com.googler.python 1.0.0

package/python3.4.2/lib/python3.4/site-packages/pip/_vendor/html5lib/sanitizer.py

@@ -0,0 +1,271 @@
+from __future__ import absolute_import, division, unicode_literals
+
+import re
+from xml.sax.saxutils import escape, unescape
+
+from .tokenizer import HTMLTokenizer
+from .constants import tokenTypes
+
+
+class HTMLSanitizerMixin(object):
+    """ sanitization of XHTML+MathML+SVG and of inline style attributes."""
+
+    acceptable_elements = ['a', 'abbr', 'acronym', 'address', 'area',
+                           'article', 'aside', 'audio', 'b', 'big', 'blockquote', 'br', 'button',
+                           'canvas', 'caption', 'center', 'cite', 'code', 'col', 'colgroup',
+                           'command', 'datagrid', 'datalist', 'dd', 'del', 'details', 'dfn',
+                           'dialog', 'dir', 'div', 'dl', 'dt', 'em', 'event-source', 'fieldset',
+                           'figcaption', 'figure', 'footer', 'font', 'form', 'header', 'h1',
+                           'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i', 'img', 'input', 'ins',
+                           'keygen', 'kbd', 'label', 'legend', 'li', 'm', 'map', 'menu', 'meter',
+                           'multicol', 'nav', 'nextid', 'ol', 'output', 'optgroup', 'option',
+                           'p', 'pre', 'progress', 'q', 's', 'samp', 'section', 'select',
+                           'small', 'sound', 'source', 'spacer', 'span', 'strike', 'strong',
+                           'sub', 'sup', 'table', 'tbody', 'td', 'textarea', 'time', 'tfoot',
+                           'th', 'thead', 'tr', 'tt', 'u', 'ul', 'var', 'video']
+
+    mathml_elements = ['maction', 'math', 'merror', 'mfrac', 'mi',
+                       'mmultiscripts', 'mn', 'mo', 'mover', 'mpadded', 'mphantom',
+                       'mprescripts', 'mroot', 'mrow', 'mspace', 'msqrt', 'mstyle', 'msub',
+                       'msubsup', 'msup', 'mtable', 'mtd', 'mtext', 'mtr', 'munder',
+                       'munderover', 'none']
+
+    svg_elements = ['a', 'animate', 'animateColor', 'animateMotion',
+                    'animateTransform', 'clipPath', 'circle', 'defs', 'desc', 'ellipse',
+                    'font-face', 'font-face-name', 'font-face-src', 'g', 'glyph', 'hkern',
+                    'linearGradient', 'line', 'marker', 'metadata', 'missing-glyph',
+                    'mpath', 'path', 'polygon', 'polyline', 'radialGradient', 'rect',
+                    'set', 'stop', 'svg', 'switch', 'text', 'title', 'tspan', 'use']
+
+    acceptable_attributes = ['abbr', 'accept', 'accept-charset', 'accesskey',
+                             'action', 'align', 'alt', 'autocomplete', 'autofocus', 'axis',
+                             'background', 'balance', 'bgcolor', 'bgproperties', 'border',
+                             'bordercolor', 'bordercolordark', 'bordercolorlight', 'bottompadding',
+                             'cellpadding', 'cellspacing', 'ch', 'challenge', 'char', 'charoff',
+                             'choff', 'charset', 'checked', 'cite', 'class', 'clear', 'color',
+                             'cols', 'colspan', 'compact', 'contenteditable', 'controls', 'coords',
+                             'data', 'datafld', 'datapagesize', 'datasrc', 'datetime', 'default',
+                             'delay', 'dir', 'disabled', 'draggable', 'dynsrc', 'enctype', 'end',
+                             'face', 'for', 'form', 'frame', 'galleryimg', 'gutter', 'headers',
+                             'height', 'hidefocus', 'hidden', 'high', 'href', 'hreflang', 'hspace',
+                             'icon', 'id', 'inputmode', 'ismap', 'keytype', 'label', 'leftspacing',
+                             'lang', 'list', 'longdesc', 'loop', 'loopcount', 'loopend',
+                             'loopstart', 'low', 'lowsrc', 'max', 'maxlength', 'media', 'method',
