org.testifyproject.apache.commons.codec.language.ColognePhonetic Maven / Gradle / Ivy
The newest version!
/*
* 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 org.testifyproject.testifyprojectpliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org.testifyproject/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 org.testifyproject.apache.org.testifyproject.testifyprojectmons.codec.language;
import java.util.Locale;
import org.testifyproject.apache.org.testifyproject.testifyprojectmons.codec.EncoderException;
import org.testifyproject.apache.org.testifyproject.testifyprojectmons.codec.StringEncoder;
/**
* Encodes a string into a Cologne Phonetic value.
*
* Implements the Kölner Phonetik
* (Cologne Phonetic) algorithm issued by Hans Joachim Postel in 1969.
*
* The Kölner Phonetik is a phonetic algorithm which is optimized for the German language.
* It is related to the well-known soundex algorithm.
*
*
*
Algorithm
*
*
*
* -
*
Step 1:
* After preprocessing (conversion to upper case, transcription of germanic umlauts, removal of non alphabetical characters) the
* letters of the supplied text are replaced by their phonetic code according to the following table.
*
*
*
* Letter
* Context
* Code
*
*
* A, E, I, J, O, U, Y
* 0
*
*
*
* H
* -
*
*
* B
* 1
*
*
* P
* not before H
*
*
*
* D, T
* not before C, S, Z
* 2
*
*
* F, V, W
* 3
*
*
*
* P
* before H
*
*
* G, K, Q
* 4
*
*
* C
* at onset before A, H, K, L, O, Q, R, U, X
*
*
*
* before A, H, K, O, Q, U, X except after S, Z
*
*
* X
* not after C, K, Q
* 48
*
*
* L
* 5
*
*
* M, N
* 6
*
*
* R
* 7
*
*
*
* S, Z
* 8
*
*
* C
* after S, Z
*
*
* at onset except before A, H, K, L, O, Q, R, U, X
*
*
*
* not before A, H, K, O, Q, U, X
*
*
* D, T
* before C, S, Z
*
*
* X
* after C, K, Q
*
*
*
*
* (Source: Wikipedia (de):
* Kölner Phonetik -- Buchstabencodes)
*
*
* Example:
*
* {@code "M}ü{@code ller-L}ü{@code denscheidt" => "MULLERLUDENSCHEIDT" => "6005507500206880022"}
*
*
*
* -
*
Step 2:
* Collapse of all multiple consecutive code digits.
* Example:
* {@code "6005507500206880022" => "6050750206802"}
*
* -
*
Step 3:
* 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.
*
* Example:
* {@code "6050750206802" => "65752682"}
*
*
*
* This class is thread-safe.
*
* @see Wikipedia (de): Kölner Phonetik (in German)
* @since 1.5
*/
public class ColognePhonetic implements StringEncoder {
// Predefined char arrays for better performance and less GC load
private static final char[] AEIJOUY = new char[] { 'A', 'E', 'I', 'J', 'O', 'U', 'Y' };
private static final char[] SCZ = new char[] { 'S', 'C', 'Z' };
private static final char[] WFPV = new char[] { 'W', 'F', 'P', 'V' };
private static final char[] GKQ = new char[] { 'G', 'K', 'Q' };
private static final char[] CKQ = new char[] { 'C', 'K', 'Q' };
private static final char[] AHKLOQRUX = new char[] { 'A', 'H', 'K', 'L', 'O', 'Q', 'R', 'U', 'X' };
private static final char[] SZ = new char[] { 'S', 'Z' };
private static final char[] AHOUKQX = new char[] { 'A', 'H', 'O', 'U', 'K', 'Q', 'X' };
private static final char[] TDX = new char[] { 'T', 'D', 'X' };
/**
* This class is not thread-safe; the field {@link #length} is mutable.
* However, it is not shared between threads, as it is constructed on demand
* by the method {@link ColognePhonetic#colognePhonetic(String)}
*/
private abstract class CologneBuffer {
protected final char[] data;
protected int length = 0;
public CologneBuffer(final char[] data) {
this.data = data;
this.length = data.length;
}
public CologneBuffer(final 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(final int buffSize) {
super(buffSize);
}
public void addRight(final char chr) {
data[length] = chr;
length++;
}
@Override
protected char[] copyData(final int start, final int length) {
final char[] newData = new char[length];
System.arraycopy(data, start, newData, 0, length);
return newData;
}
}
private class CologneInputBuffer extends CologneBuffer {
public CologneInputBuffer(final char[] data) {
super(data);
}
public void addLeft(final char ch) {
length++;
data[getNextPos()] = ch;
}
@Override
protected char[] copyData(final int start, final int length) {
final 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() {
final char ch = getNextChar();
length--;
return ch;
}
}
/**
* Maps some Germanic characters to plain for internal processing. The following characters are mapped:
*
* - capital a, umlaut mark
* - capital u, umlaut mark
* - capital o, umlaut mark
* - small sharp s, German
*
*/
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(final char[] arr, final char key) {
for (final char element : arr) {
if (element == key) {
return true;
}
}
return false;
}
/**
*
* Implements the Kölner Phonetik algorithm.
*
*
* In contrast to the initial description of the algorithm, this implementation does the encoding in one pass.
*
*
* @param text
* @return the corresponding encoding according to the Kölner Phonetik algorithm
*/
public String colognePhonetic(String text) {
if (text == null) {
return null;
}
text = preprocess(text);
final CologneOutputBuffer output = new CologneOutputBuffer(text.length() * 2);
final 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(AEIJOUY, 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(SCZ, nextChar)) {
code = '2';
} else if (arrayContains(WFPV, chr)) {
code = '3';
} else if (arrayContains(GKQ, chr)) {
code = '4';
} else if (chr == 'X' && !arrayContains(CKQ, lastChar)) {
code = '4';
input.addLeft('S');
rightLength++;
} else if (chr == 'S' || chr == 'Z') {
code = '8';
} else if (chr == 'C') {
if (lastCode == '/') {
if (arrayContains(AHKLOQRUX, nextChar)) {
code = '4';
} else {
code = '8';
}
} else {
if (arrayContains(SZ, lastChar) || !arrayContains(AHOUKQX, nextChar)) {
code = '8';
} else {
code = '4';
}
}
} else if (arrayContains(TDX, 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();
}
@Override
public Object encode(final 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);
}
@Override
public String encode(final String text) {
return colognePhonetic(text);
}
public boolean isEncodeEqual(final String text1, final 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);
final char[] chrs = text.toCharArray();
for (int index = 0; index < chrs.length; index++) {
if (chrs[index] > 'Z') {
for (final char[] element : PREPROCESS_MAP) {
if (chrs[index] == element[0]) {
chrs[index] = element[1];
break;
}
}
}
}
return new String(chrs);
}
}
© 2015 - 2024 Weber Informatics LLC | Privacy Policy