本文整理汇总了Java中org.apache.lucene.analysis.miscellaneous.ASCIIFoldingFilterFactory类的典型用法代码示例。如果您正苦于以下问题：Java ASCIIFoldingFilterFactory类的具体用法？Java ASCIIFoldingFilterFactory怎么用？Java ASCIIFoldingFilterFactory使用的例子？那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。
ASCIIFoldingFilterFactory类属于org.apache.lucene.analysis.miscellaneous包，在下文中一共展示了ASCIIFoldingFilterFactory类的4个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Java代码示例。
示例1: testDefaultCopiedToMulti
import org.apache.lucene.analysis.miscellaneous.ASCIIFoldingFilterFactory; //导入依赖的package包/类
@Test
public void testDefaultCopiedToMulti() {
SchemaField field = h.getCore().getLatestSchema().getField("content_ws");
Analyzer analyzer = ((TextField)field.getType()).getMultiTermAnalyzer();
assertTrue(analyzer instanceof TokenizerChain);
assertTrue(((TokenizerChain) analyzer).getTokenizerFactory() instanceof KeywordTokenizerFactory);
TokenizerChain tc = (TokenizerChain) analyzer;
for (TokenFilterFactory factory : tc.getTokenFilterFactories()) {
assertTrue((factory instanceof ASCIIFoldingFilterFactory) || (factory instanceof LowerCaseFilterFactory));
}
assertTrue(tc.getCharFilterFactories() == null);
}
示例2: testASCIIFolding
import org.apache.lucene.analysis.miscellaneous.ASCIIFoldingFilterFactory; //导入依赖的package包/类
/**
* Ensure the ASCIIFoldingFilterFactory works
*/
public void testASCIIFolding() throws Exception {
Reader reader = new StringReader("Česká");
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
ASCIIFoldingFilterFactory factory = new ASCIIFoldingFilterFactory();
factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
Map<String, String> args = Collections.emptyMap();
factory.init(args);
TokenStream stream = factory.create(tokenizer);
assertTokenStreamContents(stream, new String[] { "Ceska" });
}
示例3: testDefaultCopiedToMulti
import org.apache.lucene.analysis.miscellaneous.ASCIIFoldingFilterFactory; //导入依赖的package包/类
@Test
public void testDefaultCopiedToMulti() {
SchemaField field = h.getCore().getSchema().getField("content_ws");
Analyzer analyzer = ((TextField)field.getType()).getMultiTermAnalyzer();
assertTrue(analyzer instanceof TokenizerChain);
assertTrue(((TokenizerChain) analyzer).getTokenizerFactory() instanceof KeywordTokenizerFactory);
TokenizerChain tc = (TokenizerChain) analyzer;
for (TokenFilterFactory factory : tc.getTokenFilterFactories()) {
assertTrue((factory instanceof ASCIIFoldingFilterFactory) || (factory instanceof LowerCaseFilterFactory));
}
assertTrue(tc.getCharFilterFactories() == null);
}
示例4: registerWithPrefix
import org.apache.lucene.analysis.miscellaneous.ASCIIFoldingFilterFactory; //导入依赖的package包/类
protected void registerWithPrefix(String prefix, LuceneAnalyzerDefinitionRegistryBuilder builder) {
builder.analyzer(prefix + HibernateSearchAnalyzer.KEYWORD).tokenizer(KeywordTokenizerFactory.class);
builder.analyzer(prefix + HibernateSearchAnalyzer.KEYWORD_CLEAN).tokenizer(KeywordTokenizerFactory.class)
.tokenFilter(ASCIIFoldingFilterFactory.class)
.tokenFilter(LowerCaseFilterFactory.class);
builder.analyzer(prefix + HibernateSearchAnalyzer.TEXT).tokenizer(WhitespaceTokenizerFactory.class)
.tokenFilter(ASCIIFoldingFilterFactory.class)
.tokenFilter(WordDelimiterFilterFactory.class)
.param("generateWordParts", "1")
.param("generateNumberParts", "1")
.param("catenateWords", "0")
.param("catenateNumbers", "0")
.param("catenateAll", "0")
.param("splitOnCaseChange", "0")
.param("splitOnNumerics", "0")
.param("preserveOriginal", "1")
.tokenFilter(LowerCaseFilterFactory.class);
builder.analyzer(prefix + HibernateSearchAnalyzer.TEXT_STEMMING).tokenizer(WhitespaceTokenizerFactory.class)
.tokenFilter(ASCIIFoldingFilterFactory.class)
.tokenFilter(WordDelimiterFilterFactory.class)
.param("generateWordParts", "1")
.param("generateNumberParts", "1")
.param("catenateWords", "0")
.param("catenateNumbers", "0")
.param("catenateAll", "0")
.param("splitOnCaseChange", "0")
.param("splitOnNumerics", "0")
.param("preserveOriginal", "1")
.tokenFilter(LowerCaseFilterFactory.class)
.tokenFilter(CoreFrenchMinimalStemFilterFactory.class);
builder.analyzer(prefix + HibernateSearchAnalyzer.TEXT_SORT).tokenizer(KeywordTokenizerFactory.class)
.tokenFilter(ASCIIFoldingFilterFactory.class)
.tokenFilter(LowerCaseFilterFactory.class)
.tokenFilter(PatternReplaceFilterFactory.class)
.param("pattern", "('-&\\.,\\(\\))")
.param("replacement", " ")
.param("replace", "all")
.tokenFilter(PatternReplaceFilterFactory.class)
.param("pattern", "([^0-9\\p{L} ])")
.param("replacement", "")
.param("replace", "all")
.tokenFilter(TrimFilterFactory.class);
}