我试图读取一个大文件一行在一次。我在Quora上找到了一个关于这个主题的问题,但我错过了一些联系,把整个事情联系在一起。

 var Lazy=require("lazy");
 new Lazy(process.stdin)
     .lines
     .forEach(
          function(line) { 
              console.log(line.toString()); 
          }
 );
 process.stdin.resume();

我想要弄清楚的是如何一次从文件中读取一行,而不是像本例中那样读取STDIN。

我试着:

 fs.open('./VeryBigFile.csv', 'r', '0666', Process);

 function Process(err, fd) {
    if (err) throw err;
    // DO lazy read 
 }

但这并不奏效。我知道在必要时我可以使用PHP之类的东西,但我想弄清楚这个问题。

我不认为其他答案会起作用,因为文件比我运行它的服务器的内存大得多。


当前回答

function createLineReader(fileName){
    var EM = require("events").EventEmitter
    var ev = new EM()
    var stream = require("fs").createReadStream(fileName)
    var remainder = null;
    stream.on("data",function(data){
        if(remainder != null){//append newly received data chunk
            var tmp = new Buffer(remainder.length+data.length)
            remainder.copy(tmp)
            data.copy(tmp,remainder.length)
            data = tmp;
        }
        var start = 0;
        for(var i=0; i<data.length; i++){
            if(data[i] == 10){ //\n new line
                var line = data.slice(start,i)
                ev.emit("line", line)
                start = i+1;
            }
        }
        if(start<data.length){
            remainder = data.slice(start);
        }else{
            remainder = null;
        }
    })

    stream.on("end",function(){
        if(null!=remainder) ev.emit("line",remainder)
    })

    return ev
}


//---------main---------------
fileName = process.argv[2]

lineReader = createLineReader(fileName)
lineReader.on("line",function(line){
    console.log(line.toString())
    //console.log("++++++++++++++++++++")
})

其他回答

我已经看了以上所有的答案,他们都使用第三方库来解决它。它在Node的API中有一个简单的解决方案。如

const fs= require('fs')

let stream = fs.createReadStream('<filename>', { autoClose: true })

stream.on('data', chunk => {
    let row = chunk.toString('ascii')
}))

我对缺乏全面的解决方案感到沮丧,所以我把自己的尝试(git / npm)放在一起。复制粘贴功能列表:

Interactive line processing (callback-based, no loading the entire file into RAM) Optionally, return all lines in an array (detailed or raw mode) Interactively interrupt streaming, or perform map/filter like processing Detect any newline convention (PC/Mac/Linux) Correct eof / last line treatment Correct handling of multi-byte UTF-8 characters Retrieve byte offset and byte length information on per-line basis Random access, using line-based or byte-based offsets Automatically map line-offset information, to speed up random access Zero dependencies Tests

国家卫生研究院?你决定:-)

在进行此类操作时,我们必须问自己两个问题:

执行它需要多少内存? 内存消耗是否随着文件大小的增加而急剧增加?

require('fs'). readfilesync()等解决方案将整个文件加载到内存中。这意味着执行操作所需的内存量将几乎等同于文件大小。对于大于50mbs的数据,我们应该避免使用这种方法

通过在函数调用之后放置以下代码行,我们可以很容易地跟踪函数所使用的内存量:

    const used = process.memoryUsage().heapUsed / 1024 / 1024;
    console.log(
      `The script uses approximately ${Math.round(used * 100) / 100} MB`
    );

现在,从大文件中读取特定行最好的方法是使用node的readline。文档中有一些惊人的例子。

我使用下面的代码读取行后,验证它不是一个目录,它不包括在文件列表不需要检查。

(function () {
  var fs = require('fs');
  var glob = require('glob-fs')();
  var path = require('path');
  var result = 0;
  var exclude = ['LICENSE',
    path.join('e2e', 'util', 'db-ca', 'someother-file'),
    path.join('src', 'favicon.ico')];
  var files = [];
  files = glob.readdirSync('**');

  var allFiles = [];

  var patternString = [
    'trade',
    'order',
    'market',
    'securities'
  ];

  files.map((file) => {
    try {
      if (!fs.lstatSync(file).isDirectory() && exclude.indexOf(file) === -1) {
        fs.readFileSync(file).toString().split(/\r?\n/).forEach(function(line){
          patternString.map((pattern) => {
            if (line.indexOf(pattern) !== -1) {
              console.log(file + ' contain `' + pattern + '` in in line "' + line +'";');
              result = 1;
            }
          });
        });
      }
    } catch (e) {
      console.log('Error:', e.stack);
    }
  });
  process.exit(result);

})();
function createLineReader(fileName){
    var EM = require("events").EventEmitter
    var ev = new EM()
    var stream = require("fs").createReadStream(fileName)
    var remainder = null;
    stream.on("data",function(data){
        if(remainder != null){//append newly received data chunk
            var tmp = new Buffer(remainder.length+data.length)
            remainder.copy(tmp)
            data.copy(tmp,remainder.length)
            data = tmp;
        }
        var start = 0;
        for(var i=0; i<data.length; i++){
            if(data[i] == 10){ //\n new line
                var line = data.slice(start,i)
                ev.emit("line", line)
                start = i+1;
            }
        }
        if(start<data.length){
            remainder = data.slice(start);
        }else{
            remainder = null;
        }
    })

    stream.on("end",function(){
        if(null!=remainder) ev.emit("line",remainder)
    })

    return ev
}


//---------main---------------
fileName = process.argv[2]

lineReader = createLineReader(fileName)
lineReader.on("line",function(line){
    console.log(line.toString())
    //console.log("++++++++++++++++++++")
})