Example #1
1
  @SuppressWarnings("unchecked")
  public ResidentConverter(List<ObjectConverter.ColumnInfo> allColumns) throws java.io.IOException {
    Optional<ObjectConverter.ColumnInfo> column;

    final java.util.List<ObjectConverter.ColumnInfo> columns =
        allColumns
            .stream()
            .filter(
                it ->
                    "mixinReference".equals(it.typeSchema) && "Resident_entity".equals(it.typeName))
            .collect(Collectors.toList());
    columnCount = columns.size();

    readers = new ObjectConverter.Reader[columnCount];
    for (int i = 0; i < readers.length; i++) {
      readers[i] = (instance, rdr, ctx) -> StringConverter.skip(rdr, ctx);
    }

    final java.util.List<ObjectConverter.ColumnInfo> columnsExtended =
        allColumns
            .stream()
            .filter(
                it ->
                    "mixinReference".equals(it.typeSchema)
                        && "-ngs_Resident_type-".equals(it.typeName))
            .collect(Collectors.toList());
    columnCountExtended = columnsExtended.size();

    readersExtended = new ObjectConverter.Reader[columnCountExtended];
    for (int i = 0; i < readersExtended.length; i++) {
      readersExtended[i] = (instance, rdr, ctx) -> StringConverter.skip(rdr, ctx);
    }

    column = columns.stream().filter(it -> "id".equals(it.columnName)).findAny();
    if (!column.isPresent())
      throw new java.io.IOException(
          "Unable to find 'id' column in mixinReference Resident_entity. Check if DB is in sync");
    __index___id = (int) column.get().order - 1;

    column = columnsExtended.stream().filter(it -> "id".equals(it.columnName)).findAny();
    if (!column.isPresent())
      throw new java.io.IOException(
          "Unable to find 'id' column in mixinReference Resident. Check if DB is in sync");
    __index__extended_id = (int) column.get().order - 1;

    column = columns.stream().filter(it -> "birth".equals(it.columnName)).findAny();
    if (!column.isPresent())
      throw new java.io.IOException(
          "Unable to find 'birth' column in mixinReference Resident_entity. Check if DB is in sync");
    __index___birth = (int) column.get().order - 1;

    column = columnsExtended.stream().filter(it -> "birth".equals(it.columnName)).findAny();
    if (!column.isPresent())
      throw new java.io.IOException(
          "Unable to find 'birth' column in mixinReference Resident. Check if DB is in sync");
    __index__extended_birth = (int) column.get().order - 1;
  }
  /**
   * Search the tree for the first instance of `pattern`, giving preference to the left child.
   *
   * <p>`pattern` is a tree, representing a pattern of nodes. `NilNode`s should be considered
   * wildcards.
   *
   * <p>Example patterns ---------------- `Tree()` Matches any tree.
   *
   * <p>`Tree(3)` Matches any tree where the root node has a value of `3`.
   *
   * <p>`Tree(3, Tree(2), Tree())` Matches any tree where the root node has a value of `3`, and a
   * left sub-tree with a root value of `2`, and any (or no) right sub-tree.
   */
  static Optional<Tree> find(Tree target, Tree pattern) {
    if (pattern.isEmpty()) return Optional.of(target);
    if (target.isEmpty()) return Optional.empty();
    if (prefixMatches(target, pattern)) return Optional.of(target);

