4 files changed, 999 insertions, 279 deletions

diff --git a/bitbake/lib/bs4/builder/__init__.py b/bitbake/lib/bs4/builder/__init__.py
index 6ccd4d23d6..ffb31fc25e 100644
--- a/bitbake/lib/bs4/builder/__init__.py
+++ b/bitbake/lib/bs4/builder/__init__.py
@@ -1,11 +1,21 @@
+# Use of this source code is governed by the MIT license.
+__license__ = "MIT"
+
 from collections import defaultdict
 import itertools
+import re
+import warnings
 import sys
 from bs4.element import (
     CharsetMetaAttributeValue,
     ContentMetaAttributeValue,
-    whitespace_re
-    )
+    RubyParenthesisString,
+    RubyTextString,
+    Stylesheet,
+    Script,
+    TemplateString,
+    nonwhitespace_re
+)
 
 __all__ = [
     'HTMLTreeBuilder',
@@ -22,20 +32,41 @@ XML = 'xml'
 HTML = 'html'
 HTML_5 = 'html5'
 
+class XMLParsedAsHTMLWarning(UserWarning):
+    """The warning issued when an HTML parser is used to parse
+    XML that is not XHTML.
+    """
+    MESSAGE = """It looks like you're parsing an XML document using an HTML parser. If this really is an HTML document (maybe it's XHTML?), you can ignore or filter this warning. If it's XML, you should know that using an XML parser will be more reliable. To parse this document as XML, make sure you have the lxml package installed, and pass the keyword argument `features="xml"` into the BeautifulSoup constructor."""
+
 
 class TreeBuilderRegistry(object):
-
+    """A way of looking up TreeBuilder subclasses by their name or by desired
+    features.
+    """
+    
     def __init__(self):
         self.builders_for_feature = defaultdict(list)
         self.builders = []
 
     def register(self, treebuilder_class):
-        """Register a treebuilder based on its advertised features."""
+        """Register a treebuilder based on its advertised features.
+
+        :param treebuilder_class: A subclass of Treebuilder. its .features
+           attribute should list its features.
+        """
         for feature in treebuilder_class.features:
             self.builders_for_feature[feature].insert(0, treebuilder_class)
         self.builders.insert(0, treebuilder_class)
 
     def lookup(self, *features):
+        """Look up a TreeBuilder subclass with the desired features.
+
+        :param features: A list of features to look for. If none are
+            provided, the most recently registered TreeBuilder subclass
+            will be used.
+        :return: A TreeBuilder subclass, or None if there's no
+            registered subclass with all the requested features.
+        """
         if len(self.builders) == 0:
             # There are no builders at all.
             return None
@@ -78,7 +109,7 @@ class TreeBuilderRegistry(object):
 builder_registry = TreeBuilderRegistry()
 
 class TreeBuilder(object):
-    """Turn a document into a Beautiful Soup object tree."""
+    """Turn a textual document into a Beautiful Soup object tree."""
 
     NAME = "[Unknown tree builder]"
     ALTERNATE_NAMES = []
@@ -86,19 +117,89 @@ class TreeBuilder(object):
 
     is_xml = False
     picklable = False
-    preserve_whitespace_tags = set()
     empty_element_tags = None # A tag will be considered an empty-element
                               # tag when and only when it has no contents.
-
+    
     # A value for these tag/attribute combinations is a space- or
     # comma-separated list of CDATA, rather than a single CDATA.
-    cdata_list_attributes = {}
-
-
-    def __init__(self):
+    DEFAULT_CDATA_LIST_ATTRIBUTES = defaultdict(list)
+
+    # Whitespace should be preserved inside these tags.
+    DEFAULT_PRESERVE_WHITESPACE_TAGS = set()
+
+    # The textual contents of tags with these names should be
+    # instantiated with some class other than NavigableString.
+    DEFAULT_STRING_CONTAINERS = {}
+    
+    USE_DEFAULT = object()
+
+    # Most parsers don't keep track of line numbers.
+    TRACKS_LINE_NUMBERS = False
+    
+    def __init__(self, multi_valued_attributes=USE_DEFAULT,
+                 preserve_whitespace_tags=USE_DEFAULT,
+                 store_line_numbers=USE_DEFAULT,
+                 string_containers=USE_DEFAULT,
+    ):
+        """Constructor.
+
+        :param multi_valued_attributes: If this is set to None, the
+         TreeBuilder will not turn any values for attributes like
+         'class' into lists. Setting this to a dictionary will
+         customize this behavior; look at DEFAULT_CDATA_LIST_ATTRIBUTES
+         for an example.
+
+         Internally, these are called "CDATA list attributes", but that
+         probably doesn't make sense to an end-user, so the argument name
+         is `multi_valued_attributes`.
+
+        :param preserve_whitespace_tags: A list of tags to treat
+         the way <pre> tags are treated in HTML. Tags in this list
+         are immune from pretty-printing; their contents will always be
+         output as-is.
+
+        :param string_containers: A dictionary mapping tag names to
+        the classes that should be instantiated to contain the textual
+        contents of those tags. The default is to use NavigableString
+        for every tag, no matter what the name. You can override the
+        default by changing DEFAULT_STRING_CONTAINERS.
+
+        :param store_line_numbers: If the parser keeps track of the
+         line numbers and positions of the original markup, that
+         information will, by default, be stored in each corresponding
+         `Tag` object. You can turn this off by passing
+         store_line_numbers=False. If the parser you're using doesn't 
+         keep track of this information, then setting store_line_numbers=True
+         will do nothing.
+        """
         self.soup = None
-
+        if multi_valued_attributes is self.USE_DEFAULT:
+            multi_valued_attributes = self.DEFAULT_CDATA_LIST_ATTRIBUTES
+        self.cdata_list_attributes = multi_valued_attributes
+        if preserve_whitespace_tags is self.USE_DEFAULT:
+            preserve_whitespace_tags = self.DEFAULT_PRESERVE_WHITESPACE_TAGS
+        self.preserve_whitespace_tags = preserve_whitespace_tags
+        if store_line_numbers == self.USE_DEFAULT:
+            store_line_numbers = self.TRACKS_LINE_NUMBERS
+        self.store_line_numbers = store_line_numbers 
+        if string_containers == self.USE_DEFAULT:
+            string_containers = self.DEFAULT_STRING_CONTAINERS
+        self.string_containers = string_containers
+        
+    def initialize_soup(self, soup):
+        """The BeautifulSoup object has been initialized and is now
+        being associated with the TreeBuilder.
+
+        :param soup: A BeautifulSoup object.
+        """
+        self.soup = soup
+        
     def reset(self):
+        """Do any work necessary to reset the underlying parser
+        for a new document.
+
+        By default, this does nothing.
+        """
         pass
 
     def can_be_empty_element(self, tag_name):
@@ -110,24 +211,58 @@ class TreeBuilder(object):
         For instance: an HTMLBuilder does not consider a <p> tag to be
         an empty-element tag (it's not in
         HTMLBuilder.empty_element_tags). This means an empty <p> tag
-        will be presented as "<p></p>", not "<p />".
+        will be presented as "<p></p>", not "<p/>" or "<p>".
 
         The default implementation has no opinion about which tags are
         empty-element tags, so a tag will be presented as an
-        empty-element tag if and only if it has no contents.
-        "<foo></foo>" will become "<foo />", and "<foo>bar</foo>" will
+        empty-element tag if and only if it has no children.
+        "<foo></foo>" will become "<foo/>", and "<foo>bar</foo>" will
         be left alone.
+
+        :param tag_name: The name of a markup tag.
         """
         if self.empty_element_tags is None:
             return True
         return tag_name in self.empty_element_tags
-
+    
     def feed(self, markup):
+        """Run some incoming markup through some parsing process,
+        populating the `BeautifulSoup` object in self.soup.
+
+        This method is not implemented in TreeBuilder; it must be
+        implemented in subclasses.
+
+        :return: None.
+        """
         raise NotImplementedError()
 
     def prepare_markup(self, markup, user_specified_encoding=None,
-                       document_declared_encoding=None):
-        return markup, None, None, False
+                       document_declared_encoding=None, exclude_encodings=None):
+        """Run any preliminary steps necessary to make incoming markup
+        acceptable to the parser.
+
+        :param markup: Some markup -- probably a bytestring.
+        :param user_specified_encoding: The user asked to try this encoding.
+        :param document_declared_encoding: The markup itself claims to be
+            in this encoding. NOTE: This argument is not used by the
+            calling code and can probably be removed.
+        :param exclude_encodings: The user asked _not_ to try any of
+            these encodings.
+
+        :yield: A series of 4-tuples:
+         (markup, encoding, declared encoding,
+          has undergone character replacement)
+
+         Each 4-tuple represents a strategy for converting the
+         document to Unicode and parsing it. Each strategy will be tried 
+         in turn.
+
+         By default, the only strategy is to parse the markup
+         as-is. See `LXMLTreeBuilderForXML` and
+         `HTMLParserTreeBuilder` for implementations that take into
+         account the quirks of particular parsers.
+        """
+        yield markup, None, None, False
 
     def test_fragment_to_document(self, fragment):
         """Wrap an HTML fragment to make it look like a document.
@@ -139,16 +274,36 @@ class TreeBuilder(object):
         results against other HTML fragments.
 
