Java AnalyzerProvider类代码示例

import org.elasticsearch.index.analysis.AnalyzerProvider; //导入依赖的package包/类
@Override
public Map<String, AnalysisModule.AnalysisProvider<AnalyzerProvider<? extends Analyzer>>> getAnalyzers() {
  Map<String, AnalysisModule.AnalysisProvider<AnalyzerProvider<? extends Analyzer>>> extra = new HashMap<>();

  extra.put("jieba_search", JiebaAnalyzerProvider::getJiebaSearchAnalyzerProvider);
  extra.put("jieba_index", JiebaAnalyzerProvider::getJiebaIndexAnalyzerProvider);

  return extra;
}
 

import org.elasticsearch.index.analysis.AnalyzerProvider; //导入依赖的package包/类
public AnalysisModule(Environment environment, List<AnalysisPlugin> plugins) throws IOException {
    NamedRegistry<AnalysisProvider<CharFilterFactory>> charFilters = setupCharFilters(plugins);
    NamedRegistry<org.apache.lucene.analysis.hunspell.Dictionary> hunspellDictionaries = setupHunspellDictionaries(plugins);
    hunspellService = new HunspellService(environment.settings(), environment, hunspellDictionaries.getRegistry());
    NamedRegistry<AnalysisProvider<TokenFilterFactory>> tokenFilters = setupTokenFilters(plugins, hunspellService);
    NamedRegistry<AnalysisProvider<TokenizerFactory>> tokenizers = setupTokenizers(plugins);
    NamedRegistry<AnalysisProvider<AnalyzerProvider<?>>> analyzers = setupAnalyzers(plugins);
    NamedRegistry<AnalysisProvider<AnalyzerProvider<?>>> normalizers = setupNormalizers(plugins);
    analysisRegistry = new AnalysisRegistry(environment, charFilters.getRegistry(), tokenFilters.getRegistry(), tokenizers
        .getRegistry(), analyzers.getRegistry(), normalizers.getRegistry());
}
 

import org.elasticsearch.index.analysis.AnalyzerProvider; //导入依赖的package包/类
@Override
public Map<String, AnalysisModule.AnalysisProvider<AnalyzerProvider<? extends Analyzer>>> getAnalyzers() {
    Map<String, AnalysisModule.AnalysisProvider<AnalyzerProvider<? extends Analyzer>>> extra = new HashMap<>();

    extra.put("ik_smart", IkAnalyzerProvider::getIkSmartAnalyzerProvider);
    extra.put("ik_max_word", IkAnalyzerProvider::getIkAnalyzerProvider);

    return extra;
}
 

import org.elasticsearch.index.analysis.AnalyzerProvider; //导入依赖的package包/类
@Override
public Map<String, AnalysisModule.AnalysisProvider<AnalyzerProvider<? extends Analyzer>>> getAnalyzers() {
    Map<String, AnalysisModule.AnalysisProvider<AnalyzerProvider<? extends Analyzer>>> providerMap
            = new HashMap<String, AnalysisModule.AnalysisProvider<AnalyzerProvider<? extends Analyzer>>>();

    providerMap.put("lc_index", LcPinyinAnalyzerProvider::getIndexAnalyzerProvider);
    providerMap.put("lc_search", LcPinyinAnalyzerProvider::getSmartPinyinAnalyzerProvider);

    return providerMap;
}
 

import org.elasticsearch.index.analysis.AnalyzerProvider; //导入依赖的package包/类
@Override
public Map<String, AnalysisModule.AnalysisProvider<AnalyzerProvider<? extends Analyzer>>> getAnalyzers() {
    Map<String, AnalysisModule.AnalysisProvider<AnalyzerProvider<? extends Analyzer>>> retMap = new HashMap<>();
    for (Config.AnalysisConfig ca : config.getSegmentConfig()) {
        final Segment segment = ca.createSegment(config.getCjkLexicon());
        retMap.put(segment.getName(), (indexSettings, environment, name, settings) -> new AbstractIndexAnalyzerProvider(indexSettings, name, settings) {

