diff -r 38df99776901 -r 0a5a40a4674a Doc/library/io.rst --- a/Doc/library/io.rst Tue Apr 24 21:09:17 2012 +0200 +++ b/Doc/library/io.rst Tue Apr 24 21:47:38 2012 +0200 @@ -291,6 +291,11 @@ .. versionadded:: 3.1 The ``SEEK_*`` constants. + .. versionadded:: 3.3 + Some operating systems could support additional values, like + :data:`os.SEEK_HOLE` or :data:`os.SEEK_DATA`. The valid values + for a file could depend on it being open in text or binary mode. + .. method:: seekable() Return ``True`` if the stream supports random access. If ``False``, diff -r 38df99776901 -r 0a5a40a4674a Doc/library/os.rst --- a/Doc/library/os.rst Tue Apr 24 21:09:17 2012 +0200 +++ b/Doc/library/os.rst Tue Apr 24 21:47:38 2012 +0200 @@ -992,6 +992,10 @@ Parameters to the :func:`lseek` function. Their values are 0, 1, and 2, respectively. Availability: Windows, Unix. + .. versionadded:: 3.3 + Some operating systems could support additional values, like + :data:`os.SEEK_HOLE` or :data:`os.SEEK_DATA`. + .. function:: mkdirat(dirfd, path, mode=0o777) diff -r 38df99776901 -r 0a5a40a4674a Lib/_pyio.py --- a/Lib/_pyio.py Tue Apr 24 21:09:17 2012 +0200 +++ b/Lib/_pyio.py Tue Apr 24 21:47:38 2012 +0200 @@ -306,6 +306,7 @@ * 0 -- start of stream (the default); offset should be zero or positive * 1 -- current stream position; offset may be negative * 2 -- end of stream; offset is usually negative + Some operating systems / file systems could provide additional values. Return an int indicating the new absolute position. """ @@ -866,7 +867,7 @@ elif whence == 2: self._pos = max(0, len(self._buffer) + pos) else: - raise ValueError("invalid whence value") + raise ValueError("unsupported whence value") return self._pos def tell(self): @@ -1041,8 +1042,6 @@ return _BufferedIOMixin.tell(self) - len(self._read_buf) + self._read_pos def seek(self, pos, whence=0): - if not (0 <= whence <= 2): - raise ValueError("invalid whence value") with self._read_lock: if whence == 1: pos -= len(self._read_buf) - self._read_pos @@ -1138,8 +1137,6 @@ return _BufferedIOMixin.tell(self) + len(self._write_buf) def seek(self, pos, whence=0): - if not (0 <= whence <= 2): - raise ValueError("invalid whence") with self._write_lock: self._flush_unlocked() return _BufferedIOMixin.seek(self, pos, whence) @@ -1235,8 +1232,6 @@ BufferedWriter.__init__(self, raw, buffer_size, max_buffer_size) def seek(self, pos, whence=0): - if not (0 <= whence <= 2): - raise ValueError("invalid whence") self.flush() if self._read_buf: # Undo read ahead. @@ -1852,8 +1847,7 @@ self._decoder.reset() return position if whence != 0: - raise ValueError("invalid whence (%r, should be 0, 1 or 2)" % - (whence,)) + raise ValueError("unsupported whence (%r)" % (whence,)) if cookie < 0: raise ValueError("negative seek position %r" % (cookie,)) self.flush() diff -r 38df99776901 -r 0a5a40a4674a Lib/os.py --- a/Lib/os.py Tue Apr 24 21:09:17 2012 +0200 +++ b/Lib/os.py Tue Apr 24 21:47:38 2012 +0200 @@ -116,6 +116,7 @@ # Python uses fixed values for the SEEK_ constants; they are mapped # to native constants if necessary in posixmodule.c +# Other possible SEEK values are directly imported from posixmodule.c SEEK_SET = 0 SEEK_CUR = 1 SEEK_END = 2 diff -r 38df99776901 -r 0a5a40a4674a Lib/test/test_posix.py --- a/Lib/test/test_posix.py Tue Apr 24 21:09:17 2012 +0200 +++ b/Lib/test/test_posix.py Tue Apr 24 21:47:38 2012 +0200 @@ -1009,6 +1009,27 @@ posix.RTLD_GLOBAL posix.RTLD_LOCAL + @unittest.skipUnless('PC_MIN_HOLE_SIZE' in os.pathconf_names, + "test needs an OS that reports file holes") + def test_fs_holes(self) : + # Even if the filesystem doesn't report holes, + # if the OS supports it the SEEK_* constants + # will be defined and will have a consistent + # behaviour: + # os.SEEK_DATA = current position + # os.SEEK_HOLE = end of file position + fp = open(support.TESTFN, 'r+b') + fp.write(b"hello") + fp.flush() + size = fp.tell() + fno = fp.fileno() + for i in range(size) : + self.assertEqual(i, os.lseek(fno, i, os.SEEK_DATA)) + self.assertLessEqual(size, os.lseek(fno, i, os.SEEK_HOLE)) + self.assertRaises(OSError, os.lseek, fno, size, os.SEEK_DATA) + self.assertRaises(OSError, os.lseek, fno, size, os.SEEK_HOLE) + fp.close() + class PosixGroupsTester(unittest.TestCase): def setUp(self): diff -r 38df99776901 -r 0a5a40a4674a Misc/NEWS --- a/Misc/NEWS Tue Apr 24 21:09:17 2012 +0200 +++ b/Misc/NEWS Tue Apr 24 21:47:38 2012 +0200 @@ -406,6 +406,8 @@ - Issue #14212: The re module didn't retain a reference to buffers it was scanning, resulting in segfaults. +- Issue #10142: Support for SEEK_HOLE/SEEK_DATA (for example, under ZFS). + - Issue #14259: The finditer() method of re objects did not take any keyword arguments, contrary to the documentation. diff -r 38df99776901 -r 0a5a40a4674a Modules/_io/bufferedio.c --- a/Modules/_io/bufferedio.c Tue Apr 24 21:09:17 2012 +0200 +++ b/Modules/_io/bufferedio.c Tue Apr 24 21:47:38 2012 +0200 @@ -1157,9 +1157,20 @@ if (!PyArg_ParseTuple(args, "O|i:seek", &targetobj, &whence)) { return NULL; } - if (whence < 0 || whence > 2) { + + /* Do some error checking instead of trusting OS 'seek()' + ** error detection, just in case. + */ + if ((whence < 0 || whence >2) +#ifdef SEEK_HOLE + && (whence != SEEK_HOLE) +#endif +#ifdef SEEK_DATA + && (whence != SEEK_DATA) +#endif + ) { PyErr_Format(PyExc_ValueError, - "whence must be between 0 and 2, not %d", whence); + "whence value %d unsupported", whence); return NULL; } @@ -1172,7 +1183,11 @@ if (target == -1 && PyErr_Occurred()) return NULL; - if (whence != 2 && self->readable) { + /* SEEK_SET and SEEK_CUR are special because we could seek inside the + buffer. Other whence values must be managed without this optimization. + Some Operating Systems can provide additional values, like + SEEK_HOLE/SEEK_DATA. */ + if (((whence == 0) || (whence == 1)) && self->readable) { Py_off_t current, avail; /* Check if seeking leaves us inside the current buffer, so as to return quickly if possible. Also, we needn't take the diff -r 38df99776901 -r 0a5a40a4674a Modules/posixmodule.c --- a/Modules/posixmodule.c Tue Apr 24 21:09:17 2012 +0200 +++ b/Modules/posixmodule.c Tue Apr 24 21:47:38 2012 +0200 @@ -11227,6 +11227,13 @@ #endif +#ifdef SEEK_HOLE + if (ins(d, "SEEK_HOLE", (long)SEEK_HOLE)) return -1; +#endif +#ifdef SEEK_DATA + if (ins(d, "SEEK_DATA", (long)SEEK_DATA)) return -1; +#endif + /* MS Windows */ #ifdef O_NOINHERIT /* Don't inherit in child processes. */