From 69529ad0ccbe2fb68427de92763d7a5322b63d31 Mon Sep 17 00:00:00 2001 From: Guido van Rossum Date: Thu, 4 May 2000 15:55:17 +0000 Subject: When the UTF-8 conversion to Unicode fails, return an 8-bit string instead. This seems more robust than returning an Unicode string with some unconverted charcters in it. This still doesn't support getting truly binary data out of Tcl, since we look for the trailing null byte; but the old (pre-Unicode) code did this too, so apparently there's no need. (Plus, I really don't feel like finding out how Tcl deals with this in each version.) --- Modules/_tkinter.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/Modules/_tkinter.c b/Modules/_tkinter.c index 882715f..6c3beef 100644 --- a/Modules/_tkinter.c +++ b/Modules/_tkinter.c @@ -654,7 +654,11 @@ Tkapp_Call(self, args) else { /* Convert UTF-8 to Unicode string */ p = strchr(p, '\0'); - res = PyUnicode_DecodeUTF8(s, (int)(p-s), "ignore"); + res = PyUnicode_DecodeUTF8(s, (int)(p-s), "strict"); + if (res == NULL) { + PyErr_Clear(); + res = PyString_FromStringAndSize(s, (int)(p-s)); + } } } -- cgit v0.12