[3.9] bpo-45461: Fix IncrementalDecoder and StreamReader in the "unicode-escape" codec (GH-28939) (GH-28945)

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.
(cherry picked from commit c96d1546b1)

Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
This commit is contained in:
Serhiy Storchaka 2021-10-14 20:03:29 +03:00 committed by GitHub
parent 38fadbc5b9
commit 7c722e32bf
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
10 changed files with 9836 additions and 4890 deletions

View file

@ -857,12 +857,20 @@ PyAPI_FUNC(PyObject*) _PyUnicode_EncodeUTF16(
/* --- Unicode-Escape Codecs ---------------------------------------------- */
/* Helper for PyUnicode_DecodeUnicodeEscape that detects invalid escape
chars. */
PyAPI_FUNC(PyObject*) _PyUnicode_DecodeUnicodeEscape(
/* 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_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. */