/*
* Test secondary strength, for english case is not significant.
*/
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testSecondaryStrength() throws Exception
public virtual void testSecondaryStrength()
{
string upperCase = "TESTING";
string lowerCase = "testing";
TokenFilterFactory factory = tokenFilterFactory("CollationKey", "language", "en", "strength", "secondary", "decomposition", "no");
TokenStream tsUpper = factory.create(new MockTokenizer(new StringReader(upperCase), MockTokenizer.KEYWORD, false));
TokenStream tsLower = factory.create(new MockTokenizer(new StringReader(lowerCase), MockTokenizer.KEYWORD, false));
assertCollatesToSame(tsUpper, tsLower);
}
/*
* Test usage of the K decomposition option for unicode normalization.
* This works even with identical strength.
*/
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testFullDecomposition() throws Exception
public virtual void testFullDecomposition()
{
string fullWidth = "Ｔｅｓｔｉｎｇ";
string halfWidth = "Testing";
TokenFilterFactory factory = tokenFilterFactory("CollationKey", "language", "zh", "strength", "identical", "decomposition", "full");
TokenStream tsFull = factory.create(new MockTokenizer(new StringReader(fullWidth), MockTokenizer.KEYWORD, false));
TokenStream tsHalf = factory.create(new MockTokenizer(new StringReader(halfWidth), MockTokenizer.KEYWORD, false));
assertCollatesToSame(tsFull, tsHalf);
}
/*
* Test usage of the decomposition option for unicode normalization.
*/
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testNormalization() throws Exception
public virtual void testNormalization()
{
string turkishUpperCase = "I W\u0049\u0307LL USE TURKİSH CASING";
string turkishLowerCase = "ı will use turkish casıng";
TokenFilterFactory factory = tokenFilterFactory("CollationKey", "language", "tr", "strength", "primary", "decomposition", "canonical");
TokenStream tsUpper = factory.create(new MockTokenizer(new StringReader(turkishUpperCase), MockTokenizer.KEYWORD, false));
TokenStream tsLower = factory.create(new MockTokenizer(new StringReader(turkishLowerCase), MockTokenizer.KEYWORD, false));
assertCollatesToSame(tsUpper, tsLower);
}
/*
* Turkish has some funny casing.
* This test shows how you can solve this kind of thing easily with collation.
* Instead of using LowerCaseFilter, use a turkish collator with primary strength.
* Then things will sort and match correctly.
*/
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testBasicUsage() throws Exception
public virtual void testBasicUsage()
{
string turkishUpperCase = "I WİLL USE TURKİSH CASING";
string turkishLowerCase = "ı will use turkish casıng";
TokenFilterFactory factory = tokenFilterFactory("CollationKey", "language", "tr", "strength", "primary");
TokenStream tsUpper = factory.create(new MockTokenizer(new StringReader(turkishUpperCase), MockTokenizer.KEYWORD, false));
TokenStream tsLower = factory.create(new MockTokenizer(new StringReader(turkishLowerCase), MockTokenizer.KEYWORD, false));
assertCollatesToSame(tsUpper, tsLower);
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testCreationWithWhiteList() throws Exception
public virtual void testCreationWithWhiteList()
{
TokenFilterFactory factory = tokenFilterFactory("Type", "types", "stoptypes-1.txt, stoptypes-2.txt", "enablePositionIncrements", "true", "useWhitelist", "true");
NumericTokenStream input = new NumericTokenStream();
input.IntValue = 123;
factory.create(input);
}
/// <summary>
/// checks for synonyms of "second" in synonyms-wordnet.txt </summary>
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: private void checkWordnetSynonyms(org.apache.lucene.analysis.util.TokenFilterFactory factory) throws Exception
private void checkWordnetSynonyms(TokenFilterFactory factory)
{
Reader reader = new StringReader("second");
TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
stream = factory.create(stream);
assertTrue(stream is SynonymFilter);
assertTokenStreamContents(stream, new string[] { "second", "2nd", "two" }, new int[] { 1, 0, 0 });
}
/// <summary>
/// checks for synonyms of "GB" in synonyms.txt </summary>
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: private void checkSolrSynonyms(org.apache.lucene.analysis.util.TokenFilterFactory factory) throws Exception
private void checkSolrSynonyms(TokenFilterFactory factory)
{
Reader reader = new StringReader("GB");
TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
stream = factory.create(stream);
assertTrue(stream is SynonymFilter);
assertTokenStreamContents(stream, new string[] { "GB", "gib", "gigabyte", "gigabytes" }, new int[] { 1, 0, 0, 0 });
}
protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader)
