bpo-39939: Add str.removeprefix and str.removesuffix (GH-18939)
Added str.removeprefix and str.removesuffix methods and corresponding
bytes, bytearray, and collections.UserString methods to remove affixes
from a string if present. See PEP 616 for a full description.
diff --git a/Objects/bytearrayobject.c b/Objects/bytearrayobject.c
index b271e57..5a803be 100644
--- a/Objects/bytearrayobject.c
+++ b/Objects/bytearrayobject.c
@@ -1181,6 +1181,71 @@
return _Py_bytes_endswith(PyByteArray_AS_STRING(self), PyByteArray_GET_SIZE(self), args);
}
+/*[clinic input]
+bytearray.removeprefix as bytearray_removeprefix
+
+ prefix: Py_buffer
+ /
+
+Return a bytearray with the given prefix string removed if present.
+
+If the bytearray starts with the prefix string, return
+bytearray[len(prefix):]. Otherwise, return a copy of the original
+bytearray.
+[clinic start generated code]*/
+
+static PyObject *
+bytearray_removeprefix_impl(PyByteArrayObject *self, Py_buffer *prefix)
+/*[clinic end generated code: output=6cabc585e7f502e0 input=968aada38aedd262]*/
+{
+ const char *self_start = PyByteArray_AS_STRING(self);
+ Py_ssize_t self_len = PyByteArray_GET_SIZE(self);
+ const char *prefix_start = prefix->buf;
+ Py_ssize_t prefix_len = prefix->len;
+
+ if (self_len >= prefix_len
+ && memcmp(self_start, prefix_start, prefix_len) == 0)
+ {
+ return PyByteArray_FromStringAndSize(self_start + prefix_len,
+ self_len - prefix_len);
+ }
+
+ return PyByteArray_FromStringAndSize(self_start, self_len);
+}
+
+/*[clinic input]
+bytearray.removesuffix as bytearray_removesuffix
+
+ suffix: Py_buffer
+ /
+
+Return a bytearray with the given suffix string removed if present.
+
+If the bytearray ends with the suffix string and that suffix is not
+empty, return bytearray[:-len(suffix)]. Otherwise, return a copy of
+the original bytearray.
+[clinic start generated code]*/
+
+static PyObject *
+bytearray_removesuffix_impl(PyByteArrayObject *self, Py_buffer *suffix)
+/*[clinic end generated code: output=2bc8cfb79de793d3 input=c1827e810b2f6b99]*/
+{
+ const char *self_start = PyByteArray_AS_STRING(self);
+ Py_ssize_t self_len = PyByteArray_GET_SIZE(self);
+ const char *suffix_start = suffix->buf;
+ Py_ssize_t suffix_len = suffix->len;
+
+ if (self_len >= suffix_len
+ && memcmp(self_start + self_len - suffix_len,
+ suffix_start, suffix_len) == 0)
+ {
+ return PyByteArray_FromStringAndSize(self_start,
+ self_len - suffix_len);
+ }
+
+ return PyByteArray_FromStringAndSize(self_start, self_len);
+}
+
/*[clinic input]
bytearray.translate
@@ -2203,6 +2268,8 @@
BYTEARRAY_POP_METHODDEF
BYTEARRAY_REMOVE_METHODDEF
BYTEARRAY_REPLACE_METHODDEF
+ BYTEARRAY_REMOVEPREFIX_METHODDEF
+ BYTEARRAY_REMOVESUFFIX_METHODDEF
BYTEARRAY_REVERSE_METHODDEF
{"rfind", (PyCFunction)bytearray_rfind, METH_VARARGS, _Py_rfind__doc__},
{"rindex", (PyCFunction)bytearray_rindex, METH_VARARGS, _Py_rindex__doc__},
diff --git a/Objects/bytesobject.c b/Objects/bytesobject.c
index 06ead2b..25d9814 100644
--- a/Objects/bytesobject.c
+++ b/Objects/bytesobject.c
@@ -2182,6 +2182,81 @@
/** End DALKE **/
+/*[clinic input]
+bytes.removeprefix as bytes_removeprefix
+
+ prefix: Py_buffer
+ /
+
+Return a bytes object with the given prefix string removed if present.
