diff options
Diffstat (limited to 'Lib/xml/dom/minidom.py')
| -rw-r--r-- | Lib/xml/dom/minidom.py | 91 |
1 files changed, 58 insertions, 33 deletions
diff --git a/Lib/xml/dom/minidom.py b/Lib/xml/dom/minidom.py index 7e2898cd3ef..f23ad053333 100644 --- a/Lib/xml/dom/minidom.py +++ b/Lib/xml/dom/minidom.py @@ -14,6 +14,8 @@ Todo: * SAX 2 namespaces """ +import codecs +import io import xml.dom from xml.dom import EMPTY_NAMESPACE, EMPTY_PREFIX, XMLNS_NAMESPACE, domreg @@ -38,26 +40,26 @@ class Node(xml.dom.Node): prefix = EMPTY_PREFIX # non-null only for NS elements and attributes - def __nonzero__(self): + def __bool__(self): return True - def toxml(self, encoding = None): + def toxml(self, encoding=None): return self.toprettyxml("", "", encoding) - def toprettyxml(self, indent="\t", newl="\n", encoding = None): + def toprettyxml(self, indent="\t", newl="\n", encoding=None): # indent = the indentation string to prepend, per level # newl = the newline string to append - writer = _get_StringIO() - if encoding is not None: - import codecs - # Can't use codecs.getwriter to preserve 2.0 compatibility - writer = codecs.lookup(encoding)[3](writer) + use_encoding = "utf-8" if encoding is None else encoding + writer = codecs.getwriter(use_encoding)(io.BytesIO()) if self.nodeType == Node.DOCUMENT_NODE: # Can pass encoding only to document, to put it into XML header self.writexml(writer, "", indent, newl, encoding) else: self.writexml(writer, "", indent, newl) - return writer.getvalue() + if encoding is None: + return writer.stream.getvalue().decode(use_encoding) + else: + return writer.stream.getvalue() def hasChildNodes(self): if self.childNodes: @@ -251,7 +253,7 @@ class Node(xml.dom.Node): def _call_user_data_handler(self, operation, src, dst): if hasattr(self, "_user_data"): - for key, (data, handler) in self._user_data.items(): + for key, (data, handler) in list(self._user_data.items()): if handler is not None: handler.handle(operation, key, data, src, dst) @@ -266,6 +268,14 @@ class Node(xml.dom.Node): self.previousSibling = None self.nextSibling = None + # A Node is its own context manager, to ensure that an unlink() call occurs. + # This is similar to how a file object works. + def __enter__(self): + return self + + def __exit__(self, et, ev, tb): + self.unlink() + defproperty(Node, "firstChild", doc="First child node, or None.") defproperty(Node, "lastChild", doc="Last child node, or None.") defproperty(Node, "localName", doc="Namespace-local name of this node.") @@ -355,6 +365,8 @@ class Attr(Node): # nodeValue and value are set elsewhere def _get_localName(self): + if 'localName' in self.__dict__: + return self.__dict__['localName'] return self.nodeName.split(":", 1)[-1] def _get_name(self): @@ -474,7 +486,7 @@ class NamedNodeMap(object): def item(self, index): try: - return self[self._attrs.keys()[index]] + return self[list(self._attrs.keys())[index]] except IndexError: return None @@ -490,8 +502,8 @@ class NamedNodeMap(object): L.append(((node.namespaceURI, node.localName), node.value)) return L - def has_key(self, key): - if isinstance(key, StringTypes): + def __contains__(self, key): + if isinstance(key, str): return key in self._attrs else: return key in self._attrsNS @@ -510,12 +522,29 @@ class NamedNodeMap(object): __len__ = _get_length - __hash__ = None # Mutable type can't be correctly hashed - def __cmp__(self, other): + def _cmp(self, other): if self._attrs is getattr(other, "_attrs", None): return 0 else: - return cmp(id(self), id(other)) + return (id(self) > id(other)) - (id(self) < id(other)) + + def __eq__(self, other): + return self._cmp(other) == 0 + + def __ge__(self, other): + return self._cmp(other) >= 0 + + def __gt__(self, other): + return self._cmp(other) > 0 + + def __le__(self, other): + return self._cmp(other) <= 0 + + def __lt__(self, other): + return self._cmp(other) < 0 + + def __ne__(self, other): + return self._cmp(other) != 0 def __getitem__(self, attname_or_tuple): if isinstance(attname_or_tuple, tuple): @@ -525,7 +554,7 @@ class NamedNodeMap(object): # same as set def __setitem__(self, attname, value): - if isinstance(value, StringTypes): + if isinstance(value, str): try: node = self._attrs[attname] except KeyError: @@ -535,7 +564,7 @@ class NamedNodeMap(object): node.value = value else: if not isinstance(value, Attr): - raise TypeError, "value must be a string or Attr object" + raise TypeError("value must be a string or Attr object") node = value self.setNamedItem(node) @@ -659,13 +688,15 @@ class Element(Node): # namespaces. def _get_localName(self): + if 'localName' in self.__dict__: + return self.__dict__['localName'] return self.tagName.split(":", 1)[-1] def _get_tagName(self): return self.tagName def unlink(self): - for attr in self._attrs.values(): + for attr in list(self._attrs.values()): attr.unlink() self._attrs = None self._attrsNS = None @@ -798,8 +829,7 @@ class Element(Node): writer.write(indent+"<" + self.tagName) attrs = self._get_attributes() - a_names = attrs.keys() - a_names.sort() + a_names = sorted(attrs.keys()) for a_name in a_names: writer.write(" %s=\"" % a_name) @@ -1125,7 +1155,7 @@ def _get_containing_entref(node): return None -class Comment(Childless, CharacterData): +class Comment(CharacterData): nodeType = Node.COMMENT_NODE nodeName = "#comment" @@ -1182,7 +1212,7 @@ class ReadOnlySequentialNamedNodeMap(object): else: node = self.getNamedItem(name_or_tuple) if node is None: - raise KeyError, name_or_tuple + raise KeyError(name_or_tuple) return node def item(self, index): @@ -1609,16 +1639,16 @@ class Document(Node, DocumentLS): return e def createTextNode(self, data): - if not isinstance(data, StringTypes): - raise TypeError, "node contents must be a string" + if not isinstance(data, str): + raise TypeError("node contents must be a string") t = Text() t.data = data t.ownerDocument = self return t def createCDATASection(self, data): - if not isinstance(data, StringTypes): - raise TypeError, "node contents must be a string" + if not isinstance(data, str): + raise TypeError("node contents must be a string") c = CDATASection() c.data = data c.ownerDocument = self @@ -1901,11 +1931,6 @@ def _nssplit(qualifiedName): return (None, fields[0]) -def _get_StringIO(): - # we can't use cStringIO since it doesn't support Unicode strings - from StringIO import StringIO - return StringIO() - def _do_pulldom_parse(func, args, kwargs): events = func(*args, **kwargs) toktype, rootNode = events.getEvent() @@ -1935,7 +1960,7 @@ def parseString(string, parser=None): def getDOMImplementation(features=None): if features: - if isinstance(features, StringTypes): + if isinstance(features, str): features = domreg._parse_feature_string(features) for f, v in features: if not Document.implementation.hasFeature(f, v): |