// variables needed to process the files to be parsed
TokenizerFactory<Word> tokenizerFactory = null;
// DocumentPreprocessor documentPreprocessor = new DocumentPreprocessor();
boolean tokenized = false; // whether or not the input file has already been tokenized
Function<List<HasWord>, List<HasWord>> escaper = new ChineseEscaper();
// int tagDelimiter = -1;
// String sentenceDelimiter = "\n";
// boolean fromXML = false;
int argIndex = 0;
if (args.length < 1) {