Package org.apache.lucene.analysis.shingle.ShingleMatrixFilter.Matrix

Examples of org.apache.lucene.analysis.shingle.ShingleMatrixFilter.Matrix.Column


    if (token == null) {
      return false;
    }

    Matrix.Column currentReaderColumn = matrix.new Column();
    Matrix.Column.Row currentReaderRow = currentReaderColumn.new Row();

    currentReaderRow.getTokens().add(token);
    TokenPositioner tokenPositioner;
    while ((readColumnBuf = getNextInputToken(new Token())) != null
        && (tokenPositioner = settingsCodec.getTokenPositioner(readColumnBuf)) != TokenPositioner.newColumn) {

      if (tokenPositioner == TokenPositioner.sameRow) {
        currentReaderRow.getTokens().add(readColumnBuf);
      } else /*if (tokenPositioner == TokenPositioner.newRow)*/ {
        currentReaderRow = currentReaderColumn.new Row();
        currentReaderRow.getTokens().add(readColumnBuf);
      }
      readColumnBuf = null;

    }

    if (readColumnBuf == null) {
      readColumnBuf = getNextInputToken(new Token());
      if (readColumnBuf == null) {
        currentReaderColumn.setLast(true);
      }
    }


    return true;
View Full Code Here


    // some other tests set this to null.
    // set it here in case tests are run out of the usual order.
    ShingleMatrixFilter.defaultSettingsCodec = new ShingleMatrixFilter.SimpleThreeDimensionalTokenSettingsCodec();
    Matrix matrix = new Matrix();

    matrix.new Column(tokenFactory("no", 1));
    matrix.new Column(tokenFactory("surprise", 1));
    matrix.new Column(tokenFactory("to", 1));
    matrix.new Column(tokenFactory("see", 1));
    matrix.new Column(tokenFactory("england", 1));
    matrix.new Column(tokenFactory("manager", 1));

    Column col = matrix.new Column();

    // sven göran eriksson is a multi token synonym to svennis
    col.new Row().getTokens().add(tokenFactory("svennis", 1));

    Column.Row row = col.new Row();
    row.getTokens().add(tokenFactory("sven", 1));
    row.getTokens().add(tokenFactory("göran", 1));
    row.getTokens().add(tokenFactory("eriksson", 1));

    matrix.new Column(tokenFactory("in", 1));
    matrix.new Column(tokenFactory("the", 1));
    matrix.new Column(tokenFactory("croud", 1));

    TokenStream ts = new ShingleMatrixFilter(matrix, 2, 4, new Character('_'), true, new ShingleMatrixFilter.SimpleThreeDimensionalTokenSettingsCodec());

//  for (Token token = ts.next(new Token()); token != null; token = ts.next(token)) {
//      System.out.println("assertNext(ts, \"" + token.term() + "\", " + token.getPositionIncrement() + ", " + (token.getPayload() == null ? "1.0" : PayloadHelper.decodeFloat(token.getPayload().getData())) + "f, " + token.startOffset() + ", " + token.endOffset() + ");");
View Full Code Here

    // some other tests set this to null.
    // set it here in case tests are run out of the usual order.
    ShingleMatrixFilter.defaultSettingsCodec = new ShingleMatrixFilter.SimpleThreeDimensionalTokenSettingsCodec();
    Matrix matrix = new Matrix();

    matrix.new Column(tokenFactory("no", 1));
    matrix.new Column(tokenFactory("surprise", 1));
    matrix.new Column(tokenFactory("to", 1));
    matrix.new Column(tokenFactory("see", 1));
    matrix.new Column(tokenFactory("england", 1));
    matrix.new Column(tokenFactory("manager", 1));

    Column col = matrix.new Column();

    // sven göran eriksson is a multi token synonym to svennis
    col.new Row().getTokens().add(tokenFactory("svennis", 1));

    Column.Row row = col.new Row();
    row.getTokens().add(tokenFactory("sven", 1));
    row.getTokens().add(tokenFactory("göran", 1));
    row.getTokens().add(tokenFactory("eriksson", 1));

    matrix.new Column(tokenFactory("in", 1));
    matrix.new Column(tokenFactory("the", 1));
    matrix.new Column(tokenFactory("croud", 1));

    TokenStream ts = new ShingleMatrixFilter(matrix, 2, 4, new Character('_'), true, new ShingleMatrixFilter.SimpleThreeDimensionalTokenSettingsCodec());

