rallback on wrong version of morphology, adding interafce for morphology
git-svn-id: https://russianmorphology.googlecode.com/svn/trunk@88 d817d54c-26ab-11de-abc9-2f7d1455ff7a
This commit is contained in:
alexander.a.kuznetsov
@ -23,7 +23,7 @@ import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
|
||||
|
||||
public class LuceneMorphology extends MorphologyWithPrefix {
|
||||
public class LuceneMorphology extends MorphologyImpl {
|
||||
|
||||
public LuceneMorphology(String fileName, LetterDecoderEncoder decoderEncoder) throws IOException {
|
||||
super(fileName, decoderEncoder);
|
||||
@ -33,13 +33,15 @@ public class LuceneMorphology extends MorphologyWithPrefix {
|
||||
super(inputStream, decoderEncoder);
|
||||
}
|
||||
|
||||
public LuceneMorphology(InputStream morphFormInputStream, InputStream prefixesInputStream, LetterDecoderEncoder decoderEncoder) throws IOException {
|
||||
super(morphFormInputStream, prefixesInputStream, decoderEncoder);
|
||||
}
|
||||
|
||||
@Override
|
||||
protected String createForm(String form, String grammaInfo) {
|
||||
return form;
|
||||
public List<String> getMorhInfo(String s) {
|
||||
ArrayList<String> result = new ArrayList<String>();
|
||||
int[] ints = decoderEncoder.encodeToArray(revertWord(s));
|
||||
int ruleId = findRuleId(ints);
|
||||
for (Heuristic h : rules[rulesId[ruleId]]) {
|
||||
result.add(h.transofrmWord(s));
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
protected void readRules(BufferedReader bufferedReader) throws IOException {
|
||||
|
||||
@ -1,214 +1,25 @@
|
||||
/**
|
||||
* Copyright 2009 Alexander Kuznetsov
|
||||
*
|
||||
* Licensed 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.apache.lucene.morphology;
|
||||
|
||||
|
||||
import java.io.*;
|
||||
import java.util.ArrayList;
|
||||
import java.util.HashSet;
|
||||
import java.util.List;
|
||||
|
||||
|
||||
public class Morphology {
|
||||
protected int[][] separators;
|
||||
protected short[] rulesId;
|
||||
protected Heuristic[][] rules;
|
||||
protected String[] grammaInfo;
|
||||
protected LetterDecoderEncoder decoderEncoder;
|
||||
|
||||
|
||||
public Morphology(String fileName, LetterDecoderEncoder decoderEncoder) throws IOException {
|
||||
readFromFile(fileName);
|
||||
this.decoderEncoder = decoderEncoder;
|
||||
}
|
||||
|
||||
public Morphology(InputStream inputStream, LetterDecoderEncoder decoderEncoder) throws IOException {
|
||||
readFromInputStream(inputStream);
|
||||
this.decoderEncoder = decoderEncoder;
|
||||
}
|
||||
|
||||
public Morphology(int[][] separators, short[] rulesId, Heuristic[][] rules, String[] grammaInfo) {
|
||||
this.separators = separators;
|
||||
this.rulesId = rulesId;
|
||||
this.rules = rules;
|
||||
this.grammaInfo = grammaInfo;
|
||||
}
|
||||
|
||||
public int[][] getSeparators() {
|
||||
return separators;
|
||||
}
|
||||
|
||||
public short[] getRulesId() {
|
||||
return rulesId;
|
||||
}
|
||||
|
||||
public Heuristic[][] getRules() {
|
||||
return rules;
|
||||
}
|
||||
|
||||
public String[] getGrammaInfo() {
|
||||
return grammaInfo;
|
||||
}
|
||||
|
||||
public List<String> getMorhInfo(String s) {
|
||||
ArrayList<String> result = new ArrayList<String>();
|
||||
int[] ints = decoderEncoder.encodeToArray(revertWord(s));
|
||||
int ruleId = findRuleId(ints);
|
||||
for (Heuristic h : rules[rulesId[ruleId]]) {
|
||||
