBUTES
+/* SETTINGS FOR WINDOW C-Win
+  VISIBLE,,RUN-PERSISTENT                                               */
+/* SETTINGS FOR FRAME DEFAULT-FRAME
+   FRAME-NAME                                                           */
+IF SESSION:DISPLAY-TYPE = "GUI":U AND VALID-HANDLE(C-Win)
+THEN C-Win:HIDDEN = no.
+
+/* _RUN-TIME-ATTRIBUTES-END */
+&ANALYZE-RESUME
+
+ 
+
+
+
+/* ************************  Control Triggers  ************************ */
+
+&Scoped-define SELF-NAME C-Win
+&ANALYZE-SUSPEND _UIB-CODE-BLOCK _CONTROL C-Win C-Win
+ON END-ERROR OF C-Win /* <insert window title> */
+OR ENDKEY OF {&WINDOW-NAME} ANYWHERE DO:
+  /* This case occurs when the user presses the "Esc" key.
+     In a persistently run window, just ignore this.  If we did not, the
+     application would exit. */
+  IF THIS-PROCEDURE:PERSISTENT THEN RETURN NO-APPLY.
+END.
+
+/* _UIB-CODE-BLOCK-END */
+&ANALYZE-RESUME
+
+
+&ANALYZE-SUSPEND _UIB-CODE-BLOCK _CONTROL C-Win C-Win
+ON WINDOW-CLOSE OF C-Win /* <insert window title> */
+DO:
+  /* This event will close the window and terminate the procedure.  */
+  APPLY "CLOSE":U TO THIS-PROCEDURE.
+  RETURN NO-APPLY.
+END.
+
+/* _UIB-CODE-BLOCK-END */
+&ANALYZE-RESUME
+
+
+&UNDEFINE SELF-NAME
+
+&ANALYZE-SUSPEND _UIB-CODE-BLOCK _CUSTOM _MAIN-BLOCK C-Win 
+
+
+/* ***************************  Main Block  *************************** */
+
+/* Set CURRENT-WINDOW: this will parent dialog-boxes and frames.        */
+ASSIGN CURRENT-WINDOW                = {&WINDOW-NAME} 
+       THIS-PROCEDURE:CURRENT-WINDOW = {&WINDOW-NAME}.
+
+/* The CLOSE event can be used from inside or outside the procedure to  */
+/* terminate it.                                                        */
+ON CLOSE OF THIS-PROCEDURE 
+   RUN disable_UI.
+
+/* Best default for GUI applications is...                              */
+PAUSE 0 BEFORE-HIDE.
+
+/* Now enable the interface and wait for the exit condition.            */
+/* (NOTE: handle ERROR and END-KEY so cleanup code will always fire.    */
+MAIN-BLOCK:
+DO ON ERROR   UNDO MAIN-BLOCK, LEAVE MAIN-BLOCK
+   ON END-KEY UNDO MAIN-BLOCK, LEAVE MAIN-BLOCK:
+  RUN enable_UI.
+  IF NOT THIS-PROCEDURE:PERSISTENT THEN
+    WAIT-FOR CLOSE OF THIS-PROCEDURE.
+END.
+
+/* _UIB-CODE-BLOCK-END */
+&ANALYZE-RESUME
+
+
+/* **********************  Internal Procedures  *********************** */
+
+&ANALYZE-SUSPEND _UIB-CODE-BLOCK _PROCEDURE disable_UI C-Win  _DEFAULT-DISABLE
+PROCEDURE disable_UI :
+/*------------------------------------------------------------------------------
+  Purpose:     DISABLE the User Interface
+  Parameters:  <none>
+  Notes:       Here we clean-up the user-interface by deleting
+               dynamic widgets we have created and/or hide 
+               frames.  This procedure is usually called when
+               we are ready to "clean-up" after running.
+------------------------------------------------------------------------------*/
+  /* Delete the WINDOW we created */
+  IF SESSION:DISPLAY-TYPE = "GUI":U AND VALID-HANDLE(C-Win)
+  THEN DELETE WIDGET C-Win.
+  IF THIS-PROCEDURE:PERSISTENT THEN DELETE PROCEDURE THIS-PROCEDURE.
+END PROCEDURE.
+
+/* _UIB-CODE-BLOCK-END */
+&ANALYZE-RESUME
+
+&ANALYZE-SUSPEND _UIB-CODE-BLOCK _PROCEDURE enable_UI C-Win  _DEFAULT-ENABLE
+PROCEDURE enable_UI :
+/*------------------------------------------------------------------------------
+  Purpose:     ENABLE the User Interface
+  Parameters:  <none>
+  Notes:       Here we display/view/enable the widgets in the
+               user-interface.  In addition, OPEN all queries
+               associated with each FRAME and BROWSE.
+               These statements here are based on the "Other 
+               Settings" section of the widget Property Sheets.
+------------------------------------------------------------------------------*/
+  VIEW FRAME DEFAULT-FRAME IN WINDOW C-Win.
+  {&OPEN-BROWSERS-IN-QUERY-DEFAULT-FRAME}
+  VIEW C-Win.
+END PROCEDURE.
+
+/* _UIB-CODE-BLOCK-END */
+&ANALYZE-RESUME
+

samples/PostCSS/sample.pcss

@@ -0,0 +1,13 @@
+@define-mixin size $size {
+  width: $size;
+}
+
+$big: 100px;
+
+/* Main block */
+.block {
+  &_logo {
+    background: inline("./logo.png");
+    @mixin size $big;
+  }
+}

samples/SugarSS/sample.sss

@@ -0,0 +1,10 @@
+@define-mixin size $size
+  width: $size
+
+$big: 100px
+
+// Main block
+.block
+  &_logo
+    background: inline("./logo.png")
+    @mixin size $big

samples/TypeScript/cache.ts

@@ -0,0 +1,102 @@
+import { DocumentNode } from 'graphql';
+import { getFragmentQueryDocument } from 'apollo-utilities';
+
+import { DataProxy, Cache } from './types';
+
+export type Transaction<T> = (c: ApolloCache<T>) => void;
+
+export abstract class ApolloCache<TSerialized> implements DataProxy {
+  // required to implement
+  // core API
+  public abstract read<T>(query: Cache.ReadOptions): T;
+  public abstract write(write: Cache.WriteOptions): void;
+  public abstract diff<T>(query: Cache.DiffOptions): Cache.DiffResult<T>;
+  public abstract watch(watch: Cache.WatchOptions): () => void;
+  public abstract evict(query: Cache.EvictOptions): Cache.EvictionResult;
+  public abstract reset(): Promise<void>;
+
+  // intializer / offline / ssr API
+  /**
+   * Replaces existing state in the cache (if any) with the values expressed by
+   * `serializedState`.
+   *
+   * Called when hydrating a cache (server side rendering, or offline storage),
+   * and also (potentially) during hot reloads.
+   */
+  public abstract restore(
+    serializedState: TSerialized,
+  ): ApolloCache<TSerialized>;
+
+  /**
+   * Exposes the cache's complete state, in a serializable format for later restoration.
+   */
+  public abstract extract(optimistic: boolean): TSerialized;
+
+  // optimistic API
+  public abstract removeOptimistic(id: string): void;
+
+  // transactional API
+  public abstract performTransaction(
+    transaction: Transaction<TSerialized>,
+  ): void;
+  public abstract recordOptimisticTransaction(
+    transaction: Transaction<TSerialized>,
+    id: string,
+  ): void;
+
+  // optional API
+  public transformDocument(document: DocumentNode): DocumentNode {
+    return document;
+  }
+  // experimental
+  public transformForLink(document: DocumentNode): DocumentNode {
+    return document;
+  }
+
+  // DataProxy API
+  /**
+   *
+   * @param options
+   * @param optimistic
+   */
+  public readQuery<QueryType>(
+    options: DataProxy.Query,
+    optimistic: boolean = false,
+  ): QueryType {
+    return this.read({
+      query: options.query,
+      variables: options.variables,
+      optimistic,
+    });
+  }
+
+  public readFragment<FragmentType>(
+    options: DataProxy.Fragment,
+    optimistic: boolean = false,
+  ): FragmentType | null {
+    return this.read({
+      query: getFragmentQueryDocument(options.fragment, options.fragmentName),
+      variables: options.variables,
+      rootId: options.id,
+      optimistic,
+    });
+  }
+
+  public writeQuery(options: Cache.WriteQueryOptions): void {
+    this.write({
+      dataId: 'ROOT_QUERY',
+      result: options.data,
+      query: options.query,
+      variables: options.variables,
+    });
+  }
+
+  public writeFragment(options: Cache.WriteFragmentOptions): void {
+    this.write({
+      dataId: options.id,
+      result: options.data,
+      variables: options.variables,
+      query: getFragmentQueryDocument(options.fragment, options.fragmentName),
+    });
+  }
+}

samples/XML/NDepends_Example.ndproj

@@ -0,0 +1,77 @@
+<?xml version="1.0" encoding="utf-8" standalone="yes"?>
+<NDepend AppName="ExampleNDApp" Platform="DotNet">
+  <OutputDir KeepHistoric="True" KeepXmlFiles="True">c:\temp</OutputDir>
+  <Assemblies />
+  <FrameworkAssemblies />
+  <Dirs>
+    <Dir>C:\Windows\Microsoft.NET\Framework\v4.0.30319</Dir>
+    <Dir>C:\Windows\Microsoft.NET\Framework\v4.0.30319\WPF</Dir>
+  </Dirs>
+  <Report Kind="0" SectionsEnabled="12287" XslPath="" Flags="64512">
+    <Section Enabled="True">Application Metrics</Section>
+    <Section Enabled="True">.NET Assemblies Metrics</Section>
+    <Section Enabled="True">Treemap Metric View</Section>
+    <Section Enabled="True">.NET Assemblies Abstractness vs. Instability</Section>
+    <Section Enabled="True">.NET Assemblies Dependencies</Section>
+    <Section Enabled="True">.NET Assemblies Dependency Graph</Section>
+    <Section Enabled="True">.NET Assemblies Build Order</Section>
+    <Section Enabled="True">Analysis Log</Section>
+    <Section Enabled="True">CQL Rules Violated</Section>
+    <Section Enabled="True">Types Metrics</Section>
+    <Section Enabled="False">Types Dependencies</Section>
+  </Report>
+  <BuildComparisonSetting ProjectMode="DontCompare" BuildMode="MostRecentAnalysisResultAvailable" ProjectFileToCompareWith="" BuildFileToCompareWith="" NDaysAgo="1" />
+  <BaselineInUISetting ProjectMode="DontCompare" BuildMode="MostRecentAnalysisResultAvailable" ProjectFileToCompareWith="" BuildFileToCompareWith="" NDaysAgo="1" />
+  <CoverageFiles UncoverableAttribute="" />
+  <SourceFileRebasing FromPath="" ToPath="" />
+  <Queries>
+    <Group Name="Code Quality" Active="True" ShownInReport="False">
+      <Query Active="True" DisplayList="True" DisplayStat="True" DisplaySelectionView="False" IsCriticalRule="False"><![CDATA[// <Name>Discard generated and designer Methods from JustMyCode</Name>
+// --- Make sure to make this query richer to discard generated methods from NDepend rules results ---
+notmycode 
+
+//
+// First define source files paths to discard
+//
+from a in Application.Assemblies 
+where a.SourceFileDeclAvailable 
+let asmSourceFilesPaths = a.SourceDecls.Select(s => s.SourceFile.FilePath)
+
+let sourceFilesPathsToDiscard = (
+    from filePath in asmSourceFilesPaths 
+    let filePathLower= filePath.ToString().ToLower()
+    where     
+      filePathLower.EndsWithAny(
+        ".g.cs",        // Popular pattern to name generated files.
+        ".g.vb",
+        ".xaml",        // notmycode WPF xaml code
+        ".designer.cs", // notmycode C# Windows Forms designer code
+        ".designer.vb") // notmycode VB.NET Windows Forms designer code
+       ||
+       // notmycode methods in source files in a directory containing generated
+       filePathLower.Contains("generated")
+  select filePath
+).ToHashSet() 
+  
+//
+// Second: discard methods in sourceFilesPathsToDiscard 
+//
+from m in a.ChildMethods
+where (m.SourceFileDeclAvailable && 
+       sourceFilesPathsToDiscard.Contains(m.SourceDecls.First().SourceFile.FilePath)) ||
+      // Generated methods might be tagged with this attribute
+      m.HasAttribute ("System.CodeDom.Compiler.GeneratedCodeAttribute".AllowNoMatch())
+select new { m, m.NbLinesOfCode }]]></Query>
+      <Query Active="True" DisplayList="True" DisplayStat="True" DisplaySelectionView="False" IsCriticalRule="False"><![CDATA[// <Name>Discard generated Fields from JustMyCode</Name>
+// --- Make sure to make this query richer to discard generated fields from NDepend rules results ---
+notmycode
+from f in Application.Fields where 
+  f.HasAttribute ("System.CodeDom.Compiler.GeneratedCodeAttribute".AllowNoMatch()) ||
+
+  // Eliminate "components" generated in Windows Form Conrol context
+  f.Name == "components" && f.ParentType.DeriveFrom("System.Windows.Forms.Control".AllowNoMatch())
+select f]]></Query>
+    </Group>
+  </Queries>
+  <WarnFilter />
+</NDepend>

