diff --git a/bs4/__init__.py b/bs4/__init__.py new file mode 100644 index 00000000..80f6f684 --- /dev/null +++ b/bs4/__init__.py @@ -0,0 +1,359 @@ +"""Beautiful Soup +Elixir and Tonic +"The Screen-Scraper's Friend" +http://www.crummy.com/software/BeautifulSoup/ + +Beautiful Soup uses a pluggable XML or HTML parser to parse a +(possibly invalid) document into a tree representation. Beautiful Soup +provides provides methods and Pythonic idioms that make it easy to +navigate, search, and modify the parse tree. + +Beautiful Soup works with Python 2.6 and up. It works better if lxml +and/or html5lib is installed. + +For more than you ever wanted to know about Beautiful Soup, see the +documentation: +http://www.crummy.com/software/BeautifulSoup/bs4/doc/ +""" + +__author__ = "Leonard Richardson (leonardr@segfault.org)" +__version__ = "4.1.3" +__copyright__ = "Copyright (c) 2004-2012 Leonard Richardson" +__license__ = "MIT" + +__all__ = ['BeautifulSoup'] + +import re +import warnings + +from .builder import builder_registry +from .dammit import UnicodeDammit +from .element import ( + CData, + Comment, + DEFAULT_OUTPUT_ENCODING, + Declaration, + Doctype, + NavigableString, + PageElement, + ProcessingInstruction, + ResultSet, + SoupStrainer, + Tag, + ) + +# The very first thing we do is give a useful error if someone is +# running this code under Python 3 without converting it. +syntax_error = u'You are trying to run the Python 2 version of Beautiful Soup under Python 3. This will not work. You need to convert the code, either by installing it (`python setup.py install`) or by running 2to3 (`2to3 -w bs4`).' + +class BeautifulSoup(Tag): + """ + This class defines the basic interface called by the tree builders. + + These methods will be called by the parser: + reset() + feed(markup) + + The tree builder may call these methods from its feed() implementation: + handle_starttag(name, attrs) # See note about return value + handle_endtag(name) + handle_data(data) # Appends to the current data node + endData(containerClass=NavigableString) # Ends the current data node + + No matter how complicated the underlying parser is, you should be + able to build a tree using 'start tag' events, 'end tag' events, + 'data' events, and "done with data" events. + + If you encounter an empty-element tag (aka a self-closing tag, + like HTML's
tag), call handle_starttag and then + handle_endtag. + """ + ROOT_TAG_NAME = u'[document]' + + # If the end-user gives no indication which tree builder they + # want, look for one with these features. + DEFAULT_BUILDER_FEATURES = ['html', 'fast'] + + # Used when determining whether a text node is all whitespace and + # can be replaced with a single space. A text node that contains + # fancy Unicode spaces (usually non-breaking) should be left + # alone. + STRIP_ASCII_SPACES = {9: None, 10: None, 12: None, 13: None, 32: None, } + + def __init__(self, markup="", features=None, builder=None, + parse_only=None, from_encoding=None, **kwargs): + """The Soup object is initialized as the 'root tag', and the + provided markup (which can be a string or a file-like object) + is fed into the underlying parser.""" + + if 'convertEntities' in kwargs: + warnings.warn( + "BS4 does not respect the convertEntities argument to the " + "BeautifulSoup constructor. Entities are always converted " + "to Unicode characters.") + + if 'markupMassage' in kwargs: + del kwargs['markupMassage'] + warnings.warn( + "BS4 does not respect the markupMassage argument to the " + "BeautifulSoup constructor. The tree builder is responsible " + "for any necessary markup massage.") + + if 'smartQuotesTo' in kwargs: + del kwargs['smartQuotesTo'] + warnings.warn( + "BS4 does not respect the smartQuotesTo argument to the " + "BeautifulSoup constructor. Smart quotes are always converted " + "to Unicode characters.") + + if 'selfClosingTags' in kwargs: + del kwargs['selfClosingTags'] + warnings.warn( + "BS4 does not respect the selfClosingTags argument to the " + "BeautifulSoup constructor. The tree builder is responsible " + "for understanding self-closing tags.") + + if 'isHTML' in kwargs: + del kwargs['isHTML'] + warnings.warn( + "BS4 does not respect the isHTML argument to the " + "BeautifulSoup constructor. You can pass in features='html' " + "or features='xml' to get a builder capable of handling " + "one or the other.") + + def deprecated_argument(old_name, new_name): + if old_name in kwargs: + warnings.warn( + 'The "%s" argument to the BeautifulSoup constructor ' + 'has been renamed to "%s."' % (old_name, new_name)) + value = kwargs[old_name] + del kwargs[old_name] + return value + return None + + parse_only = parse_only or deprecated_argument( + "parseOnlyThese", "parse_only") + + from_encoding = from_encoding or deprecated_argument( + "fromEncoding", "from_encoding") + + if len(kwargs) > 0: + arg = kwargs.keys().pop() + raise TypeError( + "__init__() got an unexpected keyword argument '%s'" % arg) + + if builder is None: + if isinstance(features, basestring): + features = [features] + if features is None or len(features) == 0: + features = self.DEFAULT_BUILDER_FEATURES + builder_class = builder_registry.lookup(*features) + if builder_class is None: + raise FeatureNotFound( + "Couldn't find a tree builder with the features you " + "requested: %s. Do you need to install a parser library?" + % ",".join(features)) + builder = builder_class() + self.builder = builder + self.is_xml = builder.is_xml + self.builder.soup = self + + self.parse_only = parse_only + + self.reset() + + if hasattr(markup, 'read'): # It's a file-type object. + markup = markup.read() + (self.markup, self.original_encoding, self.declared_html_encoding, + self.contains_replacement_characters) = ( + self.builder.prepare_markup(markup, from_encoding)) + + try: + self._feed() + except StopParsing: + pass + + # Clear out the markup and remove the builder's circular + # reference to this object. + self.markup = None + self.builder.soup = None + + def _feed(self): + # Convert the document to Unicode. + self.builder.reset() + + self.builder.feed(self.markup) + # Close out any unfinished strings and close all the open tags. + self.endData() + while self.currentTag.name != self.ROOT_TAG_NAME: + self.popTag() + + def reset(self): + Tag.__init__(self, self, self.builder, self.ROOT_TAG_NAME) + self.hidden = 1 + self.builder.reset() + self.currentData = [] + self.currentTag = None + self.tagStack = [] + self.pushTag(self) + + def new_tag(self, name, namespace=None, nsprefix=None, **attrs): + """Create a new tag associated with this soup.""" + return Tag(None, self.builder, name, namespace, nsprefix, attrs) + + def new_string(self, s): + """Create a new NavigableString associated with this soup.""" + navigable = NavigableString(s) + navigable.setup() + return navigable + + def insert_before(self, successor): + raise NotImplementedError("BeautifulSoup objects don't support insert_before().") + + def insert_after(self, successor): + raise NotImplementedError("BeautifulSoup objects don't support insert_after().") + + def popTag(self): + tag = self.tagStack.pop() + #print "Pop", tag.name + if self.tagStack: + self.currentTag = self.tagStack[-1] + return self.currentTag + + def pushTag(self, tag): + #print "Push", tag.name + if self.currentTag: + self.currentTag.contents.append(tag) + self.tagStack.append(tag) + self.currentTag = self.tagStack[-1] + + def endData(self, containerClass=NavigableString): + if self.currentData: + currentData = u''.join(self.currentData) + if (currentData.translate(self.STRIP_ASCII_SPACES) == '' and + not set([tag.name for tag in self.tagStack]).intersection( + self.builder.preserve_whitespace_tags)): + if '\n' in currentData: + currentData = '\n' + else: + currentData = ' ' + self.currentData = [] + if self.parse_only and len(self.tagStack) <= 1 and \ + (not self.parse_only.text or \ + not self.parse_only.search(currentData)): + return + o = containerClass(currentData) + self.object_was_parsed(o) + + def object_was_parsed(self, o): + """Add an object to the parse tree.""" + o.setup(self.currentTag, self.previous_element) + if self.previous_element: + self.previous_element.next_element = o + self.previous_element = o + self.currentTag.contents.append(o) + + def _popToTag(self, name, nsprefix=None, inclusivePop=True): + """Pops the tag stack up to and including the most recent + instance of the given tag. If inclusivePop is false, pops the tag + stack up to but *not* including the most recent instqance of + the given tag.""" + #print "Popping to %s" % name + if name == self.ROOT_TAG_NAME: + return + + numPops = 0 + mostRecentTag = None + + for i in range(len(self.tagStack) - 1, 0, -1): + if (name == self.tagStack[i].name + and nsprefix == self.tagStack[i].prefix): + numPops = len(self.tagStack) - i + break + if not inclusivePop: + numPops = numPops - 1 + + for i in range(0, numPops): + mostRecentTag = self.popTag() + return mostRecentTag + + def handle_starttag(self, name, namespace, nsprefix, attrs): + """Push a start tag on to the stack. + + If this method returns None, the tag was rejected by the + SoupStrainer. You should proceed as if the tag had not occured + in the document. For instance, if this was a self-closing tag, + don't call handle_endtag. + """ + + # print "Start tag %s: %s" % (name, attrs) + self.endData() + + if (self.parse_only and len(self.tagStack) <= 1 + and (self.parse_only.text + or not self.parse_only.search_tag(name, attrs))): + return None + + tag = Tag(self, self.builder, name, namespace, nsprefix, attrs, + self.currentTag, self.previous_element) + if tag is None: + return tag + if self.previous_element: + self.previous_element.next_element = tag + self.previous_element = tag + self.pushTag(tag) + return tag + + def handle_endtag(self, name, nsprefix=None): + #print "End tag: " + name + self.endData() + self._popToTag(name, nsprefix) + + def handle_data(self, data): + self.currentData.append(data) + + def decode(self, pretty_print=False, + eventual_encoding=DEFAULT_OUTPUT_ENCODING, + formatter="minimal"): + """Returns a string or Unicode representation of this document. + To get Unicode, pass None for encoding.""" + + if self.is_xml: + # Print the XML declaration + encoding_part = '' + if eventual_encoding != None: + encoding_part = ' encoding="%s"' % eventual_encoding + prefix = u'\n' % encoding_part + else: + prefix = u'' + if not pretty_print: + indent_level = None + else: + indent_level = 0 + return prefix + super(BeautifulSoup, self).decode( + indent_level, eventual_encoding, formatter) + +class BeautifulStoneSoup(BeautifulSoup): + """Deprecated interface to an XML parser.""" + + def __init__(self, *args, **kwargs): + kwargs['features'] = 'xml' + warnings.warn( + 'The BeautifulStoneSoup class is deprecated. Instead of using ' + 'it, pass features="xml" into the BeautifulSoup constructor.') + super(BeautifulStoneSoup, self).__init__(*args, **kwargs) + + +class StopParsing(Exception): + pass + + +class FeatureNotFound(ValueError): + pass + + +#By default, act as an HTML pretty-printer. +if __name__ == '__main__': + import sys + soup = BeautifulSoup(sys.stdin) + print soup.prettify() diff --git a/bs4/builder/__init__.py b/bs4/builder/__init__.py new file mode 100644 index 00000000..dc7deb93 --- /dev/null +++ b/bs4/builder/__init__.py @@ -0,0 +1,316 @@ +from collections import defaultdict +import itertools +import sys +from bs4.element import ( + CharsetMetaAttributeValue, + ContentMetaAttributeValue, + whitespace_re + ) + +__all__ = [ + 'HTMLTreeBuilder', + 'SAXTreeBuilder', + 'TreeBuilder', + 'TreeBuilderRegistry', + ] + +# Some useful features for a TreeBuilder to have. +FAST = 'fast' +PERMISSIVE = 'permissive' +STRICT = 'strict' +XML = 'xml' +HTML = 'html' +HTML_5 = 'html5' + + +class TreeBuilderRegistry(object): + + def __init__(self): + self.builders_for_feature = defaultdict(list) + self.builders = [] + + def register(self, treebuilder_class): + """Register a treebuilder based on its advertised 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): + if len(self.builders) == 0: + # There are no builders at all. + return None + + if len(features) == 0: + # They didn't ask for any features. Give them the most + # recently registered builder. + return self.builders[0] + + # Go down the list of features in order, and eliminate any builders + # that don't match every feature. + features = list(features) + features.reverse() + candidates = None + candidate_set = None + while len(features) > 0: + feature = features.pop() + we_have_the_feature = self.builders_for_feature.get(feature, []) + if len(we_have_the_feature) > 0: + if candidates is None: + candidates = we_have_the_feature + candidate_set = set(candidates) + else: + # Eliminate any candidates that don't have this feature. + candidate_set = candidate_set.intersection( + set(we_have_the_feature)) + + # The only valid candidates are the ones in candidate_set. + # Go through the original list of candidates and pick the first one + # that's in candidate_set. + if candidate_set is None: + return None + for candidate in candidates: + if candidate in candidate_set: + return candidate + return None + +# The BeautifulSoup class will take feature lists from developers and use them +# to look up builders in this registry. +builder_registry = TreeBuilderRegistry() + +class TreeBuilder(object): + """Turn a document into a Beautiful Soup object tree.""" + + features = [] + + is_xml = 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): + self.soup = None + + def reset(self): + pass + + def can_be_empty_element(self, tag_name): + """Might a tag with this name be an empty-element tag? + + The final markup may or may not actually present this tag as + self-closing. + + For instance: an HTMLBuilder does not consider a

tag to be + an empty-element tag (it's not in + HTMLBuilder.empty_element_tags). This means an empty

tag + will be presented as "

", not "

". + + 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. + "" will become "", and "bar" will + be left alone. + """ + if self.empty_element_tags is None: + return True + return tag_name in self.empty_element_tags + + def feed(self, markup): + raise NotImplementedError() + + def prepare_markup(self, markup, user_specified_encoding=None, + document_declared_encoding=None): + return markup, None, None, False + + def test_fragment_to_document(self, fragment): + """Wrap an HTML fragment to make it look like a document. + + Different parsers do this differently. For instance, lxml + introduces an empty tag, and html5lib + doesn't. Abstracting this away lets us write simple tests + which run HTML fragments through the parser and compare the + results against other HTML fragments. + + This method should not be used outside of tests. + """ + return fragment + + def set_up_substitutions(self, tag): + return False + + def _replace_cdata_list_attribute_values(self, tag_name, attrs): + """Replaces class="foo bar" with class=["foo", "bar"] + + Modifies its input in place. + """ + if self.cdata_list_attributes: + universal = self.cdata_list_attributes.get('*', []) + tag_specific = self.cdata_list_attributes.get( + tag_name.lower(), []) + for cdata_list_attr in itertools.chain(universal, tag_specific): + if cdata_list_attr in dict(attrs): + # Basically, we have a "class" attribute whose + # value is a whitespace-separated list of CSS + # classes. Split it into a list. + value = attrs[cdata_list_attr] + if isinstance(value, basestring): + values = whitespace_re.split(value) + else: + # html5lib sometimes calls setAttributes twice + # for the same tag when rearranging the parse + # tree. On the second call the attribute value + # here is already a list. If this happens, + # leave the value alone rather than trying to + # split it again. + values = value + attrs[cdata_list_attr] = values + return attrs + +class SAXTreeBuilder(TreeBuilder): + """A Beautiful Soup treebuilder that listens for SAX events.""" + + def feed(self, markup): + raise NotImplementedError() + + def close(self): + pass + + def startElement(self, name, attrs): + attrs = dict((key[1], value) for key, value in list(attrs.items())) + #print "Start %s, %r" % (name, attrs) + self.soup.handle_starttag(name, attrs) + + def endElement(self, name): + #print "End %s" % name + self.soup.handle_endtag(name) + + def startElementNS(self, nsTuple, nodeName, attrs): + # Throw away (ns, nodeName) for now. + self.startElement(nodeName, attrs) + + def endElementNS(self, nsTuple, nodeName): + # Throw away (ns, nodeName) for now. + self.endElement(nodeName) + #handler.endElementNS((ns, node.nodeName), node.nodeName) + + def startPrefixMapping(self, prefix, nodeValue): + # Ignore the prefix for now. + pass + + def endPrefixMapping(self, prefix): + # Ignore the prefix for now. + # handler.endPrefixMapping(prefix) + pass + + def characters(self, content): + self.soup.handle_data(content) + + def startDocument(self): + pass + + def endDocument(self): + pass + + +class HTMLTreeBuilder(TreeBuilder): + """This TreeBuilder knows facts about HTML. + + 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']) + + # 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, + # 'foo' and 'bar', not the single value 'foo bar'. When we + # 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 = { + "*" : ['class', 'accesskey', 'dropzone'], + "a" : ['rel', 'rev'], + "link" : ['rel', 'rev'], + "td" : ["headers"], + "th" : ["headers"], + "td" : ["headers"], + "form" : ["accept-charset"], + "object" : ["archive"], + + # These are HTML5 specific, as are *.accesskey and *.dropzone above. + "area" : ["rel"], + "icon" : ["sizes"], + "iframe" : ["sandbox"], + "output" : ["for"], + } + + def set_up_substitutions(self, tag): + # We are only interested in tags + if tag.name != 'meta': + return False + + http_equiv = tag.get('http-equiv') + content = tag.get('content') + charset = tag.get('charset') + + # We are interested in tags that say what encoding the + # document was originally in. This means HTML 5-style + # tags that provide the "charset" attribute. It also means + # HTML 4-style tags that provide the "content" + # attribute and have "http-equiv" set to "content-type". + # + # In both cases we will replace the value of the appropriate + # attribute with a standin object that can take on any + # encoding. + meta_encoding = None + if charset is not None: + # HTML 5 style: + # + meta_encoding = charset + tag['charset'] = CharsetMetaAttributeValue(charset) + + elif (content is not None and http_equiv is not None + and http_equiv.lower() == 'content-type'): + # HTML 4 style: + # + tag['content'] = ContentMetaAttributeValue(content) + + return (meta_encoding is not None) + +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'] + for name in module.__all__: + obj = getattr(module, name) + + if issubclass(obj, TreeBuilder): + setattr(this_module, name, obj) + this_module.__all__.append(name) + # Register the builder while we're at it. + this_module.builder_registry.register(obj) + +# 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. +from . import _htmlparser +register_treebuilders_from(_htmlparser) +try: + from . import _html5lib + register_treebuilders_from(_html5lib) +except ImportError: + # They don't have html5lib installed. + pass +try: + from . import _lxml + register_treebuilders_from(_lxml) +except ImportError: + # They don't have lxml installed. + pass diff --git a/bs4/builder/_html5lib.py b/bs4/builder/_html5lib.py new file mode 100644 index 00000000..6001e386 --- /dev/null +++ b/bs4/builder/_html5lib.py @@ -0,0 +1,222 @@ +__all__ = [ + 'HTML5TreeBuilder', + ] + +import warnings +from bs4.builder import ( + PERMISSIVE, + HTML, + HTML_5, + HTMLTreeBuilder, + ) +from bs4.element import NamespacedAttribute +import html5lib +from html5lib.constants import namespaces +from bs4.element import ( + Comment, + Doctype, + NavigableString, + Tag, + ) + +class HTML5TreeBuilder(HTMLTreeBuilder): + """Use html5lib to build a tree.""" + + features = ['html5lib', PERMISSIVE, HTML_5, HTML] + + def prepare_markup(self, markup, user_specified_encoding): + # Store the user-specified encoding for use later on. + self.user_specified_encoding = user_specified_encoding + return 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.") + parser = html5lib.HTMLParser(tree=self.create_treebuilder) + doc = parser.parse(markup, encoding=self.user_specified_encoding) + + # Set the character encoding detected by the tokenizer. + if isinstance(markup, unicode): + # 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] + + def create_treebuilder(self, namespaceHTMLElements): + self.underlying_builder = TreeBuilderForHtml5lib( + self.soup, namespaceHTMLElements) + return self.underlying_builder + + def test_fragment_to_document(self, fragment): + """See `TreeBuilder`.""" + return u'%s' % fragment + + +class TreeBuilderForHtml5lib(html5lib.treebuilders._base.TreeBuilder): + + def __init__(self, soup, namespaceHTMLElements): + self.soup = soup + super(TreeBuilderForHtml5lib, self).__init__(namespaceHTMLElements) + + def documentClass(self): + self.soup.reset() + return Element(self.soup, self.soup, None) + + def insertDoctype(self, token): + name = token["name"] + publicId = token["publicId"] + systemId = token["systemId"] + + doctype = Doctype.for_name_and_ids(name, publicId, systemId) + self.soup.object_was_parsed(doctype) + + def elementClass(self, name, namespace): + tag = self.soup.new_tag(name, namespace) + return Element(tag, self.soup, namespace) + + def commentClass(self, data): + return TextNode(Comment(data), self.soup) + + def fragmentClass(self): + self.soup = BeautifulSoup("") + self.soup.name = "[document_fragment]" + return Element(self.soup, self.soup, None) + + def appendChild(self, node): + # XXX This code is not covered by the BS4 tests. + self.soup.append(node.element) + + def getDocument(self): + return self.soup + + def getFragment(self): + return html5lib.treebuilders._base.TreeBuilder.getFragment(self).element + +class AttrList(object): + def __init__(self, element): + self.element = element + self.attrs = dict(self.element.attrs) + def __iter__(self): + return list(self.attrs.items()).__iter__() + def __setitem__(self, name, value): + "set attr", name, value + self.element[name] = value + def items(self): + return list(self.attrs.items()) + def keys(self): + return list(self.attrs.keys()) + def __len__(self): + return len(self.attrs) + def __getitem__(self, name): + return self.attrs[name] + def __contains__(self, name): + return name in list(self.attrs.keys()) + + +class Element(html5lib.treebuilders._base.Node): + def __init__(self, element, soup, namespace): + html5lib.treebuilders._base.Node.__init__(self, element.name) + self.element = element + self.soup = soup + self.namespace = namespace + + def appendChild(self, node): + if (node.element.__class__ == NavigableString and self.element.contents + and self.element.contents[-1].__class__ == NavigableString): + # Concatenate new text onto old text node + # XXX This has O(n^2) performance, for input like + # "aaa..." + old_element = self.element.contents[-1] + new_element = self.soup.new_string(old_element + node.element) + old_element.replace_with(new_element) + else: + self.element.append(node.element) + node.parent = self + + def getAttributes(self): + 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): + new_name = NamespacedAttribute(*name) + del attributes[name] + attributes[new_name] = value + + self.soup.builder._replace_cdata_list_attribute_values( + self.name, attributes) + for name, value in attributes.items(): + self.element[name] = value + + # The attributes may contain variables that need substitution. + # Call set_up_substitutions manually. + # + # The Tag constructor called this method when the Tag was created, + # but we just set/changed the attributes, so call it again. + self.soup.builder.set_up_substitutions(self.element) + attributes = property(getAttributes, setAttributes) + + def insertText(self, data, insertBefore=None): + text = TextNode(self.soup.new_string(data), self.soup) + if insertBefore: + self.insertBefore(text, insertBefore) + else: + self.appendChild(text) + + def insertBefore(self, node, refNode): + index = self.element.index(refNode.element) + if (node.element.__class__ == NavigableString and self.element.contents + and self.element.contents[index-1].__class__ == NavigableString): + # (See comments in appendChild) + old_node = self.element.contents[index-1] + new_str = self.soup.new_string(old_node + node.element) + old_node.replace_with(new_str) + else: + self.element.insert(index, node.element) + node.parent = self + + def removeChild(self, node): + node.element.extract() + + def reparentChildren(self, newParent): + while self.element.contents: + child = self.element.contents[0] + child.extract() + if isinstance(child, Tag): + newParent.appendChild( + Element(child, self.soup, namespaces["html"])) + else: + newParent.appendChild( + TextNode(child, self.soup)) + + def cloneNode(self): + tag = self.soup.new_tag(self.element.name, self.namespace) + node = Element(tag, self.soup, self.namespace) + for key,value in self.attributes: + node.attributes[key] = value + return node + + def hasContent(self): + return self.element.contents + + def getNameTuple(self): + if self.namespace == None: + return namespaces["html"], self.name + else: + return self.namespace, self.name + + nameTuple = property(getNameTuple) + +class TextNode(Element): + def __init__(self, element, soup): + html5lib.treebuilders._base.Node.__init__(self, None) + self.element = element + self.soup = soup + + def cloneNode(self): + raise NotImplementedError diff --git a/bs4/builder/_htmlparser.py b/bs4/builder/_htmlparser.py new file mode 100644 index 00000000..ede5cecb --- /dev/null +++ b/bs4/builder/_htmlparser.py @@ -0,0 +1,244 @@ +"""Use the HTMLParser library to parse HTML files that aren't too bad.""" + +__all__ = [ + 'HTMLParserTreeBuilder', + ] + +from HTMLParser import ( + HTMLParser, + HTMLParseError, + ) +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 + or (major == 3 and minor > 2) + or (major == 3 and minor == 2 and release >= 3)) + +from bs4.element import ( + CData, + Comment, + Declaration, + Doctype, + ProcessingInstruction, + ) +from bs4.dammit import EntitySubstitution, UnicodeDammit + +from bs4.builder import ( + HTML, + HTMLTreeBuilder, + STRICT, + ) + + +HTMLPARSER = 'html.parser' + +class BeautifulSoupHTMLParser(HTMLParser): + def handle_starttag(self, name, attrs): + # XXX namespace + self.soup.handle_starttag(name, None, None, dict(attrs)) + + def handle_endtag(self, name): + self.soup.handle_endtag(name) + + def handle_data(self, data): + self.soup.handle_data(data) + + def handle_charref(self, name): + # XXX workaround for a bug in HTMLParser. Remove this once + # it's fixed. + if name.startswith('x'): + real_name = int(name.lstrip('x'), 16) + else: + real_name = int(name) + + try: + data = unichr(real_name) + except (ValueError, OverflowError), e: + data = u"\N{REPLACEMENT CHARACTER}" + + self.handle_data(data) + + def handle_entityref(self, name): + character = EntitySubstitution.HTML_ENTITY_TO_CHARACTER.get(name) + if character is not None: + data = character + else: + data = "&%s;" % name + self.handle_data(data) + + def handle_comment(self, data): + self.soup.endData() + self.soup.handle_data(data) + self.soup.endData(Comment) + + def handle_decl(self, data): + self.soup.endData() + if data.startswith("DOCTYPE "): + data = data[len("DOCTYPE "):] + self.soup.handle_data(data) + self.soup.endData(Doctype) + + def unknown_decl(self, data): + if data.upper().startswith('CDATA['): + cls = CData + data = data[len('CDATA['):] + else: + cls = Declaration + self.soup.endData() + self.soup.handle_data(data) + self.soup.endData(cls) + + def handle_pi(self, data): + self.soup.endData() + if data.endswith("?") and data.lower().startswith("xml"): + # "An XHTML processing instruction using the trailing '?' + # will cause the '?' to be included in data." - HTMLParser + # docs. + # + # Strip the question mark so we don't end up with two + # question marks. + data = data[:-1] + self.soup.handle_data(data) + self.soup.endData(ProcessingInstruction) + + +class HTMLParserTreeBuilder(HTMLTreeBuilder): + + is_xml = False + features = [HTML, STRICT, HTMLPARSER] + + def __init__(self, *args, **kwargs): + if CONSTRUCTOR_TAKES_STRICT: + kwargs['strict'] = False + self.parser_args = (args, kwargs) + + def prepare_markup(self, markup, user_specified_encoding=None, + document_declared_encoding=None): + """ + :return: A 4-tuple (markup, original encoding, encoding + declared within markup, whether any characters had to be + replaced with REPLACEMENT CHARACTER). + """ + if isinstance(markup, unicode): + return markup, None, None, False + + try_encodings = [user_specified_encoding, document_declared_encoding] + dammit = UnicodeDammit(markup, try_encodings, is_html=True) + return (dammit.markup, dammit.original_encoding, + dammit.declared_html_encoding, + dammit.contains_replacement_characters) + + def feed(self, markup): + args, kwargs = self.parser_args + parser = BeautifulSoupHTMLParser(*args, **kwargs) + parser.soup = self.soup + try: + parser.feed(markup) + except HTMLParseError, 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

