From d70cca07d290157ae5133036cb7bd70536e76726 Mon Sep 17 00:00:00 2001
From: "google-labs-jules[bot]"
 <161369871+google-labs-jules[bot]@users.noreply.github.com>
Date: Fri, 1 May 2026 16:11:15 +0000
Subject: [PATCH] =?UTF-8?q?=E2=9A=A1=20Optimize=20regex=20performance=20by?=
 =?UTF-8?q?=20pre-compiling=20patterns=20in=20src/domain=5Ffronter.py?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Moved repeated regex compilations to module-level constants to improve
efficiency. This provides a measurable speedup in status line and header
parsing.

Patterns optimized:
- RE_CONTENT_RANGE
- RE_JSON_EXTRACT
- RE_STATUS_CODE
- RE_COOKIE_SPLIT

Co-authored-by: maattyi <228237318+maattyi@users.noreply.github.com>
---
 src/domain_fronter.py | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/src/domain_fronter.py b/src/domain_fronter.py
index a623cab..44c981c 100644
--- a/src/domain_fronter.py
+++ b/src/domain_fronter.py
@@ -30,6 +30,12 @@
 
 from ws import ws_encode, ws_decode
 
+# Pre-compiled regex patterns for performance
+RE_CONTENT_RANGE = re.compile(r"/(\d+)")
+RE_JSON_EXTRACT = re.compile(r"\{.*\}", re.DOTALL)
+RE_STATUS_CODE = re.compile(r"\d{3}")
+RE_COOKIE_SPLIT = re.compile(r",\s*(?=[A-Za-z0-9!#$%&'*+\-.^_`|~]+=)")
+
 log = logging.getLogger("Fronter")
 
 
@@ -590,7 +596,7 @@ async def relay_parallel(self, method: str, url: str,
 
         # Parse total size from Content-Range: "bytes 0-262143/1048576"
         content_range = resp_hdrs.get("content-range", "")
-        m = re.search(r"/(\d+)", content_range)
+        m = RE_CONTENT_RANGE.search(content_range)
         if not m:
             # Can't parse — downgrade to 200 so the client (which sent a
             # plain GET) doesn't get confused by 206 + Content-Range.
@@ -1012,7 +1018,7 @@ def _parse_batch_body(self, resp_body: bytes,
         try:
             data = json.loads(text)
         except json.JSONDecodeError:
-            m = re.search(r'\{.*\}', text, re.DOTALL)
+            m = RE_JSON_EXTRACT.search(text)
             data = json.loads(m.group()) if m else None
         if not data:
             raise RuntimeError(f"Bad batch response: {text[:200]}")
@@ -1049,7 +1055,7 @@ async def _read_http_response(self, reader: asyncio.StreamReader):
         lines = header_section.split(b"\r\n")
 
         status_line = lines[0].decode(errors="replace")
-        m = re.search(r"\d{3}", status_line)
+        m = RE_STATUS_CODE.search(status_line)
         status = int(m.group()) if m else 0
 
         headers = {}
@@ -1139,7 +1145,7 @@ def _parse_relay_response(self, body: bytes) -> bytes:
         try:
             data = json.loads(text)
         except json.JSONDecodeError:
-            m = re.search(r'\{.*\}', text, re.DOTALL)
+            m = RE_JSON_EXTRACT.search(text)
             if m:
                 try:
                     data = json.loads(m.group())
@@ -1201,7 +1207,7 @@ def _split_set_cookie(blob: str) -> list[str]:
             return []
         # Split on ", " but only when the following text looks like the start
         # of a new cookie (a token followed by '=').
-        parts = re.split(r",\s*(?=[A-Za-z0-9!#$%&'*+\-.^_`|~]+=)", blob)
+        parts = RE_COOKIE_SPLIT.split(blob)
         return [p.strip() for p in parts if p.strip()]
 
     def _split_raw_response(self, raw: bytes):
@@ -1210,7 +1216,7 @@ def _split_raw_response(self, raw: bytes):
             return 0, {}, raw
         header_section, body = raw.split(b"\r\n\r\n", 1)
         lines = header_section.split(b"\r\n")
-        m = re.search(r"\d{3}", lines[0].decode(errors="replace"))
+        m = RE_STATUS_CODE.search(lines[0].decode(errors="replace"))
         status = int(m.group()) if m else 0
         headers = {}
         for line in lines[1:]: