You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
cipher-analytical-machine/src/cipher_analytical_machine/language_analyzer.clj

22 lines
518 B

(ns cipher-analytical-machine.language-analyzer
(:import [org.apache.tika.language LanguageIdentifier])
(:gen-class))
(defn detect-language
"Return a identified language."
[text]
(-> (new LanguageIdentifier text)
.getLanguage))
(defn is-language?
"Check if the text written a language."
[text language-id]
(= (detect-language text)
language-id))
(defn is-nonsense?
"Check if the text written a language is not a language."
[text language-id]
(not (is-language? text language-id)))