https://github.com/html5lib/html5lib-python/pull/600
From b7e8c4ccec36c87e076daed4db68201de151cc57 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Tom=C3=A1=C5=A1=20Hrn=C4=8Diar?=
Date: Mon, 29 Jun 2026 10:20:38 +0200
Subject: [PATCH] Fix test compatibility with pytest >= 9.1
Pytest 9.1 no longer accepts non-Collection iterables in parametrize. Wrap generator
functions and itertools.product calls with list(). Also deduplicate the parametrize
values in testLegacyQuoteAttribute. The character list had 6 duplicates
between the "spec" prefix and the extended character ranges. With --strict (set
in pytest.ini), pytest 9.1 enforces unique parametrization IDs and rejects them.
Assisted-by: Claude Opus 4.6
---
html5lib/tests/test_encoding.py | 4 ++--
html5lib/tests/test_sanitizer.py | 4 ++--
html5lib/tests/test_serializer.py | 12 +++++-------
html5lib/tests/test_treewalkers.py | 4 ++--
4 files changed, 11 insertions(+), 13 deletions(-)
diff --git a/html5lib/tests/test_encoding.py b/html5lib/tests/test_encoding.py
index 47c4814a..951fd42f 100644
--- a/html5lib/tests/test_encoding.py
+++ b/html5lib/tests/test_encoding.py
@@ -82,7 +82,7 @@ def param_encoding():
yield test[b'data'], test[b'encoding']
-@pytest.mark.parametrize("data, encoding", param_encoding())
+@pytest.mark.parametrize("data, encoding", list(param_encoding()))
def test_parser_encoding(data, encoding):
p = HTMLParser()
assert p.documentEncoding is None
@@ -92,7 +92,7 @@ def test_parser_encoding(data, encoding):
assert encoding == p.documentEncoding, errorMessage(data, encoding, p.documentEncoding)
-@pytest.mark.parametrize("data, encoding", param_encoding())
+@pytest.mark.parametrize("data, encoding", list(param_encoding()))
def test_prescan_encoding(data, encoding):
stream = _inputstream.HTMLBinaryInputStream(data, useChardet=False)
encoding = encoding.lower().decode("ascii")
diff --git a/html5lib/tests/test_sanitizer.py b/html5lib/tests/test_sanitizer.py
index 499310b6..15746ffa 100644
--- a/html5lib/tests/test_sanitizer.py
+++ b/html5lib/tests/test_sanitizer.py
@@ -130,8 +130,8 @@ def test_details_summary_allowed():
@pytest.mark.parametrize("expected, input",
- (pytest.param(expected, input, id=id)
- for id, expected, input in param_sanitizer()))
+ [pytest.param(expected, input, id=id)
+ for id, expected, input in param_sanitizer()])
def test_sanitizer(expected, input):
parsed = parseFragment(expected)
expected = serialize(parsed,
diff --git a/html5lib/tests/test_serializer.py b/html5lib/tests/test_serializer.py
index a2be0be5..2fec0341 100644
--- a/html5lib/tests/test_serializer.py
+++ b/html5lib/tests/test_serializer.py
@@ -155,14 +155,12 @@ def testSpecQuoteAttribute(c):
test_serializer(input_, output_, options_)
-@pytest.mark.parametrize("c", list("\t\n\u000C\x20\r\"'=<>`"
- "\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n"
+@pytest.mark.parametrize("c", list("\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n"
"\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15"
"\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
- "\x20\x2f\x60\xa0\u1680\u180e\u180f\u2000"
- "\u2001\u2002\u2003\u2004\u2005\u2006\u2007"
- "\u2008\u2009\u200a\u2028\u2029\u202f\u205f"
- "\u3000"))
+ "\x20\"'=<>/\x60\xa0\u1680\u180e\u180f"
+ "\u2000\u2001\u2002\u2003\u2004\u2005\u2006"
+ "\u2007\u2008\u2009\u200a\u2028\u2029\u202f\u205f\u3000"))
def testLegacyQuoteAttribute(c):
input_ = [["StartTag", "http://www.w3.org/1999/xhtml", "span",
[{"namespace": None, "name": "foo", "value": c}]]]
@@ -212,7 +210,7 @@ def param_serializer():
yield test["input"], test["expected"], test.get("options", {})
-@pytest.mark.parametrize("input, expected, options", param_serializer())
+@pytest.mark.parametrize("input, expected, options", list(param_serializer()))
def test_serializer(input, expected, options):
encoding = options.get("encoding", None)
diff --git a/html5lib/tests/test_treewalkers.py b/html5lib/tests/test_treewalkers.py
index 780ca964..4fb5d1f7 100644
--- a/html5lib/tests/test_treewalkers.py
+++ b/html5lib/tests/test_treewalkers.py
@@ -87,7 +87,7 @@ def param_treewalker_six_mix():
yield intext, expected, attrs, tree
-@pytest.mark.parametrize("intext, expected, attrs_to_add, tree", param_treewalker_six_mix())
+@pytest.mark.parametrize("intext, expected, attrs_to_add, tree", list(param_treewalker_six_mix()))
def test_treewalker_six_mix(intext, expected, attrs_to_add, tree):
"""tests what happens when we add attributes to the intext"""
treeName, treeClass = tree
@@ -105,7 +105,7 @@ def test_treewalker_six_mix(intext, expected, attrs_to_add, tree):
raise AssertionError("TreewalkerEditTest: %s\nExpected:\n%s\nReceived:\n%s" % (treeName, expected, output))
-@pytest.mark.parametrize("tree,char", itertools.product(sorted(treeTypes.items()), ["x", "\u1234"]))
+@pytest.mark.parametrize("tree,char", list(itertools.product(sorted(treeTypes.items()), ["x", "\u1234"])))
def test_fragment_single_char(tree, char):
expected = [
{'data': char, 'type': 'Characters'}