Bench/ci continue profiling (#35)

* add: bench

.github/workflows/bench.yml

@@ -0,0 +1,25 @@
+name: Rust Bencher
+
+on:
+  push:
+    branches: [ "master" ]
+  pull_request:
+    branches: [ "master" ]
+
+jobs:
+  benchmark_base_branch:
+    name: Continuous Benchmarking with Bencher
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: bencherdev/bencher@main
+      - name: Track base branch benchmarks with Bencher
+        run: |
+          bencher run \
+          --project bleuscore \
+          --token '${{ secrets.BENCHER_API_TOKEN }}' \
+          --branch master \
+          --testbed ubuntu-latest \
+          --adapter rust \
+          --err \
+          cargo bench --all

rust-toolchain.toml

@@ -0,0 +1,2 @@
+[toolchain]
+channel = "nightly"

src/bleu.rs

@@ -131,3 +131,23 @@ mod test {
         assert!((res.bleu - 0.668740304976422).abs() < 1e-10);
     }
 }
+
+#[cfg(test)]
+mod benchmark {
+    use crate::bleu::compute_score;
+    use test::Bencher;
+    #[bench]
+    fn bench_bleu(b: &mut Bencher) {
+        let max_order: usize = 4;
+        let smooth: bool = true;
+        let references: Vec<Vec<String>> = vec![vec!["Hello, World!".to_string()]];
+        let predictions: Vec<String> = vec!["Yellow, World!".to_string()];
+
+        let iter_num: usize = 100;
+        b.iter(|| {
+            std::hint::black_box(for _ in 1..=iter_num {
+                compute_score(&references, &predictions, max_order, smooth);
+            });
+        });
+    }
+}

src/lib.rs

@@ -37,6 +37,9 @@ println!("result: {:?}", res);
 // brevity_penalty: 1.0, length_ratio: 1.0, translation_length: 4, reference_length: 4 }
 ```
 !*/
+#![feature(test)]
+extern crate test;
+
 mod tokenizer;
 pub use crate::tokenizer::{Tokenizer, Tokenizer13a, TokenizerRegex};
 mod bleu;

src/ngram.rs

@@ -95,3 +95,23 @@ mod test {
         assert_eq!(counter[&"aabc"], 1);
     }
 }
+
+#[cfg(test)]
+mod benchmark {
+    use crate::ngram::{get_ngram_counter, get_token_ngram_counter};
+    use std::cmp::max;
+    use test::Bencher;
+
+    #[bench]
+    fn bench_ngram(b: &mut Bencher) {
+        let line = "aabc";
+        let max_order = 4;
+
+        let iter_num: usize = 100;
+        b.iter(|| {
+            std::hint::black_box(for _ in 1..=iter_num {
+                get_ngram_counter(line, max_order);
+            });
+        });
+    }
+}

src/tokenizer.rs

@@ -143,3 +143,22 @@ mod test {
         )
     }
 }
+
+#[cfg(test)]
+mod benchmark {
+    use crate::tokenizer;
+    use crate::tokenizer::Tokenizer;
+    use test::Bencher;
+    #[bench]
+    fn bench_tokenizer(b: &mut Bencher) {
+        let tokenizer_regex = tokenizer::Tokenizer13a::new();
+        let line = "Hello, &quot;World!<skipped>";
+
+        let iter_num: usize = 100;
+        b.iter(|| {
+            std::hint::black_box(for _ in 1..=iter_num {
+                tokenizer_regex.tokenize(line);
+            });
+        });
+    }
+}