Close #10142: Support for SEEK_HOLE/SEEK_DATA

diff --git a/Doc/library/io.rst b/Doc/library/io.rst
index 4d564bb3f9011d3cc95f0ca642bfd8c92252d9c4..ff4dc7578cb2fa8ef478cafc2e1f6bc95a5c4e9c 100644 (file)
--- a/Doc/library/io.rst
+++ b/Doc/library/io.rst
@@ -291,6 +291,11 @@ I/O Base Classes
       .. 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 --git a/Doc/library/os.rst b/Doc/library/os.rst
index 14f9e07edcb5bbcfea4eab2a5d95e56f4a8418a2..a43b43476f5737f9b5f8bab7c4fee9e171e88187 100644 (file)
--- a/Doc/library/os.rst
+++ b/Doc/library/os.rst
@@ -992,6 +992,10 @@ as internal buffering of data.
    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 --git a/Lib/_pyio.py b/Lib/_pyio.py
index f66290fa51aa5345efbbeca908fbe1b70ca6336c..41402b1452707ea538c37d6d36cad1d589a3f387 100644 (file)
--- a/Lib/_pyio.py
+++ b/Lib/_pyio.py
@@ -306,6 +306,7 @@ class IOBase(metaclass=abc.ABCMeta):
         * 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 @@ class BytesIO(BufferedIOBase):
         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 @@ class BufferedReader(_BufferedIOMixin):
         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 @@ class BufferedWriter(_BufferedIOMixin):
         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 @@ class BufferedRandom(BufferedWriter, BufferedReader):
         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 @@ class TextIOWrapper(TextIOBase):
                 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 --git a/Lib/os.py b/Lib/os.py
index 2c7d9548646c1bf91c070470a5756d86f06a4d14..2403f30c2f432fa55cd59ee89574877e1d442d99 100644 (file)
--- a/Lib/os.py
+++ b/Lib/os.py
@@ -116,6 +116,7 @@ del _names
 
 # 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 --git a/Lib/test/test_posix.py b/Lib/test/test_posix.py
index 142dddd09b6238e4a304a7f5c393c62c627cddb6..c8798a9a93b9326152e5890d3ec8c8a0a9743bf2 100644 (file)
--- a/Lib/test/test_posix.py
+++ b/Lib/test/test_posix.py
@@ -1009,6 +1009,26 @@ class PosixTester(unittest.TestCase):
         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
+        with open(support.TESTFN, 'r+b') as fp :
+            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)
+
 class PosixGroupsTester(unittest.TestCase):
 
     def setUp(self):

diff --git a/Misc/NEWS b/Misc/NEWS
index 21cead03115350320d6f812ed4d317bbdadd897a..d45bb2021b9b44e3de2b2bbfeb59a6baceaea184 100644 (file)
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -423,6 +423,8 @@ Extension Modules
 - Issue #14259: The finditer() method of re objects did not take any
   keyword arguments, contrary to the documentation.
 
+- Issue #10142: Support for SEEK_HOLE/SEEK_DATA (for example, under ZFS).
+
 Tests
 -----
 

diff --git a/Modules/_io/bufferedio.c b/Modules/_io/bufferedio.c
index 8a9ae4704e45539cfafab68aa7554c368ae0d7cd..dc723b1793673998df4cf6fcc4bd74c4d965339c 100644 (file)
--- a/Modules/_io/bufferedio.c
+++ b/Modules/_io/bufferedio.c
@@ -1157,9 +1157,20 @@ buffered_seek(buffered *self, PyObject *args)
     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 @@ buffered_seek(buffered *self, PyObject *args)
     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 --git a/Modules/posixmodule.c b/Modules/posixmodule.c
index 92a627745851b7240ddbc65454a4409006ba080a..8254f81d81088721410bdf170ed4c21f4c86b887 100644 (file)
--- a/Modules/posixmodule.c
+++ b/Modules/posixmodule.c
@@ -11227,6 +11227,13 @@ all_ins(PyObject *d)
 #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. */