近期,须要将汉字与字符的非常合串作为combine的输出的key,
这样做是希望,利用hadoop的归并来依照key进行分组,然后,在reduce阶段,拿到的都是一个一个组。
可是,发现,这样的,汉字混合的传做key,居然,在reduce阶段中,接受的的key并非唯一的,于是,考虑利用转码来实现。
终于,问题攻克了。
package test.com.gjob.services; import java.util.Properties; public class Test { public static void main(String[] args) { String s = "简单介绍"; String tt = gbEncoding(s); // String tt1 = "你好,我想给你说一个事情"; System.out.println(decodeUnicode("\u7b80\u4ecb")); // System.out.println(decodeUnicode(tt1)); System.out.println(HTMLDecoder.decode("中国")); String s1 = "u7b80u4ecb"; System.out.println(s.indexOf("\")); } public static String gbEncoding(final String gbString) { char[] utfBytes = gbString.toCharArray(); String unicodeBytes = ""; for (int byteIndex = 0; byteIndex < utfBytes.length; byteIndex++) { String hexB = Integer.toHexString(utfBytes[byteIndex]); if (hexB.length() <= 2) { hexB = "00" + hexB; } unicodeBytes = unicodeBytes + "\u" + hexB; } System.out.println("unicodeBytes is: " + unicodeBytes); return unicodeBytes; } public static String decodeUnicode(final String dataStr) { int start = 0; int end = 0; final StringBuffer buffer = new StringBuffer(); while (start > -1) { end = dataStr.indexOf("\u", start + 2); String charStr = ""; if (end == -1) { charStr = dataStr.substring(start + 2, dataStr.length()); } else { charStr = dataStr.substring(start + 2, end); } char letter = (char) Integer.parseInt(charStr, 16); // 16进制parse整形字符串。 buffer.append(new Character(letter).toString()); start = end; } return buffer.toString(); } }