https://github.com/c8ef created https://github.com/llvm/llvm-project/pull/121341
This will prevent the error on systems with a default encoding other than utf-8.
```
UnicodeDecodeError: 'gbk' codec can't decode byte 0xb6 in position 12958:
illegal multibyte sequence
```
>From 33db3086f1f822aa1f4bbacb028d5fa31cb3e3be Mon Sep 17 00:00:00 2001
From: c8ef <c...@outlook.com>
Date: Mon, 30 Dec 2024 22:27:26 +0800
Subject: [PATCH] open with utf-8
---
clang/tools/include-mapping/cppreference_parser.py | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/clang/tools/include-mapping/cppreference_parser.py
b/clang/tools/include-mapping/cppreference_parser.py
index 9101f3dbff0f94..f7da2ba8bb6d84 100644
--- a/clang/tools/include-mapping/cppreference_parser.py
+++ b/clang/tools/include-mapping/cppreference_parser.py
@@ -139,7 +139,7 @@ def _ParseIndexPage(index_page_html):
def _ReadSymbolPage(path, name, qual_name):
- with open(path) as f:
+ with open(path, encoding="utf-8") as f:
return _ParseSymbolPage(f.read(), name, qual_name)
@@ -156,7 +156,7 @@ def _GetSymbols(pool, root_dir, index_page_name, namespace,
variants_to_accept):
# contains the defined header.
# 2. Parse the symbol page to get the defined header.
index_page_path = os.path.join(root_dir, index_page_name)
- with open(index_page_path, "r") as f:
+ with open(index_page_path, "r", encoding="utf-8") as f:
# Read each symbol page in parallel.
results = [] # (symbol_name, promise of [header...])
for symbol_name, symbol_page_path, variant in
_ParseIndexPage(f.read()):
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
