From 14e3f9a1b2711336ca2e68235eb53bf1b49880c5 Mon Sep 17 00:00:00 2001
From: Ronen Schaffer <ronen.schaffer@ibm.com>
Date: Sat, 16 Mar 2024 06:01:30 +0200
Subject: [PATCH] Replace `lstrip()` with `removeprefix()` to fix Ruff linter
 warning (#2958)

---
 benchmarks/backend_request_func.py | 15 +++++++++++----
 pyproject.toml                     |  2 --
 2 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/benchmarks/backend_request_func.py b/benchmarks/backend_request_func.py
index d7cac22ce7..51fb8d9e81 100644
--- a/benchmarks/backend_request_func.py
+++ b/benchmarks/backend_request_func.py
@@ -64,7 +64,7 @@ async def async_request_tgi(
                             output.ttft = ttft
                     output.latency = time.perf_counter() - st
 
-                    body = data.decode("utf-8").lstrip("data:")
+                    body = remove_prefix(data.decode("utf-8"), "data:")
                     output.generated_text = json.loads(body)["generated_text"]
                     output.success = True
                 else:
@@ -158,7 +158,7 @@ async def async_request_trt_llm(
                             output.ttft = ttft
                     output.latency = time.perf_counter() - st
 
-                    body = data.decode("utf-8").lstrip("data:")
+                    body = remove_prefix(data.decode("utf-8"), "data:")
                     output.generated_text = json.loads(body)["text_output"]
                     output.success = True
 
@@ -255,7 +255,7 @@ async def async_request_openai_completions(
                         if not chunk:
                             continue
 
-                        chunk = chunk.decode("utf-8").lstrip("data: ")
+                        chunk = remove_prefix(chunk.decode("utf-8"), "data: ")
                         if chunk == "[DONE]":
                             latency = time.perf_counter() - st
                         else:
@@ -322,7 +322,7 @@ async def async_request_openai_chat_completions(
                         if not chunk:
                             continue
 
-                        chunk = chunk.decode("utf-8").lstrip("data: ")
+                        chunk = remove_prefix(chunk.decode("utf-8"), "data: ")
                         if chunk == "[DONE]":
                             latency = time.perf_counter() - st
                         else:
@@ -344,6 +344,13 @@ async def async_request_openai_chat_completions(
     return output
 
 
+# Since vllm must support Python 3.8, we can't use str.removeprefix(prefix) introduced in Python 3.9
+def remove_prefix(text: str, prefix: str) -> str:
+    if text.startswith(prefix):
+        return text[len(prefix):]
+    return text
+
+
 ASYNC_REQUEST_FUNCS = {
     "tgi": async_request_tgi,
     "vllm": async_request_vllm,
diff --git a/pyproject.toml b/pyproject.toml
index d6fa5d7a03..e0a01215ef 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -33,8 +33,6 @@ ignore = [
     "F405", "F403",
     # lambda expression assignment
     "E731",
-    # .strip() with multi-character strings
-    "B005",
     # Loop control variable not used within loop body
     "B007",
 ]