bpo-45461: Fix IncrementalDecoder and StreamReader in the "unicode-escape" codec (GH-28939)

They support now splitting escape sequences between input chunks.

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

1 files changed, 9 insertions, 1 deletions

diff --git a/Include/cpython/unicodeobject.h b/Include/cpython/unicodeobject.h
index 0cbdbdb..bc5a3b4 100644
--- a/Include/cpython/unicodeobject.h
+++ b/Include/cpython/unicodeobject.h
@@ -777,12 +777,20 @@ PyAPI_FUNC(PyObject*) _PyUnicode_EncodeUTF16(
 
 /* --- Unicode-Escape Codecs ---------------------------------------------- */
 
+/* Variant of PyUnicode_DecodeUnicodeEscape that supports partial decoding. */
+PyAPI_FUNC(PyObject*) _PyUnicode_DecodeUnicodeEscapeStateful(
+        const char *string,     /* Unicode-Escape encoded string */
+        Py_ssize_t length,      /* size of string */
+        const char *errors,     /* error handling */
+        Py_ssize_t *consumed    /* bytes consumed */
+);
 /* Helper for PyUnicode_DecodeUnicodeEscape that detects invalid escape
    chars. */
-PyAPI_FUNC(PyObject*) _PyUnicode_DecodeUnicodeEscape(
+PyAPI_FUNC(PyObject*) _PyUnicode_DecodeUnicodeEscapeInternal(
         const char *string,     /* Unicode-Escape encoded string */
         Py_ssize_t length,      /* size of string */
         const char *errors,     /* error handling */
+        Py_ssize_t *consumed,   /* bytes consumed */
         const char **first_invalid_escape  /* on return, points to first
                                               invalid escaped char in
                                               string. */