import edu.stanford.nlp.io.RuntimeIOException; //导入依赖的package包/类
public static List<Pair<String, String>> readMacros(BufferedReader bin) {
  try {
    List<Pair<String, String>> macros = new ArrayList<Pair<String, String>>();
    String line;
    int lineNumber = 0;
    while ((line = bin.readLine()) != null) {
      ++lineNumber;
      String trimmed = line.trim();
      if (trimmed.equals("") || trimmed.charAt(0) == '#') {
        continue;
      }
      String[] pieces = line.split("\t", 2);
      if (pieces.length < 2) {
        throw new IllegalArgumentException("Expected lines of the format " +
                                           "original (tab) replacement.  " +
                                           "Line number " + lineNumber +
                                           " does not match.");
      }
      macros.add(new Pair<String, String>(pieces[0], pieces[1]));
    }
    return macros;
  } catch (IOException e) {
    throw new RuntimeIOException(e);
  }
}
 

import edu.stanford.nlp.io.RuntimeIOException; //导入依赖的package包/类
/**
 * Internally fetches the next token.
 *
 * @return the next token in the token stream, or null if none exists.
 */
@Override
@SuppressWarnings("unchecked")
protected T getNext() {
  // if (lexer == null) {
  //   return null;
  // }
  try {
    return (T) lexer.next();
  } catch (IOException e) {
    throw new RuntimeIOException(e);
  }
  // cdm 2007: this shouldn't be necessary: PTBLexer decides for itself whether to return CRs based on the same flag!
  // get rid of CRs if necessary
  // while (!tokenizeNLs && PTBLexer.cr.equals(((HasWord) token).word())) {
  //   token = (T)lexer.next();
  // }

  // horatio: we used to catch exceptions here, which led to broken
  // behavior and made it very difficult to debug whatever the
  // problem was.
}
 

import edu.stanford.nlp.io.RuntimeIOException; //导入依赖的package包/类
private static RVFDataset<String, String> readSVMLightFormat(String filename, Index<String> featureIndex, Index<String> labelIndex, List<String> lines) {
  BufferedReader in = null;
  RVFDataset<String, String> dataset;
  try {
    dataset = new RVFDataset<String, String>(10, featureIndex, labelIndex);
    in = new BufferedReader(new FileReader(filename));

    while (in.ready()) {
      String line = in.readLine();
      if (lines != null)
        lines.add(line);
      dataset.add(svmLightLineToRVFDatum(line));
    }
  } catch (IOException e) {
    throw new RuntimeIOException(e);
  } finally {
    IOUtils.closeIgnoringExceptions(in);
  }
  return dataset;
}
 

import edu.stanford.nlp.io.RuntimeIOException; //导入依赖的package包/类
/**
 * This method reads in properties listed in a file in the format prop=value, one property per line.
 * Although <code>Properties.load(InputStream)</code> exists, I implemented this method to trim the lines,
 * something not implemented in the <code>load()</code> method.
 * @param filename A properties file to read
 * @return The corresponding Properties object
 */
public static Properties propFileToProperties(String filename) {
  Properties result = new Properties();
  try {
    InputStream is = new BufferedInputStream(new FileInputStream(filename));
    result.load(is);
    // trim all values
    for (Object propKey : result.keySet()){
      String newVal = result.getProperty((String)propKey);
      result.setProperty((String)propKey,newVal.trim());
    }
    is.close();
    return result;
  } catch (IOException e) {
    throw new RuntimeIOException("propFileToProperties could not read properties file: " + filename, e);
  }
}
 

import edu.stanford.nlp.io.RuntimeIOException; //导入依赖的package包/类
@Override
@SuppressWarnings("unchecked")
protected T getNext() {
  try {
    T nextToken = null;
    // Depending on the orthographic normalization options,
    // some tokens can be obliterated. In this case, keep iterating
    // until we see a non-zero length token.
    do {
      nextToken = (T) lexer.next();
    } while (nextToken != null && nextToken.word().length() == 0);

    return nextToken;

