public virtual void TestMatching()
{
b = new SynonymMap.Builder(true);
const bool keepOrig = false;
Add("a b", "ab", keepOrig);
Add("a c", "ac", keepOrig);
Add("a", "aa", keepOrig);
Add("b", "bb", keepOrig);
Add("z x c v", "zxcv", keepOrig);
Add("x c", "xc", keepOrig);
SynonymMap map = b.Build();
Analyzer a = new AnalyzerAnonymousInnerClassHelper6(this, map);
CheckOneTerm(a, "$", "$");
CheckOneTerm(a, "a", "aa");
CheckOneTerm(a, "b", "bb");
AssertAnalyzesTo(a, "a $", new string[] { "aa", "$" }, new int[] { 1, 1 });
AssertAnalyzesTo(a, "$ a", new string[] { "$", "aa" }, new int[] { 1, 1 });
AssertAnalyzesTo(a, "a a", new string[] { "aa", "aa" }, new int[] { 1, 1 });
AssertAnalyzesTo(a, "z x c v", new string[] { "zxcv" }, new int[] { 1 });
AssertAnalyzesTo(a, "z x c $", new string[] { "z", "xc", "$" }, new int[] { 1, 1, 1 });
}
public virtual void TestVersion40()
{
Analyzer a = new AnalyzerAnonymousInnerClassHelper6(this);
// U+061C is a new combining mark in 6.3, found using "[[\p{WB:Format}\p{WB:Extend}]&[^\p{Age:6.2}]]"
// on the online UnicodeSet utility: <http://unicode.org/cldr/utility/list-unicodeset.jsp>
AssertAnalyzesTo(a, "this is just a t\u061Cst [email protected]", new string[] { "this", "is", "just", "a", "t", "st", "*****@*****.**" });
}
public virtual void TestLetterUnicodeHuge()
{
Random random = Random;
int maxLength = 4300; // CharTokenizer.IO_BUFFER_SIZE + fudge
MockAnalyzer left = new MockAnalyzer(random, jvmLetter, false);
left.MaxTokenLength = 255; // match CharTokenizer's max token length
Analyzer right = new AnalyzerAnonymousInnerClassHelper6(this);
int numIterations = AtLeast(50);
for (int i = 0; i < numIterations; i++)
{
string s = TestUtil.RandomUnicodeString(random, maxLength);
assertEquals(s, left.GetTokenStream("foo", newStringReader(s)), right.GetTokenStream("foo", newStringReader(s)));
}
}
public virtual void TestMockGraphTokenFilterAfterHolesRandom()
{
for (int iter = 0; iter < 10 * RANDOM_MULTIPLIER; iter++)
{
if (VERBOSE)
{
Console.WriteLine("\nTEST: iter=" + iter);
}
// Make new analyzer each time, because MGTF has fixed
// seed:
Analyzer a = new AnalyzerAnonymousInnerClassHelper6(this);
Random random = Random;
CheckRandomData(random, a, 5, AtLeast(100));
}
}
/// <summary>
/// blast some random strings through the analyzer </summary>
public virtual void TestRandomStrings()
{
int numIterations = AtLeast(5);
for (int i = 0; i < numIterations; i++)
{
WordDelimiterFlags flags = (WordDelimiterFlags)Random.Next(512);
CharArraySet protectedWords;
if (Random.nextBoolean())
{
protectedWords = new CharArraySet(TEST_VERSION_CURRENT, new string[] { "a", "b", "cd" }, false);
}
else
{
protectedWords = null;
}
Analyzer a = new AnalyzerAnonymousInnerClassHelper6(this, flags, protectedWords);
CheckRandomData(Random, a, 1000 * RANDOM_MULTIPLIER);
}
}
/// <summary>
/// blast some random strings through the analyzer </summary>
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testRandomStrings() throws Exception
public virtual void testRandomStrings()
{
int numIterations = atLeast(5);
for (int i = 0; i < numIterations; i++)
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int flags = random().nextInt(512);
int flags = random().Next(512);
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.util.CharArraySet protectedWords;
CharArraySet protectedWords;
if (random().nextBoolean())
{
protectedWords = new CharArraySet(TEST_VERSION_CURRENT, new HashSet<>("a", "b", "cd"), false);
}
else
{
protectedWords = null;
}
Analyzer a = new AnalyzerAnonymousInnerClassHelper6(this, flags, protectedWords);
checkRandomData(random(), a, 1000 * RANDOM_MULTIPLIER);
}
}
/// <summary>
/// blast some random strings through the analyzer </summary>
public virtual void TestRandomStrings()
