Java 类org.apache.lucene.analysis.util.ClasspathResourceLoader 实例源码

项目：IK-Analyzer-2012FF 文件：IKSynonymAnalyzer.java

@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
    Tokenizer token = new IKTokenizer(reader, useSmart);
    Map<String, String> paramsMap = new HashMap<String, String>();
    Configuration cfg = DefaultConfig.getInstance();
    paramsMap.put("luceneMatchVersion", luceneMatchVersion.toString());
    paramsMap.put("synonyms", cfg.getExtSynonymDictionarys().get(0));
    paramsMap.put("ignoreCase", "true");
    SynonymFilterFactory factory = new SynonymFilterFactory(paramsMap);
    ResourceLoader loader = new ClasspathResourceLoader();
    try {
        factory.inform(loader);
    } catch (IOException e) {
        e.printStackTrace();
    }
    return new TokenStreamComponents(token, factory.create(token));
}

项目：search 文件：TestKeepFilterFactory.java

public void testInform() throws Exception {
  ResourceLoader loader = new ClasspathResourceLoader(getClass());
  assertTrue("loader is null and it shouldn't be", loader != null);
  KeepWordFilterFactory factory = (KeepWordFilterFactory) tokenFilterFactory("KeepWord",
      "words", "keep-1.txt",
      "ignoreCase", "true");
  CharArraySet words = factory.getWords();
  assertTrue("words is null and it shouldn't be", words != null);
  assertTrue("words Size: " + words.size() + " is not: " + 2, words.size() == 2);

  factory = (KeepWordFilterFactory) tokenFilterFactory("KeepWord",
      "words", "keep-1.txt, keep-2.txt",
      "ignoreCase", "true");
  words = factory.getWords();
  assertTrue("words is null and it shouldn't be", words != null);
  assertTrue("words Size: " + words.size() + " is not: " + 4, words.size() == 4);
}

项目：solr-jdbc 文件：JdbcStopFilterFactoryTest.java

/**
 * Test for {@link JdbcSynonymFilterFactory#create(TokenStream)}.
 */
@Test
public void create() throws Exception {
   Map<String, String> args = new HashMap<>();
   args.put(AbstractAnalysisFactory.LUCENE_MATCH_VERSION_PARAM, Version.LATEST.toString());
   args.put(JdbcReaderFactoryParams.DATASOURCE, "java:comp/env/dataSource");
   args.put(JdbcReaderFactoryParams.SQL, "select stopword from stopwords");

   // White space tokenizer, to lower case tokenizer.
   MockTokenizer tokenizer = new MockTokenizer();
   tokenizer.setReader(new StringReader("test1 somestring test2 anotherstring"));

   JdbcStopFilterFactory factory = new JdbcStopFilterFactory(args);
   factory.inform(new ClasspathResourceLoader(getClass().getClassLoader()));

   try (TokenStream stream = factory.create(tokenizer)) {
      CharTermAttribute attribute = stream.addAttribute(CharTermAttribute.class);
      stream.reset();
      assertTrue(stream.incrementToken());
      assertEquals("test1", attribute.toString());
      assertTrue(stream.incrementToken());
      assertEquals("test2", attribute.toString());
      assertFalse(stream.incrementToken());
      stream.end();
   }
}

项目：NYBC 文件：TestPhoneticFilterFactory.java

/**
 * Case: default
 */
public void testFactory() throws IOException {
  Map<String,String> args = new HashMap<String, String>();

  PhoneticFilterFactory ff = new PhoneticFilterFactory();

  args.put( PhoneticFilterFactory.ENCODER, "Metaphone" );
  ff.init( args );
  ff.inform(new ClasspathResourceLoader(ff.getClass()));
  assertTrue( ff.getEncoder() instanceof Metaphone );
  assertTrue( ff.inject ); // default

  args.put( PhoneticFilterFactory.INJECT, "false" );
  ff.init( args );
  ff.inform(new ClasspathResourceLoader(ff.getClass()));
  assertFalse( ff.inject );

  args.put( PhoneticFilterFactory.MAX_CODE_LENGTH, "2");
  ff.init(args);
  ff.inform(new ClasspathResourceLoader(ff.getClass()));
  assertEquals(2, ((Metaphone) ff.getEncoder()).getMaxCodeLen());
}

项目：NYBC 文件：TestHyphenationCompoundWordTokenFilterFactory.java

/**
 * Ensure the factory works with hyphenation grammar+dictionary: using default options.
 */
public void testHyphenationWithDictionary() throws Exception {
  Reader reader = new StringReader("min veninde som er lidt af en læsehest");
  Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
  HyphenationCompoundWordTokenFilterFactory factory = new HyphenationCompoundWordTokenFilterFactory();
  ResourceLoader loader = new ClasspathResourceLoader(getClass());
  Map<String,String> args = new HashMap<String,String>();
  args.put("hyphenator", "da_UTF8.xml");
  args.put("dictionary", "da_compoundDictionary.txt");
  factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
  factory.init(args);
  factory.inform(loader);
  TokenStream stream = factory.create(tokenizer);

  assertTokenStreamContents(stream, 
      new String[] { "min", "veninde", "som", "er", "lidt", "af", "en", "læsehest", "læse", "hest" },
      new int[] { 1, 1, 1, 1, 1, 1, 1, 1, 0, 0 }
  );
}