+
+If the bytes starts with the prefix string, return bytes[len(prefix):].
+Otherwise, return a copy of the original bytes.
+[clinic start generated code]*/
+
+static PyObject *
+bytes_removeprefix_impl(PyBytesObject *self, Py_buffer *prefix)
+/*[clinic end generated code: output=f006865331a06ab6 input=0c93bac817a8502c]*/
+{
+ const char *self_start = PyBytes_AS_STRING(self);
+ Py_ssize_t self_len = PyBytes_GET_SIZE(self);
+ const char *prefix_start = prefix->buf;
+ Py_ssize_t prefix_len = prefix->len;
+
+ if (self_len >= prefix_len
+ && prefix_len > 0
+ && memcmp(self_start, prefix_start, prefix_len) == 0)
+ {
+ return PyBytes_FromStringAndSize(self_start + prefix_len,
+ self_len - prefix_len);
+ }
+
+ if (PyBytes_CheckExact(self)) {
+ Py_INCREF(self);
+ return (PyObject *)self;
+ }
+
+ return PyBytes_FromStringAndSize(self_start, self_len);
+}
+
+/*[clinic input]
+bytes.removesuffix as bytes_removesuffix
+
+ suffix: Py_buffer
+ /
+
+Return a bytes object with the given suffix string removed if present.
+
+If the bytes ends with the suffix string and that suffix is not empty,
+return bytes[:-len(prefix)]. Otherwise, return a copy of the original
+bytes.
+[clinic start generated code]*/
+
+static PyObject *
+bytes_removesuffix_impl(PyBytesObject *self, Py_buffer *suffix)
+/*[clinic end generated code: output=d887d308e3242eeb input=9f4e1da8c637bbf1]*/
+{
+ const char *self_start = PyBytes_AS_STRING(self);
+ Py_ssize_t self_len = PyBytes_GET_SIZE(self);
+ const char *suffix_start = suffix->buf;
+ Py_ssize_t suffix_len = suffix->len;
+
+ if (self_len >= suffix_len
+ && suffix_len > 0
+ && memcmp(self_start + self_len - suffix_len,
+ suffix_start, suffix_len) == 0)
+ {
+ return PyBytes_FromStringAndSize(self_start,
+ self_len - suffix_len);
+ }
+
+ if (PyBytes_CheckExact(self)) {
+ Py_INCREF(self);
+ return (PyObject *)self;
+ }
+
+ return PyBytes_FromStringAndSize(self_start, self_len);
+}
static PyObject *
bytes_startswith(PyBytesObject *self, PyObject *args)
@@ -2421,6 +2496,8 @@
BYTES_MAKETRANS_METHODDEF
BYTES_PARTITION_METHODDEF
BYTES_REPLACE_METHODDEF
+ BYTES_REMOVEPREFIX_METHODDEF
+ BYTES_REMOVESUFFIX_METHODDEF
{"rfind", (PyCFunction)bytes_rfind, METH_VARARGS, _Py_rfind__doc__},
{"rindex", (PyCFunction)bytes_rindex, METH_VARARGS, _Py_rindex__doc__},
STRINGLIB_RJUST_METHODDEF
diff --git a/Objects/clinic/bytearrayobject.c.h b/Objects/clinic/bytearrayobject.c.h
index 0557707..35ba1ff 100644
--- a/Objects/clinic/bytearrayobject.c.h
+++ b/Objects/clinic/bytearrayobject.c.h
@@ -38,6 +38,86 @@
return bytearray_copy_impl(self);
}
+PyDoc_STRVAR(bytearray_removeprefix__doc__,
+"removeprefix($self, prefix, /)\n"
+"--\n"
+"\n"
+"Return a bytearray with the given prefix string removed if present.\n"
+"\n"
+"If the bytearray starts with the prefix string, return\n"
+"bytearray[len(prefix):]. Otherwise, return a copy of the original\n"
+"bytearray.");
+
+#define BYTEARRAY_REMOVEPREFIX_METHODDEF \
+ {"removeprefix", (PyCFunction)bytearray_removeprefix, METH_O, bytearray_removeprefix__doc__},
+
+static PyObject *
