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.Matcher;
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 RegexReplace is used to replace a matched regex with a replacement value.
036 * <p/>
037 * RegexReplace only expects one field value. If more than one argument value is passed, only the
038 * first is handled, the remainder are ignored.
039 */
040 public class RegexReplace extends RegexOperation<Pair<Matcher, Tuple>> implements Function<Pair<Matcher, Tuple>>
041 {
042 /** Field replacement */
043 private final String replacement;
044 /** Field replaceAll */
045 private boolean replaceAll = true;
046
047 /**
048 * Constructor RegexReplace creates a new RegexReplace instance,
049 *
050 * @param fieldDeclaration of type Fields
051 * @param patternString of type String
052 * @param replacement of type String
053 * @param replaceAll of type boolean
054 */
055 @ConstructorProperties({"fieldDeclaration", "patternString", "replacement", "replaceAll"})
056 public RegexReplace( Fields fieldDeclaration, String patternString, String replacement, boolean replaceAll )
057 {
058 this( fieldDeclaration, patternString, replacement );
059 this.replaceAll = replaceAll;
060 }
061
062 /**
063 * Constructor RegexReplace creates a new RegexReplace instance.
064 *
065 * @param fieldDeclaration of type Fields
066 * @param patternString of type String
067 * @param replacement of type String
068 */
069 @ConstructorProperties({"fieldDeclaration", "patternString", "replacement"})
070 public RegexReplace( Fields fieldDeclaration, String patternString, String replacement )
071 {
072 super( 1, fieldDeclaration, patternString );
073 this.replacement = replacement;
074 }
075
076 public String getReplacement()
077 {
078 return replacement;
079 }
080
081 public boolean isReplaceAll()
082 {
083 return replaceAll;
084 }
085
086 @Override
087 public void prepare( FlowProcess flowProcess, OperationCall<Pair<Matcher, Tuple>> operationCall )
088 {
089 operationCall.setContext( new Pair<Matcher, Tuple>( getPattern().matcher( "" ), Tuple.size( 1 ) ) );
090 }
091
092 @Override
093 public void operate( FlowProcess flowProcess, FunctionCall<Pair<Matcher, Tuple>> functionCall )
094 {
095 // coerce to string
096 String value = functionCall.getArguments().getString( 0 );
097
098 // make safe
099 if( value == null )
100 value = "";
101
102 Tuple output = functionCall.getContext().getRhs();
103 Matcher matcher = functionCall.getContext().getLhs().reset( value );
104
105 if( replaceAll )
106 output.set( 0, matcher.replaceAll( replacement ) );
107 else
108 output.set( 0, matcher.replaceFirst( replacement ) );
109
110 functionCall.getOutputCollector().add( output );
111 }
112
113 @Override
114 public boolean equals( Object object )
115 {
116 if( this == object )
117 return true;
118 if( !( object instanceof RegexReplace ) )
119 return false;
120 if( !super.equals( object ) )
121 return false;
122
123 RegexReplace that = (RegexReplace) object;
124
125 if( replaceAll != that.replaceAll )
126 return false;
127 if( replacement != null ? !replacement.equals( that.replacement ) : that.replacement != null )
128 return false;
129
130 return true;
131 }
132
133 @Override
134 public int hashCode()
135 {
136 int result = super.hashCode();
137 result = 31 * result + ( replacement != null ? replacement.hashCode() : 0 );
138 result = 31 * result + ( replaceAll ? 1 : 0 );
139 return result;
140 }
141 }