fix GaussianOutput bug with multiple route lines (#2937)

* fix GaussianOutput bug when multiple completed lines in route parameters * fix GaussianOutput bug delete only one space at the start of line * zip test_files/molecules/EC.log * rename var, tweak doc str --------- Co-authored-by: Janosh Riebesell <[email protected]>
materialsproject · Apr 27, 2023 · 51280b9 · 51280b9
1 parent 33b3195
commit 51280b9
Show file tree

Hide file tree

Showing 3 changed files with 24 additions and 2 deletions.
diff --git a/pymatgen/io/gaussian.py b/pymatgen/io/gaussian.py
@@ -824,7 +824,7 @@ def _parse(self, filename):
         geom_orientation = None
         opt_structures = []
 
-        with zopen(filename) as f:
+        with zopen(filename, mode="rt") as f:
             for line in f:
                 if parse_stage == 0:
                     if start_patt.search(line):
@@ -842,7 +842,8 @@ def _parse(self, filename):
                             self.dieze_tag = params[3]
                             parse_stage = 1
                         else:
-                            routeline += line.strip()
+                            line = line.replace(" ", "", 1).rstrip("\n")
+                            routeline += line
                 elif parse_stage == 1:
                     if set(line.strip()) == {"-"} and self.title is None:
                         self.title = ""

diff --git a/pymatgen/io/tests/test_gaussian.py b/pymatgen/io/tests/test_gaussian.py
@@ -457,6 +457,27 @@ def test_multiple_parameters(self):
         assert gout.charge == 0
         assert gout.spin_multiplicity == 1
 
+    def test_multiple_parameters_with_multiple_completed_lines(self):
+        """
+        This test makes sure that input files with multi-parameter keywords
+        and route cards with multiple completed lines which are split by line break parse correctly.
+        """
+        filepath = os.path.join(test_dir, "EC.log.gz")
+        route_params = {
+            "opt": {"loose": None, "maxcyc": "400"},
+            "freq": None,
+            "SCRF": "(SMD,READ)",
+            "EmpiricalDispersion": "GD3BJ",
+        }
+        gout = GaussianOutput(filepath)
+        assert gout.dieze_tag == "#N"
+        assert gout.functional == "B3LYP"
+        assert gout.basis_set == "6-311++G(2d,p)"
+        assert gout.route_parameters == route_params
+        assert gout.title == "H4 C3 O3"
+        assert gout.charge == 0
+        assert gout.spin_multiplicity == 1
+
 
 if __name__ == "__main__":
     unittest.main()
diff --git a/test_files/molecules/EC.log.gz b/test_files/molecules/EC.log.gz