Data commit

This commit is contained in:
Ingy döt Net 2023-07-01 11:58:00 -04:00
parent 7387c8f97b
commit cb5bb5e222
199093 changed files with 3378972 additions and 0 deletions

View file

@ -0,0 +1,8 @@
(def utf-8-octet-length #(-> % (.getBytes "UTF-8") count))
(map utf-8-octet-length ["møøse" "𝔘𝔫𝔦𝔠𝔬𝔡𝔢" "J\u0332o\u0332s\u0332e\u0301\u0332"]) ; (7 28 14)
(def utf-16-octet-length (comp (partial * 2) count))
(map utf-16-octet-length ["møøse" "𝔘𝔫𝔦𝔠𝔬𝔡𝔢" "J\u0332o\u0332s\u0332e\u0301\u0332"]) ; (10 28 18)
(def code-unit-length count)
(map code-unit-length ["møøse" "𝔘𝔫𝔦𝔠𝔬𝔡𝔢" "J\u0332o\u0332s\u0332e\u0301\u0332"]) ; (5 14 9)

View file

@ -0,0 +1,2 @@
(def character-length #(.codePointCount % 0 (count %)))
(map character-length ["møøse" "𝔘𝔫𝔦𝔠𝔬𝔡𝔢" "J\u0332o\u0332s\u0332e\u0301\u0332"]) ; (5 7 9)

View file

@ -0,0 +1,8 @@
(def grapheme-length
#(->> (doto (java.text.BreakIterator/getCharacterInstance)
(.setText %))
(partial (memfn next))
repeatedly
(take-while (partial not= java.text.BreakIterator/DONE))
count))
(map grapheme-length ["møøse" "𝔘𝔫𝔦𝔠𝔬𝔡𝔢" "J\u0332o\u0332s\u0332e\u0301\u0332"]) ; (5 7 4)