result.add(createForm(h.transofrmWord(s),grammaInfo[h.getFormMorphInfo()]));
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
protected String createForm(String form,String grammaInfo){
|
||||
return form+"|"+grammaInfo;
|
||||
}
|
||||
|
||||
protected int findRuleId(int[] ints) {
|
||||
int low = 0;
|
||||
int high = separators.length - 1;
|
||||
int mid = 0;
|
||||
while (low <= high) {
|
||||
mid = (low + high) >>> 1;
|
||||
int[] midVal = separators[mid];
|
||||
|
||||
int comResult = compareToInts(ints, midVal);
|
||||
if (comResult > 0)
|
||||
low = mid + 1;
|
||||
else if (comResult < 0)
|
||||
high = mid - 1;
|
||||
else
|
||||
break;
|
||||
}
|
||||
if (compareToInts(ints, separators[mid]) >= 0) {
|
||||
return mid;
|
||||
} else {
|
||||
return mid - 1;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
private int compareToInts(int[] i1, int[] i2) {
|
||||
int minLength = Math.min(i1.length, i2.length);
|
||||
for (int i = 0; i < minLength; i++) {
|
||||
int i3 = i1[i] < i2[i] ? -1 : (i1[i] == i2[i] ? 0 : 1);
|
||||
if (i3 != 0) return i3;
|
||||
}
|
||||
return i1.length - i2.length;
|
||||
}
|
||||
|
||||
public void writeToFile(String fileName) throws IOException {
|
||||
OutputStreamWriter writer = new OutputStreamWriter(new FileOutputStream(fileName), "UTF-8");
|
||||
writer.write(separators.length + "\n");
|
||||
for (int[] i : separators) {
|
||||
writer.write(i.length + "\n");
|
||||
for (int j : i) {
|
||||
writer.write(j + "\n");
|
||||
}
|
||||
}
|
||||
for (short i : rulesId) {
|
||||
writer.write(i + "\n");
|
||||
}
|
||||
writer.write(rules.length + "\n");
|
||||
for (Heuristic[] heuristics : rules) {
|
||||
writer.write(heuristics.length + "\n");
|
||||
for (Heuristic heuristic : heuristics) {
|
||||
writer.write(heuristic.toString() + "\n");
|
||||
}
|
||||
}
|
||||
writer.write(grammaInfo.length + "\n");
|
||||
for (String s : grammaInfo) {
|
||||
writer.write(s + "\n");
|
||||
}
|
||||
writer.close();
|
||||
}
|
||||
|
||||
public void readFromFile(String fileName) throws IOException {
|
||||
FileInputStream inputStream = new FileInputStream(fileName);
|
||||
readFromInputStream(inputStream);
|
||||
}
|
||||
|
||||
private void readFromInputStream(InputStream inputStream) throws IOException {
|
||||
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(inputStream, "UTF-8"));
|
||||
String s = bufferedReader.readLine();
|
||||
Integer amount = Integer.valueOf(s);
|
||||
|
||||
readSeparators(bufferedReader, amount);
|
||||
|
||||
readRulesId(bufferedReader, amount);
|
||||
|
||||
readRules(bufferedReader);
|
||||
readGrammaInfo(bufferedReader);
|
||||
bufferedReader.close();
|
||||
}
|
||||
|
||||
private void readGrammaInfo(BufferedReader bufferedReader) throws IOException {
|
||||
String s;
|
||||
Integer amount;
|
||||
s = bufferedReader.readLine();
|
||||
amount = Integer.valueOf(s);
|
||||
grammaInfo = new String[amount];
|
||||
for (int i = 0; i < amount; i++) {
|
||||
grammaInfo[i] = bufferedReader.readLine();
|
||||
}
|
||||
}
|
||||
|
||||
protected void readRules(BufferedReader bufferedReader) throws IOException {
|
||||
String s;
|
||||
Integer amount;
|
||||
s = bufferedReader.readLine();
|
||||
amount = Integer.valueOf(s);
|
||||
rules = new Heuristic[amount][];
|
||||
for (int i = 0; i < amount; i++) {
|
||||
String s1 = bufferedReader.readLine();
|
||||