         This method should not be used outside of tests.
+
+        :param fragment: A string -- fragment of HTML.
+        :return: A string -- a full HTML document.
         """
         return fragment
 
     def set_up_substitutions(self, tag):
+        """Set up any substitutions that will need to be performed on 
+        a `Tag` when it's output as a string.
+
+        By default, this does nothing. See `HTMLTreeBuilder` for a
+        case where this is used.
+
+        :param tag: A `Tag`
+        :return: Whether or not a substitution was performed.
+        """
         return False
 
     def _replace_cdata_list_attribute_values(self, tag_name, attrs):
-        """Replaces class="foo bar" with class=["foo", "bar"]
+        """When an attribute value is associated with a tag that can
+        have multiple values for that attribute, convert the string
+        value to a list of strings.
 
-        Modifies its input in place.
+        Basically, replaces class="foo bar" with class=["foo", "bar"]
+
+        NOTE: This method modifies its input in place.
+
+        :param tag_name: The name of a tag.
+        :param attrs: A dictionary containing the tag's attributes.
+           Any appropriate attribute values will be modified in place.
         """
         if not attrs:
             return attrs
@@ -163,7 +318,7 @@ class TreeBuilder(object):
                     # values. Split it into a list.
                     value = attrs[attr]
                     if isinstance(value, str):
-                        values = whitespace_re.split(value)
+                        values = nonwhitespace_re.findall(value)
                     else:
                         # html5lib sometimes calls setAttributes twice
                         # for the same tag when rearranging the parse
@@ -174,9 +329,13 @@ class TreeBuilder(object):
                         values = value
                     attrs[attr] = values
         return attrs
-
+    
 class SAXTreeBuilder(TreeBuilder):
-    """A Beautiful Soup treebuilder that listens for SAX events."""
+    """A Beautiful Soup treebuilder that listens for SAX events.
+
+    This is not currently used for anything, but it demonstrates
+    how a simple TreeBuilder would work.
+    """
 
     def feed(self, markup):
         raise NotImplementedError()
@@ -186,11 +345,11 @@ class SAXTreeBuilder(TreeBuilder):
 
     def startElement(self, name, attrs):
         attrs = dict((key[1], value) for key, value in list(attrs.items()))
-        #print "Start %s, %r" % (name, attrs)
+        #print("Start %s, %r" % (name, attrs))
         self.soup.handle_starttag(name, attrs)
 
     def endElement(self, name):
-        #print "End %s" % name
+        #print("End %s" % name)
         self.soup.handle_endtag(name)
 
     def startElementNS(self, nsTuple, nodeName, attrs):
@@ -227,10 +386,44 @@ class HTMLTreeBuilder(TreeBuilder):
     Such as which tags are empty-element tags.
     """
 
-    preserve_whitespace_tags = set(['pre', 'textarea'])
-    empty_element_tags = set(['br' , 'hr', 'input', 'img', 'meta',
-                              'spacer', 'link', 'frame', 'base'])
-
+    empty_element_tags = set([
+        # These are from HTML5.
+        'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'keygen', 'link', 'menuitem', 'meta', 'param', 'source', 'track', 'wbr',
+        
+        # These are from earlier versions of HTML and are removed in HTML5.
+        'basefont', 'bgsound', 'command', 'frame', 'image', 'isindex', 'nextid', 'spacer'
+    ])
+
+    # The HTML standard defines these as block-level elements. Beautiful
+    # Soup does not treat these elements differently from other elements,
+    # but it may do so eventually, and this information is available if
+    # you need to use it.
+    block_elements = set(["address", "article", "aside", "blockquote", "canvas", "dd", "div", "dl", "dt", "fieldset", "figcaption", "figure", "footer", "form", "h1", "h2", "h3", "h4", "h5", "h6", "header", "hr", "li", "main", "nav", "noscript", "ol", "output", "p", "pre", "section", "table", "tfoot", "ul", "video"])
+
+    # These HTML tags need special treatment so they can be
+    # represented by a string class other than NavigableString.
+    #
+    # For some of these tags, it's because the HTML standard defines
+    # an unusual content model for them. I made this list by going
+    # through the HTML spec
+    # (https://html.spec.whatwg.org/#metadata-content) and looking for
+    # "metadata content" elements that can contain strings.
+    #
+    # The Ruby tags (<rt> and <rp>) are here despite being normal
+    # "phrasing content" tags, because the content they contain is
+    # qualitatively different from other text in the document, and it
+    # can be useful to be able to distinguish it.
+    #
+    # TODO: Arguably <noscript> could go here but it seems
+    # qualitatively different from the other tags.
+    DEFAULT_STRING_CONTAINERS = {
+        'rt' : RubyTextString,
+        'rp' : RubyParenthesisString,
+        'style': Stylesheet,
+        'script': Script,
+        'template': TemplateString,
+    }    
+    
     # The HTML standard defines these attributes as containing a
     # space-separated list of values, not a single value. That is,
     # class="foo bar" means that the 'class' attribute has two values,
@@ -238,7 +431,7 @@ class HTMLTreeBuilder(TreeBuilder):
     # encounter one of these attributes, we will parse its value into
     # a list of values if possible. Upon output, the list will be
     # converted back into a string.
-    cdata_list_attributes = {
+    DEFAULT_CDATA_LIST_ATTRIBUTES = {
         "*" : ['class', 'accesskey', 'dropzone'],
         "a" : ['rel', 'rev'],
         "link" :  ['rel', 'rev'],
@@ -255,7 +448,19 @@ class HTMLTreeBuilder(TreeBuilder):
         "output" : ["for"],
         }
 
+    DEFAULT_PRESERVE_WHITESPACE_TAGS = set(['pre', 'textarea'])
+
     def set_up_substitutions(self, tag):
+        """Replace the declared encoding in a <meta> tag with a placeholder,
+        to be substituted when the tag is output to a string.
+
+        An HTML document may come in to Beautiful Soup as one
+        encoding, but exit in a different encoding, and the <meta> tag
+        needs to be changed to reflect this.
+
+        :param tag: A `Tag`
+        :return: Whether or not a substitution was performed.
+        """
         # We are only interested in <meta> tags
         if tag.name != 'meta':
             return False
@@ -288,10 +493,107 @@ class HTMLTreeBuilder(TreeBuilder):
 
         return (meta_encoding is not None)
 
+class DetectsXMLParsedAsHTML(object):
+    """A mixin class for any class (a TreeBuilder, or some class used by a
+    TreeBuilder) that's in a position to detect whether an XML
+    document is being incorrectly parsed as HTML, and issue an
+    appropriate warning.
+
+    This requires being able to observe an incoming processing
+    instruction that might be an XML declaration, and also able to
+    observe tags as they're opened. If you can't do that for a given
+    TreeBuilder, there's a less reliable implementation based on
+    examining the raw markup.
+    """
+
+    # Regular expression for seeing if markup has an <html> tag.
+    LOOKS_LIKE_HTML = re.compile("<[^ +]html", re.I)
+    LOOKS_LIKE_HTML_B = re.compile(b"<[^ +]html", re.I)
+
+    XML_PREFIX = '<?xml'
+    XML_PREFIX_B = b'<?xml'
+    
+    @classmethod
+    def warn_if_markup_looks_like_xml(cls, markup, stacklevel=3):
+        """Perform a check on some markup to see if it looks like XML
+        that's not XHTML. If so, issue a warning.
+
+        This is much less reliable than doing the check while parsing,
+        but some of the tree builders can't do that.
+
+        :param stacklevel: The stacklevel of the code calling this
+        function.
+
+        :return: True if the markup looks like non-XHTML XML, False
+        otherwise.
+
+        """
+        if isinstance(markup, bytes):
+            prefix = cls.XML_PREFIX_B
+            looks_like_html = cls.LOOKS_LIKE_HTML_B
+        else:
+            prefix = cls.XML_PREFIX
+            looks_like_html = cls.LOOKS_LIKE_HTML
+        
+        if (markup is not None
+            and markup.startswith(prefix)
+            and not looks_like_html.search(markup[:500])
+        ):
+            cls._warn(stacklevel=stacklevel+2)
+            return True
+        return False
+
+    @classmethod
+    def _warn(cls, stacklevel=5):
+        """Issue a warning about XML being parsed as HTML."""
+        warnings.warn(
+            XMLParsedAsHTMLWarning.MESSAGE, XMLParsedAsHTMLWarning,
+            stacklevel=stacklevel
+        )
+        
+    def _initialize_xml_detector(self):
+        """Call this method before parsing a document."""
+        self._first_processing_instruction = None
+        self._root_tag = None
+       
+    def _document_might_be_xml(self, processing_instruction):
+        """Call this method when encountering an XML declaration, or a
+        "processing instruction" that might be an XML declaration.
+        """
+        if (self._first_processing_instruction is not None
+            or self._root_tag is not None):
+            # The document has already started. Don't bother checking
+            # anymore.
+            return
+
+        self._first_processing_instruction = processing_instruction
+
+        # We won't know until we encounter the first tag whether or
+        # not this is actually a problem.
+        
+    def _root_tag_encountered(self, name):
+        """Call this when you encounter the document's root tag.
+
+        This is where we actually check whether an XML document is
+        being incorrectly parsed as HTML, and issue the warning.
+        """
+        if self._root_tag is not None:
+            # This method was incorrectly called multiple times. Do
+            # nothing.
+            return
+
+        self._root_tag = name
+        if (name != 'html' and self._first_processing_instruction is not None
+            and self._first_processing_instruction.lower().startswith('xml ')):
+            # We encountered an XML declaration and then a tag other
+            # than 'html'. This is a reliable indicator that a
+            # non-XHTML document is being parsed as XML.
+            self._warn()
+
+    
 def register_treebuilders_from(module):
     """Copy TreeBuilders from the given module into this module."""
-    # I'm fairly sure this is not the best way to do this.
-    this_module = sys.modules['bs4.builder']
+    this_module = sys.modules[__name__]
     for name in module.__all__:
         obj = getattr(module, name)
 
