public static boolean kristinasChemicalShortTokenFilterRule( String term, Set<String> stopwordsForFiltering) { term = term.toLowerCase(); ChemicalSBDtokenizer tokenizer = new ChemicalSBDtokenizer(); tokenizer.tokenize(term); String tokenizedTerm = ""; for (String token : tokenizer.tokens) { tokenizedTerm = tokenizedTerm.concat(token); } if (tokenizedTerm.length() < minWordSize || StringUtilities.isNumber(tokenizedTerm) || StringUtilities.isRomanNumeral(tokenizedTerm.toUpperCase()) || stopwordsForFiltering.contains(tokenizedTerm)) { return true; } return false; }