private void tallyTree(
     Tree<String> tree,
     Counter<String> symbolCounter,
     Counter<UnaryRule> unaryRuleCounter,
     Counter<BinaryRule> binaryRuleCounter) {
   if (tree.isLeaf()) return;
   if (tree.isPreTerminal()) return;
   if (tree.getChildren().size() == 1) {
     UnaryRule unaryRule = makeUnaryRule(tree);
     symbolCounter.incrementCount(tree.getLabel(), 1.0);
     unaryRuleCounter.incrementCount(unaryRule, 1.0);
   }
   if (tree.getChildren().size() == 2) {
     BinaryRule binaryRule = makeBinaryRule(tree);
     symbolCounter.incrementCount(tree.getLabel(), 1.0);
     binaryRuleCounter.incrementCount(binaryRule, 1.0);
   }
   if (tree.getChildren().size() < 1 || tree.getChildren().size() > 2) {
     throw new RuntimeException(
         "Attempted to construct a Grammar with an illegal tree: " + tree);
   }
   for (Tree<String> child : tree.getChildren()) {
     tallyTree(child, symbolCounter, unaryRuleCounter, binaryRuleCounter);
   }
 }
Example #2
0
 private static <L> void appendPreTerminalYield(Tree<L> tree, List<L> yield) {
   if (tree.isPreTerminal()) {
     yield.add(tree.getLabel());
     return;
   }
   for (Tree<L> child : tree.getChildren()) {
     appendPreTerminalYield(child, yield);
   }
 }
Example #3
0
 private static <L> int toConstituentCollectionHelper(
     Tree<L> tree, int start, List<Constituent<L>> constituents) {
   if (tree.isLeaf() || tree.isPreTerminal()) return 1;
   int span = 0;
   for (Tree<L> child : tree.getChildren()) {
     span += toConstituentCollectionHelper(child, start + span, constituents);
   }
   constituents.add(new Constituent<L>(tree.getLabel(), start, start + span));
   return span;
 }
Example #4
0
 private int tallySpans(Tree<String> tree, int start) {
   if (tree.isLeaf() || tree.isPreTerminal()) return 1;
   int end = start;
   for (Tree<String> child : tree.getChildren()) {
     int childSpan = tallySpans(child, end);
     end += childSpan;
   }
   String category = tree.getLabel();
   if (!category.equals("ROOT")) spanToCategories.incrementCount(end - start, category, 1.0);
   return end - start;
 }