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: + 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'' % self.cdata_elem, re.I) + + BeautifulSoupHTMLParser.parse_starttag = parse_starttag + BeautifulSoupHTMLParser.set_cdata_mode = set_cdata_mode + + CONSTRUCTOR_TAKES_STRICT = True diff --git a/bs4/builder/_lxml.py b/bs4/builder/_lxml.py new file mode 100644 index 00000000..f6b91ff5 --- /dev/null +++ b/bs4/builder/_lxml.py @@ -0,0 +1,199 @@ +__all__ = [ + 'LXMLTreeBuilderForXML', + 'LXMLTreeBuilder', + ] + +from StringIO import StringIO +import collections +from lxml import etree +from bs4.element import Comment, Doctype, NamespacedAttribute +from bs4.builder import ( + FAST, + HTML, + HTMLTreeBuilder, + PERMISSIVE, + TreeBuilder, + XML) +from bs4.dammit import UnicodeDammit + +LXML = 'lxml' + +class LXMLTreeBuilderForXML(TreeBuilder): + DEFAULT_PARSER_CLASS = etree.XMLParser + + is_xml = True + + # Well, it's permissive by XML parser standards. + features = [LXML, XML, FAST, PERMISSIVE] + + CHUNK_SIZE = 512 + + @property + def default_parser(self): + # This can either return a parser object or a class, which + # will be instantiated with default arguments. + return etree.XMLParser(target=self, strip_cdata=False, recover=True) + + def __init__(self, parser=None, empty_element_tags=None): + if empty_element_tags is not None: + self.empty_element_tags = set(empty_element_tags) + if parser is None: + # Use the default parser. + parser = self.default_parser + if isinstance(parser, collections.Callable): + # Instantiate the parser with default arguments + parser = parser(target=self, strip_cdata=False) + self.parser = parser + self.soup = None + self.nsmaps = None + + def _getNsTag(self, tag): + # Split the namespace URL out of a fully-qualified lxml tag + # name. Copied from lxml's src/lxml/sax.py. + if tag[0] == '{': + return tuple(tag[1:].split('}', 1)) + else: + return (None, tag) + + def prepare_markup(self, markup, user_specified_encoding=None, + document_declared_encoding=None): + """ + :return: A 3-tuple (markup, original encoding, encoding + declared within markup). + """ + if isinstance(markup, unicode): + return markup, None, None, False + + try_encodings = [user_specified_encoding, document_declared_encoding] + dammit = UnicodeDammit(markup, try_encodings, is_html=True) + return (dammit.markup, dammit.original_encoding, + dammit.declared_html_encoding, + dammit.contains_replacement_characters) + + def feed(self, markup): + if isinstance(markup, basestring): + markup = StringIO(markup) + # Call feed() at least once, even if the markup is empty, + # or the parser won't be initialized. + data = markup.read(self.CHUNK_SIZE) + self.parser.feed(data) + while data != '': + # Now call feed() on the rest of the data, chunk by chunk. + data = markup.read(self.CHUNK_SIZE) + if data != '': + self.parser.feed(data) + self.parser.close() + + def close(self): + self.nsmaps = None + + 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(nsmap) == 0 and self.nsmaps != None: + # There are no new namespaces for this tag, but 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. + if self.nsmaps is None: + self.nsmaps = [] + inverted_nsmap = dict((value, key) for key, value in nsmap.items()) + self.nsmaps.append(inverted_nsmap) + # Also treat the namespace mapping as a set of attributes on the + # tag, so we can recreate it later. + attrs = attrs.copy() + for prefix, namespace in nsmap.items(): + attribute = NamespacedAttribute( + "xmlns", prefix, "http://www.w3.org/2000/xmlns/") + attrs[attribute] = namespace + + if self.nsmaps is not None and len(self.nsmaps) > 0: + # Namespaces are in play. Find any attributes that came in + # from lxml with namespaces attached to their names, and + # turn then into NamespacedAttribute objects. + new_attrs = {} + for attr, value in attrs.items(): + namespace, attr = self._getNsTag(attr) + if namespace is None: + new_attrs[attr] = value + else: + nsprefix = self._prefix_for_namespace(namespace) + attr = NamespacedAttribute(nsprefix, attr, namespace) + new_attrs[attr] = value + attrs = new_attrs + + namespace, name = self._getNsTag(name) + nsprefix = self._prefix_for_namespace(namespace) + self.soup.handle_starttag(name, namespace, nsprefix, attrs) + + def _prefix_for_namespace(self, namespace): + """Find the currently active prefix for the given namespace.""" + if namespace is None: + return None + for inverted_nsmap in reversed(self.nsmaps): + if inverted_nsmap is not None and namespace in inverted_nsmap: + return inverted_nsmap[namespace] + + def end(self, name): + self.soup.endData() + completed_tag = self.soup.tagStack[-1] + namespace, name = self._getNsTag(name) + nsprefix = None + if namespace is not None: + for inverted_nsmap in reversed(self.nsmaps): + if inverted_nsmap is not None and namespace in inverted_nsmap: + nsprefix = inverted_nsmap[namespace] + break + self.soup.handle_endtag(name, nsprefix) + if self.nsmaps != None: + # This tag, or one of its parents, introduced a namespace + # mapping, so pop it off the stack. + self.nsmaps.pop() + if len(self.nsmaps) == 0: + # Namespaces are no longer in play, so don't bother keeping + # track of the namespace stack. + self.nsmaps = None + + def pi(self, target, data): + pass + + def data(self, content): + self.soup.handle_data(content) + + def doctype(self, name, pubid, system): + self.soup.endData() + doctype = Doctype.for_name_and_ids(name, pubid, system) + self.soup.object_was_parsed(doctype) + + def comment(self, content): + "Handle comments as Comment objects." + self.soup.endData() + self.soup.handle_data(content) + self.soup.endData(Comment) + + def test_fragment_to_document(self, fragment): + """See `TreeBuilder`.""" + return u'\n%s' % fragment + + +class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML): + + features = [LXML, HTML, FAST, PERMISSIVE] + is_xml = False + + @property + def default_parser(self): + return etree.HTMLParser + + def feed(self, markup): + self.parser.feed(markup) + self.parser.close() + + def test_fragment_to_document(self, fragment): + """See `TreeBuilder`.""" + return u'%s' % fragment diff --git a/bs4/dammit.py b/bs4/dammit.py new file mode 100644 index 00000000..983ade0f --- /dev/null +++ b/bs4/dammit.py @@ -0,0 +1,803 @@ +# -*- coding: utf-8 -*- +"""Beautiful Soup bonus library: Unicode, Dammit + +This class forces XML data into a standard format (usually to UTF-8 or +Unicode). It is heavily based on code from Mark Pilgrim's Universal +Feed Parser. It does not rewrite the XML or HTML to reflect a new +encoding; that's the tree builder's job. +""" + +import codecs +from htmlentitydefs import codepoint2name +import re +import logging + +# Import a library to autodetect character encodings. +chardet_type = None +try: + # First try the fast C implementation. + # PyPI package: cchardet + import cchardet + def chardet_dammit(s): + return cchardet.detect(s)['encoding'] +except ImportError: + try: + # Fall back to the pure Python implementation + # Debian package: python-chardet + # PyPI package: chardet + import chardet + def chardet_dammit(s): + return chardet.detect(s)['encoding'] + #import chardet.constants + #chardet.constants._debug = 1 + except ImportError: + # No chardet available. + def chardet_dammit(s): + return None + +# Available from http://cjkpython.i18n.org/. +try: + import iconv_codec +except ImportError: + pass + +xml_encoding_re = re.compile( + '^<\?.*encoding=[\'"](.*?)[\'"].*\?>'.encode(), re.I) +html_meta_re = re.compile( + '<\s*meta[^>]+charset\s*=\s*["\']?([^>]*?)[ /;\'">]'.encode(), re.I) + +class EntitySubstitution(object): + + """Substitute XML or HTML entities for the corresponding characters.""" + + def _populate_class_variables(): + lookup = {} + reverse_lookup = {} + characters_for_re = [] + for codepoint, name in list(codepoint2name.items()): + character = unichr(codepoint) + if codepoint != 34: + # There's no point in turning the quotation mark into + # ", unless it happens within an attribute value, which + # is handled elsewhere. + characters_for_re.append(character) + lookup[character] = name + # But we do want to turn " into the quotation mark. + reverse_lookup[name] = character + re_definition = "[%s]" % "".join(characters_for_re) + return lookup, reverse_lookup, re.compile(re_definition) + (CHARACTER_TO_HTML_ENTITY, HTML_ENTITY_TO_CHARACTER, + CHARACTER_TO_HTML_ENTITY_RE) = _populate_class_variables() + + CHARACTER_TO_XML_ENTITY = { + "'": "apos", + '"': "quot", + "&": "amp", + "<": "lt", + ">": "gt", + } + + BARE_AMPERSAND_OR_BRACKET = re.compile("([<>]|" + "&(?!#\d+;|#x[0-9a-fA-F]+;|\w+;)" + ")") + + @classmethod + def _substitute_html_entity(cls, matchobj): + entity = cls.CHARACTER_TO_HTML_ENTITY.get(matchobj.group(0)) + return "&%s;" % entity + + @classmethod + def _substitute_xml_entity(cls, matchobj): + """Used with a regular expression to substitute the + appropriate XML entity for an XML special character.""" + entity = cls.CHARACTER_TO_XML_ENTITY[matchobj.group(0)] + return "&%s;" % entity + + @classmethod + def quoted_attribute_value(self, value): + """Make a value into a quoted XML attribute, possibly escaping it. + + Most strings will be quoted using double quotes. + + Bob's Bar -> "Bob's Bar" + + If a string contains double quotes, it will be quoted using + single quotes. + + Welcome to "my bar" -> 'Welcome to "my bar"' + + If a string contains both single and double quotes, the + double quotes will be escaped, and the string will be quoted + using double quotes. + + Welcome to "Bob's Bar" -> "Welcome to "Bob's bar" + """ + quote_with = '"' + if '"' in value: + if "'" in value: + # The string contains both single and double + # quotes. Turn the double quotes into + # entities. We quote the double quotes rather than + # the single quotes because the entity name is + # """ whether this is HTML or XML. If we + # quoted the single quotes, we'd have to decide + # between ' and &squot;. + replace_with = """ + value = value.replace('"', replace_with) + else: + # There are double quotes but no single quotes. + # We can use single quotes to quote the attribute. + quote_with = "'" + return quote_with + value + quote_with + + @classmethod + def substitute_xml(cls, value, make_quoted_attribute=False): + """Substitute XML entities for special XML characters. + + :param value: A string to be substituted. The less-than sign will + become <, the greater-than sign will become >, and any + ampersands that are not part of an entity defition will + become &. + + :param make_quoted_attribute: If True, then the string will be + quoted, as befits an attribute value. + """ + # Escape angle brackets, and ampersands that aren't part of + # entities. + value = cls.BARE_AMPERSAND_OR_BRACKET.sub( + cls._substitute_xml_entity, value) + + if make_quoted_attribute: + value = cls.quoted_attribute_value(value) + return value + + @classmethod + def substitute_html(cls, s): + """Replace certain Unicode characters with named HTML entities. + + This differs from data.encode(encoding, 'xmlcharrefreplace') + in that the goal is to make the result more readable (to those + with ASCII displays) rather than to recover from + errors. There's absolutely nothing wrong with a UTF-8 string + containg a LATIN SMALL LETTER E WITH ACUTE, but replacing that + character with "é" will make it more readable to some + people. + """ + return cls.CHARACTER_TO_HTML_ENTITY_RE.sub( + cls._substitute_html_entity, s) + + +class UnicodeDammit: + """A class for detecting the encoding of a *ML document and + converting it to a Unicode string. If the source encoding is + windows-1252, can replace MS smart quotes with their HTML or XML + equivalents.""" + + # This dictionary maps commonly seen values for "charset" in HTML + # meta tags to the corresponding Python codec names. It only covers + # values that aren't in Python's aliases and can't be determined + # by the heuristics in find_codec. + CHARSET_ALIASES = {"macintosh": "mac-roman", + "x-sjis": "shift-jis"} + + ENCODINGS_WITH_SMART_QUOTES = [ + "windows-1252", + "iso-8859-1", + "iso-8859-2", + ] + + def __init__(self, markup, override_encodings=[], + smart_quotes_to=None, is_html=False): + self.declared_html_encoding = None + self.smart_quotes_to = smart_quotes_to + self.tried_encodings = [] + self.contains_replacement_characters = False + + if markup == '' or isinstance(markup, unicode): + self.markup = markup + self.unicode_markup = unicode(markup) + self.original_encoding = None + return + + new_markup, document_encoding, sniffed_encoding = \ + self._detectEncoding(markup, is_html) + self.markup = new_markup + + u = None + if new_markup != markup: + # _detectEncoding modified the markup, then converted it to + # Unicode and then to UTF-8. So convert it from UTF-8. + u = self._convert_from("utf8") + self.original_encoding = sniffed_encoding + + if not u: + for proposed_encoding in ( + override_encodings + [document_encoding, sniffed_encoding]): + if proposed_encoding is not None: + u = self._convert_from(proposed_encoding) + if u: + break + + # If no luck and we have auto-detection library, try that: + if not u and not isinstance(self.markup, unicode): + u = self._convert_from(chardet_dammit(self.markup)) + + # As a last resort, try utf-8 and windows-1252: + if not u: + for proposed_encoding in ("utf-8", "windows-1252"): + u = self._convert_from(proposed_encoding) + if u: + break + + # As an absolute last resort, try the encodings again with + # character replacement. + if not u: + for proposed_encoding in ( + override_encodings + [ + document_encoding, sniffed_encoding, "utf-8", "windows-1252"]): + if proposed_encoding != "ascii": + u = self._convert_from(proposed_encoding, "replace") + if u is not None: + logging.warning( + "Some characters could not be decoded, and were " + "replaced with REPLACEMENT CHARACTER.") + self.contains_replacement_characters = True + break + + # We could at this point force it to ASCII, but that would + # destroy so much data that I think giving up is better + self.unicode_markup = u + if not u: + self.original_encoding = None + + def _sub_ms_char(self, match): + """Changes a MS smart quote character to an XML or HTML + entity, or an ASCII character.""" + orig = match.group(1) + if self.smart_quotes_to == 'ascii': + sub = self.MS_CHARS_TO_ASCII.get(orig).encode() + else: + sub = self.MS_CHARS.get(orig) + if type(sub) == tuple: + if self.smart_quotes_to == 'xml': + sub = '&#x'.encode() + sub[1].encode() + ';'.encode() + else: + sub = '&'.encode() + sub[0].encode() + ';'.encode() + else: + sub = sub.encode() + return sub + + def _convert_from(self, proposed, errors="strict"): + proposed = self.find_codec(proposed) + if not proposed or (proposed, errors) in self.tried_encodings: + return None + self.tried_encodings.append((proposed, errors)) + markup = self.markup + + # Convert smart quotes to HTML if coming from an encoding + # that might have them. + if (self.smart_quotes_to is not None + and proposed.lower() in self.ENCODINGS_WITH_SMART_QUOTES): + smart_quotes_re = b"([\x80-\x9f])" + smart_quotes_compiled = re.compile(smart_quotes_re) + markup = smart_quotes_compiled.sub(self._sub_ms_char, markup) + + try: + #print "Trying to convert document to %s (errors=%s)" % ( + # proposed, errors) + u = self._to_unicode(markup, proposed, errors) + self.markup = u + self.original_encoding = proposed + except Exception as e: + #print "That didn't work!" + #print e + return None + #print "Correct encoding: %s" % proposed + return self.markup + + def _to_unicode(self, data, encoding, errors="strict"): + '''Given a string and its encoding, decodes the string into Unicode. + %encoding is a string recognized by encodings.aliases''' + + # strip Byte Order Mark (if present) + if (len(data) >= 4) and (data[:2] == '\xfe\xff') \ + and (data[2:4] != '\x00\x00'): + encoding = 'utf-16be' + data = data[2:] + elif (len(data) >= 4) and (data[:2] == '\xff\xfe') \ + and (data[2:4] != '\x00\x00'): + encoding = 'utf-16le' + data = data[2:] + elif data[:3] == '\xef\xbb\xbf': + encoding = 'utf-8' + data = data[3:] + elif data[:4] == '\x00\x00\xfe\xff': + encoding = 'utf-32be' + data = data[4:] + elif data[:4] == '\xff\xfe\x00\x00': + encoding = 'utf-32le' + data = data[4:] + newdata = unicode(data, encoding, errors) + return newdata + + def _detectEncoding(self, xml_data, is_html=False): + """Given a document, tries to detect its XML encoding.""" + xml_encoding = sniffed_xml_encoding = None + try: + if xml_data[:4] == b'\x4c\x6f\xa7\x94': + # EBCDIC + xml_data = self._ebcdic_to_ascii(xml_data) + elif xml_data[:4] == b'\x00\x3c\x00\x3f': + # UTF-16BE + sniffed_xml_encoding = 'utf-16be' + xml_data = unicode(xml_data, 'utf-16be').encode('utf-8') + elif (len(xml_data) >= 4) and (xml_data[:2] == b'\xfe\xff') \ + and (xml_data[2:4] != b'\x00\x00'): + # UTF-16BE with BOM + sniffed_xml_encoding = 'utf-16be' + xml_data = unicode(xml_data[2:], 'utf-16be').encode('utf-8') + elif xml_data[:4] == b'\x3c\x00\x3f\x00': + # UTF-16LE + sniffed_xml_encoding = 'utf-16le' + xml_data = unicode(xml_data, 'utf-16le').encode('utf-8') + elif (len(xml_data) >= 4) and (xml_data[:2] == b'\xff\xfe') and \ + (xml_data[2:4] != b'\x00\x00'): + # UTF-16LE with BOM + sniffed_xml_encoding = 'utf-16le' + xml_data = unicode(xml_data[2:], 'utf-16le').encode('utf-8') + elif xml_data[:4] == b'\x00\x00\x00\x3c': + # UTF-32BE + sniffed_xml_encoding = 'utf-32be' + xml_data = unicode(xml_data, 'utf-32be').encode('utf-8') + elif xml_data[:4] == b'\x3c\x00\x00\x00': + # UTF-32LE + sniffed_xml_encoding = 'utf-32le' + xml_data = unicode(xml_data, 'utf-32le').encode('utf-8') + elif xml_data[:4] == b'\x00\x00\xfe\xff': + # UTF-32BE with BOM + sniffed_xml_encoding = 'utf-32be' + xml_data = unicode(xml_data[4:], 'utf-32be').encode('utf-8') + elif xml_data[:4] == b'\xff\xfe\x00\x00': + # UTF-32LE with BOM + sniffed_xml_encoding = 'utf-32le' + xml_data = unicode(xml_data[4:], 'utf-32le').encode('utf-8') + elif xml_data[:3] == b'\xef\xbb\xbf': + # UTF-8 with BOM + sniffed_xml_encoding = 'utf-8' + xml_data = unicode(xml_data[3:], 'utf-8').encode('utf-8') + else: + sniffed_xml_encoding = 'ascii' + pass + except: + xml_encoding_match = None + xml_encoding_match = xml_encoding_re.match(xml_data) + if not xml_encoding_match and is_html: + xml_encoding_match = html_meta_re.search(xml_data) + if xml_encoding_match is not None: + xml_encoding = xml_encoding_match.groups()[0].decode( + 'ascii').lower() + if is_html: + self.declared_html_encoding = xml_encoding + if sniffed_xml_encoding and \ + (xml_encoding in ('iso-10646-ucs-2', 'ucs-2', 'csunicode', + 'iso-10646-ucs-4', 'ucs-4', 'csucs4', + 'utf-16', 'utf-32', 'utf_16', 'utf_32', + 'utf16', 'u16')): + xml_encoding = sniffed_xml_encoding + return xml_data, xml_encoding, sniffed_xml_encoding + + def find_codec(self, charset): + return self._codec(self.CHARSET_ALIASES.get(charset, charset)) \ + or (charset and self._codec(charset.replace("-", ""))) \ + or (charset and self._codec(charset.replace("-", "_"))) \ + or charset + + def _codec(self, charset): + if not charset: + return charset + codec = None + try: + codecs.lookup(charset) + codec = charset + except (LookupError, ValueError): + pass + return codec + + EBCDIC_TO_ASCII_MAP = None + + def _ebcdic_to_ascii(self, s): + c = self.__class__ + if not c.EBCDIC_TO_ASCII_MAP: + emap = (0,1,2,3,156,9,134,127,151,141,142,11,12,13,14,15, + 16,17,18,19,157,133,8,135,24,25,146,143,28,29,30,31, + 128,129,130,131,132,10,23,27,136,137,138,139,140,5,6,7, + 144,145,22,147,148,149,150,4,152,153,154,155,20,21,158,26, + 32,160,161,162,163,164,165,166,167,168,91,46,60,40,43,33, + 38,169,170,171,172,173,174,175,176,177,93,36,42,41,59,94, + 45,47,178,179,180,181,182,183,184,185,124,44,37,95,62,63, + 186,187,188,189,190,191,192,193,194,96,58,35,64,39,61,34, + 195,97,98,99,100,101,102,103,104,105,196,197,198,199,200, + 201,202,106,107,108,109,110,111,112,113,114,203,204,205, + 206,207,208,209,126,115,116,117,118,119,120,121,122,210, + 211,212,213,214,215,216,217,218,219,220,221,222,223,224, + 225,226,227,228,229,230,231,123,65,66,67,68,69,70,71,72, + 73,232,233,234,235,236,237,125,74,75,76,77,78,79,80,81, + 82,238,239,240,241,242,243,92,159,83,84,85,86,87,88,89, + 90,244,245,246,247,248,249,48,49,50,51,52,53,54,55,56,57, + 250,251,252,253,254,255) + import string + c.EBCDIC_TO_ASCII_MAP = string.maketrans( + ''.join(map(chr, list(range(256)))), ''.join(map(chr, emap))) + return s.translate(c.EBCDIC_TO_ASCII_MAP) + + # A partial mapping of ISO-Latin-1 to HTML entities/XML numeric entities. + MS_CHARS = {b'\x80': ('euro', '20AC'), + b'\x81': ' ', + b'\x82': ('sbquo', '201A'), + b'\x83': ('fnof', '192'), + b'\x84': ('bdquo', '201E'), + b'\x85': ('hellip', '2026'), + b'\x86': ('dagger', '2020'), + b'\x87': ('Dagger', '2021'), + b'\x88': ('circ', '2C6'), + b'\x89': ('permil', '2030'), + b'\x8A': ('Scaron', '160'), + b'\x8B': ('lsaquo', '2039'), + b'\x8C': ('OElig', '152'), + b'\x8D': '?', + b'\x8E': ('#x17D', '17D'), + b'\x8F': '?', + b'\x90': '?', + b'\x91': ('lsquo', '2018'), + b'\x92': ('rsquo', '2019'), + b'\x93': ('ldquo', '201C'), + b'\x94': ('rdquo', '201D'), + b'\x95': ('bull', '2022'), + b'\x96': ('ndash', '2013'), + b'\x97': ('mdash', '2014'), + b'\x98': ('tilde', '2DC'), + b'\x99': ('trade', '2122'), + b'\x9a': ('scaron', '161'), + b'\x9b': ('rsaquo', '203A'), + b'\x9c': ('oelig', '153'), + b'\x9d': '?', + b'\x9e': ('#x17E', '17E'), + b'\x9f': ('Yuml', ''),} + + # A parochial partial mapping of ISO-Latin-1 to ASCII. Contains + # horrors like stripping diacritical marks to turn á into a, but also + # contains non-horrors like turning “ into ". + MS_CHARS_TO_ASCII = { + b'\x80' : 'EUR', + b'\x81' : ' ', + b'\x82' : ',', + b'\x83' : 'f', + b'\x84' : ',,', + b'\x85' : '...', + b'\x86' : '+', + b'\x87' : '++', + b'\x88' : '^', + b'\x89' : '%', + b'\x8a' : 'S', + b'\x8b' : '<', + b'\x8c' : 'OE', + b'\x8d' : '?', + b'\x8e' : 'Z', + b'\x8f' : '?', + b'\x90' : '?', + b'\x91' : "'", + b'\x92' : "'", + b'\x93' : '"', + b'\x94' : '"', + b'\x95' : '*', + b'\x96' : '-', + b'\x97' : '--', + b'\x98' : '~', + b'\x99' : '(TM)', + b'\x9a' : 's', + b'\x9b' : '>', + b'\x9c' : 'oe', + b'\x9d' : '?', + b'\x9e' : 'z', + b'\x9f' : 'Y', + b'\xa0' : ' ', + b'\xa1' : '!', + b'\xa2' : 'c', + b'\xa3' : 'GBP', + b'\xa4' : '$', #This approximation is especially parochial--this is the + #generic currency symbol. + b'\xa5' : 'YEN', + b'\xa6' : '|', + b'\xa7' : 'S', + b'\xa8' : '..', + b'\xa9' : '', + b'\xaa' : '(th)', + b'\xab' : '<<', + b'\xac' : '!', + b'\xad' : ' ', + b'\xae' : '(R)', + b'\xaf' : '-', + b'\xb0' : 'o', + b'\xb1' : '+-', + b'\xb2' : '2', + b'\xb3' : '3', + b'\xb4' : ("'", 'acute'), + b'\xb5' : 'u', + b'\xb6' : 'P', + b'\xb7' : '*', + b'\xb8' : ',', + b'\xb9' : '1', + b'\xba' : '(th)', + b'\xbb' : '>>', + b'\xbc' : '1/4', + b'\xbd' : '1/2', + b'\xbe' : '3/4', + b'\xbf' : '?', + b'\xc0' : 'A', + b'\xc1' : 'A', + b'\xc2' : 'A', + b'\xc3' : 'A', + b'\xc4' : 'A', + b'\xc5' : 'A', + b'\xc6' : 'AE', + b'\xc7' : 'C', + b'\xc8' : 'E', + b'\xc9' : 'E', + b'\xca' : 'E', + b'\xcb' : 'E', + b'\xcc' : 'I', + b'\xcd' : 'I', + b'\xce' : 'I', + b'\xcf' : 'I', + b'\xd0' : 'D', + b'\xd1' : 'N', + b'\xd2' : 'O', + b'\xd3' : 'O', + b'\xd4' : 'O', + b'\xd5' : 'O', + b'\xd6' : 'O', + b'\xd7' : '*', + b'\xd8' : 'O', + b'\xd9' : 'U', + b'\xda' : 'U', + b'\xdb' : 'U', + b'\xdc' : 'U', + b'\xdd' : 'Y', + b'\xde' : 'b', + b'\xdf' : 'B', + b'\xe0' : 'a', + b'\xe1' : 'a', + b'\xe2' : 'a', + b'\xe3' : 'a', + b'\xe4' : 'a', + b'\xe5' : 'a', + b'\xe6' : 'ae', + b'\xe7' : 'c', + b'\xe8' : 'e', + b'\xe9' : 'e', + b'\xea' : 'e', + b'\xeb' : 'e', + b'\xec' : 'i', + b'\xed' : 'i', + b'\xee' : 'i', + b'\xef' : 'i', + b'\xf0' : 'o', + b'\xf1' : 'n', + b'\xf2' : 'o', + b'\xf3' : 'o', + b'\xf4' : 'o', + b'\xf5' : 'o', + b'\xf6' : 'o', + b'\xf7' : '/', + b'\xf8' : 'o', + b'\xf9' : 'u', + b'\xfa' : 'u', + b'\xfb' : 'u', + b'\xfc' : 'u', + b'\xfd' : 'y', + b'\xfe' : 'b', + b'\xff' : 'y', + } + + # A map used when removing rogue Windows-1252/ISO-8859-1 + # characters in otherwise UTF-8 documents. + # + # Note that \x81, \x8d, \x8f, \x90, and \x9d are undefined in + # Windows-1252. + WINDOWS_1252_TO_UTF8 = { + 0x80 : b'\xe2\x82\xac', # € + 0x82 : b'\xe2\x80\x9a', # ‚ + 0x83 : b'\xc6\x92', # Æ’ + 0x84 : b'\xe2\x80\x9e', # „ + 0x85 : b'\xe2\x80\xa6', # … + 0x86 : b'\xe2\x80\xa0', # † + 0x87 : b'\xe2\x80\xa1', # ‡ + 0x88 : b'\xcb\x86', # ˆ + 0x89 : b'\xe2\x80\xb0', # ‰ + 0x8a : b'\xc5\xa0', # Å  + 0x8b : b'\xe2\x80\xb9', # ‹ + 0x8c : b'\xc5\x92', # Å’ + 0x8e : b'\xc5\xbd', # Ž + 0x91 : b'\xe2\x80\x98', # ‘ + 0x92 : b'\xe2\x80\x99', # ’ + 0x93 : b'\xe2\x80\x9c', # “ + 0x94 : b'\xe2\x80\x9d', # †+ 0x95 : b'\xe2\x80\xa2', # • + 0x96 : b'\xe2\x80\x93', # – + 0x97 : b'\xe2\x80\x94', # — + 0x98 : b'\xcb\x9c', # Ëœ + 0x99 : b'\xe2\x84\xa2', # â„¢ + 0x9a : b'\xc5\xa1', # Å¡ + 0x9b : b'\xe2\x80\xba', # › + 0x9c : b'\xc5\x93', # Å“ + 0x9e : b'\xc5\xbe', # ž + 0x9f : b'\xc5\xb8', # Ÿ + 0xa0 : b'\xc2\xa0', #   + 0xa1 : b'\xc2\xa1', # ¡ + 0xa2 : b'\xc2\xa2', # ¢ + 0xa3 : b'\xc2\xa3', # £ + 0xa4 : b'\xc2\xa4', # ¤ + 0xa5 : b'\xc2\xa5', # Â¥ + 0xa6 : b'\xc2\xa6', # ¦ + 0xa7 : b'\xc2\xa7', # § + 0xa8 : b'\xc2\xa8', # ¨ + 0xa9 : b'\xc2\xa9', # © + 0xaa : b'\xc2\xaa', # ª + 0xab : b'\xc2\xab', # « + 0xac : b'\xc2\xac', # ¬ + 0xad : b'\xc2\xad', # ­ + 0xae : b'\xc2\xae', # ® + 0xaf : b'\xc2\xaf', # ¯ + 0xb0 : b'\xc2\xb0', # ° + 0xb1 : b'\xc2\xb1', # ± + 0xb2 : b'\xc2\xb2', # ² + 0xb3 : b'\xc2\xb3', # ³ + 0xb4 : b'\xc2\xb4', # ´ + 0xb5 : b'\xc2\xb5', # µ + 0xb6 : b'\xc2\xb6', # ¶ + 0xb7 : b'\xc2\xb7', # · + 0xb8 : b'\xc2\xb8', # ¸ + 0xb9 : b'\xc2\xb9', # ¹ + 0xba : b'\xc2\xba', # º + 0xbb : b'\xc2\xbb', # » + 0xbc : b'\xc2\xbc', # ¼ + 0xbd : b'\xc2\xbd', # ½ + 0xbe : b'\xc2\xbe', # ¾ + 0xbf : b'\xc2\xbf', # ¿ + 0xc0 : b'\xc3\x80', # À + 0xc1 : b'\xc3\x81', # à + 0xc2 : b'\xc3\x82', #  + 0xc3 : b'\xc3\x83', # à + 0xc4 : b'\xc3\x84', # Ä + 0xc5 : b'\xc3\x85', # Ã… + 0xc6 : b'\xc3\x86', # Æ + 0xc7 : b'\xc3\x87', # Ç + 0xc8 : b'\xc3\x88', # È + 0xc9 : b'\xc3\x89', # É + 0xca : b'\xc3\x8a', # Ê + 0xcb : b'\xc3\x8b', # Ë + 0xcc : b'\xc3\x8c', # ÃŒ + 0xcd : b'\xc3\x8d', # à + 0xce : b'\xc3\x8e', # ÃŽ + 0xcf : b'\xc3\x8f', # à + 0xd0 : b'\xc3\x90', # à + 0xd1 : b'\xc3\x91', # Ñ + 0xd2 : b'\xc3\x92', # Ã’ + 0xd3 : b'\xc3\x93', # Ó + 0xd4 : b'\xc3\x94', # Ô + 0xd5 : b'\xc3\x95', # Õ + 0xd6 : b'\xc3\x96', # Ö + 0xd7 : b'\xc3\x97', # × + 0xd8 : b'\xc3\x98', # Ø + 0xd9 : b'\xc3\x99', # Ù + 0xda : b'\xc3\x9a', # Ú + 0xdb : b'\xc3\x9b', # Û + 0xdc : b'\xc3\x9c', # Ãœ + 0xdd : b'\xc3\x9d', # à + 0xde : b'\xc3\x9e', # Þ + 0xdf : b'\xc3\x9f', # ß + 0xe0 : b'\xc3\xa0', # à + 0xe1 : b'\xa1', # á + 0xe2 : b'\xc3\xa2', # â + 0xe3 : b'\xc3\xa3', # ã + 0xe4 : b'\xc3\xa4', # ä + 0xe5 : b'\xc3\xa5', # Ã¥ + 0xe6 : b'\xc3\xa6', # æ + 0xe7 : b'\xc3\xa7', # ç + 0xe8 : b'\xc3\xa8', # è + 0xe9 : b'\xc3\xa9', # é + 0xea : b'\xc3\xaa', # ê + 0xeb : b'\xc3\xab', # ë + 0xec : b'\xc3\xac', # ì + 0xed : b'\xc3\xad', # í + 0xee : b'\xc3\xae', # î + 0xef : b'\xc3\xaf', # ï + 0xf0 : b'\xc3\xb0', # ð + 0xf1 : b'\xc3\xb1', # ñ + 0xf2 : b'\xc3\xb2', # ò + 0xf3 : b'\xc3\xb3', # ó + 0xf4 : b'\xc3\xb4', # ô + 0xf5 : b'\xc3\xb5', # õ + 0xf6 : b'\xc3\xb6', # ö + 0xf7 : b'\xc3\xb7', # ÷ + 0xf8 : b'\xc3\xb8', # ø + 0xf9 : b'\xc3\xb9', # ù + 0xfa : b'\xc3\xba', # ú + 0xfb : b'\xc3\xbb', # û + 0xfc : b'\xc3\xbc', # ü + 0xfd : b'\xc3\xbd', # ý + 0xfe : b'\xc3\xbe', # þ + } + + MULTIBYTE_MARKERS_AND_SIZES = [ + (0xc2, 0xdf, 2), # 2-byte characters start with a byte C2-DF + (0xe0, 0xef, 3), # 3-byte characters start with E0-EF + (0xf0, 0xf4, 4), # 4-byte characters start with F0-F4 + ] + + FIRST_MULTIBYTE_MARKER = MULTIBYTE_MARKERS_AND_SIZES[0][0] + LAST_MULTIBYTE_MARKER = MULTIBYTE_MARKERS_AND_SIZES[-1][1] + + @classmethod + def detwingle(cls, in_bytes, main_encoding="utf8", + embedded_encoding="windows-1252"): + """Fix characters from one encoding embedded in some other encoding. + + Currently the only situation supported is Windows-1252 (or its + subset ISO-8859-1), embedded in UTF-8. + + The input must be a bytestring. If you've already converted + the document to Unicode, you're too late. + + The output is a bytestring in which `embedded_encoding` + characters have been converted to their `main_encoding` + equivalents. + """ + if embedded_encoding.replace('_', '-').lower() not in ( + 'windows-1252', 'windows_1252'): + raise NotImplementedError( + "Windows-1252 and ISO-8859-1 are the only currently supported " + "embedded encodings.") + + if main_encoding.lower() not in ('utf8', 'utf-8'): + raise NotImplementedError( + "UTF-8 is the only currently supported main encoding.") + + byte_chunks = [] + + chunk_start = 0 + pos = 0 + while pos < len(in_bytes): + byte = in_bytes[pos] + if not isinstance(byte, int): + # Python 2.x + byte = ord(byte) + if (byte >= cls.FIRST_MULTIBYTE_MARKER + and byte <= cls.LAST_MULTIBYTE_MARKER): + # This is the start of a UTF-8 multibyte character. Skip + # to the end. + for start, end, size in cls.MULTIBYTE_MARKERS_AND_SIZES: + if byte >= start and byte <= end: + pos += size + break + elif byte >= 0x80 and byte in cls.WINDOWS_1252_TO_UTF8: + # We found a Windows-1252 character! + # Save the string up to this point as a chunk. + byte_chunks.append(in_bytes[chunk_start:pos]) + + # Now translate the Windows-1252 character into UTF-8 + # and add it as another, one-byte chunk. + byte_chunks.append(cls.WINDOWS_1252_TO_UTF8[byte]) + pos += 1 + chunk_start = pos + else: + # Go on to the next character. + pos += 1 + if chunk_start == 0: + # The string is unchanged. + return in_bytes + else: + # Store the final chunk. + byte_chunks.append(in_bytes[chunk_start:]) + return b''.join(byte_chunks) + diff --git a/bs4/element.py b/bs4/element.py new file mode 100644 index 00000000..26422fda --- /dev/null +++ b/bs4/element.py @@ -0,0 +1,1355 @@ +import collections +import re +import sys +import warnings +from bs4.dammit import EntitySubstitution + +DEFAULT_OUTPUT_ENCODING = "utf-8" +PY3K = (sys.version_info[0] > 2) + +whitespace_re = re.compile("\s+") + +def _alias(attr): + """Alias one attribute name to another for backward compatibility""" + @property + def alias(self): + return getattr(self, attr) + + @alias.setter + def alias(self): + return setattr(self, attr) + return alias + + +class NamespacedAttribute(unicode): + + def __new__(cls, prefix, name, namespace=None): + if name is None: + obj = unicode.__new__(cls, prefix) + else: + obj = unicode.__new__(cls, prefix + ":" + name) + obj.prefix = prefix + obj.name = name + obj.namespace = namespace + return obj + +class AttributeValueWithCharsetSubstitution(unicode): + """A stand-in object for a character encoding specified in HTML.""" + +class CharsetMetaAttributeValue(AttributeValueWithCharsetSubstitution): + """A generic stand-in for the value of a meta tag's 'charset' attribute. + + When Beautiful Soup parses the markup '', the + value of the 'charset' attribute will be one of these objects. + """ + + def __new__(cls, original_value): + obj = unicode.__new__(cls, original_value) + obj.original_value = original_value + return obj + + def encode(self, encoding): + return encoding + + +class ContentMetaAttributeValue(AttributeValueWithCharsetSubstitution): + """A generic stand-in for the value of a meta tag's 'content' attribute. + + When Beautiful Soup parses the markup: + + + The value of the 'content' attribute will be one of these objects. + """ + + CHARSET_RE = re.compile("((^|;)\s*charset=)([^;]*)", re.M) + + def __new__(cls, original_value): + match = cls.CHARSET_RE.search(original_value) + if match is None: + # No substitution necessary. + return unicode.__new__(unicode, original_value) + + obj = unicode.