Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance. Project price only 1 $
You can buy this project and download/modify it how often you want.
/*
* Licensed to Elasticsearch under one or more contributor
* license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright
* ownership. Elasticsearch 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 org.elasticsearch.index.analysis.phonetic;
import org.apache.commons.codec.EncoderException;
import org.apache.commons.codec.StringEncoder;
import java.util.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/**
* Kölner Phonetik
*
* H.J. Postel, Die Kölner Phonetik. Ein Verfahren zu Identifizierung
* von Personennamen auf der Grundlage der Gestaltanalyse. IBM-Nachrichten 19 (1969), 925-931
*
* Algorithmus aus der Matching Toolbox von Rainer Schnell
* Java-Programmierung von Jörg Reiher
*
* mit Änderungen von Jörg Prante
*
*/
public class KoelnerPhonetik implements StringEncoder {
private static final String[] POSTEL_VARIATIONS_PATTERNS = {"AUN", "OWN", "RB", "RW", "WSK", "RSK"};
private static final String[] POSTEL_VARIATIONS_REPLACEMENTS = {"OWN", "AUN", "RW", "RB", "RSK", "WSK"};
private Pattern[] variationsPatterns;
private boolean primary = false;
private final Set csz = new HashSet(Arrays.asList(
'C', 'S', 'Z'));
private final Set ckq = new HashSet(Arrays.asList(
'C', 'K', 'Q'));
private final Set aouhkxq = new HashSet(Arrays.asList(
'A', 'O', 'U', 'H', 'K', 'X', 'Q'));
private final Set ahkloqrux = new HashSet(Arrays.asList(
'A', 'H', 'K', 'L', 'O', 'Q', 'R', 'U', 'X'));
/**
* Constructor for Kölner Phonetik
*/
public KoelnerPhonetik() {
init();
}
public KoelnerPhonetik(boolean useOnlyPrimaryCode) {
this();
this.primary = useOnlyPrimaryCode;
}
/**
* Get variation patterns
*
* @return string array of variations
*/
protected String[] getPatterns() {
return POSTEL_VARIATIONS_PATTERNS;
}
protected String[] getReplacements() {
return POSTEL_VARIATIONS_REPLACEMENTS;
}
protected char getCode() {
return '0';
}
public double getRelativeValue(Object o1, Object o2) {
String[] kopho1 = code(expandUmlauts(o1.toString().toUpperCase(Locale.GERMANY)));
String[] kopho2 = code(expandUmlauts(o2.toString().toUpperCase(Locale.GERMANY)));
for (int i = 0; i < kopho1.length; i++) {
for (int ii = 0; ii < kopho2.length; ii++) {
if (kopho1[i].equals(kopho2[ii])) {
return 1;
}
}
}
return 0;
}
@Override
public Object encode(Object str) throws EncoderException {
return encode((String) str);
}
@Override
public String encode(String str) throws EncoderException {
if (str == null) return null;
String[] s = code(str.toString());
StringBuilder sb = new StringBuilder();
for (int i = 0; i < s.length; i++) {
sb.append(s[i]);
if (i < s.length - 1) {
sb.append('_');
}
}
return sb.toString();
}
private void init() {
this.variationsPatterns = new Pattern[getPatterns().length];
for (int i = 0; i < getPatterns().length; i++) {
this.variationsPatterns[i] = Pattern.compile(getPatterns()[i]);
}
}
private String[] code(String str) {
List parts = partition(str);
String[] codes = new String[parts.size()];
int i = 0;
for (String s : parts) {
codes[i++] = substitute(s);
}
return codes;
}
private List partition(String str) {
String primaryForm = str;
List parts = new ArrayList();
parts.add(primaryForm.replaceAll("[^\\p{L}\\p{N}]", ""));
