Drop support for EOL Python 3.6

.github/workflows/test.yml

@@ -9,7 +9,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.6", "3.7", "3.8", "3.9", "3.10", "pypy3"]
+        python-version: ["3.7", "3.8", "3.9", "3.10", "pypy-3.8"]
         os: [ubuntu-latest, macos-latest, windows-latest]
 
     steps:

bleach/__init__.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 import packaging.version
 
 from bleach.linkifier import (

bleach/html5lib_shim.py

@@ -257,7 +257,7 @@ class BleachHTMLTokenizer(HTMLTokenizer):
     """Tokenizer that doesn't consume character entities"""
 
     def __init__(self, consume_entities=False, **kwargs):
-        super(BleachHTMLTokenizer, self).__init__(**kwargs)
+        super().__init__(**kwargs)
 
         self.consume_entities = consume_entities
 
@@ -267,7 +267,7 @@ def __init__(self, consume_entities=False, **kwargs):
     def __iter__(self):
         last_error_token = None
 
-        for token in super(BleachHTMLTokenizer, self).__iter__():
+        for token in super().__iter__():
             if last_error_token is not None:
                 if (
                     last_error_token["data"] == "invalid-character-in-attribute-name"
@@ -342,9 +342,7 @@ def consumeEntity(self, allowedChar=None, fromAttribute=False):
         # If this tokenizer is set to consume entities, then we can let the
         # superclass do its thing.
         if self.consume_entities:
-            return super(BleachHTMLTokenizer, self).consumeEntity(
-                allowedChar, fromAttribute
-            )
+            return super().consumeEntity(allowedChar, fromAttribute)
 
         # If this tokenizer is set to not consume entities, then we don't want
         # to consume and convert them, so this overrides the html5lib tokenizer's
@@ -364,7 +362,7 @@ def tagOpenState(self):
         # we've collected so far and we do that by calling start_tag() on
         # the input stream wrapper.
         self.stream.start_tag()
-        return super(BleachHTMLTokenizer, self).tagOpenState()
+        return super().tagOpenState()
 
     def emitCurrentToken(self):
         token = self.currentToken
@@ -397,7 +395,7 @@ def emitCurrentToken(self):
             self.state = self.dataState
             return
 
-        super(BleachHTMLTokenizer, self).emitCurrentToken()
+        super().emitCurrentToken()
 
 
 class BleachHTMLParser(HTMLParser):
@@ -416,7 +414,7 @@ def __init__(self, tags, strip, consume_entities, **kwargs):
         self.tags = [tag.lower() for tag in tags] if tags is not None else None
         self.strip = strip
         self.consume_entities = consume_entities
-        super(BleachHTMLParser, self).__init__(**kwargs)
+        super().__init__(**kwargs)
 
     def _parse(
         self, stream, innerHTML=False, container="div", scripting=True, **kwargs
@@ -642,15 +640,14 @@ def serialize(self, treewalker, encoding=None):
         in_tag = False
         after_equals = False
 
-        for stoken in super(BleachHTMLSerializer, self).serialize(treewalker, encoding):
+        for stoken in super().serialize(treewalker, encoding):
             if in_tag:
                 if stoken == ">":
                     in_tag = False
 
                 elif after_equals:
                     if stoken != '"':
-                        for part in self.escape_base_amp(stoken):
-                            yield part
+                        yield from self.escape_base_amp(stoken)
 
                         after_equals = False
                         continue

bleach/linkifier.py

@@ -228,7 +228,7 @@ def __init__(
         :arg re email_re: email matching regex
 
         """
-        super(LinkifyFilter, self).__init__(source)
+        super().__init__(source)
 
         self.callbacks = callbacks or []
         self.skip_tags = skip_tags or []
@@ -332,8 +332,7 @@ def handle_email_addresses(self, src_iter):
                     if end < len(text):
                         new_tokens.append({"type": "Characters", "data": text[end:]})
 
-                    for new_token in new_tokens:
-                        yield new_token
+                    yield from new_tokens
 
                     continue
 
@@ -460,8 +459,7 @@ def handle_links(self, src_iter):
                     if end < len(text):
                         new_tokens.append({"type": "Characters", "data": text[end:]})
 
