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

update to jdk11, fix migration issues, some typos, deprecated apis, bump up Lucene to 8.11

Browse Source
This commit is contained in:
Konstantin Perikov
2021-12-10 18:15:47 +00:00
parent b2fec940d0
commit 96900e334e
32 changed files with 184 additions and 198 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
english/pom.xml
View File

@ -6,7 +6,6 @@
<version>1.5</version>
</parent>
<modelVersion>4.0.0</modelVersion>
<groupId>org.apache.lucene.morphology</groupId>
<artifactId>english</artifactId>
<name>english</name>
<version>1.5</version>
@ -20,4 +19,4 @@
</dependency>
</dependencies>
</project>
</project>

23
english/src/main/java/org/apache/lucene/morphology/english/EnglishLetterDecoderEncoder.java
View File

@ -32,7 +32,7 @@ public class EnglishLetterDecoderEncoder implements LetterDecoderEncoder {
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;
int c = string.charAt(i) - ENGLISH_SMALL_LETTER_OFFSET;
if (c == 45 - ENGLISH_SMALL_LETTER_OFFSET) {
c = DASH_CODE;
}
@ -48,7 +48,7 @@ public class EnglishLetterDecoderEncoder implements LetterDecoderEncoder {
public int[] encodeToArray(String s) {
ArrayList<Integer> integers = new ArrayList<Integer>();
ArrayList<Integer> integers = new ArrayList<>();
while (s.length() > 6) {
integers.add(encode(s.substring(0, 6)));
s = s.substring(6);
@ -64,16 +64,16 @@ public class EnglishLetterDecoderEncoder implements LetterDecoderEncoder {
}
public String decodeArray(int[] array) {
String result = "";
StringBuilder result = new StringBuilder();
for (int i : array) {
result += decode(i);
result.append(decode(i));
}
return result;
return result.toString();
}
public String decode(Integer suffixN) {
String result = "";
StringBuilder result = new StringBuilder();
while (suffixN > 27) {
int c = suffixN % 28 + ENGLISH_SMALL_LETTER_OFFSET;
if (c == ENGLISH_SMALL_LETTER_OFFSET) {
@ -81,21 +81,20 @@ public class EnglishLetterDecoderEncoder implements LetterDecoderEncoder {
continue;
}
if (c == DASH_CODE + ENGLISH_SMALL_LETTER_OFFSET) c = DASH_CHAR;
result = (char) c + result;
result.insert(0, (char) c);
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;
result.insert(0, (char) c);
return result.toString();
}
public boolean checkCharacter(char c) {
int code = 0 + c;
int code = c;
if (code == 45) return true;
code -= ENGLISH_SMALL_LETTER_OFFSET;
if (code > 0 && code < 27) return true;
return false;
return code > 0 && code < 27;
}

13
english/src/test/java/org/apache/lucene/morphology/english/EnglishLetterDecoderEncoderTest.java
View File

@ -16,7 +16,8 @@
package org.apache.lucene.morphology.english;
import static org.hamcrest.core.IsEqual.equalTo;
import static org.junit.Assert.assertThat;
import org.hamcrest.MatcherAssert;
import org.junit.Before;
@ -30,11 +31,11 @@ public class EnglishLetterDecoderEncoderTest {
@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"));
MatcherAssert.assertThat(decoderEncoder.decodeArray(decoderEncoder.encodeToArray("abcdefghijklmnopqrstuvwxyz")), equalTo("abcdefghijklmnopqrstuvwxyz"));
MatcherAssert.assertThat(decoderEncoder.decodeArray(decoderEncoder.encodeToArray("xyz")), equalTo("xyz"));
MatcherAssert.assertThat(decoderEncoder.decodeArray(decoderEncoder.encodeToArray("ytrrty")), equalTo("ytrrty"));
MatcherAssert.assertThat(decoderEncoder.decodeArray(decoderEncoder.encodeToArray("ytrrtyz")), equalTo("ytrrtyz"));
MatcherAssert.assertThat(decoderEncoder.decodeArray(decoderEncoder.encodeToArray("ytrrtyzqwqwe")), equalTo("ytrrtyzqwqwe"));
}
}

40
english/src/test/java/org/apache/lucene/morphology/english/stemmer/EnglishStemmerTest.java
View File