samples/XML/chrome.natvis

@@ -0,0 +1,183 @@
+<?xml version="1.0" encoding="utf-8" ?>
+<!-- 
+Copyright 2015 The Chromium Authors. All rights reserved.
+
+https://cs.chromium.org/chromium/src/tools/win/DebugVisualizers/chrome.natvis
+-->
+<AutoVisualizer
+    xmlns="http://schemas.microsoft.com/vstudio/debugger/natvis/2010">
+  <Type Name="gfx::Point">
+    <AlternativeType Name="gfx::PointF"/>
+    <DisplayString>({x_}, {y_})</DisplayString>
+  </Type>
+  <Type Name="gfx::Size">
+    <AlternativeType Name="gfx::SizeF"/>
+    <DisplayString>({width_}, {height_})</DisplayString>
+  </Type>
+  <Type Name="gfx::Rect">
+    <AlternativeType Name="gfx::RectF"/>
+    <DisplayString>({origin_.x_}, {origin_.y_}) x ({size_.width_}, {size_.height_})</DisplayString>
+  </Type>
+  <Type Name="scoped_refptr&lt;*&gt;">
+    <DisplayString Condition="ptr_ == 0">null</DisplayString>
+    <DisplayString>[{((base::subtle::RefCountedBase*)ptr_)-&gt;ref_count_}] {(void*)ptr_} {*ptr_}</DisplayString>
+    <Expand>
+      <Item Name="Ptr">ptr_</Item>
+      <Item Name="RefCount">((base::subtle::RefCountedBase*)ptr_)-&gt;ref_count_</Item>
+    </Expand>
+  </Type>
+  <Type Name="base::Optional&lt;*&gt;">
+    <DisplayString Condition="storage_.is_null_">(null)</DisplayString>
+    <DisplayString>{storage_.value_}</DisplayString>
+  </Type>
+  <Type Name="base::RefCounted&lt;*&gt;">
+    <DisplayString>RefCount: {ref_count_}</DisplayString>
+    <Expand>
+      <Item Name="RefCount">ref_count_</Item>
+    </Expand>
+  </Type>
+  <Type Name="IPC::Message::Header">
+    <DisplayString>{{Routing: {routing}, Type: {type}}}</DisplayString>
+    <Expand>
+      <Item Name="RoutingId">routing</Item>
+      <Item Name="Type">type</Item>
+      <Synthetic Name="Priority"
+                 Condition="(flags &amp; IPC::Message::PRIORITY_MASK) ==
+                                IPC::Message::PRIORITY_LOW">
+        <DisplayString>Low</DisplayString>
+      </Synthetic>
+      <Synthetic Name="Priority"
+                 Condition="(flags &amp; IPC::Message::PRIORITY_MASK) ==
+                                IPC::Message::PRIORITY_NORMAL">
+        <DisplayString>Normal</DisplayString>
+      </Synthetic>
+      <Synthetic Name="Priority"
+                 Condition="(flags &amp; IPC::Message::PRIORITY_MASK) ==
+                                IPC::Message::PRIORITY_HIGH">
+        <DisplayString>High</DisplayString>
+      </Synthetic>
+      <Synthetic Name="Sync"
+                 Condition="(flags &amp; IPC::Message::SYNC_BIT) != 0">
+        <DisplayString>true</DisplayString>
+      </Synthetic>
+      <Synthetic Name="Sync"
+                 Condition="(flags &amp; IPC::Message::SYNC_BIT) == 0">
+        <DisplayString>false</DisplayString>
+      </Synthetic>
+      <Synthetic Name="Reply"
+                 Condition="(flags &amp; IPC::Message::REPLY_BIT) != 0">
+        <DisplayString>true</DisplayString>
+      </Synthetic>
+      <Synthetic Name="Reply"
+                 Condition="(flags &amp; IPC::Message::REPLY_BIT) == 0">
+        <DisplayString>false</DisplayString>
+      </Synthetic>
+      <Synthetic Name="ReplyError"
+                 Condition="(flags &amp; IPC::Message::REPLY_ERROR_BIT) != 0">
+        <DisplayString>true</DisplayString>
+      </Synthetic>
+      <Synthetic Name="ReplyError"
+                 Condition="(flags &amp; IPC::Message::REPLY_ERROR_BIT) == 0">
+        <DisplayString>false</DisplayString>
+      </Synthetic>
+      <Synthetic Name="Unblock"
+                 Condition="(flags &amp; IPC::Message::UNBLOCK_BIT) != 0">
+        <DisplayString>true</DisplayString>
+      </Synthetic>
+      <Synthetic Name="Unblock"
+                 Condition="(flags &amp; IPC::Message::UNBLOCK_BIT) == 0">
+        <DisplayString>false</DisplayString>
+      </Synthetic>
+      <Synthetic Name="PumpingMessages"
+                 Condition="(flags &amp; IPC::Message::PUMPING_MSGS_BIT) != 0">
+        <DisplayString>true</DisplayString>
+      </Synthetic>
+      <Synthetic Name="PumpingMessages"
+                 Condition="(flags &amp; IPC::Message::PUMPING_MSGS_BIT) == 0">
+        <DisplayString>false</DisplayString>
+      </Synthetic>
+      <Synthetic Name="HasSentTime"
+                 Condition="(flags &amp; IPC::Message::HAS_SENT_TIME_BIT) != 0">
+        <DisplayString>true</DisplayString>
+      </Synthetic>
+      <Synthetic Name="HasSentTime"
+                 Condition="(flags &amp; IPC::Message::HAS_SENT_TIME_BIT) == 0">
+        <DisplayString>false</DisplayString>
+      </Synthetic>
+    </Expand>
+  </Type>
+  <Type Name="IPC::Message">
+    <DisplayString>{{size = {header_size_+capacity_after_header_}}}</DisplayString>
+    <Expand>
+      <ExpandedItem>*((IPC::Message::Header*)header_),nd</ExpandedItem>
+      <Item Name="Payload">(void*)((char*)header_ + header_size_)</Item>
+    </Expand>
+  </Type>
+  <Type Name="base::TimeDelta">
+    <DisplayString>{delta_}</DisplayString>
+    <Expand>
+      <Synthetic Name="Days">
+        <DisplayString>{(int)(delta_ / {,,base.dll}base::Time::kMicrosecondsPerDay)}</DisplayString>
+      </Synthetic>
+      <Synthetic Name="Hours">
+        <DisplayString>{(int)(delta_ / {,,base.dll}base::Time::kMicrosecondsPerHour)}</DisplayString>
+      </Synthetic>
+      <Synthetic Name="Minutes">
+        <DisplayString>{(int)(delta_ / {,,base.dll}base::Time::kMicrosecondsPerMinute)}</DisplayString>
+      </Synthetic>
+      <Synthetic Name="Seconds">
+        <DisplayString>{(int)(delta_ / {,,base.dll}base::Time::kMicrosecondsPerSecond)}</DisplayString>
+      </Synthetic>
+      <Synthetic Name="Milliseconds">
+        <DisplayString>{(int)(delta_ / {,,base.dll}base::Time::kMicrosecondsPerMillisecond)}</DisplayString>
+      </Synthetic>
+      <Item Name="Microseconds">delta_</Item>
+    </Expand>
+  </Type>
+  <Type Name="GURL">
+    <DisplayString>{spec_}</DisplayString>
+  </Type>
+  <Type Name="base::ManualConstructor&lt;*&gt;">
+    <!-- $T1 expands to the first "*" in the name which is the template
+         type. Use that to cast to the correct value. -->
+    <DisplayString>{*($T1*)space_.data_}</DisplayString>
+    <Expand>
+      <ExpandedItem>*($T1*)space_.data_</ExpandedItem>
+    </Expand>
+  </Type>
+  <Type Name="base::internal::flat_tree&lt;*&gt;">
+    <AlternativeType Name="base::flat_set&lt;*&gt;"/>
+    <DisplayString>{impl_.body_}</DisplayString>
+    <Expand>
+      <ExpandedItem>impl_.body_</ExpandedItem>
+    </Expand>
+  </Type>
+  <Type Name="base::flat_map&lt;*&gt;">
+    <DisplayString>{impl_.body_}</DisplayString>
+    <Expand>
+      <ExpandedItem>impl_.body_</ExpandedItem>
+    </Expand>
+  </Type>
+  <Type Name="base::Value">
+    <DisplayString Condition="type_ == NONE">NONE</DisplayString>
+    <DisplayString Condition="type_ == BOOLEAN">BOOLEAN {bool_value_}</DisplayString>
+    <DisplayString Condition="type_ == INTEGER">INTEGER {int_value_}</DisplayString>
+    <DisplayString Condition="type_ == DOUBLE">DOUBLE {double_value_}</DisplayString>
+    <DisplayString Condition="type_ == STRING">STRING {string_value_}</DisplayString>
+    <DisplayString Condition="type_ == BINARY">BINARY {binary_value_}</DisplayString>
+    <DisplayString Condition="type_ == DICTIONARY">DICTIONARY {dict_}</DisplayString>
+    <DisplayString Condition="type_ == LIST">LIST {list_}</DisplayString>
+    <Expand>
+      <Item Name="[type]">type_</Item>
+      <Item Condition="type_ == BOOLEAN" Name="[boolean]">bool_value_</Item>
+      <Item Condition="type_ == INTEGER" Name="[integer]">int_value_</Item>
+      <Item Condition="type_ == DOUBLE" Name="[double]">double_value_</Item>
+      <Item Condition="type_ == STRING" Name="[string]">string_value_</Item>
+      <Item Condition="type_ == BINARY" Name="[binary]">binary_value_</Item>
+      <!-- Put the members for dictionary and list directly inline without
+           requiring a separate expansion to view. -->
+      <ExpandedItem Condition="type_ == DICTIONARY">dict_</ExpandedItem>
+      <ExpandedItem Condition="type_ == LIST">list_</ExpandedItem>
+    </Expand>
+  </Type>
+</AutoVisualizer>

samples/XML/cloudconfig.cscfg

@@ -0,0 +1,9 @@
+<?xml version="1.0"?>
+<ServiceConfiguration serviceName="MyDef" xmlns="http://schemas.microsoft.com/ServiceHosting/2008/10/ServiceConfiguration">
+  <Role name="My.Web">
+    <Instances count="1" />
+    <ConfigurationSettings>
+      <Setting name="DiagnosticsConnectionString" value="UseDevelopmentStorage=true" />
+    </ConfigurationSettings>
+  </Role>
+</ServiceConfiguration>

samples/XML/clouddef.csdef

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="utf-8"?>
+<ServiceDefinition name="MyDef" xmlns="http://schemas.microsoft.com/ServiceHosting/2008/10/ServiceDefinition">
+  <WebRole name="My.Web">
+    <InputEndpoints>
+      <InputEndpoint name="HttpIn" protocol="http" port="80" />
+    </InputEndpoints>
+    <ConfigurationSettings>
+      <Setting name="DiagnosticsConnectionString" />
+    </ConfigurationSettings>
+  </WebRole>
+</ServiceDefinition>

samples/XML/configdef.cscfg

@@ -0,0 +1,9 @@
+<?xml version="1.0"?>
+<ServiceConfiguration serviceName="MyDef" xmlns="http://schemas.microsoft.com/ServiceHosting/2008/10/ServiceConfiguration">
+  <Role name="My.Web">
+    <Instances count="1" />
+    <ConfigurationSettings>
+      <Setting name="DiagnosticsConnectionString" value="UseDevelopmentStorage=true" />
+    </ConfigurationSettings>
+  </Role>
+</ServiceConfiguration>

