GitHub Linguist - Heuristic Evaluation Benchmark

-- https://github.com/github/linguist/pull/2749



Original/Current `.ms` Heuristic
================================

/((^|\s)move?[. ])|\.(include|globa?l)\s/.match(data)

	1.	real	0m40.133s
		user	0m39.271s
		sys	0m0.841s

	2.	real	0m39.607s
		user	0m38.796s
		sys	0m0.803s

	3.	real	0m40.440s
		user	0m39.629s
		sys	0m0.802s

	4.	real	0m39.692s
		user	0m38.854s
		sys	0m0.825s

	5.	real	0m40.053s
		user	0m39.234s
		sys	0m0.806s

	6.	real	0m39.801s
		user	0m38.989s
		sys	0m0.798s

	7.	real	0m39.468s
		user	0m38.677s
		sys	0m0.784s

	8.	real	0m39.409s
		user	0m38.625s
		sys	0m0.774s

	9.	real	0m39.469s
		user	0m38.687s
		sys	0m0.770s

	10.	real	0m39.932s
		user	0m39.107s
		sys	0m0.820s


Amended Heuristic
=================
/(?<!\S)\.(include|globa?l)\s/.match(data) || /(?<!\/\*)(\A|\n)\s*\.[A-Za-z]/.match(data.gsub(/"([^\\"]|\\.)*"|'([^\\']|\\.)*'|\\\s*(?:--.*)?\n/, ""))

	1.	real	0m42.147s
		user	0m41.144s
		sys	0m0.985s

	2.	real	0m41.115s
		user	0m40.100s
		sys	0m1.006s

	3.	real	0m40.729s
		user	0m39.756s
		sys	0m0.961s

	4.	real	0m41.440s
		user	0m40.417s
		sys	0m1.006s

	5.	real	0m41.783s
		user	0m40.751s
		sys	0m1.018s

	6.	real	0m41.039s
		user	0m40.051s
		sys	0m0.976s

	7.	real	0m41.489s
		user	0m40.508s
		sys	0m0.970s

	8.	real	0m40.818s
		user	0m39.860s
		sys	0m0.949s

	9.	real	0m41.055s
		user	0m40.117s
		sys	0m0.928s

	10.	real	0m41.462s
		user	0m40.502s
		sys	0m0.945s



Earlier variations
==================

/(?<!\S)\.(include|globa?l)\s/.match(data) || /(?<!\/\*)(\A|\n)\s*\.[A-Za-z]/.match(data.sub(/"([^\\"]|\\.)*"|'([^\\']|\\.)*'/, ""))

	1.	real	0m38.690s
		user	0m37.928s
		sys	0m0.752s

	2.	real	0m39.567s
		user	0m38.743s
		sys	0m0.787s

	3.	real	0m41.650s
		user	0m40.663s
		sys	0m0.970s

	4.	real	0m39.447s
		user	0m38.652s
		sys	0m0.784s

	5.	real	0m40.228s
		user	0m39.404s
		sys	0m0.806s

	6.	real	0m38.712s
		user	0m37.991s
		sys	0m0.712s

	7.	real	0m40.370s
		user	0m39.536s
		sys	0m0.816s

	8.	real	0m40.918s
		user	0m40.093s
		sys	0m0.810s

	9.	real	0m40.444s
		user	0m39.671s
		sys	0m0.760s

	10.	real	0m39.979s
		user	0m39.218s
		sys	0m0.750s



/(?<!\S)\.(include|globa?l)\s/.match(data) || /(?<!\/\*)(\A|\n)\s*\.[A-Za-z]/.match(data)

	1.	real	0m38.791s
		user	0m38.062s
		sys	0m0.720s

	2.	real	0m38.471s
		user	0m37.734s
		sys	0m0.728s

	3.	real	0m38.468s
		user	0m37.750s
		sys	0m0.715s

	4.	real	0m38.961s
		user	0m38.213s
		sys	0m0.740s

	5.	real	0m38.646s
		user	0m37.919s
		sys	0m0.725s

	6. 	real	0m38.688s
		user	0m37.939s
		sys	0m0.741s

	7.	real	0m38.891s
		user	0m38.116s
		sys	0m0.765s

	8.	real	0m39.273s
		user	0m38.493s
		sys	0m0.769s

	9.	real	0m39.468s
		user	0m38.637s
		sys	0m0.820s

	10.	real	0m39.515s
		user	0m38.669s
		sys	0m0.838s