本文整理汇总了C#中Lucene.Net.Analysis.TokenStream类的典型用法代码示例。如果您正苦于以下问题:C# TokenStream类的具体用法?C# TokenStream怎么用?C# TokenStream使用的例子?那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。
TokenStream类属于Lucene.Net.Analysis命名空间,在下文中一共展示了TokenStream类的20个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于我们的系统推荐出更棒的C#代码示例。
示例1: GetTokenView
public string GetTokenView(TokenStream tokenStream, out int numberOfTokens)
{
var sb = new StringBuilder();
numberOfTokens = 0;
var termAttr = tokenStream.GetAttribute<ITermAttribute>();
var startOffset = tokenStream.GetAttribute<Lucene.Net.Analysis.Tokenattributes.IOffsetAttribute>();
while (tokenStream.IncrementToken())
{
sb.Append(termAttr.Term + " Start: " + startOffset.StartOffset.ToString().PadLeft(5) + " End: " + startOffset.EndOffset.ToString().PadLeft(5) + "\r\n");
//var view = "[" + termAttr.Term + "] ";
//sb.Append(view);
numberOfTokens++;
}
return sb.ToString();
//StringBuilder sb = new StringBuilder();
//Token token = tokenStream.Next();
//numberOfTokens = 0;
//while (token != null)
//{
// numberOfTokens++;
// sb.Append(token.TermText() + " Start: " + token.StartOffset().ToString().PadLeft(5) + " End: " + token.EndOffset().ToString().PadLeft(5) + "\r\n");
// token = tokenStream.Next();
//}
//return sb.ToString();
}
开发者ID:rajmenon,项目名称:AnalyzerViewer,代码行数:34,代码来源:Default.aspx.cs
示例2: MockHoleInjectingTokenFilter
public MockHoleInjectingTokenFilter(Random random, TokenStream @in)
: base(@in)
{
RandomSeed = random.Next();
PosIncAtt = AddAttribute<IPositionIncrementAttribute>();
PosLenAtt = AddAttribute<IPositionLengthAttribute>();
}
开发者ID:joyanta,项目名称:lucene.net,代码行数:7,代码来源:MockHoleInjectingTokenFilter.cs
示例3: SimplePayloadFilter
public SimplePayloadFilter(TokenStream input)
: base(input)
{
Pos = 0;
PayloadAttr = input.AddAttribute<IPayloadAttribute>();
TermAttr = input.AddAttribute<ICharTermAttribute>();
}
开发者ID:ChristopherHaws,项目名称:lucenenet,代码行数:7,代码来源:TestBasics.cs
示例4: MockVariableLengthPayloadFilter
public MockVariableLengthPayloadFilter(Random random, TokenStream @in)
: base(@in)
{
this.Random = random;
this.Payload = new BytesRef(Bytes);
this.PayloadAtt = AddAttribute<IPayloadAttribute>();
}
开发者ID:Cefa68000,项目名称:lucenenet,代码行数:7,代码来源:MockVariableLengthPayloadFilter.cs
示例5: FrenchStemFilter
public FrenchStemFilter(TokenStream _in)
: base(_in)
{
stemmer = new FrenchStemmer();
termAtt = AddAttribute<ITermAttribute>();
}
开发者ID:synhershko,项目名称:lucene.net,代码行数:7,代码来源:FrenchStemFilter.cs
示例6: LengthFilter
/// <summary> Build a filter that removes words that are too long or too
/// short from the text.
/// </summary>
public LengthFilter(TokenStream in_Renamed, int min, int max)
: base(in_Renamed)
{
this.min = min;
this.max = max;
termAtt = (TermAttribute) AddAttribute(typeof(TermAttribute));
}
开发者ID:BackupTheBerlios,项目名称:lyra2-svn,代码行数:10,代码来源:LengthFilter.cs
示例7: NextToken
public static Token NextToken(TokenStream input, Token reusableToken)
{
if (input == null)
return null;
if (!input.IncrementToken())
return null;
ITermAttribute termAtt = input.GetAttribute<ITermAttribute>();
IOffsetAttribute offsetAtt = input.GetAttribute<IOffsetAttribute>();
ITypeAttribute typeAtt = input.GetAttribute<ITypeAttribute>();
if (reusableToken == null)
{
reusableToken = new Token();
}
reusableToken.Clear();
if (termAtt != null)
reusableToken.SetTermBuffer(termAtt.TermBuffer(), 0, termAtt.TermLength());
if (offsetAtt != null)
{
reusableToken.StartOffset = offsetAtt.StartOffset;
reusableToken.EndOffset = offsetAtt.EndOffset;
}
if (typeAtt != null)
reusableToken.Type = typeAtt.Type;
return reusableToken;
}
开发者ID:vebin,项目名称:Lucene.Net.Analysis.MMSeg,代码行数:31,代码来源:TokenUtils.cs
示例8: NoiseEmailHostFilter
public NoiseEmailHostFilter (TokenStream input, bool tokenize_email_hostname, LinkCallback link_call_back)
: base (input)
{
this.token_stream = input;
this.tokenize_email_hostname = tokenize_email_hostname;
this.link_call_back = link_call_back;
}
开发者ID:ArsenShnurkov,项目名称:beagle-1,代码行数:7,代码来源:NoiseFilter.cs
示例9: SingleCharTokenizer
public SingleCharTokenizer(TokenStream input): base(input)
{
_input = input;
_termAttribute = (TermAttribute)AddAttribute(typeof(TermAttribute));
_offsetAttribute = (OffsetAttribute)AddAttribute(typeof(OffsetAttribute));
_positionIncrementAttribute = (PositionIncrementAttribute)AddAttribute(typeof(PositionIncrementAttribute));
}
开发者ID:VirtueMe,项目名称:ravendb,代码行数:7,代码来源:Analysis.Ext.cs
示例10: MockTokenFilter
/// <summary>
/// Create a new MockTokenFilter.
