From fa1308061802ac7b7d20e954ba7372c5ac292333 Mon Sep 17 00:00:00 2001 From: reivilibre Date: Tue, 28 Jun 2022 14:29:08 +0100 Subject: Merge pull request from GHSA-22p3-qrh9-cx32 * Make _iterate_over_text easier to read by using simple data structures * Prefer a set of tags to ignore In my tests, it's 4x faster to check for containment in a set of this size * Add a stack size limit to _iterate_over_text * Continue accepting the case where there is no body element * Use an early return instead for None Co-authored-by: Richard van der Hoff --- tests/rest/media/v1/test_html_preview.py | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'tests/rest/media/v1') diff --git a/tests/rest/media/v1/test_html_preview.py b/tests/rest/media/v1/test_html_preview.py index ea9e5889bf..61357622bd 100644 --- a/tests/rest/media/v1/test_html_preview.py +++ b/tests/rest/media/v1/test_html_preview.py @@ -370,6 +370,23 @@ class OpenGraphFromHtmlTestCase(unittest.TestCase): og = parse_html_to_open_graph(tree) self.assertEqual(og, {"og:title": "รณ", "og:description": "Some text."}) + def test_nested_nodes(self) -> None: + """A body with some nested nodes. Tests that we iterate over children + in the right order (and don't reverse the order of the text).""" + html = b""" + Welcome the bold and underlined text + with a cheeky SVG and some tail text + """ + tree = decode_body(html, "http://example.com/test.html") + og = parse_html_to_open_graph(tree) + self.assertEqual( + og, + { + "og:title": None, + "og:description": "Welcome\n\nthe bold\n\nand underlined text\n\nand\n\nsome\n\ntail text", + }, + ) + class MediaEncodingTestCase(unittest.TestCase): def test_meta_charset(self) -> None: -- cgit 1.4.1