public NameSample read()

in opennlp-tools/src/main/java/opennlp/tools/formats/EvalitaNameSampleStream.java [111:210]
71 lines of code
25 McCabe index (conditional complexity)

  public NameSample read() throws IOException {

    List<String> sentence = new ArrayList<>();
    List<String> tags = new ArrayList<>();

    boolean isClearAdaptiveData = false;

    // Empty line indicates end of sentence
    String line;
    while ((line = lineStream.read()) != null && !StringUtil.isEmpty(line)) {

      if (line.startsWith(DOCSTART)) {
        isClearAdaptiveData = true;
        String emptyLine = lineStream.read();

        if (!StringUtil.isEmpty(emptyLine))
          throw new IOException("Empty line after -DOCSTART- not empty: '" + emptyLine + "'!");

        continue;
      }

      String[] fields = line.split(" ");

      // For Italian: WORD  POS-TAG SC-TAG NE-TAG
      if (LANGUAGE.IT.equals(lang) && fields.length == 4) {
        sentence.add(fields[0]);
        tags.add(fields[3]); // 3 is NE-TAG
      }
      else {
        throw new IOException("Incorrect number of fields per line for language: '" + line + "'!");
      }
    }

    // Always clear adaptive data for Italian
    if (LANGUAGE.IT.equals(lang))
      isClearAdaptiveData = true;

    if (!sentence.isEmpty()) {

      // convert name tags into spans
      List<Span> names = new ArrayList<>();

      int beginIndex = -1;
      int endIndex = -1;
      for (int i = 0; i < tags.size(); i++) {

        String tag = tags.get(i);

        if (tag.endsWith(ENT_TYPE_PER) && (types & GENERATE_PERSON_ENTITIES) == 0)
          tag = CODEC_TAG_O;

        if (tag.endsWith(ENT_TYPE_ORG) && (types & GENERATE_ORGANIZATION_ENTITIES) == 0)
          tag = CODEC_TAG_O;

        if (tag.endsWith(ENT_TYPE_LOC) && (types & GENERATE_LOCATION_ENTITIES) == 0)
          tag = CODEC_TAG_O;

        if (tag.endsWith(ENT_TYPE_GPE) && (types & GENERATE_GPE_ENTITIES) == 0)
          tag = CODEC_TAG_O;

        if (tag.startsWith(CODEC_TAG_B)) {

          if (beginIndex != -1) {
            names.add(extract(beginIndex, endIndex, tags.get(beginIndex)));
          }

          beginIndex = i;
          endIndex = i + 1;
        }
        else if (tag.startsWith(CODEC_TAG_I)) {
          endIndex++;
        }
        else if (tag.equals(CODEC_TAG_O)) {
          if (beginIndex != -1) {
            names.add(extract(beginIndex, endIndex, tags.get(beginIndex)));
            beginIndex = -1;
            endIndex = -1;
          }
        }
        else {
          throw new IOException("Invalid tag: " + tag);
        }
      }

      // if one span remains, create it here
      if (beginIndex != -1)
        names.add(extract(beginIndex, endIndex, tags.get(beginIndex)));

      return new NameSample(sentence.toArray(new String[0]),
          names.toArray(new Span[0]), isClearAdaptiveData);
    }
    else if (line != null) {
      // Just filter out empty events, if two lines in a row are empty
      return read();
    }
    else {
      // source stream is not returning anymore lines
      return null;
    }
  }