Skip to content

armgit / solr

Public Imported from GitHub
0

Apache Solr open-source search software

LUCENE-9765: Hunspell: rename SpellChecker to Hunspell, fix test name, update javadoc and CHANGES.txt (#2354)

Peter Gromov02ea7a113928
diff --git a/lucene/CHANGES.txt b/lucene/CHANGES.txt
index f833be3206b..337f3769fdc 100644
--- a/lucene/CHANGES.txt
+++ b/lucene/CHANGES.txt
@@ -89,8 +89,8 @@ API Changes
Improvements
-* LUCENE-9687: Hunspell support improvements: add SpellChecker API, support default encoding and
- BREAK/FORBIDDENWORD/COMPOUNDRULE affix rules, improve stemming of all-caps words (Peter Gromov)
+* LUCENE-9687: Hunspell support improvements: add API for spell-checking and suggestions, support compound words,
+ fix various behavior differences between Java and C++ implementations, improve performance (Peter Gromov, Dawid Weiss)
* LUCENE-9633: Improve match highlighter behavior for degenerate intervals (on non-existing positions).
(Dawid Weiss)
diff --git a/lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/GeneratingSuggester.java b/lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/GeneratingSuggester.java
index 54a42819fbd..9d9c582b984 100644
--- a/lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/GeneratingSuggester.java
+++ b/lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/GeneratingSuggester.java
@@ -43,9 +43,9 @@ class GeneratingSuggester {
private static final int MAX_WORDS = 100;
private static final int MAX_GUESSES = 200;
private final Dictionary dictionary;
- private final SpellChecker speller;
+ private final Hunspell speller;
- GeneratingSuggester(SpellChecker speller) {
+ GeneratingSuggester(Hunspell speller) {
this.dictionary = speller.dictionary;
this.speller = speller;
}
diff --git a/lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/SpellChecker.java b/lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/Hunspell.java
similarity index 95%
rename from lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/SpellChecker.java
rename to lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/Hunspell.java
index a24f49b2fc1..db0e3e4e837 100644
--- a/lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/SpellChecker.java
+++ b/lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/Hunspell.java
@@ -34,15 +34,25 @@ import org.apache.lucene.util.CharsRef;
import org.apache.lucene.util.IntsRef;
/**
- * A spell checker based on Hunspell dictionaries. The objects of this class are not thread-safe
- * (but a single underlying Dictionary can be shared by multiple spell-checkers in different
- * threads). Not all Hunspell features are supported yet.
+ * A spell checker based on Hunspell dictionaries. This class can be used in place of native
+ * Hunspell for many languages for spell-checking and suggesting purposes. Note that not all
+ * languages are supported yet. For example:
+ *
+ * <ul>
+ * <li>Hungarian (as it doesn't only rely on dictionaries, but has some logic directly in the
+ * source code
+ * <li>Languages with Unicode characters outside of the Basic Multilingual Plane
+ * <li>PHONE affix file option for suggestions
+ * </ul>
+ *
+ * <p>The objects of this class are not thread-safe (but a single underlying Dictionary can be
+ * shared by multiple spell-checkers in different threads).
*/
-public class SpellChecker {
+public class Hunspell {
final Dictionary dictionary;
final Stemmer stemmer;
- public SpellChecker(Dictionary dictionary) {
+ public Hunspell(Dictionary dictionary) {
this.dictionary = dictionary;
stemmer = new Stemmer(dictionary);
}
@@ -448,8 +458,8 @@ public class SpellChecker {
}
}
- SpellChecker suggestionSpeller =
- new SpellChecker(dictionary) {
+ Hunspell suggestionSpeller =
+ new Hunspell(dictionary) {
@Override
boolean acceptsStem(int formID) {
return !dictionary.hasFlag(formID, dictionary.noSuggest)
diff --git a/lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/ModifyingSuggester.java b/lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/ModifyingSuggester.java
index 50c5dceadc0..5017ff28a46 100644
--- a/lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/ModifyingSuggester.java
+++ b/lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/ModifyingSuggester.java
@@ -28,10 +28,10 @@ class ModifyingSuggester {
private static final int MAX_CHAR_DISTANCE = 4;
private final LinkedHashSet<String> result = new LinkedHashSet<>();
private final char[] tryChars;
- private final SpellChecker speller;
+ private final Hunspell speller;
boolean hasGoodSuggestions;
- ModifyingSuggester(SpellChecker speller) {
+ ModifyingSuggester(Hunspell speller) {
