added phonetic classes

source/net/yacy/cora/language/phonetic/ColognePhonetic.java

@@ -0,0 +1,429 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ * 
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ * 
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package net.yacy.cora.language.phonetic;
+
+import java.util.Locale;
+
+import org.apache.commons.codec.EncoderException;
+import org.apache.commons.codec.StringEncoder;
+
+/**
+ * <p>
+ * Encodes a string into a Cologne Phonetic value.
+ * </p>
+ * <p>
+ * Implements the <a href="http://de.wikipedia.org/wiki/K%C3%B6lner_Phonetik">K&ouml;lner Phonetik</a> (Cologne Phonetic)
+ * algorithm issued by Hans Joachim Postel in 1969.
+ * </p>
+ * 
+ * <p>
+ * The <i>K&ouml;lner Phonetik</i> is a phonetic algorithm which is optimized for the German language. It is related to the
+ * well-known soundex algorithm.
+ * </p>
+ * 
+ * <h2>Algorithm</h2>
+ * 
+ * <ul>
+ * 
+ * <li>
+ * <h3>Step 1:</h3>
+ * After preprocessing (conversion to upper case, transcription of <a
+ * href="http://en.wikipedia.org/wiki/Germanic_umlaut">germanic umlauts</a>, removal of non alphabetical characters) the
+ * letters of the supplied text are replaced by their phonetic code according to the following table.
+ * <table border="1">
+ * <tbody>
+ * <tr>
+ * <th>Letter</th>
+ * <th>Context</th>
+ * <th align="center">Code</th>
+ * </tr>
+ * <tr>
+ * <td>A, E, I, J, O, U, Y</td>
+ * <td></td>
+ * <td align="center">0</td>
+ * </tr>
+ * <tr>
+ * 
+ * <td>H</td>
+ * <td></td>
+ * <td align="center">-</td>
+ * </tr>
+ * <tr>
+ * <td>B</td>
+ * <td></td>
+ * <td rowspan="2" align="center">1</td>
+ * </tr>
+ * <tr>
+ * <td>P</td>
+ * <td>not before H</td>
+ * 
+ * </tr>
+ * <tr>
+ * <td>D, T</td>
+ * <td>not before C, S, Z</td>
+ * <td align="center">2</td>
+ * </tr>
+ * <tr>
+ * <td>F, V, W</td>
+ * <td></td>
+ * <td rowspan="2" align="center">3</td>
+ * </tr>
+ * <tr>
+ * 
+ * <td>P</td>
+ * <td>before H</td>
+ * </tr>
+ * <tr>
+ * <td>G, K, Q</td>
+ * <td></td>
+ * <td rowspan="3" align="center">4</td>
+ * </tr>
+ * <tr>
+ * <td rowspan="2">C</td>
+ * <td>at onset before A, H, K, L, O, Q, R, U, X</td>
+ * 
+ * </tr>
+ * <tr>
+ * <td>before A, H, K, O, Q, U, X except after S, Z</td>
+ * </tr>
+ * <tr>
+ * <td>X</td>
+ * <td>not after C, K, Q</td>
+ * <td align="center">48</td>
+ * </tr>
+ * <tr>
+ * <td>L</td>
+ * <td></td>
+ * 
+ * <td align="center">5</td>
+ * </tr>
+ * <tr>
+ * <td>M, N</td>
+ * <td></td>
+ * <td align="center">6</td>
+ * </tr>
+ * <tr>
+ * <td>R</td>
+ * <td></td>
+ * <td align="center">7</td>
+ * </tr>
+ * 
+ * <tr>
+ * <td>S, Z</td>
+ * <td></td>
+ * <td rowspan="6" align="center">8</td>
+ * </tr>
+ * <tr>
+ * <td rowspan="3">C</td>
+ * <td>after S, Z</td>
+ * </tr>
+ * <tr>
+ * <td>at onset except before A, H, K, L, O, Q, R, U, X</td>
+ * </tr>
+ * 
+ * <tr>
+ * <td>not before A, H, K, O, Q, U, X</td>
+ * </tr>
+ * <tr>
+ * <td>D, T</td>
+ * <td>before C, S, Z</td>
+ * </tr>
+ * <tr>
+ * <td>X</td>
+ * <td>after C, K, Q</td>
+ * </tr>
+ * </tbody>
+ * </table>
+ * <p>
+ * <small><i>(Source: <a href= "http://de.wikipedia.org/wiki/K%C3%B6lner_Phonetik#Buchstabencodes" >Wikipedia (de):
+ * K&ouml;lner Phonetik -- Buchstabencodes</a>)</i></small>
+ * </p>
+ * 
+ * <h4>Example:</h4>
+ * 
+ * {@code "M}&uuml;{@code ller-L}&uuml;{@code denscheidt" => "MULLERLUDENSCHEIDT" => "6005507500206880022"}
+ * 
+ * </li>
+ * 
+ * <li>
+ * <h3>Step 2:</h3>
+ * Collapse of all multiple consecutive code digits.
+ * <h4>Example:</h4>
+ * {@code "6005507500206880022" => "6050750206802"}</li>
+ * 
+ * <li>
+ * <h3>Step 3:</h3>
+ * Removal of all codes "0" except at the beginning. This means that two or more identical consecutive digits can occur
+ * if they occur after removing the "0" digits.
