From d4b77a8d8967ce1bf701ec65ceb9a75e85e5f2e0 Mon Sep 17 00:00:00 2001
From: Andrew Gallant <jamslam@gmail.com>
Date: Tue, 14 Oct 2025 13:46:02 -0400
Subject: [PATCH] searcher: fix a performance bug with `-A/--after-context`

Previously (with the previous commit):

```
$ cat bigger.txt | (time rg ZQZQZQZQZQ -A999) | wc -l

real    2.321
user    0.674
sys     0.735
maxmem  30 MB
faults  0
1000

$ cat bigger.txt | (time rg ZQZQZQZQZQ -A9999) | wc -l

real    2.513
user    0.823
sys     0.686
maxmem  30 MB
faults  0
10000

$ cat bigger.txt | (time rg ZQZQZQZQZQ -A99999) | wc -l

real    5.067
user    3.254
sys     0.676
maxmem  30 MB
faults  0
100000

$ cat bigger.txt | (time rg ZQZQZQZQZQ -A999999) | wc -l

real    6.658
user    4.841
sys     0.778
maxmem  51 MB
faults  0
1000000
```

Now with this commit:

```
$ cat bigger.txt | (time rg ZQZQZQZQZQ -A999) | wc -l

real    1.845
user    0.328
sys     0.757
maxmem  30 MB
faults  0
1000

$ cat bigger.txt | (time rg ZQZQZQZQZQ -A9999) | wc -l

real    1.917
user    0.334
sys     0.771
maxmem  30 MB
faults  0
10000

$ cat bigger.txt | (time rg ZQZQZQZQZQ -A99999) | wc -l

real    1.972
user    0.319
sys     0.812
maxmem  30 MB
faults  0
100000

$ cat bigger.txt | (time rg ZQZQZQZQZQ -A999999) | wc -l

real    2.005
user    0.333
sys     0.855
maxmem  30 MB
faults  0
1000000
```

And compare to GNU grep:

```
$ cat bigger.txt | (time grep ZQZQZQZQZQ -A999) | wc -l

real    1.488
user    0.143
sys     0.866
maxmem  30 MB
faults  0
1000

$ cat bigger.txt | (time grep ZQZQZQZQZQ -A9999) | wc -l

real    1.697
user    0.170
sys     0.986
maxmem  30 MB
faults  1
10000

$ cat bigger.txt | (time grep ZQZQZQZQZQ -A99999) | wc -l

real    1.515
user    0.166
sys     0.856
maxmem  29 MB
faults  0
100000

$ cat bigger.txt | (time grep ZQZQZQZQZQ -A999999) | wc -l

real    1.490
user    0.174
sys     0.851
maxmem  30 MB
faults  0
1000000
```

Interestingly, GNU grep is still a bit faster. But both commands remain
roughly invariant in search time as `-A` is increased.

There is definitely something "odd" about searching `stdin`, where it
seems substantially slower. We can also observe with GNU grep:

```
$ (time grep ZQZQZQZQZQ -A999999 bigger.txt) | wc -l

real    0.692
user    0.184
sys     0.506
maxmem  30 MB
faults  0
1000000

$ cat bigger.txt | (time grep ZQZQZQZQZQ -A999999) | wc -l

real    1.700
user    0.201
sys     0.954
maxmem  30 MB
faults  0
1000000

$ (time rg ZQZQZQZQZQ -A999999 bigger.txt) | wc -l

real    0.640
user    0.428
sys     0.209
maxmem  7734 MB
faults  0
1000000

$ (time rg ZQZQZQZQZQ --no-mmap -A999999 bigger.txt) | wc -l

real    0.866
user    0.282
sys     0.581
maxmem  30 MB
faults  0
1000000

$ cat bigger.txt | (time rg ZQZQZQZQZQ -A999999) | wc -l

real    1.991
user    0.338
sys     0.819
maxmem  30 MB
faults  0
1000000
```

I wonder if this is related to my discovery in the previous commit where
`read` calls on `stdin` seem to never return anything more than ~64K. Oh
well, I'm satisfied at this point, especially given that GNU grep seems
to do a lot worse than ripgrep with bigger values of
`-B/--before-context`:

```
$ cat bigger.txt | (time grep ZQZQZQZQZQ -B9) | wc -l

real    1.568
user    0.170
sys     0.885
maxmem  30 MB
faults  0
1

$ cat bigger.txt | (time grep ZQZQZQZQZQ -B99) | wc -l

real    1.734
user    0.338
sys     0.879
maxmem  30 MB
faults  0
1

$ cat bigger.txt | (time grep ZQZQZQZQZQ -B999) | wc -l

real    2.349
user    1.723
sys     0.620
maxmem  30 MB
faults  0
1

$ cat bigger.txt | (time grep ZQZQZQZQZQ -B9999) | wc -l

real    16.459
user    15.848
sys     0.586
maxmem  30 MB
faults  0
1

$ time grep ZQZQZQZQZQ -B99999 bigger.txt
ZQZQZQZQZQ

real    1:45.06
user    1:44.12
sys     0.772
maxmem  30 MB
faults  0
```

The above pattern occurs regardless of whether you put `bigger.txt` on
stdin or whether you search it directly.

And now ripgrep:

```
$ cat bigger.txt | (time rg ZQZQZQZQZQ -B9) | wc -l

real    1.965
user    0.326
sys     0.814
maxmem  29 MB
faults  0
1

$ cat bigger.txt | (time rg ZQZQZQZQZQ -B99) | wc -l

real    1.941
user    0.423
sys     0.813
maxmem  29 MB
faults  0
1

$ cat bigger.txt | (time rg ZQZQZQZQZQ -B999) | wc -l

real    2.372
user    0.759
sys     0.703
maxmem  30 MB
faults  0
1

$ cat bigger.txt | (time rg ZQZQZQZQZQ -B9999) | wc -l

real    2.638
user    0.895
sys     0.665
maxmem  29 MB
faults  0
1

$ cat bigger.txt | (time rg ZQZQZQZQZQ -B99999) | wc -l

real    5.172
user    3.282
sys     0.748
maxmem  29 MB
faults  0
1
```

NOTE: To get `bigger.txt`:

```
$ curl -LO 'https://burntsushi.net/stuff/opensubtitles/2018/en/sixteenth.txt.gz'
$ gzip -d sixteenth.txt.gz
$ (echo ZQZQZQZQZQ && for ((i=0;i<10;i++)); do cat sixteenth.txt; done) > bigger.txt
```
---
 crates/searcher/src/searcher/core.rs | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/crates/searcher/src/searcher/core.rs b/crates/searcher/src/searcher/core.rs
index 87eaf7f4..e0693c09 100644
--- a/crates/searcher/src/searcher/core.rs
+++ b/crates/searcher/src/searcher/core.rs
@@ -191,10 +191,14 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
             // separator (when before_context==0 and after_context>0), we
             // need to know something about the position of the previous
             // line visited, even if we're at the beginning of the buffer.
+            //
+            // ... however, we only need to find the N preceding lines based
+            // on before context. We can skip this (potentially costly, for
+            // large values of N) step when before_context==0.
             let context_start = lines::preceding(
                 buf,
                 self.config.line_term.as_byte(),
-                self.config.max_context(),
+                self.config.before_context,
             );
             let consumed =
                 std::cmp::max(context_start, self.last_line_visited);