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

Example 21 with RuntimeIOException

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

the class PatternsSimpleThreadedITest method setUp.

@BeforeClass
public static void setUp() {
    nlpPipeline = new AnnotationPipeline();
    // We assume the input is already tokenized, so we use a cheap whitespace tokenizer.
    // The original code uses this property for the tokenizer:
    // props.setProperty("tokenize.options", "ptb3Escaping=false,normalizeParentheses=false,escapeForwardSlashAsterisk=false");
    nlpPipeline.addAnnotator(new TokenizerAnnotator(false, TokenizerType.Whitespace));
    nlpPipeline.addAnnotator(new WordsToSentencesAnnotator(false));
    nlpPipeline.addAnnotator(new POSTaggerAnnotator());
    nlpPipeline.addAnnotator(new MorphaAnnotator(false));
    Properties nerAnnotatorProperties = new Properties();
    nerAnnotatorProperties.setProperty("ner.useSUTime", Boolean.toString(false));
    nerAnnotatorProperties.setProperty("ner.applyFineGrained", Boolean.toString(false));
    // nerAnnotatorProperties.setProperty("ner.fine.regexner.mapping", spiedProperties.getProperty("fineGrainedRegexnerMapping"));
    try {
        nlpPipeline.addAnnotator(new NERCombinerAnnotator(nerAnnotatorProperties));
    } catch (IOException e) {
        throw new RuntimeIOException(e);
    }
}

Example 22 with RuntimeIOException

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

the class PatternsSimpleThreadedITest method runTest.

void runTest(String numThreads) {
    Properties spiedProperties = new Properties();
    final Path tempPath;
    try {
        tempPath = Files.createTempDirectory(null);
        spiedProperties.load(new InputStreamReader(new FileInputStream(new File("data/edu/stanford/nlp/patterns/patterns_itest.properties")), StandardCharsets.UTF_8));
    } catch (IOException e) {
        throw new RuntimeIOException(e);
    }
    Path outputPath = Paths.get(tempPath.toString(), "output");
    Path modelPath = Paths.get(tempPath.toString(), "model");
    Path docsentsPath = Paths.get(tempPath.toString(), "docsents.ser");
    System.out.println("Test " + numThreads + " writing to " + tempPath);
    spiedProperties.setProperty("seedWordsFiles", "VACCINE_PREVENTABLE_DISEASE,data/edu/stanford/nlp/patterns/VACCINE_PREVENTABLE_DISEASE.txt");
    // We generate this file below
    spiedProperties.setProperty("file", docsentsPath.toString());
    spiedProperties.setProperty("fileFormat", "ser");
    spiedProperties.setProperty("outDir", outputPath.toString());
    spiedProperties.setProperty("patternsWordsDir", modelPath.toString());
    spiedProperties.setProperty("loadSavedPatternsWordsDir", Boolean.toString(false));
    spiedProperties.setProperty("numThreads", numThreads);
    // Run the pipeline on an input document
    // Algorithm based on
    // https://github.com/stanfordnlp/CoreNLP/blob/a9a4c2d75b177790a24c0f46188810668d044cd8/src/edu/stanford/nlp/patterns/GetPatternsFromDataMultiClass.java#L702
    // useTargetParserParentRestriction is false
    final Annotation document = new Annotation("** If you survive measles without complications ** I love these . " + "Why would n't you survive without complications , Immunologist ?");
    nlpPipeline.annotate(document);
    // Convert annotation to map to serialize, similarly to the original code algorithm
    int i = 0;
    final Map<String, DataInstance> sentenceMap = new HashMap<>();
    for (final CoreMap sentence : document.get(SentencesAnnotation.class)) {
        sentenceMap.put(Integer.toString(i++), DataInstance.getNewInstance(PatternFactory.PatternType.SURFACE, sentence));
    }
    try (final ObjectOutputStream sentenceMapStream = new ObjectOutputStream(new FileOutputStream(docsentsPath.toString()))) {
        sentenceMapStream.writeObject(sentenceMap);
    } catch (IOException e) {
        throw new RuntimeIOException(e);
    }
    try {
        GetPatternsFromDataMultiClass.<SurfacePattern>run(spiedProperties);
    } catch (Exception e) {
        System.out.println("Test " + numThreads + " FAILED");
        System.out.println("  Intermediate files in " + tempPath);
        throw new RuntimeException(e);
    }
    System.out.println("Cleaning up temp files from " + tempPath);
    FileSystem.deleteDir(tempPath.toFile());
}

Example 23 with RuntimeIOException

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

the class CoNLL2011DocumentReader method getNextDocument.

public Document getNextDocument() {
    try {
        // DONE!
        if (curFileIndex >= fileList.size())
            return null;
        File curFile = fileList.get(curFileIndex);
        if (docIterator == null) {
            docIterator = new DocumentIterator(curFile.getAbsolutePath(), options);
        }
        while (!docIterator.hasNext()) {
            logger.info("Processed " + docIterator.docCnt + " documents in " + curFile.getAbsolutePath());
            docIterator.close();
            curFileIndex++;
            if (curFileIndex >= fileList.size()) {
                // DONE!
                return null;
            }
            curFile = fileList.get(curFileIndex);
            docIterator = new DocumentIterator(curFile.getAbsolutePath(), options);
        }
        Document next = docIterator.next();
        SieveCoreferenceSystem.logger.fine("Reading document: " + next.getDocumentID());
        return next;
    } catch (IOException ex) {
        throw new RuntimeIOException(ex);
    }
}

Example 24 with RuntimeIOException

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

the class SieveCoreferenceSystem method getSingletonPredictorFromSerializedFile.

public static LogisticClassifier<String, String> getSingletonPredictorFromSerializedFile(String serializedFile) {
    try {
        ObjectInputStream ois = IOUtils.readStreamFromString(serializedFile);
        Object o = ois.readObject();
        if (o instanceof LogisticClassifier<?, ?>) {
            return (LogisticClassifier<String, String>) o;
        }
        throw new ClassCastException("Wanted SingletonPredictor, got " + o.getClass());
    } catch (IOException e) {
        throw new RuntimeIOException(e);
    } catch (ClassNotFoundException e) {
        throw new RuntimeException(e);
    }
}

Example 25 with RuntimeIOException

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

the class Dictionaries method loadDemonymLists.

/**
 * The format of the demonyms file is
 *     countryCityOrState ( TAB demonym )*
 *  Lines starting with # are ignored
 *  The file is cased but stored in in-memory data structures uncased.
 *  The results are:
 *  demonyms is a hash from each country (etc.) to a set of demonymic Strings;
 *  adjectiveNation is a set of demonymic Strings;
 *  demonymSet has all country (etc.) names and all demonymic Strings.
 */
private void loadDemonymLists(String demonymFile) {
    BufferedReader reader = null;
    try {
        reader = IOUtils.readerFromString(demonymFile);
        for (String line; (line = reader.readLine()) != null; ) {
            line = line.toLowerCase(Locale.ENGLISH);
            String[] tokens = line.split("\t");
            if (tokens[0].startsWith("#"))
                continue;
            Set<String> set = Generics.newHashSet();
            for (String s : tokens) {
                set.add(s);
                demonymSet.add(s);
            }
            demonyms.put(tokens[0], set);
        }
        adjectiveNation.addAll(demonymSet);
        adjectiveNation.removeAll(demonyms.keySet());
    } catch (IOException e) {
        throw new RuntimeIOException(e);
    } finally {
        IOUtils.closeIgnoringExceptions(reader);
    }
}