Fix tag recognition if at start of HTML paragraph

federation/tests/utils/test_text.py

@@ -83,6 +83,14 @@ class TestFindTags:
         tags, text = find_tags(source, replacer=self._replacer)
         assert text == source
 
+    def test_start_of_paragraph_in_html_content(self):
+        source = '<p>First line</p><p>#foobar #barfoo</p>'
+        tags, text = find_tags(source)
+        assert tags == {"foobar", "barfoo"}
+        assert text == source
+        tags, text = find_tags(source, replacer=self._replacer)
+        assert text == '<p>First line</p><p>#foobar/foobar #barfoo/barfoo</p>'
+
 
 class TestProcessTextLinks:
     def test_link_at_start_or_end(self):

federation/utils/text.py

@@ -33,7 +33,9 @@ def find_tags(text: str, replacer: callable = None) -> Tuple[Set, str]:
     Returns a set of tags and the original or replaced text.
     """
     found_tags = set()
-    lines = text.splitlines(keepends=True)
+    # <br> and <p> tags cause issues in us finding words - add some spacing around them
+    new_text = text.replace("<br>", " <br> ").replace("<p>", " <p> ").replace("</p>", " </p> ")
+    lines = new_text.splitlines(keepends=True)
     final_lines = []
     code_block = False
     final_text = None
@@ -78,6 +80,8 @@ def find_tags(text: str, replacer: callable = None) -> Tuple[Set, str]:
         final_lines.append(" ".join(final_words))
     if replacer:
         final_text = "".join(final_lines)
+    if final_text:
+        final_text = final_text.replace(" <br> ", "<br>").replace(" <p> ", "<p>").replace(" </p> ", "</p>")
     return found_tags, final_text or text