+ * 
+ * <h4>Example:</h4>
+ * {@code "6050750206802" => "65752682"}</li>
+ * 
+ * </ul>
+ * 
+ * @see <a href="http://de.wikipedia.org/wiki/K%C3%B6lner_Phonetik">Wikipedia (de): K&ouml;lner Phonetik (in German)</a>
+ * @author Apache Software Foundation
+ * @since 1.5
+ */
+public class ColognePhonetic implements StringEncoder {
+
+    private abstract class CologneBuffer {
+
+        protected final char[] data;
+
+        protected int length = 0;
+
+        public CologneBuffer(char[] data) {
+            this.data = data;
+            this.length = data.length;
+        }
+
+        public CologneBuffer(int buffSize) {
+            this.data = new char[buffSize];
+            this.length = 0;
+        }
+
+        protected abstract char[] copyData(int start, final int length);
+
+        public int length() {
+            return length;
+        }
+
+        @Override
+        public String toString() {
+            return new String(copyData(0, length));
+        }
+    }
+
+    private class CologneOutputBuffer extends CologneBuffer {
+
+        public CologneOutputBuffer(int buffSize) {
+            super(buffSize);
+        }
+
+        public void addRight(char chr) {
+            data[length] = chr;
+            length++;
+        }
+
+        @Override
+        protected char[] copyData(int start, final int length) {
+            char[] newData = new char[length];
+            System.arraycopy(data, start, newData, 0, length);
+            return newData;
+        }
+    }
+
+    private class CologneInputBuffer extends CologneBuffer {
+
+        public CologneInputBuffer(char[] data) {
+            super(data);
+        }
+
+        public void addLeft(char ch) {
+            length++;
+            data[getNextPos()] = ch;
+        }
+
+        @Override
+        protected char[] copyData(int start, final int length) {
+            char[] newData = new char[length];
+            System.arraycopy(data, data.length - this.length + start, newData, 0, length);
+            return newData;
+        }
+
+        public char getNextChar() {
+            return data[getNextPos()];
+        }
+
+        protected int getNextPos() {
+            return data.length - length;
+        }
+
+        public char removeNext() {
+            char ch = getNextChar();
+            length--;
+            return ch;
+        }
+    }
+
+    /**
+     * Maps some Germanic characters to plain for internal processing. The following characters are mapped:
+     * <ul>
+     * <li>capital a, umlaut mark</li>
+     * <li>capital u, umlaut mark</li>
+     * <li>capital o, umlaut mark</li>
+     * <li>small sharp s, German</li>
+     * </ul>
+     */
+    private static final char[][] PREPROCESS_MAP = new char[][]{
+        {'\u00C4', 'A'}, // capital a, umlaut mark
+        {'\u00DC', 'U'}, // capital u, umlaut mark
+        {'\u00D6', 'O'}, // capital o, umlaut mark
+        {'\u00DF', 'S'} // small sharp s, German
+    };
+
+    /*
+     * Returns whether the array contains the key, or not.
+     */
+    private static boolean arrayContains(char[] arr, char key) {
+        for (char element : arr) {
+            if (element == key) {
+                return true;
+            }
+        }
+        return false;
+    }
+
+    /**
+     * <p>
+     * Implements the <i>K&ouml;lner Phonetik</i> algorithm.
+     * </p>
+     * <p>
+     * In contrast to the initial description of the algorithm, this implementation does the encoding in one pass.
+     * </p>
+     * 
+     * @param text
+     * @return the corresponding encoding according to the <i>K&ouml;lner Phonetik</i> algorithm
+     */
+    public String colognePhonetic(String text) {
+        if (text == null) {
+            return null;
+        }
+
+        text = preprocess(text);
+
+        CologneOutputBuffer output = new CologneOutputBuffer(text.length() * 2);
+        CologneInputBuffer input = new CologneInputBuffer(text.toCharArray());
+
+        char nextChar;
+
+        char lastChar = '-';
+        char lastCode = '/';
+        char code;
+        char chr;
+
+        int rightLength = input.length();
+
+        while (rightLength > 0) {
+            chr = input.removeNext();
+
+            if ((rightLength = input.length()) > 0) {
+                nextChar = input.getNextChar();
+            } else {
+                nextChar = '-';
+            }
+
+            if (arrayContains(new char[]{'A', 'E', 'I', 'J', 'O', 'U', 'Y'}, chr)) {
+                code = '0';
+            } else if (chr == 'H' || chr < 'A' || chr > 'Z') {
+                if (lastCode == '/') {
+                    continue;
+                }
+                code = '-';
+            } else if (chr == 'B' || (chr == 'P' && nextChar != 'H')) {
+                code = '1';
+            } else if ((chr == 'D' || chr == 'T') && !arrayContains(new char[]{'S', 'C', 'Z'}, nextChar)) {
+                code = '2';
+            } else if (arrayContains(new char[]{'W', 'F', 'P', 'V'}, chr)) {
+                code = '3';
+            } else if (arrayContains(new char[]{'G', 'K', 'Q'}, chr)) {
+                code = '4';
+            } else if (chr == 'X' && !arrayContains(new char[]{'C', 'K', 'Q'}, lastChar)) {