samples/XML/dependency-example.depproj

@@ -0,0 +1,14 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003" DefaultTargets="Build">
+  <Import Project="$([MSBuild]::GetDirectoryNameOfFileAbove($(MSBuildThisFileDirectory), dir.props))\dir.props" />
+  <PropertyGroup>
+    <AssemblyVersion>3.9.0.0</AssemblyVersion>
+    <OutputType>Library</OutputType>
+    <PackageTargetFramework>dotnet5.1</PackageTargetFramework>
+    <NuGetTargetMoniker>.NETPlatform,Version=v5.1</NuGetTargetMoniker>
+  </PropertyGroup>
+  <ItemGroup>
+    <None Include="project.json" />
+  </ItemGroup>
+  <Import Project="$([MSBuild]::GetDirectoryNameOfFileAbove($(MSBuildThisFileDirectory), dir.targets))\dir.targets" />
+</Project>

samples/XML/example-sharedproj.shproj

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <PropertyGroup>
+    <ProjectGuid>{86244B26-C4AE-4F69-9315-B6148C0FE270}</ProjectGuid>
+  </PropertyGroup>
+  <Import Project="$(MSBuildExtensionsPath)\$(MSBuildToolsVersion)\Microsoft.Common.props" Condition="Exists('$(MSBuildExtensionsPath)\$(MSBuildToolsVersion)\Microsoft.Common.props')" />
+  <Import Project="$(MSBuildExtensionsPath32)\Microsoft\VisualStudio\v$(VisualStudioVersion)\CodeSharing\Microsoft.CodeSharing.Common.Default.props" />
+  <Import Project="$(MSBuildExtensionsPath32)\Microsoft\VisualStudio\v$(VisualStudioVersion)\CodeSharing\Microsoft.CodeSharing.Common.props" />
+  <Import Project="SharedProject.projitems" Label="Shared" />
+  <Import Project="$(MSBuildExtensionsPath32)\Microsoft\VisualStudio\v$(VisualStudioVersion)\CodeSharing\Microsoft.CodeSharing.CSharp.targets" />
+</Project>

samples/XML/example.ccproj

@@ -0,0 +1,38 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="4.0" DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <PropertyGroup>
+    <Configuration Condition=" '$(Configuration)' == '' ">Debug</Configuration>
+    <Platform Condition=" '$(Platform)' == '' ">AnyCPU</Platform>
+    <ProductVersion>1.0.0</ProductVersion>
+    <ProjectGuid>{0beae469-c1c6-4648-a2e5-0ae0ea9efffa}</ProjectGuid>
+    <OutputType>Library</OutputType>
+    <AppDesignerFolder>Properties</AppDesignerFolder>
+    <RootNamespace>MyDef</RootNamespace>
+    <AssemblyName>MyDef</AssemblyName>
+    <StartDevelopmentStorage>True</StartDevelopmentStorage>
+    <Name>My</Name>
+  </PropertyGroup>
+  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
+    <DebugSymbols>true</DebugSymbols>
+    <DebugType>full</DebugType>
+    <Optimize>false</Optimize>
+    <OutputPath>bin\Debug\</OutputPath>
+    <DefineConstants>DEBUG;TRACE</DefineConstants>
+    <ErrorReport>prompt</ErrorReport>
+    <WarningLevel>4</WarningLevel>
+  </PropertyGroup>
+  <!-- Items for the project -->
+  <ItemGroup>
+    <ServiceDefinition Include="ServiceDefinition.csdef" />
+    <ServiceConfiguration Include="ServiceConfiguration.cscfg" />
+  </ItemGroup>
+  <ItemGroup>
+    <ProjectReference Include="..\My.Web\My.Web.csproj">
+      <Name>My.Web</Name>
+      <Project>{1515c2c3-0b57-422c-a6f9-0891b86fb7d3}</Project>
+      <Private>True</Private>
+      <RoleType>Web</RoleType>
+      <RoleName>My.Web</RoleName>
+    </ProjectReference>
+  </ItemGroup>
+</Project>

samples/XML/msbuild-example.proj

@@ -0,0 +1,85 @@
+<Project xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <Import Project="$(MSBuildExtensionsPath)\MSBuildCommunityTasks\MSBuild.Community.Tasks.Targets"/>
+  <UsingTask TaskName="Microsoft.Build.Tasks.XmlPeek" AssemblyName="Microsoft.Build.Tasks.v4.0, Version=4.0.0.0, Culture=neutral, PublicKeyToken=b03f5f7f11d50a3a"/>
+  <UsingTask TaskName="Microsoft.Build.Tasks.XmlPoke" AssemblyName="Microsoft.Build.Tasks.v4.0, Version=4.0.0.0, Culture=neutral, PublicKeyToken=b03f5f7f11d50a3a"/>
+  <PropertyGroup>
+    <SolutionRoot>$(MSBuildProjectDirectory)\..</SolutionRoot>
+    <ProjectRoot>$(SolutionRoot)\Src\Bowerbird.Website</ProjectRoot>
+    <ArtifactsDir>$(SolutionRoot)\Release</ArtifactsDir>
+    <CurrentBuildDateStamp>$([System.DateTime]::Now.ToString("yyyyMMdd"))</CurrentBuildDateStamp>
+    <CurrentBuildTimeStamp>$([System.DateTime]::Now.ToString("hhmm"))</CurrentBuildTimeStamp>
+    <CurrentBuildDir>$(ArtifactsDir)\$(CurrentBuildDateStamp)-$(Configuration)</CurrentBuildDir>
+  </PropertyGroup>
+  <PropertyGroup>
+    <VersionMajor>0</VersionMajor>
+    <VersionMinor>1</VersionMinor>
+    <VersionPatch>0</VersionPatch>
+    <VersionPreRelease></VersionPreRelease>
+  </PropertyGroup>
+  <PropertyGroup>
+    <WebConfig>$(CurrentBuildDir)\Web.config</WebConfig>
+  </PropertyGroup>
+  <ItemGroup>
+    <PackageFiles Include="$(ProjectRoot)\**\*.*"
+                  Exclude="$(ProjectRoot)\bin\*.pdb;
+                  $(ProjectRoot)\bin\*.xml;
+                  $(ProjectRoot)\Logs\**\*.*;
+                  $(ProjectRoot)\obj\**\*.*;
+                  $(ProjectRoot)\test\**\*.*;
+                  $(ProjectRoot)\media\**\*.*;
+                  $(ProjectRoot)\**\*.orig;
+                  $(ProjectRoot)\*.config;
+                  $(ProjectRoot)\*.xml;
+                  $(ProjectRoot)\**\*.csproj;
+                  $(ProjectRoot)\*.csproj.user;">
+    </PackageFiles>
+    <ConfigFiles Include="$(ProjectRoot)\Web.config" >
+    </ConfigFiles>
+  </ItemGroup>
+  <Target Name="UpdateWebConfig"  Condition=" '$(CurrentBuildDateStamp)' != '' ">
+      <XmlPoke Namespaces="&lt;Namespace Prefix='msb' Uri='http://schemas.microsoft.com/developer/msbuild/2003'/&gt;"
+          XmlInputPath="$(WebConfig)"
+          Query="//add[@key='staticContentIncrement']/@value"
+          Value="$(CurrentBuildDateStamp)-$(CurrentBuildTimeStamp)" />
+    </Target>
+  <Target Name="CreateOutputDir">
+    <Message Text="Creating Directory $(CurrentBuildDir)" />
+    <RemoveDir Directories="$(CurrentBuildDir)" />
+    <Delete Files="$(CurrentBuildDir)" />
+    <MakeDir Directories="$(CurrentBuildDir)" />
+  </Target>
+  <Target Name="BuildMediaDirectories">
+    <MakeDir Directories="$(CurrentBuildDir)\media" />
+  </Target>
+  <Target Name="ConfigSettingsMessages">
+    <Message Text="Configuration is $(Configuration)" />
+    <Message Text="BuildNumber is $(BuildNumber)" />
+    <Message Text="ProjectRoot is $(ProjectRoot)" />
+    <Message Text="CurrentBuildDir is $(CurrentBuildDir)" />
+  </Target>
+  <Target Name="BuildSolution">
+    <MSBuild Projects="$(SolutionRoot)\Bowerbird.sln" Targets="Build" Properties="Configuration=$(Configuration)" />
+  </Target>
+  <Target Name="CopyFilesToReleaseDir">
+    <Copy SourceFiles="@(PackageFiles)" DestinationFiles="@(PackageFiles->'$(CurrentBuildDir)\%(RecursiveDir)%(Filename)%(Extension)')" />
+    <Copy SourceFiles="@(ConfigFiles)" DestinationFiles="$(CurrentBuildDir)\web.config" />
+  </Target>
+  <Target Name="ZipUpReleaseFiles">
+    <ItemGroup>
+      <ZipFiles Include="$(CurrentBuildDir)\**\*.*" Exclude="*.zip" />
+    </ItemGroup>
+    <Zip Files="@(ZipFiles)" WorkingDirectory="$(CurrentBuildDir)\$(Configuration)\" ZipFileName="$(CurrentBuildDateStamp)-$(Configuration).zip" ZipLevel="9" />
+  </Target>
+  <Target Name="CopyZipToReleaseDir" DependsOnTargets="ZipUpReleaseFiles">
+    <Copy SourceFiles="$(MSBuildProjectDirectory)\$(CurrentBuildDateStamp)-$(Configuration).zip" DestinationFiles="$(ArtifactsDir)\$(CurrentBuildDateStamp)-$(Configuration).zip" />
+    <Delete Files="$(MSBuildProjectDirectory)\$(CurrentBuildDateStamp)-$(Configuration).zip" />
+  </Target>
+  <Target Name="Build" DependsOnTargets="CreateOutputDir">
+    <CallTarget Targets="BuildMediaDirectories"/>
+    <CallTarget Targets="ConfigSettingsMessages"/>
+    <CallTarget Targets="BuildSolution"/>
+    <CallTarget Targets="CopyFilesToReleaseDir"/>
+    <CallTarget Targets="UpdateWebConfig" />
+    <CallTarget Targets="CopyZipToReleaseDir"/>
+  </Target>
+</Project>

samples/YAML/filenames/.clang-tidy

@@ -0,0 +1,30 @@
+---
+Checks:          'clang-diagnostic-*,clang-analyzer-*'
+WarningsAsErrors: ''
+HeaderFilterRegex: ''
+AnalyzeTemporaryDtors: false
+FormatStyle:     none
+User:            linguist-user
+CheckOptions:
+  - key:             google-readability-braces-around-statements.ShortStatementLines
+    value:           '1'
+  - key:             google-readability-function-size.StatementThreshold
+    value:           '800'
+  - key:             google-readability-namespace-comments.ShortNamespaceLines
+    value:           '10'
+  - key:             google-readability-namespace-comments.SpacesBeforeComments
+    value:           '2'
+  - key:             modernize-loop-convert.MaxCopySize
+    value:           '16'
+  - key:             modernize-loop-convert.MinConfidence
+    value:           reasonable
+  - key:             modernize-loop-convert.NamingStyle
+    value:           CamelCase
+  - key:             modernize-pass-by-value.IncludeStyle
+    value:           llvm
+  - key:             modernize-replace-auto-ptr.IncludeStyle
+    value:           llvm
+  - key:             modernize-use-nullptr.NullMacros
+    value:           'NULL'
+...
+

samples/YARA/OfExample.yar

@@ -0,0 +1,23 @@
+rule OfExample2
+{
+    strings:
+        $foo1 = "foo1"
+        $foo2 = "foo2"
+        $foo3 = "foo3"
+
+    condition:
+        2 of ($foo*)  // equivalent to 2 of ($foo1,$foo2,$foo3)
+}
+
+rule OfExample3
+{
+    strings:
+        $foo1 = "foo1"
+        $foo2 = "foo2"
+
+        $bar1 = "bar1"
+        $bar2 = "bar2"
+
+    condition:
+        3 of ($foo*,$bar1,$bar2)
+}

samples/YARA/example.yara

@@ -0,0 +1,13 @@
+rule silent_banker : banker
+{
+    meta:
+        description = "This is just an example"
+        thread_level = 3
+        in_the_wild = true
+    strings:
+        $a = {6A 40 68 00 30 00 00 6A 14 8D 91}
+        $b = {8D 4D B0 2B C1 83 C0 27 99 6A 4E 59 F7 F9}
+        $c = "UVODFRYSIHLNWPEJXQZAKCBGMT"
+    condition:
+        $a or $b or $c
+}

