Java HasTag类代码示例

import edu.stanford.nlp.ling.HasTag; //导入依赖的package包/类
private static Sentence<TaggedWord> myExtractor(Tree t, Sentence<TaggedWord> ty) {
  Tree[] kids = t.children();
  // this inlines the content of t.isPreTerminal()
  if (kids.length == 1 && kids[0].isLeaf()) {
    if (t.label() instanceof HasTag) {
      //   System.err.println("Object is: " + ((CategoryWordTag) t.label()).toString("full"));
      ty.add(new TaggedWord(kids[0].label().value(), ((HasTag) t.label()).tag()));
    } else {
      //   System.err.println("Object is: " + StringUtils.getShortClassName(t.label()) + " " + t.label());
      ty.add(new TaggedWord(kids[0].label().value(), t.label().value()));
    }
  } else {
    for (int i = 0; i < kids.length; i++) {
      myExtractor(kids[i], ty);
    }
  }
  return ty;
}
 

import edu.stanford.nlp.ling.HasTag; //导入依赖的package包/类
/**
 * Convert a constituency label to a dependency label. Options are provided for selecting annotations
 * to copy.
 *
 * @param oldLabel
 * @param copyLabel
 * @param copyIndex
 * @param copyPosTag
 */
private static Label makeDependencyLabel(Label oldLabel, boolean copyLabel, boolean copyIndex, boolean copyPosTag) {
  if ( ! copyLabel)
    return oldLabel;

  String wordForm = (oldLabel instanceof HasWord) ? ((HasWord) oldLabel).word() : oldLabel.value();
  Label newLabel = oldLabel.labelFactory().newLabel(wordForm);
  if (newLabel instanceof HasWord) ((HasWord) newLabel).setWord(wordForm);
  if (copyPosTag && newLabel instanceof HasTag && oldLabel instanceof HasTag) {
    String tag = ((HasTag) oldLabel).tag();
    ((HasTag) newLabel).setTag(tag);
  }
  if (copyIndex && newLabel instanceof HasIndex && oldLabel instanceof HasIndex) {
    int index = ((HasIndex) oldLabel).index();
    ((HasIndex) newLabel).setIndex(index);
  }

  return newLabel;
}
 

import edu.stanford.nlp.ling.HasTag; //导入依赖的package包/类
private static boolean vpContainsParticiple(Tree t) {
  for (Tree kid : t.children()) {
    if (DEBUG) {
      System.err.println("vpContainsParticiple examining " + kid);
    }
    if (kid.isPreTerminal()) {
      Label kidLabel = kid.label();
      String tag = null;
      if (kidLabel instanceof HasTag) {
        tag = ((HasTag) kidLabel).tag();
      }
      if (tag == null) {
        tag = kid.value();
      }
      if ("VBN".equals(tag) || "VBG".equals(tag) || "VBD".equals(tag)) {
        if (DEBUG) {
          System.err.println("vpContainsParticiple found VBN/VBG/VBD VP");
        }
        return true;
      }
    }
  }
  return false;
}
 

import edu.stanford.nlp.ling.HasTag; //导入依赖的package包/类
/**
 * Set the tags of the original tokens and the leaves if they
 * aren't already set
 */
public static void setMissingTags(CoreMap sentence, Tree tree) {
  List<TaggedWord> taggedWords = null;
  List<Label> leaves = null;
  List<CoreLabel> tokens = sentence.get(CoreAnnotations.TokensAnnotation.class);
  for (int i = 0; i < tokens.size(); ++i) {
    CoreLabel token = tokens.get(i);
    if (token.tag() == null) {
      if (taggedWords == null) {
        taggedWords = tree.taggedYield();
      }
      if (leaves == null) {
        leaves = tree.yield();
      }
      token.setTag(taggedWords.get(i).tag());
      Label leaf = leaves.get(i);
      if (leaf instanceof HasTag) {
        ((HasTag) leaf).setTag(taggedWords.get(i).tag());
      }
    }
  }
}
 

import edu.stanford.nlp.ling.HasTag; //导入依赖的package包/类
/**
 * Set the tags of the original tokens and the leaves if they
 * aren't already set
 */
public static void setMissingTags(CoreMap sentence, Tree tree) {
  List<TaggedWord> taggedWords = null;
  List<Label> leaves = null;
  List<CoreLabel> tokens = sentence.get(TokensAnnotation.class);
  for (int i = 0; i < tokens.size(); ++i) {
    CoreLabel token = tokens.get(i);
    if (token.tag() == null) {
      if (taggedWords == null) {
        taggedWords = tree.taggedYield();
      }
      if (leaves == null) {
        leaves = tree.yield();
      }
      token.setTag(taggedWords.get(i).tag());
      Label leaf = leaves.get(i);
      if (leaf instanceof HasTag) {
        ((HasTag) leaf).setTag(taggedWords.get(i).tag());
      }
    }
  }
}
 

