feat: prevent processing errors from empty XML tags

Create helper function to remove empty XML tags to avoid unexpected
behavior when processing elements like keywords in
`workbook.get_description`.

src/spinneret/utilities.py

@@ -2,6 +2,7 @@
 
 from os import environ
 from json import load
+from lxml import etree
 
 
 def load_configuration(config_file: str) -> None:
@@ -18,3 +19,14 @@ def load_configuration(config_file: str) -> None:
         config = load(config)
         for key, value in config.items():
             environ[key] = value
+
+
+def delete_empty_tags(xml: etree._ElementTree) -> etree._ElementTree:
+    """Deletes empty tags from an XML file
+
+    :param xml: The XML file to be cleaned.
+    :returns: The cleaned XML file.
+    """
+    for element in xml.xpath(".//*[not(node())]"):
+        element.getparent().remove(element)
+    return xml

tests/test_utilities.py

@@ -0,0 +1,25 @@
+"""Test utilities module"""
+
+from lxml import etree
+from spinneret import datasets
+from spinneret.utilities import delete_empty_tags
+
+
+def test_delete_empty_tags():
+    """Test that empty tags are removed from an XML file"""
+
+    # Read test file
+    eml_file = datasets.get_example_eml_dir() + "/" + "edi.3.9.xml"
+    eml = etree.parse(eml_file)
+
+    # Add an empty tag to the XML and check that it is added
+    # to the XML
+    empty_tag = etree.Element("empty_tag")
+    eml.getroot().append(empty_tag)
+    assert len(eml.xpath(".//empty_tag")) == 1
+
+    # Remove empty tags
+    eml = delete_empty_tags(eml)
+
+    # Check that the empty tag has been removed
+    assert len(eml.xpath(".//empty_tag")) == 0