summaryrefslogtreecommitdiffstats
path: root/Objects/unicodeobject.c
diff options
context:
space:
mode:
authorEric V. Smith <eric@trueblade.com>2016-10-31 18:46:26 (GMT)
committerEric V. Smith <eric@trueblade.com>2016-10-31 18:46:26 (GMT)
commit5646648678295a44aa82636c6e92826651baf33a (patch)
tree2a41306ca416712ba7b55a4e51bcb836ab2a693c /Objects/unicodeobject.c
parent7f0514ad54dd806817ce6d1f54969b8979475d34 (diff)
downloadcpython-5646648678295a44aa82636c6e92826651baf33a.zip
cpython-5646648678295a44aa82636c6e92826651baf33a.tar.gz
cpython-5646648678295a44aa82636c6e92826651baf33a.tar.bz2
Issue 28128: Print out better error/warning messages for invalid string escapes. Backport to 3.6.
Diffstat (limited to 'Objects/unicodeobject.c')
-rw-r--r--Objects/unicodeobject.c38
1 files changed, 32 insertions, 6 deletions
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index e45f3d7..50b21cf 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -5896,9 +5896,10 @@ PyUnicode_AsUTF16String(PyObject *unicode)
static _PyUnicode_Name_CAPI *ucnhash_CAPI = NULL;
PyObject *
-PyUnicode_DecodeUnicodeEscape(const char *s,
- Py_ssize_t size,
- const char *errors)
+_PyUnicode_DecodeUnicodeEscape(const char *s,
+ Py_ssize_t size,
+ const char *errors,
+ const char **first_invalid_escape)
{
const char *starts = s;
_PyUnicodeWriter writer;
@@ -5906,6 +5907,9 @@ PyUnicode_DecodeUnicodeEscape(const char *s,
PyObject *errorHandler = NULL;
PyObject *exc = NULL;
+ // so we can remember if we've seen an invalid escape char or not
+ *first_invalid_escape = NULL;
+
if (size == 0) {
_Py_RETURN_UNICODE_EMPTY();
}
@@ -6080,9 +6084,10 @@ PyUnicode_DecodeUnicodeEscape(const char *s,
goto error;
default:
- if (PyErr_WarnFormat(PyExc_DeprecationWarning, 1,
- "invalid escape sequence '\\%c'", c) < 0)
- goto onError;
+ if (*first_invalid_escape == NULL) {
+ *first_invalid_escape = s-1; /* Back up one char, since we've
+ already incremented s. */
+ }
WRITE_ASCII_CHAR('\\');
WRITE_CHAR(c);
continue;
@@ -6117,6 +6122,27 @@ PyUnicode_DecodeUnicodeEscape(const char *s,
return NULL;
}
+PyObject *
+PyUnicode_DecodeUnicodeEscape(const char *s,
+ Py_ssize_t size,
+ const char *errors)
+{
+ const char *first_invalid_escape;
+ PyObject *result = _PyUnicode_DecodeUnicodeEscape(s, size, errors,
+ &first_invalid_escape);
+ if (result == NULL)
+ return NULL;
+ if (first_invalid_escape != NULL) {
+ if (PyErr_WarnFormat(PyExc_DeprecationWarning, 1,
+ "invalid escape sequence '\\%c'",
+ *first_invalid_escape) < 0) {
+ Py_DECREF(result);
+ return NULL;
+ }
+ }
+ return result;
+}
+
/* Return a Unicode-Escape string version of the Unicode object.
If quotes is true, the string is enclosed in u"" or u'' quotes as