From 8fb1626118198ec0ac538075eb02d7f5249494b2 Mon Sep 17 00:00:00 2001
From: Jameson Nash <vtjnash@gmail.com>
Date: Wed, 14 Apr 2021 16:21:43 -0400
Subject: [PATCH] use appropriate optimizations in regex_dna

The multi-replace method is being added in https://github.com/JuliaLang/julia/pull/40484
---
 src/shootout/regex_dna.jl | 68 ++++++++++++++++++++++-----------------
 1 file changed, 38 insertions(+), 30 deletions(-)

diff --git a/src/shootout/regex_dna.jl b/src/shootout/regex_dna.jl
index 8e519fde..63320493 100644
--- a/src/shootout/regex_dna.jl
+++ b/src/shootout/regex_dna.jl
@@ -5,30 +5,30 @@
 # Fix from David Campbell
 
 const variants = [
-      "agggtaaa|tttaccct",
-      "[cgt]gggtaaa|tttaccc[acg]",
-      "a[act]ggtaaa|tttacc[agt]t",
-      "ag[act]gtaaa|tttac[agt]ct",
-      "agg[act]taaa|ttta[agt]cct",
-      "aggg[acg]aaa|ttt[cgt]ccct",
-      "agggt[cgt]aa|tt[acg]accct",
-      "agggta[cgt]a|t[acg]taccct",
-      "agggtaa[cgt]|[acg]ttaccct"
+      r"agggtaaa|tttaccct",
+      r"[cgt]gggtaaa|tttaccc[acg]",
+      r"a[act]ggtaaa|tttacc[agt]t",
+      r"ag[act]gtaaa|tttac[agt]ct",
+      r"agg[act]taaa|ttta[agt]cct",
+      r"aggg[acg]aaa|ttt[cgt]ccct",
+      r"agggt[cgt]aa|tt[acg]accct",
+      r"agggta[cgt]a|t[acg]taccct",
+      r"agggtaa[cgt]|[acg]ttaccct"
 ]
 
-const subs = [
-    (r"B", "(c|g|t)"),
-    (r"D", "(a|g|t)"),
-    (r"H", "(a|c|t)"),
-    (r"K", "(g|t)"),
-    (r"M", "(a|c)"),
-    (r"N", "(a|c|g|t)"),
-    (r"R", "(a|g)"),
-    (r"S", "(c|g)"),
-    (r"V", "(a|c|g)"),
-    (r"W", "(a|t)"),
-    (r"Y", "(c|t)")
-]
+const subs = (
+    ("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)")
+)
 
 function perf_regex_dna()
     infile = joinpath(SHOOTOUT_DATA_PATH, "regexdna-input.txt")
@@ -40,18 +40,26 @@ function perf_regex_dna()
 
     for v in variants
         k = 0
-        for m in eachmatch(Regex(v), seq)
+        for m in eachmatch(v, seq)
             k += 1
         end
-#        @printf("%s %d\n", v, k)
     end
 
-    for (u, v) in subs
-        seq = replace(seq, u => v)
+    if applicable(replace, seq, subs...)
+        # VERSION > 1.7-dev
+        seq = replace(seq, subs...)
+    elseif false
+        # semi-optimized regex
+        seq = replace(seq, subs...)
+        r = Regex(join(first.(subs), "|"))
+        repl = Dict(subs)
+        seq = replace(seq, r => (r -> repl[r]))
+    else
+        # multiple passes
+        for sub in subs
+            seq = replace(seq, sub)
+        end
     end
 
-#    println()
-#    println(l1)
-#    println(l2)
-#    println(length(seq))
+    seq, k
 end