Rollup merge of #124551 - Swatinem:debug-str-bench, r=cuviper

Add benchmarks for `impl Debug for str`

In order to inform future perf improvements and prevent regressions, lets add some benchmarks that stress `impl Debug for str`.

---

As I am currently working on improving the perf in https://github.com/rust-lang/rust/pull/121150, its nice to have these benchmarks.

Writing them, I also saw that escapes are written out one char at a time, even though other parts of the code are already optimizing that via `as_str`, which I intend to do as well as a followup improvement.

r? ``@cuviper``
☝🏻 as you were also assigned to https://github.com/rust-lang/rust/pull/121150, CC ``@the8472`` if you want to steal the review :-)

2 files changed, 80 insertions, 0 deletions

diff --git a/library/core/benches/str.rs b/library/core/benches/str.rs
index 7d36eff3d6c..0f14809444b 100644
--- a/library/core/benches/str.rs
+++ b/library/core/benches/str.rs
@@ -3,6 +3,7 @@ use test::{black_box, Bencher};
 
 mod char_count;
 mod corpora;
+mod debug;
 mod iter;
 
 #[bench]
diff --git a/library/core/benches/str/debug.rs b/library/core/benches/str/debug.rs
new file mode 100644
index 00000000000..7c72228f0fb
--- /dev/null
+++ b/library/core/benches/str/debug.rs
@@ -0,0 +1,79 @@
+//! This primarily benchmarks `impl Debug for str`,
+//! and it also explicitly tests that we minimizes calls to the underlying `Write`r.
+//! While that is an implementation detail and there are no guarantees about it,
+//! we should still try to minimize those calls over time rather than regress them.
+
+use std::fmt::{self, Write};
+use test::{black_box, Bencher};
+
+#[derive(Default)]
+struct CountingWriter {
+    buf: String,
+    write_calls: usize,
+}
+
+impl Write for CountingWriter {
+    fn write_str(&mut self, s: &str) -> fmt::Result {
+        self.buf.push_str(s);
+        self.write_calls += 1;
+        Ok(())
+    }
+}
+
+fn assert_fmt(s: &str, expected: &str, expected_write_calls: usize) {
+    let mut w = CountingWriter::default();
+
+    write!(&mut w, "{s:?}").unwrap();
+    assert_eq!(s.len(), 64);
+    assert_eq!(w.buf, expected);
+    assert_eq!(w.write_calls, expected_write_calls);
+}
+
+#[bench]
+fn ascii_only(b: &mut Bencher) {
+    let s = "just a bit of ascii text that has no escapes. 64 bytes exactly!!";
+    assert_fmt(s, r#""just a bit of ascii text that has no escapes. 64 bytes exactly!!""#, 3);
+    b.iter(|| {
+        black_box(format!("{:?}", black_box(s)));
+    });
+}
+
+#[bench]
+fn ascii_escapes(b: &mut Bencher) {
+    let s = "some\tmore\tascii\ttext\nthis time with some \"escapes\", also 64 byte";
+    assert_fmt(
+        s,
+        r#""some\tmore\tascii\ttext\nthis time with some \"escapes\", also 64 byte""#,
+        21,
+    );
+    b.iter(|| {
+        black_box(format!("{:?}", black_box(s)));
+    });
+}
+
+#[bench]
+fn some_unicode(b: &mut Bencher) {
+    let s = "egy kis szöveg néhány unicode betűvel. legyen ez is 64 byte.";
+    assert_fmt(s, r#""egy kis szöveg néhány unicode betűvel. legyen ez is 64 byte.""#, 3);
+    b.iter(|| {
+        black_box(format!("{:?}", black_box(s)));
+    });
+}
+
+#[bench]
+fn mostly_unicode(b: &mut Bencher) {
+    let s = "предложение из кириллических букв.";
+    assert_fmt(s, r#""предложение из кириллических букв.""#, 3);
+    b.iter(|| {
+        black_box(format!("{:?}", black_box(s)));
+    });
+}
+
+#[bench]
+fn mixed(b: &mut Bencher) {
+    let s = "\"❤️\"\n\"hűha ez betű\"\n\"кириллических букв\".";
+    assert_fmt(s, r#""\"❤\u{fe0f}\"\n\"hűha ez betű\"\n\"кириллических букв\".""#, 36);
+    b.iter(|| {
+        black_box(format!("{:?}", black_box(s)));
+    });
+}