edu.stanford.nlp.tagger.io.TextTaggedFileReader Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of stanford-corenlp Show documentation

Stanford CoreNLP provides a set of natural language analysis tools which can take raw English language text input and give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize dates, times, and numeric quantities, mark up the structure of sentences in terms of phrases and word dependencies, and indicate which noun phrases refer to the same entities. It provides the foundational building blocks for higher level text understanding applications.

There is a newer version: 4.5.7

Show newest version

package edu.stanford.nlp.tagger.io;

import java.io.BufferedReader;
import java.io.FileInputStream;
import java.io.InputStreamReader;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import java.util.NoSuchElementException;
import java.util.StringTokenizer;
import edu.stanford.nlp.ling.TaggedWord;

public class TextTaggedFileReader implements TaggedFileReader {
  final BufferedReader reader;
  final String tagSeparator;
  final String filename;

  int numSentences = 0;

  List next;

  public TextTaggedFileReader(TaggedFileRecord record) {
    filename = record.file;
    try {
      reader = new BufferedReader(new InputStreamReader
                                  (new FileInputStream(filename), 
                                   record.encoding));
    } catch (IOException e) {
      throw new RuntimeException(e);
    }
    tagSeparator = record.tagSeparator;

    primeNext();
  }

  public Iterator> iterator() { return this; }

  public String filename() { return filename; }

  public boolean hasNext() { return next != null; }

  public List next() {
    if (next == null) {
      throw new NoSuchElementException();
    }
    List thisIteration = next;
    primeNext();
    return thisIteration;
  }

  void primeNext() {
    String line;
    try {
      line = reader.readLine();
    } catch (IOException e) {
      throw new RuntimeException(e);
    }
    if (line == null) {
      next = null;
      return;
    }

    ++numSentences;
    next = new ArrayList<>();
    StringTokenizer st = new StringTokenizer(line);
    //loop over words in a single sentence

    while (st.hasMoreTokens()) {
      String token = st.nextToken();

      int indexUnd = token.lastIndexOf(tagSeparator);
      if (indexUnd < 0) {
        throw new IllegalArgumentException("Data format error: can't find delimiter \"" + tagSeparator + "\" in word \"" + token + "\" (line " + (numSentences+1) + " of " + filename + ')');
      }
      String word = token.substring(0, indexUnd).intern();
      String tag = token.substring(indexUnd + 1).intern();
      next.add(new TaggedWord(word, tag));
    }
  }

  public void remove() { throw new UnsupportedOperationException(); }
}