com.googler.python 1.0.7 → 1.0.9

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

@@ -1,20 +1,29 @@
-from __future__ import absolute_import, division, unicode_literals
-
-from . import _base
-
-try:
-    from collections import OrderedDict
-except ImportError:
-    from ordereddict import OrderedDict
-
-
-class Filter(_base.Filter):
-    def __iter__(self):
-        for token in _base.Filter.__iter__(self):
-            if token["type"] in ("StartTag", "EmptyTag"):
-                attrs = OrderedDict()
-                for name, value in sorted(token["data"].items(),
-                                          key=lambda x: x[0]):
-                    attrs[name] = value
-                token["data"] = attrs
-            yield token
+from __future__ import absolute_import, division, unicode_literals
+
+from . import base
+
+from collections import OrderedDict
+
+
+def _attr_key(attr):
+    """Return an appropriate key for an attribute for sorting
+
+    Attributes have a namespace that can be either ``None`` or a string. We
+    can't compare the two because they're different types, so we convert
+    ``None`` to an empty string first.
+
+    """
+    return (attr[0][0] or ''), attr[0][1]
+
+
+class Filter(base.Filter):
+    """Alphabetizes attributes for elements"""
+    def __iter__(self):
+        for token in base.Filter.__iter__(self):
+            if token["type"] in ("StartTag", "EmptyTag"):
+                attrs = OrderedDict()
+                for name, value in sorted(token["data"].items(),
+                                          key=_attr_key):
+                    attrs[name] = value
+                token["data"] = attrs
+            yield token

package/python3.4.2/lib/python3.4/site-packages/pip/_vendor/html5lib/filters/{_base.py → base.py}

@@ -1,12 +1,12 @@
-from __future__ import absolute_import, division, unicode_literals
-
-
-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)
+from __future__ import absolute_import, division, unicode_literals
+
+
+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)

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

@@ -1,65 +1,73 @@
-from __future__ import absolute_import, division, unicode_literals
-
-from . import _base
-
-
-class Filter(_base.Filter):
-    def __init__(self, source, encoding):
-        _base.Filter.__init__(self, source)
-        self.encoding = encoding
-
-    def __iter__(self):
-        state = "pre_head"
-        meta_found = (self.encoding is None)
-        pending = []
-
-        for token in _base.Filter.__iter__(self):
-            type = token["type"]
-            if type == "StartTag":
-                if token["name"].lower() == "head":
-                    state = "in_head"
-
-            elif type == "EmptyTag":
-                if token["name"].lower() == "meta":
-                    # replace charset with actual encoding
-                    has_http_equiv_content_type = False
-                    for (namespace, name), value in token["data"].items():
-                        if namespace is not None:
-                            continue
-                        elif name.lower() == 'charset':
-                            token["data"][(namespace, name)] = self.encoding
-                            meta_found = True
-                            break
-                        elif name == 'http-equiv' and value.lower() == 'content-type':
-                            has_http_equiv_content_type = True
-                    else:
-                        if has_http_equiv_content_type and (None, "content") in token["data"]:
-                            token["data"][(None, "content")] = 'text/html; charset=%s' % self.encoding
-                            meta_found = True
-
-                elif token["name"].lower() == "head" and not meta_found:
-                    # insert meta into empty head
-                    yield {"type": "StartTag", "name": "head",
-                           "data": token["data"]}
-                    yield {"type": "EmptyTag", "name": "meta",
-                           "data": {(None, "charset"): self.encoding}}
-                    yield {"type": "EndTag", "name": "head"}
-                    meta_found = True
-                    continue
-
-            elif type == "EndTag":
-                if token["name"].lower() == "head" and pending:
-                    # insert meta into head (if necessary) and flush pending queue
-                    yield pending.pop(0)
-                    if not meta_found:
-                        yield {"type": "EmptyTag", "name": "meta",
-                               "data": {(None, "charset"): self.encoding}}
-                    while pending:
-                        yield pending.pop(0)
-                    meta_found = True
-                    state = "post_head"
-
-            if state == "in_head":
-                pending.append(token)
-            else:
-                yield token
+from __future__ import absolute_import, division, unicode_literals
+
+from . import base
+
+
+class Filter(base.Filter):
+    """Injects ``<meta charset=ENCODING>`` tag into head of document"""
+    def __init__(self, source, encoding):
+        """Creates a Filter
+
+        :arg source: the source token stream
+
+        :arg encoding: the encoding to set
+
+        """
+        base.Filter.__init__(self, source)
+        self.encoding = encoding
+
+    def __iter__(self):
+        state = "pre_head"
+        meta_found = (self.encoding is None)
+        pending = []
+
+        for token in base.Filter.__iter__(self):
+            type = token["type"]
+            if type == "StartTag":
+                if token["name"].lower() == "head":
+                    state = "in_head"
+
+            elif type == "EmptyTag":
+                if token["name"].lower() == "meta":
+                    # replace charset with actual encoding
+                    has_http_equiv_content_type = False
+                    for (namespace, name), value in token["data"].items():
+                        if namespace is not None:
+                            continue
+                        elif name.lower() == 'charset':
+                            token["data"][(namespace, name)] = self.encoding
+                            meta_found = True
+                            break
+                        elif name == 'http-equiv' and value.lower() == 'content-type':
+                            has_http_equiv_content_type = True
+                    else:
+                        if has_http_equiv_content_type and (None, "content") in token["data"]:
+                            token["data"][(None, "content")] = 'text/html; charset=%s' % self.encoding
+                            meta_found = True
+
+                elif token["name"].lower() == "head" and not meta_found:
+                    # insert meta into empty head
+                    yield {"type": "StartTag", "name": "head",
+                           "data": token["data"]}
+                    yield {"type": "EmptyTag", "name": "meta",
+                           "data": {(None, "charset"): self.encoding}}
+                    yield {"type": "EndTag", "name": "head"}
+                    meta_found = True
+                    continue
+
+            elif type == "EndTag":
+                if token["name"].lower() == "head" and pending:
+                    # insert meta into head (if necessary) and flush pending queue
+                    yield pending.pop(0)
+                    if not meta_found:
+                        yield {"type": "EmptyTag", "name": "meta",
+                               "data": {(None, "charset"): self.encoding}}
+                    while pending:
+                        yield pending.pop(0)
+                    meta_found = True
+                    state = "post_head"
+
+            if state == "in_head":
+                pending.append(token)
+            else:
+                yield token

