//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testMaxPosition3WithSynomyms() throws java.io.IOException
public virtual void testMaxPosition3WithSynomyms()
{
foreach (bool consumeAll in new bool[]{true, false})
{
MockTokenizer tokenizer = new MockTokenizer(new StringReader("one two three four five"), MockTokenizer.WHITESPACE, false);
// if we are consuming all tokens, we can use the checks, otherwise we can't
tokenizer.EnableChecks = consumeAll;
SynonymMap.Builder builder = new SynonymMap.Builder(true);
builder.add(new CharsRef("one"), new CharsRef("first"), true);
builder.add(new CharsRef("one"), new CharsRef("alpha"), true);
builder.add(new CharsRef("one"), new CharsRef("beguine"), true);
CharsRef multiWordCharsRef = new CharsRef();
SynonymMap.Builder.join(new string[]{"and", "indubitably", "single", "only"}, multiWordCharsRef);
builder.add(new CharsRef("one"), multiWordCharsRef, true);
SynonymMap.Builder.join(new string[]{"dopple", "ganger"}, multiWordCharsRef);
builder.add(new CharsRef("two"), multiWordCharsRef, true);
SynonymMap synonymMap = builder.build();
TokenStream stream = new SynonymFilter(tokenizer, synonymMap, true);
stream = new LimitTokenPositionFilter(stream, 3, consumeAll);
// "only", the 4th word of multi-word synonym "and indubitably single only" is not emitted, since its position is greater than 3.
assertTokenStreamContents(stream, new string[]{"one", "first", "alpha", "beguine", "and", "two", "indubitably", "dopple", "three", "single", "ganger"}, new int[]{1, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0});
}
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testMaxPosition3WithSynomyms() throws java.io.IOException
public virtual void testMaxPosition3WithSynomyms()
{
foreach (bool consumeAll in new bool[] { true, false })
{
MockTokenizer tokenizer = new MockTokenizer(new StringReader("one two three four five"), MockTokenizer.WHITESPACE, false);
// if we are consuming all tokens, we can use the checks, otherwise we can't
tokenizer.EnableChecks = consumeAll;
SynonymMap.Builder builder = new SynonymMap.Builder(true);
builder.add(new CharsRef("one"), new CharsRef("first"), true);
builder.add(new CharsRef("one"), new CharsRef("alpha"), true);
builder.add(new CharsRef("one"), new CharsRef("beguine"), true);
CharsRef multiWordCharsRef = new CharsRef();
SynonymMap.Builder.join(new string[] { "and", "indubitably", "single", "only" }, multiWordCharsRef);
builder.add(new CharsRef("one"), multiWordCharsRef, true);
SynonymMap.Builder.join(new string[] { "dopple", "ganger" }, multiWordCharsRef);
builder.add(new CharsRef("two"), multiWordCharsRef, true);
SynonymMap synonymMap = builder.build();
TokenStream stream = new SynonymFilter(tokenizer, synonymMap, true);
stream = new LimitTokenPositionFilter(stream, 3, consumeAll);
// "only", the 4th word of multi-word synonym "and indubitably single only" is not emitted, since its position is greater than 3.
assertTokenStreamContents(stream, new string[] { "one", "first", "alpha", "beguine", "and", "two", "indubitably", "dopple", "three", "single", "ganger" }, new int[] { 1, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0 });
}
}
private void add(string input, string output, bool keepOrig)
{
if (VERBOSE)
{
Console.WriteLine(" add input=" + input + " output=" + output + " keepOrig=" + keepOrig);
}
CharsRef inputCharsRef = new CharsRef();
SynonymMap.Builder.join(input.Split(" +", true), inputCharsRef);
CharsRef outputCharsRef = new CharsRef();
SynonymMap.Builder.join(output.Split(" +", true), outputCharsRef);
b.add(inputCharsRef, outputCharsRef, keepOrig);
}
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);
}
}
}
