Issue python#20699: Merge io bytes-like fixes from 3.5

Doc/library/io.rst

@@ -66,7 +66,8 @@ The text stream API is described in detail in the documentation of
 Binary I/O
 ^^^^^^^^^^
 
-Binary I/O (also called *buffered I/O*) expects and produces :class:`bytes`
+Binary I/O (also called *buffered I/O*) expects
+:term:`bytes-like objects <bytes-like object>` and produces :class:`bytes`
 objects.  No encoding, decoding, or newline translation is performed.  This
 category of streams can be used for all kinds of non-text data, and also when
 manual control over the handling of text data is desired.
@@ -227,9 +228,10 @@ I/O Base Classes
    when operations they do not support are called.
 
    The basic type used for binary data read from or written to a file is
-   :class:`bytes`.  :class:`bytearray`\s are accepted too, and in some cases
-   (such as :meth:`readinto`) required.  Text I/O classes work with
-   :class:`str` data.
+   :class:`bytes`.  Other :term:`bytes-like objects <bytes-like object>` are
+   accepted as method arguments too.  In some cases, such as
+   :meth:`~RawIOBase.readinto`, a writable object such as :class:`bytearray`
+   is required.  Text I/O classes work with :class:`str` data.
 
    Note that calling any method (even inquiries) on a closed stream is
    undefined.  Implementations may raise :exc:`ValueError` in this case.
@@ -393,18 +395,22 @@ I/O Base Classes
 
    .. method:: readinto(b)
 
-      Read up to ``len(b)`` bytes into :class:`bytearray` *b* and return the
+      Read bytes into a pre-allocated, writable
+      :term:`bytes-like object` *b*, and return the
       number of bytes read.  If the object is in non-blocking mode and no bytes
       are available, ``None`` is returned.
 
    .. method:: write(b)
 
-      Write the given :class:`bytes` or :class:`bytearray` object, *b*, to the
-      underlying raw stream and return the number of bytes written.  This can
-      be less than ``len(b)``, depending on specifics of the underlying raw
+      Write the given :term:`bytes-like object`, *b*, to the
+      underlying raw stream, and return the number of
+      bytes written.  This can be less than the length of *b* in
+      bytes, depending on specifics of the underlying raw
       stream, and especially if it is in non-blocking mode.  ``None`` is
       returned if the raw stream is set not to block and no single byte could
-      be readily written to it.
+      be readily written to it.  The caller may release or mutate *b* after
+      this method returns, so the implementation should only access *b*
+      during the method call.
 
 
 .. class:: BufferedIOBase
@@ -476,8 +482,8 @@ I/O Base Classes
 
    .. method:: readinto(b)
 
-      Read up to ``len(b)`` bytes into bytearray *b* and return the number of
-      bytes read.
+      Read bytes into a pre-allocated, writable
+      :term:`bytes-like object` *b* and return the number of bytes read.
 
       Like :meth:`read`, multiple reads may be issued to the underlying raw
       stream, unless the latter is interactive.
@@ -487,7 +493,8 @@ I/O Base Classes
 
    .. method:: readinto1(b)
 
-      Read up to ``len(b)`` bytes into bytearray *b*, using at most one call to
+      Read bytes into a pre-allocated, writable
+      :term:`bytes-like object` *b*, using at most one call to
       the underlying raw stream's :meth:`~RawIOBase.read` (or
       :meth:`~RawIOBase.readinto`) method. Return the number of bytes read.
 
@@ -498,8 +505,8 @@ I/O Base Classes
 
    .. method:: write(b)
 
-      Write the given :class:`bytes` or :class:`bytearray` object, *b* and
-      return the number of bytes written (never less than ``len(b)``, since if
+      Write the given :term:`bytes-like object`, *b*, and return the number
+      of bytes written (always equal to the length of *b* in bytes, since if
       the write fails an :exc:`OSError` will be raised).  Depending on the
       actual implementation, these bytes may be readily written to the
       underlying stream, or held in a buffer for performance and latency
@@ -509,6 +516,9 @@ I/O Base Classes
       data needed to be written to the raw stream but it couldn't accept
       all the data without blocking.
 
