Last active
December 17, 2021 17:51
-
-
Save AkazaRenn/533b8064a885ffaa1faaa99f72d4bbc8 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import java.io.IOException | |
import java.util.Scanner | |
import java.net.URL | |
import java.util.HashMap | |
val TS_CHAR_URL = URL("https://github.com/BYVoid/OpenCC/raw/master/data/dictionary/TSCharacters.txt") | |
val ST_CHAR_URL = URL("https://github.com/BYVoid/OpenCC/raw/master/data/dictionary/STCharacters.txt") | |
enum class ChineseTypes { | |
SIMPLIFIED_CHINESE, | |
TRADITIONAL_CHINESE, | |
JAPANESE, | |
NONE | |
} | |
var charMap = HashMap<Char, ChineseTypes>(); | |
fun buildMap() { | |
try { | |
var scanner = Scanner(TS_CHAR_URL.openStream()) | |
while(scanner.hasNext()) { | |
var chars = scanner.nextLine().trim().split('\t') | |
if(!chars[1].contains(chars[0])) { | |
charMap.put(chars[0][0], ChineseTypes.TRADITIONAL_CHINESE) | |
} | |
} | |
} catch (e: IOException) { | |
println("Error saving TS_CHAR_URL") | |
} | |
try { | |
var scanner = Scanner(ST_CHAR_URL.openStream()) | |
while(scanner.hasNext()) { | |
var chars = scanner.nextLine().trim().split('\t') | |
if(!chars[1].contains(chars[0])) { | |
if(charMap.get(chars[0][0]) != null) { | |
charMap.remove(chars[0][0]) | |
} | |
else { | |
charMap.put(chars[0][0], ChineseTypes.SIMPLIFIED_CHINESE) | |
} | |
} | |
} | |
} catch (e: IOException) { | |
println("Error saving ST_CHAR_URL") | |
} | |
} | |
fun checkString(str: String): ChineseTypes { | |
var result = ChineseTypes.NONE | |
if (str != null) { | |
for (char in str) { | |
result = charMap.getOrDefault(char, ChineseTypes.NONE) | |
if (result != ChineseTypes.NONE) { | |
break | |
} | |
} | |
} | |
return result | |
} | |
fun main(args: Array<String>) { | |
buildMap(); | |
when(checkString(args[0])) { | |
ChineseTypes.TRADITIONAL_CHINESE -> println("TC") | |
ChineseTypes.SIMPLIFIED_CHINESE -> println("SC") | |
else -> { | |
println("Both or non-Chinese") | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment