//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testNormalizeWinDelimToLinuxDelim() throws Exception
public virtual void testNormalizeWinDelimToLinuxDelim()
{
NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
builder.add("\\", "/");
NormalizeCharMap normMap = builder.build();
string path = "c:\\a\\b\\c";
Reader cs = new MappingCharFilter(normMap, new StringReader(path));
PathHierarchyTokenizer t = new PathHierarchyTokenizer(cs);
assertTokenStreamContents(t, new string[]{"c:", "c:/a", "c:/a/b", "c:/a/b/c"}, new int[]{0, 0, 0, 0}, new int[]{2, 4, 6, 8}, new int[]{1, 0, 0, 0}, path.Length);
}
// SOLR-2891
// *CompoundWordTokenFilter blindly adds term length to offset, but this can take things out of bounds
// wrt original text if a previous filter increases the length of the word (in this case ü -> ue)
// so in this case we behave like WDF, and preserve any modified offsets
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testInvalidOffsets() throws Exception
public virtual void testInvalidOffsets()
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.util.CharArraySet dict = makeDictionary("fall");
CharArraySet dict = makeDictionary("fall");
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.charfilter.NormalizeCharMap.Builder builder = new org.apache.lucene.analysis.charfilter.NormalizeCharMap.Builder();
NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
builder.add("ü", "ue");
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.charfilter.NormalizeCharMap normMap = builder.build();
NormalizeCharMap normMap = builder.build();
Analyzer analyzer = new AnalyzerAnonymousInnerClassHelper(this, dict, normMap);
assertAnalyzesTo(analyzer, "banküberfall", new string[] { "bankueberfall", "fall" }, new int[] { 0, 0 }, new int[] { 12, 12 });
}
/// <summary>
/// test that offsets are correct when mappingcharfilter is previously applied </summary>
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testChangedOffsets() throws java.io.IOException
public virtual void testChangedOffsets()
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.charfilter.NormalizeCharMap.Builder builder = new org.apache.lucene.analysis.charfilter.NormalizeCharMap.Builder();
NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
builder.add("a", "一二");
builder.add("b", "二三");
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.charfilter.NormalizeCharMap norm = builder.build();
NormalizeCharMap norm = builder.build();
Analyzer analyzer = new AnalyzerAnonymousInnerClassHelper(this, norm);
assertAnalyzesTo(analyzer, "ab", new string[] {"一二", "二二", "二三"}, new int[] {0, 0, 1}, new int[] {1, 1, 2});
// note: offsets are strange since this is how the charfilter maps them...
// before bigramming, the 4 tokens look like:
// { 0, 0, 1, 1 },
// { 0, 1, 1, 2 }
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testOffsetCorrection() throws Exception
public virtual void testOffsetCorrection()
{
const string INPUT = "Günther Günther is here";
// create MappingCharFilter
IList<string> mappingRules = new List<string>();
mappingRules.Add("\"ü\" => \"ü\"");
NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
builder.add("ü", "ü");
NormalizeCharMap normMap = builder.build();
CharFilter charStream = new MappingCharFilter(normMap, new StringReader(INPUT));
// create PatternTokenizer
TokenStream stream = new PatternTokenizer(charStream, Pattern.compile("[,;/\\s]+"), -1);
assertTokenStreamContents(stream, new string[] {"Günther", "Günther", "is", "here"}, new int[] {0, 13, 26, 29}, new int[] {12, 25, 28, 33}, INPUT.Length);
charStream = new MappingCharFilter(normMap, new StringReader(INPUT));
stream = new PatternTokenizer(charStream, Pattern.compile("Günther"), 0);
assertTokenStreamContents(stream, new string[] {"Günther", "Günther"}, new int[] {0, 13}, new int[] {12, 25}, INPUT.Length);
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void test() throws Exception
public virtual void test()
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.util.CharArraySet cas = new org.apache.lucene.analysis.util.CharArraySet(TEST_VERSION_CURRENT, 3, false);
CharArraySet cas = new CharArraySet(TEST_VERSION_CURRENT, 3, false);
cas.add("jjp");
cas.add("wlmwoknt");
cas.add("tcgyreo");
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.charfilter.NormalizeCharMap.Builder builder = new org.apache.lucene.analysis.charfilter.NormalizeCharMap.Builder();
NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
builder.add("mtqlpi", "");
builder.add("mwoknt", "jjp");
builder.add("tcgyreo", "zpfpajyws");
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.charfilter.NormalizeCharMap map = builder.build();
NormalizeCharMap map = builder.build();
Analyzer a = new AnalyzerAnonymousInnerClassHelper(this, cas, map);
checkAnalysisConsistency(random(), a, false, "wmgddzunizdomqyj");
}
// SOLR-2891
// *CompoundWordTokenFilter blindly adds term length to offset, but this can take things out of bounds
// wrt original text if a previous filter increases the length of the word (in this case ü -> ue)
// so in this case we behave like WDF, and preserve any modified offsets
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testInvalidOffsets() throws Exception
public virtual void testInvalidOffsets()
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.util.CharArraySet dict = makeDictionary("fall");
CharArraySet dict = makeDictionary("fall");
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.charfilter.NormalizeCharMap.Builder builder = new org.apache.lucene.analysis.charfilter.NormalizeCharMap.Builder();
NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
builder.add("ü", "ue");
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.charfilter.NormalizeCharMap normMap = builder.build();
NormalizeCharMap normMap = builder.build();
Analyzer analyzer = new AnalyzerAnonymousInnerClassHelper(this, dict, normMap);
assertAnalyzesTo(analyzer, "banküberfall", new string[] {"bankueberfall", "fall"}, new int[] {0, 0}, new int[] {12, 12});
}