__new__(cls, original_value) + obj.original_value = original_value + return obj + + def encode(self, encoding): + def rewrite(match): + return match.group(1) + encoding + return self.CHARSET_RE.sub(rewrite, self.original_value) + + +class PageElement(object): + """Contains the navigational information for some part of the page + (either a tag or a piece of text)""" + + # There are five possible values for the "formatter" argument passed in + # to methods like encode() and prettify(): + # + # "html" - All Unicode characters with corresponding HTML entities + # are converted to those entities on output. + # "minimal" - Bare ampersands and angle brackets are converted to + # XML entities: & < > + # None - The null formatter. Unicode characters are never + # converted to entities. This is not recommended, but it's + # faster than "minimal". + # A function - This function will be called on every string that + # needs to undergo entity substition + FORMATTERS = { + "html" : EntitySubstitution.substitute_html, + "minimal" : EntitySubstitution.substitute_xml, + None : None + } + + @classmethod + def format_string(self, s, formatter='minimal'): + """Format the given string using the given formatter.""" + if not callable(formatter): + formatter = self.FORMATTERS.get( + formatter, EntitySubstitution.substitute_xml) + if formatter is None: + output = s + else: + output = formatter(s) + return output + + def setup(self, parent=None, previous_element=None): + """Sets up the initial relations between this element and + other elements.""" + self.parent = parent + self.previous_element = previous_element + if previous_element is not None: + self.previous_element.next_element = self + self.next_element = None + self.previous_sibling = None + self.next_sibling = None + if self.parent is not None and self.parent.contents: + self.previous_sibling = self.parent.contents[-1] + self.previous_sibling.next_sibling = self + + nextSibling = _alias("next_sibling") # BS3 + previousSibling = _alias("previous_sibling") # BS3 + + def replace_with(self, replace_with): + if replace_with is self: + return + if replace_with is self.parent: + raise ValueError("Cannot replace a Tag with its parent.") + old_parent = self.parent + my_index = self.parent.index(self) + self.extract() + old_parent.insert(my_index, replace_with) + return self + replaceWith = replace_with # BS3 + + def unwrap(self): + my_parent = self.parent + my_index = self.parent.index(self) + self.extract() + for child in reversed(self.contents[:]): + my_parent.insert(my_index, child) + return self + replace_with_children = unwrap + replaceWithChildren = unwrap # BS3 + + def wrap(self, wrap_inside): + me = self.replace_with(wrap_inside) + wrap_inside.append(me) + return wrap_inside + + def extract(self): + """Destructively rips this element out of the tree.""" + if self.parent is not None: + del self.parent.contents[self.parent.index(self)] + + #Find the two elements that would be next to each other if + #this element (and any children) hadn't been parsed. Connect + #the two. + last_child = self._last_descendant() + next_element = last_child.next_element + + if self.previous_element is not None: + self.previous_element.next_element = next_element + if next_element is not None: + next_element.previous_element = self.previous_element + self.previous_element = None + last_child.next_element = None + + self.parent = None + if self.previous_sibling is not None: + self.previous_sibling.next_sibling = self.next_sibling + if self.next_sibling is not None: + self.next_sibling.previous_sibling = self.previous_sibling + self.previous_sibling = self.next_sibling = None + return self + + def _last_descendant(self): + "Finds the last element beneath this object to be parsed." + last_child = self + while hasattr(last_child, 'contents') and last_child.contents: + last_child = last_child.contents[-1] + return last_child + # BS3: Not part of the API! + _lastRecursiveChild = _last_descendant + + def insert(self, position, new_child): + if new_child is self: + raise ValueError("Cannot insert a tag into itself.") + if (isinstance(new_child, basestring) + and not isinstance(new_child, NavigableString)): + new_child = NavigableString(new_child) + + position = min(position, len(self.contents)) + if hasattr(new_child, 'parent') and new_child.parent is not None: + # We're 'inserting' an element that's already one + # of this object's children. + if new_child.parent is self: + current_index = self.index(new_child) + if current_index < position: + # We're moving this element further down the list + # of this object's children. That means that when + # we extract this element, our target index will + # jump down one. + position -= 1 + new_child.extract() + + new_child.parent = self + previous_child = None + if position == 0: + new_child.previous_sibling = None + new_child.previous_element = self + else: + previous_child = self.contents[position - 1] + new_child.previous_sibling = previous_child + new_child.previous_sibling.next_sibling = new_child + new_child.previous_element = previous_child._last_descendant() + if new_child.previous_element is not None: + new_child.previous_element.next_element = new_child + + new_childs_last_element = new_child._last_descendant() + + if position >= len(self.contents): + new_child.next_sibling = None + + parent = self + parents_next_sibling = None + while parents_next_sibling is None and parent is not None: + parents_next_sibling = parent.next_sibling + parent = parent.parent + if parents_next_sibling is not None: + # We found the element that comes next in the document. + break + if parents_next_sibling is not None: + new_childs_last_element.next_element = parents_next_sibling + else: + # The last element of this tag is the last element in + # the document. + new_childs_last_element.next_element = None + else: + next_child = self.contents[position] + new_child.next_sibling = next_child + if new_child.next_sibling is not None: + new_child.next_sibling.previous_sibling = new_child + new_childs_last_element.next_element = next_child + + if new_childs_last_element.next_element is not None: + new_childs_last_element.next_element.previous_element = new_childs_last_element + self.contents.insert(position, new_child) + + def append(self, tag): + """Appends the given tag to the contents of this tag.""" + self.insert(len(self.contents), tag) + + def insert_before(self, predecessor): + """Makes the given element the immediate predecessor of this one. + + The two elements will have the same parent, and the given element + will be immediately before this one. + """ + if self is predecessor: + raise ValueError("Can't insert an element before itself.") + parent = self.parent + if parent is None: + raise ValueError( + "Element has no parent, so 'before' has no meaning.") + # Extract first so that the index won't be screwed up if they + # are siblings. + if isinstance(predecessor, PageElement): + predecessor.extract() + index = parent.index(self) + parent.insert(index, predecessor) + + def insert_after(self, successor): + """Makes the given element the immediate successor of this one. + + The two elements will have the same parent, and the given element + will be immediately after this one. + """ + if self is successor: + raise ValueError("Can't insert an element after itself.") + parent = self.parent + if parent is None: + raise ValueError( + "Element has no parent, so 'after' has no meaning.") + # Extract first so that the index won't be screwed up if they + # are siblings. + if isinstance(successor, PageElement): + successor.extract() + index = parent.index(self) + parent.insert(index+1, successor) + + def find_next(self, name=None, attrs={}, text=None, **kwargs): + """Returns the first item that matches the given criteria and + appears after this Tag in the document.""" + return self._find_one(self.find_all_next, name, attrs, text, **kwargs) + findNext = find_next # BS3 + + def find_all_next(self, name=None, attrs={}, text=None, limit=None, + **kwargs): + """Returns all items that match the given criteria and appear + after this Tag in the document.""" + return self._find_all(name, attrs, text, limit, self.next_elements, + **kwargs) + findAllNext = find_all_next # BS3 + + def find_next_sibling(self, name=None, attrs={}, text=None, **kwargs): + """Returns the closest sibling to this Tag that matches the + given criteria and appears after this Tag in the document.""" + return self._find_one(self.find_next_siblings, name, attrs, text, + **kwargs) + findNextSibling = find_next_sibling # BS3 + + def find_next_siblings(self, name=None, attrs={}, text=None, limit=None, + **kwargs): + """Returns the siblings of this Tag that match the given + criteria and appear after this Tag in the document.""" + return self._find_all(name, attrs, text, limit, + self.next_siblings, **kwargs) + findNextSiblings = find_next_siblings # BS3 + fetchNextSiblings = find_next_siblings # BS2 + + def find_previous(self, name=None, attrs={}, text=None, **kwargs): + """Returns the first item that matches the given criteria and + appears before this Tag in the document.""" + return self._find_one( + self.find_all_previous, name, attrs, text, **kwargs) + findPrevious = find_previous # BS3 + + def find_all_previous(self, name=None, attrs={}, text=None, limit=None, + **kwargs): + """Returns all items that match the given criteria and appear + before this Tag in the document.""" + return self._find_all(name, attrs, text, limit, self.previous_elements, + **kwargs) + findAllPrevious = find_all_previous # BS3 + fetchPrevious = find_all_previous # BS2 + + def find_previous_sibling(self, name=None, attrs={}, text=None, **kwargs): + """Returns the closest sibling to this Tag that matches the + given criteria and appears before this Tag in the document.""" + return self._find_one(self.find_previous_siblings, name, attrs, text, + **kwargs) + findPreviousSibling = find_previous_sibling # BS3 + + def find_previous_siblings(self, name=None, attrs={}, text=None, + limit=None, **kwargs): + """Returns the siblings of this Tag that match the given + criteria and appear before this Tag in the document.""" + return self._find_all(name, attrs, text, limit, + self.previous_siblings, **kwargs) + findPreviousSiblings = find_previous_siblings # BS3 + fetchPreviousSiblings = find_previous_siblings # BS2 + + def find_parent(self, name=None, attrs={}, **kwargs): + """Returns the closest parent of this Tag that matches the given + criteria.""" + # NOTE: We can't use _find_one because findParents takes a different + # set of arguments. + r = None + l = self.find_parents(name, attrs, 1) + if l: + r = l[0] + return r + findParent = find_parent # BS3 + + def find_parents(self, name=None, attrs={}, limit=None, **kwargs): + """Returns the parents of this Tag that match the given + criteria.""" + + return self._find_all(name, attrs, None, limit, self.parents, + **kwargs) + findParents = find_parents # BS3 + fetchParents = find_parents # BS2 + + @property + def next(self): + return self.next_element + + @property + def previous(self): + return self.previous_element + + #These methods do the real heavy lifting. + + def _find_one(self, method, name, attrs, text, **kwargs): + r = None + l = method(name, attrs, text, 1, **kwargs) + if l: + r = l[0] + return r + + def _find_all(self, name, attrs, text, limit, generator, **kwargs): + "Iterates over a generator looking for things that match." + + if isinstance(name, SoupStrainer): + strainer = name + elif text is None and not limit and not attrs and not kwargs: + # Optimization to find all tags. + if name is True or name is None: + return [element for element in generator + if isinstance(element, Tag)] + # Optimization to find all tags with a given name. + elif isinstance(name, basestring): + return [element for element in generator + if isinstance(element, Tag) and element.name == name] + else: + strainer = SoupStrainer(name, attrs, text, **kwargs) + else: + # Build a SoupStrainer + strainer = SoupStrainer(name, attrs, text, **kwargs) + results = ResultSet(strainer) + while True: + try: + i = next(generator) + except StopIteration: + break + if i: + found = strainer.search(i) + if found: + results.append(found) + if limit and len(results) >= limit: + break + return results + + #These generators can be used to navigate starting from both + #NavigableStrings and Tags. + @property + def next_elements(self): + i = self.next_element + while i is not None: + yield i + i = i.next_element + + @property + def next_siblings(self): + i = self.next_sibling + while i is not None: + yield i + i = i.next_sibling + + @property + def previous_elements(self): + i = self.previous_element + while i is not None: + yield i + i = i.previous_element + + @property + def previous_siblings(self): + i = self.previous_sibling + while i is not None: + yield i + i = i.previous_sibling + + @property + def parents(self): + i = self.parent + while i is not None: + yield i + i = i.parent + + # Methods for supporting CSS selectors. + + tag_name_re = re.compile('^[a-z0-9]+$') + + # /^(\w+)\[(\w+)([=~\|\^\$\*]?)=?"?([^\]"]*)"?\]$/ + # \---/ \---/\-------------/ \-------/ + # | | | | + # | | | The value + # | | ~,|,^,$,* or = + # | Attribute + # Tag + attribselect_re = re.compile( + r'^(?P\w+)?\[(?P\w+)(?P[=~\|\^\$\*]?)' + + r'=?"?(?P[^\]"]*)"?\]$' + ) + + def _attr_value_as_string(self, value, default=None): + """Force an attribute value into a string representation. + + A multi-valued attribute will be converted into a + space-separated stirng. + """ + value = self.get(value, default) + if isinstance(value, list) or isinstance(value, tuple): + value =" ".join(value) + return value + + def _attribute_checker(self, operator, attribute, value=''): + """Create a function that performs a CSS selector operation. + + Takes an operator, attribute and optional value. Returns a + function that will return True for elements that match that + combination. + """ + if operator == '=': + # string representation of `attribute` is equal to `value` + return lambda el: el._attr_value_as_string(attribute) == value + elif operator == '~': + # space-separated list representation of `attribute` + # contains `value` + def _includes_value(element): + attribute_value = element.get(attribute, []) + if not isinstance(attribute_value, list): + attribute_value = attribute_value.split() + return value in attribute_value + return _includes_value + elif operator == '^': + # string representation of `attribute` starts with `value` + return lambda el: el._attr_value_as_string( + attribute, '').startswith(value) + elif operator == '$': + # string represenation of `attribute` ends with `value` + return lambda el: el._attr_value_as_string( + attribute, '').endswith(value) + elif operator == '*': + # string representation of `attribute` contains `value` + return lambda el: value in el._attr_value_as_string(attribute, '') + elif operator == '|': + # string representation of `attribute` is either exactly + # `value` or starts with `value` and then a dash. + def _is_or_starts_with_dash(element): + attribute_value = element._attr_value_as_string(attribute, '') + return (attribute_value == value or attribute_value.startswith( + value + '-')) + return _is_or_starts_with_dash + else: + return lambda el: el.has_attr(attribute) + + def select(self, selector): + """Perform a CSS selection operation on the current element.""" + tokens = selector.split() + current_context = [self] + for index, token in enumerate(tokens): + if tokens[index - 1] == '>': + # already found direct descendants in last step. skip this + # step. + continue + m = self.attribselect_re.match(token) + if m is not None: + # Attribute selector + tag, attribute, operator, value = m.groups() + if not tag: + tag = True + checker = self._attribute_checker(operator, attribute, value) + found = [] + for context in current_context: + found.extend( + [el for el in context.find_all(tag) if checker(el)]) + current_context = found + continue + + if '#' in token: + # ID selector + tag, id = token.split('#', 1) + if tag == "": + tag = True + el = current_context[0].find(tag, {'id': id}) + if el is None: + return [] # No match + current_context = [el] + continue + + if '.' in token: + # Class selector + tag_name, klass = token.split('.', 1) + if not tag_name: + tag_name = True + classes = set(klass.split('.')) + found = [] + def classes_match(tag): + if tag_name is not True and tag.name != tag_name: + return False + if not tag.has_attr('class'): + return False + return classes.issubset(tag['class']) + for context in current_context: + found.extend(context.find_all(classes_match)) + current_context = found + continue + + if token == '*': + # Star selector + found = [] + for context in current_context: + found.extend(context.findAll(True)) + current_context = found + continue + + if token == '>': + # Child selector + tag = tokens[index + 1] + if not tag: + tag = True + + found = [] + for context in current_context: + found.extend(context.find_all(tag, recursive=False)) + current_context = found + continue + + # Here we should just have a regular tag + if not self.tag_name_re.match(token): + return [] + found = [] + for context in current_context: + found.extend(context.findAll(token)) + current_context = found + return current_context + + # Old non-property versions of the generators, for backwards + # compatibility with BS3. + def nextGenerator(self): + return self.next_elements + + def nextSiblingGenerator(self): + return self.next_siblings + + def previousGenerator(self): + return self.previous_elements + + def previousSiblingGenerator(self): + return self.previous_siblings + + def parentGenerator(self): + return self.parents + + +class NavigableString(unicode, PageElement): + + PREFIX = '' + SUFFIX = '' + + def __new__(cls, value): + """Create a new NavigableString. + + When unpickling a NavigableString, this method is called with + the string in DEFAULT_OUTPUT_ENCODING. That encoding needs to be + passed in to the superclass's __new__ or the superclass won't know + how to handle non-ASCII characters. + """ + if isinstance(value, unicode): + return unicode.__new__(cls, value) + return unicode.__new__(cls, value, DEFAULT_OUTPUT_ENCODING) + + def __getnewargs__(self): + return (unicode(self),) + + def __getattr__(self, attr): + """text.string gives you text. This is for backwards + compatibility for Navigable*String, but for CData* it lets you + get the string without the CData wrapper.""" + if attr == 'string': + return self + else: + raise AttributeError( + "'%s' object has no attribute '%s'" % ( + self.__class__.__name__, attr)) + + def output_ready(self, formatter="minimal"): + output = self.format_string(self, formatter) + return self.PREFIX + output + self.SUFFIX + + +class PreformattedString(NavigableString): + """A NavigableString not subject to the normal formatting rules. + + The string will be passed into the formatter (to trigger side effects), + but the return value will be ignored. + """ + + def output_ready(self, formatter="minimal"): + """CData strings are passed into the formatter. + But the return value is ignored.""" + self.format_string(self, formatter) + return self.PREFIX + self + self.SUFFIX + +class CData(PreformattedString): + + PREFIX = u'' + +class ProcessingInstruction(PreformattedString): + + PREFIX = u'' + +class Comment(PreformattedString): + + PREFIX = u'' + + +class Declaration(PreformattedString): + PREFIX = u'' + + +class Doctype(PreformattedString): + + @classmethod + def for_name_and_ids(cls, name, pub_id, system_id): + value = name + if pub_id is not None: + value += ' PUBLIC "%s"' % pub_id + if system_id is not None: + value += ' "%s"' % system_id + elif system_id is not None: + value += ' SYSTEM "%s"' % system_id + + return Doctype(value) + + PREFIX = u'\n' + + +class Tag(PageElement): + + """Represents a found HTML tag with its attributes and contents.""" + + def __init__(self, parser=None, builder=None, name=None, namespace=None, + prefix=None, attrs=None, parent=None, previous=None): + "Basic constructor." + + if parser is None: + self.parser_class = None + else: + # We don't actually store the parser object: that lets extracted + # chunks be garbage-collected. + self.parser_class = parser.__class__ + if name is None: + raise ValueError("No value provided for new tag's name.") + self.name = name + self.namespace = namespace + self.prefix = prefix + if attrs is None: + attrs = {} + elif builder.cdata_list_attributes: + attrs = builder._replace_cdata_list_attribute_values( + self.name, attrs) + else: + attrs = dict(attrs) + self.attrs = attrs + self.contents = [] + self.setup(parent, previous) + self.hidden = False + + # Set up any substitutions, such as the charset in a META tag. + if builder is not None: + builder.set_up_substitutions(self) + self.can_be_empty_element = builder.can_be_empty_element(name) + else: + self.can_be_empty_element = False + + parserClass = _alias("parser_class") # BS3 + + @property + def is_empty_element(self): + """Is this tag an empty-element tag? (aka a self-closing tag) + + A tag that has contents is never an empty-element tag. + + A tag that has no contents may or may not be an empty-element + tag. It depends on the builder used to create the tag. If the + builder has a designated list of empty-element tags, then only + a tag whose name shows up in that list is considered an + empty-element tag. + + If the builder has no designated list of empty-element tags, + then any tag with no contents is an empty-element tag. + """ + return len(self.contents) == 0 and self.can_be_empty_element + isSelfClosing = is_empty_element # BS3 + + @property + def string(self): + """Convenience property to get the single string within this tag. + + :Return: If this tag has a single string child, return value + is that string. If this tag has no children, or more than one + child, return value is None. If this tag has one child tag, + return value is the 'string' attribute of the child tag, + recursively. + """ + if len(self.contents) != 1: + return None + child = self.contents[0] + if isinstance(child, NavigableString): + return child + return child.string + + @string.setter + def string(self, string): + self.clear() + self.append(string.__class__(string)) + + def _all_strings(self, strip=False): + """Yield all child strings, possibly stripping them.""" + for descendant in self.descendants: + if not isinstance(descendant, NavigableString): + continue + if strip: + descendant = descendant.strip() + if len(descendant) == 0: + continue + yield descendant + strings = property(_all_strings) + + @property + def stripped_strings(self): + for string in self._all_strings(True): + yield string + + def get_text(self, separator=u"", strip=False): + """ + Get all child strings, concatenated using the given separator. + """ + return separator.join([s for s in self._all_strings(strip)]) + getText = get_text + text = property(get_text) + + def decompose(self): + """Recursively destroys the contents of this tree.""" + self.extract() + i = self + while i is not None: + next = i.next_element + i.__dict__.clear() + i = next + + def clear(self, decompose=False): + """ + Extract all children. If decompose is True, decompose instead. + """ + if decompose: + for element in self.contents[:]: + if isinstance(element, Tag): + element.decompose() + else: + element.extract() + else: + for element in self.contents[:]: + element.extract() + + def index(self, element): + """ + Find the index of a child by identity, not value. Avoids issues with + tag.contents.index(element) getting the index of equal elements. + """ + for i, child in enumerate(self.contents): + if child is element: + return i + raise ValueError("Tag.index: element not in tag") + + def get(self, key, default=None): + """Returns the value of the 'key' attribute for the tag, or + the value given for 'default' if it doesn't have that + attribute.""" + return self.attrs.get(key, default) + + def has_attr(self, key): + return key in self.attrs + + def __hash__(self): + return str(self).__hash__() + + def __getitem__(self, key): + """tag[key] returns the value of the 'key' attribute for the tag, + and throws an exception if it's not there.""" + return self.attrs[key] + + def __iter__(self): + "Iterating over a tag iterates over its contents." + return iter(self.contents) + + def __len__(self): + "The length of a tag is the length of its list of contents." + return len(self.contents) + + def __contains__(self, x): + return x in self.contents + + def __nonzero__(self): + "A tag is non-None even if it has no contents." + return True + + def __setitem__(self, key, value): + """Setting tag[key] sets the value of the 'key' attribute for the + tag.""" + self.attrs[key] = value + + def __delitem__(self, key): + "Deleting tag[key] deletes all 'key' attributes for the tag." + self.attrs.pop(key, None) + + def __call__(self, *args, **kwargs): + """Calling a tag like a function is the same as calling its + find_all() method. Eg. tag('a') returns a list of all the A tags + found within this tag.""" + return self.find_all(*args, **kwargs) + + def __getattr__(self, tag): + #print "Getattr %s.%s" % (self.__class__, tag) + if len(tag) > 3 and tag.endswith('Tag'): + # BS3: soup.aTag -> "soup.find("a") + tag_name = tag[:-3] + warnings.warn( + '.%sTag is deprecated, use .find("%s") instead.' % ( + tag_name, tag_name)) + return self.find(tag_name) + # We special case contents to avoid recursion. + elif not tag.startswith("__") and not tag=="contents": + return self.find(tag) + raise AttributeError( + "'%s' object has no attribute '%s'" % (self.__class__, tag)) + + def __eq__(self, other): + """Returns true iff this tag has the same name, the same attributes, + and the same contents (recursively) as the given tag.""" + if self is other: + return True + if (not hasattr(other, 'name') or + not hasattr(other, 'attrs') or + not hasattr(other, 'contents') or + self.name != other.name or + self.attrs != other.attrs or + len(self) != len(other)): + return False + for i, my_child in enumerate(self.contents): + if my_child != other.contents[i]: + return False + return True + + def __ne__(self, other): + """Returns true iff this tag is not identical to the other tag, + as defined in __eq__.""" + return not self == other + + def __repr__(self, encoding=DEFAULT_OUTPUT_ENCODING): + """Renders this tag as a string.""" + return self.encode(encoding) + + def __unicode__(self): + return self.decode() + + def __str__(self): + return self.encode() + + if PY3K: + __str__ = __repr__ = __unicode__ + + def encode(self, encoding=DEFAULT_OUTPUT_ENCODING, + indent_level=None, formatter="minimal", + errors="xmlcharrefreplace"): + # Turn the data structure into Unicode, then encode the + # Unicode. + u = self.decode(indent_level, encoding, formatter) + return u.encode(encoding, errors) + + def decode(self, indent_level=None, + eventual_encoding=DEFAULT_OUTPUT_ENCODING, + formatter="minimal"): + """Returns a Unicode representation of this tag and its contents. + + :param eventual_encoding: The tag is destined to be + encoded into this encoding. This method is _not_ + responsible for performing that encoding. This information + is passed in so that it can be substituted in if the + document contains a tag that mentions the document's + encoding. + """ + attrs = [] + if self.attrs: + for key, val in sorted(self.attrs.items()): + if val is None: + decoded = key + else: + if isinstance(val, list) or isinstance(val, tuple): + val = ' '.join(val) + elif not isinstance(val, basestring): + val = unicode(val) + elif ( + isinstance(val, AttributeValueWithCharsetSubstitution) + and eventual_encoding is not None): + val = val.encode(eventual_encoding) + + text = self.format_string(val, formatter) + decoded = ( + unicode(key) + '=' + + EntitySubstitution.quoted_attribute_value(text)) + attrs.append(decoded) + close = '' + closeTag = '' + + prefix = '' + if self.prefix: + prefix = self.prefix + ":" + + if self.is_empty_element: + close = '/' + else: + closeTag = '' % (prefix, self.name) + + pretty_print = (indent_level is not None) + if pretty_print: + space = (' ' * (indent_level - 1)) + indent_contents = indent_level + 1 + else: + space = '' + indent_contents = None + contents = self.decode_contents( + indent_contents, eventual_encoding, formatter) + + if self.hidden: + # This is the 'document root' object. + s = contents + else: + s = [] + attribute_string = '' + if attrs: + attribute_string = ' ' + ' '.join(attrs) + if pretty_print: + s.append(space) + s.append('<%s%s%s%s>' % ( + prefix, self.name, attribute_string, close)) + if pretty_print: + s.append("\n") + s.append(contents) + if pretty_print and contents and contents[-1] != "\n": + s.append("\n") + if pretty_print and closeTag: + s.append(space) + s.append(closeTag) + if pretty_print and closeTag and self.next_sibling: + s.append("\n") + s = ''.join(s) + return s + + def prettify(self, encoding=None, formatter="minimal"): + if encoding is None: + return self.decode(True, formatter=formatter) + else: + return self.encode(encoding, True, formatter=formatter) + + def decode_contents(self, indent_level=None, + eventual_encoding=DEFAULT_OUTPUT_ENCODING, + formatter="minimal"): + """Renders the contents of this tag as a Unicode string. + + :param eventual_encoding: The tag is destined to be + encoded into this encoding. This method is _not_ + responsible for performing that encoding. This information + is passed in so that it can be substituted in if the + document contains a tag that mentions the document's + encoding. + """ + pretty_print = (indent_level is not None) + s = [] + for c in self: + text = None + if isinstance(c, NavigableString): + text = c.output_ready(formatter) + elif isinstance(c, Tag): + s.append(c.decode(indent_level, eventual_encoding, + formatter)) + if text and indent_level: + text = text.strip() + if text: + if pretty_print: + s.append(" " * (indent_level - 1)) + s.append(text) + if pretty_print: + s.append("\n") + return ''.join(s) + + def encode_contents( + self, indent_level=None, encoding=DEFAULT_OUTPUT_ENCODING, + formatter="minimal"): + """Renders the contents of this tag as a bytestring.""" + contents = self.decode_contents(indent_level, encoding, formatter) + return contents.encode(encoding) + + # Old method for BS3 compatibility + def renderContents(self, encoding=DEFAULT_OUTPUT_ENCODING, + prettyPrint=False, indentLevel=0): + if not prettyPrint: + indentLevel = None + return self.encode_contents( + indent_level=indentLevel, encoding=encoding) + + #Soup methods + + def find(self, name=None, attrs={}, recursive=True, text=None, + **kwargs): + """Return only the first child of this Tag matching the given + criteria.""" + r = None + l = self.find_all(name, attrs, recursive, text, 1, **kwargs) + if l: + r = l[0] + return r + findChild = find + + def find_all(self, name=None, attrs={}, recursive=True, text=None, + limit=None, **kwargs): + """Extracts a list of Tag objects that match the given + criteria. You can specify the name of the Tag and any + attributes you want the Tag to have. + + The value of a key-value pair in the 'attrs' map can be a + string, a list of strings, a regular expression object, or a + callable that takes a string and returns whether or not the + string matches for some custom definition of 'matches'. The + same is true of the tag name.""" + + generator = self.descendants + if not recursive: + generator = self.children + return self._find_all(name, attrs, text, limit, generator, **kwargs) + findAll = find_all # BS3 + findChildren = find_all # BS2 + + #Generator methods + @property + def children(self): + # return iter() to make the purpose of the method clear + return iter(self.contents) # XXX This seems to be untested. + + @property + def descendants(self): + if not len(self.contents): + return + stopNode = self._last_descendant().next_element + current = self.contents[0] + while current is not stopNode: + yield current + current = current.next_element + + # Old names for backwards compatibility + def childGenerator(self): + return self.children + + def recursiveChildGenerator(self): + return self.descendants + + # This was kind of misleading because has_key() (attributes) was + # different from __in__ (contents). has_key() is gone in Python 3, + # anyway. + has_key = has_attr + +# Next, a couple classes to represent queries and their results. +class SoupStrainer(object): + """Encapsulates a number of ways of matching a markup element (tag or + text).""" + + def __init__(self, name=None, attrs={}, text=None, **kwargs): + self.name = self._normalize_search_value(name) + if not isinstance(attrs, dict): + # Treat a non-dict value for attrs as a search for the 'class' + # attribute. + kwargs['class'] = attrs + attrs = None + + if 'class_' in kwargs: + # Treat class_="foo" as a search for the 'class' + # attribute, overriding any non-dict value for attrs. + kwargs['class'] = kwargs['class_'] + del kwargs['class_'] + + if kwargs: + if attrs: + attrs = attrs.copy() + attrs.update(kwargs) + else: + attrs = kwargs + normalized_attrs = {} + for key, value in attrs.items(): + normalized_attrs[key] = self._normalize_search_value(value) + + self.attrs = normalized_attrs + self.text = self._normalize_search_value(text) + + def _normalize_search_value(self, value): + # Leave it alone if it's a Unicode string, a callable, a + # regular expression, a boolean, or None. + if (isinstance(value, unicode) or callable(value) or hasattr(value, 'match') + or isinstance(value, bool) or value is None): + return value + + # If it's a bytestring, convert it to Unicode, treating it as UTF-8. + if isinstance(value, bytes): + return value.decode("utf8") + + # If it's listlike, convert it into a list of strings. + if hasattr(value, '__iter__'): + new_value = [] + for v in value: + if (hasattr(v, '__iter__') and not isinstance(v, bytes) + and not isinstance(v, unicode)): + # This is almost certainly the user's mistake. In the + # interests of avoiding infinite loops, we'll let + # it through as-is rather than doing a recursive call. + new_value.append(v) + else: + new_value.append(self._normalize_search_value(v)) + return new_value + + # Otherwise, convert it into a Unicode string. + # The unicode(str()) thing is so this will do the same thing on Python 2 + # and Python 3. + return unicode(str(value)) + + def __str__(self): + if self.text: + return self.text + else: + return "%s|%s" % (self.name, self.attrs) + + def search_tag(self, markup_name=None, markup_attrs={}): + found = None + markup = None + if isinstance(markup_name, Tag): + markup = markup_name + markup_attrs = markup + call_function_with_tag_data = ( + isinstance(self.name, collections.Callable) + and not isinstance(markup_name, Tag)) + + if ((not self.name) + or call_function_with_tag_data + or (markup and self._matches(markup, self.name)) + or (not markup and self._matches(markup_name, self.name))): + if call_function_with_tag_data: + match = self.name(markup_name, markup_attrs) + else: + match = True + markup_attr_map = None + for attr, match_against in list(self.attrs.items()): + if not markup_attr_map: + if hasattr(markup_attrs, 'get'): + markup_attr_map = markup_attrs + else: + markup_attr_map = {} + for k, v in markup_attrs: + markup_attr_map[k] = v + attr_value = markup_attr_map.get(attr) + if not self._matches(attr_value, match_against): + match = False + break + if match: + if markup: + found = markup + else: + found = markup_name + if found and self.text and not self._matches(found.string, self.text): + found = None + return found + searchTag = search_tag + + def search(self, markup): + # print 'looking for %s in %s' % (self, markup) + found = None + # If given a list of items, scan it for a text element that + # matches. + if hasattr(markup, '__iter__') and not isinstance(markup, (Tag, basestring)): + for element in markup: + if isinstance(element, NavigableString) \ + and self.search(element): + found = element + break + # If it's a Tag, make sure its name or attributes match. + # Don't bother with Tags if we're searching for text. + elif isinstance(markup, Tag): + if not self.text or self.name or self.attrs: + found = self.search_tag(markup) + # If it's text, make sure the text matches. + elif isinstance(markup, NavigableString) or \ + isinstance(markup, basestring): + if not self.name and not self.attrs and self._matches(markup, self.text): + found = markup + else: + raise Exception( + "I don't know how to match against a %s" % markup.__class__) + return found + + def _matches(self, markup, match_against): + # print u"Matching %s against %s" % (markup, match_against) + result = False + if isinstance(markup, list) or isinstance(markup, tuple): + # This should only happen when searching a multi-valued attribute + # like 'class'. + if (isinstance(match_against, unicode) + and ' ' in match_against): + # A bit of a special case. If they try to match "foo + # bar" on a multivalue attribute's value, only accept + # the literal value "foo bar" + # + # XXX This is going to be pretty slow because we keep + # splitting match_against. But it shouldn't come up + # too often. + return (whitespace_re.split(match_against) == markup) + else: + for item in markup: + if self._matches(item, match_against): + return True + return False + + if match_against is True: + # True matches any non-None value. + return markup is not None + + if isinstance(match_against, collections.Callable): + return match_against(markup) + + # Custom callables take the tag as an argument, but all + # other ways of matching match the tag name as a string. + if isinstance(markup, Tag): + markup = markup.name + + # Ensure that `markup` is either a Unicode string, or None. + markup = self._normalize_search_value(markup) + + if markup is None: + # None matches None, False, an empty string, an empty list, and so on. + return not match_against + + if isinstance(match_against, unicode): + # Exact string match + return markup == match_against + + if hasattr(match_against, 'match'): + # Regexp match + return match_against.search(markup) + + if hasattr(match_against, '__iter__'): + # The markup must be an exact match against something + # in the iterable. + return markup in match_against + + +class ResultSet(list): + """A ResultSet is just a list that keeps track of the SoupStrainer + that created it.""" + def __init__(self, source): + list.__init__([]) + self.source = source diff --git a/bs4/testing.py b/bs4/testing.py new file mode 100644 index 00000000..30e74f42 --- /dev/null +++ b/bs4/testing.py @@ -0,0 +1,537 @@ +"""Helper classes for tests.""" + +import copy +import functools +import unittest +from unittest import TestCase +from bs4 import BeautifulSoup +from bs4.element import ( + CharsetMetaAttributeValue, + Comment, + ContentMetaAttributeValue, + Doctype, + SoupStrainer, +) + +from bs4.builder import HTMLParserTreeBuilder +default_builder = HTMLParserTreeBuilder + + +class SoupTest(unittest.TestCase): + + @property + def default_builder(self): + return default_builder() + + def soup(self, markup, **kwargs): + """Build a Beautiful Soup object from markup.""" + builder = kwargs.pop('builder', self.default_builder) + return BeautifulSoup(markup, builder=builder, **kwargs) + + def document_for(self, markup): + """Turn an HTML fragment into a document. + + The details depend on the builder. + """ + return self.default_builder.test_fragment_to_document(markup) + + def assertSoupEquals(self, to_parse, compare_parsed_to=None): + builder = self.default_builder + obj = BeautifulSoup(to_parse, builder=builder) + if compare_parsed_to is None: + compare_parsed_to = to_parse + + self.assertEqual(obj.decode(), self.document_for(compare_parsed_to)) + + +class HTMLTreeBuilderSmokeTest(object): + + """A basic test of a treebuilder's competence. + + Any HTML treebuilder, present or future, should be able to pass + these tests. With invalid markup, there's room for interpretation, + and different parsers can handle it differently. But with the + markup in these tests, there's not much room for interpretation. + """ + + def assertDoctypeHandled(self, doctype_fragment): + """Assert that a given doctype string is handled correctly.""" + doctype_str, soup = self._document_with_doctype(doctype_fragment) + + # Make sure a Doctype object was created. + doctype = soup.contents[0] + self.assertEqual(doctype.__class__, Doctype) + self.assertEqual(doctype, doctype_fragment) + self.assertEqual(str(soup)[:len(doctype_str)], doctype_str) + + # Make sure that the doctype was correctly associated with the + # parse tree and that the rest of the document parsed. + self.assertEqual(soup.p.contents[0], 'foo') + + def _document_with_doctype(self, doctype_fragment): + """Generate and parse a document with the given doctype.""" + doctype = '' % doctype_fragment + markup = doctype + '\n

