import org.openscience.cdk.DefaultChemObjectBuilder
import org.openscience.cdk.smiles.SmilesParser
import org.openscience.cdk.smiles.smarts.SMARTSQueryTool
import org.openscience.cdk.exception.CDKException
import org.openscience.cdk.fingerprint.FingerprinterTool
import org.openscience.cdk.fingerprint.ExtendedFingerprinter

ExtendedFingerprinter fingerprinter = new ExtendedFingerprinter();
int i = 0;
SmilesParser sp = new SmilesParser(DefaultChemObjectBuilder.getInstance());
def resultSMARTS = [:], resultFP = [:]
def queries = ["c1ccccc1C(N)C(O)=O", "CC(C)OCC(C)=C","Nc1ccc(CC)cc1","O=c1[nH]c(=O)c2ccccc12","O=C4C=C3CCC2C1CCCC1CCC2C3CC4","CC2(C)CN1C(=O)C(N)C1S2","OC1CCCCOCC1"]
def queryMols = queries.collect {sp.parseSmiles(it)}
def queryFPs = queryMols.collect {fingerprinter.getFingerprint(it)}

queries.each {String query->
  resultSMARTS[query] = []
  resultFP[query] = []
}
new File("junk.smi").eachLine {String line ->
  queries.eachWithIndex {String query, int index ->
    SMARTSQueryTool sqt = new SMARTSQueryTool(query)
    try {
      def targetMol = sp.parseSmiles(line)
      if (sqt.matches(targetMol)) {
        resultSMARTS[query].add line
      }
      if (FingerprinterTool.isSubset(fingerprinter.getFingerprint(targetMol), queryFPs.get(index))) {
        resultFP[query].add line
      }
    } catch (CDKException e) {
      e.printStackTrace()
    }
  }
  println i++
}
queries.each{String query->
println "Result for "+query
println resultSMARTS[query].size() + " structure got by SMARTS"
println(resultFP[query].size() + " structure got by fingerprint with" + (resultSMARTS[query] - resultFP[query]).size() + " missing, and " + (resultFP[query] - resultSMARTS[query]).size() + " extra")
}