CoffeeScript JS guessing

lib/linguist/blob_helper.rb

@@ -150,6 +150,8 @@ module Linguist
     # Generated source code is supressed in diffs and is ignored by
     # langauge statistics.
     #
+    # Requires Blob#data
+    #
     # Includes:
     # - XCode project XML files
     # - Minified JavaScript
@@ -158,6 +160,8 @@ module Linguist
     def generated?
       if ['.xib', '.nib', '.pbxproj'].include?(pathname.extname)
         true
+      elsif generated_coffeescript?
+        true
       elsif pathname.extname == '.js'
         # JS is minified if any lines are longer than 1000c
         lines.any? { |l| l.length > 1000 }
@@ -166,6 +170,42 @@ module Linguist
       end
     end
 
+    # Internal: Is the blob JS generated by CoffeeScript?
+    #
+    # Requires Blob#data
+    #
+    # CoffeScript is meant to output JS that would be difficult to
+    # tell if it was generated or not. Look for a number of patterns
+    # outputed by the CS compiler.
+    #
+    # Return true or false
+    def generated_coffeescript?
+      return unless pathname.extname == '.js'
+
+      if lines[0] == '(function() {' &&     # First line is module closure opening
+          lines[-2] == '}).call(this);' &&  # Second to last line closes module closure
+          lines[-1] == ''                   # Last line is blank
+
+        score = 0
+
+        lines.each do |line|
+          if line =~ /var /
+            # Underscored temp vars are likely to be Coffee
+            score += 1 * line.gsub(/(_fn|_i|_len|_ref|_results)/).count
+
+            # bind and extend functions are very Coffee specific
+            score += 3 * line.gsub(/(__bind|__extends|__hasProp|__indexOf|__slice)/).count
+          end
+        end
+
+        # Require a score of 3. This is fairly arbitrary. Consider
+        # tweaking later.
+        score >= 3
+      else
+        false
+      end
+    end
+
     # Public: Should the blob be indexed for searching?
     #
     # Excluded: