Java Document类代码示例

import edu.stanford.nlp.ling.Document; //导入依赖的package包/类
/**
 * This will do the escaping on an input file. Input file must already be tokenized,
 * with tokens separated by whitespace. <br>
 * Usage: java edu.stanford.nlp.process.PTBEscapingProcessor fileOrUrl
 *
 * @param args Command line argument: a file or URL
 */
public static void main(String[] args) {
  if (args.length != 1) {
    System.out.println("usage: java edu.stanford.nlp.process.PTBEscapingProcessor fileOrUrl");
    System.exit(0);
  }
  String filename = args[0];
  try {
    Document<String, Word, Word> d; // initialized below
    if (filename.startsWith("http://")) {
      Document<String, Word, Word> dpre = new BasicDocument<String>(WhitespaceTokenizer.factory()).init(new URL(filename));
      DocumentProcessor<Word, Word, String, Word> notags = new StripTagsProcessor<String, Word>();
      d = notags.processDocument(dpre);
    } else {
      d = new BasicDocument<String>(WhitespaceTokenizer.factory()).init(new File(filename));
    }
    DocumentProcessor<Word, HasWord, String, Word> proc = new PTBEscapingProcessor<Word, String, Word>();
    Document<String, Word, HasWord> newD = proc.processDocument(d);
    for (HasWord word : newD) {
      System.out.println(word);
    }
  } catch (Exception e) {
    e.printStackTrace();
  }

}
 

import edu.stanford.nlp.ling.Document; //导入依赖的package包/类
/**
 * This will do the escaping on an input file. Input file should already be tokenized,
 * with tokens separated by whitespace. <br>
 * Usage: java edu.stanford.nlp.process.PTBEscapingProcessor fileOrUrl
 *
 * @param args Command line argument: a file or URL
 */
public static void main(String[] args) {
  if (args.length != 1) {
    System.out.println("usage: java edu.stanford.nlp.process.PTBEscapingProcessor fileOrUrl");
    return;
  }
  String filename = args[0];
  try {
    Document<String, Word, Word> d; // initialized below
    if (filename.startsWith("http://")) {
      Document<String, Word, Word> dpre = new BasicDocument<String>(WhitespaceTokenizer.factory()).init(new URL(filename));
      DocumentProcessor<Word, Word, String, Word> notags = new StripTagsProcessor<String, Word>();
      d = notags.processDocument(dpre);
    } else {
      d = new BasicDocument<String>(WhitespaceTokenizer.factory()).init(new File(filename));
    }
    DocumentProcessor<Word, HasWord, String, Word> proc = new PTBEscapingProcessor<Word, String, Word>();
    Document<String, Word, HasWord> newD = proc.processDocument(d);
    for (HasWord word : newD) {
      System.out.println(word);
    }
  } catch (Exception e) {
    e.printStackTrace();
  }

}
 

import edu.stanford.nlp.ling.Document; //导入依赖的package包/类
/**
 * For internal debugging purposes only.
 */
public static void main(String[] args) {
  new BasicDocument<String>();
  Document<String, Word, Word> htmlDoc = BasicDocument.init("top text <h1>HEADING text</h1> this is <p>new paragraph<br>next line<br/>xhtml break etc.");
  System.out.println("Before:");
  System.out.println(htmlDoc);
  Document<String, Word, Word> txtDoc = new StripTagsProcessor<String, Word>(true).processDocument(htmlDoc);
  System.out.println("After:");
  System.out.println(txtDoc);
  Document<String, Word, List<Word>> sentences = new WordToSentenceProcessor<Word>().processDocument(txtDoc);
  System.out.println("Sentences:");
  System.out.println(sentences);
}
 

import edu.stanford.nlp.ling.Document; //导入依赖的package包/类
/**
 * This will print out some text, recognizing tags.  It can be used to
 * test tag breaking.  <br>  Usage: <code>
 * java edu.stanford.nlp.process.WordToTaggedWordProcessor fileOrUrl
 * </code>
 *
 * @param args Command line argument: a file or URL
 */
public static void main(String[] args) {
  if (args.length != 1) {
    System.out.println("usage: java edu.stanford.nlp.process.WordToTaggedWordProcessor fileOrUrl");
    System.exit(0);
  }
  String filename = args[0];
  try {
    Document<HasWord, Word, Word> d;
    if (filename.startsWith("http://")) {
      Document<HasWord, Word, Word> dpre = new BasicDocument<HasWord>().init(new URL(filename));
      DocumentProcessor<Word, Word, HasWord, Word> notags = new StripTagsProcessor<HasWord, Word>();
      d = notags.processDocument(dpre);
    } else {
      d = new BasicDocument<HasWord>().init(new File(filename));
    }
    DocumentProcessor<Word, HasWord, HasWord, Word> proc = new WordToTaggedWordProcessor<Word, HasWord, Word>();
    Document<HasWord, Word, HasWord> sentd = proc.processDocument(d);
    // System.out.println(sentd);
    int i = 0;
    for (HasWord w : sentd) {
      System.out.println(i + ": " + w);
      i++;
    }
  } catch (Exception e) {
    e.printStackTrace();
  }
}
 

import edu.stanford.nlp.ling.Document; //导入依赖的package包/类
public Document<L, F, OUT> processDocument(Document<L, F, IN> in) {
  Document<L, F, OUT> doc = in.blankDocument();
  doc.addAll(process(in));
  return doc;
}
 

import edu.stanford.nlp.ling.Document; //导入依赖的package包/类
public <L, F> Document<L, F, List<IN>> processDocument(Document<L, F, IN> in) {
  Document<L, F, List<IN>> doc = in.blankDocument();
  doc.addAll(process(in));
  return doc;
}
 

import edu.stanford.nlp.ling.Document; //导入依赖的package包/类
/**
 * Converts a Document to a different Document, by transforming
 * or filtering the original Document. The general contract of this method
 * is to not modify the <code>in</code> Document in any way, and to
 * preserve the metadata of the <code>in</code> Document in the
 * returned Document.
 *
 * @see FunctionProcessor
 */
public Document<L, F, OUT> processDocument(Document<L, F, IN> in);