dev-python/html5lib: revbump, EAPI=7, py38

Copyright: Sony Interactive Entertainment Inc.
Package-Manager: Portage-2.3.79, Repoman-2.3.18
Signed-off-by: Patrick McLean <chutzpah@gentoo.org>

3 files changed, 308 insertions, 0 deletions

diff --git a/dev-python/html5lib/files/html5lib-python-1.0.1-support-pytest4.patch b/dev-python/html5lib/files/html5lib-python-1.0.1-support-pytest4.patch
new file mode 100644
index 000000000000..98c9fb23fc77
--- /dev/null
+++ b/dev-python/html5lib/files/html5lib-python-1.0.1-support-pytest4.patch
@@ -0,0 +1,270 @@
+From 2699544837e68b12f1740a7eb56882a0dc0a4008 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Miro=20Hron=C4=8Dok?= <miro@hroncok.cz>
+Date: Thu, 28 Mar 2019 01:45:43 +0100
+Subject: [PATCH 1/4] Support pytest 4
+
+Fixes https://github.com/html5lib/html5lib-python/issues/411
+---
+ html5lib/tests/test_encoding.py    |  4 ++--
+ html5lib/tests/test_sanitizer.py   | 14 +++++++-------
+ html5lib/tests/test_serializer.py  |  2 +-
+ html5lib/tests/test_stream.py      |  7 ++++---
+ html5lib/tests/test_treewalkers.py |  2 +-
+ requirements-test.txt              |  2 +-
+ tox.ini                            |  2 +-
+ 7 files changed, 17 insertions(+), 16 deletions(-)
+
+diff --git a/html5lib/tests/test_encoding.py b/html5lib/tests/test_encoding.py
+index 9a411c77..97b6ca2a 100644
+--- a/html5lib/tests/test_encoding.py
++++ b/html5lib/tests/test_encoding.py
+@@ -99,8 +99,8 @@ def test_encoding():
+     for filename in get_data_files("encoding"):
+         tests = _TestData(filename, b"data", encoding=None)
+         for test in tests:
+-            yield (runParserEncodingTest, test[b'data'], test[b'encoding'])
+-            yield (runPreScanEncodingTest, test[b'data'], test[b'encoding'])
++            runParserEncodingTest(test[b'data'], test[b'encoding'])
++            runPreScanEncodingTest(test[b'data'], test[b'encoding'])
+
+
+ # pylint:disable=wrong-import-position
+diff --git a/html5lib/tests/test_sanitizer.py b/html5lib/tests/test_sanitizer.py
+index 45046d57..1b7285fc 100644
+--- a/html5lib/tests/test_sanitizer.py
++++ b/html5lib/tests/test_sanitizer.py
+@@ -67,19 +67,19 @@ def test_sanitizer():
+                         'tfoot', 'th', 'thead', 'tr', 'select']:
+             continue  # TODO
+         if tag_name == 'image':
+-            yield (runSanitizerTest, "test_should_allow_%s_tag" % tag_name,
++            runSanitizerTest("test_should_allow_%s_tag" % tag_name,
+                    "<img title=\"1\"/>foo &lt;bad&gt;bar&lt;/bad&gt; baz",
+                    "<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name))
+         elif tag_name == 'br':
+-            yield (runSanitizerTest, "test_should_allow_%s_tag" % tag_name,
++            runSanitizerTest("test_should_allow_%s_tag" % tag_name,
+                    "<br title=\"1\"/>foo &lt;bad&gt;bar&lt;/bad&gt; baz<br/>",
+                    "<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name))
+         elif tag_name in constants.voidElements:
+-            yield (runSanitizerTest, "test_should_allow_%s_tag" % tag_name,
++            runSanitizerTest("test_should_allow_%s_tag" % tag_name,
+                    "<%s title=\"1\"/>foo &lt;bad&gt;bar&lt;/bad&gt; baz" % tag_name,
+                    "<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name))
+         else:
+-            yield (runSanitizerTest, "test_should_allow_%s_tag" % tag_name,
++            runSanitizerTest("test_should_allow_%s_tag" % tag_name,
+                    "<%s title=\"1\">foo &lt;bad&gt;bar&lt;/bad&gt; baz</%s>" % (tag_name, tag_name),
+                    "<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name))
+
+@@ -93,7 +93,7 @@ def test_sanitizer():
+         attribute_value = 'foo'
+         if attribute_name in sanitizer.attr_val_is_uri:
+             attribute_value = '%s://sub.domain.tld/path/object.ext' % sanitizer.allowed_protocols[0]
+-        yield (runSanitizerTest, "test_should_allow_%s_attribute" % attribute_name,
