diff options
Diffstat (limited to 'Objects/unicodeobject.c')
| -rw-r--r-- | Objects/unicodeobject.c | 49 |
1 files changed, 37 insertions, 12 deletions
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c index 38fb3ffc5e..d6fc03e1ae 100644 --- a/Objects/unicodeobject.c +++ b/Objects/unicodeobject.c @@ -6271,9 +6271,10 @@ PyUnicode_AsUTF16String(PyObject *unicode) static _PyUnicode_Name_CAPI *ucnhash_CAPI = NULL; PyObject * -_PyUnicode_DecodeUnicodeEscape(const char *s, +_PyUnicode_DecodeUnicodeEscapeInternal(const char *s, Py_ssize_t size, const char *errors, + Py_ssize_t *consumed, const char **first_invalid_escape) { const char *starts = s; @@ -6286,6 +6287,9 @@ _PyUnicode_DecodeUnicodeEscape(const char *s, *first_invalid_escape = NULL; if (size == 0) { + if (consumed) { + *consumed = 0; + } _Py_RETURN_UNICODE_EMPTY(); } /* Escaped strings will always be longer than the resulting @@ -6336,7 +6340,7 @@ _PyUnicode_DecodeUnicodeEscape(const char *s, /* \ - Escapes */ if (s >= end) { message = "\\ at end of string"; - goto error; + goto incomplete; } c = (unsigned char) *s++; @@ -6390,7 +6394,10 @@ _PyUnicode_DecodeUnicodeEscape(const char *s, count = 8; message = "truncated \\UXXXXXXXX escape"; hexescape: - for (ch = 0; count && s < end; ++s, --count) { + for (ch = 0; count; ++s, --count) { + if (s >= end) { + goto incomplete; + } c = (unsigned char)*s; ch <<= 4; if (c >= '0' && c <= '9') { @@ -6403,12 +6410,9 @@ _PyUnicode_DecodeUnicodeEscape(const char *s, ch += c - ('A' - 10); } else { - break; + goto error; } } - if (count) { - goto error; - } /* when we get here, ch is a 32-bit unicode character */ if (ch > MAX_UNICODE) { @@ -6435,14 +6439,20 @@ _PyUnicode_DecodeUnicodeEscape(const char *s, } message = "malformed \\N character escape"; - if (s < end && *s == '{') { + if (s >= end) { + goto incomplete; + } + if (*s == '{') { const char *start = ++s; size_t namelen; /* look for the closing brace */ while (s < end && *s != '}') s++; + if (s >= end) { + goto incomplete; + } namelen = s - start; - if (namelen && s < end) { + if (namelen) { /* found a name. look it up in the unicode database */ s++; ch = 0xffffffff; /* in case 'getcode' messes up */ @@ -6468,6 +6478,11 @@ _PyUnicode_DecodeUnicodeEscape(const char *s, continue; } + incomplete: + if (consumed) { + *consumed = startinpos; + break; + } error: endinpos = s-starts; writer.min_length = end - s + writer.pos; @@ -6496,12 +6511,14 @@ _PyUnicode_DecodeUnicodeEscape(const char *s, } PyObject * -PyUnicode_DecodeUnicodeEscape(const char *s, +_PyUnicode_DecodeUnicodeEscapeStateful(const char *s, Py_ssize_t size, - const char *errors) + const char *errors, + Py_ssize_t *consumed) { const char *first_invalid_escape; - PyObject *result = _PyUnicode_DecodeUnicodeEscape(s, size, errors, + PyObject *result = _PyUnicode_DecodeUnicodeEscapeInternal(s, size, errors, + consumed, &first_invalid_escape); if (result == NULL) return NULL; @@ -6516,6 +6533,14 @@ PyUnicode_DecodeUnicodeEscape(const char *s, return result; } +PyObject * +PyUnicode_DecodeUnicodeEscape(const char *s, + Py_ssize_t size, + const char *errors) +{ + return _PyUnicode_DecodeUnicodeEscapeStateful(s, size, errors, NULL); +} + /* Return a Unicode-Escape string version of the Unicode object. */ PyObject * |