+      The caller may release or mutate *b* after this method returns,
+      so the implementation should only access *b* during the method call.
+
 
 Raw File I/O
 ^^^^^^^^^^^^
@@ -584,7 +594,8 @@ than raw I/O does.
    :class:`BufferedIOBase`.  The buffer is discarded when the
    :meth:`~IOBase.close` method is called.
 
-   The argument *initial_bytes* contains optional initial :class:`bytes` data.
+   The optional argument *initial_bytes* is a :term:`bytes-like object` that
+   contains initial data.
 
    :class:`BytesIO` provides or overrides these methods in addition to those
    from :class:`BufferedIOBase` and :class:`IOBase`:
@@ -682,7 +693,7 @@ than raw I/O does.
 
    .. method:: write(b)
 
-      Write the :class:`bytes` or :class:`bytearray` object, *b* and return the
+      Write the :term:`bytes-like object`, *b*, and return the
       number of bytes written.  When in non-blocking mode, a
       :exc:`BlockingIOError` is raised if the buffer needs to be written out but
       the raw stream blocks.

Lib/_pyio.py

@@ -296,8 +296,9 @@ class IOBase(metaclass=abc.ABCMeta):
     called.
 
     The basic type used for binary data read from or written to a file is
-    bytes. bytearrays are accepted too, and in some cases (such as
-    readinto) needed. Text I/O classes work with str data.
+    bytes. Other bytes-like objects are accepted as method arguments too. In
+    some cases (such as readinto), a writable object is required. Text I/O
+    classes work with str data.
 
     Note that calling any method (even inquiries) on a closed stream is
     undefined. Implementations may raise OSError in this case.
@@ -596,7 +597,7 @@ def readall(self):
             return data
 
     def readinto(self, b):
-        """Read up to len(b) bytes into bytearray b.
+        """Read bytes into a pre-allocated bytes-like object b.
 
         Returns an int representing the number of bytes read (0 for EOF), or
         None if the object is set not to block and has no data to read.
@@ -606,7 +607,8 @@ def readinto(self, b):
     def write(self, b):
         """Write the given buffer to the IO stream.
 
-        Returns the number of bytes written, which may be less than len(b).
+        Returns the number of bytes written, which may be less than the
+        length of b in bytes.
         """
         self._unsupported("write")
 
@@ -659,7 +661,7 @@ def read1(self, size=None):
         self._unsupported("read1")
 
     def readinto(self, b):
-        """Read up to len(b) bytes into bytearray b.
+        """Read bytes into a pre-allocated bytes-like object b.
 
         Like read(), this may issue multiple reads to the underlying raw
         stream, unless the latter is 'interactive'.
@@ -673,7 +675,7 @@ def readinto(self, b):
         return self._readinto(b, read1=False)
 
     def readinto1(self, b):
-        """Read up to len(b) bytes into *b*, using at most one system call
+        """Read bytes into buffer *b*, using at most one system call
 
         Returns an int representing the number of bytes read (0 for EOF).
 
@@ -701,8 +703,8 @@ def _readinto(self, b, read1):
     def write(self, b):
         """Write the given bytes buffer to the IO stream.
 
-        Return the number of bytes written, which is never less than
-        len(b).
+        Return the number of bytes written, which is always the length of b
+        in bytes.
 
         Raises BlockingIOError if the buffer is full and the
         underlying raw stream cannot accept more data at the moment.
@@ -884,7 +886,8 @@ def write(self, b):
             raise ValueError("write to closed file")
         if isinstance(b, str):
             raise TypeError("can't write str to binary stream")
-        n = len(b)
+        with memoryview(b) as view:
+            n = view.nbytes  # Size of any bytes-like object
         if n == 0:
             return 0
         pos = self._pos
@@ -1090,14 +1093,13 @@ def read1(self, size):
     def _readinto(self, buf, read1):
         """Read data into *buf* with at most one system call."""
 