-                    for new_token in new_tokens:
-                        yield new_token
+                    yield from new_tokens
 
                     continue
 
@@ -499,8 +497,7 @@ def handle_a_tag(self, token_buffer):
                 # The callbacks didn't change the text, so we yield the new "a"
                 # token, then whatever else was there, then the end "a" token
                 yield a_token
-                for mem in token_buffer[1:]:
-                    yield mem
+                yield from token_buffer[1:]
 
             else:
                 # If the callbacks changed the text, then we're going to drop
@@ -516,16 +513,15 @@ def __iter__(self):
 
         token_buffer = []
 
-        for token in super(LinkifyFilter, self).__iter__():
+        for token in super().__iter__():
             if in_a:
                 # Handle the case where we're in an "a" tag--we want to buffer tokens
                 # until we hit an end "a" tag.
                 if token["type"] == "EndTag" and token["name"] == "a":
                     # Add the end tag to the token buffer and then handle them
                     # and yield anything returned
                     token_buffer.append(token)
-                    for new_token in self.handle_a_tag(token_buffer):
-                        yield new_token
+                    yield from self.handle_a_tag(token_buffer)
 
                     # Clear "a" related state and continue since we've yielded all
                     # the tokens we're going to yield

bleach/sanitizer.py

@@ -280,7 +280,7 @@ def __init__(
             category=DeprecationWarning,
             module="bleach._vendor.html5lib",
         )
-        return super(BleachSanitizerFilter, self).__init__(source, **kwargs)
+        return super().__init__(source, **kwargs)
 
     def sanitize_stream(self, token_iterator):
         for token in token_iterator:
@@ -290,8 +290,7 @@ def sanitize_stream(self, token_iterator):
                 continue
 
             if isinstance(ret, list):
-                for subtoken in ret:
-                    yield subtoken
+                yield from ret
             else:
                 yield ret
 
@@ -575,7 +574,7 @@ def disallowed_token(self, token):
                 if ns is None or ns not in html5lib_shim.prefixes:
                     namespaced_name = name
                 else:
-                    namespaced_name = "%s:%s" % (html5lib_shim.prefixes[ns], name)
+                    namespaced_name = "{}:{}".format(html5lib_shim.prefixes[ns], name)
 
                 attrs.append(
                     ' %s="%s"'
@@ -587,7 +586,7 @@ def disallowed_token(self, token):
                         v,
                     )
                 )
-            token["data"] = "<%s%s>" % (token["name"], "".join(attrs))
+            token["data"] = "<{}{}>".format(token["name"], "".join(attrs))
 
         else:
             token["data"] = "<%s>" % token["name"]

docs/conf.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 #
 # Bleach documentation build configuration file, created by
 # sphinx-quickstart on Fri May 11 21:11:39 2012.
@@ -40,8 +39,8 @@
 master_doc = 'index'
 
 # General information about the project.
-project = u'Bleach'
-copyright = u'2012-2015, James Socol; 2015-2017, Mozilla Foundation'
+project = 'Bleach'
+copyright = '2012-2015, James Socol; 2015-2017, Mozilla Foundation'
 
 # The version info for the project you're documenting, acts as replacement for
 # |version| and |release|, also used in various other places throughout the
@@ -196,8 +195,8 @@
 # Grouping the document tree into LaTeX files. List of tuples
 # (source start file, target name, title, author, documentclass [howto/manual]).
 latex_documents = [
-  ('index', 'Bleach.tex', u'Bleach Documentation',
-   u'Will Kahn-Greene', 'manual'),
+  ('index', 'Bleach.tex', 'Bleach Documentation',
+   'Will Kahn-Greene', 'manual'),
 ]
 
 # The name of an image file (relative to this directory) to place at the top of
@@ -226,8 +225,8 @@
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
 man_pages = [
-    ('index', 'bleach', u'Bleach Documentation',
-     [u'Will Kahn-Greene'], 1)
+    ('index', 'bleach', 'Bleach Documentation',
+     ['Will Kahn-Greene'], 1)
 ]
 
 # If true, show URL addresses after external links.
@@ -240,8 +239,8 @@
 # (source start file, target name, title, author,
 #  dir menu entry, description, category)
 texinfo_documents = [
-  ('index', 'Bleach', u'Bleach Documentation',
-   u'Will Kahn-Greene', 'Bleach', 'One line description of project.',
+  ('index', 'Bleach', 'Bleach Documentation',
+   'Will Kahn-Greene', 'Bleach', 'One line description of project.',
    'Miscellaneous'),
 ]
 

