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

虽然您可能应该像上面的答案所建议的那样使用readline模块,但readline似乎面向命令行接口,而不是行读取。关于缓冲,它也有点不透明。(任何需要流式行阅读器的人可能都想调整缓冲区大小)。readline模块大约有1000行,而这个,加上统计和测试,是34行。

const EventEmitter = require('events').EventEmitter;
class LineReader extends EventEmitter{
    constructor(f, delim='\n'){
        super();
        this.totalChars = 0;
        this.totalLines = 0;
        this.leftover = '';

        f.on('data', (chunk)=>{
            this.totalChars += chunk.length;
            let lines = chunk.split(delim);
            if (lines.length === 1){
                this.leftover += chunk;
                return;
            }
            lines[0] = this.leftover + lines[0];
            this.leftover = lines[lines.length-1];
            if (this.leftover) lines.pop();
            this.totalLines += lines.length;
            for (let l of lines) this.onLine(l);
        });
        // f.on('error', ()=>{});
        f.on('end', ()=>{console.log('chars', this.totalChars, 'lines', this.totalLines)});
    }
    onLine(l){
        this.emit('line', l);
    }
}
//Command line test
const f = require('fs').createReadStream(process.argv[2], 'utf8');
const delim = process.argv[3];
const lineReader = new LineReader(f, delim);
lineReader.on('line', (line)=> console.log(line));

下面是一个更短的版本,没有统计数据,只有19行:

class LineReader extends require('events').EventEmitter{
    constructor(f, delim='\n'){
        super();
        this.leftover = '';
        f.on('data', (chunk)=>{
            let lines = chunk.split(delim);
            if (lines.length === 1){
                this.leftover += chunk;
                return;
            }
            lines[0] = this.leftover + lines[0];
            this.leftover = lines[lines.length-1];
            if (this.leftover) 
                lines.pop();
            for (let l of lines)
                this.emit('line', l);
        });
    }
}

其他回答

在Node.js v18.11.0中添加了一个逐行读取文件的新函数

filehandle.readLines([选项])

这就是如何将此功能用于想要读取的文本文件

import { open } from 'node:fs/promises';
myFileReader();
async function myFileReader() {
    const file = await open('./TextFileName.txt');
    for await (const line of file.readLines()) {
        console.log(line)
    }
}

为了了解更多read Node.js文档,这里有文件系统readlines()的链接: https://nodejs.org/api/fs.html#filehandlereadlinesoptions

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:-)

var fs = require('fs');

function readfile(name,online,onend,encoding) {
    var bufsize = 1024;
    var buffer = new Buffer(bufsize);
    var bufread = 0;
    var fd = fs.openSync(name,'r');
    var position = 0;
    var eof = false;
    var data = "";
    var lines = 0;

    encoding = encoding || "utf8";

    function readbuf() {
        bufread = fs.readSync(fd,buffer,0,bufsize,position);
        position += bufread;
        eof = bufread ? false : true;
        data += buffer.toString(encoding,0,bufread);
    }

    function getLine() {
        var nl = data.indexOf("\r"), hasnl = nl !== -1;
        if (!hasnl && eof) return fs.closeSync(fd), online(data,++lines), onend(lines); 
        if (!hasnl && !eof) readbuf(), nl = data.indexOf("\r"), hasnl = nl !== -1;
        if (!hasnl) return process.nextTick(getLine);
        var line = data.substr(0,nl);
        data = data.substr(nl+1);
        if (data[0] === "\n") data = data.substr(1);
        online(line,++lines);
        process.nextTick(getLine);
    }
    getLine();
}

我也有同样的问题,想出了上面的解决方案 看起来类似于其他,但是异步的,可以读取大文件非常快

希望这能有所帮助

老话题了,但这个很管用:

var rl = readline.createInterface({
      input : fs.createReadStream('/path/file.txt'),
      output: process.stdout,
      terminal: false
})
rl.on('line',function(line){
     console.log(line) //or parse line
})

简单。不需要外部模块。

在大多数情况下,这应该足够了:

const fs = require("fs")

fs.readFile('./file', 'utf-8', (err, file) => {
  const lines = file.split('\n')

  for (let line of lines)
    console.log(line)
});