var http = require('http');
 
var server = http.createServer(function(req,res) {
    var data = '';
    req.setEncoding('utf8');
 
    req.on('data',function(chunk) {
        data += chunk;
    });
 
    req.on('end',function() {
        // parse data
    });
});

假设输入是UTF8编码的,使用req.setEncoding(‘utf8’)会自动将输入字节解码为字符串.但我觉得它可以打破.如果我们收到一个以多字节UTF8字符结尾的数据块怎么办？我们可以模拟这个：

> new Buffer("café")
<Buffer 63 61 66 c3 a9>
> new Buffer("café").slice(0,4)
<Buffer 63 61 66 c3>
> new Buffer("café").slice(0,4).toString('utf8')
'caf?'

所以我们得到一个错误的字符,而不是等待下一个字节正确解码最后一个字符.

因此,除非请求对象处理这个问题,确保只将完全解码的字符推入块中,否则这个无处不在的代码示例将被破坏.

另一种方法是使用缓冲区,处理缓冲区大小限制的问题：

var http = require('http');
var MAX_REQUEST_BODY_SIZE = 16 * 1024 * 1024;
 
var server = http.createServer(function(req,res) {
    // A better way to do this could be to start with a small buffer
    // and grow it geometrically until the limit is reached.
    var requestBody = new Buffer(MAX_REQUEST_BODY_SIZE); 
    var requestBodyLength = 0;
 
    req.on('data',function(chunk) {
        if(requestBodyLength + chunk.length >= MAX_REQUEST_BODY_SIZE) {
           res.statusCode = 413; // Request Entity Too Large
           return;
        }
        chunk.copy(requestBody,requestBodyLength,chunk.length);
        requestBodyLength += chunk.length;
    });
 
    req.on('end',function() {
        if(res.statusCode == 413) {
            // handle 413 error
            return;
        }
 
        requestBody = requestBody.toString('utf8',requestBodyLength);
        // process requestBody as string
    });
});

我是对的,还是已经由http请求类处理了？