From d586ccb04f79863c819b212ec5b9d873964078e4 Mon Sep 17 00:00:00 2001 From: Serhiy Storchaka Date: Sat, 12 Jan 2019 10:30:35 +0200 Subject: [PATCH] bpo-35552: Fix reading past the end in PyUnicode_FromFormat() and PyBytes_FromFormat(). (GH-11276) Format characters "%s" and "%V" in PyUnicode_FromFormat() and "%s" in PyBytes_FromFormat() no longer read memory past the limit if precision is specified. --- .../2018-12-21-13-29-30.bpo-35552.1DzQQc.rst | 3 +++ Objects/bytesobject.c | 12 +++++++++--- Objects/unicodeobject.c | 12 +++++++++--- 3 files changed, 21 insertions(+), 6 deletions(-) create mode 100644 Misc/NEWS.d/next/Core and Builtins/2018-12-21-13-29-30.bpo-35552.1DzQQc.rst diff --git a/Misc/NEWS.d/next/Core and Builtins/2018-12-21-13-29-30.bpo-35552.1DzQQc.rst b/Misc/NEWS.d/next/Core and Builtins/2018-12-21-13-29-30.bpo-35552.1DzQQc.rst new file mode 100644 index 00000000000..dbc00bcd75e --- /dev/null +++ b/Misc/NEWS.d/next/Core and Builtins/2018-12-21-13-29-30.bpo-35552.1DzQQc.rst @@ -0,0 +1,3 @@ +Format characters ``%s`` and ``%V`` in :c:func:`PyUnicode_FromFormat` and +``%s`` in :c:func:`PyBytes_FromFormat` no longer read memory past the +limit if *precision* is specified. diff --git a/Objects/bytesobject.c b/Objects/bytesobject.c index 40ef47144e5..b299d487170 100644 --- a/Objects/bytesobject.c +++ b/Objects/bytesobject.c @@ -312,9 +312,15 @@ PyBytes_FromFormatV(const char *format, va_list vargs) Py_ssize_t i; p = va_arg(vargs, const char*); - i = strlen(p); - if (prec > 0 && i > prec) - i = prec; + if (prec <= 0) { + i = strlen(p); + } + else { + i = 0; + while (i < prec && p[i]) { + i++; + } + } s = _PyBytesWriter_WriteBytes(&writer, s, p, i); if (s == NULL) goto error; diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c index 304ea7471f4..f1d23b66fa1 100644 --- a/Objects/unicodeobject.c +++ b/Objects/unicodeobject.c @@ -2578,9 +2578,15 @@ unicode_fromformat_write_cstr(_PyUnicodeWriter *writer, const char *str, PyObject *unicode; int res; - length = strlen(str); - if (precision != -1) - length = Py_MIN(length, precision); + if (precision == -1) { + length = strlen(str); + } + else { + length = 0; + while (length < precision && str[length]) { + length++; + } + } unicode = PyUnicode_DecodeUTF8Stateful(str, length, "replace", NULL); if (unicode == NULL) return -1;