++        runSanitizerTest("test_should_allow_%s_attribute" % attribute_name,
+                "<p %s=\"%s\">foo &lt;bad&gt;bar&lt;/bad&gt; baz</p>" % (attribute_name, attribute_value),
+                "<p %s='%s'>foo <bad>bar</bad> baz</p>" % (attribute_name, attribute_value))
+
+@@ -101,7 +101,7 @@ def test_sanitizer():
+         rest_of_uri = '//sub.domain.tld/path/object.ext'
+         if protocol == 'data':
+             rest_of_uri = 'image/png;base64,aGVsbG8gd29ybGQ='
+-        yield (runSanitizerTest, "test_should_allow_uppercase_%s_uris" % protocol,
++        runSanitizerTest("test_should_allow_uppercase_%s_uris" % protocol,
+                "<img src=\"%s:%s\">foo</a>" % (protocol, rest_of_uri),
+                """<img src="%s:%s">foo</a>""" % (protocol, rest_of_uri))
+
+@@ -110,7 +110,7 @@ def test_sanitizer():
+         if protocol == 'data':
+             rest_of_uri = 'image/png;base64,aGVsbG8gd29ybGQ='
+         protocol = protocol.upper()
+-        yield (runSanitizerTest, "test_should_allow_uppercase_%s_uris" % protocol,
++        runSanitizerTest("test_should_allow_uppercase_%s_uris" % protocol,
+                "<img src=\"%s:%s\">foo</a>" % (protocol, rest_of_uri),
+                """<img src="%s:%s">foo</a>""" % (protocol, rest_of_uri))
+
+diff --git a/html5lib/tests/test_serializer.py b/html5lib/tests/test_serializer.py
+index c23592af..a4250935 100644
+--- a/html5lib/tests/test_serializer.py
++++ b/html5lib/tests/test_serializer.py
+@@ -222,4 +222,4 @@ def test_serializer():
+         with open(filename) as fp:
+             tests = json.load(fp)
+             for test in tests['tests']:
+-                yield runSerializerTest, test["input"], test["expected"], test.get("options", {})
++                runSerializerTest(test["input"], test["expected"], test.get("options", {}))
+diff --git a/html5lib/tests/test_stream.py b/html5lib/tests/test_stream.py
+index 27c39538..a9b3ebbe 100644
+--- a/html5lib/tests/test_stream.py
++++ b/html5lib/tests/test_stream.py
+@@ -308,9 +308,10 @@ def test_invalid_codepoints(inp, num):
+                           ("'\\uD800\\uD800\\uD800'", 3),
+                           ("'a\\uD800a\\uD800a\\uD800a'", 3),
+                           ("'\\uDFFF\\uDBFF'", 2),
+-                          pytest.mark.skipif(sys.maxunicode == 0xFFFF,
+-                                             ("'\\uDBFF\\uDFFF'", 2),
+-                                             reason="narrow Python")])
++                          pytest.param(
++                              "'\\uDBFF\\uDFFF'", 2,
++                              mark=pytest.mark.skipif(sys.maxunicode == 0xFFFF,
++                                                      reason="narrow Python"))])
+ def test_invalid_codepoints_surrogates(inp, num):
+     inp = eval(inp)  # pylint:disable=eval-used
+     fp = StringIO(inp)
+diff --git a/html5lib/tests/test_treewalkers.py b/html5lib/tests/test_treewalkers.py
+index 67fc89e5..c2323b7e 100644
+--- a/html5lib/tests/test_treewalkers.py
++++ b/html5lib/tests/test_treewalkers.py
+@@ -99,7 +99,7 @@ def test_treewalker_six_mix():
+
+     for tree in sorted(treeTypes.items()):
+         for intext, attrs, expected in sm_tests:
+-            yield runTreewalkerEditTest, intext, expected, attrs, tree
++            runTreewalkerEditTest(intext, expected, attrs, tree)
+
+
+ @pytest.mark.parametrize("tree,char", itertools.product(sorted(treeTypes.items()), ["x", "\u1234"]))
+diff --git a/requirements-test.txt b/requirements-test.txt
+index 4e223a3f..b936e0fa 100644
+--- a/requirements-test.txt
++++ b/requirements-test.txt
+@@ -4,7 +4,7 @@ tox
+
+ flake8<3.0
+
+-pytest==3.2.5
++pytest>=4.3,<4.4
+ coverage
+ pytest-expect>=1.1,<2.0
+ mock
+diff --git a/html5lib/tests/test_encoding.py b/html5lib/tests/test_encoding.py
+index 97b6ca2a..9f137e7a 100644
+--- a/html5lib/tests/test_encoding.py
++++ b/html5lib/tests/test_encoding.py
+@@ -95,6 +95,7 @@ def runPreScanEncodingTest(data, encoding):
