Examples with AnalysisRegistry org.opensearch.index.analysis.AnalysisRegistry used on opensource projects

Example 1 with AnalysisRegistry

use of org.opensearch.index.analysis.AnalysisRegistry in project OpenSearch by opensearch-project.

the class AnalysisModuleTests method testPluginPreConfiguredCharFilters.

/**
 * Tests that plugins can register pre-configured char filters that vary in behavior based on OpenSearch version, Lucene version,
 * and that do not vary based on version at all.
 */
public void testPluginPreConfiguredCharFilters() throws IOException {
    boolean noVersionSupportsMultiTerm = randomBoolean();
    boolean luceneVersionSupportsMultiTerm = randomBoolean();
    boolean opensearchVersionSupportsMultiTerm = randomBoolean();
    AnalysisRegistry registry = new AnalysisModule(TestEnvironment.newEnvironment(emptyNodeSettings), singletonList(new AnalysisPlugin() {

        @Override
        public List<PreConfiguredCharFilter> getPreConfiguredCharFilters() {
            return Arrays.asList(PreConfiguredCharFilter.singleton("no_version", noVersionSupportsMultiTerm, tokenStream -> new AppendCharFilter(tokenStream, "no_version")), PreConfiguredCharFilter.luceneVersion("lucene_version", luceneVersionSupportsMultiTerm, (tokenStream, luceneVersion) -> new AppendCharFilter(tokenStream, luceneVersion.toString())), PreConfiguredCharFilter.openSearchVersion("opensearch_version", opensearchVersionSupportsMultiTerm, (tokenStream, esVersion) -> new AppendCharFilter(tokenStream, esVersion.toString())));
        }

        @Override
        public Map<String, AnalysisProvider<TokenizerFactory>> getTokenizers() {
            // Need mock keyword tokenizer here, because alpha / beta versions are broken up by the dash.
            return singletonMap("keyword", (indexSettings, environment, name, settings) -> TokenizerFactory.newFactory(name, () -> new MockTokenizer(MockTokenizer.KEYWORD, false)));
        }
    })).getAnalysisRegistry();
    Version version = VersionUtils.randomVersion(random());
    IndexAnalyzers analyzers = getIndexAnalyzers(registry, Settings.builder().put("index.analysis.analyzer.no_version.tokenizer", "keyword").put("index.analysis.analyzer.no_version.char_filter", "no_version").put("index.analysis.analyzer.lucene_version.tokenizer", "keyword").put("index.analysis.analyzer.lucene_version.char_filter", "lucene_version").put("index.analysis.analyzer.opensearch_version.tokenizer", "keyword").put("index.analysis.analyzer.opensearch_version.char_filter", "opensearch_version").put(IndexMetadata.SETTING_VERSION_CREATED, version).build());
    assertTokenStreamContents(analyzers.get("no_version").tokenStream("", "test"), new String[] { "testno_version" });
    assertTokenStreamContents(analyzers.get("lucene_version").tokenStream("", "test"), new String[] { "test" + version.luceneVersion });
    assertTokenStreamContents(analyzers.get("opensearch_version").tokenStream("", "test"), new String[] { "test" + version });
    assertEquals("test" + (noVersionSupportsMultiTerm ? "no_version" : ""), analyzers.get("no_version").normalize("", "test").utf8ToString());
    assertEquals("test" + (luceneVersionSupportsMultiTerm ? version.luceneVersion.toString() : ""), analyzers.get("lucene_version").normalize("", "test").utf8ToString());
    assertEquals("test" + (opensearchVersionSupportsMultiTerm ? version.toString() : ""), analyzers.get("opensearch_version").normalize("", "test").utf8ToString());
}

Example 2 with AnalysisRegistry

use of org.opensearch.index.analysis.AnalysisRegistry in project OpenSearch by opensearch-project.

the class AnalysisModuleTests method testPluginPreConfiguredTokenFilters.

/**
 * Tests that plugins can register pre-configured token filters that vary in behavior based on OpenSearch version, Lucene version,
 * and that do not vary based on version at all.
 */
public void testPluginPreConfiguredTokenFilters() throws IOException {
    boolean noVersionSupportsMultiTerm = randomBoolean();
    boolean luceneVersionSupportsMultiTerm = randomBoolean();
    boolean opensearchVersionSupportsMultiTerm = randomBoolean();
    AnalysisRegistry registry = new AnalysisModule(TestEnvironment.newEnvironment(emptyNodeSettings), singletonList(new AnalysisPlugin() {

        @Override
        public List<PreConfiguredTokenFilter> getPreConfiguredTokenFilters() {
            return Arrays.asList(PreConfiguredTokenFilter.singleton("no_version", noVersionSupportsMultiTerm, tokenStream -> new AppendTokenFilter(tokenStream, "no_version")), PreConfiguredTokenFilter.luceneVersion("lucene_version", luceneVersionSupportsMultiTerm, (tokenStream, luceneVersion) -> new AppendTokenFilter(tokenStream, luceneVersion.toString())), PreConfiguredTokenFilter.openSearchVersion("opensearch_version", opensearchVersionSupportsMultiTerm, (tokenStream, esVersion) -> new AppendTokenFilter(tokenStream, esVersion.toString())));
        }
    })).getAnalysisRegistry();
    Version version = VersionUtils.randomVersion(random());
    IndexAnalyzers analyzers = getIndexAnalyzers(registry, Settings.builder().put("index.analysis.analyzer.no_version.tokenizer", "standard").put("index.analysis.analyzer.no_version.filter", "no_version").put("index.analysis.analyzer.lucene_version.tokenizer", "standard").put("index.analysis.analyzer.lucene_version.filter", "lucene_version").put("index.analysis.analyzer.opensearch_version.tokenizer", "standard").put("index.analysis.analyzer.opensearch_version.filter", "opensearch_version").put(IndexMetadata.SETTING_VERSION_CREATED, version).build());
    assertTokenStreamContents(analyzers.get("no_version").tokenStream("", "test"), new String[] { "testno_version" });
    assertTokenStreamContents(analyzers.get("lucene_version").tokenStream("", "test"), new String[] { "test" + version.luceneVersion });
    assertTokenStreamContents(analyzers.get("opensearch_version").tokenStream("", "test"), new String[] { "test" + version });
    assertEquals("test" + (noVersionSupportsMultiTerm ? "no_version" : ""), analyzers.get("no_version").normalize("", "test").utf8ToString());
    assertEquals("test" + (luceneVersionSupportsMultiTerm ? version.luceneVersion.toString() : ""), analyzers.get("lucene_version").normalize("", "test").utf8ToString());
    assertEquals("test" + (opensearchVersionSupportsMultiTerm ? version.toString() : ""), analyzers.get("opensearch_version").normalize("", "test").utf8ToString());
}