            @Override
            public Analyzer get() {
                return new BenzAnalyzer(config, segment);
            }
        });
    }
    return retMap;
}
 

import org.elasticsearch.index.analysis.AnalyzerProvider; //导入依赖的package包/类
public static DocumentMapperParser newDocumentMapperParser(Settings customSettings, String index) throws IOException {
    Settings settings = Settings.builder()
            .put("path.home", System.getProperty("path.home", System.getProperty("user.dir")))
            .put(IndexMetaData.SETTING_VERSION_CREATED, Version.CURRENT)
            .put(customSettings)
            .build();
    Environment environment = new Environment(settings);
    ReferencePlugin referencePlugin = new ReferencePlugin();
    AnalysisModule analysisModule = new AnalysisModule(environment, Collections.emptyList());
    IndicesModule indicesModule = new IndicesModule(Collections.singletonList(referencePlugin));
    MapperRegistry mapperRegistry = indicesModule.getMapperRegistry();
    AnalysisRegistry analysisRegistry = analysisModule.getAnalysisRegistry();
    IndexMetaData indexMetaData = IndexMetaData.builder(index)
            .settings(settings)
            .numberOfShards(1)
            .numberOfReplicas(1)
            .build();
    IndexSettings indexSettings = new IndexSettings(indexMetaData, settings);
    SimilarityService similarityService = new SimilarityService(indexSettings, SimilarityService.BUILT_IN);
    Map<String, CharFilterFactory> charFilterFactoryMap = analysisRegistry.buildCharFilterFactories(indexSettings);
    Map<String, TokenFilterFactory> tokenFilterFactoryMap = analysisRegistry.buildTokenFilterFactories(indexSettings);
    Map<String, TokenizerFactory> tokenizerFactoryMap = analysisRegistry.buildTokenizerFactories(indexSettings);
    Map<String, AnalyzerProvider<?>> analyzerProviderMap = analysisRegistry.buildAnalyzerFactories(indexSettings);
    Map<String, AnalyzerProvider<?>> normalizerProviderMap = analysisRegistry.buildNormalizerFactories(indexSettings);
    IndexAnalyzers indexAnalyzers = analysisRegistry.build(indexSettings,
            analyzerProviderMap,
            normalizerProviderMap,
            tokenizerFactoryMap,
            charFilterFactoryMap,
            tokenFilterFactoryMap);
    MapperService mapperService = new MapperService(indexSettings, indexAnalyzers, NamedXContentRegistry.EMPTY,
            similarityService, mapperRegistry, null);
    return new DocumentMapperParser(indexSettings, mapperService, indexAnalyzers, NamedXContentRegistry.EMPTY,
            similarityService, mapperRegistry, null);
}
 

import org.elasticsearch.index.analysis.AnalyzerProvider; //导入依赖的package包/类
@Override
public Map<String, AnalysisModule.AnalysisProvider<AnalyzerProvider<? extends Analyzer>>> getAnalyzers() {
    Map<String, AnalysisModule.AnalysisProvider<AnalyzerProvider<? extends Analyzer>>> extra = new LinkedHashMap<>();
    if (settings.getAsBoolean("plugins.xbib.icu.enabled", true)) {
        extra.put("icu_collation", IcuCollationKeyAnalyzerProvider::new);
    }
    extra.put("hyphen", HyphenAnalyzerProvider::new);
    extra.put("naturalsort", NaturalSortKeyAnalyzerProvider::new);
    extra.put("sortform", SortformAnalyzerProvider::new);
    extra.put("standardnumber", (indexSettings, environment, name, factorySettings) ->
            new StandardnumberAnalyzerProvider(indexSettings, environment, name, factorySettings, standardNumberTypeParser));
    return extra;
}
 