foo

' + soup = self.soup(markup) + return doctype, soup + + def test_normal_doctypes(self): + """Make sure normal, everyday HTML doctypes are handled correctly.""" + self.assertDoctypeHandled("html") + self.assertDoctypeHandled( + 'html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"') + + def test_public_doctype_with_url(self): + doctype = 'html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"' + self.assertDoctypeHandled(doctype) + + def test_system_doctype(self): + self.assertDoctypeHandled('foo SYSTEM "http://www.example.com/"') + + def test_namespaced_system_doctype(self): + # We can handle a namespaced doctype with a system ID. + self.assertDoctypeHandled('xsl:stylesheet SYSTEM "htmlent.dtd"') + + def test_namespaced_public_doctype(self): + # Test a namespaced doctype with a public id. + self.assertDoctypeHandled('xsl:stylesheet PUBLIC "htmlent.dtd"') + + def test_real_xhtml_document(self): + """A real XHTML document should come out more or less the same as it went in.""" + markup = b""" + + +Hello. +Goodbye. +""" + soup = self.soup(markup) + self.assertEqual( + soup.encode("utf-8").replace(b"\n", b""), + markup.replace(b"\n", b"")) + + def test_deepcopy(self): + """Make sure you can copy the tree builder. + + This is important because the builder is part of a + BeautifulSoup object, and we want to be able to copy that. + """ + copy.deepcopy(self.default_builder) + + def test_p_tag_is_never_empty_element(self): + """A

tag is never designated as an empty-element tag. + + Even if the markup shows it as an empty-element tag, it + shouldn't be presented that way. + """ + soup = self.soup("

") + self.assertFalse(soup.p.is_empty_element) + self.assertEqual(str(soup.p), "

") + + def test_unclosed_tags_get_closed(self): + """A tag that's not closed by the end of the document should be closed. + + This applies to all tags except empty-element tags. + """ + self.assertSoupEquals("

", "

") + self.assertSoupEquals("", "") + + self.assertSoupEquals("
", "
") + + def test_br_is_always_empty_element_tag(self): + """A
tag is designated as an empty-element tag. + + Some parsers treat

as one
tag, some parsers as + two tags, but it should always be an empty-element tag. + """ + soup = self.soup("