samples/YARA/true.yar

@@ -0,0 +1 @@
+rule test { condition: true }

samples/wdl/hello.wdl

@@ -0,0 +1,21 @@
+# Sample originally from https://github.com/broadinstitute/centaur
+
+task hello {
+  String addressee
+  command {
+    echo "Hello ${addressee}!"
+  }
+  output {
+    String salutation = read_string(stdout())
+  }
+  runtime {
+    docker: "ubuntu@sha256:71cd81252a3563a03ad8daee81047b62ab5d892ebbfbf71cf53415f29c130950"
+  }
+}
+
+workflow wf_hello {
+  call hello
+  output {
+     hello.salutation
+  }
+}

samples/wdl/ifs_in_scatters.wdl

@@ -0,0 +1,44 @@
+# Sample originally from https://github.com/broadinstitute/centaur
+
+task validate_int {
+  Int i
+  command {
+    echo $(( ${i} % 2 ))
+  }
+  output {
+    Boolean validation = read_int(stdout()) == 1
+  }
+  runtime {
+    docker: "ubuntu:latest"
+  }
+}
+
+task mirror {
+  Int i
+  command {
+    echo ${i}
+  }
+  output {
+    Int out = read_int(stdout())
+  }
+  runtime {
+    docker: "ubuntu:latest"
+  }
+}
+
+workflow ifs_in_scatters {
+  Array[Int] numbers = range(5)
+
+  scatter (n in numbers) {
+
+    call validate_int { input: i = n }
+    if (validate_int.validation) {
+      Int incremented = n + 1
+      call mirror { input: i = incremented }
+    }
+  }
+
+  output {
+    Array[Int?] mirrors = mirror.out
+  }
+}

samples/wdl/passingfiles.wdl

@@ -0,0 +1,42 @@
+# Sample originally from https://github.com/broadinstitute/centaur
+
+##
+# Check that we can:
+# - Create a file from a task and feed it into subsequent commands.
+# - Create a file output by interpolating a file name
+# - Use engine functions on an interpolated file name
+##
+
+task mkFile {
+  command { 
+    echo "small file contents" > out.txt
+  }
+  output { File out = "out.txt" }
+  runtime { docker: "ubuntu:latest" }
+}
+
+task consumeFile {
+  File in_file
+  String out_name
+
+  command {
+    cat ${in_file} > ${out_name}
+  }
+  runtime {
+    docker: "ubuntu:latest"
+  }
+  output {
+    File out_interpolation = "${out_name}"
+    String contents = read_string("${out_name}")
+    String contentsAlt = read_string(out_interpolation)
+  }
+}
+
+workflow filepassing {
+  call mkFile
+  call consumeFile {input: in_file=mkFile.out, out_name = "myFileName.abc.txt" }
+  output {
+      consumeFile.contents
+      consumeFile.contentsAlt
+  }
+}

script/add-grammar

@@ -1,6 +1,7 @@
 #!/usr/bin/env ruby
 
 require "optparse"
+require "open3"
 
 ROOT = File.expand_path("../../", __FILE__)
 
@@ -42,6 +43,17 @@ def log(msg)
   puts msg if $verbose
 end
 
+def command(*args)
+  log "$ #{args.join(' ')}"
+  output, status = Open3.capture2e(*args)
+  if !status.success?
+    output.each_line do |line|
+      log "  > #{line}"
+    end
+    warn "Command failed. Aborting."
+    exit 1
+  end
+end
 
 usage = """Usage:
   #{$0} [-v|--verbose] [--replace grammar] url
@@ -51,12 +63,12 @@ Examples:
 """
 
 $replace = nil
-$verbose = false
+$verbose = true
 
 OptionParser.new do |opts|
   opts.banner = usage
-  opts.on("-v", "--verbose", "Print verbose feedback to STDOUT") do
-    $verbose = true
+  opts.on("-q", "--quiet", "Do not print output unless there's a failure") do
+    $verbose = false
   end
   opts.on("-rSUBMODULE", "--replace=SUBMODDULE", "Replace an existing grammar submodule.") do |name|
     $replace = name
@@ -82,23 +94,22 @@ Dir.chdir(ROOT)
 
 if repo_old
   log "Deregistering: #{repo_old}"
-  `git submodule deinit #{repo_old}`
-  `git rm -rf #{repo_old}`
-  `script/convert-grammars`
+  command('git', 'submodule', 'deinit', repo_old)
+  command('git', 'rm', '-rf', repo_old)
+  command('script/grammar-compiler', 'update', '-f')
 end
 
 log "Registering new submodule: #{repo_new}"
-`git submodule add -f #{https} #{repo_new}`
-exit 1 if $?.exitstatus > 0
-`script/convert-grammars --add #{repo_new}`
+command('git', 'submodule', 'add', '-f', https, repo_new)
+command('script/grammar-compiler', 'add', repo_new)
 
 log "Confirming license"
 if repo_old
-  `script/licensed`
+  command('script/licensed')
 else
-  `script/licensed --module "#{repo_new}"`
+  command('script/licensed', '--module', repo_new)
 end
 
-log "Updating grammar documentation in vendor/REAEDME.md"
-`bundle exec rake samples`
-`script/list-grammars`
+log "Updating grammar documentation in vendor/README.md"
+command('bundle', 'exec', 'rake', 'samples')
+command('script/list-grammars')

script/convert-grammars

@@ -1,319 +0,0 @@
-#!/usr/bin/env ruby
-
-require 'bundler/setup'
-require 'json'
-require 'net/http'
-require 'optparse'
-require 'plist'
-require 'set'
-require 'thread'
-require 'tmpdir'
-require 'uri'
-require 'yaml'
-
-ROOT = File.expand_path("../..", __FILE__)
-GRAMMARS_PATH = File.join(ROOT, "grammars")
-SOURCES_FILE = File.join(ROOT, "grammars.yml")
-CSONC = File.join(ROOT, "node_modules", ".bin", "csonc")
-
-$options = {
-  :add => false,
-  :install => true,
-  :output => SOURCES_FILE,
-  :remote => true,
-}
-
-class SingleFile
-  def initialize(path)
-    @path = path
-  end
-
-  def url
-    @path
-  end
-
-  def fetch(tmp_dir)
-    [@path]
-  end
-end
-
-class DirectoryPackage
-  def self.fetch(dir)
-    Dir["#{dir}/**/*"].select do |path|
-      case File.extname(path.downcase)
-      when '.plist'
-        path.split('/')[-2] == 'Syntaxes'
-      when '.tmlanguage', '.yaml-tmlanguage'
-        true
-      when '.cson', '.json'
-        path.split('/')[-2] == 'grammars'
-      else
-        false
-      end
-    end
-  end
-
-  def initialize(directory)
-    @directory = directory
-  end
-
-  def url
-    @directory
-  end
-
-  def fetch(tmp_dir)
-    self.class.fetch(File.join(ROOT, @directory))
-  end
-end
-
-class TarballPackage
-  def self.fetch(tmp_dir, url)
-    `curl --silent --location --max-time 30 --output "#{tmp_dir}/archive" "#{url}"`
-    raise "Failed to fetch GH package: #{url} #{$?.to_s}" unless $?.success?
-
-    output = File.join(tmp_dir, 'extracted')
-    Dir.mkdir(output)
-    `tar -C "#{output}" -xf "#{tmp_dir}/archive"`
-    raise "Failed to uncompress tarball: #{tmp_dir}/archive (from #{url}) #{$?.to_s}" unless $?.success?
-
-    DirectoryPackage.fetch(output)
-  end
-
-  attr_reader :url
-
-  def initialize(url)
-    @url = url
-  end
-
-  def fetch(tmp_dir)
-    self.class.fetch(tmp_dir, url)
-  end
-end
-
-class SingleGrammar
-  attr_reader :url
-
-  def initialize(url)
-    @url = url
-  end
-
-  def fetch(tmp_dir)
-    filename = File.join(tmp_dir, File.basename(url))
-    `curl --silent --location --max-time 10 --output "#{filename}" "#{url}"`
-    raise "Failed to fetch grammar: #{url}: #{$?.to_s}" unless $?.success?
-    [filename]
-  end
-end
-
-class SVNPackage
-  attr_reader :url
-
-  def initialize(url)
-    @url = url
-  end
-
-  def fetch(tmp_dir)
-    `svn export -q "#{url}/Syntaxes" "#{tmp_dir}/Syntaxes"`
-    raise "Failed to export SVN repository: #{url}: #{$?.to_s}" unless $?.success?
-    Dir["#{tmp_dir}/Syntaxes/*.{plist,tmLanguage,tmlanguage,YAML-tmLanguage}"]
-  end
-end
-
-class GitHubPackage
-  def self.parse_url(url)
-    url, ref = url.split("@", 2)
-    path = URI.parse(url).path.split('/')
-    [path[1], path[2].chomp('.git'), ref || "master"]
-  end
-
-  attr_reader :user
-  attr_reader :repo
-  attr_reader :ref
-
-  def initialize(url)
-    @user, @repo, @ref = self.class.parse_url(url)
-  end
-
-  def url
-    suffix = "@#{ref}" unless ref == "master"
-    "https://github.com/#{user}/#{repo}#{suffix}"
-  end
-
-  def fetch(tmp_dir)
-    url = "https://github.com/#{user}/#{repo}/archive/#{ref}.tar.gz"
-    TarballPackage.fetch(tmp_dir, url)
-  end
-end
-
-def load_grammar(path)
-  case File.extname(path.downcase)
-  when '.plist', '.tmlanguage'
-    Plist::parse_xml(path)
-  when '.yaml-tmlanguage'
-    content = File.read(path)
-    # Attempt to parse YAML file even if it has a YAML 1.2 header
-    if content.lines[0] =~ /^%YAML[ :]1\.2/
-      content = content.lines[1..-1].join
-    end
-    begin
-      YAML.load(content)
-    rescue Psych::SyntaxError => e
-      $stderr.puts "Failed to parse YAML grammar '#{path}'"
-    end
-  when '.cson'
-    cson = `"#{CSONC}" "#{path}"`
-    raise "Failed to convert CSON grammar '#{path}': #{$?.to_s}" unless $?.success?
-    JSON.parse(cson)
-  when '.json'
-    JSON.parse(File.read(path))
-  else
-    raise "Invalid document type #{path}"
-  end
-end
-
-def load_grammars(tmp_dir, source, all_scopes)
-  is_url = source.start_with?("http:", "https:")
-  return [] if is_url && !$options[:remote]
-  return [] if !is_url && !File.exist?(source)
-
-  p = if !is_url
-        if File.directory?(source)
-          DirectoryPackage.new(source)
-        else
-          SingleFile.new(source)
-        end
-      elsif source.end_with?('.tmLanguage', '.plist', '.YAML-tmLanguage')
-        SingleGrammar.new(source)
-      elsif source.start_with?('https://github.com')
-        GitHubPackage.new(source)
-      elsif source.start_with?('http://svn.textmate.org')
-        SVNPackage.new(source)
-      elsif source.end_with?('.tar.gz')
-        TarballPackage.new(source)
-      else
-        nil
-      end
-
-  raise "Unsupported source: #{source}" unless p
-
-  p.fetch(tmp_dir).map do |path|
-    grammar = load_grammar(path)
-    scope = grammar['scopeName'] || grammar['scope']
-
-    if all_scopes.key?(scope)
-      unless all_scopes[scope] == p.url
-        $stderr.puts "WARN: Duplicated scope #{scope}\n" +
-          "  Current package: #{p.url}\n" +
-          "  Previous package: #{all_scopes[scope]}"
-      end
-      next
-    end
-    all_scopes[scope] = p.url
-    grammar
-  end.compact
-end
-
-def install_grammars(grammars, path)
-  installed = []
-
-  grammars.each do |grammar|
-    scope = grammar['scopeName'] || grammar['scope']
-    File.write(File.join(GRAMMARS_PATH, "#{scope}.json"), JSON.pretty_generate(grammar))
-    installed << scope
-  end
-
-  $stderr.puts("OK #{path} (#{installed.join(', ')})")
-end
-
-def run_thread(queue, all_scopes)
-  Dir.mktmpdir do |tmpdir|
-    loop do
-      source, index = begin
-        queue.pop(true)
-      rescue ThreadError
-        # The queue is empty.
-        break
-      end
-
-      dir = "#{tmpdir}/#{index}"
-      Dir.mkdir(dir)
-
-      grammars = load_grammars(dir, source, all_scopes)
-      install_grammars(grammars, source) if $options[:install]
-    end
-  end
-end
-
-def generate_yaml(all_scopes, base)
-  yaml = all_scopes.each_with_object(base) do |(key,value),out|
-    out[value] ||= []
-    out[value] << key
-  end
-
-  yaml = Hash[yaml.sort]
-  yaml.each { |k, v| v.sort! }
-  yaml
-end
-
-def main(sources)
-  begin
-    Dir.mkdir(GRAMMARS_PATH)
-  rescue Errno::EEXIST
-  end
-
-  `npm install`
-
-  all_scopes = {}
-
-  if source = $options[:add]
-    Dir.mktmpdir do |tmpdir|
-      grammars = load_grammars(tmpdir, source, all_scopes)
-      install_grammars(grammars, source) if $options[:install]
-    end
-    generate_yaml(all_scopes, sources)
-  else
-    queue = Queue.new
-
-    sources.each do |url, scopes|
-      queue.push([url, queue.length])
-    end
-
-    threads = 8.times.map do
-      Thread.new { run_thread(queue, all_scopes) }
-    end
-    threads.each(&:join)
-    generate_yaml(all_scopes, {})
-  end
-end
-
-OptionParser.new do |opts|
-  opts.banner = "Usage: #{$0} [options]"
-
-  opts.on("--add GRAMMAR", "Add a new grammar. GRAMMAR may be a file path or URL.") do |a|
-    $options[:add] = a
-  end
-
-  opts.on("--[no-]install", "Install grammars into grammars/ directory.") do |i|
-    $options[:install] = i
-  end
-
-  opts.on("--output FILE", "Write output to FILE. Use - for stdout.") do |o|
-    $options[:output] = o == "-" ? $stdout : o
-  end
-
-  opts.on("--[no-]remote", "Download remote grammars.") do |r|
-    $options[:remote] = r
-  end
-end.parse!
-
-sources = File.open(SOURCES_FILE) do |file|
-  YAML.load(file)
-end
-
-yaml = main(sources)
-
-if $options[:output].is_a?(IO)
-  $options[:output].write(YAML.dump(yaml))
-else
-  File.write($options[:output], YAML.dump(yaml))
-end

