org.elasticsearch.index.analysis.SmartChineseAnalysisTests.java Source code

Introduction

Here is the source code for org.elasticsearch.index.analysis.SmartChineseAnalysisTests.java

Source

/*
 * Licensed to Elastic Search and Shay Banon under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership. Elastic Search licenses this
 * file to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing,
 * software distributed under the License is distributed on an
 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
 * KIND, either express or implied.  See the License for the
 * specific language governing permissions and limitations
 * under the License.
 */

package org.elasticsearch.index.analysis;

import static org.elasticsearch.common.settings.ImmutableSettings.Builder.EMPTY_SETTINGS;
import static org.hamcrest.Matchers.equalTo;
import static org.hamcrest.Matchers.hasItems;

import java.util.ArrayList;
import java.util.List;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.TermAttribute;
import org.elasticsearch.common.inject.Injector;
import org.elasticsearch.common.inject.ModulesBuilder;
import org.elasticsearch.common.lucene.all.AllEntries;
import org.elasticsearch.common.lucene.all.AllTokenStream;
import org.elasticsearch.common.settings.SettingsModule;
import org.elasticsearch.env.Environment;
import org.elasticsearch.env.EnvironmentModule;
import org.elasticsearch.index.Index;
import org.elasticsearch.index.IndexNameModule;
import org.elasticsearch.index.settings.IndexSettingsModule;
import org.elasticsearch.indices.analysis.IndicesAnalysisModule;
import org.elasticsearch.indices.analysis.IndicesAnalysisService;
import org.hamcrest.MatcherAssert;
import org.testng.annotations.Test;

/**
 * @author thmttch (matt.chu@gmail.com)
 */
public class SmartChineseAnalysisTests {

    /**
     * With the default analyzer or the default Chinese analyzer, you would get: 
     * { "", "", "", "", "" }.
     * <p>
     * But the SmartAnalyzer gets you the more desirable:
     * { "", "", "", "" }.
     * That is, "" (China) is one token.
     */
    @Test
    public void analyzeSomeChineseText() throws Exception {
        Index index = new Index("test");

        Injector parentInjector = new ModulesBuilder().add(new SettingsModule(EMPTY_SETTINGS),
                new EnvironmentModule(new Environment(EMPTY_SETTINGS)), new IndicesAnalysisModule())
                .createInjector();
        Injector injector = new ModulesBuilder()
                .add(new IndexSettingsModule(index, EMPTY_SETTINGS), new IndexNameModule(index),
                        new AnalysisModule(EMPTY_SETTINGS, parentInjector.getInstance(IndicesAnalysisService.class))
                                .addProcessor(new SmartChineseAnalysisBinderProcessor()))
                .createChildInjector(parentInjector);

        AnalysisService analysisService = injector.getInstance(AnalysisService.class);

        Analyzer analyzer = analysisService.analyzer("smartcn").analyzer();

        AllEntries allEntries = new AllEntries();
        allEntries.addText("message", "", 1.0f);
        allEntries.reset();

        TokenStream stream = AllTokenStream.allTokenStream("_all", allEntries, analyzer);
        TermAttribute termAtt = stream.addAttribute(TermAttribute.class);

        List<String> terms = new ArrayList<String>();
        while (stream.incrementToken()) {
            String tokText = termAtt.term();
            terms.add(tokText);
        }

        MatcherAssert.assertThat(terms.size(), equalTo(4));
        MatcherAssert.assertThat(terms, hasItems("", "", "", ""));
    }

}