") + self.assertTrue(soup.br.is_empty_element) + self.assertEqual(str(soup.br), "
") + + def test_nested_formatting_elements(self): + self.assertSoupEquals("") + + def test_comment(self): + # Comments are represented as Comment objects. + markup = "

foobaz

" + self.assertSoupEquals(markup) + + soup = self.soup(markup) + comment = soup.find(text="foobar") + self.assertEqual(comment.__class__, Comment) + + def test_preserved_whitespace_in_pre_and_textarea(self): + """Whitespace must be preserved in 
 and ")
+
+    def test_nested_inline_elements(self):
+        """Inline elements can be nested indefinitely."""
+        b_tag = "Inside a B tag"
+        self.assertSoupEquals(b_tag)
+
+        nested_b_tag = "
A nested tag
"
+        self.assertSoupEquals(nested_b_tag)
+
+        double_nested_b_tag = "
A doubly nested tag
"
+        self.assertSoupEquals(nested_b_tag)
+
+    def test_nested_block_level_elements(self):
+        """Block elements can be nested."""
+        soup = self.soup('
Foo
')
+        blockquote = soup.blockquote
+        self.assertEqual(blockquote.p.b.string, 'Foo')
+        self.assertEqual(blockquote.b.string, 'Foo')
+
+    def test_correctly_nested_tables(self):
+        """One table can go inside another one."""
+        markup = (''
+                  ''
+                  "')
+
+        self.assertSoupEquals(
+            markup,
+            '
Here's another table:"
+                  ''
+                  ''
+                  '
foo
Here\'s another table:'
+            '
foo
'
+            '
')
+
+        self.assertSoupEquals(
+            ""
+            ""
+            "
Foo
Bar
Baz
")
+
+    def test_deeply_nested_multivalued_attribute(self):
+        # html5lib can set the attributes of the same tag many times
+        # as it rearranges the tree. This has caused problems with
+        # multivalued attributes.
+        markup = '
'
+        soup = self.soup(markup)
+        self.assertEqual(["css"], soup.div.div['class'])
+
+    def test_angle_brackets_in_attribute_values_are_escaped(self):
+        self.assertSoupEquals('', '')
+
+    def test_entities_in_attributes_converted_to_unicode(self):
+        expect = u'
'
+        self.assertSoupEquals('
', expect)
+        self.assertSoupEquals('
', expect)
+        self.assertSoupEquals('
', expect)
+
+    def test_entities_in_text_converted_to_unicode(self):
+        expect = u'
pi\N{LATIN SMALL LETTER N WITH TILDE}ata
'
+        self.assertSoupEquals("
piñata
", expect)
+        self.assertSoupEquals("
piñata
", expect)
+        self.assertSoupEquals("
piñata
", expect)
+
+    def test_quot_entity_converted_to_quotation_mark(self):
+        self.assertSoupEquals("
I said "good day!"
",
+                              '
I said "good day!"
')
+
+    def test_out_of_range_entity(self):
+        expect = u"\N{REPLACEMENT CHARACTER}"
+        self.assertSoupEquals("�", expect)
+        self.assertSoupEquals("�", expect)
+        self.assertSoupEquals("�", expect)
+
+    def test_basic_namespaces(self):
+        """Parsers don't need to *understand* namespaces, but at the
+        very least they should not choke on namespaces or lose
+        data."""
+
+        markup = b'4'
+        soup = self.soup(markup)
+        self.assertEqual(markup, soup.encode())
+        html = soup.html
+        self.assertEqual('http://www.w3.org/1999/xhtml', soup.html['xmlns'])
+        self.assertEqual(
+            'http://www.w3.org/1998/Math/MathML', soup.html['xmlns:mathml'])
+        self.assertEqual(
+            'http://www.w3.org/2000/svg', soup.html['xmlns:svg'])
+
+    def test_multivalued_attribute_value_becomes_list(self):
+        markup = b''
+        soup = self.soup(markup)
+        self.assertEqual(['foo', 'bar'], soup.a['class'])
+
+    #
+    # Generally speaking, tests below this point are more tests of
+    # Beautiful Soup than tests of the tree builders. But parsers are
+    # weird, so we run these tests separately for every tree builder
+    # to detect any differences between them.
+    #
+
+    def test_soupstrainer(self):
+        """Parsers should be able to work with SoupStrainers."""
+        strainer = SoupStrainer("b")
+        soup = self.soup("A bold  statement",
+                         parse_only=strainer)
+        self.assertEqual(soup.decode(), "bold")
+
+    def test_single_quote_attribute_values_become_double_quotes(self):
+        self.assertSoupEquals("",
+                              '')
+
+    def test_attribute_values_with_nested_quotes_are_left_alone(self):
+        text = """a"""
+        self.assertSoupEquals(text)
+
+    def test_attribute_values_with_double_nested_quotes_get_quoted(self):
+        text = """a"""
+        soup = self.soup(text)
+        soup.foo['attr'] = 'Brawls happen at "Bob\'s Bar"'
+        self.assertSoupEquals(
+            soup.foo.decode(),
+            """a""")
+
+    def test_ampersand_in_attribute_value_gets_escaped(self):
+        self.assertSoupEquals('',
+                              '')
+
+        self.assertSoupEquals(
+            'foo',
+            'foo')
+
+    def test_escaped_ampersand_in_attribute_value_is_left_alone(self):
+        self.assertSoupEquals('')
+
+    def test_entities_in_strings_converted_during_parsing(self):
+        # Both XML and HTML entities are converted to Unicode characters
+        # during parsing.
+        text = "
<<sacré bleu!>>
"
+        expected = u"
<<sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>>
"
+        self.assertSoupEquals(text, expected)
+
+    def test_smart_quotes_converted_on_the_way_in(self):
+        # Microsoft smart quotes are converted to Unicode characters during
+        # parsing.
+        quote = b"
\x91Foo\x92
"
+        soup = self.soup(quote)
+        self.assertEqual(
+            soup.p.string,
+            u"\N{LEFT SINGLE QUOTATION MARK}Foo\N{RIGHT SINGLE QUOTATION MARK}")
+
+    def test_non_breaking_spaces_converted_on_the_way_in(self):
+        soup = self.soup("  ")
+        self.assertEqual(soup.a.string, u"\N{NO-BREAK SPACE}" * 2)
+
+    def test_entities_converted_on_the_way_out(self):
+        text = "
<<sacré bleu!>>
"
+        expected = u"
<<sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>>
".encode("utf-8")
+        soup = self.soup(text)
+        self.assertEqual(soup.p.encode("utf-8"), expected)
+
+    def test_real_iso_latin_document(self):
+        # Smoke test of interrelated functionality, using an
+        # easy-to-understand document.
+
+        # Here it is in Unicode. Note that it claims to be in ISO-Latin-1.
+        unicode_html = u'
Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!
'
+
+        # That's because we're going to encode it into ISO-Latin-1, and use
+        # that to test.
+        iso_latin_html = unicode_html.encode("iso-8859-1")
+
+        # Parse the ISO-Latin-1 HTML.
+        soup = self.soup(iso_latin_html)
+        # Encode it to UTF-8.
+        result = soup.encode("utf-8")
+
+        # What do we expect the result to look like? Well, it would
+        # look like unicode_html, except that the META tag would say
+        # UTF-8 instead of ISO-Latin-1.
+        expected = unicode_html.replace("ISO-Latin-1", "utf-8")
+
+        # And, of course, it would be in UTF-8, not Unicode.
+        expected = expected.encode("utf-8")
+
+        # Ta-da!
+        self.assertEqual(result, expected)
+
+    def test_real_shift_jis_document(self):
+        # Smoke test to make sure the parser can handle a document in
+        # Shift-JIS encoding, without choking.
+        shift_jis_html = (
+            b'
'
+            b'\x82\xb1\x82\xea\x82\xcdShift-JIS\x82\xc5\x83R\x81[\x83f'
+            b'\x83B\x83\x93\x83O\x82\xb3\x82\xea\x82\xbd\x93\xfa\x96{\x8c'
+            b'\xea\x82\xcc\x83t\x83@\x83C\x83\x8b\x82\xc5\x82\xb7\x81B'
+            b'
')
+        unicode_html = shift_jis_html.decode("shift-jis")
+        soup = self.soup(unicode_html)
+
+        # Make sure the parse tree is correctly encoded to various
+        # encodings.
+        self.assertEqual(soup.encode("utf-8"), unicode_html.encode("utf-8"))
+        self.assertEqual(soup.encode("euc_jp"), unicode_html.encode("euc_jp"))
+
+    def test_real_hebrew_document(self):
+        # A real-world test to make sure we can convert ISO-8859-9 (a
+        # Hebrew encoding) to UTF-8.
+        hebrew_document = b'Hebrew (ISO 8859-8) in Visual Directionality
Hebrew (ISO 8859-8) in Visual Directionality
\xed\xe5\xec\xf9'
+        soup = self.soup(
+            hebrew_document, from_encoding="iso8859-8")
+        self.assertEqual(soup.original_encoding, 'iso8859-8')
+        self.assertEqual(
+            soup.encode('utf-8'),
+            hebrew_document.decode("iso8859-8").encode("utf-8"))
+
+    def test_meta_tag_reflects_current_encoding(self):
+        # Here's the  tag saying that a document is
+        # encoded in Shift-JIS.
+        meta_tag = ('')
+
+        # Here's a document incorporating that meta tag.
+        shift_jis_html = (
+            '\n%s\n'
+            ''
+            'Shift-JIS markup goes here.') % meta_tag
+        soup = self.soup(shift_jis_html)
+
+        # Parse the document, and the charset is seemingly unaffected.
+        parsed_meta = soup.find('meta', {'http-equiv': 'Content-type'})
+        content = parsed_meta['content']
+        self.assertEqual('text/html; charset=x-sjis', content)
+
+        # But that value is actually a ContentMetaAttributeValue object.
+        self.assertTrue(isinstance(content, ContentMetaAttributeValue))
+
+        # And it will take on a value that reflects its current
+        # encoding.
+        self.assertEqual('text/html; charset=utf8', content.encode("utf8"))
+
+        # For the rest of the story, see TestSubstitutions in
+        # test_tree.py.
+
+    def test_html5_style_meta_tag_reflects_current_encoding(self):
+        # Here's the  tag saying that a document is
+        # encoded in Shift-JIS.
+        meta_tag = ('')
+
+        # Here's a document incorporating that meta tag.
+        shift_jis_html = (
+            '\n%s\n'
+            ''
+            'Shift-JIS markup goes here.') % meta_tag
+        soup = self.soup(shift_jis_html)
+
+        # Parse the document, and the charset is seemingly unaffected.
+        parsed_meta = soup.find('meta', id="encoding")
+        charset = parsed_meta['charset']
+        self.assertEqual('x-sjis', charset)
+
+        # But that value is actually a CharsetMetaAttributeValue object.
+        self.assertTrue(isinstance(charset, CharsetMetaAttributeValue))
+
+        # And it will take on a value that reflects its current
+        # encoding.
+        self.assertEqual('utf8', charset.encode("utf8"))
+
+    def test_tag_with_no_attributes_can_have_attributes_added(self):
+        data = self.soup("text")
+        data.a['foo'] = 'bar'
+        self.assertEqual('text', data.a.decode())
+
+class XMLTreeBuilderSmokeTest(object):
+
+    def test_docstring_generated(self):
+        soup = self.soup("")
+        self.assertEqual(
+            soup.encode(), b'\n')
+
+    def test_real_xhtml_document(self):
+        """A real XHTML document should come out *exactly* the same as it went in."""
+        markup = b"""
+
+
+Hello.
+Goodbye.
+"""
+        soup = self.soup(markup)
+        self.assertEqual(
+            soup.encode("utf-8"), markup)
+
+    def test_popping_namespaced_tag(self):
+        markup = 'b2012-07-02T20:33:42Zcd'
+        soup = self.soup(markup)
+        self.assertEqual(
+            unicode(soup.rss), markup)
+
+    def test_docstring_includes_correct_encoding(self):
+        soup = self.soup("")
+        self.assertEqual(
+            soup.encode("latin1"),
+            b'\n')
+
+    def test_large_xml_document(self):
+        """A large XML document should come out the same as it went in."""
+        markup = (b'\n'
+                  + b'0' * (2**12)
+                  + b'')
+        soup = self.soup(markup)
+        self.assertEqual(soup.encode("utf-8"), markup)
+
+
+    def test_tags_are_empty_element_if_and_only_if_they_are_empty(self):
+        self.assertSoupEquals("
", "
")
+        self.assertSoupEquals("
foo
")
+
+    def test_namespaces_are_preserved(self):
+        markup = 'This tag is in the a namespaceThis tag is in the b namespace'
+        soup = self.soup(markup)
+        root = soup.root
+        self.assertEqual("http://example.com/", root['xmlns:a'])
+        self.assertEqual("http://example.net/", root['xmlns:b'])
+
+    def test_closing_namespaced_tag(self):
+        markup = '
20010504
'
+        soup = self.soup(markup)
+        self.assertEqual(unicode(soup.p), markup)
+
+    def test_namespaced_attributes(self):
+        markup = ''
+        soup = self.soup(markup)
+        self.assertEqual(unicode(soup.foo), markup)
+
+class HTML5TreeBuilderSmokeTest(HTMLTreeBuilderSmokeTest):
+    """Smoke test for a tree builder that supports HTML5."""
+
+    def test_real_xhtml_document(self):
+        # Since XHTML is not HTML5, HTML5 parsers are not tested to handle
+        # XHTML documents in any particular way.
+        pass
+
+    def test_html_tags_have_namespace(self):
+        markup = ""
+        soup = self.soup(markup)
+        self.assertEqual("http://www.w3.org/1999/xhtml", soup.a.namespace)
+
+    def test_svg_tags_have_namespace(self):
+        markup = ''
+        soup = self.soup(markup)
+        namespace = "http://www.w3.org/2000/svg"
+        self.assertEqual(namespace, soup.svg.namespace)
+        self.assertEqual(namespace, soup.circle.namespace)
+
+
+    def test_mathml_tags_have_namespace(self):
+        markup = '5'
+        soup = self.soup(markup)
+        namespace = 'http://www.w3.org/1998/Math/MathML'
+        self.assertEqual(namespace, soup.math.namespace)
+        self.assertEqual(namespace, soup.msqrt.namespace)
+
+
+def skipIf(condition, reason):
+   def nothing(test, *args, **kwargs):
+       return None
+
+   def decorator(test_item):
+       if condition:
+           return nothing
+       else:
+           return test_item
+
+   return decorator
diff --git a/data/interfaces/default/base.html b/data/interfaces/default/base.html
index 4fc8590b..152f9311 100644
--- a/data/interfaces/default/base.html
+++ b/data/interfaces/default/base.html
@@ -36,7 +36,7 @@
             
             % elif headphones.CURRENT_VERSION != headphones.LATEST_VERSION and headphones.INSTALL_TYPE != 'win':
             

-                A  newer version is available. You're ${headphones.COMMITS_BEHIND} commits behind. Update or Close
+                A  newer version is available. You're ${headphones.COMMITS_BEHIND} commits behind. Update or Close
             

 			% endif
 	
diff --git a/data/interfaces/default/config.html b/data/interfaces/default/config.html
index 643af20e..edbf1834 100644
--- a/data/interfaces/default/config.html
+++ b/data/interfaces/default/config.html
@@ -302,6 +302,19 @@ m<%inherit file="base.html"/>
                                 
                             
                         
+                        

+                            
+                        

+                        

+                            

+                                
+                                
+                            

+                            

+                                
+                                
+                            

+                        

                     
                     
                 
@@ -926,6 +939,7 @@ m<%inherit file="base.html"/>
 		initConfigCheckbox("#usenewzbin");
 		initConfigCheckbox("#usenzbsorg");
 		initConfigCheckbox("#usewaffles");
+		initConfigCheckbox("#userutracker");
 		initConfigCheckbox("#useblackhole");
 		initConfigCheckbox("#useapi");
 	}
diff --git a/data/interfaces/default/history.html b/data/interfaces/default/history.html
index 162dab2d..616459cc 100644
--- a/data/interfaces/default/history.html
+++ b/data/interfaces/default/history.html
@@ -45,6 +45,8 @@
 					fileid = 'nzb'
 				if item['URL'].find('torrent') != -1:
 					fileid = 'torrent'
+				if item['URL'].find('rutracker') != -1:
+					fileid = 'torrent'
 			%>
 			
 				${item['DateAdded']}
diff --git a/headphones/__init__.py b/headphones/__init__.py
index 0e06ba4c..b22ad120 100644
--- a/headphones/__init__.py
+++ b/headphones/__init__.py
@@ -154,6 +154,9 @@ MININOVA = None
 WAFFLES = None
 WAFFLES_UID = None
 WAFFLES_PASSKEY = None
+RUTRACKER = None
+RUTRACKER_USER = None
+RUTRACKER_PASSWORD = None
 DOWNLOAD_TORRENT_DIR = None
 
 INTERFACE = None
@@ -248,7 +251,7 @@ def initialize():
                 LOSSLESS_DESTINATION_DIR, PREFERRED_QUALITY, PREFERRED_BITRATE, DETECT_BITRATE, ADD_ARTISTS, CORRECT_METADATA, MOVE_FILES, \
                 RENAME_FILES, FOLDER_FORMAT, FILE_FORMAT, CLEANUP_FILES, INCLUDE_EXTRAS, EXTRAS, AUTOWANT_UPCOMING, AUTOWANT_ALL, \
                 ADD_ALBUM_ART, EMBED_ALBUM_ART, EMBED_LYRICS, DOWNLOAD_DIR, BLACKHOLE, BLACKHOLE_DIR, USENET_RETENTION, SEARCH_INTERVAL, \
-                TORRENTBLACKHOLE_DIR, NUMBEROFSEEDERS, ISOHUNT, KAT, MININOVA, WAFFLES, WAFFLES_UID, WAFFLES_PASSKEY, DOWNLOAD_TORRENT_DIR, \
+                TORRENTBLACKHOLE_DIR, NUMBEROFSEEDERS, ISOHUNT, KAT, MININOVA, WAFFLES, WAFFLES_UID, WAFFLES_PASSKEY, RUTRACKER, RUTRACKER_USER, RUTRACKER_PASSWORD, DOWNLOAD_TORRENT_DIR, \
                 LIBRARYSCAN_INTERVAL, DOWNLOAD_SCAN_INTERVAL, SAB_HOST, SAB_USERNAME, SAB_PASSWORD, SAB_APIKEY, SAB_CATEGORY, \
                 NZBMATRIX, NZBMATRIX_USERNAME, NZBMATRIX_APIKEY, NEWZNAB, NEWZNAB_HOST, NEWZNAB_APIKEY, NEWZNAB_ENABLED, EXTRA_NEWZNABS,\
                 NZBSORG, NZBSORG_UID, NZBSORG_HASH, NEWZBIN, NEWZBIN_UID, NEWZBIN_PASSWORD, LASTFM_USERNAME, INTERFACE, FOLDER_PERMISSIONS, \
@@ -269,6 +272,7 @@ def initialize():
         CheckSection('NZBsorg')
         CheckSection('Newzbin')
         CheckSection('Waffles')
+        CheckSection('Rutracker')
         CheckSection('Prowl')
         CheckSection('XBMC')
         CheckSection('NMA')
@@ -342,6 +346,10 @@ def initialize():
         WAFFLES = bool(check_setting_int(CFG, 'Waffles', 'waffles', 0))
         WAFFLES_UID = check_setting_str(CFG, 'Waffles', 'waffles_uid', '')
         WAFFLES_PASSKEY = check_setting_str(CFG, 'Waffles', 'waffles_passkey', '')
+        
+        RUTRACKER = bool(check_setting_int(CFG, 'Rutracker', 'rutracker', 0))
+        RUTRACKER_USER = check_setting_str(CFG, 'Rutracker', 'rutracker_user', '')
+        RUTRACKER_PASSWORD = check_setting_str(CFG, 'Rutracker', 'rutracker_password', '')
 
         SAB_HOST = check_setting_str(CFG, 'SABnzbd', 'sab_host', '')
         SAB_USERNAME = check_setting_str(CFG, 'SABnzbd', 'sab_username', '')
@@ -620,6 +628,11 @@ def config_write():
     new_config['Waffles']['waffles'] = int(WAFFLES)
     new_config['Waffles']['waffles_uid'] = WAFFLES_UID
     new_config['Waffles']['waffles_passkey'] = WAFFLES_PASSKEY
+    
+    new_config['Rutracker'] = {}
+    new_config['Rutracker']['rutracker'] = int(RUTRACKER)
+    new_config['Rutracker']['rutracker_user'] = RUTRACKER_USER
+    new_config['Rutracker']['rutracker_password'] = RUTRACKER_PASSWORD
 
     new_config['General']['search_interval'] = SEARCH_INTERVAL
     new_config['General']['libraryscan_interval'] = LIBRARYSCAN_INTERVAL
diff --git a/headphones/searcher.py b/headphones/searcher.py
index 7470c790..5c48b816 100644
--- a/headphones/searcher.py
+++ b/headphones/searcher.py
@@ -28,6 +28,9 @@ from headphones import logger, db, helpers, classes, sab
 
 import lib.bencode as bencode
 
+import headphones.searcher_rutracker as rutrackersearch
+rutracker = rutrackersearch.Rutracker()
+
 class NewzbinDownloader(urllib.FancyURLopener):
 
     def __init__(self):
@@ -97,7 +100,7 @@ def searchforalbum(albumid=None, new=False, lossless=False):
                 else:
                     foundNZB = searchNZB(result['AlbumID'], new)
 
-            if (headphones.KAT or headphones.ISOHUNT or headphones.MININOVA or headphones.WAFFLES) and foundNZB == "none":
+            if (headphones.KAT or headphones.ISOHUNT or headphones.MININOVA or headphones.WAFFLES or headphones.RUTRACKER) and foundNZB == "none":
                 if result['Status'] == "Wanted Lossless":
                     searchTorrent(result['AlbumID'], new, losslessOnly=True)
                 else:
@@ -109,7 +112,7 @@ def searchforalbum(albumid=None, new=False, lossless=False):
         if (headphones.NZBMATRIX or headphones.NEWZNAB or headphones.NZBSORG or headphones.NEWZBIN) and (headphones.SAB_HOST or headphones.BLACKHOLE):
             foundNZB = searchNZB(albumid, new, lossless)
 
-        if (headphones.KAT or headphones.ISOHUNT or headphones.MININOVA or headphones.WAFFLES) and foundNZB == "none":
+        if (headphones.KAT or headphones.ISOHUNT or headphones.MININOVA or headphones.WAFFLES or headphones.RUTRACKER) and foundNZB == "none":
             searchTorrent(albumid, new, lossless)
 
 def searchNZB(albumid=None, new=False, losslessOnly=False):
@@ -632,6 +635,13 @@ def searchTorrent(albumid=None, new=False, losslessOnly=False):
         results = myDB.select('SELECT ArtistName, AlbumTitle, AlbumID, ReleaseDate from albums WHERE Status="Wanted" OR Status="Wanted Lossless"')
         new = True
         
+    # rutracker login
+    
+    if headphones.RUTRACKER and results:
+        rulogin = rutracker.login(headphones.RUTRACKER_USER, headphones.RUTRACKER_PASSWORD)
+        if not rulogin:
+            logger.info(u'Could not login to rutracker, search results will exclude this provider')
+    
     for albums in results:
         
         albumid = albums[2]
@@ -806,7 +816,54 @@ def searchTorrent(albumid=None, new=False, losslessOnly=False):
                         except Exception, e:
                             logger.error(u"An error occurred while trying to parse the response from Waffles.fm: %s" % e)
 
-
+        
+        # rutracker.org
+        
+        if headphones.RUTRACKER and rulogin:
+        
+            provider = "rutracker.org"
+            
+            # Ignore if release date not specified, results too unpredictable
+            
+            if not year:
+                logger.info(u'Release date not specified, ignoring for rutracker.org')
+            else:
+            
+                bitrate = False
+            
+                if headphones.PREFERRED_QUALITY == 3 or losslessOnly:
+                    format = 'lossless'
+                    maxsize = 10000000000
+                elif headphones.PREFERRED_QUALITY == 1:
+                    format = 'lossless+mp3'
+                    maxsize = 10000000000
+                else:
+                    format = 'mp3'
+                    maxsize = 300000000
+                    if headphones.PREFERRED_QUALITY == 2 and headphones.PREFERRED_BITRATE:
+                        bitrate = True
+                
+                # build search url based on above
+            
+                searchURL = rutracker.searchurl(artistterm, albumterm, year, format)
+                logger.info(u'Parsing results from rutracker.org' % searchURL)
+            
+                # parse results and get best match
+            
+                rulist = rutracker.search(searchURL, maxsize, minimumseeders, albumid, bitrate)
+            
+                # add best match to overall results list
+            
+                if rulist:
+                    for ru in rulist:
+                        title = ru[0].decode('utf-8')
+                        size = ru[1]
+                        url = ru[2]
+                        resultlist.append((title, size, url, provider))
+                        logger.info('Found %s. Size: %s' % (title, helpers.bytes_to_mb(size)))
+                else:
+                    logger.info(u"No valid results found from %s" % (provider))
+                
 
         if headphones.ISOHUNT:
             provider = "isoHunt"    
@@ -1029,19 +1086,24 @@ def searchTorrent(albumid=None, new=False, losslessOnly=False):
                 
                     # Get torrent name from .torrent, this is usually used by the torrent client as the folder name
 
-
                     torrent_name = torrent_folder_name + '.torrent'
                     download_path = os.path.join(headphones.TORRENTBLACKHOLE_DIR, torrent_name)
                     try:
-			#Write the torrent file to a path derived from the TORRENTBLACKHOLE_DIR and file name.
-			torrent_file = open(download_path, 'wb')
-			torrent_file.write(data)
-			torrent_file.close()
-			#Open the fresh torrent file again so we can extract the proper torrent name
-			#Used later in post-processing.
-			torrent_file = open(download_path, 'rb')
+                        if bestqual[3] == 'rutracker.org':
+			                download_path = rutracker.get_torrent(bestqual[2], headphones.TORRENTBLACKHOLE_DIR)
+			                if not download_path:
+			                    break
+                        else:  
+			                #Write the torrent file to a path derived from the TORRENTBLACKHOLE_DIR and file name.
+			                torrent_file = open(download_path, 'wb')
+			                torrent_file.write(data)
+			                torrent_file.close()
+			                
+			            #Open the fresh torrent file again so we can extract the proper torrent name
+			            #Used later in post-processing.
+                        torrent_file = open(download_path, 'rb')
                         torrent_info = bencode.bdecode(torrent_file.read())
-			torrent_file.close()
+                        torrent_file.close()
                         torrent_folder_name = torrent_info['info'].get('name','').decode('utf-8')
                         logger.info('Torrent folder name: %s' % torrent_folder_name)
                     except Exception, e:
@@ -1058,7 +1120,12 @@ def preprocesstorrent(resultlist):
             selresult = result
         elif int(selresult[1]) < int(result[1]): # if size is lower than new result replace previous selected result (bigger size = better quality?)
             selresult = result
-            
+             
+    # get outta here if rutracker
+        
+    if selresult[3] == 'rutracker.org':
+        return True, selresult
+                   
     try:
         request = urllib2.Request(selresult[2])
         request.add_header('Accept-encoding', 'gzip')
diff --git a/headphones/searcher_rutracker.py b/headphones/searcher_rutracker.py
new file mode 100644
index 00000000..8bde0d1a
--- /dev/null
+++ b/headphones/searcher_rutracker.py
@@ -0,0 +1,287 @@
+#!/usr/bin/env python
+# coding=utf-8
+
+# Headphones rutracker.org search
+# Functions called from searcher.py
+
+import urllib
+import urllib2
+import cookielib
+from urlparse import urlparse
+from bs4 import BeautifulSoup
+from headphones import logger, db
+import lib.bencode as bencode
+import os
+
+class Rutracker():
+
+    logged_in = False
+    # Stores a number of login attempts to prevent recursion.
+    #login_counter = 0
+    
+    def __init__(self):
+
+        self.cookiejar = cookielib.CookieJar()
+        self.opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(self.cookiejar))
+        urllib2.install_opener(self.opener)
+
+    def login(self, login, password):
+        """Implements tracker login procedure."""
+        
+        self.logged_in = False
+
+        if login is None or password is None:
+            return False
+
+        #self.login_counter += 1
+        
+        # No recursion wanted.
+        #if self.login_counter > 1:
+        #    return False
+        
+        params = urllib.urlencode({"login_username" : login,
+                                   "login_password" : password,
+                                   "login" : "Вход"})
+
+        try:
+            self.opener.open("http://login.rutracker.org/forum/login.php", params)
+        except :
+            pass
+            
+        # Check if we're logged in
+        
+        for cookie in self.cookiejar:
+            if cookie.name == 'bb_data':
+                self.logged_in = True
+        
+        return self.logged_in
+
+    def searchurl(self, artist, album, year, format):
+        """
+        Return the search url
+        """
+         
+        # Build search url
+        
+        searchterm = ''
+        if artist != 'Various Artists':
+            searchterm = artist
+            searchterm = searchterm + ' '
+        searchterm = searchterm + album
+        searchterm = searchterm + ' '
+        searchterm = searchterm + year
+        
+        providerurl = "http://rutracker.org/forum/tracker.php"
+        
+        if format == 'lossless':
+            format = '+lossless'
+        elif format == 'lossless+mp3':
+            format = '+lossless||mp3||aac'
+        else:
+            format = '+mp3||aac'
+            
+        # sort by size, descending. 
+        
+        sort = '&o=7&s=2'
+        
+        searchurl = "%s?nm=%s%s%s" % (providerurl, urllib.quote(searchterm), format, sort)
+        
+        return searchurl
+    
+    def search(self, searchurl, maxsize, minseeders, albumid, bitrate):
+        """
+        Parse the search results and return the first valid torrent
+        """
+        
+        titles = []
+        urls = []
+        seeders = []
+        sizes = []
+        torrentlist = [] 
+        rulist = []
+        
+        try:
+            
+            page = self.opener.open(searchurl, timeout=60)
+            soup = BeautifulSoup(page.read())
+            
+            # Debug
+            #logger.debug (soup.prettify()) 
+            
+            # Title
+             
+            for link in soup.find_all('a', attrs={'class' : 'med tLink bold'}): 
+                title = link.get_text()
+                titles.append(title)
+            
+            # Download URL
+
+            for link in soup.find_all('a', attrs={'class' : 'small tr-dl dl-stub'}):
+                url = link.get('href')
+                urls.append(url)
+                
+            # Seeders
+             
+            for link in soup.find_all('td', attrs={'class' : 'row4 seedmed'}): 
+                seeder = link.get_text()
+                seeders.append(seeder)
+            
+            # Size
+             
+            for link in soup.find_all('td', attrs={'class' : 'row4 small nowrap tor-size'}): 
+                size = link.u.string
+                sizes.append(size)
+                
+        except :
+            pass
+            
+        # Combine lists
+        
+        torrentlist = zip(titles, urls, seeders, sizes)
+        
+        # return if nothing found
+        
+        if not torrentlist:
+            return False
+            
+         # get headphones track count for album, return if not found
+        
+        hptrackcount = 0
+        
+        myDB = db.DBConnection()
+        tracks = myDB.select('SELECT TrackTitle from tracks WHERE AlbumID=?', [albumid])
+        for track in tracks:
+            hptrackcount += 1
+        
+        if not hptrackcount:
+            logger.info('headphones track info not found, cannot compare to torrent') 
+            return False
+        
+        # Return the first valid torrent, unless we want a preferred bitrate then we want all valid entries
+       
+        for torrent in torrentlist:
+            
+            returntitle = torrent[0].encode('utf-8')
+            url = torrent[1]
+            seeders = torrent[2]
+            size = torrent[3]
+            
+            # Attempt to filter out unwanted
+            
+            title = returntitle.lower()
+            
+            if 'promo' not in title and 'vinyl' not in title and 'songbook' not in title and 'tvrip' not in title and 'hdtv' not in title and 'dvd' not in title \
+              and int(size) <= maxsize and int(seeders) >= minseeders:
+                     
+                # Check torrent info
+                
+                torrent_id = dict([part.split('=') for part in urlparse(url)[4].split('&')])['t']
+                self.cookiejar.set_cookie(cookielib.Cookie(version=0, name='bb_dl', value=torrent_id, port=None, port_specified=False, domain='.rutracker.org', domain_specified=False, domain_initial_dot=False, path='/', path_specified=True, secure=False, expires=None, discard=True, comment=None, comment_url=None, rest={'HttpOnly': None}, rfc2109=False))
+                                          
+                # Debug
+                #for cookie in self.cookiejar:
+                #    logger.debug ('Cookie: %s' % cookie) 
+                     
+                try:
+                    page = self.opener.open(url)
+                    torrent = page.read()
+                    if torrent:
+                        decoded = bencode.bdecode(torrent)
+                        metainfo = decoded['info']
+                    page.close ()
+                except Exception, e:
+                    logger.error('Error getting torrent: %s' % e)  
+                    return False      
+                
+                # get torrent track count and check for cue
+                
+                trackcount = 0
+                cuecount = 0
+                
+                if 'files' in metainfo: # multi
+                    for pathfile in metainfo['files']:
+                        path = pathfile['path']
+                        for file in path:
+                            if '.ape' in file or '.flac' in file or '.ogg' in file or '.m4a' in file or '.aac' in file or '.mp3' in file or '.wav' in file or '.aif' in file:
+                                trackcount += 1
+                            if '.cue' in file:
+                                cuecount += 1
+                                     
+                #Torrent topic page
+        
+                topicurl = 'http://rutracker.org/forum/viewtopic.php?t=' + torrent_id
+                logger.debug ('torrent title: %s' % title)
+                logger.debug ('headphones trackcount: %s' % hptrackcount) 
+                logger.debug ('rutracker trackcount: %s' % trackcount)
+
+                # If torrent track count less than headphones track count, and there's a cue, then attempt to get track count from log(s)
+                # This is for the case where we have a single .flac/.wav which can be split by cue
+                # Not great, but shouldn't be doing this too often
+                
+                totallogcount = 0
+                if trackcount < hptrackcount and cuecount > 0 and cuecount < hptrackcount:
+                    page = self.opener.open(topicurl, timeout=60)
+                    soup = BeautifulSoup(page.read())
+                    findtoc = soup.find_all(text='TOC of the extracted CD')
+                    if not findtoc:
+                        findtoc = soup.find_all(text='TOC извлечённого CD')
+                    for toc in findtoc:
+                        logcount = 0
+                        for toccontent in toc.find_all_next(text=True):
+                            cut_string = toccontent.split('|')
+                            new_string = cut_string[0].lstrip().rstrip()
+                            if new_string == '1' or new_string == '01':
+                                logcount = 1
+                            elif logcount > 0:
+                                if new_string.isdigit():
+                                    logcount += 1
+                                else:
+                                    break
+                        totallogcount = totallogcount + logcount
+                            
+                if totallogcount > 0:
+                    trackcount = totallogcount        
+                    logger.debug ('rutracker logtrackcount: %s' % totallogcount)
+                
+                # If torrent track count = hp track count then return torrent, 
+                # if greater, check for deluxe/special/foreign editions
+                # if less, then allow if it's a single track with a cue
+                
+                valid = False
+                
+                if trackcount == hptrackcount:
+                    valid = True
+                elif trackcount > hptrackcount:
+                    if 'deluxe' in title or 'edition' in title or 'japanese' in title:
+                        valid = True
+                        
+                # return 1st valid torrent if not checking by bitrate, else add to list and return at end
+                
+                if valid:
+                    rulist.append((returntitle, size, topicurl))
+                    if not bitrate:
+                        return rulist
+                         
+        return rulist
+
+
+    def get_torrent(self, url, savelocation):
+    
+        torrent_id = dict([part.split('=') for part in urlparse(url)[4].split('&')])['t']
+        self.cookiejar.set_cookie(cookielib.Cookie(version=0, name='bb_dl', value=torrent_id, port=None, port_specified=False, domain='.rutracker.org', domain_specified=False, domain_initial_dot=False, path='/', path_specified=True, secure=False, expires=None, discard=True, comment=None, comment_url=None, rest={'HttpOnly': None}, rfc2109=False))
+        downloadurl = 'http://dl.rutracker.org/forum/dl.php?t=' + torrent_id                  
+        torrent_name = torrent_id + '.torrent'
+        download_path = os.path.join(savelocation, torrent_name)
+        
+        try:
+            page = self.opener.open(downloadurl)
+            torrent = page.read()
+            fp = open (download_path, 'wb')
+            fp.write (torrent)
+            fp.close ()
+        except Exception, e:
+            logger.error('Error getting torrent: %s' % e)  
+            return False      
+        
+        return download_path
+        
diff --git a/headphones/versioncheck.py b/headphones/versioncheck.py
index 429ec8b9..e1440fd8 100644
--- a/headphones/versioncheck.py
+++ b/headphones/versioncheck.py
@@ -20,7 +20,7 @@ from headphones import logger, version
 
