SickGear/lib/feedparser/parsers/loose.py

# The loose feed parser that interfaces with an SGML parsing library
# Copyright 2010-2023 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.


class LooseXMLParser:
    contentparams = None

    def __init__(self, baseuri=None, baselang=None, encoding=None, entities=None):
        self.baseuri = baseuri or ""
        self.lang = baselang or None
        self.encoding = encoding or "utf-8"  # character encoding
        self.entities = entities or {}
        super().__init__()

    @staticmethod
    def _normalize_attributes(kv):
        k = kv[0].lower()
        v = k in ("rel", "type") and kv[1].lower() or kv[1]
        # the sgml parser doesn't handle entities in attributes, nor
        # does it pass the attribute values through as unicode, while
        # strict xml parsers do -- account for this difference
        v = v.replace("&amp;", "&")
        return k, v

    def decode_entities(self, element, data):
        data = data.replace("&#60;", "&lt;")
        data = data.replace("&#x3c;", "&lt;")
        data = data.replace("&#x3C;", "&lt;")
        data = data.replace("&#62;", "&gt;")
        data = data.replace("&#x3e;", "&gt;")
        data = data.replace("&#x3E;", "&gt;")
        data = data.replace("&#38;", "&amp;")
        data = data.replace("&#x26;", "&amp;")
        data = data.replace("&#34;", "&quot;")
        data = data.replace("&#x22;", "&quot;")
        data = data.replace("&#39;", "&apos;")
        data = data.replace("&#x27;", "&apos;")
        if not self.contentparams.get("type", "xml").endswith("xml"):
            data = data.replace("&lt;", "<")
            data = data.replace("&gt;", ">")
            data = data.replace("&amp;", "&")
            data = data.replace("&quot;", '"')
            data = data.replace("&apos;", "'")
            data = data.replace("&#x2f;", "/")
            data = data.replace("&#x2F;", "/")
        return data

    @staticmethod
    def strattrs(attrs):
        return "".join(' {}="{}"'.format(n, v.replace('"', "&quot;")) for n, v in attrs)