/// </summary>
/// <param name="input"> TokenStream to filter </param>
/// <param name="filter"> DFA representing the terms that should be removed. </param>
public MockTokenFilter(TokenStream input, CharacterRunAutomaton filter)
: base(input)
{
this.Filter = filter;
TermAtt = AddAttribute<ICharTermAttribute>();
PosIncrAtt = AddAttribute<IPositionIncrementAttribute>();
}
开发者ID:Cefa68000,项目名称:lucenenet,代码行数:12,代码来源:MockTokenFilter.cs
示例11: LengthFilter
/// <summary> Build a filter that removes words that are too long or too
/// short from the text.
/// </summary>
public LengthFilter(TokenStream in_Renamed, int min, int max)
: base(in_Renamed)
{
this.min = min;
this.max = max;
termAtt = AddAttribute<ITermAttribute>();
}
开发者ID:Cefa68000,项目名称:lucenenet,代码行数:10,代码来源:LengthFilter.cs
示例12: CamelCaseFilter
public CamelCaseFilter(TokenStream stream)
: base(stream)
{
_termAttribute = AddAttribute<ITermAttribute>();
_offsetAttribute = AddAttribute<IOffsetAttribute>();
_positionIncrementAttribute = AddAttribute<IPositionIncrementAttribute>();
}
开发者ID:NuGet,项目名称:Entropy,代码行数:7,代码来源:CamelCaseFilter.cs
示例13: AddSuffixFilter
public AddSuffixFilter(TokenStream input, Dictionary<string, char[]> _suffixByTokenType)
: base(input)
{
termAtt = AddAttribute <ITermAttribute>();
typeAtt = AddAttribute <ITypeAttribute>();
this.suffixByTokenType = _suffixByTokenType;
}
开发者ID:doronuziel71,项目名称:HebMorph,代码行数:7,代码来源:AddSuffixFilter.cs
示例14: AssertTokenStreamContents
public static void AssertTokenStreamContents(TokenStream ts, System.String[] output, int[] startOffsets, int[] endOffsets, System.String[] types, int[] posIncrements, int? finalOffset)
{
Assert.IsNotNull(output);
ICheckClearAttributesAttribute checkClearAtt = ts.AddAttribute<ICheckClearAttributesAttribute>();
Assert.IsTrue(ts.HasAttribute<ITermAttribute>(), "has no TermAttribute");
ITermAttribute termAtt = ts.GetAttribute<ITermAttribute>();
IOffsetAttribute offsetAtt = null;
if (startOffsets != null || endOffsets != null || finalOffset != null)
{
Assert.IsTrue(ts.HasAttribute<IOffsetAttribute>(), "has no OffsetAttribute");
offsetAtt = ts.GetAttribute<IOffsetAttribute>();
}
ITypeAttribute typeAtt = null;
if (types != null)
{
Assert.IsTrue(ts.HasAttribute<ITypeAttribute>(), "has no TypeAttribute");
typeAtt = ts.GetAttribute<ITypeAttribute>();
}
IPositionIncrementAttribute posIncrAtt = null;
if (posIncrements != null)
{
Assert.IsTrue(ts.HasAttribute<IPositionIncrementAttribute>(), "has no PositionIncrementAttribute");
posIncrAtt = ts.GetAttribute<IPositionIncrementAttribute>();
}
ts.Reset();
for (int i = 0; i < output.Length; i++)
{
// extra safety to enforce, that the state is not preserved and also assign bogus values
ts.ClearAttributes();
termAtt.SetTermBuffer("bogusTerm");
if (offsetAtt != null) offsetAtt.SetOffset(14584724, 24683243);
if (typeAtt != null) typeAtt.Type = "bogusType";
if (posIncrAtt != null) posIncrAtt.PositionIncrement = 45987657;
checkClearAtt.GetAndResetClearCalled(); // reset it, because we called clearAttribute() before
Assert.IsTrue(ts.IncrementToken(), "token " + i + " does not exist");
Assert.IsTrue(checkClearAtt.GetAndResetClearCalled(), "clearAttributes() was not called correctly in TokenStream chain");
