Merge pull request #4102 from MDAnalysis/prerelease-package-2.4.3

Add necessary commits for 2.4.3

maintainer/conda/MDAnalysis/meta.yaml

@@ -1,7 +1,7 @@
 package:
   name: mdanalysis
   # This has to be changed after a release
-  version: "2.4.2"
+  version: "2.4.3"
 
 source:
    git_url: https://github.com/MDAnalysis/mdanalysis

package/CHANGELOG

@@ -13,6 +13,16 @@ The rules for this file:
   * release numbers follow "Semantic Versioning" http://semver.org
 
 ------------------------------------------------------------------------------
+03/29/23 richardjgowers, IAlibay
+
+ * 2.4.3
+
+Fixes
+  * Fixed DCD reading for large (>2Gb) files (Issue #4039).  This was broken
+    for versions 2.4.0, 2.4.1 and 2.4.2
+  * Fix element parsing from PSF files tests read via Parmed (Issue #4015)
+
+
 01/04/23 IAlibay
 
  * 2.4.2

package/MDAnalysis/lib/formats/libdcd.pxd

@@ -115,11 +115,11 @@ cdef class DCDFile:
     # The current DCD frame
     cdef int current_frame
     # size of the first DCD frame
-    cdef readonly int _firstframesize
+    cdef readonly fio_size_t _firstframesize
     # Size of a DCD frame 
-    cdef readonly int _framesize
+    cdef readonly fio_size_t _framesize
     # Size of the DCD header
-    cdef readonly int _header_size
+    cdef readonly fio_size_t _header_size
     # Is the file open?
     cdef int is_open
     # Have we reached the end of the file

package/MDAnalysis/lib/formats/libdcd.pyx

@@ -391,7 +391,9 @@ cdef class DCDFile:
         if frame == 0:
             offset = self._header_size
         else:
-            offset = self._header_size + self._firstframesize + self._framesize * (frame - 1)
+            offset = self._header_size
+            offset += self._firstframesize
+            offset += self._framesize * (frame - 1)
 
         cdef int ok = fio_fseek(self.fp, offset, _whence_vals['FIO_SEEK_SET'])
         if ok != 0:

package/MDAnalysis/version.py

@@ -67,4 +67,4 @@
 # e.g. with lib.log
 
 #: Release of MDAnalysis as a string, using `semantic versioning`_.
-__version__ = "2.4.2"  # NOTE: keep in sync with RELEASE in setup.py
+__version__ = "2.4.3"  # NOTE: keep in sync with RELEASE in setup.py

package/setup.py

@@ -67,7 +67,7 @@
 from subprocess import getoutput
 
 # NOTE: keep in sync with MDAnalysis.__version__ in version.py
-RELEASE = "2.4.2"
+RELEASE = "2.4.3"
 
 is_release = 'dev' not in RELEASE
 

testsuite/MDAnalysisTests/__init__.py

@@ -97,7 +97,7 @@
 logger = logging.getLogger("MDAnalysisTests.__init__")
 
 # keep in sync with RELEASE in setup.py
-__version__ = "2.4.2"
+__version__ = "2.4.3"
 
 
 # Do NOT import MDAnalysis at this level. Tests should do it themselves.

testsuite/MDAnalysisTests/converters/test_parmed_parser.py

@@ -119,9 +119,11 @@ class TestParmedParserPSF(BaseTestParmedParser):
     expected_n_dihedrals = 8921
     expected_n_impropers = 541
     expected_n_cmaps = 212
-    elems_ranges = ((0, 3342),)
+    elems_ranges = ((100, 120),)
     # No atomic numbers set by parmed == no elements
-    expected_elems = (np.array(['' for i in range(3341)], dtype=object),)
+    expected_elems = (np.array(
+        ['N', 'H', 'C', 'H', 'C', 'H', 'H', 'C', 'H', 'C', 'H', 'H', 'H', 'C',
+         'H', 'H', 'H', 'C', 'O', 'N',], dtype=object),)
 
     def test_bonds_atom_counts(self, universe):
         assert len(universe.atoms[[0]].bonds) == 4

testsuite/MDAnalysisTests/coordinates/test_dcd.py

@@ -20,6 +20,7 @@
 # MDAnalysis: A Toolkit for the Analysis of Molecular Dynamics Simulations.
 # J. Comput. Chem. 32 (2011), 2319--2327, doi:10.1002/jcc.21787
 #
+import os
 from pathlib import Path
 import numpy as np
 
@@ -436,3 +437,38 @@ def test_pathlib():
     # we really only care that pathlib
     # object handling worked
     assert u.atoms.n_atoms == 3341
+
+
+@pytest.fixture
+def large_dcdfile(tmpdir):
+    # creates a >2Gb DCD file
+    fsize = 3.8  # mb
+    nreps_reqs = int(2100 // fsize)  # times to duplicate traj to hit 2.1Gb
+
+    newf = str(tmpdir / "jabba.dcd")
+
+    u = mda.Universe(PSF, DCD)
+
+    with mda.Writer(newf, n_atoms=len(u.atoms)) as w:
+        for _ in range(nreps_reqs):
+            for ts in u.trajectory:
+                w.write(u.atoms)
+
+    yield newf, nreps_reqs
+
+
+@pytest.mark.skipif(
+    not os.environ.get("LARGEDCD", False), reason="Skipping large file test"
+)
+def test_large_dcdfile(large_dcdfile):
+    DCD_large, nreps = large_dcdfile
+
+    u_small = mda.Universe(PSF, DCD)
+    u = mda.Universe(PSF, DCD_large)
+
+    assert len(u.trajectory) == len(u_small.trajectory) * nreps
+
+    u_small.trajectory[-1]
+    u.trajectory[-1]
+
+    assert_array_almost_equal(u.atoms.positions, u_small.atoms.positions)

testsuite/setup.py

@@ -87,7 +87,7 @@ def run(self):
 
 if __name__ == '__main__':
     # this must be in-sync with MDAnalysis
-    RELEASE = "2.4.2"
+    RELEASE = "2.4.3"
     with open("README") as summary:
         LONG_DESCRIPTION = summary.read()