本文整理汇总了C#中ITermAttribute类的典型用法代码示例。如果您正苦于以下问题:C# ITermAttribute类的具体用法?C# ITermAttribute怎么用?C# ITermAttribute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。
ITermAttribute类属于命名空间,在下文中一共展示了ITermAttribute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: Init
private void Init(int bufferSize)
{
this.done = false;
termAtt = AddAttribute<ITermAttribute>();
offsetAtt = AddAttribute<IOffsetAttribute>();
termAtt.ResizeTermBuffer(bufferSize);
}
开发者ID:mindis,项目名称:Transformalize,代码行数:7,代码来源:KeywordTokenizer.cs
示例2: IKTokenizer
///<summary>
///Lucene Tokenizer适配器类构造函数
/// </summary>
/// <param name="isMaxWordLength">当为true时,分词器进行最大词长切分;当为false是,采用最细粒度切分</param>
public IKTokenizer(TextReader inreader, bool isMaxWordLength)
: base(inreader)
{
offsetAtt = AddAttribute<IOffsetAttribute>();
termAtt = AddAttribute<ITermAttribute>();
_IKImplement = new IKSegmentation(inreader, isMaxWordLength);
}
开发者ID:mamboer,项目名称:IKAnalyzer.Net,代码行数:11,代码来源:IKTokenizer.cs
示例3: 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4: 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5: 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6: 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7: Init
void Init()
{
InitPanGuSegment();
termAtt = AddAttribute<ITermAttribute>();
offsetAtt = AddAttribute<IOffsetAttribute>();
posIncrAtt = AddAttribute<IPositionIncrementAttribute>();
typeAtt = AddAttribute<ITypeAttribute>();
}
开发者ID:alinote,项目名称:Lucene.Net.Analysis.PanGu,代码行数:8,代码来源:PanGuTokenizer.cs
示例8: 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9: 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10: MMSegTokenizer
/*
* 此处忽略调用base(input);因调用后input的position会被移动
* by zh
*/
public MMSegTokenizer(Seg seg, TextReader input)
: base(input)
{
mmSeg = new MMSeg(input, seg);
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:12,代码来源:MMSegTokenizer.cs
示例11: DelimitedPayloadTokenFilter
public DelimitedPayloadTokenFilter(TokenStream input, char delimiter, PayloadEncoder encoder)
: base(input)
{
termAtt = AddAttribute<ITermAttribute>();
payAtt = AddAttribute<IPayloadAttribute>();
this.delimiter = delimiter;
this.encoder = encoder;
}
开发者ID:synhershko,项目名称:lucene.net,代码行数:8,代码来源:DelimitedPayloadTokenFilter.cs
示例12: HunspellStemFilter
/// <summary>
/// Creates a new HunspellStemFilter that will stem tokens from the given TokenStream using
/// affix rules in the provided HunspellDictionary.
/// </summary>
/// <param name="input">TokenStream whose tokens will be stemmed.</param>
/// <param name="dictionary">HunspellDictionary containing the affix rules and words that will be used to stem the tokens.</param>
/// <param name="dedup">true if only unique terms should be output.</param>
public HunspellStemFilter(TokenStream input, HunspellDictionary dictionary, Boolean dedup = true)
: base(input)
{
_posIncAtt = AddAttribute<IPositionIncrementAttribute>();
_termAtt = AddAttribute<ITermAttribute>();
_dedup = dedup;
_stemmer = new HunspellStemmer(dictionary);
}
开发者ID:Cefa68000,项目名称:lucenenet,代码行数:16,代码来源:HunspellStemFilter.cs
示例13: Init
private void Init(System.IO.TextReader _input, HebMorph.DataStructures.DictRadix<int> _prefixesTree)
{
termAtt = AddAttribute <ITermAttribute>();
offsetAtt = AddAttribute <IOffsetAttribute>();
//posIncrAtt = (PositionIncrementAttribute)AddAttribute(typeof(PositionIncrementAttribute));
typeAtt = AddAttribute <ITypeAttribute>();
input = _input;
hebMorphTokenizer = new HebMorph.Tokenizer(_input);
prefixesTree = _prefixesTree;
}
开发者ID:doronuziel71,项目名称:HebMorph,代码行数:10,代码来源:HebrewTokenizer.cs
示例14: ExpandAcronymsFilter
public ExpandAcronymsFilter(TokenStream input, IAcronymExpansionProvider acronymExpansionProvider)
: base(input)
{
_acronymExpansionProvider = acronymExpansionProvider;
_termAttribute = AddAttribute<ITermAttribute>();
_positionIncrementAttribute = AddAttribute<IPositionIncrementAttribute>();
_tokenSet = new Queue<string>();
_recognizedTokens = new HashSet<string>();
}
开发者ID:NuGet,项目名称:NuGet.Services.Metadata,代码行数:10,代码来源:ExpandAcronymsFilter.cs
示例15: JiebaTokenizer
public JiebaTokenizer(JiebaSegmenter seg, string input)
{
segmenter = seg;
termAtt = AddAttribute<ITermAttribute>();
offsetAtt = AddAttribute<IOffsetAttribute>();
typeAtt = AddAttribute<ITypeAttribute>();
var text = input;
tokens = segmenter.Tokenize(text, TokenizerMode.Search).ToList();
}
开发者ID:applenele,项目名称:SmallCode,代码行数:10,代码来源:JiebaTokenizer.cs
示例16: ExpanderFilter
public ExpanderFilter(TokenStream input, [NotNull] Func<String, IEnumerable<Expansion>> expander, Boolean emitSource = true)
: base(input)
{
if (expander == null)
throw new ArgumentNullException("expander");
_expander = expander;
_emitSource = emitSource;
_termAttr = AddAttribute<ITermAttribute>();
_posAttr = AddAttribute<IPositionIncrementAttribute>();
_typeAttr = AddAttribute<ITypeAttribute>();
}
开发者ID:devhost,项目名称:Corelicious,代码行数:12,代码来源:ExpanderFilter.cs
示例17: SnowballFilter
/// <summary>Construct the named stemming filter.