-        if len(buf) == 0:
-            return 0
-
         # Need to create a memoryview object of type 'b', otherwise
         # we may not be able to assign bytes to it, and slicing it
         # would create a new object.
         if not isinstance(buf, memoryview):
             buf = memoryview(buf)
+        if buf.nbytes == 0:
+            return 0
         buf = buf.cast('B')
 
         written = 0

Lib/test/test_io.py

@@ -45,6 +45,22 @@
 except ImportError:
     threading = None
 
+try:
+    import ctypes
+except ImportError:
+    def byteslike(*pos, **kw):
+        return array.array("b", bytes(*pos, **kw))
+else:
+    def byteslike(*pos, **kw):
+        """Create a bytes-like object having no string or sequence methods"""
+        data = bytes(*pos, **kw)
+        obj = EmptyStruct()
+        ctypes.resize(obj, len(data))
+        memoryview(obj).cast("B")[:] = data
+        return obj
+    class EmptyStruct(ctypes.Structure):
+        pass
+
 def _default_chunk_size():
     """Get the default TextIOWrapper chunk size"""
     with open(__file__, "r", encoding="latin-1") as f:
@@ -284,7 +300,9 @@ def write_ops(self, f):
         self.assertEqual(f.tell(), 6)
         self.assertEqual(f.seek(-1, 1), 5)
         self.assertEqual(f.tell(), 5)
-        self.assertEqual(f.write(bytearray(b" world\n\n\n")), 9)
+        buffer = bytearray(b" world\n\n\n")
+        self.assertEqual(f.write(buffer), 9)
+        buffer[:] = b"*" * 9  # Overwrite our copy of the data
         self.assertEqual(f.seek(0), 0)
         self.assertEqual(f.write(b"h"), 1)
         self.assertEqual(f.seek(-1, 2), 13)
@@ -297,20 +315,21 @@ def write_ops(self, f):
     def read_ops(self, f, buffered=False):
         data = f.read(5)
         self.assertEqual(data, b"hello")
-        data = bytearray(data)
+        data = byteslike(data)
         self.assertEqual(f.readinto(data), 5)
-        self.assertEqual(data, b" worl")
+        self.assertEqual(bytes(data), b" worl")
+        data = bytearray(5)
         self.assertEqual(f.readinto(data), 2)
         self.assertEqual(len(data), 5)
         self.assertEqual(data[:2], b"d\n")
         self.assertEqual(f.seek(0), 0)
         self.assertEqual(f.read(20), b"hello world\n")
         self.assertEqual(f.read(1), b"")
-        self.assertEqual(f.readinto(bytearray(b"x")), 0)
+        self.assertEqual(f.readinto(byteslike(b"x")), 0)
         self.assertEqual(f.seek(-6, 2), 6)
         self.assertEqual(f.read(5), b"world")
         self.assertEqual(f.read(0), b"")
-        self.assertEqual(f.readinto(bytearray()), 0)
+        self.assertEqual(f.readinto(byteslike()), 0)
         self.assertEqual(f.seek(-6, 1), 5)
         self.assertEqual(f.read(5), b" worl")
         self.assertEqual(f.tell(), 10)
@@ -321,6 +340,10 @@ def read_ops(self, f, buffered=False):
             f.seek(6)
             self.assertEqual(f.read(), b"world\n")
             self.assertEqual(f.read(), b"")
+            f.seek(0)
+            data = byteslike(5)
+            self.assertEqual(f.readinto1(data), 5)
+            self.assertEqual(bytes(data), b"hello")
 
     LARGE = 2**31
 
@@ -641,10 +664,15 @@ def test_close_flushes(self):
     def test_array_writes(self):
         a = array.array('i', range(10))
         n = len(a.tobytes())
-        with self.open(support.TESTFN, "wb", 0) as f:
-            self.assertEqual(f.write(a), n)
-        with self.open(support.TESTFN, "wb") as f:
-            self.assertEqual(f.write(a), n)
+        def check(f):
+            with f:
+                self.assertEqual(f.write(a), n)
+                f.writelines((a,))
+        check(self.BytesIO())
+        check(self.FileIO(support.TESTFN, "w"))
+        check(self.BufferedWriter(self.MockRawIO()))
+        check(self.BufferedRandom(self.MockRawIO()))
+        check(self.BufferedRWPair(self.MockRawIO(), self.MockRawIO()))
 
     def test_closefd(self):
         self.assertRaises(ValueError, self.open, support.TESTFN, 'w',
@@ -803,6 +831,19 @@ def test_invalid_newline(self):
             with self.assertRaises(ValueError):
                 self.open(support.TESTFN, 'w', newline='invalid')
 
