From 31bb38ecce5580c9253476a2e91b51ae6b55acf0 Mon Sep 17 00:00:00 2001
From: SimonBoothroyd <simon.boothroyd@hotmail.com>
Date: Wed, 22 Dec 2021 11:07:19 +0000
Subject: [PATCH] Handle uncaught exceptions when filtering (#32)

---
 .lgtm.yml                  |  2 ++
 nagl/cli/prepare/filter.py | 67 +++++++++++++++++++++++---------------
 nagl/labelling.py          |  2 +-
 3 files changed, 43 insertions(+), 28 deletions(-)

diff --git a/.lgtm.yml b/.lgtm.yml
index 0574bb7..87b1364 100644
--- a/.lgtm.yml
+++ b/.lgtm.yml
@@ -10,3 +10,5 @@ path_classifiers:
     - devtools/*
   generated:
     - nagl/_version.py
+queries:
+  - exclude: py/catch-base-exception
diff --git a/nagl/cli/prepare/filter.py b/nagl/cli/prepare/filter.py
index 6bfb01a..50521c5 100644
--- a/nagl/cli/prepare/filter.py
+++ b/nagl/cli/prepare/filter.py
@@ -1,4 +1,5 @@
 import functools
+import logging
 from multiprocessing import Pool
 from typing import TYPE_CHECKING, Tuple
 
@@ -16,38 +17,50 @@
 if TYPE_CHECKING:
     from openff.toolkit.topology import Molecule
 
+_logger = logging.getLogger(__name__)
+
 
 def apply_filter(molecule: "Molecule", retain_largest: bool) -> Tuple["Molecule", bool]:
 
     with capture_toolkit_warnings():
 
-        from openff.toolkit.topology import Molecule
-        from simtk import unit as simtk_unit
-
-        split_smiles = molecule.to_smiles().split(".")
-        n_sub_molecules = len(split_smiles)
-
-        if retain_largest and n_sub_molecules > 1:
-
-            largest_smiles = max(split_smiles, key=len)
-            molecule = Molecule.from_smiles(largest_smiles, allow_undefined_stereo=True)
-
-        # Retain H, C, N, O, F, P, S, Cl, Br, I
-        allowed_elements = [1, 6, 7, 8, 9, 15, 16, 17, 35, 53]
-
-        mass = sum(
-            atom.mass.value_in_unit(simtk_unit.gram / simtk_unit.mole)
-            for atom in molecule.atoms
-        )
-
-        return (
-            molecule,
-            (
-                all(atom.atomic_number in allowed_elements for atom in molecule.atoms)
-                and (250.0 < mass < 350.0)
-                and (len(molecule.find_rotatable_bonds()) <= 7)
-            ),
-        )
+        try:
+            from openff.toolkit.topology import Molecule
+            from simtk import unit as simtk_unit
+
+            split_smiles = molecule.to_smiles().split(".")
+            n_sub_molecules = len(split_smiles)
+
+            if retain_largest and n_sub_molecules > 1:
+
+                largest_smiles = max(split_smiles, key=len)
+                molecule = Molecule.from_smiles(
+                    largest_smiles, allow_undefined_stereo=True
+                )
+
+            # Retain H, C, N, O, F, P, S, Cl, Br, I
+            allowed_elements = [1, 6, 7, 8, 9, 15, 16, 17, 35, 53]
+
+            mass = sum(
+                atom.mass.value_in_unit(simtk_unit.gram / simtk_unit.mole)
+                for atom in molecule.atoms
+            )
+
+            return (
+                molecule,
+                (
+                    all(
+                        atom.atomic_number in allowed_elements
+                        for atom in molecule.atoms
+                    )
+                    and (250.0 < mass < 350.0)
+                    and (len(molecule.find_rotatable_bonds()) <= 7)
+                ),
+            )
+
+        except BaseException:
+            _logger.exception("failed to apply filter")
+            return molecule, False
 
 
 @click.command(
diff --git a/nagl/labelling.py b/nagl/labelling.py
index 22de36e..9dceca0 100644
--- a/nagl/labelling.py
+++ b/nagl/labelling.py
@@ -183,7 +183,7 @@ def label_molecules(
                     n_conformers,
                     rms_cutoff,
                 )
-            except (BaseException, Exception) as e:  # lgtm [py/catch-base-exception]
+            except (BaseException, Exception) as e:
 
                 formatted_traceback = traceback.format_exception(
                     etype=type(e), value=e, tb=e.__traceback__