Examples with RuntimeIOException edu.stanford.nlp.io.RuntimeIOException used on opensource projects

Example 31 with RuntimeIOException

use of edu.stanford.nlp.io.RuntimeIOException in project CoreNLP by stanfordnlp.

the class CacheParseHypotheses method convertToTrees.

public static List<Tree> convertToTrees(byte[] input) {
    try {
        List<Tree> output = new ArrayList<>();
        ByteArrayInputStream bis = new ByteArrayInputStream(input);
        GZIPInputStream gis = new GZIPInputStream(bis);
        ObjectInputStream ois = new ObjectInputStream(gis);
        int size = ErasureUtils.<Integer>uncheckedCast(ois.readObject());
        for (int i = 0; i < size; ++i) {
            String rawTree = ErasureUtils.uncheckedCast(ois.readObject());
            Tree tree = Tree.valueOf(rawTree, trf);
            tree.setSpans();
            output.add(tree);
        }
        ois.close();
        gis.close();
        bis.close();
        return output;
    } catch (IOException e) {
        throw new RuntimeIOException(e);
    } catch (ClassNotFoundException e) {
        throw new RuntimeException(e);
    }
}

Example 32 with RuntimeIOException

use of edu.stanford.nlp.io.RuntimeIOException in project CoreNLP by stanfordnlp.

the class CustomAnnotationSerializer method loadToken.

private static CoreLabel loadToken(String line, boolean haveExplicitAntecedent) {
    CoreLabel token = new CoreLabel();
    String[] bits = line.split("\t", -1);
    if (bits.length < 7)
        throw new RuntimeIOException("ERROR: Invalid format token for serialized token (only " + bits.length + " tokens): " + line);
    // word
    String word = bits[0].replaceAll(SPACE_HOLDER, " ");
    token.set(CoreAnnotations.TextAnnotation.class, word);
    token.set(CoreAnnotations.ValueAnnotation.class, word);
    // lemma
    if (bits[1].length() > 0 || bits[0].length() == 0) {
        String lemma = bits[1].replaceAll(SPACE_HOLDER, " ");
        token.set(CoreAnnotations.LemmaAnnotation.class, lemma);
    }
    // POS tag
    if (bits[2].length() > 0)
        token.set(CoreAnnotations.PartOfSpeechAnnotation.class, bits[2]);
    // NE tag
    if (bits[3].length() > 0)
        token.set(CoreAnnotations.NamedEntityTagAnnotation.class, bits[3]);
    // Normalized NE tag
    if (bits[4].length() > 0)
        token.set(CoreAnnotations.NormalizedNamedEntityTagAnnotation.class, bits[4]);
    // Character offsets
    if (bits[5].length() > 0)
        token.set(CoreAnnotations.CharacterOffsetBeginAnnotation.class, Integer.parseInt(bits[5]));
    if (bits[6].length() > 0)
        token.set(CoreAnnotations.CharacterOffsetEndAnnotation.class, Integer.parseInt(bits[6]));
    if (haveExplicitAntecedent) {
        // We may have AntecedentAnnotation
        if (bits.length > 7) {
            String aa = bits[7].replaceAll(SPACE_HOLDER, " ");
            if (aa.length() > 0)
                token.set(CoreAnnotations.AntecedentAnnotation.class, aa);
        }
    }
    return token;
}

Example 33 with RuntimeIOException

use of edu.stanford.nlp.io.RuntimeIOException in project CoreNLP by stanfordnlp.

the class ColumnDataClassifier method loadWordVectors.

