From 4d5ad03e1fd09b8be26843f7cb165051ab9a9c05 Mon Sep 17 00:00:00 2001
From: Jeremy Maitin-Shepard <jbms@google.com>
Date: Thu, 9 Sep 2021 12:56:10 -0700
Subject: [PATCH] Avoid use of temporary `bytes` object in string_caster for
 UTF-8 (#3257)

Fixes #3252
---
 include/pybind11/cast.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/include/pybind11/cast.h b/include/pybind11/cast.h
index db79f57cda..3e621eba7d 100644
--- a/include/pybind11/cast.h
+++ b/include/pybind11/cast.h
@@ -377,6 +377,22 @@ template <typename StringType, bool IsView = false> struct string_caster {
 #endif
         }
 
+#if PY_VERSION_HEX >= 0x03030000
+        // On Python >= 3.3, for UTF-8 we avoid the need for a temporary `bytes`
+        // object by using `PyUnicode_AsUTF8AndSize`.
+        if (PYBIND11_SILENCE_MSVC_C4127(UTF_N == 8)) {
+            Py_ssize_t size = -1;
+            const auto *buffer
+                = reinterpret_cast<const CharT *>(PyUnicode_AsUTF8AndSize(load_src.ptr(), &size));
+            if (!buffer) {
+                PyErr_Clear();
+                return false;
+            }
+            value = StringType(buffer, static_cast<size_t>(size));
+            return true;
+        }
+#endif
+
         auto utfNbytes = reinterpret_steal<object>(PyUnicode_AsEncodedString(
             load_src.ptr(), UTF_N == 8 ? "utf-8" : UTF_N == 16 ? "utf-16" : "utf-32", nullptr));
         if (!utfNbytes) { PyErr_Clear(); return false; }