feat(excel2xml): allow for single tags in XML text (DEV-3427) (#885)

src/dsp_tools/commands/excel2xml/excel2xml_lib.py

@@ -1416,9 +1416,9 @@ def _escape_reserved_chars(text: str) -> str:
         "code",
     ]
     allowed_tags_regex = "|".join(allowed_tags)
-    lookahead = rf"(?!/?({allowed_tags_regex})>)"
-    lookbehind = rf"(?<!</?({allowed_tags_regex}))"
+    lookahead = rf"(?!/?({allowed_tags_regex})/?>)"
     illegal_lt = rf"<{lookahead}"
+    lookbehind = rf"(?<!</?({allowed_tags_regex})/?)"
     illegal_gt = rf"{lookbehind}>"
     illegal_amp = r"&(?![#a-zA-Z0-9]+;)"
     text = regex.sub(illegal_lt, "&lt;", text)

test/unittests/commands/excel2xml/test_excel2xml_lib.py

@@ -14,6 +14,7 @@
 from lxml import etree
 
 from dsp_tools import excel2xml
+from dsp_tools.commands.excel2xml.excel2xml_lib import _escape_reserved_chars
 from dsp_tools.models.exceptions import BaseError
 
 # ruff: noqa: PT009 (pytest-unittest-assertion) (remove this line when pytest is used instead of unittest)
@@ -823,6 +824,42 @@ def test_create_json_list_mapping(self) -> None:
         self.assertDictEqual(testlist_mapping_returned, testlist_mapping_expected)
 
 
+class TestEscapedChars:
+    def test_single_br(self) -> None:
+        test_text = "Text <br/> text after"
+        res = _escape_reserved_chars(test_text)
+        assert res == test_text
+
+    def test_single_br_with_other(self) -> None:
+        test_text = "Text <br/>> text after"
+        expected = "Text <br/>&gt; text after"
+        res = _escape_reserved_chars(test_text)
+        assert res == expected
+
+    def test_wrong_single_br(self) -> None:
+        test_text = "Text <br//> text after"
+        expected = "Text &lt;br//&gt; text after"
+        res = _escape_reserved_chars(test_text)
+        assert res == expected
+
+    def test_emphasis(self) -> None:
+        test_text = "Text before [<em>emphasis</em>] Text after illegal amp: &"
+        expected = "Text before [<em>emphasis</em>] Text after illegal amp: &amp;"
+        res = _escape_reserved_chars(test_text)
+        assert res == expected
+
+    def test_link(self) -> None:
+        test_text = 'Before <a class="salsah-link" href="IRI:link:IRI">link</a> after'
+        res = _escape_reserved_chars(test_text)
+        assert res == test_text
+
+    def test_illegal_angular(self) -> None:
+        test_text = "Before <TagNotKnown>in tags</TagNotKnown> After."
+        expected = "Before &lt;TagNotKnown&gt;in tags&lt;/TagNotKnown&gt; After."
+        res = _escape_reserved_chars(test_text)
+        assert res == expected
+
+
 def _strip_namespace(element: etree._Element) -> str:
     """Removes the namespace from the XML element."""
     xml = etree.tostring(element, encoding="unicode")