From 3fd4ab356d76b048f2dbd25797fec87f68dd7f73 Mon Sep 17 00:00:00 2001 From: Serhiy Storchaka Date: Thu, 7 Feb 2013 16:23:21 +0200 Subject: Issue #17043: The unicode-internal decoder no longer read past the end of input buffer. --- Misc/NEWS | 3 +++ Objects/unicodeobject.c | 51 +++++++++++++++++++++++-------------------------- 2 files changed, 27 insertions(+), 27 deletions(-) diff --git a/Misc/NEWS b/Misc/NEWS index 83f52af..c715170 100644 --- a/Misc/NEWS +++ b/Misc/NEWS @@ -10,6 +10,9 @@ What's New in Python 3.2.4 Core and Builtins ----------------- +- Issue #17043: The unicode-internal decoder no longer read past the end of + input buffer. + - Issue #16979: Fix error handling bugs in the unicode-escape-decode decoder. - Issue #10156: In the interpreter's initialization phase, unicode globals diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c index 3a288d8..cd4e9e9 100644 --- a/Objects/unicodeobject.c +++ b/Objects/unicodeobject.c @@ -4392,37 +4392,34 @@ PyObject *_PyUnicode_DecodeUnicodeInternal(const char *s, end = s + size; while (s < end) { + if (end-s < Py_UNICODE_SIZE) { + endinpos = end-starts; + reason = "truncated input"; + goto error; + } memcpy(p, s, sizeof(Py_UNICODE)); +#ifdef Py_UNICODE_WIDE /* We have to sanity check the raw data, otherwise doom looms for some malformed UCS-4 data. */ - if ( -#ifdef Py_UNICODE_WIDE - *p > unimax || *p < 0 || -#endif - end-s < Py_UNICODE_SIZE - ) - { - startinpos = s - starts; - if (end-s < Py_UNICODE_SIZE) { - endinpos = end-starts; - reason = "truncated input"; - } - else { - endinpos = s - starts + Py_UNICODE_SIZE; - reason = "illegal code point (> 0x10FFFF)"; - } - outpos = p - PyUnicode_AS_UNICODE(v); - if (unicode_decode_call_errorhandler( - errors, &errorHandler, - "unicode_internal", reason, - &starts, &end, &startinpos, &endinpos, &exc, &s, - &v, &outpos, &p)) { - goto onError; - } + if (*p > unimax || *p < 0) { + endinpos = s - starts + Py_UNICODE_SIZE; + reason = "illegal code point (> 0x10FFFF)"; + goto error; } - else { - p++; - s += Py_UNICODE_SIZE; +#endif + p++; + s += Py_UNICODE_SIZE; + continue; + + error: + startinpos = s - starts; + outpos = p - PyUnicode_AS_UNICODE(v); + if (unicode_decode_call_errorhandler( + errors, &errorHandler, + "unicode_internal", reason, + &starts, &end, &startinpos, &endinpos, &exc, &s, + &v, &outpos, &p)) { + goto onError; } } -- cgit v0.12