diff options
Diffstat (limited to 'Objects/unicodeobject.c')
| -rw-r--r-- | Objects/unicodeobject.c | 46 |
1 files changed, 28 insertions, 18 deletions
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c index eb3e1c4..4e1aafb 100644 --- a/Objects/unicodeobject.c +++ b/Objects/unicodeobject.c @@ -6621,13 +6621,15 @@ _PyUnicode_GetNameCAPI(void) /* --- Unicode Escape Codec ----------------------------------------------- */ PyObject * -_PyUnicode_DecodeUnicodeEscapeInternal(const char *s, +_PyUnicode_DecodeUnicodeEscapeInternal2(const char *s, Py_ssize_t size, const char *errors, Py_ssize_t *consumed, - const char **first_invalid_escape) + int *first_invalid_escape_char, + const char **first_invalid_escape_ptr) { const char *starts = s; + const char *initial_starts = starts; _PyUnicodeWriter writer; const char *end; PyObject *errorHandler = NULL; @@ -6635,7 +6637,8 @@ _PyUnicode_DecodeUnicodeEscapeInternal(const char *s, _PyUnicode_Name_CAPI *ucnhash_capi; // so we can remember if we've seen an invalid escape char or not - *first_invalid_escape = NULL; + *first_invalid_escape_char = -1; + *first_invalid_escape_ptr = NULL; if (size == 0) { if (consumed) { @@ -6723,9 +6726,12 @@ _PyUnicode_DecodeUnicodeEscapeInternal(const char *s, } } if (ch > 0377) { - if (*first_invalid_escape == NULL) { - *first_invalid_escape = s-3; /* Back up 3 chars, since we've - already incremented s. */ + if (*first_invalid_escape_char == -1) { + *first_invalid_escape_char = ch; + if (starts == initial_starts) { + /* Back up 3 chars, since we've already incremented s. */ + *first_invalid_escape_ptr = s - 3; + } } } WRITE_CHAR(ch); @@ -6820,9 +6826,12 @@ _PyUnicode_DecodeUnicodeEscapeInternal(const char *s, goto error; default: - if (*first_invalid_escape == NULL) { - *first_invalid_escape = s-1; /* Back up one char, since we've - already incremented s. */ + if (*first_invalid_escape_char == -1) { + *first_invalid_escape_char = c; + if (starts == initial_starts) { + /* Back up one char, since we've already incremented s. */ + *first_invalid_escape_ptr = s - 1; + } } WRITE_ASCII_CHAR('\\'); WRITE_CHAR(c); @@ -6867,19 +6876,20 @@ _PyUnicode_DecodeUnicodeEscapeStateful(const char *s, const char *errors, Py_ssize_t *consumed) { - const char *first_invalid_escape; - PyObject *result = _PyUnicode_DecodeUnicodeEscapeInternal(s, size, errors, + int first_invalid_escape_char; + const char *first_invalid_escape_ptr; + PyObject *result = _PyUnicode_DecodeUnicodeEscapeInternal2(s, size, errors, consumed, - &first_invalid_escape); + &first_invalid_escape_char, + &first_invalid_escape_ptr); if (result == NULL) return NULL; - if (first_invalid_escape != NULL) { - unsigned char c = *first_invalid_escape; - if ('4' <= c && c <= '7') { + if (first_invalid_escape_char != -1) { + if (first_invalid_escape_char > 0xff) { if (PyErr_WarnFormat(PyExc_DeprecationWarning, 1, - "\"\\%.3s\" is an invalid octal escape sequence. " + "\"\\%o\" is an invalid octal escape sequence. " "Such sequences will not work in the future. ", - first_invalid_escape) < 0) + first_invalid_escape_char) < 0) { Py_DECREF(result); return NULL; @@ -6889,7 +6899,7 @@ _PyUnicode_DecodeUnicodeEscapeStateful(const char *s, if (PyErr_WarnFormat(PyExc_DeprecationWarning, 1, "\"\\%c\" is an invalid escape sequence. " "Such sequences will not work in the future. ", - c) < 0) + first_invalid_escape_char) < 0) { Py_DECREF(result); return NULL; |