 import lib.simplejson as simplejson
 
-user = "rembo10"
+user = "AdeHub"
 branch = "master"
 
 def runGit(args):
diff --git a/headphones/webserve.py b/headphones/webserve.py
index 799d84f3..d985dc2b 100644
--- a/headphones/webserve.py
+++ b/headphones/webserve.py
@@ -463,6 +463,9 @@ class WebInterface(object):
                     "use_waffles" : checked(headphones.WAFFLES),
                     "waffles_uid" : headphones.WAFFLES_UID,
                     "waffles_passkey": headphones.WAFFLES_PASSKEY,
+                    "use_rutracker" : checked(headphones.RUTRACKER),
+                    "rutracker_user" : headphones.RUTRACKER_USER,
+                    "rutracker_password": headphones.RUTRACKER_PASSWORD,
                     "pref_qual_0" : radio(headphones.PREFERRED_QUALITY, 0),
                     "pref_qual_1" : radio(headphones.PREFERRED_QUALITY, 1),
                     "pref_qual_3" : radio(headphones.PREFERRED_QUALITY, 3),
@@ -545,7 +548,7 @@ class WebInterface(object):
         sab_category=None, download_dir=None, blackhole=0, blackhole_dir=None, usenet_retention=None, nzbmatrix=0, nzbmatrix_username=None, nzbmatrix_apikey=None, 
         newznab=0, newznab_host=None, newznab_apikey=None, newznab_enabled=0, nzbsorg=0, nzbsorg_uid=None, nzbsorg_hash=None, newzbin=0, newzbin_uid=None, 
         newzbin_password=None, preferred_quality=0, preferred_bitrate=None, detect_bitrate=0, move_files=0, torrentblackhole_dir=None, download_torrent_dir=None, 
-        numberofseeders=10, use_isohunt=0, use_kat=0, use_mininova=0, waffles=0, waffles_uid=None, waffles_passkey=None, rename_files=0, correct_metadata=0, 
+        numberofseeders=10, use_isohunt=0, use_kat=0, use_mininova=0, waffles=0, waffles_uid=None, waffles_passkey=None, rutracker=0, rutracker_user=None, rutracker_password=None, rename_files=0, correct_metadata=0, 
         cleanup_files=0, add_album_art=0, embed_album_art=0, embed_lyrics=0, destination_dir=None, lossless_destination_dir=None, folder_format=None, file_format=None, 
         include_extras=0, single=0, ep=0, compilation=0, soundtrack=0, live=0, remix=0, spokenword=0, audiobook=0, autowant_upcoming=False, autowant_all=False, 
         interface=None, log_dir=None, music_encoder=0, encoder=None, bitrate=None, samplingfrequency=None, encoderfolder=None, advancedencoder=None, 
@@ -595,6 +598,9 @@ class WebInterface(object):
         headphones.WAFFLES = waffles
         headphones.WAFFLES_UID = waffles_uid
         headphones.WAFFLES_PASSKEY = waffles_passkey
+        headphones.RUTRACKER = rutracker
+        headphones.RUTRACKER_USER = rutracker_user
+        headphones.RUTRACKER_PASSWORD = rutracker_password
         headphones.PREFERRED_QUALITY = int(preferred_quality)
         headphones.PREFERRED_BITRATE = preferred_bitrate
         headphones.PREFERRED_BITRATE_HIGH_BUFFER = preferred_bitrate_high_buffer
diff --git a/html5lib/__init__.py b/html5lib/__init__.py
new file mode 100644
index 00000000..16537aad
--- /dev/null
+++ b/html5lib/__init__.py
@@ -0,0 +1,17 @@
+""" 
+HTML parsing library based on the WHATWG "HTML5"
+specification. The parser is designed to be compatible with existing
+HTML found in the wild and implements well-defined error recovery that
+is largely compatible with modern desktop web browsers.
+
+Example usage:
+
+import html5lib
+f = open("my_document.html")
+tree = html5lib.parse(f) 
+"""
+__version__ = "0.95-dev"
+from html5parser import HTMLParser, parse, parseFragment
+from treebuilders import getTreeBuilder
+from treewalkers import getTreeWalker
+from serializer import serialize
diff --git a/html5lib/constants.py b/html5lib/constants.py
new file mode 100644
index 00000000..b533018e
--- /dev/null
+++ b/html5lib/constants.py
@@ -0,0 +1,3085 @@
+import string, gettext
+_ = gettext.gettext
+
+try:
+    frozenset
+except NameError:
+    # Import from the sets module for python 2.3
+    from sets import Set as set
+    from sets import ImmutableSet as frozenset
+
+EOF = None
+
+E = {
+    "null-character": 
+       _(u"Null character in input stream, replaced with U+FFFD."),
+    "invalid-codepoint": 
+       _(u"Invalid codepoint in stream."),
+    "incorrectly-placed-solidus":
+       _(u"Solidus (/) incorrectly placed in tag."),
+    "incorrect-cr-newline-entity":
+       _(u"Incorrect CR newline entity, replaced with LF."),
+    "illegal-windows-1252-entity":
+       _(u"Entity used with illegal number (windows-1252 reference)."),
+    "cant-convert-numeric-entity":
+       _(u"Numeric entity couldn't be converted to character "
+         u"(codepoint U+%(charAsInt)08x)."),
+    "illegal-codepoint-for-numeric-entity":
+       _(u"Numeric entity represents an illegal codepoint: "
+         u"U+%(charAsInt)08x."),
+    "numeric-entity-without-semicolon":
+       _(u"Numeric entity didn't end with ';'."),
+    "expected-numeric-entity-but-got-eof":
+       _(u"Numeric entity expected. Got end of file instead."),
+    "expected-numeric-entity":
+       _(u"Numeric entity expected but none found."),
+    "named-entity-without-semicolon":
+       _(u"Named entity didn't end with ';'."),
+    "expected-named-entity":
+       _(u"Named entity expected. Got none."),
+    "attributes-in-end-tag":
+       _(u"End tag contains unexpected attributes."),
+    'self-closing-flag-on-end-tag':
+        _(u"End tag contains unexpected self-closing flag."),
+    "expected-tag-name-but-got-right-bracket":
+       _(u"Expected tag name. Got '>' instead."),
+    "expected-tag-name-but-got-question-mark":
+       _(u"Expected tag name. Got '?' instead. (HTML doesn't "
+         u"support processing instructions.)"),
+    "expected-tag-name":
+       _(u"Expected tag name. Got something else instead"),
+    "expected-closing-tag-but-got-right-bracket":
+       _(u"Expected closing tag. Got '>' instead. Ignoring ''."),
+    "expected-closing-tag-but-got-eof":
+       _(u"Expected closing tag. Unexpected end of file."),
+    "expected-closing-tag-but-got-char":
+       _(u"Expected closing tag. Unexpected character '%(data)s' found."),
+    "eof-in-tag-name":
+       _(u"Unexpected end of file in the tag name."),
+    "expected-attribute-name-but-got-eof":
+       _(u"Unexpected end of file. Expected attribute name instead."),
+    "eof-in-attribute-name":
+       _(u"Unexpected end of file in attribute name."),
+    "invalid-character-in-attribute-name":
+        _(u"Invalid chracter in attribute name"),
+    "duplicate-attribute":
+       _(u"Dropped duplicate attribute on tag."),
+    "expected-end-of-tag-name-but-got-eof":
+       _(u"Unexpected end of file. Expected = or end of tag."),
+    "expected-attribute-value-but-got-eof":
+       _(u"Unexpected end of file. Expected attribute value."),
+    "expected-attribute-value-but-got-right-bracket":
+       _(u"Expected attribute value. Got '>' instead."),
+    'equals-in-unquoted-attribute-value':
+        _(u"Unexpected = in unquoted attribute"),
+    'unexpected-character-in-unquoted-attribute-value':
+        _(u"Unexpected character in unquoted attribute"),
+    "invalid-character-after-attribute-name":
+       _(u"Unexpected character after attribute name."),
+    "unexpected-character-after-attribute-value":
+       _(u"Unexpected character after attribute value."),
+    "eof-in-attribute-value-double-quote":
+       _(u"Unexpected end of file in attribute value (\")."),
+    "eof-in-attribute-value-single-quote":
+       _(u"Unexpected end of file in attribute value (')."),
+    "eof-in-attribute-value-no-quotes":
+       _(u"Unexpected end of file in attribute value."),
+    "unexpected-EOF-after-solidus-in-tag":
+        _(u"Unexpected end of file in tag. Expected >"),
+    "unexpected-character-after-soldius-in-tag":
+        _(u"Unexpected character after / in tag. Expected >"),
+    "expected-dashes-or-doctype":
+       _(u"Expected '--' or 'DOCTYPE'. Not found."),
+    "unexpected-bang-after-double-dash-in-comment":
+        _(u"Unexpected ! after -- in comment"),
+    "unexpected-space-after-double-dash-in-comment":
+        _(u"Unexpected space after -- in comment"),
+    "incorrect-comment":
+       _(u"Incorrect comment."),
+    "eof-in-comment":
+       _(u"Unexpected end of file in comment."),
+    "eof-in-comment-end-dash":
+       _(u"Unexpected end of file in comment (-)"),
+    "unexpected-dash-after-double-dash-in-comment":
+       _(u"Unexpected '-' after '--' found in comment."),
+    "eof-in-comment-double-dash":
+       _(u"Unexpected end of file in comment (--)."),
+    "eof-in-comment-end-space-state":
+       _(u"Unexpected end of file in comment."),
+    "eof-in-comment-end-bang-state":
+       _(u"Unexpected end of file in comment."),
+    "unexpected-char-in-comment":
+       _(u"Unexpected character in comment found."),
+    "need-space-after-doctype":
+       _(u"No space after literal string 'DOCTYPE'."),
+    "expected-doctype-name-but-got-right-bracket":
+       _(u"Unexpected > character. Expected DOCTYPE name."),
+    "expected-doctype-name-but-got-eof":
+       _(u"Unexpected end of file. Expected DOCTYPE name."),
+    "eof-in-doctype-name":
+       _(u"Unexpected end of file in DOCTYPE name."),
+    "eof-in-doctype":
+       _(u"Unexpected end of file in DOCTYPE."),
+    "expected-space-or-right-bracket-in-doctype":
+       _(u"Expected space or '>'. Got '%(data)s'"),
+    "unexpected-end-of-doctype":
+       _(u"Unexpected end of DOCTYPE."),
+    "unexpected-char-in-doctype":
+       _(u"Unexpected character in DOCTYPE."),
+    "eof-in-innerhtml":
+       _(u"XXX innerHTML EOF"),
+    "unexpected-doctype":
+       _(u"Unexpected DOCTYPE. Ignored."),
+    "non-html-root":
+       _(u"html needs to be the first start tag."),
+    "expected-doctype-but-got-eof":
+       _(u"Unexpected End of file. Expected DOCTYPE."),
+    "unknown-doctype":
+       _(u"Erroneous DOCTYPE."),
+    "expected-doctype-but-got-chars":
+       _(u"Unexpected non-space characters. Expected DOCTYPE."),
+    "expected-doctype-but-got-start-tag":
+       _(u"Unexpected start tag (%(name)s). Expected DOCTYPE."),
+    "expected-doctype-but-got-end-tag":
+       _(u"Unexpected end tag (%(name)s). Expected DOCTYPE."),
+    "end-tag-after-implied-root":
+       _(u"Unexpected end tag (%(name)s) after the (implied) root element."),
+    "expected-named-closing-tag-but-got-eof":
+       _(u"Unexpected end of file. Expected end tag (%(name)s)."),
+    "two-heads-are-not-better-than-one":
+       _(u"Unexpected start tag head in existing head. Ignored."),
+    "unexpected-end-tag":
+       _(u"Unexpected end tag (%(name)s). Ignored."),
+    "unexpected-start-tag-out-of-my-head":
+       _(u"Unexpected start tag (%(name)s) that can be in head. Moved."),
+    "unexpected-start-tag":
+       _(u"Unexpected start tag (%(name)s)."),
+    "missing-end-tag":
+       _(u"Missing end tag (%(name)s)."),
+    "missing-end-tags":
+       _(u"Missing end tags (%(name)s)."),
+    "unexpected-start-tag-implies-end-tag":
+       _(u"Unexpected start tag (%(startName)s) "
+         u"implies end tag (%(endName)s)."),
+    "unexpected-start-tag-treated-as":
+       _(u"Unexpected start tag (%(originalName)s). Treated as %(newName)s."),
+    "deprecated-tag":
+       _(u"Unexpected start tag %(name)s. Don't use it!"),
+    "unexpected-start-tag-ignored":
+       _(u"Unexpected start tag %(name)s. Ignored."),
+    "expected-one-end-tag-but-got-another":
+       _(u"Unexpected end tag (%(gotName)s). "
+         u"Missing end tag (%(expectedName)s)."),
+    "end-tag-too-early":
+       _(u"End tag (%(name)s) seen too early. Expected other end tag."),
+    "end-tag-too-early-named":
+       _(u"Unexpected end tag (%(gotName)s). Expected end tag (%(expectedName)s)."),
+    "end-tag-too-early-ignored":
+       _(u"End tag (%(name)s) seen too early. Ignored."),
+    "adoption-agency-1.1":
+       _(u"End tag (%(name)s) violates step 1, "
+         u"paragraph 1 of the adoption agency algorithm."),
+    "adoption-agency-1.2":
+       _(u"End tag (%(name)s) violates step 1, "
+         u"paragraph 2 of the adoption agency algorithm."),
+    "adoption-agency-1.3":
+       _(u"End tag (%(name)s) violates step 1, "
+         u"paragraph 3 of the adoption agency algorithm."),
+    "unexpected-end-tag-treated-as":
+       _(u"Unexpected end tag (%(originalName)s). Treated as %(newName)s."),
+    "no-end-tag":
+       _(u"This element (%(name)s) has no end tag."),
+    "unexpected-implied-end-tag-in-table":
+       _(u"Unexpected implied end tag (%(name)s) in the table phase."),
+    "unexpected-implied-end-tag-in-table-body":
+       _(u"Unexpected implied end tag (%(name)s) in the table body phase."),
+    "unexpected-char-implies-table-voodoo":
+       _(u"Unexpected non-space characters in "
+         u"table context caused voodoo mode."),
+    "unexpected-hidden-input-in-table":
+       _(u"Unexpected input with type hidden in table context."),
+    "unexpected-form-in-table":
+       _(u"Unexpected form in table context."),
+    "unexpected-start-tag-implies-table-voodoo":
+       _(u"Unexpected start tag (%(name)s) in "
+         u"table context caused voodoo mode."),
+    "unexpected-end-tag-implies-table-voodoo":
+       _(u"Unexpected end tag (%(name)s) in "
+         u"table context caused voodoo mode."),
+    "unexpected-cell-in-table-body":
+       _(u"Unexpected table cell start tag (%(name)s) "
+         u"in the table body phase."),
+    "unexpected-cell-end-tag":
+       _(u"Got table cell end tag (%(name)s) "
+         u"while required end tags are missing."),
+    "unexpected-end-tag-in-table-body":
+       _(u"Unexpected end tag (%(name)s) in the table body phase. Ignored."),
+    "unexpected-implied-end-tag-in-table-row":
+       _(u"Unexpected implied end tag (%(name)s) in the table row phase."),
+    "unexpected-end-tag-in-table-row":
+       _(u"Unexpected end tag (%(name)s) in the table row phase. Ignored."),
+    "unexpected-select-in-select":
+       _(u"Unexpected select start tag in the select phase "
+         u"treated as select end tag."),
+    "unexpected-input-in-select":
+       _(u"Unexpected input start tag in the select phase."),
+    "unexpected-start-tag-in-select":
+       _(u"Unexpected start tag token (%(name)s in the select phase. "
+         u"Ignored."),
+    "unexpected-end-tag-in-select":
+       _(u"Unexpected end tag (%(name)s) in the select phase. Ignored."),
+    "unexpected-table-element-start-tag-in-select-in-table":
+       _(u"Unexpected table element start tag (%(name)s) in the select in table phase."),
+    "unexpected-table-element-end-tag-in-select-in-table":
+       _(u"Unexpected table element end tag (%(name)s) in the select in table phase."),
+    "unexpected-char-after-body":
+       _(u"Unexpected non-space characters in the after body phase."),
+    "unexpected-start-tag-after-body":
+       _(u"Unexpected start tag token (%(name)s)"
+         u" in the after body phase."),
+    "unexpected-end-tag-after-body":
+       _(u"Unexpected end tag token (%(name)s)"
+         u" in the after body phase."),
+    "unexpected-char-in-frameset":
+       _(u"Unepxected characters in the frameset phase. Characters ignored."),
+    "unexpected-start-tag-in-frameset":
+       _(u"Unexpected start tag token (%(name)s)"
+         u" in the frameset phase. Ignored."),
+    "unexpected-frameset-in-frameset-innerhtml":
+       _(u"Unexpected end tag token (frameset) "
+         u"in the frameset phase (innerHTML)."),
+    "unexpected-end-tag-in-frameset":
+       _(u"Unexpected end tag token (%(name)s)"
+         u" in the frameset phase. Ignored."),
+    "unexpected-char-after-frameset":
+       _(u"Unexpected non-space characters in the "
+         u"after frameset phase. Ignored."),
+    "unexpected-start-tag-after-frameset":
+       _(u"Unexpected start tag (%(name)s)"
+         u" in the after frameset phase. Ignored."),
+    "unexpected-end-tag-after-frameset":
+       _(u"Unexpected end tag (%(name)s)"
+         u" in the after frameset phase. Ignored."),
+    "unexpected-end-tag-after-body-innerhtml":
+       _(u"Unexpected end tag after body(innerHtml)"),
+    "expected-eof-but-got-char":
+       _(u"Unexpected non-space characters. Expected end of file."),
+    "expected-eof-but-got-start-tag":
+       _(u"Unexpected start tag (%(name)s)"
+         u". Expected end of file."),
+    "expected-eof-but-got-end-tag":
+       _(u"Unexpected end tag (%(name)s)"
+         u". Expected end of file."),
+    "eof-in-table":
+       _(u"Unexpected end of file. Expected table content."),
+    "eof-in-select":
+       _(u"Unexpected end of file. Expected select content."),
+    "eof-in-frameset":
+       _(u"Unexpected end of file. Expected frameset content."),
+    "eof-in-script-in-script":
+       _(u"Unexpected end of file. Expected script content."),
+    "eof-in-foreign-lands":
+       _(u"Unexpected end of file. Expected foreign content"),
+    "non-void-element-with-trailing-solidus":
+       _(u"Trailing solidus not allowed on element %(name)s"),
+    "unexpected-html-element-in-foreign-content":
+       _(u"Element %(name)s not allowed in a non-html context"),
+    "unexpected-end-tag-before-html":
+        _(u"Unexpected end tag (%(name)s) before html."),
+    "XXX-undefined-error":
+        (u"Undefined error (this sucks and should be fixed)"),
+}
+
+namespaces = {
+    "html":"http://www.w3.org/1999/xhtml",
+    "mathml":"http://www.w3.org/1998/Math/MathML",
+    "svg":"http://www.w3.org/2000/svg",
+    "xlink":"http://www.w3.org/1999/xlink",
+    "xml":"http://www.w3.org/XML/1998/namespace",
+    "xmlns":"http://www.w3.org/2000/xmlns/"
+}
+
+scopingElements = frozenset((
+    (namespaces["html"], "applet"),
+    (namespaces["html"], "caption"),
+    (namespaces["html"], "html"),
+    (namespaces["html"], "marquee"),
+    (namespaces["html"], "object"),
+    (namespaces["html"], "table"),
+    (namespaces["html"], "td"),
+    (namespaces["html"], "th"),
+    (namespaces["mathml"], "mi"),
+    (namespaces["mathml"], "mo"),
+    (namespaces["mathml"], "mn"),
+    (namespaces["mathml"], "ms"),
+    (namespaces["mathml"], "mtext"),
+    (namespaces["mathml"], "annotation-xml"),
+    (namespaces["svg"], "foreignObject"),
+    (namespaces["svg"], "desc"),
+    (namespaces["svg"], "title"),
+))
+
+formattingElements = frozenset((
+    (namespaces["html"], "a"),
+    (namespaces["html"], "b"),
+    (namespaces["html"], "big"),
+    (namespaces["html"], "code"),
+    (namespaces["html"], "em"),
+    (namespaces["html"], "font"),
+    (namespaces["html"], "i"),
+    (namespaces["html"], "nobr"),
+    (namespaces["html"], "s"),
+    (namespaces["html"], "small"),
+    (namespaces["html"], "strike"),
+    (namespaces["html"], "strong"),
+    (namespaces["html"], "tt"),
+    (namespaces["html"], "u")
+))
+
+specialElements = frozenset((
+    (namespaces["html"], "address"),
+    (namespaces["html"], "applet"),
+    (namespaces["html"], "area"),
+    (namespaces["html"], "article"),
+    (namespaces["html"], "aside"),
+    (namespaces["html"], "base"),
+    (namespaces["html"], "basefont"),
+    (namespaces["html"], "bgsound"),
+    (namespaces["html"], "blockquote"),
+    (namespaces["html"], "body"),
+    (namespaces["html"], "br"),
+    (namespaces["html"], "button"),
+    (namespaces["html"], "caption"),
+    (namespaces["html"], "center"),
+    (namespaces["html"], "col"),
+    (namespaces["html"], "colgroup"),
+    (namespaces["html"], "command"),
+    (namespaces["html"], "dd"),
+    (namespaces["html"], "details"),
+    (namespaces["html"], "dir"),
+    (namespaces["html"], "div"),
+    (namespaces["html"], "dl"),
+    (namespaces["html"], "dt"),
+    (namespaces["html"], "embed"),
+    (namespaces["html"], "fieldset"),
+    (namespaces["html"], "figure"),
+    (namespaces["html"], "footer"),
+    (namespaces["html"], "form"),
+    (namespaces["html"], "frame"),
+    (namespaces["html"], "frameset"),
+    (namespaces["html"], "h1"),
+    (namespaces["html"], "h2"),
+    (namespaces["html"], "h3"),
+    (namespaces["html"], "h4"),
+    (namespaces["html"], "h5"),
+    (namespaces["html"], "h6"),
+    (namespaces["html"], "head"),
+    (namespaces["html"], "header"),
+    (namespaces["html"], "hr"),
+    (namespaces["html"], "html"),
+    (namespaces["html"], "iframe"),
+    # Note that image is commented out in the spec as "this isn't an
+    # element that can end up on the stack, so it doesn't matter,"
+    (namespaces["html"], "image"), 
+    (namespaces["html"], "img"),
+    (namespaces["html"], "input"),
+    (namespaces["html"], "isindex"),
+    (namespaces["html"], "li"),
+    (namespaces["html"], "link"),
+    (namespaces["html"], "listing"),
+    (namespaces["html"], "marquee"),
+    (namespaces["html"], "menu"),
+    (namespaces["html"], "meta"),
+    (namespaces["html"], "nav"),
+    (namespaces["html"], "noembed"),
+    (namespaces["html"], "noframes"),
+    (namespaces["html"], "noscript"),
+    (namespaces["html"], "object"),
+    (namespaces["html"], "ol"),
+    (namespaces["html"], "p"),
+    (namespaces["html"], "param"),
+    (namespaces["html"], "plaintext"),
+    (namespaces["html"], "pre"),
+    (namespaces["html"], "script"),
+    (namespaces["html"], "section"),
+    (namespaces["html"], "select"),
+    (namespaces["html"], "style"),
+    (namespaces["html"], "table"),
+    (namespaces["html"], "tbody"),
+    (namespaces["html"], "td"),
+    (namespaces["html"], "textarea"),
+    (namespaces["html"], "tfoot"),
+    (namespaces["html"], "th"),
+    (namespaces["html"], "thead"),
+    (namespaces["html"], "title"),
+    (namespaces["html"], "tr"),
+    (namespaces["html"], "ul"),
+    (namespaces["html"], "wbr"),
+    (namespaces["html"], "xmp"),
+    (namespaces["svg"], "foreignObject")
+))
+
+htmlIntegrationPointElements = frozenset((
+    (namespaces["mathml"], "annotaion-xml"),
+    (namespaces["svg"], "foreignObject"),
+    (namespaces["svg"], "desc"),
+    (namespaces["svg"], "title")
+))
+
+mathmlTextIntegrationPointElements = frozenset((
+    (namespaces["mathml"], "mi"),
+    (namespaces["mathml"], "mo"),
+    (namespaces["mathml"], "mn"),
+    (namespaces["mathml"], "ms"),
+    (namespaces["mathml"], "mtext")
+))
+
+spaceCharacters = frozenset((
+    u"\t",
+    u"\n",
+    u"\u000C",
+    u" ",
+    u"\r"
+))
+
+tableInsertModeElements = frozenset((
+    "table",
+    "tbody",
+    "tfoot",
+    "thead",
+    "tr"
+))
+
+asciiLowercase = frozenset(string.ascii_lowercase)
+asciiUppercase = frozenset(string.ascii_uppercase)
+asciiLetters = frozenset(string.ascii_letters)
+digits = frozenset(string.digits)
+hexDigits = frozenset(string.hexdigits)
+
+asciiUpper2Lower = dict([(ord(c),ord(c.lower()))
+    for c in string.ascii_uppercase])
+
+# Heading elements need to be ordered
+headingElements = (
+    "h1",
+    "h2",
+    "h3",
+    "h4",
+    "h5",
+    "h6"
+)
+
+voidElements = frozenset((
+    "base",
+    "command",
+    "event-source",
+    "link",
+    "meta",
+    "hr",
+    "br",
+    "img",
+    "embed",
+    "param",
+    "area",
+    "col",
+    "input",
+    "source",
+    "track"
+))
+
+cdataElements = frozenset(('title', 'textarea'))
+
+rcdataElements = frozenset((
+    'style',
+    'script',
+    'xmp',
+    'iframe',
+    'noembed',
+    'noframes',
+    'noscript'
+))
+
+booleanAttributes = {
+    "": frozenset(("irrelevant",)),
+    "style": frozenset(("scoped",)),
+    "img": frozenset(("ismap",)),
+    "audio": frozenset(("autoplay","controls")),
+    "video": frozenset(("autoplay","controls")),
+    "script": frozenset(("defer", "async")),
+    "details": frozenset(("open",)),
+    "datagrid": frozenset(("multiple", "disabled")),
+    "command": frozenset(("hidden", "disabled", "checked", "default")),
+    "hr": frozenset(("noshade")),
+    "menu": frozenset(("autosubmit",)),
+    "fieldset": frozenset(("disabled", "readonly")),
+    "option": frozenset(("disabled", "readonly", "selected")),
+    "optgroup": frozenset(("disabled", "readonly")),
+    "button": frozenset(("disabled", "autofocus")),
+    "input": frozenset(("disabled", "readonly", "required", "autofocus", "checked", "ismap")),
+    "select": frozenset(("disabled", "readonly", "autofocus", "multiple")),
+    "output": frozenset(("disabled", "readonly")),
+}
+
+# entitiesWindows1252 has to be _ordered_ and needs to have an index. It
+# therefore can't be a frozenset.
+entitiesWindows1252 = (
+    8364,  # 0x80  0x20AC  EURO SIGN
+    65533, # 0x81          UNDEFINED
+    8218,  # 0x82  0x201A  SINGLE LOW-9 QUOTATION MARK
+    402,   # 0x83  0x0192  LATIN SMALL LETTER F WITH HOOK
+    8222,  # 0x84  0x201E  DOUBLE LOW-9 QUOTATION MARK
+    8230,  # 0x85  0x2026  HORIZONTAL ELLIPSIS
+    8224,  # 0x86  0x2020  DAGGER
+    8225,  # 0x87  0x2021  DOUBLE DAGGER
+    710,   # 0x88  0x02C6  MODIFIER LETTER CIRCUMFLEX ACCENT
+    8240,  # 0x89  0x2030  PER MILLE SIGN
+    352,   # 0x8A  0x0160  LATIN CAPITAL LETTER S WITH CARON
+    8249,  # 0x8B  0x2039  SINGLE LEFT-POINTING ANGLE QUOTATION MARK
+    338,   # 0x8C  0x0152  LATIN CAPITAL LIGATURE OE
+    65533, # 0x8D          UNDEFINED
+    381,   # 0x8E  0x017D  LATIN CAPITAL LETTER Z WITH CARON
+    65533, # 0x8F          UNDEFINED
+    65533, # 0x90          UNDEFINED
+    8216,  # 0x91  0x2018  LEFT SINGLE QUOTATION MARK
+    8217,  # 0x92  0x2019  RIGHT SINGLE QUOTATION MARK
+    8220,  # 0x93  0x201C  LEFT DOUBLE QUOTATION MARK
+    8221,  # 0x94  0x201D  RIGHT DOUBLE QUOTATION MARK
+    8226,  # 0x95  0x2022  BULLET
+    8211,  # 0x96  0x2013  EN DASH
+    8212,  # 0x97  0x2014  EM DASH
+    732,   # 0x98  0x02DC  SMALL TILDE
+    8482,  # 0x99  0x2122  TRADE MARK SIGN
+    353,   # 0x9A  0x0161  LATIN SMALL LETTER S WITH CARON
+    8250,  # 0x9B  0x203A  SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
+    339,   # 0x9C  0x0153  LATIN SMALL LIGATURE OE
+    65533, # 0x9D          UNDEFINED
+    382,   # 0x9E  0x017E  LATIN SMALL LETTER Z WITH CARON
+    376    # 0x9F  0x0178  LATIN CAPITAL LETTER Y WITH DIAERESIS
+)
+
+xmlEntities = frozenset(('lt;', 'gt;', 'amp;', 'apos;', 'quot;'))
+
+entities = {
+    "AElig": u"\xc6",
+    "AElig;": u"\xc6",
+    "AMP": u"&",
+    "AMP;": u"&",
+    "Aacute": u"\xc1",
+    "Aacute;": u"\xc1",
+    "Abreve;": u"\u0102",
+    "Acirc": u"\xc2",
+    "Acirc;": u"\xc2",
+    "Acy;": u"\u0410",
+    "Afr;": u"\U0001d504",
+    "Agrave": u"\xc0",
+    "Agrave;": u"\xc0",
+    "Alpha;": u"\u0391",
+    "Amacr;": u"\u0100",
+    "And;": u"\u2a53",
+    "Aogon;": u"\u0104",
+    "Aopf;": u"\U0001d538",
+    "ApplyFunction;": u"\u2061",
+    "Aring": u"\xc5",
+    "Aring;": u"\xc5",
+    "Ascr;": u"\U0001d49c",
+    "Assign;": u"\u2254",
+    "Atilde": u"\xc3",
+    "Atilde;": u"\xc3",
+    "Auml": u"\xc4",
+    "Auml;": u"\xc4",
+    "Backslash;": u"\u2216",
+    "Barv;": u"\u2ae7",
+    "Barwed;": u"\u2306",
+    "Bcy;": u"\u0411",
+    "Because;": u"\u2235",
+    "Bernoullis;": u"\u212c",
+    "Beta;": u"\u0392",
+    "Bfr;": u"\U0001d505",
+    "Bopf;": u"\U0001d539",
+    "Breve;": u"\u02d8",
+    "Bscr;": u"\u212c",
+    "Bumpeq;": u"\u224e",
+    "CHcy;": u"\u0427",
+    "COPY": u"\xa9",
+    "COPY;": u"\xa9",
+    "Cacute;": u"\u0106",
+    "Cap;": u"\u22d2",
+    "CapitalDifferentialD;": u"\u2145",
+    "Cayleys;": u"\u212d",
+    "Ccaron;": u"\u010c",
+    "Ccedil": u"\xc7",
+    "Ccedil;": u"\xc7",
+    "Ccirc;": u"\u0108",
+    "Cconint;": u"\u2230",
+    "Cdot;": u"\u010a",
+    "Cedilla;": u"\xb8",
+    "CenterDot;": u"\xb7",
+    "Cfr;": u"\u212d",
+    "Chi;": u"\u03a7",
+    "CircleDot;": u"\u2299",
+    "CircleMinus;": u"\u2296",
+    "CirclePlus;": u"\u2295",
+    "CircleTimes;": u"\u2297",
+    "ClockwiseContourIntegral;": u"\u2232",
+    "CloseCurlyDoubleQuote;": u"\u201d",
+    "CloseCurlyQuote;": u"\u2019",
+    "Colon;": u"\u2237",
+    "Colone;": u"\u2a74",
+    "Congruent;": u"\u2261",
+    "Conint;": u"\u222f",
+    "ContourIntegral;": u"\u222e",
+    "Copf;": u"\u2102",
+    "Coproduct;": u"\u2210",
+    "CounterClockwiseContourIntegral;": u"\u2233",
+    "Cross;": u"\u2a2f",
+    "Cscr;": u"\U0001d49e",
+    "Cup;": u"\u22d3",
+    "CupCap;": u"\u224d",
+    "DD;": u"\u2145",
+    "DDotrahd;": u"\u2911",
+    "DJcy;": u"\u0402",
+    "DScy;": u"\u0405",
+    "DZcy;": u"\u040f",
+    "Dagger;": u"\u2021",
+    "Darr;": u"\u21a1",
+    "Dashv;": u"\u2ae4",
+    "Dcaron;": u"\u010e",
+    "Dcy;": u"\u0414",
+    "Del;": u"\u2207",
+    "Delta;": u"\u0394",
+    "Dfr;": u"\U0001d507",
+    "DiacriticalAcute;": u"\xb4",
+    "DiacriticalDot;": u"\u02d9",
+    "DiacriticalDoubleAcute;": u"\u02dd",
+    "DiacriticalGrave;": u"`",
+    "DiacriticalTilde;": u"\u02dc",
+    "Diamond;": u"\u22c4",
+    "DifferentialD;": u"\u2146",
+    "Dopf;": u"\U0001d53b",
+    "Dot;": u"\xa8",
+    "DotDot;": u"\u20dc",
+    "DotEqual;": u"\u2250",
+    "DoubleContourIntegral;": u"\u222f",
+    "DoubleDot;": u"\xa8",
+    "DoubleDownArrow;": u"\u21d3",
+    "DoubleLeftArrow;": u"\u21d0",
+    "DoubleLeftRightArrow;": u"\u21d4",
+    "DoubleLeftTee;": u"\u2ae4",
+    "DoubleLongLeftArrow;": u"\u27f8",
+    "DoubleLongLeftRightArrow;": u"\u27fa",
+    "DoubleLongRightArrow;": u"\u27f9",
+    "DoubleRightArrow;": u"\u21d2",
+    "DoubleRightTee;": u"\u22a8",
+    "DoubleUpArrow;": u"\u21d1",
+    "DoubleUpDownArrow;": u"\u21d5",
+    "DoubleVerticalBar;": u"\u2225",
+    "DownArrow;": u"\u2193",
+    "DownArrowBar;": u"\u2913",
+    "DownArrowUpArrow;": u"\u21f5",
+    "DownBreve;": u"\u0311",
+    "DownLeftRightVector;": u"\u2950",
+    "DownLeftTeeVector;": u"\u295e",
+    "DownLeftVector;": u"\u21bd",
+    "DownLeftVectorBar;": u"\u2956",
+    "DownRightTeeVector;": u"\u295f",
+    "DownRightVector;": u"\u21c1",
+    "DownRightVectorBar;": u"\u2957",
+    "DownTee;": u"\u22a4",
+    "DownTeeArrow;": u"\u21a7",
+    "Downarrow;": u"\u21d3",
+    "Dscr;": u"\U0001d49f",
+    "Dstrok;": u"\u0110",
+    "ENG;": u"\u014a",
+    "ETH": u"\xd0",
+    "ETH;": u"\xd0",
+    "Eacute": u"\xc9",
+    "Eacute;": u"\xc9",
+    "Ecaron;": u"\u011a",
+    "Ecirc": u"\xca",
+    "Ecirc;": u"\xca",
+    "Ecy;": u"\u042d",
+    "Edot;": u"\u0116",
+    "Efr;": u"\U0001d508",
+    "Egrave": u"\xc8",
+    "Egrave;": u"\xc8",
+    "Element;": u"\u2208",
+    "Emacr;": u"\u0112",
+    "EmptySmallSquare;": u"\u25fb",
+    "EmptyVerySmallSquare;": u"\u25ab",
+    "Eogon;": u"\u0118",
+    "Eopf;": u"\U0001d53c",
+    "Epsilon;": u"\u0395",
+    "Equal;": u"\u2a75",
+    "EqualTilde;": u"\u2242",
+    "Equilibrium;": u"\u21cc",
+    "Escr;": u"\u2130",
+    "Esim;": u"\u2a73",
+    "Eta;": u"\u0397",
+    "Euml": u"\xcb",
+    "Euml;": u"\xcb",
+    "Exists;": u"\u2203",
+    "ExponentialE;": u"\u2147",
+    "Fcy;": u"\u0424",
+    "Ffr;": u"\U0001d509",
+    "FilledSmallSquare;": u"\u25fc",
+    "FilledVerySmallSquare;": u"\u25aa",
+    "Fopf;": u"\U0001d53d",
+    "ForAll;": u"\u2200",
+    "Fouriertrf;": u"\u2131",
+    "Fscr;": u"\u2131",
+    "GJcy;": u"\u0403",
+    "GT": u">",
+    "GT;": u">",
+    "Gamma;": u"\u0393",
+    "Gammad;": u"\u03dc",
+    "Gbreve;": u"\u011e",
+    "Gcedil;": u"\u0122",
+    "Gcirc;": u"\u011c",
+    "Gcy;": u"\u0413",
+    "Gdot;": u"\u0120",
+    "Gfr;": u"\U0001d50a",
+    "Gg;": u"\u22d9",
+    "Gopf;": u"\U0001d53e",
+    "GreaterEqual;": u"\u2265",
+    "GreaterEqualLess;": u"\u22db",
+    "GreaterFullEqual;": u"\u2267",
+    "GreaterGreater;": u"\u2aa2",
+    "GreaterLess;": u"\u2277",
+    "GreaterSlantEqual;": u"\u2a7e",
+    "GreaterTilde;": u"\u2273",
+    "Gscr;": u"\U0001d4a2",
+    "Gt;": u"\u226b",
+    "HARDcy;": u"\u042a",
+    "Hacek;": u"\u02c7",
+    "Hat;": u"^",
+    "Hcirc;": u"\u0124",
+    "Hfr;": u"\u210c",
+    "HilbertSpace;": u"\u210b",
+    "Hopf;": u"\u210d",
+    "HorizontalLine;": u"\u2500",
+    "Hscr;": u"\u210b",
+    "Hstrok;": u"\u0126",
+    "HumpDownHump;": u"\u224e",
+    "HumpEqual;": u"\u224f",
+    "IEcy;": u"\u0415",
+    "IJlig;": u"\u0132",
+    "IOcy;": u"\u0401",
+    "Iacute": u"\xcd",
+    "Iacute;": u"\xcd",
+    "Icirc": u"\xce",
+    "Icirc;": u"\xce",
+    "Icy;": u"\u0418",
+    "Idot;": u"\u0130",
+    "Ifr;": u"\u2111",
+    "Igrave": u"\xcc",
+    "Igrave;": u"\xcc",
+    "Im;": u"\u2111",
+    "Imacr;": u"\u012a",
+    "ImaginaryI;": u"\u2148",
+    "Implies;": u"\u21d2",
+    "Int;": u"\u222c",
+    "Integral;": u"\u222b",
+    "Intersection;": u"\u22c2",
+    "InvisibleComma;": u"\u2063",
+    "InvisibleTimes;": u"\u2062",
+    "Iogon;": u"\u012e",
+    "Iopf;": u"\U0001d540",
+    "Iota;": u"\u0399",
+    "Iscr;": u"\u2110",
+    "Itilde;": u"\u0128",
+    "Iukcy;": u"\u0406",
+    "Iuml": u"\xcf",
+    "Iuml;": u"\xcf",
+    "Jcirc;": u"\u0134",
+    "Jcy;": u"\u0419",
+    "Jfr;": u"\U0001d50d",
+    "Jopf;": u"\U0001d541",
+    "Jscr;": u"\U0001d4a5",
+    "Jsercy;": u"\u0408",
+    "Jukcy;": u"\u0404",
+    "KHcy;": u"\u0425",
+    "KJcy;": u"\u040c",
+    "Kappa;": u"\u039a",
+    "Kcedil;": u"\u0136",
+    "Kcy;": u"\u041a",
+    "Kfr;": u"\U0001d50e",
+    "Kopf;": u"\U0001d542",
+    "Kscr;": u"\U0001d4a6",
+    "LJcy;": u"\u0409",
+    "LT": u"<",
+    "LT;": u"<",
+    "Lacute;": u"\u0139",
+    "Lambda;": u"\u039b",
+    "Lang;": u"\u27ea",
+    "Laplacetrf;": u"\u2112",
+    "Larr;": u"\u219e",
+    "Lcaron;": u"\u013d",
