From 17c1411551e7dcc083d2b81188bb68596a1ba0c2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Rapha=C3=ABl=20Robidas?= <raphael.robidas@usherbrooke.ca>
Date: Mon, 26 Aug 2024 12:18:31 -0400
Subject: [PATCH] Fixed bug where extra lines in input files would mistakingly
 be counted as extra atoms for the purpose of checking the number of atoms in
 the file

---
 ccinput/tests/structures/ethanol_extra_line.xyz | 12 ++++++++++++
 ccinput/tests/test_cli.py                       | 14 ++++++++++++++
 ccinput/tests/test_structures.py                | 15 +++++++++++++++
 ccinput/utilities.py                            |  9 ++++++++-
 4 files changed, 49 insertions(+), 1 deletion(-)
 create mode 100644 ccinput/tests/structures/ethanol_extra_line.xyz

diff --git a/ccinput/tests/structures/ethanol_extra_line.xyz b/ccinput/tests/structures/ethanol_extra_line.xyz
new file mode 100644
index 0000000..f49db64
--- /dev/null
+++ b/ccinput/tests/structures/ethanol_extra_line.xyz
@@ -0,0 +1,12 @@
+9
+
+C         -1.31970       -0.64380        0.00000
+H         -0.96310       -1.65260        0.00000
+H         -0.96310       -0.13940       -0.87370
+H         -2.38970       -0.64380        0.00000
+C         -0.80640        0.08220        1.25740
+H         -1.16150        1.09160        1.25640
+H         -1.16470       -0.42110        2.13110
+O          0.62360        0.07990        1.25870
+H          0.94410        0.53240        2.04240
+
diff --git a/ccinput/tests/test_cli.py b/ccinput/tests/test_cli.py
index 4a43497..a4c53a6 100644
--- a/ccinput/tests/test_cli.py
+++ b/ccinput/tests/test_cli.py
@@ -762,6 +762,20 @@ def test_synonym_basis_set(self):
 
         objs, outputs = get_input_from_args(args)
 
+    def test_file_extra_line(self):
+        args = {
+            "software": "gaussian",
+            "type": "sp",
+            "method": "HF",
+            "basis_set": "Def2SVP",
+            "file": self.struct("ethanol_extra_line"),
+            "nproc": 1,
+            "mem": "1G",
+            "name": "ethanol",
+        }
+        line = f"gaussian sp HF -bs Def2SVP -f {self.struct('ethanol')} -n 1 --mem 1G"
+        self.assertTrue(self.args_cmd_equivalent(args, line))
+
 
 class CliPresetTests(InputTests):
     def test_create_preset(self):
diff --git a/ccinput/tests/test_structures.py b/ccinput/tests/test_structures.py
index 936b158..a83a421 100644
--- a/ccinput/tests/test_structures.py
+++ b/ccinput/tests/test_structures.py
@@ -82,6 +82,21 @@ def test_multiple_atoms_invalid_header2(self):
         with self.assertRaises(InvalidXYZ):
             standardize_xyz(xyz)
 
+    def test_multiple_atoms_extra_lines(self):
+        xyz = """3
+        header
+        Cl 0.0 0.0 0.0
+        Cl 0.0 0.0 0.0
+        Cl 0.0 0.0 0.0
+
+
+
+        """
+        self.assertEqual(
+            standardize_xyz(xyz),
+            "Cl   0.00000000   0.00000000   0.00000000\nCl   0.00000000   0.00000000   0.00000000\nCl   0.00000000   0.00000000   0.00000000\n",
+        )
+
     def test_invalid_element(self):
         xyz = "1\n\nBl 0.0 0.0 0.0\n"
         with self.assertRaises(InvalidXYZ):
diff --git a/ccinput/utilities.py b/ccinput/utilities.py
index 977c2e1..2965b71 100644
--- a/ccinput/utilities.py
+++ b/ccinput/utilities.py
@@ -159,7 +159,14 @@ def parse_xyz_from_file(path):
         raise InvalidParameter(f"Input file not found: {path}")
 
     with open(path) as f:
-        lines = f.readlines()
+        _lines = f.readlines()
+
+    lines = _lines[2:]
+
+    if len(_lines) < 3:
+        raise InvalidXYZ("Invalid XYZ: No atoms specified")
+
+    lines = [i.strip() for i in _lines[2:] if i.strip() != ""]
 
     return standardize_xyz(lines)