001/*
002 * Copyright (c) 2007-2016 Concurrent, Inc. All Rights Reserved.
003 *
004 * Project and contact information: http://www.cascading.org/
005 *
006 * This file is part of the Cascading project.
007 *
008 * Licensed under the Apache License, Version 2.0 (the "License");
009 * you may not use this file except in compliance with the License.
010 * You may obtain a copy of the License at
011 *
012 *     http://www.apache.org/licenses/LICENSE-2.0
013 *
014 * Unless required by applicable law or agreed to in writing, software
015 * distributed under the License is distributed on an "AS IS" BASIS,
016 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
017 * See the License for the specific language governing permissions and
018 * limitations under the License.
019 */
020
021package cascading.operation.xml;
022
023import javax.xml.parsers.DocumentBuilder;
024import javax.xml.xpath.XPathConstants;
025import javax.xml.xpath.XPathExpression;
026import javax.xml.xpath.XPathExpressionException;
027
028import cascading.flow.FlowProcess;
029import cascading.operation.Filter;
030import cascading.operation.FilterCall;
031import cascading.operation.OperationException;
032import cascading.tuple.Tuple;
033import cascading.util.Pair;
034import org.slf4j.Logger;
035import org.slf4j.LoggerFactory;
036import org.w3c.dom.Document;
037
038/**
039 * XPathFilter will filter out a Tuple if the given XPath expression returns false. Set removeMatch to true
040 * if the filter should be reversed.
041 */
042public class XPathFilter extends XPathOperation implements Filter<Pair<DocumentBuilder, Tuple>>
043  {
044  /** Field LOG */
045  private static final Logger LOG = LoggerFactory.getLogger( XPathFilter.class );
046
047  /** Field removeMatch */
048  private boolean removeMatch = false;
049
050  /**
051   * Constructor XPathFilter creates a new XPathFilter instance.
052   *
053   * @param namespaces of type String[][]
054   * @param path       of type String
055   */
056  public XPathFilter( String[][] namespaces, String path )
057    {
058    super( 1, namespaces, path );
059    }
060
061  /**
062   * Constructor XPathFilter creates a new XPathFilter instance.
063   *
064   * @param removeMatch of type boolean
065   * @param namespaces  of type String[][]
066   * @param path        of type String
067   */
068  public XPathFilter( boolean removeMatch, String[][] namespaces, String path )
069    {
070    super( 1, namespaces, path );
071    this.removeMatch = removeMatch;
072    }
073
074  @Override
075  public boolean isRemove( FlowProcess flowProcess, FilterCall<Pair<DocumentBuilder, Tuple>> filterCall )
076    {
077    String argument = filterCall.getArguments().getString( 0 );
078    Document document = parseDocument( filterCall.getContext().getLhs(), argument );
079    XPathExpression expression = getExpressions().get( 0 );
080
081    try
082      {
083      boolean value = (Boolean) expression.evaluate( document, XPathConstants.BOOLEAN );
084
085      LOG.debug( "xpath: {} matches: {}", paths[ 0 ], value );
086
087      return value == removeMatch;
088      }
089    catch( XPathExpressionException exception )
090      {
091      throw new OperationException( "could not evaluate xpath expression: " + paths[ 0 ], exception );
092      }
093    }
094  }