+     assert encoding == stream.charEncoding[0].name, errorMessage(data, encoding, stream.charEncoding[0].name)
+
+
++@pytest.mark.skip(reason="broken under pytest4")
+ def test_encoding():
+     for filename in get_data_files("encoding"):
+         tests = _TestData(filename, b"data", encoding=None)
+
+From 8ded69fdc0ae45f0531e1633927beb2190ab18a6 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Mat=C4=9Bj=20Cepl?= <mcepl@cepl.eu>
+Date: Fri, 8 Nov 2019 15:28:00 +0100
+Subject: [PATCH 3/4] Make flake8 happy
+
+---
+ html5lib/tests/test_sanitizer.py | 44 ++++++++++++++++++++------------
+ 1 file changed, 27 insertions(+), 17 deletions(-)
+
+diff --git a/html5lib/tests/test_sanitizer.py b/html5lib/tests/test_sanitizer.py
+index 1b7285fc..a29d5ef3 100644
+--- a/html5lib/tests/test_sanitizer.py
++++ b/html5lib/tests/test_sanitizer.py
+@@ -63,25 +63,32 @@ def test_sanitizer():
+     for ns, tag_name in sanitizer.allowed_elements:
+         if ns != constants.namespaces["html"]:
+             continue
+-        if tag_name in ['caption', 'col', 'colgroup', 'optgroup', 'option', 'table', 'tbody', 'td',
+-                        'tfoot', 'th', 'thead', 'tr', 'select']:
++        if tag_name in ['caption', 'col', 'colgroup', 'optgroup', 'option',
++                        'table', 'tbody', 'td', 'tfoot', 'th', 'thead',
++                        'tr', 'select']:
+             continue  # TODO
+         if tag_name == 'image':
+             runSanitizerTest("test_should_allow_%s_tag" % tag_name,
+-                   "<img title=\"1\"/>foo &lt;bad&gt;bar&lt;/bad&gt; baz",
+-                   "<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name))
++                             "<img title=\"1\"/>foo &lt;bad&gt;bar&lt;/bad&gt; baz",
++                             "<%s title='1'>foo <bad>bar</bad> baz</%s>" %
++                             (tag_name, tag_name))
+         elif tag_name == 'br':
+             runSanitizerTest("test_should_allow_%s_tag" % tag_name,
+-                   "<br title=\"1\"/>foo &lt;bad&gt;bar&lt;/bad&gt; baz<br/>",
+-                   "<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name))
++                             "<br title=\"1\"/>foo &lt;bad&gt;bar&lt;/bad&gt; baz<br/>",
++                             "<%s title='1'>foo <bad>bar</bad> baz</%s>" %
++                             (tag_name, tag_name))
+         elif tag_name in constants.voidElements:
+             runSanitizerTest("test_should_allow_%s_tag" % tag_name,
+-                   "<%s title=\"1\"/>foo &lt;bad&gt;bar&lt;/bad&gt; baz" % tag_name,
+-                   "<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name))
++                             "<%s title=\"1\"/>foo &lt;bad&gt;bar&lt;/bad&gt; baz" %
++                             tag_name,
++                             "<%s title='1'>foo <bad>bar</bad> baz</%s>" %
++                             (tag_name, tag_name))
+         else:
+             runSanitizerTest("test_should_allow_%s_tag" % tag_name,
+-                   "<%s title=\"1\">foo &lt;bad&gt;bar&lt;/bad&gt; baz</%s>" % (tag_name, tag_name),
+-                   "<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name))
++                             "<%s title=\"1\">foo &lt;bad&gt;bar&lt;/bad&gt; baz</%s>" %
++                             (tag_name, tag_name),
++                             "<%s title='1'>foo <bad>bar</bad> baz</%s>" %
++                             (tag_name, tag_name))
+
+     for ns, attribute_name in sanitizer.allowed_attributes:
+         if ns is not None:
+@@ -92,18 +99,21 @@ def test_sanitizer():
+             continue
+         attribute_value = 'foo'
+         if attribute_name in sanitizer.attr_val_is_uri:
+-            attribute_value = '%s://sub.domain.tld/path/object.ext' % sanitizer.allowed_protocols[0]
++            attribute_value = '%s://sub.domain.tld/path/object.ext' \
++                % sanitizer.allowed_protocols[0]
+         runSanitizerTest("test_should_allow_%s_attribute" % attribute_name,
