Backport fast alternate io.BytesIO implementation.

Merged r62778, r62779, r62802, r62806, r62807, r62808, r62809, r62844,
r62846, r62952, r62956.

Lib/io.py

@@ -494,6 +494,7 @@ class IOBase(object):
         files, the newlines argument to open can be used to select the line
         terminator(s) recognized.
         """
+        self._checkClosed()
         if hasattr(self, "peek"):
             def nreadahead():
                 readahead = self.peek(1)
@@ -508,6 +509,8 @@ class IOBase(object):
                 return 1
         if limit is None:
             limit = -1
+        if not isinstance(limit, (int, long)):
+            raise TypeError("limit must be an integer")
         res = bytearray()
         while limit < 0 or len(res) < limit:
             b = self.read(nreadahead())
@@ -536,6 +539,10 @@ class IOBase(object):
         lines so far exceeds hint.
         """
         if hint is None:
+            hint = -1
+        if not isinstance(hint, (int, long)):
+            raise TypeError("hint must be an integer")
+        if hint <= 0:
             return list(self)
         n = 0
         lines = []
@@ -686,7 +693,7 @@ class BufferedIOBase(IOBase):
             import array
             if not isinstance(b, array.array):
                 raise err
-            b[:n] = array.array('b', data)
+            b[:n] = array.array(b'b', data)
         return n
 
     def write(self, b):
@@ -729,6 +736,8 @@ class _BufferedIOMixin(BufferedIOBase):
 
         if pos is None:
             pos = self.tell()
+        # XXX: Should seek() be used, instead of passing the position
+        # XXX  directly to truncate?
         return self.raw.truncate(pos)
 
     ### Flush and close ###
@@ -768,7 +777,7 @@ class _BufferedIOMixin(BufferedIOBase):
         return self.raw.isatty()
 
 
-class BytesIO(BufferedIOBase):
+class _BytesIO(BufferedIOBase):
 
     """Buffered I/O implementation using an in-memory bytes buffer."""
 
@@ -777,20 +786,28 @@ class BytesIO(BufferedIOBase):
     def __init__(self, initial_bytes=None):
         buf = bytearray()
         if initial_bytes is not None:
-            buf += initial_bytes
+            buf += bytearray(initial_bytes)
         self._buffer = buf
         self._pos = 0
 
     def getvalue(self):
         """Return the bytes value (contents) of the buffer
         """
+        if self.closed:
+            raise ValueError("getvalue on closed file")
         return bytes(self._buffer)
 
     def read(self, n=None):
+        if self.closed:
+            raise ValueError("read from closed file")
         if n is None:
             n = -1
+        if not isinstance(n, (int, long)):
+            raise TypeError("argument must be an integer")
         if n < 0:
             n = len(self._buffer)
+        if len(self._buffer) <= self._pos:
+            return b""
         newpos = min(len(self._buffer), self._pos + n)
         b = self._buffer[self._pos : newpos]
         self._pos = newpos
@@ -807,6 +824,8 @@ class BytesIO(BufferedIOBase):
         if isinstance(b, unicode):
             raise TypeError("can't write unicode to binary stream")
         n = len(b)
+        if n == 0:
+            return 0
         newpos = self._pos + n
         if newpos > len(self._buffer):
             # Inserts null bytes between the current end of the file
@@ -818,28 +837,38 @@ class BytesIO(BufferedIOBase):
         return n
 
     def seek(self, pos, whence=0):
+        if self.closed:
+            raise ValueError("seek on closed file")
         try:
             pos = pos.__index__()
         except AttributeError as err:
             raise TypeError("an integer is required") # from err
         if whence == 0:
-            self._pos = max(0, pos)
+            if pos < 0:
+                raise ValueError("negative seek position %r" % (pos,))
+            self._pos = pos
         elif whence == 1:
             self._pos = max(0, self._pos + pos)
         elif whence == 2:
             self._pos = max(0, len(self._buffer) + pos)
         else:
-            raise IOError("invalid whence value")
+            raise ValueError("invalid whence value")
         return self._pos
 
     def tell(self):
+        if self.closed:
+            raise ValueError("tell on closed file")
         return self._pos
 
     def truncate(self, pos=None):
+        if self.closed:
+            raise ValueError("truncate on closed file")
         if pos is None:
             pos = self._pos
+        elif pos < 0:
+            raise ValueError("negative truncate position %r" % (pos,))
         del self._buffer[pos:]
-        return pos
+        return self.seek(pos)
 
     def readable(self):
         return True
@@ -850,6 +879,16 @@ class BytesIO(BufferedIOBase):
     def seekable(self):
         return True
 