import org.elasticsearch.index.analysis.AnalyzerProvider; //导入依赖的package包/类
public static DocumentMapperParser newDocumentMapperParser(Settings customSettings, String index) throws IOException {
    Settings settings = Settings.builder()
            .put("path.home", System.getProperty("path.home", "/tmp"))
            .put(IndexMetaData.SETTING_VERSION_CREATED, Version.CURRENT)
            .put(customSettings)
            .build();
    Environment environment = new Environment(settings);
    BundlePlugin bundlePlugin = new BundlePlugin(settings);
    AnalysisModule analysisModule = new AnalysisModule(environment, Collections.singletonList(bundlePlugin));
    IndicesModule indicesModule = new IndicesModule(Collections.singletonList(bundlePlugin));
    MapperRegistry mapperRegistry = indicesModule.getMapperRegistry();
    AnalysisRegistry analysisRegistry = analysisModule.getAnalysisRegistry();
    IndexMetaData indexMetaData = IndexMetaData.builder(index)
            .settings(settings)
            .numberOfShards(1)
            .numberOfReplicas(1)
            .build();
    IndexSettings indexSettings = new IndexSettings(indexMetaData, settings);
    SimilarityService similarityService = new SimilarityService(indexSettings, SimilarityService.BUILT_IN);
    Map<String, CharFilterFactory> charFilterFactoryMap = analysisRegistry.buildCharFilterFactories(indexSettings);
    Map<String, TokenFilterFactory> tokenFilterFactoryMap = analysisRegistry.buildTokenFilterFactories(indexSettings);
    Map<String, TokenizerFactory> tokenizerFactoryMap = analysisRegistry.buildTokenizerFactories(indexSettings);
    Map<String, AnalyzerProvider<?>> analyzerProviderMap = analysisRegistry.buildAnalyzerFactories(indexSettings);
    Map<String, AnalyzerProvider<?>> normalizerProviderMap = analysisRegistry.buildNormalizerFactories(indexSettings);
    IndexAnalyzers indexAnalyzers = analysisRegistry.build(indexSettings,
            analyzerProviderMap,
            normalizerProviderMap,
            tokenizerFactoryMap,
            charFilterFactoryMap,
            tokenFilterFactoryMap);
    MapperService mapperService = new MapperService(indexSettings, indexAnalyzers, NamedXContentRegistry.EMPTY,
            similarityService, mapperRegistry, null);
    return new DocumentMapperParser(indexSettings, mapperService, indexAnalyzers, NamedXContentRegistry.EMPTY,
            similarityService, mapperRegistry, null);
}
 