@@ -302,12 +604,22 @@ def register_treebuilders_from(module):
             this_module.builder_registry.register(obj)
 
 class ParserRejectedMarkup(Exception):
-    pass
-
+    """An Exception to be raised when the underlying parser simply
+    refuses to parse the given markup.
+    """
+    def __init__(self, message_or_exception):
+        """Explain why the parser rejected the given markup, either
+        with a textual explanation or another exception.
+        """
+        if isinstance(message_or_exception, Exception):
+            e = message_or_exception
+            message_or_exception = "%s: %s" % (e.__class__.__name__, str(e))
+        super(ParserRejectedMarkup, self).__init__(message_or_exception)
+            
 # Builders are registered in reverse order of priority, so that custom
 # builder registrations will take precedence. In general, we want lxml
 # to take precedence over html5lib, because it's faster. And we only
-# want to use HTMLParser as a last result.
+# want to use HTMLParser as a last resort.
 from . import _htmlparser
 register_treebuilders_from(_htmlparser)
 try:
diff --git a/bitbake/lib/bs4/builder/_html5lib.py b/bitbake/lib/bs4/builder/_html5lib.py
index 9e9216ef9c..7c46a85118 100644
--- a/bitbake/lib/bs4/builder/_html5lib.py
+++ b/bitbake/lib/bs4/builder/_html5lib.py
@@ -1,9 +1,14 @@
+# Use of this source code is governed by the MIT license.
+__license__ = "MIT"
+
 __all__ = [
     'HTML5TreeBuilder',
     ]
 
 import warnings
+import re
 from bs4.builder import (
+    DetectsXMLParsedAsHTML,
     PERMISSIVE,
     HTML,
     HTML_5,
@@ -11,17 +16,13 @@ from bs4.builder import (
     )
 from bs4.element import (
     NamespacedAttribute,
-    whitespace_re,
+    nonwhitespace_re,
 )
 import html5lib
-try:
-    # html5lib >= 0.99999999/1.0b9
-    from html5lib.treebuilders import base as treebuildersbase
-except ImportError:
-    # html5lib <= 0.9999999/1.0b8
-    from html5lib.treebuilders import _base as treebuildersbase
-from html5lib.constants import namespaces
-
+from html5lib.constants import (
+    namespaces,
+    prefixes,
+    )
 from bs4.element import (
     Comment,
     Doctype,
@@ -29,13 +30,37 @@ from bs4.element import (
     Tag,
     )
 
+try:
+    # Pre-0.99999999
+    from html5lib.treebuilders import _base as treebuilder_base
+    new_html5lib = False
+except ImportError as e:
+    # 0.99999999 and up
+    from html5lib.treebuilders import base as treebuilder_base
+    new_html5lib = True
+
 class HTML5TreeBuilder(HTMLTreeBuilder):
-    """Use html5lib to build a tree."""
+    """Use html5lib to build a tree.
+
+    Note that this TreeBuilder does not support some features common
+    to HTML TreeBuilders. Some of these features could theoretically
+    be implemented, but at the very least it's quite difficult,
+    because html5lib moves the parse tree around as it's being built.
+
+    * This TreeBuilder doesn't use different subclasses of NavigableString
+      based on the name of the tag in which the string was found.
+
+    * You can't use a SoupStrainer to parse only part of a document.
+    """
 
     NAME = "html5lib"
 
     features = [NAME, PERMISSIVE, HTML_5, HTML]
 
+    # html5lib can tell us which line number and position in the
+    # original file is the source of an element.
+    TRACKS_LINE_NUMBERS = True
+    
     def prepare_markup(self, markup, user_specified_encoding,
                        document_declared_encoding=None, exclude_encodings=None):
         # Store the user-specified encoding for use later on.
@@ -45,27 +70,56 @@ class HTML5TreeBuilder(HTMLTreeBuilder):
         # ATM because the html5lib TreeBuilder doesn't use
         # UnicodeDammit.
         if exclude_encodings:
-            warnings.warn("You provided a value for exclude_encoding, but the html5lib tree builder doesn't support exclude_encoding.")
+            warnings.warn(
+                "You provided a value for exclude_encoding, but the html5lib tree builder doesn't support exclude_encoding.",
+                stacklevel=3
+            )
+
+        # html5lib only parses HTML, so if it's given XML that's worth
+        # noting.
+        DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(
+            markup, stacklevel=3
+        )
+
         yield (markup, None, None, False)
 
     # These methods are defined by Beautiful Soup.
     def feed(self, markup):
         if self.soup.parse_only is not None:
-            warnings.warn("You provided a value for parse_only, but the html5lib tree builder doesn't support parse_only. The entire document will be parsed.")
+            warnings.warn(
+                "You provided a value for parse_only, but the html5lib tree builder doesn't support parse_only. The entire document will be parsed.",
+                stacklevel=4
+            )
         parser = html5lib.HTMLParser(tree=self.create_treebuilder)
-        doc = parser.parse(markup, encoding=self.user_specified_encoding)
-
+        self.underlying_builder.parser = parser
+        extra_kwargs = dict()
+        if not isinstance(markup, str):
+            if new_html5lib:
+                extra_kwargs['override_encoding'] = self.user_specified_encoding
+            else:
+                extra_kwargs['encoding'] = self.user_specified_encoding
+        doc = parser.parse(markup, **extra_kwargs)
+        
         # Set the character encoding detected by the tokenizer.
         if isinstance(markup, str):
             # We need to special-case this because html5lib sets
             # charEncoding to UTF-8 if it gets Unicode input.
             doc.original_encoding = None
         else:
-            doc.original_encoding = parser.tokenizer.stream.charEncoding[0]
-
+            original_encoding = parser.tokenizer.stream.charEncoding[0]
+            if not isinstance(original_encoding, str):
+                # In 0.99999999 and up, the encoding is an html5lib
+                # Encoding object. We want to use a string for compatibility
+                # with other tree builders.
+                original_encoding = original_encoding.name
+            doc.original_encoding = original_encoding
+        self.underlying_builder.parser = None
+            
     def create_treebuilder(self, namespaceHTMLElements):
         self.underlying_builder = TreeBuilderForHtml5lib(
-            self.soup, namespaceHTMLElements)
+            namespaceHTMLElements, self.soup,
+            store_line_numbers=self.store_line_numbers
+        )
         return self.underlying_builder
 
     def test_fragment_to_document(self, fragment):
@@ -73,12 +127,30 @@ class HTML5TreeBuilder(HTMLTreeBuilder):
         return '<html><head></head><body>%s</body></html>' % fragment
 
 
-class TreeBuilderForHtml5lib(treebuildersbase.TreeBuilder):
-
-    def __init__(self, soup, namespaceHTMLElements):
-        self.soup = soup
+class TreeBuilderForHtml5lib(treebuilder_base.TreeBuilder):
+    
+    def __init__(self, namespaceHTMLElements, soup=None,
+                 store_line_numbers=True, **kwargs):
+        if soup:
+            self.soup = soup
+        else:
+            from bs4 import BeautifulSoup
+            # TODO: Why is the parser 'html.parser' here? To avoid an
+            # infinite loop?
+            self.soup = BeautifulSoup(
+                "", "html.parser", store_line_numbers=store_line_numbers,
+                **kwargs
+            )
+        # TODO: What are **kwargs exactly? Should they be passed in
+        # here in addition to/instead of being passed to the BeautifulSoup
+        # constructor?
         super(TreeBuilderForHtml5lib, self).__init__(namespaceHTMLElements)
 