+    "Lcedil;": u"\u013b",
+    "Lcy;": u"\u041b",
+    "LeftAngleBracket;": u"\u27e8",
+    "LeftArrow;": u"\u2190",
+    "LeftArrowBar;": u"\u21e4",
+    "LeftArrowRightArrow;": u"\u21c6",
+    "LeftCeiling;": u"\u2308",
+    "LeftDoubleBracket;": u"\u27e6",
+    "LeftDownTeeVector;": u"\u2961",
+    "LeftDownVector;": u"\u21c3",
+    "LeftDownVectorBar;": u"\u2959",
+    "LeftFloor;": u"\u230a",
+    "LeftRightArrow;": u"\u2194",
+    "LeftRightVector;": u"\u294e",
+    "LeftTee;": u"\u22a3",
+    "LeftTeeArrow;": u"\u21a4",
+    "LeftTeeVector;": u"\u295a",
+    "LeftTriangle;": u"\u22b2",
+    "LeftTriangleBar;": u"\u29cf",
+    "LeftTriangleEqual;": u"\u22b4",
+    "LeftUpDownVector;": u"\u2951",
+    "LeftUpTeeVector;": u"\u2960",
+    "LeftUpVector;": u"\u21bf",
+    "LeftUpVectorBar;": u"\u2958",
+    "LeftVector;": u"\u21bc",
+    "LeftVectorBar;": u"\u2952",
+    "Leftarrow;": u"\u21d0",
+    "Leftrightarrow;": u"\u21d4",
+    "LessEqualGreater;": u"\u22da",
+    "LessFullEqual;": u"\u2266",
+    "LessGreater;": u"\u2276",
+    "LessLess;": u"\u2aa1",
+    "LessSlantEqual;": u"\u2a7d",
+    "LessTilde;": u"\u2272",
+    "Lfr;": u"\U0001d50f",
+    "Ll;": u"\u22d8",
+    "Lleftarrow;": u"\u21da",
+    "Lmidot;": u"\u013f",
+    "LongLeftArrow;": u"\u27f5",
+    "LongLeftRightArrow;": u"\u27f7",
+    "LongRightArrow;": u"\u27f6",
+    "Longleftarrow;": u"\u27f8",
+    "Longleftrightarrow;": u"\u27fa",
+    "Longrightarrow;": u"\u27f9",
+    "Lopf;": u"\U0001d543",
+    "LowerLeftArrow;": u"\u2199",
+    "LowerRightArrow;": u"\u2198",
+    "Lscr;": u"\u2112",
+    "Lsh;": u"\u21b0",
+    "Lstrok;": u"\u0141",
+    "Lt;": u"\u226a",
+    "Map;": u"\u2905",
+    "Mcy;": u"\u041c",
+    "MediumSpace;": u"\u205f",
+    "Mellintrf;": u"\u2133",
+    "Mfr;": u"\U0001d510",
+    "MinusPlus;": u"\u2213",
+    "Mopf;": u"\U0001d544",
+    "Mscr;": u"\u2133",
+    "Mu;": u"\u039c",
+    "NJcy;": u"\u040a",
+    "Nacute;": u"\u0143",
+    "Ncaron;": u"\u0147",
+    "Ncedil;": u"\u0145",
+    "Ncy;": u"\u041d",
+    "NegativeMediumSpace;": u"\u200b",
+    "NegativeThickSpace;": u"\u200b",
+    "NegativeThinSpace;": u"\u200b",
+    "NegativeVeryThinSpace;": u"\u200b",
+    "NestedGreaterGreater;": u"\u226b",
+    "NestedLessLess;": u"\u226a",
+    "NewLine;": u"\n",
+    "Nfr;": u"\U0001d511",
+    "NoBreak;": u"\u2060",
+    "NonBreakingSpace;": u"\xa0",
+    "Nopf;": u"\u2115",
+    "Not;": u"\u2aec",
+    "NotCongruent;": u"\u2262",
+    "NotCupCap;": u"\u226d",
+    "NotDoubleVerticalBar;": u"\u2226",
+    "NotElement;": u"\u2209",
+    "NotEqual;": u"\u2260",
+    "NotEqualTilde;": u"\u2242\u0338",
+    "NotExists;": u"\u2204",
+    "NotGreater;": u"\u226f",
+    "NotGreaterEqual;": u"\u2271",
+    "NotGreaterFullEqual;": u"\u2267\u0338",
+    "NotGreaterGreater;": u"\u226b\u0338",
+    "NotGreaterLess;": u"\u2279",
+    "NotGreaterSlantEqual;": u"\u2a7e\u0338",
+    "NotGreaterTilde;": u"\u2275",
+    "NotHumpDownHump;": u"\u224e\u0338",
+    "NotHumpEqual;": u"\u224f\u0338",
+    "NotLeftTriangle;": u"\u22ea",
+    "NotLeftTriangleBar;": u"\u29cf\u0338",
+    "NotLeftTriangleEqual;": u"\u22ec",
+    "NotLess;": u"\u226e",
+    "NotLessEqual;": u"\u2270",
+    "NotLessGreater;": u"\u2278",
+    "NotLessLess;": u"\u226a\u0338",
+    "NotLessSlantEqual;": u"\u2a7d\u0338",
+    "NotLessTilde;": u"\u2274",
+    "NotNestedGreaterGreater;": u"\u2aa2\u0338",
+    "NotNestedLessLess;": u"\u2aa1\u0338",
+    "NotPrecedes;": u"\u2280",
+    "NotPrecedesEqual;": u"\u2aaf\u0338",
+    "NotPrecedesSlantEqual;": u"\u22e0",
+    "NotReverseElement;": u"\u220c",
+    "NotRightTriangle;": u"\u22eb",
+    "NotRightTriangleBar;": u"\u29d0\u0338",
+    "NotRightTriangleEqual;": u"\u22ed",
+    "NotSquareSubset;": u"\u228f\u0338",
+    "NotSquareSubsetEqual;": u"\u22e2",
+    "NotSquareSuperset;": u"\u2290\u0338",
+    "NotSquareSupersetEqual;": u"\u22e3",
+    "NotSubset;": u"\u2282\u20d2",
+    "NotSubsetEqual;": u"\u2288",
+    "NotSucceeds;": u"\u2281",
+    "NotSucceedsEqual;": u"\u2ab0\u0338",
+    "NotSucceedsSlantEqual;": u"\u22e1",
+    "NotSucceedsTilde;": u"\u227f\u0338",
+    "NotSuperset;": u"\u2283\u20d2",
+    "NotSupersetEqual;": u"\u2289",
+    "NotTilde;": u"\u2241",
+    "NotTildeEqual;": u"\u2244",
+    "NotTildeFullEqual;": u"\u2247",
+    "NotTildeTilde;": u"\u2249",
+    "NotVerticalBar;": u"\u2224",
+    "Nscr;": u"\U0001d4a9",
+    "Ntilde": u"\xd1",
+    "Ntilde;": u"\xd1",
+    "Nu;": u"\u039d",
+    "OElig;": u"\u0152",
+    "Oacute": u"\xd3",
+    "Oacute;": u"\xd3",
+    "Ocirc": u"\xd4",
+    "Ocirc;": u"\xd4",
+    "Ocy;": u"\u041e",
+    "Odblac;": u"\u0150",
+    "Ofr;": u"\U0001d512",
+    "Ograve": u"\xd2",
+    "Ograve;": u"\xd2",
+    "Omacr;": u"\u014c",
+    "Omega;": u"\u03a9",
+    "Omicron;": u"\u039f",
+    "Oopf;": u"\U0001d546",
+    "OpenCurlyDoubleQuote;": u"\u201c",
+    "OpenCurlyQuote;": u"\u2018",
+    "Or;": u"\u2a54",
+    "Oscr;": u"\U0001d4aa",
+    "Oslash": u"\xd8",
+    "Oslash;": u"\xd8",
+    "Otilde": u"\xd5",
+    "Otilde;": u"\xd5",
+    "Otimes;": u"\u2a37",
+    "Ouml": u"\xd6",
+    "Ouml;": u"\xd6",
+    "OverBar;": u"\u203e",
+    "OverBrace;": u"\u23de",
+    "OverBracket;": u"\u23b4",
+    "OverParenthesis;": u"\u23dc",
+    "PartialD;": u"\u2202",
+    "Pcy;": u"\u041f",
+    "Pfr;": u"\U0001d513",
+    "Phi;": u"\u03a6",
+    "Pi;": u"\u03a0",
+    "PlusMinus;": u"\xb1",
+    "Poincareplane;": u"\u210c",
+    "Popf;": u"\u2119",
+    "Pr;": u"\u2abb",
+    "Precedes;": u"\u227a",
+    "PrecedesEqual;": u"\u2aaf",
+    "PrecedesSlantEqual;": u"\u227c",
+    "PrecedesTilde;": u"\u227e",
+    "Prime;": u"\u2033",
+    "Product;": u"\u220f",
+    "Proportion;": u"\u2237",
+    "Proportional;": u"\u221d",
+    "Pscr;": u"\U0001d4ab",
+    "Psi;": u"\u03a8",
+    "QUOT": u"\"",
+    "QUOT;": u"\"",
+    "Qfr;": u"\U0001d514",
+    "Qopf;": u"\u211a",
+    "Qscr;": u"\U0001d4ac",
+    "RBarr;": u"\u2910",
+    "REG": u"\xae",
+    "REG;": u"\xae",
+    "Racute;": u"\u0154",
+    "Rang;": u"\u27eb",
+    "Rarr;": u"\u21a0",
+    "Rarrtl;": u"\u2916",
+    "Rcaron;": u"\u0158",
+    "Rcedil;": u"\u0156",
+    "Rcy;": u"\u0420",
+    "Re;": u"\u211c",
+    "ReverseElement;": u"\u220b",
+    "ReverseEquilibrium;": u"\u21cb",
+    "ReverseUpEquilibrium;": u"\u296f",
+    "Rfr;": u"\u211c",
+    "Rho;": u"\u03a1",
+    "RightAngleBracket;": u"\u27e9",
+    "RightArrow;": u"\u2192",
+    "RightArrowBar;": u"\u21e5",
+    "RightArrowLeftArrow;": u"\u21c4",
+    "RightCeiling;": u"\u2309",
+    "RightDoubleBracket;": u"\u27e7",
+    "RightDownTeeVector;": u"\u295d",
+    "RightDownVector;": u"\u21c2",
+    "RightDownVectorBar;": u"\u2955",
+    "RightFloor;": u"\u230b",
+    "RightTee;": u"\u22a2",
+    "RightTeeArrow;": u"\u21a6",
+    "RightTeeVector;": u"\u295b",
+    "RightTriangle;": u"\u22b3",
+    "RightTriangleBar;": u"\u29d0",
+    "RightTriangleEqual;": u"\u22b5",
+    "RightUpDownVector;": u"\u294f",
+    "RightUpTeeVector;": u"\u295c",
+    "RightUpVector;": u"\u21be",
+    "RightUpVectorBar;": u"\u2954",
+    "RightVector;": u"\u21c0",
+    "RightVectorBar;": u"\u2953",
+    "Rightarrow;": u"\u21d2",
+    "Ropf;": u"\u211d",
+    "RoundImplies;": u"\u2970",
+    "Rrightarrow;": u"\u21db",
+    "Rscr;": u"\u211b",
+    "Rsh;": u"\u21b1",
+    "RuleDelayed;": u"\u29f4",
+    "SHCHcy;": u"\u0429",
+    "SHcy;": u"\u0428",
+    "SOFTcy;": u"\u042c",
+    "Sacute;": u"\u015a",
+    "Sc;": u"\u2abc",
+    "Scaron;": u"\u0160",
+    "Scedil;": u"\u015e",
+    "Scirc;": u"\u015c",
+    "Scy;": u"\u0421",
+    "Sfr;": u"\U0001d516",
+    "ShortDownArrow;": u"\u2193",
+    "ShortLeftArrow;": u"\u2190",
+    "ShortRightArrow;": u"\u2192",
+    "ShortUpArrow;": u"\u2191",
+    "Sigma;": u"\u03a3",
+    "SmallCircle;": u"\u2218",
+    "Sopf;": u"\U0001d54a",
+    "Sqrt;": u"\u221a",
+    "Square;": u"\u25a1",
+    "SquareIntersection;": u"\u2293",
+    "SquareSubset;": u"\u228f",
+    "SquareSubsetEqual;": u"\u2291",
+    "SquareSuperset;": u"\u2290",
+    "SquareSupersetEqual;": u"\u2292",
+    "SquareUnion;": u"\u2294",
+    "Sscr;": u"\U0001d4ae",
+    "Star;": u"\u22c6",
+    "Sub;": u"\u22d0",
+    "Subset;": u"\u22d0",
+    "SubsetEqual;": u"\u2286",
+    "Succeeds;": u"\u227b",
+    "SucceedsEqual;": u"\u2ab0",
+    "SucceedsSlantEqual;": u"\u227d",
+    "SucceedsTilde;": u"\u227f",
+    "SuchThat;": u"\u220b",
+    "Sum;": u"\u2211",
+    "Sup;": u"\u22d1",
+    "Superset;": u"\u2283",
+    "SupersetEqual;": u"\u2287",
+    "Supset;": u"\u22d1",
+    "THORN": u"\xde",
+    "THORN;": u"\xde",
+    "TRADE;": u"\u2122",
+    "TSHcy;": u"\u040b",
+    "TScy;": u"\u0426",
+    "Tab;": u"\t",
+    "Tau;": u"\u03a4",
+    "Tcaron;": u"\u0164",
+    "Tcedil;": u"\u0162",
+    "Tcy;": u"\u0422",
+    "Tfr;": u"\U0001d517",
+    "Therefore;": u"\u2234",
+    "Theta;": u"\u0398",
+    "ThickSpace;": u"\u205f\u200a",
+    "ThinSpace;": u"\u2009",
+    "Tilde;": u"\u223c",
+    "TildeEqual;": u"\u2243",
+    "TildeFullEqual;": u"\u2245",
+    "TildeTilde;": u"\u2248",
+    "Topf;": u"\U0001d54b",
+    "TripleDot;": u"\u20db",
+    "Tscr;": u"\U0001d4af",
+    "Tstrok;": u"\u0166",
+    "Uacute": u"\xda",
+    "Uacute;": u"\xda",
+    "Uarr;": u"\u219f",
+    "Uarrocir;": u"\u2949",
+    "Ubrcy;": u"\u040e",
+    "Ubreve;": u"\u016c",
+    "Ucirc": u"\xdb",
+    "Ucirc;": u"\xdb",
+    "Ucy;": u"\u0423",
+    "Udblac;": u"\u0170",
+    "Ufr;": u"\U0001d518",
+    "Ugrave": u"\xd9",
+    "Ugrave;": u"\xd9",
+    "Umacr;": u"\u016a",
+    "UnderBar;": u"_",
+    "UnderBrace;": u"\u23df",
+    "UnderBracket;": u"\u23b5",
+    "UnderParenthesis;": u"\u23dd",
+    "Union;": u"\u22c3",
+    "UnionPlus;": u"\u228e",
+    "Uogon;": u"\u0172",
+    "Uopf;": u"\U0001d54c",
+    "UpArrow;": u"\u2191",
+    "UpArrowBar;": u"\u2912",
+    "UpArrowDownArrow;": u"\u21c5",
+    "UpDownArrow;": u"\u2195",
+    "UpEquilibrium;": u"\u296e",
+    "UpTee;": u"\u22a5",
+    "UpTeeArrow;": u"\u21a5",
+    "Uparrow;": u"\u21d1",
+    "Updownarrow;": u"\u21d5",
+    "UpperLeftArrow;": u"\u2196",
+    "UpperRightArrow;": u"\u2197",
+    "Upsi;": u"\u03d2",
+    "Upsilon;": u"\u03a5",
+    "Uring;": u"\u016e",
+    "Uscr;": u"\U0001d4b0",
+    "Utilde;": u"\u0168",
+    "Uuml": u"\xdc",
+    "Uuml;": u"\xdc",
+    "VDash;": u"\u22ab",
+    "Vbar;": u"\u2aeb",
+    "Vcy;": u"\u0412",
+    "Vdash;": u"\u22a9",
+    "Vdashl;": u"\u2ae6",
+    "Vee;": u"\u22c1",
+    "Verbar;": u"\u2016",
+    "Vert;": u"\u2016",
+    "VerticalBar;": u"\u2223",
+    "VerticalLine;": u"|",
+    "VerticalSeparator;": u"\u2758",
+    "VerticalTilde;": u"\u2240",
+    "VeryThinSpace;": u"\u200a",
+    "Vfr;": u"\U0001d519",
+    "Vopf;": u"\U0001d54d",
+    "Vscr;": u"\U0001d4b1",
+    "Vvdash;": u"\u22aa",
+    "Wcirc;": u"\u0174",
+    "Wedge;": u"\u22c0",
+    "Wfr;": u"\U0001d51a",
+    "Wopf;": u"\U0001d54e",
+    "Wscr;": u"\U0001d4b2",
+    "Xfr;": u"\U0001d51b",
+    "Xi;": u"\u039e",
+    "Xopf;": u"\U0001d54f",
+    "Xscr;": u"\U0001d4b3",
+    "YAcy;": u"\u042f",
+    "YIcy;": u"\u0407",
+    "YUcy;": u"\u042e",
+    "Yacute": u"\xdd",
+    "Yacute;": u"\xdd",
+    "Ycirc;": u"\u0176",
+    "Ycy;": u"\u042b",
+    "Yfr;": u"\U0001d51c",
+    "Yopf;": u"\U0001d550",
+    "Yscr;": u"\U0001d4b4",
+    "Yuml;": u"\u0178",
+    "ZHcy;": u"\u0416",
+    "Zacute;": u"\u0179",
+    "Zcaron;": u"\u017d",
+    "Zcy;": u"\u0417",
+    "Zdot;": u"\u017b",
+    "ZeroWidthSpace;": u"\u200b",
+    "Zeta;": u"\u0396",
+    "Zfr;": u"\u2128",
+    "Zopf;": u"\u2124",
+    "Zscr;": u"\U0001d4b5",
+    "aacute": u"\xe1",
+    "aacute;": u"\xe1",
+    "abreve;": u"\u0103",
+    "ac;": u"\u223e",
+    "acE;": u"\u223e\u0333",
+    "acd;": u"\u223f",
+    "acirc": u"\xe2",
+    "acirc;": u"\xe2",
+    "acute": u"\xb4",
+    "acute;": u"\xb4",
+    "acy;": u"\u0430",
+    "aelig": u"\xe6",
+    "aelig;": u"\xe6",
+    "af;": u"\u2061",
+    "afr;": u"\U0001d51e",
+    "agrave": u"\xe0",
+    "agrave;": u"\xe0",
+    "alefsym;": u"\u2135",
+    "aleph;": u"\u2135",
+    "alpha;": u"\u03b1",
+    "amacr;": u"\u0101",
+    "amalg;": u"\u2a3f",
+    "amp": u"&",
+    "amp;": u"&",
+    "and;": u"\u2227",
+    "andand;": u"\u2a55",
+    "andd;": u"\u2a5c",
+    "andslope;": u"\u2a58",
+    "andv;": u"\u2a5a",
+    "ang;": u"\u2220",
+    "ange;": u"\u29a4",
+    "angle;": u"\u2220",
+    "angmsd;": u"\u2221",
+    "angmsdaa;": u"\u29a8",
+    "angmsdab;": u"\u29a9",
+    "angmsdac;": u"\u29aa",
+    "angmsdad;": u"\u29ab",
+    "angmsdae;": u"\u29ac",
+    "angmsdaf;": u"\u29ad",
+    "angmsdag;": u"\u29ae",
+    "angmsdah;": u"\u29af",
+    "angrt;": u"\u221f",
+    "angrtvb;": u"\u22be",
+    "angrtvbd;": u"\u299d",
+    "angsph;": u"\u2222",
+    "angst;": u"\xc5",
+    "angzarr;": u"\u237c",
+    "aogon;": u"\u0105",
+    "aopf;": u"\U0001d552",
+    "ap;": u"\u2248",
+    "apE;": u"\u2a70",
+    "apacir;": u"\u2a6f",
+    "ape;": u"\u224a",
+    "apid;": u"\u224b",
+    "apos;": u"'",
+    "approx;": u"\u2248",
+    "approxeq;": u"\u224a",
+    "aring": u"\xe5",
+    "aring;": u"\xe5",
+    "ascr;": u"\U0001d4b6",
+    "ast;": u"*",
+    "asymp;": u"\u2248",
+    "asympeq;": u"\u224d",
+    "atilde": u"\xe3",
+    "atilde;": u"\xe3",
+    "auml": u"\xe4",
+    "auml;": u"\xe4",
+    "awconint;": u"\u2233",
+    "awint;": u"\u2a11",
+    "bNot;": u"\u2aed",
+    "backcong;": u"\u224c",
+    "backepsilon;": u"\u03f6",
+    "backprime;": u"\u2035",
+    "backsim;": u"\u223d",
+    "backsimeq;": u"\u22cd",
+    "barvee;": u"\u22bd",
+    "barwed;": u"\u2305",
+    "barwedge;": u"\u2305",
+    "bbrk;": u"\u23b5",
+    "bbrktbrk;": u"\u23b6",
+    "bcong;": u"\u224c",
+    "bcy;": u"\u0431",
+    "bdquo;": u"\u201e",
+    "becaus;": u"\u2235",
+    "because;": u"\u2235",
+    "bemptyv;": u"\u29b0",
+    "bepsi;": u"\u03f6",
+    "bernou;": u"\u212c",
+    "beta;": u"\u03b2",
+    "beth;": u"\u2136",
+    "between;": u"\u226c",
+    "bfr;": u"\U0001d51f",
+    "bigcap;": u"\u22c2",
+    "bigcirc;": u"\u25ef",
+    "bigcup;": u"\u22c3",
+    "bigodot;": u"\u2a00",
+    "bigoplus;": u"\u2a01",
+    "bigotimes;": u"\u2a02",
+    "bigsqcup;": u"\u2a06",
+    "bigstar;": u"\u2605",
+    "bigtriangledown;": u"\u25bd",
+    "bigtriangleup;": u"\u25b3",
+    "biguplus;": u"\u2a04",
+    "bigvee;": u"\u22c1",
+    "bigwedge;": u"\u22c0",
+    "bkarow;": u"\u290d",
+    "blacklozenge;": u"\u29eb",
+    "blacksquare;": u"\u25aa",
+    "blacktriangle;": u"\u25b4",
+    "blacktriangledown;": u"\u25be",
+    "blacktriangleleft;": u"\u25c2",
+    "blacktriangleright;": u"\u25b8",
+    "blank;": u"\u2423",
+    "blk12;": u"\u2592",
+    "blk14;": u"\u2591",
+    "blk34;": u"\u2593",
+    "block;": u"\u2588",
+    "bne;": u"=\u20e5",
+    "bnequiv;": u"\u2261\u20e5",
+    "bnot;": u"\u2310",
+    "bopf;": u"\U0001d553",
+    "bot;": u"\u22a5",
+    "bottom;": u"\u22a5",
+    "bowtie;": u"\u22c8",
+    "boxDL;": u"\u2557",
+    "boxDR;": u"\u2554",
+    "boxDl;": u"\u2556",
+    "boxDr;": u"\u2553",
+    "boxH;": u"\u2550",
+    "boxHD;": u"\u2566",
+    "boxHU;": u"\u2569",
+    "boxHd;": u"\u2564",
+    "boxHu;": u"\u2567",
+    "boxUL;": u"\u255d",
+    "boxUR;": u"\u255a",
+    "boxUl;": u"\u255c",
+    "boxUr;": u"\u2559",
+    "boxV;": u"\u2551",
+    "boxVH;": u"\u256c",
+    "boxVL;": u"\u2563",
+    "boxVR;": u"\u2560",
+    "boxVh;": u"\u256b",
+    "boxVl;": u"\u2562",
+    "boxVr;": u"\u255f",
+    "boxbox;": u"\u29c9",
+    "boxdL;": u"\u2555",
+    "boxdR;": u"\u2552",
+    "boxdl;": u"\u2510",
+    "boxdr;": u"\u250c",
+    "boxh;": u"\u2500",
+    "boxhD;": u"\u2565",
+    "boxhU;": u"\u2568",
+    "boxhd;": u"\u252c",
+    "boxhu;": u"\u2534",
+    "boxminus;": u"\u229f",
+    "boxplus;": u"\u229e",
+    "boxtimes;": u"\u22a0",
+    "boxuL;": u"\u255b",
+    "boxuR;": u"\u2558",
+    "boxul;": u"\u2518",
+    "boxur;": u"\u2514",
+    "boxv;": u"\u2502",
+    "boxvH;": u"\u256a",
+    "boxvL;": u"\u2561",
+    "boxvR;": u"\u255e",
+    "boxvh;": u"\u253c",
+    "boxvl;": u"\u2524",
+    "boxvr;": u"\u251c",
+    "bprime;": u"\u2035",
+    "breve;": u"\u02d8",
+    "brvbar": u"\xa6",
+    "brvbar;": u"\xa6",
+    "bscr;": u"\U0001d4b7",
+    "bsemi;": u"\u204f",
+    "bsim;": u"\u223d",
+    "bsime;": u"\u22cd",
+    "bsol;": u"\\",
+    "bsolb;": u"\u29c5",
+    "bsolhsub;": u"\u27c8",
+    "bull;": u"\u2022",
+    "bullet;": u"\u2022",
+    "bump;": u"\u224e",
+    "bumpE;": u"\u2aae",
+    "bumpe;": u"\u224f",
+    "bumpeq;": u"\u224f",
+    "cacute;": u"\u0107",
+    "cap;": u"\u2229",
+    "capand;": u"\u2a44",
+    "capbrcup;": u"\u2a49",
+    "capcap;": u"\u2a4b",
+    "capcup;": u"\u2a47",
+    "capdot;": u"\u2a40",
+    "caps;": u"\u2229\ufe00",
+    "caret;": u"\u2041",
+    "caron;": u"\u02c7",
+    "ccaps;": u"\u2a4d",
+    "ccaron;": u"\u010d",
+    "ccedil": u"\xe7",
+    "ccedil;": u"\xe7",
+    "ccirc;": u"\u0109",
+    "ccups;": u"\u2a4c",
+    "ccupssm;": u"\u2a50",
+    "cdot;": u"\u010b",
+    "cedil": u"\xb8",
+    "cedil;": u"\xb8",
+    "cemptyv;": u"\u29b2",
+    "cent": u"\xa2",
+    "cent;": u"\xa2",
+    "centerdot;": u"\xb7",
+    "cfr;": u"\U0001d520",
+    "chcy;": u"\u0447",
+    "check;": u"\u2713",
+    "checkmark;": u"\u2713",
+    "chi;": u"\u03c7",
+    "cir;": u"\u25cb",
+    "cirE;": u"\u29c3",
+    "circ;": u"\u02c6",
+    "circeq;": u"\u2257",
+    "circlearrowleft;": u"\u21ba",
+    "circlearrowright;": u"\u21bb",
+    "circledR;": u"\xae",
+    "circledS;": u"\u24c8",
+    "circledast;": u"\u229b",
+    "circledcirc;": u"\u229a",
+    "circleddash;": u"\u229d",
+    "cire;": u"\u2257",
+    "cirfnint;": u"\u2a10",
+    "cirmid;": u"\u2aef",
+    "cirscir;": u"\u29c2",
+    "clubs;": u"\u2663",
+    "clubsuit;": u"\u2663",
+    "colon;": u":",
+    "colone;": u"\u2254",
+    "coloneq;": u"\u2254",
+    "comma;": u",",
+    "commat;": u"@",
+    "comp;": u"\u2201",
+    "compfn;": u"\u2218",
+    "complement;": u"\u2201",
+    "complexes;": u"\u2102",
+    "cong;": u"\u2245",
+    "congdot;": u"\u2a6d",
+    "conint;": u"\u222e",
+    "copf;": u"\U0001d554",
+    "coprod;": u"\u2210",
+    "copy": u"\xa9",
+    "copy;": u"\xa9",
+    "copysr;": u"\u2117",
+    "crarr;": u"\u21b5",
+    "cross;": u"\u2717",
+    "cscr;": u"\U0001d4b8",
+    "csub;": u"\u2acf",
+    "csube;": u"\u2ad1",
+    "csup;": u"\u2ad0",
+    "csupe;": u"\u2ad2",
+    "ctdot;": u"\u22ef",
+    "cudarrl;": u"\u2938",
+    "cudarrr;": u"\u2935",
+    "cuepr;": u"\u22de",
+    "cuesc;": u"\u22df",
+    "cularr;": u"\u21b6",
+    "cularrp;": u"\u293d",
+    "cup;": u"\u222a",
+    "cupbrcap;": u"\u2a48",
+    "cupcap;": u"\u2a46",
+    "cupcup;": u"\u2a4a",
+    "cupdot;": u"\u228d",
+    "cupor;": u"\u2a45",
+    "cups;": u"\u222a\ufe00",
+    "curarr;": u"\u21b7",
+    "curarrm;": u"\u293c",
+    "curlyeqprec;": u"\u22de",
+    "curlyeqsucc;": u"\u22df",
+    "curlyvee;": u"\u22ce",
+    "curlywedge;": u"\u22cf",
+    "curren": u"\xa4",
+    "curren;": u"\xa4",
+    "curvearrowleft;": u"\u21b6",
+    "curvearrowright;": u"\u21b7",
+    "cuvee;": u"\u22ce",
+    "cuwed;": u"\u22cf",
+    "cwconint;": u"\u2232",
+    "cwint;": u"\u2231",
+    "cylcty;": u"\u232d",
+    "dArr;": u"\u21d3",
+    "dHar;": u"\u2965",
+    "dagger;": u"\u2020",
+    "daleth;": u"\u2138",
+    "darr;": u"\u2193",
+    "dash;": u"\u2010",
+    "dashv;": u"\u22a3",
+    "dbkarow;": u"\u290f",
+    "dblac;": u"\u02dd",
+    "dcaron;": u"\u010f",
+    "dcy;": u"\u0434",
+    "dd;": u"\u2146",
+    "ddagger;": u"\u2021",
+    "ddarr;": u"\u21ca",
+    "ddotseq;": u"\u2a77",
+    "deg": u"\xb0",
+    "deg;": u"\xb0",
+    "delta;": u"\u03b4",
+    "demptyv;": u"\u29b1",
+    "dfisht;": u"\u297f",
+    "dfr;": u"\U0001d521",
+    "dharl;": u"\u21c3",
+    "dharr;": u"\u21c2",
+    "diam;": u"\u22c4",
+    "diamond;": u"\u22c4",
+    "diamondsuit;": u"\u2666",
+    "diams;": u"\u2666",
+    "die;": u"\xa8",
+    "digamma;": u"\u03dd",
+    "disin;": u"\u22f2",
+    "div;": u"\xf7",
+    "divide": u"\xf7",
+    "divide;": u"\xf7",
+    "divideontimes;": u"\u22c7",
+    "divonx;": u"\u22c7",
+    "djcy;": u"\u0452",
+    "dlcorn;": u"\u231e",
+    "dlcrop;": u"\u230d",
+    "dollar;": u"$",
+    "dopf;": u"\U0001d555",
+    "dot;": u"\u02d9",
+    "doteq;": u"\u2250",
+    "doteqdot;": u"\u2251",
+    "dotminus;": u"\u2238",
+    "dotplus;": u"\u2214",
+    "dotsquare;": u"\u22a1",
+    "doublebarwedge;": u"\u2306",
+    "downarrow;": u"\u2193",
+    "downdownarrows;": u"\u21ca",
+    "downharpoonleft;": u"\u21c3",
+    "downharpoonright;": u"\u21c2",
+    "drbkarow;": u"\u2910",
+    "drcorn;": u"\u231f",
+    "drcrop;": u"\u230c",
+    "dscr;": u"\U0001d4b9",
+    "dscy;": u"\u0455",
+    "dsol;": u"\u29f6",
+    "dstrok;": u"\u0111",
+    "dtdot;": u"\u22f1",
+    "dtri;": u"\u25bf",
+    "dtrif;": u"\u25be",
+    "duarr;": u"\u21f5",
+    "duhar;": u"\u296f",
+    "dwangle;": u"\u29a6",
+    "dzcy;": u"\u045f",
+    "dzigrarr;": u"\u27ff",
+    "eDDot;": u"\u2a77",
+    "eDot;": u"\u2251",
+    "eacute": u"\xe9",
+    "eacute;": u"\xe9",
+    "easter;": u"\u2a6e",
+    "ecaron;": u"\u011b",
+    "ecir;": u"\u2256",
+    "ecirc": u"\xea",
+    "ecirc;": u"\xea",
+    "ecolon;": u"\u2255",
+    "ecy;": u"\u044d",
+    "edot;": u"\u0117",
+    "ee;": u"\u2147",
+    "efDot;": u"\u2252",
+    "efr;": u"\U0001d522",
+    "eg;": u"\u2a9a",
+    "egrave": u"\xe8",
+    "egrave;": u"\xe8",
+    "egs;": u"\u2a96",
+    "egsdot;": u"\u2a98",
+    "el;": u"\u2a99",
+    "elinters;": u"\u23e7",
+    "ell;": u"\u2113",
+    "els;": u"\u2a95",
+    "elsdot;": u"\u2a97",
+    "emacr;": u"\u0113",
+    "empty;": u"\u2205",
+    "emptyset;": u"\u2205",
+    "emptyv;": u"\u2205",
+    "emsp13;": u"\u2004",
+    "emsp14;": u"\u2005",
+    "emsp;": u"\u2003",
+    "eng;": u"\u014b",
+    "ensp;": u"\u2002",
+    "eogon;": u"\u0119",
+    "eopf;": u"\U0001d556",
+    "epar;": u"\u22d5",
+    "eparsl;": u"\u29e3",
+    "eplus;": u"\u2a71",
+    "epsi;": u"\u03b5",
+    "epsilon;": u"\u03b5",
+    "epsiv;": u"\u03f5",
+    "eqcirc;": u"\u2256",
+    "eqcolon;": u"\u2255",
+    "eqsim;": u"\u2242",
+    "eqslantgtr;": u"\u2a96",
+    "eqslantless;": u"\u2a95",
+    "equals;": u"=",
+    "equest;": u"\u225f",
+    "equiv;": u"\u2261",
+    "equivDD;": u"\u2a78",
+    "eqvparsl;": u"\u29e5",
+    "erDot;": u"\u2253",
+    "erarr;": u"\u2971",
+    "escr;": u"\u212f",
+    "esdot;": u"\u2250",
+    "esim;": u"\u2242",
+    "eta;": u"\u03b7",
+    "eth": u"\xf0",
+    "eth;": u"\xf0",
+    "euml": u"\xeb",
+    "euml;": u"\xeb",
+    "euro;": u"\u20ac",
+    "excl;": u"!",
+    "exist;": u"\u2203",
+    "expectation;": u"\u2130",
+    "exponentiale;": u"\u2147",
+    "fallingdotseq;": u"\u2252",
+    "fcy;": u"\u0444",
+    "female;": u"\u2640",
+    "ffilig;": u"\ufb03",
+    "fflig;": u"\ufb00",
+    "ffllig;": u"\ufb04",
+    "ffr;": u"\U0001d523",
+    "filig;": u"\ufb01",
+    "fjlig;": u"fj",
+    "flat;": u"\u266d",
+    "fllig;": u"\ufb02",
+    "fltns;": u"\u25b1",
+    "fnof;": u"\u0192",
+    "fopf;": u"\U0001d557",
+    "forall;": u"\u2200",
+    "fork;": u"\u22d4",
+    "forkv;": u"\u2ad9",
+    "fpartint;": u"\u2a0d",
+    "frac12": u"\xbd",
+    "frac12;": u"\xbd",
+    "frac13;": u"\u2153",
+    "frac14": u"\xbc",
+    "frac14;": u"\xbc",
+    "frac15;": u"\u2155",
+    "frac16;": u"\u2159",
+    "frac18;": u"\u215b",
+    "frac23;": u"\u2154",
+    "frac25;": u"\u2156",
+    "frac34": u"\xbe",
+    "frac34;": u"\xbe",
+    "frac35;": u"\u2157",
+    "frac38;": u"\u215c",
+    "frac45;": u"\u2158",
+    "frac56;": u"\u215a",
+    "frac58;": u"\u215d",
+    "frac78;": u"\u215e",
+    "frasl;": u"\u2044",
+    "frown;": u"\u2322",
+    "fscr;": u"\U0001d4bb",
+    "gE;": u"\u2267",
+    "gEl;": u"\u2a8c",
+    "gacute;": u"\u01f5",
+    "gamma;": u"\u03b3",
+    "gammad;": u"\u03dd",
+    "gap;": u"\u2a86",
+    "gbreve;": u"\u011f",
+    "gcirc;": u"\u011d",
+    "gcy;": u"\u0433",
+    "gdot;": u"\u0121",
+    "ge;": u"\u2265",
+    "gel;": u"\u22db",
+    "geq;": u"\u2265",
+    "geqq;": u"\u2267",
+    "geqslant;": u"\u2a7e",
+    "ges;": u"\u2a7e",
+    "gescc;": u"\u2aa9",
+    "gesdot;": u"\u2a80",
+    "gesdoto;": u"\u2a82",
+    "gesdotol;": u"\u2a84",
+    "gesl;": u"\u22db\ufe00",
+    "gesles;": u"\u2a94",
+    "gfr;": u"\U0001d524",
+    "gg;": u"\u226b",
+    "ggg;": u"\u22d9",
+    "gimel;": u"\u2137",
+    "gjcy;": u"\u0453",
+    "gl;": u"\u2277",
+    "glE;": u"\u2a92",
+    "gla;": u"\u2aa5",
+    "glj;": u"\u2aa4",
+    "gnE;": u"\u2269",
+    "gnap;": u"\u2a8a",
+    "gnapprox;": u"\u2a8a",
+    "gne;": u"\u2a88",
+    "gneq;": u"\u2a88",
+    "gneqq;": u"\u2269",
+    "gnsim;": u"\u22e7",
+    "gopf;": u"\U0001d558",
+    "grave;": u"`",
+    "gscr;": u"\u210a",
+    "gsim;": u"\u2273",
+    "gsime;": u"\u2a8e",
+    "gsiml;": u"\u2a90",
+    "gt": u">",
+    "gt;": u">",
+    "gtcc;": u"\u2aa7",
+    "gtcir;": u"\u2a7a",
+    "gtdot;": u"\u22d7",
+    "gtlPar;": u"\u2995",
+    "gtquest;": u"\u2a7c",
+    "gtrapprox;": u"\u2a86",
+    "gtrarr;": u"\u2978",
+    "gtrdot;": u"\u22d7",
+    "gtreqless;": u"\u22db",
+    "gtreqqless;": u"\u2a8c",
+    "gtrless;": u"\u2277",
+    "gtrsim;": u"\u2273",
+    "gvertneqq;": u"\u2269\ufe00",
+    "gvnE;": u"\u2269\ufe00",
+    "hArr;": u"\u21d4",
+    "hairsp;": u"\u200a",
+    "half;": u"\xbd",
+    "hamilt;": u"\u210b",
+    "hardcy;": u"\u044a",
+    "harr;": u"\u2194",
+    "harrcir;": u"\u2948",
+    "harrw;": u"\u21ad",
+    "hbar;": u"\u210f",
+    "hcirc;": u"\u0125",
+    "hearts;": u"\u2665",
+    "heartsuit;": u"\u2665",
+    "hellip;": u"\u2026",
+    "hercon;": u"\u22b9",
+    "hfr;": u"\U0001d525",
+    "hksearow;": u"\u2925",
+    "hkswarow;": u"\u2926",
+    "hoarr;": u"\u21ff",
+    "homtht;": u"\u223b",
+    "hookleftarrow;": u"\u21a9",
+    "hookrightarrow;": u"\u21aa",
+    "hopf;": u"\U0001d559",
+    "horbar;": u"\u2015",
+    "hscr;": u"\U0001d4bd",
+    "hslash;": u"\u210f",
+    "hstrok;": u"\u0127",
+    "hybull;": u"\u2043",
+    "hyphen;": u"\u2010",
+    "iacute": u"\xed",
+    "iacute;": u"\xed",
+    "ic;": u"\u2063",
+    "icirc": u"\xee",
+    "icirc;": u"\xee",
+    "icy;": u"\u0438",
+    "iecy;": u"\u0435",
+    "iexcl": u"\xa1",
+    "iexcl;": u"\xa1",
+    "iff;": u"\u21d4",
+    "ifr;": u"\U0001d526",
+    "igrave": u"\xec",
+    "igrave;": u"\xec",
+    "ii;": u"\u2148",
+    "iiiint;": u"\u2a0c",
+    "iiint;": u"\u222d",
+    "iinfin;": u"\u29dc",
+    "iiota;": u"\u2129",
+    "ijlig;": u"\u0133",
+    "imacr;": u"\u012b",
+    "image;": u"\u2111",
+    "imagline;": u"\u2110",
+    "imagpart;": u"\u2111",
+    "imath;": u"\u0131",
+    "imof;": u"\u22b7",
+    "imped;": u"\u01b5",
+    "in;": u"\u2208",
+    "incare;": u"\u2105",
+    "infin;": u"\u221e",
+    "infintie;": u"\u29dd",
+    "inodot;": u"\u0131",
+    "int;": u"\u222b",
+    "intcal;": u"\u22ba",
+    "integers;": u"\u2124",
+    "intercal;": u"\u22ba",
+    "intlarhk;": u"\u2a17",
+    "intprod;": u"\u2a3c",
+    "iocy;": u"\u0451",
+    "iogon;": u"\u012f",
+    "iopf;": u"\U0001d55a",
+    "iota;": u"\u03b9",
+    "iprod;": u"\u2a3c",
+    "iquest": u"\xbf",
+    "iquest;": u"\xbf",
+    "iscr;": u"\U0001d4be",
+    "isin;": u"\u2208",
+    "isinE;": u"\u22f9",
+    "isindot;": u"\u22f5",
+    "isins;": u"\u22f4",
+    "isinsv;": u"\u22f3",
+    "isinv;": u"\u2208",
+    "it;": u"\u2062",
+    "itilde;": u"\u0129",
+    "iukcy;": u"\u0456",
+    "iuml": u"\xef",
+    "iuml;": u"\xef",
+    "jcirc;": u"\u0135",
+    "jcy;": u"\u0439",
+    "jfr;": u"\U0001d527",
+    "jmath;": u"\u0237",
+    "jopf;": u"\U0001d55b",
+    "jscr;": u"\U0001d4bf",
+    "jsercy;": u"\u0458",
+    "jukcy;": u"\u0454",
+    "kappa;": u"\u03ba",
+    "kappav;": u"\u03f0",
+    "kcedil;": u"\u0137",
+    "kcy;": u"\u043a",
+    "kfr;": u"\U0001d528",
+    "kgreen;": u"\u0138",
+    "khcy;": u"\u0445",
+    "kjcy;": u"\u045c",
+    "kopf;": u"\U0001d55c",
+    "kscr;": u"\U0001d4c0",
+    "lAarr;": u"\u21da",
+    "lArr;": u"\u21d0",
+    "lAtail;": u"\u291b",
+    "lBarr;": u"\u290e",
+    "lE;": u"\u2266",
+    "lEg;": u"\u2a8b",
+    "lHar;": u"\u2962",
+    "lacute;": u"\u013a",
+    "laemptyv;": u"\u29b4",
+    "lagran;": u"\u2112",
+    "lambda;": u"\u03bb",
+    "lang;": u"\u27e8",
+    "langd;": u"\u2991",
+    "langle;": u"\u27e8",
+    "lap;": u"\u2a85",
+    "laquo": u"\xab",
+    "laquo;": u"\xab",
+    "larr;": u"\u2190",
+    "larrb;": u"\u21e4",
+    "larrbfs;": u"\u291f",
+    "larrfs;": u"\u291d",
+    "larrhk;": u"\u21a9",
+    "larrlp;": u"\u21ab",
+    "larrpl;": u"\u2939",
+    "larrsim;": u"\u2973",
+    "larrtl;": u"\u21a2",
+    "lat;": u"\u2aab",
+    "latail;": u"\u2919",
+    "late;": u"\u2aad",
+    "lates;": u"\u2aad\ufe00",
+    "lbarr;": u"\u290c",
+    "lbbrk;": u"\u2772",
+    "lbrace;": u"{",
+    "lbrack;": u"[",
+    "lbrke;": u"\u298b",
+    "lbrksld;": u"\u298f",
+    "lbrkslu;": u"\u298d",
+    "lcaron;": u"\u013e",
+    "lcedil;": u"\u013c",
+    "lceil;": u"\u2308",
+    "lcub;": u"{",
+    "lcy;": u"\u043b",
+    "ldca;": u"\u2936",
+    "ldquo;": u"\u201c",
+    "ldquor;": u"\u201e",
+    "ldrdhar;": u"\u2967",
+    "ldrushar;": u"\u294b",
+    "ldsh;": u"\u21b2",
+    "le;": u"\u2264",
+    "leftarrow;": u"\u2190",
+    "leftarrowtail;": u"\u21a2",
+    "leftharpoondown;": u"\u21bd",
+    "leftharpoonup;": u"\u21bc",
+    "leftleftarrows;": u"\u21c7",
+    "leftrightarrow;": u"\u2194",
+    "leftrightarrows;": u"\u21c6",
+    "leftrightharpoons;": u"\u21cb",
+    "leftrightsquigarrow;": u"\u21ad",
+    "leftthreetimes;": u"\u22cb",
+    "leg;": u"\u22da",
+    "leq;": u"\u2264",
+    "leqq;": u"\u2266",
+    "leqslant;": u"\u2a7d",
+    "les;": u"\u2a7d",
+    "lescc;": u"\u2aa8",
+    "lesdot;": u"\u2a7f",
+    "lesdoto;": u"\u2a81",
+    "lesdotor;": u"\u2a83",
+    "lesg;": u"\u22da\ufe00",
+    "lesges;": u"\u2a93",
+    "lessapprox;": u"\u2a85",
+    "lessdot;": u"\u22d6",
+    "lesseqgtr;": u"\u22da",
+    "lesseqqgtr;": u"\u2a8b",
+    "lessgtr;": u"\u2276",
+    "lesssim;": u"\u2272",
+    "lfisht;": u"\u297c",
+    "lfloor;": u"\u230a",
+    "lfr;": u"\U0001d529",
+    "lg;": u"\u2276",
+    "lgE;": u"\u2a91",
+    "lhard;": u"\u21bd",
+    "lharu;": u"\u21bc",
+    "lharul;": u"\u296a",
+    "lhblk;": u"\u2584",
+    "ljcy;": u"\u0459",
+    "ll;": u"\u226a",
+    "llarr;": u"\u21c7",
+    "llcorner;": u"\u231e",
+    "llhard;": u"\u296b",
+    "lltri;": u"\u25fa",
+    "lmidot;": u"\u0140",
+    "lmoust;": u"\u23b0",
+    "lmoustache;": u"\u23b0",
+    "lnE;": u"\u2268",
+    "lnap;": u"\u2a89",
+    "lnapprox;": u"\u2a89",
+    "lne;": u"\u2a87",
+    "lneq;": u"\u2a87",
+    "lneqq;": u"\u2268",
+    "lnsim;": u"\u22e6",
+    "loang;": u"\u27ec",
+    "loarr;": u"\u21fd",
+    "lobrk;": u"\u27e6",
+    "longleftarrow;": u"\u27f5",
+    "longleftrightarrow;": u"\u27f7",
+    "longmapsto;": u"\u27fc",
+    "longrightarrow;": u"\u27f6",
+    "looparrowleft;": u"\u21ab",
+    "looparrowright;": u"\u21ac",
+    "lopar;": u"\u2985",
+    "lopf;": u"\U0001d55d",
+    "loplus;": u"\u2a2d",
+    "lotimes;": u"\u2a34",
+    "lowast;": u"\u2217",
+    "lowbar;": u"_",
+    "loz;": u"\u25ca",
+    "lozenge;": u"\u25ca",
+    "lozf;": u"\u29eb",
+    "lpar;": u"(",
+    "lparlt;": u"\u2993",
+    "lrarr;": u"\u21c6",
+    "lrcorner;": u"\u231f",
+    "lrhar;": u"\u21cb",
+    "lrhard;": u"\u296d",
+    "lrm;": u"\u200e",
+    "lrtri;": u"\u22bf",
+    "lsaquo;": u"\u2039",
+    "lscr;": u"\U0001d4c1",
+    "lsh;": u"\u21b0",
+    "lsim;": u"\u2272",
+    "lsime;": u"\u2a8d",
+    "lsimg;": u"\u2a8f",
+    "lsqb;": u"[",
+    "lsquo;": u"\u2018",
+    "lsquor;": u"\u201a",
+    "lstrok;": u"\u0142",
+    "lt": u"<",
+    "lt;": u"<",
+    "ltcc;": u"\u2aa6",
+    "ltcir;": u"\u2a79",
+    "ltdot;": u"\u22d6",
+    "lthree;": u"\u22cb",
+    "ltimes;": u"\u22c9",
+    "ltlarr;": u"\u2976",
+    "ltquest;": u"\u2a7b",
+    "ltrPar;": u"\u2996",
+    "ltri;": u"\u25c3",
+    "ltrie;": u"\u22b4",
+    "ltrif;": u"\u25c2",
+    "lurdshar;": u"\u294a",
+    "luruhar;": u"\u2966",
+    "lvertneqq;": u"\u2268\ufe00",
+    "lvnE;": u"\u2268\ufe00",
+    "mDDot;": u"\u223a",
+    "macr": u"\xaf",
+    "macr;": u"\xaf",
+    "male;": u"\u2642",
+    "malt;": u"\u2720",
+    "maltese;": u"\u2720",
+    "map;": u"\u21a6",
+    "mapsto;": u"\u21a6",
+    "mapstodown;": u"\u21a7",
+    "mapstoleft;": u"\u21a4",
+    "mapstoup;": u"\u21a5",
+    "marker;": u"\u25ae",
+    "mcomma;": u"\u2a29",
+    "mcy;": u"\u043c",
+    "mdash;": u"\u2014",
+    "measuredangle;": u"\u2221",
+    "mfr;": u"\U0001d52a",
+    "mho;": u"\u2127",
+    "micro": u"\xb5",
+    "micro;": u"\xb5",
+    "mid;": u"\u2223",
+    "midast;": u"*",
+    "midcir;": u"\u2af0",
+    "middot": u"\xb7",
+    "middot;": u"\xb7",
+    "minus;": u"\u2212",
+    "minusb;": u"\u229f",
+    "minusd;": u"\u2238",
+    "minusdu;": u"\u2a2a",
+    "mlcp;": u"\u2adb",
+    "mldr;": u"\u2026",
+    "mnplus;": u"\u2213",
+    "models;": u"\u22a7",
+    "mopf;": u"\U0001d55e",
+    "mp;": u"\u2213",
+    "mscr;": u"\U0001d4c2",
+    "mstpos;": u"\u223e",
+    "mu;": u"\u03bc",
+    "multimap;": u"\u22b8",
+    "mumap;": u"\u22b8",
+    "nGg;": u"\u22d9\u0338",
+    "nGt;": u"\u226b\u20d2",
+    "nGtv;": u"\u226b\u0338",
+    "nLeftarrow;": u"\u21cd",