@ -16,9 +16,9 @@
package org.apache.lucene.morphology.english.stemmer;
import org.apache.lucene.morphology.english.EnglishLuceneMorphology;
import org.hamcrest.MatcherAssert;
import org.junit.Test;
import static org.hamcrest.core.IsEqual.equalTo;
import static org.junit.Assert.assertThat;
public class EnglishStemmerTest {
@ -26,24 +26,24 @@ public class EnglishStemmerTest {
public void testGetStemmedWord() throws Exception {
EnglishLuceneMorphology englishLuceneMorphology = new EnglishLuceneMorphology();
EnglishStemmer englishStemmer = new EnglishStemmer(englishLuceneMorphology);
assertThat(englishStemmer.getStemmedWord("running"),equalTo("run"));
assertThat(englishStemmer.getStemmedWord("run"),equalTo("run"));
assertThat(englishStemmer.getStemmedWord("killed"),equalTo("kill"));
assertThat(englishStemmer.getStemmedWord("kill"),equalTo("kill"));
assertThat(englishStemmer.getStemmedWord("networking"),equalTo("network"));
assertThat(englishStemmer.getStemmedWord("network"),equalTo("network"));
assertThat(englishStemmer.getStemmedWord("statistics"),equalTo("statistic"));
assertThat(englishStemmer.getStemmedWord("statistic"),equalTo("statistic"));
assertThat(englishStemmer.getStemmedWord("stats"),equalTo("stat"));
assertThat(englishStemmer.getStemmedWord("stat"),equalTo("stat"));
assertThat(englishStemmer.getStemmedWord("countries"),equalTo("country"));
assertThat(englishStemmer.getStemmedWord("country"),equalTo("country"));
assertThat(englishStemmer.getStemmedWord("delete"),equalTo("delete"));
assertThat(englishStemmer.getStemmedWord("ended"),equalTo("end"));
assertThat(englishStemmer.getStemmedWord("end"),equalTo("end"));
assertThat(englishStemmer.getStemmedWord("ends"),equalTo("end"));
assertThat(englishStemmer.getStemmedWord("given"),equalTo("give"));
assertThat(englishStemmer.getStemmedWord("give"),equalTo("give"));
assertThat(englishStemmer.getStemmedWord("log4j"),equalTo("log4j"));
MatcherAssert.assertThat(englishStemmer.getStemmedWord("running"),equalTo("run"));
MatcherAssert.assertThat(englishStemmer.getStemmedWord("run"),equalTo("run"));
MatcherAssert.assertThat(englishStemmer.getStemmedWord("killed"),equalTo("kill"));
MatcherAssert.assertThat(englishStemmer.getStemmedWord("kill"),equalTo("kill"));
MatcherAssert.assertThat(englishStemmer.getStemmedWord("networking"),equalTo("network"));
MatcherAssert.assertThat(englishStemmer.getStemmedWord("network"),equalTo("network"));
MatcherAssert.assertThat(englishStemmer.getStemmedWord("statistics"),equalTo("statistic"));
MatcherAssert.assertThat(englishStemmer.getStemmedWord("statistic"),equalTo("statistic"));
MatcherAssert.assertThat(englishStemmer.getStemmedWord("stats"),equalTo("stat"));
MatcherAssert.assertThat(englishStemmer.getStemmedWord("stat"),equalTo("stat"));
MatcherAssert.assertThat(englishStemmer.getStemmedWord("countries"),equalTo("country"));
MatcherAssert.assertThat(englishStemmer.getStemmedWord("country"),equalTo("country"));
MatcherAssert.assertThat(englishStemmer.getStemmedWord("delete"),equalTo("delete"));
MatcherAssert.assertThat(englishStemmer.getStemmedWord("ended"),equalTo("end"));
MatcherAssert.assertThat(englishStemmer.getStemmedWord("end"),equalTo("end"));
MatcherAssert.assertThat(englishStemmer.getStemmedWord("ends"),equalTo("end"));
MatcherAssert.assertThat(englishStemmer.getStemmedWord("given"),equalTo("give"));
MatcherAssert.assertThat(englishStemmer.getStemmedWord("give"),equalTo("give"));
MatcherAssert.assertThat(englishStemmer.getStemmedWord("log4j"),equalTo("log4j"));
}
}