+# Use the faster implementation of BytesIO if available
+try:
+    import _bytesio
+
+    class BytesIO(_bytesio._BytesIO, BufferedIOBase):
+        __doc__ = _bytesio._BytesIO.__doc__
+
+except ImportError:
+    BytesIO = _BytesIO
+
 
 class BufferedReader(_BufferedIOMixin):
 
@@ -983,6 +1022,12 @@ class BufferedWriter(_BufferedIOMixin):
                     raise BlockingIOError(e.errno, e.strerror, overage)
         return written
 
+    def truncate(self, pos=None):
+        self.flush()
+        if pos is None:
+            pos = self.raw.tell()
+        return self.raw.truncate(pos)
+
     def flush(self):
         if self.closed:
             raise ValueError("flush of closed file")
@@ -1102,6 +1147,13 @@ class BufferedRandom(BufferedWriter, BufferedReader):
         else:
             return self.raw.tell() - len(self._read_buf)
 
+    def truncate(self, pos=None):
+        if pos is None:
+            pos = self.tell()
+        # Use seek to flush the read buffer.
+        self.seek(pos)
+        return BufferedWriter.truncate(self)
+
     def read(self, n=None):
         if n is None:
             n = -1
@@ -1150,11 +1202,7 @@ class TextIOBase(IOBase):
 
     def truncate(self, pos = None):
         """Truncate size to pos."""
-        self.flush()
-        if pos is None:
-            pos = self.tell()
-        self.seek(pos)
-        return self.buffer.truncate()
+        self._unsupported("truncate")
 
     def readline(self):
         """Read until newline or EOF.
@@ -1351,6 +1399,12 @@ class TextIOWrapper(TextIOBase):
     def seekable(self):
         return self._seekable
 
+    def readable(self):
+        return self.buffer.readable()
+
+    def writable(self):
+        return self.buffer.writable()
+
     def flush(self):
         self.buffer.flush()
         self._telling = self._seekable
@@ -1542,7 +1596,16 @@ class TextIOWrapper(TextIOBase):
         finally:
             decoder.setstate(saved_state)
 
+    def truncate(self, pos=None):
+        self.flush()
+        if pos is None:
+            pos = self.tell()
+        self.seek(pos)
+        return self.buffer.truncate()
+
     def seek(self, cookie, whence=0):
+        if self.closed:
+            raise ValueError("tell on closed file")
         if not self._seekable:
             raise IOError("underlying stream is not seekable")
         if whence == 1: # seek relative to current position
@@ -1629,8 +1692,12 @@ class TextIOWrapper(TextIOBase):
         return line
 
     def readline(self, limit=None):
+        if self.closed:
+            raise ValueError("read from closed file")
         if limit is None:
             limit = -1
+        if not isinstance(limit, (int, long)):
+            raise TypeError("limit must be an integer")
 
         # Grab all the decoded text (we will rewind any extra bits later).
         line = self._get_decoded_chars()

Lib/test/test_io.py

@@ -97,7 +97,7 @@ class IOTest(unittest.TestCase):
         self.assertEqual(f.seek(-1, 2), 13)
         self.assertEqual(f.tell(), 13)
         self.assertEqual(f.truncate(12), 12)
-        self.assertEqual(f.tell(), 13)
+        self.assertEqual(f.tell(), 12)
         self.assertRaises(TypeError, f.seek, 0.0)
 
