Support for Mathematica and Wolfram Language

* Provides highlighting of standard built-in symbols that are extracted from
an online list of functions provided by Wolfram.
* Support for the various number formats that Mathematica supports. Handling of context symbols
* Support for named characters like \[Alpha]
* Support for messages
* Support for slots and association slots of pure functions
* Support for In[1]:= and Out[1]= markers
* Support for nested comments and comment markup

lib/rouge/demos/mathematica

@@ -0,0 +1,8 @@
+(* Fibonacci numbers with memoization *)
+
+fib::usage = "f[n] calculates the n'th Fibonacci number.";
+fib[0] = fib[1] = 1;
+fib[n_Integer?Positive]:= fib[n] = fib[n-1] + fib[n-2];
+
+In[4]:= fib[42]
+Out[4]= 433494437

lib/rouge/lexers/mathematica.rb

@@ -0,0 +1,95 @@
+# -*- coding: utf-8 -*- #
+
+module Rouge
+  module Lexers
+    class Mathematica < RegexLexer
+      title "Mathematica"
+      desc "Wolfram Mathematica, the world's definitive system for modern technical computing."
+      tag 'mathematica'
+      aliases 'wl'
+      filenames '*.m', '*.wl'
+      mimetypes 'application/vnd.wolfram.mathematica.package', 'application/vnd.wolfram.wl'
+
+      # Mathematica has various input forms for numbers. We need to handle numbers in bases, precision, accuracy,
+      # and *^ scientific notation. All this works for integers and real numbers. Some examples
+      # 1  1234567  1.1  .3  0.2  1*^10  2*^+10  3*^-10
+      # 1`1  1``1  1.2`  1.2``1.234*^-10  1.2``1.234*^+10  1.2``1.234*^10
+      # 2^^01001 10^^1.2``20.1234*^-10
+      base = /(?:\d+)/
+      number = /(?:\.\d+|\d+\.\d*|\d+)/
+      number_base = /(?:\.\w+|\w+\.\w*|\w+)/
+      precision = /`(`?#{number})?/
+
+      operators = /[+\-*\/|,;.:@~=><&`'^?!_%]/
+      braces = /[\[\](){}]/
+
+      string = /"(\\\\|\\"|[^"])*"/
+
+      # symbols and namespaced symbols. Note the special form \[Gamma] for named characters. These are also symbols.
+      # Module With Block Integrate Table Plot
+      # x32 $x x$ $Context` Context123`$x `Private`Context
+      # \[Gamma] \[Alpha]x32 Context`\[Xi]
+      identifier = /[a-zA-Z$][$a-zA-Z0-9]*/
+      named_character = /\\\[#{identifier}\]/
+      symbol = /(#{identifier}|#{named_character})+/
+      context_symbol = /`?#{symbol}(`#{symbol})*`?/
+
+      # Slots for pure functions.
+      # Examples: # ## #1 ##3 #Test #"Test" #[Test] #["Test"]
+      association_slot = /#(#{identifier}|\"#{identifier}\")| /
+      slot = /#{association_slot}|#[0-9]*/
+
+      # Handling of message like symbol::usage or symbol::"argx"
+      message = /::(#{identifier}|#{string})/
+
+      # Highlighting of the special in and out markers that are prepended when you copy a cell
+      in_out = /(In|Out)\[[0-9]+\]:?=/
+
+      # Although Module, With and Block are normal built-in symbols, we give them a special treatment as they are
+      # the most important expressions for defining local variables
+      def self.keywords
+        @keywords = Set.new %w(
+          Module With Block
+        )
+      end
+
+      # The list of built-in symbols comes from a wolfram server and is created automatically by rake
+      def self.builtins
+        load Pathname.new(__FILE__).dirname.join('mathematica/builtins.rb')
+        self.builtins
+      end
+
+      state :root do
+        rule /\s+/, Text::Whitespace
+        rule /\(\*/, Comment, :comment
+        rule /#{base}\^\^#{number_base}#{precision}?(\*\^[+-]?\d+)?/, Num # a number with a base
+        rule /(?:#{number}#{precision}?(?:\*\^[+-]?\d+)?)/, Num # all other numbers
+        rule message, Operator::Word
+        rule in_out, Generic::Prompt
+        rule /#{context_symbol}/m do |m|
+          match = m[0]
+          if self.class.keywords.include? match
+            token Keyword::Reserved
+          elsif self.class.builtins.include? match
+            token Name::Builtin
+          else
+            token Name
+          end
+        end
+        rule slot, Name::Namespace
+        rule operators, Operator
+        rule braces, Operator::Word
+        rule string, Str::Single
+      end
+
+      # Allow for nested comments and special treatment of ::Section:: or :Author: markup
+      state :comment do
+        rule /\(\*/, Comment, :comment
+        rule /\*\)/, Comment, :pop!
+        rule /::#{identifier}::/, Comment::Preproc
+        rule /:(#{identifier}|[^\S])+:/, Comment::Preproc
+        rule /./, Comment
+      end
+    end
+  end
+end

