Writes compressed output of given format

.travis.yml

@@ -50,10 +50,11 @@ matrix:
     - env: NAME="Doc"
            MAIN_CMD="cd package && python setup.py"
            SETUP_CMD="build_sphinx"
+           PYTHON_VERSION=3.7
            BUILD_DOCS=true
            BUILD_CMD="cd ${TRAVIS_BUILD_DIR}/package && python setup.py build_ext --inplace"
            INSTALL_HOLE="false"
-           PIP_DEPENDENCIES="${PIP_DEPENDENCIES} sphinx-sitemap"
+           PIP_DEPENDENCIES="${PIP_DEPENDENCIES} sphinx==1.8.5 sphinx-sitemap"
 
     - env: NAME="Lint"
            PYLINTRC="${TRAVIS_BUILD_DIR}/package/.pylintrc"

package/AUTHORS

@@ -117,6 +117,7 @@ Chronological list of authors
   - Daniele Padula
 2019
   - Ninad Bhat
+  - Fenil Suchak
 
 External code
 -------------

package/CHANGELOG

@@ -49,6 +49,8 @@ Enhancements
     distance_array. (Issue #2103, PR #2209)
   * updated analysis.distances.contact_matrix to use capped_distance. (Issue #2102,
     PR #2215)
+  * added functionality to write files in compressed form(gz,bz2). (Issue #2216,
+    PR #2221)
 
 Changes
   * added official support for Python 3.7 (PR #1963)
@@ -91,6 +93,8 @@ Fixes
   * Fixed documentation of MDAnalysis.analysis.contacts
   * Enforced consistent dtype (numpy.float32) of Universe.dimensions and
     Timestep.dimensions for all Universes and Readers (Issue #2190, PR #2213)
+  * Fixed analysis.nucleic.hydroxyl() function: correctly recognize the
+    2'-hydroxyl hydrogen H2'; gave wrong results (Issue #2218)
 
 Deprecations
   * analysis.polymer.PersistenceLength no longer requires the perform_fit()

package/MDAnalysis/analysis/nuclinfo.py

@@ -704,10 +704,10 @@ def hydroxyl(universe, seg, i):
     .. versionadded:: 0.7.6
 
     """
-    h = universe.select_atoms(" atom {0!s} {1!s} C1\' ".format(seg, i),
-                              " atom {0!s} {1!s} C2\' ".format(seg, i),
-                              " atom {0!s} {1!s} O2\' ".format(seg, i),
-                              " atom {0!s} {1!s} H2\'\' ".format(seg, i))
+    h = universe.select_atoms("atom {0!s} {1!s} C1'".format(seg, i),
+                              "atom {0!s} {1!s} C2'".format(seg, i),
+                              "atom {0!s} {1!s} O2'".format(seg, i),
+                              "atom {0!s} {1!s} H2'".format(seg, i))
     try:
         hydr = h.dihedral.value() % 360
     except ValueError:

package/MDAnalysis/coordinates/GRO.py

@@ -326,7 +326,7 @@ def __init__(self, filename, convert_units=None, n_atoms=None, **kwargs):
                w.write(u.atoms)
 
         """
-        self.filename = util.filename(filename, ext='gro')
+        self.filename = util.filename(filename, ext='gro', keep=True)
         self.n_atoms = n_atoms
         self.reindex = kwargs.pop('reindex', True)
 

package/MDAnalysis/core/groups.py

@@ -2975,7 +2975,7 @@ def improper(self):
                 "improper only makes sense for a group with exactly 4 atoms")
         return topologyobjects.ImproperDihedral(self.ix, self.universe)
 
-    def write(self, filename=None, file_format="PDB",
+    def write(self, filename=None, file_format=None,
               filenamefmt="{trjname}_{frame}", frames=None, **kwargs):
         """Write `AtomGroup` to a file.
 
