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 testToString()
{
CharArraySet set = CharArraySet.copy(TEST_VERSION_CURRENT, Collections.singleton("test"));
assertEquals("[test]", set.ToString());
set.add("test2");
assertTrue(set.ToString().Contains(", "));
set = CharArraySet.copy(Version.LUCENE_30, Collections.singleton("test"));
assertEquals("[test]", set.ToString());
set.add("test2");
assertTrue(set.ToString().Contains(", "));
}
/// <summary>
/// Test the static #copy() function with a CharArraySet as a source
/// </summary>
public virtual void testCopyCharArraySet()
{
CharArraySet setIngoreCase = new CharArraySet(TEST_VERSION_CURRENT, 10, true);
CharArraySet setCaseSensitive = new CharArraySet(TEST_VERSION_CURRENT, 10, false);
IList <string> stopwords = TEST_STOP_WORDS;
IList <string> stopwordsUpper = new List <string>();
foreach (string @string in stopwords)
{
stopwordsUpper.Add(@string.ToUpper(Locale.ROOT));
}
setIngoreCase.addAll(TEST_STOP_WORDS);
setIngoreCase.add(Convert.ToInt32(1));
setCaseSensitive.addAll(TEST_STOP_WORDS);
setCaseSensitive.add(Convert.ToInt32(1));
CharArraySet copy = CharArraySet.copy(TEST_VERSION_CURRENT, setIngoreCase);
CharArraySet copyCaseSens = CharArraySet.copy(TEST_VERSION_CURRENT, setCaseSensitive);
assertEquals(setIngoreCase.size(), copy.size());
assertEquals(setCaseSensitive.size(), copy.size());
assertTrue(copy.containsAll(stopwords));
assertTrue(copy.containsAll(stopwordsUpper));
assertTrue(copyCaseSens.containsAll(stopwords));
foreach (string @string in stopwordsUpper)
{
assertFalse(copyCaseSens.contains(@string));
}
// test adding terms to the copy
IList <string> newWords = new List <string>();
foreach (string @string in stopwords)
{
newWords.Add(@string + "_1");
}
copy.addAll(newWords);
assertTrue(copy.containsAll(stopwords));
assertTrue(copy.containsAll(stopwordsUpper));
assertTrue(copy.containsAll(newWords));
// new added terms are not in the source set
foreach (string @string in newWords)
{
assertFalse(setIngoreCase.contains(@string));
assertFalse(setCaseSensitive.contains(@string));
}
}
/// <summary>
/// Test the static #copy() function with a JDK <seealso cref="Set"/> as a source
/// </summary>
public virtual void testCopyJDKSet()
{
ISet <string> set = new HashSet <string>();
IList <string> stopwords = TEST_STOP_WORDS;
IList <string> stopwordsUpper = new List <string>();
foreach (string @string in stopwords)
{
stopwordsUpper.Add(@string.ToUpper(Locale.ROOT));
}
set.addAll(TEST_STOP_WORDS);
CharArraySet copy = CharArraySet.copy(TEST_VERSION_CURRENT, set);
assertEquals(set.Count, copy.size());
assertEquals(set.Count, copy.size());
assertTrue(copy.containsAll(stopwords));
foreach (string @string in stopwordsUpper)
{
assertFalse(copy.contains(@string));
}
IList <string> newWords = new List <string>();
foreach (string @string in stopwords)
{
newWords.Add(@string + "_1");
}
copy.addAll(newWords);
assertTrue(copy.containsAll(stopwords));
assertTrue(copy.containsAll(newWords));
// new added terms are not in the source set
foreach (string @string in newWords)
{
assertFalse(set.Contains(@string));
}
}
/// <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));
}
/// <summary>
/// Tests a special case of <seealso cref="CharArraySet#copy(Version, Set)"/> where the
/// set to copy is the <seealso cref="CharArraySet#EMPTY_SET"/>
/// </summary>
public virtual void testCopyEmptySet()
{
assertSame(CharArraySet.EMPTY_SET, CharArraySet.copy(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET));
}
