001    /*
002     * Copyright (c) 2007-2014 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    
021    package cascading.operation.regex;
022    
023    import java.beans.ConstructorProperties;
024    import java.util.regex.Pattern;
025    
026    import cascading.flow.FlowProcess;
027    import cascading.operation.Function;
028    import cascading.operation.FunctionCall;
029    import cascading.operation.OperationCall;
030    import cascading.tuple.Fields;
031    import cascading.tuple.Tuple;
032    import cascading.util.Pair;
033    
034    /**
035     * Class RegexGenerator will emit a new Tuple for every split on the incoming argument value delimited by the given patternString.
036     * <p/>
037     * This could be used to break a document into single word tuples for later processing for a word count.
038     */
039    public class RegexSplitGenerator extends RegexOperation<Pair<Pattern, Tuple>> implements Function<Pair<Pattern, Tuple>>
040      {
041      /**
042       * Constructor RegexGenerator creates a new RegexGenerator instance.
043       *
044       * @param patternString of type String
045       */
046      @ConstructorProperties({"patternString"})
047      public RegexSplitGenerator( String patternString )
048        {
049        super( 1, Fields.size( 1 ), patternString );
050        }
051    
052      /**
053       * Constructor RegexGenerator creates a new RegexGenerator instance.
054       *
055       * @param fieldDeclaration of type Fields
056       * @param patternString    of type String
057       */
058      @ConstructorProperties({"fieldDeclaration", "patternString"})
059      public RegexSplitGenerator( Fields fieldDeclaration, String patternString )
060        {
061        super( 1, fieldDeclaration, patternString );
062    
063        if( fieldDeclaration.size() != 1 )
064          throw new IllegalArgumentException( "fieldDeclaration may only declare one field, was " + fieldDeclaration.print() );
065        }
066    
067      @Override
068      public void prepare( FlowProcess flowProcess, OperationCall<Pair<Pattern, Tuple>> operationCall )
069        {
070        operationCall.setContext( new Pair<Pattern, Tuple>( getPattern(), Tuple.size( 1 ) ) );
071        }
072    
073      @Override
074      public void operate( FlowProcess flowProcess, FunctionCall<Pair<Pattern, Tuple>> functionCall )
075        {
076        String value = functionCall.getArguments().getString( 0 );
077    
078        if( value == null )
079          value = "";
080    
081        String[] split = functionCall.getContext().getLhs().split( value );
082    
083        for( String string : split )
084          {
085          functionCall.getContext().getRhs().set( 0, string );
086          functionCall.getOutputCollector().add( functionCall.getContext().getRhs() );
087          }
088        }
089      }