PyPI - quarchpy - Versions diffs - 2.1.13.dev1__py2.py3-none-any.whl → 2.1.14__py2.py3-none-any.whl - Mend

quarchpy 2.1.13.dev1py2.py3-none-any.whl → 2.1.14py2.py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (837) hide show

quarchpy/venv/Lib/site-packages/pip/_vendor/html5lib/serializer.py ADDED Viewed

@@ -0,0 +1,409 @@
+from __future__ import absolute_import, division, unicode_literals
+from pip._vendor.six import text_type
+import re
+from codecs import register_error, xmlcharrefreplace_errors
+from .constants import voidElements, booleanAttributes, spaceCharacters
+from .constants import rcdataElements, entities, xmlEntities
+from . import treewalkers, _utils
+from xml.sax.saxutils import escape
+_quoteAttributeSpecChars = "".join(spaceCharacters) + "\"'=<>`"
+_quoteAttributeSpec = re.compile("[" + _quoteAttributeSpecChars + "]")
+_quoteAttributeLegacy = re.compile("[" + _quoteAttributeSpecChars +
+                                   "\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n"
+                                   "\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15"
+                                   "\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+                                   "\x20\x2f\x60\xa0\u1680\u180e\u180f\u2000"
+                                   "\u2001\u2002\u2003\u2004\u2005\u2006\u2007"
+                                   "\u2008\u2009\u200a\u2028\u2029\u202f\u205f"
+                                   "\u3000]")
+_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 v not in _encode_entity_map or k.islower():
+            # prefer &lt; over &LT; and similarly for &amp;, &gt;, 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("htmlentityreplace", htmlentityreplace_errors)
+def serialize(input, tree="etree", encoding=None, **serializer_opts):
+    """Serializes the input token stream using the specified treewalker
+    :arg input: the token stream to serialize
+    :arg tree: the treewalker to use
+    :arg encoding: the encoding to use
+    :arg serializer_opts: any options to pass to the
+        :py:class:`html5lib.serializer.HTMLSerializer` that gets created
+    :returns: the tree serialized as a string
+    Example:
+    >>> from html5lib.html5parser import parse
+    >>> from html5lib.serializer import serialize
+    >>> token_stream = parse('<html><body><p>Hi!</p></body></html>')
+    >>> serialize(token_stream, omit_optional_tags=False)
+    '<html><head></head><body><p>Hi!</p></body></html>'
+    """
+    # XXX: Should we cache this?
+    walker = treewalkers.getTreeWalker(tree)
+    s = HTMLSerializer(**serializer_opts)
+    return s.render(walker(input), encoding)
+class HTMLSerializer(object):
+    # attribute quoting options
+    quote_attr_values = "legacy"  # be secure by default
+    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
+        :arg inject_meta_charset: Whether or not to inject the meta charset.
+            Defaults to ``True``.
+        :arg quote_attr_values: Whether to quote attribute values that don't
+            require quoting per legacy browser behavior (``"legacy"``), when
+            required by the standard (``"spec"``), or always (``"always"``).
+            Defaults to ``"legacy"``.
+        :arg quote_char: Use given quote character for attribute quoting.
+            Defaults to ``"`` which will use double quotes unless attribute
+            value contains a double quote, in which case single quotes are
+            used.
+        :arg escape_lt_in_attrs: Whether or not to escape ``<`` in attribute
+            values.
+            Defaults to ``False``.
+        :arg escape_rcdata: Whether to escape characters that need to be
+            escaped within normal elements within rcdata elements such as
+            style.
+            Defaults to ``False``.
+        :arg resolve_entities: 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.
+            Defaults to ``True``.
+        :arg strip_whitespace: Whether to remove semantically meaningless
+            whitespace. (This compresses all whitespace to a single space
+            except within ``pre``.)
+            Defaults to ``False``.
+        :arg minimize_boolean_attributes: Shortens boolean attributes to give
+            just the attribute value, for example::
+              <input disabled="disabled">
+            becomes::
+              <input disabled>
+            Defaults to ``True``.
+        :arg use_trailing_solidus: 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/>``.
+            Defaults to ``False``.
+        :arg space_before_trailing_solidus: Places a space immediately before
+            the closing slash in a tag using a trailing solidus. E.g.
+            ``<hr />``. Requires ``use_trailing_solidus=True``.
+            Defaults to ``True``.
+        :arg sanitize: Strip all unsafe or unknown constructs from output.
+            See :py:class:`html5lib.filters.sanitizer.Filter`.
+            Defaults to ``False``.
+        :arg omit_optional_tags: Omit start/end tags that are optional.
+            Defaults to ``True``.
+        :arg alphabetical_attributes: Reorder attributes to be in alphabetical order.
+            Defaults to ``False``.
+        """
+        unexpected_args = frozenset(kwargs) - frozenset(self.options)
+        if len(unexpected_args) > 0:
+            raise TypeError("__init__() got an unexpected keyword argument '%s'" % next(iter(unexpected_args)))
+        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, "htmlentityreplace")
+        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):
+        # pylint:disable=too-many-nested-blocks
+        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)
+        # Alphabetical attributes is here under the assumption that none of
+        # the later filters add or change order of attributes; it needs to be
+        # before the sanitizer so escaped elements come out correctly
+        if self.alphabetical_attributes:
+            from .filters.alphabeticalattributes import Filter
+            treewalker = Filter(treewalker)
+        # 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)
+        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 identifier 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_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 == "always" or len(v) == 0:
+                            quote_attr = True
+                        elif self.quote_attr_values == "spec":
+                            quote_attr = _quoteAttributeSpec.search(v) is not None
+                        elif self.quote_attr_values == "legacy":
+                            quote_attr = _quoteAttributeLegacy.search(v) is not None
+                        else:
+                            raise ValueError("quote_attr_values must be one of: "
+                                             "'always', 'spec', or 'legacy'")
+                        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 key not 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):
+        """Serializes the stream from the treewalker into a string
+        :arg treewalker: the treewalker to serialize
+        :arg encoding: the string encoding to use
+        :returns: the serialized tree
+        Example:
+        >>> from html5lib import parse, getTreeWalker
+        >>> from html5lib.serializer import HTMLSerializer
+        >>> token_stream = parse('<html><body>Hi!</body></html>')
+        >>> walker = getTreeWalker('etree')
+        >>> serializer = HTMLSerializer(omit_optional_tags=False)
+        >>> serializer.render(walker(token_stream))
+        '<html><head></head><body>Hi!</body></html>'
+        """
+        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
+class SerializeError(Exception):
+    """Error in serialized tree"""
+    pass