+        # This will be set later to an html5lib.html5parser.HTMLParser
+        # object, which we can use to track the current line number.
+        self.parser = None
+        self.store_line_numbers = store_line_numbers
+        
     def documentClass(self):
         self.soup.reset()
         return Element(self.soup, self.soup, None)
@@ -92,14 +164,26 @@ class TreeBuilderForHtml5lib(treebuildersbase.TreeBuilder):
         self.soup.object_was_parsed(doctype)
 
     def elementClass(self, name, namespace):
-        tag = self.soup.new_tag(name, namespace)
+        kwargs = {}
+        if self.parser and self.store_line_numbers:
+            # This represents the point immediately after the end of the
+            # tag. We don't know when the tag started, but we do know
+            # where it ended -- the character just before this one.
+            sourceline, sourcepos = self.parser.tokenizer.stream.position()
+            kwargs['sourceline'] = sourceline
+            kwargs['sourcepos'] = sourcepos-1
+        tag = self.soup.new_tag(name, namespace, **kwargs)
+
         return Element(tag, self.soup, namespace)
 
     def commentClass(self, data):
         return TextNode(Comment(data), self.soup)
 
     def fragmentClass(self):
-        self.soup = BeautifulSoup("")
+        from bs4 import BeautifulSoup
+        # TODO: Why is the parser 'html.parser' here? To avoid an
+        # infinite loop?
+        self.soup = BeautifulSoup("", "html.parser")
         self.soup.name = "[document_fragment]"
         return Element(self.soup, self.soup, None)
 
@@ -111,7 +195,57 @@ class TreeBuilderForHtml5lib(treebuildersbase.TreeBuilder):
         return self.soup
 
     def getFragment(self):
-        return treebuildersbase.TreeBuilder.getFragment(self).element
+        return treebuilder_base.TreeBuilder.getFragment(self).element
+
+    def testSerializer(self, element):
+        from bs4 import BeautifulSoup
+        rv = []
+        doctype_re = re.compile(r'^(.*?)(?: PUBLIC "(.*?)"(?: "(.*?)")?| SYSTEM "(.*?)")?$')
+
+        def serializeElement(element, indent=0):
+            if isinstance(element, BeautifulSoup):
+                pass
+            if isinstance(element, Doctype):
+                m = doctype_re.match(element)
+                if m:
+                    name = m.group(1)
+                    if m.lastindex > 1:
+                        publicId = m.group(2) or ""
+                        systemId = m.group(3) or m.group(4) or ""
+                        rv.append("""|%s<!DOCTYPE %s "%s" "%s">""" %
+                                  (' ' * indent, name, publicId, systemId))
+                    else:
+                        rv.append("|%s<!DOCTYPE %s>" % (' ' * indent, name))
+                else:
+                    rv.append("|%s<!DOCTYPE >" % (' ' * indent,))
+            elif isinstance(element, Comment):
+                rv.append("|%s<!-- %s -->" % (' ' * indent, element))
+            elif isinstance(element, NavigableString):
+                rv.append("|%s\"%s\"" % (' ' * indent, element))
+            else:
+                if element.namespace:
+                    name = "%s %s" % (prefixes[element.namespace],
+                                      element.name)
+                else:
+                    name = element.name
+                rv.append("|%s<%s>" % (' ' * indent, name))
+                if element.attrs:
+                    attributes = []
+                    for name, value in list(element.attrs.items()):
+                        if isinstance(name, NamespacedAttribute):
+                            name = "%s %s" % (prefixes[name.namespace], name.name)
+                        if isinstance(value, list):
+                            value = " ".join(value)
+                        attributes.append((name, value))
+
+                    for name, value in sorted(attributes):
+                        rv.append('|%s%s="%s"' % (' ' * (indent + 2), name, value))
+                indent += 2
+                for child in element.children:
+                    serializeElement(child, indent)
+        serializeElement(element, 0)
+
+        return "\n".join(rv)
 
 class AttrList(object):
     def __init__(self, element):
@@ -122,14 +256,14 @@ class AttrList(object):
     def __setitem__(self, name, value):
         # If this attribute is a multi-valued attribute for this element,
         # turn its value into a list.
-        list_attr = HTML5TreeBuilder.cdata_list_attributes
-        if (name in list_attr['*']
+        list_attr = self.element.cdata_list_attributes or {}
+        if (name in list_attr.get('*', [])
             or (self.element.name in list_attr
-                and name in list_attr[self.element.name])):
+                and name in list_attr.get(self.element.name, []))):
             # A node that is being cloned may have already undergone
             # this procedure.
             if not isinstance(value, list):
-                value = whitespace_re.split(value)
+                value = nonwhitespace_re.findall(value)
         self.element[name] = value
     def items(self):
         return list(self.attrs.items())
@@ -143,9 +277,9 @@ class AttrList(object):
         return name in list(self.attrs.keys())
 
 
-class Element(treebuildersbase.Node):
+class Element(treebuilder_base.Node):
     def __init__(self, element, soup, namespace):
-        treebuildersbase.Node.__init__(self, element.name)
+        treebuilder_base.Node.__init__(self, element.name)
         self.element = element
         self.soup = soup
         self.namespace = namespace
@@ -164,13 +298,15 @@ class Element(treebuildersbase.Node):
             child = node
         elif node.element.__class__ == NavigableString:
             string_child = child = node.element
+            node.parent = self
         else:
             child = node.element
+            node.parent = self
 
         if not isinstance(child, str) and child.parent is not None:
             node.element.extract()
 
-        if (string_child and self.element.contents
+        if (string_child is not None and self.element.contents
             and self.element.contents[-1].__class__ == NavigableString):
             # We are appending a string onto another string.
             # TODO This has O(n^2) performance, for input like
@@ -203,12 +339,12 @@ class Element(treebuildersbase.Node):
                 most_recent_element=most_recent_element)
 
     def getAttributes(self):
+        if isinstance(self.element, Comment):
+            return {}
         return AttrList(self.element)
 
     def setAttributes(self, attributes):
-
         if attributes is not None and len(attributes) > 0:
-
             converted_attributes = []
             for name, value in list(attributes.items()):
                 if isinstance(name, tuple):
@@ -230,11 +366,11 @@ class Element(treebuildersbase.Node):
     attributes = property(getAttributes, setAttributes)
 
     def insertText(self, data, insertBefore=None):
+        text = TextNode(self.soup.new_string(data), self.soup)
         if insertBefore:
-            text = TextNode(self.soup.new_string(data), self.soup)
-            self.insertBefore(data, insertBefore)
+            self.insertBefore(text, insertBefore)
         else:
-            self.appendChild(data)
+            self.appendChild(text)
 
     def insertBefore(self, node, refNode):
         index = self.element.index(refNode.element)
@@ -253,9 +389,10 @@ class Element(treebuildersbase.Node):
 
     def reparentChildren(self, new_parent):
         """Move all of this tag's children into another tag."""
-        # print "MOVE", self.element.contents
-        # print "FROM", self.element
-        # print "TO", new_parent.element
+        # print("MOVE", self.element.contents)
+        # print("FROM", self.element)
+        # print("TO", new_parent.element)
+
         element = self.element
         new_parent_element = new_parent.element
         # Determine what this tag's next_element will be once all the children
@@ -274,29 +411,35 @@ class Element(treebuildersbase.Node):
             new_parents_last_descendant_next_element = new_parent_element.next_element
 
         to_append = element.contents
-        append_after = new_parent_element.contents
         if len(to_append) > 0:
             # Set the first child's previous_element and previous_sibling
             # to elements within the new parent
             first_child = to_append[0]
-            if new_parents_last_descendant:
+            if new_parents_last_descendant is not None:
                 first_child.previous_element = new_parents_last_descendant
             else:
                 first_child.previous_element = new_parent_element
             first_child.previous_sibling = new_parents_last_child
-            if new_parents_last_descendant:
+            if new_parents_last_descendant is not None:
                 new_parents_last_descendant.next_element = first_child
             else:
                 new_parent_element.next_element = first_child
-            if new_parents_last_child:
+            if new_parents_last_child is not None:
                 new_parents_last_child.next_sibling = first_child
 
-            # Fix the last child's next_element and next_sibling
-            last_child = to_append[-1]
-            last_child.next_element = new_parents_last_descendant_next_element
-            if new_parents_last_descendant_next_element:
-                new_parents_last_descendant_next_element.previous_element = last_child
-            last_child.next_sibling = None
+            # Find the very last element being moved. It is now the
+            # parent's last descendant. It has no .next_sibling and
+            # its .next_element is whatever the previous last
+            # descendant had.
+            last_childs_last_descendant = to_append[-1]._last_descendant(False, True)
+
+            last_childs_last_descendant.next_element = new_parents_last_descendant_next_element
+            if new_parents_last_descendant_next_element is not None:
+                # TODO: This code has no test coverage and I'm not sure
+                # how to get html5lib to go through this path, but it's
+                # just the other side of the previous line.
+                new_parents_last_descendant_next_element.previous_element = last_childs_last_descendant
+            last_childs_last_descendant.next_sibling = None
 
         for child in to_append:
             child.parent = new_parent_element
@@ -306,9 +449,9 @@ class Element(treebuildersbase.Node):
         element.contents = []
         element.next_element = final_next_element
 
