From b46a86d48a552f64e48dd1d04b5ef89ba85d801b Mon Sep 17 00:00:00 2001
From: Sylvestre Ledru <sylvestre@debian.org>
Date: Sun, 31 May 2026 10:41:52 +0200
Subject: [PATCH] bench: end-to-end search throughput via uumain

The existing match/throughput benches call Matcher::match_line on
pre-split lines, so they only measure matching in isolation and cannot
observe how the searcher feeds data to the matcher. Add a 'search'
group that drives the whole pipeline through uumain over a multi-MB
file: a literal pattern (which a buffer-at-a-time searcher can speed
up) and an extended-regex control (which it cannot). Uses -q with a
non-matching pattern for a silent full-file scan.
---
 benches/grep_bench.rs | 70 ++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 69 insertions(+), 1 deletion(-)

diff --git a/benches/grep_bench.rs b/benches/grep_bench.rs
index 3232f08..a87ab50 100644
--- a/benches/grep_bench.rs
+++ b/benches/grep_bench.rs
@@ -284,5 +284,73 @@ fn bench_throughput(c: &mut Criterion) {
     group.finish();
 }
 
-criterion_group!(benches, bench_compile, bench_match, bench_throughput);
+/// End-to-end search throughput, driven through the real `uumain` entry point
+/// so the whole pipeline (input buffering, searcher, output) is exercised.
+///
+/// `bench_match` / `bench_throughput` call `Matcher::match_line` on pre-split
+/// lines, which measures matching in isolation. They cannot see a change to how
+/// the *searcher* feeds data to the matcher (e.g. scanning whole buffers instead
+/// of testing one line at a time), because they never run the searcher. These
+/// cases do: a literal pattern (which a buffer-at-a-time engine can accelerate)
+/// and an extended-regex control (which cannot), over a multi-megabyte file.
+fn bench_search(c: &mut Criterion) {
+    use std::ffi::OsString;
+
+    // A log-like file large enough to cross many internal read buffers.
+    let mut content = String::new();
+    for i in 0..80_000u32 {
+        if i % 100 == 0 {
+            content.push_str(&format!(
+                "2024-01-15 10:30:{:02} ERROR worker-{i} connection reset\n",
+                i % 60
+            ));
+        } else {
+            content.push_str(&format!(
+                "2024-01-15 10:30:{:02} INFO  worker-{i} request handled in {}ms\n",
+                i % 60,
+                i % 1000
+            ));
+        }
+    }
+    assert!(content.len() > 4 * 1024 * 1024);
+
+    let mut path = std::env::temp_dir();
+    path.push(format!("uu_grep_bench_{}.log", std::process::id()));
+    std::fs::write(&path, &content).unwrap();
+    let path_arg = path.clone().into_os_string();
+
+    // `-q` with a pattern that never matches forces a full scan of the file and
+    // produces no output, so the timing reflects pure scanning throughput.
+    let run = |extra_flag: Option<&str>, pattern: &str| {
+        let mut args: Vec<OsString> = vec![OsString::from("grep"), OsString::from("-q")];
+        if let Some(flag) = extra_flag {
+            args.push(OsString::from(flag));
+        }
+        args.push(OsString::from(pattern));
+        args.push(path_arg.clone());
+        // No match => Err(exit code 1); we only care about the work, not status.
+        let _ = uu_grep::uumain(args.into_iter());
+    };
+
+    let mut group = c.benchmark_group("search");
+
+    group.bench_function("scan_literal_no_match", |b| {
+        b.iter(|| run(None, black_box("NONEXISTENT_TOKEN_XYZ")))
+    });
+
+    group.bench_function("scan_regex_no_match", |b| {
+        b.iter(|| run(Some("-E"), black_box("NON[0-9]EXISTENT_TOKEN")))
+    });
+
+    group.finish();
+    let _ = std::fs::remove_file(&path);
+}
+
+criterion_group!(
+    benches,
+    bench_compile,
+    bench_match,
+    bench_throughput,
+    bench_search
+);
 criterion_main!(benches);