🐛 Escape annotated HTML tags in span renderer (#12817)

These changes add a missing call to `escape_html` in the displaCy span
renderer. Previously span-annotated tokens would be inserted into the
page markup without being escaped, resulting in potentially incorrect
rendering. When I encountered this issue, it resulted in some docs and
span underlines being superimposed on top of properly rendered docs and
span underlines near the beginning of the visualization (due to an
unescaped `<span>` tag).

spacy/displacy/render.py

@@ -1,4 +1,3 @@
-import itertools
 import uuid
 from typing import Any, Dict, List, Optional, Tuple, Union
 
@@ -218,7 +217,7 @@ def _render_markup(self, per_token_info: List[Dict[str, Any]]) -> str:
  + (self.offset_step * (len(entities) - 1))
  )
  markup += self.span_template.format(
- text=token["text"],
+ text=escape_html(token["text"]),
  span_slices=slices,
  span_starts=starts,
  total_height=total_height,

spacy/tests/test_displacy.py

@@ -377,3 +377,22 @@ def test_displacy_manual_sorted_entities():
 
  html = displacy.render(doc, style="ent", manual=True)
  assert html.find("FIRST") < html.find("SECOND")
+
+
+@pytest.mark.issue(12816)
+def test_issue12816(en_vocab) -> None:
+ """Test that displaCy's span visualizer escapes annotated HTML tags correctly."""
+ # Create a doc containing an annotated word and an unannotated HTML tag
+ doc = Doc(en_vocab, words=["test", "<TEST>"])
+ doc.spans["sc"] = [Span(doc, 0, 1, label="test")]
+
+ # Verify that the HTML tag is escaped when unannotated
+ html = displacy.render(doc, style="span")
+ assert "&lt;TEST&gt;" in html
+
+ # Annotate the HTML tag
+ doc.spans["sc"].append(Span(doc, 1, 2, label="test"))
+
+ # Verify that the HTML tag is still escaped
+ html = displacy.render(doc, style="span")
+ assert "&lt;TEST&gt;" in html