fix: reject truncated moldescriptor molecule blocks

PQAnalysis/io/moldescriptor_reader.py

@@ -61,6 +61,9 @@ def read(self) -> Residues:
         ------
         MoldescriptorReaderError
             If the number of columns in the header of a mol type is not 3.
+        MoldescriptorReaderError
+            If a mol type declares more atoms than atom lines follow
+            before the end of the file.
         """
         with open(self.filename, 'r', encoding='utf-8') as f:
             lines = f.readlines()
@@ -103,6 +106,17 @@ def read(self) -> Residues:
 
                     n_atoms = int(splitted_line[1])
 
+                    if counter + n_atoms + 1 > len(lines):
+                        self.logger.error(
+                            (
+                            f"The mol type {splitted_line[0]} declares "
+                            f"{n_atoms} atoms, but only "
+                            f"{len(lines) - counter - 1} atom lines follow "
+                            "before the end of the file.\n"
+                            ),
+                            exception=MoldescriptorReaderError
+                        )
+
                     mol_types.append(
                         self._read_mol_type(
                         lines[counter:counter + n_atoms + 1],

tests/data/readMoldescriptor/moldescriptor_tooFewAtoms.dat

@@ -0,0 +1,4 @@
+# Molecule 1
+  H2O            3   0.0
+  O              0  -0.65966
+  H              1   0.32983

tests/data/readMoldescriptor/moldescriptor_tooFewAtoms_midFile.dat

@@ -0,0 +1,5 @@
+  H2O            3   0.0
+  O              0  -0.65966
+  H              1   0.32983
+  AR             1   0.0
+  Ar             2   0.0

tests/io/test_moldescriptorReader.py

@@ -115,3 +115,25 @@ def test_read(self, test_with_data_dir):
         assert str(
             exception.value
         ) == "The number of columns in the header of a mol type must be 3.\nGot 2 columns instead in text: '  H2O            3'\n"
+
+    @pytest.mark.parametrize(
+        "example_dir",
+        ["readMoldescriptor"],
+        indirect=False
+    )
+    def test_read_too_few_atom_lines(self, test_with_data_dir):
+        reader = MoldescriptorReader("moldescriptor_tooFewAtoms.dat")
+        with pytest.raises(MoldescriptorReaderError) as exception:
+            reader.read()
+        assert str(exception.value) == (
+            "The mol type H2O declares 3 atoms, but only 2 atom lines "
+            "follow before the end of the file.\n"
+        )
+
+        reader = MoldescriptorReader("moldescriptor_tooFewAtoms_midFile.dat")
+        with pytest.raises(MoldescriptorReaderError) as exception:
+            reader.read()
+        assert str(exception.value) == (
+            "The mol type Ar declares 2 atoms, but only 0 atom lines "
+            "follow before the end of the file.\n"
+        )