+bytearray_removeprefix_impl(PyByteArrayObject *self, Py_buffer *prefix);
+
+static PyObject *
+bytearray_removeprefix(PyByteArrayObject *self, PyObject *arg)
+{
+ PyObject *return_value = NULL;
+ Py_buffer prefix = {NULL, NULL};
+
+ if (PyObject_GetBuffer(arg, &prefix, PyBUF_SIMPLE) != 0) {
+ goto exit;
+ }
+ if (!PyBuffer_IsContiguous(&prefix, 'C')) {
+ _PyArg_BadArgument("removeprefix", "argument", "contiguous buffer", arg);
+ goto exit;
+ }
+ return_value = bytearray_removeprefix_impl(self, &prefix);
+
+exit:
+ /* Cleanup for prefix */
+ if (prefix.obj) {
+ PyBuffer_Release(&prefix);
+ }
+
+ return return_value;
+}
+
+PyDoc_STRVAR(bytearray_removesuffix__doc__,
+"removesuffix($self, suffix, /)\n"
+"--\n"
+"\n"
+"Return a bytearray with the given suffix string removed if present.\n"
+"\n"
+"If the bytearray ends with the suffix string and that suffix is not\n"
+"empty, return bytearray[:-len(suffix)]. Otherwise, return a copy of\n"
+"the original bytearray.");
+
+#define BYTEARRAY_REMOVESUFFIX_METHODDEF \
+ {"removesuffix", (PyCFunction)bytearray_removesuffix, METH_O, bytearray_removesuffix__doc__},
+
+static PyObject *
+bytearray_removesuffix_impl(PyByteArrayObject *self, Py_buffer *suffix);
+
+static PyObject *
+bytearray_removesuffix(PyByteArrayObject *self, PyObject *arg)
+{
+ PyObject *return_value = NULL;
+ Py_buffer suffix = {NULL, NULL};
+
+ if (PyObject_GetBuffer(arg, &suffix, PyBUF_SIMPLE) != 0) {
+ goto exit;
+ }
+ if (!PyBuffer_IsContiguous(&suffix, 'C')) {
+ _PyArg_BadArgument("removesuffix", "argument", "contiguous buffer", arg);
+ goto exit;
+ }
+ return_value = bytearray_removesuffix_impl(self, &suffix);
+
+exit:
+ /* Cleanup for suffix */
+ if (suffix.obj) {
+ PyBuffer_Release(&suffix);
+ }
+
+ return return_value;
+}
+
PyDoc_STRVAR(bytearray_translate__doc__,
"translate($self, table, /, delete=b\'\')\n"
"--\n"
@@ -1011,4 +1091,4 @@
{
return bytearray_sizeof_impl(self);
}
-/*[clinic end generated code: output=508dce79cf2dffcc input=a9049054013a1b77]*/
+/*[clinic end generated code: output=b2919f76709e48dc input=a9049054013a1b77]*/
diff --git a/Objects/clinic/bytesobject.c.h b/Objects/clinic/bytesobject.c.h
index 22024ab..063a377 100644
--- a/Objects/clinic/bytesobject.c.h
+++ b/Objects/clinic/bytesobject.c.h
@@ -526,6 +526,85 @@
return return_value;
}
+PyDoc_STRVAR(bytes_removeprefix__doc__,
+"removeprefix($self, prefix, /)\n"
+"--\n"
+"\n"
+"Return a bytes object with the given prefix string removed if present.\n"
+"\n"
+"If the bytes starts with the prefix string, return bytes[len(prefix):].\n"
+"Otherwise, return a copy of the original bytes.");
+
+#define BYTES_REMOVEPREFIX_METHODDEF \
+ {"removeprefix", (PyCFunction)bytes_removeprefix, METH_O, bytes_removeprefix__doc__},
+
+static PyObject *
+bytes_removeprefix_impl(PyBytesObject *self, Py_buffer *prefix);
+
+static PyObject *
+bytes_removeprefix(PyBytesObject *self, PyObject *arg)
+{
+ PyObject *return_value = NULL;
+ Py_buffer prefix = {NULL, NULL};
+
+ if (PyObject_GetBuffer(arg, &prefix, PyBUF_SIMPLE) != 0) {
+ goto exit;
+ }
+ if (!PyBuffer_IsContiguous(&prefix, 'C')) {