项目：NYBC 文件：TestHyphenationCompoundWordTokenFilterFactory.java

/**
 * Ensure the factory works with no dictionary: using hyphenation grammar only.
 * Also change the min/max subword sizes from the default. When using no dictionary,
 * its generally necessary to tweak these, or you get lots of expansions.
 */
public void testHyphenationOnly() throws Exception {
  Reader reader = new StringReader("basketballkurv");
  Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
  HyphenationCompoundWordTokenFilterFactory factory = new HyphenationCompoundWordTokenFilterFactory();
  ResourceLoader loader = new ClasspathResourceLoader(getClass());
  Map<String,String> args = new HashMap<String,String>();
  args.put("hyphenator", "da_UTF8.xml");
  args.put("minSubwordSize", "2");
  args.put("maxSubwordSize", "4");
  factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
  factory.init(args);
  factory.inform(loader);
  TokenStream stream = factory.create(tokenizer);

  assertTokenStreamContents(stream,
      new String[] { "basketballkurv", "ba", "sket", "bal", "ball", "kurv" }
  );
}

项目：NYBC 文件：TestCommonGramsFilterFactory.java

/**
 * If no words are provided, then a set of english default stopwords is used.
 */
public void testDefaults() throws Exception {
  ResourceLoader loader = new ClasspathResourceLoader(TestStopFilter.class);
  assertTrue("loader is null and it shouldn't be", loader != null);
  CommonGramsFilterFactory factory = new CommonGramsFilterFactory();
  factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
  Map<String, String> args = Collections.emptyMap();
  factory.init(args);
  factory.inform(loader);
  CharArraySet words = factory.getCommonWords();
  assertTrue("words is null and it shouldn't be", words != null);
  assertTrue(words.contains("the"));
  Tokenizer tokenizer = new MockTokenizer(new StringReader("testing the factory"), MockTokenizer.WHITESPACE, false);
  TokenStream stream = factory.create(tokenizer);
  assertTokenStreamContents(stream, 
      new String[] { "testing", "testing_the", "the", "the_factory", "factory" });
}

项目：NYBC 文件：TestCommonGramsQueryFilterFactory.java

/**
 * If no words are provided, then a set of english default stopwords is used.
 */
public void testDefaults() throws Exception {
  ResourceLoader loader = new ClasspathResourceLoader(TestStopFilter.class);
  assertTrue("loader is null and it shouldn't be", loader != null);
  CommonGramsQueryFilterFactory factory = new CommonGramsQueryFilterFactory();
  factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
  Map<String, String> args = Collections.emptyMap();
  factory.init(args);
  factory.inform(loader);
  CharArraySet words = factory.getCommonWords();
  assertTrue("words is null and it shouldn't be", words != null);
  assertTrue(words.contains("the"));
  Tokenizer tokenizer = new MockTokenizer(new StringReader("testing the factory"), MockTokenizer.WHITESPACE, false);
  TokenStream stream = factory.create(tokenizer);
  assertTokenStreamContents(stream, 
      new String[] { "testing_the", "the_factory" });
}

项目：NYBC 文件：TestTypeTokenFilterFactory.java

@Test
public void testInform() throws Exception {
  ResourceLoader loader = new ClasspathResourceLoader(getClass());
  TypeTokenFilterFactory factory = new TypeTokenFilterFactory();
  Map<String, String> args = new HashMap<String, String>();
  args.put("types", "stoptypes-1.txt");
  args.put("enablePositionIncrements", "true");
  factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
  factory.init(args);
  factory.inform(loader);
  Set<String> types = factory.getStopTypes();
  assertTrue("types is null and it shouldn't be", types != null);
  assertTrue("types Size: " + types.size() + " is not: " + 2, types.size() == 2);
  assertTrue("enablePositionIncrements was set to true but not correctly parsed", factory.isEnablePositionIncrements());

  factory = new TypeTokenFilterFactory();
  args.put("types", "stoptypes-1.txt, stoptypes-2.txt");
  args.put("enablePositionIncrements", "false");
  args.put("useWhitelist","true");
  factory.init(args);
  factory.inform(loader);
  types = factory.getStopTypes();
  assertTrue("types is null and it shouldn't be", types != null);
  assertTrue("types Size: " + types.size() + " is not: " + 4, types.size() == 4);
  assertTrue("enablePositionIncrements was set to false but not correctly parsed", !factory.isEnablePositionIncrements());
}