Integer ruleLenght = Integer.valueOf(s1);
|
||||
rules[i] = new Heuristic[ruleLenght];
|
||||
for (int j = 0; j < ruleLenght; j++) {
|
||||
rules[i][j] = new Heuristic(bufferedReader.readLine());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private void readRulesId(BufferedReader bufferedReader, Integer amount) throws IOException {
|
||||
rulesId = new short[amount];
|
||||
for (int i = 0; i < amount; i++) {
|
||||
String s1 = bufferedReader.readLine();
|
||||
rulesId[i] = Short.valueOf(s1);
|
||||
}
|
||||
}
|
||||
|
||||
private void readSeparators(BufferedReader bufferedReader, Integer amount) throws IOException {
|
||||
HashSet intetger = new HashSet<Integer>();
|
||||
separators = new int[amount][];
|
||||
for (int i = 0; i < amount; i++) {
|
||||
String s1 = bufferedReader.readLine();
|
||||
Integer wordLenght = Integer.valueOf(s1);
|
||||
separators[i] = new int[wordLenght];
|
||||
for (int j = 0; j < wordLenght; j++) {
|
||||
separators[i][j] = Integer.valueOf(bufferedReader.readLine());
|
||||
}
|
||||
intetger.add(separators[i][0]);
|
||||
}
|
||||
}
|
||||
|
||||
protected String revertWord(String s) {
|
||||
String result = "";
|
||||
for (int i = 1; i <= s.length(); i++) {
|
||||
result += s.charAt(s.length() - i);
|
||||
}
|
||||
return result;
|
||||
}
|
||||
}
|
||||
/**
|
||||
* Copyright 2009 Alexander Kuznetsov
|
||||
*
|
||||
* Licensed 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.apache.lucene.morphology;
|
||||
|
||||
import java.util.List;
|
||||
|
||||
|
||||
public interface Morphology {
|
||||
|
||||
List<String> getMorhInfo(String s);
|
||||
|
||||
}
|
||||
|
||||
@ -0,0 +1,210 @@
|
||||
/**
|
||||
* Copyright 2009 Alexander Kuznetsov
|
||||
*
|
||||
* Licensed 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.apache.lucene.morphology;
|
||||
|
||||
|
||||
import java.io.*;
|
||||
import java.util.ArrayList;
|
||||
import java.util.HashSet;
|
||||
import java.util.List;
|
||||
|
||||
|
||||
public class MorphologyImpl implements Morphology {
|
||||
protected int[][] separators;
|
||||
protected short[] rulesId;
|
||||
protected Heuristic[][] rules;
|
||||
protected String[] grammaInfo;
|
||||
protected LetterDecoderEncoder decoderEncoder;
|
||||
|
||||
|
||||
public MorphologyImpl(String fileName, LetterDecoderEncoder decoderEncoder) throws IOException {
|
||||
readFromFile(fileName);
|
||||
this.decoderEncoder = decoderEncoder;
|
||||
}
|
||||
|
||||
public MorphologyImpl(InputStream inputStream, LetterDecoderEncoder decoderEncoder) throws IOException {
|
||||
readFromInputStream(inputStream);
|
||||
this.decoderEncoder = decoderEncoder;
|
||||
}
|
||||
|
||||
public MorphologyImpl(int[][] separators, short[] rulesId, Heuristic[][] rules, String[] grammaInfo) {
|
||||
this.separators = separators;
|
||||
this.rulesId = rulesId;
|
||||
this.rules = rules;
|
||||
this.grammaInfo = grammaInfo;
|
||||
}
|
||||
|
||||
public int[][] getSeparators() {
|
||||
return separators;
|
||||
}
|
||||
|
||||
public short[] getRulesId() {
|
||||
return rulesId;
|
||||
}
|
||||
|
||||
public Heuristic[][] getRules() {
|
||||
return rules;
|
||||
}
|
||||
|
||||
public String[] getGrammaInfo() {
|
||||
return grammaInfo;
|
||||
}
|
||||
|
||||
public List<String> getMorhInfo(String s) {
|
||||
ArrayList<String> result = new ArrayList<String>();
|
||||
int[] ints = decoderEncoder.encodeToArray(revertWord(s));