@@ -3054,8 +3054,9 @@ def write(self, filename=None, file_format="PDB",
         if filename is None:
             trjname, ext = os.path.splitext(os.path.basename(trj.filename))
             filename = filenamefmt.format(trjname=trjname, frame=trj.frame)
-        filename = util.filename(filename, ext=file_format.lower(), keep=True)
-
+        filename = util.filename(filename,
+                                 ext=file_format if file_format is not None else 'PDB',
+                                 keep=True)
         # Some writer behave differently when they are given a "multiframe"
         # argument. It is the case of the PDB writer tht writes models when
         # "multiframe" is True.
@@ -3080,14 +3081,7 @@ def write(self, filename=None, file_format="PDB",
         # Try and select a Class using get_ methods (becomes `writer`)
         # Once (and if!) class is selected, use it in with block
         try:
-            # format keyword works differently in get_writer and get_selection_writer
-            # here it overrides everything, in get_sel it is just a default
-            # apply sparingly here!
-            format = os.path.splitext(filename)[1][1:]  # strip initial dot!
-            format = format or file_format
-            format = format.strip().upper()
-
-            writer = get_writer_for(filename, format=format, multiframe=multiframe)
+            writer = get_writer_for(filename, format=file_format, multiframe=multiframe)
         except (ValueError, TypeError):
             pass
         else:
@@ -3106,7 +3100,8 @@ def write(self, filename=None, file_format="PDB",
         try:
             # here `file_format` is only used as default,
             # anything pulled off `filename` will be used preferentially
-            writer = get_selection_writer_for(filename, file_format)
+            writer = get_selection_writer_for(filename,
+                                              file_format if file_format is not None else 'PDB')
         except (TypeError, NotImplementedError):
             pass
         else:

package/MDAnalysis/lib/util.py

@@ -249,6 +249,7 @@ def filename(name, ext=None, keep=False):
        Also permits :class:`NamedStream` to pass through.
     """
     if ext is not None:
+        ext = ext.lower()
         if not ext.startswith(os.path.extsep):
             ext = os.path.extsep + ext
         root, origext = os.path.splitext(name)

testsuite/MDAnalysisTests/analysis/test_nuclinfo.py

@@ -25,7 +25,7 @@
 import MDAnalysis as mda
 import pytest
 from MDAnalysis.analysis import nuclinfo
-from MDAnalysisTests.datafiles import NUCL
+from MDAnalysisTests.datafiles import RNA_PSF, RNA_PDB
 from numpy.testing import (
     assert_almost_equal,
     assert_allclose,
@@ -34,140 +34,144 @@
 
 @pytest.fixture(scope='module')
 def u():
-    return mda.Universe(NUCL)
+    return mda.Universe(RNA_PSF, RNA_PDB)
 
 
 @pytest.mark.parametrize('i, bp, seg1, seg2, expected_value', (
-        (1, 2, 'RNAA', 'RNAA', 4.449),
-        (22, 23, 'RNAA', 'RNAA', 4.601)
+    ( 1,  2, 'RNAA', 'RNAA', 4.3874702),
+    (22, 23, 'RNAA', 'RNAA', 4.1716404),
 ))
 def test_wc_pair(u, i, bp, seg1, seg2, expected_value):
     val = nuclinfo.wc_pair(u, i, bp, seg1=seg1, seg2=seg2)
     assert_almost_equal(val, expected_value, decimal=3)
 
 
 @pytest.mark.parametrize('i, bp, seg1, seg2, expected_value', (
-        (3, 17, 'RNAA', 'RNAA', 16.649),
-        (20, 5, 'RNAA', 'RNAA', 4.356)
+    ( 3, 17, 'RNAA', 'RNAA', 15.06506),
+    (20,  5, 'RNAA', 'RNAA', 3.219116),
 ))
 def test_minor_pair(u, i, bp, seg1, seg2, expected_value):
     val = nuclinfo.minor_pair(u, i, bp, seg1=seg1, seg2=seg2)
     assert_almost_equal(val, expected_value, decimal=3)
 
