Ejemplo n.º 1
0
  private boolean readData(boolean dump) throws IOException {
    if (m_sourceReader == null) {
      throw new IOException("No source has been specified");
    }

    boolean finished = false;
    do {
      String checked = getInstance(m_st);
      if (checked == null) {
        return false;
      }

      if (dump) {
        dumpRow(checked);
      }
      m_rowBuffer.add(checked);

      if (m_rowBuffer.size() == m_bufferSize) {
        finished = true;

        if (getRetrieval() == BATCH) {
          m_rowBuffer.clear();
        }
      }
    } while (!finished);

    return true;
  }
Ejemplo n.º 2
0
  private void readHeader() throws IOException {
    m_rowCount = 1;
    m_incrementalReader = null;
    m_current = new ArrayList<Object>();
    openTempFiles();

    m_rowBuffer = new ArrayList<String>();

    String firstRow = m_sourceReader.readLine();
    if (firstRow == null) {
      throw new IOException("No data in the file!");
    }
    if (m_noHeaderRow) {
      m_rowBuffer.add(firstRow);
    }

    ArrayList<Attribute> attribNames = new ArrayList<Attribute>();

    // now tokenize to determine attribute names (or create att names if
    // no header row
    StringReader sr = new StringReader(firstRow + "\n");
    // System.out.print(firstRow + "\n");
    m_st = new StreamTokenizer(sr);
    initTokenizer(m_st);

    m_st.ordinaryChar(m_FieldSeparator.charAt(0));

    int attNum = 1;
    StreamTokenizerUtils.getFirstToken(m_st);
    if (m_st.ttype == StreamTokenizer.TT_EOF) {
      StreamTokenizerUtils.errms(m_st, "premature end of file");
    }
    boolean first = true;
    boolean wasSep;

    while (m_st.ttype != StreamTokenizer.TT_EOL && m_st.ttype != StreamTokenizer.TT_EOF) {
      // Get next token

      if (!first) {
        StreamTokenizerUtils.getToken(m_st);
      }

      if (m_st.ttype == m_FieldSeparator.charAt(0) || m_st.ttype == StreamTokenizer.TT_EOL) {
        wasSep = true;
      } else {
        wasSep = false;

        String attName = null;

        if (m_noHeaderRow) {
          attName = "att" + attNum;
          attNum++;
        } else {
          attName = m_st.sval;
        }

        attribNames.add(new Attribute(attName, (java.util.List<String>) null));
      }
      if (!wasSep) {
        StreamTokenizerUtils.getToken(m_st);
      }
      first = false;
    }
    String relationName;
    if (m_sourceFile != null) {
      relationName = (m_sourceFile.getName()).replaceAll("\\.[cC][sS][vV]$", "");
    } else {
      relationName = "stream";
    }
    m_structure = new Instances(relationName, attribNames, 0);
    m_NominalAttributes.setUpper(m_structure.numAttributes() - 1);
    m_StringAttributes.setUpper(m_structure.numAttributes() - 1);
    m_dateAttributes.setUpper(m_structure.numAttributes() - 1);
    m_numericAttributes.setUpper(m_structure.numAttributes() - 1);
    m_nominalVals = new HashMap<Integer, LinkedHashSet<String>>();

    m_types = new TYPE[m_structure.numAttributes()];
    for (int i = 0; i < m_structure.numAttributes(); i++) {
      if (m_NominalAttributes.isInRange(i)) {
        m_types[i] = TYPE.NOMINAL;
        LinkedHashSet<String> ts = new LinkedHashSet<String>();
        m_nominalVals.put(i, ts);
      } else if (m_StringAttributes.isInRange(i)) {
        m_types[i] = TYPE.STRING;
      } else if (m_dateAttributes.isInRange(i)) {
        m_types[i] = TYPE.DATE;
      } else if (m_numericAttributes.isInRange(i)) {
        m_types[i] = TYPE.NUMERIC;
      } else {
        m_types[i] = TYPE.UNDETERMINED;
      }
    }

    if (m_nominalLabelSpecs.size() > 0) {
      for (String spec : m_nominalLabelSpecs) {
        String[] attsAndLabels = spec.split(":");
        if (attsAndLabels.length == 2) {
          String[] labels = attsAndLabels[1].split(",");
          try {
            // try as a range string first
            Range tempR = new Range();
            tempR.setRanges(attsAndLabels[0].trim());
            tempR.setUpper(m_structure.numAttributes() - 1);

            int[] rangeIndexes = tempR.getSelection();
            for (int i = 0; i < rangeIndexes.length; i++) {
              m_types[rangeIndexes[i]] = TYPE.NOMINAL;
              LinkedHashSet<String> ts = new LinkedHashSet<String>();
              for (String lab : labels) {
                ts.add(lab);
              }
              m_nominalVals.put(rangeIndexes[i], ts);
            }
          } catch (IllegalArgumentException e) {
            // one or more named attributes?
            String[] attNames = attsAndLabels[0].split(",");
            for (String attN : attNames) {
              Attribute a = m_structure.attribute(attN.trim());
              if (a != null) {
                int attIndex = a.index();
                m_types[attIndex] = TYPE.NOMINAL;
                LinkedHashSet<String> ts = new LinkedHashSet<String>();
                for (String lab : labels) {
                  ts.add(lab);
                }
                m_nominalVals.put(attIndex, ts);
              }
            }
          }
        }
      }
    }

    // Prevents the first row from getting lost in the
    // case where there is no header row and we're
    // running in batch mode
    if (m_noHeaderRow && getRetrieval() == BATCH) {
      StreamTokenizer tempT = new StreamTokenizer(new StringReader(firstRow));
      initTokenizer(tempT);
      tempT.ordinaryChar(m_FieldSeparator.charAt(0));
      String checked = getInstance(tempT);
      dumpRow(checked);
    }

    m_st = new StreamTokenizer(m_sourceReader);
    initTokenizer(m_st);
    m_st.ordinaryChar(m_FieldSeparator.charAt(0));

    // try and determine a more accurate structure from the first batch
    readData(false || getRetrieval() == BATCH);
    makeStructure();
  }