case classCustomAnalyzer(name: String, tokenizer: String, charFilters: List[String], tokenFilters: List[String], positionIncrementGap: Int = 100) extends Analyzer with Product with Serializable
When the built-in analyzers do not fulfil your needs, you can create a custom analyzer
which uses the appropriate combination of:
When the built-in analyzers do not fulfil your needs, you can create a custom analyzer
which uses the appropriate combination of:
zero or more character filters
a tokenizer
zero or more token filters.
Reference these by name, and if they are custom or configurable add them to the analysis definition.
case classCustomNormalizer(name: String, charFilters: List[String], tokenFilters: List[String]) extends Normalizer with Product with Serializable
case classEdgeNGramTokenFilter(name: String, minGram: Option[Int] = None, maxGram: Option[Int] = None, side: Option[String] = None) extends TokenFilter with Product with Serializable
case classEdgeNGramTokenizer(name: String, minGram: Int = 1, maxGram: Int = 2, tokenChars: Iterable[String] = Nil) extends Tokenizer with Product with Serializable
case classElisionTokenFilter(name: String, articles: Seq[String] = Nil) extends TokenFilter with Product with Serializable
case classFingerprintAnalyzer(name: String, separator: Option[String] = None, stopwords: Iterable[String] = Nil, maxOutputSize: Int = 255) extends Analyzer with Product with Serializable
case classHunspellTokenFilter(name: String, locale: String, dedup: Option[Boolean] = None, longestOnly: Option[Boolean] = None, dictionary: Option[String] = None) extends TokenFilter with Product with Serializable
case classICUTokenizer(name: String, ruleFiles: String) extends Tokenizer with Product with Serializable
case classKeywordMarkerTokenFilter(name: String, keywords: Seq[String] = Nil, keywordsPath: Option[String] = None, keywordsPattern: Option[String] = None, ignoreCase: Option[Boolean] = None) extends TokenFilter with Product with Serializable
case classKeywordTokenizer(name: String, bufferSize: Int = 256) extends Tokenizer with Product with Serializable
case classLengthTokenFilter(name: String, min: Option[Int] = None, max: Option[Int] = None) extends TokenFilter with Product with Serializable
case classLimitTokenCountTokenFilter(name: String, maxTokenCount: Option[Int] = None, consumeAllTokens: Option[Boolean] = None) extends TokenFilter with Product with Serializable
case classMappingCharFilter(name: String, mappings: Map[String, String]) extends CharFilter with Product with Serializable
case classNGramTokenFilter(name: String, minGram: Option[Int] = None, maxGram: Option[Int] = None) extends TokenFilter with Product with Serializable
case classNGramTokenizer(name: String, minGram: Int = 1, maxGram: Int = 2, tokenChars: Iterable[String] = Nil) extends Tokenizer with Product with Serializable
When the built-in analyzers do not fulfil your needs, you can create a custom analyzer which uses the appropriate combination of:
zero or more character filters a tokenizer zero or more token filters.
Reference these by name, and if they are custom or configurable add them to the analysis definition.