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/platform/runtime.rs | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'crates/shirabe/src/platform/runtime.rs')

diff --git a/crates/shirabe/src/platform/runtime.rs b/crates/shirabe/src/platform/runtime.rs
index 40297907..28cfa095 100644
--- a/crates/shirabe/src/platform/runtime.rs
+++ b/crates/shirabe/src/platform/runtime.rs
@@ -4,7 +4,7 @@ use indexmap::IndexMap;
 use shirabe_external_packages::composer::pcre::{CaptureKey, Preg};
 use shirabe_php_shim::{
     PhpMixed, class_exists, function_exists, html_entity_decode, implode, instantiate_class, ltrim,
-    strip_tags, trim,
+    php_regex, strip_tags, trim,
 };
 
 /// Seam over the PHP runtime so PlatformRepository can be tested against mocked
@@ -96,7 +96,7 @@ impl Runtime {
 
         let mut matches: IndexMap<CaptureKey, String> = IndexMap::new();
         if Preg::match3(
-            r"~<h2>\s*<a[^>]*>([^<]+)</a>\s*</h2>~i",
+            php_regex!(r"~<h2>\s*<a[^>]*>([^<]+)</a>\s*</h2>~i"),
             html,
             Some(&mut matches),
         ) {
@@ -114,7 +114,9 @@ impl Runtime {
 
         let mut matches: IndexMap<CaptureKey, Vec<String>> = IndexMap::new();
         if Preg::match_all3(
-            r#"~<tr>\s*<td class="e">\s*(.*?)\s*</td>\s*<td class="v">\s*(.*?)\s*</td>\s*</tr>~is"#,
+            php_regex!(
+                r#"~<tr>\s*<td class="e">\s*(.*?)\s*</td>\s*<td class="v">\s*(.*?)\s*</td>\s*</tr>~is"#
+            ),
             html,
             Some(&mut matches),
         ) > 0
-- 
cgit v1.3.1