+                             'min', 'multiple', 'name', 'nohref', 'noshade', 'nowrap', 'open',
+                             'optimum', 'pattern', 'ping', 'point-size', 'poster', 'pqg', 'preload',
+                             'prompt', 'radiogroup', 'readonly', 'rel', 'repeat-max', 'repeat-min',
+                             'replace', 'required', 'rev', 'rightspacing', 'rows', 'rowspan',
+                             'rules', 'scope', 'selected', 'shape', 'size', 'span', 'src', 'start',
+                             'step', 'style', 'summary', 'suppress', 'tabindex', 'target',
+                             'template', 'title', 'toppadding', 'type', 'unselectable', 'usemap',
+                             'urn', 'valign', 'value', 'variable', 'volume', 'vspace', 'vrml',
+                             'width', 'wrap', 'xml:lang']
+
+    mathml_attributes = ['actiontype', 'align', 'columnalign', 'columnalign',
+                         'columnalign', 'columnlines', 'columnspacing', 'columnspan', 'depth',
+                         'display', 'displaystyle', 'equalcolumns', 'equalrows', 'fence',
+                         'fontstyle', 'fontweight', 'frame', 'height', 'linethickness', 'lspace',
+                         'mathbackground', 'mathcolor', 'mathvariant', 'mathvariant', 'maxsize',
+                         'minsize', 'other', 'rowalign', 'rowalign', 'rowalign', 'rowlines',
+                         'rowspacing', 'rowspan', 'rspace', 'scriptlevel', 'selection',
+                         'separator', 'stretchy', 'width', 'width', 'xlink:href', 'xlink:show',
+                         'xlink:type', 'xmlns', 'xmlns:xlink']
+
+    svg_attributes = ['accent-height', 'accumulate', 'additive', 'alphabetic',
+                      'arabic-form', 'ascent', 'attributeName', 'attributeType',
+                      'baseProfile', 'bbox', 'begin', 'by', 'calcMode', 'cap-height',
+                      'class', 'clip-path', 'color', 'color-rendering', 'content', 'cx',
+                      'cy', 'd', 'dx', 'dy', 'descent', 'display', 'dur', 'end', 'fill',
+                      'fill-opacity', 'fill-rule', 'font-family', 'font-size',
+                      'font-stretch', 'font-style', 'font-variant', 'font-weight', 'from',
+                      'fx', 'fy', 'g1', 'g2', 'glyph-name', 'gradientUnits', 'hanging',
+                      'height', 'horiz-adv-x', 'horiz-origin-x', 'id', 'ideographic', 'k',
+                      'keyPoints', 'keySplines', 'keyTimes', 'lang', 'marker-end',
+                      'marker-mid', 'marker-start', 'markerHeight', 'markerUnits',
+                      'markerWidth', 'mathematical', 'max', 'min', 'name', 'offset',
+                      'opacity', 'orient', 'origin', 'overline-position',
+                      'overline-thickness', 'panose-1', 'path', 'pathLength', 'points',
+                      'preserveAspectRatio', 'r', 'refX', 'refY', 'repeatCount',
+                      'repeatDur', 'requiredExtensions', 'requiredFeatures', 'restart',
+                      'rotate', 'rx', 'ry', 'slope', 'stemh', 'stemv', 'stop-color',
+                      'stop-opacity', 'strikethrough-position', 'strikethrough-thickness',
+                      'stroke', 'stroke-dasharray', 'stroke-dashoffset', 'stroke-linecap',
+                      'stroke-linejoin', 'stroke-miterlimit', 'stroke-opacity',
+                      'stroke-width', 'systemLanguage', 'target', 'text-anchor', 'to',
+                      'transform', 'type', 'u1', 'u2', 'underline-position',
+                      'underline-thickness', 'unicode', 'unicode-range', 'units-per-em',
+                      'values', 'version', 'viewBox', 'visibility', 'width', 'widths', 'x',
+                      'x-height', 'x1', 'x2', 'xlink:actuate', 'xlink:arcrole',