 
 @pytest.mark.parametrize('i, bp, seg1, seg2, expected_value', (
-        (2, 12, 'RNAA', 'RNAA', 30.001),
-        (5, 9, 'RNAA', 'RNAA', 12.581)
+    (2, 12, 'RNAA', 'RNAA', 26.884272),
+    (5,  9, 'RNAA', 'RNAA', 13.578535),
 ))
 def test_major_pair(u, i, bp, seg1, seg2, expected_value):
     val = nuclinfo.major_pair(u, i, bp, seg1=seg1, seg2=seg2)
     assert_almost_equal(val, expected_value, decimal=3)
 
 
 @pytest.mark.parametrize('seg, i, expected_value', (
-        ('RNAA', 9, 14.846),
-        ('RNAA', 21, 16.199)
+    ('RNAA',  9,  3.16497),
+    ('RNAA', 21, 22.07721),
 ))
 def test_phase_cp(u, seg, i, expected_value):
     val = nuclinfo.phase_cp(u, seg=seg, i=i)
     assert_almost_equal(val, expected_value, decimal=3)
 
 
 @pytest.mark.parametrize('seg, i, expected_value', (
-        ('RNAA', 1, 8.565),
-        ('RNAA', 11, 151.397)
+    ('RNAA',  1, 359.57580),
+    ('RNAA', 11, 171.71645),
 ))
 def test_phase_as(u, seg, i, expected_value):
     val = nuclinfo.phase_as(u, seg=seg, i=i)
     assert_almost_equal(val, expected_value, decimal=3)
 
 
 @pytest.mark.parametrize('seg, i, expected_value', (
-        ('RNAA', 5, [296.103016, 179.084427, 47.712818, 81.49588, 205.350479,
-                     284.046562, 198.58165]),
-        ('RNAA', 21, [300.047634, 172.476593, 50.744877, 82.144211, 206.106445,
-                      286.208565, 195.652176])
+    ('RNAA', 5, [302.203802, 179.043077,  35.271411,  79.499729, 201.000393,
+                 282.14321 , 210.709327]),
+    ('RNAA', 21, [280.388619, 185.12919 ,  56.616215,  64.87354 , 187.153367,
+                  279.340915, 215.332144]),
 ))
 def test_tors(u, seg, i, expected_value):
     val = nuclinfo.tors(u, seg=seg, i=i)
     assert_allclose(val, expected_value, rtol=1e-03)
 
 
 @pytest.mark.parametrize('seg, i, expected_value', (
-        ('RNAA', 6, 299.278),
-        ('RNAA', 18, 304.093)
+    ('RNAA',  6, 279.15103),
+    ('RNAA', 18, 298.09936),
 ))
 def test_tors_alpha(u, seg, i, expected_value):
     val = nuclinfo.tors_alpha(u, seg=seg, i=i)
     assert_almost_equal(val, expected_value, decimal=3)
 
 
 @pytest.mark.parametrize('seg, i, expected_value', (
-        ('RNAA', 7, 177.041),
-        ('RNAA', 15, 162.441)
+    ('RNAA',  7, 184.20501),
+    ('RNAA', 15, 169.70042),
 ))
 def test_tors_beta(u, seg, i, expected_value):
     val = nuclinfo.tors_beta(u, seg=seg, i=i)
     assert_almost_equal(val, expected_value, decimal=3)
 
 
 @pytest.mark.parametrize('seg, i, expected_value', (
-        ('RNAA', 7, 47.201),
-        ('RNAA', 15, 64.276)
+    ('RNAA',  7, 52.72022),
+    ('RNAA', 15, 54.59684),
 ))
 def test_tors_gamma(u, seg, i, expected_value):
     val = nuclinfo.tors_gamma(u, seg=seg, i=i)
     assert_almost_equal(val, expected_value, decimal=3)
 