+ _PyArg_BadArgument("removeprefix", "argument", "contiguous buffer", arg);
+ goto exit;
+ }
+ return_value = bytes_removeprefix_impl(self, &prefix);
+
+exit:
+ /* Cleanup for prefix */
+ if (prefix.obj) {
+ PyBuffer_Release(&prefix);
+ }
+
+ return return_value;
+}
+
+PyDoc_STRVAR(bytes_removesuffix__doc__,
+"removesuffix($self, suffix, /)\n"
+"--\n"
+"\n"
+"Return a bytes object with the given suffix string removed if present.\n"
+"\n"
+"If the bytes ends with the suffix string and that suffix is not empty,\n"
+"return bytes[:-len(prefix)]. Otherwise, return a copy of the original\n"
+"bytes.");
+
+#define BYTES_REMOVESUFFIX_METHODDEF \
+ {"removesuffix", (PyCFunction)bytes_removesuffix, METH_O, bytes_removesuffix__doc__},
+
+static PyObject *
+bytes_removesuffix_impl(PyBytesObject *self, Py_buffer *suffix);
+
+static PyObject *
+bytes_removesuffix(PyBytesObject *self, PyObject *arg)
+{
+ PyObject *return_value = NULL;
+ Py_buffer suffix = {NULL, NULL};
+
+ if (PyObject_GetBuffer(arg, &suffix, PyBUF_SIMPLE) != 0) {
+ goto exit;
+ }
+ if (!PyBuffer_IsContiguous(&suffix, 'C')) {
+ _PyArg_BadArgument("removesuffix", "argument", "contiguous buffer", arg);
+ goto exit;
+ }
+ return_value = bytes_removesuffix_impl(self, &suffix);
+
+exit:
+ /* Cleanup for suffix */
+ if (suffix.obj) {
+ PyBuffer_Release(&suffix);
+ }
+
+ return return_value;
+}
+
PyDoc_STRVAR(bytes_decode__doc__,
"decode($self, /, encoding=\'utf-8\', errors=\'strict\')\n"
"--\n"
@@ -755,4 +834,4 @@
exit:
return return_value;
}
-/*[clinic end generated code: output=ca60dfccf8d51e88 input=a9049054013a1b77]*/
+/*[clinic end generated code: output=220388917d7bf751 input=a9049054013a1b77]*/
diff --git a/Objects/clinic/unicodeobject.c.h b/Objects/clinic/unicodeobject.c.h
index 0d13406..cf81df4 100644
--- a/Objects/clinic/unicodeobject.c.h
+++ b/Objects/clinic/unicodeobject.c.h
@@ -754,6 +754,77 @@
return return_value;
}
+PyDoc_STRVAR(unicode_removeprefix__doc__,
+"removeprefix($self, prefix, /)\n"
+"--\n"
+"\n"
+"Return a str with the given prefix string removed if present.\n"
+"\n"
+"If the string starts with the prefix string, return string[len(prefix):].\n"
+"Otherwise, return a copy of the original string.");
+
+#define UNICODE_REMOVEPREFIX_METHODDEF \
+ {"removeprefix", (PyCFunction)unicode_removeprefix, METH_O, unicode_removeprefix__doc__},
+
+static PyObject *
+unicode_removeprefix_impl(PyObject *self, PyObject *prefix);
+
+static PyObject *
+unicode_removeprefix(PyObject *self, PyObject *arg)
+{
+ PyObject *return_value = NULL;
+ PyObject *prefix;
+
+ if (!PyUnicode_Check(arg)) {
+ _PyArg_BadArgument("removeprefix", "argument", "str", arg);
+ goto exit;
+ }
+ if (PyUnicode_READY(arg) == -1) {
+ goto exit;
+ }
+ prefix = arg;
+ return_value = unicode_removeprefix_impl(self, prefix);
+
+exit:
+ return return_value;
+}
+
+PyDoc_STRVAR(unicode_removesuffix__doc__,
+"removesuffix($self, suffix, /)\n"
+"--\n"
+"\n"
+"Return a str with the given suffix string removed if present.\n"
+"\n"
+"If the string ends with the suffix string and that suffix is not empty,\n"