//  for (Token token = ts.next(new Token()); token != null; token = ts.next(token)) {
//      System.out.println("assertNext(ts, \"" + token.term() + "\", " + token.getPositionIncrement() + ", " + (token.getPayload() == null ? "1.0" : PayloadHelper.decodeFloat(token.getPayload().getData())) + "f, " + token.startOffset() + ", " + token.endOffset() + ");");
View Full Code Here

   */
  public void testMatrix() throws IOException {

    Matrix matrix = new Matrix();

    matrix.new Column(tokenFactory("no", 1));
    matrix.new Column(tokenFactory("surprise", 1));
    matrix.new Column(tokenFactory("to", 1));
    matrix.new Column(tokenFactory("see", 1));
    matrix.new Column(tokenFactory("england", 1));
    matrix.new Column(tokenFactory("manager", 1));

    Column col = matrix.new Column();

    // sven göran eriksson is a multi token synonym to svennis
    col.new Row().getTokens().add(tokenFactory("svennis", 1));

    Column.Row row = col.new Row();
    row.getTokens().add(tokenFactory("sven", 1));
    row.getTokens().add(tokenFactory("göran", 1));
    row.getTokens().add(tokenFactory("eriksson", 1));

    matrix.new Column(tokenFactory("in", 1));
    matrix.new Column(tokenFactory("the", 1));
    matrix.new Column(tokenFactory("croud", 1));

    TokenStream ts = new ShingleMatrixFilter(matrix, 2, 4, new Character('_'), true, new ShingleMatrixFilter.SimpleThreeDimensionalTokenSettingsCodec());

//  for (Token token = ts.next(new Token()); token != null; token = ts.next(token)) {
//      System.out.println("assertNext(ts, \"" + token.term() + "\", " + token.getPositionIncrement() + ", " + (token.getPayload() == null ? "1.0" : PayloadHelper.decodeFloat(token.getPayload().getData())) + "f, " + token.startOffset() + ", " + token.endOffset() + ");");
View Full Code Here

    // some other tests set this to null.
    // set it here in case tests are run out of the usual order.
    ShingleMatrixFilter.defaultSettingsCodec = new ShingleMatrixFilter.SimpleThreeDimensionalTokenSettingsCodec();
    Matrix matrix = new Matrix();

    matrix.new Column(tokenFactory("no", 1));
    matrix.new Column(tokenFactory("surprise", 1));
    matrix.new Column(tokenFactory("to", 1));
    matrix.new Column(tokenFactory("see", 1));
    matrix.new Column(tokenFactory("england", 1));
    matrix.new Column(tokenFactory("manager", 1));

    Column col = matrix.new Column();

    // sven göran eriksson is a multi token synonym to svennis
    col.new Row().getTokens().add(tokenFactory("svennis", 1));

    Column.Row row = col.new Row();
    row.getTokens().add(tokenFactory("sven", 1));
    row.getTokens().add(tokenFactory("göran", 1));
    row.getTokens().add(tokenFactory("eriksson", 1));

    matrix.new Column(tokenFactory("in", 1));
    matrix.new Column(tokenFactory("the", 1));
    matrix.new Column(tokenFactory("croud", 1));

    TokenStream ts = new ShingleMatrixFilter(matrix, 2, 4, new Character('_'), true, new ShingleMatrixFilter.SimpleThreeDimensionalTokenSettingsCodec());

//  for (Token token = ts.next(new Token()); token != null; token = ts.next(token)) {
//      System.out.println("assertNext(ts, \"" + token.term() + "\", " + token.getPositionIncrement() + ", " + (token.getPayload() == null ? "1.0" : PayloadHelper.decodeFloat(token.getPayload().getData())) + "f, " + token.startOffset() + ", " + token.endOffset() + ");");
View Full Code Here

    if (token == null) {
      return false;
    }

    Matrix.Column currentReaderColumn = matrix.new Column();
    Matrix.Column.Row currentReaderRow = currentReaderColumn.new Row();

    currentReaderRow.getTokens().add(token);
    TokenPositioner tokenPositioner;
    while ((readColumnBuf = getNextInputToken(new Token())) != null
        && (tokenPositioner = settingsCodec.getTokenPositioner(readColumnBuf)) != TokenPositioner.newColumn) {

      if (tokenPositioner == TokenPositioner.sameRow) {
        currentReaderRow.getTokens().add(readColumnBuf);
      } else /*if (tokenPositioner == TokenPositioner.newRow)*/ {
        currentReaderRow = currentReaderColumn.new Row();
        currentReaderRow.getTokens().add(readColumnBuf);
      }
      readColumnBuf = null;

