# Wrapper around StanfordNLP jar.
#
# FIXME this should use the Java FFI.
class NLPJavaProcessor
	super NLPProcessor

	# Classpath to give to Java when loading the StanfordNLP jars.
	var java_cp: String

	# Temp dir used to store batch results
	var tmp_dir = ".nlp"

	# Process a string and return a new NLPDocument from this.
	redef fun process(string) do
		var tmp_file = ".nlp.in"
		var file = new FileWriter.open(tmp_file)
		file.write string
		file.close
		var doc = process_file(tmp_file)
		tmp_file.file_delete
		return doc
	end

	# Process the `input` file and return a new NLPDocument from this.
	redef fun process_file(input) do
		# TODO opt annotators
		var tmp_file = "{input.basename}.xml"
		sys.system "java -cp \"{java_cp}\" -Xmx2g edu.stanford.nlp.pipeline.StanfordCoreNLP -annotators tokenize,ssplit,pos,lemma -outputFormat xml -file {input}"
		var doc = new NLPDocument.from_xml_file(tmp_file)
		tmp_file.file_delete
		return doc
	end

	# Batch mode.
	#
	# Returns a map of file path associated with their NLPDocument.
	redef fun process_files(inputs) do
		# Prepare the input file list
		var input_file = "inputs.list"
		var fw = new FileWriter.open(input_file)
		for input in inputs do fw.write "{input}\n"
		fw.close

		# Run Stanford NLP jar
		sys.system "java -cp \"{java_cp}\" -Xmx2g edu.stanford.nlp.pipeline.StanfordCoreNLP -annotators tokenize,ssplit,pos,lemma -outputFormat xml -filelist {input_file} -outputDirectory {tmp_dir}"
		# Parse output
		var map = new HashMap[String, NLPDocument]
		for input in inputs do
			var out_file = tmp_dir / "{input.basename}.xml"
			map[input] = new NLPDocument.from_xml_file(out_file)
		end
		input_file.file_delete
		tmp_dir.rmdir
		return map
	end
end