+                      'xlink:href', 'xlink:role', 'xlink:show', 'xlink:title', 'xlink:type',
+                      'xml:base', 'xml:lang', 'xml:space', 'xmlns', 'xmlns:xlink', 'y',
+                      'y1', 'y2', 'zoomAndPan']
+
+    attr_val_is_uri = ['href', 'src', 'cite', 'action', 'longdesc', 'poster',
+                       'xlink:href', 'xml:base']
+
+    svg_attr_val_allows_ref = ['clip-path', 'color-profile', 'cursor', 'fill',
+                               'filter', 'marker', 'marker-start', 'marker-mid', 'marker-end',
+                               'mask', 'stroke']
+
+    svg_allow_local_href = ['altGlyph', 'animate', 'animateColor',
+                            'animateMotion', 'animateTransform', 'cursor', 'feImage', 'filter',
+                            'linearGradient', 'pattern', 'radialGradient', 'textpath', 'tref',
+                            'set', 'use']
+
+    acceptable_css_properties = ['azimuth', 'background-color',
+                                 'border-bottom-color', 'border-collapse', 'border-color',
+                                 'border-left-color', 'border-right-color', 'border-top-color', 'clear',
+                                 'color', 'cursor', 'direction', 'display', 'elevation', 'float', 'font',
+                                 'font-family', 'font-size', 'font-style', 'font-variant', 'font-weight',
+                                 'height', 'letter-spacing', 'line-height', 'overflow', 'pause',
+                                 'pause-after', 'pause-before', 'pitch', 'pitch-range', 'richness',
+                                 'speak', 'speak-header', 'speak-numeral', 'speak-punctuation',
+                                 'speech-rate', 'stress', 'text-align', 'text-decoration', 'text-indent',
+                                 'unicode-bidi', 'vertical-align', 'voice-family', 'volume',
+                                 'white-space', 'width']
+
+    acceptable_css_keywords = ['auto', 'aqua', 'black', 'block', 'blue',
+                               'bold', 'both', 'bottom', 'brown', 'center', 'collapse', 'dashed',
+                               'dotted', 'fuchsia', 'gray', 'green', '!important', 'italic', 'left',
+                               'lime', 'maroon', 'medium', 'none', 'navy', 'normal', 'nowrap', 'olive',
+                               'pointer', 'purple', 'red', 'right', 'solid', 'silver', 'teal', 'top',
+                               'transparent', 'underline', 'white', 'yellow']
+
+    acceptable_svg_properties = ['fill', 'fill-opacity', 'fill-rule',
+                                 'stroke', 'stroke-width', 'stroke-linecap', 'stroke-linejoin',
+                                 'stroke-opacity']
+
+    acceptable_protocols = ['ed2k', 'ftp', 'http', 'https', 'irc',
+                            'mailto', 'news', 'gopher', 'nntp', 'telnet', 'webcal',
+                            'xmpp', 'callto', 'feed', 'urn', 'aim', 'rsync', 'tag',
+                            'ssh', 'sftp', 'rtsp', 'afs']
+
+    # subclasses may define their own versions of these constants
+    allowed_elements = acceptable_elements + mathml_elements + svg_elements
+    allowed_attributes = acceptable_attributes + mathml_attributes + svg_attributes
+    allowed_css_properties = acceptable_css_properties
+    allowed_css_keywords = acceptable_css_keywords
+    allowed_svg_properties = acceptable_svg_properties
+    allowed_protocols = acceptable_protocols
+
+    # Sanitize the +html+, escaping all elements not in ALLOWED_ELEMENTS, and
+    # stripping out all # attributes not in ALLOWED_ATTRIBUTES. Style
+    # attributes are parsed, and a restricted set, # specified by
+    # ALLOWED_CSS_PROPERTIES and ALLOWED_CSS_KEYWORDS, are allowed through.
+    # attributes in ATTR_VAL_IS_URI are scanned, and only URI schemes specified
+    # in ALLOWED_PROTOCOLS are allowed.
