Stemming for languages
(proxy [Analyzer] []
(createComponents [^String field-name]
(Analyzer$TokenStreamComponents.
tokenizer (SnowballFilter. tokenizer (LithuanianStemmer.)))))
(deftest lt-stemming
(let [dictionary [{:text "Dainius" :stem :lt}]
annotator (phrases/annotator dictionary)
anns (annotator "test Dainiui test")]
(is (not (empty? anns)))))
Edited by Dainius