Issue 28128: Print out better error/warning messages for invalid string escapes. Backport to 3.6.

2 files changed, 65 insertions, 10 deletions

diff --git a/Objects/bytesobject.c b/Objects/bytesobject.c
index 598f6a13cf..779fe295db 100644
--- a/Objects/bytesobject.c
+++ b/Objects/bytesobject.c
@@ -1105,11 +1105,12 @@ _PyBytes_DecodeEscapeRecode(const char **s, const char *end,
     return p;
 }
 
-PyObject *PyBytes_DecodeEscape(const char *s,
+PyObject *_PyBytes_DecodeEscape(const char *s,
                                 Py_ssize_t len,
                                 const char *errors,
                                 Py_ssize_t unicode,
-                                const char *recode_encoding)
+                                const char *recode_encoding,
+                                const char **first_invalid_escape)
 {
     int c;
     char *p;
@@ -1123,6 +1124,8 @@ PyObject *PyBytes_DecodeEscape(const char *s,
         return NULL;
     writer.overallocate = 1;
 
+    *first_invalid_escape = NULL;
+
     end = s + len;
     while (s < end) {
         if (*s != '\\') {
@@ -1207,9 +1210,12 @@ PyObject *PyBytes_DecodeEscape(const char *s,
             break;
 
         default:
-            if (PyErr_WarnFormat(PyExc_DeprecationWarning, 1, "invalid escape sequence '\\%c'", *(--s)) < 0)
-                goto failed;
+            if (*first_invalid_escape == NULL) {
+                *first_invalid_escape = s-1; /* Back up one char, since we've
+                                                already incremented s. */
+            }
             *p++ = '\\';
+            s--;
             goto non_esc; /* an arbitrary number of unescaped
                              UTF-8 bytes may follow. */
         }
@@ -1222,6 +1228,29 @@ PyObject *PyBytes_DecodeEscape(const char *s,
     return NULL;
 }
 
+PyObject *PyBytes_DecodeEscape(const char *s,
+                                Py_ssize_t len,
+                                const char *errors,
+                                Py_ssize_t unicode,
+                                const char *recode_encoding)
+{
+    const char* first_invalid_escape;
+    PyObject *result = _PyBytes_DecodeEscape(s, len, errors, unicode,
+                                             recode_encoding,
+                                             &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;
+
+}
 /* -------------------------------------------------------------------- */
 /* object api */
 
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index e45f3d7c27..50b21cf9e6 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