001/* 002 * Licensed to the Apache Software Foundation (ASF) under one 003 * or more contributor license agreements. See the NOTICE file 004 * distributed with this work for additional information 005 * regarding copyright ownership. The ASF licenses this file 006 * to you under the Apache License, Version 2.0 (the 007 * "License"); you may not use this file except in compliance 008 * with the License. You may obtain a copy of the License at 009 * 010 * http://www.apache.org/licenses/LICENSE-2.0 011 * 012 * Unless required by applicable law or agreed to in writing, 013 * software distributed under the License is distributed on an 014 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY 015 * KIND, either express or implied. See the License for the 016 * specific language governing permissions and limitations 017 * under the License. 018 * 019 */ 020package org.apache.directory.api.ldap.model.schema.comparators; 021 022 023import org.apache.directory.api.ldap.model.schema.LdapComparator; 024import org.apache.directory.api.util.Strings; 025import org.slf4j.Logger; 026import org.slf4j.LoggerFactory; 027 028 029/** 030 * <p> 031 * A comparator for Words/KeyWords. RFC 4517 par. 4.2.21 (KeywordMatch) and par. 032 * 4.2.32 is pretty vague about the definition of what is a word or a keyword 033 * ("...The precise definition of a word is implementation specific...) 034 * ("...The identification of keywords in the attribute value and the exactness 035 * of the match are both implementation specific...). 036 * <p> 037 * We will simply check that the assertion is present in the value at some place, 038 * after having deep trimmed the word. 039 * <p> 040 * For instance, the word " World " will be found in the value "Hello world!". 041 * <p> 042 * A word is defined by the following regexp : "(^|[^A-Za-z0-9])([A-Za-z0-9])*([^A-Za-z0-9]|$)". 043 * Anything that is not matched by this regexp will not be considered as a word. 044 * 045 * @author <a href="mailto:dev@directory.apache.org">Apache Directory Project</a> 046 */ 047public class WordComparator extends LdapComparator<String> 048{ 049 /** The serial version UID */ 050 private static final long serialVersionUID = 2L; 051 052 /** A logger for this class */ 053 private static final Logger LOG = LoggerFactory.getLogger( WordComparator.class ); 054 055 056 /** 057 * The StringComparator constructor. Its OID is the StringMatch matching 058 * rule OID. 059 * 060 * @param oid The Comparator's OID 061 */ 062 public WordComparator( String oid ) 063 { 064 super( oid ); 065 } 066 067 068 /** 069 * {@inheritDoc} 070 */ 071 public int compare( String value, String assertion ) 072 { 073 LOG.debug( "comparing String objects '{}' with '{}'", value, assertion ); 074 075 if ( value == assertion ) 076 { 077 return 0; 078 } 079 080 // ------------------------------------------------------------------- 081 // Handle some basis cases 082 // ------------------------------------------------------------------- 083 if ( ( value == null ) || ( assertion == null ) ) 084 { 085 return ( assertion == null ) ? 1 : -1; 086 } 087 088 // Now, trim the assertion and find it in the value 089 String trimmedAssertion = Strings.trim( assertion ); 090 int pos = value.indexOf( trimmedAssertion ); 091 092 if ( pos != -1 ) 093 { 094 int assertionLength = trimmedAssertion.length(); 095 096 // Check that we are not in a middle of some text 097 if ( assertionLength == value.length() ) 098 { 099 return 0; 100 } 101 102 if ( pos == 0 ) 103 { 104 char after = value.charAt( assertionLength ); 105 106 if ( !Character.isLetterOrDigit( after ) ) 107 { 108 return 0; 109 } 110 else 111 { 112 return -1; 113 } 114 } 115 116 if ( pos + assertionLength == value.length() ) 117 { 118 char before = value.charAt( value.length() - assertionLength - 1 ); 119 120 if ( !Character.isLetterOrDigit( before ) ) 121 { 122 return 0; 123 } 124 else 125 { 126 return -1; 127 } 128 } 129 130 char before = value.charAt( value.length() - assertionLength ); 131 char after = value.charAt( assertionLength ); 132 133 if ( Character.isLetterOrDigit( after ) ) 134 { 135 return -1; 136 } 137 138 if ( !Character.isLetterOrDigit( before ) ) 139 { 140 return -1; 141 } 142 143 return 0; 144 } 145 146 return -1; 147 } 148}