Created
December 21, 2022 22:20
-
-
Save spinscale/c38e2158267f1e0a272cf5b0b75510ae to your computer and use it in GitHub Desktop.
Lucene Suggestions using phonetic algorithms
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package de.spinscale.prt; | |
import org.apache.lucene.analysis.custom.CustomAnalyzer; | |
import org.apache.lucene.analysis.phonetic.PhoneticFilterFactory; | |
import org.apache.lucene.search.suggest.FileDictionary; | |
import org.apache.lucene.search.suggest.Lookup; | |
import org.apache.lucene.search.suggest.analyzing.AnalyzingSuggester; | |
import org.apache.lucene.store.Directory; | |
import org.apache.lucene.store.NIOFSDirectory; | |
import org.junit.jupiter.api.Test; | |
import java.io.StringReader; | |
import java.nio.file.Paths; | |
import java.util.HashMap; | |
import java.util.List; | |
import java.util.Map; | |
import static org.assertj.core.api.Assertions.assertThat; | |
public class PhoneticFstTests { | |
@Test | |
public void testPhoneticSuggester() throws Exception { | |
Map<String, String> args = new HashMap<>(); | |
args.put("encoder", "ColognePhonetic"); | |
CustomAnalyzer analyzer = CustomAnalyzer.builder() | |
.addTokenFilter(PhoneticFilterFactory.class, args) | |
.withTokenizer("standard") | |
.build(); | |
Directory directory = new NIOFSDirectory(Paths.get("/tmp/")); | |
AnalyzingSuggester suggester = new AnalyzingSuggester(directory, "lucene-tmp", analyzer); | |
// payloads are optional | |
String input = """ | |
spülmaschine\t10\tspülmaschine | |
spüle\t1\tspüle | |
speer\t5\tspeer | |
gabel\t100\tgabel | |
"""; | |
FileDictionary dictionary = new FileDictionary(new StringReader(input)); | |
suggester.build(dictionary); | |
assertLookup("sp", suggester, "spülmaschine/10", "speer/5", "spüle/1"); | |
assertLookup("spul", suggester, "spülmaschine/10", "spüle/1"); | |
assertLookup("spöl", suggester, "spülmaschine/10", "spüle/1"); | |
assertLookup("spln", suggester, "spülmaschine/10"); | |
// this is why you shouldnt use this as your default suggester | |
assertLookup("spe", suggester, "spülmaschine/10", "speer/5", "spüle/1"); | |
assertLookup("spee", suggester, "spülmaschine/10", "speer/5", "spüle/1"); | |
// back to normal | |
assertLookup("speer", suggester, "speer/5"); | |
assertLookup("gabel", suggester, "gabel/100"); | |
assertLookup("gabbel", suggester, "gabel/100"); | |
assertLookup("gobel", suggester, "gabel/100"); | |
assertLookup("ggobel", suggester, "gabel/100"); | |
} | |
private void assertLookup(String input, AnalyzingSuggester suggester, String ... expectedOutcomesWithScore) { | |
List<Lookup.LookupResult> results = suggester.lookup(input, null, false, 10); | |
assertThat(results).map(Lookup.LookupResult::toString).containsExactly(expectedOutcomesWithScore); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment