Merged revisions 74929 via svnmerge from
svn+ssh://pythondev@svn.python.org/python/trunk
........
r74929 | benjamin.peterson | 2009-09-18 16:14:55 -0500 (Fri, 18 Sep 2009) | 1 line
add keyword arguments support to str/unicode encode and decode #6300
........
diff --git a/Doc/library/stdtypes.rst b/Doc/library/stdtypes.rst
index c9e7287..a11c2d3 100644
--- a/Doc/library/stdtypes.rst
+++ b/Doc/library/stdtypes.rst
@@ -788,11 +788,10 @@
.. index:: pair: string; methods
-String objects support the methods listed below. Note that none of these
-methods take keyword arguments.
+String objects support the methods listed below.
-In addition, Python's strings support the sequence type methods described in
-the :ref:`typesseq` section. To output formatted strings, see the
+In addition, Python's strings support the sequence type methods described in the
+:ref:`typesseq` section. To output formatted strings, see the
:ref:`string-formatting` section. Also, see the :mod:`re` module for string
functions based on regular expressions.
@@ -825,6 +824,8 @@
:func:`codecs.register_error`, see section :ref:`codec-base-classes`. For a
list of possible encodings, see section :ref:`standard-encodings`.
+ .. versionchanged:: 3.1
+ Added support for keyword arguments added.
.. method:: str.endswith(suffix[, start[, end]])
@@ -1539,6 +1540,9 @@
:func:`codecs.register_error`, see section :ref:`codec-base-classes`. For a
list of possible encodings, see section :ref:`standard-encodings`.
+ .. versionchanged:: 3.1
+ Added support for keyword arguments.
+
The bytes and bytearray types have an additional class method:
diff --git a/Lib/test/test_bytes.py b/Lib/test/test_bytes.py
index dd01b93..ad11686 100644
--- a/Lib/test/test_bytes.py
+++ b/Lib/test/test_bytes.py
@@ -186,6 +186,8 @@
b = self.type2test(sample, "latin1")
self.assertRaises(UnicodeDecodeError, b.decode, "utf8")
self.assertEqual(b.decode("utf8", "ignore"), "Hello world\n")
+ self.assertEqual(b.decode(errors="ignore", encoding="utf8"),
+ "Hello world\n")
def test_from_int(self):
b = self.type2test(0)
diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py
index 7f87b43..66368f4 100644
--- a/Lib/test/test_unicode.py
+++ b/Lib/test/test_unicode.py
@@ -955,6 +955,10 @@
self.assertRaises(UnicodeError, 'Andr\202 x'.encode, 'ascii','strict')
self.assertEqual('Andr\202 x'.encode('ascii','ignore'), b"Andr x")
self.assertEqual('Andr\202 x'.encode('ascii','replace'), b"Andr? x")
+ self.assertEqual('Andr\202 x'.encode('ascii', 'replace'),
+ 'Andr\202 x'.encode('ascii', errors='replace'))
+ self.assertEqual('Andr\202 x'.encode('ascii', 'ignore'),
+ 'Andr\202 x'.encode(encoding='ascii', errors='ignore'))
# Error handling (decoding)
self.assertRaises(UnicodeError, str, b'Andr\202 x', 'ascii')
diff --git a/Misc/ACKS b/Misc/ACKS
index defc355..b2ada2b 100644
--- a/Misc/ACKS
+++ b/Misc/ACKS
@@ -87,6 +87,7 @@
Eric Bouck
Thierry Bousch
Sebastian Boving
+Jeff Bradberry
Monty Brandenberg
Georg Brandl
Christopher Brannon
diff --git a/Objects/bytearrayobject.c b/Objects/bytearrayobject.c
index 835244a..c09ccde 100644
--- a/Objects/bytearrayobject.c
+++ b/Objects/bytearrayobject.c
@@ -2877,12 +2877,13 @@
able to handle UnicodeDecodeErrors.");
static PyObject *
-bytearray_decode(PyObject *self, PyObject *args)
+bytearray_decode(PyObject *self, PyObject *args, PyObject *kwargs)
{
const char *encoding = NULL;
const char *errors = NULL;
+ static char *kwlist[] = {"encoding", "errors", 0};
- if (!PyArg_ParseTuple(args, "|ss:decode", &encoding, &errors))
