From 0612e3f17dd61d10f7c9f81096210991b5ee79bb Mon Sep 17 00:00:00 2001
From: Rong Ma <rongma1997@gmail.com>
Date: Fri, 24 Jan 2025 10:33:28 +0000
Subject: [PATCH] Add build option for skipping simdjson utf8 validation

---
 CMake/resolve_dependency_modules/simdjson.cmake | 4 ++++
 CMakeLists.txt                                  | 2 ++
 2 files changed, 6 insertions(+)

diff --git a/CMake/resolve_dependency_modules/simdjson.cmake b/CMake/resolve_dependency_modules/simdjson.cmake
index ddd232050961..a0c55c3758a3 100644
--- a/CMake/resolve_dependency_modules/simdjson.cmake
+++ b/CMake/resolve_dependency_modules/simdjson.cmake
@@ -29,4 +29,8 @@ FetchContent_Declare(
   URL ${VELOX_SIMDJSON_SOURCE_URL}
   URL_HASH ${VELOX_SIMDJSON_BUILD_SHA256_CHECKSUM})
 
+if(${VELOX_SIMDJSON_SKIPUTF8VALIDATION})
+  set(SIMDJSON_SKIPUTF8VALIDATION ON)
+endif()
+
 FetchContent_MakeAvailable(simdjson)
diff --git a/CMakeLists.txt b/CMakeLists.txt
index f8d9508c175e..339d1ed0dda2 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -149,6 +149,8 @@ option(
   VELOX_ENABLE_INT64_BUILD_PARTITION_BOUND
   "make buildPartitionBounds_ a vector int64 instead of int32 to avoid integer overflow when the hashtable has billions of records"
   OFF)
+option(VELOX_SIMDJSON_SKIPUTF8VALIDATION
+       "Skip simdjson utf8 validation in JSON parsing" OFF)
 
 # Explicitly force compilers to generate colored output. Compilers usually do
 # this by default if they detect the output is a terminal, but this assumption