std.text.index.stemmer — xyz.zcaudate/std.text 4.1.0

*excluded-words* clj

*max-word-length* clj

*min-word-length* clj

default-stemmer clj

excluded-word? clj

(excluded-word? word)

checks if word is excluded from indexing

(excluded-word? "and") => true

expand-hyphenated-words clj

(expand-hyphenated-words word-seq)

split hyphenated words

(expand-hyphenated-words ["hello-world"]) => ["hello-world" "hello" "world"]

remove-excluded-words clj

(remove-excluded-words word-seq)

remove excluded words

stems clj

(stems phrase)

(stems phrase stemmer-func)

classifies text into word stems

(stems "The lazy brown fox jumped over") => ["lazi" "brown" "fox" "jump" "over"]

tokenise clj

(tokenise txt)

makes tokens from text

(tokenise "The lazy brown fox jumped over") => ["lazy" "brown" "fox" "jumped" "over"]