Example #1
0
  public static JavaRDD<IAtomContainer> sdfFilesToMols(String path, JavaSparkContext ctx) {
    JavaPairRDD<String, String> sdfFiles = ctx.wholeTextFiles(path);

    FlatMapFunction<Tuple2<String, String>, IAtomContainer> sdfBlockBuilder =
        new FlatMapFunction<Tuple2<String, String>, IAtomContainer>() {

          public Iterable<IAtomContainer> call(Tuple2<String, String> sdfFile) throws Exception {
            return SDFUtils.parseSDF(sdfFile._2());
          }
        };

    JavaRDD<IAtomContainer> molecules = sdfFiles.flatMap(sdfBlockBuilder);

    return molecules;
  }