import edu.stanford.nlp.ling.HasTag; //导入依赖的package包/类
public Tree transformTree(Tree tree) {
  Label lab = tree.label();
  if (tree.isLeaf()) {
    Tree leaf = tf.newLeaf(lab);
    leaf.setScore(tree.score());
    return leaf;
  }
  String s = lab.value();
  s = treebankLanguagePack().basicCategory(s);
  int numKids = tree.numChildren();
  List<Tree> children = new ArrayList<Tree>(numKids);
  for (int cNum = 0; cNum < numKids; cNum++) {
    Tree child = tree.getChild(cNum);
    Tree newChild = transformTree(child);
    // cdm 2007: for just subcategory stripping, null shouldn't happen
    // if (newChild != null) {
    children.add(newChild);
    // }
  }
  // if (children.isEmpty()) {
  //   return null;
  // }
  CategoryWordTag newLabel = new CategoryWordTag(lab);
  newLabel.setCategory(s);
  if (lab instanceof HasTag) {
    String tag = ((HasTag) lab).tag();
    tag = treebankLanguagePack().basicCategory(tag);
    newLabel.setTag(tag);
  }
  Tree node = tf.newTreeNode(newLabel, children);
  node.setScore(tree.score());
  return node;
}
 

import edu.stanford.nlp.ling.HasTag; //导入依赖的package包/类
public boolean accept(Dependency<G, D, N> d) {
  if (d == null) {
    return false;
  }
  if ( ! (d.dependent() instanceof HasTag)) {
    return false;
  }
  String tag = ((HasTag) d.dependent()).tag();
  return tagRejectFilter.accept(tag);
}
 

import edu.stanford.nlp.ling.HasTag; //导入依赖的package包/类
@Override
public Tree transformTree(Tree tree) {
  Label lab = tree.label();
  if (tree.isLeaf()) {
    Tree leaf = tf.newLeaf(lab);
    leaf.setScore(tree.score());
    return leaf;
  }
  String s = lab.value();
  s = treebankLanguagePack().basicCategory(s);
  int numKids = tree.numChildren();
  List<Tree> children = new ArrayList<Tree>(numKids);
  for (int cNum = 0; cNum < numKids; cNum++) {
    Tree child = tree.getChild(cNum);
    Tree newChild = transformTree(child);
    // cdm 2007: for just subcategory stripping, null shouldn't happen
    // if (newChild != null) {
    children.add(newChild);
    // }
  }
  // if (children.isEmpty()) {
  //   return null;
  // }
  CategoryWordTag newLabel = new CategoryWordTag(lab);
  newLabel.setCategory(s);
  if (lab instanceof HasTag) {
    String tag = ((HasTag) lab).tag();
    tag = treebankLanguagePack().basicCategory(tag);
    newLabel.setTag(tag);
  }
  Tree node = tf.newTreeNode(newLabel, children);
  node.setScore(tree.score());
  return node;
}
 

import edu.stanford.nlp.ling.HasTag; //导入依赖的package包/类
public boolean accept(Dependency<G, D, N> d) {
  /*
  System.err.println("DRF: Checking " + d + ": hasTag?: " +
                     (d.dependent() instanceof HasTag) + "; value: " +
                     ((d.dependent() instanceof HasTag)? ((HasTag) d.dependent()).tag(): null));
  */
  if (d == null) {
    return false;
  }
  if ( ! (d.dependent() instanceof HasTag)) {
    return false;
  }
  String tag = ((HasTag) d.dependent()).tag();
  return tagRejectFilter.accept(tag);
}
 

import edu.stanford.nlp.ling.HasTag; //导入依赖的package包/类
private boolean isVerbalAuxiliary(Tree preterminal, Set<String> verbalSet, boolean allowJustTagMatch) {
  if (preterminal.isPreTerminal()) {
    Label kidLabel = preterminal.label();
    String tag = null;
    if (kidLabel instanceof HasTag) {
      tag = ((HasTag) kidLabel).tag();
    }
    if (tag == null) {
      tag = preterminal.value();
    }
    Label wordLabel = preterminal.firstChild().label();
    String word = null;
    if (wordLabel instanceof HasWord) {
      word = ((HasWord) wordLabel).word();
    }
    if (word == null) {
      word = wordLabel.value();
    }

    if (DEBUG) {
      System.err.println("Checking " + preterminal.value() + " head is " + word + '/' + tag);
    }
    String lcWord = word.toLowerCase();
    if (allowJustTagMatch && unambiguousAuxiliaryTags.contains(tag) || verbalTags.contains(tag) && verbalSet.contains(lcWord)) {
      if (DEBUG) {
        System.err.println("isAuxiliary found desired type of aux");
      }
      return true;
    }
  }
  return false;
}
 

import edu.stanford.nlp.ling.HasTag; //导入依赖的package包/类
@Override
public Tree transformTree(Tree t, Tree root) {