+-               "<p %s=\"%s\">foo &lt;bad&gt;bar&lt;/bad&gt; baz</p>" % (attribute_name, attribute_value),
+-               "<p %s='%s'>foo <bad>bar</bad> baz</p>" % (attribute_name, attribute_value))
++                         "<p %s=\"%s\">foo &lt;bad&gt;bar&lt;/bad&gt; baz</p>" %
++                         (attribute_name, attribute_value),
++                         "<p %s='%s'>foo <bad>bar</bad> baz</p>" %
++                         (attribute_name, attribute_value))
+
+     for protocol in sanitizer.allowed_protocols:
+         rest_of_uri = '//sub.domain.tld/path/object.ext'
+         if protocol == 'data':
+             rest_of_uri = 'image/png;base64,aGVsbG8gd29ybGQ='
+         runSanitizerTest("test_should_allow_uppercase_%s_uris" % protocol,
+-               "<img src=\"%s:%s\">foo</a>" % (protocol, rest_of_uri),
+-               """<img src="%s:%s">foo</a>""" % (protocol, rest_of_uri))
++                         "<img src=\"%s:%s\">foo</a>" % (protocol, rest_of_uri),
++                         '<img src="%s:%s">foo</a>' % (protocol, rest_of_uri))
+
+     for protocol in sanitizer.allowed_protocols:
+         rest_of_uri = '//sub.domain.tld/path/object.ext'
+@@ -111,8 +121,8 @@ def test_sanitizer():
+             rest_of_uri = 'image/png;base64,aGVsbG8gd29ybGQ='
+         protocol = protocol.upper()
+         runSanitizerTest("test_should_allow_uppercase_%s_uris" % protocol,
+-               "<img src=\"%s:%s\">foo</a>" % (protocol, rest_of_uri),
+-               """<img src="%s:%s">foo</a>""" % (protocol, rest_of_uri))
++                         "<img src=\"%s:%s\">foo</a>" % (protocol, rest_of_uri),
++                         '<img src="%s:%s">foo</a>' % (protocol, rest_of_uri))
+
+
+ def test_lowercase_color_codes_in_style():
+
+From b4d066b2d9b4ea1135183c6500565c2ab8758bf1 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Mat=C4=9Bj=20Cepl?= <mcepl@cepl.eu>
+Date: Fri, 8 Nov 2019 16:17:19 +0100
+Subject: [PATCH 4/4] No limits on the upper version of pytest
+
+---
+ requirements-test.txt | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/requirements-test.txt b/requirements-test.txt
+index b936e0fa..1cd46922 100644
+--- a/requirements-test.txt
++++ b/requirements-test.txt
+@@ -4,7 +4,7 @@ tox
+
+ flake8<3.0
+
+-pytest>=4.3,<4.4
++pytest>=4.3
+ coverage
+ pytest-expect>=1.1,<2.0
+ mock
diff --git a/dev-python/html5lib/html5lib-1.0.1-r1.ebuild b/dev-python/html5lib/html5lib-1.0.1-r1.ebuild
new file mode 100644
index 000000000000..751b9bc332dc
--- /dev/null
+++ b/dev-python/html5lib/html5lib-1.0.1-r1.ebuild
@@ -0,0 +1,36 @@
+# Copyright 1999-2019 Gentoo Authors
+# Distributed under the terms of the GNU General Public License v2
+
+EAPI=7
+
+PYTHON_COMPAT=( python{2_7,3_{5,6,7,8}} pypy{,3} )
+PYTHON_REQ_USE="xml(+)"
+
+inherit distutils-r1
+
+DESCRIPTION="HTML parser based on the HTML5 specification"
+HOMEPAGE="https://github.com/html5lib/html5lib-python/ https://html5lib.readthedocs.org"
+SRC_URI="mirror://pypi/${PN:0:1}/${PN}/${P}.tar.gz"
+
+LICENSE="MIT"
+SLOT="0"
+KEYWORDS="~alpha ~amd64 ~arm ~arm64 ~hppa ~ia64 ~mips ~ppc ~ppc64 ~s390 ~sparc ~x86 ~x64-macos"
+IUSE="test"
+
+RDEPEND=">=dev-python/six-1.9[${PYTHON_USEDEP}]
+	dev-python/webencodings[${PYTHON_USEDEP}]"
+BDEPEND="${RDEPEND}
+	dev-python/setuptools[${PYTHON_USEDEP}]
+	test? (
+		dev-python/pytest-expect[${PYTHON_USEDEP}]
+		dev-python/mock[${PYTHON_USEDEP}]
+	)"
+
+RESTRICT+=" !test? ( test )"
+
+PATCHES=(
+	# https://github.com/html5lib/html5lib-python/pull/429
+	"${FILESDIR}/html5lib-python-1.0.1-support-pytest4.patch"
+)
+
+distutils_enable_tests pytest
diff --git a/dev-python/html5lib/html5lib-1.0.1.ebuild b/dev-python/html5lib/html5lib-1.0.1.ebuild
index e6da9bacdd22..c67285351b05 100644
--- a/dev-python/html5lib/html5lib-1.0.1.ebuild
+++ b/dev-python/html5lib/html5lib-1.0.1.ebuild
@@ -27,6 +27,8 @@ DEPEND="${RDEPEND}
 		dev-python/mock[${PYTHON_USEDEP}]
 	)"
 
+RESTRICT="!test? ( test )"
+
 python_test() {
 	py.test -v || die "Tests fail with ${EPYTHON}"
 }