Skip to content

Fix kuromoji default stoptags #26600

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Sep 15, 2017
Merged

Fix kuromoji default stoptags #26600

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
52d1c28
[TEST] Fix parameter order to `assertThat` call
avdv Sep 12, 2017
7b4e0f7
Use default stop-tags for Kuromoji part-of-speech filter
avdv Sep 12, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions ...oji/src/main/java/org/elasticsearch/index/analysis/KuromojiPartOfSpeechFilterFactory.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@
package org.elasticsearch.index.analysis;

import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.ja.JapaneseAnalyzer;
import org.apache.lucene.analysis.ja.JapanesePartOfSpeechStopFilter;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.env.Environment;
Expand All @@ -38,6 +39,8 @@ public KuromojiPartOfSpeechFilterFactory(IndexSettings indexSettings, Environmen
List<String> wordList = Analysis.getWordList(env, settings, "stoptags");
if (wordList != null) {
stopTags.addAll(wordList);
} else {
stopTags.addAll(JapaneseAnalyzer.getDefaultStopTags());
}
}

Expand Down
17 changes: 16 additions & 1 deletion ...alysis-kuromoji/src/test/java/org/elasticsearch/index/analysis/KuromojiAnalysisTests.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,6 +93,21 @@ public void testBaseFormFilterFactory() throws IOException {
assertSimpleTSOutput(tokenFilter.create(tokenizer), expected);
}

public void testPartOfSpeechFilter() throws IOException {
TestAnalysis analysis = createTestAnalysis();
TokenFilterFactory tokenFilter = analysis.tokenFilter.get("kuromoji_part_of_speech");

assertThat(tokenFilter, instanceOf(KuromojiPartOfSpeechFilterFactory.class));

String source = "寿司がおいしいね";
String[] expected_tokens = new String[]{"寿司", "おいしい"};

Tokenizer tokenizer = new JapaneseTokenizer(null, true, JapaneseTokenizer.Mode.SEARCH);
tokenizer.setReader(new StringReader(source));

assertSimpleTSOutput(tokenFilter.create(tokenizer), expected_tokens);
}

public void testReadingFormFilterFactory() throws IOException {
TestAnalysis analysis = createTestAnalysis();
TokenFilterFactory tokenFilter = analysis.tokenFilter.get("kuromoji_rf");
Expand Down Expand Up @@ -208,7 +223,7 @@ public static void assertSimpleTSOutput(TokenStream stream,
int i = 0;
while (stream.incrementToken()) {
assertThat(expected.length, greaterThan(i));
assertThat( "expected different term at index " + i, expected[i++], equalTo(termAttr.toString()));
assertThat("expected different term at index " + i, termAttr.toString(), equalTo(expected[i++]));
}
assertThat("not all tokens produced", i, equalTo(expected.length));
}
Expand Down