From bf5b6467f8cc06759f3396ab1a8ad64fe7d1db2e Mon Sep 17 00:00:00 2001 From: Alyssa Coghlan Date: Sat, 25 May 2024 00:29:19 +1000 Subject: [PATCH] GH-119496: accept UTF-8 BOM in .pth files (GH-119503) `Out-File -Encoding utf8` and similar commands in Windows Powershell 5.1 emit UTF-8 with a BOM marker, which the regular `utf-8` codec decodes incorrectly. `utf-8-sig` accepts a BOM, but also works correctly without one. This change also makes .pth files match the way Python source files are handled. Co-authored-by: Inada Naoki --- Lib/site.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/Lib/site.py b/Lib/site.py index f1a6d9cf66f..7eace190f5a 100644 --- a/Lib/site.py +++ b/Lib/site.py @@ -185,7 +185,9 @@ def addpackage(sitedir, name, known_paths): return try: - pth_content = pth_content.decode() + # Accept BOM markers in .pth files as we do in source files + # (Windows PowerShell 5.1 makes it hard to emit UTF-8 files without a BOM) + pth_content = pth_content.decode("utf-8-sig") except UnicodeDecodeError: # Fallback to locale encoding for backward compatibility. # We will deprecate this fallback in the future.