From a5d246066b5352a7d72e70ec0acb643e7c0861fa Mon Sep 17 00:00:00 2001 From: Serhiy Storchaka Date: Thu, 17 Mar 2022 18:32:53 +0200 Subject: [PATCH] bpo-47042: Fix testing the HTML output in test_pydoc (GH-31959) Previously it tested that that the actual output contains every non-whitespace character from the expected output (ignoring order and repetitions). Now it will test that the actual output contains the same lines as the expected output, in the same order, ignoring indentation and empty lines. --- Lib/test/test_pydoc.py | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/Lib/test/test_pydoc.py b/Lib/test/test_pydoc.py index 057780d51f9..4f18af3f0ec 100644 --- a/Lib/test/test_pydoc.py +++ b/Lib/test/test_pydoc.py @@ -340,9 +340,10 @@ def html2text(html): Tailored for pydoc tests only. """ - return pydoc.replace( - re.sub("<.*?>", "", html), - " ", " ", ">", ">", "<", "<") + html = html.replace("
", "\n") + html = re.sub("<.*?>", "", html) + html = pydoc.replace(html, " ", " ", ">", ">", "<", "<") + return html class PydocBaseTest(unittest.TestCase): @@ -384,9 +385,12 @@ class PydocDocTest(unittest.TestCase): def test_html_doc(self): result, doc_loc = get_pydoc_html(pydoc_mod) text_result = html2text(result) - expected_lines = [line.strip() for line in html2text_of_expected if line] - for line in expected_lines: - self.assertIn(line, text_result) + text_lines = [line.strip() for line in text_result.splitlines()] + text_lines = [line for line in text_lines if line] + del text_lines[1] + expected_lines = html2text_of_expected.splitlines() + expected_lines = [line.strip() for line in expected_lines if line] + self.assertEqual(text_lines, expected_lines) mod_file = inspect.getabsfile(pydoc_mod) mod_url = urllib.parse.quote(mod_file) self.assertIn(mod_url, result)