script/grammar-compiler

@@ -0,0 +1,12 @@
+#!/bin/sh
+
+set -e
+cd "$(dirname "$0")/.."
+
+image="linguist/grammar-compiler:latest"
+mkdir -p grammars
+
+exec docker run --rm \
+    -u $(id -u $USER):$(id -g $USER) \
+    -v $PWD:/src/linguist \
+    -w /src/linguist $image "$@"

script/list-grammars

@@ -99,4 +99,8 @@ class GrammarList
 end
 
 list = GrammarList.new
-list.update_readme()
+if ARGV.include? "--print"
+  puts list.to_markdown
+else
+  list.update_readme
+end

script/prune-grammars

@@ -1,60 +0,0 @@
-#!/usr/bin/env ruby
-
-require "bundler/setup"
-require "json"
-require "linguist"
-require "set"
-require "yaml"
-
-ROOT = File.expand_path("../../", __FILE__)
-
-def find_includes(json)
-  case json
-  when Hash
-    result = []
-    if inc = json["include"]
-      result << inc.split("#", 2).first unless inc.start_with?("#", "$")
-    end
-    result + json.values.flat_map { |v| find_includes(v) }
-  when Array
-    json.flat_map { |v| find_includes(v) }
-  else
-    []
-  end
-end
-
-def transitive_includes(scope, includes)
-  scopes = Set.new
-  queue = includes[scope] || []
-  while s = queue.shift
-    next if scopes.include?(s)
-    scopes << s
-    queue += includes[s] || []
-  end
-  scopes
-end
-
-includes = {}
-Dir[File.join(ROOT, "grammars/*.json")].each do |path|
-  scope = File.basename(path).sub(/\.json/, '')
-  json = JSON.load(File.read(path))
-  incs = find_includes(json)
-  next if incs.empty?
-  includes[scope] ||= []
-  includes[scope] += incs
-end
-
-yaml = YAML.load(File.read(File.join(ROOT, "grammars.yml")))
-language_scopes = Linguist::Language.all.map(&:tm_scope).to_set
-
-# The set of used scopes is the scopes for each language, plus all the scopes
-# they include, transitively.
-used_scopes = language_scopes + language_scopes.flat_map { |s| transitive_includes(s, includes).to_a }.to_set
-
-unused = yaml.reject { |repo, scopes| scopes.any? { |scope| used_scopes.include?(scope) } }
-
-puts "Unused grammar repos"
-puts unused.map { |repo, scopes| sprintf("%-100s %s", repo, scopes.join(", ")) }.sort.join("\n")
-
-yaml.delete_if { |k| unused.key?(k) }
-File.write(File.join(ROOT, "grammars.yml"), YAML.dump(yaml))

test/fixtures/Perl/Module.pm

@@ -0,0 +1,8 @@
+use 5.006;
+use strict;
+
+=head1
+
+module
+
+=cut

test/test_file_blob.rb

@@ -188,6 +188,17 @@ class TestFileBlob < Minitest::Test
     assert fixture_blob("Binary/MainMenu.nib").generated?
     assert !sample_blob("XML/project.pbxproj").generated?
 
+    # Cocoapods
+    assert sample_blob('Pods/blah').generated?
+    assert !sample_blob('My-Pods/blah').generated?
+
+    # Carthage
+    assert sample_blob('Carthage/Build/blah').generated?
+    assert !sample_blob('Carthage/blah').generated?
+    assert !sample_blob('Carthage/Checkout/blah').generated?
+    assert !sample_blob('My-Carthage/Build/blah').generated?
+    assert !sample_blob('My-Carthage/Build/blah').generated?
+
     # Gemfile.lock is NOT generated
     assert !sample_blob("Gemfile.lock").generated?
 
@@ -313,8 +324,6 @@ class TestFileBlob < Minitest::Test
     assert sample_blob("deps/http_parser/http_parser.c").vendored?
     assert sample_blob("deps/v8/src/v8.h").vendored?
 
-    assert sample_blob("tools/something/else.c").vendored?
-
     # Chart.js
     assert sample_blob("some/vendored/path/Chart.js").vendored?
     assert !sample_blob("some/vendored/path/chart.js").vendored?
@@ -490,9 +499,9 @@ class TestFileBlob < Minitest::Test
 
     # Carthage
     assert sample_blob('Carthage/blah').vendored?
-
-    # Cocoapods
-    assert sample_blob('Pods/blah').vendored?
+    assert sample_blob('iOS/Carthage/blah').vendored?
+    assert !sample_blob('My-Carthage/blah').vendored?
+    assert !sample_blob('iOS/My-Carthage/blah').vendored?
 
     # Html5shiv
     assert sample_blob("Scripts/html5shiv.js").vendored?

test/test_generated.rb

@@ -42,6 +42,24 @@ class TestGenerated < Minitest::Test
     generated_sample_without_loading_data("Dummy/foo.xcworkspacedata")
     generated_sample_without_loading_data("Dummy/foo.xcuserstate")
 
+    # Cocoapods
+    generated_sample_without_loading_data("Pods/Pods.xcodeproj")
+    generated_sample_without_loading_data("Pods/SwiftDependency/foo.swift")
+    generated_sample_without_loading_data("Pods/ObjCDependency/foo.h")
+    generated_sample_without_loading_data("Pods/ObjCDependency/foo.m")
+    generated_sample_without_loading_data("Dummy/Pods/Pods.xcodeproj")
+    generated_sample_without_loading_data("Dummy/Pods/SwiftDependency/foo.swift")
+    generated_sample_without_loading_data("Dummy/Pods/ObjCDependency/foo.h")
+    generated_sample_without_loading_data("Dummy/Pods/ObjCDependency/foo.m")
+
+    # Carthage
+    generated_sample_without_loading_data("Carthage/Build/.Dependency.version")
+    generated_sample_without_loading_data("Carthage/Build/iOS/Dependency.framework")
+    generated_sample_without_loading_data("Carthage/Build/Mac/Dependency.framework")
+    generated_sample_without_loading_data("src/Carthage/Build/.Dependency.version")
+    generated_sample_without_loading_data("src/Carthage/Build/iOS/Dependency.framework")
+    generated_sample_without_loading_data("src/Carthage/Build/Mac/Dependency.framework")
+
     # Go-specific vendored paths
     generated_sample_without_loading_data("go/vendor/github.com/foo.go")
     generated_sample_without_loading_data("go/vendor/golang.org/src/foo.c")

test/test_grammars.rb

@@ -23,7 +23,6 @@ class TestGrammars < Minitest::Test
     "8653305b358375d0fced85dc24793b99919b11ef", # language-shellscript
     "9f0c0b0926a18f5038e455e8df60221125fc3111", # elixir-tmbundle
     "a4dadb2374282098c5b8b14df308906f5347d79a", # mako-tmbundle
-    "b9b24778619dce325b651f0d77cbc72e7ae0b0a3", # Julia.tmbundle
     "e06722add999e7428048abcc067cd85f1f7ca71c", # r.tmbundle
     "50b14a0e3f03d7ca754dac42ffb33302b5882b78", # smalltalk-tmbundle
     "eafbc4a2f283752858e6908907f3c0c90188785b", # gap-tmbundle
@@ -43,6 +42,8 @@ class TestGrammars < Minitest::Test
     "82c356d6ecb143a8a20e1658b0d6a2d77ea8126f", # idl.tmbundle
     "9dafd4e2a79cb13a6793b93877a254bc4d351e74", # sublime-text-ox
     "8e111741d97ba2e27b3d18a309d426b4a37e604f", # sublime-varnish
+    "23d2538e33ce62d58abda2c039364b92f64ea6bc", # sublime-angelscript
+    "53714285caad3c480ebd248c490509695d10404b", # atom-language-julia
   ].freeze
 
   # List of allowed SPDX license names
@@ -90,34 +91,27 @@ class TestGrammars < Minitest::Test
       message << unlisted_submodules.sort.join("\n")
     end
 
-    assert nonexistent_submodules.empty? && unlisted_submodules.empty?, message
+    assert nonexistent_submodules.empty? && unlisted_submodules.empty?, message.sub(/\.\Z/, "")
   end
 
-  def test_local_scopes_are_in_sync
-    actual = YAML.load(`"#{File.join(ROOT, "script", "convert-grammars")}" --output - --no-install --no-remote`)
-    assert $?.success?, "script/convert-grammars failed"
-
-    # We're not checking remote grammars. That can take a long time and make CI
-    # flaky if network conditions are poor.
-    @grammars.delete_if { |k, v| k.start_with?("http:", "https:") }
-
-    @grammars.each do |k, v|
-      assert_equal v, actual[k], "The scopes listed for #{k} in grammars.yml don't match the scopes found in that repository"
-    end
+  def test_readme_file_is_in_sync
+    current_data = File.read("#{ROOT}/vendor/README.md").to_s.sub(/\A.+?<!--.+?-->\n/ms, "")
+    updated_data = `script/list-grammars --print`
+    assert_equal current_data, updated_data, "Grammar list is out-of-date. Run `script/list-grammars`"
   end
 
   def test_submodules_have_recognized_licenses
     unrecognized = submodule_licenses.select { |k,v| v.nil? && Licensee::FSProject.new(k).license_file }
     unrecognized.reject! { |k,v| PROJECT_WHITELIST.include?(k) }
     message = "The following submodules have unrecognized licenses:\n* #{unrecognized.keys.join("\n* ")}\n"
-    message << "Please ensure that the project's LICENSE file contains the full text of the license."
+    message << "Please ensure that the project's LICENSE file contains the full text of the license"
     assert_equal Hash.new, unrecognized, message
   end
 
   def test_submodules_have_licenses
     unlicensed = submodule_licenses.select { |k,v| v.nil? }.reject { |k,v| PROJECT_WHITELIST.include?(k) }
     message = "The following submodules don't have licenses:\n* #{unlicensed.keys.join("\n* ")}\n"
-    message << "Please ensure that the project has a LICENSE file, and that the LICENSE file contains the full text of the license."
+    message << "Please ensure that the project has a LICENSE file, and that the LICENSE file contains the full text of the license"
     assert_equal Hash.new, unlicensed, message
   end
 
