From 6cdb99ea61d585cc32716d181517d71b4df769b5 Mon Sep 17 00:00:00 2001
From: Andrew Gallant <jamslam@gmail.com>
Date: Sat, 2 Sep 2023 12:25:34 -0400
Subject: [PATCH] deps: drop bytecount in favor of memchr_iter(..).count()

As of the memchr 2.6 release, its Iterator::count method is specialized
to only count the number of occurrences instead of finding the offset of
each occurrence. This replaces ripgrep's use of the bytecount crate.
While micro-benchmarks suggest that memchr's method has better
throughput than bytecount, it turned out to be an illusion. Namely, on a
~13GB haystack prior to this change:

    $ time rg-bytecount 'You killed my friend, my best friend, my lifelong friend!' OpenSubtitles2018.raw.en --line-number
    441450441:- You killed my friend, my best friend, my lifelong friend!

    real    1.473
    user    1.186
    sys     0.286
    maxmem  12512 MB
    faults  0

And then after:

    $ time rg 'You killed my friend, my best friend, my lifelong friend!' OpenSubtitles2018.raw.en --line-number
    441450441:- You killed my friend, my best friend, my lifelong friend!

    real    1.532
    user    1.280
    sys     0.250
    maxmem  12512 MB
    faults  0

But perf is just about in the same ballpark. That's good enough for me
at the moment in order to drop the extra dependency.

I did this because the marginal cost of adding the Iterator::count()
specialization to memchr was extremely small.
---
 Cargo.lock                   | 8 +-------
 crates/searcher/Cargo.toml   | 5 ++---
 crates/searcher/src/lines.rs | 3 +--
 3 files changed, 4 insertions(+), 12 deletions(-)

diff --git a/Cargo.lock b/Cargo.lock
index 50b377c3..fa1ea97e 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -40,12 +40,6 @@ dependencies = [
  "serde",
 ]
 
-[[package]]
-name = "bytecount"
-version = "0.6.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2c676a478f63e9fa2dd5368a42f28bba0d6c560b775f38583c8bbaa7fcd67c9c"
-
 [[package]]
 name = "cc"
 version = "1.0.83"
@@ -215,12 +209,12 @@ name = "grep-searcher"
 version = "0.1.11"
 dependencies = [
  "bstr",
- "bytecount",
  "encoding_rs",
  "encoding_rs_io",
  "grep-matcher",
  "grep-regex",
  "log",
+ "memchr",
  "memmap2",
  "regex",
 ]
diff --git a/crates/searcher/Cargo.toml b/crates/searcher/Cargo.toml
index 68864cee..579d1370 100644
--- a/crates/searcher/Cargo.toml
+++ b/crates/searcher/Cargo.toml
@@ -15,19 +15,18 @@ edition = "2018"
 
 [dependencies]
 bstr = { version = "1.6.0", default-features = false, features = ["std"] }
-bytecount = "0.6"
 encoding_rs = "0.8.14"
 encoding_rs_io = "0.1.6"
 grep-matcher = { version = "0.1.6", path = "../matcher" }
 log = "0.4.5"
+memchr = "2.6.2"
 memmap = { package = "memmap2", version = "0.5.3" }
 
 [dev-dependencies]
 grep-regex = { version = "0.1.11", path = "../regex" }
-regex = "1.1"
+regex = "1.9.5"
 
 [features]
-default = ["bytecount/runtime-dispatch-simd"]
 simd-accel = ["encoding_rs/simd-accel"]
 
 # This feature is DEPRECATED. Runtime dispatch is used for SIMD now.
diff --git a/crates/searcher/src/lines.rs b/crates/searcher/src/lines.rs
index 387a1b46..5e47c9b3 100644
--- a/crates/searcher/src/lines.rs
+++ b/crates/searcher/src/lines.rs
@@ -3,7 +3,6 @@ A collection of routines for performing operations on lines.
 */
 
 use bstr::ByteSlice;
-use bytecount;
 use grep_matcher::{LineTerminator, Match};
 
 /// An iterator over lines in a particular slice of bytes.
@@ -110,7 +109,7 @@ impl LineStep {
 
 /// Count the number of occurrences of `line_term` in `bytes`.
 pub fn count(bytes: &[u8], line_term: u8) -> u64 {
-    bytecount::count(bytes, line_term) as u64
+    memchr::memchr_iter(line_term, bytes).count() as u64
 }
 
 /// Given a line that possibly ends with a terminator, return that line without