字符串截取

import java.io.IOException;
import java.io.UnsupportedEncodingException;

import org.junit.Test;

/*
 *在java中，字符串“abcd”与字符串“ab你好”的长度是一样，都是四个字符。
 *但对应的字节数不同，一个汉字占两个字节。
 *定义一个方法，按照指定的字节数来取子串。
 *如：对于“ab你好”，如果取三个字节，那么子串就是ab与“你”字的半个，那么半个就要舍弃。如果取四个字节就是“ab你”，取五个字节还是“ab你”。
 */
public class indexOfString {
	@Test
	// 观察一下字节数据的规律
	public void test1() throws IOException {
		String str = new String("ab你好");
		print(str.getBytes("gbk"));
		print(str.getBytes("utf-8"));
	}

	private void print(byte[] bs) {
		for (byte b : bs) {
			System.out.print(b + "");
		}
		System.out.println();
	}

	@Test
	public void test2() throws IOException {
		String str = "ab你好琲a我aa";
		for (int i = 0; i < str.getBytes("gbk").length; i++) {
			System.out.println(i + ":" + cutStringByByteGbk(str, i));
		}
	}

	private static String cutStringByByteGbk(String str, int len) {
		try {
			byte bs[] = str.getBytes("gbk");
			// 从后往前，统计字节编码为负数的个数,统计到非负数字节停止
			int count = 0;
			for (int i = len - 1; i > 0; i--) {
				if (bs[i] < 0) {
					count++;
				} else {
					break;
				}
			}
			if (count % 2 == 0) {// 字节码值为负的字节个数为偶数，汉字刚好完整
				return new String(bs, 0, len, "gbk");
			} else {// 奇数,要舍去最后一个字节
				return new String(bs, 0, len - 1, "gbk");
			}

		} catch (UnsupportedEncodingException e) {
			throw new RuntimeException("字符编码异常，不支持gbk", e);
		}
	}

	@Test
	// 测试cutStringByByteUtf8()方法
	public void t3() throws IOException {
		String str = "ab你好琲a我aa";
		for (int i = 0; i < str.getBytes("utf-8").length; i++) {
			System.out.println(i + ":" + cutStringByByteUtf8(str, i));
		}
	}

	private static String cutStringByByteUtf8(String str, int len) {
		try {
			byte bs[] = str.getBytes("utf-8");
			// 从后往前，统计字节编码为负数的个数,统计到非负数字节停止
			int count = 0;
			for (int i = len - 1; i > 0; i--) {
				if (bs[i] < 0) {
					count++;
				} else {
					break;
				}
			}
			return new String(bs,0,len-count%3,"utf-8"); 

		} catch (UnsupportedEncodingException e) {
			throw new RuntimeException("字符编码异常，不支持utf-8", e);
		}
	}

	public static String cutStringByByte(String str, int len) {

		if (System.getProperty("file.encoding").equalsIgnoreCase("gbk")) {
			return cutStringByByteGbk(str, len);
		}
		if (System.getProperty("file.encoding").equalsIgnoreCase("utf-8")) {
			return cutStringByByteUtf8(str, len);
		}

		return "";
	}
	
	public static void main(String[] args) {
		String str="ab你好琲a我aa";
		for(int i=0;i<str.getBytes().length;i++){
		  System.out.println(i+":"+ cutStringByByte(str, i));
		}
	}
}