@@ -127,14 +121,14 @@ class TestGrammars < Minitest::Test
                                                    HASH_WHITELIST.include?(v) }
                                    .map { |k,v| "#{k}: #{v}"}
     message = "The following submodules have unapproved licenses:\n* #{unapproved.join("\n* ")}\n"
-    message << "The license must be added to the LICENSE_WHITELIST in /test/test_grammars.rb once approved."
+    message << "The license must be added to the LICENSE_WHITELIST in /test/test_grammars.rb once approved"
     assert_equal [], unapproved, message
   end
 
   def test_whitelisted_submodules_dont_have_licenses
     licensed = submodule_licenses.reject { |k,v| v.nil? }.select { |k,v| PROJECT_WHITELIST.include?(k) }
     message = "The following whitelisted submodules have a license:\n* #{licensed.keys.join("\n* ")}\n"
-    message << "Please remove them from the project whitelist."
+    message << "Please remove them from the project whitelist"
     assert_equal Hash.new, licensed, message
   end
 
@@ -142,7 +136,7 @@ class TestGrammars < Minitest::Test
     used_hashes = submodule_licenses.values.reject { |v| v.nil? || LICENSE_WHITELIST.include?(v) }
     unused_hashes = HASH_WHITELIST - used_hashes
     message = "The following whitelisted license hashes are unused:\n* #{unused_hashes.join("\n* ")}\n"
-    message << "Please remove them from the hash whitelist."
+    message << "Please remove them from the hash whitelist"
     assert_equal Array.new, unused_hashes, message
   end
 

test/test_heuristics.rb

@@ -1,6 +1,6 @@
 require_relative "./helper"
 
-class TestHeuristcs < Minitest::Test
+class TestHeuristics < Minitest::Test
   include Linguist
 
   def fixture(name)
@@ -44,6 +44,13 @@ class TestHeuristcs < Minitest::Test
     assert_equal Language["Objective-C"], match
   end
 
+  def test_as_by_heuristics
+    assert_heuristics({
+      "ActionScript" => all_fixtures("ActionScript", "*.as"),
+      "AngelScript" => all_fixtures("AngelScript", "*.as")
+    })
+  end
+
   # Candidate languages = ["AGS Script", "AsciiDoc", "Public Key"]
   def test_asc_by_heuristics
     assert_heuristics({
@@ -230,14 +237,6 @@ class TestHeuristcs < Minitest::Test
     })
   end
 
-  # Candidate languages = ["Pod", "Perl"]
-  def test_pod_by_heuristics
-    assert_heuristics({
-      "Perl" => all_fixtures("Perl", "*.pod"),
-      "Pod" => all_fixtures("Pod", "*.pod")
-    })
-  end
-
   # Candidate languages = ["IDL", "Prolog", "QMake", "INI"]
   def test_pro_by_heuristics
     assert_heuristics({

test/test_language.rb

@@ -470,5 +470,7 @@ class TestLanguage < Minitest::Test
 
   def test_non_crash_on_comma
     assert_nil Language[',']
+    assert_nil Language.find_by_name(',')
+    assert_nil Language.find_by_alias(',')
   end
 end

tools/grammars/.gitignore

@@ -0,0 +1 @@
+/vendor

tools/grammars/Dockerfile

@@ -0,0 +1,35 @@
+FROM golang:1.9.2
+
+RUN apt-get update
+RUN apt-get upgrade -y
+RUN apt-get install -y curl gnupg
+
+RUN curl -sL https://deb.nodesource.com/setup_6.x | bash -
+RUN apt-get install -y nodejs
+RUN npm install -g season
+
+RUN apt-get install -y cmake
+RUN cd /tmp && git clone https://github.com/vmg/pcre
+RUN mkdir -p /tmp/pcre/build && cd /tmp/pcre/build && \
+	cmake .. \
+		-DPCRE_SUPPORT_JIT=ON \
+		-DPCRE_SUPPORT_UTF=ON \
+		-DPCRE_SUPPORT_UNICODE_PROPERTIES=ON \
+		-DBUILD_SHARED_LIBS=OFF \
+		-DCMAKE_C_FLAGS="-fPIC $(EXTRA_PCRE_CFLAGS)" \
+		-DCMAKE_BUILD_TYPE=RelWithDebInfo \
+		-DPCRE_BUILD_PCRECPP=OFF \
+		-DPCRE_BUILD_PCREGREP=OFF \
+		-DPCRE_BUILD_TESTS=OFF \
+		-G "Unix Makefiles" && \
+    make && make install
+RUN rm -rf /tmp/pcre
+
+RUN go get -u github.com/golang/dep/cmd/dep
+WORKDIR /go/src/github.com/github/linguist/tools/grammars
+COPY . .
+
+RUN dep ensure
+RUN go install ./cmd/grammar-compiler
+
+ENTRYPOINT ["grammar-compiler"]

tools/grammars/Gopkg.lock

@@ -0,0 +1,51 @@
+# This file is autogenerated, do not edit; changes may be undone by the next 'dep ensure'.
+
+
+[[projects]]
+  branch = "master"
+  name = "github.com/golang/protobuf"
+  packages = ["proto"]
+  revision = "1e59b77b52bf8e4b449a57e6f79f21226d571845"
+
+[[projects]]
+  branch = "master"
+  name = "github.com/groob/plist"
+  packages = ["."]
+  revision = "7b367e0aa692e62a223e823f3288c0c00f519a36"
+
+[[projects]]
+  name = "github.com/mattn/go-runewidth"
+  packages = ["."]
+  revision = "9e777a8366cce605130a531d2cd6363d07ad7317"
+  version = "v0.0.2"
+
+[[projects]]
+  branch = "master"
+  name = "github.com/mitchellh/mapstructure"
+  packages = ["."]
+  revision = "06020f85339e21b2478f756a78e295255ffa4d6a"
+
+[[projects]]
+  name = "github.com/urfave/cli"
+  packages = ["."]
+  revision = "cfb38830724cc34fedffe9a2a29fb54fa9169cd1"
+  version = "v1.20.0"
+
+[[projects]]
+  name = "gopkg.in/cheggaaa/pb.v1"
+  packages = ["."]
+  revision = "657164d0228d6bebe316fdf725c69f131a50fb10"
+  version = "v1.0.18"
+
+[[projects]]
+  branch = "v2"
+  name = "gopkg.in/yaml.v2"
+  packages = ["."]
+  revision = "287cf08546ab5e7e37d55a84f7ed3fd1db036de5"
+
+[solve-meta]
+  analyzer-name = "dep"
+  analyzer-version = 1
+  inputs-digest = "ba2e3150d728692b49e3e2d652b6ea23db82777c340e0c432cd4af6f0eef9f55"
+  solver-name = "gps-cdcl"
+  solver-version = 1

tools/grammars/Gopkg.toml

@@ -0,0 +1,23 @@
+[[constraint]]
+  branch = "v2"
+  name = "gopkg.in/yaml.v2"
+
+[[constraint]]
+  branch = "master"
+  name = "github.com/groob/plist"
+
+[[constraint]]
+  branch = "master"
+  name = "github.com/golang/protobuf"
+
+[[constraint]]
+  branch = "master"
+  name = "github.com/mitchellh/mapstructure"
+
+[[constraint]]
+  name = "gopkg.in/cheggaaa/pb.v1"
+  version = "1.0.18"
+
+[[constraint]]
+  name = "github.com/urfave/cli"
+  version = "1.20.0"

tools/grammars/cmd/grammar-compiler/main.go

@@ -0,0 +1,120 @@
+package main
+
+import (
+	"os"
+
+	"github.com/github/linguist/tools/grammars/compiler"
+	"github.com/urfave/cli"
+)
+
+func cwd() string {
+	cwd, _ := os.Getwd()
+	return cwd
+}
+
+func wrap(err error) error {
+	return cli.NewExitError(err, 255)
+}
+
+func main() {
+	app := cli.NewApp()
+	app.Name = "Linguist Grammars Compiler"
+	app.Usage = "Compile user-submitted grammars and check them for errors"
+
+	app.Flags = []cli.Flag{
+		cli.StringFlag{
+			Name:  "linguist-path",
+			Value: cwd(),
+			Usage: "path to Linguist root",
+		},
+	}
+
+	app.Commands = []cli.Command{
+		{
+			Name:  "add",
+			Usage: "add a new grammar source",
+			Flags: []cli.Flag{
+				cli.BoolFlag{
+					Name:  "force, f",
+					Usage: "ignore compilation errors",
+				},
+			},
+			Action: func(c *cli.Context) error {
+				conv, err := compiler.NewConverter(c.String("linguist-path"))
+				if err != nil {
+					return wrap(err)
+				}
+				if err := conv.AddGrammar(c.Args().First()); err != nil {
+					if !c.Bool("force") {
+						return wrap(err)
+					}
+				}
+				if err := conv.WriteGrammarList(); err != nil {
+					return wrap(err)
+				}
+				return nil
+			},
+		},
+		{
+			Name:  "update",
+			Usage: "update grammars.yml with the contents of the grammars library",
+			Flags: []cli.Flag{
+				cli.BoolFlag{
+					Name:  "force, f",
+					Usage: "write grammars.yml even if grammars fail to compile",
+				},
+			},
+			Action: func(c *cli.Context) error {
+				conv, err := compiler.NewConverter(c.String("linguist-path"))
+				if err != nil {
+					return wrap(err)
+				}
+				if err := conv.ConvertGrammars(true); err != nil {
+					return wrap(err)
+				}
+				if err := conv.Report(); err != nil {
+					if !c.Bool("force") {
+						return wrap(err)
+					}
+				}
+				if err := conv.WriteGrammarList(); err != nil {
+					return wrap(err)
+				}
+				return nil
+			},
+		},
+		{
+			Name:  "compile",
+			Usage: "convert the grammars from the library",
+			Flags: []cli.Flag{
+				cli.StringFlag{Name: "proto-out, P"},
+				cli.StringFlag{Name: "out, o"},
+			},
+			Action: func(c *cli.Context) error {
+				conv, err := compiler.NewConverter(c.String("linguist-path"))
+				if err != nil {
+					return cli.NewExitError(err, 1)
+				}
+				if err := conv.ConvertGrammars(false); err != nil {
+					return cli.NewExitError(err, 1)
+				}
+				if out := c.String("proto-out"); out != "" {
+					if err := conv.WriteProto(out); err != nil {
+						return cli.NewExitError(err, 1)
+					}
+				}
+				if out := c.String("out"); out != "" {
+					if err := conv.WriteJSON(out); err != nil {
+						return cli.NewExitError(err, 1)
+					}
+				}
+				if err := conv.Report(); err != nil {
+					return wrap(err)
+				}
+				return nil
+			},
+		},
+	}
+
+	app.Run(os.Args)
+}

