From 2412853f8e65f7c4359ebf59902ad2553589b908 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Martin=20v=2E=20L=C3=B6wis?= Date: Mon, 9 Sep 2002 06:17:05 +0000 Subject: Fix escaping of non-ASCII characters. --- Lib/test/test_pep263.py | 1 + Objects/stringobject.c | 6 ++++-- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/Lib/test/test_pep263.py b/Lib/test/test_pep263.py index b1ffc03..7cc5526 100644 --- a/Lib/test/test_pep263.py +++ b/Lib/test/test_pep263.py @@ -1,2 +1,3 @@ #! -*- coding: koi8-r -*- assert u"ðÉÔÏÎ".encode("utf-8") == '\xd0\x9f\xd0\xb8\xd1\x82\xd0\xbe\xd0\xbd' +assert u"\ð".encode("utf-8") == '\\\xd0\x9f' diff --git a/Objects/stringobject.c b/Objects/stringobject.c index dd38ee3..c090e9b 100644 --- a/Objects/stringobject.c +++ b/Objects/stringobject.c @@ -541,6 +541,7 @@ PyObject *PyString_DecodeEscape(const char *s, end = s + len; while (s < end) { if (*s != '\\') { + non_esc: #ifdef Py_USING_UNICODE if (recode_encoding && (*s & 0x80)) { PyObject *u, *w; @@ -656,8 +657,9 @@ PyObject *PyString_DecodeEscape(const char *s, #endif default: *p++ = '\\'; - *p++ = s[-1]; - break; + s--; + goto non_esc; /* an arbitry number of unescaped + UTF-8 bytes may follow. */ } } if (p-buf < newlen) -- cgit v0.12