From 91692846909ed191addb7ec1c34aad11392ab88b Mon Sep 17 00:00:00 2001
From: nsfisis <nsfisis@gmail.com>
Date: Sat, 18 Jul 2026 15:03:55 +0900
Subject: perf(regex): eliminate per-call clone overhead in preg_* dispatch

regex::Regex::clone() does not share the underlying meta engine's
search-cache pool, so every fresh clone pays a ~10us warmup cost on
its first use. Two changes together eliminate this across nearly all
preg_* call sites:

- A php_regex! macro resolves PHP-style patterns to a per-call-site
  &'static regex::Regex (via regex-macro's LazyLock), applied at the
  majority of call sites throughout the codebase.
- Call sites still passing dynamic pattern strings go through
  PATTERN_CACHE, which now stores Arc<(Regex, bool)> and hands out
  Arc::clone()s instead of cloning the Regex itself.

PregPattern::resolve() returns a ResolvedPattern enum (Arc or
'static reference) rather than an owned Regex, so neither path ever
clones the Regex proper.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
---
 crates/shirabe/src/util/hg.rs | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'crates/shirabe/src/util/hg.rs')

diff --git a/crates/shirabe/src/util/hg.rs b/crates/shirabe/src/util/hg.rs
index 56e5044f..9f5ea3b5 100644
--- a/crates/shirabe/src/util/hg.rs
+++ b/crates/shirabe/src/util/hg.rs
@@ -6,7 +6,7 @@ use crate::io::IOInterfaceImmutable;
 use crate::util::ProcessExecutor;
 use crate::util::Url;
 use shirabe_external_packages::composer::pcre::Preg;
-use shirabe_php_shim::rawurlencode;
+use shirabe_php_shim::{php_regex, rawurlencode};
 use std::sync::OnceLock;
 
 static VERSION: OnceLock<Option<String>> = OnceLock::new();
@@ -58,7 +58,9 @@ impl Hg {
         // Try with the authentication information available
         let mut matches: indexmap::IndexMap<String, String> = indexmap::IndexMap::new();
         let matched = Preg::is_match_named(
-            r"{^(?P<proto>ssh|https?)://(?:(?P<user>[^:@]+)(?::(?P<pass>[^:@]+))?@)?(?P<host>[^/]+)(?P<path>/.*)?}mi",
+            php_regex!(
+                r"{^(?P<proto>ssh|https?)://(?:(?P<user>[^:@]+)(?::(?P<pass>[^:@]+))?@)?(?P<host>[^/]+)(?P<path>/.*)?}mi"
+            ),
             &url,
             &mut matches,
         );
@@ -152,7 +154,7 @@ impl Hg {
                     None,
                 ) == 0
                     && let Some(matches) = Preg::is_match_with_indexed_captures(
-                        r"/^.+? (\d+(?:\.\d+)+)(?:\+.*?)?\)?\r?\n/",
+                        php_regex!(r"/^.+? (\d+(?:\.\d+)+)(?:\+.*?)?\)?\r?\n/"),
                         &output,
                     )
                 {
-- 
cgit v1.3.1