Python saxutils.XMLFilterBase类代码示例

    def __init__(
            self, upstream, downstream, tag_name,
            layers_blacklist=None, layers_whitelist=None):
        XMLFilterBase.__init__(self, upstream)
        self._downstream = downstream
        self._accumulator = []

        assert layers_blacklist is not None or layers_whitelist is not None, \
            "either layers_blacklist OR layers_whitelist must be set"
        assert not (
            layers_blacklist is not None and
            layers_whitelist is not None), \
            "only either layers_blacklist OR layers_whitelist can be set"

        if layers_blacklist is not None:
            layers_blacklist = [layer.lower() for layer in layers_blacklist]
        if layers_whitelist is not None:
            layers_whitelist = [layer.lower() for layer in layers_whitelist]
        self.layers_blacklist = layers_blacklist
        self.layers_whitelist = layers_whitelist

        self.layers_path = []
        self.in_name = False
        self.tag_name = tag_name
        self.level = 0

    def endElement(self, name):
        if not self._eat_tag:
            XMLFilterBase.endElement(self, name)

        if name == 'text' and self._catch_full_line:
            self._catch_full_line = False
        elif name == 'dialogue_act' and self._write_full_line:
            self._write_full_line = False
            if len(self._full_line) < self._da_line_len:
                self._whole_line.append("... (missing)")
                self.errorCallback()
            line = self._full_line[:self._da_line_len]
            del self._full_line[:self._da_line_len]
            self._da_line_len = 0
            line = u' '.join(line)

            writer = self.getContentHandler()
            writer.characters('\n' + ' '*self.TAG_INDENT)
            attrs = {'type': self.text_type}
            attrs.update(self._da_attrs)
            writer.startElement('parametrized_act', attrs)
            writer.characters('\n' + ' '*self.CHAR_INDENT)
            writer.characters(line)
            writer.characters('\n' + ' '*self.TAG_INDENT)
            writer.endElement('parametrized_act')
        elif name == 'utterance':
            if self._full_line and self._da_count != 0:
                self.errorCallback()
        elif name == 'parametrized_act':
            self._eat_tag = False

	def startElement(self, name, attrs):
		if name == 'xcb':
			self.header.insert(0, attrs['header'])
		elif name == 'field':
			size = self.types.get(attrs['type'], 0)
			if self.struct is not None:
				self.totalsize += size
			elif self.union is not None:
				self.totalsize = max(self.totalsize, size)
			attrs = AttributesUnion(attrs, bytes=str(size))
		elif name == 'pad':
			assert self.union is None
			if self.struct is not None:
				self.totalsize += int(attrs['bytes'])
		elif name == 'xidtype':
			self.setTypeSize(attrs['name'], 4)
		elif name == 'typedef':
			self.setTypeSize(attrs['newname'], self.types[attrs['oldname']])
		elif name == 'struct' or name == 'union':
			assert self.struct is None and self.union is None
			setattr(self, name, attrs['name'])
			self.totalsize = 0

		if len(self.header) == 1 or name == 'xcb':
			XMLFilterBase.startElement(self, name, attrs)

 def characters(self, text):
     if self.recording == "cell":
         self.cell.append(text)
     elif self.recording == "cell_active":
         self.cell_active.append(text)
     elif self.recording is None:
         XMLFilterBase.characters(self, text)

  def __init__ (self, upstream, SkipEvents = False):

    self.EventCounters = {}
    self.TotalEventCount = 0
    self.SkipEvents = SkipEvents
    self.NewEventType = True
    self.AccumulatingEventContent = False
    self.CurrentEventContent = ''
    self.StreamCopyEnabled = False

    # This buffer will be used to compile a copy of the incoming EDXML
    # stream that has all event data filtered out. We use this stripped
    # copy to do RelaxNG validation, as Python has no incremental XML
    # validator like for instance PHP does.
    self.DefinitionsXMLStringIO = StringIO()

    # And this is the XMLGenerator instance that we will use
    # to fill the buffer.
    self.DefinitionsXMLGenerator = XMLGenerator(self.DefinitionsXMLStringIO, 'utf-8')

