@Test
public void testWordListPath() throws Exception {
Environment env = new Environment(ImmutableSettings.Builder.EMPTY_SETTINGS);
String[] words = new String[] {"donau", "dampf", "schiff", "spargel", "creme", "suppe"};
File wordListFile = generateWordList(words);
Settings settings =
settingsBuilder()
.loadFromSource("index: \n word_list_path: " + wordListFile.getAbsolutePath())
.build();
Set<String> wordList = Analysis.getWordSet(env, settings, "index.word_list");
MatcherAssert.assertThat(wordList.size(), equalTo(6));
MatcherAssert.assertThat(wordList, hasItems(words));
}
private void testSimpleConfiguration(Settings settings) {
Index index = new Index("test");
Injector parentInjector =
new ModulesBuilder()
.add(
new SettingsModule(settings),
new EnvironmentModule(new Environment(settings)),
new IndicesAnalysisModule())
.createInjector();
Injector injector =
new ModulesBuilder()
.add(
new IndexSettingsModule(index, settings),
new IndexNameModule(index),
new AnalysisModule(
settings, parentInjector.getInstance(IndicesAnalysisService.class)))
.createChildInjector(parentInjector);
AnalysisService analysisService = injector.getInstance(AnalysisService.class);
Analyzer analyzer = analysisService.analyzer("custom1").analyzer();
assertThat(analyzer, instanceOf(CustomAnalyzer.class));
CustomAnalyzer custom1 = (CustomAnalyzer) analyzer;
assertThat(custom1.tokenizerFactory(), instanceOf(StandardTokenizerFactory.class));
assertThat(custom1.tokenFilters().length, equalTo(2));
StopTokenFilterFactory stop1 = (StopTokenFilterFactory) custom1.tokenFilters()[0];
assertThat(stop1.stopWords().size(), equalTo(1));
assertThat((Iterable<String>) stop1.stopWords(), hasItem("test-stop"));
analyzer = analysisService.analyzer("custom2").analyzer();
assertThat(analyzer, instanceOf(CustomAnalyzer.class));
CustomAnalyzer custom2 = (CustomAnalyzer) analyzer;
// HtmlStripCharFilterFactory html = (HtmlStripCharFilterFactory)
// custom2.charFilters()[0];
// assertThat(html.readAheadLimit(), equalTo(HTMLStripCharFilter.DEFAULT_READ_AHEAD));
//
// html = (HtmlStripCharFilterFactory) custom2.charFilters()[1];
// assertThat(html.readAheadLimit(), equalTo(1024));
// verify characters mapping
analyzer = analysisService.analyzer("custom5").analyzer();
assertThat(analyzer, instanceOf(CustomAnalyzer.class));
CustomAnalyzer custom5 = (CustomAnalyzer) analyzer;
assertThat(custom5.tokenFilters()[0], instanceOf(MappingCharFilterFactory.class));
// verify aliases
analyzer = analysisService.analyzer("alias1").analyzer();
assertThat(analyzer, instanceOf(StandardAnalyzer.class));
// check phonetic
analyzer = analysisService.analyzer("custom3").analyzer();
assertThat(analyzer, instanceOf(CustomAnalyzer.class));
CustomAnalyzer custom3 = (CustomAnalyzer) analyzer;
assertThat(custom3.tokenFilters()[0], instanceOf(PhoneticTokenFilterFactory.class));
// check custom class name (my)
analyzer = analysisService.analyzer("custom4").analyzer();
assertThat(analyzer, instanceOf(CustomAnalyzer.class));
CustomAnalyzer custom4 = (CustomAnalyzer) analyzer;
assertThat(custom4.tokenFilters()[0], instanceOf(MyFilterTokenFilterFactory.class));
// // verify Czech stemmer
// analyzer = analysisService.analyzer("czechAnalyzerWithStemmer").analyzer();
// assertThat(analyzer, instanceOf(CustomAnalyzer.class));
// CustomAnalyzer czechstemmeranalyzer = (CustomAnalyzer) analyzer;
// assertThat(czechstemmeranalyzer.tokenizerFactory(),
// instanceOf(StandardTokenizerFactory.class));
// assertThat(czechstemmeranalyzer.tokenFilters().length, equalTo(4));
// assertThat(czechstemmeranalyzer.tokenFilters()[3],
// instanceOf(CzechStemTokenFilterFactory.class));
//
// // check dictionary decompounder
// analyzer = analysisService.analyzer("decompoundingAnalyzer").analyzer();
// assertThat(analyzer, instanceOf(CustomAnalyzer.class));
// CustomAnalyzer dictionaryDecompounderAnalyze = (CustomAnalyzer) analyzer;
// assertThat(dictionaryDecompounderAnalyze.tokenizerFactory(),
// instanceOf(StandardTokenizerFactory.class));
// assertThat(dictionaryDecompounderAnalyze.tokenFilters().length, equalTo(1));
// assertThat(dictionaryDecompounderAnalyze.tokenFilters()[0],
// instanceOf(DictionaryCompoundWordTokenFilterFactory.class));
Set<String> wordList =
Analysis.getWordSet(null, settings, "index.analysis.filter.dict_dec.word_list");
MatcherAssert.assertThat(wordList.size(), equalTo(6));
MatcherAssert.assertThat(
wordList, hasItems("donau", "dampf", "schiff", "spargel", "creme", "suppe"));
}