|
||||
int ruleId = findRuleId(ints);
|
||||
for (Heuristic h : rules[rulesId[ruleId]]) {
|
||||
result.add(h.transofrmWord(s) + "|" + grammaInfo[h.getFormMorphInfo()]);
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
protected int findRuleId(int[] ints) {
|
||||
int low = 0;
|
||||
int high = separators.length - 1;
|
||||
int mid = 0;
|
||||
while (low <= high) {
|
||||
mid = (low + high) >>> 1;
|
||||
int[] midVal = separators[mid];
|
||||
|
||||
int comResult = compareToInts(ints, midVal);
|
||||
if (comResult > 0)
|
||||
low = mid + 1;
|
||||
else if (comResult < 0)
|
||||
high = mid - 1;
|
||||
else
|
||||
break;
|
||||
}
|
||||
if (compareToInts(ints, separators[mid]) >= 0) {
|
||||
return mid;
|
||||
} else {
|
||||
return mid - 1;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
private int compareToInts(int[] i1, int[] i2) {
|
||||
int minLength = Math.min(i1.length, i2.length);
|
||||
for (int i = 0; i < minLength; i++) {
|
||||
int i3 = i1[i] < i2[i] ? -1 : (i1[i] == i2[i] ? 0 : 1);
|
||||
if (i3 != 0) return i3;
|
||||
}
|
||||
return i1.length - i2.length;
|
||||
}
|
||||
|
||||
public void writeToFile(String fileName) throws IOException {
|
||||
OutputStreamWriter writer = new OutputStreamWriter(new FileOutputStream(fileName), "UTF-8");
|
||||
writer.write(separators.length + "\n");
|
||||
for (int[] i : separators) {
|
||||
writer.write(i.length + "\n");
|
||||
for (int j : i) {
|
||||
writer.write(j + "\n");
|
||||
}
|
||||
}
|
||||
for (short i : rulesId) {
|
||||
writer.write(i + "\n");
|
||||
}
|
||||
writer.write(rules.length + "\n");
|
||||
for (Heuristic[] heuristics : rules) {
|
||||
writer.write(heuristics.length + "\n");
|
||||
for (Heuristic heuristic : heuristics) {
|
||||
writer.write(heuristic.toString() + "\n");
|
||||
}
|
||||
}
|
||||
writer.write(grammaInfo.length + "\n");
|
||||
for (String s : grammaInfo) {
|
||||
writer.write(s + "\n");
|
||||
}
|
||||
writer.close();
|
||||
}
|
||||
|
||||
public void readFromFile(String fileName) throws IOException {
|
||||
FileInputStream inputStream = new FileInputStream(fileName);
|
||||
readFromInputStream(inputStream);
|
||||
}
|
||||
|
||||
private void readFromInputStream(InputStream inputStream) throws IOException {
|
||||
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(inputStream, "UTF-8"));
|
||||
String s = bufferedReader.readLine();
|
||||
Integer amount = Integer.valueOf(s);
|
||||
|
||||
readSeparators(bufferedReader, amount);
|
||||
|
||||
readRulesId(bufferedReader, amount);
|
||||
|
||||
readRules(bufferedReader);
|
||||
readGrammaInfo(bufferedReader);
|
||||
bufferedReader.close();
|
||||
}
|
||||
|
||||
private void readGrammaInfo(BufferedReader bufferedReader) throws IOException {
|
||||
String s;
|
||||
Integer amount;
|
||||
s = bufferedReader.readLine();
|
||||
amount = Integer.valueOf(s);
|
||||
grammaInfo = new String[amount];
|
||||
for (int i = 0; i < amount; i++) {
|
||||
grammaInfo[i] = bufferedReader.readLine();
|
||||
}
|
||||
}
|
||||
|
||||
protected void readRules(BufferedReader bufferedReader) throws IOException {
|
||||
String s;
|
||||
Integer amount;
|
||||
s = bufferedReader.readLine();
|
||||
amount = Integer.valueOf(s);
|
||||
rules = new Heuristic[amount][];
|
||||
for (int i = 0; i < amount; i++) {
|
||||
String s1 = bufferedReader.readLine();
|
||||
