mol2 bugfix for #2318

package/AUTHORS

@@ -121,6 +121,7 @@ Chronological list of authors
   - Yibo Zhang
   - Luís Pedro Borges Araújo
   - Abhishek A. Kognole
+  - Rocco Meli
 
 External code
 -------------

package/CHANGELOG

@@ -16,7 +16,7 @@ The rules for this file:
 mm/dd/yy micaela-matta, xiki-tempula, zemanj, mattwthompson, orbeckst, aliehlen,
          dpadula85, jbarnoud, manuel.nuno.melo, richardjgowers, mattwthompson,
          ayushsuhane, picocentauri, NinadBhat, bieniekmateusz, p-j-smith, Lp0lp,
-         IAlibay, tyler.je.reddy, aakognole
+         IAlibay, tyler.je.reddy, aakognole, RMeli
 
   * 0.20.0
 
@@ -76,6 +76,7 @@ Changes
 Fixes
   * fixes ProgressMeter issues with older Jupyter Lab versions (Issue #2078)
   * fixes ProgressMeter behaviour for non-AnalysisBase methods (Issue #2084)
+  * fixed mol2 parser for status bit strings (Issue #2318)
   * fixed reading AMBER topologies with negative ATOMIC_NUMBERS (Issue #2306)
   * fixed reading bz2 compressed psf files (Issue #2232)
   * fixed mol2 comment header handling (Issue #2261)

package/MDAnalysis/coordinates/MOL2.py

@@ -129,6 +129,7 @@ class MOL2Reader(base.ReaderBase):
        previously created a new instance of Timestep each frame.
     .. versionchanged:: 0.20.0
        Allows for comments at top of file.
+       Ignores status bit strings
     """
     format = 'MOL2'
     units = {'time': None, 'length': 'Angstrom'}
@@ -197,7 +198,8 @@ def parse_block(self, block):
 
         coords = np.zeros((self.n_atoms, 3), dtype=np.float32)
         for i, a in enumerate(atom_lines):
-            aid, name, x, y, z, atom_type, resid, resname, charge = a.split()
+            aid, name, x, y, z, atom_type, resid, resname, charge = a.split()[:9]
+
             #x, y, z = float(x), float(y), float(z)
             coords[i, :] = x, y, z
 

package/MDAnalysis/topology/MOL2Parser.py

@@ -83,6 +83,7 @@ class MOL2Parser(TopologyReaderBase):
        Now subclasses TopologyReaderBase
     .. versionchanged:: 0.20.0
        Allows for comments at the top of the file
+       Ignores status bit strings
     """
     format = 'MOL2'
 
@@ -139,7 +140,8 @@ def parse(self, **kwargs):
         charges = []
 
         for a in atom_lines:
-            aid, name, x, y, z, atom_type, resid, resname, charge = a.split()
+            aid, name, x, y, z, atom_type, resid, resname, charge = a.split()[:9]
+
             ids.append(aid)
             names.append(name)
             types.append(atom_type)
@@ -174,7 +176,8 @@ def parse(self, **kwargs):
         bondorder = []
         for b in bond_lines:
             # bond_type can be: 1, 2, am, ar
-            bid, a0, a1, bond_type = b.split()
+            bid, a0, a1, bond_type = b.split()[:4]
+
             a0, a1 = int(a0) - 1, int(a1) - 1
             bond = tuple(sorted([a0, a1]))
             bondorder.append(bond_type)

testsuite/MDAnalysisTests/coordinates/test_mol2.py

@@ -33,7 +33,7 @@
 
 from MDAnalysisTests.datafiles import (
     mol2_molecules, mol2_molecule, mol2_broken_molecule,
-    mol2_zinc, mol2_comments_header
+    mol2_zinc, mol2_comments_header, mol2_ligand
 )
 from MDAnalysis import Universe
 import MDAnalysis as mda
@@ -56,6 +56,11 @@ def test_read(self):
         u.trajectory[199]
         assert_array_almost_equal(u.atoms.positions[0], [1.7240, 11.2730, 14.1200])
 
+    def test_read_statusbit(self):
+        u = Universe(mol2_ligand)
+        assert_equal(len(u.atoms), 297)
+        assert_equal(u.trajectory.n_frames, 1)
+
     def test_write(self):
         ref = Universe(mol2_molecules)
         ref.atoms.write(self.outfile)

testsuite/MDAnalysisTests/datafiles.py

@@ -115,7 +115,7 @@
     "TRR_multi_frame",
     "merge_protein", "merge_ligand", "merge_water",
     "mol2_molecules", "mol2_molecule", "mol2_broken_molecule",
-    "mol2_zinc", "mol2_comments_header",
+    "mol2_zinc", "mol2_comments_header", "mol2_ligand",
     "capping_input", "capping_output", "capping_ace", "capping_nma",
     "contacts_villin_folded", "contacts_villin_unfolded", "contacts_file",
     "LAMMPSdata", "trz4data", "LAMMPSdata_mini",
@@ -383,6 +383,7 @@
 
 mol2_molecules = resource_filename(__name__, "data/mol2/Molecules.mol2")
 mol2_molecule = resource_filename(__name__, "data/mol2/Molecule.mol2")
+mol2_ligand = resource_filename(__name__, "data/mol2/Ligand.mol2")
 mol2_broken_molecule = resource_filename(__name__, "data/mol2/BrokenMolecule.mol2")
 mol2_comments_header = resource_filename(__name__, "data/mol2/Molecule_comments_header.mol2")
 # MOL2 file without substructure field