    }

    if (readColumnBuf == null) {
      readColumnBuf = getNextInputToken(new Token());
      if (readColumnBuf == null) {
        currentReaderColumn.setLast(true);
      }
    }


    return true;
View Full Code Here

    // some other tests set this to null.
    // set it here in case tests are run out of the usual order.
    ShingleMatrixFilter.defaultSettingsCodec = new ShingleMatrixFilter.SimpleThreeDimensionalTokenSettingsCodec();
    Matrix matrix = new Matrix();

    matrix.new Column(tokenFactory("no", 1));
    matrix.new Column(tokenFactory("surprise", 1));
    matrix.new Column(tokenFactory("to", 1));
    matrix.new Column(tokenFactory("see", 1));
    matrix.new Column(tokenFactory("england", 1));
    matrix.new Column(tokenFactory("manager", 1));

    Column col = matrix.new Column();

    // sven göran eriksson is a multi token synonym to svennis
    col.new Row().getTokens().add(tokenFactory("svennis", 1));

    Column.Row row = col.new Row();
    row.getTokens().add(tokenFactory("sven", 1));
    row.getTokens().add(tokenFactory("göran", 1));
    row.getTokens().add(tokenFactory("eriksson", 1));

    matrix.new Column(tokenFactory("in", 1));
    matrix.new Column(tokenFactory("the", 1));
    matrix.new Column(tokenFactory("croud", 1));

    TokenStream ts = new ShingleMatrixFilter(matrix, 2, 4, new Character('_'), true, new ShingleMatrixFilter.SimpleThreeDimensionalTokenSettingsCodec());

//  for (Token token = ts.next(new Token()); token != null; token = ts.next(token)) {
//      System.out.println("assertNext(ts, \"" + token.term() + "\", " + token.getPositionIncrement() + ", " + (token.getPayload() == null ? "1.0" : PayloadHelper.decodeFloat(token.getPayload().getData())) + "f, " + token.startOffset() + ", " + token.endOffset() + ");");
View Full Code Here

    // some other tests set this to null.
    // set it here in case tests are run out of the usual order.
    ShingleMatrixFilter.defaultSettingsCodec = new ShingleMatrixFilter.SimpleThreeDimensionalTokenSettingsCodec();
    Matrix matrix = new Matrix();

    matrix.new Column(tokenFactory("no", 1));
    matrix.new Column(tokenFactory("surprise", 1));
    matrix.new Column(tokenFactory("to", 1));
    matrix.new Column(tokenFactory("see", 1));
    matrix.new Column(tokenFactory("england", 1));
    matrix.new Column(tokenFactory("manager", 1));

    Column col = matrix.new Column();

    // sven göran eriksson is a multi token synonym to svennis
    col.new Row().getTokens().add(tokenFactory("svennis", 1));

    Column.Row row = col.new Row();
    row.getTokens().add(tokenFactory("sven", 1));
    row.getTokens().add(tokenFactory("göran", 1));
    row.getTokens().add(tokenFactory("eriksson", 1));

    matrix.new Column(tokenFactory("in", 1));
    matrix.new Column(tokenFactory("the", 1));
    matrix.new Column(tokenFactory("croud", 1));

    TokenStream ts = new ShingleMatrixFilter(matrix, 2, 4, new Character('_'), true, new ShingleMatrixFilter.SimpleThreeDimensionalTokenSettingsCodec());

//  for (Token token = ts.next(new Token()); token != null; token = ts.next(token)) {
//      System.out.println("assertNext(ts, \"" + token.term() + "\", " + token.getPositionIncrement() + ", " + (token.getPayload() == null ? "1.0" : PayloadHelper.decodeFloat(token.getPayload().getData())) + "f, " + token.startOffset() + ", " + token.endOffset() + ");");
View Full Code Here

TOP

Related Classes of org.apache.lucene.analysis.shingle.ShingleMatrixFilter.Matrix.Column

Copyright © 2018 www.massapicom. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.