static StopAnalyzer()
{
IList <string> stopWords = Arrays.AsList("a", "an", "and", "are", "as", "at", "be", "but", "by", "for", "if", "in", "into", "is", "it", "no", "not", "of", "on", "or", "such", "that", "the", "their", "then", "there", "these", "they", "this", "to", "was", "will", "with");
var stopSet = new CharArraySet(Version.LUCENE_CURRENT, stopWords, false);
ENGLISH_STOP_WORDS_SET = CharArraySet.unmodifiableSet(stopSet);
}
public DutchAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionTable, CharArrayMap <string> stemOverrideDict)
{
this.matchVersion = matchVersion;
this.stoptable = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion, stopwords));
this.excltable = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion, stemExclusionTable));
if (stemOverrideDict.Empty || !matchVersion.onOrAfter(Version.LUCENE_31))
{
this.stemdict = null;
this.origStemdict = CharArrayMap.unmodifiableMap(CharArrayMap.copy(matchVersion, stemOverrideDict));
}
else
{
this.origStemdict = null;
// we don't need to ignore case here since we lowercase in this analyzer anyway
StemmerOverrideFilter.Builder builder = new StemmerOverrideFilter.Builder(false);
CharArrayMap <string> .EntryIterator iter = stemOverrideDict.entrySet().GetEnumerator();
CharsRef spare = new CharsRef();
while (iter.hasNext())
{
char[] nextKey = iter.nextKey();
spare.copyChars(nextKey, 0, nextKey.Length);
builder.add(spare, iter.currentValue());
}
try
{
this.stemdict = builder.build();
}
catch (IOException ex)
{
throw new Exception("can not build stem dict", ex);
}
}
}
public virtual void testUnmodifiableSet()
{
CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 10, true);
set.addAll(TEST_STOP_WORDS);
set.add(Convert.ToInt32(1));
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int size = set.size();
int size = set.size();
set = CharArraySet.unmodifiableSet(set);
assertEquals("Set size changed due to unmodifiableSet call", size, set.size());
foreach (string stopword in TEST_STOP_WORDS)
{
assertTrue(set.contains(stopword));
}
assertTrue(set.contains(Convert.ToInt32(1)));
assertTrue(set.contains("1"));
assertTrue(set.contains(new char[] { '1' }));
try
{
CharArraySet.unmodifiableSet(null);
fail("can not make null unmodifiable");
}
catch (System.NullReferenceException)
{
// expected
}
}
public virtual void testNonZeroOffset()
{
string[] words = new string[] { "Hello", "World", "this", "is", "a", "test" };
char[] findme = "xthisy".ToCharArray();
CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 10, true);
set.addAll(words);
assertTrue(set.contains(findme, 1, 4));
assertTrue(set.contains(new string(findme, 1, 4)));
// test unmodifiable
set = CharArraySet.unmodifiableSet(set);
assertTrue(set.contains(findme, 1, 4));
assertTrue(set.contains(new string(findme, 1, 4)));
}
public virtual void testObjectContains()
{
CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 10, true);
int? val = Convert.ToInt32(1);
set.add(val);
assertTrue(set.contains(val));
assertTrue(set.contains(new int?(1))); // another integer
assertTrue(set.contains("1"));
assertTrue(set.contains(new char[] { '1' }));
// test unmodifiable
set = CharArraySet.unmodifiableSet(set);
assertTrue(set.contains(val));
assertTrue(set.contains(new int?(1))); // another integer
assertTrue(set.contains("1"));
assertTrue(set.contains(new char[] { '1' }));
}
/// <summary>
/// Builds an analyzer with the given stop words. If a non-empty stem exclusion set is
/// provided this analyzer will add a <seealso cref="SetKeywordMarkerFilter"/> before
/// stemming.
/// </summary>
/// <param name="matchVersion"> lucene compatibility version </param>
/// <param name="stopwords"> a stopword set </param>
/// <param name="stemExclusionSet"> a set of terms not to be stemmed </param>
public IrishAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) : base(matchVersion, stopwords)
{
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion, stemExclusionSet));
}
/// <summary>
/// Builds the named analyzer with the given stop words. </summary>
public SnowballAnalyzer(Version matchVersion, string name, CharArraySet stopWords) : this(matchVersion, name)
{
stopSet = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion, stopWords));
}
/// <summary>
/// Builds an analyzer with the given stop words
/// </summary>
/// <param name="matchVersion">
/// lucene compatibility version </param>
/// <param name="stopwords">
/// a stopword set </param>
/// <param name="stemExclutionSet">
/// a stemming exclusion set </param>
public FrenchAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclutionSet) : base(matchVersion, stopwords)
{
this.excltable = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion, stemExclutionSet));
}
/// <summary>
/// Builds an analyzer with the given stop words and a set of work to be
/// excluded from the <seealso cref="CzechStemFilter"/>.