项目：solr-jdbc-synonyms 文件：JdbcStopFilterFactoryTest.java

/**
 * Test for {@link JdbcSynonymFilterFactory#create(TokenStream)}.
 */
@Test
public void create() throws Exception {
   Map<String, String> args = new HashMap<>();
   args.put(AbstractAnalysisFactory.LUCENE_MATCH_VERSION_PARAM, Version.LUCENE_5_0_0.toString());
   args.put(JdbcReaderFactoryParams.DATASOURCE, "java:comp/env/dataSource");
   args.put(JdbcReaderFactoryParams.SQL, "select stopword from stopwords");

   // White space tokenizer, to lower case tokenizer.
   MockTokenizer tokenizer = new MockTokenizer();
   tokenizer.setReader(new StringReader("test1 somestring test2 anotherstring"));

   JdbcStopFilterFactory factory = new JdbcStopFilterFactory(args);
   factory.inform(new ClasspathResourceLoader());

   try (TokenStream stream = factory.create(tokenizer)) {
      CharTermAttribute attribute = stream.addAttribute(CharTermAttribute.class);
      stream.reset();
      assertTrue(stream.incrementToken());
      assertEquals("test1", attribute.toString());
      assertTrue(stream.incrementToken());
      assertEquals("test2", attribute.toString());
      assertFalse(stream.incrementToken());
      stream.end();
   }
}

项目：Maskana-Gestor-de-Conocimiento 文件：TestKeepFilterFactory.java

public void testInform() throws Exception {
  ResourceLoader loader = new ClasspathResourceLoader(getClass());
  assertTrue("loader is null and it shouldn't be", loader != null);
  KeepWordFilterFactory factory = (KeepWordFilterFactory) tokenFilterFactory("KeepWord",
      "words", "keep-1.txt",
      "ignoreCase", "true");
  CharArraySet words = factory.getWords();
  assertTrue("words is null and it shouldn't be", words != null);
  assertTrue("words Size: " + words.size() + " is not: " + 2, words.size() == 2);

  factory = (KeepWordFilterFactory) tokenFilterFactory("KeepWord",
      "words", "keep-1.txt, keep-2.txt",
      "ignoreCase", "true");
  words = factory.getWords();
  assertTrue("words is null and it shouldn't be", words != null);
  assertTrue("words Size: " + words.size() + " is not: " + 4, words.size() == 4);
}

项目：search 文件：TestICUTokenizerFactory.java

public void testMixedText() throws Exception {
  Reader reader = new StringReader("การที่ได้ต้องแสดงว่างานดี  This is a test ກວ່າດອກ");
  ICUTokenizerFactory factory = new ICUTokenizerFactory(new HashMap<String,String>());
  factory.inform(new ClasspathResourceLoader(getClass()));
  TokenStream stream = factory.create(newAttributeFactory(), reader);
  assertTokenStreamContents(stream,
      new String[] { "การ", "ที่", "ได้", "ต้อง", "แสดง", "ว่า", "งาน", "ดี",
      "This", "is", "a", "test", "ກວ່າ", "ດອກ"});
}

项目：search 文件：TestICUTokenizerFactory.java

public void testTokenizeLatinDontBreakOnHyphens() throws Exception {
  Reader reader = new StringReader
      ("One-two punch.  Brang-, not brung-it.  This one--not that one--is the right one, -ish.");
  final Map<String,String> args = new HashMap<>();
  args.put(ICUTokenizerFactory.RULEFILES, "Latn:Latin-dont-break-on-hyphens.rbbi");
  ICUTokenizerFactory factory = new ICUTokenizerFactory(args);
  factory.inform(new ClasspathResourceLoader(getClass()));
  TokenStream stream = factory.create(newAttributeFactory(), reader);
  assertTokenStreamContents(stream,
      new String[] { "One-two", "punch",
          "Brang", "not", "brung-it",
          "This", "one", "not", "that", "one", "is", "the", "right", "one", "ish" });
}

项目：search 文件：TestICUTokenizerFactory.java

/**
 * Specify more than one script/rule file pair.
 * Override default DefaultICUTokenizerConfig Thai script tokenization.
 * Use the same rule file for both scripts.
 */
public void testKeywordTokenizeCyrillicAndThai() throws Exception {
  Reader reader = new StringReader
      ("Some English.  Немного русский.  ข้อความภาษาไทยเล็ก ๆ น้อย ๆ  More English.");
  final Map<String,String> args = new HashMap<>();
  args.put(ICUTokenizerFactory.RULEFILES, "Cyrl:KeywordTokenizer.rbbi,Thai:KeywordTokenizer.rbbi");
  ICUTokenizerFactory factory = new ICUTokenizerFactory(args);
  factory.inform(new ClasspathResourceLoader(getClass()));
  TokenStream stream = factory.create(newAttributeFactory(), reader);
  assertTokenStreamContents(stream, new String[] { "Some", "English",
      "Немного русский.  ",
      "ข้อความภาษาไทยเล็ก ๆ น้อย ๆ  ",
      "More", "English" });
}