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

@@ -1,93 +1,93 @@
-from __future__ import absolute_import, division, unicode_literals
-
-from gettext import gettext
-_ = gettext
-
-from . import _base
-from ..constants import cdataElements, rcdataElements, voidElements
-
-from ..constants import spaceCharacters
-spaceCharacters = "".join(spaceCharacters)
-
-
-class LintError(Exception):
-    pass
-
-
-class Filter(_base.Filter):
-    def __iter__(self):
-        open_elements = []
-        contentModelFlag = "PCDATA"
-        for token in _base.Filter.__iter__(self):
-            type = token["type"]
-            if type in ("StartTag", "EmptyTag"):
-                name = token["name"]
-                if contentModelFlag != "PCDATA":
-                    raise LintError(_("StartTag not in PCDATA content model flag: %(tag)s") % {"tag": name})
-                if not isinstance(name, str):
-                    raise LintError(_("Tag name is not a string: %(tag)r") % {"tag": name})
-                if not name:
-                    raise LintError(_("Empty tag name"))
-                if type == "StartTag" and name in voidElements:
-                    raise LintError(_("Void element reported as StartTag token: %(tag)s") % {"tag": name})
-                elif type == "EmptyTag" and name not in voidElements:
-                    raise LintError(_("Non-void element reported as EmptyTag token: %(tag)s") % {"tag": token["name"]})
-                if type == "StartTag":
-                    open_elements.append(name)
-                for name, value in token["data"]:
-                    if not isinstance(name, str):
-                        raise LintError(_("Attribute name is not a string: %(name)r") % {"name": name})
-                    if not name:
-                        raise LintError(_("Empty attribute name"))
-                    if not isinstance(value, str):
-                        raise LintError(_("Attribute value is not a string: %(value)r") % {"value": value})
-                if name in cdataElements:
-                    contentModelFlag = "CDATA"
-                elif name in rcdataElements:
-                    contentModelFlag = "RCDATA"
-                elif name == "plaintext":
-                    contentModelFlag = "PLAINTEXT"
-
-            elif type == "EndTag":
-                name = token["name"]
-                if not isinstance(name, str):
-                    raise LintError(_("Tag name is not a string: %(tag)r") % {"tag": name})
-                if not name:
-                    raise LintError(_("Empty tag name"))
-                if name in voidElements:
-                    raise LintError(_("Void element reported as EndTag token: %(tag)s") % {"tag": name})
-                start_name = open_elements.pop()
-                if start_name != name:
-                    raise LintError(_("EndTag (%(end)s) does not match StartTag (%(start)s)") % {"end": name, "start": start_name})
-                contentModelFlag = "PCDATA"
-
-            elif type == "Comment":
-                if contentModelFlag != "PCDATA":
-                    raise LintError(_("Comment not in PCDATA content model flag"))
-
-            elif type in ("Characters", "SpaceCharacters"):
-                data = token["data"]
-                if not isinstance(data, str):
-                    raise LintError(_("Attribute name is not a string: %(name)r") % {"name": data})
-                if not data:
-                    raise LintError(_("%(type)s token with empty data") % {"type": type})
-                if type == "SpaceCharacters":
-                    data = data.strip(spaceCharacters)
-                    if data:
-                        raise LintError(_("Non-space character(s) found in SpaceCharacters token: %(token)r") % {"token": data})
-
-            elif type == "Doctype":
-                name = token["name"]
-                if contentModelFlag != "PCDATA":
-                    raise LintError(_("Doctype not in PCDATA content model flag: %(name)s") % {"name": name})
-                if not isinstance(name, str):
