+ if self.supports_namespaces and self.has_ns(element):
+ ns_text = self.ns2text(element)
+ print "-r--r--r-- 1 user group %d Jan 1 00:00 %s/namespaces" % (
+ len(ns_text), subpath_encoded)
+ text = self.collect_text(element)
+ if text:
+ print "-r--r--r-- 1 user group %d Jan 1 00:00 %s/text" % (
+ len(text), subpath_encoded)
+ self._list(element, subpath)
+
+ def get_tag_node(self, node, i):
+ n = 0
+ for element in self.getchildren(node):
+ if self.istag(element):
+ n += 1
+ if n == i:
+ return element
+ xml_error('There are less than %d nodes' % i)
+
+ def attrs2text(self, node):
+ attr_accumulator = []
+ for name, value in self.getattrs(node):
+ name = self.getlocalname(name).encode(default_encoding, "replace")
+ value = value.encode(default_encoding, "replace")
+ attr_accumulator.append("%s=%s" % (name, value))
+ return '\n'.join(attr_accumulator)
+
+ def has_ns(self, node):
+ return False
+
+
+class MiniDOMXmlVfs(XmlVfs):
+ def parse(self):
+ self.document = xml.dom.minidom.parse(sys.argv[2])
+
+ def getattrs(self, node):
+ attrs = node.attributes
+ attrs = [attrs.item(i) for i in range(attrs.length)]
+ return [(a.name, a.value) for a in attrs]
+
+ def collect_text(self, node):
+ text_accumulator = []
+ for element in node.childNodes:
+ if element.localName:
+ continue
+ elif element.nodeType == element.COMMENT_NODE:
+ text = u"<!--%s-->" % element.nodeValue
+ elif element.nodeType == element.TEXT_NODE:
+ text = element.nodeValue.strip()
+ else:
+ xml_error("Unknown node type %d" % element.nodeType)
+ if text: text_accumulator.append(text)
+ return '\n'.join(text_accumulator).encode(default_encoding, "replace")
+
+ def getroot(self):
+ return self.document
+
+ def get_root_comments(self):
+ return self.collect_text(self.document)
+
+ def getchildren(self, node):
+ return node.childNodes
+
+ def gettag(self, node):
+ return node.localName
+
+ def istag(self, node):
+ return bool(node.localName)
+
+ def getlocalname(self, name):
+ return name
+
+
+if use_elementtree or use_lxml:
+ class CommonEtreeXmlVfs(XmlVfs):
+ def getattrs(self, node):
+ return node.attrib.items()
+
+ def collect_text(self, node):
+ text_accumulator = []
+ if node.text:
+ text = node.text.strip()
+ if text: text_accumulator.append(text)
+ for element in node:
+ if not self.istag(element):
+ text = u"<!--%s-->" % element.text
+ text_accumulator.append(text)
+ if node.tail:
+ text = node.tail.strip()
+ if text: text_accumulator.append(text)
+ return '\n'.join(text_accumulator).encode(default_encoding, "replace")
+
+ def getchildren(self, node):
+ return list(node)
+
+ def gettag(self, node):
+ return node.tag
+
+ def istag(self, node):
+ return isinstance(node.tag, basestring)
+
+
+if use_elementtree:
+ class ElementTreeXmlVfs(CommonEtreeXmlVfs):
+ def parse(self):
+ # Copied from http://effbot.org/zone/element-pi.ht
+
+ class PIParser(ET.XMLTreeBuilder):
+
+ def __init__(self):
+ ET.XMLTreeBuilder.__init__(self)
+ # assumes ElementTree 1.2.X
+ self._parser.CommentHandler = self.handle_comment
+ self._parser.ProcessingInstructionHandler = self.handle_pi
+ self._target.start("document", {})
+
+ def close(self):
+ self._target.end("document")
+ return ET.XMLTreeBuilder.close(self)
+
+ def handle_comment(self, data):
+ self._target.start(ET.Comment, {})
+ self._target.data(data)
+ self._target.end(ET.Comment)
+
+ def handle_pi(self, target, data):
+ self._target.start(ET.PI, {})
+ self._target.data(target + " " + data)
+ self._target.end(ET.PI)
+
+ self.document = ET.parse(sys.argv[2], PIParser())
+
+ def getroot(self):
+ return self.document.getroot()
+
+ def get_root_comments(self):
+ text_accumulator = []
+ for element in self.getroot():
+ if not self.istag(element):
+ text = u"<!--%s-->" % element.text
+ text_accumulator.append(text)
+ return '\n'.join(text_accumulator).encode(default_encoding, "replace")
+
+ def getlocalname(self, name):
+ if name.startswith('{'):
+ name = name.split('}', 1)[1] # Remove XML namespace
+ return name
+
+
+if use_lxml:
+ class LxmlEtreeXmlVfs(CommonEtreeXmlVfs):
+ supports_namespaces = True
+
+ def parse(self):
+ self.document = etree.parse(sys.argv[2])
+
+ def getroot(self):
+ return [self.document.getroot()]
+
+ def get_root_comments(self):
+ text_accumulator = []
+ for element in self.document.getroot().itersiblings(tag=etree.Comment, preceding=True):
+ text = u"<!--%s-->" % element.text
+ text_accumulator.append(text)
+ return '\n'.join(text_accumulator).encode(default_encoding, "replace")
+
+ def getlocalname(self, name):
+ return etree.QName(name).localname
+
+ def _get_local_ns(self, node):
+ this_nsmap = node.nsmap
+ parent = node.getparent()
+ if parent is not None:
+ parent_nsmap = parent.nsmap
+ for key in parent_nsmap:
+ if this_nsmap[key] == parent_nsmap[key]:
+ del this_nsmap[key]
+ return this_nsmap
+
+ def has_ns(self, node):
+ return bool(self._get_local_ns(node))
+
+ def ns2text(self, node):
+ ns_accumulator = []
+ for name, value in self._get_local_ns(node).items():
+ if name is None: name = ''
+ name = name.encode(default_encoding, "replace")
+ value = value.encode(default_encoding, "replace")
+ ns_accumulator.append("%s=%s" % (name, value))
+ return '\n'.join(ns_accumulator)
+
+
+def build_xmlvfs():
+ if force_implementation is None:
+ if use_lxml:
+ return LxmlEtreeXmlVfs()
+ elif use_elementtree:
+ return ElementTreeXmlVfs()
+ else:
+ return MiniDOMXmlVfs()
+ elif force_implementation == 'minidom':
+ return MiniDOMXmlVfs()
+ elif force_implementation == 'elementtree':
+ return ElementTreeXmlVfs()
+ elif force_implementation == 'lxml':
+ return LxmlEtreeXmlVfs()
+ else:
+ raise ValueError('Unknown implementation "%s", expected "minidom", "elementtree" or "lxml"' % force_implementation)
+