quarchpy/venv/Lib/site-packages/pip/_vendor/html5lib/treeadapters/__init__.py ADDED Viewed

@@ -0,0 +1,30 @@
+"""Tree adapters let you convert from one tree structure to another
+Example:
+.. code-block:: python
+   from pip._vendor import html5lib
+   from pip._vendor.html5lib.treeadapters import genshi
+   doc = '<html><body>Hi!</body></html>'
+   treebuilder = html5lib.getTreeBuilder('etree')
+   parser = html5lib.HTMLParser(tree=treebuilder)
+   tree = parser.parse(doc)
+   TreeWalker = html5lib.getTreeWalker('etree')
+   genshi_tree = genshi.to_genshi(TreeWalker(tree))
+"""
+from __future__ import absolute_import, division, unicode_literals
+from . import sax
+__all__ = ["sax"]
+try:
+    from . import genshi  # noqa
+except ImportError:
+    pass
+else:
+    __all__.append("genshi")

quarchpy/venv/Lib/site-packages/pip/_vendor/html5lib/treeadapters/genshi.py ADDED Viewed

@@ -0,0 +1,54 @@
+from __future__ import absolute_import, division, unicode_literals
+from genshi.core import QName, Attrs
+from genshi.core import START, END, TEXT, COMMENT, DOCTYPE
+def to_genshi(walker):
+    """Convert a tree to a genshi tree
+    :arg walker: the treewalker to use to walk the tree to convert it
+    :returns: generator of genshi nodes
+    """
+    text = []
+    for token in walker:
+        type = token["type"]
+        if type in ("Characters", "SpaceCharacters"):
+            text.append(token["data"])
+        elif text:
+            yield TEXT, "".join(text), (None, -1, -1)
+            text = []
+        if type in ("StartTag", "EmptyTag"):
+            if token["namespace"]:
+                name = "{%s}%s" % (token["namespace"], token["name"])
+            else:
+                name = token["name"]
+            attrs = Attrs([(QName("{%s}%s" % attr if attr[0] is not None else attr[1]), value)
+                           for attr, value in token["data"].items()])
+            yield (START, (QName(name), attrs), (None, -1, -1))
+            if type == "EmptyTag":
+                type = "EndTag"
+        if type == "EndTag":
+            if token["namespace"]:
+                name = "{%s}%s" % (token["namespace"], token["name"])
+            else:
+                name = token["name"]
+            yield END, QName(name), (None, -1, -1)
+        elif type == "Comment":
+            yield COMMENT, token["data"], (None, -1, -1)
+        elif type == "Doctype":
+            yield DOCTYPE, (token["name"], token["publicId"],
+                            token["systemId"]), (None, -1, -1)
+        else:
+            pass  # FIXME: What to do?
+    if text:
+        yield TEXT, "".join(text), (None, -1, -1)

quarchpy/venv/Lib/site-packages/pip/_vendor/html5lib/treeadapters/sax.py ADDED Viewed