scripts/run_tests.sh

@@ -23,10 +23,10 @@ case "${MODE}" in
     tox -e docs
     ;;
   format)
-    black --target-version=py36 bleach/*.py tests/ tests_website/
+    black --target-version=py37 bleach/*.py tests/ tests_website/
     ;;
   format-check)
-    black --target-version=py36 --check --diff bleach/*.py tests/ tests_website/
+    black --target-version=py37 --check --diff bleach/*.py tests/ tests_website/
     ;;
   check-reqs)
     mv requirements-dev.txt requirements-dev.txt.orig

setup.cfg

@@ -14,6 +14,3 @@ max-line-length = 100
 
 [tool:pytest]
 addopts = -W error:html5lib:DeprecationWarning
-
-[wheel]
-universal=1

setup.py

@@ -16,18 +16,18 @@
 
 
 def get_long_desc():
-    with io.open('README.rst', encoding='utf-8') as fp:
+    with open('README.rst', encoding='utf-8') as fp:
         desc = fp.read()
     desc += '\n\n'
-    with io.open('CHANGES', encoding='utf-8') as fp:
+    with open('CHANGES', encoding='utf-8') as fp:
         desc += fp.read()
     return desc
 
 
 def get_version():
     fn = os.path.join('bleach', '__init__.py')
     vsre = r"""^__version__ = ['"]([^'"]*)['"]"""
-    with io.open(fn, encoding='utf-8') as fp:
+    with open(fn, encoding='utf-8') as fp:
         version_file = fp.read()
     return re.search(vsre, version_file, re.M).group(1)
 
@@ -45,7 +45,7 @@ def get_version():
     include_package_data=True,
     package_data={'': ['README.rst']},
     zip_safe=False,
-    python_requires='>=3.6',
+    python_requires='>=3.7',
     install_requires=install_requires,
     classifiers=[
         'Development Status :: 5 - Production/Stable',
@@ -55,7 +55,7 @@ def get_version():
         'Operating System :: OS Independent',
         'Programming Language :: Python',
         'Programming Language :: Python :: 3 :: Only',
-        'Programming Language :: Python :: 3.6',
+        'Programming Language :: Python :: 3',
         'Programming Language :: Python :: 3.7',
         'Programming Language :: Python :: 3.8',
         'Programming Language :: Python :: 3.9',

tests/test_linkify.py

@@ -48,7 +48,7 @@ def test_mangle_link():
     def filter_url(attrs, new=False):
         if not attrs.get((None, "href"), "").startswith("http://bouncer"):
             quoted = quote_plus(attrs[(None, "href")])
-            attrs[(None, "href")] = "http://bouncer/?u={0!s}".format(quoted)
+            attrs[(None, "href")] = "http://bouncer/?u={!s}".format(quoted)
         return attrs
 
     assert (

tests/test_unicode.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import pytest
 
 from bleach import clean, linkify

tests_website/data_to_json.py

@@ -39,7 +39,7 @@ def main():
     for infn in ins:
         case_name = infn.rsplit(".test", 1)[0]
 
-        with open(infn, "r") as fin:
+        with open(infn) as fin:
             data, expected = fin.read().split("\n--\n")
             data = data.strip()
             expected = expected.strip()

tests_website/open_test_page.py

@@ -36,4 +36,4 @@
             browser = webbrowser.get(browser_name)
             browser.open_new_tab("http://localhost:8080")
         except Exception as error:
-            print("error getting test browser %s: %s" % (browser_name, error))
+            print("error getting test browser {}: {}".format(browser_name, error))

tests_website/server.py

@@ -27,7 +27,7 @@ class BleachCleanHandler(http.server.SimpleHTTPRequestHandler):
     def do_POST(self):
         content_len = int(self.headers.get("content-length", 0))
         body = self.rfile.read(content_len)
-        print("read %s bytes: %s" % (content_len, body))
+        print("read {} bytes: {}".format(content_len, body))
 
         body = body.decode("utf-8")
         print("input: %r" % body)

tox.ini

@@ -2,8 +2,8 @@
 
 [tox]
 envlist =
-    py{36,37,38,39,310,py3}
-    py{36,37,38,39,310}-build-no-lang
+    py{37,38,39,310,py3}
+    py{37,38,39,310}-build-no-lang
     docs
     format-check
     lint
@@ -16,12 +16,6 @@ commands =
     pytest {posargs:-v}
     python setup.py build
 
-[testenv:py36-build-no-lang]
-setenv =
-    LANG=
-commands =
-    python setup.py build
-
 [testenv:py37-build-no-lang]
 setenv =
     LANG=