  } catch (IOException e) {
    throw new RuntimeIOException(e);
  }
}
 

import edu.stanford.nlp.io.RuntimeIOException; //导入依赖的package包/类
protected void save(DataOutputStream file,
                    Map<String, Set<String>> tagTokens) {
  try {
    file.writeInt(index.size());
    for (String item : index) {
      file.writeUTF(item);
      if (learnClosedTags) {
        if (tagTokens.get(item).size() < closedTagThreshold) {
          markClosed(item);
        }
      }
      file.writeBoolean(isClosed(item));
    }
  } catch (IOException e) {
    throw new RuntimeIOException(e);
  }
}
 

import edu.stanford.nlp.io.RuntimeIOException; //导入依赖的package包/类
public void outputTaggedSentence(List<? extends HasWord> sentence,
                                 boolean outputLemmas, OutputStyle outputStyle,
                                 boolean outputVerbosity, int numSentences,
                                 String separator, Writer writer) {
  try {
    switch (outputStyle) {
    case TSV:
      writer.write(getTsvWords(outputVerbosity, outputLemmas, sentence));
      break;
    case XML:
    case INLINE_XML:
      writeXMLSentence(writer, sentence, numSentences, outputLemmas);
      break;
    case SLASH_TAGS:
      writer.write(Sentence.listToString(sentence, false, config.getTagSeparator()));
      writer.write(separator);
      break;
    default:
      throw new IllegalArgumentException("Unsupported output style " + outputStyle);
    }
  } catch (IOException e) {
    throw new RuntimeIOException(e);
  }
}
 

import edu.stanford.nlp.io.RuntimeIOException; //导入依赖的package包/类
private void loadDemonymLists(String demonymFile) {
  BufferedReader reader = null;
  try {
    reader = IOUtils.readerFromString(demonymFile);
    while(reader.ready()){
      String[] line = reader.readLine().split("\t");
      if(line[0].startsWith("#")) continue;
      Set<String> set = Generics.newHashSet();
      for(String s : line){
        set.add(s.toLowerCase());
        demonymSet.add(s.toLowerCase());
      }
      demonyms.put(line[0].toLowerCase(), set);
    }
    adjectiveNation.addAll(demonymSet);
    adjectiveNation.removeAll(demonyms.keySet());
  } catch (IOException e){
    throw new RuntimeIOException(e);
  } finally {
    IOUtils.closeIgnoringExceptions(reader);
  }
}
 

import edu.stanford.nlp.io.RuntimeIOException; //导入依赖的package包/类
private void loadGenderNumber(String file){
  try {
    BufferedReader reader = IOUtils.readerFromString(file);
    String line;
    while ((line = reader.readLine())!=null){
      String[] split = line.split("\t");
      List<String> tokens = new ArrayList<String>(Arrays.asList(split[0].split(" ")));
      String[] countStr = split[1].split(" ");
      int[] counts = new int[4];
      counts[0] = Integer.parseInt(countStr[0]);
      counts[1] = Integer.parseInt(countStr[1]);
      counts[2] = Integer.parseInt(countStr[2]);
      counts[3] = Integer.parseInt(countStr[3]);

      genderNumber.put(tokens, counts);
    }
    reader.close();
  } catch (IOException e) {
    throw new RuntimeIOException(e);
  }
}
 

import edu.stanford.nlp.io.RuntimeIOException; //导入依赖的package包/类
public Document getNextDocument()
{
  try {
    if (curFileIndex >= fileList.size()) return null;  // DONE!
    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()) {
        return null;  // DONE!
      }
      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);
  }
}
 

import edu.stanford.nlp.io.RuntimeIOException; //导入依赖的package包/类
public static List<Pair<String, String>> readMacros(BufferedReader bin) {
  try {
    List<Pair<String, String>> macros = new ArrayList<Pair<String, String>>();
    String line;
    int lineNumber = 0;
    while ((line = bin.readLine()) != null) {
      ++lineNumber;
      String trimmed = line.trim();
      if (trimmed.equals("") || trimmed.charAt(0) == '#') {
        continue;
      }
      String[] pieces = line.split("\t", 2);
      if (pieces.length < 2) {
        throw new IllegalArgumentException("Expected lines of the format " + 
                                           "original (tab) replacement.  " +
                                           "Line number " + lineNumber + 
                                           " does not match.");
      }
      macros.add(new Pair<String, String>(pieces[0], pieces[1]));
    }
    return macros;
  } catch (IOException e) {
    throw new RuntimeIOException(e);
  }
}
 

import edu.stanford.nlp.io.RuntimeIOException; //导入依赖的package包/类
/** A TagCount object's fields are read from the file. They are read from
  *  the current position and the file is not closed afterwards.
  */
 public static TagCount readTagCount(DataInputStream rf) {
   try {
     TagCount tc = new TagCount();
     int numTags = rf.readInt();
     tc.map = Generics.newHashMap(numTags);

     for (int i = 0; i < numTags; i++) {
String tag = rf.readUTF();
       int count = rf.readInt();

if (tag.equals(NULL_SYMBOL)) tag = null;
tc.map.put(tag, count);
     }

     tc.getTagsCache = tc.map.keySet().toArray(new String[tc.map.keySet().size()]);
     tc.sumCache = tc.calculateSumCache();
     return tc;
   } catch (IOException e) {
     throw new RuntimeIOException(e);
   }
 }
 

import edu.stanford.nlp.io.RuntimeIOException; //导入依赖的package包/类
/**
 * Create a new KBP annotator from the given properties.
 *
 * @param props The properties to use when creating this extractor.
 */
public IntelKBPAnnotator(String name, Properties props) {
    // Parse standard properties  
    ArgumentParser.fillOptions(this, name, props);

    // Load the extractor 
    try {
        this.extractor = new IntelKBPEnsembleExtractor(
                new IntelKBPTokensregexExtractor(tokensregexdir),
                new IntelKBPSemgrexExtractor(semgrexdir),
                IntelKBPStatisticalExtractor.loadStatisticalExtractor(),
                DefaultKBPStatisticalExtractor.loadStatisticalExtractor()
        ).setEnsembleStrategy(IntelConfig.ENSEMBLE_STRATEGY);
        
    } catch (IOException | ClassNotFoundException e) {
        throw new RuntimeIOException(e);
    }


    // Load TokensRegexNER
/*this.casedNER = new TokensRegexNERAnnotator(
    regexnerCasedPath,
    false);
this.caselessNER = new TokensRegexNERAnnotator(
    regexnerCaselessPath,
    true,
    "^(NN|JJ).*");*/

    // Create entity mention annotator
    this.entityMentionAnnotator = new EntityMentionsAnnotator("kbp.entitymention", new Properties() {{
        setProperty("kbp.entitymention.acronyms", "true");
        setProperty("acronyms", "true");
    }});
}
 

import edu.stanford.nlp.io.RuntimeIOException; //导入依赖的package包/类
public static void main(String[] args) throws IOException {
    RedwoodConfiguration.standard().apply();  // Disable SLF4J crap.
    ArgumentParser.fillOptions(IntelKBPSemgrexExtractor.class, args);
    IntelKBPSemgrexExtractor extractor = new IntelKBPSemgrexExtractor(DIR);
    List<Pair<KBPInput, String>> testExamples = DatasetUtils.readDataset(TEST_FILE);

    extractor.computeAccuracy(testExamples.stream(), PREDICTIONS.map(x -> {
        try {
            return "stdout".equalsIgnoreCase(x) ? System.out : new PrintStream(new FileOutputStream(x));
        } catch (IOException e) {
            throw new RuntimeIOException(e);
        }
    }));
}
 

import edu.stanford.nlp.io.RuntimeIOException; //导入依赖的package包/类
public static void main(String[] args) throws IOException {
    RedwoodConfiguration.standard().apply();  // Disable SLF4J crap.
    ArgumentParser.fillOptions(IntelKBPTokensregexExtractor.class, args);
    IntelKBPTokensregexExtractor extractor = new IntelKBPTokensregexExtractor(DIR);
    List<Pair<KBPInput, String>> testExamples = DatasetUtils.readDataset(TEST_FILE);

    extractor.computeAccuracy(testExamples.stream(), PREDICTIONS.map(x -> {
        try {
            return "stdout".equalsIgnoreCase(x) ? System.out : new PrintStream(new FileOutputStream(x));
        } catch (IOException e) {
            throw new RuntimeIOException(e);
        }
    }));

}
 

import edu.stanford.nlp.io.RuntimeIOException; //导入依赖的package包/类
public static void main(String[] args) throws IOException, ClassNotFoundException {
    RedwoodConfiguration.standard().apply();  // Disable SLF4J crap.
    ArgumentParser.fillOptions(edu.stanford.nlp.ie.KBPEnsembleExtractor.class, args);

    Object object = IOUtils.readObjectFromURLOrClasspathOrFileSystem(STATISTICAL_MODEL);
    IntelKBPRelationExtractor statisticalExtractor;
    if (object instanceof LinearClassifier) {
        //noinspection unchecked
        statisticalExtractor = new IntelKBPStatisticalExtractor((Classifier<String, String>) object);
    } else if (object instanceof IntelKBPStatisticalExtractor) {
        statisticalExtractor = (IntelKBPStatisticalExtractor) object;
    } else {
        throw new ClassCastException(object.getClass() + " cannot be cast into a " + IntelKBPStatisticalExtractor.class);
    }
    logger.info("Read statistical model from " + STATISTICAL_MODEL);
    IntelKBPRelationExtractor extractor = new IntelKBPEnsembleExtractor(
            new IntelKBPTokensregexExtractor(TOKENSREGEX_DIR),
            new IntelKBPSemgrexExtractor(SEMGREX_DIR),
            statisticalExtractor
    );