spec/lexers/mathematica_spec.rb

@@ -0,0 +1,20 @@
+# -*- coding: utf-8 -*- #
+
+describe Rouge::Lexers::Mathematica do
+  let(:subject) { Rouge::Lexers::Mathematica.new }
+
+  describe 'guessing' do
+    include Support::Guessing
+
+    it 'guesses by filename' do
+      assert_guess :filename => 'foo.wl'
+      assert_guess :filename => 'foo.m'
+    end
+
+    it 'guesses by mimetype' do
+      assert_guess :mimetype => 'application/vnd.wolfram.mathematica.package'
+      assert_guess :mimetype => 'application/vnd.wolfram.wl'
+    end
+  end
+end
+

spec/visual/samples/mathematica

@@ -0,0 +1,29 @@
+(* :Title: Collatz Visualization *)
+(* :Author: halirutan *)
+(* :Mathematica Version: 10+ *)
+
+CollatzSequence::usage = "CollatzSequence[list] creates a Collatz sequence.";
+CollatzSequence[list_] := Module[{memory, tmp, chain, result = Internal`Bag[]},
+  memory[1] = False;
+  memory[n_] := (memory[n] = False; True);
+
+  Do[
+   chain = Internal`Bag[];
+   tmp = l;
+   While[memory[tmp],
+    Internal`StuffBag[chain, tmp];
+    tmp = If[EvenQ[tmp], tmp/2, 3 tmp + 1];
+    ];
+   Internal`StuffBag[chain, tmp];
+   Internal`StuffBag[result, chain],
+   {l, list}];
+  Internal`BagPart[#, All] & /@ Internal`BagPart[result, All]
+];
+
+Graph[
+ Flatten[(Rule @@@ Partition[#, 2, 1]) & /@
+   CollatzSequence[Range[50000]]],
+ PerformanceGoal -> "Speed",
+ GraphLayout -> {"PackingLayout" -> "ClosestPacking"},
+ VertexStyle -> Opacity[0.2, RGBColor[44/51, 10/51, 47/255]],
+ EdgeStyle -> RGBColor[38/255, 139/255, 14/17]]

tasks/mathematica.rake

@@ -0,0 +1,42 @@
+# -*- coding: utf-8 -*- #
+
+require 'open-uri'
+
+def mathematica_builtins(&b)
+  return enum_for :mathematica_builtins unless block_given?
+
+  mathematica_doc_url = 'http://reference.wolfram.com/language/guide/AlphabeticalListing.html'
+
+  mathematica_docs = open(mathematica_doc_url).read
+
+  p :docs => mathematica_docs
+
+  mathematica_docs.scan %r(<span class="IFSans"><a href="/language/ref/(\w+)[.]html">)m do |word|
+    p :word => word
+    yield word
+  end
+end
+
+def mathematica_builtins_source
+  yield   "# -*- coding: utf-8 -*- #"
+  yield   "# automatically generated by `rake builtins:mathematica`"
+  yield   "module Rouge"
+  yield   "  module Lexers"
+  yield   "    class Mathematica"
+  yield   "      def self.builtins"
+  yield   "        @builtins ||= Set.new %w(#{mathematica_builtins.to_a.join(' ')})"
+  yield   "      end"
+  yield   "    end"
+  yield   "  end"
+  yield   "end"
+end
+
+namespace :builtins do
+  task :mathematica do
+    File.open('lib/rouge/lexers/mathematica/builtins.rb', 'w') do |f|
+      mathematica_builtins_source do |line|
+        f.puts line
+      end
+    end
+  end
+end