    Optional<Tree> leftMatch = find(target.left(), pattern);
    if (leftMatch.isPresent()) return leftMatch;
    return find(target.right(), pattern);
  }
 @Override
 public Object apply(List<Object> args, Context context) throws ParseException {
   File outFile = null;
   String editor = getEditor();
   try {
     outFile = File.createTempFile("stellar_shell", "out");
     if (args.size() > 0) {
       String arg = (String) args.get(0);
       try (PrintWriter pw = new PrintWriter(outFile)) {
         IOUtils.write(arg, pw);
       }
     }
   } catch (IOException e) {
     String message = "Unable to create temp file: " + e.getMessage();
     LOG.error(message, e);
     throw new IllegalStateException(message, e);
   }
   Optional<Object> console = context.getCapability(CONSOLE, false);
   try {
     PausableInput.INSTANCE.pause();
     // shut down the IO for the console
     ProcessBuilder processBuilder = new ProcessBuilder(editor, outFile.getAbsolutePath());
     processBuilder.redirectInput(ProcessBuilder.Redirect.INHERIT);
     processBuilder.redirectOutput(ProcessBuilder.Redirect.INHERIT);
     processBuilder.redirectError(ProcessBuilder.Redirect.INHERIT);
     try {
       Process p = processBuilder.start();
       // wait for termination.
       p.waitFor();
       try (BufferedReader br = new BufferedReader(new FileReader(outFile))) {
         String ret = IOUtils.toString(br).trim();
         return ret;
       }
     } catch (Exception e) {
       String message = "Unable to read output: " + e.getMessage();
       LOG.error(message, e);
       return null;
     }
   } finally {
     try {
       PausableInput.INSTANCE.unpause();
       if (console.isPresent()) {
         ((Console) console.get()).pushToInputStream("\b\n");
       }
     } catch (IOException e) {
       LOG.error("Unable to unpause: " + e.getMessage(), e);
     }
     if (outFile.exists()) {
       outFile.delete();
     }
   }
 }
  /**
   * The core implementation of the search.
   *
   * @param root The root word to search from. Traditionally, this is the root of the sentence.
   * @param candidateFragments The callback for the resulting sentence fragments. This is a
   *     predicate of a triple of values. The return value of the predicate determines whether we
   *     should continue searching. The triple is a triple of
   *     <ol>
   *       <li>The log probability of the sentence fragment, according to the featurizer and the
   *           weights
   *       <li>The features along the path to this fragment. The last element of this is the
   *           features from the most recent step.
   *       <li>The sentence fragment. Because it is relatively expensive to compute the resulting
   *           tree, this is returned as a lazy {@link Supplier}.
   *     </ol>
   *
   * @param classifier The classifier for whether an arc should be on the path to a clause split, a
   *     clause split itself, or neither.
   * @param featurizer The featurizer to use. Make sure this matches the weights!
   * @param actionSpace The action space we are allowed to take. Each action defines a means of
   *     splitting a clause on a dependency boundary.
   */
  protected void search(
      // The root to search from
      IndexedWord root,
      // The output specs
      final Predicate<Triple<Double, List<Counter<String>>, Supplier<SentenceFragment>>>
          candidateFragments,
      // The learning specs
      final Classifier<ClauseSplitter.ClauseClassifierLabel, String> classifier,
      Map<String, ? extends List<String>> hardCodedSplits,
      final Function<Triple<State, Action, State>, Counter<String>> featurizer,
      final Collection<Action> actionSpace,
      final int maxTicks) {
    // (the fringe)
    PriorityQueue<Pair<State, List<Counter<String>>>> fringe = new FixedPrioritiesPriorityQueue<>();
    // (avoid duplicate work)
    Set<IndexedWord> seenWords = new HashSet<>();

    State firstState =
        new State(null, null, -9000, null, x -> {}, true); // First state is implicitly "done"
    fringe.add(Pair.makePair(firstState, new ArrayList<>(0)), -0.0);
    int ticks = 0;

    while (!fringe.isEmpty()) {
      if (++ticks > maxTicks) {
        //        System.err.println("WARNING! Timed out on search with " + ticks + " ticks");
        return;
      }
      // Useful variables
      double logProbSoFar = fringe.getPriority();
      assert logProbSoFar <= 0.0;
      Pair<State, List<Counter<String>>> lastStatePair = fringe.removeFirst();
      State lastState = lastStatePair.first;
      List<Counter<String>> featuresSoFar = lastStatePair.second;
      IndexedWord rootWord = lastState.edge == null ? root : lastState.edge.getDependent();

      // Register thunk
      if (lastState.isDone) {
        if (!candidateFragments.test(
            Triple.makeTriple(
                logProbSoFar,
                featuresSoFar,
                () -> {
                  SemanticGraph copy = new SemanticGraph(tree);
                  lastState
                      .thunk
                      .andThen(
                          x -> {
                            // Add the extra edges back in, if they don't break the tree-ness of the
                            // extraction
                            for (IndexedWord newTreeRoot : x.getRoots()) {
                              if (newTreeRoot != null) { // what a strange thing to have happen...
                                for (SemanticGraphEdge extraEdge :
                                    extraEdgesByGovernor.get(newTreeRoot)) {
                                  assert Util.isTree(x);
                                  //noinspection unchecked
                                  addSubtree(
                                      x,
                                      newTreeRoot,
                                      extraEdge.getRelation().toString(),
                                      tree,
                                      extraEdge.getDependent(),
                                      tree.getIncomingEdgesSorted(newTreeRoot));
                                  assert Util.isTree(x);
                                }
                              }
                            }
                          })
                      .accept(copy);
                  return new SentenceFragment(copy, assumedTruth, false);
                }))) {
          break;
        }
      }

