bpo-45467: Fix IncrementalDecoder and StreamReader in the "raw-unicode-escape" codec (GH-28944)

They support now splitting escape sequences between input chunks.

Add the third parameter "final" in codecs.raw_unicode_escape_decode().
It is True by default to match the former behavior.

2 files changed, 21 insertions, 10 deletions

diff --git a/Modules/_codecsmodule.c b/Modules/_codecsmodule.c
index fc74127..50afc09 100644
--- a/Modules/_codecsmodule.c
+++ b/Modules/_codecsmodule.c
@@ -509,17 +509,20 @@ _codecs_unicode_escape_decode_impl(PyObject *module, Py_buffer *data,
 _codecs.raw_unicode_escape_decode
     data: Py_buffer(accept={str, buffer})
     errors: str(accept={str, NoneType}) = None
+    final: bool(accept={int}) = True
     /
 [clinic start generated code]*/
 
 static PyObject *
 _codecs_raw_unicode_escape_decode_impl(PyObject *module, Py_buffer *data,
-                                       const char *errors)
-/*[clinic end generated code: output=c98eeb56028070a6 input=d2f5159ce3b3392f]*/
+                                       const char *errors, int final)
+/*[clinic end generated code: output=11dbd96301e2879e input=2d166191beb3235a]*/
 {
-    PyObject *decoded = PyUnicode_DecodeRawUnicodeEscape(data->buf, data->len,
-                                                         errors);
-    return codec_tuple(decoded, data->len);
+    Py_ssize_t consumed = data->len;
+    PyObject *decoded = _PyUnicode_DecodeRawUnicodeEscapeStateful(data->buf, data->len,
+                                                                  errors,
+                                                                  final ? NULL : &consumed);
+    return codec_tuple(decoded, consumed);
 }
 
 /*[clinic input]
diff --git a/Modules/clinic/_codecsmodule.c.h b/Modules/clinic/_codecsmodule.c.h
index a7086dd..855ac77 100644
--- a/Modules/clinic/_codecsmodule.c.h
+++ b/Modules/clinic/_codecsmodule.c.h
@@ -1143,7 +1143,7 @@ exit:
 }
 
 PyDoc_STRVAR(_codecs_raw_unicode_escape_decode__doc__,
-"raw_unicode_escape_decode($module, data, errors=None, /)\n"
+"raw_unicode_escape_decode($module, data, errors=None, final=True, /)\n"
 "--\n"
 "\n");
 
@@ -1152,7 +1152,7 @@ PyDoc_STRVAR(_codecs_raw_unicode_escape_decode__doc__,
 
 static PyObject *
 _codecs_raw_unicode_escape_decode_impl(PyObject *module, Py_buffer *data,
-                                       const char *errors);
+                                       const char *errors, int final);
 
 static PyObject *
 _codecs_raw_unicode_escape_decode(PyObject *module, PyObject *const *args, Py_ssize_t nargs)
@@ -1160,8 +1160,9 @@ _codecs_raw_unicode_escape_decode(PyObject *module, PyObject *const *args, Py_ss
     PyObject *return_value = NULL;
     Py_buffer data = {NULL, NULL};
     const char *errors = NULL;
+    int final = 1;
 
-    if (!_PyArg_CheckPositional("raw_unicode_escape_decode", nargs, 1, 2)) {
+    if (!_PyArg_CheckPositional("raw_unicode_escape_decode", nargs, 1, 3)) {
         goto exit;
     }
     if (PyUnicode_Check(args[0])) {
@@ -1202,8 +1203,15 @@ _codecs_raw_unicode_escape_decode(PyObject *module, PyObject *const *args, Py_ss
         _PyArg_BadArgument("raw_unicode_escape_decode", "argument 2", "str or None", args[1]);
         goto exit;
     }
+    if (nargs < 3) {
+        goto skip_optional;
+    }
+    final = _PyLong_AsInt(args[2]);
+    if (final == -1 && PyErr_Occurred()) {
+        goto exit;
+    }
 skip_optional:
-    return_value = _codecs_raw_unicode_escape_decode_impl(module, &data, errors);
+    return_value = _codecs_raw_unicode_escape_decode_impl(module, &data, errors, final);
 
 exit:
     /* Cleanup for data */
@@ -2809,4 +2817,4 @@ exit:
 #ifndef _CODECS_CODE_PAGE_ENCODE_METHODDEF
     #define _CODECS_CODE_PAGE_ENCODE_METHODDEF
 #endif /* !defined(_CODECS_CODE_PAGE_ENCODE_METHODDEF) */
-/*[clinic end generated code: output=9e9fb1d5d81577e0 input=a9049054013a1b77]*/
+/*[clinic end generated code: output=814dae36b6f885cb input=a9049054013a1b77]*/