Major refactoring and performance improvements.

.travis.yml

@@ -7,6 +7,7 @@ sudo: false
 script:
   - cargo build --verbose
   - cargo test --verbose
+  - ./run-shootout-test
   - |
     [ $TRAVIS_RUST_VERSION != nightly ] || (
       cargo test --verbose --features pattern &&

Cargo.toml

@@ -13,7 +13,15 @@ An implementation of regular expressions for Rust.
 
 [[test]]
 path = "regex_macros/tests/test_dynamic.rs"
-name = "all"
+name = "dynamic"
+
+[[test]]
+path = "regex_macros/tests/test_dynamic_nfa.rs"
+name = "dynamic_nfa"
+
+[[test]]
+path = "regex_macros/tests/test_dynamic_backtrack.rs"
+name = "dynamic_backtrack"
 
 [[bench]]
 name = "all"
@@ -22,6 +30,8 @@ test = false
 bench = true
 
 [dependencies]
+aho-corasick = "0.1"
+memchr = "0.1"
 regex-syntax = { path = "regex-syntax", version = "0.1" }
 
 [dev-dependencies]

README.md

@@ -8,6 +8,7 @@ A Rust library for parsing, compiling, and executing regular expressions.
 
 [Documentation](http://doc.rust-lang.org/regex)
 
+
 ## Usage
 
 Add this to your `Cargo.toml`:
@@ -23,6 +24,7 @@ and this to your crate root:
 extern crate regex;
 ```
 
+
 # License
 
 `regex` is primarily distributed under the terms of both the MIT license and

examples/regexdna-output.txt

@@ -0,0 +1,13 @@
+agggtaaa|tttaccct 0
+[cgt]gggtaaa|tttaccc[acg] 3
+a[act]ggtaaa|tttacc[agt]t 9
+ag[act]gtaaa|tttac[agt]ct 8
+agg[act]taaa|ttta[agt]cct 10
+aggg[acg]aaa|ttt[cgt]ccct 3
+agggt[cgt]aa|tt[acg]accct 4
+agggta[cgt]a|t[acg]taccct 3
+agggtaa[cgt]|[acg]ttaccct 5
+
+101745
+100000
+133640

examples/shootout-regex-dna.rs

@@ -0,0 +1,67 @@
+// The Computer Language Benchmarks Game
+// http://benchmarksgame.alioth.debian.org/
+//
+// contributed by the Rust Project Developers
+// contributed by TeXitoi
+// contributed by BurntSushi
+
+extern crate regex;
+
+use std::io::{self, Read};
+use std::sync::Arc;
+use std::thread;
+
+macro_rules! regex { ($re:expr) => { ::regex::Regex::new($re).unwrap() } }
+
+fn main() {
+    let mut seq = String::with_capacity(10 * (1 << 20));
+    io::stdin().read_to_string(&mut seq).unwrap();
+    let ilen = seq.len();
+
+    seq = regex!(">[^\n]*\n|\n").replace_all(&seq, "");
+    let clen = seq.len();
+    let seq_arc = Arc::new(seq.clone());
+
+    let variants = vec![
+        regex!("agggtaaa|tttaccct"),
+        regex!("[cgt]gggtaaa|tttaccc[acg]"),
+        regex!("a[act]ggtaaa|tttacc[agt]t"),
+        regex!("ag[act]gtaaa|tttac[agt]ct"),
+        regex!("agg[act]taaa|ttta[agt]cct"),
+        regex!("aggg[acg]aaa|ttt[cgt]ccct"),
+        regex!("agggt[cgt]aa|tt[acg]accct"),
+        regex!("agggta[cgt]a|t[acg]taccct"),
+        regex!("agggtaa[cgt]|[acg]ttaccct"),
+    ];
+    let mut counts = vec![];
+    for variant in variants {
+        let seq = seq_arc.clone();
+        let restr = variant.to_string();
+        let future = thread::spawn(move || variant.find_iter(&seq).count());
+        counts.push((restr, future));
+    }
+
+    let substs = vec![
+        (regex!("B"), "(c|g|t)"),
+        (regex!("D"), "(a|g|t)"),
+        (regex!("H"), "(a|c|t)"),
+        (regex!("K"), "(g|t)"),
+        (regex!("M"), "(a|c)"),
+        (regex!("N"), "(a|c|g|t)"),
+        (regex!("R"), "(a|g)"),
+        (regex!("S"), "(c|g)"),
+        (regex!("V"), "(a|c|g)"),
+        (regex!("W"), "(a|t)"),
+        (regex!("Y"), "(c|t)"),
+    ];
+    let mut seq = seq;
+    for (re, replacement) in substs.into_iter() {
+        seq = re.replace_all(&seq, replacement);
+    }
+    let rlen = seq.len();
+
+    for (variant, count) in counts {
+        println!("{} {}", variant, count.join().unwrap());
+    }
+    println!("\n{}\n{}\n{}", ilen, clen, rlen);
+}

regex_macros/Cargo.toml

@@ -17,10 +17,6 @@ plugin = true
 path = "tests/test_native.rs"
 name = "all"
 
-[[test]]
-path = "benches/shootout-regex-dna.rs"
-name = "shootout_regex_dna"
-
 [[bench]]
 name = "all"
 path = "benches/bench_native.rs"

regex_macros/benches/bench.rs

@@ -59,6 +59,13 @@ fn match_class_in_range(b: &mut Bencher) {
     bench_assert_match(b, re, &text);
 }
 
+#[bench]
+fn match_class_unicode(b: &mut Bencher) {
+    let re = regex!(r"\pL");
+    let text = format!("{}a", repeat("☃5☃5").take(20).collect::<String>());
+    bench_assert_match(b, re, &text);
+}
+
 #[bench]
 fn replace_all(b: &mut Bencher) {
     let re = regex!("[cjrw]");
@@ -171,15 +178,19 @@ fn gen_text(n: usize) -> String {
 throughput!(easy0_32, easy0(), 32);
 throughput!(easy0_1K, easy0(), 1<<10);
 throughput!(easy0_32K, easy0(), 32<<10);
+throughput!(easy0_1MB, easy0(), 1<<20);
 
 throughput!(easy1_32, easy1(), 32);
 throughput!(easy1_1K, easy1(), 1<<10);
 throughput!(easy1_32K, easy1(), 32<<10);
+throughput!(easy1_1MB, easy1(), 1<<20);
 
 throughput!(medium_32, medium(), 32);
 throughput!(medium_1K, medium(), 1<<10);
 throughput!(medium_32K,medium(), 32<<10);
+throughput!(medium_1MB, medium(), 1<<20);
 
 throughput!(hard_32, hard(), 32);
 throughput!(hard_1K, hard(), 1<<10);
 throughput!(hard_32K,hard(), 32<<10);
+throughput!(hard_1MB, hard(), 1<<20);