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

js:

var array = fs.readFileSync('file.txt', 'utf8').split('\n');

ts:

var array = fs.readFileSync('file.txt', 'utf8').toString().split('\n');

其他回答

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);

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

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
});

我有同样的问题,我已经解决了它与模块逐行

https://www.npmjs.com/package/line-by-line

至少对我来说,无论是在同步模式还是异步模式下,它都很有魅力。

同样,行终止不终止\n的问题可以用选项解决:

{ encoding: 'utf8', skipEmptyLines: false }

行同步处理:

var LineByLineReader = require('line-by-line'),
    lr = new LineByLineReader('big_file.txt');

lr.on('error', function (err) {
    // 'err' contains error object
});

lr.on('line', function (line) {
    // 'line' contains the current line without the trailing newline character.
});

lr.on('end', function () {
    // All lines are read, file is closed now.
}); 

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);
});