import org.elasticsearch.index.analysis.AnalyzerProvider; //导入依赖的package包/类
private NamedRegistry<AnalysisProvider<AnalyzerProvider<?>>> setupAnalyzers(List<AnalysisPlugin> plugins) {
    NamedRegistry<AnalysisProvider<AnalyzerProvider<?>>> analyzers = new NamedRegistry<>("analyzer");
    analyzers.register("default", StandardAnalyzerProvider::new);
    analyzers.register("standard", StandardAnalyzerProvider::new);
    analyzers.register("standard_html_strip", StandardHtmlStripAnalyzerProvider::new);
    analyzers.register("simple", SimpleAnalyzerProvider::new);
    analyzers.register("stop", StopAnalyzerProvider::new);
    analyzers.register("whitespace", WhitespaceAnalyzerProvider::new);
    analyzers.register("keyword", KeywordAnalyzerProvider::new);
    analyzers.register("pattern", PatternAnalyzerProvider::new);
    analyzers.register("snowball", SnowballAnalyzerProvider::new);
    analyzers.register("arabic", ArabicAnalyzerProvider::new);
    analyzers.register("armenian", ArmenianAnalyzerProvider::new);
    analyzers.register("basque", BasqueAnalyzerProvider::new);
    analyzers.register("brazilian", BrazilianAnalyzerProvider::new);
    analyzers.register("bulgarian", BulgarianAnalyzerProvider::new);
    analyzers.register("catalan", CatalanAnalyzerProvider::new);
    analyzers.register("chinese", ChineseAnalyzerProvider::new);
    analyzers.register("cjk", CjkAnalyzerProvider::new);
    analyzers.register("czech", CzechAnalyzerProvider::new);
    analyzers.register("danish", DanishAnalyzerProvider::new);
    analyzers.register("dutch", DutchAnalyzerProvider::new);
    analyzers.register("english", EnglishAnalyzerProvider::new);
    analyzers.register("finnish", FinnishAnalyzerProvider::new);
    analyzers.register("french", FrenchAnalyzerProvider::new);
    analyzers.register("galician", GalicianAnalyzerProvider::new);
    analyzers.register("german", GermanAnalyzerProvider::new);
    analyzers.register("greek", GreekAnalyzerProvider::new);
    analyzers.register("hindi", HindiAnalyzerProvider::new);
    analyzers.register("hungarian", HungarianAnalyzerProvider::new);
    analyzers.register("indonesian", IndonesianAnalyzerProvider::new);
    analyzers.register("irish", IrishAnalyzerProvider::new);
    analyzers.register("italian", ItalianAnalyzerProvider::new);
    analyzers.register("latvian", LatvianAnalyzerProvider::new);
    analyzers.register("lithuanian", LithuanianAnalyzerProvider::new);
    analyzers.register("norwegian", NorwegianAnalyzerProvider::new);
    analyzers.register("persian", PersianAnalyzerProvider::new);
    analyzers.register("portuguese", PortugueseAnalyzerProvider::new);
    analyzers.register("romanian", RomanianAnalyzerProvider::new);
    analyzers.register("russian", RussianAnalyzerProvider::new);
    analyzers.register("sorani", SoraniAnalyzerProvider::new);
    analyzers.register("spanish", SpanishAnalyzerProvider::new);
    analyzers.register("swedish", SwedishAnalyzerProvider::new);
    analyzers.register("turkish", TurkishAnalyzerProvider::new);
    analyzers.register("thai", ThaiAnalyzerProvider::new);
    analyzers.register("fingerprint", FingerprintAnalyzerProvider::new);
    analyzers.extractAndRegister(plugins, AnalysisPlugin::getAnalyzers);
    return analyzers;
}
 

import org.elasticsearch.index.analysis.AnalyzerProvider; //导入依赖的package包/类
private NamedRegistry<AnalysisProvider<AnalyzerProvider<?>>> setupNormalizers(List<AnalysisPlugin> plugins) {
    NamedRegistry<AnalysisProvider<AnalyzerProvider<?>>> normalizers = new NamedRegistry<>("normalizer");
    // TODO: provide built-in normalizer providers?
    // TODO: pluggability?
    return normalizers;
}
 

import org.elasticsearch.index.analysis.AnalyzerProvider; //导入依赖的package包/类
/**
 * Override to add additional {@link Analyzer}s.
 */
default Map<String, AnalysisProvider<AnalyzerProvider<? extends Analyzer>>> getAnalyzers() {
    return emptyMap();
}
 

import org.elasticsearch.index.analysis.AnalyzerProvider; //导入依赖的package包/类
@Override
public Map<String, AnalysisProvider<AnalyzerProvider<? extends Analyzer>>> getAnalyzers() {
    return singletonMap("dummy", (a, b, c, d) -> new DummyAnalyzerProvider());
}
 

import org.elasticsearch.index.analysis.AnalyzerProvider; //导入依赖的package包/类
@Override
public Map<String, AnalysisProvider<AnalyzerProvider<? extends Analyzer>>> getAnalyzers() {
    return singletonMap("polish", PolishAnalyzerProvider::new);
}
 

import org.elasticsearch.index.analysis.AnalyzerProvider; //导入依赖的package包/类
@Override
public Map<String, AnalysisProvider<AnalyzerProvider<? extends Analyzer>>> getAnalyzers() {
    return singletonMap("ukrainian", UkrainianAnalyzerProvider::new);
}
 

import org.elasticsearch.index.analysis.AnalyzerProvider; //导入依赖的package包/类
@Override
public Map<String, AnalysisProvider<AnalyzerProvider<? extends Analyzer>>> getAnalyzers() {
    return singletonMap("smartcn", SmartChineseAnalyzerProvider::new);
}