@@ -0,0 +1,50 @@
+from __future__ import absolute_import, division, unicode_literals
+from xml.sax.xmlreader import AttributesNSImpl
+from ..constants import adjustForeignAttributes, unadjustForeignAttributes
+prefix_mapping = {}
+for prefix, localName, namespace in adjustForeignAttributes.values():
+    if prefix is not None:
+        prefix_mapping[prefix] = namespace
+def to_sax(walker, handler):
+    """Call SAX-like content handler based on treewalker walker
+    :arg walker: the treewalker to use to walk the tree to convert it
+    :arg handler: SAX handler to use
+    """
+    handler.startDocument()
+    for prefix, namespace in prefix_mapping.items():
+        handler.startPrefixMapping(prefix, namespace)
+    for token in walker:
+        type = token["type"]
+        if type == "Doctype":
+            continue
+        elif type in ("StartTag", "EmptyTag"):
+            attrs = AttributesNSImpl(token["data"],
+                                     unadjustForeignAttributes)
+            handler.startElementNS((token["namespace"], token["name"]),
+                                   token["name"],
+                                   attrs)
+            if type == "EmptyTag":
+                handler.endElementNS((token["namespace"], token["name"]),
+                                     token["name"])
+        elif type == "EndTag":
+            handler.endElementNS((token["namespace"], token["name"]),
+                                 token["name"])
+        elif type in ("Characters", "SpaceCharacters"):
+            handler.characters(token["data"])
+        elif type == "Comment":
+            pass
+        else:
+            assert False, "Unknown token type"
+    for prefix, namespace in prefix_mapping.items():
+        handler.endPrefixMapping(prefix)
+    handler.endDocument()

quarchpy/venv/Lib/site-packages/pip/_vendor/html5lib/treebuilders/__init__.py ADDED Viewed

@@ -0,0 +1,88 @@
+"""A collection of modules for building different kinds of trees from HTML
+documents.
+To create a treebuilder for a new type of tree, you need to do
+implement several things:
+1. A set of classes for various types of elements: Document, Doctype, Comment,
+   Element. These must implement the interface of ``base.treebuilders.Node``
+   (although comment nodes have a different signature for their constructor,
+   see ``treebuilders.etree.Comment``) Textual content may also be implemented
+   as another node type, or not, as your tree implementation requires.
+2. A treebuilder object (called ``TreeBuilder`` by convention) that inherits
+   from ``treebuilders.base.TreeBuilder``. This has 4 required attributes:
+   * ``documentClass`` - the class to use for the bottommost node of a document
+   * ``elementClass`` - the class to use for HTML Elements
+   * ``commentClass`` - the class to use for comments
+   * ``doctypeClass`` - the class to use for doctypes
+   It also has one required method:
+   * ``getDocument`` - Returns the root node of the complete document tree
+3. If you wish to run the unit tests, you must also create a ``testSerializer``
+   method on your treebuilder which accepts a node and returns a string
+   containing Node and its children serialized according to the format used in
+   the unittests
+"""
+from __future__ import absolute_import, division, unicode_literals
+from .._utils import default_etree
+treeBuilderCache = {}
+def getTreeBuilder(treeType, implementation=None, **kwargs):
+    """Get a TreeBuilder class for various types of trees with built-in support
+    :arg treeType: the name of the tree type required (case-insensitive). Supported
+        values are:
+        * "dom" - A generic builder for DOM implementations, defaulting to a
+          xml.dom.minidom based implementation.
+        * "etree" - A generic builder for tree implementations exposing an
+          ElementTree-like interface, defaulting to xml.etree.cElementTree if
+          available and xml.etree.ElementTree if not.
+        * "lxml" - A etree-based builder for lxml.etree, handling limitations
+          of lxml's implementation.
+    :arg implementation: (Currently applies to the "etree" and "dom" tree
+        types). A module implementing the tree type e.g. xml.etree.ElementTree
+        or xml.etree.cElementTree.
+    :arg kwargs: Any additional options to pass to the TreeBuilder when
+        creating it.
+    Example:
+    >>> from html5lib.treebuilders import getTreeBuilder
+    >>> builder = getTreeBuilder('etree')
+    """
+    treeType = treeType.lower()
+    if treeType not in treeBuilderCache:
+        if treeType == "dom":
+            from . import dom
+            # Come up with a sane default (pref. from the stdlib)
+            if implementation is None:
+                from xml.dom import minidom
+                implementation = minidom
+            # NEVER cache here, caching is done in the dom submodule
+            return dom.getDomModule(implementation, **kwargs).TreeBuilder
+        elif treeType == "lxml":
+            from . import etree_lxml
+            treeBuilderCache[treeType] = etree_lxml.TreeBuilder
+        elif treeType == "etree":
+            from . import etree
+            if implementation is None:
+                implementation = default_etree
+            # NEVER cache here, caching is done in the etree submodule
+            return etree.getETreeModule(implementation, **kwargs).TreeBuilder
+        else:
+            raise ValueError("""Unrecognised treebuilder "%s" """ % treeType)
+    return treeBuilderCache.get(treeType)

quarchpy 2.1.13.dev1__py2.py3-none-any.whl → 2.1.14__py2.py3-none-any.whl

quarchpy 2.1.13.dev1py2.py3-none-any.whl → 2.1.14py2.py3-none-any.whl