tools/grammars/compiler/converter.go

@@ -0,0 +1,261 @@
+package compiler
+
+import (
+	"encoding/json"
+	"fmt"
+	"io/ioutil"
+	"os"
+	"path"
+	"runtime"
+	"sort"
+	"strings"
+	"sync"
+
+	grammar "github.com/github/linguist/tools/grammars/proto"
+	"github.com/golang/protobuf/proto"
+	pb "gopkg.in/cheggaaa/pb.v1"
+	yaml "gopkg.in/yaml.v2"
+)
+
+type Converter struct {
+	root string
+
+	modified bool
+	grammars map[string][]string
+	Loaded   map[string]*Repository
+
+	progress *pb.ProgressBar
+	wg       sync.WaitGroup
+	queue    chan string
+	mu       sync.Mutex
+}
+
+func (conv *Converter) Load(src string) *Repository {
+	if strings.HasPrefix(src, "http://") || strings.HasPrefix(src, "https://") {
+		return LoadFromURL(src)
+	}
+	return LoadFromFilesystem(conv.root, src)
+}
+
+func (conv *Converter) work() {
+	for source := range conv.queue {
+		repo := conv.Load(source)
+
+		conv.mu.Lock()
+		conv.Loaded[source] = repo
+		conv.mu.Unlock()
+
+		conv.progress.Increment()
+	}
+
+	conv.wg.Done()
+}
+
+func (conv *Converter) tmpScopes() map[string]bool {
+	scopes := make(map[string]bool)
+	for _, ary := range conv.grammars {
+		for _, s := range ary {
+			scopes[s] = true
+		}
+	}
+	return scopes
+}
+
+func (conv *Converter) AddGrammar(source string) error {
+	repo := conv.Load(source)
+	if len(repo.Files) == 0 {
+		return fmt.Errorf("source '%s' contains no grammar files", source)
+	}
+
+	conv.grammars[source] = repo.Scopes()
+	conv.modified = true
+
+	knownScopes := conv.tmpScopes()
+	repo.FixRules(knownScopes)
+
+	if len(repo.Errors) > 0 {
+		fmt.Fprintf(os.Stderr, "The new grammar %s contains %d errors:\n",
+			repo, len(repo.Errors))
+		for _, err := range repo.Errors {
+			fmt.Fprintf(os.Stderr, "    - %s\n", err)
+		}
+		fmt.Fprintf(os.Stderr, "\n")
+		return fmt.Errorf("failed to compile the given grammar")
+	}
+
+	fmt.Printf("OK! added grammar source '%s'\n", source)
+	for scope := range repo.Files {
+		fmt.Printf("\tnew scope: %s\n", scope)
+	}
+	return nil
+}
+
+func (conv *Converter) AllScopes() map[string]bool {
+	// Map from scope -> Repository first to error check
+	// possible duplicates
+	allScopes := make(map[string]*Repository)
+	for _, repo := range conv.Loaded {
+		for scope := range repo.Files {
+			if original := allScopes[scope]; original != nil {
+				repo.Fail(&DuplicateScopeError{original, scope})
+			} else {
+				allScopes[scope] = repo
+			}
+		}
+	}
+
+	// Convert to scope -> bool
+	scopes := make(map[string]bool)
+	for s := range allScopes {
+		scopes[s] = true
+	}
+	return scopes
+}
+
+func (conv *Converter) ConvertGrammars(update bool) error {
+	conv.Loaded = make(map[string]*Repository)
+	conv.queue = make(chan string, 128)
+
+	conv.progress = pb.New(len(conv.grammars))
+	conv.progress.Start()
+
+	for i := 0; i < runtime.NumCPU(); i++ {
+		conv.wg.Add(1)
+		go conv.work()
+	}
+
+	for src := range conv.grammars {
+		conv.queue <- src
+	}
+
+	close(conv.queue)
+	conv.wg.Wait()
+
+	done := fmt.Sprintf("done! processed %d grammars\n", len(conv.Loaded))
+	conv.progress.FinishPrint(done)
+
+	if update {
+		conv.grammars = make(map[string][]string)
+		conv.modified = true
+	}
+
+	knownScopes := conv.AllScopes()
+
+	for source, repo := range conv.Loaded {
+		repo.FixRules(knownScopes)
+
+		if update {
+			conv.grammars[source] = repo.Scopes()
+		} else {
+			expected := conv.grammars[source]
+			repo.CompareScopes(expected)
+		}
+	}
+
+	return nil
+}
+
+func (conv *Converter) WriteProto(path string) error {
+	library := grammar.Library{
+		Grammars: make(map[string]*grammar.Rule),
+	}
+
+	for _, repo := range conv.Loaded {
+		for scope, file := range repo.Files {
+			library.Grammars[scope] = file.Rule
+		}
+	}
+
+	pb, err := proto.Marshal(&library)
+	if err != nil {
+		return err
+	}
+
+	return ioutil.WriteFile(path, pb, 0666)
+}
+
+func (conv *Converter) writeJSONFile(path string, rule *grammar.Rule) error {
+	j, err := os.Create(path)
+	if err != nil {
+		return err
+	}
+	defer j.Close()
+
+	enc := json.NewEncoder(j)
+	enc.SetIndent("", "  ")
+	return enc.Encode(rule)
+}
+
+func (conv *Converter) WriteJSON(rulePath string) error {
+	if err := os.MkdirAll(rulePath, os.ModePerm); err != nil {
+		return err
+	}
+
+	for _, repo := range conv.Loaded {
+		for scope, file := range repo.Files {
+			p := path.Join(rulePath, scope+".json")
+			if err := conv.writeJSONFile(p, file.Rule); err != nil {
+				return err
+			}
+		}
+	}
+
+	return nil
+}
+
+func (conv *Converter) WriteGrammarList() error {
+	if !conv.modified {
+		return nil
+	}
+
+	outyml, err := yaml.Marshal(conv.grammars)
+	if err != nil {
+		return err
+	}
+
+	ymlpath := path.Join(conv.root, "grammars.yml")
+	return ioutil.WriteFile(ymlpath, outyml, 0666)
+}
+
+func (conv *Converter) Report() error {
+	var failed []*Repository
+	for _, repo := range conv.Loaded {
+		if len(repo.Errors) > 0 {
+			failed = append(failed, repo)
+		}
+	}
+
+	sort.Slice(failed, func(i, j int) bool {
+		return failed[i].Source < failed[j].Source
+	})
+
+	total := 0
+	for _, repo := range failed {
+		fmt.Fprintf(os.Stderr, "- [ ] %s (%d errors)\n", repo, len(repo.Errors))
+		for _, err := range repo.Errors {
+			fmt.Fprintf(os.Stderr, "    - [ ] %s\n", err)
+		}
+		fmt.Fprintf(os.Stderr, "\n")
+		total += len(repo.Errors)
+	}
+
+	if total > 0 {
+		return fmt.Errorf("the grammar library contains %d errors", total)
+	}
+	return nil
+}
+
+func NewConverter(root string) (*Converter, error) {
+	yml, err := ioutil.ReadFile(path.Join(root, "grammars.yml"))
+	if err != nil {
+		return nil, err
+	}
+
+	conv := &Converter{root: root}
+
+	if err := yaml.Unmarshal(yml, &conv.grammars); err != nil {
+		return nil, err
+	}
+
+	return conv, nil
+}

tools/grammars/compiler/cson.go

@@ -0,0 +1,21 @@
+package compiler
+
+import (
+	"bytes"
+	"os/exec"
+)
+
+func ConvertCSON(data []byte) ([]byte, error) {
+	stdin := bytes.NewBuffer(data)
+	stdout := &bytes.Buffer{}
+
+	cmd := exec.Command("csonc")
+	cmd.Stdin = stdin
+	cmd.Stdout = stdout
+
+	if err := cmd.Run(); err != nil {
+		return nil, err
+	}
+
+	return stdout.Bytes(), nil
+}

tools/grammars/compiler/data.go

@@ -0,0 +1,29 @@
+package compiler
+
+var GrammarAliases = map[string]string{
+	"source.erb":         "text.html.erb",
+	"source.cpp":         "source.c++",
+	"source.less":        "source.css.less",
+	"text.html.markdown": "source.gfm",
+	"text.md":            "source.gfm",
+	"source.php":         "text.html.php",
+	"text.plain":         "",
+	"source.asciidoc":    "text.html.asciidoc",
+	"source.perl6":       "source.perl6fe",
+	"source.css.scss":    "source.scss",
+}
+
+var KnownFields = map[string]bool{
+	"comment":            true,
+	"uuid":               true,
+	"author":             true,
+	"comments":           true,
+	"macros":             true,
+	"fileTypes":          true,
+	"firstLineMatch":     true,
+	"keyEquivalent":      true,
+	"foldingStopMarker":  true,
+	"foldingStartMarker": true,
+	"foldingEndMarker":   true,
+	"limitLineLength":    true,
+}

tools/grammars/compiler/errors.go

@@ -0,0 +1,85 @@
+package compiler
+
+import "fmt"
+import "strings"
+
+type ConversionError struct {
+	Path string
+	Err  error
+}
+
+func (err *ConversionError) Error() string {
+	return fmt.Sprintf(
+		"Grammar conversion failed. File `%s` failed to parse: %s",
+		err.Path, err.Err)
+}
+
+type DuplicateScopeError struct {
+	Original  *Repository
+	Duplicate string
+}
+
+func (err *DuplicateScopeError) Error() string {
+	return fmt.Sprintf(
+		"Duplicate scope in repository: scope `%s` was already defined in %s",
+		err.Duplicate, err.Original)
+}
+
+type MissingScopeError struct {
+	Scope string
+}
+
+func (err *MissingScopeError) Error() string {
+	return fmt.Sprintf(
+		"Missing scope in repository: `%s` is listed in grammars.yml but cannot be found",
+		err.Scope)
+}
+
+type UnexpectedScopeError struct {
+	File  *LoadedFile
+	Scope string
+}
+
+func (err *UnexpectedScopeError) Error() string {
+	return fmt.Sprintf(
+		"Unexpected scope in repository: `%s` declared in %s was not listed in grammars.yml",
+		err.Scope, err.File)
+}
+
+type MissingIncludeError struct {
+	File    *LoadedFile
+	Include string
+}
+
+func (err *MissingIncludeError) Error() string {
+	return fmt.Sprintf(
+		"Missing include in grammar: %s attempts to include `%s` but the scope cannot be found",
+		err.File, err.Include)
+}
+
+type UnknownKeysError struct {
+	File *LoadedFile
+	Keys []string
+}
+
+func (err *UnknownKeysError) Error() string {
+	var keys []string
+	for _, k := range err.Keys {
+		keys = append(keys, fmt.Sprintf("`%s`", k))
+	}
+
+	return fmt.Sprintf(
+		"Unknown keys in grammar: %s contains invalid keys (%s)",
+		err.File, strings.Join(keys, ", "))
+}
+
+type InvalidRegexError struct {
+	File *LoadedFile
+	Err  error
+}
+
+func (err *InvalidRegexError) Error() string {
+	return fmt.Sprintf(
+		"Invalid regex in grammar: %s contains a malformed regex (%s)",
+		err.File, err.Err)
+}

tools/grammars/compiler/loader.go

@@ -0,0 +1,124 @@
+package compiler
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+	"sort"
+	"strings"
+
+	grammar "github.com/github/linguist/tools/grammars/proto"
+)
+
+type LoadedFile struct {
+	Path string
+	Rule *grammar.Rule
+}
+
+func (f *LoadedFile) String() string {
+	return fmt.Sprintf("`%s` (in `%s`)", f.Rule.ScopeName, f.Path)
+}
+
+type Repository struct {
+	Source   string
+	Upstream string
+	Files    map[string]*LoadedFile
+	Errors   []error
+}
+
+func newRepository(src string) *Repository {
+	return &Repository{
+		Source: src,
+		Files:  make(map[string]*LoadedFile),
+	}
+}
+
+func (repo *Repository) String() string {
+	str := fmt.Sprintf("repository `%s`", repo.Source)
+	if repo.Upstream != "" {
+		str = str + fmt.Sprintf(" (from %s)", repo.Upstream)
+	}
+	return str
+}
+
+func (repo *Repository) Fail(err error) {
+	repo.Errors = append(repo.Errors, err)
+}
+
+func (repo *Repository) AddFile(path string, rule *grammar.Rule, uk []string) {
+	file := &LoadedFile{
+		Path: path,
+		Rule: rule,
+	}
+
+	repo.Files[rule.ScopeName] = file
+	if len(uk) > 0 {
+		repo.Fail(&UnknownKeysError{file, uk})
+	}
+}
+
+func toMap(slice []string) map[string]bool {
+	m := make(map[string]bool)
+	for _, s := range slice {
+		m[s] = true
+	}
+	return m
+}
+
+func (repo *Repository) CompareScopes(scopes []string) {
+	expected := toMap(scopes)
+
+	for scope, file := range repo.Files {
+		if !expected[scope] {
+			repo.Fail(&UnexpectedScopeError{file, scope})
+		}
+	}
+
+	for scope := range expected {
+		if _, ok := repo.Files[scope]; !ok {
+			repo.Fail(&MissingScopeError{scope})
+		}
+	}
+}
+
+func (repo *Repository) FixRules(knownScopes map[string]bool) {
+	for _, file := range repo.Files {
+		w := walker{
+			File:    file,
+			Known:   knownScopes,
+			Missing: make(map[string]bool),
+		}
+
+		w.walk(file.Rule)
+		repo.Errors = append(repo.Errors, w.Errors...)
+
+	}
+}
+
+func (repo *Repository) Scopes() (scopes []string) {
+	for s := range repo.Files {
+		scopes = append(scopes, s)
+	}
+	sort.Strings(scopes)
+	return
+}
+
+func isValidGrammar(path string, info os.FileInfo) bool {
+	if info.IsDir() {
+		return false
+	}
+
+	dir := filepath.Dir(path)
+	ext := filepath.Ext(path)
+
+	switch strings.ToLower(ext) {
+	case ".plist":
+		return strings.HasSuffix(dir, "/Syntaxes")
+	case ".tmlanguage", ".yaml-tmlanguage":
+		return true
+	case ".cson", ".json":
+		return strings.HasSuffix(dir, "/grammars")
+	default:
+		return false
+	}
+}