-        # print "DONE WITH MOVE"
-        # print "FROM", self.element
-        # print "TO", new_parent_element
+        # print("DONE WITH MOVE")
+        # print("FROM", self.element)
+        # print("TO", new_parent_element)
 
     def cloneNode(self):
         tag = self.soup.new_tag(self.element.name, self.namespace)
@@ -321,7 +464,7 @@ class Element(treebuildersbase.Node):
         return self.element.contents
 
     def getNameTuple(self):
-        if self.namespace is None:
+        if self.namespace == None:
             return namespaces["html"], self.name
         else:
             return self.namespace, self.name
@@ -330,7 +473,7 @@ class Element(treebuildersbase.Node):
 
 class TextNode(Element):
     def __init__(self, element, soup):
-        treebuildersbase.Node.__init__(self, None)
+        treebuilder_base.Node.__init__(self, None)
         self.element = element
         self.soup = soup
 
diff --git a/bitbake/lib/bs4/builder/_htmlparser.py b/bitbake/lib/bs4/builder/_htmlparser.py
index bb0a63f2f3..3cc187f892 100644
--- a/bitbake/lib/bs4/builder/_htmlparser.py
+++ b/bitbake/lib/bs4/builder/_htmlparser.py
@@ -1,35 +1,18 @@
+# encoding: utf-8
 """Use the HTMLParser library to parse HTML files that aren't too bad."""
 
+# Use of this source code is governed by the MIT license.
+__license__ = "MIT"
+
 __all__ = [
     'HTMLParserTreeBuilder',
     ]
 
 from html.parser import HTMLParser
 
-try:
-    from html.parser import HTMLParseError
-except ImportError as e:
-    # HTMLParseError is removed in Python 3.5. Since it can never be
-    # thrown in 3.5, we can just define our own class as a placeholder.
-    class HTMLParseError(Exception):
-        pass
-
 import sys
 import warnings
 
-# Starting in Python 3.2, the HTMLParser constructor takes a 'strict'
-# argument, which we'd like to set to False. Unfortunately,
-# http://bugs.python.org/issue13273 makes strict=True a better bet
-# before Python 3.2.3.
-#
-# At the end of this file, we monkeypatch HTMLParser so that
-# strict=True works well on Python 3.2.2.
-major, minor, release = sys.version_info[:3]
-CONSTRUCTOR_TAKES_STRICT = major == 3 and minor == 2 and release >= 3
-CONSTRUCTOR_STRICT_IS_DEPRECATED = major == 3 and minor == 3
-CONSTRUCTOR_TAKES_CONVERT_CHARREFS = major == 3 and minor >= 4
-
-
 from bs4.element import (
     CData,
     Comment,
@@ -40,6 +23,8 @@ from bs4.element import (
 from bs4.dammit import EntitySubstitution, UnicodeDammit
 
 from bs4.builder import (
+    DetectsXMLParsedAsHTML,
+    ParserRejectedMarkup,
     HTML,
     HTMLTreeBuilder,
     STRICT,
@@ -48,8 +33,84 @@ from bs4.builder import (
 
 HTMLPARSER = 'html.parser'
 
-class BeautifulSoupHTMLParser(HTMLParser):
-    def handle_starttag(self, name, attrs):
+class BeautifulSoupHTMLParser(HTMLParser, DetectsXMLParsedAsHTML):
+    """A subclass of the Python standard library's HTMLParser class, which
+    listens for HTMLParser events and translates them into calls
+    to Beautiful Soup's tree construction API.
+    """
+
+    # Strategies for handling duplicate attributes
+    IGNORE = 'ignore'
+    REPLACE = 'replace'
+    
+    def __init__(self, *args, **kwargs):
+        """Constructor.
+
+        :param on_duplicate_attribute: A strategy for what to do if a
+            tag includes the same attribute more than once. Accepted
+            values are: REPLACE (replace earlier values with later
+            ones, the default), IGNORE (keep the earliest value
+            encountered), or a callable. A callable must take three
+            arguments: the dictionary of attributes already processed,
+            the name of the duplicate attribute, and the most recent value
+            encountered.           
+        """
+        self.on_duplicate_attribute = kwargs.pop(
+            'on_duplicate_attribute', self.REPLACE
+        )
+        HTMLParser.__init__(self, *args, **kwargs)
+
+        # Keep a list of empty-element tags that were encountered
+        # without an explicit closing tag. If we encounter a closing tag
+        # of this type, we'll associate it with one of those entries.
+        #
+        # This isn't a stack because we don't care about the
+        # order. It's a list of closing tags we've already handled and
+        # will ignore, assuming they ever show up.
+        self.already_closed_empty_element = []
+
+        self._initialize_xml_detector()
+
+    def error(self, message):
+        # NOTE: This method is required so long as Python 3.9 is
+        # supported. The corresponding code is removed from HTMLParser
+        # in 3.5, but not removed from ParserBase until 3.10.
+        # https://github.com/python/cpython/issues/76025
+        #
+        # The original implementation turned the error into a warning,
+        # but in every case I discovered, this made HTMLParser
+        # immediately crash with an error message that was less
+        # helpful than the warning. The new implementation makes it
+        # more clear that html.parser just can't parse this
+        # markup. The 3.10 implementation does the same, though it
+        # raises AssertionError rather than calling a method. (We
+        # catch this error and wrap it in a ParserRejectedMarkup.)
+        raise ParserRejectedMarkup(message)
+
+    def handle_startendtag(self, name, attrs):
+        """Handle an incoming empty-element tag.
+
+        This is only called when the markup looks like <tag/>.
+
+        :param name: Name of the tag.
+        :param attrs: Dictionary of the tag's attributes.
+        """
+        # is_startend() tells handle_starttag not to close the tag
+        # just because its name matches a known empty-element tag. We
+        # know that this is an empty-element tag and we want to call
+        # handle_endtag ourselves.
+        tag = self.handle_starttag(name, attrs, handle_empty_element=False)
+        self.handle_endtag(name)
+        
+    def handle_starttag(self, name, attrs, handle_empty_element=True):
+        """Handle an opening tag, e.g. '<tag>'
+
+        :param name: Name of the tag.
+        :param attrs: Dictionary of the tag's attributes.
+        :param handle_empty_element: True if this tag is known to be
+            an empty-element tag (i.e. there is not expected to be any
+            closing tag).
+        """
         # XXX namespace
         attr_dict = {}
         for key, value in attrs:
@@ -57,20 +118,78 @@ class BeautifulSoupHTMLParser(HTMLParser):
             # for consistency with the other tree builders.
             if value is None:
                 value = ''
-            attr_dict[key] = value
+            if key in attr_dict:
+                # A single attribute shows up multiple times in this
+                # tag. How to handle it depends on the
+                # on_duplicate_attribute setting.
+                on_dupe = self.on_duplicate_attribute
+                if on_dupe == self.IGNORE:
+                    pass
+                elif on_dupe in (None, self.REPLACE):
+                    attr_dict[key] = value
+                else:
+                    on_dupe(attr_dict, key, value)
+            else:
+                attr_dict[key] = value
             attrvalue = '""'
-        self.soup.handle_starttag(name, None, None, attr_dict)
-
-    def handle_endtag(self, name):
-        self.soup.handle_endtag(name)
-
+        #print("START", name)
+        sourceline, sourcepos = self.getpos()
+        tag = self.soup.handle_starttag(
+            name, None, None, attr_dict, sourceline=sourceline,
+            sourcepos=sourcepos
+        )
+        if tag and tag.is_empty_element and handle_empty_element:
+            # Unlike other parsers, html.parser doesn't send separate end tag
+            # events for empty-element tags. (It's handled in
+            # handle_startendtag, but only if the original markup looked like
+            # <tag/>.)
+            #
+            # So we need to call handle_endtag() ourselves. Since we
+            # know the start event is identical to the end event, we
+            # don't want handle_endtag() to cross off any previous end
+            # events for tags of this name.
+            self.handle_endtag(name, check_already_closed=False)
+
+            # But we might encounter an explicit closing tag for this tag
+            # later on. If so, we want to ignore it.
+            self.already_closed_empty_element.append(name)
+
+        if self._root_tag is None:
+            self._root_tag_encountered(name)
+            
+    def handle_endtag(self, name, check_already_closed=True):
+        """Handle a closing tag, e.g. '</tag>'
+        
+        :param name: A tag name.
+        :param check_already_closed: True if this tag is expected to
+           be the closing portion of an empty-element tag,
+           e.g. '<tag></tag>'.
+        """
+        #print("END", name)
+        if check_already_closed and name in self.already_closed_empty_element:
+            # This is a redundant end tag for an empty-element tag.
+            # We've already called handle_endtag() for it, so just
+            # check it off the list.
+            #print("ALREADY CLOSED", name)
+            self.already_closed_empty_element.remove(name)
+        else:
+            self.soup.handle_endtag(name)
+            
     def handle_data(self, data):
+        """Handle some textual data that shows up between tags."""
         self.soup.handle_data(data)
 
