Examples with TaggedWord edu.stanford.nlp.ling.TaggedWord used on opensource projects

Example 41 with TaggedWord

use of edu.stanford.nlp.ling.TaggedWord in project CoreNLP by stanfordnlp.

the class FindTreebankTree method main.

public static void main(String[] args) {
    // Args specified with -tagSeparator, -encoding, etc are assigned
    // to the appropriate option.  Otherwise, the first arg found is
    // the sentence to look for, and all other args are paths in which
    // to look for that sentence.
    String needle = "";
    String tagSeparator = "_";
    String encoding = "utf-8";
    String fileRegex = "";
    List<String> paths = new ArrayList<>();
    for (int i = 0; i < args.length; ++i) {
        if ((args[i].equalsIgnoreCase("-tagSeparator") || args[i].equalsIgnoreCase("--tagSeparator")) && i + 1 < args.length) {
            tagSeparator = args[i + 1];
            ++i;
        } else if ((args[i].equalsIgnoreCase("-encoding") || args[i].equalsIgnoreCase("--encoding")) && i + 1 < args.length) {
            encoding = args[i + 1];
            ++i;
        } else if ((args[i].equalsIgnoreCase("-fileRegex") || args[i].equalsIgnoreCase("--fileRegex")) && i + 1 < args.length) {
            fileRegex = args[i + 1];
            ++i;
        } else if (needle.equals("")) {
            needle = args[i].trim();
        } else {
            paths.add(args[i]);
        }
    }
    TreeReaderFactory trf = new LabeledScoredTreeReaderFactory();
    // If the user specified a regex, here we make a filter using that
    // regex.  We just use an anonymous class for the filter
    FileFilter filter = null;
    if (!fileRegex.equals("")) {
        final Pattern filePattern = Pattern.compile(fileRegex);
        filter = pathname -> (pathname.isDirectory() || filePattern.matcher(pathname.getName()).matches());
    }
    for (String path : paths) {
        // Start a new treebank with the given path, encoding, filter, etc
        DiskTreebank treebank = new DiskTreebank(trf, encoding);
        treebank.loadPath(path, filter);
        Iterator<Tree> treeIterator = treebank.iterator();
        int treeCount = 0;
        String currentFile = "";
        while (treeIterator.hasNext()) {
            // keep track of which file we are currently looking at
            if (!currentFile.equals(treebank.getCurrentFilename())) {
                currentFile = treebank.getCurrentFilename();
                treeCount = 0;
            }
            ++treeCount;
            Tree tree = treeIterator.next();
            List<TaggedWord> sentence = tree.taggedYield();
            boolean found = false;
            // The tree can match in one of three ways: tagged, untagged,
            // or untagged and unsegmented (which is useful for Chinese,
            // for example)
            String haystack = SentenceUtils.listToString(sentence, true);
            found = needle.equals(haystack);
            haystack = haystack.replaceAll(" ", "");
            found = found || needle.equals(haystack);
            haystack = SentenceUtils.listToString(sentence, false, tagSeparator);
            found = found || needle.equals(haystack);
            if (found) {
                System.out.println("needle found in " + currentFile + " tree " + treeCount);
            }
        }
    }
}

Example 42 with TaggedWord

use of edu.stanford.nlp.ling.TaggedWord in project CoreNLP by stanfordnlp.

the class TreeLemmatizer method transformTree.

@Override
public Tree transformTree(Tree t) {
    Morphology morphology = new Morphology();
    List<TaggedWord> tagged = null;
    int index = 0;
    for (Tree leaf : t.getLeaves()) {
        Label label = leaf.label();
        if (label == null) {
            continue;
        }
        String tag;
        if (!(label instanceof HasTag) || ((HasTag) label).tag() == null) {
            if (tagged == null) {
                tagged = t.taggedYield();
            }
            tag = tagged.get(index).tag();
        } else {
            tag = ((HasTag) label).tag();
        }
        if (!(label instanceof HasLemma)) {
            throw new IllegalArgumentException("Got a tree with labels which do not support lemma");
        }
        ((HasLemma) label).setLemma(morphology.lemma(label.value(), tag, true));
        ++index;
    }
    return t;
}

Example 43 with TaggedWord

use of edu.stanford.nlp.ling.TaggedWord in project CoreNLP by stanfordnlp.

the class TSVTaggedFileReaderTest method testReadBackwards.

public void testReadBackwards() throws IOException {
    File file = createTestFile();
    TaggedFileRecord record = createRecord(file, "tagColumn=0,wordColumn=1,");
    List<List<TaggedWord>> sentences = new ArrayList<List<TaggedWord>>();
    for (List<TaggedWord> sentence : record.reader()) {
        sentences.add(sentence);
    }
    assertEquals(3, sentences.size());
    assertEquals(3, sentences.get(0).size());
    assertEquals("A", sentences.get(0).get(0).tag());
    assertEquals("B", sentences.get(0).get(1).tag());
    assertEquals("C", sentences.get(0).get(2).tag());
    assertEquals("D", sentences.get(1).get(0).tag());
    assertEquals("E", sentences.get(1).get(1).tag());
    assertEquals("F", sentences.get(2).get(0).tag());
    assertEquals("1", sentences.get(0).get(0).word());
    assertEquals("2", sentences.get(0).get(1).word());
    assertEquals("3", sentences.get(0).get(2).word());
    assertEquals("4", sentences.get(1).get(0).word());
    assertEquals("5", sentences.get(1).get(1).word());
    assertEquals("6", sentences.get(2).get(0).word());
}