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.

Author: sweeneyde

Doc/library/stdtypes.rst

@@ -1549,6 +1549,33 @@ expression support in the :mod:`re` module).
  interpreted as in slice notation.
 
 
+.. method:: str.removeprefix(prefix, /)
+
+ If the string starts with the *prefix* string, return
+ ``string[len(prefix):]``. Otherwise, return a copy of the original
+ string::
+
+ >>> 'TestHook'.removeprefix('Test')
+ 'Hook'
+ >>> 'BaseTestCase'.removeprefix('Test')
+ 'BaseTestCase'
+
+ .. versionadded:: 3.9
+
+.. method:: str.removesuffix(suffix, /)
+
+ 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::
+
+ >>> 'MiscTests'.removesuffix('Tests')
+ 'Misc'
+ >>> 'TmpDirMixin'.removesuffix('Tests')
+ 'TmpDirMixin'
+
+ .. versionadded:: 3.9
+
+
 .. method:: str.encode(encoding="utf-8", errors="strict")
 
  Return an encoded version of the string as a bytes object. Default encoding
@@ -1831,6 +1858,14 @@ expression support in the :mod:`re` module).
  >>> 'www.example.com'.lstrip('cmowz.')
  'example.com'
 
+ See :meth:`str.removeprefix` for a method that will remove a single prefix
+ string rather than all of a set of characters. For example::
+
+ >>> 'Arthur: three!'.lstrip('Arthur: ')
+ 'ee!'
+ >>> 'Arthur: three!'.removeprefix('Arthur: ')
+ 'three!'
+
 
 .. staticmethod:: str.maketrans(x[, y[, z]])
 
@@ -1911,6 +1946,13 @@ expression support in the :mod:`re` module).
  >>> 'mississippi'.rstrip('ipz')
  'mississ'
 
+ See :meth:`str.removesuffix` for a method that will remove a single suffix
+ string rather than all of a set of characters. For example::
+
+ >>> 'Monty Python'.rstrip(' Python')
+ 'M'
+ >>> 'Monty Python'.removesuffix(' Python')
+ 'Monty'
 
 .. method:: str.split(sep=None, maxsplit=-1)
 
@@ -2591,6 +2633,50 @@ arbitrary binary data.
  Also accept an integer in the range 0 to 255 as the subsequence.
 
 
+.. method:: bytes.removeprefix(prefix, /)
+ bytearray.removeprefix(prefix, /)
+
+ If the binary data starts with the *prefix* string, return
+ ``bytes[len(prefix):]``. Otherwise, return a copy of the original
+ binary data::
+
+ >>> b'TestHook'.removeprefix(b'Test')
+ b'Hook'
+ >>> b'BaseTestCase'.removeprefix(b'Test')
+ b'BaseTestCase'
+
+ The *prefix* may be any :term:`bytes-like object`.
+
+ .. note::
+
+ The bytearray version of this method does *not* operate in place -
+ it always produces a new object, even if no changes were made.
+
+ .. versionadded:: 3.9
+
+
+.. method:: bytes.removesuffix(suffix, /)
+ bytearray.removesuffix(suffix, /)
+
+ If the binary data ends with the *suffix* string and that *suffix* is
+ not empty, return ``bytes[:-len(suffix)]``. Otherwise, return a copy of
+ the original binary data::
+
+ >>> b'MiscTests'.removesuffix(b'Tests')
+ b'Misc'
+ >>> b'TmpDirMixin'.removesuffix(b'Tests')
+ b'TmpDirMixin'
+
+ The *suffix* may be any :term:`bytes-like object`.
+
+ .. note::
+
+ The bytearray version of this method does *not* operate in place -
+ it always produces a new object, even if no changes were made.
+
+ .. versionadded:: 3.9
+
+
 .. method:: bytes.decode(encoding="utf-8", errors="strict")
  bytearray.decode(encoding="utf-8", errors="strict")
 
@@ -2841,7 +2927,14 @@ produce new objects.
  b'example.com'
 
  The binary sequence of byte values to remove may be any
- :term:`bytes-like object`.
+ :term:`bytes-like object`. See :meth:`~bytes.removeprefix` for a method
+ that will remove a single prefix string rather than all of a set of
+ characters. For example::
+
+ >>> b'Arthur: three!'.lstrip(b'Arthur: ')
+ b'ee!'
+ >>> b'Arthur: three!'.removeprefix(b'Arthur: ')
+ b'three!'
 
  .. note::
 
@@ -2890,7 +2983,14 @@ produce new objects.
  b'mississ'
 
  The binary sequence of byte values to remove may be any
- :term:`bytes-like object`.
+ :term:`bytes-like object`. See :meth:`~bytes.removesuffix` for a method
+ that will remove a single suffix string rather than all of a set of
+ characters. For example::
+
+ >>> b'Monty Python'.rstrip(b' Python')
+ b'M'
+ >>> b'Monty Python'.removesuffix(b' Python')
+ b'Monty'
 
  .. note::
 

Doc/whatsnew/3.9.rst

@@ -105,6 +105,16 @@ Merge (``|``) and update (``|=``) operators have been added to the built-in
 :class:`dict` class. See :pep:`584` for a full description.
 (Contributed by Brandt Bucher in :issue:`36144`.)
 
