import edu.stanford.nlp.io.NumberRangeFileFilter; //导入依赖的package包/类
public static List<Tree> getTrees(String path, int low, int high, int minLength, int maxLength) {
  Treebank treebank = new DiskTreebank(new TreeReaderFactory() {
    public TreeReader newTreeReader(Reader in) {
      return new PennTreeReader(in, new LabeledScoredTreeFactory(new WordFactory()), new BobChrisTreeNormalizer());
    }
  });
  treebank.loadPath(path, new NumberRangeFileFilter(low, high, true));
  List<Tree> trees = new ArrayList<Tree>();
  for (Tree tree : treebank) {
    if (tree.yield().size() <= maxLength && tree.yield().size() >= minLength) {
      trees.add(tree);
    }
  }
  return trees;
}
 

import edu.stanford.nlp.io.NumberRangeFileFilter; //导入依赖的package包/类
/**
 * This is hardwired to calculate the split categories from English
 * Penn Treebank sections 2-21 with a default cutoff of 300 (as used
 * in ACL03PCFG).  It was added to upgrading of code in cases where no
 * Treebank was available, and the pre-stored list was being used).
 */
public static Set<String> getEnglishSplitCategories(String treebankRoot) {
  TreebankLangParserParams tlpParams = new EnglishTreebankParserParams();
  Treebank trees = tlpParams.memoryTreebank();
  trees.loadPath(treebankRoot, new NumberRangeFileFilter(200, 2199, true));
  return getSplitCategories(trees, 300.0, tlpParams.treebankLanguagePack());
}