+                code = '4';
+                input.addLeft('S');
+                rightLength++;
+            } else if (chr == 'S' || chr == 'Z') {
+                code = '8';
+            } else if (chr == 'C') {
+                if (lastCode == '/') {
+                    if (arrayContains(new char[]{'A', 'H', 'K', 'L', 'O', 'Q', 'R', 'U', 'X'}, nextChar)) {
+                        code = '4';
+                    } else {
+                        code = '8';
+                    }
+                } else {
+                    if (arrayContains(new char[]{'S', 'Z'}, lastChar) ||
+                        !arrayContains(new char[]{'A', 'H', 'O', 'U', 'K', 'Q', 'X'}, nextChar)) {
+                        code = '8';
+                    } else {
+                        code = '4';
+                    }
+                }
+            } else if (arrayContains(new char[]{'T', 'D', 'X'}, chr)) {
+                code = '8';
+            } else if (chr == 'R') {
+                code = '7';
+            } else if (chr == 'L') {
+                code = '5';
+            } else if (chr == 'M' || chr == 'N') {
+                code = '6';
+            } else {
+                code = chr;
+            }
+
+            if (code != '-' && (lastCode != code && (code != '0' || lastCode == '/') || code < '0' || code > '8')) {
+                output.addRight(code);
+            }
+
+            lastChar = chr;
+            lastCode = code;
+        }
+        return output.toString();
+    }
+
+    public Object encode(Object object) throws EncoderException {
+        if (!(object instanceof String)) {
+            throw new EncoderException("This method's parameter was expected to be of the type " +
+                String.class.getName() +
+                ". But actually it was of the type " +
+                object.getClass().getName() +
+                ".");
+        }
+        return encode((String) object);
+    }
+
+    public String encode(String text) {
+        return colognePhonetic(text);
+    }
+
+    public boolean isEncodeEqual(String text1, String text2) {
+        return colognePhonetic(text1).equals(colognePhonetic(text2));
+    }
+
+    /**
+     * Converts the string to upper case and replaces germanic characters as defined in {@link #PREPROCESS_MAP}.
+     */
+    private String preprocess(String text) {
+        text = text.toUpperCase(Locale.GERMAN);
+
+        char[] chrs = text.toCharArray();
+
+        for (int index = 0; index < chrs.length; index++) {
+            if (chrs[index] > 'Z') {
+                for (char[] element : PREPROCESS_MAP) {
+                    if (chrs[index] == element[0]) {
+                        chrs[index] = element[1];
+                        break;
+                    }
+                }
+            }
+        }
+        return new String(chrs);
+    }
+}

source/net/yacy/cora/language/phonetic/Metaphone.java

@@ -0,0 +1,407 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ * 
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ * 
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package net.yacy.cora.language.phonetic;
+
+import org.apache.commons.codec.EncoderException;
+import org.apache.commons.codec.StringEncoder;
+
+/**
+ * Encodes a string into a Metaphone value. 
+ * <p>
+ * Initial Java implementation by <CITE>William B. Brogden. December, 1997</CITE>. 
+ * Permission given by <CITE>wbrogden</CITE> for code to be used anywhere.
+ * </p>
+ * <p>
+ * <CITE>Hanging on the Metaphone</CITE> by <CITE>Lawrence Philips</CITE> in <CITE>Computer Language of Dec. 1990, p
+ * 39.</CITE>
+ * </p>
+ * <p>
+ * Note, that this does not match the algorithm that ships with PHP, or the algorithm 
+ * found in the Perl <a href="http://search.cpan.org/~mschwern/Text-Metaphone-1.96/Metaphone.pm">Text:Metaphone-1.96</a>.
+ * They have had undocumented changes from the originally published algorithm. 
+ * For more information, see <a href="https://issues.apache.org/jira/browse/CODEC-57">CODEC-57</a>.
+ * </p>
+ * 
+ * @author Apache Software Foundation
+ * @version $Id: Metaphone.java 1157192 2011-08-12 17:27:38Z ggregory $
+ */
+public class Metaphone implements StringEncoder {
+
+    /**
+     * Five values in the English language 
+     */
+    private static final String VOWELS = "AEIOU" ;
+
+    /**
+     * Variable used in Metaphone algorithm
+     */
+    private static final String FRONTV = "EIY"   ;
+
+    /**
+     * Variable used in Metaphone algorithm
+     */
+    private static final String VARSON = "CSPTG" ;
+
+    /**
+     * The max code length for metaphone is 4
+     */
+    private int maxCodeLen = 4 ;
+
+    /**
+     * Creates an instance of the Metaphone encoder
+     */
+    public Metaphone() {
+        super();
+    }
+
+    /**
+     * Find the metaphone value of a String. This is similar to the
+     * soundex algorithm, but better at finding similar sounding words.
+     * All input is converted to upper case.
+     * Limitations: Input format is expected to be a single ASCII word
+     * with only characters in the A - Z range, no punctuation or numbers.