+PEP 616: New removeprefix() and removesuffix() string methods
+-------------------------------------------------------------
+
+:meth:`str.removeprefix(prefix)<str.removeprefix>` and
+:meth:`str.removesuffix(suffix)<str.removesuffix>` have been added
+to easily remove an unneeded prefix or a suffix from a string. Corresponding
+``bytes``, ``bytearray``, and ``collections.UserString`` methods have also been
+added. See :pep:`616` for a full description. (Contributed by Dennis Sweeney in
+:issue:`18939`.)
+
 
 Other Language Changes
 ======================

Lib/collections/__init__.py

@@ -1239,6 +1239,14 @@ def count(self, sub, start=0, end=_sys.maxsize):
  if isinstance(sub, UserString):
  sub = sub.data
  return self.data.count(sub, start, end)
+ def removeprefix(self, prefix, /):
+ if isinstance(prefix, UserString):
+ prefix = prefix.data
+ return self.__class__(self.data.removeprefix(prefix))
+ def removesuffix(self, suffix, /):
+ if isinstance(suffix, UserString):
+ suffix = suffix.data
+ return self.__class__(self.data.removesuffix(suffix))
  def encode(self, encoding='utf-8', errors='strict'):
  encoding = 'utf-8' if encoding is None else encoding
  errors = 'strict' if errors is None else errors

Lib/test/string_tests.py

@@ -682,6 +682,42 @@ def test_replace_overflow(self):
  self.checkraises(OverflowError, A2_16, "replace", "A", A2_16)
  self.checkraises(OverflowError, A2_16, "replace", "AA", A2_16+A2_16)
 
+ def test_removeprefix(self):
+ self.checkequal('am', 'spam', 'removeprefix', 'sp')
+ self.checkequal('spamspam', 'spamspamspam', 'removeprefix', 'spam')
+ self.checkequal('spam', 'spam', 'removeprefix', 'python')
+ self.checkequal('spam', 'spam', 'removeprefix', 'spider')
+ self.checkequal('spam', 'spam', 'removeprefix', 'spam and eggs')
+
+ self.checkequal('', '', 'removeprefix', '')
+ self.checkequal('', '', 'removeprefix', 'abcde')
+ self.checkequal('abcde', 'abcde', 'removeprefix', '')
+ self.checkequal('', 'abcde', 'removeprefix', 'abcde')
+
+ self.checkraises(TypeError, 'hello', 'removeprefix')
+ self.checkraises(TypeError, 'hello', 'removeprefix', 42)
+ self.checkraises(TypeError, 'hello', 'removeprefix', 42, 'h')
+ self.checkraises(TypeError, 'hello', 'removeprefix', 'h', 42)
+ self.checkraises(TypeError, 'hello', 'removeprefix', ("he", "l"))
+
+ def test_removesuffix(self):
+ self.checkequal('sp', 'spam', 'removesuffix', 'am')
+ self.checkequal('spamspam', 'spamspamspam', 'removesuffix', 'spam')
+ self.checkequal('spam', 'spam', 'removesuffix', 'python')
+ self.checkequal('spam', 'spam', 'removesuffix', 'blam')
+ self.checkequal('spam', 'spam', 'removesuffix', 'eggs and spam')
+
+ self.checkequal('', '', 'removesuffix', '')
+ self.checkequal('', '', 'removesuffix', 'abcde')
+ self.checkequal('abcde', 'abcde', 'removesuffix', '')
+ self.checkequal('', 'abcde', 'removesuffix', 'abcde')
+
+ self.checkraises(TypeError, 'hello', 'removesuffix')
+ self.checkraises(TypeError, 'hello', 'removesuffix', 42)
+ self.checkraises(TypeError, 'hello', 'removesuffix', 42, 'h')
+ self.checkraises(TypeError, 'hello', 'removesuffix', 'h', 42)
+ self.checkraises(TypeError, 'hello', 'removesuffix', ("lo", "l"))
+
  def test_capitalize(self):
  self.checkequal(' hello ', ' hello ', 'capitalize')
  self.checkequal('Hello ', 'Hello ','capitalize')

Lib/test/test_doctest.py

@@ -665,7 +665,7 @@ def non_Python_modules(): r"""
 
  >>> import builtins
  >>> tests = doctest.DocTestFinder().find(builtins)
- >>> 810 < len(tests) < 830 # approximate number of objects with docstrings
+ >>> 816 < len(tests) < 836 # approximate number of objects with docstrings
  True
  >>> real_tests = [t for t in tests if len(t.examples) > 0]
  >>> len(real_tests) # objects that actually have doctests

Misc/ACKS

@@ -1660,6 +1660,7 @@ Hisao Suzuki
 Kalle Svensson
 Andrew Svetlov
 Paul Swartz
+Dennis Sweeney
 Al Sweigart
 Sviatoslav Sydorenko
 Thenault Sylvain

Misc/NEWS.d/next/Core and Builtins/2020-03-11-19-17-36.bpo-39939.NwCnAM.rst

@@ -0,0 +1,5 @@
+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.
+Patch by Dennis Sweeney.

Objects/bytearrayobject.c

@@ -1181,6 +1181,71 @@ bytearray_endswith(PyByteArrayObject *self, PyObject *args)
  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_methods[] = {
  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__},