tools/grammars/compiler/loader_fs.go

@@ -0,0 +1,80 @@
+package compiler
+
+import (
+	"io/ioutil"
+	"os"
+	"os/exec"
+	"path"
+	"path/filepath"
+	"strings"
+)
+
+type fsLoader struct {
+	*Repository
+	abspath string
+}
+
+func (l *fsLoader) findGrammars() (files []string, err error) {
+	err = filepath.Walk(l.abspath,
+		func(path string, info os.FileInfo, err error) error {
+			if err == nil && isValidGrammar(path, info) {
+				files = append(files, path)
+			}
+			return nil
+		})
+	return
+}
+
+func (l *fsLoader) load() {
+	grammars, err := l.findGrammars()
+	if err != nil {
+		l.Fail(err)
+		return
+	}
+
+	for _, path := range grammars {
+		data, err := ioutil.ReadFile(path)
+		if err != nil {
+			l.Fail(err)
+			continue
+		}
+
+		if rel, err := filepath.Rel(l.abspath, path); err == nil {
+			path = rel
+		}
+
+		rule, unknown, err := ConvertProto(filepath.Ext(path), data)
+		if err != nil {
+			l.Fail(&ConversionError{path, err})
+			continue
+		}
+
+		if _, ok := l.Files[rule.ScopeName]; ok {
+			continue
+		}
+
+		l.AddFile(path, rule, unknown)
+	}
+}
+
+func gitRemoteName(path string) (string, error) {
+	remote, err := exec.Command("git", "-C", path, "remote", "get-url", "origin").Output()
+	if err != nil {
+		return "", err
+	}
+	return strings.TrimSpace(string(remote)), nil
+}
+
+func LoadFromFilesystem(root, src string) *Repository {
+	loader := fsLoader{
+		Repository: newRepository(src),
+		abspath:    path.Join(root, src),
+	}
+	loader.load()
+
+	if ups, err := gitRemoteName(loader.abspath); err == nil {
+		loader.Repository.Upstream = ups
+	}
+
+	return loader.Repository
+}

tools/grammars/compiler/loader_url.go

@@ -0,0 +1,93 @@
+package compiler
+
+import (
+	"archive/tar"
+	"compress/gzip"
+	"io"
+	"io/ioutil"
+	"net/http"
+	"path/filepath"
+	"strings"
+)
+
+type urlLoader struct {
+	*Repository
+}
+
+func (l *urlLoader) loadTarball(r io.Reader) {
+	gzf, err := gzip.NewReader(r)
+	if err != nil {
+		l.Fail(err)
+		return
+	}
+	defer gzf.Close()
+
+	tarReader := tar.NewReader(gzf)
+	for true {
+		header, err := tarReader.Next()
+
+		if err != nil {
+			if err != io.EOF {
+				l.Fail(err)
+			}
+			return
+		}
+
+		if isValidGrammar(header.Name, header.FileInfo()) {
+			data, err := ioutil.ReadAll(tarReader)
+			if err != nil {
+				l.Fail(err)
+				return
+			}
+
+			ext := filepath.Ext(header.Name)
+			rule, unknown, err := ConvertProto(ext, data)
+			if err != nil {
+				l.Fail(&ConversionError{header.Name, err})
+				continue
+			}
+
+			if _, ok := l.Files[rule.ScopeName]; ok {
+				continue
+			}
+
+			l.AddFile(header.Name, rule, unknown)
+		}
+	}
+}
+
+func (l *urlLoader) load() {
+	res, err := http.Get(l.Source)
+	if err != nil {
+		l.Fail(err)
+		return
+	}
+	defer res.Body.Close()
+
+	if strings.HasSuffix(l.Source, ".tar.gz") {
+		l.loadTarball(res.Body)
+		return
+	}
+
+	data, err := ioutil.ReadAll(res.Body)
+	if err != nil {
+		l.Fail(err)
+		return
+	}
+
+	ext := filepath.Ext(l.Source)
+	filename := filepath.Base(l.Source)
+	rule, unknown, err := ConvertProto(ext, data)
+	if err != nil {
+		l.Fail(&ConversionError{filename, err})
+		return
+	}
+
+	l.AddFile(filename, rule, unknown)
+}
+
+func LoadFromURL(src string) *Repository {
+	loader := urlLoader{newRepository(src)}
+	loader.load()
+	return loader.Repository
+}

tools/grammars/compiler/pcre.go

@@ -0,0 +1,68 @@
+package compiler
+
+import (
+	"fmt"
+
+	"github.com/github/linguist/tools/grammars/pcre"
+)
+
+type replacement struct {
+	pos int
+	len int
+	val string
+}
+
+func fixRegex(re string) (string, bool) {
+	var (
+		replace     []replacement
+		escape      = false
+		hasBackRefs = false
+	)
+
+	for i, ch := range re {
+		if escape {
+			if ch == 'h' {
+				replace = append(replace, replacement{i - 1, 2, "[[:xdigit:]]"})
+			}
+			if '0' <= ch && ch <= '9' {
+				hasBackRefs = true
+			}
+		}
+		escape = !escape && ch == '\\'
+	}
+
+	if len(replace) > 0 {
+		reb := []byte(re)
+		offset := 0
+		for _, repl := range replace {
+			reb = append(
+				reb[:offset+repl.pos],
+				append([]byte(repl.val), reb[offset+repl.pos+repl.len:]...)...)
+			offset += len(repl.val) - repl.len
+		}
+		return string(reb), hasBackRefs
+	}
+
+	return re, hasBackRefs
+}
+
+func CheckPCRE(re string) (string, error) {
+	hasBackRefs := false
+
+	if re == "" {
+		return "", nil
+	}
+	if len(re) > 32*1024 {
+		return "", fmt.Errorf(
+			"regex %s: definition too long (%d bytes)",
+			pcre.RegexPP(re), len(re))
+	}
+
+	re, hasBackRefs = fixRegex(re)
+	if !hasBackRefs {
+		if err := pcre.CheckRegexp(re, pcre.DefaultFlags); err != nil {
+			return "", err
+		}
+	}
+	return re, nil
+}

tools/grammars/compiler/pcre_test.go

@@ -0,0 +1,27 @@
+package compiler
+
+import (
+	"testing"
+)
+
+func Test_fixRegex(t *testing.T) {
+	tests := []struct {
+		re   string
+		want string
+	}{
+		{"foobar", "foobar"},
+		{`testing\h`, "testing[[:xdigit:]]"},
+		{`\htest`, `[[:xdigit:]]test`},
+		{`abc\hdef`, `abc[[:xdigit:]]def`},
+		{`\\\htest`, `\\[[:xdigit:]]test`},
+		{`\\htest`, `\\htest`},
+		{`\h\h\h\h`, `[[:xdigit:]][[:xdigit:]][[:xdigit:]][[:xdigit:]]`},
+		{`abc\hdef\hghi\h`, `abc[[:xdigit:]]def[[:xdigit:]]ghi[[:xdigit:]]`},
+	}
+	for _, tt := range tests {
+		got, _ := fixRegex(tt.re)
+		if got != tt.want {
+			t.Errorf("fixRegex() got = %v, want %v", got, tt.want)
+		}
+	}
+}

tools/grammars/compiler/proto.go

@@ -0,0 +1,96 @@
+package compiler
+
+import (
+	"encoding/json"
+	"fmt"
+	"reflect"
+	"strings"
+
+	grammar "github.com/github/linguist/tools/grammars/proto"
+	"github.com/groob/plist"
+	"github.com/mitchellh/mapstructure"
+	yaml "gopkg.in/yaml.v2"
+)
+
+func looseDecoder(f reflect.Kind, t reflect.Kind, data interface{}) (interface{}, error) {
+	dataVal := reflect.ValueOf(data)
+	switch t {
+	case reflect.Bool:
+		switch f {
+		case reflect.Bool:
+			return dataVal.Bool(), nil
+		case reflect.Float32, reflect.Float64:
+			return (int(dataVal.Float()) != 0), nil
+		case reflect.Int, reflect.Int8, reflect.Int16, reflect.Int32, reflect.Int64:
+			return (dataVal.Int() != 0), nil
+		case reflect.Uint, reflect.Uint8, reflect.Uint16, reflect.Uint32, reflect.Uint64:
+			return (dataVal.Uint() != 0), nil
+		case reflect.String:
+			switch dataVal.String() {
+			case "1":
+				return true, nil
+			case "0":
+				return false, nil
+			}
+		}
+	}
+
+	return data, nil
+}
+
+func filterUnusedKeys(keys []string) (out []string) {
+	for _, k := range keys {
+		parts := strings.Split(k, ".")
+		field := parts[len(parts)-1]
+		if !KnownFields[field] {
+			out = append(out, k)
+		}
+	}
+	return
+}
+
+func ConvertProto(ext string, data []byte) (*grammar.Rule, []string, error) {
+	var (
+		raw map[string]interface{}
+		out grammar.Rule
+		err error
+		md  mapstructure.Metadata
+	)
+
+	switch strings.ToLower(ext) {
+	case ".plist", ".tmlanguage":
+		err = plist.Unmarshal(data, &raw)
+	case ".yaml-tmlanguage":
+		err = yaml.Unmarshal(data, &raw)
+	case ".cson":
+		data, err = ConvertCSON(data)
+		if err == nil {
+			err = json.Unmarshal(data, &raw)
+		}
+	case ".json":
+		err = json.Unmarshal(data, &raw)
+	default:
+		err = fmt.Errorf("grammars: unsupported extension '%s'", ext)
+	}
+
+	if err != nil {
+		return nil, nil, err
+	}
+
+	config := mapstructure.DecoderConfig{
+		Result:     &out,
+		Metadata:   &md,
+		DecodeHook: looseDecoder,
+	}
+
+	decoder, err := mapstructure.NewDecoder(&config)
+	if err != nil {
+		return nil, nil, err
+	}
+
+	if err := decoder.Decode(raw); err != nil {
+		return nil, nil, err
+	}
+
+	return &out, filterUnusedKeys(md.Unused), nil
+}

tools/grammars/compiler/walker.go

@@ -0,0 +1,79 @@
+package compiler
+
+import (
+	"strings"
+
+	grammar "github.com/github/linguist/tools/grammars/proto"
+)
+
+func (w *walker) checkInclude(rule *grammar.Rule) {
+	include := rule.Include
+
+	if include == "" || include[0] == '#' || include[0] == '$' {
+		return
+	}
+
+	if alias, ok := GrammarAliases[include]; ok {
+		rule.Include = alias
+		return
+	}
+
+	include = strings.Split(include, "#")[0]
+	ok := w.Known[include]
+	if !ok {
+		if !w.Missing[include] {
+			w.Missing[include] = true
+			w.Errors = append(w.Errors, &MissingIncludeError{w.File, include})
+		}
+		rule.Include = ""
+	}
+}
+
+func (w *walker) checkRegexps(rule *grammar.Rule) {
+	check := func(re string) string {
+		re2, err := CheckPCRE(re)
+		if err != nil {
+			w.Errors = append(w.Errors, &InvalidRegexError{w.File, err})
+		}
+		return re2
+	}
+
+	rule.Match = check(rule.Match)
+	rule.Begin = check(rule.Begin)
+	rule.While = check(rule.While)
+	rule.End = check(rule.End)
+}
+
+func (w *walker) walk(rule *grammar.Rule) {
+	w.checkInclude(rule)
+	w.checkRegexps(rule)
+
+	for _, rule := range rule.Patterns {
+		w.walk(rule)
+	}
+	for _, rule := range rule.Captures {
+		w.walk(rule)
+	}
+	for _, rule := range rule.BeginCaptures {
+		w.walk(rule)
+	}
+	for _, rule := range rule.WhileCaptures {
+		w.walk(rule)
+	}
+	for _, rule := range rule.EndCaptures {
+		w.walk(rule)
+	}
+	for _, rule := range rule.Repository {
+		w.walk(rule)
+	}
+	for _, rule := range rule.Injections {
+		w.walk(rule)
+	}
+}
+
+type walker struct {
+	File    *LoadedFile
+	Known   map[string]bool
+	Missing map[string]bool
+	Errors  []error
+}

tools/grammars/docker/build

@@ -0,0 +1,11 @@
+#!/bin/sh
+
+set -ex
+cd "$(dirname "$0")/.."
+
+image=linguist/grammar-compiler
+docker build -t $image .
+
+if [ "$1" = "--push" ]; then
+    docker push $image
+fi