Integer ruleLenght = Integer.valueOf(s1);
|
||||
rules[i] = new Heuristic[ruleLenght];
|
||||
for (int j = 0; j < ruleLenght; j++) {
|
||||
rules[i][j] = new Heuristic(bufferedReader.readLine());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private void readRulesId(BufferedReader bufferedReader, Integer amount) throws IOException {
|
||||
rulesId = new short[amount];
|
||||
for (int i = 0; i < amount; i++) {
|
||||
String s1 = bufferedReader.readLine();
|
||||
rulesId[i] = Short.valueOf(s1);
|
||||
}
|
||||
}
|
||||
|
||||
private void readSeparators(BufferedReader bufferedReader, Integer amount) throws IOException {
|
||||
HashSet intetger = new HashSet<Integer>();
|
||||
separators = new int[amount][];
|
||||
for (int i = 0; i < amount; i++) {
|
||||
String s1 = bufferedReader.readLine();
|
||||
Integer wordLenght = Integer.valueOf(s1);
|
||||
separators[i] = new int[wordLenght];
|
||||
for (int j = 0; j < wordLenght; j++) {
|
||||
separators[i][j] = Integer.valueOf(bufferedReader.readLine());
|
||||
}
|
||||
intetger.add(separators[i][0]);
|
||||
}
|
||||
}
|
||||
|
||||
protected String revertWord(String s) {
|
||||
String result = "";
|
||||
for (int i = 1; i <= s.length(); i++) {
|
||||
result += s.charAt(s.length() - i);
|
||||
}
|
||||
return result;
|
||||
}
|
||||
}
|
||||
@ -1,96 +0,0 @@
|
||||
/**
|
||||
* Copyright 2009 Alexander Kuznetsov
|
||||
*
|
||||
* Licensed 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.apache.lucene.morphology;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.io.InputStream;
|
||||
import java.io.BufferedReader;
|
||||
import java.io.InputStreamReader;
|
||||
import java.util.*;
|
||||
|
||||
|
||||
public class MorphologyWithPrefix extends Morphology {
|
||||
private Map<String, PrefixRule> prefixRuleMap = new HashMap<String, PrefixRule>();
|
||||
|
||||
public MorphologyWithPrefix(String fileName, LetterDecoderEncoder decoderEncoder) throws IOException {
|
||||
super(fileName, decoderEncoder);
|
||||
}
|
||||
|
||||
public MorphologyWithPrefix(InputStream morphFormInputStream, LetterDecoderEncoder decoderEncoder) throws IOException {
|
||||
super(morphFormInputStream, decoderEncoder);
|
||||
}
|
||||
|
||||
public MorphologyWithPrefix(InputStream morphFormInputStream,InputStream prefixesInputStream, LetterDecoderEncoder decoderEncoder) throws IOException {
|
||||
super(morphFormInputStream, decoderEncoder);
|
||||
readPrefixes(prefixesInputStream);
|
||||
}
|
||||
|
||||
private void readPrefixes(InputStream inputStream) throws IOException {
|
||||
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(inputStream, "UTF-8"));
|
||||
Integer prefixAmount = Integer.parseInt(bufferedReader.readLine());
|
||||
for(int i = 0; i < prefixAmount;i++){
|
||||
PrefixRule prefixRule = readPrefix(bufferedReader);
|
||||
prefixRuleMap.put(prefixRule.getHashString(),prefixRule);
|
||||
}
|
||||
bufferedReader.close();
|
||||
}
|
||||
|
||||
private PrefixRule readPrefix(BufferedReader bufferedReader) throws IOException {
|
||||
PrefixRule prefixRule = new PrefixRule();
|
||||
String s = bufferedReader.readLine();
|
||||
prefixRule.setPrefix(s);
|
||||
s = bufferedReader.readLine();
|
||||
prefixRule.setLastLetter(s.charAt(0));
|
||||
HashSet<Short> morph = new HashSet<Short>();
|
||||
int formAmount = Integer.valueOf(bufferedReader.readLine());
|
||||
for(int i = 0; i < formAmount; i++){