 
 @pytest.mark.parametrize('seg, i, expected_value', (
-        ('RNAA', 7, 80.223),
-        ('RNAA', 15, 81.553)
+    ('RNAA',  7, 84.80554),
+    ('RNAA', 15, 82.00043),
 ))
 def test_tors_delta(u, seg, i, expected_value):
     val = nuclinfo.tors_delta(u, seg=seg, i=i)
     assert_almost_equal(val, expected_value, decimal=3)
 
 
 @pytest.mark.parametrize('seg, i, expected_value', (
-        ('RNAA', 7, 207.476),
-        ('RNAA', 15, 202.352)
+    ('RNAA',  7, 200.40990),
+    ('RNAA', 15, 210.96953),
 ))
 def test_tors_eps(u, seg, i, expected_value):
     val = nuclinfo.tors_eps(u, seg=seg, i=i)
     assert_almost_equal(val, expected_value, decimal=3)
 
 
 @pytest.mark.parametrize('seg, i, expected_value', (
-        ('RNAA', 7, 289.429),
-        ('RNAA', 15, 289.318)
+        ('RNAA',  7, 297.84736),
+        ('RNAA', 15, 330.24898)
 ))
 def test_tors_zeta(u, seg, i, expected_value):
     val = nuclinfo.tors_zeta(u, seg=seg, i=i)
     assert_almost_equal(val, expected_value, decimal=3)
 
 
 @pytest.mark.parametrize('seg, i, expected_value', (
-        ('RNAA', 1, 198.601),
-        ('RNAA', 2, 198.932)
+        ('RNAA',  1, 177.12643),
+        ('RNAA',  2, 212.08998),
+        ('RNAA',  7, 209.56533),
+        ('RNAA', 15, 209.32109),
 ))
 def test_tors_chi(u, seg, i, expected_value):
     val = nuclinfo.tors_chi(u, seg=seg, i=i)
     assert_almost_equal(val, expected_value, decimal=3)
 
 
 @pytest.mark.parametrize('seg, i, expected_value', (
-        ('RNAA', 20, 122.689),
-        ('RNAA', 5, 122.965)
+        ('RNAA', 20, 103.07024),
+        ('RNAA',  5, 156.62223),
+        ('RNAA',  7 , 77.94538),
+        ('RNAA', 15, 130.18539),
 ))
 def test_hydroxyl(u, seg, i, expected_value):
     val = nuclinfo.hydroxyl(u, seg=seg, i=i)
     assert_almost_equal(val, expected_value, decimal=3)
 
 
 @pytest.mark.parametrize('bp1, bp2, i, seg1, seg2, seg3, expected_value', (
-        (16, 2, 3, 'RNAA', 'RNAA', 'RNAA', 308.244),
-        (8, 9, 10, 'RNAA', 'RNAA', 'RNAA', 25.224),
+        (16, 2, 3, 'RNAA', 'RNAA', 'RNAA', 314.69804),
+        (8, 9, 10, 'RNAA', 'RNAA', 'RNAA', 34.50106),
 ))
 def test_pseudo_dihe_baseflip(u, bp1, bp2, i, seg1, seg2, seg3, expected_value):
     val = nuclinfo.pseudo_dihe_baseflip(u, bp1, bp2, i, seg1, seg2, seg3)

testsuite/MDAnalysisTests/core/test_atomgroup.py

@@ -156,7 +156,7 @@ def test_write_frame_iterator(self, u, tmpdir, frames):
 
         assert_array_almost_equal(new_positions, ref_positions)
 