      // Find relevant auxilliary terms
      SemanticGraphEdge subjOrNull = null;
      SemanticGraphEdge objOrNull = null;
      for (SemanticGraphEdge auxEdge : tree.outgoingEdgeIterable(rootWord)) {
        String relString = auxEdge.getRelation().toString();
        if (relString.contains("obj")) {
          objOrNull = auxEdge;
        } else if (relString.contains("subj")) {
          subjOrNull = auxEdge;
        }
      }

      // Iterate over children
      // For each outgoing edge...
      for (SemanticGraphEdge outgoingEdge : tree.outgoingEdgeIterable(rootWord)) {
        // Prohibit indirect speech verbs from splitting off clauses
        // (e.g., 'said', 'think')
        // This fires if the governor is an indirect speech verb, and the outgoing edge is a ccomp
        if (outgoingEdge.getRelation().toString().equals("ccomp")
            && ((outgoingEdge.getGovernor().lemma() != null
                    && INDIRECT_SPEECH_LEMMAS.contains(outgoingEdge.getGovernor().lemma()))
                || INDIRECT_SPEECH_LEMMAS.contains(outgoingEdge.getGovernor().word()))) {
          continue;
        }
        // Get some variables
        String outgoingEdgeRelation = outgoingEdge.getRelation().toString();
        List<String> forcedArcOrder = hardCodedSplits.get(outgoingEdgeRelation);
        if (forcedArcOrder == null && outgoingEdgeRelation.contains(":")) {
          forcedArcOrder =
              hardCodedSplits.get(
                  outgoingEdgeRelation.substring(0, outgoingEdgeRelation.indexOf(":")) + ":*");
        }
        boolean doneForcedArc = false;
        // For each action...
        for (Action action :
            (forcedArcOrder == null ? actionSpace : orderActions(actionSpace, forcedArcOrder))) {
          // Check the prerequisite
          if (!action.prerequisitesMet(tree, outgoingEdge)) {
            continue;
          }
          if (forcedArcOrder != null && doneForcedArc) {
            break;
          }
          // 1. Compute the child state
          Optional<State> candidate =
              action.applyTo(tree, lastState, outgoingEdge, subjOrNull, objOrNull);
          if (candidate.isPresent()) {
            double logProbability;
            ClauseClassifierLabel bestLabel;
            Counter<String> features =
                featurizer.apply(Triple.makeTriple(lastState, action, candidate.get()));
            if (forcedArcOrder != null && !doneForcedArc) {
              logProbability = 0.0;
              bestLabel = ClauseClassifierLabel.CLAUSE_SPLIT;
              doneForcedArc = true;
            } else if (features.containsKey("__undocumented_junit_no_classifier")) {
              logProbability = Double.NEGATIVE_INFINITY;
              bestLabel = ClauseClassifierLabel.CLAUSE_INTERM;
            } else {
              Counter<ClauseClassifierLabel> scores = classifier.scoresOf(new RVFDatum<>(features));
              if (scores.size() > 0) {
                Counters.logNormalizeInPlace(scores);
              }
              String rel = outgoingEdge.getRelation().toString();
              if ("nsubj".equals(rel) || "dobj".equals(rel)) {
                scores.remove(
                    ClauseClassifierLabel.NOT_A_CLAUSE); // Always at least yield on nsubj and dobj
              }
              logProbability = Counters.max(scores, Double.NEGATIVE_INFINITY);
              bestLabel = Counters.argmax(scores, (x, y) -> 0, ClauseClassifierLabel.CLAUSE_SPLIT);
            }

            if (bestLabel != ClauseClassifierLabel.NOT_A_CLAUSE) {
              Pair<State, List<Counter<String>>> childState =
                  Pair.makePair(
                      candidate.get().withIsDone(bestLabel),
                      new ArrayList<Counter<String>>(featuresSoFar) {
                        {
                          add(features);
                        }
                      });
              // 2. Register the child state
              if (!seenWords.contains(childState.first.edge.getDependent())) {
                //            System.err.println("  pushing " + action.signature() + " with " +
                // argmax.first.edge);
                fringe.add(childState, logProbability);
              }
            }
          }
        }
      }

