Remove Python 2.7 support (#8760)

* mvt remove ext2 packages * update readme * rm ext2 folder * Update main readme * Stop testing Python 2.7, add Python 3.9 * Update feedparser
pymedusa · Nov 24, 2020 · 1fd5d6c · 1fd5d6c
1 parent ccc0e2a
commit 1fd5d6c
Show file tree

Hide file tree

Showing 330 changed files with 2,184 additions and 66,947 deletions.
diff --git a/.travis.yml b/.travis.yml
@@ -56,12 +56,6 @@ jobs:
         - yarn lint-css
         - yarn test
         - yarn coverage
-    # backend tests (py2.7) start here
-    - name: 'Backend tests (py2.7)'
-      python: '2.7'
-      env:
-        - TOXENV=py27
-      <<: *_backend_tests
     # backend tests (py3.6) start here
     - name: 'Backend tests (py3.6)'
       python: '3.6'
@@ -80,6 +74,12 @@ jobs:
       env:
         - TOXENV=py38
       <<: *_backend_tests
+    # backend tests (py3.9) start here
+    - name: 'Backend tests (py3.9)'
+      python: '3.9'
+      env:
+        - TOXENV=py39
+      <<: *_backend_tests
     # dredd tests (py3.7) start here
     - name: 'Dredd tests (py3.7)'
       python: '3.7'

diff --git a/ext/feedparser/__init__.py b/ext/feedparser/__init__.py
@@ -1,4 +1,4 @@
-# Copyright 2010-2015 Kurt McKee <contactme@kurtmckee.org>
+# Copyright 2010-2020 Kurt McKee <contactme@kurtmckee.org>
 # Copyright 2002-2008 Mark Pilgrim
 # All rights reserved.
 #
@@ -25,22 +25,20 @@
 # ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
 # POSSIBILITY OF SUCH DAMAGE."""
 
-from __future__ import absolute_import, unicode_literals
+from .api import parse
+from .datetimes import registerDateHandler
+from .exceptions import *
+from .util import FeedParserDict
 
 __author__ = 'Kurt McKee <contactme@kurtmckee.org>'
 __license__ = 'BSD 2-clause'
-__version__ = '5.2.1'
+__version__ = '6.0.2'
 
 # HTTP "User-Agent" header to send to servers when downloading feeds.
 # If you are embedding feedparser in a larger application, you should
 # change this to your application name and URL.
 USER_AGENT = "feedparser/%s +https://github.com/kurtmckee/feedparser/" % __version__
 
-from . import api
-from .api import parse
-from .datetimes import registerDateHandler
-from .exceptions import *
-
 # If you want feedparser to automatically resolve all relative URIs, set this
 # to 1.
 RESOLVE_RELATIVE_URIS = 1

diff --git a/ext/feedparser/api.py b/ext/feedparser/api.py
@@ -1,5 +1,5 @@
 # The public API for feedparser
-# Copyright 2010-2015 Kurt McKee <contactme@kurtmckee.org>
+# Copyright 2010-2020 Kurt McKee <contactme@kurtmckee.org>
 # Copyright 2002-2008 Mark Pilgrim
 # All rights reserved.
 #
@@ -26,27 +26,10 @@
 # ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
 # POSSIBILITY OF SUCH DAMAGE.
 
-from __future__ import absolute_import, unicode_literals
-
+import io
+import urllib.parse
 import xml.sax
 
-try:
-    from io import BytesIO as _StringIO
-except ImportError:
-    try:
-        from cStringIO import StringIO as _StringIO
-    except ImportError:
-        from StringIO import StringIO as _StringIO
-
-try:
-    import urllib.parse
-except ImportError:
-    from urlparse import urlparse
-
-    class urllib(object):
-        class parse(object):
-            urlparse = staticmethod(urlparse)
-
 from .datetimes import registerDateHandler, _parse_date
 from .encodings import convert_to_utf8
 from .exceptions import *
@@ -58,17 +41,9 @@ class parse(object):
 from .parsers.strict import _StrictFeedParser
 from .sanitizer import replace_doctype
 from .sgml import *
-from .urls import _convert_to_idn, _makeSafeAbsoluteURI
+from .urls import convert_to_idn, make_safe_absolute_uri
 from .util import FeedParserDict
 
-bytes_ = type(b'')
-unicode_ = type('')
-try:
-    unichr
-    basestring
-except NameError:
-    unichr = chr
-    basestring = str
 
 # List of preferred XML parsers, by SAX driver name.  These will be tried first,
 # but if they're not installed, Python will keep searching through its own list
@@ -96,6 +71,7 @@ class parse(object):
     'cdf': 'CDF',
 }
 
+
 def _open_resource(url_file_stream_or_string, etag, modified, agent, referrer, handlers, request_headers, result):
     """URL, filename, or string --> stream
 
@@ -127,13 +103,13 @@ def _open_resource(url_file_stream_or_string, etag, modified, agent, referrer, h
     if request_headers is supplied it is a dictionary of HTTP request headers
     that will override the values generated by FeedParser.
 