     def read_ops(self, f, buffered=False):
@@ -142,7 +142,7 @@ class IOTest(unittest.TestCase):
         self.assertEqual(f.tell(), self.LARGE + 2)
         self.assertEqual(f.seek(0, 2), self.LARGE + 2)
         self.assertEqual(f.truncate(self.LARGE + 1), self.LARGE + 1)
-        self.assertEqual(f.tell(), self.LARGE + 2)
+        self.assertEqual(f.tell(), self.LARGE + 1)
         self.assertEqual(f.seek(0, 2), self.LARGE + 1)
         self.assertEqual(f.seek(-1, 2), self.LARGE)
         self.assertEqual(f.read(2), b"x")
@@ -726,6 +726,7 @@ class TextIOWrapperTest(unittest.TestCase):
             txt.write("BB\nCCC\n")
             txt.write("X\rY\r\nZ")
             txt.flush()
+            self.assertEquals(buf.closed, False)
             self.assertEquals(buf.getvalue(), expected)
 
     def testNewlines(self):
@@ -806,7 +807,8 @@ class TextIOWrapperTest(unittest.TestCase):
                 txt = io.TextIOWrapper(buf, encoding="ascii", newline=newline)
                 txt.write(data)
                 txt.close()
-                self.assertEquals(buf.getvalue(), expected)
+                self.assertEquals(buf.closed, True)
+                self.assertRaises(ValueError, buf.getvalue)
         finally:
             os.linesep = save_linesep
 

Modules/_fileio.c

@@ -552,11 +552,10 @@ portable_lseek(int fd, PyObject *posobj, int whence)
 			PyErr_SetString(PyExc_TypeError, "an integer is required");
 			return NULL;
 		}
-#if !defined(HAVE_LARGEFILE_SUPPORT)
-		pos = PyLong_AsLong(posobj);
+#if defined(HAVE_LARGEFILE_SUPPORT)
+		pos = PyLong_AsLongLong(posobj);
 #else
-		pos = PyLong_Check(posobj) ?
-			PyLong_AsLongLong(posobj) : PyLong_AsLong(posobj);
+		pos = PyLong_AsLong(posobj);
 #endif
 		if (PyErr_Occurred())
 			return NULL;
@@ -572,10 +571,10 @@ portable_lseek(int fd, PyObject *posobj, int whence)
 	if (res < 0)
 		return PyErr_SetFromErrno(PyExc_IOError);
 
-#if !defined(HAVE_LARGEFILE_SUPPORT)
-	return PyLong_FromLong(res);
-#else
+#if defined(HAVE_LARGEFILE_SUPPORT)
 	return PyLong_FromLongLong(res);
+#else
+	return PyLong_FromLong(res);
 #endif
 }
 
@@ -622,48 +621,29 @@ fileio_truncate(PyFileIOObject *self, PyObject *args)
 		return NULL;
 
 	if (posobj == Py_None || posobj == NULL) {
+		/* Get the current position. */
                 posobj = portable_lseek(fd, NULL, 1);
                 if (posobj == NULL)
-                  return NULL;
+			return NULL;
         }
         else {
-		Py_INCREF(posobj);
+		/* Move to the position to be truncated. */
+                posobj = portable_lseek(fd, posobj, 0);
         }
 
-#if !defined(HAVE_LARGEFILE_SUPPORT)
-	pos = PyLong_AsLong(posobj);
+#if defined(HAVE_LARGEFILE_SUPPORT)
+	pos = PyLong_AsLongLong(posobj);
 #else
-	pos = PyLong_Check(posobj) ?
-		PyLong_AsLongLong(posobj) : PyLong_AsLong(posobj);
+	pos = PyLong_AsLong(posobj);
 #endif
-	if (PyErr_Occurred()) {
-		Py_DECREF(posobj);
+	if (PyErr_Occurred())
 		return NULL;
-	}
 
 #ifdef MS_WINDOWS
 	/* MS _chsize doesn't work if newsize doesn't fit in 32 bits,
 	   so don't even try using it. */
 	{
 		HANDLE hFile;
-		PyObject *pos2, *oldposobj;
-
-		/* store the current position */
-		oldposobj = portable_lseek(self->fd, NULL, 1);
-		if (oldposobj == NULL) {
-			Py_DECREF(posobj);
-			return NULL;
-		}
-
-		/* Have to move current pos to desired endpoint on Windows. */
-		errno = 0;
-		pos2 = portable_lseek(fd, posobj, SEEK_SET);
-		if (pos2 == NULL) {
-			Py_DECREF(posobj);
-			Py_DECREF(oldposobj);
-			return NULL;
-		}
-		Py_DECREF(pos2);
 
