edkuksa/russianmorphology
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

adding english version

Browse Source 
git-svn-id: https://russianmorphology.googlecode.com/svn/trunk@57 d817d54c-26ab-11de-abc9-2f7d1455ff7a
This commit is contained in:
alexander.a.kuznetsov
2009-10-15 18:19:31 +00:00
parent 1b8ee03cc6
commit a1e39d750f
19 changed files with 105555 additions and 71 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
english/pom.xml Normal file
View File

@ -0,0 +1,29 @@
<?xml version="1.0"?>
<project>
<parent>
<artifactId>morpholgy</artifactId>
<groupId>org.apache.lucene.morpholgy</groupId>
<version>0.7-SNAPSHOT</version>
</parent>
<modelVersion>4.0.0</modelVersion>
<groupId>org.apache.lucene.morpholgy</groupId>
<artifactId>english</artifactId>
<name>english</name>
<version>0.7-SNAPSHOT</version>
<url>http://maven.apache.org</url>
<dependencies>
<dependency>
<groupId>org.apache.lucene.morpholgy</groupId>
<artifactId>morph</artifactId>
<version>0.7-SNAPSHOT</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.4</version>
<scope>test</scope>
</dependency>
</dependencies>
</project>

116
english/src/main/java/org/apache/lucene/morpholgy/english/EnglishLetterDecoderEncoder.java Normal file
View File

@ -0,0 +1,116 @@
/**
* 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.morpholgy.english;
import org.apache.lucene.morphology.LetterDecoderEncoder;
import org.apache.lucene.morphology.SuffixToLongException;
import org.apache.lucene.morphology.WrongCharaterException;
import java.util.ArrayList;
//todo extract supper class for common method with russian letter decoder
public class EnglishLetterDecoderEncoder implements LetterDecoderEncoder {
public static final int ENGLISH_SMALL_LETTER_OFFSET = 96;
static public int SUFFIX_LENGTH = 6;
public static final int DASH_CHAR = 45;
public static final int DASH_CODE = 27;
public Integer encode(String string) {
if (string.length() > 6) throw new SuffixToLongException("Suffix length should not be greater then " + 12);
int result = 0;
for (int i = 0; i < string.length(); i++) {
int c = 0 + string.charAt(i) - ENGLISH_SMALL_LETTER_OFFSET;
if (c == 45 - ENGLISH_SMALL_LETTER_OFFSET) {
c = DASH_CODE;
}
if (c < 0 || c > 27)
throw new WrongCharaterException("Symblo " + string.charAt(i) + " is not small cirillic letter");
result = result * 28 + c;
}
for (int i = string.length(); i < 6; i++) {
result *= 28;
}
return result;
}
public int[] encodeToArray(String s) {
ArrayList<Integer> integers = new ArrayList<Integer>();
while (s.length() > 6) {
integers.add(encode(s.substring(0, 6)));
s = s.substring(6);
}
integers.add(encode(s));
int[] ints = new int[integers.size()];
int pos = 0;
for (Integer i : integers) {
ints[pos] = i;
pos++;
}
return ints;
}
public String decodeArray(int[] array) {
String result = "";
for (int i : array) {
result += decode(i);
}
return result;
}
public String decode(Integer suffixN) {
String result = "";
while (suffixN > 27) {
int c = suffixN % 28 + ENGLISH_SMALL_LETTER_OFFSET;
if (c == ENGLISH_SMALL_LETTER_OFFSET) {
suffixN /= 28;
continue;
}
if (c == DASH_CODE + ENGLISH_SMALL_LETTER_OFFSET) c = DASH_CHAR;
result = (char) c + result;
suffixN /= 28;
}
long c = suffixN + ENGLISH_SMALL_LETTER_OFFSET;
if (c == DASH_CODE + ENGLISH_SMALL_LETTER_OFFSET) c = DASH_CHAR;
result = (char) c + result;
return result;
}
public boolean checkCharacter(char c) {
int code = 0 + c;
if (code == 45) return true;
code -= ENGLISH_SMALL_LETTER_OFFSET;
if (code > 0 && code < 27) return true;
return false;
}
public boolean checkString(String word) {
for (int i = 0; i < word.length(); i++) {
if (!checkCharacter(word.charAt(i))) {
return false;
}
}
return true;
}
public String cleanString(String s) {
return s;
}
}

40
english/src/test/java/org/apache/lucene/morpholgy/english/EnglishLetterDecoderEncoderTest.java Normal file
View File

@ -0,0 +1,40 @@
/**
* 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.morpholgy.english;
import static org.hamcrest.core.IsEqual.equalTo;
import static org.junit.Assert.assertThat;
import org.junit.Before;
public class EnglishLetterDecoderEncoderTest {
private EnglishLetterDecoderEncoder decoderEncoder;
@Before
public void setUp() {
decoderEncoder = new EnglishLetterDecoderEncoder();
}
@org.junit.Test
public void testDecodeEncodeToArray() {
assertThat(decoderEncoder.decodeArray(decoderEncoder.encodeToArray("abcdefghijklmnopqrstuvwxyz")), equalTo("abcdefghijklmnopqrstuvwxyz"));
assertThat(decoderEncoder.decodeArray(decoderEncoder.encodeToArray("xyz")), equalTo("xyz"));
assertThat(decoderEncoder.decodeArray(decoderEncoder.encodeToArray("ytrrty")), equalTo("ytrrty"));
assertThat(decoderEncoder.decodeArray(decoderEncoder.encodeToArray("ytrrtyz")), equalTo("ytrrtyz"));
assertThat(decoderEncoder.decodeArray(decoderEncoder.encodeToArray("ytrrtyzqwqwe")), equalTo("ytrrtyzqwqwe"));
}
}

38
english/src/test/java/org/apache/lucene/morpholgy/english/RussianLuceneMorphTest.java Normal file
View File

@ -0,0 +1,38 @@
/**
* 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.morpholgy.english;
import org.apache.lucene.morphology.LuceneMorph;
import org.junit.Before;
import org.junit.Test;
import java.io.IOException;
public class RussianLuceneMorphTest {
private LuceneMorph luceneMorph;
@Before
public void setUp() throws IOException {
luceneMorph = new LuceneMorph(this.getClass().getResourceAsStream("/org/apache/lucene/morphology/english/morph.info"), new EnglishLetterDecoderEncoder());
}
@Test
public void shoudGetCorrentMorphInfo() throws IOException {
System.out.println(luceneMorph.getMorhInfo("purchases"));
System.out.println(luceneMorph.getMorhInfo("existing"));
System.out.println(luceneMorph.getMorhInfo("was"));
}
}