+    "nLeftrightarrow;": u"\u21ce",
+    "nLl;": u"\u22d8\u0338",
+    "nLt;": u"\u226a\u20d2",
+    "nLtv;": u"\u226a\u0338",
+    "nRightarrow;": u"\u21cf",
+    "nVDash;": u"\u22af",
+    "nVdash;": u"\u22ae",
+    "nabla;": u"\u2207",
+    "nacute;": u"\u0144",
+    "nang;": u"\u2220\u20d2",
+    "nap;": u"\u2249",
+    "napE;": u"\u2a70\u0338",
+    "napid;": u"\u224b\u0338",
+    "napos;": u"\u0149",
+    "napprox;": u"\u2249",
+    "natur;": u"\u266e",
+    "natural;": u"\u266e",
+    "naturals;": u"\u2115",
+    "nbsp": u"\xa0",
+    "nbsp;": u"\xa0",
+    "nbump;": u"\u224e\u0338",
+    "nbumpe;": u"\u224f\u0338",
+    "ncap;": u"\u2a43",
+    "ncaron;": u"\u0148",
+    "ncedil;": u"\u0146",
+    "ncong;": u"\u2247",
+    "ncongdot;": u"\u2a6d\u0338",
+    "ncup;": u"\u2a42",
+    "ncy;": u"\u043d",
+    "ndash;": u"\u2013",
+    "ne;": u"\u2260",
+    "neArr;": u"\u21d7",
+    "nearhk;": u"\u2924",
+    "nearr;": u"\u2197",
+    "nearrow;": u"\u2197",
+    "nedot;": u"\u2250\u0338",
+    "nequiv;": u"\u2262",
+    "nesear;": u"\u2928",
+    "nesim;": u"\u2242\u0338",
+    "nexist;": u"\u2204",
+    "nexists;": u"\u2204",
+    "nfr;": u"\U0001d52b",
+    "ngE;": u"\u2267\u0338",
+    "nge;": u"\u2271",
+    "ngeq;": u"\u2271",
+    "ngeqq;": u"\u2267\u0338",
+    "ngeqslant;": u"\u2a7e\u0338",
+    "nges;": u"\u2a7e\u0338",
+    "ngsim;": u"\u2275",
+    "ngt;": u"\u226f",
+    "ngtr;": u"\u226f",
+    "nhArr;": u"\u21ce",
+    "nharr;": u"\u21ae",
+    "nhpar;": u"\u2af2",
+    "ni;": u"\u220b",
+    "nis;": u"\u22fc",
+    "nisd;": u"\u22fa",
+    "niv;": u"\u220b",
+    "njcy;": u"\u045a",
+    "nlArr;": u"\u21cd",
+    "nlE;": u"\u2266\u0338",
+    "nlarr;": u"\u219a",
+    "nldr;": u"\u2025",
+    "nle;": u"\u2270",
+    "nleftarrow;": u"\u219a",
+    "nleftrightarrow;": u"\u21ae",
+    "nleq;": u"\u2270",
+    "nleqq;": u"\u2266\u0338",
+    "nleqslant;": u"\u2a7d\u0338",
+    "nles;": u"\u2a7d\u0338",
+    "nless;": u"\u226e",
+    "nlsim;": u"\u2274",
+    "nlt;": u"\u226e",
+    "nltri;": u"\u22ea",
+    "nltrie;": u"\u22ec",
+    "nmid;": u"\u2224",
+    "nopf;": u"\U0001d55f",
+    "not": u"\xac",
+    "not;": u"\xac",
+    "notin;": u"\u2209",
+    "notinE;": u"\u22f9\u0338",
+    "notindot;": u"\u22f5\u0338",
+    "notinva;": u"\u2209",
+    "notinvb;": u"\u22f7",
+    "notinvc;": u"\u22f6",
+    "notni;": u"\u220c",
+    "notniva;": u"\u220c",
+    "notnivb;": u"\u22fe",
+    "notnivc;": u"\u22fd",
+    "npar;": u"\u2226",
+    "nparallel;": u"\u2226",
+    "nparsl;": u"\u2afd\u20e5",
+    "npart;": u"\u2202\u0338",
+    "npolint;": u"\u2a14",
+    "npr;": u"\u2280",
+    "nprcue;": u"\u22e0",
+    "npre;": u"\u2aaf\u0338",
+    "nprec;": u"\u2280",
+    "npreceq;": u"\u2aaf\u0338",
+    "nrArr;": u"\u21cf",
+    "nrarr;": u"\u219b",
+    "nrarrc;": u"\u2933\u0338",
+    "nrarrw;": u"\u219d\u0338",
+    "nrightarrow;": u"\u219b",
+    "nrtri;": u"\u22eb",
+    "nrtrie;": u"\u22ed",
+    "nsc;": u"\u2281",
+    "nsccue;": u"\u22e1",
+    "nsce;": u"\u2ab0\u0338",
+    "nscr;": u"\U0001d4c3",
+    "nshortmid;": u"\u2224",
+    "nshortparallel;": u"\u2226",
+    "nsim;": u"\u2241",
+    "nsime;": u"\u2244",
+    "nsimeq;": u"\u2244",
+    "nsmid;": u"\u2224",
+    "nspar;": u"\u2226",
+    "nsqsube;": u"\u22e2",
+    "nsqsupe;": u"\u22e3",
+    "nsub;": u"\u2284",
+    "nsubE;": u"\u2ac5\u0338",
+    "nsube;": u"\u2288",
+    "nsubset;": u"\u2282\u20d2",
+    "nsubseteq;": u"\u2288",
+    "nsubseteqq;": u"\u2ac5\u0338",
+    "nsucc;": u"\u2281",
+    "nsucceq;": u"\u2ab0\u0338",
+    "nsup;": u"\u2285",
+    "nsupE;": u"\u2ac6\u0338",
+    "nsupe;": u"\u2289",
+    "nsupset;": u"\u2283\u20d2",
+    "nsupseteq;": u"\u2289",
+    "nsupseteqq;": u"\u2ac6\u0338",
+    "ntgl;": u"\u2279",
+    "ntilde": u"\xf1",
+    "ntilde;": u"\xf1",
+    "ntlg;": u"\u2278",
+    "ntriangleleft;": u"\u22ea",
+    "ntrianglelefteq;": u"\u22ec",
+    "ntriangleright;": u"\u22eb",
+    "ntrianglerighteq;": u"\u22ed",
+    "nu;": u"\u03bd",
+    "num;": u"#",
+    "numero;": u"\u2116",
+    "numsp;": u"\u2007",
+    "nvDash;": u"\u22ad",
+    "nvHarr;": u"\u2904",
+    "nvap;": u"\u224d\u20d2",
+    "nvdash;": u"\u22ac",
+    "nvge;": u"\u2265\u20d2",
+    "nvgt;": u">\u20d2",
+    "nvinfin;": u"\u29de",
+    "nvlArr;": u"\u2902",
+    "nvle;": u"\u2264\u20d2",
+    "nvlt;": u"<\u20d2",
+    "nvltrie;": u"\u22b4\u20d2",
+    "nvrArr;": u"\u2903",
+    "nvrtrie;": u"\u22b5\u20d2",
+    "nvsim;": u"\u223c\u20d2",
+    "nwArr;": u"\u21d6",
+    "nwarhk;": u"\u2923",
+    "nwarr;": u"\u2196",
+    "nwarrow;": u"\u2196",
+    "nwnear;": u"\u2927",
+    "oS;": u"\u24c8",
+    "oacute": u"\xf3",
+    "oacute;": u"\xf3",
+    "oast;": u"\u229b",
+    "ocir;": u"\u229a",
+    "ocirc": u"\xf4",
+    "ocirc;": u"\xf4",
+    "ocy;": u"\u043e",
+    "odash;": u"\u229d",
+    "odblac;": u"\u0151",
+    "odiv;": u"\u2a38",
+    "odot;": u"\u2299",
+    "odsold;": u"\u29bc",
+    "oelig;": u"\u0153",
+    "ofcir;": u"\u29bf",
+    "ofr;": u"\U0001d52c",
+    "ogon;": u"\u02db",
+    "ograve": u"\xf2",
+    "ograve;": u"\xf2",
+    "ogt;": u"\u29c1",
+    "ohbar;": u"\u29b5",
+    "ohm;": u"\u03a9",
+    "oint;": u"\u222e",
+    "olarr;": u"\u21ba",
+    "olcir;": u"\u29be",
+    "olcross;": u"\u29bb",
+    "oline;": u"\u203e",
+    "olt;": u"\u29c0",
+    "omacr;": u"\u014d",
+    "omega;": u"\u03c9",
+    "omicron;": u"\u03bf",
+    "omid;": u"\u29b6",
+    "ominus;": u"\u2296",
+    "oopf;": u"\U0001d560",
+    "opar;": u"\u29b7",
+    "operp;": u"\u29b9",
+    "oplus;": u"\u2295",
+    "or;": u"\u2228",
+    "orarr;": u"\u21bb",
+    "ord;": u"\u2a5d",
+    "order;": u"\u2134",
+    "orderof;": u"\u2134",
+    "ordf": u"\xaa",
+    "ordf;": u"\xaa",
+    "ordm": u"\xba",
+    "ordm;": u"\xba",
+    "origof;": u"\u22b6",
+    "oror;": u"\u2a56",
+    "orslope;": u"\u2a57",
+    "orv;": u"\u2a5b",
+    "oscr;": u"\u2134",
+    "oslash": u"\xf8",
+    "oslash;": u"\xf8",
+    "osol;": u"\u2298",
+    "otilde": u"\xf5",
+    "otilde;": u"\xf5",
+    "otimes;": u"\u2297",
+    "otimesas;": u"\u2a36",
+    "ouml": u"\xf6",
+    "ouml;": u"\xf6",
+    "ovbar;": u"\u233d",
+    "par;": u"\u2225",
+    "para": u"\xb6",
+    "para;": u"\xb6",
+    "parallel;": u"\u2225",
+    "parsim;": u"\u2af3",
+    "parsl;": u"\u2afd",
+    "part;": u"\u2202",
+    "pcy;": u"\u043f",
+    "percnt;": u"%",
+    "period;": u".",
+    "permil;": u"\u2030",
+    "perp;": u"\u22a5",
+    "pertenk;": u"\u2031",
+    "pfr;": u"\U0001d52d",
+    "phi;": u"\u03c6",
+    "phiv;": u"\u03d5",
+    "phmmat;": u"\u2133",
+    "phone;": u"\u260e",
+    "pi;": u"\u03c0",
+    "pitchfork;": u"\u22d4",
+    "piv;": u"\u03d6",
+    "planck;": u"\u210f",
+    "planckh;": u"\u210e",
+    "plankv;": u"\u210f",
+    "plus;": u"+",
+    "plusacir;": u"\u2a23",
+    "plusb;": u"\u229e",
+    "pluscir;": u"\u2a22",
+    "plusdo;": u"\u2214",
+    "plusdu;": u"\u2a25",
+    "pluse;": u"\u2a72",
+    "plusmn": u"\xb1",
+    "plusmn;": u"\xb1",
+    "plussim;": u"\u2a26",
+    "plustwo;": u"\u2a27",
+    "pm;": u"\xb1",
+    "pointint;": u"\u2a15",
+    "popf;": u"\U0001d561",
+    "pound": u"\xa3",
+    "pound;": u"\xa3",
+    "pr;": u"\u227a",
+    "prE;": u"\u2ab3",
+    "prap;": u"\u2ab7",
+    "prcue;": u"\u227c",
+    "pre;": u"\u2aaf",
+    "prec;": u"\u227a",
+    "precapprox;": u"\u2ab7",
+    "preccurlyeq;": u"\u227c",
+    "preceq;": u"\u2aaf",
+    "precnapprox;": u"\u2ab9",
+    "precneqq;": u"\u2ab5",
+    "precnsim;": u"\u22e8",
+    "precsim;": u"\u227e",
+    "prime;": u"\u2032",
+    "primes;": u"\u2119",
+    "prnE;": u"\u2ab5",
+    "prnap;": u"\u2ab9",
+    "prnsim;": u"\u22e8",
+    "prod;": u"\u220f",
+    "profalar;": u"\u232e",
+    "profline;": u"\u2312",
+    "profsurf;": u"\u2313",
+    "prop;": u"\u221d",
+    "propto;": u"\u221d",
+    "prsim;": u"\u227e",
+    "prurel;": u"\u22b0",
+    "pscr;": u"\U0001d4c5",
+    "psi;": u"\u03c8",
+    "puncsp;": u"\u2008",
+    "qfr;": u"\U0001d52e",
+    "qint;": u"\u2a0c",
+    "qopf;": u"\U0001d562",
+    "qprime;": u"\u2057",
+    "qscr;": u"\U0001d4c6",
+    "quaternions;": u"\u210d",
+    "quatint;": u"\u2a16",
+    "quest;": u"?",
+    "questeq;": u"\u225f",
+    "quot": u"\"",
+    "quot;": u"\"",
+    "rAarr;": u"\u21db",
+    "rArr;": u"\u21d2",
+    "rAtail;": u"\u291c",
+    "rBarr;": u"\u290f",
+    "rHar;": u"\u2964",
+    "race;": u"\u223d\u0331",
+    "racute;": u"\u0155",
+    "radic;": u"\u221a",
+    "raemptyv;": u"\u29b3",
+    "rang;": u"\u27e9",
+    "rangd;": u"\u2992",
+    "range;": u"\u29a5",
+    "rangle;": u"\u27e9",
+    "raquo": u"\xbb",
+    "raquo;": u"\xbb",
+    "rarr;": u"\u2192",
+    "rarrap;": u"\u2975",
+    "rarrb;": u"\u21e5",
+    "rarrbfs;": u"\u2920",
+    "rarrc;": u"\u2933",
+    "rarrfs;": u"\u291e",
+    "rarrhk;": u"\u21aa",
+    "rarrlp;": u"\u21ac",
+    "rarrpl;": u"\u2945",
+    "rarrsim;": u"\u2974",
+    "rarrtl;": u"\u21a3",
+    "rarrw;": u"\u219d",
+    "ratail;": u"\u291a",
+    "ratio;": u"\u2236",
+    "rationals;": u"\u211a",
+    "rbarr;": u"\u290d",
+    "rbbrk;": u"\u2773",
+    "rbrace;": u"}",
+    "rbrack;": u"]",
+    "rbrke;": u"\u298c",
+    "rbrksld;": u"\u298e",
+    "rbrkslu;": u"\u2990",
+    "rcaron;": u"\u0159",
+    "rcedil;": u"\u0157",
+    "rceil;": u"\u2309",
+    "rcub;": u"}",
+    "rcy;": u"\u0440",
+    "rdca;": u"\u2937",
+    "rdldhar;": u"\u2969",
+    "rdquo;": u"\u201d",
+    "rdquor;": u"\u201d",
+    "rdsh;": u"\u21b3",
+    "real;": u"\u211c",
+    "realine;": u"\u211b",
+    "realpart;": u"\u211c",
+    "reals;": u"\u211d",
+    "rect;": u"\u25ad",
+    "reg": u"\xae",
+    "reg;": u"\xae",
+    "rfisht;": u"\u297d",
+    "rfloor;": u"\u230b",
+    "rfr;": u"\U0001d52f",
+    "rhard;": u"\u21c1",
+    "rharu;": u"\u21c0",
+    "rharul;": u"\u296c",
+    "rho;": u"\u03c1",
+    "rhov;": u"\u03f1",
+    "rightarrow;": u"\u2192",
+    "rightarrowtail;": u"\u21a3",
+    "rightharpoondown;": u"\u21c1",
+    "rightharpoonup;": u"\u21c0",
+    "rightleftarrows;": u"\u21c4",
+    "rightleftharpoons;": u"\u21cc",
+    "rightrightarrows;": u"\u21c9",
+    "rightsquigarrow;": u"\u219d",
+    "rightthreetimes;": u"\u22cc",
+    "ring;": u"\u02da",
+    "risingdotseq;": u"\u2253",
+    "rlarr;": u"\u21c4",
+    "rlhar;": u"\u21cc",
+    "rlm;": u"\u200f",
+    "rmoust;": u"\u23b1",
+    "rmoustache;": u"\u23b1",
+    "rnmid;": u"\u2aee",
+    "roang;": u"\u27ed",
+    "roarr;": u"\u21fe",
+    "robrk;": u"\u27e7",
+    "ropar;": u"\u2986",
+    "ropf;": u"\U0001d563",
+    "roplus;": u"\u2a2e",
+    "rotimes;": u"\u2a35",
+    "rpar;": u")",
+    "rpargt;": u"\u2994",
+    "rppolint;": u"\u2a12",
+    "rrarr;": u"\u21c9",
+    "rsaquo;": u"\u203a",
+    "rscr;": u"\U0001d4c7",
+    "rsh;": u"\u21b1",
+    "rsqb;": u"]",
+    "rsquo;": u"\u2019",
+    "rsquor;": u"\u2019",
+    "rthree;": u"\u22cc",
+    "rtimes;": u"\u22ca",
+    "rtri;": u"\u25b9",
+    "rtrie;": u"\u22b5",
+    "rtrif;": u"\u25b8",
+    "rtriltri;": u"\u29ce",
+    "ruluhar;": u"\u2968",
+    "rx;": u"\u211e",
+    "sacute;": u"\u015b",
+    "sbquo;": u"\u201a",
+    "sc;": u"\u227b",
+    "scE;": u"\u2ab4",
+    "scap;": u"\u2ab8",
+    "scaron;": u"\u0161",
+    "sccue;": u"\u227d",
+    "sce;": u"\u2ab0",
+    "scedil;": u"\u015f",
+    "scirc;": u"\u015d",
+    "scnE;": u"\u2ab6",
+    "scnap;": u"\u2aba",
+    "scnsim;": u"\u22e9",
+    "scpolint;": u"\u2a13",
+    "scsim;": u"\u227f",
+    "scy;": u"\u0441",
+    "sdot;": u"\u22c5",
+    "sdotb;": u"\u22a1",
+    "sdote;": u"\u2a66",
+    "seArr;": u"\u21d8",
+    "searhk;": u"\u2925",
+    "searr;": u"\u2198",
+    "searrow;": u"\u2198",
+    "sect": u"\xa7",
+    "sect;": u"\xa7",
+    "semi;": u";",
+    "seswar;": u"\u2929",
+    "setminus;": u"\u2216",
+    "setmn;": u"\u2216",
+    "sext;": u"\u2736",
+    "sfr;": u"\U0001d530",
+    "sfrown;": u"\u2322",
+    "sharp;": u"\u266f",
+    "shchcy;": u"\u0449",
+    "shcy;": u"\u0448",
+    "shortmid;": u"\u2223",
+    "shortparallel;": u"\u2225",
+    "shy": u"\xad",
+    "shy;": u"\xad",
+    "sigma;": u"\u03c3",
+    "sigmaf;": u"\u03c2",
+    "sigmav;": u"\u03c2",
+    "sim;": u"\u223c",
+    "simdot;": u"\u2a6a",
+    "sime;": u"\u2243",
+    "simeq;": u"\u2243",
+    "simg;": u"\u2a9e",
+    "simgE;": u"\u2aa0",
+    "siml;": u"\u2a9d",
+    "simlE;": u"\u2a9f",
+    "simne;": u"\u2246",
+    "simplus;": u"\u2a24",
+    "simrarr;": u"\u2972",
+    "slarr;": u"\u2190",
+    "smallsetminus;": u"\u2216",
+    "smashp;": u"\u2a33",
+    "smeparsl;": u"\u29e4",
+    "smid;": u"\u2223",
+    "smile;": u"\u2323",
+    "smt;": u"\u2aaa",
+    "smte;": u"\u2aac",
+    "smtes;": u"\u2aac\ufe00",
+    "softcy;": u"\u044c",
+    "sol;": u"/",
+    "solb;": u"\u29c4",
+    "solbar;": u"\u233f",
+    "sopf;": u"\U0001d564",
+    "spades;": u"\u2660",
+    "spadesuit;": u"\u2660",
+    "spar;": u"\u2225",
+    "sqcap;": u"\u2293",
+    "sqcaps;": u"\u2293\ufe00",
+    "sqcup;": u"\u2294",
+    "sqcups;": u"\u2294\ufe00",
+    "sqsub;": u"\u228f",
+    "sqsube;": u"\u2291",
+    "sqsubset;": u"\u228f",
+    "sqsubseteq;": u"\u2291",
+    "sqsup;": u"\u2290",
+    "sqsupe;": u"\u2292",
+    "sqsupset;": u"\u2290",
+    "sqsupseteq;": u"\u2292",
+    "squ;": u"\u25a1",
+    "square;": u"\u25a1",
+    "squarf;": u"\u25aa",
+    "squf;": u"\u25aa",
+    "srarr;": u"\u2192",
+    "sscr;": u"\U0001d4c8",
+    "ssetmn;": u"\u2216",
+    "ssmile;": u"\u2323",
+    "sstarf;": u"\u22c6",
+    "star;": u"\u2606",
+    "starf;": u"\u2605",
+    "straightepsilon;": u"\u03f5",
+    "straightphi;": u"\u03d5",
+    "strns;": u"\xaf",
+    "sub;": u"\u2282",
+    "subE;": u"\u2ac5",
+    "subdot;": u"\u2abd",
+    "sube;": u"\u2286",
+    "subedot;": u"\u2ac3",
+    "submult;": u"\u2ac1",
+    "subnE;": u"\u2acb",
+    "subne;": u"\u228a",
+    "subplus;": u"\u2abf",
+    "subrarr;": u"\u2979",
+    "subset;": u"\u2282",
+    "subseteq;": u"\u2286",
+    "subseteqq;": u"\u2ac5",
+    "subsetneq;": u"\u228a",
+    "subsetneqq;": u"\u2acb",
+    "subsim;": u"\u2ac7",
+    "subsub;": u"\u2ad5",
+    "subsup;": u"\u2ad3",
+    "succ;": u"\u227b",
+    "succapprox;": u"\u2ab8",
+    "succcurlyeq;": u"\u227d",
+    "succeq;": u"\u2ab0",
+    "succnapprox;": u"\u2aba",
+    "succneqq;": u"\u2ab6",
+    "succnsim;": u"\u22e9",
+    "succsim;": u"\u227f",
+    "sum;": u"\u2211",
+    "sung;": u"\u266a",
+    "sup1": u"\xb9",
+    "sup1;": u"\xb9",
+    "sup2": u"\xb2",
+    "sup2;": u"\xb2",
+    "sup3": u"\xb3",
+    "sup3;": u"\xb3",
+    "sup;": u"\u2283",
+    "supE;": u"\u2ac6",
+    "supdot;": u"\u2abe",
+    "supdsub;": u"\u2ad8",
+    "supe;": u"\u2287",
+    "supedot;": u"\u2ac4",
+    "suphsol;": u"\u27c9",
+    "suphsub;": u"\u2ad7",
+    "suplarr;": u"\u297b",
+    "supmult;": u"\u2ac2",
+    "supnE;": u"\u2acc",
+    "supne;": u"\u228b",
+    "supplus;": u"\u2ac0",
+    "supset;": u"\u2283",
+    "supseteq;": u"\u2287",
+    "supseteqq;": u"\u2ac6",
+    "supsetneq;": u"\u228b",
+    "supsetneqq;": u"\u2acc",
+    "supsim;": u"\u2ac8",
+    "supsub;": u"\u2ad4",
+    "supsup;": u"\u2ad6",
+    "swArr;": u"\u21d9",
+    "swarhk;": u"\u2926",
+    "swarr;": u"\u2199",
+    "swarrow;": u"\u2199",
+    "swnwar;": u"\u292a",
+    "szlig": u"\xdf",
+    "szlig;": u"\xdf",
+    "target;": u"\u2316",
+    "tau;": u"\u03c4",
+    "tbrk;": u"\u23b4",
+    "tcaron;": u"\u0165",
+    "tcedil;": u"\u0163",
+    "tcy;": u"\u0442",
+    "tdot;": u"\u20db",
+    "telrec;": u"\u2315",
+    "tfr;": u"\U0001d531",
+    "there4;": u"\u2234",
+    "therefore;": u"\u2234",
+    "theta;": u"\u03b8",
+    "thetasym;": u"\u03d1",
+    "thetav;": u"\u03d1",
+    "thickapprox;": u"\u2248",
+    "thicksim;": u"\u223c",
+    "thinsp;": u"\u2009",
+    "thkap;": u"\u2248",
+    "thksim;": u"\u223c",
+    "thorn": u"\xfe",
+    "thorn;": u"\xfe",
+    "tilde;": u"\u02dc",
+    "times": u"\xd7",
+    "times;": u"\xd7",
+    "timesb;": u"\u22a0",
+    "timesbar;": u"\u2a31",
+    "timesd;": u"\u2a30",
+    "tint;": u"\u222d",
+    "toea;": u"\u2928",
+    "top;": u"\u22a4",
+    "topbot;": u"\u2336",
+    "topcir;": u"\u2af1",
+    "topf;": u"\U0001d565",
+    "topfork;": u"\u2ada",
+    "tosa;": u"\u2929",
+    "tprime;": u"\u2034",
+    "trade;": u"\u2122",
+    "triangle;": u"\u25b5",
+    "triangledown;": u"\u25bf",
+    "triangleleft;": u"\u25c3",
+    "trianglelefteq;": u"\u22b4",
+    "triangleq;": u"\u225c",
+    "triangleright;": u"\u25b9",
+    "trianglerighteq;": u"\u22b5",
+    "tridot;": u"\u25ec",
+    "trie;": u"\u225c",
+    "triminus;": u"\u2a3a",
+    "triplus;": u"\u2a39",
+    "trisb;": u"\u29cd",
+    "tritime;": u"\u2a3b",
+    "trpezium;": u"\u23e2",
+    "tscr;": u"\U0001d4c9",
+    "tscy;": u"\u0446",
+    "tshcy;": u"\u045b",
+    "tstrok;": u"\u0167",
+    "twixt;": u"\u226c",
+    "twoheadleftarrow;": u"\u219e",
+    "twoheadrightarrow;": u"\u21a0",
+    "uArr;": u"\u21d1",
+    "uHar;": u"\u2963",
+    "uacute": u"\xfa",
+    "uacute;": u"\xfa",
+    "uarr;": u"\u2191",
+    "ubrcy;": u"\u045e",
+    "ubreve;": u"\u016d",
+    "ucirc": u"\xfb",
+    "ucirc;": u"\xfb",
+    "ucy;": u"\u0443",
+    "udarr;": u"\u21c5",
+    "udblac;": u"\u0171",
+    "udhar;": u"\u296e",
+    "ufisht;": u"\u297e",
+    "ufr;": u"\U0001d532",
+    "ugrave": u"\xf9",
+    "ugrave;": u"\xf9",
+    "uharl;": u"\u21bf",
+    "uharr;": u"\u21be",
+    "uhblk;": u"\u2580",
+    "ulcorn;": u"\u231c",
+    "ulcorner;": u"\u231c",
+    "ulcrop;": u"\u230f",
+    "ultri;": u"\u25f8",
+    "umacr;": u"\u016b",
+    "uml": u"\xa8",
+    "uml;": u"\xa8",
+    "uogon;": u"\u0173",
+    "uopf;": u"\U0001d566",
+    "uparrow;": u"\u2191",
+    "updownarrow;": u"\u2195",
+    "upharpoonleft;": u"\u21bf",
+    "upharpoonright;": u"\u21be",
+    "uplus;": u"\u228e",
+    "upsi;": u"\u03c5",
+    "upsih;": u"\u03d2",
+    "upsilon;": u"\u03c5",
+    "upuparrows;": u"\u21c8",
+    "urcorn;": u"\u231d",
+    "urcorner;": u"\u231d",
+    "urcrop;": u"\u230e",
+    "uring;": u"\u016f",
+    "urtri;": u"\u25f9",
+    "uscr;": u"\U0001d4ca",
+    "utdot;": u"\u22f0",
+    "utilde;": u"\u0169",
+    "utri;": u"\u25b5",
+    "utrif;": u"\u25b4",
+    "uuarr;": u"\u21c8",
+    "uuml": u"\xfc",
+    "uuml;": u"\xfc",
+    "uwangle;": u"\u29a7",
+    "vArr;": u"\u21d5",
+    "vBar;": u"\u2ae8",
+    "vBarv;": u"\u2ae9",
+    "vDash;": u"\u22a8",
+    "vangrt;": u"\u299c",
+    "varepsilon;": u"\u03f5",
+    "varkappa;": u"\u03f0",
+    "varnothing;": u"\u2205",
+    "varphi;": u"\u03d5",
+    "varpi;": u"\u03d6",
+    "varpropto;": u"\u221d",
+    "varr;": u"\u2195",
+    "varrho;": u"\u03f1",
+    "varsigma;": u"\u03c2",
+    "varsubsetneq;": u"\u228a\ufe00",
+    "varsubsetneqq;": u"\u2acb\ufe00",
+    "varsupsetneq;": u"\u228b\ufe00",
+    "varsupsetneqq;": u"\u2acc\ufe00",
+    "vartheta;": u"\u03d1",
+    "vartriangleleft;": u"\u22b2",
+    "vartriangleright;": u"\u22b3",
+    "vcy;": u"\u0432",
+    "vdash;": u"\u22a2",
+    "vee;": u"\u2228",
+    "veebar;": u"\u22bb",
+    "veeeq;": u"\u225a",
+    "vellip;": u"\u22ee",
+    "verbar;": u"|",
+    "vert;": u"|",
+    "vfr;": u"\U0001d533",
+    "vltri;": u"\u22b2",
+    "vnsub;": u"\u2282\u20d2",
+    "vnsup;": u"\u2283\u20d2",
+    "vopf;": u"\U0001d567",
+    "vprop;": u"\u221d",
+    "vrtri;": u"\u22b3",
+    "vscr;": u"\U0001d4cb",
+    "vsubnE;": u"\u2acb\ufe00",
+    "vsubne;": u"\u228a\ufe00",
+    "vsupnE;": u"\u2acc\ufe00",
+    "vsupne;": u"\u228b\ufe00",
+    "vzigzag;": u"\u299a",
+    "wcirc;": u"\u0175",
+    "wedbar;": u"\u2a5f",
+    "wedge;": u"\u2227",
+    "wedgeq;": u"\u2259",
+    "weierp;": u"\u2118",
+    "wfr;": u"\U0001d534",
+    "wopf;": u"\U0001d568",
+    "wp;": u"\u2118",
+    "wr;": u"\u2240",
+    "wreath;": u"\u2240",
+    "wscr;": u"\U0001d4cc",
+    "xcap;": u"\u22c2",
+    "xcirc;": u"\u25ef",
+    "xcup;": u"\u22c3",
+    "xdtri;": u"\u25bd",
+    "xfr;": u"\U0001d535",
+    "xhArr;": u"\u27fa",
+    "xharr;": u"\u27f7",
+    "xi;": u"\u03be",
+    "xlArr;": u"\u27f8",
+    "xlarr;": u"\u27f5",
+    "xmap;": u"\u27fc",
+    "xnis;": u"\u22fb",
+    "xodot;": u"\u2a00",
+    "xopf;": u"\U0001d569",
+    "xoplus;": u"\u2a01",
+    "xotime;": u"\u2a02",
+    "xrArr;": u"\u27f9",
+    "xrarr;": u"\u27f6",
+    "xscr;": u"\U0001d4cd",
+    "xsqcup;": u"\u2a06",
+    "xuplus;": u"\u2a04",
+    "xutri;": u"\u25b3",
+    "xvee;": u"\u22c1",
+    "xwedge;": u"\u22c0",
+    "yacute": u"\xfd",
+    "yacute;": u"\xfd",
+    "yacy;": u"\u044f",
+    "ycirc;": u"\u0177",
+    "ycy;": u"\u044b",
+    "yen": u"\xa5",
+    "yen;": u"\xa5",
+    "yfr;": u"\U0001d536",
+    "yicy;": u"\u0457",
+    "yopf;": u"\U0001d56a",
+    "yscr;": u"\U0001d4ce",
+    "yucy;": u"\u044e",
+    "yuml": u"\xff",
+    "yuml;": u"\xff",
+    "zacute;": u"\u017a",
+    "zcaron;": u"\u017e",
+    "zcy;": u"\u0437",
+    "zdot;": u"\u017c",
+    "zeetrf;": u"\u2128",
+    "zeta;": u"\u03b6",
+    "zfr;": u"\U0001d537",
+    "zhcy;": u"\u0436",
+    "zigrarr;": u"\u21dd",
+    "zopf;": u"\U0001d56b",
+    "zscr;": u"\U0001d4cf",
+    "zwj;": u"\u200d",
+    "zwnj;": u"\u200c",
+}
+
+replacementCharacters = {
+    0x0:u"\uFFFD",
+    0x0d:u"\u000D",
+    0x80:u"\u20AC",
+    0x81:u"\u0081",
+    0x81:u"\u0081",
+    0x82:u"\u201A",
+    0x83:u"\u0192",
+    0x84:u"\u201E",
+    0x85:u"\u2026",
+    0x86:u"\u2020",
+    0x87:u"\u2021",
+    0x88:u"\u02C6",
+    0x89:u"\u2030",
+    0x8A:u"\u0160",
+    0x8B:u"\u2039",
+    0x8C:u"\u0152",
+    0x8D:u"\u008D",
+    0x8E:u"\u017D",
+    0x8F:u"\u008F",
+    0x90:u"\u0090",
+    0x91:u"\u2018",
+    0x92:u"\u2019",
+    0x93:u"\u201C",
+    0x94:u"\u201D",
+    0x95:u"\u2022",
+    0x96:u"\u2013",
+    0x97:u"\u2014",
+    0x98:u"\u02DC",
+    0x99:u"\u2122",
+    0x9A:u"\u0161",
+    0x9B:u"\u203A",
+    0x9C:u"\u0153",
+    0x9D:u"\u009D",
+    0x9E:u"\u017E",
+    0x9F:u"\u0178",
+}
+
+encodings = {
+    '437': 'cp437',
+    '850': 'cp850',
+    '852': 'cp852',
+    '855': 'cp855',
+    '857': 'cp857',
+    '860': 'cp860',
+    '861': 'cp861',
+    '862': 'cp862',
+    '863': 'cp863',
+    '865': 'cp865',
+    '866': 'cp866',
+    '869': 'cp869',
+    'ansix341968': 'ascii',
+    'ansix341986': 'ascii',
+    'arabic': 'iso8859-6',
+    'ascii': 'ascii',
+    'asmo708': 'iso8859-6',
+    'big5': 'big5',
+    'big5hkscs': 'big5hkscs',
+    'chinese': 'gbk',
+    'cp037': 'cp037',
+    'cp1026': 'cp1026',
+    'cp154': 'ptcp154',
+    'cp367': 'ascii',
+    'cp424': 'cp424',
+    'cp437': 'cp437',
+    'cp500': 'cp500',
+    'cp775': 'cp775',
+    'cp819': 'windows-1252',
+    'cp850': 'cp850',
+    'cp852': 'cp852',
+    'cp855': 'cp855',
+    'cp857': 'cp857',
+    'cp860': 'cp860',
+    'cp861': 'cp861',
+    'cp862': 'cp862',
+    'cp863': 'cp863',
+    'cp864': 'cp864',
+    'cp865': 'cp865',
+    'cp866': 'cp866',
+    'cp869': 'cp869',
+    'cp936': 'gbk',
+    'cpgr': 'cp869',
+    'cpis': 'cp861',
+    'csascii': 'ascii',
+    'csbig5': 'big5',
+    'cseuckr': 'cp949',
+    'cseucpkdfmtjapanese': 'euc_jp',
+    'csgb2312': 'gbk',
+    'cshproman8': 'hp-roman8',
+    'csibm037': 'cp037',
+    'csibm1026': 'cp1026',
+    'csibm424': 'cp424',
+    'csibm500': 'cp500',
+    'csibm855': 'cp855',
+    'csibm857': 'cp857',
+    'csibm860': 'cp860',
+    'csibm861': 'cp861',
+    'csibm863': 'cp863',
+    'csibm864': 'cp864',
+    'csibm865': 'cp865',
+    'csibm866': 'cp866',
+    'csibm869': 'cp869',
+    'csiso2022jp': 'iso2022_jp',
+    'csiso2022jp2': 'iso2022_jp_2',
+    'csiso2022kr': 'iso2022_kr',
+    'csiso58gb231280': 'gbk',
+    'csisolatin1': 'windows-1252',
+    'csisolatin2': 'iso8859-2',
+    'csisolatin3': 'iso8859-3',
+    'csisolatin4': 'iso8859-4',
+    'csisolatin5': 'windows-1254',
+    'csisolatin6': 'iso8859-10',
+    'csisolatinarabic': 'iso8859-6',
+    'csisolatincyrillic': 'iso8859-5',
+    'csisolatingreek': 'iso8859-7',
+    'csisolatinhebrew': 'iso8859-8',
+    'cskoi8r': 'koi8-r',
+    'csksc56011987': 'cp949',
+    'cspc775baltic': 'cp775',
+    'cspc850multilingual': 'cp850',
+    'cspc862latinhebrew': 'cp862',
+    'cspc8codepage437': 'cp437',
+    'cspcp852': 'cp852',
+    'csptcp154': 'ptcp154',
+    'csshiftjis': 'shift_jis',
+    'csunicode11utf7': 'utf-7',
+    'cyrillic': 'iso8859-5',
+    'cyrillicasian': 'ptcp154',
+    'ebcdiccpbe': 'cp500',
+    'ebcdiccpca': 'cp037',
+    'ebcdiccpch': 'cp500',
+    'ebcdiccphe': 'cp424',
+    'ebcdiccpnl': 'cp037',
+    'ebcdiccpus': 'cp037',
+    'ebcdiccpwt': 'cp037',
+    'ecma114': 'iso8859-6',
+    'ecma118': 'iso8859-7',
+    'elot928': 'iso8859-7',
+    'eucjp': 'euc_jp',
+    'euckr': 'cp949',
+    'extendedunixcodepackedformatforjapanese': 'euc_jp',
+    'gb18030': 'gb18030',
+    'gb2312': 'gbk',
+    'gb231280': 'gbk',
+    'gbk': 'gbk',
+    'greek': 'iso8859-7',
+    'greek8': 'iso8859-7',
+    'hebrew': 'iso8859-8',
+    'hproman8': 'hp-roman8',
+    'hzgb2312': 'hz',
+    'ibm037': 'cp037',
+    'ibm1026': 'cp1026',
+    'ibm367': 'ascii',
+    'ibm424': 'cp424',
+    'ibm437': 'cp437',
+    'ibm500': 'cp500',
+    'ibm775': 'cp775',
+    'ibm819': 'windows-1252',
+    'ibm850': 'cp850',
+    'ibm852': 'cp852',
+    'ibm855': 'cp855',
+    'ibm857': 'cp857',
+    'ibm860': 'cp860',
+    'ibm861': 'cp861',
+    'ibm862': 'cp862',
+    'ibm863': 'cp863',
+    'ibm864': 'cp864',
+    'ibm865': 'cp865',
+    'ibm866': 'cp866',
+    'ibm869': 'cp869',
+    'iso2022jp': 'iso2022_jp',
+    'iso2022jp2': 'iso2022_jp_2',
+    'iso2022kr': 'iso2022_kr',
+    'iso646irv1991': 'ascii',
+    'iso646us': 'ascii',
+    'iso88591': 'windows-1252',
+    'iso885910': 'iso8859-10',
+    'iso8859101992': 'iso8859-10',
+    'iso885911987': 'windows-1252',
+    'iso885913': 'iso8859-13',
+    'iso885914': 'iso8859-14',
+    'iso8859141998': 'iso8859-14',
+    'iso885915': 'iso8859-15',
+    'iso885916': 'iso8859-16',
+    'iso8859162001': 'iso8859-16',
+    'iso88592': 'iso8859-2',
+    'iso885921987': 'iso8859-2',
+    'iso88593': 'iso8859-3',
+    'iso885931988': 'iso8859-3',
+    'iso88594': 'iso8859-4',
+    'iso885941988': 'iso8859-4',
+    'iso88595': 'iso8859-5',
+    'iso885951988': 'iso8859-5',
+    'iso88596': 'iso8859-6',
+    'iso885961987': 'iso8859-6',
+    'iso88597': 'iso8859-7',
+    'iso885971987': 'iso8859-7',
+    'iso88598': 'iso8859-8',
+    'iso885981988': 'iso8859-8',
+    'iso88599': 'windows-1254',
+    'iso885991989': 'windows-1254',
+    'isoceltic': 'iso8859-14',
+    'isoir100': 'windows-1252',
+    'isoir101': 'iso8859-2',
+    'isoir109': 'iso8859-3',
+    'isoir110': 'iso8859-4',
+    'isoir126': 'iso8859-7',
+    'isoir127': 'iso8859-6',
+    'isoir138': 'iso8859-8',
+    'isoir144': 'iso8859-5',
+    'isoir148': 'windows-1254',
+    'isoir149': 'cp949',
+    'isoir157': 'iso8859-10',
+    'isoir199': 'iso8859-14',
+    'isoir226': 'iso8859-16',
+    'isoir58': 'gbk',
+    'isoir6': 'ascii',
+    'koi8r': 'koi8-r',
+    'koi8u': 'koi8-u',
+    'korean': 'cp949',
+    'ksc5601': 'cp949',
+    'ksc56011987': 'cp949',
+    'ksc56011989': 'cp949',
+    'l1': 'windows-1252',
+    'l10': 'iso8859-16',
+    'l2': 'iso8859-2',
+    'l3': 'iso8859-3',
+    'l4': 'iso8859-4',
+    'l5': 'windows-1254',
+    'l6': 'iso8859-10',
+    'l8': 'iso8859-14',
+    'latin1': 'windows-1252',
+    'latin10': 'iso8859-16',
+    'latin2': 'iso8859-2',
+    'latin3': 'iso8859-3',
+    'latin4': 'iso8859-4',
+    'latin5': 'windows-1254',
+    'latin6': 'iso8859-10',
+    'latin8': 'iso8859-14',
+    'latin9': 'iso8859-15',
+    'ms936': 'gbk',
+    'mskanji': 'shift_jis',
+    'pt154': 'ptcp154',
+    'ptcp154': 'ptcp154',
+    'r8': 'hp-roman8',
+    'roman8': 'hp-roman8',
+    'shiftjis': 'shift_jis',
+    'tis620': 'cp874',
+    'unicode11utf7': 'utf-7',
+    'us': 'ascii',
+    'usascii': 'ascii',
+    'utf16': 'utf-16',
+    'utf16be': 'utf-16-be',
+    'utf16le': 'utf-16-le',
+    'utf8': 'utf-8',
+    'windows1250': 'cp1250',
+    'windows1251': 'cp1251',
+    'windows1252': 'cp1252',
+    'windows1253': 'cp1253',
+    'windows1254': 'cp1254',
+    'windows1255': 'cp1255',
+    'windows1256': 'cp1256',
+    'windows1257': 'cp1257',
+    'windows1258': 'cp1258',
+    'windows936': 'gbk',
+    'x-x-big5': 'big5'}
+
+tokenTypes = {
+    "Doctype":0,
+    "Characters":1,
+    "SpaceCharacters":2,
+    "StartTag":3,
+    "EndTag":4,
+    "EmptyTag":5,
+    "Comment":6,
+    "ParseError":7
+}
+
+tagTokenTypes = frozenset((tokenTypes["StartTag"], tokenTypes["EndTag"], 
+                           tokenTypes["EmptyTag"]))
+
+
+prefixes = dict([(v,k) for k,v in namespaces.iteritems()])
+prefixes["http://www.w3.org/1998/Math/MathML"] = "math"
+
+class DataLossWarning(UserWarning):
+    pass
+
+class ReparseException(Exception):
+    pass
diff --git a/html5lib/filters/__init__.py b/html5lib/filters/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/html5lib/filters/_base.py b/html5lib/filters/_base.py
new file mode 100644
index 00000000..bca94ada
--- /dev/null
+++ b/html5lib/filters/_base.py
@@ -0,0 +1,10 @@
+
+class Filter(object):
+    def __init__(self, source):
+        self.source = source
+
+    def __iter__(self):
+        return iter(self.source)
+
+    def __getattr__(self, name):
+        return getattr(self.source, name)
diff --git a/html5lib/filters/formfiller.py b/html5lib/filters/formfiller.py
new file mode 100644
index 00000000..94001714
--- /dev/null
+++ b/html5lib/filters/formfiller.py
@@ -0,0 +1,127 @@
+#
+# The goal is to finally have a form filler where you pass data for
+# each form, using the algorithm for "Seeding a form with initial values"
+# See http://www.whatwg.org/specs/web-forms/current-work/#seeding
+#
+
+import _base
+
+from html5lib.constants import spaceCharacters
+spaceCharacters = u"".join(spaceCharacters)
+
+class SimpleFilter(_base.Filter):
+    def __init__(self, source, fieldStorage):
+        _base.Filter.__init__(self, source)
+        self.fieldStorage = fieldStorage
+
+    def __iter__(self):
+        field_indices = {}
+        state = None
+        field_name = None
+        for token in _base.Filter.__iter__(self):
+            type = token["type"]
+            if type in ("StartTag", "EmptyTag"):
+                name = token["name"].lower()
+                if name == "input":
+                    field_name = None
+                    field_type = None
+                    input_value_index = -1
+                    input_checked_index = -1
+                    for i,(n,v) in enumerate(token["data"]):
+                        n = n.lower()
+                        if n == u"name":
+                            field_name = v.strip(spaceCharacters)
+                        elif n == u"type":
+                            field_type = v.strip(spaceCharacters)
+                        elif n == u"checked":
+                            input_checked_index = i
+                        elif n == u"value":
+                            input_value_index = i
+
+                    value_list = self.fieldStorage.getlist(field_name)
+                    field_index = field_indices.setdefault(field_name, 0)
+                    if field_index < len(value_list):
+                        value = value_list[field_index]
+                    else:
+                        value = ""
+
+                    if field_type in (u"checkbox", u"radio"):
+                        if value_list:
+                            if token["data"][input_value_index][1] == value:
+                                if input_checked_index < 0:
+                                    token["data"].append((u"checked", u""))
+                                field_indices[field_name] = field_index + 1
+                            elif input_checked_index >= 0:
+                                del token["data"][input_checked_index]
+
+                    elif field_type not in (u"button", u"submit", u"reset"):
+                        if input_value_index >= 0:
+                            token["data"][input_value_index] = (u"value", value)
+                        else:
+                            token["data"].append((u"value", value))
+                        field_indices[field_name] = field_index + 1
+
+                    field_type = None
+                    field_name = None
+
+                elif name == "textarea":
+                    field_type = "textarea"
+                    field_name = dict((token["data"])[::-1])["name"]
+
+                elif name == "select":
+                    field_type = "select"
+                    attributes = dict(token["data"][::-1])
+                    field_name = attributes.get("name")
+                    is_select_multiple = "multiple" in attributes
+                    is_selected_option_found = False
+
+                elif field_type == "select" and field_name and name == "option":
+                    option_selected_index = -1
+                    option_value = None
+                    for i,(n,v) in enumerate(token["data"]):
+                        n = n.lower()
+                        if n == "selected":
+                            option_selected_index = i
+                        elif n == "value":
+                            option_value = v.strip(spaceCharacters)
+                    if option_value is None:
+                        raise NotImplementedError("