{
Tokenizer tf = tokenizer.create(reader);
if (tokenfilter != null)
{
return(new TokenStreamComponents(tf, tokenfilter.create(tf)));
}
else
{
return(new TokenStreamComponents(tf));
}
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void test() throws Exception
public virtual void test()
{
IList <Type> analysisClasses = new List <Type>();
((List <Type>)analysisClasses).AddRange(TestRandomChains.getClassesForPackage("org.apache.lucene.analysis"));
((List <Type>)analysisClasses).AddRange(TestRandomChains.getClassesForPackage("org.apache.lucene.collation"));
foreach (Class c in analysisClasses)
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int modifiers = c.getModifiers();
int modifiers = c.Modifiers;
if (Modifier.isAbstract(modifiers) || !Modifier.isPublic(modifiers) || c.Synthetic || c.AnonymousClass || c.MemberClass || c.Interface || testComponents.Contains(c) || crazyComponents.Contains(c) || oddlyNamedComponents.Contains(c) || deprecatedDuplicatedComponents.Contains(c) || c.isAnnotationPresent(typeof(Deprecated)) || !(c.IsSubclassOf(typeof(Tokenizer)) || c.IsSubclassOf(typeof(TokenFilter)) || c.IsSubclassOf(typeof(CharFilter))))
{ // deprecated ones are typically back compat hacks
// don't waste time with abstract classes
continue;
}
IDictionary <string, string> args = new Dictionary <string, string>();
args["luceneMatchVersion"] = TEST_VERSION_CURRENT.ToString();
if (c.IsSubclassOf(typeof(Tokenizer)))
{
string clazzName = c.SimpleName;
assertTrue(clazzName.EndsWith("Tokenizer", StringComparison.Ordinal));
string simpleName = clazzName.Substring(0, clazzName.Length - 9);
assertNotNull(TokenizerFactory.lookupClass(simpleName));
TokenizerFactory instance = null;
try
{
instance = TokenizerFactory.forName(simpleName, args);
assertNotNull(instance);
if (instance is ResourceLoaderAware)
{
((ResourceLoaderAware)instance).inform(loader);
}
assertSame(c, instance.create(new StringReader("")).GetType());
}
catch (System.ArgumentException e)
{
if (e.InnerException is NoSuchMethodException)
{
// there is no corresponding ctor available
throw e;
}
// TODO: For now pass because some factories have not yet a default config that always works
}
}
else if (c.IsSubclassOf(typeof(TokenFilter)))
{
string clazzName = c.SimpleName;
assertTrue(clazzName.EndsWith("Filter", StringComparison.Ordinal));
string simpleName = clazzName.Substring(0, clazzName.Length - (clazzName.EndsWith("TokenFilter", StringComparison.Ordinal) ? 11 : 6));
assertNotNull(TokenFilterFactory.lookupClass(simpleName));
TokenFilterFactory instance = null;
try
{
instance = TokenFilterFactory.forName(simpleName, args);
assertNotNull(instance);
if (instance is ResourceLoaderAware)
{
((ResourceLoaderAware)instance).inform(loader);
}
//JAVA TO C# CONVERTER TODO TASK: Java wildcard generics are not converted to .NET:
//ORIGINAL LINE: Class<? extends org.apache.lucene.analysis.TokenStream> createdClazz = instance.create(new KeywordTokenizer(new java.io.StringReader(""))).getClass();
Type <?> createdClazz = instance.create(new KeywordTokenizer(new StringReader(""))).GetType();
// only check instance if factory have wrapped at all!
if (typeof(KeywordTokenizer) != createdClazz)
{
assertSame(c, createdClazz);
}
}
catch (System.ArgumentException e)
{
if (e.InnerException is NoSuchMethodException)
{
// there is no corresponding ctor available
throw e;
}
// TODO: For now pass because some factories have not yet a default config that always works
}
}
else if (c.IsSubclassOf(typeof(CharFilter)))
{
string clazzName = c.SimpleName;
assertTrue(clazzName.EndsWith("CharFilter", StringComparison.Ordinal));
string simpleName = clazzName.Substring(0, clazzName.Length - 10);
assertNotNull(CharFilterFactory.lookupClass(simpleName));
CharFilterFactory instance = null;
try
{
instance = CharFilterFactory.forName(simpleName, args);
assertNotNull(instance);
if (instance is ResourceLoaderAware)
{
((ResourceLoaderAware)instance).inform(loader);
}
//JAVA TO C# CONVERTER TODO TASK: Java wildcard generics are not converted to .NET:
//ORIGINAL LINE: Class<? extends java.io.Reader> createdClazz = instance.create(new java.io.StringReader("")).getClass();
Type <?> createdClazz = instance.create(new StringReader("")).GetType();
// only check instance if factory have wrapped at all!
if (typeof(StringReader) != createdClazz)
{
assertSame(c, createdClazz);
}
}
catch (System.ArgumentException e)
{
if (e.InnerException is NoSuchMethodException)
{
// there is no corresponding ctor available
throw e;
}
// TODO: For now pass because some factories have not yet a default config that always works
}
}
}
}
