fix: partition html fail with table without tbody (#1817)

This PR resolves #1807 
- fix a bug where when a table tagged content does not contain `tbody`
tag but `thead` tag for the rows the code fails
- now when there is no `tbody` in a table section we try to look for
`thead` isntead
- when both are not found return empty table

CHANGELOG.md

@@ -20,6 +20,7 @@
 * **Fix metrics folder not discoverable** Fixes issue where unstructured/metrics folder is not discoverable on PyPI by adding
 an `__init__.py` file under the folder.
 * **Fix a bug when `parition_pdf` get `model_name=None`** In API usage the `model_name` value is `None` and the `cast` function in `partition_pdf` would return `None` and lead to attribution error. Now we use `str` function to explicit convert the content to string so it is garanteed to have `starts_with` and other string functions as attributes
+* **Fix html partition fail on tables without `tbody` tag** HTML tables may sometimes just contain headers without body (`tbody` tag)
 
 ## 0.10.24
 

test_unstructured/partition/test_html_partition.py

@@ -672,3 +672,22 @@ def test_partition_html_respects_detect_language_per_element():
     elements = partition_html(filename=filename, detect_language_per_element=True)
     langs = [element.metadata.languages for element in elements]
     assert langs == [["eng"], ["spa", "eng"], ["eng"], ["eng"], ["spa"]]
+
+
+@pytest.mark.parametrize(
+    ("tag", "expected"),
+    [
+        ("thead", ""),
+        ("foo", ""),
+    ],
+)
+def test_partition_html_with_table_without_tbody(tag, expected):
+    table_html = f"""
+    <table>
+      <{tag}>
+        <tr><th>Header 1</th><th>Header 2</th></tr>
+        </{tag}>
+    </table>
+    """
+    partitions = partition_html(text=table_html)
+    assert partitions[0].metadata.text_as_html == expected

unstructured/documents/html.py

@@ -495,7 +495,7 @@ def _process_leaf_table_item(
             rows = tag_elem.findall("tr")
             if not rows:
                 body = tag_elem.find("tbody")
-                rows = body.findall("tr")
+                rows = body.findall("tr") if body else []
             if len(rows) > 0:
                 table_data = [list(row.itertext()) for row in rows]
                 html_table = tabulate(table_data, tablefmt="html")