87

I need to run two commands in series that need to read data from the same stream. After piping a stream into another the buffer is emptied so i can't read data from that stream again so this doesn't work:

var spawn = require('child_process').spawn;
var fs = require('fs');
var request = require('request');

var inputStream = request('http://placehold.it/640x360');
var identify = spawn('identify',['-']);

inputStream.pipe(identify.stdin);

var chunks = [];
identify.stdout.on('data',function(chunk) {
  chunks.push(chunk);
});

identify.stdout.on('end',function() {
  var size = getSize(Buffer.concat(chunks)); //width
  var convert = spawn('convert',['-','-scale',size * 0.5,'png:-']);
  inputStream.pipe(convert.stdin);
  convert.stdout.pipe(fs.createWriteStream('half.png'));
});

function getSize(buffer){
  return parseInt(buffer.toString().split(' ')[2].split('x')[0]);
}

Request complains about this

Error: You cannot pipe after data has been emitted from the response.

and changing the inputStream to fs.createWriteStream yields the same issue of course. I don't want to write into a file but reuse in some way the stream that request produces (or any other for that matter).

Is there a way to reuse a readable stream once it finishes piping? What would be the best way to accomplish something like the above example?

4

7 回答 7

90

您必须通过将其连接到两个流来创建流的副本。您可以使用 PassThrough 流创建一个简单的流，它只是将输入传递到输出。

const spawn = require('child_process').spawn;
const PassThrough = require('stream').PassThrough;

const a = spawn('echo', ['hi user']);
const b = new PassThrough();
const c = new PassThrough();

a.stdout.pipe(b);
a.stdout.pipe(c);

let count = 0;
b.on('data', function (chunk) {
  count += chunk.length;
});
b.on('end', function () {
  console.log(count);
  c.pipe(process.stdout);
});

输出：

8
hi user
于 2013-10-24T09:13:40.970 回答
12

第一个答案仅在流需要大致相同的时间来处理数据时才有效。如果需要更长的时间，则较快的将请求新数据，从而覆盖较慢的仍在使用的数据（我在尝试使用重复流解决此问题后遇到了这个问题）。

以下模式对我来说效果很好。它使用基于 Stream2 流、Streamz 和 Promises 的库通过回调同步异步流。使用第一个答案中熟悉的示例：

spawn = require('child_process').spawn;
pass = require('stream').PassThrough;
streamz = require('streamz').PassThrough;
var Promise = require('bluebird');

a = spawn('echo', ['hi user']);
b = new pass;
c = new pass;   

a.stdout.pipe(streamz(combineStreamOperations)); 

function combineStreamOperations(data, next){
  Promise.join(b, c, function(b, c){ //perform n operations on the same data
  next(); //request more
}

count = 0;
b.on('data', function(chunk) { count += chunk.length; });
b.on('end', function() { console.log(count); c.pipe(process.stdout); });
于 2015-11-23T19:38:12.040 回答
3

你可以使用我创建的这个小 npm 包：

readable-stream-clone

有了这个，您可以根据需要多次重用可读流

于 2020-03-25T04:47:03.213 回答
2

对于一般问题，以下代码可以正常工作

var PassThrough = require('stream').PassThrough
a=PassThrough()
b1=PassThrough()
b2=PassThrough()
a.pipe(b1)
a.pipe(b2)
b1.on('data', function(data) {
  console.log('b1:', data.toString())
})
b2.on('data', function(data) {
  console.log('b2:', data.toString())
})
a.write('text')
于 2015-11-06T09:55:14.390 回答
1

如果您对 PassThrough 流进行异步操作，则此处发布的答案将不起作用。适用于异步操作的解决方案包括缓冲流内容，然后从缓冲的结果创建流。

  1. 要缓冲结果，您可以使用concat-stream

    const Promise = require('bluebird');
const concat = require('concat-stream');
const getBuffer = function(stream){
    return new Promise(function(resolve, reject){
        var gotBuffer = function(buffer){
            resolve(buffer);
        }
        var concatStream = concat(gotBuffer);
        stream.on('error', reject);
        stream.pipe(concatStream);
    });
}

  2. 要从缓冲区创建流，您可以使用：

    const { Readable } = require('stream');
const getBufferStream = function(buffer){
    const stream = new Readable();
    stream.push(buffer);
    stream.push(null);
    return Promise.resolve(stream);
}
于 2019-05-28T19:18:52.873 回答
1

我有一个同时写入两个流的不同解决方案，自然，写入时间将是两次的加法，但我用它来响应下载请求，我想在其中保留下载文件的副本我的服务器（实际上我使用的是 S3 备份，所以我在本地缓存了最常用的文件以避免多个文件传输）

/**
 * A utility class made to write to a file while answering a file download request
 */
class TwoOutputStreams {
  constructor(streamOne, streamTwo) {
    this.streamOne = streamOne
    this.streamTwo = streamTwo
  }

  setHeader(header, value) {
    if (this.streamOne.setHeader)
      this.streamOne.setHeader(header, value)
    if (this.streamTwo.setHeader)
      this.streamTwo.setHeader(header, value)
  }

  write(chunk) {
    this.streamOne.write(chunk)
    this.streamTwo.write(chunk)
  }

  end() {
    this.streamOne.end()
    this.streamTwo.end()
  }
}

然后，您可以将其用作常规 OutputStream

const twoStreamsOut = new TwoOutputStreams(fileOut, responseStream)

并将其传递给您的方法，就好像它是响应或 fileOutputStream

于 2017-11-08T17:50:37.483 回答
0

不同时将管道连接到两个或多个流中会怎样？

例如 ：

var PassThrough = require('stream').PassThrough;
var mybiraryStream = stream.start(); //never ending audio stream
var file1 = fs.createWriteStream('file1.wav',{encoding:'binary'})
var file2 = fs.createWriteStream('file2.wav',{encoding:'binary'})
var mypass = PassThrough
mybinaryStream.pipe(mypass)
mypass.pipe(file1)
setTimeout(function(){
   mypass.pipe(file2);
},2000)

上面的代码没有产生任何错误但是file2是空的

于 2016-11-29T20:14:41.460 回答