 		/* Truncate.  Note that this may grow the file! */
 		Py_BEGIN_ALLOW_THREADS
@@ -676,18 +656,6 @@ fileio_truncate(PyFileIOObject *self, PyObject *args)
 				errno = EACCES;
 		}
 		Py_END_ALLOW_THREADS
-
-		if (ret == 0) {
-			/* Move to the previous position in the file */
-			pos2 = portable_lseek(fd, oldposobj, SEEK_SET);
-			if (pos2 == NULL) {
-				Py_DECREF(posobj);
-				Py_DECREF(oldposobj);
-				return NULL;
-			}
-		}
-		Py_DECREF(pos2);
-		Py_DECREF(oldposobj);
 	}
 #else
 	Py_BEGIN_ALLOW_THREADS
@@ -697,7 +665,6 @@ fileio_truncate(PyFileIOObject *self, PyObject *args)
 #endif /* !MS_WINDOWS */
 
 	if (ret != 0) {
-		Py_DECREF(posobj);
 		PyErr_SetFromErrno(PyExc_IOError);
 		return NULL;
 	}
@@ -791,7 +758,8 @@ PyDoc_STRVAR(seek_doc,
 PyDoc_STRVAR(truncate_doc,
 "truncate([size: int]) -> None.	 Truncate the file to at most size bytes.\n"
 "\n"
-"Size defaults to the current file position, as returned by tell().");
+"Size defaults to the current file position, as returned by tell()."
+"The current file position is changed to the value of size.");
 #endif
 
 PyDoc_STRVAR(tell_doc,

Objects/bytesobject.c

@@ -315,8 +315,8 @@ bytes_iconcat(PyBytesObject *self, PyObject *other)
     Py_buffer vo;
 
     if (_getbuffer(other, &vo) < 0) {
-        PyErr_Format(PyExc_TypeError, "can't concat bytes to %.100s",
-                     Py_TYPE(self)->tp_name);
+        PyErr_Format(PyExc_TypeError, "can't concat %.100s to %.100s",
+                     Py_TYPE(other)->tp_name, Py_TYPE(self)->tp_name);
         return NULL;
     }
 

PC/VS8.0/pythoncore.vcproj

@@ -990,6 +990,10 @@
 				RelativePath="..\..\Modules\_fileio.c"
 				>
 			</File>
+			<File
+				RelativePath="..\..\Modules\_bytesio.c"
+				>
+			</File>
 			<File
 				RelativePath="..\..\Modules\_functoolsmodule.c"
 				>

PC/config.c

@@ -53,6 +53,7 @@ extern void init_winreg(void);
 extern void init_struct(void);
 extern void initdatetime(void);
 extern void init_fileio(void);
+extern void init_bytesio(void);
 extern void init_functools(void);
 extern void init_json(void);
 extern void initzlib(void);
@@ -132,6 +133,7 @@ struct _inittab _PyImport_Inittab[] = {
 	{"_struct", init_struct},
 	{"datetime", initdatetime},
 	{"_fileio", init_fileio},
+	{"_bytesio", init_bytesio},
 	{"_functools", init_functools},
 	{"_json", init_json},
 

PCbuild/pythoncore.vcproj

@@ -994,6 +994,10 @@
 				RelativePath="..\Modules\_fileio.c"
 				>
 			</File>
+			<File
+				RelativePath="..\Modules\_bytesio.c"
+				>
+			</File>
 			<File
 				RelativePath="..\Modules\_functoolsmodule.c"
 				>

setup.py

@@ -436,6 +436,8 @@ class PyBuildExt(build_ext):
         exts.append( Extension('operator', ['operator.c']) )
         # Python 3.0 _fileio module
         exts.append( Extension("_fileio", ["_fileio.c"]) )
+        # Python 3.0 _bytesio module
+        exts.append( Extension("_bytesio", ["_bytesio.c"]) )
         # _functools
         exts.append( Extension("_functools", ["_functoolsmodule.c"]) )
         # _json speedups