Assert.AreEqual(output[i], termAtt.Term, "term " + i);
if (startOffsets != null)
Assert.AreEqual(startOffsets[i], offsetAtt.StartOffset, "startOffset " + i);
if (endOffsets != null)
Assert.AreEqual(endOffsets[i], offsetAtt.EndOffset, "endOffset " + i);
if (types != null)
Assert.AreEqual(types[i], typeAtt.Type, "type " + i);
if (posIncrements != null)
Assert.AreEqual(posIncrements[i], posIncrAtt.PositionIncrement, "posIncrement " + i);
}
Assert.IsFalse(ts.IncrementToken(), "end of stream");
ts.End();
if (finalOffset.HasValue)
Assert.AreEqual(finalOffset, offsetAtt.EndOffset, "finalOffset ");
ts.Close();
}
开发者ID:synhershko,项目名称:lucene.net,代码行数:59,代码来源:BaseTokenStreamTestCase.cs
示例15: DisplayTokens
private static void DisplayTokens(TokenStream stream)
{
TermAttribute term = (TermAttribute) stream.AddAttribute(typeof(TermAttribute));
while (stream.IncrementToken())
{
Console.WriteLine("[{0}] ", term.Term());
}
}
开发者ID:diegocaxito,项目名称:LuceneTest,代码行数:8,代码来源:AnalyzerUtil.cs
示例16: SynonymFilter
/// <summary>
///
/// </summary>
/// <remarks></remarks>
/// <seealso cref=""/>
/// <param name="input"></param>
/// <param name="synonymEngine"></param>
/// <return></return>
public SynonymFilter(TokenStream input, ISynonymEngine synonymEngine)
: base(input)
{
synonymStack = new Stack<String>();
this.engine = synonymEngine;
this.termAtt = AddAttribute<ITermAttribute>();
this.posIncrAtt = AddAttribute<IPositionIncrementAttribute>();
}
开发者ID:BEXIS2,项目名称:Core,代码行数:16,代码来源:SynonymFilter.cs
示例17: SynonymFilter
public SynonymFilter(TokenStream input, ISynonymEngine engine)
: base(input)
{
synonymStack = new Stack<string>();
this.engine = engine;
this.termAttr = AddAttribute(typeof(TermAttribute)) as TermAttribute;
this.posIncrAttr = AddAttribute(typeof(PositionIncrementAttribute)) as PositionIncrementAttribute;
}
开发者ID:diegocaxito,项目名称:LuceneTest,代码行数:8,代码来源:SynonymFilter.cs
示例18: CutLeterDigitFilter
public CutLeterDigitFilter(TokenStream input)
: base(input)
{
reusableToken = new Token();
termAtt = AddAttribute<ITermAttribute>();
offsetAtt = AddAttribute<IOffsetAttribute>();
typeAtt = AddAttribute<ITypeAttribute>();
}
开发者ID:vebin,项目名称:Lucene.Net.Analysis.MMSeg,代码行数:8,代码来源:CutLeterDigitFilter.cs
示例19: SuggestStopFilter
/// <summary>
/// Sole constructor. </summary>
public SuggestStopFilter(TokenStream input, CharArraySet stopWords)
: base(input)
{
this.stopWords = stopWords;
this.termAtt = AddAttribute<ICharTermAttribute>();
this.posIncAtt = AddAttribute<IPositionIncrementAttribute>();
this.keywordAtt = AddAttribute<IKeywordAttribute>();
this.offsetAtt = AddAttribute<IOffsetAttribute>();
}
开发者ID:ChristopherHaws,项目名称:lucenenet,代码行数:11,代码来源:SuggestStopFilter.cs
示例20: SynonymFilter
public SynonymFilter(TokenStream in_Renamed, ISynonymEngine engine)
: base(in_Renamed)
{
synonymStack = new Stack<string>();
this.engine = engine;
termAtt = (TermAttribute)AddAttribute(typeof(TermAttribute));
posIncrAtt = (PositionIncrementAttribute)AddAttribute(typeof(PositionIncrementAttribute));
}
开发者ID:NightOwl888,项目名称:FacetedSearchPrototype,代码行数:9,代码来源:SynonymFilter.cs
注:本文中的Lucene.Net.Analysis.TokenStream类示例由纯净天空整理自Github/MSDocs等源码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。 |
请发表评论