From 547c9f995041703a07bda91b52ae4cf3e62bbef1 Mon Sep 17 00:00:00 2001
From: MechaCat02 <fabian@diekaulbachs.de>
Date: Sun, 7 Jun 2026 20:51:20 +0200
Subject: [PATCH] fix(executor-core): F-P-014 thread-local LRU regex cache (128
 entries)

regex::is_match, find, find_all, replace, replace_all, split, captures
all called Regex::new(pattern) per invocation. A script doing
`regex::is_match("\\d+", x)` in a tight loop paid the compile every
iteration. Regex compile dominates is_match on short strings.

Add a thread-local LruCache<String, Arc<Regex>> (cap 128). The
compile helper now memoises by pattern string, returning Arc<Regex>
on hit. Cap is well above what any sensible script uses but bounded
enough to keep memory predictable on long-running threads.

AUDIT.md anchor: F-P-014.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---
 crates/executor-core/src/sdk/stdlib/regex.rs | 38 ++++++++++++++++----
 1 file changed, 32 insertions(+), 6 deletions(-)

diff --git a/crates/executor-core/src/sdk/stdlib/regex.rs b/crates/executor-core/src/sdk/stdlib/regex.rs
index 7ba5557..3fc87a3 100644
--- a/crates/executor-core/src/sdk/stdlib/regex.rs
+++ b/crates/executor-core/src/sdk/stdlib/regex.rs
@@ -1,13 +1,29 @@
 //! `regex::` — non-backtracking regular expressions (Rust `regex` crate).
 //!
-//! Patterns compile per call. No cache: premature for v1.1.0, and the
-//! `regex` crate's linear-time guarantees keep per-call cost bounded.
-//! Catastrophic patterns are rejected at compile time by the crate
-//! itself; no extra defense needed.
+//! F-P-014: compiled patterns are cached in a thread-local LRU so a
+//! tight script loop like `regex::is_match("\\d+", x)` doesn't recompile
+//! every iteration. Compile dominates `is_match` on short strings;
+//! caching shrinks per-call cost to a HashMap probe + `Arc::clone`.
 
+use std::cell::RefCell;
+use std::num::NonZeroUsize;
+use std::sync::Arc;
+
+use lru::LruCache;
 use regex::Regex;
 use rhai::{Array, Dynamic, Engine as RhaiEngine, EvalAltResult, Module};
 
+/// Per-thread cap on compiled regex patterns. 128 is well above what
+/// any sensible script uses but bounded enough to keep memory in
+/// check on a fleet of long-running threads.
+const REGEX_CACHE_SIZE: usize = 128;
+
+thread_local! {
+    static REGEX_CACHE: RefCell<LruCache<String, Arc<Regex>>> = RefCell::new(
+        LruCache::new(NonZeroUsize::new(REGEX_CACHE_SIZE).expect("non-zero"))
+    );
+}
+
 pub fn register(engine: &mut RhaiEngine) {
     let mut module = Module::new();
     register_is_match(&mut module);
@@ -20,8 +36,18 @@ pub fn register(engine: &mut RhaiEngine) {
     engine.register_static_module("regex", module.into());
 }
 
-fn compile(pattern: &str) -> Result<Regex, Box<EvalAltResult>> {
-    Regex::new(pattern).map_err(|e| format!("invalid regex: {e}").into())
+fn compile(pattern: &str) -> Result<Arc<Regex>, Box<EvalAltResult>> {
+    REGEX_CACHE.with(|cell| {
+        if let Some(cached) = cell.borrow_mut().get(pattern) {
+            return Ok(cached.clone());
+        }
+        let re = Arc::new(
+            Regex::new(pattern)
+                .map_err(|e| -> Box<EvalAltResult> { format!("invalid regex: {e}").into() })?,
+        );
+        cell.borrow_mut().put(pattern.to_string(), re.clone());
+        Ok(re)
+    })
 }
 
 fn register_is_match(module: &mut Module) {