From 412ea0b675522fd161382d5ce437e51f0505337a Mon Sep 17 00:00:00 2001 From: Jonas Devlieghere Date: Fri, 8 Aug 2025 13:57:58 -0700 Subject: [lldb] Support the Python stable C API in PythonString::AsUTF8 (#152599) This conditionally reimplements PythonString::AsUTF8 using PyUnicode_AsUTF8String instead of PyUnicode_AsUTF8AndSize. PyUnicode_AsUTF8AndSize caches the UTF-8 representation of the string in the Unicode object, which makes it more efficient and ties the lifetime of the data to the Python string. However, it was only added to the Stable API in Python 3.10. Older versions that want to use the Stable API must use PyUnicode_AsUTF8String in combination with ConstString. --- .../ScriptInterpreter/Python/PythonDataObjects.cpp | 28 ++++++++++++++++++---- 1 file changed, 23 insertions(+), 5 deletions(-) (limited to 'lldb/source/Plugins/ScriptInterpreter/Python/PythonDataObjects.cpp') diff --git a/lldb/source/Plugins/ScriptInterpreter/Python/PythonDataObjects.cpp b/lldb/source/Plugins/ScriptInterpreter/Python/PythonDataObjects.cpp index 27ac5432..a2a287a 100644 --- a/lldb/source/Plugins/ScriptInterpreter/Python/PythonDataObjects.cpp +++ b/lldb/source/Plugins/ScriptInterpreter/Python/PythonDataObjects.cpp @@ -405,15 +405,33 @@ Expected PythonString::AsUTF8() const { if (!IsValid()) return nullDeref(); - Py_ssize_t size; - const char *data; + // PyUnicode_AsUTF8AndSize caches the UTF-8 representation of the string in + // the Unicode object, which makes it more efficient and ties the lifetime of + // the data to the Python string. However, it was only added to the Stable API + // in Python 3.10. Older versions that want to use the Stable API must use + // PyUnicode_AsUTF8String in combination with ConstString. +#if defined(Py_LIMITED_API) && (Py_LIMITED_API < 0x030a0000) + PyObject *py_bytes = PyUnicode_AsUTF8String(m_py_obj); + if (!py_bytes) + return exception(); + auto release_py_str = + llvm::make_scope_exit([py_bytes] { Py_DECREF(py_bytes); }); + Py_ssize_t size = PyBytes_Size(py_bytes); + const char *str = PyBytes_AsString(py_bytes); + + if (!str) + return exception(); - data = PyUnicode_AsUTF8AndSize(m_py_obj, &size); + return ConstString(str, size).GetStringRef(); +#else + Py_ssize_t size; + const char *str = PyUnicode_AsUTF8AndSize(m_py_obj, &size); - if (!data) + if (!str) return exception(); - return llvm::StringRef(data, size); + return llvm::StringRef(str, size); +#endif } size_t PythonString::GetSize() const { -- cgit v1.1