     def handle_charref(self, name):
-        # XXX workaround for a bug in HTMLParser. Remove this once
-        # it's fixed in all supported versions.
-        # http://bugs.python.org/issue13633
+        """Handle a numeric character reference by converting it to the
+        corresponding Unicode character and treating it as textual
+        data.
+
+        :param name: Character number, possibly in hexadecimal.
+        """
+        # TODO: This was originally a workaround for a bug in
+        # HTMLParser. (http://bugs.python.org/issue13633) The bug has
+        # been fixed, but removing this code still makes some
+        # Beautiful Soup tests fail. This needs investigation.
         if name.startswith('x'):
             real_name = int(name.lstrip('x'), 16)
         elif name.startswith('X'):
@@ -78,37 +197,71 @@ class BeautifulSoupHTMLParser(HTMLParser):
         else:
             real_name = int(name)
 
-        try:
-            data = chr(real_name)
-        except (ValueError, OverflowError) as e:
-            data = "\N{REPLACEMENT CHARACTER}"
-
+        data = None
+        if real_name < 256:
+            # HTML numeric entities are supposed to reference Unicode
+            # code points, but sometimes they reference code points in
+            # some other encoding (ahem, Windows-1252). E.g. &#147;
+            # instead of &#201; for LEFT DOUBLE QUOTATION MARK. This
+            # code tries to detect this situation and compensate.
+            for encoding in (self.soup.original_encoding, 'windows-1252'):
+                if not encoding:
+                    continue
+                try:
+                    data = bytearray([real_name]).decode(encoding)
+                except UnicodeDecodeError as e:
+                    pass
+        if not data:
+            try:
+                data = chr(real_name)
+            except (ValueError, OverflowError) as e:
+                pass
+        data = data or "\N{REPLACEMENT CHARACTER}"
         self.handle_data(data)
 
     def handle_entityref(self, name):
+        """Handle a named entity reference by converting it to the
+        corresponding Unicode character(s) and treating it as textual
+        data.
+
+        :param name: Name of the entity reference.
+        """
         character = EntitySubstitution.HTML_ENTITY_TO_CHARACTER.get(name)
         if character is not None:
             data = character
         else:
-            data = "&%s;" % name
+            # If this were XML, it would be ambiguous whether "&foo"
+            # was an character entity reference with a missing
+            # semicolon or the literal string "&foo". Since this is
+            # HTML, we have a complete list of all character entity references,
+            # and this one wasn't found, so assume it's the literal string "&foo".
+            data = "&%s" % name
         self.handle_data(data)
 
     def handle_comment(self, data):
+        """Handle an HTML comment.
+
+        :param data: The text of the comment.
+        """
         self.soup.endData()
         self.soup.handle_data(data)
         self.soup.endData(Comment)
 
     def handle_decl(self, data):
+        """Handle a DOCTYPE declaration.
+
+        :param data: The text of the declaration.
+        """
         self.soup.endData()
-        if data.startswith("DOCTYPE "):
-            data = data[len("DOCTYPE "):]
-        elif data == 'DOCTYPE':
-            # i.e. "<!DOCTYPE>"
-            data = ''
+        data = data[len("DOCTYPE "):]
         self.soup.handle_data(data)
         self.soup.endData(Doctype)
 
     def unknown_decl(self, data):
+        """Handle a declaration of unknown type -- probably a CDATA block.
+
+        :param data: The text of the declaration.
+        """
         if data.upper().startswith('CDATA['):
             cls = CData
             data = data[len('CDATA['):]
@@ -119,144 +272,116 @@ class BeautifulSoupHTMLParser(HTMLParser):
         self.soup.endData(cls)
 
     def handle_pi(self, data):
+        """Handle a processing instruction.
+
+        :param data: The text of the instruction.
+        """
         self.soup.endData()
         self.soup.handle_data(data)
+        self._document_might_be_xml(data)
         self.soup.endData(ProcessingInstruction)
 
 
 class HTMLParserTreeBuilder(HTMLTreeBuilder):
-
+    """A Beautiful soup `TreeBuilder` that uses the `HTMLParser` parser,
+    found in the Python standard library.
+    """
     is_xml = False
     picklable = True
     NAME = HTMLPARSER
     features = [NAME, HTML, STRICT]
 
-    def __init__(self, *args, **kwargs):
-        if CONSTRUCTOR_TAKES_STRICT and not CONSTRUCTOR_STRICT_IS_DEPRECATED:
-            kwargs['strict'] = False
-        if CONSTRUCTOR_TAKES_CONVERT_CHARREFS:
-            kwargs['convert_charrefs'] = False
-        self.parser_args = (args, kwargs)
+    # The html.parser knows which line number and position in the
+    # original file is the source of an element.
+    TRACKS_LINE_NUMBERS = True
 
+    def __init__(self, parser_args=None, parser_kwargs=None, **kwargs):
+        """Constructor.
+
+        :param parser_args: Positional arguments to pass into 
+            the BeautifulSoupHTMLParser constructor, once it's
+            invoked.
+        :param parser_kwargs: Keyword arguments to pass into 
+            the BeautifulSoupHTMLParser constructor, once it's
+            invoked.
+        :param kwargs: Keyword arguments for the superclass constructor.
+        """
+        # Some keyword arguments will be pulled out of kwargs and placed
+        # into parser_kwargs.
+        extra_parser_kwargs = dict()
+        for arg in ('on_duplicate_attribute',):
+            if arg in kwargs:
+                value = kwargs.pop(arg)
+                extra_parser_kwargs[arg] = value
+        super(HTMLParserTreeBuilder, self).__init__(**kwargs)
+        parser_args = parser_args or []
+        parser_kwargs = parser_kwargs or {}
+        parser_kwargs.update(extra_parser_kwargs)
+        parser_kwargs['convert_charrefs'] = False
+        self.parser_args = (parser_args, parser_kwargs)
+        
     def prepare_markup(self, markup, user_specified_encoding=None,
                        document_declared_encoding=None, exclude_encodings=None):
-        """
-        :return: A 4-tuple (markup, original encoding, encoding
-        declared within markup, whether any characters had to be
-        replaced with REPLACEMENT CHARACTER).
+
+        """Run any preliminary steps necessary to make incoming markup
+        acceptable to the parser.
+
+        :param markup: Some markup -- probably a bytestring.
+        :param user_specified_encoding: The user asked to try this encoding.
+        :param document_declared_encoding: The markup itself claims to be
+            in this encoding.
+        :param exclude_encodings: The user asked _not_ to try any of
+            these encodings.
+
+        :yield: A series of 4-tuples:
+         (markup, encoding, declared encoding,
+          has undergone character replacement)
+
+         Each 4-tuple represents a strategy for converting the
+         document to Unicode and parsing it. Each strategy will be tried 
+         in turn.
         """
         if isinstance(markup, str):
+            # Parse Unicode as-is.
             yield (markup, None, None, False)
             return
 
+        # Ask UnicodeDammit to sniff the most likely encoding.
+
+        # This was provided by the end-user; treat it as a known
+        # definite encoding per the algorithm laid out in the HTML5
+        # spec.  (See the EncodingDetector class for details.)
+        known_definite_encodings = [user_specified_encoding]
+
+        # This was found in the document; treat it as a slightly lower-priority
+        # user encoding.
+        user_encodings = [document_declared_encoding]
+
         try_encodings = [user_specified_encoding, document_declared_encoding]
-        dammit = UnicodeDammit(markup, try_encodings, is_html=True,
-                               exclude_encodings=exclude_encodings)
+        dammit = UnicodeDammit(
+            markup,
+            known_definite_encodings=known_definite_encodings,
+            user_encodings=user_encodings,
+            is_html=True,
+            exclude_encodings=exclude_encodings
+        )
         yield (dammit.markup, dammit.original_encoding,
                dammit.declared_html_encoding,
                dammit.contains_replacement_characters)
 