    List<Pair<KBPInput, String>> testExamples = DatasetUtils.readDataset(TEST_FILE);

    extractor.computeAccuracy(testExamples.stream(), PREDICTIONS.map(x -> {
        try {
            return "stdout".equalsIgnoreCase(x) ? System.out : new PrintStream(new FileOutputStream(x));
        } catch (IOException e) {
            throw new RuntimeIOException(e);
        }
    }));

}
 

import edu.stanford.nlp.io.RuntimeIOException; //导入依赖的package包/类
public static void main(String[] args) throws IOException {
  RedwoodConfiguration.standard().apply();  // Disable SLF4J crap.
  ArgumentParser.fillOptions(edu.stanford.nlp.ie.KBPSemgrexExtractor.class, args);
  edu.stanford.nlp.ie.KBPSemgrexExtractor extractor = new edu.stanford.nlp.ie.KBPSemgrexExtractor(DIR);
  List<Pair<KBPInput, String>> testExamples = KBPRelationExtractor.readDataset(TEST_FILE);

  extractor.computeAccuracy(testExamples.stream(), PREDICTIONS.map(x -> {
    try {
      return "stdout".equalsIgnoreCase(x) ? System.out : new PrintStream(new FileOutputStream(x));
    } catch (IOException e) {
      throw new RuntimeIOException(e);
    }
  }));
}
 

import edu.stanford.nlp.io.RuntimeIOException; //导入依赖的package包/类
public static void main(String[] args) throws IOException {
  RedwoodConfiguration.standard().apply();  // Disable SLF4J crap.
  ArgumentParser.fillOptions(edu.stanford.nlp.ie.KBPTokensregexExtractor.class, args);
  edu.stanford.nlp.ie.KBPTokensregexExtractor extractor = new edu.stanford.nlp.ie.KBPTokensregexExtractor(DIR);
  List<Pair<KBPInput, String>> testExamples = KBPRelationExtractor.readDataset(TEST_FILE);

  extractor.computeAccuracy(testExamples.stream(), PREDICTIONS.map(x -> {
    try {
      return "stdout".equalsIgnoreCase(x) ? System.out : new PrintStream(new FileOutputStream(x));
    } catch (IOException e) {
      throw new RuntimeIOException(e);
    }
  }));

}
 

import edu.stanford.nlp.io.RuntimeIOException; //导入依赖的package包/类
public static void main(String[] args) throws IOException, ClassNotFoundException {
  RedwoodConfiguration.standard().apply();  // Disable SLF4J crap.
  ArgumentParser.fillOptions(edu.stanford.nlp.ie.KBPEnsembleExtractor.class, args);

  Object object = IOUtils.readObjectFromURLOrClasspathOrFileSystem(STATISTICAL_MODEL);
  edu.stanford.nlp.ie.KBPRelationExtractor statisticalExtractor;
  if (object instanceof LinearClassifier) {
    //noinspection unchecked
    statisticalExtractor = new IntelKBPStatisticalExtractor((Classifier<String, String>) object);
  } else if (object instanceof IntelKBPStatisticalExtractor) {
    statisticalExtractor = (IntelKBPStatisticalExtractor) object;
  } else {
    throw new ClassCastException(object.getClass() + " cannot be cast into a " + IntelKBPStatisticalExtractor.class);
  }
  logger.info("Read statistical model from " + STATISTICAL_MODEL);
  edu.stanford.nlp.ie.KBPRelationExtractor extractor = new edu.stanford.nlp.ie.KBPEnsembleExtractor(
      new IntelKBPTokensregexExtractor(TOKENSREGEX_DIR),
      new IntelKBPSemgrexExtractor(SEMGREX_DIR),
      statisticalExtractor
  );

  List<Pair<KBPInput, String>> testExamples = KBPRelationExtractor.readDataset(TEST_FILE);

  extractor.computeAccuracy(testExamples.stream(), PREDICTIONS.map(x -> {
    try {
      return "stdout".equalsIgnoreCase(x) ? System.out : new PrintStream(new FileOutputStream(x));
    } catch (IOException e) {
      throw new RuntimeIOException(e);
    }
  }));

}
 

import edu.stanford.nlp.io.RuntimeIOException; //导入依赖的package包/类
public SzTECoreNLP(String propsFileNamePrefix, boolean enforceRequirements) {
  Properties props = loadProperties(propsFileNamePrefix);
  if (props == null) {
    throw new RuntimeIOException("ERROR: cannot find properties file \"" + propsFileNamePrefix
        + "\" in the classpath!");
  }
  construct(props, enforceRequirements);
}