+     *
+     * @param txt String to find the metaphone code for
+     * @return A metaphone code corresponding to the String supplied
+     */
+    public String metaphone(String txt) {
+        boolean hard = false ;
+        if ((txt == null) || (txt.length() == 0)) {
+            return "" ;
+        }
+        // single character is itself
+        if (txt.length() == 1) {
+            return txt.toUpperCase(java.util.Locale.ENGLISH) ;
+        }
+      
+        char[] inwd = txt.toUpperCase(java.util.Locale.ENGLISH).toCharArray() ;
+      
+        StringBuffer local = new StringBuffer(40); // manipulate
+        StringBuffer code = new StringBuffer(10) ; //   output
+        // handle initial 2 characters exceptions
+        switch(inwd[0]) {
+        case 'K' : 
+        case 'G' : 
+        case 'P' : /* looking for KN, etc*/
+            if (inwd[1] == 'N') {
+                local.append(inwd, 1, inwd.length - 1);
+            } else {
+                local.append(inwd);
+            }
+            break;
+        case 'A': /* looking for AE */
+            if (inwd[1] == 'E') {
+                local.append(inwd, 1, inwd.length - 1);
+            } else {
+                local.append(inwd);
+            }
+            break;
+        case 'W' : /* looking for WR or WH */
+            if (inwd[1] == 'R') {   // WR -> R
+                local.append(inwd, 1, inwd.length - 1); 
+                break ;
+            }
+            if (inwd[1] == 'H') {
+                local.append(inwd, 1, inwd.length - 1);
+                local.setCharAt(0, 'W'); // WH -> W
+            } else {
+                local.append(inwd);
+            }
+            break;
+        case 'X' : /* initial X becomes S */
+            inwd[0] = 'S';
+            local.append(inwd);
+            break ;
+        default :
+            local.append(inwd);
+        } // now local has working string with initials fixed
+
+        int wdsz = local.length();
+        int n = 0 ;
+
+        while ((code.length() < this.getMaxCodeLen()) && 
+               (n < wdsz) ) { // max code size of 4 works well
+            char symb = local.charAt(n) ;
+            // remove duplicate letters except C
+            if ((symb != 'C') && (isPreviousChar( local, n, symb )) ) {
+                n++ ;
+            } else { // not dup
+                switch(symb) {
+                case 'A' : case 'E' : case 'I' : case 'O' : case 'U' :
+                    if (n == 0) { 
+                        code.append(symb);
+                    }
+                    break ; // only use vowel if leading char
+                case 'B' :
+                    if ( isPreviousChar(local, n, 'M') && 
+                         isLastChar(wdsz, n) ) { // B is silent if word ends in MB
+                        break;
+                    }
+                    code.append(symb);
+                    break;
+                case 'C' : // lots of C special cases
+                    /* discard if SCI, SCE or SCY */
+                    if ( isPreviousChar(local, n, 'S') && 
+                         !isLastChar(wdsz, n) && 
+                         (FRONTV.indexOf(local.charAt(n + 1)) >= 0) ) { 
+                        break;
+                    }
+                    if (regionMatch(local, n, "CIA")) { // "CIA" -> X
+                        code.append('X'); 
+                        break;
+                    }
+                    if (!isLastChar(wdsz, n) && 
+                        (FRONTV.indexOf(local.charAt(n + 1)) >= 0)) {
+                        code.append('S');
+                        break; // CI,CE,CY -> S
+                    }
+                    if (isPreviousChar(local, n, 'S') &&
+                        isNextChar(local, n, 'H') ) { // SCH->sk
+                        code.append('K') ; 
+                        break ;
+                    }
+                    if (isNextChar(local, n, 'H')) { // detect CH
+                        if ((n == 0) && 
+                            (wdsz >= 3) && 
+                            isVowel(local,2) ) { // CH consonant -> K consonant
+                            code.append('K');
+                        } else { 
+                            code.append('X'); // CHvowel -> X
+                        }
+                    } else { 
+                        code.append('K');
+                    }
+                    break ;
+                case 'D' :
+                    if (!isLastChar(wdsz, n + 1) && 
+                        isNextChar(local, n, 'G') && 
+                        (FRONTV.indexOf(local.charAt(n + 2)) >= 0)) { // DGE DGI DGY -> J 
+                        code.append('J'); n += 2 ;
+                    } else { 
+                        code.append('T');
+                    }
+                    break ;
+                case 'G' : // GH silent at end or before consonant
+                    if (isLastChar(wdsz, n + 1) && 
+                        isNextChar(local, n, 'H')) {
+                        break;
+                    }
+                    if (!isLastChar(wdsz, n + 1) &&  
+                        isNextChar(local,n,'H') && 
+                        !isVowel(local,n+2)) {
+                        break;
+                    }
+                    if ((n > 0) && 
+                        ( regionMatch(local, n, "GN") ||
+                          regionMatch(local, n, "GNED") ) ) {
+                        break; // silent G
+                    }
+                    if (isPreviousChar(local, n, 'G')) {
+                        // NOTE: Given that duplicated chars are removed, I don't see how this can ever be true
+                        hard = true ;
+                    } else {
+                        hard = false ;
+                    }
+                    if (!isLastChar(wdsz, n) && 
+                        (FRONTV.indexOf(local.charAt(n + 1)) >= 0) && 
+                        (!hard)) {
+                        code.append('J');
+                    } else {