    """EDXMLDefinitions instance"""
    self.Definitions = EDXMLDefinitions()

    # We want the EDXMLDefinitions instance to call our
    # error handler, so anyone who wishes to extend the EDXMLParser
    # class can reimplement it to handle all generated errors.
    self.Definitions.Error = self.Error

    XMLFilterBase.__init__(self, upstream)
    EDXMLBase.__init__(self)

 def __init__(self, file):
     XMLFilterBase.__init__(self)
     self.generator = XMLGenerator(file, 'UTF-8')
     self.generator.startPrefixMapping(u'', u'http://www.eucalyptus.com/ns/reporting/export/2012-08-24/')
     self.replyData = StringIO()
     self.replyGenerator = XMLGenerator( self.replyData, 'UTF-8' )
     self.switchTarget( self.replyGenerator )

    def __init__(self, upstream, downstream, text_filter, manualOverride = False):
        XMLFilterBase.__init__(self, upstream)
        self._downstream = downstream
        self._accumulator = []
        self.text_filter = text_filter
        self.should_filter = False
	self.manualOverride = manualOverride # Set this to True if you want text_filter never to run
        return

 def startPrefixMapping(self, prefix, uri):
     if self.prefixes.has_key(prefix):
         if self.prefixesStack.has_key(prefix):
             self.prefixesStack[prefix].append(self.prefixes[prefix])
         else:
             self.prefixesStack[prefix] = [self.prefixes[prefix]]
     self.prefixes[prefix] = uri
     XMLFilterBase.startPrefixMapping(self, prefix, uri)

 def endPrefixMapping(self, prefix):
     if self.prefixesStack.has_key(prefix):
         self.prefixes[prefix] = self.prefixesStack[prefix][-1]
         del(self.prefixesStack[prefix][-1])
         if self.prefixesStack[prefix] == []:
             del (self.prefixesStack[prefix])
     else:
         del(self.prefixes[prefix])
     XMLFilterBase.endPrefixMapping(self, prefix)

 def startElement(self, name, attrs):
     if name == 'text' and attrs.get('type') == self._new_type:
         self._eat_tag = True
     else:
         self._eat_tag = False
     if name == 'text' and attrs.get('type') == self._after:
         self._write_tag = True
     if not self._eat_tag:
         XMLFilterBase.startElement(self, name, attrs)

 def characters(self, chars):
     words = self.createWords(chars)
     if self._catch_full_line:
         self._full_line.extend(words)
         self._whole_line.extend(words)
     if self._write_full_line:
         self._da_line_len += len(words)
     if not self._eat_tag:
         XMLFilterBase.characters(self, chars)

	def startElement(self, name, attrs):
		assert self.inimport is None
		if name == 'import':
			self.inimport = ""
			return
		XMLFilterBase.startElement(self, name, attrs)
		if name == 'xcb':
			seen[attrs['header']] = True
			self.ensure('xproto')

	def __init__(self, upstream, downstream):
		XMLFilterBase.__init__(self, upstream)
		self._downstream = downstream
		self._accumulator = []
		#self.padding_level = -1  # for pretty debug printing
		self.current_element = None  # what element are we inside?
		self.passthrough = False  # allow current element through the filter?
		# Placeholders for the attributes for the builder and shape elements...
		self.builder_info = None
		self.shape_info = None

 def __init__(self, upstream, downstream, filename,chunksize = 100):
     XMLFilterBase.__init__(self, upstream)
     self.handlers = []
     self.pushHandler(downstream)
     self.filename = filename
     self.chunksize = int(chunksize)
     self.rec_count = 0
     self.chunknames = []
     self.tempdir = ''
     self.verbose = False

	def endElement(self, name):
		if len(self.header) == 1 or name == 'xcb':
			XMLFilterBase.endElement(self, name)

		if name == 'xcb':
			self.header.pop(0)
		elif name == 'struct' or name == 'union':
			assert getattr(self, name) is not None
			self.setTypeSize(getattr(self, name), self.totalsize)
			setattr(self, name, None)
			del self.totalsize