|
||||
morph.add(Short.valueOf(bufferedReader.readLine()));
|
||||
}
|
||||
prefixRule.setForms(morph);
|
||||
return prefixRule;
|
||||
}
|
||||
|
||||
public MorphologyWithPrefix(int[][] separators, short[] rulesId, Heuristic[][] rules, String[] grammaInfo) {
|
||||
super(separators, rulesId, rules, grammaInfo);
|
||||
}
|
||||
|
||||
@Override
|
||||
public List<String> getMorhInfo(String s) {
|
||||
if (prefixRuleMap.size() == 0 || s.length() < 4) {
|
||||
return super.getMorhInfo(s);
|
||||
}
|
||||
String ruleIndex = "" + s.charAt(0) + s.charAt(s.length() - 1);
|
||||
PrefixRule prefixRule = prefixRuleMap.get(ruleIndex);
|
||||
if (prefixRule == null) {
|
||||
return super.getMorhInfo(s);
|
||||
}
|
||||
if (!s.startsWith(prefixRule.getPrefix())) {
|
||||
return super.getMorhInfo(s);
|
||||
}
|
||||
String sWithoutPrefix = s.substring(prefixRule.getPrefix().length());
|
||||
|
||||
int[] ints = decoderEncoder.encodeToArray(revertWord(sWithoutPrefix));
|
||||
int ruleId = findRuleId(ints);
|
||||
ArrayList<String> result = new ArrayList<String>();
|
||||
for (Heuristic h : rules[rulesId[ruleId]]) {
|
||||
//String morphInfo = grammaInfo[];
|
||||
if(prefixRule.getForms().contains(h.getFormMorphInfo())){
|
||||
result.add(createForm(h.transofrmWord(sWithoutPrefix),"pr"));
|
||||
}
|
||||
}
|
||||
return result.size() > 0 ? result : super.getMorhInfo(s);
|
||||
}
|
||||
}
|
||||
@ -1,76 +0,0 @@
|
||||
/**
|
||||
* Copyright 2009 Alexander Kuznetsov
|
||||
*
|
||||
* Licensed 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.apache.lucene.morphology;
|
||||
|
||||
import java.io.Serializable;
|
||||
import java.util.HashSet;
|
||||
|
||||
|
||||
public class PrefixRule implements Serializable {
|
||||
private Character lastLetter;
|
||||
private String prefix;
|
||||
private HashSet<Short> forms;
|
||||
|
||||
public Character getLastLetter() {
|
||||
return lastLetter;
|
||||
}
|
||||
|
||||
public void setLastLetter(Character lastLetter) {
|
||||
this.lastLetter = lastLetter;
|
||||
}
|
||||
|
||||
public String getPrefix() {
|
||||
return prefix;
|
||||
}
|
||||
|
||||
public void setPrefix(String prefix) {
|
||||
this.prefix = prefix;
|
||||
}
|
||||
|
||||
public HashSet<Short> getForms() {
|
||||
return forms;
|
||||
}
|
||||
|
||||
public void setForms(HashSet<Short> forms) {
|
||||
this.forms = forms;
|
||||
}
|
||||
|
||||
public String getHashString() {
|
||||
return "" + prefix.charAt(0) + lastLetter;
|
||||
}
|
||||
|
||||
@Override
|
||||
public boolean equals(Object o) {
|
||||
if (this == o) return true;
|
||||
if (o == null || getClass() != o.getClass()) return false;
|
||||
|
||||
PrefixRule that = (PrefixRule) o;
|
||||
|
||||
if (forms != null ? !forms.equals(that.forms) : that.forms != null) return false;
|
||||
if (lastLetter != null ? !lastLetter.equals(that.lastLetter) : that.lastLetter != null) return false;
|
||||
if (prefix != null ? !prefix.equals(that.prefix) : that.prefix != null) return false;
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
@Override
|
||||
public int hashCode() {
|
||||
int result = lastLetter != null ? lastLetter.hashCode() : 0;
|
||||
result = 31 * result + (prefix != null ? prefix.hashCode() : 0);
|
||||
result = 31 * result + (forms != null ? forms.hashCode() : 0);
|
||||
return result;
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user