this.speller = speller;
tryChars = speller.dictionary.tryChars.toCharArray();
}
diff --git a/lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/package-info.java b/lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/package-info.java
index 94870a3a5f6..4d6cd0427aa 100644
--- a/lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/package-info.java
+++ b/lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/package-info.java
@@ -17,13 +17,11 @@
/**
* A Java implementation of <a href="http://hunspell.github.io/">Hunspell</a> stemming and
- * spell-checking algorithms, and a stemming TokenFilter based on it.
+ * spell-checking algorithms ({@link org.apache.lucene.analysis.hunspell.Hunspell}), and a stemming
+ * TokenFilter ({@link org.apache.lucene.analysis.hunspell.HunspellStemFilter}) based on it.
*
* <p>For dictionaries, see e.g. <a href="https://github.com/LibreOffice/dictionaries">LibreOffice
* repository</a> or <a href="https://github.com/wooorm/dictionaries">Titus Wormer's collection
* (UTF)</a>
- *
- * @see org.apache.lucene.analysis.hunspell.HunspellStemFilter
- * @see org.apache.lucene.analysis.hunspell.SpellChecker
*/
package org.apache.lucene.analysis.hunspell;
diff --git a/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/TestHunspellRepositoryTestCases.java b/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/TestHunspellRepositoryTestCases.java
index 6bf0297b67b..c7a67762a75 100644
--- a/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/TestHunspellRepositoryTestCases.java
+++ b/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/TestHunspellRepositoryTestCases.java
@@ -32,7 +32,7 @@ import org.junit.runner.RunWith;
import org.junit.runners.Parameterized;
/**
- * Same as {@link SpellCheckerTest}, but checks all Hunspell's test data. The path to the checked
+ * Same as {@link TestSpellChecking}, but checks all Hunspell's test data. The path to the checked
* out Hunspell repository should be in {@code hunspell.repo.path} system property.
*/
@RunWith(Parameterized.class)
@@ -78,7 +78,7 @@ public class TestHunspellRepositoryTestCases {
@Test
public void test() throws Throwable {
- ThrowingRunnable test = () -> SpellCheckerTest.checkSpellCheckerExpectations(pathPrefix);
+ ThrowingRunnable test = () -> TestSpellChecking.checkSpellCheckerExpectations(pathPrefix);
if (EXPECTED_FAILURES.contains(testName)) {
Assert.assertThrows(Throwable.class, test);
} else {
diff --git a/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/TestPerformance.java b/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/TestPerformance.java
index f859262bd50..8ae56420cf5 100644
--- a/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/TestPerformance.java
+++ b/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/TestPerformance.java
@@ -76,7 +76,7 @@ public class TestPerformance extends LuceneTestCase {
List<String> words = loadWords(code, wordCount, dictionary);
Stemmer stemmer = new Stemmer(dictionary);
- SpellChecker speller = new SpellChecker(dictionary);
+ Hunspell speller = new Hunspell(dictionary);
measure(
"Stemming " + code,
blackHole -> {
diff --git a/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/SpellCheckerTest.java b/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/TestSpellChecking.java
similarity index 98%
rename from lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/SpellCheckerTest.java
rename to lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/TestSpellChecking.java
index 8b75c018863..57adce60605 100644
--- a/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/SpellCheckerTest.java
+++ b/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/TestSpellChecking.java
@@ -26,7 +26,7 @@ import java.util.stream.Collectors;
import org.apache.lucene.store.ByteBuffersDirectory;
import org.apache.lucene.util.IOUtils;
-public class SpellCheckerTest extends StemmerTestBase {
+public class TestSpellChecking extends StemmerTestBase {
public void testBase() throws Exception {
doTest("base");
@@ -221,11 +221,11 @@ public class SpellCheckerTest extends StemmerTestBase {
InputStream affixStream = Files.newInputStream(Path.of(basePath.toString() + ".aff"));
InputStream dictStream = Files.newInputStream(Path.of(basePath.toString() + ".dic"));
- SpellChecker speller;
+ Hunspell speller;
try {
Dictionary dictionary =
new Dictionary(new ByteBuffersDirectory(), "dictionary", affixStream, dictStream);
- speller = new SpellChecker(dictionary);
+ speller = new Hunspell(dictionary);
} finally {
IOUtils.closeWhileHandlingException(affixStream);
IOUtils.closeWhileHandlingException(dictStream);