Convert single-item lists in table cells into paragraphs

CHANGELOG.md

@@ -10,6 +10,8 @@ The format is based on Keep a Changelog, and this project adheres to Semantic Ve
 
 ### Changed
 
+- Convert single-item lists to paragraphs inside of table cells
+
 ### Fixed
 
 ## [1.40.0] - 2023-12-16

bloom_nofos/nofos/nofo.py

@@ -1257,6 +1257,43 @@ def unwrap_empty_elements(soup):
         el.unwrap()
 
 
+def _convert_single_item_lists_to_paragraphs(soup, cell):
+    """
+    This function mutates the soup!
+
+    Converts single-item lists in a table cell to paragraphs for improved accessibility.
+
+    This function checks if a given table cell (`<td>` or `<th>`) contains exactly one child,
+    which must be a list (`<ul>` or `<ol>`) with only one list item (`<li>`). If such a list
+    is found, it is replaced with a `<p>` tag containing the same HTML content as the list item.
+
+    Modifies:
+        The `cell` object is modified in place. If a matching single-item list is found,
+        it is replaced with a paragraph (`<p>`).
+
+    Example:
+        Input:
+        <td><ul><li><strong>Bold</strong> list item</li></ul></td>
+
+        Output:
+        <td><p><strong>Bold</strong> list item</p></td>
+    """
+    cell_children = list(cell.children)
+    if (
+        len(cell_children) == 1
+        and cell_children[0].name in ["ul", "ol"]
+        and len(cell_children[0].find_all("li")) == 1
+    ):
+        # Extract the text content of the single list item
+        li = cell_children[0].find("li", recursive=False)
+
+        # Replace with a paragraph, then remove the list
+        new_paragraph = soup.new_tag("p")
+        new_paragraph.extend(li.contents)
+        cell.append(new_paragraph)
+        cell_children[0].decompose()
+
+
 def clean_table_cells(soup):
     """
     This function mutates the soup!
@@ -1287,6 +1324,8 @@ def clean_table_cells(soup):
         for span in cell.find_all("span"):
             span.unwrap()
 
+        _convert_single_item_lists_to_paragraphs(soup, cell)
+
 
 def replace_src_for_inline_images(soup):
     """

bloom_nofos/nofos/test_nofo.py

@@ -111,7 +111,7 @@ def test_no_replacements_needed(self):
         self.assertEqual(replace_chars(test_string), test_string)
 
 
-class TestsCleanTableCells(TestCase):
+class TestsCleanTableCellsSpans(TestCase):
     def test_remove_span_keep_content(self):
         html = "<table><tr><td><span>Content</span> and more <span>content</span></td></tr></table>"
         soup = BeautifulSoup(html, "html.parser")
@@ -155,6 +155,75 @@ def test_multiple_spans_in_cell(self):
         self.assertEqual(soup.td.text, "FirstSecond")
 
 
+class TestsCleanTableCellsLists(TestCase):
+    def test_replace_single_item_ul_in_table_cell(self):
+        html = "<table><tr><td><ul><li>UL list item 1</li></ul></td></tr></table>"
+        soup = BeautifulSoup(html, "html.parser")
+        clean_table_cells(soup)
+        self.assertEqual(
+            str(soup), "<table><tr><td><p>UL list item 1</p></td></tr></table>"
+        )
+
+    def test_replace_single_item_ul_in_table_cell_with_other_tags(self):
+        html = '<table><tr><td><ul><li>UL list item 1 with <a href="https://google.com">a link</a> and <strong>bold formatting</strong></li></ul></td></tr></table>'
+        soup = BeautifulSoup(html, "html.parser")
+        clean_table_cells(soup)
+        self.assertEqual(
+            str(soup),
+            '<table><tr><td><p>UL list item 1 with <a href="https://google.com">a link</a> and <strong>bold formatting</strong></p></td></tr></table>',
+        )
+
+    def test_replace_single_item_ol_in_table_cell(self):
+        html = "<table><tr><td><ol><li>OL list item 1</li></ol></td></tr></table>"
+        soup = BeautifulSoup(html, "html.parser")
+        clean_table_cells(soup)
+        self.assertEqual(
+            str(soup), "<table><tr><td><p>OL list item 1</p></td></tr></table>"
+        )
+
+    def test_NO_replace_multiple_item_ul_in_table_cell(self):
+        html = "<table><tr><td><ul><li>UL list item 1</li><li>UL list item 2</li></ul></td></tr></table>"
+        soup = BeautifulSoup(html, "html.parser")
+        clean_table_cells(soup)
+        self.assertEqual(str(soup), html)
+
+    def test_NO_replace_multiple_item_ol_in_table_cell(self):
+        html = "<table><tr><td><ol><li>OL list item 1</li><li>OL list item 2</li></ol></td></tr></table>"
+        soup = BeautifulSoup(html, "html.parser")
+        clean_table_cells(soup)
+        self.assertEqual(str(soup), html)
+
+    def test_NO_replace_single_item_ul_in_table_cell_if_element_before(self):
+        html = "<table><tr><td><p>Paragraph 1 before ul</p><ul><li>UL list item 1</li></ul></td></tr></table>"
+        soup = BeautifulSoup(html, "html.parser")
+        clean_table_cells(soup)
+        self.assertEqual(str(soup), html)
+
+    def test_NO_replace_single_item_ul_in_table_cell_if_element_after(self):
+        html = "<table><tr><td><ul><li>UL list item 1</li></ul><p>Paragraph 1 after ul</p></td></tr></table>"
+        soup = BeautifulSoup(html, "html.parser")
+        clean_table_cells(soup)
+        self.assertEqual(str(soup), html)
+
+    def test_NO_replace_2_single_item_uls_in_table_cell(self):
+        html = "<table><tr><td><ul><li>UL list 1 item 1</li></ul><ul><li>UL list 2 item 1</li></ul></td></tr></table>"
+        soup = BeautifulSoup(html, "html.parser")
+        clean_table_cells(soup)
+        self.assertEqual(str(soup), html)
+
+    def test_NO_replace_2_single_item_ols_in_table_cell(self):
+        html = "<table><tr><td><ol><li>OL list 1 item 1</li></ol><ol><li>OL list 2 item 1</li></ol></td></tr></table>"
+        soup = BeautifulSoup(html, "html.parser")
+        clean_table_cells(soup)
+        self.assertEqual(str(soup), html)
+
+    def test_NO_replace_single_item_ul_and_single_item_ol_in_table_cell(self):
+        html = "<table><tr><td><ul><li>UL list 1 item 1</li></ul><ol><li>OL list 1 item 1</li></ol></td></tr></table>"
+        soup = BeautifulSoup(html, "html.parser")
+        clean_table_cells(soup)
+        self.assertEqual(str(soup), html)
+
+
 class TableConvertFirstRowToHeaderRowTests(TestCase):
     def setUp(self):
         self.caption_text = "Physician Assistant Training Chart"