     def feed(self, markup):
+        """Run some incoming markup through some parsing process,
+        populating the `BeautifulSoup` object in self.soup.
+        """
         args, kwargs = self.parser_args
         parser = BeautifulSoupHTMLParser(*args, **kwargs)
         parser.soup = self.soup
         try:
             parser.feed(markup)
-        except HTMLParseError as e:
-            warnings.warn(RuntimeWarning(
-                "Python's built-in HTMLParser cannot parse the given document. This is not a bug in Beautiful Soup. The best solution is to install an external parser (lxml or html5lib), and use Beautiful Soup with that parser. See http://www.crummy.com/software/BeautifulSoup/bs4/doc/#installing-a-parser for help."))
-            raise e
-
-# Patch 3.2 versions of HTMLParser earlier than 3.2.3 to use some
-# 3.2.3 code. This ensures they don't treat markup like <p></p> as a
-# string.
-#
-# XXX This code can be removed once most Python 3 users are on 3.2.3.
-if major == 3 and minor == 2 and not CONSTRUCTOR_TAKES_STRICT:
-    import re
-    attrfind_tolerant = re.compile(
-        r'\s*((?<=[\'"\s])[^\s/>][^\s/=>]*)(\s*=+\s*'
-        r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?')
-    HTMLParserTreeBuilder.attrfind_tolerant = attrfind_tolerant
-
-    locatestarttagend = re.compile(r"""
-  <[a-zA-Z][-.a-zA-Z0-9:_]*          # tag name
-  (?:\s+                             # whitespace before attribute name
-    (?:[a-zA-Z_][-.:a-zA-Z0-9_]*     # attribute name
-      (?:\s*=\s*                     # value indicator
-        (?:'[^']*'                   # LITA-enclosed value
-          |\"[^\"]*\"                # LIT-enclosed value
-          |[^'\">\s]+                # bare value
-         )
-       )?
-     )
-   )*
-  \s*                                # trailing whitespace
-""", re.VERBOSE)
-    BeautifulSoupHTMLParser.locatestarttagend = locatestarttagend
-
-    from html.parser import tagfind, attrfind
-
-    def parse_starttag(self, i):
-        self.__starttag_text = None
-        endpos = self.check_for_whole_start_tag(i)
-        if endpos < 0:
-            return endpos
-        rawdata = self.rawdata
-        self.__starttag_text = rawdata[i:endpos]
-
-        # Now parse the data between i+1 and j into a tag and attrs
-        attrs = []
-        match = tagfind.match(rawdata, i+1)
-        assert match, 'unexpected call to parse_starttag()'
-        k = match.end()
-        self.lasttag = tag = rawdata[i+1:k].lower()
-        while k < endpos:
-            if self.strict:
-                m = attrfind.match(rawdata, k)
-            else:
-                m = attrfind_tolerant.match(rawdata, k)
-            if not m:
-                break
-            attrname, rest, attrvalue = m.group(1, 2, 3)
-            if not rest:
-                attrvalue = None
-            elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
-                 attrvalue[:1] == '"' == attrvalue[-1:]:
-                attrvalue = attrvalue[1:-1]
-            if attrvalue:
-                attrvalue = self.unescape(attrvalue)
-            attrs.append((attrname.lower(), attrvalue))
-            k = m.end()
-
-        end = rawdata[k:endpos].strip()
-        if end not in (">", "/>"):
-            lineno, offset = self.getpos()
-            if "\n" in self.__starttag_text:
-                lineno = lineno + self.__starttag_text.count("\n")
-                offset = len(self.__starttag_text) \
-                         - self.__starttag_text.rfind("\n")
-            else:
-                offset = offset + len(self.__starttag_text)
-            if self.strict:
-                self.error("junk characters in start tag: %r"
-                           % (rawdata[k:endpos][:20],))
-            self.handle_data(rawdata[i:endpos])
-            return endpos
-        if end.endswith('/>'):
-            # XHTML-style empty tag: <span attr="value" />
-            self.handle_startendtag(tag, attrs)
-        else:
-            self.handle_starttag(tag, attrs)
-            if tag in self.CDATA_CONTENT_ELEMENTS:
-                self.set_cdata_mode(tag)
-        return endpos
-
-    def set_cdata_mode(self, elem):
-        self.cdata_elem = elem.lower()
-        self.interesting = re.compile(r'</\s*%s\s*>' % self.cdata_elem, re.I)
-
-    BeautifulSoupHTMLParser.parse_starttag = parse_starttag
-    BeautifulSoupHTMLParser.set_cdata_mode = set_cdata_mode
-
-    CONSTRUCTOR_TAKES_STRICT = True
+            parser.close()
+        except AssertionError as e:
+            # html.parser raises AssertionError in rare cases to
+            # indicate a fatal problem with the markup, especially
+            # when there's an error in the doctype declaration.
+            raise ParserRejectedMarkup(e)
+        parser.already_closed_empty_element = []
diff --git a/bitbake/lib/bs4/builder/_lxml.py b/bitbake/lib/bs4/builder/_lxml.py
index 9c6c14ee65..4f7cf74681 100644
--- a/bitbake/lib/bs4/builder/_lxml.py
+++ b/bitbake/lib/bs4/builder/_lxml.py
@@ -1,19 +1,28 @@
+# Use of this source code is governed by the MIT license.
+__license__ = "MIT"
+
 __all__ = [
     'LXMLTreeBuilderForXML',
     'LXMLTreeBuilder',
     ]
 
+try:
+    from collections.abc import Callable # Python 3.6
+except ImportError as e:
+    from collections import Callable
+
 from io import BytesIO
 from io import StringIO
-import collections
 from lxml import etree
 from bs4.element import (
     Comment,
     Doctype,
     NamespacedAttribute,
     ProcessingInstruction,
+    XMLProcessingInstruction,
 )
 from bs4.builder import (
+    DetectsXMLParsedAsHTML,
     FAST,
     HTML,
     HTMLTreeBuilder,
@@ -25,10 +34,15 @@ from bs4.dammit import EncodingDetector
 
 LXML = 'lxml'
 
+def _invert(d):
+    "Invert a dictionary."
+    return dict((v,k) for k, v in list(d.items()))
+
 class LXMLTreeBuilderForXML(TreeBuilder):
     DEFAULT_PARSER_CLASS = etree.XMLParser
 
     is_xml = True
+    processing_instruction_class = XMLProcessingInstruction
 
     NAME = "lxml-xml"
     ALTERNATE_NAMES = ["xml"]
@@ -40,26 +54,79 @@ class LXMLTreeBuilderForXML(TreeBuilder):
 
     # This namespace mapping is specified in the XML Namespace
     # standard.
-    DEFAULT_NSMAPS = {'http://www.w3.org/XML/1998/namespace' : "xml"}
+    DEFAULT_NSMAPS = dict(xml='http://www.w3.org/XML/1998/namespace')
+
+    DEFAULT_NSMAPS_INVERTED = _invert(DEFAULT_NSMAPS)
+
+    # NOTE: If we parsed Element objects and looked at .sourceline,
+    # we'd be able to see the line numbers from the original document.
+    # But instead we build an XMLParser or HTMLParser object to serve
+    # as the target of parse messages, and those messages don't include
+    # line numbers.
+    # See: https://bugs.launchpad.net/lxml/+bug/1846906
+    
+    def initialize_soup(self, soup):
+        """Let the BeautifulSoup object know about the standard namespace
+        mapping.
+
+        :param soup: A `BeautifulSoup`.
+        """
+        super(LXMLTreeBuilderForXML, self).initialize_soup(soup)
+        self._register_namespaces(self.DEFAULT_NSMAPS)
+
+    def _register_namespaces(self, mapping):
+        """Let the BeautifulSoup object know about namespaces encountered
+        while parsing the document.
+
+        This might be useful later on when creating CSS selectors.
+
+        This will track (almost) all namespaces, even ones that were
+        only in scope for part of the document. If two namespaces have
+        the same prefix, only the first one encountered will be
+        tracked. Un-prefixed namespaces are not tracked.
 
+        :param mapping: A dictionary mapping namespace prefixes to URIs.
+        """
+        for key, value in list(mapping.items()):
+            # This is 'if key' and not 'if key is not None' because we
+            # don't track un-prefixed namespaces. Soupselect will
+            # treat an un-prefixed namespace as the default, which
+            # causes confusion in some cases.
+            if key and key not in self.soup._namespaces:
+                # Let the BeautifulSoup object know about a new namespace.
+                # If there are multiple namespaces defined with the same
+                # prefix, the first one in the document takes precedence.
+                self.soup._namespaces[key] = value
+                
     def default_parser(self, encoding):
-        # This can either return a parser object or a class, which
-        # will be instantiated with default arguments.
+        """Find the default parser for the given encoding.
+
+        :param encoding: A string.
+        :return: Either a parser object or a class, which
+          will be instantiated with default arguments.
+        """
         if self._default_parser is not None:
             return self._default_parser
         return etree.XMLParser(
             target=self, strip_cdata=False, recover=True, encoding=encoding)
 
     def parser_for(self, encoding):
+        """Instantiate an appropriate parser for the given encoding.
+
+        :param encoding: A string.
+        :return: A parser object such as an `etree.XMLParser`.
+        """
         # Use the default parser.
         parser = self.default_parser(encoding)
 
-        if isinstance(parser, collections.Callable):
+        if isinstance(parser, Callable):
             # Instantiate the parser with default arguments
-            parser = parser(target=self, strip_cdata=False, encoding=encoding)
+            parser = parser(
+                target=self, strip_cdata=False, recover=True, encoding=encoding
+            )
         return parser
 