if (!primary) {
List tmpParts = new ArrayList();
tmpParts.addAll((Arrays.asList(str.split("[\\p{Z}\\p{C}\\p{P}]"))));
int numberOfParts = tmpParts.size();
while (tmpParts.size() > 0) {
StringBuilder part = new StringBuilder();
for (int i = 0; i < tmpParts.size(); i++) {
part.append(tmpParts.get(i));
if (!(i + 1 == numberOfParts)) {
parts.add(part.toString());
}
}
tmpParts.remove(0);
}
}
List variations = new ArrayList();
for (int i = 0; i < parts.size(); i++) {
List variation = getVariations(parts.get(i));
if (variation != null) {
variations.addAll(variation);
}
}
return variations;
}
private List getVariations(String str) {
int position = 0;
List variations = new ArrayList();
variations.add("");
while (position < str.length()) {
int i = 0;
int substPos = -1;
while (substPos < position && i < getPatterns().length) {
Matcher m = variationsPatterns[i].matcher(str);
while (substPos < position && m.find()) {
substPos = m.start();
}
i++;
}
if (substPos >= position) {
i--;
List varNew = new ArrayList();
String prevPart = str.substring(position, substPos);
for (int ii = 0; ii < variations.size(); ii++) {
String tmp = variations.get(ii);
varNew.add(tmp.concat(prevPart + getReplacements()[i]));
variations.set(ii, variations.get(ii) + prevPart + getPatterns()[i]);
}
variations.addAll(varNew);
position = substPos + getPatterns()[i].length();
} else {
for (int ii = 0; ii < variations.size(); ii++) {
variations.set(ii, variations.get(ii) + str.substring(position, str.length()));
}
position = str.length();
}
}
return variations;
}
private String substitute(String str) {
String s = expandUmlauts(str.toUpperCase(Locale.GERMAN));
s = removeSequences(s);
StringBuilder sb = new StringBuilder();
for (int i = 0; i < s.length(); i++) {
char current = s.charAt(i);
char next = i + 1 < s.length() ? s.charAt(i + 1) : '_';
char prev = i > 0 ? s.charAt(i - 1) : '_';
switch (current) {
case 'A':
case 'E':
case 'I':
case 'J':
case 'Y':
case 'O':
case 'U':
if (i == 0 || ((i == 1) && prev == 'H')) {
sb.append(getCode());
}
break;
case 'P':
sb.append(next == 'H' ? "33" : '1');
break;
case 'B':
sb.append('1');
break;
case 'D':
case 'T':
sb.append(csz.contains(next) ? '8' : '2');
break;
case 'F':
case 'V':
case 'W':
sb.append('3');
break;
case 'G':
case 'K':
case 'Q':
sb.append('4');
break;
case 'C':
if (i == 0) {
sb.append(ahkloqrux.contains(next) ? '4' : '8');
} else {
sb.append(aouhkxq.contains(next) ? '4' : '8');
}
if (sb.length() >= 2 && sb.charAt(sb.length() - 2) == '8') {
sb.setCharAt(sb.length() - 1, '8');
}
break;
case 'X':
sb.append(i < 1 || !ckq.contains(prev) ? "48" : '8');
break;
case 'L':
sb.append('5');
break;
case 'M':
case 'N':
sb.append('6');
break;
case 'R':
sb.append('7');
break;
case 'S':
case 'Z':
sb.append('8');
break;
case 'H':
break;
}
}
s = sb.toString();
s = removeSequences(s);
return s;
}
private String expandUmlauts(String str) {
return str.replaceAll("\u00C4", "AE").replaceAll("\u00D6", "OE").replaceAll("\u00DC", "UE");
}
private String removeSequences(String str) {
if (str == null || str.length() == 0) {
return "";
}
int i = 0, j = 0;
StringBuilder sb = new StringBuilder().append(str.charAt(i++));
char c;
while (i < str.length()) {
c = str.charAt(i);
if (c != sb.charAt(j)) {
sb.append(c);
j++;
}
i++;
}
return sb.toString();
}
}