Example 3 with AnalysisRegistry

use of org.opensearch.index.analysis.AnalysisRegistry in project OpenSearch by opensearch-project.

the class OpenSearchTestCase method createTestAnalysis.

/**
 * Creates an TestAnalysis with all the default analyzers configured.
 */
public static TestAnalysis createTestAnalysis(IndexSettings indexSettings, Settings nodeSettings, AnalysisPlugin... analysisPlugins) throws IOException {
    Environment env = TestEnvironment.newEnvironment(nodeSettings);
    AnalysisModule analysisModule = new AnalysisModule(env, Arrays.asList(analysisPlugins));
    AnalysisRegistry analysisRegistry = analysisModule.getAnalysisRegistry();
    return new TestAnalysis(analysisRegistry.build(indexSettings), analysisRegistry.buildTokenFilterFactories(indexSettings), analysisRegistry.buildTokenizerFactories(indexSettings), analysisRegistry.buildCharFilterFactories(indexSettings));
}

Example 4 with AnalysisRegistry

use of org.opensearch.index.analysis.AnalysisRegistry in project OpenSearch by opensearch-project.

the class IndexModuleTests method testIndexAnalyzersCleanedUpIfIndexServiceCreationFails.

public void testIndexAnalyzersCleanedUpIfIndexServiceCreationFails() {
    Settings settings = Settings.builder().put(Environment.PATH_HOME_SETTING.getKey(), createTempDir().toString()).put(IndexMetadata.SETTING_VERSION_CREATED, Version.CURRENT).build();
    final IndexSettings indexSettings = IndexSettingsModule.newIndexSettings("foo", settings);
    final HashSet<Analyzer> openAnalyzers = new HashSet<>();
    final AnalysisModule.AnalysisProvider<AnalyzerProvider<?>> analysisProvider = (i, e, n, s) -> new AnalyzerProvider<Analyzer>() {

        @Override
        public String name() {
            return "test";
        }

        @Override
        public AnalyzerScope scope() {
            return AnalyzerScope.INDEX;
        }

        @Override
        public Analyzer get() {
            final Analyzer analyzer = new Analyzer() {

                @Override
                protected TokenStreamComponents createComponents(String fieldName) {
                    return new TokenStreamComponents(new StandardTokenizer());
                }

                @Override
                public void close() {
                    super.close();
                    openAnalyzers.remove(this);
                }
            };
            openAnalyzers.add(analyzer);
            return analyzer;
        }
    };
    final AnalysisRegistry analysisRegistry = new AnalysisRegistry(environment, emptyMap(), emptyMap(), emptyMap(), singletonMap("test", analysisProvider), emptyMap(), emptyMap(), emptyMap(), emptyMap(), emptyMap());
    IndexModule module = createIndexModule(indexSettings, analysisRegistry);
    // causes index service creation to fail
    threadPool.shutdown();
    expectThrows(OpenSearchRejectedExecutionException.class, () -> newIndexService(module));
    assertThat(openAnalyzers, empty());
}

Example 5 with AnalysisRegistry

use of org.opensearch.index.analysis.AnalysisRegistry in project OpenSearch by opensearch-project.

the class IndexModuleTests method setUp.

@Override
public void setUp() throws Exception {
    super.setUp();
    settings = Settings.builder().put(IndexMetadata.SETTING_VERSION_CREATED, Version.CURRENT).put(Environment.PATH_HOME_SETTING.getKey(), createTempDir().toString()).build();
    indicesQueryCache = new IndicesQueryCache(settings);
    indexSettings = IndexSettingsModule.newIndexSettings("foo", settings);
    index = indexSettings.getIndex();
    environment = TestEnvironment.newEnvironment(settings);
    emptyAnalysisRegistry = new AnalysisRegistry(environment, emptyMap(), emptyMap(), emptyMap(), emptyMap(), emptyMap(), emptyMap(), emptyMap(), emptyMap(), emptyMap());
    threadPool = new TestThreadPool("test");
    circuitBreakerService = new NoneCircuitBreakerService();
    PageCacheRecycler pageCacheRecycler = new PageCacheRecycler(settings);
    bigArrays = new BigArrays(pageCacheRecycler, circuitBreakerService, CircuitBreaker.REQUEST);
    scriptService = new ScriptService(settings, Collections.emptyMap(), Collections.emptyMap());
    clusterService = ClusterServiceUtils.createClusterService(threadPool);
    nodeEnvironment = new NodeEnvironment(settings, environment);
    mapperRegistry = new IndicesModule(Collections.emptyList()).getMapperRegistry();
}