The Computer Language
Benchmarks Game

regex-dna F# Mono LLVM #2 program

source code

// The Computer Language Benchmarks Game
// Contributed by Valentin Kraevskiy

open System.Text.RegularExpressions

let regex s = Regex (s, RegexOptions.Compiled)
let input = stdin.ReadToEnd ()
let text = (regex ">.*\n|\n").Replace (input, "")

|> List.iter (fun s ->
         printf "%s %i\n" s ((regex s).Matches text).Count)

let newText =
    ["B", "(c|g|t)"
     "D", "(a|g|t)"
     "H", "(a|c|t)"
     "K", "(g|t)"
     "M", "(a|c)"
     "N", "(a|c|g|t)"
     "R", "(a|g)"
     "S", "(c|g)"
     "V", "(a|c|g)"
     "W", "(a|t)"
     "Y", "(c|t)"]
     |> List.fold (fun s (code, alt) -> 
            (regex code).Replace (s, alt)) text

printf "\n%i\n%i\n%i\n" input.Length text.Length newText.Length

notes, command-line, and program output

32-bit Ubuntu one core
F# Compiler for F# 4.0 (Open Source Edition)
Mono JIT compiler version 4.5.1 (master/3e844dd Fri May  6 19:24:07 PDT 2016)
	LLVM:          yes(3.6.0svn-mono-master/9f79399)
	GC:            sgen

Sat, 07 May 2016 19:51:15 GMT

mv regexdna.fsharp-2.fsharp regexdna.fsharp-2.fs
/usr/local/bin/fsharpc --target:exe --platform:x86 -O  -o regexdna.fsharp-2.fsharp_run.exe regexdna.fsharp-2.fs
F# Compiler for F# 4.0 (Open Source Edition)
Freely distributed under the Apache 2.0 Open Source License

/home/dunham/benchmarksgame_onecore/regexdna/tmp/regexdna.fsharp-2.fs(6,1): warning FS0221: The declarations in this file will be placed in an implicit module 'Regexdna.fsharp-2' based on the file name 'regexdna.fsharp-2.fs'. However this is not a valid F# identifier, so the contents will not be accessible from other files. Consider renaming the file or adding a 'module' or 'namespace' declaration at the top of the file.
rm regexdna.fsharp-2.fs
4.09s to complete and log all make actions

/usr/local/bin/mono --llvm --gc=sgen regexdna.fsharp-2.fsharp_run.exe 0 < regexdna-input5000000.txt

agggtaaa|tttaccct 356
[cgt]gggtaaa|tttaccc[acg] 1250
a[act]ggtaaa|tttacc[agt]t 4252
ag[act]gtaaa|tttac[agt]ct 2894
agg[act]taaa|ttta[agt]cct 5435
aggg[acg]aaa|ttt[cgt]ccct 1537
agggt[cgt]aa|tt[acg]accct 1431
agggta[cgt]a|t[acg]taccct 1608
agggtaa[cgt]|[acg]ttaccct 2178