From 48bf39458511b38f185a24d52dfef61e0a8796ae Mon Sep 17 00:00:00 2001
From: Andrew Gallant <jamslam@gmail.com>
Date: Sun, 17 Aug 2025 10:44:02 -0400
Subject: [PATCH] stats: fix case where "bytes searched" could be wrong

Specifically, if the search was instructed to quit early, we might not
have correctly marked the number of bytes consumed.

I don't think this bug occurs when memory maps are used to read the
haystack.

Closes #2944
---
 CHANGELOG.md                         |  2 ++
 crates/searcher/src/searcher/glue.rs | 11 ++++++++++-
 tests/regression.rs                  |  7 +++++++
 3 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 5aff37e7..e0159bb0 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -21,6 +21,8 @@ Bug fixes:
   Make `rg -vf file` where `file` is empty match everything.
 * [BUG #2177](https://github.com/BurntSushi/ripgrep/issues/2177):
   Ignore a UTF-8 BOM marker at the start of `.gitignore` (and similar files).
+* [BUG #2944](https://github.com/BurntSushi/ripgrep/pull/2944):
+  Fix a bug where the "bytes searched" in `--stats` output could be incorrect.
 
 Feature enhancements:
 
diff --git a/crates/searcher/src/searcher/glue.rs b/crates/searcher/src/searcher/glue.rs
index 006afad3..5db57019 100644
--- a/crates/searcher/src/searcher/glue.rs
+++ b/crates/searcher/src/searcher/glue.rs
@@ -37,7 +37,11 @@ where
 
     pub(crate) fn run(mut self) -> Result<(), S::Error> {
         if self.core.begin()? {
-            while self.fill()? && self.core.match_by_line(self.rdr.buffer())? {
+            while self.fill()? {
+                if !self.core.match_by_line(self.rdr.buffer())? {
+                    self.consume_remaining();
+                    break;
+                }
             }
         }
         self.core.finish(
@@ -46,6 +50,11 @@ where
         )
     }
 
+    fn consume_remaining(&mut self) {
+        let consumed = self.core.pos();
+        self.rdr.consume(consumed);
+    }
+
     fn fill(&mut self) -> Result<bool, S::Error> {
         assert!(self.rdr.buffer()[self.core.pos()..].is_empty());
 
diff --git a/tests/regression.rs b/tests/regression.rs
index bd845905..4fd3c0f8 100644
--- a/tests/regression.rs
+++ b/tests/regression.rs
@@ -1454,3 +1454,10 @@ rgtest!(r2658_null_data_line_regexp, |dir: Dir, mut cmd: TestCommand| {
     let got = cmd.args(&["--null-data", "--line-regexp", r"bar"]).stdout();
     eqnice!("haystack:bar\0", got);
 });
+
+// See: https://github.com/BurntSushi/ripgrep/pull/2944
+rgtest!(r2944_incorrect_bytes_searched, |dir: Dir, mut cmd: TestCommand| {
+    dir.create("haystack", "foo1\nfoo2\nfoo3\nfoo4\nfoo5\n");
+    let got = cmd.args(&["--stats", "-m2", "foo", "."]).stdout();
+    assert!(got.contains("10 bytes searched\n"));
+});