+    #
+    #   sanitize_html('<script> do_nasty_stuff() </script>')
+    #    => &lt;script> do_nasty_stuff() &lt;/script>
+    #   sanitize_html('<a href="javascript: sucker();">Click here for $100</a>')
+    #    => <a>Click here for $100</a>
+    def sanitize_token(self, token):
+
+        # accommodate filters which use token_type differently
+        token_type = token["type"]
+        if token_type in list(tokenTypes.keys()):
+            token_type = tokenTypes[token_type]
+
+        if token_type in (tokenTypes["StartTag"], tokenTypes["EndTag"],
+                          tokenTypes["EmptyTag"]):
+            if token["name"] in self.allowed_elements:
+                return self.allowed_token(token, token_type)
+            else:
+                return self.disallowed_token(token, token_type)
+        elif token_type == tokenTypes["Comment"]:
+            pass
+        else:
+            return token
+
+    def allowed_token(self, token, token_type):
+        if "data" in token:
+            attrs = dict([(name, val) for name, val in
+                          token["data"][::-1]
+                          if name in self.allowed_attributes])
+            for attr in self.attr_val_is_uri:
+                if attr not in attrs:
+                    continue
+                val_unescaped = re.sub("[`\000-\040\177-\240\s]+", '',
+                                       unescape(attrs[attr])).lower()
+                # remove replacement characters from unescaped characters
+                val_unescaped = val_unescaped.replace("\ufffd", "")
+                if (re.match("^[a-z0-9][-+.a-z0-9]*:", val_unescaped) and
+                    (val_unescaped.split(':')[0] not in
+                     self.allowed_protocols)):
+                    del attrs[attr]
+            for attr in self.svg_attr_val_allows_ref:
+                if attr in attrs:
+                    attrs[attr] = re.sub(r'url\s*\(\s*[^#\s][^)]+?\)',
+                                         ' ',
+                                         unescape(attrs[attr]))
+            if (token["name"] in self.svg_allow_local_href and
+                'xlink:href' in attrs and re.search('^\s*[^#\s].*',
+                                                    attrs['xlink:href'])):
+                del attrs['xlink:href']
+            if 'style' in attrs:
+                attrs['style'] = self.sanitize_css(attrs['style'])
+            token["data"] = [[name, val] for name, val in list(attrs.items())]
+        return token
+
+    def disallowed_token(self, token, token_type):
+        if token_type == tokenTypes["EndTag"]:
+            token["data"] = "</%s>" % token["name"]
+        elif token["data"]:
+            attrs = ''.join([' %s="%s"' % (k, escape(v)) for k, v in token["data"]])
+            token["data"] = "<%s%s>" % (token["name"], attrs)
+        else:
+            token["data"] = "<%s>" % token["name"]
+        if token.get("selfClosing"):
+            token["data"] = token["data"][:-1] + "/>"
+
+        if token["type"] in list(tokenTypes.keys()):
+            token["type"] = "Characters"
+        else:
+            token["type"] = tokenTypes["Characters"]
+
+        del token["name"]
+        return token
+
+    def sanitize_css(self, style):
+        # disallow urls
+        style = re.compile('url\s*\(\s*[^\s)]+?\s*\)\s*').sub(' ', style)
+
+        # gauntlet
+        if not re.match("""^([:,;#%.\sa-zA-Z0-9!]|\w-\w|'[\s\w]+'|"[\s\w]+"|\([\d,\s]+\))*$""", style):
+            return ''
+        if not re.match("^\s*([-\w]+\s*:[^:;]*(;\s*|$))*$", style):
+            return ''
+
+        clean = []
+        for prop, value in re.findall("([-\w]+)\s*:\s*([^:;]*)", style):
+            if not value:
+                continue
+            if prop.lower() in self.allowed_css_properties:
+                clean.append(prop + ': ' + value + ';')
+            elif prop.split('-')[0].lower() in ['background', 'border', 'margin',
+                                                'padding']:
+                for keyword in value.split():
+                    if not keyword in self.acceptable_css_keywords and \
+                            not re.match("^(#[0-9a-f]+|rgb\(\d+%?,\d*%?,?\d*%?\)?|\d{0,2}\.?\d{0,2}(cm|em|ex|in|mm|pc|pt|px|%|,|\))?)$", keyword):
+                        break
+                else:
+                    clean.append(prop + ': ' + value + ';')
+            elif prop.lower() in self.allowed_svg_properties:
+                clean.append(prop + ': ' + value + ';')
+
+        return ' '.join(clean)
+
+
+class HTMLSanitizer(HTMLTokenizer, HTMLSanitizerMixin):
+    def __init__(self, stream, encoding=None, parseMeta=True, useChardet=True,
+                 lowercaseElementName=False, lowercaseAttrName=False, parser=None):
+        # Change case matching defaults as we only output lowercase html anyway
+        # This solution doesn't seem ideal...
+        HTMLTokenizer.__init__(self, stream, encoding, parseMeta, useChardet,
+                               lowercaseElementName, lowercaseAttrName, parser=parser)
+
+    def __iter__(self):
+        for token in HTMLTokenizer.__iter__(self):
+            token = self.sanitize_token(token)
+            if token:
+                yield token

package/python3.4.2/lib/python3.4/site-packages/pip/_vendor/html5lib/serializer/__init__.py

@@ -0,0 +1,16 @@
+from __future__ import absolute_import, division, unicode_literals
+
+from .. import treewalkers
+
+from .htmlserializer import HTMLSerializer
+
+
+def serialize(input, tree="etree", format="html", encoding=None,
+              **serializer_opts):
+    # XXX: Should we cache this?
+    walker = treewalkers.getTreeWalker(tree)
+    if format == "html":
+        s = HTMLSerializer(**serializer_opts)
+    else:
+        raise ValueError("type must be html")
+    return s.render(walker(input), encoding)

package/python3.4.2/lib/python3.4/site-packages/pip/_vendor/html5lib/serializer/htmlserializer.py

@@ -0,0 +1,320 @@
+from __future__ import absolute_import, division, unicode_literals
+from pip._vendor.six import text_type
+
+import gettext
+_ = gettext.gettext
+
+try:
+    from functools import reduce
+except ImportError:
+    pass
+
+from ..constants import voidElements, booleanAttributes, spaceCharacters
+from ..constants import rcdataElements, entities, xmlEntities
+from .. import utils
+from xml.sax.saxutils import escape
+
+spaceCharacters = "".join(spaceCharacters)
+
+try:
+    from codecs import register_error, xmlcharrefreplace_errors
+except ImportError:
+    unicode_encode_errors = "strict"
+else:
+    unicode_encode_errors = "htmlentityreplace"
+
+    encode_entity_map = {}
+    is_ucs4 = len("\U0010FFFF") == 1
+    for k, v in list(entities.items()):
+        # skip multi-character entities
+        if ((is_ucs4 and len(v) > 1) or
+                (not is_ucs4 and len(v) > 2)):
+            continue
+        if v != "&":
+            if len(v) == 2:
+                v = utils.surrogatePairToCodepoint(v)
+            else:
+                v = ord(v)
+            if not v in encode_entity_map or k.islower():
+                # prefer < over < and similarly for &, >, etc.
+                encode_entity_map[v] = k
+
+    def htmlentityreplace_errors(exc):
+        if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
+            res = []
+            codepoints = []
+            skip = False
+            for i, c in enumerate(exc.object[exc.start:exc.end]):
+                if skip:
+                    skip = False
+                    continue
+                index = i + exc.start
+                if utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
+                    codepoint = utils.surrogatePairToCodepoint(exc.object[index:index + 2])
+                    skip = True
+                else:
+                    codepoint = ord(c)
+                codepoints.append(codepoint)
+            for cp in codepoints:
+                e = encode_entity_map.get(cp)
+                if e:
+                    res.append("&")
+                    res.append(e)
+                    if not e.endswith(";"):
+                        res.append(";")
+                else:
+                    res.append("&#x%s;" % (hex(cp)[2:]))
+            return ("".join(res), exc.end)
+        else:
+            return xmlcharrefreplace_errors(exc)
+
+    register_error(unicode_encode_errors, htmlentityreplace_errors)
+
+    del register_error
+
+
+class HTMLSerializer(object):
+
+    # attribute quoting options
+    quote_attr_values = False
+    quote_char = '"'
+    use_best_quote_char = True
+
+    # tag syntax options
+    omit_optional_tags = True
+    minimize_boolean_attributes = True
+    use_trailing_solidus = False
+    space_before_trailing_solidus = True
+
+    # escaping options
+    escape_lt_in_attrs = False
+    escape_rcdata = False
+    resolve_entities = True
+
+    # miscellaneous options
+    alphabetical_attributes = False
+    inject_meta_charset = True
+    strip_whitespace = False
+    sanitize = False
+
+    options = ("quote_attr_values", "quote_char", "use_best_quote_char",
+               "omit_optional_tags", "minimize_boolean_attributes",
+               "use_trailing_solidus", "space_before_trailing_solidus",
+               "escape_lt_in_attrs", "escape_rcdata", "resolve_entities",
+               "alphabetical_attributes", "inject_meta_charset",
+               "strip_whitespace", "sanitize")
+
+    def __init__(self, **kwargs):
+        """Initialize HTMLSerializer.
