dl4clj-nlp.tokenization — hswick/dl4clj-nlp 0.0.1

common-preprocessor clj

(common-preprocessor)

common-stemmer-preprocessor clj

(common-stemmer-preprocessor)

default-tokenizer-factory clj

(default-tokenizer-factory)

(default-tokenizer-factory preprocessor)

ending-preprocessor clj

(ending-preprocessor)

lower-case-preprocessor clj

(lower-case-preprocessor)

ngram-tokenizer-factory clj

(ngram-tokenizer-factory tokenizer-factory min-n max-n)

set-token-preprocessor! clj

(set-token-preprocessor! tokenizer preprocessor)

strip-punct clj

(strip-punct base)