-    :return: A :class:`StringIO.StringIO` or :class:`io.BytesIO`.
+    :return: A bytes object.
     """
 
     if hasattr(url_file_stream_or_string, 'read'):
         return url_file_stream_or_string.read()
 
-    if isinstance(url_file_stream_or_string, basestring) \
+    if isinstance(url_file_stream_or_string, str) \
        and urllib.parse.urlparse(url_file_stream_or_string)[0] in ('http', 'https', 'ftp', 'file', 'feed'):
         return http.get(url_file_stream_or_string, etag, modified, agent, referrer, handlers, request_headers, result)
 
@@ -142,7 +118,7 @@ def _open_resource(url_file_stream_or_string, etag, modified, agent, referrer, h
         with open(url_file_stream_or_string, 'rb') as f:
             data = f.read()
     except (IOError, UnicodeEncodeError, TypeError, ValueError):
-        # if url_file_stream_or_string is a unicode object that
+        # if url_file_stream_or_string is a str object that
         # cannot be converted to the encoding returned by
         # sys.getfilesystemencoding(), a UnicodeEncodeError
         # will be thrown
@@ -154,19 +130,26 @@ def _open_resource(url_file_stream_or_string, etag, modified, agent, referrer, h
         return data
 
     # treat url_file_stream_or_string as string
-    if not isinstance(url_file_stream_or_string, bytes_):
+    if not isinstance(url_file_stream_or_string, bytes):
         return url_file_stream_or_string.encode('utf-8')
     return url_file_stream_or_string
 
-LooseFeedParser = type(str('LooseFeedParser'), (
-    _LooseFeedParser, _FeedParserMixin, _BaseHTMLProcessor, object
-), {})
-StrictFeedParser = type(str('StrictFeedParser'), (
-    _StrictFeedParser, _FeedParserMixin, xml.sax.handler.ContentHandler, object
-), {})
+
+LooseFeedParser = type(
+    'LooseFeedParser',
+    (_LooseFeedParser, _FeedParserMixin, _BaseHTMLProcessor, object),
+    {},
+)
+
+StrictFeedParser = type(
+    'StrictFeedParser',
+    (_StrictFeedParser, _FeedParserMixin, xml.sax.handler.ContentHandler, object),
+    {},
+)
+
 
 def parse(url_file_stream_or_string, etag=None, modified=None, agent=None, referrer=None, handlers=None, request_headers=None, response_headers=None, resolve_relative_uris=None, sanitize_html=None):
-    '''Parse a feed from a URL, file, stream, or string.
+    """Parse a feed from a URL, file, stream, or string.
 
     :param url_file_stream_or_string:
         File-like object, URL, file path, or string. Both byte and text strings
@@ -210,7 +193,8 @@ def parse(url_file_stream_or_string, etag=None, modified=None, agent=None, refer
         :data:`feedparser.SANITIZE_HTML`, which is ``True``.
 
     :return: A :class:`FeedParserDict`.
-    '''
+    """
+
     if not agent or sanitize_html is None or resolve_relative_uris is None:
         import feedparser
     if not agent:
@@ -221,10 +205,10 @@ def parse(url_file_stream_or_string, etag=None, modified=None, agent=None, refer
         resolve_relative_uris = feedparser.RESOLVE_RELATIVE_URIS
 
     result = FeedParserDict(
-        bozo = False,
-        entries = [],
-        feed = FeedParserDict(),
-        headers = {},
+        bozo=False,
+        entries=[],
+        feed=FeedParserDict(),
+        headers={},
     )
 
     data = _open_resource(url_file_stream_or_string, etag, modified, agent, referrer, handlers, request_headers, result)
@@ -243,10 +227,10 @@ def parse(url_file_stream_or_string, etag=None, modified=None, agent=None, refer
     # Ensure that baseuri is an absolute URI using an acceptable URI scheme.
     contentloc = result['headers'].get('content-location', '')
     href = result.get('href', '')
-    baseuri = _makeSafeAbsoluteURI(href, contentloc) or _makeSafeAbsoluteURI(contentloc) or href
+    baseuri = make_safe_absolute_uri(href, contentloc) or make_safe_absolute_uri(contentloc) or href
 
     baselang = result['headers'].get('content-language', None)
-    if isinstance(baselang, bytes_) and baselang is not None:
+    if isinstance(baselang, bytes) and baselang is not None:
         baselang = baselang.decode('utf-8', 'ignore')
 
     if not _XML_AVAILABLE:
@@ -266,20 +250,20 @@ def parse(url_file_stream_or_string, etag=None, modified=None, agent=None, refer
         saxparser.setContentHandler(feedparser)
         saxparser.setErrorHandler(feedparser)
         source = xml.sax.xmlreader.InputSource()
-        source.setByteStream(_StringIO(data))
+        source.setByteStream(io.BytesIO(data))
         try:
             saxparser.parse(source)
         except xml.sax.SAXException as e:
             result['bozo'] = 1
             result['bozo_exception'] = feedparser.exc or e
             use_strict_parser = 0
-    if not use_strict_parser and _SGML_AVAILABLE:
+    if not use_strict_parser:
         feedparser = LooseFeedParser(baseuri, baselang, 'utf-8', entities)
         feedparser.resolve_relative_uris = resolve_relative_uris
         feedparser.sanitize_html = sanitize_html
         feedparser.feed(data.decode('utf-8', 'replace'))
     result['feed'] = feedparser.feeddata
     result['entries'] = feedparser.entries
     result['version'] = result['version'] or feedparser.version
-    result['namespaces'] = feedparser.namespacesInUse
+    result['namespaces'] = feedparser.namespaces_in_use
     return result
diff --git a/ext/feedparser/datetimes/__init__.py b/ext/feedparser/datetimes/__init__.py
@@ -1,4 +1,29 @@
-from __future__ import absolute_import
+# Copyright 2010-2020 Kurt McKee <contactme@kurtmckee.org>
+# Copyright 2002-2008 Mark Pilgrim
+# All rights reserved.
+#
+# This file is a part of feedparser.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+# * Redistributions of source code must retain the above copyright notice,
+#   this list of conditions and the following disclaimer.
+# * Redistributions in binary form must reproduce the above copyright notice,
+#   this list of conditions and the following disclaimer in the documentation
+#   and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS'
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
 
 from .asctime import _parse_date_asctime
 from .greek import _parse_date_greek
@@ -10,18 +35,21 @@
 from .w3dtf import _parse_date_w3dtf
 
 _date_handlers = []
+
+
 def registerDateHandler(func):
-    '''Register a date handler function (takes string, returns 9-tuple date in GMT)'''
+    """Register a date handler function (takes string, returns 9-tuple date in GMT)"""
     _date_handlers.insert(0, func)
 
-def _parse_date(dateString):
-    '''Parses a variety of date formats into a 9-tuple in GMT'''
-    if not dateString:
+
+def _parse_date(date_string):
+    """Parses a variety of date formats into a 9-tuple in GMT"""
+    if not date_string:
         return None
     for handler in _date_handlers:
         try:
-            date9tuple = handler(dateString)
-        except (KeyError, OverflowError, ValueError):
+            date9tuple = handler(date_string)
+        except (KeyError, OverflowError, ValueError, AttributeError):
             continue
         if not date9tuple:
             continue
@@ -30,6 +58,7 @@ def _parse_date(dateString):
         return date9tuple
     return None
 
+
 registerDateHandler(_parse_date_onblog)
 registerDateHandler(_parse_date_nate)
 registerDateHandler(_parse_date_greek)

diff --git a/ext/feedparser/datetimes/asctime.py b/ext/feedparser/datetimes/asctime.py
@@ -1,9 +1,48 @@
-from __future__ import absolute_import, unicode_literals
+# Copyright 2010-2020 Kurt McKee <contactme@kurtmckee.org>
+# Copyright 2002-2008 Mark Pilgrim
+# All rights reserved.
+#
+# This file is a part of feedparser.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+# * Redistributions of source code must retain the above copyright notice,
+#   this list of conditions and the following disclaimer.
+# * Redistributions in binary form must reproduce the above copyright notice,
+#   this list of conditions and the following disclaimer in the documentation
+#   and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS'
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
 
 from .rfc822 import _parse_date_rfc822
 
-_months = ['jan', 'feb', 'mar', 'apr', 'may', 'jun',
-           'jul', 'aug', 'sep', 'oct', 'nov', 'dec']
+_months = [
+    'jan',
+    'feb',
+    'mar',
+    'apr',
+    'may',
+    'jun',
+    'jul',
+    'aug',
+    'sep',
+    'oct',
+    'nov',
+    'dec',
+]
+
+
 def _parse_date_asctime(dt):
     """Parse asctime-style dates.