Examples with IndexSettings org.elasticsearch.index.IndexSettings used on opensource projects

Example 11 with IndexSettings

use of org.elasticsearch.index.IndexSettings in project elasticsearch by elastic.

the class CodecTests method createCodecService.

private CodecService createCodecService() throws IOException {
    Settings nodeSettings = Settings.builder().put(Environment.PATH_HOME_SETTING.getKey(), createTempDir()).build();
    IndexSettings settings = IndexSettingsModule.newIndexSettings("_na", nodeSettings);
    SimilarityService similarityService = new SimilarityService(settings, Collections.emptyMap());
    IndexAnalyzers indexAnalyzers = createTestAnalysis(settings, nodeSettings).indexAnalyzers;
    MapperRegistry mapperRegistry = new MapperRegistry(Collections.emptyMap(), Collections.emptyMap());
    MapperService service = new MapperService(settings, indexAnalyzers, xContentRegistry(), similarityService, mapperRegistry, () -> null);
    return new CodecService(service, ESLoggerFactory.getLogger("test"));
}

Example 12 with IndexSettings

use of org.elasticsearch.index.IndexSettings in project elasticsearch by elastic.

the class NGramTokenizerFactoryTests method testBackwardsCompatibilityEdgeNgramTokenFilter.

public void testBackwardsCompatibilityEdgeNgramTokenFilter() throws Exception {
    int iters = scaledRandomIntBetween(20, 100);
    for (int i = 0; i < iters; i++) {
        final Index index = new Index("test", "_na_");
        final String name = "ngr";
        Version v = randomVersion(random());
        Builder builder = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 3);
        boolean reverse = random().nextBoolean();
        if (reverse) {
            builder.put("side", "back");
        }
        Settings settings = builder.build();
        Settings indexSettings = newAnalysisSettingsBuilder().put(IndexMetaData.SETTING_VERSION_CREATED, v.id).build();
        Tokenizer tokenizer = new MockTokenizer();
        tokenizer.setReader(new StringReader("foo bar"));
        TokenStream edgeNGramTokenFilter = new EdgeNGramTokenFilterFactory(IndexSettingsModule.newIndexSettings(index, indexSettings), null, name, settings).create(tokenizer);
        if (reverse) {
            assertThat(edgeNGramTokenFilter, instanceOf(ReverseStringFilter.class));
        } else {
            assertThat(edgeNGramTokenFilter, instanceOf(EdgeNGramTokenFilter.class));
        }
    }
}

Example 13 with IndexSettings

use of org.elasticsearch.index.IndexSettings in project elasticsearch by elastic.

the class NGramTokenizerFactoryTests method testNoTokenChars.

public void testNoTokenChars() throws IOException {
    final Index index = new Index("test", "_na_");
    final String name = "ngr";
    final Settings indexSettings = newAnalysisSettingsBuilder().build();
    final Settings settings = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 4).putArray("token_chars", new String[0]).build();
    Tokenizer tokenizer = new NGramTokenizerFactory(IndexSettingsModule.newIndexSettings(index, indexSettings), null, name, settings).create();
    tokenizer.setReader(new StringReader("1.34"));
    assertTokenStreamContents(tokenizer, new String[] { "1.", "1.3", "1.34", ".3", ".34", "34" });
}

Example 14 with IndexSettings

use of org.elasticsearch.index.IndexSettings in project elasticsearch by elastic.

the class NGramTokenizerFactoryTests method testPreTokenizationEdge.

public void testPreTokenizationEdge() throws IOException {
    // Make sure that pretokenization works well and that it can be used even with token chars which are supplementary characters
    final Index index = new Index("test", "_na_");
    final String name = "ngr";
    final Settings indexSettings = newAnalysisSettingsBuilder().build();
    Settings settings = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 3).put("token_chars", "letter,digit").build();
    Tokenizer tokenizer = new EdgeNGramTokenizerFactory(IndexSettingsModule.newIndexSettings(index, indexSettings), null, name, settings).create();
    tokenizer.setReader(new StringReader("Åbc déf g𐐀f "));
    assertTokenStreamContents(tokenizer, new String[] { "Åb", "Åbc", "dé", "déf", "g𐐀", "g𐐀f" });
    settings = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 3).put("token_chars", "letter,digit,punctuation,whitespace,symbol").build();
    tokenizer = new EdgeNGramTokenizerFactory(IndexSettingsModule.newIndexSettings(index, indexSettings), null, name, settings).create();
    tokenizer.setReader(new StringReader(" a!$ 9"));
    assertTokenStreamContents(tokenizer, new String[] { " a", " a!" });
}

Example 15 with IndexSettings

use of org.elasticsearch.index.IndexSettings in project elasticsearch by elastic.

the class NGramTokenizerFactoryTests method testPreTokenization.

public void testPreTokenization() throws IOException {
    // Make sure that pretokenization works well and that it can be used even with token chars which are supplementary characters
    final Index index = new Index("test", "_na_");
    final String name = "ngr";
    final Settings indexSettings = newAnalysisSettingsBuilder().build();
    Settings settings = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 3).put("token_chars", "letter,digit").build();
    Tokenizer tokenizer = new NGramTokenizerFactory(IndexSettingsModule.newIndexSettings(index, indexSettings), null, name, settings).create();
    tokenizer.setReader(new StringReader("Åbc déf g𐐀f "));
    assertTokenStreamContents(tokenizer, new String[] { "Åb", "Åbc", "bc", "dé", "déf", "éf", "g𐐀", "g𐐀f", "𐐀f" });
    settings = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 3).put("token_chars", "letter,digit,punctuation,whitespace,symbol").build();
    tokenizer = new NGramTokenizerFactory(IndexSettingsModule.newIndexSettings(index, indexSettings), null, name, settings).create();
    tokenizer.setReader(new StringReader(" a!$ 9"));
    assertTokenStreamContents(tokenizer, new String[] { " a", " a!", "a!", "a!$", "!$", "!$ ", "$ ", "$ 9", " 9" });
}