+                        code.append('K');
+                    }
+                    break ;
+                case 'H':
+                    if (isLastChar(wdsz, n)) {
+                        break ; // terminal H
+                    }
+                    if ((n > 0) && 
+                        (VARSON.indexOf(local.charAt(n - 1)) >= 0)) {
+                        break;
+                    }
+                    if (isVowel(local,n+1)) {
+                        code.append('H'); // Hvowel
+                    }
+                    break;
+                case 'F': 
+                case 'J' : 
+                case 'L' :
+                case 'M': 
+                case 'N' : 
+                case 'R' :
+                    code.append(symb); 
+                    break;
+                case 'K' :
+                    if (n > 0) { // not initial
+                        if (!isPreviousChar(local, n, 'C')) {
+                            code.append(symb);
+                        }
+                    } else {
+                        code.append(symb); // initial K
+                    }
+                    break ;
+                case 'P' :
+                    if (isNextChar(local,n,'H')) {
+                        // PH -> F
+                        code.append('F');
+                    } else {
+                        code.append(symb);
+                    }
+                    break ;
+                case 'Q' :
+                    code.append('K');
+                    break;
+                case 'S' :
+                    if (regionMatch(local,n,"SH") || 
+                        regionMatch(local,n,"SIO") || 
+                        regionMatch(local,n,"SIA")) {
+                        code.append('X');
+                    } else {
+                        code.append('S');
+                    }
+                    break;
+                case 'T' :
+                    if (regionMatch(local,n,"TIA") || 
+                        regionMatch(local,n,"TIO")) {
+                        code.append('X'); 
+                        break;
+                    }
+                    if (regionMatch(local,n,"TCH")) {
+                        // Silent if in "TCH"
+                        break;
+                    }
+                    // substitute numeral 0 for TH (resembles theta after all)
+                    if (regionMatch(local,n,"TH")) {
+                        code.append('0');
+                    } else {
+                        code.append('T');
+                    }
+                    break ;
+                case 'V' :
+                    code.append('F'); break ;
+                case 'W' : case 'Y' : // silent if not followed by vowel
+                    if (!isLastChar(wdsz,n) && 
+                        isVowel(local,n+1)) {
+                        code.append(symb);
+                    }
+                    break ;
+                case 'X' :
+                    code.append('K'); code.append('S');
+                    break ;
+                case 'Z' :
+                    code.append('S'); break ;
+                } // end switch
+                n++ ;
+            } // end else from symb != 'C'
+            if (code.length() > this.getMaxCodeLen()) { 
+                code.setLength(this.getMaxCodeLen()); 
+            }
+        }
+        return code.toString();
+    }
+
+    private boolean isVowel(StringBuffer string, int index) {
+        return VOWELS.indexOf(string.charAt(index)) >= 0;
+    }
+
+    private boolean isPreviousChar(StringBuffer string, int index, char c) {
+        boolean matches = false;
+        if( index > 0 &&
+            index < string.length() ) {
+            matches = string.charAt(index - 1) == c;
+        }
+        return matches;
+    }
+
+    private boolean isNextChar(StringBuffer string, int index, char c) {
+        boolean matches = false;
+        if( index >= 0 &&
+            index < string.length() - 1 ) {
+            matches = string.charAt(index + 1) == c;
+        }
+        return matches;
+    }
+
+    private boolean regionMatch(StringBuffer string, int index, String test) {
+        boolean matches = false;
+        if( index >= 0 &&
+            (index + test.length() - 1) < string.length() ) {
+            String substring = string.substring( index, index + test.length());
+            matches = substring.equals( test );
+        }
+        return matches;
+    }
+
+    private boolean isLastChar(int wdsz, int n) {
+        return n + 1 == wdsz;
+    } 
+    
+    
+    /**
+     * Encodes an Object using the metaphone algorithm.  This method
+     * is provided in order to satisfy the requirements of the
+     * Encoder interface, and will throw an EncoderException if the
+     * supplied object is not of type java.lang.String.
+     *
+     * @param pObject Object to encode
+     * @return An object (or type java.lang.String) containing the 
+     *         metaphone code which corresponds to the String supplied.
+     * @throws EncoderException if the parameter supplied is not
+     *                          of type java.lang.String
+     */
+    public Object encode(Object pObject) throws EncoderException {
+        if (!(pObject instanceof String)) {
+            throw new EncoderException("Parameter supplied to Metaphone encode is not of type java.lang.String"); 
+        }
+        return metaphone((String) pObject);
+    }
+
+    /**
+     * Encodes a String using the Metaphone algorithm. 
+     *
+     * @param pString String object to encode
+     * @return The metaphone code corresponding to the String supplied
+     */
+    public String encode(String pString) {
+        return metaphone(pString);   
+    }
+
+    /**
+     * Tests is the metaphones of two strings are identical.
+     *
+     * @param str1 First of two strings to compare
+     * @param str2 Second of two strings to compare
+     * @return <code>true</code> if the metaphones of these strings are identical, 
+     *        <code>false</code> otherwise.
