# Represent one sentence in a `Document`.
class NLPSentence

	# Index of this sentence in the input text.
	var index: Int

	#  NLPTokens contained in `self`.
	var tokens = new Array[NLPToken]

	# Init `self` from an XML element.
	#
	# ~~~
	# var xml = """
	# <sentence id="1">
	#   <tokens>
	#     <token id="1">
	#       <word>Stanford</word>
	#       <lemma>Stanford</lemma>
	#       <CharacterOffsetBegin>0</CharacterOffsetBegin>
	#       <CharacterOffsetEnd>8</CharacterOffsetEnd>
	#       <POS>NNP</POS>
	#     </token>
	#     <token id="2">
	#       <word>University</word>
	#       <lemma>University</lemma>
	#       <CharacterOffsetBegin>9</CharacterOffsetBegin>
	#       <CharacterOffsetEnd>19</CharacterOffsetEnd>
	#       <POS>NNP</POS>
	#     </token>
	#   </tokens>
	# </sentence>""".to_xml["sentence"].first.as(XMLStartTag)
	#
	# var sentence = new  NLPSentence.from_xml(xml)
	# assert sentence.index == 1
	# assert sentence.tokens.length == 2
	# ~~~
	init from_xml(xml: XMLStartTag) do
		var index = xml.attributes.first.as(XMLStringAttr).value.to_i
		for obj in xml["tokens"].first["token"] do
			if obj isa XMLStartTag then
				tokens.add new NLPToken.from_xml(obj)
			else
				print "Warning: malformed xml, `tokens` is supposed to contain `token` tags"
			end
		end
		init(index)
	end
end