A BreakIterator-like API for iterating over subwords in text, according to WordDelimiterFilter rules. @lucene.internal
コード例 #1
0
 /// <summary>
 /// Creates a new WordDelimiterFilter
 /// </summary>
 /// <param name="in"> TokenStream to be filtered </param>
 /// <param name="charTypeTable"> table containing character types </param>
 /// <param name="configurationFlags"> Flags configuring the filter </param>
 /// <param name="protWords"> If not null is the set of tokens to protect from being delimited </param>
 public Lucene47WordDelimiterFilter(TokenStream @in, sbyte[] charTypeTable, int configurationFlags, CharArraySet protWords) : base(@in)
 {
     if (!InstanceFieldsInitialized)
     {
         InitializeInstanceFields();
         InstanceFieldsInitialized = true;
     }
     this.flags     = configurationFlags;
     this.protWords = protWords;
     this.iterator  = new WordDelimiterIterator(charTypeTable, has(SPLIT_ON_CASE_CHANGE), has(SPLIT_ON_NUMERICS), has(STEM_ENGLISH_POSSESSIVE));
 }
コード例 #2
0
 /// <summary>
 /// Creates a new WordDelimiterFilter
 /// </summary>
 /// <param name="in"> TokenStream to be filtered </param>
 /// <param name="charTypeTable"> table containing character types </param>
 /// <param name="configurationFlags"> Flags configuring the filter </param>
 /// <param name="protWords"> If not null is the set of tokens to protect from being delimited </param>
 public WordDelimiterFilter(Version matchVersion, TokenStream @in, sbyte[] charTypeTable, int configurationFlags, CharArraySet protWords) : base(@in)
 {
     if (!InstanceFieldsInitialized)
     {
         InitializeInstanceFields();
         InstanceFieldsInitialized = true;
     }
     if (!matchVersion.onOrAfter(Version.LUCENE_48))
     {
         throw new System.ArgumentException("This class only works with Lucene 4.8+. To emulate the old (broken) behavior of WordDelimiterFilter, use Lucene47WordDelimiterFilter");
     }
     this.flags     = configurationFlags;
     this.protWords = protWords;
     this.iterator  = new WordDelimiterIterator(charTypeTable, has(SPLIT_ON_CASE_CHANGE), has(SPLIT_ON_NUMERICS), has(STEM_ENGLISH_POSSESSIVE));
 }
コード例 #3
0
	  /// <summary>
	  /// Creates a new WordDelimiterFilter
	  /// </summary>
	  /// <param name="in"> TokenStream to be filtered </param>
	  /// <param name="charTypeTable"> table containing character types </param>
	  /// <param name="configurationFlags"> Flags configuring the filter </param>
	  /// <param name="protWords"> If not null is the set of tokens to protect from being delimited </param>
	  public WordDelimiterFilter(Version matchVersion, TokenStream @in, sbyte[] charTypeTable, int configurationFlags, CharArraySet protWords) : base(@in)
	  {
		  if (!InstanceFieldsInitialized)
		  {
			  InitializeInstanceFields();
			  InstanceFieldsInitialized = true;
		  }
		if (!matchVersion.onOrAfter(Version.LUCENE_48))
		{
		  throw new System.ArgumentException("This class only works with Lucene 4.8+. To emulate the old (broken) behavior of WordDelimiterFilter, use Lucene47WordDelimiterFilter");
		}
		this.flags = configurationFlags;
		this.protWords = protWords;
		this.iterator = new WordDelimiterIterator(charTypeTable, has(SPLIT_ON_CASE_CHANGE), has(SPLIT_ON_NUMERICS), has(STEM_ENGLISH_POSSESSIVE));
	  }
コード例 #4
0
	  /// <summary>
	  /// Creates a new WordDelimiterFilter
	  /// </summary>
	  /// <param name="in"> TokenStream to be filtered </param>
	  /// <param name="charTypeTable"> table containing character types </param>
	  /// <param name="configurationFlags"> Flags configuring the filter </param>
	  /// <param name="protWords"> If not null is the set of tokens to protect from being delimited </param>
	  public Lucene47WordDelimiterFilter(TokenStream @in, sbyte[] charTypeTable, int configurationFlags, CharArraySet protWords) : base(@in)
	  {
		  if (!InstanceFieldsInitialized)
		  {
			  InitializeInstanceFields();
			  InstanceFieldsInitialized = true;
		  }
		this.flags = configurationFlags;
		this.protWords = protWords;
		this.iterator = new WordDelimiterIterator(charTypeTable, has(SPLIT_ON_CASE_CHANGE), has(SPLIT_ON_NUMERICS), has(STEM_ENGLISH_POSSESSIVE));
	  }