+     */
+    public boolean isMetaphoneEqual(String str1, String str2) {
+        return metaphone(str1).equals(metaphone(str2));
+    }
+
+    /**
+     * Returns the maxCodeLen.
+     * @return int
+     */
+    public int getMaxCodeLen() { return this.maxCodeLen; }
+
+    /**
+     * Sets the maxCodeLen.
+     * @param maxCodeLen The maxCodeLen to set
+     */
+    public void setMaxCodeLen(int maxCodeLen) { this.maxCodeLen = maxCodeLen; }
+
+}

source/net/yacy/cora/language/phonetic/Phonetic.java

@@ -0,0 +1,73 @@
+/**
+ *  Phonetic
+ *  Copyright 201 by Michael Peter Christen, mc@yacy.net, Frankfurt a. M., Germany
+ *  First released 13.12.2011 at http://yacy.net
+ *
+ *  $LastChangedDate$
+ *  $LastChangedRevision$
+ *  $LastChangedBy$
+ *
+ *  This library is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU Lesser General Public
+ *  License as published by the Free Software Foundation; either
+ *  version 2.1 of the License, or (at your option) any later version.
+ *
+ *  This library is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  Lesser General Public License for more details.
+ *
+ *  You should have received a copy of the GNU Lesser General Public License
+ *  along with this program in the file lgpl21.txt
+ *  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+package net.yacy.cora.language.phonetic;
+
+public class Phonetic {
+
+    public enum Encoder {
+        SOUNDEX("Soundex", ""),
+        COLONE_PHONETIC("Koelner Phonetik", "http://de.wikipedia.org/wiki/K%C3%B6lner_Phonetik"),
+        METAPHONE("Metaphone", ""),
+        DOUBLE_METAPHONE("Double Metaphone", ""),
+        NONE("", "");
+        
+        final String printName;
+        final String infoUrl;
+        
+        private Encoder(final String printName, final String infoUrl) {
+            this.printName = printName;
+            this.infoUrl = infoUrl;
+        }
+    }
+    
+    private static final Soundex soundexEncoder = new Soundex();
+    private static final Metaphone metaphoneEncoder = new Metaphone();
+    private static final DoubleMetaphone doubleMetaphoneEncoder = new DoubleMetaphone();
+    private static final ColognePhonetic colognePhonetic = new ColognePhonetic();
+    
+    public static String encode(final Encoder encoder, final String s) {
+        try {
+            if (encoder == Encoder.SOUNDEX) return soundexEncoder.encode(s);
+            if (encoder == Encoder.COLONE_PHONETIC) return colognePhonetic.encode(s);
+            if (encoder == Encoder.METAPHONE) return metaphoneEncoder.encode(s);
+            if (encoder == Encoder.DOUBLE_METAPHONE) return doubleMetaphoneEncoder.encode(s);
+            return s;
+        } catch (Throwable e) {
+            // some encoders do not work with non-ASCII charachters and throw an exception
+            return s;
+        }
+    }
+    
+    public static void main(String[] args) {
+        for (Encoder encoder: Encoder.values()) {
+            for (String s: args) {
+                System.out.print(Phonetic.encode(encoder, s));
+                System.out.print(" ");
+            }
+            System.out.println();
+        }
+    }
+    
+}

source/net/yacy/cora/language/phonetic/Soundex.java

@@ -0,0 +1,340 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ * 
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ * 
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package net.yacy.cora.language.phonetic;
+
+import org.apache.commons.codec.EncoderException;
+import org.apache.commons.codec.StringEncoder;
+
+/**
+ * Encodes a string into a Soundex value. Soundex is an encoding used to relate similar names, but can also be used as a
+ * general purpose scheme to find word with similar phonemes.
+ * 
+ * @author Apache Software Foundation
+ * @version $Id: Soundex.java 1201529 2011-11-13 21:57:16Z ggregory $
+ */
+public class Soundex implements StringEncoder {
+
+    /**
+     * This is a default mapping of the 26 letters used in US English. A value of <code>0</code> for a letter position
+     * means do not encode.
+     * <p>
+     * (This constant is provided as both an implementation convenience and to allow Javadoc to pick
+     * up the value for the constant values page.)
+     * </p>
+     * 
+     * @see #US_ENGLISH_MAPPING
+     */
+    public static final String US_ENGLISH_MAPPING_STRING = "01230120022455012623010202";
+
+    /**
+     * This is a default mapping of the 26 letters used in US English. A value of <code>0</code> for a letter position
+     * means do not encode.
+     * 
+     * @see Soundex#Soundex(char[])
+     */
+    private static final char[] US_ENGLISH_MAPPING = US_ENGLISH_MAPPING_STRING.toCharArray();
+
+    /**
+     * An instance of Soundex using the US_ENGLISH_MAPPING mapping.
+     * 
+     * @see #US_ENGLISH_MAPPING
+     */
+    public static final Soundex US_ENGLISH = new Soundex();
+
+    /**
+     * Every letter of the alphabet is "mapped" to a numerical value. This char array holds the values to which each
+     * letter is mapped. This implementation contains a default map for US_ENGLISH
+     */
+    private final char[] soundexMapping;
+
+    /**
+     * Creates an instance using US_ENGLISH_MAPPING
+     * 
+     * @see Soundex#Soundex(char[])
+     * @see Soundex#US_ENGLISH_MAPPING
+     */
+    public Soundex() {
+        this.soundexMapping = US_ENGLISH_MAPPING;
+    }
+
+    /**
+     * Creates a soundex instance using the given mapping. This constructor can be used to provide an internationalized
+     * mapping for a non-Western character set.