+    def test_buffered_readinto_mixin(self):
+        # Test the implementation provided by BufferedIOBase
+        class Stream(self.BufferedIOBase):
+            def read(self, size):
+                return b"12345"
+            read1 = read
+        stream = Stream()
+        for method in ("readinto", "readinto1"):
+            with self.subTest(method):
+                buffer = byteslike(5)
+                self.assertEqual(getattr(stream, method)(buffer), 5)
+                self.assertEqual(bytes(buffer), b"12345")
+
 
 class CIOTest(IOTest):
 
@@ -1394,6 +1435,11 @@ def test_write(self):
         bufio = self.tp(writer, 8)
         bufio.write(b"abc")
         self.assertFalse(writer._write_stack)
+        buffer = bytearray(b"def")
+        bufio.write(buffer)
+        buffer[:] = b"***"  # Overwrite our copy of the data
+        bufio.flush()
+        self.assertEqual(b"".join(writer._write_stack), b"abcdef")
 
     def test_write_overflow(self):
         writer = self.MockRawIO()
@@ -1720,19 +1766,23 @@ def test_read1(self):
         self.assertEqual(pair.read1(3), b"abc")
 
     def test_readinto(self):
-        pair = self.tp(self.BytesIO(b"abcdef"), self.MockRawIO())
+        for method in ("readinto", "readinto1"):
+            with self.subTest(method):
+                pair = self.tp(self.BytesIO(b"abcdef"), self.MockRawIO())
 
-        data = bytearray(5)
-        self.assertEqual(pair.readinto(data), 5)
-        self.assertEqual(data, b"abcde")
+                data = byteslike(5)
+                self.assertEqual(getattr(pair, method)(data), 5)
+                self.assertEqual(bytes(data), b"abcde")
 
     def test_write(self):
         w = self.MockRawIO()
         pair = self.tp(self.MockRawIO(), w)
 
         pair.write(b"abc")
         pair.flush()
-        pair.write(b"def")
+        buffer = bytearray(b"def")
+        pair.write(buffer)
+        buffer[:] = b"***"  # Overwrite our copy of the data
         pair.flush()
         self.assertEqual(w._write_stack, [b"abc", b"def"])
 

Lib/test/test_memoryio.py

@@ -399,7 +399,16 @@ def __init__(me, initvalue, foo):
         del __main__.PickleTestMemIO
 
 
-class BytesIOMixin:
+class PyBytesIOTest(MemoryTestMixin, MemorySeekTestMixin, unittest.TestCase):
+    # Test _pyio.BytesIO; class also inherited for testing C implementation
+
+    UnsupportedOperation = pyio.UnsupportedOperation
+
+    @staticmethod
+    def buftype(s):
+        return s.encode("ascii")
+    ioclass = pyio.BytesIO
+    EOF = b""
 
     def test_getbuffer(self):
         memio = self.ioclass(b"1234567890")
@@ -426,18 +435,6 @@ def test_getbuffer(self):
         memio.close()
         self.assertRaises(ValueError, memio.getbuffer)
 
-
-class PyBytesIOTest(MemoryTestMixin, MemorySeekTestMixin,
-                    BytesIOMixin, unittest.TestCase):
-
-    UnsupportedOperation = pyio.UnsupportedOperation
-
-    @staticmethod
-    def buftype(s):
-        return s.encode("ascii")
-    ioclass = pyio.BytesIO
-    EOF = b""
-
     def test_read1(self):
         buf = self.buftype("1234567890")
         memio = self.ioclass(buf)

Modules/_io/bufferedio.c

@@ -190,8 +190,8 @@ bufferediobase_read1(PyObject *self, PyObject *args)
 PyDoc_STRVAR(bufferediobase_write_doc,
     "Write the given buffer to the IO stream.\n"
     "\n"
-    "Returns the number of bytes written, which is never less than\n"
-    "len(b).\n"
+    "Returns the number of bytes written, which is always the length of b\n"
+    "in bytes.\n"
     "\n"
     "Raises BlockingIOError if the buffer is full and the\n"
     "underlying raw stream cannot accept more data at the moment.\n");