json中包含Unicode转码问题

今天在解析json数据的时候得到了一堆这样的数据：{"errNum":0,"errMsg":"success","retData":[{"title":"\u6536\u5e9f\u54c1\u5927\u53d4\u521a\u4e0a\u53f0\uff0c\u5c31\u60e8\u906d\u8bc4\u59d4\u706d\u706f\uff0c\u4f46\u63a5\u4e0b\u6765\u5168\u573a\u90fd\u9707\u60ca\u4e86\uff01","url":"http:\/\/toutiao.com\/group\/6263036756505920002\/","abstract":"\u8ba2\u9605\u6211\u83b7\u53d6\u66f4\u591a\u7cbe\u5f69\u5185\u5bb9\uff01","image_url":"http:\/\/p1.pstatp.com\/list\/2f90009a31a7ee8bb15"}]}

这是因为，为了更好的传输中文，json进行了Unicode编码。

这样一来，我们在解析json之前，就得要先将json数据中的Unicode编码转换为我们使用的中文；

一：http请求数据返回json中string字段包含unicode的转码

public static String decodeUnicode(String theString) {  
        char aChar;  
        int len = theString.length();  
        StringBuffer outBuffer = new StringBuffer(len);  
        for (int x = 0; x < len;) {  
            aChar = theString.charAt(x++);  
            if (aChar == '\\') {  
                aChar = theString.charAt(x++);  
                if (aChar == 'u') {  
                    // Read the xxxx  
                    int value = 0;  
                    for (int i = 0; i < 4; i++) {  
                        aChar = theString.charAt(x++);  
                        switch (aChar) {  
                        case '0':  
                        case '1':  
                        case '2':  
                        case '3':  
                        case '4':  
                        case '5':  
                        case '6':  
                        case '7':  
                        case '8':  
                        case '9':  
                            value = (value << 4) + aChar - '0';  
                            break;  
                        case 'a':  
                        case 'b':  
                        case 'c':  
                        case 'd':  
                        case 'e':  
                        case 'f':  
                            value = (value << 4) + 10 + aChar - 'a';  
                            break;  
                        case 'A':  
                        case 'B':  
                        case 'C':  
                        case 'D':  
                        case 'E':  
                        case 'F':  
                            value = (value << 4) + 10 + aChar - 'A';  
                            break;  
                        default:  
                            throw new IllegalArgumentException(  
                                    "Malformed   \\uxxxx   encoding.");  
                        }  
      
                    }  
                    outBuffer.append((char) value);  
                } else {  
                    if (aChar == 't')  
                        aChar = '\t';  
                    else if (aChar == 'r')  
                        aChar = '\r';  
                    else if (aChar == 'n')  
                        aChar = '\n';  
                    else if (aChar == 'f')  
                        aChar = '\f';  
                    outBuffer.append(aChar);  
                }  
            } else  
                outBuffer.append(aChar);  
        }  
        return outBuffer.toString();  
    }

二、普通string含有unicode转码方法

 public static String reEncoding(String text, String newEncoding) { 
                String str = null; 
                try { 
                        str = new String(text.getBytes(), newEncoding); 
                } catch (UnsupportedEncodingException e) { 
                        log.error("不支持的字符编码" + newEncoding); 
                        throw new RuntimeException(e); 
                } 
                return str; 
        } 

三、说一下比较奇怪的方案，测试中无意发现的，暂时没弄明白原理（有明白原理的大神，请告知一声，谢谢）

我用HttpClent的post方式获取的json数据，得到的是带Unicode码的数据，需要转换成中文才行，但是转换的时间感觉有点长，就用HttpURLConnection的get方式又试了一下，在不转码的情况下，经过gson解析后，竟然神奇的自动转换成了中文：

简直是太神奇了，而且需要的时间相对于HttpClient的post请求方式的请求和处理时间更短，所以，果断换用HttpURLConnection的get方式了

①现在先贴一下HttpURLConnection的get的方式：

@Test
	public void test() {
		try {
			long start = System.currentTimeMillis();
			URL url = new URL("http://apis.baidu.com/songshuxiansheng/news/news");
			
			HttpURLConnection connection = (HttpURLConnection) url.openConnection();
				connection.addRequestProperty("apikey","0fc807e45a37ce264f45d169646f4a9e" );
				String dataString = new String(GsonTools.IsToByte(connection.getInputStream()),"utf-8");
				HeadlineJson newsJson = GsonTools.getObjectData(dataString, HeadlineJson.class);
				List<Headline>list = newsJson.getRetData();
				System.out.println(list.toString());
				long end = System.currentTimeMillis();
				
			System.out.println("timeGap:"+(end-start));
		} catch (Exception e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}

调用的GsonTools的方法：（之前的博文中有写到过）

public static <T> T getObjectData(String jsonString, Class<T> type) {

		T t = null;
		try {
			Gson gson = new Gson();
			t = gson.fromJson(jsonString, type);
		} catch (JsonSyntaxException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
		return t;
	}

②然后贴一下HttpClient的post方式：

@Test
	public void TestHeadLine() {
		long start = System.currentTimeMillis();
		List<NameValuePair> params = new ArrayList<NameValuePair>();
		String url = "http://apis.baidu.com/songshuxiansheng/news/news";
		String jsonString = HttpUtils.getBaiDuString2(url, params);
		HeadlineJson lineJson = GsonTools.getObjectData(jsonString, HeadlineJson.class);
		System.out.println(lineJson.toString());
		long end = System.currentTimeMillis();
		
		System.out.println("timeGap:"+(end-start));
	}

调用的HttpUtils的方法：

public static String getBaiDuString(String url,List<NameValuePair> params) {
		String serverDataString = null;
		HttpPost post = new HttpPost(url);
		try {
			post.setEntity(new UrlEncodedFormEntity(params, HTTP.UTF_8));
			post.addHeader("apikey", UrlUtils.BAIDU_API_KEY);
			HttpClient client = new DefaultHttpClient();
			HttpResponse response = client.execute(post);
			int code = response.getStatusLine().getStatusCode();
			System.out.println("StatusCode:" + code);

			if (code == 200) {
				serverDataString = decodeUnicode(EntityUtils.toString(response.getEntity()));
//				serverDataString = EntityUtils.toString(response.getEntity());

				System.out.println("接收字符串数据成功\nServerData:"+serverDataString);
			}
		} catch (Exception e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}

		return serverDataString;
	}

③调用的HttpClient的get方式

public static String getBaiDuString2(String url,List<NameValuePair> params) {
		String serverDataString = null;
		HttpGet get = new HttpGet(url);
		try {get.addHeader("apikey", UrlUtils.BAIDU_API_KEY);
			HttpClient client = new DefaultHttpClient();
			HttpResponse response = client.execute(get);
			int code = response.getStatusLine().getStatusCode();
			System.out.println("StatusCode:" + code);

			if (code == 200) {
//				serverDataString = decodeUnicode(EntityUtils.toString(response.getEntity()));
				serverDataString = EntityUtils.toString(response.getEntity());

				System.out.println("接收字符串数据成功\nServerData:"+serverDataString);
			}
		} catch (Exception e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}

		return serverDataString;
	}

谷歌提供的HttpClient的通信和HttpURLConnection网络通信的时间间隔我也做了比较，明显，HttpURLConnection的请求时间更短，所以果断使用HttpURLConnection的方式

四、java中本身就提供了对Unicode 的url进行解码的方法了：

System.out.println(URLDecoder.decode("\u82f9\u679c", "utf-8"));