Examples with TreeReaderFactory edu.stanford.nlp.trees.TreeReaderFactory used on opensource projects

Example 6 with TreeReaderFactory

use of edu.stanford.nlp.trees.TreeReaderFactory in project CoreNLP by stanfordnlp.

the class ThreadedParserSlowITest method readTrees.

public static List<Tree> readTrees(String filename, String encoding) {
    ArrayList<Tree> trees = new ArrayList<Tree>();
    try {
        TreeReaderFactory trf = new LabeledScoredTreeReaderFactory();
        TreeReader tr = trf.newTreeReader(new InputStreamReader(new FileInputStream(filename), encoding));
        Tree next;
        while ((next = tr.readTree()) != null) {
            trees.add(next);
        }
        System.out.println("Read " + trees.size() + " trees from " + filename);
        return trees;
    } catch (IOException e) {
        throw new RuntimeException(e);
    }
}

Example 7 with TreeReaderFactory

use of edu.stanford.nlp.trees.TreeReaderFactory in project CoreNLP by stanfordnlp.

the class ATBCorrector method main.

//For those trees that lack a sentence-final punc, add one.
//    ("/^[^\\.!\\?]$/ >>- (__ > @ROOT <- __=loc) <: __\n"
//        + "insert (PUNC .) $- loc\n"
//        + "\n");
/**
   * @param args
   */
public static void main(String[] args) {
    if (args.length != 1) {
        log.info("Usage: java " + ATBCorrector.class.getName() + " filename\n");
        System.exit(-1);
    }
    TreeTransformer tt = new ATBCorrector();
    File f = new File(args[0]);
    try {
        BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(f), "UTF-8"));
        TreeReaderFactory trf = new ArabicTreeReaderFactory.ArabicRawTreeReaderFactory();
        TreeReader tr = trf.newTreeReader(br);
        int nTrees = 0;
        for (Tree t; (t = tr.readTree()) != null; nTrees++) {
            Tree fixedT = tt.transformTree(t);
            System.out.println(fixedT.toString());
        }
        tr.close();
        System.err.printf("Wrote %d trees%n", nTrees);
    } catch (UnsupportedEncodingException e) {
        e.printStackTrace();
    } catch (FileNotFoundException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    }
}

Example 8 with TreeReaderFactory

use of edu.stanford.nlp.trees.TreeReaderFactory in project CoreNLP by stanfordnlp.

the class SplitCanditoTrees method readTrees.

static Map<String, Tree> readTrees(String[] filenames) throws IOException {
    // TODO: perhaps we can just pass in CC_TAGSET and get rid of replacePOSTags
    // need to test that
    final TreeReaderFactory trf = new FrenchXMLTreeReaderFactory(false);
    Map<String, Tree> treeMap = Generics.newHashMap();
    for (String filename : filenames) {
        File file = new File(filename);
        String canonicalFilename = file.getName().substring(0, file.getName().lastIndexOf('.'));
        FrenchXMLTreeReader tr = (FrenchXMLTreeReader) trf.newTreeReader(new BufferedReader(new InputStreamReader(new FileInputStream(file), "ISO8859_1")));
        Tree t = null;
        int numTrees;
        for (numTrees = 0; (t = tr.readTree()) != null; numTrees++) {
            String id = canonicalFilename + "-" + ((CoreLabel) t.label()).get(CoreAnnotations.SentenceIDAnnotation.class);
            treeMap.put(id, t);
        }
        tr.close();
        System.err.printf("%s: %d trees%n", file.getName(), numTrees);
    }
    return treeMap;
}

Example 9 with TreeReaderFactory

use of edu.stanford.nlp.trees.TreeReaderFactory in project CoreNLP by stanfordnlp.

the class MultiWordPreprocessor method main.

