genshistream.py 文件源码

def tokens(self, event, next):
        kind, data, pos = event
        if kind == START:
            tag, attribs = data
            name = tag.localname
            namespace = tag.namespace
            converted_attribs = {}
            for k, v in attribs:
                if isinstance(k, QName):
                    converted_attribs[(k.namespace, k.localname)] = v
                else:
                    converted_attribs[(None, k)] = v

            if namespace == namespaces["html"] and name in voidElements:
                for token in self.emptyTag(namespace, name, converted_attribs,
                                           not next or next[0] != END
                                           or next[1] != tag):
                    yield token
            else:
                yield self.startTag(namespace, name, converted_attribs)

        elif kind == END:
            name = data.localname
            namespace = data.namespace
            if name not in voidElements:
                yield self.endTag(namespace, name)

        elif kind == COMMENT:
            yield self.comment(data)

        elif kind == TEXT:
            for token in self.text(data):
                yield token

        elif kind == DOCTYPE:
            yield self.doctype(*data)

        elif kind in (XML_NAMESPACE, DOCTYPE, START_NS, END_NS,
                      START_CDATA, END_CDATA, PI):
            pass

        else:
            yield self.unknown(kind)