def __call__(self, tag, *children, **attrib):
elem = ET.Element(tag, attrib)
for item in children:
if isinstance(item, dict):
elem.attrib.update(item)
elif isinstance(item, basestring):
if len(elem):
elem[-1].tail = (elem[-1].tail or "") + item
else:
elem.text = (elem.text or "") + item
elif ET.iselement(item):
elem.append(item)
else:
raise TypeError("bad argument: %r" % item)
return elem
def concat(docs):
"""
Concatenate together the contents of multiple documents from a
single corpus, using an appropriate concatenation function. This
utility function is used by corpus readers when the user requests
more than one document at a time.
"""
if len(docs) == 1:
return docs[0]
if len(docs) == 0:
raise ValueError('concat() expects at least one object!')
types = set([d.__class__ for d in docs])
# If they're all strings, use string concatenation.
if types.issubset([str, unicode, basestring]):
return reduce((lambda a, b: a + b), docs, '')
# If they're all corpus views, then use ConcatenatedCorpusView.
for typ in types:
if not issubclass(typ, AbstractCorpusView):
break
else:
return ConcatenatedCorpusView(docs)
# Otherwise, see what we can do:
if len(types) == 1:
typ = list(types)[0]
if issubclass(typ, list):
return reduce((lambda a, b: a + b), docs, [])
if issubclass(typ, tuple):
return reduce((lambda a, b: a + b), docs, ())
if ElementTree.iselement(typ):
xmltree = ElementTree.Element('documents')
for doc in docs:
xmltree.append(doc)
return xmltree
# No method found!
raise ValueError("Don't know how to concatenate types: %r" % types)