我想把一个非常非常大的文件读入node。js中的JavaScript数组。

所以,如果文件是这样的:

first line
two 
three
...
...

我有一个数组:

['first line','two','three', ... , ... ] 

函数看起来是这样的:

var array = load(filename); 

因此,将其全部作为字符串加载,然后将其拆分的想法是不可接受的。


当前回答

如果你能把最终的数据放入一个数组,那么你不也能把它放入一个字符串中并分割它吗? 在任何情况下,如果你想一次处理一行文件,你也可以尝试这样做:

var fs = require('fs');

function readLines(input, func) {
  var remaining = '';

  input.on('data', function(data) {
    remaining += data;
    var index = remaining.indexOf('\n');
    while (index > -1) {
      var line = remaining.substring(0, index);
      remaining = remaining.substring(index + 1);
      func(line);
      index = remaining.indexOf('\n');
    }
  });

  input.on('end', function() {
    if (remaining.length > 0) {
      func(remaining);
    }
  });
}

function func(data) {
  console.log('Line: ' + data);
}

var input = fs.createReadStream('lines.txt');
readLines(input, func);

编辑:(回应phopkins的评论)我认为(至少在新版本中)substring不复制数据,而是创建一个特殊的SlicedString对象(从v8源代码中快速浏览)。在任何情况下,这里有一个修改,避免了提到的子字符串(在一个文件上测试了几个兆字节的“只工作不玩耍,聪明的孩子会变傻”):

function readLines(input, func) {
  var remaining = '';

  input.on('data', function(data) {
    remaining += data;
    var index = remaining.indexOf('\n');
    var last  = 0;
    while (index > -1) {
      var line = remaining.substring(last, index);
      last = index + 1;
      func(line);
      index = remaining.indexOf('\n', last);
    }

    remaining = remaining.substring(last);
  });

  input.on('end', function() {
    if (remaining.length > 0) {
      func(remaining);
    }
  });
}

其他回答

使用readline(文档)。下面是一个例子,读取一个CSS文件,解析图标并将它们写入json

var results = [];
  var rl = require('readline').createInterface({
    input: require('fs').createReadStream('./assets/stylesheets/_icons.scss')
  });


  // for every new line, if it matches the regex, add it to an array
  // this is ugly regex :)
  rl.on('line', function (line) {
    var re = /\.icon-icon.*:/;
    var match;
    if ((match = re.exec(line)) !== null) {
      results.push(match[0].replace(".",'').replace(":",''));
    }
  });


  // readline emits a close event when the file is read.
  rl.on('close', function(){
    var outputFilename = './icons.json';
    fs.writeFile(outputFilename, JSON.stringify(results, null, 2), function(err) {
        if(err) {
          console.log(err);
        } else {
          console.log("JSON saved to " + outputFilename);
        }
    });
  });

要将一个大文件读入数组,您可以逐行或逐块读取。

一行一行的参考我这里的答案

var fs = require('fs'),
    es = require('event-stream'),

var lines = [];

var s = fs.createReadStream('filepath')
    .pipe(es.split())
    .pipe(es.mapSync(function(line) {
        //pause the readstream
        s.pause();
        lines.push(line);
        s.resume();
    })
    .on('error', function(err) {
        console.log('Error:', err);
    })
    .on('end', function() {
        console.log('Finish reading.');
        console.log(lines);
    })
);

一块一块的参考本文

var offset = 0;
var chunkSize = 2048;
var chunkBuffer = new Buffer(chunkSize);
var fp = fs.openSync('filepath', 'r');
var bytesRead = 0;
while(bytesRead = fs.readSync(fp, chunkBuffer, 0, chunkSize, offset)) {
    offset += bytesRead;
    var str = chunkBuffer.slice(0, bytesRead).toString();
    var arr = str.split('\n');

    if(bytesRead = chunkSize) {
        // the last item of the arr may be not a full line, leave it to the next chunk
        offset -= arr.pop().length;
    }
    lines.push(arr);
}
console.log(lines);

使用Node.js的readline模块。

var fs = require('fs');
var readline = require('readline');

var filename = process.argv[2];
readline.createInterface({
    input: fs.createReadStream(filename),
    terminal: false
}).on('line', function(line) {
   console.log('Line: ' + line);
});

这是@mtomis上面回答的一个变体。

它创建了一个行流。它发出'data'和'end'事件,允许您处理流的结束。

var events = require('events');

var LineStream = function (input) {
    var remaining = '';

    input.on('data', function (data) {
        remaining += data;
        var index = remaining.indexOf('\n');
        var last = 0;
        while (index > -1) {
            var line = remaining.substring(last, index);
            last = index + 1;
            this.emit('data', line);
            index = remaining.indexOf('\n', last);
        }
        remaining = remaining.substring(last);
    }.bind(this));

    input.on('end', function() {
        if (remaining.length > 0) {
            this.emit('data', remaining);
        }
        this.emit('end');
    }.bind(this));
}

LineStream.prototype = new events.EventEmitter;

用它来包装:

var lineInput = new LineStream(input);

lineInput.on('data', function (line) {
    // handle line
});

lineInput.on('end', function() {
    // wrap it up
});

文件。行与我的JFile包

var JFile=require('jfile');

var myF=new JFile("./data.txt");
myF.lines // ["first line","second line"] ....

不要忘记之前:

npm install jfile --save