+
+        Keyword options (default given first unless specified) include:
+
+        inject_meta_charset=True|False
+          Whether it insert a meta element to define the character set of the
+          document.
+        quote_attr_values=True|False
+          Whether to quote attribute values that don't require quoting
+          per HTML5 parsing rules.
+        quote_char=u'"'|u"'"
+          Use given quote character for attribute quoting. Default is to
+          use double quote unless attribute value contains a double quote,
+          in which case single quotes are used instead.
+        escape_lt_in_attrs=False|True
+          Whether to escape < in attribute values.
+        escape_rcdata=False|True
+          Whether to escape characters that need to be escaped within normal
+          elements within rcdata elements such as style.
+        resolve_entities=True|False
+          Whether to resolve named character entities that appear in the
+          source tree. The XML predefined entities &lt; &gt; &amp; &quot; &apos;
+          are unaffected by this setting.
+        strip_whitespace=False|True
+          Whether to remove semantically meaningless whitespace. (This
+          compresses all whitespace to a single space except within pre.)
+        minimize_boolean_attributes=True|False
+          Shortens boolean attributes to give just the attribute value,
+          for example <input disabled="disabled"> becomes <input disabled>.
+        use_trailing_solidus=False|True
+          Includes a close-tag slash at the end of the start tag of void
+          elements (empty elements whose end tag is forbidden). E.g. <hr/>.
+        space_before_trailing_solidus=True|False
+          Places a space immediately before the closing slash in a tag
+          using a trailing solidus. E.g. <hr />. Requires use_trailing_solidus.
+        sanitize=False|True
+          Strip all unsafe or unknown constructs from output.
+          See `html5lib user documentation`_
+        omit_optional_tags=True|False
+          Omit start/end tags that are optional.
+        alphabetical_attributes=False|True
+          Reorder attributes to be in alphabetical order.
+
+        .. _html5lib user documentation: http://code.google.com/p/html5lib/wiki/UserDocumentation
+        """
+        if 'quote_char' in kwargs:
+            self.use_best_quote_char = False
+        for attr in self.options:
+            setattr(self, attr, kwargs.get(attr, getattr(self, attr)))
+        self.errors = []
+        self.strict = False
+
+    def encode(self, string):
+        assert(isinstance(string, text_type))
+        if self.encoding:
+            return string.encode(self.encoding, unicode_encode_errors)
+        else:
+            return string
+
+    def encodeStrict(self, string):
+        assert(isinstance(string, text_type))
+        if self.encoding:
+            return string.encode(self.encoding, "strict")
+        else:
+            return string
+
+    def serialize(self, treewalker, encoding=None):
+        self.encoding = encoding
+        in_cdata = False
+        self.errors = []
+
+        if encoding and self.inject_meta_charset:
+            from ..filters.inject_meta_charset import Filter
+            treewalker = Filter(treewalker, encoding)
+        # WhitespaceFilter should be used before OptionalTagFilter
+        # for maximum efficiently of this latter filter
+        if self.strip_whitespace:
+            from ..filters.whitespace import Filter
+            treewalker = Filter(treewalker)
+        if self.sanitize:
+            from ..filters.sanitizer import Filter
+            treewalker = Filter(treewalker)
+        if self.omit_optional_tags:
+            from ..filters.optionaltags import Filter
+            treewalker = Filter(treewalker)
+        # Alphabetical attributes must be last, as other filters
+        # could add attributes and alter the order
+        if self.alphabetical_attributes:
+            from ..filters.alphabeticalattributes import Filter
+            treewalker = Filter(treewalker)
+
+        for token in treewalker:
+            type = token["type"]
+            if type == "Doctype":
+                doctype = "<!DOCTYPE %s" % token["name"]
+
+                if token["publicId"]:
+                    doctype += ' PUBLIC "%s"' % token["publicId"]
+                elif token["systemId"]:
+                    doctype += " SYSTEM"
+                if token["systemId"]:
+                    if token["systemId"].find('"') >= 0:
+                        if token["systemId"].find("'") >= 0:
+                            self.serializeError(_("System identifer contains both single and double quote characters"))
+                        quote_char = "'"
+                    else:
+                        quote_char = '"'