+     * 
+     * Every letter of the alphabet is "mapped" to a numerical value. This char array holds the values to which each
+     * letter is mapped. This implementation contains a default map for US_ENGLISH
+     * 
+     * @param mapping
+     *                  Mapping array to use when finding the corresponding code for a given character
+     */
+    public Soundex(char[] mapping) {
+        this.soundexMapping = new char[mapping.length];
+        System.arraycopy(mapping, 0, this.soundexMapping, 0, mapping.length);
+    }
+
+    /**
+     * Creates a refined soundex instance using a custom mapping. This constructor can be used to customize the mapping,
+     * and/or possibly provide an internationalized mapping for a non-Western character set.
+     * 
+     * @param mapping
+     *            Mapping string to use when finding the corresponding code for a given character
+     * @since 1.4
+     */
+    public Soundex(String mapping) {
+        this.soundexMapping = mapping.toCharArray();
+    }
+
+    /**
+     * Encodes the Strings and returns the number of characters in the two encoded Strings that are the same. This
+     * return value ranges from 0 through 4: 0 indicates little or no similarity, and 4 indicates strong similarity or
+     * identical values.
+     * 
+     * @param s1
+     *                  A String that will be encoded and compared.
+     * @param s2
+     *                  A String that will be encoded and compared.
+     * @return The number of characters in the two encoded Strings that are the same from 0 to 4.
+     * 
+     * @see SoundexUtils#difference(StringEncoder,String,String)
+     * @see <a href="http://msdn.microsoft.com/library/default.asp?url=/library/en-us/tsqlref/ts_de-dz_8co5.asp"> MS
+     *          T-SQL DIFFERENCE </a>
+     * 
+     * @throws EncoderException
+     *                  if an error occurs encoding one of the strings
+     * @since 1.3
+     */
+    public int difference(String s1, String s2) throws EncoderException {
+        return difference(this, s1, s2);
+    }
+
+    /**
+     * Encodes an Object using the soundex algorithm. This method is provided in order to satisfy the requirements of
+     * the Encoder interface, and will throw an EncoderException if the supplied object is not of type java.lang.String.
+     * 
+     * @param pObject
+     *                  Object to encode
+     * @return An object (or type java.lang.String) containing the soundex code which corresponds to the String
+     *             supplied.
+     * @throws EncoderException
+     *                  if the parameter supplied is not of type java.lang.String
+     * @throws IllegalArgumentException
+     *                  if a character is not mapped
+     */
+    public Object encode(Object pObject) throws EncoderException {
+        if (!(pObject instanceof String)) {
+            throw new EncoderException("Parameter supplied to Soundex encode is not of type java.lang.String");
+        }
+        return soundex((String) pObject);
+    }
+
+    /**
+     * Encodes a String using the soundex algorithm.
+     * 
+     * @param pString
+     *                  A String object to encode
+     * @return A Soundex code corresponding to the String supplied
+     * @throws IllegalArgumentException
+     *                  if a character is not mapped
+     */
+    public String encode(String pString) {
+        return soundex(pString);
+    }
+
+    /**
+     * Used internally by the SoundEx algorithm.
+     * 
+     * Consonants from the same code group separated by W or H are treated as one.
+     * 
+     * @param str
+     *                  the cleaned working string to encode (in upper case).
+     * @param index
+     *                  the character position to encode
+     * @return Mapping code for a particular character
+     * @throws IllegalArgumentException
+     *                  if the character is not mapped
+     */
+    private char getMappingCode(String str, int index) {
+        // map() throws IllegalArgumentException
+        char mappedChar = this.map(str.charAt(index));
+        // HW rule check
+        if (index > 1 && mappedChar != '0') {
+            char hwChar = str.charAt(index - 1);
+            if ('H' == hwChar || 'W' == hwChar) {
+                char preHWChar = str.charAt(index - 2);
+                char firstCode = this.map(preHWChar);
+                if (firstCode == mappedChar || 'H' == preHWChar || 'W' == preHWChar) {
+                    return 0;
+                }
+            }
+        }
+        return mappedChar;
+    }
+    
+    /**
+     * Returns the soundex mapping.
+     * 
+     * @return soundexMapping.
+     */
+    private char[] getSoundexMapping() {
+        return this.soundexMapping;
+    }
+
+    /**
+     * Maps the given upper-case character to its Soundex code.
+     * 
+     * @param ch
+     *                  An upper-case character.
+     * @return A Soundex code.
+     * @throws IllegalArgumentException
+     *                  Thrown if <code>ch</code> is not mapped.
+     */
+    private char map(char ch) {
+        int index = ch - 'A';
+        if (index < 0 || index >= this.getSoundexMapping().length) {
+            throw new IllegalArgumentException("The character is not mapped: " + ch);
+        }
+        return this.getSoundexMapping()[index];
+    }
+
+    /**
+     * Retrieves the Soundex code for a given String object.