private static Map<String, float[]> loadWordVectors(String filename) {
    Timing timing = new Timing();
    // presumably they'll load a fair-sized vocab!?
    Map<String, float[]> map = new HashMap<>(10000);
    try (BufferedReader br = IOUtils.readerFromString(filename)) {
        int numDimensions = -1;
        boolean warned = false;
        for (String line; (line = br.readLine()) != null; ) {
            String[] fields = line.split("\\s+");
            if (numDimensions < 0) {
                numDimensions = fields.length - 1;
            } else {
                if (numDimensions != fields.length - 1 && !warned) {
                    logger.info("loadWordVectors: Inconsistent vector size: " + numDimensions + " vs. " + (fields.length - 1));
                    warned = true;
                }
            }
            float[] vector = new float[fields.length - 1];
            for (int i = 1; i < fields.length; i++) {
                vector[i - 1] = Float.parseFloat(fields[i]);
            }
            map.put(fields[0], vector);
        }
    } catch (IOException ioe) {
        throw new RuntimeIOException("Couldn't load word vectors", ioe);
    }
    timing.done("Loading word vectors from " + filename + " ... ");
    return map;
}

Example 34 with RuntimeIOException

use of edu.stanford.nlp.io.RuntimeIOException in project CoreNLP by stanfordnlp.

the class LinearClassifierFactory method loadFromFilename.

/**
 * Given the path to a file representing the text based serialization of a
 * Linear Classifier, reconstitutes and returns that LinearClassifier.
 *
 * TODO: Leverage Index
 */
public static LinearClassifier<String, String> loadFromFilename(String file) {
    try {
        BufferedReader in = IOUtils.readerFromString(file);
        // Format: read indices first, weights, then thresholds
        Index<String> labelIndex = HashIndex.loadFromReader(in);
        Index<String> featureIndex = HashIndex.loadFromReader(in);
        double[][] weights = new double[featureIndex.size()][labelIndex.size()];
        int currLine = 1;
        String line = in.readLine();
        while (line != null && line.length() > 0) {
            String[] tuples = line.split(LinearClassifier.TEXT_SERIALIZATION_DELIMITER);
            if (tuples.length != 3) {
                throw new Exception("Error: incorrect number of tokens in weight specifier, line=" + currLine + " in file " + file);
            }
            currLine++;
            int feature = Integer.parseInt(tuples[0]);
            int label = Integer.parseInt(tuples[1]);
            double value = Double.parseDouble(tuples[2]);
            weights[feature][label] = value;
            line = in.readLine();
        }
        // First line in thresholds is the number of thresholds
        int numThresholds = Integer.parseInt(in.readLine());
        double[] thresholds = new double[numThresholds];
        int curr = 0;
        while ((line = in.readLine()) != null) {
            double tval = Double.parseDouble(line.trim());
            thresholds[curr++] = tval;
        }
        in.close();
        LinearClassifier<String, String> classifier = new LinearClassifier<>(weights, featureIndex, labelIndex);
        return classifier;
    } catch (Exception e) {
        throw new RuntimeIOException("Error in LinearClassifierFactory, loading from file=" + file, e);
    }
}

Example 35 with RuntimeIOException

use of edu.stanford.nlp.io.RuntimeIOException in project CoreNLP by stanfordnlp.

the class CRFClassifier method serializeClassifier.

/**
 * Serialize the classifier to the given ObjectOutputStream.
 * <br>
 * (Since the classifier is a processor, we don't want to serialize the
 * whole classifier but just the data that represents a classifier model.)
 */
@Override
public void serializeClassifier(ObjectOutputStream oos) {
    try {
        oos.writeObject(labelIndices);
        oos.writeObject(classIndex);
        oos.writeObject(featureIndex);
        oos.writeObject(flags);
        if (flags.useEmbedding) {
            oos.writeObject(embeddings);
        }
        // For some reason, writing out the array of FeatureFactory
        // objects doesn't seem to work.  The resulting classifier
        // doesn't have the lexicon (distsim object) correctly saved.  So now custom write the list
        oos.writeObject(featureFactories.size());
        for (FeatureFactory<IN> ff : featureFactories) {
            oos.writeObject(ff);
        }
        oos.writeInt(windowSize);
        oos.writeObject(weights);
        // oos.writeObject(WordShapeClassifier.getKnownLowerCaseWords());
        oos.writeObject(knownLCWords);
        if (labelDictionary != null) {
            oos.writeObject(labelDictionary);
        }
    } catch (IOException e) {
        throw new RuntimeIOException(e);
    }
}