///
/// </summary>
/// <param name="input">the input tokens to stem
/// </param>
/// <param name="name">the name of a stemmer
/// </param>
public SnowballFilter(TokenStream input, System.String name) : base(input)
{
try
{
System.Type stemClass = System.Type.GetType("SF.Snowball.Ext." + name + "Stemmer");
stemmer = (SnowballProgram) System.Activator.CreateInstance(stemClass);
}
catch (System.Exception e)
{
throw new System.SystemException(e.ToString());
}
termAtt = AddAttribute<ITermAttribute>();
}
开发者ID:synhershko,项目名称:lucene.net,代码行数:20,代码来源:SnowballFilter.cs
示例18: Init
private void Init(System.IO.TextReader input, HebMorph.StreamLemmatizer _lemmatizer,
HebMorph.LemmaFilters.LemmaFilterBase _lemmaFilter, bool AlwaysSaveMarkedOriginal)
{
termAtt = AddAttribute <ITermAttribute>();
offsetAtt = AddAttribute<IOffsetAttribute>();
posIncrAtt = AddAttribute<IPositionIncrementAttribute>();
typeAtt = AddAttribute <ITypeAttribute>();
//payAtt = (PayloadAttribute)AddAttribute(typeof(PayloadAttribute));
this.input = input;
this._streamLemmatizer = _lemmatizer;
this._streamLemmatizer.SetStream(input);
this.alwaysSaveMarkedOriginal = AlwaysSaveMarkedOriginal;
this.lemmaFilter = _lemmaFilter;
}
开发者ID:doronuziel71,项目名称:HebMorph,代码行数:15,代码来源:StreamLemmasFilter.cs
示例19: StopFilter
/// <summary> Construct a token stream filtering the given input.
/// If <c>stopWords</c> is an instance of <see cref="CharArraySet" /> (true if
/// <c>makeStopSet()</c> was used to construct the set) it will be directly used
/// and <c>ignoreCase</c> will be ignored since <c>CharArraySet</c>
/// directly controls case sensitivity.
/// <p/>
/// If <c>stopWords</c> is not an instance of <see cref="CharArraySet" />,
/// a new CharArraySet will be constructed and <c>ignoreCase</c> will be
/// used to specify the case sensitivity of that set.
/// </summary>
/// <param name="enablePositionIncrements">true if token positions should record the removed stop words</param>
/// <param name="input">Input TokenStream</param>
/// <param name="stopWords">A Set of strings or strings or char[] or any other ToString()-able set representing the stopwords</param>
/// <param name="ignoreCase">if true, all words are lower cased first</param>
public StopFilter(bool enablePositionIncrements, TokenStream input, ISet<string> stopWords, bool ignoreCase)
: base(input)
{
if (stopWords is CharArraySet)
{
this.stopWords = (CharArraySet) stopWords;
}
else
{
this.stopWords = new CharArraySet(stopWords.Count, ignoreCase);
this.stopWords.AddAll(stopWords);
}
this.enablePositionIncrements = enablePositionIncrements;
termAtt = AddAttribute<ITermAttribute>();
posIncrAtt = AddAttribute<IPositionIncrementAttribute>();
}
开发者ID:JokerMisfits,项目名称:linux-packaging-mono,代码行数:30,代码来源:StopFilter.cs
示例20: NGramTokenFilter
/*
* Creates NGramTokenFilter with given min and max n-grams.
* <param name="input"><see cref="TokenStream"/> holding the input to be tokenized</param>
* <param name="minGram">the smallest n-gram to generate</param>
* <param name="maxGram">the largest n-gram to generate</param>
*/
public NGramTokenFilter(TokenStream input, int minGram, int maxGram)
: base(input)
{
if (minGram < 1)
{
throw new System.ArgumentException("minGram must be greater than zero");
}
if (minGram > maxGram)
{
throw new System.ArgumentException("minGram must not be greater than maxGram");
}
this.minGram = minGram;
this.maxGram = maxGram;
this.termAtt = AddAttribute<ITermAttribute>();
this.offsetAtt = AddAttribute<IOffsetAttribute>();
}
开发者ID:Cefa68000,项目名称:lucenenet,代码行数:23,代码来源:NGramTokenFilter.cs
注:本文中的ITermAttribute类示例整理自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