      seenWords.add(rootWord);
    }
    //    System.err.println("Search finished in " + ticks + " ticks and " + classifierEvals + "
    // classifier evaluations.");
  }
Example #5
0
  @SuppressWarnings("unchecked")
  public Detail2Converter(List<ObjectConverter.ColumnInfo> allColumns) throws java.io.IOException {
    Optional<ObjectConverter.ColumnInfo> column;

    final java.util.List<ObjectConverter.ColumnInfo> columns =
        allColumns
            .stream()
            .filter(it -> "test".equals(it.typeSchema) && "Detail2_entity".equals(it.typeName))
            .collect(Collectors.toList());
    columnCount = columns.size();

    readers = new ObjectConverter.Reader[columnCount];
    for (int i = 0; i < readers.length; i++) {
      readers[i] =
          (instance, rdr, ctx) -> {
            StringConverter.skip(rdr, ctx);
            return instance;
          };
    }

    final java.util.List<ObjectConverter.ColumnInfo> columnsExtended =
        allColumns
            .stream()
            .filter(it -> "test".equals(it.typeSchema) && "-ngs_Detail2_type-".equals(it.typeName))
            .collect(Collectors.toList());
    columnCountExtended = columnsExtended.size();

    readersExtended = new ObjectConverter.Reader[columnCountExtended];
    for (int i = 0; i < readersExtended.length; i++) {
      readersExtended[i] =
          (instance, rdr, ctx) -> {
            StringConverter.skip(rdr, ctx);
            return instance;
          };
    }

    column = columns.stream().filter(it -> "u".equals(it.columnName)).findAny();
    if (!column.isPresent())
      throw new java.io.IOException(
          "Unable to find 'u' column in test Detail2_entity. Check if DB is in sync");
    __index___u = (int) column.get().order - 1;

    column = columnsExtended.stream().filter(it -> "u".equals(it.columnName)).findAny();
    if (!column.isPresent())
      throw new java.io.IOException(
          "Unable to find 'u' column in test Detail2. Check if DB is in sync");
    __index__extended_u = (int) column.get().order - 1;

    column = columns.stream().filter(it -> "dd".equals(it.columnName)).findAny();
    if (!column.isPresent())
      throw new java.io.IOException(
          "Unable to find 'dd' column in test Detail2_entity. Check if DB is in sync");
    __index___dd = (int) column.get().order - 1;

    column = columnsExtended.stream().filter(it -> "dd".equals(it.columnName)).findAny();
    if (!column.isPresent())
      throw new java.io.IOException(
          "Unable to find 'dd' column in test Detail2. Check if DB is in sync");
    __index__extended_dd = (int) column.get().order - 1;

    column = columns.stream().filter(it -> "EntityCompositeid".equals(it.columnName)).findAny();
    if (!column.isPresent())
      throw new java.io.IOException(
          "Unable to find 'EntityCompositeid' column in test Detail2_entity. Check if DB is in sync");
    __index___EntityCompositeid = (int) column.get().order - 1;

    column =
        columnsExtended.stream().filter(it -> "EntityCompositeid".equals(it.columnName)).findAny();
    if (!column.isPresent())
      throw new java.io.IOException(
          "Unable to find 'EntityCompositeid' column in test Detail2. Check if DB is in sync");
    __index__extended_EntityCompositeid = (int) column.get().order - 1;

    column = columns.stream().filter(it -> "EntityIndex".equals(it.columnName)).findAny();
    if (!column.isPresent())
      throw new java.io.IOException(
          "Unable to find 'EntityIndex' column in test Detail2_entity. Check if DB is in sync");
    __index___EntityIndex = (int) column.get().order - 1;

    column = columnsExtended.stream().filter(it -> "EntityIndex".equals(it.columnName)).findAny();
    if (!column.isPresent())
      throw new java.io.IOException(
          "Unable to find 'EntityIndex' column in test Detail2. Check if DB is in sync");
    __index__extended_EntityIndex = (int) column.get().order - 1;

    column = columns.stream().filter(it -> "Index".equals(it.columnName)).findAny();
    if (!column.isPresent())
      throw new java.io.IOException(
          "Unable to find 'Index' column in test Detail2_entity. Check if DB is in sync");
    __index___Index = (int) column.get().order - 1;

    column = columnsExtended.stream().filter(it -> "Index".equals(it.columnName)).findAny();
    if (!column.isPresent())
      throw new java.io.IOException(
          "Unable to find 'Index' column in test Detail2. Check if DB is in sync");
    __index__extended_Index = (int) column.get().order - 1;
  }