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
russian/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>russian</artifactId>
<name>russian</name>
<version>1.5</version>
@ -23,7 +22,7 @@
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.13.1</version>
<version>${junit.version}</version>
<scope>test</scope>
</dependency>

24
russian/src/main/java/org/apache/lucene/morphology/russian/RussianLetterDecoderEncoder.java
View File

@ -20,7 +20,6 @@ import org.apache.lucene.morphology.LetterDecoderEncoder;
import org.apache.lucene.morphology.SuffixToLongException;
import org.apache.lucene.morphology.WrongCharaterException;
import java.util.ArrayList;
import java.util.LinkedList;
/**
@ -42,7 +41,7 @@ public class RussianLetterDecoderEncoder implements LetterDecoderEncoder {
throw new SuffixToLongException("Suffix length should not be greater then " + WORD_PART_LENGHT + " " + string);
int result = 0;
for (int i = 0; i < string.length(); i++) {
int c = 0 + string.charAt(i) - RUSSIAN_SMALL_LETTER_OFFSET;
int c = string.charAt(i) - RUSSIAN_SMALL_LETTER_OFFSET;
if (c == 45 - RUSSIAN_SMALL_LETTER_OFFSET) {
c = DASH_CODE;
}
@ -58,7 +57,7 @@ public class RussianLetterDecoderEncoder implements LetterDecoderEncoder {
}
public int[] encodeToArray(String s) {
LinkedList<Integer> integers = new LinkedList<Integer>();
LinkedList<Integer> integers = new LinkedList<>();
while (s.length() > WORD_PART_LENGHT) {
integers.add(encode(s.substring(0, WORD_PART_LENGHT)));
s = s.substring(WORD_PART_LENGHT);
@ -74,16 +73,16 @@ public class RussianLetterDecoderEncoder 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 > 33) {
int c = suffixN % 34 + RUSSIAN_SMALL_LETTER_OFFSET;
if (c == RUSSIAN_SMALL_LETTER_OFFSET) {
@ -91,21 +90,20 @@ public class RussianLetterDecoderEncoder implements LetterDecoderEncoder {
continue;
}
if (c == DASH_CODE + RUSSIAN_SMALL_LETTER_OFFSET) c = DASH_CHAR;
result = (char) c + result;
result.insert(0, (char) c);
suffixN /= 34;
}
long c = suffixN + RUSSIAN_SMALL_LETTER_OFFSET;
if (c == DASH_CODE + RUSSIAN_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 -= RUSSIAN_SMALL_LETTER_OFFSET;
if (code > 0 && code < 33) return true;
return false;
return code > 0 && code < 33;
}
public boolean checkString(String word) {

15
russian/src/test/java/org/apache/lucene/morphology/russian/RussianLetterDecoderEncoderTest.java
View File

@ -17,6 +17,7 @@ package org.apache.lucene.morphology.russian;
import org.apache.lucene.morphology.SuffixToLongException;
import org.apache.lucene.morphology.WrongCharaterException;
import org.hamcrest.MatcherAssert;
import org.junit.Before;
import org.junit.Test;
@ -24,9 +25,9 @@ import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.nio.charset.StandardCharsets;
import static org.hamcrest.core.IsEqual.equalTo;
import static org.junit.Assert.assertThat;
public class RussianLetterDecoderEncoderTest {
private RussianLetterDecoderEncoder decoderEncoder;
@ -40,12 +41,12 @@ public class RussianLetterDecoderEncoderTest {
@Test
public void testShouldPreserverStringComporision() throws IOException {
InputStream stream = this.getClass().getResourceAsStream("/org/apache/lucene/morphology/russian/decoder-test-monotonic.txt");
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(stream, "UTF-8"));
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(stream, StandardCharsets.UTF_8));
String s = bufferedReader.readLine();
while (s != null) {
String[] qa = s.trim().split(" ");
if (qa[0].length() <= RussianLetterDecoderEncoder.WORD_PART_LENGHT && qa[1].length() <= RussianLetterDecoderEncoder.WORD_PART_LENGHT) {
assertThat(decoderEncoder.encode(qa[1]) > decoderEncoder.encode(qa[0]), equalTo(true));
MatcherAssert.assertThat(decoderEncoder.encode(qa[1]) > decoderEncoder.encode(qa[0]), equalTo(true));
}
s = bufferedReader.readLine();
}
@ -55,13 +56,13 @@ public class RussianLetterDecoderEncoderTest {
@Test
public void testShouldCorrectDecodeEncode() throws IOException {
InputStream stream = this.getClass().getResourceAsStream("/org/apache/lucene/morphology/russian/decoder-test-data.txt");
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(stream, "UTF-8"));
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(stream, StandardCharsets.UTF_8));
String s = bufferedReader.readLine();
while (s != null) {
String[] qa = s.trim().split(" ");
if (qa[0].length() <= RussianLetterDecoderEncoder.WORD_PART_LENGHT) {
Integer encodedSuffix = decoderEncoder.encode(qa[0]);
assertThat(decoderEncoder.decode(encodedSuffix), equalTo(qa[1]));
MatcherAssert.assertThat(decoderEncoder.decode(encodedSuffix), equalTo(qa[1]));
}
s = bufferedReader.readLine();
}
@ -70,12 +71,12 @@ public class RussianLetterDecoderEncoderTest {
@Test
public void testShouldCorrectDecodeEncodeStringToArray() throws IOException {
InputStream stream = this.getClass().getResourceAsStream("/org/apache/lucene/morphology/russian/decoder-test-data-for-array.txt");
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(stream, "UTF-8"));
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(stream, StandardCharsets.UTF_8));
String s = bufferedReader.readLine();
while (s != null) {
String[] qa = s.trim().split(" ");
int[] ecodedSuffix = decoderEncoder.encodeToArray(qa[0]);
assertThat(decoderEncoder.decodeArray(ecodedSuffix), equalTo(qa[1]));
MatcherAssert.assertThat(decoderEncoder.decodeArray(ecodedSuffix), equalTo(qa[1]));
s = bufferedReader.readLine();
}
}