fix [NEX-49] : Fix TypeError for empty HTML content (#4032)

### Summary

Addressed a TypeError that occurred when partitioning empty or
whitespace-only HTML content.

## Test
* unit test
`test_unstructured/partition/html/test_partition.py::test_partition_html_with_empty_content_raises_error`
can reproduce the TypeErro before fix
* now test can pass

CHANGELOG.md

@@ -1,3 +1,13 @@
+## 0.18.2-dev0
+
+### Enhancements
+
+### Features
+
+### Fixes
+- **Fixes empty HTML content** Previously, when the HTML content was empty, the partitioner would raise a TypeError: Invalid input object: NoneType. Now it will return an empty list of elements.
+
+
 ## 0.18.1
 
 ### Enhancements

test_unstructured/partition/html/test_partition.py

@@ -5,7 +5,9 @@
 from __future__ import annotations
 
 import io
+import os
 import pathlib
+import tempfile
 from typing import Any, Optional
 
 import pytest
@@ -1477,3 +1479,40 @@ class Describe_HtmlPartitioner:
         opts = HtmlPartitionerOptions(**opts_args)
 
         assert list(_HtmlPartitioner.iter_elements(opts)) == []
+
+
+@pytest.mark.parametrize(
+    ("test_case", "content"),
+    [
+        ("empty_file", ""),
+        ("empty_bytes", b""),
+        ("whitespace_only", "   \n\t  \n  "),
+    ],
+)
+def test_partition_html_with_empty_content_raises_error(test_case, content):
+    """Test that partitioning empty/whitespace-only HTML content won't
+    raise TypeError: Invalid input object: NoneType.
+
+    This reproduces the production error where lxml.etree.strip_elements is called with None
+    when the HTML content is empty, causing etree.fromstring to return None.
+
+    Args:
+        test_case: Description of the test scenario
+        content: The content to test (empty string, empty bytes, or whitespace)
+    """
+    if test_case == "empty_bytes":
+        # Create a file-like object with empty content
+        empty_file = io.BytesIO(content)
+        partition_html(file=empty_file)
+    else:
+        # Create a temporary file with the given content
+        with tempfile.NamedTemporaryFile(mode="w", suffix=".html", delete=False) as f:
+            f.write(content)
+            f.flush()
+            temp_filename = f.name
+
+        try:
+            elements = partition_html(filename=temp_filename)
+            assert len(elements) == 0
+        finally:
+            os.unlink(temp_filename)

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.18.1"  # pragma: no cover
+__version__ = "0.18.2-dev0"  # pragma: no cover

unstructured/partition/html/partition.py

@@ -210,6 +210,11 @@ class _HtmlPartitioner:
 
         Elements appear in document order.
         """
+        # -- handle empty or whitespace-only HTML content --
+        html_text = self._opts.html_text
+        if not html_text or html_text.strip() == "":
+            return
+
         elements_iter = (
             self._main.iter_elements()
             if self._opts.html_parser_version == "v1"
@@ -264,6 +269,11 @@ class _HtmlPartitioner:
     def _from_ontology(self) -> List[Element]:
         """Convert an ontology elements represented in HTML to an ontology element."""
         html_text = self._opts.html_text
+
+        # -- handle empty or whitespace-only HTML content --
+        if not html_text or html_text.strip() == "":
+            return []
+
         ontology = parse_html_to_ontology(html_text)
         unstructured_elements = ontology_to_unstructured_elements(
             ontology, add_img_alt_text=self._opts.add_img_alt_text