mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-11-03 03:22:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

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

Browse source 
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.
This commit is contained in:
Serhiy Storchaka 2021-10-14 13:17:00 +03:00 • committed by GitHub
parent e71662c1ae
commit c96d1546b1
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
8 changed files with 123 additions and 34 deletions
Download patch file Download diff file Expand all files Collapse all files

13
Modules/_codecsmodule.c
View file

@ -489,17 +489,20 @@ _codecs_utf_32_ex_decode_impl(PyObject *module, Py_buffer *data,
_codecs.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_unicode_escape_decode_impl(PyObject *module, Py_buffer *data,
const char *errors)
/*[clinic end generated code: output=3ca3c917176b82ab input=8328081a3a569bd6]*/
const char *errors, int final)
/*[clinic end generated code: output=b284f97b12c635ee input=6154f039a9f7c639]*/
{
PyObject *decoded = PyUnicode_DecodeUnicodeEscape(data->buf, data->len,
errors);
return codec_tuple(decoded, data->len);
Py_ssize_t consumed = data->len;
PyObject *decoded = _PyUnicode_DecodeUnicodeEscapeStateful(data->buf, data->len,
errors,
final ? NULL : &consumed);
return codec_tuple(decoded, consumed);
}
/*[clinic input]

18
Modules/clinic/_codecsmodule.c.h generated
View file

@ -1063,7 +1063,7 @@ exit:
}
PyDoc_STRVAR(_codecs_unicode_escape_decode__doc__,
"unicode_escape_decode($module, data, errors=None, /)\n"
"unicode_escape_decode($module, data, errors=None, final=True, /)\n"
"--\n"
"\n");
@ -1072,7 +1072,7 @@ PyDoc_STRVAR(_codecs_unicode_escape_decode__doc__,
static PyObject *
_codecs_unicode_escape_decode_impl(PyObject *module, Py_buffer *data,
const char *errors);
const char *errors, int final);
static PyObject *
_codecs_unicode_escape_decode(PyObject *module, PyObject *const *args, Py_ssize_t nargs)
@ -1080,8 +1080,9 @@ _codecs_unicode_escape_decode(PyObject *module, PyObject *const *args, Py_ssize_
PyObject *return_value = NULL;
Py_buffer data = {NULL, NULL};
const char *errors = NULL;
int final = 1;
if (!_PyArg_CheckPositional("unicode_escape_decode", nargs, 1, 2)) {
if (!_PyArg_CheckPositional("unicode_escape_decode", nargs, 1, 3)) {
goto exit;
}
if (PyUnicode_Check(args[0])) {
@ -1122,8 +1123,15 @@ _codecs_unicode_escape_decode(PyObject *module, PyObject *const *args, Py_ssize_
_PyArg_BadArgument("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_unicode_escape_decode_impl(module, &data, errors);
return_value = _codecs_unicode_escape_decode_impl(module, &data, errors, final);
exit:
/* Cleanup for data */
@ -2801,4 +2809,4 @@ 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=557c3b37e4c492ac input=a9049054013a1b77]*/
/*[clinic end generated code: output=9e9fb1d5d81577e0 input=a9049054013a1b77]*/