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ss:decode", kwlist, &encoding, &errors))
return NULL;
if (encoding == NULL)
encoding = PyUnicode_GetDefaultEncoding();
@@ -3112,7 +3113,7 @@
_Py_capitalize__doc__},
{"center", (PyCFunction)stringlib_center, METH_VARARGS, center__doc__},
{"count", (PyCFunction)bytearray_count, METH_VARARGS, count__doc__},
- {"decode", (PyCFunction)bytearray_decode, METH_VARARGS, decode_doc},
+ {"decode", (PyCFunction)bytearray_decode, METH_VARARGS | METH_KEYWORDS, decode_doc},
{"endswith", (PyCFunction)bytearray_endswith, METH_VARARGS, endswith__doc__},
{"expandtabs", (PyCFunction)stringlib_expandtabs, METH_VARARGS,
expandtabs__doc__},
diff --git a/Objects/bytesobject.c b/Objects/bytesobject.c
index fb4a845..27d4f95 100644
--- a/Objects/bytesobject.c
+++ b/Objects/bytesobject.c
@@ -2725,12 +2725,13 @@
able to handle UnicodeDecodeErrors.");
static PyObject *
-bytes_decode(PyObject *self, PyObject *args)
+bytes_decode(PyObject *self, PyObject *args, PyObject *kwargs)
{
const char *encoding = NULL;
const char *errors = NULL;
+ static char *kwlist[] = {"encoding", "errors", 0};
- if (!PyArg_ParseTuple(args, "|ss:decode", &encoding, &errors))
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ss:decode", kwlist, &encoding, &errors))
return NULL;
if (encoding == NULL)
encoding = PyUnicode_GetDefaultEncoding();
@@ -2831,7 +2832,7 @@
_Py_capitalize__doc__},
{"center", (PyCFunction)stringlib_center, METH_VARARGS, center__doc__},
{"count", (PyCFunction)bytes_count, METH_VARARGS, count__doc__},
- {"decode", (PyCFunction)bytes_decode, METH_VARARGS, decode__doc__},
+ {"decode", (PyCFunction)bytes_decode, METH_VARARGS | METH_KEYWORDS, decode__doc__},
{"endswith", (PyCFunction)bytes_endswith, METH_VARARGS,
endswith__doc__},
{"expandtabs", (PyCFunction)stringlib_expandtabs, METH_VARARGS,
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 758d054..78ef7e1 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -7141,13 +7141,15 @@
codecs.register_error that can handle UnicodeEncodeErrors.");
static PyObject *
-unicode_encode(PyUnicodeObject *self, PyObject *args)
+unicode_encode(PyUnicodeObject *self, PyObject *args, PyObject *kwargs)
{
+ static char *kwlist[] = {"encoding", "errors", 0};
char *encoding = NULL;
char *errors = NULL;
PyObject *v;
- if (!PyArg_ParseTuple(args, "|ss:encode", &encoding, &errors))
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ss:encode",
+ kwlist, &encoding, &errors))
return NULL;
v = PyUnicode_AsEncodedString((PyObject *)self, encoding, errors);
if (v == NULL)
@@ -8804,7 +8806,7 @@
/* Order is according to common usage: often used methods should
appear first, since lookup is done sequentially. */
- {"encode", (PyCFunction) unicode_encode, METH_VARARGS, encode__doc__},
+ {"encode", (PyCFunction) unicode_encode, METH_VARARGS | METH_KEYWORDS, encode__doc__},
{"replace", (PyCFunction) unicode_replace, METH_VARARGS, replace__doc__},
{"split", (PyCFunction) unicode_split, METH_VARARGS, split__doc__},
{"rsplit", (PyCFunction) unicode_rsplit, METH_VARARGS, rsplit__doc__},
@@ -8820,6 +8822,7 @@
{"ljust", (PyCFunction) unicode_ljust, METH_VARARGS, ljust__doc__},
{"lower", (PyCFunction) unicode_lower, METH_NOARGS, lower__doc__},
{"lstrip", (PyCFunction) unicode_lstrip, METH_VARARGS, lstrip__doc__},
+/* {"maketrans", (PyCFunction) unicode_maketrans, METH_VARARGS, maketrans__doc__}, */
{"rfind", (PyCFunction) unicode_rfind, METH_VARARGS, rfind__doc__},
{"rindex", (PyCFunction) unicode_rindex, METH_VARARGS, rindex__doc__},
{"rjust", (PyCFunction) unicode_rjust, METH_VARARGS, rjust__doc__},