clustering words based on their char set

var x = "これは猫です、けどKittyも大丈夫。";
x.match(/[ぁ-ゖァ-ヺー一-龯々]/g).length; //Result: 12 : これは猫ですけども大丈夫

x.match(/\w+/g).length; //Result: 1 : "Kitty"

function myCount(str) {
   return str.match(/[ぁ-ゖァ-ヺー一-龯々]|\w+/g).length;
}
alert(myCount("これは猫です、けどKittyも大丈夫。")); //13    
alert(myCount("これは犬です。DogとPuppyもOKですね！")); //14

["こ", "れ", "は", "猫", "で", "す", "け", "ど", "Kitty", "も", "大", "丈", "夫"]
["こ", "れ", "は", "犬", "で", "す", "Dog", "と", "Puppy", "も", "OK", "で", "す", "ね"]

function myCount(str) {
   return str.match(/[ぁ-ㆌㇰ-䶵一-鿃々가-힣-豈ｦ-ﾝ]|\w+/g).length;
}

dictionarySize = 5

BOW = cv2.BOWKMeansTrainer(dictionarySize)

for p in training_paths:
    image = cv2.imread(p)
    gray = cv2.cvtColor(image, cv2.CV_LOAD_IMAGE_GRAYSCALE)
    kp, dsc= sift.detectAndCompute(gray, None)
    BOW.add(dsc)

#dictionary created
dictionary = BOW.cluster()