Merge pull request equinor#249 from ErlendHaa/copy-sliced-array

Copy sliced array in channel.curves()

python/dlisio/plumbing/channel.py

@@ -165,6 +165,18 @@ def curves(self):
         """
         Returns a numpy ndarray with the curves-values.
 
+        Notes
+        -----
+
+        This method should only be used if there is only *one* channel of
+        interest in a particular frame.
+
+        Due to the memory-layout of dlis-files, reading a single channel from
+        disk and reading the entire frame is almost equally fast. That means
+        reading channels from the same frame one-by-one with this method is
+        _way_ slower than reading the entire frame with :func:`Frame.curves()`
+        and then indexing on the channels-of-interest.
+
         Examples
         --------
 
@@ -203,7 +215,7 @@ def curves(self):
         -------
         curves : np.ndarray
         """
-        return self.frame.curves()[self.name]
+        return np.copy(self.frame.curves()[self.name])
 
     def describe_attr(self, buf, width, indent, exclude):
         describe_description(buf, self.long_name, width, indent, exclude)

python/docs/examples.rst

@@ -179,6 +179,11 @@ which returns a structured numpy array that support common slicing operations:
     >>> curve[0:5]
     array([852606., 852606., 852606., 852606., 852606.], dtype=float32)
 
+Note that its almost always considerably faster to read curves-data with
+:py:func:`dlisio.plumbing.Frame.curves()`. Please refer to
+:py:func:`dlisio.plumbing.Channel.curves()` for further elaboration on why this
+is.
+
 Access all curves in a frame with :py:func:`dlisio.plumbing.Frame.curves()`.
 The returned structured numpy array can be indexed by Channel mnemonics
 and/or sliced by samples:

python/tests/test_curves.py

@@ -73,6 +73,16 @@ def makeframe():
     frame.link()
     return frame
 
+def test_curves_are_copy(f):
+    # All channel.curves() really does is to slice the full frame array
+    # returned by frame.curves(). Make sure the returned slice is a copy not a
+    # view.  Returning a view makes it impossible to free up any memory from
+    # the original array, hence holding on to way more memory than needed.
+
+    channel = f.object('CHANNEL', 'CHANN1')
+    curves = channel.curves()
+    assert curves.flags['OWNDATA']
+
 def test_curves_values(f):
     frame = f.object('FRAME', 'FRAME1', 10, 0)
     curves = frame.curves()