  String baseCat = t.value();
  StringBuilder newCategory = new StringBuilder();

  //Add manual state splits
  for (Pair<TregexPattern,Function<TregexMatcher,String>> e : activeAnnotations) {
    TregexMatcher m = e.first().matcher(root);
    if (m.matchesAt(t))
      newCategory.append(e.second().apply(m));
  }

  // WSGDEBUG
  //Add morphosyntactic features if this is a POS tag
  if(t.isPreTerminal() && tagSpec != null) {
    if( !(t.firstChild().label() instanceof CoreLabel) || ((CoreLabel) t.firstChild().label()).originalText() == null )
      throw new RuntimeException(String.format("%s: Term lacks morpho analysis: %s",this.getClass().getName(),t.toString()));

    String morphoStr = ((CoreLabel) t.firstChild().label()).originalText();
    MorphoFeatures feats = tagSpec.strToFeatures(morphoStr);
    baseCat = feats.getTag(baseCat);
  }

  //Update the label(s)
  String newCat = baseCat + newCategory.toString();
  t.setValue(newCat);
  if (t.isPreTerminal() && t.label() instanceof HasTag)
    ((HasTag) t.label()).setTag(newCat);

  return t;
}
 

import edu.stanford.nlp.ling.HasTag; //导入依赖的package包/类
@Override
public Tree transformTree(Tree t, Tree root) {

  String baseCat = t.value();
  StringBuilder newCategory = new StringBuilder();

  //Add manual state splits
  for (Pair<TregexPattern,Function<TregexMatcher,String>> e : activeAnnotations) {
    TregexMatcher m = e.first().matcher(root);
    if (m.matchesAt(t))
      newCategory.append(e.second().apply(m));
  }

  //Add morphosyntactic features if this is a POS tag
  if(t.isPreTerminal() && tagSpec != null) {
    if( !(t.firstChild().label() instanceof CoreLabel) || ((CoreLabel) t.firstChild().label()).originalText() == null )
      throw new RuntimeException(String.format("%s: Term lacks morpho analysis: %s",this.getClass().getName(),t.toString()));

    String morphoStr = ((CoreLabel) t.firstChild().label()).originalText();
    Pair<String,String> lemmaMorph = MorphoFeatureSpecification.splitMorphString("", morphoStr);
    MorphoFeatures feats = tagSpec.strToFeatures(lemmaMorph.second());
    baseCat = feats.getTag(baseCat);
  }

  //Update the label(s)
  String newCat = baseCat + newCategory.toString();
  t.setValue(newCat);
  if (t.isPreTerminal() && t.label() instanceof HasTag)
    ((HasTag) t.label()).setTag(newCat);

  return t;
}
 

import edu.stanford.nlp.ling.HasTag; //导入依赖的package包/类
public void setCorrectTags(List<? extends HasTag> sentence) {
  int len = sentence.size();
  correctTags = new String[len];
  for (int i = 0; i < len; i++) {
    correctTags[i] = sentence.get(i).tag();
  }
}
 

import edu.stanford.nlp.ling.HasTag; //导入依赖的package包/类
/**
 * Tags the sentence s by running maxent model.  Returns a sentence (List) of
 * TaggedWord objects.
 *
 * @param s Input sentence (List).  This isn't changed.
 * @return Tagged sentence
 */
public ArrayList<TaggedWord> tagSentence(List<? extends HasWord> s,
                                         boolean reuseTags) {
  this.origWords = new ArrayList<HasWord>(s);
  int sz = s.size();
  this.sent = new ArrayList<String>(sz + 1);
  for (int j = 0; j < sz; j++) {
    if (maxentTagger.wordFunction != null) {
      sent.add(maxentTagger.wordFunction.apply(s.get(j).word()));
    } else {
      sent.add(s.get(j).word());
    }
  }
  sent.add(TaggerConstants.EOS_WORD);
  if (reuseTags) {
    this.originalTags = new ArrayList<String>(sz + 1);
    for (int j = 0; j < sz; ++j) {
      if (s.get(j) instanceof HasTag) {
        originalTags.add(((HasTag) s.get(j)).tag());
      } else {
        originalTags.add(null);
      }
    }
    originalTags.add(TaggerConstants.EOS_TAG);
  }
  size = sz + 1;
  if (VERBOSE) {
    System.err.println("Sentence is " + Sentence.listToString(sent, false, tagSeparator));
  }
  init();
  result = testTagInference();
  if (maxentTagger.wordFunction != null) {
    for (int j = 0; j < sz; ++j) {
      result.get(j).setWord(s.get(j).word());
    }
  }
  return result;
}