# Represent one word (or puncutation mark) in a `NLPSentence`.
class NLPToken

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

	# Original word
	var word: String

	# `word` lemma
	var lemma: String

	# Position of the first character in the input
	var begin_offset: Int

	# Position of the last character in the input
	var end_offset: Int

	# Part Of Speech tag
	var pos: String

	# Init `self` from an XML element.
	#
	# ~~~
	# var xml = """
	#  <token id="2">
	#	<word>University</word>
	#	<lemma>University</lemma>
	#	<CharacterOffsetBegin>9</CharacterOffsetBegin>
	#	<CharacterOffsetEnd>19</CharacterOffsetEnd>
	#	<POS>NNP</POS>
	#  </token>""".to_xml["token"].first.as(XMLStartTag)
	#
	# var token = new  NLPToken.from_xml(xml)
	# assert token.index == 2
	# assert token.word == "University"
	# assert token.lemma == "University"
	# assert token.begin_offset == 9
	# assert token.end_offset == 19
	# assert token.pos == "NNP"
	# ~~~
	init from_xml(xml: XMLStartTag) do
		var index = xml.attributes.first.as(XMLStringAttr).value.to_i
		var word = read_data(xml, "word")
		var lemma = read_data(xml, "lemma")
		var begin_offset = read_data(xml, "CharacterOffsetBegin").to_i
		var end_offset = read_data(xml, "CharacterOffsetEnd").to_i
		var pos = read_data(xml, "POS")
		init(index, word, lemma, begin_offset, end_offset, pos)
	end

	private fun read_data(xml: XMLStartTag, tag_name: String): String do
		var res = ""
		if xml[tag_name].is_empty then return res
		var first = xml[tag_name].first
		if not first isa XMLStartTag then return res
		var data = first.data
		if data == null then return res
		return data
	end
end