Merge pull request #1 from Mic92/python2.7-removal

Only support python versions that receive security update

Author: ashleysommer

.appveyor.yml

@@ -12,9 +12,6 @@ jobs:
         os: [ubuntu-latest, windows-latest]
         deps: [base, optional]
         include:
-          - python: "pypy-2.7"
-            os: ubuntu-latest
-            deps: base
           - python: "pypy-3.10"
             os: ubuntu-latest
             deps: base

.github/workflows/python-tox.yml

@@ -29,7 +29,7 @@ or:
 
 By default, the ``document`` will be an ``xml.etree`` element instance.
 Whenever possible, html5lib chooses the accelerated ``ElementTree``
-implementation (i.e. ``xml.etree.cElementTree`` on Python 2.x).
+implementation.
 
 Two other tree types are supported: ``xml.dom.minidom`` and
 ``lxml.etree``. To use an alternative format, specify the name of
@@ -41,18 +41,6 @@ a treebuilder:
   with open("mydocument.html", "rb") as f:
       lxml_etree_document = html5lib.parse(f, treebuilder="lxml")
 
-When using with ``urllib2`` (Python 2), the charset from HTTP should be
-pass into html5lib as follows:
-
-.. code-block:: python
-
-  from contextlib import closing
-  from urllib2 import urlopen
-  import html5lib
-
-  with closing(urlopen("http://example.com/")) as f:
-      document = html5lib.parse(f, transport_encoding=f.info().getparam("charset"))
-
 When using with ``urllib.request`` (Python 3), the charset from HTTP
 should be pass into html5lib as follows:
 
@@ -90,7 +78,7 @@ More documentation is available at https://html5lib.readthedocs.io/.
 Installation
 ------------
 
-html5lib works on CPython 2.7+, CPython 3.5+ and PyPy. To install:
+html5lib works on CPython 3.8+ and PyPy. To install:
 
 .. code-block:: bash
 

README.rst

@@ -1,4 +1,3 @@
-from __future__ import print_function, unicode_literals
 
 import platform
 import sys

debug-info.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 #
 # html5lib documentation build configuration file, created by
 # sphinx-quickstart on Wed May  8 00:04:49 2013.
@@ -100,7 +99,7 @@
 }
 
 
-class CExtMock(object):
+class CExtMock:
     """Required for autodoc on readthedocs.org where you cannot build C extensions."""
     def __init__(self, *args, **kwargs):
         pass

doc/conf.py

@@ -20,7 +20,6 @@
 * :func:`~.serializer.serialize`
 """
 
-from __future__ import absolute_import, division, unicode_literals
 
 from .html5parser import HTMLParser, parse, parseFragment
 from .treebuilders import getTreeBuilder

html5lib/__init__.py

@@ -1,4 +1,3 @@
-from __future__ import absolute_import, division, unicode_literals
 
 import re
 import warnings
@@ -181,7 +180,7 @@ def escapeRegexp(string):
 nonPubidCharRegexp = re.compile("[^\x20\x0D\x0Aa-zA-Z0-9\\-'()+,./:=?;!*#@$_%]")
 
 
-class InfosetFilter(object):
+class InfosetFilter:
     replacementRegexp = re.compile(r"U[\dA-F]{5,5}")
 
     def __init__(self,

html5lib/_ihatexml.py

@@ -1,4 +1,3 @@
-from __future__ import absolute_import, division, unicode_literals
 
 from six import text_type
 from six.moves import http_client, urllib
@@ -48,7 +47,7 @@
 charsUntilRegEx = {}
 
 
-class BufferedStream(object):
+class BufferedStream:
     """Buffering for streams that do not have buffering of their own
 
     The buffer is implemented as a list of chunks on the assumption that
@@ -145,7 +144,7 @@ def HTMLInputStream(source, **kwargs):
         return HTMLBinaryInputStream(source, **kwargs)
 
 
-class HTMLUnicodeInputStream(object):
+class HTMLUnicodeInputStream:
     """Provides a unicode stream of characters to the HTMLTokenizer.
 
     This class takes care of character encoding and removing or replacing
@@ -673,7 +672,7 @@ def jumpTo(self, bytes):
         return True
 
 
-class EncodingParser(object):
+class EncodingParser:
     """Mini parser for detecting character encoding from meta elements"""
 
     def __init__(self, data):
@@ -861,7 +860,7 @@ def getAttribute(self):
                 attrValue.append(c)
 
 
-class ContentAttrParser(object):
+class ContentAttrParser:
     def __init__(self, data):
         assert isinstance(data, bytes)
         self.data = data

html5lib/_inputstream.py

@@ -1,4 +1,3 @@
-from __future__ import absolute_import, division, unicode_literals
 
 from six import unichr as chr
 
@@ -24,7 +23,7 @@
     attributeMap = OrderedDict
 
 
-class HTMLTokenizer(object):
+class HTMLTokenizer:
     """ This class takes care of tokenizing HTML.
 
     * self.currentToken

html5lib/_tokenizer.py

@@ -1,4 +1,3 @@
-from __future__ import absolute_import, division, unicode_literals
 
 from .py import Trie