/**
   *
   * @param args
   */
public static void main(String[] args) {
    Properties options = StringUtils.argsToProperties(args, argOptionDefs);
    if (!options.containsKey("") || options.containsKey("help")) {
        log.info(usage());
        return;
    }
    boolean retainNER = PropertiesUtils.getBool(options, "ner", false);
    boolean normalize = PropertiesUtils.getBool(options, "normalize", true);
    final File treeFile = new File(options.getProperty(""));
    TwoDimensionalCounter<String, String> labelTerm = new TwoDimensionalCounter<>();
    TwoDimensionalCounter<String, String> termLabel = new TwoDimensionalCounter<>();
    TwoDimensionalCounter<String, String> labelPreterm = new TwoDimensionalCounter<>();
    TwoDimensionalCounter<String, String> pretermLabel = new TwoDimensionalCounter<>();
    TwoDimensionalCounter<String, String> unigramTagger = new TwoDimensionalCounter<>();
    try {
        BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8"));
        TreeReaderFactory trf = new SpanishTreeReaderFactory();
        TreeReader tr = trf.newTreeReader(br);
        for (Tree t; (t = tr.readTree()) != null; ) {
            updateTagger(unigramTagger, t);
        }
        //Closes the underlying reader
        tr.close();
        System.out.println("Resolving DUMMY tags");
        resolveDummyTags(treeFile, unigramTagger, retainNER, normalize ? new SpanishTreeNormalizer(true, false, false) : null);
        System.out.println("#Unknown Word Types: " + ManualUWModel.nUnknownWordTypes);
        System.out.println(String.format("#Missing POS: %d (fixed: %d, %.2f%%)", nMissingPOS, nFixedPOS, (double) nFixedPOS / nMissingPOS * 100));
        System.out.println(String.format("#Missing Phrasal: %d (fixed: %d, %.2f%%)", nMissingPhrasal, nFixedPhrasal, (double) nFixedPhrasal / nMissingPhrasal * 100));
        System.out.println("Done!");
    } catch (UnsupportedEncodingException e) {
        e.printStackTrace();
    } catch (FileNotFoundException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    }
}

Example 10 with TreeReaderFactory

use of edu.stanford.nlp.trees.TreeReaderFactory in project CoreNLP by stanfordnlp.

the class MWEPreprocessor method main.

/**
   *
   * @param args
   */
public static void main(String[] args) {
    if (args.length != 1) {
        System.err.printf("Usage: java %s file%n", MWEPreprocessor.class.getName());
        System.exit(-1);
    }
    final File treeFile = new File(args[0]);
    TwoDimensionalCounter<String, String> labelTerm = new TwoDimensionalCounter<>();
    TwoDimensionalCounter<String, String> termLabel = new TwoDimensionalCounter<>();
    TwoDimensionalCounter<String, String> labelPreterm = new TwoDimensionalCounter<>();
    TwoDimensionalCounter<String, String> pretermLabel = new TwoDimensionalCounter<>();
    TwoDimensionalCounter<String, String> unigramTagger = new TwoDimensionalCounter<>();
    try {
        BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8"));
        TreeReaderFactory trf = new FrenchTreeReaderFactory();
        TreeReader tr = trf.newTreeReader(br);
        for (Tree t; (t = tr.readTree()) != null; ) {
            countMWEStatistics(t, unigramTagger, labelPreterm, pretermLabel, labelTerm, termLabel);
        }
        //Closes the underlying reader
        tr.close();
        System.out.println("Generating {MWE Type -> Terminal}");
        printCounter(labelTerm, "label_term.csv");
        System.out.println("Generating {Terminal -> MWE Type}");
        printCounter(termLabel, "term_label.csv");
        System.out.println("Generating {MWE Type -> POS sequence}");
        printCounter(labelPreterm, "label_pos.csv");
        System.out.println("Generating {POS sequence -> MWE Type}");
        printCounter(pretermLabel, "pos_label.csv");
        if (RESOLVE_DUMMY_TAGS) {
            System.out.println("Resolving DUMMY tags");
            resolveDummyTags(treeFile, pretermLabel, unigramTagger);
        }
        System.out.println("#Unknown Word Types: " + ManualUWModel.nUnknownWordTypes);
        System.out.println("#Missing POS: " + nMissingPOS);
        System.out.println("#Missing Phrasal: " + nMissingPhrasal);
        System.out.println("Done!");
    } catch (UnsupportedEncodingException e) {
        e.printStackTrace();
    } catch (FileNotFoundException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    }
}