/// </summary>
/// <param name="matchVersion"> Lucene version to match See
/// <seealso cref="<a href="#version">above</a>"/> </param>
/// <param name="stopwords"> a stopword set </param>
/// <param name="stemExclusionTable"> a stemming exclusion set </param>
public CzechAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionTable) : base(matchVersion, stopwords)
{
this.stemExclusionTable = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion, stemExclusionTable));
}
/// <summary>
/// Builds an analyzer with the given stop words and stemming exclusion words
/// </summary>
/// <param name="matchVersion">
/// lucene compatibility version </param>
/// <param name="stopwords">
/// a stopword set </param>
public BrazilianAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) : this(matchVersion, stopwords)
{
excltable = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion, stemExclusionSet));
}
public virtual void testModifyOnUnmodifiable()
{
CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 10, true);
set.addAll(TEST_STOP_WORDS);
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int size = set.size();
int size = set.size();
set = CharArraySet.unmodifiableSet(set);
assertEquals("Set size changed due to unmodifiableSet call", size, set.size());
string NOT_IN_SET = "SirGallahad";
assertFalse("Test String already exists in set", set.contains(NOT_IN_SET));
try
{
set.add(NOT_IN_SET.ToCharArray());
fail("Modified unmodifiable set");
}
catch (System.NotSupportedException)
{
// expected
assertFalse("Test String has been added to unmodifiable set", set.contains(NOT_IN_SET));
assertEquals("Size of unmodifiable set has changed", size, set.size());
}
try
{
set.add(NOT_IN_SET);
fail("Modified unmodifiable set");
}
catch (System.NotSupportedException)
{
// expected
assertFalse("Test String has been added to unmodifiable set", set.contains(NOT_IN_SET));
assertEquals("Size of unmodifiable set has changed", size, set.size());
}
try
{
set.add(new StringBuilder(NOT_IN_SET));
fail("Modified unmodifiable set");
}
catch (System.NotSupportedException)
{
// expected
assertFalse("Test String has been added to unmodifiable set", set.contains(NOT_IN_SET));
assertEquals("Size of unmodifiable set has changed", size, set.size());
}
try
{
set.clear();
fail("Modified unmodifiable set");
}
catch (System.NotSupportedException)
{
// expected
assertFalse("Changed unmodifiable set", set.contains(NOT_IN_SET));
assertEquals("Size of unmodifiable set has changed", size, set.size());
}
try
{
set.add((object)NOT_IN_SET);
fail("Modified unmodifiable set");
}
catch (System.NotSupportedException)
{
// expected
assertFalse("Test String has been added to unmodifiable set", set.contains(NOT_IN_SET));
assertEquals("Size of unmodifiable set has changed", size, set.size());
}
// This test was changed in 3.1, as a contains() call on the given Collection using the "correct" iterator's
// current key (now a char[]) on a Set<String> would not hit any element of the CAS and therefor never call
// remove() on the iterator
try
{
set.removeAll(new CharArraySet(TEST_VERSION_CURRENT, TEST_STOP_WORDS, true));
fail("Modified unmodifiable set");
}
catch (System.NotSupportedException)
{
// expected
assertEquals("Size of unmodifiable set has changed", size, set.size());
}
try
{
set.retainAll(new CharArraySet(TEST_VERSION_CURRENT, NOT_IN_SET, true));
fail("Modified unmodifiable set");
}
catch (System.NotSupportedException)
{
// expected
assertEquals("Size of unmodifiable set has changed", size, set.size());
}
try
{
set.addAll(NOT_IN_SET);
fail("Modified unmodifiable set");
}
catch (System.NotSupportedException)
{
// expected
assertFalse("Test String has been added to unmodifiable set", set.contains(NOT_IN_SET));
}
for (int i = 0; i < TEST_STOP_WORDS.Length; i++)
{
assertTrue(set.contains(TEST_STOP_WORDS[i]));
}
}
