Demo of regular expressions with Unicode support: split a text into words

split-into-words.clj

(def split-into-words (partial re-seq #"\w+"))

(comment
  ;; split-into-words, implemented with the trivial \w+ regular
  ;; expression, it works fine in English:
  
  (split-into-words "Have a nice day.")
  ;; => ("Have" "a" "nice" "day")

  ;; But it fails with other languages, like in Spanish.  In the
  ;; following example, the word "día" is splited into "d" and "a"

  (split-into-words "Que tenga un buen día")
  ;; => ("Que" "tenga" "un" "buen" "d" "a")
)

(def split-into-words (partial re-seq #"\p{IsAlphabetic}+"))


(comment
  ;; Now, split-into-words, implemented with the regular expression
  ;; with Unicode Support, works correctly with other languages like
  ;; Spanish:
  
  (split-into-words "Que tenga un buen día")
  ;; => ("Que" "tenga" "un" "buen" "día")
)

split-into-words.es.clj

;; Demostración del uso de expresiones regulares con soporte de Unicode.
;; Divide un texto en palabras.

(def split-into-words (partial re-seq #"\w+"))

(comment
  ;; split-into-words, implementado con la expression regular trivial
  ;; \w+, funciona bien en inglés:
  
  (split-into-words "Have a nice day.")
  ;; => ("Have" "a" "nice" "day")

  ;; Pero falla con otros lenguajes, como el español.  En el siguiente
  ;; ejemplo, la palabra día es dividida en «d» y en «a»:

  (split-into-words "Que tenga un buen día")
  ;; => ("Que" "tenga" "un" "buen" "d" "a")
)

(def split-into-words (partial re-seq #"\p{IsAlphabetic}+"))


(comment
  ;; En cambio ahora, split-into-words, implementado con una
  ;; expression regular usando el soporte a Unicode, trabaja
  ;; conrrectamente con lenguajes como el español:
  
  (split-into-words "Que tenga un buen día")
  ;; => ("Que" "tenga" "un" "buen" "día")
)