+                    doctype += " %s%s%s" % (quote_char, token["systemId"], quote_char)
+
+                doctype += ">"
+                yield self.encodeStrict(doctype)
+
+            elif type in ("Characters", "SpaceCharacters"):
+                if type == "SpaceCharacters" or in_cdata:
+                    if in_cdata and token["data"].find("</") >= 0:
+                        self.serializeError(_("Unexpected </ in CDATA"))
+                    yield self.encode(token["data"])
+                else:
+                    yield self.encode(escape(token["data"]))
+
+            elif type in ("StartTag", "EmptyTag"):
+                name = token["name"]
+                yield self.encodeStrict("<%s" % name)
+                if name in rcdataElements and not self.escape_rcdata:
+                    in_cdata = True
+                elif in_cdata:
+                    self.serializeError(_("Unexpected child element of a CDATA element"))
+                for (attr_namespace, attr_name), attr_value in token["data"].items():
+                    # TODO: Add namespace support here
+                    k = attr_name
+                    v = attr_value
+                    yield self.encodeStrict(' ')
+
+                    yield self.encodeStrict(k)
+                    if not self.minimize_boolean_attributes or \
+                        (k not in booleanAttributes.get(name, tuple())
+                         and k not in booleanAttributes.get("", tuple())):
+                        yield self.encodeStrict("=")
+                        if self.quote_attr_values or not v:
+                            quote_attr = True
+                        else:
+                            quote_attr = reduce(lambda x, y: x or (y in v),
+                                                spaceCharacters + ">\"'=", False)
+                        v = v.replace("&", "&amp;")
+                        if self.escape_lt_in_attrs:
+                            v = v.replace("<", "&lt;")
+                        if quote_attr:
+                            quote_char = self.quote_char
+                            if self.use_best_quote_char:
+                                if "'" in v and '"' not in v:
+                                    quote_char = '"'
+                                elif '"' in v and "'" not in v:
+                                    quote_char = "'"
+                            if quote_char == "'":
+                                v = v.replace("'", "&#39;")
+                            else:
+                                v = v.replace('"', "&quot;")
+                            yield self.encodeStrict(quote_char)
+                            yield self.encode(v)
+                            yield self.encodeStrict(quote_char)
+                        else:
+                            yield self.encode(v)
+                if name in voidElements and self.use_trailing_solidus:
+                    if self.space_before_trailing_solidus:
+                        yield self.encodeStrict(" /")
+                    else:
+                        yield self.encodeStrict("/")
+                yield self.encode(">")
+
+            elif type == "EndTag":
+                name = token["name"]
+                if name in rcdataElements:
+                    in_cdata = False
+                elif in_cdata:
+                    self.serializeError(_("Unexpected child element of a CDATA element"))
+                yield self.encodeStrict("</%s>" % name)
+
+            elif type == "Comment":
+                data = token["data"]
+                if data.find("--") >= 0:
+                    self.serializeError(_("Comment contains --"))
+                yield self.encodeStrict("<!--%s-->" % token["data"])
+
+            elif type == "Entity":
+                name = token["name"]
+                key = name + ";"
+                if not key in entities:
+                    self.serializeError(_("Entity %s not recognized" % name))
+                if self.resolve_entities and key not in xmlEntities:
+                    data = entities[key]
+                else:
+                    data = "&%s;" % name
+                yield self.encodeStrict(data)
+
+            else:
+                self.serializeError(token["data"])
+
+    def render(self, treewalker, encoding=None):
+        if encoding:
+            return b"".join(list(self.serialize(treewalker, encoding)))
+        else:
+            return "".join(list(self.serialize(treewalker)))
+
+    def serializeError(self, data="XXX ERROR MESSAGE NEEDED"):
+        # XXX The idea is to make data mandatory.
+        self.errors.append(data)
+        if self.strict:
+            raise SerializeError
+
+
+def SerializeError(Exception):
+    """Error in serialized tree"""
+    pass