+     * 
+     * @param str
+     *                  String to encode using the Soundex algorithm
+     * @return A soundex code for the String supplied
+     * @throws IllegalArgumentException
+     *                  if a character is not mapped
+     */
+    public String soundex(String str) {
+        if (str == null) {
+            return null;
+        }
+        str = clean(str);
+        if (str.length() == 0) {
+            return str;
+        }
+        char out[] = {'0', '0', '0', '0'};
+        char last, mapped;
+        int incount = 1, count = 1;
+        out[0] = str.charAt(0);
+        // getMappingCode() throws IllegalArgumentException
+        last = getMappingCode(str, 0);
+        while ((incount < str.length()) && (count < out.length)) {
+            mapped = getMappingCode(str, incount++);
+            if (mapped != 0) {
+                if ((mapped != '0') && (mapped != last)) {
+                    out[count++] = mapped;
+                }
+                last = mapped;
+            }
+        }
+        return new String(out);
+    }
+
+
+    /**
+     * Cleans up the input string before Soundex processing by only returning
+     * upper case letters.
+     * 
+     * @param str
+     *                  The String to clean.
+     * @return A clean String.
+     */
+    static String clean(String str) {
+        if (str == null || str.length() == 0) {
+            return str;
+        }
+        int len = str.length();
+        char[] chars = new char[len];
+        int count = 0;
+        for (int i = 0; i < len; i++) {
+            if (Character.isLetter(str.charAt(i))) {
+                chars[count++] = str.charAt(i);
+            }
+        }
+        if (count == len) {
+            return str.toUpperCase(java.util.Locale.ENGLISH);
+        }
+        return new String(chars, 0, count).toUpperCase(java.util.Locale.ENGLISH);
+    }
+
+    /**
+     * Encodes the Strings and returns the number of characters in the two
+     * encoded Strings that are the same.
+     * <ul>
+     * <li>For Soundex, this return value ranges from 0 through 4: 0 indicates
+     * little or no similarity, and 4 indicates strong similarity or identical
+     * values.</li>
+     * <li>For refined Soundex, the return value can be greater than 4.</li>
+     * </ul>
+     * 
+     * @param encoder
+     *                  The encoder to use to encode the Strings.
+     * @param s1
+     *                  A String that will be encoded and compared.
+     * @param s2
+     *                  A String that will be encoded and compared.
+     * @return The number of characters in the two Soundex encoded Strings that
+     *             are the same.
+     * 
+     * @see #differenceEncoded(String,String)
+     * @see <a href="http://msdn.microsoft.com/library/default.asp?url=/library/en-us/tsqlref/ts_de-dz_8co5.asp">
+     *          MS T-SQL DIFFERENCE</a>
+     * 
+     * @throws EncoderException
+     *                  if an error occurs encoding one of the strings
+     */
+    static int difference(StringEncoder encoder, String s1, String s2) throws EncoderException {
+        return differenceEncoded(encoder.encode(s1), encoder.encode(s2));
+    }
+
+    /**
+     * Returns the number of characters in the two Soundex encoded Strings that
+     * are the same.
+     * <ul>
+     * <li>For Soundex, this return value ranges from 0 through 4: 0 indicates
+     * little or no similarity, and 4 indicates strong similarity or identical
+     * values.</li>
+     * <li>For refined Soundex, the return value can be greater than 4.</li>
+     * </ul>
+     * 
+     * @param es1
+     *                  An encoded String.
+     * @param es2
+     *                  An encoded String.
+     * @return The number of characters in the two Soundex encoded Strings that
+     *             are the same.
+     * 
+     * @see <a href="http://msdn.microsoft.com/library/default.asp?url=/library/en-us/tsqlref/ts_de-dz_8co5.asp">
+     *          MS T-SQL DIFFERENCE</a>
+     */
+    static int differenceEncoded(String es1, String es2) {
+
+        if (es1 == null || es2 == null) {
+            return 0;
+        }
+        int lengthToMatch = Math.min(es1.length(), es2.length());
+        int diff = 0;
+        for (int i = 0; i < lengthToMatch; i++) {
+            if (es1.charAt(i) == es2.charAt(i)) {
+                diff++;
+            }
+        }
+        return diff;
+    }
+}

source/net/yacy/cora/plugin/ClassProvider.java

@@ -1,3 +1,27 @@
+/**
+ *  ClassProvider
+ *  Copyright 201 by Michael Peter Christen, mc@yacy.net, Frankfurt a. M., Germany
+ *  First released 13.12.2011 at http://yacy.net
+ *
+ *  $LastChangedDate$
+ *  $LastChangedRevision$
+ *  $LastChangedBy$
+ *
+ *  This library is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU Lesser General Public
+ *  License as published by the Free Software Foundation; either
+ *  version 2.1 of the License, or (at your option) any later version.
+ *
+ *  This library is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  Lesser General Public License for more details.
+ *
+ *  You should have received a copy of the GNU Lesser General Public License
+ *  along with this program in the file lgpl21.txt
+ *  If not, see <http://www.gnu.org/licenses/>.
+ */
+
 package net.yacy.cora.plugin;
 
 import java.io.File;