{
int numIterations = AtLeast(5);
for (int i = 0; i < numIterations; i++)
{
int flags = Random().Next(512);
CharArraySet protectedWords;
if (Random().nextBoolean())
{
protectedWords = new CharArraySet(TEST_VERSION_CURRENT, new string[] { "a", "b", "cd" }, false);
}
else
{
protectedWords = null;
}
Analyzer a = new AnalyzerAnonymousInnerClassHelper6(this, flags, protectedWords);
CheckRandomData(Random(), a, 1000 * RANDOM_MULTIPLIER);
}
}
public virtual void TestMockGraphTokenFilterAfterHolesRandom()
{
for (int iter = 0; iter < 10 * RANDOM_MULTIPLIER; iter++)
{
if (VERBOSE)
{
Console.WriteLine("\nTEST: iter=" + iter);
}
// Make new analyzer each time, because MGTF has fixed
// seed:
Analyzer a = new AnalyzerAnonymousInnerClassHelper6(this);
Random random = Random();
CheckRandomData(random, a, 5, AtLeast(100));
}
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testLetterUnicodeHuge() throws Exception
public virtual void testLetterUnicodeHuge()
{
Random random = random();
int maxLength = 4300; // CharTokenizer.IO_BUFFER_SIZE + fudge
MockAnalyzer left = new MockAnalyzer(random, jvmLetter, false);
left.MaxTokenLength = 255; // match CharTokenizer's max token length
Analyzer right = new AnalyzerAnonymousInnerClassHelper6(this);
int numIterations = atLeast(50);
for (int i = 0; i < numIterations; i++)
{
string s = TestUtil.randomUnicodeString(random, maxLength);
assertEquals(s, left.tokenStream("foo", newStringReader(s)), right.tokenStream("foo", newStringReader(s)));
}
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testMatching() throws Exception
public virtual void testMatching()
{
b = new SynonymMap.Builder(true);
const bool keepOrig = false;
add("a b", "ab", keepOrig);
add("a c", "ac", keepOrig);
add("a", "aa", keepOrig);
add("b", "bb", keepOrig);
add("z x c v", "zxcv", keepOrig);
add("x c", "xc", keepOrig);
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final SynonymMap map = b.build();
SynonymMap map = b.build();
Analyzer a = new AnalyzerAnonymousInnerClassHelper6(this, map);
checkOneTerm(a, "$", "$");
checkOneTerm(a, "a", "aa");
checkOneTerm(a, "b", "bb");
assertAnalyzesTo(a, "a $", new string[] {"aa", "$"}, new int[] {1, 1});
assertAnalyzesTo(a, "$ a", new string[] {"$", "aa"}, new int[] {1, 1});
assertAnalyzesTo(a, "a a", new string[] {"aa", "aa"}, new int[] {1, 1});
assertAnalyzesTo(a, "z x c v", new string[] {"zxcv"}, new int[] {1});
assertAnalyzesTo(a, "z x c $", new string[] {"z", "xc", "$"}, new int[] {1, 1, 1});
}
public virtual void TestMatching()
{
b = new SynonymMap.Builder(true);
const bool keepOrig = false;
Add("a b", "ab", keepOrig);
Add("a c", "ac", keepOrig);
Add("a", "aa", keepOrig);
Add("b", "bb", keepOrig);
Add("z x c v", "zxcv", keepOrig);
Add("x c", "xc", keepOrig);
SynonymMap map = b.Build();
Analyzer a = new AnalyzerAnonymousInnerClassHelper6(this, map);
CheckOneTerm(a, "$", "$");
CheckOneTerm(a, "a", "aa");
CheckOneTerm(a, "b", "bb");
AssertAnalyzesTo(a, "a $", new string[] { "aa", "$" }, new int[] { 1, 1 });
AssertAnalyzesTo(a, "$ a", new string[] { "$", "aa" }, new int[] { 1, 1 });
AssertAnalyzesTo(a, "a a", new string[] { "aa", "aa" }, new int[] { 1, 1 });
AssertAnalyzesTo(a, "z x c v", new string[] { "zxcv" }, new int[] { 1 });
AssertAnalyzesTo(a, "z x c $", new string[] { "z", "xc", "$" }, new int[] { 1, 1, 1 });
}
public virtual void TestVersion40()
{
Analyzer a = new AnalyzerAnonymousInnerClassHelper6(this);
// U+061C is a new combining mark in 6.3, found using "[[\p{WB:Format}\p{WB:Extend}]&[^\p{Age:6.2}]]"
// on the online UnicodeSet utility: <http://unicode.org/cldr/utility/list-unicodeset.jsp>
AssertAnalyzesTo(a, "this is just a t\u061Cst [email protected]", new string[] { "this", "is", "just", "a", "t", "st", "*****@*****.**" });
}