+"return string[:-len(suffix)]. Otherwise, return a copy of the original\n"
+"string.");
+
+#define UNICODE_REMOVESUFFIX_METHODDEF \
+ {"removesuffix", (PyCFunction)unicode_removesuffix, METH_O, unicode_removesuffix__doc__},
+
+static PyObject *
+unicode_removesuffix_impl(PyObject *self, PyObject *suffix);
+
+static PyObject *
+unicode_removesuffix(PyObject *self, PyObject *arg)
+{
+ PyObject *return_value = NULL;
+ PyObject *suffix;
+
+ if (!PyUnicode_Check(arg)) {
+ _PyArg_BadArgument("removesuffix", "argument", "str", arg);
+ goto exit;
+ }
+ if (PyUnicode_READY(arg) == -1) {
+ goto exit;
+ }
+ suffix = arg;
+ return_value = unicode_removesuffix_impl(self, suffix);
+
+exit:
+ return return_value;
+}
+
PyDoc_STRVAR(unicode_rjust__doc__,
"rjust($self, width, fillchar=\' \', /)\n"
"--\n"
@@ -1232,4 +1303,4 @@
{
return unicode_sizeof_impl(self);
}
-/*[clinic end generated code: output=e4ed33400979c7e8 input=a9049054013a1b77]*/
+/*[clinic end generated code: output=b91233f3722643be input=a9049054013a1b77]*/
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 51775df..aba7407 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -12789,6 +12789,61 @@
return replace(self, old, new, count);
}
+/*[clinic input]
+str.removeprefix as unicode_removeprefix
+
+ prefix: unicode
+ /
+
+Return a str with the given prefix string removed if present.
+
+If the string starts with the prefix string, return string[len(prefix):].
+Otherwise, return a copy of the original string.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_removeprefix_impl(PyObject *self, PyObject *prefix)
+/*[clinic end generated code: output=f1e5945e9763bcb9 input=27ec40b99a37eb88]*/
+{
+ int match = tailmatch(self, prefix, 0, PY_SSIZE_T_MAX, -1);
+ if (match == -1) {
+ return NULL;
+ }
+ if (match) {
+ return PyUnicode_Substring(self, PyUnicode_GET_LENGTH(prefix),
+ PyUnicode_GET_LENGTH(self));
+ }
+ return unicode_result_unchanged(self);
+}
+
+/*[clinic input]
+str.removesuffix as unicode_removesuffix
+
+ suffix: unicode
+ /
+
+Return a str with the given suffix string removed if present.
+
+If the string ends with the suffix string and that suffix is not empty,
+return string[:-len(suffix)]. Otherwise, return a copy of the original
+string.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_removesuffix_impl(PyObject *self, PyObject *suffix)
+/*[clinic end generated code: output=d36629e227636822 input=12cc32561e769be4]*/
+{
+ int match = tailmatch(self, suffix, 0, PY_SSIZE_T_MAX, +1);
+ if (match == -1) {
+ return NULL;
+ }
+ if (match) {
+ return PyUnicode_Substring(self, 0, PyUnicode_GET_LENGTH(self)
+ - PyUnicode_GET_LENGTH(suffix));
+ }
+ return unicode_result_unchanged(self);
+}
+
static PyObject *
unicode_repr(PyObject *unicode)
{
@@ -14105,6 +14160,8 @@
UNICODE_UPPER_METHODDEF
{"startswith", (PyCFunction) unicode_startswith, METH_VARARGS, startswith__doc__},
{"endswith", (PyCFunction) unicode_endswith, METH_VARARGS, endswith__doc__},
+ UNICODE_REMOVEPREFIX_METHODDEF
+ UNICODE_REMOVESUFFIX_METHODDEF
UNICODE_ISASCII_METHODDEF
UNICODE_ISLOWER_METHODDEF
UNICODE_ISUPPER_METHODDEF