-                    raise LintError(_("Tag name is not a string: %(tag)r") % {"tag": name})
-                # XXX: what to do with token["data"] ?
-
-            elif type in ("ParseError", "SerializeError"):
-                pass
-
-            else:
-                raise LintError(_("Unknown token type: %(type)s") % {"type": type})
-
-            yield token
+from __future__ import absolute_import, division, unicode_literals
+
+from pip._vendor.six import text_type
+
+from . import base
+from ..constants import namespaces, voidElements
+
+from ..constants import spaceCharacters
+spaceCharacters = "".join(spaceCharacters)
+
+
+class Filter(base.Filter):
+    """Lints the token stream for errors
+
+    If it finds any errors, it'll raise an ``AssertionError``.
+
+    """
+    def __init__(self, source, require_matching_tags=True):
+        """Creates a Filter
+
+        :arg source: the source token stream
+
+        :arg require_matching_tags: whether or not to require matching tags
+
+        """
+        super(Filter, self).__init__(source)
+        self.require_matching_tags = require_matching_tags
+
+    def __iter__(self):
+        open_elements = []
+        for token in base.Filter.__iter__(self):
+            type = token["type"]
+            if type in ("StartTag", "EmptyTag"):
+                namespace = token["namespace"]
+                name = token["name"]
+                assert namespace is None or isinstance(namespace, text_type)
+                assert namespace != ""
+                assert isinstance(name, text_type)
+                assert name != ""
+                assert isinstance(token["data"], dict)
+                if (not namespace or namespace == namespaces["html"]) and name in voidElements:
+                    assert type == "EmptyTag"
+                else:
+                    assert type == "StartTag"
+                if type == "StartTag" and self.require_matching_tags:
+                    open_elements.append((namespace, name))
+                for (namespace, name), value in token["data"].items():
+                    assert namespace is None or isinstance(namespace, text_type)
+                    assert namespace != ""
+                    assert isinstance(name, text_type)
+                    assert name != ""
+                    assert isinstance(value, text_type)
+
+            elif type == "EndTag":
+                namespace = token["namespace"]
+                name = token["name"]
+                assert namespace is None or isinstance(namespace, text_type)
+                assert namespace != ""
+                assert isinstance(name, text_type)
+                assert name != ""
+                if (not namespace or namespace == namespaces["html"]) and name in voidElements:
+                    assert False, "Void element reported as EndTag token: %(tag)s" % {"tag": name}
+                elif self.require_matching_tags:
+                    start = open_elements.pop()
+                    assert start == (namespace, name)
+
+            elif type == "Comment":
+                data = token["data"]
+                assert isinstance(data, text_type)
+
+            elif type in ("Characters", "SpaceCharacters"):
+                data = token["data"]
+                assert isinstance(data, text_type)
+                assert data != ""
+                if type == "SpaceCharacters":
+                    assert data.strip(spaceCharacters) == ""
+
+            elif type == "Doctype":
+                name = token["name"]
+                assert name is None or isinstance(name, text_type)
+                assert token["publicId"] is None or isinstance(name, text_type)
+                assert token["systemId"] is None or isinstance(name, text_type)
+
+            elif type == "Entity":
+                assert isinstance(token["name"], text_type)
+
+            elif type == "SerializerError":
+                assert isinstance(token["data"], text_type)
+
+            else:
+                assert False, "Unknown token type: %(type)s" % {"type": type}
+
+            yield token