-    def __init__(self, parser=None, empty_element_tags=None):
+    def __init__(self, parser=None, empty_element_tags=None, **kwargs):
         # TODO: Issue a warning if parser is present but not a
         # callable, since that means there's no way to create new
         # parsers for different encodings.
@@ -67,8 +134,10 @@ class LXMLTreeBuilderForXML(TreeBuilder):
         if empty_element_tags is not None:
             self.empty_element_tags = set(empty_element_tags)
         self.soup = None
-        self.nsmaps = [self.DEFAULT_NSMAPS]
-
+        self.nsmaps = [self.DEFAULT_NSMAPS_INVERTED]
+        self.active_namespace_prefixes = [dict(self.DEFAULT_NSMAPS)]
+        super(LXMLTreeBuilderForXML, self).__init__(**kwargs)
+        
     def _getNsTag(self, tag):
         # Split the namespace URL out of a fully-qualified lxml tag
         # name. Copied from lxml's src/lxml/sax.py.
@@ -80,16 +149,51 @@ class LXMLTreeBuilderForXML(TreeBuilder):
     def prepare_markup(self, markup, user_specified_encoding=None,
                        exclude_encodings=None,
                        document_declared_encoding=None):
-        """
-        :yield: A series of 4-tuples.
+        """Run any preliminary steps necessary to make incoming markup
+        acceptable to the parser.
+
+        lxml really wants to get a bytestring and convert it to
+        Unicode itself. So instead of using UnicodeDammit to convert
+        the bytestring to Unicode using different encodings, this
+        implementation uses EncodingDetector to iterate over the
+        encodings, and tell lxml to try to parse the document as each
+        one in turn.
+
+        :param markup: Some markup -- hopefully a bytestring.
+        :param user_specified_encoding: The user asked to try this encoding.
+        :param document_declared_encoding: The markup itself claims to be
+            in this encoding.
+        :param exclude_encodings: The user asked _not_ to try any of
+            these encodings.
+
+        :yield: A series of 4-tuples:
          (markup, encoding, declared encoding,
           has undergone character replacement)
 
-        Each 4-tuple represents a strategy for parsing the document.
+         Each 4-tuple represents a strategy for converting the
+         document to Unicode and parsing it. Each strategy will be tried 
+         in turn.
         """
+        is_html = not self.is_xml
+        if is_html:
+            self.processing_instruction_class = ProcessingInstruction
+            # We're in HTML mode, so if we're given XML, that's worth
+            # noting.
+            DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(
+                markup, stacklevel=3
+            )
+        else:
+            self.processing_instruction_class = XMLProcessingInstruction
+
         if isinstance(markup, str):
             # We were given Unicode. Maybe lxml can parse Unicode on
             # this system?
+
+            # TODO: This is a workaround for
+            # https://bugs.launchpad.net/lxml/+bug/1948551.
+            # We can remove it once the upstream issue is fixed.
+            if len(markup) > 0 and markup[0] == u'\N{BYTE ORDER MARK}':
+                markup = markup[1:]
             yield markup, None, document_declared_encoding, False
 
         if isinstance(markup, str):
@@ -98,14 +202,19 @@ class LXMLTreeBuilderForXML(TreeBuilder):
             yield (markup.encode("utf8"), "utf8",
                    document_declared_encoding, False)
 
-        # Instead of using UnicodeDammit to convert the bytestring to
-        # Unicode using different encodings, use EncodingDetector to
-        # iterate over the encodings, and tell lxml to try to parse
-        # the document as each one in turn.
-        is_html = not self.is_xml
-        try_encodings = [user_specified_encoding, document_declared_encoding]
+        # This was provided by the end-user; treat it as a known
+        # definite encoding per the algorithm laid out in the HTML5
+        # spec.  (See the EncodingDetector class for details.)
+        known_definite_encodings = [user_specified_encoding]
+
+        # This was found in the document; treat it as a slightly lower-priority
+        # user encoding.
+        user_encodings = [document_declared_encoding]
         detector = EncodingDetector(
-            markup, try_encodings, is_html, exclude_encodings)
+            markup, known_definite_encodings=known_definite_encodings,
+            user_encodings=user_encodings, is_html=is_html,
+            exclude_encodings=exclude_encodings
+        )
         for encoding in detector.encodings:
             yield (detector.markup, encoding, document_declared_encoding, False)
 
@@ -128,25 +237,45 @@ class LXMLTreeBuilderForXML(TreeBuilder):
                     self.parser.feed(data)
             self.parser.close()
         except (UnicodeDecodeError, LookupError, etree.ParserError) as e:
-            raise ParserRejectedMarkup(str(e))
+            raise ParserRejectedMarkup(e)
 
     def close(self):
-        self.nsmaps = [self.DEFAULT_NSMAPS]
+        self.nsmaps = [self.DEFAULT_NSMAPS_INVERTED]
 
     def start(self, name, attrs, nsmap={}):
         # Make sure attrs is a mutable dict--lxml may send an immutable dictproxy.
         attrs = dict(attrs)
         nsprefix = None
         # Invert each namespace map as it comes in.
-        if len(self.nsmaps) > 1:
-            # There are no new namespaces for this tag, but
-            # non-default namespaces are in play, so we need a
-            # separate tag stack to know when they end.
-            self.nsmaps.append(None)
+        if len(nsmap) == 0 and len(self.nsmaps) > 1:
+                # There are no new namespaces for this tag, but
+                # non-default namespaces are in play, so we need a
+                # separate tag stack to know when they end.
+                self.nsmaps.append(None)
         elif len(nsmap) > 0:
             # A new namespace mapping has come into play.
-            inverted_nsmap = dict((value, key) for key, value in list(nsmap.items()))
-            self.nsmaps.append(inverted_nsmap)
+
+            # First, Let the BeautifulSoup object know about it.
+            self._register_namespaces(nsmap)
+
+            # Then, add it to our running list of inverted namespace
+            # mappings.
+            self.nsmaps.append(_invert(nsmap))
+
+            # The currently active namespace prefixes have
+            # changed. Calculate the new mapping so it can be stored
+            # with all Tag objects created while these prefixes are in
+            # scope.
+            current_mapping = dict(self.active_namespace_prefixes[-1])
+            current_mapping.update(nsmap)
+
+            # We should not track un-prefixed namespaces as we can only hold one
+            # and it will be recognized as the default namespace by soupsieve,
+            # which may be confusing in some situations.
+            if '' in current_mapping:
+                del current_mapping['']
+            self.active_namespace_prefixes.append(current_mapping)
+            
             # Also treat the namespace mapping as a set of attributes on the
             # tag, so we can recreate it later.
             attrs = attrs.copy()
@@ -171,8 +300,11 @@ class LXMLTreeBuilderForXML(TreeBuilder):
 
         namespace, name = self._getNsTag(name)
         nsprefix = self._prefix_for_namespace(namespace)
-        self.soup.handle_starttag(name, namespace, nsprefix, attrs)
-
+        self.soup.handle_starttag(
+            name, namespace, nsprefix, attrs,
+            namespaces=self.active_namespace_prefixes[-1]
+        )
+        
     def _prefix_for_namespace(self, namespace):
         """Find the currently active prefix for the given namespace."""
         if namespace is None:
@@ -196,13 +328,20 @@ class LXMLTreeBuilderForXML(TreeBuilder):
         if len(self.nsmaps) > 1:
             # This tag, or one of its parents, introduced a namespace
             # mapping, so pop it off the stack.
-            self.nsmaps.pop()
-
+            out_of_scope_nsmap = self.nsmaps.pop()
+
+            if out_of_scope_nsmap is not None:
+                # This tag introduced a namespace mapping which is no
+                # longer in scope. Recalculate the currently active
+                # namespace prefixes.
+                self.active_namespace_prefixes.pop()
+            
     def pi(self, target, data):
         self.soup.endData()
-        self.soup.handle_data(target + ' ' + data)
-        self.soup.endData(ProcessingInstruction)
-
+        data = target + ' ' + data
+        self.soup.handle_data(data)
+        self.soup.endData(self.processing_instruction_class)
+        
     def data(self, content):
         self.soup.handle_data(content)
 
@@ -229,6 +368,7 @@ class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML):
 
     features = ALTERNATE_NAMES + [NAME, HTML, FAST, PERMISSIVE]
     is_xml = False
+    processing_instruction_class = ProcessingInstruction
 
     def default_parser(self, encoding):
         return etree.HTMLParser
@@ -240,7 +380,7 @@ class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML):
             self.parser.feed(markup)
             self.parser.close()
         except (UnicodeDecodeError, LookupError, etree.ParserError) as e:
-            raise ParserRejectedMarkup(str(e))
+            raise ParserRejectedMarkup(e)
 
 
     def test_fragment_to_document(self, fragment):