Changeset 088760e for python/lib/aubio/slicing.py

Timestamp:

Oct 31, 2018, 10:26:52 PM (5 years ago)

Author:

Paul Brossier <piem@piem.org>

Branches:

feature/constantq

Children:

c03d191

Parents:

45c2c5c (diff), 7a54b37 (diff)
Note: this is a merge changeset, the changes displayed below correspond to the merge itself.
Use the (diff) links above to see all the changes relative to each parent.

Message:

Merge branch 'master' into feature/constantq

File:

• python/lib/aubio/slicing.py (modified) (5 diffs)

python/lib/aubio/slicing.py

@@ -7 +7 @@
 
 def slice_source_at_stamps(source_file, timestamps, timestamps_end=None,
-                           output_dir=None, samplerate=0, hopsize=256):
-    """ slice a sound file at given timestamps """
+                           output_dir=None, samplerate=0, hopsize=256,
+                           create_first=False):
+    """Slice a sound file at given timestamps.
+
+    This function reads `source_file` and creates slices, new smaller
+    files each starting at `t` in `timestamps`, a list of integer
+    corresponding to time locations in `source_file`, in samples.
+
+    If `timestamps_end` is unspecified, the slices will end at
+    `timestamps_end[n] = timestamps[n+1]-1`, or the end of file.
+    Otherwise, `timestamps_end` should be a list with the same length
+    as `timestamps` containing the locations of the end of each slice.
+
+    If `output_dir` is unspecified, the new slices will be written in
+    the current directory. If `output_dir` is a string, new slices
+    will be written in `output_dir`, after creating the directory if
+    required.
+
+    The default `samplerate` is 0, meaning the original sampling rate
+    of `source_file` will be used. When using a sampling rate
+    different to the one of the original files, `timestamps` and
+    `timestamps_end` should be expressed in the re-sampled signal.
+
+    The `hopsize` parameter simply tells :class:`source` to use this
+    hopsize and does not change the output slices.
+
+    If `create_first` is True and `timestamps` does not start with `0`, the
+    first slice from `0` to `timestamps[0] - 1` will be automatically added.
+
+    Parameters
+    ----------
+    source_file : str
+        path of the resource to slice
+    timestamps : :obj:`list` of :obj:`int`
+        time stamps at which to slice, in samples
+    timestamps_end : :obj:`list` of :obj:`int` (optional)
+        time stamps at which to end the slices
+    output_dir : str (optional)
+        output directory to write the slices to
+    samplerate : int (optional)
+        samplerate to read the file at
+    hopsize : int (optional)
+        number of samples read from source per iteration
+    create_first : bool (optional)
+        always create the slice at the start of the file
+
+    Examples
+    --------
+    Create two slices: the first slice starts at the beginning of the
+    input file `loop.wav` and lasts exactly one second, starting at
+    sample `0` and ending at sample `44099`; the second slice starts
+    at sample `44100` and lasts until the end of the input file:
+
+    >>> aubio.slice_source_at_stamps('loop.wav', [0, 44100])
+
+    Create one slice, from 1 second to 2 seconds:
+
+    >>> aubio.slice_source_at_stamps('loop.wav', [44100], [44100 * 2 - 1])
+
+    Notes
+    -----
+    Slices may be overlapping. If `timestamps_end` is `1` element
+    shorter than `timestamps`, the last slice will end at the end of
+    the file.
+    """
 
     if timestamps is None or len(timestamps) == 0:
         raise ValueError("no timestamps given")
 
-    if timestamps[0] != 0:
+    if timestamps[0] != 0 and create_first:
         timestamps = [0] + timestamps
         if timestamps_end is not None:
@@ -19 +82 @@
 
     if timestamps_end is not None:
-        if len(timestamps_end) != len(timestamps):
+        if len(timestamps_end) == len(timestamps) - 1:
+            timestamps_end = timestamps_end + [_max_timestamp]
+        elif len(timestamps_end) != len(timestamps):
             raise ValueError("len(timestamps_end) != len(timestamps)")
     else:
@@ -49 +114 @@
         vec, read = _source.do_multi()
         # if the total number of frames read will exceed the next region start
-        if len(regions) and total_frames + read >= regions[0][0]:
+        while len(regions) and total_frames + read >= regions[0][0]:
             #print "getting", regions[0], "at", total_frames
             # get next region
@@ -76 +141 @@
                     # write remaining samples from current region
                     _sink.do_multi(vec[:, start:remaining], remaining - start)
-                    #print "closing region", "remaining", remaining
+                    #print("closing region", "remaining", remaining)
                     # close this file
                     _sink.close()
@@ -83 +148 @@
                 _sink.do_multi(vec[:, start:read], read - start)
         total_frames += read
+        # remove old slices
+        slices = list(filter(lambda s: s['end_stamp'] > total_frames,
+            slices))
         if read < hopsize:
             break