-    @pytest.mark.parametrize('extension', ('xtc', 'dcd', 'pdb', 'xyz'))
+    @pytest.mark.parametrize('extension', ('xtc', 'dcd', 'pdb', 'xyz', 'PDB'))
     def test_write_frame_none(self, u, tmpdir, extension):
         destination = str(tmpdir / 'test.' + extension)
         u.atoms.write(destination, frames=None)
@@ -167,6 +167,26 @@ def test_write_frame_none(self, u, tmpdir, extension):
             u.atoms.positions[None, ...], new_positions, decimal=2
         )
 
+    @pytest.mark.parametrize('extension', ('xtc', 'dcd', 'pdb', 'xyz', 'PDB'))
+    def test_compressed_write_frame_none(self, u, tmpdir, extension):
+        for ext in ('.gz', '.bz2'):
+            destination = str(tmpdir / 'test.' + extension + ext)
+            u.atoms.write(destination, frames=None)
+            u_new = mda.Universe(destination)
+            new_positions = np.stack([ts.positions for ts in u_new.trajectory])
+            assert_array_almost_equal(
+                u.atoms.positions[None, ...], new_positions, decimal=2
+        )
+
+    def test_compressed_write_frames_all(self, u, tmpdir):
+        for ext in ('.gz', '.bz2'):
+            destination = str(tmpdir / 'test.dcd') + ext
+            u.atoms.write(destination, frames='all')
+            u_new = mda.Universe(destination)
+            ref_positions = np.stack([ts.positions for ts in u.trajectory])
+            new_positions = np.stack([ts.positions for ts in u_new.trajectory])
+            assert_array_almost_equal(new_positions, ref_positions)
+
     def test_write_frames_all(self, u, tmpdir):
         destination = str(tmpdir / 'test.dcd')
         u.atoms.write(destination, frames='all')
@@ -238,6 +258,16 @@ def test_write_atoms(self, universe, outfile):
             err_msg=("atom coordinate mismatch between original and {0!s} file"
                      "".format(self.ext)))
 
+    def test_compressed_write_atoms(self, universe, outfile):
+        for compressed_ext in ('.gz', '.bz2'):
+            universe.atoms.write(outfile + compressed_ext)
+            u2 = self.universe_from_tmp(outfile + compressed_ext)
+            assert_almost_equal(
+                universe.atoms.positions, u2.atoms.positions,
+                self.precision,
+                err_msg=("atom coordinate mismatch between original and {0!s} file"
+                        "".format(self.ext)))
+
     def test_write_empty_atomgroup(self, universe, outfile):
         sel = universe.select_atoms('name doesntexist')
         with pytest.raises(IndexError):

testsuite/MDAnalysisTests/core/test_atomselections.py

@@ -42,7 +42,7 @@
     PSF, DCD,
     PRMpbc, TRJpbc_bz2,
     PSF_NAMD, PDB_NAMD,
-    GRO, NUCL, NUCLsel, TPR, XTC,
+    GRO, RNA_PSF, NUCLsel, TPR, XTC,
     TRZ_psf, TRZ,
     PDB_icodes,
     PDB_HOLE,
@@ -449,20 +449,22 @@ def test_molnum(self, universe, selection_string, reference):
 
 
 class TestSelectionsNucleicAcids(object):
-    @pytest.fixture()
+    @pytest.fixture(scope='class')
     def universe(self):
-        return MDAnalysis.Universe(NUCL)
+        return MDAnalysis.Universe(RNA_PSF)
+
+    @pytest.fixture(scope='class')
+    def universe2(self):
+        return MDAnalysis.Universe(NUCLsel)
+
 
     def test_nucleic(self, universe):
         rna = universe.select_atoms("nucleic")
         assert_equal(rna.n_atoms, 739)
         assert_equal(rna.n_residues, 23)
 
-    def test_nucleic_all(self, universe):
-        u = mda.Universe(NUCLsel)
-
-        sel = u.select_atoms('nucleic')
-
+    def test_nucleic_all(self, universe2):
+        sel = universe2.select_atoms('nucleic')
         assert len(sel) == 34
 
     def test_nucleicbackbone(self, universe):