Downloaded 13 times
![1
Unicode
package org.zakky.gudanama;
import java.text.Normalizer;
public class NormalizeMain {
private static void printCodePoints(String str) {
public static void main(String[] args) {
StringBuilder sb = new StringBuilder();
// [ ϓ ], [ ϔ ], [ ẛ ]
int index = 0;
final String src = "u03d3u03d4u1e9b";
while(index < str.length()) {
printCodePoints(src);
char c = str.charAt(index);
sb.append("U+");
// [ ϓ ], [ ϔ ], [ ẛ ]
if (Character.isHighSurrogate(c)) {
System.out.print("NFC: ");
sb.append(Character.toCodePoint(c, str.charAt(index+1)));
printCodePoints(Normalizer.normalize(src, Normalizer.Form.NFC));
index++;
// [ ϒ ], [ ́ ], [ ϒ ], [ ̈ ], [ ſ ], [ ̇ ]
} else {
System.out.print("NFD: ");
sb.append((int) c);
printCodePoints(Normalizer.normalize(src, Normalizer.Form.NFD));
}
// [ Ύ ], [ Ϋ ], [ ṡ ]
index++;
System.out.print("NFKC: ");
sb.append(' ');
printCodePoints(Normalizer.normalize(src, Normalizer.Form.NFKC));
}
// [ Υ ], [ ́ ], [ Υ ], [ ̈ ], [ s ], [ ̇ ]
if (sb.length() != 0) {
System.out.print("NFKD: ");
sb.setLength(sb.length() - 1);
printCodePoints(Normalizer.normalize(src, Normalizer.Form.NFKD));
}
System.out.println(sb);
}
}
}](/p?url=https%3A%2F%2Fimage.slidesharecdn.com%2F20110416java-110416090816-phpapp01%2F85%2FJava-Keynote-40-320.jpg&__src=https%3A%2F%2Fwww.slideshare.net%2Fslideshow%2F20110416-java%2F7648839&__type=image)
![2
package org.zakky.gudanama;
public class SurrogatePairMain {
public static void main(String[] args) {
final String str = " ";
System.out.println("str: " + str);
System.out.println("length: " + str.length());
System.out.println("code point count" + str.codePointCount(0, str.length()));
System.out.println("code point of str: "
+ Character.toCodePoint(str.charAt(0), str.charAt(1)) + "(U+"
+ Integer.toHexString(Character.toCodePoint(str.charAt(0), str.charAt(1))) + ")");
System.out.println("str[0] is high surrogate: " + Character.isHighSurrogate(str.charAt(0)));
System.out.println("str[0] is low surrogate: " + Character.isLowSurrogate(str.charAt(0)));
System.out.println("str[1] is high surrogate: " + Character.isHighSurrogate(str.charAt(1)));
System.out.println("str[1] is low surrogate: " + Character.isLowSurrogate(str.charAt(1)));
System.out.println(new String(new char[] {str.charAt(0), str.charAt(1)
}));
}
}](/p?url=https%3A%2F%2Fimage.slidesharecdn.com%2F20110416java-110416090816-phpapp01%2F85%2FJava-Keynote-41-320.jpg&__src=https%3A%2F%2Fwww.slideshare.net%2Fslideshow%2F20110416-java%2F7648839&__type=image)
![3
BOM
package org.zakky.gudanama;
import java.io.IOException;
import java.io.PushbackReader;
import java.io.Reader;
public class BomMain {
public static void main(String[] args) throws IOException {
Reader r = null;
// skip bom
int first = r.read();
if (!isBom(first)) {
PushbackReader pushbackReader = new PushbackReader(r);
pushbackReader.unread(first);
r = pushbackReader;
}
}
private static boolean isBom(int codepoint) {
return codepoint == 0xfeff;
}
}](/p?url=https%3A%2F%2Fimage.slidesharecdn.com%2F20110416java-110416090816-phpapp01%2F85%2FJava-Keynote-42-320.jpg&__src=https%3A%2F%2Fwww.slideshare.net%2Fslideshow%2F20110416-java%2F7648839&__type=image)
Uploaded byMakoto Yamazaki
ぐだ生 Java入門第三回(文字コードの話)(Keynote版)
The document discusses Unicode encoding formats such as UTF-8, UTF-16, and UTF-32. It explains how each encoding maps Unicode code points to variable length bit sequences and describes features of the encodings like byte order marks and surrogate pairs. Java code examples are provided to demonstrate working with Unicode strings and encodings.
