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/http/curl_downloader.rs | 10 +++++-----
 crates/shirabe/src/util/http/response.rs        |  4 ++--
 2 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'crates/shirabe/src/util/http')

diff --git a/crates/shirabe/src/util/http/curl_downloader.rs b/crates/shirabe/src/util/http/curl_downloader.rs
index 47260a85..508aa56e 100644
--- a/crates/shirabe/src/util/http/curl_downloader.rs
+++ b/crates/shirabe/src/util/http/curl_downloader.rs
@@ -33,7 +33,7 @@ use crate::util::{AuthHelper, PromptAuthResult, StoreAuth};
 use indexmap::IndexMap;
 use shirabe_external_packages::composer::pcre::Preg;
 use shirabe_php_shim::{
-    PhpMixed, in_array, parse_url, preg_quote, rename, strpos, substr, unlink_silent,
+    PhpMixed, in_array, parse_url, php_regex, preg_quote, rename, strpos, substr, unlink_silent,
 };
 use std::sync::atomic::{AtomicBool, Ordering};
 
@@ -150,7 +150,7 @@ impl CurlDownloader {
 
         // check URL can be accessed (i.e. is not insecure), but allow insecure Packagist calls to
         // $hashed providers as file integrity is verified with sha256
-        if !Preg::is_match(r"{^http://(repo\.)?packagist\.org/p/}", url)
+        if !Preg::is_match(php_regex!(r"{^http://(repo\.)?packagist\.org/p/}"), url)
             || (strpos(url, "$").is_none() && strpos(url, "%24").is_none())
         {
             self.config.borrow_mut().prohibit_url_by_config(
@@ -659,7 +659,7 @@ impl CurlDownloader {
                 let url_host = parse_url(url, shirabe_php_shim::PHP_URL_HOST);
                 let url_host_str = url_host.as_string().unwrap_or("");
                 target_url = Preg::replace(
-                    &format!(
+                    format!(
                         r"{{^(.+(?://|@){}(?::\d+)?)(?:[/\?].*)?$}}",
                         preg_quote(url_host_str, None)
                     ),
@@ -669,7 +669,7 @@ impl CurlDownloader {
             } else {
                 // Relative path; e.g. foo
                 target_url = Preg::replace(
-                    r"{^(.+/)[^/?]*(?:\?.*)?$}",
+                    php_regex!(r"{^(.+/)[^/?]*(?:\?.*)?$}"),
                     &format!("\\1{}", location_header),
                     url,
                 );
@@ -754,7 +754,7 @@ impl CurlDownloader {
             && (location_header.is_none()
                 || substr(location_header.as_deref().unwrap_or(""), -4, None) != ".zip")
             && Preg::is_match(
-                r"{^text/html\b}i",
+                php_regex!(r"{^text/html\b}i"),
                 &response
                     .inner
                     .get_header("content-type")
diff --git a/crates/shirabe/src/util/http/response.rs b/crates/shirabe/src/util/http/response.rs
index 5398fe25..3ee538d5 100644
--- a/crates/shirabe/src/util/http/response.rs
+++ b/crates/shirabe/src/util/http/response.rs
@@ -2,7 +2,7 @@
 
 use crate::json::JsonFile;
 use shirabe_external_packages::composer::pcre::Preg;
-use shirabe_php_shim::{PhpMixed, preg_quote};
+use shirabe_php_shim::{PhpMixed, php_regex, preg_quote};
 
 #[derive(Debug)]
 pub struct Response {
@@ -29,7 +29,7 @@ impl Response {
     pub fn get_status_message(&self) -> Option<String> {
         let mut value = None;
         for header in &self.headers {
-            if Preg::is_match(r"{^HTTP/\S+ \d+}i", header) {
+            if Preg::is_match(php_regex!(r"{^HTTP/\S+ \d+}i"), header) {
                 // In case of redirects, headers contain the headers of all responses
                 // so we can not return directly and need to keep iterating
                 value = Some(header.clone());
-- 
cgit v1.3.1